Merge remote-tracking branch 'torvalds/master' into perf-tools-next

To pick up fixes sent via perf-tools, by Namhyung Kim.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

251 files changed, 2646 insertions, 1309 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 182ed8f67850..5a0c476361c3 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -68,6 +68,7 @@ config DRM_USE_DYNAMIC_DEBUG
 config DRM_KUNIT_TEST_HELPERS
 	tristate
 	depends on DRM && KUNIT
+	select DRM_KMS_HELPER
 	help
 	  KUnit Helpers for KMS drivers.
 
@@ -80,7 +81,6 @@ config DRM_KUNIT_TEST
 	select DRM_EXEC
 	select DRM_EXPORT_FOR_TESTS if m
 	select DRM_GEM_SHMEM_HELPER
-	select DRM_KMS_HELPER
 	select DRM_KUNIT_TEST_HELPERS
 	select DRM_LIB_RANDOM
 	select PRIME_NUMBERS
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9c62552bec34..b3b84647207e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -210,6 +210,7 @@ extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
 extern int amdgpu_mes;
+extern int amdgpu_mes_log_enable;
 extern int amdgpu_mes_kiq;
 extern int amdgpu_noretry;
 extern int amdgpu_force_asic_type;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index f5f2945711be..35dd6effa9a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -146,7 +146,7 @@ int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev)
 {
 	int ret;
 
-	if (!adev->kfd.init_complete)
+	if (!adev->kfd.init_complete || adev->kfd.client.dev)
 		return 0;
 
 	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 14dc9d2d8d53..df58a6a1a67e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2869,14 +2869,16 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 
 	mutex_lock(&process_info->lock);
 
-	drm_exec_init(&exec, 0, 0);
+	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
 	drm_exec_until_all_locked(&exec) {
 		list_for_each_entry(peer_vm, &process_info->vm_list_head,
 				    vm_list_node) {
 			ret = amdgpu_vm_lock_pd(peer_vm, &exec, 2);
 			drm_exec_retry_on_contention(&exec);
-			if (unlikely(ret))
+			if (unlikely(ret)) {
+				pr_err("Locking VM PD failed, ret: %d\n", ret);
 				goto ttm_reserve_fail;
+			}
 		}
 
 		/* Reserve all BOs and page tables/directory. Add all BOs from
@@ -2889,8 +2891,10 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 			gobj = &mem->bo->tbo.base;
 			ret = drm_exec_prepare_obj(&exec, gobj, 1);
 			drm_exec_retry_on_contention(&exec);
-			if (unlikely(ret))
+			if (unlikely(ret)) {
+				pr_err("drm_exec_prepare_obj failed, ret: %d\n", ret);
 				goto ttm_reserve_fail;
+			}
 		}
 	}
 
@@ -2950,8 +2954,10 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 	 * validations above would invalidate DMABuf imports again.
 	 */
 	ret = process_validate_vms(process_info, &exec.ticket);
-	if (ret)
+	if (ret) {
+		pr_debug("Validating VMs failed, ret: %d\n", ret);
 		goto validate_map_fail;
+	}
 
 	/* Update mappings not managed by KFD */
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 0a4b09709cfb..ec888fc6ead8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -819,7 +819,7 @@ retry:
 
 	p->bytes_moved += ctx.bytes_moved;
 	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
-	    amdgpu_bo_in_cpu_visible_vram(bo))
+	    amdgpu_res_cpu_visible(adev, bo->tbo.resource))
 		p->bytes_moved_vis += ctx.bytes_moved;
 
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1e9454e6e4cb..7753a2e64d41 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4040,10 +4040,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * early on during init and before calling to RREG32.
 	 */
 	adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev");
-	if (!adev->reset_domain) {
-		r = -ENOMEM;
-		goto unmap_memory;
-	}
+	if (!adev->reset_domain)
+		return -ENOMEM;
 
 	/* detect hw virtualization here */
 	amdgpu_detect_virtualization(adev);
@@ -4053,7 +4051,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_device_get_job_timeout_settings(adev);
 	if (r) {
 		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
-		goto unmap_memory;
+		return r;
 	}
 
 	amdgpu_device_set_mcbp(adev);
@@ -4061,12 +4059,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	/* early init functions */
 	r = amdgpu_device_ip_early_init(adev);
 	if (r)
-		goto unmap_memory;
+		return r;
 
 	/* Get rid of things like offb */
 	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
 	if (r)
-		goto unmap_memory;
+		return r;
 
 	/* Enable TMZ based on IP_VERSION */
 	amdgpu_gmc_tmz_set(adev);
@@ -4076,7 +4074,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (adev->gmc.xgmi.supported) {
 		r = adev->gfxhub.funcs->get_xgmi_info(adev);
 		if (r)
-			goto unmap_memory;
+			return r;
 	}
 
 	/* enable PCIE atomic ops */
@@ -4137,18 +4135,22 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 					adev->ip_blocks[i].status.hw = true;
 				}
 			}
+		} else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
+				   !amdgpu_device_has_display_hardware(adev)) {
+					r = psp_gpu_reset(adev);
 		} else {
-			tmp = amdgpu_reset_method;
-			/* It should do a default reset when loading or reloading the driver,
-			 * regardless of the module parameter reset_method.
-			 */
-			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-			r = amdgpu_asic_reset(adev);
-			amdgpu_reset_method = tmp;
-			if (r) {
-				dev_err(adev->dev, "asic reset on init failed\n");
-				goto failed;
-			}
+				tmp = amdgpu_reset_method;
+				/* It should do a default reset when loading or reloading the driver,
+				 * regardless of the module parameter reset_method.
+				 */
+				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+				r = amdgpu_asic_reset(adev);
+				amdgpu_reset_method = tmp;
+		}
+
+		if (r) {
+		  dev_err(adev->dev, "asic reset on init failed\n");
+		  goto failed;
 		}
 	}
 
@@ -4345,8 +4347,6 @@ release_ras_con:
 failed:
 	amdgpu_vf_error_trans_all(adev);
 
-unmap_memory:
-	iounmap(adev->rmmio);
 	return r;
 }
 
@@ -4543,6 +4543,8 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	if (r)
 		goto unprepare;
 
+	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
+
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index a07e4b87d4ca..ac5bf01fe8d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1896,6 +1896,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		break;
 	case IP_VERSION(14, 0, 0):
+	case IP_VERSION(14, 0, 1):
 		amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block);
 		break;
 	default:
@@ -2237,6 +2238,7 @@ static int amdgpu_discovery_set_umsch_mm_ip_blocks(struct amdgpu_device *adev)
 {
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		if (amdgpu_umsch_mm & 0x1) {
 			amdgpu_device_ip_block_add(adev, &umsch_mm_v4_0_ip_block);
 			adev->enable_umsch_mm = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 15b188aaf681..e4277298cf1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -195,6 +195,7 @@ int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = -1;
 int amdgpu_discovery = -1;
 int amdgpu_mes;
+int amdgpu_mes_log_enable = 0;
 int amdgpu_mes_kiq;
 int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
@@ -668,6 +669,15 @@ MODULE_PARM_DESC(mes,
 module_param_named(mes, amdgpu_mes, int, 0444);
 
 /**
+ * DOC: mes_log_enable (int)
+ * Enable Micro Engine Scheduler log. This is used to enable/disable MES internal log.
+ * (0 = disabled (default), 1 = enabled)
+ */
+MODULE_PARM_DESC(mes_log_enable,
+	"Enable Micro Engine Scheduler log (0 = disabled (default), 1 = enabled)");
+module_param_named(mes_log_enable, amdgpu_mes_log_enable, int, 0444);
+
+/**
  * DOC: mes_kiq (int)
  * Enable Micro Engine Scheduler KIQ. This is a new engine pipe for kiq.
  * (0 = disabled (default), 1 = enabled)
@@ -2479,8 +2489,11 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work)
 	}
 	for (i = 0; i < mgpu_info.num_dgpu; i++) {
 		adev = mgpu_info.gpu_ins[i].adev;
-		if (!adev->kfd.init_complete)
+		if (!adev->kfd.init_complete) {
+			kgd2kfd_init_zone_device(adev);
 			amdgpu_amdkfd_device_init(adev);
+			amdgpu_amdkfd_drm_client_create(adev);
+		}
 		amdgpu_ttm_set_buffer_funcs_status(adev, true);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index f8b48fd93108..55d5508987ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -687,7 +687,7 @@ int amdgpu_gfx_enable_kgq(struct amdgpu_device *adev, int xcc_id)
 	r = amdgpu_ring_test_helper(kiq_ring);
 	spin_unlock(&kiq->ring_lock);
 	if (r)
-		DRM_ERROR("KCQ enable failed\n");
+		DRM_ERROR("KGQ enable failed\n");
 
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
index 55b65fc04b65..431ec72655ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
@@ -129,13 +129,25 @@ static const struct mmu_interval_notifier_ops amdgpu_hmm_hsa_ops = {
  */
 int amdgpu_hmm_register(struct amdgpu_bo *bo, unsigned long addr)
 {
+	int r;
+
 	if (bo->kfd_bo)
-		return mmu_interval_notifier_insert(&bo->notifier, current->mm,
+		r = mmu_interval_notifier_insert(&bo->notifier, current->mm,
 						    addr, amdgpu_bo_size(bo),
 						    &amdgpu_hmm_hsa_ops);
-	return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr,
-					    amdgpu_bo_size(bo),
-					    &amdgpu_hmm_gfx_ops);
+	else
+		r = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr,
+							amdgpu_bo_size(bo),
+							&amdgpu_hmm_gfx_ops);
+	if (r)
+		/*
+		 * Make sure amdgpu_hmm_unregister() doesn't call
+		 * mmu_interval_notifier_remove() when the notifier isn't properly
+		 * initialized.
+		 */
+		bo->notifier.mm = NULL;
+
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4b3000c21ef2..e4742b65032d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -304,12 +304,15 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 		dma_fence_set_error(finished, -ECANCELED);
 
 	if (finished->error < 0) {
-		DRM_INFO("Skip scheduling IBs!\n");
+		dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)",
+			ring->name);
 	} else {
 		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job,
 				       &fence);
 		if (r)
-			DRM_ERROR("Error scheduling IBs (%d)\n", r);
+			dev_err(adev->dev,
+				"Error scheduling IBs (%d) in ring(%s)", r,
+				ring->name);
 	}
 
 	job->job_run_counter++;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index a98e03e0a51f..a00cf4756ad0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -102,7 +102,10 @@ static int amdgpu_mes_event_log_init(struct amdgpu_device *adev)
 {
 	int r;
 
-	r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE,
+	if (!amdgpu_mes_log_enable)
+		return 0;
+
+	r = amdgpu_bo_create_kernel(adev, AMDGPU_MES_LOG_BUFFER_SIZE, PAGE_SIZE,
 				    AMDGPU_GEM_DOMAIN_GTT,
 				    &adev->mes.event_log_gpu_obj,
 				    &adev->mes.event_log_gpu_addr,
@@ -1549,12 +1552,11 @@ static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
 	uint32_t *mem = (uint32_t *)(adev->mes.event_log_cpu_addr);
 
 	seq_hex_dump(m, "", DUMP_PREFIX_OFFSET, 32, 4,
-		     mem, PAGE_SIZE, false);
+		     mem, AMDGPU_MES_LOG_BUFFER_SIZE, false);
 
 	return 0;
 }
 
-
 DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_mes_event_log);
 
 #endif
@@ -1565,7 +1567,7 @@ void amdgpu_debugfs_mes_event_log_init(struct amdgpu_device *adev)
 #if defined(CONFIG_DEBUG_FS)
 	struct drm_minor *minor = adev_to_drm(adev)->primary;
 	struct dentry *root = minor->debugfs_root;
-	if (adev->enable_mes)
+	if (adev->enable_mes && amdgpu_mes_log_enable)
 		debugfs_create_file("amdgpu_mes_event_log", 0444, root,
 				    adev, &amdgpu_debugfs_mes_event_log_fops);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 7d4f93fea937..4c8fc3117ef8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -52,6 +52,7 @@ enum amdgpu_mes_priority_level {
 
 #define AMDGPU_MES_PROC_CTX_SIZE 0x1000 /* one page area */
 #define AMDGPU_MES_GANG_CTX_SIZE 0x1000 /* one page area */
+#define AMDGPU_MES_LOG_BUFFER_SIZE 0x4000 /* Maximu log buffer size for MES */
 
 struct amdgpu_mes_funcs;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 010b0cb7693c..2099159a693f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -617,8 +617,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 		return r;
 
 	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
-	    bo->tbo.resource->mem_type == TTM_PL_VRAM &&
-	    amdgpu_bo_in_cpu_visible_vram(bo))
+	    amdgpu_res_cpu_visible(adev, bo->tbo.resource))
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
 					     ctx.bytes_moved);
 	else
@@ -1272,23 +1271,25 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
 void amdgpu_bo_get_memory(struct amdgpu_bo *bo,
 			  struct amdgpu_mem_stats *stats)
 {
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct ttm_resource *res = bo->tbo.resource;
 	uint64_t size = amdgpu_bo_size(bo);
 	struct drm_gem_object *obj;
 	unsigned int domain;
 	bool shared;
 
 	/* Abort if the BO doesn't currently have a backing store */
-	if (!bo->tbo.resource)
+	if (!res)
 		return;
 
 	obj = &bo->tbo.base;
 	shared = drm_gem_object_is_shared_for_memory_stats(obj);
 
-	domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
+	domain = amdgpu_mem_type_to_domain(res->mem_type);
 	switch (domain) {
 	case AMDGPU_GEM_DOMAIN_VRAM:
 		stats->vram += size;
-		if (amdgpu_bo_in_cpu_visible_vram(bo))
+		if (amdgpu_res_cpu_visible(adev, bo->tbo.resource))
 			stats->visible_vram += size;
 		if (shared)
 			stats->vram_shared += size;
@@ -1389,10 +1390,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	/* Remember that this BO was accessed by the CPU */
 	abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 
-	if (bo->resource->mem_type != TTM_PL_VRAM)
-		return 0;
-
-	if (amdgpu_bo_in_cpu_visible_vram(abo))
+	if (amdgpu_res_cpu_visible(adev, bo->resource))
 		return 0;
 
 	/* Can't move a pinned BO to visible VRAM */
@@ -1415,7 +1413,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	/* this should never happen */
 	if (bo->resource->mem_type == TTM_PL_VRAM &&
-	    !amdgpu_bo_in_cpu_visible_vram(abo))
+	    !amdgpu_res_cpu_visible(adev, bo->resource))
 		return VM_FAULT_SIGBUS;
 
 	ttm_bo_move_to_lru_tail_unlocked(bo);
@@ -1579,6 +1577,7 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
  */
 u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m)
 {
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct dma_buf_attachment *attachment;
 	struct dma_buf *dma_buf;
 	const char *placement;
@@ -1587,10 +1586,11 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m)
 
 	if (dma_resv_trylock(bo->tbo.base.resv)) {
 		unsigned int domain;
+
 		domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
 		switch (domain) {
 		case AMDGPU_GEM_DOMAIN_VRAM:
-			if (amdgpu_bo_in_cpu_visible_vram(bo))
+			if (amdgpu_res_cpu_visible(adev, bo->tbo.resource))
 				placement = "VRAM VISIBLE";
 			else
 				placement = "VRAM";
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index be679c42b0b8..fa03d9e4874c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -251,28 +251,6 @@ static inline u64 amdgpu_bo_mmap_offset(struct amdgpu_bo *bo)
 }
 
 /**
- * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM
- */
-static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo)
-{
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	struct amdgpu_res_cursor cursor;
-
-	if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM)
-		return false;
-
-	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
-	while (cursor.remaining) {
-		if (cursor.start < adev->gmc.visible_vram_size)
-			return true;
-
-		amdgpu_res_next(&cursor, cursor.size);
-	}
-
-	return false;
-}
-
-/**
  * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced
  */
 static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 3c2b1413058b..94b310fdb719 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1830,6 +1830,10 @@ static int psp_hdcp_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
+	/* bypass hdcp initialization if dmu is harvested */
+	if (!amdgpu_device_has_display_hardware(psp->adev))
+		return 0;
+
 	if (!psp->hdcp_context.context.bin_desc.size_bytes ||
 	    !psp->hdcp_context.context.bin_desc.start_addr) {
 		dev_info(psp->adev->dev, "HDCP: optional hdcp ta ucode is not available\n");
@@ -1862,6 +1866,9 @@ int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
+	if (!psp->hdcp_context.context.initialized)
+		return 0;
+
 	return psp_ta_invoke(psp, ta_cmd_id, &psp->hdcp_context.context);
 }
 
@@ -1897,6 +1904,10 @@ static int psp_dtm_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
+	/* bypass dtm initialization if dmu is harvested */
+	if (!amdgpu_device_has_display_hardware(psp->adev))
+		return 0;
+
 	if (!psp->dtm_context.context.bin_desc.size_bytes ||
 	    !psp->dtm_context.context.bin_desc.start_addr) {
 		dev_info(psp->adev->dev, "DTM: optional dtm ta ucode is not available\n");
@@ -1929,6 +1940,9 @@ int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
+	if (!psp->dtm_context.context.initialized)
+		return 0;
+
 	return psp_ta_invoke(psp, ta_cmd_id, &psp->dtm_context.context);
 }
 
@@ -2063,6 +2077,10 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
+	/* bypass securedisplay initialization if dmu is harvested */
+	if (!amdgpu_device_has_display_hardware(psp->adev))
+		return 0;
+
 	if (!psp->securedisplay_context.context.bin_desc.size_bytes ||
 	    !psp->securedisplay_context.context.bin_desc.start_addr) {
 		dev_info(psp->adev->dev, "SECUREDISPLAY: securedisplay ta ucode is not available\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 5505d646f43a..06f0a6534a94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -524,46 +524,58 @@ static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf,
 {
 	struct amdgpu_ring *ring = file_inode(f)->i_private;
 	volatile u32 *mqd;
-	int r;
+	u32 *kbuf;
+	int r, i;
 	uint32_t value, result;
 
 	if (*pos & 3 || size & 3)
 		return -EINVAL;
 
-	result = 0;
+	kbuf = kmalloc(ring->mqd_size, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
 
 	r = amdgpu_bo_reserve(ring->mqd_obj, false);
 	if (unlikely(r != 0))
-		return r;
+		goto err_free;
 
 	r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd);
-	if (r) {
-		amdgpu_bo_unreserve(ring->mqd_obj);
-		return r;
-	}
+	if (r)
+		goto err_unreserve;
 
+	/*
+	 * Copy to local buffer to avoid put_user(), which might fault
+	 * and acquire mmap_sem, under reservation_ww_class_mutex.
+	 */
+	for (i = 0; i < ring->mqd_size/sizeof(u32); i++)
+		kbuf[i] = mqd[i];
+
+	amdgpu_bo_kunmap(ring->mqd_obj);
+	amdgpu_bo_unreserve(ring->mqd_obj);
+
+	result = 0;
 	while (size) {
 		if (*pos >= ring->mqd_size)
-			goto done;
+			break;
 
-		value = mqd[*pos/4];
+		value = kbuf[*pos/4];
 		r = put_user(value, (uint32_t *)buf);
 		if (r)
-			goto done;
+			goto err_free;
 		buf += 4;
 		result += 4;
 		size -= 4;
 		*pos += 4;
 	}
 
-done:
-	amdgpu_bo_kunmap(ring->mqd_obj);
-	mqd = NULL;
-	amdgpu_bo_unreserve(ring->mqd_obj);
-	if (r)
-		return r;
-
+	kfree(kbuf);
 	return result;
+
+err_unreserve:
+	amdgpu_bo_unreserve(ring->mqd_obj);
+err_free:
+	kfree(kbuf);
+	return r;
 }
 
 static const struct file_operations amdgpu_debugfs_mqd_fops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 8722beba494e..1d71729e3f6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -133,7 +133,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 
 		} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
-			   amdgpu_bo_in_cpu_visible_vram(abo)) {
+			   amdgpu_res_cpu_visible(adev, bo->resource)) {
 
 			/* Try evicting to the CPU inaccessible part of VRAM
 			 * first, but only set GTT as busy placement, so this
@@ -403,40 +403,55 @@ error:
 	return r;
 }
 
-/*
- * amdgpu_mem_visible - Check that memory can be accessed by ttm_bo_move_memcpy
+/**
+ * amdgpu_res_cpu_visible - Check that resource can be accessed by CPU
+ * @adev: amdgpu device
+ * @res: the resource to check
  *
- * Called by amdgpu_bo_move()
+ * Returns: true if the full resource is CPU visible, false otherwise.
  */
-static bool amdgpu_mem_visible(struct amdgpu_device *adev,
-			       struct ttm_resource *mem)
+bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
+			    struct ttm_resource *res)
 {
-	u64 mem_size = (u64)mem->size;
 	struct amdgpu_res_cursor cursor;
-	u64 end;
 
-	if (mem->mem_type == TTM_PL_SYSTEM ||
-	    mem->mem_type == TTM_PL_TT)
+	if (!res)
+		return false;
+
+	if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT ||
+	    res->mem_type == AMDGPU_PL_PREEMPT)
 		return true;
-	if (mem->mem_type != TTM_PL_VRAM)
+
+	if (res->mem_type != TTM_PL_VRAM)
 		return false;
 
-	amdgpu_res_first(mem, 0, mem_size, &cursor);
-	end = cursor.start + cursor.size;
+	amdgpu_res_first(res, 0, res->size, &cursor);
 	while (cursor.remaining) {
+		if ((cursor.start + cursor.size) >= adev->gmc.visible_vram_size)
+			return false;
 		amdgpu_res_next(&cursor, cursor.size);
+	}
 
-		if (!cursor.remaining)
-			break;
+	return true;
+}
 
-		/* ttm_resource_ioremap only supports contiguous memory */
-		if (end != cursor.start)
-			return false;
+/*
+ * amdgpu_res_copyable - Check that memory can be accessed by ttm_bo_move_memcpy
+ *
+ * Called by amdgpu_bo_move()
+ */
+static bool amdgpu_res_copyable(struct amdgpu_device *adev,
+				struct ttm_resource *mem)
+{
+	if (!amdgpu_res_cpu_visible(adev, mem))
+		return false;
 
-		end = cursor.start + cursor.size;
-	}
+	/* ttm_resource_ioremap only supports contiguous memory */
+	if (mem->mem_type == TTM_PL_VRAM &&
+	    !(mem->placement & TTM_PL_FLAG_CONTIGUOUS))
+		return false;
 
-	return end <= adev->gmc.visible_vram_size;
+	return true;
 }
 
 /*
@@ -529,8 +544,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 	if (r) {
 		/* Check that all memory is CPU accessible */
-		if (!amdgpu_mem_visible(adev, old_mem) ||
-		    !amdgpu_mem_visible(adev, new_mem)) {
+		if (!amdgpu_res_copyable(adev, old_mem) ||
+		    !amdgpu_res_copyable(adev, new_mem)) {
 			pr_err("Move buffer fallback to memcpy unavailable\n");
 			return r;
 		}
@@ -557,7 +572,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev,
 				     struct ttm_resource *mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	size_t bus_size = (size_t)mem->size;
 
 	switch (mem->mem_type) {
 	case TTM_PL_SYSTEM:
@@ -568,9 +582,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev,
 		break;
 	case TTM_PL_VRAM:
 		mem->bus.offset = mem->start << PAGE_SHIFT;
-		/* check if it's visible */
-		if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size)
-			return -EINVAL;
 
 		if (adev->mman.aper_base_kaddr &&
 		    mem->placement & TTM_PL_FLAG_CONTIGUOUS)
@@ -864,6 +875,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
 		amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages,
 				 gtt->ttm.dma_address, flags);
 	}
+	gtt->bound = true;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 65ec82141a8e..32cf6b6f6efd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -139,6 +139,9 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr,
 int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr,
 				      uint64_t start);
 
+bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
+			    struct ttm_resource *res);
+
 int amdgpu_ttm_init(struct amdgpu_device *adev);
 void amdgpu_ttm_fini(struct amdgpu_device *adev);
 void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index ab820cf52668..0df97c3e3a70 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -189,10 +189,13 @@ static void setup_vpe_queue(struct amdgpu_device *adev,
 	mqd->rptr_val = 0;
 	mqd->unmapped = 1;
 
+	if (adev->vpe.collaborate_mode)
+		memcpy(++mqd, test->mqd_data_cpu_addr, sizeof(struct MQD_INFO));
+
 	qinfo->mqd_addr = test->mqd_data_gpu_addr;
 	qinfo->csa_addr = test->ctx_data_gpu_addr +
 		offsetof(struct umsch_mm_test_ctx_data, vpe_ctx_csa);
-	qinfo->doorbell_offset_0 = (adev->doorbell_index.vpe_ring + 1) << 1;
+	qinfo->doorbell_offset_0 = 0;
 	qinfo->doorbell_offset_1 = 0;
 }
 
@@ -287,7 +290,10 @@ static int submit_vpe_queue(struct amdgpu_device *adev, struct umsch_mm_test *te
 	ring[5] = 0;
 
 	mqd->wptr_val = (6 << 2);
-	// WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
+	if (adev->vpe.collaborate_mode)
+		(++mqd)->wptr_val = (6 << 2);
+
+	WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (*fence == test_pattern)
@@ -571,6 +577,7 @@ int amdgpu_umsch_mm_init_microcode(struct amdgpu_umsch_mm *umsch)
 
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		fw_name = "amdgpu/umsch_mm_4_0_0.bin";
 		break;
 	default:
@@ -750,6 +757,7 @@ static int umsch_mm_early_init(void *handle)
 
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		umsch_mm_v4_0_set_funcs(&adev->umsch_mm);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
index 8258a43a6236..5014b5af95fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
@@ -33,13 +33,6 @@ enum UMSCH_SWIP_ENGINE_TYPE {
 	UMSCH_SWIP_ENGINE_TYPE_MAX
 };
 
-enum UMSCH_SWIP_AFFINITY_TYPE {
-	UMSCH_SWIP_AFFINITY_TYPE_ANY = 0,
-	UMSCH_SWIP_AFFINITY_TYPE_VCN0 = 1,
-	UMSCH_SWIP_AFFINITY_TYPE_VCN1 = 2,
-	UMSCH_SWIP_AFFINITY_TYPE_MAX
-};
-
 enum UMSCH_CONTEXT_PRIORITY_LEVEL {
 	CONTEXT_PRIORITY_LEVEL_IDLE = 0,
 	CONTEXT_PRIORITY_LEVEL_NORMAL = 1,
@@ -51,13 +44,15 @@ enum UMSCH_CONTEXT_PRIORITY_LEVEL {
 struct umsch_mm_set_resource_input {
 	uint32_t vmid_mask_mm_vcn;
 	uint32_t vmid_mask_mm_vpe;
+	uint32_t collaboration_mask_vpe;
 	uint32_t logging_vmid;
 	uint32_t engine_mask;
 	union {
 		struct {
 			uint32_t disable_reset : 1;
 			uint32_t disable_umsch_mm_log : 1;
-			uint32_t reserved : 30;
+			uint32_t use_rs64mem_for_proc_ctx_csa : 1;
+			uint32_t reserved : 29;
 		};
 		uint32_t uint32_all;
 	};
@@ -78,15 +73,18 @@ struct umsch_mm_add_queue_input {
 	uint32_t doorbell_offset_1;
 	enum UMSCH_SWIP_ENGINE_TYPE engine_type;
 	uint32_t affinity;
-	enum UMSCH_SWIP_AFFINITY_TYPE affinity_type;
 	uint64_t mqd_addr;
 	uint64_t h_context;
 	uint64_t h_queue;
 	uint32_t vm_context_cntl;
 
+	uint32_t process_csa_array_index;
+	uint32_t context_csa_array_index;
+
 	struct {
 		uint32_t is_context_suspended : 1;
-		uint32_t reserved : 31;
+		uint32_t collaboration_mode : 1;
+		uint32_t reserved : 30;
 	};
 };
 
@@ -94,6 +92,7 @@ struct umsch_mm_remove_queue_input {
 	uint32_t doorbell_offset_0;
 	uint32_t doorbell_offset_1;
 	uint64_t context_csa_addr;
+	uint32_t context_csa_array_index;
 };
 
 struct MQD_INFO {
@@ -103,6 +102,7 @@ struct MQD_INFO {
 	uint32_t wptr_val;
 	uint32_t rptr_val;
 	uint32_t unmapped;
+	uint32_t vmid;
 };
 
 struct amdgpu_umsch_mm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index b2535023764f..9c514a606a2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -60,6 +60,7 @@
 #define FIRMWARE_VCN4_0_4		"amdgpu/vcn_4_0_4.bin"
 #define FIRMWARE_VCN4_0_5		"amdgpu/vcn_4_0_5.bin"
 #define FIRMWARE_VCN4_0_6		"amdgpu/vcn_4_0_6.bin"
+#define FIRMWARE_VCN4_0_6_1		"amdgpu/vcn_4_0_6_1.bin"
 #define FIRMWARE_VCN5_0_0		"amdgpu/vcn_5_0_0.bin"
 
 MODULE_FIRMWARE(FIRMWARE_RAVEN);
@@ -85,6 +86,7 @@ MODULE_FIRMWARE(FIRMWARE_VCN4_0_3);
 MODULE_FIRMWARE(FIRMWARE_VCN4_0_4);
 MODULE_FIRMWARE(FIRMWARE_VCN4_0_5);
 MODULE_FIRMWARE(FIRMWARE_VCN4_0_6);
+MODULE_FIRMWARE(FIRMWARE_VCN4_0_6_1);
 MODULE_FIRMWARE(FIRMWARE_VCN5_0_0);
 
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
@@ -93,14 +95,22 @@ int amdgpu_vcn_early_init(struct amdgpu_device *adev)
 {
 	char ucode_prefix[30];
 	char fw_name[40];
-	int r;
+	int r, i;
 
-	amdgpu_ucode_ip_version_decode(adev, UVD_HWIP, ucode_prefix, sizeof(ucode_prefix));
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix);
-	r = amdgpu_ucode_request(adev, &adev->vcn.fw, fw_name);
-	if (r)
-		amdgpu_ucode_release(&adev->vcn.fw);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		amdgpu_ucode_ip_version_decode(adev, UVD_HWIP, ucode_prefix, sizeof(ucode_prefix));
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix);
+		if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==  IP_VERSION(4, 0, 6) &&
+			i == 1) {
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_%d.bin", ucode_prefix, i);
+		}
 
+		r = amdgpu_ucode_request(adev, &adev->vcn.fw[i], fw_name);
+		if (r) {
+			amdgpu_ucode_release(&adev->vcn.fw[i]);
+			return r;
+		}
+	}
 	return r;
 }
 
@@ -141,7 +151,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		}
 	}
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[0]->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
 	/* Bit 20-23, it is encode major and non-zero for new naming convention.
@@ -256,9 +266,10 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]);
+
+		amdgpu_ucode_release(&adev->vcn.fw[j]);
 	}
 
-	amdgpu_ucode_release(&adev->vcn.fw);
 	mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround);
 	mutex_destroy(&adev->vcn.vcn_pg_lock);
 
@@ -354,11 +365,12 @@ int amdgpu_vcn_resume(struct amdgpu_device *adev)
 			const struct common_firmware_header *hdr;
 			unsigned int offset;
 
-			hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+			hdr = (const struct common_firmware_header *)adev->vcn.fw[i]->data;
 			if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
 				offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
 				if (drm_dev_enter(adev_to_drm(adev), &idx)) {
-					memcpy_toio(adev->vcn.inst[i].cpu_addr, adev->vcn.fw->data + offset,
+					memcpy_toio(adev->vcn.inst[i].cpu_addr,
+						    adev->vcn.fw[i]->data + offset,
 						    le32_to_cpu(hdr->ucode_size_bytes));
 					drm_dev_exit(idx);
 				}
@@ -1043,11 +1055,11 @@ void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev)
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		const struct common_firmware_header *hdr;
 
-		hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
-
 		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 			if (adev->vcn.harvest_config & (1 << i))
 				continue;
+
+			hdr = (const struct common_firmware_header *)adev->vcn.fw[i]->data;
 			/* currently only support 2 FW instances */
 			if (i >= 2) {
 				dev_info(adev->dev, "More then 2 VCN FW instances!\n");
@@ -1055,7 +1067,7 @@ void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev)
 			}
 			idx = AMDGPU_UCODE_ID_VCN + i;
 			adev->firmware.ucode[idx].ucode_id = idx;
-			adev->firmware.ucode[idx].fw = adev->vcn.fw;
+			adev->firmware.ucode[idx].fw = adev->vcn.fw[i];
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 1985f71b4373..a418393d89ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -306,7 +306,7 @@ struct amdgpu_vcn_ras {
 struct amdgpu_vcn {
 	unsigned		fw_version;
 	struct delayed_work	idle_work;
-	const struct firmware	*fw;	/* VCN firmware */
+	const struct firmware	*fw[AMDGPU_MAX_VCN_INSTANCES];	/* VCN firmware */
 	unsigned		num_enc_rings;
 	enum amd_powergating_state cur_state;
 	bool			indirect_sram;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 4299ce386322..94089069c9ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1613,6 +1613,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
 	trace_amdgpu_vm_bo_map(bo_va, mapping);
 }
 
+/* Validate operation parameters to prevent potential abuse */
+static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev,
+					  struct amdgpu_bo *bo,
+					  uint64_t saddr,
+					  uint64_t offset,
+					  uint64_t size)
+{
+	uint64_t tmp, lpfn;
+
+	if (saddr & AMDGPU_GPU_PAGE_MASK
+	    || offset & AMDGPU_GPU_PAGE_MASK
+	    || size & AMDGPU_GPU_PAGE_MASK)
+		return -EINVAL;
+
+	if (check_add_overflow(saddr, size, &tmp)
+	    || check_add_overflow(offset, size, &tmp)
+	    || size == 0 /* which also leads to end < begin */)
+		return -EINVAL;
+
+	/* make sure object fit at this offset */
+	if (bo && offset + size > amdgpu_bo_size(bo))
+		return -EINVAL;
+
+	/* Ensure last pfn not exceed max_pfn */
+	lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT;
+	if (lpfn >= adev->vm_manager.max_pfn)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * amdgpu_vm_bo_map - map bo inside a vm
  *
@@ -1639,21 +1670,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	struct amdgpu_bo *bo = bo_va->base.bo;
 	struct amdgpu_vm *vm = bo_va->base.vm;
 	uint64_t eaddr;
+	int r;
 
-	/* validate the parameters */
-	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK)
-		return -EINVAL;
-	if (saddr + size <= saddr || offset + size <= offset)
-		return -EINVAL;
-
-	/* make sure object fit at this offset */
-	eaddr = saddr + size - 1;
-	if ((bo && offset + size > amdgpu_bo_size(bo)) ||
-	    (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT))
-		return -EINVAL;
+	r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size);
+	if (r)
+		return r;
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
-	eaddr /= AMDGPU_GPU_PAGE_SIZE;
+	eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;
 
 	tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr);
 	if (tmp) {
@@ -1706,17 +1730,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
 	uint64_t eaddr;
 	int r;
 
-	/* validate the parameters */
-	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK)
-		return -EINVAL;
-	if (saddr + size <= saddr || offset + size <= offset)
-		return -EINVAL;
-
-	/* make sure object fit at this offset */
-	eaddr = saddr + size - 1;
-	if ((bo && offset + size > amdgpu_bo_size(bo)) ||
-	    (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT))
-		return -EINVAL;
+	r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size);
+	if (r)
+		return r;
 
 	/* Allocate all the needed memory */
 	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
@@ -1730,7 +1746,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
 	}
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
-	eaddr /= AMDGPU_GPU_PAGE_SIZE;
+	eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;
 
 	mapping->start = saddr;
 	mapping->last = eaddr;
@@ -1817,10 +1833,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 	struct amdgpu_bo_va_mapping *before, *after, *tmp, *next;
 	LIST_HEAD(removed);
 	uint64_t eaddr;
+	int r;
+
+	r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size);
+	if (r)
+		return r;
 
-	eaddr = saddr + size - 1;
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
-	eaddr /= AMDGPU_GPU_PAGE_SIZE;
+	eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;
 
 	/* Allocate all the needed memory */
 	before = kzalloc(sizeof(*before), GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 70c5cc80ecdc..6695481f870f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -396,6 +396,12 @@ static int vpe_hw_init(void *handle)
 	struct amdgpu_vpe *vpe = &adev->vpe;
 	int ret;
 
+	/* Power on VPE */
+	ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE,
+						     AMD_PG_STATE_UNGATE);
+	if (ret)
+		return ret;
+
 	ret = vpe_load_microcode(vpe);
 	if (ret)
 		return ret;
@@ -575,9 +581,6 @@ static unsigned int vpe_ring_init_cond_exec(struct amdgpu_ring *ring,
 {
 	unsigned int ret;
 
-	if (ring->adev->vpe.collaborate_mode)
-		return ~0;
-
 	amdgpu_ring_write(ring, VPE_CMD_HEADER(VPE_CMD_OPCODE_COND_EXE, 0));
 	amdgpu_ring_write(ring, lower_32_bits(addr));
 	amdgpu_ring_write(ring, upper_32_bits(addr));
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index d6f808acfb17..fbb43ae7624f 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -62,6 +62,11 @@ void aqua_vanjaram_doorbell_index_init(struct amdgpu_device *adev)
 	adev->doorbell_index.max_assignment = AMDGPU_DOORBELL_LAYOUT1_MAX_ASSIGNMENT << 1;
 }
 
+static bool aqua_vanjaram_xcp_vcn_shared(struct amdgpu_device *adev)
+{
+	return (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst);
+}
+
 static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev,
 			     uint32_t inst_idx, struct amdgpu_ring *ring)
 {
@@ -87,7 +92,7 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev,
 	case AMDGPU_RING_TYPE_VCN_ENC:
 	case AMDGPU_RING_TYPE_VCN_JPEG:
 		ip_blk = AMDGPU_XCP_VCN;
-		if (adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE)
+		if (aqua_vanjaram_xcp_vcn_shared(adev))
 			inst_mask = 1 << (inst_idx * 2);
 		break;
 	default:
@@ -140,10 +145,12 @@ static int aqua_vanjaram_xcp_sched_list_update(
 
 		aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id);
 
-		/* VCN is shared by two partitions under CPX MODE */
+		/* VCN may be shared by two partitions under CPX MODE in certain
+		 * configs.
+		 */
 		if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
-			ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
-			adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE)
+		     ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
+		    aqua_vanjaram_xcp_vcn_shared(adev))
 			aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 904b9ff5ead2..f90905ef32c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3657,6 +3657,9 @@ static void gfx_v10_0_init_spm_golden_registers(struct amdgpu_device *adev)
 
 static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 {
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(10, 1, 10):
 		soc15_program_register_sequence(adev,
@@ -4982,7 +4985,8 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 	u32 tmp;
 	int i;
 
-	WREG32_FIELD15(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
+	if (!amdgpu_sriov_vf(adev))
+		WREG32_FIELD15(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff);
 
 	gfx_v10_0_setup_rb(adev);
 	gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info);
@@ -7163,7 +7167,7 @@ static int gfx_v10_0_hw_init(void *handle)
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(10, 3, 0))
 		gfx_v10_3_program_pbb_mode(adev);
 
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 3, 0))
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 3, 0) && !amdgpu_sriov_vf(adev))
 		gfx_v10_3_set_power_brake_sequence(adev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 1770e496c1b7..f7325b02a191 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1635,7 +1635,7 @@ static void gfx_v11_0_setup_rb(struct amdgpu_device *adev)
 			active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa));
 	}
 
