Merge drm/drm-next into drm-misc-next-fixes

Alex needs v5.6 into drm-misc-next-fixes to merge a fix for a regression in
the scatterlist processing in PRIME.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

29 files changed, 729 insertions, 722 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 7d9e63e20ded..724024a2243a 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1446,18 +1446,31 @@ static const struct adreno_gpu_funcs funcs = {
 static void check_speed_bin(struct device *dev)
 {
 	struct nvmem_cell *cell;
-	u32 bin, val;
+	u32 val;
+
+	/*
+	 * If the OPP table specifies a opp-supported-hw property then we have
+	 * to set something with dev_pm_opp_set_supported_hw() or the table
+	 * doesn't get populated so pick an arbitrary value that should
+	 * ensure the default frequencies are selected but not conflict with any
+	 * actual bins
+	 */
+	val = 0x80;
 
 	cell = nvmem_cell_get(dev, "speed_bin");
 
-	/* If a nvmem cell isn't defined, nothing to do */
-	if (IS_ERR(cell))
-		return;
+	if (!IS_ERR(cell)) {
+		void *buf = nvmem_cell_read(cell, NULL);
+
+		if (!IS_ERR(buf)) {
+			u8 bin = *((u8 *) buf);
 
-	bin = *((u32 *) nvmem_cell_read(cell, NULL));
-	nvmem_cell_put(cell);
+			val = (1 << bin);
+			kfree(buf);
+		}
 
-	val = (1 << bin);
+		nvmem_cell_put(cell);
+	}
 
 	dev_pm_opp_set_supported_hw(dev, &val, 1);
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 983afeaee737..c4e71abbdd53 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interconnect.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
@@ -796,12 +797,41 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu)
 	return true;
 }
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if (!a6xx_has_gbif(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/* The GBIF halt needs to be explicitly cleared */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 /* Gracefully try to shut down the GMU and by extension the GPU */
 static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 {
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
-	struct msm_gpu *gpu = &adreno_gpu->base;
 	u32 val;
 
 	/*
@@ -819,11 +849,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 			return;
 		}
 
-		/* Clear the VBIF pipe before shutting down */
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf)
-			== 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+		a6xx_bus_clear_pending_transactions(adreno_gpu);
 
 		/* tell the GMU we want to slumber */
 		a6xx_gmu_notify_slumber(gmu);
@@ -895,21 +921,10 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 
 static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo)
 {
-	int count, i;
-	u64 iova;
-
 	if (IS_ERR_OR_NULL(bo))
 		return;
 
-	count = bo->size >> PAGE_SHIFT;
-	iova = bo->iova;
-
-	for (i = 0; i < count; i++, iova += PAGE_SIZE) {
-		iommu_unmap(gmu->domain, iova, PAGE_SIZE);
-		__free_pages(bo->pages[i], 0);
-	}
-
-	kfree(bo->pages);
+	dma_free_wc(gmu->dev, bo->size, bo->virt, bo->iova);
 	kfree(bo);
 }
 
@@ -917,7 +932,6 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu,
 		size_t size)
 {
 	struct a6xx_gmu_bo *bo;
-	int ret, count, i;
 
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
 	if (!bo)
@@ -925,86 +939,14 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu,
 
 	bo->size = PAGE_ALIGN(size);
 
-	count = bo->size >> PAGE_SHIFT;
+	bo->virt = dma_alloc_wc(gmu->dev, bo->size, &bo->iova, GFP_KERNEL);
 
-	bo->pages = kcalloc(count, sizeof(struct page *), GFP_KERNEL);
-	if (!bo->pages) {
+	if (!bo->virt) {
 		kfree(bo);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	for (i = 0; i < count; i++) {
-		bo->pages[i] = alloc_page(GFP_KERNEL);
-		if (!bo->pages[i])
-			goto err;
-	}
-
-	bo->iova = gmu->uncached_iova_base;
-
-	for (i = 0; i < count; i++) {
-		ret = iommu_map(gmu->domain,
-			bo->iova + (PAGE_SIZE * i),
-			page_to_phys(bo->pages[i]), PAGE_SIZE,
-			IOMMU_READ | IOMMU_WRITE);
-
-		if (ret) {
-			DRM_DEV_ERROR(gmu->dev, "Unable to map GMU buffer object\n");
-
-			for (i = i - 1 ; i >= 0; i--)
-				iommu_unmap(gmu->domain,
-					bo->iova + (PAGE_SIZE * i),
-					PAGE_SIZE);
-
-			goto err;
-		}
-	}
-
-	bo->virt = vmap(bo->pages, count, VM_IOREMAP,
-		pgprot_writecombine(PAGE_KERNEL));
-	if (!bo->virt)
-		goto err;
-
-	/* Align future IOVA addresses on 1MB boundaries */
-	gmu->uncached_iova_base += ALIGN(size, SZ_1M);
-
 	return bo;
-
-err:
-	for (i = 0; i < count; i++) {
-		if (bo->pages[i])
-			__free_pages(bo->pages[i], 0);
-	}
-
-	kfree(bo->pages);
-	kfree(bo);
-
-	return ERR_PTR(-ENOMEM);
-}
-
-static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
-{
-	int ret;
-
-	/*
-	 * The GMU address space is hardcoded to treat the range
-	 * 0x60000000 - 0x80000000 as un-cached memory. All buffers shared
-	 * between the GMU and the CPU will live in this space
-	 */
-	gmu->uncached_iova_base = 0x60000000;
-
-
-	gmu->domain = iommu_domain_alloc(&platform_bus_type);
-	if (!gmu->domain)
-		return -ENODEV;
-
-	ret = iommu_attach_device(gmu->domain, gmu->dev);
-
-	if (ret) {
-		iommu_domain_free(gmu->domain);
-		gmu->domain = NULL;
-	}
-
-	return ret;
 }
 
 /* Return the 'arc-level' for the given frequency */
@@ -1264,10 +1206,6 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 
 	a6xx_gmu_memory_free(gmu, gmu->hfi);
 
-	iommu_detach_device(gmu->domain, gmu->dev);
-
-	iommu_domain_free(gmu->domain);
-
 	free_irq(gmu->gmu_irq, gmu);
 	free_irq(gmu->hfi_irq, gmu);
 
@@ -1288,7 +1226,15 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 
 	gmu->dev = &pdev->dev;
 
-	of_dma_configure(gmu->dev, node, true);
+	/* Pass force_dma false to require the DT to set the dma region */
+	ret = of_dma_configure(gmu->dev, node, false);
+	if (ret)
+		return ret;
+
+	/* Set the mask after the of_dma_configure() */
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(31));
+	if (ret)
+		return ret;
 
 	/* Fow now, don't do anything fancy until we get our feet under us */
 	gmu->idle_level = GMU_IDLE_STATE_ACTIVE;
@@ -1300,11 +1246,6 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	if (ret)
 		goto err_put_device;
 
-	/* Set up the IOMMU context bank */
-	ret = a6xx_gmu_memory_probe(gmu);
-	if (ret)
-		goto err_put_device;
-
 	/* Allocate memory for for the HFI queues */
 	gmu->hfi = a6xx_gmu_memory_alloc(gmu, SZ_16K);
 	if (IS_ERR(gmu->hfi))
@@ -1350,11 +1291,6 @@ err_mmio:
 err_memory:
 	a6xx_gmu_memory_free(gmu, gmu->hfi);
 
-	if (gmu->domain) {
-		iommu_detach_device(gmu->domain, gmu->dev);
-
-		iommu_domain_free(gmu->domain);
-	}
 	ret = -ENODEV;
 
 err_put_device:
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 2af91ed7ed0c..4af65a36d5ca 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -12,8 +12,7 @@
 struct a6xx_gmu_bo {
 	void *virt;
 	size_t size;
-	u64 iova;
-	struct page **pages;
+	dma_addr_t iova;
 };
 
 /*
@@ -49,9 +48,6 @@ struct a6xx_gmu {
 	int hfi_irq;
 	int gmu_irq;
 
-	struct iommu_domain *domain;
-	u64 uncached_iova_base;
-
 	struct device *gxpd;
 
 	int idle_level;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index daf07800cde0..68af24150de5 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -378,18 +378,6 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
-	/*
-	 * During a previous slumber, GBIF halt is asserted to ensure
-	 * no further transaction can go through GPU before GPU
-	 * headswitch is turned off.
-	 *
-	 * This halt is deasserted once headswitch goes off but
-	 * incase headswitch doesn't goes off clear GBIF halt
-	 * here to ensure GPU wake-up doesn't fail because of
-	 * halted GPU transactions.
-	 */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
@@ -470,10 +458,12 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Select CP0 to always count cycles */
 	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
 
-	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+	if (adreno_is_a630(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+	}
 
 	/* Enable fault detection */
 	gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL,
@@ -748,39 +738,6 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
-#define GBIF_CLIENT_HALT_MASK             BIT(0)
-#define GBIF_ARB_HALT_MASK                BIT(1)
-
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
-{
-	struct msm_gpu *gpu = &adreno_gpu->base;
-
-	if(!a6xx_has_gbif(adreno_gpu)){
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
-								0xf) == 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
-
-		return;
-	}
-
-	/* Halt new client requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
-	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
-
-	/* Halt all AXI requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
-	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
-
-	/*
-	 * GMU needs DDR access in slumber path. Deassert GBIF halt now
-	 * to allow for GMU to access system memory.
-	 */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-}
-
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -805,16 +762,6 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
-	/*
-	 * Make sure the GMU is idle before continuing (because some transitions
-	 * may use VBIF
-	 */
-	a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
-
-	/* Clear the VBIF pipe before shutting down */
-	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
-	a6xx_bus_clear_pending_transactions(adreno_gpu);
-
 	return a6xx_gmu_stop(a6xx_gpu);
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index e67c20c415af..24c974c293e5 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -379,7 +379,7 @@ static const struct a6xx_indexed_registers {
 };
 
 static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = {
-	"CP_MEMPOOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+	"CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
 		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060,
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index eda11abc5f01..e450e0b97211 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -7,6 +7,7 @@
 
