Merge tag 'amd-drm-next-6.9-2024-03-01' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.9-2024-03-01:

amdgpu:
- GC 11.5.1 updates
- Misc display cleanups
- NBIO 7.9 updates
- Backlight fixes
- DMUB fixes
- MPO fixes
- atomfirmware table updates
- SR-IOV fixes
- VCN 4.x updates
- use RMW accessors for pci config registers
- PSR fixes
- Suspend/resume fixes
- RAS fixes
- ABM fixes
- Misc code cleanups
- SI DPM fix
- Revert freesync video

amdkfd:
- Misc cleanups
- Error handling fixes

radeon:
- use RMW accessors for pci config registers

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240301204857.13960-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

41 files changed, 391 insertions, 283 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9246bca0a008..9c62552bec34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -194,6 +194,7 @@ extern int amdgpu_emu_mode;
 extern uint amdgpu_smu_memory_pool_size;
 extern int amdgpu_smu_pptable_id;
 extern uint amdgpu_dc_feature_mask;
+extern uint amdgpu_freesync_vid_mode;
 extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dc_visual_confirm;
 extern int amdgpu_dm_abm_level;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 190039f14c30..f5f2945711be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -742,6 +742,11 @@ void amdgpu_amdkfd_debug_mem_fence(struct amdgpu_device *adev)
 	amdgpu_device_flush_hdp(adev, NULL);
 }
 
+bool amdgpu_amdkfd_is_fed(struct amdgpu_device *adev)
+{
+	return amdgpu_ras_get_fed_status(adev);
+}
+
 void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev,
 	enum amdgpu_ras_block block, bool reset)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index e60f63ccf79a..0ef223c2affb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -320,7 +320,7 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
 					     void **kptr, uint64_t *size);
 void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_mem *mem);
 
-int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo);
+int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_bo *bo);
 
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence __rcu **ef);
@@ -337,6 +337,7 @@ int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev,
 				struct tile_config *config);
 void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev,
 			enum amdgpu_ras_block block, bool reset);
+bool amdgpu_amdkfd_is_fed(struct amdgpu_device *adev);
 bool amdgpu_amdkfd_bo_mapped_to_dev(struct amdgpu_device *adev, struct kgd_mem *mem);
 void amdgpu_amdkfd_block_mmu_notifications(void *p);
 int amdgpu_amdkfd_criu_resume(void *p);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 5cd84f72bf26..14dc9d2d8d53 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2189,13 +2189,12 @@ int amdgpu_amdkfd_gpuvm_sync_memory(
 
 /**
  * amdgpu_amdkfd_map_gtt_bo_to_gart - Map BO to GART and increment reference count
- * @adev: Device to which allocated BO belongs
  * @bo: Buffer object to be mapped
  *
  * Before return, bo reference count is incremented. To release the reference and unpin/
  * unmap the BO, call amdgpu_amdkfd_free_gtt_mem.
  */
-int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo)
+int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_bo *bo)
 {
 	int ret;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b0ea4ddc8e72..e68bd6f8a6a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4040,8 +4040,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * early on during init and before calling to RREG32.
 	 */
 	adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev");
-	if (!adev->reset_domain)
-		return -ENOMEM;
+	if (!adev->reset_domain) {
+		r = -ENOMEM;
+		goto unmap_memory;
+	}
 
 	/* detect hw virtualization here */
 	amdgpu_detect_virtualization(adev);
@@ -4051,20 +4053,20 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_device_get_job_timeout_settings(adev);
 	if (r) {
 		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
-		return r;
+		goto unmap_memory;
 	}
 
 	/* early init functions */
 	r = amdgpu_device_ip_early_init(adev);
 	if (r)
-		return r;
+		goto unmap_memory;
 
 	amdgpu_device_set_mcbp(adev);
 
 	/* Get rid of things like offb */
 	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
 	if (r)
-		return r;
+		goto unmap_memory;
 
 	/* Enable TMZ based on IP_VERSION */
 	amdgpu_gmc_tmz_set(adev);
@@ -4074,7 +4076,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (adev->gmc.xgmi.supported) {
 		r = adev->gfxhub.funcs->get_xgmi_info(adev);
 		if (r)
-			return r;
+			goto unmap_memory;
 	}
 
 	/* enable PCIE atomic ops */
@@ -4343,6 +4345,8 @@ release_ras_con:
 failed:
 	amdgpu_vf_error_trans_all(adev);
 
