diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index e67c194..649f17d 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -206,6 +206,7 @@
 config DRM_RADEON
 	tristate "ATI Radeon"
 	depends on DRM && PCI && MMU
+	depends on AGP || !AGP
 	select FW_LOADER
         select DRM_KMS_HELPER
         select DRM_TTM
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index bd37df5..1b2fa83 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -762,7 +762,7 @@
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	8
+#define HWIP_MAX_INSTANCE	10
 
 struct amd_powerplay {
 	void *pp_handle;
@@ -813,6 +813,7 @@
 	uint8_t				*bios;
 	uint32_t			bios_size;
 	struct amdgpu_bo		*stolen_vga_memory;
+	struct amdgpu_bo		*discovery_memory;
 	uint32_t			bios_scratch_reg_offset;
 	uint32_t			bios_scratch[AMDGPU_BIOS_NUM_SCRATCH];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index 82155ac..64ee44c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -163,17 +163,28 @@
 	return 0;
 }
 
-static struct device *get_mfd_cell_dev(const char *device_name, int r)
+static int acp_genpd_add_device(struct device *dev, void *data)
 {
-	char auto_dev_name[25];
-	struct device *dev;
+	struct generic_pm_domain *gpd = data;
+	int ret;
 
-	snprintf(auto_dev_name, sizeof(auto_dev_name),
-		 "%s.%d.auto", device_name, r);
-	dev = bus_find_device_by_name(&platform_bus_type, NULL, auto_dev_name);
-	dev_info(dev, "device %s added to pm domain\n", auto_dev_name);
+	ret = pm_genpd_add_device(gpd, dev);
+	if (ret)
+		dev_err(dev, "Failed to add dev to genpd %d\n", ret);
 
-	return dev;
+	return ret;
+}
+
+static int acp_genpd_remove_device(struct device *dev, void *data)
+{
+	int ret;
+
+	ret = pm_genpd_remove_device(dev);
+	if (ret)
+		dev_err(dev, "Failed to remove dev from genpd %d\n", ret);
+
+	/* Continue to remove */
+	return 0;
 }
 
 /**
@@ -184,11 +195,10 @@
  */
 static int acp_hw_init(void *handle)
 {
-	int r, i;
+	int r;
 	uint64_t acp_base;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -344,15 +354,10 @@
 	if (r)
 		goto failure;
 
-	for (i = 0; i < ACP_DEVS ; i++) {
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-		r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
-		if (r) {
-			dev_err(dev, "Failed to add dev to genpd\n");
-			goto failure;
-		}
-	}
-
+	r = device_for_each_child(adev->acp.parent, &adev->acp.acp_genpd->gpd,
+				  acp_genpd_add_device);
+	if (r)
+		goto failure;
 
 	/* Assert Soft reset of ACP */
 	val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
@@ -413,10 +418,8 @@
  */
 static int acp_hw_fini(void *handle)
 {
-	int i, ret;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* return early if no ACP */
@@ -461,13 +464,8 @@
 		udelay(100);
 	}
 
-	for (i = 0; i < ACP_DEVS ; i++) {
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-		ret = pm_genpd_remove_device(dev);
-		/* If removal fails, dont giveup and try rest */
-		if (ret)
-			dev_err(dev, "remove dev from genpd failed\n");
-	}
+	device_for_each_child(adev->acp.parent, NULL,
+			      acp_genpd_remove_device);
 
 	mfd_remove_devices(adev->acp.parent);
 	kfree(adev->acp.acp_res);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index d10f483..ce30d4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -644,6 +644,9 @@
 	uint32_t temp;
 	struct v10_compute_mqd *m = get_mqd(mqd);
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+		return 0;
+
 #if 0
 	unsigned long flags;
 	int retry;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index e262f2a..92754cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -540,6 +540,9 @@
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+		return 0;
+
 	if (adev->in_gpu_reset)
 		return -EIO;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6d021ec..25af45a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -55,12 +55,6 @@
 	spinlock_t mem_limit_lock;
 } kfd_mem_limit;
 
-/* Struct used for amdgpu_amdkfd_bo_validate */
-struct amdgpu_vm_parser {
-	uint32_t        domain;
-	bool            wait;
-};
-
 static const char * const domain_bit_to_string[] = {
 		"CPU",
 		"GTT",
@@ -293,11 +287,9 @@
 	return ret;
 }
 
-static int amdgpu_amdkfd_validate(void *param, struct amdgpu_bo *bo)
+static int amdgpu_amdkfd_validate_vm_bo(void *_unused, struct amdgpu_bo *bo)
 {
-	struct amdgpu_vm_parser *p = param;
-
-	return amdgpu_amdkfd_bo_validate(bo, p->domain, p->wait);
+	return amdgpu_amdkfd_bo_validate(bo, bo->allowed_domains, false);
 }
 
 /* vm_validate_pt_pd_bos - Validate page table and directory BOs
@@ -311,20 +303,15 @@
 {
 	struct amdgpu_bo *pd = vm->root.base.bo;
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
-	struct amdgpu_vm_parser param;
 	int ret;
 
-	param.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	param.wait = false;
-
-	ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate,
-					&param);
+	ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate_vm_bo, NULL);
 	if (ret) {
 		pr_err("amdgpu: failed to validate PT BOs\n");
 		return ret;
 	}
 
-	ret = amdgpu_amdkfd_validate(&param, pd);
+	ret = amdgpu_amdkfd_validate_vm_bo(NULL, pd);
 	if (ret) {
 		pr_err("amdgpu: failed to validate PD\n");
 		return ret;
@@ -1247,15 +1234,15 @@
 	 * be freed anyway
 	 */
 
-	/* No more MMU notifiers */
-	amdgpu_mn_unregister(mem->bo);
-
 	/* Make sure restore workers don't access the BO any more */
 	bo_list_entry = &mem->validate_list;
 	mutex_lock(&process_info->lock);
 	list_del(&bo_list_entry->head);
 	mutex_unlock(&process_info->lock);
 
+	/* No more MMU notifiers */
+	amdgpu_mn_unregister(mem->bo);
+
 	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);
 	if (unlikely(ret))
 		return ret;
@@ -1288,7 +1275,7 @@
 	}
 
 	/* Free the BO*/
-	amdgpu_bo_unref(&mem->bo);
+	drm_gem_object_put_unlocked(&mem->bo->tbo.base);
 	mutex_destroy(&mem->lock);
 	kfree(mem);
 
@@ -1630,7 +1617,8 @@
 		AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
 		AMDGPU_VM_PAGE_EXECUTABLE | AMDGPU_VM_MTYPE_NC;
 
-	(*mem)->bo = amdgpu_bo_ref(bo);
+	drm_gem_object_get(&bo->tbo.base);
+	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
 		AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 1c9d40f..c687432 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -338,17 +338,9 @@
 		path_size += le16_to_cpu(path->usSize);
 
 		if (device_support & le16_to_cpu(path->usDeviceTag)) {
-			uint8_t con_obj_id, con_obj_num, con_obj_type;
-
-			con_obj_id =
+			uint8_t con_obj_id =
 			    (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK)
 			    >> OBJECT_ID_SHIFT;
-			con_obj_num =
-			    (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK)
-			    >> ENUM_ID_SHIFT;
-			con_obj_type =
-			    (le16_to_cpu(path->usConnObjectId) &
-			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
 			/* Skip TV/CV support */
 			if ((le16_to_cpu(path->usDeviceTag) ==
@@ -373,15 +365,7 @@
 			router.ddc_valid = false;
 			router.cd_valid = false;
 			for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) {
-				uint8_t grph_obj_id, grph_obj_num, grph_obj_type;
-
-				grph_obj_id =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-				grph_obj_num =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     ENUM_ID_MASK) >> ENUM_ID_SHIFT;
-				grph_obj_type =
+				uint8_t grph_obj_type =
 				    (le16_to_cpu(path->usGraphicObjIds[j]) &
 				     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index daf6874..663314f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -150,6 +150,7 @@
 				(mode_info->atom_context->bios + data_offset);
 			switch (crev) {
 			case 11:
+			case 12:
 				mem_channel_number = igp_info->v11.umachannelnumber;
 				/* channel width is 64 */
 				return mem_channel_number * 64;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 50dff69..b1172d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -192,30 +192,35 @@
 
 static bool amdgpu_read_platform_bios(struct amdgpu_device *adev)
 {
-	uint8_t __iomem *bios;
-	size_t size;
+	phys_addr_t rom = adev->pdev->rom;
+	size_t romlen = adev->pdev->romlen;
+	void __iomem *bios;
 
 	adev->bios = NULL;
 
-	bios = pci_platform_rom(adev->pdev, &size);
-	if (!bios) {
-		return false;
-	}
-
-	adev->bios = kzalloc(size, GFP_KERNEL);
-	if (adev->bios == NULL)
+	if (!rom || romlen == 0)
 		return false;
 
-	memcpy_fromio(adev->bios, bios, size);
-
-	if (!check_atom_bios(adev->bios, size)) {
-		kfree(adev->bios);
+	adev->bios = kzalloc(romlen, GFP_KERNEL);
+	if (!adev->bios)
 		return false;
-	}
 
-	adev->bios_size = size;
+	bios = ioremap(rom, romlen);
+	if (!bios)
+		goto free_bios;
+
+	memcpy_fromio(adev->bios, bios, romlen);
+	iounmap(bios);
+
+	if (!check_atom_bios(adev->bios, romlen))
+		goto free_bios;
+
+	adev->bios_size = romlen;
 
 	return true;
+free_bios:
+	kfree(adev->bios);
+	return false;
 }
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index ece55c8..cda0a76 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -719,8 +719,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (encoder) {
@@ -857,8 +859,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	encoder = amdgpu_connector_best_single_encoder(connector);
@@ -980,8 +984,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
@@ -1330,8 +1336,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 2cdaf3b..39ca071 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -351,7 +351,6 @@
 {
 	struct amdgpu_ctx *ctx;
 	struct amdgpu_ctx_mgr *mgr;
-	unsigned long ras_counter;
 
 	if (!fpriv)
 		return -EINVAL;
@@ -376,21 +375,6 @@
 	if (atomic_read(&ctx->guilty))
 		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY;
 
-	/*query ue count*/
-	ras_counter = amdgpu_ras_query_error_count(adev, false);
-	/*ras counter is monotonic increasing*/
-	if (ras_counter != ctx->ras_counter_ue) {
-		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_UE;
-		ctx->ras_counter_ue = ras_counter;
-	}
-
-	/*query ce count*/
-	ras_counter = amdgpu_ras_query_error_count(adev, true);
-	if (ras_counter != ctx->ras_counter_ce) {
-		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_CE;
-		ctx->ras_counter_ce = ras_counter;
-	}
-
 	mutex_unlock(&mgr->lock);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 5652cc7..a9a81e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -240,7 +240,7 @@
 	while (size) {
 		uint32_t value;
 
-		value = RREG32_PCIE(*pos >> 2);
+		value = RREG32_PCIE(*pos);
 		r = put_user(value, (uint32_t *)buf);
 		if (r)
 			return r;
@@ -283,7 +283,7 @@
 		if (r)
 			return r;
 
-		WREG32_PCIE(*pos >> 2, value);
+		WREG32_PCIE(*pos, value);
 
 		result += 4;
 		buf += 4;
@@ -694,11 +694,11 @@
 	ssize_t result = 0;
 	uint32_t offset, se, sh, cu, wave, simd, thread, bank, *data;
 
-	if (size & 3 || *pos & 3)
+	if (size > 4096 || size & 3 || *pos & 3)
 		return -EINVAL;
 
 	/* decode offset */
-	offset = *pos & GENMASK_ULL(11, 0);
+	offset = (*pos & GENMASK_ULL(11, 0)) >> 2;
 	se = (*pos & GENMASK_ULL(19, 12)) >> 12;
 	sh = (*pos & GENMASK_ULL(27, 20)) >> 20;
 	cu = (*pos & GENMASK_ULL(35, 28)) >> 28;
@@ -729,7 +729,7 @@
 	while (size) {
 		uint32_t value;
 