-	active_rb_bitmap |= global_active_rb_bitmap;
+	active_rb_bitmap &= global_active_rb_bitmap;
 	adev->gfx.config.backend_enable_mask = active_rb_bitmap;
 	adev->gfx.config.num_rbs = hweight32(active_rb_bitmap);
 }
@@ -5465,6 +5465,7 @@ static void gfx_v11_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	/* Make sure that we can't skip the SET_Q_MODE packets when the VM
 	 * changed in any way.
 	 */
+	ring->set_q_mode_offs = 0;
 	ring->set_q_mode_ptr = NULL;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index cd0e8a321e46..17509f32f61a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -155,6 +155,9 @@ static void gfxhub_v2_1_init_system_aperture_regs(struct amdgpu_device *adev)
 {
 	uint64_t value;
 
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	/* Program the AGP BAR */
 	WREG32_SOC15(GC, 0, mmGCMC_VM_AGP_BASE, 0);
 	WREG32_SOC15(GC, 0, mmGCMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
index 16fe428c0722..7aed96fa10a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
@@ -418,6 +418,12 @@ static u32 ih_v7_0_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 072c478665ad..63f281a9984d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -411,8 +411,11 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
-	mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
-	mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr;
+	if (amdgpu_mes_log_enable) {
+		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
+		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr =
+					mes->event_log_gpu_addr;
+	}
 
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
index b3961968c10c..238ea40c2450 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
@@ -99,16 +99,15 @@ mmhub_v3_3_print_l2_protection_fault_status(struct amdgpu_device *adev,
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(3, 3, 0):
 	case IP_VERSION(3, 3, 1):
-		mmhub_cid = mmhub_client_ids_v3_3[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_3) ?
+			    mmhub_client_ids_v3_3[cid][rw] :
+			    cid == 0x140 ? "UMSCH" : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
 		break;
 	}
 
-	if (!mmhub_cid && cid == 0x140)
-		mmhub_cid = "UMSCH";
-
 	dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
 		mmhub_cid ? mmhub_cid : "unknown", cid);
 	dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 2d904ee72701..82eab49be82b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -431,16 +431,11 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 	struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
 	u32 doorbell_offset, doorbell;
 	u32 rb_cntl, ib_cntl;
-	int i, unset = 0;
+	int i;
 
 	for_each_inst(i, inst_mask) {
 		sdma[i] = &adev->sdma.instance[i].ring;
 
-		if ((adev->mman.buffer_funcs_ring == sdma[i]) && unset != 1) {
-			amdgpu_ttm_set_buffer_funcs_status(adev, false);
-			unset = 1;
-		}
-
 		rb_cntl = RREG32_SDMA(i, regSDMA_GFX_RB_CNTL);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA_GFX_RB_CNTL, RB_ENABLE, 0);
 		WREG32_SDMA(i, regSDMA_GFX_RB_CNTL, rb_cntl);
@@ -487,20 +482,10 @@ static void sdma_v4_4_2_inst_rlc_stop(struct amdgpu_device *adev,
 static void sdma_v4_4_2_inst_page_stop(struct amdgpu_device *adev,
 				       uint32_t inst_mask)
 {
-	struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
 	u32 rb_cntl, ib_cntl;
 	int i;
-	bool unset = false;
 
 	for_each_inst(i, inst_mask) {
-		sdma[i] = &adev->sdma.instance[i].page;
-
-		if ((adev->mman.buffer_funcs_ring == sdma[i]) &&
-			(!unset)) {
-			amdgpu_ttm_set_buffer_funcs_status(adev, false);
-			unset = true;
-		}
-
 		rb_cntl = RREG32_SDMA(i, regSDMA_PAGE_RB_CNTL);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA_PAGE_RB_CNTL,
 					RB_ENABLE, 0);
@@ -950,13 +935,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
 			r = amdgpu_ring_test_helper(page);
 			if (r)
 				return r;
-
-			if (adev->mman.buffer_funcs_ring == page)
-				amdgpu_ttm_set_buffer_funcs_status(adev, true);
 		}
-
-		if (adev->mman.buffer_funcs_ring == ring)
-			amdgpu_ttm_set_buffer_funcs_status(adev, true);
 	}
 
 	return r;
@@ -1623,19 +1602,9 @@ static int sdma_v4_4_2_set_ecc_irq_state(struct amdgpu_device *adev,
 	u32 sdma_cntl;
 
 	sdma_cntl = RREG32_SDMA(type, regSDMA_CNTL);
-	switch (state) {
-	case AMDGPU_IRQ_STATE_DISABLE:
-		sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL,
-					  DRAM_ECC_INT_ENABLE, 0);
-		WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl);
-		break;
-	/* sdma ecc interrupt is enabled by default
-	 * driver doesn't need to do anything to
-	 * enable the interrupt */
-	case AMDGPU_IRQ_STATE_ENABLE:
-	default:
-		break;
-	}
+	sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, DRAM_ECC_INT_ENABLE,
+					state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0);
+	WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 581a3bd11481..43ca63fe85ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -457,10 +457,8 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev)
 {
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(11, 0, 0):
-		return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC);
 	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
-		return false;
 	default:
 		return true;
 	}
@@ -722,7 +720,10 @@ static int soc21_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_GFX_PG;
-		adev->external_rev_id = adev->rev_id + 0x1;
+		if (adev->rev_id == 0)
+			adev->external_rev_id = 0x1;
+		else
+			adev->external_rev_id = adev->rev_id + 0x10;
 		break;
 	case IP_VERSION(11, 5, 1):
 		adev->cg_flags =
@@ -869,10 +870,35 @@ static int soc21_common_suspend(void *handle)
 	return soc21_common_hw_fini(adev);
 }
 
+static bool soc21_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg1, sol_reg2;
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset dGPU side.
+	 * 2) S3 suspend got aborted and TOS is active.
+	 */
+	if (!(adev->flags & AMD_IS_APU) && adev->in_s3 &&
+	    !adev->suspend_complete) {
+		sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+		msleep(100);
+		sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+
+		return (sol_reg1 != sol_reg2);
+	}
+
+	return false;
+}
+
 static int soc21_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc21_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend aborted, resetting...");
+		soc21_asic_reset(adev);
+	}
+
 	return soc21_common_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index 8e7b763cfdb7..bd57896ab85d 100644
--- a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
@@ -60,7 +60,7 @@ static int umsch_mm_v4_0_load_microcode(struct amdgpu_umsch_mm *umsch)
 
 	umsch->cmd_buf_curr_ptr = umsch->cmd_buf_ptr;
 
-	if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+	if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
 		WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
 			1 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
 		SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -225,6 +225,8 @@ static int umsch_mm_v4_0_ring_start(struct amdgpu_umsch_mm *umsch)
 
 	WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_SIZE, ring->ring_size);
 
+	ring->wptr = 0;
+
 	data = RREG32_SOC15(VCN, 0, regVCN_RB_ENABLE);
 	data &= ~(VCN_RB_ENABLE__AUDIO_RB_EN_MASK);
 	WREG32_SOC15(VCN, 0, regVCN_RB_ENABLE, data);
@@ -248,7 +250,7 @@ static int umsch_mm_v4_0_ring_stop(struct amdgpu_umsch_mm *umsch)
 	data = REG_SET_FIELD(data, VCN_UMSCH_RB_DB_CTRL, EN, 0);
 	WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_DB_CTRL, data);
 
-	if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+	if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
 		WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
 			2 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
 		SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -271,6 +273,8 @@ static int umsch_mm_v4_0_set_hw_resources(struct amdgpu_umsch_mm *umsch)
 
 	set_hw_resources.vmid_mask_mm_vcn = umsch->vmid_mask_mm_vcn;
 	set_hw_resources.vmid_mask_mm_vpe = umsch->vmid_mask_mm_vpe;
+	set_hw_resources.collaboration_mask_vpe =
+		adev->vpe.collaborate_mode ? 0x3 : 0x0;
 	set_hw_resources.engine_mask = umsch->engine_mask;
 
 	set_hw_resources.vcn0_hqd_mask[0] = umsch->vcn0_hqd_mask;
@@ -346,6 +350,7 @@ static int umsch_mm_v4_0_add_queue(struct amdgpu_umsch_mm *umsch,
 	add_queue.h_queue = input_ptr->h_queue;
 	add_queue.vm_context_cntl = input_ptr->vm_context_cntl;
 	add_queue.is_context_suspended = input_ptr->is_context_suspended;
+	add_queue.collaboration_mode = adev->vpe.collaborate_mode ? 1 : 0;
 
 	add_queue.api_status.api_completion_fence_addr = umsch->ring.fence_drv.gpu_addr;
 	add_queue.api_status.api_completion_fence_value = ++umsch->ring.fence_drv.sync_seq;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 25ba27151ac0..aaceecd558cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -304,7 +304,7 @@ static int vcn_v1_0_resume(void *handle)
  */
 static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[0]->size + 4);
 	uint32_t offset;
 
 	/* cache window 0: fw */
@@ -371,7 +371,7 @@ static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev)
 
 static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[0]->size + 4);
 	uint32_t offset;
 
 	/* cache window 0: fw */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 18794394c5a0..e357d8cf0c01 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -330,7 +330,7 @@ static int vcn_v2_0_resume(void *handle)
  */
 static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[0]->size + 4);
 	uint32_t offset;
 
 	if (amdgpu_sriov_vf(adev))
@@ -386,7 +386,7 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 
 static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirect)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[0]->size + 4);
 	uint32_t offset;
 
 	/* cache window 0: fw */
@@ -1878,7 +1878,7 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev)
 
 		init_table += header->vcn_table_offset;
 
-		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[0]->size + 4);
 
 		MMSCH_V2_0_INSERT_DIRECT_RD_MOD_WT(
 			SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS),
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index aba403d71806..1cd8a94b0fbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -414,13 +414,15 @@ static int vcn_v2_5_resume(void *handle)
  */
 static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size;
 	uint32_t offset;
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+
+		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[i]->size + 4);
 		/* cache window 0: fw */
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
@@ -469,7 +471,7 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
 
 static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[inst_idx]->size + 4);
 	uint32_t offset;
 
 	/* cache window 0: fw */
@@ -1240,7 +1242,7 @@ static int vcn_v2_5_sriov_start(struct amdgpu_device *adev)
 			SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS),
 			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
 
-		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[i]->size + 4);
 		/* mc resume*/
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			MMSCH_V1_0_INSERT_DIRECT_WT(
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index e02af4de521c..8f82fb887e9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -449,7 +449,7 @@ static int vcn_v3_0_resume(void *handle)
  */
 static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[inst]->size + 4);
 	uint32_t offset;
 
 	/* cache window 0: fw */
@@ -499,7 +499,7 @@ static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst)
 
 static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
 {
-	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[inst_idx]->size + 4);
 	uint32_t offset;
 
 	/* cache window 0: fw */
@@ -1332,7 +1332,7 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
 			mmUVD_STATUS),
 			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
 
-		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[i]->size + 4);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			MMSCH_V3_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, i,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 8ab01ae919d2..832d15f7b5f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -382,7 +382,7 @@ static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst)
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
@@ -442,7 +442,7 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 {
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst_idx]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
@@ -1289,7 +1289,7 @@ static int vcn_v4_0_start_sriov(struct amdgpu_device *adev)
 			regUVD_STATUS),
 			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
 
-		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[i]->size + 4);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			MMSCH_V4_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, i,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 810bbfccd6f2..203fa988322b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -332,7 +332,7 @@ static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx)
 	uint32_t offset, size, vcn_inst;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst_idx]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	vcn_inst = GET_INST(VCN, inst_idx);
@@ -407,7 +407,7 @@ static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst_idx]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
@@ -894,7 +894,7 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev)
 		MMSCH_V4_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCN, 0, regUVD_STATUS),
 			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
 
-		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw[i]->size + 4);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			MMSCH_V4_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 0468955338b7..501e53e69f2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -45,7 +45,7 @@
 #define mmUVD_DPG_LMA_DATA_BASE_IDX					regUVD_DPG_LMA_DATA_BASE_IDX
 
 #define VCN_VID_SOC_ADDRESS_2_0						0x1fb00
-#define VCN1_VID_SOC_ADDRESS_3_0					0x48300
+#define VCN1_VID_SOC_ADDRESS_3_0					(0x48300 + 0x38000)
 
 #define VCN_HARVEST_MMSCH							0
 
@@ -329,7 +329,7 @@ static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst)
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
@@ -390,7 +390,7 @@ static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst_idx]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
@@ -486,7 +486,8 @@ static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 
 	/* VCN global tiling registers */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
-		VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+		VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG),
+		adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
 /**
@@ -911,7 +912,6 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
 		VCN, inst_idx, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-
 	if (indirect)
 		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index d6ee9958ba5f..bc60c554eb32 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -290,7 +290,7 @@ static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst)
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
@@ -351,7 +351,7 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i
 	uint32_t offset, size;
 	const struct common_firmware_header *hdr;
 
-	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+	hdr = (const struct common_firmware_header *)adev->vcn.fw[inst_idx]->data;
 	size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	/* cache window 0: fw */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index dfa8c69532d4..55aa74cbc532 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -779,8 +779,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp,
 	 * nodes, but not more than args->num_of_nodes as that is
 	 * the amount of memory allocated by user
 	 */
-	pa = kzalloc((sizeof(struct kfd_process_device_apertures) *
-				args->num_of_nodes), GFP_KERNEL);
+	pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures),
+		     GFP_KERNEL);
 	if (!pa)
 		return -ENOMEM;
 
@@ -1523,7 +1523,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep,
 
 	/* Find a KFD GPU device that supports the get_dmabuf_info query */
 	for (i = 0; kfd_topology_enum_kfd_devices(i, &dev) == 0; i++)
-		if (dev)
+		if (dev && !kfd_devcgroup_check_permission(dev))
 			break;
 	if (!dev)
 		return -EINVAL;
@@ -1545,7 +1545,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep,
 	if (xcp_id >= 0)
 		args->gpu_id = dmabuf_adev->kfd.dev->nodes[xcp_id]->id;
 	else
-		args->gpu_id = dmabuf_adev->kfd.dev->nodes[0]->id;
+		args->gpu_id = dev->id;
 	args->flags = flags;
 
 	/* Copy metadata buffer to user mode */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 041ec3de55e7..719d6d365e15 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -960,7 +960,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 	struct kfd_node *node;
 	int i;
-	int count;
 
 	if (!kfd->init_complete)
 		return;
@@ -968,12 +967,10 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 	/* for runtime suspend, skip locking kfd */
 	if (!run_pm) {
 		mutex_lock(&kfd_processes_mutex);
-		count = ++kfd_locked;
-		mutex_unlock(&kfd_processes_mutex);
-
 		/* For first KFD device suspend all the KFD processes */
-		if (count == 1)
+		if (++kfd_locked == 1)
 			kfd_suspend_all_processes();
+		mutex_unlock(&kfd_processes_mutex);
 	}
 
 	for (i = 0; i < kfd->num_nodes; i++) {
@@ -984,7 +981,7 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
-	int ret, count, i;
+	int ret, i;
 
 	if (!kfd->init_complete)
 		return 0;
@@ -998,12 +995,10 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 	/* for runtime resume, skip unlocking kfd */
 	if (!run_pm) {
 		mutex_lock(&kfd_processes_mutex);
-		count = --kfd_locked;
-		mutex_unlock(&kfd_processes_mutex);
-
-		WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
-		if (count == 0)
+		if (--kfd_locked == 0)
 			ret = kfd_resume_all_processes();
+		WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error");
+		mutex_unlock(&kfd_processes_mutex);
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f4d395e38683..0b655555e167 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2001,6 +2001,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 		dev_err(dev, "HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n");
 		while (halt_if_hws_hang)
 			schedule();
+		kfd_hws_hang(dqm);
 		return -ETIME;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
index 9a06c6fb6605..40a21be6c07c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
@@ -339,7 +339,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev,
 				break;
 			}
 			kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23);
-		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+			   KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_DEBUG_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
index 7e2859736a55..fe2ad0c0de95 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
@@ -328,7 +328,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev,
 		/* CP */
 		if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
 			kfd_signal_event_interrupt(pasid, context_id0, 32);
-		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
+		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+			 KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)))
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_CTXID0_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 91dd5e045b51..c4c6a29052ac 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -388,7 +388,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
 				break;
 			}
 			kfd_signal_event_interrupt(pasid, sq_int_data, 24);
-		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+		} else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+			   KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_DEBUG_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 42d40560cd30..a81ef232fdef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1473,7 +1473,7 @@ static inline void kfd_flush_tlb(struct kfd_process_device *pdd,
 
 static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
 {
-	return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) ||
+	return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) ||
 	       (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
 	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 717a60d7a4ea..b79986412cd8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -819,9 +819,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	mutex_lock(&kfd_processes_mutex);
 
 	if (kfd_is_locked()) {
-		mutex_unlock(&kfd_processes_mutex);
 		pr_debug("KFD is locked! Cannot create process");
-		return ERR_PTR(-EINVAL);
+		process = ERR_PTR(-EINVAL);
+		goto out;
 	}
 
 	/* A prior open of /dev/kfd could have already created the process. */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1c9c6096e28f..6d2f60c61dec 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -148,6 +148,9 @@ MODULE_FIRMWARE(FIRMWARE_NAVI12_DMCU);
 #define FIRMWARE_DCN_35_DMUB "amdgpu/dcn_3_5_dmcub.bin"
 MODULE_FIRMWARE(FIRMWARE_DCN_35_DMUB);
 
+#define FIRMWARE_DCN_351_DMUB "amdgpu/dcn_3_5_1_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_DCN_351_DMUB);
+
 /* Number of bytes in PSP header for firmware. */
 #define PSP_HEADER_BYTES 0x100
 
@@ -1767,6 +1770,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_dc_debug_mask & DC_FORCE_SUBVP_MCLK_SWITCH)
 		adev->dm.dc->debug.force_subvp_mclk_switch = true;
 
+	if (amdgpu_dc_debug_mask & DC_ENABLE_DML2)
+		adev->dm.dc->debug.using_dml2 = true;
+
 	adev->dm.dc->debug.visual_confirm = amdgpu_dc_visual_confirm;
 
 	/* TODO: Remove after DP2 receiver gets proper support of Cable ID feature */
@@ -3041,6 +3047,10 @@ static int dm_resume(void *handle)
 	/* Do mst topology probing after resuming cached state*/
 	drm_connector_list_iter_begin(ddev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
+
+		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+			continue;
+
 		aconnector = to_amdgpu_dm_connector(connector);
 		if (aconnector->dc_link->type != dc_connection_mst_branch ||
 		    aconnector->mst_root)
@@ -4817,9 +4827,11 @@ static int dm_init_microcode(struct amdgpu_device *adev)
 		fw_name_dmub = FIRMWARE_DCN_V3_2_1_DMCUB;
 		break;
 	case IP_VERSION(3, 5, 0):
-	case IP_VERSION(3, 5, 1):
 		fw_name_dmub = FIRMWARE_DCN_35_DMUB;
 		break;
+	case IP_VERSION(3, 5, 1):
+		fw_name_dmub = FIRMWARE_DCN_351_DMUB;
+		break;
 	default:
 		/* ASIC doesn't support DMUB. */
 		return 0;
@@ -5918,6 +5930,9 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector,
 		&aconnector->base.probed_modes :
 		&aconnector->base.modes;
 
+	if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+		return NULL;
+
 	if (aconnector->freesync_vid_base.clock != 0)
 		return &aconnector->freesync_vid_base;
 
@@ -6302,27 +6317,22 @@ create_stream_for_sink(struct drm_connector *connector,
 
 	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
-	else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
-			 stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
-			 stream->signal == SIGNAL_TYPE_EDP) {
+
+	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
+	    stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+	    stream->signal == SIGNAL_TYPE_EDP) {
 		//
 		// should decide stream support vsc sdp colorimetry capability
 		// before building vsc info packet
 		//
-		stream->use_vsc_sdp_for_colorimetry = false;
-		if (aconnector->dc_sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
-			stream->use_vsc_sdp_for_colorimetry =
-				aconnector->dc_sink->is_vsc_sdp_colorimetry_supported;
-		} else {
-			if (stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED)
-				stream->use_vsc_sdp_for_colorimetry = true;
-		}
+		stream->use_vsc_sdp_for_colorimetry = stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 &&
+						      stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED;
+
 		if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
+		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
-		if (stream->link->psr_settings.psr_feature_enabled)
-			aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 	}
 finish:
 	dc_sink_release(sink);
@@ -8761,10 +8771,10 @@ static void amdgpu_dm_commit_audio(struct drm_device *dev,
 		if (!drm_atomic_crtc_needs_modeset(new_crtc_state))
 			continue;
 
+notify:
 		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
 			continue;
 
-notify:
 		aconnector = to_amdgpu_dm_connector(connector);
 
 		mutex_lock(&adev->dm.audio_lock);
@@ -11271,18 +11281,24 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 	if (!adev->dm.freesync_module)
 		goto update;
 
-	if (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT
-		|| sink->sink_signal == SIGNAL_TYPE_EDP) {
+	if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT ||
+		     sink->sink_signal == SIGNAL_TYPE_EDP)) {
 		bool edid_check_required = false;
 
-		if (edid) {
-			edid_check_required = is_dp_capable_without_timing_msa(
-						adev->dm.dc,
-						amdgpu_dm_connector);
+		if (is_dp_capable_without_timing_msa(adev->dm.dc,
+						     amdgpu_dm_connector)) {
+			if (edid->features & DRM_EDID_FEATURE_CONTINUOUS_FREQ) {
+				freesync_capable = true;
+				amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq;
+				amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq;
+			} else {
+				edid_check_required = edid->version > 1 ||
+						      (edid->version == 1 &&
+						       edid->revision > 1);
+			}
 		}
 
-		if (edid_check_required == true && (edid->version > 1 ||
-		   (edid->version == 1 && edid->revision > 1))) {
+		if (edid_check_required) {
 			for (i = 0; i < 4; i++) {
 
 				timing	= &edid->detailed_timings[i];
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 1f08c6564c3b..286ecd28cc6e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -141,9 +141,8 @@ bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)
  * amdgpu_dm_psr_enable() - enable psr f/w
  * @stream: stream state
  *
- * Return: true if success
  */
-bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
+void amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 {
 	struct dc_link *link = stream->link;
 	unsigned int vsync_rate_hz = 0;
@@ -190,7 +189,10 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 	if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1)
 		power_opt |= psr_power_opt_z10_static_screen;
 
-	return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
+	dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
+
+	if (link->ctx->dc->caps.ips_support)
+		dc_allow_idle_optimizations(link->ctx->dc, true);
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
index 6806b3c9c84b..1fdfd183c0d9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
@@ -32,7 +32,7 @@
 #define AMDGPU_DM_PSR_ENTRY_DELAY 5
 
 void amdgpu_dm_set_psr_caps(struct dc_link *link);
-bool amdgpu_dm_psr_enable(struct dc_stream_state *stream);
+void amdgpu_dm_psr_enable(struct dc_stream_state *stream);
 bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream);
 bool amdgpu_dm_psr_disable(struct dc_stream_state *stream);
 bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
index 16e72d623630..08c494a7a21b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
@@ -76,10 +76,8 @@ static int amdgpu_dm_wb_encoder_atomic_check(struct drm_encoder *encoder,
 
 static int amdgpu_dm_wb_connector_get_modes(struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
-
-	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
-				    dev->mode_config.max_height);
+	/* Maximum resolution supported by DWB */
+	return drm_add_modes_noedid(connector, 3840, 2160);
 }
 
 static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
index 12f3e8aa46d8..6ad4f4efec5d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
@@ -99,20 +99,25 @@ static int dcn316_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
+static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context,
+		bool safe_to_lower, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
 
 	for (i = 0; i < dc->res_pool->pipe_count; ++i) {
-		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe = safe_to_lower
+			? &context->res_ctx.pipe_ctx[i]
+			: &dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe->top_pipe || pipe->prev_odm_pipe)
 			continue;
-		if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL ||
-				     dc_is_virtual_signal(pipe->stream->signal))) {
+		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) ||
+				     !pipe->stream->link_enc)) {
 			if (disable) {
-				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
+				if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc)
+					pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
+
 				reset_sync_context_for_pipe(dc, context, i);
 			} else
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
@@ -207,11 +212,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn316_disable_otg_wa(clk_mgr_base, context, true);
+		dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn316_disable_otg_wa(clk_mgr_base, context, false);
+		dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index 668f05c8654e..bec252e1dd27 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -216,6 +216,16 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
 	if (clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz > 1950)
 		clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = 1950;
 
+	/* DPPCLK */
+	dcn32_init_single_clock(clk_mgr, PPCLK_DPPCLK,
+			&clk_mgr_base->bw_params->clk_table.entries[0].dppclk_mhz,
+			&num_entries_per_clk->num_dppclk_levels);
+	num_levels = num_entries_per_clk->num_dppclk_levels;
+	clk_mgr_base->bw_params->dc_mode_limit.dppclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DPPCLK);
+	//HW recommends limit of 1950 MHz in display clock for all DCN3.2.x
+	if (clk_mgr_base->bw_params->dc_mode_limit.dppclk_mhz > 1950)
+		clk_mgr_base->bw_params->dc_mode_limit.dppclk_mhz = 1950;
+
 	if (num_entries_per_clk->num_dcfclk_levels &&
 			num_entries_per_clk->num_dtbclk_levels &&
 			num_entries_per_clk->num_dispclk_levels)
@@ -240,6 +250,10 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
 					= khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_dpp_clk_khz);
 	}
 
+	for (i = 0; i < num_levels; i++)
+		if (clk_mgr_base->bw_params->clk_table.entries[i].dppclk_mhz > 1950)
+			clk_mgr_base->bw_params->clk_table.entries[i].dppclk_mhz = 1950;
+
 	/* Get UCLK, update bounding box */
 	clk_mgr_base->funcs->get_memclk_states_from_smu(clk_mgr_base);
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index c378b879c76d..d9c5692c86c2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -73,6 +73,14 @@
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK		0x00000007L
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK		0x000F0000L
 
+#define regCLK5_0_CLK5_spll_field_8				0x464b
+#define regCLK5_0_CLK5_spll_field_8_BASE_IDX	0
+
+#define CLK5_0_CLK5_spll_field_8__spll_ssc_en__SHIFT	0xd
+#define CLK5_0_CLK5_spll_field_8__spll_ssc_en_MASK		0x00002000L
+
+#define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0
+
 #define REG(reg_name) \
 	(ctx->clk_reg_offsets[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
 
@@ -409,11 +417,25 @@ static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs
 {
 }
 
+static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	struct dc_context *ctx = clk_mgr->base.ctx;
+	uint32_t ssc_enable;
+
+	REG_GET(CLK5_0_CLK5_spll_field_8, spll_ssc_en, &ssc_enable);
+
+	return ssc_enable == 1;
+}
+
 static void init_clk_states(struct clk_mgr *clk_mgr)
 {
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
 	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
 	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
 
+	if (clk_mgr_int->smu_ver >= SMU_VER_THRESHOLD)
+		clk_mgr->clks.dtbclk_en = true; // request DTBCLK disable on first commit
 	clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk;	// restore ref_dtbclk
 	clk_mgr->clks.p_state_change_support = true;
 	clk_mgr->clks.prev_p_state_change_support = true;
@@ -423,7 +445,16 @@ static void init_clk_states(struct clk_mgr *clk_mgr)
 
 void dcn35_init_clocks(struct clk_mgr *clk_mgr)
 {
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
 	init_clk_states(clk_mgr);
+
+	// to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk
+	if (dcn35_is_spll_ssc_enabled(clk_mgr))
+		clk_mgr->dp_dto_source_clock_in_khz =
+			dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
+	else
+		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+
 }
 static struct clk_bw_params dcn35_bw_params = {
 	.vram_type = Ddr4MemType,
@@ -512,6 +543,28 @@ static DpmClocks_t_dcn35 dummy_clocks;
 
 static struct dcn35_watermarks dummy_wms = { 0 };
 
+static struct dcn35_ss_info_table ss_info_table = {
+	.ss_divider = 1000,
+	.ss_percentage = {0, 0, 375, 375, 375}
+};
+
+static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
+{
+	struct dc_context *ctx = clk_mgr->base.ctx;
+	uint32_t clock_source;
+
+	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
+	// If it's DFS mode, clock_source is 0.
+	if (dcn35_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) {
+		clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
+
+		if (clk_mgr->dprefclk_ss_percentage != 0) {
+			clk_mgr->ss_on_dprefclk = true;
+			clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
+		}
+	}
+}
+
 static void dcn35_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn35_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -709,7 +762,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 		clock_table->NumFclkLevelsEnabled;
 	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
 
-	num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+	num_dcfclk = (clock_table->NumDcfClkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
 		clock_table->NumDcfClkLevelsEnabled;
 	for (i = 0; i < num_dcfclk; i++) {
 		int j;
@@ -1056,6 +1109,8 @@ void dcn35_clk_mgr_construct(
 	dce_clock_read_ss_info(&clk_mgr->base);
 	/*when clk src is from FCH, it could have ss, same clock src as DPREF clk*/
 
+	dcn35_read_ss_info_from_lut(&clk_mgr->base);
+
 	clk_mgr->base.base.bw_params = &dcn35_bw_params;
 
 	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5211c1c0f3c0..03b554e912a2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1302,6 +1302,54 @@ static void disable_vbios_mode_if_required(
 	}
 }
 
+/**
+ * wait_for_blank_complete - wait for all active OPPs to finish pending blank
+ * pattern updates
+ *
+ * @dc: [in] dc reference
+ * @context: [in] hardware context in use
+ */
+static void wait_for_blank_complete(struct dc *dc,
+		struct dc_state *context)
+{
+	struct pipe_ctx *opp_head;
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	if (!hws->funcs.wait_for_blank_complete)
+		return;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		opp_head = &context->res_ctx.pipe_ctx[i];
+
+		if (!resource_is_pipe_type(opp_head, OPP_HEAD) ||
+				dc_state_get_pipe_subvp_type(context, opp_head) == SUBVP_PHANTOM)
+			continue;
+
+		hws->funcs.wait_for_blank_complete(opp_head->stream_res.opp);
+	}
+}
+
+static void wait_for_odm_update_pending_complete(struct dc *dc, struct dc_state *context)
+{
+	struct pipe_ctx *otg_master;
+	struct timing_generator *tg;
+	int i;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		otg_master = &context->res_ctx.pipe_ctx[i];
+		if (!resource_is_pipe_type(otg_master, OTG_MASTER) ||
+				dc_state_get_pipe_subvp_type(context, otg_master) == SUBVP_PHANTOM)
+			continue;
+		tg = otg_master->stream_res.tg;
+		if (tg->funcs->wait_odm_doublebuffer_pending_clear)
+			tg->funcs->wait_odm_doublebuffer_pending_clear(tg);
+	}
+
+	/* ODM update may require to reprogram blank pattern for each OPP */
+	wait_for_blank_complete(dc, context);
+}
+
 static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context)
 {
 	int i;
@@ -1993,6 +2041,11 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 		context->stream_count == 0) {
 		/* Must wait for no flips to be pending before doing optimize bw */
 		wait_for_no_pipes_pending(dc, context);
+		/*
+		 * optimized dispclk depends on ODM setup. Need to wait for ODM
+		 * update pending complete before optimizing bandwidth.
+		 */
+		wait_for_odm_update_pending_complete(dc, context);
 		/* pplib is notified if disp_num changed */
 		dc->hwss.optimize_bandwidth(dc, context);
 		/* Need to do otg sync again as otg could be out of sync due to otg
@@ -2971,7 +3024,8 @@ static void backup_planes_and_stream_state(
 		scratch->blend_tf[i] = *status->plane_states[i]->blend_tf;
 	}
 	scratch->stream_state = *stream;
-	scratch->out_transfer_func = *stream->out_transfer_func;
+	if (stream->out_transfer_func)
+		scratch->out_transfer_func = *stream->out_transfer_func;
 }
 
 static void restore_planes_and_stream_state(
@@ -2993,7 +3047,8 @@ static void restore_planes_and_stream_state(
 		*status->plane_states[i]->blend_tf = scratch->blend_tf[i];
 	}
 	*stream = scratch->stream_state;
-	*stream->out_transfer_func = scratch->out_transfer_func;
+	if (stream->out_transfer_func)
+		*stream->out_transfer_func = scratch->out_transfer_func;
 }
 
 static bool update_planes_and_stream_state(struct dc *dc,
@@ -3270,6 +3325,9 @@ static bool dc_dmub_should_send_dirty_rect_cmd(struct dc *dc, struct dc_stream_s
 	if (stream->link->replay_settings.config.replay_supported)
 		return true;
 
+	if (stream->ctx->dce_version >= DCN_VERSION_3_5 && stream->abm_level)
+		return true;
+
 	return false;
 }
 
@@ -3493,7 +3551,7 @@ static void commit_planes_for_stream_fast(struct dc *dc,
 		top_pipe_to_program->stream->update_flags.raw = 0;
 }
 
-static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context)
+static void wait_for_outstanding_hw_updates(struct dc *dc, struct dc_state *dc_context)
 {
 /*
  * This function calls HWSS to wait for any potentially double buffered
@@ -3531,6 +3589,7 @@ static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state
 			}
 		}
 	}
+	wait_for_odm_update_pending_complete(dc, dc_context);
 }
 
 static void commit_planes_for_stream(struct dc *dc,
@@ -4844,22 +4903,16 @@ void dc_exit_ips_for_hw_access(struct dc *dc)
 
 bool dc_dmub_is_ips_idle_state(struct dc *dc)
 {
-	uint32_t idle_state = 0;
-
 	if (dc->debug.disable_idle_power_optimizations)
 		return false;
 
 	if (!dc->caps.ips_support || (dc->config.disable_ips == DMUB_IPS_DISABLE_ALL))
 		return false;
 
-	if (dc->hwss.get_idle_state)
-		idle_state = dc->hwss.get_idle_state(dc);
-
-	if (!(idle_state & DMUB_IPS1_ALLOW_MASK) ||
-		!(idle_state & DMUB_IPS2_ALLOW_MASK))
-		return true;
+	if (!dc->ctx->dmub_srv)
+		return false;
 
-	return false;
+	return dc->ctx->dmub_srv->idle_allowed;
 }
 
 /* set min and max memory clock to lowest and highest DPM level, respectively */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 180ac47868c2..61986e5cb491 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -334,7 +334,8 @@ static void dc_state_free(struct kref *kref)
 
 void dc_state_release(struct dc_state *state)
 {
-	kref_put(&state->refcount, dc_state_free);
+	if (state != NULL)
+		kref_put(&state->refcount, dc_state_free);
 }
 /*
  * dc_state_add_stream() - Add a new dc_stream_state to a dc_state.
@@ -435,6 +436,15 @@ bool dc_state_add_plane(
 		goto out;
 	}
 
+	if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm)
+		/* ODM combine could prevent us from supporting more planes
+		 * we will reset ODM slice count back to 1 when all planes have
+		 * been removed to maximize the amount of planes supported when
+		 * new planes are added.
+		 */
+		resource_update_pipes_for_stream_with_slice_count(
+				state, dc->current_state, dc->res_pool, stream, 1);
+
 	otg_master_pipe = resource_get_otg_master_for_stream(
 			&state->res_ctx, stream);
 	if (otg_master_pipe)
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 9900dda2eef5..be2ac5c442a4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1085,9 +1085,9 @@ struct replay_settings {
 	/* SMU optimization is enabled */
 	bool replay_smu_opt_enable;
 	/* Current Coasting vtotal */
-	uint16_t coasting_vtotal;
+	uint32_t coasting_vtotal;
 	/* Coasting vtotal table */
-	uint16_t coasting_vtotal_table[PR_COASTING_TYPE_NUM];
+	uint32_t coasting_vtotal_table[PR_COASTING_TYPE_NUM];
 	/* Maximum link off frame count */
 	enum replay_link_off_frame_count_level link_off_frame_count_level;
 	/* Replay pseudo vtotal for abm + ips on full screen video which can improve ips residency */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 970644b695cd..b5e0289d2fe8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -976,7 +976,10 @@ static bool dcn31_program_pix_clk(
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 	enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24;
 
-	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+	// Apply ssed(spread spectrum) dpref clock for edp only.
+	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0
+		&& pix_clk_params->signal_type == SIGNAL_TYPE_EDP
+		&& encoding == DP_8b_10b_ENCODING)
 		dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
 	// For these signal types Driver to program DP_DTO without calling VBIOS Command table
 	if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) {
@@ -1093,9 +1096,6 @@ static bool get_pixel_clk_frequency_100hz(
 	unsigned int modulo_hz = 0;
 	unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz;
 
-	if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
-		dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
-
 	if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) {
 		clock_hz = REG_READ(PHASE[inst]);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/Makefile b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
index f0777d61c2cb..c307f040e48f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
@@ -23,7 +23,7 @@
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
-CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = -Wno-override-init
 
 DCE110 = dce110_timing_generator.o \
 dce110_compressor.o dce110_opp_regamma_v.o \
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/Makefile b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
index 7e92effec894..683866797709 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
@@ -23,7 +23,7 @@
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
-CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = -Wno-override-init
 
 DCE112 = dce112_compressor.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/Makefile b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
index 1e3ef68a452a..8f508e662748 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
@@ -24,7 +24,7 @@
 # It provides the control and status of HW CRTC block.
 
 
-CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = -Wno-override-init
 
 DCE120 = dce120_timing_generator.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/Makefile b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
index fee331accc0e..eede83ad91fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dce60/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
@@ -23,7 +23,7 @@
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
-CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = -Wno-override-init
 
 DCE60 = dce60_timing_generator.o dce60_hw_sequencer.o \
 	dce60_resource.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/Makefile b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
index 7eefffbdc925..fba189d26652 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
@@ -23,7 +23,7 @@
 # Makefile for the 'controller' sub-component of DAL.
 # It provides the control and status of HW CRTC block.
 
-CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = -Wno-override-init
 
 DCE80 = dce80_timing_generator.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
index 48a40dcc7050..5838a11efd00 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -384,6 +384,7 @@ static const struct opp_funcs dcn10_opp_funcs = {
 		.opp_set_disp_pattern_generator = NULL,
 		.opp_program_dpg_dimensions = NULL,
 		.dpg_is_blanked = NULL,
+		.dpg_is_pending = NULL,
 		.opp_destroy = opp1_destroy
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
index 0784d0198661..fbf1b6370eb2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
@@ -337,6 +337,19 @@ bool opp2_dpg_is_blanked(struct output_pixel_processor *opp)
 		(double_buffer_pending == 0);
 }
 
+bool opp2_dpg_is_pending(struct output_pixel_processor *opp)
+{
+	struct dcn20_opp *oppn20 = TO_DCN20_OPP(opp);
+	uint32_t double_buffer_pending;
+	uint32_t dpg_en;
+
+	REG_GET(DPG_CONTROL, DPG_EN, &dpg_en);
+
+	REG_GET(DPG_STATUS, DPG_DOUBLE_BUFFER_PENDING, &double_buffer_pending);
+
+	return (dpg_en == 1 && double_buffer_pending == 1);
+}
+
 void opp2_program_left_edge_extra_pixel (
 		struct output_pixel_processor *opp,
 		bool count)
@@ -363,6 +376,7 @@ static struct opp_funcs dcn20_opp_funcs = {
 		.opp_set_disp_pattern_generator = opp2_set_disp_pattern_generator,
 		.opp_program_dpg_dimensions = opp2_program_dpg_dimensions,
 		.dpg_is_blanked = opp2_dpg_is_blanked,
+		.dpg_is_pending = opp2_dpg_is_pending,
 		.opp_dpg_set_blank_color = opp2_dpg_set_blank_color,
 		.opp_destroy = opp1_destroy,
 		.opp_program_left_edge_extra_pixel = opp2_program_left_edge_extra_pixel,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
index 3ab221bdd27d..8f186abd558d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
@@ -159,6 +159,8 @@ void opp2_program_dpg_dimensions(
 
 bool opp2_dpg_is_blanked(struct output_pixel_processor *opp);
 
+bool opp2_dpg_is_pending(struct output_pixel_processor *opp);
+
 void opp2_dpg_set_blank_color(
 		struct output_pixel_processor *opp,
 		const struct tg_color *color);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c
index 8e77db46a409..6a71ba3dfc63 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c
@@ -50,6 +50,7 @@ static struct opp_funcs dcn201_opp_funcs = {
 		.opp_set_disp_pattern_generator = opp2_set_disp_pattern_generator,
 		.opp_program_dpg_dimensions = opp2_program_dpg_dimensions,
 		.dpg_is_blanked = opp2_dpg_is_blanked,
+		.dpg_is_pending = opp2_dpg_is_pending,
 		.opp_dpg_set_blank_color = opp2_dpg_set_blank_color,
 		.opp_destroy = opp1_destroy,
 		.opp_program_left_edge_extra_pixel = opp2_program_left_edge_extra_pixel,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
index bf3386cd444d..5ebb57303130 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@@ -44,6 +44,36 @@
 #define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
 
 
+void mpc3_mpc_init(struct mpc *mpc)
+{
+	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
+	int opp_id;
+
+	mpc1_mpc_init(mpc);
+
+	for (opp_id = 0; opp_id < MAX_OPP; opp_id++) {
+		if (REG(MUX[opp_id]))
+			/* disable mpc out rate and flow control */
+			REG_UPDATE_2(MUX[opp_id], MPC_OUT_RATE_CONTROL_DISABLE,
+					1, MPC_OUT_FLOW_CONTROL_COUNT, 0);
+	}
+}
+
+void mpc3_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id)
+{
+	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
+
+	mpc1_mpc_init_single_inst(mpc, mpcc_id);
+
+	/* assuming mpc out mux is connected to opp with the same index at this
+	 * point in time (e.g. transitioning from vbios to driver)
+	 */
+	if (mpcc_id < MAX_OPP && REG(MUX[mpcc_id]))
+		/* disable mpc out rate and flow control */
+		REG_UPDATE_2(MUX[mpcc_id], MPC_OUT_RATE_CONTROL_DISABLE,
+				1, MPC_OUT_FLOW_CONTROL_COUNT, 0);
+}
+
 bool mpc3_is_dwb_idle(
 	struct mpc *mpc,
 	int dwb_id)
@@ -80,25 +110,6 @@ void mpc3_disable_dwb_mux(
 		MPC_DWB0_MUX, 0xf);
 }
 
-void mpc3_set_out_rate_control(
-	struct mpc *mpc,
-	int opp_id,
-	bool enable,
-	bool rate_2x_mode,
-	struct mpc_dwb_flow_control *flow_control)
-{
-	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
-
-	REG_UPDATE_2(MUX[opp_id],
-			MPC_OUT_RATE_CONTROL_DISABLE, !enable,
-			MPC_OUT_RATE_CONTROL, rate_2x_mode);
-
-	if (flow_control)
-		REG_UPDATE_2(MUX[opp_id],
-			MPC_OUT_FLOW_CONTROL_MODE, flow_control->flow_ctrl_mode,
-			MPC_OUT_FLOW_CONTROL_COUNT, flow_control->flow_ctrl_cnt1);
-}
-
 enum dc_lut_mode mpc3_get_ogam_current(struct mpc *mpc, int mpcc_id)
 {
 	/*Contrary to DCN2 and DCN1 wherein a single status register field holds this info;
@@ -1490,8 +1501,8 @@ static const struct mpc_funcs dcn30_mpc_funcs = {
 	.read_mpcc_state = mpc3_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
-	.mpc_init = mpc1_mpc_init,
-	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
+	.mpc_init = mpc3_mpc_init,
+	.mpc_init_single_inst = mpc3_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
 	.cursor_lock = mpc1_cursor_lock,
 	.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
@@ -1508,7 +1519,6 @@ static const struct mpc_funcs dcn30_mpc_funcs = {
 	.set_dwb_mux = mpc3_set_dwb_mux,
 	.disable_dwb_mux = mpc3_disable_dwb_mux,
 	.is_dwb_idle = mpc3_is_dwb_idle,
-	.set_out_rate_control = mpc3_set_out_rate_control,
 	.set_gamut_remap = mpc3_set_gamut_remap,
 	.program_shaper = mpc3_program_shaper,
 	.acquire_rmu = mpcc3_acquire_rmu,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
index 9cb96ae95a2f..ce93003dae01 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
@@ -1007,6 +1007,13 @@ void dcn30_mpc_construct(struct dcn30_mpc *mpc30,
 	int num_mpcc,
 	int num_rmu);
 
+void mpc3_mpc_init(
+	struct mpc *mpc);
+
+void mpc3_mpc_init_single_inst(
+	struct mpc *mpc,
+	unsigned int mpcc_id);
+
 bool mpc3_program_shaper(
 		struct mpc *mpc,
 		const struct pwl_params *params,
@@ -1078,13 +1085,6 @@ bool mpc3_is_dwb_idle(
 	struct mpc *mpc,
 	int dwb_id);
 
-void mpc3_set_out_rate_control(
-	struct mpc *mpc,
-	int opp_id,
-	bool enable,
-	bool rate_2x_mode,
-	struct mpc_dwb_flow_control *flow_control);
-
 void mpc3_power_on_ogam_lut(
 	struct mpc *mpc, int mpcc_id,
 	bool power_on);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
index e224a028d68a..8a0460e86309 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
@@ -248,14 +248,12 @@ void dcn32_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
-
-	enc10->base.features = *enc_features;
 	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
 		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
+	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
+
+	enc10->base.features = *enc_features;
 
 	enc10->base.transmitter = init_data->transmitter;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
index e789e654c387..e408e859b355 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
@@ -47,7 +47,7 @@ void mpc32_mpc_init(struct mpc *mpc)
 	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
 	int mpcc_id;
 
-	mpc1_mpc_init(mpc);
+	mpc3_mpc_init(mpc);
 
 	if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) {
 		if (mpc30->mpc_mask->MPCC_MCM_SHAPER_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPCC_MCM_3DLUT_MEM_LOW_PWR_MODE) {
@@ -991,7 +991,7 @@ static const struct mpc_funcs dcn32_mpc_funcs = {
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
 	.mpc_init = mpc32_mpc_init,
-	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
+	.mpc_init_single_inst = mpc3_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
 	.cursor_lock = mpc1_cursor_lock,
 	.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
@@ -1008,7 +1008,6 @@ static const struct mpc_funcs dcn32_mpc_funcs = {
 	.set_dwb_mux = mpc3_set_dwb_mux,
 	.disable_dwb_mux = mpc3_disable_dwb_mux,
 	.is_dwb_idle = mpc3_is_dwb_idle,
-	.set_out_rate_control = mpc3_set_out_rate_control,
 	.set_gamut_remap = mpc3_set_gamut_remap,
 	.program_shaper = mpc32_program_shaper,
 	.program_3dlut = mpc32_program_3dlut,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index 87760600e154..f98def6c8c2d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -782,3 +782,9 @@ void dcn32_update_dml_pipes_odm_policy_based_on_context(struct dc *dc, struct dc
 		pipe_cnt++;
 	}
 }
+
+void dcn32_override_min_req_dcfclk(struct dc *dc, struct dc_state *context)
+{
+	if (dcn32_subvp_in_use(dc, context) && context->bw_ctx.bw.dcn.clk.dcfclk_khz <= MIN_SUBVP_DCFCLK_KHZ)
+		context->bw_ctx.bw.dcn.clk.dcfclk_khz = MIN_SUBVP_DCFCLK_KHZ;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
index 81e349d5835b..da94e5309fba 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
@@ -184,6 +184,8 @@ void dcn35_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
@@ -238,8 +240,6 @@ void dcn35_link_encoder_construct(
 	}
 
 	enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	if (bp_funcs->get_connector_speed_cap_info)
 		result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index b49e1dc9d8ba..a0a65e099104 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -623,6 +623,7 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc,
 		 * - Not TMZ surface
 		 */
 		if (pipe->plane_state && !pipe->top_pipe && !dcn32_is_center_timing(pipe) &&
+				!(pipe->stream->timing.pix_clk_100hz / 10000 > DCN3_2_MAX_SUBVP_PIXEL_RATE_MHZ) &&
 				(!dcn32_is_psr_capable(pipe) || (context->stream_count == 1 && dc->caps.dmub_caps.subvp_psr)) &&
 				dc_state_get_pipe_subvp_type(context, pipe) == SUBVP_NONE &&
 				(refresh_rate < 120 || dcn32_allow_subvp_high_refresh_rate(dc, context, pipe)) &&
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 80bebfc268db..21e0eef3269b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -166,8 +166,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 	.num_states = 5,
 	.sr_exit_time_us = 28.0,
 	.sr_enter_plus_exit_time_us = 30.0,
-	.sr_exit_z8_time_us = 210.0,
-	.sr_enter_plus_exit_z8_time_us = 320.0,
+	.sr_exit_z8_time_us = 250.0,
+	.sr_enter_plus_exit_z8_time_us = 350.0,
 	.fclk_change_latency_us = 24.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index dc9e1b758ed6..b3ffab77cf88 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -98,55 +98,114 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = {
 	.clock_limits = {
 		{
 			.state = 0,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 400.0,
+			.fabricclk_mhz = 400.0,
+			.socclk_mhz = 600.0,
+			.dram_speed_mts = 3200.0,
+			.dispclk_mhz = 600.0,
+			.dppclk_mhz = 600.0,
 			.phyclk_mhz = 600.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 186.0,
+			.dscclk_mhz = 200.0,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 1,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 600.0,
+			.fabricclk_mhz = 1000.0,
+			.socclk_mhz = 733.0,
+			.dram_speed_mts = 6400.0,
+			.dispclk_mhz = 800.0,
+			.dppclk_mhz = 800.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
+			.dscclk_mhz = 266.7,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 2,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 738.0,
+			.fabricclk_mhz = 1200.0,
+			.socclk_mhz = 880.0,
+			.dram_speed_mts = 7500.0,
+			.dispclk_mhz = 800.0,
+			.dppclk_mhz = 800.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
+			.dscclk_mhz = 266.7,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 3,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
+			.dcfclk_mhz = 800.0,
+			.fabricclk_mhz = 1400.0,
+			.socclk_mhz = 978.0,
+			.dram_speed_mts = 7500.0,
+			.dispclk_mhz = 960.0,
+			.dppclk_mhz = 960.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 371.0,
+			.dscclk_mhz = 320.0,
 			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 4,
+			.dcfclk_mhz = 873.0,
+			.fabricclk_mhz = 1600.0,
+			.socclk_mhz = 1100.0,
+			.dram_speed_mts = 8533.0,
+			.dispclk_mhz = 1066.7,
+			.dppclk_mhz = 1066.7,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 355.6,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 5,
+			.dcfclk_mhz = 960.0,
+			.fabricclk_mhz = 1700.0,
+			.socclk_mhz = 1257.0,
+			.dram_speed_mts = 8533.0,
 			.dispclk_mhz = 1200.0,
 			.dppclk_mhz = 1200.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 417.0,
+			.dscclk_mhz = 400.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 6,
+			.dcfclk_mhz = 1067.0,
+			.fabricclk_mhz = 1850.0,
+			.socclk_mhz = 1257.0,
+			.dram_speed_mts = 8533.0,
+			.dispclk_mhz = 1371.4,
+			.dppclk_mhz = 1371.4,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 457.1,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 7,
+			.dcfclk_mhz = 1200.0,
+			.fabricclk_mhz = 2000.0,
+			.socclk_mhz = 1467.0,
+			.dram_speed_mts = 8533.0,
+			.dispclk_mhz = 1600.0,
+			.dppclk_mhz = 1600.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 533.3,
 			.dtbclk_mhz = 600.0,
 		},
 	},
-	.num_states = 5,
+	.num_states = 8,
 	.sr_exit_time_us = 28.0,
 	.sr_enter_plus_exit_time_us = 30.0,
-	.sr_exit_z8_time_us = 210.0,
-	.sr_enter_plus_exit_z8_time_us = 320.0,
+	.sr_exit_z8_time_us = 250.0,
+	.sr_enter_plus_exit_z8_time_us = 350.0,
 	.fclk_change_latency_us = 24.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
@@ -177,6 +236,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = {
 	.do_urgent_latency_adjustment = 0,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.num_chans = 4,
+	.dram_clock_change_latency_us = 11.72,
+	.dispclk_dppclk_vco_speed_mhz = 2400.0,
 };
 
 /*
@@ -340,6 +402,8 @@ void dcn351_update_bw_bounding_box_fpu(struct dc *dc,
 				clock_limits[i].socclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
 				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
+				clock_limits[i].dtbclk_mhz;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
 				clk_table->num_entries;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
@@ -352,6 +416,8 @@ void dcn351_update_bw_bounding_box_fpu(struct dc *dc,
 				clk_table->num_entries;
 			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
 				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels =
+				clk_table->num_entries;
 		}
 	}
 
@@ -551,6 +617,7 @@ void dcn351_decide_zstate_support(struct dc *dc, struct dc_state *context)
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
 	}
+
 	/*dcn351 does not support z9/z10*/
 	if (context->stream_count == 0 || plane_count == 0) {
 		support = DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY;
@@ -564,11 +631,9 @@ void dcn351_decide_zstate_support(struct dc *dc, struct dc_state *context)
 			dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
 		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
 
-
 		/*for psr1/psr-su, we allow z8 and z10 based on latency, for replay with IPS enabled, it will enter ips2*/
-		 if (is_pwrseq0 && (is_psr || is_replay))
+		if (is_pwrseq0 && (is_psr || is_replay))
 			support = allow_z8 ? allow_z8 : DCN_ZSTATE_SUPPORT_DISALLOW;
-
 	}
 	context->bw_ctx.bw.dcn.clk.zstate_support = support;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 1ba6933d2b36..a20f28a5d2e7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -228,17 +228,13 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s
 		break;
 
 	case dml_project_dcn35:
+	case dml_project_dcn351:
 		out->num_chans = 4;
 		out->round_trip_ping_latency_dcfclk_cycles = 106;
 		out->smn_latency_us = 2;
 		out->dispclk_dppclk_vco_speed_mhz = 3600;
 		break;
 
-	case dml_project_dcn351:
-		out->num_chans = 16;
-		out->round_trip_ping_latency_dcfclk_cycles = 1100;
-		out->smn_latency_us = 2;
-		break;
 	}
 	/* ---Overrides if available--- */
 	if (dml2->config.bbox_overrides.dram_num_chan)
@@ -824,13 +820,25 @@ static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in)
 {
+	dml_uint_t width, height;
+
+	if (in->timing.h_addressable > 3840)
+		width = 3840;
+	else
+		width = in->timing.h_addressable;	// 4K max
+
+	if (in->timing.v_addressable > 2160)
+		height = 2160;
+	else
+		height = in->timing.v_addressable;	// 4K max
+
 	out->CursorBPP[location] = dml_cur_32bit;
 	out->CursorWidth[location] = 256;
 
 	out->GPUVMMinPageSizeKBytes[location] = 256;
 
-	out->ViewportWidth[location] = in->timing.h_addressable;
-	out->ViewportHeight[location] = in->timing.v_addressable;
+	out->ViewportWidth[location] = width;
+	out->ViewportHeight[location] = height;
 	out->ViewportStationary[location] = false;
 	out->ViewportWidthChroma[location] = 0;
 	out->ViewportHeightChroma[location] = 0;
@@ -849,7 +857,7 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned
 	out->HTapsChroma[location] = 0;
 	out->VTapsChroma[location] = 0;
 	out->SourceScan[location] = dml_rotation_0;
-	out->ScalerRecoutWidth[location] = in->timing.h_addressable;
+	out->ScalerRecoutWidth[location] = width;
 
 	out->LBBitPerPixel[location] = 57;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 2a58a7687bdb..72cca367062e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -703,13 +703,8 @@ static inline struct dml2_context *dml2_allocate_memory(void)
 	return (struct dml2_context *) kzalloc(sizeof(struct dml2_context), GFP_KERNEL);
 }
 
-bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
+static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
 {
-	// Allocate Mode Lib Ctx
-	*dml2 = dml2_allocate_memory();
-
-	if (!(*dml2))
-		return false;
 
 	// Store config options
 	(*dml2)->config = *config;
@@ -737,9 +732,18 @@ bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options
 	initialize_dml2_soc_bbox(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc);
 
 	initialize_dml2_soc_states(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc, &(*dml2)->v20.dml_core_ctx.states);
+}
+
+bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2)
+{
+	// Allocate Mode Lib Ctx
+	*dml2 = dml2_allocate_memory();
+
+	if (!(*dml2))
+		return false;
+
+	dml2_init(in_dc, config, dml2);
 
-	/*Initialize DML20 instance which calls dml2_core_create, and core_dcn3_populate_informative*/
-	//dml2_initialize_instance(&(*dml_ctx)->v20.dml_init);
 	return true;
 }
 
@@ -779,3 +783,11 @@ bool dml2_create_copy(struct dml2_context **dst_dml2,
 
 	return true;
 }
+
+void dml2_reinit(const struct dc *in_dc,
+				 const struct dml2_configuration_options *config,
+				 struct dml2_context **dml2)
+{
+
+	dml2_init(in_dc, config, dml2);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
index ee0eb184eb6d..cc662d682fd4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
@@ -214,6 +214,9 @@ void dml2_copy(struct dml2_context *dst_dml2,
 	struct dml2_context *src_dml2);
 bool dml2_create_copy(struct dml2_context **dst_dml2,
 	struct dml2_context *src_dml2);
+void dml2_reinit(const struct dc *in_dc,
+				 const struct dml2_configuration_options *config,
+				 struct dml2_context **dml2);
 
 /*
  * dml2_validate - Determines if a display configuration is supported or not.
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 9d5df4c0da59..0ba1feaf96c0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1185,7 +1185,8 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		if (dccg) {
 			dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
 			dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst);
-			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+			if (dccg && dccg->funcs->set_dtbclk_dto)
+				dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 		}
 	} else if (dccg && dccg->funcs->disable_symclk_se) {
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index c55d5155ecb9..8b3536c380b8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -1498,6 +1498,11 @@ static void dcn20_detect_pipe_changes(struct dc_state *old_state,
 		return;
 	}
 
+	if (resource_is_pipe_type(new_pipe, OTG_MASTER) &&
+			resource_is_odm_topology_changed(new_pipe, old_pipe))
+		/* Detect odm changes */
+		new_pipe->update_flags.bits.odm = 1;
+
 	/* Exit on unchanged, unused pipe */
 	if (!old_pipe->plane_state && !new_pipe->plane_state)
 		return;
@@ -1551,10 +1556,6 @@ static void dcn20_detect_pipe_changes(struct dc_state *old_state,
 
 	/* Detect top pipe only changes */
 	if (resource_is_pipe_type(new_pipe, OTG_MASTER)) {
-		/* Detect odm changes */
-		if (resource_is_odm_topology_changed(new_pipe, old_pipe))
-			new_pipe->update_flags.bits.odm = 1;
-
 		/* Detect global sync changes */
 		if (old_pipe->pipe_dlg_param.vready_offset != new_pipe->pipe_dlg_param.vready_offset
 				|| old_pipe->pipe_dlg_param.vstartup_start != new_pipe->pipe_dlg_param.vstartup_start
@@ -1999,19 +2000,20 @@ void dcn20_program_front_end_for_ctx(
 	DC_LOGGER_INIT(dc->ctx->logger);
 	unsigned int prev_hubp_count = 0;
 	unsigned int hubp_count = 0;
+	struct pipe_ctx *pipe;
 
 	if (resource_is_pipe_topology_changed(dc->current_state, context))
 		resource_log_pipe_topology_update(dc, context);
 
 	if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) {
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+			pipe = &context->res_ctx.pipe_ctx[i];
 
-			if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->plane_state) {
-				ASSERT(!pipe_ctx->plane_state->triplebuffer_flips);
+			if (!pipe->top_pipe && !pipe->prev_odm_pipe && pipe->plane_state) {
+				ASSERT(!pipe->plane_state->triplebuffer_flips);
 				/*turn off triple buffer for full update*/
 				dc->hwss.program_triplebuffer(
-						dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
+						dc, pipe, pipe->plane_state->triplebuffer_flips);
 			}
 		}
 	}
@@ -2085,12 +2087,22 @@ void dcn20_program_front_end_for_ctx(
 			DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
 		}
 
+	/* update ODM for blanked OTG master pipes */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+		if (resource_is_pipe_type(pipe, OTG_MASTER) &&
+				!resource_is_pipe_type(pipe, DPP_PIPE) &&
+				pipe->update_flags.bits.odm &&
+				hws->funcs.update_odm)
+			hws->funcs.update_odm(dc, context, pipe);
+	}
+
 	/*
 	 * Program all updated pipes, order matters for mpcc setup. Start with
 	 * top pipe and program all pipes that follow in order
 	 */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+		pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (pipe->plane_state && !pipe->top_pipe) {
 			while (pipe) {
@@ -2129,17 +2141,6 @@ void dcn20_program_front_end_for_ctx(
 			context->stream_status[0].plane_count > 1) {
 			pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start(pipe->plane_res.hubp);
 		}
-
-		/* when dynamic ODM is active, pipes must be reconfigured when all planes are
-		 * disabled, as some transitions will leave software and hardware state
-		 * mismatched.
-		 */
-		if (dc->debug.enable_single_display_2to1_odm_policy &&
-			pipe->stream &&
-			pipe->update_flags.bits.disable &&
-			!pipe->prev_odm_pipe &&
-			hws->funcs.update_odm)
-			hws->funcs.update_odm(dc, context, pipe);
 	}
 }
 
@@ -2451,7 +2452,7 @@ bool dcn20_wait_for_blank_complete(
 	int counter;
 
 	for (counter = 0; counter < 1000; counter++) {
-		if (opp->funcs->dpg_is_blanked(opp))
+		if (!opp->funcs->dpg_is_pending(opp))
 			break;
 
 		udelay(100);
@@ -2462,7 +2463,7 @@ bool dcn20_wait_for_blank_complete(
 		return false;
 	}
 
-	return true;
+	return opp->funcs->dpg_is_blanked(opp);
 }
 
 bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
index 7e6b7f2a6dc9..8bc3d01537bb 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
@@ -812,10 +812,20 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 	if (pipe_ctx == NULL)
 		return;
 
-	if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL)
+	if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) {
 		pipe_ctx->stream_res.stream_enc->funcs->set_avmute(
 				pipe_ctx->stream_res.stream_enc,
 				enable);
+
+		/* Wait for two frame to make sure AV mute is sent out */
+		if (enable) {
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
+			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+		}
+	}
 }
 
 void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index 3a9cc8ac0c07..093f4387553c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -69,29 +69,6 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
-		int opp_cnt)
-{
-	bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
-	int flow_ctrl_cnt;
-
-	if (opp_cnt >= 2)
-		hblank_halved = true;
-
-	flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
-			stream->timing.h_border_left -
-			stream->timing.h_border_right;
-
-	if (hblank_halved)
-		flow_ctrl_cnt /= 2;
-
-	/* ODM combine 4:1 case */
-	if (opp_cnt == 4)
-		flow_ctrl_cnt /= 2;
-
-	return flow_ctrl_cnt;
-}
-
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -183,10 +160,6 @@ void dcn314_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 0;
 	int opp_inst[MAX_PIPES] = {0};
-	bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
-	struct mpc_dwb_flow_control flow_control;
-	struct mpc *mpc = dc->res_pool->mpc;
-	int i;
 
 	opp_cnt = get_odm_config(pipe_ctx, opp_inst);
 
@@ -199,20 +172,6 @@ void dcn314_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-	rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
-	flow_control.flow_ctrl_mode = 0;
-	flow_control.flow_ctrl_cnt0 = 0x80;
-	flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
-	if (mpc->funcs->set_out_rate_control) {
-		for (i = 0; i < opp_cnt; ++i) {
-			mpc->funcs->set_out_rate_control(
-					mpc, opp_inst[i],
-					true,
-					rate_control_2x_pclk,
-					&flow_control);
-		}
-	}
-
 	for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
 				odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index aa36d7a56ca8..7668229438da 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -966,29 +966,6 @@ void dcn32_init_hw(struct dc *dc)
 	}
 }
 
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
-		int opp_cnt)
-{
-	bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
-	int flow_ctrl_cnt;
-
-	if (opp_cnt >= 2)
-		hblank_halved = true;
-
-	flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
-			stream->timing.h_border_left -
-			stream->timing.h_border_right;
-
-	if (hblank_halved)
-		flow_ctrl_cnt /= 2;
-
-	/* ODM combine 4:1 case */
-	if (opp_cnt == 4)
-		flow_ctrl_cnt /= 2;
-
-	return flow_ctrl_cnt;
-}
-
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -1103,10 +1080,6 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 0;
 	int opp_inst[MAX_PIPES] = {0};
-	bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
-	struct mpc_dwb_flow_control flow_control;
-	struct mpc *mpc = dc->res_pool->mpc;
-	int i;
 
 	opp_cnt = get_odm_config(pipe_ctx, opp_inst);
 
@@ -1119,20 +1092,6 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-	rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
-	flow_control.flow_ctrl_mode = 0;
-	flow_control.flow_ctrl_cnt0 = 0x80;
-	flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
-	if (mpc->funcs->set_out_rate_control) {
-		for (i = 0; i < opp_cnt; ++i) {
-			mpc->funcs->set_out_rate_control(
-					mpc, opp_inst[i],
-					true,
-					rate_control_2x_pclk,
-					&flow_control);
-		}
-	}
-
 	for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
 				odm_pipe->stream_res.opp,
@@ -1156,6 +1115,13 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 			dsc->funcs->dsc_disconnect(dsc);
 		}
 	}
+
+	if (!resource_is_pipe_type(pipe_ctx, DPP_PIPE))
+		/*
+		 * blank pattern is generated by OPP, reprogram blank pattern
+		 * due to OPP count change
+		 */
+		dc->hwseq->funcs.blank_pixel_data(dc, pipe_ctx, true);
 }
 
 unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div)
@@ -1778,3 +1744,26 @@ void dcn32_prepare_bandwidth(struct dc *dc,
 		context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support;
 	}
 }
+
+void dcn32_interdependent_update_lock(struct dc *dc,
+		struct dc_state *context, bool lock)
+{
+	unsigned int i;
+	struct pipe_ctx *pipe;
+	struct timing_generator *tg;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+		tg = pipe->stream_res.tg;
+
+		if (!resource_is_pipe_type(pipe, OTG_MASTER) ||
+				!tg->funcs->is_tg_enabled(tg) ||
+				dc_state_get_pipe_subvp_type(context, pipe) == SUBVP_PHANTOM)
+			continue;
+
+		if (lock)
+			dc->hwss.pipe_control_lock(dc, pipe, true);
+		else
+			dc->hwss.pipe_control_lock(dc, pipe, false);
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index 069e20bc87c0..f55c11fc56ec 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -129,4 +129,6 @@ bool dcn32_is_pipe_topology_transition_seamless(struct dc *dc,
 void dcn32_prepare_bandwidth(struct dc *dc,
 	struct dc_state *context);
 
+void dcn32_interdependent_update_lock(struct dc *dc,
+		struct dc_state *context, bool lock);
 #endif /* __DC_HWSS_DCN32_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 2b073123d3ed..67d661dbd5b7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -58,7 +58,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.disable_plane = dcn20_disable_plane,
 	.disable_pixel_data = dcn20_disable_pixel_data,
 	.pipe_control_lock = dcn20_pipe_control_lock,
-	.interdependent_update_lock = dcn10_lock_all_pipes,
+	.interdependent_update_lock = dcn32_interdependent_update_lock,
 	.cursor_lock = dcn10_cursor_lock,
 	.prepare_bandwidth = dcn32_prepare_bandwidth,
 	.optimize_bandwidth = dcn20_optimize_bandwidth,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 4b92df23ff0d..a5560b3fc39b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -358,29 +358,6 @@ void dcn35_init_hw(struct dc *dc)
 	}
 }
 
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
-		int opp_cnt)
-{
-	bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
-	int flow_ctrl_cnt;
-
-	if (opp_cnt >= 2)
-		hblank_halved = true;
-
-	flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
-			stream->timing.h_border_left -
-			stream->timing.h_border_right;
-
-	if (hblank_halved)
-		flow_ctrl_cnt /= 2;
-
-	/* ODM combine 4:1 case */
-	if (opp_cnt == 4)
-		flow_ctrl_cnt /= 2;
-
-	return flow_ctrl_cnt;
-}
-
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -474,10 +451,6 @@ void dcn35_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 0;
 	int opp_inst[MAX_PIPES] = {0};
-	bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
-	struct mpc_dwb_flow_control flow_control;
-	struct mpc *mpc = dc->res_pool->mpc;
-	int i;
 
 	opp_cnt = get_odm_config(pipe_ctx, opp_inst);
 
@@ -490,20 +463,6 @@ void dcn35_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-	rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
-	flow_control.flow_ctrl_mode = 0;
-	flow_control.flow_ctrl_cnt0 = 0x80;
-	flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
-	if (mpc->funcs->set_out_rate_control) {
-		for (i = 0; i < opp_cnt; ++i) {
-			mpc->funcs->set_out_rate_control(
-					mpc, opp_inst[i],
-					true,
-					rate_control_2x_pclk,
-					&flow_control);
-		}
-	}
-
 	for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
 				odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index ab17fa1c64e8..670255c9bc82 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -67,7 +67,7 @@ static const struct hw_sequencer_funcs dcn351_funcs = {
 	.prepare_bandwidth = dcn35_prepare_bandwidth,
 	.optimize_bandwidth = dcn35_optimize_bandwidth,
 	.update_bandwidth = dcn20_update_bandwidth,
-	.set_drr = dcn10_set_drr,
+	.set_drr = dcn35_set_drr,
 	.get_position = dcn10_get_position,
 	.set_static_screen_control = dcn35_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index aee5372e292c..d89c92370d5b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -337,6 +337,9 @@ struct opp_funcs {
 	bool (*dpg_is_blanked)(
 			struct output_pixel_processor *opp);
 
+	bool (*dpg_is_pending)(struct output_pixel_processor *opp);
+
+
 	void (*opp_dpg_set_blank_color)(
 			struct output_pixel_processor *opp,
 			const struct tg_color *color);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index d98d72f35be5..ffad8fe16c54 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -331,6 +331,7 @@ struct timing_generator_funcs {
 
 	void (*init_odm)(struct timing_generator *tg);
 	void (*wait_drr_doublebuffer_pending_clear)(struct timing_generator *tg);
+	void (*wait_odm_doublebuffer_pending_clear)(struct timing_generator *tg);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link.h
index 26fe81f213da..bf29fc58ea6a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/link.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/link.h
@@ -285,12 +285,12 @@ struct link_service {
 			enum replay_FW_Message_type msg,
 			union dmub_replay_cmd_set *cmd_data);
 	bool (*edp_set_coasting_vtotal)(
-			struct dc_link *link, uint16_t coasting_vtotal);
+			struct dc_link *link, uint32_t coasting_vtotal);
 	bool (*edp_replay_residency)(const struct dc_link *link,
 			unsigned int *residency, const bool is_start,
 			const bool is_alpm);
 	bool (*edp_set_replay_power_opt_and_coasting_vtotal)(struct dc_link *link,
-			const unsigned int *power_opts, uint16_t coasting_vtotal);
+			const unsigned int *power_opts, uint32_t coasting_vtotal);
 
 	bool (*edp_wait_for_t12)(struct dc_link *link);
 	bool (*edp_is_ilr_optimization_required)(struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index acfbbc638cc6..3baa2bdd6dd6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -1034,7 +1034,7 @@ bool edp_send_replay_cmd(struct dc_link *link,
 	return true;
 }
 
-bool edp_set_coasting_vtotal(struct dc_link *link, uint16_t coasting_vtotal)
+bool edp_set_coasting_vtotal(struct dc_link *link, uint32_t coasting_vtotal)
 {
 	struct dc *dc = link->ctx->dc;
 	struct dmub_replay *replay = dc->res_pool->replay;
@@ -1073,7 +1073,7 @@ bool edp_replay_residency(const struct dc_link *link,
 }
 
 bool edp_set_replay_power_opt_and_coasting_vtotal(struct dc_link *link,
-	const unsigned int *power_opts, uint16_t coasting_vtotal)
+	const unsigned int *power_opts, uint32_t coasting_vtotal)
 {
 	struct dc  *dc = link->ctx->dc;
 	struct dmub_replay *replay = dc->res_pool->replay;
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
index 34e521af7bb4..a158c6234d42 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
@@ -59,12 +59,12 @@ bool edp_setup_replay(struct dc_link *link,
 bool edp_send_replay_cmd(struct dc_link *link,
 			enum replay_FW_Message_type msg,
 			union dmub_replay_cmd_set *cmd_data);
-bool edp_set_coasting_vtotal(struct dc_link *link, uint16_t coasting_vtotal);
+bool edp_set_coasting_vtotal(struct dc_link *link, uint32_t coasting_vtotal);
 bool edp_replay_residency(const struct dc_link *link,
 	unsigned int *residency, const bool is_start, const bool is_alpm);
 bool edp_get_replay_state(const struct dc_link *link, uint64_t *state);
 bool edp_set_replay_power_opt_and_coasting_vtotal(struct dc_link *link,
-	const unsigned int *power_opts, uint16_t coasting_vtotal);
+	const unsigned int *power_opts, uint32_t coasting_vtotal);
 bool edp_wait_for_t12(struct dc_link *link);
 bool edp_is_ilr_optimization_required(struct dc_link *link,
        struct dc_crtc_timing *crtc_timing);
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h
index ab81594a7fad..6c2e84d3967f 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h
@@ -557,7 +557,8 @@ struct dcn_optc_registers {
 	type OTG_CRC_DATA_STREAM_SPLIT_MODE;\
 	type OTG_CRC_DATA_FORMAT;\
 	type OTG_V_TOTAL_LAST_USED_BY_DRR;\
-	type OTG_DRR_TIMING_DBUF_UPDATE_PENDING;
+	type OTG_DRR_TIMING_DBUF_UPDATE_PENDING;\
+	type OTG_H_TIMING_DIV_MODE_DB_UPDATE_PENDING;
 
 #define TG_REG_FIELD_LIST_DCN3_2(type) \
 	type OTG_H_TIMING_DIV_MODE_MANUAL;
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
index 823493543325..52eab8fccb7f 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
@@ -122,6 +122,13 @@ void optc32_get_odm_combine_segments(struct timing_generator *tg, int *odm_combi
 	}
 }
 
+void optc32_wait_odm_doublebuffer_pending_clear(struct timing_generator *tg)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(tg);
+
+	REG_WAIT(OTG_DOUBLE_BUFFER_CONTROL, OTG_H_TIMING_DIV_MODE_DB_UPDATE_PENDING, 0, 2, 50000);
+}
+
 void optc32_set_h_timing_div_manual_mode(struct timing_generator *optc, bool manual_mode)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
@@ -260,9 +267,6 @@ static void optc32_setup_manual_trigger(struct timing_generator *optc)
 				OTG_V_TOTAL_MAX_SEL, 1,
 				OTG_FORCE_LOCK_ON_EVENT, 0,
 				OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */
-
-		// Setup manual flow control for EOF via TRIG_A
-		optc->funcs->setup_manual_trigger(optc);
 	}
 }
 
@@ -345,6 +349,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = {
 		.set_odm_bypass = optc32_set_odm_bypass,
 		.set_odm_combine = optc32_set_odm_combine,
 		.get_odm_combine_segments = optc32_get_odm_combine_segments,
+		.wait_odm_doublebuffer_pending_clear = optc32_wait_odm_doublebuffer_pending_clear,
 		.set_h_timing_div_manual_mode = optc32_set_h_timing_div_manual_mode,
 		.get_optc_source = optc2_get_optc_source,
 		.set_out_mux = optc3_set_out_mux,
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h
index 8ce3b178cab0..0c2c14695561 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h
@@ -183,5 +183,6 @@ void optc32_set_h_timing_div_manual_mode(struct timing_generator *optc, bool man
 void optc32_get_odm_combine_segments(struct timing_generator *tg, int *odm_combine_segments);
 void optc32_set_odm_bypass(struct timing_generator *optc,
 		const struct dc_crtc_timing *dc_crtc_timing);
+void optc32_wait_odm_doublebuffer_pending_clear(struct timing_generator *tg);
 
 #endif /* __DC_OPTC_DCN32_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index 3f3951f3ba98..ce1754cc1f46 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1771,6 +1771,7 @@ static bool dml1_validate(struct dc *dc, struct dc_state *context, bool fast_val
 	dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel);
 
 	dcn32_override_min_req_memclk(dc, context);
+	dcn32_override_min_req_dcfclk(dc, context);
 
 	BW_VAL_TRACE_END_WATERMARKS();
 
@@ -1930,6 +1931,8 @@ static void dcn32_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw
 {
 	DC_FP_START();
 	dcn32_update_bw_bounding_box_fpu(dc, bw_params);
+	if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2)
+		dml2_reinit(dc, &dc->dml2_options, &dc->current_state->bw_ctx.dml2);
 	DC_FP_END();
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 0c87b0fabba7..2258c5c7212d 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -42,6 +42,7 @@
 #define SUBVP_ACTIVE_MARGIN_LIST_LEN 2
 #define DCN3_2_MAX_SUBVP_PIXEL_RATE_MHZ 1800
 #define DCN3_2_VMIN_DISPCLK_HZ 717000000
+#define MIN_SUBVP_DCFCLK_KHZ 400000
 
 #define TO_DCN32_RES_POOL(pool)\
 	container_of(pool, struct dcn32_resource_pool, base)
@@ -181,6 +182,8 @@ bool dcn32_subvp_vblank_admissable(struct dc *dc, struct dc_state *context, int
 
 void dcn32_update_dml_pipes_odm_policy_based_on_context(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes);
 
+void dcn32_override_min_req_dcfclk(struct dc *dc, struct dc_state *context);
+
 /* definitions for run time init of reg offsets */
 
 /* CLK SRC */
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
index b356fed1726d..296a0a8e7145 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
@@ -1581,6 +1581,8 @@ static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b
 {
 	DC_FP_START();
 	dcn321_update_bw_bounding_box_fpu(dc, bw_params);
+	if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2)
+		dml2_reinit(dc, &dc->dml2_options, &dc->current_state->bw_ctx.dml2);
 	DC_FP_END();
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index 5b486400dfdb..909e14261f9b 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -700,6 +700,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_dcc = DCC_ENABLE,
 	.disable_dpp_power_gate = true,
 	.disable_hubp_power_gate = true,
+	.disable_optc_power_gate = true, /*should the same as above two*/
+	.disable_hpo_power_gate = true, /*dmubfw force domain25 on*/
 	.disable_clock_gate = false,
 	.disable_dsc_power_gate = true,
 	.vsr_support = true,
@@ -742,12 +744,13 @@ static const struct dc_debug_options debug_defaults_drv = {
 	},
 	.seamless_boot_odm_combine = DML_FAIL_SOURCE_PIXEL_FORMAT,
 	.enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/
+	.minimum_z8_residency_time = 2100,
 	.using_dml2 = true,
 	.support_eDP1_5 = true,
 	.enable_hpo_pg_support = false,
 	.enable_legacy_fast_update = true,
 	.enable_single_display_2to1_odm_policy = true,
-	.disable_idle_power_optimizations = true,
+	.disable_idle_power_optimizations = false,
 	.dmcub_emulation = false,
 	.disable_boot_optimizations = false,
 	.disable_unbounded_requesting = false,
@@ -758,8 +761,10 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = true,
 	.ignore_pg = true,
 	.psp_disabled_wa = true,
-	.ips2_eval_delay_us = 200,
-	.ips2_entry_delay_us = 400
+	.ips2_eval_delay_us = 2000,
+	.ips2_entry_delay_us = 800,
+	.disable_dmub_reallow_idle = true,
+	.static_screen_wait_frames = 2,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index a529e369b2ac..af3fe8bb0728 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -3238,6 +3238,14 @@ struct dmub_cmd_replay_set_coasting_vtotal_data {
 	 * Currently the support is only for 0 or 1
 	 */
 	uint8_t panel_inst;
+	/**
+	 * 16-bit value dicated by driver that indicates the coasting vtotal high byte part.
+	 */
+	uint16_t coasting_vtotal_high;
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad[2];
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index 8c137d7c032e..7c9805705fd3 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -513,6 +513,9 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp)
 	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
 
