Merge tag 'drm-msm-next-2017-06-20' of git://people.freedesktop.org/~robclark/linux into drm-next

This time around, the biggest thing is a bunch of GEM rework for more fine grained locking and prep work to handle multiple address spaces (ie. per-process pagetables). Also some HDMI fixes for 8x96 (snapdragon 820). One unrelated bus patch, for something that seems to get merged through whatever random tree (and has all the right ack's). * tag 'drm-msm-next-2017-06-20' of git://people.freedesktop.org/~robclark/linux: drm/msm: Fix potential buffer overflow issue bus: SIMPLE_PM_BUS does not depend on ARCH_RENESAS drm/msm: Separate locking of buffer resources from struct_mutex drm/msm/hdmi: Fix HDMI pink strip issue seen on 8x96 drm/msm/hdmi: 8996 PLL: Populate unprepare drm/msm/hdmi: Use bitwise operators when building register values drm/msm: update generated headers drm/msm: remove address-space id drm/msm: support for an arbitrary number of address spaces drm/msm: refactor how we handle vram carveout buffers drm/msm: pass address-space to _get_iova() and friends drm/msm/mdp4+5: move aspace/id to base class drm/msm/mdp5: kill pipe_lock drm/msm: fix locking inconsistency for gpu->hw_init() drm/msm: Remove memptrs->wptr drm/msm: Add a struct to pass configuration to msm_gpu_init() drm/msm: Add hint to DRM_IOCTL_MSM_GEM_INFO to return an object IOVA drm/msm: Remove idle function hook drm/msm: Remove DRM_MSM_NUM_IOCTLS drm/msm: gpu: Enable zap shader for A5XX
author: Dave Airlie <airlied@redhat.com> 2017-06-21 08:49:54 +1000
committer: Dave Airlie <airlied@redhat.com> 2017-06-21 08:49:54 +1000
commit: eafae133e48c9e5f5537d5c6df34eab912336b9a (patch)
tree: fb9fd9337cd93e597114cf3c5f4ca9e9bb3a4f7e
parent: 8c52f36413063bedbb3d31a65048a61ea2f1e169 (diff)
parent: 4a630fadbb29d9efaedb525f1a8f7449ad107641 (diff)
download: linux-stable-eafae133e48c9e5f5537d5c6df34eab912336b9a.tar.gz
linux-stable-eafae133e48c9e5f5537d5c6df34eab912336b9a.tar.bz2
linux-stable-eafae133e48c9e5f5537d5c6df34eab912336b9a.zip
52 files changed, 2822 insertions, 678 deletions
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index 0a52da439abf..b83c5351376c 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -121,7 +121,6 @@ config QCOM_EBI2
 config SIMPLE_PM_BUS
 	bool "Simple Power-Managed Bus Driver"
 	depends on OF && PM
-	depends on ARCH_RENESAS || COMPILE_TEST
 	help
 	  Driver for transparent busses that don't need a real driver, but
 	  where the bus controller is part of a PM domain, or under the control
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 0a31cd6d01ce..b638d192ce5e 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -5,6 +5,7 @@ config DRM_MSM
 	depends on ARCH_QCOM || (ARM && COMPILE_TEST)
 	depends on OF && COMMON_CLK
 	depends on MMU
+	select QCOM_MDT_LOADER
 	select REGULATOR
 	select DRM_KMS_HELPER
 	select DRM_PANEL
diff --git a/drivers/gpu/drm/msm/adreno/a2xx.xml.h b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
index 4be092f911f9..644374c7b3e0 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
@@ -8,17 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2016-04-26 17:56:44)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32907 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  12025 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  22544 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 110765 bytes, from 2016-11-26 23:01:48)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          (  90321 bytes, from 2016-11-28 16:50:05)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2015-09-24 17:30:00)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  37162 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  13324 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  31866 bytes, from 2017-06-06 18:26:14)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 111898 bytes, from 2017-06-06 18:23:59)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          ( 139480 bytes, from 2017-06-16 12:44:39)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -352,6 +352,38 @@ static inline uint32_t A2XX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_cln
 #define REG_A2XX_RBBM_DEBUG					0x0000039b
 
 #define REG_A2XX_RBBM_PM_OVERRIDE1				0x0000039c
+#define A2XX_RBBM_PM_OVERRIDE1_RBBM_AHBCLK_PM_OVERRIDE		0x00000001
+#define A2XX_RBBM_PM_OVERRIDE1_SC_REG_SCLK_PM_OVERRIDE		0x00000002
+#define A2XX_RBBM_PM_OVERRIDE1_SC_SCLK_PM_OVERRIDE		0x00000004
+#define A2XX_RBBM_PM_OVERRIDE1_SP_TOP_SCLK_PM_OVERRIDE		0x00000008
+#define A2XX_RBBM_PM_OVERRIDE1_SP_V0_SCLK_PM_OVERRIDE		0x00000010
+#define A2XX_RBBM_PM_OVERRIDE1_SQ_REG_SCLK_PM_OVERRIDE		0x00000020
+#define A2XX_RBBM_PM_OVERRIDE1_SQ_REG_FIFOS_SCLK_PM_OVERRIDE	0x00000040
+#define A2XX_RBBM_PM_OVERRIDE1_SQ_CONST_MEM_SCLK_PM_OVERRIDE	0x00000080
+#define A2XX_RBBM_PM_OVERRIDE1_SQ_SQ_SCLK_PM_OVERRIDE		0x00000100
+#define A2XX_RBBM_PM_OVERRIDE1_SX_SCLK_PM_OVERRIDE		0x00000200
+#define A2XX_RBBM_PM_OVERRIDE1_SX_REG_SCLK_PM_OVERRIDE		0x00000400
+#define A2XX_RBBM_PM_OVERRIDE1_TCM_TCO_SCLK_PM_OVERRIDE		0x00000800
+#define A2XX_RBBM_PM_OVERRIDE1_TCM_TCM_SCLK_PM_OVERRIDE		0x00001000
+#define A2XX_RBBM_PM_OVERRIDE1_TCM_TCD_SCLK_PM_OVERRIDE		0x00002000
+#define A2XX_RBBM_PM_OVERRIDE1_TCM_REG_SCLK_PM_OVERRIDE		0x00004000
+#define A2XX_RBBM_PM_OVERRIDE1_TPC_TPC_SCLK_PM_OVERRIDE		0x00008000
+#define A2XX_RBBM_PM_OVERRIDE1_TPC_REG_SCLK_PM_OVERRIDE		0x00010000
+#define A2XX_RBBM_PM_OVERRIDE1_TCF_TCA_SCLK_PM_OVERRIDE		0x00020000
+#define A2XX_RBBM_PM_OVERRIDE1_TCF_TCB_SCLK_PM_OVERRIDE		0x00040000
+#define A2XX_RBBM_PM_OVERRIDE1_TCF_TCB_READ_SCLK_PM_OVERRIDE	0x00080000
+#define A2XX_RBBM_PM_OVERRIDE1_TP_TP_SCLK_PM_OVERRIDE		0x00100000
+#define A2XX_RBBM_PM_OVERRIDE1_TP_REG_SCLK_PM_OVERRIDE		0x00200000
+#define A2XX_RBBM_PM_OVERRIDE1_CP_G_SCLK_PM_OVERRIDE		0x00400000
+#define A2XX_RBBM_PM_OVERRIDE1_CP_REG_SCLK_PM_OVERRIDE		0x00800000
+#define A2XX_RBBM_PM_OVERRIDE1_CP_G_REG_SCLK_PM_OVERRIDE	0x01000000
+#define A2XX_RBBM_PM_OVERRIDE1_SPI_SCLK_PM_OVERRIDE		0x02000000
+#define A2XX_RBBM_PM_OVERRIDE1_RB_REG_SCLK_PM_OVERRIDE		0x04000000
+#define A2XX_RBBM_PM_OVERRIDE1_RB_SCLK_PM_OVERRIDE		0x08000000
+#define A2XX_RBBM_PM_OVERRIDE1_MH_MH_SCLK_PM_OVERRIDE		0x10000000
+#define A2XX_RBBM_PM_OVERRIDE1_MH_REG_SCLK_PM_OVERRIDE		0x20000000
+#define A2XX_RBBM_PM_OVERRIDE1_MH_MMU_SCLK_PM_OVERRIDE		0x40000000
+#define A2XX_RBBM_PM_OVERRIDE1_MH_TCROQ_SCLK_PM_OVERRIDE	0x80000000
 
 #define REG_A2XX_RBBM_PM_OVERRIDE2				0x0000039d
 
@@ -477,12 +509,43 @@ static inline uint32_t REG_A2XX_VSC_PIPE_DATA_LENGTH(uint32_t i0) { return 0x000
 #define REG_A2XX_PA_SU_DEBUG_DATA				0x00000c81
 
 #define REG_A2XX_PA_SU_FACE_DATA				0x00000c86
+#define A2XX_PA_SU_FACE_DATA_BASE_ADDR__MASK			0xffffffe0
+#define A2XX_PA_SU_FACE_DATA_BASE_ADDR__SHIFT			5
+static inline uint32_t A2XX_PA_SU_FACE_DATA_BASE_ADDR(uint32_t val)
+{
+	return ((val) << A2XX_PA_SU_FACE_DATA_BASE_ADDR__SHIFT) & A2XX_PA_SU_FACE_DATA_BASE_ADDR__MASK;
+}
 
 #define REG_A2XX_SQ_GPR_MANAGEMENT				0x00000d00
+#define A2XX_SQ_GPR_MANAGEMENT_REG_DYNAMIC			0x00000001
+#define A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_PIX__MASK		0x00000ff0
+#define A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_PIX__SHIFT		4
+static inline uint32_t A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_PIX(uint32_t val)
+{
+	return ((val) << A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_PIX__SHIFT) & A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_PIX__MASK;
+}
+#define A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_VTX__MASK		0x000ff000
+#define A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_VTX__SHIFT		12
+static inline uint32_t A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_VTX(uint32_t val)
+{
+	return ((val) << A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_VTX__SHIFT) & A2XX_SQ_GPR_MANAGEMENT_REG_SIZE_VTX__MASK;
+}
 
 #define REG_A2XX_SQ_FLOW_CONTROL				0x00000d01
 
 #define REG_A2XX_SQ_INST_STORE_MANAGMENT			0x00000d02
+#define A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_PIX__MASK	0x00000fff
+#define A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_PIX__SHIFT	0
+static inline uint32_t A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_PIX(uint32_t val)
+{
+	return ((val) << A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_PIX__SHIFT) & A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_PIX__MASK;
+}
+#define A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_VTX__MASK	0x0fff0000
+#define A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_VTX__SHIFT	16
+static inline uint32_t A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_VTX(uint32_t val)
+{
+	return ((val) << A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_VTX__SHIFT) & A2XX_SQ_INST_STORE_MANAGMENT_INST_BASE_VTX__MASK;
+}
 
 #define REG_A2XX_SQ_DEBUG_MISC					0x00000d05
 
@@ -742,6 +805,24 @@ static inline uint32_t A2XX_PA_SC_WINDOW_SCISSOR_BR_Y(uint32_t val)
 #define REG_A2XX_RB_BLEND_ALPHA					0x00002108
 
 #define REG_A2XX_RB_FOG_COLOR					0x00002109
+#define A2XX_RB_FOG_COLOR_FOG_RED__MASK				0x000000ff
+#define A2XX_RB_FOG_COLOR_FOG_RED__SHIFT			0
+static inline uint32_t A2XX_RB_FOG_COLOR_FOG_RED(uint32_t val)
+{
+	return ((val) << A2XX_RB_FOG_COLOR_FOG_RED__SHIFT) & A2XX_RB_FOG_COLOR_FOG_RED__MASK;
+}
+#define A2XX_RB_FOG_COLOR_FOG_GREEN__MASK			0x0000ff00
+#define A2XX_RB_FOG_COLOR_FOG_GREEN__SHIFT			8
+static inline uint32_t A2XX_RB_FOG_COLOR_FOG_GREEN(uint32_t val)
+{
+	return ((val) << A2XX_RB_FOG_COLOR_FOG_GREEN__SHIFT) & A2XX_RB_FOG_COLOR_FOG_GREEN__MASK;
+}
+#define A2XX_RB_FOG_COLOR_FOG_BLUE__MASK			0x00ff0000
+#define A2XX_RB_FOG_COLOR_FOG_BLUE__SHIFT			16
+static inline uint32_t A2XX_RB_FOG_COLOR_FOG_BLUE(uint32_t val)
+{
+	return ((val) << A2XX_RB_FOG_COLOR_FOG_BLUE__SHIFT) & A2XX_RB_FOG_COLOR_FOG_BLUE__MASK;
+}
 
 #define REG_A2XX_RB_STENCILREFMASK_BF				0x0000210c
 #define A2XX_RB_STENCILREFMASK_BF_STENCILREF__MASK		0x000000ff
@@ -890,14 +971,146 @@ static inline uint32_t A2XX_SQ_CONTEXT_MISC_PARAM_GEN_POS(uint32_t val)
 #define A2XX_SQ_CONTEXT_MISC_TX_CACHE_SEL			0x00040000
 
 #define REG_A2XX_SQ_INTERPOLATOR_CNTL				0x00002182
+#define A2XX_SQ_INTERPOLATOR_CNTL_PARAM_SHADE__MASK		0x0000ffff
+#define A2XX_SQ_INTERPOLATOR_CNTL_PARAM_SHADE__SHIFT		0
+static inline uint32_t A2XX_SQ_INTERPOLATOR_CNTL_PARAM_SHADE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_INTERPOLATOR_CNTL_PARAM_SHADE__SHIFT) & A2XX_SQ_INTERPOLATOR_CNTL_PARAM_SHADE__MASK;
+}
+#define A2XX_SQ_INTERPOLATOR_CNTL_SAMPLING_PATTERN__MASK	0xffff0000
+#define A2XX_SQ_INTERPOLATOR_CNTL_SAMPLING_PATTERN__SHIFT	16
+static inline uint32_t A2XX_SQ_INTERPOLATOR_CNTL_SAMPLING_PATTERN(uint32_t val)
+{
+	return ((val) << A2XX_SQ_INTERPOLATOR_CNTL_SAMPLING_PATTERN__SHIFT) & A2XX_SQ_INTERPOLATOR_CNTL_SAMPLING_PATTERN__MASK;
+}
 
 #define REG_A2XX_SQ_WRAPPING_0					0x00002183
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_0__MASK			0x0000000f
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_0__SHIFT			0
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_0(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_0__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_0__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_1__MASK			0x000000f0
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_1__SHIFT			4
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_1(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_1__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_1__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_2__MASK			0x00000f00
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_2__SHIFT			8
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_2(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_2__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_2__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_3__MASK			0x0000f000
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_3__SHIFT			12
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_3(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_3__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_3__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_4__MASK			0x000f0000
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_4__SHIFT			16
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_4(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_4__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_4__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_5__MASK			0x00f00000
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_5__SHIFT			20
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_5(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_5__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_5__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_6__MASK			0x0f000000
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_6__SHIFT			24
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_6(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_6__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_6__MASK;
+}
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_7__MASK			0xf0000000
+#define A2XX_SQ_WRAPPING_0_PARAM_WRAP_7__SHIFT			28
+static inline uint32_t A2XX_SQ_WRAPPING_0_PARAM_WRAP_7(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_0_PARAM_WRAP_7__SHIFT) & A2XX_SQ_WRAPPING_0_PARAM_WRAP_7__MASK;
+}
 
 #define REG_A2XX_SQ_WRAPPING_1					0x00002184
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_8__MASK			0x0000000f
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_8__SHIFT			0
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_8(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_8__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_8__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_9__MASK			0x000000f0
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_9__SHIFT			4
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_9(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_9__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_9__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_10__MASK			0x00000f00
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_10__SHIFT			8
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_10(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_10__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_10__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_11__MASK			0x0000f000
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_11__SHIFT			12
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_11(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_11__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_11__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_12__MASK			0x000f0000
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_12__SHIFT			16
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_12(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_12__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_12__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_13__MASK			0x00f00000
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_13__SHIFT			20
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_13(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_13__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_13__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_14__MASK			0x0f000000
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_14__SHIFT			24
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_14(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_14__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_14__MASK;
+}
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_15__MASK			0xf0000000
+#define A2XX_SQ_WRAPPING_1_PARAM_WRAP_15__SHIFT			28
+static inline uint32_t A2XX_SQ_WRAPPING_1_PARAM_WRAP_15(uint32_t val)
+{
+	return ((val) << A2XX_SQ_WRAPPING_1_PARAM_WRAP_15__SHIFT) & A2XX_SQ_WRAPPING_1_PARAM_WRAP_15__MASK;
+}
 
 #define REG_A2XX_SQ_PS_PROGRAM					0x000021f6
+#define A2XX_SQ_PS_PROGRAM_BASE__MASK				0x00000fff
+#define A2XX_SQ_PS_PROGRAM_BASE__SHIFT				0
+static inline uint32_t A2XX_SQ_PS_PROGRAM_BASE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PS_PROGRAM_BASE__SHIFT) & A2XX_SQ_PS_PROGRAM_BASE__MASK;
+}
+#define A2XX_SQ_PS_PROGRAM_SIZE__MASK				0x00fff000
+#define A2XX_SQ_PS_PROGRAM_SIZE__SHIFT				12
+static inline uint32_t A2XX_SQ_PS_PROGRAM_SIZE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PS_PROGRAM_SIZE__SHIFT) & A2XX_SQ_PS_PROGRAM_SIZE__MASK;
+}
 
 #define REG_A2XX_SQ_VS_PROGRAM					0x000021f7
+#define A2XX_SQ_VS_PROGRAM_BASE__MASK				0x00000fff
+#define A2XX_SQ_VS_PROGRAM_BASE__SHIFT				0
+static inline uint32_t A2XX_SQ_VS_PROGRAM_BASE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_VS_PROGRAM_BASE__SHIFT) & A2XX_SQ_VS_PROGRAM_BASE__MASK;
+}
+#define A2XX_SQ_VS_PROGRAM_SIZE__MASK				0x00fff000
+#define A2XX_SQ_VS_PROGRAM_SIZE__SHIFT				12
+static inline uint32_t A2XX_SQ_VS_PROGRAM_SIZE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_VS_PROGRAM_SIZE__SHIFT) & A2XX_SQ_VS_PROGRAM_SIZE__MASK;
+}
 
 #define REG_A2XX_VGT_EVENT_INITIATOR				0x000021f9
 
@@ -1304,6 +1517,14 @@ static inline uint32_t A2XX_PA_SC_LINE_STIPPLE_AUTO_RESET_CNTL(enum a2xx_pa_sc_a
 }
 
 #define REG_A2XX_PA_SC_VIZ_QUERY				0x00002293
+#define A2XX_PA_SC_VIZ_QUERY_VIZ_QUERY_ENA			0x00000001
+#define A2XX_PA_SC_VIZ_QUERY_VIZ_QUERY_ID__MASK			0x0000007e
+#define A2XX_PA_SC_VIZ_QUERY_VIZ_QUERY_ID__SHIFT		1
+static inline uint32_t A2XX_PA_SC_VIZ_QUERY_VIZ_QUERY_ID(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_VIZ_QUERY_VIZ_QUERY_ID__SHIFT) & A2XX_PA_SC_VIZ_QUERY_VIZ_QUERY_ID__MASK;
+}
+#define A2XX_PA_SC_VIZ_QUERY_KILL_PIX_POST_EARLY_Z		0x00000100
 
 #define REG_A2XX_VGT_ENHANCE					0x00002294
 
@@ -1319,6 +1540,18 @@ static inline uint32_t A2XX_PA_SC_LINE_CNTL_BRES_CNTL(uint32_t val)
 #define A2XX_PA_SC_LINE_CNTL_LAST_PIXEL				0x00000400
 
 #define REG_A2XX_PA_SC_AA_CONFIG				0x00002301
+#define A2XX_PA_SC_AA_CONFIG_MSAA_NUM_SAMPLES__MASK		0x00000007
+#define A2XX_PA_SC_AA_CONFIG_MSAA_NUM_SAMPLES__SHIFT		0
+static inline uint32_t A2XX_PA_SC_AA_CONFIG_MSAA_NUM_SAMPLES(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_AA_CONFIG_MSAA_NUM_SAMPLES__SHIFT) & A2XX_PA_SC_AA_CONFIG_MSAA_NUM_SAMPLES__MASK;
+}
+#define A2XX_PA_SC_AA_CONFIG_MAX_SAMPLE_DIST__MASK		0x0001e000
+#define A2XX_PA_SC_AA_CONFIG_MAX_SAMPLE_DIST__SHIFT		13
+static inline uint32_t A2XX_PA_SC_AA_CONFIG_MAX_SAMPLE_DIST(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_AA_CONFIG_MAX_SAMPLE_DIST__SHIFT) & A2XX_PA_SC_AA_CONFIG_MAX_SAMPLE_DIST__MASK;
+}
 
 #define REG_A2XX_PA_SU_VTX_CNTL					0x00002302
 #define A2XX_PA_SU_VTX_CNTL_PIX_CENTER__MASK			0x00000001
@@ -1407,8 +1640,20 @@ static inline uint32_t A2XX_SQ_PS_CONST_SIZE(uint32_t val)
 #define REG_A2XX_PA_SC_AA_MASK					0x00002312
 
 #define REG_A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL			0x00002316
+#define A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL_VTX_REUSE_DEPTH__MASK	0x00000007
+#define A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL_VTX_REUSE_DEPTH__SHIFT	0
+static inline uint32_t A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL_VTX_REUSE_DEPTH(uint32_t val)
+{
+	return ((val) << A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL_VTX_REUSE_DEPTH__SHIFT) & A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL_VTX_REUSE_DEPTH__MASK;
+}
 
 #define REG_A2XX_VGT_OUT_DEALLOC_CNTL				0x00002317
+#define A2XX_VGT_OUT_DEALLOC_CNTL_DEALLOC_DIST__MASK		0x00000003
+#define A2XX_VGT_OUT_DEALLOC_CNTL_DEALLOC_DIST__SHIFT		0
+static inline uint32_t A2XX_VGT_OUT_DEALLOC_CNTL_DEALLOC_DIST(uint32_t val)
+{
+	return ((val) << A2XX_VGT_OUT_DEALLOC_CNTL_DEALLOC_DIST__SHIFT) & A2XX_VGT_OUT_DEALLOC_CNTL_DEALLOC_DIST__MASK;
+}
 
 #define REG_A2XX_RB_COPY_CONTROL				0x00002318
 #define A2XX_RB_COPY_CONTROL_COPY_SAMPLE_SELECT__MASK		0x00000007
diff --git a/drivers/gpu/drm/msm/adreno/a3xx.xml.h b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
index a066c8b9eccd..663a73216926 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
@@ -8,17 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2016-04-26 17:56:44)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32907 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  12025 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  22544 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 110765 bytes, from 2016-11-26 23:01:48)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          (  90321 bytes, from 2016-11-28 16:50:05)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2015-09-24 17:30:00)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  37162 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  13324 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  31866 bytes, from 2017-06-06 18:26:14)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 111898 bytes, from 2017-06-06 18:23:59)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          ( 139480 bytes, from 2017-06-16 12:44:39)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 7fd77958a436..0e3828ed1e46 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -40,6 +40,7 @@
 extern bool hang_debug;
 
 static void a3xx_dump(struct msm_gpu *gpu);
+static bool a3xx_idle(struct msm_gpu *gpu);
 
 static bool a3xx_me_init(struct msm_gpu *gpu)
 {
@@ -65,7 +66,7 @@ static bool a3xx_me_init(struct msm_gpu *gpu)
 	OUT_RING(ring, 0x00000000);
 
 	gpu->funcs->flush(gpu);
-	return gpu->funcs->idle(gpu);
+	return a3xx_idle(gpu);
 }
 
 static int a3xx_hw_init(struct msm_gpu *gpu)
@@ -446,7 +447,6 @@ static const struct adreno_gpu_funcs funcs = {
 		.last_fence = adreno_last_fence,
 		.submit = adreno_submit,
 		.flush = adreno_flush,
-		.idle = a3xx_idle,
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/msm/adreno/a4xx.xml.h b/drivers/gpu/drm/msm/adreno/a4xx.xml.h
index 4ce21b902779..1a14f4a40b9c 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a4xx.xml.h
@@ -8,17 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2016-04-26 17:56:44)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32907 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  12025 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  22544 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 110765 bytes, from 2016-11-26 23:01:48)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          (  90321 bytes, from 2016-11-28 16:50:05)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2015-09-24 17:30:00)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  37162 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  13324 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  31866 bytes, from 2017-06-06 18:26:14)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 111898 bytes, from 2017-06-06 18:23:59)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          ( 139480 bytes, from 2017-06-16 12:44:39)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -3010,11 +3010,11 @@ static inline uint32_t A4XX_VFD_FETCH_INSTR_0_BUFSTRIDE(uint32_t val)
 static inline uint32_t REG_A4XX_VFD_FETCH_INSTR_1(uint32_t i0) { return 0x0000220b + 0x4*i0; }
 
 static inline uint32_t REG_A4XX_VFD_FETCH_INSTR_2(uint32_t i0) { return 0x0000220c + 0x4*i0; }
-#define A4XX_VFD_FETCH_INSTR_2_SIZE__MASK			0xfffffff0
-#define A4XX_VFD_FETCH_INSTR_2_SIZE__SHIFT			4
+#define A4XX_VFD_FETCH_INSTR_2_SIZE__MASK			0xffffffff
+#define A4XX_VFD_FETCH_INSTR_2_SIZE__SHIFT			0
 static inline uint32_t A4XX_VFD_FETCH_INSTR_2_SIZE(uint32_t val)
 {
-	return ((val >> 4) << A4XX_VFD_FETCH_INSTR_2_SIZE__SHIFT) & A4XX_VFD_FETCH_INSTR_2_SIZE__MASK;
+	return ((val) << A4XX_VFD_FETCH_INSTR_2_SIZE__SHIFT) & A4XX_VFD_FETCH_INSTR_2_SIZE__MASK;
 }
 
 static inline uint32_t REG_A4XX_VFD_FETCH_INSTR_3(uint32_t i0) { return 0x0000220d + 0x4*i0; }
@@ -3829,6 +3829,44 @@ static inline uint32_t A4XX_PC_HS_PARAM_SPACING(enum a4xx_tess_spacing val)
 
 #define REG_A4XX_VBIF_ROUND_ROBIN_QOS_ARB			0x00003049
 
+#define REG_A4XX_VBIF_PERF_CNT_EN0				0x000030c0
+
+#define REG_A4XX_VBIF_PERF_CNT_EN1				0x000030c1
+
+#define REG_A4XX_VBIF_PERF_CNT_EN2				0x000030c2
+
+#define REG_A4XX_VBIF_PERF_CNT_EN3				0x000030c3
+
+#define REG_A4XX_VBIF_PERF_CNT_SEL0				0x000030d0
+
+#define REG_A4XX_VBIF_PERF_CNT_SEL1				0x000030d1
+
+#define REG_A4XX_VBIF_PERF_CNT_SEL2				0x000030d2
+
+#define REG_A4XX_VBIF_PERF_CNT_SEL3				0x000030d3
+
+#define REG_A4XX_VBIF_PERF_CNT_LOW0				0x000030d8
+
+#define REG_A4XX_VBIF_PERF_CNT_LOW1				0x000030d9
+
+#define REG_A4XX_VBIF_PERF_CNT_LOW2				0x000030da
+
+#define REG_A4XX_VBIF_PERF_CNT_LOW3				0x000030db
+
+#define REG_A4XX_VBIF_PERF_CNT_HIGH0				0x000030e0
+
+#define REG_A4XX_VBIF_PERF_CNT_HIGH1				0x000030e1
+
+#define REG_A4XX_VBIF_PERF_CNT_HIGH2				0x000030e2
+
+#define REG_A4XX_VBIF_PERF_CNT_HIGH3				0x000030e3
+
+#define REG_A4XX_VBIF_PERF_PWR_CNT_EN0				0x00003100
+
+#define REG_A4XX_VBIF_PERF_PWR_CNT_EN1				0x00003101
+
+#define REG_A4XX_VBIF_PERF_PWR_CNT_EN2				0x00003102
+
 #define REG_A4XX_UNKNOWN_0CC5					0x00000cc5
 
 #define REG_A4XX_UNKNOWN_0CC6					0x00000cc6
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index dfe0eceaae3b..19abf229b08d 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -31,6 +31,7 @@
 
 extern bool hang_debug;
 static void a4xx_dump(struct msm_gpu *gpu);
+static bool a4xx_idle(struct msm_gpu *gpu);
 
 /*
  * a4xx_enable_hwcg() - Program the clock control registers
@@ -137,7 +138,7 @@ static bool a4xx_me_init(struct msm_gpu *gpu)
 	OUT_RING(ring, 0x00000000);
 
 	gpu->funcs->flush(gpu);
-	return gpu->funcs->idle(gpu);
+	return a4xx_idle(gpu);
 }
 
 static int a4xx_hw_init(struct msm_gpu *gpu)
@@ -534,7 +535,6 @@ static const struct adreno_gpu_funcs funcs = {
 		.last_fence = adreno_last_fence,
 		.submit = adreno_submit,
 		.flush = adreno_flush,
-		.idle = a4xx_idle,
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
index b6fe763ddf34..e0e6711f4f78 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
@@ -8,17 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2016-04-26 17:56:44)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32907 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  12025 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  22544 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 110765 bytes, from 2016-11-26 23:01:48)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          (  90321 bytes, from 2016-11-28 16:50:05)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2015-09-24 17:30:00)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  37162 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  13324 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  31866 bytes, from 2017-06-06 18:26:14)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 111898 bytes, from 2017-06-06 18:23:59)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          ( 139480 bytes, from 2017-06-16 12:44:39)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -45,20 +45,50 @@ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 
 enum a5xx_color_fmt {
+	RB5_A8_UNORM = 2,
 	RB5_R8_UNORM = 3,
+	RB5_R8_SNORM = 4,
+	RB5_R8_UINT = 5,
+	RB5_R8_SINT = 6,
 	RB5_R4G4B4A4_UNORM = 8,
 	RB5_R5G5B5A1_UNORM = 10,
 	RB5_R5G6B5_UNORM = 14,
+	RB5_R8G8_UNORM = 15,
+	RB5_R8G8_SNORM = 16,
+	RB5_R8G8_UINT = 17,
+	RB5_R8G8_SINT = 18,
+	RB5_R16_UNORM = 21,
+	RB5_R16_SNORM = 22,
 	RB5_R16_FLOAT = 23,
+	RB5_R16_UINT = 24,
+	RB5_R16_SINT = 25,
 	RB5_R8G8B8A8_UNORM = 48,
 	RB5_R8G8B8_UNORM = 49,
+	RB5_R8G8B8A8_SNORM = 50,
 	RB5_R8G8B8A8_UINT = 51,
+	RB5_R8G8B8A8_SINT = 52,
+	RB5_R10G10B10A2_UNORM = 55,
 	RB5_R10G10B10A2_UINT = 58,
+	RB5_R11G11B10_FLOAT = 66,
+	RB5_R16G16_UNORM = 67,
+	RB5_R16G16_SNORM = 68,
 	RB5_R16G16_FLOAT = 69,
+	RB5_R16G16_UINT = 70,
+	RB5_R16G16_SINT = 71,
 	RB5_R32_FLOAT = 74,
+	RB5_R32_UINT = 75,
+	RB5_R32_SINT = 76,
+	RB5_R16G16B16A16_UNORM = 96,
+	RB5_R16G16B16A16_SNORM = 97,
 	RB5_R16G16B16A16_FLOAT = 98,
+	RB5_R16G16B16A16_UINT = 99,
+	RB5_R16G16B16A16_SINT = 100,
 	RB5_R32G32_FLOAT = 103,
+	RB5_R32G32_UINT = 104,
+	RB5_R32G32_SINT = 105,
 	RB5_R32G32B32A32_FLOAT = 130,
+	RB5_R32G32B32A32_UINT = 131,
+	RB5_R32G32B32A32_SINT = 132,
 };
 
 enum a5xx_tile_mode {
@@ -133,25 +163,55 @@ enum a5xx_vtx_fmt {
 enum a5xx_tex_fmt {
 	TFMT5_A8_UNORM = 2,
 	TFMT5_8_UNORM = 3,
+	TFMT5_8_SNORM = 4,
+	TFMT5_8_UINT = 5,
+	TFMT5_8_SINT = 6,
 	TFMT5_4_4_4_4_UNORM = 8,
 	TFMT5_5_5_5_1_UNORM = 10,
 	TFMT5_5_6_5_UNORM = 14,
 	TFMT5_8_8_UNORM = 15,
 	TFMT5_8_8_SNORM = 16,
+	TFMT5_8_8_UINT = 17,
+	TFMT5_8_8_SINT = 18,
 	TFMT5_L8_A8_UNORM = 19,
+	TFMT5_16_UNORM = 21,
+	TFMT5_16_SNORM = 22,
 	TFMT5_16_FLOAT = 23,
+	TFMT5_16_UINT = 24,
+	TFMT5_16_SINT = 25,
 	TFMT5_8_8_8_8_UNORM = 48,
 	TFMT5_8_8_8_UNORM = 49,
-	TFMT5_8_8_8_SNORM = 50,
+	TFMT5_8_8_8_8_SNORM = 50,
+	TFMT5_8_8_8_8_UINT = 51,
+	TFMT5_8_8_8_8_SINT = 52,
 	TFMT5_9_9_9_E5_FLOAT = 53,
 	TFMT5_10_10_10_2_UNORM = 54,
+	TFMT5_10_10_10_2_UINT = 58,
 	TFMT5_11_11_10_FLOAT = 66,
+	TFMT5_16_16_UNORM = 67,
+	TFMT5_16_16_SNORM = 68,
 	TFMT5_16_16_FLOAT = 69,
+	TFMT5_16_16_UINT = 70,
+	TFMT5_16_16_SINT = 71,
 	TFMT5_32_FLOAT = 74,
+	TFMT5_32_UINT = 75,
+	TFMT5_32_SINT = 76,
+	TFMT5_16_16_16_16_UNORM = 96,
+	TFMT5_16_16_16_16_SNORM = 97,
 	TFMT5_16_16_16_16_FLOAT = 98,
+	TFMT5_16_16_16_16_UINT = 99,
+	TFMT5_16_16_16_16_SINT = 100,
 	TFMT5_32_32_FLOAT = 103,
+	TFMT5_32_32_UINT = 104,
+	TFMT5_32_32_SINT = 105,
 	TFMT5_32_32_32_32_FLOAT = 130,
+	TFMT5_32_32_32_32_UINT = 131,
+	TFMT5_32_32_32_32_SINT = 132,
 	TFMT5_X8Z24_UNORM = 160,
+	TFMT5_RGTC1_UNORM = 183,
+	TFMT5_RGTC1_SNORM = 184,
+	TFMT5_RGTC2_UNORM = 187,
+	TFMT5_RGTC2_SNORM = 188,
 };
 
 enum a5xx_tex_fetchsize {
@@ -182,6 +242,565 @@ enum a5xx_blit_buf {
 	BLIT_Z32 = 9,
 };
 
