Merge drm/drm-fixes into drm-misc-fixes

Sima needs a more recent release to apply a patch.

Signed-off-by: Maxime Ripard <mripard@kernel.org>

177 files changed, 1379 insertions, 954 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d8a48f46b01..79827a6dcd7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -200,6 +200,7 @@ extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dc_visual_confirm;
 extern uint amdgpu_dm_abm_level;
 extern int amdgpu_backlight;
+extern int amdgpu_damage_clips;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
@@ -1078,6 +1079,8 @@ struct amdgpu_device {
 	bool				in_s3;
 	bool				in_s4;
 	bool				in_s0ix;
+	/* indicate amdgpu suspension status */
+	bool				suspend_complete;
 
 	enum pp_mp1_state               mp1_state;
 	struct amdgpu_doorbell_index doorbell_index;
@@ -1547,9 +1550,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
 #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
 bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
 #else
 static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
+static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
 #endif
 
 #if defined(CONFIG_DRM_AMD_DC)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 2deebece810e..7099ff9cf8c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1519,4 +1519,22 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 #endif /* CONFIG_AMD_PMC */
 }
 
+/**
+ * amdgpu_choose_low_power_state
+ *
+ * @adev: amdgpu_device_pointer
+ *
+ * Choose the target low power state for the GPU
+ */
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
+{
+	if (adev->in_runpm)
+		return;
+
+	if (amdgpu_acpi_is_s0ix_active(adev))
+		adev->in_s0ix = true;
+	else if (amdgpu_acpi_is_s3_active(adev))
+		adev->in_s3 = true;
+}
+
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 77e263660288..41db030ddc4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -141,11 +141,31 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 static const struct drm_client_funcs kfd_client_funcs = {
 	.unregister	= drm_client_release,
 };
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev)
+{
+	int ret;
+
+	if (!adev->kfd.init_complete)
+		return 0;
+
+	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",
+			      &kfd_client_funcs);
+	if (ret) {
+		dev_err(adev->dev, "Failed to init DRM client: %d\n",
+			ret);
+		return ret;
+	}
+
+	drm_client_register(&adev->kfd.client);
+
+	return 0;
+}
+
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
 	int i;
 	int last_valid_bit;
-	int ret;
 
 	amdgpu_amdkfd_gpuvm_init_mem_limits();
 
@@ -164,12 +184,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.enable_mes = adev->enable_mes,
 		};
 
-		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);
-		if (ret) {
-			dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
-			return;
-		}
-
 		/* this is going to have a few of the MSBs set that we need to
 		 * clear
 		 */
@@ -208,10 +222,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 
 		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
 							&gpu_resources);
-		if (adev->kfd.init_complete)
-			drm_client_register(&adev->kfd.client);
-		else
-			drm_client_release(&adev->kfd.client);
 
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index f262b9d89541..27c61c535e29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -182,6 +182,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
 				struct mm_struct *mm,
 				struct svm_range_bo *svm_bo);
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev);
 #if defined(CONFIG_DEBUG_FS)
 int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);
 #endif
@@ -301,7 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev,
 					  struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv);
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
 		struct amdgpu_device *adev, struct kgd_mem *mem, bool intr);
 int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 899e31e3a5e8..3a3f3ce09f00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
-		if (!(ring && drm_sched_wqueue_ready(&ring->sched)))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* stop secheduler and drain ring. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index f183d7faeeec..231fd927dcfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2085,21 +2085,35 @@ out:
 	return ret;
 }
 
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
 {
 	struct kfd_mem_attachment *entry;
 	struct amdgpu_vm *vm;
+	int ret;
 
 	vm = drm_priv_to_vm(drm_priv);
 
 	mutex_lock(&mem->lock);
 
+	ret = amdgpu_bo_reserve(mem->bo, true);
+	if (ret)
+		goto out;
+
 	list_for_each_entry(entry, &mem->attachments, list) {
-		if (entry->bo_va->base.vm == vm)
-			kfd_mem_dmaunmap_attachment(mem, entry);
+		if (entry->bo_va->base.vm != vm)
+			continue;
+		if (entry->bo_va->base.bo->tbo.ttm &&
+		    !entry->bo_va->base.bo->tbo.ttm->sg)
+			continue;
+
+		kfd_mem_dmaunmap_attachment(mem, entry);
 	}
 
+	amdgpu_bo_unreserve(mem->bo);
+out:
 	mutex_unlock(&mem->lock);
+
+	return ret;
 }
 
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index e485dd3357c6..1afbb2e932c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1678,7 +1678,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_stop(&ring->sched);
 	}
@@ -1694,7 +1694,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_start(&ring->sched);
 	}
@@ -1916,8 +1916,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 
 	ring = adev->rings[val];
 
-	if (!ring || !ring->funcs->preempt_ib ||
-	    !drm_sched_wqueue_ready(&ring->sched))
+	if (!amdgpu_ring_sched_ready(ring) ||
+	    !ring->funcs->preempt_ib)
 		return -EINVAL;
 
 	/* the last preemption failed */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b158d27d0a71..94bdb5fa6ebc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4121,23 +4121,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				}
 			}
 		} else {
-			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-			case IP_VERSION(13, 0, 0):
-			case IP_VERSION(13, 0, 7):
-			case IP_VERSION(13, 0, 10):
-				r = psp_gpu_reset(adev);
-				break;
-			default:
-				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;
-				break;
-			}
-
+			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;
@@ -4524,13 +4514,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i, r;
 
+	amdgpu_choose_low_power_state(adev);
+
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	/* Evict the majority of BOs before starting suspend sequence */
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		return r;
+		goto unprepare;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
@@ -4539,10 +4531,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
 		if (r)
-			return r;
+			goto unprepare;
 	}
 
 	return 0;
+
+unprepare:
+	adev->in_s0ix = adev->in_s3 = false;
+
+	return r;
 }
 
 /**
@@ -4579,7 +4576,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
-	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
 	amdgpu_ras_suspend(adev);
 
@@ -5031,7 +5027,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		spin_lock(&ring->sched.job_list_lock);
@@ -5170,7 +5166,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* Clear job fence from fence drv to avoid force_completion
@@ -5637,7 +5633,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
@@ -5706,7 +5702,7 @@ skip_hw_reset:
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_start(&ring->sched, true);
@@ -6061,7 +6057,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, NULL);
@@ -6189,7 +6185,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		drm_sched_start(&ring->sched, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index cc69005f5b46..586f4d03039d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -211,6 +211,7 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
+int amdgpu_damage_clips = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -860,6 +861,18 @@ MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (defau
 module_param_named(backlight, amdgpu_backlight, bint, 0444);
 
 /**
+ * DOC: damageclips (int)
+ * Enable or disable damage clips support. If damage clips support is disabled,
+ * we will force full frame updates, irrespective of what user space sends to
+ * us.
+ *
+ * Defaults to -1 (where it is enabled unless a PSR-SU display is detected).
+ */
+MODULE_PARM_DESC(damageclips,
+		 "Damage clips support (0 = disable, 1 = enable, -1 auto (default))");
+module_param_named(damageclips, amdgpu_damage_clips, int, 0444);
+
+/**
  * DOC: tmz (int)
  * Trusted Memory Zone (TMZ) is a method to protect data being written
  * to or read from memory.
@@ -2255,6 +2268,10 @@ retry_init:
 	if (ret)
 		goto err_pci;
 
+	ret = amdgpu_amdkfd_drm_client_create(adev);
+	if (ret)
+		goto err_pci;
+
 	/*
 	 * 1. don't init fbdev on hw without DCE
 	 * 2. don't init fbdev if there are no connectors
@@ -2472,6 +2489,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = false;
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	else if (amdgpu_acpi_is_s3_active(adev))
@@ -2486,6 +2504,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = true;
 	if (amdgpu_acpi_should_gpu_reset(adev))
 		return amdgpu_asic_reset(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 73b8cca35bab..c623e23049d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -121,6 +121,7 @@ int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
 	struct amdgpu_bo_param bp;
 	dma_addr_t dma_addr;
 	struct page *p;
+	unsigned long x;
 	int ret;
 
 	if (adev->gart.bo != NULL)
@@ -130,6 +131,10 @@ int amdgpu_gart_table_ram_alloc(struct amdgpu_device *adev)
 	if (!p)
 		return -ENOMEM;
 
+	/* assign pages to this device */
+	for (x = 0; x < (1UL << order); x++)
+		p[x].mapping = adev->mman.bdev.dev_mapping;
+
 	/* If the hardware does not support UTCL2 snooping of the CPU caches
 	 * then set_memory_wc() could be used as a workaround to mark the pages
 	 * as write combine memory.
@@ -223,6 +228,7 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
 	unsigned int order = get_order(adev->gart.table_size);
 	struct sg_table *sg = adev->gart.bo->tbo.sg;
 	struct page *p;
+	unsigned long x;
 	int ret;
 
 	ret = amdgpu_bo_reserve(adev->gart.bo, false);
@@ -234,6 +240,8 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev)
 	sg_free_table(sg);
 	kfree(sg);
 	p = virt_to_page(adev->gart.ptr);
+	for (x = 0; x < (1UL << order); x++)
+		p[x].mapping = NULL;
 	__free_pages(p, order);
 
 	adev->gart.ptr = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b9674c57c436..6ddc8e3360e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -723,8 +723,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		if (adev->gfx.gfx_off_req_count == 0 &&
 		    !adev->gfx.gfx_off_state) {
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix) {
+				if (!amdgpu_dpm_set_powergating_by_smu(adev,
+						AMD_IP_BLOCK_TYPE_GFX, true))
+					adev->gfx.gfx_off_state = true;
+			} else {
+				schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
 					      delay);
+			}
 		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4..ca5c86e5f7cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		}
 	}
 
-	if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
 err_free_shared_buf:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 45424ebf9681..5505d646f43a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -635,6 +635,7 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 			      ring->name);
 
 	ring->sched.ready = !r;
+
 	return r;
 }
 
@@ -717,3 +718,14 @@ void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring)
 	if (ring->is_sw_ring)
 		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE);
 }
+
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)
+{
+	if (!ring)
+		return false;
+
+	if (ring->no_scheduler || !drm_sched_wqueue_ready(&ring->sched))
+		return false;
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index bbb53720a018..fe1a61eb6e4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -450,5 +450,5 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 int amdgpu_ib_pool_init(struct amdgpu_device *adev);
 void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
-
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 08916538a615..8db880244324 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -221,8 +221,23 @@ static struct attribute *amdgpu_vram_mgr_attributes[] = {
 	NULL
 };
 
+static umode_t amdgpu_vram_attrs_is_visible(struct kobject *kobj,
+					    struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (attr == &dev_attr_mem_info_vram_vendor.attr &&
+	    !adev->gmc.vram_vendor)
+		return 0;
+
+	return attr->mode;
+}
+
 const struct attribute_group amdgpu_vram_mgr_attr_group = {
-	.attrs = amdgpu_vram_mgr_attributes
+	.attrs = amdgpu_vram_mgr_attributes,
+	.is_visible = amdgpu_vram_attrs_is_visible
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 6f7c031dd197..f24e34dc33d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(mmIH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(mmIH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(mmIH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index b8c47e0cf37a..c19681492efa 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_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(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d63cab294883..dcdecb18b230 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4027,8 +4027,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
 	}
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);
 
 	gfx_v10_0_check_fw_write_wait(adev);
 out:
@@ -6589,7 +6587,7 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 #ifdef __BIG_ENDIAN
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, ENDIAN_SWAP, 1);
 #endif
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 0ea0866c261f..4f3bfdc75b37 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -107,23 +107,6 @@ static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xfcffffff, 0x0000000a)
 };
 
-static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = {
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_DEBUG5, 0xffffffff, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x80009007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL2, 0x007f0000, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xffcfffff, 0x0000200a),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regUTCL1_CTRL_2, 0xffffffff, 0x0000048f)
-};
-
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
 	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
@@ -304,11 +287,6 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_11_0_1,
 						(const u32)ARRAY_SIZE(golden_settings_gc_11_0_1));
 		break;
-	case IP_VERSION(11, 5, 0):
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_11_5_0,
-						(const u32)ARRAY_SIZE(golden_settings_gc_11_5_0));
-		break;
 	default:
 		break;
 	}
@@ -3846,7 +3824,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 			    (order_base_2(prop->queue_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
 			    (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c500910746..3bc6943365a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	gfx_v9_0_cp_gfx_enable(adev, true);
 
+	/* Now only limit the quirk on the APU gfx9 series and already
+	 * confirmed that the APU gfx10/gfx11 needn't such update.
+	 */
+	if (adev->flags & AMD_IS_APU &&
+			adev->in_s3 && !adev->suspend_complete) {
+		DRM_INFO(" Will skip the CSB packet resubmit\n");
+		return 0;
+	}
 	r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
 	if (r) {
 		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 42e103d7077d..59d9215e5556 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -915,8 +915,8 @@ static int gmc_v6_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v6_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index efc16e580f1e..45a2f8e031a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1099,8 +1099,8 @@ static int gmc_v7_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v7_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ff4ae73d27ec..4422b27a3cc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1219,8 +1219,8 @@ static int gmc_v8_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v8_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f9039d64ff2d..e67a62db9e12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,13 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
 
 static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
 {
-	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
-	u32 vram_info;
-
-	if (!amdgpu_sriov_vf(adev)) {
-		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
-		adev->gmc.vram_vendor = vram_info & 0xF;
-	}
 	adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
 	adev->gmc.vram_width = 128 * 64;
 }
@@ -2340,8 +2333,8 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index aecad530b10a..2c02ae69883d 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_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(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index d9ed7332d805..ad4ad39f128f 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -418,6 +418,12 @@ static u32 ih_v6_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/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
index 8fb05eae340a..b8da0fc29378 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -418,6 +418,13 @@ static u32 ih_v6_1_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/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf8..88ea58d5c4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
-	.set = jpeg_v4_0_set_interrupt_state,
 	.process = jpeg_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8..78b74daf4eeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
 			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
 			jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 	}
-	amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
 
 	return 0;
 }
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
-	.set = jpeg_v4_0_5_set_interrupt_state,
 	.process = jpeg_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index e64b33115848..de93614726c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -442,6 +442,12 @@ static u32 navi10_ih_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/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index e90f33780803..b4723d68eab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	u32 inst_mask;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset =
+			SOC15_REG_OFFSET(
+				NBIO, 0,
+				regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+			<< 2;
 	WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
 		0xff & ~(adev->gfx.xcc_mask));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 9a24f17a5750..cada9f300a7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(IH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(IH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2ba..c64c01e2944a 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1298,10 +1298,32 @@ static int soc15_common_suspend(void *handle)
 	return soc15_common_hw_fini(adev);
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc15_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+		soc15_asic_reset(adev);
+	}
 	return soc15_common_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 48c6efcdeac9..4d7188912edf 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 917707bba7f3..450b6e831509 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_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(mmIH_RB_CNTL, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 169ed400ee7b..8ab01ae919d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -2018,22 +2018,6 @@ static int vcn_v4_0_set_powergating_state(void *handle, enum amd_powergating_sta
 }
 
 /**
- * vcn_v4_0_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-      unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
-/**
  * vcn_v4_0_set_ras_interrupt_state - set VCN block RAS interrupt state
  *
  * @adev: amdgpu_device pointer
@@ -2097,7 +2081,6 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_irq_funcs = {
-	.set = vcn_v4_0_set_interrupt_state,
 	.process = vcn_v4_0_process_interrupt,
 };
 
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 2eda30e78f61..49e4c3c09aca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -269,8 +269,6 @@ static int vcn_v4_0_5_hw_fini(void *handle)
 				vcn_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 			}
 		}
-
-		amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0);
 	}
 
 	return 0;
@@ -1669,22 +1667,6 @@ static int vcn_v4_0_5_set_powergating_state(void *handle, enum amd_powergating_s
 }
 
 /**
- * vcn_v4_0_5_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_5_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-		unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
-/**
  * vcn_v4_0_5_process_interrupt - process VCN block interrupt
  *
  * @adev: amdgpu_device pointer
@@ -1726,7 +1708,6 @@ static int vcn_v4_0_5_process_interrupt(struct amdgpu_device *adev, struct amdgp
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_5_irq_funcs = {
-	.set = vcn_v4_0_5_set_interrupt_state,
 	.process = vcn_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index d364c6dd152c..bf68e18e3824 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	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/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index ddfc6941f9d5..db66e6cccaf2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	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/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index df75863393fc..d1caaf0e6a7c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -674,7 +674,7 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_nv1x_hex[] = {
@@ -1091,7 +1091,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 	0xb9eef807, 0x876dff6d,
 	0x0000ffff, 0x87fe7e7e,
 	0x87ea6a6a, 0xb9faf802,
-	0xbe80226c, 0xbf810000,
+	0xbe80226c, 0xbf9b0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -1574,7 +1574,7 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_aldebaran_hex[] = {
@@ -2065,7 +2065,7 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_gfx10_hex[] = {
@@ -2500,7 +2500,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x876dff6d, 0x0000ffff,
 	0x87fe7e7e, 0x87ea6a6a,
 	0xb9faf802, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0xbf9b0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 };
@@ -2944,7 +2944,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = {
 	0xb8eef802, 0xbf0d866e,
 	0xbfa20002, 0xb97af802,
 	0xbe80486c, 0xb97af802,
-	0xbe804a6c, 0xbfb00000,
+	0xbe804a6c, 0xbfb10000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -3436,5 +3436,5 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index e0140df0b0ec..71b3dc0c7363 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -1104,7 +1104,7 @@ L_RETURN_WITHOUT_PRIV:
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM:
-	s_endpgm
+	s_endpgm_saved
 end
 
 function write_hwreg_to_mem(s, s_rsrc, s_mem_offset)
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index e506411ad28a..bb26338204f4 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -921,7 +921,7 @@ L_RESTORE:
 /*			the END						  */
 /**************************************************************************/
 L_END_PGM:
-    s_endpgm
+    s_endpgm_saved
 
 end
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index ce4c52ec34d8..80e90fdef291 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1442,7 +1442,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
 
 		/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
-		amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		if (err)
+			goto sync_memory_failed;
 	}
 
 	mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index f856901055d3..bdc01ca9609a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -574,7 +574,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
 		 prange->last);
 
-	addr = prange->start << PAGE_SHIFT;
+	addr = migrate->start;
 
 	src = (uint64_t *)(scratch + npages);
 	dst = scratch;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 8b7fed913526..22cbfa1bdadd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -170,6 +170,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 15277f1d5cf0..826bc4f6c8a7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -55,8 +55,8 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 	m = get_mqd(mqd);
 
 	if (has_wa_flag) {
-		uint32_t wa_mask = minfo->update_flag == UPDATE_FLAG_DBG_WA_ENABLE ?
-						0xffff : 0xffffffff;
+		uint32_t wa_mask =
+			(minfo->update_flag & UPDATE_FLAG_DBG_WA_ENABLE) ? 0xffff : 0xffffffff;
 
 		m->compute_static_thread_mgmt_se0 = wa_mask;
 		m->compute_static_thread_mgmt_se1 = wa_mask;
@@ -224,6 +224,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 42d881809dc7..697b6d530d12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -303,6 +303,15 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 		update_cu_mask(mm, mqd, minfo, 0);
 	set_priority(m, q);
 