 #include "a6xx_gmu.h"
 #include "a6xx_gmu.xml.h"
+#include "a6xx_gpu.h"
 
 #define HFI_MSG_ID(val) [val] = #val
 
@@ -216,48 +217,82 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu)
 		NULL, 0);
 }
 
-static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
-	struct a6xx_hfi_msg_bw_table msg = { 0 };
+	/* Send a single "off" entry since the 618 GMU doesn't do bus scaling */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x01;
+
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5003c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
 
 	/*
-	 * The sdm845 GMU doesn't do bus frequency scaling on its own but it
-	 * does need at least one entry in the list because it might be accessed
-	 * when the GMU is shutting down. Send a single "off" entry.
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
 	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x5007c;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 
-	msg.bw_level_num = 1;
+static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
+	msg->bw_level_num = 1;
 
-	msg.ddr_cmds_num = 3;
-	msg.ddr_wait_bitmask = 0x07;
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x07;
 
-	msg.ddr_cmds_addrs[0] = 0x50000;
-	msg.ddr_cmds_addrs[1] = 0x5005c;
-	msg.ddr_cmds_addrs[2] = 0x5000c;
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5005c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
 
-	msg.ddr_cmds_data[0][0] =  0x40000000;
-	msg.ddr_cmds_data[0][1] =  0x40000000;
-	msg.ddr_cmds_data[0][2] =  0x40000000;
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
 
 	/*
 	 * These are the CX (CNOC) votes.  This is used but the values for the
 	 * sdm845 GMU are known and fixed so we can hard code them.
 	 */
 
-	msg.cnoc_cmds_num = 3;
-	msg.cnoc_wait_bitmask = 0x05;
+	msg->cnoc_cmds_num = 3;
+	msg->cnoc_wait_bitmask = 0x05;
 
-	msg.cnoc_cmds_addrs[0] = 0x50034;
-	msg.cnoc_cmds_addrs[1] = 0x5007c;
-	msg.cnoc_cmds_addrs[2] = 0x5004c;
+	msg->cnoc_cmds_addrs[0] = 0x50034;
+	msg->cnoc_cmds_addrs[1] = 0x5007c;
+	msg->cnoc_cmds_addrs[2] = 0x5004c;
 
-	msg.cnoc_cmds_data[0][0] =  0x40000000;
-	msg.cnoc_cmds_data[0][1] =  0x00000000;
-	msg.cnoc_cmds_data[0][2] =  0x40000000;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[0][1] =  0x00000000;
+	msg->cnoc_cmds_data[0][2] =  0x40000000;
+
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+	msg->cnoc_cmds_data[1][1] =  0x20000001;
+	msg->cnoc_cmds_data[1][2] =  0x60000001;
+}
+
+
+static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+{
+	struct a6xx_hfi_msg_bw_table msg = { 0 };
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 
-	msg.cnoc_cmds_data[1][0] =  0x60000001;
-	msg.cnoc_cmds_data[1][1] =  0x20000001;
-	msg.cnoc_cmds_data[1][2] =  0x60000001;
+	if (adreno_is_a618(adreno_gpu))
+		a618_build_bw_table(&msg);
+	else
+		a6xx_build_bw_table(&msg);
 
 	return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg),
 		NULL, 0);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 7fd29829b2fa..1d5c43c22269 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -673,7 +673,7 @@ static char *adreno_gpu_ascii85_encode(u32 *src, size_t len)
 		return NULL;
 
 	for (i = 0; i < l; i++)
-		buf_itr += snprintf(buf + buf_itr, buffer_size - buf_itr, "%s",
+		buf_itr += scnprintf(buf + buf_itr, buffer_size - buf_itr, "%s",
 				ascii85_encode(src[i], out));
 
 	return buf;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 58d3400668f5..a1b79ee2bd9d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -164,7 +164,6 @@ enum dpu_enc_rc_states {
  *				clks and resources after IDLE_TIMEOUT time.
  * @vsync_event_work:		worker to handle vsync event for autorefresh
  * @topology:                   topology of the display
- * @mode_set_complete:          flag to indicate modeset completion
  * @idle_timeout:		idle timeout duration in milliseconds
  */
 struct dpu_encoder_virt {
@@ -202,7 +201,6 @@ struct dpu_encoder_virt {
 	struct delayed_work delayed_off_work;
 	struct kthread_work vsync_event_work;
 	struct msm_display_topology topology;
-	bool mode_set_complete;
 
 	u32 idle_timeout;
 };
@@ -461,7 +459,7 @@ void dpu_encoder_helper_split_config(
 	struct msm_display_info *disp_info;
 
 	if (!phys_enc->hw_mdptop || !phys_enc->parent) {
-		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != NULL);
 		return;
 	}
 
@@ -562,12 +560,13 @@ static int dpu_encoder_virt_atomic_check(
 	const struct drm_display_mode *mode;
 	struct drm_display_mode *adj_mode;
 	struct msm_display_topology topology;
+	struct dpu_global_state *global_state;
 	int i = 0;
 	int ret = 0;
 
 	if (!drm_enc || !crtc_state || !conn_state) {
 		DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n",
-				drm_enc != 0, crtc_state != 0, conn_state != 0);
+				drm_enc != NULL, crtc_state != NULL, conn_state != NULL);
 		return -EINVAL;
 	}
 
@@ -578,6 +577,7 @@ static int dpu_encoder_virt_atomic_check(
 	dpu_kms = to_dpu_kms(priv->kms);
 	mode = &crtc_state->mode;
 	adj_mode = &crtc_state->adjusted_mode;
+	global_state = dpu_kms_get_existing_global_state(dpu_kms);
 	trace_dpu_enc_atomic_check(DRMID(drm_enc));
 
 	/*
@@ -609,17 +609,15 @@ static int dpu_encoder_virt_atomic_check(
 
 	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
 
-	/* Reserve dynamic resources now. Indicating AtomicTest phase */
+	/* Reserve dynamic resources now. */
 	if (!ret) {
 		/*
 		 * Avoid reserving resources when mode set is pending. Topology
 		 * info may not be available to complete reservation.
 		 */
-		if (drm_atomic_crtc_needs_modeset(crtc_state)
-				&& dpu_enc->mode_set_complete) {
-			ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, crtc_state,
-					     topology, true);
-			dpu_enc->mode_set_complete = false;
+		if (drm_atomic_crtc_needs_modeset(crtc_state)) {
+			ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
+					drm_enc, crtc_state, topology);
 		}
 	}
 
@@ -956,12 +954,13 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
 	struct drm_connector *conn = NULL, *conn_iter;
 	struct drm_crtc *drm_crtc;
 	struct dpu_crtc_state *cstate;
-	struct dpu_rm_hw_iter hw_iter;
+	struct dpu_global_state *global_state;
 	struct msm_display_topology topology;
-	struct dpu_hw_ctl *hw_ctl[MAX_CHANNELS_PER_ENC] = { NULL };
-	struct dpu_hw_mixer *hw_lm[MAX_CHANNELS_PER_ENC] = { NULL };
-	int num_lm = 0, num_ctl = 0;
-	int i, j, ret;
+	struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
+	int num_lm, num_ctl, num_pp;
+	int i, j;
 
 	if (!drm_enc) {
 		DPU_ERROR("invalid encoder\n");
@@ -975,6 +974,12 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
 	dpu_kms = to_dpu_kms(priv->kms);
 	connector_list = &dpu_kms->dev->mode_config.connector_list;
 
+	global_state = dpu_kms_get_existing_global_state(dpu_kms);
+	if (IS_ERR_OR_NULL(global_state)) {
+		DPU_ERROR("Failed to get global state");
+		return;
+	}
+
 	trace_dpu_enc_mode_set(DRMID(drm_enc));
 
 	list_for_each_entry(conn_iter, connector_list, head)
@@ -995,77 +1000,57 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
 
 	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
 
-	/* Reserve dynamic resources now. Indicating non-AtomicTest phase */
-	ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, drm_crtc->state,
-			     topology, false);
-	if (ret) {
-		DPU_ERROR_ENC(dpu_enc,
-				"failed to reserve hw resources, %d\n", ret);
-		return;
-	}
-
-	dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, DPU_HW_BLK_PINGPONG);
-	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
-		dpu_enc->hw_pp[i] = NULL;
-		if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
-			break;
-		dpu_enc->hw_pp[i] = (struct dpu_hw_pingpong *) hw_iter.hw;
-	}
-
-	dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, DPU_HW_BLK_CTL);
-	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
-		if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
-			break;
-		hw_ctl[i] = (struct dpu_hw_ctl *)hw_iter.hw;
-		num_ctl++;
-	}
+	/* Query resource that have been reserved in atomic check step. */
+	num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_PINGPONG, hw_pp,
+		ARRAY_SIZE(hw_pp));
+	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
+	num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
 
-	dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, DPU_HW_BLK_LM);
-	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
-		if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
-			break;
-		hw_lm[i] = (struct dpu_hw_mixer *)hw_iter.hw;
-		num_lm++;
-	}
+	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
+		dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i])
+						: NULL;
 
 	cstate = to_dpu_crtc_state(drm_crtc->state);
 
 	for (i = 0; i < num_lm; i++) {
 		int ctl_idx = (i < num_ctl) ? i : (num_ctl-1);
 
