Merge tag 'drm-msm-next-2018-12-12' of git://people.freedesktop.org/~robclark/linux into drm-next

This time around, seeing some love for some older hw: - a2xx gpu support for apq8060 (hp touchpad) and imx5 (headless gpu-only mode) - a2xx gpummu support (a2xx was pre-iommu) - mdp4 display support for apq8060/touchpad For display/dpu: - a big pile of continuing dpu fixes and cleanups On the gpu side of things: - per-submit statistics and traceevents for better profiling - a6xx crashdump support - decouple get_iova() and page pinning.. so we can unpin from physical memory inactive bo's while using softpin to lower cpu overhead - new interface to set debug names on GEM BOs and debugfs output improvements - additional submit flag to indicate buffers that are used to dump (so $debugfs/rd cmdstream dumping is useful with softpin + state-objects) Signed-off-by: Dave Airlie <airlied@redhat.com> From: Rob Clark <robdclark@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvVvLPD9_Z4kyfGe98Y--byj6HbxHivEYSgF7Rq7=bFnw@mail.gmail.com
author: Dave Airlie <airlied@redhat.com> 2018-12-13 01:29:14 +0100
committer: Dave Airlie <airlied@redhat.com> 2018-12-13 01:29:30 +0100
commit: d675ba4b9e6ccd782e4db9109cbab708a85b8ff8 (patch)
tree: e488f7fc7e13f87a3b9e04c31aadb04a6a6ca43c /drivers/gpu
parent: Merge branch 'linux-4.21' of git://github.com/skeggsb/linux into drm-next (diff)
parent: drm/msm/dpu: Fix clock issue after bind failure (diff)
download: linux-d675ba4b9e6ccd782e4db9109cbab708a85b8ff8.tar.xz
linux-d675ba4b9e6ccd782e4db9109cbab708a85b8ff8.zip
125 files changed, 4566 insertions, 5493 deletions
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 843a9d40c05e..cf549f1ed403 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -2,7 +2,7 @@
 config DRM_MSM
 	tristate "MSM DRM"
 	depends on DRM
-	depends on ARCH_QCOM || (ARM && COMPILE_TEST)
+	depends on ARCH_QCOM || SOC_IMX5 || (ARM && COMPILE_TEST)
 	depends on OF && COMMON_CLK
 	depends on MMU
 	select QCOM_MDT_LOADER if ARCH_QCOM
@@ -11,7 +11,7 @@ config DRM_MSM
 	select DRM_PANEL
 	select SHMEM
 	select TMPFS
-	select QCOM_SCM
+	select QCOM_SCM if ARCH_QCOM
 	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 19ab521d4c3a..56a70c74af4e 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -6,6 +6,7 @@ ccflags-$(CONFIG_DRM_MSM_DSI) += -Idrivers/gpu/drm/msm/dsi
 msm-y := \
 	adreno/adreno_device.o \
 	adreno/adreno_gpu.o \
+	adreno/a2xx_gpu.o \
 	adreno/a3xx_gpu.o \
 	adreno/a4xx_gpu.o \
 	adreno/a5xx_gpu.o \
@@ -14,6 +15,7 @@ msm-y := \
 	adreno/a6xx_gpu.o \
 	adreno/a6xx_gmu.o \
 	adreno/a6xx_hfi.o \
+	adreno/a6xx_gpu_state.o \
 	hdmi/hdmi.o \
 	hdmi/hdmi_audio.o \
 	hdmi/hdmi_bridge.o \
@@ -68,11 +70,9 @@ msm-y := \
 	disp/dpu1/dpu_hw_util.o \
 	disp/dpu1/dpu_hw_vbif.o \
 	disp/dpu1/dpu_io_util.o \
-	disp/dpu1/dpu_irq.o \
 	disp/dpu1/dpu_kms.o \
 	disp/dpu1/dpu_mdss.o \
 	disp/dpu1/dpu_plane.o \
-	disp/dpu1/dpu_power_handle.o \
 	disp/dpu1/dpu_rm.o \
 	disp/dpu1/dpu_vbif.o \
 	msm_atomic.o \
@@ -90,10 +90,11 @@ msm-y := \
 	msm_perf.o \
 	msm_rd.o \
 	msm_ringbuffer.o \
-	msm_submitqueue.o
+	msm_submitqueue.o \
+	msm_gpu_tracepoints.o \
+	msm_gpummu.o
 
-msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \
-			  disp/dpu1/dpu_dbg.o
+msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o
 
 msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o
 msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o
diff --git a/drivers/gpu/drm/msm/adreno/a2xx.xml.h b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
index 12b0ba270b5e..14eb52f3e605 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
@@ -239,7 +239,63 @@ enum sq_tex_swiz {
 enum sq_tex_filter {
 	SQ_TEX_FILTER_POINT = 0,
 	SQ_TEX_FILTER_BILINEAR = 1,
-	SQ_TEX_FILTER_BICUBIC = 2,
+	SQ_TEX_FILTER_BASEMAP = 2,
+	SQ_TEX_FILTER_USE_FETCH_CONST = 3,
+};
+
+enum sq_tex_aniso_filter {
+	SQ_TEX_ANISO_FILTER_DISABLED = 0,
+	SQ_TEX_ANISO_FILTER_MAX_1_1 = 1,
+	SQ_TEX_ANISO_FILTER_MAX_2_1 = 2,
+	SQ_TEX_ANISO_FILTER_MAX_4_1 = 3,
+	SQ_TEX_ANISO_FILTER_MAX_8_1 = 4,
+	SQ_TEX_ANISO_FILTER_MAX_16_1 = 5,
+	SQ_TEX_ANISO_FILTER_USE_FETCH_CONST = 7,
+};
+
+enum sq_tex_dimension {
+	SQ_TEX_DIMENSION_1D = 0,
+	SQ_TEX_DIMENSION_2D = 1,
+	SQ_TEX_DIMENSION_3D = 2,
+	SQ_TEX_DIMENSION_CUBE = 3,
+};
+
+enum sq_tex_border_color {
+	SQ_TEX_BORDER_COLOR_BLACK = 0,
+	SQ_TEX_BORDER_COLOR_WHITE = 1,
+	SQ_TEX_BORDER_COLOR_ACBYCR_BLACK = 2,
+	SQ_TEX_BORDER_COLOR_ACBCRY_BLACK = 3,
+};
+
+enum sq_tex_sign {
+	SQ_TEX_SIGN_UNISIGNED = 0,
+	SQ_TEX_SIGN_SIGNED = 1,
+	SQ_TEX_SIGN_UNISIGNED_BIASED = 2,
+	SQ_TEX_SIGN_GAMMA = 3,
+};
+
+enum sq_tex_endian {
+	SQ_TEX_ENDIAN_NONE = 0,
+	SQ_TEX_ENDIAN_8IN16 = 1,
+	SQ_TEX_ENDIAN_8IN32 = 2,
+	SQ_TEX_ENDIAN_16IN32 = 3,
+};
+
+enum sq_tex_clamp_policy {
+	SQ_TEX_CLAMP_POLICY_D3D = 0,
+	SQ_TEX_CLAMP_POLICY_OGL = 1,
+};
+
+enum sq_tex_num_format {
+	SQ_TEX_NUM_FORMAT_FRAC = 0,
+	SQ_TEX_NUM_FORMAT_INT = 1,
+};
+
+enum sq_tex_type {
+	SQ_TEX_TYPE_0 = 0,
+	SQ_TEX_TYPE_1 = 1,
+	SQ_TEX_TYPE_2 = 2,
+	SQ_TEX_TYPE_3 = 3,
 };
 
 #define REG_A2XX_RBBM_PATCH_RELEASE				0x00000001
@@ -323,6 +379,18 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln
 }
 
 #define REG_A2XX_MH_MMU_VA_RANGE				0x00000041
+#define A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__MASK		0x00000fff
+#define A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__SHIFT		0
+static inline uint32_t A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS(uint32_t val)
+{
+	return ((val) << A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__SHIFT) & A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS__MASK;
+}
+#define A2XX_MH_MMU_VA_RANGE_VA_BASE__MASK			0xfffff000
+#define A2XX_MH_MMU_VA_RANGE_VA_BASE__SHIFT			12
+static inline uint32_t A2XX_MH_MMU_VA_RANGE_VA_BASE(uint32_t val)
+{
+	return ((val) << A2XX_MH_MMU_VA_RANGE_VA_BASE__SHIFT) & A2XX_MH_MMU_VA_RANGE_VA_BASE__MASK;
+}
 
 #define REG_A2XX_MH_MMU_PT_BASE					0x00000042
 
@@ -331,6 +399,8 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln
 #define REG_A2XX_MH_MMU_TRAN_ERROR				0x00000044
 
 #define REG_A2XX_MH_MMU_INVALIDATE				0x00000045
+#define A2XX_MH_MMU_INVALIDATE_INVALIDATE_ALL			0x00000001
+#define A2XX_MH_MMU_INVALIDATE_INVALIDATE_TC			0x00000002
 
 #define REG_A2XX_MH_MMU_MPU_BASE				0x00000046
 
@@ -389,12 +459,19 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln
 #define REG_A2XX_RBBM_READ_ERROR				0x000003b3
 
 #define REG_A2XX_RBBM_INT_CNTL					0x000003b4
+#define A2XX_RBBM_INT_CNTL_RDERR_INT_MASK			0x00000001
+#define A2XX_RBBM_INT_CNTL_DISPLAY_UPDATE_INT_MASK		0x00000002
+#define A2XX_RBBM_INT_CNTL_GUI_IDLE_INT_MASK			0x00080000
 
 #define REG_A2XX_RBBM_INT_STATUS				0x000003b5
 
 #define REG_A2XX_RBBM_INT_ACK					0x000003b6
 
 #define REG_A2XX_MASTER_INT_SIGNAL				0x000003b7
+#define A2XX_MASTER_INT_SIGNAL_MH_INT_STAT			0x00000020
+#define A2XX_MASTER_INT_SIGNAL_SQ_INT_STAT			0x04000000
+#define A2XX_MASTER_INT_SIGNAL_CP_INT_STAT			0x40000000
+#define A2XX_MASTER_INT_SIGNAL_RBBM_INT_STAT			0x80000000
 
 #define REG_A2XX_RBBM_PERIPHID1					0x000003f9
 
@@ -467,6 +544,19 @@ static inline uint32_t A2XX_MH_ARBITER_CONFIG_IN_FLIGHT_LIMIT(uint32_t val)
 #define A2XX_MH_ARBITER_CONFIG_RB_CLNT_ENABLE			0x02000000
 #define A2XX_MH_ARBITER_CONFIG_PA_CLNT_ENABLE			0x04000000
 
+#define REG_A2XX_MH_INTERRUPT_MASK				0x00000a42
+#define A2XX_MH_INTERRUPT_MASK_AXI_READ_ERROR			0x00000001
+#define A2XX_MH_INTERRUPT_MASK_AXI_WRITE_ERROR			0x00000002
+#define A2XX_MH_INTERRUPT_MASK_MMU_PAGE_FAULT			0x00000004
+
+#define REG_A2XX_MH_INTERRUPT_STATUS				0x00000a43
+
+#define REG_A2XX_MH_INTERRUPT_CLEAR				0x00000a44
+
+#define REG_A2XX_MH_CLNT_INTF_CTRL_CONFIG1			0x00000a54
+
+#define REG_A2XX_MH_CLNT_INTF_CTRL_CONFIG2			0x00000a55
+
 #define REG_A2XX_A220_VSC_BIN_SIZE				0x00000c01
 #define A2XX_A220_VSC_BIN_SIZE_WIDTH__MASK			0x0000001f
 #define A2XX_A220_VSC_BIN_SIZE_WIDTH__SHIFT			0
@@ -648,6 +738,18 @@ static inline uint32_t A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT(uint32_t val
 #define REG_A2XX_RB_DEBUG_DATA					0x00000f27
 
 #define REG_A2XX_RB_SURFACE_INFO				0x00002000
+#define A2XX_RB_SURFACE_INFO_SURFACE_PITCH__MASK		0x00003fff
+#define A2XX_RB_SURFACE_INFO_SURFACE_PITCH__SHIFT		0
+static inline uint32_t A2XX_RB_SURFACE_INFO_SURFACE_PITCH(uint32_t val)
+{
+	return ((val) << A2XX_RB_SURFACE_INFO_SURFACE_PITCH__SHIFT) & A2XX_RB_SURFACE_INFO_SURFACE_PITCH__MASK;
+}
+#define A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__MASK			0x0000c000
+#define A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__SHIFT		14
+static inline uint32_t A2XX_RB_SURFACE_INFO_MSAA_SAMPLES(uint32_t val)
+{
+	return ((val) << A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__SHIFT) & A2XX_RB_SURFACE_INFO_MSAA_SAMPLES__MASK;
+}
 
 #define REG_A2XX_RB_COLOR_INFO					0x00002001
 #define A2XX_RB_COLOR_INFO_FORMAT__MASK				0x0000000f
@@ -679,7 +781,7 @@ static inline uint32_t A2XX_RB_COLOR_INFO_SWAP(uint32_t val)
 #define A2XX_RB_COLOR_INFO_BASE__SHIFT				12
 static inline uint32_t A2XX_RB_COLOR_INFO_BASE(uint32_t val)
 {
-	return ((val >> 10) << A2XX_RB_COLOR_INFO_BASE__SHIFT) & A2XX_RB_COLOR_INFO_BASE__MASK;
+	return ((val >> 12) << A2XX_RB_COLOR_INFO_BASE__SHIFT) & A2XX_RB_COLOR_INFO_BASE__MASK;
 }
 
 #define REG_A2XX_RB_DEPTH_INFO					0x00002002
@@ -693,7 +795,7 @@ static inline uint32_t A2XX_RB_DEPTH_INFO_DEPTH_FORMAT(enum adreno_rb_depth_form
 #define A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT			12
 static inline uint32_t A2XX_RB_DEPTH_INFO_DEPTH_BASE(uint32_t val)
 {
-	return ((val >> 10) << A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT) & A2XX_RB_DEPTH_INFO_DEPTH_BASE__MASK;
+	return ((val >> 12) << A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT) & A2XX_RB_DEPTH_INFO_DEPTH_BASE__MASK;
 }
 
 #define REG_A2XX_A225_RB_COLOR_INFO3				0x00002005
@@ -1757,6 +1859,36 @@ static inline uint32_t A2XX_RB_COPY_DEST_OFFSET_Y(uint32_t val)
 #define REG_A2XX_COHER_STATUS_PM4				0x00000a2b
 
 #define REG_A2XX_SQ_TEX_0					0x00000000
+#define A2XX_SQ_TEX_0_TYPE__MASK				0x00000003
+#define A2XX_SQ_TEX_0_TYPE__SHIFT				0
+static inline uint32_t A2XX_SQ_TEX_0_TYPE(enum sq_tex_type val)
+{
+	return ((val) << A2XX_SQ_TEX_0_TYPE__SHIFT) & A2XX_SQ_TEX_0_TYPE__MASK;
+}
+#define A2XX_SQ_TEX_0_SIGN_X__MASK				0x0000000c
+#define A2XX_SQ_TEX_0_SIGN_X__SHIFT				2
+static inline uint32_t A2XX_SQ_TEX_0_SIGN_X(enum sq_tex_sign val)
+{
+	return ((val) << A2XX_SQ_TEX_0_SIGN_X__SHIFT) & A2XX_SQ_TEX_0_SIGN_X__MASK;
+}
+#define A2XX_SQ_TEX_0_SIGN_Y__MASK				0x00000030
+#define A2XX_SQ_TEX_0_SIGN_Y__SHIFT				4
+static inline uint32_t A2XX_SQ_TEX_0_SIGN_Y(enum sq_tex_sign val)
+{
+	return ((val) << A2XX_SQ_TEX_0_SIGN_Y__SHIFT) & A2XX_SQ_TEX_0_SIGN_Y__MASK;
+}
+#define A2XX_SQ_TEX_0_SIGN_Z__MASK				0x000000c0
+#define A2XX_SQ_TEX_0_SIGN_Z__SHIFT				6
+static inline uint32_t A2XX_SQ_TEX_0_SIGN_Z(enum sq_tex_sign val)
+{
+	return ((val) << A2XX_SQ_TEX_0_SIGN_Z__SHIFT) & A2XX_SQ_TEX_0_SIGN_Z__MASK;
+}
+#define A2XX_SQ_TEX_0_SIGN_W__MASK				0x00000300
+#define A2XX_SQ_TEX_0_SIGN_W__SHIFT				8
+static inline uint32_t A2XX_SQ_TEX_0_SIGN_W(enum sq_tex_sign val)
+{
+	return ((val) << A2XX_SQ_TEX_0_SIGN_W__SHIFT) & A2XX_SQ_TEX_0_SIGN_W__MASK;
+}
 #define A2XX_SQ_TEX_0_CLAMP_X__MASK				0x00001c00
 #define A2XX_SQ_TEX_0_CLAMP_X__SHIFT				10
 static inline uint32_t A2XX_SQ_TEX_0_CLAMP_X(enum sq_tex_clamp val)
@@ -1775,14 +1907,46 @@ static inline uint32_t A2XX_SQ_TEX_0_CLAMP_Z(enum sq_tex_clamp val)
 {
 	return ((val) << A2XX_SQ_TEX_0_CLAMP_Z__SHIFT) & A2XX_SQ_TEX_0_CLAMP_Z__MASK;
 }
-#define A2XX_SQ_TEX_0_PITCH__MASK				0xffc00000
+#define A2XX_SQ_TEX_0_PITCH__MASK				0x7fc00000
 #define A2XX_SQ_TEX_0_PITCH__SHIFT				22
 static inline uint32_t A2XX_SQ_TEX_0_PITCH(uint32_t val)
 {
 	return ((val >> 5) << A2XX_SQ_TEX_0_PITCH__SHIFT) & A2XX_SQ_TEX_0_PITCH__MASK;
 }
+#define A2XX_SQ_TEX_0_TILED					0x00000002
 
 #define REG_A2XX_SQ_TEX_1					0x00000001
+#define A2XX_SQ_TEX_1_FORMAT__MASK				0x0000003f
+#define A2XX_SQ_TEX_1_FORMAT__SHIFT				0
+static inline uint32_t A2XX_SQ_TEX_1_FORMAT(enum a2xx_sq_surfaceformat val)
+{
+	return ((val) << A2XX_SQ_TEX_1_FORMAT__SHIFT) & A2XX_SQ_TEX_1_FORMAT__MASK;
+}
+#define A2XX_SQ_TEX_1_ENDIANNESS__MASK				0x000000c0
+#define A2XX_SQ_TEX_1_ENDIANNESS__SHIFT				6
+static inline uint32_t A2XX_SQ_TEX_1_ENDIANNESS(enum sq_tex_endian val)
+{
+	return ((val) << A2XX_SQ_TEX_1_ENDIANNESS__SHIFT) & A2XX_SQ_TEX_1_ENDIANNESS__MASK;
+}
+#define A2XX_SQ_TEX_1_REQUEST_SIZE__MASK			0x00000300
+#define A2XX_SQ_TEX_1_REQUEST_SIZE__SHIFT			8
+static inline uint32_t A2XX_SQ_TEX_1_REQUEST_SIZE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_1_REQUEST_SIZE__SHIFT) & A2XX_SQ_TEX_1_REQUEST_SIZE__MASK;
+}
+#define A2XX_SQ_TEX_1_STACKED					0x00000400
+#define A2XX_SQ_TEX_1_CLAMP_POLICY__MASK			0x00000800
+#define A2XX_SQ_TEX_1_CLAMP_POLICY__SHIFT			11
+static inline uint32_t A2XX_SQ_TEX_1_CLAMP_POLICY(enum sq_tex_clamp_policy val)
+{
+	return ((val) << A2XX_SQ_TEX_1_CLAMP_POLICY__SHIFT) & A2XX_SQ_TEX_1_CLAMP_POLICY__MASK;
+}
+#define A2XX_SQ_TEX_1_BASE_ADDRESS__MASK			0xfffff000
+#define A2XX_SQ_TEX_1_BASE_ADDRESS__SHIFT			12
+static inline uint32_t A2XX_SQ_TEX_1_BASE_ADDRESS(uint32_t val)
+{
+	return ((val >> 12) << A2XX_SQ_TEX_1_BASE_ADDRESS__SHIFT) & A2XX_SQ_TEX_1_BASE_ADDRESS__MASK;
+}
 
 #define REG_A2XX_SQ_TEX_2					0x00000002
 #define A2XX_SQ_TEX_2_WIDTH__MASK				0x00001fff
@@ -1797,8 +1961,20 @@ static inline uint32_t A2XX_SQ_TEX_2_HEIGHT(uint32_t val)
 {
 	return ((val) << A2XX_SQ_TEX_2_HEIGHT__SHIFT) & A2XX_SQ_TEX_2_HEIGHT__MASK;
 }
+#define A2XX_SQ_TEX_2_DEPTH__MASK				0xfc000000
+#define A2XX_SQ_TEX_2_DEPTH__SHIFT				26
+static inline uint32_t A2XX_SQ_TEX_2_DEPTH(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_2_DEPTH__SHIFT) & A2XX_SQ_TEX_2_DEPTH__MASK;
+}
 
 #define REG_A2XX_SQ_TEX_3					0x00000003
+#define A2XX_SQ_TEX_3_NUM_FORMAT__MASK				0x00000001
+#define A2XX_SQ_TEX_3_NUM_FORMAT__SHIFT				0
+static inline uint32_t A2XX_SQ_TEX_3_NUM_FORMAT(enum sq_tex_num_format val)
+{
+	return ((val) << A2XX_SQ_TEX_3_NUM_FORMAT__SHIFT) & A2XX_SQ_TEX_3_NUM_FORMAT__MASK;
+}
 #define A2XX_SQ_TEX_3_SWIZ_X__MASK				0x0000000e
 #define A2XX_SQ_TEX_3_SWIZ_X__SHIFT				1
 static inline uint32_t A2XX_SQ_TEX_3_SWIZ_X(enum sq_tex_swiz val)
@@ -1823,6 +1999,12 @@ static inline uint32_t A2XX_SQ_TEX_3_SWIZ_W(enum sq_tex_swiz val)
 {
 	return ((val) << A2XX_SQ_TEX_3_SWIZ_W__SHIFT) & A2XX_SQ_TEX_3_SWIZ_W__MASK;
 }
+#define A2XX_SQ_TEX_3_EXP_ADJUST__MASK				0x0007e000
+#define A2XX_SQ_TEX_3_EXP_ADJUST__SHIFT				13
+static inline uint32_t A2XX_SQ_TEX_3_EXP_ADJUST(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_3_EXP_ADJUST__SHIFT) & A2XX_SQ_TEX_3_EXP_ADJUST__MASK;
+}
 #define A2XX_SQ_TEX_3_XY_MAG_FILTER__MASK			0x00180000
 #define A2XX_SQ_TEX_3_XY_MAG_FILTER__SHIFT			19
 static inline uint32_t A2XX_SQ_TEX_3_XY_MAG_FILTER(enum sq_tex_filter val)
@@ -1835,6 +2017,104 @@ static inline uint32_t A2XX_SQ_TEX_3_XY_MIN_FILTER(enum sq_tex_filter val)
 {
 	return ((val) << A2XX_SQ_TEX_3_XY_MIN_FILTER__SHIFT) & A2XX_SQ_TEX_3_XY_MIN_FILTER__MASK;
 }
+#define A2XX_SQ_TEX_3_MIP_FILTER__MASK				0x01800000
+#define A2XX_SQ_TEX_3_MIP_FILTER__SHIFT				23
+static inline uint32_t A2XX_SQ_TEX_3_MIP_FILTER(enum sq_tex_filter val)
+{
+	return ((val) << A2XX_SQ_TEX_3_MIP_FILTER__SHIFT) & A2XX_SQ_TEX_3_MIP_FILTER__MASK;
+}
+#define A2XX_SQ_TEX_3_ANISO_FILTER__MASK			0x0e000000
+#define A2XX_SQ_TEX_3_ANISO_FILTER__SHIFT			25
+static inline uint32_t A2XX_SQ_TEX_3_ANISO_FILTER(enum sq_tex_aniso_filter val)
+{
+	return ((val) << A2XX_SQ_TEX_3_ANISO_FILTER__SHIFT) & A2XX_SQ_TEX_3_ANISO_FILTER__MASK;
+}
+#define A2XX_SQ_TEX_3_BORDER_SIZE__MASK				0x80000000
+#define A2XX_SQ_TEX_3_BORDER_SIZE__SHIFT			31
+static inline uint32_t A2XX_SQ_TEX_3_BORDER_SIZE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_3_BORDER_SIZE__SHIFT) & A2XX_SQ_TEX_3_BORDER_SIZE__MASK;
+}
+
+#define REG_A2XX_SQ_TEX_4					0x00000004
+#define A2XX_SQ_TEX_4_VOL_MAG_FILTER__MASK			0x00000001
+#define A2XX_SQ_TEX_4_VOL_MAG_FILTER__SHIFT			0
+static inline uint32_t A2XX_SQ_TEX_4_VOL_MAG_FILTER(enum sq_tex_filter val)
+{
+	return ((val) << A2XX_SQ_TEX_4_VOL_MAG_FILTER__SHIFT) & A2XX_SQ_TEX_4_VOL_MAG_FILTER__MASK;
+}
+#define A2XX_SQ_TEX_4_VOL_MIN_FILTER__MASK			0x00000002
+#define A2XX_SQ_TEX_4_VOL_MIN_FILTER__SHIFT			1
+static inline uint32_t A2XX_SQ_TEX_4_VOL_MIN_FILTER(enum sq_tex_filter val)
+{
+	return ((val) << A2XX_SQ_TEX_4_VOL_MIN_FILTER__SHIFT) & A2XX_SQ_TEX_4_VOL_MIN_FILTER__MASK;
+}
+#define A2XX_SQ_TEX_4_MIP_MIN_LEVEL__MASK			0x0000003c
+#define A2XX_SQ_TEX_4_MIP_MIN_LEVEL__SHIFT			2
+static inline uint32_t A2XX_SQ_TEX_4_MIP_MIN_LEVEL(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_4_MIP_MIN_LEVEL__SHIFT) & A2XX_SQ_TEX_4_MIP_MIN_LEVEL__MASK;
+}
+#define A2XX_SQ_TEX_4_MIP_MAX_LEVEL__MASK			0x000003c0
+#define A2XX_SQ_TEX_4_MIP_MAX_LEVEL__SHIFT			6
+static inline uint32_t A2XX_SQ_TEX_4_MIP_MAX_LEVEL(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_4_MIP_MAX_LEVEL__SHIFT) & A2XX_SQ_TEX_4_MIP_MAX_LEVEL__MASK;
+}
+#define A2XX_SQ_TEX_4_MAX_ANISO_WALK				0x00000400
+#define A2XX_SQ_TEX_4_MIN_ANISO_WALK				0x00000800
+#define A2XX_SQ_TEX_4_LOD_BIAS__MASK				0x003ff000
+#define A2XX_SQ_TEX_4_LOD_BIAS__SHIFT				12
+static inline uint32_t A2XX_SQ_TEX_4_LOD_BIAS(float val)
+{
+	return ((((int32_t)(val * 32.0))) << A2XX_SQ_TEX_4_LOD_BIAS__SHIFT) & A2XX_SQ_TEX_4_LOD_BIAS__MASK;
+}
+#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__MASK			0x07c00000
+#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__SHIFT			22
+static inline uint32_t A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__SHIFT) & A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_H__MASK;
+}
+#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__MASK			0xf8000000
+#define A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__SHIFT			27
+static inline uint32_t A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__SHIFT) & A2XX_SQ_TEX_4_GRAD_EXP_ADJUST_V__MASK;
+}
+
+#define REG_A2XX_SQ_TEX_5					0x00000005
+#define A2XX_SQ_TEX_5_BORDER_COLOR__MASK			0x00000003
+#define A2XX_SQ_TEX_5_BORDER_COLOR__SHIFT			0
+static inline uint32_t A2XX_SQ_TEX_5_BORDER_COLOR(enum sq_tex_border_color val)
+{
+	return ((val) << A2XX_SQ_TEX_5_BORDER_COLOR__SHIFT) & A2XX_SQ_TEX_5_BORDER_COLOR__MASK;
+}
+#define A2XX_SQ_TEX_5_FORCE_BCW_MAX				0x00000004
+#define A2XX_SQ_TEX_5_TRI_CLAMP__MASK				0x00000018
+#define A2XX_SQ_TEX_5_TRI_CLAMP__SHIFT				3
+static inline uint32_t A2XX_SQ_TEX_5_TRI_CLAMP(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_5_TRI_CLAMP__SHIFT) & A2XX_SQ_TEX_5_TRI_CLAMP__MASK;
+}
+#define A2XX_SQ_TEX_5_ANISO_BIAS__MASK				0x000001e0
+#define A2XX_SQ_TEX_5_ANISO_BIAS__SHIFT				5
+static inline uint32_t A2XX_SQ_TEX_5_ANISO_BIAS(float val)
+{
+	return ((((int32_t)(val * 1.0))) << A2XX_SQ_TEX_5_ANISO_BIAS__SHIFT) & A2XX_SQ_TEX_5_ANISO_BIAS__MASK;
+}
+#define A2XX_SQ_TEX_5_DIMENSION__MASK				0x00000600
+#define A2XX_SQ_TEX_5_DIMENSION__SHIFT				9
+static inline uint32_t A2XX_SQ_TEX_5_DIMENSION(enum sq_tex_dimension val)
+{
+	return ((val) << A2XX_SQ_TEX_5_DIMENSION__SHIFT) & A2XX_SQ_TEX_5_DIMENSION__MASK;
+}
+#define A2XX_SQ_TEX_5_PACKED_MIPS				0x00000800
+#define A2XX_SQ_TEX_5_MIP_ADDRESS__MASK				0xfffff000
+#define A2XX_SQ_TEX_5_MIP_ADDRESS__SHIFT			12
+static inline uint32_t A2XX_SQ_TEX_5_MIP_ADDRESS(uint32_t val)
+{
+	return ((val >> 12) << A2XX_SQ_TEX_5_MIP_ADDRESS__SHIFT) & A2XX_SQ_TEX_5_MIP_ADDRESS__MASK;
+}
 
 
 #endif /* A2XX_XML */
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
new file mode 100644
index 000000000000..1f83bc18d500
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -0,0 +1,492 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+
+#include "a2xx_gpu.h"
+#include "msm_gem.h"
+#include "msm_mmu.h"
+
+extern bool hang_debug;
+
+static void a2xx_dump(struct msm_gpu *gpu);
+static bool a2xx_idle(struct msm_gpu *gpu);
+
+static bool a2xx_me_init(struct msm_gpu *gpu)
+{
+	struct msm_ringbuffer *ring = gpu->rb[0];
+
+	OUT_PKT3(ring, CP_ME_INIT, 18);
+
+	/* All fields present (bits 9:0) */
+	OUT_RING(ring, 0x000003ff);
+	/* Disable/Enable Real-Time Stream processing (present but ignored) */
+	OUT_RING(ring, 0x00000000);
+	/* Enable (2D <-> 3D) implicit synchronization (present but ignored) */
+	OUT_RING(ring, 0x00000000);
+
+	OUT_RING(ring, REG_A2XX_RB_SURFACE_INFO - 0x2000);
+	OUT_RING(ring, REG_A2XX_PA_SC_WINDOW_OFFSET - 0x2000);
+	OUT_RING(ring, REG_A2XX_VGT_MAX_VTX_INDX - 0x2000);
+	OUT_RING(ring, REG_A2XX_SQ_PROGRAM_CNTL - 0x2000);
+	OUT_RING(ring, REG_A2XX_RB_DEPTHCONTROL - 0x2000);
+	OUT_RING(ring, REG_A2XX_PA_SU_POINT_SIZE - 0x2000);
+	OUT_RING(ring, REG_A2XX_PA_SC_LINE_CNTL - 0x2000);
+	OUT_RING(ring, REG_A2XX_PA_SU_POLY_OFFSET_FRONT_SCALE - 0x2000);
+
+	/* Vertex and Pixel Shader Start Addresses in instructions
+	 * (3 DWORDS per instruction) */
+	OUT_RING(ring, 0x80000180);
+	/* Maximum Contexts */
+	OUT_RING(ring, 0x00000001);
+	/* Write Confirm Interval and The CP will wait the
+	 * wait_interval * 16 clocks between polling  */
+	OUT_RING(ring, 0x00000000);
+	/* NQ and External Memory Swap */
+	OUT_RING(ring, 0x00000000);
+	/* protected mode error checking (0x1f2 is REG_AXXX_CP_INT_CNTL) */
+	OUT_RING(ring, 0x200001f2);
+	/* Disable header dumping and Header dump address */
+	OUT_RING(ring, 0x00000000);
+	/* Header dump size */
+	OUT_RING(ring, 0x00000000);
+
+	/* enable protected mode */
+	OUT_PKT3(ring, CP_SET_PROTECTED_MODE, 1);
+	OUT_RING(ring, 1);
+
+	gpu->funcs->flush(gpu, ring);
+	return a2xx_idle(gpu);
+}
+
+static int a2xx_hw_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	dma_addr_t pt_base, tran_error;
+	uint32_t *ptr, len;
+	int i, ret;
+
+	msm_gpummu_params(gpu->aspace->mmu, &pt_base, &tran_error);
+
+	DBG("%s", gpu->name);
+
+	/* halt ME to avoid ucode upload issues on a20x */
+	gpu_write(gpu, REG_AXXX_CP_ME_CNTL, AXXX_CP_ME_CNTL_HALT);
+
+	gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE1, 0xfffffffe);
+	gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE2, 0xffffffff);
+
+	/* note: kgsl uses 0x00000001 after first reset on a22x */
+	gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 0xffffffff);
+	msleep(30);
+	gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 0x00000000);
+
+	if (adreno_is_a225(adreno_gpu))
+		gpu_write(gpu, REG_A2XX_SQ_FLOW_CONTROL, 0x18000000);
+
+	/* note: kgsl uses 0x0000ffff for a20x */
+	gpu_write(gpu, REG_A2XX_RBBM_CNTL, 0x00004442);
+
+	/* MPU: physical range */
+	gpu_write(gpu, REG_A2XX_MH_MMU_MPU_BASE, 0x00000000);
+	gpu_write(gpu, REG_A2XX_MH_MMU_MPU_END, 0xfffff000);
+
+	gpu_write(gpu, REG_A2XX_MH_MMU_CONFIG, A2XX_MH_MMU_CONFIG_MMU_ENABLE |
+		A2XX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR(BEH_TRAN_RNG) |
+		A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(BEH_TRAN_RNG));
+
+	/* same as parameters in adreno_gpu */
+	gpu_write(gpu, REG_A2XX_MH_MMU_VA_RANGE, SZ_16M |
+		A2XX_MH_MMU_VA_RANGE_NUM_64KB_REGIONS(0xfff));
+
+	gpu_write(gpu, REG_A2XX_MH_MMU_PT_BASE, pt_base);
+	gpu_write(gpu, REG_A2XX_MH_MMU_TRAN_ERROR, tran_error);
+
+	gpu_write(gpu, REG_A2XX_MH_MMU_INVALIDATE,
+		A2XX_MH_MMU_INVALIDATE_INVALIDATE_ALL |
+		A2XX_MH_MMU_INVALIDATE_INVALIDATE_TC);
+
+	gpu_write(gpu, REG_A2XX_MH_ARBITER_CONFIG,
+		A2XX_MH_ARBITER_CONFIG_SAME_PAGE_LIMIT(16) |
+		A2XX_MH_ARBITER_CONFIG_L1_ARB_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_L1_ARB_HOLD_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_PAGE_SIZE(1) |
+		A2XX_MH_ARBITER_CONFIG_TC_REORDER_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_TC_ARB_HOLD_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_IN_FLIGHT_LIMIT_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_IN_FLIGHT_LIMIT(8) |
+		A2XX_MH_ARBITER_CONFIG_CP_CLNT_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_VGT_CLNT_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_TC_CLNT_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_RB_CLNT_ENABLE |
+		A2XX_MH_ARBITER_CONFIG_PA_CLNT_ENABLE);
+	if (!adreno_is_a20x(adreno_gpu))
+		gpu_write(gpu, REG_A2XX_MH_CLNT_INTF_CTRL_CONFIG1, 0x00032f07);
+
+	gpu_write(gpu, REG_A2XX_SQ_VS_PROGRAM, 0x00000000);
+	gpu_write(gpu, REG_A2XX_SQ_PS_PROGRAM, 0x00000000);
+
+	gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE1, 0); /* 0x200 for msm8960? */
+	gpu_write(gpu, REG_A2XX_RBBM_PM_OVERRIDE2, 0); /* 0x80/0x1a0 for a22x? */
+
+	/* note: gsl doesn't set this */
+	gpu_write(gpu, REG_A2XX_RBBM_DEBUG, 0x00080000);
+
+	gpu_write(gpu, REG_A2XX_RBBM_INT_CNTL,
+		A2XX_RBBM_INT_CNTL_RDERR_INT_MASK);
+	gpu_write(gpu, REG_AXXX_CP_INT_CNTL,
+		AXXX_CP_INT_CNTL_T0_PACKET_IN_IB_MASK |
+		AXXX_CP_INT_CNTL_OPCODE_ERROR_MASK |
+		AXXX_CP_INT_CNTL_PROTECTED_MODE_ERROR_MASK |
+		AXXX_CP_INT_CNTL_RESERVED_BIT_ERROR_MASK |
+		AXXX_CP_INT_CNTL_IB_ERROR_MASK |
+		AXXX_CP_INT_CNTL_IB1_INT_MASK |
+		AXXX_CP_INT_CNTL_RB_INT_MASK);
+	gpu_write(gpu, REG_A2XX_SQ_INT_CNTL, 0);
+	gpu_write(gpu, REG_A2XX_MH_INTERRUPT_MASK,
+		A2XX_MH_INTERRUPT_MASK_AXI_READ_ERROR |
+		A2XX_MH_INTERRUPT_MASK_AXI_WRITE_ERROR |
+		A2XX_MH_INTERRUPT_MASK_MMU_PAGE_FAULT);
+
+	for (i = 3; i <= 5; i++)
+		if ((SZ_16K << i) == adreno_gpu->gmem)
+			break;
+	gpu_write(gpu, REG_A2XX_RB_EDRAM_INFO, i);
+
+	ret = adreno_hw_init(gpu);
+	if (ret)
+		return ret;
+
+	/* NOTE: PM4/micro-engine firmware registers look to be the same
+	 * for a2xx and a3xx.. we could possibly push that part down to
+	 * adreno_gpu base class.  Or push both PM4 and PFP but
+	 * parameterize the pfp ucode addr/data registers..
+	 */
+
+	/* Load PM4: */
+	ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data);
+	len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4;
+	DBG("loading PM4 ucode version: %x", ptr[1]);
+
+	gpu_write(gpu, REG_AXXX_CP_DEBUG,
+			AXXX_CP_DEBUG_MIU_128BIT_WRITE_ENABLE);
+	gpu_write(gpu, REG_AXXX_CP_ME_RAM_WADDR, 0);
+	for (i = 1; i < len; i++)
+		gpu_write(gpu, REG_AXXX_CP_ME_RAM_DATA, ptr[i]);
+
+	/* Load PFP: */
+	ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PFP]->data);
+	len = adreno_gpu->fw[ADRENO_FW_PFP]->size / 4;
+	DBG("loading PFP ucode version: %x", ptr[5]);
+
+	gpu_write(gpu, REG_A2XX_CP_PFP_UCODE_ADDR, 0);
+	for (i = 1; i < len; i++)
+		gpu_write(gpu, REG_A2XX_CP_PFP_UCODE_DATA, ptr[i]);
+
+	gpu_write(gpu, REG_AXXX_CP_QUEUE_THRESHOLDS, 0x000C0804);
+
+	/* clear ME_HALT to start micro engine */
+	gpu_write(gpu, REG_AXXX_CP_ME_CNTL, 0);
+
+	return a2xx_me_init(gpu) ? 0 : -EINVAL;
+}
+
+static void a2xx_recover(struct msm_gpu *gpu)
+{
+	int i;
+
+	adreno_dump_info(gpu);
+
+	for (i = 0; i < 8; i++) {
+		printk("CP_SCRATCH_REG%d: %u\n", i,
+			gpu_read(gpu, REG_AXXX_CP_SCRATCH_REG0 + i));
+	}
+
+	/* dump registers before resetting gpu, if enabled: */
+	if (hang_debug)
+		a2xx_dump(gpu);
+
+	gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 1);
+	gpu_read(gpu, REG_A2XX_RBBM_SOFT_RESET);
+	gpu_write(gpu, REG_A2XX_RBBM_SOFT_RESET, 0);
+	adreno_recover(gpu);
+}
+
+static void a2xx_destroy(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a2xx_gpu *a2xx_gpu = to_a2xx_gpu(adreno_gpu);
+
+	DBG("%s", gpu->name);
+
+	adreno_gpu_cleanup(adreno_gpu);
+
+	kfree(a2xx_gpu);
+}
+
+static bool a2xx_idle(struct msm_gpu *gpu)
+{
+	/* wait for ringbuffer to drain: */
+	if (!adreno_idle(gpu, gpu->rb[0]))
+		return false;
+
+	/* then wait for GPU to finish: */
+	if (spin_until(!(gpu_read(gpu, REG_A2XX_RBBM_STATUS) &
+			A2XX_RBBM_STATUS_GUI_ACTIVE))) {
+		DRM_ERROR("%s: timeout waiting for GPU to idle!\n", gpu->name);
+
+		/* TODO maybe we need to reset GPU here to recover from hang? */
+		return false;
+	}
+
+	return true;
+}
+
+static irqreturn_t a2xx_irq(struct msm_gpu *gpu)
+{
+	uint32_t mstatus, status;
+
+	mstatus = gpu_read(gpu, REG_A2XX_MASTER_INT_SIGNAL);
+
+	if (mstatus & A2XX_MASTER_INT_SIGNAL_MH_INT_STAT) {
+		status = gpu_read(gpu, REG_A2XX_MH_INTERRUPT_STATUS);
+
+		dev_warn(gpu->dev->dev, "MH_INT: %08X\n", status);
+		dev_warn(gpu->dev->dev, "MMU_PAGE_FAULT: %08X\n",
+			gpu_read(gpu, REG_A2XX_MH_MMU_PAGE_FAULT));
+
+		gpu_write(gpu, REG_A2XX_MH_INTERRUPT_CLEAR, status);
+	}
+
+	if (mstatus & A2XX_MASTER_INT_SIGNAL_CP_INT_STAT) {
+		status = gpu_read(gpu, REG_AXXX_CP_INT_STATUS);
+
+		/* only RB_INT is expected */
+		if (status & ~AXXX_CP_INT_CNTL_RB_INT_MASK)
+			dev_warn(gpu->dev->dev, "CP_INT: %08X\n", status);
+
+		gpu_write(gpu, REG_AXXX_CP_INT_ACK, status);
+	}
+
+	if (mstatus & A2XX_MASTER_INT_SIGNAL_RBBM_INT_STAT) {
+		status = gpu_read(gpu, REG_A2XX_RBBM_INT_STATUS);
+
+		dev_warn(gpu->dev->dev, "RBBM_INT: %08X\n", status);
+
+		gpu_write(gpu, REG_A2XX_RBBM_INT_ACK, status);
+	}
+
+	msm_gpu_retire(gpu);
+
+	return IRQ_HANDLED;
+}
+
+static const unsigned int a200_registers[] = {
+	0x0000, 0x0002, 0x0004, 0x000B, 0x003B, 0x003D, 0x0040, 0x0044,
+	0x0046, 0x0047, 0x01C0, 0x01C1, 0x01C3, 0x01C8, 0x01D5, 0x01D9,
+	0x01DC, 0x01DD, 0x01EA, 0x01EA, 0x01EE, 0x01F3, 0x01F6, 0x01F7,
+	0x01FC, 0x01FF, 0x0391, 0x0392, 0x039B, 0x039E, 0x03B2, 0x03B5,
+	0x03B7, 0x03B7, 0x03F8, 0x03FB, 0x0440, 0x0440, 0x0443, 0x0444,
+	0x044B, 0x044B, 0x044D, 0x044F, 0x0452, 0x0452, 0x0454, 0x045B,
+	0x047F, 0x047F, 0x0578, 0x0587, 0x05C9, 0x05C9, 0x05D0, 0x05D0,
+	0x0601, 0x0604, 0x0606, 0x0609, 0x060B, 0x060E, 0x0613, 0x0614,
+	0x0A29, 0x0A2B, 0x0A2F, 0x0A31, 0x0A40, 0x0A43, 0x0A45, 0x0A45,
+	0x0A4E, 0x0A4F, 0x0C2C, 0x0C2C, 0x0C30, 0x0C30, 0x0C38, 0x0C3C,
+	0x0C40, 0x0C40, 0x0C44, 0x0C44, 0x0C80, 0x0C86, 0x0C88, 0x0C94,
+	0x0C99, 0x0C9A, 0x0CA4, 0x0CA5, 0x0D00, 0x0D03, 0x0D06, 0x0D06,
+	0x0D08, 0x0D0B, 0x0D34, 0x0D35, 0x0DAE, 0x0DC1, 0x0DC8, 0x0DD4,
+	0x0DD8, 0x0DD9, 0x0E00, 0x0E00, 0x0E02, 0x0E04, 0x0E17, 0x0E1E,
+	0x0EC0, 0x0EC9, 0x0ECB, 0x0ECC, 0x0ED0, 0x0ED0, 0x0ED4, 0x0ED7,
+	0x0EE0, 0x0EE2, 0x0F01, 0x0F02, 0x0F0C, 0x0F0C, 0x0F0E, 0x0F12,
+	0x0F26, 0x0F2A, 0x0F2C, 0x0F2C, 0x2000, 0x2002, 0x2006, 0x200F,
+	0x2080, 0x2082, 0x2100, 0x2109, 0x210C, 0x2114, 0x2180, 0x2184,
+	0x21F5, 0x21F7, 0x2200, 0x2208, 0x2280, 0x2283, 0x2293, 0x2294,
+	0x2300, 0x2308, 0x2312, 0x2312, 0x2316, 0x231D, 0x2324, 0x2326,
+	0x2380, 0x2383, 0x2400, 0x2402, 0x2406, 0x240F, 0x2480, 0x2482,
+	0x2500, 0x2509, 0x250C, 0x2514, 0x2580, 0x2584, 0x25F5, 0x25F7,
+	0x2600, 0x2608, 0x2680, 0x2683, 0x2693, 0x2694, 0x2700, 0x2708,
+	0x2712, 0x2712, 0x2716, 0x271D, 0x2724, 0x2726, 0x2780, 0x2783,
+	0x4000, 0x4003, 0x4800, 0x4805, 0x4900, 0x4900, 0x4908, 0x4908,
+	~0   /* sentinel */
+};
+
+static const unsigned int a220_registers[] = {
+	0x0000, 0x0002, 0x0004, 0x000B, 0x003B, 0x003D, 0x0040, 0x0044,
+	0x0046, 0x0047, 0x01C0, 0x01C1, 0x01C3, 0x01C8, 0x01D5, 0x01D9,
+	0x01DC, 0x01DD, 0x01EA, 0x01EA, 0x01EE, 0x01F3, 0x01F6, 0x01F7,
+	0x01FC, 0x01FF, 0x0391, 0x0392, 0x039B, 0x039E, 0x03B2, 0x03B5,
+	0x03B7, 0x03B7, 0x03F8, 0x03FB, 0x0440, 0x0440, 0x0443, 0x0444,
+	0x044B, 0x044B, 0x044D, 0x044F, 0x0452, 0x0452, 0x0454, 0x045B,
+	0x047F, 0x047F, 0x0578, 0x0587, 0x05C9, 0x05C9, 0x05D0, 0x05D0,
+	0x0601, 0x0604, 0x0606, 0x0609, 0x060B, 0x060E, 0x0613, 0x0614,
+	0x0A29, 0x0A2B, 0x0A2F, 0x0A31, 0x0A40, 0x0A40, 0x0A42, 0x0A43,
+	0x0A45, 0x0A45, 0x0A4E, 0x0A4F, 0x0C30, 0x0C30, 0x0C38, 0x0C39,
+	0x0C3C, 0x0C3C, 0x0C80, 0x0C81, 0x0C88, 0x0C93, 0x0D00, 0x0D03,
+	0x0D05, 0x0D06, 0x0D08, 0x0D0B, 0x0D34, 0x0D35, 0x0DAE, 0x0DC1,
+	0x0DC8, 0x0DD4, 0x0DD8, 0x0DD9, 0x0E00, 0x0E00, 0x0E02, 0x0E04,
+	0x0E17, 0x0E1E, 0x0EC0, 0x0EC9, 0x0ECB, 0x0ECC, 0x0ED0, 0x0ED0,
+	0x0ED4, 0x0ED7, 0x0EE0, 0x0EE2, 0x0F01, 0x0F02, 0x2000, 0x2002,
+	0x2006, 0x200F, 0x2080, 0x2082, 0x2100, 0x2102, 0x2104, 0x2109,
+	0x210C, 0x2114, 0x2180, 0x2184, 0x21F5, 0x21F7, 0x2200, 0x2202,
+	0x2204, 0x2204, 0x2208, 0x2208, 0x2280, 0x2282, 0x2294, 0x2294,
+	0x2300, 0x2308, 0x2309, 0x230A, 0x2312, 0x2312, 0x2316, 0x2316,
+	0x2318, 0x231D, 0x2324, 0x2326, 0x2380, 0x2383, 0x2400, 0x2402,
+	0x2406, 0x240F, 0x2480, 0x2482, 0x2500, 0x2502, 0x2504, 0x2509,
+	0x250C, 0x2514, 0x2580, 0x2584, 0x25F5, 0x25F7, 0x2600, 0x2602,
+	0x2604, 0x2606, 0x2608, 0x2608, 0x2680, 0x2682, 0x2694, 0x2694,
+	0x2700, 0x2708, 0x2712, 0x2712, 0x2716, 0x2716, 0x2718, 0x271D,
+	0x2724, 0x2726, 0x2780, 0x2783, 0x4000, 0x4003, 0x4800, 0x4805,
+	0x4900, 0x4900, 0x4908, 0x4908,
+	~0   /* sentinel */
+};
+
+static const unsigned int a225_registers[] = {
+	0x0000, 0x0002, 0x0004, 0x000B, 0x003B, 0x003D, 0x0040, 0x0044,
+	0x0046, 0x0047, 0x013C, 0x013C, 0x0140, 0x014F, 0x01C0, 0x01C1,
+	0x01C3, 0x01C8, 0x01D5, 0x01D9, 0x01DC, 0x01DD, 0x01EA, 0x01EA,
+	0x01EE, 0x01F3, 0x01F6, 0x01F7, 0x01FC, 0x01FF, 0x0391, 0x0392,
+	0x039B, 0x039E, 0x03B2, 0x03B5, 0x03B7, 0x03B7, 0x03F8, 0x03FB,
+	0x0440, 0x0440, 0x0443, 0x0444, 0x044B, 0x044B, 0x044D, 0x044F,
+	0x0452, 0x0452, 0x0454, 0x045B, 0x047F, 0x047F, 0x0578, 0x0587,
+	0x05C9, 0x05C9, 0x05D0, 0x05D0, 0x0601, 0x0604, 0x0606, 0x0609,
+	0x060B, 0x060E, 0x0613, 0x0614, 0x0A29, 0x0A2B, 0x0A2F, 0x0A31,
+	0x0A40, 0x0A40, 0x0A42, 0x0A43, 0x0A45, 0x0A45, 0x0A4E, 0x0A4F,
+	0x0C01, 0x0C1D, 0x0C30, 0x0C30, 0x0C38, 0x0C39, 0x0C3C, 0x0C3C,
+	0x0C80, 0x0C81, 0x0C88, 0x0C93, 0x0D00, 0x0D03, 0x0D05, 0x0D06,
+	0x0D08, 0x0D0B, 0x0D34, 0x0D35, 0x0DAE, 0x0DC1, 0x0DC8, 0x0DD4,
+	0x0DD8, 0x0DD9, 0x0E00, 0x0E00, 0x0E02, 0x0E04, 0x0E17, 0x0E1E,
+	0x0EC0, 0x0EC9, 0x0ECB, 0x0ECC, 0x0ED0, 0x0ED0, 0x0ED4, 0x0ED7,
+	0x0EE0, 0x0EE2, 0x0F01, 0x0F02, 0x2000, 0x200F, 0x2080, 0x2082,
+	0x2100, 0x2109, 0x210C, 0x2114, 0x2180, 0x2184, 0x21F5, 0x21F7,
+	0x2200, 0x2202, 0x2204, 0x2206, 0x2208, 0x2210, 0x2220, 0x2222,
+	0x2280, 0x2282, 0x2294, 0x2294, 0x2297, 0x2297, 0x2300, 0x230A,
+	0x2312, 0x2312, 0x2315, 0x2316, 0x2318, 0x231D, 0x2324, 0x2326,
+	0x2340, 0x2357, 0x2360, 0x2360, 0x2380, 0x2383, 0x2400, 0x240F,
+	0x2480, 0x2482, 0x2500, 0x2509, 0x250C, 0x2514, 0x2580, 0x2584,
+	0x25F5, 0x25F7, 0x2600, 0x2602, 0x2604, 0x2606, 0x2608, 0x2610,
+	0x2620, 0x2622, 0x2680, 0x2682, 0x2694, 0x2694, 0x2697, 0x2697,
+	0x2700, 0x270A, 0x2712, 0x2712, 0x2715, 0x2716, 0x2718, 0x271D,
+	0x2724, 0x2726, 0x2740, 0x2757, 0x2760, 0x2760, 0x2780, 0x2783,
+	0x4000, 0x4003, 0x4800, 0x4806, 0x4808, 0x4808, 0x4900, 0x4900,
+	0x4908, 0x4908,
+	~0   /* sentinel */
+};
+
+/* would be nice to not have to duplicate the _show() stuff with printk(): */
+static void a2xx_dump(struct msm_gpu *gpu)
+{
+	printk("status:   %08x\n",
+			gpu_read(gpu, REG_A2XX_RBBM_STATUS));
+	adreno_dump(gpu);
+}
+
+static struct msm_gpu_state *a2xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
+
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
+
+	state->rbbm_status = gpu_read(gpu, REG_A2XX_RBBM_STATUS);
+
+	return state;
+}
+
+/* Register offset defines for A2XX - copy of A3XX */
+static const unsigned int a2xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE),
+	REG_ADRENO_SKIP(REG_ADRENO_CP_RB_BASE_HI),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_AXXX_CP_RB_RPTR_ADDR),
+	REG_ADRENO_SKIP(REG_ADRENO_CP_RB_RPTR_ADDR_HI),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_AXXX_CP_RB_RPTR),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_AXXX_CP_RB_WPTR),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_AXXX_CP_RB_CNTL),
+};
+
+static const struct adreno_gpu_funcs funcs = {
+	.base = {
+		.get_param = adreno_get_param,
+		.hw_init = a2xx_hw_init,
+		.pm_suspend = msm_gpu_pm_suspend,
+		.pm_resume = msm_gpu_pm_resume,
+		.recover = a2xx_recover,
+		.submit = adreno_submit,
+		.flush = adreno_flush,
+		.active_ring = adreno_active_ring,
+		.irq = a2xx_irq,
+		.destroy = a2xx_destroy,
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+		.show = adreno_show,
+#endif
+		.gpu_state_get = a2xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
+	},
+};
+
+static const struct msm_gpu_perfcntr perfcntrs[] = {
+/* TODO */
+};
+
+struct msm_gpu *a2xx_gpu_init(struct drm_device *dev)
+{
+	struct a2xx_gpu *a2xx_gpu = NULL;
+	struct adreno_gpu *adreno_gpu;
+	struct msm_gpu *gpu;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct platform_device *pdev = priv->gpu_pdev;
+	int ret;
+
+	if (!pdev) {
+		dev_err(dev->dev, "no a2xx device\n");
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	a2xx_gpu = kzalloc(sizeof(*a2xx_gpu), GFP_KERNEL);
+	if (!a2xx_gpu) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	adreno_gpu = &a2xx_gpu->base;
+	gpu = &adreno_gpu->base;
+
+	gpu->perfcntrs = perfcntrs;
+	gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs);
+
+	if (adreno_is_a20x(adreno_gpu))
+		adreno_gpu->registers = a200_registers;
+	else if (adreno_is_a225(adreno_gpu))
+		adreno_gpu->registers = a225_registers;
+	else
+		adreno_gpu->registers = a220_registers;
+
+	adreno_gpu->reg_offsets = a2xx_register_offsets;
+
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
+	if (ret)
+		goto fail;
+
+	if (!gpu->aspace) {
+		dev_err(dev->dev, "No memory protection without MMU\n");
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	return gpu;
+
+fail:
+	if (a2xx_gpu)
+		a2xx_destroy(&a2xx_gpu->base.base);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.h b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h
new file mode 100644
index 000000000000..02fba2cb8932
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+
+#ifndef __A2XX_GPU_H__
+#define __A2XX_GPU_H__
+
+#include "adreno_gpu.h"
+
+/* arrg, somehow fb.h is getting pulled in: */
+#undef ROP_COPY
+#undef ROP_XOR
+
+#include "a2xx.xml.h"
+
+struct a2xx_gpu {
+	struct adreno_gpu base;
+	bool pm_enabled;
+};
+#define to_a2xx_gpu(x) container_of(x, struct a2xx_gpu, base)
+
+#endif /* __A2XX_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/a3xx.xml.h b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
index a89f7bb8b5cc..17059f242a98 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 669c2d4b070d..c3b4bc6e4155 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -481,7 +481,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	int ret;
 
 	if (!pdev) {
-		dev_err(dev->dev, "no a3xx device\n");
+		DRM_DEV_ERROR(dev->dev, "no a3xx device\n");
 		ret = -ENXIO;
 		goto fail;
 	}
@@ -528,7 +528,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		 * to not be possible to restrict access, then we must
 		 * implement a cmdstream validator.
 		 */
-		dev_err(dev->dev, "No memory protection without IOMMU\n");
+		DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n");
 		ret = -ENXIO;
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/adreno/a4xx.xml.h b/drivers/gpu/drm/msm/adreno/a4xx.xml.h
index 858690f52854..9b51e25a9583 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a4xx.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 7c4e6dc1ed59..18f9a8e0bf3b 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -561,7 +561,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 	int ret;
 
 	if (!pdev) {
-		dev_err(dev->dev, "no a4xx device\n");
+		DRM_DEV_ERROR(dev->dev, "no a4xx device\n");
 		ret = -ENXIO;
 		goto fail;
 	}
@@ -608,7 +608,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 		 * to not be possible to restrict access, then we must
 		 * implement a cmdstream validator.
 		 */
-		dev_err(dev->dev, "No memory protection without IOMMU\n");
+		DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n");
 		ret = -ENXIO;
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
index b4944cc0e62f..cf4fe14ddd6e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
index d2127b1c4ece..d9af3aff690f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
@@ -130,15 +130,13 @@ reset_set(void *data, u64 val)
 	adreno_gpu->fw[ADRENO_FW_PFP] = NULL;
 
 	if (a5xx_gpu->pm4_bo) {
-		if (a5xx_gpu->pm4_iova)
-			msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace);
+		msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace);
 		drm_gem_object_put(a5xx_gpu->pm4_bo);
 		a5xx_gpu->pm4_bo = NULL;
 	}
 
 	if (a5xx_gpu->pfp_bo) {
-		if (a5xx_gpu->pfp_iova)
-			msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->aspace);
+		msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace);
 		drm_gem_object_put(a5xx_gpu->pfp_bo);
 		a5xx_gpu->pfp_bo = NULL;
 	}
@@ -173,7 +171,7 @@ int a5xx_debugfs_init(struct msm_gpu *gpu, struct drm_minor *minor)
 			minor->debugfs_root, minor);
 
 	if (ret) {
-		dev_err(dev->dev, "could not install a5xx_debugfs_list\n");
+		DRM_DEV_ERROR(dev->dev, "could not install a5xx_debugfs_list\n");
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 8edd80bb0428..d5f5e56422f5 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -20,7 +20,6 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/pm_opp.h>
 #include <linux/nvmem-consumer.h>
-#include <linux/iopoll.h>
 #include <linux/slab.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
@@ -511,13 +510,16 @@ static int a5xx_ucode_init(struct msm_gpu *gpu)
 		a5xx_gpu->pm4_bo = adreno_fw_create_bo(gpu,
 			adreno_gpu->fw[ADRENO_FW_PM4], &a5xx_gpu->pm4_iova);
 
+
 		if (IS_ERR(a5xx_gpu->pm4_bo)) {
 			ret = PTR_ERR(a5xx_gpu->pm4_bo);
 			a5xx_gpu->pm4_bo = NULL;
-			dev_err(gpu->dev->dev, "could not allocate PM4: %d\n",
+			DRM_DEV_ERROR(gpu->dev->dev, "could not allocate PM4: %d\n",
 				ret);
 			return ret;
 		}
+
+		msm_gem_object_set_name(a5xx_gpu->pm4_bo, "pm4fw");
 	}
 
 	if (!a5xx_gpu->pfp_bo) {
@@ -527,10 +529,12 @@ static int a5xx_ucode_init(struct msm_gpu *gpu)
 		if (IS_ERR(a5xx_gpu->pfp_bo)) {
 			ret = PTR_ERR(a5xx_gpu->pfp_bo);
 			a5xx_gpu->pfp_bo = NULL;
-			dev_err(gpu->dev->dev, "could not allocate PFP: %d\n",
+			DRM_DEV_ERROR(gpu->dev->dev, "could not allocate PFP: %d\n",
 				ret);
 			return ret;
 		}
+
+		msm_gem_object_set_name(a5xx_gpu->pfp_bo, "pfpfw");
 	}
 
 	gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO,
@@ -841,20 +845,17 @@ static void a5xx_destroy(struct msm_gpu *gpu)
 	a5xx_preempt_fini(gpu);
 
 	if (a5xx_gpu->pm4_bo) {
-		if (a5xx_gpu->pm4_iova)
-			msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace);
+		msm_gem_unpin_iova(a5xx_gpu->pm4_bo, gpu->aspace);
 		drm_gem_object_put_unlocked(a5xx_gpu->pm4_bo);
 	}
 
 	if (a5xx_gpu->pfp_bo) {
-		if (a5xx_gpu->pfp_iova)
-			msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->aspace);
+		msm_gem_unpin_iova(a5xx_gpu->pfp_bo, gpu->aspace);
 		drm_gem_object_put_unlocked(a5xx_gpu->pfp_bo);
 	}
 
 	if (a5xx_gpu->gpmu_bo) {
-		if (a5xx_gpu->gpmu_iova)
-			msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->aspace);
+		msm_gem_unpin_iova(a5xx_gpu->gpmu_bo, gpu->aspace);
 		drm_gem_object_put_unlocked(a5xx_gpu->gpmu_bo);
 	}
 
@@ -1028,7 +1029,7 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 
-	dev_err(dev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n",
+	DRM_DEV_ERROR(dev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n",
 		ring ? ring->id : -1, ring ? ring->seqno : 0,
 		gpu_read(gpu, REG_A5XX_RBBM_STATUS),
 		gpu_read(gpu, REG_A5XX_CP_RB_RPTR),
@@ -1134,7 +1135,7 @@ static const u32 a5xx_registers[] = {
 
 static void a5xx_dump(struct msm_gpu *gpu)
 {
-	dev_info(gpu->dev->dev, "status:   %08x\n",
+	DRM_DEV_INFO(gpu->dev->dev, "status:   %08x\n",
 		gpu_read(gpu, REG_A5XX_RBBM_STATUS));
 	adreno_dump(gpu);
 }
@@ -1211,10 +1212,6 @@ struct a5xx_gpu_state {
 	u32 *hlsqregs;
 };
 
-#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
-	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
-		interval, timeout)
-
 static int a5xx_crashdumper_init(struct msm_gpu *gpu,
 		struct a5xx_crashdumper *dumper)
 {
@@ -1222,16 +1219,10 @@ static int a5xx_crashdumper_init(struct msm_gpu *gpu,
 		SZ_1M, MSM_BO_UNCACHED, gpu->aspace,
 		&dumper->bo, &dumper->iova);
 
-	return PTR_ERR_OR_ZERO(dumper->ptr);
-}
-
-static void a5xx_crashdumper_free(struct msm_gpu *gpu,
-		struct a5xx_crashdumper *dumper)
-{
-	msm_gem_put_iova(dumper->bo, gpu->aspace);
-	msm_gem_put_vaddr(dumper->bo);
+	if (!IS_ERR(dumper->ptr))
+		msm_gem_object_set_name(dumper->bo, "crashdump");
 
-	drm_gem_object_put(dumper->bo);
+	return PTR_ERR_OR_ZERO(dumper->ptr);
 }
 
 static int a5xx_crashdumper_run(struct msm_gpu *gpu,
@@ -1326,7 +1317,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 
 	if (a5xx_crashdumper_run(gpu, &dumper)) {
 		kfree(a5xx_state->hlsqregs);
-		a5xx_crashdumper_free(gpu, &dumper);
+		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
 		return;
 	}
 
@@ -1334,7 +1325,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
 	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
 		count * sizeof(u32));
 
-	a5xx_crashdumper_free(gpu, &dumper);
+	msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
 }
 
 static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
@@ -1505,7 +1496,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 	int ret;
 
 	if (!pdev) {
-		dev_err(dev->dev, "No A5XX device is defined\n");
+		DRM_DEV_ERROR(dev->dev, "No A5XX device is defined\n");
 		return ERR_PTR(-ENXIO);
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index 7a41e1c147e4..70e65c94e525 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -298,7 +298,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 		MSM_BO_UNCACHED | MSM_BO_GPU_READONLY, gpu->aspace,
 		&a5xx_gpu->gpmu_bo, &a5xx_gpu->gpmu_iova);
 	if (IS_ERR(ptr))
-		goto err;
+		return;
+
+	msm_gem_object_set_name(a5xx_gpu->gpmu_bo, "gpmufw");
 
 	while (cmds_size > 0) {
 		int i;
@@ -317,15 +319,4 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 
 	msm_gem_put_vaddr(a5xx_gpu->gpmu_bo);
 	a5xx_gpu->gpmu_dwords = dwords;
-
-	return;
-err:
-	if (a5xx_gpu->gpmu_iova)
-		msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->aspace);
-	if (a5xx_gpu->gpmu_bo)
-		drm_gem_object_put(a5xx_gpu->gpmu_bo);
-
-	a5xx_gpu->gpmu_bo = NULL;
-	a5xx_gpu->gpmu_iova = 0;
-	a5xx_gpu->gpmu_dwords = 0;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index 4c357ead1be6..3d62310a535f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -92,7 +92,7 @@ static void a5xx_preempt_timer(struct timer_list *t)
 	if (!try_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED, PREEMPT_FAULTED))
 		return;
 
-	dev_err(dev->dev, "%s: preemption timed out\n", gpu->name);
+	DRM_DEV_ERROR(dev->dev, "%s: preemption timed out\n", gpu->name);
 	queue_work(priv->wq, &gpu->recover_work);
 }
 
@@ -188,7 +188,7 @@ void a5xx_preempt_irq(struct msm_gpu *gpu)
 	status = gpu_read(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL);
 	if (unlikely(status)) {
 		set_preempt_state(a5xx_gpu, PREEMPT_FAULTED);
-		dev_err(dev->dev, "%s: Preemption failed to complete\n",
+		DRM_DEV_ERROR(dev->dev, "%s: Preemption failed to complete\n",
 			gpu->name);
 		queue_work(priv->wq, &gpu->recover_work);
 		return;
@@ -245,6 +245,8 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
+	msm_gem_object_set_name(bo, "preempt");
+
 	a5xx_gpu->preempt_bo[ring->id] = bo;
 	a5xx_gpu->preempt_iova[ring->id] = iova;
 	a5xx_gpu->preempt[ring->id] = ptr;
@@ -267,18 +269,8 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	int i;
 
-	for (i = 0; i < gpu->nr_rings; i++) {
-		if (!a5xx_gpu->preempt_bo[i])
-			continue;
-
-		msm_gem_put_vaddr(a5xx_gpu->preempt_bo[i]);
-
-		if (a5xx_gpu->preempt_iova[i])
-			msm_gem_put_iova(a5xx_gpu->preempt_bo[i], gpu->aspace);
-
-		drm_gem_object_put(a5xx_gpu->preempt_bo[i]);
-		a5xx_gpu->preempt_bo[i] = NULL;
-	}
+	for (i = 0; i < gpu->nr_rings; i++)
+		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
 }
 
 void a5xx_preempt_init(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
index a6f7c40454a6..f44553ec3193 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
@@ -501,7 +501,7 @@ enum a6xx_vfd_perfcounter_select {
 	PERF_VFDP_VS_STAGE_WAVES = 22,
 };
 
-enum a6xx_hslq_perfcounter_select {
+enum a6xx_hlsq_perfcounter_select {
 	PERF_HLSQ_BUSY_CYCLES = 0,
 	PERF_HLSQ_STALL_CYCLES_UCHE = 1,
 	PERF_HLSQ_STALL_CYCLES_SP_STATE = 2,
@@ -2959,6 +2959,8 @@ static inline uint32_t A6XX_GRAS_SC_WINDOW_SCISSOR_BR_Y(uint32_t val)
 #define A6XX_GRAS_LRZ_CNTL_ENABLE				0x00000001
 #define A6XX_GRAS_LRZ_CNTL_LRZ_WRITE				0x00000002
 #define A6XX_GRAS_LRZ_CNTL_GREATER				0x00000004
+#define A6XX_GRAS_LRZ_CNTL_UNK3					0x00000008
+#define A6XX_GRAS_LRZ_CNTL_UNK4					0x00000010
 
 #define REG_A6XX_GRAS_UNKNOWN_8101				0x00008101
 
@@ -2997,6 +2999,13 @@ static inline uint32_t A6XX_GRAS_LRZ_BUFFER_PITCH_ARRAY_PITCH(uint32_t val)
 #define REG_A6XX_GRAS_UNKNOWN_8110				0x00008110
 
 #define REG_A6XX_GRAS_2D_BLIT_CNTL				0x00008400
+#define A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__MASK		0x0000ff00
+#define A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__SHIFT		8
+static inline uint32_t A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT(enum a6xx_color_fmt val)
+{
+	return ((val) << A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__SHIFT) & A6XX_GRAS_2D_BLIT_CNTL_COLOR_FORMAT__MASK;
+}
+#define A6XX_GRAS_2D_BLIT_CNTL_SCISSOR				0x00010000
 
 #define REG_A6XX_GRAS_2D_SRC_TL_X				0x00008401
 #define A6XX_GRAS_2D_SRC_TL_X_X__MASK				0x00ffff00
@@ -3449,6 +3458,7 @@ static inline uint32_t A6XX_RB_BLEND_CNTL_ENABLE_BLEND(uint32_t val)
 	return ((val) << A6XX_RB_BLEND_CNTL_ENABLE_BLEND__SHIFT) & A6XX_RB_BLEND_CNTL_ENABLE_BLEND__MASK;
 }
 #define A6XX_RB_BLEND_CNTL_INDEPENDENT_BLEND			0x00000100
+#define A6XX_RB_BLEND_CNTL_ALPHA_TO_COVERAGE			0x00000400
 #define A6XX_RB_BLEND_CNTL_SAMPLE_MASK__MASK			0xffff0000
 #define A6XX_RB_BLEND_CNTL_SAMPLE_MASK__SHIFT			16
 static inline uint32_t A6XX_RB_BLEND_CNTL_SAMPLE_MASK(uint32_t val)
@@ -3642,6 +3652,9 @@ static inline uint32_t A6XX_RB_WINDOW_OFFSET_Y(uint32_t val)
 #define REG_A6XX_RB_SAMPLE_COUNT_CONTROL			0x00008891
 #define A6XX_RB_SAMPLE_COUNT_CONTROL_COPY			0x00000002
 
+#define REG_A6XX_RB_LRZ_CNTL					0x00008898
+#define A6XX_RB_LRZ_CNTL_ENABLE					0x00000001
+
 #define REG_A6XX_RB_UNKNOWN_88D0				0x000088d0
 
 #define REG_A6XX_RB_BLIT_SCISSOR_TL				0x000088d1
@@ -3674,6 +3687,14 @@ static inline uint32_t A6XX_RB_BLIT_SCISSOR_BR_Y(uint32_t val)
 	return ((val) << A6XX_RB_BLIT_SCISSOR_BR_Y__SHIFT) & A6XX_RB_BLIT_SCISSOR_BR_Y__MASK;
 }
 
+#define REG_A6XX_RB_MSAA_CNTL					0x000088d5
+#define A6XX_RB_MSAA_CNTL_SAMPLES__MASK				0x00000018
+#define A6XX_RB_MSAA_CNTL_SAMPLES__SHIFT			3
+static inline uint32_t A6XX_RB_MSAA_CNTL_SAMPLES(enum a3xx_msaa_samples val)
+{
+	return ((val) << A6XX_RB_MSAA_CNTL_SAMPLES__SHIFT) & A6XX_RB_MSAA_CNTL_SAMPLES__MASK;
+}
+
 #define REG_A6XX_RB_BLIT_BASE_GMEM				0x000088d6
 
 #define REG_A6XX_RB_BLIT_DST_INFO				0x000088d7
@@ -3684,6 +3705,12 @@ static inline uint32_t A6XX_RB_BLIT_DST_INFO_TILE_MODE(enum a6xx_tile_mode val)
 	return ((val) << A6XX_RB_BLIT_DST_INFO_TILE_MODE__SHIFT) & A6XX_RB_BLIT_DST_INFO_TILE_MODE__MASK;
 }
 #define A6XX_RB_BLIT_DST_INFO_FLAGS				0x00000004
+#define A6XX_RB_BLIT_DST_INFO_SAMPLES__MASK			0x00000018
+#define A6XX_RB_BLIT_DST_INFO_SAMPLES__SHIFT			3
+static inline uint32_t A6XX_RB_BLIT_DST_INFO_SAMPLES(enum a3xx_msaa_samples val)
+{
+	return ((val) << A6XX_RB_BLIT_DST_INFO_SAMPLES__SHIFT) & A6XX_RB_BLIT_DST_INFO_SAMPLES__MASK;
+}
 #define A6XX_RB_BLIT_DST_INFO_COLOR_FORMAT__MASK		0x00007f80
 #define A6XX_RB_BLIT_DST_INFO_COLOR_FORMAT__SHIFT		7
 static inline uint32_t A6XX_RB_BLIT_DST_INFO_COLOR_FORMAT(enum a6xx_color_fmt val)
@@ -3780,6 +3807,9 @@ static inline uint32_t A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT(enum a6xx_color_fmt val
 {
 	return ((val) << A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT__SHIFT) & A6XX_RB_2D_BLIT_CNTL_COLOR_FORMAT__MASK;
 }
+#define A6XX_RB_2D_BLIT_CNTL_SCISSOR				0x00010000
+
+#define REG_A6XX_RB_UNKNOWN_8C01				0x00008c01
 
 #define REG_A6XX_RB_2D_DST_INFO					0x00008c17
 #define A6XX_RB_2D_DST_INFO_COLOR_FORMAT__MASK			0x000000ff
@@ -4465,6 +4495,7 @@ static inline uint32_t A6XX_SP_FS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val)
 #define REG_A6XX_SP_BLEND_CNTL					0x0000a989
 #define A6XX_SP_BLEND_CNTL_ENABLED				0x00000001
 #define A6XX_SP_BLEND_CNTL_UNK8					0x00000100
+#define A6XX_SP_BLEND_CNTL_ALPHA_TO_COVERAGE			0x00000400
 
