Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights are usual, more AMD IP blocks for future hw, i915/xe
  changes, Displayport tunnelling support for i915, msm YUV over DP
  changes, new tests for ttm, but its mostly a lot of stuff all over the
  place from lots of people.

  core:
   - EDID cleanups
   - scheduler error handling fixes
   - managed: add drmm_release_action() with tests
   - add ratelimited drm debug print
   - DPCD PSR early transport macro
   - DP tunneling and bandwidth allocation helpers
   - remove built-in edids
   - dp: Avoid AUX transfers on powered-down displays
   - dp: Add VSC SDP helpers

  cross drivers:
   - use new drm print helpers
   - switch to ->read_edid callback
   - gem: add stats for shared buffers plus updates to amdgpu, i915, xe

  syncobj:
   - fixes to waiting and sleeping

  ttm:
   - add tests
   - fix errno codes
   - simply busy-placement handling
   - fix page decryption

  media:
   - tc358743: fix v4l device registration

  video:
   - move all kernel parameters for video behind CONFIG_VIDEO

  sound:
   - remove <drm/drm_edid.h> include from header

  ci:
   - add tests for msm
   - fix apq8016 runner

  efifb:
   - use copy of global screen_info state

  vesafb:
   - use copy of global screen_info state

  simplefb:
   - fix logging

  bridge:
   - ite-6505: fix DP link-training bug
   - samsung-dsim: fix error checking in probe
   - samsung-dsim: add bsh-smm-s2/pro boards
   - tc358767: fix regmap usage
   - imx: add i.MX8MP HDMI PVI plus DT bindings
   - imx: add i.MX8MP HDMI TX plus DT bindings
   - sii902x: fix probing and unregistration
   - tc358767: limit pixel PLL input range
   - switch to new drm_bridge_read_edid() interface

  panel:
   - ltk050h3146w: error-handling fixes
   - panel-edp: support delay between power-on and enable; use put_sync
     in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
     V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
   - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
   - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
   - add BOE TH101MB31IG002-28A plus DT bindings
   - add EDT ETML1010G3DRA plus DT bindings
   - add Novatek NT36672E LCD DSI plus DT bindings
   - nt36523: support 120Hz timings, fix includes
   - simple: fix display timings on RK32FN48H
   - visionox-vtdr6130: fix initialization
   - add Powkiddy RGB10MAX3 plus DT bindings
   - st7703: support panel rotation plus DT bindings
   - add Himax HX83112A plus DT bindings
   - ltk500hd1829: add support for ltk101b4029w and admatec 9904370
   - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs

  panel-orientation-quirks:
   - GPD Win Mini

  amdgpu:
   - Validate DMABuf imports in compute VMs
   - Add RAS ACA framework
   - PSP 13 fixes
   - Misc code cleanups
   - Replay fixes
   - Atom interpretor PS, WS bounds checking
   - DML2 fixes
   - Audio fixes
   - DCN 3.5 Z state fixes
   - Remove deprecated ida_simple usage
   - UBSAN fixes
   - RAS fixes
   - Enable seq64 infrastructure
   - DC color block enablement
   - Documentation updates
   - DC documentation updates
   - DMCUB updates
   - ATHUB 4.1 support
   - LSDMA 7.0 support
   - JPEG DPG support
   - IH 7.0 support
   - HDP 7.0 support
   - VCN 5.0 support
   - SMU 13.0.6 updates
   - NBIO 7.11 updates
   - SDMA 6.1 updates
   - MMHUB 3.3 updates
   - DCN 3.5.1 support
   - NBIF 6.3.1 support
   - VPE 6.1.1 support

  amdkfd:
   - Validate DMABuf imports in compute VMs
   - SVM fixes
   - Trap handler updates and enhancements
   - Fix cache size reporting
   - Relocate the trap handler

