Merge tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This adds a couple of patches outside the drm core, all should be
  acked appropriately, the string and pstore ones are the main ones that
  come to mind.

  Otherwise it's the usual drivers, xe is getting enabled by default on
  some new hardware, we've changed the device number handling to allow
  more devices, and we added some optional rust code to create QR codes
  in the panic handler, an idea first suggested I think 10 years ago :-)

  string:
   - add mem_is_zero()

  core:
   - support more device numbers
   - use XArray for minor ids
   - add backlight constants
   - Split dma fence array creation into alloc and arm

  fbdev:
   - remove usage of old fbdev hooks

  kms:
   - Add might_fault() to drm_modeset_lock priming
   - Add dynamic per-crtc vblank configuration support

  dma-buf:
   - docs cleanup

  buddy:
   - Add start address support for trim function

  printk:
   - pass description to kmsg_dump

  scheduler:
   - Remove full_recover from drm_sched_start

  ttm:
   - Make LRU walk restartable after dropping locks
   - Allow direct reclaim to allocate local memory

  panic:
   - add display QR code (in rust)

  displayport:
   - mst: GUID improvements

  bridge:
   - Silence error message on -EPROBE_DEFER
   - analogix: Clean aup
   - bridge-connector: Fix double free
   - lt6505: Disable interrupt when powered off
   - tc358767: Make default DP port preemphasis configurable
   - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
   - anx7625: simplify OF array handling
   - dw-hdmi: simplify clock handling
   - lontium-lt8912b: fix mode validation
   - nwl-dsi: fix mode vsync/hsync polarity

  xe:
   - Enable LunarLake and Battlemage support
   - Introducing Xe2 ccs modifiers for integrated and discrete graphics
   - rename xe perf to xe observation
   - use wb caching on DGFX for system memory
   - add fence timeouts
   - Lunar Lake graphics/media/display workarounds
   - Battlemage workarounds
   - Battlemage GSC support
   - GSC and HuC fw updates for LL/BM
   - use dma_fence_chain_free
   - refactor hw engine lookup and mmio access
   - enable priority mem read for Xe2
   - Add first GuC BMG fw
   - fix dma-resv lock
   - Fix DGFX display suspend/resume
   - Use xe_managed for kernel BOs
   - Use reserved copy engine for user binds on faulting devices
   - Allow mixing dma-fence jobs and long-running faulting jobs
   - fix media TLB invalidation
   - fix rpm in TTM swapout path
   - track resources and VF state by PF

  i915:
   - Type-C programming fix for MTL+
   - FBC cleanup
   - Calc vblank delay more accurately
   - On DP MST, Enable LT fallback for UHBR<->non-UHBR rates
   - Fix DP LTTPR detection
   - limit relocations to INT_MAX
   - fix long hangs in buddy allocator on DG2/A380

  amdgpu:
   - Per-queue reset support
   - SDMA devcoredump support
   - DCN 4.0.1 updates
   - GFX12/VCN4/JPEG4 updates
   - Convert vbios embedded EDID to drm_edid
   - GFX9.3/9.4 devcoredump support
   - process isolation framework for GFX 9.4.3/4
   - take IOMMU mappings into account for P2P DMA

  amdkfd:
   - CRIU fixes
   - HMM fix
   - Enable process isolation support for GFX 9.4.3/4
   - Allow users to target recommended SDMA engines
   - KFD support for targetting queues on recommended SDMA engines

  radeon:
   - remove .load and drm_dev_alloc
   - Fix vbios embedded EDID size handling
   - Convert vbios embedded EDID to drm_edid
   - Use GEM references instead of TTM
   - r100 cp init cleanup
   - Fix potential overflows in evergreen CS offset tracking

  msm:
   - DPU:
      - implement DP/PHY mapping on SC8180X
      - Enable writeback on SM8150, SC8180X, SM6125, SM6350
   - DP:
      - Enable widebus on all relevant chipsets
      - MSM8998 HDMI support
   - GPU:
      - A642L speedbin support
      - A615/A306/A621 support
      - A7xx devcoredump support

