Merge commit 'v2.6.29-rc1' into perfcounters/core

Conflicts:
	include/linux/kernel_stat.h

6 files changed, 239 insertions, 116 deletions

diff --git a/init/Kconfig b/init/Kconfig
index c38ae71a5e1..a588cdc274b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -271,59 +271,6 @@ config LOG_BUF_SHIFT
 		     13 =>  8 KB
 		     12 =>  4 KB
 
-config CGROUPS
-	bool "Control Group support"
-	help
-	  This option will let you use process cgroup subsystems
-	  such as Cpusets
-
-	  Say N if unsure.
-
-config CGROUP_DEBUG
-	bool "Example debug cgroup subsystem"
-	depends on CGROUPS
-	default n
-	help
-	  This option enables a simple cgroup subsystem that
-	  exports useful debugging information about the cgroups
-	  framework
-
-	  Say N if unsure
-
-config CGROUP_NS
-        bool "Namespace cgroup subsystem"
-        depends on CGROUPS
-        help
-          Provides a simple namespace cgroup subsystem to
-          provide hierarchical naming of sets of namespaces,
-          for instance virtual servers and checkpoint/restart
-          jobs.
-
-config CGROUP_FREEZER
-        bool "control group freezer subsystem"
-        depends on CGROUPS
-        help
-          Provides a way to freeze and unfreeze all tasks in a
-	  cgroup.
-
-config CGROUP_DEVICE
-	bool "Device controller for cgroups"
-	depends on CGROUPS && EXPERIMENTAL
-	help
-	  Provides a cgroup implementing whitelists for devices which
-	  a process in the cgroup can mknod or open.
-
-config CPUSETS
-	bool "Cpuset support"
-	depends on SMP && CGROUPS
-	help
-	  This option will let you create and manage CPUSETs which
-	  allow dynamically partitioning a system into sets of CPUs and
-	  Memory Nodes and assigning tasks to run only within those sets.
-	  This is primarily useful on large SMP or NUMA systems.
-
-	  Say N if unsure.
-
 #
 # Architectures with an unreliable sched_clock() should select this:
 #
@@ -337,6 +284,8 @@ config GROUP_SCHED
 	help
 	  This feature lets CPU scheduler recognize task groups and control CPU
 	  bandwidth allocation to such task groups.
+	  In order to create a group from arbitrary set of processes, use
+	  CONFIG_CGROUPS. (See Control Group support.)
 
 config FAIR_GROUP_SCHED
 	bool "Group scheduling for SCHED_OTHER"
@@ -379,6 +328,66 @@ config CGROUP_SCHED
 
 endchoice
 
+menu "Control Group support"
+config CGROUPS
+	bool "Control Group support"
+	help
+	  This option add support for grouping sets of processes together, for
+	  use with process control subsystems such as Cpusets, CFS, memory
+	  controls or device isolation.
+	  See
+		- Documentation/cpusets.txt	(Cpusets)
+		- Documentation/scheduler/sched-design-CFS.txt	(CFS)
+		- Documentation/cgroups/ (features for grouping, isolation)
+		- Documentation/controllers/ (features for resource control)
+
+	  Say N if unsure.
+
+config CGROUP_DEBUG
+	bool "Example debug cgroup subsystem"
+	depends on CGROUPS
+	default n
+	help
+	  This option enables a simple cgroup subsystem that
+	  exports useful debugging information about the cgroups
+	  framework
+
+	  Say N if unsure
+
+config CGROUP_NS
+        bool "Namespace cgroup subsystem"
+        depends on CGROUPS
+        help
+          Provides a simple namespace cgroup subsystem to
+          provide hierarchical naming of sets of namespaces,
+          for instance virtual servers and checkpoint/restart
+          jobs.
+
+config CGROUP_FREEZER
+        bool "control group freezer subsystem"
+        depends on CGROUPS
+        help
+          Provides a way to freeze and unfreeze all tasks in a
+	  cgroup.
+
+config CGROUP_DEVICE
+	bool "Device controller for cgroups"
+	depends on CGROUPS && EXPERIMENTAL
+	help
+	  Provides a cgroup implementing whitelists for devices which
+	  a process in the cgroup can mknod or open.
+
+config CPUSETS
+	bool "Cpuset support"
+	depends on SMP && CGROUPS
+	help
+	  This option will let you create and manage CPUSETs which
+	  allow dynamically partitioning a system into sets of CPUs and
+	  Memory Nodes and assigning tasks to run only within those sets.
+	  This is primarily useful on large SMP or NUMA systems.
+
+	  Say N if unsure.
+
 config CGROUP_CPUACCT
 	bool "Simple CPU accounting cgroup subsystem"
 	depends on CGROUPS
@@ -393,9 +402,6 @@ config RESOURCE_COUNTERS
           infrastructure that works with cgroups
 	depends on CGROUPS
 