 #define REG_A6XX_SP_SRGB_CNTL					0x0000a98a
 #define A6XX_SP_SRGB_CNTL_SRGB_MRT0				0x00000001
@@ -4643,6 +4674,8 @@ static inline uint32_t A6XX_SP_FS_CONFIG_NSAMP(uint32_t val)
 
 #define REG_A6XX_SP_UNKNOWN_AB20				0x0000ab20
 
+#define REG_A6XX_SP_UNKNOWN_ACC0				0x0000acc0
+
 #define REG_A6XX_SP_UNKNOWN_AE00				0x0000ae00
 
 #define REG_A6XX_SP_UNKNOWN_AE03				0x0000ae03
@@ -4700,11 +4733,34 @@ static inline uint32_t A6XX_SP_PS_2D_SRC_INFO_COLOR_SWAP(enum a3xx_color_swap va
 	return ((val) << A6XX_SP_PS_2D_SRC_INFO_COLOR_SWAP__SHIFT) & A6XX_SP_PS_2D_SRC_INFO_COLOR_SWAP__MASK;
 }
 #define A6XX_SP_PS_2D_SRC_INFO_FLAGS				0x00001000
+#define A6XX_SP_PS_2D_SRC_INFO_FILTER				0x00010000
+
+#define REG_A6XX_SP_PS_2D_SRC_SIZE				0x0000b4c1
+#define A6XX_SP_PS_2D_SRC_SIZE_WIDTH__MASK			0x00007fff
+#define A6XX_SP_PS_2D_SRC_SIZE_WIDTH__SHIFT			0
+static inline uint32_t A6XX_SP_PS_2D_SRC_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << A6XX_SP_PS_2D_SRC_SIZE_WIDTH__SHIFT) & A6XX_SP_PS_2D_SRC_SIZE_WIDTH__MASK;
+}
+#define A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__MASK			0x3fff8000
+#define A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__SHIFT			15
+static inline uint32_t A6XX_SP_PS_2D_SRC_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__SHIFT) & A6XX_SP_PS_2D_SRC_SIZE_HEIGHT__MASK;
+}
 
 #define REG_A6XX_SP_PS_2D_SRC_LO				0x0000b4c2
 
 #define REG_A6XX_SP_PS_2D_SRC_HI				0x0000b4c3
 
+#define REG_A6XX_SP_PS_2D_SRC_PITCH				0x0000b4c4
+#define A6XX_SP_PS_2D_SRC_PITCH_PITCH__MASK			0x01fffe00
+#define A6XX_SP_PS_2D_SRC_PITCH_PITCH__SHIFT			9
+static inline uint32_t A6XX_SP_PS_2D_SRC_PITCH_PITCH(uint32_t val)
+{
+	return ((val >> 6) << A6XX_SP_PS_2D_SRC_PITCH_PITCH__SHIFT) & A6XX_SP_PS_2D_SRC_PITCH_PITCH__MASK;
+}
+
 #define REG_A6XX_SP_PS_2D_SRC_FLAGS_LO				0x0000b4ca
 
 #define REG_A6XX_SP_PS_2D_SRC_FLAGS_HI				0x0000b4cb
@@ -5033,6 +5089,12 @@ static inline uint32_t A6XX_TEX_CONST_0_MIPLVLS(uint32_t val)
 {
 	return ((val) << A6XX_TEX_CONST_0_MIPLVLS__SHIFT) & A6XX_TEX_CONST_0_MIPLVLS__MASK;
 }
+#define A6XX_TEX_CONST_0_SAMPLES__MASK				0x00300000
+#define A6XX_TEX_CONST_0_SAMPLES__SHIFT				20
+static inline uint32_t A6XX_TEX_CONST_0_SAMPLES(enum a3xx_msaa_samples val)
+{
+	return ((val) << A6XX_TEX_CONST_0_SAMPLES__SHIFT) & A6XX_TEX_CONST_0_SAMPLES__MASK;
+}
 #define A6XX_TEX_CONST_0_FMT__MASK				0x3fc00000
 #define A6XX_TEX_CONST_0_FMT__SHIFT				22
 static inline uint32_t A6XX_TEX_CONST_0_FMT(enum a6xx_tex_fmt val)
@@ -5365,5 +5427,9 @@ static inline uint32_t A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1_BYTEL15(uint32_t val)
 
 #define REG_A6XX_CX_DBGC_CFG_DBGBUS_TRACE_BUF2			0x00000030
 
+#define REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_0			0x00000001
+
+#define REG_A6XX_CX_MISC_SYSTEM_CACHE_CNTL_1			0x00000002
+
 
 #endif /* A6XX_XML */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index d4e98e5876bc..c58e953fefa3 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -51,10 +51,31 @@ static irqreturn_t a6xx_hfi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu)
+{
+	u32 val;
+
+	/* This can be called from gpu state code so make sure GMU is valid */
+	if (IS_ERR_OR_NULL(gmu->mmio))
+		return false;
+
+	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);
+
+	return !(val &
+		(A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_SPTPRAC_GDSC_POWER_OFF |
+		A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_SP_CLOCK_OFF));
+}
+
 /* Check to see if the GX rail is still powered */
-static bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
+bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
 {
-	u32 val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);
+	u32 val;
+
+	/* This can be called from gpu state code so make sure GMU is valid */
+	if (IS_ERR_OR_NULL(gmu->mmio))
+		return false;
+
+	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);
 
 	return !(val &
 		(A6XX_GMU_SPTPRAC_PWR_CLK_STATUS_GX_HM_GDSC_POWER_OFF |
@@ -153,7 +174,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 		val == 0xbabeface, 100, 10000);
 
 	if (ret)
-		dev_err(gmu->dev, "GMU firmware initialization timed out\n");
+		DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n");
 
 	return ret;
 }
@@ -168,7 +189,7 @@ static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu)
 	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_HFI_CTRL_STATUS, val,
 		val & 1, 100, 10000);
 	if (ret)
-		dev_err(gmu->dev, "Unable to start the HFI queues\n");
+		DRM_DEV_ERROR(gmu->dev, "Unable to start the HFI queues\n");
 
 	return ret;
 }
@@ -209,7 +230,7 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 		val & (1 << ack), 100, 10000);
 
 	if (ret)
-		dev_err(gmu->dev,
+		DRM_DEV_ERROR(gmu->dev,
 			"Timeout waiting for GMU OOB set %s: 0x%x\n",
 				name,
 				gmu_read(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO));
@@ -251,7 +272,7 @@ static int a6xx_sptprac_enable(struct a6xx_gmu *gmu)
 		(val & 0x38) == 0x28, 1, 100);
 
 	if (ret) {
-		dev_err(gmu->dev, "Unable to power on SPTPRAC: 0x%x\n",
+		DRM_DEV_ERROR(gmu->dev, "Unable to power on SPTPRAC: 0x%x\n",
 			gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS));
 	}
 
@@ -273,7 +294,7 @@ static void a6xx_sptprac_disable(struct a6xx_gmu *gmu)
 		(val & 0x04), 100, 10000);
 
 	if (ret)
-		dev_err(gmu->dev, "failed to power off SPTPRAC: 0x%x\n",
+		DRM_DEV_ERROR(gmu->dev, "failed to power off SPTPRAC: 0x%x\n",
 			gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS));
 }
 
@@ -317,7 +338,7 @@ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu)
 		/* Check to see if the GMU really did slumber */
 		if (gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE)
 			!= 0x0f) {
-			dev_err(gmu->dev, "The GMU did not go into slumber\n");
+			DRM_DEV_ERROR(gmu->dev, "The GMU did not go into slumber\n");
 			ret = -ETIMEDOUT;
 		}
 	}
@@ -339,23 +360,27 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu)
 	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_RSCC_CONTROL_ACK, val,
 		val & (1 << 1), 100, 10000);
 	if (ret) {
-		dev_err(gmu->dev, "Unable to power on the GPU RSC\n");
+		DRM_DEV_ERROR(gmu->dev, "Unable to power on the GPU RSC\n");
 		return ret;
 	}
 
 	ret = gmu_poll_timeout(gmu, REG_A6XX_RSCC_SEQ_BUSY_DRV0, val,
 		!val, 100, 10000);
 
-	if (!ret) {
-		gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0);
-
-		/* Re-enable the power counter */
-		gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1);
-		return 0;
+	if (ret) {
+		DRM_DEV_ERROR(gmu->dev, "GPU RSC sequence stuck while waking up the GPU\n");
+		return ret;
 	}
 
-	dev_err(gmu->dev, "GPU RSC sequence stuck while waking up the GPU\n");
-	return ret;
+	gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0);
+
+	/* Set up CX GMU counter 0 to count busy ticks */
+	gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, 0xff000000);
+	gmu_rmw(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0, 0xff, 0x20);
+
+	/* Enable the power counter */
+	gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1);
+	return 0;
 }
 
 static void a6xx_rpmh_stop(struct a6xx_gmu *gmu)
@@ -368,7 +393,7 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu)
 	ret = gmu_poll_timeout(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0,
 		val, val & (1 << 16), 100, 10000);
 	if (ret)
-		dev_err(gmu->dev, "Unable to power off the GPU RSC\n");
+		DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n");
 
 	gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 0);
 }
@@ -520,7 +545,7 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 
 		/* Sanity check the size of the firmware that was loaded */
 		if (adreno_gpu->fw[ADRENO_FW_GMU]->size > 0x8000) {
-			dev_err(gmu->dev,
+			DRM_DEV_ERROR(gmu->dev,
 				"GMU firmware is bigger than the available region\n");
 			return -EINVAL;
 		}
@@ -764,7 +789,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 		 */
 
 		if (ret)
-			dev_err(gmu->dev,
+			DRM_DEV_ERROR(gmu->dev,
 				"Unable to slumber GMU: status = 0%x/0%x\n",
 				gmu_read(gmu,
 					REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS),
@@ -843,7 +868,7 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu,
 			IOMMU_READ | IOMMU_WRITE);
 
 		if (ret) {
-			dev_err(gmu->dev, "Unable to map GMU buffer object\n");
+			DRM_DEV_ERROR(gmu->dev, "Unable to map GMU buffer object\n");
 
 			for (i = i - 1 ; i >= 0; i--)
 				iommu_unmap(gmu->domain,
@@ -969,12 +994,12 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes,
 		}
 
 		if (j == pri_count) {
-			dev_err(dev,
+			DRM_DEV_ERROR(dev,
 				"Level %u not found in in the RPMh list\n",
 					level);
-			dev_err(dev, "Available levels:\n");
+			DRM_DEV_ERROR(dev, "Available levels:\n");
 			for (j = 0; j < pri_count; j++)
-				dev_err(dev, "  %u\n", pri[j]);
+				DRM_DEV_ERROR(dev, "  %u\n", pri[j]);
 
 			return -EINVAL;
 		}
@@ -1081,7 +1106,7 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
 	 */
 	ret = dev_pm_opp_of_add_table(gmu->dev);
 	if (ret) {
-		dev_err(gmu->dev, "Unable to set the OPP table for the GMU\n");
+		DRM_DEV_ERROR(gmu->dev, "Unable to set the OPP table for the GMU\n");
 		return ret;
 	}
 
@@ -1122,13 +1147,13 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
 			IORESOURCE_MEM, name);
 
 	if (!res) {
-		dev_err(&pdev->dev, "Unable to find the %s registers\n", name);
+		DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name);
 		return ERR_PTR(-EINVAL);
 	}
 
 	ret = devm_ioremap(&pdev->dev, res->start, resource_size(res));
 	if (!ret) {
-		dev_err(&pdev->dev, "Unable to map the %s registers\n", name);
+		DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1145,7 +1170,7 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev,
 	ret = devm_request_irq(&pdev->dev, irq, handler, IRQF_TRIGGER_HIGH,
 		name, gmu);
 	if (ret) {
-		dev_err(&pdev->dev, "Unable to get interrupt %s\n", name);
+		DRM_DEV_ERROR(&pdev->dev, "Unable to get interrupt %s\n", name);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 35f765afae45..c721d9165d8e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -164,4 +164,7 @@ void a6xx_hfi_init(struct a6xx_gmu *gmu);
 int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state);
 void a6xx_hfi_stop(struct a6xx_gmu *gmu);
 
+bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu);
+bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu);
+
 #endif
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h
index db56f263ed77..1cc1c135236b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 631257c297fd..fefe773c989e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -4,6 +4,7 @@
 
 #include "msm_gem.h"
 #include "msm_mmu.h"
+#include "msm_gpu_trace.h"
 #include "a6xx_gpu.h"
 #include "a6xx_gmu.xml.h"
 
@@ -67,13 +68,36 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr);
 }
 
+static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
+		u64 iova)
+{
+	OUT_PKT7(ring, CP_REG_TO_MEM, 3);
+	OUT_RING(ring, counter | (1 << 30) | (2 << 18));
+	OUT_RING(ring, lower_32_bits(iova));
+	OUT_RING(ring, upper_32_bits(iova));
+}
+
 static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	struct msm_file_private *ctx)
 {
+	unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
 	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i;
 
+	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
+		rbmemptr_stats(ring, index, cpcycles_start));
+
+	/*
+	 * For PM4 the GMU register offsets are calculated from the base of the
+	 * GPU registers so we need to add 0x1a800 to the register value on A630
+	 * to get the right value from PM4.
+	 */
+	get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
+		rbmemptr_stats(ring, index, alwayson_start));
+
 	/* Invalidate CCU depth and color */
 	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
 	OUT_RING(ring, PC_CCU_INVALIDATE_DEPTH);
@@ -98,6 +122,11 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		}
 	}
 
+	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
+		rbmemptr_stats(ring, index, cpcycles_end));
+	get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
+		rbmemptr_stats(ring, index, alwayson_end));
+
 	/* Write the fence to the scratch register */
 	OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1);
 	OUT_RING(ring, submit->seqno);
@@ -112,6 +141,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
 	OUT_RING(ring, submit->seqno);
 
+	trace_msm_gpu_submit_flush(submit,
+		gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L,
+			REG_A6XX_GMU_ALWAYS_ON_COUNTER_H));
+
 	a6xx_flush(gpu, ring);
 }
 
@@ -300,6 +333,8 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
 
 			return ret;
 		}
+
+		msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw");
 	}
 
 	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,
@@ -387,14 +422,6 @@ 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);
 
-	/* FIXME: not sure if this should live here or in a6xx_gmu.c */
-	gmu_write(&a6xx_gpu->gmu,  REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK,
-		0xff000000);
-	gmu_rmw(&a6xx_gpu->gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0,
-		0xff, 0x20);
-	gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE,
-		0x01);
-
 	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);
@@ -481,7 +508,7 @@ out:
 
 static void a6xx_dump(struct msm_gpu *gpu)
 {
-	dev_info(&gpu->pdev->dev, "status:   %08x\n",
+	DRM_DEV_INFO(&gpu->pdev->dev, "status:   %08x\n",
 			gpu_read(gpu, REG_A6XX_RBBM_STATUS));
 	adreno_dump(gpu);
 }
@@ -498,7 +525,7 @@ static void a6xx_recover(struct msm_gpu *gpu)
 	adreno_dump_info(gpu);
 
 	for (i = 0; i < 8; i++)
-		dev_info(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i,
+		DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i,
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i)));
 
 	if (hang_debug)
@@ -645,33 +672,6 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
-static const u32 a6xx_registers[] = {
-	0x0000, 0x0002, 0x0010, 0x0010, 0x0012, 0x0012, 0x0018, 0x001b,
-	0x001e, 0x0032, 0x0038, 0x003c, 0x0042, 0x0042, 0x0044, 0x0044,
-	0x0047, 0x0047, 0x0056, 0x0056, 0x00ad, 0x00ae, 0x00b0, 0x00fb,
-	0x0100, 0x011d, 0x0200, 0x020d, 0x0210, 0x0213, 0x0218, 0x023d,
-	0x0400, 0x04f9, 0x0500, 0x0500, 0x0505, 0x050b, 0x050e, 0x0511,
-	0x0533, 0x0533, 0x0540, 0x0555, 0x0800, 0x0808, 0x0810, 0x0813,
-	0x0820, 0x0821, 0x0823, 0x0827, 0x0830, 0x0833, 0x0840, 0x0843,
-	0x084f, 0x086f, 0x0880, 0x088a, 0x08a0, 0x08ab, 0x08c0, 0x08c4,
-	0x08d0, 0x08dd, 0x08f0, 0x08f3, 0x0900, 0x0903, 0x0908, 0x0911,
-	0x0928, 0x093e, 0x0942, 0x094d, 0x0980, 0x0984, 0x098d, 0x0996,
-	0x0998, 0x099e, 0x09a0, 0x09a6, 0x09a8, 0x09ae, 0x09b0, 0x09b1,
-	0x09c2, 0x09c8, 0x0a00, 0x0a03, 0x0c00, 0x0c04, 0x0c06, 0x0c06,
-	0x0c10, 0x0cd9, 0x0e00, 0x0e0e, 0x0e10, 0x0e13, 0x0e17, 0x0e19,
-	0x0e1c, 0x0e2b, 0x0e30, 0x0e32, 0x0e38, 0x0e39, 0x8600, 0x8601,
-	0x8610, 0x861b, 0x8620, 0x8620, 0x8628, 0x862b, 0x8630, 0x8637,
-	0x8e01, 0x8e01, 0x8e04, 0x8e05, 0x8e07, 0x8e08, 0x8e0c, 0x8e0c,
-	0x8e10, 0x8e1c, 0x8e20, 0x8e25, 0x8e28, 0x8e28, 0x8e2c, 0x8e2f,
-	0x8e3b, 0x8e3e, 0x8e40, 0x8e43, 0x8e50, 0x8e5e, 0x8e70, 0x8e77,
-	0x9600, 0x9604, 0x9624, 0x9637, 0x9e00, 0x9e01, 0x9e03, 0x9e0e,
-	0x9e11, 0x9e16, 0x9e19, 0x9e19, 0x9e1c, 0x9e1c, 0x9e20, 0x9e23,
-	0x9e30, 0x9e31, 0x9e34, 0x9e34, 0x9e70, 0x9e72, 0x9e78, 0x9e79,
-	0x9e80, 0x9fff, 0xa600, 0xa601, 0xa603, 0xa603, 0xa60a, 0xa60a,
-	0xa610, 0xa617, 0xa630, 0xa630,
-	~0
-};
-
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -724,14 +724,6 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
-#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
-static void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct drm_printer *p)
-{
-	adreno_show(gpu, state, p);
-}
-#endif
-
 static struct msm_ringbuffer *a6xx_active_ring(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -746,8 +738,7 @@ static void a6xx_destroy(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 
 	if (a6xx_gpu->sqe_bo) {
-		if (a6xx_gpu->sqe_iova)
-			msm_gem_put_iova(a6xx_gpu->sqe_bo, gpu->aspace);
+		msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
 		drm_gem_object_put_unlocked(a6xx_gpu->sqe_bo);
 	}
 
@@ -796,6 +787,8 @@ static const struct adreno_gpu_funcs funcs = {
 		.gpu_busy = a6xx_gpu_busy,
 		.gpu_get_freq = a6xx_gmu_get_freq,
 		.gpu_set_freq = a6xx_gmu_set_freq,
+		.gpu_state_get = a6xx_gpu_state_get,
+		.gpu_state_put = a6xx_gpu_state_put,
 	},
 	.get_timestamp = a6xx_get_timestamp,
 };
@@ -817,7 +810,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	adreno_gpu = &a6xx_gpu->base;
 	gpu = &adreno_gpu->base;
 
-	adreno_gpu->registers = a6xx_registers;
+	adreno_gpu->registers = NULL;
 	adreno_gpu->reg_offsets = a6xx_register_offsets;
 
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 4127dcebc202..528a4cfe07cd 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -56,6 +56,14 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
 
 int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
 void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu);
+
 void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq);
 unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu);
+
+void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p);
+
+struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu);
+int a6xx_gpu_state_put(struct msm_gpu_state *state);
+
 #endif /* __A6XX_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
new file mode 100644
index 000000000000..e686331fa089
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -0,0 +1,1165 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+
+#include <linux/ascii85.h>
+#include "msm_gem.h"
+#include "a6xx_gpu.h"
+#include "a6xx_gmu.h"
+#include "a6xx_gpu_state.h"
+#include "a6xx_gmu.xml.h"
+
+struct a6xx_gpu_state_obj {
+	const void *handle;
+	u32 *data;
+};
+
+struct a6xx_gpu_state {
+	struct msm_gpu_state base;
+
+	struct a6xx_gpu_state_obj *gmu_registers;
+	int nr_gmu_registers;
+
+	struct a6xx_gpu_state_obj *registers;
+	int nr_registers;
+
+	struct a6xx_gpu_state_obj *shaders;
+	int nr_shaders;
+
+	struct a6xx_gpu_state_obj *clusters;
+	int nr_clusters;
+
+	struct a6xx_gpu_state_obj *dbgahb_clusters;
+	int nr_dbgahb_clusters;
+
+	struct a6xx_gpu_state_obj *indexed_regs;
+	int nr_indexed_regs;
+
+	struct a6xx_gpu_state_obj *debugbus;
+	int nr_debugbus;
+
+	struct a6xx_gpu_state_obj *vbif_debugbus;
+
+	struct a6xx_gpu_state_obj *cx_debugbus;
+	int nr_cx_debugbus;
+
+	struct list_head objs;
+};
+
+static inline int CRASHDUMP_WRITE(u64 *in, u32 reg, u32 val)
+{
+	in[0] = val;
+	in[1] = (((u64) reg) << 44 | (1 << 21) | 1);
+
+	return 2;
+}
+
+static inline int CRASHDUMP_READ(u64 *in, u32 reg, u32 dwords, u64 target)
+{
+	in[0] = target;
+	in[1] = (((u64) reg) << 44 | dwords);
+
+	return 2;
+}
+
+static inline int CRASHDUMP_FINI(u64 *in)
+{
+	in[0] = 0;
+	in[1] = 0;
+
+	return 2;
+}
+
+struct a6xx_crashdumper {
+	void *ptr;
+	struct drm_gem_object *bo;
+	u64 iova;
+};
+
+struct a6xx_state_memobj {
+	struct list_head node;
+	unsigned long long data[];
+};
+
+void *state_kcalloc(struct a6xx_gpu_state *a6xx_state, int nr, size_t objsize)
+{
+	struct a6xx_state_memobj *obj =
+		kzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL);
+
+	if (!obj)
+		return NULL;
+
+	list_add_tail(&obj->node, &a6xx_state->objs);
+	return &obj->data;
+}
+
+void *state_kmemdup(struct a6xx_gpu_state *a6xx_state, void *src,
+		size_t size)
+{
+	void *dst = state_kcalloc(a6xx_state, 1, size);
+
+	if (dst)
+		memcpy(dst, src, size);
+	return dst;
+}
+
+/*
+ * Allocate 1MB for the crashdumper scratch region - 8k for the script and
+ * the rest for the data
+ */
+#define A6XX_CD_DATA_OFFSET 8192
+#define A6XX_CD_DATA_SIZE  (SZ_1M - 8192)
+
+static int a6xx_crashdumper_init(struct msm_gpu *gpu,
+		struct a6xx_crashdumper *dumper)
+{
+	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+		SZ_1M, MSM_BO_UNCACHED, gpu->aspace,
+		&dumper->bo, &dumper->iova);
+
+	if (!IS_ERR(dumper->ptr))
+		msm_gem_object_set_name(dumper->bo, "crashdump");
+
+	return PTR_ERR_OR_ZERO(dumper->ptr);
+}
+
+static int a6xx_crashdumper_run(struct msm_gpu *gpu,
+		struct a6xx_crashdumper *dumper)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	u32 val;
+	int ret;
+
+	if (IS_ERR_OR_NULL(dumper->ptr))
+		return -EINVAL;
+
+	if (!a6xx_gmu_sptprac_is_on(&a6xx_gpu->gmu))
+		return -EINVAL;
+
+	/* Make sure all pending memory writes are posted */
+	wmb();
+
+	gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO,
+		REG_A6XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+
+	gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1);
+
+	ret = gpu_poll_timeout(gpu, REG_A6XX_CP_CRASH_DUMP_STATUS, val,
+		val & 0x02, 100, 10000);
+
+	gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 0);
+
+	return ret;
+}
+
+/* read a value from the GX debug bus */
+static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset,
+		u32 *data)
+{
+	u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
+		A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_C, reg);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_D, reg);
+
+	/* Wait 1 us to make sure the data is flowing */
+	udelay(1);
+
+	data[0] = gpu_read(gpu, REG_A6XX_DBGC_CFG_DBGBUS_TRACE_BUF2);
+	data[1] = gpu_read(gpu, REG_A6XX_DBGC_CFG_DBGBUS_TRACE_BUF1);
+
+	return 2;
+}
+
+#define cxdbg_write(ptr, offset, val) \
+	msm_writel((val), (ptr) + ((offset) << 2))
+
+#define cxdbg_read(ptr, offset) \
+	msm_readl((ptr) + ((offset) << 2))
+
+/* read a value from the CX debug bus */
+static int cx_debugbus_read(void *__iomem cxdbg, u32 block, u32 offset,
+		u32 *data)
+{
+	u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
+		A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+
+	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg);
+	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg);
+	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_C, reg);
+	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_D, reg);
+
+	/* Wait 1 us to make sure the data is flowing */
+	udelay(1);
+
+	data[0] = cxdbg_read(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_TRACE_BUF2);
+	data[1] = cxdbg_read(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_TRACE_BUF1);
+
+	return 2;
+}
+
+/* Read a chunk of data from the VBIF debug bus */
+static int vbif_debugbus_read(struct msm_gpu *gpu, u32 ctrl0, u32 ctrl1,
+		u32 reg, int count, u32 *data)
+{
+	int i;
+
+	gpu_write(gpu, ctrl0, reg);
+
+	for (i = 0; i < count; i++) {
+		gpu_write(gpu, ctrl1, i);
+		data[i] = gpu_read(gpu, REG_A6XX_VBIF_TEST_BUS_OUT);
+	}
+
+	return count;
+}
+
+#define AXI_ARB_BLOCKS 2
+#define XIN_AXI_BLOCKS 5
+#define XIN_CORE_BLOCKS 4
+
+#define VBIF_DEBUGBUS_BLOCK_SIZE \
+	((16 * AXI_ARB_BLOCKS) + \
+	 (18 * XIN_AXI_BLOCKS) + \
+	 (12 * XIN_CORE_BLOCKS))
+
+static void a6xx_get_vbif_debugbus_block(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		struct a6xx_gpu_state_obj *obj)
+{
+	u32 clk, *ptr;
+	int i;
+
+	obj->data = state_kcalloc(a6xx_state, VBIF_DEBUGBUS_BLOCK_SIZE,
+		sizeof(u32));
+	if (!obj->data)
+		return;
+
+	obj->handle = NULL;
+
+	/* Get the current clock setting */
+	clk = gpu_read(gpu, REG_A6XX_VBIF_CLKON);
+
+	/* Force on the bus so we can read it */
+	gpu_write(gpu, REG_A6XX_VBIF_CLKON,
+		clk | A6XX_VBIF_CLKON_FORCE_ON_TESTBUS);
+
+	/* We will read from BUS2 first, so disable BUS1 */
+	gpu_write(gpu, REG_A6XX_VBIF_TEST_BUS1_CTRL0, 0);
+
+	/* Enable the VBIF bus for reading */
+	gpu_write(gpu, REG_A6XX_VBIF_TEST_BUS_OUT_CTRL, 1);
+
+	ptr = obj->data;
+
+	for (i = 0; i < AXI_ARB_BLOCKS; i++)
+		ptr += vbif_debugbus_read(gpu,
+			REG_A6XX_VBIF_TEST_BUS2_CTRL0,
+			REG_A6XX_VBIF_TEST_BUS2_CTRL1,
+			1 << (i + 16), 16, ptr);
+
+	for (i = 0; i < XIN_AXI_BLOCKS; i++)
+		ptr += vbif_debugbus_read(gpu,
+			REG_A6XX_VBIF_TEST_BUS2_CTRL0,
+			REG_A6XX_VBIF_TEST_BUS2_CTRL1,
+			1 << i, 18, ptr);
+
+	/* Stop BUS2 so we can turn on BUS1 */
+	gpu_write(gpu, REG_A6XX_VBIF_TEST_BUS2_CTRL0, 0);
+
+	for (i = 0; i < XIN_CORE_BLOCKS; i++)
+		ptr += vbif_debugbus_read(gpu,
+			REG_A6XX_VBIF_TEST_BUS1_CTRL0,
+			REG_A6XX_VBIF_TEST_BUS1_CTRL1,
+			1 << i, 12, ptr);
+
+	/* Restore the VBIF clock setting */
+	gpu_write(gpu, REG_A6XX_VBIF_CLKON, clk);
+}
+
+static void a6xx_get_debugbus_block(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_debugbus_block *block,
+		struct a6xx_gpu_state_obj *obj)
+{
+	int i;
+	u32 *ptr;
+
+	obj->data = state_kcalloc(a6xx_state, block->count, sizeof(u64));
+	if (!obj->data)
+		return;
+
+	obj->handle = block;
+
+	for (ptr = obj->data, i = 0; i < block->count; i++)
+		ptr += debugbus_read(gpu, block->id, i, ptr);
+}
+
+static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_debugbus_block *block,
+		struct a6xx_gpu_state_obj *obj)
+{
+	int i;
+	u32 *ptr;
+
+	obj->data = state_kcalloc(a6xx_state, block->count, sizeof(u64));
+	if (!obj->data)
+		return;
+
+	obj->handle = block;
+
+	for (ptr = obj->data, i = 0; i < block->count; i++)
+		ptr += cx_debugbus_read(cxdbg, block->id, i, ptr);
+}
+
+static void a6xx_get_debugbus(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state)
+{
+	struct resource *res;
+	void __iomem *cxdbg = NULL;
+
+	/* Set up the GX debug bus */
+
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT,
+		A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf));
+
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM,
+		A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf));
+
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0);
+
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0, 0x76543210);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1, 0xFEDCBA98);
+
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0);
+	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0);
+
+	/* Set up the CX debug bus - it lives elsewhere in the system so do a
+	 * temporary ioremap for the registers
+	 */
+	res = platform_get_resource_byname(gpu->pdev, IORESOURCE_MEM,
+			"cx_dbgc");
+
+	if (res)
+		cxdbg = ioremap(res->start, resource_size(res));
+
+	if (cxdbg) {
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT,
+			A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf));
+
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM,
+			A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf));
+
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0);
+
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0,
+			0x76543210);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1,
+			0xFEDCBA98);
+
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0);
+		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0);
+	}
+
+	a6xx_state->debugbus = state_kcalloc(a6xx_state,
+		ARRAY_SIZE(a6xx_debugbus_blocks),
+		sizeof(*a6xx_state->debugbus));
+
+	if (a6xx_state->debugbus) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(a6xx_debugbus_blocks); i++)
+			a6xx_get_debugbus_block(gpu,
+				a6xx_state,
+				&a6xx_debugbus_blocks[i],
+				&a6xx_state->debugbus[i]);
+
+		a6xx_state->nr_debugbus = ARRAY_SIZE(a6xx_debugbus_blocks);
+	}
+
+	a6xx_state->vbif_debugbus =
+		state_kcalloc(a6xx_state, 1,
+			sizeof(*a6xx_state->vbif_debugbus));
+
+	if (a6xx_state->vbif_debugbus)
+		a6xx_get_vbif_debugbus_block(gpu, a6xx_state,
+			a6xx_state->vbif_debugbus);
+
+	if (cxdbg) {
+		a6xx_state->cx_debugbus =
+			state_kcalloc(a6xx_state,
+			ARRAY_SIZE(a6xx_cx_debugbus_blocks),
+			sizeof(*a6xx_state->cx_debugbus));
+
+		if (a6xx_state->cx_debugbus) {
+			int i;
+
+			for (i = 0; i < ARRAY_SIZE(a6xx_cx_debugbus_blocks); i++)
+				a6xx_get_cx_debugbus_block(cxdbg,
+					a6xx_state,
+					&a6xx_cx_debugbus_blocks[i],
+					&a6xx_state->cx_debugbus[i]);
+
+			a6xx_state->nr_cx_debugbus =
+				ARRAY_SIZE(a6xx_cx_debugbus_blocks);
+		}
+
+		iounmap(cxdbg);
+	}
+}
+
+#define RANGE(reg, a) ((reg)[(a) + 1] - (reg)[(a)] + 1)
+
+/* Read a data cluster from behind the AHB aperture */
+static void a6xx_get_dbgahb_cluster(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_dbgahb_cluster *dbgahb,
+		struct a6xx_gpu_state_obj *obj,
+		struct a6xx_crashdumper *dumper)
+{
+	u64 *in = dumper->ptr;
+	u64 out = dumper->iova + A6XX_CD_DATA_OFFSET;
+	size_t datasize;
+	int i, regcount = 0;
+
+	for (i = 0; i < A6XX_NUM_CONTEXTS; i++) {
+		int j;
+
+		in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL,
+			(dbgahb->statetype + i * 2) << 8);
+
+		for (j = 0; j < dbgahb->count; j += 2) {
+			int count = RANGE(dbgahb->registers, j);
+			u32 offset = REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE +
+				dbgahb->registers[j] - (dbgahb->base >> 2);
+
+			in += CRASHDUMP_READ(in, offset, count, out);
+
+			out += count * sizeof(u32);
+
+			if (i == 0)
+				regcount += count;
+		}
+	}
+
+	CRASHDUMP_FINI(in);
+
+	datasize = regcount * A6XX_NUM_CONTEXTS * sizeof(u32);
+
+	if (WARN_ON(datasize > A6XX_CD_DATA_SIZE))
+		return;
+
+	if (a6xx_crashdumper_run(gpu, dumper))
+		return;
+
+	obj->handle = dbgahb;
+	obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET,
+		datasize);
+}
+
+static void a6xx_get_dbgahb_clusters(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		struct a6xx_crashdumper *dumper)
+{
+	int i;
+
+	a6xx_state->dbgahb_clusters = state_kcalloc(a6xx_state,
+		ARRAY_SIZE(a6xx_dbgahb_clusters),
+		sizeof(*a6xx_state->dbgahb_clusters));
+
+	if (!a6xx_state->dbgahb_clusters)
+		return;
+
+	a6xx_state->nr_dbgahb_clusters = ARRAY_SIZE(a6xx_dbgahb_clusters);
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_dbgahb_clusters); i++)
+		a6xx_get_dbgahb_cluster(gpu, a6xx_state,
+			&a6xx_dbgahb_clusters[i],
+			&a6xx_state->dbgahb_clusters[i], dumper);
+}
+
+/* Read a data cluster from the CP aperture with the crashdumper */
+static void a6xx_get_cluster(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_cluster *cluster,
+		struct a6xx_gpu_state_obj *obj,
+		struct a6xx_crashdumper *dumper)
+{
+	u64 *in = dumper->ptr;
+	u64 out = dumper->iova + A6XX_CD_DATA_OFFSET;
+	size_t datasize;
+	int i, regcount = 0;
+
+	/* Some clusters need a selector register to be programmed too */
+	if (cluster->sel_reg)
+		in += CRASHDUMP_WRITE(in, cluster->sel_reg, cluster->sel_val);
+
+	for (i = 0; i < A6XX_NUM_CONTEXTS; i++) {
+		int j;
+
+		in += CRASHDUMP_WRITE(in, REG_A6XX_CP_APERTURE_CNTL_CD,
+			(cluster->id << 8) | (i << 4) | i);
+
+		for (j = 0; j < cluster->count; j += 2) {
+			int count = RANGE(cluster->registers, j);
+
+			in += CRASHDUMP_READ(in, cluster->registers[j],
+				count, out);
+
+			out += count * sizeof(u32);
+
+			if (i == 0)
+				regcount += count;
+		}
+	}
+
+	CRASHDUMP_FINI(in);
+
+	datasize = regcount * A6XX_NUM_CONTEXTS * sizeof(u32);
+
+	if (WARN_ON(datasize > A6XX_CD_DATA_SIZE))
+		return;
+
+	if (a6xx_crashdumper_run(gpu, dumper))
+		return;
+
+	obj->handle = cluster;
+	obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET,
+		datasize);
+}
+
+static void a6xx_get_clusters(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		struct a6xx_crashdumper *dumper)
+{
+	int i;
+
+	a6xx_state->clusters = state_kcalloc(a6xx_state,
+		ARRAY_SIZE(a6xx_clusters), sizeof(*a6xx_state->clusters));
+
+	if (!a6xx_state->clusters)
+		return;
+
+	a6xx_state->nr_clusters = ARRAY_SIZE(a6xx_clusters);
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_clusters); i++)
+		a6xx_get_cluster(gpu, a6xx_state, &a6xx_clusters[i],
+			&a6xx_state->clusters[i], dumper);
+}
+
+/* Read a shader / debug block from the HLSQ aperture with the crashdumper */
+static void a6xx_get_shader_block(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_shader_block *block,
+		struct a6xx_gpu_state_obj *obj,
+		struct a6xx_crashdumper *dumper)
+{
+	u64 *in = dumper->ptr;
+	size_t datasize = block->size * A6XX_NUM_SHADER_BANKS * sizeof(u32);
+	int i;
+
+	if (WARN_ON(datasize > A6XX_CD_DATA_SIZE))
+		return;
+
+	for (i = 0; i < A6XX_NUM_SHADER_BANKS; i++) {
+		in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL,
+			(block->type << 8) | i);
+
+		in += CRASHDUMP_READ(in, REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE,
+			block->size, dumper->iova + A6XX_CD_DATA_OFFSET);
+	}
+
+	CRASHDUMP_FINI(in);
+
+	if (a6xx_crashdumper_run(gpu, dumper))
+		return;
+
+	obj->handle = block;
+	obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET,
+		datasize);
+}
+
+static void a6xx_get_shaders(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		struct a6xx_crashdumper *dumper)
+{
+	int i;
+
+	a6xx_state->shaders = state_kcalloc(a6xx_state,
+		ARRAY_SIZE(a6xx_shader_blocks), sizeof(*a6xx_state->shaders));
+
+	if (!a6xx_state->shaders)
+		return;
+
+	a6xx_state->nr_shaders = ARRAY_SIZE(a6xx_shader_blocks);
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_shader_blocks); i++)
+		a6xx_get_shader_block(gpu, a6xx_state, &a6xx_shader_blocks[i],
+			&a6xx_state->shaders[i], dumper);
+}
+
+/* Read registers from behind the HLSQ aperture with the crashdumper */
+static void a6xx_get_crashdumper_hlsq_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_registers *regs,
+		struct a6xx_gpu_state_obj *obj,
+		struct a6xx_crashdumper *dumper)
+
+{
+	u64 *in = dumper->ptr;
+	u64 out = dumper->iova + A6XX_CD_DATA_OFFSET;
+	int i, regcount = 0;
+
+	in += CRASHDUMP_WRITE(in, REG_A6XX_HLSQ_DBG_READ_SEL, regs->val1);
+
+	for (i = 0; i < regs->count; i += 2) {
+		u32 count = RANGE(regs->registers, i);
+		u32 offset = REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE +
+			regs->registers[i] - (regs->val0 >> 2);
+
+		in += CRASHDUMP_READ(in, offset, count, out);
+
+		out += count * sizeof(u32);
+		regcount += count;
+	}
+
+	CRASHDUMP_FINI(in);
+
+	if (WARN_ON((regcount * sizeof(u32)) > A6XX_CD_DATA_SIZE))
+		return;
+
+	if (a6xx_crashdumper_run(gpu, dumper))
+		return;
+
+	obj->handle = regs;
+	obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET,
+		regcount * sizeof(u32));
+}
+
+/* Read a block of registers using the crashdumper */
+static void a6xx_get_crashdumper_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_registers *regs,
+		struct a6xx_gpu_state_obj *obj,
+		struct a6xx_crashdumper *dumper)
+
+{
+	u64 *in = dumper->ptr;
+	u64 out = dumper->iova + A6XX_CD_DATA_OFFSET;
+	int i, regcount = 0;
+
+	/* Some blocks might need to program a selector register first */
+	if (regs->val0)
+		in += CRASHDUMP_WRITE(in, regs->val0, regs->val1);
+
+	for (i = 0; i < regs->count; i += 2) {
+		u32 count = RANGE(regs->registers, i);
+
+		in += CRASHDUMP_READ(in, regs->registers[i], count, out);
+
+		out += count * sizeof(u32);
+		regcount += count;
+	}
+
+	CRASHDUMP_FINI(in);
+
+	if (WARN_ON((regcount * sizeof(u32)) > A6XX_CD_DATA_SIZE))
+		return;
+
+	if (a6xx_crashdumper_run(gpu, dumper))
+		return;
+
+	obj->handle = regs;
+	obj->data = state_kmemdup(a6xx_state, dumper->ptr + A6XX_CD_DATA_OFFSET,
+		regcount * sizeof(u32));
+}
+
+/* Read a block of registers via AHB */
+static void a6xx_get_ahb_gpu_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_registers *regs,
+		struct a6xx_gpu_state_obj *obj)
+{
+	int i, regcount = 0, index = 0;
+
+	for (i = 0; i < regs->count; i += 2)
+		regcount += RANGE(regs->registers, i);
+
+	obj->handle = (const void *) regs;
+	obj->data = state_kcalloc(a6xx_state, regcount, sizeof(u32));
+	if (!obj->data)
+		return;
+
+	for (i = 0; i < regs->count; i += 2) {
+		u32 count = RANGE(regs->registers, i);
+		int j;
+
+		for (j = 0; j < count; j++)
+			obj->data[index++] = gpu_read(gpu,
+				regs->registers[i] + j);
+	}
+}
+
+/* Read a block of GMU registers */
+static void _a6xx_get_gmu_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_registers *regs,
+		struct a6xx_gpu_state_obj *obj)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	int i, regcount = 0, index = 0;
+
+	for (i = 0; i < regs->count; i += 2)
+		regcount += RANGE(regs->registers, i);
+
+	obj->handle = (const void *) regs;
+	obj->data = state_kcalloc(a6xx_state, regcount, sizeof(u32));
+	if (!obj->data)
+		return;
+
+	for (i = 0; i < regs->count; i += 2) {
+		u32 count = RANGE(regs->registers, i);
+		int j;
+
+		for (j = 0; j < count; j++)
+			obj->data[index++] = gmu_read(gmu,
+				regs->registers[i] + j);
+	}
+}
+
+static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+
+	a6xx_state->gmu_registers = state_kcalloc(a6xx_state,
+		2, sizeof(*a6xx_state->gmu_registers));
+
+	if (!a6xx_state->gmu_registers)
+		return;
+
+	a6xx_state->nr_gmu_registers = 2;
+
+	/* Get the CX GMU registers from AHB */
+	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0],
+		&a6xx_state->gmu_registers[0]);
+
+	if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu))
+		return;
+
+	/* Set the fence to ALLOW mode so we can access the registers */
+	gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0);
+
+	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1],
+		&a6xx_state->gmu_registers[1]);
+}
+
+static void a6xx_get_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		struct a6xx_crashdumper *dumper)
+{
+	int i, count = ARRAY_SIZE(a6xx_ahb_reglist) +
+		ARRAY_SIZE(a6xx_reglist) +
+		ARRAY_SIZE(a6xx_hlsq_reglist);
+	int index = 0;
+
+	a6xx_state->registers = state_kcalloc(a6xx_state,
+		count, sizeof(*a6xx_state->registers));
+
+	if (!a6xx_state->registers)
+		return;
+
+	a6xx_state->nr_registers = count;
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_ahb_reglist); i++)
+		a6xx_get_ahb_gpu_registers(gpu,
+			a6xx_state, &a6xx_ahb_reglist[i],
+			&a6xx_state->registers[index++]);
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++)
+		a6xx_get_crashdumper_registers(gpu,
+			a6xx_state, &a6xx_reglist[i],
+			&a6xx_state->registers[index++],
+			dumper);
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_hlsq_reglist); i++)
+		a6xx_get_crashdumper_hlsq_registers(gpu,
+			a6xx_state, &a6xx_hlsq_reglist[i],
+			&a6xx_state->registers[index++],
+			dumper);
+}
+
+/* Read a block of data from an indexed register pair */
+static void a6xx_get_indexed_regs(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state,
+		const struct a6xx_indexed_registers *indexed,
+		struct a6xx_gpu_state_obj *obj)
+{
+	int i;
+
+	obj->handle = (const void *) indexed;
+	obj->data = state_kcalloc(a6xx_state, indexed->count, sizeof(u32));
+	if (!obj->data)
+		return;
+
+	/* All the indexed banks start at address 0 */
+	gpu_write(gpu, indexed->addr, 0);
+
+	/* Read the data - each read increments the internal address by 1 */
+	for (i = 0; i < indexed->count; i++)
+		obj->data[i] = gpu_read(gpu, indexed->data);
+}
+
+static void a6xx_get_indexed_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state)
+{
+	u32 mempool_size;
+	int count = ARRAY_SIZE(a6xx_indexed_reglist) + 1;
+	int i;
+
+	a6xx_state->indexed_regs = state_kcalloc(a6xx_state, count,
+		sizeof(a6xx_state->indexed_regs));
+	if (!a6xx_state->indexed_regs)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(a6xx_indexed_reglist); i++)
+		a6xx_get_indexed_regs(gpu, a6xx_state, &a6xx_indexed_reglist[i],
+			&a6xx_state->indexed_regs[i]);
+
+	/* Set the CP mempool size to 0 to stabilize it while dumping */
+	mempool_size = gpu_read(gpu, REG_A6XX_CP_MEM_POOL_SIZE);
+	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 0);
+
+	/* Get the contents of the CP mempool */
+	a6xx_get_indexed_regs(gpu, a6xx_state, &a6xx_cp_mempool_indexed,
+		&a6xx_state->indexed_regs[i]);
+
+	/*
+	 * Offset 0x2000 in the mempool is the size - copy the saved size over
+	 * so the data is consistent
+	 */
+	a6xx_state->indexed_regs[i].data[0x2000] = mempool_size;
+
+	/* Restore the size in the hardware */
+	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size);
+
+	a6xx_state->nr_indexed_regs = count;
+}
+
+struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct a6xx_crashdumper dumper = { 0 };
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	struct a6xx_gpu_state *a6xx_state = kzalloc(sizeof(*a6xx_state),
+		GFP_KERNEL);
+
+	if (!a6xx_state)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&a6xx_state->objs);
+
+	/* Get the generic state from the adreno core */
+	adreno_gpu_state_get(gpu, &a6xx_state->base);
+
+	a6xx_get_gmu_registers(gpu, a6xx_state);
+
+	/* If GX isn't on the rest of the data isn't going to be accessible */
+	if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu))
+		return &a6xx_state->base;
+
+	/* Get the banks of indexed registers */
+	a6xx_get_indexed_registers(gpu, a6xx_state);
+
+	/* Try to initialize the crashdumper */
+	if (!a6xx_crashdumper_init(gpu, &dumper)) {
+		a6xx_get_registers(gpu, a6xx_state, &dumper);
+		a6xx_get_shaders(gpu, a6xx_state, &dumper);
+		a6xx_get_clusters(gpu, a6xx_state, &dumper);
+		a6xx_get_dbgahb_clusters(gpu, a6xx_state, &dumper);
+
+		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
+	}
+
+	a6xx_get_debugbus(gpu, a6xx_state);
+
+	return  &a6xx_state->base;
+}
+
+void a6xx_gpu_state_destroy(struct kref *kref)
+{
+	struct a6xx_state_memobj *obj, *tmp;
+	struct msm_gpu_state *state = container_of(kref,
+			struct msm_gpu_state, ref);
+	struct a6xx_gpu_state *a6xx_state = container_of(state,
+			struct a6xx_gpu_state, base);
+
+	list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node)
+		kfree(obj);
+
+	adreno_gpu_state_destroy(state);
+	kfree(a6xx_state);
+}
+
+int a6xx_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, a6xx_gpu_state_destroy);
+}
+
+static void a6xx_show_registers(const u32 *registers, u32 *data, size_t count,
+		struct drm_printer *p)
+{
+	int i, index = 0;
+
+	if (!data)
+		return;
+
+	for (i = 0; i < count; i += 2) {
+		u32 count = RANGE(registers, i);
+		u32 offset = registers[i];
+		int j;
+
+		for (j = 0; j < count; index++, offset++, j++) {
+			if (data[index] == 0xdeafbead)
+				continue;
+
+			drm_printf(p, "  - { offset: 0x%06x, value: 0x%08x }\n",
+				offset << 2, data[index]);
+		}
+	}
+}
+
+static void print_ascii85(struct drm_printer *p, size_t len, u32 *data)
+{
+	char out[ASCII85_BUFSZ];
+	long i, l, datalen = 0;
+
+	for (i = 0; i < len >> 2; i++) {
+		if (data[i])
+			datalen = (i + 1) << 2;
+	}
+
+	if (datalen == 0)
+		return;
+
+	drm_puts(p, "    data: !!ascii85 |\n");
+	drm_puts(p, "      ");
+
+
+	l = ascii85_encode_len(datalen);
+
+	for (i = 0; i < l; i++)
+		drm_puts(p, ascii85_encode(data[i], out));
+
+	drm_puts(p, "\n");
+}
+
+static void print_name(struct drm_printer *p, const char *fmt, const char *name)
+{
+	drm_puts(p, fmt);
+	drm_puts(p, name);
+	drm_puts(p, "\n");
+}
+
+static void a6xx_show_shader(struct a6xx_gpu_state_obj *obj,
+		struct drm_printer *p)
+{
+	const struct a6xx_shader_block *block = obj->handle;
+	int i;
+
+	if (!obj->handle)
+		return;
+
+	print_name(p, "  - type: ", block->name);
+
+	for (i = 0; i < A6XX_NUM_SHADER_BANKS; i++) {
+		drm_printf(p, "    - bank: %d\n", i);
+		drm_printf(p, "      size: %d\n", block->size);
+
+		if (!obj->data)
+			continue;
+
+		print_ascii85(p, block->size << 2,
+			obj->data + (block->size * i));
+	}
+}
+
+static void a6xx_show_cluster_data(const u32 *registers, int size, u32 *data,
+		struct drm_printer *p)
+{
+	int ctx, index = 0;
+
+	for (ctx = 0; ctx < A6XX_NUM_CONTEXTS; ctx++) {
+		int j;
+
+		drm_printf(p, "    - context: %d\n", ctx);
+
+		for (j = 0; j < size; j += 2) {
+			u32 count = RANGE(registers, j);
+			u32 offset = registers[j];
+			int k;
+
+			for (k = 0; k < count; index++, offset++, k++) {
+				if (data[index] == 0xdeafbead)
+					continue;
+
+				drm_printf(p, "      - { offset: 0x%06x, value: 0x%08x }\n",
+					offset << 2, data[index]);
+			}
+		}
+	}
+}
+
+static void a6xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj,
+		struct drm_printer *p)
+{
+	const struct a6xx_dbgahb_cluster *dbgahb = obj->handle;
+
+	if (dbgahb) {
+		print_name(p, "  - cluster-name: ", dbgahb->name);
+		a6xx_show_cluster_data(dbgahb->registers, dbgahb->count,
+			obj->data, p);
+	}
+}
+
+static void a6xx_show_cluster(struct a6xx_gpu_state_obj *obj,
+		struct drm_printer *p)
+{
+	const struct a6xx_cluster *cluster = obj->handle;
+
+	if (cluster) {
+		print_name(p, "  - cluster-name: ", cluster->name);
+		a6xx_show_cluster_data(cluster->registers, cluster->count,
+			obj->data, p);
+	}
+}
+
+static void a6xx_show_indexed_regs(struct a6xx_gpu_state_obj *obj,
+		struct drm_printer *p)
+{
+	const struct a6xx_indexed_registers *indexed = obj->handle;
+
+	if (!indexed)
+		return;
+
+	print_name(p, "  - regs-name: ", indexed->name);
+	drm_printf(p, "    dwords: %d\n", indexed->count);
+
+	print_ascii85(p, indexed->count << 2, obj->data);
+}
+
+static void a6xx_show_debugbus_block(const struct a6xx_debugbus_block *block,
+		u32 *data, struct drm_printer *p)
+{
+	if (block) {
+		print_name(p, "  - debugbus-block: ", block->name);
+
+		/*
+		 * count for regular debugbus data is in quadwords,
+		 * but print the size in dwords for consistency
+		 */
+		drm_printf(p, "    count: %d\n", block->count << 1);
+
+		print_ascii85(p, block->count << 3, data);
+	}
+}
+
+static void a6xx_show_debugbus(struct a6xx_gpu_state *a6xx_state,
+		struct drm_printer *p)
+{
+	int i;
+
+	for (i = 0; i < a6xx_state->nr_debugbus; i++) {
+		struct a6xx_gpu_state_obj *obj = &a6xx_state->debugbus[i];
+
+		a6xx_show_debugbus_block(obj->handle, obj->data, p);
+	}
+
+	if (a6xx_state->vbif_debugbus) {
+		struct a6xx_gpu_state_obj *obj = a6xx_state->vbif_debugbus;
+
+		drm_puts(p, "  - debugbus-block: A6XX_DBGBUS_VBIF\n");
+		drm_printf(p, "    count: %d\n", VBIF_DEBUGBUS_BLOCK_SIZE);
+
+		/* vbif debugbus data is in dwords.  Confusing, huh? */
+		print_ascii85(p, VBIF_DEBUGBUS_BLOCK_SIZE << 2, obj->data);
+	}
+
+	for (i = 0; i < a6xx_state->nr_cx_debugbus; i++) {
+		struct a6xx_gpu_state_obj *obj = &a6xx_state->cx_debugbus[i];
+
+		a6xx_show_debugbus_block(obj->handle, obj->data, p);
+	}
+}
+
+void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	struct a6xx_gpu_state *a6xx_state = container_of(state,
+			struct a6xx_gpu_state, base);
+	int i;
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	adreno_show(gpu, state, p);
+
+	drm_puts(p, "registers:\n");
+	for (i = 0; i < a6xx_state->nr_registers; i++) {
+		struct a6xx_gpu_state_obj *obj = &a6xx_state->registers[i];
+		const struct a6xx_registers *regs = obj->handle;
+
+		if (!obj->handle)
+			continue;
+
+		a6xx_show_registers(regs->registers, obj->data, regs->count, p);
+	}
+
+	drm_puts(p, "registers-gmu:\n");
+	for (i = 0; i < a6xx_state->nr_gmu_registers; i++) {
+		struct a6xx_gpu_state_obj *obj = &a6xx_state->gmu_registers[i];
+		const struct a6xx_registers *regs = obj->handle;
+
+		if (!obj->handle)
+			continue;
+
+		a6xx_show_registers(regs->registers, obj->data, regs->count, p);
+	}
+
+	drm_puts(p, "indexed-registers:\n");
+	for (i = 0; i < a6xx_state->nr_indexed_regs; i++)
+		a6xx_show_indexed_regs(&a6xx_state->indexed_regs[i], p);
+
+	drm_puts(p, "shader-blocks:\n");
+	for (i = 0; i < a6xx_state->nr_shaders; i++)
+		a6xx_show_shader(&a6xx_state->shaders[i], p);
+
+	drm_puts(p, "clusters:\n");
+	for (i = 0; i < a6xx_state->nr_clusters; i++)
+		a6xx_show_cluster(&a6xx_state->clusters[i], p);
+
+	for (i = 0; i < a6xx_state->nr_dbgahb_clusters; i++)
+		a6xx_show_dbgahb_cluster(&a6xx_state->dbgahb_clusters[i], p);
+
+	drm_puts(p, "debugbus:\n");
+	a6xx_show_debugbus(a6xx_state, p);
+}
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
new file mode 100644
index 000000000000..68cccfa2870a
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -0,0 +1,430 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+
+#ifndef _A6XX_CRASH_DUMP_H_
+#define _A6XX_CRASH_DUMP_H_
+
+#include "a6xx.xml.h"
+
+#define A6XX_NUM_CONTEXTS 2
+#define A6XX_NUM_SHADER_BANKS 3
+
+static const u32 a6xx_gras_cluster[] = {
+	0x8000, 0x8006, 0x8010, 0x8092, 0x8094, 0x809d, 0x80a0, 0x80a6,
+	0x80af, 0x80f1, 0x8100, 0x8107, 0x8109, 0x8109, 0x8110, 0x8110,
+	0x8400, 0x840b,
+};
+
+static const u32 a6xx_ps_cluster_rac[] = {
+	0x8800, 0x8806, 0x8809, 0x8811, 0x8818, 0x881e, 0x8820, 0x8865,
+	0x8870, 0x8879, 0x8880, 0x8889, 0x8890, 0x8891, 0x8898, 0x8898,
+	0x88c0, 0x88c1, 0x88d0, 0x88e3, 0x8900, 0x890c, 0x890f, 0x891a,
+	0x8c00, 0x8c01, 0x8c08, 0x8c10, 0x8c17, 0x8c1f, 0x8c26, 0x8c33,
+};
+
+static const u32 a6xx_ps_cluster_rbp[] = {
+	0x88f0, 0x88f3, 0x890d, 0x890e, 0x8927, 0x8928, 0x8bf0, 0x8bf1,
+	0x8c02, 0x8c07, 0x8c11, 0x8c16, 0x8c20, 0x8c25,
+};
+
+static const u32 a6xx_ps_cluster[] = {
+	0x9200, 0x9216, 0x9218, 0x9236, 0x9300, 0x9306,
+};
+
+static const u32 a6xx_fe_cluster[] = {
+	0x9300, 0x9306, 0x9800, 0x9806, 0x9b00, 0x9b07, 0xa000, 0xa009,
+	0xa00e, 0xa0ef, 0xa0f8, 0xa0f8,
+};
+
+static const u32 a6xx_pc_vs_cluster[] = {
+	0x9100, 0x9108, 0x9300, 0x9306, 0x9980, 0x9981, 0x9b00, 0x9b07,
+};
+
+#define CLUSTER_FE    0
+#define CLUSTER_SP_VS 1
+#define CLUSTER_PC_VS 2
+#define CLUSTER_GRAS  3
+#define CLUSTER_SP_PS 4
+#define CLUSTER_PS    5
+
+#define CLUSTER(_id, _reg, _sel_reg, _sel_val) \
+	{ .id = _id, .name = #_id,\
+		.registers = _reg, \
+		.count = ARRAY_SIZE(_reg), \
+		.sel_reg = _sel_reg, .sel_val = _sel_val }
+
+static const struct a6xx_cluster {
+	u32 id;
+	const char *name;
+	const u32 *registers;
+	size_t count;
+	u32 sel_reg;
+	u32 sel_val;
+} a6xx_clusters[] = {
+	CLUSTER(CLUSTER_GRAS, a6xx_gras_cluster, 0, 0),
+	CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rac, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x0),
+	CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rbp, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x9),
+	CLUSTER(CLUSTER_PS, a6xx_ps_cluster, 0, 0),
+	CLUSTER(CLUSTER_FE, a6xx_fe_cluster, 0, 0),
+	CLUSTER(CLUSTER_PC_VS, a6xx_pc_vs_cluster, 0, 0),
+};
+
+static const u32 a6xx_sp_vs_hlsq_cluster[] = {
+	0xb800, 0xb803, 0xb820, 0xb822,
+};
+
+static const u32 a6xx_sp_vs_sp_cluster[] = {
+	0xa800, 0xa824, 0xa830, 0xa83c, 0xa840, 0xa864, 0xa870, 0xa895,
+	0xa8a0, 0xa8af, 0xa8c0, 0xa8c3,
+};
+
+static const u32 a6xx_hlsq_duplicate_cluster[] = {
+	0xbb10, 0xbb11, 0xbb20, 0xbb29,
+};
+
+static const u32 a6xx_hlsq_2d_duplicate_cluster[] = {
+	0xbd80, 0xbd80,
+};
+
+static const u32 a6xx_sp_duplicate_cluster[] = {
+	0xab00, 0xab00, 0xab04, 0xab05, 0xab10, 0xab1b, 0xab20, 0xab20,
+};
+
+static const u32 a6xx_tp_duplicate_cluster[] = {
+	0xb300, 0xb307, 0xb309, 0xb309, 0xb380, 0xb382,
+};
+
+static const u32 a6xx_sp_ps_hlsq_cluster[] = {
+	0xb980, 0xb980, 0xb982, 0xb987, 0xb990, 0xb99b, 0xb9a0, 0xb9a2,
+	0xb9c0, 0xb9c9,
+};
+
+static const u32 a6xx_sp_ps_hlsq_2d_cluster[] = {
+	0xbd80, 0xbd80,
+};
+
+static const u32 a6xx_sp_ps_sp_cluster[] = {
+	0xa980, 0xa9a8, 0xa9b0, 0xa9bc, 0xa9d0, 0xa9d3, 0xa9e0, 0xa9f3,
+	0xaa00, 0xaa00, 0xaa30, 0xaa31,
+};
+
+static const u32 a6xx_sp_ps_sp_2d_cluster[] = {
+	0xacc0, 0xacc0,
+};
+
+static const u32 a6xx_sp_ps_tp_cluster[] = {
+	0xb180, 0xb183, 0xb190, 0xb191,
+};
+
+static const u32 a6xx_sp_ps_tp_2d_cluster[] = {
+	0xb4c0, 0xb4d1,
+};
+
+#define CLUSTER_DBGAHB(_id, _base, _type, _reg) \
+	{ .name = #_id, .statetype = _type, .base = _base, \
+		.registers = _reg, .count = ARRAY_SIZE(_reg) }
+
+static const struct a6xx_dbgahb_cluster {
+	const char *name;
+	u32 statetype;
+	u32 base;
+	const u32 *registers;
+	size_t count;
+} a6xx_dbgahb_clusters[] = {
+	CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002e000, 0x41, a6xx_sp_vs_hlsq_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002a000, 0x21, a6xx_sp_vs_sp_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002e000, 0x41, a6xx_hlsq_duplicate_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002f000, 0x45, a6xx_hlsq_2d_duplicate_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002a000, 0x21, a6xx_sp_duplicate_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_VS, 0x0002c000, 0x1, a6xx_tp_duplicate_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002e000, 0x42, a6xx_sp_ps_hlsq_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002f000, 0x46, a6xx_sp_ps_hlsq_2d_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002a000, 0x22, a6xx_sp_ps_sp_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002b000, 0x26, a6xx_sp_ps_sp_2d_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002c000, 0x2, a6xx_sp_ps_tp_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002d000, 0x6, a6xx_sp_ps_tp_2d_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002e000, 0x42, a6xx_hlsq_duplicate_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002a000, 0x22, a6xx_sp_duplicate_cluster),
+	CLUSTER_DBGAHB(CLUSTER_SP_PS, 0x0002c000, 0x2, a6xx_tp_duplicate_cluster),
+};
+
+static const u32 a6xx_hlsq_registers[] = {
+	0xbe00, 0xbe01, 0xbe04, 0xbe05, 0xbe08, 0xbe09, 0xbe10, 0xbe15,
+	0xbe20, 0xbe23,
+};
+
+static const u32 a6xx_sp_registers[] = {
+	0xae00, 0xae04, 0xae0c, 0xae0c, 0xae0f, 0xae2b, 0xae30, 0xae32,
+	0xae35, 0xae35, 0xae3a, 0xae3f, 0xae50, 0xae52,
+};
+
+static const u32 a6xx_tp_registers[] = {
+	0xb600, 0xb601, 0xb604, 0xb605, 0xb610, 0xb61b, 0xb620, 0xb623,
+};
+
+struct a6xx_registers {
+	const u32 *registers;
+	size_t count;
+	u32 val0;
+	u32 val1;
+};
+
+#define HLSQ_DBG_REGS(_base, _type, _array) \
+	{ .val0 = _base, .val1 = _type, .registers = _array, \
+		.count = ARRAY_SIZE(_array), }
+
+static const struct a6xx_registers a6xx_hlsq_reglist[] = {
+	HLSQ_DBG_REGS(0x0002F800, 0x40, a6xx_hlsq_registers),
+	HLSQ_DBG_REGS(0x0002B800, 0x20, a6xx_sp_registers),
+	HLSQ_DBG_REGS(0x0002D800, 0x0, a6xx_tp_registers),
+};
+
+#define SHADER(_type, _size) \
+	{ .type = _type, .name = #_type, .size = _size }
+
+static const struct a6xx_shader_block {
+	const char *name;
+	u32 type;
+	u32 size;
+} a6xx_shader_blocks[] = {
+	SHADER(A6XX_TP0_TMO_DATA, 0x200),
+	SHADER(A6XX_TP0_SMO_DATA, 0x80),
+	SHADER(A6XX_TP0_MIPMAP_BASE_DATA, 0x3c0),
+	SHADER(A6XX_TP1_TMO_DATA, 0x200),
+	SHADER(A6XX_TP1_SMO_DATA, 0x80),
+	SHADER(A6XX_TP1_MIPMAP_BASE_DATA, 0x3c0),
+	SHADER(A6XX_SP_INST_DATA, 0x800),
+	SHADER(A6XX_SP_LB_0_DATA, 0x800),
+	SHADER(A6XX_SP_LB_1_DATA, 0x800),
+	SHADER(A6XX_SP_LB_2_DATA, 0x800),
+	SHADER(A6XX_SP_LB_3_DATA, 0x800),
+	SHADER(A6XX_SP_LB_4_DATA, 0x800),
+	SHADER(A6XX_SP_LB_5_DATA, 0x200),
+	SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x2000),
+	SHADER(A6XX_SP_CB_LEGACY_DATA, 0x280),
+	SHADER(A6XX_SP_UAV_DATA, 0x80),
+	SHADER(A6XX_SP_INST_TAG, 0x80),
+	SHADER(A6XX_SP_CB_BINDLESS_TAG, 0x80),
+	SHADER(A6XX_SP_TMO_UMO_TAG, 0x80),
+	SHADER(A6XX_SP_SMO_TAG, 0x80),
+	SHADER(A6XX_SP_STATE_DATA, 0x3f),
+	SHADER(A6XX_HLSQ_CHUNK_CVS_RAM, 0x1c0),
+	SHADER(A6XX_HLSQ_CHUNK_CPS_RAM, 0x280),
+	SHADER(A6XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40),
+	SHADER(A6XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40),
+	SHADER(A6XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x4),
+	SHADER(A6XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x4),
+	SHADER(A6XX_HLSQ_CVS_MISC_RAM, 0x1c0),
+	SHADER(A6XX_HLSQ_CPS_MISC_RAM, 0x580),
+	SHADER(A6XX_HLSQ_INST_RAM, 0x800),
+	SHADER(A6XX_HLSQ_GFX_CVS_CONST_RAM, 0x800),
+	SHADER(A6XX_HLSQ_GFX_CPS_CONST_RAM, 0x800),
+	SHADER(A6XX_HLSQ_CVS_MISC_RAM_TAG, 0x8),
+	SHADER(A6XX_HLSQ_CPS_MISC_RAM_TAG, 0x4),
+	SHADER(A6XX_HLSQ_INST_RAM_TAG, 0x80),
+	SHADER(A6XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0xc),
+	SHADER(A6XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x10),
+	SHADER(A6XX_HLSQ_PWR_REST_RAM, 0x28),
+	SHADER(A6XX_HLSQ_PWR_REST_TAG, 0x14),
+	SHADER(A6XX_HLSQ_DATAPATH_META, 0x40),
+	SHADER(A6XX_HLSQ_FRONTEND_META, 0x40),
+	SHADER(A6XX_HLSQ_INDIRECT_META, 0x40),
+};
+
+static const u32 a6xx_rb_rac_registers[] = {
+	0x8e04, 0x8e05, 0x8e07, 0x8e08, 0x8e10, 0x8e1c, 0x8e20, 0x8e25,
+	0x8e28, 0x8e28, 0x8e2c, 0x8e2f, 0x8e50, 0x8e52,
+};
+
+static const u32 a6xx_rb_rbp_registers[] = {
+	0x8e01, 0x8e01, 0x8e0c, 0x8e0c, 0x8e3b, 0x8e3e, 0x8e40, 0x8e43,
+	0x8e53, 0x8e5f, 0x8e70, 0x8e77,
+};
+
+static const u32 a6xx_registers[] = {
+	/* RBBM */
+	0x0000, 0x0002, 0x0010, 0x0010, 0x0012, 0x0012, 0x0018, 0x001b,
+	0x001e, 0x0032, 0x0038, 0x003c, 0x0042, 0x0042, 0x0044, 0x0044,
+	0x0047, 0x0047, 0x0056, 0x0056, 0x00ad, 0x00ae, 0x00b0, 0x00fb,
+	0x0100, 0x011d, 0x0200, 0x020d, 0x0218, 0x023d, 0x0400, 0x04f9,
+	0x0500, 0x0500, 0x0505, 0x050b, 0x050e, 0x0511, 0x0533, 0x0533,
+	0x0540, 0x0555,
+	/* CP */
+	0x0800, 0x0808, 0x0810, 0x0813, 0x0820, 0x0821, 0x0823, 0x0824,
+	0x0826, 0x0827, 0x0830, 0x0833, 0x0840, 0x0843, 0x084f, 0x086f,
+	0x0880, 0x088a, 0x08a0, 0x08ab, 0x08c0, 0x08c4, 0x08d0, 0x08dd,
+	0x08f0, 0x08f3, 0x0900, 0x0903, 0x0908, 0x0911, 0x0928, 0x093e,
+	0x0942, 0x094d, 0x0980, 0x0984, 0x098d, 0x0996, 0x0998, 0x099e,
+	0x09a0, 0x09a6, 0x09a8, 0x09ae, 0x09b0, 0x09b1, 0x09c2, 0x09c8,
+	0x0a00, 0x0a03,
+	/* VSC */
+	0x0c00, 0x0c04, 0x0c06, 0x0c06, 0x0c10, 0x0cd9, 0x0e00, 0x0e0e,
+	/* UCHE */
+	0x0e10, 0x0e13, 0x0e17, 0x0e19, 0x0e1c, 0x0e2b, 0x0e30, 0x0e32,
+	0x0e38, 0x0e39,
+	/* GRAS */
+	0x8600, 0x8601, 0x8610, 0x861b, 0x8620, 0x8620, 0x8628, 0x862b,
+	0x8630, 0x8637,
+	/* VPC */
+	0x9600, 0x9604, 0x9624, 0x9637,
+	/* PC */
+	0x9e00, 0x9e01, 0x9e03, 0x9e0e, 0x9e11, 0x9e16, 0x9e19, 0x9e19,
+	0x9e1c, 0x9e1c, 0x9e20, 0x9e23, 0x9e30, 0x9e31, 0x9e34, 0x9e34,
+	0x9e70, 0x9e72, 0x9e78, 0x9e79, 0x9e80, 0x9fff,
+	/* VFD */
+	0xa600, 0xa601, 0xa603, 0xa603, 0xa60a, 0xa60a, 0xa610, 0xa617,
+	0xa630, 0xa630,
+};
+
+#define REGS(_array, _sel_reg, _sel_val) \
+	{ .registers = _array, .count = ARRAY_SIZE(_array), \
+		.val0 = _sel_reg, .val1 = _sel_val }
+
+static const struct a6xx_registers a6xx_reglist[] = {
+	REGS(a6xx_registers, 0, 0),
+	REGS(a6xx_rb_rac_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0),
+	REGS(a6xx_rb_rbp_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 9),
+};
+
+static const u32 a6xx_ahb_registers[] = {
+	/* RBBM_STATUS - RBBM_STATUS3 */
+	0x210, 0x213,
+	/* CP_STATUS_1 */
+	0x825, 0x825,
+};
+
+static const u32 a6xx_vbif_registers[] = {
+	0x3000, 0x3007, 0x300c, 0x3014, 0x3018, 0x302d, 0x3030, 0x3031,
+	0x3034, 0x3036, 0x303c, 0x303d, 0x3040, 0x3040, 0x3042, 0x3042,
+	0x3049, 0x3049, 0x3058, 0x3058, 0x305a, 0x3061, 0x3064, 0x3068,
+	0x306c, 0x306d, 0x3080, 0x3088, 0x308b, 0x308c, 0x3090, 0x3094,
+	0x3098, 0x3098, 0x309c, 0x309c, 0x30c0, 0x30c0, 0x30c8, 0x30c8,
+	0x30d0, 0x30d0, 0x30d8, 0x30d8, 0x30e0, 0x30e0, 0x3100, 0x3100,
+	0x3108, 0x3108, 0x3110, 0x3110, 0x3118, 0x3118, 0x3120, 0x3120,
+	0x3124, 0x3125, 0x3129, 0x3129, 0x3131, 0x3131, 0x3154, 0x3154,
+	0x3156, 0x3156, 0x3158, 0x3158, 0x315a, 0x315a, 0x315c, 0x315c,
+	0x315e, 0x315e, 0x3160, 0x3160, 0x3162, 0x3162, 0x340c, 0x340c,
+	0x3410, 0x3410, 0x3800, 0x3801,
+};
+
+static const struct a6xx_registers a6xx_ahb_reglist[] = {
+	REGS(a6xx_ahb_registers, 0, 0),
+	REGS(a6xx_vbif_registers, 0, 0),
+};
+
+static const u32 a6xx_gmu_gx_registers[] = {
+	/* GMU GX */
+	0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b,
+	0x001e, 0x001e, 0x0020, 0x0023, 0x0026, 0x0026, 0x0028, 0x002b,
+	0x002e, 0x002e, 0x0030, 0x0033, 0x0036, 0x0036, 0x0038, 0x003b,
+	0x003e, 0x003e, 0x0040, 0x0043, 0x0046, 0x0046, 0x0080, 0x0084,
+	0x0100, 0x012b, 0x0140, 0x0140,
+};
+
+static const u32 a6xx_gmu_cx_registers[] = {
+	/* GMU CX */
+	0x4c00, 0x4c07, 0x4c10, 0x4c12, 0x4d00, 0x4d00, 0x4d07, 0x4d0a,
+	0x5000, 0x5004, 0x5007, 0x5008, 0x500b, 0x500c, 0x500f, 0x501c,
+	0x5024, 0x502a, 0x502d, 0x5030, 0x5040, 0x5053, 0x5087, 0x5089,
+	0x50a0, 0x50a2, 0x50a4, 0x50af, 0x50c0, 0x50c3, 0x50d0, 0x50d0,
+	0x50e4, 0x50e4, 0x50e8, 0x50ec, 0x5100, 0x5103, 0x5140, 0x5140,
+	0x5142, 0x5144, 0x514c, 0x514d, 0x514f, 0x5151, 0x5154, 0x5154,
+	0x5157, 0x5158, 0x515d, 0x515d, 0x5162, 0x5162, 0x5164, 0x5165,
+	0x5180, 0x5186, 0x5190, 0x519e, 0x51c0, 0x51c0, 0x51c5, 0x51cc,
+	0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201,
+	/* GPU RSCC */
+	0x8c8c, 0x8c8c, 0x8d01, 0x8d02, 0x8f40, 0x8f42, 0x8f44, 0x8f47,
+	0x8f4c, 0x8f87, 0x8fec, 0x8fef, 0x8ff4, 0x902f, 0x9094, 0x9097,
+	0x909c, 0x90d7, 0x913c, 0x913f, 0x9144, 0x917f,
+	/* GMU AO */
+	0x9300, 0x9316, 0x9400, 0x9400,
+	/* GPU CC */
+	0x9800, 0x9812, 0x9840, 0x9852, 0x9c00, 0x9c04, 0x9c07, 0x9c0b,
+	0x9c15, 0x9c1c, 0x9c1e, 0x9c2d, 0x9c3c, 0x9c3d, 0x9c3f, 0x9c40,
+	0x9c42, 0x9c49, 0x9c58, 0x9c5a, 0x9d40, 0x9d5e, 0xa000, 0xa002,
+	0xa400, 0xa402, 0xac00, 0xac02, 0xb000, 0xb002, 0xb400, 0xb402,
+	0xb800, 0xb802,
+	/* GPU CC ACD */
+	0xbc00, 0xbc16, 0xbc20, 0xbc27,
+};
+
+static const struct a6xx_registers a6xx_gmu_reglist[] = {
+	REGS(a6xx_gmu_cx_registers, 0, 0),
+	REGS(a6xx_gmu_gx_registers, 0, 0),
+};
+
+static const struct a6xx_indexed_registers {
+	const char *name;
+	u32 addr;
+	u32 data;
+	u32 count;
+} a6xx_indexed_reglist[] = {
+	{ "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
+		REG_A6XX_CP_SQE_STAT_DATA, 0x33 },
+	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
+		REG_A6XX_CP_DRAW_STATE_DATA, 0x100 },
+	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x6000 },
+	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+		REG_A6XX_CP_ROQ_DBG_DATA, 0x400 },
+};
+
+static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = {
+	"CP_MEMPOOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060,
+};
+
+#define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count }
+
+static const struct a6xx_debugbus_block {
+	const char *name;
+	u32 id;
+	u32 count;
+} a6xx_debugbus_blocks[] = {
+	DEBUGBUS(A6XX_DBGBUS_CP, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_RBBM, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_HLSQ, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_UCHE, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_DPM, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TESS, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_PC, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VFDP, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VPC, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TSE, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_RAS, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VSC, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_COM, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_LRZ, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_A2D, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_CCUFCHE, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_RBP, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_DCS, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_DBGC, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_GMU_GX, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TPFCHE, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_GPC, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_LARC, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_HLSQ_SPTP, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_RB_0, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_RB_1, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_UCHE_WRAPPER, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_CCU_0, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_CCU_1, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VFD_0, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VFD_1, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VFD_2, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_VFD_3, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_SP_0, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_SP_1, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TPL1_0, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TPL1_1, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TPL1_2, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_TPL1_3, 0x100),
+};
+
+static const struct a6xx_debugbus_block a6xx_cx_debugbus_blocks[] = {
+	DEBUGBUS(A6XX_DBGBUS_GMU_CX, 0x100),
+	DEBUGBUS(A6XX_DBGBUS_CX, 0x100),
+};
+
+#endif
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index 6ff9baec2658..eda11abc5f01 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -91,7 +91,7 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum,
 		val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 5000);
 
 	if (ret) {
-		dev_err(gmu->dev,
+		DRM_DEV_ERROR(gmu->dev,
 			"Message %s id %d timed out waiting for response\n",
 			a6xx_hfi_msg_id[id], seqnum);
 		return -ETIMEDOUT;
@@ -110,7 +110,7 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum,
 