-		value = data[offset++];
+		value = data[result >> 2];
 		r = put_user(value, (uint32_t *)buf);
 		if (r) {
 			result = r;
@@ -859,6 +859,9 @@
 	struct amdgpu_device *adev = dev->dev_private;
 	int r = 0, i;
 
+	/* Avoid accidently unparking the sched thread during GPU reset */
+	mutex_lock(&adev->lock_reset);
+
 	/* hold on the scheduler */
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -884,6 +887,8 @@
 		kthread_unpark(ring->sched.thread);
 	}
 
+	mutex_unlock(&adev->lock_reset);
+
 	return 0;
 }
 
@@ -985,27 +990,37 @@
 static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring)
 {
 	struct amdgpu_job *job;
-	struct drm_sched_job *s_job;
+	struct drm_sched_job *s_job, *tmp;
 	uint32_t preempt_seq;
 	struct dma_fence *fence, **ptr;
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
 	struct drm_gpu_scheduler *sched = &ring->sched;
+	bool preempted = true;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
 		return;
 
 	preempt_seq = le32_to_cpu(*(drv->cpu_addr + 2));
-	if (preempt_seq <= atomic_read(&drv->last_seq))
-		return;
+	if (preempt_seq <= atomic_read(&drv->last_seq)) {
+		preempted = false;
+		goto no_preempt;
+	}
 
 	preempt_seq &= drv->num_fences_mask;
 	ptr = &drv->fences[preempt_seq];
 	fence = rcu_dereference_protected(*ptr, 1);
 
+no_preempt:
 	spin_lock(&sched->job_list_lock);
-	list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		if (dma_fence_is_signaled(&s_job->s_fence->finished)) {
+			/* remove job from ring_mirror_list */
+			list_del_init(&s_job->node);
+			sched->ops->free_job(s_job);
+			continue;
+		}
 		job = to_amdgpu_job(s_job);
-		if (job->fence == fence)
+		if (preempted && job->fence == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
@@ -1036,6 +1051,9 @@
 	if (!fences)
 		return -ENOMEM;
 
+	/* Avoid accidently unparking the sched thread during GPU reset */
+	mutex_lock(&adev->lock_reset);
+
 	/* stop the scheduler */
 	kthread_park(ring->sched.thread);
 
@@ -1075,6 +1093,8 @@
 	/* restart the scheduler */
 	kthread_unpark(ring->sched.thread);
 
+	mutex_unlock(&adev->lock_reset);
+
 	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
 
 	if (fences)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7a6c837..d0e1fd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2057,11 +2057,11 @@
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_remove_device(adev);
 
-	amdgpu_amdkfd_device_fini(adev);
-
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
+	amdgpu_amdkfd_device_fini(adev);
+
 	/* need to disable SMC first */
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.hw)
@@ -2291,7 +2291,7 @@
 		AMD_IP_BLOCK_TYPE_IH,
 	};
 
-	for (i = 0; i < ARRAY_SIZE(ip_order); i++) {
+	for (i = 0; i < adev->num_ip_blocks; i++) {
 		int j;
 		struct amdgpu_ip_block *block;
 
@@ -3070,12 +3070,12 @@
 		}
 	}
 
-	amdgpu_amdkfd_suspend(adev);
-
 	amdgpu_ras_suspend(adev);
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
+	amdgpu_amdkfd_suspend(adev);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
@@ -3704,7 +3704,6 @@
 			r = amdgpu_ib_ring_tests(tmp_adev);
 			if (r) {
 				dev_err(tmp_adev->dev, "ib ring test failed (%d).\n", r);
-				r = amdgpu_device_ip_suspend(tmp_adev);
 				need_full_reset = true;
 				r = -EAGAIN;
 				goto end;
@@ -3890,7 +3889,7 @@
 
 		amdgpu_device_lock_adev(tmp_adev, false);
 		r = amdgpu_device_pre_asic_reset(tmp_adev,
-						 NULL,
+						 (tmp_adev == adev) ? job : NULL,
 						 &need_full_reset);
 		/*TODO Should we stop ?*/
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 1481899..71198c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -136,7 +136,7 @@
 {
 	uint32_t *p = (uint32_t *)binary;
 	uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
-	uint64_t pos = vram_size - BINARY_MAX_SIZE;
+	uint64_t pos = vram_size - DISCOVERY_TMR_SIZE;
 	unsigned long flags;
 
 	while (pos < vram_size) {
@@ -179,7 +179,7 @@
 	uint16_t checksum;
 	int r;
 
-	adev->discovery = kzalloc(BINARY_MAX_SIZE, GFP_KERNEL);
+	adev->discovery = kzalloc(DISCOVERY_TMR_SIZE, GFP_KERNEL);
 	if (!adev->discovery)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
index 85b8c4d..5a6693d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
@@ -24,6 +24,8 @@
 #ifndef __AMDGPU_DISCOVERY__
 #define __AMDGPU_DISCOVERY__
 
+#define DISCOVERY_TMR_SIZE  (64 << 10)
+
 int amdgpu_discovery_init(struct amdgpu_device *adev);
 void amdgpu_discovery_fini(struct amdgpu_device *adev);
 int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 82efc1e..b588e0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -282,7 +282,7 @@
 
 	ret = pm_runtime_get_sync(dev->dev);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = drm_crtc_helper_set_config(set, ctx);
 
@@ -306,6 +306,7 @@
 		adev->have_disp_power_ref = false;
 	}
 
+out:
 	/* drop the power reference we got coming in here */
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b19157b..e8e1720 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -145,7 +145,7 @@
 int amdgpu_mcbp = 0;
 int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
-int amdgpu_noretry = 1;
+int amdgpu_noretry;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
@@ -613,7 +613,7 @@
 module_param_named(mes, amdgpu_mes, int, 0444);
 
 MODULE_PARM_DESC(noretry,
-	"Disable retry faults (0 = retry enabled, 1 = retry disabled (default))");
+	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
 module_param_named(noretry, amdgpu_noretry, int, 0644);
 
 #ifdef CONFIG_HSA_AMD
@@ -1011,6 +1011,7 @@
 	{0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x731E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	/* Navi14 */
 	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
@@ -1023,6 +1024,7 @@
 
 	/* Navi12 */
 	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
 
 	{0, 0, 0}
 };
@@ -1285,11 +1287,12 @@
 	dev = file_priv->minor->dev;
 	ret = pm_runtime_get_sync(dev->dev);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = drm_ioctl(filp, cmd, arg);
 
 	pm_runtime_mark_last_busy(dev->dev);
+out:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
 }
@@ -1420,7 +1423,7 @@
 
 static struct drm_driver kms_driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_ATOMIC |
+	    DRIVER_ATOMIC |
 	    DRIVER_GEM |
 	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ,
 	.load = amdgpu_driver_load_kms,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 143753d..4652280 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -133,8 +133,7 @@
 	u32 cpp;
 	u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 			       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS     |
-			       AMDGPU_GEM_CREATE_VRAM_CLEARED 	     |
-			       AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+			       AMDGPU_GEM_CREATE_VRAM_CLEARED;
 
 	info = drm_get_format_info(adev->ddev, mode_cmd);
 	cpp = info->cpp[0];
@@ -147,7 +146,7 @@
 	size = mode_cmd->pitches[0] * height;
 	aligned_size = ALIGN(size, PAGE_SIZE);
 	ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain, flags,
-				       ttm_bo_type_kernel, NULL, &gobj);
+				       ttm_bo_type_device, NULL, &gobj);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
 		return -ENOMEM;
@@ -290,10 +289,13 @@
 static int amdgpu_fbdev_destroy(struct drm_device *dev, struct amdgpu_fbdev *rfbdev)
 {
 	struct amdgpu_framebuffer *rfb = &rfbdev->rfb;
+	int i;
 
 	drm_fb_helper_unregister_fbi(&rfbdev->helper);
 
 	if (rfb->base.obj[0]) {
+		for (i = 0; i < rfb->base.format->num_planes; i++)
+			drm_gem_object_put(rfb->base.obj[0]);
 		amdgpufb_destroy_pinned_object(rfb->base.obj[0]);
 		rfb->base.obj[0] = NULL;
 		drm_framebuffer_unregister_private(&rfb->base);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 23085b3..c212d5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -404,7 +404,9 @@
 		ring->fence_drv.gpu_addr = adev->uvd.inst[ring->me].gpu_addr + index;
 	}
 	amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq));
-	amdgpu_irq_get(adev, irq_src, irq_type);
+
+	if (irq_src)
+		amdgpu_irq_get(adev, irq_src, irq_type);
 
 	ring->fence_drv.irq_src = irq_src;
 	ring->fence_drv.irq_type = irq_type;
@@ -539,8 +541,9 @@
 			/* no need to trigger GPU reset as we are unloading */
 			amdgpu_fence_driver_force_completion(ring);
 		}
-		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
-			       ring->fence_drv.irq_type);
+		if (ring->fence_drv.irq_src)
+			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
+				       ring->fence_drv.irq_type);
 		drm_sched_fini(&ring->sched);
 		del_timer_sync(&ring->fence_drv.fallback_timer);
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
@@ -576,8 +579,9 @@
 		}
 
 		/* disable the interrupt */
-		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
-			       ring->fence_drv.irq_type);
+		if (ring->fence_drv.irq_src)
+			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
+				       ring->fence_drv.irq_type);
 	}
 }
 
@@ -603,8 +607,9 @@
 			continue;
 
 		/* enable the interrupt */
-		amdgpu_irq_get(adev, ring->fence_drv.irq_src,
-			       ring->fence_drv.irq_type);
+		if (ring->fence_drv.irq_src)
+			amdgpu_irq_get(adev, ring->fence_drv.irq_src,
+				       ring->fence_drv.irq_type);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 8ceb449..9d61d1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -161,16 +161,17 @@
 
 	struct amdgpu_bo_list_entry vm_pd;
 	struct list_head list, duplicates;
+	struct dma_fence *fence = NULL;
 	struct ttm_validate_buffer tv;
 	struct ww_acquire_ctx ticket;
 	struct amdgpu_bo_va *bo_va;
-	int r;
+	long r;
 
 	INIT_LIST_HEAD(&list);
 	INIT_LIST_HEAD(&duplicates);
 
 	tv.bo = &bo->tbo;
-	tv.num_shared = 1;
+	tv.num_shared = 2;
 	list_add(&tv.head, &list);
 
 	amdgpu_vm_get_pd_bo(vm, &list, &vm_pd);
@@ -178,28 +179,34 @@
 	r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates, false);
 	if (r) {
 		dev_err(adev->dev, "leaking bo va because "
-			"we fail to reserve bo (%d)\n", r);
+			"we fail to reserve bo (%ld)\n", r);
 		return;
 	}
 	bo_va = amdgpu_vm_bo_find(vm, bo);
-	if (bo_va && --bo_va->ref_count == 0) {
-		amdgpu_vm_bo_rmv(adev, bo_va);
+	if (!bo_va || --bo_va->ref_count)
+		goto out_unlock;
 
-		if (amdgpu_vm_ready(vm)) {
-			struct dma_fence *fence = NULL;
+	amdgpu_vm_bo_rmv(adev, bo_va);
+	if (!amdgpu_vm_ready(vm))
+		goto out_unlock;
 
-			r = amdgpu_vm_clear_freed(adev, vm, &fence);
-			if (unlikely(r)) {
-				dev_err(adev->dev, "failed to clear page "
-					"tables on GEM object close (%d)\n", r);
-			}
-
-			if (fence) {
-				amdgpu_bo_fence(bo, fence, true);
-				dma_fence_put(fence);
-			}
-		}
+	fence = dma_resv_get_excl(bo->tbo.base.resv);
+	if (fence) {
+		amdgpu_bo_fence(bo, fence, true);
+		fence = NULL;
 	}
+
+	r = amdgpu_vm_clear_freed(adev, vm, &fence);
+	if (r || !fence)
+		goto out_unlock;
+
+	amdgpu_bo_fence(bo, fence, true);
+	dma_fence_put(fence);
+
+out_unlock:
+	if (unlikely(r < 0))
+		dev_err(adev->dev, "failed to clear page "
+			"tables on GEM object close (%ld)\n", r);
 	ttm_eu_backoff_reservation(&ticket, &list);
 }
 