+	if (minfo && KFD_GC_VERSION(mm->dev) >= IP_VERSION(9, 4, 2)) {
+		if (minfo->update_flag & UPDATE_FLAG_IS_GWS)
+			m->compute_resource_limits |=
+				COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+		else
+			m->compute_resource_limits &=
+				~COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+	}
+
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 17fbedbf3651..80320b8603fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -532,6 +532,7 @@ struct queue_properties {
 enum mqd_update_flag {
 	UPDATE_FLAG_DBG_WA_ENABLE = 1,
 	UPDATE_FLAG_DBG_WA_DISABLE = 2,
+	UPDATE_FLAG_IS_GWS = 4, /* quirk for gfx9 IP */
 };
 
 struct mqd_update_info {
@@ -1488,10 +1489,15 @@ void kfd_dec_compute_active(struct kfd_node *dev);
 
 /* Cgroup Support */
 /* Check with device cgroup if @kfd device is accessible */
-static inline int kfd_devcgroup_check_permission(struct kfd_node *kfd)
+static inline int kfd_devcgroup_check_permission(struct kfd_node *node)
 {
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
-	struct drm_device *ddev = adev_to_drm(kfd->adev);
+	struct drm_device *ddev;
+
+	if (node->xcp)
+		ddev = node->xcp->ddev;
+	else
+		ddev = adev_to_drm(node->adev);
 
 	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 43eff221eae5..4858112f9a53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -95,6 +95,7 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
 int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 			void *gws)
 {
+	struct mqd_update_info minfo = {0};
 	struct kfd_node *dev = NULL;
 	struct process_queue_node *pqn;
 	struct kfd_process_device *pdd;
@@ -146,9 +147,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 	}
 
 	pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
+	minfo.update_flag = gws ? UPDATE_FLAG_IS_GWS : 0;
 
 	return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
-							pqn->q, NULL);
+							pqn->q, &minfo);
 }
 
 void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e5f7c92eebcb..6ed2ec381aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1638,12 +1638,10 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 		else
 			mode = UNKNOWN_MEMORY_PARTITION_MODE;
 
-		if (pcache->cache_level == 2)
-			pcache->cache_size = pcache_info[cache_type].cache_size * num_xcc;
-		else if (mode)
-			pcache->cache_size = pcache_info[cache_type].cache_size / mode;
-		else
-			pcache->cache_size = pcache_info[cache_type].cache_size;
+		pcache->cache_size = pcache_info[cache_type].cache_size;
+		/* Partition mode only affects L3 cache size */
+		if (mode && pcache->cache_level == 3)
+			pcache->cache_size /= mode;
 
 		if (pcache_info[cache_type].flags & CRAT_CACHE_FLAGS_DATA_CACHE)
 			pcache->cache_type |= HSA_CACHE_TYPE_DATA;
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 d4f525b66a09..5853cf022917 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -272,6 +272,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 {
 	u32 v_blank_start, v_blank_end, h_position, v_position;
 	struct amdgpu_crtc *acrtc = NULL;
+	struct dc *dc = adev->dm.dc;
 
 	if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc))
 		return -EINVAL;
@@ -284,6 +285,9 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 		return 0;
 	}
 
+	if (dc && dc->caps.ips_support && dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dc, false);
+
 	/*
 	 * TODO rework base driver to use values directly.
 	 * for now parse it back into reg-format
@@ -1715,7 +1719,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	init_data.nbio_reg_offsets = adev->reg_offset[NBIO_HWIP][0];
 	init_data.clk_reg_offsets = adev->reg_offset[CLK_HWIP][0];
 
-	init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
+	if (amdgpu_dc_debug_mask & DC_DISABLE_IPS)
+		init_data.flags.disable_ips = DMUB_IPS_DISABLE_ALL;
+
+	init_data.flags.disable_ips_in_vpb = 1;
 
 	/* Enable DWB for tested platforms only */
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
@@ -1836,21 +1843,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			DRM_ERROR("amdgpu: fail to register dmub aux callback");
 			goto error;
 		}
-		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) {
-			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
-			goto error;
-		}
-		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) {
-			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
-			goto error;
-		}
-	}
-
-	/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
-	 * It is expected that DMUB will resend any pending notifications at this point, for
-	 * example HPD from DPIA.
-	 */
-	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
+		 * It is expected that DMUB will resend any pending notifications at this point. Note
+		 * that hpd and hpd_irq handler registration are deferred to register_hpd_handlers() to
+		 * align legacy interface initialization sequence. Connection status will be proactivly
+		 * detected once in the amdgpu_dm_initialize_drm_device.
+		 */
 		dc_enable_dmub_outbox(adev->dm.dc);
 
 		/* DPIA trace goes to dmesg logs only if outbox is enabled */
@@ -1949,7 +1947,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 				      &adev->dm.dmub_bo_gpu_addr,
 				      &adev->dm.dmub_bo_cpu_addr);
 
-	if (adev->dm.hpd_rx_offload_wq) {
+	if (adev->dm.hpd_rx_offload_wq && adev->dm.dc) {
 		for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
 			if (adev->dm.hpd_rx_offload_wq[i].wq) {
 				destroy_workqueue(adev->dm.hpd_rx_offload_wq[i].wq);
@@ -2280,6 +2278,7 @@ static int dm_sw_fini(void *handle)
 
 	if (adev->dm.dmub_srv) {
 		dmub_srv_destroy(adev->dm.dmub_srv);
+		kfree(adev->dm.dmub_srv);
 		adev->dm.dmub_srv = NULL;
 	}
 
@@ -3529,6 +3528,14 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 	int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT;
 	int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT;
 
+	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true))
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true))
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+	}
+
 	list_for_each_entry(connector,
 			&dev->mode_config.connector_list, head)	{
 
@@ -3557,10 +3564,6 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 					handle_hpd_rx_irq,
 					(void *) aconnector);
 		}
-
-		if (adev->dm.hpd_rx_offload_wq)
-			adev->dm.hpd_rx_offload_wq[connector->index].aconnector =
-				aconnector;
 	}
 }
 
@@ -4554,6 +4557,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 
+		if (dm->hpd_rx_offload_wq)
+			dm->hpd_rx_offload_wq[aconnector->base.index].aconnector =
+				aconnector;
+
 		if (!dc_link_detect_connection_type(link, &new_connection_type))
 			DRM_ERROR("KMS: Failed to detect connector\n");
 
@@ -5212,6 +5219,7 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 				struct drm_plane_state *new_plane_state,
 				struct drm_crtc_state *crtc_state,
 				struct dc_flip_addrs *flip_addrs,
+				bool is_psr_su,
 				bool *dirty_regions_changed)
 {
 	struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state);
@@ -5236,6 +5244,10 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 	num_clips = drm_plane_get_damage_clips_count(new_plane_state);
 	clips = drm_plane_get_damage_clips(new_plane_state);
 
+	if (num_clips && (!amdgpu_damage_clips || (amdgpu_damage_clips < 0 &&
+						   is_psr_su)))
+		goto ffu;
+
 	if (!dm_crtc_state->mpo_requested) {
 		if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS)
 			goto ffu;
@@ -6187,7 +6199,9 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
 			drm_mode_copy(&saved_mode, &mode);
+			saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
 			drm_mode_copy(&mode, freesync_mode);
+			mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
 		} else {
 			decide_crtc_timing_for_drm_display_mode(
 					&mode, preferred_mode, scale);
@@ -6520,10 +6534,15 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector)
 static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
 	struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
 	/*
 	 * Note: drm_get_edid gets edid in the following order:
@@ -6531,7 +6550,7 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 	 * 2) firmware EDID if set via edid_firmware module parameter
 	 * 3) regular DDC read.
 	 */
-	edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+	edid = drm_get_edid(connector, ddc);
 	if (!edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
 		return;
@@ -6572,12 +6591,18 @@ static int get_modes(struct drm_connector *connector)
 static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 {
 	struct drm_connector *connector = &aconnector->base;
-	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(&aconnector->base);
+	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink_init_data init_params = {
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_VIRTUAL
 	};
 	struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
 	/*
 	 * Note: drm_get_edid gets edid in the following order:
@@ -6585,7 +6610,7 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 	 * 2) firmware EDID if set via edid_firmware module parameter
 	 * 3) regular DDC read.
 	 */
-	edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+	edid = drm_get_edid(connector, ddc);
 	if (!edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
 		return;
@@ -8291,6 +8316,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			fill_dc_dirty_rects(plane, old_plane_state,
 					    new_plane_state, new_crtc_state,
 					    &bundle->flip_addrs[planes_count],
+					    acrtc_state->stream->link->psr_settings.psr_version ==
+					    DC_PSR_VERSION_SU_1,
 					    &dirty_rects_changed);
 
 			/*
@@ -8976,16 +9003,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	trace_amdgpu_dm_atomic_commit_tail_begin(state);
 
-	if (dm->dc->caps.ips_support) {
-		for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
-			if (new_con_state->crtc &&
-				new_con_state->crtc->state->active &&
-				drm_atomic_crtc_needs_modeset(new_con_state->crtc->state)) {
-				dc_dmub_srv_apply_idle_power_optimizations(dm->dc, false);
-				break;
-			}
-		}
-	}
+	if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dm->dc, false);
 
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
 	drm_dp_mst_atomic_wait_for_dependencies(state);
@@ -9188,6 +9207,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		 * To fix this, DC should permit updating only stream properties.
 		 */
 		dummy_updates = kzalloc(sizeof(struct dc_surface_update) * MAX_SURFACES, GFP_ATOMIC);
+		if (!dummy_updates) {
+			DRM_ERROR("Failed to allocate memory for dummy_updates.\n");
+			continue;
+		}
 		for (j = 0; j < status->plane_count; j++)
 			dummy_updates[j].surface = status->plane_states[0];
 
@@ -10728,11 +10751,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		}
 
-		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
-		if (ret) {
-			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
-			ret = -EINVAL;
-			goto fail;
+		if (dc_resource_is_dsc_encoding_supported(dc)) {
+			ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+			if (ret) {
+				DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+				ret = -EINVAL;
+				goto fail;
+			}
 		}
 
 		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 58b880acb087..3390f0d8420a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -711,7 +711,7 @@ static inline int dm_irq_state(struct amdgpu_device *adev,
 {
 	bool st;
 	enum dc_irq_source irq_source;
-
+	struct dc *dc = adev->dm.dc;
 	struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc_id];
 
 	if (!acrtc) {
@@ -729,6 +729,9 @@ static inline int dm_irq_state(struct amdgpu_device *adev,
 
 	st = (state == AMDGPU_IRQ_STATE_ENABLE);
 
+	if (dc && dc->caps.ips_support && dc->idle_optimizations_allowed)
+		dc_allow_idle_optimizations(dc, false);
+
 	dc_interrupt_set(adev->dm.dc, irq_source, st);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
index f2dfa96f9ef5..39530b2ea495 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
@@ -94,7 +94,7 @@ static void calculate_bandwidth(
 	const uint32_t s_high = 7;
 	const uint32_t dmif_chunk_buff_margin = 1;
 
-	uint32_t max_chunks_fbc_mode;
+	uint32_t max_chunks_fbc_mode = 0;
 	int32_t num_cursor_lines;
 
 	int32_t i, j, k;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 960c4b4f6ddf..05f392501c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1850,19 +1850,21 @@ static enum bp_result get_firmware_info_v3_2(
 		/* Vega12 */
 		smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
 							DATA_TABLES(smu_info));
-		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
 		if (!smu_info_v3_2)
 			return BP_RESULT_BADBIOSTABLE;
 
+		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
+
 		info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
 	} else if (revision.minor == 3) {
 		/* Vega20 */
 		smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
 							DATA_TABLES(smu_info));
-		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
 		if (!smu_info_v3_3)
 			return BP_RESULT_BADBIOSTABLE;
 
+		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
+
 		info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
 	}
 
@@ -2422,10 +2424,11 @@ static enum bp_result get_integrated_info_v11(
 	info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11,
 					DATA_TABLES(integratedsysteminfo));
 
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
 	if (info_v11 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v11->gpucapinfo);
 	/*
@@ -2637,11 +2640,12 @@ static enum bp_result get_integrated_info_v2_1(
 
 	info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1,
 					DATA_TABLES(integratedsysteminfo));
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
 
 	if (info_v2_1 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v2_1->gpucapinfo);
 	/*
@@ -2799,11 +2803,11 @@ static enum bp_result get_integrated_info_v2_2(
 	info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2,
 					DATA_TABLES(integratedsysteminfo));
 
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
-
 	if (info_v2_2 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v2_2->gpucapinfo);
 	/*
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index a5489fe6875f..aa9fd1dc550a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -546,6 +546,8 @@ static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_ta
 	int i;
 
 	for (i = 0; i < VG_NUM_SOC_VOLTAGE_LEVELS; i++) {
+		if (i >= VG_NUM_DCFCLK_DPM_LEVELS)
+			break;
 		if (clock_table->SocVoltage[i] == voltage)
 			return clock_table->DcfClocks[i];
 	}
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 9c660d1facc7..e64890259235 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
@@ -437,32 +437,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -474,32 +474,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -655,10 +655,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
 	uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
 	uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
+	uint32_t num_memps, num_fclk, num_dcfclk;
 	int i;
 
 	/* Determine min/max p-state values. */
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+	num_memps = (clock_table->NumMemPstatesEnabled > NUM_MEM_PSTATE_LEVELS) ? NUM_MEM_PSTATE_LEVELS :
+		clock_table->NumMemPstatesEnabled;
+	for (i = 0; i < num_memps; i++) {
 		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
 
 		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
@@ -670,7 +673,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	min_dram_speed_mts = max_dram_speed_mts;
 	min_pstate = max_pstate;
 
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+	for (i = 0; i < num_memps; i++) {
 		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
 
 		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
@@ -699,9 +702,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
 	ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
 
-	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+	num_fclk = (clock_table->NumFclkLevelsEnabled > NUM_FCLK_DPM_LEVELS) ? NUM_FCLK_DPM_LEVELS :
+		clock_table->NumFclkLevelsEnabled;
+	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
 
-	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+	num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+		clock_table->NumDcfClkLevelsEnabled;
+	for (i = 0; i < num_dcfclk; i++) {
 		int j;
 
 		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aa7c02ba948e..2c424e435962 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
 		 * programming has completed (we turn on phantom OTG in order
 		 * to complete the plane disable for phantom pipes).
 		 */
-		dc->hwss.apply_ctx_to_hw(dc, context);
+
+		if (dc->hwss.disable_phantom_streams)
+			dc->hwss.disable_phantom_streams(dc, context);
 	}
 
 	if (update_type != UPDATE_TYPE_FAST)
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 88c6436b28b6..180ac47868c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
 		dc_stream_release(state->phantom_streams[i]);
 		state->phantom_streams[i] = NULL;
 	}
+	state->phantom_stream_count = 0;
 
 	for (i = 0; i < state->phantom_plane_count; i++) {
 		dc_plane_state_release(state->phantom_planes[i]);
 		state->phantom_planes[i] = NULL;
 	}
+	state->phantom_plane_count = 0;
+
 	state->stream_mask = 0;
 	memset(&state->res_ctx, 0, sizeof(state->res_ctx));
 	memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 5d7aa882416b..c9317ea0258e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -434,6 +434,7 @@ struct dc_config {
 	bool EnableMinDispClkODM;
 	bool enable_auto_dpm_test_logs;
 	unsigned int disable_ips;
+	unsigned int disable_ips_in_vpb;
 };
 
 enum visual_confirm {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 2b79a0e5638e..363d522603a2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -125,7 +125,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
 		unsigned int count,
 		union dmub_rb_cmd *cmd_list)
 {
-	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dc_context *dc_ctx;
 	struct dmub_srv *dmub;
 	enum dmub_status status;
 	int i;
@@ -133,6 +133,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
 	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
 		return false;
 
+	dc_ctx = dc_dmub_srv->ctx;
 	dmub = dc_dmub_srv->dmub;
 
 	for (i = 0 ; i < count; i++) {
@@ -1161,7 +1162,7 @@ void dc_dmub_srv_subvp_save_surf_addr(const struct dc_dmub_srv *dc_dmub_srv, con
 
 bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
 {
-	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dc_context *dc_ctx;
 	enum dmub_status status;
 
 	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
@@ -1170,6 +1171,8 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
 	if (dc_dmub_srv->ctx->dc->debug.dmcub_emulation)
 		return true;
 
+	dc_ctx = dc_dmub_srv->ctx;
+
 	if (wait) {
 		if (dc_dmub_srv->ctx->dc->debug.disable_timeout) {
 			do {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index b08ccb8c68bc..9900dda2eef5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1034,6 +1034,7 @@ enum replay_FW_Message_type {
 	Replay_Msg_Not_Support = -1,
 	Replay_Set_Timing_Sync_Supported,
 	Replay_Set_Residency_Frameupdate_Timer,
+	Replay_Set_Pseudo_VTotal,
 };
 
 union replay_error_status {
@@ -1089,6 +1090,10 @@ struct replay_settings {
 	uint16_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 */
+	uint16_t abm_with_ips_on_full_screen_video_pseudo_vtotal;
+	/* Replay last pseudo vtotal set to DMUB */
+	uint16_t last_pseudo_vtotal;
 };
 
 /* To split out "global" and "per-panel" config settings.
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index e8570060d007..5bca67407c5b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -290,4 +290,5 @@ void dce_panel_cntl_construct(
 	dce_panel_cntl->base.funcs = &dce_link_panel_cntl_funcs;
 	dce_panel_cntl->base.ctx = init_data->ctx;
 	dce_panel_cntl->base.inst = init_data->inst;
+	dce_panel_cntl->base.pwrseq_inst = 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
index e43f77c11c00..5f97a868ada3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
@@ -56,16 +56,13 @@ static void dpp3_enable_cm_block(
 
 static enum dc_lut_mode dpp30_get_gamcor_current(struct dpp *dpp_base)
 {
-	enum dc_lut_mode mode;
+	enum dc_lut_mode mode = LUT_BYPASS;
 	uint32_t state_mode;
 	uint32_t lut_mode;
 	struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base);
 
 	REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_MODE_CURRENT, &state_mode);
 
-	if (state_mode == 0)
-		mode = LUT_BYPASS;
-
 	if (state_mode == 2) {//Programmable RAM LUT
 		REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_SELECT_CURRENT, &lut_mode);
 		if (lut_mode == 0)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
index ad0df1a72a90..9e96a3ace207 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
@@ -215,4 +215,5 @@ void dcn301_panel_cntl_construct(
 	dcn301_panel_cntl->base.funcs = &dcn301_link_panel_cntl_funcs;
 	dcn301_panel_cntl->base.ctx = init_data->ctx;
 	dcn301_panel_cntl->base.inst = init_data->inst;
+	dcn301_panel_cntl->base.pwrseq_inst = 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
index 03248422d6ff..281be20b1a10 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
@@ -154,8 +154,24 @@ void dcn31_panel_cntl_construct(
 	struct dcn31_panel_cntl *dcn31_panel_cntl,
 	const struct panel_cntl_init_data *init_data)
 {
+	uint8_t pwrseq_inst = 0xF;
+
 	dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs;
 	dcn31_panel_cntl->base.ctx = init_data->ctx;
 	dcn31_panel_cntl->base.inst = init_data->inst;
-	dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst;
+
+	switch (init_data->eng_id) {
+	case ENGINE_ID_DIGA:
+		pwrseq_inst = 0;
+		break;
+	case ENGINE_ID_DIGB:
+		pwrseq_inst = 1;
+		break;
+	default:
+		DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", init_data->eng_id);
+		ASSERT(false);
+		break;
+	}
+
+	dcn31_panel_cntl->base.pwrseq_inst = pwrseq_inst;
 }
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 501388014855..d761b0df2878 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
@@ -203,12 +203,12 @@ void dcn32_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;
 
 	enc10->base.features = *enc_features;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.transmitter = init_data->transmitter;
 