 		/* If the queue is empty our response never made it */
 		if (!ret) {
-			dev_err(gmu->dev,
+			DRM_DEV_ERROR(gmu->dev,
 				"The HFI response queue is unexpectedly empty\n");
 
 			return -ENOENT;
@@ -120,20 +120,20 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum,
 			struct a6xx_hfi_msg_error *error =
 				(struct a6xx_hfi_msg_error *) &resp;
 
-			dev_err(gmu->dev, "GMU firmware error %d\n",
+			DRM_DEV_ERROR(gmu->dev, "GMU firmware error %d\n",
 				error->code);
 			continue;
 		}
 
 		if (seqnum != HFI_HEADER_SEQNUM(resp.ret_header)) {
-			dev_err(gmu->dev,
+			DRM_DEV_ERROR(gmu->dev,
 				"Unexpected message id %d on the response queue\n",
 				HFI_HEADER_SEQNUM(resp.ret_header));
 			continue;
 		}
 
 		if (resp.error) {
-			dev_err(gmu->dev,
+			DRM_DEV_ERROR(gmu->dev,
 				"Message %s id %d returned error %d\n",
 				a6xx_hfi_msg_id[id], seqnum, resp.error);
 			return -EINVAL;
@@ -163,7 +163,7 @@ static int a6xx_hfi_send_msg(struct a6xx_gmu *gmu, int id,
 
 	ret = a6xx_hfi_queue_write(gmu, queue, data, dwords);
 	if (ret) {
-		dev_err(gmu->dev, "Unable to send message %s id %d\n",
+		DRM_DEV_ERROR(gmu->dev, "Unable to send message %s id %d\n",
 			a6xx_hfi_msg_id[id], seqnum);
 		return ret;
 	}
@@ -317,7 +317,7 @@ void a6xx_hfi_stop(struct a6xx_gmu *gmu)
 			continue;
 
 		if (queue->header->read_index != queue->header->write_index)
-			dev_err(gmu->dev, "HFI queue %d is not empty\n", i);
+			DRM_DEV_ERROR(gmu->dev, "HFI queue %d is not empty\n", i);
 
 		queue->header->read_index = 0;
 		queue->header->write_index = 0;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
index 1318959d504d..641d3ba477b6 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
@@ -339,6 +339,15 @@ static inline uint32_t AXXX_SCRATCH_UMSK_SWAP(uint32_t val)
 #define REG_AXXX_CP_STATE_DEBUG_DATA				0x000001ed
 
 #define REG_AXXX_CP_INT_CNTL					0x000001f2
+#define AXXX_CP_INT_CNTL_SW_INT_MASK				0x00080000
+#define AXXX_CP_INT_CNTL_T0_PACKET_IN_IB_MASK			0x00800000
+#define AXXX_CP_INT_CNTL_OPCODE_ERROR_MASK			0x01000000
+#define AXXX_CP_INT_CNTL_PROTECTED_MODE_ERROR_MASK		0x02000000
+#define AXXX_CP_INT_CNTL_RESERVED_BIT_ERROR_MASK		0x04000000
+#define AXXX_CP_INT_CNTL_IB_ERROR_MASK				0x08000000
+#define AXXX_CP_INT_CNTL_IB2_INT_MASK				0x20000000
+#define AXXX_CP_INT_CNTL_IB1_INT_MASK				0x40000000
+#define AXXX_CP_INT_CNTL_RB_INT_MASK				0x80000000
 
 #define REG_AXXX_CP_INT_STATUS					0x000001f3
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 86abdb2b3a9c..714ed6505e47 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -27,6 +27,39 @@ module_param_named(hang_debug, hang_debug, bool, 0600);
 
 static const struct adreno_info gpulist[] = {
 	{
+		.rev   = ADRENO_REV(2, 0, 0, 0),
+		.revn  = 200,
+		.name  = "A200",
+		.fw = {
+			[ADRENO_FW_PM4] = "yamato_pm4.fw",
+			[ADRENO_FW_PFP] = "yamato_pfp.fw",
+		},
+		.gmem  = SZ_256K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init  = a2xx_gpu_init,
+	}, { /* a200 on i.mx51 has only 128kib gmem */
+		.rev   = ADRENO_REV(2, 0, 0, 1),
+		.revn  = 201,
+		.name  = "A200",
+		.fw = {
+			[ADRENO_FW_PM4] = "yamato_pm4.fw",
+			[ADRENO_FW_PFP] = "yamato_pfp.fw",
+		},
+		.gmem  = SZ_128K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init  = a2xx_gpu_init,
+	}, {
+		.rev   = ADRENO_REV(2, 2, 0, ANY_ID),
+		.revn  = 220,
+		.name  = "A220",
+		.fw = {
+			[ADRENO_FW_PM4] = "leia_pm4_470.fw",
+			[ADRENO_FW_PFP] = "leia_pfp_470.fw",
+		},
+		.gmem  = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init  = a2xx_gpu_init,
+	}, {
 		.rev   = ADRENO_REV(3, 0, 5, ANY_ID),
 		.revn  = 305,
 		.name  = "A305",
@@ -196,7 +229,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
-		dev_err(dev->dev, "Couldn't power up the GPU: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "Couldn't power up the GPU: %d\n", ret);
 		return NULL;
 	}
 
@@ -205,7 +238,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	mutex_unlock(&dev->struct_mutex);
 	pm_runtime_put_autosuspend(&pdev->dev);
 	if (ret) {
-		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "gpu hw init failed: %d\n", ret);
 		return NULL;
 	}
 
@@ -238,7 +271,8 @@ static int find_chipid(struct device *dev, struct adreno_rev *rev)
 	if (ret == 0) {
 		unsigned int r, patch;
 
-		if (sscanf(compat, "qcom,adreno-%u.%u", &r, &patch) == 2) {
+		if (sscanf(compat, "qcom,adreno-%u.%u", &r, &patch) == 2 ||
+		    sscanf(compat, "amd,imageon-%u.%u", &r, &patch) == 2) {
 			rev->core = r / 100;
 			r %= 100;
 			rev->major = r / 10;
@@ -253,7 +287,7 @@ static int find_chipid(struct device *dev, struct adreno_rev *rev)
 	/* and if that fails, fall back to legacy "qcom,chipid" property: */
 	ret = of_property_read_u32(node, "qcom,chipid", &chipid);
 	if (ret) {
-		dev_err(dev, "could not parse qcom,chipid: %d\n", ret);
+		DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret);
 		return ret;
 	}
 
@@ -274,6 +308,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 	static struct adreno_platform_config config = {};
 	const struct adreno_info *info;
 	struct drm_device *drm = dev_get_drvdata(master);
+	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu *gpu;
 	int ret;
 
@@ -296,6 +331,8 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 	DBG("Found GPU: %u.%u.%u.%u", config.rev.core, config.rev.major,
 		config.rev.minor, config.rev.patchid);
 
+	priv->is_a2xx = config.rev.core == 2;
+
 	gpu = info->init(drm);
 	if (IS_ERR(gpu)) {
 		dev_warn(drm->dev, "failed to load adreno gpu\n");
@@ -323,9 +360,37 @@ static const struct component_ops a3xx_ops = {
 		.unbind = adreno_unbind,
 };
 
+static void adreno_device_register_headless(void)
+{
+	/* on imx5, we don't have a top-level mdp/dpu node
+	 * this creates a dummy node for the driver for that case
+	 */
+	struct platform_device_info dummy_info = {
+		.parent = NULL,
+		.name = "msm",
+		.id = -1,
+		.res = NULL,
+		.num_res = 0,
+		.data = NULL,
+		.size_data = 0,
+		.dma_mask = ~0,
+	};
+	platform_device_register_full(&dummy_info);
+}
+
 static int adreno_probe(struct platform_device *pdev)
 {
-	return component_add(&pdev->dev, &a3xx_ops);
+
+	int ret;
+
+	ret = component_add(&pdev->dev, &a3xx_ops);
+	if (ret)
+		return ret;
+
+	if (of_device_is_compatible(pdev->dev.of_node, "amd,imageon"))
+		adreno_device_register_headless();
+
+	return 0;
 }
 
 static int adreno_remove(struct platform_device *pdev)
@@ -337,6 +402,8 @@ static int adreno_remove(struct platform_device *pdev)
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,adreno" },
 	{ .compatible = "qcom,adreno-3xx" },
+	/* for compatibility with imx5 gpu: */
+	{ .compatible = "amd,imageon" },
 	/* for backwards compat w/ downstream kgsl DT files: */
 	{ .compatible = "qcom,kgsl-3d0" },
 	{}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 93d70f4a2154..2e4372ef17a3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -89,12 +89,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname)
 
 		ret = request_firmware_direct(&fw, newname, drm->dev);
 		if (!ret) {
-			dev_info(drm->dev, "loaded %s from new location\n",
+			DRM_DEV_INFO(drm->dev, "loaded %s from new location\n",
 				newname);
 			adreno_gpu->fwloc = FW_LOCATION_NEW;
 			goto out;
 		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
-			dev_err(drm->dev, "failed to load %s: %d\n",
+			DRM_DEV_ERROR(drm->dev, "failed to load %s: %d\n",
 				newname, ret);
 			fw = ERR_PTR(ret);
 			goto out;
@@ -109,12 +109,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname)
 
 		ret = request_firmware_direct(&fw, fwname, drm->dev);
 		if (!ret) {
-			dev_info(drm->dev, "loaded %s from legacy location\n",
+			DRM_DEV_INFO(drm->dev, "loaded %s from legacy location\n",
 				newname);
 			adreno_gpu->fwloc = FW_LOCATION_LEGACY;
 			goto out;
 		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
-			dev_err(drm->dev, "failed to load %s: %d\n",
+			DRM_DEV_ERROR(drm->dev, "failed to load %s: %d\n",
 				fwname, ret);
 			fw = ERR_PTR(ret);
 			goto out;
@@ -130,19 +130,19 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname)
 
 		ret = request_firmware(&fw, newname, drm->dev);
 		if (!ret) {
-			dev_info(drm->dev, "loaded %s with helper\n",
+			DRM_DEV_INFO(drm->dev, "loaded %s with helper\n",
 				newname);
 			adreno_gpu->fwloc = FW_LOCATION_HELPER;
 			goto out;
 		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
-			dev_err(drm->dev, "failed to load %s: %d\n",
+			DRM_DEV_ERROR(drm->dev, "failed to load %s: %d\n",
 				newname, ret);
 			fw = ERR_PTR(ret);
 			goto out;
 		}
 	}
 
-	dev_err(drm->dev, "failed to load %s\n", fwname);
+	DRM_DEV_ERROR(drm->dev, "failed to load %s\n", fwname);
 	fw = ERR_PTR(-ENOENT);
 out:
 	kfree(newname);
@@ -209,14 +209,6 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		if (!ring)
 			continue;
 
-		ret = msm_gem_get_iova(ring->bo, gpu->aspace, &ring->iova);
-		if (ret) {
-			ring->iova = 0;
-			dev_err(gpu->dev->dev,
-				"could not map ringbuffer %d: %d\n", i, ret);
-			return ret;
-		}
-
 		ring->cur = ring->start;
 		ring->next = ring->start;
 
@@ -277,7 +269,7 @@ void adreno_recover(struct msm_gpu *gpu)
 
 	ret = msm_gpu_hw_init(gpu);
 	if (ret) {
-		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "gpu hw init failed: %d\n", ret);
 		/* hmm, oh well? */
 	}
 }
@@ -319,16 +311,27 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		 */
 		OUT_PKT3(ring, CP_EVENT_WRITE, 1);
 		OUT_RING(ring, HLSQ_FLUSH);
-
-		OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
-		OUT_RING(ring, 0x00000000);
 	}
 
-	/* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */
-	OUT_PKT3(ring, CP_EVENT_WRITE, 3);
-	OUT_RING(ring, CACHE_FLUSH_TS | BIT(31));
-	OUT_RING(ring, rbmemptr(ring, fence));
-	OUT_RING(ring, submit->seqno);
+	/* wait for idle before cache flush/interrupt */
+	OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
+	OUT_RING(ring, 0x00000000);
+
+	if (!adreno_is_a2xx(adreno_gpu)) {
+		/* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */
+		OUT_PKT3(ring, CP_EVENT_WRITE, 3);
+		OUT_RING(ring, CACHE_FLUSH_TS | BIT(31));
+		OUT_RING(ring, rbmemptr(ring, fence));
+		OUT_RING(ring, submit->seqno);
+	} else {
+		/* BIT(31) means something else on a2xx */
+		OUT_PKT3(ring, CP_EVENT_WRITE, 3);
+		OUT_RING(ring, CACHE_FLUSH_TS);
+		OUT_RING(ring, rbmemptr(ring, fence));
+		OUT_RING(ring, submit->seqno);
+		OUT_PKT3(ring, CP_INTERRUPT, 1);
+		OUT_RING(ring, 0x80000000);
+	}
 
 #if 0
 	if (adreno_is_a3xx(adreno_gpu)) {
@@ -406,7 +409,7 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 				size = j + 1;
 
 		if (size) {
-			state->ring[i].data = kmalloc(size << 2, GFP_KERNEL);
+			state->ring[i].data = kvmalloc(size << 2, GFP_KERNEL);
 			if (state->ring[i].data) {
 				memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2);
 				state->ring[i].data_size = size << 2;
@@ -414,6 +417,10 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 		}
 	}
 
+	/* Some targets prefer to collect their own registers */
+	if (!adreno_gpu->registers)
+		return 0;
+
 	/* Count the number of registers */
 	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2)
 		count += adreno_gpu->registers[i + 1] -
@@ -445,7 +452,7 @@ void adreno_gpu_state_destroy(struct msm_gpu_state *state)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
-		kfree(state->ring[i].data);
+		kvfree(state->ring[i].data);
 
 	for (i = 0; state->bos && i < state->nr_bos; i++)
 		kvfree(state->bos[i].data);
@@ -475,34 +482,74 @@ int adreno_gpu_state_put(struct msm_gpu_state *state)
 
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 
-static void adreno_show_object(struct drm_printer *p, u32 *ptr, int len)
+static char *adreno_gpu_ascii85_encode(u32 *src, size_t len)
 {
+	void *buf;
+	size_t buf_itr = 0, buffer_size;
 	char out[ASCII85_BUFSZ];
-	long l, datalen, i;
+	long l;
+	int i;
 
-	if (!ptr || !len)
-		return;
+	if (!src || !len)
+		return NULL;
+
+	l = ascii85_encode_len(len);
 
 	/*
-	 * Only dump the non-zero part of the buffer - rarely will any data
-	 * completely fill the entire allocated size of the buffer
+	 * Ascii85 outputs either a 5 byte string or a 1 byte string. So we
+	 * account for the worst case of 5 bytes per dword plus the 1 for '\0'
 	 */
-	for (datalen = 0, i = 0; i < len >> 2; i++) {
-		if (ptr[i])
-			datalen = (i << 2) + 1;
-	}
+	buffer_size = (l * 5) + 1;
+
+	buf = kvmalloc(buffer_size, GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	for (i = 0; i < l; i++)
+		buf_itr += snprintf(buf + buf_itr, buffer_size - buf_itr, "%s",
+				ascii85_encode(src[i], out));
+
+	return buf;
+}
 
-	/* Skip printing the object if it is empty */
-	if (datalen == 0)
+/* len is expected to be in bytes */
+static void adreno_show_object(struct drm_printer *p, void **ptr, int len,
+		bool *encoded)
+{
+	if (!*ptr || !len)
 		return;
 
-	l = ascii85_encode_len(datalen);
+	if (!*encoded) {
+		long datalen, i;
+		u32 *buf = *ptr;
+
+		/*
+		 * Only dump the non-zero part of the buffer - rarely will
+		 * any data completely fill the entire allocated size of
+		 * the buffer.
+		 */
+		for (datalen = 0, i = 0; i < len >> 2; i++)
+			if (buf[i])
+				datalen = ((i + 1) << 2);
+
+		/*
+		 * If we reach here, then the originally captured binary buffer
+		 * will be replaced with the ascii85 encoded string
+		 */
+		*ptr = adreno_gpu_ascii85_encode(buf, datalen);
+
+		kvfree(buf);
+
+		*encoded = true;
+	}
+
+	if (!*ptr)
+		return;
 
 	drm_puts(p, "    data: !!ascii85 |\n");
 	drm_puts(p, "     ");
 
-	for (i = 0; i < l; i++)
-		drm_puts(p, ascii85_encode(ptr[i], out));
+	drm_puts(p, *ptr);
 
 	drm_puts(p, "\n");
 }
@@ -534,8 +581,8 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
 		drm_printf(p, "    size: %d\n", MSM_GPU_RINGBUFFER_SZ);
 
-		adreno_show_object(p, state->ring[i].data,
-			state->ring[i].data_size);
+		adreno_show_object(p, &state->ring[i].data,
+			state->ring[i].data_size, &state->ring[i].encoded);
 	}
 
 	if (state->bos) {
@@ -546,17 +593,19 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 				state->bos[i].iova);
 			drm_printf(p, "    size: %zd\n", state->bos[i].size);
 
-			adreno_show_object(p, state->bos[i].data,
-				state->bos[i].size);
+			adreno_show_object(p, &state->bos[i].data,
+				state->bos[i].size, &state->bos[i].encoded);
 		}
 	}
 
-	drm_puts(p, "registers:\n");
+	if (state->nr_registers) {
+		drm_puts(p, "registers:\n");
 
-	for (i = 0; i < state->nr_registers; i++) {
-		drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
-			state->registers[i * 2] << 2,
-			state->registers[(i * 2) + 1]);
+		for (i = 0; i < state->nr_registers; i++) {
+			drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+				state->registers[i * 2] << 2,
+				state->registers[(i * 2) + 1]);
+		}
 	}
 }
 #endif
@@ -595,6 +644,9 @@ void adreno_dump(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
 
+	if (!adreno_gpu->registers)
+		return;
+
 	/* dump these out in a form that can be parsed by demsm: */
 	printk("IO:region %s 00000000 00020000\n", gpu->name);
 	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
@@ -635,7 +687,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev)
 
 	node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels");
 	if (!node) {
-		dev_err(dev, "Could not find the GPU powerlevels\n");
+		DRM_DEV_ERROR(dev, "Could not find the GPU powerlevels\n");
 		return -ENXIO;
 	}
 
@@ -674,7 +726,7 @@ static int adreno_get_pwrlevels(struct device *dev,
 	else {
 		ret = dev_pm_opp_of_add_table(dev);
 		if (ret)
-			dev_err(dev, "Unable to set the OPP table\n");
+			DRM_DEV_ERROR(dev, "Unable to set the OPP table\n");
 	}
 
 	if (!ret) {
@@ -717,6 +769,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_gpu_config.va_start = SZ_16M;
 	adreno_gpu_config.va_end = 0xffffffff;
+	/* maximum range of a2xx mmu */
+	if (adreno_is_a2xx(adreno_gpu))
+		adreno_gpu_config.va_end = SZ_16M + 0xfff * SZ_64K;
 
 	adreno_gpu_config.nr_rings = nr_rings;
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index de6e6ee42fba..5db459bc28a7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -21,6 +21,7 @@
 #define __ADRENO_GPU_H__
 
 #include <linux/firmware.h>
+#include <linux/iopoll.h>
 
 #include "msm_gpu.h"
 
@@ -154,6 +155,20 @@ struct adreno_platform_config {
 	__ret;                                             \
 })
 
+static inline bool adreno_is_a2xx(struct adreno_gpu *gpu)
+{
+	return (gpu->revn < 300);
+}
+
+static inline bool adreno_is_a20x(struct adreno_gpu *gpu)
+{
+	return (gpu->revn < 210);
+}
+
+static inline bool adreno_is_a225(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 225;
+}
 
 static inline bool adreno_is_a3xx(struct adreno_gpu *gpu)
 {
@@ -334,6 +349,7 @@ static inline void adreno_gpu_write(struct adreno_gpu *gpu,
 		gpu_write(&gpu->base, reg - 1, data);
 }
 
+struct msm_gpu *a2xx_gpu_init(struct drm_device *dev);
 struct msm_gpu *a3xx_gpu_init(struct drm_device *dev);
 struct msm_gpu *a4xx_gpu_init(struct drm_device *dev);
 struct msm_gpu *a5xx_gpu_init(struct drm_device *dev);
@@ -375,4 +391,9 @@ static inline uint32_t get_wptr(struct msm_ringbuffer *ring)
 	((1 << 29) \
 	((ilog2((_len)) & 0x1F) << 24) | (((_reg) << 2) & 0xFFFFF))
 
+
+#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
+	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
+		interval, timeout)
+
 #endif /* __ADRENO_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
index 15eb03bed984..79b907ac0b4b 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
@@ -10,13 +10,13 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  36805 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  13634 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  42585 bytes, from 2018-10-04 19:06:37)
+- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-10-04 19:06:37)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 139581 bytes, from 2018-10-04 19:06:42)
+- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
+- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
@@ -108,6 +108,13 @@ enum pc_di_src_sel {
 	DI_SRC_SEL_RESERVED = 3,
 };
 
+enum pc_di_face_cull_sel {
+	DI_FACE_CULL_NONE = 0,
+	DI_FACE_CULL_FETCH = 1,
+	DI_FACE_BACKFACE_CULL = 2,
+	DI_FACE_FRONTFACE_CULL = 3,
+};
+
 enum pc_di_index_size {
 	INDEX_SIZE_IGN = 0,
 	INDEX_SIZE_16_BIT = 0,
@@ -356,6 +363,7 @@ enum a6xx_render_mode {
 	RM6_GMEM = 4,
 	RM6_BLIT2D = 5,
 	RM6_RESOLVE = 6,
+	RM6_BLIT2DSCALE = 12,
 };
 
 enum pseudo_reg {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
index 879c13fe74e0..e45c69044935 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -319,10 +319,8 @@ static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
 	unsigned long irq_flags;
 	int i, irq_count, enable_count, cb_count;
 
-	if (!irq_obj || !irq_obj->enable_counts || !irq_obj->irq_cb_tbl) {
-		DPU_ERROR("invalid parameters\n");
+	if (WARN_ON(!irq_obj->enable_counts || !irq_obj->irq_cb_tbl))
 		return 0;
-	}
 
 	for (i = 0; i < irq_obj->total_irqs; i++) {
 		spin_lock_irqsave(&irq_obj->cb_lock, irq_flags);
@@ -343,31 +341,11 @@ static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
 
 DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_core_irq);
 
-int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
-		struct dentry *parent)
-{
-	dpu_kms->irq_obj.debugfs_file = debugfs_create_file("core_irq", 0600,
-			parent, &dpu_kms->irq_obj,
-			&dpu_debugfs_core_irq_fops);
-
-	return 0;
-}
-
-void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
-{
-	debugfs_remove(dpu_kms->irq_obj.debugfs_file);
-	dpu_kms->irq_obj.debugfs_file = NULL;
-}
-
-#else
-int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
 		struct dentry *parent)
 {
-	return 0;
-}
-
-void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
-{
+	debugfs_create_file("core_irq", 0600, parent, &dpu_kms->irq_obj,
+		&dpu_debugfs_core_irq_fops);
 }
 #endif
 
@@ -376,10 +354,7 @@ void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	} else if (!dpu_kms->dev) {
+	if (!dpu_kms->dev) {
 		DPU_ERROR("invalid drm device\n");
 		return;
 	} else if (!dpu_kms->dev->dev_private) {
@@ -410,20 +385,12 @@ void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 	}
 }
 
-int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms)
-{
-	return 0;
-}
-
 void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
 {
 	struct msm_drm_private *priv;
 	int i;
 
-	if (!dpu_kms) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return;
-	} else if (!dpu_kms->dev) {
+	if (!dpu_kms->dev) {
 		DPU_ERROR("invalid drm device\n");
 		return;
 	} else if (!dpu_kms->dev->dev_private) {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
index 5e98bba46af5..e9015a2b23fe 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
@@ -24,13 +24,6 @@
 void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms);
 
 /**
- * dpu_core_irq_postinstall - perform post-installation of core IRQ handler
- * @dpu_kms:		DPU handle
- * @return:		0 if success; error code otherwise
- */
-int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms);
-
-/**
  * dpu_core_irq_uninstall - uninstall core IRQ handler
  * @dpu_kms:		DPU handle
  * @return:		none
@@ -139,15 +132,8 @@ int dpu_core_irq_unregister_callback(
  * dpu_debugfs_core_irq_init - register core irq debugfs
  * @dpu_kms: pointer to kms
  * @parent: debugfs directory root
- * @Return: 0 on success
  */
-int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
 		struct dentry *parent);
 
-/**
- * dpu_debugfs_core_irq_destroy - deregister core irq debugfs
- * @dpu_kms: pointer to kms
- */
-void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms);
-
 #endif /* __DPU_CORE_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 41c5191f9056..9f20f397f77d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -24,8 +24,6 @@
 #include "dpu_crtc.h"
 #include "dpu_core_perf.h"
 
-#define DPU_PERF_MODE_STRING_SIZE	128
-
 /**
  * enum dpu_perf_mode - performance tuning mode
  * @DPU_PERF_MODE_NORMAL: performance controlled by user mode client
@@ -57,31 +55,20 @@ static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
 	return to_dpu_kms(priv->kms);
 }
 
-static bool _dpu_core_perf_crtc_is_power_on(struct drm_crtc *crtc)
-{
-	return dpu_crtc_is_enabled(crtc);
-}
-
 static bool _dpu_core_video_mode_intf_connected(struct drm_crtc *crtc)
 {
 	struct drm_crtc *tmp_crtc;
-	bool intf_connected = false;
-
-	if (!crtc)
-		goto end;
 
 	drm_for_each_crtc(tmp_crtc, crtc->dev) {
 		if ((dpu_crtc_get_intf_mode(tmp_crtc) == INTF_MODE_VIDEO) &&
-				_dpu_core_perf_crtc_is_power_on(tmp_crtc)) {
+				tmp_crtc->enabled) {
 			DPU_DEBUG("video interface connected crtc:%d\n",
 				tmp_crtc->base.id);
-			intf_connected = true;
-			goto end;
+			return true;
 		}
 	}
 
-end:
-	return intf_connected;
+	return false;
 }
 
 static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
@@ -101,20 +88,20 @@ static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
 	memset(perf, 0, sizeof(struct dpu_core_perf_params));
 
 	if (!dpu_cstate->bw_control) {
-		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		for (i = 0; i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 			perf->bw_ctl[i] = kms->catalog->perf.max_bw_high *
 					1000ULL;
 			perf->max_per_pipe_ib[i] = perf->bw_ctl[i];
 		}
 		perf->core_clk_rate = kms->perf.max_core_clk_rate;
 	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
-		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		for (i = 0; i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 			perf->bw_ctl[i] = 0;
 			perf->max_per_pipe_ib[i] = 0;
 		}
 		perf->core_clk_rate = 0;
 	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) {
-		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		for (i = 0; i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 			perf->bw_ctl[i] = kms->perf.fix_core_ab_vote;
 			perf->max_per_pipe_ib[i] = kms->perf.fix_core_ib_vote;
 		}
@@ -124,12 +111,12 @@ static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
 	DPU_DEBUG(
 		"crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu llcc_ib=%llu llcc_ab=%llu mem_ib=%llu mem_ab=%llu\n",
 			crtc->base.id, perf->core_clk_rate,
-			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MNOC],
-			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
-			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_LLCC],
-			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
-			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_EBI],
-			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI]);
+			perf->max_per_pipe_ib[DPU_CORE_PERF_DATA_BUS_ID_MNOC],
+			perf->bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_MNOC],
+			perf->max_per_pipe_ib[DPU_CORE_PERF_DATA_BUS_ID_LLCC],
+			perf->bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_LLCC],
+			perf->max_per_pipe_ib[DPU_CORE_PERF_DATA_BUS_ID_EBI],
+			perf->bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_EBI]);
 }
 
 int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
@@ -164,13 +151,13 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	/* obtain new values */
 	_dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf);
 
-	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
-			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+	for (i = DPU_CORE_PERF_DATA_BUS_ID_MNOC;
+			i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 		bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl[i];
 		curr_client_type = dpu_crtc_get_client_type(crtc);
 
 		drm_for_each_crtc(tmp_crtc, crtc->dev) {
-			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			if (tmp_crtc->enabled &&
 			    (dpu_crtc_get_client_type(tmp_crtc) ==
 					    curr_client_type) &&
 			    (tmp_crtc != crtc)) {
@@ -229,7 +216,7 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
 	int ret = 0;
 
 	drm_for_each_crtc(tmp_crtc, crtc->dev) {
-		if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+		if (tmp_crtc->enabled &&
 			curr_client_type ==
 				dpu_crtc_get_client_type(tmp_crtc)) {
 			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
@@ -286,7 +273,7 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 	 */
 	if (dpu_crtc_get_intf_mode(crtc) == INTF_MODE_CMD)
 		drm_for_each_crtc(tmp_crtc, crtc->dev) {
-			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			if (tmp_crtc->enabled &&
 				dpu_crtc_get_intf_mode(tmp_crtc) ==
 						INTF_MODE_VIDEO)
 				return;
@@ -296,7 +283,7 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 	if (kms->perf.enable_bw_release) {
 		trace_dpu_cmd_release_bw(crtc->base.id);
 		DPU_DEBUG("Release BW crtc=%d\n", crtc->base.id);
-		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		for (i = 0; i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 			dpu_crtc->cur_perf.bw_ctl[i] = 0;
 			_dpu_core_perf_crtc_update_bus(kms, crtc, i);
 		}
@@ -321,7 +308,7 @@ static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
 	struct dpu_crtc_state *dpu_cstate;
 
 	drm_for_each_crtc(crtc, kms->dev) {
-		if (_dpu_core_perf_crtc_is_power_on(crtc)) {
+		if (crtc->enabled) {
 			dpu_cstate = to_dpu_crtc_state(crtc->state);
 			clk_rate = max(dpu_cstate->new_perf.core_clk_rate,
 							clk_rate);
@@ -372,8 +359,8 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	old = &dpu_crtc->cur_perf;
 	new = &dpu_cstate->new_perf;
 
-	if (_dpu_core_perf_crtc_is_power_on(crtc) && !stop_req) {
-		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+	if (crtc->enabled && !stop_req) {
+		for (i = 0; i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 			/*
 			 * cases for bus bandwidth update.
 			 * 1. new bandwidth vote - "ab or ib vote" is higher
@@ -415,13 +402,13 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 		update_clk = 1;
 	}
 	trace_dpu_perf_crtc_update(crtc->base.id,
-				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
-				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
-				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI],
+				new->bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_MNOC],
+				new->bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_LLCC],
+				new->bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_EBI],
 				new->core_clk_rate, stop_req,
 				update_bus, update_clk);
 
-	for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+	for (i = 0; i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
 		if (update_bus & BIT(i)) {
 			ret = _dpu_core_perf_crtc_update_bus(kms, crtc, i);
 			if (ret) {
@@ -462,24 +449,14 @@ static ssize_t _dpu_core_perf_mode_write(struct file *file,
 	struct dpu_core_perf *perf = file->private_data;
 	struct dpu_perf_cfg *cfg = &perf->catalog->perf;
 	u32 perf_mode = 0;
-	char buf[10];
-
-	if (!perf)
-		return -ENODEV;
-
-	if (count >= sizeof(buf))
-		return -EFAULT;
-
-	if (copy_from_user(buf, user_buf, count))
-		return -EFAULT;
-
-	buf[count] = 0;	/* end of string */
+	int ret;
 
-	if (kstrtouint(buf, 0, &perf_mode))
-		return -EFAULT;
+	ret = kstrtouint_from_user(user_buf, count, 0, &perf_mode);
+	if (ret)
+		return ret;
 
 	if (perf_mode >= DPU_PERF_MODE_MAX)
-		return -EFAULT;
+		return -EINVAL;
 
 	if (perf_mode == DPU_PERF_MODE_FIXED) {
 		DRM_INFO("fix performance mode\n");
@@ -504,29 +481,16 @@ static ssize_t _dpu_core_perf_mode_read(struct file *file,
 			char __user *buff, size_t count, loff_t *ppos)
 {
 	struct dpu_core_perf *perf = file->private_data;
-	int len = 0;
-	char buf[DPU_PERF_MODE_STRING_SIZE] = {'\0'};
-
-	if (!perf)
-		return -ENODEV;
+	int len;
+	char buf[128];
 
-	if (*ppos)
-		return 0;	/* the end */
-
-	len = snprintf(buf, sizeof(buf),
+	len = scnprintf(buf, sizeof(buf),
 			"mode %d min_mdp_clk %llu min_bus_vote %llu\n",
 			perf->perf_tune.mode,
 			perf->perf_tune.min_core_clk,
 			perf->perf_tune.min_bus_vote);
-	if (len < 0 || len >= sizeof(buf))
-		return 0;
-
-	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
-		return -EFAULT;
-
-	*ppos += len;   /* increase offset */
 
-	return len;
+	return simple_read_from_buffer(buff, count, ppos, buf, len);
 }
 
 static const struct file_operations dpu_core_perf_mode_fops = {
@@ -535,70 +499,43 @@ static const struct file_operations dpu_core_perf_mode_fops = {
 	.write = _dpu_core_perf_mode_write,
 };
 
-static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
-{
-	debugfs_remove_recursive(perf->debugfs_root);
-	perf->debugfs_root = NULL;
-}
-
-int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
-		struct dentry *parent)
+int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent)
 {
+	struct dpu_core_perf *perf = &dpu_kms->perf;
 	struct dpu_mdss_cfg *catalog = perf->catalog;
-	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
-
-	priv = perf->dev->dev_private;
-	if (!priv || !priv->kms) {
-		DPU_ERROR("invalid KMS reference\n");
-		return -EINVAL;
-	}
+	struct dentry *entry;
 
-	dpu_kms = to_dpu_kms(priv->kms);
-
-	perf->debugfs_root = debugfs_create_dir("core_perf", parent);
-	if (!perf->debugfs_root) {
-		DPU_ERROR("failed to create core perf debugfs\n");
+	entry = debugfs_create_dir("core_perf", parent);
+	if (IS_ERR_OR_NULL(entry))
 		return -EINVAL;
-	}
 
-	debugfs_create_u64("max_core_clk_rate", 0600, perf->debugfs_root,
+	debugfs_create_u64("max_core_clk_rate", 0600, entry,
 			&perf->max_core_clk_rate);
-	debugfs_create_u64("core_clk_rate", 0600, perf->debugfs_root,
+	debugfs_create_u64("core_clk_rate", 0600, entry,
 			&perf->core_clk_rate);
-	debugfs_create_u32("enable_bw_release", 0600, perf->debugfs_root,
+	debugfs_create_u32("enable_bw_release", 0600, entry,
 			(u32 *)&perf->enable_bw_release);
-	debugfs_create_u32("threshold_low", 0600, perf->debugfs_root,
+	debugfs_create_u32("threshold_low", 0600, entry,
 			(u32 *)&catalog->perf.max_bw_low);
-	debugfs_create_u32("threshold_high", 0600, perf->debugfs_root,
+	debugfs_create_u32("threshold_high", 0600, entry,
 			(u32 *)&catalog->perf.max_bw_high);
-	debugfs_create_u32("min_core_ib", 0600, perf->debugfs_root,
+	debugfs_create_u32("min_core_ib", 0600, entry,
 			(u32 *)&catalog->perf.min_core_ib);
-	debugfs_create_u32("min_llcc_ib", 0600, perf->debugfs_root,
+	debugfs_create_u32("min_llcc_ib", 0600, entry,
 			(u32 *)&catalog->perf.min_llcc_ib);
-	debugfs_create_u32("min_dram_ib", 0600, perf->debugfs_root,
+	debugfs_create_u32("min_dram_ib", 0600, entry,
 			(u32 *)&catalog->perf.min_dram_ib);
-	debugfs_create_file("perf_mode", 0600, perf->debugfs_root,
+	debugfs_create_file("perf_mode", 0600, entry,
 			(u32 *)perf, &dpu_core_perf_mode_fops);
-	debugfs_create_u64("fix_core_clk_rate", 0600, perf->debugfs_root,
+	debugfs_create_u64("fix_core_clk_rate", 0600, entry,
 			&perf->fix_core_clk_rate);
-	debugfs_create_u64("fix_core_ib_vote", 0600, perf->debugfs_root,
+	debugfs_create_u64("fix_core_ib_vote", 0600, entry,
 			&perf->fix_core_ib_vote);
-	debugfs_create_u64("fix_core_ab_vote", 0600, perf->debugfs_root,
+	debugfs_create_u64("fix_core_ab_vote", 0600, entry,
 			&perf->fix_core_ab_vote);
 
 	return 0;
 }
-#else
-static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
-{
-}
-
-int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
-		struct dentry *parent)
-{
-	return 0;
-}
 #endif
 
 void dpu_core_perf_destroy(struct dpu_core_perf *perf)
@@ -608,10 +545,8 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf)
 		return;
 	}
 
-	dpu_core_perf_debugfs_destroy(perf);
 	perf->max_core_clk_rate = 0;
 	perf->core_clk = NULL;
-	perf->phandle = NULL;
 	perf->catalog = NULL;
 	perf->dev = NULL;
 }
@@ -619,12 +554,10 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf)
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		struct drm_device *dev,
 		struct dpu_mdss_cfg *catalog,
-		struct dpu_power_handle *phandle,
 		struct dss_clk *core_clk)
 {
 	perf->dev = dev;
 	perf->catalog = catalog;
-	perf->phandle = phandle;
 	perf->core_clk = core_clk;
 
 	perf->max_core_clk_rate = core_clk->max_rate;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index fbcbe0c7527a..37f518815eb7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -19,19 +19,31 @@
 #include <drm/drm_crtc.h>
 
 #include "dpu_hw_catalog.h"
-#include "dpu_power_handle.h"
 
 #define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
 
 /**
+ * enum dpu_core_perf_data_bus_id - data bus identifier
+ * @DPU_CORE_PERF_DATA_BUS_ID_MNOC: DPU/MNOC data bus
+ * @DPU_CORE_PERF_DATA_BUS_ID_LLCC: MNOC/LLCC data bus
+ * @DPU_CORE_PERF_DATA_BUS_ID_EBI: LLCC/EBI data bus
+ */
+enum dpu_core_perf_data_bus_id {
+	DPU_CORE_PERF_DATA_BUS_ID_MNOC,
+	DPU_CORE_PERF_DATA_BUS_ID_LLCC,
+	DPU_CORE_PERF_DATA_BUS_ID_EBI,
+	DPU_CORE_PERF_DATA_BUS_ID_MAX,
+};
+
+/**
  * struct dpu_core_perf_params - definition of performance parameters
  * @max_per_pipe_ib: maximum instantaneous bandwidth request
  * @bw_ctl: arbitrated bandwidth request
  * @core_clk_rate: core clock rate request
  */
 struct dpu_core_perf_params {
-	u64 max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MAX];
-	u64 bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 max_per_pipe_ib[DPU_CORE_PERF_DATA_BUS_ID_MAX];
+	u64 bw_ctl[DPU_CORE_PERF_DATA_BUS_ID_MAX];
 	u64 core_clk_rate;
 };
 
@@ -52,7 +64,6 @@ struct dpu_core_perf_tune {
  * @dev: Pointer to drm device
  * @debugfs_root: top level debug folder
  * @catalog: Pointer to catalog configuration
- * @phandle: Pointer to power handler
  * @core_clk: Pointer to core clock structure
  * @core_clk_rate: current core clock rate
  * @max_core_clk_rate: maximum allowable core clock rate
@@ -66,7 +77,6 @@ struct dpu_core_perf {
 	struct drm_device *dev;
 	struct dentry *debugfs_root;
 	struct dpu_mdss_cfg *catalog;
-	struct dpu_power_handle *phandle;
 	struct dss_clk *core_clk;
 	u64 core_clk_rate;
 	u64 max_core_clk_rate;
@@ -113,21 +123,20 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf);
  * @perf: Pointer to core performance context
  * @dev: Pointer to drm device
  * @catalog: Pointer to catalog
- * @phandle: Pointer to power handle
  * @core_clk: pointer to core clock
  */
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		struct drm_device *dev,
 		struct dpu_mdss_cfg *catalog,
-		struct dpu_power_handle *phandle,
 		struct dss_clk *core_clk);
 
+struct dpu_kms;
+
 /**
  * dpu_core_perf_debugfs_init - initialize debugfs for core performance context
- * @perf: Pointer to core performance context
+ * @dpu_kms: Pointer to the dpu_kms struct
  * @debugfs_parent: Pointer to parent debugfs
  */
-int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
-		struct dentry *parent);
+int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent);
 
 #endif /* _DPU_CORE_PERF_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index d4530d60767b..a6f0c38a0a95 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -33,7 +33,6 @@
 #include "dpu_plane.h"
 #include "dpu_encoder.h"
 #include "dpu_vbif.h"
-#include "dpu_power_handle.h"
 #include "dpu_core_perf.h"
 #include "dpu_trace.h"
 
@@ -47,13 +46,7 @@
 #define LEFT_MIXER 0
 #define RIGHT_MIXER 1
 
-static inline int _dpu_crtc_get_mixer_width(struct dpu_crtc_state *cstate,
-					    struct drm_display_mode *mode)
-{
-	return mode->hdisplay / cstate->num_mixers;
-}
-
-static inline struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
 {
 	struct msm_drm_private *priv = crtc->dev->dev_private;
 
@@ -69,10 +62,7 @@ static void dpu_crtc_destroy(struct drm_crtc *crtc)
 	if (!crtc)
 		return;
 
-	dpu_crtc->phandle = NULL;
-
 	drm_crtc_cleanup(crtc);
-	mutex_destroy(&dpu_crtc->crtc_lock);
 	kfree(dpu_crtc);
 }
 
@@ -287,16 +277,17 @@ enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
 		return INTF_MODE_NONE;
 	}
 
-	drm_for_each_encoder(encoder, crtc->dev)
-		if (encoder->crtc == crtc)
-			return dpu_encoder_get_intf_mode(encoder);
+	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
+	/* TODO: Returns the first INTF_MODE, could there be multiple values? */
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		return dpu_encoder_get_intf_mode(encoder);
 
 	return INTF_MODE_NONE;
 }
 
-static void dpu_crtc_vblank_cb(void *data)
+void dpu_crtc_vblank_callback(struct drm_crtc *crtc)
 {
-	struct drm_crtc *crtc = (struct drm_crtc *)data;
 	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
 
 	/* keep statistics on vblank callback - with auto reset via debugfs */
@@ -309,6 +300,19 @@ static void dpu_crtc_vblank_cb(void *data)
 	trace_dpu_crtc_vblank_cb(DRMID(crtc));
 }
 
+static void dpu_crtc_release_bw_unlocked(struct drm_crtc *crtc)
+{
+	int ret = 0;
+	struct drm_modeset_acquire_ctx ctx;
+
+	DRM_MODESET_LOCK_ALL_BEGIN(crtc->dev, ctx, 0, ret);
+	dpu_core_perf_crtc_release_bw(crtc);
+	DRM_MODESET_LOCK_ALL_END(ctx, ret);
+	if (ret)
+		DRM_ERROR("Failed to acquire modeset locks to release bw, %d\n",
+			  ret);
+}
+
 static void dpu_crtc_frame_event_work(struct kthread_work *work)
 {
 	struct dpu_crtc_frame_event *fevent = container_of(work,
@@ -338,7 +342,7 @@ static void dpu_crtc_frame_event_work(struct kthread_work *work)
 			/* release bandwidth and other resources */
 			trace_dpu_crtc_frame_event_done(DRMID(crtc),
 							fevent->event);
-			dpu_core_perf_crtc_release_bw(crtc);
+			dpu_crtc_release_bw_unlocked(crtc);
 		} else {
 			trace_dpu_crtc_frame_event_more_pending(DRMID(crtc),
 								fevent->event);
@@ -473,28 +477,21 @@ static void _dpu_crtc_setup_mixer_for_encoder(
 
 static void _dpu_crtc_setup_mixers(struct drm_crtc *crtc)
 {
-	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
 	struct drm_encoder *enc;
 
-	mutex_lock(&dpu_crtc->crtc_lock);
-	/* Check for mixers on all encoders attached to this crtc */
-	list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) {
-		if (enc->crtc != crtc)
-			continue;
+	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
+	/* Check for mixers on all encoders attached to this crtc */
+	drm_for_each_encoder_mask(enc, crtc->dev, crtc->state->encoder_mask)
 		_dpu_crtc_setup_mixer_for_encoder(crtc, enc);
-	}
-
-	mutex_unlock(&dpu_crtc->crtc_lock);
 }
 
 static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
 		struct drm_crtc_state *state)
 {
-	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
 	struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
 	struct drm_display_mode *adj_mode = &state->adjusted_mode;
-	u32 crtc_split_width = _dpu_crtc_get_mixer_width(cstate, adj_mode);
+	u32 crtc_split_width = adj_mode->hdisplay / cstate->num_mixers;
 	int i;
 
 	for (i = 0; i < cstate->num_mixers; i++) {
@@ -502,7 +499,7 @@ static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
 		r->x1 = crtc_split_width * i;
 		r->y1 = 0;
 		r->x2 = r->x1 + crtc_split_width;
-		r->y2 = dpu_crtc_get_mixer_height(dpu_crtc, cstate, adj_mode);
+		r->y2 = adj_mode->vdisplay;
 
 		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
 	}
@@ -552,13 +549,9 @@ static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->crtc != crtc)
-			continue;
-
-		/* encoder will trigger pending mask now */
+	/* encoder will trigger pending mask now */
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
 		dpu_encoder_trigger_kickoff_pending(encoder);
-	}
 
 	/*
 	 * If no mixers have been allocated in dpu_crtc_atomic_check(),
@@ -702,10 +695,9 @@ static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc)
 	return rc;
 }
 
-void dpu_crtc_commit_kickoff(struct drm_crtc *crtc)
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc, bool async)
 {
 	struct drm_encoder *encoder;
-	struct drm_device *dev = crtc->dev;
 	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
 	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
 	struct dpu_crtc_state *cstate = to_dpu_crtc_state(crtc->state);
@@ -721,127 +713,59 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc)
 
 	DPU_ATRACE_BEGIN("crtc_commit");
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+	/*
+	 * Encoder will flush/start now, unless it has a tx pending. If so, it
+	 * may delay and flush at an irq event (e.g. ppdone)
+	 */
+	drm_for_each_encoder_mask(encoder, crtc->dev,
+				  crtc->state->encoder_mask) {
 		struct dpu_encoder_kickoff_params params = { 0 };
-
-		if (encoder->crtc != crtc)
-			continue;
-
-		/*
-		 * Encoder will flush/start now, unless it has a tx pending.
-		 * If so, it may delay and flush at an irq event (e.g. ppdone)
-		 */
-		dpu_encoder_prepare_for_kickoff(encoder, &params);
+		dpu_encoder_prepare_for_kickoff(encoder, &params, async);
 	}
 
-	/* wait for frame_event_done completion */
-	DPU_ATRACE_BEGIN("wait_for_frame_done_event");
-	ret = _dpu_crtc_wait_for_frame_done(crtc);
-	DPU_ATRACE_END("wait_for_frame_done_event");
-	if (ret) {
-		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
-				crtc->base.id,
-				atomic_read(&dpu_crtc->frame_pending));
-		goto end;
-	}
 
-	if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) {
-		/* acquire bandwidth and other resources */
-		DPU_DEBUG("crtc%d first commit\n", crtc->base.id);
-	} else
-		DPU_DEBUG("crtc%d commit\n", crtc->base.id);
+	if (!async) {
+		/* wait for frame_event_done completion */
+		DPU_ATRACE_BEGIN("wait_for_frame_done_event");
+		ret = _dpu_crtc_wait_for_frame_done(crtc);
+		DPU_ATRACE_END("wait_for_frame_done_event");
+		if (ret) {
+			DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+					crtc->base.id,
+					atomic_read(&dpu_crtc->frame_pending));
+			goto end;
+		}
+
+		if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) {
+			/* acquire bandwidth and other resources */
+			DPU_DEBUG("crtc%d first commit\n", crtc->base.id);
+		} else
+			DPU_DEBUG("crtc%d commit\n", crtc->base.id);
 
-	dpu_crtc->play_count++;
+		dpu_crtc->play_count++;
+	}
 
 	dpu_vbif_clear_errors(dpu_kms);
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->crtc != crtc)
-			continue;
-
-		dpu_encoder_kickoff(encoder);
-	}
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_kickoff(encoder, async);
 
 end:
-	reinit_completion(&dpu_crtc->frame_done_comp);
+	if (!async)
+		reinit_completion(&dpu_crtc->frame_done_comp);
 	DPU_ATRACE_END("crtc_commit");
 }
 
-/**
- * _dpu_crtc_vblank_enable_no_lock - update power resource and vblank request
- * @dpu_crtc: Pointer to dpu crtc structure
- * @enable: Whether to enable/disable vblanks
- */
-static void _dpu_crtc_vblank_enable_no_lock(
-		struct dpu_crtc *dpu_crtc, bool enable)
-{
-	struct drm_crtc *crtc = &dpu_crtc->base;
-	struct drm_device *dev = crtc->dev;
-	struct drm_encoder *enc;
-
-	if (enable) {
-		/* drop lock since power crtc cb may try to re-acquire lock */
-		mutex_unlock(&dpu_crtc->crtc_lock);
-		pm_runtime_get_sync(dev->dev);
-		mutex_lock(&dpu_crtc->crtc_lock);
-
-		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
-			if (enc->crtc != crtc)
-				continue;
-
-			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
-						     DRMID(enc), enable,
-						     dpu_crtc);
-
-			dpu_encoder_register_vblank_callback(enc,
-					dpu_crtc_vblank_cb, (void *)crtc);
-		}
-	} else {
-		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
-			if (enc->crtc != crtc)
-				continue;
-
-			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
-						     DRMID(enc), enable,
-						     dpu_crtc);
-
-			dpu_encoder_register_vblank_callback(enc, NULL, NULL);
-		}
-
-		/* drop lock since power crtc cb may try to re-acquire lock */
-		mutex_unlock(&dpu_crtc->crtc_lock);
-		pm_runtime_put_sync(dev->dev);
-		mutex_lock(&dpu_crtc->crtc_lock);
-	}
-}
-
-/**
- * _dpu_crtc_set_suspend - notify crtc of suspend enable/disable
- * @crtc: Pointer to drm crtc object
- * @enable: true to enable suspend, false to indicate resume
- */
-static void _dpu_crtc_set_suspend(struct drm_crtc *crtc, bool enable)
+static void dpu_crtc_reset(struct drm_crtc *crtc)
 {
-	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
-
-	DRM_DEBUG_KMS("crtc%d suspend = %d\n", crtc->base.id, enable);
-
-	mutex_lock(&dpu_crtc->crtc_lock);
+	struct dpu_crtc_state *cstate;
 
-	/*
-	 * If the vblank is enabled, release a power reference on suspend
-	 * and take it back during resume (if it is still enabled).
-	 */
-	trace_dpu_crtc_set_suspend(DRMID(&dpu_crtc->base), enable, dpu_crtc);
-	if (dpu_crtc->suspend == enable)
-		DPU_DEBUG("crtc%d suspend already set to %d, ignoring update\n",
-				crtc->base.id, enable);
-	else if (dpu_crtc->enabled && dpu_crtc->vblank_requested) {
-		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, !enable);
-	}
+	if (crtc->state)
+		dpu_crtc_destroy_state(crtc, crtc->state);
 
-	dpu_crtc->suspend = enable;
-	mutex_unlock(&dpu_crtc->crtc_lock);
+	crtc->state = kzalloc(sizeof(*cstate), GFP_KERNEL);
+	if (crtc->state)
+		crtc->state->crtc = crtc;
 }
 
 /**
@@ -873,65 +797,8 @@ static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc)
 	return &cstate->base;
 }
 
-/**
- * dpu_crtc_reset - reset hook for CRTCs
- * Resets the atomic state for @crtc by freeing the state pointer (which might
- * be NULL, e.g. at driver load time) and allocating a new empty state object.
- * @crtc: Pointer to drm crtc structure
- */
-static void dpu_crtc_reset(struct drm_crtc *crtc)
-{
-	struct dpu_crtc *dpu_crtc;
-	struct dpu_crtc_state *cstate;
-
-	if (!crtc) {
-		DPU_ERROR("invalid crtc\n");
-		return;
-	}
-
-	/* revert suspend actions, if necessary */
-	if (dpu_kms_is_suspend_state(crtc->dev))
-		_dpu_crtc_set_suspend(crtc, false);
-
-	/* remove previous state, if present */
-	if (crtc->state) {
-		dpu_crtc_destroy_state(crtc, crtc->state);
-		crtc->state = 0;
-	}
-
-	dpu_crtc = to_dpu_crtc(crtc);
-	cstate = kzalloc(sizeof(*cstate), GFP_KERNEL);
-	if (!cstate) {
-		DPU_ERROR("failed to allocate state\n");
-		return;
-	}
-
-	cstate->base.crtc = crtc;
-	crtc->state = &cstate->base;
-}
-
-static void dpu_crtc_handle_power_event(u32 event_type, void *arg)
-{
-	struct drm_crtc *crtc = arg;
-	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
-	struct drm_encoder *encoder;
-
-	mutex_lock(&dpu_crtc->crtc_lock);
-
-	trace_dpu_crtc_handle_power_event(DRMID(crtc), event_type);
-
-	/* restore encoder; crtc will be programmed during commit */
-	drm_for_each_encoder(encoder, crtc->dev) {
-		if (encoder->crtc != crtc)
-			continue;
-
-		dpu_encoder_virt_restore(encoder);
-	}
-
-	mutex_unlock(&dpu_crtc->crtc_lock);
-}
-
-static void dpu_crtc_disable(struct drm_crtc *crtc)
+static void dpu_crtc_disable(struct drm_crtc *crtc,
+			     struct drm_crtc_state *old_crtc_state)
 {
 	struct dpu_crtc *dpu_crtc;
 	struct dpu_crtc_state *cstate;
@@ -951,13 +818,12 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 
 	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
 
-	if (dpu_kms_is_suspend_state(crtc->dev))
-		_dpu_crtc_set_suspend(crtc, true);
-
 	/* Disable/save vblank irq handling */
 	drm_crtc_vblank_off(crtc);
 
-	mutex_lock(&dpu_crtc->crtc_lock);
+	drm_for_each_encoder_mask(encoder, crtc->dev,
+				  old_crtc_state->encoder_mask)
+		dpu_encoder_assign_crtc(encoder, NULL);
 
 	/* wait for frame_event_done completion */
 	if (_dpu_crtc_wait_for_frame_done(crtc))
@@ -966,10 +832,6 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 				atomic_read(&dpu_crtc->frame_pending));
 
 	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
-	if (dpu_crtc->enabled && !dpu_crtc->suspend &&
-			dpu_crtc->vblank_requested) {
-		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
-	}
 	dpu_crtc->enabled = false;
 
 	if (atomic_read(&dpu_crtc->frame_pending)) {
@@ -981,15 +843,8 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 
 	dpu_core_perf_crtc_update(crtc, 0, true);
 
-	drm_for_each_encoder(encoder, crtc->dev) {
-		if (encoder->crtc != crtc)
-			continue;
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
 		dpu_encoder_register_frame_event_callback(encoder, NULL, NULL);
-	}
-
-	if (dpu_crtc->power_event)
-		dpu_power_handle_unregister_event(dpu_crtc->phandle,
-				dpu_crtc->power_event);
 
 	memset(cstate->mixers, 0, sizeof(cstate->mixers));
 	cstate->num_mixers = 0;
@@ -998,14 +853,14 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 	cstate->bw_control = false;
 	cstate->bw_split_vote = false;
 
-	mutex_unlock(&dpu_crtc->crtc_lock);
-
 	if (crtc->state->event && !crtc->state->active) {
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 		drm_crtc_send_vblank_event(crtc, crtc->state->event);
 		crtc->state->event = NULL;
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 	}
+
+	pm_runtime_put_sync(crtc->dev->dev);
 }
 
 static void dpu_crtc_enable(struct drm_crtc *crtc,
@@ -1021,33 +876,23 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 	}
 	priv = crtc->dev->dev_private;
 
+	pm_runtime_get_sync(crtc->dev->dev);
+
 	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
 	dpu_crtc = to_dpu_crtc(crtc);
 
-	drm_for_each_encoder(encoder, crtc->dev) {
-		if (encoder->crtc != crtc)
-			continue;
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
 		dpu_encoder_register_frame_event_callback(encoder,
 				dpu_crtc_frame_event_cb, (void *)crtc);
-	}
 
-	mutex_lock(&dpu_crtc->crtc_lock);
 	trace_dpu_crtc_enable(DRMID(crtc), true, dpu_crtc);
-	if (!dpu_crtc->enabled && !dpu_crtc->suspend &&
-			dpu_crtc->vblank_requested) {
-		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, true);
-	}
 	dpu_crtc->enabled = true;
 
-	mutex_unlock(&dpu_crtc->crtc_lock);
+	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
+		dpu_encoder_assign_crtc(encoder, crtc);
 
 	/* Enable/restore vblank irq handling */
 	drm_crtc_vblank_on(crtc);
-
-	dpu_crtc->power_event = dpu_power_handle_register_event(
-		dpu_crtc->phandle, DPU_POWER_EVENT_ENABLE,
-		dpu_crtc_handle_power_event, crtc, dpu_crtc->name);
-
 }
 
 struct plane_state {
@@ -1101,7 +946,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 
 	memset(pipe_staged, 0, sizeof(pipe_staged));
 
-	mixer_width = _dpu_crtc_get_mixer_width(cstate, mode);
+	mixer_width = mode->hdisplay / cstate->num_mixers;
 
 	_dpu_crtc_setup_lm_bounds(crtc, state);
 
@@ -1289,21 +1134,32 @@ end:
 
 int dpu_crtc_vblank(struct drm_crtc *crtc, bool en)
 {
-	struct dpu_crtc *dpu_crtc;
-
-	if (!crtc) {
-		DPU_ERROR("invalid crtc\n");
-		return -EINVAL;
-	}
-	dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_encoder *enc;
 
-	mutex_lock(&dpu_crtc->crtc_lock);
 	trace_dpu_crtc_vblank(DRMID(&dpu_crtc->base), en, dpu_crtc);
-	if (dpu_crtc->enabled && !dpu_crtc->suspend) {
-		_dpu_crtc_vblank_enable_no_lock(dpu_crtc, en);
+
+	/*
+	 * Normally we would iterate through encoder_mask in crtc state to find
+	 * attached encoders. In this case, we might be disabling vblank _after_
+	 * encoder_mask has been cleared.
+	 *
+	 * Instead, we "assign" a crtc to the encoder in enable and clear it in
+	 * disable (which is also after encoder_mask is cleared). So instead of
+	 * using encoder mask, we'll ask the encoder to toggle itself iff it's
+	 * currently assigned to our crtc.
+	 *
+	 * Note also that this function cannot be called while crtc is disabled
+	 * since we use drm_crtc_vblank_on/off. So we don't need to worry
+	 * about the assigned crtcs being inconsistent with the current state
+	 * (which means no need to worry about modeset locks).
+	 */
+	list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) {
+		trace_dpu_crtc_vblank_enable(DRMID(crtc), DRMID(enc), en,
+					     dpu_crtc);
+
+		dpu_encoder_toggle_vblank_for_crtc(enc, crtc, en);
 	}
-	dpu_crtc->vblank_requested = en;
-	mutex_unlock(&dpu_crtc->crtc_lock);
 
 	return 0;
 }
@@ -1324,18 +1180,14 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
 
 	int i, out_width;
 
-	if (!s || !s->private)
-		return -EINVAL;
-
 	dpu_crtc = s->private;
 	crtc = &dpu_crtc->base;
 
 	drm_modeset_lock_all(crtc->dev);
 	cstate = to_dpu_crtc_state(crtc->state);
 
-	mutex_lock(&dpu_crtc->crtc_lock);
 	mode = &crtc->state->adjusted_mode;
-	out_width = _dpu_crtc_get_mixer_width(cstate, mode);
+	out_width = mode->hdisplay / cstate->num_mixers;
 
 	seq_printf(s, "crtc:%d width:%d height:%d\n", crtc->base.id,
 				mode->hdisplay, mode->vdisplay);
@@ -1420,9 +1272,6 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
 		dpu_crtc->vblank_cb_time = ktime_set(0, 0);
 	}
 
-	seq_printf(s, "vblank_enable:%d\n", dpu_crtc->vblank_requested);
-
-	mutex_unlock(&dpu_crtc->crtc_lock);
 	drm_modeset_unlock_all(crtc->dev);
 
 	return 0;
@@ -1456,13 +1305,11 @@ static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v)
 	seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc));
 	seq_printf(s, "core_clk_rate: %llu\n",
 			dpu_crtc->cur_perf.core_clk_rate);
-	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
-			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
-		seq_printf(s, "bw_ctl[%s]: %llu\n",
-				dpu_power_handle_get_dbus_name(i),
+	for (i = DPU_CORE_PERF_DATA_BUS_ID_MNOC;
+			i < DPU_CORE_PERF_DATA_BUS_ID_MAX; i++) {
+		seq_printf(s, "bw_ctl[%d]: %llu\n", i,
 				dpu_crtc->cur_perf.bw_ctl[i]);
-		seq_printf(s, "max_per_pipe_ib[%s]: %llu\n",
-				dpu_power_handle_get_dbus_name(i),
+		seq_printf(s, "max_per_pipe_ib[%d]: %llu\n", i,
 				dpu_crtc->cur_perf.max_per_pipe_ib[i]);
 	}
 
@@ -1472,8 +1319,7 @@ DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_crtc_debugfs_state);
 
 static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
 {
-	struct dpu_crtc *dpu_crtc;
-	struct dpu_kms *dpu_kms;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
 
 	static const struct file_operations debugfs_status_fops = {
 		.open =		_dpu_debugfs_status_open,
@@ -1482,12 +1328,6 @@ static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
 		.release =	single_release,
 	};
 
-	if (!crtc)
-		return -EINVAL;
-	dpu_crtc = to_dpu_crtc(crtc);
-
-	dpu_kms = _dpu_crtc_get_kms(crtc);
-
 	dpu_crtc->debugfs_root = debugfs_create_dir(dpu_crtc->name,
 			crtc->dev->primary->debugfs_root);
 	if (!dpu_crtc->debugfs_root)
@@ -1504,25 +1344,11 @@ static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
 
 	return 0;
 }
-
-static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
-{
-	struct dpu_crtc *dpu_crtc;
-
-	if (!crtc)
-		return;
-	dpu_crtc = to_dpu_crtc(crtc);
-	debugfs_remove_recursive(dpu_crtc->debugfs_root);
-}
 #else
 static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
 {
 	return 0;
 }
-
-static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
-{
-}
 #endif /* CONFIG_DEBUG_FS */
 
 static int dpu_crtc_late_register(struct drm_crtc *crtc)
@@ -1532,7 +1358,9 @@ static int dpu_crtc_late_register(struct drm_crtc *crtc)
 
 static void dpu_crtc_early_unregister(struct drm_crtc *crtc)
 {
-	_dpu_crtc_destroy_debugfs(crtc);
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	debugfs_remove_recursive(dpu_crtc->debugfs_root);
 }
 
 static const struct drm_crtc_funcs dpu_crtc_funcs = {
@@ -1547,7 +1375,7 @@ static const struct drm_crtc_funcs dpu_crtc_funcs = {
 };
 
 static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
-	.disable = dpu_crtc_disable,
+	.atomic_disable = dpu_crtc_disable,
 	.atomic_enable = dpu_crtc_enable,
 	.atomic_check = dpu_crtc_atomic_check,
 	.atomic_begin = dpu_crtc_atomic_begin,
@@ -1574,7 +1402,6 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
 	crtc = &dpu_crtc->base;
 	crtc->dev = dev;
 
-	mutex_init(&dpu_crtc->crtc_lock);
 	spin_lock_init(&dpu_crtc->spin_lock);
 	atomic_set(&dpu_crtc->frame_pending, 0);
 
@@ -1602,8 +1429,6 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane,
 	/* initialize event handling */
 	spin_lock_init(&dpu_crtc->event_lock);
 
-	dpu_crtc->phandle = &kms->phandle;
-
 	DPU_DEBUG("%s: successfully initialized crtc\n", dpu_crtc->name);
 	return crtc;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
index 3723b4830335..dbfb38a1986c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
@@ -132,8 +132,6 @@ struct dpu_crtc_frame_event {
  * @vblank_cb_count : count of vblank callback since last reset
  * @play_count    : frame count between crtc enable and disable
  * @vblank_cb_time  : ktime at vblank count reset
- * @vblank_requested : whether the user has requested vblank events
- * @suspend         : whether or not a suspend operation is in progress
  * @enabled       : whether the DPU CRTC is currently enabled. updated in the
  *                  commit-thread, not state-swap time which is earlier, so
  *                  safe to make decisions on during VBLANK on/off work
@@ -142,7 +140,6 @@ struct dpu_crtc_frame_event {
  * @dirty_list    : list of color processing features are dirty
  * @ad_dirty: list containing ad properties that are dirty
  * @ad_active: list containing ad properties that are active
- * @crtc_lock     : crtc lock around create, destroy and access.
  * @frame_pending : Whether or not an update is pending
  * @frame_events  : static allocation of in-flight frame events
  * @frame_event_list : available frame event list
@@ -152,7 +149,6 @@ struct dpu_crtc_frame_event {
  * @event_worker  : Event worker queue
  * @event_lock    : Spinlock around event handling code
  * @phandle: Pointer to power handler
- * @power_event   : registered power event handle
  * @cur_perf      : current performance committed to clock/bandwidth driver
  */
 struct dpu_crtc {
@@ -168,8 +164,6 @@ struct dpu_crtc {
 	u32 vblank_cb_count;
 	u64 play_count;
 	ktime_t vblank_cb_time;
-	bool vblank_requested;
-	bool suspend;
 	bool enabled;
 
 	struct list_head feature_list;
@@ -178,8 +172,6 @@ struct dpu_crtc {
 	struct list_head ad_dirty;
 	struct list_head ad_active;
 
-	struct mutex crtc_lock;
-
 	atomic_t frame_pending;
 	struct dpu_crtc_frame_event frame_events[DPU_CRTC_FRAME_EVENT_SIZE];
 	struct list_head frame_event_list;
@@ -189,9 +181,6 @@ struct dpu_crtc {
 	/* for handling internal event thread */
 	spinlock_t event_lock;
 
-	struct dpu_power_handle *phandle;
-	struct dpu_power_event *power_event;
-
 	struct dpu_core_perf_params cur_perf;
 
 	struct dpu_crtc_smmu_state_data smmu_state;
@@ -238,41 +227,12 @@ struct dpu_crtc_state {
 	container_of(x, struct dpu_crtc_state, base)
 
 /**
- * dpu_crtc_state_is_stereo - Is crtc virtualized with two mixers?
- * @cstate: Pointer to dpu crtc state
- * @Return: true - has two mixers, false - has one mixer
- */
-static inline bool dpu_crtc_state_is_stereo(struct dpu_crtc_state *cstate)
-{
-	return cstate->num_mixers == CRTC_DUAL_MIXERS;
-}
-
-/**
- * dpu_crtc_get_mixer_height - get the mixer height
- * Mixer height will be same as panel height
- */
-static inline int dpu_crtc_get_mixer_height(struct dpu_crtc *dpu_crtc,
-		struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
-{
-	if (!dpu_crtc || !cstate || !mode)
-		return 0;
-
-	return mode->vdisplay;
-}
-
-/**
  * dpu_crtc_frame_pending - retun the number of pending frames
  * @crtc: Pointer to drm crtc object
  */
 static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc)
 {
-	struct dpu_crtc *dpu_crtc;
-
-	if (!crtc)
-		return -EINVAL;
-
-	dpu_crtc = to_dpu_crtc(crtc);
-	return atomic_read(&dpu_crtc->frame_pending);
+	return crtc ? atomic_read(&to_dpu_crtc(crtc)->frame_pending) : -EINVAL;
 }
 
 /**
@@ -283,10 +243,17 @@ static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc)
 int dpu_crtc_vblank(struct drm_crtc *crtc, bool en);
 
 /**
+ * dpu_crtc_vblank_callback - called on vblank irq, issues completion events
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_vblank_callback(struct drm_crtc *crtc);
+
+/**
  * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc
  * @crtc: Pointer to drm crtc object
+ * @async: true if the commit is asynchronous, false otherwise
  */
-void dpu_crtc_commit_kickoff(struct drm_crtc *crtc);
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc, bool async);
 
 /**
  * dpu_crtc_complete_commit - callback signalling completion of current commit
@@ -329,22 +296,7 @@ enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc);
 static inline enum dpu_crtc_client_type dpu_crtc_get_client_type(
 						struct drm_crtc *crtc)
 {
-	struct dpu_crtc_state *cstate =
-			crtc ? to_dpu_crtc_state(crtc->state) : NULL;
-
-	if (!cstate)
-		return NRT_CLIENT;
-
-	return RT_CLIENT;
-}
-
-/**
- * dpu_crtc_is_enabled - check if dpu crtc is enabled or not
- * @crtc: Pointer to crtc
- */
-static inline bool dpu_crtc_is_enabled(struct drm_crtc *crtc)
-{
-	return crtc ? crtc->enabled : false;
+	return crtc && crtc->state ? RT_CLIENT : NRT_CLIENT;
 }
 