+enum a5xx_cp_perfcounter_select {
+	PERF_CP_ALWAYS_COUNT = 0,
+	PERF_CP_BUSY_GFX_CORE_IDLE = 1,
+	PERF_CP_BUSY_CYCLES = 2,
+	PERF_CP_PFP_IDLE = 3,
+	PERF_CP_PFP_BUSY_WORKING = 4,
+	PERF_CP_PFP_STALL_CYCLES_ANY = 5,
+	PERF_CP_PFP_STARVE_CYCLES_ANY = 6,
+	PERF_CP_PFP_ICACHE_MISS = 7,
+	PERF_CP_PFP_ICACHE_HIT = 8,
+	PERF_CP_PFP_MATCH_PM4_PKT_PROFILE = 9,
+	PERF_CP_ME_BUSY_WORKING = 10,
+	PERF_CP_ME_IDLE = 11,
+	PERF_CP_ME_STARVE_CYCLES_ANY = 12,
+	PERF_CP_ME_FIFO_EMPTY_PFP_IDLE = 13,
+	PERF_CP_ME_FIFO_EMPTY_PFP_BUSY = 14,
+	PERF_CP_ME_FIFO_FULL_ME_BUSY = 15,
+	PERF_CP_ME_FIFO_FULL_ME_NON_WORKING = 16,
+	PERF_CP_ME_STALL_CYCLES_ANY = 17,
+	PERF_CP_ME_ICACHE_MISS = 18,
+	PERF_CP_ME_ICACHE_HIT = 19,
+	PERF_CP_NUM_PREEMPTIONS = 20,
+	PERF_CP_PREEMPTION_REACTION_DELAY = 21,
+	PERF_CP_PREEMPTION_SWITCH_OUT_TIME = 22,
+	PERF_CP_PREEMPTION_SWITCH_IN_TIME = 23,
+	PERF_CP_DEAD_DRAWS_IN_BIN_RENDER = 24,
+	PERF_CP_PREDICATED_DRAWS_KILLED = 25,
+	PERF_CP_MODE_SWITCH = 26,
+	PERF_CP_ZPASS_DONE = 27,
+	PERF_CP_CONTEXT_DONE = 28,
+	PERF_CP_CACHE_FLUSH = 29,
+	PERF_CP_LONG_PREEMPTIONS = 30,
+};
+
+enum a5xx_rbbm_perfcounter_select {
+	PERF_RBBM_ALWAYS_COUNT = 0,
+	PERF_RBBM_ALWAYS_ON = 1,
+	PERF_RBBM_TSE_BUSY = 2,
+	PERF_RBBM_RAS_BUSY = 3,
+	PERF_RBBM_PC_DCALL_BUSY = 4,
+	PERF_RBBM_PC_VSD_BUSY = 5,
+	PERF_RBBM_STATUS_MASKED = 6,
+	PERF_RBBM_COM_BUSY = 7,
+	PERF_RBBM_DCOM_BUSY = 8,
+	PERF_RBBM_VBIF_BUSY = 9,
+	PERF_RBBM_VSC_BUSY = 10,
+	PERF_RBBM_TESS_BUSY = 11,
+	PERF_RBBM_UCHE_BUSY = 12,
+	PERF_RBBM_HLSQ_BUSY = 13,
+};
+
+enum a5xx_pc_perfcounter_select {
+	PERF_PC_BUSY_CYCLES = 0,
+	PERF_PC_WORKING_CYCLES = 1,
+	PERF_PC_STALL_CYCLES_VFD = 2,
+	PERF_PC_STALL_CYCLES_TSE = 3,
+	PERF_PC_STALL_CYCLES_VPC = 4,
+	PERF_PC_STALL_CYCLES_UCHE = 5,
+	PERF_PC_STALL_CYCLES_TESS = 6,
+	PERF_PC_STALL_CYCLES_TSE_ONLY = 7,
+	PERF_PC_STALL_CYCLES_VPC_ONLY = 8,
+	PERF_PC_PASS1_TF_STALL_CYCLES = 9,
+	PERF_PC_STARVE_CYCLES_FOR_INDEX = 10,
+	PERF_PC_STARVE_CYCLES_FOR_TESS_FACTOR = 11,
+	PERF_PC_STARVE_CYCLES_FOR_VIZ_STREAM = 12,
+	PERF_PC_STARVE_CYCLES_FOR_POSITION = 13,
+	PERF_PC_STARVE_CYCLES_DI = 14,
+	PERF_PC_VIS_STREAMS_LOADED = 15,
+	PERF_PC_INSTANCES = 16,
+	PERF_PC_VPC_PRIMITIVES = 17,
+	PERF_PC_DEAD_PRIM = 18,
+	PERF_PC_LIVE_PRIM = 19,
+	PERF_PC_VERTEX_HITS = 20,
+	PERF_PC_IA_VERTICES = 21,
+	PERF_PC_IA_PRIMITIVES = 22,
+	PERF_PC_GS_PRIMITIVES = 23,
+	PERF_PC_HS_INVOCATIONS = 24,
+	PERF_PC_DS_INVOCATIONS = 25,
+	PERF_PC_VS_INVOCATIONS = 26,
+	PERF_PC_GS_INVOCATIONS = 27,
+	PERF_PC_DS_PRIMITIVES = 28,
+	PERF_PC_VPC_POS_DATA_TRANSACTION = 29,
+	PERF_PC_3D_DRAWCALLS = 30,
+	PERF_PC_2D_DRAWCALLS = 31,
+	PERF_PC_NON_DRAWCALL_GLOBAL_EVENTS = 32,
+	PERF_TESS_BUSY_CYCLES = 33,
+	PERF_TESS_WORKING_CYCLES = 34,
+	PERF_TESS_STALL_CYCLES_PC = 35,
+	PERF_TESS_STARVE_CYCLES_PC = 36,
+};
+
+enum a5xx_vfd_perfcounter_select {
+	PERF_VFD_BUSY_CYCLES = 0,
+	PERF_VFD_STALL_CYCLES_UCHE = 1,
+	PERF_VFD_STALL_CYCLES_VPC_ALLOC = 2,
+	PERF_VFD_STALL_CYCLES_MISS_VB = 3,
+	PERF_VFD_STALL_CYCLES_MISS_Q = 4,
+	PERF_VFD_STALL_CYCLES_SP_INFO = 5,
+	PERF_VFD_STALL_CYCLES_SP_ATTR = 6,
+	PERF_VFD_STALL_CYCLES_VFDP_VB = 7,
+	PERF_VFD_STALL_CYCLES_VFDP_Q = 8,
+	PERF_VFD_DECODER_PACKER_STALL = 9,
+	PERF_VFD_STARVE_CYCLES_UCHE = 10,
+	PERF_VFD_RBUFFER_FULL = 11,
+	PERF_VFD_ATTR_INFO_FIFO_FULL = 12,
+	PERF_VFD_DECODED_ATTRIBUTE_BYTES = 13,
+	PERF_VFD_NUM_ATTRIBUTES = 14,
+	PERF_VFD_INSTRUCTIONS = 15,
+	PERF_VFD_UPPER_SHADER_FIBERS = 16,
+	PERF_VFD_LOWER_SHADER_FIBERS = 17,
+	PERF_VFD_MODE_0_FIBERS = 18,
+	PERF_VFD_MODE_1_FIBERS = 19,
+	PERF_VFD_MODE_2_FIBERS = 20,
+	PERF_VFD_MODE_3_FIBERS = 21,
+	PERF_VFD_MODE_4_FIBERS = 22,
+	PERF_VFD_TOTAL_VERTICES = 23,
+	PERF_VFD_NUM_ATTR_MISS = 24,
+	PERF_VFD_1_BURST_REQ = 25,
+	PERF_VFDP_STALL_CYCLES_VFD = 26,
+	PERF_VFDP_STALL_CYCLES_VFD_INDEX = 27,
+	PERF_VFDP_STALL_CYCLES_VFD_PROG = 28,
+	PERF_VFDP_STARVE_CYCLES_PC = 29,
+	PERF_VFDP_VS_STAGE_32_WAVES = 30,
+};
+
+enum a5xx_hlsq_perfcounter_select {
+	PERF_HLSQ_BUSY_CYCLES = 0,
+	PERF_HLSQ_STALL_CYCLES_UCHE = 1,
+	PERF_HLSQ_STALL_CYCLES_SP_STATE = 2,
+	PERF_HLSQ_STALL_CYCLES_SP_FS_STAGE = 3,
+	PERF_HLSQ_UCHE_LATENCY_CYCLES = 4,
+	PERF_HLSQ_UCHE_LATENCY_COUNT = 5,
+	PERF_HLSQ_FS_STAGE_32_WAVES = 6,
+	PERF_HLSQ_FS_STAGE_64_WAVES = 7,
+	PERF_HLSQ_QUADS = 8,
+	PERF_HLSQ_SP_STATE_COPY_TRANS_FS_STAGE = 9,
+	PERF_HLSQ_SP_STATE_COPY_TRANS_VS_STAGE = 10,
+	PERF_HLSQ_TP_STATE_COPY_TRANS_FS_STAGE = 11,
+	PERF_HLSQ_TP_STATE_COPY_TRANS_VS_STAGE = 12,
+	PERF_HLSQ_CS_INVOCATIONS = 13,
+	PERF_HLSQ_COMPUTE_DRAWCALLS = 14,
+};
+
+enum a5xx_vpc_perfcounter_select {
+	PERF_VPC_BUSY_CYCLES = 0,
+	PERF_VPC_WORKING_CYCLES = 1,
+	PERF_VPC_STALL_CYCLES_UCHE = 2,
+	PERF_VPC_STALL_CYCLES_VFD_WACK = 3,
+	PERF_VPC_STALL_CYCLES_HLSQ_PRIM_ALLOC = 4,
+	PERF_VPC_STALL_CYCLES_PC = 5,
+	PERF_VPC_STALL_CYCLES_SP_LM = 6,
+	PERF_VPC_POS_EXPORT_STALL_CYCLES = 7,
+	PERF_VPC_STARVE_CYCLES_SP = 8,
+	PERF_VPC_STARVE_CYCLES_LRZ = 9,
+	PERF_VPC_PC_PRIMITIVES = 10,
+	PERF_VPC_SP_COMPONENTS = 11,
+	PERF_VPC_SP_LM_PRIMITIVES = 12,
+	PERF_VPC_SP_LM_COMPONENTS = 13,
+	PERF_VPC_SP_LM_DWORDS = 14,
+	PERF_VPC_STREAMOUT_COMPONENTS = 15,
+	PERF_VPC_GRANT_PHASES = 16,
+};
+
+enum a5xx_tse_perfcounter_select {
+	PERF_TSE_BUSY_CYCLES = 0,
+	PERF_TSE_CLIPPING_CYCLES = 1,
+	PERF_TSE_STALL_CYCLES_RAS = 2,
+	PERF_TSE_STALL_CYCLES_LRZ_BARYPLANE = 3,
+	PERF_TSE_STALL_CYCLES_LRZ_ZPLANE = 4,
+	PERF_TSE_STARVE_CYCLES_PC = 5,
+	PERF_TSE_INPUT_PRIM = 6,
+	PERF_TSE_INPUT_NULL_PRIM = 7,
+	PERF_TSE_TRIVAL_REJ_PRIM = 8,
+	PERF_TSE_CLIPPED_PRIM = 9,
+	PERF_TSE_ZERO_AREA_PRIM = 10,
+	PERF_TSE_FACENESS_CULLED_PRIM = 11,
+	PERF_TSE_ZERO_PIXEL_PRIM = 12,
+	PERF_TSE_OUTPUT_NULL_PRIM = 13,
+	PERF_TSE_OUTPUT_VISIBLE_PRIM = 14,
+	PERF_TSE_CINVOCATION = 15,
+	PERF_TSE_CPRIMITIVES = 16,
+	PERF_TSE_2D_INPUT_PRIM = 17,
+	PERF_TSE_2D_ALIVE_CLCLES = 18,
+};
+
+enum a5xx_ras_perfcounter_select {
+	PERF_RAS_BUSY_CYCLES = 0,
+	PERF_RAS_SUPERTILE_ACTIVE_CYCLES = 1,
+	PERF_RAS_STALL_CYCLES_LRZ = 2,
+	PERF_RAS_STARVE_CYCLES_TSE = 3,
+	PERF_RAS_SUPER_TILES = 4,
+	PERF_RAS_8X4_TILES = 5,
+	PERF_RAS_MASKGEN_ACTIVE = 6,
+	PERF_RAS_FULLY_COVERED_SUPER_TILES = 7,
+	PERF_RAS_FULLY_COVERED_8X4_TILES = 8,
+	PERF_RAS_PRIM_KILLED_INVISILBE = 9,
+};
+
+enum a5xx_lrz_perfcounter_select {
+	PERF_LRZ_BUSY_CYCLES = 0,
+	PERF_LRZ_STARVE_CYCLES_RAS = 1,
+	PERF_LRZ_STALL_CYCLES_RB = 2,
+	PERF_LRZ_STALL_CYCLES_VSC = 3,
+	PERF_LRZ_STALL_CYCLES_VPC = 4,
+	PERF_LRZ_STALL_CYCLES_FLAG_PREFETCH = 5,
+	PERF_LRZ_STALL_CYCLES_UCHE = 6,
+	PERF_LRZ_LRZ_READ = 7,
+	PERF_LRZ_LRZ_WRITE = 8,
+	PERF_LRZ_READ_LATENCY = 9,
+	PERF_LRZ_MERGE_CACHE_UPDATING = 10,
+	PERF_LRZ_PRIM_KILLED_BY_MASKGEN = 11,
+	PERF_LRZ_PRIM_KILLED_BY_LRZ = 12,
+	PERF_LRZ_VISIBLE_PRIM_AFTER_LRZ = 13,
+	PERF_LRZ_FULL_8X8_TILES = 14,
+	PERF_LRZ_PARTIAL_8X8_TILES = 15,
+	PERF_LRZ_TILE_KILLED = 16,
+	PERF_LRZ_TOTAL_PIXEL = 17,
+	PERF_LRZ_VISIBLE_PIXEL_AFTER_LRZ = 18,
+};
+
+enum a5xx_uche_perfcounter_select {
+	PERF_UCHE_BUSY_CYCLES = 0,
+	PERF_UCHE_STALL_CYCLES_VBIF = 1,
+	PERF_UCHE_VBIF_LATENCY_CYCLES = 2,
+	PERF_UCHE_VBIF_LATENCY_SAMPLES = 3,
+	PERF_UCHE_VBIF_READ_BEATS_TP = 4,
+	PERF_UCHE_VBIF_READ_BEATS_VFD = 5,
+	PERF_UCHE_VBIF_READ_BEATS_HLSQ = 6,
+	PERF_UCHE_VBIF_READ_BEATS_LRZ = 7,
+	PERF_UCHE_VBIF_READ_BEATS_SP = 8,
+	PERF_UCHE_READ_REQUESTS_TP = 9,
+	PERF_UCHE_READ_REQUESTS_VFD = 10,
+	PERF_UCHE_READ_REQUESTS_HLSQ = 11,
+	PERF_UCHE_READ_REQUESTS_LRZ = 12,
+	PERF_UCHE_READ_REQUESTS_SP = 13,
+	PERF_UCHE_WRITE_REQUESTS_LRZ = 14,
+	PERF_UCHE_WRITE_REQUESTS_SP = 15,
+	PERF_UCHE_WRITE_REQUESTS_VPC = 16,
+	PERF_UCHE_WRITE_REQUESTS_VSC = 17,
+	PERF_UCHE_EVICTS = 18,
+	PERF_UCHE_BANK_REQ0 = 19,
+	PERF_UCHE_BANK_REQ1 = 20,
+	PERF_UCHE_BANK_REQ2 = 21,
+	PERF_UCHE_BANK_REQ3 = 22,
+	PERF_UCHE_BANK_REQ4 = 23,
+	PERF_UCHE_BANK_REQ5 = 24,
+	PERF_UCHE_BANK_REQ6 = 25,
+	PERF_UCHE_BANK_REQ7 = 26,
+	PERF_UCHE_VBIF_READ_BEATS_CH0 = 27,
+	PERF_UCHE_VBIF_READ_BEATS_CH1 = 28,
+	PERF_UCHE_GMEM_READ_BEATS = 29,
+	PERF_UCHE_FLAG_COUNT = 30,
+};
+
+enum a5xx_tp_perfcounter_select {
+	PERF_TP_BUSY_CYCLES = 0,
+	PERF_TP_STALL_CYCLES_UCHE = 1,
+	PERF_TP_LATENCY_CYCLES = 2,
+	PERF_TP_LATENCY_TRANS = 3,
+	PERF_TP_FLAG_CACHE_REQUEST_SAMPLES = 4,
+	PERF_TP_FLAG_CACHE_REQUEST_LATENCY = 5,
+	PERF_TP_L1_CACHELINE_REQUESTS = 6,
+	PERF_TP_L1_CACHELINE_MISSES = 7,
+	PERF_TP_SP_TP_TRANS = 8,
+	PERF_TP_TP_SP_TRANS = 9,
+	PERF_TP_OUTPUT_PIXELS = 10,
+	PERF_TP_FILTER_WORKLOAD_16BIT = 11,
+	PERF_TP_FILTER_WORKLOAD_32BIT = 12,
+	PERF_TP_QUADS_RECEIVED = 13,
+	PERF_TP_QUADS_OFFSET = 14,
+	PERF_TP_QUADS_SHADOW = 15,
+	PERF_TP_QUADS_ARRAY = 16,
+	PERF_TP_QUADS_GRADIENT = 17,
+	PERF_TP_QUADS_1D = 18,
+	PERF_TP_QUADS_2D = 19,
+	PERF_TP_QUADS_BUFFER = 20,
+	PERF_TP_QUADS_3D = 21,
+	PERF_TP_QUADS_CUBE = 22,
+	PERF_TP_STATE_CACHE_REQUESTS = 23,
+	PERF_TP_STATE_CACHE_MISSES = 24,
+	PERF_TP_DIVERGENT_QUADS_RECEIVED = 25,
+	PERF_TP_BINDLESS_STATE_CACHE_REQUESTS = 26,
+	PERF_TP_BINDLESS_STATE_CACHE_MISSES = 27,
+	PERF_TP_PRT_NON_RESIDENT_EVENTS = 28,
+	PERF_TP_OUTPUT_PIXELS_POINT = 29,
+	PERF_TP_OUTPUT_PIXELS_BILINEAR = 30,
+	PERF_TP_OUTPUT_PIXELS_MIP = 31,
+	PERF_TP_OUTPUT_PIXELS_ANISO = 32,
+	PERF_TP_OUTPUT_PIXELS_ZERO_LOD = 33,
+	PERF_TP_FLAG_CACHE_REQUESTS = 34,
+	PERF_TP_FLAG_CACHE_MISSES = 35,
+	PERF_TP_L1_5_L2_REQUESTS = 36,
+	PERF_TP_2D_OUTPUT_PIXELS = 37,
+	PERF_TP_2D_OUTPUT_PIXELS_POINT = 38,
+	PERF_TP_2D_OUTPUT_PIXELS_BILINEAR = 39,
+	PERF_TP_2D_FILTER_WORKLOAD_16BIT = 40,
+	PERF_TP_2D_FILTER_WORKLOAD_32BIT = 41,
+};
+
+enum a5xx_sp_perfcounter_select {
+	PERF_SP_BUSY_CYCLES = 0,
+	PERF_SP_ALU_WORKING_CYCLES = 1,
+	PERF_SP_EFU_WORKING_CYCLES = 2,
+	PERF_SP_STALL_CYCLES_VPC = 3,
+	PERF_SP_STALL_CYCLES_TP = 4,
+	PERF_SP_STALL_CYCLES_UCHE = 5,
+	PERF_SP_STALL_CYCLES_RB = 6,
+	PERF_SP_SCHEDULER_NON_WORKING = 7,
+	PERF_SP_WAVE_CONTEXTS = 8,
+	PERF_SP_WAVE_CONTEXT_CYCLES = 9,
+	PERF_SP_FS_STAGE_WAVE_CYCLES = 10,
+	PERF_SP_FS_STAGE_WAVE_SAMPLES = 11,
+	PERF_SP_VS_STAGE_WAVE_CYCLES = 12,
+	PERF_SP_VS_STAGE_WAVE_SAMPLES = 13,
+	PERF_SP_FS_STAGE_DURATION_CYCLES = 14,
+	PERF_SP_VS_STAGE_DURATION_CYCLES = 15,
+	PERF_SP_WAVE_CTRL_CYCLES = 16,
+	PERF_SP_WAVE_LOAD_CYCLES = 17,
+	PERF_SP_WAVE_EMIT_CYCLES = 18,
+	PERF_SP_WAVE_NOP_CYCLES = 19,
+	PERF_SP_WAVE_WAIT_CYCLES = 20,
+	PERF_SP_WAVE_FETCH_CYCLES = 21,
+	PERF_SP_WAVE_IDLE_CYCLES = 22,
+	PERF_SP_WAVE_END_CYCLES = 23,
+	PERF_SP_WAVE_LONG_SYNC_CYCLES = 24,
+	PERF_SP_WAVE_SHORT_SYNC_CYCLES = 25,
+	PERF_SP_WAVE_JOIN_CYCLES = 26,
+	PERF_SP_LM_LOAD_INSTRUCTIONS = 27,
+	PERF_SP_LM_STORE_INSTRUCTIONS = 28,
+	PERF_SP_LM_ATOMICS = 29,
+	PERF_SP_GM_LOAD_INSTRUCTIONS = 30,
+	PERF_SP_GM_STORE_INSTRUCTIONS = 31,
+	PERF_SP_GM_ATOMICS = 32,
+	PERF_SP_VS_STAGE_TEX_INSTRUCTIONS = 33,
+	PERF_SP_VS_STAGE_CFLOW_INSTRUCTIONS = 34,
+	PERF_SP_VS_STAGE_EFU_INSTRUCTIONS = 35,
+	PERF_SP_VS_STAGE_FULL_ALU_INSTRUCTIONS = 36,
+	PERF_SP_VS_STAGE_HALF_ALU_INSTRUCTIONS = 37,
+	PERF_SP_FS_STAGE_TEX_INSTRUCTIONS = 38,
+	PERF_SP_FS_STAGE_CFLOW_INSTRUCTIONS = 39,
+	PERF_SP_FS_STAGE_EFU_INSTRUCTIONS = 40,
+	PERF_SP_FS_STAGE_FULL_ALU_INSTRUCTIONS = 41,
+	PERF_SP_FS_STAGE_HALF_ALU_INSTRUCTIONS = 42,
+	PERF_SP_FS_STAGE_BARY_INSTRUCTIONS = 43,
+	PERF_SP_VS_INSTRUCTIONS = 44,
+	PERF_SP_FS_INSTRUCTIONS = 45,
+	PERF_SP_ADDR_LOCK_COUNT = 46,
+	PERF_SP_UCHE_READ_TRANS = 47,
+	PERF_SP_UCHE_WRITE_TRANS = 48,
+	PERF_SP_EXPORT_VPC_TRANS = 49,
+	PERF_SP_EXPORT_RB_TRANS = 50,
+	PERF_SP_PIXELS_KILLED = 51,
+	PERF_SP_ICL1_REQUESTS = 52,
+	PERF_SP_ICL1_MISSES = 53,
+	PERF_SP_ICL0_REQUESTS = 54,
+	PERF_SP_ICL0_MISSES = 55,
+	PERF_SP_HS_INSTRUCTIONS = 56,
+	PERF_SP_DS_INSTRUCTIONS = 57,
+	PERF_SP_GS_INSTRUCTIONS = 58,
+	PERF_SP_CS_INSTRUCTIONS = 59,
+	PERF_SP_GPR_READ = 60,
+	PERF_SP_GPR_WRITE = 61,
+	PERF_SP_LM_CH0_REQUESTS = 62,
+	PERF_SP_LM_CH1_REQUESTS = 63,
+	PERF_SP_LM_BANK_CONFLICTS = 64,
+};
+
+enum a5xx_rb_perfcounter_select {
+	PERF_RB_BUSY_CYCLES = 0,
+	PERF_RB_STALL_CYCLES_CCU = 1,
+	PERF_RB_STALL_CYCLES_HLSQ = 2,
+	PERF_RB_STALL_CYCLES_FIFO0_FULL = 3,
+	PERF_RB_STALL_CYCLES_FIFO1_FULL = 4,
+	PERF_RB_STALL_CYCLES_FIFO2_FULL = 5,
+	PERF_RB_STARVE_CYCLES_SP = 6,
+	PERF_RB_STARVE_CYCLES_LRZ_TILE = 7,
+	PERF_RB_STARVE_CYCLES_CCU = 8,
+	PERF_RB_STARVE_CYCLES_Z_PLANE = 9,
+	PERF_RB_STARVE_CYCLES_BARY_PLANE = 10,
+	PERF_RB_Z_WORKLOAD = 11,
+	PERF_RB_HLSQ_ACTIVE = 12,
+	PERF_RB_Z_READ = 13,
+	PERF_RB_Z_WRITE = 14,
+	PERF_RB_C_READ = 15,
+	PERF_RB_C_WRITE = 16,
+	PERF_RB_TOTAL_PASS = 17,
+	PERF_RB_Z_PASS = 18,
+	PERF_RB_Z_FAIL = 19,
+	PERF_RB_S_FAIL = 20,
+	PERF_RB_BLENDED_FXP_COMPONENTS = 21,
+	PERF_RB_BLENDED_FP16_COMPONENTS = 22,
+	RB_RESERVED = 23,
+	PERF_RB_2D_ALIVE_CYCLES = 24,
+	PERF_RB_2D_STALL_CYCLES_A2D = 25,
+	PERF_RB_2D_STARVE_CYCLES_SRC = 26,
+	PERF_RB_2D_STARVE_CYCLES_SP = 27,
+	PERF_RB_2D_STARVE_CYCLES_DST = 28,
+	PERF_RB_2D_VALID_PIXELS = 29,
+};
+
+enum a5xx_rb_samples_perfcounter_select {
+	TOTAL_SAMPLES = 0,
+	ZPASS_SAMPLES = 1,
+	ZFAIL_SAMPLES = 2,
+	SFAIL_SAMPLES = 3,
+};
+
+enum a5xx_vsc_perfcounter_select {
+	PERF_VSC_BUSY_CYCLES = 0,
+	PERF_VSC_WORKING_CYCLES = 1,
+	PERF_VSC_STALL_CYCLES_UCHE = 2,
+	PERF_VSC_EOT_NUM = 3,
+};
+
+enum a5xx_ccu_perfcounter_select {
+	PERF_CCU_BUSY_CYCLES = 0,
+	PERF_CCU_STALL_CYCLES_RB_DEPTH_RETURN = 1,
+	PERF_CCU_STALL_CYCLES_RB_COLOR_RETURN = 2,
+	PERF_CCU_STARVE_CYCLES_FLAG_RETURN = 3,
+	PERF_CCU_DEPTH_BLOCKS = 4,
+	PERF_CCU_COLOR_BLOCKS = 5,
+	PERF_CCU_DEPTH_BLOCK_HIT = 6,
+	PERF_CCU_COLOR_BLOCK_HIT = 7,
+	PERF_CCU_PARTIAL_BLOCK_READ = 8,
+	PERF_CCU_GMEM_READ = 9,
+	PERF_CCU_GMEM_WRITE = 10,
+	PERF_CCU_DEPTH_READ_FLAG0_COUNT = 11,
+	PERF_CCU_DEPTH_READ_FLAG1_COUNT = 12,
+	PERF_CCU_DEPTH_READ_FLAG2_COUNT = 13,
+	PERF_CCU_DEPTH_READ_FLAG3_COUNT = 14,
+	PERF_CCU_DEPTH_READ_FLAG4_COUNT = 15,
+	PERF_CCU_COLOR_READ_FLAG0_COUNT = 16,
+	PERF_CCU_COLOR_READ_FLAG1_COUNT = 17,
+	PERF_CCU_COLOR_READ_FLAG2_COUNT = 18,
+	PERF_CCU_COLOR_READ_FLAG3_COUNT = 19,
+	PERF_CCU_COLOR_READ_FLAG4_COUNT = 20,
+	PERF_CCU_2D_BUSY_CYCLES = 21,
+	PERF_CCU_2D_RD_REQ = 22,
+	PERF_CCU_2D_WR_REQ = 23,
+	PERF_CCU_2D_REORDER_STARVE_CYCLES = 24,
+	PERF_CCU_2D_PIXELS = 25,
+};
+
+enum a5xx_cmp_perfcounter_select {
+	PERF_CMPDECMP_STALL_CYCLES_VBIF = 0,
+	PERF_CMPDECMP_VBIF_LATENCY_CYCLES = 1,
+	PERF_CMPDECMP_VBIF_LATENCY_SAMPLES = 2,
+	PERF_CMPDECMP_VBIF_READ_DATA_CCU = 3,
+	PERF_CMPDECMP_VBIF_WRITE_DATA_CCU = 4,
+	PERF_CMPDECMP_VBIF_READ_REQUEST = 5,
+	PERF_CMPDECMP_VBIF_WRITE_REQUEST = 6,
+	PERF_CMPDECMP_VBIF_READ_DATA = 7,
+	PERF_CMPDECMP_VBIF_WRITE_DATA = 8,
+	PERF_CMPDECMP_FLAG_FETCH_CYCLES = 9,
+	PERF_CMPDECMP_FLAG_FETCH_SAMPLES = 10,
+	PERF_CMPDECMP_DEPTH_WRITE_FLAG1_COUNT = 11,
+	PERF_CMPDECMP_DEPTH_WRITE_FLAG2_COUNT = 12,
+	PERF_CMPDECMP_DEPTH_WRITE_FLAG3_COUNT = 13,
+	PERF_CMPDECMP_DEPTH_WRITE_FLAG4_COUNT = 14,
+	PERF_CMPDECMP_COLOR_WRITE_FLAG1_COUNT = 15,
+	PERF_CMPDECMP_COLOR_WRITE_FLAG2_COUNT = 16,
+	PERF_CMPDECMP_COLOR_WRITE_FLAG3_COUNT = 17,
+	PERF_CMPDECMP_COLOR_WRITE_FLAG4_COUNT = 18,
+	PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_REQ = 19,
+	PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_WR = 20,
+	PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_RETURN = 21,
+	PERF_CMPDECMP_2D_RD_DATA = 22,
+	PERF_CMPDECMP_2D_WR_DATA = 23,
+};
+
+enum a5xx_vbif_perfcounter_select {
+	AXI_READ_REQUESTS_ID_0 = 0,
+	AXI_READ_REQUESTS_ID_1 = 1,
+	AXI_READ_REQUESTS_ID_2 = 2,
+	AXI_READ_REQUESTS_ID_3 = 3,
+	AXI_READ_REQUESTS_ID_4 = 4,
+	AXI_READ_REQUESTS_ID_5 = 5,
+	AXI_READ_REQUESTS_ID_6 = 6,
+	AXI_READ_REQUESTS_ID_7 = 7,
+	AXI_READ_REQUESTS_ID_8 = 8,
+	AXI_READ_REQUESTS_ID_9 = 9,
+	AXI_READ_REQUESTS_ID_10 = 10,
+	AXI_READ_REQUESTS_ID_11 = 11,
+	AXI_READ_REQUESTS_ID_12 = 12,
+	AXI_READ_REQUESTS_ID_13 = 13,
+	AXI_READ_REQUESTS_ID_14 = 14,
+	AXI_READ_REQUESTS_ID_15 = 15,
+	AXI0_READ_REQUESTS_TOTAL = 16,
+	AXI1_READ_REQUESTS_TOTAL = 17,
+	AXI2_READ_REQUESTS_TOTAL = 18,
+	AXI3_READ_REQUESTS_TOTAL = 19,
+	AXI_READ_REQUESTS_TOTAL = 20,
+	AXI_WRITE_REQUESTS_ID_0 = 21,
+	AXI_WRITE_REQUESTS_ID_1 = 22,
+	AXI_WRITE_REQUESTS_ID_2 = 23,
+	AXI_WRITE_REQUESTS_ID_3 = 24,
+	AXI_WRITE_REQUESTS_ID_4 = 25,
+	AXI_WRITE_REQUESTS_ID_5 = 26,
+	AXI_WRITE_REQUESTS_ID_6 = 27,
+	AXI_WRITE_REQUESTS_ID_7 = 28,
+	AXI_WRITE_REQUESTS_ID_8 = 29,
+	AXI_WRITE_REQUESTS_ID_9 = 30,
+	AXI_WRITE_REQUESTS_ID_10 = 31,
+	AXI_WRITE_REQUESTS_ID_11 = 32,
+	AXI_WRITE_REQUESTS_ID_12 = 33,
+	AXI_WRITE_REQUESTS_ID_13 = 34,
+	AXI_WRITE_REQUESTS_ID_14 = 35,
+	AXI_WRITE_REQUESTS_ID_15 = 36,
+	AXI0_WRITE_REQUESTS_TOTAL = 37,
+	AXI1_WRITE_REQUESTS_TOTAL = 38,
+	AXI2_WRITE_REQUESTS_TOTAL = 39,
+	AXI3_WRITE_REQUESTS_TOTAL = 40,
+	AXI_WRITE_REQUESTS_TOTAL = 41,
+	AXI_TOTAL_REQUESTS = 42,
+	AXI_READ_DATA_BEATS_ID_0 = 43,
+	AXI_READ_DATA_BEATS_ID_1 = 44,
+	AXI_READ_DATA_BEATS_ID_2 = 45,
+	AXI_READ_DATA_BEATS_ID_3 = 46,
+	AXI_READ_DATA_BEATS_ID_4 = 47,
+	AXI_READ_DATA_BEATS_ID_5 = 48,
+	AXI_READ_DATA_BEATS_ID_6 = 49,
+	AXI_READ_DATA_BEATS_ID_7 = 50,
+	AXI_READ_DATA_BEATS_ID_8 = 51,
+	AXI_READ_DATA_BEATS_ID_9 = 52,
+	AXI_READ_DATA_BEATS_ID_10 = 53,
+	AXI_READ_DATA_BEATS_ID_11 = 54,
+	AXI_READ_DATA_BEATS_ID_12 = 55,
+	AXI_READ_DATA_BEATS_ID_13 = 56,
+	AXI_READ_DATA_BEATS_ID_14 = 57,
+	AXI_READ_DATA_BEATS_ID_15 = 58,
+	AXI0_READ_DATA_BEATS_TOTAL = 59,
+	AXI1_READ_DATA_BEATS_TOTAL = 60,
+	AXI2_READ_DATA_BEATS_TOTAL = 61,
+	AXI3_READ_DATA_BEATS_TOTAL = 62,
+	AXI_READ_DATA_BEATS_TOTAL = 63,
+	AXI_WRITE_DATA_BEATS_ID_0 = 64,
+	AXI_WRITE_DATA_BEATS_ID_1 = 65,
+	AXI_WRITE_DATA_BEATS_ID_2 = 66,
+	AXI_WRITE_DATA_BEATS_ID_3 = 67,
+	AXI_WRITE_DATA_BEATS_ID_4 = 68,
+	AXI_WRITE_DATA_BEATS_ID_5 = 69,
+	AXI_WRITE_DATA_BEATS_ID_6 = 70,
+	AXI_WRITE_DATA_BEATS_ID_7 = 71,
+	AXI_WRITE_DATA_BEATS_ID_8 = 72,
+	AXI_WRITE_DATA_BEATS_ID_9 = 73,
+	AXI_WRITE_DATA_BEATS_ID_10 = 74,
+	AXI_WRITE_DATA_BEATS_ID_11 = 75,
+	AXI_WRITE_DATA_BEATS_ID_12 = 76,
+	AXI_WRITE_DATA_BEATS_ID_13 = 77,
+	AXI_WRITE_DATA_BEATS_ID_14 = 78,
+	AXI_WRITE_DATA_BEATS_ID_15 = 79,
+	AXI0_WRITE_DATA_BEATS_TOTAL = 80,
+	AXI1_WRITE_DATA_BEATS_TOTAL = 81,
+	AXI2_WRITE_DATA_BEATS_TOTAL = 82,
+	AXI3_WRITE_DATA_BEATS_TOTAL = 83,
+	AXI_WRITE_DATA_BEATS_TOTAL = 84,
+	AXI_DATA_BEATS_TOTAL = 85,
+};
+
 enum a5xx_tex_filter {
 	A5XX_TEX_NEAREST = 0,
 	A5XX_TEX_LINEAR = 1,
@@ -1289,25 +1908,83 @@ static inline uint32_t A5XX_CP_PROTECT_REG_MASK_LEN(uint32_t val)
 