-		cstate->mixers[i].hw_lm = hw_lm[i];
-		cstate->mixers[i].lm_ctl = hw_ctl[ctl_idx];
+		cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]);
+		cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]);
 	}
 
 	cstate->num_mixers = num_lm;
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		int num_blk;
+		struct dpu_hw_blk *hw_blk[MAX_CHANNELS_PER_ENC];
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
 		if (!dpu_enc->hw_pp[i]) {
 			DPU_ERROR_ENC(dpu_enc,
 				"no pp block assigned at idx: %d\n", i);
-			goto error;
+			return;
 		}
 
 		if (!hw_ctl[i]) {
 			DPU_ERROR_ENC(dpu_enc,
 				"no ctl block assigned at idx: %d\n", i);
-			goto error;
+			return;
 		}
 
 		phys->hw_pp = dpu_enc->hw_pp[i];
-		phys->hw_ctl = hw_ctl[i];
+		phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]);
 
-		dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id,
-				    DPU_HW_BLK_INTF);
-		for (j = 0; j < MAX_CHANNELS_PER_ENC; j++) {
+		num_blk = dpu_rm_get_assigned_resources(&dpu_kms->rm,
+			global_state, drm_enc->base.id, DPU_HW_BLK_INTF,
+			hw_blk, ARRAY_SIZE(hw_blk));
+		for (j = 0; j < num_blk; j++) {
 			struct dpu_hw_intf *hw_intf;
 
-			if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
-				break;
-
-			hw_intf = (struct dpu_hw_intf *)hw_iter.hw;
+			hw_intf = to_dpu_hw_intf(hw_blk[i]);
 			if (hw_intf->idx == phys->intf_idx)
 				phys->hw_intf = hw_intf;
 		}
@@ -1073,18 +1058,13 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
 		if (!phys->hw_intf) {
 			DPU_ERROR_ENC(dpu_enc,
 				      "no intf block assigned at idx: %d\n", i);
-				goto error;
+			return;
 		}
 
 		phys->connector = conn->state->connector;
 		if (phys->ops.mode_set)
 			phys->ops.mode_set(phys, mode, adj_mode);
 	}
-
-	dpu_enc->mode_set_complete = true;
-
-error:
-	dpu_rm_release(&dpu_kms->rm, drm_enc);
 }
 
 static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
@@ -1181,6 +1161,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
+	struct dpu_global_state *global_state;
 	int i = 0;
 
 	if (!drm_enc) {
@@ -1199,6 +1180,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
+	global_state = dpu_kms_get_existing_global_state(dpu_kms);
 
 	trace_dpu_enc_disable(DRMID(drm_enc));
 
@@ -1228,7 +1210,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 
 	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
 
-	dpu_rm_release(&dpu_kms->rm, drm_enc);
+	dpu_rm_release(global_state, drm_enc);
 
 	mutex_unlock(&dpu_enc->enc_lock);
 }
@@ -1964,7 +1946,7 @@ static int dpu_encoder_virt_add_phys_encs(
 		if (IS_ERR_OR_NULL(enc)) {
 			DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n",
 				PTR_ERR(enc));
-			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+			return enc == NULL ? -EINVAL : PTR_ERR(enc);
 		}
 
 		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
@@ -1977,7 +1959,7 @@ static int dpu_encoder_virt_add_phys_encs(
 		if (IS_ERR_OR_NULL(enc)) {
 			DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n",
 				PTR_ERR(enc));
-			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+			return enc == NULL ? -EINVAL : PTR_ERR(enc);
 		}
 
 		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
@@ -2008,7 +1990,7 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 	struct dpu_enc_phys_init_params phys_params;
 
 	if (!dpu_enc) {
-		DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != 0);
+		DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != NULL);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 39e1e280ba44..8493d68ad841 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -411,7 +411,7 @@ static void _dpu_encoder_phys_cmd_pingpong_config(
 		to_dpu_encoder_phys_cmd(phys_enc);
 
 	if (!phys_enc->hw_pp || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
-		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0);
+		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != NULL);
 		return;
 	}
 
@@ -440,7 +440,7 @@ static void dpu_encoder_phys_cmd_enable_helper(
 	u32 flush_mask = 0;
 
 	if (!phys_enc->hw_pp) {
-		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != NULL);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index c71c18de5966..b5a49050d131 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -239,7 +239,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	struct dpu_hw_intf_cfg intf_cfg = { 0 };
 
 	if (!phys_enc->hw_ctl->ops.setup_intf_cfg) {
-		DPU_ERROR("invalid encoder %d\n", phys_enc != 0);
+		DPU_ERROR("invalid encoder %d\n", phys_enc != NULL);
 		return;
 	}
 
@@ -559,7 +559,7 @@ static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
 
 	if (!phys_enc->hw_intf) {
 		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
-				phys_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+				phys_enc->hw_intf != NULL, phys_enc->hw_ctl != NULL);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 528632690f1e..a05282dede91 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -255,13 +255,13 @@ static const struct dpu_format dpu_format_map[] = {
 
 	INTERLEAVED_RGB_FMT(RGB565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
 	INTERLEAVED_RGB_FMT(BGR565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
index 85468981632d..0ead64d3f63d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -90,6 +90,16 @@ struct dpu_hw_intf {
 };
 
 /**
+ * to_dpu_hw_intf - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_intf, base);
+}
+
+/**
  * dpu_hw_intf_init(): Initializes the intf driver for the passed
  * interface idx.
  * @idx:  interface index for which driver object is required
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
index 3d6f46b1db30..d73cb73e938b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -97,6 +97,16 @@ struct dpu_hw_pingpong {
 };
 
 /**
+ * to_dpu_hw_pingpong - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pingpong, base);
+}
+
+/**
  * dpu_hw_pingpong_init - initializes the pingpong driver for the passed
  *	pingpong idx.
  * @idx:  Pingpong index for which driver object is required
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index cb08fafb1dc1..ce19f1d39367 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -138,16 +138,12 @@ static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
 {
 	struct dpu_debugfs_regset32 *regset = s->private;
 	struct dpu_kms *dpu_kms = regset->dpu_kms;
-	struct drm_device *dev;
-	struct msm_drm_private *priv;
 	void __iomem *base;
 	uint32_t i, addr;
 
 	if (!dpu_kms->mmio)
 		return 0;
 
-	dev = dpu_kms->dev;
-	priv = dev->dev_private;
 	base = dpu_kms->mmio + regset->offset;
 
 	/* insert padding spaces, if needed */
@@ -228,6 +224,85 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
 }
 #endif
 
+/* Global/shared object state funcs */
+
+/*
+ * This is a helper that returns the private state currently in operation.
+ * Note that this would return the "old_state" if called in the atomic check
+ * path, and the "new_state" after the atomic swap has been done.
+ */
+struct dpu_global_state *
+dpu_kms_get_existing_global_state(struct dpu_kms *dpu_kms)
+{
+	return to_dpu_global_state(dpu_kms->global_state.state);
+}
+
+/*
+ * This acquires the modeset lock set aside for global state, creates
+ * a new duplicated private object state.
+ */
+struct dpu_global_state *dpu_kms_get_global_state(struct drm_atomic_state *s)
+{
+	struct msm_drm_private *priv = s->dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_private_state *priv_state;
+	int ret;
+
+	ret = drm_modeset_lock(&dpu_kms->global_state_lock, s->acquire_ctx);
+	if (ret)
+		return ERR_PTR(ret);
+
+	priv_state = drm_atomic_get_private_obj_state(s,
+						&dpu_kms->global_state);
+	if (IS_ERR(priv_state))
+		return ERR_CAST(priv_state);
+
+	return to_dpu_global_state(priv_state);
+}
+
+static struct drm_private_state *
+dpu_kms_global_duplicate_state(struct drm_private_obj *obj)
+{
+	struct dpu_global_state *state;
+
+	state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+	return &state->base;
+}
+
+static void dpu_kms_global_destroy_state(struct drm_private_obj *obj,
+				      struct drm_private_state *state)
+{
+	struct dpu_global_state *dpu_state = to_dpu_global_state(state);
+
+	kfree(dpu_state);
+}
+
+static const struct drm_private_state_funcs dpu_kms_global_state_funcs = {
+	.atomic_duplicate_state = dpu_kms_global_duplicate_state,
+	.atomic_destroy_state = dpu_kms_global_destroy_state,
+};
+
+static int dpu_kms_global_obj_init(struct dpu_kms *dpu_kms)
+{
+	struct dpu_global_state *state;
+
+	drm_modeset_lock_init(&dpu_kms->global_state_lock);
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	drm_atomic_private_obj_init(dpu_kms->dev, &dpu_kms->global_state,
+				    &state->base,
+				    &dpu_kms_global_state_funcs);
+	return 0;
+}
+
 static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
 {
 	return dpu_crtc_vblank(crtc, true);
@@ -267,8 +342,6 @@ static ktime_t dpu_kms_vsync_time(struct msm_kms *kms, struct drm_crtc *crtc)
 static void dpu_kms_prepare_commit(struct msm_kms *kms,
 		struct drm_atomic_state *state)
 {
-	struct dpu_kms *dpu_kms;
-	struct drm_device *dev;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	struct drm_encoder *encoder;
@@ -276,8 +349,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 
 	if (!kms)
 		return;
-	dpu_kms = to_dpu_kms(kms);
-	dev = dpu_kms->dev;
 
 	/* Call prepare_commit for all affected encoders */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
@@ -552,11 +623,8 @@ static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate,
 
 static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 {
-	struct drm_device *dev;
 	int i;
 
-	dev = dpu_kms->dev;
-
 	if (dpu_kms->hw_intr)
 		dpu_hw_intr_destroy(dpu_kms->hw_intr);
 	dpu_kms->hw_intr = NULL;
@@ -760,7 +828,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 {
 	struct dpu_kms *dpu_kms;
 	struct drm_device *dev;
-	struct msm_drm_private *priv;
 	int i, rc = -EINVAL;
 
 	if (!kms) {
@@ -770,7 +837,10 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
-	priv = dev->dev_private;
+
+	rc = dpu_kms_global_obj_init(dpu_kms);
+	if (rc)
+		return rc;
 
 	atomic_set(&dpu_kms->bandwidth_ref, 0);
 