 #endif /* _DPU_CRTC_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
deleted file mode 100644
index ae2aee7ed9e1..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
+++ /dev/null
@@ -1,2393 +0,0 @@
-/* Copyright (c) 2009-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
-
-#include <linux/delay.h>
-#include <linux/spinlock.h>
-#include <linux/ktime.h>
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
-#include <linux/dma-buf.h>
-#include <linux/slab.h>
-#include <linux/list_sort.h>
-#include <linux/pm_runtime.h>
-
-#include "dpu_dbg.h"
-#include "disp/dpu1/dpu_hw_catalog.h"
-
-
-#define DEFAULT_DBGBUS_DPU	DPU_DBG_DUMP_IN_MEM
-#define DEFAULT_DBGBUS_VBIFRT	DPU_DBG_DUMP_IN_MEM
-#define REG_BASE_NAME_LEN	80
-
-#define DBGBUS_FLAGS_DSPP	BIT(0)
-#define DBGBUS_DSPP_STATUS	0x34C
-
-#define DBGBUS_NAME_DPU		"dpu"
-#define DBGBUS_NAME_VBIF_RT	"vbif_rt"
-
-/* offsets from dpu top address for the debug buses */
-#define DBGBUS_SSPP0	0x188
-#define DBGBUS_AXI_INTF	0x194
-#define DBGBUS_SSPP1	0x298
-#define DBGBUS_DSPP	0x348
-#define DBGBUS_PERIPH	0x418
-
-#define TEST_MASK(id, tp)	((id << 4) | (tp << 1) | BIT(0))
-
-/* following offsets are with respect to MDP VBIF base for DBG BUS access */
-#define MMSS_VBIF_CLKON			0x4
-#define MMSS_VBIF_TEST_BUS_OUT_CTRL	0x210
-#define MMSS_VBIF_TEST_BUS_OUT		0x230
-
-/* Vbif error info */
-#define MMSS_VBIF_PND_ERR		0x190
-#define MMSS_VBIF_SRC_ERR		0x194
-#define MMSS_VBIF_XIN_HALT_CTRL1	0x204
-#define MMSS_VBIF_ERR_INFO		0X1a0
-#define MMSS_VBIF_ERR_INFO_1		0x1a4
-#define MMSS_VBIF_CLIENT_NUM		14
-
-/**
- * struct dpu_dbg_reg_base - register region base.
- *	may sub-ranges: sub-ranges are used for dumping
- *	or may not have sub-ranges: dumping is base -> max_offset
- * @reg_base_head: head of this node
- * @name: register base name
- * @base: base pointer
- * @off: cached offset of region for manual register dumping
- * @cnt: cached range of region for manual register dumping
- * @max_offset: length of region
- * @buf: buffer used for manual register dumping
- * @buf_len:  buffer length used for manual register dumping
- * @cb: callback for external dump function, null if not defined
- * @cb_ptr: private pointer to callback function
- */
-struct dpu_dbg_reg_base {
-	struct list_head reg_base_head;
-	char name[REG_BASE_NAME_LEN];
-	void __iomem *base;
-	size_t off;
-	size_t cnt;
-	size_t max_offset;
-	char *buf;
-	size_t buf_len;
-	void (*cb)(void *ptr);
-	void *cb_ptr;
-};
-
-struct dpu_debug_bus_entry {
-	u32 wr_addr;
-	u32 block_id;
-	u32 test_id;
-	void (*analyzer)(void __iomem *mem_base,
-				struct dpu_debug_bus_entry *entry, u32 val);
-};
-
-struct vbif_debug_bus_entry {
-	u32 disable_bus_addr;
-	u32 block_bus_addr;
-	u32 bit_offset;
-	u32 block_cnt;
-	u32 test_pnt_start;
-	u32 test_pnt_cnt;
-};
-
-struct dpu_dbg_debug_bus_common {
-	char *name;
-	u32 enable_mask;
-	bool include_in_deferred_work;
-	u32 flags;
-	u32 entries_size;
-	u32 *dumped_content;
-};
-
-struct dpu_dbg_dpu_debug_bus {
-	struct dpu_dbg_debug_bus_common cmn;
-	struct dpu_debug_bus_entry *entries;
-	u32 top_blk_off;
-};
-
-struct dpu_dbg_vbif_debug_bus {
-	struct dpu_dbg_debug_bus_common cmn;
-	struct vbif_debug_bus_entry *entries;
-};
-
-/**
- * struct dpu_dbg_base - global dpu debug base structure
- * @reg_base_list: list of register dumping regions
- * @dev: device pointer
- * @dump_work: work struct for deferring register dump work to separate thread
- * @dbgbus_dpu: debug bus structure for the dpu
- * @dbgbus_vbif_rt: debug bus structure for the realtime vbif
- */
-static struct dpu_dbg_base {
-	struct list_head reg_base_list;
-	struct device *dev;
-
-	struct work_struct dump_work;
-
-	struct dpu_dbg_dpu_debug_bus dbgbus_dpu;
-	struct dpu_dbg_vbif_debug_bus dbgbus_vbif_rt;
-} dpu_dbg_base;
-
-static void _dpu_debug_bus_xbar_dump(void __iomem *mem_base,
-		struct dpu_debug_bus_entry *entry, u32 val)
-{
-	dev_err(dpu_dbg_base.dev, "xbar 0x%x %d %d 0x%x\n",
-			entry->wr_addr, entry->block_id, entry->test_id, val);
-}
-
-static void _dpu_debug_bus_lm_dump(void __iomem *mem_base,
-		struct dpu_debug_bus_entry *entry, u32 val)
-{
-	if (!(val & 0xFFF000))
-		return;
-
-	dev_err(dpu_dbg_base.dev, "lm 0x%x %d %d 0x%x\n",
-			entry->wr_addr, entry->block_id, entry->test_id, val);
-}
-
-static void _dpu_debug_bus_ppb0_dump(void __iomem *mem_base,
-		struct dpu_debug_bus_entry *entry, u32 val)
-{
-	if (!(val & BIT(15)))
-		return;
-
-	dev_err(dpu_dbg_base.dev, "ppb0 0x%x %d %d 0x%x\n",
-			entry->wr_addr, entry->block_id, entry->test_id, val);
-}
-
-static void _dpu_debug_bus_ppb1_dump(void __iomem *mem_base,
-		struct dpu_debug_bus_entry *entry, u32 val)
-{
-	if (!(val & BIT(15)))
-		return;
-
-	dev_err(dpu_dbg_base.dev, "ppb1 0x%x %d %d 0x%x\n",
-			entry->wr_addr, entry->block_id, entry->test_id, val);
-}
-
-static struct dpu_debug_bus_entry dbg_bus_dpu_8998[] = {
-
-	/* Unpack 0 sspp 0*/
-	{ DBGBUS_SSPP0, 50, 2 },
-	{ DBGBUS_SSPP0, 60, 2 },
-	{ DBGBUS_SSPP0, 70, 2 },
-	{ DBGBUS_SSPP0, 85, 2 },
-
-	/* Upack 0 sspp 1*/
-	{ DBGBUS_SSPP1, 50, 2 },
-	{ DBGBUS_SSPP1, 60, 2 },
-	{ DBGBUS_SSPP1, 70, 2 },
-	{ DBGBUS_SSPP1, 85, 2 },
-
-	/* scheduler */
-	{ DBGBUS_DSPP, 130, 0 },
-	{ DBGBUS_DSPP, 130, 1 },
-	{ DBGBUS_DSPP, 130, 2 },
-	{ DBGBUS_DSPP, 130, 3 },
-	{ DBGBUS_DSPP, 130, 4 },
-	{ DBGBUS_DSPP, 130, 5 },
-
-	/* qseed */
-	{ DBGBUS_SSPP0, 6, 0},
-	{ DBGBUS_SSPP0, 6, 1},
-	{ DBGBUS_SSPP0, 26, 0},
-	{ DBGBUS_SSPP0, 26, 1},
-	{ DBGBUS_SSPP1, 6, 0},
-	{ DBGBUS_SSPP1, 6, 1},
-	{ DBGBUS_SSPP1, 26, 0},
-	{ DBGBUS_SSPP1, 26, 1},
-
-	/* scale */
-	{ DBGBUS_SSPP0, 16, 0},
-	{ DBGBUS_SSPP0, 16, 1},
-	{ DBGBUS_SSPP0, 36, 0},
-	{ DBGBUS_SSPP0, 36, 1},
-	{ DBGBUS_SSPP1, 16, 0},
-	{ DBGBUS_SSPP1, 16, 1},
-	{ DBGBUS_SSPP1, 36, 0},
-	{ DBGBUS_SSPP1, 36, 1},
-
-	/* fetch sspp0 */
-
-	/* vig 0 */
-	{ DBGBUS_SSPP0, 0, 0 },
-	{ DBGBUS_SSPP0, 0, 1 },
-	{ DBGBUS_SSPP0, 0, 2 },
-	{ DBGBUS_SSPP0, 0, 3 },
-	{ DBGBUS_SSPP0, 0, 4 },
-	{ DBGBUS_SSPP0, 0, 5 },
-	{ DBGBUS_SSPP0, 0, 6 },
-	{ DBGBUS_SSPP0, 0, 7 },
-
-	{ DBGBUS_SSPP0, 1, 0 },
-	{ DBGBUS_SSPP0, 1, 1 },
-	{ DBGBUS_SSPP0, 1, 2 },
-	{ DBGBUS_SSPP0, 1, 3 },
-	{ DBGBUS_SSPP0, 1, 4 },
-	{ DBGBUS_SSPP0, 1, 5 },
-	{ DBGBUS_SSPP0, 1, 6 },
-	{ DBGBUS_SSPP0, 1, 7 },
-
-	{ DBGBUS_SSPP0, 2, 0 },
-	{ DBGBUS_SSPP0, 2, 1 },
-	{ DBGBUS_SSPP0, 2, 2 },
-	{ DBGBUS_SSPP0, 2, 3 },
-	{ DBGBUS_SSPP0, 2, 4 },
-	{ DBGBUS_SSPP0, 2, 5 },
-	{ DBGBUS_SSPP0, 2, 6 },
-	{ DBGBUS_SSPP0, 2, 7 },
-
-	{ DBGBUS_SSPP0, 4, 0 },
-	{ DBGBUS_SSPP0, 4, 1 },
-	{ DBGBUS_SSPP0, 4, 2 },
-	{ DBGBUS_SSPP0, 4, 3 },
-	{ DBGBUS_SSPP0, 4, 4 },
-	{ DBGBUS_SSPP0, 4, 5 },
-	{ DBGBUS_SSPP0, 4, 6 },
-	{ DBGBUS_SSPP0, 4, 7 },
-
-	{ DBGBUS_SSPP0, 5, 0 },
-	{ DBGBUS_SSPP0, 5, 1 },
-	{ DBGBUS_SSPP0, 5, 2 },
-	{ DBGBUS_SSPP0, 5, 3 },
-	{ DBGBUS_SSPP0, 5, 4 },
-	{ DBGBUS_SSPP0, 5, 5 },
-	{ DBGBUS_SSPP0, 5, 6 },
-	{ DBGBUS_SSPP0, 5, 7 },
-
-	/* vig 2 */
-	{ DBGBUS_SSPP0, 20, 0 },
-	{ DBGBUS_SSPP0, 20, 1 },
-	{ DBGBUS_SSPP0, 20, 2 },
-	{ DBGBUS_SSPP0, 20, 3 },
-	{ DBGBUS_SSPP0, 20, 4 },
-	{ DBGBUS_SSPP0, 20, 5 },
-	{ DBGBUS_SSPP0, 20, 6 },
-	{ DBGBUS_SSPP0, 20, 7 },
-
-	{ DBGBUS_SSPP0, 21, 0 },
-	{ DBGBUS_SSPP0, 21, 1 },
-	{ DBGBUS_SSPP0, 21, 2 },
-	{ DBGBUS_SSPP0, 21, 3 },
-	{ DBGBUS_SSPP0, 21, 4 },
-	{ DBGBUS_SSPP0, 21, 5 },
-	{ DBGBUS_SSPP0, 21, 6 },
-	{ DBGBUS_SSPP0, 21, 7 },
-
-	{ DBGBUS_SSPP0, 22, 0 },
-	{ DBGBUS_SSPP0, 22, 1 },
-	{ DBGBUS_SSPP0, 22, 2 },
-	{ DBGBUS_SSPP0, 22, 3 },
-	{ DBGBUS_SSPP0, 22, 4 },
-	{ DBGBUS_SSPP0, 22, 5 },
-	{ DBGBUS_SSPP0, 22, 6 },
-	{ DBGBUS_SSPP0, 22, 7 },
-
-	{ DBGBUS_SSPP0, 24, 0 },
-	{ DBGBUS_SSPP0, 24, 1 },
-	{ DBGBUS_SSPP0, 24, 2 },
-	{ DBGBUS_SSPP0, 24, 3 },
-	{ DBGBUS_SSPP0, 24, 4 },
-	{ DBGBUS_SSPP0, 24, 5 },
-	{ DBGBUS_SSPP0, 24, 6 },
-	{ DBGBUS_SSPP0, 24, 7 },
-
-	{ DBGBUS_SSPP0, 25, 0 },
-	{ DBGBUS_SSPP0, 25, 1 },
-	{ DBGBUS_SSPP0, 25, 2 },
-	{ DBGBUS_SSPP0, 25, 3 },
-	{ DBGBUS_SSPP0, 25, 4 },
-	{ DBGBUS_SSPP0, 25, 5 },
-	{ DBGBUS_SSPP0, 25, 6 },
-	{ DBGBUS_SSPP0, 25, 7 },
-
-	/* dma 2 */
-	{ DBGBUS_SSPP0, 30, 0 },
-	{ DBGBUS_SSPP0, 30, 1 },
-	{ DBGBUS_SSPP0, 30, 2 },
-	{ DBGBUS_SSPP0, 30, 3 },
-	{ DBGBUS_SSPP0, 30, 4 },
-	{ DBGBUS_SSPP0, 30, 5 },
-	{ DBGBUS_SSPP0, 30, 6 },
-	{ DBGBUS_SSPP0, 30, 7 },
-
-	{ DBGBUS_SSPP0, 31, 0 },
-	{ DBGBUS_SSPP0, 31, 1 },
-	{ DBGBUS_SSPP0, 31, 2 },
-	{ DBGBUS_SSPP0, 31, 3 },
-	{ DBGBUS_SSPP0, 31, 4 },
-	{ DBGBUS_SSPP0, 31, 5 },
-	{ DBGBUS_SSPP0, 31, 6 },
-	{ DBGBUS_SSPP0, 31, 7 },
-
-	{ DBGBUS_SSPP0, 32, 0 },
-	{ DBGBUS_SSPP0, 32, 1 },
-	{ DBGBUS_SSPP0, 32, 2 },
-	{ DBGBUS_SSPP0, 32, 3 },
-	{ DBGBUS_SSPP0, 32, 4 },
-	{ DBGBUS_SSPP0, 32, 5 },
-	{ DBGBUS_SSPP0, 32, 6 },
-	{ DBGBUS_SSPP0, 32, 7 },
-
-	{ DBGBUS_SSPP0, 33, 0 },
-	{ DBGBUS_SSPP0, 33, 1 },
-	{ DBGBUS_SSPP0, 33, 2 },
-	{ DBGBUS_SSPP0, 33, 3 },
-	{ DBGBUS_SSPP0, 33, 4 },
-	{ DBGBUS_SSPP0, 33, 5 },
-	{ DBGBUS_SSPP0, 33, 6 },
-	{ DBGBUS_SSPP0, 33, 7 },
-
-	{ DBGBUS_SSPP0, 34, 0 },
-	{ DBGBUS_SSPP0, 34, 1 },
-	{ DBGBUS_SSPP0, 34, 2 },
-	{ DBGBUS_SSPP0, 34, 3 },
-	{ DBGBUS_SSPP0, 34, 4 },
-	{ DBGBUS_SSPP0, 34, 5 },
-	{ DBGBUS_SSPP0, 34, 6 },
-	{ DBGBUS_SSPP0, 34, 7 },
-
-	{ DBGBUS_SSPP0, 35, 0 },
-	{ DBGBUS_SSPP0, 35, 1 },
-	{ DBGBUS_SSPP0, 35, 2 },
-	{ DBGBUS_SSPP0, 35, 3 },
-
-	/* dma 0 */
-	{ DBGBUS_SSPP0, 40, 0 },
-	{ DBGBUS_SSPP0, 40, 1 },
-	{ DBGBUS_SSPP0, 40, 2 },
-	{ DBGBUS_SSPP0, 40, 3 },
-	{ DBGBUS_SSPP0, 40, 4 },
-	{ DBGBUS_SSPP0, 40, 5 },
-	{ DBGBUS_SSPP0, 40, 6 },
-	{ DBGBUS_SSPP0, 40, 7 },
-
-	{ DBGBUS_SSPP0, 41, 0 },
-	{ DBGBUS_SSPP0, 41, 1 },
-	{ DBGBUS_SSPP0, 41, 2 },
-	{ DBGBUS_SSPP0, 41, 3 },
-	{ DBGBUS_SSPP0, 41, 4 },
-	{ DBGBUS_SSPP0, 41, 5 },
-	{ DBGBUS_SSPP0, 41, 6 },
-	{ DBGBUS_SSPP0, 41, 7 },
-
-	{ DBGBUS_SSPP0, 42, 0 },
-	{ DBGBUS_SSPP0, 42, 1 },
-	{ DBGBUS_SSPP0, 42, 2 },
-	{ DBGBUS_SSPP0, 42, 3 },
-	{ DBGBUS_SSPP0, 42, 4 },
-	{ DBGBUS_SSPP0, 42, 5 },
-	{ DBGBUS_SSPP0, 42, 6 },
-	{ DBGBUS_SSPP0, 42, 7 },
-
-	{ DBGBUS_SSPP0, 44, 0 },
-	{ DBGBUS_SSPP0, 44, 1 },
-	{ DBGBUS_SSPP0, 44, 2 },
-	{ DBGBUS_SSPP0, 44, 3 },
-	{ DBGBUS_SSPP0, 44, 4 },
-	{ DBGBUS_SSPP0, 44, 5 },
-	{ DBGBUS_SSPP0, 44, 6 },
-	{ DBGBUS_SSPP0, 44, 7 },
-
-	{ DBGBUS_SSPP0, 45, 0 },
-	{ DBGBUS_SSPP0, 45, 1 },
-	{ DBGBUS_SSPP0, 45, 2 },
-	{ DBGBUS_SSPP0, 45, 3 },
-	{ DBGBUS_SSPP0, 45, 4 },
-	{ DBGBUS_SSPP0, 45, 5 },
-	{ DBGBUS_SSPP0, 45, 6 },
-	{ DBGBUS_SSPP0, 45, 7 },
-
-	/* fetch sspp1 */
-	/* vig 1 */
-	{ DBGBUS_SSPP1, 0, 0 },
-	{ DBGBUS_SSPP1, 0, 1 },
-	{ DBGBUS_SSPP1, 0, 2 },
-	{ DBGBUS_SSPP1, 0, 3 },
-	{ DBGBUS_SSPP1, 0, 4 },
-	{ DBGBUS_SSPP1, 0, 5 },
-	{ DBGBUS_SSPP1, 0, 6 },
-	{ DBGBUS_SSPP1, 0, 7 },
-
-	{ DBGBUS_SSPP1, 1, 0 },
-	{ DBGBUS_SSPP1, 1, 1 },
-	{ DBGBUS_SSPP1, 1, 2 },
-	{ DBGBUS_SSPP1, 1, 3 },
-	{ DBGBUS_SSPP1, 1, 4 },
-	{ DBGBUS_SSPP1, 1, 5 },
-	{ DBGBUS_SSPP1, 1, 6 },
-	{ DBGBUS_SSPP1, 1, 7 },
-
-	{ DBGBUS_SSPP1, 2, 0 },
-	{ DBGBUS_SSPP1, 2, 1 },
-	{ DBGBUS_SSPP1, 2, 2 },
-	{ DBGBUS_SSPP1, 2, 3 },
-	{ DBGBUS_SSPP1, 2, 4 },
-	{ DBGBUS_SSPP1, 2, 5 },
-	{ DBGBUS_SSPP1, 2, 6 },
-	{ DBGBUS_SSPP1, 2, 7 },
-
-	{ DBGBUS_SSPP1, 4, 0 },
-	{ DBGBUS_SSPP1, 4, 1 },
-	{ DBGBUS_SSPP1, 4, 2 },
-	{ DBGBUS_SSPP1, 4, 3 },
-	{ DBGBUS_SSPP1, 4, 4 },
-	{ DBGBUS_SSPP1, 4, 5 },
-	{ DBGBUS_SSPP1, 4, 6 },
-	{ DBGBUS_SSPP1, 4, 7 },
-
-	{ DBGBUS_SSPP1, 5, 0 },
-	{ DBGBUS_SSPP1, 5, 1 },
-	{ DBGBUS_SSPP1, 5, 2 },
-	{ DBGBUS_SSPP1, 5, 3 },
-	{ DBGBUS_SSPP1, 5, 4 },
-	{ DBGBUS_SSPP1, 5, 5 },
-	{ DBGBUS_SSPP1, 5, 6 },
-	{ DBGBUS_SSPP1, 5, 7 },
-
-	/* vig 3 */
-	{ DBGBUS_SSPP1, 20, 0 },
-	{ DBGBUS_SSPP1, 20, 1 },
-	{ DBGBUS_SSPP1, 20, 2 },
-	{ DBGBUS_SSPP1, 20, 3 },
-	{ DBGBUS_SSPP1, 20, 4 },
-	{ DBGBUS_SSPP1, 20, 5 },
-	{ DBGBUS_SSPP1, 20, 6 },
-	{ DBGBUS_SSPP1, 20, 7 },
-
-	{ DBGBUS_SSPP1, 21, 0 },
-	{ DBGBUS_SSPP1, 21, 1 },
-	{ DBGBUS_SSPP1, 21, 2 },
-	{ DBGBUS_SSPP1, 21, 3 },
-	{ DBGBUS_SSPP1, 21, 4 },
-	{ DBGBUS_SSPP1, 21, 5 },
-	{ DBGBUS_SSPP1, 21, 6 },
-	{ DBGBUS_SSPP1, 21, 7 },
-
-	{ DBGBUS_SSPP1, 22, 0 },
-	{ DBGBUS_SSPP1, 22, 1 },
-	{ DBGBUS_SSPP1, 22, 2 },
-	{ DBGBUS_SSPP1, 22, 3 },
-	{ DBGBUS_SSPP1, 22, 4 },
-	{ DBGBUS_SSPP1, 22, 5 },
-	{ DBGBUS_SSPP1, 22, 6 },
-	{ DBGBUS_SSPP1, 22, 7 },
-
-	{ DBGBUS_SSPP1, 24, 0 },
-	{ DBGBUS_SSPP1, 24, 1 },
-	{ DBGBUS_SSPP1, 24, 2 },
-	{ DBGBUS_SSPP1, 24, 3 },
-	{ DBGBUS_SSPP1, 24, 4 },
-	{ DBGBUS_SSPP1, 24, 5 },
-	{ DBGBUS_SSPP1, 24, 6 },
-	{ DBGBUS_SSPP1, 24, 7 },
-
-	{ DBGBUS_SSPP1, 25, 0 },
-	{ DBGBUS_SSPP1, 25, 1 },
-	{ DBGBUS_SSPP1, 25, 2 },
-	{ DBGBUS_SSPP1, 25, 3 },
-	{ DBGBUS_SSPP1, 25, 4 },
-	{ DBGBUS_SSPP1, 25, 5 },
-	{ DBGBUS_SSPP1, 25, 6 },
-	{ DBGBUS_SSPP1, 25, 7 },
-
-	/* dma 3 */
-	{ DBGBUS_SSPP1, 30, 0 },
-	{ DBGBUS_SSPP1, 30, 1 },
-	{ DBGBUS_SSPP1, 30, 2 },
-	{ DBGBUS_SSPP1, 30, 3 },
-	{ DBGBUS_SSPP1, 30, 4 },
-	{ DBGBUS_SSPP1, 30, 5 },
-	{ DBGBUS_SSPP1, 30, 6 },
-	{ DBGBUS_SSPP1, 30, 7 },
-
-	{ DBGBUS_SSPP1, 31, 0 },
-	{ DBGBUS_SSPP1, 31, 1 },
-	{ DBGBUS_SSPP1, 31, 2 },
-	{ DBGBUS_SSPP1, 31, 3 },
-	{ DBGBUS_SSPP1, 31, 4 },
-	{ DBGBUS_SSPP1, 31, 5 },
-	{ DBGBUS_SSPP1, 31, 6 },
-	{ DBGBUS_SSPP1, 31, 7 },
-
-	{ DBGBUS_SSPP1, 32, 0 },
-	{ DBGBUS_SSPP1, 32, 1 },
-	{ DBGBUS_SSPP1, 32, 2 },
-	{ DBGBUS_SSPP1, 32, 3 },
-	{ DBGBUS_SSPP1, 32, 4 },
-	{ DBGBUS_SSPP1, 32, 5 },
-	{ DBGBUS_SSPP1, 32, 6 },
-	{ DBGBUS_SSPP1, 32, 7 },
-
-	{ DBGBUS_SSPP1, 33, 0 },
-	{ DBGBUS_SSPP1, 33, 1 },
-	{ DBGBUS_SSPP1, 33, 2 },
-	{ DBGBUS_SSPP1, 33, 3 },
-	{ DBGBUS_SSPP1, 33, 4 },
-	{ DBGBUS_SSPP1, 33, 5 },
-	{ DBGBUS_SSPP1, 33, 6 },
-	{ DBGBUS_SSPP1, 33, 7 },
-
-	{ DBGBUS_SSPP1, 34, 0 },
-	{ DBGBUS_SSPP1, 34, 1 },
-	{ DBGBUS_SSPP1, 34, 2 },
-	{ DBGBUS_SSPP1, 34, 3 },
-	{ DBGBUS_SSPP1, 34, 4 },
-	{ DBGBUS_SSPP1, 34, 5 },
-	{ DBGBUS_SSPP1, 34, 6 },
-	{ DBGBUS_SSPP1, 34, 7 },
-
-	{ DBGBUS_SSPP1, 35, 0 },
-	{ DBGBUS_SSPP1, 35, 1 },
-	{ DBGBUS_SSPP1, 35, 2 },
-
-	/* dma 1 */
-	{ DBGBUS_SSPP1, 40, 0 },
-	{ DBGBUS_SSPP1, 40, 1 },
-	{ DBGBUS_SSPP1, 40, 2 },
-	{ DBGBUS_SSPP1, 40, 3 },
-	{ DBGBUS_SSPP1, 40, 4 },
-	{ DBGBUS_SSPP1, 40, 5 },
-	{ DBGBUS_SSPP1, 40, 6 },
-	{ DBGBUS_SSPP1, 40, 7 },
-
-	{ DBGBUS_SSPP1, 41, 0 },
-	{ DBGBUS_SSPP1, 41, 1 },
-	{ DBGBUS_SSPP1, 41, 2 },
-	{ DBGBUS_SSPP1, 41, 3 },
-	{ DBGBUS_SSPP1, 41, 4 },
-	{ DBGBUS_SSPP1, 41, 5 },
-	{ DBGBUS_SSPP1, 41, 6 },
-	{ DBGBUS_SSPP1, 41, 7 },
-
-	{ DBGBUS_SSPP1, 42, 0 },
-	{ DBGBUS_SSPP1, 42, 1 },
-	{ DBGBUS_SSPP1, 42, 2 },
-	{ DBGBUS_SSPP1, 42, 3 },
-	{ DBGBUS_SSPP1, 42, 4 },
-	{ DBGBUS_SSPP1, 42, 5 },
-	{ DBGBUS_SSPP1, 42, 6 },
-	{ DBGBUS_SSPP1, 42, 7 },
-
-	{ DBGBUS_SSPP1, 44, 0 },
-	{ DBGBUS_SSPP1, 44, 1 },
-	{ DBGBUS_SSPP1, 44, 2 },
-	{ DBGBUS_SSPP1, 44, 3 },
-	{ DBGBUS_SSPP1, 44, 4 },
-	{ DBGBUS_SSPP1, 44, 5 },
-	{ DBGBUS_SSPP1, 44, 6 },
-	{ DBGBUS_SSPP1, 44, 7 },
-
-	{ DBGBUS_SSPP1, 45, 0 },
-	{ DBGBUS_SSPP1, 45, 1 },
-	{ DBGBUS_SSPP1, 45, 2 },
-	{ DBGBUS_SSPP1, 45, 3 },
-	{ DBGBUS_SSPP1, 45, 4 },
-	{ DBGBUS_SSPP1, 45, 5 },
-	{ DBGBUS_SSPP1, 45, 6 },
-	{ DBGBUS_SSPP1, 45, 7 },
-
-	/* cursor 1 */
-	{ DBGBUS_SSPP1, 80, 0 },
-	{ DBGBUS_SSPP1, 80, 1 },
-	{ DBGBUS_SSPP1, 80, 2 },
-	{ DBGBUS_SSPP1, 80, 3 },
-	{ DBGBUS_SSPP1, 80, 4 },
-	{ DBGBUS_SSPP1, 80, 5 },
-	{ DBGBUS_SSPP1, 80, 6 },
-	{ DBGBUS_SSPP1, 80, 7 },
-
-	{ DBGBUS_SSPP1, 81, 0 },
-	{ DBGBUS_SSPP1, 81, 1 },
-	{ DBGBUS_SSPP1, 81, 2 },
-	{ DBGBUS_SSPP1, 81, 3 },
-	{ DBGBUS_SSPP1, 81, 4 },
-	{ DBGBUS_SSPP1, 81, 5 },
-	{ DBGBUS_SSPP1, 81, 6 },
-	{ DBGBUS_SSPP1, 81, 7 },
-
-	{ DBGBUS_SSPP1, 82, 0 },
-	{ DBGBUS_SSPP1, 82, 1 },
-	{ DBGBUS_SSPP1, 82, 2 },
-	{ DBGBUS_SSPP1, 82, 3 },
-	{ DBGBUS_SSPP1, 82, 4 },
-	{ DBGBUS_SSPP1, 82, 5 },
-	{ DBGBUS_SSPP1, 82, 6 },
-	{ DBGBUS_SSPP1, 82, 7 },
-
-	{ DBGBUS_SSPP1, 83, 0 },
-	{ DBGBUS_SSPP1, 83, 1 },
-	{ DBGBUS_SSPP1, 83, 2 },
-	{ DBGBUS_SSPP1, 83, 3 },
-	{ DBGBUS_SSPP1, 83, 4 },
-	{ DBGBUS_SSPP1, 83, 5 },
-	{ DBGBUS_SSPP1, 83, 6 },
-	{ DBGBUS_SSPP1, 83, 7 },
-
-	{ DBGBUS_SSPP1, 84, 0 },
-	{ DBGBUS_SSPP1, 84, 1 },
-	{ DBGBUS_SSPP1, 84, 2 },
-	{ DBGBUS_SSPP1, 84, 3 },
-	{ DBGBUS_SSPP1, 84, 4 },
-	{ DBGBUS_SSPP1, 84, 5 },
-	{ DBGBUS_SSPP1, 84, 6 },
-	{ DBGBUS_SSPP1, 84, 7 },
-
-	/* dspp */
-	{ DBGBUS_DSPP, 13, 0 },
-	{ DBGBUS_DSPP, 19, 0 },
-	{ DBGBUS_DSPP, 14, 0 },
-	{ DBGBUS_DSPP, 14, 1 },
-	{ DBGBUS_DSPP, 14, 3 },
-	{ DBGBUS_DSPP, 20, 0 },
-	{ DBGBUS_DSPP, 20, 1 },
-	{ DBGBUS_DSPP, 20, 3 },
-
-	/* ppb_0 */
-	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
-	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
-	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
-	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
-
-	/* ppb_1 */
-	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
-	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
-	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
-	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
-
-	/* lm_lut */
-	{ DBGBUS_DSPP, 109, 0 },
-	{ DBGBUS_DSPP, 105, 0 },
-	{ DBGBUS_DSPP, 103, 0 },
-
-	/* tear-check */
-	{ DBGBUS_PERIPH, 63, 0 },
-	{ DBGBUS_PERIPH, 64, 0 },
-	{ DBGBUS_PERIPH, 65, 0 },
-	{ DBGBUS_PERIPH, 73, 0 },
-	{ DBGBUS_PERIPH, 74, 0 },
-
-	/* crossbar */
-	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
-
-	/* rotator */
-	{ DBGBUS_DSPP, 9, 0},
-
-	/* blend */
-	/* LM0 */
-	{ DBGBUS_DSPP, 63, 0},
-	{ DBGBUS_DSPP, 63, 1},
-	{ DBGBUS_DSPP, 63, 2},
-	{ DBGBUS_DSPP, 63, 3},
-	{ DBGBUS_DSPP, 63, 4},
-	{ DBGBUS_DSPP, 63, 5},
-	{ DBGBUS_DSPP, 63, 6},
-	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 64, 0},
-	{ DBGBUS_DSPP, 64, 1},
-	{ DBGBUS_DSPP, 64, 2},
-	{ DBGBUS_DSPP, 64, 3},
-	{ DBGBUS_DSPP, 64, 4},
-	{ DBGBUS_DSPP, 64, 5},
-	{ DBGBUS_DSPP, 64, 6},
-	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 65, 0},
-	{ DBGBUS_DSPP, 65, 1},
-	{ DBGBUS_DSPP, 65, 2},
-	{ DBGBUS_DSPP, 65, 3},
-	{ DBGBUS_DSPP, 65, 4},
-	{ DBGBUS_DSPP, 65, 5},
-	{ DBGBUS_DSPP, 65, 6},
-	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 66, 0},
-	{ DBGBUS_DSPP, 66, 1},
-	{ DBGBUS_DSPP, 66, 2},
-	{ DBGBUS_DSPP, 66, 3},
-	{ DBGBUS_DSPP, 66, 4},
-	{ DBGBUS_DSPP, 66, 5},
-	{ DBGBUS_DSPP, 66, 6},
-	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 67, 0},
-	{ DBGBUS_DSPP, 67, 1},
-	{ DBGBUS_DSPP, 67, 2},
-	{ DBGBUS_DSPP, 67, 3},
-	{ DBGBUS_DSPP, 67, 4},
-	{ DBGBUS_DSPP, 67, 5},
-	{ DBGBUS_DSPP, 67, 6},
-	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 68, 0},
-	{ DBGBUS_DSPP, 68, 1},
-	{ DBGBUS_DSPP, 68, 2},
-	{ DBGBUS_DSPP, 68, 3},
-	{ DBGBUS_DSPP, 68, 4},
-	{ DBGBUS_DSPP, 68, 5},
-	{ DBGBUS_DSPP, 68, 6},
-	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 69, 0},
-	{ DBGBUS_DSPP, 69, 1},
-	{ DBGBUS_DSPP, 69, 2},
-	{ DBGBUS_DSPP, 69, 3},
-	{ DBGBUS_DSPP, 69, 4},
-	{ DBGBUS_DSPP, 69, 5},
-	{ DBGBUS_DSPP, 69, 6},
-	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
-
-	/* LM1 */
-	{ DBGBUS_DSPP, 70, 0},
-	{ DBGBUS_DSPP, 70, 1},
-	{ DBGBUS_DSPP, 70, 2},
-	{ DBGBUS_DSPP, 70, 3},
-	{ DBGBUS_DSPP, 70, 4},
-	{ DBGBUS_DSPP, 70, 5},
-	{ DBGBUS_DSPP, 70, 6},
-	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 71, 0},
-	{ DBGBUS_DSPP, 71, 1},
-	{ DBGBUS_DSPP, 71, 2},
-	{ DBGBUS_DSPP, 71, 3},
-	{ DBGBUS_DSPP, 71, 4},
-	{ DBGBUS_DSPP, 71, 5},
-	{ DBGBUS_DSPP, 71, 6},
-	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 72, 0},
-	{ DBGBUS_DSPP, 72, 1},
-	{ DBGBUS_DSPP, 72, 2},
-	{ DBGBUS_DSPP, 72, 3},
-	{ DBGBUS_DSPP, 72, 4},
-	{ DBGBUS_DSPP, 72, 5},
-	{ DBGBUS_DSPP, 72, 6},
-	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 73, 0},
-	{ DBGBUS_DSPP, 73, 1},
-	{ DBGBUS_DSPP, 73, 2},
-	{ DBGBUS_DSPP, 73, 3},
-	{ DBGBUS_DSPP, 73, 4},
-	{ DBGBUS_DSPP, 73, 5},
-	{ DBGBUS_DSPP, 73, 6},
-	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 74, 0},
-	{ DBGBUS_DSPP, 74, 1},
-	{ DBGBUS_DSPP, 74, 2},
-	{ DBGBUS_DSPP, 74, 3},
-	{ DBGBUS_DSPP, 74, 4},
-	{ DBGBUS_DSPP, 74, 5},
-	{ DBGBUS_DSPP, 74, 6},
-	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 75, 0},
-	{ DBGBUS_DSPP, 75, 1},
-	{ DBGBUS_DSPP, 75, 2},
-	{ DBGBUS_DSPP, 75, 3},
-	{ DBGBUS_DSPP, 75, 4},
-	{ DBGBUS_DSPP, 75, 5},
-	{ DBGBUS_DSPP, 75, 6},
-	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 76, 0},
-	{ DBGBUS_DSPP, 76, 1},
-	{ DBGBUS_DSPP, 76, 2},
-	{ DBGBUS_DSPP, 76, 3},
-	{ DBGBUS_DSPP, 76, 4},
-	{ DBGBUS_DSPP, 76, 5},
-	{ DBGBUS_DSPP, 76, 6},
-	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
-
-	/* LM2 */
-	{ DBGBUS_DSPP, 77, 0},
-	{ DBGBUS_DSPP, 77, 1},
-	{ DBGBUS_DSPP, 77, 2},
-	{ DBGBUS_DSPP, 77, 3},
-	{ DBGBUS_DSPP, 77, 4},
-	{ DBGBUS_DSPP, 77, 5},
-	{ DBGBUS_DSPP, 77, 6},
-	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 78, 0},
-	{ DBGBUS_DSPP, 78, 1},
-	{ DBGBUS_DSPP, 78, 2},
-	{ DBGBUS_DSPP, 78, 3},
-	{ DBGBUS_DSPP, 78, 4},
-	{ DBGBUS_DSPP, 78, 5},
-	{ DBGBUS_DSPP, 78, 6},
-	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 79, 0},
-	{ DBGBUS_DSPP, 79, 1},
-	{ DBGBUS_DSPP, 79, 2},
-	{ DBGBUS_DSPP, 79, 3},
-	{ DBGBUS_DSPP, 79, 4},
-	{ DBGBUS_DSPP, 79, 5},
-	{ DBGBUS_DSPP, 79, 6},
-	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 80, 0},
-	{ DBGBUS_DSPP, 80, 1},
-	{ DBGBUS_DSPP, 80, 2},
-	{ DBGBUS_DSPP, 80, 3},
-	{ DBGBUS_DSPP, 80, 4},
-	{ DBGBUS_DSPP, 80, 5},
-	{ DBGBUS_DSPP, 80, 6},
-	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 81, 0},
-	{ DBGBUS_DSPP, 81, 1},
-	{ DBGBUS_DSPP, 81, 2},
-	{ DBGBUS_DSPP, 81, 3},
-	{ DBGBUS_DSPP, 81, 4},
-	{ DBGBUS_DSPP, 81, 5},
-	{ DBGBUS_DSPP, 81, 6},
-	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 82, 0},
-	{ DBGBUS_DSPP, 82, 1},
-	{ DBGBUS_DSPP, 82, 2},
-	{ DBGBUS_DSPP, 82, 3},
-	{ DBGBUS_DSPP, 82, 4},
-	{ DBGBUS_DSPP, 82, 5},
-	{ DBGBUS_DSPP, 82, 6},
-	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 83, 0},
-	{ DBGBUS_DSPP, 83, 1},
-	{ DBGBUS_DSPP, 83, 2},
-	{ DBGBUS_DSPP, 83, 3},
-	{ DBGBUS_DSPP, 83, 4},
-	{ DBGBUS_DSPP, 83, 5},
-	{ DBGBUS_DSPP, 83, 6},
-	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
-
-	/* csc */
-	{ DBGBUS_SSPP0, 7, 0},
-	{ DBGBUS_SSPP0, 7, 1},
-	{ DBGBUS_SSPP0, 27, 0},
-	{ DBGBUS_SSPP0, 27, 1},
-	{ DBGBUS_SSPP1, 7, 0},
-	{ DBGBUS_SSPP1, 7, 1},
-	{ DBGBUS_SSPP1, 27, 0},
-	{ DBGBUS_SSPP1, 27, 1},
-
-	/* pcc */
-	{ DBGBUS_SSPP0, 3,  3},
-	{ DBGBUS_SSPP0, 23, 3},
-	{ DBGBUS_SSPP0, 33, 3},
-	{ DBGBUS_SSPP0, 43, 3},
-	{ DBGBUS_SSPP1, 3,  3},
-	{ DBGBUS_SSPP1, 23, 3},
-	{ DBGBUS_SSPP1, 33, 3},
-	{ DBGBUS_SSPP1, 43, 3},
-
-	/* spa */
-	{ DBGBUS_SSPP0, 8,  0},
-	{ DBGBUS_SSPP0, 28, 0},
-	{ DBGBUS_SSPP1, 8,  0},
-	{ DBGBUS_SSPP1, 28, 0},
-	{ DBGBUS_DSPP, 13, 0},
-	{ DBGBUS_DSPP, 19, 0},
-
-	/* igc */
-	{ DBGBUS_SSPP0, 9,  0},
-	{ DBGBUS_SSPP0, 9,  1},
-	{ DBGBUS_SSPP0, 9,  3},
-	{ DBGBUS_SSPP0, 29, 0},
-	{ DBGBUS_SSPP0, 29, 1},
-	{ DBGBUS_SSPP0, 29, 3},
-	{ DBGBUS_SSPP0, 17, 0},
-	{ DBGBUS_SSPP0, 17, 1},
-	{ DBGBUS_SSPP0, 17, 3},
-	{ DBGBUS_SSPP0, 37, 0},
-	{ DBGBUS_SSPP0, 37, 1},
-	{ DBGBUS_SSPP0, 37, 3},
-	{ DBGBUS_SSPP0, 46, 0},
-	{ DBGBUS_SSPP0, 46, 1},
-	{ DBGBUS_SSPP0, 46, 3},
-
-	{ DBGBUS_SSPP1, 9,  0},
-	{ DBGBUS_SSPP1, 9,  1},
-	{ DBGBUS_SSPP1, 9,  3},
-	{ DBGBUS_SSPP1, 29, 0},
-	{ DBGBUS_SSPP1, 29, 1},
-	{ DBGBUS_SSPP1, 29, 3},
-	{ DBGBUS_SSPP1, 17, 0},
-	{ DBGBUS_SSPP1, 17, 1},
-	{ DBGBUS_SSPP1, 17, 3},
-	{ DBGBUS_SSPP1, 37, 0},
-	{ DBGBUS_SSPP1, 37, 1},
-	{ DBGBUS_SSPP1, 37, 3},
-	{ DBGBUS_SSPP1, 46, 0},
-	{ DBGBUS_SSPP1, 46, 1},
-	{ DBGBUS_SSPP1, 46, 3},
-
-	{ DBGBUS_DSPP, 14, 0},
-	{ DBGBUS_DSPP, 14, 1},
-	{ DBGBUS_DSPP, 14, 3},
-	{ DBGBUS_DSPP, 20, 0},
-	{ DBGBUS_DSPP, 20, 1},
-	{ DBGBUS_DSPP, 20, 3},
-
-	{ DBGBUS_PERIPH, 60, 0},
-};
-
-static struct dpu_debug_bus_entry dbg_bus_dpu_sdm845[] = {
-
-	/* Unpack 0 sspp 0*/
-	{ DBGBUS_SSPP0, 50, 2 },
-	{ DBGBUS_SSPP0, 60, 2 },
-	{ DBGBUS_SSPP0, 70, 2 },
-
-	/* Upack 0 sspp 1*/
-	{ DBGBUS_SSPP1, 50, 2 },
-	{ DBGBUS_SSPP1, 60, 2 },
-	{ DBGBUS_SSPP1, 70, 2 },
-
-	/* scheduler */
-	{ DBGBUS_DSPP, 130, 0 },
-	{ DBGBUS_DSPP, 130, 1 },
-	{ DBGBUS_DSPP, 130, 2 },
-	{ DBGBUS_DSPP, 130, 3 },
-	{ DBGBUS_DSPP, 130, 4 },
-	{ DBGBUS_DSPP, 130, 5 },
-
-	/* qseed */
-	{ DBGBUS_SSPP0, 6, 0},
-	{ DBGBUS_SSPP0, 6, 1},
-	{ DBGBUS_SSPP0, 26, 0},
-	{ DBGBUS_SSPP0, 26, 1},
-	{ DBGBUS_SSPP1, 6, 0},
-	{ DBGBUS_SSPP1, 6, 1},
-	{ DBGBUS_SSPP1, 26, 0},
-	{ DBGBUS_SSPP1, 26, 1},
-
-	/* scale */
-	{ DBGBUS_SSPP0, 16, 0},
-	{ DBGBUS_SSPP0, 16, 1},
-	{ DBGBUS_SSPP0, 36, 0},
-	{ DBGBUS_SSPP0, 36, 1},
-	{ DBGBUS_SSPP1, 16, 0},
-	{ DBGBUS_SSPP1, 16, 1},
-	{ DBGBUS_SSPP1, 36, 0},
-	{ DBGBUS_SSPP1, 36, 1},
-
-	/* fetch sspp0 */
-
-	/* vig 0 */
-	{ DBGBUS_SSPP0, 0, 0 },
-	{ DBGBUS_SSPP0, 0, 1 },
-	{ DBGBUS_SSPP0, 0, 2 },
-	{ DBGBUS_SSPP0, 0, 3 },
-	{ DBGBUS_SSPP0, 0, 4 },
-	{ DBGBUS_SSPP0, 0, 5 },
-	{ DBGBUS_SSPP0, 0, 6 },
-	{ DBGBUS_SSPP0, 0, 7 },
-
-	{ DBGBUS_SSPP0, 1, 0 },
-	{ DBGBUS_SSPP0, 1, 1 },
-	{ DBGBUS_SSPP0, 1, 2 },
-	{ DBGBUS_SSPP0, 1, 3 },
-	{ DBGBUS_SSPP0, 1, 4 },
-	{ DBGBUS_SSPP0, 1, 5 },
-	{ DBGBUS_SSPP0, 1, 6 },
-	{ DBGBUS_SSPP0, 1, 7 },
-
-	{ DBGBUS_SSPP0, 2, 0 },
-	{ DBGBUS_SSPP0, 2, 1 },
-	{ DBGBUS_SSPP0, 2, 2 },
-	{ DBGBUS_SSPP0, 2, 3 },
-	{ DBGBUS_SSPP0, 2, 4 },
-	{ DBGBUS_SSPP0, 2, 5 },
-	{ DBGBUS_SSPP0, 2, 6 },
-	{ DBGBUS_SSPP0, 2, 7 },
-
-	{ DBGBUS_SSPP0, 4, 0 },
-	{ DBGBUS_SSPP0, 4, 1 },
-	{ DBGBUS_SSPP0, 4, 2 },
-	{ DBGBUS_SSPP0, 4, 3 },
-	{ DBGBUS_SSPP0, 4, 4 },
-	{ DBGBUS_SSPP0, 4, 5 },
-	{ DBGBUS_SSPP0, 4, 6 },
-	{ DBGBUS_SSPP0, 4, 7 },
-
-	{ DBGBUS_SSPP0, 5, 0 },
-	{ DBGBUS_SSPP0, 5, 1 },
-	{ DBGBUS_SSPP0, 5, 2 },
-	{ DBGBUS_SSPP0, 5, 3 },
-	{ DBGBUS_SSPP0, 5, 4 },
-	{ DBGBUS_SSPP0, 5, 5 },
-	{ DBGBUS_SSPP0, 5, 6 },
-	{ DBGBUS_SSPP0, 5, 7 },
-
-	/* vig 2 */
-	{ DBGBUS_SSPP0, 20, 0 },
-	{ DBGBUS_SSPP0, 20, 1 },
-	{ DBGBUS_SSPP0, 20, 2 },
-	{ DBGBUS_SSPP0, 20, 3 },
-	{ DBGBUS_SSPP0, 20, 4 },
-	{ DBGBUS_SSPP0, 20, 5 },
-	{ DBGBUS_SSPP0, 20, 6 },
-	{ DBGBUS_SSPP0, 20, 7 },
-
-	{ DBGBUS_SSPP0, 21, 0 },
-	{ DBGBUS_SSPP0, 21, 1 },
-	{ DBGBUS_SSPP0, 21, 2 },
-	{ DBGBUS_SSPP0, 21, 3 },
-	{ DBGBUS_SSPP0, 21, 4 },
-	{ DBGBUS_SSPP0, 21, 5 },
-	{ DBGBUS_SSPP0, 21, 6 },
-	{ DBGBUS_SSPP0, 21, 7 },
-
-	{ DBGBUS_SSPP0, 22, 0 },
-	{ DBGBUS_SSPP0, 22, 1 },
-	{ DBGBUS_SSPP0, 22, 2 },
-	{ DBGBUS_SSPP0, 22, 3 },
-	{ DBGBUS_SSPP0, 22, 4 },
-	{ DBGBUS_SSPP0, 22, 5 },
-	{ DBGBUS_SSPP0, 22, 6 },
-	{ DBGBUS_SSPP0, 22, 7 },
-
-	{ DBGBUS_SSPP0, 24, 0 },
-	{ DBGBUS_SSPP0, 24, 1 },
-	{ DBGBUS_SSPP0, 24, 2 },
-	{ DBGBUS_SSPP0, 24, 3 },
-	{ DBGBUS_SSPP0, 24, 4 },
-	{ DBGBUS_SSPP0, 24, 5 },
-	{ DBGBUS_SSPP0, 24, 6 },
-	{ DBGBUS_SSPP0, 24, 7 },
-
-	{ DBGBUS_SSPP0, 25, 0 },
-	{ DBGBUS_SSPP0, 25, 1 },
-	{ DBGBUS_SSPP0, 25, 2 },
-	{ DBGBUS_SSPP0, 25, 3 },
-	{ DBGBUS_SSPP0, 25, 4 },
-	{ DBGBUS_SSPP0, 25, 5 },
-	{ DBGBUS_SSPP0, 25, 6 },
-	{ DBGBUS_SSPP0, 25, 7 },
-
-	/* dma 2 */
-	{ DBGBUS_SSPP0, 30, 0 },
-	{ DBGBUS_SSPP0, 30, 1 },
-	{ DBGBUS_SSPP0, 30, 2 },
-	{ DBGBUS_SSPP0, 30, 3 },
-	{ DBGBUS_SSPP0, 30, 4 },
-	{ DBGBUS_SSPP0, 30, 5 },
-	{ DBGBUS_SSPP0, 30, 6 },
-	{ DBGBUS_SSPP0, 30, 7 },
-
-	{ DBGBUS_SSPP0, 31, 0 },
-	{ DBGBUS_SSPP0, 31, 1 },
-	{ DBGBUS_SSPP0, 31, 2 },
-	{ DBGBUS_SSPP0, 31, 3 },
-	{ DBGBUS_SSPP0, 31, 4 },
-	{ DBGBUS_SSPP0, 31, 5 },
-	{ DBGBUS_SSPP0, 31, 6 },
-	{ DBGBUS_SSPP0, 31, 7 },
-
-	{ DBGBUS_SSPP0, 32, 0 },
-	{ DBGBUS_SSPP0, 32, 1 },
-	{ DBGBUS_SSPP0, 32, 2 },
-	{ DBGBUS_SSPP0, 32, 3 },
-	{ DBGBUS_SSPP0, 32, 4 },
-	{ DBGBUS_SSPP0, 32, 5 },
-	{ DBGBUS_SSPP0, 32, 6 },
-	{ DBGBUS_SSPP0, 32, 7 },
-
-	{ DBGBUS_SSPP0, 33, 0 },
-	{ DBGBUS_SSPP0, 33, 1 },
-	{ DBGBUS_SSPP0, 33, 2 },
-	{ DBGBUS_SSPP0, 33, 3 },
-	{ DBGBUS_SSPP0, 33, 4 },
-	{ DBGBUS_SSPP0, 33, 5 },
-	{ DBGBUS_SSPP0, 33, 6 },
-	{ DBGBUS_SSPP0, 33, 7 },
-
-	{ DBGBUS_SSPP0, 34, 0 },
-	{ DBGBUS_SSPP0, 34, 1 },
-	{ DBGBUS_SSPP0, 34, 2 },
-	{ DBGBUS_SSPP0, 34, 3 },
-	{ DBGBUS_SSPP0, 34, 4 },
-	{ DBGBUS_SSPP0, 34, 5 },
-	{ DBGBUS_SSPP0, 34, 6 },
-	{ DBGBUS_SSPP0, 34, 7 },
-
-	{ DBGBUS_SSPP0, 35, 0 },
-	{ DBGBUS_SSPP0, 35, 1 },
-	{ DBGBUS_SSPP0, 35, 2 },
-	{ DBGBUS_SSPP0, 35, 3 },
-
-	/* dma 0 */
-	{ DBGBUS_SSPP0, 40, 0 },
-	{ DBGBUS_SSPP0, 40, 1 },
-	{ DBGBUS_SSPP0, 40, 2 },
-	{ DBGBUS_SSPP0, 40, 3 },
-	{ DBGBUS_SSPP0, 40, 4 },
-	{ DBGBUS_SSPP0, 40, 5 },
-	{ DBGBUS_SSPP0, 40, 6 },
-	{ DBGBUS_SSPP0, 40, 7 },
-
-	{ DBGBUS_SSPP0, 41, 0 },
-	{ DBGBUS_SSPP0, 41, 1 },
-	{ DBGBUS_SSPP0, 41, 2 },
-	{ DBGBUS_SSPP0, 41, 3 },
-	{ DBGBUS_SSPP0, 41, 4 },
-	{ DBGBUS_SSPP0, 41, 5 },
-	{ DBGBUS_SSPP0, 41, 6 },
-	{ DBGBUS_SSPP0, 41, 7 },
-
-	{ DBGBUS_SSPP0, 42, 0 },
-	{ DBGBUS_SSPP0, 42, 1 },
-	{ DBGBUS_SSPP0, 42, 2 },
-	{ DBGBUS_SSPP0, 42, 3 },
-	{ DBGBUS_SSPP0, 42, 4 },
-	{ DBGBUS_SSPP0, 42, 5 },
-	{ DBGBUS_SSPP0, 42, 6 },
-	{ DBGBUS_SSPP0, 42, 7 },
-
-	{ DBGBUS_SSPP0, 44, 0 },
-	{ DBGBUS_SSPP0, 44, 1 },
-	{ DBGBUS_SSPP0, 44, 2 },
-	{ DBGBUS_SSPP0, 44, 3 },
-	{ DBGBUS_SSPP0, 44, 4 },
-	{ DBGBUS_SSPP0, 44, 5 },
-	{ DBGBUS_SSPP0, 44, 6 },
-	{ DBGBUS_SSPP0, 44, 7 },
-
-	{ DBGBUS_SSPP0, 45, 0 },
-	{ DBGBUS_SSPP0, 45, 1 },
-	{ DBGBUS_SSPP0, 45, 2 },
-	{ DBGBUS_SSPP0, 45, 3 },
-	{ DBGBUS_SSPP0, 45, 4 },
-	{ DBGBUS_SSPP0, 45, 5 },
-	{ DBGBUS_SSPP0, 45, 6 },
-	{ DBGBUS_SSPP0, 45, 7 },
-
-	/* fetch sspp1 */
-	/* vig 1 */
-	{ DBGBUS_SSPP1, 0, 0 },
-	{ DBGBUS_SSPP1, 0, 1 },
-	{ DBGBUS_SSPP1, 0, 2 },
-	{ DBGBUS_SSPP1, 0, 3 },
-	{ DBGBUS_SSPP1, 0, 4 },
-	{ DBGBUS_SSPP1, 0, 5 },
-	{ DBGBUS_SSPP1, 0, 6 },
-	{ DBGBUS_SSPP1, 0, 7 },
-
-	{ DBGBUS_SSPP1, 1, 0 },
-	{ DBGBUS_SSPP1, 1, 1 },
-	{ DBGBUS_SSPP1, 1, 2 },
-	{ DBGBUS_SSPP1, 1, 3 },
-	{ DBGBUS_SSPP1, 1, 4 },
-	{ DBGBUS_SSPP1, 1, 5 },
-	{ DBGBUS_SSPP1, 1, 6 },
-	{ DBGBUS_SSPP1, 1, 7 },
-
-	{ DBGBUS_SSPP1, 2, 0 },
-	{ DBGBUS_SSPP1, 2, 1 },
-	{ DBGBUS_SSPP1, 2, 2 },
-	{ DBGBUS_SSPP1, 2, 3 },
-	{ DBGBUS_SSPP1, 2, 4 },
-	{ DBGBUS_SSPP1, 2, 5 },
-	{ DBGBUS_SSPP1, 2, 6 },
-	{ DBGBUS_SSPP1, 2, 7 },
-
-	{ DBGBUS_SSPP1, 4, 0 },
-	{ DBGBUS_SSPP1, 4, 1 },
-	{ DBGBUS_SSPP1, 4, 2 },
-	{ DBGBUS_SSPP1, 4, 3 },
-	{ DBGBUS_SSPP1, 4, 4 },
-	{ DBGBUS_SSPP1, 4, 5 },
-	{ DBGBUS_SSPP1, 4, 6 },
-	{ DBGBUS_SSPP1, 4, 7 },
-
-	{ DBGBUS_SSPP1, 5, 0 },
-	{ DBGBUS_SSPP1, 5, 1 },
-	{ DBGBUS_SSPP1, 5, 2 },
-	{ DBGBUS_SSPP1, 5, 3 },
-	{ DBGBUS_SSPP1, 5, 4 },
-	{ DBGBUS_SSPP1, 5, 5 },
-	{ DBGBUS_SSPP1, 5, 6 },
-	{ DBGBUS_SSPP1, 5, 7 },
-
-	/* vig 3 */
-	{ DBGBUS_SSPP1, 20, 0 },
-	{ DBGBUS_SSPP1, 20, 1 },
-	{ DBGBUS_SSPP1, 20, 2 },
-	{ DBGBUS_SSPP1, 20, 3 },
-	{ DBGBUS_SSPP1, 20, 4 },
-	{ DBGBUS_SSPP1, 20, 5 },
-	{ DBGBUS_SSPP1, 20, 6 },
-	{ DBGBUS_SSPP1, 20, 7 },
-
-	{ DBGBUS_SSPP1, 21, 0 },
-	{ DBGBUS_SSPP1, 21, 1 },
-	{ DBGBUS_SSPP1, 21, 2 },
-	{ DBGBUS_SSPP1, 21, 3 },
-	{ DBGBUS_SSPP1, 21, 4 },
-	{ DBGBUS_SSPP1, 21, 5 },
-	{ DBGBUS_SSPP1, 21, 6 },
-	{ DBGBUS_SSPP1, 21, 7 },
-
-	{ DBGBUS_SSPP1, 22, 0 },
-	{ DBGBUS_SSPP1, 22, 1 },
-	{ DBGBUS_SSPP1, 22, 2 },
-	{ DBGBUS_SSPP1, 22, 3 },
-	{ DBGBUS_SSPP1, 22, 4 },
-	{ DBGBUS_SSPP1, 22, 5 },
-	{ DBGBUS_SSPP1, 22, 6 },
-	{ DBGBUS_SSPP1, 22, 7 },
-
-	{ DBGBUS_SSPP1, 24, 0 },
-	{ DBGBUS_SSPP1, 24, 1 },
-	{ DBGBUS_SSPP1, 24, 2 },
-	{ DBGBUS_SSPP1, 24, 3 },
-	{ DBGBUS_SSPP1, 24, 4 },
-	{ DBGBUS_SSPP1, 24, 5 },
-	{ DBGBUS_SSPP1, 24, 6 },
-	{ DBGBUS_SSPP1, 24, 7 },
-
-	{ DBGBUS_SSPP1, 25, 0 },
-	{ DBGBUS_SSPP1, 25, 1 },
-	{ DBGBUS_SSPP1, 25, 2 },
-	{ DBGBUS_SSPP1, 25, 3 },
-	{ DBGBUS_SSPP1, 25, 4 },
-	{ DBGBUS_SSPP1, 25, 5 },
-	{ DBGBUS_SSPP1, 25, 6 },
-	{ DBGBUS_SSPP1, 25, 7 },
-
-	/* dma 3 */
-	{ DBGBUS_SSPP1, 30, 0 },
-	{ DBGBUS_SSPP1, 30, 1 },
-	{ DBGBUS_SSPP1, 30, 2 },
-	{ DBGBUS_SSPP1, 30, 3 },
-	{ DBGBUS_SSPP1, 30, 4 },
-	{ DBGBUS_SSPP1, 30, 5 },
-	{ DBGBUS_SSPP1, 30, 6 },
-	{ DBGBUS_SSPP1, 30, 7 },
-
-	{ DBGBUS_SSPP1, 31, 0 },
-	{ DBGBUS_SSPP1, 31, 1 },
-	{ DBGBUS_SSPP1, 31, 2 },
-	{ DBGBUS_SSPP1, 31, 3 },
-	{ DBGBUS_SSPP1, 31, 4 },
-	{ DBGBUS_SSPP1, 31, 5 },
-	{ DBGBUS_SSPP1, 31, 6 },
-	{ DBGBUS_SSPP1, 31, 7 },
-
-	{ DBGBUS_SSPP1, 32, 0 },
-	{ DBGBUS_SSPP1, 32, 1 },
-	{ DBGBUS_SSPP1, 32, 2 },
-	{ DBGBUS_SSPP1, 32, 3 },
-	{ DBGBUS_SSPP1, 32, 4 },
-	{ DBGBUS_SSPP1, 32, 5 },
-	{ DBGBUS_SSPP1, 32, 6 },
-	{ DBGBUS_SSPP1, 32, 7 },
-
-	{ DBGBUS_SSPP1, 33, 0 },
-	{ DBGBUS_SSPP1, 33, 1 },
-	{ DBGBUS_SSPP1, 33, 2 },
-	{ DBGBUS_SSPP1, 33, 3 },
-	{ DBGBUS_SSPP1, 33, 4 },
-	{ DBGBUS_SSPP1, 33, 5 },
-	{ DBGBUS_SSPP1, 33, 6 },
-	{ DBGBUS_SSPP1, 33, 7 },
-
-	{ DBGBUS_SSPP1, 34, 0 },
-	{ DBGBUS_SSPP1, 34, 1 },
-	{ DBGBUS_SSPP1, 34, 2 },
-	{ DBGBUS_SSPP1, 34, 3 },
-	{ DBGBUS_SSPP1, 34, 4 },
-	{ DBGBUS_SSPP1, 34, 5 },
-	{ DBGBUS_SSPP1, 34, 6 },
-	{ DBGBUS_SSPP1, 34, 7 },
-
-	{ DBGBUS_SSPP1, 35, 0 },
-	{ DBGBUS_SSPP1, 35, 1 },
-	{ DBGBUS_SSPP1, 35, 2 },
-
-	/* dma 1 */
-	{ DBGBUS_SSPP1, 40, 0 },
-	{ DBGBUS_SSPP1, 40, 1 },
-	{ DBGBUS_SSPP1, 40, 2 },
-	{ DBGBUS_SSPP1, 40, 3 },
-	{ DBGBUS_SSPP1, 40, 4 },
-	{ DBGBUS_SSPP1, 40, 5 },
-	{ DBGBUS_SSPP1, 40, 6 },
-	{ DBGBUS_SSPP1, 40, 7 },
-
-	{ DBGBUS_SSPP1, 41, 0 },
-	{ DBGBUS_SSPP1, 41, 1 },
-	{ DBGBUS_SSPP1, 41, 2 },
-	{ DBGBUS_SSPP1, 41, 3 },
-	{ DBGBUS_SSPP1, 41, 4 },
-	{ DBGBUS_SSPP1, 41, 5 },
-	{ DBGBUS_SSPP1, 41, 6 },
-	{ DBGBUS_SSPP1, 41, 7 },
-
-	{ DBGBUS_SSPP1, 42, 0 },
-	{ DBGBUS_SSPP1, 42, 1 },
-	{ DBGBUS_SSPP1, 42, 2 },
-	{ DBGBUS_SSPP1, 42, 3 },
-	{ DBGBUS_SSPP1, 42, 4 },
-	{ DBGBUS_SSPP1, 42, 5 },
-	{ DBGBUS_SSPP1, 42, 6 },
-	{ DBGBUS_SSPP1, 42, 7 },
-
-	{ DBGBUS_SSPP1, 44, 0 },
-	{ DBGBUS_SSPP1, 44, 1 },
-	{ DBGBUS_SSPP1, 44, 2 },
-	{ DBGBUS_SSPP1, 44, 3 },
-	{ DBGBUS_SSPP1, 44, 4 },
-	{ DBGBUS_SSPP1, 44, 5 },
-	{ DBGBUS_SSPP1, 44, 6 },
-	{ DBGBUS_SSPP1, 44, 7 },
-
-	{ DBGBUS_SSPP1, 45, 0 },
-	{ DBGBUS_SSPP1, 45, 1 },
-	{ DBGBUS_SSPP1, 45, 2 },
-	{ DBGBUS_SSPP1, 45, 3 },
-	{ DBGBUS_SSPP1, 45, 4 },
-	{ DBGBUS_SSPP1, 45, 5 },
-	{ DBGBUS_SSPP1, 45, 6 },
-	{ DBGBUS_SSPP1, 45, 7 },
-
-	/* dspp */
-	{ DBGBUS_DSPP, 13, 0 },
-	{ DBGBUS_DSPP, 19, 0 },
-	{ DBGBUS_DSPP, 14, 0 },
-	{ DBGBUS_DSPP, 14, 1 },
-	{ DBGBUS_DSPP, 14, 3 },
-	{ DBGBUS_DSPP, 20, 0 },
-	{ DBGBUS_DSPP, 20, 1 },
-	{ DBGBUS_DSPP, 20, 3 },
-
-	/* ppb_0 */
-	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
-	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
-	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
-	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
-
-	/* ppb_1 */
-	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
-	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
-	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
-	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
-
-	/* lm_lut */
-	{ DBGBUS_DSPP, 109, 0 },
-	{ DBGBUS_DSPP, 105, 0 },
-	{ DBGBUS_DSPP, 103, 0 },
-
-	/* crossbar */
-	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
-
-	/* rotator */
-	{ DBGBUS_DSPP, 9, 0},
-
-	/* blend */
-	/* LM0 */
-	{ DBGBUS_DSPP, 63, 1},
-	{ DBGBUS_DSPP, 63, 2},
-	{ DBGBUS_DSPP, 63, 3},
-	{ DBGBUS_DSPP, 63, 4},
-	{ DBGBUS_DSPP, 63, 5},
-	{ DBGBUS_DSPP, 63, 6},
-	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 64, 1},
-	{ DBGBUS_DSPP, 64, 2},
-	{ DBGBUS_DSPP, 64, 3},
-	{ DBGBUS_DSPP, 64, 4},
-	{ DBGBUS_DSPP, 64, 5},
-	{ DBGBUS_DSPP, 64, 6},
-	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 65, 1},
-	{ DBGBUS_DSPP, 65, 2},
-	{ DBGBUS_DSPP, 65, 3},
-	{ DBGBUS_DSPP, 65, 4},
-	{ DBGBUS_DSPP, 65, 5},
-	{ DBGBUS_DSPP, 65, 6},
-	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 66, 1},
-	{ DBGBUS_DSPP, 66, 2},
-	{ DBGBUS_DSPP, 66, 3},
-	{ DBGBUS_DSPP, 66, 4},
-	{ DBGBUS_DSPP, 66, 5},
-	{ DBGBUS_DSPP, 66, 6},
-	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 67, 1},
-	{ DBGBUS_DSPP, 67, 2},
-	{ DBGBUS_DSPP, 67, 3},
-	{ DBGBUS_DSPP, 67, 4},
-	{ DBGBUS_DSPP, 67, 5},
-	{ DBGBUS_DSPP, 67, 6},
-	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 68, 1},
-	{ DBGBUS_DSPP, 68, 2},
-	{ DBGBUS_DSPP, 68, 3},
-	{ DBGBUS_DSPP, 68, 4},
-	{ DBGBUS_DSPP, 68, 5},
-	{ DBGBUS_DSPP, 68, 6},
-	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 69, 1},
-	{ DBGBUS_DSPP, 69, 2},
-	{ DBGBUS_DSPP, 69, 3},
-	{ DBGBUS_DSPP, 69, 4},
-	{ DBGBUS_DSPP, 69, 5},
-	{ DBGBUS_DSPP, 69, 6},
-	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 84, 1},
-	{ DBGBUS_DSPP, 84, 2},
-	{ DBGBUS_DSPP, 84, 3},
-	{ DBGBUS_DSPP, 84, 4},
-	{ DBGBUS_DSPP, 84, 5},
-	{ DBGBUS_DSPP, 84, 6},
-	{ DBGBUS_DSPP, 84, 7, _dpu_debug_bus_lm_dump },
-
-
-	{ DBGBUS_DSPP, 85, 1},
-	{ DBGBUS_DSPP, 85, 2},
-	{ DBGBUS_DSPP, 85, 3},
-	{ DBGBUS_DSPP, 85, 4},
-	{ DBGBUS_DSPP, 85, 5},
-	{ DBGBUS_DSPP, 85, 6},
-	{ DBGBUS_DSPP, 85, 7, _dpu_debug_bus_lm_dump },
-
-
-	{ DBGBUS_DSPP, 86, 1},
-	{ DBGBUS_DSPP, 86, 2},
-	{ DBGBUS_DSPP, 86, 3},
-	{ DBGBUS_DSPP, 86, 4},
-	{ DBGBUS_DSPP, 86, 5},
-	{ DBGBUS_DSPP, 86, 6},
-	{ DBGBUS_DSPP, 86, 7, _dpu_debug_bus_lm_dump },
-
-
-	{ DBGBUS_DSPP, 87, 1},
-	{ DBGBUS_DSPP, 87, 2},
-	{ DBGBUS_DSPP, 87, 3},
-	{ DBGBUS_DSPP, 87, 4},
-	{ DBGBUS_DSPP, 87, 5},
-	{ DBGBUS_DSPP, 87, 6},
-	{ DBGBUS_DSPP, 87, 7, _dpu_debug_bus_lm_dump },
-
-	/* LM1 */
-	{ DBGBUS_DSPP, 70, 1},
-	{ DBGBUS_DSPP, 70, 2},
-	{ DBGBUS_DSPP, 70, 3},
-	{ DBGBUS_DSPP, 70, 4},
-	{ DBGBUS_DSPP, 70, 5},
-	{ DBGBUS_DSPP, 70, 6},
-	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 71, 1},
-	{ DBGBUS_DSPP, 71, 2},
-	{ DBGBUS_DSPP, 71, 3},
-	{ DBGBUS_DSPP, 71, 4},
-	{ DBGBUS_DSPP, 71, 5},
-	{ DBGBUS_DSPP, 71, 6},
-	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 72, 1},
-	{ DBGBUS_DSPP, 72, 2},
-	{ DBGBUS_DSPP, 72, 3},
-	{ DBGBUS_DSPP, 72, 4},
-	{ DBGBUS_DSPP, 72, 5},
-	{ DBGBUS_DSPP, 72, 6},
-	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 73, 1},
-	{ DBGBUS_DSPP, 73, 2},
-	{ DBGBUS_DSPP, 73, 3},
-	{ DBGBUS_DSPP, 73, 4},
-	{ DBGBUS_DSPP, 73, 5},
-	{ DBGBUS_DSPP, 73, 6},
-	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 74, 1},
-	{ DBGBUS_DSPP, 74, 2},
-	{ DBGBUS_DSPP, 74, 3},
-	{ DBGBUS_DSPP, 74, 4},
-	{ DBGBUS_DSPP, 74, 5},
-	{ DBGBUS_DSPP, 74, 6},
-	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 75, 1},
-	{ DBGBUS_DSPP, 75, 2},
-	{ DBGBUS_DSPP, 75, 3},
-	{ DBGBUS_DSPP, 75, 4},
-	{ DBGBUS_DSPP, 75, 5},
-	{ DBGBUS_DSPP, 75, 6},
-	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 76, 1},
-	{ DBGBUS_DSPP, 76, 2},
-	{ DBGBUS_DSPP, 76, 3},
-	{ DBGBUS_DSPP, 76, 4},
-	{ DBGBUS_DSPP, 76, 5},
-	{ DBGBUS_DSPP, 76, 6},
-	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 88, 1},
-	{ DBGBUS_DSPP, 88, 2},
-	{ DBGBUS_DSPP, 88, 3},
-	{ DBGBUS_DSPP, 88, 4},
-	{ DBGBUS_DSPP, 88, 5},
-	{ DBGBUS_DSPP, 88, 6},
-	{ DBGBUS_DSPP, 88, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 89, 1},
-	{ DBGBUS_DSPP, 89, 2},
-	{ DBGBUS_DSPP, 89, 3},
-	{ DBGBUS_DSPP, 89, 4},
-	{ DBGBUS_DSPP, 89, 5},
-	{ DBGBUS_DSPP, 89, 6},
-	{ DBGBUS_DSPP, 89, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 90, 1},
-	{ DBGBUS_DSPP, 90, 2},
-	{ DBGBUS_DSPP, 90, 3},
-	{ DBGBUS_DSPP, 90, 4},
-	{ DBGBUS_DSPP, 90, 5},
-	{ DBGBUS_DSPP, 90, 6},
-	{ DBGBUS_DSPP, 90, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 91, 1},
-	{ DBGBUS_DSPP, 91, 2},
-	{ DBGBUS_DSPP, 91, 3},
-	{ DBGBUS_DSPP, 91, 4},
-	{ DBGBUS_DSPP, 91, 5},
-	{ DBGBUS_DSPP, 91, 6},
-	{ DBGBUS_DSPP, 91, 7, _dpu_debug_bus_lm_dump },
-
-	/* LM2 */
-	{ DBGBUS_DSPP, 77, 0},
-	{ DBGBUS_DSPP, 77, 1},
-	{ DBGBUS_DSPP, 77, 2},
-	{ DBGBUS_DSPP, 77, 3},
-	{ DBGBUS_DSPP, 77, 4},
-	{ DBGBUS_DSPP, 77, 5},
-	{ DBGBUS_DSPP, 77, 6},
-	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 78, 0},
-	{ DBGBUS_DSPP, 78, 1},
-	{ DBGBUS_DSPP, 78, 2},
-	{ DBGBUS_DSPP, 78, 3},
-	{ DBGBUS_DSPP, 78, 4},
-	{ DBGBUS_DSPP, 78, 5},
-	{ DBGBUS_DSPP, 78, 6},
-	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 79, 0},
-	{ DBGBUS_DSPP, 79, 1},
-	{ DBGBUS_DSPP, 79, 2},
-	{ DBGBUS_DSPP, 79, 3},
-	{ DBGBUS_DSPP, 79, 4},
-	{ DBGBUS_DSPP, 79, 5},
-	{ DBGBUS_DSPP, 79, 6},
-	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 80, 0},
-	{ DBGBUS_DSPP, 80, 1},
-	{ DBGBUS_DSPP, 80, 2},
-	{ DBGBUS_DSPP, 80, 3},
-	{ DBGBUS_DSPP, 80, 4},
-	{ DBGBUS_DSPP, 80, 5},
-	{ DBGBUS_DSPP, 80, 6},
-	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 81, 0},
-	{ DBGBUS_DSPP, 81, 1},
-	{ DBGBUS_DSPP, 81, 2},
-	{ DBGBUS_DSPP, 81, 3},
-	{ DBGBUS_DSPP, 81, 4},
-	{ DBGBUS_DSPP, 81, 5},
-	{ DBGBUS_DSPP, 81, 6},
-	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 82, 0},
-	{ DBGBUS_DSPP, 82, 1},
-	{ DBGBUS_DSPP, 82, 2},
-	{ DBGBUS_DSPP, 82, 3},
-	{ DBGBUS_DSPP, 82, 4},
-	{ DBGBUS_DSPP, 82, 5},
-	{ DBGBUS_DSPP, 82, 6},
-	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 83, 0},
-	{ DBGBUS_DSPP, 83, 1},
-	{ DBGBUS_DSPP, 83, 2},
-	{ DBGBUS_DSPP, 83, 3},
-	{ DBGBUS_DSPP, 83, 4},
-	{ DBGBUS_DSPP, 83, 5},
-	{ DBGBUS_DSPP, 83, 6},
-	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 92, 1},
-	{ DBGBUS_DSPP, 92, 2},
-	{ DBGBUS_DSPP, 92, 3},
-	{ DBGBUS_DSPP, 92, 4},
-	{ DBGBUS_DSPP, 92, 5},
-	{ DBGBUS_DSPP, 92, 6},
-	{ DBGBUS_DSPP, 92, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 93, 1},
-	{ DBGBUS_DSPP, 93, 2},
-	{ DBGBUS_DSPP, 93, 3},
-	{ DBGBUS_DSPP, 93, 4},
-	{ DBGBUS_DSPP, 93, 5},
-	{ DBGBUS_DSPP, 93, 6},
-	{ DBGBUS_DSPP, 93, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 94, 1},
-	{ DBGBUS_DSPP, 94, 2},
-	{ DBGBUS_DSPP, 94, 3},
-	{ DBGBUS_DSPP, 94, 4},
-	{ DBGBUS_DSPP, 94, 5},
-	{ DBGBUS_DSPP, 94, 6},
-	{ DBGBUS_DSPP, 94, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 95, 1},
-	{ DBGBUS_DSPP, 95, 2},
-	{ DBGBUS_DSPP, 95, 3},
-	{ DBGBUS_DSPP, 95, 4},
-	{ DBGBUS_DSPP, 95, 5},
-	{ DBGBUS_DSPP, 95, 6},
-	{ DBGBUS_DSPP, 95, 7, _dpu_debug_bus_lm_dump },
-
-	/* LM5 */
-	{ DBGBUS_DSPP, 110, 1},
-	{ DBGBUS_DSPP, 110, 2},
-	{ DBGBUS_DSPP, 110, 3},
-	{ DBGBUS_DSPP, 110, 4},
-	{ DBGBUS_DSPP, 110, 5},
-	{ DBGBUS_DSPP, 110, 6},
-	{ DBGBUS_DSPP, 110, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 111, 1},
-	{ DBGBUS_DSPP, 111, 2},
-	{ DBGBUS_DSPP, 111, 3},
-	{ DBGBUS_DSPP, 111, 4},
-	{ DBGBUS_DSPP, 111, 5},
-	{ DBGBUS_DSPP, 111, 6},
-	{ DBGBUS_DSPP, 111, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 112, 1},
-	{ DBGBUS_DSPP, 112, 2},
-	{ DBGBUS_DSPP, 112, 3},
-	{ DBGBUS_DSPP, 112, 4},
-	{ DBGBUS_DSPP, 112, 5},
-	{ DBGBUS_DSPP, 112, 6},
-	{ DBGBUS_DSPP, 112, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 113, 1},
-	{ DBGBUS_DSPP, 113, 2},
-	{ DBGBUS_DSPP, 113, 3},
-	{ DBGBUS_DSPP, 113, 4},
-	{ DBGBUS_DSPP, 113, 5},
-	{ DBGBUS_DSPP, 113, 6},
-	{ DBGBUS_DSPP, 113, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 114, 1},
-	{ DBGBUS_DSPP, 114, 2},
-	{ DBGBUS_DSPP, 114, 3},
-	{ DBGBUS_DSPP, 114, 4},
-	{ DBGBUS_DSPP, 114, 5},
-	{ DBGBUS_DSPP, 114, 6},
-	{ DBGBUS_DSPP, 114, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 115, 1},
-	{ DBGBUS_DSPP, 115, 2},
-	{ DBGBUS_DSPP, 115, 3},
-	{ DBGBUS_DSPP, 115, 4},
-	{ DBGBUS_DSPP, 115, 5},
-	{ DBGBUS_DSPP, 115, 6},
-	{ DBGBUS_DSPP, 115, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 116, 1},
-	{ DBGBUS_DSPP, 116, 2},
-	{ DBGBUS_DSPP, 116, 3},
-	{ DBGBUS_DSPP, 116, 4},
-	{ DBGBUS_DSPP, 116, 5},
-	{ DBGBUS_DSPP, 116, 6},
-	{ DBGBUS_DSPP, 116, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 117, 1},
-	{ DBGBUS_DSPP, 117, 2},
-	{ DBGBUS_DSPP, 117, 3},
-	{ DBGBUS_DSPP, 117, 4},
-	{ DBGBUS_DSPP, 117, 5},
-	{ DBGBUS_DSPP, 117, 6},
-	{ DBGBUS_DSPP, 117, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 118, 1},
-	{ DBGBUS_DSPP, 118, 2},
-	{ DBGBUS_DSPP, 118, 3},
-	{ DBGBUS_DSPP, 118, 4},
-	{ DBGBUS_DSPP, 118, 5},
-	{ DBGBUS_DSPP, 118, 6},
-	{ DBGBUS_DSPP, 118, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 119, 1},
-	{ DBGBUS_DSPP, 119, 2},
-	{ DBGBUS_DSPP, 119, 3},
-	{ DBGBUS_DSPP, 119, 4},
-	{ DBGBUS_DSPP, 119, 5},
-	{ DBGBUS_DSPP, 119, 6},
-	{ DBGBUS_DSPP, 119, 7, _dpu_debug_bus_lm_dump },
-
-	{ DBGBUS_DSPP, 120, 1},
-	{ DBGBUS_DSPP, 120, 2},
-	{ DBGBUS_DSPP, 120, 3},
-	{ DBGBUS_DSPP, 120, 4},
-	{ DBGBUS_DSPP, 120, 5},
-	{ DBGBUS_DSPP, 120, 6},
-	{ DBGBUS_DSPP, 120, 7, _dpu_debug_bus_lm_dump },
-
-	/* csc */
-	{ DBGBUS_SSPP0, 7, 0},
-	{ DBGBUS_SSPP0, 7, 1},
-	{ DBGBUS_SSPP0, 27, 0},
-	{ DBGBUS_SSPP0, 27, 1},
-	{ DBGBUS_SSPP1, 7, 0},
-	{ DBGBUS_SSPP1, 7, 1},
-	{ DBGBUS_SSPP1, 27, 0},
-	{ DBGBUS_SSPP1, 27, 1},
-
-	/* pcc */
-	{ DBGBUS_SSPP0, 3,  3},
-	{ DBGBUS_SSPP0, 23, 3},
-	{ DBGBUS_SSPP0, 33, 3},
-	{ DBGBUS_SSPP0, 43, 3},
-	{ DBGBUS_SSPP1, 3,  3},
-	{ DBGBUS_SSPP1, 23, 3},
-	{ DBGBUS_SSPP1, 33, 3},
-	{ DBGBUS_SSPP1, 43, 3},
-
-	/* spa */
-	{ DBGBUS_SSPP0, 8,  0},
-	{ DBGBUS_SSPP0, 28, 0},
-	{ DBGBUS_SSPP1, 8,  0},
-	{ DBGBUS_SSPP1, 28, 0},
-	{ DBGBUS_DSPP, 13, 0},
-	{ DBGBUS_DSPP, 19, 0},
-
-	/* igc */
-	{ DBGBUS_SSPP0, 17, 0},
-	{ DBGBUS_SSPP0, 17, 1},
-	{ DBGBUS_SSPP0, 17, 3},
-	{ DBGBUS_SSPP0, 37, 0},
-	{ DBGBUS_SSPP0, 37, 1},
-	{ DBGBUS_SSPP0, 37, 3},
-	{ DBGBUS_SSPP0, 46, 0},
-	{ DBGBUS_SSPP0, 46, 1},
-	{ DBGBUS_SSPP0, 46, 3},
-
-	{ DBGBUS_SSPP1, 17, 0},
-	{ DBGBUS_SSPP1, 17, 1},
-	{ DBGBUS_SSPP1, 17, 3},
-	{ DBGBUS_SSPP1, 37, 0},
-	{ DBGBUS_SSPP1, 37, 1},
-	{ DBGBUS_SSPP1, 37, 3},
-	{ DBGBUS_SSPP1, 46, 0},
-	{ DBGBUS_SSPP1, 46, 1},
-	{ DBGBUS_SSPP1, 46, 3},
-
-	{ DBGBUS_DSPP, 14, 0},
-	{ DBGBUS_DSPP, 14, 1},
-	{ DBGBUS_DSPP, 14, 3},
-	{ DBGBUS_DSPP, 20, 0},
-	{ DBGBUS_DSPP, 20, 1},
-	{ DBGBUS_DSPP, 20, 3},
-
-	/* intf0-3 */
-	{ DBGBUS_PERIPH, 0, 0},
-	{ DBGBUS_PERIPH, 1, 0},
-	{ DBGBUS_PERIPH, 2, 0},
-	{ DBGBUS_PERIPH, 3, 0},
-
-	/* te counter wrapper */
-	{ DBGBUS_PERIPH, 60, 0},
-
-	/* dsc0 */
-	{ DBGBUS_PERIPH, 47, 0},
-	{ DBGBUS_PERIPH, 47, 1},
-	{ DBGBUS_PERIPH, 47, 2},
-	{ DBGBUS_PERIPH, 47, 3},
-	{ DBGBUS_PERIPH, 47, 4},
-	{ DBGBUS_PERIPH, 47, 5},
-	{ DBGBUS_PERIPH, 47, 6},
-	{ DBGBUS_PERIPH, 47, 7},
-
-	/* dsc1 */
-	{ DBGBUS_PERIPH, 48, 0},
-	{ DBGBUS_PERIPH, 48, 1},
-	{ DBGBUS_PERIPH, 48, 2},
-	{ DBGBUS_PERIPH, 48, 3},
-	{ DBGBUS_PERIPH, 48, 4},
-	{ DBGBUS_PERIPH, 48, 5},
-	{ DBGBUS_PERIPH, 48, 6},
-	{ DBGBUS_PERIPH, 48, 7},
-
-	/* dsc2 */
-	{ DBGBUS_PERIPH, 51, 0},
-	{ DBGBUS_PERIPH, 51, 1},
-	{ DBGBUS_PERIPH, 51, 2},
-	{ DBGBUS_PERIPH, 51, 3},
-	{ DBGBUS_PERIPH, 51, 4},
-	{ DBGBUS_PERIPH, 51, 5},
-	{ DBGBUS_PERIPH, 51, 6},
-	{ DBGBUS_PERIPH, 51, 7},
-
-	/* dsc3 */
-	{ DBGBUS_PERIPH, 52, 0},
-	{ DBGBUS_PERIPH, 52, 1},
-	{ DBGBUS_PERIPH, 52, 2},
-	{ DBGBUS_PERIPH, 52, 3},
-	{ DBGBUS_PERIPH, 52, 4},
-	{ DBGBUS_PERIPH, 52, 5},
-	{ DBGBUS_PERIPH, 52, 6},
-	{ DBGBUS_PERIPH, 52, 7},
-
-	/* tear-check */
-	{ DBGBUS_PERIPH, 63, 0 },
-	{ DBGBUS_PERIPH, 64, 0 },
-	{ DBGBUS_PERIPH, 65, 0 },
-	{ DBGBUS_PERIPH, 73, 0 },
-	{ DBGBUS_PERIPH, 74, 0 },
-
-	/* cdwn */
-	{ DBGBUS_PERIPH, 80, 0},
-	{ DBGBUS_PERIPH, 80, 1},
-	{ DBGBUS_PERIPH, 80, 2},
-
-	{ DBGBUS_PERIPH, 81, 0},
-	{ DBGBUS_PERIPH, 81, 1},
-	{ DBGBUS_PERIPH, 81, 2},
-
-	{ DBGBUS_PERIPH, 82, 0},
-	{ DBGBUS_PERIPH, 82, 1},
-	{ DBGBUS_PERIPH, 82, 2},
-	{ DBGBUS_PERIPH, 82, 3},
-	{ DBGBUS_PERIPH, 82, 4},
-	{ DBGBUS_PERIPH, 82, 5},
-	{ DBGBUS_PERIPH, 82, 6},
-	{ DBGBUS_PERIPH, 82, 7},
-
-	/* hdmi */
-	{ DBGBUS_PERIPH, 68, 0},
-	{ DBGBUS_PERIPH, 68, 1},
-	{ DBGBUS_PERIPH, 68, 2},
-	{ DBGBUS_PERIPH, 68, 3},
-	{ DBGBUS_PERIPH, 68, 4},
-	{ DBGBUS_PERIPH, 68, 5},
-
-	/* edp */
-	{ DBGBUS_PERIPH, 69, 0},
-	{ DBGBUS_PERIPH, 69, 1},
-	{ DBGBUS_PERIPH, 69, 2},
-	{ DBGBUS_PERIPH, 69, 3},
-	{ DBGBUS_PERIPH, 69, 4},
-	{ DBGBUS_PERIPH, 69, 5},
-
-	/* dsi0 */
-	{ DBGBUS_PERIPH, 70, 0},
-	{ DBGBUS_PERIPH, 70, 1},
-	{ DBGBUS_PERIPH, 70, 2},
-	{ DBGBUS_PERIPH, 70, 3},
-	{ DBGBUS_PERIPH, 70, 4},
-	{ DBGBUS_PERIPH, 70, 5},
-
-	/* dsi1 */
-	{ DBGBUS_PERIPH, 71, 0},
-	{ DBGBUS_PERIPH, 71, 1},
-	{ DBGBUS_PERIPH, 71, 2},
-	{ DBGBUS_PERIPH, 71, 3},
-	{ DBGBUS_PERIPH, 71, 4},
-	{ DBGBUS_PERIPH, 71, 5},
-};
-
-static struct vbif_debug_bus_entry vbif_dbg_bus_msm8998[] = {
-	{0x214, 0x21c, 16, 2, 0x0, 0xd},     /* arb clients */
-	{0x214, 0x21c, 16, 2, 0x80, 0xc0},   /* arb clients */
-	{0x214, 0x21c, 16, 2, 0x100, 0x140}, /* arb clients */
-	{0x214, 0x21c, 0, 16, 0x0, 0xf},     /* xin blocks - axi side */
-	{0x214, 0x21c, 0, 16, 0x80, 0xa4},   /* xin blocks - axi side */
-	{0x214, 0x21c, 0, 15, 0x100, 0x124}, /* xin blocks - axi side */
-	{0x21c, 0x214, 0, 14, 0, 0xc}, /* xin blocks - clock side */
-};
-
-/**
- * _dpu_dbg_enable_power - use callback to turn power on for hw register access
- * @enable: whether to turn power on or off
- */
-static inline void _dpu_dbg_enable_power(int enable)
-{
-	if (enable)
-		pm_runtime_get_sync(dpu_dbg_base.dev);
-	else
-		pm_runtime_put_sync(dpu_dbg_base.dev);
-}
-
-static void _dpu_dbg_dump_dpu_dbg_bus(struct dpu_dbg_dpu_debug_bus *bus)
-{
-	bool in_log, in_mem;
-	u32 **dump_mem = NULL;
-	u32 *dump_addr = NULL;
-	u32 status = 0;
-	struct dpu_debug_bus_entry *head;
-	phys_addr_t phys = 0;
-	int list_size;
-	int i;
-	u32 offset;
-	void __iomem *mem_base = NULL;
-	struct dpu_dbg_reg_base *reg_base;
-
-	if (!bus || !bus->cmn.entries_size)
-		return;
-
-	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
-			reg_base_head)
-		if (strlen(reg_base->name) &&
-			!strcmp(reg_base->name, bus->cmn.name))
-			mem_base = reg_base->base + bus->top_blk_off;
-
-	if (!mem_base) {
-		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
-		return;
-	}
-
-	dump_mem = &bus->cmn.dumped_content;
-
-	/* will keep in memory 4 entries of 4 bytes each */
-	list_size = (bus->cmn.entries_size * 4 * 4);
-
-	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
-	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
-
-	if (!in_log && !in_mem)
-		return;
-
-	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
-			bus->cmn.name);
-
-	if (in_mem) {
-		if (!(*dump_mem))
-			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
-				list_size, &phys, GFP_KERNEL);
-
-		if (*dump_mem) {
-			dump_addr = *dump_mem;
-			dev_info(dpu_dbg_base.dev,
-				"%s: start_addr:0x%pK len:0x%x\n",
-				__func__, dump_addr, list_size);
-		} else {
-			in_mem = false;
-			pr_err("dump_mem: allocation fails\n");
-		}
-	}
-
-	_dpu_dbg_enable_power(true);
-	for (i = 0; i < bus->cmn.entries_size; i++) {
-		head = bus->entries + i;
-		writel_relaxed(TEST_MASK(head->block_id, head->test_id),
-				mem_base + head->wr_addr);
-		wmb(); /* make sure test bits were written */
-
-		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP) {
-			offset = DBGBUS_DSPP_STATUS;
-			/* keep DSPP test point enabled */
-			if (head->wr_addr != DBGBUS_DSPP)
-				writel_relaxed(0xF, mem_base + DBGBUS_DSPP);
-		} else {
-			offset = head->wr_addr + 0x4;
-		}
-
-		status = readl_relaxed(mem_base + offset);
-
-		if (in_log)
-			dev_info(dpu_dbg_base.dev,
-					"waddr=0x%x blk=%d tst=%d val=0x%x\n",
-					head->wr_addr, head->block_id,
-					head->test_id, status);
-
-		if (dump_addr && in_mem) {
-			dump_addr[i*4]     = head->wr_addr;
-			dump_addr[i*4 + 1] = head->block_id;
-			dump_addr[i*4 + 2] = head->test_id;
-			dump_addr[i*4 + 3] = status;
-		}
-
-		if (head->analyzer)
-			head->analyzer(mem_base, head, status);
-
-		/* Disable debug bus once we are done */
-		writel_relaxed(0, mem_base + head->wr_addr);
-		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP &&
-						head->wr_addr != DBGBUS_DSPP)
-			writel_relaxed(0x0, mem_base + DBGBUS_DSPP);
-	}
-	_dpu_dbg_enable_power(false);
-
-	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
-			bus->cmn.name);
-}
-
-static void _dpu_dbg_dump_vbif_debug_bus_entry(
-		struct vbif_debug_bus_entry *head, void __iomem *mem_base,
-		u32 *dump_addr, bool in_log)
-{
-	int i, j;
-	u32 val;
-
-	if (!dump_addr && !in_log)
-		return;
-
-	for (i = 0; i < head->block_cnt; i++) {
-		writel_relaxed(1 << (i + head->bit_offset),
-				mem_base + head->block_bus_addr);
-		/* make sure that current bus blcok enable */
-		wmb();
-		for (j = head->test_pnt_start; j < head->test_pnt_cnt; j++) {
-			writel_relaxed(j, mem_base + head->block_bus_addr + 4);
-			/* make sure that test point is enabled */
-			wmb();
-			val = readl_relaxed(mem_base + MMSS_VBIF_TEST_BUS_OUT);
-			if (dump_addr) {
-				*dump_addr++ = head->block_bus_addr;
-				*dump_addr++ = i;
-				*dump_addr++ = j;
-				*dump_addr++ = val;
-			}
-			if (in_log)
-				dev_info(dpu_dbg_base.dev,
-					"testpoint:%x arb/xin id=%d index=%d val=0x%x\n",
-					head->block_bus_addr, i, j, val);
-		}
-	}
-}
-
-static void _dpu_dbg_dump_vbif_dbg_bus(struct dpu_dbg_vbif_debug_bus *bus)
-{
-	bool in_log, in_mem;
-	u32 **dump_mem = NULL;
-	u32 *dump_addr = NULL;
-	u32 value, d0, d1;
-	unsigned long reg, reg1, reg2;
-	struct vbif_debug_bus_entry *head;
-	phys_addr_t phys = 0;
-	int i, list_size = 0;
-	void __iomem *mem_base = NULL;
-	struct vbif_debug_bus_entry *dbg_bus;
-	u32 bus_size;
-	struct dpu_dbg_reg_base *reg_base;
-
-	if (!bus || !bus->cmn.entries_size)
-		return;
-
-	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
-			reg_base_head)
-		if (strlen(reg_base->name) &&
-			!strcmp(reg_base->name, bus->cmn.name))
-			mem_base = reg_base->base;
-
-	if (!mem_base) {
-		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
-		return;
-	}
-
-	dbg_bus = bus->entries;
-	bus_size = bus->cmn.entries_size;
-	list_size = bus->cmn.entries_size;
-	dump_mem = &bus->cmn.dumped_content;
-
-	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
-			bus->cmn.name);
-
-	if (!dump_mem || !dbg_bus || !bus_size || !list_size)
-		return;
-
-	/* allocate memory for each test point */
-	for (i = 0; i < bus_size; i++) {
-		head = dbg_bus + i;
-		list_size += (head->block_cnt * head->test_pnt_cnt);
-	}
-
-	/* 4 bytes * 4 entries for each test point*/
-	list_size *= 16;
-
-	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
-	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
-
-	if (!in_log && !in_mem)
-		return;
-
-	if (in_mem) {
-		if (!(*dump_mem))
-			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
-				list_size, &phys, GFP_KERNEL);
-
-		if (*dump_mem) {
-			dump_addr = *dump_mem;
-			dev_info(dpu_dbg_base.dev,
-				"%s: start_addr:0x%pK len:0x%x\n",
-				__func__, dump_addr, list_size);
-		} else {
-			in_mem = false;
-			pr_err("dump_mem: allocation fails\n");
-		}
-	}
-
-	_dpu_dbg_enable_power(true);
-
-	value = readl_relaxed(mem_base + MMSS_VBIF_CLKON);
-	writel_relaxed(value | BIT(1), mem_base + MMSS_VBIF_CLKON);
-
-	/* make sure that vbif core is on */
-	wmb();
-
-	/**
-	 * Extract VBIF error info based on XIN halt and error status.
-	 * If the XIN client is not in HALT state, or an error is detected,
-	 * then retrieve the VBIF error info for it.
-	 */
-	reg = readl_relaxed(mem_base + MMSS_VBIF_XIN_HALT_CTRL1);
-	reg1 = readl_relaxed(mem_base + MMSS_VBIF_PND_ERR);
-	reg2 = readl_relaxed(mem_base + MMSS_VBIF_SRC_ERR);
-	dev_err(dpu_dbg_base.dev,
-			"XIN HALT:0x%lX, PND ERR:0x%lX, SRC ERR:0x%lX\n",
-			reg, reg1, reg2);
-	reg >>= 16;
-	reg &= ~(reg1 | reg2);
-	for (i = 0; i < MMSS_VBIF_CLIENT_NUM; i++) {
-		if (!test_bit(0, &reg)) {
-			writel_relaxed(i, mem_base + MMSS_VBIF_ERR_INFO);
-			/* make sure reg write goes through */
-			wmb();
-
-			d0 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO);
-			d1 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO_1);
-
-			dev_err(dpu_dbg_base.dev,
-					"Client:%d, errinfo=0x%X, errinfo1=0x%X\n",
-					i, d0, d1);
-		}
-		reg >>= 1;
-	}
-
-	for (i = 0; i < bus_size; i++) {
-		head = dbg_bus + i;
-
-		writel_relaxed(0, mem_base + head->disable_bus_addr);
-		writel_relaxed(BIT(0), mem_base + MMSS_VBIF_TEST_BUS_OUT_CTRL);
-		/* make sure that other bus is off */
-		wmb();
-
-		_dpu_dbg_dump_vbif_debug_bus_entry(head, mem_base, dump_addr,
-				in_log);
-		if (dump_addr)
-			dump_addr += (head->block_cnt * head->test_pnt_cnt * 4);
-	}
-
-	_dpu_dbg_enable_power(false);
-
-	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
-			bus->cmn.name);
-}
-
-/**
- * _dpu_dump_array - dump array of register bases
- * @name: string indicating origin of dump
- * @dump_dbgbus_dpu: whether to dump the dpu debug bus
- * @dump_dbgbus_vbif_rt: whether to dump the vbif rt debug bus
- */
-static void _dpu_dump_array(const char *name, bool dump_dbgbus_dpu,
-			    bool dump_dbgbus_vbif_rt)
-{
-	if (dump_dbgbus_dpu)
-		_dpu_dbg_dump_dpu_dbg_bus(&dpu_dbg_base.dbgbus_dpu);
-
-	if (dump_dbgbus_vbif_rt)
-		_dpu_dbg_dump_vbif_dbg_bus(&dpu_dbg_base.dbgbus_vbif_rt);
-}
-
-/**
- * _dpu_dump_work - deferred dump work function
- * @work: work structure
- */
-static void _dpu_dump_work(struct work_struct *work)
-{
-	_dpu_dump_array("dpudump_workitem",
-		dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work,
-		dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work);
-}
-
-void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
-		  bool dump_dbgbus_vbif_rt)
-{
-	if (queue_work && work_pending(&dpu_dbg_base.dump_work))
-		return;
-
-	if (!queue_work) {
-		_dpu_dump_array(name, dump_dbgbus_dpu, dump_dbgbus_vbif_rt);
-		return;
-	}
-
-	/* schedule work to dump later */
-	dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work = dump_dbgbus_dpu;
-	dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work =
-			dump_dbgbus_vbif_rt;
-	schedule_work(&dpu_dbg_base.dump_work);
-}
-
-/*
- * dpu_dbg_debugfs_open - debugfs open handler for debug dump
- * @inode: debugfs inode
- * @file: file handle
- */
-static int dpu_dbg_debugfs_open(struct inode *inode, struct file *file)
-{
-	/* non-seekable */
-	file->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
-	file->private_data = inode->i_private;
-	return 0;
-}
-
-/**
- * dpu_dbg_dump_write - debugfs write handler for debug dump
- * @file: file handler
- * @user_buf: user buffer content from debugfs
- * @count: size of user buffer
- * @ppos: position offset of user buffer
- */
-static ssize_t dpu_dbg_dump_write(struct file *file,
-	const char __user *user_buf, size_t count, loff_t *ppos)
-{
-	_dpu_dump_array("dump_debugfs", true, true);
-	return count;
-}
-
-static const struct file_operations dpu_dbg_dump_fops = {
-	.open = dpu_dbg_debugfs_open,
-	.write = dpu_dbg_dump_write,
-};
-
-int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
-{
-	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
-	char debug_name[80] = "";
-
-	if (!debugfs_root)
-		return -EINVAL;
-
-	debugfs_create_file("dump", 0600, debugfs_root, NULL,
-			&dpu_dbg_dump_fops);
-
-	if (dbg->dbgbus_dpu.entries) {
-		dbg->dbgbus_dpu.cmn.name = DBGBUS_NAME_DPU;
-		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
-				dbg->dbgbus_dpu.cmn.name);
-		dbg->dbgbus_dpu.cmn.enable_mask = DEFAULT_DBGBUS_DPU;
-		debugfs_create_u32(debug_name, 0600, debugfs_root,
-				&dbg->dbgbus_dpu.cmn.enable_mask);
-	}
-
-	if (dbg->dbgbus_vbif_rt.entries) {
-		dbg->dbgbus_vbif_rt.cmn.name = DBGBUS_NAME_VBIF_RT;
-		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
-				dbg->dbgbus_vbif_rt.cmn.name);
-		dbg->dbgbus_vbif_rt.cmn.enable_mask = DEFAULT_DBGBUS_VBIFRT;
-		debugfs_create_u32(debug_name, 0600, debugfs_root,
-				&dbg->dbgbus_vbif_rt.cmn.enable_mask);
-	}
-
-	return 0;
-}
-
-static void _dpu_dbg_debugfs_destroy(void)
-{
-}
-
-void dpu_dbg_init_dbg_buses(u32 hwversion)
-{
-	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
-
-	memset(&dbg->dbgbus_dpu, 0, sizeof(dbg->dbgbus_dpu));
-	memset(&dbg->dbgbus_vbif_rt, 0, sizeof(dbg->dbgbus_vbif_rt));
-
-	if (IS_MSM8998_TARGET(hwversion)) {
-		dbg->dbgbus_dpu.entries = dbg_bus_dpu_8998;
-		dbg->dbgbus_dpu.cmn.entries_size = ARRAY_SIZE(dbg_bus_dpu_8998);
-		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
-
-		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
-		dbg->dbgbus_vbif_rt.cmn.entries_size =
-				ARRAY_SIZE(vbif_dbg_bus_msm8998);
-	} else if (IS_SDM845_TARGET(hwversion) || IS_SDM670_TARGET(hwversion)) {
-		dbg->dbgbus_dpu.entries = dbg_bus_dpu_sdm845;
-		dbg->dbgbus_dpu.cmn.entries_size =
-				ARRAY_SIZE(dbg_bus_dpu_sdm845);
-		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
-
-		/* vbif is unchanged vs 8998 */
-		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
-		dbg->dbgbus_vbif_rt.cmn.entries_size =
-				ARRAY_SIZE(vbif_dbg_bus_msm8998);
-	} else {
-		pr_err("unsupported chipset id %X\n", hwversion);
-	}
-}
-
-int dpu_dbg_init(struct device *dev)
-{
-	if (!dev) {
-		pr_err("invalid params\n");
-		return -EINVAL;
-	}
-
-	INIT_LIST_HEAD(&dpu_dbg_base.reg_base_list);
-	dpu_dbg_base.dev = dev;
-
-	INIT_WORK(&dpu_dbg_base.dump_work, _dpu_dump_work);
-
-	return 0;
-}
-
-/**
- * dpu_dbg_destroy - destroy dpu debug facilities
- */
-void dpu_dbg_destroy(void)
-{
-	_dpu_dbg_debugfs_destroy();
-}
-
-void dpu_dbg_set_dpu_top_offset(u32 blk_off)
-{
-	dpu_dbg_base.dbgbus_dpu.top_blk_off = blk_off;
-}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
deleted file mode 100644
index 1e6fa945f98b..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
+++ /dev/null
@@ -1,103 +0,0 @@
-/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef DPU_DBG_H_
-#define DPU_DBG_H_
-
-#include <stdarg.h>
-#include <linux/debugfs.h>
-#include <linux/list.h>
-
-enum dpu_dbg_dump_flag {
-	DPU_DBG_DUMP_IN_LOG = BIT(0),
-	DPU_DBG_DUMP_IN_MEM = BIT(1),
-};
-
-#if defined(CONFIG_DEBUG_FS)
-
-/**
- * dpu_dbg_init_dbg_buses - initialize debug bus dumping support for the chipset
- * @hwversion:		Chipset revision
- */
-void dpu_dbg_init_dbg_buses(u32 hwversion);
-
-/**
- * dpu_dbg_init - initialize global dpu debug facilities: regdump
- * @dev:		device handle
- * Returns:		0 or -ERROR
- */
-int dpu_dbg_init(struct device *dev);
-
-/**
- * dpu_dbg_debugfs_register - register entries at the given debugfs dir
- * @debugfs_root:	debugfs root in which to create dpu debug entries
- * Returns:	0 or -ERROR
- */
-int dpu_dbg_debugfs_register(struct dentry *debugfs_root);
-
-/**
- * dpu_dbg_destroy - destroy the global dpu debug facilities
- * Returns:	none
- */
-void dpu_dbg_destroy(void);
-
-/**
- * dpu_dbg_dump - trigger dumping of all dpu_dbg facilities
- * @queue_work:	  whether to queue the dumping work to the work_struct
- * @name:	  string indicating origin of dump
- * @dump_dbgbus:  dump the dpu debug bus
- * @dump_vbif_rt: dump the vbif rt bus
- * Returns:	none
- */
-void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
-		  bool dump_dbgbus_vbif_rt);
-
-/**
- * dpu_dbg_set_dpu_top_offset - set the target specific offset from mdss base
- *	address of the top registers. Used for accessing debug bus controls.
- * @blk_off: offset from mdss base of the top block
- */
-void dpu_dbg_set_dpu_top_offset(u32 blk_off);
-
-#else
-
-static inline void dpu_dbg_init_dbg_buses(u32 hwversion)
-{
-}
-
-static inline int dpu_dbg_init(struct device *dev)
-{
-	return 0;
-}
-
-static inline int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
-{
-	return 0;
-}
-
-static inline void dpu_dbg_destroy(void)
-{
-}
-
-static inline void dpu_dbg_dump(bool queue_work, const char *name,
-				bool dump_dbgbus_dpu, bool dump_dbgbus_vbif_rt)
-{
-}
-
-static inline void dpu_dbg_set_dpu_top_offset(u32 blk_off)
-{
-}
-
-#endif /* defined(CONFIG_DEBUG_FS) */
-
-
-#endif /* DPU_DBG_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 96cdf06e7da2..0dda4a603685 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -130,8 +130,9 @@ enum dpu_enc_rc_states {
  *	Virtual encoder defers as much as possible to the physical encoders.
  *	Virtual encoder registers itself with the DRM Framework as the encoder.
  * @base:		drm_encoder base class for registration with DRM
- * @enc_spin_lock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
  * @bus_scaling_client:	Client handle to the bus scaling interface
+ * @enabled:		True if the encoder is active, protected by enc_lock
  * @num_phys_encs:	Actual number of physical encoders contained.
  * @phys_encs:		Container of physical encoders managed.
  * @cur_master:		Pointer to the current master in this mode. Optimization
@@ -141,15 +142,17 @@ enum dpu_enc_rc_states {
  * @intfs_swapped	Whether or not the phys_enc interfaces have been swapped
  *			for partial update right-only cases, such as pingpong
  *			split where virtual pingpong does not generate IRQs
- * @crtc_vblank_cb:	Callback into the upper layer / CRTC for
- *			notification of the VBLANK
- * @crtc_vblank_cb_data:	Data from upper layer for VBLANK notification
+ * @crtc:		Pointer to the currently assigned crtc. Normally you
+ *			would use crtc->state->encoder_mask to determine the
+ *			link between encoder/crtc. However in this case we need
+ *			to track crtc in the disable() hook which is called
+ *			_after_ encoder_mask is cleared.
  * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
  *				all CTL paths
  * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
  * @debugfs_root:		Debug file system root file node
- * @enc_lock:			Lock around physical encoder create/destroy and
-				access.
+ * @enc_lock:			Lock around physical encoder
+ *				create/destroy/enable/disable
  * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
  *				busy processing current command.
  *				Bit0 = phys_encs[0] etc.
@@ -175,6 +178,8 @@ struct dpu_encoder_virt {
 	spinlock_t enc_spinlock;
 	uint32_t bus_scaling_client;
 