 #define REG_A5XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL			0x0000f810
 
-#define REG_A5XX_VSC_PIPE_DATA_LENGTH_0				0x00000c00
+#define REG_A5XX_VSC_BIN_SIZE					0x00000bc2
+#define A5XX_VSC_BIN_SIZE_WIDTH__MASK				0x000000ff
+#define A5XX_VSC_BIN_SIZE_WIDTH__SHIFT				0
+static inline uint32_t A5XX_VSC_BIN_SIZE_WIDTH(uint32_t val)
+{
+	return ((val >> 5) << A5XX_VSC_BIN_SIZE_WIDTH__SHIFT) & A5XX_VSC_BIN_SIZE_WIDTH__MASK;
+}
+#define A5XX_VSC_BIN_SIZE_HEIGHT__MASK				0x0001fe00
+#define A5XX_VSC_BIN_SIZE_HEIGHT__SHIFT				9
+static inline uint32_t A5XX_VSC_BIN_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val >> 5) << A5XX_VSC_BIN_SIZE_HEIGHT__SHIFT) & A5XX_VSC_BIN_SIZE_HEIGHT__MASK;
+}
+
+#define REG_A5XX_VSC_SIZE_ADDRESS_LO				0x00000bc3
+
+#define REG_A5XX_VSC_SIZE_ADDRESS_HI				0x00000bc4
+
+#define REG_A5XX_UNKNOWN_0BC5					0x00000bc5
+
+#define REG_A5XX_UNKNOWN_0BC6					0x00000bc6
+
+static inline uint32_t REG_A5XX_VSC_PIPE_CONFIG(uint32_t i0) { return 0x00000bd0 + 0x1*i0; }
+
+static inline uint32_t REG_A5XX_VSC_PIPE_CONFIG_REG(uint32_t i0) { return 0x00000bd0 + 0x1*i0; }
+#define A5XX_VSC_PIPE_CONFIG_REG_X__MASK			0x000003ff
+#define A5XX_VSC_PIPE_CONFIG_REG_X__SHIFT			0
+static inline uint32_t A5XX_VSC_PIPE_CONFIG_REG_X(uint32_t val)
+{
+	return ((val) << A5XX_VSC_PIPE_CONFIG_REG_X__SHIFT) & A5XX_VSC_PIPE_CONFIG_REG_X__MASK;
+}
+#define A5XX_VSC_PIPE_CONFIG_REG_Y__MASK			0x000ffc00
+#define A5XX_VSC_PIPE_CONFIG_REG_Y__SHIFT			10
+static inline uint32_t A5XX_VSC_PIPE_CONFIG_REG_Y(uint32_t val)
+{
+	return ((val) << A5XX_VSC_PIPE_CONFIG_REG_Y__SHIFT) & A5XX_VSC_PIPE_CONFIG_REG_Y__MASK;
+}
+#define A5XX_VSC_PIPE_CONFIG_REG_W__MASK			0x00f00000
+#define A5XX_VSC_PIPE_CONFIG_REG_W__SHIFT			20
+static inline uint32_t A5XX_VSC_PIPE_CONFIG_REG_W(uint32_t val)
+{
+	return ((val) << A5XX_VSC_PIPE_CONFIG_REG_W__SHIFT) & A5XX_VSC_PIPE_CONFIG_REG_W__MASK;
+}
+#define A5XX_VSC_PIPE_CONFIG_REG_H__MASK			0x0f000000
+#define A5XX_VSC_PIPE_CONFIG_REG_H__SHIFT			24
+static inline uint32_t A5XX_VSC_PIPE_CONFIG_REG_H(uint32_t val)
+{
+	return ((val) << A5XX_VSC_PIPE_CONFIG_REG_H__SHIFT) & A5XX_VSC_PIPE_CONFIG_REG_H__MASK;
+}
+
+static inline uint32_t REG_A5XX_VSC_PIPE_DATA_ADDRESS(uint32_t i0) { return 0x00000be0 + 0x2*i0; }
+
+static inline uint32_t REG_A5XX_VSC_PIPE_DATA_ADDRESS_LO(uint32_t i0) { return 0x00000be0 + 0x2*i0; }
+
+static inline uint32_t REG_A5XX_VSC_PIPE_DATA_ADDRESS_HI(uint32_t i0) { return 0x00000be1 + 0x2*i0; }
+
+static inline uint32_t REG_A5XX_VSC_PIPE_DATA_LENGTH(uint32_t i0) { return 0x00000c00 + 0x1*i0; }
+
+static inline uint32_t REG_A5XX_VSC_PIPE_DATA_LENGTH_REG(uint32_t i0) { return 0x00000c00 + 0x1*i0; }
 
 #define REG_A5XX_VSC_PERFCTR_VSC_SEL_0				0x00000c60
 
 #define REG_A5XX_VSC_PERFCTR_VSC_SEL_1				0x00000c61
 
-#define REG_A5XX_VSC_BIN_SIZE					0x00000cdd
-#define A5XX_VSC_BIN_SIZE_WINDOW_OFFSET_DISABLE			0x80000000
-#define A5XX_VSC_BIN_SIZE_X__MASK				0x00007fff
-#define A5XX_VSC_BIN_SIZE_X__SHIFT				0
-static inline uint32_t A5XX_VSC_BIN_SIZE_X(uint32_t val)
+#define REG_A5XX_VSC_RESOLVE_CNTL				0x00000cdd
+#define A5XX_VSC_RESOLVE_CNTL_WINDOW_OFFSET_DISABLE		0x80000000
+#define A5XX_VSC_RESOLVE_CNTL_X__MASK				0x00007fff
+#define A5XX_VSC_RESOLVE_CNTL_X__SHIFT				0
+static inline uint32_t A5XX_VSC_RESOLVE_CNTL_X(uint32_t val)
 {
-	return ((val) << A5XX_VSC_BIN_SIZE_X__SHIFT) & A5XX_VSC_BIN_SIZE_X__MASK;
+	return ((val) << A5XX_VSC_RESOLVE_CNTL_X__SHIFT) & A5XX_VSC_RESOLVE_CNTL_X__MASK;
 }
-#define A5XX_VSC_BIN_SIZE_Y__MASK				0x7fff0000
-#define A5XX_VSC_BIN_SIZE_Y__SHIFT				16
-static inline uint32_t A5XX_VSC_BIN_SIZE_Y(uint32_t val)
+#define A5XX_VSC_RESOLVE_CNTL_Y__MASK				0x7fff0000
+#define A5XX_VSC_RESOLVE_CNTL_Y__SHIFT				16
+static inline uint32_t A5XX_VSC_RESOLVE_CNTL_Y(uint32_t val)
 {
-	return ((val) << A5XX_VSC_BIN_SIZE_Y__SHIFT) & A5XX_VSC_BIN_SIZE_Y__MASK;
+	return ((val) << A5XX_VSC_RESOLVE_CNTL_Y__SHIFT) & A5XX_VSC_RESOLVE_CNTL_Y__MASK;
 }
 
 #define REG_A5XX_GRAS_ADDR_MODE_CNTL				0x00000c81
@@ -1470,6 +2147,7 @@ static inline uint32_t A5XX_VSC_BIN_SIZE_Y(uint32_t val)
 #define REG_A5XX_VPC_ADDR_MODE_CNTL				0x00000e61
 
 #define REG_A5XX_VPC_MODE_CNTL					0x00000e62
+#define A5XX_VPC_MODE_CNTL_BINNING_PASS				0x00000001
 
 #define REG_A5XX_VPC_PERFCTR_VPC_SEL_0				0x00000e64
 
@@ -1641,6 +2319,14 @@ static inline uint32_t A5XX_VSC_BIN_SIZE_Y(uint32_t val)
 
 #define REG_A5XX_VBIF_TEST_BUS_OUT				0x0000308c
 
+#define REG_A5XX_VBIF_PERF_CNT_EN0				0x000030c0
+
+#define REG_A5XX_VBIF_PERF_CNT_EN1				0x000030c1
+
+#define REG_A5XX_VBIF_PERF_CNT_EN2				0x000030c2
+
+#define REG_A5XX_VBIF_PERF_CNT_EN3				0x000030c3
+
 #define REG_A5XX_VBIF_PERF_CNT_SEL0				0x000030d0
 
 #define REG_A5XX_VBIF_PERF_CNT_SEL1				0x000030d1
@@ -1911,6 +2597,11 @@ static inline uint32_t A5XX_VSC_BIN_SIZE_Y(uint32_t val)
 
 #define REG_A5XX_GRAS_CNTL					0x0000e005
 #define A5XX_GRAS_CNTL_VARYING					0x00000001
+#define A5XX_GRAS_CNTL_UNK3					0x00000008
+#define A5XX_GRAS_CNTL_XCOORD					0x00000040
+#define A5XX_GRAS_CNTL_YCOORD					0x00000080
+#define A5XX_GRAS_CNTL_ZCOORD					0x00000100
+#define A5XX_GRAS_CNTL_WCOORD					0x00000200
 
 #define REG_A5XX_GRAS_CL_GUARDBAND_CLIP_ADJ			0x0000e006
 #define A5XX_GRAS_CL_GUARDBAND_CLIP_ADJ_HORZ__MASK		0x000003ff
@@ -1975,6 +2666,8 @@ static inline uint32_t A5XX_GRAS_CL_VPORT_ZSCALE_0(float val)
 }
 
 #define REG_A5XX_GRAS_SU_CNTL					0x0000e090
+#define A5XX_GRAS_SU_CNTL_CULL_FRONT				0x00000001
+#define A5XX_GRAS_SU_CNTL_CULL_BACK				0x00000002
 #define A5XX_GRAS_SU_CNTL_FRONT_CW				0x00000004
 #define A5XX_GRAS_SU_CNTL_LINEHALFWIDTH__MASK			0x000007f8
 #define A5XX_GRAS_SU_CNTL_LINEHALFWIDTH__SHIFT			3
@@ -2010,7 +2703,8 @@ static inline uint32_t A5XX_GRAS_SU_POINT_SIZE(float val)
 #define REG_A5XX_UNKNOWN_E093					0x0000e093
 
 #define REG_A5XX_GRAS_SU_DEPTH_PLANE_CNTL			0x0000e094
-#define A5XX_GRAS_SU_DEPTH_PLANE_CNTL_ALPHA_TEST_ENABLE		0x00000001
+#define A5XX_GRAS_SU_DEPTH_PLANE_CNTL_FRAG_WRITES_Z		0x00000001
+#define A5XX_GRAS_SU_DEPTH_PLANE_CNTL_UNK1			0x00000002
 
 #define REG_A5XX_GRAS_SU_POLY_OFFSET_SCALE			0x0000e095
 #define A5XX_GRAS_SU_POLY_OFFSET_SCALE__MASK			0xffffffff
@@ -2047,6 +2741,7 @@ static inline uint32_t A5XX_GRAS_SU_DEPTH_BUFFER_INFO_DEPTH_FORMAT(enum a5xx_dep
 #define REG_A5XX_GRAS_SU_CONSERVATIVE_RAS_CNTL			0x0000e099
 
 #define REG_A5XX_GRAS_SC_CNTL					0x0000e0a0
+#define A5XX_GRAS_SC_CNTL_BINNING_PASS				0x00000001
 #define A5XX_GRAS_SC_CNTL_SAMPLES_PASSED			0x00008000
 
 #define REG_A5XX_GRAS_SC_BIN_CNTL				0x0000e0a1
@@ -2161,12 +2856,21 @@ static inline uint32_t A5XX_GRAS_SC_WINDOW_SCISSOR_BR_Y(uint32_t val)
 }
 
 #define REG_A5XX_GRAS_LRZ_CNTL					0x0000e100
+#define A5XX_GRAS_LRZ_CNTL_ENABLE				0x00000001
+#define A5XX_GRAS_LRZ_CNTL_LRZ_WRITE				0x00000002
+#define A5XX_GRAS_LRZ_CNTL_GREATER				0x00000004
 
 #define REG_A5XX_GRAS_LRZ_BUFFER_BASE_LO			0x0000e101
 
 #define REG_A5XX_GRAS_LRZ_BUFFER_BASE_HI			0x0000e102
 
 #define REG_A5XX_GRAS_LRZ_BUFFER_PITCH				0x0000e103
+#define A5XX_GRAS_LRZ_BUFFER_PITCH__MASK			0xffffffff
+#define A5XX_GRAS_LRZ_BUFFER_PITCH__SHIFT			0
+static inline uint32_t A5XX_GRAS_LRZ_BUFFER_PITCH(uint32_t val)
+{
+	return ((val >> 5) << A5XX_GRAS_LRZ_BUFFER_PITCH__SHIFT) & A5XX_GRAS_LRZ_BUFFER_PITCH__MASK;
+}
 
 #define REG_A5XX_GRAS_LRZ_FAST_CLEAR_BUFFER_BASE_LO		0x0000e104
 
@@ -2188,7 +2892,9 @@ static inline uint32_t A5XX_RB_CNTL_HEIGHT(uint32_t val)
 #define A5XX_RB_CNTL_BYPASS					0x00020000
 
 #define REG_A5XX_RB_RENDER_CNTL					0x0000e141
+#define A5XX_RB_RENDER_CNTL_BINNING_PASS			0x00000001
 #define A5XX_RB_RENDER_CNTL_SAMPLES_PASSED			0x00000040
+#define A5XX_RB_RENDER_CNTL_DISABLE_COLOR_PIPE			0x00000080
 #define A5XX_RB_RENDER_CNTL_FLAG_DEPTH				0x00004000
 #define A5XX_RB_RENDER_CNTL_FLAG_DEPTH2				0x00008000
 #define A5XX_RB_RENDER_CNTL_FLAG_MRTS__MASK			0x00ff0000
@@ -2223,6 +2929,7 @@ static inline uint32_t A5XX_RB_DEST_MSAA_CNTL_SAMPLES(enum a3xx_msaa_samples val
 
 #define REG_A5XX_RB_RENDER_CONTROL0				0x0000e144
 #define A5XX_RB_RENDER_CONTROL0_VARYING				0x00000001
+#define A5XX_RB_RENDER_CONTROL0_UNK3				0x00000008
 #define A5XX_RB_RENDER_CONTROL0_XCOORD				0x00000040
 #define A5XX_RB_RENDER_CONTROL0_YCOORD				0x00000080
 #define A5XX_RB_RENDER_CONTROL0_ZCOORD				0x00000100
@@ -2525,6 +3232,7 @@ static inline uint32_t A5XX_RB_BLEND_CNTL_SAMPLE_MASK(uint32_t val)
 
 #define REG_A5XX_RB_DEPTH_PLANE_CNTL				0x0000e1b0
 #define A5XX_RB_DEPTH_PLANE_CNTL_FRAG_WRITES_Z			0x00000001
+#define A5XX_RB_DEPTH_PLANE_CNTL_UNK1				0x00000002
 
 #define REG_A5XX_RB_DEPTH_CNTL					0x0000e1b1
 #define A5XX_RB_DEPTH_CNTL_Z_ENABLE				0x00000001
@@ -2554,7 +3262,7 @@ static inline uint32_t A5XX_RB_DEPTH_BUFFER_INFO_DEPTH_FORMAT(enum a5xx_depth_fo
 #define A5XX_RB_DEPTH_BUFFER_PITCH__SHIFT			0
 static inline uint32_t A5XX_RB_DEPTH_BUFFER_PITCH(uint32_t val)
 {
-	return ((val >> 5) << A5XX_RB_DEPTH_BUFFER_PITCH__SHIFT) & A5XX_RB_DEPTH_BUFFER_PITCH__MASK;
+	return ((val >> 6) << A5XX_RB_DEPTH_BUFFER_PITCH__SHIFT) & A5XX_RB_DEPTH_BUFFER_PITCH__MASK;
 }
 
 #define REG_A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH			0x0000e1b6
@@ -2562,7 +3270,7 @@ static inline uint32_t A5XX_RB_DEPTH_BUFFER_PITCH(uint32_t val)
 #define A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH__SHIFT			0
 static inline uint32_t A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH(uint32_t val)
 {
-	return ((val >> 5) << A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH__SHIFT) & A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH__MASK;
+	return ((val >> 6) << A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH__SHIFT) & A5XX_RB_DEPTH_BUFFER_ARRAY_PITCH__MASK;
 }
 
 #define REG_A5XX_RB_STENCIL_CONTROL				0x0000e1c0
@@ -2678,8 +3386,11 @@ static inline uint32_t A5XX_RB_WINDOW_OFFSET_Y(uint32_t val)
 	return ((val) << A5XX_RB_WINDOW_OFFSET_Y__SHIFT) & A5XX_RB_WINDOW_OFFSET_Y__MASK;
 }
 
+#define REG_A5XX_RB_SAMPLE_COUNT_CONTROL			0x0000e1d1
+#define A5XX_RB_SAMPLE_COUNT_CONTROL_COPY			0x00000002
+
 #define REG_A5XX_RB_BLIT_CNTL					0x0000e210
-#define A5XX_RB_BLIT_CNTL_BUF__MASK				0x0000003f
+#define A5XX_RB_BLIT_CNTL_BUF__MASK				0x0000000f
 #define A5XX_RB_BLIT_CNTL_BUF__SHIFT				0
 static inline uint32_t A5XX_RB_BLIT_CNTL_BUF(enum a5xx_blit_buf val)
 {
@@ -2803,6 +3514,10 @@ static inline uint32_t A5XX_RB_BLIT_FLAG_DST_ARRAY_PITCH(uint32_t val)
 	return ((val >> 6) << A5XX_RB_BLIT_FLAG_DST_ARRAY_PITCH__SHIFT) & A5XX_RB_BLIT_FLAG_DST_ARRAY_PITCH__MASK;
 }
 
+#define REG_A5XX_RB_SAMPLE_COUNT_ADDR_LO			0x0000e267
+
+#define REG_A5XX_RB_SAMPLE_COUNT_ADDR_HI			0x0000e268
+
 #define REG_A5XX_VPC_CNTL_0					0x0000e280
 #define A5XX_VPC_CNTL_0_STRIDE_IN_VPC__MASK			0x0000007f
 #define A5XX_VPC_CNTL_0_STRIDE_IN_VPC__SHIFT			0
@@ -2839,32 +3554,71 @@ static inline uint32_t A5XX_VPC_PACK_NUMNONPOSVAR(uint32_t val)
 {
 	return ((val) << A5XX_VPC_PACK_NUMNONPOSVAR__SHIFT) & A5XX_VPC_PACK_NUMNONPOSVAR__MASK;
 }
+#define A5XX_VPC_PACK_PSIZELOC__MASK				0x0000ff00
+#define A5XX_VPC_PACK_PSIZELOC__SHIFT				8
+static inline uint32_t A5XX_VPC_PACK_PSIZELOC(uint32_t val)
+{
+	return ((val) << A5XX_VPC_PACK_PSIZELOC__SHIFT) & A5XX_VPC_PACK_PSIZELOC__MASK;
+}
 
 #define REG_A5XX_VPC_FS_PRIMITIVEID_CNTL			0x0000e2a0
 
-#define REG_A5XX_UNKNOWN_E2A1					0x0000e2a1
+#define REG_A5XX_VPC_SO_BUF_CNTL				0x0000e2a1
+#define A5XX_VPC_SO_BUF_CNTL_BUF0				0x00000001
+#define A5XX_VPC_SO_BUF_CNTL_BUF1				0x00000008
+#define A5XX_VPC_SO_BUF_CNTL_BUF2				0x00000040
+#define A5XX_VPC_SO_BUF_CNTL_BUF3				0x00000200
+#define A5XX_VPC_SO_BUF_CNTL_ENABLE				0x00008000
 
 #define REG_A5XX_VPC_SO_OVERRIDE				0x0000e2a2
+#define A5XX_VPC_SO_OVERRIDE_SO_DISABLE				0x00000001
 
-#define REG_A5XX_VPC_SO_BUFFER_BASE_LO_0			0x0000e2a7
+#define REG_A5XX_VPC_SO_CNTL					0x0000e2a3
+#define A5XX_VPC_SO_CNTL_ENABLE					0x00010000
 
-#define REG_A5XX_VPC_SO_BUFFER_BASE_HI_0			0x0000e2a8
+#define REG_A5XX_VPC_SO_PROG					0x0000e2a4
+#define A5XX_VPC_SO_PROG_A_BUF__MASK				0x00000003
+#define A5XX_VPC_SO_PROG_A_BUF__SHIFT				0
+static inline uint32_t A5XX_VPC_SO_PROG_A_BUF(uint32_t val)
+{
+	return ((val) << A5XX_VPC_SO_PROG_A_BUF__SHIFT) & A5XX_VPC_SO_PROG_A_BUF__MASK;
+}
+#define A5XX_VPC_SO_PROG_A_OFF__MASK				0x000007fc
+#define A5XX_VPC_SO_PROG_A_OFF__SHIFT				2
+static inline uint32_t A5XX_VPC_SO_PROG_A_OFF(uint32_t val)
+{
+	return ((val >> 2) << A5XX_VPC_SO_PROG_A_OFF__SHIFT) & A5XX_VPC_SO_PROG_A_OFF__MASK;
+}
+#define A5XX_VPC_SO_PROG_A_EN					0x00000800
+#define A5XX_VPC_SO_PROG_B_BUF__MASK				0x00003000
+#define A5XX_VPC_SO_PROG_B_BUF__SHIFT				12
+static inline uint32_t A5XX_VPC_SO_PROG_B_BUF(uint32_t val)
+{
+	return ((val) << A5XX_VPC_SO_PROG_B_BUF__SHIFT) & A5XX_VPC_SO_PROG_B_BUF__MASK;
+}
+#define A5XX_VPC_SO_PROG_B_OFF__MASK				0x007fc000
+#define A5XX_VPC_SO_PROG_B_OFF__SHIFT				14
+static inline uint32_t A5XX_VPC_SO_PROG_B_OFF(uint32_t val)
+{
+	return ((val >> 2) << A5XX_VPC_SO_PROG_B_OFF__SHIFT) & A5XX_VPC_SO_PROG_B_OFF__MASK;
+}
+#define A5XX_VPC_SO_PROG_B_EN					0x00800000
 
-#define REG_A5XX_VPC_SO_BUFFER_SIZE_0				0x0000e2a9
+static inline uint32_t REG_A5XX_VPC_SO(uint32_t i0) { return 0x0000e2a7 + 0x7*i0; }
 
-#define REG_A5XX_UNKNOWN_E2AB					0x0000e2ab
+static inline uint32_t REG_A5XX_VPC_SO_BUFFER_BASE_LO(uint32_t i0) { return 0x0000e2a7 + 0x7*i0; }
 
-#define REG_A5XX_VPC_SO_FLUSH_BASE_LO_0				0x0000e2ac
+static inline uint32_t REG_A5XX_VPC_SO_BUFFER_BASE_HI(uint32_t i0) { return 0x0000e2a8 + 0x7*i0; }
 
-#define REG_A5XX_VPC_SO_FLUSH_BASE_HI_0				0x0000e2ad
+static inline uint32_t REG_A5XX_VPC_SO_BUFFER_SIZE(uint32_t i0) { return 0x0000e2a9 + 0x7*i0; }
 
-#define REG_A5XX_UNKNOWN_E2AE					0x0000e2ae
+static inline uint32_t REG_A5XX_VPC_SO_NCOMP(uint32_t i0) { return 0x0000e2aa + 0x7*i0; }
 
-#define REG_A5XX_UNKNOWN_E2B2					0x0000e2b2
+static inline uint32_t REG_A5XX_VPC_SO_BUFFER_OFFSET(uint32_t i0) { return 0x0000e2ab + 0x7*i0; }
 
-#define REG_A5XX_UNKNOWN_E2B9					0x0000e2b9
+static inline uint32_t REG_A5XX_VPC_SO_FLUSH_BASE_LO(uint32_t i0) { return 0x0000e2ac + 0x7*i0; }
 
-#define REG_A5XX_UNKNOWN_E2C0					0x0000e2c0
+static inline uint32_t REG_A5XX_VPC_SO_FLUSH_BASE_HI(uint32_t i0) { return 0x0000e2ad + 0x7*i0; }
 
 #define REG_A5XX_PC_PRIMITIVE_CNTL				0x0000e384
 #define A5XX_PC_PRIMITIVE_CNTL_STRIDE_IN_VPC__MASK		0x0000007f
@@ -2873,6 +3627,7 @@ static inline uint32_t A5XX_PC_PRIMITIVE_CNTL_STRIDE_IN_VPC(uint32_t val)
 {
 	return ((val) << A5XX_PC_PRIMITIVE_CNTL_STRIDE_IN_VPC__SHIFT) & A5XX_PC_PRIMITIVE_CNTL_STRIDE_IN_VPC__MASK;
 }
+#define A5XX_PC_PRIMITIVE_CNTL_PROVOKING_VTX_LAST		0x00000400
 
 #define REG_A5XX_PC_PRIM_VTX_CNTL				0x0000e385
 #define A5XX_PC_PRIM_VTX_CNTL_PSIZE				0x00000800
@@ -2900,18 +3655,18 @@ static inline uint32_t A5XX_VFD_CONTROL_0_VTXCNT(uint32_t val)
 }
 
 #define REG_A5XX_VFD_CONTROL_1					0x0000e401
+#define A5XX_VFD_CONTROL_1_REGID4VTX__MASK			0x000000ff
+#define A5XX_VFD_CONTROL_1_REGID4VTX__SHIFT			0
+static inline uint32_t A5XX_VFD_CONTROL_1_REGID4VTX(uint32_t val)
+{
+	return ((val) << A5XX_VFD_CONTROL_1_REGID4VTX__SHIFT) & A5XX_VFD_CONTROL_1_REGID4VTX__MASK;
+}
 #define A5XX_VFD_CONTROL_1_REGID4INST__MASK			0x0000ff00
 #define A5XX_VFD_CONTROL_1_REGID4INST__SHIFT			8
 static inline uint32_t A5XX_VFD_CONTROL_1_REGID4INST(uint32_t val)
 {
 	return ((val) << A5XX_VFD_CONTROL_1_REGID4INST__SHIFT) & A5XX_VFD_CONTROL_1_REGID4INST__MASK;
 }
-#define A5XX_VFD_CONTROL_1_REGID4VTX__MASK			0x00ff0000
-#define A5XX_VFD_CONTROL_1_REGID4VTX__SHIFT			16
-static inline uint32_t A5XX_VFD_CONTROL_1_REGID4VTX(uint32_t val)
-{
-	return ((val) << A5XX_VFD_CONTROL_1_REGID4VTX__SHIFT) & A5XX_VFD_CONTROL_1_REGID4VTX__MASK;
-}
 
 #define REG_A5XX_VFD_CONTROL_2					0x0000e402
 
@@ -2944,18 +3699,15 @@ static inline uint32_t A5XX_VFD_DECODE_INSTR_IDX(uint32_t val)
 {
 	return ((val) << A5XX_VFD_DECODE_INSTR_IDX__SHIFT) & A5XX_VFD_DECODE_INSTR_IDX__MASK;
 }
+#define A5XX_VFD_DECODE_INSTR_INSTANCED				0x00020000
 #define A5XX_VFD_DECODE_INSTR_FORMAT__MASK			0x3ff00000
 #define A5XX_VFD_DECODE_INSTR_FORMAT__SHIFT			20
 static inline uint32_t A5XX_VFD_DECODE_INSTR_FORMAT(enum a5xx_vtx_fmt val)
 {
 	return ((val) << A5XX_VFD_DECODE_INSTR_FORMAT__SHIFT) & A5XX_VFD_DECODE_INSTR_FORMAT__MASK;
 }
-#define A5XX_VFD_DECODE_INSTR_SWAP__MASK			0xc0000000
-#define A5XX_VFD_DECODE_INSTR_SWAP__SHIFT			30
-static inline uint32_t A5XX_VFD_DECODE_INSTR_SWAP(enum a3xx_color_swap val)
-{
-	return ((val) << A5XX_VFD_DECODE_INSTR_SWAP__SHIFT) & A5XX_VFD_DECODE_INSTR_SWAP__MASK;
-}
+#define A5XX_VFD_DECODE_INSTR_UNK30				0x40000000
+#define A5XX_VFD_DECODE_INSTR_FLOAT				0x80000000
 
 static inline uint32_t REG_A5XX_VFD_DECODE_STEP_RATE(uint32_t i0) { return 0x0000e48b + 0x2*i0; }
 
