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/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -320,7 +320,7 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr,
 				DEBUG("IMM 0x%02X\n", val);
 			return val;
 		}
-		return 0;
+		break;
 	case ATOM_ARG_PLL:
 		idx = U8(*ptr);
 		(*ptr)++;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 4dfaa017cf7f..a3a643254d7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1638,28 +1638,18 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev)
 								   PCI_EXP_LNKCTL_HAWD);
 
 				/* linkctl2 */
-				pcie_capability_read_word(root, PCI_EXP_LNKCTL2,
-							  &tmp16);
-				tmp16 &= ~(PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN);
-				tmp16 |= (bridge_cfg2 &
-					  (PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN));
-				pcie_capability_write_word(root,
-							   PCI_EXP_LNKCTL2,
-							   tmp16);
-
-				pcie_capability_read_word(adev->pdev,
-							  PCI_EXP_LNKCTL2,
-							  &tmp16);
-				tmp16 &= ~(PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN);
-				tmp16 |= (gpu_cfg2 &
-					  (PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN));
-				pcie_capability_write_word(adev->pdev,
-							   PCI_EXP_LNKCTL2,
-							   tmp16);
+				pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL2,
+								   PCI_EXP_LNKCTL2_ENTER_COMP |
+								   PCI_EXP_LNKCTL2_TX_MARGIN,
+								   bridge_cfg2 &
+								   (PCI_EXP_LNKCTL2_ENTER_COMP |
+								    PCI_EXP_LNKCTL2_TX_MARGIN));
+				pcie_capability_clear_and_set_word(adev->pdev, PCI_EXP_LNKCTL2,
+								   PCI_EXP_LNKCTL2_ENTER_COMP |
+								   PCI_EXP_LNKCTL2_TX_MARGIN,
+								   gpu_cfg2 &
+								   (PCI_EXP_LNKCTL2_ENTER_COMP |
+								    PCI_EXP_LNKCTL2_TX_MARGIN));
 
 				tmp = RREG32_PCIE(ixPCIE_LC_CNTL4);
 				tmp &= ~PCIE_LC_CNTL4__LC_SET_QUIESCE_MASK;
@@ -1674,16 +1664,15 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev)
 	speed_cntl &= ~PCIE_LC_SPEED_CNTL__LC_FORCE_DIS_SW_SPEED_CHANGE_MASK;
 	WREG32_PCIE(ixPCIE_LC_SPEED_CNTL, speed_cntl);
 
-	pcie_capability_read_word(adev->pdev, PCI_EXP_LNKCTL2, &tmp16);
-	tmp16 &= ~PCI_EXP_LNKCTL2_TLS;
-
+	tmp16 = 0;
 	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
 		tmp16 |= PCI_EXP_LNKCTL2_TLS_8_0GT; /* gen3 */
 	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
 		tmp16 |= PCI_EXP_LNKCTL2_TLS_5_0GT; /* gen2 */
 	else
 		tmp16 |= PCI_EXP_LNKCTL2_TLS_2_5GT; /* gen1 */
-	pcie_capability_write_word(adev->pdev, PCI_EXP_LNKCTL2, tmp16);
+	pcie_capability_clear_and_set_word(adev->pdev, PCI_EXP_LNKCTL2,
+					   PCI_EXP_LNKCTL2_TLS, tmp16);
 
 	speed_cntl = RREG32_PCIE(ixPCIE_LC_SPEED_CNTL);
 	speed_cntl |= PCIE_LC_SPEED_CNTL__LC_INITIATE_LINK_SPEED_CHANGE_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index b02d63328f1c..691fa40e4e01 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4490,7 +4490,7 @@ static int gfx_v10_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 static int gfx_v10_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id = 0;
-	struct amdgpu_kiq *kiq;
+	int xcc_id = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
@@ -4619,8 +4619,7 @@ static int gfx_v10_0_sw_init(void *handle)
 			return r;
 		}
 
-		kiq = &adev->gfx.kiq[0];
-		r = amdgpu_gfx_kiq_init_ring(adev, &kiq->ring, &kiq->irq, 0);
+		r = amdgpu_gfx_kiq_init_ring(adev, xcc_id);
 		if (r)
 			return r;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 2fb1342d5bd9..0d90d60a21d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -89,6 +89,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_0_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_pfp.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_me.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_mec.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_rlc.bin");
 
 static const struct soc15_reg_golden golden_settings_gc_11_0[] = {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000)
@@ -907,6 +911,7 @@ static int gfx_v11_0_gpu_early_init(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->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -1329,7 +1334,7 @@ static int gfx_v11_0_rlc_backdoor_autoload_enable(struct amdgpu_device *adev)
 static int gfx_v11_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id = 0;
-	struct amdgpu_kiq *kiq;
+	int xcc_id = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
@@ -1346,6 +1351,7 @@ static int gfx_v11_0_sw_init(void *handle)
 	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->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
@@ -1454,8 +1460,7 @@ static int gfx_v11_0_sw_init(void *handle)
 			return r;
 		}
 