+	bool enabled;
+
 	unsigned int num_phys_encs;
 	struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL];
 	struct dpu_encoder_phys *cur_master;
@@ -183,8 +188,7 @@ struct dpu_encoder_virt {
 
 	bool intfs_swapped;
 
-	void (*crtc_vblank_cb)(void *);
-	void *crtc_vblank_cb_data;
+	struct drm_crtc *crtc;
 
 	struct dentry *debugfs_root;
 	struct mutex enc_lock;
@@ -210,39 +214,6 @@ struct dpu_encoder_virt {
 };
 
 #define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base)
-static inline int _dpu_encoder_power_enable(struct dpu_encoder_virt *dpu_enc,
-								bool enable)
-{
-	struct drm_encoder *drm_enc;
-	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
-
-	if (!dpu_enc) {
-		DPU_ERROR("invalid dpu enc\n");
-		return -EINVAL;
-	}
-
-	drm_enc = &dpu_enc->base;
-	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
-		DPU_ERROR("drm device invalid\n");
-		return -EINVAL;
-	}
-
-	priv = drm_enc->dev->dev_private;
-	if (!priv->kms) {
-		DPU_ERROR("invalid kms\n");
-		return -EINVAL;
-	}
-
-	dpu_kms = to_dpu_kms(priv->kms);
-
-	if (enable)
-		pm_runtime_get_sync(&dpu_kms->pdev->dev);
-	else
-		pm_runtime_put_sync(&dpu_kms->pdev->dev);
-
-	return 0;
-}
 
 void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
 		enum dpu_intr_idx intr_idx)
@@ -1119,28 +1090,24 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 	_dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info);
 }
 
-void dpu_encoder_virt_restore(struct drm_encoder *drm_enc)
+void dpu_encoder_virt_runtime_resume(struct drm_encoder *drm_enc)
 {
-	struct dpu_encoder_virt *dpu_enc = NULL;
-	int i;
-
-	if (!drm_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
-	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
 
-	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
-		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+	mutex_lock(&dpu_enc->enc_lock);
 
-		if (phys && (phys != dpu_enc->cur_master) && phys->ops.restore)
-			phys->ops.restore(phys);
-	}
+	if (!dpu_enc->enabled)
+		goto out;
 
+	if (dpu_enc->cur_slave && dpu_enc->cur_slave->ops.restore)
+		dpu_enc->cur_slave->ops.restore(dpu_enc->cur_slave);
 	if (dpu_enc->cur_master && dpu_enc->cur_master->ops.restore)
 		dpu_enc->cur_master->ops.restore(dpu_enc->cur_master);
 
 	_dpu_encoder_virt_enable_helper(drm_enc);
+
+out:
+	mutex_unlock(&dpu_enc->enc_lock);
 }
 
 static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
@@ -1154,6 +1121,8 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
 		return;
 	}
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	mutex_lock(&dpu_enc->enc_lock);
 	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
 
 	trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay,
@@ -1170,10 +1139,15 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
 	if (ret) {
 		DPU_ERROR_ENC(dpu_enc, "dpu resource control failed: %d\n",
 				ret);
-		return;
+		goto out;
 	}
 
 	_dpu_encoder_virt_enable_helper(drm_enc);
+
+	dpu_enc->enabled = true;
+
+out:
+	mutex_unlock(&dpu_enc->enc_lock);
 }
 
 static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
@@ -1195,11 +1169,14 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 		return;
 	}
 
-	mode = &drm_enc->crtc->state->adjusted_mode;
-
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
 	DPU_DEBUG_ENC(dpu_enc, "\n");
 
+	mutex_lock(&dpu_enc->enc_lock);
+	dpu_enc->enabled = false;
+
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
 
@@ -1233,6 +1210,8 @@ 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);
+
+	mutex_unlock(&dpu_enc->enc_lock);
 }
 
 static enum dpu_intf dpu_encoder_get_intf(struct dpu_mdss_cfg *catalog,
@@ -1263,8 +1242,8 @@ static void dpu_encoder_vblank_callback(struct drm_encoder *drm_enc,
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
 
 	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
-	if (dpu_enc->crtc_vblank_cb)
-		dpu_enc->crtc_vblank_cb(dpu_enc->crtc_vblank_cb_data);
+	if (dpu_enc->crtc)
+		dpu_crtc_vblank_callback(dpu_enc->crtc);
 	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
 
 	atomic_inc(&phy_enc->vsync_cnt);
@@ -1284,25 +1263,32 @@ static void dpu_encoder_underrun_callback(struct drm_encoder *drm_enc,
 	DPU_ATRACE_END("encoder_underrun_callback");
 }
 
-void dpu_encoder_register_vblank_callback(struct drm_encoder *drm_enc,
-		void (*vbl_cb)(void *), void *vbl_data)
+void dpu_encoder_assign_crtc(struct drm_encoder *drm_enc, struct drm_crtc *crtc)
 {
 	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
 	unsigned long lock_flags;
-	bool enable;
-	int i;
 
-	enable = vbl_cb ? true : false;
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	/* crtc should always be cleared before re-assigning */
+	WARN_ON(crtc && dpu_enc->crtc);
+	dpu_enc->crtc = crtc;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+void dpu_encoder_toggle_vblank_for_crtc(struct drm_encoder *drm_enc,
+					struct drm_crtc *crtc, bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	int i;
 
-	if (!drm_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
 	trace_dpu_enc_vblank_cb(DRMID(drm_enc), enable);
 
 	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
-	dpu_enc->crtc_vblank_cb = vbl_cb;
-	dpu_enc->crtc_vblank_cb_data = vbl_data;
+	if (dpu_enc->crtc != crtc) {
+		spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+		return;
+	}
 	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
@@ -1407,8 +1393,9 @@ static void dpu_encoder_off_work(struct kthread_work *work)
  * phys: Pointer to physical encoder structure
  * extra_flush_bits: Additional bit mask to include in flush trigger
  */
-static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
-		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits)
+static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits,
+		bool async)
 {
 	struct dpu_hw_ctl *ctl;
 	int pending_kickoff_cnt;
@@ -1431,7 +1418,10 @@ static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
 		return;
 	}
 
-	pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
+	if (!async)
+		pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
+	else
+		pending_kickoff_cnt = atomic_read(&phys->pending_kickoff_cnt);
 
 	if (extra_flush_bits && ctl->ops.update_pending_flush)
 		ctl->ops.update_pending_flush(ctl, extra_flush_bits);
@@ -1450,7 +1440,7 @@ static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
  * _dpu_encoder_trigger_start - trigger start for a physical encoder
  * phys: Pointer to physical encoder structure
  */
-static inline void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
+static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
 {
 	if (!phys) {
 		DPU_ERROR("invalid argument(s)\n");
@@ -1507,7 +1497,7 @@ static int dpu_encoder_helper_wait_event_timeout(
 	return rc;
 }
 
-void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
+static void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
 {
 	struct dpu_encoder_virt *dpu_enc;
 	struct dpu_hw_ctl *ctl;
@@ -1527,10 +1517,8 @@ void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
 		      ctl->idx);
 
 	rc = ctl->ops.reset(ctl);
-	if (rc) {
+	if (rc)
 		DPU_ERROR_ENC(dpu_enc, "ctl %d reset failure\n",  ctl->idx);
-		dpu_dbg_dump(false, __func__, true, true);
-	}
 
 	phys_enc->enable_state = DPU_ENC_ENABLED;
 }
@@ -1544,7 +1532,8 @@ void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
  *	a time.
  * dpu_enc: Pointer to virtual encoder structure
  */
-static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
+static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc,
+				      bool async)
 {
 	struct dpu_hw_ctl *ctl;
 	uint32_t i, pending_flush;
@@ -1575,7 +1564,8 @@ static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
 			set_bit(i, dpu_enc->frame_busy_mask);
 		if (!phys->ops.needs_single_flush ||
 				!phys->ops.needs_single_flush(phys))
-			_dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0);
+			_dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0,
+						   async);
 		else if (ctl->ops.get_pending_flush)
 			pending_flush |= ctl->ops.get_pending_flush(ctl);
 	}
@@ -1585,7 +1575,7 @@ static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
 		_dpu_encoder_trigger_flush(
 				&dpu_enc->base,
 				dpu_enc->cur_master,
-				pending_flush);
+				pending_flush, async);
 	}
 
 	_dpu_encoder_trigger_start(dpu_enc->cur_master);
@@ -1769,7 +1759,7 @@ static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work)
 }
 
 void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc,
-		struct dpu_encoder_kickoff_params *params)
+		struct dpu_encoder_kickoff_params *params, bool async)
 {
 	struct dpu_encoder_virt *dpu_enc;
 	struct dpu_encoder_phys *phys;
@@ -1803,14 +1793,12 @@ void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc,
 	if (needs_hw_reset) {
 		trace_dpu_enc_prepare_kickoff_reset(DRMID(drm_enc));
 		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
-			phys = dpu_enc->phys_encs[i];
-			if (phys && phys->ops.hw_reset)
-				phys->ops.hw_reset(phys);
+			dpu_encoder_helper_hw_reset(dpu_enc->phys_encs[i]);
 		}
 	}
 }
 
-void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
+void dpu_encoder_kickoff(struct drm_encoder *drm_enc, bool async)
 {
 	struct dpu_encoder_virt *dpu_enc;
 	struct dpu_encoder_phys *phys;
@@ -1833,7 +1821,7 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
 		((atomic_read(&dpu_enc->frame_done_timeout) * HZ) / 1000));
 
 	/* All phys encs are ready to go, trigger the kickoff */
-	_dpu_encoder_kickoff_phys(dpu_enc);
+	_dpu_encoder_kickoff_phys(dpu_enc, async);
 
 	/* allow phys encs to handle any post-kickoff business */
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
@@ -1875,14 +1863,9 @@ void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
 #ifdef CONFIG_DEBUG_FS
 static int _dpu_encoder_status_show(struct seq_file *s, void *data)
 {
-	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_virt *dpu_enc = s->private;
 	int i;
 
-	if (!s || !s->private)
-		return -EINVAL;
-
-	dpu_enc = s->private;
-
 	mutex_lock(&dpu_enc->enc_lock);
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
@@ -1920,7 +1903,7 @@ static int _dpu_encoder_debugfs_status_open(struct inode *inode,
 
 static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 {
-	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
 	int i;
@@ -1934,12 +1917,11 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 
 	char name[DPU_NAME_SIZE];
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
 		DPU_ERROR("invalid encoder or kms\n");
 		return -EINVAL;
 	}
 
-	dpu_enc = to_dpu_encoder_virt(drm_enc);
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
 
@@ -1964,26 +1946,11 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 
 	return 0;
 }
-
-static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
-{
-	struct dpu_encoder_virt *dpu_enc;
-
-	if (!drm_enc)
-		return;
-
-	dpu_enc = to_dpu_encoder_virt(drm_enc);
-	debugfs_remove_recursive(dpu_enc->debugfs_root);
-}
 #else
 static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 {
 	return 0;
 }
-
-static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
-{
-}
 #endif
 
 static int dpu_encoder_late_register(struct drm_encoder *encoder)
@@ -1993,7 +1960,9 @@ static int dpu_encoder_late_register(struct drm_encoder *encoder)
 
 static void dpu_encoder_early_unregister(struct drm_encoder *encoder)
 {
-	_dpu_encoder_destroy_debugfs(encoder);
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(encoder);
+
+	debugfs_remove_recursive(dpu_enc->debugfs_root);
 }
 
 static int dpu_encoder_virt_add_phys_encs(
@@ -2268,6 +2237,8 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
 
 	drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs);
 
+	dpu_enc->enabled = false;
+
 	return &dpu_enc->base;
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
index 9dbf38f446d9..3f5dafe00580 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -55,14 +55,22 @@ void dpu_encoder_get_hw_resources(struct drm_encoder *encoder,
 				  struct dpu_encoder_hw_resources *hw_res);
 
 /**
- * dpu_encoder_register_vblank_callback - provide callback to encoder that
- *	will be called on the next vblank.
+ * dpu_encoder_assign_crtc - Link the encoder to the crtc it's assigned to
  * @encoder:	encoder pointer
- * @cb:		callback pointer, provide NULL to deregister and disable IRQs
- * @data:	user data provided to callback
+ * @crtc:	crtc pointer
+ */
+void dpu_encoder_assign_crtc(struct drm_encoder *encoder,
+			     struct drm_crtc *crtc);
+
+/**
+ * dpu_encoder_toggle_vblank_for_crtc - Toggles vblank interrupts on or off if
+ *	the encoder is assigned to the given crtc
+ * @encoder:	encoder pointer
+ * @crtc:	crtc pointer
+ * @enable:	true if vblank should be enabled
  */
-void dpu_encoder_register_vblank_callback(struct drm_encoder *encoder,
-		void (*cb)(void *), void *data);
+void dpu_encoder_toggle_vblank_for_crtc(struct drm_encoder *encoder,
+					struct drm_crtc *crtc, bool enable);
 
 /**
  * dpu_encoder_register_frame_event_callback - provide callback to encoder that
@@ -81,9 +89,10 @@ void dpu_encoder_register_frame_event_callback(struct drm_encoder *encoder,
  *	Delayed: Block until next trigger can be issued.
  * @encoder:	encoder pointer
  * @params:	kickoff time parameters
+ * @async:	true if this is an asynchronous commit
  */
 void dpu_encoder_prepare_for_kickoff(struct drm_encoder *encoder,
-		struct dpu_encoder_kickoff_params *params);
+		struct dpu_encoder_kickoff_params *params, bool async);
 
 /**
  * dpu_encoder_trigger_kickoff_pending - Clear the flush bits from previous
@@ -96,8 +105,9 @@ void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *encoder);
  * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path
  *	(i.e. ctl flush and start) immediately.
  * @encoder:	encoder pointer
+ * @async:	true if this is an asynchronous commit
  */
-void dpu_encoder_kickoff(struct drm_encoder *encoder);
+void dpu_encoder_kickoff(struct drm_encoder *encoder, bool async);
 
 /**
  * dpu_encoder_wait_for_event - Waits for encoder events
@@ -126,10 +136,10 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder,
 enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder);
 
 /**
- * dpu_encoder_virt_restore - restore the encoder configs
+ * dpu_encoder_virt_runtime_resume - pm runtime resume the encoder configs
  * @encoder:	encoder pointer
  */
-void dpu_encoder_virt_restore(struct drm_encoder *encoder);
+void dpu_encoder_virt_runtime_resume(struct drm_encoder *encoder);
 
 /**
  * dpu_encoder_init - initialize virtual encoder object
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
index 964efcc757a4..44e6f8b68e70 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -114,8 +114,6 @@ struct dpu_encoder_virt_ops {
  * @handle_post_kickoff:	Do any work necessary post-kickoff work
  * @trigger_start:		Process start event on physical encoder
  * @needs_single_flush:		Whether encoder slaves need to be flushed
- * @hw_reset:			Issue HW recovery such as CTL reset and clear
- *				DPU_ENC_ERR_NEEDS_HW_RESET state
  * @irq_control:		Handler to enable/disable all the encoder IRQs
  * @prepare_idle_pc:		phys encoder can update the vsync_enable status
  *                              on idle power collapse prepare
@@ -151,7 +149,6 @@ struct dpu_encoder_phys_ops {
 	void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc);
 	void (*trigger_start)(struct dpu_encoder_phys *phys_enc);
 	bool (*needs_single_flush)(struct dpu_encoder_phys *phys_enc);
-	void (*hw_reset)(struct dpu_encoder_phys *phys_enc);
 	void (*irq_control)(struct dpu_encoder_phys *phys, bool enable);
 	void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc);
 	void (*restore)(struct dpu_encoder_phys *phys);
@@ -342,15 +339,6 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
  */
 void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc);
 
-/**
- * dpu_encoder_helper_hw_reset - issue ctl hw reset
- *	This helper function may be optionally specified by physical
- *	encoders if they require ctl hw reset. If state is currently
- *	DPU_ENC_ERR_NEEDS_HW_RESET, it is set back to DPU_ENC_ENABLED.
- * @phys_enc: Pointer to physical encoder structure
- */
-void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc);
-
 static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
 		struct dpu_encoder_phys *phys_enc)
 {
@@ -362,7 +350,7 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
 	dpu_cstate = to_dpu_crtc_state(phys_enc->parent->crtc->state);
 
 	if (phys_enc->split_role == ENC_ROLE_SOLO &&
-	    dpu_crtc_state_is_stereo(dpu_cstate))
+	    dpu_cstate->num_mixers == CRTC_DUAL_MIXERS)
 		return BLEND_3D_H_ROW_INT;
 
 	return BLEND_3D_NONE;
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 b2d7f0ded24c..99ab5ca9bed3 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
@@ -44,14 +44,7 @@
 
 #define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000
 
-static inline int _dpu_encoder_phys_cmd_get_idle_timeout(
-		struct dpu_encoder_phys_cmd *cmd_enc)
-{
-	return KICKOFF_TIMEOUT_MS;
-}
-
-static inline bool dpu_encoder_phys_cmd_is_master(
-		struct dpu_encoder_phys *phys_enc)
+static bool dpu_encoder_phys_cmd_is_master(struct dpu_encoder_phys *phys_enc)
 {
 	return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false;
 }
@@ -243,7 +236,6 @@ static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
 			  atomic_read(&phys_enc->pending_kickoff_cnt));
 
 		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_RDPTR);
-		dpu_dbg_dump(false, __func__, true, true);
 	}
 
 	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
@@ -496,14 +488,11 @@ static void dpu_encoder_phys_cmd_enable_helper(
 	_dpu_encoder_phys_cmd_pingpong_config(phys_enc);
 
 	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
-		goto skip_flush;
+		return;
 
 	ctl = phys_enc->hw_ctl;
 	ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->intf_idx);
 	ctl->ops.update_pending_flush(ctl, flush_mask);
-
-skip_flush:
-	return;
 }
 
 static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
@@ -727,7 +716,7 @@ static int dpu_encoder_phys_cmd_wait_for_vblank(
 
 	wait_info.wq = &cmd_enc->pending_vblank_wq;
 	wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt;
-	wait_info.timeout_ms = _dpu_encoder_phys_cmd_get_idle_timeout(cmd_enc);
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
 
 	atomic_inc(&cmd_enc->pending_vblank_cnt);
 
@@ -776,7 +765,6 @@ static void dpu_encoder_phys_cmd_init_ops(
 	ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank;
 	ops->trigger_start = dpu_encoder_phys_cmd_trigger_start;
 	ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush;
-	ops->hw_reset = dpu_encoder_helper_hw_reset;
 	ops->irq_control = dpu_encoder_phys_cmd_irq_control;
 	ops->restore = dpu_encoder_phys_cmd_enable_helper;
 	ops->prepare_idle_pc = dpu_encoder_phys_cmd_prepare_idle_pc;
@@ -798,7 +786,7 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
 	if (!cmd_enc) {
 		ret = -ENOMEM;
 		DPU_ERROR("failed to allocate\n");
-		goto fail;
+		return ERR_PTR(ret);
 	}
 	phys_enc = &cmd_enc->base;
 	phys_enc->hw_mdptop = p->dpu_kms->hw_mdp;
@@ -856,6 +844,5 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
 
 	return phys_enc;
 
-fail:
 	return ERR_PTR(ret);
 }
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 84de385a9f62..acdab5b0db18 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
@@ -110,7 +110,7 @@ static void drm_mode_to_intf_timing_params(
 	 */
 }
 
-static inline u32 get_horizontal_total(const struct intf_timing_params *timing)
+static u32 get_horizontal_total(const struct intf_timing_params *timing)
 {
 	u32 active = timing->xres;
 	u32 inactive =
@@ -119,7 +119,7 @@ static inline u32 get_horizontal_total(const struct intf_timing_params *timing)
 	return active + inactive;
 }
 
-static inline u32 get_vertical_total(const struct intf_timing_params *timing)
+static u32 get_vertical_total(const struct intf_timing_params *timing)
 {
 	u32 active = timing->yres;
 	u32 inactive =
@@ -331,7 +331,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
 	if (hw_ctl && hw_ctl->ops.get_flush_register)
 		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
 
-	if (flush_register == 0)
+	if (!(flush_register & hw_ctl->ops.get_pending_flush(hw_ctl)))
 		new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt,
 				-1, 0);
 	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
@@ -613,7 +613,6 @@ static void dpu_encoder_phys_vid_prepare_for_kickoff(
 		DPU_ERROR_VIDENC(vid_enc, "ctl %d reset failure: %d\n",
 				ctl->idx, rc);
 		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_VSYNC);
-		dpu_dbg_dump(false, __func__, true, true);
 	}
 }
 
@@ -766,7 +765,6 @@ static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops)
 	ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff;
 	ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff;
 	ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush;
-	ops->hw_reset = dpu_encoder_helper_hw_reset;
 	ops->get_line_count = dpu_encoder_phys_vid_get_line_count;
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index bfcd165e96df..0aa9b8e1ae70 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -921,7 +921,7 @@ static int _dpu_format_populate_addrs_ubwc(
 			+ layout->plane_size[2] + layout->plane_size[3];
 
 		if (!meta)
-			goto done;
+			return 0;
 
 		/* configure Y metadata plane */
 		layout->plane_addr[2] = base_addr;
@@ -952,12 +952,11 @@ static int _dpu_format_populate_addrs_ubwc(
 		layout->plane_addr[1] = 0;
 
 		if (!meta)
-			goto done;
+			return 0;
 
 		layout->plane_addr[2] = base_addr;
 		layout->plane_addr[3] = 0;
 	}
-done:
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
index 58d29e43faef..92f1c4241b9a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
@@ -30,16 +30,10 @@ static LIST_HEAD(dpu_hw_blk_list);
  * @type: hw block type - enum dpu_hw_blk_type
  * @id: instance id of the hw block
  * @ops: Pointer to block operations
- * return: 0 if success; error code otherwise
  */
-int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+void dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
 		struct dpu_hw_blk_ops *ops)
 {
-	if (!hw_blk) {
-		pr_err("invalid parameters\n");
-		return -EINVAL;
-	}
-
 	INIT_LIST_HEAD(&hw_blk->list);
 	hw_blk->type = type;
 	hw_blk->id = id;
@@ -51,8 +45,6 @@ int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
 	mutex_lock(&dpu_hw_blk_lock);
 	list_add(&hw_blk->list, &dpu_hw_blk_list);
 	mutex_unlock(&dpu_hw_blk_lock);
-
-	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
index 0f4ca8af1ec5..1934c2f7e8fa 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
@@ -44,7 +44,7 @@ struct dpu_hw_blk {
 	struct dpu_hw_blk_ops ops;
 };
 
-int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+void dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
 		struct dpu_hw_blk_ops *ops);
 void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk);
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
index dc060e7358e4..144358a3d0fb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -736,13 +736,4 @@ struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev);
  */
 void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg);
 
-/**
- * dpu_hw_sspp_multirect_enabled - check multirect enabled for the sspp
- * @cfg:          pointer to sspp cfg
- */
-static inline bool dpu_hw_sspp_multirect_enabled(const struct dpu_sspp_cfg *cfg)
-{
-	return test_bit(DPU_SSPP_SMART_DMA_V1, &cfg->features) ||
-			 test_bit(DPU_SSPP_SMART_DMA_V2, &cfg->features);
-}
 #endif /* _DPU_HW_CATALOG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index eec1051f2afc..1068b4b7940f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -13,8 +13,8 @@
 #include <linux/delay.h>
 #include "dpu_hwio.h"
 #include "dpu_hw_ctl.h"
-#include "dpu_dbg.h"
 #include "dpu_kms.h"
+#include "dpu_trace.h"
 
 #define   CTL_LAYER(lm)                 \
 	(((lm) == LM_5) ? (0x024) : (((lm) - LM_0) * 0x004))
@@ -72,24 +72,39 @@ static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
 	return stages;
 }
 
+static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, CTL_FLUSH);
+}
+
 static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx)
 {
+	trace_dpu_hw_ctl_trigger_start(ctx->pending_flush_mask,
+				       dpu_hw_ctl_get_flush_register(ctx));
 	DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1);
 }
 
 static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx)
 {
+	trace_dpu_hw_ctl_trigger_prepare(ctx->pending_flush_mask,
+					 dpu_hw_ctl_get_flush_register(ctx));
 	DPU_REG_WRITE(&ctx->hw, CTL_PREPARE, 0x1);
 }
 
 static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx)
 {
+	trace_dpu_hw_ctl_clear_pending_flush(ctx->pending_flush_mask,
+				     dpu_hw_ctl_get_flush_register(ctx));
 	ctx->pending_flush_mask = 0x0;
 }
 
 static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
 		u32 flushbits)
 {
+	trace_dpu_hw_ctl_update_pending_flush(flushbits,
+					      ctx->pending_flush_mask);
 	ctx->pending_flush_mask |= flushbits;
 }
 
@@ -103,18 +118,12 @@ static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
 
 static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
 {
-
+	trace_dpu_hw_ctl_trigger_pending_flush(ctx->pending_flush_mask,
+				     dpu_hw_ctl_get_flush_register(ctx));
 	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
 }
 
-static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx)
-{
-	struct dpu_hw_blk_reg_map *c = &ctx->hw;
-
-	return DPU_REG_READ(c, CTL_FLUSH);
-}
-
-static inline uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx,
+static uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx,
 	enum dpu_sspp sspp)
 {
 	uint32_t flushbits = 0;
@@ -169,7 +178,7 @@ static inline uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx,
 	return flushbits;
 }
 
-static inline uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx,
+static uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx,
 	enum dpu_lm lm)
 {
 	uint32_t flushbits = 0;
@@ -202,7 +211,7 @@ static inline uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx,
 	return flushbits;
 }
 
-static inline int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
+static int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
 		u32 *flushbits, enum dpu_intf intf)
 {
 	switch (intf) {
@@ -474,10 +483,7 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
 	ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
 };
 
-static struct dpu_hw_blk_ops dpu_hw_ops = {
-	.start = NULL,
-	.stop = NULL,
-};
+static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 		void __iomem *addr,
@@ -485,7 +491,6 @@ struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 {
 	struct dpu_hw_ctl *c;
 	struct dpu_ctl_cfg *cfg;
-	int rc;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
@@ -504,18 +509,9 @@ struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 	c->mixer_count = m->mixer_count;
 	c->mixer_hw_caps = m->mixer;
 
-	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CTL, idx, &dpu_hw_ops);
-	if (rc) {
-		DPU_ERROR("failed to init hw blk %d\n", rc);
-		goto blk_init_error;
-	}
+	dpu_hw_blk_init(&c->base, DPU_HW_BLK_CTL, idx, &dpu_hw_ops);
 
 	return c;
-
-blk_init_error:
-	kzfree(c);
-
-	return ERR_PTR(rc);
 }
 
 void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
index 9c6bba0ac7c3..f6a83daa385b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -13,7 +13,6 @@
 #include "dpu_hwio.h"
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_intf.h"
-#include "dpu_dbg.h"
 #include "dpu_kms.h"
 
 #define INTF_TIMING_ENGINE_EN           0x000
@@ -265,10 +264,7 @@ static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
 	ops->get_line_count = dpu_hw_intf_get_line_count;
 }
 
-static struct dpu_hw_blk_ops dpu_hw_ops = {
-	.start = NULL,
-	.stop = NULL,
-};
+static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 		void __iomem *addr,
@@ -276,7 +272,6 @@ struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 {
 	struct dpu_hw_intf *c;
 	struct dpu_intf_cfg *cfg;
-	int rc;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
@@ -297,18 +292,9 @@ struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 	c->mdss = m;
 	_setup_intf_ops(&c->ops, c->cap->features);
 
-	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_INTF, idx, &dpu_hw_ops);
-	if (rc) {
-		DPU_ERROR("failed to init hw blk %d\n", rc);
-		goto blk_init_error;
-	}
+	dpu_hw_blk_init(&c->base, DPU_HW_BLK_INTF, idx, &dpu_hw_ops);
 
 	return c;
-
-blk_init_error:
-	kzfree(c);
-
-	return ERR_PTR(rc);
 }
 
 void dpu_hw_intf_destroy(struct dpu_hw_intf *intf)
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 3b77df460dea..a2b0dbc23058 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -92,16 +92,6 @@ 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_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
index acb8dc8acaa5..018df2c3b7ed 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -15,7 +15,6 @@
 #include "dpu_hwio.h"
 #include "dpu_hw_lm.h"
 #include "dpu_hw_mdss.h"
-#include "dpu_dbg.h"
 #include "dpu_kms.h"
 
 #define LM_OP_MODE                        0x00
@@ -64,16 +63,10 @@ static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
 static inline int _stage_offset(struct dpu_hw_mixer *ctx, enum dpu_stage stage)
 {
 	const struct dpu_lm_sub_blks *sblk = ctx->cap->sblk;
-	int rc;
+	if (stage != DPU_STAGE_BASE && stage <= sblk->maxblendstages)
+		return sblk->blendstage_base[stage - DPU_STAGE_0];
 
-	if (stage == DPU_STAGE_BASE)
-		rc = -EINVAL;
-	else if (stage <= sblk->maxblendstages)
-		rc = sblk->blendstage_base[stage - DPU_STAGE_0];
-	else
-		rc = -EINVAL;
-
-	return rc;
+	return -EINVAL;
 }
 
 static void dpu_hw_lm_setup_out(struct dpu_hw_mixer *ctx,
@@ -163,11 +156,6 @@ static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
 	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
 }
 
-static void dpu_hw_lm_gc(struct dpu_hw_mixer *mixer,
-			void *cfg)
-{
-}
-
 static void _setup_mixer_ops(struct dpu_mdss_cfg *m,
 		struct dpu_hw_lm_ops *ops,
 		unsigned long features)
@@ -179,13 +167,9 @@ static void _setup_mixer_ops(struct dpu_mdss_cfg *m,
 		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
 	ops->setup_alpha_out = dpu_hw_lm_setup_color3;
 	ops->setup_border_color = dpu_hw_lm_setup_border_color;
-	ops->setup_gc = dpu_hw_lm_gc;
 };
 
-static struct dpu_hw_blk_ops dpu_hw_ops = {
-	.start = NULL,
-	.stop = NULL,
-};
+static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 		void __iomem *addr,
@@ -193,7 +177,6 @@ struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 {
 	struct dpu_hw_mixer *c;
 	struct dpu_lm_cfg *cfg;
-	int rc;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
@@ -210,18 +193,9 @@ struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 	c->cap = cfg;
 	_setup_mixer_ops(m, &c->ops, c->cap->features);
 
-	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_LM, idx, &dpu_hw_ops);
-	if (rc) {
-		DPU_ERROR("failed to init hw blk %d\n", rc);
-		goto blk_init_error;
-	}
+	dpu_hw_blk_init(&c->base, DPU_HW_BLK_LM, idx, &dpu_hw_ops);
 
 	return c;
-
-blk_init_error:
-	kzfree(c);
-
-	return ERR_PTR(rc);
 }
 
 void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
index 5b036aca8340..6aee839a6a23 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -61,11 +61,6 @@ struct dpu_hw_lm_ops {
 	void (*setup_border_color)(struct dpu_hw_mixer *ctx,
 		struct dpu_mdss_color *color,
 		u8 border_en);
-	/**
-	 * setup_gc : enable/disable gamma correction feature
-	 */
-	void (*setup_gc)(struct dpu_hw_mixer *mixer,
-			void *cfg);
 };
 
 struct dpu_hw_mixer {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
index cc3a623903f4..3bdf47ed1845 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -16,7 +16,6 @@
 #include "dpu_hwio.h"
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_pingpong.h"
-#include "dpu_dbg.h"
 #include "dpu_kms.h"
 #include "dpu_trace.h"
 
@@ -177,7 +176,7 @@ static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp)
 	height = DPU_REG_READ(c, PP_SYNC_CONFIG_HEIGHT) & 0xFFFF;
 
 	if (height < init)
-		goto line_count_exit;
+		return line;
 
 	line = DPU_REG_READ(c, PP_INT_COUNT_VAL) & 0xFFFF;
 
@@ -186,7 +185,6 @@ static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp)
 	else
 		line -= init;
 
-line_count_exit:
 	return line;
 }
 
@@ -201,10 +199,7 @@ static void _setup_pingpong_ops(struct dpu_hw_pingpong_ops *ops,
 	ops->get_line_count = dpu_hw_pp_get_line_count;
 };
 
-static struct dpu_hw_blk_ops dpu_hw_ops = {
-	.start = NULL,
-	.stop = NULL,
-};
+static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 		void __iomem *addr,
@@ -212,7 +207,6 @@ struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 {
 	struct dpu_hw_pingpong *c;
 	struct dpu_pingpong_cfg *cfg;
-	int rc;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
@@ -228,18 +222,9 @@ struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 	c->caps = cfg;
 	_setup_pingpong_ops(&c->ops, c->caps);
 
-	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_PINGPONG, idx, &dpu_hw_ops);
-	if (rc) {
-		DPU_ERROR("failed to init hw blk %d\n", rc);
-		goto blk_init_error;
-	}
+	dpu_hw_blk_init(&c->base, DPU_HW_BLK_PINGPONG, idx, &dpu_hw_ops);
 
 	return c;
-
-blk_init_error:
-	kzfree(c);
-
-	return ERR_PTR(rc);
 }
 
 void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp)
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 3caccd7d6a3e..0e02e43cee14 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -105,16 +105,6 @@ struct dpu_hw_pingpong {
 };
 
 /**
- * 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_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
index c25b52a6b219..e9132bf5166b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -14,7 +14,6 @@
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_lm.h"
 #include "dpu_hw_sspp.h"
-#include "dpu_dbg.h"
 #include "dpu_kms.h"
 
 #define DPU_FETCH_CONFIG_RESET_VALUE   0x00000087
@@ -141,7 +140,7 @@
 /* traffic shaper clock in Hz */
 #define TS_CLK			19200000
 
-static inline int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
+static int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
 		int s_id,
 		u32 *idx)
 {
@@ -662,7 +661,8 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c,
 		test_bit(DPU_SSPP_CSC_10BIT, &features))
 		c->ops.setup_csc = dpu_hw_sspp_setup_csc;
 
-	if (dpu_hw_sspp_multirect_enabled(c->cap))
+	if (test_bit(DPU_SSPP_SMART_DMA_V1, &c->cap->features) ||
+		test_bit(DPU_SSPP_SMART_DMA_V2, &c->cap->features))
 		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
 
 	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) {
@@ -697,10 +697,7 @@ static struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
 	return ERR_PTR(-ENOMEM);
 }
 
-static struct dpu_hw_blk_ops dpu_hw_ops = {
-	.start = NULL,
-	.stop = NULL,
-};
+static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
 		void __iomem *addr, struct dpu_mdss_cfg *catalog,
@@ -708,7 +705,6 @@ struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
 {
 	struct dpu_hw_pipe *hw_pipe;
 	struct dpu_sspp_cfg *cfg;
-	int rc;
 
 	if (!addr || !catalog)
 		return ERR_PTR(-EINVAL);
@@ -730,18 +726,9 @@ struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
 	hw_pipe->cap = cfg;
 	_setup_layer_ops(hw_pipe, hw_pipe->cap->features);
 
-	rc = dpu_hw_blk_init(&hw_pipe->base, DPU_HW_BLK_SSPP, idx, &dpu_hw_ops);
-	if (rc) {
-		DPU_ERROR("failed to init hw blk %d\n", rc);
-		goto blk_init_error;
-	}
+	dpu_hw_blk_init(&hw_pipe->base, DPU_HW_BLK_SSPP, idx, &dpu_hw_ops);
 
 	return hw_pipe;
-
-blk_init_error:
-	kzfree(hw_pipe);
-
-	return ERR_PTR(rc);
 }
 
 void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
index 4d81e5f5ce1b..119b4e1c16be 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -392,16 +392,6 @@ struct dpu_hw_pipe {
 };
 
 /**
- * dpu_hw_pipe - 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_pipe *to_dpu_hw_pipe(struct dpu_hw_blk *hw)
-{
-	return container_of(hw, struct dpu_hw_pipe, base);
-}
-
-/**
  * dpu_hw_sspp_init - initializes the sspp hw driver object.
  * Should be called once before accessing every pipe.
  * @idx:  Pipe index for which driver object is required
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
index b8781256e21b..a041597bb849 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -13,7 +13,6 @@
 #include "dpu_hwio.h"
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_top.h"
-#include "dpu_dbg.h"
 #include "dpu_kms.h"
 
 #define SSPP_SPARE                        0x28
@@ -322,10 +321,7 @@ static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp,
 	return ERR_PTR(-EINVAL);
 }
 
-static struct dpu_hw_blk_ops dpu_hw_ops = {
-	.start = NULL,
-	.stop = NULL,
-};
+static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
 		void __iomem *addr,
@@ -333,7 +329,6 @@ struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
 {
 	struct dpu_hw_mdp *mdp;
 	const struct dpu_mdp_cfg *cfg;
-	int rc;
 
 	if (!addr || !m)
 		return ERR_PTR(-EINVAL);
@@ -355,20 +350,9 @@ struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
 	mdp->caps = cfg;
 	_setup_mdp_ops(&mdp->ops, mdp->caps->features);
 
-	rc = dpu_hw_blk_init(&mdp->base, DPU_HW_BLK_TOP, idx, &dpu_hw_ops);
-	if (rc) {
-		DPU_ERROR("failed to init hw blk %d\n", rc);
-		goto blk_init_error;
-	}
-
-	dpu_dbg_set_dpu_top_offset(mdp->hw.blk_off);
+	dpu_hw_blk_init(&mdp->base, DPU_HW_BLK_TOP, idx, &dpu_hw_ops);
 
 	return mdp;
-
-blk_init_error:
-	kzfree(mdp);
-
-	return ERR_PTR(rc);
 }
 
 void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
index 192e338f20bb..aa21fd834398 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
@@ -161,16 +161,6 @@ struct dpu_hw_mdp {
 };
 
 /**
- * to_dpu_hw_mdp - 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_mdp *to_dpu_hw_mdp(struct dpu_hw_blk *hw)
-{
-	return container_of(hw, struct dpu_hw_mdp, base);
-}
-
-/**
  * dpu_hw_mdptop_init - initializes the top driver for the passed idx
  * @idx:  Interface index for which driver object is required
  * @addr: Mapped register io address of MDP
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
index d43905525f92..38bfd222ed72 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
@@ -13,7 +13,6 @@
 #include "dpu_hwio.h"
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_vbif.h"
-#include "dpu_dbg.h"
 
 #define VBIF_VERSION			0x0000
 #define VBIF_CLK_FORCE_CTRL0		0x0008
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
index b557687b1964..78833c2c27f8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -16,6 +16,8 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 
+#include <drm/drm_print.h>
+
 #include "dpu_io_util.h"
 
 void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk)
@@ -164,7 +166,7 @@ int msm_dss_parse_clock(struct platform_device *pdev,
 						   "clock-names", i,
 						   &clock_name);
 		if (rc) {
-			dev_err(&pdev->dev, "Failed to get clock name for %d\n",
+			DRM_DEV_ERROR(&pdev->dev, "Failed to get clock name for %d\n",
 				i);
 			break;
 		}
@@ -176,13 +178,13 @@ int msm_dss_parse_clock(struct platform_device *pdev,
 
 	rc = msm_dss_get_clk(&pdev->dev, mp->clk_config, num_clk);
 	if (rc) {
-		dev_err(&pdev->dev, "Failed to get clock refs %d\n", rc);
+		DRM_DEV_ERROR(&pdev->dev, "Failed to get clock refs %d\n", rc);
 		goto err;
 	}
 
 	rc = of_clk_set_defaults(pdev->dev.of_node, false);
 	if (rc) {
-		dev_err(&pdev->dev, "Failed to set clock defaults %d\n", rc);
+		DRM_DEV_ERROR(&pdev->dev, "Failed to set clock defaults %d\n", rc);
 		goto err;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
deleted file mode 100644
index d5e6ce0140cf..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
-
-#include <linux/irqdomain.h>
-#include <linux/irq.h>
-#include <linux/kthread.h>
-
-#include "dpu_irq.h"
-#include "dpu_core_irq.h"
-
-irqreturn_t dpu_irq(struct msm_kms *kms)
-{
-	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
-
-	return dpu_core_irq(dpu_kms);
-}
-
-void dpu_irq_preinstall(struct msm_kms *kms)
-{
-	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
-
-	if (!dpu_kms->dev || !dpu_kms->dev->dev) {
-		pr_err("invalid device handles\n");
-		return;
-	}
-
-	dpu_core_irq_preinstall(dpu_kms);
-}
-
-int dpu_irq_postinstall(struct msm_kms *kms)
-{
-	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
-	int rc;
-
-	if (!kms) {
-		DPU_ERROR("invalid parameters\n");
-		return -EINVAL;
-	}
-
-	rc = dpu_core_irq_postinstall(dpu_kms);
-
-	return rc;
-}
-
-void dpu_irq_uninstall(struct msm_kms *kms)
-{
-	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
-
-	if (!kms) {
-		DPU_ERROR("invalid parameters\n");
-		return;
-	}
-
-	dpu_core_irq_uninstall(dpu_kms);
-}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
deleted file mode 100644
index 3e147f7176e2..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __DPU_IRQ_H__
-#define __DPU_IRQ_H__
-
-#include <linux/kernel.h>
-#include <linux/irqdomain.h>
-
-#include "msm_kms.h"
-
-/**
- * dpu_irq_controller - define MDSS level interrupt controller context
- * @enabled_mask:	enable status of MDSS level interrupt
- * @domain:		interrupt domain of this controller
- */
-struct dpu_irq_controller {
-	unsigned long enabled_mask;
-	struct irq_domain *domain;
-};
-
-/**
- * dpu_irq_preinstall - perform pre-installation of MDSS IRQ handler
- * @kms:		pointer to kms context
- * @return:		none
- */
-void dpu_irq_preinstall(struct msm_kms *kms);
-
-/**
- * dpu_irq_postinstall - perform post-installation of MDSS IRQ handler
- * @kms:		pointer to kms context
- * @return:		0 if success; error code otherwise
- */
-int dpu_irq_postinstall(struct msm_kms *kms);
-
-/**
- * dpu_irq_uninstall - uninstall MDSS IRQ handler
- * @drm_dev:		pointer to kms context
- * @return:		none
- */
-void dpu_irq_uninstall(struct msm_kms *kms);
-
-/**
- * dpu_irq - MDSS level IRQ handler
- * @kms:		pointer to kms context
- * @return:		interrupt handling status
- */
-irqreturn_t dpu_irq(struct msm_kms *kms);
-
-#endif /* __DPU_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 0a683e65a9f3..4d67b3c96702 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -81,7 +81,7 @@ static int _dpu_danger_signal_status(struct seq_file *s,
 	struct dpu_danger_safe_status status;
 	int i;
 
-	if (!kms || !kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+	if (!kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
 		DPU_ERROR("invalid arg(s)\n");
 		return 0;
 	}
@@ -138,46 +138,29 @@ static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v)
 }
 DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_safe_stats);
 
-static void dpu_debugfs_danger_destroy(struct dpu_kms *dpu_kms)
-{
-	debugfs_remove_recursive(dpu_kms->debugfs_danger);
-	dpu_kms->debugfs_danger = NULL;
-}
-
-static int dpu_debugfs_danger_init(struct dpu_kms *dpu_kms,
+static void dpu_debugfs_danger_init(struct dpu_kms *dpu_kms,
 		struct dentry *parent)
 {
-	dpu_kms->debugfs_danger = debugfs_create_dir("danger",
-			parent);
-	if (!dpu_kms->debugfs_danger) {
-		DPU_ERROR("failed to create danger debugfs\n");
-		return -EINVAL;
-	}
+	struct dentry *entry = debugfs_create_dir("danger", parent);
+	if (IS_ERR_OR_NULL(entry))
+		return;
 