@@ -2979,88 +3731,107 @@ static inline uint32_t A5XX_VFD_DEST_CNTL_INSTR_REGID(uint32_t val)
 
 #define REG_A5XX_SP_SP_CNTL					0x0000e580
 
-#define REG_A5XX_SP_VS_CONTROL_REG				0x0000e584
-#define A5XX_SP_VS_CONTROL_REG_ENABLED				0x00000001
-#define A5XX_SP_VS_CONTROL_REG_CONSTOBJECTOFFSET__MASK		0x000000fe
-#define A5XX_SP_VS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT		1
-static inline uint32_t A5XX_SP_VS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_SP_VS_CONFIG					0x0000e584
+#define A5XX_SP_VS_CONFIG_ENABLED				0x00000001
+#define A5XX_SP_VS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_SP_VS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_SP_VS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_VS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_VS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_SP_VS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_VS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_SP_VS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_SP_VS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_SP_VS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_SP_VS_CONFIG_SHADEROBJOFFSET__MASK			0x00007f00
+#define A5XX_SP_VS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_SP_VS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_VS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_VS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_SP_VS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_VS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_SP_FS_CONTROL_REG				0x0000e585
-#define A5XX_SP_FS_CONTROL_REG_ENABLED				0x00000001
-#define A5XX_SP_FS_CONTROL_REG_CONSTOBJECTOFFSET__MASK		0x000000fe
-#define A5XX_SP_FS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT		1
-static inline uint32_t A5XX_SP_FS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_SP_FS_CONFIG					0x0000e585
+#define A5XX_SP_FS_CONFIG_ENABLED				0x00000001
+#define A5XX_SP_FS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_SP_FS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_SP_FS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_FS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_FS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_SP_FS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_FS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_SP_FS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_SP_FS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_SP_FS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_SP_FS_CONFIG_SHADEROBJOFFSET__MASK			0x00007f00
+#define A5XX_SP_FS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_SP_FS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_FS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_FS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_SP_FS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_FS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_SP_HS_CONTROL_REG				0x0000e586
-#define A5XX_SP_HS_CONTROL_REG_ENABLED				0x00000001
-#define A5XX_SP_HS_CONTROL_REG_CONSTOBJECTOFFSET__MASK		0x000000fe
-#define A5XX_SP_HS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT		1
-static inline uint32_t A5XX_SP_HS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_SP_HS_CONFIG					0x0000e586
+#define A5XX_SP_HS_CONFIG_ENABLED				0x00000001
+#define A5XX_SP_HS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_SP_HS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_SP_HS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_HS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_HS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_SP_HS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_HS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_SP_HS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_SP_HS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_SP_HS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_SP_HS_CONFIG_SHADEROBJOFFSET__MASK			0x00007f00
+#define A5XX_SP_HS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_SP_HS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_HS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_HS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_SP_HS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_HS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_SP_DS_CONTROL_REG				0x0000e587
-#define A5XX_SP_DS_CONTROL_REG_ENABLED				0x00000001
-#define A5XX_SP_DS_CONTROL_REG_CONSTOBJECTOFFSET__MASK		0x000000fe
-#define A5XX_SP_DS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT		1
-static inline uint32_t A5XX_SP_DS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_SP_DS_CONFIG					0x0000e587
+#define A5XX_SP_DS_CONFIG_ENABLED				0x00000001
+#define A5XX_SP_DS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_SP_DS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_SP_DS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_DS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_DS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_SP_DS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_DS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_SP_DS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_SP_DS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_SP_DS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_SP_DS_CONFIG_SHADEROBJOFFSET__MASK			0x00007f00
+#define A5XX_SP_DS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_SP_DS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_DS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_DS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_SP_DS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_DS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_SP_GS_CONTROL_REG				0x0000e588
-#define A5XX_SP_GS_CONTROL_REG_ENABLED				0x00000001
-#define A5XX_SP_GS_CONTROL_REG_CONSTOBJECTOFFSET__MASK		0x000000fe
-#define A5XX_SP_GS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT		1
-static inline uint32_t A5XX_SP_GS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_SP_GS_CONFIG					0x0000e588
+#define A5XX_SP_GS_CONFIG_ENABLED				0x00000001
+#define A5XX_SP_GS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_SP_GS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_SP_GS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_GS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_GS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_SP_GS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_GS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_SP_GS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_SP_GS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_SP_GS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_SP_GS_CONFIG_SHADEROBJOFFSET__MASK			0x00007f00
+#define A5XX_SP_GS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_SP_GS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_SP_GS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_GS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_SP_GS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_GS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
 #define REG_A5XX_SP_CS_CONFIG					0x0000e589
+#define A5XX_SP_CS_CONFIG_ENABLED				0x00000001
+#define A5XX_SP_CS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_SP_CS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_SP_CS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
+{
+	return ((val) << A5XX_SP_CS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_SP_CS_CONFIG_CONSTOBJECTOFFSET__MASK;
+}
+#define A5XX_SP_CS_CONFIG_SHADEROBJOFFSET__MASK			0x00007f00
+#define A5XX_SP_CS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_SP_CS_CONFIG_SHADEROBJOFFSET(uint32_t val)
+{
+	return ((val) << A5XX_SP_CS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_SP_CS_CONFIG_SHADEROBJOFFSET__MASK;
+}
 
 #define REG_A5XX_SP_VS_CONFIG_MAX_CONST				0x0000e58a
 
 #define REG_A5XX_SP_FS_CONFIG_MAX_CONST				0x0000e58b
 
 #define REG_A5XX_SP_VS_CTRL_REG0				0x0000e590
+#define A5XX_SP_VS_CTRL_REG0_THREADSIZE__MASK			0x00000008
+#define A5XX_SP_VS_CTRL_REG0_THREADSIZE__SHIFT			3
+static inline uint32_t A5XX_SP_VS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A5XX_SP_VS_CTRL_REG0_THREADSIZE__SHIFT) & A5XX_SP_VS_CTRL_REG0_THREADSIZE__MASK;
+}
 #define A5XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT__MASK		0x000003f0
 #define A5XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT		4
 static inline uint32_t A5XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT(uint32_t val)
@@ -3075,13 +3846,19 @@ static inline uint32_t A5XX_SP_VS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val)
 }
 #define A5XX_SP_VS_CTRL_REG0_VARYING				0x00010000
 #define A5XX_SP_VS_CTRL_REG0_PIXLODENABLE			0x00100000
+#define A5XX_SP_VS_CTRL_REG0_BRANCHSTACK__MASK			0xfe000000
+#define A5XX_SP_VS_CTRL_REG0_BRANCHSTACK__SHIFT			25
+static inline uint32_t A5XX_SP_VS_CTRL_REG0_BRANCHSTACK(uint32_t val)
+{
+	return ((val) << A5XX_SP_VS_CTRL_REG0_BRANCHSTACK__SHIFT) & A5XX_SP_VS_CTRL_REG0_BRANCHSTACK__MASK;
+}
 
 #define REG_A5XX_SP_PRIMITIVE_CNTL				0x0000e592
-#define A5XX_SP_PRIMITIVE_CNTL_STRIDE_IN_VPC__MASK		0x0000001f
-#define A5XX_SP_PRIMITIVE_CNTL_STRIDE_IN_VPC__SHIFT		0
-static inline uint32_t A5XX_SP_PRIMITIVE_CNTL_STRIDE_IN_VPC(uint32_t val)
+#define A5XX_SP_PRIMITIVE_CNTL_VSOUT__MASK			0x0000001f
+#define A5XX_SP_PRIMITIVE_CNTL_VSOUT__SHIFT			0
+static inline uint32_t A5XX_SP_PRIMITIVE_CNTL_VSOUT(uint32_t val)
 {
-	return ((val >> 2) << A5XX_SP_PRIMITIVE_CNTL_STRIDE_IN_VPC__SHIFT) & A5XX_SP_PRIMITIVE_CNTL_STRIDE_IN_VPC__MASK;
+	return ((val) << A5XX_SP_PRIMITIVE_CNTL_VSOUT__SHIFT) & A5XX_SP_PRIMITIVE_CNTL_VSOUT__MASK;
 }
 
 static inline uint32_t REG_A5XX_SP_VS_OUT(uint32_t i0) { return 0x0000e593 + 0x1*i0; }
@@ -3147,6 +3924,12 @@ static inline uint32_t A5XX_SP_VS_VPC_DST_REG_OUTLOC3(uint32_t val)
 #define REG_A5XX_SP_VS_OBJ_START_HI				0x0000e5ad
 
 #define REG_A5XX_SP_FS_CTRL_REG0				0x0000e5c0
+#define A5XX_SP_FS_CTRL_REG0_THREADSIZE__MASK			0x00000008
+#define A5XX_SP_FS_CTRL_REG0_THREADSIZE__SHIFT			3
+static inline uint32_t A5XX_SP_FS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A5XX_SP_FS_CTRL_REG0_THREADSIZE__SHIFT) & A5XX_SP_FS_CTRL_REG0_THREADSIZE__MASK;
+}
 #define A5XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT__MASK		0x000003f0
 #define A5XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT		4
 static inline uint32_t A5XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT(uint32_t val)
@@ -3161,6 +3944,12 @@ static inline uint32_t A5XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val)
 }
 #define A5XX_SP_FS_CTRL_REG0_VARYING				0x00010000
 #define A5XX_SP_FS_CTRL_REG0_PIXLODENABLE			0x00100000
+#define A5XX_SP_FS_CTRL_REG0_BRANCHSTACK__MASK			0xfe000000
+#define A5XX_SP_FS_CTRL_REG0_BRANCHSTACK__SHIFT			25
+static inline uint32_t A5XX_SP_FS_CTRL_REG0_BRANCHSTACK(uint32_t val)
+{
+	return ((val) << A5XX_SP_FS_CTRL_REG0_BRANCHSTACK__SHIFT) & A5XX_SP_FS_CTRL_REG0_BRANCHSTACK__MASK;
+}
 
 #define REG_A5XX_UNKNOWN_E5C2					0x0000e5c2
 
@@ -3169,6 +3958,8 @@ static inline uint32_t A5XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val)
 #define REG_A5XX_SP_FS_OBJ_START_HI				0x0000e5c4
 
 #define REG_A5XX_SP_BLEND_CNTL					0x0000e5c9
+#define A5XX_SP_BLEND_CNTL_ENABLED				0x00000001
+#define A5XX_SP_BLEND_CNTL_UNK8					0x00000100
 
 #define REG_A5XX_SP_FS_OUTPUT_CNTL				0x0000e5ca
 #define A5XX_SP_FS_OUTPUT_CNTL_MRT__MASK			0x0000000f
@@ -3210,15 +4001,66 @@ static inline uint32_t A5XX_SP_FS_MRT_REG_COLOR_FORMAT(enum a5xx_color_fmt val)
 {
 	return ((val) << A5XX_SP_FS_MRT_REG_COLOR_FORMAT__SHIFT) & A5XX_SP_FS_MRT_REG_COLOR_FORMAT__MASK;
 }
+#define A5XX_SP_FS_MRT_REG_COLOR_SRGB				0x00000400
 
 #define REG_A5XX_UNKNOWN_E5DB					0x0000e5db
 
-#define REG_A5XX_SP_CS_CNTL_0					0x0000e5f0
+#define REG_A5XX_UNKNOWN_E5F2					0x0000e5f2
+
+#define REG_A5XX_SP_CS_OBJ_START_LO				0x0000e5f3
+
+#define REG_A5XX_SP_CS_OBJ_START_HI				0x0000e5f4
+
+#define REG_A5XX_SP_CS_CTRL_REG0				0x0000e5f0
+#define A5XX_SP_CS_CTRL_REG0_THREADSIZE__MASK			0x00000008
+#define A5XX_SP_CS_CTRL_REG0_THREADSIZE__SHIFT			3
+static inline uint32_t A5XX_SP_CS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A5XX_SP_CS_CTRL_REG0_THREADSIZE__SHIFT) & A5XX_SP_CS_CTRL_REG0_THREADSIZE__MASK;
+}
+#define A5XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__MASK		0x000003f0
+#define A5XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT		4
+static inline uint32_t A5XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT(uint32_t val)
+{
+	return ((val) << A5XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT) & A5XX_SP_CS_CTRL_REG0_HALFREGFOOTPRINT__MASK;
+}
+#define A5XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__MASK		0x0000fc00
+#define A5XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT		10
+static inline uint32_t A5XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val)
+{
+	return ((val) << A5XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT) & A5XX_SP_CS_CTRL_REG0_FULLREGFOOTPRINT__MASK;
+}
+#define A5XX_SP_CS_CTRL_REG0_VARYING				0x00010000
+#define A5XX_SP_CS_CTRL_REG0_PIXLODENABLE			0x00100000
+#define A5XX_SP_CS_CTRL_REG0_BRANCHSTACK__MASK			0xfe000000
+#define A5XX_SP_CS_CTRL_REG0_BRANCHSTACK__SHIFT			25
+static inline uint32_t A5XX_SP_CS_CTRL_REG0_BRANCHSTACK(uint32_t val)
+{
+	return ((val) << A5XX_SP_CS_CTRL_REG0_BRANCHSTACK__SHIFT) & A5XX_SP_CS_CTRL_REG0_BRANCHSTACK__MASK;
+}
 
 #define REG_A5XX_UNKNOWN_E600					0x0000e600
 
+#define REG_A5XX_UNKNOWN_E602					0x0000e602
+
+#define REG_A5XX_SP_HS_OBJ_START_LO				0x0000e603
+
+#define REG_A5XX_SP_HS_OBJ_START_HI				0x0000e604
+
+#define REG_A5XX_UNKNOWN_E62B					0x0000e62b
+
+#define REG_A5XX_SP_DS_OBJ_START_LO				0x0000e62c
+
+#define REG_A5XX_SP_DS_OBJ_START_HI				0x0000e62d
+
 #define REG_A5XX_UNKNOWN_E640					0x0000e640
 
+#define REG_A5XX_UNKNOWN_E65B					0x0000e65b
+
+#define REG_A5XX_SP_GS_OBJ_START_LO				0x0000e65c
+
+#define REG_A5XX_SP_GS_OBJ_START_HI				0x0000e65d
+
 #define REG_A5XX_TPL1_TP_RAS_MSAA_CNTL				0x0000e704
 #define A5XX_TPL1_TP_RAS_MSAA_CNTL_SAMPLES__MASK		0x00000003
 #define A5XX_TPL1_TP_RAS_MSAA_CNTL_SAMPLES__SHIFT		0
@@ -3236,29 +4078,85 @@ static inline uint32_t A5XX_TPL1_TP_DEST_MSAA_CNTL_SAMPLES(enum a3xx_msaa_sample
 }
 #define A5XX_TPL1_TP_DEST_MSAA_CNTL_MSAA_DISABLE		0x00000004
 
+#define REG_A5XX_TPL1_TP_BORDER_COLOR_BASE_ADDR_LO		0x0000e706
+
+#define REG_A5XX_TPL1_TP_BORDER_COLOR_BASE_ADDR_HI		0x0000e707
+
 #define REG_A5XX_TPL1_VS_TEX_COUNT				0x0000e700
 
+#define REG_A5XX_TPL1_HS_TEX_COUNT				0x0000e701
+
+#define REG_A5XX_TPL1_DS_TEX_COUNT				0x0000e702
+
+#define REG_A5XX_TPL1_GS_TEX_COUNT				0x0000e703
+
 #define REG_A5XX_TPL1_VS_TEX_SAMP_LO				0x0000e722
 
 #define REG_A5XX_TPL1_VS_TEX_SAMP_HI				0x0000e723
 
+#define REG_A5XX_TPL1_HS_TEX_SAMP_LO				0x0000e724
+
+#define REG_A5XX_TPL1_HS_TEX_SAMP_HI				0x0000e725
+
+#define REG_A5XX_TPL1_DS_TEX_SAMP_LO				0x0000e726
+
+#define REG_A5XX_TPL1_DS_TEX_SAMP_HI				0x0000e727
+
+#define REG_A5XX_TPL1_GS_TEX_SAMP_LO				0x0000e728
+
+#define REG_A5XX_TPL1_GS_TEX_SAMP_HI				0x0000e729
+
 #define REG_A5XX_TPL1_VS_TEX_CONST_LO				0x0000e72a
 
 #define REG_A5XX_TPL1_VS_TEX_CONST_HI				0x0000e72b
 
+#define REG_A5XX_TPL1_HS_TEX_CONST_LO				0x0000e72c
+
+#define REG_A5XX_TPL1_HS_TEX_CONST_HI				0x0000e72d
+
+#define REG_A5XX_TPL1_DS_TEX_CONST_LO				0x0000e72e
+
+#define REG_A5XX_TPL1_DS_TEX_CONST_HI				0x0000e72f
+
+#define REG_A5XX_TPL1_GS_TEX_CONST_LO				0x0000e730
+
+#define REG_A5XX_TPL1_GS_TEX_CONST_HI				0x0000e731
+
 #define REG_A5XX_TPL1_FS_TEX_COUNT				0x0000e750
 
+#define REG_A5XX_TPL1_CS_TEX_COUNT				0x0000e751
+
 #define REG_A5XX_TPL1_FS_TEX_SAMP_LO				0x0000e75a
 
 #define REG_A5XX_TPL1_FS_TEX_SAMP_HI				0x0000e75b
 
+#define REG_A5XX_TPL1_CS_TEX_SAMP_LO				0x0000e75c
+
+#define REG_A5XX_TPL1_CS_TEX_SAMP_HI				0x0000e75d
+
 #define REG_A5XX_TPL1_FS_TEX_CONST_LO				0x0000e75e
 
 #define REG_A5XX_TPL1_FS_TEX_CONST_HI				0x0000e75f
 
+#define REG_A5XX_TPL1_CS_TEX_CONST_LO				0x0000e760
+
+#define REG_A5XX_TPL1_CS_TEX_CONST_HI				0x0000e761
+
 #define REG_A5XX_TPL1_TP_FS_ROTATION_CNTL			0x0000e764
 
 #define REG_A5XX_HLSQ_CONTROL_0_REG				0x0000e784
+#define A5XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__MASK		0x00000001
+#define A5XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__SHIFT		0
+static inline uint32_t A5XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A5XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__SHIFT) & A5XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__MASK;
+}
+#define A5XX_HLSQ_CONTROL_0_REG_CSTHREADSIZE__MASK		0x00000004
+#define A5XX_HLSQ_CONTROL_0_REG_CSTHREADSIZE__SHIFT		2
+static inline uint32_t A5XX_HLSQ_CONTROL_0_REG_CSTHREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A5XX_HLSQ_CONTROL_0_REG_CSTHREADSIZE__SHIFT) & A5XX_HLSQ_CONTROL_0_REG_CSTHREADSIZE__MASK;
+}
 
 #define REG_A5XX_HLSQ_CONTROL_1_REG				0x0000e785
 #define A5XX_HLSQ_CONTROL_1_REG_PRIMALLOCTHRESHOLD__MASK	0x0000003f
@@ -3300,84 +4198,98 @@ static inline uint32_t A5XX_HLSQ_CONTROL_4_REG_ZWCOORDREGID(uint32_t val)
 
 #define REG_A5XX_HLSQ_UPDATE_CNTL				0x0000e78a
 
-#define REG_A5XX_HLSQ_VS_CONTROL_REG				0x0000e78b
-#define A5XX_HLSQ_VS_CONTROL_REG_ENABLED			0x00000001
-#define A5XX_HLSQ_VS_CONTROL_REG_CONSTOBJECTOFFSET__MASK	0x000000fe
-#define A5XX_HLSQ_VS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT	1
-static inline uint32_t A5XX_HLSQ_VS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_HLSQ_VS_CONFIG					0x0000e78b
+#define A5XX_HLSQ_VS_CONFIG_ENABLED				0x00000001
+#define A5XX_HLSQ_VS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_HLSQ_VS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_HLSQ_VS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_VS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_VS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_VS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_VS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_HLSQ_VS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_HLSQ_VS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_HLSQ_VS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_HLSQ_VS_CONFIG_SHADEROBJOFFSET__MASK		0x00007f00
+#define A5XX_HLSQ_VS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_HLSQ_VS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_VS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_VS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_VS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_VS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_HLSQ_FS_CONTROL_REG				0x0000e78c
-#define A5XX_HLSQ_FS_CONTROL_REG_ENABLED			0x00000001
-#define A5XX_HLSQ_FS_CONTROL_REG_CONSTOBJECTOFFSET__MASK	0x000000fe
-#define A5XX_HLSQ_FS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT	1
-static inline uint32_t A5XX_HLSQ_FS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_HLSQ_FS_CONFIG					0x0000e78c
+#define A5XX_HLSQ_FS_CONFIG_ENABLED				0x00000001
+#define A5XX_HLSQ_FS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_HLSQ_FS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_HLSQ_FS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_FS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_FS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_FS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_FS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_HLSQ_FS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_HLSQ_FS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_HLSQ_FS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_HLSQ_FS_CONFIG_SHADEROBJOFFSET__MASK		0x00007f00
+#define A5XX_HLSQ_FS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_HLSQ_FS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_FS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_FS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_FS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_FS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_HLSQ_HS_CONTROL_REG				0x0000e78d
-#define A5XX_HLSQ_HS_CONTROL_REG_ENABLED			0x00000001
-#define A5XX_HLSQ_HS_CONTROL_REG_CONSTOBJECTOFFSET__MASK	0x000000fe
-#define A5XX_HLSQ_HS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT	1
-static inline uint32_t A5XX_HLSQ_HS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_HLSQ_HS_CONFIG					0x0000e78d
+#define A5XX_HLSQ_HS_CONFIG_ENABLED				0x00000001
+#define A5XX_HLSQ_HS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_HLSQ_HS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_HLSQ_HS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_HS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_HS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_HS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_HS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_HLSQ_HS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_HLSQ_HS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_HLSQ_HS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_HLSQ_HS_CONFIG_SHADEROBJOFFSET__MASK		0x00007f00
+#define A5XX_HLSQ_HS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_HLSQ_HS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_HS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_HS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_HS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_HS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_HLSQ_DS_CONTROL_REG				0x0000e78e
-#define A5XX_HLSQ_DS_CONTROL_REG_ENABLED			0x00000001
-#define A5XX_HLSQ_DS_CONTROL_REG_CONSTOBJECTOFFSET__MASK	0x000000fe
-#define A5XX_HLSQ_DS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT	1
-static inline uint32_t A5XX_HLSQ_DS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_HLSQ_DS_CONFIG					0x0000e78e
+#define A5XX_HLSQ_DS_CONFIG_ENABLED				0x00000001
+#define A5XX_HLSQ_DS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_HLSQ_DS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_HLSQ_DS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_DS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_DS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_DS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_DS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_HLSQ_DS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_HLSQ_DS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_HLSQ_DS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_HLSQ_DS_CONFIG_SHADEROBJOFFSET__MASK		0x00007f00
+#define A5XX_HLSQ_DS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_HLSQ_DS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_DS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_DS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_DS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_DS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
-#define REG_A5XX_HLSQ_GS_CONTROL_REG				0x0000e78f
-#define A5XX_HLSQ_GS_CONTROL_REG_ENABLED			0x00000001
-#define A5XX_HLSQ_GS_CONTROL_REG_CONSTOBJECTOFFSET__MASK	0x000000fe
-#define A5XX_HLSQ_GS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT	1
-static inline uint32_t A5XX_HLSQ_GS_CONTROL_REG_CONSTOBJECTOFFSET(uint32_t val)
+#define REG_A5XX_HLSQ_GS_CONFIG					0x0000e78f
+#define A5XX_HLSQ_GS_CONFIG_ENABLED				0x00000001
+#define A5XX_HLSQ_GS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_HLSQ_GS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_HLSQ_GS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_GS_CONTROL_REG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_GS_CONTROL_REG_CONSTOBJECTOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_GS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_GS_CONFIG_CONSTOBJECTOFFSET__MASK;
 }
-#define A5XX_HLSQ_GS_CONTROL_REG_SHADEROBJOFFSET__MASK		0x00007f00
-#define A5XX_HLSQ_GS_CONTROL_REG_SHADEROBJOFFSET__SHIFT		8
-static inline uint32_t A5XX_HLSQ_GS_CONTROL_REG_SHADEROBJOFFSET(uint32_t val)
+#define A5XX_HLSQ_GS_CONFIG_SHADEROBJOFFSET__MASK		0x00007f00
+#define A5XX_HLSQ_GS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_HLSQ_GS_CONFIG_SHADEROBJOFFSET(uint32_t val)
 {
-	return ((val) << A5XX_HLSQ_GS_CONTROL_REG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_GS_CONTROL_REG_SHADEROBJOFFSET__MASK;
+	return ((val) << A5XX_HLSQ_GS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_GS_CONFIG_SHADEROBJOFFSET__MASK;
 }
 
 #define REG_A5XX_HLSQ_CS_CONFIG					0x0000e790
+#define A5XX_HLSQ_CS_CONFIG_ENABLED				0x00000001
+#define A5XX_HLSQ_CS_CONFIG_CONSTOBJECTOFFSET__MASK		0x000000fe
+#define A5XX_HLSQ_CS_CONFIG_CONSTOBJECTOFFSET__SHIFT		1
+static inline uint32_t A5XX_HLSQ_CS_CONFIG_CONSTOBJECTOFFSET(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_CONFIG_CONSTOBJECTOFFSET__SHIFT) & A5XX_HLSQ_CS_CONFIG_CONSTOBJECTOFFSET__MASK;
+}
+#define A5XX_HLSQ_CS_CONFIG_SHADEROBJOFFSET__MASK		0x00007f00
+#define A5XX_HLSQ_CS_CONFIG_SHADEROBJOFFSET__SHIFT		8
+static inline uint32_t A5XX_HLSQ_CS_CONFIG_SHADEROBJOFFSET(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_CONFIG_SHADEROBJOFFSET__SHIFT) & A5XX_HLSQ_CS_CONFIG_SHADEROBJOFFSET__MASK;
+}
 
 #define REG_A5XX_HLSQ_VS_CNTL					0x0000e791
+#define A5XX_HLSQ_VS_CNTL_SSBO_ENABLE				0x00000001
 #define A5XX_HLSQ_VS_CNTL_INSTRLEN__MASK			0xfffffffe
 #define A5XX_HLSQ_VS_CNTL_INSTRLEN__SHIFT			1
 static inline uint32_t A5XX_HLSQ_VS_CNTL_INSTRLEN(uint32_t val)
@@ -3386,6 +4298,7 @@ static inline uint32_t A5XX_HLSQ_VS_CNTL_INSTRLEN(uint32_t val)
 }
 
 #define REG_A5XX_HLSQ_FS_CNTL					0x0000e792
+#define A5XX_HLSQ_FS_CNTL_SSBO_ENABLE				0x00000001
 #define A5XX_HLSQ_FS_CNTL_INSTRLEN__MASK			0xfffffffe
 #define A5XX_HLSQ_FS_CNTL_INSTRLEN__SHIFT			1
 static inline uint32_t A5XX_HLSQ_FS_CNTL_INSTRLEN(uint32_t val)
@@ -3394,6 +4307,7 @@ static inline uint32_t A5XX_HLSQ_FS_CNTL_INSTRLEN(uint32_t val)
 }
 
 #define REG_A5XX_HLSQ_HS_CNTL					0x0000e793
+#define A5XX_HLSQ_HS_CNTL_SSBO_ENABLE				0x00000001
 #define A5XX_HLSQ_HS_CNTL_INSTRLEN__MASK			0xfffffffe
 #define A5XX_HLSQ_HS_CNTL_INSTRLEN__SHIFT			1
 static inline uint32_t A5XX_HLSQ_HS_CNTL_INSTRLEN(uint32_t val)
@@ -3402,6 +4316,7 @@ static inline uint32_t A5XX_HLSQ_HS_CNTL_INSTRLEN(uint32_t val)
 }
 
 #define REG_A5XX_HLSQ_DS_CNTL					0x0000e794
+#define A5XX_HLSQ_DS_CNTL_SSBO_ENABLE				0x00000001
 #define A5XX_HLSQ_DS_CNTL_INSTRLEN__MASK			0xfffffffe
 #define A5XX_HLSQ_DS_CNTL_INSTRLEN__SHIFT			1
 static inline uint32_t A5XX_HLSQ_DS_CNTL_INSTRLEN(uint32_t val)
@@ -3410,6 +4325,7 @@ static inline uint32_t A5XX_HLSQ_DS_CNTL_INSTRLEN(uint32_t val)
 }
 
 #define REG_A5XX_HLSQ_GS_CNTL					0x0000e795
+#define A5XX_HLSQ_GS_CNTL_SSBO_ENABLE				0x00000001
 #define A5XX_HLSQ_GS_CNTL_INSTRLEN__MASK			0xfffffffe
 #define A5XX_HLSQ_GS_CNTL_INSTRLEN__SHIFT			1
 static inline uint32_t A5XX_HLSQ_GS_CNTL_INSTRLEN(uint32_t val)
@@ -3418,6 +4334,7 @@ static inline uint32_t A5XX_HLSQ_GS_CNTL_INSTRLEN(uint32_t val)
 }
 
 #define REG_A5XX_HLSQ_CS_CNTL					0x0000e796
+#define A5XX_HLSQ_CS_CNTL_SSBO_ENABLE				0x00000001
 #define A5XX_HLSQ_CS_CNTL_INSTRLEN__MASK			0xfffffffe
 #define A5XX_HLSQ_CS_CNTL_INSTRLEN__SHIFT			1
 static inline uint32_t A5XX_HLSQ_CS_CNTL_INSTRLEN(uint32_t val)
@@ -3432,20 +4349,86 @@ static inline uint32_t A5XX_HLSQ_CS_CNTL_INSTRLEN(uint32_t val)
 #define REG_A5XX_HLSQ_CS_KERNEL_GROUP_Z				0x0000e7bb
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_0				0x0000e7b0
+#define A5XX_HLSQ_CS_NDRANGE_0_KERNELDIM__MASK			0x00000003
+#define A5XX_HLSQ_CS_NDRANGE_0_KERNELDIM__SHIFT			0
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_0_KERNELDIM(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_0_KERNELDIM__SHIFT) & A5XX_HLSQ_CS_NDRANGE_0_KERNELDIM__MASK;
+}
+#define A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEX__MASK			0x00000ffc
+#define A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEX__SHIFT		2
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEX(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEX__SHIFT) & A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEX__MASK;
+}
+#define A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEY__MASK			0x003ff000
+#define A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEY__SHIFT		12
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEY(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEY__SHIFT) & A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEY__MASK;
+}
+#define A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEZ__MASK			0xffc00000
+#define A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEZ__SHIFT		22
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEZ(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEZ__SHIFT) & A5XX_HLSQ_CS_NDRANGE_0_LOCALSIZEZ__MASK;
+}
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_1				0x0000e7b1
+#define A5XX_HLSQ_CS_NDRANGE_1_SIZE_X__MASK			0xffffffff
+#define A5XX_HLSQ_CS_NDRANGE_1_SIZE_X__SHIFT			0
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_1_SIZE_X(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_1_SIZE_X__SHIFT) & A5XX_HLSQ_CS_NDRANGE_1_SIZE_X__MASK;
+}
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_2				0x0000e7b2
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_3				0x0000e7b3
+#define A5XX_HLSQ_CS_NDRANGE_3_SIZE_Y__MASK			0xffffffff
+#define A5XX_HLSQ_CS_NDRANGE_3_SIZE_Y__SHIFT			0
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_3_SIZE_Y(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_3_SIZE_Y__SHIFT) & A5XX_HLSQ_CS_NDRANGE_3_SIZE_Y__MASK;
+}
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_4				0x0000e7b4
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_5				0x0000e7b5
+#define A5XX_HLSQ_CS_NDRANGE_5_SIZE_Z__MASK			0xffffffff
+#define A5XX_HLSQ_CS_NDRANGE_5_SIZE_Z__SHIFT			0
+static inline uint32_t A5XX_HLSQ_CS_NDRANGE_5_SIZE_Z(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_NDRANGE_5_SIZE_Z__SHIFT) & A5XX_HLSQ_CS_NDRANGE_5_SIZE_Z__MASK;
+}
 
 #define REG_A5XX_HLSQ_CS_NDRANGE_6				0x0000e7b6
 
 #define REG_A5XX_HLSQ_CS_CNTL_0					0x0000e7b7
+#define A5XX_HLSQ_CS_CNTL_0_WGIDCONSTID__MASK			0x000000ff
+#define A5XX_HLSQ_CS_CNTL_0_WGIDCONSTID__SHIFT			0
+static inline uint32_t A5XX_HLSQ_CS_CNTL_0_WGIDCONSTID(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_CNTL_0_WGIDCONSTID__SHIFT) & A5XX_HLSQ_CS_CNTL_0_WGIDCONSTID__MASK;
+}
+#define A5XX_HLSQ_CS_CNTL_0_UNK0__MASK				0x0000ff00
+#define A5XX_HLSQ_CS_CNTL_0_UNK0__SHIFT				8
+static inline uint32_t A5XX_HLSQ_CS_CNTL_0_UNK0(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_CNTL_0_UNK0__SHIFT) & A5XX_HLSQ_CS_CNTL_0_UNK0__MASK;
+}
+#define A5XX_HLSQ_CS_CNTL_0_UNK1__MASK				0x00ff0000
+#define A5XX_HLSQ_CS_CNTL_0_UNK1__SHIFT				16
+static inline uint32_t A5XX_HLSQ_CS_CNTL_0_UNK1(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_CNTL_0_UNK1__SHIFT) & A5XX_HLSQ_CS_CNTL_0_UNK1__MASK;
+}
+#define A5XX_HLSQ_CS_CNTL_0_LOCALIDREGID__MASK			0xff000000
+#define A5XX_HLSQ_CS_CNTL_0_LOCALIDREGID__SHIFT			24
+static inline uint32_t A5XX_HLSQ_CS_CNTL_0_LOCALIDREGID(uint32_t val)
+{
+	return ((val) << A5XX_HLSQ_CS_CNTL_0_LOCALIDREGID__SHIFT) & A5XX_HLSQ_CS_CNTL_0_LOCALIDREGID__MASK;
+}
 