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
 	hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index;
 
 	if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0)
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index 738ee763f24a..84f9b412a4f1 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -147,15 +147,12 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 	}
 
 	/* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */
-	if (stream->link->psr_settings.psr_feature_enabled) {
-		if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
-			vsc_packet_revision = vsc_packet_rev4;
-		else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
-			vsc_packet_revision = vsc_packet_rev2;
-	}
-
-	if (stream->link->replay_settings.config.replay_supported)
+	if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
+		vsc_packet_revision = vsc_packet_rev4;
+	else if (stream->link->replay_settings.config.replay_supported)
 		vsc_packet_revision = vsc_packet_rev4;
+	else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
+		vsc_packet_revision = vsc_packet_rev2;
 
 	/* Update to revision 5 for extended colorimetry support */
 	if (stream->use_vsc_sdp_for_colorimetry)
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index e304e8435fb8..2a3698fd2dc2 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -975,7 +975,7 @@ bool psr_su_set_dsc_slice_height(struct dc *dc, struct dc_link *link,
 
 void set_replay_coasting_vtotal(struct dc_link *link,
 	enum replay_coasting_vtotal_type type,
-	uint16_t vtotal)
+	uint32_t vtotal)
 {
 	link->replay_settings.coasting_vtotal_table[type] = vtotal;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index bef4815e1703..ff7e6f3cd6be 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -56,7 +56,7 @@ bool dmub_init_abm_config(struct resource_pool *res_pool,
 void init_replay_config(struct dc_link *link, struct replay_config *pr_config);
 void set_replay_coasting_vtotal(struct dc_link *link,
 	enum replay_coasting_vtotal_type type,
-	uint16_t vtotal);
+	uint32_t vtotal);
 void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal);
 void calculate_replay_link_off_frame_count(struct dc_link *link,
 	uint16_t vtotal, uint16_t htotal);
diff --git a/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h b/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
index beadb9e42850..ca83e9e5c3ff 100644
--- a/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
+++ b/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
@@ -234,7 +234,8 @@ union UMSCHAPI__SET_HW_RESOURCES {
 				uint32_t enable_level_process_quantum_check : 1;
 				uint32_t is_vcn0_enabled : 1;
 				uint32_t is_vcn1_enabled : 1;
-				uint32_t reserved : 27;
+				uint32_t use_rs64mem_for_proc_ctx_csa : 1;
+				uint32_t reserved : 26;
 			};
 			uint32_t uint32_all;
 		};
@@ -297,9 +298,12 @@ union UMSCHAPI__ADD_QUEUE {
 
 		struct {
 			uint32_t is_context_suspended : 1;
-			uint32_t reserved : 31;
+			uint32_t collaboration_mode : 1;
+			uint32_t reserved : 30;
 		};
 		struct UMSCH_API_STATUS api_status;
+		uint32_t process_csa_array_index;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -314,6 +318,7 @@ union UMSCHAPI__REMOVE_QUEUE {
 		uint64_t context_csa_addr;
 
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -337,6 +342,7 @@ union UMSCHAPI__SUSPEND {
 		uint32_t suspend_fence_value;
 
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -356,6 +362,7 @@ union UMSCHAPI__RESUME {
 		enum UMSCH_ENGINE_TYPE engine_type;
 
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -404,6 +411,7 @@ union UMSCHAPI__UPDATE_AFFINITY {
 		union UMSCH_AFFINITY affinity;
 		uint64_t context_csa_addr;
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -417,6 +425,7 @@ union UMSCHAPI__CHANGE_CONTEXT_PRIORITY_LEVEL {
 		uint64_t context_quantum;
 		uint64_t context_csa_addr;
 		struct UMSCH_API_STATUS api_status;
+		uint32_t context_csa_array_index;
 	};
 
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 246b211b1e85..65333141b1c1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -735,7 +735,7 @@ static int smu_early_init(void *handle)
 	smu->adev = adev;
 	smu->pm_enabled = !!amdgpu_dpm;
 	smu->is_apu = false;
-	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
+	smu->smu_baco.state = SMU_BACO_STATE_NONE;
 	smu->smu_baco.platform_support = false;
 	smu->user_dpm_profile.fan_mode = -1;
 
@@ -1966,10 +1966,25 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 	return 0;
 }
 
+static int smu_reset_mp1_state(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+
+	if ((!adev->in_runpm) && (!adev->in_suspend) &&
+		(!amdgpu_in_reset(adev)) && amdgpu_ip_version(adev, MP1_HWIP, 0) ==
+									IP_VERSION(13, 0, 10) &&
+		!amdgpu_device_has_display_hardware(adev))
+		ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
+
+	return ret;
+}
+
 static int smu_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = adev->powerplay.pp_handle;
+	int ret;
 
 	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
@@ -1987,7 +2002,15 @@ static int smu_hw_fini(void *handle)
 
 	adev->pm.dpm_enabled = false;
 
-	return smu_smc_hw_cleanup(smu);
+	ret = smu_smc_hw_cleanup(smu);
+	if (ret)
+		return ret;
+
+	ret = smu_reset_mp1_state(smu);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static void smu_late_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index a870bdd49a4e..1fa81575788c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,6 +424,7 @@ enum smu_reset_mode {
 enum smu_baco_state {
 	SMU_BACO_STATE_ENTER = 0,
 	SMU_BACO_STATE_EXIT,
+	SMU_BACO_STATE_NONE,
 };
 
 struct smu_baco_context {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
index 5bb7a63c0602..97522c085258 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
@@ -144,6 +144,37 @@ typedef struct {
   uint32_t MaxGfxClk;
 } DpmClocks_t;
 
+//Freq in MHz
+//Voltage in milli volts with 2 fractional bits
+typedef struct {
+  uint32_t DcfClocks[NUM_DCFCLK_DPM_LEVELS];
+  uint32_t DispClocks[NUM_DISPCLK_DPM_LEVELS];
+  uint32_t DppClocks[NUM_DPPCLK_DPM_LEVELS];
+  uint32_t SocClocks[NUM_SOCCLK_DPM_LEVELS];
+  uint32_t VClocks0[NUM_VCN_DPM_LEVELS];
+  uint32_t VClocks1[NUM_VCN_DPM_LEVELS];
+  uint32_t DClocks0[NUM_VCN_DPM_LEVELS];
+  uint32_t DClocks1[NUM_VCN_DPM_LEVELS];
+  uint32_t VPEClocks[NUM_VPE_DPM_LEVELS];
+  uint32_t FclkClocks_Freq[NUM_FCLK_DPM_LEVELS];
+  uint32_t FclkClocks_Voltage[NUM_FCLK_DPM_LEVELS];
+  uint32_t SocVoltage[NUM_SOC_VOLTAGE_LEVELS];
+  MemPstateTable_t MemPstateTable[NUM_MEM_PSTATE_LEVELS];
+
+  uint8_t  NumDcfClkLevelsEnabled;
+  uint8_t  NumDispClkLevelsEnabled; //Applies to both Dispclk and Dppclk
+  uint8_t  NumSocClkLevelsEnabled;
+  uint8_t  Vcn0ClkLevelsEnabled;     //Applies to both Vclk0 and Dclk0
+  uint8_t  Vcn1ClkLevelsEnabled;     //Applies to both Vclk1 and Dclk1
+  uint8_t  VpeClkLevelsEnabled;
+  uint8_t  NumMemPstatesEnabled;
+  uint8_t  NumFclkLevelsEnabled;
+  uint8_t  spare;
+
+  uint32_t MinGfxClk;
+  uint32_t MaxGfxClk;
+} DpmClocks_t_v14_0_1;
+
 typedef struct {
   uint16_t CoreFrequency[16];          //Target core frequency [MHz]
   uint16_t CorePower[16];              //CAC calculated core power [mW]
@@ -224,7 +255,7 @@ typedef enum {
 #define TABLE_CUSTOM_DPM            2 // Called by Driver
 #define TABLE_BIOS_GPIO_CONFIG      3 // Called by BIOS
 #define TABLE_DPMCLOCKS             4 // Called by Driver and VBIOS
-#define TABLE_SPARE0                5 // Unused
+#define TABLE_MOMENTARY_PM          5 // Called by Tools
 #define TABLE_MODERN_STDBY          6 // Called by Tools for Modern Standby Log
 #define TABLE_SMU_METRICS           7 // Called by Driver and SMF/PMF
 #define TABLE_COUNT                 8
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h
index 356e0f57a426..ddb625860083 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h
@@ -42,7 +42,7 @@
 #define FEATURE_EDC_BIT                      7
 #define FEATURE_PLL_POWER_DOWN_BIT           8
 #define FEATURE_VDDOFF_BIT                   9
-#define FEATURE_VCN_DPM_BIT                 10
+#define FEATURE_VCN_DPM_BIT                 10   /* this is for both VCN0 and VCN1 */
 #define FEATURE_DS_MPM_BIT                  11
 #define FEATURE_FCLK_DPM_BIT                12
 #define FEATURE_SOCCLK_DPM_BIT              13
@@ -56,9 +56,9 @@
 #define FEATURE_DS_GFXCLK_BIT               21
 #define FEATURE_DS_SOCCLK_BIT               22
 #define FEATURE_DS_LCLK_BIT                 23
-#define FEATURE_LOW_POWER_DCNCLKS_BIT       24  // for all DISP clks
+#define FEATURE_LOW_POWER_DCNCLKS_BIT       24
 #define FEATURE_DS_SHUBCLK_BIT              25
-#define FEATURE_SPARE0_BIT                  26  //SPARE
+#define FEATURE_RESERVED0_BIT               26
 #define FEATURE_ZSTATES_BIT                 27
 #define FEATURE_IOMMUL2_PG_BIT              28
 #define FEATURE_DS_FCLK_BIT                 29
@@ -66,8 +66,8 @@
 #define FEATURE_DS_MP1CLK_BIT               31
 #define FEATURE_WHISPER_MODE_BIT            32
 #define FEATURE_SMU_LOW_POWER_BIT           33
-#define FEATURE_SMART_L3_RINSER_BIT         34
-#define FEATURE_SPARE1_BIT                  35  //SPARE
+#define FEATURE_RESERVED1_BIT               34  /* v14_0_0 SMART_L3_RINSER; v14_0_1 RESERVED1 */
+#define FEATURE_GFX_DEM_BIT                 35  /* v14_0_0 SPARE; v14_0_1 GFX_DEM */
 #define FEATURE_PSI_BIT                     36
 #define FEATURE_PROCHOT_BIT                 37
 #define FEATURE_CPUOFF_BIT                  38
@@ -77,11 +77,11 @@
 #define FEATURE_PERF_LIMIT_BIT              42
 #define FEATURE_CORE_DLDO_BIT               43
 #define FEATURE_DVO_BIT                     44
-#define FEATURE_DS_VCN_BIT                  45
+#define FEATURE_DS_VCN_BIT                  45  /* v14_0_1 this is for both VCN0 and VCN1 */
 #define FEATURE_CPPC_BIT                    46
 #define FEATURE_CPPC_PREFERRED_CORES        47
 #define FEATURE_DF_CSTATES_BIT              48
-#define FEATURE_SPARE2_BIT                  49  //SPARE
+#define FEATURE_FAST_PSTATE_CLDO_BIT        49  /* v14_0_0 SPARE */
 #define FEATURE_ATHUB_PG_BIT                50
 #define FEATURE_VDDOFF_ECO_BIT              51
 #define FEATURE_ZSTATES_ECO_BIT             52
@@ -93,8 +93,8 @@
 #define FEATURE_DS_IPUCLK_BIT               58
 #define FEATURE_DS_VPECLK_BIT               59
 #define FEATURE_VPE_DPM_BIT                 60
-#define FEATURE_SPARE_61                    61
-#define FEATURE_FP_DIDT                     62
+#define FEATURE_SMART_L3_RINSER_BIT         61  /* v14_0_0 SPARE*/
+#define FEATURE_PCC_BIT                     62  /* v14_0_0 FP_DIDT v14_0_1 PCC_BIT */
 #define NUM_FEATURES                        63
 
 // Firmware Header/Footer
@@ -151,6 +151,43 @@ typedef struct {
   // MP1_EXT_SCRATCH7 = RTOS Current Job
 } FwStatus_t;
 
+typedef struct {
+  // MP1_EXT_SCRATCH0
+  uint32_t DpmHandlerID         : 8;
+  uint32_t ActivityMonitorID    : 8;
+  uint32_t DpmTimerID           : 8;
+  uint32_t DpmHubID             : 4;
+  uint32_t DpmHubTask           : 4;
+  // MP1_EXT_SCRATCH1
+  uint32_t CclkSyncStatus       : 8;
+  uint32_t ZstateStatus         : 4;
+  uint32_t Cpu1VddOff           : 4;
+  uint32_t DstateFun            : 4;
+  uint32_t DstateDev            : 4;
+  uint32_t GfxOffStatus         : 2;
+  uint32_t Cpu0Off              : 2;
+  uint32_t Cpu1Off              : 2;
+  uint32_t Cpu0VddOff           : 2;
+  // MP1_EXT_SCRATCH2
+  uint32_t P2JobHandler         :32;
+  // MP1_EXT_SCRATCH3
+  uint32_t PostCode             :32;
+  // MP1_EXT_SCRATCH4
+  uint32_t MsgPortBusy          :15;
+  uint32_t RsmuPmiP1Pending     : 1;
+  uint32_t RsmuPmiP2PendingCnt  : 8;
+  uint32_t DfCstateExitPending  : 1;
+  uint32_t Pc6EntryPending      : 1;
+  uint32_t Pc6ExitPending       : 1;
+  uint32_t WarmResetPending     : 1;
+  uint32_t Mp0ClkPending        : 1;
+  uint32_t InWhisperMode        : 1;
+  uint32_t spare2               : 2;
+  // MP1_EXT_SCRATCH5
+  uint32_t IdleMask             :32;
+  // MP1_EXT_SCRATCH6 = RTOS threads' status
+  // MP1_EXT_SCRATCH7 = RTOS Current Job
+} FwStatus_t_v14_0_1;
 
 #pragma pack(pop)
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
index 8a8a57c56bc0..c4dc5881d8df 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
@@ -54,14 +54,14 @@
 #define PPSMC_MSG_TestMessage                   0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team
 #define PPSMC_MSG_GetPmfwVersion                0x02 ///< Get PMFW version
 #define PPSMC_MSG_GetDriverIfVersion            0x03 ///< Get PMFW_DRIVER_IF version
-#define PPSMC_MSG_SPARE0                        0x04 ///< SPARE
-#define PPSMC_MSG_SPARE1                        0x05 ///< SPARE
-#define PPSMC_MSG_PowerDownVcn                  0x06 ///< Power down VCN
-#define PPSMC_MSG_PowerUpVcn                    0x07 ///< Power up VCN; VCN is power gated by default
-#define PPSMC_MSG_SetHardMinVcn                 0x08 ///< For wireless display
+#define PPSMC_MSG_PowerDownVcn1                 0x04 ///< Power down VCN1
+#define PPSMC_MSG_PowerUpVcn1                   0x05 ///< Power up VCN1; VCN1 is power gated by default
+#define PPSMC_MSG_PowerDownVcn0                 0x06 ///< Power down VCN0
+#define PPSMC_MSG_PowerUpVcn0                   0x07 ///< Power up VCN0; VCN0 is power gated by default
+#define PPSMC_MSG_SetHardMinVcn0                0x08 ///< For wireless display
 #define PPSMC_MSG_SetSoftMinGfxclk              0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz
-#define PPSMC_MSG_SPARE2                        0x0A ///< SPARE
-#define PPSMC_MSG_SPARE3                        0x0B ///< SPARE
+#define PPSMC_MSG_SetHardMinVcn1                0x0A ///< For wireless display
+#define PPSMC_MSG_SetSoftMinVcn1                0x0B ///< Set soft min for VCN1 clocks (VCLK1 and DCLK1)
 #define PPSMC_MSG_PrepareMp1ForUnload           0x0C ///< Prepare PMFW for GFX driver unload
 #define PPSMC_MSG_SetDriverDramAddrHigh         0x0D ///< Set high 32 bits of DRAM address for Driver table transfer
 #define PPSMC_MSG_SetDriverDramAddrLow          0x0E ///< Set low 32 bits of DRAM address for Driver table transfer
@@ -71,36 +71,32 @@
 #define PPSMC_MSG_GetEnabledSmuFeatures         0x12 ///< Get enabled features in PMFW
 #define PPSMC_MSG_SetHardMinSocclkByFreq        0x13 ///< Set hard min for SOC CLK
 #define PPSMC_MSG_SetSoftMinFclk                0x14 ///< Set hard min for FCLK
-#define PPSMC_MSG_SetSoftMinVcn                 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK)
-
+#define PPSMC_MSG_SetSoftMinVcn0                0x15 ///< Set soft min for VCN0 clocks (VCLK0 and DCLK0)
 #define PPSMC_MSG_EnableGfxImu                  0x16 ///< Enable GFX IMU
-
-#define PPSMC_MSG_spare_0x17                    0x17
-#define PPSMC_MSG_spare_0x18                    0x18
+#define PPSMC_MSG_spare_0x17                    0x17 ///< Get GFX clock frequency
+#define PPSMC_MSG_spare_0x18                    0x18 ///< Get FCLK frequency
 #define PPSMC_MSG_AllowGfxOff                   0x19 ///< Inform PMFW of allowing GFXOFF entry
 #define PPSMC_MSG_DisallowGfxOff                0x1A ///< Inform PMFW of disallowing GFXOFF entry
 #define PPSMC_MSG_SetSoftMaxGfxClk              0x1B ///< Set soft max for GFX CLK
 #define PPSMC_MSG_SetHardMinGfxClk              0x1C ///< Set hard min for GFX CLK
-
 #define PPSMC_MSG_SetSoftMaxSocclkByFreq        0x1D ///< Set soft max for SOC CLK
 #define PPSMC_MSG_SetSoftMaxFclkByFreq          0x1E ///< Set soft max for FCLK
-#define PPSMC_MSG_SetSoftMaxVcn                 0x1F ///< Set soft max for VCN clocks (VCLK and DCLK)
-#define PPSMC_MSG_spare_0x20                    0x20
-#define PPSMC_MSG_PowerDownJpeg                 0x21 ///< Power down Jpeg
-#define PPSMC_MSG_PowerUpJpeg                   0x22 ///< Power up Jpeg; VCN is power gated by default
-
+#define PPSMC_MSG_SetSoftMaxVcn0                0x1F ///< Set soft max for VCN0 clocks (VCLK0 and DCLK0)
+#define PPSMC_MSG_spare_0x20                    0x20 ///< Set power limit percentage
+#define PPSMC_MSG_PowerDownJpeg0                0x21 ///< Power down Jpeg of VCN0
+#define PPSMC_MSG_PowerUpJpeg0                  0x22 ///< Power up Jpeg of VCN0; VCN0 is power gated by default
 #define PPSMC_MSG_SetHardMinFclkByFreq          0x23 ///< Set hard min for FCLK
 #define PPSMC_MSG_SetSoftMinSocclkByFreq        0x24 ///< Set soft min for SOC CLK
 #define PPSMC_MSG_AllowZstates                  0x25 ///< Inform PMFM of allowing Zstate entry, i.e. no Miracast activity
-#define PPSMC_MSG_Reserved                      0x26 ///< Not used
-#define PPSMC_MSG_Reserved1                     0x27 ///< Not used, previously PPSMC_MSG_RequestActiveWgp
-#define PPSMC_MSG_Reserved2                     0x28 ///< Not used, previously PPSMC_MSG_QueryActiveWgp
+#define PPSMC_MSG_PowerDownJpeg1                0x26 ///< Power down Jpeg of VCN1
+#define PPSMC_MSG_PowerUpJpeg1                  0x27 ///< Power up Jpeg of VCN1; VCN1 is power gated by default
+#define PPSMC_MSG_SetSoftMaxVcn1                0x28 ///< Set soft max for VCN1 clocks (VCLK1 and DCLK1)
 #define PPSMC_MSG_PowerDownIspByTile            0x29 ///< ISP is power gated by default
 #define PPSMC_MSG_PowerUpIspByTile              0x2A ///< This message is used to power up ISP tiles and enable the ISP DPM
 #define PPSMC_MSG_SetHardMinIspiclkByFreq       0x2B ///< Set HardMin by frequency for ISPICLK
 #define PPSMC_MSG_SetHardMinIspxclkByFreq       0x2C ///< Set HardMin by frequency for ISPXCLK
-#define PPSMC_MSG_PowerDownUmsch                0x2D ///< Power down VCN.UMSCH (aka VSCH) scheduler
-#define PPSMC_MSG_PowerUpUmsch                  0x2E ///< Power up VCN.UMSCH (aka VSCH) scheduler
+#define PPSMC_MSG_PowerDownUmsch                0x2D ///< Power down VCN0.UMSCH (aka VSCH) scheduler
+#define PPSMC_MSG_PowerUpUmsch                  0x2E ///< Power up VCN0.UMSCH (aka VSCH) scheduler
 #define PPSMC_Message_IspStutterOn_MmhubPgDis   0x2F ///< ISP StutterOn mmHub PgDis
 #define PPSMC_Message_IspStutterOff_MmhubPgEn   0x30 ///< ISP StufferOff mmHub PgEn
 #define PPSMC_MSG_PowerUpVpe                    0x31 ///< Power up VPE
@@ -110,7 +106,9 @@
 #define PPSMC_MSG_DisableLSdma                  0x35 ///< Disable LSDMA
 #define PPSMC_MSG_SetSoftMaxVpe                 0x36 ///<
 #define PPSMC_MSG_SetSoftMinVpe                 0x37 ///<
-#define PPSMC_Message_Count                     0x38 ///< Total number of PPSMC messages
+#define PPSMC_MSG_AllocMALLCache                0x38 ///< Allocating MALL Cache
+#define PPSMC_MSG_ReleaseMALLCache              0x39 ///< Releasing MALL Cache
+#define PPSMC_Message_Count                     0x3A ///< Total number of PPSMC messages
 /** @}*/
 
 /**
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index a941fdbf78b6..af427cc7dbb8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -115,6 +115,10 @@
        __SMU_DUMMY_MAP(PowerDownVcn),                 \
        __SMU_DUMMY_MAP(PowerUpJpeg),                  \
        __SMU_DUMMY_MAP(PowerDownJpeg),                \
+       __SMU_DUMMY_MAP(PowerUpJpeg0),                 \
+       __SMU_DUMMY_MAP(PowerDownJpeg0),               \
+       __SMU_DUMMY_MAP(PowerUpJpeg1),                 \
+       __SMU_DUMMY_MAP(PowerDownJpeg1),               \
        __SMU_DUMMY_MAP(BacoAudioD3PME),               \
        __SMU_DUMMY_MAP(ArmD3),                        \
        __SMU_DUMMY_MAP(RunDcBtc),                     \
@@ -135,6 +139,8 @@
 	__SMU_DUMMY_MAP(PowerUpSdma),                 \
 	__SMU_DUMMY_MAP(SetHardMinIspclkByFreq),      \
 	__SMU_DUMMY_MAP(SetHardMinVcn),               \
+       __SMU_DUMMY_MAP(SetHardMinVcn0),               \
+       __SMU_DUMMY_MAP(SetHardMinVcn1),               \
 	__SMU_DUMMY_MAP(SetAllowFclkSwitch),          \
 	__SMU_DUMMY_MAP(SetMinVideoGfxclkFreq),       \
 	__SMU_DUMMY_MAP(ActiveProcessNotify),         \
@@ -150,6 +156,8 @@
 	__SMU_DUMMY_MAP(SetPhyclkVoltageByFreq),      \
 	__SMU_DUMMY_MAP(SetDppclkVoltageByFreq),      \
 	__SMU_DUMMY_MAP(SetSoftMinVcn),               \
+       __SMU_DUMMY_MAP(SetSoftMinVcn0),              \
+       __SMU_DUMMY_MAP(SetSoftMinVcn1),              \
 	__SMU_DUMMY_MAP(EnablePostCode),              \
 	__SMU_DUMMY_MAP(GetGfxclkFrequency),          \
 	__SMU_DUMMY_MAP(GetFclkFrequency),            \
@@ -161,6 +169,8 @@
 	__SMU_DUMMY_MAP(SetSoftMaxSocclkByFreq),      \
 	__SMU_DUMMY_MAP(SetSoftMaxFclkByFreq),        \
 	__SMU_DUMMY_MAP(SetSoftMaxVcn),               \
+       __SMU_DUMMY_MAP(SetSoftMaxVcn0),              \
+       __SMU_DUMMY_MAP(SetSoftMaxVcn1),              \
 	__SMU_DUMMY_MAP(PowerGateMmHub),              \
 	__SMU_DUMMY_MAP(UpdatePmeRestore),            \
 	__SMU_DUMMY_MAP(GpuChangeState),              \
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 3f7463c1c1a9..4af1985ae446 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -27,6 +27,7 @@
 
 #define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7
+#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6
 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x1
 
 #define FEATURE_MASK(feature) (1ULL << feature)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 1d96eb274d72..0c2d04f978ac 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1283,10 +1283,8 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 					uint32_t *max_power_limit,
 					uint32_t *min_power_limit)
 {
-	struct smu_11_0_powerplay_table *powerplay_table =
-		(struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table;
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
-	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t power_limit;
 
 	if (smu_v11_0_get_current_power_limit(smu, &power_limit)) {
 		/* the last hope to figure out the ppt limit */
@@ -1302,26 +1300,10 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 		*current_power_limit = power_limit;
 	if (default_power_limit)
 		*default_power_limit = power_limit;
-
-	if (smu->od_enabled)
-		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-	else
-		od_percent_upper = 0;
-
-	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-
-	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
-							od_percent_upper, od_percent_lower, power_limit);
-
-	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
-		*max_power_limit /= 100;
-	}
-
-	if (min_power_limit) {
-		*min_power_limit = power_limit * (100 - od_percent_lower);
-		*min_power_limit /= 100;
-	}
+	if (max_power_limit)
+		*max_power_limit = power_limit;
+	if (min_power_limit)
+		*min_power_limit = power_limit;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index ed189a3878eb..836b1df79928 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2339,7 +2339,7 @@ static int navi10_get_power_limit(struct smu_context *smu,
 		(struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table;
 	struct smu_11_0_overdrive_table *od_settings = smu->od_settings;
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
-	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0;
 
 	if (smu_v11_0_get_current_power_limit(smu, &power_limit)) {
 		/* the last hope to figure out the ppt limit */
@@ -2356,13 +2356,16 @@ static int navi10_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled &&
-		    navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT))
-		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-	else
-		od_percent_upper = 0;
-
-	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
+	if (powerplay_table) {
+		if (smu->od_enabled &&
+			    navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) {
+			od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
+		} else if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) {
+			od_percent_upper = 0;
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
+		}
+	}
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index e2ad2b972ab0..1f18b61884f3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -617,6 +617,12 @@ static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *s
 	return throttler_status;
 }
 
+static bool sienna_cichlid_is_od_feature_supported(struct smu_11_0_7_overdrive_table *od_table,
+						   enum SMU_11_0_7_ODFEATURE_CAP cap)
+{
+	return od_table->cap[cap];
+}
+
 static int sienna_cichlid_get_power_limit(struct smu_context *smu,
 					  uint32_t *current_power_limit,
 					  uint32_t *default_power_limit,
@@ -625,7 +631,8 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu,
 {
 	struct smu_11_0_7_powerplay_table *powerplay_table =
 		(struct smu_11_0_7_powerplay_table *)smu->smu_table.power_play_table;
-	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	struct smu_11_0_7_overdrive_table *od_settings = smu->od_settings;
+	uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0;
 	uint16_t *table_member;
 
 	GET_PPTABLE_MEMBER(SocketPowerLimitAc, &table_member);
@@ -640,12 +647,16 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled)
-		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
-	else
-		od_percent_upper = 0;
-
-	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
+	if (powerplay_table) {
+		if (smu->od_enabled &&
+				sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_POWER_LIMIT)) {
+			od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
+		} else if ((sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_POWER_LIMIT))) {
+			od_percent_upper = 0;
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
+		}
+	}
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
@@ -1250,12 +1261,6 @@ static bool sienna_cichlid_is_support_fine_grained_dpm(struct smu_context *smu,
 	return dpm_desc->SnapToDiscrete == 0;
 }
 
-static bool sienna_cichlid_is_od_feature_supported(struct smu_11_0_7_overdrive_table *od_table,
-						   enum SMU_11_0_7_ODFEATURE_CAP cap)
-{
-	return od_table->cap[cap];
-}
-
 static void sienna_cichlid_get_od_setting_range(struct smu_11_0_7_overdrive_table *od_table,
 						enum SMU_11_0_7_ODSETTING_ID setting,
 						uint32_t *min, uint32_t *max)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 9b80f18ea6c3..67117ced7c6a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2356,7 +2356,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 		(struct smu_13_0_0_powerplay_table *)table_context->power_play_table;
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
-	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0;
 	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
@@ -2369,12 +2369,16 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled)
-		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
-	else
-		od_percent_upper = 0;
-
-	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
+	if (powerplay_table) {
+		if (smu->od_enabled &&
+				smu_v13_0_0_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
+		} else if (smu_v13_0_0_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = 0;
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
+		}
+	}
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
@@ -2747,7 +2751,13 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_set_mp1_state(smu, mp1_state);
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+											  SMU_MSG_PrepareMp1ForUnload,
+											  0x55, NULL);
+
+		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
+			ret = smu_v13_0_disable_pmfw_state(smu);
+
 		break;
 	default:
 		/* Ignore others */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
index bb98156b2fa1..949131bd1ecb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
@@ -226,8 +226,18 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en)
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	if (!en && !adev->in_s0ix)
+	if (!en && !adev->in_s0ix) {
+		/* Adds a GFX reset as workaround just before sending the
+		 * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering
+		 * an invalid state.
+		 */
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset,
+						      SMU_RESET_MODE_2, NULL);
+		if (ret)
+			return ret;
+
 		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 3dc7b60cb075..7318964f1f14 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2320,7 +2320,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 		(struct smu_13_0_7_powerplay_table *)table_context->power_play_table;
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
-	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0;
 	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
@@ -2333,12 +2333,16 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled)
-		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
-	else
-		od_percent_upper = 0;
-
-	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
+	if (powerplay_table) {
+		if (smu->od_enabled &&
+				(smu_v13_0_7_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT))) {
+			od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
+		} else if (smu_v13_0_7_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = 0;
+			od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
+		}
+	}
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index b06a3cc43305..07a65e005785 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -234,7 +234,7 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
 		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
 		break;
 	case IP_VERSION(14, 0, 1):
-		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
+		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_1;
 		break;
 
 	default:
@@ -1402,9 +1402,22 @@ int smu_v14_0_set_vcn_enable(struct smu_context *smu,
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
 
-		ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
-						      SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn,
-						      i << 16U, NULL);
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+		    amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
+			if (i == 0)
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpVcn0 : SMU_MSG_PowerDownVcn0,
+								      i << 16U, NULL);
+			else if (i == 1)
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpVcn1 : SMU_MSG_PowerDownVcn1,
+								      i << 16U, NULL);
+		} else {
+			ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+							      SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn,
+							      i << 16U, NULL);
+		}
+
 		if (ret)
 			return ret;
 	}
@@ -1415,9 +1428,34 @@ int smu_v14_0_set_vcn_enable(struct smu_context *smu,
 int smu_v14_0_set_jpeg_enable(struct smu_context *smu,
 			      bool enable)
 {
-	return smu_cmn_send_smc_msg_with_param(smu, enable ?
-					       SMU_MSG_PowerUpJpeg : SMU_MSG_PowerDownJpeg,
-					       0, NULL);
+	struct amdgpu_device *adev = smu->adev;
+	int i, ret = 0;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+		    amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
+			if (i == 0)
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpJpeg0 : SMU_MSG_PowerDownJpeg0,
+								      i << 16U, NULL);
+			else if (i == 1 && amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+				ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+								      SMU_MSG_PowerUpJpeg1 : SMU_MSG_PowerDownJpeg1,
+								      i << 16U, NULL);
+		} else {
+			ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+							      SMU_MSG_PowerUpJpeg : SMU_MSG_PowerDownJpeg,
+							      i << 16U, NULL);
+		}
+
+		if (ret)
+			return ret;
+	}
+
+	return ret;
 }
 
 int smu_v14_0_run_btc(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 9310c4758e38..63399c00cc28 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -70,9 +70,12 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,				1),
 	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetPmfwVersion,			1),
 	MSG_MAP(GetDriverIfVersion,             PPSMC_MSG_GetDriverIfVersion,		1),
-	MSG_MAP(PowerDownVcn,                   PPSMC_MSG_PowerDownVcn,				1),
-	MSG_MAP(PowerUpVcn,                     PPSMC_MSG_PowerUpVcn,				1),
-	MSG_MAP(SetHardMinVcn,                  PPSMC_MSG_SetHardMinVcn,			1),
+	MSG_MAP(PowerDownVcn0,                  PPSMC_MSG_PowerDownVcn0,			1),
+	MSG_MAP(PowerUpVcn0,                    PPSMC_MSG_PowerUpVcn0,				1),
+	MSG_MAP(SetHardMinVcn0,                 PPSMC_MSG_SetHardMinVcn0,			1),
+	MSG_MAP(PowerDownVcn1,                  PPSMC_MSG_PowerDownVcn1,			1),
+	MSG_MAP(PowerUpVcn1,                    PPSMC_MSG_PowerUpVcn1,				1),
+	MSG_MAP(SetHardMinVcn1,                 PPSMC_MSG_SetHardMinVcn1,			1),
 	MSG_MAP(SetSoftMinGfxclk,               PPSMC_MSG_SetSoftMinGfxclk,			1),
 	MSG_MAP(PrepareMp1ForUnload,            PPSMC_MSG_PrepareMp1ForUnload,		1),
 	MSG_MAP(SetDriverDramAddrHigh,          PPSMC_MSG_SetDriverDramAddrHigh,	1),
@@ -83,7 +86,8 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(GetEnabledSmuFeatures,          PPSMC_MSG_GetEnabledSmuFeatures,	1),
 	MSG_MAP(SetHardMinSocclkByFreq,         PPSMC_MSG_SetHardMinSocclkByFreq,	1),
 	MSG_MAP(SetSoftMinFclk,                 PPSMC_MSG_SetSoftMinFclk,			1),
-	MSG_MAP(SetSoftMinVcn,                  PPSMC_MSG_SetSoftMinVcn,			1),
+	MSG_MAP(SetSoftMinVcn0,                 PPSMC_MSG_SetSoftMinVcn0,			1),
+	MSG_MAP(SetSoftMinVcn1,                 PPSMC_MSG_SetSoftMinVcn1,			1),
 	MSG_MAP(EnableGfxImu,                   PPSMC_MSG_EnableGfxImu,				1),
 	MSG_MAP(AllowGfxOff,                    PPSMC_MSG_AllowGfxOff,				1),
 	MSG_MAP(DisallowGfxOff,                 PPSMC_MSG_DisallowGfxOff,			1),
@@ -91,9 +95,12 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(SetHardMinGfxClk,               PPSMC_MSG_SetHardMinGfxClk,			1),
 	MSG_MAP(SetSoftMaxSocclkByFreq,         PPSMC_MSG_SetSoftMaxSocclkByFreq,	1),
 	MSG_MAP(SetSoftMaxFclkByFreq,           PPSMC_MSG_SetSoftMaxFclkByFreq,		1),
-	MSG_MAP(SetSoftMaxVcn,                  PPSMC_MSG_SetSoftMaxVcn,			1),
-	MSG_MAP(PowerDownJpeg,                  PPSMC_MSG_PowerDownJpeg,			1),
-	MSG_MAP(PowerUpJpeg,                    PPSMC_MSG_PowerUpJpeg,				1),
+	MSG_MAP(SetSoftMaxVcn0,                 PPSMC_MSG_SetSoftMaxVcn0,			1),
+	MSG_MAP(SetSoftMaxVcn1,                 PPSMC_MSG_SetSoftMaxVcn1,			1),
+	MSG_MAP(PowerDownJpeg0,                 PPSMC_MSG_PowerDownJpeg0,			1),
+	MSG_MAP(PowerUpJpeg0,                   PPSMC_MSG_PowerUpJpeg0,				1),
+	MSG_MAP(PowerDownJpeg1,                 PPSMC_MSG_PowerDownJpeg1,			1),
+	MSG_MAP(PowerUpJpeg1,                   PPSMC_MSG_PowerUpJpeg1,				1),
 	MSG_MAP(SetHardMinFclkByFreq,           PPSMC_MSG_SetHardMinFclkByFreq,		1),
 	MSG_MAP(SetSoftMinSocclkByFreq,         PPSMC_MSG_SetSoftMinSocclkByFreq,	1),
 	MSG_MAP(PowerDownIspByTile,             PPSMC_MSG_PowerDownIspByTile,		1),
@@ -154,7 +161,7 @@ static int smu_v14_0_0_init_smc_tables(struct smu_context *smu)
 
 	SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t),
 		PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
-	SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t),
+	SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, max(sizeof(DpmClocks_t), sizeof(DpmClocks_t_v14_0_1)),
 		PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t),
 		PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
@@ -164,7 +171,7 @@ static int smu_v14_0_0_init_smc_tables(struct smu_context *smu)
 		goto err0_out;
 	smu_table->metrics_time = 0;
 
-	smu_table->clocks_table = kzalloc(sizeof(DpmClocks_t), GFP_KERNEL);
+	smu_table->clocks_table = kzalloc(max(sizeof(DpmClocks_t), sizeof(DpmClocks_t_v14_0_1)), GFP_KERNEL);
 	if (!smu_table->clocks_table)
 		goto err1_out;
 
@@ -586,6 +593,60 @@ static int smu_v14_0_0_mode2_reset(struct smu_context *smu)
 	return ret;
 }
 
+static int smu_v14_0_1_get_dpm_freq_by_index(struct smu_context *smu,
+						enum smu_clk_type clk_type,
+						uint32_t dpm_level,
+						uint32_t *freq)
+{
+	DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+
+	if (!clk_table || clk_type >= SMU_CLK_COUNT)
+		return -EINVAL;
+
+	switch (clk_type) {
+	case SMU_SOCCLK:
+		if (dpm_level >= clk_table->NumSocClkLevelsEnabled)
+			return -EINVAL;
+		*freq = clk_table->SocClocks[dpm_level];
+		break;
+	case SMU_VCLK:
+		if (dpm_level >= clk_table->Vcn0ClkLevelsEnabled)
+			return -EINVAL;
+		*freq = clk_table->VClocks0[dpm_level];
+		break;
+	case SMU_DCLK:
+		if (dpm_level >= clk_table->Vcn0ClkLevelsEnabled)
+			return -EINVAL;
+		*freq = clk_table->DClocks0[dpm_level];
+		break;
+	case SMU_VCLK1:
+		if (dpm_level >= clk_table->Vcn1ClkLevelsEnabled)
+			return -EINVAL;
+		*freq = clk_table->VClocks1[dpm_level];
+		break;
+	case SMU_DCLK1:
+		if (dpm_level >= clk_table->Vcn1ClkLevelsEnabled)
+			return -EINVAL;
+		*freq = clk_table->DClocks1[dpm_level];
+		break;
+	case SMU_UCLK:
+	case SMU_MCLK:
+		if (dpm_level >= clk_table->NumMemPstatesEnabled)
+			return -EINVAL;
+		*freq = clk_table->MemPstateTable[dpm_level].MemClk;
+		break;
+	case SMU_FCLK:
+		if (dpm_level >= clk_table->NumFclkLevelsEnabled)
+			return -EINVAL;
+		*freq = clk_table->FclkClocks_Freq[dpm_level];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int smu_v14_0_0_get_dpm_freq_by_index(struct smu_context *smu,
 						enum smu_clk_type clk_type,
 						uint32_t dpm_level,
@@ -630,6 +691,19 @@ static int smu_v14_0_0_get_dpm_freq_by_index(struct smu_context *smu,
 	return 0;
 }
 