  radeon:
   - Atom interpretor PS, WS bounds checking
   - Misc code cleanups

  xe:
   - new query for GuC submission version
   - Remove unused persistent exec_queues
   - Add vram frequency sysfs attributes
   - Add the flag XE_VM_BIND_FLAG_DUMPABLE
   - Drop pre-production workarounds
   - Drop kunit tests for unsupported platforms
   - Start pumbling SR-IOV support with memory based interrupts for VF
   - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
     to work with memory based interrupts
   - Add GuC Doorbells Manager as prep work SR-IOV
   - Implement additional workarounds for xe2 and MTL
   - Program a few registers according to perfomance guide spec for Xe2
   - Fix remaining 32b build issues and enable it back
   - Fix build with CONFIG_DEBUG_FS=n
   - Fix warnings from GuC ABI headers
   - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
   - Release mmap mappings on rpm suspend
   - Disable mid-thread preemption when not properly supported by
     hardware
   - Fix xe_exec by reserving extra fence slot for CPU bind
   - Fix xe_exec with full long running exec queue
   - Canonicalize addresses where needed for Xe2 and add to devcoredum
   - Toggle USM support for Xe2
   - Only allow 1 ufence per exec / bind IOCTL
   - Add GuC firmware loading for Lunar Lake
   - Add XE_VMA_PTE_64K VMA flag

  i915:
   - Add more ADL-N PCI IDs
   - Enable fastboot also on older platforms
   - Early transport for panel replay and PSR
   - New ARL PCI IDs
   - DP TPS4 PHY test pattern support
   - Unify and improve VSC SDP for PSR and non-PSR cases
   - Refactor memory regions and improve debug logging
   - Rework global state serialization
   - Remove unused CDCLK divider fields
   - Unify HDCP connector logging format
   - Use display instead of graphics version in display code
   - Move VBT and opregion debugfs next to the implementation
   - Abstract opregion interface, use opaque type
   - MTL fixes
   - HPD handling fixes
   - Add GuC submission interface version query
   - Atomically invalidate userptr on mmu-notifier
   - Update handling of MMIO triggered reports
   - Don't make assumptions about intel_wakeref_t type
   - Extend driver code of Xe_LPG to Xe_LPG+
   - Add flex arrays to struct i915_syncmap
   - Allow for very slow HuC loading
   - DP tunneling and bandwidth allocation support

  msm:
   - Correct bindings for MSM8976 and SM8650 platforms
   - Start migration of MDP5 platforms to DPU driver
   - X1E80100 MDSS support
   - DPU:
      - Improve DSC allocation, fixing several important corner cases
      - Add support for SDM630/SDM660 platforms
      - Simplify dpu_encoder_phys_ops
      - Apply fixes targeting DSC support with a single DSC encoder
      - Apply fixes for HCTL_EN timing configuration
      - X1E80100 support
      - Add support for YUV420 over DP
   - GPU:
      - fix sc7180 UBWC config
      - fix a7xx LLC config
      - new gpu support: a305B, a750, a702
      - machine support: SM7150 (different power levels than other a618)
      - a7xx devcoredump support

  habanalabs:
   - configure IRQ affinity according to NUMA node
   - move HBM MMU page tables inside the HBM
   - improve device reset
   - check extended PCIe errors

  ivpu:
   - updates to firmware API
   - refactor BO allocation

  imx:
   - use devm_ functions during init

  hisilicon:
   - fix EDID includes

  mgag200:
   - improve ioremap usage
   - convert to struct drm_edid
   - Work around PCI write bursts

  nouveau:
   - disp: use kmemdup()
   - fix EDID includes
   - documentation fixes

  qaic:
   - fixes to BO handling
   - make use of DRM managed release
   - fix order of remove operations

  rockchip:
   - analogix_dp: get encoder port from DT
   - inno_hdmi: support HDMI for RK3128
   - lvds: error-handling fixes

  ssd130x:
   - support SSD133x plus DT bindings

  tegra:
   - fix error handling

  tilcdc:
   - make use of DRM managed release

  v3d:
   - show memory stats in debugfs
   - Support display MMU page size

  vc4:
   - fix error handling in plane prepare_fb
   - fix framebuffer test in plane helpers