 #define REG_A5XX_HLSQ_CS_CNTL_1					0x0000e7b8
 
@@ -3457,16 +4440,12 @@ static inline uint32_t A5XX_HLSQ_CS_CNTL_INSTRLEN(uint32_t val)
 
 #define REG_A5XX_UNKNOWN_E7C5					0x0000e7c5
 
-#define REG_A5XX_UNKNOWN_E7CA					0x0000e7ca
-
-#define REG_A5XX_HLSQ_FS_CONSTLEN				0x0000e7d7
-
-#define REG_A5XX_HLSQ_FS_INSTRLEN				0x0000e7d8
-
 #define REG_A5XX_HLSQ_HS_CONSTLEN				0x0000e7c8
 
 #define REG_A5XX_HLSQ_HS_INSTRLEN				0x0000e7c9
 
+#define REG_A5XX_UNKNOWN_E7CA					0x0000e7ca
+
 #define REG_A5XX_HLSQ_DS_CONSTLEN				0x0000e7cd
 
 #define REG_A5XX_HLSQ_DS_INSTRLEN				0x0000e7ce
@@ -3479,13 +4458,23 @@ static inline uint32_t A5XX_HLSQ_CS_CNTL_INSTRLEN(uint32_t val)
 
 #define REG_A5XX_UNKNOWN_E7D4					0x0000e7d4
 
+#define REG_A5XX_HLSQ_FS_CONSTLEN				0x0000e7d7
+
+#define REG_A5XX_HLSQ_FS_INSTRLEN				0x0000e7d8
+
 #define REG_A5XX_UNKNOWN_E7D9					0x0000e7d9
 
-#define REG_A5XX_HLSQ_CONTEXT_SWITCH_CS_SW_3			0x0000e7dc
+#define REG_A5XX_HLSQ_CS_CONSTLEN				0x0000e7dc
+
+#define REG_A5XX_HLSQ_CS_INSTRLEN				0x0000e7dd
+
+#define REG_A5XX_RB_2D_SRC_SOLID_DW0				0x00002101
 
-#define REG_A5XX_HLSQ_CONTEXT_SWITCH_CS_SW_4			0x0000e7dd
+#define REG_A5XX_RB_2D_SRC_SOLID_DW1				0x00002102
 
-#define REG_A5XX_RB_2D_DST_FILL					0x00002101
+#define REG_A5XX_RB_2D_SRC_SOLID_DW2				0x00002103
+
+#define REG_A5XX_RB_2D_SRC_SOLID_DW3				0x00002104
 
 #define REG_A5XX_RB_2D_SRC_INFO					0x00002107
 #define A5XX_RB_2D_SRC_INFO_COLOR_FORMAT__MASK			0x000000ff
@@ -3505,6 +4494,20 @@ static inline uint32_t A5XX_RB_2D_SRC_INFO_COLOR_SWAP(enum a3xx_color_swap val)
 
 #define REG_A5XX_RB_2D_SRC_HI					0x00002109
 
+#define REG_A5XX_RB_2D_SRC_SIZE					0x0000210a
+#define A5XX_RB_2D_SRC_SIZE_PITCH__MASK				0x0000ffff
+#define A5XX_RB_2D_SRC_SIZE_PITCH__SHIFT			0
+static inline uint32_t A5XX_RB_2D_SRC_SIZE_PITCH(uint32_t val)
+{
+	return ((val >> 6) << A5XX_RB_2D_SRC_SIZE_PITCH__SHIFT) & A5XX_RB_2D_SRC_SIZE_PITCH__MASK;
+}
+#define A5XX_RB_2D_SRC_SIZE_ARRAY_PITCH__MASK			0xffff0000
+#define A5XX_RB_2D_SRC_SIZE_ARRAY_PITCH__SHIFT			16
+static inline uint32_t A5XX_RB_2D_SRC_SIZE_ARRAY_PITCH(uint32_t val)
+{
+	return ((val >> 6) << A5XX_RB_2D_SRC_SIZE_ARRAY_PITCH__SHIFT) & A5XX_RB_2D_SRC_SIZE_ARRAY_PITCH__MASK;
+}
+
 #define REG_A5XX_RB_2D_DST_INFO					0x00002110
 #define A5XX_RB_2D_DST_INFO_COLOR_FORMAT__MASK			0x000000ff
 #define A5XX_RB_2D_DST_INFO_COLOR_FORMAT__SHIFT			0
@@ -3519,14 +4522,28 @@ static inline uint32_t A5XX_RB_2D_DST_INFO_COLOR_SWAP(enum a3xx_color_swap val)
 	return ((val) << A5XX_RB_2D_DST_INFO_COLOR_SWAP__SHIFT) & A5XX_RB_2D_DST_INFO_COLOR_SWAP__MASK;
 }
 
-#define REG_A5XX_RB_2D_SRC_FLAGS_LO				0x00002140
-
-#define REG_A5XX_RB_2D_SRC_FLAGS_HI				0x00002141
-
 #define REG_A5XX_RB_2D_DST_LO					0x00002111
 
 #define REG_A5XX_RB_2D_DST_HI					0x00002112
 
+#define REG_A5XX_RB_2D_DST_SIZE					0x00002113
+#define A5XX_RB_2D_DST_SIZE_PITCH__MASK				0x0000ffff
+#define A5XX_RB_2D_DST_SIZE_PITCH__SHIFT			0
+static inline uint32_t A5XX_RB_2D_DST_SIZE_PITCH(uint32_t val)
+{
+	return ((val >> 6) << A5XX_RB_2D_DST_SIZE_PITCH__SHIFT) & A5XX_RB_2D_DST_SIZE_PITCH__MASK;
+}
+#define A5XX_RB_2D_DST_SIZE_ARRAY_PITCH__MASK			0xffff0000
+#define A5XX_RB_2D_DST_SIZE_ARRAY_PITCH__SHIFT			16
+static inline uint32_t A5XX_RB_2D_DST_SIZE_ARRAY_PITCH(uint32_t val)
+{
+	return ((val >> 6) << A5XX_RB_2D_DST_SIZE_ARRAY_PITCH__SHIFT) & A5XX_RB_2D_DST_SIZE_ARRAY_PITCH__MASK;
+}
+
+#define REG_A5XX_RB_2D_SRC_FLAGS_LO				0x00002140
+
+#define REG_A5XX_RB_2D_SRC_FLAGS_HI				0x00002141
+
 #define REG_A5XX_RB_2D_DST_FLAGS_LO				0x00002143
 
 #define REG_A5XX_RB_2D_DST_FLAGS_HI				0x00002144
@@ -3559,6 +4576,12 @@ static inline uint32_t A5XX_GRAS_2D_DST_INFO_COLOR_SWAP(enum a3xx_color_swap val
 	return ((val) << A5XX_GRAS_2D_DST_INFO_COLOR_SWAP__SHIFT) & A5XX_GRAS_2D_DST_INFO_COLOR_SWAP__MASK;
 }
 
+#define REG_A5XX_UNKNOWN_2100					0x00002100
+
+#define REG_A5XX_UNKNOWN_2180					0x00002180
+
+#define REG_A5XX_UNKNOWN_2184					0x00002184
+
 #define REG_A5XX_TEX_SAMP_0					0x00000000
 #define A5XX_TEX_SAMP_0_MIPFILTER_LINEAR_NEAR			0x00000001
 #define A5XX_TEX_SAMP_0_XY_MAG__MASK				0x00000006
@@ -3628,6 +4651,12 @@ static inline uint32_t A5XX_TEX_SAMP_1_MIN_LOD(float val)
 }
 
 #define REG_A5XX_TEX_SAMP_2					0x00000002
+#define A5XX_TEX_SAMP_2_BCOLOR_OFFSET__MASK			0xfffffff0
+#define A5XX_TEX_SAMP_2_BCOLOR_OFFSET__SHIFT			4
+static inline uint32_t A5XX_TEX_SAMP_2_BCOLOR_OFFSET(uint32_t val)
+{
+	return ((val) << A5XX_TEX_SAMP_2_BCOLOR_OFFSET__SHIFT) & A5XX_TEX_SAMP_2_BCOLOR_OFFSET__MASK;
+}
 
 #define REG_A5XX_TEX_SAMP_3					0x00000003
 
@@ -3663,6 +4692,12 @@ static inline uint32_t A5XX_TEX_CONST_0_SWIZ_W(enum a5xx_tex_swiz val)
 {
 	return ((val) << A5XX_TEX_CONST_0_SWIZ_W__SHIFT) & A5XX_TEX_CONST_0_SWIZ_W__MASK;
 }
+#define A5XX_TEX_CONST_0_MIPLVLS__MASK				0x000f0000
+#define A5XX_TEX_CONST_0_MIPLVLS__SHIFT				16
+static inline uint32_t A5XX_TEX_CONST_0_MIPLVLS(uint32_t val)
+{
+	return ((val) << A5XX_TEX_CONST_0_MIPLVLS__SHIFT) & A5XX_TEX_CONST_0_MIPLVLS__MASK;
+}
 #define A5XX_TEX_CONST_0_FMT__MASK				0x3fc00000
 #define A5XX_TEX_CONST_0_FMT__SHIFT				22
 static inline uint32_t A5XX_TEX_CONST_0_FMT(enum a5xx_tex_fmt val)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 31a9bceed32c..b4b54f1c24bc 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -11,6 +11,12 @@
  *
  */
 
+#include <linux/types.h>
+#include <linux/cpumask.h>
+#include <linux/qcom_scm.h>
+#include <linux/dma-mapping.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/soc/qcom/mdt_loader.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "a5xx_gpu.h"
@@ -18,6 +24,62 @@
 extern bool hang_debug;
 static void a5xx_dump(struct msm_gpu *gpu);
 
+#define GPU_PAS_ID 13
+
+#if IS_ENABLED(CONFIG_QCOM_MDT_LOADER)
+
+static int zap_shader_load_mdt(struct device *dev, const char *fwname)
+{
+	const struct firmware *fw;
+	phys_addr_t mem_phys;
+	ssize_t mem_size;
+	void *mem_region = NULL;
+	int ret;
+
+	/* Request the MDT file for the firmware */
+	ret = request_firmware(&fw, fwname, dev);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname);
+		return ret;
+	}
+
+	/* Figure out how much memory we need */
+	mem_size = qcom_mdt_get_size(fw);
+	if (mem_size < 0) {
+		ret = mem_size;
+		goto out;
+	}
+
+	/* Allocate memory for the firmware image */
+	mem_region = dmam_alloc_coherent(dev, mem_size, &mem_phys, GFP_KERNEL);
+	if (!mem_region) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Load the rest of the MDT */
+	ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, mem_region, mem_phys,
+		mem_size);
+	if (ret)
+		goto out;
+
+	/* Send the image to the secure world */
+	ret = qcom_scm_pas_auth_and_reset(GPU_PAS_ID);
+	if (ret)
+		DRM_DEV_ERROR(dev, "Unable to authorize the image\n");
+
+out:
+	release_firmware(fw);
+
+	return ret;
+}
+#else
+static int zap_shader_load_mdt(struct device *dev, const char *fwname)
+{
+	return -ENODEV;
+}
+#endif
+
 static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	struct msm_file_private *ctx)
 {
@@ -225,7 +287,7 @@ static int a5xx_me_init(struct msm_gpu *gpu)
 
 	gpu->funcs->flush(gpu);
 
-	return gpu->funcs->idle(gpu) ? 0 : -EINVAL;
+	return a5xx_idle(gpu) ? 0 : -EINVAL;
 }
 
 static struct drm_gem_object *a5xx_ucode_load_bo(struct msm_gpu *gpu,
@@ -235,24 +297,21 @@ static struct drm_gem_object *a5xx_ucode_load_bo(struct msm_gpu *gpu,
 	struct drm_gem_object *bo;
 	void *ptr;
 
-	mutex_lock(&drm->struct_mutex);
-	bo = msm_gem_new(drm, fw->size - 4, MSM_BO_UNCACHED);
-	mutex_unlock(&drm->struct_mutex);
-
+	bo = msm_gem_new_locked(drm, fw->size - 4, MSM_BO_UNCACHED);
 	if (IS_ERR(bo))
 		return bo;
 
 	ptr = msm_gem_get_vaddr(bo);
 	if (!ptr) {
-		drm_gem_object_unreference_unlocked(bo);
+		drm_gem_object_unreference(bo);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	if (iova) {
-		int ret = msm_gem_get_iova(bo, gpu->id, iova);
+		int ret = msm_gem_get_iova(bo, gpu->aspace, iova);
 
 		if (ret) {
-			drm_gem_object_unreference_unlocked(bo);
+			drm_gem_object_unreference(bo);
 			return ERR_PTR(ret);
 		}
 	}
@@ -304,6 +363,98 @@ static int a5xx_ucode_init(struct msm_gpu *gpu)
 	return 0;
 }
 
+#define SCM_GPU_ZAP_SHADER_RESUME 0
+
+static int a5xx_zap_shader_resume(struct msm_gpu *gpu)
+{
+	int ret;
+
+	ret = qcom_scm_set_remote_state(SCM_GPU_ZAP_SHADER_RESUME, GPU_PAS_ID);
+	if (ret)
+		DRM_ERROR("%s: zap-shader resume failed: %d\n",
+			gpu->name, ret);
+
+	return ret;
+}
+
+/* Set up a child device to "own" the zap shader */
+static int a5xx_zap_shader_dev_init(struct device *parent, struct device *dev)
+{
+	struct device_node *node;
+	int ret;
+
+	if (dev->parent)
+		return 0;
+
+	/* Find the sub-node for the zap shader */
+	node = of_get_child_by_name(parent->of_node, "zap-shader");
+	if (!node) {
+		DRM_DEV_ERROR(parent, "zap-shader not found in device tree\n");
+		return -ENODEV;
+	}
+
+	dev->parent = parent;
+	dev->of_node = node;
+	dev_set_name(dev, "adreno_zap_shader");
+
+	ret = device_register(dev);
+	if (ret) {
+		DRM_DEV_ERROR(parent, "Couldn't register zap shader device\n");
+		goto out;
+	}
+
+	ret = of_reserved_mem_device_init(dev);
+	if (ret) {
+		DRM_DEV_ERROR(parent, "Unable to set up the reserved memory\n");
+		device_unregister(dev);
+	}
+
+out:
+	if (ret)
+		dev->parent = NULL;
+
+	return ret;
+}
+
+static int a5xx_zap_shader_init(struct msm_gpu *gpu)
+{
+	static bool loaded;
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+	struct platform_device *pdev = a5xx_gpu->pdev;
+	int ret;
+
+	/*
+	 * If the zap shader is already loaded into memory we just need to kick
+	 * the remote processor to reinitialize it
+	 */
+	if (loaded)
+		return a5xx_zap_shader_resume(gpu);
+
+	/* We need SCM to be able to load the firmware */
+	if (!qcom_scm_is_available()) {
+		DRM_DEV_ERROR(&pdev->dev, "SCM is not available\n");
+		return -EPROBE_DEFER;
+	}
+
+	/* Each GPU has a target specific zap shader firmware name to use */
+	if (!adreno_gpu->info->zapfw) {
+		DRM_DEV_ERROR(&pdev->dev,
+			"Zap shader firmware file not specified for this target\n");
+		return -ENODEV;
+	}
+
+	ret = a5xx_zap_shader_dev_init(&pdev->dev, &a5xx_gpu->zap_dev);
+
+	if (!ret)
+		ret = zap_shader_load_mdt(&a5xx_gpu->zap_dev,
+			adreno_gpu->info->zapfw);
+
+	loaded = !ret;
+
+	return ret;
+}
+
 #define A5XX_INT_MASK (A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR | \
 	  A5XX_RBBM_INT_0_MASK_RBBM_TRANSFER_TIMEOUT | \
 	  A5XX_RBBM_INT_0_MASK_RBBM_ME_MS_TIMEOUT | \
@@ -484,12 +635,31 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		OUT_RING(gpu->rb, 0x0F);
 
 		gpu->funcs->flush(gpu);
-		if (!gpu->funcs->idle(gpu))
+		if (!a5xx_idle(gpu))
 			return -EINVAL;
 	}
 
-	/* Put the GPU into unsecure mode */
-	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	/*
+	 * Try to load a zap shader into the secure world. If successful
+	 * we can use the CP to switch out of secure mode. If not then we
+	 * have no resource but to try to switch ourselves out manually. If we
+	 * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will
+	 * be blocked and a permissions violation will soon follow.
+	 */
+	ret = a5xx_zap_shader_init(gpu);
+	if (!ret) {
+		OUT_PKT7(gpu->rb, CP_SET_SECURE_MODE, 1);
+		OUT_RING(gpu->rb, 0x00000000);
+
+		gpu->funcs->flush(gpu);
+		if (!a5xx_idle(gpu))
+			return -EINVAL;
+	} else {
+		/* Print a warning so if we die, we know why */
+		dev_warn_once(gpu->dev->dev,
+			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
+		gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	}
 
 	return 0;
 }
@@ -521,21 +691,24 @@ static void a5xx_destroy(struct msm_gpu *gpu)
 
 	DBG("%s", gpu->name);
 
+	if (a5xx_gpu->zap_dev.parent)
+		device_unregister(&a5xx_gpu->zap_dev);
+
 	if (a5xx_gpu->pm4_bo) {
 		if (a5xx_gpu->pm4_iova)
-			msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->id);
+			msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace);
 		drm_gem_object_unreference_unlocked(a5xx_gpu->pm4_bo);
 	}
 
 	if (a5xx_gpu->pfp_bo) {
 		if (a5xx_gpu->pfp_iova)
-			msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->id);
+			msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->aspace);
 		drm_gem_object_unreference_unlocked(a5xx_gpu->pfp_bo);
 	}
 
 	if (a5xx_gpu->gpmu_bo) {
 		if (a5xx_gpu->gpmu_iova)
-			msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->id);
+			msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->aspace);
 		drm_gem_object_unreference_unlocked(a5xx_gpu->gpmu_bo);
 	}
 
@@ -556,7 +729,7 @@ static inline bool _a5xx_check_idle(struct msm_gpu *gpu)
 		A5XX_RBBM_INT_0_MASK_MISC_HANG_DETECT);
 }
 
-static bool a5xx_idle(struct msm_gpu *gpu)
+bool a5xx_idle(struct msm_gpu *gpu)
 {
 	/* wait for CP to drain ringbuffer: */
 	if (!adreno_idle(gpu))
@@ -861,7 +1034,6 @@ static const struct adreno_gpu_funcs funcs = {
 		.last_fence = adreno_last_fence,
 		.submit = a5xx_submit,
 		.flush = adreno_flush,
-		.idle = a5xx_idle,
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
index 1590f845d554..6638bc85645d 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
@@ -36,6 +36,8 @@ struct a5xx_gpu {
 	uint32_t gpmu_dwords;
 
 	uint32_t lm_leakage;
+
+	struct device zap_dev;
 };
 
 #define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base)
@@ -56,5 +58,6 @@ static inline int spin_usecs(struct msm_gpu *gpu, uint32_t usecs,
 	return -ETIMEDOUT;
 }
 
+bool a5xx_idle(struct msm_gpu *gpu);
 
 #endif /* __A5XX_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index 72d52c71f769..87af6eea0483 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -194,7 +194,7 @@ static int a5xx_gpmu_init(struct msm_gpu *gpu)
 
 	gpu->funcs->flush(gpu);
 
-	if (!gpu->funcs->idle(gpu)) {
+	if (!a5xx_idle(gpu)) {
 		DRM_ERROR("%s: Unable to load GPMU firmware. GPMU will not be active\n",
 			gpu->name);
 		return -EINVAL;
@@ -294,14 +294,12 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	 */
 	bosize = (cmds_size + (cmds_size / TYPE4_MAX_PAYLOAD) + 1) << 2;
 
-	mutex_lock(&drm->struct_mutex);
-	a5xx_gpu->gpmu_bo = msm_gem_new(drm, bosize, MSM_BO_UNCACHED);
-	mutex_unlock(&drm->struct_mutex);
-
+	a5xx_gpu->gpmu_bo = msm_gem_new_locked(drm, bosize, MSM_BO_UNCACHED);
 	if (IS_ERR(a5xx_gpu->gpmu_bo))
 		goto err;
 
-	if (msm_gem_get_iova(a5xx_gpu->gpmu_bo, gpu->id, &a5xx_gpu->gpmu_iova))
+	if (msm_gem_get_iova(a5xx_gpu->gpmu_bo, gpu->aspace,
+			&a5xx_gpu->gpmu_iova))
 		goto err;
 
 	ptr = msm_gem_get_vaddr(a5xx_gpu->gpmu_bo);
@@ -330,9 +328,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 
 err:
 	if (a5xx_gpu->gpmu_iova)
-		msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->id);
+		msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->aspace);
 	if (a5xx_gpu->gpmu_bo)
-		drm_gem_object_unreference_unlocked(a5xx_gpu->gpmu_bo);
+		drm_gem_object_unreference(a5xx_gpu->gpmu_bo);
 
 	a5xx_gpu->gpmu_bo = NULL;
 	a5xx_gpu->gpmu_iova = 0;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
index 4a33ba6f1244..b634cf71352b 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
@@ -8,17 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2016-04-26 17:56:44)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32907 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  12025 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  22544 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 110765 bytes, from 2016-11-26 23:01:48)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          (  90321 bytes, from 2016-11-28 16:50:05)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2015-09-24 17:30:00)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  37162 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  13324 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  31866 bytes, from 2017-06-06 18:26:14)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 111898 bytes, from 2017-06-06 18:23:59)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          ( 139480 bytes, from 2017-06-16 12:44:39)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -421,6 +421,35 @@ static inline uint32_t AXXX_CP_CSQ_IB2_STAT_WPTR(uint32_t val)
 #define REG_AXXX_CP_IB2_BUFSZ					0x0000045b
 
 #define REG_AXXX_CP_STAT					0x0000047f
+#define AXXX_CP_STAT_CP_BUSY					0x80000000
+#define AXXX_CP_STAT_VS_EVENT_FIFO_BUSY				0x40000000
+#define AXXX_CP_STAT_PS_EVENT_FIFO_BUSY				0x20000000
+#define AXXX_CP_STAT_CF_EVENT_FIFO_BUSY				0x10000000
+#define AXXX_CP_STAT_RB_EVENT_FIFO_BUSY				0x08000000
+#define AXXX_CP_STAT_ME_BUSY					0x04000000
+#define AXXX_CP_STAT_MIU_WR_C_BUSY				0x02000000
+#define AXXX_CP_STAT_CP_3D_BUSY					0x00800000
+#define AXXX_CP_STAT_CP_NRT_BUSY				0x00400000
+#define AXXX_CP_STAT_RBIU_SCRATCH_BUSY				0x00200000
+#define AXXX_CP_STAT_RCIU_ME_BUSY				0x00100000
+#define AXXX_CP_STAT_RCIU_PFP_BUSY				0x00080000
+#define AXXX_CP_STAT_MEQ_RING_BUSY				0x00040000
+#define AXXX_CP_STAT_PFP_BUSY					0x00020000
+#define AXXX_CP_STAT_ST_QUEUE_BUSY				0x00010000
+#define AXXX_CP_STAT_INDIRECT2_QUEUE_BUSY			0x00002000
+#define AXXX_CP_STAT_INDIRECTS_QUEUE_BUSY			0x00001000
+#define AXXX_CP_STAT_RING_QUEUE_BUSY				0x00000800
+#define AXXX_CP_STAT_CSF_BUSY					0x00000400
+#define AXXX_CP_STAT_CSF_ST_BUSY				0x00000200
+#define AXXX_CP_STAT_EVENT_BUSY					0x00000100
+#define AXXX_CP_STAT_CSF_INDIRECT2_BUSY				0x00000080
+#define AXXX_CP_STAT_CSF_INDIRECTS_BUSY				0x00000040
+#define AXXX_CP_STAT_CSF_RING_BUSY				0x00000020
+#define AXXX_CP_STAT_RCIU_BUSY					0x00000010
+#define AXXX_CP_STAT_RBIU_BUSY					0x00000008
+#define AXXX_CP_STAT_MIU_RD_RETURN_BUSY				0x00000004
+#define AXXX_CP_STAT_MIU_RD_REQ_BUSY				0x00000002
+#define AXXX_CP_STAT_MIU_WR_BUSY				0x00000001
 
 #define REG_AXXX_CP_SCRATCH_REG0				0x00000578
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index c0fa5d1c75ff..c75c4df4bc39 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -86,6 +86,7 @@ static const struct adreno_info gpulist[] = {
 			ADRENO_QUIRK_FAULT_DETECT_MASK,
 		.init = a5xx_gpu_init,
 		.gpmufw = "a530v3_gpmu.fw2",
+		.zapfw = "a530_zap.mdt",
 	},
 };
 
@@ -158,7 +159,9 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 		int ret;
 
 		pm_runtime_get_sync(&pdev->dev);
+		mutex_lock(&dev->struct_mutex);
 		ret = msm_gpu_hw_init(gpu);
+		mutex_unlock(&dev->struct_mutex);
 		pm_runtime_put_sync(&pdev->dev);
 		if (ret) {
 			dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 5b63fc649dcc..f1ab2703674a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -64,7 +64,7 @@ int adreno_hw_init(struct msm_gpu *gpu)
 
 	DBG("%s", gpu->name);
 
-	ret = msm_gem_get_iova(gpu->rb->bo, gpu->id, &gpu->rb_iova);
+	ret = msm_gem_get_iova(gpu->rb->bo, gpu->aspace, &gpu->rb_iova);
 	if (ret) {
 		gpu->rb_iova = 0;
 		dev_err(gpu->dev->dev, "could not map ringbuffer: %d\n", ret);
@@ -77,7 +77,6 @@ int adreno_hw_init(struct msm_gpu *gpu)
 	/* reset completed fence seqno: */
 	adreno_gpu->memptrs->fence = gpu->fctx->completed_fence;
 	adreno_gpu->memptrs->rptr  = 0;
-	adreno_gpu->memptrs->wptr  = 0;
 
 	/* Setup REG_CP_RB_CNTL: */
 	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
@@ -258,7 +257,6 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 	seq_printf(m, "fence:    %d/%d\n", adreno_gpu->memptrs->fence,
 			gpu->fctx->last_fence);
 	seq_printf(m, "rptr:     %d\n", get_rptr(adreno_gpu));
-	seq_printf(m, "wptr:     %d\n", adreno_gpu->memptrs->wptr);
 	seq_printf(m, "rb wptr:  %d\n", get_wptr(gpu->rb));
 
 	/* dump these out in a form that can be parsed by demsm: */
@@ -294,7 +292,6 @@ void adreno_dump_info(struct msm_gpu *gpu)
 	printk("fence:    %d/%d\n", adreno_gpu->memptrs->fence,
 			gpu->fctx->last_fence);
 	printk("rptr:     %d\n", get_rptr(adreno_gpu));
-	printk("wptr:     %d\n", adreno_gpu->memptrs->wptr);
 	printk("rb wptr:  %d\n", get_wptr(gpu->rb));
 }
 
@@ -342,6 +339,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs)
 {
 	struct adreno_platform_config *config = pdev->dev.platform_data;
+	struct msm_gpu_config adreno_gpu_config  = { 0 };
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	int ret;
 
@@ -360,9 +358,16 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	DBG("fast_rate=%u, slow_rate=27000000, bus_freq=%u",
 			gpu->fast_rate, gpu->bus_freq);
 
+	adreno_gpu_config.ioname = "kgsl_3d0_reg_memory";
+	adreno_gpu_config.irqname = "kgsl_3d0_irq";
+
+	adreno_gpu_config.va_start = SZ_16M;
+	adreno_gpu_config.va_end = 0xffffffff;
+
+	adreno_gpu_config.ringsz = RB_SIZE;
+
 	ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
-			adreno_gpu->info->name, "kgsl_3d0_reg_memory", "kgsl_3d0_irq",
-			RB_SIZE);
+			adreno_gpu->info->name, &adreno_gpu_config);
 	if (ret)
 		return ret;
 
@@ -392,10 +397,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 			return ret;
 	}
 
-	mutex_lock(&drm->struct_mutex);
 	adreno_gpu->memptrs_bo = msm_gem_new(drm, sizeof(*adreno_gpu->memptrs),
 			MSM_BO_UNCACHED);
-	mutex_unlock(&drm->struct_mutex);
 	if (IS_ERR(adreno_gpu->memptrs_bo)) {
 		ret = PTR_ERR(adreno_gpu->memptrs_bo);
 		adreno_gpu->memptrs_bo = NULL;
@@ -409,7 +412,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		return -ENOMEM;
 	}
 
-	ret = msm_gem_get_iova(adreno_gpu->memptrs_bo, gpu->id,
+	ret = msm_gem_get_iova(adreno_gpu->memptrs_bo, gpu->aspace,
 			&adreno_gpu->memptrs_iova);
 	if (ret) {
 		dev_err(drm->dev, "could not map memptrs: %d\n", ret);
@@ -428,7 +431,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 			msm_gem_put_vaddr(adreno_gpu->memptrs_bo);
 
 		if (adreno_gpu->memptrs_iova)
-			msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->id);
+			msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->aspace);
 
 		drm_gem_object_unreference_unlocked(adreno_gpu->memptrs_bo);
 	}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index fb4831f9f80b..4d9165f29f43 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -77,6 +77,7 @@ struct adreno_info {
 	uint32_t gmem;
 	enum adreno_quirks quirks;
 	struct msm_gpu *(*init)(struct drm_device *dev);
+	const char *zapfw;
 };
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);
@@ -86,7 +87,6 @@ const struct adreno_info *adreno_info(struct adreno_rev rev);
 
 struct adreno_rbmemptrs {
 	volatile uint32_t rptr;
-	volatile uint32_t wptr;
 	volatile uint32_t fence;
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
index 6a2930e75503..fb605a3534cf 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
@@ -8,17 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2016-04-26 17:56:44)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32907 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  12025 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  22544 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 110765 bytes, from 2016-11-26 23:01:48)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          (  90321 bytes, from 2016-11-28 16:50:05)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2015-09-24 17:30:00)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml               (    431 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  37162 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (  13324 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  31866 bytes, from 2017-06-06 18:26:14)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          ( 111898 bytes, from 2017-06-06 18:23:59)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a5xx.xml          ( 139480 bytes, from 2017-06-16 12:44:39)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -67,10 +67,18 @@ enum vgt_event_type {
 	PERFCOUNTER_STOP = 24,
 	VS_FETCH_DONE = 27,
 	FACENESS_FLUSH = 28,
+	FLUSH_SO_0 = 17,
+	FLUSH_SO_1 = 18,
+	FLUSH_SO_2 = 19,
+	FLUSH_SO_3 = 20,
+	UNK_19 = 25,
 	UNK_1C = 28,
 	UNK_1D = 29,
 	BLIT = 30,
-	UNK_26 = 38,
+	UNK_25 = 37,
+	LRZ_FLUSH = 38,
+	UNK_2C = 44,
+	UNK_2D = 45,
 };
 
 enum pc_di_primtype {
@@ -134,11 +142,13 @@ enum adreno_pm4_type3_packets {
 	CP_WAIT_IB_PFD_COMPLETE = 93,
 	CP_REG_RMW = 33,
 	CP_SET_BIN_DATA = 47,
+	CP_SET_BIN_DATA5 = 47,
 	CP_REG_TO_MEM = 62,
 	CP_MEM_WRITE = 61,
 	CP_MEM_WRITE_CNTR = 79,
 	CP_COND_EXEC = 68,
 	CP_COND_WRITE = 69,
+	CP_COND_WRITE5 = 69,
 	CP_EVENT_WRITE = 70,
 	CP_EVENT_WRITE_SHD = 88,
 	CP_EVENT_WRITE_CFL = 89,
@@ -165,6 +175,7 @@ enum adreno_pm4_type3_packets {
 	CP_SET_PROTECTED_MODE = 95,
 	CP_BOOTSTRAP_UCODE = 111,
 	CP_LOAD_STATE = 48,
+	CP_LOAD_STATE4 = 48,
 	CP_COND_INDIRECT_BUFFER_PFE = 58,
 	CP_COND_INDIRECT_BUFFER_PFD = 50,
 	CP_INDIRECT_BUFFER_PFE = 63,
@@ -204,6 +215,7 @@ enum adreno_pm4_type3_packets {
 	CP_COMPUTE_CHECKPOINT = 110,
 	CP_MEM_TO_MEM = 115,
 	CP_BLIT = 44,
+	CP_UNK_39 = 57,
 	IN_IB_PREFETCH_END = 23,
 	IN_SUBBLK_PREFETCH = 31,
 	IN_INSTR_PREFETCH = 32,
@@ -239,21 +251,61 @@ enum adreno_state_src {
 	SS_INDIRECT_STM = 6,
 };
 