-		kiq = &adev->gfx.kiq[0];
-		r = amdgpu_gfx_kiq_init_ring(adev, &kiq->ring, &kiq->irq, 0);
+		r = amdgpu_gfx_kiq_init_ring(adev, xcc_id);
 		if (r)
 			return r;
 	}
@@ -2588,7 +2593,8 @@ static int gfx_v11_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev)
 			    IP_VERSION(11, 0, 1) ||
 		    amdgpu_ip_version(adev, GC_HWIP, 0) ==
 			    IP_VERSION(11, 0, 4) ||
-		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 0))
+		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 0) ||
+		    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 5, 1))
 			bootload_status = RREG32_SOC15(GC, 0,
 					regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1);
 		else
@@ -5082,6 +5088,7 @@ static void gfx_v11_cntl_power_gating(struct amdgpu_device *adev, bool enable)
 		case IP_VERSION(11, 0, 1):
 		case IP_VERSION(11, 0, 4):
 		case IP_VERSION(11, 5, 0):
+		case IP_VERSION(11, 5, 1):
 			WREG32_SOC15(GC, 0, regRLC_PG_DELAY_3, RLC_PG_DELAY_3_DEFAULT_GC_11_0_1);
 			break;
 		default:
@@ -5117,6 +5124,7 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		if (!enable)
 			amdgpu_gfx_off_ctrl(adev, false);
 
@@ -5148,6 +5156,7 @@ static int gfx_v11_0_set_clockgating_state(void *handle,
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 	        gfx_v11_0_update_gfx_clock_gating(adev,
 	                        state ==  AMD_CG_STATE_GATE);
 	        break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index ea174b76ee70..b97ea62212b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1900,8 +1900,8 @@ static void gfx_v8_0_sq_irq_work_func(struct work_struct *work);
 static int gfx_v8_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id;
+	int xcc_id = 0;
 	struct amdgpu_ring *ring;
-	struct amdgpu_kiq *kiq;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	switch (adev->asic_type) {
@@ -2022,8 +2022,7 @@ static int gfx_v8_0_sw_init(void *handle)
 		return r;
 	}
 
-	kiq = &adev->gfx.kiq[0];
-	r = amdgpu_gfx_kiq_init_ring(adev, &kiq->ring, &kiq->irq, 0);
+	r = amdgpu_gfx_kiq_init_ring(adev, xcc_id);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 169d45268ef6..7669f82aa1da 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1997,8 +1997,8 @@ static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 static int gfx_v9_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id;
+	int xcc_id = 0;
 	struct amdgpu_ring *ring;
-	struct amdgpu_kiq *kiq;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	unsigned int hw_prio;
 
@@ -2151,8 +2151,7 @@ static int gfx_v9_0_sw_init(void *handle)
 		return r;
 	}
 
-	kiq = &adev->gfx.kiq[0];
-	r = amdgpu_gfx_kiq_init_ring(adev, &kiq->ring, &kiq->irq, 0);
+	r = amdgpu_gfx_kiq_init_ring(adev, xcc_id);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index aace4594a603..b53c8fd4e8cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -843,7 +843,6 @@ static int gfx_v9_4_3_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 static int gfx_v9_4_3_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id, xcc_id, num_xcc;
-	struct amdgpu_kiq *kiq;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	adev->gfx.mec.num_mec = 2;
@@ -912,8 +911,7 @@ static int gfx_v9_4_3_sw_init(void *handle)
 			return r;
 		}
 
-		kiq = &adev->gfx.kiq[xcc_id];
-		r = amdgpu_gfx_kiq_init_ring(adev, &kiq->ring, &kiq->irq, xcc_id);
+		r = amdgpu_gfx_kiq_init_ring(adev, xcc_id);
 		if (r)
 			return r;
 
@@ -3953,6 +3951,9 @@ static void gfx_v9_4_3_inst_enable_watchdog_timer(struct amdgpu_device *adev,
 	uint32_t i;
 	uint32_t data;
 