  virtio:
   - add venus capset defines

  vkms:
   - fix OOB access when programming the LUT
   - Kconfig improvements

  vmwgfx:
   - unmap surface before changing plane state
   - fix memory leak in error handling
   - documentation fixes
   - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
   - fix null-pointer deref in execbuf
   - refactor display-mode probing
   - fix fencing for creating cursor MOBs
   - fix cursor-memory lifetime

  xlnx:
   - fix live video input for ZynqMP DPSUB

  lima:
   - fix memory leak

  loongson:
   - fail if no VRAM present

  meson:
   - switch to new drm_bridge_read_edid() interface

  renesas:
   - add RZ/G2L DU support plus DT bindings

  mxsfb:
   - Use managed mode config

  sun4i:
   - HDMI: updates to atomic mode setting

  mediatek:
   - Add display driver for MT8188 VDOSYS1
   - DSI driver cleanups
   - Filter modes according to hardware capability
   - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip

  etnaviv:
   - enhancements for NPU and MRT support"

* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
  drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
  drm/amd/pm: wait for completion of the EnableGfxImu message
  drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
  drm/amdgpu: add smu 14.0.1 support
  drm/amdgpu: add VPE 6.1.1 discovery support
  drm/amdgpu/vpe: add VPE 6.1.1 support
  drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
  drm/amdgpu/vpe: add collaborate mode support for VPE
  drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
  drm/amdgpu/vpe: add multi instance VPE support
  drm/amdgpu/discovery: add nbif v6_3_1 ip block
  drm/amdgpu: Add nbif v6_3_1 ip block support
  drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
  drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
  arch/powerpc: Remove <linux/fb.h> from backlight code
  macintosh/via-pmu-backlight: Include <linux/backlight.h>
  fbdev/chipsfb: Include <linux/backlight.h>
  drm/etnaviv: Restore some id values
  drm/amdkfd: make kfd_class constant
  drm/amdgpu: add ring timeout information in devcoredump
  ...

1 files changed, 196 insertions, 24 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c9c55e2ea584..0674aca0f8a3 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -837,6 +837,65 @@ const struct adreno_reglist a690_hwcg[] = {
 	{}
 };
 
+const struct adreno_reglist a702_hwcg[] = {
+	{ REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000081 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000f3cf },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777 },
+	{ REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01202222 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040f00 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x05522022 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x02222222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002 },
+	{ REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002 },
+	{ REG_A6XX_RBBM_ISDB_CNT, 0x00000182 },
+	{ REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000 },
+	{ REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_FCHE, 0x00000222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_FCHE, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_FCHE, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_GLC, 0x00222222 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_GLC, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_GLC, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_CNTL_MHUB, 0x00000002 },
+	{ REG_A6XX_RBBM_CLOCK_DELAY_MHUB, 0x00000000 },
+	{ REG_A6XX_RBBM_CLOCK_HYST_MHUB, 0x00000000 },
+	{}
+};
+
 const struct adreno_reglist a730_hwcg[] = {
 	{ REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222 },
 	{ REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02022222 },
@@ -961,13 +1020,15 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 	unsigned int i;
 	u32 val, clock_cntl_on, cgc_mode;
 
-	if (!adreno_gpu->info->hwcg)
+	if (!(adreno_gpu->info->hwcg || adreno_is_a7xx(adreno_gpu)))
 		return;
 
 	if (adreno_is_a630(adreno_gpu))
 		clock_cntl_on = 0x8aa8aa02;
 	else if (adreno_is_a610(adreno_gpu))
 		clock_cntl_on = 0xaaa8aa82;
+	else if (adreno_is_a702(adreno_gpu))
+		clock_cntl_on = 0xaaaaaa82;
 	else
 		clock_cntl_on = 0x8aa8aa82;
 
@@ -982,6 +1043,25 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 			  state ? 0x5555 : 0);
 	}
 