+static int smu_v14_0_common_get_dpm_freq_by_index(struct smu_context *smu,
+						enum smu_clk_type clk_type,
+						uint32_t dpm_level,
+						uint32_t *freq)
+{
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+		smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq);
+	else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+		smu_v14_0_1_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq);
+
+	return 0;
+}
+
 static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu,
 						enum smu_clk_type clk_type)
 {
@@ -650,6 +724,8 @@ static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu,
 		break;
 	case SMU_VCLK:
 	case SMU_DCLK:
+	case SMU_VCLK1:
+	case SMU_DCLK1:
 		feature_id = SMU_FEATURE_VCN_DPM_BIT;
 		break;
 	default:
@@ -659,6 +735,126 @@ static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu,
 	return smu_cmn_feature_is_enabled(smu, feature_id);
 }
 
+static int smu_v14_0_1_get_dpm_ultimate_freq(struct smu_context *smu,
+							enum smu_clk_type clk_type,
+							uint32_t *min,
+							uint32_t *max)
+{
+	DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+	uint32_t clock_limit;
+	uint32_t max_dpm_level, min_dpm_level;
+	int ret = 0;
+
+	if (!smu_v14_0_0_clk_dpm_is_enabled(smu, clk_type)) {
+		switch (clk_type) {
+		case SMU_MCLK:
+		case SMU_UCLK:
+			clock_limit = smu->smu_table.boot_values.uclk;
+			break;
+		case SMU_FCLK:
+			clock_limit = smu->smu_table.boot_values.fclk;
+			break;
+		case SMU_GFXCLK:
+		case SMU_SCLK:
+			clock_limit = smu->smu_table.boot_values.gfxclk;
+			break;
+		case SMU_SOCCLK:
+			clock_limit = smu->smu_table.boot_values.socclk;
+			break;
+		case SMU_VCLK:
+		case SMU_VCLK1:
+			clock_limit = smu->smu_table.boot_values.vclk;
+			break;
+		case SMU_DCLK:
+		case SMU_DCLK1:
+			clock_limit = smu->smu_table.boot_values.dclk;
+			break;
+		default:
+			clock_limit = 0;
+			break;
+		}
+
+		/* clock in Mhz unit */
+		if (min)
+			*min = clock_limit / 100;
+		if (max)
+			*max = clock_limit / 100;
+
+		return 0;
+	}
+
+	if (max) {
+		switch (clk_type) {
+		case SMU_GFXCLK:
+		case SMU_SCLK:
+			*max = clk_table->MaxGfxClk;
+			break;
+		case SMU_MCLK:
+		case SMU_UCLK:
+		case SMU_FCLK:
+			max_dpm_level = 0;
+			break;
+		case SMU_SOCCLK:
+			max_dpm_level = clk_table->NumSocClkLevelsEnabled - 1;
+			break;
+		case SMU_VCLK:
+		case SMU_DCLK:
+			max_dpm_level = clk_table->Vcn0ClkLevelsEnabled - 1;
+			break;
+		case SMU_VCLK1:
+		case SMU_DCLK1:
+			max_dpm_level = clk_table->Vcn1ClkLevelsEnabled - 1;
+			break;
+		default:
+			ret = -EINVAL;
+			goto failed;
+		}
+
+		if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max);
+			if (ret)
+				goto failed;
+		}
+	}
+
+	if (min) {
+		switch (clk_type) {
+		case SMU_GFXCLK:
+		case SMU_SCLK:
+			*min = clk_table->MinGfxClk;
+			break;
+		case SMU_MCLK:
+		case SMU_UCLK:
+			min_dpm_level = clk_table->NumMemPstatesEnabled - 1;
+			break;
+		case SMU_FCLK:
+			min_dpm_level = clk_table->NumFclkLevelsEnabled - 1;
+			break;
+		case SMU_SOCCLK:
+			min_dpm_level = 0;
+			break;
+		case SMU_VCLK:
+		case SMU_DCLK:
+		case SMU_VCLK1:
+		case SMU_DCLK1:
+			min_dpm_level = 0;
+			break;
+		default:
+			ret = -EINVAL;
+			goto failed;
+		}
+
+		if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min);
+			if (ret)
+				goto failed;
+		}
+	}
+
+failed:
+	return ret;
+}
+
 static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu,
 							enum smu_clk_type clk_type,
 							uint32_t *min,
@@ -729,7 +925,7 @@ static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu,
 		}
 
 		if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
-			ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max);
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max);
 			if (ret)
 				goto failed;
 		}
@@ -761,7 +957,7 @@ static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu,
 		}
 
 		if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
-			ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min);
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min);
 			if (ret)
 				goto failed;
 		}
@@ -771,6 +967,19 @@ failed:
 	return ret;
 }
 
+static int smu_v14_0_common_get_dpm_ultimate_freq(struct smu_context *smu,
+							enum smu_clk_type clk_type,
+							uint32_t *min,
+							uint32_t *max)
+{
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+		smu_v14_0_0_get_dpm_ultimate_freq(smu, clk_type, min, max);
+	else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+		smu_v14_0_1_get_dpm_ultimate_freq(smu, clk_type, min, max);
+
+	return 0;
+}
+
 static int smu_v14_0_0_get_current_clk_freq(struct smu_context *smu,
 					    enum smu_clk_type clk_type,
 					    uint32_t *value)
@@ -804,6 +1013,37 @@ static int smu_v14_0_0_get_current_clk_freq(struct smu_context *smu,
 	return smu_v14_0_0_get_smu_metrics_data(smu, member_type, value);
 }
 
+static int smu_v14_0_1_get_dpm_level_count(struct smu_context *smu,
+					   enum smu_clk_type clk_type,
+					   uint32_t *count)
+{
+	DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+
+	switch (clk_type) {
+	case SMU_SOCCLK:
+		*count = clk_table->NumSocClkLevelsEnabled;
+		break;
+	case SMU_VCLK:
+	case SMU_DCLK:
+		*count = clk_table->Vcn0ClkLevelsEnabled;
+		break;
+	case SMU_VCLK1:
+	case SMU_DCLK1:
+		*count = clk_table->Vcn1ClkLevelsEnabled;
+		break;
+	case SMU_MCLK:
+		*count = clk_table->NumMemPstatesEnabled;
+		break;
+	case SMU_FCLK:
+		*count = clk_table->NumFclkLevelsEnabled;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int smu_v14_0_0_get_dpm_level_count(struct smu_context *smu,
 					   enum smu_clk_type clk_type,
 					   uint32_t *count)
@@ -833,6 +1073,18 @@ static int smu_v14_0_0_get_dpm_level_count(struct smu_context *smu,
 	return 0;
 }
 
+static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu,
+					   enum smu_clk_type clk_type,
+					   uint32_t *count)
+{
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+		smu_v14_0_0_get_dpm_level_count(smu, clk_type, count);
+	else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+		smu_v14_0_1_get_dpm_level_count(smu, clk_type, count);
+
+	return 0;
+}
+
 static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 					enum smu_clk_type clk_type, char *buf)
 {
@@ -859,18 +1111,20 @@ static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 	case SMU_SOCCLK:
 	case SMU_VCLK:
 	case SMU_DCLK:
+	case SMU_VCLK1:
+	case SMU_DCLK1:
 	case SMU_MCLK:
 	case SMU_FCLK:
 		ret = smu_v14_0_0_get_current_clk_freq(smu, clk_type, &cur_value);
 		if (ret)
 			break;
 
-		ret = smu_v14_0_0_get_dpm_level_count(smu, clk_type, &count);
+		ret = smu_v14_0_common_get_dpm_level_count(smu, clk_type, &count);
 		if (ret)
 			break;
 
 		for (i = 0; i < count; i++) {
-			ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, i, &value);
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value);
 			if (ret)
 				break;
 
@@ -933,8 +1187,13 @@ static int smu_v14_0_0_set_soft_freq_limited_range(struct smu_context *smu,
 		break;
 	case SMU_VCLK:
 	case SMU_DCLK:
-		msg_set_min = SMU_MSG_SetHardMinVcn;
-		msg_set_max = SMU_MSG_SetSoftMaxVcn;
+		msg_set_min = SMU_MSG_SetHardMinVcn0;
+		msg_set_max = SMU_MSG_SetSoftMaxVcn0;
+		break;
+	case SMU_VCLK1:
+	case SMU_DCLK1:
+		msg_set_min = SMU_MSG_SetHardMinVcn1;
+		msg_set_max = SMU_MSG_SetSoftMaxVcn1;
 		break;
 	default:
 		return -EINVAL;
@@ -964,11 +1223,11 @@ static int smu_v14_0_0_force_clk_levels(struct smu_context *smu,
 	case SMU_FCLK:
 	case SMU_VCLK:
 	case SMU_DCLK:
-		ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
+		ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
 		if (ret)
 			break;
 
-		ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
+		ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
 		if (ret)
 			break;
 
@@ -993,25 +1252,25 @@ static int smu_v14_0_0_set_performance_level(struct smu_context *smu,
 
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_HIGH:
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &sclk_max);
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &fclk_max);
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &socclk_max);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &sclk_max);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &fclk_max);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &socclk_max);
 		sclk_min = sclk_max;
 		fclk_min = fclk_max;
 		socclk_min = socclk_max;
 		break;
 	case AMD_DPM_FORCED_LEVEL_LOW:
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, NULL);
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, NULL);
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, NULL);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, NULL);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, NULL);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, NULL);
 		sclk_max = sclk_min;
 		fclk_max = fclk_min;
 		socclk_max = socclk_min;
 		break;
 	case AMD_DPM_FORCED_LEVEL_AUTO:
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, &sclk_max);
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, &fclk_max);
-		smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, &socclk_max);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, &sclk_max);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, &fclk_max);
+		smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, &socclk_max);
 		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
@@ -1060,6 +1319,18 @@ static int smu_v14_0_0_set_performance_level(struct smu_context *smu,
 	return ret;
 }
 
+static int smu_v14_0_1_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
+{
+	DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+
+	smu->gfx_default_hard_min_freq = clk_table->MinGfxClk;
+	smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk;
+	smu->gfx_actual_hard_min_freq = 0;
+	smu->gfx_actual_soft_max_freq = 0;
+
+	return 0;
+}
+
 static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
 {
 	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
@@ -1072,6 +1343,16 @@ static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *sm
 	return 0;
 }
 
+static int smu_v14_0_common_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
+{
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+		smu_v14_0_0_set_fine_grain_gfx_freq_parameters(smu);
+	else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+		smu_v14_0_1_set_fine_grain_gfx_freq_parameters(smu);
+
+	return 0;
+}
+
 static int smu_v14_0_0_set_vpe_enable(struct smu_context *smu,
 				      bool enable)
 {
@@ -1088,6 +1369,25 @@ static int smu_v14_0_0_set_umsch_mm_enable(struct smu_context *smu,
 					       0, NULL);
 }
 
+static int smu_14_0_1_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table)
+{
+	DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+	uint8_t idx;
+
+	/* Only the Clock information of SOC and VPE is copied to provide VPE DPM settings for use. */
+	for (idx = 0; idx < NUM_SOCCLK_DPM_LEVELS; idx++) {
+		clock_table->SocClocks[idx].Freq = (idx < clk_table->NumSocClkLevelsEnabled) ? clk_table->SocClocks[idx]:0;
+		clock_table->SocClocks[idx].Vol = 0;
+	}
+
+	for (idx = 0; idx < NUM_VPE_DPM_LEVELS; idx++) {
+		clock_table->VPEClocks[idx].Freq = (idx < clk_table->VpeClkLevelsEnabled) ? clk_table->VPEClocks[idx]:0;
+		clock_table->VPEClocks[idx].Vol = 0;
+	}
+
+	return 0;
+}
+
 static int smu_14_0_0_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table)
 {
 	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
@@ -1107,6 +1407,16 @@ static int smu_14_0_0_get_dpm_table(struct smu_context *smu, struct dpm_clocks *
 	return 0;
 }
 
+static int smu_v14_0_common_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table)
+{
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+		smu_14_0_0_get_dpm_table(smu, clock_table);
+	else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+		smu_14_0_1_get_dpm_table(smu, clock_table);
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v14_0_0_ppt_funcs = {
 	.check_fw_status = smu_v14_0_check_fw_status,
 	.check_fw_version = smu_v14_0_check_fw_version,
@@ -1128,16 +1438,16 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = {
 	.set_driver_table_location = smu_v14_0_set_driver_table_location,
 	.gfx_off_control = smu_v14_0_gfx_off_control,
 	.mode2_reset = smu_v14_0_0_mode2_reset,
-	.get_dpm_ultimate_freq = smu_v14_0_0_get_dpm_ultimate_freq,
+	.get_dpm_ultimate_freq = smu_v14_0_common_get_dpm_ultimate_freq,
 	.od_edit_dpm_table = smu_v14_0_od_edit_dpm_table,
 	.print_clk_levels = smu_v14_0_0_print_clk_levels,
 	.force_clk_levels = smu_v14_0_0_force_clk_levels,
 	.set_performance_level = smu_v14_0_0_set_performance_level,
-	.set_fine_grain_gfx_freq_parameters = smu_v14_0_0_set_fine_grain_gfx_freq_parameters,
+	.set_fine_grain_gfx_freq_parameters = smu_v14_0_common_set_fine_grain_gfx_freq_parameters,
 	.set_gfx_power_up_by_imu = smu_v14_0_set_gfx_power_up_by_imu,
 	.dpm_set_vpe_enable = smu_v14_0_0_set_vpe_enable,
 	.dpm_set_umsch_mm_enable = smu_v14_0_0_set_umsch_mm_enable,
-	.get_dpm_clock_table = smu_14_0_0_get_dpm_table,
+	.get_dpm_clock_table = smu_v14_0_common_get_dpm_table,
 };
 
 static void smu_v14_0_0_set_smu_mailbox_registers(struct smu_context *smu)
diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
index ebb6d8ebd44e..1e9259416980 100644
--- a/drivers/gpu/drm/ast/ast_dp.c
+++ b/drivers/gpu/drm/ast/ast_dp.c
@@ -180,6 +180,7 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on)
 {
 	struct ast_device *ast = to_ast_device(dev);
 	u8 video_on_off = on;
+	u32 i = 0;
 
 	// Video On/Off
 	ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on);
@@ -192,6 +193,8 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on)
 						ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) {
 			// wait 1 ms
 			mdelay(1);
+			if (++i > 200)
+				break;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c
index e7c4bef74aa4..4b2ae27f0a57 100644
--- a/drivers/gpu/drm/bridge/lontium-lt8912b.c
+++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c
@@ -441,23 +441,21 @@ lt8912_connector_mode_valid(struct drm_connector *connector,
 static int lt8912_connector_get_modes(struct drm_connector *connector)
 {
 	const struct drm_edid *drm_edid;
-	int ret = -1;
-	int num = 0;
 	struct lt8912 *lt = connector_to_lt8912(connector);
 	u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+	int ret, num;
 
 	drm_edid = drm_bridge_edid_read(lt->hdmi_port, connector);
 	drm_edid_connector_update(connector, drm_edid);
-	if (drm_edid) {
-		num = drm_edid_connector_add_modes(connector);
-	} else {
-		return ret;
-	}
+	if (!drm_edid)
+		return 0;
+
+	num = drm_edid_connector_add_modes(connector);
 
 	ret = drm_display_info_set_bus_formats(&connector->display_info,
 					       &bus_format, 1);
-	if (ret)
-		num = ret;
+	if (ret < 0)
+		num = 0;
 
 	drm_edid_free(drm_edid);
 	return num;
diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
index bcf8bccd86d6..f4f593ad8f79 100644
--- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
+++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
@@ -294,8 +294,8 @@ static struct mipi_dsi_device *lt9611uxc_attach_dsi(struct lt9611uxc *lt9611uxc,
 static int lt9611uxc_connector_get_modes(struct drm_connector *connector)
 {
 	struct lt9611uxc *lt9611uxc = connector_to_lt9611uxc(connector);
-	unsigned int count;
 	const struct drm_edid *drm_edid;
+	int count;
 
 	drm_edid = drm_bridge_edid_read(&lt9611uxc->bridge, connector);
 	drm_edid_connector_update(connector, drm_edid);
diff --git a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c
index bd61e20770a5..14a2a8473682 100644
--- a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c
@@ -52,7 +52,7 @@
  * @adapter: I2C adapter for the DDC bus
  * @offset: register offset
  * @buffer: buffer for return data
- * @size: sizo of the buffer
+ * @size: size of the buffer
  *
  * Reads @size bytes from the DP dual mode adaptor registers
  * starting at @offset.
@@ -116,7 +116,7 @@ EXPORT_SYMBOL(drm_dp_dual_mode_read);
  * @adapter: I2C adapter for the DDC bus
  * @offset: register offset
  * @buffer: buffer for write data
- * @size: sizo of the buffer
+ * @size: size of the buffer
  *
  * Writes @size bytes to the DP dual mode adaptor registers
  * starting at @offset.
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index 266826eac4a7..f5d4be897866 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -4111,6 +4111,13 @@ int drm_dp_bw_overhead(int lane_count, int hactive,
 	u32 overhead = 1000000;
 	int symbol_cycles;
 
+	if (lane_count == 0 || hactive == 0 || bpp_x16 == 0) {
+		DRM_DEBUG_KMS("Invalid BW overhead params: lane_count %d, hactive %d, bpp_x16 %d.%04d\n",
+			      lane_count, hactive,
+			      bpp_x16 >> 4, (bpp_x16 & 0xf) * 625);
+		return 0;
+	}
+
 	/*
 	 * DP Standard v2.1 2.6.4.1
 	 * SSC downspread and ref clock variation margin:
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 871e4e2129d6..0683a129b362 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -777,6 +777,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
 	unsigned int total_modes_count = 0;
 	struct drm_client_offset *offsets;
 	unsigned int connector_count = 0;
+	/* points to modes protected by mode_config.mutex */
 	struct drm_display_mode **modes;
 	struct drm_crtc **crtcs;
 	int i, ret = 0;
@@ -845,7 +846,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
 		drm_client_pick_crtcs(client, connectors, connector_count,
 				      crtcs, modes, 0, width, height);
 	}
-	mutex_unlock(&dev->mode_config.mutex);
 
 	drm_client_modeset_release(client);
 
@@ -875,6 +875,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
 			modeset->y = offset->y;
 		}
 	}
+	mutex_unlock(&dev->mode_config.mutex);
 
 	mutex_unlock(&client->modeset_mutex);
 out:
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index e814020bbcd3..cfbe020de54e 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -274,19 +274,24 @@ EXPORT_SYMBOL(drm_panel_disable);
  * The modes probed from the panel are automatically added to the connector
  * that the panel is attached to.
  *
- * Return: The number of modes available from the panel on success or a
- * negative error code on failure.
+ * Return: The number of modes available from the panel on success, or 0 on
+ * failure (no modes).
  */
 int drm_panel_get_modes(struct drm_panel *panel,
 			struct drm_connector *connector)
 {
 	if (!panel)
-		return -EINVAL;
+		return 0;
 
-	if (panel->funcs && panel->funcs->get_modes)
-		return panel->funcs->get_modes(panel, connector);
+	if (panel->funcs && panel->funcs->get_modes) {
+		int num;
 
-	return -EOPNOTSUPP;
+		num = panel->funcs->get_modes(panel, connector);
+		if (num > 0)
+			return num;
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_get_modes);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 7352bde299d5..03bd3c7bd0dc 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -582,7 +582,12 @@ int drm_gem_map_attach(struct dma_buf *dma_buf,
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 
-	if (!obj->funcs->get_sg_table)
+	/*
+	 * drm_gem_map_dma_buf() requires obj->get_sg_table(), but drivers
+	 * that implement their own ->map_dma_buf() do not.
+	 */
+	if (dma_buf->ops->map_dma_buf == drm_gem_map_dma_buf &&
+	    !obj->funcs->get_sg_table)
 		return -ENOSYS;
 
 	return drm_gem_pin(obj);
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 4d60cc810b57..bf2dd1f46b6c 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -422,6 +422,13 @@ static int drm_helper_probe_get_modes(struct drm_connector *connector)
 
 	count = connector_funcs->get_modes(connector);
 
+	/* The .get_modes() callback should not return negative values. */
+	if (count < 0) {
+		drm_err(connector->dev, ".get_modes() returned %pe\n",
+			ERR_PTR(count));
+		count = 0;
+	}
+
 	/*
 	 * Fallback for when DDC probe failed in drm_get_edid() and thus skipped
 	 * override/firmware EDID.
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index ca31bad6c576..f48c4343f469 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -74,16 +74,15 @@ static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data,
 {
 	struct exynos_dp_device *dp = to_dp(plat_data);
 	struct drm_display_mode *mode;
-	int num_modes = 0;
 
 	if (dp->plat_data.panel)
-		return num_modes;
+		return 0;
 
 	mode = drm_mode_create(connector->dev);
 	if (!mode) {
 		DRM_DEV_ERROR(dp->dev,
 			      "failed to create a new display mode.\n");
-		return num_modes;
+		return 0;
 	}
 
 	drm_display_mode_from_videomode(&dp->vm, mode);
@@ -94,7 +93,7 @@ static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data,
 	drm_mode_set_name(mode);
 	drm_mode_probed_add(connector, mode);
 
-	return num_modes + 1;
+	return 1;
 }
 
 static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 00382f28748a..f5bbba9ad225 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -316,14 +316,14 @@ static int vidi_get_modes(struct drm_connector *connector)
 	 */
 	if (!ctx->raw_edid) {
 		DRM_DEV_DEBUG_KMS(ctx->dev, "raw_edid is null.\n");
-		return -EFAULT;
+		return 0;
 	}
 
 	edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH;
 	edid = kmemdup(ctx->raw_edid, edid_len, GFP_KERNEL);
 	if (!edid) {
 		DRM_DEV_DEBUG_KMS(ctx->dev, "failed to allocate edid\n");
-		return -ENOMEM;
+		return 0;
 	}
 
 	drm_connector_update_edid_property(connector, edid);
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 43bed6cbaaea..b1d02dec3774 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (!hdata->ddc_adpt)
-		return -ENODEV;
+		return 0;
 
 	edid = drm_get_edid(connector, hdata->ddc_adpt);
 	if (!edid)
-		return -ENODEV;
+		return 0;
 
 	hdata->dvi_mode = !connector->display_info.is_hdmi;
 	DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n",
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 3ef6ed41e62b..fba73c38e235 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -33,9 +33,9 @@ endif
 subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
 
 # Fine grained warnings disable
-CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init)
-CFLAGS_display/intel_display_device.o = $(call cc-disable-warning, override-init)
-CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init)
+CFLAGS_i915_pci.o = -Wno-override-init
+CFLAGS_display/intel_display_device.o = -Wno-override-init
+CFLAGS_display/intel_fbdev.o = -Wno-override-init
 
 # Support compiling the display code separately for both i915 and xe
 # drivers. Define I915 when building i915.
@@ -118,6 +118,7 @@ gt-y += \
 	gt/intel_ggtt_fencing.o \
 	gt/intel_gt.o \
 	gt/intel_gt_buffer_pool.o \
+	gt/intel_gt_ccs_mode.o \
 	gt/intel_gt_clock_utils.o \
 	gt/intel_gt_debugfs.o \
 	gt/intel_gt_engines_debugfs.o \
diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index dfe0b07a122d..06ec04e667e3 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -717,7 +717,6 @@ static void g4x_enable_dp(struct intel_atomic_state *state,
 {
 	intel_enable_dp(state, encoder, pipe_config, conn_state);
 	intel_edp_backlight_on(pipe_config, conn_state);
-	encoder->audio_enable(encoder, pipe_config, conn_state);
 }
 
 static void vlv_enable_dp(struct intel_atomic_state *state,
@@ -726,7 +725,6 @@ static void vlv_enable_dp(struct intel_atomic_state *state,
 			  const struct drm_connector_state *conn_state)
 {
 	intel_edp_backlight_on(pipe_config, conn_state);
-	encoder->audio_enable(encoder, pipe_config, conn_state);
 }
 
 static void g4x_pre_enable_dp(struct intel_atomic_state *state,
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index eda4a8b88590..ac456a2275db 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1155,7 +1155,6 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 	}
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
 
 	/* ensure all panel commands dispatched before enabling transcoder */
 	wait_for_cmds_dispatched_to_panel(encoder);
@@ -1256,6 +1255,8 @@ static void gen11_dsi_enable(struct intel_atomic_state *state,
 	/* step6d: enable dsi transcoder */
 	gen11_dsi_enable_transcoder(encoder);
 
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
+
 	/* step7: enable backlight */
 	intel_backlight_enable(crtc_state, conn_state);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index fe52c06271ef..52bd3576835b 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1955,16 +1955,12 @@ static int get_init_otp_deassert_fragment_len(struct drm_i915_private *i915,
  * these devices we split the init OTP sequence into a deassert sequence and
  * the actual init OTP part.
  */
-static void fixup_mipi_sequences(struct drm_i915_private *i915,
-				 struct intel_panel *panel)
+static void vlv_fixup_mipi_sequences(struct drm_i915_private *i915,
+				     struct intel_panel *panel)
 {
 	u8 *init_otp;
 	int len;
 
-	/* Limit this to VLV for now. */
-	if (!IS_VALLEYVIEW(i915))
-		return;
-
 	/* Limit this to v1 vid-mode sequences */
 	if (panel->vbt.dsi.config->is_cmd_mode ||
 	    panel->vbt.dsi.seq_version != 1)
@@ -2000,6 +1996,41 @@ static void fixup_mipi_sequences(struct drm_i915_private *i915,
 	panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1;
 }
 
+/*
+ * Some machines (eg. Lenovo 82TQ) appear to have broken
+ * VBT sequences:
+ * - INIT_OTP is not present at all
+ * - what should be in INIT_OTP is in DISPLAY_ON
+ * - what should be in DISPLAY_ON is in BACKLIGHT_ON
+ *   (along with the actual backlight stuff)
+ *
+ * To make those work we simply swap DISPLAY_ON and INIT_OTP.
+ *
+ * TODO: Do we need to limit this to specific machines,
+ *       or examine the contents of the sequences to
+ *       avoid false positives?
+ */
+static void icl_fixup_mipi_sequences(struct drm_i915_private *i915,
+				     struct intel_panel *panel)
+{
+	if (!panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] &&
+	    panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]) {
+		drm_dbg_kms(&i915->drm, "Broken VBT: Swapping INIT_OTP and DISPLAY_ON sequences\n");
+
+		swap(panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP],
+		     panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]);
+	}
+}
+
+static void fixup_mipi_sequences(struct drm_i915_private *i915,
+				 struct intel_panel *panel)
+{
+	if (DISPLAY_VER(i915) >= 11)
+		icl_fixup_mipi_sequences(i915, panel);
+	else if (IS_VALLEYVIEW(i915))
+		vlv_fixup_mipi_sequences(i915, panel);
+}
+
 static void
 parse_mipi_sequence(struct drm_i915_private *i915,
 		    struct intel_panel *panel)
@@ -3351,6 +3382,9 @@ bool intel_bios_encoder_supports_dp_dual_mode(const struct intel_bios_encoder_da
 {
 	const struct child_device_config *child = &devdata->child;
 
+	if (!devdata)
+		return false;
+
 	if (!intel_bios_encoder_supports_dp(devdata) ||
 	    !intel_bios_encoder_supports_hdmi(devdata))
 		return false;
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ed89b86ea625..f672bfd70d45 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2534,7 +2534,8 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state)
 		intel_atomic_get_old_cdclk_state(state);
 	const struct intel_cdclk_state *new_cdclk_state =
 		intel_atomic_get_new_cdclk_state(state);
-	enum pipe pipe = new_cdclk_state->pipe;
+	struct intel_cdclk_config cdclk_config;
+	enum pipe pipe;
 
 	if (!intel_cdclk_changed(&old_cdclk_state->actual,
 				 &new_cdclk_state->actual))
@@ -2543,12 +2544,25 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state)
 	if (IS_DG2(i915))
 		intel_cdclk_pcode_pre_notify(state);
 
-	if (pipe == INVALID_PIPE ||
-	    old_cdclk_state->actual.cdclk <= new_cdclk_state->actual.cdclk) {
-		drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+	if (new_cdclk_state->disable_pipes) {
+		cdclk_config = new_cdclk_state->actual;
+		pipe = INVALID_PIPE;
+	} else {
+		if (new_cdclk_state->actual.cdclk >= old_cdclk_state->actual.cdclk) {
+			cdclk_config = new_cdclk_state->actual;
+			pipe = new_cdclk_state->pipe;
+		} else {
+			cdclk_config = old_cdclk_state->actual;
+			pipe = INVALID_PIPE;
+		}
 
-		intel_set_cdclk(i915, &new_cdclk_state->actual, pipe);
+		cdclk_config.voltage_level = max(new_cdclk_state->actual.voltage_level,
+						 old_cdclk_state->actual.voltage_level);
 	}
+
+	drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+
+	intel_set_cdclk(i915, &cdclk_config, pipe);
 }
 
 /**
@@ -2566,7 +2580,7 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state)
 		intel_atomic_get_old_cdclk_state(state);
 	const struct intel_cdclk_state *new_cdclk_state =
 		intel_atomic_get_new_cdclk_state(state);
-	enum pipe pipe = new_cdclk_state->pipe;
+	enum pipe pipe;
 
 	if (!intel_cdclk_changed(&old_cdclk_state->actual,
 				 &new_cdclk_state->actual))
@@ -2575,12 +2589,15 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state)
 	if (IS_DG2(i915))
 		intel_cdclk_pcode_post_notify(state);
 
-	if (pipe != INVALID_PIPE &&
-	    old_cdclk_state->actual.cdclk > new_cdclk_state->actual.cdclk) {
-		drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+	if (!new_cdclk_state->disable_pipes &&
+	    new_cdclk_state->actual.cdclk < old_cdclk_state->actual.cdclk)
+		pipe = new_cdclk_state->pipe;
+	else
+		pipe = INVALID_PIPE;
+
+	drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
 
-		intel_set_cdclk(i915, &new_cdclk_state->actual, pipe);
-	}
+	intel_set_cdclk(i915, &new_cdclk_state->actual, pipe);
 }
 
 static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
@@ -3058,6 +3075,7 @@ static struct intel_global_state *intel_cdclk_duplicate_state(struct intel_globa
 		return NULL;
 
 	cdclk_state->pipe = INVALID_PIPE;
+	cdclk_state->disable_pipes = false;
 
 	return &cdclk_state->base;
 }
@@ -3236,6 +3254,8 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 		if (ret)
 			return ret;
 
+		new_cdclk_state->disable_pipes = true;
+
 		drm_dbg_kms(&dev_priv->drm,
 			    "Modeset required for cdclk change\n");
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h
index 48fd7d39e0cd..71bc032bfef1 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.h
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.h
@@ -51,6 +51,9 @@ struct intel_cdclk_state {
 
 	/* bitmask of active pipes */
 	u8 active_pipes;
+
+	/* update cdclk with pipes disabled */
+	bool disable_pipes;
 };
 
 int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index f8b33999d43f..0d3da55e1c24 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -36,12 +36,10 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(plane_state->uapi.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->hw.fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 base;
 
 	if (DISPLAY_INFO(dev_priv)->cursor_needs_physical)
-		base = i915_gem_object_get_dma_address(obj, 0);
+		base = plane_state->phys_dma_addr;
 	else
 		base = intel_plane_ggtt_offset(plane_state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index c587a8efeafc..c17462b4c2ac 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -4256,7 +4256,12 @@ static bool m_n_equal(const struct intel_link_m_n *m_n_1,
 static bool crtcs_port_sync_compatible(const struct intel_crtc_state *crtc_state1,
 				       const struct intel_crtc_state *crtc_state2)
 {
+	/*
+	 * FIXME the modeset sequence is currently wrong and
+	 * can't deal with bigjoiner + port sync at the same time.
+	 */
 	return crtc_state1->hw.active && crtc_state2->hw.active &&
+		!crtc_state1->bigjoiner_pipes && !crtc_state2->bigjoiner_pipes &&
 		crtc_state1->output_types == crtc_state2->output_types &&
 		crtc_state1->output_format == crtc_state2->output_format &&
 		crtc_state1->lane_count == crtc_state2->lane_count &&
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ab2f52d21bad..8af9e6128277 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2709,15 +2709,6 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
 	 */
 	intel_de_write(dev_priv, PIPESRC(pipe),
 		       PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1));
-
-	if (!crtc_state->enable_psr2_su_region_et)
-		return;
-
-	width = drm_rect_width(&crtc_state->psr2_su_area);
-	height = drm_rect_height(&crtc_state->psr2_su_area);
-
-	intel_de_write(dev_priv, PIPE_SRCSZ_ERLY_TPT(pipe),
-		       PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1));
 }
 
 static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h
index fe4268813786..9b1bce2624b9 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.h
+++ b/drivers/gpu/drm/i915/display/intel_display_device.h
@@ -47,6 +47,7 @@ struct drm_printer;
 #define HAS_DPT(i915)			(DISPLAY_VER(i915) >= 13)
 #define HAS_DSB(i915)			(DISPLAY_INFO(i915)->has_dsb)
 #define HAS_DSC(__i915)			(DISPLAY_RUNTIME_INFO(__i915)->has_dsc)
+#define HAS_DSC_MST(__i915)		(DISPLAY_VER(__i915) >= 12 && HAS_DSC(__i915))
 #define HAS_FBC(i915)			(DISPLAY_RUNTIME_INFO(i915)->fbc_mask != 0)
 #define HAS_FPGA_DBG_UNCLAIMED(i915)	(DISPLAY_INFO(i915)->has_fpga_dbg)
 #define HAS_FW_BLC(i915)		(DISPLAY_VER(i915) >= 3)
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index e67cd5b02e84..bf3f942e19c3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -727,6 +727,7 @@ struct intel_plane_state {
 #define PLANE_HAS_FENCE BIT(0)
 
 	struct intel_fb_view view;
+	u32 phys_dma_addr; /* for cursor_needs_physical */
 
 	/* Plane pxp decryption state */
 	bool decrypt;
@@ -1422,6 +1423,8 @@ struct intel_crtc_state {
 
 	u32 psr2_man_track_ctl;
 
+	u32 pipe_srcsz_early_tpt;
+
 	struct drm_rect psr2_su_area;
 
 	/* Variable Refresh Rate state */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f0c3ed37b350..e583515f9b25 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -67,6 +67,7 @@
 #include "intel_dp_tunnel.h"
 #include "intel_dpio_phy.h"
 #include "intel_dpll.h"
+#include "intel_drrs.h"
 #include "intel_fifo_underrun.h"
 #include "intel_hdcp.h"
 #include "intel_hdmi.h"
@@ -498,7 +499,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 	/* The values must be in increasing order */
 	static const int mtl_rates[] = {
 		162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000,
-		810000,	1000000, 1350000, 2000000,
+		810000,	1000000, 2000000,
 	};
 	static const int icl_rates[] = {
 		162000, 216000, 270000, 324000, 432000, 540000, 648000, 810000,
@@ -1421,7 +1422,8 @@ static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp,
 	if (DISPLAY_VER(dev_priv) >= 12)
 		return true;
 
-	if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A)
+	if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A &&
+	    !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST))
 		return true;
 
 	return false;
@@ -1916,8 +1918,9 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp,
 	dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1);
 
 	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) {
-		if (valid_dsc_bpp[i] < dsc_min_bpp ||
-		    valid_dsc_bpp[i] > dsc_max_bpp)
+		if (valid_dsc_bpp[i] < dsc_min_bpp)
+			continue;
+		if (valid_dsc_bpp[i] > dsc_max_bpp)
 			break;
 
 		ret = dsc_compute_link_config(intel_dp,
@@ -2683,15 +2686,6 @@ intel_dp_compute_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp,
 		intel_hdmi_infoframe_enable(HDMI_PACKET_TYPE_GAMUT_METADATA);
 }
 
-static bool cpu_transcoder_has_drrs(struct drm_i915_private *i915,
-				    enum transcoder cpu_transcoder)
-{
-	if (HAS_DOUBLE_BUFFERED_M_N(i915))
-		return true;
-
-	return intel_cpu_transcoder_has_m2_n2(i915, cpu_transcoder);
-}
-
 static bool can_enable_drrs(struct intel_connector *connector,
 			    const struct intel_crtc_state *pipe_config,
 			    const struct drm_display_mode *downclock_mode)
@@ -2714,7 +2708,7 @@ static bool can_enable_drrs(struct intel_connector *connector,
 	if (pipe_config->has_pch_encoder)
 		return false;
 
-	if (!cpu_transcoder_has_drrs(i915, pipe_config->cpu_transcoder))
+	if (!intel_cpu_transcoder_has_drrs(i915, pipe_config->cpu_transcoder))
 		return false;
 
 	return downclock_mode &&
@@ -2731,7 +2725,11 @@ intel_dp_drrs_compute_config(struct intel_connector *connector,
 		intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode);
 	int pixel_clock;
 
-	if (has_seamless_m_n(connector))
+	/*
+	 * FIXME all joined pipes share the same transcoder.
+	 * Need to account for that when updating M/N live.
+	 */
+	if (has_seamless_m_n(connector) && !pipe_config->bigjoiner_pipes)
 		pipe_config->update_m_n = true;
 
 	if (!can_enable_drrs(connector, pipe_config, downclock_mode)) {
@@ -6565,6 +6563,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port,
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->sync_state = intel_dp_connector_sync_state;
 
 	if (!intel_edp_init_connector(intel_dp, intel_connector)) {
 		intel_dp_aux_fini(intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index b98a87883fef..9db43bd81ce2 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -691,12 +691,15 @@ int intel_dp_hdcp_get_remote_capability(struct intel_connector *connector,
 	u8 bcaps;
 	int ret;
 
+	*hdcp_capable = false;
+	*hdcp2_capable = false;
 	if (!intel_encoder_is_mst(connector->encoder))
 		return -EINVAL;
 
 	ret =  _intel_dp_hdcp2_get_capability(aux, hdcp2_capable);
 	if (ret)
-		return ret;
+		drm_dbg_kms(&i915->drm,
+			    "HDCP2 DPCD capability read failed err: %d\n", ret);
 
 	ret = intel_dp_hdcp_read_bcaps(aux, i915, &bcaps);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 53aec023ce92..b651c990af85 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1355,7 +1355,7 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 		return 0;
 	}
 
-	if (DISPLAY_VER(dev_priv) >= 10 &&
+	if (HAS_DSC_MST(dev_priv) &&
 	    drm_dp_sink_supports_dsc(intel_connector->dp.dsc_dpcd)) {
 		/*
 		 * TBD pass the connector BPC,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index ff480f171f75..b6d24410740f 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2554,7 +2554,7 @@ static void icl_wrpll_params_populate(struct skl_wrpll_params *params,
 static bool
 ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915)
 {
-	return (((IS_ELKHARTLAKE(i915) || IS_JASPERLAKE(i915)) &&
+	return ((IS_ELKHARTLAKE(i915) &&
 		 IS_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) ||
 		 IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) &&
 		 i915->display.dpll.ref_clks.nssc == 38400;
diff --git a/drivers/gpu/drm/i915/display/intel_drrs.c b/drivers/gpu/drm/i915/display/intel_drrs.c
index 169ef38ff188..597f8bd6aa1a 100644
--- a/drivers/gpu/drm/i915/display/intel_drrs.c
+++ b/drivers/gpu/drm/i915/display/intel_drrs.c
@@ -63,6 +63,15 @@ const char *intel_drrs_type_str(enum drrs_type drrs_type)
 	return str[drrs_type];
 }
 
