Merge tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The drm core grew a new generic gpu virtual address manager, and new
  execution locking helpers. These are used by nouveau now to provide
  uAPI support for the userspace Vulkan driver. AMD had a bunch of new
  IP core support, loads of refactoring around fbdev, but mostly just
  the usual amount of stuff across the board.

  core:
   - fix gfp flags in drmm_kmalloc

  gpuva:
   - add new generic GPU VA manager (for nouveau initially)

  syncobj:
   - add new DRM_IOCTL_SYNCOBJ_EVENTFD ioctl

  dma-buf:
   - acquire resv lock for mmap() in exporters
   - support dma-buf self import automatically
   - docs fixes

  backlight:
   - fix fbdev interactions

  atomic:
   - improve logging

  prime:
   - remove struct gem_prim_mmap plus driver updates

  gem:
   - drm_exec: add locking over multiple GEM objects
   - fix lockdep checking

  fbdev:
   - make fbdev userspace interfaces optional
   - use linux device instead of fbdev device
   - use deferred i/o helper macros in various drivers
   - Make FB core selectable without drivers
   - Remove obsolete flags FBINFO_DEFAULT and FBINFO_FLAG_DEFAULT
   - Add helper macros and Kconfig tokens for DMA-allocated framebuffer

  ttm:
   - support init_on_free
   - swapout fixes

  panel:
   - panel-edp: Support AUO B116XAB01.4
   - Support Visionox R66451 plus DT bindings
   - ld9040:
      - Backlight support
      - magic improved
      - Kconfig fix
   - Convert to of_device_get_match_data()
   - Fix Kconfig dependencies
   - simple:
      - Set bpc value to fix warning
      - Set connector type for AUO T215HVN01
      - Support Innolux G156HCE-L01 plus DT bindings
   - ili9881: Support TDO TL050HDV35 LCD panel plus DT bindings
   - startek: Support KD070FHFID015 MIPI-DSI panel plus DT bindings
   - sitronix-st7789v:
      - Support Inanbo T28CP45TN89 plus DT bindings
      - Support EDT ET028013DMA plus DT bindings
      - Various cleanups
   - edp: Add timings for N140HCA-EAC
   - Allow panels and touchscreens to power sequence together
   - Fix Innolux G156HCE-L01 LVDS clock

  bridge:
   - debugfs for chains support
   - dw-hdmi:
      - Improve support for YUV420 bus format
      - CEC suspend/resume
      - update EDID on HDMI detect
   - dw-mipi-dsi: Fix enable/disable of DSI controller
   - lt9611uxc: Use MODULE_FIRMWARE()
   - ps8640: Remove broken EDID code
   - samsung-dsim: Fix command transfer
   - tc358764:
      - Handle HS/VS polarity
      - Use BIT() macro
      - Various cleanups
   - adv7511: Fix low refresh rate
   - anx7625:
      - Switch to macros instead of hardcoded values
      - locking fixes
   - tc358767: fix hardware delays
   - sitronix-st7789v:
      - Support panel orientation
      - Support rotation property
      - Add support for Jasonic JT240MHQS-HWT-EK-E3 plus DT bindings

  amdgpu:
   - SDMA 6.1.0 support
   - HDP 6.1 support
   - SMUIO 14.0 support
   - PSP 14.0 support
   - IH 6.1 support
   - Lots of checkpatch cleanups
   - GFX 9.4.3 updates
   - Add USB PD and IFWI flashing documentation
   - GPUVM updates
   - RAS fixes
   - DRR fixes
   - FAMS fixes
   - Virtual display fixes
   - Soft IH fixes
   - SMU13 fixes
   - Rework PSP firmware loading for other IPs
   - Kernel doc fixes
   - DCN 3.0.1 fixes
   - LTTPR fixes
   - DP MST fixes
   - DCN 3.1.6 fixes
   - SMU 13.x fixes
   - PSP 13.x fixes
   - SubVP fixes
   - GC 9.4.3 fixes
   - Display bandwidth calculation fixes
   - VCN4 secure submission fixes
   - Allow building DC on RISC-V
   - Add visible FB info to bo_print_info
   - HBR3 fixes
   - GFX9 MCBP fix
   - GMC10 vmhub index fix
   - GMC11 vmhub index fix
   - Create a new doorbell manager
   - SR-IOV fixes
   - initial freesync panel replay support
   - revert zpos properly until igt regression is fixeed
   - use TTM to manage doorbell BAR
   - Expose both current and average power via hwmon if supported