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 da94e5309fba..81e349d5835b 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
@@ -184,8 +184,6 @@ 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;
 
@@ -240,6 +238,8 @@ 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/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f..59ade76ffb18 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
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 9f37f717a1f8..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
@@ -1112,7 +1112,7 @@ struct pipe_slice_table {
 		struct pipe_ctx *pri_pipe;
 		struct dc_plane_state *plane;
 		int slice_count;
-	} mpc_combines[MAX_SURFACES];
+	} mpc_combines[MAX_PLANES];
 	int mpc_combine_count;
 };
 
@@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
 	return updated;
 }
 
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
 		struct dc_state *context, struct vba_vars_st *v, int *split,
 		bool *merge)
 {
@@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
 {
 	int i;
 	unsigned int new_vlevel;
+	unsigned int cur_policy[MAX_PIPES];
 
-	for (i = 0; i < pipe_cnt; i++)
+	for (i = 0; i < pipe_cnt; i++) {
+		cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
 		pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+	}
 
 	new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
 		memset(merge, 0, MAX_PIPES * sizeof(bool));
 		*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
 		context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+	} else {
+		for (i = 0; i < pipe_cnt; i++)
+			pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
 	}
 }
 
@@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 		}
 	}
 
-	if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+	if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
 		try_odm_power_optimization_and_revalidate(
 				dc, context, pipes, split, merge, vlevel, *pipe_cnt);
 
@@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		int i;
 
 		pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
-		dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+		if (!dc->config.enable_windowed_mpo_odm)
+			dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
 
 		/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
 		 * we have to re-calculate the DET allocation and run through DML once more to
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 475c4ec43c01..7ea2bd5374d5 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
@@ -164,8 +164,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 14.0,
-	.sr_enter_plus_exit_time_us = 16.0,
+	.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,
 	.fclk_change_latency_us = 24.0,
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 64d01a9cd68c..1ba6933d2b36 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
@@ -341,9 +341,6 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	if (dml2->config.bbox_overrides.clks_table.num_states)
-			p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
-
 	/* Override from passed values, if available */
 	for (i = 0; i < p->in_states->num_states; i++) {
 		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
@@ -400,7 +397,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 	/* Copy clocks tables entries, if available */
 	if (dml2->config.bbox_overrides.clks_table.num_states) {
-
+		p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels; i++) {
 			p->in_states->state_array[i].dcfclk_mhz = dml2->config.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz;
 		}
@@ -439,6 +436,14 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 
 	dml2_policy_build_synthetic_soc_states(s, p);
+	if (dml2->v20.dml_core_ctx.project == dml_project_dcn35 ||
+		dml2->v20.dml_core_ctx.project == dml_project_dcn351) {
+		// Override last out_state with data from last in_state
+		// This will ensure that out_state contains max fclk
+		memcpy(&p->out_states->state_array[p->out_states->num_states - 1],
+				&p->in_states->state_array[p->in_states->num_states - 1],
+				sizeof(struct soc_state_bounding_box_st));
+	}
 }
 
 void dml2_translate_ip_params(const struct dc *in, struct ip_params_st *out)
@@ -793,35 +798,28 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-/*TODO no support for mpc combine, need rework - should calculate scaling params based on plane+stream*/
-static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, const struct dc_state *context)
+static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context)
 {
 	int i;
-	struct scaler_data data = { 0 };
+	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
+
+	memset(temp_pipe, 0, sizeof(struct pipe_ctx));
 
 	for (i = 0; i < MAX_PIPES; i++)	{
 		const struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (pipe->plane_state == in && !pipe->prev_odm_pipe) {
-			const struct pipe_ctx *next_pipe = pipe->next_odm_pipe;
-
-			data = context->res_ctx.pipe_ctx[i].plane_res.scl_data;
-			while (next_pipe) {
-				data.h_active += next_pipe->plane_res.scl_data.h_active;
-				data.recout.width += next_pipe->plane_res.scl_data.recout.width;
-				if (in->rotation == ROTATION_ANGLE_0 || in->rotation == ROTATION_ANGLE_180) {
-					data.viewport.width += next_pipe->plane_res.scl_data.viewport.width;
-				} else {
-					data.viewport.height += next_pipe->plane_res.scl_data.viewport.height;
-				}
-				next_pipe = next_pipe->next_odm_pipe;
-			}
+			temp_pipe->stream = pipe->stream;
+			temp_pipe->plane_state = pipe->plane_state;
+			temp_pipe->plane_res.scl_data.taps = pipe->plane_res.scl_data.taps;
+
+			resource_build_scaling_params(temp_pipe);
 			break;
 		}
 	}
 
 	ASSERT(i < MAX_PIPES);
-	return data;
+	return temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in)
@@ -866,7 +864,7 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned
 	out->ScalerEnabled[location] = false;
 }
 
-static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, const struct dc_state *context)
+static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, struct dc_state *context)
 {
 	const struct scaler_data scaler_data = get_scaler_data_for_plane(in, context);
 
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 5660f15da291..01493c49bd7a 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
@@ -1183,9 +1183,9 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
 		if (dccg) {
-			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 			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);
 		}
 	} else if (dccg && dccg->funcs->disable_symclk_se) {
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
 	return DC_OK;
 }
 
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
 			continue;
 
-		status = apply_single_controller_ctx_to_hw(
+		status = dce110_apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
 				dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae..ed3cc3648e8e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context);
 
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
 
 void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
 
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 e931342fcf4c..931ac8ed7069 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
@@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
@@ -2790,18 +2790,17 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	}
 
 	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
-
-		phyd32clk = get_phyd32clk_src(link);
-		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
-
 		dto_params.otg_inst = tg->inst;
 		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
 		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
 		dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
+		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
+
+		phyd32clk = get_phyd32clk_src(link);
+		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
 	} else {
 		if (dccg->funcs->enable_symclk_se)
 			dccg->funcs->enable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abf..d950b3e54ec2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
 void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
 void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5..7252f5f781f0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
 void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
 {
 	struct abm *abm = pipe_ctx->stream_res.abm;
-	uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
 	struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+	uint32_t otg_inst;
+
+	if (!abm || !tg || !panel_cntl)
+		return;
+
+	otg_inst = tg->inst;
 
 	if (dmcu) {
 		dce110_set_pipe(pipe_ctx);
 		return;
 	}
 
-	if (abm && panel_cntl) {
-		if (abm->funcs && abm->funcs->set_pipe_ex) {
-			abm->funcs->set_pipe_ex(abm,
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
 					otg_inst,
 					SET_ABM_PIPE_NORMAL,
 					panel_cntl->inst,
 					panel_cntl->pwrseq_inst);
-		} else {
-				dmub_abm_set_pipe(abm, otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-		}
+	} else {
+		dmub_abm_set_pipe(abm, otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 }
 
@@ -237,34 +241,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
 {
 	struct dc_context *dc = pipe_ctx->stream->ctx;
 	struct abm *abm = pipe_ctx->stream_res.abm;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+	uint32_t otg_inst;
+
+	if (!abm || !tg || !panel_cntl)
+		return false;
+
+	otg_inst = tg->inst;
 
 	if (dc->dc->res_pool->dmcu) {
 		dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
 		return true;
 	}
 
-	if (abm != NULL) {
-		uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
-		if (abm && panel_cntl) {
-			if (abm->funcs && abm->funcs->set_pipe_ex) {
-				abm->funcs->set_pipe_ex(abm,
-						otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-			} else {
-					dmub_abm_set_pipe(abm,
-							otg_inst,
-							SET_ABM_PIPE_NORMAL,
-							panel_cntl->inst,
-							panel_cntl->pwrseq_inst);
-			}
-		}
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
+					otg_inst,
+					SET_ABM_PIPE_NORMAL,
+					panel_cntl->inst,
+					panel_cntl->pwrseq_inst);
+	} else {
+		dmub_abm_set_pipe(abm,
+				  otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 
-	if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+	if (abm->funcs && abm->funcs->set_backlight_level_pwm)
 		abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
 			frame_ramp, 0, panel_cntl->inst);
 	else
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 6c9299c7683d..aa36d7a56ca8 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
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
 	}
 }
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+		struct pipe_ctx *pipe_ctx_old =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx_old->stream)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+			continue;
+
+		if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+				(pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+			struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+			if (hws->funcs.reset_back_end_for_pipe)
+				hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+			if (old_clk)
+				old_clk->funcs->cs_power_down(old_clk);
+		}
+	}
+}
+
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 {
 	unsigned int i;
+	enum dc_status status = DC_OK;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 		}
 	}
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
-			// If old context or new context has phantom pipes, apply
-			// the phantom timings now. We can't change the phantom
-			// pipe configuration safely without driver acquiring
-			// the DMCUB lock first.
-			dc->hwss.apply_ctx_to_hw(dc, context);
-			break;
+		struct pipe_ctx *pipe_ctx_old =
+					&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx->stream == pipe_ctx_old->stream &&
+			pipe_ctx->stream->link->link_state_valid) {
+			continue;
 		}
+
+		if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+			continue;
+
+		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+			continue;
+
+		if (hws->funcs.apply_single_controller_ctx_to_hw)
+			status = hws->funcs.apply_single_controller_ctx_to_hw(
+					pipe_ctx,
+					context,
+					dc);
+
+		ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+		if (hws->funcs.resync_fifo_dccg_dio)
+			hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
 	}
 }
 
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 cecf7f0f5671..069e20bc87c0 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
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
 
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
 void dcn32_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
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 427cfc8c24a4..e8ac94a005b8 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
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.get_dcc_en_bits = dcn10_get_dcc_en_bits,
 	.commit_subvp_config = dcn32_commit_subvp_config,
 	.enable_phantom_streams = dcn32_enable_phantom_streams,
+	.disable_phantom_streams = dcn32_disable_phantom_streams,
 	.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
 	.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
 	.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+	.apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+	.reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
 };
 
 void dcn32_hw_sequencer_init_functions(struct dc *dc)
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 9c806385ecbd..8b6c49622f3b 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
@@ -680,7 +680,7 @@ void dcn35_power_down_on_boot(struct dc *dc)
 bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
 	struct dc_link *edp_links[MAX_NUM_EDP];
-	int edp_num;
+	int i, edp_num;
 	if (dc->debug.dmcub_emulation)
 		return true;
 
@@ -688,6 +688,13 @@ bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable)
 		dc_get_edp_links(dc, edp_links, &edp_num);
 		if (edp_num == 0 || edp_num > 1)
 			return false;
+
+		for (i = 0; i < dc->current_state->stream_count; ++i) {
+			struct dc_stream_state *stream = dc->current_state->streams[i];
+
+			if (!stream->dpms_off && !dc_is_embedded_signal(stream->signal))
+				return false;
+		}
 	}
 
 	// TODO: review other cases when idle optimization is allowed
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a54399383318..64ca7c66509b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
 			struct dc_cursor_attributes *cursor_attr);
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+	void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
 	void (*subvp_pipe_control_lock)(struct dc *dc,
 			struct dc_state *context,
 			bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54..b3c62a82cb1c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
 	void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
 	void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
 			struct dc_state *context);
+	enum dc_status (*apply_single_controller_ctx_to_hw)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
 	bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
 #endif
+	void (*reset_back_end_for_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
 };
 
 struct dce_hwseq {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index f74ae0d41d3c..3a6bf77a6873 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -469,6 +469,8 @@ struct resource_context {
 	unsigned int hpo_dp_link_enc_to_link_idx[MAX_HPO_DP2_LINK_ENCODERS];
 	int hpo_dp_link_enc_ref_cnts[MAX_HPO_DP2_LINK_ENCODERS];
 	bool is_mpc_3dlut_acquired[MAX_PIPES];
+	/* solely used for build scalar data in dml2 */
+	struct pipe_ctx temp_pipe;
 };
 
 struct dce_bw_output {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
index 5dcbaa2db964..e97d964a1791 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
@@ -57,7 +57,7 @@ struct panel_cntl_funcs {
 struct panel_cntl_init_data {
 	struct dc_context *ctx;
 	uint32_t inst;
-	uint32_t pwrseq_inst;
+	uint32_t eng_id;
 };
 
 struct panel_cntl {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index c958ef37b78a..77a60aa9f27b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
 int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
 
 /*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
  */
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
 
 /*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
  */
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
 
 /* Get the ODM slice index counting from 0 from left most slice */
 int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
index 37d3027c32dc..cf22b8f28ba6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
@@ -370,30 +370,6 @@ static enum transmitter translate_encoder_to_transmitter(
 	}
 }
 
-static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link)
-{
-	uint8_t pwrseq_inst = 0xF;
-	struct dc_context *dc_ctx = link->dc->ctx;
-
-	DC_LOGGER_INIT(dc_ctx->logger);
-
-	switch (link->eng_id) {
-	case ENGINE_ID_DIGA:
-		pwrseq_inst = 0;
-		break;
-	case ENGINE_ID_DIGB:
-		pwrseq_inst = 1;
-		break;
-	default:
-		DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id);
-		ASSERT(false);
-		break;
-	}
-
-	return pwrseq_inst;
-}
-
-
 static void link_destruct(struct dc_link *link)
 {
 	int i;
@@ -657,7 +633,7 @@ static bool construct_phy(struct dc_link *link,
 			link->link_id.id == CONNECTOR_ID_LVDS)) {
 		panel_cntl_init_data.ctx = dc_ctx;
 		panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count;
-		panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link);
+		panel_cntl_init_data.eng_id = link->eng_id;
 		link->panel_cntl =
 			link->dc->res_pool->funcs->panel_cntl_create(
 								&panel_cntl_init_data);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index 8fe66c367850..5b0bc7f6a188 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -361,7 +361,7 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un
 	struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
 	int num_dpias = 0;
 
-	for (uint8_t i = 0; i < num_streams; ++i) {
+	for (unsigned int i = 0; i < num_streams; ++i) {
 		if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
 			/* new dpia sst stream, check whether it exceeds max dpia */
 			if (num_dpias >= MAX_DPIA_NUM)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index dd0d2b206462..5491b707cec8 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -196,7 +196,7 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
 	struct dc_link *link_dpia_primary, *link_dpia_secondary;
 	int total_bw = 0;
 
-	for (uint8_t i = 0; i < MAX_PIPES * 2; ++i) {
+	for (uint8_t i = 0; i < (MAX_PIPES * 2) - 1; ++i) {
 
 		if (!dc->links[i] || dc->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
 			continue;
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 5a0b04518956..16a62e018712 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status(
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
 	union lane_status lane_status;
+	union lane_align_status_updated dpcd_lane_status_updated;
 	uint8_t dpcd_buf[6] = {0};
 	uint32_t lane;
 
@@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status(
 		 * check lanes status
 		 */
 		lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane);
+		dpcd_lane_status_updated.raw = dpcd_buf[4];
 
 		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
 			!lane_status.bits.CR_DONE_0 ||
-			!lane_status.bits.SYMBOL_LOCKED_0) {
+			!lane_status.bits.SYMBOL_LOCKED_0 ||
+			!dp_is_interlane_aligned(dpcd_lane_status_updated)) {
 			/* if one of the channel equalization, clock
 			 * recovery or symbol lock is dropped
 			 * consider it as (link has been
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
index e8dda44b23cb..5d36bab0029c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
@@ -619,7 +619,7 @@ static enum link_training_result dpia_training_eq_non_transparent(
 	uint32_t retries_eq = 0;
 	enum dc_status status;
 	enum dc_dp_training_pattern tr_pattern;
-	uint32_t wait_time_microsec;
+	uint32_t wait_time_microsec = 0;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	union lane_align_status_updated dpcd_lane_status_updated = {0};
 	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0};
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
index 5c9a30211c10..fc50931c2aec 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
@@ -205,7 +205,7 @@ enum dc_status core_link_read_dpcd(
 	uint32_t extended_size;
 	/* size of the remaining partitioned address space */
 	uint32_t size_left_to_read;
-	enum dc_status status;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
 	/* size of the next partition to be read from */
 	uint32_t partition_size;
 	uint32_t data_index = 0;
@@ -234,7 +234,7 @@ enum dc_status core_link_write_dpcd(
 {
 	uint32_t partition_size;
 	uint32_t data_index = 0;
-	enum dc_status status;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
 
 	while (size) {
 		partition_size = dpcd_get_next_partition_size(address, size);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b985..7538b548c572 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
 	vpg = dcn301_vpg_create(ctx, vpg_inst);
 	afmt = dcn301_afmt_create(ctx, afmt_inst);
 
-	if (!enc1 || !vpg || !afmt) {
+	if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
 		kfree(enc1);
 		kfree(vpg);
 		kfree(afmt);
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 c4d71e7f18af..6f10052caeef 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
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
 		dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
 		DC_FP_END();
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		if (dc->config.enable_windowed_mpo_odm &&
+				dc->debug.enable_single_display_2to1_odm_policy) {
+			switch (resource_get_odm_slice_count(pipe)) {
+			case 2:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+				break;
+			case 4:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+				break;
+			default:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+			}
+		} else {
+			pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		}
 		pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 		pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec9891875..5fdcda8f8602 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.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,
 	.static_screen_wait_frames = 2,
 };
 
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
 	dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
 	dc->dml2_options.use_native_pstate_optimization = true;
 	dc->dml2_options.use_native_soc_bb_construction = true;
+	dc->dml2_options.minimize_dispclk_using_odm = false;
 	if (dc->config.EnableMinDispClkODM)
 		dc->dml2_options.minimize_dispclk_using_odm = true;
 	dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
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 c64b6c848ef7..e699731ee68e 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -2832,6 +2832,7 @@ struct dmub_rb_cmd_psr_set_power_opt {
 #define REPLAY_RESIDENCY_MODE_MASK             (0x1 << REPLAY_RESIDENCY_MODE_SHIFT)
 # define REPLAY_RESIDENCY_MODE_PHY             (0x0 << REPLAY_RESIDENCY_MODE_SHIFT)
 # define REPLAY_RESIDENCY_MODE_ALPM            (0x1 << REPLAY_RESIDENCY_MODE_SHIFT)
+# define REPLAY_RESIDENCY_MODE_IPS             0x10
 
 #define REPLAY_RESIDENCY_ENABLE_MASK           (0x1 << REPLAY_RESIDENCY_ENABLE_SHIFT)
 # define REPLAY_RESIDENCY_DISABLE              (0x0 << REPLAY_RESIDENCY_ENABLE_SHIFT)
@@ -2894,6 +2895,10 @@ enum dmub_cmd_replay_type {
 	 * Set Residency Frameupdate Timer.
 	 */
 	DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER = 6,
+	/**
+	 * Set pseudo vtotal
+	 */
+	DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL = 7,
 };
 
 /**
@@ -3077,6 +3082,26 @@ struct dmub_cmd_replay_set_timing_sync_data {
 };
 
 /**
+ * Data passed from driver to FW in a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+ */
+struct dmub_cmd_replay_set_pseudo_vtotal {
+	/**
+	 * Panel Instance.
+	 * Panel isntance to identify which replay_state to use
+	 * Currently the support is only for 0 or 1
+	 */
+	uint8_t panel_inst;
+	/**
+	 * Source Vtotal that Replay + IPS + ABM full screen video src vtotal
+	 */
+	uint16_t vtotal;
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad;
+};
+
+/**
  * Definition of a DMUB_CMD__SET_REPLAY_POWER_OPT command.
  */
 struct dmub_rb_cmd_replay_set_power_opt {
@@ -3157,6 +3182,20 @@ struct dmub_rb_cmd_replay_set_timing_sync {
 };
 