+unmap_memory:
+	iounmap(adev->rmmio);
 	return r;
 }
 
@@ -5321,6 +5325,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 		if (need_full_reset) {
 			/* post card */
+			amdgpu_ras_set_fed(tmp_adev, false);
 			r = amdgpu_device_asic_init(tmp_adev);
 			if (r) {
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 78588334577a..502333725b49 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1683,6 +1683,7 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		amdgpu_device_ip_block_add(adev, &soc21_common_ip_block);
 		break;
 	default:
@@ -1730,6 +1731,7 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		amdgpu_device_ip_block_add(adev, &gmc_v11_0_ip_block);
 		break;
 	default:
@@ -2003,6 +2005,7 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		amdgpu_device_ip_block_add(adev, &gfx_v11_0_ip_block);
 		break;
 	default:
@@ -2137,6 +2140,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &jpeg_v4_0_3_ip_block);
 			break;
 		case IP_VERSION(4, 0, 5):
+		case IP_VERSION(4, 0, 6):
 			amdgpu_device_ip_block_add(adev, &vcn_v4_0_5_ip_block);
 			amdgpu_device_ip_block_add(adev, &jpeg_v4_0_5_ip_block);
 			break;
@@ -2182,6 +2186,7 @@ static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		amdgpu_device_ip_block_add(adev, &mes_v11_0_ip_block);
 		adev->enable_mes = true;
 		adev->enable_mes_kiq = true;
@@ -2460,6 +2465,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->family = AMDGPU_FAMILY_GC_11_0_1;
 		break;
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		adev->family = AMDGPU_FAMILY_GC_11_5_0;
 		break;
 	default:
@@ -2479,6 +2485,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		adev->flags |= AMD_IS_APU;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index b8fbe97efe1d..3ecc7ef95172 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -1350,14 +1350,6 @@ int amdgpu_display_modeset_create_props(struct amdgpu_device *adev)
 					 "dither",
 					 amdgpu_dither_enum_list, sz);
 
-	if (adev->dc_enabled) {
-		adev->mode_info.abm_level_property =
-			drm_property_create_range(adev_to_drm(adev), 0,
-						  "abm level", 0, 4);
-		if (!adev->mode_info.abm_level_property)
-			return -ENOMEM;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index af7fae7907d7..6acffedf648c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -199,6 +199,7 @@ int amdgpu_mes_kiq;
 int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = -1; /* auto */
+uint amdgpu_freesync_vid_mode;
 int amdgpu_reset_method = -1; /* auto */
 int amdgpu_num_kcq = -1;
 int amdgpu_smartshift_bias;
@@ -884,6 +885,32 @@ MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto (default), 0 = off, 1 = on)
 module_param_named(tmz, amdgpu_tmz, int, 0444);
 
 /**
+ * DOC: freesync_video (uint)
+ * Enable the optimization to adjust front porch timing to achieve seamless
+ * mode change experience when setting a freesync supported mode for which full
+ * modeset is not needed.
+ *
+ * The Display Core will add a set of modes derived from the base FreeSync
+ * video mode into the corresponding connector's mode list based on commonly
+ * used refresh rates and VRR range of the connected display, when users enable
+ * this feature. From the userspace perspective, they can see a seamless mode
+ * change experience when the change between different refresh rates under the
+ * same resolution. Additionally, userspace applications such as Video playback
+ * can read this modeset list and change the refresh rate based on the video
+ * frame rate. Finally, the userspace can also derive an appropriate mode for a
+ * particular refresh rate based on the FreeSync Mode and add it to the
+ * connector's mode list.
+ *
+ * Note: This is an experimental feature.
+ *
+ * The default value: 0 (off).
+ */
+MODULE_PARM_DESC(
+	freesync_video,
+	"Enable freesync modesetting optimization feature (0 = off (default), 1 = on)");
+module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
+
+/**
  * DOC: reset_method (int)
  * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
  */
@@ -2764,8 +2791,7 @@ static int amdgpu_pmops_runtime_idle(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
-	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
-	int ret = 1;
+	int ret;
 
 	if (adev->pm.rpm_mode == AMDGPU_RUNPM_NONE) {
 		pm_runtime_forbid(dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 70bff8cecfda..10832b470448 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -61,9 +61,7 @@ static struct kmem_cache *amdgpu_fence_slab;
 
 int amdgpu_fence_slab_init(void)
 {
-	amdgpu_fence_slab = kmem_cache_create(
-		"amdgpu_fence", sizeof(struct amdgpu_fence), 0,
-		SLAB_HWCACHE_ALIGN, NULL);
+	amdgpu_fence_slab = KMEM_CACHE(amdgpu_fence, SLAB_HWCACHE_ALIGN);
 	if (!amdgpu_fence_slab)
 		return -ENOMEM;
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index f04803a44b44..f8b48fd93108 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -304,11 +304,11 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
 	return -EINVAL;
 }
 