  amdkfd:
   - Cleanup CRIU dma-buf handling
   - Use KIQ to unmap HIQ
   - GFX 9.4.3 debugger updates
   - GFX 9.4.2 debugger fixes
   - Enable cooperative groups fof gfx11
   - SVM fixes
   - Convert older APUs to use dGPU path like newer APUs
   - Drop IOMMUv2 path as it is no longer used
   - TBA fix for aldebaran

  i915:
   - ICL+ DSI modeset sequence
   - HDCP improvements
   - MTL display fixes and cleanups
   - HSW/BDW PSR1 restored
   - Init DDI ports in VBT order
   - General display refactors
   - Start using plane scale factor for relative data rate
   - Use shmem for dpt objects
   - Expose RPS thresholds in sysfs
   - Apply GuC SLPC min frequency softlimit correctly
   - Extend Wa_14015795083 to TGL, RKL, DG1 and ADL
   - Fix a VMA UAF for multi-gt platform
   - Do not use stolen on MTL due to HW bug
   - Check HuC and GuC version compatibility on MTL
   - avoid infinite GPU waits due to premature release of request memory
   - Fixes and updates for GSC memory allocation
   - Display SDVO fixes
   - Take stolen handling out of FBC code
   - Make i915_coherent_map_type GT-centric
   - Simplify shmem_create_from_object map_type

  msm:
   - SM6125 MDSS support
   - DPU: SM6125 DPU support
   - DSI: runtime PM support, burst mode support
   - DSI PHY: SM6125 support in 14nm DSI PHY driver
   - GPU: prepare for a7xx
   - fix a690 firmware
   - disable relocs on a6xx and newer

  radeon:
   - Lots of checkpatch cleanups

  ast:
   - improve device-model detection
   - Represent BMV as virtual connector
   - Report DP connection status

  nouveau:
   - add new exec/bind interface to support Vulkan
   - document some getparam ioctls
   - improve VRAM detection
   - various fixes/cleanups
   - workraound DPCD issues

  ivpu:
   - MMU updates
   - debugfs support
   - Support vpu4

  virtio:
   - add sync object support

  atmel-hlcdc:
   - Support inverted pixclock polarity

  etnaviv:
   - runtime PM cleanups
   - hang handling fixes

  exynos:
   - use fbdev DMA helpers
   - fix possible NULL ptr dereference

  komeda:
   - always attach encoder

  omapdrm:
   - use fbdev DMA helpers
ingenic:
   - kconfig regmap fixes

  loongson:
   - support display controller

  mediatek:
   - Small mtk-dpi cleanups
   - DisplayPort: support eDP and aux-bus
   - Fix coverity issues
   - Fix potential memory leak if vmap() fail

  mgag200:
   - minor fixes

  mxsfb:
   - support disabling overlay planes

  panfrost:
   - fix sync in IRQ handling

  ssd130x:
   - Support per-controller default resolution plus DT bindings
   - Reduce memory-allocation overhead
   - Improve intermediate buffer size computation
   - Fix allocation of temporary buffers
   - Fix pitch computation
   - Fix shadow plane allocation

  tegra:
   - use fbdev DMA helpers
   - Convert to devm_platform_ioremap_resource()
   - support bridge/connector
   - enable PM

  tidss:
   - Support TI AM625 plus DT bindings
   - Implement new connector model plus driver updates

  vkms:
   - improve write back support
   - docs fixes
   - support gamma LUT

  zynqmp-dpsub:
   - misc fixes"

* tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm: (1327 commits)
  drm/gpuva_mgr: remove unused prev pointer in __drm_gpuva_sm_map()
  drm/tests/drm_kunit_helpers: Place correct function name in the comment header
  drm/nouveau: uapi: don't pass NO_PREFETCH flag implicitly
  drm/nouveau: uvmm: fix unset region pointer on remap
  drm/nouveau: sched: avoid job races between entities
  drm/i915: Fix HPD polling, reenabling the output poll work as needed
  drm: Add an HPD poll helper to reschedule the poll work
  drm/i915: Fix TLB-Invalidation seqno store
  drm/ttm/tests: Fix type conversion in ttm_pool_test
  drm/msm/a6xx: Bail out early if setting GPU OOB fails
  drm/msm/a6xx: Move LLC accessors to the common header
  drm/msm/a6xx: Introduce a6xx_llc_read
  drm/ttm/tests: Require MMU when testing
  drm/panel: simple: Fix Innolux G156HCE-L01 LVDS clock
  Revert "Revert "drm/amdgpu/display: change pipe policy for DCN 2.0""
  drm/amdgpu: Add memory vendor information
  drm/amd: flush any delayed gfxoff on suspend entry
  drm/amdgpu: skip fence GFX interrupts disable/enable for S0ix
  drm/amdgpu: Remove gfxoff check in GFX v9.4.3
  drm/amd/pm: Update pci link speed for smu v13.0.6
  ...

1 files changed, 58 insertions, 44 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 8aaa427f8c0f..7689395e44fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -35,6 +35,7 @@
 #include "amdgpu_xgmi.h"
 #include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
 #include "nbio_v4_3.h"
+#include "nbio_v7_9.h"
 #include "atom.h"
 #include "amdgpu_reset.h"
 
@@ -757,16 +758,6 @@ static int __amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int amdgpu_ras_check_feature_allowed(struct amdgpu_device *adev,
-		struct ras_common_if *head)
-{
-	if (amdgpu_ras_is_feature_allowed(adev, head) ||
-		amdgpu_ras_is_poison_mode_supported(adev))
-		return 1;
-	else
-		return 0;
-}
-
 /* wrapper of psp_ras_enable_features */
 int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 		struct ras_common_if *head, bool enable)
@@ -778,7 +769,16 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (!con)
 		return -EINVAL;
 
-	if (head->block == AMDGPU_RAS_BLOCK__GFX) {
+	/* Do not enable ras feature if it is not allowed */
+	if (enable &&
+	    head->block != AMDGPU_RAS_BLOCK__GFX &&
+	    !amdgpu_ras_is_feature_allowed(adev, head))
+		goto out;
+
+	/* Only enable gfx ras feature from host side */
+	if (head->block == AMDGPU_RAS_BLOCK__GFX &&
+	    !amdgpu_sriov_vf(adev) &&
+	    !amdgpu_ras_intr_triggered()) {
 		info = kzalloc(sizeof(union ta_ras_cmd_input), GFP_KERNEL);
 		if (!info)
 			return -ENOMEM;
@@ -794,16 +794,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 				.error_type = amdgpu_ras_error_to_ta(head->type),
 			};
 		}
-	}
 
-	/* Do not enable if it is not allowed. */
-	if (enable && !amdgpu_ras_check_feature_allowed(adev, head))
-		goto out;
-
-	/* Only enable ras feature operation handle on host side */
-	if (head->block == AMDGPU_RAS_BLOCK__GFX &&
-		!amdgpu_sriov_vf(adev) &&
-		!amdgpu_ras_intr_triggered()) {
 		ret = psp_ras_enable_features(&adev->psp, info, enable);
 		if (ret) {
 			dev_err(adev->dev, "ras %s %s failed poison:%d ret:%d\n",
@@ -1159,7 +1150,8 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
 	}
 
 	/* Calculate XGMI relative offset */
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+	if (adev->gmc.xgmi.num_physical_nodes > 1 &&
+	    info->head.block != AMDGPU_RAS_BLOCK__GFX) {
 		block_info.address =
 			amdgpu_xgmi_get_relative_phy_addr(adev,
 							  block_info.address);
@@ -2072,6 +2064,8 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 			if (ras->gpu_reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET) {
 				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 				set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+
+				psp_fatal_error_recovery_quirk(&adev->psp);
 			}
 		}
 
@@ -2414,6 +2408,7 @@ static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev)
 	if (adev->asic_type == CHIP_IP_DISCOVERY) {
 		switch (adev->ip_versions[MP0_HWIP][0]) {
 		case IP_VERSION(13, 0, 0):
+		case IP_VERSION(13, 0, 6):
 		case IP_VERSION(13, 0, 10):
 			return true;
 		default:
@@ -2440,10 +2435,10 @@ static void amdgpu_ras_get_quirks(struct amdgpu_device *adev)
 	if (!ctx)
 		return;
 