+enum a4xx_state_block {
+	SB4_VS_TEX = 0,
+	SB4_HS_TEX = 1,
+	SB4_DS_TEX = 2,
+	SB4_GS_TEX = 3,
+	SB4_FS_TEX = 4,
+	SB4_CS_TEX = 5,
+	SB4_VS_SHADER = 8,
+	SB4_HS_SHADER = 9,
+	SB4_DS_SHADER = 10,
+	SB4_GS_SHADER = 11,
+	SB4_FS_SHADER = 12,
+	SB4_CS_SHADER = 13,
+	SB4_SSBO = 14,
+	SB4_CS_SSBO = 15,
+};
+
+enum a4xx_state_type {
+	ST4_SHADER = 0,
+	ST4_CONSTANTS = 1,
+};
+
+enum a4xx_state_src {
+	SS4_DIRECT = 0,
+	SS4_INDIRECT = 2,
+};
+
 enum a4xx_index_size {
 	INDEX4_SIZE_8_BIT = 0,
 	INDEX4_SIZE_16_BIT = 1,
 	INDEX4_SIZE_32_BIT = 2,
 };
 
+enum cp_cond_function {
+	WRITE_ALWAYS = 0,
+	WRITE_LT = 1,
+	WRITE_LE = 2,
+	WRITE_EQ = 3,
+	WRITE_NE = 4,
+	WRITE_GE = 5,
+	WRITE_GT = 6,
+};
+
 enum render_mode_cmd {
 	BYPASS = 1,
+	BINNING = 2,
 	GMEM = 3,
 	BLIT2D = 5,
+	BLIT2DSCALE = 7,
 };
 
 enum cp_blit_cmd {
 	BLIT_OP_FILL = 0,
-	BLIT_OP_BLIT = 1,
+	BLIT_OP_COPY = 1,
+	BLIT_OP_SCALE = 3,
 };
 
 #define REG_CP_LOAD_STATE_0					0x00000000
@@ -296,12 +348,52 @@ static inline uint32_t CP_LOAD_STATE_1_EXT_SRC_ADDR(uint32_t val)
 	return ((val >> 2) << CP_LOAD_STATE_1_EXT_SRC_ADDR__SHIFT) & CP_LOAD_STATE_1_EXT_SRC_ADDR__MASK;
 }
 
-#define REG_CP_LOAD_STATE_2					0x00000002
-#define CP_LOAD_STATE_2_EXT_SRC_ADDR_HI__MASK			0xffffffff
-#define CP_LOAD_STATE_2_EXT_SRC_ADDR_HI__SHIFT			0
-static inline uint32_t CP_LOAD_STATE_2_EXT_SRC_ADDR_HI(uint32_t val)
+#define REG_CP_LOAD_STATE4_0					0x00000000
+#define CP_LOAD_STATE4_0_DST_OFF__MASK				0x0000ffff
+#define CP_LOAD_STATE4_0_DST_OFF__SHIFT				0
+static inline uint32_t CP_LOAD_STATE4_0_DST_OFF(uint32_t val)
+{
+	return ((val) << CP_LOAD_STATE4_0_DST_OFF__SHIFT) & CP_LOAD_STATE4_0_DST_OFF__MASK;
+}
+#define CP_LOAD_STATE4_0_STATE_SRC__MASK			0x00030000
+#define CP_LOAD_STATE4_0_STATE_SRC__SHIFT			16
+static inline uint32_t CP_LOAD_STATE4_0_STATE_SRC(enum a4xx_state_src val)
+{
+	return ((val) << CP_LOAD_STATE4_0_STATE_SRC__SHIFT) & CP_LOAD_STATE4_0_STATE_SRC__MASK;
+}
+#define CP_LOAD_STATE4_0_STATE_BLOCK__MASK			0x003c0000
+#define CP_LOAD_STATE4_0_STATE_BLOCK__SHIFT			18
+static inline uint32_t CP_LOAD_STATE4_0_STATE_BLOCK(enum a4xx_state_block val)
+{
+	return ((val) << CP_LOAD_STATE4_0_STATE_BLOCK__SHIFT) & CP_LOAD_STATE4_0_STATE_BLOCK__MASK;
+}
+#define CP_LOAD_STATE4_0_NUM_UNIT__MASK				0xffc00000
+#define CP_LOAD_STATE4_0_NUM_UNIT__SHIFT			22
+static inline uint32_t CP_LOAD_STATE4_0_NUM_UNIT(uint32_t val)
+{
+	return ((val) << CP_LOAD_STATE4_0_NUM_UNIT__SHIFT) & CP_LOAD_STATE4_0_NUM_UNIT__MASK;
+}
+
+#define REG_CP_LOAD_STATE4_1					0x00000001
+#define CP_LOAD_STATE4_1_STATE_TYPE__MASK			0x00000003
+#define CP_LOAD_STATE4_1_STATE_TYPE__SHIFT			0
+static inline uint32_t CP_LOAD_STATE4_1_STATE_TYPE(enum a4xx_state_type val)
+{
+	return ((val) << CP_LOAD_STATE4_1_STATE_TYPE__SHIFT) & CP_LOAD_STATE4_1_STATE_TYPE__MASK;
+}
+#define CP_LOAD_STATE4_1_EXT_SRC_ADDR__MASK			0xfffffffc
+#define CP_LOAD_STATE4_1_EXT_SRC_ADDR__SHIFT			2
+static inline uint32_t CP_LOAD_STATE4_1_EXT_SRC_ADDR(uint32_t val)
+{
+	return ((val >> 2) << CP_LOAD_STATE4_1_EXT_SRC_ADDR__SHIFT) & CP_LOAD_STATE4_1_EXT_SRC_ADDR__MASK;
+}
+
+#define REG_CP_LOAD_STATE4_2					0x00000002
+#define CP_LOAD_STATE4_2_EXT_SRC_ADDR_HI__MASK			0xffffffff
+#define CP_LOAD_STATE4_2_EXT_SRC_ADDR_HI__SHIFT			0
+static inline uint32_t CP_LOAD_STATE4_2_EXT_SRC_ADDR_HI(uint32_t val)
 {
-	return ((val) << CP_LOAD_STATE_2_EXT_SRC_ADDR_HI__SHIFT) & CP_LOAD_STATE_2_EXT_SRC_ADDR_HI__MASK;
+	return ((val) << CP_LOAD_STATE4_2_EXT_SRC_ADDR_HI__SHIFT) & CP_LOAD_STATE4_2_EXT_SRC_ADDR_HI__MASK;
 }
 
 #define REG_CP_DRAW_INDX_0					0x00000000
@@ -570,6 +662,52 @@ static inline uint32_t CP_SET_BIN_DATA_1_BIN_SIZE_ADDRESS(uint32_t val)
 	return ((val) << CP_SET_BIN_DATA_1_BIN_SIZE_ADDRESS__SHIFT) & CP_SET_BIN_DATA_1_BIN_SIZE_ADDRESS__MASK;
 }
 
+#define REG_CP_SET_BIN_DATA5_0					0x00000000
+#define CP_SET_BIN_DATA5_0_VSC_SIZE__MASK			0x003f0000
+#define CP_SET_BIN_DATA5_0_VSC_SIZE__SHIFT			16
+static inline uint32_t CP_SET_BIN_DATA5_0_VSC_SIZE(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_DATA5_0_VSC_SIZE__SHIFT) & CP_SET_BIN_DATA5_0_VSC_SIZE__MASK;
+}
+#define CP_SET_BIN_DATA5_0_VSC_N__MASK				0x07c00000
+#define CP_SET_BIN_DATA5_0_VSC_N__SHIFT				22
+static inline uint32_t CP_SET_BIN_DATA5_0_VSC_N(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_DATA5_0_VSC_N__SHIFT) & CP_SET_BIN_DATA5_0_VSC_N__MASK;
+}
+
+#define REG_CP_SET_BIN_DATA5_1					0x00000001
+#define CP_SET_BIN_DATA5_1_BIN_DATA_ADDR_LO__MASK		0xffffffff
+#define CP_SET_BIN_DATA5_1_BIN_DATA_ADDR_LO__SHIFT		0
+static inline uint32_t CP_SET_BIN_DATA5_1_BIN_DATA_ADDR_LO(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_DATA5_1_BIN_DATA_ADDR_LO__SHIFT) & CP_SET_BIN_DATA5_1_BIN_DATA_ADDR_LO__MASK;
+}
+
+#define REG_CP_SET_BIN_DATA5_2					0x00000002
+#define CP_SET_BIN_DATA5_2_BIN_DATA_ADDR_HI__MASK		0xffffffff
+#define CP_SET_BIN_DATA5_2_BIN_DATA_ADDR_HI__SHIFT		0
+static inline uint32_t CP_SET_BIN_DATA5_2_BIN_DATA_ADDR_HI(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_DATA5_2_BIN_DATA_ADDR_HI__SHIFT) & CP_SET_BIN_DATA5_2_BIN_DATA_ADDR_HI__MASK;
+}
+
+#define REG_CP_SET_BIN_DATA5_3					0x00000003
+#define CP_SET_BIN_DATA5_3_BIN_SIZE_ADDRESS_LO__MASK		0xffffffff
+#define CP_SET_BIN_DATA5_3_BIN_SIZE_ADDRESS_LO__SHIFT		0
+static inline uint32_t CP_SET_BIN_DATA5_3_BIN_SIZE_ADDRESS_LO(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_DATA5_3_BIN_SIZE_ADDRESS_LO__SHIFT) & CP_SET_BIN_DATA5_3_BIN_SIZE_ADDRESS_LO__MASK;
+}
+
+#define REG_CP_SET_BIN_DATA5_4					0x00000004
+#define CP_SET_BIN_DATA5_4_BIN_SIZE_ADDRESS_HI__MASK		0xffffffff
+#define CP_SET_BIN_DATA5_4_BIN_SIZE_ADDRESS_HI__SHIFT		0
+static inline uint32_t CP_SET_BIN_DATA5_4_BIN_SIZE_ADDRESS_HI(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_DATA5_4_BIN_SIZE_ADDRESS_HI__SHIFT) & CP_SET_BIN_DATA5_4_BIN_SIZE_ADDRESS_HI__MASK;
+}
+
 #define REG_CP_REG_TO_MEM_0					0x00000000
 #define CP_REG_TO_MEM_0_REG__MASK				0x0000ffff
 #define CP_REG_TO_MEM_0_REG__SHIFT				0
@@ -594,6 +732,128 @@ static inline uint32_t CP_REG_TO_MEM_1_DEST(uint32_t val)
 	return ((val) << CP_REG_TO_MEM_1_DEST__SHIFT) & CP_REG_TO_MEM_1_DEST__MASK;
 }
 
+#define REG_CP_MEM_TO_MEM_0					0x00000000
+#define CP_MEM_TO_MEM_0_NEG_A					0x00000001
+#define CP_MEM_TO_MEM_0_NEG_B					0x00000002
+#define CP_MEM_TO_MEM_0_NEG_C					0x00000004
+#define CP_MEM_TO_MEM_0_DOUBLE					0x20000000
+
+#define REG_CP_COND_WRITE_0					0x00000000
+#define CP_COND_WRITE_0_FUNCTION__MASK				0x00000007
+#define CP_COND_WRITE_0_FUNCTION__SHIFT				0
+static inline uint32_t CP_COND_WRITE_0_FUNCTION(enum cp_cond_function val)
+{
+	return ((val) << CP_COND_WRITE_0_FUNCTION__SHIFT) & CP_COND_WRITE_0_FUNCTION__MASK;
+}
+#define CP_COND_WRITE_0_POLL_MEMORY				0x00000010
+#define CP_COND_WRITE_0_WRITE_MEMORY				0x00000100
+
+#define REG_CP_COND_WRITE_1					0x00000001
+#define CP_COND_WRITE_1_POLL_ADDR__MASK				0xffffffff
+#define CP_COND_WRITE_1_POLL_ADDR__SHIFT			0
+static inline uint32_t CP_COND_WRITE_1_POLL_ADDR(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE_1_POLL_ADDR__SHIFT) & CP_COND_WRITE_1_POLL_ADDR__MASK;
+}
+
+#define REG_CP_COND_WRITE_2					0x00000002
+#define CP_COND_WRITE_2_REF__MASK				0xffffffff
+#define CP_COND_WRITE_2_REF__SHIFT				0
+static inline uint32_t CP_COND_WRITE_2_REF(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE_2_REF__SHIFT) & CP_COND_WRITE_2_REF__MASK;
+}
+
+#define REG_CP_COND_WRITE_3					0x00000003
+#define CP_COND_WRITE_3_MASK__MASK				0xffffffff
+#define CP_COND_WRITE_3_MASK__SHIFT				0
+static inline uint32_t CP_COND_WRITE_3_MASK(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE_3_MASK__SHIFT) & CP_COND_WRITE_3_MASK__MASK;
+}
+
+#define REG_CP_COND_WRITE_4					0x00000004
+#define CP_COND_WRITE_4_WRITE_ADDR__MASK			0xffffffff
+#define CP_COND_WRITE_4_WRITE_ADDR__SHIFT			0
+static inline uint32_t CP_COND_WRITE_4_WRITE_ADDR(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE_4_WRITE_ADDR__SHIFT) & CP_COND_WRITE_4_WRITE_ADDR__MASK;
+}
+
+#define REG_CP_COND_WRITE_5					0x00000005
+#define CP_COND_WRITE_5_WRITE_DATA__MASK			0xffffffff
+#define CP_COND_WRITE_5_WRITE_DATA__SHIFT			0
+static inline uint32_t CP_COND_WRITE_5_WRITE_DATA(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE_5_WRITE_DATA__SHIFT) & CP_COND_WRITE_5_WRITE_DATA__MASK;
+}
+
+#define REG_CP_COND_WRITE5_0					0x00000000
+#define CP_COND_WRITE5_0_FUNCTION__MASK				0x00000007
+#define CP_COND_WRITE5_0_FUNCTION__SHIFT			0
+static inline uint32_t CP_COND_WRITE5_0_FUNCTION(enum cp_cond_function val)
+{
+	return ((val) << CP_COND_WRITE5_0_FUNCTION__SHIFT) & CP_COND_WRITE5_0_FUNCTION__MASK;
+}
+#define CP_COND_WRITE5_0_POLL_MEMORY				0x00000010
+#define CP_COND_WRITE5_0_WRITE_MEMORY				0x00000100
+
+#define REG_CP_COND_WRITE5_1					0x00000001
+#define CP_COND_WRITE5_1_POLL_ADDR_LO__MASK			0xffffffff
+#define CP_COND_WRITE5_1_POLL_ADDR_LO__SHIFT			0
+static inline uint32_t CP_COND_WRITE5_1_POLL_ADDR_LO(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_1_POLL_ADDR_LO__SHIFT) & CP_COND_WRITE5_1_POLL_ADDR_LO__MASK;
+}
+
+#define REG_CP_COND_WRITE5_2					0x00000002
+#define CP_COND_WRITE5_2_POLL_ADDR_HI__MASK			0xffffffff
+#define CP_COND_WRITE5_2_POLL_ADDR_HI__SHIFT			0
+static inline uint32_t CP_COND_WRITE5_2_POLL_ADDR_HI(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_2_POLL_ADDR_HI__SHIFT) & CP_COND_WRITE5_2_POLL_ADDR_HI__MASK;
+}
+
+#define REG_CP_COND_WRITE5_3					0x00000003
+#define CP_COND_WRITE5_3_REF__MASK				0xffffffff
+#define CP_COND_WRITE5_3_REF__SHIFT				0
+static inline uint32_t CP_COND_WRITE5_3_REF(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_3_REF__SHIFT) & CP_COND_WRITE5_3_REF__MASK;
+}
+
+#define REG_CP_COND_WRITE5_4					0x00000004
+#define CP_COND_WRITE5_4_MASK__MASK				0xffffffff
+#define CP_COND_WRITE5_4_MASK__SHIFT				0
+static inline uint32_t CP_COND_WRITE5_4_MASK(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_4_MASK__SHIFT) & CP_COND_WRITE5_4_MASK__MASK;
+}
+
+#define REG_CP_COND_WRITE5_5					0x00000005
+#define CP_COND_WRITE5_5_WRITE_ADDR_LO__MASK			0xffffffff
+#define CP_COND_WRITE5_5_WRITE_ADDR_LO__SHIFT			0
+static inline uint32_t CP_COND_WRITE5_5_WRITE_ADDR_LO(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_5_WRITE_ADDR_LO__SHIFT) & CP_COND_WRITE5_5_WRITE_ADDR_LO__MASK;
+}
+
+#define REG_CP_COND_WRITE5_6					0x00000006
+#define CP_COND_WRITE5_6_WRITE_ADDR_HI__MASK			0xffffffff
+#define CP_COND_WRITE5_6_WRITE_ADDR_HI__SHIFT			0
+static inline uint32_t CP_COND_WRITE5_6_WRITE_ADDR_HI(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_6_WRITE_ADDR_HI__SHIFT) & CP_COND_WRITE5_6_WRITE_ADDR_HI__MASK;
+}
+
+#define REG_CP_COND_WRITE5_7					0x00000007
+#define CP_COND_WRITE5_7_WRITE_DATA__MASK			0xffffffff
+#define CP_COND_WRITE5_7_WRITE_DATA__SHIFT			0
+static inline uint32_t CP_COND_WRITE5_7_WRITE_DATA(uint32_t val)
+{
+	return ((val) << CP_COND_WRITE5_7_WRITE_DATA__SHIFT) & CP_COND_WRITE5_7_WRITE_DATA__MASK;
+}
+
 #define REG_CP_DISPATCH_COMPUTE_0				0x00000000
 
 #define REG_CP_DISPATCH_COMPUTE_1				0x00000001
@@ -645,6 +905,7 @@ static inline uint32_t CP_SET_RENDER_MODE_2_ADDR_0_HI(uint32_t val)
 }
 
 #define REG_CP_SET_RENDER_MODE_3				0x00000003
+#define CP_SET_RENDER_MODE_3_VSC_ENABLE				0x00000008
 #define CP_SET_RENDER_MODE_3_GMEM_ENABLE			0x00000010
 
 #define REG_CP_SET_RENDER_MODE_4				0x00000004
@@ -673,6 +934,50 @@ static inline uint32_t CP_SET_RENDER_MODE_7_ADDR_1_HI(uint32_t val)
 	return ((val) << CP_SET_RENDER_MODE_7_ADDR_1_HI__SHIFT) & CP_SET_RENDER_MODE_7_ADDR_1_HI__MASK;
 }
 
+#define REG_CP_COMPUTE_CHECKPOINT_0				0x00000000
+#define CP_COMPUTE_CHECKPOINT_0_ADDR_0_LO__MASK			0xffffffff
+#define CP_COMPUTE_CHECKPOINT_0_ADDR_0_LO__SHIFT		0
+static inline uint32_t CP_COMPUTE_CHECKPOINT_0_ADDR_0_LO(uint32_t val)
+{
+	return ((val) << CP_COMPUTE_CHECKPOINT_0_ADDR_0_LO__SHIFT) & CP_COMPUTE_CHECKPOINT_0_ADDR_0_LO__MASK;
+}
+
+#define REG_CP_COMPUTE_CHECKPOINT_1				0x00000001
+#define CP_COMPUTE_CHECKPOINT_1_ADDR_0_HI__MASK			0xffffffff
+#define CP_COMPUTE_CHECKPOINT_1_ADDR_0_HI__SHIFT		0
+static inline uint32_t CP_COMPUTE_CHECKPOINT_1_ADDR_0_HI(uint32_t val)
+{
+	return ((val) << CP_COMPUTE_CHECKPOINT_1_ADDR_0_HI__SHIFT) & CP_COMPUTE_CHECKPOINT_1_ADDR_0_HI__MASK;
+}
+
+#define REG_CP_COMPUTE_CHECKPOINT_2				0x00000002
+
+#define REG_CP_COMPUTE_CHECKPOINT_3				0x00000003
+
+#define REG_CP_COMPUTE_CHECKPOINT_4				0x00000004
+#define CP_COMPUTE_CHECKPOINT_4_ADDR_1_LEN__MASK		0xffffffff
+#define CP_COMPUTE_CHECKPOINT_4_ADDR_1_LEN__SHIFT		0
+static inline uint32_t CP_COMPUTE_CHECKPOINT_4_ADDR_1_LEN(uint32_t val)
+{
+	return ((val) << CP_COMPUTE_CHECKPOINT_4_ADDR_1_LEN__SHIFT) & CP_COMPUTE_CHECKPOINT_4_ADDR_1_LEN__MASK;
+}
+
+#define REG_CP_COMPUTE_CHECKPOINT_5				0x00000005
+#define CP_COMPUTE_CHECKPOINT_5_ADDR_1_LO__MASK			0xffffffff
+#define CP_COMPUTE_CHECKPOINT_5_ADDR_1_LO__SHIFT		0
+static inline uint32_t CP_COMPUTE_CHECKPOINT_5_ADDR_1_LO(uint32_t val)
+{
+	return ((val) << CP_COMPUTE_CHECKPOINT_5_ADDR_1_LO__SHIFT) & CP_COMPUTE_CHECKPOINT_5_ADDR_1_LO__MASK;
+}
+
+#define REG_CP_COMPUTE_CHECKPOINT_6				0x00000006
+#define CP_COMPUTE_CHECKPOINT_6_ADDR_1_HI__MASK			0xffffffff
+#define CP_COMPUTE_CHECKPOINT_6_ADDR_1_HI__SHIFT		0
+static inline uint32_t CP_COMPUTE_CHECKPOINT_6_ADDR_1_HI(uint32_t val)
+{
+	return ((val) << CP_COMPUTE_CHECKPOINT_6_ADDR_1_HI__SHIFT) & CP_COMPUTE_CHECKPOINT_6_ADDR_1_HI__MASK;
+}
+
 #define REG_CP_PERFCOUNTER_ACTION_0				0x00000000
 
 #define REG_CP_PERFCOUNTER_ACTION_1				0x00000001
@@ -698,6 +1003,7 @@ static inline uint32_t CP_EVENT_WRITE_0_EVENT(enum vgt_event_type val)
 {
 	return ((val) << CP_EVENT_WRITE_0_EVENT__SHIFT) & CP_EVENT_WRITE_0_EVENT__MASK;
 }
+#define CP_EVENT_WRITE_0_TIMESTAMP				0x40000000
 
 #define REG_CP_EVENT_WRITE_1					0x00000001
 #define CP_EVENT_WRITE_1_ADDR_0_LO__MASK			0xffffffff
@@ -781,5 +1087,31 @@ static inline uint32_t CP_BLIT_4_DST_Y2(uint32_t val)
 	return ((val) << CP_BLIT_4_DST_Y2__SHIFT) & CP_BLIT_4_DST_Y2__MASK;
 }
 
+#define REG_CP_EXEC_CS_0					0x00000000
+
+#define REG_CP_EXEC_CS_1					0x00000001
+#define CP_EXEC_CS_1_NGROUPS_X__MASK				0xffffffff
+#define CP_EXEC_CS_1_NGROUPS_X__SHIFT				0
+static inline uint32_t CP_EXEC_CS_1_NGROUPS_X(uint32_t val)
+{
+	return ((val) << CP_EXEC_CS_1_NGROUPS_X__SHIFT) & CP_EXEC_CS_1_NGROUPS_X__MASK;
+}
+
+#define REG_CP_EXEC_CS_2					0x00000002
+#define CP_EXEC_CS_2_NGROUPS_Y__MASK				0xffffffff
+#define CP_EXEC_CS_2_NGROUPS_Y__SHIFT				0
+static inline uint32_t CP_EXEC_CS_2_NGROUPS_Y(uint32_t val)
+{
+	return ((val) << CP_EXEC_CS_2_NGROUPS_Y__SHIFT) & CP_EXEC_CS_2_NGROUPS_Y__MASK;
+}
+
+#define REG_CP_EXEC_CS_3					0x00000003
+#define CP_EXEC_CS_3_NGROUPS_Z__MASK				0xffffffff
+#define CP_EXEC_CS_3_NGROUPS_Z__SHIFT				0
+static inline uint32_t CP_EXEC_CS_3_NGROUPS_Z(uint32_t val)
+{
+	return ((val) << CP_EXEC_CS_3_NGROUPS_Z__SHIFT) & CP_EXEC_CS_3_NGROUPS_Z__MASK;
+}
+
 
 #endif /* ADRENO_PM4_XML */
diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h
index b3d70ea42891..479086ccf180 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.xml.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h
@@ -8,8 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /local/mnt/workspace/source_trees/envytools/rnndb/../rnndb/dsi/dsi.xml    (  33004 bytes, from 2017-01-11 05:19:19)
-- /local/mnt/workspace/source_trees/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-05-09 06:32:54)
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
 
 Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index f97a7803a02d..9e9c5696bc03 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -32,6 +32,7 @@
 #include "dsi.xml.h"
 #include "sfpb.xml.h"
 #include "dsi_cfg.h"
+#include "msm_kms.h"
 
 static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 {
@@ -975,23 +976,23 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
 static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
 {
 	struct drm_device *dev = msm_host->dev;
+	struct msm_drm_private *priv = dev->dev_private;
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 	uint64_t iova;
 
 	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		mutex_lock(&dev->struct_mutex);
 		msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED);
 		if (IS_ERR(msm_host->tx_gem_obj)) {
 			ret = PTR_ERR(msm_host->tx_gem_obj);
 			pr_err("%s: failed to allocate gem, %d\n",
 				__func__, ret);
 			msm_host->tx_gem_obj = NULL;
-			mutex_unlock(&dev->struct_mutex);
 			return ret;
 		}
 
-		ret = msm_gem_get_iova_locked(msm_host->tx_gem_obj, 0, &iova);
+		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
+				priv->kms->aspace, &iova);
 		mutex_unlock(&dev->struct_mutex);
 		if (ret) {
 			pr_err("%s: failed to get iova, %d\n", __func__, ret);
@@ -1141,12 +1142,15 @@ static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 {
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+	struct drm_device *dev = msm_host->dev;
+	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
 	uint64_t dma_base;
 	bool triggered;
 
 	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj, 0, &dma_base);
+		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
+				priv->kms->aspace, &dma_base);
 		if (ret) {
 			pr_err("%s: failed to get iova: %d\n", __func__, ret);
 			return ret;
diff --git a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
index 8b9f3ebaeba7..57cf7fa7f1c4 100644
--- a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
+++ b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/dsi/sfpb.xml.h b/drivers/gpu/drm/msm/dsi/sfpb.xml.h
index 3fcbb30dc241..9d4d1feaefd7 100644
--- a/drivers/gpu/drm/msm/dsi/sfpb.xml.h
+++ b/drivers/gpu/drm/msm/dsi/sfpb.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/edp/edp.xml.h b/drivers/gpu/drm/msm/edp/edp.xml.h
index d7bf3232dc88..f150d4a47707 100644
--- a/drivers/gpu/drm/msm/edp/edp.xml.h
+++ b/drivers/gpu/drm/msm/edp/edp.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
index 0a97ff75ed6f..ecebf8b623ab 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2016 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -111,6 +111,32 @@ static inline uint32_t HDMI_ACR_PKT_CTRL_N_MULTIPLIER(uint32_t val)
 #define HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE			0x00000040
 #define HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE			0x00000080
 
+#define REG_HDMI_INFOFRAME_CTRL1				0x00000030
+#define HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK		0x0000003f
+#define HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__SHIFT		0
+static inline uint32_t HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(uint32_t val)
+{
+	return ((val) << HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__SHIFT) & HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK;
+}
+#define HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK		0x00003f00
+#define HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__SHIFT		8
+static inline uint32_t HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE(uint32_t val)
+{
+	return ((val) << HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__SHIFT) & HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK;
+}
+#define HDMI_INFOFRAME_CTRL1_MPEG_INFO_LINE__MASK		0x003f0000
+#define HDMI_INFOFRAME_CTRL1_MPEG_INFO_LINE__SHIFT		16
+static inline uint32_t HDMI_INFOFRAME_CTRL1_MPEG_INFO_LINE(uint32_t val)
+{
+	return ((val) << HDMI_INFOFRAME_CTRL1_MPEG_INFO_LINE__SHIFT) & HDMI_INFOFRAME_CTRL1_MPEG_INFO_LINE__MASK;
+}
+#define HDMI_INFOFRAME_CTRL1_VENSPEC_INFO_LINE__MASK		0x3f000000
+#define HDMI_INFOFRAME_CTRL1_VENSPEC_INFO_LINE__SHIFT		24
+static inline uint32_t HDMI_INFOFRAME_CTRL1_VENSPEC_INFO_LINE(uint32_t val)
+{
+	return ((val) << HDMI_INFOFRAME_CTRL1_VENSPEC_INFO_LINE__SHIFT) & HDMI_INFOFRAME_CTRL1_VENSPEC_INFO_LINE__MASK;
+}
+
 #define REG_HDMI_GEN_PKT_CTRL					0x00000034
 #define HDMI_GEN_PKT_CTRL_GENERIC0_SEND				0x00000001
 #define HDMI_GEN_PKT_CTRL_GENERIC0_CONT				0x00000002
@@ -463,7 +489,7 @@ static inline uint32_t HDMI_DDC_REF_REFTIMER(uint32_t val)
 #define REG_HDMI_CEC_RD_FILTER					0x000002b0
 
 #define REG_HDMI_ACTIVE_HSYNC					0x000002b4
-#define HDMI_ACTIVE_HSYNC_START__MASK				0x00000fff
+#define HDMI_ACTIVE_HSYNC_START__MASK				0x00001fff
 #define HDMI_ACTIVE_HSYNC_START__SHIFT				0
 static inline uint32_t HDMI_ACTIVE_HSYNC_START(uint32_t val)
 {
@@ -477,13 +503,13 @@ static inline uint32_t HDMI_ACTIVE_HSYNC_END(uint32_t val)
 }
 
 #define REG_HDMI_ACTIVE_VSYNC					0x000002b8
-#define HDMI_ACTIVE_VSYNC_START__MASK				0x00000fff
+#define HDMI_ACTIVE_VSYNC_START__MASK				0x00001fff
 #define HDMI_ACTIVE_VSYNC_START__SHIFT				0
 static inline uint32_t HDMI_ACTIVE_VSYNC_START(uint32_t val)
 {
 	return ((val) << HDMI_ACTIVE_VSYNC_START__SHIFT) & HDMI_ACTIVE_VSYNC_START__MASK;
 }
-#define HDMI_ACTIVE_VSYNC_END__MASK				0x0fff0000
+#define HDMI_ACTIVE_VSYNC_END__MASK				0x1fff0000
 #define HDMI_ACTIVE_VSYNC_END__SHIFT				16
 static inline uint32_t HDMI_ACTIVE_VSYNC_END(uint32_t val)
 {
@@ -491,13 +517,13 @@ static inline uint32_t HDMI_ACTIVE_VSYNC_END(uint32_t val)
 }
 
 #define REG_HDMI_VSYNC_ACTIVE_F2				0x000002bc
-#define HDMI_VSYNC_ACTIVE_F2_START__MASK			0x00000fff
+#define HDMI_VSYNC_ACTIVE_F2_START__MASK			0x00001fff
 #define HDMI_VSYNC_ACTIVE_F2_START__SHIFT			0
 static inline uint32_t HDMI_VSYNC_ACTIVE_F2_START(uint32_t val)
 {
 	return ((val) << HDMI_VSYNC_ACTIVE_F2_START__SHIFT) & HDMI_VSYNC_ACTIVE_F2_START__MASK;
 }
-#define HDMI_VSYNC_ACTIVE_F2_END__MASK				0x0fff0000
+#define HDMI_VSYNC_ACTIVE_F2_END__MASK				0x1fff0000
 #define HDMI_VSYNC_ACTIVE_F2_END__SHIFT				16
 static inline uint32_t HDMI_VSYNC_ACTIVE_F2_END(uint32_t val)
 {
@@ -505,13 +531,13 @@ static inline uint32_t HDMI_VSYNC_ACTIVE_F2_END(uint32_t val)
 }
 
 #define REG_HDMI_TOTAL						0x000002c0
-#define HDMI_TOTAL_H_TOTAL__MASK				0x00000fff
+#define HDMI_TOTAL_H_TOTAL__MASK				0x00001fff
 #define HDMI_TOTAL_H_TOTAL__SHIFT				0
 static inline uint32_t HDMI_TOTAL_H_TOTAL(uint32_t val)
 {
 	return ((val) << HDMI_TOTAL_H_TOTAL__SHIFT) & HDMI_TOTAL_H_TOTAL__MASK;
 }
-#define HDMI_TOTAL_V_TOTAL__MASK				0x0fff0000
+#define HDMI_TOTAL_V_TOTAL__MASK				0x1fff0000
 #define HDMI_TOTAL_V_TOTAL__SHIFT				16
 static inline uint32_t HDMI_TOTAL_V_TOTAL(uint32_t val)
 {
@@ -519,7 +545,7 @@ static inline uint32_t HDMI_TOTAL_V_TOTAL(uint32_t val)
 }
 