-int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
-			     struct amdgpu_ring *ring,
-			     struct amdgpu_irq_src *irq, int xcc_id)
+int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev, int xcc_id)
 {
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_id];
+	struct amdgpu_irq_src *irq = &kiq->irq;
+	struct amdgpu_ring *ring = &kiq->ring;
 	int r = 0;
 
 	spin_lock_init(&kiq->ring_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index f23bafec71c5..8fcf889ddce9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -471,9 +471,7 @@ static inline u32 amdgpu_gfx_create_bitmask(u32 bit_width)
 void amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se,
 				 unsigned max_sh);
 
-int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
-			     struct amdgpu_ring *ring,
-			     struct amdgpu_irq_src *irq, int xcc_id);
+int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev, int xcc_id);
 
 void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index d4a848c51a83..be4629cdac04 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -843,6 +843,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case IP_VERSION(10, 3, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		/* Don't enable it by default yet.
 		 */
 		if (amdgpu_tmz < 1) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 2e4911050cc5..1fe21a70ddd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -324,8 +324,6 @@ struct amdgpu_mode_info {
 	struct drm_property *audio_property;
 	/* FMT dithering */
 	struct drm_property *dither_property;
-	/* Adaptive Backlight Modulation (power feature) */
-	struct drm_property *abm_level_property;
 	/* hardcoded DFP edid from BIOS */
 	struct edid *bios_hardcoded_edid;
 	int bios_hardcoded_edid_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
index 51ca544a7094..d085687a47ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
@@ -53,14 +53,6 @@ u64 amdgpu_nbio_get_pcie_replay_count(struct amdgpu_device *adev)
 	return 0;
 }
 
-void amdgpu_nbio_get_pcie_usage(struct amdgpu_device *adev, uint64_t *count0,
-				uint64_t *count1)
-{
-	if (adev->nbio.funcs->get_pcie_usage)
-		adev->nbio.funcs->get_pcie_usage(adev, count0, count1);
-
-}
-
 int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
 {
 	int r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
index 65e35059de40..7b8c03be1d9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
@@ -102,8 +102,6 @@ struct amdgpu_nbio_funcs {
 	u32 (*get_memory_partition_mode)(struct amdgpu_device *adev,
 					 u32 *supp_modes);
 	u64 (*get_pcie_replay_count)(struct amdgpu_device *adev);
-	void (*get_pcie_usage)(struct amdgpu_device *adev, uint64_t *count0,
-					uint64_t *count1);
 };
 
 struct amdgpu_nbio {
@@ -116,7 +114,6 @@ struct amdgpu_nbio {
 };
 
 int amdgpu_nbio_ras_sw_init(struct amdgpu_device *adev);
-void amdgpu_nbio_get_pcie_usage(struct amdgpu_device *adev, uint64_t *count0, uint64_t *count1);
 int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block);
 u64 amdgpu_nbio_get_pcie_replay_count(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 46f3d1013e8c..8ebab6f22e5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2439,6 +2439,18 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 				set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 
+				/* For any RAS error that needs a full reset to
+				 * recover, set the fatal error status
+				 */
+				if (hive) {
+					list_for_each_entry(remote_adev,
+							    &hive->device_list,
+							    gmc.xgmi.head)
+						amdgpu_ras_set_fed(remote_adev,
+								   true);
+				} else {
+					amdgpu_ras_set_fed(adev, true);
+				}
 				psp_fatal_error_recovery_quirk(&adev->psp);
 			}
 		}
@@ -3440,6 +3452,26 @@ int amdgpu_ras_fini(struct amdgpu_device *adev)
 	return 0;
 }
 
+bool amdgpu_ras_get_fed_status(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *ras;
+
+	ras = amdgpu_ras_get_context(adev);
+	if (!ras)
+		return false;
+
+	return atomic_read(&ras->fed);
+}
+
+void amdgpu_ras_set_fed(struct amdgpu_device *adev, bool status)
+{
+	struct amdgpu_ras *ras;
+
+	ras = amdgpu_ras_get_context(adev);
+	if (ras)
+		atomic_set(&ras->fed, !!status);
+}
+
 void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 {
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
@@ -3620,6 +3652,7 @@ int amdgpu_ras_is_supported(struct amdgpu_device *adev,
 	     block == AMDGPU_RAS_BLOCK__SDMA ||
 	     block == AMDGPU_RAS_BLOCK__VCN ||
 	     block == AMDGPU_RAS_BLOCK__JPEG) &&
+		(amdgpu_ras_mask & (1 << block)) &&
 	    amdgpu_ras_is_poison_mode_supported(adev) &&
 	    amdgpu_ras_get_ras_block(adev, block, 0))
 		ret = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index d10e5bb0e52f..e0f8ce9d8440 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -477,6 +477,8 @@ struct amdgpu_ras {
 	wait_queue_head_t page_retirement_wq;
 	struct mutex page_retirement_lock;
 	atomic_t page_retirement_req_cnt;
+	/* Fatal error detected flag */
+	atomic_t fed;
 };
 