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	data = RREG32_SOC15(GC, GET_INST(GC, 0), regSQ_TIMEOUT_CONFIG);
 	data = REG_SET_FIELD(data, SQ_TIMEOUT_CONFIG, TIMEOUT_FATAL_DISABLE,
 			     amdgpu_watchdog_timer.timeout_fatal_disable ? 1 : 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 998daa702b44..a3812f0036a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -587,6 +587,7 @@ static void gmc_v11_0_set_gfxhub_funcs(struct amdgpu_device *adev)
 		adev->gfxhub.funcs = &gfxhub_v3_0_3_funcs;
 		break;
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		adev->gfxhub.funcs = &gfxhub_v11_5_0_funcs;
 		break;
 	default:
@@ -748,6 +749,7 @@ static int gmc_v11_0_sw_init(void *handle)
 	case IP_VERSION(11, 0, 3):
 	case IP_VERSION(11, 0, 4):
 	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(11, 5, 1):
 		set_bit(AMDGPU_GFXHUB(0), adev->vmhubs_mask);
 		set_bit(AMDGPU_MMHUB0(0), adev->vmhubs_mask);
 		/*
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index d442ae85162d..1439e62e9378 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -496,14 +496,14 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 				if (j >= AMDGPU_MMHUB0(0))
 					tmp = RREG32_SOC15_IP(MMHUB, reg);
 				else
-					tmp = RREG32_SOC15_IP(GC, reg);
+					tmp = RREG32_XCC(reg, j);
 
 				tmp &= ~bits;
 
 				if (j >= AMDGPU_MMHUB0(0))
 					WREG32_SOC15_IP(MMHUB, reg, tmp);
 				else
-					WREG32_SOC15_IP(GC, reg, tmp);
+					WREG32_XCC(reg, tmp, j);
 			}
 		}
 		break;
@@ -524,14 +524,14 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 				if (j >= AMDGPU_MMHUB0(0))
 					tmp = RREG32_SOC15_IP(MMHUB, reg);
 				else
-					tmp = RREG32_SOC15_IP(GC, reg);
+					tmp = RREG32_XCC(reg, j);
 
 				tmp |= bits;
 
 				if (j >= AMDGPU_MMHUB0(0))
 					WREG32_SOC15_IP(MMHUB, reg, tmp);
 				else
-					WREG32_SOC15_IP(GC, reg, tmp);
+					WREG32_XCC(reg, tmp, j);
 			}
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index c0bdab3bf0e4..3e91a8e42c21 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -37,6 +37,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_imu.bin");
 
 static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 8d1754e35605..edf5bcdd2bc9 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -53,6 +53,11 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
 
 static void jpeg_v4_0_5_dec_ring_set_wptr(struct amdgpu_ring *ring);
 
+static int amdgpu_ih_clientid_jpeg[] = {
+	SOC15_IH_CLIENTID_VCN,
+	SOC15_IH_CLIENTID_VCN1
+};
+
 /**
  * jpeg_v4_0_5_early_init - set function pointers
  *
@@ -64,8 +69,20 @@ static int jpeg_v4_0_5_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	switch (amdgpu_ip_version(adev, UVD_HWIP, 0)) {
+	case IP_VERSION(4, 0, 5):
+		adev->jpeg.num_jpeg_inst = 1;
+		break;
+	case IP_VERSION(4, 0, 6):
+		adev->jpeg.num_jpeg_inst = 2;
+		break;
+	default:
+		DRM_DEV_ERROR(adev->dev,
+			"Failed to init vcn ip block(UVD_HWIP:0x%x)\n",
+			amdgpu_ip_version(adev, UVD_HWIP, 0));
+		return -EINVAL;
+	}
 
-	adev->jpeg.num_jpeg_inst = 1;
 	adev->jpeg.num_jpeg_rings = 1;
 
 	jpeg_v4_0_5_set_dec_ring_funcs(adev);
@@ -85,25 +102,30 @@ static int jpeg_v4_0_5_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring;
-	int r;
+	int r, i;
 
-	/* JPEG TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
-		VCN_4_0__SRCID__JPEG_DECODE, &adev->jpeg.inst->irq);
-	if (r)
-		return r;
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
 
-	/* JPEG DJPEG POISON EVENT */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
-			VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst->irq);
-	if (r)
-		return r;
+		/* JPEG TRAP */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i],
+				VCN_4_0__SRCID__JPEG_DECODE, &adev->jpeg.inst[i].irq);
+		if (r)
+			return r;
 
-	/* JPEG EJPEG POISON EVENT */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
-			VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst->irq);
-	if (r)
-		return r;
+		/* JPEG DJPEG POISON EVENT */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i],
+			VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst[i].irq);
+		if (r)
+			return r;
+
+		/* JPEG EJPEG POISON EVENT */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i],
+			VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst[i].irq);
+		if (r)
+			return r;
+	}
 
 	r = amdgpu_jpeg_sw_init(adev);
 	if (r)
@@ -113,21 +135,23 @@ static int jpeg_v4_0_5_sw_init(void *handle)
 	if (r)
 		return r;
 