-config MM_OWNER
-	bool
-
 config CGROUP_MEM_RES_CTLR
 	bool "Memory Resource Controller for Control Groups"
 	depends on CGROUPS && RESOURCE_COUNTERS
@@ -414,36 +420,68 @@ config CGROUP_MEM_RES_CTLR
 	  sure you need the memory resource controller. Even when you enable
 	  this, you can set "cgroup_disable=memory" at your boot option to
 	  disable memory resource controller and you can avoid overheads.
-	  (and lose benefits of memory resource contoller)
+	  (and lose benefits of memory resource controller)
 
 	  This config option also selects MM_OWNER config option, which
 	  could in turn add some fork/exit overhead.
 
+config MM_OWNER
+	bool
+
+config CGROUP_MEM_RES_CTLR_SWAP
+	bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)"
+	depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL
+	help
+	  Add swap management feature to memory resource controller. When you
+	  enable this, you can limit mem+swap usage per cgroup. In other words,
+	  when you disable this, memory resource controller has no cares to
+	  usage of swap...a process can exhaust all of the swap. This extension
+	  is useful when you want to avoid exhaustion swap but this itself
+	  adds more overheads and consumes memory for remembering information.
+	  Especially if you use 32bit system or small memory system, please
+	  be careful about enabling this. When memory resource controller
+	  is disabled by boot option, this will be automatically disabled and
+	  there will be no overhead from this. Even when you set this config=y,
+	  if boot option "noswapaccount" is set, swap will not be accounted.
+
+
+endmenu
+
 config SYSFS_DEPRECATED
 	bool
 
 config SYSFS_DEPRECATED_V2
-	bool "Create deprecated sysfs files"
+	bool "Create deprecated sysfs layout for older userspace tools"
 	depends on SYSFS
 	default y
 	select SYSFS_DEPRECATED
 	help
-	  This option creates deprecated symlinks such as the
-	  "device"-link, the <subsystem>:<name>-link, and the
-	  "bus"-link. It may also add deprecated key in the
-	  uevent environment.
-	  None of these features or values should be used today, as
-	  they export driver core implementation details to userspace
-	  or export properties which can't be kept stable across kernel
-	  releases.
-
-	  If enabled, this option will also move any device structures
-	  that belong to a class, back into the /sys/class hierarchy, in
-	  order to support older versions of udev and some userspace
-	  programs.
-
-	  If you are using a distro with the most recent userspace
-	  packages, it should be safe to say N here.
+	  This option switches the layout of sysfs to the deprecated
+	  version.
+
+	  The current sysfs layout features a unified device tree at
+	  /sys/devices/, which is able to express a hierarchy between
+	  class devices. If the deprecated option is set to Y, the
+	  unified device tree is split into a bus device tree at
+	  /sys/devices/ and several individual class device trees at
+	  /sys/class/. The class and bus devices will be connected by
+	  "<subsystem>:<name>" and the "device" links. The "block"
+	  class devices, will not show up in /sys/class/block/. Some
+	  subsystems will suppress the creation of some devices which
+	  depend on the unified device tree.
+
+	  This option is not a pure compatibility option that can
+	  be safely enabled on newer distributions. It will change the
+	  layout of sysfs to the non-extensible deprecated version,
+	  and disable some features, which can not be exported without
+	  confusing older userspace tools. Since 2007/2008 all major
+	  distributions do not enable this option, and ship no tools which
+	  depend on the deprecated layout or this option.
+
+	  If you are using a new kernel on an older distribution, or use
+	  older userspace tools, you might need to say Y here. Do not say Y,
+	  if the original kernel, that came with your distribution, has
+	  this option set to N.
 