@@ -1018,10 +1088,8 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev)
 	int rc = -1;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
-	struct drm_device *ddev;
 	struct dss_module_power *mp = &dpu_kms->mp;
 
-	ddev = dpu_kms->dev;
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
 	if (rc)
 		DPU_ERROR("clock disable failed rc:%d\n", rc);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index c6169e7df19d..211f5de99a44 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -111,6 +111,13 @@ struct dpu_kms {
 
 	struct dpu_core_perf perf;
 
+	/*
+	 * Global private object state, Do not access directly, use
+	 * dpu_kms_global_get_state()
+	 */
+	struct drm_modeset_lock global_state_lock;
+	struct drm_private_obj global_state;
+
 	struct dpu_rm rm;
 	bool rm_init;
 
@@ -139,6 +146,25 @@ struct vsync_info {
 
 #define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
 
+#define to_dpu_global_state(x) container_of(x, struct dpu_global_state, base)
+
+/* Global private object state for tracking resources that are shared across
+ * multiple kms objects (planes/crtcs/etc).
+ */
+struct dpu_global_state {
+	struct drm_private_state base;
+
+	uint32_t pingpong_to_enc_id[PINGPONG_MAX - PINGPONG_0];
+	uint32_t mixer_to_enc_id[LM_MAX - LM_0];
+	uint32_t ctl_to_enc_id[CTL_MAX - CTL_0];
+	uint32_t intf_to_enc_id[INTF_MAX - INTF_0];
+};
+
+struct dpu_global_state
+	*dpu_kms_get_existing_global_state(struct dpu_kms *dpu_kms);
+struct dpu_global_state
+	*__must_check dpu_kms_get_global_state(struct drm_atomic_state *s);
+
 /**
  * Debugfs functions - extra helper functions for debugfs support
  *
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
index 29705e773a4b..80d3cfc14007 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -12,6 +12,7 @@
 
 #define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
 
+#define HW_REV				0x0
 #define HW_INTR_STATUS			0x0010
 
 /* Max BW defined in KBps */
@@ -22,6 +23,17 @@ struct dpu_irq_controller {
 	struct irq_domain *domain;
 };
 
+struct dpu_hw_cfg {
+	u32 val;
+	u32 offset;
+};
+
+struct dpu_mdss_hw_init_handler {
+	u32 hw_rev;
+	u32 hw_reg_count;
+	struct dpu_hw_cfg* hw_cfg;
+};
+
 struct dpu_mdss {
 	struct msm_mdss base;
 	void __iomem *mmio;
@@ -32,6 +44,44 @@ struct dpu_mdss {
 	u32 num_paths;
 };
 
+static struct dpu_hw_cfg hw_cfg[] = {
+    {
+	/* UBWC global settings */
+	.val = 0x1E,
+	.offset = 0x144,
+    }
+};
+
+static struct dpu_mdss_hw_init_handler cfg_handler[] = {
+    { .hw_rev = DPU_HW_VER_620,
+      .hw_reg_count = ARRAY_SIZE(hw_cfg),
+      .hw_cfg = hw_cfg
+    },
+};
+
+static void dpu_mdss_hw_init(struct dpu_mdss *dpu_mdss, u32 hw_rev)
+{
+	int i;
+	u32 count = 0;
+	struct dpu_hw_cfg *hw_cfg = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev) {
+			hw_cfg = cfg_handler[i].hw_cfg;
+			count = cfg_handler[i].hw_reg_count;
+			break;
+	    }
+	}
+
+	for (i = 0; i < count; i++ ) {
+		writel_relaxed(hw_cfg->val,
+			dpu_mdss->mmio + hw_cfg->offset);
+		hw_cfg++;
+	}
+
+    return;
+}
+
 static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev,
 						struct dpu_mdss *dpu_mdss)
 {
@@ -174,12 +224,18 @@ static int dpu_mdss_enable(struct msm_mdss *mdss)
 	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
 	struct dss_module_power *mp = &dpu_mdss->mp;
 	int ret;
+	u32 mdss_rev;
 
 	dpu_mdss_icc_request_bw(mdss);
 
 	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
-	if (ret)
+	if (ret) {
 		DPU_ERROR("clock enable failed, ret:%d\n", ret);
+		return ret;
+	}
+
+	mdss_rev = readl_relaxed(dpu_mdss->mmio + HW_REV);
+	dpu_mdss_hw_init(dpu_mdss, mdss_rev);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index 23f5b1433b35..9b62451b01ee 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -12,8 +12,12 @@
 #include "dpu_encoder.h"
 #include "dpu_trace.h"
 
-#define RESERVED_BY_OTHER(h, r)  \
-		((h)->enc_id && (h)->enc_id != r)
+
+static inline bool reserved_by_other(uint32_t *res_map, int idx,
+				     uint32_t enc_id)
+{
+	return res_map[idx] && res_map[idx] != enc_id;
+}
 
 /**
  * struct dpu_rm_requirements - Reservation requirements parameter bundle
@@ -25,171 +29,43 @@ struct dpu_rm_requirements {
 	struct dpu_encoder_hw_resources hw_res;
 };
 
-
-/**
- * struct dpu_rm_hw_blk - hardware block tracking list member
- * @list:	List head for list of all hardware blocks tracking items
- * @id:		Hardware ID number, within it's own space, ie. LM_X
- * @enc_id:	Encoder id to which this blk is binded
- * @hw:		Pointer to the hardware register access object for this block
- */
-struct dpu_rm_hw_blk {
-	struct list_head list;
-	uint32_t id;
-	uint32_t enc_id;
-	struct dpu_hw_blk *hw;
-};
-
-void dpu_rm_init_hw_iter(
-		struct dpu_rm_hw_iter *iter,
-		uint32_t enc_id,
-		enum dpu_hw_blk_type type)
-{
-	memset(iter, 0, sizeof(*iter));
-	iter->enc_id = enc_id;
-	iter->type = type;
-}
-
-static bool _dpu_rm_get_hw_locked(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+int dpu_rm_destroy(struct dpu_rm *rm)
 {
-	struct list_head *blk_list;
-
-	if (!rm || !i || i->type >= DPU_HW_BLK_MAX) {
-		DPU_ERROR("invalid rm\n");
-		return false;
-	}
+	int i;
 
-	i->hw = NULL;
-	blk_list = &rm->hw_blks[i->type];
+	for (i = 0; i < ARRAY_SIZE(rm->pingpong_blks); i++) {
+		struct dpu_hw_pingpong *hw;
 
-	if (i->blk && (&i->blk->list == blk_list)) {
-		DPU_DEBUG("attempt resume iteration past last\n");
-		return false;
-	}
-
-	i->blk = list_prepare_entry(i->blk, blk_list, list);
-
-	list_for_each_entry_continue(i->blk, blk_list, list) {
-		if (i->enc_id == i->blk->enc_id) {
-			i->hw = i->blk->hw;
-			DPU_DEBUG("found type %d id %d for enc %d\n",
-					i->type, i->blk->id, i->enc_id);
-			return true;
+		if (rm->pingpong_blks[i]) {
+			hw = to_dpu_hw_pingpong(rm->pingpong_blks[i]);
+			dpu_hw_pingpong_destroy(hw);
 		}
 	}
+	for (i = 0; i < ARRAY_SIZE(rm->mixer_blks); i++) {
+		struct dpu_hw_mixer *hw;
 
-	DPU_DEBUG("no match, type %d for enc %d\n", i->type, i->enc_id);
-
-	return false;
-}
-
-bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
-{
-	bool ret;
-
-	mutex_lock(&rm->rm_lock);
-	ret = _dpu_rm_get_hw_locked(rm, i);
-	mutex_unlock(&rm->rm_lock);
-
-	return ret;
-}
-
-static void _dpu_rm_hw_destroy(enum dpu_hw_blk_type type, void *hw)
-{
-	switch (type) {
-	case DPU_HW_BLK_LM:
-		dpu_hw_lm_destroy(hw);
-		break;
-	case DPU_HW_BLK_CTL:
-		dpu_hw_ctl_destroy(hw);
-		break;
-	case DPU_HW_BLK_PINGPONG:
-		dpu_hw_pingpong_destroy(hw);
-		break;
-	case DPU_HW_BLK_INTF:
-		dpu_hw_intf_destroy(hw);
-		break;
-	case DPU_HW_BLK_SSPP:
-		/* SSPPs are not managed by the resource manager */
-	case DPU_HW_BLK_TOP:
-		/* Top is a singleton, not managed in hw_blks list */
-	case DPU_HW_BLK_MAX:
-	default:
-		DPU_ERROR("unsupported block type %d\n", type);
-		break;
-	}
-}
-
-int dpu_rm_destroy(struct dpu_rm *rm)
-{
-	struct dpu_rm_hw_blk *hw_cur, *hw_nxt;
-	enum dpu_hw_blk_type type;
-
-	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
-		list_for_each_entry_safe(hw_cur, hw_nxt, &rm->hw_blks[type],
-				list) {
-			list_del(&hw_cur->list);
-			_dpu_rm_hw_destroy(type, hw_cur->hw);
-			kfree(hw_cur);
+		if (rm->mixer_blks[i]) {
+			hw = to_dpu_hw_mixer(rm->mixer_blks[i]);
+			dpu_hw_lm_destroy(hw);
 		}
 	}
+	for (i = 0; i < ARRAY_SIZE(rm->ctl_blks); i++) {
+		struct dpu_hw_ctl *hw;
 