 /**
+ * Definition of a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+ */
+struct dmub_rb_cmd_replay_set_pseudo_vtotal {
+	/**
+	 * Command header.
+	 */
+	struct dmub_cmd_header header;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+	 */
+	struct dmub_cmd_replay_set_pseudo_vtotal data;
+};
+
+/**
  * Data passed from driver to FW in  DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command.
  */
 struct dmub_cmd_replay_frameupdate_timer_data {
@@ -3207,6 +3246,10 @@ union dmub_replay_cmd_set {
 	 * Definition of DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command data.
 	 */
 	struct dmub_cmd_replay_frameupdate_timer_data timer_data;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command data.
+	 */
+	struct dmub_cmd_replay_set_pseudo_vtotal pseudo_vtotal_data;
 };
 
 /**
@@ -4358,6 +4401,10 @@ union dmub_rb_cmd {
 	 * Definition of a DMUB_CMD__REPLAY_SET_RESIDENCY_FRAMEUPDATE_TIMER command.
 	 */
 	struct dmub_rb_cmd_replay_set_frameupdate_timer replay_set_frameupdate_timer;
+	/**
+	 * Definition of a DMUB_CMD__REPLAY_SET_PSEUDO_VTOTAL command.
+	 */
+	struct dmub_rb_cmd_replay_set_pseudo_vtotal replay_set_pseudo_vtotal;
 };
 
 /**
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 ad98e504c00d..e304e8435fb8 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -980,6 +980,11 @@ void set_replay_coasting_vtotal(struct dc_link *link,
 	link->replay_settings.coasting_vtotal_table[type] = vtotal;
 }
 
+void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal)
+{
+	link->replay_settings.abm_with_ips_on_full_screen_video_pseudo_vtotal = 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/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index c17bbc6fb38c..bef4815e1703 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -57,6 +57,7 @@ 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);
+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/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 1dc5dd9b7bf7..df2c7ffe190f 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -258,6 +258,7 @@ enum DC_DEBUG_MASK {
 	DC_ENABLE_DML2 = 0x100,
 	DC_DISABLE_PSR_SU = 0x200,
 	DC_DISABLE_REPLAY = 0x400,
+	DC_DISABLE_IPS = 0x800,
 };
 
 enum amd_dpm_forced_level;
diff --git a/drivers/gpu/drm/amd/include/amdgpu_reg_state.h b/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
index be519c8edf49..335980e2afbf 100644
--- a/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
+++ b/drivers/gpu/drm/amd/include/amdgpu_reg_state.h
@@ -138,7 +138,7 @@ static inline size_t amdgpu_reginst_size(uint16_t num_inst, size_t inst_size,
 }
 
 #define amdgpu_asic_get_reg_state_supported(adev) \
-	((adev)->asic_funcs->get_reg_state ? 1 : 0)
+	(((adev)->asic_funcs && (adev)->asic_funcs->get_reg_state) ? 1 : 0)
 
 #define amdgpu_asic_get_reg_state(adev, state, buf, size)                  \
 	((adev)->asic_funcs->get_reg_state ?                               \
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index c16703868e5c..0ad947df777a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -24,6 +24,7 @@
 
 #include <linux/firmware.h>
 #include <linux/pci.h>
+#include <linux/power_supply.h>
 #include <linux/reboot.h>
 
 #include "amdgpu.h"
@@ -733,7 +734,7 @@ 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_NONE;
+	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 	smu->user_dpm_profile.fan_mode = -1;
 
@@ -817,16 +818,8 @@ static int smu_late_init(void *handle)
 	 * handle the switch automatically. Driver involvement
 	 * is unnecessary.
 	 */
-	if (!smu->dc_controlled_by_gpio) {
-		ret = smu_set_power_source(smu,
-					   adev->pm.ac_power ? SMU_POWER_SOURCE_AC :
-					   SMU_POWER_SOURCE_DC);
-		if (ret) {
-			dev_err(adev->dev, "Failed to switch to %s mode!\n",
-				adev->pm.ac_power ? "AC" : "DC");
-			return ret;
-		}
-	}
+	adev->pm.ac_power = power_supply_is_system_supplied() > 0;
+	smu_set_ac_dc(smu);
 
 	if ((amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 1)) ||
 	    (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 3)))
@@ -1961,31 +1954,10 @@ 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)))
-		switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-		case IP_VERSION(13, 0, 0):
-		case IP_VERSION(13, 0, 7):
-		case IP_VERSION(13, 0, 10):
-			ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
-			break;
-		default:
-			break;
-		}
-
-	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;
@@ -2003,15 +1975,7 @@ static int smu_hw_fini(void *handle)
 
 	adev->pm.dpm_enabled = false;
 
-	ret = smu_smc_hw_cleanup(smu);
-	if (ret)
-		return ret;
-
-	ret = smu_reset_mp1_state(smu);
-	if (ret)
-		return ret;
-
-	return 0;
+	return smu_smc_hw_cleanup(smu);
 }
 
 static void smu_late_fini(void *handle)
@@ -2710,6 +2674,7 @@ int smu_get_power_limit(void *handle,
 		case SMU_PPT_LIMIT_CURRENT:
 			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 			case IP_VERSION(13, 0, 2):
+			case IP_VERSION(13, 0, 6):
 			case IP_VERSION(11, 0, 7):
 			case IP_VERSION(11, 0, 11):
 			case IP_VERSION(11, 0, 12):
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 2aa4fea87314..66e84defd0b6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,7 +424,6 @@ 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/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 5a314d0316c1..c7bfa68bf00f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1442,10 +1442,12 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				schedule_work(&smu->interrupt_work);
+				adev->pm.ac_power = true;
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				schedule_work(&smu->interrupt_work);
+				adev->pm.ac_power = false;
 				break;
 			case 0x7:
 				/*
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 771a3d457c33..c486182ff275 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1379,10 +1379,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
+				adev->pm.ac_power = true;
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
 				smu_v13_0_ack_ac_dc_interrupt(smu);
+				adev->pm.ac_power = false;
 				break;
 			case 0x7:
 				/*
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 a9b25faa63e4..a9954ffc02c5 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
@@ -2357,6 +2357,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
 	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
 		power_limit = smu->adev->pm.ac_power ?
@@ -2380,7 +2381,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 					od_percent_upper, od_percent_lower, power_limit);
 
 	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
 		*max_power_limit /= 100;
 	}
 
@@ -2747,13 +2748,7 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		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);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
@@ -2949,7 +2944,7 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	switch (adev->ip_versions[MP1_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 	case IP_VERSION(13, 0, 0):
 		return smu->smc_fw_version >= 0x004e6300;
 	case IP_VERSION(13, 0, 10):
@@ -2959,6 +2954,55 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 	}
 }
 
+static int smu_v13_0_0_set_power_limit(struct smu_context *smu,
+				       enum smu_ppt_limit_type limit_type,
+				       uint32_t limit)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	SkuTable_t *skutable = &pptable->SkuTable;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTableExternal_t *od_table =
+		(OverDriveTableExternal_t *)table_context->overdrive_table;
+	int ret = 0;
+
+	if (limit_type != SMU_DEFAULT_PPT_LIMIT)
+		return -EINVAL;
+
+	if (limit <= msg_limit) {
+		if (smu->current_power_limit > msg_limit) {
+			od_table->OverDriveTable.Ppt = 0;
+			od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+			ret = smu_v13_0_0_upload_overdrive_table(smu, od_table);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+				return ret;
+			}
+		}
+		return smu_v13_0_set_power_limit(smu, limit_type, limit);
+	} else if (smu->od_enabled) {
+		ret = smu_v13_0_set_power_limit(smu, limit_type, msg_limit);
+		if (ret)
+			return ret;
+
+		od_table->OverDriveTable.Ppt = (limit * 100) / msg_limit - 100;
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+		ret = smu_v13_0_0_upload_overdrive_table(smu, od_table);
+		if (ret) {
+		  dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+		  return ret;
+		}
+
+		smu->current_power_limit = limit;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_0_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_0_set_default_dpm_table,
@@ -3013,7 +3057,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.set_fan_control_mode = smu_v13_0_set_fan_control_mode,
 	.enable_mgpu_fan_boost = smu_v13_0_0_enable_mgpu_fan_boost,
 	.get_power_limit = smu_v13_0_0_get_power_limit,
-	.set_power_limit = smu_v13_0_set_power_limit,
+	.set_power_limit = smu_v13_0_0_set_power_limit,
 	.set_power_source = smu_v13_0_set_power_source,
 	.get_power_profile_mode = smu_v13_0_0_get_power_profile_mode,
 	.set_power_profile_mode = smu_v13_0_0_set_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 3c98a8a0386a..7e1941cf1796 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -160,8 +160,8 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(GfxDriverResetRecovery,		     PPSMC_MSG_GfxDriverResetRecovery,		0),
 	MSG_MAP(GetMinGfxclkFrequency,               PPSMC_MSG_GetMinGfxDpmFreq,                1),
 	MSG_MAP(GetMaxGfxclkFrequency,               PPSMC_MSG_GetMaxGfxDpmFreq,                1),
-	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                0),
-	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                0),
+	MSG_MAP(SetSoftMinGfxclk,                    PPSMC_MSG_SetSoftMinGfxClk,                1),
+	MSG_MAP(SetSoftMaxGfxClk,                    PPSMC_MSG_SetSoftMaxGfxClk,                1),
 	MSG_MAP(PrepareMp1ForUnload,                 PPSMC_MSG_PrepareForDriverUnload,          0),
 	MSG_MAP(GetCTFLimit,                         PPSMC_MSG_GetCTFLimit,                     0),
 	MSG_MAP(GetThermalLimit,                     PPSMC_MSG_ReadThrottlerLimit,              0),
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 59606a19e3d2..0ffdb58af74e 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
@@ -2321,6 +2321,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 	PPTable_t *pptable = table_context->driver_pptable;
 	SkuTable_t *skutable = &pptable->SkuTable;
 	uint32_t power_limit, od_percent_upper, od_percent_lower;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v13_0_get_current_power_limit(smu, &power_limit))
 		power_limit = smu->adev->pm.ac_power ?
@@ -2344,7 +2345,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 					od_percent_upper, od_percent_lower, power_limit);
 
 	if (max_power_limit) {
-		*max_power_limit = power_limit * (100 + od_percent_upper);
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
 		*max_power_limit /= 100;
 	}
 
@@ -2504,13 +2505,7 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		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);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
@@ -2545,6 +2540,55 @@ static bool smu_v13_0_7_wbrf_support_check(struct smu_context *smu)
 	return smu->smc_fw_version > 0x00524600;
 }
 
+static int smu_v13_0_7_set_power_limit(struct smu_context *smu,
+				       enum smu_ppt_limit_type limit_type,
+				       uint32_t limit)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	SkuTable_t *skutable = &pptable->SkuTable;
+	uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTableExternal_t *od_table =
+		(OverDriveTableExternal_t *)table_context->overdrive_table;
+	int ret = 0;
+
+	if (limit_type != SMU_DEFAULT_PPT_LIMIT)
+		return -EINVAL;
+
+	if (limit <= msg_limit) {
+		if (smu->current_power_limit > msg_limit) {
+			od_table->OverDriveTable.Ppt = 0;
+			od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+			ret = smu_v13_0_7_upload_overdrive_table(smu, od_table);
+			if (ret) {
+				dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+				return ret;
+			}
+		}
+		return smu_v13_0_set_power_limit(smu, limit_type, limit);
+	} else if (smu->od_enabled) {
+		ret = smu_v13_0_set_power_limit(smu, limit_type, msg_limit);
+		if (ret)
+			return ret;
+
+		od_table->OverDriveTable.Ppt = (limit * 100) / msg_limit - 100;
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_PPT_BIT;
+
+		ret = smu_v13_0_7_upload_overdrive_table(smu, od_table);
+		if (ret) {
+		  dev_err(smu->adev->dev, "Failed to upload overdrive table!\n");
+		  return ret;
+		}
+
+		smu->current_power_limit = limit;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_7_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_7_set_default_dpm_table,
@@ -2596,7 +2640,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.set_fan_control_mode = smu_v13_0_set_fan_control_mode,
 	.enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost,
 	.get_power_limit = smu_v13_0_7_get_power_limit,
-	.set_power_limit = smu_v13_0_set_power_limit,
+	.set_power_limit = smu_v13_0_7_set_power_limit,
 	.set_power_source = smu_v13_0_set_power_source,
 	.get_power_profile_mode = smu_v13_0_7_get_power_profile_mode,
 	.set_power_profile_mode = smu_v13_0_7_set_power_profile_mode,
diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c
index be5914caa17d..63a1a0c88be4 100644
--- a/drivers/gpu/drm/bridge/samsung-dsim.c
+++ b/drivers/gpu/drm/bridge/samsung-dsim.c
@@ -969,10 +969,6 @@ static int samsung_dsim_init_link(struct samsung_dsim *dsi)
 	reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG);
 	reg &= ~DSIM_STOP_STATE_CNT_MASK;
 	reg |= DSIM_STOP_STATE_CNT(driver_data->reg_values[STOP_STATE_CNT]);
-
-	if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type))
-		reg |= DSIM_FORCE_STOP_STATE;
-
 	samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg);
 
 	reg = DSIM_BTA_TIMEOUT(0xff) | DSIM_LPDR_TIMEOUT(0xffff);
@@ -1431,18 +1427,6 @@ static void samsung_dsim_disable_irq(struct samsung_dsim *dsi)
 	disable_irq(dsi->irq);
 }
 
-static void samsung_dsim_set_stop_state(struct samsung_dsim *dsi, bool enable)
-{
-	u32 reg = samsung_dsim_read(dsi, DSIM_ESCMODE_REG);
-
-	if (enable)
-		reg |= DSIM_FORCE_STOP_STATE;
-	else
-		reg &= ~DSIM_FORCE_STOP_STATE;
-
-	samsung_dsim_write(dsi, DSIM_ESCMODE_REG, reg);
-}
-
 static int samsung_dsim_init(struct samsung_dsim *dsi)
 {
 	const struct samsung_dsim_driver_data *driver_data = dsi->driver_data;
@@ -1492,9 +1476,6 @@ static void samsung_dsim_atomic_pre_enable(struct drm_bridge *bridge,
 		ret = samsung_dsim_init(dsi);
 		if (ret)
 			return;
-
-		samsung_dsim_set_display_mode(dsi);
-		samsung_dsim_set_display_enable(dsi, true);
 	}
 }
 
@@ -1503,12 +1484,8 @@ static void samsung_dsim_atomic_enable(struct drm_bridge *bridge,
 {
 	struct samsung_dsim *dsi = bridge_to_dsi(bridge);
 
-	if (samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type)) {
-		samsung_dsim_set_display_mode(dsi);
-		samsung_dsim_set_display_enable(dsi, true);
-	} else {
-		samsung_dsim_set_stop_state(dsi, false);
-	}
+	samsung_dsim_set_display_mode(dsi);
+	samsung_dsim_set_display_enable(dsi, true);
 
 	dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE;
 }
@@ -1521,9 +1498,6 @@ static void samsung_dsim_atomic_disable(struct drm_bridge *bridge,
 	if (!(dsi->state & DSIM_STATE_ENABLED))
 		return;
 
-	if (!samsung_dsim_hw_is_exynos(dsi->plat_data->hw_type))
-		samsung_dsim_set_stop_state(dsi, true);
-
 	dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE;
 }
 
@@ -1828,8 +1802,6 @@ static ssize_t samsung_dsim_host_transfer(struct mipi_dsi_host *host,
 	if (ret)
 		return ret;
 
-	samsung_dsim_set_stop_state(dsi, false);
-
 	ret = mipi_dsi_create_packet(&xfer.packet, msg);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 776f2f0b602d..0ef7bc8848b0 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -319,9 +319,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win,
 static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win,
 				 struct drm_framebuffer *fb)
 {
-	struct exynos_drm_plane plane = ctx->planes[win];
+	struct exynos_drm_plane *plane = &ctx->planes[win];
 	struct exynos_drm_plane_state *state =
-		to_exynos_plane_state(plane.base.state);
+		to_exynos_plane_state(plane->base.state);
 	unsigned int alpha = state->base.alpha;
 	unsigned int pixel_alpha;
 	unsigned long val;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index a9f1c5c05894..f2145227a1e0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -480,7 +480,7 @@ static void fimd_commit(struct exynos_drm_crtc *crtc)
 	struct fimd_context *ctx = crtc->ctx;
 	struct drm_display_mode *mode = &crtc->base.state->adjusted_mode;
 	const struct fimd_driver_data *driver_data = ctx->driver_data;
-	void *timing_base = ctx->regs + driver_data->timing_base;
+	void __iomem *timing_base = ctx->regs + driver_data->timing_base;
 	u32 val;
 
 	if (ctx->suspended)
@@ -661,9 +661,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win,
 static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win,
 				struct drm_framebuffer *fb, int width)
 {
-	struct exynos_drm_plane plane = ctx->planes[win];
+	struct exynos_drm_plane *plane = &ctx->planes[win];
 	struct exynos_drm_plane_state *state =
-		to_exynos_plane_state(plane.base.state);
+		to_exynos_plane_state(plane->base.state);
 	uint32_t pixel_format = fb->format->format;
 	unsigned int alpha = state->base.alpha;
 	u32 val = WINCONx_ENWIN;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index e9a769590415..180507a47700 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1341,7 +1341,7 @@ static int __maybe_unused gsc_runtime_resume(struct device *dev)
 	for (i = 0; i < ctx->num_clocks; i++) {
 		ret = clk_prepare_enable(ctx->clocks[i]);
 		if (ret) {
-			while (--i > 0)
+			while (--i >= 0)
 				clk_disable_unprepare(ctx->clocks[i]);
 			return ret;
 		}
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071..3089029abba4 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
 
 	  Note that this driver only supports newer device from Broadwell on.
 	  For further information and setup guide, you can visit:
-	  http://01.org/igvt-g.
+	  https://github.com/intel/gvt-linux/wiki.
 