-	debugfs_create_file("danger_status", 0600, dpu_kms->debugfs_danger,
+	debugfs_create_file("danger_status", 0600, entry,
 			dpu_kms, &dpu_debugfs_danger_stats_fops);
-	debugfs_create_file("safe_status", 0600, dpu_kms->debugfs_danger,
+	debugfs_create_file("safe_status", 0600, entry,
 			dpu_kms, &dpu_debugfs_safe_stats_fops);
-
-	return 0;
 }
 
 static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
 {
-	struct dpu_debugfs_regset32 *regset;
-	struct dpu_kms *dpu_kms;
+	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 (!s || !s->private)
-		return 0;
-
-	regset = s->private;
-
-	dpu_kms = regset->dpu_kms;
-	if (!dpu_kms || !dpu_kms->mmio)
+	if (!dpu_kms->mmio)
 		return 0;
 
 	dev = dpu_kms->dev;
@@ -250,57 +233,24 @@ void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
 
 static int _dpu_debugfs_init(struct dpu_kms *dpu_kms)
 {
-	void *p;
-	int rc;
-
-	p = dpu_hw_util_get_log_mask_ptr();
+	void *p = dpu_hw_util_get_log_mask_ptr();
+	struct dentry *entry;
 
-	if (!dpu_kms || !p)
+	if (!p)
 		return -EINVAL;
 
-	dpu_kms->debugfs_root = debugfs_create_dir("debug",
-					   dpu_kms->dev->primary->debugfs_root);
-	if (IS_ERR_OR_NULL(dpu_kms->debugfs_root)) {
-		DRM_ERROR("debugfs create_dir failed %ld\n",
-			  PTR_ERR(dpu_kms->debugfs_root));
-		return PTR_ERR(dpu_kms->debugfs_root);
-	}
-
-	rc = dpu_dbg_debugfs_register(dpu_kms->debugfs_root);
-	if (rc) {
-		DRM_ERROR("failed to reg dpu dbg debugfs: %d\n", rc);
-		return rc;
-	}
+	entry = debugfs_create_dir("debug", dpu_kms->dev->primary->debugfs_root);
+	if (IS_ERR_OR_NULL(entry))
+		return -ENODEV;
 
 	/* allow root to be NULL */
-	debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, dpu_kms->debugfs_root, p);
-
-	(void) dpu_debugfs_danger_init(dpu_kms, dpu_kms->debugfs_root);
-	(void) dpu_debugfs_vbif_init(dpu_kms, dpu_kms->debugfs_root);
-	(void) dpu_debugfs_core_irq_init(dpu_kms, dpu_kms->debugfs_root);
-
-	rc = dpu_core_perf_debugfs_init(&dpu_kms->perf, dpu_kms->debugfs_root);
-	if (rc) {
-		DPU_ERROR("failed to init perf %d\n", rc);
-		return rc;
-	}
+	debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, entry, p);
 
-	return 0;
-}
+	dpu_debugfs_danger_init(dpu_kms, entry);
+	dpu_debugfs_vbif_init(dpu_kms, entry);
+	dpu_debugfs_core_irq_init(dpu_kms, entry);
 
-static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
-{
-	/* don't need to NULL check debugfs_root */
-	if (dpu_kms) {
-		dpu_debugfs_vbif_destroy(dpu_kms);
-		dpu_debugfs_danger_destroy(dpu_kms);
-		dpu_debugfs_core_irq_destroy(dpu_kms);
-		debugfs_remove_recursive(dpu_kms->debugfs_root);
-	}
-}
-#else
-static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
-{
+	return dpu_core_perf_debugfs_init(dpu_kms, entry);
 }
 #endif
 
@@ -320,7 +270,10 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 	struct dpu_kms *dpu_kms;
 	struct msm_drm_private *priv;
 	struct drm_device *dev;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
 	struct drm_encoder *encoder;
+	int i;
 
 	if (!kms)
 		return;
@@ -332,9 +285,13 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 	priv = dev->dev_private;
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
-		if (encoder->crtc != NULL)
+	/* Call prepare_commit for all affected encoders */
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		drm_for_each_encoder_mask(encoder, crtc->dev,
+					  crtc_state->encoder_mask) {
 			dpu_encoder_prepare_commit(encoder);
+		}
+	}
 }
 
 /*
@@ -344,15 +301,20 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 void dpu_kms_encoder_enable(struct drm_encoder *encoder)
 {
 	const struct drm_encoder_helper_funcs *funcs = encoder->helper_private;
-	struct drm_crtc *crtc = encoder->crtc;
+	struct drm_device *dev = encoder->dev;
+	struct drm_crtc *crtc;
 
 	/* Forward this enable call to the commit hook */
 	if (funcs && funcs->commit)
 		funcs->commit(encoder);
 
-	if (crtc && crtc->state->active) {
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	drm_for_each_crtc(crtc, dev) {
+		if (!(crtc->state->encoder_mask & drm_encoder_mask(encoder)))
+			continue;
+
 		trace_dpu_kms_enc_enable(DRMID(crtc));
-		dpu_crtc_commit_kickoff(crtc);
+		dpu_crtc_commit_kickoff(crtc, false);
 	}
 }
 
@@ -369,7 +331,8 @@ static void dpu_kms_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 
 		if (crtc->state->active) {
 			trace_dpu_kms_commit(DRMID(crtc));
-			dpu_crtc_commit_kickoff(crtc);
+			dpu_crtc_commit_kickoff(crtc,
+						state->legacy_cursor_update);
 		}
 	}
 }
@@ -613,22 +576,7 @@ fail:
 #ifdef CONFIG_DEBUG_FS
 static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
 {
-	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
-	struct drm_device *dev;
-	int rc;
-
-	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
-		DPU_ERROR("invalid dpu_kms\n");
-		return -EINVAL;
-	}
-
-	dev = dpu_kms->dev;
-
-	rc = _dpu_debugfs_init(dpu_kms);
-	if (rc)
-		DPU_ERROR("dpu_debugfs init failed: %d\n", rc);
-
-	return rc;
+	return _dpu_debugfs_init(to_dpu_kms(kms));
 }
 #endif
 
@@ -651,12 +599,7 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 		dpu_hw_intr_destroy(dpu_kms->hw_intr);
 	dpu_kms->hw_intr = NULL;
 
-	if (dpu_kms->power_event)
-		dpu_power_handle_unregister_event(
-				&dpu_kms->phandle, dpu_kms->power_event);
-
 	/* safe to call these more than once during shutdown */
-	_dpu_debugfs_destroy(dpu_kms);
 	_dpu_kms_mmu_destroy(dpu_kms);
 
 	if (dpu_kms->catalog) {
@@ -676,11 +619,6 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 		dpu_hw_catalog_deinit(dpu_kms->catalog);
 	dpu_kms->catalog = NULL;
 
-	if (dpu_kms->core_client)
-		dpu_power_client_destroy(&dpu_kms->phandle,
-			dpu_kms->core_client);
-	dpu_kms->core_client = NULL;
-
 	if (dpu_kms->vbif[VBIF_NRT])
 		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_NRT]);
 	dpu_kms->vbif[VBIF_NRT] = NULL;
@@ -705,131 +643,9 @@ static void dpu_kms_destroy(struct msm_kms *kms)
 
 	dpu_kms = to_dpu_kms(kms);
 
-	dpu_dbg_destroy();
 	_dpu_kms_hw_destroy(dpu_kms);
 }
 
-static int dpu_kms_pm_suspend(struct device *dev)
-{
-	struct drm_device *ddev;
-	struct drm_modeset_acquire_ctx ctx;
-	struct drm_atomic_state *state;
-	struct dpu_kms *dpu_kms;
-	int ret = 0, num_crtcs = 0;
-
-	if (!dev)
-		return -EINVAL;
-
-	ddev = dev_get_drvdata(dev);
-	if (!ddev || !ddev_to_msm_kms(ddev))
-		return -EINVAL;
-
-	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
-
-	/* disable hot-plug polling */
-	drm_kms_helper_poll_disable(ddev);
-
-	/* acquire modeset lock(s) */
-	drm_modeset_acquire_init(&ctx, 0);
-
-retry:
-	DPU_ATRACE_BEGIN("kms_pm_suspend");
-
-	ret = drm_modeset_lock_all_ctx(ddev, &ctx);
-	if (ret)
-		goto unlock;
-
-	/* save current state for resume */
-	if (dpu_kms->suspend_state)
-		drm_atomic_state_put(dpu_kms->suspend_state);
-	dpu_kms->suspend_state = drm_atomic_helper_duplicate_state(ddev, &ctx);
-	if (IS_ERR_OR_NULL(dpu_kms->suspend_state)) {
-		DRM_ERROR("failed to back up suspend state\n");
-		dpu_kms->suspend_state = NULL;
-		goto unlock;
-	}
-
-	/* create atomic state to disable all CRTCs */
-	state = drm_atomic_state_alloc(ddev);
-	if (IS_ERR_OR_NULL(state)) {
-		DRM_ERROR("failed to allocate crtc disable state\n");
-		goto unlock;
-	}
-
-	state->acquire_ctx = &ctx;
-
-	/* check for nothing to do */
-	if (num_crtcs == 0) {
-		DRM_DEBUG("all crtcs are already in the off state\n");
-		drm_atomic_state_put(state);
-		goto suspended;
-	}
-
-	/* commit the "disable all" state */
-	ret = drm_atomic_commit(state);
-	if (ret < 0) {
-		DRM_ERROR("failed to disable crtcs, %d\n", ret);
-		drm_atomic_state_put(state);
-		goto unlock;
-	}
-
-suspended:
-	dpu_kms->suspend_block = true;
-
-unlock:
-	if (ret == -EDEADLK) {
-		drm_modeset_backoff(&ctx);
-		goto retry;
-	}
-	drm_modeset_drop_locks(&ctx);
-	drm_modeset_acquire_fini(&ctx);
-
-	DPU_ATRACE_END("kms_pm_suspend");
-	return 0;
-}
-
-static int dpu_kms_pm_resume(struct device *dev)
-{
-	struct drm_device *ddev;
-	struct dpu_kms *dpu_kms;
-	int ret;
-
-	if (!dev)
-		return -EINVAL;
-
-	ddev = dev_get_drvdata(dev);
-	if (!ddev || !ddev_to_msm_kms(ddev))
-		return -EINVAL;
-
-	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
-
-	DPU_ATRACE_BEGIN("kms_pm_resume");
-
-	drm_mode_config_reset(ddev);
-
-	drm_modeset_lock_all(ddev);
-
-	dpu_kms->suspend_block = false;
-
-	if (dpu_kms->suspend_state) {
-		dpu_kms->suspend_state->acquire_ctx =
-			ddev->mode_config.acquire_ctx;
-		ret = drm_atomic_commit(dpu_kms->suspend_state);
-		if (ret < 0) {
-			DRM_ERROR("failed to restore state, %d\n", ret);
-			drm_atomic_state_put(dpu_kms->suspend_state);
-		}
-		dpu_kms->suspend_state = NULL;
-	}
-	drm_modeset_unlock_all(ddev);
-
-	/* enable hot-plug polling */
-	drm_kms_helper_poll_enable(ddev);
-
-	DPU_ATRACE_END("kms_pm_resume");
-	return 0;
-}
-
 static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
 				 struct drm_encoder *encoder,
 				 bool cmd_mode)
@@ -858,10 +674,30 @@ static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
 			encoder->base.id, rc);
 }
 
+static irqreturn_t dpu_irq(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	return dpu_core_irq(dpu_kms);
+}
+
+static void dpu_irq_preinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	dpu_core_irq_preinstall(dpu_kms);
+}
+
+static void dpu_irq_uninstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	dpu_core_irq_uninstall(dpu_kms);
+}
+
 static const struct msm_kms_funcs kms_funcs = {
 	.hw_init         = dpu_kms_hw_init,
 	.irq_preinstall  = dpu_irq_preinstall,
-	.irq_postinstall = dpu_irq_postinstall,
 	.irq_uninstall   = dpu_irq_uninstall,
 	.irq             = dpu_irq,
 	.prepare_commit  = dpu_kms_prepare_commit,
@@ -873,8 +709,6 @@ static const struct msm_kms_funcs kms_funcs = {
 	.check_modified_format = dpu_format_check_modified_format,
 	.get_format      = dpu_get_msm_format,
 	.round_pixclk    = dpu_kms_round_pixclk,
-	.pm_suspend      = dpu_kms_pm_suspend,
-	.pm_resume       = dpu_kms_pm_resume,
 	.destroy         = dpu_kms_destroy,
 	.set_encoder_mode = _dpu_kms_set_encoder_mode,
 #ifdef CONFIG_DEBUG_FS
@@ -882,12 +716,6 @@ static const struct msm_kms_funcs kms_funcs = {
 #endif
 };
 
-/* the caller api needs to turn on clock before calling it */
-static inline void _dpu_kms_core_hw_rev_init(struct dpu_kms *dpu_kms)
-{
-	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
-}
-
 static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
 {
 	struct msm_mmu *mmu;
@@ -911,6 +739,9 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
 	if (!domain)
 		return 0;
 
+	domain->geometry.aperture_start = 0x1000;
+	domain->geometry.aperture_end = 0xffffffff;
+
 	aspace = msm_gem_address_space_create(dpu_kms->dev->dev,
 			domain, "dpu1");
 	if (IS_ERR(aspace)) {
@@ -960,16 +791,6 @@ u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name)
 	return clk_get_rate(clk->clk);
 }
 
-static void dpu_kms_handle_power_event(u32 event_type, void *usr)
-{
-	struct dpu_kms *dpu_kms = usr;
-
-	if (!dpu_kms)
-		return;
-
-	dpu_vbif_init_memtypes(dpu_kms);
-}
-
 static int dpu_kms_hw_init(struct msm_kms *kms)
 {
 	struct dpu_kms *dpu_kms;
@@ -979,26 +800,20 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	if (!kms) {
 		DPU_ERROR("invalid kms\n");
-		goto end;
+		return rc;
 	}
 
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
 	if (!dev) {
 		DPU_ERROR("invalid device\n");
-		goto end;
-	}
-
-	rc = dpu_dbg_init(&dpu_kms->pdev->dev);
-	if (rc) {
-		DRM_ERROR("failed to init dpu dbg: %d\n", rc);
-		goto end;
+		return rc;
 	}
 
 	priv = dev->dev_private;
 	if (!priv) {
 		DPU_ERROR("invalid private data\n");
-		goto dbg_destroy;
+		return rc;
 	}
 
 	dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp", "mdp");
@@ -1036,20 +851,9 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		dpu_kms->reg_dma_len = dpu_iomap_size(dpu_kms->pdev, "regdma");
 	}
 
-	dpu_kms->core_client = dpu_power_client_create(&dpu_kms->phandle,
-					"core");
-	if (IS_ERR_OR_NULL(dpu_kms->core_client)) {
-		rc = PTR_ERR(dpu_kms->core_client);
-		if (!dpu_kms->core_client)
-			rc = -EINVAL;
-		DPU_ERROR("dpu power client create failed: %d\n", rc);
-		dpu_kms->core_client = NULL;
-		goto error;
-	}
-
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 
-	_dpu_kms_core_hw_rev_init(dpu_kms);
+	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
 
 	pr_info("dpu hardware revision:0x%x\n", dpu_kms->core_rev);
 
@@ -1063,8 +867,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		goto power_error;
 	}
 
-	dpu_dbg_init_dbg_buses(dpu_kms->core_rev);
-
 	/*
 	 * Now we need to read the HW catalog and initialize resources such as
 	 * clocks, regulators, GDSC/MMAGIC, ioremap the register ranges etc
@@ -1110,7 +912,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 	}
 
 	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog,
-			&dpu_kms->phandle,
 			_dpu_kms_get_clk(dpu_kms, "core"));
 	if (rc) {
 		DPU_ERROR("failed to init perf %d\n", rc);
@@ -1151,13 +952,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 	 */
 	dev->mode_config.allow_fb_modifiers = true;
 
-	/*
-	 * Handle (re)initializations during power enable
-	 */
-	dpu_kms_handle_power_event(DPU_POWER_EVENT_ENABLE, dpu_kms);
-	dpu_kms->power_event = dpu_power_handle_register_event(
-			&dpu_kms->phandle, DPU_POWER_EVENT_ENABLE,
-			dpu_kms_handle_power_event, dpu_kms, "kms");
+	dpu_vbif_init_memtypes(dpu_kms);
 
 	pm_runtime_put_sync(&dpu_kms->pdev->dev);
 
@@ -1171,9 +966,7 @@ power_error:
 	pm_runtime_put_sync(&dpu_kms->pdev->dev);
 error:
 	_dpu_kms_hw_destroy(dpu_kms);
-dbg_destroy:
-	dpu_dbg_destroy();
-end:
+
 	return rc;
 }
 
@@ -1221,8 +1014,6 @@ static int dpu_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	dpu_power_resource_init(pdev, &dpu_kms->phandle);
-
 	platform_set_drvdata(pdev, dpu_kms);
 
 	msm_kms_init(&dpu_kms->base, &kms_funcs);
@@ -1242,7 +1033,6 @@ static void dpu_unbind(struct device *dev, struct device *master, void *data)
 	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
 	struct dss_module_power *mp = &dpu_kms->mp;
 
-	dpu_power_resource_deinit(pdev, &dpu_kms->phandle);
 	msm_dss_put_clk(mp->clk_config, mp->num_clk);
 	devm_kfree(&pdev->dev, mp->clk_config);
 	mp->num_clk = 0;
@@ -1278,19 +1068,13 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev)
 	ddev = dpu_kms->dev;
 	if (!ddev) {
 		DPU_ERROR("invalid drm_device\n");
-		goto exit;
+		return rc;
 	}
 
-	rc = dpu_power_resource_enable(&dpu_kms->phandle,
-			dpu_kms->core_client, false);
-	if (rc)
-		DPU_ERROR("resource disable failed: %d\n", rc);
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
 	if (rc)
 		DPU_ERROR("clock disable failed rc:%d\n", rc);
 
-exit:
 	return rc;
 }
 
@@ -1299,27 +1083,27 @@ static int __maybe_unused dpu_runtime_resume(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_encoder *encoder;
 	struct drm_device *ddev;
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
 	if (!ddev) {
 		DPU_ERROR("invalid drm_device\n");
-		goto exit;
+		return rc;
 	}
 
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (rc) {
 		DPU_ERROR("clock enable failed rc:%d\n", rc);
-		goto exit;
+		return rc;
 	}
 
-	rc = dpu_power_resource_enable(&dpu_kms->phandle,
-			dpu_kms->core_client, true);
-	if (rc)
-		DPU_ERROR("resource enable failed: %d\n", rc);
+	dpu_vbif_init_memtypes(dpu_kms);
+
+	drm_for_each_encoder(encoder, ddev)
+		dpu_encoder_virt_runtime_resume(encoder);
 
-exit:
 	return rc;
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index 66d466628e2b..ac75cfc267f4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -23,15 +23,13 @@
 #include "msm_kms.h"
 #include "msm_mmu.h"
 #include "msm_gem.h"
-#include "dpu_dbg.h"
 #include "dpu_hw_catalog.h"
 #include "dpu_hw_ctl.h"
 #include "dpu_hw_lm.h"
 #include "dpu_hw_interrupts.h"
 #include "dpu_hw_top.h"
+#include "dpu_io_util.h"
 #include "dpu_rm.h"
-#include "dpu_power_handle.h"
-#include "dpu_irq.h"
 #include "dpu_core_perf.h"
 
 #define DRMID(x) ((x) ? (x)->base.id : -1)
@@ -104,7 +102,6 @@ struct dpu_irq {
 	atomic_t *enable_counts;
 	atomic_t *irq_counts;
 	spinlock_t cb_lock;
-	struct dentry *debugfs_file;
 };
 
 struct dpu_kms {
@@ -113,15 +110,6 @@ struct dpu_kms {
 	int core_rev;
 	struct dpu_mdss_cfg *catalog;
 
-	struct dpu_power_handle phandle;
-	struct dpu_power_client *core_client;
-	struct dpu_power_event *power_event;
-
-	/* directory entry for debugfs */
-	struct dentry *debugfs_root;
-	struct dentry *debugfs_danger;
-	struct dentry *debugfs_vbif;
-
 	/* io/register spaces: */
 	void __iomem *mmio, *vbif[VBIF_MAX], *reg_dma;
 	unsigned long mmio_len, vbif_len[VBIF_MAX], reg_dma_len;
@@ -135,10 +123,6 @@ struct dpu_kms {
 
 	struct dpu_core_perf perf;
 
-	/* saved atomic state during system suspend */
-	struct drm_atomic_state *suspend_state;
-	bool suspend_block;
-
 	struct dpu_rm rm;
 	bool rm_init;
 
@@ -164,33 +148,6 @@ struct vsync_info {
 		((struct msm_drm_private *)((D)->dev_private))->kms : NULL)
 
 /**
- * dpu_kms_is_suspend_state - whether or not the system is pm suspended
- * @dev: Pointer to drm device
- * Return: Suspend status
- */
-static inline bool dpu_kms_is_suspend_state(struct drm_device *dev)
-{
-	if (!ddev_to_msm_kms(dev))
-		return false;
-
-	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_state != NULL;
-}
-
-/**
- * dpu_kms_is_suspend_blocked - whether or not commits are blocked due to pm
- *				suspend status
- * @dev: Pointer to drm device
- * Return: True if commits should be rejected due to pm suspend
- */
-static inline bool dpu_kms_is_suspend_blocked(struct drm_device *dev)
-{
-	if (!dpu_kms_is_suspend_state(dev))
-		return false;
-
-	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_block;
-}
-
-/**
  * Debugfs functions - extra helper functions for debugfs support
  *
  * Main debugfs documentation is located at,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
index 2235ef8129f4..cb307a2abf06 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -9,6 +9,11 @@
 
 #define HW_INTR_STATUS			0x0010
 
+struct dpu_irq_controller {
+	unsigned long enabled_mask;
+	struct irq_domain *domain;
+};
+
 struct dpu_mdss {
 	struct msm_mdss base;
 	void __iomem *mmio;
@@ -115,13 +120,12 @@ static int _dpu_mdss_irq_domain_add(struct dpu_mdss *dpu_mdss)
 	return 0;
 }
 
-static int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
+static void _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
 {
 	if (dpu_mdss->irq_controller.domain) {
 		irq_domain_remove(dpu_mdss->irq_controller.domain);
 		dpu_mdss->irq_controller.domain = NULL;
 	}
-	return 0;
 }
 static int dpu_mdss_enable(struct msm_mdss *mdss)
 {
@@ -156,18 +160,16 @@ static void dpu_mdss_destroy(struct drm_device *dev)
 	struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss);
 	struct dss_module_power *mp = &dpu_mdss->mp;
 
+	pm_runtime_suspend(dev->dev);
+	pm_runtime_disable(dev->dev);
 	_dpu_mdss_irq_domain_fini(dpu_mdss);
-
 	free_irq(platform_get_irq(pdev, 0), dpu_mdss);
-
 	msm_dss_put_clk(mp->clk_config, mp->num_clk);
 	devm_kfree(&pdev->dev, mp->clk_config);
 
 	if (dpu_mdss->mmio)
 		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
 	dpu_mdss->mmio = NULL;
-
-	pm_runtime_disable(dev->dev);
 	priv->mdss = NULL;
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index d77a8cb15404..fd75870eb17f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -137,7 +137,7 @@ static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane)
  * @src_wdith:		width of source buffer
  * Return: fill level corresponding to the source buffer/format or 0 if error
  */
-static inline int _dpu_plane_calc_fill_level(struct drm_plane *plane,
+static int _dpu_plane_calc_fill_level(struct drm_plane *plane,
 		const struct dpu_format *fmt, u32 src_width)
 {
 	struct dpu_plane *pdpu, *tmp;
@@ -430,24 +430,14 @@ static void _dpu_plane_set_qos_remap(struct drm_plane *plane)
 	dpu_vbif_set_qos_remap(dpu_kms, &qos_params);
 }
 
-/**
- * _dpu_plane_get_aspace: gets the address space
- */
-static inline struct msm_gem_address_space *_dpu_plane_get_aspace(
-		struct dpu_plane *pdpu)
-{
-	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
-
-	return kms->base.aspace;
-}
-
-static inline void _dpu_plane_set_scanout(struct drm_plane *plane,
+static void _dpu_plane_set_scanout(struct drm_plane *plane,
 		struct dpu_plane_state *pstate,
 		struct dpu_hw_pipe_cfg *pipe_cfg,
 		struct drm_framebuffer *fb)
 {
 	struct dpu_plane *pdpu = to_dpu_plane(plane);
-	struct msm_gem_address_space *aspace = _dpu_plane_get_aspace(pdpu);
+	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
+	struct msm_gem_address_space *aspace = kms->base.aspace;
 	int ret;
 
 	ret = dpu_format_populate_layout(aspace, fb, &pipe_cfg->layout);
@@ -525,7 +515,7 @@ static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
 	scale_cfg->enable = 1;
 }
 
-static inline void _dpu_plane_setup_csc(struct dpu_plane *pdpu)
+static void _dpu_plane_setup_csc(struct dpu_plane *pdpu)
 {
 	static const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L = {
 		{
@@ -801,7 +791,7 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_gem_object *obj;
 	struct msm_gem_object *msm_obj;
 	struct dma_fence *fence;
-	struct msm_gem_address_space *aspace = _dpu_plane_get_aspace(pdpu);
+	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
 	int ret;
 
 	if (!new_state->fb)
@@ -810,7 +800,7 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
 	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", fb->base.id);
 
 	/* cache aspace */
-	pstate->aspace = aspace;
+	pstate->aspace = kms->base.aspace;
 
 	/*
 	 * TODO: Need to sort out the msm_framebuffer_prepare() call below so
@@ -1191,19 +1181,8 @@ static void dpu_plane_destroy(struct drm_plane *plane)
 static void dpu_plane_destroy_state(struct drm_plane *plane,
 		struct drm_plane_state *state)
 {
-	struct dpu_plane_state *pstate;
-
-	if (!plane || !state) {
-		DPU_ERROR("invalid arg(s), plane %d state %d\n",
-				plane != 0, state != 0);
-		return;
-	}
-
-	pstate = to_dpu_plane_state(state);
-
 	__drm_atomic_helper_plane_destroy_state(state);
-
-	kfree(pstate);
+	kfree(to_dpu_plane_state(state));
 }
 
 static struct drm_plane_state *
@@ -1273,26 +1252,12 @@ static ssize_t _dpu_plane_danger_read(struct file *file,
 			char __user *buff, size_t count, loff_t *ppos)
 {
 	struct dpu_kms *kms = file->private_data;
-	struct dpu_mdss_cfg *cfg = kms->catalog;
-	int len = 0;
-	char buf[40] = {'\0'};
-
-	if (!cfg)
-		return -ENODEV;
+	int len;
+	char buf[40];
 
-	if (*ppos)
-		return 0; /* the end */
-
-	len = snprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl);
-	if (len < 0 || len >= sizeof(buf))
-		return 0;
+	len = scnprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl);
 
-	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
-		return -EFAULT;
-
-	*ppos += len;   /* increase offset */
-
-	return len;
+	return simple_read_from_buffer(buff, count, ppos, buf, len);
 }
 
 static void _dpu_plane_set_danger_state(struct dpu_kms *kms, bool enable)
@@ -1322,23 +1287,12 @@ static ssize_t _dpu_plane_danger_write(struct file *file,
 		    const char __user *user_buf, size_t count, loff_t *ppos)
 {
 	struct dpu_kms *kms = file->private_data;
-	struct dpu_mdss_cfg *cfg = kms->catalog;
 	int disable_panic;
-	char buf[10];
-
-	if (!cfg)
-		return -EFAULT;
-
-	if (count >= sizeof(buf))
-		return -EFAULT;
-
-	if (copy_from_user(buf, user_buf, count))
-		return -EFAULT;
-
-	buf[count] = 0;	/* end of string */
+	int ret;
 
-	if (kstrtoint(buf, 0, &disable_panic))
-		return -EFAULT;
+	ret = kstrtouint_from_user(user_buf, count, 0, &disable_panic);
+	if (ret)
+		return ret;
 
 	if (disable_panic) {
 		/* Disable panic signal for all active pipes */
@@ -1363,33 +1317,10 @@ static const struct file_operations dpu_plane_danger_enable = {
 
 static int _dpu_plane_init_debugfs(struct drm_plane *plane)
 {
-	struct dpu_plane *pdpu;
-	struct dpu_kms *kms;
-	struct msm_drm_private *priv;
-	const struct dpu_sspp_sub_blks *sblk = 0;
-	const struct dpu_sspp_cfg *cfg = 0;
-
-	if (!plane || !plane->dev) {
-		DPU_ERROR("invalid arguments\n");
-		return -EINVAL;
-	}
-
-	priv = plane->dev->dev_private;
-	if (!priv || !priv->kms) {
-		DPU_ERROR("invalid KMS reference\n");
-		return -EINVAL;
-	}
-
-	kms = to_dpu_kms(priv->kms);
-	pdpu = to_dpu_plane(plane);
-
-	if (pdpu && pdpu->pipe_hw)
-		cfg = pdpu->pipe_hw->cap;
-	if (cfg)
-		sblk = cfg->sblk;
-
-	if (!sblk)
-		return 0;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_kms *kms = _dpu_plane_get_kms(plane);
+	const struct dpu_sspp_cfg *cfg = pdpu->pipe_hw->cap;
+	const struct dpu_sspp_sub_blks *sblk = cfg->sblk;
 
 	/* create overall sub-directory for the pipe */
 	pdpu->debugfs_root =
@@ -1460,25 +1391,11 @@ static int _dpu_plane_init_debugfs(struct drm_plane *plane)
 
 	return 0;
 }
-
-static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
-{
-	struct dpu_plane *pdpu;
-
-	if (!plane)
-		return;
-	pdpu = to_dpu_plane(plane);
-
-	debugfs_remove_recursive(pdpu->debugfs_root);
-}
 #else
 static int _dpu_plane_init_debugfs(struct drm_plane *plane)
 {
 	return 0;
 }
-static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
-{
-}
 #endif
 
 static int dpu_plane_late_register(struct drm_plane *plane)
@@ -1488,7 +1405,9 @@ static int dpu_plane_late_register(struct drm_plane *plane)
 
 static void dpu_plane_early_unregister(struct drm_plane *plane)
 {
-	_dpu_plane_destroy_debugfs(plane);
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+
+	debugfs_remove_recursive(pdpu->debugfs_root);
 }
 
 static const struct drm_plane_funcs dpu_plane_funcs = {
@@ -1537,7 +1456,7 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev,
 	if (!pdpu) {
 		DPU_ERROR("[%u]failed to allocate local plane struct\n", pipe);
 		ret = -ENOMEM;
-		goto exit;
+		return ERR_PTR(ret);
 	}
 
 	/* cache local stuff for later */
@@ -1623,6 +1542,5 @@ clean_sspp:
 		dpu_hw_sspp_destroy(pdpu->pipe_hw);
 clean_plane:
 	kfree(pdpu);
-exit:
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
deleted file mode 100644
index fc14116789f2..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
+++ /dev/null
@@ -1,240 +0,0 @@
-/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#define pr_fmt(fmt)	"[drm:%s:%d]: " fmt, __func__, __LINE__
-
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/string.h>
-#include <linux/of_address.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/of_platform.h>
-
-#include "dpu_power_handle.h"
-#include "dpu_trace.h"
-
-static const char *data_bus_name[DPU_POWER_HANDLE_DBUS_ID_MAX] = {
-	[DPU_POWER_HANDLE_DBUS_ID_MNOC] = "qcom,dpu-data-bus",
-	[DPU_POWER_HANDLE_DBUS_ID_LLCC] = "qcom,dpu-llcc-bus",
-	[DPU_POWER_HANDLE_DBUS_ID_EBI] = "qcom,dpu-ebi-bus",
-};
-
-const char *dpu_power_handle_get_dbus_name(u32 bus_id)
-{
-	if (bus_id < DPU_POWER_HANDLE_DBUS_ID_MAX)
-		return data_bus_name[bus_id];
-
-	return NULL;
-}
-
-static void dpu_power_event_trigger_locked(struct dpu_power_handle *phandle,
-		u32 event_type)
-{
-	struct dpu_power_event *event;
-
-	list_for_each_entry(event, &phandle->event_list, list) {
-		if (event->event_type & event_type)
-			event->cb_fnc(event_type, event->usr);
-	}
-}
-
-struct dpu_power_client *dpu_power_client_create(
-	struct dpu_power_handle *phandle, char *client_name)
-{
-	struct dpu_power_client *client;
-	static u32 id;
-
-	if (!client_name || !phandle) {
-		pr_err("client name is null or invalid power data\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	client = kzalloc(sizeof(struct dpu_power_client), GFP_KERNEL);
-	if (!client)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_lock(&phandle->phandle_lock);
-	strlcpy(client->name, client_name, MAX_CLIENT_NAME_LEN);
-	client->usecase_ndx = VOTE_INDEX_DISABLE;
-	client->id = id;
-	client->active = true;
-	pr_debug("client %s created:%pK id :%d\n", client_name,
-		client, id);
-	id++;
-	list_add(&client->list, &phandle->power_client_clist);
-	mutex_unlock(&phandle->phandle_lock);
-
-	return client;
-}
-
-void dpu_power_client_destroy(struct dpu_power_handle *phandle,
-	struct dpu_power_client *client)
-{
-	if (!client  || !phandle) {
-		pr_err("reg bus vote: invalid client handle\n");
-	} else if (!client->active) {
-		pr_err("dpu power deinit already done\n");
-		kfree(client);
-	} else {
-		pr_debug("bus vote client %s destroyed:%pK id:%u\n",
-			client->name, client, client->id);
-		mutex_lock(&phandle->phandle_lock);
-		list_del_init(&client->list);
-		mutex_unlock(&phandle->phandle_lock);
-		kfree(client);
-	}
-}
-
-void dpu_power_resource_init(struct platform_device *pdev,
-	struct dpu_power_handle *phandle)
-{
-	phandle->dev = &pdev->dev;
-
-	INIT_LIST_HEAD(&phandle->power_client_clist);
-	INIT_LIST_HEAD(&phandle->event_list);
-
-	mutex_init(&phandle->phandle_lock);
-}
-
-void dpu_power_resource_deinit(struct platform_device *pdev,
-	struct dpu_power_handle *phandle)
-{
-	struct dpu_power_client *curr_client, *next_client;
-	struct dpu_power_event *curr_event, *next_event;
-
-	if (!phandle || !pdev) {
-		pr_err("invalid input param\n");
-		return;
-	}
-
-	mutex_lock(&phandle->phandle_lock);
-	list_for_each_entry_safe(curr_client, next_client,
-			&phandle->power_client_clist, list) {
-		pr_err("client:%s-%d still registered with refcount:%d\n",
-				curr_client->name, curr_client->id,
-				curr_client->refcount);
-		curr_client->active = false;
-		list_del(&curr_client->list);
-	}
-
-	list_for_each_entry_safe(curr_event, next_event,
-			&phandle->event_list, list) {
-		pr_err("event:%d, client:%s still registered\n",
-				curr_event->event_type,
-				curr_event->client_name);
-		curr_event->active = false;
-		list_del(&curr_event->list);
-	}
-	mutex_unlock(&phandle->phandle_lock);
-}
-
-int dpu_power_resource_enable(struct dpu_power_handle *phandle,
-	struct dpu_power_client *pclient, bool enable)
-{
-	bool changed = false;
-	u32 max_usecase_ndx = VOTE_INDEX_DISABLE, prev_usecase_ndx;
-	struct dpu_power_client *client;
-	u32 event_type;
-
-	if (!phandle || !pclient) {
-		pr_err("invalid input argument\n");
-		return -EINVAL;
-	}
-
-	mutex_lock(&phandle->phandle_lock);
-	if (enable)
-		pclient->refcount++;
-	else if (pclient->refcount)
-		pclient->refcount--;
-
-	if (pclient->refcount)
-		pclient->usecase_ndx = VOTE_INDEX_LOW;
-	else
-		pclient->usecase_ndx = VOTE_INDEX_DISABLE;
-
-	list_for_each_entry(client, &phandle->power_client_clist, list) {
-		if (client->usecase_ndx < VOTE_INDEX_MAX &&
-		    client->usecase_ndx > max_usecase_ndx)
-			max_usecase_ndx = client->usecase_ndx;
-	}
-
-	if (phandle->current_usecase_ndx != max_usecase_ndx) {
-		changed = true;
-		prev_usecase_ndx = phandle->current_usecase_ndx;
-		phandle->current_usecase_ndx = max_usecase_ndx;
-	}
-
-	pr_debug("%pS: changed=%d current idx=%d request client %s id:%u enable:%d refcount:%d\n",
-		__builtin_return_address(0), changed, max_usecase_ndx,
-		pclient->name, pclient->id, enable, pclient->refcount);
-
-	if (!changed)
-		goto end;
-
-	event_type = enable ? DPU_POWER_EVENT_ENABLE : DPU_POWER_EVENT_DISABLE;
-
-	dpu_power_event_trigger_locked(phandle,	event_type);
-end:
-	mutex_unlock(&phandle->phandle_lock);
-	return 0;
-}
-
-struct dpu_power_event *dpu_power_handle_register_event(
-		struct dpu_power_handle *phandle,
-		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
-		void *usr, char *client_name)
-{
-	struct dpu_power_event *event;
-
-	if (!phandle) {
-		pr_err("invalid power handle\n");
-		return ERR_PTR(-EINVAL);
-	} else if (!cb_fnc || !event_type) {
-		pr_err("no callback fnc or event type\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	event = kzalloc(sizeof(struct dpu_power_event), GFP_KERNEL);
-	if (!event)
-		return ERR_PTR(-ENOMEM);
-
-	event->event_type = event_type;
-	event->cb_fnc = cb_fnc;
-	event->usr = usr;
-	strlcpy(event->client_name, client_name, MAX_CLIENT_NAME_LEN);
-	event->active = true;
-
-	mutex_lock(&phandle->phandle_lock);
-	list_add(&event->list, &phandle->event_list);
-	mutex_unlock(&phandle->phandle_lock);
-
-	return event;
-}
-
-void dpu_power_handle_unregister_event(
-		struct dpu_power_handle *phandle,
-		struct dpu_power_event *event)
-{
-	if (!phandle || !event) {
-		pr_err("invalid phandle or event\n");
-	} else if (!event->active) {
-		pr_err("power handle deinit already done\n");
-		kfree(event);
-	} else {
-		mutex_lock(&phandle->phandle_lock);
-		list_del_init(&event->list);
-		mutex_unlock(&phandle->phandle_lock);
-		kfree(event);
-	}
-}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
deleted file mode 100644
index a65b7a297f21..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
+++ /dev/null
@@ -1,217 +0,0 @@
-/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _DPU_POWER_HANDLE_H_
-#define _DPU_POWER_HANDLE_H_
-
-#define MAX_CLIENT_NAME_LEN 128
-
-#define DPU_POWER_HANDLE_ENABLE_BUS_AB_QUOTA	0
-#define DPU_POWER_HANDLE_DISABLE_BUS_AB_QUOTA	0
-#define DPU_POWER_HANDLE_ENABLE_BUS_IB_QUOTA	1600000000
-#define DPU_POWER_HANDLE_DISABLE_BUS_IB_QUOTA	0
-
-#include "dpu_io_util.h"
-
-/* events will be triggered on power handler enable/disable */
-#define DPU_POWER_EVENT_DISABLE	BIT(0)
-#define DPU_POWER_EVENT_ENABLE	BIT(1)
-
-/**
- * mdss_bus_vote_type: register bus vote type
- * VOTE_INDEX_DISABLE: removes the client vote
- * VOTE_INDEX_LOW: keeps the lowest vote for register bus
- * VOTE_INDEX_MAX: invalid
- */
-enum mdss_bus_vote_type {
-	VOTE_INDEX_DISABLE,
-	VOTE_INDEX_LOW,
-	VOTE_INDEX_MAX,
-};
-
-/**
- * enum dpu_power_handle_data_bus_client - type of axi bus clients
- * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT: core real-time bus client
- * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT: core non-real-time bus client
- * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX: maximum number of bus client type
- */
-enum dpu_power_handle_data_bus_client {
-	DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT,
-	DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT,
-	DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX
-};
-
-/**
- * enum DPU_POWER_HANDLE_DBUS_ID - data bus identifier
- * @DPU_POWER_HANDLE_DBUS_ID_MNOC: DPU/MNOC data bus
- * @DPU_POWER_HANDLE_DBUS_ID_LLCC: MNOC/LLCC data bus
- * @DPU_POWER_HANDLE_DBUS_ID_EBI: LLCC/EBI data bus
- */
-enum DPU_POWER_HANDLE_DBUS_ID {
-	DPU_POWER_HANDLE_DBUS_ID_MNOC,
-	DPU_POWER_HANDLE_DBUS_ID_LLCC,
-	DPU_POWER_HANDLE_DBUS_ID_EBI,
-	DPU_POWER_HANDLE_DBUS_ID_MAX,
-};
-
-/**
- * struct dpu_power_client: stores the power client for dpu driver
- * @name:	name of the client
- * @usecase_ndx: current regs bus vote type
- * @refcount:	current refcount if multiple modules are using same
- *              same client for enable/disable. Power module will
- *              aggregate the refcount and vote accordingly for this
- *              client.
- * @id:		assigned during create. helps for debugging.
- * @list:	list to attach power handle master list
- * @ab:         arbitrated bandwidth for each bus client
- * @ib:         instantaneous bandwidth for each bus client
- * @active:	inidcates the state of dpu power handle
- */
-struct dpu_power_client {
-	char name[MAX_CLIENT_NAME_LEN];
-	short usecase_ndx;
-	short refcount;
-	u32 id;
-	struct list_head list;
-	u64 ab[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
-	u64 ib[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
-	bool active;
-};
-
-/*
- * struct dpu_power_event - local event registration structure
- * @client_name: name of the client registering
- * @cb_fnc: pointer to desired callback function
- * @usr: user pointer to pass to callback event trigger
- * @event: refer to DPU_POWER_HANDLE_EVENT_*
- * @list: list to attach event master list
- * @active: indicates the state of dpu power handle
- */
-struct dpu_power_event {
-	char client_name[MAX_CLIENT_NAME_LEN];
-	void (*cb_fnc)(u32 event_type, void *usr);
-	void *usr;
-	u32 event_type;
-	struct list_head list;
-	bool active;
-};
-
-/**
- * struct dpu_power_handle: power handle main struct
- * @client_clist: master list to store all clients
- * @phandle_lock: lock to synchronize the enable/disable
- * @dev: pointer to device structure
- * @usecase_ndx: current usecase index
- * @event_list: current power handle event list
- */
-struct dpu_power_handle {
-	struct list_head power_client_clist;
-	struct mutex phandle_lock;
-	struct device *dev;
-	u32 current_usecase_ndx;
-	struct list_head event_list;
-};
-
-/**
- * dpu_power_resource_init() - initializes the dpu power handle
- * @pdev:   platform device to search the power resources
- * @pdata:  power handle to store the power resources
- */
-void dpu_power_resource_init(struct platform_device *pdev,
-	struct dpu_power_handle *pdata);
-
-/**
- * dpu_power_resource_deinit() - release the dpu power handle
- * @pdev:   platform device for power resources
- * @pdata:  power handle containing the resources
- *
- * Return: error code.
- */
-void dpu_power_resource_deinit(struct platform_device *pdev,
-	struct dpu_power_handle *pdata);
-
-/**
- * dpu_power_client_create() - create the client on power handle
- * @pdata:  power handle containing the resources
- * @client_name: new client name for registration
- *
- * Return: error code.
- */
-struct dpu_power_client *dpu_power_client_create(struct dpu_power_handle *pdata,
-	char *client_name);
-
-/**
- * dpu_power_client_destroy() - destroy the client on power handle
- * @pdata:  power handle containing the resources
- * @client_name: new client name for registration
- *
- * Return: none
- */
-void dpu_power_client_destroy(struct dpu_power_handle *phandle,
-	struct dpu_power_client *client);
-
-/**
- * dpu_power_resource_enable() - enable/disable the power resources
- * @pdata:  power handle containing the resources
- * @client: client information to enable/disable its vote
- * @enable: boolean request for enable/disable
- *
- * Return: error code.
- */
-int dpu_power_resource_enable(struct dpu_power_handle *pdata,
-	struct dpu_power_client *pclient, bool enable);
-
-/**
- * dpu_power_data_bus_bandwidth_ctrl() - control data bus bandwidth enable
- * @phandle:  power handle containing the resources
- * @client: client information to bandwidth control
- * @enable: true to enable bandwidth for data base
- *
- * Return: none
- */
-void dpu_power_data_bus_bandwidth_ctrl(struct dpu_power_handle *phandle,
-		struct dpu_power_client *pclient, int enable);
-
-/**
- * dpu_power_handle_register_event - register a callback function for an event.
- *	Clients can register for multiple events with a single register.
- *	Any block with access to phandle can register for the event
- *	notification.
- * @phandle:	power handle containing the resources
- * @event_type:	event type to register; refer DPU_POWER_HANDLE_EVENT_*
- * @cb_fnc:	pointer to desired callback function
- * @usr:	user pointer to pass to callback on event trigger
- *
- * Return:	event pointer if success, or error code otherwise
- */
-struct dpu_power_event *dpu_power_handle_register_event(
-		struct dpu_power_handle *phandle,
-		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
-		void *usr, char *client_name);
-/**
- * dpu_power_handle_unregister_event - unregister callback for event(s)
- * @phandle:	power handle containing the resources
- * @event:	event pointer returned after power handle register
- */
-void dpu_power_handle_unregister_event(struct dpu_power_handle *phandle,
-		struct dpu_power_event *event);
-
-/**
- * dpu_power_handle_get_dbus_name - get name of given data bus identifier
- * @bus_id:	data bus identifier
- * Return:	Pointer to name string if success; NULL otherwise
- */
-const char *dpu_power_handle_get_dbus_name(u32 bus_id);
-
-#endif /* _DPU_POWER_HANDLE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
index e12c4cefb742..c78b521ceda1 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
@@ -99,27 +99,6 @@ TRACE_EVENT(dpu_perf_set_ot,
 			__entry->vbif_idx)
 )
 
-TRACE_EVENT(dpu_perf_update_bus,
-	TP_PROTO(int client, unsigned long long ab_quota,
-	unsigned long long ib_quota),
-	TP_ARGS(client, ab_quota, ib_quota),
-	TP_STRUCT__entry(
-			__field(int, client)
-			__field(u64, ab_quota)
-			__field(u64, ib_quota)
-	),
-	TP_fast_assign(
-			__entry->client = client;
-			__entry->ab_quota = ab_quota;
-			__entry->ib_quota = ib_quota;
-	),
-	TP_printk("Request client:%d ab=%llu ib=%llu",
-			__entry->client,
-			__entry->ab_quota,
-			__entry->ib_quota)
-)
-
-
 TRACE_EVENT(dpu_cmd_release_bw,
 	TP_PROTO(u32 crtc_id),
 	TP_ARGS(crtc_id),
@@ -319,6 +298,10 @@ DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_wait_for_commit_done,
 	TP_PROTO(uint32_t drm_id),
 	TP_ARGS(drm_id)
 );
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_runtime_resume,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
 
 TRACE_EVENT(dpu_enc_enable,
 	TP_PROTO(uint32_t drm_id, int hdisplay, int vdisplay),
@@ -539,10 +522,6 @@ DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_cb,
 	TP_PROTO(uint32_t drm_id, u32 event),
 	TP_ARGS(drm_id, event)
 );
-DEFINE_EVENT(dpu_id_event_template, dpu_crtc_handle_power_event,
-	TP_PROTO(uint32_t drm_id, u32 event),
-	TP_ARGS(drm_id, event)
-);
 DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_done,
 	TP_PROTO(uint32_t drm_id, u32 event),
 	TP_ARGS(drm_id, event)
@@ -749,24 +728,17 @@ TRACE_EVENT(dpu_crtc_vblank_enable,
 		__field(	uint32_t,		enc_id	)
 		__field(	bool,			enable	)
 		__field(	bool,			enabled )
-		__field(	bool,			suspend )
-		__field(	bool,			vblank_requested )
 	),
 	TP_fast_assign(
 		__entry->drm_id = drm_id;
 		__entry->enc_id = enc_id;
 		__entry->enable = enable;
 		__entry->enabled = crtc->enabled;
-		__entry->suspend = crtc->suspend;
-		__entry->vblank_requested = crtc->vblank_requested;
 	),
-	TP_printk("id:%u encoder:%u enable:%s state{enabled:%s suspend:%s "
-		  "vblank_req:%s}",
+	TP_printk("id:%u encoder:%u enable:%s state{enabled:%s}",
 		  __entry->drm_id, __entry->enc_id,
 		  __entry->enable ? "true" : "false",
-		  __entry->enabled ? "true" : "false",
-		  __entry->suspend ? "true" : "false",
-		  __entry->vblank_requested ? "true" : "false")
+		  __entry->enabled ? "true" : "false")
 );
 
 DECLARE_EVENT_CLASS(dpu_crtc_enable_template,
@@ -776,25 +748,15 @@ DECLARE_EVENT_CLASS(dpu_crtc_enable_template,
 		__field(	uint32_t,		drm_id	)
 		__field(	bool,			enable	)
 		__field(	bool,			enabled )
-		__field(	bool,			suspend )
-		__field(	bool,			vblank_requested )
 	),
 	TP_fast_assign(
 		__entry->drm_id = drm_id;
 		__entry->enable = enable;
 		__entry->enabled = crtc->enabled;
-		__entry->suspend = crtc->suspend;
-		__entry->vblank_requested = crtc->vblank_requested;
 	),
-	TP_printk("id:%u enable:%s state{enabled:%s suspend:%s vblank_req:%s}",
+	TP_printk("id:%u enable:%s state{enabled:%s}",
 		  __entry->drm_id, __entry->enable ? "true" : "false",
-		  __entry->enabled ? "true" : "false",
-		  __entry->suspend ? "true" : "false",
-		  __entry->vblank_requested ? "true" : "false")
-);
-DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_set_suspend,
-	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
-	TP_ARGS(drm_id, enable, crtc)
+		  __entry->enabled ? "true" : "false")
 );
 DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_enable,
 	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
@@ -1004,6 +966,53 @@ TRACE_EVENT(dpu_core_perf_update_clk,
 		  __entry->stop_req ? "true" : "false", __entry->clk_rate)
 );
 
+TRACE_EVENT(dpu_hw_ctl_update_pending_flush,
+	TP_PROTO(u32 new_bits, u32 pending_mask),
+	TP_ARGS(new_bits, pending_mask),
+	TP_STRUCT__entry(
+		__field(	u32,			new_bits	)
+		__field(	u32,			pending_mask	)
+	),
+	TP_fast_assign(
+		__entry->new_bits = new_bits;
+		__entry->pending_mask = pending_mask;
+	),
+	TP_printk("new=%x existing=%x", __entry->new_bits,
+		  __entry->pending_mask)
+);
+
+DECLARE_EVENT_CLASS(dpu_hw_ctl_pending_flush_template,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush),
+	TP_STRUCT__entry(
+		__field(	u32,			pending_mask	)
+		__field(	u32,			ctl_flush	)
+	),
+	TP_fast_assign(
+		__entry->pending_mask = pending_mask;
+		__entry->ctl_flush = ctl_flush;
+	),
+	TP_printk("pending_mask=%x CTL_FLUSH=%x", __entry->pending_mask,
+		  __entry->ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template, dpu_hw_ctl_clear_pending_flush,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template,
+	     dpu_hw_ctl_trigger_pending_flush,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template, dpu_hw_ctl_trigger_prepare,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+DEFINE_EVENT(dpu_hw_ctl_pending_flush_template, dpu_hw_ctl_trigger_start,
+	TP_PROTO(u32 pending_mask, u32 ctl_flush),
+	TP_ARGS(pending_mask, ctl_flush)
+);
+
 #define DPU_ATRACE_END(name) trace_tracing_mark_write(current->tgid, name, 0)
 #define DPU_ATRACE_BEGIN(name) trace_tracing_mark_write(current->tgid, name, 1)
 #define DPU_ATRACE_FUNC() DPU_ATRACE_BEGIN(__func__)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 295528292296..ef753ea9c499 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -191,7 +191,7 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 	ot_lim = _dpu_vbif_get_ot_limit(vbif, params) & 0xFF;
 
 	if (ot_lim == 0)
-		goto exit;
+		return;
 
 	trace_dpu_perf_set_ot(params->num, params->xin_id, ot_lim,
 		params->vbif_idx);
@@ -210,8 +210,6 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 
 	if (forced_on)
 		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
-exit:
-	return;
 }
 
 void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
@@ -312,31 +310,25 @@ void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms)
 }
 
 #ifdef CONFIG_DEBUG_FS
-void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
-{
-	debugfs_remove_recursive(dpu_kms->debugfs_vbif);
-	dpu_kms->debugfs_vbif = NULL;
-}
 
-int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
+void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 {
 	char vbif_name[32];
-	struct dentry *debugfs_vbif;
+	struct dentry *entry, *debugfs_vbif;
 	int i, j;
 
-	dpu_kms->debugfs_vbif = debugfs_create_dir("vbif", debugfs_root);
-	if (!dpu_kms->debugfs_vbif) {
-		DPU_ERROR("failed to create vbif debugfs\n");
-		return -EINVAL;
-	}
+	entry = debugfs_create_dir("vbif", debugfs_root);
+	if (IS_ERR_OR_NULL(entry))
+		return;
 
 	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
 		struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
 
 		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
 
-		debugfs_vbif = debugfs_create_dir(vbif_name,
-				dpu_kms->debugfs_vbif);
+		debugfs_vbif = debugfs_create_dir(vbif_name, entry);
+		if (IS_ERR_OR_NULL(debugfs_vbif))
+			continue;
 
 		debugfs_create_u32("features", 0600, debugfs_vbif,
 			(u32 *)&vbif->features);
@@ -378,7 +370,5 @@ int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 					(u32 *)&cfg->ot_limit);
 		}
 	}
-
-	return 0;
 }
 #endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
index f17af52dbbd5..6356876d7a66 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
@@ -78,17 +78,6 @@ void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms);
  */
 void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms);
 
-#ifdef CONFIG_DEBUG_FS
-int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
-void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms);
-#else
-static inline int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms,
-		struct dentry *debugfs_root)
-{
-	return 0;
-}
-static inline void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
-{
-}
-#endif
+void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
+
 #endif /* __DPU_VBIF_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
index 4f12e5c534c8..9fc9dbde8a27 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
@@ -813,18 +813,6 @@ enum color_fmts {
 #define COLOR_FMT_P010_UBWC		COLOR_FMT_P010_UBWC
 #define COLOR_FMT_P010		COLOR_FMT_P010
 
-static inline unsigned int VENUS_EXTRADATA_SIZE(int width, int height)
-{
-	(void)height;
-	(void)width;
-
-	/*
-	 * In the future, calculate the size based on the w/h but just
-	 * hardcode it for now since 16K satisfies all current usecases.
-	 */
-	return 16 * 1024;
-}
-
 /*
  * Function arguments:
  * @color_fmt
@@ -832,38 +820,32 @@ static inline unsigned int VENUS_EXTRADATA_SIZE(int width, int height)
  * Progressive: width
  * Interlaced: width
  */
-static inline unsigned int VENUS_Y_STRIDE(int color_fmt, int width)
+static unsigned int VENUS_Y_STRIDE(int color_fmt, int width)
 {
-	unsigned int alignment, stride = 0;
+	unsigned int stride = 0;
 
 	if (!width)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV21:
 	case COLOR_FMT_NV12:
 	case COLOR_FMT_NV12_MVTB:
 	case COLOR_FMT_NV12_UBWC:
-		alignment = 128;
-		stride = MSM_MEDIA_ALIGN(width, alignment);
+		stride = MSM_MEDIA_ALIGN(width, 128);
 		break;
 	case COLOR_FMT_NV12_BPP10_UBWC:
-		alignment = 256;
 		stride = MSM_MEDIA_ALIGN(width, 192);
-		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		stride = MSM_MEDIA_ALIGN(stride * 4 / 3, 256);
 		break;
 	case COLOR_FMT_P010_UBWC:
-		alignment = 256;
-		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		stride = MSM_MEDIA_ALIGN(width * 2, 256);
 		break;
 	case COLOR_FMT_P010:
-		alignment = 128;
-		stride = MSM_MEDIA_ALIGN(width*2, alignment);
-		break;
-	default:
+		stride = MSM_MEDIA_ALIGN(width * 2, 128);
 		break;
 	}
-invalid_input:
+
 	return stride;
 }
 
@@ -874,38 +856,32 @@ invalid_input:
  * Progressive: width
  * Interlaced: width
  */
-static inline unsigned int VENUS_UV_STRIDE(int color_fmt, int width)
+static unsigned int VENUS_UV_STRIDE(int color_fmt, int width)
 {
-	unsigned int alignment, stride = 0;
+	unsigned int stride = 0;
 
 	if (!width)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV21:
 	case COLOR_FMT_NV12:
 	case COLOR_FMT_NV12_MVTB:
 	case COLOR_FMT_NV12_UBWC:
-		alignment = 128;
-		stride = MSM_MEDIA_ALIGN(width, alignment);
+		stride = MSM_MEDIA_ALIGN(width, 128);
 		break;
 	case COLOR_FMT_NV12_BPP10_UBWC:
-		alignment = 256;
 		stride = MSM_MEDIA_ALIGN(width, 192);
-		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		stride = MSM_MEDIA_ALIGN(stride * 4 / 3, 256);
 		break;
 	case COLOR_FMT_P010_UBWC:
-		alignment = 256;
-		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		stride = MSM_MEDIA_ALIGN(width * 2, 256);
 		break;
 	case COLOR_FMT_P010:
-		alignment = 128;
-		stride = MSM_MEDIA_ALIGN(width*2, alignment);
-		break;
-	default:
+		stride = MSM_MEDIA_ALIGN(width * 2, 128);
 		break;
 	}
-invalid_input:
+
 	return stride;
 }
 
@@ -916,12 +892,12 @@ invalid_input:
  * Progressive: height
  * Interlaced: (height+1)>>1
  */
-static inline unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
+static unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
 {
-	unsigned int alignment, sclines = 0;
+	unsigned int sclines = 0;
 
 	if (!height)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV21:
@@ -929,17 +905,14 @@ static inline unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
 	case COLOR_FMT_NV12_MVTB:
 	case COLOR_FMT_NV12_UBWC:
 	case COLOR_FMT_P010:
-		alignment = 32;
+		sclines = MSM_MEDIA_ALIGN(height, 32);
 		break;
 	case COLOR_FMT_NV12_BPP10_UBWC:
 	case COLOR_FMT_P010_UBWC:
-		alignment = 16;
+		sclines = MSM_MEDIA_ALIGN(height, 16);
 		break;
-	default:
-		return 0;
 	}
-	sclines = MSM_MEDIA_ALIGN(height, alignment);
-invalid_input:
+
 	return sclines;
 }
 
@@ -950,12 +923,12 @@ invalid_input:
  * Progressive: height
  * Interlaced: (height+1)>>1
  */
-static inline unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
+static unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
 {
-	unsigned int alignment, sclines = 0;
+	unsigned int sclines = 0;
 
 	if (!height)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV21:
@@ -964,18 +937,13 @@ static inline unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
 	case COLOR_FMT_NV12_BPP10_UBWC:
 	case COLOR_FMT_P010_UBWC:
 	case COLOR_FMT_P010:
-		alignment = 16;
+		sclines = MSM_MEDIA_ALIGN((height + 1) >> 1, 16);
 		break;
 	case COLOR_FMT_NV12_UBWC:
-		alignment = 32;
+		sclines = MSM_MEDIA_ALIGN((height + 1) >> 1, 32);
 		break;
-	default:
-		goto invalid_input;
 	}
 
-	sclines = MSM_MEDIA_ALIGN((height+1)>>1, alignment);
-
-invalid_input:
 	return sclines;
 }
 
@@ -986,12 +954,12 @@ invalid_input:
  * Progressive: width
  * Interlaced: width
  */
-static inline unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
+static unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
 {
-	int y_tile_width = 0, y_meta_stride = 0;
+	int y_tile_width = 0, y_meta_stride;
 
 	if (!width)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV12_UBWC:
@@ -1002,14 +970,11 @@ static inline unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
 		y_tile_width = 48;
 		break;
 	default:
-		goto invalid_input;
+		return 0;
 	}
 
 	y_meta_stride = MSM_MEDIA_ROUNDUP(width, y_tile_width);
-	y_meta_stride = MSM_MEDIA_ALIGN(y_meta_stride, 64);
-
-invalid_input:
-	return y_meta_stride;
+	return MSM_MEDIA_ALIGN(y_meta_stride, 64);
 }
 
 /*
@@ -1019,12 +984,12 @@ invalid_input:
  * Progressive: height
  * Interlaced: (height+1)>>1
  */
-static inline unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
+static unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
 {
-	int y_tile_height = 0, y_meta_scanlines = 0;
+	int y_tile_height = 0, y_meta_scanlines;
 
 	if (!height)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV12_UBWC:
@@ -1035,14 +1000,11 @@ static inline unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
 		y_tile_height = 4;
 		break;
 	default:
-		goto invalid_input;
+		return 0;
 	}
 
 	y_meta_scanlines = MSM_MEDIA_ROUNDUP(height, y_tile_height);
-	y_meta_scanlines = MSM_MEDIA_ALIGN(y_meta_scanlines, 16);
-
-invalid_input:
-	return y_meta_scanlines;
+	return MSM_MEDIA_ALIGN(y_meta_scanlines, 16);
 }
 
 /*
@@ -1052,12 +1014,12 @@ invalid_input:
  * Progressive: width
  * Interlaced: width
  */
-static inline unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
+static unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
 {
-	int uv_tile_width = 0, uv_meta_stride = 0;
+	int uv_tile_width = 0, uv_meta_stride;
 
 	if (!width)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV12_UBWC:
@@ -1068,14 +1030,11 @@ static inline unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
 		uv_tile_width = 24;
 		break;
 	default:
-		goto invalid_input;
+		return 0;
 	}
 
 	uv_meta_stride = MSM_MEDIA_ROUNDUP((width+1)>>1, uv_tile_width);
-	uv_meta_stride = MSM_MEDIA_ALIGN(uv_meta_stride, 64);
-
-invalid_input:
-	return uv_meta_stride;
+	return MSM_MEDIA_ALIGN(uv_meta_stride, 64);
 }
 
 /*
@@ -1085,12 +1044,12 @@ invalid_input:
  * Progressive: height
  * Interlaced: (height+1)>>1
  */
-static inline unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
+static unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
 {
-	int uv_tile_height = 0, uv_meta_scanlines = 0;
+	int uv_tile_height = 0, uv_meta_scanlines;
 
 	if (!height)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_NV12_UBWC:
@@ -1101,22 +1060,19 @@ static inline unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
 		uv_tile_height = 4;
 		break;
 	default:
-		goto invalid_input;
+		return 0;
 	}
 
 	uv_meta_scanlines = MSM_MEDIA_ROUNDUP((height+1)>>1, uv_tile_height);
-	uv_meta_scanlines = MSM_MEDIA_ALIGN(uv_meta_scanlines, 16);
-
-invalid_input:
-	return uv_meta_scanlines;
+	return MSM_MEDIA_ALIGN(uv_meta_scanlines, 16);
 }
 
-static inline unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
+static unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
 {
-	unsigned int alignment = 0, stride = 0, bpp = 4;
+	unsigned int alignment = 0, bpp = 4;
 
 	if (!width)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_RGBA8888:
@@ -1131,21 +1087,18 @@ static inline unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
 		alignment = 256;
 		break;
 	default:
-		goto invalid_input;
+		return 0;
 	}
 
-	stride = MSM_MEDIA_ALIGN(width * bpp, alignment);
-
-invalid_input:
-	return stride;
+	return MSM_MEDIA_ALIGN(width * bpp, alignment);
 }
 
-static inline unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
+static unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
 {
-	unsigned int alignment = 0, scanlines = 0;
+	unsigned int alignment = 0;
 
 	if (!height)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_RGBA8888:
@@ -1157,220 +1110,46 @@ static inline unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
 		alignment = 16;
 		break;
 	default:
-		goto invalid_input;
+		return 0;
 	}
 
-	scanlines = MSM_MEDIA_ALIGN(height, alignment);
-
-invalid_input:
-	return scanlines;
+	return MSM_MEDIA_ALIGN(height, alignment);
 }
 
-static inline unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width)
+static unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width)
 {
-	int rgb_tile_width = 0, rgb_meta_stride = 0;
+	int rgb_meta_stride;
 
 	if (!width)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_RGBA8888_UBWC:
 	case COLOR_FMT_RGBA1010102_UBWC:
 	case COLOR_FMT_RGB565_UBWC:
-		rgb_tile_width = 16;
-		break;
-	default:
-		goto invalid_input;
+		rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, 16);
+		return MSM_MEDIA_ALIGN(rgb_meta_stride, 64);
 	}
 
-	rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, rgb_tile_width);
-	rgb_meta_stride = MSM_MEDIA_ALIGN(rgb_meta_stride, 64);
-
-invalid_input:
-	return rgb_meta_stride;
+	return 0;
 }
 
-static inline unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height)
+static unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height)
 {
-	int rgb_tile_height = 0, rgb_meta_scanlines = 0;
+	int rgb_meta_scanlines;
 
 	if (!height)
-		goto invalid_input;
+		return 0;
 
 	switch (color_fmt) {
 	case COLOR_FMT_RGBA8888_UBWC:
 	case COLOR_FMT_RGBA1010102_UBWC:
 	case COLOR_FMT_RGB565_UBWC:
-		rgb_tile_height = 4;
-		break;
-	default:
-		goto invalid_input;
+		rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, 4);
+		return MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16);
 	}
 
-	rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, rgb_tile_height);
-	rgb_meta_scanlines = MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16);
-
-invalid_input:
-	return rgb_meta_scanlines;
-}
-
-/*
- * Function arguments:
- * @color_fmt
- * @width
- * Progressive: width
- * Interlaced: width
- * @height
- * Progressive: height
- * Interlaced: height
- */
-static inline unsigned int VENUS_BUFFER_SIZE(
-	int color_fmt, int width, int height)
-{
-	const unsigned int extra_size = VENUS_EXTRADATA_SIZE(width, height);
-	unsigned int uv_alignment = 0, size = 0;
-	unsigned int y_plane, uv_plane, y_stride,
-		uv_stride, y_sclines, uv_sclines;
-	unsigned int y_ubwc_plane = 0, uv_ubwc_plane = 0;
-	unsigned int y_meta_stride = 0, y_meta_scanlines = 0;
-	unsigned int uv_meta_stride = 0, uv_meta_scanlines = 0;
-	unsigned int y_meta_plane = 0, uv_meta_plane = 0;
-	unsigned int rgb_stride = 0, rgb_scanlines = 0;
-	unsigned int rgb_plane = 0, rgb_ubwc_plane = 0, rgb_meta_plane = 0;
-	unsigned int rgb_meta_stride = 0, rgb_meta_scanlines = 0;
-
-	if (!width || !height)
-		goto invalid_input;
-
-	y_stride = VENUS_Y_STRIDE(color_fmt, width);
-	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
-	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
-	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
-	rgb_stride = VENUS_RGB_STRIDE(color_fmt, width);
-	rgb_scanlines = VENUS_RGB_SCANLINES(color_fmt, height);
-
-	switch (color_fmt) {
-	case COLOR_FMT_NV21:
-	case COLOR_FMT_NV12:
-	case COLOR_FMT_P010:
-		uv_alignment = 4096;
-		y_plane = y_stride * y_sclines;
-		uv_plane = uv_stride * uv_sclines + uv_alignment;
-		size = y_plane + uv_plane +
-				MSM_MEDIA_MAX(extra_size, 8 * y_stride);
-		size = MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	case COLOR_FMT_NV12_MVTB:
-		uv_alignment = 4096;
-		y_plane = y_stride * y_sclines;
-		uv_plane = uv_stride * uv_sclines + uv_alignment;
-		size = y_plane + uv_plane;
-		size = 2 * size + extra_size;
-		size = MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	case COLOR_FMT_NV12_UBWC:
-		y_sclines = VENUS_Y_SCANLINES(color_fmt, (height+1)>>1);
-		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
-		uv_sclines = VENUS_UV_SCANLINES(color_fmt, (height+1)>>1);
-		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
-		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
-		y_meta_scanlines =
-			VENUS_Y_META_SCANLINES(color_fmt, (height+1)>>1);
-		y_meta_plane = MSM_MEDIA_ALIGN(
-			y_meta_stride * y_meta_scanlines, 4096);
-		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
-		uv_meta_scanlines =
-			VENUS_UV_META_SCANLINES(color_fmt, (height+1)>>1);
-		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
-			uv_meta_scanlines, 4096);
-
-		size = (y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
-			uv_meta_plane)*2 +
-			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
-		size = MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	case COLOR_FMT_NV12_BPP10_UBWC:
-		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
-		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
-		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
-		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
-		y_meta_plane = MSM_MEDIA_ALIGN(
-				y_meta_stride * y_meta_scanlines, 4096);
-		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
-		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
-		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
-					uv_meta_scanlines, 4096);
-
-		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
-			uv_meta_plane +
-			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
-		size = MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	case COLOR_FMT_P010_UBWC:
-		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
-		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
-		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
-		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
-		y_meta_plane = MSM_MEDIA_ALIGN(
-				y_meta_stride * y_meta_scanlines, 4096);
-		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
-		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
-		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
-					uv_meta_scanlines, 4096);
-
-		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
-			uv_meta_plane;
-		size = MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	case COLOR_FMT_RGBA8888:
-		rgb_plane = MSM_MEDIA_ALIGN(rgb_stride  * rgb_scanlines, 4096);
-		size = rgb_plane;
-		size =  MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	case COLOR_FMT_RGBA8888_UBWC:
-	case COLOR_FMT_RGBA1010102_UBWC:
-	case COLOR_FMT_RGB565_UBWC:
-		rgb_ubwc_plane = MSM_MEDIA_ALIGN(rgb_stride * rgb_scanlines,
-							4096);
-		rgb_meta_stride = VENUS_RGB_META_STRIDE(color_fmt, width);
-		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color_fmt,
-					height);
-		rgb_meta_plane = MSM_MEDIA_ALIGN(rgb_meta_stride *
-					rgb_meta_scanlines, 4096);
-		size = rgb_ubwc_plane + rgb_meta_plane;
-		size = MSM_MEDIA_ALIGN(size, 4096);
-		break;
-	default:
-		break;
-	}
-invalid_input:
-	return size;
-}
-
-static inline unsigned int VENUS_VIEW2_OFFSET(
-	int color_fmt, int width, int height)
-{
-	unsigned int offset = 0;
-	unsigned int y_plane, uv_plane, y_stride,
-		uv_stride, y_sclines, uv_sclines;
-	if (!width || !height)
-		goto invalid_input;
-
-	y_stride = VENUS_Y_STRIDE(color_fmt, width);
-	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
-	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
-	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
-	switch (color_fmt) {
-	case COLOR_FMT_NV12_MVTB:
-		y_plane = y_stride * y_sclines;
-		uv_plane = uv_stride * uv_sclines;
-		offset = y_plane + uv_plane;
-		break;
-	default:
-		break;
-	}
-invalid_input:
-	return offset;
+	return 0;
 }
 
 #endif
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
index 457c29dba4a1..8f2359dc87b4 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
@@ -128,7 +128,7 @@ static void unref_cursor_worker(struct drm_flip_work *work, void *val)
 	struct mdp4_kms *mdp4_kms = get_kms(&mdp4_crtc->base);
 	struct msm_kms *kms = &mdp4_kms->base.base;
 
-	msm_gem_put_iova(val, kms->aspace);
+	msm_gem_unpin_iova(val, kms->aspace);
 	drm_gem_object_put_unlocked(val);
 }
 
@@ -384,7 +384,7 @@ static void update_cursor(struct drm_crtc *crtc)
 		if (next_bo) {
 			/* take a obj ref + iova ref when we start scanning out: */
 			drm_gem_object_get(next_bo);
-			msm_gem_get_iova(next_bo, kms->aspace, &iova);
+			msm_gem_get_and_pin_iova(next_bo, kms->aspace, &iova);
 
 			/* enable cursor: */
 			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_SIZE(dma),
@@ -429,7 +429,7 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc,
 	int ret;
 
 	if ((width > CURSOR_WIDTH) || (height > CURSOR_HEIGHT)) {
-		dev_err(dev->dev, "bad cursor size: %dx%d\n", width, height);
+		DRM_DEV_ERROR(dev->dev, "bad cursor size: %dx%d\n", width, height);
 		return -EINVAL;
 	}
 
@@ -442,7 +442,7 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc,
 	}
 
 	if (cursor_bo) {
-		ret = msm_gem_get_iova(cursor_bo, kms->aspace, &iova);
+		ret = msm_gem_get_and_pin_iova(cursor_bo, kms->aspace, &iova);
 		if (ret)
 			goto fail;
 	} else {
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c
index ba8e587f734b..a8fd14d4846b 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dtv_encoder.c
@@ -45,7 +45,7 @@ static void bs_init(struct mdp4_dtv_encoder *mdp4_dtv_encoder)
 	struct lcdc_platform_data *dtv_pdata = mdp4_find_pdata("dtv.0");
 
 	if (!dtv_pdata) {
-		dev_err(dev->dev, "could not find dtv pdata\n");
+		DRM_DEV_ERROR(dev->dev, "could not find dtv pdata\n");
 		return;
 	}
 
@@ -209,16 +209,16 @@ static void mdp4_dtv_encoder_enable(struct drm_encoder *encoder)
 
 	ret = clk_set_rate(mdp4_dtv_encoder->mdp_clk, pc);
 	if (ret)
-		dev_err(dev->dev, "failed to set mdp_clk to %lu: %d\n",
+		DRM_DEV_ERROR(dev->dev, "failed to set mdp_clk to %lu: %d\n",
 			pc, ret);
 
 	ret = clk_prepare_enable(mdp4_dtv_encoder->mdp_clk);
 	if (ret)
-		dev_err(dev->dev, "failed to enabled mdp_clk: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to enabled mdp_clk: %d\n", ret);
 
 	ret = clk_prepare_enable(mdp4_dtv_encoder->hdmi_clk);
 	if (ret)
-		dev_err(dev->dev, "failed to enable hdmi_clk: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to enable hdmi_clk: %d\n", ret);
 
 	mdp4_write(mdp4_kms, REG_MDP4_DTV_ENABLE, 1);
 
@@ -258,14 +258,14 @@ struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev)
 
 	mdp4_dtv_encoder->hdmi_clk = devm_clk_get(dev->dev, "hdmi_clk");
 	if (IS_ERR(mdp4_dtv_encoder->hdmi_clk)) {
-		dev_err(dev->dev, "failed to get hdmi_clk\n");
+		DRM_DEV_ERROR(dev->dev, "failed to get hdmi_clk\n");
 		ret = PTR_ERR(mdp4_dtv_encoder->hdmi_clk);
 		goto fail;
 	}
 
 	mdp4_dtv_encoder->mdp_clk = devm_clk_get(dev->dev, "tv_clk");
 	if (IS_ERR(mdp4_dtv_encoder->mdp_clk)) {
-		dev_err(dev->dev, "failed to get tv_clk\n");
+		DRM_DEV_ERROR(dev->dev, "failed to get tv_clk\n");
 		ret = PTR_ERR(mdp4_dtv_encoder->mdp_clk);
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 44d1cda56974..e437aa806f7b 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -43,7 +43,7 @@ static int mdp4_hw_init(struct msm_kms *kms)
 	DBG("found MDP4 version v%d.%d", major, minor);
 
 	if (major != 4) {
-		dev_err(dev->dev, "unexpected MDP version: v%d.%d\n",
+		DRM_DEV_ERROR(dev->dev, "unexpected MDP version: v%d.%d\n",
 				major, minor);
 		ret = -ENXIO;
 		goto out;
@@ -165,7 +165,7 @@ static void mdp4_destroy(struct msm_kms *kms)
 	struct msm_gem_address_space *aspace = kms->aspace;
 
 	if (mdp4_kms->blank_cursor_iova)
-		msm_gem_put_iova(mdp4_kms->blank_cursor_bo, kms->aspace);
+		msm_gem_unpin_iova(mdp4_kms->blank_cursor_bo, kms->aspace);
 	drm_gem_object_put_unlocked(mdp4_kms->blank_cursor_bo);
 
 	if (aspace) {
@@ -206,7 +206,8 @@ int mdp4_disable(struct mdp4_kms *mdp4_kms)
 	clk_disable_unprepare(mdp4_kms->clk);
 	if (mdp4_kms->pclk)
 		clk_disable_unprepare(mdp4_kms->pclk);
-	clk_disable_unprepare(mdp4_kms->lut_clk);
+	if (mdp4_kms->lut_clk)
+		clk_disable_unprepare(mdp4_kms->lut_clk);
 	if (mdp4_kms->axi_clk)
 		clk_disable_unprepare(mdp4_kms->axi_clk);
 