-	mutex_destroy(&rm->rm_lock);
-
-	return 0;
-}
-
-static int _dpu_rm_hw_blk_create(
-		struct dpu_rm *rm,
-		const struct dpu_mdss_cfg *cat,
-		void __iomem *mmio,
-		enum dpu_hw_blk_type type,
-		uint32_t id,
-		const void *hw_catalog_info)
-{
-	struct dpu_rm_hw_blk *blk;
-	void *hw;
-
-	switch (type) {
-	case DPU_HW_BLK_LM:
-		hw = dpu_hw_lm_init(id, mmio, cat);
-		break;
-	case DPU_HW_BLK_CTL:
-		hw = dpu_hw_ctl_init(id, mmio, cat);
-		break;
-	case DPU_HW_BLK_PINGPONG:
-		hw = dpu_hw_pingpong_init(id, mmio, cat);
-		break;
-	case DPU_HW_BLK_INTF:
-		hw = dpu_hw_intf_init(id, mmio, cat);
-		break;
-	case DPU_HW_BLK_SSPP:
-		/* SSPPs are not managed by the resource manager */
-	case DPU_HW_BLK_TOP:
-		/* Top is a singleton, not managed in hw_blks list */
-	case DPU_HW_BLK_MAX:
-	default:
-		DPU_ERROR("unsupported block type %d\n", type);
-		return -EINVAL;
-	}
-
-	if (IS_ERR_OR_NULL(hw)) {
-		DPU_ERROR("failed hw object creation: type %d, err %ld\n",
-				type, PTR_ERR(hw));
-		return -EFAULT;
+		if (rm->ctl_blks[i]) {
+			hw = to_dpu_hw_ctl(rm->ctl_blks[i]);
+			dpu_hw_ctl_destroy(hw);
+		}
 	}
+	for (i = 0; i < ARRAY_SIZE(rm->intf_blks); i++) {
+		struct dpu_hw_intf *hw;
 
-	blk = kzalloc(sizeof(*blk), GFP_KERNEL);
-	if (!blk) {
-		_dpu_rm_hw_destroy(type, hw);
-		return -ENOMEM;
+		if (rm->intf_blks[i]) {
+			hw = to_dpu_hw_intf(rm->intf_blks[i]);
+			dpu_hw_intf_destroy(hw);
+		}
 	}
 
-	blk->id = id;
-	blk->hw = hw;
-	blk->enc_id = 0;
-	list_add_tail(&blk->list, &rm->hw_blks[type]);
-
 	return 0;
 }
 
@@ -198,7 +74,6 @@ int dpu_rm_init(struct dpu_rm *rm,
 		void __iomem *mmio)
 {
 	int rc, i;
-	enum dpu_hw_blk_type type;
 
 	if (!rm || !cat || !mmio) {
 		DPU_ERROR("invalid kms\n");
@@ -208,13 +83,9 @@ int dpu_rm_init(struct dpu_rm *rm,
 	/* Clear, setup lists */
 	memset(rm, 0, sizeof(*rm));
 
-	mutex_init(&rm->rm_lock);
-
-	for (type = 0; type < DPU_HW_BLK_MAX; type++)
-		INIT_LIST_HEAD(&rm->hw_blks[type]);
-
 	/* Interrogate HW catalog and create tracking items for hw blocks */
 	for (i = 0; i < cat->mixer_count; i++) {
+		struct dpu_hw_mixer *hw;
 		const struct dpu_lm_cfg *lm = &cat->mixer[i];
 
 		if (lm->pingpong == PINGPONG_MAX) {
@@ -222,12 +93,17 @@ int dpu_rm_init(struct dpu_rm *rm,
 			continue;
 		}
 
-		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_LM,
-				cat->mixer[i].id, &cat->mixer[i]);
-		if (rc) {
-			DPU_ERROR("failed: lm hw not available\n");
+		if (lm->id < LM_0 || lm->id >= LM_MAX) {
+			DPU_ERROR("skip mixer %d with invalid id\n", lm->id);
+			continue;
+		}
+		hw = dpu_hw_lm_init(lm->id, mmio, cat);
+		if (IS_ERR_OR_NULL(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed lm object creation: err %d\n", rc);
 			goto fail;
 		}
+		rm->mixer_blks[lm->id - LM_0] = &hw->base;
 
 		if (!rm->lm_max_width) {
 			rm->lm_max_width = lm->sblk->maxwidth;
@@ -243,35 +119,59 @@ int dpu_rm_init(struct dpu_rm *rm,
 	}
 
 	for (i = 0; i < cat->pingpong_count; i++) {
-		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_PINGPONG,
-				cat->pingpong[i].id, &cat->pingpong[i]);
-		if (rc) {
-			DPU_ERROR("failed: pp hw not available\n");
+		struct dpu_hw_pingpong *hw;
+		const struct dpu_pingpong_cfg *pp = &cat->pingpong[i];
+
+		if (pp->id < PINGPONG_0 || pp->id >= PINGPONG_MAX) {
+			DPU_ERROR("skip pingpong %d with invalid id\n", pp->id);
+			continue;
+		}
+		hw = dpu_hw_pingpong_init(pp->id, mmio, cat);
+		if (IS_ERR_OR_NULL(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed pingpong object creation: err %d\n",
+				rc);
 			goto fail;
 		}
+		rm->pingpong_blks[pp->id - PINGPONG_0] = &hw->base;
 	}
 
 	for (i = 0; i < cat->intf_count; i++) {
-		if (cat->intf[i].type == INTF_NONE) {
+		struct dpu_hw_intf *hw;
+		const struct dpu_intf_cfg *intf = &cat->intf[i];
+
+		if (intf->type == INTF_NONE) {
 			DPU_DEBUG("skip intf %d with type none\n", i);
 			continue;
 		}
-
-		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_INTF,
-				cat->intf[i].id, &cat->intf[i]);
-		if (rc) {
-			DPU_ERROR("failed: intf hw not available\n");
+		if (intf->id < INTF_0 || intf->id >= INTF_MAX) {
+			DPU_ERROR("skip intf %d with invalid id\n", intf->id);
+			continue;
+		}
+		hw = dpu_hw_intf_init(intf->id, mmio, cat);
+		if (IS_ERR_OR_NULL(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed intf object creation: err %d\n", rc);
 			goto fail;
 		}
+		rm->intf_blks[intf->id - INTF_0] = &hw->base;
 	}
 
 	for (i = 0; i < cat->ctl_count; i++) {
-		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CTL,
-				cat->ctl[i].id, &cat->ctl[i]);
-		if (rc) {
-			DPU_ERROR("failed: ctl hw not available\n");
+		struct dpu_hw_ctl *hw;
+		const struct dpu_ctl_cfg *ctl = &cat->ctl[i];
+
+		if (ctl->id < CTL_0 || ctl->id >= CTL_MAX) {
+			DPU_ERROR("skip ctl %d with invalid id\n", ctl->id);
+			continue;
+		}
+		hw = dpu_hw_ctl_init(ctl->id, mmio, cat);
+		if (IS_ERR_OR_NULL(hw)) {
+			rc = PTR_ERR(hw);
+			DPU_ERROR("failed ctl object creation: err %d\n", rc);
 			goto fail;
 		}
+		rm->ctl_blks[ctl->id - CTL_0] = &hw->base;
 	}
 
 	return 0;
@@ -279,7 +179,7 @@ int dpu_rm_init(struct dpu_rm *rm,
 fail:
 	dpu_rm_destroy(rm);
 
-	return rc;
+	return rc ? rc : -EFAULT;
 }
 
 static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
@@ -288,85 +188,81 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
 }
 
 /**
+ * _dpu_rm_check_lm_peer - check if a mixer is a peer of the primary
+ * @rm: dpu resource manager handle
+ * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ * @peer_idx: index of other mixer in rm->mixer_blks[]
+ * @Return: true if rm->mixer_blks[peer_idx] is a peer of
+ *          rm->mixer_blks[primary_idx]
+ */
+static bool _dpu_rm_check_lm_peer(struct dpu_rm *rm, int primary_idx,
+		int peer_idx)
+{
+	const struct dpu_lm_cfg *prim_lm_cfg;
+	const struct dpu_lm_cfg *peer_cfg;
+
+	prim_lm_cfg = to_dpu_hw_mixer(rm->mixer_blks[primary_idx])->cap;
+	peer_cfg = to_dpu_hw_mixer(rm->mixer_blks[peer_idx])->cap;
+
+	if (!test_bit(peer_cfg->id, &prim_lm_cfg->lm_pair_mask)) {
+		DPU_DEBUG("lm %d not peer of lm %d\n", peer_cfg->id,
+				peer_cfg->id);
+		return false;
+	}
+	return true;
+}
+
+/**
  * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets
  *	proposed use case requirements, incl. hardwired dependent blocks like
  *	pingpong
  * @rm: dpu resource manager handle
  * @enc_id: encoder id requesting for allocation
- * @reqs: proposed use case requirements
- * @lm: proposed layer mixer, function checks if lm, and all other hardwired
- *      blocks connected to the lm (pp) is available and appropriate
- * @pp: output parameter, pingpong block attached to the layer mixer.
- *      NULL if pp was not available, or not matching requirements.
- * @primary_lm: if non-null, this function check if lm is compatible primary_lm
- *              as well as satisfying all other requirements
+ * @lm_idx: index of proposed layer mixer in rm->mixer_blks[], function checks
+ *      if lm, and all other hardwired blocks connected to the lm (pp) is
+ *      available and appropriate
+ * @pp_idx: output parameter, index of pingpong block attached to the layer
+ *      mixer in rm->pongpong_blks[].
  * @Return: true if lm matches all requirements, false otherwise
  */
-static bool _dpu_rm_check_lm_and_get_connected_blks(
-		struct dpu_rm *rm,
-		uint32_t enc_id,
-		struct dpu_rm_requirements *reqs,
-		struct dpu_rm_hw_blk *lm,
-		struct dpu_rm_hw_blk **pp,
-		struct dpu_rm_hw_blk *primary_lm)
+static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
+		uint32_t enc_id, int lm_idx, int *pp_idx)
 {
-	const struct dpu_lm_cfg *lm_cfg = to_dpu_hw_mixer(lm->hw)->cap;
-	struct dpu_rm_hw_iter iter;
-
-	*pp = NULL;
-
-	DPU_DEBUG("check lm %d pp %d\n",
-			   lm_cfg->id, lm_cfg->pingpong);
-
-	/* Check if this layer mixer is a peer of the proposed primary LM */
-	if (primary_lm) {
-		const struct dpu_lm_cfg *prim_lm_cfg =
-				to_dpu_hw_mixer(primary_lm->hw)->cap;
-
-		if (!test_bit(lm_cfg->id, &prim_lm_cfg->lm_pair_mask)) {
-			DPU_DEBUG("lm %d not peer of lm %d\n", lm_cfg->id,
-					prim_lm_cfg->id);
-			return false;
-		}
-	}
+	const struct dpu_lm_cfg *lm_cfg;
+	int idx;
 