 	  If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e777686190ca..c13f14edb508 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -17,7 +17,6 @@ subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
 subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
 subdir-ccflags-y += $(call cc-option, -Wformat-overflow)
 subdir-ccflags-y += $(call cc-option, -Wformat-truncation)
-subdir-ccflags-y += $(call cc-option, -Wstringop-overflow)
 subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
 # The following turn off the warnings enabled by -Wextra
 ifeq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index ac456a2275db..eda4a8b88590 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1155,6 +1155,7 @@ 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);
@@ -1255,8 +1256,6 @@ 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_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f5ef95da5534..ae647d03af25 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2355,6 +2355,9 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 	limits->min_rate = intel_dp_common_rate(intel_dp, 0);
 	limits->max_rate = intel_dp_max_link_rate(intel_dp);
 
+	/* FIXME 128b/132b SST support missing */
+	limits->max_rate = min(limits->max_rate, 810000);
+
 	limits->min_lane_count = 1;
 	limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 8f702c3fc62d..57bbf3e3af92 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1525,8 +1525,18 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 	 * can rely on frontbuffer tracking.
 	 */
 	mask = EDP_PSR_DEBUG_MASK_MEMUP |
-	       EDP_PSR_DEBUG_MASK_HPD |
-	       EDP_PSR_DEBUG_MASK_LPSP;
+	       EDP_PSR_DEBUG_MASK_HPD;
+
+	/*
+	 * For some unknown reason on HSW non-ULT (or at least on
+	 * Dell Latitude E6540) external displays start to flicker
+	 * when PSR is enabled on the eDP. SR/PC6 residency is much
+	 * higher than should be possible with an external display.
+	 * As a workaround leave LPSP unmasked to prevent PSR entry
+	 * when external displays are active.
+	 */
+	if (DISPLAY_VER(dev_priv) >= 8 || IS_HASWELL_ULT(dev_priv))
+		mask |= EDP_PSR_DEBUG_MASK_LPSP;
 
 	if (DISPLAY_VER(dev_priv) < 20)
 		mask |= EDP_PSR_DEBUG_MASK_MAX_SLEEP;
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index acc6b6804105..2915d7afe5cc 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1209,7 +1209,7 @@ static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo,
 	struct intel_sdvo_tv_format format;
 	u32 format_map;
 
-	format_map = 1 << conn_state->tv.mode;
+	format_map = 1 << conn_state->tv.legacy_mode;
 	memset(&format, 0, sizeof(format));
 	memcpy(&format, &format_map, min(sizeof(format), sizeof(format_map)));
 
@@ -2298,7 +2298,7 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector)
 	 * Read the list of supported input resolutions for the selected TV
 	 * format.
 	 */
-	format_map = 1 << conn_state->tv.mode;
+	format_map = 1 << conn_state->tv.legacy_mode;
 	memcpy(&tv_res, &format_map,
 	       min(sizeof(format_map), sizeof(struct intel_sdvo_sdtv_resolution_request)));
 
@@ -2363,7 +2363,7 @@ intel_sdvo_connector_atomic_get_property(struct drm_connector *connector,
 		int i;
 
 		for (i = 0; i < intel_sdvo_connector->format_supported_num; i++)
-			if (state->tv.mode == intel_sdvo_connector->tv_format_supported[i]) {
+			if (state->tv.legacy_mode == intel_sdvo_connector->tv_format_supported[i]) {
 				*val = i;
 
 				return 0;
@@ -2419,7 +2419,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector,
 	struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(state);
 
 	if (property == intel_sdvo_connector->tv_format) {
-		state->tv.mode = intel_sdvo_connector->tv_format_supported[val];
+		state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[val];
 
 		if (state->crtc) {
 			struct drm_crtc_state *crtc_state =
@@ -3076,7 +3076,7 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo,
 		drm_property_add_enum(intel_sdvo_connector->tv_format, i,
 				      tv_format_names[intel_sdvo_connector->tv_format_supported[i]]);
 
-	intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0];
+	intel_sdvo_connector->base.base.state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[0];
 	drm_object_attach_property(&intel_sdvo_connector->base.base.base,
 				   intel_sdvo_connector->tv_format, 0);
 	return true;
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index d4386cb3569e..992a725de751 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -949,7 +949,7 @@ intel_disable_tv(struct intel_atomic_state *state,
 
 static const struct tv_mode *intel_tv_mode_find(const struct drm_connector_state *conn_state)
 {
-	int format = conn_state->tv.mode;
+	int format = conn_state->tv.legacy_mode;
 
 	return &tv_modes[format];
 }
@@ -1704,7 +1704,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector)
 			break;
 	}
 
-	connector->state->tv.mode = i;
+	connector->state->tv.legacy_mode = i;
 }
 
 static int
@@ -1859,7 +1859,7 @@ static int intel_tv_atomic_check(struct drm_connector *connector,
 	old_state = drm_atomic_get_old_connector_state(state, connector);
 	new_crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc);
 
-	if (old_state->tv.mode != new_state->tv.mode ||
+	if (old_state->tv.legacy_mode != new_state->tv.legacy_mode ||
 	    old_state->tv.margins.left != new_state->tv.margins.left ||
 	    old_state->tv.margins.right != new_state->tv.margins.right ||
 	    old_state->tv.margins.top != new_state->tv.margins.top ||
@@ -1896,7 +1896,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
 	conn_state->tv.margins.right = 46;
 	conn_state->tv.margins.bottom = 37;
 
-	conn_state->tv.mode = 0;
+	conn_state->tv.legacy_mode = 0;
 
 	/* Create TV properties then attach current values */
 	for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
@@ -1910,7 +1910,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
 
 	drm_object_attach_property(&connector->base,
 				   i915->drm.mode_config.legacy_tv_mode_property,
-				   conn_state->tv.mode);
+				   conn_state->tv.legacy_mode);
 	drm_object_attach_property(&connector->base,
 				   i915->drm.mode_config.tv_left_margin_property,
 				   conn_state->tv.margins.left);
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 64f440fdc22b..8b21dc8e26d5 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -51,8 +51,8 @@
 #define DSCC_PICTURE_PARAMETER_SET_0		_MMIO(0x6BA00)
 #define _DSCA_PPS_0				0x6B200
 #define _DSCC_PPS_0				0x6BA00
-#define DSCA_PPS(pps)				_MMIO(_DSCA_PPS_0 + (pps) * 4)
-#define DSCC_PPS(pps)				_MMIO(_DSCC_PPS_0 + (pps) * 4)
+#define DSCA_PPS(pps)				_MMIO(_DSCA_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
+#define DSCC_PPS(pps)				_MMIO(_DSCC_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
 #define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB	0x78270
 #define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB	0x78370
 #define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC	0x78470
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d..efcb00472be2 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
 	for (i = start; i < end; i += 4) {
 		p = intel_gvt_find_mmio_info(gvt, i);
 		if (p) {
-			WARN(1, "dup mmio definition offset %x\n",
-				info->offset);
+			WARN(1, "dup mmio definition offset %x\n", i);
 
 			/* We return -EEXIST here to make GVT-g load fail.
 			 * So duplicated MMIO can be found as soon as
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91a..9b6d87c8b583 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
  * To virtualize GPU resources GVT-g driver depends on hypervisor technology
  * e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
  * and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
  */
 
 static LIST_HEAD(intel_gvt_devices);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c0bc924cd302..c9c55e2ea584 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1287,7 +1287,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 	gpu->ubwc_config.highest_bank_bit = 15;
 
 	if (adreno_is_a610(gpu)) {
-		gpu->ubwc_config.highest_bank_bit = 14;
+		gpu->ubwc_config.highest_bank_bit = 13;
 		gpu->ubwc_config.min_acc_len = 1;
 		gpu->ubwc_config.ubwc_mode = 1;
 	}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00..6a4b489d44e5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
  *			to track crtc in the disable() hook which is called
  *			_after_ encoder_mask is cleared.
  * @connector:		If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
- *				all CTL paths
- * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
- * @debugfs_root:		Debug file system root file node
  * @enc_lock:			Lock around physical encoder
  *				create/destroy/enable/disable
  * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
@@ -2072,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	}
 
 	/* reset the merge 3D HW block */
-	if (phys_enc->hw_pp->merge_3d) {
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
 		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2103,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_wb)
 		intf_cfg.wb = phys_enc->hw_wb->idx;
 
-	if (phys_enc->hw_pp->merge_3d)
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	if (ctl->ops.reset_intf_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326..724537ab776d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
 /**
  * struct dpu_rm_requirements - Reservation requirements parameter bundle
  * @topology:  selected topology for the display
- * @hw_res:	   Hardware resources required as reported by the encoders
  */
 struct dpu_rm_requirements {
 	struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
  * _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
  * @rm: dpu resource manager handle
  * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
  */
 static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
 {
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7..fb588fde298a 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
 	tbd = dp_link_get_test_bits_depth(ctrl->link,
 			ctrl->panel->dp_mode.bpp);
 
-	if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
-		pr_debug("BIT_DEPTH not set. Configure default\n");
-		tbd = DP_TEST_BIT_DEPTH_8;
-	}
-
 	config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
 
 	/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7..49dfac1fd1ef 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_print.h>
 
+#include "dp_reg.h"
 #include "dp_link.h"
 #include "dp_panel.h"
 
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 {
-	u32 cc;
+	u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
 	struct dp_link_private *link;
 
 	if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 	 * Unless a video pattern CTS test is ongoing, use RGB_VESA
 	 * Only RGB_VESA and RGB_CEA supported for now
 	 */
-	if (dp_link_is_video_pattern_requested(link))
-		cc = link->dp_link.test_video.test_dyn_range;
-	else
-		cc = DP_TEST_DYNAMIC_RANGE_VESA;
+	if (dp_link_is_video_pattern_requested(link)) {
+		if (link->dp_link.test_video.test_dyn_range &
+					DP_TEST_DYNAMIC_RANGE_CEA)
+			cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+	}
 
 	return cc;
 }
@@ -1179,6 +1181,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
 u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 {
 	u32 tbd;
+	struct dp_link_private *link;
+
+	link = container_of(dp_link, struct dp_link_private, dp_link);
 
 	/*
 	 * Few simplistic rules and assumptions made here:
@@ -1196,12 +1201,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 		tbd = DP_TEST_BIT_DEPTH_10;
 		break;
 	default:
-		tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+		drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+			   bpp);
+		tbd = DP_TEST_BIT_DEPTH_8;
 		break;
 	}
 
-	if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
-		tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+	tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
 
 	return tbd;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b..78785ed4b40c 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
 #define DP_MISC0_COLORIMETRY_CFG_SHIFT		(0x00000001)
 #define DP_MISC0_TEST_BITS_DEPTH_SHIFT		(0x00000005)
 
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB	(0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB		(0x04)
+
 #define REG_DP_VALID_BOUNDARY			(0x00000030)
 #define REG_DP_VALID_BOUNDARY_2			(0x00000034)
 
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e4e..0915f3b68752 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
 	void *vaddr;
 
-	vaddr = msm_gem_get_vaddr(obj);
+	vaddr = msm_gem_get_vaddr_locked(obj);
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 	iosys_map_set_vaddr(map, vaddr);
@@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
-	msm_gem_put_vaddr(obj);
+	msm_gem_put_vaddr_locked(obj);
 }
 
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 095390774f22..655002b21b0d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -751,12 +751,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned long flags;
 
-	pm_runtime_get_sync(&gpu->pdev->dev);
+	WARN_ON(!mutex_is_locked(&gpu->lock));
 
-	mutex_lock(&gpu->lock);
+	pm_runtime_get_sync(&gpu->pdev->dev);
 
 	msm_gpu_hw_init(gpu);
 
+	submit->seqno = submit->hw_fence->seqno;
+
 	update_sw_cntrs(gpu);
 
 	/*
@@ -781,11 +783,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	gpu->funcs->submit(gpu, submit);
 	gpu->cur_ctx_seqno = submit->queue->ctx->seqno;
 
-	hangcheck_timer_reset(gpu);
-
-	mutex_unlock(&gpu->lock);
-
 	pm_runtime_put(&gpu->pdev->dev);
+	hangcheck_timer_reset(gpu);
 }
 
 /*
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 5cc8d358cc97..d5512037c38b 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -21,6 +21,8 @@ struct msm_iommu_pagetable {
 	struct msm_mmu base;
 	struct msm_mmu *parent;
 	struct io_pgtable_ops *pgtbl_ops;
+	const struct iommu_flush_ops *tlb;
+	struct device *iommu_dev;
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	phys_addr_t ttbr;
 	u32 asid;
@@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = {
 
 static void msm_iommu_tlb_flush_all(void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
 		size_t granule, void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
@@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 {
 }
 
-static const struct iommu_flush_ops null_tlb_ops = {
+static const struct iommu_flush_ops tlb_ops = {
 	.tlb_flush_all = msm_iommu_tlb_flush_all,
 	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
 	.tlb_add_page = msm_iommu_tlb_add_page,
@@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* The incoming cfg will have the TTBR1 quirk enabled */
 	ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
-	ttbr0_cfg.tlb = &null_tlb_ops;
+	ttbr0_cfg.tlb = &tlb_ops;
 
 	pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
-		&ttbr0_cfg, iommu->domain);
+		&ttbr0_cfg, pagetable);
 
 	if (!pagetable->pgtbl_ops) {
 		kfree(pagetable);
@@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* Needed later for TLB flush */
 	pagetable->parent = parent;
+	pagetable->tlb = ttbr1_cfg->tlb;
+	pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
 	pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
 	pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
 
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd..35423d10aafa 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
 	.highest_bank_bit = 1,
+	.reg_bus_bw = 76800,
 };
 
 static const struct msm_mdss_data sdm845_data = {
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4bc13f7d005a..9d6655f96f0c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	msm_fence_init(submit->hw_fence, fctx);
 
-	submit->seqno = submit->hw_fence->seqno;
-
 	mutex_lock(&priv->lru.lock);
 
 	for (i = 0; i < submit->nr_bos; i++) {
@@ -35,8 +33,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	mutex_unlock(&priv->lru.lock);
 
+	/* TODO move submit path over to using a per-ring lock.. */
+	mutex_lock(&gpu->lock);
+
 	msm_gpu_submit(gpu, submit);
 
+	mutex_unlock(&gpu->lock);
+
 	return dma_fence_get(submit->hw_fence);
 }
 
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 1e6aaf95ff7c..ceef470c9fbf 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -100,3 +100,11 @@ config DRM_NOUVEAU_SVM
 	help
 	  Say Y here if you want to enable experimental support for
 	  Shared Virtual Memory (SVM).
+
+config DRM_NOUVEAU_GSP_DEFAULT
+	bool "Use GSP firmware for Turing/Ampere (needs firmware installed)"
+	depends on DRM_NOUVEAU
+	default n
+	help
+	  Say Y here if you want to use the GSP codepaths by default on
+	  Turing and Ampere GPUs.
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index d1bb8151a1df..cd14f993bdd1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -199,6 +199,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvif_device *device = &drm->client.device;
+	struct nvkm_device *nvkm_device = nvxx_device(&drm->client.device);
 	struct nvkm_gr *gr = nvxx_gr(device);
 	struct drm_nouveau_getparam *getparam = data;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
@@ -263,6 +264,14 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 		getparam->value = nouveau_exec_push_max_from_ib_max(ib_max);
 		break;
 	}
+	case NOUVEAU_GETPARAM_VRAM_BAR_SIZE:
+		getparam->value = nvkm_device->func->resource_size(nvkm_device, 1);
+		break;
+	case NOUVEAU_GETPARAM_VRAM_USED: {
+		struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
+		getparam->value = (u64)ttm_resource_manager_usage(vram_mgr) << PAGE_SHIFT;
+		break;
+	}
 	default:
 		NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 5057d976fa57..93f08f9479d8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) {
 		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 
-		if (atomic_dec_and_test(&fctx->notify_ref))
+		if (!--fctx->notify_ref)
 			drop = 1;
 	}
 
@@ -103,7 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
-	cancel_work_sync(&fctx->allow_block_work);
+	cancel_work_sync(&fctx->uevent_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -146,12 +146,13 @@ nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fc
 	return drop;
 }
 
-static int
-nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+static void
+nouveau_fence_uevent_work(struct work_struct *work)
 {
-	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
+						       uevent_work);
 	unsigned long flags;
-	int ret = NVIF_EVENT_KEEP;
+	int drop = 0;
 
 	spin_lock_irqsave(&fctx->lock, flags);
 	if (!list_empty(&fctx->pending)) {
@@ -161,23 +162,20 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
 		if (nouveau_fence_update(chan, fctx))
-			ret = NVIF_EVENT_DROP;
+			drop = 1;
 	}
-	spin_unlock_irqrestore(&fctx->lock, flags);
+	if (drop)
+		nvif_event_block(&fctx->event);
 
-	return ret;
+	spin_unlock_irqrestore(&fctx->lock, flags);
 }
 
-static void
-nouveau_fence_work_allow_block(struct work_struct *work)
+static int
+nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
 {
-	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
-						       allow_block_work);
-
-	if (atomic_read(&fctx->notify_ref) == 0)
-		nvif_event_block(&fctx->event);
-	else
-		nvif_event_allow(&fctx->event);
+	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	schedule_work(&fctx->uevent_work);
+	return NVIF_EVENT_KEEP;
 }
 
 void
@@ -191,7 +189,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
-	INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block);
+	INIT_WORK(&fctx->uevent_work, nouveau_fence_uevent_work);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
@@ -535,19 +533,15 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f)
 	struct nouveau_fence *fence = from_fence(f);
 	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 	bool ret;
-	bool do_work;
 
-	if (atomic_inc_return(&fctx->notify_ref) == 0)
-		do_work = true;
+	if (!fctx->notify_ref++)
+		nvif_event_allow(&fctx->event);
 
 	ret = nouveau_fence_no_signaling(f);
 	if (ret)
 		set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags);
-	else if (atomic_dec_and_test(&fctx->notify_ref))
-		do_work = true;
-
-	if (do_work)
-		schedule_work(&fctx->allow_block_work);
+	else if (!--fctx->notify_ref)
+		nvif_event_block(&fctx->event);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 28f5cf013b89..8bc065acfe35 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -3,7 +3,6 @@
 #define __NOUVEAU_FENCE_H__
 
 #include <linux/dma-fence.h>
-#include <linux/workqueue.h>
 #include <nvif/event.h>
 
 struct nouveau_drm;
@@ -45,10 +44,9 @@ struct nouveau_fence_chan {
 	u32 context;
 	char name[32];
 
+	struct work_struct uevent_work;
 	struct nvif_event event;
-	struct work_struct allow_block_work;
-	atomic_t notify_ref;
-	int dead, killed;
+	int notify_ref, dead, killed;
 };
 
 struct nouveau_fence_priv {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index a41735ab6068..a64c81385682 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -2312,8 +2312,12 @@ r535_gsp_load(struct nvkm_gsp *gsp, int ver, const struct nvkm_gsp_fwif *fwif)
 {
 	struct nvkm_subdev *subdev = &gsp->subdev;
 	int ret;
+	bool enable_gsp = fwif->enable;
 
-	if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", fwif->enable))
+#if IS_ENABLED(CONFIG_DRM_NOUVEAU_GSP_DEFAULT)
+	enable_gsp = true;
+#endif
+	if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", enable_gsp))
 		return -EINVAL;
 
 	if ((ret = r535_gsp_load_fw(gsp, "gsp", fwif->ver, &gsp->fws.rm)) ||
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 550492a7a031..d442b893275b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1184,14 +1184,16 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	if (READ_ONCE(sched->pause_submit))
 		return;
 
+	/* Find entity with a ready job */
 	entity = drm_sched_select_entity(sched);
 	if (!entity)
-		return;
+		return;	/* No more work */
 
 	sched_job = drm_sched_entity_pop_job(entity);
 	if (!sched_job) {
 		complete_all(&entity->entity_idle);
-		return;	/* No more work */
+		drm_sched_run_job_queue(sched);
+		return;
 	}
 
 	s_fence = sched_job->s_fence;
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 373bcd79257e..03d1c76aec2d 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -960,7 +960,8 @@ int host1x_client_iommu_attach(struct host1x_client *client)
 	 * not the shared IOMMU domain, don't try to attach it to a different
 	 * domain. This allows using the IOMMU-backed DMA API.
 	 */
-	if (domain && domain != tegra->domain)
+	if (domain && domain->type != IOMMU_DOMAIN_IDENTITY &&
+	    domain != tegra->domain)
 		return 0;
 
 	if (tegra->domain) {
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 3062e0e0d467..79ba98a169f9 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -50,8 +50,8 @@
 
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffff << 16)
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffff << 0)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffffu << 16)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffffu << 0)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32		GUC_HXG_REQUEST_MSG_n_DATAn
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64		GUC_HXG_REQUEST_MSG_n_DATAn
 
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
index 811add10c30d..c165e26c0976 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
@@ -242,8 +242,8 @@ struct slpc_shared_data {
 		(HOST2GUC_PC_SLPC_REQUEST_REQUEST_MSG_MIN_LEN + \
 			HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xff << 8)
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xff << 0)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xffu << 8)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xffu << 0)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_N_EVENT_DATA_N	GUC_HXG_REQUEST_MSG_n_DATAn
 