@@ -220,7 +221,8 @@ int mdp4_enable(struct mdp4_kms *mdp4_kms)
 	clk_prepare_enable(mdp4_kms->clk);
 	if (mdp4_kms->pclk)
 		clk_prepare_enable(mdp4_kms->pclk);
-	clk_prepare_enable(mdp4_kms->lut_clk);
+	if (mdp4_kms->lut_clk)
+		clk_prepare_enable(mdp4_kms->lut_clk);
 	if (mdp4_kms->axi_clk)
 		clk_prepare_enable(mdp4_kms->axi_clk);
 
@@ -251,7 +253,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 
 		encoder = mdp4_lcdc_encoder_init(dev, panel_node);
 		if (IS_ERR(encoder)) {
-			dev_err(dev->dev, "failed to construct LCDC encoder\n");
+			DRM_DEV_ERROR(dev->dev, "failed to construct LCDC encoder\n");
 			return PTR_ERR(encoder);
 		}
 
@@ -260,7 +262,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 
 		connector = mdp4_lvds_connector_init(dev, panel_node, encoder);
 		if (IS_ERR(connector)) {
-			dev_err(dev->dev, "failed to initialize LVDS connector\n");
+			DRM_DEV_ERROR(dev->dev, "failed to initialize LVDS connector\n");
 			return PTR_ERR(connector);
 		}
 
@@ -271,7 +273,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 	case DRM_MODE_ENCODER_TMDS:
 		encoder = mdp4_dtv_encoder_init(dev);
 		if (IS_ERR(encoder)) {
-			dev_err(dev->dev, "failed to construct DTV encoder\n");
+			DRM_DEV_ERROR(dev->dev, "failed to construct DTV encoder\n");
 			return PTR_ERR(encoder);
 		}
 
@@ -282,7 +284,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 			/* Construct bridge/connector for HDMI: */
 			ret = msm_hdmi_modeset_init(priv->hdmi, dev, encoder);
 			if (ret) {
-				dev_err(dev->dev, "failed to initialize HDMI: %d\n", ret);
+				DRM_DEV_ERROR(dev->dev, "failed to initialize HDMI: %d\n", ret);
 				return ret;
 			}
 		}
@@ -300,7 +302,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 		encoder = mdp4_dsi_encoder_init(dev);
 		if (IS_ERR(encoder)) {
 			ret = PTR_ERR(encoder);
-			dev_err(dev->dev,
+			DRM_DEV_ERROR(dev->dev,
 				"failed to construct DSI encoder: %d\n", ret);
 			return ret;
 		}
@@ -311,14 +313,14 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 
 		ret = msm_dsi_modeset_init(priv->dsi[dsi_id], dev, encoder);
 		if (ret) {
-			dev_err(dev->dev, "failed to initialize DSI: %d\n",
+			DRM_DEV_ERROR(dev->dev, "failed to initialize DSI: %d\n",
 				ret);
 			return ret;
 		}
 
 		break;
 	default:
-		dev_err(dev->dev, "Invalid or unsupported interface\n");
+		DRM_DEV_ERROR(dev->dev, "Invalid or unsupported interface\n");
 		return -EINVAL;
 	}
 
@@ -354,7 +356,7 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 	for (i = 0; i < ARRAY_SIZE(vg_planes); i++) {
 		plane = mdp4_plane_init(dev, vg_planes[i], false);
 		if (IS_ERR(plane)) {
-			dev_err(dev->dev,
+			DRM_DEV_ERROR(dev->dev,
 				"failed to construct plane for VG%d\n", i + 1);
 			ret = PTR_ERR(plane);
 			goto fail;
@@ -365,7 +367,7 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 	for (i = 0; i < ARRAY_SIZE(mdp4_crtcs); i++) {
 		plane = mdp4_plane_init(dev, rgb_planes[i], true);
 		if (IS_ERR(plane)) {
-			dev_err(dev->dev,
+			DRM_DEV_ERROR(dev->dev,
 				"failed to construct plane for RGB%d\n", i + 1);
 			ret = PTR_ERR(plane);
 			goto fail;
@@ -374,7 +376,7 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 		crtc  = mdp4_crtc_init(dev, plane, priv->num_crtcs, i,
 				mdp4_crtcs[i]);
 		if (IS_ERR(crtc)) {
-			dev_err(dev->dev, "failed to construct crtc for %s\n",
+			DRM_DEV_ERROR(dev->dev, "failed to construct crtc for %s\n",
 				mdp4_crtc_names[i]);
 			ret = PTR_ERR(crtc);
 			goto fail;
@@ -396,7 +398,7 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 	for (i = 0; i < ARRAY_SIZE(mdp4_intfs); i++) {
 		ret = mdp4_modeset_init_intf(mdp4_kms, mdp4_intfs[i]);
 		if (ret) {
-			dev_err(dev->dev, "failed to initialize intf: %d, %d\n",
+			DRM_DEV_ERROR(dev->dev, "failed to initialize intf: %d, %d\n",
 				i, ret);
 			goto fail;
 		}
@@ -419,7 +421,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 
 	mdp4_kms = kzalloc(sizeof(*mdp4_kms), GFP_KERNEL);
 	if (!mdp4_kms) {
-		dev_err(dev->dev, "failed to allocate kms\n");
+		DRM_DEV_ERROR(dev->dev, "failed to allocate kms\n");
 		ret = -ENOMEM;
 		goto fail;
 	}
@@ -439,7 +441,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = irq;
-		dev_err(dev->dev, "failed to get irq: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get irq: %d\n", ret);
 		goto fail;
 	}
 
@@ -456,14 +458,14 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	if (mdp4_kms->vdd) {
 		ret = regulator_enable(mdp4_kms->vdd);
 		if (ret) {
-			dev_err(dev->dev, "failed to enable regulator vdd: %d\n", ret);
+			DRM_DEV_ERROR(dev->dev, "failed to enable regulator vdd: %d\n", ret);
 			goto fail;
 		}
 	}
 
 	mdp4_kms->clk = devm_clk_get(&pdev->dev, "core_clk");
 	if (IS_ERR(mdp4_kms->clk)) {
-		dev_err(dev->dev, "failed to get core_clk\n");
+		DRM_DEV_ERROR(dev->dev, "failed to get core_clk\n");
 		ret = PTR_ERR(mdp4_kms->clk);
 		goto fail;
 	}
@@ -472,23 +474,25 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	if (IS_ERR(mdp4_kms->pclk))
 		mdp4_kms->pclk = NULL;
 
-	// XXX if (rev >= MDP_REV_42) { ???
-	mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
-	if (IS_ERR(mdp4_kms->lut_clk)) {
-		dev_err(dev->dev, "failed to get lut_clk\n");
-		ret = PTR_ERR(mdp4_kms->lut_clk);
-		goto fail;
+	if (mdp4_kms->rev >= 2) {
+		mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
+		if (IS_ERR(mdp4_kms->lut_clk)) {
+			DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n");
+			ret = PTR_ERR(mdp4_kms->lut_clk);
+			goto fail;
+		}
 	}
 
 	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "bus_clk");
 	if (IS_ERR(mdp4_kms->axi_clk)) {
-		dev_err(dev->dev, "failed to get axi_clk\n");
+		DRM_DEV_ERROR(dev->dev, "failed to get axi_clk\n");
 		ret = PTR_ERR(mdp4_kms->axi_clk);
 		goto fail;
 	}
 
 	clk_set_rate(mdp4_kms->clk, config->max_clk);
-	clk_set_rate(mdp4_kms->lut_clk, config->max_clk);
+	if (mdp4_kms->lut_clk)
+		clk_set_rate(mdp4_kms->lut_clk, config->max_clk);
 
 	pm_runtime_enable(dev->dev);
 	mdp4_kms->rpm_enabled = true;
@@ -519,29 +523,29 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		if (ret)
 			goto fail;
 	} else {
-		dev_info(dev->dev, "no iommu, fallback to phys "
+		DRM_DEV_INFO(dev->dev, "no iommu, fallback to phys "
 				"contig buffers for scanout\n");
 		aspace = NULL;
 	}
 
 	ret = modeset_init(mdp4_kms);
 	if (ret) {
-		dev_err(dev->dev, "modeset_init failed: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "modeset_init failed: %d\n", ret);
 		goto fail;
 	}
 
-	mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC);
+	mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC | MSM_BO_SCANOUT);
 	if (IS_ERR(mdp4_kms->blank_cursor_bo)) {
 		ret = PTR_ERR(mdp4_kms->blank_cursor_bo);
-		dev_err(dev->dev, "could not allocate blank-cursor bo: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "could not allocate blank-cursor bo: %d\n", ret);
 		mdp4_kms->blank_cursor_bo = NULL;
 		goto fail;
 	}
 
-	ret = msm_gem_get_iova(mdp4_kms->blank_cursor_bo, kms->aspace,
+	ret = msm_gem_get_and_pin_iova(mdp4_kms->blank_cursor_bo, kms->aspace,
 			&mdp4_kms->blank_cursor_iova);
 	if (ret) {
-		dev_err(dev->dev, "could not pin blank-cursor bo: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "could not pin blank-cursor bo: %d\n", ret);
 		goto fail;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
index 2bfb39082f54..c9e34501a89e 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
@@ -47,7 +47,7 @@ static void bs_init(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder)
 	struct lcdc_platform_data *lcdc_pdata = mdp4_find_pdata("lvds.0");
 
 	if (!lcdc_pdata) {
-		dev_err(dev->dev, "could not find lvds pdata\n");
+		DRM_DEV_ERROR(dev->dev, "could not find lvds pdata\n");
 		return;
 	}
 
@@ -224,7 +224,7 @@ static void setup_phy(struct drm_encoder *encoder)
 		break;
 
 	default:
-		dev_err(dev->dev, "unknown bpp: %d\n", bpp);
+		DRM_DEV_ERROR(dev->dev, "unknown bpp: %d\n", bpp);
 		return;
 	}
 
@@ -241,7 +241,7 @@ static void setup_phy(struct drm_encoder *encoder)
 				MDP4_LCDC_LVDS_INTF_CTL_CH1_CLK_LANE_EN;
 		break;
 	default:
-		dev_err(dev->dev, "unknown # of channels: %d\n", nchan);
+		DRM_DEV_ERROR(dev->dev, "unknown # of channels: %d\n", nchan);
 		return;
 	}
 
@@ -361,7 +361,7 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder)
 	for (i = 0; i < ARRAY_SIZE(mdp4_lcdc_encoder->regs); i++) {
 		ret = regulator_disable(mdp4_lcdc_encoder->regs[i]);
 		if (ret)
-			dev_err(dev->dev, "failed to disable regulator: %d\n", ret);
+			DRM_DEV_ERROR(dev->dev, "failed to disable regulator: %d\n", ret);
 	}
 
 	bs_set(mdp4_lcdc_encoder, 0);
@@ -377,20 +377,25 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder)
 	unsigned long pc = mdp4_lcdc_encoder->pixclock;
 	struct mdp4_kms *mdp4_kms = get_kms(encoder);
 	struct drm_panel *panel;
+	uint32_t config;
 	int i, ret;
 
 	if (WARN_ON(mdp4_lcdc_encoder->enabled))
 		return;
 
 	/* TODO: hard-coded for 18bpp: */
-	mdp4_crtc_set_config(encoder->crtc,
-			MDP4_DMA_CONFIG_R_BPC(BPC6) |
-			MDP4_DMA_CONFIG_G_BPC(BPC6) |
-			MDP4_DMA_CONFIG_B_BPC(BPC6) |
-			MDP4_DMA_CONFIG_PACK_ALIGN_MSB |
-			MDP4_DMA_CONFIG_PACK(0x21) |
-			MDP4_DMA_CONFIG_DEFLKR_EN |
-			MDP4_DMA_CONFIG_DITHER_EN);
+	config =
+		MDP4_DMA_CONFIG_R_BPC(BPC6) |
+		MDP4_DMA_CONFIG_G_BPC(BPC6) |
+		MDP4_DMA_CONFIG_B_BPC(BPC6) |
+		MDP4_DMA_CONFIG_PACK(0x21) |
+		MDP4_DMA_CONFIG_DEFLKR_EN |
+		MDP4_DMA_CONFIG_DITHER_EN;
+
+	if (!of_property_read_bool(dev->dev->of_node, "qcom,lcdc-align-lsb"))
+		config |= MDP4_DMA_CONFIG_PACK_ALIGN_MSB;
+
+	mdp4_crtc_set_config(encoder->crtc, config);
 	mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV, 0);
 
 	bs_set(mdp4_lcdc_encoder, 1);
@@ -398,16 +403,16 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder)
 	for (i = 0; i < ARRAY_SIZE(mdp4_lcdc_encoder->regs); i++) {
 		ret = regulator_enable(mdp4_lcdc_encoder->regs[i]);
 		if (ret)
-			dev_err(dev->dev, "failed to enable regulator: %d\n", ret);
+			DRM_DEV_ERROR(dev->dev, "failed to enable regulator: %d\n", ret);
 	}
 
 	DBG("setting lcdc_clk=%lu", pc);
 	ret = clk_set_rate(mdp4_lcdc_encoder->lcdc_clk, pc);
 	if (ret)
-		dev_err(dev->dev, "failed to configure lcdc_clk: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to configure lcdc_clk: %d\n", ret);
 	ret = clk_prepare_enable(mdp4_lcdc_encoder->lcdc_clk);
 	if (ret)
-		dev_err(dev->dev, "failed to enable lcdc_clk: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to enable lcdc_clk: %d\n", ret);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
 	if (!IS_ERR(panel)) {
@@ -461,7 +466,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
 	/* TODO: do we need different pll in other cases? */
 	mdp4_lcdc_encoder->lcdc_clk = mpd4_lvds_pll_init(dev);
 	if (IS_ERR(mdp4_lcdc_encoder->lcdc_clk)) {
-		dev_err(dev->dev, "failed to get lvds_clk\n");
+		DRM_DEV_ERROR(dev->dev, "failed to get lvds_clk\n");
 		ret = PTR_ERR(mdp4_lcdc_encoder->lcdc_clk);
 		goto fail;
 	}
@@ -470,7 +475,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
 	reg = devm_regulator_get(dev->dev, "lvds-vccs-3p3v");
 	if (IS_ERR(reg)) {
 		ret = PTR_ERR(reg);
-		dev_err(dev->dev, "failed to get lvds-vccs-3p3v: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get lvds-vccs-3p3v: %d\n", ret);
 		goto fail;
 	}
 	mdp4_lcdc_encoder->regs[0] = reg;
@@ -478,7 +483,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
 	reg = devm_regulator_get(dev->dev, "lvds-pll-vdda");
 	if (IS_ERR(reg)) {
 		ret = PTR_ERR(reg);
-		dev_err(dev->dev, "failed to get lvds-pll-vdda: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get lvds-pll-vdda: %d\n", ret);
 		goto fail;
 	}
 	mdp4_lcdc_encoder->regs[1] = reg;
@@ -486,7 +491,7 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
 	reg = devm_regulator_get(dev->dev, "lvds-vdda");
 	if (IS_ERR(reg)) {
 		ret = PTR_ERR(reg);
-		dev_err(dev->dev, "failed to get lvds-vdda: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get lvds-vdda: %d\n", ret);
 		goto fail;
 	}
 	mdp4_lcdc_encoder->regs[2] = reg;
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index 7a499731ce93..005066f7154d 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -234,22 +234,22 @@ static int mdp4_plane_mode_set(struct drm_plane *plane,
 	format = to_mdp_format(msm_framebuffer_format(fb));
 
 	if (src_w > (crtc_w * DOWN_SCALE_MAX)) {
-		dev_err(dev->dev, "Width down scaling exceeds limits!\n");
+		DRM_DEV_ERROR(dev->dev, "Width down scaling exceeds limits!\n");
 		return -ERANGE;
 	}
 
 	if (src_h > (crtc_h * DOWN_SCALE_MAX)) {
-		dev_err(dev->dev, "Height down scaling exceeds limits!\n");
+		DRM_DEV_ERROR(dev->dev, "Height down scaling exceeds limits!\n");
 		return -ERANGE;
 	}
 
 	if (crtc_w > (src_w * UP_SCALE_MAX)) {
-		dev_err(dev->dev, "Width up scaling exceeds limits!\n");
+		DRM_DEV_ERROR(dev->dev, "Width up scaling exceeds limits!\n");
 		return -ERANGE;
 	}
 
 	if (crtc_h > (src_h * UP_SCALE_MAX)) {
-		dev_err(dev->dev, "Height up scaling exceeds limits!\n");
+		DRM_DEV_ERROR(dev->dev, "Height up scaling exceeds limits!\n");
 		return -ERANGE;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index 824067d2d427..ea8f7d7daf7f 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -553,6 +553,91 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	.max_clk = 412500000,
 };
 
+const struct mdp5_cfg_hw msm8917_config = {
+	.name = "msm8917",
+	.mdp = {
+		.count = 1,
+		.caps = MDP_CAP_CDM,
+	},
+	.ctl = {
+		.count = 3,
+		.base = { 0x01000, 0x01200, 0x01400 },
+		.flush_hw_mask = 0xffffffff,
+	},
+	.pipe_vig = {
+		.count = 1,
+		.base = { 0x04000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SCALE	|
+			MDP_PIPE_CAP_CSC	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_rgb = {
+		.count = 2,
+		.base = { 0x14000, 0x16000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_dma = {
+		.count = 1,
+		.base = { 0x24000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_cursor = {
+		.count = 1,
+		.base = { 0x34000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			MDP_PIPE_CAP_CURSOR	|
+			0,
+	},
+
+	.lm = {
+		.count = 2,
+		.base = { 0x44000, 0x45000 },
+		.instances = {
+				{ .id = 0, .pp = 0, .dspp = 0,
+				  .caps = MDP_LM_CAP_DISPLAY, },
+				{ .id = 1, .pp = -1, .dspp = -1,
+				  .caps = MDP_LM_CAP_WB },
+			     },
+		.nb_stages = 8,
+		.max_width = 2048,
+		.max_height = 0xFFFF,
+	},
+	.dspp = {
+		.count = 1,
+		.base = { 0x54000 },
+
+	},
+	.pp = {
+		.count = 1,
+		.base = { 0x70000 },
+	},
+	.cdm = {
+		.count = 1,
+		.base = { 0x79200 },
+	},
+	.intf = {
+		.base = { 0x6a000, 0x6a800 },
+		.connect = {
+			[0] = INTF_DISABLED,
+			[1] = INTF_DSI,
+		},
+	},
+	.max_clk = 320000000,
+};
+
 static const struct mdp5_cfg_handler cfg_handlers[] = {
 	{ .revision = 0, .config = { .hw = &msm8x74v1_config } },
 	{ .revision = 2, .config = { .hw = &msm8x74v2_config } },
@@ -560,6 +645,7 @@ static const struct mdp5_cfg_handler cfg_handlers[] = {
 	{ .revision = 6, .config = { .hw = &msm8x16_config } },
 	{ .revision = 9, .config = { .hw = &msm8x94_config } },
 	{ .revision = 7, .config = { .hw = &msm8x96_config } },
+	{ .revision = 15, .config = { .hw = &msm8917_config } },
 };
 
 static struct mdp5_cfg_platform *mdp5_get_config(struct platform_device *dev);
@@ -600,7 +686,7 @@ struct mdp5_cfg_handler *mdp5_cfg_init(struct mdp5_kms *mdp5_kms,
 	}
 
 	if (major != 1) {
-		dev_err(dev->dev, "unexpected MDP major version: v%d.%d\n",
+		DRM_DEV_ERROR(dev->dev, "unexpected MDP major version: v%d.%d\n",
 				major, minor);
 		ret = -ENXIO;
 		goto fail;
@@ -615,7 +701,7 @@ struct mdp5_cfg_handler *mdp5_cfg_init(struct mdp5_kms *mdp5_kms,
 		break;
 	}
 	if (unlikely(!mdp5_cfg)) {
-		dev_err(dev->dev, "unexpected MDP minor revision: v%d.%d\n",
+		DRM_DEV_ERROR(dev->dev, "unexpected MDP minor revision: v%d.%d\n",
 				major, minor);
 		ret = -ENXIO;
 		goto fail;
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c
index d6f79dc755b4..c1962f29ec7d 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c
@@ -55,20 +55,20 @@ static int pingpong_tearcheck_setup(struct drm_encoder *encoder,
 	int pp_id = mixer->pp;
 
 	if (IS_ERR_OR_NULL(mdp5_kms->vsync_clk)) {
-		dev_err(dev, "vsync_clk is not initialized\n");
+		DRM_DEV_ERROR(dev, "vsync_clk is not initialized\n");
 		return -EINVAL;
 	}
 
 	total_lines_x100 = mode->vtotal * mode->vrefresh;
 	if (!total_lines_x100) {
-		dev_err(dev, "%s: vtotal(%d) or vrefresh(%d) is 0\n",
+		DRM_DEV_ERROR(dev, "%s: vtotal(%d) or vrefresh(%d) is 0\n",
 				__func__, mode->vtotal, mode->vrefresh);
 		return -EINVAL;
 	}
 
 	vsync_clk_speed = clk_round_rate(mdp5_kms->vsync_clk, VSYNC_CLK_RATE);
 	if (vsync_clk_speed <= 0) {
-		dev_err(dev, "vsync_clk round rate failed %ld\n",
+		DRM_DEV_ERROR(dev, "vsync_clk round rate failed %ld\n",
 							vsync_clk_speed);
 		return -EINVAL;
 	}
@@ -102,13 +102,13 @@ static int pingpong_tearcheck_enable(struct drm_encoder *encoder)
 	ret = clk_set_rate(mdp5_kms->vsync_clk,
 		clk_round_rate(mdp5_kms->vsync_clk, VSYNC_CLK_RATE));
 	if (ret) {
-		dev_err(encoder->dev->dev,
+		DRM_DEV_ERROR(encoder->dev->dev,
 			"vsync_clk clk_set_rate failed, %d\n", ret);
 		return ret;
 	}
 	ret = clk_prepare_enable(mdp5_kms->vsync_clk);
 	if (ret) {
-		dev_err(encoder->dev->dev,
+		DRM_DEV_ERROR(encoder->dev->dev,
 			"vsync_clk clk_prepare_enable failed, %d\n", ret);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index b1da9ce54379..c5fde1a4191a 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -173,7 +173,7 @@ static void unref_cursor_worker(struct drm_flip_work *work, void *val)
 	struct mdp5_kms *mdp5_kms = get_kms(&mdp5_crtc->base);
 	struct msm_kms *kms = &mdp5_kms->base.base;
 
-	msm_gem_put_iova(val, kms->aspace);
+	msm_gem_unpin_iova(val, kms->aspace);
 	drm_gem_object_put_unlocked(val);
 }
 
@@ -662,7 +662,7 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
 
 	ret = mdp5_crtc_setup_pipeline(crtc, state, need_right_mixer);
 	if (ret) {
-		dev_err(dev->dev, "couldn't assign mixers %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "couldn't assign mixers %d\n", ret);
 		return ret;
 	}
 
@@ -679,7 +679,7 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
 	 * and that we don't have conflicting mixer stages:
 	 */
 	if ((cnt + start - 1) >= hw_cfg->lm.nb_stages) {
-		dev_err(dev->dev, "too many planes! cnt=%d, start stage=%d\n",
+		DRM_DEV_ERROR(dev->dev, "too many planes! cnt=%d, start stage=%d\n",
 			cnt, start);
 		return -EINVAL;
 	}
@@ -879,7 +879,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 	}
 
 	if ((width > CURSOR_WIDTH) || (height > CURSOR_HEIGHT)) {
-		dev_err(dev->dev, "bad cursor size: %dx%d\n", width, height);
+		DRM_DEV_ERROR(dev->dev, "bad cursor size: %dx%d\n", width, height);
 		return -EINVAL;
 	}
 
@@ -903,7 +903,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 	if (!cursor_bo)
 		return -ENOENT;
 
-	ret = msm_gem_get_iova(cursor_bo, kms->aspace,
+	ret = msm_gem_get_and_pin_iova(cursor_bo, kms->aspace,
 			&mdp5_crtc->cursor.iova);
 	if (ret)
 		return -EINVAL;
@@ -924,7 +924,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 set_cursor:
 	ret = mdp5_ctl_set_cursor(ctl, pipeline, 0, cursor_enable);
 	if (ret) {
-		dev_err(dev->dev, "failed to %sable cursor: %d\n",
+		DRM_DEV_ERROR(dev->dev, "failed to %sable cursor: %d\n",
 				cursor_enable ? "en" : "dis", ret);
 		goto end;
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c
index f93d5681267c..65a871f9f0d9 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c
@@ -262,13 +262,13 @@ int mdp5_ctl_set_cursor(struct mdp5_ctl *ctl, struct mdp5_pipeline *pipeline,
 	struct mdp5_hw_mixer *mixer = pipeline->mixer;
 
 	if (unlikely(WARN_ON(!mixer))) {
-		dev_err(ctl_mgr->dev->dev, "CTL %d cannot find LM",
+		DRM_DEV_ERROR(ctl_mgr->dev->dev, "CTL %d cannot find LM",
 			ctl->id);
 		return -EINVAL;
 	}
 
 	if (pipeline->r_mixer) {
-		dev_err(ctl_mgr->dev->dev, "unsupported configuration");
+		DRM_DEV_ERROR(ctl_mgr->dev->dev, "unsupported configuration");
 		return -EINVAL;
 	}
 
@@ -604,10 +604,10 @@ int mdp5_ctl_pair(struct mdp5_ctl *ctlx, struct mdp5_ctl *ctly, bool enable)
 		mdp5_write(mdp5_kms, REG_MDP5_SPARE_0, 0);
 		return 0;
 	} else if ((ctlx->pair != NULL) || (ctly->pair != NULL)) {
-		dev_err(ctl_mgr->dev->dev, "CTLs already paired\n");
+		DRM_DEV_ERROR(ctl_mgr->dev->dev, "CTLs already paired\n");
 		return -EINVAL;
 	} else if (!(ctlx->status & ctly->status & CTL_STAT_BOOKED)) {
-		dev_err(ctl_mgr->dev->dev, "Only pair booked CTLs\n");
+		DRM_DEV_ERROR(ctl_mgr->dev->dev, "Only pair booked CTLs\n");
 		return -EINVAL;
 	}
 
@@ -652,7 +652,7 @@ struct mdp5_ctl *mdp5_ctlm_request(struct mdp5_ctl_manager *ctl_mgr,
 		if ((ctl_mgr->ctls[c].status & checkm) == match)
 			goto found;
 
-	dev_err(ctl_mgr->dev->dev, "No more CTL available!");
+	DRM_DEV_ERROR(ctl_mgr->dev->dev, "No more CTL available!");
 	goto unlock;
 
 found:
@@ -698,13 +698,13 @@ struct mdp5_ctl_manager *mdp5_ctlm_init(struct drm_device *dev,
 
 	ctl_mgr = kzalloc(sizeof(*ctl_mgr), GFP_KERNEL);
 	if (!ctl_mgr) {
-		dev_err(dev->dev, "failed to allocate CTL manager\n");
+		DRM_DEV_ERROR(dev->dev, "failed to allocate CTL manager\n");
 		ret = -ENOMEM;
 		goto fail;
 	}
 
 	if (unlikely(WARN_ON(ctl_cfg->count > MAX_CTL))) {
-		dev_err(dev->dev, "Increase static pool size to at least %d\n",
+		DRM_DEV_ERROR(dev->dev, "Increase static pool size to at least %d\n",
 				ctl_cfg->count);
 		ret = -ENOSPC;
 		goto fail;
@@ -723,7 +723,7 @@ struct mdp5_ctl_manager *mdp5_ctlm_init(struct drm_device *dev,
 		struct mdp5_ctl *ctl = &ctl_mgr->ctls[c];
 
 		if (WARN_ON(!ctl_cfg->base[c])) {
-			dev_err(dev->dev, "CTL_%d: base is null!\n", c);
+			DRM_DEV_ERROR(dev->dev, "CTL_%d: base is null!\n", c);
 			ret = -EINVAL;
 			spin_unlock_irqrestore(&ctl_mgr->pool_lock, flags);
 			goto fail;
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index bddd625ab91b..d27e35a217bd 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -264,7 +264,7 @@ static int mdp5_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
 			minor->debugfs_root, minor);
 
 	if (ret) {
-		dev_err(dev->dev, "could not install mdp5_debugfs_list\n");
+		DRM_DEV_ERROR(dev->dev, "could not install mdp5_debugfs_list\n");
 		return ret;
 	}
 
@@ -337,7 +337,7 @@ static struct drm_encoder *construct_encoder(struct mdp5_kms *mdp5_kms,
 
 	encoder = mdp5_encoder_init(dev, intf, ctl);
 	if (IS_ERR(encoder)) {
-		dev_err(dev->dev, "failed to construct encoder\n");
+		DRM_DEV_ERROR(dev->dev, "failed to construct encoder\n");
 		return encoder;
 	}
 
@@ -418,7 +418,7 @@ static int modeset_init_intf(struct mdp5_kms *mdp5_kms,
 		int dsi_id = get_dsi_id_from_intf(hw_cfg, intf->num);
 
 		if ((dsi_id >= ARRAY_SIZE(priv->dsi)) || (dsi_id < 0)) {
-			dev_err(dev->dev, "failed to find dsi from intf %d\n",
+			DRM_DEV_ERROR(dev->dev, "failed to find dsi from intf %d\n",
 				intf->num);
 			ret = -EINVAL;
 			break;
@@ -443,7 +443,7 @@ static int modeset_init_intf(struct mdp5_kms *mdp5_kms,
 		break;
 	}
 	default:
-		dev_err(dev->dev, "unknown intf: %d\n", intf->type);
+		DRM_DEV_ERROR(dev->dev, "unknown intf: %d\n", intf->type);
 		ret = -EINVAL;
 		break;
 	}
@@ -500,7 +500,7 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 		plane = mdp5_plane_init(dev, type);
 		if (IS_ERR(plane)) {
 			ret = PTR_ERR(plane);
-			dev_err(dev->dev, "failed to construct plane %d (%d)\n", i, ret);
+			DRM_DEV_ERROR(dev->dev, "failed to construct plane %d (%d)\n", i, ret);
 			goto fail;
 		}
 		priv->planes[priv->num_planes++] = plane;
@@ -517,7 +517,7 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 		crtc  = mdp5_crtc_init(dev, primary[i], cursor[i], i);
 		if (IS_ERR(crtc)) {
 			ret = PTR_ERR(crtc);
-			dev_err(dev->dev, "failed to construct crtc %d (%d)\n", i, ret);
+			DRM_DEV_ERROR(dev->dev, "failed to construct crtc %d (%d)\n", i, ret);
 			goto fail;
 		}
 		priv->crtcs[priv->num_crtcs++] = crtc;
@@ -552,7 +552,7 @@ static void read_mdp_hw_revision(struct mdp5_kms *mdp5_kms,
 	*major = FIELD(version, MDP5_HW_VERSION_MAJOR);
 	*minor = FIELD(version, MDP5_HW_VERSION_MINOR);
 
-	dev_info(dev, "MDP5 version v%d.%d", *major, *minor);
+	DRM_DEV_INFO(dev, "MDP5 version v%d.%d", *major, *minor);
 }
 
 static int get_clk(struct platform_device *pdev, struct clk **clkp,
@@ -561,7 +561,7 @@ static int get_clk(struct platform_device *pdev, struct clk **clkp,
 	struct device *dev = &pdev->dev;
 	struct clk *clk = msm_clk_get(pdev, name);
 	if (IS_ERR(clk) && mandatory) {
-		dev_err(dev, "failed to get %s (%ld)\n", name, PTR_ERR(clk));
+		DRM_DEV_ERROR(dev, "failed to get %s (%ld)\n", name, PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
 	if (IS_ERR(clk))
@@ -688,7 +688,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (irq < 0) {
 		ret = irq;
-		dev_err(&pdev->dev, "failed to get irq: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "failed to get irq: %d\n", ret);
 		goto fail;
 	}
 
@@ -724,12 +724,12 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
 		if (ret) {
-			dev_err(&pdev->dev, "failed to attach iommu: %d\n",
+			DRM_DEV_ERROR(&pdev->dev, "failed to attach iommu: %d\n",
 				ret);
 			goto fail;
 		}
 	} else {
-		dev_info(&pdev->dev,
+		DRM_DEV_INFO(&pdev->dev,
 			 "no iommu, fallback to phys contig buffers for scanout\n");
 		aspace = NULL;
 	}
@@ -738,7 +738,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 
 	ret = modeset_init(mdp5_kms);
 	if (ret) {
-		dev_err(&pdev->dev, "modeset_init failed: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "modeset_init failed: %d\n", ret);
 		goto fail;
 	}
 
@@ -795,7 +795,7 @@ static int construct_pipes(struct mdp5_kms *mdp5_kms, int cnt,
 		hwpipe = mdp5_pipe_init(pipes[i], offsets[i], caps);
 		if (IS_ERR(hwpipe)) {
 			ret = PTR_ERR(hwpipe);
-			dev_err(dev->dev, "failed to construct pipe for %s (%d)\n",
+			DRM_DEV_ERROR(dev->dev, "failed to construct pipe for %s (%d)\n",
 					pipe2name(pipes[i]), ret);
 			return ret;
 		}
@@ -867,7 +867,7 @@ static int hwmixer_init(struct mdp5_kms *mdp5_kms)
 		mixer = mdp5_mixer_init(&hw_cfg->lm.instances[i]);
 		if (IS_ERR(mixer)) {
 			ret = PTR_ERR(mixer);
-			dev_err(dev->dev, "failed to construct LM%d (%d)\n",
+			DRM_DEV_ERROR(dev->dev, "failed to construct LM%d (%d)\n",
 				i, ret);
 			return ret;
 		}
@@ -897,7 +897,7 @@ static int interface_init(struct mdp5_kms *mdp5_kms)
 
 		intf = kzalloc(sizeof(*intf), GFP_KERNEL);
 		if (!intf) {
-			dev_err(dev->dev, "failed to construct INTF%d\n", i);
+			DRM_DEV_ERROR(dev->dev, "failed to construct INTF%d\n", i);
 			return -ENOMEM;
 		}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
index 1cc4e57f0226..889c2940692c 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
@@ -132,7 +132,7 @@ static int mdss_irq_domain_init(struct mdp5_mdss *mdp5_mdss)
 	d = irq_domain_add_linear(dev->of_node, 32, &mdss_hw_irqdomain_ops,
 				  mdp5_mdss);
 	if (!d) {
-		dev_err(dev, "mdss irq domain add failed\n");
+		DRM_DEV_ERROR(dev, "mdss irq domain add failed\n");
 		return -ENXIO;
 	}
 
@@ -246,7 +246,7 @@ int mdp5_mdss_init(struct drm_device *dev)
 
 	ret = msm_mdss_get_clocks(mdp5_mdss);
 	if (ret) {
-		dev_err(dev->dev, "failed to get clocks: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get clocks: %d\n", ret);
 		goto fail;
 	}
 
@@ -259,7 +259,7 @@ int mdp5_mdss_init(struct drm_device *dev)
 
 	ret = regulator_enable(mdp5_mdss->vdd);
 	if (ret) {
-		dev_err(dev->dev, "failed to enable regulator vdd: %d\n",
+		DRM_DEV_ERROR(dev->dev, "failed to enable regulator vdd: %d\n",
 			ret);
 		goto fail;
 	}
@@ -267,13 +267,13 @@ int mdp5_mdss_init(struct drm_device *dev)
 	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
 			       mdss_irq, 0, "mdss_isr", mdp5_mdss);
 	if (ret) {
-		dev_err(dev->dev, "failed to init irq: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to init irq: %d\n", ret);
 		goto fail_irq;
 	}
 
 	ret = mdss_irq_domain_init(mdp5_mdss);
 	if (ret) {
-		dev_err(dev->dev, "failed to init sub-block irqs: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to init sub-block irqs: %d\n", ret);
 		goto fail_irq;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index 310459541e48..be13140967b4 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -125,7 +125,7 @@ static int mdp5_plane_atomic_set_property(struct drm_plane *plane,
 
 	SET_PROPERTY(zpos, ZPOS, uint8_t);
 
-	dev_err(dev->dev, "Invalid property\n");
+	DRM_DEV_ERROR(dev->dev, "Invalid property\n");
 	ret = -EINVAL;
 done:
 	return ret;
@@ -153,7 +153,7 @@ static int mdp5_plane_atomic_get_property(struct drm_plane *plane,
 
 	GET_PROPERTY(zpos, ZPOS, uint8_t);
 
-	dev_err(dev->dev, "Invalid property\n");
+	DRM_DEV_ERROR(dev->dev, "Invalid property\n");
 	ret = -EINVAL;
 done:
 	return ret;
@@ -658,7 +658,7 @@ static int calc_scalex_steps(struct drm_plane *plane,
 
 	ret = calc_phase_step(src, dest, &phasex_step);
 	if (ret) {
-		dev_err(dev, "X scaling (%d->%d) failed: %d\n", src, dest, ret);
+		DRM_DEV_ERROR(dev, "X scaling (%d->%d) failed: %d\n", src, dest, ret);
 		return ret;
 	}
 
@@ -683,7 +683,7 @@ static int calc_scaley_steps(struct drm_plane *plane,
 
 	ret = calc_phase_step(src, dest, &phasey_step);
 	if (ret) {
-		dev_err(dev, "Y scaling (%d->%d) failed: %d\n", src, dest, ret);
+		DRM_DEV_ERROR(dev, "Y scaling (%d->%d) failed: %d\n", src, dest, ret);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index 96c2b828dba4..7cebcb2b3a37 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -88,7 +88,7 @@ static int smp_request_block(struct mdp5_smp *smp,
 
 	avail = cnt - bitmap_weight(state->state, cnt);
 	if (nblks > avail) {
-		dev_err(smp->dev->dev, "out of blks (req=%d > avail=%d)\n",
+		DRM_DEV_ERROR(smp->dev->dev, "out of blks (req=%d > avail=%d)\n",
 				nblks, avail);
 		return -ENOSPC;
 	}
@@ -188,7 +188,7 @@ int mdp5_smp_assign(struct mdp5_smp *smp, struct mdp5_smp_state *state,
 		DBG("%s[%d]: request %d SMP blocks", pipe2name(pipe), i, n);
 		ret = smp_request_block(smp, state, cid, n);
 		if (ret) {
-			dev_err(dev->dev, "Cannot allocate %d SMP blocks: %d\n",
+			DRM_DEV_ERROR(dev->dev, "Cannot allocate %d SMP blocks: %d\n",
 					n, ret);
 			return ret;
 		}
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index a9768f823290..7b2a1e6a8810 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -29,7 +29,7 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 
 	phy_node = of_parse_phandle(pdev->dev.of_node, "phys", 0);
 	if (!phy_node) {
-		dev_err(&pdev->dev, "cannot find phy device\n");
+		DRM_DEV_ERROR(&pdev->dev, "cannot find phy device\n");
 		return -ENXIO;
 	}
 
@@ -40,7 +40,7 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 	of_node_put(phy_node);
 
 	if (!phy_pdev || !msm_dsi->phy) {
-		dev_err(&pdev->dev, "%s: phy driver is not ready\n", __func__);
+		DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__);
 		return -EPROBE_DEFER;
 	}
 
@@ -210,7 +210,7 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 
 	ret = msm_dsi_host_modeset_init(msm_dsi->host, dev);
 	if (ret) {
-		dev_err(dev->dev, "failed to modeset init host: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to modeset init host: %d\n", ret);
 		goto fail;
 	}
 
@@ -222,7 +222,7 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 	msm_dsi->bridge = msm_dsi_manager_bridge_init(msm_dsi->id);
 	if (IS_ERR(msm_dsi->bridge)) {
 		ret = PTR_ERR(msm_dsi->bridge);
-		dev_err(dev->dev, "failed to create dsi bridge: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to create dsi bridge: %d\n", ret);
 		msm_dsi->bridge = NULL;
 		goto fail;
 	}
@@ -244,7 +244,7 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 
 	if (IS_ERR(msm_dsi->connector)) {
 		ret = PTR_ERR(msm_dsi->connector);
-		dev_err(dev->dev,
+		DRM_DEV_ERROR(dev->dev,
 			"failed to create dsi connector: %d\n", ret);
 		msm_dsi->connector = NULL;
 		goto fail;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 9c6c523eacdc..38e481d2d606 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1050,7 +1050,7 @@ static void dsi_wait4video_done(struct msm_dsi_host *msm_host)
 			msecs_to_jiffies(70));
 
 	if (ret <= 0)
-		dev_err(dev, "wait for video done timed out\n");
+		DRM_DEV_ERROR(dev, "wait for video done timed out\n");
 
 	dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 0);
 }
@@ -1083,6 +1083,8 @@ int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size)
 		return PTR_ERR(data);
 	}
 
+	msm_gem_object_set_name(msm_host->tx_gem_obj, "tx_gem");
+
 	msm_host->tx_size = msm_host->tx_gem_obj->size;
 
 	return 0;
@@ -1118,7 +1120,7 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 
 	priv = dev->dev_private;
 	if (msm_host->tx_gem_obj) {
-		msm_gem_put_iova(msm_host->tx_gem_obj, priv->kms->aspace);
+		msm_gem_unpin_iova(msm_host->tx_gem_obj, priv->kms->aspace);
 		drm_gem_object_put_unlocked(msm_host->tx_gem_obj);
 		msm_host->tx_gem_obj = NULL;
 	}
@@ -1248,7 +1250,7 @@ int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *dma_base)
 	if (!dma_base)
 		return -EINVAL;
 
-	return msm_gem_get_iova(msm_host->tx_gem_obj,
+	return msm_gem_get_and_pin_iova(msm_host->tx_gem_obj,
 				priv->kms->aspace, dma_base);
 }
 
@@ -1673,7 +1675,7 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 
 	prop = of_find_property(ep, "data-lanes", &len);
 	if (!prop) {
-		dev_dbg(dev,
+		DRM_DEV_DEBUG(dev,
 			"failed to find data lane mapping, using default\n");
 		return 0;
 	}
@@ -1681,7 +1683,7 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 	num_lanes = len / sizeof(u32);
 
 	if (num_lanes < 1 || num_lanes > 4) {
-		dev_err(dev, "bad number of data lanes\n");
+		DRM_DEV_ERROR(dev, "bad number of data lanes\n");
 		return -EINVAL;
 	}
 
@@ -1690,7 +1692,7 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 	ret = of_property_read_u32_array(ep, "data-lanes", lane_map,
 					 num_lanes);
 	if (ret) {
-		dev_err(dev, "failed to read lane data\n");
+		DRM_DEV_ERROR(dev, "failed to read lane data\n");
 		return ret;
 	}
 
@@ -1711,7 +1713,7 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 		 */
 		for (j = 0; j < num_lanes; j++) {
 			if (lane_map[j] < 0 || lane_map[j] > 3)
-				dev_err(dev, "bad physical lane entry %u\n",
+				DRM_DEV_ERROR(dev, "bad physical lane entry %u\n",
 					lane_map[j]);
 
 			if (swap[lane_map[j]] != j)
@@ -1742,13 +1744,13 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host)
 	 */
 	endpoint = of_graph_get_endpoint_by_regs(np, 1, -1);
 	if (!endpoint) {
-		dev_dbg(dev, "%s: no endpoint\n", __func__);
+		DRM_DEV_DEBUG(dev, "%s: no endpoint\n", __func__);
 		return 0;
 	}
 
 	ret = dsi_host_parse_lane_data(msm_host, endpoint);
 	if (ret) {
-		dev_err(dev, "%s: invalid lane configuration %d\n",
+		DRM_DEV_ERROR(dev, "%s: invalid lane configuration %d\n",
 			__func__, ret);
 		ret = -EINVAL;
 		goto err;
@@ -1757,7 +1759,7 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host)
 	/* Get panel node from the output port's endpoint data */
 	device_node = of_graph_get_remote_node(np, 1, 0);
 	if (!device_node) {
-		dev_dbg(dev, "%s: no valid device\n", __func__);
+		DRM_DEV_DEBUG(dev, "%s: no valid device\n", __func__);
 		ret = -ENODEV;
 		goto err;
 	}
@@ -1768,7 +1770,7 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host)
 		msm_host->sfpb = syscon_regmap_lookup_by_phandle(np,
 					"syscon-sfpb");
 		if (IS_ERR(msm_host->sfpb)) {
-			dev_err(dev, "%s: failed to get sfpb regmap\n",
+			DRM_DEV_ERROR(dev, "%s: failed to get sfpb regmap\n",
 				__func__);
 			ret = PTR_ERR(msm_host->sfpb);
 		}
@@ -1918,7 +1920,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 	msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (msm_host->irq < 0) {
 		ret = msm_host->irq;
-		dev_err(dev->dev, "failed to get irq: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get irq: %d\n", ret);
 		return ret;
 	}
 
@@ -1926,7 +1928,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 			dsi_host_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
 			"dsi_isr", msm_host);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to request IRQ%u: %d\n",
+		DRM_DEV_ERROR(&pdev->dev, "failed to request IRQ%u: %d\n",
 				msm_host->irq, ret);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 9a9fa0c75a13..1760483b247e 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -404,7 +404,7 @@ static int dsi_phy_regulator_init(struct msm_dsi_phy *phy)
 
 	ret = devm_regulator_bulk_get(dev, num, s);
 	if (ret < 0) {
-		dev_err(dev, "%s: failed to init regulator, ret=%d\n",
+		DRM_DEV_ERROR(dev, "%s: failed to init regulator, ret=%d\n",
 						__func__, ret);
 		return ret;
 	}
@@ -441,7 +441,7 @@ static int dsi_phy_regulator_enable(struct msm_dsi_phy *phy)
 			ret = regulator_set_load(s[i].consumer,
 							regs[i].enable_load);
 			if (ret < 0) {
-				dev_err(dev,
+				DRM_DEV_ERROR(dev,
 					"regulator %d set op mode failed, %d\n",
 					i, ret);
 				goto fail;
@@ -451,7 +451,7 @@ static int dsi_phy_regulator_enable(struct msm_dsi_phy *phy)
 
 	ret = regulator_bulk_enable(num, s);
 	if (ret < 0) {
-		dev_err(dev, "regulator enable failed, %d\n", ret);
+		DRM_DEV_ERROR(dev, "regulator enable failed, %d\n", ret);
 		goto fail;
 	}
 
@@ -472,7 +472,7 @@ static int dsi_phy_enable_resource(struct msm_dsi_phy *phy)
 
 	ret = clk_prepare_enable(phy->ahb_clk);
 	if (ret) {
-		dev_err(dev, "%s: can't enable ahb clk, %d\n", __func__, ret);
+		DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret);
 		pm_runtime_put_sync(dev);
 	}
 
@@ -543,7 +543,7 @@ int msm_dsi_phy_init_common(struct msm_dsi_phy *phy)
 	phy->reg_base = msm_ioremap(pdev, "dsi_phy_regulator",
 				"DSI_PHY_REG");
 	if (IS_ERR(phy->reg_base)) {
-		dev_err(&pdev->dev, "%s: failed to map phy regulator base\n",
+		DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy regulator base\n",
 			__func__);
 		ret = -ENOMEM;
 		goto fail;
@@ -574,7 +574,7 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 	phy->id = dsi_phy_get_id(phy);
 	if (phy->id < 0) {
 		ret = phy->id;
-		dev_err(dev, "%s: couldn't identify PHY index, %d\n",
+		DRM_DEV_ERROR(dev, "%s: couldn't identify PHY index, %d\n",
 			__func__, ret);
 		goto fail;
 	}
@@ -584,20 +584,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 
 	phy->base = msm_ioremap(pdev, "dsi_phy", "DSI_PHY");
 	if (IS_ERR(phy->base)) {
-		dev_err(dev, "%s: failed to map phy base\n", __func__);
+		DRM_DEV_ERROR(dev, "%s: failed to map phy base\n", __func__);
 		ret = -ENOMEM;
 		goto fail;
 	}
 
 	ret = dsi_phy_regulator_init(phy);
 	if (ret) {
-		dev_err(dev, "%s: failed to init regulator\n", __func__);
+		DRM_DEV_ERROR(dev, "%s: failed to init regulator\n", __func__);
 		goto fail;
 	}
 
 	phy->ahb_clk = msm_clk_get(pdev, "iface");
 	if (IS_ERR(phy->ahb_clk)) {
-		dev_err(dev, "%s: Unable to get ahb clk\n", __func__);
+		DRM_DEV_ERROR(dev, "%s: Unable to get ahb clk\n", __func__);
 		ret = PTR_ERR(phy->ahb_clk);
 		goto fail;
 	}
@@ -617,7 +617,7 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 
 	phy->pll = msm_dsi_pll_init(pdev, phy->cfg->type, phy->id);
 	if (IS_ERR_OR_NULL(phy->pll))
-		dev_info(dev,
+		DRM_DEV_INFO(dev,
 			"%s: pll init failed: %ld, need separate pll clk driver\n",
 			__func__, PTR_ERR(phy->pll));
 
@@ -675,21 +675,21 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 
 	ret = dsi_phy_enable_resource(phy);
 	if (ret) {
-		dev_err(dev, "%s: resource enable failed, %d\n",
+		DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n",
 			__func__, ret);
 		goto res_en_fail;
 	}
 
 	ret = dsi_phy_regulator_enable(phy);
 	if (ret) {
-		dev_err(dev, "%s: regulator enable failed, %d\n",
+		DRM_DEV_ERROR(dev, "%s: regulator enable failed, %d\n",
 			__func__, ret);
 		goto reg_en_fail;
 	}
 
 	ret = phy->cfg->ops.enable(phy, src_pll_id, clk_req);
 	if (ret) {
-		dev_err(dev, "%s: phy enable failed, %d\n", __func__, ret);
+		DRM_DEV_ERROR(dev, "%s: phy enable failed, %d\n", __func__, ret);
 		goto phy_en_fail;
 	}
 
@@ -702,7 +702,7 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 	if (phy->usecase != MSM_DSI_PHY_SLAVE) {
 		ret = msm_dsi_pll_restore_state(phy->pll);
 		if (ret) {
-			dev_err(dev, "%s: failed to restore pll state, %d\n",
+			DRM_DEV_ERROR(dev, "%s: failed to restore pll state, %d\n",
 				__func__, ret);
 			goto pll_restor_fail;
 		}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index b3fffc8dbb2a..44959e79ce28 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -93,7 +93,7 @@ static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 	DBG("");
 
 	if (msm_dsi_dphy_timing_calc_v3(timing, clk_req)) {
-		dev_err(&phy->pdev->dev,
+		DRM_DEV_ERROR(&phy->pdev->dev,
 			"%s: D-PHY timing calculation failed\n", __func__);
 		return -EINVAL;
 	}
@@ -172,7 +172,7 @@ static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 
 	ret = msm_dsi_pll_set_usecase(phy->pll, phy->usecase);
 	if (ret) {
-		dev_err(&phy->pdev->dev, "%s: set pll usecase failed, %d\n",
+		DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n",
 			__func__, ret);
 		return ret;
 	}
@@ -196,7 +196,7 @@ static int dsi_10nm_phy_init(struct msm_dsi_phy *phy)
 	phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane",
 				     "DSI_PHY_LANE");
 	if (IS_ERR(phy->lane_base)) {
-		dev_err(&pdev->dev, "%s: failed to map phy lane base\n",
+		DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n",
 			__func__);
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
index 513f4234adc1..a172c667e8bc 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
@@ -64,7 +64,7 @@ static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 	void __iomem *lane_base = phy->lane_base;
 
 	if (msm_dsi_dphy_timing_calc_v2(timing, clk_req)) {
-		dev_err(&phy->pdev->dev,
+		DRM_DEV_ERROR(&phy->pdev->dev,
 			"%s: D-PHY timing calculation failed\n", __func__);
 		return -EINVAL;
 	}
@@ -115,7 +115,7 @@ static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 
 	ret = msm_dsi_pll_set_usecase(phy->pll, phy->usecase);
 	if (ret) {
-		dev_err(&phy->pdev->dev, "%s: set pll usecase failed, %d\n",
+		DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n",
 			__func__, ret);
 		return ret;
 	}
@@ -142,7 +142,7 @@ static int dsi_14nm_phy_init(struct msm_dsi_phy *phy)
 	phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane",
 				"DSI_PHY_LANE");
 	if (IS_ERR(phy->lane_base)) {
-		dev_err(&pdev->dev, "%s: failed to map phy lane base\n",
+		DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n",
 			__func__);
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
index 1ca6c69516f5..9ea9478d3707 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
@@ -82,7 +82,7 @@ static int dsi_20nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 	DBG("");
 
 	if (msm_dsi_dphy_timing_calc(timing, clk_req)) {
-		dev_err(&phy->pdev->dev,
+		DRM_DEV_ERROR(&phy->pdev->dev,
 			"%s: D-PHY timing calculation failed\n", __func__);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
index 4972b52cbe44..c79505d97fe8 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
@@ -76,7 +76,7 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 	DBG("");
 
 	if (msm_dsi_dphy_timing_calc(timing, clk_req)) {
-		dev_err(&phy->pdev->dev,
+		DRM_DEV_ERROR(&phy->pdev->dev,
 			"%s: D-PHY timing calculation failed\n", __func__);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
index 398004463498..98790b44da48 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
@@ -132,7 +132,7 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 	DBG("");
 
 	if (msm_dsi_dphy_timing_calc(timing, clk_req)) {
-		dev_err(&phy->pdev->dev,
+		DRM_DEV_ERROR(&phy->pdev->dev,
 			"%s: D-PHY timing calculation failed\n", __func__);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
index 613e206fa4fc..7a1fb4da2ad3 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
@@ -175,7 +175,7 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev,
 	}
 
 	if (IS_ERR(pll)) {
-		dev_err(dev, "%s: failed to init DSI PLL\n", __func__);
+		DRM_DEV_ERROR(dev, "%s: failed to init DSI PLL\n", __func__);
 		return pll;
 	}
 
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 4c03f0b7343e..e41f278e4e62 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -17,7 +17,7 @@
  *                              |                |
  *                              |                |
  *                 +---------+  |  +----------+  |  +----+
- *  dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0pllbyte
+ *  dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0_phy_pll_out_byteclk
  *                 +---------+  |  +----------+  |  +----+
  *                              |                |
  *                              |                |         dsi0_pll_by_2_bit_clk
@@ -25,7 +25,7 @@
  *                              |                |  +----+  |  |\  dsi0_pclk_mux
  *                              |                |--| /2 |--o--| \   |
  *                              |                |  +----+     |  \  |  +---------+
- *                              |                --------------|  |--o--| div_7_4 |-- dsi0pll
+ *                              |                --------------|  |--o--| div_7_4 |-- dsi0_phy_pll_out_dsiclk
  *                              |------------------------------|  /     +---------+
  *                              |          +-----+             | /
  *                              -----------| /4? |--o----------|/
@@ -688,7 +688,7 @@ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm)
 
 	hws[num++] = hw;
 
-	snprintf(clk_name, 32, "dsi%dpllbyte", pll_10nm->id);
+	snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_10nm->id);
 	snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->id);
 
 	/* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */
@@ -737,7 +737,7 @@ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm)
 
 	hws[num++] = hw;
 
-	snprintf(clk_name, 32, "dsi%dpll", pll_10nm->id);
+	snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_10nm->id);
 	snprintf(parent, 32, "dsi%d_pclk_mux", pll_10nm->id);
 
 	/* PIX CLK DIV : DIV_CTRL_7_4*/
@@ -760,7 +760,7 @@ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm)
 	ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
 				     pll_10nm->hw_data);
 	if (ret) {
-		dev_err(dev, "failed to register clk provider: %d\n", ret);
+		DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret);
 		return ret;
 	}
 
@@ -788,13 +788,13 @@ struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 
 	pll_10nm->phy_cmn_mmio = msm_ioremap(pdev, "dsi_phy", "DSI_PHY");
 	if (IS_ERR_OR_NULL(pll_10nm->phy_cmn_mmio)) {
-		dev_err(&pdev->dev, "failed to map CMN PHY base\n");
+		DRM_DEV_ERROR(&pdev->dev, "failed to map CMN PHY base\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
 	pll_10nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL");
 	if (IS_ERR_OR_NULL(pll_10nm->mmio)) {
-		dev_err(&pdev->dev, "failed to map PLL base\n");
+		DRM_DEV_ERROR(&pdev->dev, "failed to map PLL base\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -813,7 +813,7 @@ struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 
 	ret = pll_10nm_register(pll_10nm);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register PLL: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
index 71fe60e5f01f..0e18cddd6f22 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
@@ -783,7 +783,7 @@ static int dsi_pll_14nm_enable_seq(struct msm_dsi_pll *pll)
 					 POLL_TIMEOUT_US);
 
 	if (unlikely(!locked))
-		dev_err(&pll_14nm->pdev->dev, "DSI PLL lock failed\n");
+		DRM_DEV_ERROR(&pll_14nm->pdev->dev, "DSI PLL lock failed\n");
 	else
 		DBG("DSI PLL lock success");
 
@@ -829,7 +829,7 @@ static int dsi_pll_14nm_restore_state(struct msm_dsi_pll *pll)
 	ret = dsi_pll_14nm_vco_set_rate(&pll->clk_hw,
 					cached_state->vco_rate, 0);
 	if (ret) {
-		dev_err(&pll_14nm->pdev->dev,
+		DRM_DEV_ERROR(&pll_14nm->pdev->dev,
 			"restore vco rate failed. ret=%d\n", ret);
 		return ret;
 	}
@@ -1039,7 +1039,7 @@ static int pll_14nm_register(struct dsi_pll_14nm *pll_14nm)
 	ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
 				     pll_14nm->hw_data);
 	if (ret) {
-		dev_err(dev, "failed to register clk provider: %d\n", ret);
+		DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret);
 		return ret;
 	}
 
@@ -1067,13 +1067,13 @@ struct msm_dsi_pll *msm_dsi_pll_14nm_init(struct platform_device *pdev, int id)
 
 	pll_14nm->phy_cmn_mmio = msm_ioremap(pdev, "dsi_phy", "DSI_PHY");
 	if (IS_ERR_OR_NULL(pll_14nm->phy_cmn_mmio)) {
-		dev_err(&pdev->dev, "failed to map CMN PHY base\n");
+		DRM_DEV_ERROR(&pdev->dev, "failed to map CMN PHY base\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
 	pll_14nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL");
 	if (IS_ERR_OR_NULL(pll_14nm->mmio)) {
-		dev_err(&pdev->dev, "failed to map PLL base\n");
+		DRM_DEV_ERROR(&pdev->dev, "failed to map PLL base\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1096,7 +1096,7 @@ struct msm_dsi_pll *msm_dsi_pll_14nm_init(struct platform_device *pdev, int id)
 
 	ret = pll_14nm_register(pll_14nm);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register PLL: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
index 26e3a01a99c2..dcbbaeb1b1fb 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
@@ -156,7 +156,7 @@ static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		if (rate <= lpfr_lut[i].vco_rate)
 			break;
 	if (i == LPFR_LUT_SIZE) {
-		dev_err(dev, "unable to get loop filter resistance. vco=%lu\n",
+		DRM_DEV_ERROR(dev, "unable to get loop filter resistance. vco=%lu\n",
 				rate);
 		return -EINVAL;
 	}
@@ -386,7 +386,7 @@ static int dsi_pll_28nm_enable_seq_hpm(struct msm_dsi_pll *pll)
 	}
 
 	if (unlikely(!locked))
-		dev_err(dev, "DSI PLL lock failed\n");
+		DRM_DEV_ERROR(dev, "DSI PLL lock failed\n");
 	else
 		DBG("DSI PLL Lock success");
 
@@ -429,7 +429,7 @@ static int dsi_pll_28nm_enable_seq_lp(struct msm_dsi_pll *pll)
 	locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us);
 
 	if (unlikely(!locked))
-		dev_err(dev, "DSI PLL lock failed\n");
+		DRM_DEV_ERROR(dev, "DSI PLL lock failed\n");
 	else
 		DBG("DSI PLL lock success");
 
@@ -468,7 +468,7 @@ static int dsi_pll_28nm_restore_state(struct msm_dsi_pll *pll)
 	ret = dsi_pll_28nm_clk_set_rate(&pll->clk_hw,
 					cached_state->vco_rate, 0);
 	if (ret) {
-		dev_err(&pll_28nm->pdev->dev,
+		DRM_DEV_ERROR(&pll_28nm->pdev->dev,
 			"restore vco rate failed. ret=%d\n", ret);
 		return ret;
 	}
@@ -581,7 +581,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm)
 	ret = of_clk_add_provider(dev->of_node,
 			of_clk_src_onecell_get, &pll_28nm->clk_data);
 	if (ret) {
-		dev_err(dev, "failed to register clk provider: %d\n", ret);
+		DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret);
 		return ret;
 	}
 
@@ -607,7 +607,7 @@ struct msm_dsi_pll *msm_dsi_pll_28nm_init(struct platform_device *pdev,
 
 	pll_28nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL");
 	if (IS_ERR_OR_NULL(pll_28nm->mmio)) {
-		dev_err(&pdev->dev, "%s: failed to map pll base\n", __func__);
+		DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -633,13 +633,13 @@ struct msm_dsi_pll *msm_dsi_pll_28nm_init(struct platform_device *pdev,
 		pll->en_seq_cnt = 1;
 		pll->enable_seqs[0] = dsi_pll_28nm_enable_seq_lp;
 	} else {
-		dev_err(&pdev->dev, "phy type (%d) is not 28nm\n", type);
+		DRM_DEV_ERROR(&pdev->dev, "phy type (%d) is not 28nm\n", type);
 		return ERR_PTR(-EINVAL);
 	}
 
 	ret = pll_28nm_register(pll_28nm);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register PLL: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
index 49008451085b..d6897464755f 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
@@ -327,7 +327,7 @@ static int dsi_pll_28nm_enable_seq(struct msm_dsi_pll *pll)
 	locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us);
 
 	if (unlikely(!locked))
-		dev_err(dev, "DSI PLL lock failed\n");
+		DRM_DEV_ERROR(dev, "DSI PLL lock failed\n");
 	else
 		DBG("DSI PLL lock success");
 
@@ -368,7 +368,7 @@ static int dsi_pll_28nm_restore_state(struct msm_dsi_pll *pll)
 	ret = dsi_pll_28nm_clk_set_rate(&pll->clk_hw,
 					cached_state->vco_rate, 0);
 	if (ret) {
-		dev_err(&pll_28nm->pdev->dev,
+		DRM_DEV_ERROR(&pll_28nm->pdev->dev,
 			"restore vco rate failed. ret=%d\n", ret);
 		return ret;
 	}
@@ -482,7 +482,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm)
 	ret = of_clk_add_provider(dev->of_node,
 			of_clk_src_onecell_get, &pll_28nm->clk_data);
 	if (ret) {
-		dev_err(dev, "failed to register clk provider: %d\n", ret);
+		DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret);
 		return ret;
 	}
 
@@ -508,7 +508,7 @@ struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev,
 
 	pll_28nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL");
 	if (IS_ERR_OR_NULL(pll_28nm->mmio)) {
-		dev_err(&pdev->dev, "%s: failed to map pll base\n", __func__);
+		DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -526,7 +526,7 @@ struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev,
 
 	ret = pll_28nm_register(pll_28nm);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register PLL: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/gpu/drm/msm/edp/edp.c b/drivers/gpu/drm/msm/edp/edp.c
index 0940e84b2821..6a63aba98a30 100644
--- a/drivers/gpu/drm/msm/edp/edp.c
+++ b/drivers/gpu/drm/msm/edp/edp.c
@@ -157,7 +157,7 @@ int msm_edp_modeset_init(struct msm_edp *edp, struct drm_device *dev,
 	edp->bridge = msm_edp_bridge_init(edp);
 	if (IS_ERR(edp->bridge)) {
 		ret = PTR_ERR(edp->bridge);
-		dev_err(dev->dev, "failed to create eDP bridge: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to create eDP bridge: %d\n", ret);
 		edp->bridge = NULL;
 		goto fail;
 	}
@@ -165,7 +165,7 @@ int msm_edp_modeset_init(struct msm_edp *edp, struct drm_device *dev,
 	edp->connector = msm_edp_connector_init(edp);
 	if (IS_ERR(edp->connector)) {
 		ret = PTR_ERR(edp->connector);
-		dev_err(dev->dev, "failed to create eDP connector: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to create eDP connector: %d\n", ret);
 		edp->connector = NULL;
 		goto fail;
 	}
@@ -173,7 +173,7 @@ int msm_edp_modeset_init(struct msm_edp *edp, struct drm_device *dev,
 	edp->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (edp->irq < 0) {
 		ret = edp->irq;
-		dev_err(dev->dev, "failed to get IRQ: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get IRQ: %d\n", ret);
 		goto fail;
 	}
 
@@ -181,7 +181,7 @@ int msm_edp_modeset_init(struct msm_edp *edp, struct drm_device *dev,
 			edp_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
 			"edp_isr", edp);
 	if (ret < 0) {
-		dev_err(dev->dev, "failed to request IRQ%u: %d\n",
+		DRM_DEV_ERROR(dev->dev, "failed to request IRQ%u: %d\n",
 				edp->irq, ret);
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index 23670907a29d..f0725761b327 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -98,7 +98,7 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi)
 
 	phy_node = of_parse_phandle(pdev->dev.of_node, "phys", 0);
 	if (!phy_node) {
-		dev_err(&pdev->dev, "cannot find phy device\n");
+		DRM_DEV_ERROR(&pdev->dev, "cannot find phy device\n");
 		return -ENXIO;
 	}
 
@@ -109,7 +109,7 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi)
 	of_node_put(phy_node);
 
 	if (!phy_pdev || !hdmi->phy) {
-		dev_err(&pdev->dev, "phy driver is not ready\n");
+		DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n");
 		return -EPROBE_DEFER;
 	}
 
@@ -153,7 +153,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev)
 	hdmi->qfprom_mmio = msm_ioremap(pdev,
 		config->qfprom_mmio_name, "HDMI_QFPROM");
 	if (IS_ERR(hdmi->qfprom_mmio)) {
-		dev_info(&pdev->dev, "can't find qfprom resource\n");
+		DRM_DEV_INFO(&pdev->dev, "can't find qfprom resource\n");
 		hdmi->qfprom_mmio = NULL;
 	}
 
@@ -172,7 +172,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev)
 				config->hpd_reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
-			dev_err(&pdev->dev, "failed to get hpd regulator: %s (%d)\n",
+			DRM_DEV_ERROR(&pdev->dev, "failed to get hpd regulator: %s (%d)\n",
 					config->hpd_reg_names[i], ret);
 			goto fail;
 		}
@@ -195,7 +195,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev)
 				config->pwr_reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
-			dev_err(&pdev->dev, "failed to get pwr regulator: %s (%d)\n",
+			DRM_DEV_ERROR(&pdev->dev, "failed to get pwr regulator: %s (%d)\n",
 					config->pwr_reg_names[i], ret);
 			goto fail;
 		}
@@ -217,7 +217,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev)
 		clk = msm_clk_get(pdev, config->hpd_clk_names[i]);
 		if (IS_ERR(clk)) {
 			ret = PTR_ERR(clk);
-			dev_err(&pdev->dev, "failed to get hpd clk: %s (%d)\n",
+			DRM_DEV_ERROR(&pdev->dev, "failed to get hpd clk: %s (%d)\n",
 					config->hpd_clk_names[i], ret);
 			goto fail;
 		}
@@ -239,7 +239,7 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev)
 		clk = msm_clk_get(pdev, config->pwr_clk_names[i]);
 		if (IS_ERR(clk)) {
 			ret = PTR_ERR(clk);
-			dev_err(&pdev->dev, "failed to get pwr clk: %s (%d)\n",
+			DRM_DEV_ERROR(&pdev->dev, "failed to get pwr clk: %s (%d)\n",
 					config->pwr_clk_names[i], ret);
 			goto fail;
 		}
@@ -254,14 +254,14 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev)
 	hdmi->i2c = msm_hdmi_i2c_init(hdmi);
 	if (IS_ERR(hdmi->i2c)) {
 		ret = PTR_ERR(hdmi->i2c);
-		dev_err(&pdev->dev, "failed to get i2c: %d\n", ret);
+		DRM_DEV_ERROR(&pdev->dev, "failed to get i2c: %d\n", ret);
 		hdmi->i2c = NULL;
 		goto fail;
 	}
 
 	ret = msm_hdmi_get_phy(hdmi);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to get phy\n");
+		DRM_DEV_ERROR(&pdev->dev, "failed to get phy\n");
 		goto fail;
 	}
 
@@ -303,7 +303,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 	hdmi->bridge = msm_hdmi_bridge_init(hdmi);
 	if (IS_ERR(hdmi->bridge)) {
 		ret = PTR_ERR(hdmi->bridge);
-		dev_err(dev->dev, "failed to create HDMI bridge: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to create HDMI bridge: %d\n", ret);
 		hdmi->bridge = NULL;
 		goto fail;
 	}
@@ -311,7 +311,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 	hdmi->connector = msm_hdmi_connector_init(hdmi);
 	if (IS_ERR(hdmi->connector)) {
 		ret = PTR_ERR(hdmi->connector);
-		dev_err(dev->dev, "failed to create HDMI connector: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to create HDMI connector: %d\n", ret);
 		hdmi->connector = NULL;
 		goto fail;
 	}
@@ -319,7 +319,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 	hdmi->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (hdmi->irq < 0) {
 		ret = hdmi->irq;
-		dev_err(dev->dev, "failed to get irq: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get irq: %d\n", ret);
 		goto fail;
 	}
 
@@ -327,7 +327,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 			msm_hdmi_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
 			"hdmi_isr", hdmi);
 	if (ret < 0) {
-		dev_err(dev->dev, "failed to request IRQ%u: %d\n",
+		DRM_DEV_ERROR(dev->dev, "failed to request IRQ%u: %d\n",
 				hdmi->irq, ret);
 		goto fail;
 	}
@@ -476,7 +476,7 @@ static int msm_hdmi_audio_hw_params(struct device *dev, void *data,
 	unsigned int level_shift  = 0; /* 0dB */
 	bool down_mix = false;
 
-	dev_dbg(dev, "%u Hz, %d bit, %d channels\n", params->sample_rate,
+	DRM_DEV_DEBUG(dev, "%u Hz, %d bit, %d channels\n", params->sample_rate,
 		 params->sample_width, params->cea.channels);
 
 	switch (params->cea.channels) {
@@ -527,7 +527,7 @@ static int msm_hdmi_audio_hw_params(struct device *dev, void *data,
 		rate = HDMI_SAMPLE_RATE_192KHZ;
 		break;
 	default:
-		dev_err(dev, "rate[%d] not supported!\n",
+		DRM_DEV_ERROR(dev, "rate[%d] not supported!\n",
 			params->sample_rate);
 		return -EINVAL;
 	}
@@ -579,7 +579,7 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data)
 	hdmi_cfg = (struct hdmi_platform_config *)
 			of_device_get_match_data(dev);
 	if (!hdmi_cfg) {
-		dev_err(dev, "unknown hdmi_cfg: %pOFn\n", of_node);
+		DRM_DEV_ERROR(dev, "unknown hdmi_cfg: %pOFn\n", of_node);
 		return -ENXIO;
 	}
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
index 7e357077ed26..98d61c690260 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
@@ -40,7 +40,7 @@ static void msm_hdmi_power_on(struct drm_bridge *bridge)
 	for (i = 0; i < config->pwr_reg_cnt; i++) {
 		ret = regulator_enable(hdmi->pwr_regs[i]);
 		if (ret) {
-			dev_err(dev->dev, "failed to enable pwr regulator: %s (%d)\n",
+			DRM_DEV_ERROR(dev->dev, "failed to enable pwr regulator: %s (%d)\n",
 					config->pwr_reg_names[i], ret);
 		}
 	}
@@ -49,7 +49,7 @@ static void msm_hdmi_power_on(struct drm_bridge *bridge)
 		DBG("pixclock: %lu", hdmi->pixclock);
 		ret = clk_set_rate(hdmi->pwr_clks[0], hdmi->pixclock);
 		if (ret) {
-			dev_err(dev->dev, "failed to set pixel clk: %s (%d)\n",
+			DRM_DEV_ERROR(dev->dev, "failed to set pixel clk: %s (%d)\n",
 					config->pwr_clk_names[0], ret);
 		}
 	}
@@ -57,7 +57,7 @@ static void msm_hdmi_power_on(struct drm_bridge *bridge)
 	for (i = 0; i < config->pwr_clk_cnt; i++) {
 		ret = clk_prepare_enable(hdmi->pwr_clks[i]);
 		if (ret) {
-			dev_err(dev->dev, "failed to enable pwr clk: %s (%d)\n",
+			DRM_DEV_ERROR(dev->dev, "failed to enable pwr clk: %s (%d)\n",
 					config->pwr_clk_names[i], ret);
 		}
 	}
@@ -82,7 +82,7 @@ static void power_off(struct drm_bridge *bridge)
 	for (i = 0; i < config->pwr_reg_cnt; i++) {
 		ret = regulator_disable(hdmi->pwr_regs[i]);
 		if (ret) {
-			dev_err(dev->dev, "failed to disable pwr regulator: %s (%d)\n",
+			DRM_DEV_ERROR(dev->dev, "failed to disable pwr regulator: %s (%d)\n",
 					config->pwr_reg_names[i], ret);
 		}
 	}
@@ -105,7 +105,7 @@ static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi)
 
 	len = hdmi_infoframe_pack(&frame, buffer, sizeof(buffer));
 	if (len < 0) {
-		dev_err(&hdmi->pdev->dev,
+		DRM_DEV_ERROR(&hdmi->pdev->dev,
 			"failed to configure avi infoframe\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index e9c9a0af508e..99f2f1038258 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -90,7 +90,7 @@ static int gpio_config(struct hdmi *hdmi, bool on)
 			if (gpio.num != -1) {
 				ret = gpio_request(gpio.num, gpio.label);
 				if (ret) {
-					dev_err(dev,
+					DRM_DEV_ERROR(dev,
 						"'%s'(%d) gpio_request failed: %d\n",
 						gpio.label, gpio.num, ret);
 					goto err;
@@ -156,7 +156,7 @@ static void enable_hpd_clocks(struct hdmi *hdmi, bool enable)
 
 			ret = clk_prepare_enable(hdmi->hpd_clks[i]);
 			if (ret) {
-				dev_err(dev,
+				DRM_DEV_ERROR(dev,
 					"failed to enable hpd clk: %s (%d)\n",
 					config->hpd_clk_names[i], ret);
 			}
@@ -179,7 +179,7 @@ static int hpd_enable(struct hdmi_connector *hdmi_connector)
 	for (i = 0; i < config->hpd_reg_cnt; i++) {
 		ret = regulator_enable(hdmi->hpd_regs[i]);
 		if (ret) {
-			dev_err(dev, "failed to enable hpd regulator: %s (%d)\n",
+			DRM_DEV_ERROR(dev, "failed to enable hpd regulator: %s (%d)\n",
 					config->hpd_reg_names[i], ret);
 			goto fail;
 		}
@@ -187,13 +187,13 @@ static int hpd_enable(struct hdmi_connector *hdmi_connector)
 
 	ret = pinctrl_pm_select_default_state(dev);
 	if (ret) {
-		dev_err(dev, "pinctrl state chg failed: %d\n", ret);
+		DRM_DEV_ERROR(dev, "pinctrl state chg failed: %d\n", ret);
 		goto fail;
 	}
 
 	ret = gpio_config(hdmi, true);
 	if (ret) {
-		dev_err(dev, "failed to configure GPIOs: %d\n", ret);
+		DRM_DEV_ERROR(dev, "failed to configure GPIOs: %d\n", ret);
 		goto fail;
 	}
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
index 73e20219d431..25d2fe2c60e8 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
@@ -66,7 +66,7 @@ static int ddc_clear_irq(struct hdmi_i2c_adapter *hdmi_i2c)
 	} while ((ddc_int_ctrl & HDMI_DDC_INT_CTRL_SW_DONE_INT) && retry);
 
 	if (!retry) {
-		dev_err(dev->dev, "timeout waiting for DDC\n");
+		DRM_DEV_ERROR(dev->dev, "timeout waiting for DDC\n");
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
index 4157722d6b4d..1f4331ed69bd 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
@@ -37,7 +37,7 @@ static int msm_hdmi_phy_resource_init(struct hdmi_phy *phy)
 		reg = devm_regulator_get(dev, cfg->reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
-			dev_err(dev, "failed to get phy regulator: %s (%d)\n",
+			DRM_DEV_ERROR(dev, "failed to get phy regulator: %s (%d)\n",
 				cfg->reg_names[i], ret);
 			return ret;
 		}
@@ -51,7 +51,7 @@ static int msm_hdmi_phy_resource_init(struct hdmi_phy *phy)
 		clk = msm_clk_get(phy->pdev, cfg->clk_names[i]);
 		if (IS_ERR(clk)) {
 			ret = PTR_ERR(clk);
-			dev_err(dev, "failed to get phy clock: %s (%d)\n",
+			DRM_DEV_ERROR(dev, "failed to get phy clock: %s (%d)\n",
 				cfg->clk_names[i], ret);
 			return ret;
 		}
@@ -73,14 +73,14 @@ int msm_hdmi_phy_resource_enable(struct hdmi_phy *phy)
 	for (i = 0; i < cfg->num_regs; i++) {
 		ret = regulator_enable(phy->regs[i]);
 		if (ret)
-			dev_err(dev, "failed to enable regulator: %s (%d)\n",
+			DRM_DEV_ERROR(dev, "failed to enable regulator: %s (%d)\n",
 				cfg->reg_names[i], ret);
 	}
 
 	for (i = 0; i < cfg->num_clks; i++) {
 		ret = clk_prepare_enable(phy->clks[i]);
 		if (ret)
-			dev_err(dev, "failed to enable clock: %s (%d)\n",
+			DRM_DEV_ERROR(dev, "failed to enable clock: %s (%d)\n",
 				cfg->clk_names[i], ret);
 	}
 