  ast:
   - astdp: Support AST2600 with VGA
   - Clean up HPD
   - Fix timeout loop for DP link training
   - reorganize output code by type (VGA, DP, etc)
   - convert to struct drm_edid
   - fix BMC handling for all outputs

  exynos:
   - drop stale MAINTAINERS pattern
   - constify struct

  loongson:
   - use GEM refcount over TTM

  mgag200:
   - Improve BMC handling
   - Support VBLANK intterupts
   - transparently support BMC outputs

  nouveau:
   - Refactor and clean up internals
   - Use GEM refcount over TTM's

  gm12u320:
   - convert to struct drm_edid

  gma500:
   - update i2c terms

  lcdif:
   - pixel clock fix

  host1x:
   - fix syncpoint IRQ during resume
   - use iommu_paging_domain_alloc()

  imx:
   - ipuv3: convert to struct drm_edid

  omapdrm:
   - improve error handling
   - use common helper for_each_endpoint_of_node()

  panel:
   - add support for BOE TV101WUM-LL2 plus DT bindings
   - novatek-nt35950: improve error handling
   - nv3051d: improve error handling
   - panel-edp:
      - add support for BOE NE140WUM-N6G
      - revert support for SDC ATNA45AF01
   - visionox-vtdr6130:
      - improve error handling
      - use devm_regulator_bulk_get_const()
   - boe-th101mb31ig002:
      - Support for starry-er88577 MIPI-DSI panel plus DT
      - Fix porch parameter
   - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1, BOE
     NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
     CMN N116BCP-EA2, CSW MNB601LS1-4
   - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
   - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
   - jd9365da:
      - Support Melfas lmfbx101117480 MIPI-DSI panel plus DT
      - Refactor for code sharing
   - panel-edp: fix name for HKC MB116AN01
   - jd9365da: fix "exit sleep" commands
   - jdi-fhd-r63452: simplify error handling with DSI multi-style
     helpers
   - mantix-mlaf057we51: simplify error handling with DSI multi-style
     helpers
   - simple:
      - support Innolux G070ACE-LH3 plus DT bindings
      - support On Tat Industrial Company KD50G21-40NT-A1 plus DT
        bindings
   - st7701:
      - decouple DSI and DRM code
      - add SPI support
      - support Anbernic RG28XX plus DT bindings

  mediatek:
   - support alpha blending
   - remove cl in struct cmdq_pkt
   - ovl adaptor fix
   - add power domain binding for mediatek DPI controller

  renesas:
   - rz-du: add support for RZ/G2UL plus DT bindings

  rockchip:
   - Improve DP sink-capability reporting
   - dw_hdmi: Support 4k@60Hz
   - vop:
      - Support RGB display on Rockchip RK3066
      - Support 4096px width

  sti:
   - convert to struct drm_edid

  stm:
   - Avoid UAF wih managed plane and CRTC helpers
   - Fix module owner
   - Fix error handling in probe
   - Depend on COMMON_CLK
   - ltdc:
      - Fix transparency after disabling plane
      - Remove unused interrupt

  tegra:
   - gr3d: improve PM domain handling
   - convert to struct drm_edid
   - Call drm_atomic_helper_shutdown()

  vc4:
   - fix PM during detect
   - replace DRM_ERROR() with drm_error()
   - v3d: simplify clock retrieval

  v3d:
   - Clean up perfmon

  virtio:
   - add DRM capset"

* tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel: (1326 commits)
  drm/xe: Fix missing conversion to xe_display_pm_runtime_resume
  drm/xe/xe2hpg: Add Wa_15016589081
  drm/xe: Don't keep stale pointer to bo->ggtt_node
  drm/xe: fix missing 'xe_vm_put'
  drm/xe: fix build warning with CONFIG_PM=n
  drm/xe: Suppress missing outer rpm protection warning
  drm/xe: prevent potential UAF in pf_provision_vf_ggtt()
  drm/amd/display: Add all planes on CRTC to state for overlay cursor
  drm/i915/bios: fix printk format width
  drm/i915/display: Fix BMG CCS modifiers
  drm/amdgpu: get rid of bogus includes of fdtable.h
  drm/amdkfd: CRIU fixes
  drm/amdgpu: fix a race in kfd_mem_export_dmabuf()
  drm: new helper: drm_gem_prime_handle_to_dmabuf()
  drm/amdgpu/atomfirmware: Silence UBSAN warning
  drm/amdgpu: Fix kdoc entry in 'amdgpu_vm_cpu_prepare'
  drm/amd/amdgpu: apply command submission parser for JPEG v1
  drm/amd/amdgpu: apply command submission parser for JPEG v2+
  drm/amd/pm: fix the pp_dpm_pcie issue on smu v14.0.2/3
  drm/amd/pm: update the features set on smu v14.0.2/3
  ...

1 files changed, 92 insertions, 52 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index bcacf2e35eba..f4628412dac4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1916,6 +1916,8 @@ static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev)
  */
 static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 {
+	int i;
+
 	if (amdgpu_sched_jobs < 4) {
 		dev_warn(adev->dev, "sched jobs (%d) must be at least 4\n",
 			 amdgpu_sched_jobs);
@@ -1970,6 +1972,9 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
+	for (i = 0; i < MAX_XCP; i++)
+		adev->enforce_isolation[i] = !!enforce_isolation;
+
 	return 0;
 }
 
@@ -2471,6 +2476,7 @@ out:
  */
 static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 {
+	struct amdgpu_ip_block *ip_block;
 	struct pci_dev *parent;
 	int i, r;
 	bool total;
@@ -2608,7 +2614,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (!total)
 		return -ENODEV;
 
-	amdgpu_amdkfd_device_probe(adev);
+	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
+	if (ip_block->status.valid != false)
+		amdgpu_amdkfd_device_probe(adev);
+
 	adev->cg_flags &= amdgpu_cg_mask;
 	adev->pg_flags &= amdgpu_pg_mask;
 
@@ -3948,6 +3957,27 @@ static void amdgpu_device_check_iommu_direct_map(struct amdgpu_device *adev)
 		adev->ram_is_direct_mapped = true;
 }
 
+#if defined(CONFIG_HSA_AMD_P2P)
+/**
+ * amdgpu_device_check_iommu_remap - Check if DMA remapping is enabled.
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * return if IOMMU remapping bar address
+ */
+static bool amdgpu_device_check_iommu_remap(struct amdgpu_device *adev)
+{
+	struct iommu_domain *domain;
+
+	domain = iommu_get_domain_for_dev(adev->dev);
+	if (domain && (domain->type == IOMMU_DOMAIN_DMA ||
+		domain->type ==	IOMMU_DOMAIN_DMA_FQ))
+		return true;
+
+	return false;
+}
+#endif
+
 static const struct attribute *amdgpu_dev_attributes[] = {
 	&dev_attr_pcie_replay_count.attr,
 	NULL
@@ -4055,6 +4085,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->notifier_lock);
 	mutex_init(&adev->pm.stable_pstate_ctx_lock);
 	mutex_init(&adev->benchmark_mutex);
+	mutex_init(&adev->gfx.reset_sem_mutex);
+	/* Initialize the mutex for cleaner shader isolation between GFX and compute processes */
+	mutex_init(&adev->enforce_isolation_mutex);
+	mutex_init(&adev->gfx.kfd_sch_mutex);
 
 	amdgpu_device_init_apu_flags(adev);
 