+	if (!adreno_gpu->info->hwcg) {
+		gpu_write(gpu, REG_A7XX_RBBM_CLOCK_CNTL_GLOBAL, 1);
+		gpu_write(gpu, REG_A7XX_RBBM_CGC_GLOBAL_LOAD_CMD, state ? 1 : 0);
+
+		if (state) {
+			gpu_write(gpu, REG_A7XX_RBBM_CGC_P2S_TRIG_CMD, 1);
+
+			if (gpu_poll_timeout(gpu, REG_A7XX_RBBM_CGC_P2S_STATUS, val,
+					     val & A7XX_RBBM_CGC_P2S_STATUS_TXDONE, 1, 10)) {
+				dev_err(&gpu->pdev->dev, "RBBM_CGC_P2S_STATUS TXDONE Poll failed\n");
+				return;
+			}
+
+			gpu_write(gpu, REG_A7XX_RBBM_CLOCK_CNTL_GLOBAL, 0);
+		}
+
+		return;
+	}
+
 	val = gpu_read(gpu, REG_A6XX_RBBM_CLOCK_CNTL);
 
 	/* Don't re-program the registers if they are already correct */
@@ -989,14 +1069,14 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state)
 		return;
 
 	/* Disable SP clock before programming HWCG registers */
-	if (!adreno_is_a610(adreno_gpu) && !adreno_is_a7xx(adreno_gpu))
+	if (!adreno_is_a610_family(adreno_gpu) && !adreno_is_a7xx(adreno_gpu))
 		gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 1, 0);
 
 	for (i = 0; (reg = &adreno_gpu->info->hwcg[i], reg->offset); i++)
 		gpu_write(gpu, reg->offset, state ? reg->value : 0);
 
 	/* Enable SP clock */
-	if (!adreno_is_a610(adreno_gpu) && !adreno_is_a7xx(adreno_gpu))
+	if (!adreno_is_a610_family(adreno_gpu) && !adreno_is_a7xx(adreno_gpu))
 		gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 0, 1);
 
 	gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
@@ -1224,7 +1304,7 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 	const u32 *regs = a6xx_protect;
 	unsigned i, count, count_max;
 
-	if (adreno_is_a650(adreno_gpu)) {
+	if (adreno_is_a650(adreno_gpu) || adreno_is_a702(adreno_gpu)) {
 		regs = a650_protect;
 		count = ARRAY_SIZE(a650_protect);
 		count_max = 48;
@@ -1239,7 +1319,9 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 		count = ARRAY_SIZE(a660_protect);
 		count_max = 48;
 		BUILD_BUG_ON(ARRAY_SIZE(a660_protect) > 48);
-	} else if (adreno_is_a730(adreno_gpu) || adreno_is_a740(adreno_gpu)) {
+	} else if (adreno_is_a730(adreno_gpu) ||
+		   adreno_is_a740(adreno_gpu) ||
+		   adreno_is_a750(adreno_gpu)) {
 		regs = a730_protect;
 		count = ARRAY_SIZE(a730_protect);
 		count_max = 48;
@@ -1292,9 +1374,8 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 		gpu->ubwc_config.ubwc_mode = 1;
 	}
 
-	/* a618 is using the hw default values */
 	if (adreno_is_a618(gpu))
-		return;
+		gpu->ubwc_config.highest_bank_bit = 14;
 
 	if (adreno_is_a619_holi(gpu))
 		gpu->ubwc_config.highest_bank_bit = 13;
@@ -1320,6 +1401,12 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 		gpu->ubwc_config.rgb565_predicator = 1;
 		gpu->ubwc_config.uavflagprd_inv = 2;
 	}
+
+	if (adreno_is_a702(gpu)) {
+		gpu->ubwc_config.highest_bank_bit = 14;
+		gpu->ubwc_config.min_acc_len = 1;
+		gpu->ubwc_config.ubwc_mode = 2;
+	}
 }
 
 static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
@@ -1453,7 +1540,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		return false;
 
 	/* A7xx is safe! */
-	if (adreno_is_a7xx(adreno_gpu))
+	if (adreno_is_a7xx(adreno_gpu) || adreno_is_a702(adreno_gpu))
 		return true;
 
 	/*
@@ -1671,7 +1758,7 @@ static int hw_init(struct msm_gpu *gpu)
 	a6xx_set_hwcg(gpu, true);
 