@@ -554,6 +561,7 @@
 	struct ww_acquire_ctx ticket;
 	struct list_head list, duplicates;
 	uint64_t va_flags;
+	uint64_t vm_size;
 	int r = 0;
 
 	if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
@@ -574,6 +582,15 @@
 
 	args->va_address &= AMDGPU_GMC_HOLE_MASK;
 
+	vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
+	vm_size -= AMDGPU_VA_RESERVED_SIZE;
+	if (args->va_address + args->map_size > vm_size) {
+		dev_dbg(&dev->pdev->dev,
+			"va_address 0x%llx is in top reserved area 0x%llx\n",
+			args->va_address + args->map_size, vm_size);
+		return -EINVAL;
+	}
+
 	if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) {
 		dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n",
 			args->flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index b6e1d98..8c0ac66 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -77,6 +77,7 @@
 struct amdgpu_vmhub {
 	uint32_t	ctx0_ptb_addr_lo32;
 	uint32_t	ctx0_ptb_addr_hi32;
+	uint32_t	vm_inv_eng0_sem;
 	uint32_t	vm_inv_eng0_req;
 	uint32_t	vm_inv_eng0_ack;
 	uint32_t	vm_context0_cntl;
@@ -156,6 +157,7 @@
 	uint32_t                srbm_soft_reset;
 	bool			prt_warning;
 	uint64_t		stolen_size;
+	uint32_t		sdpif_register;
 	/* apertures */
 	u64			shared_aperture_start;
 	u64			shared_aperture_end;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index 70dbe34..89cecdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -339,7 +339,7 @@
 void
 amdgpu_i2c_router_select_ddc_port(const struct amdgpu_connector *amdgpu_connector)
 {
-	u8 val;
+	u8 val = 0;
 
 	if (!amdgpu_connector->router.ddc_valid)
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 2a3f5ec..7642993 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -469,7 +469,7 @@
 		for (j = 0; j < AMDGPU_MAX_IRQ_SRC_ID; ++j) {
 			struct amdgpu_irq_src *src = adev->irq.client[i].sources[j];
 
-			if (!src)
+			if (!src || !src->funcs || !src->funcs->set)
 				continue;
 			for (k = 0; k < src->num_types; k++)
 				amdgpu_irq_update(adev, src, k);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 96b2a31..f06a514 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -36,7 +36,8 @@
 
 	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
-	if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
+	if (amdgpu_gpu_recovery &&
+	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
 			  s_job->sched->name);
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index a732067..59fd9eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -638,8 +638,12 @@
 		 * in the bitfields */
 		if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK)
 			se_num = 0xffffffff;
+		else if (se_num >= AMDGPU_GFX_MAX_SE)
+			return -EINVAL;
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
+		else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE)
+			return -EINVAL;
 
 		if (info->read_mmr_reg.count > 128)
 			return -EINVAL;
@@ -667,9 +671,10 @@
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info = {};
+		struct drm_amdgpu_info_device dev_info;
 		uint64_t vm_size;
 
+		memset(&dev_info, 0, sizeof(dev_info));
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
 		dev_info.external_rev = adev->external_rev_id;
@@ -975,7 +980,7 @@
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0)
-		return r;
+		goto pm_put;
 
 	fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
 	if (unlikely(!fpriv)) {
@@ -1026,6 +1031,7 @@
 
 out_suspend:
 	pm_runtime_mark_last_busy(dev->dev);
+pm_put:
 	pm_runtime_put_autosuspend(dev->dev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 7289e1b..532d184 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -200,7 +200,7 @@
 		c++;
 	}
 
-	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+	BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS);
 
 	placement->num_placement = c;
 	placement->placement = places;
@@ -343,6 +343,67 @@
 }
 
 /**
+ * amdgpu_bo_create_kernel_at - create BO for kernel use at specific location
+ *
+ * @adev: amdgpu device object
+ * @offset: offset of the BO
+ * @size: size of the BO
+ * @domain: where to place it
+ * @bo_ptr:  used to initialize BOs in structures
+ * @cpu_addr: optional CPU address mapping
+ *
+ * Creates a kernel BO at a specific offset in the address space of the domain.
+ *
+ * Returns:
+ * 0 on success, negative error code otherwise.
+ */
+int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev,
+			       uint64_t offset, uint64_t size, uint32_t domain,
+			       struct amdgpu_bo **bo_ptr, void **cpu_addr)
+{
+	struct ttm_operation_ctx ctx = { false, false };
+	unsigned int i;
+	int r;
+
+	offset &= PAGE_MASK;
+	size = ALIGN(size, PAGE_SIZE);
+
+	r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, domain, bo_ptr,
+				      NULL, NULL);
+	if (r)
+		return r;
+
+	/*
+	 * Remove the original mem node and create a new one at the request
+	 * position.
+	 */
+	for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) {
+		(*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT;
+		(*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
+	}
+
+	ttm_bo_mem_put(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem);
+	r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement,
+			     &(*bo_ptr)->tbo.mem, &ctx);
+	if (r)
+		goto error;
+
+	if (cpu_addr) {
+		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
+		if (r)
+			goto error;
+	}
+
+	amdgpu_bo_unreserve(*bo_ptr);
+	return 0;
+
+error:
+	amdgpu_bo_unreserve(*bo_ptr);
+	amdgpu_bo_unref(bo_ptr);
+	return r;
+}
+
+/**
  * amdgpu_bo_free_kernel - free BO for kernel use
  *
  * @bo: amdgpu BO to free
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 658f4c9..4fcea23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -237,6 +237,9 @@
 			    unsigned long size, int align,
 			    u32 domain, struct amdgpu_bo **bo_ptr,
 			    u64 *gpu_addr, void **cpu_addr);
+int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev,
+			       uint64_t offset, uint64_t size, uint32_t domain,
+			       struct amdgpu_bo **bo_ptr, void **cpu_addr);
 void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr,
 			   void **cpu_addr);
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 0393031..bcb7ab5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -90,7 +90,8 @@
 			adev->pm.ac_power = true;
 		else
 			adev->pm.ac_power = false;
-		if (adev->powerplay.pp_funcs->enable_bapm)
+		if (adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->enable_bapm)
 			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
 		mutex_unlock(&adev->pm.mutex);
 	}
@@ -369,6 +370,15 @@
 	if (current_level == level)
 		return count;
 
+	if (adev->asic_type == CHIP_RAVEN) {
+		if (adev->rev_id < 8) {
+			if (current_level != AMD_DPM_FORCED_LEVEL_MANUAL && level == AMD_DPM_FORCED_LEVEL_MANUAL)
+				amdgpu_gfx_off_ctrl(adev, false);
+			else if (current_level == AMD_DPM_FORCED_LEVEL_MANUAL && level != AMD_DPM_FORCED_LEVEL_MANUAL)
+				amdgpu_gfx_off_ctrl(adev, true);
+		}
+	}
+
 	/* profile_exit setting is valid only when current mode is in profile mode */
 	if (!(current_level & (AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
 	    AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
@@ -415,8 +425,11 @@
 		ret = smu_get_power_num_states(&adev->smu, &data);
 		if (ret)
 			return ret;
-	} else if (adev->powerplay.pp_funcs->get_pp_num_states)
+	} else if (adev->powerplay.pp_funcs->get_pp_num_states) {
 		amdgpu_dpm_get_pp_num_states(adev, &data);
+	} else {
+		memset(&data, 0, sizeof(data));
+	}
 
 	buf_len = snprintf(buf, PAGE_SIZE, "states: %d\n", data.nums);
 	for (i = 0; i < data.nums; i++)
@@ -857,7 +870,7 @@
 static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask)
 {
 	int ret;
-	long level;
+	unsigned long level;
 	char *sub_str = NULL;
 	char *tmp;
 	char buf_cpy[AMDGPU_MASK_BUF_MAX + 1];
@@ -873,8 +886,8 @@
 	while (tmp[0]) {
 		sub_str = strsep(&tmp, delimiter);
 		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
-			if (ret)
+			ret = kstrtoul(sub_str, 0, &level);
+			if (ret || level > 31)
 				return -EINVAL;
 			*mask |= 1 << level;
 		} else
@@ -2088,7 +2101,7 @@
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev,
@@ -2118,7 +2131,7 @@
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 016ea27..9c5cbc4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -65,12 +65,6 @@
 /* inject address is 52 bits */
 #define	RAS_UMC_INJECT_ADDR_LIMIT	(0x1ULL << 52)
 
-static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev,
-		uint64_t offset, uint64_t size,
-		struct amdgpu_bo **bo_ptr);
-static int amdgpu_ras_release_vram(struct amdgpu_device *adev,
-		struct amdgpu_bo **bo_ptr);
-
 static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -1214,75 +1208,6 @@
 	atomic_set(&ras->in_recovery, 0);
 }
 
-static int amdgpu_ras_release_vram(struct amdgpu_device *adev,
-		struct amdgpu_bo **bo_ptr)
-{
-	/* no need to free it actually. */
-	amdgpu_bo_free_kernel(bo_ptr, NULL, NULL);
-	return 0;
-}
-
-/* reserve vram with size@offset */
-static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev,
-		uint64_t offset, uint64_t size,
-		struct amdgpu_bo **bo_ptr)
-{
-	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_bo_param bp;
-	int r = 0;
-	int i;
-	struct amdgpu_bo *bo;
-
-	if (bo_ptr)
-		*bo_ptr = NULL;
-	memset(&bp, 0, sizeof(bp));
-	bp.size = size;
-	bp.byte_align = PAGE_SIZE;
-	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	bp.flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
-		AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
-	bp.type = ttm_bo_type_kernel;
-	bp.resv = NULL;
-
-	r = amdgpu_bo_create(adev, &bp, &bo);
-	if (r)
-		return -EINVAL;
-
-	r = amdgpu_bo_reserve(bo, false);
-	if (r)
-		goto error_reserve;
-
-	offset = ALIGN(offset, PAGE_SIZE);
-	for (i = 0; i < bo->placement.num_placement; ++i) {
-		bo->placements[i].fpfn = offset >> PAGE_SHIFT;
-		bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
-	}
-
-	ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem);
-	r = ttm_bo_mem_space(&bo->tbo, &bo->placement, &bo->tbo.mem, &ctx);
-	if (r)
-		goto error_pin;
-
-	r = amdgpu_bo_pin_restricted(bo,
-			AMDGPU_GEM_DOMAIN_VRAM,
-			offset,
-			offset + size);
-	if (r)
-		goto error_pin;
-
-	if (bo_ptr)
-		*bo_ptr = bo;
-
-	amdgpu_bo_unreserve(bo);
-	return r;
-
-error_pin:
-	amdgpu_bo_unreserve(bo);
-error_reserve:
-	amdgpu_bo_unref(&bo);
-	return r;
-}
-
 /* alloc/realloc bps array */
 static int amdgpu_ras_realloc_eh_data_space(struct amdgpu_device *adev,
 		struct ras_err_handler_data *data, int pages)
@@ -1345,7 +1270,7 @@
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
 	uint64_t bp;
-	struct amdgpu_bo *bo;
+	struct amdgpu_bo *bo = NULL;
 	int i;
 
 	if (!con || !con->eh_data)
@@ -1359,12 +1284,14 @@
 	for (i = data->last_reserved; i < data->count; i++) {
 		bp = data->bps[i].bp;
 
-		if (amdgpu_ras_reserve_vram(adev, bp << PAGE_SHIFT,
-					PAGE_SIZE, &bo))
+		if (amdgpu_bo_create_kernel_at(adev, bp << PAGE_SHIFT, PAGE_SIZE,
+					       AMDGPU_GEM_DOMAIN_VRAM,
+					       &bo, NULL))
 			DRM_ERROR("RAS ERROR: reserve vram %llx fail\n", bp);
 
 		data->bps[i].bo = bo;
 		data->last_reserved = i + 1;
+		bo = NULL;
 	}
 out:
 	mutex_unlock(&con->recovery_lock);
@@ -1390,7 +1317,7 @@
 	for (i = data->last_reserved - 1; i >= 0; i--) {
 		bo = data->bps[i].bo;
 
-		amdgpu_ras_release_vram(adev, &bo);
+		amdgpu_bo_free_kernel(&bo, NULL, NULL);
 
 		data->bps[i].bo = bo;
 		data->last_reserved = i;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 8a32b5c..bd7ae3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -138,7 +138,7 @@
 		return ret;
 	}
 