 #endif
diff --git a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
index 3b83f907ece4..0b1146d0c997 100644
--- a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
@@ -82,11 +82,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
 #define GUC_CTB_HDR_LEN				1u
 #define GUC_CTB_MSG_MIN_LEN			GUC_CTB_HDR_LEN
 #define GUC_CTB_MSG_MAX_LEN			256u
-#define GUC_CTB_MSG_0_FENCE			(0xffff << 16)
-#define GUC_CTB_MSG_0_FORMAT			(0xf << 12)
+#define GUC_CTB_MSG_0_FENCE			(0xffffu << 16)
+#define GUC_CTB_MSG_0_FORMAT			(0xfu << 12)
 #define   GUC_CTB_FORMAT_HXG			0u
-#define GUC_CTB_MSG_0_RESERVED			(0xf << 8)
-#define GUC_CTB_MSG_0_NUM_DWORDS		(0xff << 0)
+#define GUC_CTB_MSG_0_RESERVED			(0xfu << 8)
+#define GUC_CTB_MSG_0_NUM_DWORDS		(0xffu << 0)
 
 /**
  * DOC: CTB HXG Message
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 47094b9b044c..0400bc0fccdc 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -31,9 +31,9 @@
  */
 
 #define GUC_KLV_LEN_MIN				1u
-#define GUC_KLV_0_KEY				(0xffff << 16)
-#define GUC_KLV_0_LEN				(0xffff << 0)
-#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+#define GUC_KLV_0_KEY				(0xffffu << 16)
+#define GUC_KLV_0_LEN				(0xffffu << 0)
+#define GUC_KLV_n_VALUE				(0xffffffffu << 0)
 
 /**
  * DOC: GuC Self Config KLVs
diff --git a/drivers/gpu/drm/xe/abi/guc_messages_abi.h b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
index 3d199016cf88..29e414c82d56 100644
--- a/drivers/gpu/drm/xe/abi/guc_messages_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
@@ -40,18 +40,18 @@
  */
 
 #define GUC_HXG_MSG_MIN_LEN			1u
-#define GUC_HXG_MSG_0_ORIGIN			(0x1 << 31)
+#define GUC_HXG_MSG_0_ORIGIN			(0x1u << 31)
 #define   GUC_HXG_ORIGIN_HOST			0u
 #define   GUC_HXG_ORIGIN_GUC			1u
-#define GUC_HXG_MSG_0_TYPE			(0x7 << 28)
+#define GUC_HXG_MSG_0_TYPE			(0x7u << 28)
 #define   GUC_HXG_TYPE_REQUEST			0u
 #define   GUC_HXG_TYPE_EVENT			1u
 #define   GUC_HXG_TYPE_NO_RESPONSE_BUSY		3u
 #define   GUC_HXG_TYPE_NO_RESPONSE_RETRY	5u
 #define   GUC_HXG_TYPE_RESPONSE_FAILURE		6u
 #define   GUC_HXG_TYPE_RESPONSE_SUCCESS		7u
-#define GUC_HXG_MSG_0_AUX			(0xfffffff << 0)
-#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffff << 0)
+#define GUC_HXG_MSG_0_AUX			(0xfffffffu << 0)
+#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffffu << 0)
 
 /**
  * DOC: HXG Request
@@ -85,8 +85,8 @@
  */
 
 #define GUC_HXG_REQUEST_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_REQUEST_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -117,8 +117,8 @@
  */
 
 #define GUC_HXG_EVENT_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_EVENT_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -188,8 +188,8 @@
  */
 
 #define GUC_HXG_FAILURE_MSG_LEN			GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfff << 16)
-#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffff << 0)
+#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfffu << 16)
+#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffffu << 0)
 
 /**
  * DOC: HXG Response
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
index 5f19550cc845..777c20ceabab 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
@@ -10,7 +10,7 @@
 
 #include "xe_bo.h"
 
-#define i915_gem_object_is_shmem(obj) ((obj)->flags & XE_BO_CREATE_SYSTEM_BIT)
+#define i915_gem_object_is_shmem(obj) (0) /* We don't use shmem */
 
 static inline dma_addr_t i915_gem_object_get_dma_address(const struct xe_bo *bo, pgoff_t n)
 {
@@ -35,12 +35,10 @@ static inline int i915_gem_object_read_from_page(struct xe_bo *bo,
 					  u32 ofs, u64 *ptr, u32 size)
 {
 	struct ttm_bo_kmap_obj map;
-	void *virtual;
+	void *src;
 	bool is_iomem;
 	int ret;
 
-	XE_WARN_ON(size != 8);
-
 	ret = xe_bo_lock(bo, true);
 	if (ret)
 		return ret;
@@ -50,11 +48,12 @@ static inline int i915_gem_object_read_from_page(struct xe_bo *bo,
 		goto out_unlock;
 
 	ofs &= ~PAGE_MASK;
-	virtual = ttm_kmap_obj_virtual(&map, &is_iomem);
+	src = ttm_kmap_obj_virtual(&map, &is_iomem);
+	src += ofs;
 	if (is_iomem)
-		*ptr = readq((void __iomem *)(virtual + ofs));
+		memcpy_fromio(ptr, (void __iomem *)src, size);
 	else
-		*ptr = *(u64 *)(virtual + ofs);
+		memcpy(ptr, src, size);
 
 	ttm_bo_kunmap(&map);
 out_unlock:
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs_test.c b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
index ef56bd517b28..421b819fd4ba 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
@@ -21,4 +21,5 @@ kunit_test_suite(xe_mocs_test_suite);
 
 MODULE_AUTHOR("Intel Corporation");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("xe_mocs kunit test");
 MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
diff --git a/drivers/gpu/drm/xe/tests/xe_wa_test.c b/drivers/gpu/drm/xe/tests/xe_wa_test.c
index a53c22a19582..b4715b78ef3b 100644
--- a/drivers/gpu/drm/xe/tests/xe_wa_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_wa_test.c
@@ -74,9 +74,6 @@ static const struct platform_test_case cases[] = {
 	SUBPLATFORM_CASE(DG2, G11, B1),
 	SUBPLATFORM_CASE(DG2, G12, A0),
 	SUBPLATFORM_CASE(DG2, G12, A1),
-	PLATFORM_CASE(PVC, B0),
-	PLATFORM_CASE(PVC, B1),
-	PLATFORM_CASE(PVC, C0),
 	GMDID_CASE(METEORLAKE, 1270, A0, 1300, A0),
 	GMDID_CASE(METEORLAKE, 1271, A0, 1300, A0),
 	GMDID_CASE(LUNARLAKE, 2004, A0, 2000, A0),
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index b8d8da546670..5176c27e4b6a 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -83,9 +83,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 }
 
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
-					       struct xe_file *xef);
-
 static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct xe_device *xe = to_xe_device(dev);
@@ -102,8 +99,6 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 	mutex_unlock(&xef->exec_queue.lock);
 	xa_destroy(&xef->exec_queue.xa);
 	mutex_destroy(&xef->exec_queue.lock);
-	device_kill_persistent_exec_queues(xe, xef);
-
 	mutex_lock(&xef->vm.lock);
 	xa_for_each(&xef->vm.xa, idx, vm)
 		xe_vm_close_and_put(vm);
@@ -255,9 +250,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 			xa_erase(&xe->usm.asid_to_vm, asid);
 	}
 
-	drmm_mutex_init(&xe->drm, &xe->persistent_engines.lock);
-	INIT_LIST_HEAD(&xe->persistent_engines.list);
-
 	spin_lock_init(&xe->pinned.lock);
 	INIT_LIST_HEAD(&xe->pinned.kernel_bo_present);
 	INIT_LIST_HEAD(&xe->pinned.external_vram);
@@ -570,37 +562,6 @@ void xe_device_shutdown(struct xe_device *xe)
 {
 }
 
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q)
-{
-	mutex_lock(&xe->persistent_engines.lock);
-	list_add_tail(&q->persistent.link, &xe->persistent_engines.list);
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
-					     struct xe_exec_queue *q)
-{
-	mutex_lock(&xe->persistent_engines.lock);
-	if (!list_empty(&q->persistent.link))
-		list_del(&q->persistent.link);
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
-					       struct xe_file *xef)
-{
-	struct xe_exec_queue *q, *next;
-
-	mutex_lock(&xe->persistent_engines.lock);
-	list_for_each_entry_safe(q, next, &xe->persistent_engines.list,
-				 persistent.link)
-		if (q->persistent.xef == xef) {
-			xe_exec_queue_kill(q);
-			list_del_init(&q->persistent.link);
-		}
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
 void xe_device_wmb(struct xe_device *xe)
 {
 	struct xe_gt *gt = xe_root_mmio_gt(xe);
@@ -613,7 +574,7 @@ void xe_device_wmb(struct xe_device *xe)
 u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
 {
 	return xe_device_has_flat_ccs(xe) ?
-		DIV_ROUND_UP(size, NUM_BYTES_PER_CCS_BYTE(xe)) : 0;
+		DIV_ROUND_UP_ULL(size, NUM_BYTES_PER_CCS_BYTE(xe)) : 0;
 }
 
 bool xe_device_mem_access_ongoing(struct xe_device *xe)
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 3da83b233206..08d8b72c7731 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -42,10 +42,6 @@ int xe_device_probe(struct xe_device *xe);
 void xe_device_remove(struct xe_device *xe);
 void xe_device_shutdown(struct xe_device *xe);
 
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q);
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
-					     struct xe_exec_queue *q);
-
 void xe_device_wmb(struct xe_device *xe);
 
 static inline struct xe_file *to_xe_file(const struct drm_file *file)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 5dc9127a2029..e8491979a6f2 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -341,14 +341,6 @@ struct xe_device {
 		struct mutex lock;
 	} usm;
 
-	/** @persistent_engines: engines that are closed but still running */
-	struct {
-		/** @lock: protects persistent engines */
-		struct mutex lock;
-		/** @list: list of persistent engines */
-		struct list_head list;
-	} persistent_engines;
-
 	/** @pinned: pinned BO state */
 	struct {
 		/** @lock: protected pinned BO list state */
diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae..e4db069f0db3 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
 
 int xe_display_init_nommio(struct xe_device *xe)
 {
-	int err;
-
 	if (!xe->info.enable_display)
 		return 0;
 
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(xe);
 
-	err = intel_power_domains_init(xe);
-	if (err)
-		return err;
-
 	return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index 64ed303728fd..da2627ed6ae7 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -175,7 +175,7 @@ static int xe_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 	return 0;
 }
 
-const struct dma_buf_ops xe_dmabuf_ops = {
+static const struct dma_buf_ops xe_dmabuf_ops = {
 	.attach = xe_dma_buf_attach,
 	.detach = xe_dma_buf_detach,
 	.pin = xe_dma_buf_pin,
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index b853feed9ccc..17f26952e665 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -111,7 +111,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	u64 addresses[XE_HW_ENGINE_MAX_INSTANCE];
 	struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn};
 	struct drm_exec *exec = &vm_exec.exec;
-	u32 i, num_syncs = 0;
+	u32 i, num_syncs = 0, num_ufence = 0;
 	struct xe_sched_job *job;
 	struct dma_fence *rebind_fence;
 	struct xe_vm *vm;
@@ -157,6 +157,14 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
 			goto err_syncs;
+
+		if (xe_sync_is_ufence(&syncs[i]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto err_syncs;
 	}
 
 	if (xe_exec_queue_is_parallel(q)) {
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c5..3acfd4f07666 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -60,7 +60,6 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	q->fence_irq = &gt->fence_irq[hwe->class];
 	q->ring_ops = gt->ring_ops[hwe->class];
 	q->ops = gt->exec_queue_ops;
-	INIT_LIST_HEAD(&q->persistent.link);
 	INIT_LIST_HEAD(&q->compute.link);
 	INIT_LIST_HEAD(&q->multi_gt_link);
 
@@ -326,23 +325,6 @@ static int exec_queue_set_preemption_timeout(struct xe_device *xe,
 	return q->ops->set_preempt_timeout(q, value);
 }
 
-static int exec_queue_set_persistence(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, xe_vm_in_preempt_fence_mode(q->vm)))
-		return -EINVAL;
-
-	if (value)
-		q->flags |= EXEC_QUEUE_FLAG_PERSISTENT;
-	else
-		q->flags &= ~EXEC_QUEUE_FLAG_PERSISTENT;
-
-	return 0;
-}
-
 static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q,
 				      u64 value, bool create)
 {
@@ -414,7 +396,6 @@ static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = {
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE] = exec_queue_set_persistence,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify,
@@ -441,6 +422,9 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe,
 		return -EINVAL;
 
 	idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs));
+	if (!exec_queue_set_property_funcs[idx])
+		return -EINVAL;
+
 	return exec_queue_set_property_funcs[idx](xe, q, ext.value,  create);
 }
 
@@ -704,9 +688,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 		}
 
 		q = xe_exec_queue_create(xe, vm, logical_mask,
-					 args->width, hwe,
-					 xe_vm_in_lr_mode(vm) ? 0 :
-					 EXEC_QUEUE_FLAG_PERSISTENT);
+					 args->width, hwe, 0);
 		up_read(&vm->lock);
 		xe_vm_put(vm);
 		if (IS_ERR(q))
@@ -728,8 +710,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 			goto kill_exec_queue;
 	}
 
-	q->persistent.xef = xef;
-
 	mutex_lock(&xef->exec_queue.lock);
 	err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->exec_queue.lock);
@@ -872,10 +852,7 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
 	if (XE_IOCTL_DBG(xe, !q))
 		return -ENOENT;
 
-	if (!(q->flags & EXEC_QUEUE_FLAG_PERSISTENT))
-		xe_exec_queue_kill(q);
-	else
-		xe_device_add_persistent_exec_queues(xe, q);
+	xe_exec_queue_kill(q);
 
 	trace_xe_exec_queue_close(q);
 	xe_exec_queue_put(q);
@@ -926,20 +903,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
  *
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
  *
  * Returns: last fence if not signaled, dma fence stub if signaled
  */
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
 					       struct xe_vm *vm)
 {
+	struct dma_fence *fence;
+
 	xe_exec_queue_last_fence_lockdep_assert(q, vm);
 
 	if (q->last_fence &&
 	    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
 		xe_exec_queue_last_fence_put(q, vm);
 
-	return q->last_fence ? q->last_fence : dma_fence_get_stub();
+	fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+	dma_fence_get(fence);
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 8d4b7feb8c30..947bbc4b285d 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -105,16 +105,6 @@ struct xe_exec_queue {
 		struct xe_guc_exec_queue *guc;
 	};
 
-	/**
-	 * @persistent: persistent exec queue state
-	 */
-	struct {
-		/** @xef: file which this exec queue belongs to */
-		struct xe_file *xef;
-		/** @link: link in list of persistent exec queues */
-		struct list_head link;
-	} persistent;
-
 	union {
 		/**
 		 * @parallel: parallel submission state
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 96b5224eb478..42d01bbbf7d0 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -378,8 +378,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w)
 		list_del(&exl->active_link);
 	spin_unlock_irqrestore(&exl->port->lock, flags);
 
-	if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
-		xe_device_remove_persistent_exec_queues(xe, q);
 	drm_sched_entity_fini(&exl->entity);
 	drm_sched_fini(&exl->sched);
 	kfree(exl);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec1295..35474ddbaf97 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		 * USM has its only SA pool to non-block behind user operations
 		 */
 		if (gt_to_xe(gt)->info.has_usm) {
-			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+			struct xe_device *xe = gt_to_xe(gt);
+
+			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+								IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
 			if (IS_ERR(gt->usm.bb_pool)) {
 				err = PTR_ERR(gt->usm.bb_pool);
 				goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index 9358f7336889..9fcae65b6469 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -145,10 +145,10 @@ void xe_gt_idle_sysfs_init(struct xe_gt_idle *gtidle)
 	}
 
 	if (xe_gt_is_media_type(gt)) {
-		sprintf(gtidle->name, "gt%d-mc\n", gt->info.id);
+		sprintf(gtidle->name, "gt%d-mc", gt->info.id);
 		gtidle->idle_residency = xe_guc_pc_mc6_residency;
 	} else {
-		sprintf(gtidle->name, "gt%d-rc\n", gt->info.id);
+		sprintf(gtidle->name, "gt%d-rc", gt->info.id);
 		gtidle->idle_residency = xe_guc_pc_rc6_residency;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 77925b35cf8d..8546cd3cc50d 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -480,7 +480,7 @@ static bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
  * to synchronize with external clients (e.g., firmware), so a semaphore
  * register will also need to be taken.
  */
-static void mcr_lock(struct xe_gt *gt)
+static void mcr_lock(struct xe_gt *gt) __acquires(&gt->mcr_lock)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int ret = 0;
@@ -500,7 +500,7 @@ static void mcr_lock(struct xe_gt *gt)
 	drm_WARN_ON_ONCE(&xe->drm, ret == -ETIMEDOUT);
 }
 
-static void mcr_unlock(struct xe_gt *gt)
+static void mcr_unlock(struct xe_gt *gt) __releases(&gt->mcr_lock)
 {
 	/* Release hardware semaphore - this is done by writing 1 to the register */
 	if (GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 59a70d2e0a7a..73f08f1924df 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -165,7 +165,8 @@ retry_userptr:
 		goto unlock_vm;
 	}
 
-	if (!xe_vma_is_userptr(vma) || !xe_vma_userptr_check_repin(vma)) {
+	if (!xe_vma_is_userptr(vma) ||
+	    !xe_vma_userptr_check_repin(to_userptr_vma(vma))) {
 		downgrade_write(&vm->lock);
 		write_locked = false;
 	}
@@ -181,11 +182,13 @@ retry_userptr:
 	/* TODO: Validate fault */
 
 	if (xe_vma_is_userptr(vma) && write_locked) {
+		struct xe_userptr_vma *uvma = to_userptr_vma(vma);
+
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del_init(&vma->userptr.invalidate_link);
+		list_del_init(&uvma->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 
-		ret = xe_vma_userptr_pin_pages(vma);
+		ret = xe_vma_userptr_pin_pages(uvma);
 		if (ret)
 			goto unlock_vm;
 
@@ -220,7 +223,7 @@ retry_userptr:
 	dma_fence_put(fence);
 
 	if (xe_vma_is_userptr(vma))
-		ret = xe_vma_userptr_check_repin(vma);
+		ret = xe_vma_userptr_check_repin(to_userptr_vma(vma));
 	vma->usm.tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
@@ -332,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		return -EPROTO;
 
 	asid = FIELD_GET(PFD_ASID, msg[1]);
-	pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+	pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
 
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index f71085228cb3..d91702592520 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -963,7 +963,9 @@ void xe_guc_pc_fini(struct xe_guc_pc *pc)
 	struct xe_device *xe = pc_to_xe(pc);
 
 	if (xe->info.skip_guc_pc) {
+		xe_device_mem_access_get(xe);
 		xe_gt_idle_disable_c6(pc_to_gt(pc));
+		xe_device_mem_access_put(xe);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 54ffcfcdd41f..f22ae717b0b2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1028,8 +1028,6 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
-	if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
-		xe_device_remove_persistent_exec_queues(gt_to_xe(q->gt), q);
 	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index a6094c81f2ad..a5de3e7b0bd6 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -217,13 +217,13 @@ struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx,
 	if (!fence)
 		return ERR_PTR(-ENOMEM);
 
-	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
-		       ctx->dma_fence_ctx, ctx->next_seqno++);
-
 	fence->ctx = ctx;
 	fence->seqno_map = seqno_map;
 	INIT_LIST_HEAD(&fence->irq_link);
 