 struct ras_fs_data {
@@ -873,4 +875,8 @@ void amdgpu_ras_add_mca_err_addr(struct ras_err_info *err_info,
 
 void amdgpu_ras_del_mca_err_addr(struct ras_err_info *err_info,
 		struct ras_err_addr *mca_err_addr);
+
+void amdgpu_ras_set_fed(struct amdgpu_device *adev, bool status);
+bool amdgpu_ras_get_fed_status(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
index e1ee1c7117fb..d234b7ccfaaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
@@ -159,9 +159,7 @@ int amdgpu_ring_mux_init(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring,
 	mux->ring_entry_size = entry_size;
 	mux->s_resubmit = false;
 
-	amdgpu_mux_chunk_slab = kmem_cache_create("amdgpu_mux_chunk",
-						  sizeof(struct amdgpu_mux_chunk), 0,
-						  SLAB_HWCACHE_ALIGN, NULL);
+	amdgpu_mux_chunk_slab = KMEM_CACHE(amdgpu_mux_chunk, SLAB_HWCACHE_ALIGN);
 	if (!amdgpu_mux_chunk_slab) {
 		DRM_ERROR("create amdgpu_mux_chunk cache failed\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 1b013a44ca99..bdf1ef825d89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -441,9 +441,7 @@ void amdgpu_sync_free(struct amdgpu_sync *sync)
  */
 int amdgpu_sync_init(void)
 {
-	amdgpu_sync_slab = kmem_cache_create(
-		"amdgpu_sync", sizeof(struct amdgpu_sync_entry), 0,
-		SLAB_HWCACHE_ALIGN, NULL);
+	amdgpu_sync_slab = KMEM_CACHE(amdgpu_sync_entry, SLAB_HWCACHE_ALIGN);
 	if (!amdgpu_sync_slab)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index eb2a88991206..b2535023764f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -59,6 +59,7 @@
 #define FIRMWARE_VCN4_0_3		"amdgpu/vcn_4_0_3.bin"
 #define FIRMWARE_VCN4_0_4		"amdgpu/vcn_4_0_4.bin"
 #define FIRMWARE_VCN4_0_5		"amdgpu/vcn_4_0_5.bin"
+#define FIRMWARE_VCN4_0_6		"amdgpu/vcn_4_0_6.bin"
 #define FIRMWARE_VCN5_0_0		"amdgpu/vcn_5_0_0.bin"
 
 MODULE_FIRMWARE(FIRMWARE_RAVEN);
@@ -83,6 +84,7 @@ MODULE_FIRMWARE(FIRMWARE_VCN4_0_2);
 MODULE_FIRMWARE(FIRMWARE_VCN4_0_3);
 MODULE_FIRMWARE(FIRMWARE_VCN4_0_4);
 MODULE_FIRMWARE(FIRMWARE_VCN4_0_5);
+MODULE_FIRMWARE(FIRMWARE_VCN4_0_6);
 MODULE_FIRMWARE(FIRMWARE_VCN5_0_0);
 
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 6ff7d3fb2008..7a4eae36778a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -979,7 +979,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 		 * SCRATCH_REG0 	= read/write value
 		 * SCRATCH_REG1[30:28]	= command
 		 * SCRATCH_REG1[19:0]	= address in dword
-		 * SCRATCH_REG1[26:24]	= Error reporting
+		 * SCRATCH_REG1[27:24]	= Error reporting
 		 */
 		writel(v, scratch_reg0);
 		writel((offset | flag), scratch_reg1);
@@ -993,7 +993,8 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 			udelay(10);
 		}
 
-		if (i >= timeout) {
+		tmp = readl(scratch_reg1);
+		if (i >= timeout || (tmp & AMDGPU_RLCG_SCRATCH1_ERROR_MASK) != 0) {
 			if (amdgpu_sriov_rlcg_error_report_enabled(adev)) {
 				if (tmp & AMDGPU_RLCG_VFGATE_DISABLED) {
 					dev_err(adev->dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index fa7be5f277b9..3f59b7b5523f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -45,6 +45,7 @@
 #define AMDGPU_RLCG_REG_NOT_IN_RANGE		0x1000000
 
 #define AMDGPU_RLCG_SCRATCH1_ADDRESS_MASK	0xFFFFF
+#define AMDGPU_RLCG_SCRATCH1_ERROR_MASK	0xF000000
 
 /* all asic after AI use this offset */
 #define mmRCC_IOV_FUNC_IDENTIFIER 0xDE5
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index b888613f653f..72362df352f6 100644
--- a/drivers/