 config PROC_PID_CPUSET
 	bool "Include legacy /proc/<pid>/cpuset file"
@@ -868,10 +906,6 @@ config RT_MUTEXES
 	boolean
 	select PLIST
 
-config TINY_SHMEM
-	default !SHMEM
-	bool
-
 config BASE_SMALL
 	int
 	default 0 if BASE_FULL
@@ -946,14 +980,17 @@ config MODULE_SRCVERSION_ALL
 	  the version).  With this option, such a "srcversion" field
 	  will be created for all modules.  If unsure, say N.
 
-config KMOD
-	def_bool y
-	help
-	  This is being removed soon.  These days, CONFIG_MODULES
-	  implies CONFIG_KMOD, so use that instead.
-
 endif # MODULES
 
+config INIT_ALL_POSSIBLE
+	bool
+	help
+	  Back when each arch used to define their own cpu_online_map and
+	  cpu_possible_map, some of them chose to initialize cpu_possible_map
+	  with all 1s, and others with all 0s.  When they were centralised,
+	  it was better to provide this option than to break all the archs
+	  and have several arch maintainers persuing me down dark alleys.
+
 config STOP_MACHINE
 	bool
 	default y
@@ -966,10 +1003,90 @@ source "block/Kconfig"
 config PREEMPT_NOTIFIERS
 	bool
 
+choice
+	prompt "RCU Implementation"
+	default CLASSIC_RCU
+
 config CLASSIC_RCU
-	def_bool !PREEMPT_RCU
+	bool "Classic RCU"
 	help
 	  This option selects the classic RCU implementation that is
 	  designed for best read-side performance on non-realtime
-	  systems.  Classic RCU is the default.  Note that the
-	  PREEMPT_RCU symbol is used to select/deselect this option.
+	  systems.
+
+	  Select this option if you are unsure.
+
+config TREE_RCU
+	bool "Tree-based hierarchical RCU"
+	help
+	  This option selects the RCU implementation that is
+	  designed for very large SMP system with hundreds or
+	  thousands of CPUs.
+
+config PREEMPT_RCU
+	bool "Preemptible RCU"
+	depends on PREEMPT
+	help
+	  This option reduces the latency of the kernel by making certain
+	  RCU sections preemptible. Normally RCU code is non-preemptible, if
+	  this option is selected then read-only RCU sections become
+	  preemptible. This helps latency, but may expose bugs due to
+	  now-naive assumptions about each RCU read-side critical section
+	  remaining on a given CPU through its execution.
+
+endchoice
+
+config RCU_TRACE
+	bool "Enable tracing for RCU"
+	depends on TREE_RCU || PREEMPT_RCU
+	help
+	  This option provides tracing in RCU which presents stats
+	  in debugfs for debugging RCU implementation.
+
+	  Say Y here if you want to enable RCU tracing
+	  Say N if you are unsure.
+
+config RCU_FANOUT
+	int "Tree-based hierarchical RCU fanout value"
+	range 2 64 if 64BIT
+	range 2 32 if !64BIT
+	depends on TREE_RCU
+	default 64 if 64BIT
+	default 32 if !64BIT
+	help
+	  This option controls the fanout of hierarchical implementations
+	  of RCU, allowing RCU to work efficiently on machines with
+	  large numbers of CPUs.  This value must be at least the cube
+	  root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
+	  systems and up to 262,144 for 64-bit systems.
+
+	  Select a specific number if testing RCU itself.
+	  Take the default if unsure.
+
+config RCU_FANOUT_EXACT
+	bool "Disable tree-based hierarchical RCU auto-balancing"
+	depends on TREE_RCU
+	default n
+	help
+	  This option forces use of the exact RCU_FANOUT value specified,
+	  regardless of imbalances in the hierarchy.  This is useful for
+	  testing RCU itself, and might one day be useful on systems with
+	  strong NUMA behavior.
+
+	  Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
+
+	  Say N if unsure.
+
+config TREE_RCU_TRACE
+	def_bool RCU_TRACE && TREE_RCU
+	select DEBUG_FS
+	help
+	  This option provides tracing for the TREE_RCU implementation,
+	  permitting Makefile to trivially select kernel/rcutree_trace.c.
+
+config PREEMPT_RCU_TRACE
+	def_bool RCU_TRACE && PREEMPT_RCU
+	select DEBUG_FS
+	help
+	  This option provides tracing for the PREEMPT_RCU implementation,
+	  permitting Makefile to trivially select kernel/rcupreempt_trace.c.
diff --git a/init/do_mounts.c b/init/do_mounts.c
index d055b1914c3..708105e163d 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/initrd.h>
+#include <linux/async.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
@@ -220,10 +221,10 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data)
 