@@ -4086,6 +4120,21 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 			  amdgpu_device_delayed_init_work_handler);
 	INIT_DELAYED_WORK(&adev->gfx.gfx_off_delay_work,
 			  amdgpu_device_delay_enable_gfx_off);
+	/*
+	 * Initialize the enforce_isolation work structures for each XCP
+	 * partition.  This work handler is responsible for enforcing shader
+	 * isolation on AMD GPUs.  It counts the number of emitted fences for
+	 * each GFX and compute ring.  If there are any fences, it schedules
+	 * the `enforce_isolation_work` to be run after a delay.  If there are
+	 * no fences, it signals the Kernel Fusion Driver (KFD) to resume the
+	 * runqueue.
+	 */
+	for (i = 0; i < MAX_XCP; i++) {
+		INIT_DELAYED_WORK(&adev->gfx.enforce_isolation[i].work,
+				  amdgpu_gfx_enforce_isolation_handler);
+		adev->gfx.enforce_isolation[i].adev = adev;
+		adev->gfx.enforce_isolation[i].xcp_id = i;
+	}
 
 	INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func);
 
@@ -4482,6 +4531,9 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 {
 	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
+
+	if (adev->mman.initialized)
+		drain_workqueue(adev->mman.bdev.wq);
 	adev->shutdown = true;
 
 	/* make sure IB test finished before entering exclusive mode
@@ -4502,9 +4554,6 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	}
 	amdgpu_fence_driver_hw_fini(adev);
 
-	if (adev->mman.initialized)
-		drain_workqueue(adev->mman.bdev.wq);
-
 	if (adev->pm.sysfs_initialized)
 		amdgpu_pm_sysfs_fini(adev);
 	if (adev->ucode_sysfs_en)
@@ -5278,16 +5327,15 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 {
 	int i, r = 0;
 	struct amdgpu_job *job = NULL;
+	struct amdgpu_device *tmp_adev = reset_context->reset_req_dev;
 	bool need_full_reset =
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 
 	if (reset_context->reset_req_dev == adev)
 		job = reset_context->job;
 
-	if (amdgpu_sriov_vf(adev)) {
-		/* stop the data exchange thread */
-		amdgpu_virt_fini_data_exchange(adev);
-	}
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_pre_reset(adev);
 
 	amdgpu_fence_driver_isr_toggle(adev, true);
 
@@ -5336,6 +5384,16 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 			}
 		}
 
+		if (!test_bit(AMDGPU_SKIP_COREDUMP, &reset_context->flags)) {
+			dev_info(tmp_adev->dev, "Dumping IP State\n");
+			/* Trigger ip dump before we reset the asic */
+			for (i = 0; i < tmp_adev->num_ip_blocks; i++)
+				if (tmp_adev->ip_blocks[i].version->funcs->dump_ip_state)
+					tmp_adev->ip_blocks[i].version->funcs
+						->dump_ip_state((void *)tmp_adev);
+			dev_info(tmp_adev->dev, "Dumping IP State Completed\n");
+		}
+
 		if (need_full_reset)
 			r = amdgpu_device_ip_suspend(adev);
 		if (need_full_reset)
@@ -5348,47 +5406,17 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	return r;
 }
 
-static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
-{
-	int i;
-
-	lockdep_assert_held(&adev->reset_domain->sem);
-
-	for (i = 0; i < adev->reset_info.num_regs; i++) {
-		adev->reset_info.reset_dump_reg_value[i] =
-			RREG32(adev->reset_info.reset_dump_reg_list[i]);
-
-		trace_amdgpu_reset_reg_dumps(adev->reset_info.reset_dump_reg_list[i],
-					     adev->reset_info.reset_dump_reg_value[i]);
-	}
-
-	return 0;
-}
-
 int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 			 struct amdgpu_reset_context *reset_context)
 {
 	struct amdgpu_device *tmp_adev = NULL;
 	bool need_full_reset, skip_hw_reset, vram_lost = false;
 	int r = 0;
-	uint32_t i;
 
 	/* Try reset handler method first */
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 				    reset_list);
 