-	__decode_table_header_from_buff(hdr, &buff[2]);
+	__decode_table_header_from_buff(hdr, buff);
 
 	if (hdr->header == EEPROM_TABLE_HDR_VAL) {
 		control->num_recs = (hdr->tbl_size - EEPROM_TABLE_HEADER_SIZE) /
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
index c8793e6..6373bfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -124,13 +124,12 @@
  */
 int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev)
 {
-	volatile u32 *dst_ptr;
 	u32 dws;
 	int r;
 
 	/* allocate clear state block */
 	adev->gfx.rlc.clear_state_size = dws = adev->gfx.rlc.funcs->get_csb_size(adev);
-	r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE,
+	r = amdgpu_bo_create_kernel(adev, dws * 4, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &adev->gfx.rlc.clear_state_obj,
 				      &adev->gfx.rlc.clear_state_gpu_addr,
@@ -141,13 +140,6 @@
 		return r;
 	}
 
-	/* set up the cs buffer */
-	dst_ptr = adev->gfx.rlc.cs_ptr;
-	adev->gfx.rlc.funcs->get_csb_buffer(adev, dst_ptr);
-	amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
-	amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index b66d29d..b158230 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -138,6 +138,7 @@
 		}
 
 		dma_fence_put(fence);
+		fence = NULL;
 
 		r = amdgpu_bo_kmap(vram_obj, &vram_map);
 		if (r) {
@@ -183,6 +184,7 @@
 		}
 
 		dma_fence_put(fence);
+		fence = NULL;
 
 		r = amdgpu_bo_kmap(gtt_obj[i], &gtt_map);
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 77674a7..e813221 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -21,7 +21,7 @@
  *
  */
 
-#if !defined(_AMDGPU_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_AMDGPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
 #define _AMDGPU_TRACE_H_
 
 #include <linux/stringify.h>
@@ -170,7 +170,7 @@
 			     __field(unsigned int, context)
 			     __field(unsigned int, seqno)
 			     __field(struct dma_fence *, fence)
-			     __field(char *, ring_name)
+			     __string(ring, to_amdgpu_ring(job->base.sched)->name)
 			     __field(u32, num_ibs)
 			     ),
 
@@ -179,12 +179,12 @@
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
+			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name)
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
 		      __entry->sched_job_id, __get_str(timeline), __entry->context,
-		      __entry->seqno, __entry->ring_name, __entry->num_ibs)
+		      __entry->seqno, __get_str(ring), __entry->num_ibs)
 );
 
 TRACE_EVENT(amdgpu_sched_run_job,
@@ -195,7 +195,7 @@
 			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			     __field(unsigned int, context)
 			     __field(unsigned int, seqno)
-			     __field(char *, ring_name)
+			     __string(ring, to_amdgpu_ring(job->base.sched)->name)
 			     __field(u32, num_ibs)
 			     ),
 
@@ -204,12 +204,12 @@
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
+			   __assign_str(ring, to_amdgpu_ring(job->base.sched)->name)
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
 		      __entry->sched_job_id, __get_str(timeline), __entry->context,
-		      __entry->seqno, __entry->ring_name, __entry->num_ibs)
+		      __entry->seqno, __get_str(ring), __entry->num_ibs)
 );
 
 
@@ -468,7 +468,7 @@
 	    TP_PROTO(struct amdgpu_job *sched_job, struct dma_fence *fence),
 	    TP_ARGS(sched_job, fence),
 	    TP_STRUCT__entry(
-			     __field(const char *,name)
+			     __string(ring, sched_job->base.sched->name);
 			     __field(uint64_t, id)
 			     __field(struct dma_fence *, fence)
 			     __field(uint64_t, ctx)
@@ -476,14 +476,14 @@
 			     ),
 
 	    TP_fast_assign(
-			   __entry->name = sched_job->base.sched->name;
+			   __assign_str(ring, sched_job->base.sched->name)
 			   __entry->id = sched_job->base.id;
 			   __entry->fence = fence;
 			   __entry->ctx = fence->context;
 			   __entry->seqno = fence->seqno;
 			   ),
 	    TP_printk("job ring=%s, id=%llu, need pipe sync to fence=%p, context=%llu, seq=%u",
-		      __entry->name, __entry->id,
+		      __get_str(ring), __entry->id,
 		      __entry->fence, __entry->ctx,
 		      __entry->seqno)
 );
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index dff41d0..58e14d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -35,6 +35,7 @@
 #include <linux/hmm.h>
 #include <linux/pagemap.h>
 #include <linux/sched/task.h>
+#include <linux/sched/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -788,7 +789,7 @@
 	struct hmm_mirror *mirror = bo->mn ? &bo->mn->mirror : NULL;
 	struct ttm_tt *ttm = bo->tbo.ttm;
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	struct mm_struct *mm = gtt->usertask->mm;
+	struct mm_struct *mm;
 	unsigned long start = gtt->userptr;
 	struct vm_area_struct *vma;
 	struct hmm_range *range;
@@ -796,25 +797,14 @@
 	uint64_t *pfns;
 	int r = 0;
 
-	if (!mm) /* Happens during process shutdown */
-		return -ESRCH;
-
 	if (unlikely(!mirror)) {
 		DRM_DEBUG_DRIVER("Failed to get hmm_mirror\n");
-		r = -EFAULT;
-		goto out;
+		return -EFAULT;
 	}
 
-	vma = find_vma(mm, start);
-	if (unlikely(!vma || start < vma->vm_start)) {
-		r = -EFAULT;
-		goto out;
-	}
-	if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) &&
-		vma->vm_file)) {
-		r = -EPERM;
-		goto out;
-	}
+	mm = mirror->hmm->mmu_notifier.mm;
+	if (!mmget_not_zero(mm)) /* Happens during process shutdown */
+		return -ESRCH;
 
 	range = kzalloc(sizeof(*range), GFP_KERNEL);
 	if (unlikely(!range)) {
@@ -847,6 +837,17 @@
 	hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT);
 
 	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+	if (unlikely(!vma || start < vma->vm_start)) {
+		r = -EFAULT;
+		goto out_unlock;
+	}
+	if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) &&
+		vma->vm_file)) {
+		r = -EPERM;
+		goto out_unlock;
+	}
+
 	r = hmm_range_fault(range, 0);
 	up_read(&mm->mmap_sem);
 
@@ -865,15 +866,19 @@
 	}
 
 	gtt->range = range;
+	mmput(mm);
 
 	return 0;
 
+out_unlock:
+	up_read(&mm->mmap_sem);
 out_free_pfns:
 	hmm_range_unregister(range);
 	kvfree(pfns);
 out_free_ranges:
 	kfree(range);
 out:
+	mmput(mm);
 	return r;
 }
 
@@ -962,6 +967,7 @@
 
 release_sg:
 	kfree(ttm->sg);
+	ttm->sg = NULL;
 	return r;
 }
 
@@ -978,7 +984,7 @@
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
 
 	/* double check that we don't free the table twice */
-	if (!ttm->sg->sgl)
+	if (!ttm->sg || !ttm->sg->sgl)
 		return;
 
 	/* unmap the pages mapped to the device */
@@ -1294,6 +1300,7 @@
 	if (gtt && gtt->userptr) {
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
 		kfree(ttm->sg);
+		ttm->sg = NULL;
 		ttm->page_flags &= ~TTM_PAGE_FLAG_SG;
 		return;
 	}
@@ -1634,81 +1641,25 @@
  */
 static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 {
-	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_bo_param bp;
-	int r = 0;
-	int i;
-	u64 vram_size = adev->gmc.visible_vram_size;
-	u64 offset = adev->fw_vram_usage.start_offset;
-	u64 size = adev->fw_vram_usage.size;
-	struct amdgpu_bo *bo;
+	uint64_t vram_size = adev->gmc.visible_vram_size;
+	int r;
 
-	memset(&bp, 0, sizeof(bp));
-	bp.size = adev->fw_vram_usage.size;
-	bp.byte_align = PAGE_SIZE;
-	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-		AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
-	bp.type = ttm_bo_type_kernel;
-	bp.resv = NULL;
 	adev->fw_vram_usage.va = NULL;
 	adev->fw_vram_usage.reserved_bo = NULL;
 
-	if (adev->fw_vram_usage.size > 0 &&
-		adev->fw_vram_usage.size <= vram_size) {
+	if (adev->fw_vram_usage.size == 0 ||
+	    adev->fw_vram_usage.size > vram_size)
+		return 0;
 
-		r = amdgpu_bo_create(adev, &bp,
-				     &adev->fw_vram_usage.reserved_bo);
-		if (r)
-			goto error_create;
-
-		r = amdgpu_bo_reserve(adev->fw_vram_usage.reserved_bo, false);
-		if (r)
-			goto error_reserve;
-
-		/* remove the original mem node and create a new one at the
-		 * request position
-		 */
-		bo = adev->fw_vram_usage.reserved_bo;
-		offset = ALIGN(offset, PAGE_SIZE);
-		for (i = 0; i < bo->placement.num_placement; ++i) {
-			bo->placements[i].fpfn = offset >> PAGE_SHIFT;
-			bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
-		}
-
-		ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem);
-		r = ttm_bo_mem_space(&bo->tbo, &bo->placement,
-				     &bo->tbo.mem, &ctx);
-		if (r)
-			goto error_pin;
-
-		r = amdgpu_bo_pin_restricted(adev->fw_vram_usage.reserved_bo,
-			AMDGPU_GEM_DOMAIN_VRAM,
-			adev->fw_vram_usage.start_offset,
-			(adev->fw_vram_usage.start_offset +
-			adev->fw_vram_usage.size));
-		if (r)
-			goto error_pin;
-		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
-			&adev->fw_vram_usage.va);
-		if (r)
-			goto error_kmap;
-
-		amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
-	}
-	return r;
-
-error_kmap:
-	amdgpu_bo_unpin(adev->fw_vram_usage.reserved_bo);
-error_pin:
-	amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
-error_reserve:
-	amdgpu_bo_unref(&adev->fw_vram_usage.reserved_bo);
-error_create:
-	adev->fw_vram_usage.va = NULL;
-	adev->fw_vram_usage.reserved_bo = NULL;
+	return amdgpu_bo_create_kernel_at(adev,
+					  adev->fw_vram_usage.start_offset,
+					  adev->fw_vram_usage.size,
+					  AMDGPU_GEM_DOMAIN_VRAM,
+					  &adev->fw_vram_usage.reserved_bo,
+					  &adev->fw_vram_usage.va);
 	return r;
 }
+
 /**
  * amdgpu_ttm_init - Init the memory management (ttm) as well as various
  * gtt/vram related fields.
@@ -1781,6 +1732,20 @@
 				    NULL, &stolen_vga_buf);
 	if (r)
 		return r;
+
+	/*
+	 * reserve one TMR (64K) memory at the top of VRAM which holds
+	 * IP Discovery data and is protected by PSP.
+	 */
+	r = amdgpu_bo_create_kernel_at(adev,
+				       adev->gmc.real_vram_size - DISCOVERY_TMR_SIZE,
+				       DISCOVERY_TMR_SIZE,
+				       AMDGPU_GEM_DOMAIN_VRAM,
+				       &adev->discovery_memory,
+				       NULL);
+	if (r)
+		return r;
+
 	DRM_INFO("amdgpu: %uM of VRAM memory ready\n",
 		 (unsigned) (adev->gmc.real_vram_size / (1024 * 1024)));
 