 	sys_chdir("/root");
 	ROOT_DEV = current->fs->pwd.mnt->mnt_sb->s_dev;
-	printk("VFS: Mounted root (%s filesystem)%s.\n",
+	printk("VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
 	       current->fs->pwd.mnt->mnt_sb->s_type->name,
 	       current->fs->pwd.mnt->mnt_sb->s_flags & MS_RDONLY ?
-	       " readonly" : "");
+	       " readonly" : "", MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
 	return 0;
 }
 
@@ -372,6 +373,7 @@ void __init prepare_namespace(void)
 	/* wait for the known devices to complete their probing */
 	while (driver_probe_done() != 0)
 		msleep(100);
+	async_synchronize_full();
 
 	md_run_setup();
 
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index d6da5cdd3c3..ff95e319288 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -271,7 +271,7 @@ static int __init raid_setup(char *str)
 __setup("raid=", raid_setup);
 __setup("md=", md_setup);
 
-static void autodetect_raid(void)
+static void __init autodetect_raid(void)
 {
 	int fd;
 
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index a7c748fa977..0f0f0cf3ba9 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -9,6 +9,7 @@
 #include <linux/string.h>
 
 #include "do_mounts.h"
+#include "../fs/squashfs/squashfs_fs.h"
 
 int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */
 
@@ -41,6 +42,7 @@ static int __init crd_load(int in_fd, int out_fd);
  * 	ext2
  *	romfs
  *	cramfs
+ *	squashfs
  * 	gzip
  */
 static int __init 
@@ -51,6 +53,7 @@ identify_ramdisk_image(int fd, int start_block)
 	struct ext2_super_block *ext2sb;
 	struct romfs_super_block *romfsb;
 	struct cramfs_super *cramfsb;
+	struct squashfs_super_block *squashfsb;
 	int nblocks = -1;
 	unsigned char *buf;
 
@@ -62,6 +65,7 @@ identify_ramdisk_image(int fd, int start_block)
 	ext2sb = (struct ext2_super_block *) buf;
 	romfsb = (struct romfs_super_block *) buf;
 	cramfsb = (struct cramfs_super *) buf;
+	squashfsb = (struct squashfs_super_block *) buf;
 	memset(buf, 0xe5, size);
 
 	/*
@@ -99,6 +103,16 @@ identify_ramdisk_image(int fd, int start_block)
 		goto done;
 	}
 
+	/* squashfs is at block zero too */
+	if (le32_to_cpu(squashfsb->s_magic) == SQUASHFS_MAGIC) {
+		printk(KERN_NOTICE
+		       "RAMDISK: squashfs filesystem found at block %d\n",
+		       start_block);
+		nblocks = (le64_to_cpu(squashfsb->bytes_used) + BLOCK_SIZE - 1)
+			 >> BLOCK_SIZE_BITS;
+		goto done;
+	}
+
 	/*
 	 * Read block 1 to test for minix and ext2 superblock
 	 */
diff --git a/init/initramfs.c b/init/initramfs.c
index 4f5ba75aaa7..d9c941c0c3c 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -317,6 +317,7 @@ static int __init do_name(void)
 			if (wfd >= 0) {
 				sys_fchown(wfd, uid, gid);
 				sys_fchmod(wfd, mode);
+				sys_ftruncate(wfd, body_len);
 				vcollected = kstrdup(collected, GFP_KERNEL);
 				state = CopyFile;
 			}
diff --git a/init/main.c b/init/main.c
index 17e9757bfde..844209453c0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -50,7 +50,6 @@
 #include <linux/rmap.h>
 #include <linux/mempolicy.h>
 #include <linux/key.h>
-#include <linux/unwind.h>
 #include <linux/buffer_head.h>
 #include <linux/page_cgroup.h>
 #include <linux/debug_locks.h>
@@ -63,6 +62,7 @@
 #include <linux/signal.h>
 #include <linux/idr.h>
 #include <linux/ftrace.h>
+#include <linux/async.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -75,15 +75,6 @@
 #include <asm/smp.h>
 #endif
 