 #define REG_HDMI_VSYNC_TOTAL_F2					0x000002c4
-#define HDMI_VSYNC_TOTAL_F2_V_TOTAL__MASK			0x00000fff
+#define HDMI_VSYNC_TOTAL_F2_V_TOTAL__MASK			0x00001fff
 #define HDMI_VSYNC_TOTAL_F2_V_TOTAL__SHIFT			0
 static inline uint32_t HDMI_VSYNC_TOTAL_F2_V_TOTAL(uint32_t val)
 {
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
index 8177e8511afd..9c34b91ae329 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
@@ -175,10 +175,10 @@ int msm_hdmi_audio_update(struct hdmi *hdmi)
 		/* configure infoframe: */
 		hdmi_audio_infoframe_pack(info, buf, sizeof(buf));
 		hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0,
-				(buf[3] <<  0) || (buf[4] <<  8) ||
-				(buf[5] << 16) || (buf[6] << 24));
+				(buf[3] <<  0) | (buf[4] <<  8) |
+				(buf[5] << 16) | (buf[6] << 24));
 		hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1,
-				(buf[7] <<  0) || (buf[8] << 8));
+				(buf[7] <<  0) | (buf[8] << 8));
 
 		hdmi_write(hdmi, REG_HDMI_GC, 0);
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
index 4e6d1bf27474..ae40e7179d4f 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
@@ -86,6 +86,65 @@ static void power_off(struct drm_bridge *bridge)
 	}
 }
 
+#define AVI_IFRAME_LINE_NUMBER 1
+
+static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi)
+{
+	struct drm_crtc *crtc = hdmi->encoder->crtc;
+	const struct drm_display_mode *mode = &crtc->state->adjusted_mode;
+	union hdmi_infoframe frame;
+	u8 buffer[HDMI_INFOFRAME_SIZE(AVI)];
+	u32 val;
+	int len;
+
+	drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, mode);
+
+	len = hdmi_infoframe_pack(&frame, buffer, sizeof(buffer));
+	if (len < 0) {
+		dev_err(&hdmi->pdev->dev,
+			"failed to configure avi infoframe\n");
+		return;
+	}
+
+	/*
+	 * the AVI_INFOx registers don't map exactly to how the AVI infoframes
+	 * are packed according to the spec. The checksum from the header is
+	 * written to the LSB byte of AVI_INFO0 and the version is written to
+	 * the third byte from the LSB of AVI_INFO3
+	 */
+	hdmi_write(hdmi, REG_HDMI_AVI_INFO(0),
+		   buffer[3] |
+		   buffer[4] << 8 |
+		   buffer[5] << 16 |
+		   buffer[6] << 24);
+
+	hdmi_write(hdmi, REG_HDMI_AVI_INFO(1),
+		   buffer[7] |
+		   buffer[8] << 8 |
+		   buffer[9] << 16 |
+		   buffer[10] << 24);
+
+	hdmi_write(hdmi, REG_HDMI_AVI_INFO(2),
+		   buffer[11] |
+		   buffer[12] << 8 |
+		   buffer[13] << 16 |
+		   buffer[14] << 24);
+
+	hdmi_write(hdmi, REG_HDMI_AVI_INFO(3),
+		   buffer[15] |
+		   buffer[16] << 8 |
+		   buffer[1] << 24);
+
+	hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0,
+		   HDMI_INFOFRAME_CTRL0_AVI_SEND |
+		   HDMI_INFOFRAME_CTRL0_AVI_CONT);
+
+	val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1);
+	val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK;
+	val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER);
+	hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val);
+}
+
 static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge)
 {
 	struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge);
@@ -98,7 +157,10 @@ static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge)
 		msm_hdmi_phy_resource_enable(phy);
 		msm_hdmi_power_on(bridge);
 		hdmi->power_on = true;
-		msm_hdmi_audio_update(hdmi);
+		if (hdmi->hdmi_mode) {
+			msm_hdmi_config_avi_infoframe(hdmi);
+			msm_hdmi_audio_update(hdmi);
+		}
 	}
 
 	msm_hdmi_phy_powerup(phy, hdmi->pixclock);
@@ -134,7 +196,8 @@ static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge)
 	if (hdmi->power_on) {
 		power_off(bridge);
 		hdmi->power_on = false;
-		msm_hdmi_audio_update(hdmi);
+		if (hdmi->hdmi_mode)
+			msm_hdmi_audio_update(hdmi);
 		msm_hdmi_phy_resource_disable(phy);
 	}
 }
@@ -196,7 +259,8 @@ static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge,
 	DBG("frame_ctrl=%08x", frame_ctrl);
 	hdmi_write(hdmi, REG_HDMI_FRAME_CTRL, frame_ctrl);
 
-	msm_hdmi_audio_update(hdmi);
+	if (hdmi->hdmi_mode)
+		msm_hdmi_audio_update(hdmi);
 }
 
 static const struct drm_bridge_funcs msm_hdmi_bridge_funcs = {
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
index 143eab46ba68..1fb7645cc721 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
@@ -670,6 +670,11 @@ static unsigned long hdmi_8996_pll_recalc_rate(struct clk_hw *hw,
 
 static void hdmi_8996_pll_unprepare(struct clk_hw *hw)
 {
+	struct hdmi_pll_8996 *pll = hw_clk_to_pll(hw);
+	struct hdmi_phy *phy = pll_get_phy(pll);
+
+	hdmi_phy_write(phy, REG_HDMI_8996_PHY_CFG, 0x6);
+	usleep_range(100, 150);
 }
 
 static int hdmi_8996_pll_is_enabled(struct clk_hw *hw)
diff --git a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
index 1b996ede7a65..da646deedf4b 100644
--- a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
+++ b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h
index 88037889589b..576cea30d391 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index 698e514203c6..615e1def64d9 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -126,8 +126,9 @@ static void unref_cursor_worker(struct drm_flip_work *work, void *val)
 	struct mdp4_crtc *mdp4_crtc =
 		container_of(work, struct mdp4_crtc, unref_cursor_work);
 	struct mdp4_kms *mdp4_kms = get_kms(&mdp4_crtc->base);
+	struct msm_kms *kms = &mdp4_kms->base.base;
 
-	msm_gem_put_iova(val, mdp4_kms->id);
+	msm_gem_put_iova(val, kms->aspace);
 	drm_gem_object_unreference_unlocked(val);
 }
 
@@ -360,6 +361,7 @@ static void update_cursor(struct drm_crtc *crtc)
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	struct msm_kms *kms = &mdp4_kms->base.base;
 	enum mdp4_dma dma = mdp4_crtc->dma;
 	unsigned long flags;
 
@@ -372,7 +374,7 @@ 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_reference(next_bo);
-			msm_gem_get_iova_locked(next_bo, mdp4_kms->id, &iova);
+			msm_gem_get_iova(next_bo, kms->aspace, &iova);
 
 			/* enable cursor: */
 			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_SIZE(dma),
@@ -409,6 +411,7 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc,
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	struct msm_kms *kms = &mdp4_kms->base.base;
 	struct drm_device *dev = crtc->dev;
 	struct drm_gem_object *cursor_bo, *old_bo;
 	unsigned long flags;
@@ -429,7 +432,7 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc,
 	}
 
 	if (cursor_bo) {
-		ret = msm_gem_get_iova(cursor_bo, mdp4_kms->id, &iova);
+		ret = msm_gem_get_iova(cursor_bo, kms->aspace, &iova);
 		if (ret)
 			goto fail;
 	} else {
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
index 3d26d7774c08..bcd1f5cac72c 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
@@ -160,10 +160,10 @@ static void mdp4_destroy(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
 	struct device *dev = mdp4_kms->dev->dev;
-	struct msm_gem_address_space *aspace = mdp4_kms->aspace;
+	struct msm_gem_address_space *aspace = kms->aspace;
 
 	if (mdp4_kms->blank_cursor_iova)
-		msm_gem_put_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id);
+		msm_gem_put_iova(mdp4_kms->blank_cursor_bo, kms->aspace);
 	drm_gem_object_unreference_unlocked(mdp4_kms->blank_cursor_bo);
 
 	if (aspace) {
@@ -510,7 +510,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 			goto fail;
 		}
 
-		mdp4_kms->aspace = aspace;
+		kms->aspace = aspace;
 
 		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
@@ -522,22 +522,13 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		aspace = NULL;
 	}
 
-	mdp4_kms->id = msm_register_address_space(dev, aspace);
-	if (mdp4_kms->id < 0) {
-		ret = mdp4_kms->id;
-		dev_err(dev->dev, "failed to register mdp4 iommu: %d\n", ret);
-		goto fail;
-	}
-
 	ret = modeset_init(mdp4_kms);
 	if (ret) {
 		dev_err(dev->dev, "modeset_init failed: %d\n", ret);
 		goto fail;
 	}
 
-	mutex_lock(&dev->struct_mutex);
 	mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC);
-	mutex_unlock(&dev->struct_mutex);
 	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);
@@ -545,7 +536,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	ret = msm_gem_get_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id,
+	ret = msm_gem_get_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);
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
index c413779d488a..940de51ac5cd 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
@@ -34,9 +34,6 @@ struct mdp4_kms {
 
 	int rev;
 
-	/* mapper-id used to request GEM buffer mapped for scanout: */
-	int id;
-
 	void __iomem *mmio;
 
 	struct regulator *vdd;
@@ -45,7 +42,6 @@ struct mdp4_kms {
 	struct clk *pclk;
 	struct clk *lut_clk;
 	struct clk *axi_clk;
-	struct msm_gem_address_space *aspace;
 
 	struct mdp_irq error_handler;
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
index 53619d07677e..a20e3d644523 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
@@ -103,13 +103,14 @@ static int mdp4_plane_prepare_fb(struct drm_plane *plane,
 {
 	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
 	struct mdp4_kms *mdp4_kms = get_kms(plane);
+	struct msm_kms *kms = &mdp4_kms->base.base;
 	struct drm_framebuffer *fb = new_state->fb;
 
 	if (!fb)
 		return 0;
 
 	DBG("%s: prepare: FB[%u]", mdp4_plane->name, fb->base.id);
-	return msm_framebuffer_prepare(fb, mdp4_kms->id);
+	return msm_framebuffer_prepare(fb, kms->aspace);
 }
 
 static void mdp4_plane_cleanup_fb(struct drm_plane *plane,
@@ -117,13 +118,14 @@ static void mdp4_plane_cleanup_fb(struct drm_plane *plane,
 {
 	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
 	struct mdp4_kms *mdp4_kms = get_kms(plane);
+	struct msm_kms *kms = &mdp4_kms->base.base;
 	struct drm_framebuffer *fb = old_state->fb;
 
 	if (!fb)
 		return;
 
 	DBG("%s: cleanup: FB[%u]", mdp4_plane->name, fb->base.id);
-	msm_framebuffer_cleanup(fb, mdp4_kms->id);
+	msm_framebuffer_cleanup(fb, kms->aspace);
 }
 
 
@@ -161,6 +163,7 @@ static void mdp4_plane_set_scanout(struct drm_plane *plane,
 {
 	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
 	struct mdp4_kms *mdp4_kms = get_kms(plane);
+	struct msm_kms *kms = &mdp4_kms->base.base;
 	enum mdp4_pipe pipe = mdp4_plane->pipe;
 
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_STRIDE_A(pipe),
@@ -172,13 +175,13 @@ static void mdp4_plane_set_scanout(struct drm_plane *plane,
 			MDP4_PIPE_SRC_STRIDE_B_P3(fb->pitches[3]));
 
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP0_BASE(pipe),
-			msm_framebuffer_iova(fb, mdp4_kms->id, 0));
+			msm_framebuffer_iova(fb, kms->aspace, 0));
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP1_BASE(pipe),
-			msm_framebuffer_iova(fb, mdp4_kms->id, 1));
+			msm_framebuffer_iova(fb, kms->aspace, 1));
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP2_BASE(pipe),
-			msm_framebuffer_iova(fb, mdp4_kms->id, 2));
+			msm_framebuffer_iova(fb, kms->aspace, 2));
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP3_BASE(pipe),
-			msm_framebuffer_iova(fb, mdp4_kms->id, 3));
+			msm_framebuffer_iova(fb, kms->aspace, 3));
 
 	plane->fb = fb;
 }
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
index e6dfc518d4db..d9c10e02ee41 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
@@ -8,9 +8,17 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /local/mnt/workspace/source_trees/envytools/rnndb/../rnndb/mdp/mdp5.xml   (  37411 bytes, from 2017-01-11 05:19:19)
-- /local/mnt/workspace/source_trees/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-05-09 06:32:54)
-- /local/mnt/workspace/source_trees/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2016-01-07 08:45:55)
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
 
 Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 0764a6498110..cb5415d6c04b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -160,8 +160,9 @@ static void unref_cursor_worker(struct drm_flip_work *work, void *val)
 	struct mdp5_crtc *mdp5_crtc =
 		container_of(work, struct mdp5_crtc, unref_cursor_work);
 	struct mdp5_kms *mdp5_kms = get_kms(&mdp5_crtc->base);
+	struct msm_kms *kms = &mdp5_kms->base.base;
 
-	msm_gem_put_iova(val, mdp5_kms->id);
+	msm_gem_put_iova(val, kms->aspace);
 	drm_gem_object_unreference_unlocked(val);
 }
 
@@ -724,6 +725,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 	struct mdp5_pipeline *pipeline = &mdp5_cstate->pipeline;
 	struct drm_device *dev = crtc->dev;
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
+	struct msm_kms *kms = &mdp5_kms->base.base;
 	struct drm_gem_object *cursor_bo, *old_bo = NULL;
 	uint32_t blendcfg, stride;
 	uint64_t cursor_addr;
@@ -758,7 +760,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 	if (!cursor_bo)
 		return -ENOENT;
 
-	ret = msm_gem_get_iova(cursor_bo, mdp5_kms->id, &cursor_addr);
+	ret = msm_gem_get_iova(cursor_bo, kms->aspace, &cursor_addr);
 	if (ret)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index e2b3346ead48..5d13fa5381ee 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -163,7 +163,7 @@ static void mdp5_set_encoder_mode(struct msm_kms *kms,
 static void mdp5_kms_destroy(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
-	struct msm_gem_address_space *aspace = mdp5_kms->aspace;
+	struct msm_gem_address_space *aspace = kms->aspace;
 	int i;
 
 	for (i = 0; i < mdp5_kms->num_hwmixers; i++)
@@ -663,7 +663,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 			goto fail;
 		}
 
-		mdp5_kms->aspace = aspace;
+		kms->aspace = aspace;
 
 		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
@@ -678,13 +678,6 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 		aspace = NULL;;
 	}
 
-	mdp5_kms->id = msm_register_address_space(dev, aspace);
-	if (mdp5_kms->id < 0) {
-		ret = mdp5_kms->id;
-		dev_err(&pdev->dev, "failed to register mdp5 iommu: %d\n", ret);
-		goto fail;
-	}
-
 	ret = modeset_init(mdp5_kms);
 	if (ret) {
 		dev_err(&pdev->dev, "modeset_init failed: %d\n", ret);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index 8bdb7ee4983b..17caa0e8c8ae 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -55,10 +55,6 @@ struct mdp5_kms {
 	struct mdp5_state *state;
 	struct drm_modeset_lock state_lock;
 
-	/* mapper-id used to request GEM buffer mapped for scanout: */
-	int id;
-	struct msm_gem_address_space *aspace;
-
 	struct mdp5_smp *smp;
 	struct mdp5_ctl_manager *ctlm;
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index abaaac7fea1a..fe3a4de1a433 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -22,8 +22,6 @@
 struct mdp5_plane {
 	struct drm_plane base;
 
-	spinlock_t pipe_lock;     /* protect REG_MDP5_PIPE_* registers */
-
 	uint32_t nformats;
 	uint32_t formats[32];
 };
@@ -274,26 +272,28 @@ static int mdp5_plane_prepare_fb(struct drm_plane *plane,
 				 struct drm_plane_state *new_state)
 {
 	struct mdp5_kms *mdp5_kms = get_kms(plane);
+	struct msm_kms *kms = &mdp5_kms->base.base;
 	struct drm_framebuffer *fb = new_state->fb;
 
 	if (!new_state->fb)
 		return 0;
 
 	DBG("%s: prepare: FB[%u]", plane->name, fb->base.id);
-	return msm_framebuffer_prepare(fb, mdp5_kms->id);
+	return msm_framebuffer_prepare(fb, kms->aspace);
 }
 
 static void mdp5_plane_cleanup_fb(struct drm_plane *plane,
 				  struct drm_plane_state *old_state)
 {
 	struct mdp5_kms *mdp5_kms = get_kms(plane);
+	struct msm_kms *kms = &mdp5_kms->base.base;
 	struct drm_framebuffer *fb = old_state->fb;
 
 	if (!fb)
 		return;
 
 	DBG("%s: cleanup: FB[%u]", plane->name, fb->base.id);
-	msm_framebuffer_cleanup(fb, mdp5_kms->id);
+	msm_framebuffer_cleanup(fb, kms->aspace);
 }
 
 #define FRAC_16_16(mult, div)    (((mult) << 16) / (div))
@@ -500,6 +500,8 @@ static void set_scanout_locked(struct mdp5_kms *mdp5_kms,
 			       enum mdp5_pipe pipe,
 			       struct drm_framebuffer *fb)
 {
+	struct msm_kms *kms = &mdp5_kms->base.base;
+
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC_STRIDE_A(pipe),
 			MDP5_PIPE_SRC_STRIDE_A_P0(fb->pitches[0]) |
 			MDP5_PIPE_SRC_STRIDE_A_P1(fb->pitches[1]));
@@ -509,13 +511,13 @@ static void set_scanout_locked(struct mdp5_kms *mdp5_kms,
 			MDP5_PIPE_SRC_STRIDE_B_P3(fb->pitches[3]));
 
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC0_ADDR(pipe),
-			msm_framebuffer_iova(fb, mdp5_kms->id, 0));
+			msm_framebuffer_iova(fb, kms->aspace, 0));
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC1_ADDR(pipe),
-			msm_framebuffer_iova(fb, mdp5_kms->id, 1));
+			msm_framebuffer_iova(fb, kms->aspace, 1));
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC2_ADDR(pipe),
-			msm_framebuffer_iova(fb, mdp5_kms->id, 2));
+			msm_framebuffer_iova(fb, kms->aspace, 2));
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC3_ADDR(pipe),
-			msm_framebuffer_iova(fb, mdp5_kms->id, 3));
+			msm_framebuffer_iova(fb, kms->aspace, 3));
 }
 
 /* Note: mdp5_plane->pipe_lock must be locked */
@@ -881,7 +883,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 		struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		struct drm_rect *src, struct drm_rect *dest)
 {
-	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
 	struct drm_plane_state *pstate = plane->state;
 	struct mdp5_hw_pipe *hwpipe = to_mdp5_plane_state(pstate)->hwpipe;
 	struct mdp5_kms *mdp5_kms = get_kms(plane);
@@ -902,7 +903,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 	uint32_t src_img_w, src_img_h;
 	uint32_t src_x_r;
 	int crtc_x_r;
-	unsigned long flags;
 	int ret;
 
 	nplanes = fb->format->num_planes;
@@ -981,8 +981,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 	hflip = !!(rotation & DRM_MODE_REFLECT_X);
 	vflip = !!(rotation & DRM_MODE_REFLECT_Y);
 
-	spin_lock_irqsave(&mdp5_plane->pipe_lock, flags);
-
 	mdp5_hwpipe_mode_set(mdp5_kms, hwpipe, fb, &step, &pe,
 			     config, hdecm, vdecm, hflip, vflip,
 			     crtc_x, crtc_y, crtc_w, crtc_h,
@@ -995,8 +993,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 				     src_img_w, src_img_h,
 				     src_x_r, src_y, src_w, src_h);
 
-	spin_unlock_irqrestore(&mdp5_plane->pipe_lock, flags);
-
 	plane->fb = fb;
 
 	return ret;
@@ -1139,8 +1135,6 @@ struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 	mdp5_plane->nformats = mdp_get_formats(mdp5_plane->formats,
 		ARRAY_SIZE(mdp5_plane->formats), false);
 
-	spin_lock_init(&mdp5_plane->pipe_lock);
-
 	if (type == DRM_PLANE_TYPE_CURSOR)
 		ret = drm_universal_plane_init(dev, plane, 0xff,
 				&mdp5_cursor_plane_funcs,
diff --git a/drivers/gpu/drm/msm/mdp/mdp_common.xml.h b/drivers/gpu/drm/msm/mdp/mdp_common.xml.h
index 8994c365e218..1494c407be44 100644
--- a/drivers/gpu/drm/msm/mdp/mdp_common.xml.h
+++ b/drivers/gpu/drm/msm/mdp/mdp_common.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  36965 bytes, from 2016-11-26 23:01:08)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37411 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  33004 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2017-05-17 13:21:27)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41799 bytes, from 2017-06-16 12:32:42)
+- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2017-05-17 13:21:27)
+
+Copyright (C) 2013-2017 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 9d498eb81906..f49f6ac5585c 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -51,19 +51,6 @@ static const struct drm_mode_config_funcs mode_config_funcs = {
 	.atomic_state_free = msm_atomic_state_free,
 };
 
-int msm_register_address_space(struct drm_device *dev,
-		struct msm_gem_address_space *aspace)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-
-	if (WARN_ON(priv->num_aspaces >= ARRAY_SIZE(priv->aspace)))
-		return -EINVAL;
-
-	priv->aspace[priv->num_aspaces] = aspace;
-
-	return priv->num_aspaces++;
-}
-
 #ifdef CONFIG_DRM_MSM_REGISTER_LOGGING
 static bool reglog = false;
 MODULE_PARM_DESC(reglog, "Enable register read/write logging");
@@ -349,6 +336,7 @@ static int msm_init_vram(struct drm_device *dev)
 		priv->vram.size = size;
 
 		drm_mm_init(&priv->vram.mm, 0, (size >> PAGE_SHIFT) - 1);
+		spin_lock_init(&priv->vram.lock);
 
 		attrs |= DMA_ATTR_NO_KERNEL_MAPPING;
 		attrs |= DMA_ATTR_WRITE_COMBINE;
@@ -699,6 +687,17 @@ static int msm_ioctl_gem_cpu_fini(struct drm_device *dev, void *data,
 	return ret;
 }
 
+static int msm_ioctl_gem_info_iova(struct drm_device *dev,
+		struct drm_gem_object *obj, uint64_t *iova)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+
+	if (!priv->gpu)
+		return -EINVAL;
+
+	return msm_gem_get_iova(obj, priv->gpu->aspace, iova);
+}
+
 static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 		struct drm_file *file)
 {
@@ -706,14 +705,22 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 	struct drm_gem_object *obj;
 	int ret = 0;
 
-	if (args->pad)
+	if (args->flags & ~MSM_INFO_FLAGS)
 		return -EINVAL;
 
 	obj = drm_gem_object_lookup(file, args->handle);
 	if (!obj)
 		return -ENOENT;
 
-	args->offset = msm_gem_mmap_offset(obj);
+	if (args->flags & MSM_INFO_IOVA) {
+		uint64_t iova;
+
+		ret = msm_ioctl_gem_info_iova(dev, obj, &iova);
+		if (!ret)
+			args->offset = iova;
+	} else {
+		args->offset = msm_gem_mmap_offset(obj);
+	}
 
 	drm_gem_object_unreference_unlocked(obj);
 
@@ -842,7 +849,7 @@ static struct drm_driver msm_driver = {
 	.debugfs_init       = msm_debugfs_init,
 #endif
 	.ioctls             = msm_ioctls,
-	.num_ioctls         = DRM_MSM_NUM_IOCTLS,
+	.num_ioctls         = ARRAY_SIZE(msm_ioctls),
 	.fops               = &fops,
 	.name               = "msm",
 	.desc               = "MSM Snapdragon DRM",
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 1b26ca626528..fc8d24f7c084 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -123,14 +123,6 @@ struct msm_drm_private {
 	uint32_t pending_crtcs;
 	wait_queue_head_t pending_crtcs_event;
 
-	/* Registered address spaces.. currently this is fixed per # of
-	 * iommu's.  Ie. one for display block and one for gpu block.
-	 * Eventually, to do per-process gpu pagetables, we'll want one
-	 * of these per-process.
-	 */
-	unsigned int num_aspaces;
-	struct msm_gem_address_space *aspace[NUM_DOMAINS];
-
 	unsigned int num_planes;
 	struct drm_plane *planes[16];
 
@@ -157,6 +149,7 @@ struct msm_drm_private {
 		 * and position mm_node->start is in # of pages:
 		 */
 		struct drm_mm mm;
+		spinlock_t lock; /* Protects drm_mm node allocation/removal */
 	} vram;
 
 	struct notifier_block vmap_notifier;
@@ -183,9 +176,6 @@ 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_register_address_space(struct drm_device *dev,
-		struct msm_gem_address_space *aspace);
-
 void msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
 		struct msm_gem_vma *vma, struct sg_table *sgt);
 int msm_gem_map_vma(struct msm_gem_address_space *aspace,
@@ -209,13 +199,14 @@ int msm_gem_mmap_obj(struct drm_gem_object *obj,
 int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 int msm_gem_fault(struct vm_fault *vmf);
 uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj);
-int msm_gem_get_iova_locked(struct drm_gem_object *obj, int id,
-		uint64_t *iova);
-int msm_gem_get_iova(struct drm_gem_object *obj, int id, uint64_t *iova);
-uint64_t msm_gem_iova(struct drm_gem_object *obj, int id);
+int msm_gem_get_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);
 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, int id);
+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,
@@ -229,13 +220,9 @@ struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
 void msm_gem_prime_unpin(struct drm_gem_object *obj);
-void *msm_gem_get_vaddr_locked(struct drm_gem_object *obj);
 void *msm_gem_get_vaddr(struct drm_gem_object *obj);
-void msm_gem_put_vaddr_locked(struct drm_gem_object *obj);
 void msm_gem_put_vaddr(struct drm_gem_object *obj);
 int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv);
-void msm_gem_purge(struct drm_gem_object *obj);
-void msm_gem_vunmap(struct drm_gem_object *obj);
 int msm_gem_sync_object(struct drm_gem_object *obj,
 		struct msm_fence_context *fctx, bool exclusive);
 void msm_gem_move_to_active(struct drm_gem_object *obj,
@@ -248,12 +235,17 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 		uint32_t size, uint32_t flags, uint32_t *handle);
 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,
+		uint32_t size, uint32_t flags);
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt);
 
-int msm_framebuffer_prepare(struct drm_framebuffer *fb, int id);
-void msm_framebuffer_cleanup(struct drm_framebuffer *fb, int id);
-uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb, int id, int plane);
+int msm_framebuffer_prepare(struct drm_framebuffer *fb,
+		struct msm_gem_address_space *aspace);
+void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
+		struct msm_gem_address_space *aspace);
+uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb,
+		struct msm_gem_address_space *aspace, int plane);
 struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane);
 const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb);
 struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index ba2733a95a4f..6ecb7b170316 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -84,14 +84,15 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
  * should be fine, since only the scanout (mdpN) side of things needs
  * this, the gpu doesn't care about fb's.
  */
-int msm_framebuffer_prepare(struct drm_framebuffer *fb, int id)
+int msm_framebuffer_prepare(struct drm_framebuffer *fb,
+		struct msm_gem_address_space *aspace)
 {
 	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int ret, i, n = fb->format->num_planes;
 	uint64_t iova;
 
 	for (i = 0; i < n; i++) {
-		ret = msm_gem_get_iova(msm_fb->planes[i], id, &iova);
+		ret = msm_gem_get_iova(msm_fb->planes[i], aspace, &iova);
 		DBG("FB[%u]: iova[%d]: %08llx (%d)", fb->base.id, i, iova, ret);
 		if (ret)
 			return ret;
@@ -100,21 +101,23 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb, int id)
 	return 0;
 }
 
-void msm_framebuffer_cleanup(struct drm_framebuffer *fb, int id)
+void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
+		struct msm_gem_address_space *aspace)
 {
 	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	for (i = 0; i < n; i++)
-		msm_gem_put_iova(msm_fb->planes[i], id);
+		msm_gem_put_iova(msm_fb->planes[i], aspace);
 }
 
-uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb, int id, int plane)
+uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb,
+		struct msm_gem_address_space *aspace, int plane)
 {
 	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	if (!msm_fb->planes[plane])
 		return 0;
-	return msm_gem_iova(msm_fb->planes[plane], id) + fb->offsets[plane];
+	return msm_gem_iova(msm_fb->planes[plane], aspace) + fb->offsets[plane];
 }
 
 struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane)
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index feea8ba4e05b..5ecf4ff9a059 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -20,6 +20,7 @@
 
 #include "msm_drv.h"
 #include "msm_gem.h"
+#include "msm_kms.h"
 
 extern int msm_gem_mmap_obj(struct drm_gem_object *obj,
 					struct vm_area_struct *vma);
@@ -73,6 +74,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 {
 	struct msm_fbdev *fbdev = to_msm_fbdev(helper);
 	struct drm_device *dev = helper->dev;
+	struct msm_drm_private *priv = dev->dev_private;
 	struct drm_framebuffer *fb = NULL;
 	struct fb_info *fbi = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = {0};
@@ -95,10 +97,8 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 	/* allocate backing bo */
 	size = mode_cmd.pitches[0] * mode_cmd.height;
 	DBG("allocating %d bytes for fb %d", size, dev->primary->index);
-	mutex_lock(&dev->struct_mutex);
 	fbdev->bo = msm_gem_new(dev, size, MSM_BO_SCANOUT |
 			MSM_BO_WC | MSM_BO_STOLEN);
-	mutex_unlock(&dev->struct_mutex);
 	if (IS_ERR(fbdev->bo)) {
 		ret = PTR_ERR(fbdev->bo);
 		fbdev->bo = NULL;
@@ -124,7 +124,7 @@ 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_locked(fbdev->bo, 0, &paddr);
+	ret = msm_gem_get_iova(fbdev->bo, priv->kms->aspace, &paddr);
 	if (ret) {
 		dev_err(dev->dev, "failed to get buffer obj iova: %d\n", ret);
 		goto fail_unlock;
@@ -153,7 +153,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 
 	dev->mode_config.fb_base = paddr;
 
-	fbi->screen_base = msm_gem_get_vaddr_locked(fbdev->bo);
+	fbi->screen_base = msm_gem_get_vaddr(fbdev->bo);
 	if (IS_ERR(fbi->screen_base)) {
 		ret = PTR_ERR(fbi->screen_base);
 		goto fail_unlock;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index be77a35a7a8e..65f35544c1ec 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -26,6 +26,9 @@
 #include "msm_gpu.h"
 #include "msm_mmu.h"
 
+static void msm_gem_vunmap_locked(struct drm_gem_object *obj);
+
+
 static dma_addr_t physaddr(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -41,8 +44,7 @@ static bool use_pages(struct drm_gem_object *obj)
 }
 
 /* allocate pages from VRAM carveout, used when no IOMMU: */
-static struct page **get_pages_vram(struct drm_gem_object *obj,
-		int npages)
+static struct page **get_pages_vram(struct drm_gem_object *obj, int npages)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	struct msm_drm_private *priv = obj->dev->dev_private;
@@ -54,7 +56,9 @@ static struct page **get_pages_vram(struct drm_gem_object *obj,
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
+	spin_lock(&priv->vram.lock);
 	ret = drm_mm_insert_node(&priv->vram.mm, msm_obj->vram_node, npages);
+	spin_unlock(&priv->vram.lock);
 	if (ret) {
 		kvfree(p);
 		return ERR_PTR(ret);
@@ -69,7 +73,6 @@ static struct page **get_pages_vram(struct drm_gem_object *obj,
 	return p;
 }
 
-/* called with dev->struct_mutex held */
 static struct page **get_pages(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -109,6 +112,18 @@ static struct page **get_pages(struct drm_gem_object *obj)
 	return msm_obj->pages;
 }
 
+static void put_pages_vram(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct msm_drm_private *priv = obj->dev->dev_private;
+
+	spin_lock(&priv->vram.lock);
+	drm_mm_remove_node(msm_obj->vram_node);
+	spin_unlock(&priv->vram.lock);
+
+	kvfree(msm_obj->pages);
+}
+
 static void put_pages(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -125,10 +140,8 @@ static void put_pages(struct drm_gem_object *obj)
 
 		if (use_pages(obj))
 			drm_gem_put_pages(obj, msm_obj->pages, true, false);
-		else {
-			drm_mm_remove_node(msm_obj->vram_node);
-			kvfree(msm_obj->pages);
-		}
+		else
+			put_pages_vram(obj);
 
 		msm_obj->pages = NULL;
 	}
@@ -136,11 +149,18 @@ static void put_pages(struct drm_gem_object *obj)
 
 struct page **msm_gem_get_pages(struct drm_gem_object *obj)
 {
-	struct drm_device *dev = obj->dev;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	struct page **p;
-	mutex_lock(&dev->struct_mutex);
+
+	mutex_lock(&msm_obj->lock);
+
+	if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) {
+		mutex_unlock(&msm_obj->lock);
+		return ERR_PTR(-EBUSY);
+	}
+
 	p = get_pages(obj);
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&msm_obj->lock);
 	return p;
 }
 
@@ -195,28 +215,25 @@ int msm_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
-	struct drm_device *dev = obj->dev;
-	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	struct page **pages;
 	unsigned long pfn;
 	pgoff_t pgoff;
 	int ret;
 