-	ring = adev->jpeg.inst->ring_dec;
-	ring->use_doorbell = true;
-	ring->doorbell_index = amdgpu_sriov_vf(adev) ?
-				(((adev->doorbell_index.vcn.vcn_ring0_1) << 1) + 4) :
-				((adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1);
-	ring->vm_hub = AMDGPU_MMHUB0(0);
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
 
-	sprintf(ring->name, "jpeg_dec");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, 0,
-			     AMDGPU_RING_PRIO_DEFAULT, NULL);
-	if (r)
-		return r;
+		ring = adev->jpeg.inst[i].ring_dec;
+		ring->use_doorbell = true;
+		ring->vm_hub = AMDGPU_MMHUB0(0);
+		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + 8 * i;
+		sprintf(ring->name, "jpeg_dec_%d", i);
+		r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst[i].irq,
+				     0, AMDGPU_RING_PRIO_DEFAULT, NULL);
+		if (r)
+			return r;
 
-	adev->jpeg.internal.jpeg_pitch[0] = regUVD_JPEG_PITCH_INTERNAL_OFFSET;
-	adev->jpeg.inst->external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, 0, regUVD_JPEG_PITCH);
+		adev->jpeg.internal.jpeg_pitch[0] = regUVD_JPEG_PITCH_INTERNAL_OFFSET;
+		adev->jpeg.inst[i].external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, i, regUVD_JPEG_PITCH);
+	}
 
 	return 0;
 }
@@ -162,8 +186,8 @@ static int jpeg_v4_0_5_sw_fini(void *handle)
 static int jpeg_v4_0_5_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec;
-	int r;
+	struct amdgpu_ring *ring;
+	int r, i;
 
 	// TODO: Enable ring test with DPG support
 	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG_DPG) {
@@ -171,9 +195,15 @@ static int jpeg_v4_0_5_hw_init(void *handle)
 		return 0;
 	}
 
-	r = amdgpu_ring_test_helper(ring);
-	if (r)
-		return r;
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = adev->jpeg.inst[i].ring_dec;
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
+			return r;
+	}
 
 	if (!r)
 		DRM_INFO("JPEG decode initialized successfully under SPG Mode\n");
@@ -191,14 +221,20 @@ static int jpeg_v4_0_5_hw_init(void *handle)
 static int jpeg_v4_0_5_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i;
 
 	cancel_delayed_work_sync(&adev->vcn.idle_work);
-	if (!amdgpu_sriov_vf(adev)) {
-		if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
-			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
-			jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
-	}
 
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		if (!amdgpu_sriov_vf(adev)) {
+			if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
+			    RREG32_SOC15(JPEG, i, regUVD_JRBC_STATUS))
+				jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
+		}
+	}
 	return 0;
 }
 
@@ -440,13 +476,17 @@ static void jpeg_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
  */
 static int jpeg_v4_0_5_start(struct amdgpu_device *adev)
 {
-	struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec;
+	struct amdgpu_ring *ring;
 	int r, i;
 
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_jpeg(adev, true);
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = adev->jpeg.inst[i].ring_dec;
 		/* doorbell programming is done for every playback */
 		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
 				(adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i, i);
@@ -509,11 +549,14 @@ static int jpeg_v4_0_5_stop(struct amdgpu_device *adev)
 	int r, i;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		if (adev->pg_flags & AMD_PG_SUPPORT_JPEG_DPG) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
 
+		if (adev->pg_flags & AMD_PG_SUPPORT_JPEG_DPG) {
 			jpeg_v4_0_5_stop_dpg_mode(adev, i);
 			continue;
 		}
+
 		/* reset JMI */
 		WREG32_P(SOC15_REG_OFFSET(JPEG, i, regUVD_JMI_CNTL),
 			UVD_JMI_CNTL__SOFT_RESET_MASK,
@@ -526,7 +569,6 @@ static int jpeg_v4_0_5_stop(struct amdgpu_device *adev)
 		if (r)
 			return r;
 	}
-
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_jpeg(adev, false);
 
@@ -544,7 +586,7 @@ static uint64_t jpeg_v4_0_5_dec_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	return RREG32_SOC15(JPEG, 0, regUVD_JRBC_RB_RPTR);
+	return RREG32_SOC15(JPEG, ring->me, regUVD_JRBC_RB_RPTR);
 }
 
 /**
@@ -561,7 +603,7 @@ static uint64_t jpeg_v4_0_5_dec_ring_get_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell)
 		return *ring->wptr_cpu_addr;
 	else
-		return RREG32_SOC15(JPEG, 0, regUVD_JRBC_RB_WPTR);
+		return RREG32_SOC15(JPEG, ring->me, regUVD_JRBC_RB_WPTR);
 }
 