 	/* VBIF/GBIF start*/
-	if (adreno_is_a610(adreno_gpu) ||
+	if (adreno_is_a610_family(adreno_gpu) ||
 	    adreno_is_a640_family(adreno_gpu) ||
 	    adreno_is_a650_family(adreno_gpu) ||
 	    adreno_is_a7xx(adreno_gpu)) {
@@ -1705,6 +1792,7 @@ static int hw_init(struct msm_gpu *gpu)
 	}
 
 	if (!(adreno_is_a650_family(adreno_gpu) ||
+	      adreno_is_a702(adreno_gpu) ||
 	      adreno_is_a730(adreno_gpu))) {
 		gmem_range_min = adreno_is_a740_family(adreno_gpu) ? SZ_16M : SZ_1M;
 
@@ -1725,7 +1813,7 @@ static int hw_init(struct msm_gpu *gpu)
 	if (adreno_is_a640_family(adreno_gpu) || adreno_is_a650_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140);
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c);
-	} else if (adreno_is_a610(adreno_gpu)) {
+	} else if (adreno_is_a610_family(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x00800060);
 		gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x40201b16);
 	} else if (!adreno_is_a7xx(adreno_gpu)) {
@@ -1740,13 +1828,18 @@ static int hw_init(struct msm_gpu *gpu)
 	if (adreno_is_a610(adreno_gpu)) {
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 48);
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 47);
+	} else if (adreno_is_a702(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 64);
+		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 63);
 	} else if (!adreno_is_a7xx(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 128);
 
 	/* Setting the primFifo thresholds default values,
 	 * and vccCacheSkipDis=1 bit (0x200) for A640 and newer
 	*/
-	if (adreno_is_a690(adreno_gpu))
+	if (adreno_is_a702(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x0000c000);
+	else if (adreno_is_a690(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00800200);
 	else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200);
@@ -1786,7 +1879,7 @@ static int hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x4fffff);
 	else if (adreno_is_a619(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x3fffff);
-	else if (adreno_is_a610(adreno_gpu))
+	else if (adreno_is_a610(adreno_gpu) || adreno_is_a702(adreno_gpu))
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x3ffff);
 	else
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x1fffff);
@@ -1822,6 +1915,9 @@ static int hw_init(struct msm_gpu *gpu)
 		else
 			gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, 0x1);
 		gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x0);
+	} else if (adreno_is_a702(adreno_gpu)) {
+		/* Something to do with the HLSQ cluster */
+		gpu_write(gpu, REG_A6XX_CP_CHICKEN_DBG, BIT(24));
 	}
 
 	if (adreno_is_a690(adreno_gpu))
@@ -2043,13 +2139,19 @@ static void a6xx_recover(struct msm_gpu *gpu)
 
 static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	static const char *uche_clients[7] = {
 		"VFD", "SP", "VSC", "VPC", "HLSQ", "PC", "LRZ",
 	};
 	u32 val;
 
-	if (mid < 1 || mid > 3)
-		return "UNKNOWN";
+	if (adreno_is_a7xx(adreno_gpu)) {
+		if (mid != 1 && mid != 2 && mid != 3 && mid != 8)
+			return "UNKNOWN";
+	} else {
+		if (mid < 1 || mid > 3)
+			return "UNKNOWN";
+	}
 
 	/*
 	 * The source of the data depends on the mid ID read from FSYNR1.
@@ -2057,26 +2159,95 @@ static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid)
 	 */
 	val = gpu_read(gpu, REG_A6XX_UCHE_CLIENT_PF);
 