-	if (strnstr(ctx->vbios_version, "D16406",
-		    sizeof(ctx->vbios_version)) ||
-		strnstr(ctx->vbios_version, "D36002",
-			sizeof(ctx->vbios_version)))
+	if (strnstr(ctx->vbios_pn, "D16406",
+		    sizeof(ctx->vbios_pn)) ||
+		strnstr(ctx->vbios_pn, "D36002",
+			sizeof(ctx->vbios_pn)))
 		adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__GFX);
 }
 
@@ -2515,8 +2510,18 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
 	/* hw_supported needs to be aligned with RAS block mask. */
 	adev->ras_hw_enabled &= AMDGPU_RAS_BLOCK_MASK;
 
-	adev->ras_enabled = amdgpu_ras_enable == 0 ? 0 :
-		adev->ras_hw_enabled & amdgpu_ras_mask;
+
+	/*
+	 * Disable ras feature for aqua vanjaram
+	 * by default on apu platform.
+	 */
+	if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6) &&
+	    adev->gmc.is_app_apu)
+		adev->ras_enabled = amdgpu_ras_enable != 1 ? 0 :
+			adev->ras_hw_enabled & amdgpu_ras_mask;
+	else
+		adev->ras_enabled = amdgpu_ras_enable == 0 ? 0 :
+			adev->ras_hw_enabled & amdgpu_ras_mask;
 }
 
 static void amdgpu_ras_counte_dw(struct work_struct *work)
@@ -2642,6 +2647,10 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 			 * check DF RAS */
 			adev->nbio.ras = &nbio_v4_3_ras;
 		break;
+	case IP_VERSION(7, 9, 0):
+		if (!adev->gmc.is_app_apu)
+			adev->nbio.ras = &nbio_v7_9_ras;
+		break;
 	default:
 		/* nbio ras is not available */
 		break;
@@ -2765,23 +2774,28 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 			goto cleanup;
 	}
 
-	r = amdgpu_ras_sysfs_create(adev, ras_block);
-	if (r)
-		goto interrupt;
+	if (ras_obj->hw_ops &&
+	    (ras_obj->hw_ops->query_ras_error_count ||
+	     ras_obj->hw_ops->query_ras_error_status)) {
+		r = amdgpu_ras_sysfs_create(adev, ras_block);
+		if (r)
+			goto interrupt;
 
-	/* Those are the cached values at init.
-	 */
-	query_info = kzalloc(sizeof(struct ras_query_if), GFP_KERNEL);
-	if (!query_info)
-		return -ENOMEM;
-	memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if));
+		/* Those are the cached values at init.
+		 */
+		query_info = kzalloc(sizeof(*query_info), GFP_KERNEL);
+		if (!query_info)
+			return -ENOMEM;
+		memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if));
 
-	if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) {
-		atomic_set(&con->ras_ce_count, ce_count);
-		atomic_set(&con->ras_ue_count, ue_count);
+		if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) {
+			atomic_set(&con->ras_ce_count, ce_count);
+			atomic_set(&con->ras_ue_count, ue_count);
+		}
+
+		kfree(query_info);
 	}
 
-	kfree(query_info);
 	return 0;
 
 interrupt:
@@ -2958,10 +2972,6 @@ int amdgpu_ras_fini(struct amdgpu_device *adev)
 
 void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 {
-	amdgpu_ras_check_supported(adev);
-	if (!adev->ras_hw_enabled)
-		return;
-
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
 		struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
@@ -3136,6 +3146,10 @@ int amdgpu_ras_is_supported(struct amdgpu_device *adev,
 	 * that the ras block supports ras function.
 	 */
 	if (!ret &&
+	    (block == AMDGPU_RAS_BLOCK__GFX ||
+	     block == AMDGPU_RAS_BLOCK__SDMA ||
+	     block == AMDGPU_RAS_BLOCK__VCN ||
+	     block == AMDGPU_RAS_BLOCK__JPEG) &&
 	    amdgpu_ras_is_poison_mode_supported(adev) &&
 	    amdgpu_ras_get_ras_block(adev, block, 0))
 		ret = 1;