 /**
@@ -579,29 +621,41 @@ static void jpeg_v4_0_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
 		*ring->wptr_cpu_addr = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
 	} else {
-		WREG32_SOC15(JPEG, 0, regUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(JPEG, ring->me, regUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
 	}
 }
 
 static bool jpeg_v4_0_5_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int ret = 1;
+	int i, ret = 1;
 
-	ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) &
-		UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
-		UVD_JRBC_STATUS__RB_JOB_DONE_MASK));
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
 
+		ret &= (((RREG32_SOC15(JPEG, i, regUVD_JRBC_STATUS) &
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK));
+	}
 	return ret;
 }
 
 static int jpeg_v4_0_5_wait_for_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
 
-	return SOC15_WAIT_ON_RREG(JPEG, 0, regUVD_JRBC_STATUS,
-		UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
-		UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
+		return SOC15_WAIT_ON_RREG(JPEG, i, regUVD_JRBC_STATUS,
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
+	}
+
+	return 0;
 }
 
 static int jpeg_v4_0_5_set_clockgating_state(void *handle,
@@ -657,11 +711,25 @@ static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
+	uint32_t ip_instance;
+
 	DRM_DEBUG("IH: JPEG TRAP\n");
 
+	switch (entry->client_id) {
+	case SOC15_IH_CLIENTID_VCN:
+		ip_instance = 0;
+		break;
+	case SOC15_IH_CLIENTID_VCN1:
+		ip_instance = 1;
+		break;
+	default:
+		DRM_ERROR("Unhandled client id: %d\n", entry->client_id);
+		return 0;
+	}
+
 	switch (entry->src_id) {
 	case VCN_4_0__SRCID__JPEG_DECODE:
-		amdgpu_fence_process(adev->jpeg.inst->ring_dec);
+		amdgpu_fence_process(adev->jpeg.inst[ip_instance].ring_dec);
 		break;
 	case VCN_4_0__SRCID_DJPEG0_POISON:
 	case VCN_4_0__SRCID_EJPEG0_POISON:
@@ -734,6 +802,7 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 			continue;
 
 		adev->jpeg.inst[i].ring_dec->funcs = &jpeg_v4_0_5_dec_ring_vm_funcs;
+		adev->jpeg.inst[i].ring_dec->me = i;
 		DRM_DEV_INFO(adev->dev, "JPEG%d decode is enabled in VM mode\n", i);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 26d71a22395d..072c478665ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -49,6 +49,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes_2.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mes_2.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mes1.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_mes_2.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_5_1_mes1.bin");
 
 
 static int mes_v11_0_hw_fini(void *handle);
@@ -56,6 +58,7 @@ static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev);
 static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev);
 
 #define MES_EOP_SIZE   2048
+#define GFX_MES_DRAM_SIZE	0x80000
 
 static void mes_v11_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
@@ -475,7 +478,13 @@ static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev,
 		   le32_to_cpu(mes_hdr->mes_ucode_data_offset_bytes));
 	fw_size = le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes);
 
-	r = amdgpu_bo_create_reserved(adev, fw_size,
+	if (fw_size > GFX_MES_DRAM_SIZE) {
+		dev_err(adev->dev, "PIPE%d ucode data fw size (%d) is greater than dram size (%d)\n",
+			pipe, fw_size, GFX_MES_DRAM_SIZE);
+		return -EINVAL;
+	}
+
+	r = amdgpu_bo_create_reserved(adev, GFX_MES_DRAM_SIZE,
 				      64 * 1024,
 				      AMDGPU_GEM_DOMAIN_VRAM |
 				      AMDGPU_GEM_DOMAIN_GTT,
@@ -611,8 +620,8 @@ static int mes_v11_0_load_microcode(struct amdgpu_device *adev,
 	WREG32_SOC15(GC, 0, regCP_MES_MDBASE_HI,
 		     upper_32_bits(adev->mes.data_fw_gpu_addr[pipe]));
 
-	/* Set 0x3FFFF (256K-1) to CP_MES_MDBOUND_LO */
-	WREG32_SOC15(GC, 0, regCP_MES_MDBOUND_LO, 0x3FFFF);
+	/* Set 0x7FFFF (512K-1) to CP_MES_MDBOUND_LO */
+	WREG32_SOC15(GC, 0, regCP_MES_MDBOUND_LO, 0x7FFFF);
 
 	if (prime_icache) {
 		/* invalidate ICACHE */
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index b4723d68eab0..40d1e209eab7 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -35,15 +35,6 @@
 /* Core 0 Port 0 counter */
 #define smnPCIEP_NAK_COUNTER 0x1A340218
 