-/*
- * This is one of the first .c files built. Error out early if we have compiler
- * trouble.
- */
-
-#if __GNUC__ == 4 && __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ == 0
-#warning gcc-4.1.0 is known to miscompile the kernel.  A different compiler version is recommended.
-#endif
-
 static int kernel_init(void *);
 
 extern void init_IRQ(void);
@@ -117,7 +108,7 @@ EXPORT_SYMBOL(system_state);
 
 extern void time_init(void);
 /* Default late time init is NULL. archs can override this later. */
-void (*late_time_init)(void);
+void (*__initdata late_time_init)(void);
 extern void softirq_init(void);
 
 /* Untouched command line saved by arch-specific code. */
@@ -380,12 +371,7 @@ EXPORT_SYMBOL(nr_cpu_ids);
 /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
 static void __init setup_nr_cpu_ids(void)
 {
-	int cpu, highest_cpu = 0;
-
-	for_each_possible_cpu(cpu)
-		highest_cpu = cpu;
-
-	nr_cpu_ids = highest_cpu + 1;
+	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
 }
 
 #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
@@ -461,7 +447,7 @@ static void __init setup_command_line(char *command_line)
  * gcc-3.4 accidentally inlines this function, so use noinline.
  */
 
-static void noinline __init_refok rest_init(void)
+static noinline void __init_refok rest_init(void)
 	__releases(kernel_lock)
 {
 	int pid;
@@ -527,9 +513,9 @@ static void __init boot_cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
-	cpu_set(cpu, cpu_online_map);
-	cpu_set(cpu, cpu_present_map);
-	cpu_set(cpu, cpu_possible_map);
+	set_cpu_online(cpu, true);
+	set_cpu_present(cpu, true);
+	set_cpu_possible(cpu, true);
 }
 
 void __init __weak smp_setup_processor_id(void)
@@ -551,7 +537,6 @@ asmlinkage void __init start_kernel(void)
 	 * Need to run as early as possible, to initialize the
 	 * lockdep hash:
 	 */
-	unwind_init();
 	lockdep_init();
 	debug_objects_early_init();
 	cgroup_init_early();
@@ -573,7 +558,6 @@ asmlinkage void __init start_kernel(void)
 	setup_arch(&command_line);
 	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
-	unwind_setup();
 	setup_per_cpu_areas();
 	setup_nr_cpu_ids();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
@@ -604,6 +588,8 @@ asmlinkage void __init start_kernel(void)
 	sort_main_extable();
 	trap_init();
 	rcu_init();
+	/* init some links before init_ISA_irqs() */
+	early_irq_init();
 	init_IRQ();
 	pidhash_init();
 	init_timers();
@@ -614,7 +600,8 @@ asmlinkage void __init start_kernel(void)
 	sched_clock_init();
 	profile_init();
 	if (!irqs_disabled())
-		printk("start_kernel(): bug: interrupts were enabled early\n");
+		printk(KERN_CRIT "start_kernel(): bug: interrupts were "
+				 "enabled early\n");
 	early_boot_irqs_on();
 	local_irq_enable();
 
@@ -699,7 +686,7 @@ asmlinkage void __init start_kernel(void)
 	rest_init();
 }
 
-static int initcall_debug;
+int initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
 int do_one_initcall(initcall_t fn)
@@ -798,8 +785,10 @@ static void run_init_process(char *init_filename)
 /* This is a non __init function. Force it to be noinline otherwise gcc
  * makes it inline to init() and it becomes part of init.text section
  */
-static int noinline init_post(void)
+static noinline int init_post(void)
 {
+	/* need to finish all async __init code before freeing the memory */
+	async_synchronize_full();
 	free_initmem();
 	unlock_kernel();
 	mark_rodata_ro();