@@ -1845,6 +1810,9 @@
 	void *stolen_vga_buf;
 	/* return the VGA stolen memory (if any) back to VRAM */
 	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf);
+
+	/* return the IP Discovery TMR memory back to VRAM */
+	amdgpu_bo_free_kernel(&adev->discovery_memory, NULL, NULL);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index b2c364b..cfa8324 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -231,7 +231,7 @@
 		if ((adev->asic_type == CHIP_POLARIS10 ||
 		     adev->asic_type == CHIP_POLARIS11) &&
 		    (adev->uvd.fw_version < FW_1_66_16))
-			DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n",
+			DRM_ERROR("POLARIS10/11 UVD firmware version %u.%u is too old.\n",
 				  version_major, version_minor);
 	} else {
 		unsigned int enc_major, enc_minor, dec_minor;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5251352..fb47ddc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1034,10 +1034,8 @@
 		id->oa_base != job->oa_base ||
 		id->oa_size != job->oa_size);
 	bool vm_flush_needed = job->vm_needs_flush;
-	bool pasid_mapping_needed = id->pasid != job->pasid ||
-		!id->pasid_mapping ||
-		!dma_fence_is_signaled(id->pasid_mapping);
 	struct dma_fence *fence = NULL;
+	bool pasid_mapping_needed = false;
 	unsigned patch_offset = 0;
 	int r;
 
@@ -1047,6 +1045,12 @@
 		pasid_mapping_needed = true;
 	}
 
+	mutex_lock(&id_mgr->lock);
+	if (id->pasid != job->pasid || !id->pasid_mapping ||
+	    !dma_fence_is_signaled(id->pasid_mapping))
+		pasid_mapping_needed = true;
+	mutex_unlock(&id_mgr->lock);
+
 	gds_switch_needed &= !!ring->funcs->emit_gds_switch;
 	vm_flush_needed &= !!ring->funcs->emit_vm_flush  &&
 			job->vm_pd_addr != AMDGPU_BO_INVALID_OFFSET;
@@ -1086,9 +1090,11 @@
 	}
 
 	if (pasid_mapping_needed) {
+		mutex_lock(&id_mgr->lock);
 		id->pasid = job->pasid;
 		dma_fence_put(id->pasid_mapping);
 		id->pasid_mapping = dma_fence_get(fence);
+		mutex_unlock(&id_mgr->lock);
 	}
 	dma_fence_put(fence);
 
@@ -2117,8 +2123,8 @@
 	uint64_t eaddr;
 
 	/* validate the parameters */
-	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+	    size == 0 || size & ~PAGE_MASK)
 		return -EINVAL;
 
 	/* make sure object fit at this offset */
@@ -2182,8 +2188,8 @@
 	int r;
 
 	/* validate the parameters */
-	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+	    size == 0 || size & ~PAGE_MASK)
 		return -EINVAL;
 
 	/* make sure object fit at this offset */
@@ -2327,7 +2333,7 @@
 			after->start = eaddr + 1;
 			after->last = tmp->last;
 			after->offset = tmp->offset;
-			after->offset += after->start - tmp->start;
+			after->offset += (after->start - tmp->start) << PAGE_SHIFT;
 			after->flags = tmp->flags;
 			after->bo_va = tmp->bo_va;
 			list_add(&after->list, &tmp->bo_va->invalids);
@@ -2861,10 +2867,17 @@
 	WARN_ONCE((vm->use_cpu_for_update && !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 
-	if (vm->use_cpu_for_update)
+	if (vm->use_cpu_for_update) {
+		/* Sync with last SDMA update/clear before switching to CPU */
+		r = amdgpu_bo_sync_wait(vm->root.base.bo,
+					AMDGPU_FENCE_OWNER_UNDEFINED, true);
+		if (r)
+			goto free_idr;
+
 		vm->update_funcs = &amdgpu_vm_cpu_funcs;
-	else
+	} else {
 		vm->update_funcs = &amdgpu_vm_sdma_funcs;
+	}
 	dma_fence_put(vm->last_update);
 	vm->last_update = NULL;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 2eda3a8..4a64825 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -105,8 +105,8 @@
 #define AMDGPU_MMHUB_0				1
 #define AMDGPU_MMHUB_1				2
 
-/* hardcode that limit for now */
-#define AMDGPU_VA_RESERVED_SIZE			(1ULL << 20)
+/* Reserve 2MB at top/bottom of address space for kernel use */
+#define AMDGPU_VA_RESERVED_SIZE			(2ULL << 20)
 
 /* max vmids dedicated for process */
 #define AMDGPU_VM_MAX_RESERVED_VMID	1
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 65aae75..ce1048b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -311,15 +311,22 @@
 }
 
 
+/*
+ * NOTE psp_xgmi_node_info.num_hops layout is as follows:
+ * num_hops[7:6] = link type (0 = xGMI2, 1 = xGMI3, 2/3 = reserved)
+ * num_hops[5:3] = reserved
+ * num_hops[2:0] = number of hops
+ */
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
 		struct amdgpu_device *peer_adev)
 {
 	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+	uint8_t num_hops_mask = 0x7;
 	int i;
 
 	for (i = 0 ; i < top->num_nodes; ++i)
 		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
-			return top->nodes[i].num_hops;
+			return top->nodes[i].num_hops & num_hops_mask;
 	return	-EINVAL;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index dd30f4e..cae426c 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -744,8 +744,8 @@
 			cjiffies = jiffies;
 			if (time_after(cjiffies, ctx->last_jump_jiffies)) {
 				cjiffies -= ctx->last_jump_jiffies;
-				if ((jiffies_to_msecs(cjiffies) > 5000)) {
-					DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n");
+				if ((jiffies_to_msecs(cjiffies) > 10000)) {
+					DRM_ERROR("atombios stuck in loop for more than 10secs aborting\n");
 					ctx->abort = true;
 				}
 			} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index c45304f..450ad7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -228,7 +228,7 @@
 	u32 extra_bits = vmid & 0xf;
 
 	/* IB packet must end on a 8 DW boundary */
-	cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	cik_sdma_ring_insert_nop(ring, (4 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
 	amdgpu_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
@@ -811,7 +811,7 @@
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1071,22 +1071,19 @@
 {
 	u32 srbm_soft_reset = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	u32 tmp = RREG32(mmSRBM_STATUS2);
+	u32 tmp;
 
-	if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) {
-		/* sdma0 */
-		tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
-		tmp |= SDMA0_F32_CNTL__HALT_MASK;
-		WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
-		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
-	}
-	if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) {
-		/* sdma1 */
-		tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
-		tmp |= SDMA0_F32_CNTL__HALT_MASK;
-		WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
-		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
-	}
+	/* sdma0 */
+	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
+	tmp |= SDMA0_F32_CNTL__HALT_MASK;
+	WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
+	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
+
+	/* sdma1 */
+	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
+	tmp |= SDMA0_F32_CNTL__HALT_MASK;
+	WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
+	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
 
 	if (srbm_soft_reset) {
 		tmp = RREG32(mmSRBM_SOFT_RESET);
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index 1dca0ca..13520d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -193,19 +193,30 @@
 
 	wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) {
-		wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
-		/* When a ring buffer overflow happen start parsing interrupt
-		 * from the last not overwritten vector (wptr + 16). Hopefully
-		 * this should allow us to catchup.
-		 */
-		dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
-			wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
-		ih->rptr = (wptr + 16) & ih->ptr_mask;
-		tmp = RREG32(mmIH_RB_CNTL);
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
-		WREG32(mmIH_RB_CNTL, tmp);
-	}
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	/* Double check that the overflow wasn't already cleared. */
+	wptr = RREG32(mmIH_RB_WPTR);
+
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
+
+	/* When a ring buffer overflow happen start parsing interrupt
+	 * from the last not overwritten vector (wptr + 16). Hopefully
+	 * this should allow us to catchup.
+	 */
+	dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
+		wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
+	ih->rptr = (wptr + 16) & ih->ptr_mask;
+	tmp = RREG32(mmIH_RB_CNTL);
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
+	WREG32(mmIH_RB_CNTL, tmp);
+
+
+out:
 	return (wptr & ih->ptr_mask);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 5850c8e..97d11d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -261,23 +261,29 @@
 {
 	u32 tmp;
 
-	/* Put DF on broadcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, true);
+	if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) {
+		/* Put DF on broadcast mode */
+		adev->df_funcs->enable_broadcast_mode(adev, true);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
-		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
-		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
-		tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY;
-		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
-	} else {
-		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
-		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
-		tmp |= DF_V3_6_MGCG_DISABLE;
-		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+		if (enable) {
+			tmp = RREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater);
+			tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+			tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY;
+			WREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+		} else {
+			tmp = RREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater);
+			tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+			tmp |= DF_V3_6_MGCG_DISABLE;
+			WREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+		}
+
+		/* Exit broadcast mode */
+		adev->df_funcs->enable_broadcast_mode(adev, false);
 	}
-
-	/* Exit broadcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, false);
 }
 
 static void df_v3_6_get_clockgating_state(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 53090ea..1d8739a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -190,9 +190,10 @@
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG, 0xffffffff, 0x20000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xffffffff, 0x00000420),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000200),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04800000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04900000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DFSM_TILES_IN_FLIGHT, 0x0000ffff, 0x0000003f),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_LAST_OF_BURST_CONFIG, 0xffffffff, 0x03860204),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1800ff, 0x00000044),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff0ffff, 0x00000500),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PRIV_CONTROL, 0x00007fff, 0x000001fe),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0xffffffff, 0xe4e4e4e4),
@@ -210,12 +211,13 @@
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000820, 0x00000820),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x001f0000, 0x00070104),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CNTL, 0xffdf80ff, 0x479c0010),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00800000)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00c00000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_10_1_nv14[] =
@@ -993,39 +995,6 @@
 	return 0;
 }
 
-static int gfx_v10_0_csb_vram_pin(struct amdgpu_device *adev)
-{
-	int r;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-	if (unlikely(r != 0))
-		return r;
-
-	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
-			AMDGPU_GEM_DOMAIN_VRAM);
-	if (!r)
-		adev->gfx.rlc.clear_state_gpu_addr =
-			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
-	return r;
-}
-
-static void gfx_v10_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!adev->gfx.rlc.clear_state_obj)
-		return;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
-	if (likely(r == 0)) {
-		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-	}
-}
-
 static void gfx_v10_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -1785,27 +1754,34 @@
 	WREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0, tmp);
 }
 
-static void gfx_v10_0_init_csb(struct amdgpu_device *adev)
+static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
+
 	/* csib */
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
 		     adev->gfx.rlc.clear_state_gpu_addr >> 32);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_LO,
 		     adev->gfx.rlc.clear_state_gpu_addr & 0xfffffffc);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size);
+
+	return 0;
 }
 
-static void gfx_v10_0_init_pg(struct amdgpu_device *adev)
+static int gfx_v10_0_init_pg(struct amdgpu_device *adev)
 {
 	int i;
+	int r;
 
-	gfx_v10_0_init_csb(adev);
+	r = gfx_v10_0_init_csb(adev);
+	if (r)
+		return r;
 
 	for (i = 0; i < adev->num_vmhubs; i++)
 		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
 
 	/* TODO: init power gating */
-	return;
+	return 0;
 }
 
 void gfx_v10_0_rlc_stop(struct amdgpu_device *adev)
@@ -1907,7 +1883,10 @@
 		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
 		if (r)
 			return r;
-		gfx_v10_0_init_pg(adev);
+
+		r = gfx_v10_0_init_pg(adev);
+		if (r)
+			return r;
 
 		/* enable RLC SRM */
 		gfx_v10_0_rlc_enable_srm(adev);
@@ -1933,7 +1912,10 @@
 				return r;
 		}
 
-		gfx_v10_0_init_pg(adev);
+		r = gfx_v10_0_init_pg(adev);
+		if (r)
+			return r;
+
 		adev->gfx.rlc.funcs->start(adev);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) {
@@ -2400,7 +2382,7 @@
 	return 0;
 }
 
-static void gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
+static int gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
 {
 	int i;
 	u32 tmp = RREG32_SOC15(GC, 0, mmCP_ME_CNTL);
@@ -2413,7 +2395,17 @@
 			adev->gfx.gfx_ring[i].sched.ready = false;
 	}
 	WREG32_SOC15(GC, 0, mmCP_ME_CNTL, tmp);
-	udelay(50);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (RREG32_SOC15(GC, 0, mmCP_STAT) == 0)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		DRM_ERROR("failed to %s cp gfx\n", enable ? "unhalt" : "halt");
+
+	return 0;
 }
 
 static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
@@ -3514,6 +3506,7 @@
 
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -3732,10 +3725,6 @@
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = gfx_v10_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	if (!amdgpu_emu_mode)
 		gfx_v10_0_init_golden_registers(adev);
 