-#define smnPCIE_PERF_CNTL_TXCLK3		0x1A38021c
-#define smnPCIE_PERF_CNTL_TXCLK7		0x1A380888
-#define smnPCIE_PERF_COUNT_CNTL			0x1A380200
-#define smnPCIE_PERF_COUNT0_TXCLK3		0x1A380220
-#define smnPCIE_PERF_COUNT0_TXCLK7		0x1A38088C
-#define smnPCIE_PERF_COUNT0_UPVAL_TXCLK3	0x1A3808F8
-#define smnPCIE_PERF_COUNT0_UPVAL_TXCLK7	0x1A380918
-
-
 static void nbio_v7_9_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL,
@@ -484,59 +475,6 @@ static u64 nbio_v7_9_get_pcie_replay_count(struct amdgpu_device *adev)
 	return (nak_r + nak_g);
 }
 
-static void nbio_v7_9_get_pcie_usage(struct amdgpu_device *adev, uint64_t *count0,
-				     uint64_t *count1)
-{
-	uint32_t perfctrrx = 0;
-	uint32_t perfctrtx = 0;
-
-	/* This reports 0 on APUs, so return to avoid writing/reading registers
-	 * that may or may not be different from their GPU counterparts
-	 */
-	if (adev->flags & AMD_IS_APU)
-		return;
-
-	/* Use TXCLK3 counter group for rx event */
-	/* Use TXCLK7 counter group for tx event */
-	/* Set the 2 events that we wish to watch, defined above */
-	/* 40 is event# for received msgs */
-	/* 2 is event# of posted requests sent */
-	perfctrrx = REG_SET_FIELD(perfctrrx, PCIE_PERF_CNTL_TXCLK3, EVENT0_SEL, 40);
-	perfctrtx = REG_SET_FIELD(perfctrtx, PCIE_PERF_CNTL_TXCLK7, EVENT0_SEL, 2);
-
-	/* Write to enable desired perf counters */
-	WREG32_PCIE(smnPCIE_PERF_CNTL_TXCLK3, perfctrrx);
-	WREG32_PCIE(smnPCIE_PERF_CNTL_TXCLK7, perfctrtx);
-
-	/* Zero out and enable SHADOW_WR
-	 * Write 0x6:
-	 * Bit 1 = Global Shadow wr(1)
-	 * Bit 2 = Global counter reset enable(1)
-	 */
-	WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000006);
-
-	/* Enable Gloabl Counter
-	 * Write 0x1:
-	 * Bit 0 = Global Counter Enable(1)
-	 */
-	WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000001);
-
-	msleep(1000);
-
-	/* Disable Global Counter, Reset and enable SHADOW_WR
-	 * Write 0x6:
-	 * Bit 1 = Global Shadow wr(1)
-	 * Bit 2 = Global counter reset enable(1)
-	 */
-	WREG32_PCIE(smnPCIE_PERF_COUNT_CNTL, 0x00000006);
-
-	/* Get the upper and lower count  */
-	*count0 = RREG32_PCIE(smnPCIE_PERF_COUNT0_TXCLK3) |
-		  ((uint64_t)RREG32_PCIE(smnPCIE_PERF_COUNT0_UPVAL_TXCLK3) << 32);
-	*count1 = RREG32_PCIE(smnPCIE_PERF_COUNT0_TXCLK7) |
-		  ((uint64_t)RREG32_PCIE(smnPCIE_PERF_COUNT0_UPVAL_TXCLK7) << 32);
-}
-
 const struct amdgpu_nbio_funcs nbio_v7_9_funcs = {
 	.get_hdp_flush_req_offset = nbio_v7_9_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v7_9_get_hdp_flush_done_offset,
@@ -561,7 +499,6 @@ const struct amdgpu_nbio_funcs nbio_v7_9_funcs = {
 	.get_memory_partition_mode = nbio_v7_9_get_memory_partition_mode,
 	.init_registers = nbio_v7_9_init_registers,
 	.get_pcie_replay_count = nbio_v7_9_get_pcie_replay_count,
-	.get_pcie_usage = nbio_v7_9_get_pcie_usage,
 };
 
 static void nbio_v7_9_query_ras_error_count(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index a757526153e5..23e4ef4fff7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -2331,28 +2331,18 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev)
 								   gpu_cfg &
 								   PCI_EXP_LNKCTL_HAWD);
 