+	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
+		       ctx->dma_fence_ctx, ctx->next_seqno++);
+
 	trace_xe_hw_fence_create(fence);
 
 	return fence;
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index 6ef2aa1eae8b..174ed2185481 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -419,7 +419,7 @@ static int xe_hwmon_pcode_read_i1(struct xe_gt *gt, u32 *uval)
 
 	return xe_pcode_read(gt, PCODE_MBOX(PCODE_POWER_SETUP,
 			     POWER_SETUP_SUBCOMMAND_READ_I1, 0),
-			     uval, 0);
+			     uval, NULL);
 }
 
 static int xe_hwmon_pcode_write_i1(struct xe_gt *gt, u32 uval)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b7fa3831b684..0ec5ad2539f1 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -21,10 +21,10 @@
 #include "xe_map.h"
 #include "xe_vm.h"
 
-#define CTX_VALID				(1 << 0)
-#define CTX_PRIVILEGE				(1 << 8)
-#define CTX_ADDRESSING_MODE_SHIFT		3
-#define LEGACY_64B_CONTEXT			3
+#define LRC_VALID				(1 << 0)
+#define LRC_PRIVILEGE				(1 << 8)
+#define LRC_ADDRESSING_MODE_SHIFT		3
+#define LRC_LEGACY_64B_CONTEXT			3
 
 #define ENGINE_CLASS_SHIFT			61
 #define ENGINE_INSTANCE_SHIFT			48
@@ -762,15 +762,15 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 				     (q->usm.acc_notify << ACC_NOTIFY_S) |
 				     q->usm.acc_trigger);
 
-	lrc->desc = CTX_VALID;
-	lrc->desc |= LEGACY_64B_CONTEXT << CTX_ADDRESSING_MODE_SHIFT;
+	lrc->desc = LRC_VALID;
+	lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT;
 	/* TODO: Priority */
 
 	/* While this appears to have something about privileged batches or
 	 * some such, it really just means PPGTT mode.
 	 */
 	if (vm)
-		lrc->desc |= CTX_PRIVILEGE;
+		lrc->desc |= LRC_PRIVILEGE;
 
 	if (GRAPHICS_VERx100(xe) < 1250) {
 		lrc->desc |= (u64)hwe->instance << ENGINE_INSTANCE_SHIFT;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index e05e9e7282b6..70480c305602 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
@@ -472,7 +485,7 @@ static void emit_pte(struct xe_migrate *m,
 	/* Indirect access needs compression enabled uncached PAT index */
 	if (GRAPHICS_VERx100(xe) >= 2000)
 		pat_index = is_comp_pte ? xe->pat.idx[XE_CACHE_NONE_COMPRESSION] :
-					  xe->pat.idx[XE_CACHE_NONE];
+					  xe->pat.idx[XE_CACHE_WB];
 	else
 		pat_index = xe->pat.idx[XE_CACHE_WB];
 
@@ -760,14 +773,14 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
 		else
-			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
-				 src);
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+				 &src_it, src_L0, src);
 
 		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
 			xe_res_next(&dst_it, src_L0);
 		else
-			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
-				 dst);
+			emit_pte(m, bb, dst_L0_pt, dst_is_vram, copy_system_ccs,
+				 &dst_it, src_L0, dst);
 
 		if (copy_system_ccs)
 			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
@@ -1009,8 +1022,8 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
 			xe_res_next(&src_it, clear_L0);
 		else
-			emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
-				 dst);
+			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_system_ccs,
+				 &src_it, clear_L0, dst);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -1204,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index c8c5d74b6e90..5f6b53ea5528 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -272,8 +272,8 @@ int xe_mmio_probe_vram(struct xe_device *xe)
 		drm_info(&xe->drm, "VRAM[%u, %u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n", id,
 			 tile->id, &tile->mem.vram.actual_physical_size, &tile->mem.vram.usable_size, &tile->mem.vram.io_size);
 		drm_info(&xe->drm, "VRAM[%u, %u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n", id, tile->id,
-			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + tile->mem.vram.actual_physical_size,
-			 &tile->mem.vram.io_start, tile->mem.vram.io_start + tile->mem.vram.io_size);
+			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + (u64)tile->mem.vram.actual_physical_size,
+			 &tile->mem.vram.io_start, tile->mem.vram.io_start + (u64)tile->mem.vram.io_size);
 
 		/* calculate total size using tile size to get the correct HW sizing */
 		total_size += tile_size;
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index de1030a47588..6653c045f3c9 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -20,8 +20,8 @@
 
 struct xe_pt_dir {
 	struct xe_pt pt;
-	/** @dir: Directory structure for the xe_pt_walk functionality */
-	struct xe_ptw_dir dir;
+	/** @children: Array of page-table child nodes */
+	struct xe_ptw *children[XE_PDES];
 };
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -44,7 +44,7 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
 
 static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
 {
-	return container_of(pt_dir->dir.entries[index], struct xe_pt, base);
+	return container_of(pt_dir->children[index], struct xe_pt, base);
 }
 
 static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -65,6 +65,14 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
 		XE_PTE_NULL;
 }
 
+static void xe_pt_free(struct xe_pt *pt)
+{
+	if (pt->level)
+		kfree(as_xe_pt_dir(pt));
+	else
+		kfree(pt);
+}
+
 /**
  * xe_pt_create() - Create a page-table.
  * @vm: The vm to create for.
@@ -85,15 +93,19 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 {
 	struct xe_pt *pt;
 	struct xe_bo *bo;
-	size_t size;
 	int err;
 
-	size = !level ?  sizeof(struct xe_pt) : sizeof(struct xe_pt_dir) +
-		XE_PDES * sizeof(struct xe_ptw *);
-	pt = kzalloc(size, GFP_KERNEL);
+	if (level) {
+		struct xe_pt_dir *dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+
+		pt = (dir) ? &dir->pt : NULL;
+	} else {
+		pt = kzalloc(sizeof(*pt), GFP_KERNEL);
+	}
 	if (!pt)
 		return ERR_PTR(-ENOMEM);
 
+	pt->level = level;
 	bo = xe_bo_create_pin_map(vm->xe, tile, vm, SZ_4K,
 				  ttm_bo_type_kernel,
 				  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
@@ -106,8 +118,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 		goto err_kfree;
 	}
 	pt->bo = bo;
-	pt->level = level;
-	pt->base.dir = level ? &as_xe_pt_dir(pt)->dir : NULL;
+	pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
 
 	if (vm->xef)
 		xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -116,7 +127,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 	return pt;
 
 err_kfree:
-	kfree(pt);
+	xe_pt_free(pt);
 	return ERR_PTR(err);
 }
 
@@ -193,7 +204,7 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 					      deferred);
 		}
 	}
-	kfree(pt);
+	xe_pt_free(pt);
 }
 
 /**
@@ -358,7 +369,7 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
 		struct iosys_map *map = &parent->bo->vmap;
 
 		if (unlikely(xe_child))
-			parent->base.dir->entries[offset] = &xe_child->base;
+			parent->base.children[offset] = &xe_child->base;
 
 		xe_pt_write(xe_walk->vm->xe, map, offset, pte);
 		parent->num_live++;
@@ -488,10 +499,12 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 		 * this device *requires* 64K PTE size for VRAM, fail.
 		 */
 		if (level == 0 && !xe_parent->is_compact) {
-			if (xe_pt_is_pte_ps64K(addr, next, xe_walk))
+			if (xe_pt_is_pte_ps64K(addr, next, xe_walk)) {
+				xe_walk->vma->gpuva.flags |= XE_VMA_PTE_64K;
 				pte |= XE_PTE_PS64;
-			else if (XE_WARN_ON(xe_walk->needs_64K))
+			} else if (XE_WARN_ON(xe_walk->needs_64K)) {
 				return -EINVAL;
+			}
 		}
 
 		ret = xe_pt_insert_entry(xe_walk, xe_parent, offset, NULL, pte);
@@ -534,13 +547,16 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 		*child = &xe_child->base;
 
 		/*
-		 * Prefer the compact pagetable layout for L0 if possible.
+		 * Prefer the compact pagetable layout for L0 if possible. Only
+		 * possible if VMA covers entire 2MB region as compact 64k and
+		 * 4k pages cannot be mixed within a 2MB region.
 		 * TODO: Suballocate the pt bo to avoid wasting a lot of
 		 * memory.
 		 */
 		if (GRAPHICS_VERx100(tile_to_xe(xe_walk->tile)) >= 1250 && level == 1 &&
 		    covers && xe_pt_scan_64K(addr, next, xe_walk)) {
 			walk->shifts = xe_compact_pt_shifts;
+			xe_walk->vma->gpuva.flags |= XE_VMA_PTE_COMPACT;
 			flags |= XE_PDE_64K;
 			xe_child->is_compact = true;
 		}
@@ -618,8 +634,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 
 	if (!xe_vma_is_null(vma)) {
 		if (xe_vma_is_userptr(vma))
-			xe_res_first_sg(vma->userptr.sg, 0, xe_vma_size(vma),
-					&curs);
+			xe_res_first_sg(to_userptr_vma(vma)->userptr.sg, 0,
+					xe_vma_size(vma), &curs);
 		else if (xe_bo_is_vram(bo) || xe_bo_is_stolen(bo))
 			xe_res_first(bo->ttm.resource, xe_vma_bo_offset(vma),
 				     xe_vma_size(vma), &curs);
@@ -853,7 +869,7 @@ static void xe_pt_commit_bind(struct xe_vma *vma,
 				xe_pt_destroy(xe_pt_entry(pt_dir, j_),
 					      xe_vma_vm(vma)->flags, deferred);
 
-			pt_dir->dir.entries[j_] = &newpte->base;
+			pt_dir->children[j_] = &newpte->base;
 		}
 		kfree(entries[i].pt_entries);
 	}
@@ -906,17 +922,17 @@ static void xe_vm_dbg_print_entries(struct xe_device *xe,
 
 #ifdef CONFIG_DRM_XE_USERPTR_INVAL_INJECT
 
-static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static int xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
-	u32 divisor = vma->userptr.divisor ? vma->userptr.divisor : 2;
+	u32 divisor = uvma->userptr.divisor ? uvma->userptr.divisor : 2;
 	static u32 count;
 
 	if (count++ % divisor == divisor - 1) {
-		struct xe_vm *vm = xe_vma_vm(vma);
+		struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 
-		vma->userptr.divisor = divisor << 1;
+		uvma->userptr.divisor = divisor << 1;
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&uvma->userptr.invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 		return true;
@@ -927,7 +943,7 @@ static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
 
 #else
 
-static bool xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static bool xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
 	return false;
 }
@@ -1000,9 +1016,9 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 {
 	struct xe_pt_migrate_pt_update *userptr_update =
 		container_of(pt_update, typeof(*userptr_update), base);
-	struct xe_vma *vma = pt_update->vma;
-	unsigned long notifier_seq = vma->userptr.notifier_seq;
-	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_userptr_vma *uvma = to_userptr_vma(pt_update->vma);
+	unsigned long notifier_seq = uvma->userptr.notifier_seq;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 	int err = xe_pt_vm_dependencies(pt_update->job,
 					&vm->rftree[pt_update->tile_id],
 					pt_update->start,
@@ -1023,7 +1039,7 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 	 */
 	do {
 		down_read(&vm->userptr.notifier_lock);
-		if (!mmu_interval_read_retry(&vma->userptr.notifier,
+		if (!mmu_interval_read_retry(&uvma->userptr.notifier,
 					     notifier_seq))
 			break;
 
@@ -1032,11 +1048,11 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 		if (userptr_update->bind)
 			return -EAGAIN;
 
-		notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
+		notifier_seq = mmu_interval_read_begin(&uvma->userptr.notifier);
 	} while (true);
 
 	/* Inject errors to test_whether they are handled correctly */
-	if (userptr_update->bind && xe_pt_userptr_inject_eagain(vma)) {
+	if (userptr_update->bind && xe_pt_userptr_inject_eagain(uvma)) {
 		up_read(&vm->userptr.notifier_lock);
 		return -EAGAIN;
 	}
@@ -1297,7 +1313,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 		vma->tile_present |= BIT(tile->id);
 
 		if (bind_pt_update.locked) {
-			vma->userptr.initial_bind = true;
+			to_userptr_vma(vma)->userptr.initial_bind = true;
 			up_read(&vm->userptr.notifier_lock);
 			xe_bo_put_commit(&deferred);
 		}
@@ -1507,7 +1523,7 @@ xe_pt_commit_unbind(struct xe_vma *vma,
 					xe_pt_destroy(xe_pt_entry(pt_dir, i),
 						      xe_vma_vm(vma)->flags, deferred);
 
-				pt_dir->dir.entries[i] = NULL;
+				pt_dir->children[i] = NULL;
 			}
 		}
 	}
@@ -1642,7 +1658,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
 
 		if (!vma->tile_present) {
 			spin_lock(&vm->userptr.invalidated_lock);
-			list_del_init(&vma->userptr.invalidate_link);
+			list_del_init(&to_userptr_vma(vma)->userptr.invalidate_link);
 			spin_unlock(&vm->userptr.invalidated_lock);
 		}
 		up_read(&vm->userptr.notifier_lock);
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index 8f6c8d063f39..b8b3d2aea492 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,7 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
 		     u64 addr, u64 end, struct xe_pt_walk *walk)
 {
 	pgoff_t offset = xe_pt_offset(addr, level, walk);
-	struct xe_ptw **entries = parent->dir ? parent->dir->entries : NULL;
+	struct xe_ptw **entries = parent->children ? parent->children : NULL;
 	const struct xe_pt_walk_ops *ops = walk->ops;
 	enum page_walk_action action;
 	struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index ec3d1e9efa6d..5ecc4d2f0f65 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -8,28 +8,15 @@
 #include <linux/pagewalk.h>
 #include <linux/types.h>
 
-struct xe_ptw_dir;
-
 /**
  * struct xe_ptw - base class for driver pagetable subclassing.
- * @dir: Pointer to an array of children if any.
+ * @children: Pointer to an array of children if any.
  *
  * Drivers could subclass this, and if it's a page-directory, typically
- * embed the xe_ptw_dir::entries array in the same allocation.
+ * embed an array of xe_ptw pointers.
  */
 struct xe_ptw {
-	struct xe_ptw_dir *dir;
-};
-
-/**
- * struct xe_ptw_dir - page directory structure
- * @entries: Array holding page directory children.
- *
- * It is the responsibility of the user to ensure @entries is
- * correctly sized.
- */
-struct xe_ptw_dir {
-	struct xe_ptw *entries[0];
+	struct xe_ptw **children;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 9b35673b286c..7e924faeeea0 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -459,21 +459,21 @@ static size_t calc_topo_query_size(struct xe_device *xe)
 		 sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss));
 }
 
-static void __user *copy_mask(void __user *ptr,
-			      struct drm_xe_query_topology_mask *topo,
-			      void *mask, size_t mask_size)
+static int copy_mask(void __user **ptr,
+		     struct drm_xe_query_topology_mask *topo,
+		     void *mask, size_t mask_size)
 {
 	topo->num_bytes = mask_size;
 
-	if (copy_to_user(ptr, topo, sizeof(*topo)))
-		return ERR_PTR(-EFAULT);
-	ptr += sizeof(topo);
+	if (copy_to_user(*ptr, topo, sizeof(*topo)))
+		return -EFAULT;
+	*ptr += sizeof(topo);
 
-	if (copy_to_user(ptr, mask, mask_size))
-		return ERR_PTR(-EFAULT);
-	ptr += mask_size;
+	if (copy_to_user(*ptr, mask, mask_size))
+		return -EFAULT;
+	*ptr += mask_size;
 
-	return ptr;
+	return 0;
 }
 
 static int query_gt_topology(struct xe_device *xe,
@@ -493,28 +493,28 @@ static int query_gt_topology(struct xe_device *xe,
 	}
 
 	for_each_gt(gt, xe, id) {
+		int err;
+
 		topo.gt_id = id;
 
 		topo.type = DRM_XE_TOPO_DSS_GEOMETRY;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.g_dss_mask,
-				      sizeof(gt->fuse_topo.g_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.g_dss_mask,
+				sizeof(gt->fuse_topo.g_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_DSS_COMPUTE;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.c_dss_mask,
-				      sizeof(gt->fuse_topo.c_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.c_dss_mask,
+				sizeof(gt->fuse_topo.c_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_EU_PER_DSS;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.eu_mask_per_dss,
-				      sizeof(gt->fuse_topo.eu_mask_per_dss));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo,
+				gt->fuse_topo.eu_mask_per_dss,
+				sizeof(gt->fuse_topo.eu_mask_per_dss));
+		if (err)
+			return err;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c
index d35d9ec58e86..372378e89e98 100644
--- a/drivers/gpu/drm/xe/xe_range_fence.c
+++ b/drivers/gpu/drm/xe/xe_range_fence.c
@@ -151,6 +151,11 @@ xe_range_fence_tree_next(struct xe_range_fence *rfence, u64 start, u64 last)
 	return xe_range_fence_tree_iter_next(rfence, start, last);
 }
 
+static void xe_range_fence_free(struct xe_range_fence *rfence)
+{
+	kfree(rfence);
+}
+
 const struct xe_range_fence_ops xe_range_fence_kfree_ops = {
-	.free = (void (*)(struct xe_range_fence *rfence)) kfree,
+	.free = xe_range_fence_free,
 };
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad..4e2ccad0e52f 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
-	dma_fence_get(fence);
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115..aab92bee1d7c 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -307,7 +307,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 	/* Easy case... */
 	if (!num_in_fence) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		dma_fence_get(fence);
 		return fence;
 	}
 
@@ -322,7 +321,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		}
 	}
 	fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
-	dma_fence_get(fences[current_fence - 1]);
 	cf = dma_fence_array_create(num_in_fence, fences,
 				    vm->composite_fence_ctx,
 				    vm->composite_fence_seqno++,
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index d284afbe917c..f43cdcaca6c5 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -33,4 +33,9 @@ struct dma_fence *
 xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		     struct xe_exec_queue *q, struct xe_vm *vm);
 
+static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync)
+{
+	return !!sync->ufence;
+}
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 10b6995fbf29..921ca28d49dd 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
 #include "generated/xe_wa_oob.h"
 #include "xe_wa.h"
 
-#define TEST_VM_ASYNC_OPS_ERROR
-
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -46,7 +44,7 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 
 /**
  * xe_vma_userptr_check_repin() - Advisory check for repin needed
- * @vma: The userptr vma
+ * @uvma: The userptr vma
  *
  * Check if the userptr vma has been invalidated since last successful
  * repin. The check is advisory only and can the function can be called
@@ -56,15 +54,17 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
  *
  * Return: 0 if userptr vma is valid, -EAGAIN otherwise; repin recommended.
  */
-int xe_vma_userptr_check_repin(struct xe_vma *vma)
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma)
 {
-	return mmu_interval_check_retry(&vma->userptr.notifier,
-					vma->userptr.notifier_seq) ?
+	return mmu_interval_check_retry(&uvma->userptr.notifier,
+					uvma->userptr.notifier_seq) ?
 		-EAGAIN : 0;
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma)
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma)
 {
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct xe_device *xe = vm->xe;
 	const unsigned long num_pages = xe_vma_size(vma) >> PAGE_SHIFT;
@@ -80,30 +80,30 @@ retry:
 	if (vma->gpuva.flags & XE_VMA_DESTROYED)
 		return 0;
 