@@ -3823,7 +3812,6 @@
 	}
 	gfx_v10_0_cp_enable(adev, false);
 	gfx_v10_0_enable_gui_idle_interrupt(adev, false);
-	gfx_v10_0_csb_vram_unpin(adev);
 
 	return 0;
 }
@@ -3936,11 +3924,13 @@
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
 	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
 		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
@@ -4050,10 +4040,8 @@
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
-			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
-
-		/* only for Vega10 & Raven1 */
-		data |= RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK;
+			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK |
+			  RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK);
 
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
@@ -4246,11 +4234,7 @@
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else
-			amdgpu_gfx_off_ctrl(adev, true);
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
@@ -4643,12 +4627,17 @@
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	unsigned long flags;
 
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
-	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size))
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+
+	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
+		spin_unlock_irqrestore(&kiq->ring_lock, flags);
 		return -ENOMEM;
+	}
 
 	/* assert preemption condition */
 	amdgpu_ring_set_preempt_cond_exec(ring, false);
@@ -4659,6 +4648,8 @@
 				   ++ring->trail_seq);
 	amdgpu_ring_commit(kiq_ring);
 
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
 	/* poll the trailing fence */
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (ring->trail_seq ==
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 791ba39..d92e92e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4554,6 +4554,8 @@
 
 	gfx_v7_0_constants_init(adev);
 
+	/* init CSB */
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* init rlc */
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 87dd55e..467ed7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1321,39 +1321,6 @@
 	return 0;
 }
 
-static int gfx_v8_0_csb_vram_pin(struct amdgpu_device *adev)
-{
-	int r;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-	if (unlikely(r != 0))
-		return r;
-
-	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
-			AMDGPU_GEM_DOMAIN_VRAM);
-	if (!r)
-		adev->gfx.rlc.clear_state_gpu_addr =
-			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
-	return r;
-}
-
-static void gfx_v8_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!adev->gfx.rlc.clear_state_obj)
-		return;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
-	if (likely(r == 0)) {
-		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-	}
-}
-
 static void gfx_v8_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -3917,6 +3884,7 @@
 
 static void gfx_v8_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* csib */
 	WREG32(mmRLC_CSIB_ADDR_HI,
 			adev->gfx.rlc.clear_state_gpu_addr >> 32);
@@ -4837,10 +4805,6 @@
 	gfx_v8_0_init_golden_registers(adev);
 	gfx_v8_0_constants_init(adev);
 
-	r = gfx_v8_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -4958,8 +4922,6 @@
 		pr_err("rlc is busy, skip halt rlc\n");
 	amdgpu_gfx_rlc_exit_safe_mode(adev);
 
-	gfx_v8_0_csb_vram_unpin(adev);
-
 	return 0;
 }
 
@@ -6184,7 +6146,23 @@
 	bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
 	bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
 
-	/* EVENT_WRITE_EOP - flush caches, send int */
+	/* Workaround for cache flush problems. First send a dummy EOP
+	 * event down the pipe with seq one below.
+	 */
+	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
+	amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
+				 EOP_TC_ACTION_EN |
+				 EOP_TC_WB_ACTION_EN |
+				 EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
+				 EVENT_INDEX(5)));
+	amdgpu_ring_write(ring, addr & 0xfffffffc);
+	amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
+				DATA_SEL(1) | INT_SEL(0));
+	amdgpu_ring_write(ring, lower_32_bits(seq - 1));
+	amdgpu_ring_write(ring, upper_32_bits(seq - 1));
+
+	/* Then send the real EOP event down the pipe:
+	 * EVENT_WRITE_EOP - flush caches, send int */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 	amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
 				 EOP_TC_ACTION_EN |
@@ -6926,7 +6904,7 @@
 		5 +  /* COND_EXEC */
 		7 +  /* PIPELINE_SYNC */
 		VI_FLUSH_GPU_TLB_NUM_WREG * 5 + 9 + /* VM_FLUSH */
-		8 +  /* FENCE for VM_FLUSH */
+		12 +  /* FENCE for VM_FLUSH */
 		20 + /* GDS switch */
 		4 + /* double SWITCH_BUFFER,
 		       the first COND_EXEC jump to the place just
@@ -6938,7 +6916,7 @@
 		31 + /*	DE_META */
 		3 + /* CNTX_CTRL */
 		5 + /* HDP_INVL */
-		8 + 8 + /* FENCE x2 */
+		12 + 12 + /* FENCE x2 */
 		2, /* SWITCH_BUFFER */
 	.emit_ib_size =	4, /* gfx_v8_0_ring_emit_ib_gfx */
 	.emit_ib = gfx_v8_0_ring_emit_ib_gfx,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 97cf0b5..06cdc22 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1026,6 +1026,8 @@
 			adev->gfx.mec_fw_write_wait = true;
 		break;
 	default:
+		adev->gfx.me_fw_write_wait = true;
+		adev->gfx.mec_fw_write_wait = true;
 		break;
 	}
 }
@@ -1038,17 +1040,10 @@
 	case CHIP_VEGA20:
 		break;
 	case CHIP_RAVEN:
-		/* Disable GFXOFF on original raven.  There are combinations
-		 * of sbios and platforms that are not stable.
-		 */
-		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
-			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
-		else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
-			 &&((adev->gfx.rlc_fw_version != 106 &&
-			     adev->gfx.rlc_fw_version < 531) ||
-			    (adev->gfx.rlc_fw_version == 53815) ||
-			    (adev->gfx.rlc_feature_version < 1) ||
-			    !adev->gfx.rlc.is_rlc_v2_1))
+		if (!(adev->rev_id >= 0x8 ||
+		      adev->pdev->device == 0x15d8) &&
+		    (adev->pm.fw_version < 0x41e2b || /* not raven1 fresh */
+		     !adev->gfx.rlc.is_rlc_v2_1)) /* without rlc save restore ucodes */
 			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 
 		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
@@ -1680,39 +1675,6 @@
 	return 0;
 }
 
-static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev)
-{
-	int r;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
-	if (unlikely(r != 0))
-		return r;
-
-	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
-			AMDGPU_GEM_DOMAIN_VRAM);
-	if (!r)
-		adev->gfx.rlc.clear_state_gpu_addr =
-			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
-	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
-	return r;
-}
-
-static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!adev->gfx.rlc.clear_state_obj)
-		return;
-
-	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
-	if (likely(r == 0)) {
-		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
-		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-	}
-}
-
 static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -2601,6 +2563,7 @@
 
 static void gfx_v9_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* csib */
 	WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI),
 			adev->gfx.rlc.clear_state_gpu_addr >> 32);
@@ -2930,7 +2893,10 @@
 	 * And it's needed by gfxoff feature.
 	 */
 	if (adev->gfx.rlc.is_rlc_v2_1) {
-		gfx_v9_1_init_rlc_save_restore_list(adev);
+		if (adev->asic_type == CHIP_VEGA12 ||
+		    (adev->asic_type == CHIP_RAVEN &&
+		     adev->rev_id >= 8))
+			gfx_v9_1_init_rlc_save_restore_list(adev);
 		gfx_v9_0_enable_save_restore_machine(adev);
 	}
 
@@ -3760,6 +3726,7 @@
 
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -3889,10 +3856,6 @@
 
 	gfx_v9_0_constants_init(adev);
 
-	r = gfx_v9_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -3978,8 +3941,6 @@
 	gfx_v9_0_cp_enable(adev, false);
 	adev->gfx.rlc.funcs->stop(adev);
 
-	gfx_v9_0_csb_vram_unpin(adev);
-
 	return 0;
 }
 
@@ -4084,11 +4045,13 @@
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
 	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
 		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
@@ -4698,7 +4661,7 @@
 	amdgpu_gfx_rlc_enter_safe_mode(adev);
 
 	/* Enable 3D CGCG/CGLS */
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)) {
+	if (enable) {
 		/* write cmd to clear cgcg/cgls ov */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		/* unset CGCG override */
@@ -4710,8 +4673,12 @@
 		/* enable 3Dcgcg FSM(0x0000363f) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
 
-		data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
-			RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+				RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+		else
+			data = 0x0 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
 				RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK;
@@ -4838,10 +4805,9 @@
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
-		if (!enable) {
+		if (!enable)
 			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		}
+
 		if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
 			gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true);
 			gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true);
@@ -4867,12 +4833,7 @@
 			amdgpu_gfx_off_ctrl(adev, true);
 		break;
 	case CHIP_VEGA12:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else {
-			amdgpu_gfx_off_ctrl(adev, true);
-		}
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 6ce37ce..d6fbdc6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -365,6 +365,8 @@
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(GC, 0,
 				 mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index db10640..fbe06c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -350,6 +350,8 @@
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(GC, 0,
 				 mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 5c7d5f7..f642e06 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -230,12 +230,36 @@
 				   unsigned int vmhub, uint32_t flush_type)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
-	u32 tmp = gmc_v10_0_get_invalidate_req(vmid, flush_type);
+	u32 inv_req = gmc_v10_0_get_invalidate_req(vmid, flush_type);
+	u32 tmp;
 	/* Use register 17 for GART */
 	const unsigned eng = 17;
 	unsigned int i;
 
-	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
+	spin_lock(&adev->gmc.invalidate_lock);
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1) {
+		for (i = 0; i < adev->usec_timeout; i++) {
+			/* a read return value of 1 means semaphore acuqire */
+			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+			if (tmp & 0x1)
+				break;
+			udelay(1);
+		}
+
+		if (i >= adev->usec_timeout)
+			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+	}
+
+	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, inv_req);
 
 	/*
 	 * Issue a dummy read to wait for the ACK register to be cleared
@@ -254,6 +278,17 @@
 		udelay(1);
 	}
 
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
+	spin_unlock(&adev->gmc.invalidate_lock);
+
 	if (i < adev->usec_timeout)
 		return;
 
@@ -338,6 +373,20 @@
 	uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/* a read return value of 1 means semaphore acuqire */
+		amdgpu_ring_emit_reg_wait(ring,
+					  hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 			      lower_32_bits(pd_addr));
 
@@ -348,6 +397,15 @@
 					    hub->vm_inv_eng0_ack + eng,
 					    req, 1 << vmid);
 
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
+
 	return pd_addr;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f913370..688111e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -448,6 +448,24 @@
 	return req;
 }
 
+/**
+ * gmc_v9_0_use_invalidate_semaphore - judge whether to use semaphore
+ *
+ * @adev: amdgpu_device pointer
+ * @vmhub: vmhub type
+ *
+ */
+static bool gmc_v9_0_use_invalidate_semaphore(struct amdgpu_device *adev,
+				       uint32_t vmhub)
+{
+	return ((vmhub == AMDGPU_MMHUB_0 ||
+		 vmhub == AMDGPU_MMHUB_1) &&
+		(!amdgpu_sriov_vf(adev)) &&
+		(!(adev->asic_type == CHIP_RAVEN &&
+		   adev->rev_id < 0x8 &&
+		   adev->pdev->device == 0x15d8)));
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -467,14 +485,15 @@
 static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 					uint32_t vmhub, uint32_t flush_type)
 {
+	bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(adev, vmhub);
 	const unsigned eng = 17;
-	u32 j, tmp;
+	u32 j, inv_req, tmp;
 	struct amdgpu_vmhub *hub;
 
 	BUG_ON(vmhub >= adev->num_vmhubs);
 
 	hub = &adev->vmhub[vmhub];
-	tmp = gmc_v9_0_get_invalidate_req(vmid, flush_type);
+	inv_req = gmc_v9_0_get_invalidate_req(vmid, flush_type);
 
 	/* This is necessary for a HW workaround under SRIOV as well
 	 * as GFXOFF under bare metal
@@ -485,13 +504,35 @@
 		uint32_t req = hub->vm_inv_eng0_req + eng;
 		uint32_t ack = hub->vm_inv_eng0_ack + eng;
 
-		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, tmp,
+		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
 				1 << vmid);
 		return;
 	}
 
 	spin_lock(&adev->gmc.invalidate_lock);
-	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
+
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (use_semaphore) {
+		for (j = 0; j < adev->usec_timeout; j++) {
+			/* a read return value of 1 means semaphore acuqire */
+			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+			if (tmp & 0x1)
+				break;
+			udelay(1);
+		}
+
+		if (j >= adev->usec_timeout)
+			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+	}
+
+	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, inv_req);
 