+bool intel_cpu_transcoder_has_drrs(struct drm_i915_private *i915,
+				   enum transcoder cpu_transcoder)
+{
+	if (HAS_DOUBLE_BUFFERED_M_N(i915))
+		return true;
+
+	return intel_cpu_transcoder_has_m2_n2(i915, cpu_transcoder);
+}
+
 static void
 intel_drrs_set_refresh_rate_pipeconf(struct intel_crtc *crtc,
 				     enum drrs_refresh_rate refresh_rate)
@@ -312,9 +321,8 @@ static int intel_drrs_debugfs_status_show(struct seq_file *m, void *unused)
 	mutex_lock(&crtc->drrs.mutex);
 
 	seq_printf(m, "DRRS capable: %s\n",
-		   str_yes_no(crtc_state->has_drrs ||
-			      HAS_DOUBLE_BUFFERED_M_N(i915) ||
-			      intel_cpu_transcoder_has_m2_n2(i915, crtc_state->cpu_transcoder)));
+		   str_yes_no(intel_cpu_transcoder_has_drrs(i915,
+							    crtc_state->cpu_transcoder)));
 
 	seq_printf(m, "DRRS enabled: %s\n",
 		   str_yes_no(crtc_state->has_drrs));
diff --git a/drivers/gpu/drm/i915/display/intel_drrs.h b/drivers/gpu/drm/i915/display/intel_drrs.h
index 8ef5f93a80ff..0982f95eab72 100644
--- a/drivers/gpu/drm/i915/display/intel_drrs.h
+++ b/drivers/gpu/drm/i915/display/intel_drrs.h
@@ -9,12 +9,15 @@
 #include <linux/types.h>
 
 enum drrs_type;
+enum transcoder;
 struct drm_i915_private;
 struct intel_atomic_state;
 struct intel_crtc;
 struct intel_crtc_state;
 struct intel_connector;
 
+bool intel_cpu_transcoder_has_drrs(struct drm_i915_private *i915,
+				   enum transcoder cpu_transcoder);
 const char *intel_drrs_type_str(enum drrs_type drrs_type);
 bool intel_drrs_is_active(struct intel_crtc *crtc);
 void intel_drrs_activate(const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index d62e050185e7..e4515bf92038 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -340,6 +340,17 @@ static int intel_dsb_dewake_scanline(const struct intel_crtc_state *crtc_state)
 	return max(0, vblank_start - intel_usecs_to_scanlines(adjusted_mode, latency));
 }
 
+static u32 dsb_chicken(struct intel_crtc *crtc)
+{
+	if (crtc->mode_flags & I915_MODE_FLAG_VRR)
+		return DSB_CTRL_WAIT_SAFE_WINDOW |
+			DSB_CTRL_NO_WAIT_VBLANK |
+			DSB_INST_WAIT_SAFE_WINDOW |
+			DSB_INST_NO_WAIT_VBLANK;
+	else
+		return 0;
+}
+
 static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl,
 			      int dewake_scanline)
 {
@@ -361,6 +372,9 @@ static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl,
 	intel_de_write_fw(dev_priv, DSB_CTRL(pipe, dsb->id),
 			  ctrl | DSB_ENABLE);
 
+	intel_de_write_fw(dev_priv, DSB_CHICKEN(pipe, dsb->id),
+			  dsb_chicken(crtc));
+
 	intel_de_write_fw(dev_priv, DSB_HEAD(pipe, dsb->id),
 			  intel_dsb_buffer_ggtt_offset(&dsb->dsb_buf));
 
diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 7b42aef37d2f..b6df9baf481b 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -255,6 +255,16 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state)
 			return PTR_ERR(vma);
 
 		plane_state->ggtt_vma = vma;
+
+		/*
+		 * Pre-populate the dma address before we enter the vblank
+		 * evade critical section as i915_gem_object_get_dma_address()
+		 * will trigger might_sleep() even if it won't actually sleep,
+		 * which is the case when the fb has already been pinned.
+		 */
+		if (phys_cursor)
+			plane_state->phys_dma_addr =
+				i915_gem_object_get_dma_address(intel_fb_obj(fb), 0);
 	} else {
 		struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 6927785fd6ff..aabd018bd737 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1422,6 +1422,17 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 		return;
 	}
 
+	/*
+	 * FIXME figure out what is wrong with PSR+bigjoiner and
+	 * fix it. Presumably something related to the fact that
+	 * PSR is a transcoder level feature.
+	 */
+	if (crtc_state->bigjoiner_pipes) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "PSR disabled due to bigjoiner\n");
+		return;
+	}
+
 	if (CAN_PANEL_REPLAY(intel_dp))
 		crtc_state->has_panel_replay = true;
 	else
@@ -1994,6 +2005,7 @@ static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp)
 
 void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	struct intel_encoder *encoder;
@@ -2013,6 +2025,12 @@ void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_st
 
 	intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(cpu_transcoder),
 		       crtc_state->psr2_man_track_ctl);
+
+	if (!crtc_state->enable_psr2_su_region_et)
+		return;
+
+	intel_de_write(dev_priv, PIPE_SRCSZ_ERLY_TPT(crtc->pipe),
+		       crtc_state->pipe_srcsz_early_tpt);
 }
 
 static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state,
@@ -2051,6 +2069,20 @@ exit:
 	crtc_state->psr2_man_track_ctl = val;
 }
 
+static u32 psr2_pipe_srcsz_early_tpt_calc(struct intel_crtc_state *crtc_state,
+					  bool full_update)
+{
+	int width, height;
+
+	if (!crtc_state->enable_psr2_su_region_et || full_update)
+		return 0;
+
+	width = drm_rect_width(&crtc_state->psr2_su_area);
+	height = drm_rect_height(&crtc_state->psr2_su_area);
+
+	return PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1);
+}
+
 static void clip_area_update(struct drm_rect *overlap_damage_area,
 			     struct drm_rect *damage_area,
 			     struct drm_rect *pipe_src)
@@ -2095,21 +2127,36 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st
  * cursor fully when cursor is in SU area.
  */
 static void
-intel_psr2_sel_fetch_et_alignment(struct intel_crtc_state *crtc_state,
-				  struct intel_plane_state *cursor_state)
+intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state,
+				  struct intel_crtc *crtc)
 {
-	struct drm_rect inter;
+	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+	struct intel_plane_state *new_plane_state;
+	struct intel_plane *plane;
+	int i;
 
-	if (!crtc_state->enable_psr2_su_region_et ||
-	    !cursor_state->uapi.visible)
+	if (!crtc_state->enable_psr2_su_region_et)
 		return;
 
-	inter = crtc_state->psr2_su_area;
-	if (!drm_rect_intersect(&inter, &cursor_state->uapi.dst))
-		return;
+	for_each_new_intel_plane_in_state(state, plane, new_plane_state, i) {
+		struct drm_rect inter;
+
+		if (new_plane_state->uapi.crtc != crtc_state->uapi.crtc)
+			continue;
+
+		if (plane->id != PLANE_CURSOR)
+			continue;
+
+		if (!new_plane_state->uapi.visible)
+			continue;
 
-	clip_area_update(&crtc_state->psr2_su_area, &cursor_state->uapi.dst,
-			 &crtc_state->pipe_src);
+		inter = crtc_state->psr2_su_area;
+		if (!drm_rect_intersect(&inter, &new_plane_state->uapi.dst))
+			continue;
+
+		clip_area_update(&crtc_state->psr2_su_area, &new_plane_state->uapi.dst,
+				 &crtc_state->pipe_src);
+	}
 }
 
 /*
@@ -2152,8 +2199,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
-	struct intel_plane_state *new_plane_state, *old_plane_state,
-		*cursor_plane_state = NULL;
+	struct intel_plane_state *new_plane_state, *old_plane_state;
 	struct intel_plane *plane;
 	bool full_update = false;
 	int i, ret;
@@ -2238,13 +2284,6 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 		damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1;
 
 		clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &crtc_state->pipe_src);
-
-		/*
-		 * Cursor plane new state is stored to adjust su area to cover
-		 * cursor are fully.
-		 */
-		if (plane->id == PLANE_CURSOR)
-			cursor_plane_state = new_plane_state;
 	}
 
 	/*
@@ -2273,9 +2312,13 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	if (ret)
 		return ret;
 
-	/* Adjust su area to cover cursor fully as necessary */
-	if (cursor_plane_state)
-		intel_psr2_sel_fetch_et_alignment(crtc_state, cursor_plane_state);
+	/*
+	 * Adjust su area to cover cursor fully as necessary (early
+	 * transport). This needs to be done after
+	 * drm_atomic_add_affected_planes to ensure visible cursor is added into
+	 * affected planes even when cursor is not updated by itself.
+	 */
+	intel_psr2_sel_fetch_et_alignment(state, crtc);
 
 	intel_psr2_sel_fetch_pipe_alignment(crtc_state);
 
@@ -2338,6 +2381,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 
 skip_sel_fetch_set_loop:
 	psr2_man_trk_ctl_calc(crtc_state, full_update);
+	crtc_state->pipe_srcsz_early_tpt =
+		psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 5f9e748adc89..0cd9c183f621 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1842,8 +1842,6 @@ static void intel_disable_sdvo(struct intel_atomic_state *state,
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	u32 temp;
 
-	encoder->audio_disable(encoder, old_crtc_state, conn_state);
-
 	intel_sdvo_set_active_outputs(intel_sdvo, 0);
 	if (0)
 		intel_sdvo_set_encoder_power_state(intel_sdvo,
@@ -1935,8 +1933,6 @@ static void intel_enable_sdvo(struct intel_atomic_state *state,
 		intel_sdvo_set_encoder_power_state(intel_sdvo,
 						   DRM_MODE_DPMS_ON);
 	intel_sdvo_set_active_outputs(intel_sdvo, intel_sdvo_connector->output_flag);
-
-	encoder->audio_enable(encoder, pipe_config, conn_state);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c
index 5d905f932cb4..f542ee1db1d9 100644
--- a/drivers/gpu/drm/i915/display/intel_vrr.c
+++ b/drivers/gpu/drm/i915/display/intel_vrr.c
@@ -117,6 +117,13 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state,
 	const struct drm_display_info *info = &connector->base.display_info;
 	int vmin, vmax;
 
+	/*
+	 * FIXME all joined pipes share the same transcoder.
+	 * Need to account for that during VRR toggle/push/etc.
+	 */
+	if (crtc_state->bigjoiner_pipes)
+		return;
+
 	if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
 		return;
 
@@ -187,10 +194,11 @@ void intel_vrr_set_transcoder_timings(const struct intel_crtc_state *crtc_state)
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
 	/*
-	 * TRANS_SET_CONTEXT_LATENCY with VRR enabled
-	 * requires this chicken bit on ADL/DG2.
+	 * This bit seems to have two meanings depending on the platform:
+	 * TGL: generate VRR "safe window" for DSB vblank waits
+	 * ADL/DG2: make TRANS_SET_CONTEXT_LATENCY effective with VRR
 	 */
-	if (DISPLAY_VER(dev_priv) == 13)
+	if (IS_DISPLAY_VER(dev_priv, 12, 13))
 		intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder),
 			     0, PIPE_VBLANK_WITH_DELAY);
 
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index e941e2e4fd14..860574d04f88 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -2295,6 +2295,9 @@ static u8 skl_get_plane_caps(struct drm_i915_private *i915,
 	if (HAS_4TILE(i915))
 		caps |= INTEL_PLANE_CAP_TILING_4;
 
+	if (!IS_ENABLED(I915) && !HAS_FLAT_CCS(i915))
+		return caps;
+
 	if (skl_plane_has_rc_ccs(i915, pipe, plane_id)) {
 		caps |= INTEL_PLANE_CAP_CCS_RC;
 		if (DISPLAY_VER(i915) >= 12)
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index fa46d2308b0e..81bf2216371b 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -961,6 +961,9 @@ static int gen8_init_rsvd(struct i915_address_space *vm)
 	struct i915_vma *vma;
 	int ret;
 
+	if (!intel_gt_needs_wa_16018031267(vm->gt))
+		return 0;
+
 	/* The memory will be used only by GPU. */
 	obj = i915_gem_object_create_lmem(i915, PAGE_SIZE,
 					  I915_BO_ALLOC_VOLATILE |
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 1ade568ffbfa..7a6dc371c384 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -908,6 +908,23 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 		info->engine_mask &= ~BIT(GSC0);
 	}
 
+	/*
+	 * Do not create the command streamer for CCS slices beyond the first.
+	 * All the workload submitted to the first engine will be shared among
+	 * all the slices.
+	 *
+	 * Once the user will be allowed to customize the CCS mode, then this
+	 * check needs to be removed.
+	 */
+	if (IS_DG2(gt->i915)) {
+		u8 first_ccs = __ffs(CCS_MASK(gt));
+
+		/* Mask off all the CCS engine */
+		info->engine_mask &= ~GENMASK(CCS3, CCS0);
+		/* Put back in the first CCS engine */
+		info->engine_mask |= BIT(_CCS(first_ccs));
+	}
+
 	return info->engine_mask;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 96bdb93a948d..fb7bff27b45a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -279,9 +279,6 @@ static int __engine_park(struct intel_wakeref *wf)
 	intel_engine_park_heartbeat(engine);
 	intel_breadcrumbs_park(engine->breadcrumbs);
 
-	/* Must be reset upon idling, or we may miss the busy wakeup. */
-	GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN);
-
 	if (engine->park)
 		engine->park(engine);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 42aade0faf2d..b061a0a0d6b0 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3272,6 +3272,9 @@ static void execlists_park(struct intel_engine_cs *engine)
 {
 	cancel_timer(&engine->execlists.timer);
 	cancel_timer(&engine->execlists.preempt);
+
+	/* Reset upon idling, or we may delay the busy wakeup. */
+	WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN);
 }
 
 static void add_to_engine(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..6a2c2718bcc3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -1024,6 +1024,12 @@ enum i915_map_type intel_gt_coherent_map_type(struct intel_gt *gt,
 		return I915_MAP_WC;
 }
 
+bool intel_gt_needs_wa_16018031267(struct intel_gt *gt)
+{
+	/* Wa_16018031267, Wa_16018063123 */
+	return IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 55), IP_VER(12, 71));
+}
+
 bool intel_gt_needs_wa_22016122933(struct intel_gt *gt)
 {
 	return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 608f5c872928..003eb93b826f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -82,17 +82,18 @@ struct drm_printer;
 		  ##__VA_ARGS__);					\
 } while (0)
 
-#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
-	IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 55), IP_VER(12, 71)) && \
-	engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
-
 static inline bool gt_is_root(struct intel_gt *gt)
 {
 	return !gt->info.id;
 }
 
+bool intel_gt_needs_wa_16018031267(struct intel_gt *gt);
 bool intel_gt_needs_wa_22016122933(struct intel_gt *gt);
 
+#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
+	intel_gt_needs_wa_16018031267(engine->gt) && \
+	engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
+
 static inline struct intel_gt *uc_to_gt(struct intel_uc *uc)
 {
 	return container_of(uc, struct intel_gt, uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
new file mode 100644
index 000000000000..044219c5960a
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
+#include "intel_gt_regs.h"
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+	int cslice;
+	u32 mode = 0;
+	int first_ccs = __ffs(CCS_MASK(gt));
+
+	if (!IS_DG2(gt->i915))
+		return;
+
+	/* Build the value for the fixed CCS load balancing */
+	for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
+		if (CCS_MASK(gt) & BIT(cslice))
+			/*
+			 * If available, assign the cslice
+			 * to the first available engine...
+			 */
+			mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs);
+
+		else
+			/*
+			 * ... otherwise, mark the cslice as
+			 * unavailable if no CCS dispatches here
+			 */
+			mode |= XEHP_CCS_MODE_CSLICE(cslice,
+						     XEHP_CCS_MODE_CSLICE_MASK);
+	}
+
+	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
new file mode 100644
index 000000000000..9e5549caeb26
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#ifndef __INTEL_GT_CCS_MODE_H__
+#define __INTEL_GT_CCS_MODE_H__
+
+struct intel_gt;
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+
+#endif /* __INTEL_GT_CCS_MODE_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 50962cfd1353..743fe3566722 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1477,8 +1477,14 @@
 #define   ECOBITS_PPGTT_CACHE4B			(0 << 8)
 
 #define GEN12_RCU_MODE				_MMIO(0x14800)
+#define   XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE	REG_BIT(1)
 #define   GEN12_RCU_MODE_CCS_ENABLE		REG_BIT(0)
 
+#define XEHP_CCS_MODE				_MMIO(0x14804)
+#define   XEHP_CCS_MODE_CSLICE_MASK		REG_GENMASK(2, 0) /* CCS0-3 + rsvd */
+#define   XEHP_CCS_MODE_CSLICE_WIDTH		ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1)
+#define   XEHP_CCS_MODE_CSLICE(cslice, ccs)	(ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH))
+
 #define CHV_FUSE_GT				_MMIO(VLV_GUNIT_BASE + 0x2168)
 #define   CHV_FGT_DISABLE_SS0			(1 << 10)
 #define   CHV_FGT_DISABLE_SS1			(1 << 11)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index d67d44611c28..6ec3582c9735 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -10,6 +10,7 @@
 #include "intel_engine_regs.h"
 #include "intel_gpu_commands.h"
 #include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
 #include "intel_gt_mcr.h"
 #include "intel_gt_print.h"
 #include "intel_gt_regs.h"
@@ -51,7 +52,8 @@
  *   registers belonging to BCS, VCS or VECS should be implemented in
  *   xcs_engine_wa_init(). Workarounds for registers not belonging to a specific
  *   engine's MMIO range but that are part of of the common RCS/CCS reset domain
- *   should be implemented in general_render_compute_wa_init().
+ *   should be implemented in general_render_compute_wa_init(). The settings
+ *   about the CCS load balancing should be added in ccs_engine_wa_mode().
  *
  * - GT workarounds: the list of these WAs is applied whenever these registers
  *   revert to their default values: on GPU reset, suspend/resume [1]_, etc.
@@ -1653,6 +1655,7 @@ static void
 xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 {
 	/* Wa_14018575942 / Wa_18018781329 */
+	wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
 	wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
 
 	/* Wa_22016670082 */
@@ -2853,6 +2856,28 @@ add_render_compute_tuning_settings(struct intel_gt *gt,
 		wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC);
 }
 
+static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal)
+{
+	struct intel_gt *gt = engine->gt;
+
+	if (!IS_DG2(gt->i915))
+		return;
+
+	/*
+	 * Wa_14019159160: This workaround, along with others, leads to
+	 * significant challenges in utilizing load balancing among the
+	 * CCS slices. Consequently, an architectural decision has been
+	 * made to completely disable automatic CCS load balancing.
+	 */
+	wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE);
+
+	/*
+	 * After having disabled automatic load balancing we need to
+	 * assign all slices to a single CCS. We will call it CCS mode 1
+	 */
+	intel_gt_apply_ccs_mode(gt);
+}
+
 /*
  * The workarounds in this function apply to shared registers in
  * the general render reset domain that aren't tied to a
@@ -3003,8 +3028,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal
 	 * to a single RCS/CCS engine's workaround list since
 	 * they're reset as part of the general render domain reset.
 	 */
-	if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
+	if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) {
 		general_render_compute_wa_init(engine, wal);
+		ccs_engine_wa_mode(engine, wal);
+	}
 
 	if (engine->class == COMPUTE_CLASS)
 		ccs_engine_wa_init(engine, wal);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index f3dcae4b9d45..0f83c6d4376f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1403,14 +1403,17 @@ static void guc_cancel_busyness_worker(struct intel_guc *guc)
 	 * Trying to pass a 'need_sync' or 'in_reset' flag all the way down through
 	 * every possible call stack is unfeasible. It would be too intrusive to many
 	 * areas that really don't care about the GuC backend. However, there is the
-	 * 'reset_in_progress' flag available, so just use that.
+	 * I915_RESET_BACKOFF flag and the gt->reset.mutex can be tested for is_locked.
+	 * So just use those. Note that testing both is required due to the hideously
+	 * complex nature of the i915 driver's reset code paths.
 	 *
 	 * And note that in the case of a reset occurring during driver unload
-	 * (wedge_on_fini), skipping the cancel in _prepare (when the reset flag is set
-	 * is fine because there is another cancel in _finish (when the reset flag is
-	 * not).
+	 * (wedged_on_fini), skipping the cancel in reset_prepare/reset_fini (when the
+	 * reset flag/mutex are set) is fine because there is another explicit cancel in
+	 * intel_guc_submission_fini (when the reset flag/mutex are not).
 	 */
-	if (guc_to_gt(guc)->uc.reset_in_progress)
+	if (mutex_is_locked(&guc_to_gt(guc)->reset.mutex) ||
+	    test_bit(I915_RESET_BACKOFF, &guc_to_gt(guc)->reset.flags))
 		cancel_delayed_work(&guc->timestamp.work);
 	else
 		cancel_delayed_work_sync(&guc->timestamp.work);
@@ -1424,8 +1427,6 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
 	unsigned long flags;
 	ktime_t unused;
 
-	guc_cancel_busyness_worker(guc);
-
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
 
 	guc_update_pm_timestamp(guc, &unused);
@@ -2004,13 +2005,6 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
 
 void intel_guc_submission_reset_finish(struct intel_guc *guc)
 {
-	/*
-	 * Ensure the busyness worker gets cancelled even on a fatal wedge.
-	 * Note that reset_prepare is not allowed to because it confuses lockdep.
-	 */
-	if (guc_submission_initialized(guc))
-		guc_cancel_busyness_worker(guc);
-
 	/* Reset called during driver load or during wedge? */
 	if (unlikely(!guc_submission_initialized(guc) ||
 		     !intel_guc_is_fw_running(guc) ||
@@ -2136,6 +2130,7 @@ void intel_guc_submission_fini(struct intel_guc *guc)
 	if (!guc->submission_initialized)
 		return;
 
+	guc_fini_engine_stats(guc);
 	guc_flush_destroyed_contexts(guc);
 	guc_lrc_desc_pool_destroy_v69(guc);
 	i915_sched_engine_put(guc->sched_engine);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 6dfe5d9456c6..399bc319180b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -637,6 +637,10 @@ void intel_uc_reset_finish(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 
+	/*
+	 * NB: The wedge code path results in prepare -> prepare -> finish -> finish.
+	 * So this function is sometimes called with the in-progress flag not set.
+	 */
 	uc->reset_in_progress = false;
 
 	/* Firmware expected to be running when this function is called */
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 9ee902d5b72c..4b9233c07a22 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -800,7 +800,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_cleanup_modeset2;
 
 	ret = intel_pxp_init(i915);
-	if (ret != -ENODEV)
+	if (ret && ret != -ENODEV)
 		drm_dbg(&i915->drm, "pxp init failed with %d\n", ret);
 
 	ret = intel_display_driver_probe(i915);
diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c
index 8c3f443c8347..b758fd110c20 100644
--- a/drivers/gpu/drm/i915/i915_hwmon.c
+++ b/drivers/gpu/drm/i915/i915_hwmon.c
@@ -72,12 +72,13 @@ hwm_locked_with_pm_intel_uncore_rmw(struct hwm_drvdata *ddat,
 	struct intel_uncore *uncore = ddat->uncore;
 	intel_wakeref_t wakeref;
 
-	mutex_lock(&hwmon->hwmon_lock);
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
+		mutex_lock(&hwmon->hwmon_lock);
 
-	with_intel_runtime_pm(uncore->rpm, wakeref)
 		intel_uncore_rmw(uncore, reg, clear, set);
 
-	mutex_unlock(&hwmon->hwmon_lock);
+		mutex_unlock(&hwmon->hwmon_lock);
+	}
 }
 
 /*
@@ -136,20 +137,21 @@ hwm_energy(struct hwm_drvdata *ddat, long *energy)
 	else
 		rgaddr = hwmon->rg.energy_status_all;
 
-	mutex_lock(&hwmon->hwmon_lock);
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
+		mutex_lock(&hwmon->hwmon_lock);
 
-	with_intel_runtime_pm(uncore->rpm, wakeref)
 		reg_val = intel_uncore_read(uncore, rgaddr);
 
-	if (reg_val >= ei->reg_val_prev)
-		ei->accum_energy += reg_val - ei->reg_val_prev;
-	else
-		ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val;
-	ei->reg_val_prev = reg_val;
+		if (reg_val >= ei->reg_val_prev)
+			ei->accum_energy += reg_val - ei->reg_val_prev;
+		else
+			ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val;
+		ei->reg_val_prev = reg_val;
 
-	*energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY,
-				  hwmon->scl_shift_energy);
-	mutex_unlock(&hwmon->hwmon_lock);
+		*energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY,
+					  hwmon->scl_shift_energy);
+		mutex_unlock(&hwmon->hwmon_lock);
+	}
 }
 
 static ssize_t
@@ -404,6 +406,7 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val)
 
 	/* Block waiting for GuC reset to complete when needed */
 	for (;;) {
+		wakeref = intel_runtime_pm_get(ddat->uncore->rpm);
 		mutex_lock(&hwmon->hwmon_lock);
 
 		prepare_to_wait(&ddat->waitq, &wait, TASK_INTERRUPTIBLE);
@@ -417,14 +420,13 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val)
 		}
 
 		mutex_unlock(&hwmon->hwmon_lock);
+		intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
 
 		schedule();
 	}
 	finish_wait(&ddat->waitq, &wait);
 	if (ret)
-		goto unlock;
-
-	wakeref = intel_runtime_pm_get(ddat->uncore->rpm);
+		goto exit;
 
 	/* Disable PL1 limit and verify, because the limit cannot be disabled on all platforms */
 	if (val == PL1_DISABLE) {
@@ -444,9 +446,8 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val)
 	intel_uncore_rmw(ddat->uncore, hwmon->rg.pkg_rapl_limit,
 			 PKG_PWR_LIM_1_EN | PKG_PWR_LIM_1, nval);
 exit:
-	intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
-unlock:
 	mutex_unlock(&hwmon->hwmon_lock);
+	intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c
index ba82277254b7..cc41974cee74 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.c
+++ b/drivers/gpu/drm/i915/i915_memcpy.c
@@ -25,6 +25,8 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/cpufeature.h>
+#include <linux/bug.h>
+#include <linux/build_bug.h>
 #include <asm/fpu/api.h>
 
 #include "i915_memcpy.h"
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e00557e1a57f..3b2e49ce29ba 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4599,7 +4599,7 @@
 #define MTL_CHICKEN_TRANS(trans)	_MMIO_TRANS((trans), \
 						    _MTL_CHICKEN_TRANS_A, \
 						    _MTL_CHICKEN_TRANS_B)
-#define   PIPE_VBLANK_WITH_DELAY	REG_BIT(31) /* ADL/DG2 */
+#define   PIPE_VBLANK_WITH_DELAY	REG_BIT(31) /* tgl+ */
 #define   SKL_UNMASK_VBL_TO_PIPE_IN_SRD	REG_BIT(30) /* skl+ */
 #define   HSW_FRAME_START_DELAY_MASK	REG_GENMASK(28, 27)
 #define   HSW_FRAME_START_DELAY(x)	REG_FIELD_PREP(HSW_FRAME_START_DELAY_MASK, x)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index d09aad34ba37..b70715b1411d 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -34,6 +34,7 @@
 #include "gt/intel_engine.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
 #include "gt/intel_gt_requests.h"
 #include "gt/intel_tlb.h"
 
@@ -103,12 +104,42 @@ static inline struct i915_vma *active_to_vma(struct i915_active *ref)
 
 static int __i915_vma_active(struct i915_active *ref)
 {
-	return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT;
+	struct i915_vma *vma = active_to_vma(ref);
+
+	if (!i915_vma_tryget(vma))
+		return -ENOENT;
+
+	/*
+	 * Exclude global GTT VMA from holding a GT wakeref
+	 * while active, otherwise GPU never goes idle.
+	 */
+	if (!i915_vma_is_ggtt(vma)) {
+		/*
+		 * Since we and our _retire() counterpart can be
+		 * called asynchronously, storing a wakeref tracking
+		 * handle inside struct i915_vma is not safe, and
+		 * there is no other good place for that.  Hence,
+		 * use untracked variants of intel_gt_pm_get/put().
+		 */
+		intel_gt_pm_get_untracked(vma->vm->gt);
+	}
+
+	return 0;
 }
 
 static void __i915_vma_retire(struct i915_active *ref)
 {
-	i915_vma_put(active_to_vma(ref));
+	struct i915_vma *vma = active_to_vma(ref);
+
+	if (!i915_vma_is_ggtt(vma)) {
+		/*
+		 * Since we can be called from atomic contexts,
+		 * use an async variant of intel_gt_pm_put().
+		 */
+		intel_gt_pm_put_async_untracked(vma->vm->gt);
+	}
+
+	i915_vma_put(vma);
 }
 
 static struct i915_vma *
@@ -1404,7 +1435,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	struct i915_vma_work *work = NULL;
 	struct dma_fence *moving = NULL;
 	struct i915_vma_resource *vma_res = NULL;
-	intel_wakeref_t wakeref = 0;
+	intel_wakeref_t wakeref;
 	unsigned int bound;
 	int err;
 
@@ -1424,8 +1455,14 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 	if (err)
 		return err;
 
-	if (flags & PIN_GLOBAL)
-		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
+	/*
+	 * In case of a global GTT, we must hold a runtime-pm wakeref
+	 * while global PTEs are updated.  In other cases, we hold
+	 * the rpm reference while the VMA is active.  Since runtime
+	 * resume may require allocations, which are forbidden inside
+	 * vm->mutex, get the first rpm wakeref outside of the mutex.
+	 */
+	wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
 
 	if (flags & vma->vm->bind_async_flags) {
 		/* lock VM */
@@ -1561,8 +1598,7 @@ err_fence:
 	if (work)
 		dma_fence_work_commit_imm(&work->base);
 err_rpm:
-	if (wakeref)
-		intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
 
 	if (moving)
 		dma_fence_put(moving);
diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c
index 70349739dd89..55dedd73f528 100644
--- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c
+++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c
@@ -72,14 +72,14 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 		int ret;
 
 		if (!mode)
-			return -EINVAL;
+			return 0;
 
 		ret = of_get_drm_display_mode(np, &imxpd->mode,
 					      &imxpd->bus_flags,
 					      OF_USE_NATIVE_MODE);
 		if (ret) {
 			drm_mode_destroy(connector->dev, mode);
-			return ret;
+			return 0;
 		}
 
 		drm_mode_copy(mode, &imxpd->mode);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 0674aca0f8a3..cf0b1de1c071 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1377,6 +1377,10 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 	if (adreno_is_a618(gpu))
 		gpu->ubwc_config.highest_bank_bit = 14;
 
+	if (adreno_is_a619(gpu))
+		/* TODO: Should be 14 but causes corruption at e.g. 1920x1200 on DP */
+		gpu->ubwc_config.highest_bank_bit = 13;
+
 	if (adreno_is_a619_holi(gpu))
 		gpu->ubwc_config.highest_bank_bit = 13;
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 1f5245fc2cdc..a847a0f7a73c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -852,7 +852,7 @@ static void a6xx_get_shader_block(struct msm_gpu *gpu,
 			(block->type << 8) | i);
 
 		in += CRASHDUMP_READ(in, REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE,
-			block->size, dumper->iova + A6XX_CD_DATA_OFFSET);
+			block->size, out);
 
 		out += block->size * sizeof(u32);
 	}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
index 9a9f7092c526..a3e60ac70689 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
@@ -324,6 +324,7 @@ static const struct dpu_wb_cfg x1e80100_wb[] = {
 	},
 };
 
+/* TODO: INTF 3, 8 and 7 are used for MST, marked as INTF_NONE for now */
 static const struct dpu_intf_cfg x1e80100_intf[] = {
 	{
 		.name = "intf_0", .id = INTF_0,
@@ -358,8 +359,8 @@ static const struct dpu_intf_cfg x1e80100_intf[] = {
 		.name = "intf_3", .id = INTF_3,
 		.base = 0x37000, .len = 0x280,
 		.features = INTF_SC7280_MASK,
-		.type = INTF_DP,
-		.controller_id = MSM_DP_CONTROLLER_1,
+		.type = INTF_NONE,
+		.controller_id = MSM_DP_CONTROLLER_0,	/* pair with intf_0 for DP MST */
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
@@ -368,7 +369,7 @@ static const struct dpu_intf_cfg x1e80100_intf[] = {
 		.base = 0x38000, .len = 0x280,
 		.features = INTF_SC7280_MASK,
 		.type = INTF_DP,
-		.controller_id = MSM_DP_CONTROLLER_2,
+		.controller_id = MSM_DP_CONTROLLER_1,
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21),
@@ -381,6 +382,33 @@ static const struct dpu_intf_cfg x1e80100_intf[] = {
 		.prog_fetch_lines_worst_case = 24,
 		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22),
 		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23),
+	}, {
+		.name = "intf_6", .id = INTF_6,
+		.base = 0x3A000, .len = 0x280,
+		.features = INTF_SC7280_MASK,
+		.type = INTF_DP,
+		.controller_id = MSM_DP_CONTROLLER_2,
+		.prog_fetch_lines_worst_case = 24,
+		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
+		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+	}, {
+		.name = "intf_7", .id = INTF_7,
+		.base = 0x3b000, .len = 0x280,
+		.features = INTF_SC7280_MASK,
+		.type = INTF_NONE,
+		.controller_id = MSM_DP_CONTROLLER_2,	/* pair with intf_6 for DP MST */
+		.prog_fetch_lines_worst_case = 24,
+		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 18),
+		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 19),
+	}, {
+		.name = "intf_8", .id = INTF_8,
+		.base = 0x3c000, .len = 0x280,
+		.features = INTF_SC7280_MASK,
+		.type = INTF_NONE,
+		.controller_id = MSM_DP_CONTROLLER_1,	/* pair with intf_4 for DP MST */
+		.prog_fetch_lines_worst_case = 24,
+		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12),
+		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13),
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index ef871239adb2..68fae048a9a8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -459,15 +459,15 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent)
 			&perf->core_clk_rate);
 	debugfs_create_u32("enable_bw_release", 0600, entry,
 			(u32 *)&perf->enable_bw_release);
-	debugfs_create_u32("threshold_low", 0600, entry,
+	debugfs_create_u32("threshold_low", 0400, entry,
 			(u32 *)&perf->perf_cfg->max_bw_low);
-	debugfs_create_u32("threshold_high", 0600, entry,
+	debugfs_create_u32("threshold_high", 0400, entry,
 			(u32 *)&perf->perf_cfg->max_bw_high);
-	debugfs_create_u32("min_core_ib", 0600, entry,
+	debugfs_create_u32("min_core_ib", 0400, entry,
 			(u32 *)&perf->perf_cfg->min_core_ib);
-	debugfs_create_u32("min_llcc_ib", 0600, entry,
+	debugfs_create_u32("min_llcc_ib", 0400, entry,
 			(u32 *)&perf->perf_cfg->min_llcc_ib);
-	debugfs_create_u32("min_dram_ib", 0600, entry,
+	debugfs_create_u32("min_dram_ib", 0400, entry,
 			(u32 *)&perf->perf_cfg->min_dram_ib);
 	debugfs_create_file("perf_mode", 0600, entry,
 			(u32 *)perf, &dpu_core_perf_mode_fops);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
index 946dd0135dff..6a0a74832fb6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -525,14 +525,14 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms,
 	int ret;
 
 	if (!irq_cb) {
-		DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n",
-			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb);
+		DPU_ERROR("IRQ=[%d, %d] NULL callback\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
 		return -EINVAL;
 	}
 
 	if (!dpu_core_irq_is_valid(irq_idx)) {
-		DPU_ERROR("invalid IRQ=[%d, %d]\n",
-			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
+		DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n",
+			  DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index c4cb82af5c2f..ffbfde922589 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -484,7 +484,7 @@ static void dp_display_handle_video_request(struct dp_display_private *dp)
 	}
 }
 
-static int dp_display_handle_port_ststus_changed(struct dp_display_private *dp)
+static int dp_display_handle_port_status_changed(struct dp_display_private *dp)
 {
 	int rc = 0;
 
@@ -541,7 +541,7 @@ static int dp_display_usbpd_attention_cb(struct device *dev)
 		drm_dbg_dp(dp->drm_dev, "hpd_state=%d sink_request=%d\n",
 					dp->hpd_state, sink_request);
 		if (sink_request & DS_PORT_STATUS_CHANGED)
-			rc = dp_display_handle_port_ststus_changed(dp);
+			rc = dp_display_handle_port_status_changed(dp);
 		else
 			rc = dp_display_handle_irq_hpd(dp);
 	}
@@ -588,6 +588,7 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data)
 	ret = dp_display_usbpd_configure_cb(&pdev->dev);
 	if (ret) {	/* link train failed */
 		dp->hpd_state = ST_DISCONNECTED;
+		pm_runtime_put_sync(&pdev->dev);
 	} else {
 		dp->hpd_state = ST_MAINLINK_READY;
 	}
@@ -645,6 +646,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data)
 		dp_display_host_phy_exit(dp);
 		dp->hpd_state = ST_DISCONNECTED;
 		dp_display_notify_disconnect(&dp->dp_display.pdev->dev);
+		pm_runtime_put_sync(&pdev->dev);
 		mutex_unlock(&dp->event_mutex);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index e3f61c39df69..80166f702a0d 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -89,7 +89,7 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 
 	for (i = 0; i < n; i++) {
 		ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &msm_fb->iova[i]);
-		drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)",
+		drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)\n",
 			      fb->base.id, i, msm_fb->iova[i], ret);
 		if (ret)
 			return ret;
@@ -176,7 +176,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 	const struct msm_format *format;
 	int ret, i, n;
 
-	drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)",
+	drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)\n",
 			mode_cmd, mode_cmd->width, mode_cmd->height,
 			(char *)&mode_cmd->pixel_format);
 
@@ -232,7 +232,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 
 	refcount_set(&msm_fb->dirtyfb, 1);
 
-	drm_dbg_state(dev, "create: FB ID: %d (%p)", fb->base.id, fb);
+	drm_dbg_state(dev, "create: FB ID: %d (%p)\n", fb->base.id, fb);
 
 	return fb;
 
diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
index 84c21ec2ceea..af6a6fcb1173 100644
--- a/drivers/gpu/drm/msm/msm_kms.c
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -149,7 +149,7 @@ int msm_crtc_enable_vblank(struct drm_crtc *crtc)
 	struct msm_kms *kms = priv->kms;
 	if (!kms)
 		return -ENXIO;
-	drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
+	drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id);
 	return vblank_ctrl_queue_work(priv, crtc, true);
 }
 
@@ -160,7 +160,7 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc)
 	struct msm_kms *kms = priv->kms;
 	if (!kms)
 		return;
-	drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
+	drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id);
 	vblank_ctrl_queue_work(priv, crtc, false);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 479effcf607e..79cfab53f80e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -23,6 +23,7 @@
  */
 
 #include "nouveau_drv.h"
+#include "nouveau_bios.h"
 #include "nouveau_reg.h"
 #include "dispnv04/hw.h"
 #include "nouveau_encoder.h"
@@ -1677,7 +1678,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf)
 	 */
 	if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) {
 		if (*conn == 0xf2005014 && *conf == 0xffffffff) {
-			fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1);
+			fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B);
 			return false;
 		}
 	}
@@ -1763,26 +1764,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios)
 #ifdef __powerpc__
 	/* Apple iMac G4 NV17 */
 	if (of_machine_is_compatible("PowerMac4,5")) {
-		fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1);
-		fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2);
+		fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B);
+		fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C);
 		return;
 	}
 #endif
 