 	/* Already reserved? */
-	if (RESERVED_BY_OTHER(lm, enc_id)) {
-		DPU_DEBUG("lm %d already reserved\n", lm_cfg->id);
+	if (reserved_by_other(global_state->mixer_to_enc_id, lm_idx, enc_id)) {
+		DPU_DEBUG("lm %d already reserved\n", lm_idx + LM_0);
 		return false;
 	}
 
-	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_PINGPONG);
-	while (_dpu_rm_get_hw_locked(rm, &iter)) {
-		if (iter.blk->id == lm_cfg->pingpong) {
-			*pp = iter.blk;
-			break;
-		}
-	}
-
-	if (!*pp) {
+	lm_cfg = to_dpu_hw_mixer(rm->mixer_blks[lm_idx])->cap;
+	idx = lm_cfg->pingpong - PINGPONG_0;
+	if (idx < 0 || idx >= ARRAY_SIZE(rm->pingpong_blks)) {
 		DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong);
 		return false;
 	}
 
-	if (RESERVED_BY_OTHER(*pp, enc_id)) {
-		DPU_DEBUG("lm %d pp %d already reserved\n", lm->id,
-				(*pp)->id);
+	if (reserved_by_other(global_state->pingpong_to_enc_id, idx, enc_id)) {
+		DPU_DEBUG("lm %d pp %d already reserved\n", lm_cfg->id,
+				lm_cfg->pingpong);
 		return false;
 	}
-
+	*pp_idx = idx;
 	return true;
 }
 
-static int _dpu_rm_reserve_lms(struct dpu_rm *rm, uint32_t enc_id,
+static int _dpu_rm_reserve_lms(struct dpu_rm *rm,
+			       struct dpu_global_state *global_state,
+			       uint32_t enc_id,
 			       struct dpu_rm_requirements *reqs)
 
 {
-	struct dpu_rm_hw_blk *lm[MAX_BLOCKS];
-	struct dpu_rm_hw_blk *pp[MAX_BLOCKS];
-	struct dpu_rm_hw_iter iter_i, iter_j;
-	int lm_count = 0;
-	int i, rc = 0;
+	int lm_idx[MAX_BLOCKS];
+	int pp_idx[MAX_BLOCKS];
+	int i, j, lm_count = 0;
 
 	if (!reqs->topology.num_lm) {
 		DPU_ERROR("invalid number of lm: %d\n", reqs->topology.num_lm);
@@ -374,36 +270,40 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, uint32_t enc_id,
 	}
 
 	/* Find a primary mixer */
-	dpu_rm_init_hw_iter(&iter_i, 0, DPU_HW_BLK_LM);
-	while (lm_count != reqs->topology.num_lm &&
-			_dpu_rm_get_hw_locked(rm, &iter_i)) {
-		memset(&lm, 0, sizeof(lm));
-		memset(&pp, 0, sizeof(pp));
+	for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) &&
+			lm_count < reqs->topology.num_lm; i++) {
+		if (!rm->mixer_blks[i])
+			continue;
 
 		lm_count = 0;
-		lm[lm_count] = iter_i.blk;
+		lm_idx[lm_count] = i;
 
-		if (!_dpu_rm_check_lm_and_get_connected_blks(
-				rm, enc_id, reqs, lm[lm_count],
-				&pp[lm_count], NULL))
+		if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state,
+				enc_id, i, &pp_idx[lm_count])) {
 			continue;
+		}
 
 		++lm_count;
 
 		/* Valid primary mixer found, find matching peers */
-		dpu_rm_init_hw_iter(&iter_j, 0, DPU_HW_BLK_LM);
+		for (j = i + 1; j < ARRAY_SIZE(rm->mixer_blks) &&
+				lm_count < reqs->topology.num_lm; j++) {
+			if (!rm->mixer_blks[j])
+				continue;
 
-		while (lm_count != reqs->topology.num_lm &&
-				_dpu_rm_get_hw_locked(rm, &iter_j)) {
-			if (iter_i.blk == iter_j.blk)
+			if (!_dpu_rm_check_lm_peer(rm, i, j)) {
+				DPU_DEBUG("lm %d not peer of lm %d\n", LM_0 + j,
+						LM_0 + i);
 				continue;
+			}
 
-			if (!_dpu_rm_check_lm_and_get_connected_blks(
-					rm, enc_id, reqs, iter_j.blk,
-					&pp[lm_count], iter_i.blk))
+			if (!_dpu_rm_check_lm_and_get_connected_blks(rm,
+					global_state, enc_id, j,
+					&pp_idx[lm_count])) {
 				continue;
+			}
 
-			lm[lm_count] = iter_j.blk;
+			lm_idx[lm_count] = j;
 			++lm_count;
 		}
 	}
@@ -413,65 +313,65 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, uint32_t enc_id,
 		return -ENAVAIL;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(lm); i++) {
-		if (!lm[i])
-			break;
+	for (i = 0; i < lm_count; i++) {
+		global_state->mixer_to_enc_id[lm_idx[i]] = enc_id;
+		global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id;
 
-		lm[i]->enc_id = enc_id;
-		pp[i]->enc_id = enc_id;
-
-		trace_dpu_rm_reserve_lms(lm[i]->id, enc_id, pp[i]->id);
+		trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id,
+					 pp_idx[i] + PINGPONG_0);
 	}
 
-	return rc;
+	return 0;
 }
 
 static int _dpu_rm_reserve_ctls(
 		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
 		uint32_t enc_id,
 		const struct msm_display_topology *top)
 {
-	struct dpu_rm_hw_blk *ctls[MAX_BLOCKS];
-	struct dpu_rm_hw_iter iter;
-	int i = 0, num_ctls = 0;
-	bool needs_split_display = false;
-
-	memset(&ctls, 0, sizeof(ctls));
+	int ctl_idx[MAX_BLOCKS];
+	int i = 0, j, num_ctls;
+	bool needs_split_display;
 
 	/* each hw_intf needs its own hw_ctrl to program its control path */
 	num_ctls = top->num_intf;
 
 	needs_split_display = _dpu_rm_needs_split_display(top);
 
-	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CTL);
-	while (_dpu_rm_get_hw_locked(rm, &iter)) {
-		const struct dpu_hw_ctl *ctl = to_dpu_hw_ctl(iter.blk->hw);
-		unsigned long features = ctl->caps->features;
+	for (j = 0; j < ARRAY_SIZE(rm->ctl_blks); j++) {
+		const struct dpu_hw_ctl *ctl;
+		unsigned long features;
 		bool has_split_display;
 
-		if (RESERVED_BY_OTHER(iter.blk, enc_id))
+		if (!rm->ctl_blks[j])
+			continue;
+		if (reserved_by_other(global_state->ctl_to_enc_id, j, enc_id))
 			continue;
 
+		ctl = to_dpu_hw_ctl(rm->ctl_blks[j]);
+		features = ctl->caps->features;
 		has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features;
 
-		DPU_DEBUG("ctl %d caps 0x%lX\n", iter.blk->id, features);
+		DPU_DEBUG("ctl %d caps 0x%lX\n", rm->ctl_blks[j]->id, features);
 
 		if (needs_split_display != has_split_display)
 			continue;
 
-		ctls[i] = iter.blk;
-		DPU_DEBUG("ctl %d match\n", iter.blk->id);
+		ctl_idx[i] = j;
+		DPU_DEBUG("ctl %d match\n", j + CTL_0);
 
 		if (++i == num_ctls)
 			break;
+
 	}
 
 	if (i != num_ctls)
 		return -ENAVAIL;
 
-	for (i = 0; i < ARRAY_SIZE(ctls) && i < num_ctls; i++) {
-		ctls[i]->enc_id = enc_id;
-		trace_dpu_rm_reserve_ctls(ctls[i]->id, enc_id);
+	for (i = 0; i < ARRAY_SIZE(ctl_idx) && i < num_ctls; i++) {
+		global_state->ctl_to_enc_id[ctl_idx[i]] = enc_id;
+		trace_dpu_rm_reserve_ctls(i + CTL_0, enc_id);
 	}
 
 	return 0;
@@ -479,40 +379,34 @@ static int _dpu_rm_reserve_ctls(
 
 static int _dpu_rm_reserve_intf(
 		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
 		uint32_t enc_id,
-		uint32_t id,
-		enum dpu_hw_blk_type type)
+		uint32_t id)
 {
-	struct dpu_rm_hw_iter iter;
-	int ret = 0;
-
-	/* Find the block entry in the rm, and note the reservation */
-	dpu_rm_init_hw_iter(&iter, 0, type);
-	while (_dpu_rm_get_hw_locked(rm, &iter)) {
-		if (iter.blk->id != id)
-			continue;
+	int idx = id - INTF_0;
 