 	/*
 	 * Issue a dummy read to wait for the ACK register to be cleared
@@ -506,7 +547,17 @@
 			break;
 		udelay(1);
 	}
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (use_semaphore)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
 	spin_unlock(&adev->gmc.invalidate_lock);
+
 	if (j < adev->usec_timeout)
 		return;
 
@@ -516,11 +567,25 @@
 static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 					    unsigned vmid, uint64_t pd_addr)
 {
+	bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(ring->adev, ring->funcs->vmhub);
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vmhub *hub = &adev->vmhub[ring->funcs->vmhub];
 	uint32_t req = gmc_v9_0_get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (use_semaphore)
+		/* a read return value of 1 means semaphore acuqire */
+		amdgpu_ring_emit_reg_wait(ring,
+					  hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 			      lower_32_bits(pd_addr));
 
@@ -531,6 +596,14 @@
 					    hub->vm_inv_eng0_ack + eng,
 					    req, 1 << vmid);
 
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (use_semaphore)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
+
 	return pd_addr;
 }
 
@@ -1310,6 +1383,19 @@
 }
 
 /**
+ * gmc_v9_0_restore_registers - restores regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This restores register values, saved at suspend.
+ */
+static void gmc_v9_0_restore_registers(struct amdgpu_device *adev)
+{
+	if (adev->asic_type == CHIP_RAVEN)
+		WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register);
+}
+
+/**
  * gmc_v9_0_gart_enable - gart enable
  *
  * @adev: amdgpu_device pointer
@@ -1406,6 +1492,20 @@
 }
 
 /**
+ * gmc_v9_0_save_registers - saves regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This saves potential register values that should be
+ * restored upon resume
+ */
+static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
+{
+	if (adev->asic_type == CHIP_RAVEN)
+		adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0);
+}
+
+/**
  * gmc_v9_0_gart_disable - gart disable
  *
  * @adev: amdgpu_device pointer
@@ -1441,9 +1541,16 @@
 
 static int gmc_v9_0_suspend(void *handle)
 {
+	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return gmc_v9_0_hw_fini(adev);
+	r = gmc_v9_0_hw_fini(adev);
+	if (r)
+		return r;
+
+	gmc_v9_0_save_registers(adev);
+
+	return 0;
 }
 
 static int gmc_v9_0_resume(void *handle)
@@ -1451,6 +1558,7 @@
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v9_0_restore_registers(adev);
 	r = gmc_v9_0_hw_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index a13dd9a..7d165f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -193,19 +193,29 @@
 
 	wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) {
-		wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
-		/* When a ring buffer overflow happen start parsing interrupt
-		 * from the last not overwritten vector (wptr + 16). Hopefully
-		 * this should allow us to catchup.
-		 */
-		dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
-			 wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
-		ih->rptr = (wptr + 16) & ih->ptr_mask;
-		tmp = RREG32(mmIH_RB_CNTL);
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
-		WREG32(mmIH_RB_CNTL, tmp);
-	}
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	/* Double check that the overflow wasn't already cleared. */
+	wptr = RREG32(mmIH_RB_WPTR);
+
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
+	/* When a ring buffer overflow happen start parsing interrupt
+	 * from the last not overwritten vector (wptr + 16). Hopefully
+	 * this should allow us to catchup.
+	 */
+	dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
+		wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
+	ih->rptr = (wptr + 16) & ih->ptr_mask;
+	tmp = RREG32(mmIH_RB_CNTL);
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
+	WREG32(mmIH_RB_CNTL, tmp);
+
+
+out:
 	return (wptr & ih->ptr_mask);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 04cd4b6..641f125 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -418,6 +418,8 @@
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(MMHUB, 0,
 				 mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index b39bea6..096bb88 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -341,6 +341,8 @@
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(MMHUB, 0,
 				 mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 9ed178f..fb161c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -502,6 +502,10 @@
 			SOC15_REG_OFFSET(MMHUB, 0,
 			    mmVML2VC0_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) +
 			    i * MMHUB_INSTANCE_REGISTER_OFFSET;
+		hub[i]->vm_inv_eng0_sem =
+			SOC15_REG_OFFSET(MMHUB, 0,
+					 mmVML2VC0_VM_INVALIDATE_ENG0_SEM) +
+					 i * MMHUB_INSTANCE_REGISTER_OFFSET;
 		hub[i]->vm_inv_eng0_req =
 			SOC15_REG_OFFSET(MMHUB, 0,
 					 mmVML2VC0_VM_INVALIDATE_ENG0_REQ) +
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h b/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h
index 074a9a0..a5b60c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h
@@ -73,6 +73,22 @@
 #define SDMA_OP_AQL_COPY  0
 #define SDMA_OP_AQL_BARRIER_OR  0
 
+#define SDMA_GCR_RANGE_IS_PA		(1 << 18)
+#define SDMA_GCR_SEQ(x)			(((x) & 0x3) << 16)
+#define SDMA_GCR_GL2_WB			(1 << 15)
+#define SDMA_GCR_GL2_INV		(1 << 14)
+#define SDMA_GCR_GL2_DISCARD		(1 << 13)
+#define SDMA_GCR_GL2_RANGE(x)		(((x) & 0x3) << 11)
+#define SDMA_GCR_GL2_US			(1 << 10)
+#define SDMA_GCR_GL1_INV		(1 << 9)
+#define SDMA_GCR_GLV_INV		(1 << 8)
+#define SDMA_GCR_GLK_INV		(1 << 7)
+#define SDMA_GCR_GLK_WB			(1 << 6)
+#define SDMA_GCR_GLM_INV		(1 << 5)
+#define SDMA_GCR_GLM_WB			(1 << 4)
+#define SDMA_GCR_GL1_RANGE(x)		(((x) & 0x3) << 2)
+#define SDMA_GCR_GLI_INV(x)		(((x) & 0x3) << 0)
+
 /*define for op field*/
 #define SDMA_PKT_HEADER_op_offset 0
 #define SDMA_PKT_HEADER_op_mask   0x000000FF
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index de9b995..2d78082 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -660,6 +660,12 @@
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_ATHUB;
+		/* guest vm gets 0xffffffff when reading RCC_DEV0_EPF0_STRAP0,
+		 * as a consequence, the rev_id and external_rev_id are wrong.
+		 * workaround it by hardcoding rev_id to 0 (default value).
+		 */
+		if (amdgpu_sriov_vf(adev))
+			adev->rev_id = 0;
 		adev->external_rev_id = adev->rev_id + 0xa;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 74a9fe8..8c54f0b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -44,7 +44,7 @@
     GFX_CTRL_CMD_ID_DISABLE_INT     = 0x00060000,   /* disable PSP-to-Gfx interrupt */
     GFX_CTRL_CMD_ID_MODE1_RST       = 0x00070000,   /* trigger the Mode 1 reset */
     GFX_CTRL_CMD_ID_GBR_IH_SET      = 0x00080000,   /* set Gbr IH_RB_CNTL registers */
-    GFX_CTRL_CMD_ID_CONSUME_CMD     = 0x000A0000,   /* send interrupt to psp for updating write pointer of vf */
+    GFX_CTRL_CMD_ID_CONSUME_CMD     = 0x00090000,   /* send interrupt to psp for updating write pointer of vf */
     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING = 0x000C0000, /* destroy GPCOM ring */
 
     GFX_CTRL_CMD_ID_MAX             = 0x000F0000,   /* max command ID */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 1016610..d483684 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -398,6 +398,34 @@
 	return false;
 }
 
+static int psp_v11_0_ring_stop(struct psp_context *psp,
+			      enum psp_ring_type ring_type)
+{
+	int ret = 0;
+	struct amdgpu_device *adev = psp->adev;
+
+	/* Write the ring destroy command*/
+	if (psp_v11_0_support_vmr_ring(psp))
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+				     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING);
+	else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64,
+				     GFX_CTRL_CMD_ID_DESTROY_RINGS);
+
+	/* there might be handshake issue with hardware which needs delay */
+	mdelay(20);
+
+	/* Wait for response flag (bit 31) */
+	if (psp_v11_0_support_vmr_ring(psp))
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
+				   0x80000000, 0x80000000, false);
+	else
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x80000000, false);
+
+	return ret;
+}
+
 static int psp_v11_0_ring_create(struct psp_context *psp,
 				enum psp_ring_type ring_type)
 {
@@ -407,6 +435,12 @@
 	struct amdgpu_device *adev = psp->adev;
 
 	if (psp_v11_0_support_vmr_ring(psp)) {
+		ret = psp_v11_0_ring_stop(psp, ring_type);
+		if (ret) {
+			DRM_ERROR("psp_v11_0_ring_stop_sriov failed!\n");
+			return ret;
+		}
+
 		/* Write low address of the ring to C2PMSG_102 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_ring_reg);
@@ -451,33 +485,6 @@
 	return ret;
 }
 
-static int psp_v11_0_ring_stop(struct psp_context *psp,
-			      enum psp_ring_type ring_type)
-{
-	int ret = 0;
-	struct amdgpu_device *adev = psp->adev;
-
-	/* Write the ring destroy command*/
-	if (psp_v11_0_support_vmr_ring(psp))
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
-				     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING);
-	else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64,
-				     GFX_CTRL_CMD_ID_DESTROY_RINGS);
-
-	/* there might be handshake issue with hardware which needs delay */
-	mdelay(20);
-
-	/* Wait for response flag (bit 31) */
-	if (psp_v11_0_support_vmr_ring(psp))
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
-				   0x80000000, 0x80000000, false);
-	else
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
-				   0x80000000, 0x80000000, false);
-
-	return ret;
-}
 
 static int psp_v11_0_ring_destroy(struct psp_context *psp,
 				 enum psp_ring_type ring_type)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index a101758..b6af67f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -255,7 +255,7 @@
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -750,7 +750,7 @@
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 5f4e2c6..cd3ebed 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -429,7 +429,7 @@
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v3_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1021,7 +1021,7 @@
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 4554e72..23de332 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -698,7 +698,7 @@
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v4_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1579,7 +1579,7 @@
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 8493bfb..60180ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -100,6 +100,10 @@
 
 static const struct soc15_reg_golden golden_settings_sdma_nv12[] = {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GB_ADDR_CONFIG, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GB_ADDR_CONFIG, 0x001877ff, 0x00000044),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x001877ff, 0x00000044),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSDMA1_RLC3_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 };
 
@@ -286,30 +290,20 @@
 static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u64 *wptr = NULL;
-	uint64_t local_wptr = 0;
+	u64 wptr;
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]);
-		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr);
-		*wptr = (*wptr) >> 2;
-		DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr);
+		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
-		u32 lowbit, highbit;
-
-		wptr = &local_wptr;
-		lowbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
-
-		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				ring->me, highbit, lowbit);
-		*wptr = highbit;
-		*wptr = (*wptr) << 32;
-		*wptr |= lowbit;
+		wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
+		wptr = wptr << 32;
+		wptr |= RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR));
+		DRM_DEBUG("wptr before shift [%i] wptr == 0x%016llx\n", ring->me, wptr);
 	}
 
-	return *wptr;
+	return wptr >> 2;
 }
 
 /**
@@ -382,8 +376,27 @@
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid);
 
-	/* IB packet must end on a 8 DW boundary */
-	sdma_v5_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	/* Invalidate L2, because if we don't do it, we might get stale cache
+	 * lines from previous IBs.
+	 */
+	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_GCR_REQ));
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, (SDMA_GCR_GL2_INV |
+				 SDMA_GCR_GL2_WB |
+				 SDMA_GCR_GLM_INV |
+				 SDMA_GCR_GLM_WB) << 16);
+	amdgpu_ring_write(ring, 0xffffff80);
+	amdgpu_ring_write(ring, 0xffff);
+
+	/* An IB packet must end on a 8 DW boundary--the next dword
+	 * must be on a 8-dword boundary. Our IB packet below is 6
+	 * dwords long, thus add x number of NOPs, such that, in
+	 * modular arithmetic,
+	 * wptr + 6 + x = 8k, k >= 0, which in C is,
+	 * (wptr + 6 + x) % 8 = 0.
+	 * The expression below, is a solution of x.
+	 */
+	sdma_v5_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1086,10 +1099,10 @@
 }
 