-				pcie_capability_read_word(root, PCI_EXP_LNKCTL2,
-							  &tmp16);
-				tmp16 &= ~(PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN);
-				tmp16 |= (bridge_cfg2 &
-					  (PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN));
-				pcie_capability_write_word(root,
-							   PCI_EXP_LNKCTL2,
-							   tmp16);
-
-				pcie_capability_read_word(adev->pdev,
-							  PCI_EXP_LNKCTL2,
-							  &tmp16);
-				tmp16 &= ~(PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN);
-				tmp16 |= (gpu_cfg2 &
-					  (PCI_EXP_LNKCTL2_ENTER_COMP |
-					   PCI_EXP_LNKCTL2_TX_MARGIN));
-				pcie_capability_write_word(adev->pdev,
-							   PCI_EXP_LNKCTL2,
-							   tmp16);
+				pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL2,
+								   PCI_EXP_LNKCTL2_ENTER_COMP |
+								   PCI_EXP_LNKCTL2_TX_MARGIN,
+								   bridge_cfg2 &
+								   (PCI_EXP_LNKCTL2_ENTER_COMP |
+								    PCI_EXP_LNKCTL2_TX_MARGIN));
+				pcie_capability_clear_and_set_word(adev->pdev, PCI_EXP_LNKCTL2,
+								   PCI_EXP_LNKCTL2_ENTER_COMP |
+								   PCI_EXP_LNKCTL2_TX_MARGIN,
+								   gpu_cfg2 &
+								   (PCI_EXP_LNKCTL2_ENTER_COMP |
+								    PCI_EXP_LNKCTL2_TX_MARGIN));
 
 				tmp = RREG32_PCIE_PORT(PCIE_LC_CNTL4);
 				tmp &= ~LC_SET_QUIESCE;
@@ -2365,16 +2355,15 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev)
 	speed_cntl &= ~LC_FORCE_DIS_SW_SPEED_CHANGE;
 	WREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL, speed_cntl);
 
-	pcie_capability_read_word(adev->pdev, PCI_EXP_LNKCTL2, &tmp16);
-	tmp16 &= ~PCI_EXP_LNKCTL2_TLS;
-
+	tmp16 = 0;
 	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
 		tmp16 |= PCI_EXP_LNKCTL2_TLS_8_0GT; /* gen3 */
 	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
 		tmp16 |= PCI_EXP_LNKCTL2_TLS_5_0GT; /* gen2 */
 	else
 		tmp16 |= PCI_EXP_LNKCTL2_TLS_2_5GT; /* gen1 */
-	pcie_capability_write_word(adev->pdev, PCI_EXP_LNKCTL2, tmp16);
+	pcie_capability_clear_and_set_word(adev->pdev, PCI_EXP_LNKCTL2,
+					   PCI_EXP_LNKCTL2_TLS, tmp16);
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	speed_cntl |= LC_INITIATE_LINK_SPEED_CHANGE;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index c64c01e2944a..dec81ccf6240 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE1;
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	/* original raven doesn't have full asic reset */
-	if ((adev->apu_flags & AMD_APU_IS_RAVEN) ||
-	    (adev->apu_flags & AMD_APU_IS_RAVEN2))
+	/* On the latest Raven, the GPU reset can be performed
+	 * successfully. So now, temporarily enable it for the
+	 * S3 suspend abort case.
+	 */
+	if (((adev->apu_flags & AMD_APU_IS_RAVEN) ||
+	    (adev->apu_flags & AMD_APU_IS_RAVEN2)) &&
+		!soc15_need_reset_on_resume(adev))
 		return 0;
 
 	switch (soc15_asic_reset_method(adev)) {
@@ -895,7 +918,6 @@ static const struct amdgpu_asic_funcs aqua_vanjaram_asic_funcs =
 	.get_config_memsize = &soc15_get_config_memsize,
 	.need_full_reset = &soc15_need_full_reset,
 	.init_doorbell_index = &aqua_vanjaram_doorbell_index_init,
-	.get_pcie_usage = &amdgpu_nbio_get_pcie_usage,
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &amdgpu_nbio_get_pcie_replay_count,
 	.supports_baco = &soc15_supports_baco,
@@ -1278,7 +1300,8 @@ static int soc15_common_hw_fini(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_put_irq(adev);
 
-	if (adev->nbio.ras_if &&
+	if ((!amdgpu_sriov_vf(adev)) &&
+	    adev->nbio.ras_if &&
 	    amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) {
 		if (adev->nbio.ras &&
 		    adev->nbio.ras->init_ras_controller_interrupt)
@@ -1298,24 +1321,6 @@ static int soc15_common_suspend(void *handle)
 	return soc15_common_hw_fini(adev);
 }
 