 	/* Make up some sane defaults */
 	fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG,
-			     bios->legacy.i2c_indices.crt, 1, 1);
+			     bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B);
 
 	if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0)
 		fabricate_dcb_output(dcb, DCB_OUTPUT_TV,
 				     bios->legacy.i2c_indices.tv,
-				     all_heads, 0);
+				     all_heads, DCB_OUTPUT_A);
 
 	else if (bios->tmds.output0_script_ptr ||
 		 bios->tmds.output1_script_ptr)
 		fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS,
 				     bios->legacy.i2c_indices.panel,
-				     all_heads, 1);
+				     all_heads, DCB_OUTPUT_B);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 56dcd25db1ce..db8cbf615112 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1256,6 +1256,8 @@ out:
 			drm_vma_node_unmap(&nvbo->bo.base.vma_node,
 					   bdev->dev_mapping);
 			nouveau_ttm_io_mem_free_locked(drm, nvbo->bo.resource);
+			nvbo->bo.resource->bus.offset = 0;
+			nvbo->bo.resource->bus.addr = NULL;
 			goto retry;
 		}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 12feecf71e75..6fb65b01d778 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -378,9 +378,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 	dma_addr_t *dma_addrs;
 	struct nouveau_fence *fence;
 
-	src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
-	dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
-	dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
+	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
+	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
+	dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL);
 
 	migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
 			npages);
@@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 	migrate_device_pages(src_pfns, dst_pfns, npages);
 	nouveau_dmem_fence_done(&fence);
 	migrate_device_finalize(src_pfns, dst_pfns, npages);
-	kfree(src_pfns);
-	kfree(dst_pfns);
+	kvfree(src_pfns);
+	kvfree(dst_pfns);
 	for (i = 0; i < npages; i++)
 		dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
-	kfree(dma_addrs);
+	kvfree(dma_addrs);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 7de7707ec6a8..a72c45809484 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -225,12 +225,18 @@ nouveau_dp_detect(struct nouveau_connector *nv_connector,
 	u8 *dpcd = nv_encoder->dp.dpcd;
 	int ret = NOUVEAU_DP_NONE, hpd;
 
-	/* If we've already read the DPCD on an eDP device, we don't need to
-	 * reread it as it won't change
+	/* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we
+	 * haven't probed them once before.
 	 */
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP &&
-	    dpcd[DP_DPCD_REV] != 0)
-		return NOUVEAU_DP_SST;
+	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+		if (connector->status == connector_status_connected)
+			return NOUVEAU_DP_SST;
+		else if (connector->status == connector_status_disconnected)
+			return NOUVEAU_DP_NONE;
+	}
+
+	// Ensure that the aux bus is enabled for probing
+	drm_dp_dpcd_set_powered(&nv_connector->aux, true);
 
 	mutex_lock(&nv_encoder->dp.hpd_irq_lock);
 	if (mstm) {
@@ -293,6 +299,13 @@ out:
 	if (mstm && !mstm->suspended && ret != NOUVEAU_DP_MST)
 		nv50_mstm_remove(mstm);
 
+	/* GSP doesn't like when we try to do aux transactions on a port it considers disconnected,
+	 * and since we don't really have a usecase for that anyway - just disable the aux bus here
+	 * if we've decided the connector is disconnected
+	 */
+	if (ret == NOUVEAU_DP_NONE)
+		drm_dp_dpcd_set_powered(&nv_connector->aux, false);
+
 	mutex_unlock(&nv_encoder->dp.hpd_irq_lock);
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 0a0a11dc9ec0..ee02cd833c5e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -812,15 +812,15 @@ op_remap(struct drm_gpuva_op_remap *r,
 	struct drm_gpuva_op_unmap *u = r->unmap;
 	struct nouveau_uvma *uvma = uvma_from_va(u->va);
 	u64 addr = uvma->va.va.addr;
-	u64 range = uvma->va.va.range;
+	u64 end = uvma->va.va.addr + uvma->va.va.range;
 
 	if (r->prev)
 		addr = r->prev->va.addr + r->prev->va.range;
 
 	if (r->next)
-		range = r->next->va.addr - addr;
+		end = r->next->va.addr;
 
-	op_unmap_range(u, addr, range);
+	op_unmap_range(u, addr, end - addr);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 986e8d547c94..060c74a80eb1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -420,7 +420,7 @@ gf100_gr_chan_new(struct nvkm_gr *base, struct nvkm_chan *fifoch,
 			return ret;
 	} else {
 		ret = nvkm_memory_map(gr->attrib_cb, 0, chan->vmm, chan->attrib_cb,
-				      &args, sizeof(args));;
+				      &args, sizeof(args));
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c
index 4bf486b57101..cb05f7f48a98 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c
@@ -66,11 +66,16 @@ of_init(struct nvkm_bios *bios, const char *name)
 	return ERR_PTR(-EINVAL);
 }
 
+static void of_fini(void *p)
+{
+	kfree(p);
+}
+
 const struct nvbios_source
 nvbios_of = {
 	.name = "OpenFirmware",
 	.init = of_init,
-	.fini = (void(*)(void *))kfree,
+	.fini = of_fini,
 	.read = of_read,
 	.size = of_size,
 	.rw = false,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index 7bcbc4895ec2..271bfa038f5b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -25,6 +25,7 @@
 
 #include <subdev/bios.h>
 #include <subdev/bios/init.h>
+#include <subdev/gsp.h>
 
 void
 gm107_devinit_disable(struct nvkm_devinit *init)
@@ -33,10 +34,13 @@ gm107_devinit_disable(struct nvkm_devinit *init)
 	u32 r021c00 = nvkm_rd32(device, 0x021c00);
 	u32 r021c04 = nvkm_rd32(device, 0x021c04);
 
-	if (r021c00 & 0x00000001)
-		nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
-	if (r021c00 & 0x00000004)
-		nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+	/* gsp only wants to enable/disable display */
+	if (!nvkm_gsp_rm(device->gsp)) {
+		if (r021c00 & 0x00000001)
+			nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
+		if (r021c00 & 0x00000004)
+			nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+	}
 	if (r021c04 & 0x00000001)
 		nvkm_subdev_disable(device, NVKM_ENGINE_DISP, 0);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index a73a5b589790..9858c1438aa7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1112,7 +1112,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
 
 	str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
-	strings = (char *)&rpc->entries[NV_GSP_REG_NUM_ENTRIES];
+	strings = (char *)rpc + str_offset;
 	for (i = 0; i < NV_GSP_REG_NUM_ENTRIES; i++) {
 		int name_len = strlen(r535_registry_entries[i].name) + 1;
 
@@ -1430,6 +1430,10 @@ r535_gsp_msg_post_event(void *priv, u32 fn, void *repv, u32 repc)
 
 /**
  * r535_gsp_msg_run_cpu_sequencer() -- process I/O commands from the GSP
+ * @priv: gsp pointer
+ * @fn: function number (ignored)
+ * @repv: pointer to libos print RPC
+ * @repc: message size
  *
  * The GSP sequencer is a list of I/O commands that the GSP can send to
  * the driver to perform for various purposes.  The most common usage is to
@@ -1781,6 +1785,7 @@ static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 
 /**
  * r535_gsp_libos_init() -- create the libos arguments structure
+ * @gsp: gsp pointer
  *
  * The logging buffers are byte queues that contain encoded printf-like
  * messages from GSP-RM.  They need to be decoded by a special application
@@ -1920,6 +1925,10 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
 
 /**
  * nvkm_gsp_radix3_sg - build a radix3 table from a S/G list
+ * @gsp: gsp pointer
+ * @sgt: S/G list to traverse
+ * @size: size of the image, in bytes
+ * @rx3: radix3 array to update
  *
  * The GSP uses a three-level page table, called radix3, to map the firmware.
  * Each 64-bit "pointer" in the table is either the bus address of an entry in
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
index a7f3fc342d87..dd5b5a17ece0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
@@ -222,8 +222,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory)
 	void __iomem *map = NULL;
 
 	/* Already mapped? */
-	if (refcount_inc_not_zero(&iobj->maps))
+	if (refcount_inc_not_zero(&iobj->maps)) {
+		/* read barrier match the wmb on refcount set */
+		smp_rmb();
 		return iobj->map;
+	}
 
 	/* Take the lock, and re-check that another thread hasn't
 	 * already mapped the object in the meantime.
@@ -250,6 +253,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory)
 			iobj->base.memory.ptrs = &nv50_instobj_fast;
 		else
 			iobj->base.memory.ptrs = &nv50_instobj_slow;
+		/* barrier to ensure the ptrs are written before refcount is set */
+		smp_wmb();
 		refcount_set(&iobj->maps, 1);
 	}
 
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c
index cb7406d74466..c39fe0fc5d69 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c
@@ -614,8 +614,6 @@ static void nt36672e_panel_remove(struct mipi_dsi_device *dsi)
 	struct nt36672e_panel *ctx = mipi_dsi_get_drvdata(dsi);
 
 	mipi_dsi_detach(ctx->dsi);
-	mipi_dsi_device_unregister(ctx->dsi);
-
 	drm_panel_remove(&ctx->panel);
 }
 
diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c
index 775144695283..b15ca56a09a7 100644
--- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c
+++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c
@@ -253,8 +253,6 @@ static void visionox_rm69299_remove(struct mipi_dsi_device *dsi)
 	struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi);
 
 	mipi_dsi_detach(ctx->dsi);
-	mipi_dsi_device_unregister(ctx->dsi);
-
 	drm_panel_remove(&ctx->panel);
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 9063ce254642..fd8e44992184 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -441,19 +441,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev)
 
 	gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present);
 	ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO,
-					 val, !val, 1, 1000);
+					 val, !val, 1, 2000);
 	if (ret)
 		dev_err(pfdev->dev, "shader power transition timeout");
 
 	gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present);
 	ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO,
-					 val, !val, 1, 1000);
+					 val, !val, 1, 2000);
 	if (ret)
 		dev_err(pfdev->dev, "tiler power transition timeout");
 
 	gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present);
 	ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO,
-				 val, !val, 0, 1000);
+				 val, !val, 0, 2000);
 	if (ret)
 		dev_err(pfdev->dev, "l2 power transition timeout");
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index f38385fe76bb..b91019cd5acb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -502,11 +502,18 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
 	mapping_set_unevictable(mapping);
 
 	for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) {
+		/* Can happen if the last fault only partially filled this
+		 * section of the pages array before failing. In that case
+		 * we skip already filled pages.
+		 */
+		if (pages[i])
+			continue;
+
 		pages[i] = shmem_read_mapping_page(mapping, i);
 		if (IS_ERR(pages[i])) {
 			ret = PTR_ERR(pages[i]);
 			pages[i] = NULL;
-			goto err_pages;
+			goto err_unlock;
 		}
 	}
 
@@ -514,7 +521,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
 	ret = sg_alloc_table_from_pages(sgt, pages + page_offset,
 					NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL);
 	if (ret)
-		goto err_pages;
+		goto err_unlock;
 
 	ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0);
 	if (ret)
@@ -537,8 +544,6 @@ out:
 
 err_map:
 	sg_free_table(sgt);
-err_pages:
-	drm_gem_shmem_put_pages(&bo->base);
 err_unlock:
 	dma_resv_unlock(obj->resv);
 err_bo:
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index 281edab518cd..d6ea01f3797b 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -421,7 +421,6 @@ int qxl_surface_id_alloc(struct qxl_device *qdev,
 {
 	uint32_t handle;
 	int idr_ret;
-	int count = 0;
 again:
 	idr_preload(GFP_ATOMIC);
 	spin_lock(&qdev->surf_id_idr_lock);
@@ -433,7 +432,6 @@ again:
 	handle = idr_ret;
 
 	if (handle >= qdev->rom->n_surfaces) {
-		count++;
 		spin_lock(&qdev->surf_id_idr_lock);
 		idr_remove(&qdev->surf_id_idr, handle);
 		spin_unlock(&qdev->surf_id_idr_lock);
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index dd0f834d881c..506ae1f5e099 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -145,7 +145,7 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 	struct qxl_release *release;
 	struct qxl_bo *cmd_bo;
 	void *fb_cmd;
-	int i, ret, num_relocs;
+	int i, ret;
 	int unwritten;
 
 	switch (cmd->type) {
@@ -200,7 +200,6 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 	}
 
 	/* fill out reloc info structs */
-	num_relocs = 0;
 	for (i = 0; i < cmd->relocs_num; ++i) {
 		struct drm_qxl_reloc reloc;
 		struct drm_qxl_reloc __user *u = u64_to_user_ptr(cmd->relocs);
@@ -230,7 +229,6 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 			reloc_info[i].dst_bo = cmd_bo;
 			reloc_info[i].dst_offset = reloc.dst_offset + release->release_offset;
 		}
-		num_relocs++;
 
 		/* reserve and validate the reloc dst bo */
 		if (reloc.reloc_type == QXL_RELOC_TYPE_BO || reloc.src_handle) {
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 368d26da0d6a..9febc8b73f09 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -58,16 +58,56 @@ static long qxl_fence_wait(struct dma_fence *fence, bool intr,
 			   signed long timeout)
 {
 	struct qxl_device *qdev;
+	struct qxl_release *release;
+	int count = 0, sc = 0;
+	bool have_drawable_releases;
 	unsigned long cur, end = jiffies + timeout;
 
 	qdev = container_of(fence->lock, struct qxl_device, release_lock);
+	release = container_of(fence, struct qxl_release, base);
+	have_drawable_releases = release->type == QXL_RELEASE_DRAWABLE;
 
-	if (!wait_event_timeout(qdev->release_event,
-				(dma_fence_is_signaled(fence) ||
-				 (qxl_io_notify_oom(qdev), 0)),
-				timeout))
-		return 0;
+retry:
+	sc++;
+
+	if (dma_fence_is_signaled(fence))
+		goto signaled;
+
+	qxl_io_notify_oom(qdev);
+
+	for (count = 0; count < 11; count++) {
+		if (!qxl_queue_garbage_collect(qdev, true))
+			break;
+
+		if (dma_fence_is_signaled(fence))
+			goto signaled;
+	}
+
+	if (dma_fence_is_signaled(fence))
+		goto signaled;
+
+	if (have_drawable_releases || sc < 4) {
+		if (sc > 2)
+			/* back off */
+			usleep_range(500, 1000);
+
+		if (time_after(jiffies, end))
+			return 0;
+
+		if (have_drawable_releases && sc > 300) {
+			DMA_FENCE_WARN(fence,
+				       "failed to wait on release %llu after spincount %d\n",
+				       fence->context & ~0xf0000000, sc);
+			goto signaled;
+		}
+		goto retry;
+	}
+	/*
+	 * yeah, original sync_obj_wait gave up after 3 spins when
+	 * have_drawable_releases is not set.
+	 */
 
+signaled:
 	cur = jiffies;
 	if (time_after(cur, end))
 		return 0;
diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h
index 94947229888b..b7f22597ee95 100644
--- a/drivers/gpu/drm/radeon/pptable.h
+++ b/drivers/gpu/drm/radeon/pptable.h
@@ -424,7 +424,7 @@ typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{
 typedef struct _ATOM_PPLIB_STATE_V2
 {
       //number of valid dpm levels in this state; Driver uses it to calculate the whole 
-      //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR)
+      //size of the state: struct_size(ATOM_PPLIB_STATE_V2, clockInfoIndex, ucNumDPMLevels)
       UCHAR ucNumDPMLevels;
       
       //a index to the array of nonClockInfos
@@ -432,14 +432,14 @@ typedef struct _ATOM_PPLIB_STATE_V2
       /**
       * Driver will read the first ucNumDPMLevels in this array
       */
-      UCHAR clockInfoIndex[1];
+      UCHAR clockInfoIndex[] __counted_by(ucNumDPMLevels);
 } ATOM_PPLIB_STATE_V2;
 
 typedef struct _StateArray{
     //how many states we have 
     UCHAR ucNumEntries;
     
-    ATOM_PPLIB_STATE_V2 states[1];
+    ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries);
 }StateArray;
 
 
@@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{
     //sizeof(ATOM_PPLIB_CLOCK_INFO)
     UCHAR ucEntrySize;
     
-    UCHAR clockInfo[1];
+    UCHAR clockInfo[] __counted_by(ucNumEntries);
 }ClockInfoArray;
 
 typedef struct _NonClockInfoArray{
@@ -460,7 +460,7 @@ typedef struct _NonClockInfoArray{
     //sizeof(ATOM_PPLIB_NONCLOCK_INFO)
     UCHAR ucEntrySize;
     
-    ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1];
+    ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries);
 }NonClockInfoArray;
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index bb1f0a3371ab..10793a433bf5 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -923,8 +923,12 @@ bool radeon_get_atom_connector_info_from_supported_devices_table(struct
 		max_device = ATOM_MAX_SUPPORTED_DEVICE_INFO;
 
 	for (i = 0; i < max_device; i++) {
-		ATOM_CONNECTOR_INFO_I2C ci =
-		    supported_devices->info.asConnInfo[i];
+		ATOM_CONNECTOR_INFO_I2C ci;
+
+		if (frev > 1)
+			ci = supported_devices->info_2d1.asConnInfo[i];
+		else
+			ci = supported_devices->info.asConnInfo[i];
 
 		bios_connectors[i].valid = false;
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 48170694ac6b..18efb3fe1c00 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -17,9 +17,7 @@
 
 static const uint32_t formats_cluster[] = {
 	DRM_FORMAT_XRGB2101010,
-	DRM_FORMAT_ARGB2101010,
 	DRM_FORMAT_XBGR2101010,
-	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_XBGR8888,
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 3c4f5a392b06..58c8161289fe 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -71,13 +71,19 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	entity->guilty = guilty;
 	entity->num_sched_list = num_sched_list;
 	entity->priority = priority;
+	/*
+	 * It's perfectly valid to initialize an entity without having a valid
+	 * scheduler attached. It's just not valid to use the scheduler before it
+	 * is initialized itself.
+	 */
 	entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
 	RCU_INIT_POINTER(entity->last_scheduled, NULL);
 	RB_CLEAR_NODE(&entity->rb_tree_node);
 
-	if (!sched_list[0]->sched_rq) {
-		/* Warn drivers not to do this and to fix their DRM
-		 * calling order.
+	if (num_sched_list && !sched_list[0]->sched_rq) {
+		/* Since every entry covered by num_sched_list
+		 * should be non-NULL and therefore we warn drivers
+		 * not to do this and to fix their DRM calling order.
 		 */
 		pr_warn("%s: called with uninitialized scheduler\n", __func__);
 	} else if (num_sched_list) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index 69001a3dc0df..2d1880c61b50 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -166,7 +166,7 @@ sun4i_hdmi_connector_clock_valid(const struct drm_connector *connector,
 				 unsigned long long clock)
 {
 	const struct sun4i_hdmi *hdmi = drm_connector_to_sun4i_hdmi(connector);
-	unsigned long diff = clock / 200; /* +-0.5% allowed by HDMI spec */
+	unsigned long diff = div_u64(clock, 200); /* +-0.5% allowed by HDMI spec */
 	long rounded_rate;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 112438d965ff..6e1fd6985ffc 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -288,17 +288,23 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
 						  enum ttm_caching caching,
 						  unsigned int order)
 {
-	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE)
+	if (pool->use_dma_alloc)
 		return &pool->caching[caching].orders[order];
 
 #ifdef CONFIG_X86
 	switch (caching) {
 	case ttm_write_combined:
+		if (pool->nid != NUMA_NO_NODE)
+			return &pool->caching[caching].orders[order];
+
 		if (pool->use_dma32)
 			return &global_dma32_write_combined[order];
 
 		return &global_write_combined[order];
 	case ttm_uncached:
+		if (pool->nid != NUMA_NO_NODE)
+			return &pool->caching[caching].orders[order];
+
 		if (pool->use_dma32)
 			return &global_dma32_uncached[order];
 
@@ -566,11 +572,17 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 	pool->use_dma_alloc = use_dma_alloc;
 	pool->use_dma32 = use_dma32;
 
-	if (use_dma_alloc || nid != NUMA_NO_NODE) {
-		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < NR_PAGE_ORDERS; ++j)
-				ttm_pool_type_init(&pool->caching[i].orders[j],
-						   pool, i, j);
+	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
+		for (j = 0; j < NR_PAGE_ORDERS; ++j) {
+			struct ttm_pool_type *pt;
+
+			/* Initialize only pool types which are actually used */
+			pt = ttm_pool_select_type(pool, i, j);
+			if (pt != &pool->caching[i].orders[j])
+				continue;
+
+			ttm_pool_type_init(pt, pool, i, j);
+		}
 	}
 }
 EXPORT_SYMBOL(ttm_pool_init);
@@ -599,10 +611,16 @@ void ttm_pool_fini(struct ttm_pool *pool)
 {
 	unsigned int i, j;
 
-	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) {
-		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < NR_PAGE_ORDERS; ++j)
-				ttm_pool_type_fini(&pool->caching[i].orders[j]);
+	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
+		for (j = 0; j < NR_PAGE_ORDERS; ++j) {
+			struct ttm_pool_type *pt;
+
+			pt = ttm_pool_select_type(pool, i, j);
+			if (pt != &pool->caching[i].orders[j])
+				continue;
+
+			ttm_pool_type_fini(pt);
+		}
 	}
 
 	/* We removed the pool types from the LRU, but we need to also make sure
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 2e04f6cb661e..ce6b2fb341d1 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -105,7 +105,6 @@ v3d_irq(int irq, void *arg)
 		struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv;
 		u64 runtime = local_clock() - file->start_ns[V3D_BIN];
 
-		file->enabled_ns[V3D_BIN] += local_clock() - file->start_ns[V3D_BIN];
 		file->jobs_sent[V3D_BIN]++;
 		v3d->queue[V3D_BIN].jobs_sent++;
 
@@ -126,7 +125,6 @@ v3d_irq(int irq, void *arg)
 		struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv;
 		u64 runtime = local_clock() - file->start_ns[V3D_RENDER];
 
-		file->enabled_ns[V3D_RENDER] += local_clock() - file->start_ns[V3D_RENDER];
 		file->jobs_sent[V3D_RENDER]++;
 		v3d->queue[V3D_RENDER].jobs_sent++;
 
@@ -147,7 +145,6 @@ v3d_irq(int irq, void *arg)
 		struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv;
 		u64 runtime = local_clock() - file->start_ns[V3D_CSD];
 
-		file->enabled_ns[V3D_CSD] += local_clock() - file->start_ns[V3D_CSD];
 		file->jobs_sent[V3D_CSD]++;
 		v3d->queue[V3D_CSD].jobs_sent++;
 
@@ -195,7 +192,6 @@ v3d_hub_irq(int irq, void *arg)
 		struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv;
 		u64 runtime = local_clock() - file->start_ns[V3D_TFU];
 
-		file->enabled_ns[V3D_TFU] += local_clock() - file->start_ns[V3D_TFU];
 		file->jobs_sent[V3D_TFU]++;
 		v3d->queue[V3D_TFU].jobs_sent++;
 
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 34f807ed1c31..d8751ea20303 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -509,7 +509,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 	edid = drm_get_edid(connector, vc4_hdmi->ddc);
 	cec_s_phys_addr_from_edid(vc4_hdmi->cec_adap, edid);
 	if (!edid)
-		return -ENODEV;
+		return 0;
 
 	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index c52c7bf1485b..717d624e9a05 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -456,8 +456,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 		.no_wait_gpu = false
 	};
 	u32 j, initial_line = dst_offset / dst_stride;
-	struct vmw_bo_blit_line_data d;
+	struct vmw_bo_blit_line_data d = {0};
 	int ret = 0;
+	struct page **dst_pages = NULL;
+	struct page **src_pages = NULL;
 
 	/* Buffer objects need to be either pinned or reserved: */
 	if (!(dst->pin_count))
@@ -477,12 +479,35 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 			return ret;
 	}
 
+	if (!src->ttm->pages && src->ttm->sg) {
+		src_pages = kvmalloc_array(src->ttm->num_pages,
+					   sizeof(struct page *), GFP_KERNEL);
+		if (!src_pages)
+			return -ENOMEM;
+		ret = drm_prime_sg_to_page_array(src->ttm->sg, src_pages,
+						 src->ttm->num_pages);
+		if (ret)
+			goto out;
+	}
+	if (!dst->ttm->pages && dst->ttm->sg) {
+		dst_pages = kvmalloc_array(dst->ttm->num_pages,
+					   sizeof(struct page *), GFP_KERNEL);
+		if (!dst_pages) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		ret = drm_prime_sg_to_page_array(dst->ttm->sg, dst_pages,
+						 dst->ttm->num_pages);
+		if (ret)
+			goto out;
+	}
+
 	d.mapped_dst = 0;
 	d.mapped_src = 0;
 	d.dst_addr = NULL;
 	d.src_addr = NULL;
-	d.dst_pages = dst->ttm->pages;
-	d.src_pages = src->ttm->pages;
+	d.dst_pages = dst->ttm->pages ? dst->ttm->pages : dst_pages;
+	d.src_pages = src->ttm->pages ? src->ttm->pages : src_pages;
 	d.dst_num_pages = PFN_UP(dst->resource->size);
 	d.src_num_pages = PFN_UP(src->resource->size);
 	d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL);
@@ -504,6 +529,10 @@ out:
 		kunmap_atomic(d.src_addr);
 	if (d.dst_addr)
 		kunmap_atomic(d.dst_addr);
+	if (src_pages)
+		kvfree(src_pages);
+	if (dst_pages)
+		kvfree(dst_pages);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index bfd41ce3c8f4..e5eb21a471a6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -377,7 +377,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv,
 {
 	struct ttm_operation_ctx ctx = {
 		.interruptible = params->bo_type != ttm_bo_type_kernel,
-		.no_wait_gpu = false
+		.no_wait_gpu = false,
+		.resv = params->resv,
 	};
 	struct ttm_device *bdev = &dev_priv->bdev;
 	struct drm_device *vdev = &dev_priv->drm;
@@ -394,8 +395,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv,
 
 	vmw_bo_placement_set(vmw_bo, params->domain, params->busy_domain);
 	ret = ttm_bo_init_reserved(bdev, &vmw_bo->tbo, params->bo_type,
-				   &vmw_bo->placement, 0, &ctx, NULL,
-				   NULL, destroy);
+				   &vmw_bo->placement, 0, &ctx,
+				   params->sg, params->resv, destroy);
 	if (unlikely(ret))
 		return ret;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
index 0d496dc9c6af..f349642e6190 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
@@ -55,6 +55,8 @@ struct vmw_bo_params {
 	enum ttm_bo_type bo_type;
 	size_t size;
 	bool pin;
+	struct dma_resv *resv;
+	struct sg_table *sg;
 };
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index d3e308fdfd5b..58fb40c93100 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -666,11 +666,12 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 		[vmw_dma_map_populate] = "Caching DMA mappings.",
 		[vmw_dma_map_bind] = "Giving up DMA mappings early."};
 
-	/* TTM currently doesn't fully support SEV encryption. */
-	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
-		return -EINVAL;
-
-	if (vmw_force_coherent)
+	/*
+	 * When running with SEV we always want dma mappings, because
+	 * otherwise ttm tt pool pages will bounce through swiotlb running
+	 * out of available space.
+	 */
+	if (vmw_force_coherent || cc_platform_has(CC_ATTR_MEM_ENCRYPT))
 		dev_priv->map_mode = vmw_dma_alloc_coherent;
 	else if (vmw_restrict_iommu)
 		dev_priv->map_mode = vmw_dma_map_bind;
@@ -1444,12 +1445,15 @@ static void vmw_debugfs_resource_managers_init(struct vmw_private *vmw)
 					    root, "system_ttm");
 	ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, TTM_PL_VRAM),
 					    root, "vram_ttm");
-	ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR),
-					    root, "gmr_ttm");
-	ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB),
-					    root, "mob_ttm");
-	ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM),
-					    root, "system_mob_ttm");
+	if (vmw->has_gmr)
+		ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR),
+						    root, "gmr_ttm");
+	if (vmw->has_mob) {
+		ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB),
+						    root, "mob_ttm");
+		ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM),
+						    root, "system_mob_ttm");
+	}
 }
 
 static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
@@ -1624,6 +1628,7 @@ static const struct drm_driver driver = {
 
 	.prime_fd_to_handle = vmw_prime_fd_to_handle,
 	.prime_handle_to_fd = vmw_prime_handle_to_fd,
+	.gem_prime_import_sg_table = vmw_prime_import_sg_table,
 
 	.fops = &vmwgfx_driver_fops,
 	.name = VMWGFX_DRIVER_NAME,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 12efecc17df6..b019a1a1787a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1130,6 +1130,9 @@ extern int vmw_prime_handle_to_fd(struct drm_device *dev,
 				  struct drm_file *file_priv,
 				  uint32_t handle, uint32_t flags,
 				  int *prime_fd);
+struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev,
+						 struct dma_buf_attachment *attach,
+						 struct sg_table *table);
 
 /*
  * MemoryOBject management -  vmwgfx_mob.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c
index 12787bb9c111..d6bcaf078b1f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c
@@ -149,6 +149,38 @@ out_no_bo:
 	return ret;
 }
 
+struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev,
+						 struct dma_buf_attachment *attach,
+						 struct sg_table *table)
+{
+	int ret;
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct drm_gem_object *gem = NULL;
+	struct vmw_bo *vbo;
+	struct vmw_bo_params params = {
+		.domain = (dev_priv->has_mob) ? VMW_BO_DOMAIN_SYS : VMW_BO_DOMAIN_VRAM,
+		.busy_domain = VMW_BO_DOMAIN_SYS,
+		.bo_type = ttm_bo_type_sg,
+		.size = attach->dmabuf->size,
+		.pin = false,
+		.resv = attach->dmabuf->resv,
+		.sg = table,
+
+	};
+
+	dma_resv_lock(params.resv, NULL);
+
+	ret = vmw_bo_create(dev_priv, &params, &vbo);
+	if (ret != 0)
+		goto out_no_bo;
+
+	vbo->tbo.base.funcs = &vmw_gem_object_funcs;
+
+	gem = &vbo->tbo.base;
+out_no_bo:
+	dma_resv_unlock(params.resv);
+	return gem;
+}
 
 int vmw_gem_object_create_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index cd4925346ed4..84ae4e10a2eb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -933,6 +933,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
 int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
 			     struct drm_atomic_state *state)
 {
+	struct vmw_private *vmw = vmw_priv(crtc->dev);
 	struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state,
 									 crtc);
 	struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc);
@@ -940,9 +941,13 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
 	bool has_primary = new_state->plane_mask &
 			   drm_plane_mask(crtc->primary);
 
-	/* We always want to have an active plane with an active CRTC */
-	if (has_primary != new_state->enable)
-		return -EINVAL;
+	/*
+	 * This is fine in general, but broken userspace might expect
+	 * some actual rendering so give a clue as why it's blank.
+	 */
+	if (new_state->enable && !has_primary)
+		drm_dbg_driver(&vmw->drm,
+			       "CRTC without a primary plane will be blank.\n");
 
 
 	if (new_state->connector_mask != connector_mask &&
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index a94947b588e8..19a843da87b7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -243,10 +243,10 @@ struct vmw_framebuffer_bo {
 
 
 static const uint32_t __maybe_unused vmw_primary_plane_formats[] = {
-	DRM_FORMAT_XRGB1555,
-	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB1555,
 };
 
 static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index 2d72a5ee7c0c..c99cad444991 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -75,8 +75,12 @@ int vmw_prime_fd_to_handle(struct drm_device *dev,
 			   int fd, u32 *handle)
 {
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	int ret = ttm_prime_fd_to_handle(tfile, fd, handle);
 
-	return ttm_prime_fd_to_handle(tfile, fd, handle);
+	if (ret)
+		ret = drm_gem_prime_fd_to_handle(dev, file_priv, fd, handle);
+
+	return ret;
 }
 
 int vmw_prime_handle_to_fd(struct drm_device *dev,
@@ -85,5 +89,12 @@ int vmw_prime_handle_to_fd(struct drm_device *dev,
 			   int *prime_fd)
 {
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	return ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
+	int ret;
+
+	if (handle > VMWGFX_NUM_MOB)
+		ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
+	else
+		ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd);
+
+	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 4d23d0a70bcb..621d98b376bb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -188,13 +188,18 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 	switch (dev_priv->map_mode) {
 	case vmw_dma_map_bind:
 	case vmw_dma_map_populate:
-		vsgt->sgt = &vmw_tt->sgt;
-		ret = sg_alloc_table_from_pages_segment(
-			&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
-			(unsigned long)vsgt->num_pages << PAGE_SHIFT,
-			dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL);
-		if (ret)
-			goto out_sg_alloc_fail;
+		if (vmw_tt->dma_ttm.page_flags  & TTM_TT_FLAG_EXTERNAL) {
+			vsgt->sgt = vmw_tt->dma_ttm.sg;
+		} else {
+			vsgt->sgt = &vmw_tt->sgt;
+			ret = sg_alloc_table_from_pages_segment(&vmw_tt->sgt,
+				vsgt->pages, vsgt->num_pages, 0,
+				(unsigned long)vsgt->num_pages << PAGE_SHIFT,
+				dma_get_max_seg_size(dev_priv->drm.dev),
+				GFP_KERNEL);
+			if (ret)
+				goto out_sg_alloc_fail;
+		}
 
 		ret = vmw_ttm_map_for_dma(vmw_tt);
 		if (unlikely(ret != 0))
@@ -209,8 +214,9 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 	return 0;
 
 out_map_fail:
-	sg_free_table(vmw_tt->vsgt.sgt);
-	vmw_tt->vsgt.sgt = NULL;
+	drm_warn(&dev_priv->drm, "VSG table map failed!");
+	sg_free_table(vsgt->sgt);
+	vsgt->sgt = NULL;
 out_sg_alloc_fail:
 	return ret;
 }
@@ -356,15 +362,17 @@ static void vmw_ttm_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
 static int vmw_ttm_populate(struct ttm_device *bdev,
 			    struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
-	int ret;
+	bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
 
-	/* TODO: maybe completely drop this ? */
 	if (ttm_tt_is_populated(ttm))
 		return 0;
 
-	ret = ttm_pool_alloc(&bdev->pool, ttm, ctx);
+	if (external && ttm->sg)
+		return  drm_prime_sg_to_dma_addr_array(ttm->sg,
+						       ttm->dma_address,
+						       ttm->num_pages);
 
-	return ret;
+	return ttm_pool_alloc(&bdev->pool, ttm, ctx);
 }
 
 static void vmw_ttm_unpopulate(struct ttm_device *bdev,
@@ -372,6 +380,10 @@ static void vmw_ttm_unpopulate(struct ttm_device *bdev,
 {
 	struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
 						 dma_ttm);
+	bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
+
+	if (external)
+		return;
 
 	vmw_ttm_unbind(bdev, ttm);
 
@@ -390,6 +402,7 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
 {
 	struct vmw_ttm_tt *vmw_be;
 	int ret;
+	bool external = bo->type == ttm_bo_type_sg;
 
 	vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL);
 	if (!vmw_be)
@@ -398,7 +411,10 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
 	vmw_be->dev_priv = vmw_priv_from_ttm(bo->bdev);
 	vmw_be->mob = NULL;
 
-	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
+	if (external)
+		page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE;
+
+	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent || external)
 		ret = ttm_sg_tt_init(&vmw_be->dma_ttm, bo, page_flags,
 				     ttm_cached);
 	else
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 5a428ca00f10..c29a850859ad 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -172,8 +172,8 @@ subdir-ccflags-$(CONFIG_DRM_XE_DISPLAY) += \
 	-Ddrm_i915_gem_object=xe_bo \
 	-Ddrm_i915_private=xe_device
 
-CFLAGS_i915-display/intel_fbdev.o = $(call cc-disable-warning, override-init)
-CFLAGS_i915-display/intel_display_device.o = $(call cc-disable-warning, override-init)
+CFLAGS_i915-display/intel_fbdev.o = -Wno-override-init
+CFLAGS_i915-display/intel_display_device.o = -Wno-override-init
 
 # Rule to build SOC code shared with i915
 $(obj)/i915-soc/%.o: $(srctree)/drivers/gpu/drm/i915/soc/%.c FORCE
diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.c b/drivers/gpu/drm/xe/display/intel_fb_bo.c
index b21da7b745a5..a9c1f9885c6b 100644
--- a/drivers/gpu/drm/xe/display/intel_fb_bo.c
+++ b/drivers/gpu/drm/xe/display/intel_fb_bo.c
@@ -31,7 +31,7 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb,
 
 	ret = ttm_bo_reserve(&bo->ttm, true, false, NULL);
 	if (ret)
-		return ret;
+		goto err;
 
 	if (!(bo->flags & XE_BO_SCANOUT_BIT)) {
 		/*
@@ -42,12 +42,16 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb,
 		 */
 		if (XE_IOCTL_DBG(i915, !list_empty(&bo->ttm.base.gpuva.list))) {
 			ttm_bo_unreserve(&bo->ttm);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err;
 		}
 		bo->flags |= XE_BO_SCANOUT_BIT;
 	}
 	ttm_bo_unreserve(&bo->ttm);
+	return 0;
 
+err:
+	xe_bo_put(bo);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index e4db069f0db3..6ec375c1c4b6 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -108,11 +108,6 @@ int xe_display_create(struct xe_device *xe)
 	xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0);
 
 	drmm_mutex_init(&xe->drm, &xe->sb_lock);
-	drmm_mutex_init(&xe->drm, &xe->display.backlight.lock);
-	drmm_mutex_init(&xe->drm, &xe->display.audio.mutex);
-	drmm_mutex_init(&xe->drm, &xe->display.wm.wm_mutex);
-	drmm_mutex_init(&xe->drm, &xe->display.pps.mutex);
-	drmm_mutex_init(&xe->drm, &xe->display.hdcp.hdcp_mutex);
 	xe->enabled_irq_mask = ~0;
 
 	err = drmm_add_action_or_reset(&xe->drm, display_destroy, NULL);
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 0b1266c88a6a..deddc8be48c0 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -125,7 +125,7 @@
 #define RING_EXECLIST_STATUS_LO(base)		XE_REG((base) + 0x234)
 #define RING_EXECLIST_STATUS_HI(base)		XE_REG((base) + 0x234 + 4)
 
-#define RING_CONTEXT_CONTROL(base)		XE_REG((base) + 0x244)
+#define RING_CONTEXT_CONTROL(base)		XE_REG((base) + 0x244, XE_REG_OPTION_MASKED)
 #define	  CTX_CTRL_INHIBIT_SYN_CTX_SWITCH	REG_BIT(3)
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	REG_BIT(0)
 
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 6603a0ea79c5..9c0837b6fdfc 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -144,9 +144,6 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
 			.mem_type = XE_PL_TT,
 		};
 		*c += 1;
-
-		if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
-			bo->props.preferred_mem_type = XE_PL_TT;
 	}
 }
 
@@ -181,25 +178,15 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo,
 	}
 	places[*c] = place;
 	*c += 1;
-
-	if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
-		bo->props.preferred_mem_type = mem_type;
 }
 
 static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
 			 u32 bo_flags, u32 *c)
 {
-	if (bo->props.preferred_gt == XE_GT1) {
-		if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
-			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
-		if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
-			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
-	} else {
-		if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
-			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
-		if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
-			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
-	}
+	if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
+		add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
+	if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
+		add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
 }
 
 static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
@@ -223,17 +210,8 @@ static int __xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
 {
 	u32 c = 0;
 
-	bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
-
-	/* The order of placements should indicate preferred location */
-
-	if (bo->props.preferred_mem_class == DRM_XE_MEM_REGION_CLASS_SYSMEM) {
-		try_add_system(xe, bo, bo_flags, &c);
-		try_add_vram(xe, bo, bo_flags, &c);
-	} else {
-		try_add_vram(xe, bo, bo_flags, &c);
-		try_add_system(xe, bo, bo_flags, &c);
-	}
+	try_add_vram(xe, bo, bo_flags, &c);
+	try_add_system(xe, bo, bo_flags, &c);
 	try_add_stolen(xe, bo, bo_flags, &c);
 
 	if (!c)
@@ -1126,13 +1104,6 @@ static void xe_gem_object_close(struct drm_gem_object *obj,
 	}
 }
 