-	/* This should only happen if userspace tries to pass a mmap'd
-	 * but unfaulted gem bo vaddr into submit ioctl, triggering
-	 * a page fault while struct_mutex is already held.  This is
-	 * not a valid use-case so just bail.
-	 */
-	if (priv->struct_mutex_task == current)
-		return VM_FAULT_SIGBUS;
-
-	/* Make sure we don't parallel update on a fault, nor move or remove
-	 * something from beneath our feet
+	/*
+	 * vm_ops.open/drm_gem_mmap_obj and close get and put
+	 * a reference on obj. So, we dont need to hold one here.
 	 */
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	ret = mutex_lock_interruptible(&msm_obj->lock);
 	if (ret)
 		goto out;
 
+	if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) {
+		mutex_unlock(&msm_obj->lock);
+		return VM_FAULT_SIGBUS;
+	}
+
 	/* make sure we have pages attached now */
 	pages = get_pages(obj);
 	if (IS_ERR(pages)) {
@@ -235,7 +252,7 @@ int msm_gem_fault(struct vm_fault *vmf)
 	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 out_unlock:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&msm_obj->lock);
 out:
 	switch (ret) {
 	case -EAGAIN:
@@ -259,9 +276,10 @@ out:
 static uint64_t mmap_offset(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	WARN_ON(!mutex_is_locked(&msm_obj->lock));
 
 	/* Make it mmapable */
 	ret = drm_gem_create_mmap_offset(obj);
@@ -277,95 +295,140 @@ static uint64_t mmap_offset(struct drm_gem_object *obj)
 uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj)
 {
 	uint64_t offset;
-	mutex_lock(&obj->dev->struct_mutex);
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	mutex_lock(&msm_obj->lock);
 	offset = mmap_offset(obj);
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&msm_obj->lock);
 	return offset;
 }
 
-static void
-put_iova(struct drm_gem_object *obj)
+static struct msm_gem_vma *add_vma(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace)
 {
-	struct drm_device *dev = obj->dev;
-	struct msm_drm_private *priv = obj->dev->dev_private;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	int id;
+	struct msm_gem_vma *vma;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	WARN_ON(!mutex_is_locked(&msm_obj->lock));
 
-	for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
-		if (!priv->aspace[id])
-			continue;
-		msm_gem_unmap_vma(priv->aspace[id],
-				&msm_obj->domain[id], msm_obj->sgt);
-	}
+	vma = kzalloc(sizeof(*vma), GFP_KERNEL);
+	if (!vma)
+		return ERR_PTR(-ENOMEM);
+
+	vma->aspace = aspace;
+
+	list_add_tail(&vma->list, &msm_obj->vmas);
+
+	return vma;
 }
 
-/* should be called under struct_mutex.. although it can be called
- * from atomic context without struct_mutex to acquire an extra
- * iova ref if you know one is already held.
- *
- * That means when I do eventually need to add support for unpinning
- * the refcnt counter needs to be atomic_t.
- */
-int msm_gem_get_iova_locked(struct drm_gem_object *obj, int id,
-		uint64_t *iova)
+static struct msm_gem_vma *lookup_vma(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	int ret = 0;
+	struct msm_gem_vma *vma;
 
-	if (!msm_obj->domain[id].iova) {
-		struct msm_drm_private *priv = obj->dev->dev_private;
-		struct page **pages = get_pages(obj);
+	WARN_ON(!mutex_is_locked(&msm_obj->lock));
 
-		if (IS_ERR(pages))
-			return PTR_ERR(pages);
-
-		if (iommu_present(&platform_bus_type)) {
-			ret = msm_gem_map_vma(priv->aspace[id], &msm_obj->domain[id],
-					msm_obj->sgt, obj->size >> PAGE_SHIFT);
-		} else {
-			msm_obj->domain[id].iova = physaddr(obj);
-		}
+	list_for_each_entry(vma, &msm_obj->vmas, list) {
+		if (vma->aspace == aspace)
+			return vma;
 	}
 
-	if (!ret)
-		*iova = msm_obj->domain[id].iova;
+	return NULL;
+}
 
-	return ret;
+static void del_vma(struct msm_gem_vma *vma)
+{
+	if (!vma)
+		return;
+
+	list_del(&vma->list);
+	kfree(vma);
+}
+
+/* Called with msm_obj->lock locked */
+static void
+put_iova(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct msm_gem_vma *vma, *tmp;
+
+	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);
+		del_vma(vma);
+	}
 }
 
 /* get iova, taking a reference.  Should have a matching put */
-int msm_gem_get_iova(struct drm_gem_object *obj, int id, uint64_t *iova)
+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;
+	struct msm_gem_vma *vma;
+	int ret = 0;
 
-	/* this is safe right now because we don't unmap until the
-	 * bo is deleted:
-	 */
-	if (msm_obj->domain[id].iova) {
-		*iova = msm_obj->domain[id].iova;
-		return 0;
+	mutex_lock(&msm_obj->lock);
+
+	if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) {
+		mutex_unlock(&msm_obj->lock);
+		return -EBUSY;
 	}
 
-	mutex_lock(&obj->dev->struct_mutex);
-	ret = msm_gem_get_iova_locked(obj, id, iova);
-	mutex_unlock(&obj->dev->struct_mutex);
+	vma = lookup_vma(obj, aspace);
+
+	if (!vma) {
+		struct page **pages;
+
+		vma = add_vma(obj, aspace);
+		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_map_vma(aspace, vma, msm_obj->sgt,
+				obj->size >> PAGE_SHIFT);
+		if (ret)
+			goto fail;
+	}
+
+	*iova = vma->iova;
+
+	mutex_unlock(&msm_obj->lock);
+	return 0;
+
+fail:
+	del_vma(vma);
+
+	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()'.
  */
-uint64_t msm_gem_iova(struct drm_gem_object *obj, int id)
+uint64_t msm_gem_iova(struct drm_gem_object *obj,
+		struct msm_gem_address_space *aspace)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	WARN_ON(!msm_obj->domain[id].iova);
-	return msm_obj->domain[id].iova;
+	struct msm_gem_vma *vma;
+
+	mutex_lock(&msm_obj->lock);
+	vma = lookup_vma(obj, aspace);
+	mutex_unlock(&msm_obj->lock);
+	WARN_ON(!vma);
+
+	return vma ? vma->iova : 0;
 }
 
-void msm_gem_put_iova(struct drm_gem_object *obj, int id)
+void msm_gem_put_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
@@ -405,45 +468,57 @@ fail:
 	return ret;
 }
 
-void *msm_gem_get_vaddr_locked(struct drm_gem_object *obj)
+void *msm_gem_get_vaddr(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	int ret = 0;
+
+	mutex_lock(&msm_obj->lock);
+
+	if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) {
+		mutex_unlock(&msm_obj->lock);
+		return ERR_PTR(-EBUSY);
+	}
+
+	/* increment vmap_count *before* vmap() call, so shrinker can
+	 * check vmap_count (is_vunmapable()) outside of msm_obj->lock.
+	 * This guarantees that we won't try to msm_gem_vunmap() this
+	 * same object from within the vmap() call (while we already
+	 * hold msm_obj->lock)
+	 */
+	msm_obj->vmap_count++;
+
 	if (!msm_obj->vaddr) {
 		struct page **pages = get_pages(obj);
-		if (IS_ERR(pages))
-			return ERR_CAST(pages);
+		if (IS_ERR(pages)) {
+			ret = PTR_ERR(pages);
+			goto fail;
+		}
 		msm_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
 				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
-		if (msm_obj->vaddr == NULL)
-			return ERR_PTR(-ENOMEM);
+		if (msm_obj->vaddr == NULL) {
+			ret = -ENOMEM;
+			goto fail;
+		}
 	}
-	msm_obj->vmap_count++;
+
+	mutex_unlock(&msm_obj->lock);
 	return msm_obj->vaddr;
-}
 
-void *msm_gem_get_vaddr(struct drm_gem_object *obj)
-{
-	void *ret;
-	mutex_lock(&obj->dev->struct_mutex);
-	ret = msm_gem_get_vaddr_locked(obj);
-	mutex_unlock(&obj->dev->struct_mutex);
-	return ret;
+fail:
+	msm_obj->vmap_count--;
+	mutex_unlock(&msm_obj->lock);
+	return ERR_PTR(ret);
 }
 
-void msm_gem_put_vaddr_locked(struct drm_gem_object *obj)
+void msm_gem_put_vaddr(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+
+	mutex_lock(&msm_obj->lock);
 	WARN_ON(msm_obj->vmap_count < 1);
 	msm_obj->vmap_count--;
-}
-
-void msm_gem_put_vaddr(struct drm_gem_object *obj)
-{
-	mutex_lock(&obj->dev->struct_mutex);
-	msm_gem_put_vaddr_locked(obj);
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&msm_obj->lock);
 }
 
 /* Update madvise status, returns true if not purged, else
@@ -453,15 +528,21 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
+	mutex_lock(&msm_obj->lock);
+
 	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
 
 	if (msm_obj->madv != __MSM_MADV_PURGED)
 		msm_obj->madv = madv;
 
-	return (msm_obj->madv != __MSM_MADV_PURGED);
+	madv = msm_obj->madv;
+
+	mutex_unlock(&msm_obj->lock);
+
+	return (madv != __MSM_MADV_PURGED);
 }
 
-void msm_gem_purge(struct drm_gem_object *obj)
+void msm_gem_purge(struct drm_gem_object *obj, enum msm_gem_lock subclass)
 {
 	struct drm_device *dev = obj->dev;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
@@ -470,9 +551,11 @@ void msm_gem_purge(struct drm_gem_object *obj)
 	WARN_ON(!is_purgeable(msm_obj));
 	WARN_ON(obj->import_attach);
 
+	mutex_lock_nested(&msm_obj->lock, subclass);
+
 	put_iova(obj);
 
-	msm_gem_vunmap(obj);
+	msm_gem_vunmap_locked(obj);
 
 	put_pages(obj);
 
@@ -490,12 +573,16 @@ void msm_gem_purge(struct drm_gem_object *obj)
 
 	invalidate_mapping_pages(file_inode(obj->filp)->i_mapping,
 			0, (loff_t)-1);
+
+	mutex_unlock(&msm_obj->lock);
 }
 
-void msm_gem_vunmap(struct drm_gem_object *obj)
+static void msm_gem_vunmap_locked(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
+	WARN_ON(!mutex_is_locked(&msm_obj->lock));
+
 	if (!msm_obj->vaddr || WARN_ON(!is_vunmapable(msm_obj)))
 		return;
 
@@ -503,6 +590,15 @@ void msm_gem_vunmap(struct drm_gem_object *obj)
 	msm_obj->vaddr = NULL;
 }
 
+void msm_gem_vunmap(struct drm_gem_object *obj, enum msm_gem_lock subclass)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	mutex_lock_nested(&msm_obj->lock, subclass);
+	msm_gem_vunmap_locked(obj);
+	mutex_unlock(&msm_obj->lock);
+}
+
 /* must be called before _move_to_active().. */
 int msm_gem_sync_object(struct drm_gem_object *obj,
 		struct msm_fence_context *fctx, bool exclusive)
@@ -619,13 +715,12 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	struct reservation_object *robj = msm_obj->resv;
 	struct reservation_object_list *fobj;
-	struct msm_drm_private *priv = obj->dev->dev_private;
 	struct dma_fence *fence;
+	struct msm_gem_vma *vma;
 	uint64_t off = drm_vma_node_start(&obj->vma_node);
 	const char *madv;
-	unsigned id;
 
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	mutex_lock(&msm_obj->lock);
 
 	switch (msm_obj->madv) {
 	case __MSM_MADV_PURGED:
@@ -645,8 +740,9 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 			obj->name, kref_read(&obj->refcount),
 			off, msm_obj->vaddr);
 
-	for (id = 0; id < priv->num_aspaces; id++)
-		seq_printf(m, " %08llx", msm_obj->domain[id].iova);
+	/* 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, " %zu%s\n", obj->size, madv);
 
@@ -665,6 +761,8 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	if (fence)
 		describe_fence(fence, "Exclusive", m);
 	rcu_read_unlock();
+
+	mutex_unlock(&msm_obj->lock);
 }
 
 void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
@@ -697,6 +795,8 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 
 	list_del(&msm_obj->mm_list);
 
+	mutex_lock(&msm_obj->lock);
+
 	put_iova(obj);
 
 	if (obj->import_attach) {
@@ -711,7 +811,7 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 
 		drm_prime_gem_destroy(obj, msm_obj->sgt);
 	} else {
-		msm_gem_vunmap(obj);
+		msm_gem_vunmap_locked(obj);
 		put_pages(obj);
 	}
 
@@ -720,6 +820,7 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 
 	drm_gem_object_release(obj);
 
+	mutex_unlock(&msm_obj->lock);
 	kfree(msm_obj);
 }
 
@@ -730,14 +831,8 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 	struct drm_gem_object *obj;
 	int ret;
 
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
 	obj = msm_gem_new(dev, size, flags);
 
-	mutex_unlock(&dev->struct_mutex);
-
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -752,13 +847,11 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 static int msm_gem_new_impl(struct drm_device *dev,
 		uint32_t size, uint32_t flags,
 		struct reservation_object *resv,
-		struct drm_gem_object **obj)
+		struct drm_gem_object **obj,
+		bool struct_mutex_locked)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
-	bool use_vram = false;
-
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
 	switch (flags & MSM_BO_CACHE_MASK) {
 	case MSM_BO_UNCACHED:
@@ -771,20 +864,11 @@ static int msm_gem_new_impl(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	if (!iommu_present(&platform_bus_type))
-		use_vram = true;
-	else if ((flags & MSM_BO_STOLEN) && priv->vram.size)
-		use_vram = true;
-
-	if (WARN_ON(use_vram && !priv->vram.size))
-		return -EINVAL;
-
 	msm_obj = kzalloc(sizeof(*msm_obj), GFP_KERNEL);
 	if (!msm_obj)
 		return -ENOMEM;
 
-	if (use_vram)
-		msm_obj->vram_node = &msm_obj->domain[0].node;
+	mutex_init(&msm_obj->lock);
 
 	msm_obj->flags = flags;
 	msm_obj->madv = MSM_MADV_WILLNEED;
@@ -797,48 +881,96 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	}
 
 	INIT_LIST_HEAD(&msm_obj->submit_entry);
-	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	INIT_LIST_HEAD(&msm_obj->vmas);
+
+	if (struct_mutex_locked) {
+		WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	} else {
+		mutex_lock(&dev->struct_mutex);
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+		mutex_unlock(&dev->struct_mutex);
+	}
 
 	*obj = &msm_obj->base;
 
 	return 0;
 }
 
-struct drm_gem_object *msm_gem_new(struct drm_device *dev,
-		uint32_t size, uint32_t flags)
+static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
+		uint32_t size, uint32_t flags, bool struct_mutex_locked)
 {
+	struct msm_drm_private *priv = dev->dev_private;
 	struct drm_gem_object *obj = NULL;
+	bool use_vram = false;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
 	size = PAGE_ALIGN(size);
 
+	if (!iommu_present(&platform_bus_type))
+		use_vram = true;
+	else if ((flags & MSM_BO_STOLEN) && priv->vram.size)
+		use_vram = true;
+
+	if (WARN_ON(use_vram && !priv->vram.size))
+		return ERR_PTR(-EINVAL);
+
 	/* Disallow zero sized objects as they make the underlying
 	 * infrastructure grumpy
 	 */
 	if (size == 0)
 		return ERR_PTR(-EINVAL);
 
-	ret = msm_gem_new_impl(dev, size, flags, NULL, &obj);
+	ret = msm_gem_new_impl(dev, size, flags, NULL, &obj, struct_mutex_locked);
 	if (ret)
 		goto fail;
 
-	if (use_pages(obj)) {
+	if (use_vram) {
+		struct msm_gem_vma *vma;
+		struct page **pages;
+
+		vma = add_vma(obj, NULL);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			goto fail;
+		}
+
+		to_msm_bo(obj)->vram_node = &vma->node;
+
+		drm_gem_private_object_init(dev, obj, size);
+
+		pages = get_pages(obj);
+		if (IS_ERR(pages)) {
+			ret = PTR_ERR(pages);
+			goto fail;
+		}
+
+		vma->iova = physaddr(obj);
+	} else {
 		ret = drm_gem_object_init(dev, obj, size);
 		if (ret)
 			goto fail;
-	} else {
-		drm_gem_private_object_init(dev, obj, size);
 	}
 
 	return obj;
 
 fail:
-	drm_gem_object_unreference(obj);
+	drm_gem_object_unreference_unlocked(obj);
 	return ERR_PTR(ret);
 }
 
+struct drm_gem_object *msm_gem_new_locked(struct drm_device *dev,
+		uint32_t size, uint32_t flags)
+{
+	return _msm_gem_new(dev, size, flags, true);
+}
+
+struct drm_gem_object *msm_gem_new(struct drm_device *dev,
+		uint32_t size, uint32_t flags)
+{
+	return _msm_gem_new(dev, size, flags, false);
+}
+
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt)
 {
@@ -855,11 +987,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 
 	size = PAGE_ALIGN(dmabuf->size);
 
-	/* Take mutex so we can modify the inactive list in msm_gem_new_impl */
-	mutex_lock(&dev->struct_mutex);
-	ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj);
-	mutex_unlock(&dev->struct_mutex);
-
+	ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj, false);
 	if (ret)
 		goto fail;
 
@@ -868,17 +996,22 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	npages = size / PAGE_SIZE;
 
 	msm_obj = to_msm_bo(obj);
+	mutex_lock(&msm_obj->lock);
 	msm_obj->sgt = sgt;
 	msm_obj->pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
 	if (!msm_obj->pages) {
+		mutex_unlock(&msm_obj->lock);
 		ret = -ENOMEM;
 		goto fail;
 	}
 
 	ret = drm_prime_sg_to_page_addr_arrays(sgt, msm_obj->pages, NULL, npages);
-	if (ret)
+	if (ret) {
+		mutex_unlock(&msm_obj->lock);
 		goto fail;
+	}
 
+	mutex_unlock(&msm_obj->lock);
 	return obj;
 
 fail:
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 1b4cf20043ea..91c210d2359c 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -31,6 +31,7 @@ struct msm_gem_address_space {
 	 * and position mm_node->start is in # of pages:
 	 */
 	struct drm_mm mm;
+	spinlock_t lock; /* Protects drm_mm node allocation/removal */
 	struct msm_mmu *mmu;
 	struct kref kref;
 };
@@ -38,6 +39,8 @@ struct msm_gem_address_space {
 struct msm_gem_vma {
 	struct drm_mm_node node;
 	uint64_t iova;
+	struct msm_gem_address_space *aspace;
+	struct list_head list;    /* node in msm_gem_object::vmas */
 };
 
 struct msm_gem_object {
@@ -77,7 +80,7 @@ struct msm_gem_object {
 	struct sg_table *sgt;
 	void *vaddr;
 
-	struct msm_gem_vma domain[NUM_DOMAINS];
+	struct list_head vmas;    /* list of msm_gem_vma */
 
 	/* normally (resv == &_resv) except for imported bo's */
 	struct reservation_object *resv;
@@ -87,6 +90,7 @@ struct msm_gem_object {
 	 * an IOMMU.  Also used for stolen/splashscreen buffer.
 	 */
 	struct drm_mm_node *vram_node;
+	struct mutex lock; /* Protects resources associated with bo */
 };
 #define to_msm_bo(x) container_of(x, struct msm_gem_object, base)
 
@@ -97,6 +101,7 @@ static inline bool is_active(struct msm_gem_object *msm_obj)
 
 static inline bool is_purgeable(struct msm_gem_object *msm_obj)
 {
+	WARN_ON(!mutex_is_locked(&msm_obj->base.dev->struct_mutex));
 	return (msm_obj->madv == MSM_MADV_DONTNEED) && msm_obj->sgt &&
 			!msm_obj->base.dma_buf && !msm_obj->base.import_attach;
 }
@@ -106,6 +111,25 @@ static inline bool is_vunmapable(struct msm_gem_object *msm_obj)
 	return (msm_obj->vmap_count == 0) && msm_obj->vaddr;
 }
 
+/* The shrinker can be triggered while we hold objA->lock, and need
+ * to grab objB->lock to purge it.  Lockdep just sees these as a single
+ * class of lock, so we use subclasses to teach it the difference.
+ *
+ * OBJ_LOCK_NORMAL is implicit (ie. normal mutex_lock() call), and
+ * OBJ_LOCK_SHRINKER is used by shrinker.
+ *
+ * It is *essential* that we never go down paths that could trigger the
+ * shrinker for a purgable object.  This is ensured by checking that
+ * msm_obj->madv == MSM_MADV_WILLNEED.
+ */
+enum msm_gem_lock {
+	OBJ_LOCK_NORMAL,
+	OBJ_LOCK_SHRINKER,
+};
+
+void msm_gem_purge(struct drm_gem_object *obj, enum msm_gem_lock subclass);
+void msm_gem_vunmap(struct drm_gem_object *obj, enum msm_gem_lock subclass);
+
 /* Created per submit-ioctl, to track bo's and cmdstream bufs, etc,
  * associated with the cmdstream submission for synchronization (and
  * make it easier to unwind when things go wrong, etc).  This only
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index ab1dd020eb04..b72d8e6cd51d 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -20,6 +20,18 @@
 
 static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
+	/* NOTE: we are *closer* to being able to get rid of
+	 * mutex_trylock_recursive().. the msm_gem code itself does
+	 * not need struct_mutex, although codepaths that can trigger
+	 * shrinker are still called in code-paths that hold the
+	 * struct_mutex.
+	 *
+	 * Also, msm_obj->madv is protected by struct_mutex.
+	 *
+	 * The next step is probably split out a seperate lock for
+	 * protecting inactive_list, so that shrinker does not need
+	 * struct_mutex.
+	 */
 	switch (mutex_trylock_recursive(&dev->struct_mutex)) {
 	case MUTEX_TRYLOCK_FAILED:
 		return false;
@@ -77,7 +89,7 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 		if (freed >= sc->nr_to_scan)
 			break;
 		if (is_purgeable(msm_obj)) {
-			msm_gem_purge(&msm_obj->base);
+			msm_gem_purge(&msm_obj->base, OBJ_LOCK_SHRINKER);
 			freed += msm_obj->base.size >> PAGE_SHIFT;
 		}
 	}
@@ -106,7 +118,7 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
 
 	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
 		if (is_vunmapable(msm_obj)) {
-			msm_gem_vunmap(&msm_obj->base);
+			msm_gem_vunmap(&msm_obj->base, OBJ_LOCK_SHRINKER);
 			/* since we don't know any better, lets bail after a few
 			 * and if necessary the shrinker will be invoked again.
 			 * Seems better than unmapping *everything*
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 7832e6421d25..6bfca7470141 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -31,11 +31,14 @@
 #define BO_PINNED   0x2000
 
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
-		struct msm_gpu *gpu, int nr_bos, int nr_cmds)
+		struct msm_gpu *gpu, uint32_t nr_bos, uint32_t nr_cmds)
 {
 	struct msm_gem_submit *submit;
-	int sz = sizeof(*submit) + (nr_bos * sizeof(submit->bos[0])) +
-			(nr_cmds * sizeof(*submit->cmd));
+	uint64_t sz = sizeof(*submit) + (nr_bos * sizeof(submit->bos[0])) +
+		(nr_cmds * sizeof(submit->cmd[0]));
+
+	if (sz > SIZE_MAX)
+		return NULL;
 
 	submit = kmalloc(sz, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
 	if (!submit)
@@ -158,7 +161,7 @@ static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i)
 	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->id);
+		msm_gem_put_iova(&msm_obj->base, submit->gpu->aspace);
 
 	if (submit->bos[i].flags & BO_LOCKED)
 		ww_mutex_unlock(&msm_obj->resv->lock);
@@ -245,8 +248,8 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 		uint64_t iova;
 
 		/* if locking succeeded, pin bo: */
-		ret = msm_gem_get_iova_locked(&msm_obj->base,
-				submit->gpu->id, &iova);
+		ret = msm_gem_get_iova(&msm_obj->base,
+				submit->gpu->aspace, &iova);
 
 		if (ret)
 			break;
@@ -301,7 +304,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob
 	/* For now, just map the entire thing.  Eventually we probably
 	 * to do it page-by-page, w/ kmap() if not vmap()d..
 	 */
-	ptr = msm_gem_get_vaddr_locked(&obj->base);
+	ptr = msm_gem_get_vaddr(&obj->base);
 
 	if (IS_ERR(ptr)) {
 		ret = PTR_ERR(ptr);
@@ -359,7 +362,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob
 	}
 
 out:
-	msm_gem_put_vaddr_locked(&obj->base);
+	msm_gem_put_vaddr(&obj->base);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index f285d7e210db..c36321bc8714 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -50,7 +50,9 @@ msm_gem_unmap_vma(struct msm_gem_address_space *aspace,
 		aspace->mmu->funcs->unmap(aspace->mmu, vma->iova, sgt, size);
 	}
 
+	spin_lock(&aspace->lock);
 	drm_mm_remove_node(&vma->node);
+	spin_unlock(&aspace->lock);
 
 	vma->iova = 0;
 
@@ -63,10 +65,15 @@ msm_gem_map_vma(struct msm_gem_address_space *aspace,
 {
 	int ret;
 
-	if (WARN_ON(drm_mm_node_allocated(&vma->node)))
+	spin_lock(&aspace->lock);
+	if (WARN_ON(drm_mm_node_allocated(&vma->node))) {
+		spin_unlock(&aspace->lock);
 		return 0;
+	}
 
 	ret = drm_mm_insert_node(&aspace->mm, &vma->node, npages);
+	spin_unlock(&aspace->lock);
+
 	if (ret)
 		return ret;
 
@@ -94,6 +101,7 @@ msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 	if (!aspace)
 		return ERR_PTR(-ENOMEM);
 
+	spin_lock_init(&aspace->lock);
 	aspace->name = name;
 	aspace->mmu = msm_iommu_new(dev, domain);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 0fdc88d79ca8..9f3dbc236ab3 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -203,6 +203,8 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 {
 	int ret;
 
+	WARN_ON(!mutex_is_locked(&gpu->dev->struct_mutex));
+
 	if (!gpu->needs_hw_init)
 		return 0;
 
@@ -414,7 +416,7 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 		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->id);
+		msm_gem_put_iova(&msm_obj->base, gpu->aspace);
 		drm_gem_object_unreference(&msm_obj->base);
 	}
 
@@ -495,8 +497,8 @@ 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_reference(&msm_obj->base);
-		msm_gem_get_iova_locked(&msm_obj->base,
-				submit->gpu->id, &iova);
+		msm_gem_get_iova(&msm_obj->base,
+				submit->gpu->aspace, &iova);
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
 			msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence);
@@ -562,7 +564,7 @@ static int get_clocks(struct platform_device *pdev, struct msm_gpu *gpu)
 
 int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
-		const char *name, const char *ioname, const char *irqname, int ringsz)
+		const char *name, struct msm_gpu_config *config)
 {
 	struct iommu_domain *iommu;
 	int ret;
@@ -593,14 +595,14 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 
 	/* Map registers: */
-	gpu->mmio = msm_ioremap(pdev, ioname, name);
+	gpu->mmio = msm_ioremap(pdev, config->ioname, name);
 	if (IS_ERR(gpu->mmio)) {
 		ret = PTR_ERR(gpu->mmio);
 		goto fail;
 	}
 
 	/* Get Interrupt: */
-	gpu->irq = platform_get_irq_byname(pdev, irqname);
+	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);
@@ -640,9 +642,8 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	 */
 	iommu = iommu_domain_alloc(&platform_bus_type);
 	if (iommu) {
-		/* TODO 32b vs 64b address space.. */
-		iommu->geometry.aperture_start = SZ_16M;
-		iommu->geometry.aperture_end = 0xffffffff;
+		iommu->geometry.aperture_start = config->va_start;
+		iommu->geometry.aperture_end = config->va_end;
 
 		dev_info(drm->dev, "%s: using IOMMU\n", name);
 		gpu->aspace = msm_gem_address_space_create(&pdev->dev,
@@ -658,13 +659,9 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	} else {
 		dev_info(drm->dev, "%s: no IOMMU, fallback to VRAM carveout!\n", name);
 	}
-	gpu->id = msm_register_address_space(drm, gpu->aspace);
-
 
 	/* Create ringbuffer: */
-	mutex_lock(&drm->struct_mutex);
-	gpu->rb = msm_ringbuffer_new(gpu, ringsz);
-	mutex_unlock(&drm->struct_mutex);
+	gpu->rb = msm_ringbuffer_new(gpu, config->ringsz);
 	if (IS_ERR(gpu->rb)) {
 		ret = PTR_ERR(gpu->rb);
 		gpu->rb = NULL;
@@ -693,7 +690,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 
 	if (gpu->rb) {
 		if (gpu->rb_iova)
-			msm_gem_put_iova(gpu->rb->bo, gpu->id);
+			msm_gem_put_iova(gpu->rb->bo, gpu->aspace);
 		msm_ringbuffer_destroy(gpu->rb);
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index aa3241000455..df4e2771fb85 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -28,6 +28,14 @@
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
 
+struct msm_gpu_config {
+	const char *ioname;
+	const char *irqname;
+	uint64_t va_start;
+	uint64_t va_end;
+	unsigned int ringsz;
+};
+
 /* So far, with hardware that I've seen to date, we can have:
  *  + zero, one, or two z180 2d cores
  *  + a3xx or a2xx 3d core, which share a common CP (the firmware
@@ -50,7 +58,6 @@ struct msm_gpu_funcs {
 	void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 			struct msm_file_private *ctx);
 	void (*flush)(struct msm_gpu *gpu);
-	bool (*idle)(struct msm_gpu *gpu);
 	irqreturn_t (*irq)(struct msm_gpu *irq);
 	uint32_t (*last_fence)(struct msm_gpu *gpu);
 	void (*recover)(struct msm_gpu *gpu);
@@ -99,7 +106,6 @@ struct msm_gpu {
 	int irq;
 
 	struct msm_gem_address_space *aspace;
-	int id;
 
 	/* Power Control: */
 	struct regulator *gpu_reg, *gpu_cx;
@@ -209,7 +215,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 
 int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
-		const char *name, const char *ioname, const char *irqname, int ringsz);
+		const char *name, struct msm_gpu_config *config);
+
 void msm_gpu_cleanup(struct msm_gpu *gpu);
 
 struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index faa22c7c5423..a8f2ba5e5f07 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -72,6 +72,9 @@ struct msm_kms {
 
 	/* irq number to be passed on to drm_irq_install */
 	int irq;
+
+	/* mapper-id used to request GEM buffer mapped for scanout: */
+	struct msm_gem_address_space *aspace;
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index 0e81faab2c50..0366b8092f97 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -268,7 +268,7 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	struct msm_gem_object *obj = submit->bos[idx].obj;
 	const char *buf;
 
-	buf = msm_gem_get_vaddr_locked(&obj->base);
+	buf = msm_gem_get_vaddr(&obj->base);
 	if (IS_ERR(buf))
 		return;
 
@@ -283,7 +283,7 @@ static void snapshot_buf(struct msm_rd_state *rd,
 			(uint32_t[3]){ iova, size, iova >> 32 }, 12);
 	rd_write_section(rd, RD_BUFFER_CONTENTS, buf, size);
 
-	msm_gem_put_vaddr_locked(&obj->base);
+	msm_gem_put_vaddr(&obj->base);
 }
 
 /* called under struct_mutex */
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 67b34e069abf..791bca3c6a9c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -40,7 +40,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size)
 		goto fail;
 	}
 
-	ring->start = msm_gem_get_vaddr_locked(ring->bo);
+	ring->start = msm_gem_get_vaddr(ring->bo);
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
 		goto fail;
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index a4a189a240d7..26c54f6d595d 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -104,10 +104,14 @@ struct drm_msm_gem_new {
 	__u32 handle;         /* out */
 };
 
+#define MSM_INFO_IOVA	0x01
+
+#define MSM_INFO_FLAGS (MSM_INFO_IOVA)
+
 struct drm_msm_gem_info {
 	__u32 handle;         /* in */
-	__u32 pad;
-	__u64 offset;         /* out, offset to pass to mmap() */
+	__u32 flags;	      /* in - combination of MSM_INFO_* flags */
+	__u64 offset;         /* out, mmap() offset or iova */
 };
 
 #define MSM_PREP_READ        0x01
@@ -261,7 +265,6 @@ struct drm_msm_gem_madvise {
 #define DRM_MSM_GEM_SUBMIT             0x06
 #define DRM_MSM_WAIT_FENCE             0x07
 #define DRM_MSM_GEM_MADVISE            0x08
-#define DRM_MSM_NUM_IOCTLS             0x09
 
 #define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
 #define DRM_IOCTL_MSM_GEM_NEW          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new)
author	Dave Airlie <airlied@redhat.com>	2017-06-21 08:49:54 +1000
committer	Dave Airlie <airlied@redhat.com>	2017-06-21 08:49:54 +1000
commit	eafae133e48c9e5f5537d5c6df34eab912336b9a (patch)
tree	fb9fd9337cd93e597114cf3c5f4ca9e9bb3a4f7e
parent	8c52f36413063bedbb3d31a65048a61ea2f1e169 (diff)
parent	4a630fadbb29d9efaedb525f1a8f7449ad107641 (diff)
download	linux-stable-eafae133e48c9e5f5537d5c6df34eab912336b9a.tar.gz linux-stable-eafae133e48c9e5f5537d5c6df34eab912336b9a.tar.bz2 linux-stable-eafae133e48c9e5f5537d5c6df34eab912336b9a.zip