-	notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
-	if (notifier_seq == vma->userptr.notifier_seq)
+	notifier_seq = mmu_interval_read_begin(&userptr->notifier);
+	if (notifier_seq == userptr->notifier_seq)
 		return 0;
 
 	pages = kvmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
-	if (vma->userptr.sg) {
+	if (userptr->sg) {
 		dma_unmap_sgtable(xe->drm.dev,
-				  vma->userptr.sg,
+				  userptr->sg,
 				  read_only ? DMA_TO_DEVICE :
 				  DMA_BIDIRECTIONAL, 0);
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 	}
 
 	pinned = ret = 0;
 	if (in_kthread) {
-		if (!mmget_not_zero(vma->userptr.notifier.mm)) {
+		if (!mmget_not_zero(userptr->notifier.mm)) {
 			ret = -EFAULT;
 			goto mm_closed;
 		}
-		kthread_use_mm(vma->userptr.notifier.mm);
+		kthread_use_mm(userptr->notifier.mm);
 	}
 
 	while (pinned < num_pages) {
@@ -112,43 +112,40 @@ retry:
 					  num_pages - pinned,
 					  read_only ? 0 : FOLL_WRITE,
 					  &pages[pinned]);
-		if (ret < 0) {
-			if (in_kthread)
-				ret = 0;
+		if (ret < 0)
 			break;
-		}
 
 		pinned += ret;
 		ret = 0;
 	}
 
 	if (in_kthread) {
-		kthread_unuse_mm(vma->userptr.notifier.mm);
-		mmput(vma->userptr.notifier.mm);
+		kthread_unuse_mm(userptr->notifier.mm);
+		mmput(userptr->notifier.mm);
 	}
 mm_closed:
 	if (ret)
 		goto out;
 
-	ret = sg_alloc_table_from_pages_segment(&vma->userptr.sgt, pages,
+	ret = sg_alloc_table_from_pages_segment(&userptr->sgt, pages,
 						pinned, 0,
 						(u64)pinned << PAGE_SHIFT,
 						xe_sg_segment_size(xe->drm.dev),
 						GFP_KERNEL);
 	if (ret) {
-		vma->userptr.sg = NULL;
+		userptr->sg = NULL;
 		goto out;
 	}
-	vma->userptr.sg = &vma->userptr.sgt;
+	userptr->sg = &userptr->sgt;
 
-	ret = dma_map_sgtable(xe->drm.dev, vma->userptr.sg,
+	ret = dma_map_sgtable(xe->drm.dev, userptr->sg,
 			      read_only ? DMA_TO_DEVICE :
 			      DMA_BIDIRECTIONAL,
 			      DMA_ATTR_SKIP_CPU_SYNC |
 			      DMA_ATTR_NO_KERNEL_MAPPING);
 	if (ret) {
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 		goto out;
 	}
 
@@ -167,8 +164,8 @@ out:
 	kvfree(pages);
 
 	if (!(ret < 0)) {
-		vma->userptr.notifier_seq = notifier_seq;
-		if (xe_vma_userptr_check_repin(vma) == -EAGAIN)
+		userptr->notifier_seq = notifier_seq;
+		if (xe_vma_userptr_check_repin(uvma) == -EAGAIN)
 			goto retry;
 	}
 
@@ -635,7 +632,9 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				   const struct mmu_notifier_range *range,
 				   unsigned long cur_seq)
 {
-	struct xe_vma *vma = container_of(mni, struct xe_vma, userptr.notifier);
+	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
+	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
@@ -651,7 +650,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	mmu_interval_set_seq(mni, cur_seq);
 
 	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!vma->userptr.initial_bind) {
+	if (!userptr->initial_bind) {
 		up_write(&vm->userptr.notifier_lock);
 		return true;
 	}
@@ -663,7 +662,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	if (!xe_vm_in_fault_mode(vm) &&
 	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
@@ -703,7 +702,7 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
-	struct xe_vma *vma, *next;
+	struct xe_userptr_vma *uvma, *next;
 	int err = 0;
 	LIST_HEAD(tmp_evict);
 
@@ -711,22 +710,23 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
-	list_for_each_entry_safe(vma, next, &vm->userptr.invalidated,
+	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
-		list_del_init(&vma->userptr.invalidate_link);
-		list_move_tail(&vma->combined_links.userptr,
+		list_del_init(&uvma->userptr.invalidate_link);
+		list_move_tail(&uvma->userptr.repin_link,
 			       &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
 	/* Pin and move to temporary list */
-	list_for_each_entry_safe(vma, next, &vm->userptr.repin_list,
-				 combined_links.userptr) {
-		err = xe_vma_userptr_pin_pages(vma);
+	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;
 
-		list_move_tail(&vma->combined_links.userptr, &vm->rebind_list);
+		list_del_init(&uvma->userptr.repin_link);
+		list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list);
 	}
 
 	return 0;
@@ -782,6 +782,14 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
 	return fence;
 }
 
+static void xe_vma_free(struct xe_vma *vma)
+{
+	if (xe_vma_is_userptr(vma))
+		kfree(to_userptr_vma(vma));
+	else
+		kfree(vma);
+}
+
 #define VMA_CREATE_FLAG_READ_ONLY	BIT(0)
 #define VMA_CREATE_FLAG_IS_NULL		BIT(1)
 
@@ -800,14 +808,26 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	xe_assert(vm->xe, start < end);
 	xe_assert(vm->xe, end < vm->size);
 
-	if (!bo && !is_null)	/* userptr */
+	/*
+	 * Allocate and ensure that the xe_vma_is_userptr() return
+	 * matches what was allocated.
+	 */
+	if (!bo && !is_null) {
+		struct xe_userptr_vma *uvma = kzalloc(sizeof(*uvma), GFP_KERNEL);
+
+		if (!uvma)
+			return ERR_PTR(-ENOMEM);
+
+		vma = &uvma->vma;
+	} else {
 		vma = kzalloc(sizeof(*vma), GFP_KERNEL);
-	else
-		vma = kzalloc(sizeof(*vma) - sizeof(struct xe_userptr),
-			      GFP_KERNEL);
-	if (!vma) {
-		vma = ERR_PTR(-ENOMEM);
-		return vma;
+		if (!vma)
+			return ERR_PTR(-ENOMEM);
+
+		if (is_null)
+			vma->gpuva.flags |= DRM_GPUVA_SPARSE;
+		if (bo)
+			vma->gpuva.gem.obj = &bo->ttm.base;
 	}
 
 	INIT_LIST_HEAD(&vma->combined_links.rebind);
@@ -818,8 +838,6 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	vma->gpuva.va.range = end - start + 1;
 	if (read_only)
 		vma->gpuva.flags |= XE_VMA_READ_ONLY;
-	if (is_null)
-		vma->gpuva.flags |= DRM_GPUVA_SPARSE;
 
 	for_each_tile(tile, vm->xe, id)
 		vma->tile_mask |= 0x1 << id;
@@ -836,35 +854,35 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 
 		vm_bo = drm_gpuvm_bo_obtain(vma->gpuva.vm, &bo->ttm.base);
 		if (IS_ERR(vm_bo)) {
-			kfree(vma);
+			xe_vma_free(vma);
 			return ERR_CAST(vm_bo);
 		}
 
 		drm_gpuvm_bo_extobj_add(vm_bo);
 		drm_gem_object_get(&bo->ttm.base);
-		vma->gpuva.gem.obj = &bo->ttm.base;
 		vma->gpuva.gem.offset = bo_offset_or_userptr;
 		drm_gpuva_link(&vma->gpuva, vm_bo);
 		drm_gpuvm_bo_put(vm_bo);
 	} else /* userptr or null */ {
 		if (!is_null) {
+			struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
 			u64 size = end - start + 1;
 			int err;
 
-			INIT_LIST_HEAD(&vma->userptr.invalidate_link);
+			INIT_LIST_HEAD(&userptr->invalidate_link);
+			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
 
-			err = mmu_interval_notifier_insert(&vma->userptr.notifier,
+			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
 							   xe_vma_userptr(vma), size,
 							   &vma_userptr_notifier_ops);
 			if (err) {
-				kfree(vma);
-				vma = ERR_PTR(err);
-				return vma;
+				xe_vma_free(vma);
+				return ERR_PTR(err);
 			}
 
-			vma->userptr.notifier_seq = LONG_MAX;
+			userptr->notifier_seq = LONG_MAX;
 		}
 
 		xe_vm_get(vm);
@@ -880,13 +898,15 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 	bool read_only = xe_vma_read_only(vma);
 
 	if (xe_vma_is_userptr(vma)) {
-		if (vma->userptr.sg) {
+		struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
+
+		if (userptr->sg) {
 			dma_unmap_sgtable(xe->drm.dev,
-					  vma->userptr.sg,
+					  userptr->sg,
 					  read_only ? DMA_TO_DEVICE :
 					  DMA_BIDIRECTIONAL, 0);
-			sg_free_table(vma->userptr.sg);
-			vma->userptr.sg = NULL;
+			sg_free_table(userptr->sg);
+			userptr->sg = NULL;
 		}
 
 		/*
@@ -894,7 +914,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * the notifer until we're sure the GPU is not accessing
 		 * them anymore
 		 */
-		mmu_interval_notifier_remove(&vma->userptr.notifier);
+		mmu_interval_notifier_remove(&userptr->notifier);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
@@ -902,7 +922,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		xe_bo_put(xe_vma_bo(vma));
 	}
 
-	kfree(vma);
+	xe_vma_free(vma);
 }
 
 static void vma_destroy_work_func(struct work_struct *w)
@@ -933,7 +953,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del(&vma->userptr.invalidate_link);
+		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {
 		xe_bo_assert_held(xe_vma_bo(vma));
@@ -975,9 +995,16 @@ int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
 	int err;
 
 	XE_WARN_ON(!vm);
-	err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
-	if (!err && bo && !bo->vm)
-		err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+	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);
+	}
 
 	return err;
 }
@@ -1855,10 +1882,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&xef->vm.lock);
 	err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->vm.lock);
-	if (err) {
-		xe_vm_close_and_put(vm);
-		return err;
-	}
+	if (err)
+		goto err_close_and_put;
 
 	if (xe->info.has_asid) {
 		mutex_lock(&xe->usm.lock);
@@ -1866,11 +1891,9 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 				      XA_LIMIT(1, XE_MAX_ASID - 1),
 				      &xe->usm.next_asid, GFP_KERNEL);
 		mutex_unlock(&xe->usm.lock);
-		if (err < 0) {
-			xe_vm_close_and_put(vm);
-			return err;
-		}
-		err = 0;
+		if (err < 0)
+			goto err_free_id;
+
 		vm->usm.asid = asid;
 	}
 
@@ -1888,6 +1911,15 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 #endif
 
 	return 0;
+
+err_free_id:
+	mutex_lock(&xef->vm.lock);
+	xa_erase(&xef->vm.xa, id);
+	mutex_unlock(&xef->vm.lock);
+err_close_and_put:
+	xe_vm_close_and_put(vm);
+
+	return err;
 }
 
 int xe_vm_destroy_ioctl(struct drm_device *dev, void *data,
@@ -1954,6 +1986,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 					xe_exec_queue_last_fence_get(wait_exec_queue, vm);
 
 				xe_sync_entry_signal(&syncs[i], NULL, fence);
+				dma_fence_put(fence);
 			}
 		}
 
@@ -2034,7 +2067,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *__op;
-	struct xe_vma_op *op;
 	struct drm_gpuvm_bo *vm_bo;
 	int err;
 
@@ -2081,15 +2113,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	if (IS_ERR(ops))
 		return ops;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (operation & FORCE_ASYNC_OP_ERROR) {
-		op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
-					      base.entry);
-		if (op)
-			op->inject_error = true;
-	}
-#endif
-
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
 
@@ -2145,7 +2168,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
 		drm_exec_fini(&exec);
 
 	if (xe_vma_is_userptr(vma)) {
-		err = xe_vma_userptr_pin_pages(vma);
+		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
 		if (err) {
 			prep_vma_destroy(vm, vma, false);
 			xe_vma_destroy_unlocked(vma);
@@ -2167,13 +2190,17 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
 {
 	if (vma->gpuva.flags & XE_VMA_PTE_1G)
 		return SZ_1G;
-	else if (vma->gpuva.flags & XE_VMA_PTE_2M)
+	else if (vma->gpuva.flags & (XE_VMA_PTE_2M | XE_VMA_PTE_COMPACT))
 		return SZ_2M;
+	else if (vma->gpuva.flags & XE_VMA_PTE_64K)
+		return SZ_64K;
+	else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+		return SZ_4K;
 
-	return SZ_4K;
+	return SZ_1G;	/* Uninitialized, used max size */
 }
 
-static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
+static void xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
 {
 	switch (size) {
 	case SZ_1G:
@@ -2182,9 +2209,13 @@ static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
 	case SZ_2M:
 		vma->gpuva.flags |= XE_VMA_PTE_2M;
 		break;
+	case SZ_64K:
+		vma->gpuva.flags |= XE_VMA_PTE_64K;
+		break;
+	case SZ_4K:
+		vma->gpuva.flags |= XE_VMA_PTE_4K;
+		break;
 	}
-
-	return SZ_4K;
 }
 
 static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
@@ -2500,13 +2531,25 @@ retry_userptr:
 	}
 	drm_exec_fini(&exec);
 
-	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+	if (err == -EAGAIN) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(vma);
-		if (!err)
-			goto retry_userptr;
 
-		trace_xe_vma_fail(vma);
+		if (op->base.op == DRM_GPUVA_OP_REMAP) {
+			if (!op->remap.unmap_done)
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+			else if (op->remap.prev)
+				vma = op->remap.prev;
+			else
+				vma = op->remap.next;
+		}
+
+		if (xe_vma_is_userptr(vma)) {
+			err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+			if (!err)
+				goto retry_userptr;
+
+			trace_xe_vma_fail(vma);
+		}
 	}
 
 	return err;
@@ -2518,13 +2561,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
 
 	lockdep_assert_held_write(&vm->lock);
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (op->inject_error) {
-		op->inject_error = false;
-		return -ENOMEM;
-	}
-#endif
-
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2639,7 +2675,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
 {
 	int i;
 
-	for (i = num_ops_list - 1; i; ++i) {
+	for (i = num_ops_list - 1; i >= 0; --i) {
 		struct drm_gpuva_ops *__ops = ops[i];
 		struct drm_gpuva_op *__op;
 
@@ -2684,16 +2720,9 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	return 0;
 }
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS	\
-	(FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
 #define SUPPORTED_FLAGS	\
 	(DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
-	 0xffff)
-#endif
+	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL)
 #define XE_64K_PAGE_MASK 0xffffull
 #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
 
@@ -2846,7 +2875,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct drm_gpuva_ops **ops = NULL;
 	struct xe_vm *vm;
 	struct xe_exec_queue *q = NULL;
-	u32 num_syncs;
+	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
 	struct drm_xe_vm_bind_op *bind_ops;
 	LIST_HEAD(ops_list);
@@ -2983,6 +3012,14 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_DISALLOW_USER_FENCE : 0));
 		if (err)
 			goto free_syncs;
+
+		if (xe_sync_is_ufence(&syncs[num_syncs]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto free_syncs;
 	}
 
 	if (!args->num_binds) {
@@ -3125,8 +3162,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		if (xe_vma_is_userptr(vma)) {
 			WARN_ON_ONCE(!mmu_interval_check_retry
-				     (&vma->userptr.notifier,
-				      vma->userptr.notifier_seq));
+				     (&to_userptr_vma(vma)->userptr.notifier,
+				      to_userptr_vma(vma)->userptr.notifier_seq));
 			WARN_ON_ONCE(!dma_resv_test_signaled(xe_vm_resv(xe_vma_vm(vma)),
 							     DMA_RESV_USAGE_BOOKKEEP));
 
@@ -3187,11 +3224,11 @@ int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id)
 		if (is_null) {
 			addr = 0;
 		} else if (is_userptr) {
+			struct sg_table *sg = to_userptr_vma(vma)->userptr.sg;
 			struct xe_res_cursor cur;
 
-			if (vma->userptr.sg) {
-				xe_res_first_sg(vma->userptr.sg, 0, XE_PAGE_SIZE,
-						&cur);
+			if (sg) {
+				xe_res_first_sg(sg, 0, XE_PAGE_SIZE, &cur);
 				addr = xe_res_dma(&cur);
 			} else {
 				addr = 0;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index cf2f96e8c1ab..9654a0612fc2 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -160,6 +160,18 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
 	return xe_vma_has_no_bo(vma) && !xe_vma_is_null(vma);
 }
 
+/**
+ * to_userptr_vma() - Return a pointer to an embedding userptr vma
+ * @vma: Pointer to the embedded struct xe_vma
+ *
+ * Return: Pointer to the embedding userptr vma
+ */
+static inline struct xe_userptr_vma *to_userptr_vma(struct xe_vma *vma)
+{
+	xe_assert(xe_vma_vm(vma)->xe, xe_vma_is_userptr(vma));
+	return container_of(vma, struct xe_userptr_vma, vma);
+}
+
 u64 xe_vm_pdp4_descriptor(struct xe_vm *vm, struct xe_tile *tile);
 
 int xe_vm_create_ioctl(struct drm_device *dev, void *data,
@@ -224,9 +236,9 @@ static inline void xe_vm_reactivate_rebind(struct xe_vm *vm)
 	}
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma);
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma);
 
-int xe_vma_userptr_check_repin(struct xe_vma *vma);
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma);
 
 bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 63e8a50b88e9..a603cc2eb56b 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -21,9 +21,6 @@ struct xe_bo;
 struct xe_sync_entry;
 struct xe_vm;
 
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR	BIT(31)
-
 #define XE_VMA_READ_ONLY	DRM_GPUVA_USERBITS
 #define XE_VMA_DESTROYED	(DRM_GPUVA_USERBITS << 1)
 #define XE_VMA_ATOMIC_PTE_BIT	(DRM_GPUVA_USERBITS << 2)
@@ -32,11 +29,15 @@ struct xe_vm;
 #define XE_VMA_PTE_4K		(DRM_GPUVA_USERBITS << 5)
 #define XE_VMA_PTE_2M		(DRM_GPUVA_USERBITS << 6)
 #define XE_VMA_PTE_1G		(DRM_GPUVA_USERBITS << 7)
+#define XE_VMA_PTE_64K		(DRM_GPUVA_USERBITS << 8)
+#define XE_VMA_PTE_COMPACT	(DRM_GPUVA_USERBITS << 9)
 
 /** struct xe_userptr - User pointer */
 struct xe_userptr {
 	/** @invalidate_link: Link for the vm::userptr.invalidated list */
 	struct list_head invalidate_link;
+	/** @userptr: link into VM repin list if userptr. */
+	struct list_head repin_link;
 	/**
 	 * @notifier: MMU notifier for user pointer (invalidation call back)
 	 */
@@ -68,8 +69,6 @@ struct xe_vma {
 	 * resv.
 	 */
 	union {
-		/** @userptr: link into VM repin list if userptr. */
-		struct list_head userptr;
 		/** @rebind: link into VM if this VMA needs rebinding. */
 		struct list_head rebind;
 		/** @destroy: link to contested list when VM is being closed. */
@@ -105,11 +104,15 @@ struct xe_vma {
 	 * @pat_index: The pat index to use when encoding the PTEs for this vma.
 	 */
 	u16 pat_index;
+};
 
-	/**
-	 * @userptr: user pointer state, only allocated for VMAs that are
-	 * user pointers
-	 */
+/**
+ * struct xe_userptr_vma - A userptr vma subclass
+ * @vma: The vma.
+ * @userptr: Additional userptr information.
+ */
+struct xe_userptr_vma {
+	struct xe_vma vma;
 	struct xe_userptr userptr;
 };
 
@@ -356,11 +359,6 @@ struct xe_vma_op {
 	/** @flags: operation flags */
 	enum xe_vma_op_flags flags;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	/** @inject_error: inject error to test async op error handling */
-	bool inject_error;
-#endif
-
 	union {
 		/** @map: VMA map operation specific data */
 		struct xe_vma_op_map map;