@@ -159,7 +159,7 @@ static int msm_hdmi_phy_probe(struct platform_device *pdev)
 
 	phy->mmio = msm_ioremap(pdev, "hdmi_phy", "HDMI_PHY");
 	if (IS_ERR(phy->mmio)) {
-		dev_err(dev, "%s: failed to map phy base\n", __func__);
+		DRM_DEV_ERROR(dev, "%s: failed to map phy base\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -177,7 +177,7 @@ static int msm_hdmi_phy_probe(struct platform_device *pdev)
 
 	ret = msm_hdmi_phy_pll_init(pdev, phy->cfg->type);
 	if (ret) {
-		dev_err(dev, "couldn't init PLL\n");
+		DRM_DEV_ERROR(dev, "couldn't init PLL\n");
 		msm_hdmi_phy_resource_disable(phy);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
index 0df504c61833..318708f26731 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
@@ -725,7 +725,7 @@ int msm_hdmi_pll_8996_init(struct platform_device *pdev)
 
 	pll->mmio_qserdes_com = msm_ioremap(pdev, "hdmi_pll", "HDMI_PLL");
 	if (IS_ERR(pll->mmio_qserdes_com)) {
-		dev_err(dev, "failed to map pll base\n");
+		DRM_DEV_ERROR(dev, "failed to map pll base\n");
 		return -ENOMEM;
 	}
 
@@ -737,7 +737,7 @@ int msm_hdmi_pll_8996_init(struct platform_device *pdev)
 
 		pll->mmio_qserdes_tx[i] = msm_ioremap(pdev, name, label);
 		if (IS_ERR(pll->mmio_qserdes_tx[i])) {
-			dev_err(dev, "failed to map pll base\n");
+			DRM_DEV_ERROR(dev, "failed to map pll base\n");
 			return -ENOMEM;
 		}
 	}
@@ -745,7 +745,7 @@ int msm_hdmi_pll_8996_init(struct platform_device *pdev)
 
 	clk = devm_clk_register(dev, &pll->clk_hw);
 	if (IS_ERR(clk)) {
-		dev_err(dev, "failed to register pll clock\n");
+		DRM_DEV_ERROR(dev, "failed to register pll clock\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c
index 99590758c68b..c6dae6e437f9 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c
@@ -445,7 +445,7 @@ int msm_hdmi_pll_8960_init(struct platform_device *pdev)
 
 	pll->mmio = msm_ioremap(pdev, "hdmi_pll", "HDMI_PLL");
 	if (IS_ERR(pll->mmio)) {
-		dev_err(dev, "failed to map pll base\n");
+		DRM_DEV_ERROR(dev, "failed to map pll base\n");
 		return -ENOMEM;
 	}
 
@@ -454,7 +454,7 @@ int msm_hdmi_pll_8960_init(struct platform_device *pdev)
 
 	clk = devm_clk_register(dev, &pll->clk_hw);
 	if (IS_ERR(clk)) {
-		dev_err(dev, "failed to register pll clock\n");
+		DRM_DEV_ERROR(dev, "failed to register pll clock\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 4bcdeca7479d..ff291dd0744b 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -78,7 +78,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 		kms->funcs->commit(kms, state);
 	}
 
-	msm_atomic_wait_for_commit_done(dev, state);
+	if (!state->legacy_cursor_update)
+		msm_atomic_wait_for_commit_done(dev, state);
 
 	kms->funcs->complete_commit(kms, state);
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index f0da0d3c8a80..42a2cba78998 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -194,13 +194,13 @@ static int late_init_minor(struct drm_minor *minor)
 
 	ret = msm_rd_debugfs_init(minor);
 	if (ret) {
-		dev_err(minor->dev->dev, "could not install rd debugfs\n");
+		DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n");
 		return ret;
 	}
 
 	ret = msm_perf_debugfs_init(minor);
 	if (ret) {
-		dev_err(minor->dev->dev, "could not install perf debugfs\n");
+		DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n");
 		return ret;
 	}
 
@@ -228,14 +228,14 @@ int msm_debugfs_init(struct drm_minor *minor)
 			minor->debugfs_root, minor);
 
 	if (ret) {
-		dev_err(dev->dev, "could not install msm_debugfs_list\n");
+		DRM_DEV_ERROR(dev->dev, "could not install msm_debugfs_list\n");
 		return ret;
 	}
 
 	debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root,
 		dev, &msm_gpu_fops);
 
-	if (priv->kms->funcs->debugfs_init) {
+	if (priv->kms && priv->kms->funcs->debugfs_init) {
 		ret = priv->kms->funcs->debugfs_init(priv->kms, minor);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 5e758d95751a..6265be8f4119 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -23,8 +23,10 @@
 #include "msm_drv.h"
 #include "msm_debugfs.h"
 #include "msm_fence.h"
+#include "msm_gem.h"
 #include "msm_gpu.h"
 #include "msm_kms.h"
+#include "adreno/adreno_gpu.h"
 
 
 /*
@@ -35,9 +37,11 @@
  * - 1.3.0 - adds GMEM_BASE + NR_RINGS params, SUBMITQUEUE_NEW +
  *           SUBMITQUEUE_CLOSE ioctls, and MSM_INFO_IOVA flag for
  *           MSM_GEM_INFO ioctl.
+ * - 1.4.0 - softpin, MSM_RELOC_BO_DUMP, and GEM_INFO support to set/get
+ *           GEM object's debug name
  */
 #define MSM_VERSION_MAJOR	1
-#define MSM_VERSION_MINOR	3
+#define MSM_VERSION_MINOR	4
 #define MSM_VERSION_PATCHLEVEL	0
 
 static const struct drm_mode_config_funcs mode_config_funcs = {
@@ -170,7 +174,7 @@ void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	if (!res) {
-		dev_err(&pdev->dev, "failed to get memory resource: %s\n", name);
+		DRM_DEV_ERROR(&pdev->dev, "failed to get memory resource: %s\n", name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -178,7 +182,7 @@ void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
 
 	ptr = devm_ioremap_nocache(&pdev->dev, res->start, size);
 	if (!ptr) {
-		dev_err(&pdev->dev, "failed to ioremap: %s\n", name);
+		DRM_DEV_ERROR(&pdev->dev, "failed to ioremap: %s\n", name);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -358,6 +362,14 @@ static int get_mdp_ver(struct platform_device *pdev)
 
 #include <linux/of_address.h>
 
+bool msm_use_mmu(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+
+	/* a2xx comes with its own MMU */
+	return priv->is_a2xx || iommu_present(&platform_bus_type);
+}
+
 static int msm_init_vram(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -396,7 +408,7 @@ static int msm_init_vram(struct drm_device *dev)
 		 * Grab the entire CMA chunk carved out in early startup in
 		 * mach-msm:
 		 */
-	} else if (!iommu_present(&platform_bus_type)) {
+	} else if (!msm_use_mmu(dev)) {
 		DRM_INFO("using %s VRAM carveout\n", vram);
 		size = memparse(vram, NULL);
 	}
@@ -419,12 +431,12 @@ static int msm_init_vram(struct drm_device *dev)
 		p = dma_alloc_attrs(dev->dev, size,
 				&priv->vram.paddr, GFP_KERNEL, attrs);
 		if (!p) {
-			dev_err(dev->dev, "failed to allocate VRAM\n");
+			DRM_DEV_ERROR(dev->dev, "failed to allocate VRAM\n");
 			priv->vram.paddr = 0;
 			return -ENOMEM;
 		}
 
-		dev_info(dev->dev, "VRAM: %08x->%08x\n",
+		DRM_DEV_INFO(dev->dev, "VRAM: %08x->%08x\n",
 				(uint32_t)priv->vram.paddr,
 				(uint32_t)(priv->vram.paddr + size));
 	}
@@ -444,7 +456,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	ddev = drm_dev_alloc(drv, dev);
 	if (IS_ERR(ddev)) {
-		dev_err(dev, "failed to allocate drm_device\n");
+		DRM_DEV_ERROR(dev, "failed to allocate drm_device\n");
 		return PTR_ERR(ddev);
 	}
 
@@ -508,19 +520,16 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		priv->kms = kms;
 		break;
 	default:
-		kms = ERR_PTR(-ENODEV);
+		/* valid only for the dummy headless case, where of_node=NULL */
+		WARN_ON(dev->of_node);
+		kms = NULL;
 		break;
 	}
 
 	if (IS_ERR(kms)) {
-		/*
-		 * NOTE: once we have GPU support, having no kms should not
-		 * be considered fatal.. ideally we would still support gpu
-		 * and (for example) use dmabuf/prime to share buffers with
-		 * imx drm driver on iMX5
-		 */
-		dev_err(dev, "failed to load kms\n");
+		DRM_DEV_ERROR(dev, "failed to load kms\n");
 		ret = PTR_ERR(kms);
+		priv->kms = NULL;
 		goto err_msm_uninit;
 	}
 
@@ -530,7 +539,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	if (kms) {
 		ret = kms->funcs->hw_init(kms);
 		if (ret) {
-			dev_err(dev, "kms hw init failed: %d\n", ret);
+			DRM_DEV_ERROR(dev, "kms hw init failed: %d\n", ret);
 			goto err_msm_uninit;
 		}
 	}
@@ -561,7 +570,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 									ret);
 
 		if (IS_ERR(priv->disp_thread[i].thread)) {
-			dev_err(dev, "failed to create crtc_commit kthread\n");
+			DRM_DEV_ERROR(dev, "failed to create crtc_commit kthread\n");
 			priv->disp_thread[i].thread = NULL;
 		}
 
@@ -573,6 +582,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 			kthread_run(kthread_worker_fn,
 				&priv->event_thread[i].worker,
 				"crtc_event:%d", priv->event_thread[i].crtc_id);
+
 		/**
 		 * event thread should also run at same priority as disp_thread
 		 * because it is handling frame_done events. A lower priority
@@ -613,7 +623,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	ret = drm_vblank_init(ddev, priv->num_crtcs);
 	if (ret < 0) {
-		dev_err(dev, "failed to initialize vblank\n");
+		DRM_DEV_ERROR(dev, "failed to initialize vblank\n");
 		goto err_msm_uninit;
 	}
 
@@ -622,7 +632,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		ret = drm_irq_install(ddev, kms->irq);
 		pm_runtime_put_sync(dev);
 		if (ret < 0) {
-			dev_err(dev, "failed to install IRQ handler\n");
+			DRM_DEV_ERROR(dev, "failed to install IRQ handler\n");
 			goto err_msm_uninit;
 		}
 	}
@@ -634,7 +644,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	drm_mode_config_reset(ddev);
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
-	if (fbdev)
+	if (kms && fbdev)
 		priv->fbdev = msm_fbdev_init(ddev);
 #endif
 
@@ -742,7 +752,11 @@ static int msm_irq_postinstall(struct drm_device *dev)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_kms *kms = priv->kms;
 	BUG_ON(!kms);
-	return kms->funcs->irq_postinstall(kms);
+
+	if (kms->funcs->irq_postinstall)
+		return kms->funcs->irq_postinstall(kms);
+
+	return 0;
 }
 
 static void msm_irq_uninstall(struct drm_device *dev)
@@ -809,7 +823,7 @@ static int msm_ioctl_gem_new(struct drm_device *dev, void *data,
 	}
 
 	return msm_gem_new_handle(dev, file, args->size,
-			args->flags, &args->handle);
+			args->flags, &args->handle, NULL);
 }
 
 static inline ktime_t to_ktime(struct drm_msm_timespec timeout)
@@ -867,6 +881,10 @@ static int msm_ioctl_gem_info_iova(struct drm_device *dev,
 	if (!priv->gpu)
 		return -EINVAL;
 
+	/*
+	 * Don't pin the memory here - just get an address so that userspace can
+	 * be productive
+	 */
 	return msm_gem_get_iova(obj, priv->gpu->aspace, iova);
 }
 
@@ -875,23 +893,66 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 {
 	struct drm_msm_gem_info *args = data;
 	struct drm_gem_object *obj;
-	int ret = 0;
+	struct msm_gem_object *msm_obj;
+	int i, ret = 0;
 
-	if (args->flags & ~MSM_INFO_FLAGS)
+	if (args->pad)
 		return -EINVAL;
 
+	switch (args->info) {
+	case MSM_INFO_GET_OFFSET:
+	case MSM_INFO_GET_IOVA:
+		/* value returned as immediate, not pointer, so len==0: */
+		if (args->len)
+			return -EINVAL;
+		break;
+	case MSM_INFO_SET_NAME:
+	case MSM_INFO_GET_NAME:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	obj = drm_gem_object_lookup(file, args->handle);
 	if (!obj)
 		return -ENOENT;
 
-	if (args->flags & MSM_INFO_IOVA) {
-		uint64_t iova;
+	msm_obj = to_msm_bo(obj);
 
-		ret = msm_ioctl_gem_info_iova(dev, obj, &iova);
-		if (!ret)
-			args->offset = iova;
-	} else {
-		args->offset = msm_gem_mmap_offset(obj);
+	switch (args->info) {
+	case MSM_INFO_GET_OFFSET:
+		args->value = msm_gem_mmap_offset(obj);
+		break;
+	case MSM_INFO_GET_IOVA:
+		ret = msm_ioctl_gem_info_iova(dev, obj, &args->value);
+		break;
+	case MSM_INFO_SET_NAME:
+		/* length check should leave room for terminating null: */
+		if (args->len >= sizeof(msm_obj->name)) {
+			ret = -EINVAL;
+			break;
+		}
+		ret = copy_from_user(msm_obj->name,
+			u64_to_user_ptr(args->value), args->len);
+		msm_obj->name[args->len] = '\0';
+		for (i = 0; i < args->len; i++) {
+			if (!isprint(msm_obj->name[i])) {
+				msm_obj->name[i] = '\0';
+				break;
+			}
+		}
+		break;
+	case MSM_INFO_GET_NAME:
+		if (args->value && (args->len < strlen(msm_obj->name))) {
+			ret = -EINVAL;
+			break;
+		}
+		args->len = strlen(msm_obj->name);
+		if (args->value) {
+			ret = copy_to_user(u64_to_user_ptr(args->value),
+					msm_obj->name, args->len);
+		}
+		break;
 	}
 
 	drm_gem_object_put_unlocked(obj);
@@ -1070,18 +1131,15 @@ static int msm_pm_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
-	struct msm_kms *kms = priv->kms;
 
-	/* TODO: Use atomic helper suspend/resume */
-	if (kms && kms->funcs && kms->funcs->pm_suspend)
-		return kms->funcs->pm_suspend(dev);
-
-	drm_kms_helper_poll_disable(ddev);
+	if (WARN_ON(priv->pm_state))
+		drm_atomic_state_put(priv->pm_state);
 
 	priv->pm_state = drm_atomic_helper_suspend(ddev);
 	if (IS_ERR(priv->pm_state)) {
-		drm_kms_helper_poll_enable(ddev);
-		return PTR_ERR(priv->pm_state);
+		int ret = PTR_ERR(priv->pm_state);
+		DRM_ERROR("Failed to suspend dpu, %d\n", ret);
+		return ret;
 	}
 
 	return 0;
@@ -1091,16 +1149,16 @@ static int msm_pm_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
-	struct msm_kms *kms = priv->kms;
+	int ret;
 
-	/* TODO: Use atomic helper suspend/resume */
-	if (kms && kms->funcs && kms->funcs->pm_resume)
-		return kms->funcs->pm_resume(dev);
+	if (WARN_ON(!priv->pm_state))
+		return -ENOENT;
 
-	drm_atomic_helper_resume(ddev, priv->pm_state);
-	drm_kms_helper_poll_enable(ddev);
+	ret = drm_atomic_helper_resume(ddev, priv->pm_state);
+	if (!ret)
+		priv->pm_state = NULL;
 
-	return 0;
+	return ret;
 }
 #endif
 
@@ -1185,7 +1243,7 @@ static int add_components_mdp(struct device *mdp_dev,
 
 		ret = of_graph_parse_endpoint(ep_node, &ep);
 		if (ret) {
-			dev_err(mdp_dev, "unable to parse port endpoint\n");
+			DRM_DEV_ERROR(mdp_dev, "unable to parse port endpoint\n");
 			of_node_put(ep_node);
 			return ret;
 		}
@@ -1207,8 +1265,10 @@ static int add_components_mdp(struct device *mdp_dev,
 		if (!intf)
 			continue;
 
-		drm_of_component_match_add(master_dev, matchptr, compare_of,
-					   intf);
+		if (of_device_is_available(intf))
+			drm_of_component_match_add(master_dev, matchptr,
+						   compare_of, intf);
+
 		of_node_put(intf);
 	}
 
@@ -1236,13 +1296,13 @@ static int add_display_components(struct device *dev,
 	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) {
 		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
 		if (ret) {
-			dev_err(dev, "failed to populate children devices\n");
+			DRM_DEV_ERROR(dev, "failed to populate children devices\n");
 			return ret;
 		}
 
 		mdp_dev = device_find_child(dev, NULL, compare_name_mdp);
 		if (!mdp_dev) {
-			dev_err(dev, "failed to find MDSS MDP node\n");
+			DRM_DEV_ERROR(dev, "failed to find MDSS MDP node\n");
 			of_platform_depopulate(dev);
 			return -ENODEV;
 		}
@@ -1272,6 +1332,7 @@ static int add_display_components(struct device *dev,
 static const struct of_device_id msm_gpu_match[] = {
 	{ .compatible = "qcom,adreno" },
 	{ .compatible = "qcom,adreno-3xx" },
+	{ .compatible = "amd,imageon" },
 	{ .compatible = "qcom,kgsl-3d0" },
 	{ },
 };
@@ -1316,9 +1377,11 @@ static int msm_pdev_probe(struct platform_device *pdev)
 	struct component_match *match = NULL;
 	int ret;
 
-	ret = add_display_components(&pdev->dev, &match);
-	if (ret)
-		return ret;
+	if (get_mdp_ver(pdev)) {
+		ret = add_display_components(&pdev->dev, &match);
+		if (ret)
+			return ret;
+	}
 
 	ret = add_gpu_components(&pdev->dev, &match);
 	if (ret)
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 9d11f321f5a9..9cd6a96c6bf2 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -179,6 +179,8 @@ struct msm_drm_private {
 	/* when we have more than one 'msm_gpu' these need to be an array: */
 	struct msm_gpu *gpu;
 	struct msm_file_private *lastctx;
+	/* gpu is only set on open(), but we need this info earlier */
+	bool is_a2xx;
 
 	struct drm_fb_helper *fbdev;
 
@@ -241,10 +243,16 @@ struct drm_atomic_state *msm_atomic_state_alloc(struct drm_device *dev);
 void msm_atomic_state_clear(struct drm_atomic_state *state);
 void msm_atomic_state_free(struct drm_atomic_state *state);
 
+int msm_gem_init_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma, int npages);
+void msm_gem_purge_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma);
 void msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
-		struct msm_gem_vma *vma, struct sg_table *sgt);
+		struct msm_gem_vma *vma);
 int msm_gem_map_vma(struct msm_gem_address_space *aspace,
 		struct msm_gem_vma *vma, struct sg_table *sgt, int npages);
+void msm_gem_close_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma);
 
 void msm_gem_address_space_put(struct msm_gem_address_space *aspace);
 
@@ -252,9 +260,15 @@ struct msm_gem_address_space *
 msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 		const char *name);
 
+struct msm_gem_address_space *
+msm_gem_address_space_create_a2xx(struct device *dev, struct msm_gpu *gpu,
+		const char *name, uint64_t va_start, uint64_t va_end);
+
 int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
 void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu);
 
+bool msm_use_mmu(struct drm_device *dev);
+
 void msm_gem_submit_free(struct msm_gem_submit *submit);
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
@@ -269,12 +283,14 @@ vm_fault_t msm_gem_fault(struct vm_fault *vmf);
 uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj);
 int msm_gem_get_iova(struct drm_gem_object *obj,
 		struct msm_gem_address_space *aspace, uint64_t *iova);
+int msm_gem_get_and_pin_iova(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace, uint64_t *iova);
 uint64_t msm_gem_iova(struct drm_gem_object *obj,
 		struct msm_gem_address_space *aspace);
+void msm_gem_unpin_iova(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace);
 struct page **msm_gem_get_pages(struct drm_gem_object *obj);
 void msm_gem_put_pages(struct drm_gem_object *obj);
-void msm_gem_put_iova(struct drm_gem_object *obj,
-		struct msm_gem_address_space *aspace);
 int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 		struct drm_mode_create_dumb *args);
 int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
@@ -301,7 +317,7 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout);
 int msm_gem_cpu_fini(struct drm_gem_object *obj);
 void msm_gem_free_object(struct drm_gem_object *obj);
 int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
-		uint32_t size, uint32_t flags, uint32_t *handle);
+		uint32_t size, uint32_t flags, uint32_t *handle, char *name);
 struct drm_gem_object *msm_gem_new(struct drm_device *dev,
 		uint32_t size, uint32_t flags);
 struct drm_gem_object *msm_gem_new_locked(struct drm_device *dev,
@@ -312,9 +328,13 @@ void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 void *msm_gem_kernel_new_locked(struct drm_device *dev, uint32_t size,
 		uint32_t flags, struct msm_gem_address_space *aspace,
 		struct drm_gem_object **bo, uint64_t *iova);
+void msm_gem_kernel_put(struct drm_gem_object *bo,
+		struct msm_gem_address_space *aspace, bool locked);
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt);
 
+void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...);
+
 int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace);
 void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 2a7348aeb38d..67dfd8d3dc12 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -66,7 +66,7 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 	uint64_t iova;
 
 	for (i = 0; i < n; i++) {
-		ret = msm_gem_get_iova(fb->obj[i], aspace, &iova);
+		ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &iova);
 		DBG("FB[%u]: iova[%d]: %08llx (%d)", fb->base.id, i, iova, ret);
 		if (ret)
 			return ret;
@@ -81,7 +81,7 @@ void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
 	int i, n = fb->format->num_planes;
 
 	for (i = 0; i < n; i++)
-		msm_gem_put_iova(fb->obj[i], aspace);
+		msm_gem_unpin_iova(fb->obj[i], aspace);
 }
 
 uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb,
@@ -154,7 +154,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 	format = kms->funcs->get_format(kms, mode_cmd->pixel_format,
 			mode_cmd->modifier[0]);
 	if (!format) {
-		dev_err(dev->dev, "unsupported pixel format: %4.4s\n",
+		DRM_DEV_ERROR(dev->dev, "unsupported pixel format: %4.4s\n",
 				(char *)&mode_cmd->pixel_format);
 		ret = -EINVAL;
 		goto fail;
@@ -196,7 +196,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 
 	ret = drm_framebuffer_init(dev, fb, &msm_framebuffer_funcs);
 	if (ret) {
-		dev_err(dev->dev, "framebuffer init failed: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "framebuffer init failed: %d\n", ret);
 		goto fail;
 	}
 
@@ -233,13 +233,15 @@ msm_alloc_stolen_fb(struct drm_device *dev, int w, int h, int p, uint32_t format
 		bo = msm_gem_new(dev, size, MSM_BO_SCANOUT | MSM_BO_WC);
 	}
 	if (IS_ERR(bo)) {
-		dev_err(dev->dev, "failed to allocate buffer object\n");
+		DRM_DEV_ERROR(dev->dev, "failed to allocate buffer object\n");
 		return ERR_CAST(bo);
 	}
 
+	msm_gem_object_set_name(bo, "stolenfb");
+
 	fb = msm_framebuffer_init(dev, &mode_cmd, &bo);
 	if (IS_ERR(fb)) {
-		dev_err(dev->dev, "failed to allocate fb\n");
+		DRM_DEV_ERROR(dev->dev, "failed to allocate fb\n");
 		/* note: if fb creation failed, we can't rely on fb destroy
 		 * to unref the bo:
 		 */
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index 456622b46335..c03e860ba737 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -91,7 +91,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 			sizes->surface_height, pitch, format);
 
 	if (IS_ERR(fb)) {
-		dev_err(dev->dev, "failed to allocate fb\n");
+		DRM_DEV_ERROR(dev->dev, "failed to allocate fb\n");
 		return PTR_ERR(fb);
 	}
 
@@ -104,15 +104,15 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 	 * in panic (ie. lock-safe, etc) we could avoid pinning the
 	 * buffer now:
 	 */
-	ret = msm_gem_get_iova(bo, priv->kms->aspace, &paddr);
+	ret = msm_gem_get_and_pin_iova(bo, priv->kms->aspace, &paddr);
 	if (ret) {
-		dev_err(dev->dev, "failed to get buffer obj iova: %d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "failed to get buffer obj iova: %d\n", ret);
 		goto fail_unlock;
 	}
 
 	fbi = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(fbi)) {
-		dev_err(dev->dev, "failed to allocate fb info\n");
+		DRM_DEV_ERROR(dev->dev, "failed to allocate fb info\n");
 		ret = PTR_ERR(fbi);
 		goto fail_unlock;
 	}
@@ -176,7 +176,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev)
 
 	ret = drm_fb_helper_init(dev, helper, priv->num_connectors);
 	if (ret) {
-		dev_err(dev->dev, "could not init fbdev: ret=%d\n", ret);
+		DRM_DEV_ERROR(dev->dev, "could not init fbdev: ret=%d\n", ret);
 		goto fail;
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index f59ca27a4a35..51a95da694d8 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -88,7 +88,7 @@ static struct page **get_pages(struct drm_gem_object *obj)
 			p = get_pages_vram(obj, npages);
 
 		if (IS_ERR(p)) {
-			dev_err(dev->dev, "could not get pages: %ld\n",
+			DRM_DEV_ERROR(dev->dev, "could not get pages: %ld\n",
 					PTR_ERR(p));
 			return p;
 		}
@@ -99,7 +99,7 @@ static struct page **get_pages(struct drm_gem_object *obj)
 		if (IS_ERR(msm_obj->sgt)) {
 			void *ptr = ERR_CAST(msm_obj->sgt);
 
-			dev_err(dev->dev, "failed to allocate sgt\n");
+			DRM_DEV_ERROR(dev->dev, "failed to allocate sgt\n");
 			msm_obj->sgt = NULL;
 			return ptr;
 		}
@@ -280,7 +280,7 @@ static uint64_t mmap_offset(struct drm_gem_object *obj)
 	ret = drm_gem_create_mmap_offset(obj);
 
 	if (ret) {
-		dev_err(dev->dev, "could not allocate mmap offset\n");
+		DRM_DEV_ERROR(dev->dev, "could not allocate mmap offset\n");
 		return 0;
 	}
 
@@ -352,63 +352,104 @@ put_iova(struct drm_gem_object *obj)
 	WARN_ON(!mutex_is_locked(&msm_obj->lock));
 
 	list_for_each_entry_safe(vma, tmp, &msm_obj->vmas, list) {
-		msm_gem_unmap_vma(vma->aspace, vma, msm_obj->sgt);
+		msm_gem_purge_vma(vma->aspace, vma);
+		msm_gem_close_vma(vma->aspace, vma);
 		del_vma(vma);
 	}
 }
 
-/* get iova, taking a reference.  Should have a matching put */
-int msm_gem_get_iova(struct drm_gem_object *obj,
+static int msm_gem_get_iova_locked(struct drm_gem_object *obj,
 		struct msm_gem_address_space *aspace, uint64_t *iova)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	struct msm_gem_vma *vma;
 	int ret = 0;
 
-	mutex_lock(&msm_obj->lock);
-
-	if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) {
-		mutex_unlock(&msm_obj->lock);
-		return -EBUSY;
-	}
+	WARN_ON(!mutex_is_locked(&msm_obj->lock));
 
 	vma = lookup_vma(obj, aspace);
 
 	if (!vma) {
-		struct page **pages;
-
 		vma = add_vma(obj, aspace);
-		if (IS_ERR(vma)) {
-			ret = PTR_ERR(vma);
-			goto unlock;
-		}
+		if (IS_ERR(vma))
+			return PTR_ERR(vma);
 
-		pages = get_pages(obj);
-		if (IS_ERR(pages)) {
-			ret = PTR_ERR(pages);
-			goto fail;
+		ret = msm_gem_init_vma(aspace, vma, obj->size >> PAGE_SHIFT);
+		if (ret) {
+			del_vma(vma);
+			return ret;
 		}
-
-		ret = msm_gem_map_vma(aspace, vma, msm_obj->sgt,
-				obj->size >> PAGE_SHIFT);
-		if (ret)
-			goto fail;
 	}
 
 	*iova = vma->iova;
+	return 0;
+}
+
+static int msm_gem_pin_iova(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct msm_gem_vma *vma;
+	struct page **pages;
+
+	WARN_ON(!mutex_is_locked(&msm_obj->lock));
+
+	if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED))
+		return -EBUSY;
+
+	vma = lookup_vma(obj, aspace);
+	if (WARN_ON(!vma))
+		return -EINVAL;
+
+	pages = get_pages(obj);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	return msm_gem_map_vma(aspace, vma, msm_obj->sgt,
+			obj->size >> PAGE_SHIFT);
+}
+
+/* get iova and pin it. Should have a matching put */
+int msm_gem_get_and_pin_iova(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace, uint64_t *iova)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	u64 local;
+	int ret;
+
+	mutex_lock(&msm_obj->lock);
+
+	ret = msm_gem_get_iova_locked(obj, aspace, &local);
+
+	if (!ret)
+		ret = msm_gem_pin_iova(obj, aspace);
+
+	if (!ret)
+		*iova = local;
 
 	mutex_unlock(&msm_obj->lock);
-	return 0;
+	return ret;
+}
 
-fail:
-	del_vma(vma);
-unlock:
+/*
+ * Get an iova but don't pin it. Doesn't need a put because iovas are currently
+ * valid for the life of the object
+ */
+int msm_gem_get_iova(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace, uint64_t *iova)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	int ret;
+
+	mutex_lock(&msm_obj->lock);
+	ret = msm_gem_get_iova_locked(obj, aspace, iova);
 	mutex_unlock(&msm_obj->lock);
+
 	return ret;
 }
 
 /* get iova without taking a reference, used in places where you have
- * already done a 'msm_gem_get_iova()'.
+ * already done a 'msm_gem_get_and_pin_iova' or 'msm_gem_get_iova'
  */
 uint64_t msm_gem_iova(struct drm_gem_object *obj,
 		struct msm_gem_address_space *aspace)
@@ -424,15 +465,24 @@ uint64_t msm_gem_iova(struct drm_gem_object *obj,
 	return vma ? vma->iova : 0;
 }
 
-void msm_gem_put_iova(struct drm_gem_object *obj,
+/*
+ * Unpin a iova by updating the reference counts. The memory isn't actually
+ * purged until something else (shrinker, mm_notifier, destroy, etc) decides
+ * to get rid of it
+ */
+void msm_gem_unpin_iova(struct drm_gem_object *obj,
 		struct msm_gem_address_space *aspace)
 {
-	// XXX TODO ..
-	// NOTE: probably don't need a _locked() version.. we wouldn't
-	// normally unmap here, but instead just mark that it could be
-	// unmapped (if the iova refcnt drops to zero), but then later
-	// if another _get_iova_locked() fails we can start unmapping
-	// things that are no longer needed..
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct msm_gem_vma *vma;
+
+	mutex_lock(&msm_obj->lock);
+	vma = lookup_vma(obj, aspace);
+
+	if (!WARN_ON(!vma))
+		msm_gem_unmap_vma(aspace, vma);
+
+	mutex_unlock(&msm_obj->lock);
 }
 
 int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
@@ -441,7 +491,7 @@ int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 	args->pitch = align_pitch(args->width, args->bpp);
 	args->size  = PAGE_ALIGN(args->pitch * args->height);
 	return msm_gem_new_handle(dev, file, args->size,
-			MSM_BO_SCANOUT | MSM_BO_WC, &args->handle);
+			MSM_BO_SCANOUT | MSM_BO_WC, &args->handle, "dumb");
 }
 
 int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
@@ -473,7 +523,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv)
 	mutex_lock(&msm_obj->lock);
 
 	if (WARN_ON(msm_obj->madv > madv)) {
-		dev_err(obj->dev->dev, "Invalid madv state: %u vs %u\n",
+		DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n",
 			msm_obj->madv, madv);
 		mutex_unlock(&msm_obj->lock);
 		return ERR_PTR(-EBUSY);
@@ -739,16 +789,24 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 		break;
 	}
 
-	seq_printf(m, "%08x: %c %2d (%2d) %08llx %p\t",
+	seq_printf(m, "%08x: %c %2d (%2d) %08llx %p",
 			msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
 			obj->name, kref_read(&obj->refcount),
 			off, msm_obj->vaddr);
 
-	/* FIXME: we need to print the address space here too */
-	list_for_each_entry(vma, &msm_obj->vmas, list)
-		seq_printf(m, " %08llx", vma->iova);
+	seq_printf(m, " %08zu %9s %-32s\n", obj->size, madv, msm_obj->name);
+
+	if (!list_empty(&msm_obj->vmas)) {
+
+		seq_puts(m, "      vmas:");
 
-	seq_printf(m, " %zu%s\n", obj->size, madv);
+		list_for_each_entry(vma, &msm_obj->vmas, list)
+			seq_printf(m, " [%s: %08llx,%s,inuse=%d]", vma->aspace->name,
+				vma->iova, vma->mapped ? "mapped" : "unmapped",
+				vma->inuse);
+
+		seq_puts(m, "\n");
+	}
 
 	rcu_read_lock();
 	fobj = rcu_dereference(robj->fence);
@@ -775,9 +833,10 @@ void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
 	int count = 0;
 	size_t size = 0;
 
+	seq_puts(m, "   flags       id ref  offset   kaddr            size     madv      name\n");
 	list_for_each_entry(msm_obj, list, mm_list) {
 		struct drm_gem_object *obj = &msm_obj->base;
-		seq_printf(m, "   ");
+		seq_puts(m, "   ");
 		msm_gem_describe(obj, m);
 		count++;
 		size += obj->size;
@@ -831,7 +890,8 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 
 /* convenience method to construct a GEM buffer object, and userspace handle */
 int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
-		uint32_t size, uint32_t flags, uint32_t *handle)
+		uint32_t size, uint32_t flags, uint32_t *handle,
+		char *name)
 {
 	struct drm_gem_object *obj;
 	int ret;
@@ -841,6 +901,9 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
+	if (name)
+		msm_gem_object_set_name(obj, "%s", name);
+
 	ret = drm_gem_handle_create(file, obj, handle);
 
 	/* drop reference from allocate - handle holds it now */
@@ -864,7 +927,7 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	case MSM_BO_WC:
 		break;
 	default:
-		dev_err(dev->dev, "invalid cache flag: %x\n",
+		DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n",
 				(flags & MSM_BO_CACHE_MASK));
 		return -EINVAL;
 	}
@@ -912,9 +975,9 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 
 	size = PAGE_ALIGN(size);
 
-	if (!iommu_present(&platform_bus_type))
+	if (!msm_use_mmu(dev))
 		use_vram = true;
-	else if ((flags & MSM_BO_STOLEN) && priv->vram.size)
+	else if ((flags & (MSM_BO_STOLEN | MSM_BO_SCANOUT)) && priv->vram.size)
 		use_vram = true;
 
 	if (WARN_ON(use_vram && !priv->vram.size))
@@ -989,8 +1052,8 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	int ret, npages;
 
 	/* if we don't have IOMMU, don't bother pretending we can import: */
-	if (!iommu_present(&platform_bus_type)) {
-		dev_err(dev->dev, "cannot import without IOMMU\n");
+	if (!msm_use_mmu(dev)) {
+		DRM_DEV_ERROR(dev->dev, "cannot import without IOMMU\n");
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1040,24 +1103,30 @@ static void *_msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
 		return ERR_CAST(obj);
 
 	if (iova) {
-		ret = msm_gem_get_iova(obj, aspace, iova);
-		if (ret) {
-			drm_gem_object_put(obj);
-			return ERR_PTR(ret);
-		}
+		ret = msm_gem_get_and_pin_iova(obj, aspace, iova);
+		if (ret)
+			goto err;
 	}
 
 	vaddr = msm_gem_get_vaddr(obj);
 	if (IS_ERR(vaddr)) {
-		msm_gem_put_iova(obj, aspace);
-		drm_gem_object_put(obj);
-		return ERR_CAST(vaddr);
+		msm_gem_unpin_iova(obj, aspace);
+		ret = PTR_ERR(vaddr);
+		goto err;
 	}
 
 	if (bo)
 		*bo = obj;
 
 	return vaddr;
+err:
+	if (locked)
+		drm_gem_object_put(obj);
+	else
+		drm_gem_object_put_unlocked(obj);
+
+	return ERR_PTR(ret);
+
 }
 
 void *msm_gem_kernel_new(struct drm_device *dev, uint32_t size,
@@ -1073,3 +1142,31 @@ void *msm_gem_kernel_new_locked(struct drm_device *dev, uint32_t size,
 {
 	return _msm_gem_kernel_new(dev, size, flags, aspace, bo, iova, true);
 }
+
+void msm_gem_kernel_put(struct drm_gem_object *bo,
+		struct msm_gem_address_space *aspace, bool locked)
+{
+	if (IS_ERR_OR_NULL(bo))
+		return;
+
+	msm_gem_put_vaddr(bo);
+	msm_gem_unpin_iova(bo, aspace);
+
+	if (locked)
+		drm_gem_object_put(bo);
+	else
+		drm_gem_object_put_unlocked(bo);
+}
+
+void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(bo);
+	va_list ap;
+
+	if (!fmt)
+		return;
+
+	va_start(ap, fmt);
+	vsnprintf(msm_obj->name, sizeof(msm_obj->name), fmt, ap);
+	va_end(ap);
+}
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index c5d9bd3e47a8..2064fac871b8 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -41,6 +41,8 @@ struct msm_gem_vma {
 	uint64_t iova;
 	struct msm_gem_address_space *aspace;
 	struct list_head list;    /* node in msm_gem_object::vmas */
+	bool mapped;
+	int inuse;
 };
 
 struct msm_gem_object {
@@ -91,6 +93,8 @@ struct msm_gem_object {
 	 */
 	struct drm_mm_node *vram_node;
 	struct mutex lock; /* Protects resources associated with bo */
+
+	char name[32]; /* Identifier to print for the debugfs files */
 };
 #define to_msm_bo(x) container_of(x, struct msm_gem_object, base)
 
@@ -150,6 +154,7 @@ struct msm_gem_submit {
 	struct msm_ringbuffer *ring;
 	unsigned int nr_cmds;
 	unsigned int nr_bos;
+	u32 ident;	   /* A "identifier" for the submit for logging */
 	struct {
 		uint32_t type;
 		uint32_t size;  /* in dwords */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index a90aedd6883a..3cbed4acb0f4 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -20,6 +20,7 @@
 #include "msm_drv.h"
 #include "msm_gpu.h"
 #include "msm_gem.h"
+#include "msm_gpu_trace.h"
 
 /*
  * Cmdstream submission:
@@ -48,7 +49,6 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	submit->dev = dev;
 	submit->gpu = gpu;
 	submit->fence = NULL;
-	submit->pid = get_pid(task_pid(current));
 	submit->cmd = (void *)&submit->bos[nr_bos];
 	submit->queue = queue;
 	submit->ring = gpu->rb[queue->prio];
@@ -114,8 +114,11 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 			pagefault_disable();
 		}
 
+/* at least one of READ and/or WRITE flags should be set: */
+#define MANDATORY_FLAGS (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE)
+
 		if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) ||
-			!(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) {
+			!(submit_bo.flags & MANDATORY_FLAGS)) {
 			DRM_ERROR("invalid flags: %x\n", submit_bo.flags);
 			ret = -EINVAL;
 			goto out_unlock;
@@ -167,7 +170,7 @@ static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
 	struct msm_gem_object *msm_obj = submit->bos[i].obj;
 
 	if (submit->bos[i].flags & BO_PINNED)
-		msm_gem_put_iova(&msm_obj->base, submit->gpu->aspace);
+		msm_gem_unpin_iova(&msm_obj->base, submit->gpu->aspace);
 
 	if (submit->bos[i].flags & BO_LOCKED)
 		ww_mutex_unlock(&msm_obj->resv->lock);
@@ -270,7 +273,7 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 		uint64_t iova;
 
 		/* if locking succeeded, pin bo: */
-		ret = msm_gem_get_iova(&msm_obj->base,
+		ret = msm_gem_get_and_pin_iova(&msm_obj->base,
 				submit->gpu->aspace, &iova);
 
 		if (ret)
@@ -406,6 +409,7 @@ static void submit_cleanup(struct msm_gem_submit *submit)
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file)
 {
+	static atomic_t ident = ATOMIC_INIT(0);
 	struct msm_drm_private *priv = dev->dev_private;
 	struct drm_msm_gem_submit *args = data;
 	struct msm_file_private *ctx = file->driver_priv;
@@ -416,9 +420,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_gpu_submitqueue *queue;
 	struct msm_ringbuffer *ring;
 	int out_fence_fd = -1;
+	struct pid *pid = get_pid(task_pid(current));
 	unsigned i;
-	int ret;
-
+	int ret, submitid;
 	if (!gpu)
 		return -ENXIO;
 
@@ -441,7 +445,12 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
+	/* Get a unique identifier for the submission for logging purposes */
+	submitid = atomic_inc_return(&ident) - 1;
+
 	ring = gpu->rb[queue->prio];
+	trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid,
+		args->nr_bos, args->nr_cmds);
 
 	if (args->flags & MSM_SUBMIT_FENCE_FD_IN) {
 		in_fence = sync_file_get_fence(args->fence_fd);
@@ -478,6 +487,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
+	submit->pid = pid;
+	submit->ident = submitid;
+
 	if (args->flags & MSM_SUBMIT_SUDO)
 		submit->in_rb = true;
 
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index ffbec224551b..557360788084 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -38,20 +38,72 @@ void msm_gem_address_space_put(struct msm_gem_address_space *aspace)
 		kref_put(&aspace->kref, msm_gem_address_space_destroy);
 }
 
-void
-msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
-		struct msm_gem_vma *vma, struct sg_table *sgt)
+/* Actually unmap memory for the vma */
+void msm_gem_purge_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma)
 {
-	if (!aspace || !vma->iova)
+	unsigned size = vma->node.size << PAGE_SHIFT;
+
+	/* Print a message if we try to purge a vma in use */
+	if (WARN_ON(vma->inuse > 0))
+		return;
+
+	/* Don't do anything if the memory isn't mapped */
+	if (!vma->mapped)
 		return;
 
-	if (aspace->mmu) {
-		unsigned size = vma->node.size << PAGE_SHIFT;
-		aspace->mmu->funcs->unmap(aspace->mmu, vma->iova, sgt, size);
-	}
+	if (aspace->mmu)
+		aspace->mmu->funcs->unmap(aspace->mmu, vma->iova, size);
+
+	vma->mapped = false;
+}
+
+/* Remove reference counts for the mapping */
+void msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma)
+{
+	if (!WARN_ON(!vma->iova))
+		vma->inuse--;
+}
+
+int
+msm_gem_map_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma, struct sg_table *sgt, int npages)
+{
+	unsigned size = npages << PAGE_SHIFT;
+	int ret = 0;
+
+	if (WARN_ON(!vma->iova))
+		return -EINVAL;
+
+	/* Increase the usage counter */
+	vma->inuse++;
+
+	if (vma->mapped)
+		return 0;
+
+	vma->mapped = true;
+
+	if (aspace->mmu)
+		ret = aspace->mmu->funcs->map(aspace->mmu, vma->iova, sgt,
+				size, IOMMU_READ | IOMMU_WRITE);
+
+	if (ret)
+		vma->mapped = false;
+
+	return ret;
+}
+
+/* Close an iova.  Warn if it is still in use */
+void msm_gem_close_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma)
+{
+	if (WARN_ON(vma->inuse > 0 || vma->mapped))
+		return;
 
 	spin_lock(&aspace->lock);
-	drm_mm_remove_node(&vma->node);
+	if (vma->iova)
+		drm_mm_remove_node(&vma->node);
 	spin_unlock(&aspace->lock);
 
 	vma->iova = 0;
@@ -59,18 +111,16 @@ msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
 	msm_gem_address_space_put(aspace);
 }
 
-int
-msm_gem_map_vma(struct msm_gem_address_space *aspace,
-		struct msm_gem_vma *vma, struct sg_table *sgt, int npages)
+/* Initialize a new vma and allocate an iova for it */
+int msm_gem_init_vma(struct msm_gem_address_space *aspace,
+		struct msm_gem_vma *vma, int npages)
 {
 	int ret;
 
-	spin_lock(&aspace->lock);
-	if (WARN_ON(drm_mm_node_allocated(&vma->node))) {
-		spin_unlock(&aspace->lock);
-		return 0;
-	}
+	if (WARN_ON(vma->iova))
+		return -EBUSY;
 
+	spin_lock(&aspace->lock);
 	ret = drm_mm_insert_node(&aspace->mm, &vma->node, npages);
 	spin_unlock(&aspace->lock);
 
@@ -78,19 +128,14 @@ msm_gem_map_vma(struct msm_gem_address_space *aspace,
 		return ret;
 
 	vma->iova = vma->node.start << PAGE_SHIFT;
+	vma->mapped = false;
 
-	if (aspace->mmu) {
-		unsigned size = npages << PAGE_SHIFT;
-		ret = aspace->mmu->funcs->map(aspace->mmu, vma->iova, sgt,
-				size, IOMMU_READ | IOMMU_WRITE);
-	}
-
-	/* Get a reference to the aspace to keep it around */
 	kref_get(&aspace->kref);
 
-	return ret;
+	return 0;
 }
 
+
 struct msm_gem_address_space *
 msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 		const char *name)
@@ -114,3 +159,26 @@ msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 
 	return aspace;
 }
+
+struct msm_gem_address_space *
+msm_gem_address_space_create_a2xx(struct device *dev, struct msm_gpu *gpu,
+		const char *name, uint64_t va_start, uint64_t va_end)
+{
+	struct msm_gem_address_space *aspace;
+	u64 size = va_end - va_start;
+
+	aspace = kzalloc(sizeof(*aspace), GFP_KERNEL);
+	if (!aspace)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&aspace->lock);
+	aspace->name = name;
+	aspace->mmu = msm_gpummu_new(dev, gpu);
+
+	drm_mm_init(&aspace->mm, (va_start >> PAGE_SHIFT),
+		size >> PAGE_SHIFT);
+
+	kref_init(&aspace->kref);
+
+	return aspace;
+}
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 11aac8337066..6e079a83bd36 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -19,6 +19,8 @@
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "msm_fence.h"
+#include "msm_gpu_trace.h"
+#include "adreno/adreno_gpu.h"
 
 #include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
@@ -107,7 +109,7 @@ static void msm_devfreq_init(struct msm_gpu *gpu)
 			&msm_devfreq_profile, "simple_ondemand", NULL);
 
 	if (IS_ERR(gpu->devfreq.devfreq)) {
-		dev_err(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
+		DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
 		gpu->devfreq.devfreq = NULL;
 	}
 
@@ -122,7 +124,7 @@ static int enable_pwrrail(struct msm_gpu *gpu)
 	if (gpu->gpu_reg) {
 		ret = regulator_enable(gpu->gpu_reg);
 		if (ret) {
-			dev_err(dev->dev, "failed to enable 'gpu_reg': %d\n", ret);
+			DRM_DEV_ERROR(dev->dev, "failed to enable 'gpu_reg': %d\n", ret);
 			return ret;
 		}
 	}
@@ -130,7 +132,7 @@ static int enable_pwrrail(struct msm_gpu *gpu)
 	if (gpu->gpu_cx) {
 		ret = regulator_enable(gpu->gpu_cx);
 		if (ret) {
-			dev_err(dev->dev, "failed to enable 'gpu_cx': %d\n", ret);
+			DRM_DEV_ERROR(dev->dev, "failed to enable 'gpu_cx': %d\n", ret);
 			return ret;
 		}
 	}
@@ -315,28 +317,28 @@ static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
 	struct msm_gpu_state_bo *state_bo = &state->bos[state->nr_bos];
 
 	/* Don't record write only objects */
-
 	state_bo->size = obj->base.size;
 	state_bo->iova = iova;
 
-	/* Only store the data for buffer objects marked for read */
-	if ((flags & MSM_SUBMIT_BO_READ)) {
+	/* Only store data for non imported buffer objects marked for read */
+	if ((flags & MSM_SUBMIT_BO_READ) && !obj->base.import_attach) {
 		void *ptr;
 
 		state_bo->data = kvmalloc(obj->base.size, GFP_KERNEL);
 		if (!state_bo->data)
-			return;
+			goto out;
 
 		ptr = msm_gem_get_vaddr_active(&obj->base);
 		if (IS_ERR(ptr)) {
 			kvfree(state_bo->data);
-			return;
+			state_bo->data = NULL;
+			goto out;
 		}
 
 		memcpy(state_bo->data, ptr, obj->base.size);
 		msm_gem_put_vaddr(&obj->base);
 	}
-
+out:
 	state->nr_bos++;
 }
 
@@ -360,12 +362,15 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	if (submit) {
 		int i;
 
-		state->bos = kcalloc(submit->nr_bos,
+		state->bos = kcalloc(submit->nr_cmds,
 			sizeof(struct msm_gpu_state_bo), GFP_KERNEL);
 
-		for (i = 0; state->bos && i < submit->nr_bos; 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);
+		}
 	}
 
 	/* Set the active crash state to be dumped on failure */
@@ -428,7 +433,7 @@ static void recover_worker(struct work_struct *work)
 
 	mutex_lock(&dev->struct_mutex);
 
-	dev_err(dev->dev, "%s: hangcheck recover!\n", gpu->name);
+	DRM_DEV_ERROR(dev->dev, "%s: hangcheck recover!\n", gpu->name);
 
 	submit = find_submit(cur_ring, cur_ring->memptrs->fence + 1);
 	if (submit) {
@@ -456,7 +461,7 @@ static void recover_worker(struct work_struct *work)
 		rcu_read_unlock();
 
 		if (comm && cmd) {
-			dev_err(dev->dev, "%s: offending task: %s (%s)\n",
+			DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
 				gpu->name, comm, cmd);
 
 			msm_rd_dump_submit(priv->hangrd, submit,
@@ -539,11 +544,11 @@ static void hangcheck_handler(struct timer_list *t)
 	} else if (fence < ring->seqno) {
 		/* no progress and not done.. hung! */
 		ring->hangcheck_fence = fence;
-		dev_err(dev->dev, "%s: hangcheck detected gpu lockup rb %d!\n",
+		DRM_DEV_ERROR(dev->dev, "%s: hangcheck detected gpu lockup rb %d!\n",
 				gpu->name, ring->id);
-		dev_err(dev->dev, "%s:     completed fence: %u\n",
+		DRM_DEV_ERROR(dev->dev, "%s:     completed fence: %u\n",
 				gpu->name, fence);
-		dev_err(dev->dev, "%s:     submitted fence: %u\n",
+		DRM_DEV_ERROR(dev->dev, "%s:     submitted fence: %u\n",
 				gpu->name, ring->seqno);
 
 		queue_work(priv->wq, &gpu->recover_work);
@@ -659,15 +664,33 @@ out:
  * Cmdstream submission/retirement:
  */
 
-static void retire_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
+static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
+		struct msm_gem_submit *submit)
 {
+	int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
+	volatile struct msm_gpu_submit_stats *stats;
+	u64 elapsed, clock = 0;
 	int i;
 
+	stats = &ring->memptrs->stats[index];
+	/* Convert 19.2Mhz alwayson ticks to nanoseconds for elapsed time */
+	elapsed = (stats->alwayson_end - stats->alwayson_start) * 10000;
+	do_div(elapsed, 192);
+
+	/* Calculate the clock frequency from the number of CP cycles */
+	if (elapsed) {
+		clock = (stats->cpcycles_end - stats->cpcycles_start) * 1000;
+		do_div(clock, elapsed);
+	}
+
+	trace_msm_gpu_submit_retired(submit, elapsed, clock,
+		stats->alwayson_start, stats->alwayson_end);
+
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
 		/* move to inactive: */
 		msm_gem_move_to_inactive(&msm_obj->base);
-		msm_gem_put_iova(&msm_obj->base, gpu->aspace);
+		msm_gem_unpin_iova(&msm_obj->base, gpu->aspace);
 		drm_gem_object_put(&msm_obj->base);
 	}
 
@@ -690,7 +713,7 @@ static void retire_submits(struct msm_gpu *gpu)
 
 		list_for_each_entry_safe(submit, tmp, &ring->submits, node) {
 			if (dma_fence_is_signaled(submit->fence))
-				retire_submit(gpu, submit);
+				retire_submit(gpu, ring, submit);
 		}
 	}
 }
@@ -751,7 +774,7 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 
 		/* submit takes a reference to the bo and iova until retired: */
 		drm_gem_object_get(&msm_obj->base);
-		msm_gem_get_iova(&msm_obj->base,
+		msm_gem_get_and_pin_iova(&msm_obj->base,
 				submit->gpu->aspace, &iova);
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
@@ -800,7 +823,6 @@ static struct msm_gem_address_space *
 msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
 		uint64_t va_start, uint64_t va_end)
 {
-	struct iommu_domain *iommu;
 	struct msm_gem_address_space *aspace;
 	int ret;
 
@@ -809,20 +831,27 @@ msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
 	 * and have separate page tables per context.  For now, to keep things
 	 * simple and to get something working, just use a single address space:
 	 */
-	iommu = iommu_domain_alloc(&platform_bus_type);
-	if (!iommu)
-		return NULL;
-
-	iommu->geometry.aperture_start = va_start;
-	iommu->geometry.aperture_end = va_end;
-
-	dev_info(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);
+	if (!adreno_is_a2xx(to_adreno_gpu(gpu))) {
+		struct iommu_domain *iommu = iommu_domain_alloc(&platform_bus_type);
+		if (!iommu)
+			return NULL;
+
+		iommu->geometry.aperture_start = va_start;
+		iommu->geometry.aperture_end = va_end;
+
+		DRM_DEV_INFO(gpu->dev->dev, "%s: using IOMMU\n", gpu->name);
+
+		aspace = msm_gem_address_space_create(&pdev->dev, iommu, "gpu");
+		if (IS_ERR(aspace))
+			iommu_domain_free(iommu);
+	} else {
+		aspace = msm_gem_address_space_create_a2xx(&pdev->dev, gpu, "gpu",
+			va_start, va_end);
+	}
 
-	aspace = msm_gem_address_space_create(&pdev->dev, iommu, "gpu");
 	if (IS_ERR(aspace)) {
-		dev_err(gpu->dev->dev, "failed to init iommu: %ld\n",
+		DRM_DEV_ERROR(gpu->dev->dev, "failed to init mmu: %ld\n",
 			PTR_ERR(aspace));
-		iommu_domain_free(iommu);
 		return ERR_CAST(aspace);
 	}
 
@@ -871,14 +900,14 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	gpu->irq = platform_get_irq_byname(pdev, config->irqname);
 	if (gpu->irq < 0) {
 		ret = gpu->irq;
-		dev_err(drm->dev, "failed to get irq: %d\n", ret);
+		DRM_DEV_ERROR(drm->dev, "failed to get irq: %d\n", ret);
 		goto fail;
 	}
 
 	ret = devm_request_irq(&pdev->dev, gpu->irq, irq_handler,
 			IRQF_TRIGGER_HIGH, gpu->name, gpu);
 	if (ret) {
-		dev_err(drm->dev, "failed to request IRQ%u: %d\n", gpu->irq, ret);
+		DRM_DEV_ERROR(drm->dev, "failed to request IRQ%u: %d\n", gpu->irq, ret);
 		goto fail;
 	}
 
@@ -911,22 +940,25 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		config->va_start, config->va_end);
 
 	if (gpu->aspace == NULL)
-		dev_info(drm->dev, "%s: no IOMMU, fallback to VRAM carveout!\n", name);
+		DRM_DEV_INFO(drm->dev, "%s: no IOMMU, fallback to VRAM carveout!\n", name);
 	else if (IS_ERR(gpu->aspace)) {
 		ret = PTR_ERR(gpu->aspace);
 		goto fail;
 	}
 
-	memptrs = msm_gem_kernel_new(drm, sizeof(*gpu->memptrs_bo),
+	memptrs = msm_gem_kernel_new(drm,
+		sizeof(struct msm_rbmemptrs) * nr_rings,
 		MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo,
 		&memptrs_iova);
 
 	if (IS_ERR(memptrs)) {
 		ret = PTR_ERR(memptrs);
-		dev_err(drm->dev, "could not allocate memptrs: %d\n", ret);
+		DRM_DEV_ERROR(drm->dev, "could not allocate memptrs: %d\n", ret);
 		goto fail;
 	}
 
+	msm_gem_object_set_name(gpu->memptrs_bo, "memptrs");
+
 	if (nr_rings > ARRAY_SIZE(gpu->rb)) {
 		DRM_DEV_INFO_ONCE(drm->dev, "Only creating %zu ringbuffers\n",
 			ARRAY_SIZE(gpu->rb));
@@ -939,7 +971,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 		if (IS_ERR(gpu->rb[i])) {
 			ret = PTR_ERR(gpu->rb[i]);
-			dev_err(drm->dev,
+			DRM_DEV_ERROR(drm->dev,
 				"could not create ringbuffer %d: %d\n", i, ret);
 			goto fail;
 		}
@@ -958,11 +990,7 @@ fail:
 		gpu->rb[i] = NULL;
 	}
 
-	if (gpu->memptrs_bo) {
-		msm_gem_put_vaddr(gpu->memptrs_bo);
-		msm_gem_put_iova(gpu->memptrs_bo, gpu->aspace);
-		drm_gem_object_put_unlocked(gpu->memptrs_bo);
-	}
+	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
 
 	platform_set_drvdata(pdev, NULL);
 	return ret;
@@ -981,11 +1009,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 		gpu->rb[i] = NULL;
 	}
 
-	if (gpu->memptrs_bo) {
-		msm_gem_put_vaddr(gpu->memptrs_bo);
-		msm_gem_put_iova(gpu->memptrs_bo, gpu->aspace);
-		drm_gem_object_put_unlocked(gpu->memptrs_bo);
-	}
+	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
 
 	if (!IS_ERR_OR_NULL(gpu->aspace)) {
 		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index f82bac086666..efb49bb64191 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -187,6 +187,7 @@ struct msm_gpu_state_bo {
 	u64 iova;
 	size_t size;
 	void *data;
+	bool encoded;
 };
 
 struct msm_gpu_state {
@@ -201,6 +202,7 @@ struct msm_gpu_state {
 		u32 wptr;
 		void *data;
 		int data_size;
+		bool encoded;
 	} ring[MSM_GPU_MAX_RINGS];
 
 	int nr_registers;
diff --git a/drivers/gpu/drm/msm/msm_gpu_trace.h b/drivers/gpu/drm/msm/msm_gpu_trace.h
new file mode 100644
index 000000000000..1155118a27a1
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gpu_trace.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(_MSM_GPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MSM_GPU_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM drm_msm
+#define TRACE_INCLUDE_FILE msm_gpu_trace
+
+TRACE_EVENT(msm_gpu_submit,
+	    TP_PROTO(pid_t pid, u32 ringid, u32 id, u32 nr_bos, u32 nr_cmds),
+	    TP_ARGS(pid, ringid, id, nr_bos, nr_cmds),
+	    TP_STRUCT__entry(
+		    __field(pid_t, pid)
+		    __field(u32, id)
+		    __field(u32, ringid)
+		    __field(u32, nr_cmds)
+		    __field(u32, nr_bos)
+		    ),
+	    TP_fast_assign(
+		    __entry->pid = pid;
+		    __entry->id = id;
+		    __entry->ringid = ringid;
+		    __entry->nr_bos = nr_bos;
+		    __entry->nr_cmds = nr_cmds
+		    ),
+	    TP_printk("id=%d pid=%d ring=%d bos=%d cmds=%d",
+		    __entry->id, __entry->pid, __entry->ringid,
+		    __entry->nr_bos, __entry->nr_cmds)
+);
+
+TRACE_EVENT(msm_gpu_submit_flush,
+	    TP_PROTO(struct msm_gem_submit *submit, u64 ticks),
+	    TP_ARGS(submit, ticks),
+	    TP_STRUCT__entry(
+		    __field(pid_t, pid)
+		    __field(u32, id)
+		    __field(u32, ringid)
+		    __field(u32, seqno)
+		    __field(u64, ticks)
+		    ),
+	    TP_fast_assign(
+		    __entry->pid = pid_nr(submit->pid);
+		    __entry->id = submit->ident;
+		    __entry->ringid = submit->ring->id;
+		    __entry->seqno = submit->seqno;
+		    __entry->ticks = ticks;
+		    ),
+	    TP_printk("id=%d pid=%d ring=%d:%d ticks=%lld",
+		    __entry->id, __entry->pid, __entry->ringid, __entry->seqno,
+		    __entry->ticks)
+);
+
+
+TRACE_EVENT(msm_gpu_submit_retired,
+	    TP_PROTO(struct msm_gem_submit *submit, u64 elapsed, u64 clock,
+		    u64 start, u64 end),
+	    TP_ARGS(submit, elapsed, clock, start, end),
+	    TP_STRUCT__entry(
+		    __field(pid_t, pid)
+		    __field(u32, id)
+		    __field(u32, ringid)
+		    __field(u32, seqno)
+		    __field(u64, elapsed)
+		    __field(u64, clock)
+		    __field(u64, start_ticks)
+		    __field(u64, end_ticks)
+		    ),
+	    TP_fast_assign(
+		    __entry->pid = pid_nr(submit->pid);
+		    __entry->id = submit->ident;
+		    __entry->ringid = submit->ring->id;
+		    __entry->seqno = submit->seqno;
+		    __entry->elapsed = elapsed;
+		    __entry->clock = clock;
+		    __entry->start_ticks = start;
+		    __entry->end_ticks = end;
+		    ),
+	    TP_printk("id=%d pid=%d ring=%d:%d elapsed=%lld ns mhz=%lld start=%lld end=%lld",
+		    __entry->id, __entry->pid, __entry->ringid, __entry->seqno,
+		    __entry->elapsed, __entry->clock,
+		    __entry->start_ticks, __entry->end_ticks)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/msm
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/msm/msm_gpu_tracepoints.c b/drivers/gpu/drm/msm/msm_gpu_tracepoints.c
new file mode 100644
index 000000000000..72c074f8c4f8
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gpu_tracepoints.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "msm_gem.h"
+#include "msm_ringbuffer.h"
+
+#define CREATE_TRACE_POINTS
+#include "msm_gpu_trace.h"
diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c
new file mode 100644
index 000000000000..27312b553dd8
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gpummu.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+
+#include "msm_drv.h"
+#include "msm_mmu.h"
+#include "adreno/adreno_gpu.h"
+#include "adreno/a2xx.xml.h"
+
+struct msm_gpummu {
+	struct msm_mmu base;
+	struct msm_gpu *gpu;
+	dma_addr_t pt_base;
+	uint32_t *table;
+};
+#define to_msm_gpummu(x) container_of(x, struct msm_gpummu, base)
+
+#define GPUMMU_VA_START SZ_16M
+#define GPUMMU_VA_RANGE (0xfff * SZ_64K)
+#define GPUMMU_PAGE_SIZE SZ_4K
+#define TABLE_SIZE (sizeof(uint32_t) * GPUMMU_VA_RANGE / GPUMMU_PAGE_SIZE)
+
+static int msm_gpummu_attach(struct msm_mmu *mmu, const char * const *names,
+		int cnt)
+{
+	return 0;
+}
+
+static void msm_gpummu_detach(struct msm_mmu *mmu, const char * const *names,
+		int cnt)
+{
+}
+
+static int msm_gpummu_map(struct msm_mmu *mmu, uint64_t iova,
+		struct sg_table *sgt, unsigned len, int prot)
+{
+	struct msm_gpummu *gpummu = to_msm_gpummu(mmu);
+	unsigned idx = (iova - GPUMMU_VA_START) / GPUMMU_PAGE_SIZE;
+	struct scatterlist *sg;
+	unsigned prot_bits = 0;
+	unsigned i, j;
+
+	if (prot & IOMMU_WRITE)
+		prot_bits |= 1;
+	if (prot & IOMMU_READ)
+		prot_bits |= 2;
+
+	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+		dma_addr_t addr = sg->dma_address;
+		for (j = 0; j < sg->length / GPUMMU_PAGE_SIZE; j++, idx++) {
+			gpummu->table[idx] = addr | prot_bits;
+			addr += GPUMMU_PAGE_SIZE;
+		}
+	}
+
+	/* we can improve by deferring flush for multiple map() */
+	gpu_write(gpummu->gpu, REG_A2XX_MH_MMU_INVALIDATE,
+		A2XX_MH_MMU_INVALIDATE_INVALIDATE_ALL |
+		A2XX_MH_MMU_INVALIDATE_INVALIDATE_TC);
+	return 0;
+}
+
+static int msm_gpummu_unmap(struct msm_mmu *mmu, uint64_t iova, unsigned len)
+{
+	struct msm_gpummu *gpummu = to_msm_gpummu(mmu);
+	unsigned idx = (iova - GPUMMU_VA_START) / GPUMMU_PAGE_SIZE;
+	unsigned i;
+
+	for (i = 0; i < len / GPUMMU_PAGE_SIZE; i++, idx++)
+                gpummu->table[idx] = 0;
+
+	gpu_write(gpummu->gpu, REG_A2XX_MH_MMU_INVALIDATE,
+		A2XX_MH_MMU_INVALIDATE_INVALIDATE_ALL |
+		A2XX_MH_MMU_INVALIDATE_INVALIDATE_TC);
+	return 0;
+}
+
+static void msm_gpummu_destroy(struct msm_mmu *mmu)
+{
+	struct msm_gpummu *gpummu = to_msm_gpummu(mmu);
+
+	dma_free_attrs(mmu->dev, TABLE_SIZE, gpummu->table, gpummu->pt_base,
+		DMA_ATTR_FORCE_CONTIGUOUS);
+
+	kfree(gpummu);
+}
+
+static const struct msm_mmu_funcs funcs = {
+		.attach = msm_gpummu_attach,
+		.detach = msm_gpummu_detach,
+		.map = msm_gpummu_map,
+		.unmap = msm_gpummu_unmap,
+		.destroy = msm_gpummu_destroy,
+};
+
+struct msm_mmu *msm_gpummu_new(struct device *dev, struct msm_gpu *gpu)
+{
+	struct msm_gpummu *gpummu;
+
+	gpummu = kzalloc(sizeof(*gpummu), GFP_KERNEL);
+	if (!gpummu)
+		return ERR_PTR(-ENOMEM);
+
+	gpummu->table = dma_alloc_attrs(dev, TABLE_SIZE + 32, &gpummu->pt_base,
+		GFP_KERNEL | __GFP_ZERO, DMA_ATTR_FORCE_CONTIGUOUS);
+	if (!gpummu->table) {
+		kfree(gpummu);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	gpummu->gpu = gpu;
+	msm_mmu_init(&gpummu->base, dev, &funcs);
+
+	return &gpummu->base;
+}
+
+void msm_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base,
+		dma_addr_t *tran_error)
+{
+	dma_addr_t base = to_msm_gpummu(mmu)->pt_base;
+
+	*pt_base = base;
+	*tran_error = base + TABLE_SIZE; /* 32-byte aligned */
+}
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index b23d33622f37..9c313cb129ee 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -71,8 +71,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
 	return (ret == len) ? 0 : -EINVAL;
 }
 
-static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova,
-		struct sg_table *sgt, unsigned len)
+static int msm_iommu_unmap(struct msm_mmu *mmu, uint64_t iova, unsigned len)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index fd88cebb6adb..2b81b43a4bab 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -67,9 +67,6 @@ struct msm_kms_funcs {
 	void (*set_encoder_mode)(struct msm_kms *kms,
 				 struct drm_encoder *encoder,
 				 bool cmd_mode);
-	/* pm suspend/resume hooks */
-	int (*pm_suspend)(struct device *dev);
-	int (*pm_resume)(struct device *dev);
 	/* cleanup: */
 	void (*destroy)(struct msm_kms *kms);
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index aa2c5d4580c8..d21b26604d0b 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -25,8 +25,7 @@ struct msm_mmu_funcs {
 	void (*detach)(struct msm_mmu *mmu, const char * const *names, int cnt);
 	int (*map)(struct msm_mmu *mmu, uint64_t iova, struct sg_table *sgt,
 			unsigned len, int prot);
-	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, struct sg_table *sgt,
-			unsigned len);
+	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, unsigned len);
 	void (*destroy)(struct msm_mmu *mmu);
 };
 
@@ -54,4 +53,7 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg,
 	mmu->handler = handler;
 }
 
+void msm_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base,
+		dma_addr_t *tran_error);
+
 #endif /* __MSM_MMU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index cca933458439..b5672061ae08 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -345,6 +345,12 @@ 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, ...)
@@ -386,15 +392,16 @@ void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit,
 
 	rd_write_section(rd, RD_CMD, msg, ALIGN(n, 4));
 
-	for (i = 0; rd_full && i < submit->nr_bos; i++)
-		snapshot_buf(rd, submit, i, 0, 0);
+	for (i = 0; i < submit->nr_bos; i++)
+		if (should_dump(submit, i))
+			snapshot_buf(rd, submit, i, 0, 0);
 
 	for (i = 0; i < submit->nr_cmds; i++) {
 		uint64_t iova = submit->cmd[i].iova;
 		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		/* snapshot cmdstream bo's (if we haven't already): */
-		if (!rd_full) {
+		if (!should_dump(submit, i)) {
 			snapshot_buf(rd, submit, submit->cmd[i].idx,
 					submit->cmd[i].iova, szd * 4);
 		}
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 6f5295b3f2f6..20a96fe69dcd 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -36,15 +36,18 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 
 	ring->gpu = gpu;
 	ring->id = id;
-	/* Pass NULL for the iova pointer - we will map it later */
+
 	ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ,
-		MSM_BO_WC, gpu->aspace, &ring->bo, NULL);
+		MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova);
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
 		ring->start = 0;
 		goto fail;
 	}
+
+	msm_gem_object_set_name(ring->bo, "ring%d", id);
+
 	ring->end   = ring->start + (MSM_GPU_RINGBUFFER_SZ >> 2);
 	ring->next  = ring->start;
 	ring->cur   = ring->start;
@@ -73,10 +76,7 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 
 	msm_fence_context_free(ring->fctx);
 
-	if (ring->bo) {
-		msm_gem_put_iova(ring->bo, ring->gpu->aspace);
-		msm_gem_put_vaddr(ring->bo);
-		drm_gem_object_put_unlocked(ring->bo);
-	}
+	msm_gem_kernel_put(ring->bo, ring->gpu->aspace, false);
+
 	kfree(ring);
 }
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
index cffce094aecb..6434ebb13136 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -23,9 +23,25 @@
 #define rbmemptr(ring, member)  \
 	((ring)->memptrs_iova + offsetof(struct msm_rbmemptrs, member))
 
+#define rbmemptr_stats(ring, index, member) \
+	(rbmemptr((ring), stats) + \
+	 ((index) * sizeof(struct msm_gpu_submit_stats)) + \
+	 offsetof(struct msm_gpu_submit_stats, member))
+
+struct msm_gpu_submit_stats {
+	u64 cpcycles_start;
+	u64 cpcycles_end;
+	u64 alwayson_start;
+	u64 alwayson_end;
+};
+
+#define MSM_GPU_SUBMIT_STATS_COUNT 64
+
 struct msm_rbmemptrs {
 	volatile uint32_t rptr;
 	volatile uint32_t fence;
+
+	volatile struct msm_gpu_submit_stats stats[MSM_GPU_SUBMIT_STATS_COUNT];
 };
 
 struct msm_ringbuffer {
author	Dave Airlie <airlied@redhat.com>	2018-12-13 01:29:14 +0100
committer	Dave Airlie <airlied@redhat.com>	2018-12-13 01:29:30 +0100
commit	d675ba4b9e6ccd782e4db9109cbab708a85b8ff8 (patch)
tree	e488f7fc7e13f87a3b9e04c31aadb04a6a6ca43c /drivers/gpu
parent	Merge branch 'linux-4.21' of git://github.com/skeggsb/linux into drm-next (diff)
parent	drm/msm/dpu: Fix clock issue after bind failure (diff)
download	linux-d675ba4b9e6ccd782e4db9109cbab708a85b8ff8.tar.xz linux-d675ba4b9e6ccd782e4db9109cbab708a85b8ff8.zip