-static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
-{
-	u32 sol_reg;
-
-	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
-
-	/* Will reset for the following suspend abort cases.
-	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
-	 * 2) S3 suspend abort and TOS already launched.
-	 */
-	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
-			!adev->suspend_complete &&
-			sol_reg)
-		return true;
-
-	return false;
-}
-
 static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 5f81c264e310..b92fd6760fa9 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -185,6 +185,12 @@ static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode,
 			}
 		}
 		return 0;
+	case IP_VERSION(4, 0, 6):
+		if (encode)
+			*codecs = &vcn_4_0_0_video_codecs_encode_vcn0;
+		else
+			*codecs = &vcn_4_0_0_video_codecs_decode_vcn0;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -717,6 +723,35 @@ static int soc21_common_early_init(void *handle)
 			AMD_PG_SUPPORT_GFX_PG;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
+	case IP_VERSION(11, 5, 1):
+		adev->cg_flags =
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_FGCG |
+			AMD_CG_SUPPORT_REPEATER_FGCG |
+			AMD_CG_SUPPORT_GFX_PERF_CLK	|
+			AMD_CG_SUPPORT_GFX_3D_CGCG |
+			AMD_CG_SUPPORT_GFX_3D_CGLS	|
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_DS |
+			AMD_CG_SUPPORT_HDP_SD |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG;
+		adev->pg_flags =
+			AMD_PG_SUPPORT_GFX_PG |
+			AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_JPEG;
+		adev->external_rev_id = adev->rev_id + 0xc1;
+		break;
 	default:
 		/* FIXME: not supported yet */
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index 14ef7a24be7b..77af4e25ff46 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -348,7 +348,8 @@ static int umc_v12_0_query_error_address(struct amdgpu_device *adev,
 	}
 
 	/* calculate error address if ue error is detected */
-	if (umc_v12_0_is_uncorrectable_error(adev, mc_umc_status)) {
+	if (umc_v12_0_is_uncorrectable_error(adev, mc_umc_status) ||
+	    umc_v12_0_is_deferred_error(adev, mc_umc_status)) {
 		mc_umc_addrt0 =
 			SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 49e4c3c09aca..0468955338b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -1684,6 +1684,9 @@ static int vcn_v4_0_5_process_interrupt(struct amdgpu_device *adev, struct amdgp
 	case SOC15_IH_CLIENTID_VCN:
 		ip_instance = 0;
 		break;
+	case SOC15_IH_CLIENTID_VCN1:
+		ip_instance = 1;
+		break;
 	default:
 		DRM_ERROR("Unhandled client id: %d\n", entry->client_id);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index db66e6cccaf2..b9e785846637 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -291,27 +291,29 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
 
 	adev->nbio.funcs->ih_control(adev);
 
-	if ((amdgpu_ip_version(adev, OSSSYS_HWIP, 0) == IP_VERSION(4, 2, 1)) &&
-	    adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
-		ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN);
-		if (adev->irq.ih.use_bus_addr) {
-			ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
-						   MC_SPACE_GPA_ENABLE, 1);
+	if (!amdgpu_sriov_vf(adev)) {
+		if ((amdgpu_ip_version(adev, OSSSYS_HWIP, 0) == IP_VERSION(4, 2, 1)) &&
+		    adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
+			ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN);
+			if (adev->irq.ih.use_bus_addr) {
+				ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
+							   MC_SPACE_GPA_ENABLE, 1);
+			}
+			WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN, ih_chicken);
 		}
-		WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN, ih_chicken);
-	}
 
-	/* psp firmware won't program IH_CHICKEN for aldebaran
-	 * driver needs to program it properly according to
-	 * MC_SPACE type in IH_RB_CNTL */
-	if ((amdgpu_ip_version(adev, OSSSYS_HWIP, 0) == IP_VERSION(4, 4, 0)) ||
-	    (amdgpu_ip_version(adev, OSSSYS_HWIP, 0) == IP_VERSION(4, 4, 2))) {
-		ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN_ALDEBARAN);
-		if (adev->irq.ih.use_bus_addr) {
-			ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
-						   MC_SPACE_GPA_ENABLE, 1);
+		/* psp firmware won't program IH_CHICKEN for aldebaran
+		 * driver needs to program it properly according to
+		 * MC_SPACE type in IH_RB_CNTL */
+		if ((amdgpu_ip_version(adev, OSSSYS_HWIP, 0) == IP_VERSION(4, 4, 0)) ||
+		    (amdgpu_ip_version(adev, OSSSYS_HWIP, 0) == IP_VERSION(4, 4, 2))) {
+			ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN_ALDEBARAN);
+			if (adev->irq.ih.use_bus_addr) {
+				ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
+							   MC_SPACE_GPA_ENABLE, 1);
+			}
+			WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN_ALDEBARAN, ih_chicken);
 		}
-		WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN_ALDEBARAN, ih_chicken);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(ih); i++) {