-	/* mid = 3 is most precise and refers to only one block per client */
-	if (mid == 3)
-		return uche_clients[val & 7];
+	if (adreno_is_a7xx(adreno_gpu)) {
+		/* Bit 3 for mid=3 indicates BR or BV */
+		static const char *uche_clients_a7xx[16] = {
+			"BR_VFD", "BR_SP", "BR_VSC", "BR_VPC",
+			"BR_HLSQ", "BR_PC", "BR_LRZ", "BR_TP",
+			"BV_VFD", "BV_SP", "BV_VSC", "BV_VPC",
+			"BV_HLSQ", "BV_PC", "BV_LRZ", "BV_TP",
+		};
+
+		/* LPAC has the same clients as BR and BV, but because it is
+		 * compute-only some of them do not exist and there are holes
+		 * in the array.
+		 */
+		static const char *uche_clients_lpac_a7xx[8] = {
+			"-", "LPAC_SP", "-", "-",
+			"LPAC_HLSQ", "-", "-", "LPAC_TP",
+		};
+
+		val &= GENMASK(6, 0);
+
+		/* mid=3 refers to BR or BV */
+		if (mid == 3) {
+			if (val < ARRAY_SIZE(uche_clients_a7xx))
+				return uche_clients_a7xx[val];
+			else
+				return "UCHE";
+		}
+
+		/* mid=8 refers to LPAC */
+		if (mid == 8) {
+			if (val < ARRAY_SIZE(uche_clients_lpac_a7xx))
+				return uche_clients_lpac_a7xx[val];
+			else
+				return "UCHE_LPAC";
+		}
+
+		/* mid=2 is a catchall for everything else in LPAC */
+		if (mid == 2)
+			return "UCHE_LPAC";
+
+		/* mid=1 is a catchall for everything else in BR/BV */
+		return "UCHE";
+	} else if (adreno_is_a660_family(adreno_gpu)) {
+		static const char *uche_clients_a660[8] = {
+			"VFD", "SP", "VSC", "VPC", "HLSQ", "PC", "LRZ", "TP",
+		};
 
-	/* For mid=2 the source is TP or VFD except when the client id is 0 */
-	if (mid == 2)
-		return ((val & 7) == 0) ? "TP" : "TP|VFD";
+		static const char *uche_clients_a660_not[8] = {
+			"not VFD", "not SP", "not VSC", "not VPC",
+			"not HLSQ", "not PC", "not LRZ", "not TP",
+		};
 
-	/* For mid=1 just return "UCHE" as a catchall for everything else */
-	return "UCHE";
+		val &= GENMASK(6, 0);
+
+		if (mid == 3 && val < ARRAY_SIZE(uche_clients_a660))
+			return uche_clients_a660[val];
+
+		if (mid == 1 && val < ARRAY_SIZE(uche_clients_a660_not))
+			return uche_clients_a660_not[val];
+
+		return "UCHE";
+	} else {
+		/* mid = 3 is most precise and refers to only one block per client */
+		if (mid == 3)
+			return uche_clients[val & 7];
+
+		/* For mid=2 the source is TP or VFD except when the client id is 0 */
+		if (mid == 2)
+			return ((val & 7) == 0) ? "TP" : "TP|VFD";
+
+		/* For mid=1 just return "UCHE" as a catchall for everything else */
+		return "UCHE";
+	}
 }
 
 static const char *a6xx_fault_block(struct msm_gpu *gpu, u32 id)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+
 	if (id == 0)
 		return "CP";
 	else if (id == 4)
 		return "CCU";
 	else if (id == 6)
 		return "CDP Prefetch";
+	else if (id == 7)
+		return "GMU";
+	else if (id == 5 && adreno_is_a7xx(adreno_gpu))
+		return "Flag cache";
 
 	return a6xx_uche_fault_block(gpu, id);
 }
@@ -2427,7 +2598,7 @@ static int a6xx_gmu_pm_resume(struct msm_gpu *gpu)
 
 	msm_devfreq_resume(gpu);
 
-	adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate : a6xx_llc_activate(a6xx_gpu);
+	adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate(a6xx_gpu) : a6xx_llc_activate(a6xx_gpu);
 
 	return ret;
 }
@@ -2880,7 +3051,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 
 	/* gpu->info only gets assigned in adreno_gpu_init() */
 	is_a7xx = config->info->family == ADRENO_7XX_GEN1 ||
-		  config->info->family == ADRENO_7XX_GEN2;
+		  config->info->family == ADRENO_7XX_GEN2 ||
+		  config->info->family == ADRENO_7XX_GEN3;
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx);