Backmerge remote-tracking branch 'drm/drm-next' into drm-misc-next

Required bump from v5.13-rc3 to v5.14-rc3, and to pick up sysfb compilation fixes.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

57 files changed, 1287 insertions, 881 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c0316eaba547..8ac6eb9f1fdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -619,6 +619,13 @@ struct amdgpu_video_codec_info {
 	u32 max_level;
 };
 
+#define codec_info_build(type, width, height, level) \
+			 .codec_type = type,\
+			 .max_width = width,\
+			 .max_height = height,\
+			 .max_pixels_per_frame = height * width,\
+			 .max_level = level,
+
 struct amdgpu_video_codecs {
 	const u32 codec_count;
 	const struct amdgpu_video_codec_info *codec_array;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index db16b3e83694..cf62f43a03da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -269,7 +269,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
 		uint64_t *size);
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index fdee98fae2ba..4fb15750b9bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -47,12 +47,6 @@ static struct {
 	spinlock_t mem_limit_lock;
 } kfd_mem_limit;
 
-/* Struct used for amdgpu_amdkfd_bo_validate */
-struct amdgpu_vm_parser {
-	uint32_t        domain;
-	bool            wait;
-};
-
 static const char * const domain_bit_to_string[] = {
 		"CPU",
 		"GTT",
@@ -348,11 +342,9 @@ validate_fail:
 	return ret;
 }
 
-static int amdgpu_amdkfd_validate(void *param, struct amdgpu_bo *bo)
+static int amdgpu_amdkfd_validate_vm_bo(void *_unused, struct amdgpu_bo *bo)
 {
-	struct amdgpu_vm_parser *p = param;
-
-	return amdgpu_amdkfd_bo_validate(bo, p->domain, p->wait);
+	return amdgpu_amdkfd_bo_validate(bo, bo->allowed_domains, false);
 }
 
 /* vm_validate_pt_pd_bos - Validate page table and directory BOs
@@ -364,28 +356,23 @@ static int amdgpu_amdkfd_validate(void *param, struct amdgpu_bo *bo)
  */
 static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm)
 {
-	struct amdgpu_bo *pd = vm->root.base.bo;
+	struct amdgpu_bo *pd = vm->root.bo;
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
-	struct amdgpu_vm_parser param;
 	int ret;
 
-	param.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	param.wait = false;
-
-	ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate,
-					&param);
+	ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate_vm_bo, NULL);
 	if (ret) {
 		pr_err("failed to validate PT BOs\n");
 		return ret;
 	}
 
-	ret = amdgpu_amdkfd_validate(&param, pd);
+	ret = amdgpu_amdkfd_validate_vm_bo(NULL, pd);
 	if (ret) {
 		pr_err("failed to validate PD\n");
 		return ret;
 	}
 
-	vm->pd_phys_addr = amdgpu_gmc_pd_addr(vm->root.base.bo);
+	vm->pd_phys_addr = amdgpu_gmc_pd_addr(vm->root.bo);
 
 	if (vm->use_cpu_for_update) {
 		ret = amdgpu_bo_kmap(pd, NULL);
@@ -400,7 +387,7 @@ static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm)
 
 static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 {
-	struct amdgpu_bo *pd = vm->root.base.bo;
+	struct amdgpu_bo *pd = vm->root.bo;
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
 	int ret;
 
@@ -652,7 +639,7 @@ kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem,
 		}
 	}
 
-	gobj = amdgpu_gem_prime_import(&adev->ddev, mem->dmabuf);
+	gobj = amdgpu_gem_prime_import(adev_to_drm(adev), mem->dmabuf);
 	if (IS_ERR(gobj))
 		return PTR_ERR(gobj);
 
@@ -1070,8 +1057,7 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 static int update_gpuvm_pte(struct kgd_mem *mem,
 			    struct kfd_mem_attachment *entry,
-			    struct amdgpu_sync *sync,
-			    bool *table_freed)
+			    struct amdgpu_sync *sync)
 {
 	struct amdgpu_bo_va *bo_va = entry->bo_va;
 	struct amdgpu_device *adev = entry->adev;
@@ -1082,7 +1068,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 		return ret;
 
 	/* Update the page tables  */
-	ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed);
+	ret = amdgpu_vm_bo_update(adev, bo_va, false);
 	if (ret) {
 		pr_err("amdgpu_vm_bo_update failed\n");
 		return ret;
@@ -1094,8 +1080,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 static int map_bo_to_gpuvm(struct kgd_mem *mem,
 			   struct kfd_mem_attachment *entry,
 			   struct amdgpu_sync *sync,
-			   bool no_update_pte,
-			   bool *table_freed)
+			   bool no_update_pte)
 {
 	int ret;
 
@@ -1112,7 +1097,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem,
 	if (no_update_pte)
 		return 0;
 
-	ret = update_gpuvm_pte(mem, entry, sync, table_freed);
+	ret = update_gpuvm_pte(mem, entry, sync);
 	if (ret) {
 		pr_err("update_gpuvm_pte() failed\n");
 		goto update_gpuvm_pte_failed;
@@ -1166,7 +1151,7 @@ static int process_sync_pds_resv(struct amdkfd_process_info *process_info,
 
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			    vm_list_node) {
-		struct amdgpu_bo *pd = peer_vm->root.base.bo;
+		struct amdgpu_bo *pd = peer_vm->root.bo;
 
 		ret = amdgpu_sync_resv(NULL, sync, pd->tbo.base.resv,
 				       AMDGPU_SYNC_NE_OWNER,
@@ -1233,7 +1218,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 	vm->process_info = *process_info;
 
 	/* Validate page directory and attach eviction fence */
-	ret = amdgpu_bo_reserve(vm->root.base.bo, true);
+	ret = amdgpu_bo_reserve(vm->root.bo, true);
 	if (ret)
 		goto reserve_pd_fail;
 	ret = vm_validate_pt_pd_bos(vm);
@@ -1241,16 +1226,16 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 		pr_err("validate_pt_pd_bos() failed\n");
 		goto validate_pd_fail;
 	}
-	ret = amdgpu_bo_sync_wait(vm->root.base.bo,
+	ret = amdgpu_bo_sync_wait(vm->root.bo,
 				  AMDGPU_FENCE_OWNER_KFD, false);
 	if (ret)
 		goto wait_pd_fail;
-	ret = dma_resv_reserve_shared(vm->root.base.bo->tbo.base.resv, 1);
+	ret = dma_resv_reserve_shared(vm->root.bo->tbo.base.resv, 1);
 	if (ret)
 		goto reserve_shared_fail;
-	amdgpu_bo_fence(vm->root.base.bo,
+	amdgpu_bo_fence(vm->root.bo,
 			&vm->process_info->eviction_fence->base, true);
-	amdgpu_bo_unreserve(vm->root.base.bo);
+	amdgpu_bo_unreserve(vm->root.bo);
 
 	/* Update process info */
 	mutex_lock(&vm->process_info->lock);
@@ -1264,7 +1249,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 reserve_shared_fail:
 wait_pd_fail:
 validate_pd_fail:
-	amdgpu_bo_unreserve(vm->root.base.bo);
+	amdgpu_bo_unreserve(vm->root.bo);
 reserve_pd_fail:
 	vm->process_info = NULL;
 	if (info) {
@@ -1319,7 +1304,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				    struct amdgpu_vm *vm)
 {
 	struct amdkfd_process_info *process_info = vm->process_info;
-	struct amdgpu_bo *pd = vm->root.base.bo;
+	struct amdgpu_bo *pd = vm->root.bo;
 
 	if (!process_info)
 		return;
@@ -1375,7 +1360,7 @@ void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *drm_priv)
 uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv)
 {
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
-	struct amdgpu_bo *pd = avm->root.base.bo;
+	struct amdgpu_bo *pd = avm->root.bo;
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
 
 	if (adev->asic_type < CHIP_VEGA10)
@@ -1406,8 +1391,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
 		alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
 		alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ?
-			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED :
-			AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
+			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0;
 	} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) {
 		domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
 		alloc_flags = 0;
@@ -1610,8 +1594,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 }
 
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem,
-		void *drm_priv, bool *table_freed)
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
@@ -1699,7 +1682,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 			 entry->va, entry->va + bo_size, entry);
 
 		ret = map_bo_to_gpuvm(mem, entry, ctx.sync,
-				      is_invalid_userptr, table_freed);
+				      is_invalid_userptr);
 		if (ret) {
 			pr_err("Failed to map bo to gpuvm\n");
 			goto out_unreserve;
@@ -2149,7 +2132,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync, NULL);
+			ret = update_gpuvm_pte(mem, attachment, &sync);
 			if (ret) {
 				pr_err("%s: update PTE failed\n", __func__);
 				/* make sure this gets validated again */
@@ -2355,7 +2338,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL);
+			ret = update_gpuvm_pte(mem, attachment, &sync_obj);
 			if (ret) {
 				pr_debug("Memory eviction: update PTE failed. Try again\n");
 				goto validate_map_fail;
@@ -2402,7 +2385,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 	/* Attach eviction fence to PD / PT BOs */
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			    vm_list_node) {
-		struct amdgpu_bo *bo = peer_vm->root.base.bo;
+		struct amdgpu_bo *bo = peer_vm->root.bo;
 
 		amdgpu_bo_fence(bo, &process_info->eviction_fence->base, true);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 25655414e9c0..a152363b0254 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -799,7 +799,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL);
+	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
 	if (r)
 		return r;
 
@@ -810,7 +810,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
 		bo_va = fpriv->csa_va;
 		BUG_ON(!bo_va);
-		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
 
@@ -829,7 +829,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (bo_va == NULL)
 			continue;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
 
@@ -850,7 +850,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.base.bo);
+	p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo);
 
 	if (amdgpu_vm_debug) {
 		/* Invalidate all BOs to test for userspace bugs */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index a9bbb0034e1e..536005bff24a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1304,11 +1304,11 @@ static int amdgpu_debugfs_vm_info_show(struct seq_file *m, void *unused)
 
 		seq_printf(m, "pid:%d\tProcess:%s ----------\n",
 				vm->task_info.pid, vm->task_info.process_name);
-		r = amdgpu_bo_reserve(vm->root.base.bo, true);
+		r = amdgpu_bo_reserve(vm->root.bo, true);
 		if (r)
 			break;
 		amdgpu_debugfs_vm_bo_info(vm, m);
-		amdgpu_bo_unreserve(vm->root.base.bo);
+		amdgpu_bo_unreserve(vm->root.bo);
 	}
 
 	mutex_unlock(&dev->filelist_mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 45c84e4413cb..8398daa0c06a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1370,6 +1370,38 @@ def_value:
 	adev->pm.smu_prv_buffer_size = 0;
 }
 
+static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev)
+{
+	if (!(adev->flags & AMD_IS_APU) ||
+	    adev->asic_type < CHIP_RAVEN)
+		return 0;
+
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
+		if (adev->pdev->device == 0x15dd)
+			adev->apu_flags |= AMD_APU_IS_RAVEN;
+		if (adev->pdev->device == 0x15d8)
+			adev->apu_flags |= AMD_APU_IS_PICASSO;
+		break;
+	case CHIP_RENOIR:
+		if ((adev->pdev->device == 0x1636) ||
+		    (adev->pdev->device == 0x164c))
+			adev->apu_flags |= AMD_APU_IS_RENOIR;
+		else
+			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
+		break;
+	case CHIP_VANGOGH:
+		adev->apu_flags |= AMD_APU_IS_VANGOGH;
+		break;
+	case CHIP_YELLOW_CARP:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_device_check_arguments - validate module params
  *
@@ -3387,6 +3419,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->psp.mutex);
 	mutex_init(&adev->notifier_lock);
 
+	r = amdgpu_device_init_apu_flags(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_check_arguments(adev);
 	if (r)
 		return r;
@@ -4125,6 +4161,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 {
 	struct dma_fence *fence = NULL, *next = NULL;
 	struct amdgpu_bo *shadow;
+	struct amdgpu_bo_vm *vmbo;
 	long r = 1, tmo;
 
 	if (amdgpu_sriov_runtime(adev))
@@ -4134,8 +4171,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 
 	dev_info(adev->dev, "recover vram bo from shadow start\n");
 	mutex_lock(&adev->shadow_list_lock);
-	list_for_each_entry(shadow, &adev->shadow_list, shadow_list) {
-
+	list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) {
+		shadow = &vmbo->bo;
 		/* No need to recover an evicted BO */
 		if (shadow->tbo.resource->mem_type != TTM_PL_TT ||
 		    shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET ||
@@ -4304,6 +4341,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 		case CHIP_SIENNA_CICHLID:
 		case CHIP_NAVY_FLOUNDER:
 		case CHIP_DIMGREY_CAVEFISH:
+		case CHIP_BEIGE_GOBY:
 		case CHIP_VANGOGH:
 		case CHIP_ALDEBARAN:
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index e1b6f5891759..43e7b61d1c5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -325,7 +325,7 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
+int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int number_instance,
 				    int *major, int *minor, int *revision)
 {
 	struct binary_header *bhdr;
@@ -357,7 +357,7 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
 		for (j = 0; j < num_ips; j++) {
 			ip = (struct ip *)(adev->mman.discovery_bin + ip_offset);
 
-			if (le16_to_cpu(ip->hw_id) == hw_id) {
+			if ((le16_to_cpu(ip->hw_id) == hw_id) && (ip->number_instance == number_instance)) {
 				if (major)
 					*major = ip->major;
 				if (minor)
@@ -373,6 +373,14 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
 	return -EINVAL;
 }
 
+
+int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance,
+				     int *major, int *minor, int *revision)
+{
+	return amdgpu_discovery_get_ip_version(adev, VCN_HWID,
+					       vcn_instance, major, minor, revision);
+}
+
 void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 {
 	struct binary_header *bhdr;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
index 1b1ae21b1037..48e6b88cfdfe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
@@ -30,8 +30,11 @@
 void amdgpu_discovery_fini(struct amdgpu_device *adev);
 int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev);
 void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev);
-int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
+int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int number_instance,
                                     int *major, int *minor, int *revision);
+
+int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance,
+				     int *major, int *minor, int *revision);
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev);
 
 #endif /* __AMDGPU_DISCOVERY__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 2b6a66c849d4..8e5a7ac8c36f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -1046,11 +1046,12 @@ int amdgpu_display_gem_fb_init(struct drm_device *dev,
 
 	rfb->base.obj[0] = obj;
 	drm_helper_mode_fill_fb_struct(dev, &rfb->base, mode_cmd);
-	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+
+	ret = amdgpu_display_framebuffer_init(dev, rfb, mode_cmd, obj);
 	if (ret)
 		goto err;
 
-	ret = amdgpu_display_framebuffer_init(dev, rfb, mode_cmd, obj);
+	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
 	if (ret)
 		goto err;
 
@@ -1070,9 +1071,6 @@ int amdgpu_display_gem_fb_verify_and_init(
 
 	rfb->base.obj[0] = obj;
 	drm_helper_mode_fill_fb_struct(dev, &rfb->base, mode_cmd);
-	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
-	if (ret)
-		goto err;
 	/* Verify that the modifier is supported. */
 	if (!drm_any_plane_has_format(dev, mode_cmd->pixel_format,
 				      mode_cmd->modifier[0])) {
@@ -1088,6 +1086,10 @@ int amdgpu_display_gem_fb_verify_and_init(
 	if (ret)
 		goto err;
 
+	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+	if (ret)
+		goto err;
+
 	return 0;
 err:
 	drm_dbg_kms(dev, "Failed to verify and init gem fb: %d\n", ret);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 23219fc3b28c..ae6ab93c868b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -105,9 +105,21 @@ static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach)
 {
 	struct drm_gem_object *obj = attach->dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	int r;
 
 	/* pin buffer into GTT */
-	return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
+	if (r)
+		return r;
+
+	if (bo->tbo.moving) {
+		r = dma_fence_wait(bo->tbo.moving, true);
+		if (r) {
+			amdgpu_bo_unpin(bo);
+			return r;
+		}
+	}
+	return 0;
 }
 
 /**
@@ -383,7 +395,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach)
 
 	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
 		struct amdgpu_vm *vm = bo_base->vm;
-		struct dma_resv *resv = vm->root.base.bo->tbo.base.resv;
+		struct dma_resv *resv = vm->root.bo->tbo.base.resv;
 
 		if (ticket) {
 			/* When we get an error here it means that somebody
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index d2673119e0d1..2bd13fc2541a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -160,6 +160,7 @@ int amdgpu_smu_pptable_id = -1;
  *     highest. That helps saving some idle power.
  * DISABLE_FRACTIONAL_PWM (bit 2) disabled by default
  * PSR (bit 3) disabled by default
+ * EDP NO POWER SEQUENCING (bit 4) disabled by default
  */
 uint amdgpu_dc_feature_mask = 2;
 uint amdgpu_dc_debug_mask;
@@ -837,8 +838,23 @@ module_param_named(tmz, amdgpu_tmz, int, 0444);
 
 /**
  * DOC: freesync_video (uint)
- * Enabled 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.
+ * 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(
@@ -1152,6 +1168,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
 
 	/* Renoir */
+	{0x1002, 0x15E7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
 	{0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
 	{0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
@@ -1173,6 +1190,10 @@ static const struct pci_device_id pciidlist[] = {
 	/* Van Gogh */
 	{0x1002, 0x163F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VANGOGH|AMD_IS_APU},
 
+	/* Yellow Carp */
+	{0x1002, 0x164D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+	{0x1002, 0x1681, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+
 	/* Navy_Flounder */
 	{0x1002, 0x73C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
 	{0x1002, 0x73C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
@@ -1183,6 +1204,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x73E0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73E1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73E2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73E3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73FF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 
 	/* Aldebaran */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c
index dbebbe16e3b3..d94c5419ec25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c
@@ -69,13 +69,13 @@ void amdgpu_show_fdinfo(struct seq_file *m, struct file *f)
 	dev = PCI_SLOT(adev->pdev->devfn);
 	fn = PCI_FUNC(adev->pdev->devfn);
 
-	ret = amdgpu_bo_reserve(fpriv->vm.root.base.bo, false);
+	ret = amdgpu_bo_reserve(fpriv->vm.root.bo, false);
 	if (ret) {
 		DRM_ERROR("Fail to reserve bo\n");
 		return;
 	}
 	amdgpu_vm_get_memory(&fpriv->vm, &vram_mem, &gtt_mem, &cpu_mem);
-	amdgpu_bo_unreserve(fpriv->vm.root.base.bo);
+	amdgpu_bo_unreserve(fpriv->vm.root.bo);
 	seq_printf(m, "pdev:\t%04x:%02x:%02x.%d\npasid:\t%u\n", domain, bus,
 			dev, fn, fpriv->vm.pasid);
 	seq_printf(m, "vram mem:\t%llu kB\n", vram_mem/1024UL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 1313784605b0..b36405170ff3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -300,7 +300,6 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
  * @adev: amdgpu_device pointer
  * @offset: offset into the GPU's gart aperture
  * @pages: number of pages to bind
- * @pagelist: pages to bind
  * @dma_addr: DMA addresses of pages
  * @flags: page table entry flags
  *
@@ -309,7 +308,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
  * Returns 0 for success, -EINVAL for failure.
  */
 int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
-		     int pages, struct page **pagelist, dma_addr_t *dma_addr,
+		     int pages, dma_addr_t *dma_addr,
 		     uint64_t flags)
 {
 	if (!adev->gart.ready) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index f53f6a7b9b60..78895413cf9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -64,7 +64,6 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 		    int pages, dma_addr_t *dma_addr, uint64_t flags,
 		    void *dst);
 int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
-		     int pages, struct page **pagelist,
-		     dma_addr_t *dma_addr, uint64_t flags);
+		     int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_invalidate_tlb(struct amdgpu_device *adev);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 0780e8d18992..611fd10c3410 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -170,7 +170,7 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj,
 		return -EPERM;
 
 	if (abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID &&
-	    abo->tbo.base.resv != vm->root.base.bo->tbo.base.resv)
+	    abo->tbo.base.resv != vm->root.bo->tbo.base.resv)
 		return -EPERM;
 
 	r = amdgpu_bo_reserve(abo, false);
@@ -255,6 +255,15 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str
 	if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
 		return -EPERM;
 
+	/* Workaround for Thunk bug creating PROT_NONE,MAP_PRIVATE mappings
+	 * for debugger access to invisible VRAM. Should have used MAP_SHARED
+	 * instead. Clearing VM_MAYWRITE prevents the mapping from ever
+	 * becoming writable and makes is_cow_mapping(vm_flags) false.
+	 */
+	if (is_cow_mapping(vma->vm_flags) &&
+	    !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
+		vma->vm_flags &= ~VM_MAYWRITE;
+
 	return drm_gem_ttm_mmap(obj, vma);
 }
 
@@ -320,11 +329,11 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
-		r = amdgpu_bo_reserve(vm->root.base.bo, false);
+		r = amdgpu_bo_reserve(vm->root.bo, false);
 		if (r)
 			return r;
 
-		resv = vm->root.base.bo->tbo.base.resv;
+		resv = vm->root.bo->tbo.base.resv;
 	}
 
 	initial_domain = (u32)(0xffffffff & args->in.domains);
@@ -353,9 +362,9 @@ retry:
 		if (!r) {
 			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);
 
-			abo->parent = amdgpu_bo_ref(vm->root.base.bo);
+			abo->parent = amdgpu_bo_ref(vm->root.bo);
 		}
-		amdgpu_bo_unreserve(vm->root.base.bo);
+		amdgpu_bo_unreserve(vm->root.bo);
 	}
 	if (r)
 		return r;
@@ -612,7 +621,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 
 	if (operation == AMDGPU_VA_OP_MAP ||
 	    operation == AMDGPU_VA_OP_REPLACE) {
-		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			goto error;
 	}
@@ -842,7 +851,7 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 		}
 		for (base = robj->vm_bo; base; base = base->next)
 			if (amdgpu_xgmi_same_hive(amdgpu_ttm_adev(robj->tbo.bdev),
-				amdgpu_ttm_adev(base->vm->root.base.bo->tbo.bdev))) {
+				amdgpu_ttm_adev(base->vm->root.bo->tbo.bdev))) {
 				r = -EINVAL;
 				amdgpu_bo_unreserve(robj);
 				goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 0174f7817ce2..d0b8d415b63b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -562,6 +562,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 	case CHIP_VANGOGH:
+	case CHIP_YELLOW_CARP:
 		/* Don't enable it by default yet.
 		 */
 		if (amdgpu_tmz < 1) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 7dad44e73cf6..0d01cfaca77e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -278,6 +278,21 @@ static bool amdgpu_msi_ok(struct amdgpu_device *adev)
 	return true;
 }
 
+static void amdgpu_restore_msix(struct amdgpu_device *adev)
+{
+	u16 ctrl;
+
+	pci_read_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	if (!(ctrl & PCI_MSIX_FLAGS_ENABLE))
+		return;
+
+	/* VF FLR */
+	ctrl &= ~PCI_MSIX_FLAGS_ENABLE;
+	pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl);
+	ctrl |= PCI_MSIX_FLAGS_ENABLE;
+	pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl);
+}
+
 /**
  * amdgpu_irq_init - initialize interrupt handling
  *
@@ -569,6 +584,9 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 {
 	int i, j, k;
 
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_restore_msix(adev);
+
 	for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
 		if (!adev->irq.client[i].sources)
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 425596c2f6f8..96ef3f1051d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -124,6 +124,22 @@ void amdgpu_register_gpu_instance(struct amdgpu_device *adev)
 	mutex_unlock(&mgpu_info.mutex);
 }
 
+static void amdgpu_get_audio_func(struct amdgpu_device *adev)
+{
+	struct pci_dev *p = NULL;
+
+	p = pci_get_domain_bus_and_slot(pci_domain_nr(adev->pdev->bus),
+			adev->pdev->bus->number, 1);
+	if (p) {
+		pm_runtime_get_sync(&p->dev);
+
+		pm_runtime_mark_last_busy(&p->dev);
+		pm_runtime_put_autosuspend(&p->dev);
+
+		pci_dev_put(p);
+	}
+}
+
 /**
  * amdgpu_driver_load_kms - Main load function for KMS.
  *
@@ -213,9 +229,35 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags)
 						DPM_FLAG_MAY_SKIP_RESUME);
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
+
 		pm_runtime_allow(dev->dev);
+
 		pm_runtime_mark_last_busy(dev->dev);
 		pm_runtime_put_autosuspend(dev->dev);
+
+		/*
+		 * For runpm implemented via BACO, PMFW will handle the
+		 * timing for BACO in and out:
+		 *   - put ASIC into BACO state only when both video and
+		 *     audio functions are in D3 state.
+		 *   - pull ASIC out of BACO state when either video or
+		 *     audio function is in D0 state.
+		 * Also, at startup, PMFW assumes both functions are in
+		 * D0 state.
+		 *
+		 * So if snd driver was loaded prior to amdgpu driver
+		 * and audio function was put into D3 state, there will
+		 * be no PMFW-aware D-state transition(D0->D3) on runpm
+		 * suspend. Thus the BACO will be not correctly kicked in.
+		 *
+		 * Via amdgpu_get_audio_func(), the audio dev is put
+		 * into D0 state. Then there will be a PMFW-aware D-state
+		 * transition(D0->D3) on runpm suspend.
+		 */
+		if (amdgpu_device_supports_baco(dev) &&
+		    !(adev->flags & AMD_IS_APU) &&
+		    (adev->asic_type >= CHIP_NAVI10))
+			amdgpu_get_audio_func(adev);
 	}
 
 	if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DRV_LOAD))
@@ -1220,7 +1262,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	}
 
 	pasid = fpriv->vm.pasid;
-	pd = amdgpu_bo_ref(fpriv->vm.root.base.bo);
+	pd = amdgpu_bo_ref(fpriv->vm.root.bo);
 
 	amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
 	amdgpu_vm_fini(adev, &fpriv->vm);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index d6c54c7f7679..4b153daf283d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -160,7 +160,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct mm_struct *mm, struct page **pages,
 			       uint64_t start, uint64_t npages,
 			       struct hmm_range **phmm_range, bool readonly,
-			       bool mmap_locked)
+			       bool mmap_locked, void *owner)
 {
 	struct hmm_range *hmm_range;
 	unsigned long timeout;
@@ -185,6 +185,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 	hmm_range->hmm_pfns = pfns;
 	hmm_range->start = start;
 	hmm_range->end = start + npages * PAGE_SIZE;
+	hmm_range->dev_private_owner = owner;
 
 	/* Assuming 512MB takes maxmium 1 second to fault page address */
 	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
index 7f7d37a457c3..14a3c1864085 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
@@ -34,7 +34,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct mm_struct *mm, struct page **pages,
 			       uint64_t start, uint64_t npages,
 			       struct hmm_range **phmm_range, bool readonly,
-			       bool mmap_locked);
+			       bool mmap_locked, void *owner);
 int amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range);
 
 #if defined(CONFIG_HMM_MIRROR)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
index 25ee53545837..45295dce5c3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
@@ -93,6 +93,8 @@ struct amdgpu_nbio_funcs {
 	void (*enable_aspm)(struct amdgpu_device *adev,
 			    bool enable);
 	void (*program_aspm)(struct amdgpu_device *adev);
+	void (*apply_lc_spc_mode_wa)(struct amdgpu_device *adev);
+	void (*apply_l1_link_width_reconfig_wa)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_nbio {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 22fb4ab43eef..261283f5b424 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -54,29 +54,42 @@
 
 static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
-	struct amdgpu_bo_user *ubo;
 
 	amdgpu_bo_kunmap(bo);
 
 	if (bo->tbo.base.import_attach)
 		drm_prime_gem_destroy(&bo->tbo.base, bo->tbo.sg);
 	drm_gem_object_release(&bo->tbo.base);
+	amdgpu_bo_unref(&bo->parent);
+	kvfree(bo);
+}
+
+static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo)
+{
+	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
+	struct amdgpu_bo_user *ubo;
+
+	ubo = to_amdgpu_bo_user(bo);
+	kfree(ubo->metadata);
+	amdgpu_bo_destroy(tbo);
+}
+
+static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo)
+{
+	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
+	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
+	struct amdgpu_bo_vm *vmbo;
+
+	vmbo = to_amdgpu_bo_vm(bo);
 	/* in case amdgpu_device_recover_vram got NULL of bo->parent */
-	if (!list_empty(&bo->shadow_list)) {
+	if (!list_empty(&vmbo->shadow_list)) {
 		mutex_lock(&adev->shadow_list_lock);
-		list_del_init(&bo->shadow_list);
+		list_del_init(&vmbo->shadow_list);
 		mutex_unlock(&adev->shadow_list_lock);
 	}
-	amdgpu_bo_unref(&bo->parent);
-
-	if (bo->tbo.type != ttm_bo_type_kernel) {
-		ubo = to_amdgpu_bo_user(bo);
-		kfree(ubo->metadata);
-	}
 
-	kvfree(bo);
+	amdgpu_bo_destroy(tbo);
 }
 
 /**
@@ -91,8 +104,11 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
  */
 bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 {
-	if (bo->destroy == &amdgpu_bo_destroy)
+	if (bo->destroy == &amdgpu_bo_destroy ||
+	    bo->destroy == &amdgpu_bo_user_destroy ||
+	    bo->destroy == &amdgpu_bo_vm_destroy)
 		return true;
+
 	return false;
 }
 
@@ -545,7 +561,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (bo == NULL)
 		return -ENOMEM;
 	drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size);
-	INIT_LIST_HEAD(&bo->shadow_list);
 	bo->vm_bo = NULL;
 	bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain :
 		bp->domain;
@@ -568,9 +583,12 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (bp->type == ttm_bo_type_kernel)
 		bo->tbo.priority = 1;
 
+	if (!bp->destroy)
+		bp->destroy = &amdgpu_bo_destroy;
+
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type,
 				 &bo->placement, page_align, &ctx,  NULL,
-				 bp->resv, &amdgpu_bo_destroy);
+				 bp->resv, bp->destroy);
 	if (unlikely(r != 0))
 		return r;
 
@@ -634,6 +652,7 @@ int amdgpu_bo_create_user(struct amdgpu_device *adev,
 	int r;
 
 	bp->bo_ptr_size = sizeof(struct amdgpu_bo_user);
+	bp->destroy = &amdgpu_bo_user_destroy;
 	r = amdgpu_bo_create(adev, bp, &bo_ptr);
 	if (r)
 		return r;
@@ -665,11 +684,13 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev,
 	 * num of amdgpu_vm_pt entries.
 	 */
 	BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo_vm));
+	bp->destroy = &amdgpu_bo_vm_destroy;
 	r = amdgpu_bo_create(adev, bp, &bo_ptr);
 	if (r)
 		return r;
 
 	*vmbo_ptr = to_amdgpu_bo_vm(bo_ptr);
+	INIT_LIST_HEAD(&(*vmbo_ptr)->shadow_list);
 	return r;
 }
 
@@ -714,12 +735,12 @@ retry:
  *
  * Insert a BO to the shadow list.
  */
-void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo *bo)
+void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev);
 
 	mutex_lock(&adev->shadow_list_lock);
-	list_add_tail(&bo->shadow_list, &adev->shadow_list);
+	list_add_tail(&vmbo->shadow_list, &adev->shadow_list);
 	mutex_unlock(&adev->shadow_list_lock);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index c03dfd298f45..e72f329e7f18 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -55,7 +55,8 @@ struct amdgpu_bo_param {
 	u64				flags;
 	enum ttm_bo_type		type;
 	bool				no_wait_gpu;
-	struct dma_resv	*resv;
+	struct dma_resv			*resv;
+	void				(*destroy)(struct ttm_buffer_object *bo);
 };
 
 /* bo virtual addresses in a vm */
@@ -107,9 +108,6 @@ struct amdgpu_bo {
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_interval_notifier	notifier;
 #endif
-
-	struct list_head		shadow_list;
-
 	struct kgd_mem                  *kfd_bo;
 };
 
@@ -125,7 +123,8 @@ struct amdgpu_bo_user {
 struct amdgpu_bo_vm {
 	struct amdgpu_bo		bo;
 	struct amdgpu_bo		*shadow;
-	struct amdgpu_vm_pt             entries[];
+	struct list_head		shadow_list;
+	struct amdgpu_vm_bo_base        entries[];
 };
 
 static inline struct amdgpu_bo *ttm_to_amdgpu_bo(struct ttm_buffer_object *tbo)
@@ -331,7 +330,7 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo);
 int amdgpu_bo_validate(struct amdgpu_bo *bo);
 void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem,
 				uint64_t *gtt_mem, uint64_t *cpu_mem);
-void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo *bo);
+void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo);
 int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow,
 			     struct dma_fence **fence);
 uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 6046123d0562..3ec5099ffeb6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -171,11 +171,81 @@ Err_out:
 	return ret;
 }
 
+/*
+ * Helper funciton to query psp runtime database entry
+ *
+ * @adev: amdgpu_device pointer
+ * @entry_type: the type of psp runtime database entry
+ * @db_entry: runtime database entry pointer
+ *
+ * Return false if runtime database doesn't exit or entry is invalid
+ * or true if the specific database entry is found, and copy to @db_entry
+ */
+static bool psp_get_runtime_db_entry(struct amdgpu_device *adev,
+				     enum psp_runtime_entry_type entry_type,
+				     void *db_entry)
+{
+	uint64_t db_header_pos, db_dir_pos;
+	struct psp_runtime_data_header db_header = {0};
+	struct psp_runtime_data_directory db_dir = {0};
+	bool ret = false;
+	int i;
+
+	db_header_pos = adev->gmc.mc_vram_size - PSP_RUNTIME_DB_OFFSET;
+	db_dir_pos = db_header_pos + sizeof(struct psp_runtime_data_header);
+
+	/* read runtime db header from vram */
+	amdgpu_device_vram_access(adev, db_header_pos, (uint32_t *)&db_header,
+			sizeof(struct psp_runtime_data_header), false);
+
+	if (db_header.cookie != PSP_RUNTIME_DB_COOKIE_ID) {
+		/* runtime db doesn't exist, exit */
+		dev_warn(adev->dev, "PSP runtime database doesn't exist\n");
+		return false;
+	}
+
+	/* read runtime database entry from vram */
+	amdgpu_device_vram_access(adev, db_dir_pos, (uint32_t *)&db_dir,
+			sizeof(struct psp_runtime_data_directory), false);
+
+	if (db_dir.entry_count >= PSP_RUNTIME_DB_DIAG_ENTRY_MAX_COUNT) {
+		/* invalid db entry count, exit */
+		dev_warn(adev->dev, "Invalid PSP runtime database entry count\n");
+		return false;
+	}
+
+	/* look up for requested entry type */
+	for (i = 0; i < db_dir.entry_count && !ret; i++) {
+		if (db_dir.entry_list[i].entry_type == entry_type) {
+			switch (entry_type) {
+			case PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG:
+				if (db_dir.entry_list[i].size < sizeof(struct psp_runtime_boot_cfg_entry)) {
+					/* invalid db entry size */
+					dev_warn(adev->dev, "Invalid PSP runtime database entry size\n");
+					return false;
+				}
+				/* read runtime database entry */
+				amdgpu_device_vram_access(adev, db_header_pos + db_dir.entry_list[i].offset,
+							  (uint32_t *)db_entry, sizeof(struct psp_runtime_boot_cfg_entry), false);
+				ret = true;
+				break;
+			default:
+				ret = false;
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
 static int psp_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct psp_context *psp = &adev->psp;
 	int ret;
+	struct psp_runtime_boot_cfg_entry boot_cfg_entry;
+	struct psp_memory_training_context *mem_training_ctx = &psp->mem_train_ctx;
 
 	if (!amdgpu_sriov_vf(adev)) {
 		ret = psp_init_microcode(psp);
@@ -191,15 +261,39 @@ static int psp_sw_init(void *handle)
 		}
 	}
 
-	ret = psp_memory_training_init(psp);
-	if (ret) {
-		DRM_ERROR("Failed to initialize memory training!\n");
-		return ret;
+	memset(&boot_cfg_entry, 0, sizeof(boot_cfg_entry));
+	if (psp_get_runtime_db_entry(adev,
+				PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG,
+				&boot_cfg_entry)) {
+		psp->boot_cfg_bitmask = boot_cfg_entry.boot_cfg_bitmask;
+		if ((psp->boot_cfg_bitmask) &
+		    BOOT_CFG_FEATURE_TWO_STAGE_DRAM_TRAINING) {
+			/* If psp runtime database exists, then
+			 * only enable two stage memory training
+			 * when TWO_STAGE_DRAM_TRAINING bit is set
+			 * in runtime database */
+			mem_training_ctx->enable_mem_training = true;
+		}
+
+	} else {
+		/* If psp runtime database doesn't exist or
+		 * is invalid, force enable two stage memory
+		 * training */
+		mem_training_ctx->enable_mem_training = true;
 	}
-	ret = psp_mem_training(psp, PSP_MEM_TRAIN_COLD_BOOT);
-	if (ret) {
-		DRM_ERROR("Failed to process memory training!\n");
-		return ret;
+
+	if (mem_training_ctx->enable_mem_training) {
+		ret = psp_memory_training_init(psp);
+		if (ret) {
+			DRM_ERROR("Failed to initialize memory training!\n");
+			return ret;
+		}
+
+		ret = psp_mem_training(psp, PSP_MEM_TRAIN_COLD_BOOT);
+		if (ret) {
+			DRM_ERROR("Failed to process memory training!\n");
+			return ret;
+		}
 	}
 
 	if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) {
@@ -551,7 +645,30 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_boot_config_set(struct amdgpu_device *adev)
+static int psp_boot_config_get(struct amdgpu_device *adev, uint32_t *boot_cfg)
+{
+	struct psp_context *psp = &adev->psp;
+	struct psp_gfx_cmd_resp *cmd = psp->cmd;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp));
+
+	cmd->cmd_id = GFX_CMD_ID_BOOT_CFG;
+	cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_GET;
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	if (!ret) {
+		*boot_cfg =
+			(cmd->resp.uresp.boot_cfg.boot_cfg & BOOT_CONFIG_GECC) ? 1 : 0;
+	}
+
+	return ret;
+}
+
+static int psp_boot_config_set(struct amdgpu_device *adev, uint32_t boot_cfg)
 {
 	struct psp_context *psp = &adev->psp;
 	struct psp_gfx_cmd_resp *cmd = psp->cmd;
@@ -563,8 +680,8 @@ static int psp_boot_config_set(struct amdgpu_device *adev)
 
 	cmd->cmd_id = GFX_CMD_ID_BOOT_CFG;
 	cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_SET;
-	cmd->cmd.boot_cfg.boot_config = BOOT_CONFIG_GECC;
-	cmd->cmd.boot_cfg.boot_config_valid = BOOT_CONFIG_GECC;
+	cmd->cmd.boot_cfg.boot_config = boot_cfg;
+	cmd->cmd.boot_cfg.boot_config_valid = boot_cfg;
 
 	return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 }
@@ -1212,19 +1329,62 @@ static int psp_ras_terminate(struct psp_context *psp)
 static int psp_ras_initialize(struct psp_context *psp)
 {
 	int ret;
+	uint32_t boot_cfg = 0xFF;
+	struct amdgpu_device *adev = psp->adev;
 
 	/*
 	 * TODO: bypass the initialize in sriov for now
 	 */
-	if (amdgpu_sriov_vf(psp->adev))
+	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	if (!psp->adev->psp.ta_ras_ucode_size ||
-	    !psp->adev->psp.ta_ras_start_addr) {
-		dev_info(psp->adev->dev, "RAS: optional ras ta ucode is not available\n");
+	if (!adev->psp.ta_ras_ucode_size ||
+	    !adev->psp.ta_ras_start_addr) {
+		dev_info(adev->dev, "RAS: optional ras ta ucode is not available\n");
 		return 0;
 	}
 
+	if (amdgpu_atomfirmware_dynamic_boot_config_supported(adev)) {
+		/* query GECC enablement status from boot config
+		 * boot_cfg: 1: GECC is enabled or 0: GECC is disabled
+		 */
+		ret = psp_boot_config_get(adev, &boot_cfg);
+		if (ret)
+			dev_warn(adev->dev, "PSP get boot config failed\n");
+
+		if (!amdgpu_ras_is_supported(psp->adev, AMDGPU_RAS_BLOCK__UMC)) {
+			if (!boot_cfg) {
+				dev_info(adev->dev, "GECC is disabled\n");
+			} else {
+				/* disable GECC in next boot cycle if ras is
+				 * disabled by module parameter amdgpu_ras_enable
+				 * and/or amdgpu_ras_mask, or boot_config_get call
+				 * is failed
+				 */
+				ret = psp_boot_config_set(adev, 0);
+				if (ret)
+					dev_warn(adev->dev, "PSP set boot config failed\n");
+				else
+					dev_warn(adev->dev, "GECC will be disabled in next boot cycle "
+						 "if set amdgpu_ras_enable and/or amdgpu_ras_mask to 0x0\n");
+			}
+		} else {
+			if (1 == boot_cfg) {
+				dev_info(adev->dev, "GECC is enabled\n");
+			} else {
+				/* enable GECC in next boot cycle if it is disabled
+				 * in boot config, or force enable GECC if failed to
+				 * get boot configuration
+				 */
+				ret = psp_boot_config_set(adev, BOOT_CONFIG_GECC);
+				if (ret)
+					dev_warn(adev->dev, "PSP set boot config failed\n");
+				else
+					dev_warn(adev->dev, "GECC will be enabled in next boot cycle\n");
+			}
+		}
+	}
+
 	if (!psp->ras.ras_initialized) {
 		ret = psp_ras_init_shared_buf(psp);
 		if (ret)
@@ -1945,12 +2105,6 @@ static int psp_hw_start(struct psp_context *psp)
 		return ret;
 	}
 
-	if (amdgpu_atomfirmware_dynamic_boot_config_supported(adev)) {
-		ret = psp_boot_config_set(adev);
-		if (ret)
-			dev_warn(adev->dev, "PSP set boot config failed\n");
-	}
-
 	ret = psp_tmr_init(psp);
 	if (ret) {
 		DRM_ERROR("PSP tmr init failed!\n");
@@ -2188,10 +2342,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 	if ((amdgpu_in_reset(adev) &&
 	     ras && adev->ras_enabled &&
 	     (adev->asic_type == CHIP_ARCTURUS ||
-	      adev->asic_type == CHIP_VEGA20)) ||
-	     (adev->in_runpm &&
-	      adev->asic_type >= CHIP_NAVI10 &&
-	      adev->asic_type <= CHIP_NAVI12)) {
+	      adev->asic_type == CHIP_VEGA20))) {
 		ret = amdgpu_dpm_set_mp1_state(adev, PP_MP1_STATE_UNLOAD);
 		if (ret) {
 			DRM_WARN("Failed to set MP1 state prepare for reload\n");
@@ -2562,10 +2713,12 @@ static int psp_resume(void *handle)
 
 	DRM_INFO("PSP is resuming...\n");
 
-	ret = psp_mem_training(psp, PSP_MEM_TRAIN_RESUME);
-	if (ret) {
-		DRM_ERROR("Failed to process memory training!\n");
-		return ret;
+	if (psp->mem_train_ctx.enable_mem_training) {
+		ret = psp_mem_training(psp, PSP_MEM_TRAIN_RESUME);
+		if (ret) {
+			DRM_ERROR("Failed to process memory training!\n");
+			return ret;
+		}
 	}
 
 	mutex_lock(&adev->firmware.mutex);
@@ -2749,7 +2902,7 @@ int psp_init_asd_microcode(struct psp_context *psp,
 
 	asd_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.asd_fw->data;
 	adev->psp.asd_fw_version = le32_to_cpu(asd_hdr->header.ucode_version);
-	adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->ucode_feature_version);
+	adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->sos.fw_version);
 	adev->psp.asd_ucode_size = le32_to_cpu(asd_hdr->header.ucode_size_bytes);
 	adev->psp.asd_start_addr = (uint8_t *)asd_hdr +
 				le32_to_cpu(asd_hdr->header.ucode_array_offset_bytes);
@@ -2785,7 +2938,7 @@ int psp_init_toc_microcode(struct psp_context *psp,
 
 	toc_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.toc_fw->data;
 	adev->psp.toc_fw_version = le32_to_cpu(toc_hdr->header.ucode_version);
-	adev->psp.toc_feature_version = le32_to_cpu(toc_hdr->ucode_feature_version);
+	adev->psp.toc_feature_version = le32_to_cpu(toc_hdr->sos.fw_version);
 	adev->psp.toc_bin_size = le32_to_cpu(toc_hdr->header.ucode_size_bytes);
 	adev->psp.toc_start_addr = (uint8_t *)toc_hdr +
 				le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes);
@@ -2797,6 +2950,50 @@ out:
 	return err;
 }
 
+static int psp_init_sos_base_fw(struct amdgpu_device *adev)
+{
+	const struct psp_firmware_header_v1_0 *sos_hdr;
+	const struct psp_firmware_header_v1_3 *sos_hdr_v1_3;
+	uint8_t *ucode_array_start_addr;
+
+	sos_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.sos_fw->data;
+	ucode_array_start_addr = (uint8_t *)sos_hdr +
+		le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes);
+
+	if (adev->gmc.xgmi.connected_to_cpu || (adev->asic_type != CHIP_ALDEBARAN)) {
+		adev->psp.sos_fw_version = le32_to_cpu(sos_hdr->header.ucode_version);
+		adev->psp.sos_feature_version = le32_to_cpu(sos_hdr->sos.fw_version);
+
+		adev->psp.sys_bin_size = le32_to_cpu(sos_hdr->sos.offset_bytes);
+		adev->psp.sys_start_addr = ucode_array_start_addr;
+
+		adev->psp.sos_bin_size = le32_to_cpu(sos_hdr->sos.size_bytes);
+		adev->psp.sos_start_addr = ucode_array_start_addr +
+				le32_to_cpu(sos_hdr->sos.offset_bytes);
+	} else {
+		/* Load alternate PSP SOS FW */
+		sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data;
+
+		adev->psp.sos_fw_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version);
+		adev->psp.sos_feature_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version);
+
+		adev->psp.sys_bin_size = le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.size_bytes);
+		adev->psp.sys_start_addr = ucode_array_start_addr +
+			le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.offset_bytes);
+
+		adev->psp.sos_bin_size = le32_to_cpu(sos_hdr_v1_3->sos_aux.size_bytes);
+		adev->psp.sos_start_addr = ucode_array_start_addr +
+			le32_to_cpu(sos_hdr_v1_3->sos_aux.offset_bytes);
+	}
+
+	if ((adev->psp.sys_bin_size == 0) || (adev->psp.sos_bin_size == 0)) {
+		dev_warn(adev->dev, "PSP SOS FW not available");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int psp_init_sos_microcode(struct psp_context *psp,
 			   const char *chip_name)
 {
@@ -2807,6 +3004,7 @@ int psp_init_sos_microcode(struct psp_context *psp,
 	const struct psp_firmware_header_v1_2 *sos_hdr_v1_2;
 	const struct psp_firmware_header_v1_3 *sos_hdr_v1_3;
 	int err = 0;
+	uint8_t *ucode_array_start_addr;
 
 	if (!chip_name) {
 		dev_err(adev->dev, "invalid chip name for sos microcode\n");
@@ -2823,47 +3021,45 @@ int psp_init_sos_microcode(struct psp_context *psp,
 		goto out;
 
 	sos_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.sos_fw->data;
+	ucode_array_start_addr = (uint8_t *)sos_hdr +
+		le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes);
 	amdgpu_ucode_print_psp_hdr(&sos_hdr->header);
 
 	switch (sos_hdr->header.header_version_major) {
 	case 1:
-		adev->psp.sos_fw_version = le32_to_cpu(sos_hdr->header.ucode_version);
-		adev->psp.sos_feature_version = le32_to_cpu(sos_hdr->ucode_feature_version);
-		adev->psp.sos_bin_size = le32_to_cpu(sos_hdr->sos_size_bytes);
-		adev->psp.sys_bin_size = le32_to_cpu(sos_hdr->sos_offset_bytes);
-		adev->psp.sys_start_addr = (uint8_t *)sos_hdr +
-				le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes);
-		adev->psp.sos_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-				le32_to_cpu(sos_hdr->sos_offset_bytes);
+		err = psp_init_sos_base_fw(adev);
+		if (err)
+			goto out;
+
 		if (sos_hdr->header.header_version_minor == 1) {
 			sos_hdr_v1_1 = (const struct psp_firmware_header_v1_1 *)adev->psp.sos_fw->data;
-			adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_1->toc_size_bytes);
+			adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_1->toc.size_bytes);
 			adev->psp.toc_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-					le32_to_cpu(sos_hdr_v1_1->toc_offset_bytes);
-			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_1->kdb_size_bytes);
+					le32_to_cpu(sos_hdr_v1_1->toc.offset_bytes);
+			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_1->kdb.size_bytes);
 			adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-					le32_to_cpu(sos_hdr_v1_1->kdb_offset_bytes);
+					le32_to_cpu(sos_hdr_v1_1->kdb.offset_bytes);
 		}
 		if (sos_hdr->header.header_version_minor == 2) {
 			sos_hdr_v1_2 = (const struct psp_firmware_header_v1_2 *)adev->psp.sos_fw->data;
-			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_2->kdb_size_bytes);
+			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_2->kdb.size_bytes);
 			adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-						    le32_to_cpu(sos_hdr_v1_2->kdb_offset_bytes);
+						    le32_to_cpu(sos_hdr_v1_2->kdb.offset_bytes);
 		}
 		if (sos_hdr->header.header_version_minor == 3) {
 			sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data;
-			adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.toc_size_bytes);
-			adev->psp.toc_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-				le32_to_cpu(sos_hdr_v1_3->v1_1.toc_offset_bytes);
-			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.kdb_size_bytes);
-			adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-				le32_to_cpu(sos_hdr_v1_3->v1_1.kdb_offset_bytes);
-			adev->psp.spl_bin_size = le32_to_cpu(sos_hdr_v1_3->spl_size_bytes);
-			adev->psp.spl_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-				le32_to_cpu(sos_hdr_v1_3->spl_offset_bytes);
-			adev->psp.rl_bin_size = le32_to_cpu(sos_hdr_v1_3->rl_size_bytes);
-			adev->psp.rl_start_addr = (uint8_t *)adev->psp.sys_start_addr +
-				le32_to_cpu(sos_hdr_v1_3->rl_offset_bytes);
+			adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.toc.size_bytes);
+			adev->psp.toc_start_addr = ucode_array_start_addr +
+				le32_to_cpu(sos_hdr_v1_3->v1_1.toc.offset_bytes);
+			adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.size_bytes);
+			adev->psp.kdb_start_addr = ucode_array_start_addr +
+				le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.offset_bytes);
+			adev->psp.spl_bin_size = le32_to_cpu(sos_hdr_v1_3->spl.size_bytes);
+			adev->psp.spl_start_addr = ucode_array_start_addr +
+				le32_to_cpu(sos_hdr_v1_3->spl.offset_bytes);
+			adev->psp.rl_bin_size = le32_to_cpu(sos_hdr_v1_3->rl.size_bytes);
+			adev->psp.rl_start_addr = ucode_array_start_addr +
+				le32_to_cpu(sos_hdr_v1_3->rl.offset_bytes);
 		}
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index e5023f1de7fd..3030ec24eb3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -225,6 +225,61 @@ struct psp_memory_training_context {
 
 	enum psp_memory_training_init_flag init;
 	u32 training_cnt;
+	bool enable_mem_training;
+};
+
+/** PSP runtime DB **/
+#define PSP_RUNTIME_DB_SIZE_IN_BYTES		0x10000
+#define PSP_RUNTIME_DB_OFFSET			0x100000
+#define PSP_RUNTIME_DB_COOKIE_ID		0x0ed5
+#define PSP_RUNTIME_DB_VER_1			0x0100
+#define PSP_RUNTIME_DB_DIAG_ENTRY_MAX_COUNT	0x40
+
+enum psp_runtime_entry_type {
+	PSP_RUNTIME_ENTRY_TYPE_INVALID		= 0x0,
+	PSP_RUNTIME_ENTRY_TYPE_TEST		= 0x1,
+	PSP_RUNTIME_ENTRY_TYPE_MGPU_COMMON	= 0x2,  /* Common mGPU runtime data */
+	PSP_RUNTIME_ENTRY_TYPE_MGPU_WAFL	= 0x3,  /* WAFL runtime data */
+	PSP_RUNTIME_ENTRY_TYPE_MGPU_XGMI	= 0x4,  /* XGMI runtime data */
+	PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG	= 0x5,  /* Boot Config runtime data */
+};
+
+/* PSP runtime DB header */
+struct psp_runtime_data_header {
+	/* determine the existence of runtime db */
+	uint16_t cookie;
+	/* version of runtime db */
+	uint16_t version;
+};
+
+/* PSP runtime DB entry */
+struct psp_runtime_entry {
+	/* type of runtime db entry */
+	uint32_t entry_type;
+	/* offset of entry in bytes */
+	uint16_t offset;
+	/* size of entry in bytes */
+	uint16_t size;
+};
+
+/* PSP runtime DB directory */
+struct psp_runtime_data_directory {
+	/* number of valid entries */
+	uint16_t			entry_count;
+	/* db entries*/
+	struct psp_runtime_entry	entry_list[PSP_RUNTIME_DB_DIAG_ENTRY_MAX_COUNT];
+};
+
+/* PSP runtime DB boot config feature bitmask */
+enum psp_runtime_boot_cfg_feature {
+	BOOT_CFG_FEATURE_GECC                       = 0x1,
+	BOOT_CFG_FEATURE_TWO_STAGE_DRAM_TRAINING    = 0x2,
+};
+
+/* PSP runtime DB boot config entry */
+struct psp_runtime_boot_cfg_entry {
+	uint32_t boot_cfg_bitmask;
+	uint32_t reserved;
 };
 
 struct psp_context
@@ -325,6 +380,8 @@ struct psp_context
 	struct psp_securedisplay_context	securedisplay_context;
 	struct mutex			mutex;
 	struct psp_memory_training_context mem_train_ctx;
+
+	uint32_t			boot_cfg_bitmask;
 };
 
 struct amdgpu_psp_funcs {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 9dfc1ebb41a9..fc66aca28594 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -809,7 +809,7 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev,
 
 /* query/inject/cure begin */
 int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
-	struct ras_query_if *info)
+				  struct ras_query_if *info)
 {
 	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
 	struct ras_err_data err_data = {0, 0, 0, NULL};
@@ -1043,17 +1043,32 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
 	return ret;
 }
 
-/* get the total error counts on all IPs */
-void amdgpu_ras_query_error_count(struct amdgpu_device *adev,
-				  unsigned long *ce_count,
-				  unsigned long *ue_count)
+/**
+ * amdgpu_ras_query_error_count -- Get error counts of all IPs
+ * adev: pointer to AMD GPU device
+ * ce_count: pointer to an integer to be set to the count of correctible errors.
+ * ue_count: pointer to an integer to be set to the count of uncorrectible
+ * errors.
+ *
+ * If set, @ce_count or @ue_count, count and return the corresponding
+ * error counts in those integer pointers. Return 0 if the device
+ * supports RAS. Return -EOPNOTSUPP if the device doesn't support RAS.
+ */
+int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
+				 unsigned long *ce_count,
+				 unsigned long *ue_count)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_manager *obj;
 	unsigned long ce, ue;
 
 	if (!adev->ras_enabled || !con)
-		return;
+		return -EOPNOTSUPP;
+
+	/* Don't count since no reporting.
+	 */
+	if (!ce_count && !ue_count)
+		return 0;
 
 	ce = 0;
 	ue = 0;
@@ -1061,9 +1076,11 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 		struct ras_query_if info = {
 			.head = obj->head,
 		};
+		int res;
 
-		if (amdgpu_ras_query_error_status(adev, &info))
-			return;
+		res = amdgpu_ras_query_error_status(adev, &info);
+		if (res)
+			return res;
 
 		ce += info.ce_count;
 		ue += info.ue_count;
@@ -1074,6 +1091,8 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 
 	if (ue_count)
 		*ue_count = ue;
+
+	return 0;
 }
 /* query/inject/cure end */
 
@@ -1984,6 +2003,9 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 		ret = amdgpu_ras_load_bad_pages(adev);
 		if (ret)
 			goto free;
+
+		if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->send_hbm_bad_pages_num)
+			adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.num_recs);
 	}
 
 	return 0;
@@ -2063,7 +2085,9 @@ static void amdgpu_ras_get_quirks(struct amdgpu_device *adev)
 		return;
 
 	if (strnstr(ctx->vbios_version, "D16406",
-		    sizeof(ctx->vbios_version)))
+		    sizeof(ctx->vbios_version)) ||
+		strnstr(ctx->vbios_version, "D36002",
+			sizeof(ctx->vbios_version)))
 		adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__GFX);
 }
 
@@ -2122,7 +2146,7 @@ static void amdgpu_ras_counte_dw(struct work_struct *work)
 	struct amdgpu_ras *con = container_of(work, struct amdgpu_ras,
 					      ras_counte_delay_work.work);
 	struct amdgpu_device *adev = con->adev;
-	struct drm_device *dev = &adev->ddev;
+	struct drm_device *dev = adev_to_drm(adev);
 	unsigned long ce_count, ue_count;
 	int res;
 
@@ -2132,9 +2156,10 @@ static void amdgpu_ras_counte_dw(struct work_struct *work)
 
 	/* Cache new values.
 	 */
-	amdgpu_ras_query_error_count(adev, &ce_count, &ue_count);
-	atomic_set(&con->ras_ce_count, ce_count);
-	atomic_set(&con->ras_ue_count, ue_count);
+	if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) {
+		atomic_set(&con->ras_ce_count, ce_count);
+		atomic_set(&con->ras_ue_count, ue_count);
+	}
 
 	pm_runtime_mark_last_busy(dev->dev);
 Out:
@@ -2307,9 +2332,10 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev,
 
 	/* Those are the cached values at init.
 	 */
-	amdgpu_ras_query_error_count(adev, &ce_count, &ue_count);
-	atomic_set(&con->ras_ce_count, ce_count);
-	atomic_set(&con->ras_ue_count, ue_count);
+	if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) {
+		atomic_set(&con->ras_ce_count, ce_count);
+		atomic_set(&con->ras_ue_count, ue_count);
+	}
 
 	return 0;
 cleanup:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 256cea5d34f2..b504ed8c9b50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -490,9 +490,9 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev,
 void amdgpu_ras_resume(struct amdgpu_device *adev);
 void amdgpu_ras_suspend(struct amdgpu_device *adev);
 
-void amdgpu_ras_query_error_count(struct amdgpu_device *adev,
-				  unsigned long *ce_count,
-				  unsigned long *ue_count);
+int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
+				 unsigned long *ce_count,
+				 unsigned long *ue_count);
 
 /* error handling functions */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 0527772fe1b8..d855cb53c7e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -176,10 +176,10 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 
 	    TP_fast_assign(
 			   __entry->sched_job_id = job->base.id;
-			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job));
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name)
+			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name);
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -201,10 +201,10 @@ TRACE_EVENT(amdgpu_sched_run_job,
 
 	    TP_fast_assign(
 			   __entry->sched_job_id = job->base.id;
-			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job));
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name)
+			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name);
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -229,7 +229,7 @@ TRACE_EVENT(amdgpu_vm_grab_id,
 
 	    TP_fast_assign(
 			   __entry->pasid = vm->pasid;
-			   __assign_str(ring, ring->name)
+			   __assign_str(ring, ring->name);
 			   __entry->vmid = job->vmid;
 			   __entry->vm_hub = ring->funcs->vmhub,
 			   __entry->pd_addr = job->vm_pd_addr;
@@ -424,7 +424,7 @@ TRACE_EVENT(amdgpu_vm_flush,
 			     ),
 
 	    TP_fast_assign(
-			   __assign_str(ring, ring->name)
+			   __assign_str(ring, ring->name);
 			   __entry->vmid = vmid;
 			   __entry->vm_hub = ring->funcs->vmhub;
 			   __entry->pd_addr = pd_addr;
@@ -525,7 +525,7 @@ TRACE_EVENT(amdgpu_ib_pipe_sync,
 			     ),
 
 	    TP_fast_assign(
-			   __assign_str(ring, sched_job->base.sched->name)
+			   __assign_str(ring, sched_job->base.sched->name);
 			   __entry->id = sched_job->base.id;
 			   __entry->fence = fence;
 			   __entry->ctx = fence->context;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b46726e47bce..acd95d3a4434 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -592,10 +592,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev,
 
 		mem->bus.offset += adev->gmc.aper_base;
 		mem->bus.is_iomem = true;
-		if (adev->gmc.xgmi.connected_to_cpu)
-			mem->bus.caching = ttm_cached;
-		else
-			mem->bus.caching = ttm_write_combined;
 		break;
 	default:
 		return -EINVAL;
@@ -683,23 +679,23 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 		return -ESRCH;
 
 	mmap_read_lock(mm);
-	vma = find_vma(mm, start);
-	mmap_read_unlock(mm);
-	if (unlikely(!vma || start < vma->vm_start)) {
+	vma = vma_lookup(mm, start);
+	if (unlikely(!vma)) {
 		r = -EFAULT;
-		goto out_putmm;
+		goto out_unlock;
 	}
 	if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) &&
 		vma->vm_file)) {
 		r = -EPERM;
-		goto out_putmm;
+		goto out_unlock;
 	}
 
 	readonly = amdgpu_ttm_tt_is_readonly(ttm);
 	r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start,
 				       ttm->num_pages, &gtt->range, readonly,
-				       false);
-out_putmm:
+				       true, NULL);
+out_unlock:
+	mmap_read_unlock(mm);
 	mmput(mm);
 
 	return r;
@@ -843,7 +839,7 @@ static int amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
 		uint64_t page_idx = 1;
 
 		r = amdgpu_gart_bind(adev, gtt->offset, page_idx,
-				ttm->pages, gtt->ttm.dma_address, flags);
+				gtt->ttm.dma_address, flags);
 		if (r)
 			goto gart_bind_fail;
 
@@ -857,11 +853,10 @@ static int amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
 		r = amdgpu_gart_bind(adev,
 				gtt->offset + (page_idx << PAGE_SHIFT),
 				ttm->num_pages - page_idx,
-				&ttm->pages[page_idx],
 				&(gtt->ttm.dma_address[page_idx]), flags);
 	} else {
 		r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages,
-				     ttm->pages, gtt->ttm.dma_address, flags);
+				     gtt->ttm.dma_address, flags);
 	}
 
 gart_bind_fail:
@@ -926,7 +921,8 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev,
 	    bo_mem->mem_type == AMDGPU_PL_OA)
 		return -EINVAL;
 
-	if (!amdgpu_gtt_mgr_has_gart_addr(bo_mem)) {
+	if (bo_mem->mem_type != TTM_PL_TT ||
+	    !amdgpu_gtt_mgr_has_gart_addr(bo_mem)) {
 		gtt->offset = AMDGPU_BO_INVALID_OFFSET;
 		return 0;
 	}
@@ -937,7 +933,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev,
 	/* bind pages into GART page tables */
 	gtt->offset = (u64)bo_mem->start << PAGE_SHIFT;
 	r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages,
-		ttm->pages, gtt->ttm.dma_address, flags);
+		gtt->ttm.dma_address, flags);
 
 	if (r)
 		DRM_ERROR("failed to bind %u pages at 0x%08llX\n",
@@ -1131,8 +1127,6 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 		ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL);
 		if (!ttm->sg)
 			return -ENOMEM;
-
-		ttm->page_flags |= TTM_PAGE_FLAG_SG;
 		return 0;
 	}
 
@@ -1158,7 +1152,6 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
 		kfree(ttm->sg);
 		ttm->sg = NULL;
-		ttm->page_flags &= ~TTM_PAGE_FLAG_SG;
 		return;
 	}
 
@@ -1192,6 +1185,9 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
 			return -ENOMEM;
 	}
 
+	/* Set TTM_PAGE_FLAG_SG before populate but after create. */
+	bo->ttm->page_flags |= TTM_PAGE_FLAG_SG;
+
 	gtt = (void *)bo->ttm;
 	gtt->userptr = addr;
 	gtt->userflags = flags;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 5eb84de588eb..2834981f8c08 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -257,36 +257,36 @@ void amdgpu_ucode_print_psp_hdr(const struct common_firmware_header *hdr)
 			container_of(hdr, struct psp_firmware_header_v1_0, header);
 
 		DRM_DEBUG("ucode_feature_version: %u\n",
-			  le32_to_cpu(psp_hdr->ucode_feature_version));
+			  le32_to_cpu(psp_hdr->sos.fw_version));
 		DRM_DEBUG("sos_offset_bytes: %u\n",
-			  le32_to_cpu(psp_hdr->sos_offset_bytes));
+			  le32_to_cpu(psp_hdr->sos.offset_bytes));
 		DRM_DEBUG("sos_size_bytes: %u\n",
-			  le32_to_cpu(psp_hdr->sos_size_bytes));
+			  le32_to_cpu(psp_hdr->sos.size_bytes));
 		if (version_minor == 1) {
 			const struct psp_firmware_header_v1_1 *psp_hdr_v1_1 =
 				container_of(psp_hdr, struct psp_firmware_header_v1_1, v1_0);
 			DRM_DEBUG("toc_header_version: %u\n",
-				  le32_to_cpu(psp_hdr_v1_1->toc_header_version));
+				  le32_to_cpu(psp_hdr_v1_1->toc.fw_version));
 			DRM_DEBUG("toc_offset_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_1->toc_offset_bytes));
+				  le32_to_cpu(psp_hdr_v1_1->toc.offset_bytes));
 			DRM_DEBUG("toc_size_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_1->toc_size_bytes));
+				  le32_to_cpu(psp_hdr_v1_1->toc.size_bytes));
 			DRM_DEBUG("kdb_header_version: %u\n",
-				  le32_to_cpu(psp_hdr_v1_1->kdb_header_version));
+				  le32_to_cpu(psp_hdr_v1_1->kdb.fw_version));
 			DRM_DEBUG("kdb_offset_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_1->kdb_offset_bytes));
+				  le32_to_cpu(psp_hdr_v1_1->kdb.offset_bytes));
 			DRM_DEBUG("kdb_size_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_1->kdb_size_bytes));
+				  le32_to_cpu(psp_hdr_v1_1->kdb.size_bytes));
 		}
 		if (version_minor == 2) {
 			const struct psp_firmware_header_v1_2 *psp_hdr_v1_2 =
 				container_of(psp_hdr, struct psp_firmware_header_v1_2, v1_0);
 			DRM_DEBUG("kdb_header_version: %u\n",
-				  le32_to_cpu(psp_hdr_v1_2->kdb_header_version));
+				  le32_to_cpu(psp_hdr_v1_2->kdb.fw_version));
 			DRM_DEBUG("kdb_offset_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_2->kdb_offset_bytes));
+				  le32_to_cpu(psp_hdr_v1_2->kdb.offset_bytes));
 			DRM_DEBUG("kdb_size_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_2->kdb_size_bytes));
+				  le32_to_cpu(psp_hdr_v1_2->kdb.size_bytes));
 		}
 		if (version_minor == 3) {
 			const struct psp_firmware_header_v1_1 *psp_hdr_v1_1 =
@@ -294,23 +294,23 @@ void amdgpu_ucode_print_psp_hdr(const struct common_firmware_header *hdr)
 			const struct psp_firmware_header_v1_3 *psp_hdr_v1_3 =
 				container_of(psp_hdr_v1_1, struct psp_firmware_header_v1_3, v1_1);
 			DRM_DEBUG("toc_header_version: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->v1_1.toc_header_version));
+				  le32_to_cpu(psp_hdr_v1_3->v1_1.toc.fw_version));
 			DRM_DEBUG("toc_offset_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->v1_1.toc_offset_bytes));
+				  le32_to_cpu(psp_hdr_v1_3->v1_1.toc.offset_bytes));
 			DRM_DEBUG("toc_size_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->v1_1.toc_size_bytes));
+				  le32_to_cpu(psp_hdr_v1_3->v1_1.toc.size_bytes));
 			DRM_DEBUG("kdb_header_version: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->v1_1.kdb_header_version));
+				  le32_to_cpu(psp_hdr_v1_3->v1_1.kdb.fw_version));
 			DRM_DEBUG("kdb_offset_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->v1_1.kdb_offset_bytes));
+				  le32_to_cpu(psp_hdr_v1_3->v1_1.kdb.offset_bytes));
 			DRM_DEBUG("kdb_size_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->v1_1.kdb_size_bytes));
+				  le32_to_cpu(psp_hdr_v1_3->v1_1.kdb.size_bytes));
 			DRM_DEBUG("spl_header_version: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->spl_header_version));
+				  le32_to_cpu(psp_hdr_v1_3->spl.fw_version));
 			DRM_DEBUG("spl_offset_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->spl_offset_bytes));
+				  le32_to_cpu(psp_hdr_v1_3->spl.offset_bytes));
 			DRM_DEBUG("spl_size_bytes: %u\n",
-				  le32_to_cpu(psp_hdr_v1_3->spl_size_bytes));
+				  le32_to_cpu(psp_hdr_v1_3->spl.size_bytes));
 		}
 	} else {
 		DRM_ERROR("Unknown PSP ucode version: %u.%u\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 2c42874f7784..270309e7f5f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -71,43 +71,39 @@ struct smc_firmware_header_v2_1 {
         uint32_t pptable_entry_offset;
 };
 
+struct psp_fw_bin_desc {
+	uint32_t fw_version;
+	uint32_t offset_bytes;
+	uint32_t size_bytes;
+};
+
 /* version_major=1, version_minor=0 */
 struct psp_firmware_header_v1_0 {
 	struct common_firmware_header header;
-	uint32_t ucode_feature_version;
-	uint32_t sos_offset_bytes;
-	uint32_t sos_size_bytes;
+	struct psp_fw_bin_desc sos;
 };
 
 /* version_major=1, version_minor=1 */
 struct psp_firmware_header_v1_1 {
 	struct psp_firmware_header_v1_0 v1_0;
-	uint32_t toc_header_version;
-	uint32_t toc_offset_bytes;
-	uint32_t toc_size_bytes;
-	uint32_t kdb_header_version;
-	uint32_t kdb_offset_bytes;
-	uint32_t kdb_size_bytes;
+	struct psp_fw_bin_desc toc;
+	struct psp_fw_bin_desc kdb;
 };
 
 /* version_major=1, version_minor=2 */
 struct psp_firmware_header_v1_2 {
 	struct psp_firmware_header_v1_0 v1_0;
-	uint32_t reserve[3];
-	uint32_t kdb_header_version;
-	uint32_t kdb_offset_bytes;
-	uint32_t kdb_size_bytes;
+	struct psp_fw_bin_desc res;
+	struct psp_fw_bin_desc kdb;
 };
 
 /* version_major=1, version_minor=3 */
 struct psp_firmware_header_v1_3 {
 	struct psp_firmware_header_v1_1 v1_1;
-	uint32_t spl_header_version;
-	uint32_t spl_offset_bytes;
-	uint32_t spl_size_bytes;
-	uint32_t rl_header_version;
-	uint32_t rl_offset_bytes;
-	uint32_t rl_size_bytes;
+	struct psp_fw_bin_desc spl;
+	struct psp_fw_bin_desc rl;
+	struct psp_fw_bin_desc sys_drv_aux;
+	struct psp_fw_bin_desc sos_aux;
 };
 
 /* version_major=1, version_minor=0 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index ea6f99be070b..f4489773715e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -94,6 +94,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 		struct amdgpu_iv_entry *entry)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
 	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
 	if (adev->umc.ras_funcs &&
@@ -131,6 +132,9 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 			amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
 						err_data->err_addr_cnt);
 			amdgpu_ras_save_bad_pages(adev);
+
+			if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->send_hbm_bad_pages_num)
+				adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.num_recs);
 		}
 
 		amdgpu_ras_reset_gpu(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index bbcccf53080d..e5a75fb788dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -22,6 +22,11 @@
 #define __AMDGPU_UMC_H__
 
 /*
+ * (addr / 256) * 4096, the higher 26 bits in ErrorAddr
+ * is the index of 4KB block
+ */
+#define ADDR_OF_4KB_BLOCK(addr)			(((addr) & ~0xffULL) << 4)
+/*
  * (addr / 256) * 8192, the higher 26 bits in ErrorAddr
  * is the index of 8KB block
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 647d2c31e8bd..6780df0fb265 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -288,6 +288,29 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	return 0;
 }
 
+bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
+{
+	bool ret = false;
+
+	int major;
+	int minor;
+	int revision;
+
+	/* if cannot find IP data, then this VCN does not exist */
+	if (amdgpu_discovery_get_vcn_version(adev, vcn_instance, &major, &minor, &revision) != 0)
+		return true;
+
+	if ((type == VCN_ENCODE_RING) && (revision & VCN_BLOCK_ENCODE_DISABLE_MASK)) {
+		ret = true;
+	} else if ((type == VCN_DECODE_RING) && (revision & VCN_BLOCK_DECODE_DISABLE_MASK)) {
+		ret = true;
+	} else if ((type == VCN_UNIFIED_RING) && (revision & VCN_BLOCK_QUEUE_DISABLE_MASK)) {
+		ret = true;
+	}
+
+	return ret;
+}
+
 int amdgpu_vcn_suspend(struct amdgpu_device *adev)
 {
 	unsigned size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index bc76cab67697..d74c62b49795 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -280,6 +280,16 @@ struct amdgpu_vcn_decode_buffer {
 	uint32_t pad[30];
 };
 
+#define VCN_BLOCK_ENCODE_DISABLE_MASK 0x80
+#define VCN_BLOCK_DECODE_DISABLE_MASK 0x40
+#define VCN_BLOCK_QUEUE_DISABLE_MASK 0xC0
+
+enum vcn_ring_type {
+	VCN_ENCODE_RING,
+	VCN_DECODE_RING,
+	VCN_UNIFIED_RING,
+};
+
 int amdgpu_vcn_sw_init(struct amdgpu_device *adev);
 int amdgpu_vcn_sw_fini(struct amdgpu_device *adev);
 int amdgpu_vcn_suspend(struct amdgpu_device *adev);
@@ -287,6 +297,9 @@ int amdgpu_vcn_resume(struct amdgpu_device *adev);
 void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring);
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring);
 
+bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev,
+				enum vcn_ring_type type, uint32_t vcn_instance);
+
 int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring);
 int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 int amdgpu_vcn_dec_sw_ring_test_ring(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 18246b5b6ee3..078c068937fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -332,7 +332,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 	base->next = bo->vm_bo;
 	bo->vm_bo = base;
 
-	if (bo->tbo.base.resv != vm->root.base.bo->tbo.base.resv)
+	if (bo->tbo.base.resv != vm->root.bo->tbo.base.resv)
 		return;
 
 	vm->bulk_moveable = false;
@@ -361,14 +361,14 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
  * Helper to get the parent entry for the child page table. NULL if we are at
  * the root page directory.
  */
-static struct amdgpu_vm_pt *amdgpu_vm_pt_parent(struct amdgpu_vm_pt *pt)
+static struct amdgpu_vm_bo_base *amdgpu_vm_pt_parent(struct amdgpu_vm_bo_base *pt)
 {
-	struct amdgpu_bo *parent = pt->base.bo->parent;
+	struct amdgpu_bo *parent = pt->bo->parent;
 
 	if (!parent)
 		return NULL;
 
-	return container_of(parent->vm_bo, struct amdgpu_vm_pt, base);
+	return parent->vm_bo;
 }
 
 /*
@@ -376,8 +376,8 @@ static struct amdgpu_vm_pt *amdgpu_vm_pt_parent(struct amdgpu_vm_pt *pt)
  */
 struct amdgpu_vm_pt_cursor {
 	uint64_t pfn;
-	struct amdgpu_vm_pt *parent;
-	struct amdgpu_vm_pt *entry;
+	struct amdgpu_vm_bo_base *parent;
+	struct amdgpu_vm_bo_base *entry;
 	unsigned level;
 };
 
@@ -416,17 +416,17 @@ static bool amdgpu_vm_pt_descendant(struct amdgpu_device *adev,
 {
 	unsigned mask, shift, idx;
 
-	if (!cursor->entry->entries)
+	if ((cursor->level == AMDGPU_VM_PTB) || !cursor->entry ||
+	    !cursor->entry->bo)
 		return false;
 
-	BUG_ON(!cursor->entry->base.bo);
 	mask = amdgpu_vm_entries_mask(adev, cursor->level);
 	shift = amdgpu_vm_level_shift(adev, cursor->level);
 
 	++cursor->level;
 	idx = (cursor->pfn >> shift) & mask;
 	cursor->parent = cursor->entry;
-	cursor->entry = &cursor->entry->entries[idx];
+	cursor->entry = &to_amdgpu_bo_vm(cursor->entry->bo)->entries[idx];
 	return true;
 }
 
@@ -453,7 +453,7 @@ static bool amdgpu_vm_pt_sibling(struct amdgpu_device *adev,
 	shift = amdgpu_vm_level_shift(adev, cursor->level - 1);
 	num_entries = amdgpu_vm_num_entries(adev, cursor->level - 1);
 
-	if (cursor->entry == &cursor->parent->entries[num_entries - 1])
+	if (cursor->entry == &to_amdgpu_bo_vm(cursor->parent->bo)->entries[num_entries - 1])
 		return false;
 
 	cursor->pfn += 1ULL << shift;
@@ -539,7 +539,7 @@ static void amdgpu_vm_pt_first_dfs(struct amdgpu_device *adev,
  * True when the search should continue, false otherwise.
  */
 static bool amdgpu_vm_pt_continue_dfs(struct amdgpu_vm_pt_cursor *start,
-				      struct amdgpu_vm_pt *entry)
+				      struct amdgpu_vm_bo_base *entry)
 {
 	return entry && (!start || entry != start->entry);
 }
@@ -590,7 +590,7 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 			 struct amdgpu_bo_list_entry *entry)
 {
 	entry->priority = 0;
-	entry->tv.bo = &vm->root.base.bo->tbo;
+	entry->tv.bo = &vm->root.bo->tbo;
 	/* Two for VM updates, one for TTM and one for the CS job */
 	entry->tv.num_shared = 4;
 	entry->user_pages = NULL;
@@ -622,7 +622,7 @@ void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo)
 	for (bo_base = abo->vm_bo; bo_base; bo_base = bo_base->next) {
 		struct amdgpu_vm *vm = bo_base->vm;
 
-		if (abo->tbo.base.resv == vm->root.base.bo->tbo.base.resv)
+		if (abo->tbo.base.resv == vm->root.bo->tbo.base.resv)
 			vm->bulk_moveable = false;
 	}
 
@@ -781,11 +781,11 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 		entries -= ats_entries;
 
 	} else {
-		struct amdgpu_vm_pt *pt;
+		struct amdgpu_vm_bo_base *pt;
 
-		pt = container_of(ancestor->vm_bo, struct amdgpu_vm_pt, base);
+		pt = ancestor->vm_bo;
 		ats_entries = amdgpu_vm_num_ats_entries(adev);
-		if ((pt - vm->root.entries) >= ats_entries) {
+		if ((pt - to_amdgpu_bo_vm(vm->root.bo)->entries) >= ats_entries) {
 			ats_entries = 0;
 		} else {
 			ats_entries = entries;
@@ -902,8 +902,8 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev,
 
 	bp.type = ttm_bo_type_kernel;
 	bp.no_wait_gpu = immediate;
-	if (vm->root.base.bo)
-		bp.resv = vm->root.base.bo->tbo.base.resv;
+	if (vm->root.bo)
+		bp.resv = vm->root.bo->tbo.base.resv;
 
 	r = amdgpu_bo_create_vm(adev, &bp, vmbo);
 	if (r)
@@ -938,7 +938,7 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev,
 	}
 
 	(*vmbo)->shadow->parent = amdgpu_bo_ref(bo);
-	amdgpu_bo_add_to_shadow_list((*vmbo)->shadow);
+	amdgpu_bo_add_to_shadow_list(*vmbo);
 
 	return 0;
 }
@@ -962,19 +962,13 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 			       struct amdgpu_vm_pt_cursor *cursor,
 			       bool immediate)
 {
-	struct amdgpu_vm_pt *entry = cursor->entry;
+	struct amdgpu_vm_bo_base *entry = cursor->entry;
 	struct amdgpu_bo *pt_bo;
 	struct amdgpu_bo_vm *pt;
 	int r;
 
-	if (entry->base.bo) {
-		if (cursor->level < AMDGPU_VM_PTB)
-			entry->entries =
-				to_amdgpu_bo_vm(entry->base.bo)->entries;
-		else
-			entry->entries = NULL;
+	if (entry->bo)
 		return 0;
-	}
 
 	r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt);
 	if (r)
@@ -984,13 +978,8 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 	 * freeing them up in the wrong order.
 	 */
 	pt_bo = &pt->bo;
-	pt_bo->parent = amdgpu_bo_ref(cursor->parent->base.bo);
-	amdgpu_vm_bo_base_init(&entry->base, vm, pt_bo);
-	if (cursor->level < AMDGPU_VM_PTB)
-		entry->entries = pt->entries;
-	else
-		entry->entries = NULL;
-
+	pt_bo->parent = amdgpu_bo_ref(cursor->parent->bo);
+	amdgpu_vm_bo_base_init(entry, vm, pt_bo);
 	r = amdgpu_vm_clear_bo(adev, vm, pt, immediate);
 	if (r)
 		goto error_free_pt;
@@ -1008,18 +997,17 @@ error_free_pt:
  *
  * @entry: PDE to free
  */
-static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry)
+static void amdgpu_vm_free_table(struct amdgpu_vm_bo_base *entry)
 {
 	struct amdgpu_bo *shadow;
 
-	if (entry->base.bo) {
-		shadow = amdgpu_bo_shadowed(entry->base.bo);
-		entry->base.bo->vm_bo = NULL;
-		list_del(&entry->base.vm_status);
-		amdgpu_bo_unref(&shadow);
-		amdgpu_bo_unref(&entry->base.bo);
-	}
-	entry->entries = NULL;
+	if (!entry->bo)
+		return;
+	shadow = amdgpu_bo_shadowed(entry->bo);
+	entry->bo->vm_bo = NULL;
+	list_del(&entry->vm_status);
+	amdgpu_bo_unref(&shadow);
+	amdgpu_bo_unref(&entry->bo);
 }
 
 /**
@@ -1036,7 +1024,7 @@ static void amdgpu_vm_free_pts(struct amdgpu_device *adev,
 			       struct amdgpu_vm_pt_cursor *start)
 {
 	struct amdgpu_vm_pt_cursor cursor;
-	struct amdgpu_vm_pt *entry;
+	struct amdgpu_vm_bo_base *entry;
 
 	vm->bulk_moveable = false;
 
@@ -1304,10 +1292,10 @@ uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr)
  */
 static int amdgpu_vm_update_pde(struct amdgpu_vm_update_params *params,
 				struct amdgpu_vm *vm,
-				struct amdgpu_vm_pt *entry)
+				struct amdgpu_vm_bo_base *entry)
 {
-	struct amdgpu_vm_pt *parent = amdgpu_vm_pt_parent(entry);
-	struct amdgpu_bo *bo = parent->base.bo, *pbo;
+	struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry);
+	struct amdgpu_bo *bo = parent->bo, *pbo;
 	uint64_t pde, pt, flags;
 	unsigned level;
 
@@ -1315,8 +1303,8 @@ static int amdgpu_vm_update_pde(struct amdgpu_vm_update_params *params,
 		pbo = pbo->parent;
 
 	level += params->adev->vm_manager.root_level;
-	amdgpu_gmc_get_pde_for_bo(entry->base.bo, level, &pt, &flags);
-	pde = (entry - parent->entries) * 8;
+	amdgpu_gmc_get_pde_for_bo(entry->bo, level, &pt, &flags);
+	pde = (entry - to_amdgpu_bo_vm(parent->bo)->entries) * 8;
 	return vm->update_funcs->update(params, to_amdgpu_bo_vm(bo), pde, pt,
 					1, 0, flags);
 }
@@ -1333,11 +1321,11 @@ static void amdgpu_vm_invalidate_pds(struct amdgpu_device *adev,
 				     struct amdgpu_vm *vm)
 {
 	struct amdgpu_vm_pt_cursor cursor;
-	struct amdgpu_vm_pt *entry;
+	struct amdgpu_vm_bo_base *entry;
 
 	for_each_amdgpu_vm_pt_dfs_safe(adev, vm, NULL, cursor, entry)
-		if (entry->base.bo && !entry->base.moved)
-			amdgpu_vm_bo_relocated(&entry->base);
+		if (entry->bo && !entry->moved)
+			amdgpu_vm_bo_relocated(entry);
 }
 
 /**
@@ -1371,11 +1359,12 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 		return r;
 
 	while (!list_empty(&vm->relocated)) {
-		struct amdgpu_vm_pt *entry;
+		struct amdgpu_vm_bo_base *entry;
 
-		entry = list_first_entry(&vm->relocated, struct amdgpu_vm_pt,
-					 base.vm_status);
-		amdgpu_vm_bo_idle(&entry->base);
+		entry = list_first_entry(&vm->relocated,
+					 struct amdgpu_vm_bo_base,
+					 vm_status);
+		amdgpu_vm_bo_idle(entry);
 
 		r = amdgpu_vm_update_pde(&params, vm, entry);
 		if (r)
@@ -1555,7 +1544,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 			continue;
 		}
 
-		pt = cursor.entry->base.bo;
+		pt = cursor.entry->bo;
 		if (!pt) {
 			/* We need all PDs and PTs for mapping something, */
 			if (flags & AMDGPU_PTE_VALID)
@@ -1567,7 +1556,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 			if (!amdgpu_vm_pt_ancestor(&cursor))
 				return -EINVAL;
 
-			pt = cursor.entry->base.bo;
+			pt = cursor.entry->bo;
 			shift = parent_shift;
 			frag_end = max(frag_end, ALIGN(frag_start + 1,
 				   1ULL << shift));
@@ -1622,7 +1611,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 			 */
 			while (cursor.pfn < frag_start) {
 				/* Make sure previous mapping is freed */
-				if (cursor.entry->base.bo) {
+				if (cursor.entry->bo) {
 					params->table_freed = true;
 					amdgpu_vm_free_pts(adev, params->vm, &cursor);
 				}
@@ -1704,7 +1693,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (!unlocked && !dma_fence_is_signaled(vm->last_unlocked)) {
 		struct dma_fence *tmp = dma_fence_get_stub();
 
-		amdgpu_bo_fence(vm->root.base.bo, vm->last_unlocked, true);
+		amdgpu_bo_fence(vm->root.bo, vm->last_unlocked, true);
 		swap(vm->last_unlocked, tmp);
 		dma_fence_put(tmp);
 	}
@@ -1769,7 +1758,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	r = vm->update_funcs->commit(&params, fence);
 
 	if (table_freed)
-		*table_freed = *table_freed || params.table_freed;
+		*table_freed = params.table_freed;
 
 error_unlock:
 	amdgpu_vm_eviction_unlock(vm);
@@ -1827,7 +1816,6 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
  * @adev: amdgpu_device pointer
  * @bo_va: requested BO and VM object
  * @clear: if true clear the entries
- * @table_freed: return true if page table is freed
  *
  * Fill in the page table entries for @bo_va.
  *
@@ -1835,7 +1823,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem,
  * 0 for success, -EINVAL for failure.
  */
 int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
-			bool clear, bool *table_freed)
+			bool clear)
 {
 	struct amdgpu_bo *bo = bo_va->base.bo;
 	struct amdgpu_vm *vm = bo_va->base.vm;
@@ -1850,7 +1838,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 
 	if (clear || !bo) {
 		mem = NULL;
-		resv = vm->root.base.bo->tbo.base.resv;
+		resv = vm->root.bo->tbo.base.resv;
 	} else {
 		struct drm_gem_object *obj = &bo->tbo.base;
 
@@ -1881,7 +1869,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 	}
 
 	if (clear || (bo && bo->tbo.base.resv ==
-		      vm->root.base.bo->tbo.base.resv))
+		      vm->root.bo->tbo.base.resv))
 		last_update = &vm->last_update;
 	else
 		last_update = &bo_va->last_pt_update;
@@ -1914,7 +1902,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 						resv, mapping->start,
 						mapping->last, update_flags,
 						mapping->offset, mem,
-						pages_addr, last_update, table_freed);
+						pages_addr, last_update, NULL);
 		if (r)
 			return r;
 	}
@@ -1923,7 +1911,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 	 * the evicted list so that it gets validated again on the
 	 * next command submission.
 	 */
-	if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) {
+	if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv) {
 		uint32_t mem_type = bo->tbo.resource->mem_type;
 
 		if (!(bo->preferred_domains &
@@ -2060,7 +2048,7 @@ static void amdgpu_vm_free_mapping(struct amdgpu_device *adev,
  */
 static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
-	struct dma_resv *resv = vm->root.base.bo->tbo.base.resv;
+	struct dma_resv *resv = vm->root.bo->tbo.base.resv;
 	struct dma_fence *excl, **shared;
 	unsigned i, shared_count;
 	int r;
@@ -2106,7 +2094,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm,
 			  struct dma_fence **fence)
 {
-	struct dma_resv *resv = vm->root.base.bo->tbo.base.resv;
+	struct dma_resv *resv = vm->root.bo->tbo.base.resv;
 	struct amdgpu_bo_va_mapping *mapping;
 	uint64_t init_pte_value = 0;
 	struct dma_fence *f = NULL;
@@ -2166,7 +2154,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 
 	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
 		/* Per VM BOs never need to bo cleared in the page tables */
-		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
 	}
@@ -2185,7 +2173,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		else
 			clear = true;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL);
+		r = amdgpu_vm_bo_update(adev, bo_va, clear);
 		if (r)
 			return r;
 
@@ -2265,7 +2253,7 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
 	if (mapping->flags & AMDGPU_PTE_PRT)
 		amdgpu_vm_prt_get(adev);
 
-	if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv &&
+	if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
 	    !bo_va->base.moved) {
 		list_move(&bo_va->base.vm_status, &vm->moved);
 	}
@@ -2627,7 +2615,7 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 	struct amdgpu_vm_bo_base **base;
 
 	if (bo) {
-		if (bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv)
+		if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv)
 			vm->bulk_moveable = false;
 
 		for (base = &bo_va->base.bo->vm_bo; *base;
@@ -2721,7 +2709,7 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
 		struct amdgpu_vm *vm = bo_base->vm;
 
-		if (evicted && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) {
+		if (evicted && bo->tbo.base.resv == vm->root.bo->tbo.base.resv) {
 			amdgpu_vm_bo_evicted(bo_base);
 			continue;
 		}
@@ -2732,7 +2720,7 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 
 		if (bo->tbo.type == ttm_bo_type_kernel)
 			amdgpu_vm_bo_relocated(bo_base);
-		else if (bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv)
+		else if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv)
 			amdgpu_vm_bo_moved(bo_base);
 		else
 			amdgpu_vm_bo_invalidated(bo_base);
@@ -2862,7 +2850,7 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size,
  */
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
 {
-	timeout = dma_resv_wait_timeout(vm->root.base.bo->tbo.base.resv, true,
+	timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, true,
 					true, timeout);
 	if (timeout <= 0)
 		return timeout;
@@ -2948,13 +2936,13 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid)
 	if (r)
 		goto error_unreserve;
 
-	amdgpu_vm_bo_base_init(&vm->root.base, vm, root_bo);
+	amdgpu_vm_bo_base_init(&vm->root, vm, root_bo);
 
 	r = amdgpu_vm_clear_bo(adev, vm, root, false);
 	if (r)
 		goto error_unreserve;
 
-	amdgpu_bo_unreserve(vm->root.base.bo);
+	amdgpu_bo_unreserve(vm->root.bo);
 
 	if (pasid) {
 		unsigned long flags;
@@ -2974,12 +2962,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid)
 	return 0;
 
 error_unreserve:
-	amdgpu_bo_unreserve(vm->root.base.bo);
+	amdgpu_bo_unreserve(vm->root.bo);
 
 error_free_root:
 	amdgpu_bo_unref(&root->shadow);
 	amdgpu_bo_unref(&root_bo);
-	vm->root.base.bo = NULL;
+	vm->root.bo = NULL;
 
 error_free_delayed:
 	dma_fence_put(vm->last_unlocked);
@@ -3005,17 +2993,14 @@ error_free_immediate:
  *	0 if this VM is clean
  */
 static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
-	struct amdgpu_vm *vm)
+					  struct amdgpu_vm *vm)
 {
 	enum amdgpu_vm_level root = adev->vm_manager.root_level;
 	unsigned int entries = amdgpu_vm_num_entries(adev, root);
 	unsigned int i = 0;
 
-	if (!(vm->root.entries))
-		return 0;
-
 	for (i = 0; i < entries; i++) {
-		if (vm->root.entries[i].base.bo)
+		if (to_amdgpu_bo_vm(vm->root.bo)->entries[i].bo)
 			return -EINVAL;
 	}
 
@@ -3049,7 +3034,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
 	int r;
 
-	r = amdgpu_bo_reserve(vm->root.base.bo, true);
+	r = amdgpu_bo_reserve(vm->root.bo, true);
 	if (r)
 		return r;
 
@@ -3077,7 +3062,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (pte_support_ats != vm->pte_support_ats) {
 		vm->pte_support_ats = pte_support_ats;
 		r = amdgpu_vm_clear_bo(adev, vm,
-				       to_amdgpu_bo_vm(vm->root.base.bo),
+				       to_amdgpu_bo_vm(vm->root.bo),
 				       false);
 		if (r)
 			goto free_idr;
@@ -3094,7 +3079,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	if (vm->use_cpu_for_update) {
 		/* Sync with last SDMA update/clear before switching to CPU */
-		r = amdgpu_bo_sync_wait(vm->root.base.bo,
+		r = amdgpu_bo_sync_wait(vm->root.bo,
 					AMDGPU_FENCE_OWNER_UNDEFINED, true);
 		if (r)
 			goto free_idr;
@@ -3122,7 +3107,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	/* Free the shadow bo for compute VM */
-	amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.base.bo)->shadow);
+	amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow);
 
 	if (pasid)
 		vm->pasid = pasid;
@@ -3138,7 +3123,7 @@ free_idr:
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 unreserve_bo:
-	amdgpu_bo_unreserve(vm->root.base.bo);
+	amdgpu_bo_unreserve(vm->root.bo);
 	return r;
 }
 
@@ -3181,7 +3166,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
 
-	root = amdgpu_bo_ref(vm->root.base.bo);
+	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
 	if (vm->pasid) {
 		unsigned long flags;
@@ -3208,7 +3193,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	amdgpu_vm_free_pts(adev, vm, NULL);
 	amdgpu_bo_unreserve(root);
 	amdgpu_bo_unref(&root);
-	WARN_ON(vm->root.base.bo);
+	WARN_ON(vm->root.bo);
 
 	drm_sched_entity_destroy(&vm->immediate);
 	drm_sched_entity_destroy(&vm->delayed);
@@ -3325,7 +3310,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		/* Wait vm idle to make sure the vmid set in SPM_VMID is
 		 * not referenced anymore.
 		 */
-		r = amdgpu_bo_reserve(fpriv->vm.root.base.bo, true);
+		r = amdgpu_bo_reserve(fpriv->vm.root.bo, true);
 		if (r)
 			return r;
 
@@ -3333,7 +3318,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		if (r < 0)
 			return r;
 
-		amdgpu_bo_unreserve(fpriv->vm.root.base.bo);
+		amdgpu_bo_unreserve(fpriv->vm.root.bo);
 		amdgpu_vmid_free_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB_0);
 		break;
 	default:
@@ -3399,19 +3384,20 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 {
 	bool is_compute_context = false;
 	struct amdgpu_bo *root;
+	unsigned long irqflags;
 	uint64_t value, flags;
 	struct amdgpu_vm *vm;
 	int r;
 
-	spin_lock(&adev->vm_manager.pasid_lock);
+	spin_lock_irqsave(&adev->vm_manager.pasid_lock, irqflags);
 	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
 	if (vm) {
-		root = amdgpu_bo_ref(vm->root.base.bo);
+		root = amdgpu_bo_ref(vm->root.bo);
 		is_compute_context = vm->is_compute_context;
 	} else {
 		root = NULL;
 	}
-	spin_unlock(&adev->vm_manager.pasid_lock);
+	spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, irqflags);
 
 	if (!root)
 		return false;
@@ -3429,11 +3415,11 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 		goto error_unref;
 
 	/* Double check that the VM still exists */
-	spin_lock(&adev->vm_manager.pasid_lock);
+	spin_lock_irqsave(&adev->vm_manager.pasid_lock, irqflags);
 	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
-	if (vm && vm->root.base.bo != root)
+	if (vm && vm->root.bo != root)
 		vm = NULL;
-	spin_unlock(&adev->vm_manager.pasid_lock);
+	spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, irqflags);
 	if (!vm)
 		goto error_unlock;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 1f089da1e615..f8fa653d4da7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -152,13 +152,6 @@ struct amdgpu_vm_bo_base {
 	bool				moved;
 };
 
-struct amdgpu_vm_pt {
-	struct amdgpu_vm_bo_base	base;
-
-	/* array of page tables, one for each directory entry */
-	struct amdgpu_vm_pt		*entries;
-};
-
 /* provided by hw blocks that can write ptes, e.g., sdma */
 struct amdgpu_vm_pte_funcs {
 	/* number of dw to reserve per operation */
@@ -284,7 +277,7 @@ struct amdgpu_vm {
 	struct list_head        done;
 
 	/* contains the page directory */
-	struct amdgpu_vm_pt     root;
+	struct amdgpu_vm_bo_base     root;
 	struct dma_fence	*last_update;
 
 	/* Scheduler entities for page table updates */
@@ -413,7 +406,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 				struct dma_fence **fence, bool *free_table);
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
-			bool clear, bool *table_freed);
+			bool clear);
 bool amdgpu_vm_evictable(struct amdgpu_bo *bo);
 void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 			     struct amdgpu_bo *bo, bool evicted);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 422958152c2b..dbb551762805 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -112,7 +112,7 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 		swap(p->vm->last_unlocked, f);
 		dma_fence_put(tmp);
 	} else {
-		amdgpu_bo_fence(p->vm->root.base.bo, f, true);
+		amdgpu_bo_fence(p->vm->root.bo, f, true);
 	}
 
 	if (fence && !p->immediate)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 436ec246a7da..2fd77c36a1ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -463,6 +463,11 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	if (i == 1)
 		node->base.placement |= TTM_PL_FLAG_CONTIGUOUS;
 
+	if (adev->gmc.xgmi.connected_to_cpu)
+		node->base.bus.caching = ttm_cached;
+	else
+		node->base.bus.caching = ttm_write_combined;
+
 	atomic64_add(vis_usage, &mgr->vis_usage);
 	*res = &node->base;
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
index 5b90efd6f6d0..3ac505d954c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
@@ -36,9 +36,12 @@ athub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
+		return;
+
 	def = data = RREG32_SOC15(ATHUB, 0, mmATHUB_MISC_CNTL);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
+	if (enable)
 		data |= ATHUB_MISC_CNTL__CG_ENABLE_MASK;
 	else
 		data &= ~ATHUB_MISC_CNTL__CG_ENABLE_MASK;
@@ -53,10 +56,13 @@ athub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
+	if (!((adev->cg_flags & AMD_CG_SUPPORT_MC_LS) &&
+	       (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS)))
+		return;
+
 	def = data = RREG32_SOC15(ATHUB, 0, mmATHUB_MISC_CNTL);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) &&
-	    (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
+	if (enable)
 		data |= ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
 	else
 		data &= ~ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index 33324427b555..7e0d8c092c7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -766,7 +766,7 @@ static const struct amdgpu_irq_src_funcs dce_virtual_crtc_irq_funcs = {
 
 static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VBLANK6 + 1;
+	adev->crtc_irq.num_types = adev->mode_info.num_crtc;
 	adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 2d56b60bc058..a64b2c706090 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3300,6 +3300,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000)
 };
@@ -3379,6 +3380,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1_Vangogh, 0xffffffff, 0x00070103),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQG_CONFIG, 0x000017ff, 0x00001000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00400000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
@@ -3445,6 +3447,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_4[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x01030000, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x03a00000, 0x00a00000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG,  0x00000020, 0x00000020)
@@ -5086,47 +5089,44 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 		4 + /* RMI */
 		1); /* SQG */
 
-	if (adev->asic_type == CHIP_NAVI10 ||
-	    adev->asic_type == CHIP_NAVI14 ||
-	    adev->asic_type == CHIP_NAVI12) {
-		mutex_lock(&adev->grbm_idx_mutex);
-		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
-			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-				gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff);
-				wgp_active_bitmap = gfx_v10_0_get_wgp_active_bitmap_per_sh(adev);
-				/*
-				 * Set corresponding TCP bits for the inactive WGPs in
-				 * GCRD_SA_TARGETS_DISABLE
-				 */
-				gcrd_targets_disable_tcp = 0;
-				/* Set TCP & SQC bits in UTCL1_UTCL0_INVREQ_DISABLE */
-				utcl_invreq_disable = 0;
-
-				for (k = 0; k < max_wgp_per_sh; k++) {
-					if (!(wgp_active_bitmap & (1 << k))) {
-						gcrd_targets_disable_tcp |= 3 << (2 * k);
-						utcl_invreq_disable |= (3 << (2 * k)) |
-							(3 << (2 * (max_wgp_per_sh + k)));
-					}
+	mutex_lock(&adev->grbm_idx_mutex);
+	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff);
+			wgp_active_bitmap = gfx_v10_0_get_wgp_active_bitmap_per_sh(adev);
+			/*
+			 * Set corresponding TCP bits for the inactive WGPs in
+			 * GCRD_SA_TARGETS_DISABLE
+			 */
+			gcrd_targets_disable_tcp = 0;
+			/* Set TCP & SQC bits in UTCL1_UTCL0_INVREQ_DISABLE */
+			utcl_invreq_disable = 0;
+
+			for (k = 0; k < max_wgp_per_sh; k++) {
+				if (!(wgp_active_bitmap & (1 << k))) {
+					gcrd_targets_disable_tcp |= 3 << (2 * k);
+					gcrd_targets_disable_tcp |= 1 << (k + (max_wgp_per_sh * 2));
+					utcl_invreq_disable |= (3 << (2 * k)) |
+						(3 << (2 * (max_wgp_per_sh + k)));
 				}
-
-				tmp = RREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE);
-				/* only override TCP & SQC bits */
-				tmp &= 0xffffffff << (4 * max_wgp_per_sh);
-				tmp |= (utcl_invreq_disable & utcl_invreq_disable_mask);
-				WREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE, tmp);
-
-				tmp = RREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE);
-				/* only override TCP bits */
-				tmp &= 0xffffffff << (2 * max_wgp_per_sh);
-				tmp |= (gcrd_targets_disable_tcp & gcrd_targets_disable_mask);
-				WREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE, tmp);
 			}
-		}
 
-		gfx_v10_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-		mutex_unlock(&adev->grbm_idx_mutex);
+			tmp = RREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE);
+			/* only override TCP & SQC bits */
+			tmp &= (0xffffffffU << (4 * max_wgp_per_sh));
+			tmp |= (utcl_invreq_disable & utcl_invreq_disable_mask);
+			WREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE, tmp);
+
+			tmp = RREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE);
+			/* only override TCP & SQC bits */
+			tmp &= (0xffffffffU << (3 * max_wgp_per_sh));
+			tmp |= (gcrd_targets_disable_tcp & gcrd_targets_disable_mask);
+			WREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE, tmp);
+		}
 	}
+
+	gfx_v10_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
 static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
@@ -7404,7 +7404,10 @@ static int gfx_v10_0_hw_init(void *handle)
 	 * init golden registers and rlc resume may override some registers,
 	 * reconfig them here
 	 */
-	gfx_v10_0_tcp_harvest(adev);
+	if (adev->asic_type == CHIP_NAVI10 ||
+	    adev->asic_type == CHIP_NAVI14 ||
+	    adev->asic_type == CHIP_NAVI12)
+		gfx_v10_0_tcp_harvest(adev);
 
 	r = gfx_v10_0_cp_resume(adev);
 	if (r)
@@ -7777,6 +7780,9 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t data, def;
 
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)))
+		return;
+
 	/* It is disabled by HW by default */
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 0 - Disable some blocks' MGCG */
@@ -7791,6 +7797,7 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 			  RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK |
+			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK);
 
 		if (def != data)
@@ -7813,13 +7820,15 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 					WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data);
 			}
 		}
-	} else {
+	} else if (!enable || !(adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 1 - MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		data |= (RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
-			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
+			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK |
+			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK |
+			 RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK);
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
@@ -7845,22 +7854,34 @@ static void gfx_v10_0_update_3d_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t data, def;
 
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS)))
+		return;
+
 	/* Enable 3D CGCG/CGLS */
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)) {
+	if (enable) {
 		/* write cmd to clear cgcg/cgls ov */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
+
 		/* unset CGCG override */
-		data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK;
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK;
+
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
+
 		/* enable 3Dcgcg FSM(0x0000363f) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
-		data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
-			RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+		data = 0;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+				RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
 				RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK;
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data);
 
@@ -7873,9 +7894,14 @@ static void gfx_v10_0_update_3d_clock_gating(struct amdgpu_device *adev,
 	} else {
 		/* Disable CGCG/CGLS */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
+
 		/* disable cgcg, cgls should be disabled */
-		data &= ~(RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK |
-			  RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK);
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data &= ~RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
+			data &= ~RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK;
+
 		/* disable cgcg and cgls in FSM */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data);
@@ -7887,25 +7913,35 @@ static void gfx_v10_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) {
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS)))
+		return;
+
+	if (enable) {
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
+
 		/* unset CGCG override */
-		data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK;
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK;
-		else
-			data |= RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK;
+
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
 		/* enable cgcg FSM(0x0000363F) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
-		data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
-			RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
+		data = 0;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)
+			data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+				RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
 				RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK;
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data);
 
@@ -7917,8 +7953,14 @@ static void gfx_v10_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 			WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_CNTL, data);
 	} else {
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
+
 		/* reset CGCG/CGLS bits */
-		data &= ~(RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK | RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK);
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)
+			data &= ~RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
+			data &= ~RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK;
+
 		/* disable cgcg and cgls in FSM */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data);
@@ -7930,7 +7972,10 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_FGCG)) {
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_GFX_FGCG))
+		return;
+
+	if (enable) {
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		/* unset FGCG override */
 		data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK;
@@ -7961,6 +8006,97 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev,
 	}
 }
 
+static void gfx_v10_0_apply_medium_grain_clock_gating_workaround(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+	uint32_t reg_idx = 0;
+	uint32_t i;
+
+	const uint32_t tcp_ctrl_regs[] = {
+		mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP12_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP12_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP12_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP12_CU1_TCP_CTRL_REG
+	};
+
+	const uint32_t tcp_ctrl_regs_nv12[] = {
+		mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG,
+	};
+
+	const uint32_t sm_ctlr_regs[] = {
+		mmCGTS_SA0_QUAD0_SM_CTRL_REG,
+		mmCGTS_SA0_QUAD1_SM_CTRL_REG,
+		mmCGTS_SA1_QUAD0_SM_CTRL_REG,
+		mmCGTS_SA1_QUAD1_SM_CTRL_REG
+	};
+
+	if (adev->asic_type == CHIP_NAVI12) {
+		for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs_nv12); i++) {
+			reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] +
+				  tcp_ctrl_regs_nv12[i];
+			reg_data = RREG32(reg_idx);
+			reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK;
+			WREG32(reg_idx, reg_data);
+		}
+	} else {
+		for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs); i++) {
+			reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] +
+				  tcp_ctrl_regs[i];
+			reg_data = RREG32(reg_idx);
+			reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK;
+			WREG32(reg_idx, reg_data);
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(sm_ctlr_regs); i++) {
+		reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_QUAD0_SM_CTRL_REG_BASE_IDX] +
+			  sm_ctlr_regs[i];
+		reg_data = RREG32(reg_idx);
+		reg_data &= ~CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE_MASK;
+		reg_data |= 2 << CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE__SHIFT;
+		WREG32(reg_idx, reg_data);
+	}
+}
+
 static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 					    bool enable)
 {
@@ -7977,6 +8113,10 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  CGCG + CGLS === */
 		gfx_v10_0_update_coarse_grain_clock_gating(adev, enable);
+
+		if ((adev->asic_type >= CHIP_NAVI10) &&
+		     (adev->asic_type <= CHIP_NAVI12))
+			gfx_v10_0_apply_medium_grain_clock_gating_workaround(adev);
 	} else {
 		/* CGCG/CGLS should be disabled before MGCG/MGLS
 		 * ===  CGCG + CGLS ===
@@ -9324,17 +9464,22 @@ static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(struct amdgpu_device *
 
 static u32 gfx_v10_0_get_wgp_active_bitmap_per_sh(struct amdgpu_device *adev)
 {
-	u32 data, wgp_bitmask;
-	data = RREG32_SOC15(GC, 0, mmCC_GC_SHADER_ARRAY_CONFIG);
-	data |= RREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG);
+	u32 disabled_mask =
+		~amdgpu_gfx_create_bitmask(adev->gfx.config.max_cu_per_sh >> 1);
+	u32 efuse_setting = 0;
+	u32 vbios_setting = 0;
+
+	efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SHADER_ARRAY_CONFIG);
+	efuse_setting &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK;
+	efuse_setting >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT;
 
-	data &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK;
-	data >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT;
+	vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG);
+	vbios_setting &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK;
+	vbios_setting >>= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT;
 
-	wgp_bitmask =
-		amdgpu_gfx_create_bitmask(adev->gfx.config.max_cu_per_sh >> 1);
+	disabled_mask |= efuse_setting | vbios_setting;
 
-	return (~data) & wgp_bitmask;
+	return (~disabled_mask);
 }
 
 static u32 gfx_v10_0_get_cu_active_bitmap_per_sh(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
index c0352dcc89be..1769c4cba2ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
@@ -782,11 +782,6 @@ void gfx_v9_4_2_set_power_brake_sequence(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, GC_THROTTLE_CTRL1, PWRBRK_STALL_EN, 1);
 	WREG32_SOC15(GC, 0, regGC_THROTTLE_CTRL1, tmp);
 
-	WREG32_SOC15(GC, 0, regDIDT_IND_INDEX, ixDIDT_SQ_THROTTLE_CTRL);
-	tmp = 0;
-	tmp = REG_SET_FIELD(tmp, DIDT_SQ_THROTTLE_CTRL, PWRBRK_STALL_EN, 1);
-	WREG32_SOC15(GC, 0, regDIDT_IND_DATA, tmp);
-
 	WREG32_SOC15(GC, 0, regGC_CAC_IND_INDEX, ixPWRBRK_STALL_PATTERN_CTRL);
 	tmp = 0;
 	tmp = REG_SET_FIELD(tmp, PWRBRK_STALL_PATTERN_CTRL, PWRBRK_END_STEP, 0x12);
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index 7a15e669b68d..5793977953cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -90,45 +90,56 @@ static void hdp_v5_0_update_mem_power_gating(struct amdgpu_device *adev,
 					 RC_MEM_POWER_SD_EN, 0);
 	WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
 
-	/* only one clock gating mode (LS/DS/SD) can be enabled */
-	if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_LS_EN, enable);
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_LS_EN, enable);
-	} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_DS_EN, enable);
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_DS_EN, enable);
-	} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_SD_EN, enable);
-		/* RC should not use shut down mode, fallback to ds */
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_DS_EN, enable);
-	}
-
-	/* confirmed that IPH_MEM_POWER_CTRL_EN and RC_MEM_POWER_CTRL_EN have to
-	 * be set for SRAM LS/DS/SD */
-	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
-			      AMD_CG_SUPPORT_HDP_SD)) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_CTRL_EN, 1);
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_CTRL_EN, 1);
+	/* Already disabled above. The actions below are for "enabled" only */
+	if (enable) {
+		/* only one clock gating mode (LS/DS/SD) can be enabled */
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_LS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_LS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_DS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_DS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_SD_EN, 1);
+			/* RC should not use shut down mode, fallback to ds  or ls if allowed */
+			if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS)
+				hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+								 HDP_MEM_POWER_CTRL,
+								 RC_MEM_POWER_DS_EN, 1);
+			else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS)
+				hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+								 HDP_MEM_POWER_CTRL,
+								 RC_MEM_POWER_LS_EN, 1);
+		}
+
+		/* confirmed that IPH_MEM_POWER_CTRL_EN and RC_MEM_POWER_CTRL_EN have to
+		 * be set for SRAM LS/DS/SD */
+		if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
+				      AMD_CG_SUPPORT_HDP_SD)) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_CTRL_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_CTRL_EN, 1);
+			WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+		}
 	}
 
-	WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
-
-	/* restore IPH & RC clock override after clock/power mode changing */
-	WREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL, hdp_clk_cntl1);
+	/* disable IPH & RC clock override after clock/power mode changing */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     IPH_MEM_CLK_SOFT_OVERRIDE, 0);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 0);
+	WREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL, hdp_clk_cntl);
 }
 
 static void hdp_v5_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index f7e93bbc4e15..7ded6b2f058e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -568,6 +568,9 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 {
 	uint32_t def, data, def1, data1;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
+		return;
+
 	switch (adev->asic_type) {
 	case CHIP_SIENNA_CICHLID:
 	case CHIP_NAVY_FLOUNDER:
@@ -582,7 +585,7 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 		break;
 	}
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) {
+	if (enable) {
 		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
 
 		data1 &= ~(DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK |
@@ -627,6 +630,9 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
+		return;
+
 	switch (adev->asic_type) {
 	case CHIP_SIENNA_CICHLID:
 	case CHIP_NAVY_FLOUNDER:
@@ -639,7 +645,7 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 		break;
 	}
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
+	if (enable)
 		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
 	else
 		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 3ee481557fc9..ff2307d7ee0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -252,7 +252,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	 * otherwise the mailbox msg will be ruined/reseted by
 	 * the VF FLR.
 	 */
-	if (!down_read_trylock(&adev->reset_sem))
+	if (!down_write_trylock(&adev->reset_sem))
 		return;
 
 	amdgpu_virt_fini_data_exchange(adev);
@@ -268,7 +268,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
 	atomic_set(&adev->in_gpu_reset, 0);
-	up_read(&adev->reset_sem);
+	up_write(&adev->reset_sem);
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_device_should_recover_gpu(adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 48e588d3c409..9f7aac435d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -273,7 +273,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	 * otherwise the mailbox msg will be ruined/reseted by
 	 * the VF FLR.
 	 */
-	if (!down_read_trylock(&adev->reset_sem))
+	if (!down_write_trylock(&adev->reset_sem))
 		return;
 
 	amdgpu_virt_fini_data_exchange(adev);
@@ -289,7 +289,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
 	atomic_set(&adev->in_gpu_reset, 0);
-	up_read(&adev->reset_sem);
+	up_write(&adev->reset_sem);
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_device_should_recover_gpu(adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index 05ddec7ba7e2..7b79eeaa88aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -51,6 +51,8 @@
 #define mmBIF_MMSCH1_DOORBELL_RANGE		0x01d8
 #define mmBIF_MMSCH1_DOORBELL_RANGE_BASE_IDX	2
 
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+
 static void nbio_v2_3_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
@@ -218,8 +220,11 @@ static void nbio_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG))
+		return;
+
 	def = data = RREG32_PCIE(smnCPM_CONTROL);
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG)) {
+	if (enable) {
 		data |= (CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
 			 CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
 			 CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
@@ -244,8 +249,11 @@ static void nbio_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS))
+		return;
+
 	def = data = RREG32_PCIE(smnPCIE_CNTL2);
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
+	if (enable) {
 		data |= (PCIE_CNTL2__SLV_MEM_LS_EN_MASK |
 			 PCIE_CNTL2__MST_MEM_LS_EN_MASK |
 			 PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK);
@@ -463,6 +471,43 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
 }
 
+static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+	uint32_t link_width = 0;
+
+	if (!((adev->asic_type >= CHIP_NAVI10) &&
+	     (adev->asic_type <= CHIP_NAVI12)))
+		return;
+
+	reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL);
+	link_width = (reg_data & PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+
+	/*
+	 * Program PCIE_LC_CNTL6.LC_SPC_MODE_8GT to 0x2 (4 symbols per clock data)
+	 * if link_width is 0x3 (x4)
+	 */
+	if (0x3 == link_width) {
+		reg_data = RREG32_PCIE(smnPCIE_LC_CNTL6);
+		reg_data &= ~PCIE_LC_CNTL6__LC_SPC_MODE_8GT_MASK;
+		reg_data |= (0x2 << PCIE_LC_CNTL6__LC_SPC_MODE_8GT__SHIFT);
+		WREG32_PCIE(smnPCIE_LC_CNTL6, reg_data);
+	}
+}
+
+static void nbio_v2_3_apply_l1_link_width_reconfig_wa(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+
+	if (adev->asic_type != CHIP_NAVI10)
+		return;
+
+	reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL);
+	reg_data |= PCIE_LC_LINK_WIDTH_CNTL__LC_L1_RECONFIG_EN_MASK;
+	WREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL, reg_data);
+}
+
 const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.get_hdp_flush_req_offset = nbio_v2_3_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v2_3_get_hdp_flush_done_offset,
@@ -484,4 +529,6 @@ const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.remap_hdp_registers = nbio_v2_3_remap_hdp_registers,
 	.enable_aspm = nbio_v2_3_enable_aspm,
 	.program_aspm =  nbio_v2_3_program_aspm,
+	.apply_lc_spc_mode_wa = nbio_v2_3_apply_lc_spc_mode_wa,
+	.apply_l1_link_width_reconfig_wa = nbio_v2_3_apply_l1_link_width_reconfig_wa,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 455d0425787c..94d029dbf30d 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -69,20 +69,8 @@ static const struct amd_ip_funcs nv_common_ip_funcs;
 /* Navi */
 static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_encode =
@@ -94,55 +82,13 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode =
 /* Navi1x */
 static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_decode =
@@ -154,62 +100,14 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode =
 /* Sienna Cichlid */
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs sc_video_codecs_decode =
@@ -221,80 +119,20 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode =
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codecs sriov_sc_video_codecs_encode =
@@ -309,6 +147,36 @@ static struct amdgpu_video_codecs sriov_sc_video_codecs_decode =
 	.codec_array = sriov_sc_video_codecs_decode_array,
 };
 
+/* Beige Goby*/
+static const struct amdgpu_video_codec_info bg_video_codecs_decode_array[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+};
+
+static const struct amdgpu_video_codecs bg_video_codecs_decode = {
+	.codec_count = ARRAY_SIZE(bg_video_codecs_decode_array),
+	.codec_array = bg_video_codecs_decode_array,
+};
+
+static const struct amdgpu_video_codecs bg_video_codecs_encode = {
+	.codec_count = 0,
+	.codec_array = NULL,
+};
+
+/* Yellow Carp*/
+static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+};
+
+static const struct amdgpu_video_codecs yc_video_codecs_decode = {
+	.codec_count = ARRAY_SIZE(yc_video_codecs_decode_array),
+	.codec_array = yc_video_codecs_decode_array,
+};
+
 static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 				 const struct amdgpu_video_codecs **codecs)
 {
@@ -329,12 +197,23 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 	case CHIP_NAVY_FLOUNDER:
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_VANGOGH:
-	case CHIP_YELLOW_CARP:
 		if (encode)
 			*codecs = &nv_video_codecs_encode;
 		else
 			*codecs = &sc_video_codecs_decode;
 		return 0;
+	case CHIP_YELLOW_CARP:
+		if (encode)
+			*codecs = &nv_video_codecs_encode;
+		else
+			*codecs = &yc_video_codecs_decode;
+		return 0;
+	case CHIP_BEIGE_GOBY:
+		if (encode)
+			*codecs = &bg_video_codecs_encode;
+		else
+			*codecs = &bg_video_codecs_decode;
+		return 0;
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
@@ -1275,7 +1154,6 @@ static int nv_common_early_init(void *handle)
 		break;
 
 	case CHIP_VANGOGH:
-		adev->apu_flags |= AMD_APU_IS_VANGOGH;
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_GFX_MGLS |
 			AMD_CG_SUPPORT_GFX_CP_LS |
@@ -1358,7 +1236,10 @@ static int nv_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
-		adev->external_rev_id = adev->rev_id + 0x01;
+		if (adev->pdev->device == 0x1681)
+			adev->external_rev_id = adev->rev_id + 0x19;
+		else
+			adev->external_rev_id = adev->rev_id + 0x01;
 		break;
 	default:
 		/* FIXME: not supported yet */
@@ -1411,6 +1292,12 @@ static int nv_common_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (adev->nbio.funcs->apply_lc_spc_mode_wa)
+		adev->nbio.funcs->apply_lc_spc_mode_wa(adev);
+
+	if (adev->nbio.funcs->apply_l1_link_width_reconfig_wa)
+		adev->nbio.funcs->apply_l1_link_width_reconfig_wa(adev);
+
 	/* enable pcie gen2/3 link */
 	nv_pcie_gen3_enable(adev);
 	/* enable aspm */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index f6d3180febc4..dd0dce254901 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -332,11 +332,16 @@ struct psp_gfx_uresp_fwar_db_info
     uint32_t fwar_db_addr_hi;
 };
 
+/* Command-specific response for boot config. */
+struct psp_gfx_uresp_bootcfg {
+	uint32_t boot_cfg;	/* boot config data */
+};
+
 /* Union of command-specific responses for GPCOM ring. */
-union psp_gfx_uresp
-{
-    struct psp_gfx_uresp_reserved reserved;
-    struct psp_gfx_uresp_fwar_db_info fwar_db_info;
+union psp_gfx_uresp {
+	struct psp_gfx_uresp_reserved		reserved;
+	struct psp_gfx_uresp_bootcfg		boot_cfg;
+	struct psp_gfx_uresp_fwar_db_info	fwar_db_info;
 };
 
 /* Structure of GFX Response buffer.
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index fc400d95b83b..bc133db2d538 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -461,6 +461,7 @@ static int psp_v11_0_ring_create(struct psp_context *psp,
 	struct amdgpu_device *adev = psp->adev;
 
 	if (amdgpu_sriov_vf(adev)) {
+		ring->ring_wptr = 0;
 		ret = psp_v11_0_ring_stop(psp, ring_type);
 		if (ret) {
 			DRM_ERROR("psp_v11_0_ring_stop_sriov failed!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index ce7377d2368f..b86dcbabb635 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -227,6 +227,7 @@ static int psp_v3_1_ring_create(struct psp_context *psp,
 	psp_v3_1_reroute_ih(psp);
 
 	if (amdgpu_sriov_vf(adev)) {
+		ring->ring_wptr = 0;
 		ret = psp_v3_1_ring_stop(psp, ring_type);
 		if (ret) {
 			DRM_ERROR("psp_v3_1_ring_stop_sriov failed!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ae5464e2535a..8931000dcd41 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -144,7 +144,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
-	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003e0),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
 };
 
@@ -288,7 +288,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_POWER_CNTL, 0x003fff07, 0x40000051),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
-	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003e0),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x03fbe1fe)
 };
 
@@ -1896,8 +1896,11 @@ static int sdma_v4_0_late_init(void *handle)
 
 	sdma_v4_0_setup_ulv(adev);
 
-	if (adev->sdma.funcs && adev->sdma.funcs->reset_ras_error_count)
-		adev->sdma.funcs->reset_ras_error_count(adev);
+	if (!amdgpu_persistent_edc_harvesting_supported(adev)) {
+		if (adev->sdma.funcs &&
+		    adev->sdma.funcs->reset_ras_error_count)
+			adev->sdma.funcs->reset_ras_error_count(adev);
+	}
 
 	if (adev->sdma.funcs && adev->sdma.funcs->ras_late_init)
 		return adev->sdma.funcs->ras_late_init(adev, &ih_info);
diff --git a/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c b/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c
index e9c474c217ec..b6f1322f908c 100644
--- a/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c
@@ -43,9 +43,12 @@ static void smuio_v11_0_update_rom_clock_gating(struct amdgpu_device *adev, bool
 	if (adev->flags & AMD_IS_APU)
 		return;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG))
+		return;
+
 	def = data = RREG32_SOC15(SMUIO, 0, mmCGTT_ROM_CLK_CTRL0);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG))
+	if (enable)
 		data &= ~(CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE0_MASK |
 			CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE1_MASK);
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index de85577c9cfd..b7d350be8050 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -88,20 +88,8 @@
 /* Vega, Raven, Arcturus */
 static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_encode =
@@ -113,48 +101,12 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode =
 /* Vega */
 static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_decode =
@@ -166,55 +118,13 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode =
 /* Raven */
 static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs rv_video_codecs_decode =
@@ -226,55 +136,13 @@ static const struct amdgpu_video_codecs rv_video_codecs_decode =
 /* Renoir, Arcturus */
 static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs rn_video_codecs_decode =
@@ -1360,10 +1228,7 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RAVEN:
 		adev->asic_funcs = &soc15_asic_funcs;
-		if (adev->pdev->device == 0x15dd)
-			adev->apu_flags |= AMD_APU_IS_RAVEN;
-		if (adev->pdev->device == 0x15d8)
-			adev->apu_flags |= AMD_APU_IS_PICASSO;
+
 		if (adev->rev_id >= 0x8)
 			adev->apu_flags |= AMD_APU_IS_RAVEN2;
 
@@ -1455,11 +1320,6 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RENOIR:
 		adev->asic_funcs = &soc15_asic_funcs;
-		if ((adev->pdev->device == 0x1636) ||
-		    (adev->pdev->device == 0x164c))
-			adev->apu_flags |= AMD_APU_IS_RENOIR;
-		else
-			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
 
 		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			adev->external_rev_id = adev->rev_id + 0x91;
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c
index 89d20adfa001..af59a35788e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c
@@ -234,7 +234,7 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev,
 		err_addr &= ~((0x1ULL << lsb) - 1);
 
 		/* translate umc channel address to soc pa, 3 parts are included */
-		retired_page = ADDR_OF_8KB_BLOCK(err_addr) |
+		retired_page = ADDR_OF_4KB_BLOCK(err_addr) |
 				ADDR_OF_256B_BLOCK(channel_index) |
 				OFFSET_IN_256B_BLOCK(err_addr);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 4c36fc5c9738..47d4f04cbd69 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -87,21 +87,18 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring);
 static int vcn_v3_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i;
 
 	if (amdgpu_sriov_vf(adev)) {
-		adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
+		for (i = 0; i < VCN_INSTANCES_SIENNA_CICHLID; i++)
+			if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i))
+				adev->vcn.num_vcn_inst++;
 		adev->vcn.harvest_config = 0;
 		adev->vcn.num_enc_rings = 1;
 
-	if (adev->asic_type == CHIP_BEIGE_GOBY) {
-		adev->vcn.num_vcn_inst = 1;
-		adev->vcn.num_enc_rings = 0;
-	}
-
 	} else {
 		if (adev->asic_type == CHIP_SIENNA_CICHLID) {
 			u32 harvest;
-			int i;
 
 			adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
 			for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
@@ -156,7 +153,8 @@ static int vcn_v3_0_sw_init(void *handle)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 
-		if (adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) {
+		if ((adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) ||
+		    (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)) {
 			adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1;
 			adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw;
 			adev->firmware.fw_size +=
@@ -330,19 +328,17 @@ static int vcn_v3_0_hw_init(void *handle)
 				continue;
 
 			ring = &adev->vcn.inst[i].ring_dec;
-			if (ring->sched.ready) {
-				ring->wptr = 0;
-				ring->wptr_old = 0;
-				vcn_v3_0_dec_ring_set_wptr(ring);
-			}
+			ring->wptr = 0;
+			ring->wptr_old = 0;
+			vcn_v3_0_dec_ring_set_wptr(ring);
+			ring->sched.ready = true;
 
 			for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
 				ring = &adev->vcn.inst[i].ring_enc[j];
-				if (ring->sched.ready) {
-					ring->wptr = 0;
-					ring->wptr_old = 0;
-					vcn_v3_0_enc_ring_set_wptr(ring);
-				}
+				ring->wptr = 0;
+				ring->wptr_old = 0;
+				vcn_v3_0_enc_ring_set_wptr(ring);
+				ring->sched.ready = true;
 			}
 		}
 	} else {
@@ -1309,8 +1305,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
 	uint32_t table_size;
 	uint32_t size, size_dw;
 
-	bool is_vcn_ready;
-
 	struct mmsch_v3_0_cmd_direct_write
 		direct_wt = { {0} };
 	struct mmsch_v3_0_cmd_direct_read_modify_write
@@ -1502,30 +1496,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
 		}
 	}
 
-	/* 6, check each VCN's init_status
-	 * if it remains as 0, then this VCN is not assigned to current VF
-	 * do not start ring for this VCN
-	 */
-	size = sizeof(struct mmsch_v3_0_init_header);
-	table_loc = (uint32_t *)table->cpu_addr;
-	memcpy(&header, (void *)table_loc, size);
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		is_vcn_ready = (header.inst[i].init_status == 1);
-		if (!is_vcn_ready)
-			DRM_INFO("VCN(%d) engine is disabled by hypervisor\n", i);
-
-		ring = &adev->vcn.inst[i].ring_dec;
-		ring->sched.ready = is_vcn_ready;
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
-			ring = &adev->vcn.inst[i].ring_enc[j];
-			ring->sched.ready = is_vcn_ready;
-		}
-	}
-
 	return 0;
 }