-		if (RESERVED_BY_OTHER(iter.blk, enc_id)) {
-			DPU_ERROR("type %d id %d already reserved\n", type, id);
-			return -ENAVAIL;
-		}
-
-		iter.blk->enc_id = enc_id;
-		trace_dpu_rm_reserve_intf(iter.blk->id, enc_id);
-		break;
+	if (idx < 0 || idx >= ARRAY_SIZE(rm->intf_blks)) {
+		DPU_ERROR("invalid intf id: %d", id);
+		return -EINVAL;
 	}
 
-	/* Shouldn't happen since intfs are fixed at probe */
-	if (!iter.hw) {
-		DPU_ERROR("couldn't find type %d id %d\n", type, id);
+	if (!rm->intf_blks[idx]) {
+		DPU_ERROR("couldn't find intf id %d\n", id);
 		return -EINVAL;
 	}
 
-	return ret;
+	if (reserved_by_other(global_state->intf_to_enc_id, idx, enc_id)) {
+		DPU_ERROR("intf id %d already reserved\n", id);
+		return -ENAVAIL;
+	}
+
+	global_state->intf_to_enc_id[idx] = enc_id;
+	return 0;
 }
 
 static int _dpu_rm_reserve_intf_related_hw(
 		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
 		uint32_t enc_id,
 		struct dpu_encoder_hw_resources *hw_res)
 {
@@ -523,8 +417,7 @@ static int _dpu_rm_reserve_intf_related_hw(
 		if (hw_res->intfs[i] == INTF_MODE_NONE)
 			continue;
 		id = i + INTF_0;
-		ret = _dpu_rm_reserve_intf(rm, enc_id, id,
-				DPU_HW_BLK_INTF);
+		ret = _dpu_rm_reserve_intf(rm, global_state, enc_id, id);
 		if (ret)
 			return ret;
 	}
@@ -534,25 +427,27 @@ static int _dpu_rm_reserve_intf_related_hw(
 
 static int _dpu_rm_make_reservation(
 		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
 		struct drm_encoder *enc,
-		struct drm_crtc_state *crtc_state,
 		struct dpu_rm_requirements *reqs)
 {
 	int ret;
 
-	ret = _dpu_rm_reserve_lms(rm, enc->base.id, reqs);
+	ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, reqs);
 	if (ret) {
 		DPU_ERROR("unable to find appropriate mixers\n");
 		return ret;
 	}
 
-	ret = _dpu_rm_reserve_ctls(rm, enc->base.id, &reqs->topology);
+	ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id,
+				&reqs->topology);
 	if (ret) {
 		DPU_ERROR("unable to find appropriate CTL\n");
 		return ret;
 	}
 
-	ret = _dpu_rm_reserve_intf_related_hw(rm, enc->base.id, &reqs->hw_res);
+	ret = _dpu_rm_reserve_intf_related_hw(rm, global_state, enc->base.id,
+				&reqs->hw_res);
 	if (ret)
 		return ret;
 
@@ -560,9 +455,7 @@ static int _dpu_rm_make_reservation(
 }
 
 static int _dpu_rm_populate_requirements(
-		struct dpu_rm *rm,
 		struct drm_encoder *enc,
-		struct drm_crtc_state *crtc_state,
 		struct dpu_rm_requirements *reqs,
 		struct msm_display_topology req_topology)
 {
@@ -577,37 +470,36 @@ static int _dpu_rm_populate_requirements(
 	return 0;
 }
 
-static void _dpu_rm_release_reservation(struct dpu_rm *rm, uint32_t enc_id)
+static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt,
+				  uint32_t enc_id)
 {
-	struct dpu_rm_hw_blk *blk;
-	enum dpu_hw_blk_type type;
-
-	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
-		list_for_each_entry(blk, &rm->hw_blks[type], list) {
-			if (blk->enc_id == enc_id) {
-				blk->enc_id = 0;
-				DPU_DEBUG("rel enc %d %d %d\n", enc_id,
-					  type, blk->id);
-			}
-		}
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		if (res_mapping[i] == enc_id)
+			res_mapping[i] = 0;
 	}
 }
 
-void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc)
+void dpu_rm_release(struct dpu_global_state *global_state,
+		    struct drm_encoder *enc)
 {
-	mutex_lock(&rm->rm_lock);
-
-	_dpu_rm_release_reservation(rm, enc->base.id);
-
-	mutex_unlock(&rm->rm_lock);
+	_dpu_rm_clear_mapping(global_state->pingpong_to_enc_id,
+		ARRAY_SIZE(global_state->pingpong_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->mixer_to_enc_id,
+		ARRAY_SIZE(global_state->mixer_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->ctl_to_enc_id,
+		ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->intf_to_enc_id,
+		ARRAY_SIZE(global_state->intf_to_enc_id), enc->base.id);
 }
 
 int dpu_rm_reserve(
 		struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
 		struct drm_encoder *enc,
 		struct drm_crtc_state *crtc_state,
-		struct msm_display_topology topology,
-		bool test_only)
+		struct msm_display_topology topology)
 {
 	struct dpu_rm_requirements reqs;
 	int ret;
@@ -616,31 +508,75 @@ int dpu_rm_reserve(
 	if (!drm_atomic_crtc_needs_modeset(crtc_state))
 		return 0;
 
-	DRM_DEBUG_KMS("reserving hw for enc %d crtc %d test_only %d\n",
-		      enc->base.id, crtc_state->crtc->base.id, test_only);
+	if (IS_ERR(global_state)) {
+		DPU_ERROR("failed to global state\n");
+		return PTR_ERR(global_state);
+	}
 
-	mutex_lock(&rm->rm_lock);
+	DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n",
+		      enc->base.id, crtc_state->crtc->base.id);
 
-	ret = _dpu_rm_populate_requirements(rm, enc, crtc_state, &reqs,
-					    topology);
+	ret = _dpu_rm_populate_requirements(enc, &reqs, topology);
 	if (ret) {
 		DPU_ERROR("failed to populate hw requirements\n");
-		goto end;
+		return ret;
 	}
 
-	ret = _dpu_rm_make_reservation(rm, enc, crtc_state, &reqs);
-	if (ret) {
+	ret = _dpu_rm_make_reservation(rm, global_state, enc, &reqs);
+	if (ret)
 		DPU_ERROR("failed to reserve hw resources: %d\n", ret);
-		_dpu_rm_release_reservation(rm, enc->base.id);
-	} else if (test_only) {
-		 /* test_only: test the reservation and then undo */
-		DPU_DEBUG("test_only: discard test [enc: %d]\n",
-				enc->base.id);
-		_dpu_rm_release_reservation(rm, enc->base.id);
-	}
 
-end:
-	mutex_unlock(&rm->rm_lock);
+
 
 	return ret;
 }
+
+int dpu_rm_get_assigned_resources(struct dpu_rm *rm,
+	struct dpu_global_state *global_state, uint32_t enc_id,
+	enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size)
+{
+	struct dpu_hw_blk **hw_blks;
+	uint32_t *hw_to_enc_id;
+	int i, num_blks, max_blks;
+
+	switch (type) {
+	case DPU_HW_BLK_PINGPONG:
+		hw_blks = rm->pingpong_blks;
+		hw_to_enc_id = global_state->pingpong_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->pingpong_blks);
+		break;
+	case DPU_HW_BLK_LM:
+		hw_blks = rm->mixer_blks;
+		hw_to_enc_id = global_state->mixer_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->mixer_blks);
+		break;
+	case DPU_HW_BLK_CTL:
+		hw_blks = rm->ctl_blks;
+		hw_to_enc_id = global_state->ctl_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->ctl_blks);
+		break;
+	case DPU_HW_BLK_INTF:
+		hw_blks = rm->intf_blks;
+		hw_to_enc_id = global_state->intf_to_enc_id;
+		max_blks = ARRAY_SIZE(rm->intf_blks);
+		break;
+	default:
+		DPU_ERROR("blk type %d not managed by rm\n", type);
+		return 0;
+	}
+
+	num_blks = 0;
+	for (i = 0; i < max_blks; i++) {
+		if (hw_to_enc_id[i] != enc_id)
+			continue;
+
+		if (num_blks == blks_size) {
+			DPU_ERROR("More than %d resources assigned to enc %d\n",
+				  blks_size, enc_id);
+			break;
+		}
+		blks[num_blks++] = hw_blks[i];
+	}
+
+	return num_blks;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
index 9c580a017094..6d2b04f306f0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -11,37 +11,24 @@
 #include "msm_kms.h"
 #include "dpu_hw_top.h"
 
+struct dpu_global_state;
+
 /**
  * struct dpu_rm - DPU dynamic hardware resource manager
- * @hw_blks: array of lists of hardware resources present in the system, one
- *	list per type of hardware block
+ * @pingpong_blks: array of pingpong hardware resources
+ * @mixer_blks: array of layer mixer hardware resources
+ * @ctl_blks: array of ctl hardware resources
+ * @intf_blks: array of intf hardware resources
  * @lm_max_width: cached layer mixer maximum width
  * @rm_lock: resource manager mutex
  */
 struct dpu_rm {
-	struct list_head hw_blks[DPU_HW_BLK_MAX];
-	uint32_t lm_max_width;
-	struct mutex rm_lock;
-};
+	struct dpu_hw_blk *pingpong_blks[PINGPONG_MAX - PINGPONG_0];
+	struct dpu_hw_blk *mixer_blks[LM_MAX - LM_0];
+	struct dpu_hw_blk *ctl_blks[CTL_MAX - CTL_0];
+	struct dpu_hw_blk *intf_blks[INTF_MAX - INTF_0];
 
-/**
- *  struct dpu_rm_hw_blk - resource manager internal structure
- *	forward declaration for single iterator definition without void pointer
- */
-struct dpu_rm_hw_blk;
-
-/**
- * struct dpu_rm_hw_iter - iterator for use with dpu_rm
- * @hw: dpu_hw object requested, or NULL on failure
- * @blk: dpu_rm internal block representation. Clients ignore. Used as iterator.
- * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
- * @type: Hardware Block Type client wishes to search for.
- */
-struct dpu_rm_hw_iter {
-	void *hw;
-	struct dpu_rm_hw_blk *blk;
-	uint32_t enc_id;
-	enum dpu_hw_blk_type type;
+	uint32_t lm_max_width;
 };
 
 /**
@@ -74,14 +61,13 @@ int dpu_rm_destroy(struct dpu_rm *rm);
  * @drm_enc: DRM Encoder handle
  * @crtc_state: Proposed Atomic DRM CRTC State handle
  * @topology: Pointer to topology info for the display
- * @test_only: Atomic-Test phase, discard results (unless property overrides)
  * @Return: 0 on Success otherwise -ERROR
  */
 int dpu_rm_reserve(struct dpu_rm *rm,
+		struct dpu_global_state *global_state,
 		struct drm_encoder *drm_enc,
 		struct drm_crtc_state *crtc_state,
-		struct msm_display_topology topology,
-		bool test_only);
+		struct msm_display_topology topology);
 
 /**
  * dpu_rm_reserve - Given the encoder for the display chain, release any
@@ -90,31 +76,14 @@ int dpu_rm_reserve(struct dpu_rm *rm,
  * @enc: DRM Encoder handle
  * @Return: 0 on Success otherwise -ERROR
  */
-void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc);
+void dpu_rm_release(struct dpu_global_state *global_state,
+		struct drm_encoder *enc);
 
 /**
- * dpu_rm_init_hw_iter - setup given iterator for new iteration over hw list
- *	using dpu_rm_get_hw
- * @iter: iter object to initialize
- * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
- * @type: Hardware Block Type client wishes to search for.
- */
-void dpu_rm_init_hw_iter(
-		struct dpu_rm_hw_iter *iter,
-		uint32_t enc_id,
-		enum dpu_hw_blk_type type);
-/**
- * dpu_rm_get_hw - retrieve reserved hw object given encoder and hw type
- *	Meant to do a single pass through the hardware list to iteratively
- *	retrieve hardware blocks of a given type for a given encoder.
- *	Initialize an iterator object.
- *	Set hw block type of interest. Set encoder id of interest, 0 for any.
- *	Function returns first hw of type for that encoder.
- *	Subsequent calls will return the next reserved hw of that type in-order.
- *	Iterator HW pointer will be null on failure to find hw.
- * @rm: DPU Resource Manager handle
- * @iter: iterator object
- * @Return: true on match found, false on no match found
+ * Get hw resources of the given type that are assigned to this encoder.
  */
-bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *iter);
+int dpu_rm_get_assigned_resources(struct dpu_rm *rm,
+	struct dpu_global_state *global_state, uint32_t enc_id,
+	enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size);
 #endif /* __DPU_RM_H__ */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 93ab36bd8df3..5e8c3f3e6625 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -24,7 +24,7 @@ static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id)
 	int rc;
 
 	if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) {
-		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != NULL);
 		return -EINVAL;
 	}
 
@@ -106,7 +106,7 @@ static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif,
 	u32 val;
 
 	if (!vbif || !vbif->cap) {
-		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != NULL);
 		return -EINVAL;
 	}
 
@@ -164,7 +164,7 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 
 	if (!vbif || !mdp) {
 		DPU_DEBUG("invalid arguments vbif %d mdp %d\n",
-				vbif != 0, mdp != 0);
+				vbif != NULL, mdp != NULL);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index b3d0a0fe76b9..998bef1190a3 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1191,8 +1191,8 @@ static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc)
 	ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion,
 						msecs_to_jiffies(50));
 	if (ret == 0)
-		dev_warn(dev->dev, "pp done time out, lm=%d\n",
-			 mdp5_cstate->pipeline.mixer->lm);
+		dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n",
+				     mdp5_cstate->pipeline.mixer->lm);
 }
 
 static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 6af26ab5b09d..4b363bd7ddff 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -336,7 +336,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 	return num;
 }
 
-static int dsi_mgr_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	int id = dsi_mgr_connector_get_id(connector);
@@ -506,6 +506,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
+	struct msm_dsi_pll *src_pll;
 	bool is_dual_dsi = IS_DUAL_DSI();
 	int ret;
 
@@ -539,6 +540,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 								id, ret);
 	}
 
+	/* Save PLL status if it is a clock source */
+	src_pll = msm_dsi_phy_get_pll(msm_dsi->phy);
+	msm_dsi_pll_save_state(src_pll);
+
 	ret = msm_dsi_host_power_off(host);
 	if (ret)
 		pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index b0cfa67d2a57..f509ebd77500 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -724,10 +724,6 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy)
 	if (!phy || !phy->cfg->ops.disable)
 		return;
 
-	/* Save PLL status if it is a clock source */
-	if (phy->usecase != MSM_DSI_PHY_SLAVE)
-		msm_dsi_pll_save_state(phy->pll);
-
 	phy->cfg->ops.disable(phy);
 
 	dsi_phy_regulator_disable(phy);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index 1c894548dd72..6ac04fc303f5 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -411,6 +411,12 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw)
 	if (pll_10nm->slave)
 		dsi_pll_enable_pll_bias(pll_10nm->slave);
 
+	rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
+	if (rc) {
+		pr_err("vco_set_rate failed, rc=%d\n", rc);
+		return rc;
+	}
+
 	/* Start PLL */
 	pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL,
 		  0x01);
diff --git a/drivers/gpu/drm/msm/edp/edp.c b/drivers/gpu/drm/msm/edp/edp.c
index a78d6077802b..106a67473af5 100644
--- a/drivers/gpu/drm/msm/edp/edp.c
+++ b/drivers/gpu/drm/msm/edp/edp.c
@@ -178,10 +178,6 @@ int msm_edp_modeset_init(struct msm_edp *edp, struct drm_device *dev,
 		goto fail;
 	}
 
-	ret = drm_bridge_attach(encoder, edp->bridge, NULL, 0);
-	if (ret)
-		goto fail;
-
 	priv->bridges[priv->num_bridges++]       = edp->bridge;
 	priv->connectors[priv->num_connectors++] = edp->connector;
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index 3a8646535c14..737453b6e596 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -327,10 +327,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 		goto fail;
 	}
 
-	ret = drm_bridge_attach(encoder, hdmi->bridge, NULL, 0);
-	if (ret)
-		goto fail;
-
 	priv->bridges[priv->num_bridges++]       = hdmi->bridge;
 	priv->connectors[priv->num_connectors++] = hdmi->connector;
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 2a82c23a6e4d..29295dee2a2e 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -444,8 +444,10 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	if (!dev->dma_parms) {
 		dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms),
 					      GFP_KERNEL);
-		if (!dev->dma_parms)
-			return -ENOMEM;
+		if (!dev->dma_parms) {
+			ret = -ENOMEM;
+			goto err_msm_uninit;
+		}
 	}
 	dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
 
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 9e0953c2b7ce..30584eaf8cc8 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -157,7 +157,17 @@ struct msm_gem_submit {
 			uint32_t handle;
 		};
 		uint64_t iova;
-	} bos[0];
+	} bos[];
 };
 
+/* helper to determine of a buffer in submit should be dumped, used for both
+ * devcoredump and debugfs cmdstream dumping:
+ */
+static inline bool
+should_dump(struct msm_gem_submit *submit, int idx)
+{
+	extern bool rd_full;
+	return rd_full || (submit->bos[idx].flags & MSM_SUBMIT_BO_DUMP);
+}
+
 #endif /* __MSM_GEM_H__ */
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 18f3a5c53ffb..615c5cda5389 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -355,16 +355,34 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	state->cmd = kstrdup(cmd, GFP_KERNEL);
 
 	if (submit) {
-		int i;
-
-		state->bos = kcalloc(submit->nr_cmds,
+		int i, nr = 0;
+
+		/* count # of buffers to dump: */
+		for (i = 0; i < submit->nr_bos; i++)
+			if (should_dump(submit, i))
+				nr++;
+		/* always dump cmd bo's, but don't double count them: */
+		for (i = 0; i < submit->nr_cmds; i++)
+			if (!should_dump(submit, submit->cmd[i].idx))
+				nr++;
+
+		state->bos = kcalloc(nr,
 			sizeof(struct msm_gpu_state_bo), GFP_KERNEL);
 
+		for (i = 0; i < submit->nr_bos; i++) {
+			if (should_dump(submit, i)) {
+				msm_gpu_crashstate_get_bo(state, submit->bos[i].obj,
+					submit->bos[i].iova, submit->bos[i].flags);
+			}
+		}
+
 		for (i = 0; state->bos && i < submit->nr_cmds; i++) {
 			int idx = submit->cmd[i].idx;
 
-			msm_gpu_crashstate_get_bo(state, submit->bos[idx].obj,
-				submit->bos[idx].iova, submit->bos[idx].flags);
+			if (!should_dump(submit, submit->cmd[i].idx)) {
+				msm_gpu_crashstate_get_bo(state, submit->bos[idx].obj,
+					submit->bos[idx].iova, submit->bos[idx].flags);
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index af7ceb246c7c..732f65df5c4f 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -43,7 +43,7 @@
 #include "msm_gpu.h"
 #include "msm_gem.h"
 
-static bool rd_full = false;
+bool rd_full = false;
 MODULE_PARM_DESC(rd_full, "If true, $debugfs/.../rd will snapshot all buffer contents");
 module_param_named(rd_full, rd_full, bool, 0600);
 
@@ -336,12 +336,6 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	msm_gem_put_vaddr(&obj->base);
 }
 
-static bool
-should_dump(struct msm_gem_submit *submit, int idx)
-{
-	return rd_full || (submit->bos[idx].flags & MSM_SUBMIT_BO_DUMP);
-}
-
 /* called under struct_mutex */
 void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit,
 		const char *fmt, ...)