-static bool should_migrate_to_system(struct xe_bo *bo)
-{
-	struct xe_device *xe = xe_bo_device(bo);
-
-	return xe_device_in_fault_mode(xe) && bo->props.cpu_atomic;
-}
-
 static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *tbo = vmf->vma->vm_private_data;
@@ -1141,7 +1112,7 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 	struct xe_bo *bo = ttm_to_xe_bo(tbo);
 	bool needs_rpm = bo->flags & XE_BO_CREATE_VRAM_MASK;
 	vm_fault_t ret;
-	int idx, r = 0;
+	int idx;
 
 	if (needs_rpm)
 		xe_device_mem_access_get(xe);
@@ -1153,17 +1124,8 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 	if (drm_dev_enter(ddev, &idx)) {
 		trace_xe_bo_cpu_fault(bo);
 
-		if (should_migrate_to_system(bo)) {
-			r = xe_bo_migrate(bo, XE_PL_TT);
-			if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR)
-				ret = VM_FAULT_NOPAGE;
-			else if (r)
-				ret = VM_FAULT_SIGBUS;
-		}
-		if (!ret)
-			ret = ttm_bo_vm_fault_reserved(vmf,
-						       vmf->vma->vm_page_prot,
-						       TTM_BO_VM_NUM_PREFAULT);
+		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+					       TTM_BO_VM_NUM_PREFAULT);
 		drm_dev_exit(idx);
 	} else {
 		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
@@ -1291,9 +1253,6 @@ struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo,
 	bo->flags = flags;
 	bo->cpu_caching = cpu_caching;
 	bo->ttm.base.funcs = &xe_gem_object_funcs;
-	bo->props.preferred_mem_class = XE_BO_PROPS_INVALID;
-	bo->props.preferred_gt = XE_BO_PROPS_INVALID;
-	bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
 	bo->ttm.priority = XE_BO_PRIORITY_NORMAL;
 	INIT_LIST_HEAD(&bo->pinned_link);
 #ifdef CONFIG_PROC_FS
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 14ef13b7b421..86422e113d39 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -56,25 +56,6 @@ struct xe_bo {
 	 */
 	struct list_head client_link;
 #endif
-	/** @props: BO user controlled properties */
-	struct {
-		/** @preferred_mem: preferred memory class for this BO */
-		s16 preferred_mem_class;
-		/** @prefered_gt: preferred GT for this BO */
-		s16 preferred_gt;
-		/** @preferred_mem_type: preferred memory type */
-		s32 preferred_mem_type;
-		/**
-		 * @cpu_atomic: the CPU expects to do atomics operations to
-		 * this BO
-		 */
-		bool cpu_atomic;
-		/**
-		 * @device_atomic: the device expects to do atomics operations
-		 * to this BO
-		 */
-		bool device_atomic;
-	} props;
 	/** @freed: List node for delayed put. */
 	struct llist_node freed;
 	/** @created: Whether the bo has passed initial creation */
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index ca85e81fdb44..d32ff3857e65 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -193,6 +193,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy)
 {
 	struct xe_device *xe = to_xe_device(dev);
 
+	if (xe->preempt_fence_wq)
+		destroy_workqueue(xe->preempt_fence_wq);
+
 	if (xe->ordered_wq)
 		destroy_workqueue(xe->ordered_wq);
 
@@ -258,9 +261,15 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 	INIT_LIST_HEAD(&xe->pinned.external_vram);
 	INIT_LIST_HEAD(&xe->pinned.evicted);
 
+	xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0);
 	xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0);
 	xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0);
-	if (!xe->ordered_wq || !xe->unordered_wq) {
+	if (!xe->ordered_wq || !xe->unordered_wq ||
+	    !xe->preempt_fence_wq) {
+		/*
+		 * Cleanup done in xe_device_destroy via
+		 * drmm_add_action_or_reset register above
+		 */
 		drm_err(&xe->drm, "Failed to allocate xe workqueues\n");
 		err = -ENOMEM;
 		goto err;
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 14be34d9f543..d413bc2c6be5 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -58,7 +58,7 @@ static inline struct xe_tile *xe_device_get_root_tile(struct xe_device *xe)
 
 static inline struct xe_gt *xe_tile_get_gt(struct xe_tile *tile, u8 gt_id)
 {
-	if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id > XE_MAX_GT_PER_TILE))
+	if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id >= XE_MAX_GT_PER_TILE))
 		gt_id = 0;
 
 	return gt_id ? tile->media_gt : tile->primary_gt;
@@ -79,7 +79,7 @@ static inline struct xe_gt *xe_device_get_gt(struct xe_device *xe, u8 gt_id)
 	if (MEDIA_VER(xe) >= 13) {
 		gt = xe_tile_get_gt(root_tile, gt_id);
 	} else {
-		if (drm_WARN_ON(&xe->drm, gt_id > XE_MAX_TILES_PER_DEVICE))
+		if (drm_WARN_ON(&xe->drm, gt_id >= XE_MAX_TILES_PER_DEVICE))
 			gt_id = 0;
 
 		gt = xe->tiles[gt_id].primary_gt;
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 9785eef2e5a4..8e3a222b41cf 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -363,6 +363,9 @@ struct xe_device {
 	/** @ufence_wq: user fence wait queue */
 	wait_queue_head_t ufence_wq;
 
+	/** @preempt_fence_wq: used to serialize preempt fences */
+	struct workqueue_struct *preempt_fence_wq;
+
 	/** @ordered_wq: used to serialize compute mode resume */
 	struct workqueue_struct *ordered_wq;
 
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 952496c6260d..cc5e0f75de3c 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -94,48 +94,16 @@
  *	Unlock all
  */
 
+/*
+ * Add validation and rebinding to the drm_exec locking loop, since both can
+ * trigger eviction which may require sleeping dma_resv locks.
+ */
 static int xe_exec_fn(struct drm_gpuvm_exec *vm_exec)
 {
 	struct xe_vm *vm = container_of(vm_exec->vm, struct xe_vm, gpuvm);
-	struct drm_gem_object *obj;
-	unsigned long index;
-	int num_fences;
-	int ret;
-
-	ret = drm_gpuvm_validate(vm_exec->vm, &vm_exec->exec);
-	if (ret)
-		return ret;
-
-	/*
-	 * 1 fence slot for the final submit, and 1 more for every per-tile for
-	 * GPU bind and 1 extra for CPU bind. Note that there are potentially
-	 * many vma per object/dma-resv, however the fence slot will just be
-	 * re-used, since they are largely the same timeline and the seqno
-	 * should be in order. In the case of CPU bind there is dummy fence used
-	 * for all CPU binds, so no need to have a per-tile slot for that.
-	 */
-	num_fences = 1 + 1 + vm->xe->info.tile_count;
 
-	/*
-	 * We don't know upfront exactly how many fence slots we will need at
-	 * the start of the exec, since the TTM bo_validate above can consume
-	 * numerous fence slots. Also due to how the dma_resv_reserve_fences()
-	 * works it only ensures that at least that many fence slots are
-	 * available i.e if there are already 10 slots available and we reserve
-	 * two more, it can just noop without reserving anything.  With this it
-	 * is quite possible that TTM steals some of the fence slots and then
-	 * when it comes time to do the vma binding and final exec stage we are
-	 * lacking enough fence slots, leading to some nasty BUG_ON() when
-	 * adding the fences. Hence just add our own fences here, after the
-	 * validate stage.
-	 */
-	drm_exec_for_each_locked_object(&vm_exec->exec, index, obj) {
-		ret = dma_resv_reserve_fences(obj->resv, num_fences);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	/* The fence slot added here is intended for the exec sched job. */
+	return xe_vm_validate_rebind(vm, &vm_exec->exec, 1);
 }
 
 int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
@@ -152,7 +120,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct drm_exec *exec = &vm_exec.exec;
 	u32 i, num_syncs = 0, num_ufence = 0;
 	struct xe_sched_job *job;
-	struct dma_fence *rebind_fence;
 	struct xe_vm *vm;
 	bool write_locked, skip_retry = false;
 	ktime_t end = 0;
@@ -235,6 +202,29 @@ retry:
 			goto err_unlock_list;
 	}
 
+	if (!args->num_batch_buffer) {
+		err = xe_vm_lock(vm, true);
+		if (err)
+			goto err_unlock_list;
+
+		if (!xe_vm_in_lr_mode(vm)) {
+			struct dma_fence *fence;
+
+			fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
+			if (IS_ERR(fence)) {
+				err = PTR_ERR(fence);
+				goto err_unlock_list;
+			}
+			for (i = 0; i < num_syncs; i++)
+				xe_sync_entry_signal(&syncs[i], NULL, fence);
+			xe_exec_queue_last_fence_set(q, vm, fence);
+			dma_fence_put(fence);
+		}
+
+		xe_vm_unlock(vm);
+		goto err_unlock_list;
+	}
+
 	vm_exec.vm = &vm->gpuvm;
 	vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
 	if (xe_vm_in_lr_mode(vm)) {
@@ -254,24 +244,6 @@ retry:
 		goto err_exec;
 	}
 
-	if (!args->num_batch_buffer) {
-		if (!xe_vm_in_lr_mode(vm)) {
-			struct dma_fence *fence;
-
-			fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
-			if (IS_ERR(fence)) {
-				err = PTR_ERR(fence);
-				goto err_exec;
-			}
-			for (i = 0; i < num_syncs; i++)
-				xe_sync_entry_signal(&syncs[i], NULL, fence);
-			xe_exec_queue_last_fence_set(q, vm, fence);
-			dma_fence_put(fence);
-		}
-
-		goto err_exec;
-	}
-
 	if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
 		err = -EWOULDBLOCK;	/* Aliased to -EAGAIN */
 		skip_retry = true;
@@ -285,39 +257,7 @@ retry:
 		goto err_exec;
 	}
 
-	/*
-	 * Rebind any invalidated userptr or evicted BOs in the VM, non-compute
-	 * VM mode only.
-	 */
-	rebind_fence = xe_vm_rebind(vm, false);
-	if (IS_ERR(rebind_fence)) {
-		err = PTR_ERR(rebind_fence);
-		goto err_put_job;
-	}
-
-	/*
-	 * We store the rebind_fence in the VM so subsequent execs don't get
-	 * scheduled before the rebinds of userptrs / evicted BOs is complete.
-	 */
-	if (rebind_fence) {
-		dma_fence_put(vm->rebind_fence);
-		vm->rebind_fence = rebind_fence;
-	}
-	if (vm->rebind_fence) {
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
-			     &vm->rebind_fence->flags)) {
-			dma_fence_put(vm->rebind_fence);
-			vm->rebind_fence = NULL;
-		} else {
-			dma_fence_get(vm->rebind_fence);
-			err = drm_sched_job_add_dependency(&job->drm,
-							   vm->rebind_fence);
-			if (err)
-				goto err_put_job;
-		}
-	}
-
-	/* Wait behind munmap style rebinds */
+	/* Wait behind rebinds */
 	if (!xe_vm_in_lr_mode(vm)) {
 		err = drm_sched_job_add_resv_dependencies(&job->drm,
 							  xe_vm_resv(vm),
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 11e150f4c0c1..ead25d5e723e 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -448,7 +448,7 @@ find_hw_engine(struct xe_device *xe,
 {
 	u32 idx;
 
-	if (eci.engine_class > ARRAY_SIZE(user_to_xe_engine_class))
+	if (eci.engine_class >= ARRAY_SIZE(user_to_xe_engine_class))
 		return NULL;
 
 	if (eci.gt_id >= xe->info.gt_count)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 62b3d9d1d7cd..462b33195032 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -148,6 +148,11 @@ struct xe_exec_queue {
 	const struct xe_ring_ops *ring_ops;
 	/** @entity: DRM sched entity for this exec queue (1 to 1 relationship) */
 	struct drm_sched_entity *entity;
+	/**
+	 * @tlb_flush_seqno: The seqno of the last rebind tlb flush performed
+	 * Protected by @vm's resv. Unused if @vm == NULL.
+	 */
+	u64 tlb_flush_seqno;
 	/** @lrc: logical ring context for this exec queue */
 	struct xe_lrc lrc[];
 };
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 73c535193a98..fa9e9853c53b 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type)
 static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
 {
 	return BIT(tile->id) & vma->tile_present &&
-		!(BIT(tile->id) & vma->usm.tile_invalidated);
+		!(BIT(tile->id) & vma->tile_invalidated);
 }
 
 static bool vma_matches(struct xe_vma *vma, u64 page_addr)
@@ -100,10 +100,9 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
 {
 	struct xe_bo *bo = xe_vma_bo(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
-	unsigned int num_shared = 2; /* slots for bind + move */
 	int err;
 
-	err = xe_vm_prepare_vma(exec, vma, num_shared);
+	err = xe_vm_lock_vma(exec, vma);
 	if (err)
 		return err;
 
@@ -226,7 +225,7 @@ retry_userptr:
 
 	if (xe_vma_is_userptr(vma))
 		ret = xe_vma_userptr_check_repin(to_userptr_vma(vma));
-	vma->usm.tile_invalidated &= ~BIT(tile->id);
+	vma->tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
 	drm_exec_fini(&exec);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index f03e077f81a0..e598a4363d01 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -61,7 +61,6 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt)
 	INIT_LIST_HEAD(&gt->tlb_invalidation.pending_fences);
 	spin_lock_init(&gt->tlb_invalidation.pending_lock);
 	spin_lock_init(&gt->tlb_invalidation.lock);
-	gt->tlb_invalidation.fence_context = dma_fence_context_alloc(1);
 	INIT_DELAYED_WORK(&gt->tlb_invalidation.fence_tdr,
 			  xe_gt_tlb_fence_timeout);
 
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 70c615dd1498..07b2f724ec45 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -177,13 +177,6 @@ struct xe_gt {
 		 * xe_gt_tlb_fence_timeout after the timeut interval is over.
 		 */
 		struct delayed_work fence_tdr;
-		/** @tlb_invalidation.fence_context: context for TLB invalidation fences */
-		u64 fence_context;
-		/**
-		 * @tlb_invalidation.fence_seqno: seqno to TLB invalidation fences, protected by
-		 * tlb_invalidation.lock
-		 */
-		u32 fence_seqno;
 		/** @tlb_invalidation.lock: protects TLB invalidation fences */
 		spinlock_t lock;
 	} tlb_invalidation;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index ff77bc8da1b2..e2a4c3b5e9ff 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1220,7 +1220,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	init_waitqueue_head(&ge->suspend_wait);
 
 	timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
-		  q->sched_props.job_timeout_ms;
+		  msecs_to_jiffies(q->sched_props.job_timeout_ms);
 	err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
 			    get_submit_wq(guc),
 			    q->lrc[0].ring.size / MAX_JOB_SIZE_BYTES, 64,
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index b82233a41606..9ac7fbe201b3 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -290,7 +290,7 @@ xe_hwmon_power1_max_interval_show(struct device *dev, struct device_attribute *a
 	 * As y can be < 2, we compute tau4 = (4 | x) << y
 	 * and then add 2 when doing the final right shift to account for units
 	 */
-	tau4 = ((1 << x_w) | x) << y;
+	tau4 = (u64)((1 << x_w) | x) << y;
 
 	/* val in hwmon interface units (millisec) */
 	out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
@@ -330,7 +330,7 @@ xe_hwmon_power1_max_interval_store(struct device *dev, struct device_attribute *
 	r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT);
 	x = REG_FIELD_GET(PKG_MAX_WIN_X, r);
 	y = REG_FIELD_GET(PKG_MAX_WIN_Y, r);
-	tau4 = ((1 << x_w) | x) << y;
+	tau4 = (u64)((1 << x_w) | x) << y;
 	max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
 
 	if (val > max_win)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 7ad853b0788a..57066faf575e 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -97,7 +97,6 @@ static void set_offsets(u32 *regs,
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END 0
 {
 	const u32 base = hwe->mmio_base;
 
@@ -168,7 +167,7 @@ static const u8 gen12_xcs_offsets[] = {
 	REG16(0x274),
 	REG16(0x270),
 
-	END
+	0
 };
 
 static const u8 dg2_xcs_offsets[] = {
@@ -202,7 +201,7 @@ static const u8 dg2_xcs_offsets[] = {
 	REG16(0x274),
 	REG16(0x270),
 
-	END
+	0
 };
 
 static const u8 gen12_rcs_offsets[] = {
@@ -298,7 +297,7 @@ static const u8 gen12_rcs_offsets[] = {
 	REG(0x084),
 	NOP(1),
 
-	END
+	0
 };
 
 static const u8 xehp_rcs_offsets[] = {
@@ -339,7 +338,7 @@ static const u8 xehp_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END
+	0
 };
 
 static const u8 dg2_rcs_offsets[] = {
@@ -382,7 +381,7 @@ static const u8 dg2_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END
+	0
 };
 
 static const u8 mtl_rcs_offsets[] = {
@@ -425,7 +424,7 @@ static const u8 mtl_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END
+	0
 };
 
 #define XE2_CTX_COMMON \
@@ -471,7 +470,7 @@ static const u8 xe2_rcs_offsets[] = {
 	LRI(1, 0),              /* [0x47] */
 	REG(0x0c8),             /* [0x48] R_PWR_CLK_STATE */
 
-	END
+	0
 };
 
 static const u8 xe2_bcs_offsets[] = {
@@ -482,16 +481,15 @@ static const u8 xe2_bcs_offsets[] = {
 	REG16(0x200),           /* [0x42] BCS_SWCTRL */
 	REG16(0x204),           /* [0x44] BLIT_CCTL */
 
-	END
+	0
 };
 
 static const u8 xe2_xcs_offsets[] = {
 	XE2_CTX_COMMON,
 
-	END
+	0
 };
 
-#undef END
 #undef REG16
 #undef REG
 #undef LRI
@@ -527,9 +525,8 @@ static const u8 *reg_offsets(struct xe_device *xe, enum xe_engine_class class)
 
 static void set_context_control(u32 *regs, struct xe_hw_engine *hwe)
 {
-	regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH) |
-				    _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
-				    CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT;
+	regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
+						       CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
 	/* TODO: Timestamp */
 }
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index ee1bb938c493..2ba4fb9511f6 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -227,7 +227,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 		if (vm->flags & XE_VM_FLAG_64K && level == 1)
 			flags = XE_PDE_64K;
 
-		entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (level - 1) *
+		entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (u64)(level - 1) *
 						  XE_PAGE_SIZE, pat_index);
 		xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE * level, u64,
 			  entry | flags);
@@ -235,7 +235,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 
 	/* Write PDE's that point to our BO. */
 	for (i = 0; i < num_entries - num_level; i++) {
-		entry = vm->pt_ops->pde_encode_bo(bo, i * XE_PAGE_SIZE,
+		entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE,
 						  pat_index);
 
 		xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE +
@@ -291,7 +291,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 #define VM_SA_UPDATE_UNIT_SIZE		(XE_PAGE_SIZE / NUM_VMUSA_UNIT_PER_PAGE)
 #define NUM_VMUSA_WRITES_PER_UNIT	(VM_SA_UPDATE_UNIT_SIZE / sizeof(u64))
 	drm_suballoc_manager_init(&m->vm_update_sa,
-				  (map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) *
+				  (size_t)(map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) *
 				  NUM_VMUSA_UNIT_PER_PAGE, 0);
 
 	m->pt_bo = bo;
@@ -490,7 +490,7 @@ static void emit_pte(struct xe_migrate *m,
 	struct xe_vm *vm = m->q->vm;
 	u16 pat_index;
 	u32 ptes;
-	u64 ofs = at_pt * XE_PAGE_SIZE;
+	u64 ofs = (u64)at_pt * XE_PAGE_SIZE;
 	u64 cur_ofs;
 
 	/* Indirect access needs compression enabled uncached PAT index */
diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c
index 7bce2a332603..7d50c6e89d8e 100644
--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
+++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
@@ -49,7 +49,7 @@ static bool preempt_fence_enable_signaling(struct dma_fence *fence)
 	struct xe_exec_queue *q = pfence->q;
 
 	pfence->error = q->ops->suspend(q);
-	queue_work(system_unbound_wq, &pfence->preempt_work);
+	queue_work(q->vm->xe->preempt_fence_wq, &pfence->preempt_work);
 	return true;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 7f54bc3e389d..4efc8c1a3d7a 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1135,8 +1135,7 @@ static int invalidation_fence_init(struct xe_gt *gt,
 	spin_lock_irq(&gt->tlb_invalidation.lock);
 	dma_fence_init(&ifence->base.base, &invalidation_fence_ops,
 		       &gt->tlb_invalidation.lock,
-		       gt->tlb_invalidation.fence_context,
-		       ++gt->tlb_invalidation.fence_seqno);
+		       dma_fence_context_alloc(1), 1);
 	spin_unlock_irq(&gt->tlb_invalidation.lock);
 
 	INIT_LIST_HEAD(&ifence->base.link);
@@ -1236,6 +1235,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 	err = xe_pt_prepare_bind(tile, vma, entries, &num_entries);
 	if (err)
 		goto err;
+
+	err = dma_resv_reserve_fences(xe_vm_resv(vm), 1);
+	if (!err && !xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm)
+		err = dma_resv_reserve_fences(xe_vma_bo(vma)->ttm.base.resv, 1);
+	if (err)
+		goto err;
+
 	xe_tile_assert(tile, num_entries <= ARRAY_SIZE(entries));
 
 	xe_vm_dbg_print_entries(tile_to_xe(tile), entries, num_entries);
@@ -1254,11 +1260,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 	 * non-faulting LR, in particular on user-space batch buffer chaining,
 	 * it needs to be done here.
 	 */
-	if ((rebind && !xe_vm_in_lr_mode(vm) && !vm->batch_invalidate_tlb) ||
-	    (!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) {
+	if ((!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) {
 		ifence = kzalloc(sizeof(*ifence), GFP_KERNEL);
 		if (!ifence)
 			return ERR_PTR(-ENOMEM);
+	} else if (rebind && !xe_vm_in_lr_mode(vm)) {
+		/* We bump also if batch_invalidate_tlb is true */
+		vm->tlb_flush_seqno++;
 	}
 
 	rfence = kzalloc(sizeof(*rfence), GFP_KERNEL);
@@ -1297,7 +1305,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 		}
 
 		/* add shared fence now for pagetable delayed destroy */
-		dma_resv_add_fence(xe_vm_resv(vm), fence, !rebind &&
+		dma_resv_add_fence(xe_vm_resv(vm), fence, rebind ||
 				   last_munmap_rebind ?
 				   DMA_RESV_USAGE_KERNEL :
 				   DMA_RESV_USAGE_BOOKKEEP);
@@ -1576,6 +1584,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
 	struct dma_fence *fence = NULL;
 	struct invalidation_fence *ifence;
 	struct xe_range_fence *rfence;
+	int err;
 
 	LLIST_HEAD(deferred);
 
@@ -1593,6 +1602,12 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
 	xe_pt_calc_rfence_interval(vma, &unbind_pt_update, entries,
 				   num_entries);
 
+	err = dma_resv_reserve_fences(xe_vm_resv(vm), 1);
+	if (!err && !xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm)
+		err = dma_resv_reserve_fences(xe_vma_bo(vma)->ttm.base.resv, 1);
+	if (err)
+		return ERR_PTR(err);
+
 	ifence = kzalloc(sizeof(*ifence), GFP_KERNEL);
 	if (!ifence)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 92bb06c0586e..075f9eaef031 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -132,7 +132,7 @@ query_engine_cycles(struct xe_device *xe,
 		return -EINVAL;
 
 	eci = &resp.eci;
-	if (eci->gt_id > XE_MAX_GT_PER_TILE)
+	if (eci->gt_id >= XE_MAX_GT_PER_TILE)
 		return -EINVAL;
 
 	gt = xe_device_get_gt(xe, eci->gt_id);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index c4edffcd4a32..5b2b37b59813 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -219,10 +219,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 {
 	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 	u32 ppgtt_flag = get_ppgtt_flag(job);
-	struct xe_vm *vm = job->q->vm;
 	struct xe_gt *gt = job->q->gt;
 
-	if (vm && vm->batch_invalidate_tlb) {
+	if (job->ring_ops_flush_tlb) {
 		dw[i++] = preparser_disable(true);
 		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, true, dw, i);
@@ -270,7 +269,6 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 	struct xe_gt *gt = job->q->gt;
 	struct xe_device *xe = gt_to_xe(gt);
 	bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
-	struct xe_vm *vm = job->q->vm;
 
 	dw[i++] = preparser_disable(true);
 
@@ -282,13 +280,13 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 			i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i);
 	}
 
-	if (vm && vm->batch_invalidate_tlb)
+	if (job->ring_ops_flush_tlb)
 		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, true, dw, i);
 
 	dw[i++] = preparser_disable(false);
 
-	if (!vm || !vm->batch_invalidate_tlb)
+	if (!job->ring_ops_flush_tlb)
 		i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, dw, i);
 
@@ -317,7 +315,6 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 	struct xe_gt *gt = job->q->gt;
 	struct xe_device *xe = gt_to_xe(gt);
 	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
-	struct xe_vm *vm = job->q->vm;
 	u32 mask_flags = 0;
 
 	dw[i++] = preparser_disable(true);
@@ -327,7 +324,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 		mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS;
 
 	/* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */
-	i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i);
+	i = emit_pipe_invalidate(mask_flags, job->ring_ops_flush_tlb, dw, i);
 
 	/* hsdes: 1809175790 */
 	if (has_aux_ccs(xe))
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 8151ddafb940..b0c7fa4693cf 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -250,6 +250,16 @@ bool xe_sched_job_completed(struct xe_sched_job *job)
 
 void xe_sched_job_arm(struct xe_sched_job *job)
 {
+	struct xe_exec_queue *q = job->q;
+	struct xe_vm *vm = q->vm;
+
+	if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) &&
+	    (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) {
+		xe_vm_assert_held(vm);
+		q->tlb_flush_seqno = vm->tlb_flush_seqno;
+		job->ring_ops_flush_tlb = true;
+	}
+
 	drm_sched_job_arm(&job->drm);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
index b1d83da50a53..5e12724219fd 100644
--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
+++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
@@ -39,6 +39,8 @@ struct xe_sched_job {
 	} user_fence;
 	/** @migrate_flush_flags: Additional flush flags for migration jobs */
 	u32 migrate_flush_flags;
+	/** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */
+	bool ring_ops_flush_tlb;
 	/** @batch_addr: batch buffer address of job */
 	u64 batch_addr[];
 };
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 4ddc55527f9a..846f14507d5f 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate,
 	     TP_ARGS(vma)
 );
 
-DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate,
+DEFINE_EVENT(xe_vma, xe_vma_invalidate,
 	     TP_PROTO(struct xe_vma *vma),
 	     TP_ARGS(vma)
 );
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d28260351af2..3d4c8f342e21 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -482,17 +482,53 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
 	return 0;
 }
 
+/**
+ * xe_vm_validate_rebind() - Validate buffer objects and rebind vmas
+ * @vm: The vm for which we are rebinding.
+ * @exec: The struct drm_exec with the locked GEM objects.
+ * @num_fences: The number of fences to reserve for the operation, not
+ * including rebinds and validations.
+ *
+ * Validates all evicted gem objects and rebinds their vmas. Note that
+ * rebindings may cause evictions and hence the validation-rebind
+ * sequence is rerun until there are no more objects to validate.
+ *
+ * Return: 0 on success, negative error code on error. In particular,
+ * may return -EINTR or -ERESTARTSYS if interrupted, and -EDEADLK if
+ * the drm_exec transaction needs to be restarted.
+ */
+int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,
+			  unsigned int num_fences)
+{
+	struct drm_gem_object *obj;
+	unsigned long index;
+	int ret;
+
+	do {
+		ret = drm_gpuvm_validate(&vm->gpuvm, exec);
+		if (ret)
+			return ret;
+
+		ret = xe_vm_rebind(vm, false);
+		if (ret)
+			return ret;
+	} while (!list_empty(&vm->gpuvm.evict.list));
+
+	drm_exec_for_each_locked_object(exec, index, obj) {
+		ret = dma_resv_reserve_fences(obj->resv, num_fences);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
 				 bool *done)
 {
 	int err;
 
-	/*
-	 * 1 fence for each preempt fence plus a fence for each tile from a
-	 * possible rebind
-	 */
-	err = drm_gpuvm_prepare_vm(&vm->gpuvm, exec, vm->preempt.num_exec_queues +
-				   vm->xe->info.tile_count);
+	err = drm_gpuvm_prepare_vm(&vm->gpuvm, exec, 0);
 	if (err)
 		return err;
 
@@ -507,7 +543,7 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
 		return 0;
 	}
 
-	err = drm_gpuvm_prepare_objects(&vm->gpuvm, exec, vm->preempt.num_exec_queues);
+	err = drm_gpuvm_prepare_objects(&vm->gpuvm, exec, 0);
 	if (err)
 		return err;
 
@@ -515,14 +551,19 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
 	if (err)
 		return err;
 
-	return drm_gpuvm_validate(&vm->gpuvm, exec);
+	/*
+	 * Add validation and rebinding to the locking loop since both can
+	 * cause evictions which may require blocing dma_resv locks.
+	 * The fence reservation here is intended for the new preempt fences
+	 * we attach at the end of the rebind work.
+	 */
+	return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues);
 }
 
 static void preempt_rebind_work_func(struct work_struct *w)
 {
 	struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work);
 	struct drm_exec exec;
-	struct dma_fence *rebind_fence;
 	unsigned int fence_count = 0;
 	LIST_HEAD(preempt_fences);
 	ktime_t end = 0;
@@ -568,18 +609,11 @@ retry:
 	if (err)
 		goto out_unlock;
 
-	rebind_fence = xe_vm_rebind(vm, true);
-	if (IS_ERR(rebind_fence)) {
-		err = PTR_ERR(rebind_fence);
+	err = xe_vm_rebind(vm, true);
+	if (err)
 		goto out_unlock;
-	}
-
-	if (rebind_fence) {
-		dma_fence_wait(rebind_fence, false);
-		dma_fence_put(rebind_fence);
-	}
 
-	/* Wait on munmap style VM unbinds */
+	/* Wait on rebinds and munmap style VM unbinds */
 	wait = dma_resv_wait_timeout(xe_vm_resv(vm),
 				     DMA_RESV_USAGE_KERNEL,
 				     false, MAX_SCHEDULE_TIMEOUT);
@@ -708,6 +742,7 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 	int err = 0;
 	LIST_HEAD(tmp_evict);
 
+	xe_assert(vm->xe, !xe_vm_in_fault_mode(vm));
 	lockdep_assert_held_write(&vm->lock);
 
 	/* Collect invalidated userptrs */
@@ -724,11 +759,27 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
 				 userptr.repin_link) {
 		err = xe_vma_userptr_pin_pages(uvma);
-		if (err < 0)
-			return err;
+		if (err == -EFAULT) {
+			list_del_init(&uvma->userptr.repin_link);
+
+			/* Wait for pending binds */
+			xe_vm_lock(vm, false);
+			dma_resv_wait_timeout(xe_vm_resv(vm),
+					      DMA_RESV_USAGE_BOOKKEEP,
+					      false, MAX_SCHEDULE_TIMEOUT);
 
-		list_del_init(&uvma->userptr.repin_link);
-		list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list);
+			err = xe_vm_invalidate_vma(&uvma->vma);
+			xe_vm_unlock(vm);
+			if (err)
+				return err;
+		} else {
+			if (err < 0)
+				return err;
+
+			list_del_init(&uvma->userptr.repin_link);
+			list_move_tail(&uvma->vma.combined_links.rebind,
+				       &vm->rebind_list);
+		}
 	}
 
 	return 0;
@@ -756,14 +807,14 @@ xe_vm_bind_vma(struct xe_vma *vma, struct xe_exec_queue *q,
 	       struct xe_sync_entry *syncs, u32 num_syncs,
 	       bool first_op, bool last_op);
 
-struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
+int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
 {
-	struct dma_fence *fence = NULL;
+	struct dma_fence *fence;
 	struct xe_vma *vma, *next;
 
 	lockdep_assert_held(&vm->lock);
 	if (xe_vm_in_lr_mode(vm) && !rebind_worker)
-		return NULL;
+		return 0;
 
 	xe_vm_assert_held(vm);
 	list_for_each_entry_safe(vma, next, &vm->rebind_list,
@@ -771,17 +822,17 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
 		xe_assert(vm->xe, vma->tile_present);
 
 		list_del_init(&vma->combined_links.rebind);
-		dma_fence_put(fence);
 		if (rebind_worker)
 			trace_xe_vma_rebind_worker(vma);
 		else
 			trace_xe_vma_rebind_exec(vma);
 		fence = xe_vm_bind_vma(vma, NULL, NULL, 0, false, false);
 		if (IS_ERR(fence))
-			return fence;
+			return PTR_ERR(fence);
+		dma_fence_put(fence);
 	}
 
-	return fence;
+	return 0;
 }
 
 static void xe_vma_free(struct xe_vma *vma)
@@ -987,35 +1038,26 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 }
 
 /**
- * xe_vm_prepare_vma() - drm_exec utility to lock a vma
+ * xe_vm_lock_vma() - drm_exec utility to lock a vma
  * @exec: The drm_exec object we're currently locking for.
  * @vma: The vma for witch we want to lock the vm resv and any attached
  * object's resv.
- * @num_shared: The number of dma-fence slots to pre-allocate in the
- * objects' reservation objects.
  *
  * Return: 0 on success, negative error code on error. In particular
  * may return -EDEADLK on WW transaction contention and -EINTR if
  * an interruptible wait is terminated by a signal.
  */
-int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
-		      unsigned int num_shared)
+int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma)
 {
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct xe_bo *bo = xe_vma_bo(vma);
 	int err;
 
 	XE_WARN_ON(!vm);
-	if (num_shared)
-		err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
-	else
-		err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
-	if (!err && bo && !bo->vm) {
-		if (num_shared)
-			err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
-		else
-			err = drm_exec_lock_obj(exec, &bo->ttm.base);
-	}
+
+	err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
+	if (!err && bo && !bo->vm)
+		err = drm_exec_lock_obj(exec, &bo->ttm.base);
 
 	return err;
 }
@@ -1027,7 +1069,7 @@ static void xe_vma_destroy_unlocked(struct xe_vma *vma)
 
 	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
-		err = xe_vm_prepare_vma(&exec, vma, 0);
+		err = xe_vm_lock_vma(&exec, vma);
 		drm_exec_retry_on_contention(&exec);
 		if (XE_WARN_ON(err))
 			break;
@@ -1535,6 +1577,16 @@ void xe_vm_close_and_put(struct xe_vm *vm)
 		xe->usm.num_vm_in_fault_mode--;
 	else if (!(vm->flags & XE_VM_FLAG_MIGRATION))
 		xe->usm.num_vm_in_non_fault_mode--;
+
+	if (vm->usm.asid) {
+		void *lookup;
+
+		xe_assert(xe, xe->info.has_asid);
+		xe_assert(xe, !(vm->flags & XE_VM_FLAG_MIGRATION));
+
+		lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid);
+		xe_assert(xe, lookup == vm);
+	}
 	mutex_unlock(&xe->usm.lock);
 
 	for_each_tile(tile, xe, id)
@@ -1550,29 +1602,19 @@ static void vm_destroy_work_func(struct work_struct *w)
 	struct xe_device *xe = vm->xe;
 	struct xe_tile *tile;
 	u8 id;
-	void *lookup;
 
 	/* xe_vm_close_and_put was not called? */
 	xe_assert(xe, !vm->size);
 
 	mutex_destroy(&vm->snap_mutex);
 
-	if (!(vm->flags & XE_VM_FLAG_MIGRATION)) {
+	if (!(vm->flags & XE_VM_FLAG_MIGRATION))
 		xe_device_mem_access_put(xe);
 
-		if (xe->info.has_asid && vm->usm.asid) {
-			mutex_lock(&xe->usm.lock);
-			lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid);
-			xe_assert(xe, lookup == vm);
-			mutex_unlock(&xe->usm.lock);
-		}
-	}
-
 	for_each_tile(tile, xe, id)
 		XE_WARN_ON(vm->pt_root[id]);
 
 	trace_xe_vm_free(vm);
-	dma_fence_put(vm->rebind_fence);
 	kfree(vm);
 }
 
@@ -2024,7 +2066,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 			return err;
 	}
 
-	if (vma->tile_mask != (vma->tile_present & ~vma->usm.tile_invalidated)) {
+	if (vma->tile_mask != (vma->tile_present & ~vma->tile_invalidated)) {
 		return xe_vm_bind(vm, vma, q, xe_vma_bo(vma), syncs, num_syncs,
 				  true, first_op, last_op);
 	} else {
@@ -2495,7 +2537,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm,
 
 	lockdep_assert_held_write(&vm->lock);
 
-	err = xe_vm_prepare_vma(exec, vma, 1);
+	err = xe_vm_lock_vma(exec, vma);
 	if (err)
 		return err;
 
@@ -3214,9 +3256,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 	u8 id;
 	int ret;
 
-	xe_assert(xe, xe_vm_in_fault_mode(xe_vma_vm(vma)));
 	xe_assert(xe, !xe_vma_is_null(vma));
-	trace_xe_vma_usm_invalidate(vma);
+	trace_xe_vma_invalidate(vma);
 
 	/* Check that we don't race with page-table updates */
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
@@ -3254,7 +3295,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 		}
 	}
 
-	vma->usm.tile_invalidated = vma->tile_mask;
+	vma->tile_invalidated = vma->tile_mask;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 6df1f1c7f85d..306cd0934a19 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -207,7 +207,7 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm);
 
 int xe_vm_userptr_check_repin(struct xe_vm *vm);
 
-struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
+int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
 
 int xe_vm_invalidate_vma(struct xe_vma *vma);
 
@@ -242,8 +242,10 @@ bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
 
 int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id);
 
-int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
-		      unsigned int num_shared);
+int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma);
+
+int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,
+			  unsigned int num_fences);
 
 /**
  * xe_vm_resv() - Return's the vm's reservation object
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 79b5cab57711..badf3945083d 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -84,11 +84,8 @@ struct xe_vma {
 		struct work_struct destroy_work;
 	};
 
-	/** @usm: unified shared memory state */
-	struct {
-		/** @tile_invalidated: VMA has been invalidated */
-		u8 tile_invalidated;
-	} usm;
+	/** @tile_invalidated: VMA has been invalidated */
+	u8 tile_invalidated;
 
 	/** @tile_mask: Tile mask of where to create binding for this VMA */
 	u8 tile_mask;
@@ -180,9 +177,6 @@ struct xe_vm {
 	 */
 	struct list_head rebind_list;
 
-	/** @rebind_fence: rebind fence from execbuf */
-	struct dma_fence *rebind_fence;
-
 	/**
 	 * @destroy_work: worker to destroy VM, needed as a dma_fence signaling
 	 * from an irq context can be last put and the destroy needs to be able
@@ -267,6 +261,11 @@ struct xe_vm {
 		bool capture_once;
 	} error_capture;
 
+	/**
+	 * @tlb_flush_seqno: Required TLB flush seqno for the next exec.
+	 * protected by the vm resv.
+	 */
+	u64 tlb_flush_seqno;
 	/** @batch_invalidate_tlb: Always invalidate TLB before batch start */
 	bool batch_invalidate_tlb;
 	/** @xef: XE file handle for tracking this VM's drm client */
diff --git a/drivers/gpu/drm/xe/xe_vram_freq.c b/drivers/gpu/drm/xe/xe_vram_freq.c
index 079cc283a186..c5f6b5a5d117 100644
--- a/drivers/gpu/drm/xe/xe_vram_freq.c
+++ b/drivers/gpu/drm/xe/xe_vram_freq.c
@@ -111,8 +111,10 @@ void xe_vram_freq_sysfs_init(struct xe_tile *tile)
 		return;
 
 	kobj = kobject_create_and_add("memory", tile->sysfs);
-	if (!kobj)
+	if (!kobj) {
 		drm_warn(&xe->drm, "failed to add memory directory, err: %d\n", -ENOMEM);
+		return;
+	}
 
 	err = sysfs_create_group(kobj, &freq_group_attrs);
 	if (err) {