-	if (!test_bit(AMDGPU_SKIP_COREDUMP, &reset_context->flags)) {
-		amdgpu_reset_reg_dumps(tmp_adev);
-
-		dev_info(tmp_adev->dev, "Dumping IP State\n");
-		/* Trigger ip dump before we reset the asic */
-		for (i = 0; i < tmp_adev->num_ip_blocks; i++)
-			if (tmp_adev->ip_blocks[i].version->funcs->dump_ip_state)
-				tmp_adev->ip_blocks[i].version->funcs
-				->dump_ip_state((void *)tmp_adev);
-		dev_info(tmp_adev->dev, "Dumping IP State Completed\n");
-	}
-
 	reset_context->reset_device_list = device_list_handle;
 	r = amdgpu_reset_perform_reset(tmp_adev, reset_context);
 	/* If reset handler not implemented, continue; otherwise return */
@@ -5461,7 +5489,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				vram_lost = amdgpu_device_check_vram_lost(tmp_adev);
 
 				if (!test_bit(AMDGPU_SKIP_COREDUMP, &reset_context->flags))
-					amdgpu_coredump(tmp_adev, vram_lost, reset_context);
+					amdgpu_coredump(tmp_adev, false, vram_lost, reset_context->job);
 
 				if (vram_lost) {
 					DRM_INFO("VRAM is lost due to GPU reset!\n");
@@ -5513,7 +5541,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				 * bad_page_threshold value to fix this once
 				 * probing driver again.
 				 */
-				if (!amdgpu_ras_eeprom_check_err_threshold(tmp_adev)) {
+				if (!amdgpu_ras_is_rma(tmp_adev)) {
 					/* must succeed. */
 					amdgpu_ras_resume(tmp_adev);
 				} else {
@@ -5879,7 +5907,7 @@ skip_hw_reset:
 			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
-			drm_sched_start(&ring->sched, true);
+			drm_sched_start(&ring->sched);
 		}
 
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)
@@ -5891,8 +5919,14 @@ skip_hw_reset:
 		tmp_adev->asic_reset_res = 0;
 
 		if (r) {
-			/* bad news, how to tell it to userspace ? */
-			dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", atomic_read(&tmp_adev->gpu_reset_counter));
+			/* bad news, how to tell it to userspace ?
+			 * for ras error, we should report GPU bad status instead of
+			 * reset failure
+			 */
+			if (reset_context->src != AMDGPU_RESET_SRC_RAS ||
+			    !amdgpu_ras_eeprom_check_err_threshold(tmp_adev))
+				dev_info(tmp_adev->dev, "GPU reset(%d) failed\n",
+					atomic_read(&tmp_adev->gpu_reset_counter));
 			amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
 		} else {
 			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));
@@ -6138,18 +6172,24 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 				      struct amdgpu_device *peer_adev)
 {
 #ifdef CONFIG_HSA_AMD_P2P
-	uint64_t address_mask = peer_adev->dev->dma_mask ?
-		~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
-	resource_size_t aper_limit =
-		adev->gmc.aper_base + adev->gmc.aper_size - 1;
 	bool p2p_access =
 		!adev->gmc.xgmi.connected_to_cpu &&
 		!(pci_p2pdma_distance(adev->pdev, peer_adev->dev, false) < 0);
 
-	return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size &&
-		adev->gmc.real_vram_size == adev->gmc.visible_vram_size &&
-		!(adev->gmc.aper_base & address_mask ||
-		  aper_limit & address_mask));
+	bool is_large_bar = adev->gmc.visible_vram_size &&
+		adev->gmc.real_vram_size == adev->gmc.visible_vram_size;
+	bool p2p_addressable = amdgpu_device_check_iommu_remap(peer_adev);
+
+	if (!p2p_addressable) {
+		uint64_t address_mask = peer_adev->dev->dma_mask ?
+			~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
+		resource_size_t aper_limit =
+			adev->gmc.aper_base + adev->gmc.aper_size - 1;
+
+		p2p_addressable = !(adev->gmc.aper_base & address_mask ||
+				     aper_limit & address_mask);
+	}
+	return is_large_bar && p2p_access && p2p_addressable;
 #else
 	return false;
 #endif
@@ -6374,7 +6414,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
-		drm_sched_start(&ring->sched, true);
+		drm_sched_start(&ring->sched);
 	}
 
 	amdgpu_device_unset_mp1_state(adev);