 /**
- * sdma_v5_0_ring_pad_ib - pad the IB to the required number of dw
- *
+ * sdma_v5_0_ring_pad_ib - pad the IB
  * @ib: indirect buffer to fill with padding
  *
+ * Pad the IB with NOPs to a boundary multiple of 8.
  */
 static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 {
@@ -1097,7 +1110,7 @@
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 0x7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1254,8 +1267,12 @@
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		if (adev->sdma.instance[i].fw != NULL)
+			release_firmware(adev->sdma.instance[i].fw);
+
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+	}
 
 	return 0;
 }
@@ -1600,7 +1617,7 @@
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 +
 		10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */
-	.emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */
+	.emit_ib_size = 5 + 7 + 6, /* sdma_v5_0_ring_emit_ib */
 	.emit_ib = sdma_v5_0_ring_emit_ib,
 	.emit_fence = sdma_v5_0_ring_emit_fence,
 	.emit_pipeline_sync = sdma_v5_0_ring_emit_pipeline_sync,
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 57bb5f9..88ae27a 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -64,7 +64,8 @@
 	u32 interrupt_cntl, ih_cntl, ih_rb_cntl;
 
 	si_ih_disable_interrupts(adev);
-	WREG32(INTERRUPT_CNTL2, adev->irq.ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, adev->dummy_page_addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	interrupt_cntl &= ~IH_DUMMY_RD_OVERRIDE;
 	interrupt_cntl &= ~IH_REQ_NONSNOOP_EN;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4ccfcdf..6ff1d30 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -84,6 +84,13 @@
 #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_CTRL_EN_MASK	0x00010000L
 #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_LS_EN_MASK		0x00020000L
 #define mmHDP_MEM_POWER_CTRL_BASE_IDX	0
+
+/* for Vega20/arcturus regiter offset change */
+#define	mmROM_INDEX_VG20				0x00e4
+#define	mmROM_INDEX_VG20_BASE_IDX			0
+#define	mmROM_DATA_VG20					0x00e5
+#define	mmROM_DATA_VG20_BASE_IDX			0
+
 /*
  * Indirect registers accessor
  */
@@ -267,7 +274,14 @@
 
 static u32 soc15_get_xclk(struct amdgpu_device *adev)
 {
-	return adev->clock.spll.reference_freq;
+	u32 reference_clock = adev->clock.spll.reference_freq;
+
+	if (adev->asic_type == CHIP_RENOIR)
+		return 10000;
+	if (adev->asic_type == CHIP_RAVEN)
+		return reference_clock / 4;
+
+	return reference_clock;
 }
 
 
@@ -299,6 +313,8 @@
 {
 	u32 *dw_ptr;
 	u32 i, length_dw;
+	uint32_t rom_index_offset;
+	uint32_t rom_data_offset;
 
 	if (bios == NULL)
 		return false;
@@ -311,11 +327,23 @@
 	dw_ptr = (u32 *)bios;
 	length_dw = ALIGN(length_bytes, 4) / 4;
 
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
+		rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX_VG20);
+		rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA_VG20);
+		break;
+	default:
+		rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX);
+		rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA);
+		break;
+	}
+
 	/* set rom index to 0 */
-	WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX), 0);
+	WREG32(rom_index_offset, 0);
 	/* read out the rom data */
 	for (i = 0; i < length_dw; i++)
-		dw_ptr[i] = RREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA));
+		dw_ptr[i] = RREG32(rom_data_offset);
 
 	return true;
 }
@@ -1104,7 +1132,6 @@
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
 				AMD_CG_SUPPORT_GFX_CP_LS |
-				AMD_CG_SUPPORT_GFX_3D_CGCG |
 				AMD_CG_SUPPORT_GFX_3D_CGLS |
 				AMD_CG_SUPPORT_GFX_CGCG |
 				AMD_CG_SUPPORT_GFX_CGLS |
@@ -1118,14 +1145,12 @@
 
 			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
 				AMD_PG_SUPPORT_MMHUB |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+				AMD_PG_SUPPORT_VCN;
 		} else {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
 				AMD_CG_SUPPORT_GFX_RLC_LS |
 				AMD_CG_SUPPORT_GFX_CP_LS |
-				AMD_CG_SUPPORT_GFX_3D_CGCG |
 				AMD_CG_SUPPORT_GFX_3D_CGLS |
 				AMD_CG_SUPPORT_GFX_CGCG |
 				AMD_CG_SUPPORT_GFX_CGLS |
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index a3dde0c..a1d4ea6 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -28,8 +28,8 @@
 #include "nbio_v7_0.h"
 #include "nbio_v7_4.h"
 
-#define SOC15_FLUSH_GPU_TLB_NUM_WREG		4
-#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT	1
+#define SOC15_FLUSH_GPU_TLB_NUM_WREG		6
+#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT	3
 
 extern const struct amd_ip_funcs soc15_common_ip_funcs;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 839f186..19e870c 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -52,6 +52,7 @@
 		uint32_t old_ = 0;	\
 		uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
 		uint32_t loop = adev->usec_timeout;		\
+		ret = 0;					\
 		while ((tmp_ & (mask)) != (expected_value)) {	\
 			if (old_ != tmp_) {			\
 				loop = adev->usec_timeout;	\
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index e40140b..db0a3bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -195,19 +195,30 @@
 
 	wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) {
-		wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
-		/* When a ring buffer overflow happen start parsing interrupt
-		 * from the last not overwritten vector (wptr + 16). Hopefully
-		 * this should allow us to catchup.
-		 */
-		dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
-			 wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
-		ih->rptr = (wptr + 16) & ih->ptr_mask;
-		tmp = RREG32(mmIH_RB_CNTL);
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
-		WREG32(mmIH_RB_CNTL, tmp);
-	}
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	/* Double check that the overflow wasn't already cleared. */
+	wptr = RREG32(mmIH_RB_WPTR);
+
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
+
+	/* When a ring buffer overflow happen start parsing interrupt
+	 * from the last not overwritten vector (wptr + 16). Hopefully
+	 * this should allow us to catchup.
+	 */
+
+	dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
+		wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
+	ih->rptr = (wptr + 16) & ih->ptr_mask;
+	tmp = RREG32(mmIH_RB_CNTL);
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
+	WREG32(mmIH_RB_CNTL, tmp);
+
+out:
 	return (wptr & ih->ptr_mask);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 217084d..9deef20 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -354,6 +354,7 @@
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unpin(bo);
 	amdgpu_bo_unreserve(bo);
 	amdgpu_bo_unref(&bo);
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 93b3500..1bb0f3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -233,9 +233,13 @@
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
-		RREG32_SOC15(VCN, 0, mmUVD_STATUS))
+		(adev->vcn.cur_state != AMD_PG_STATE_GATE &&
+		 RREG32_SOC15(VCN, 0, mmUVD_STATUS))) {
 		vcn_v1_0_set_powergating_state(adev, AMD_PG_STATE_GATE);
+	}
 
 	ring->sched.ready = false;
 
@@ -1375,7 +1379,7 @@
 
 	if (enable) {
 		/* wait for STATUS to clear */
-		if (vcn_v1_0_is_idle(handle))
+		if (!vcn_v1_0_is_idle(handle))
 			return -EBUSY;
 		vcn_v1_0_enable_clock_gating(adev);
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 36ad0c0..82327ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -293,6 +293,8 @@
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	int i;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
 	    (adev->vcn.cur_state != AMD_PG_STATE_GATE &&
 	      RREG32_SOC15(VCN, 0, mmUVD_STATUS)))
@@ -1026,6 +1028,10 @@
 	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp);
 
+	/* Stall DPG before WPTR/RPTR reset */
+	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+		UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
+		~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 	/* set the write pointer delay */
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR_CNTL, 0);
 
@@ -1048,6 +1054,9 @@
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 		lower_32_bits(ring->wptr));
 
+	/* Unstall DPG */
+	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+		0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 	return 0;
 }
 
@@ -1357,8 +1366,13 @@
 					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
 					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code);
 
+				/* Stall DPG before WPTR/RPTR reset */
+				WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+					   UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
+					   ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 				/* Restore */
 				ring = &adev->vcn.inst->ring_enc[0];
+				ring->wptr = 0;
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4);
@@ -1366,6 +1380,7 @@
 				WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 
 				ring = &adev->vcn.inst->ring_enc[1];
+				ring->wptr = 0;
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
@@ -1374,6 +1389,9 @@
 
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 					   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
+				/* Unstall DPG */
+				WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+					   0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 					   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 395c225..4c9a163 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -302,6 +302,8 @@
 	struct amdgpu_ring *ring;
 	int i;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
@@ -423,7 +425,6 @@
  * vcn_v2_5_disable_clock_gating - disable VCN clock gating
  *
  * @adev: amdgpu_device pointer
- * @sw: enable SW clock gating
  *
  * Disable clock gating for VCN block
  */
@@ -542,7 +543,6 @@
  * vcn_v2_5_enable_clock_gating - enable VCN clock gating
  *
  * @adev: amdgpu_device pointer
- * @sw: enable SW clock gating
  *
  * Enable clock gating for VCN block
  */
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index 901fe35..d3400da 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -905,7 +905,7 @@
 	0x7a5d0000, 0x807c817c,
 	0x807aff7a, 0x00000080,
 	0xbf0a717c, 0xbf85fff8,
-	0xbf820141, 0xbef4037e,
+	0xbf820142, 0xbef4037e,
 	0x8775ff7f, 0x0000ffff,
 	0x8875ff75, 0x00040000,
 	0xbef60380, 0xbef703ff,
@@ -967,7 +967,7 @@
 	0x725d0000, 0xe0304080,
 	0x725d0100, 0xe0304100,
 	0x725d0200, 0xe0304180,
-	0x725d0300, 0xbf820031,
+	0x725d0300, 0xbf820032,
 	0xbef603ff, 0x01000000,
 	0xbef20378, 0x8078ff78,
 	0x00000400, 0xbefc0384,
@@ -992,83 +992,84 @@
 	0x725d0000, 0xe0304100,
 	0x725d0100, 0xe0304200,
 	0x725d0200, 0xe0304300,
-	0x725d0300, 0xb9782a05,
-	0x80788178, 0x907c9973,
-	0x877c817c, 0xbf06817c,
-	0xbf850002, 0x8f788978,
-	0xbf820001, 0x8f788a78,
-	0xb9721e06, 0x8f728a72,
-	0x80787278, 0x8078ff78,
-	0x00000200, 0x80f8ff78,
-	0x00000050, 0xbef603ff,
-	0x01000000, 0xbefc03ff,
-	0x0000006c, 0x80f89078,
-	0xf429003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc847c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0x80f8a078,
-	0xf42d003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc887c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0xbe843104,
-	0xbe863106, 0x80f8c078,
-	0xf431003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0xbe843104,
-	0xbe863106, 0xbe883108,
-	0xbe8a310a, 0xbe8c310c,
-	0xbe8e310e, 0xbf06807c,
-	0xbf84fff0, 0xb9782a05,
-	0x80788178, 0x907c9973,
-	0x877c817c, 0xbf06817c,
-	0xbf850002, 0x8f788978,
-	0xbf820001, 0x8f788a78,
-	0xb9721e06, 0x8f728a72,
-	0x80787278, 0x8078ff78,
-	0x00000200, 0xbef603ff,
-	0x01000000, 0xf4211bfa,
+	0x725d0300, 0xbf8c3f70,
+	0xb9782a05, 0x80788178,
+	0x907c9973, 0x877c817c,
+	0xbf06817c, 0xbf850002,
+	0x8f788978, 0xbf820001,
+	0x8f788a78, 0xb9721e06,
+	0x8f728a72, 0x80787278,
+	0x8078ff78, 0x00000200,
+	0x80f8ff78, 0x00000050,
+	0xbef603ff, 0x01000000,
+	0xbefc03ff, 0x0000006c,
+	0x80f89078, 0xf429003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc847c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0x80f8a078, 0xf42d003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc887c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0xbe843104, 0xbe863106,
+	0x80f8c078, 0xf431003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0xbe843104, 0xbe863106,
+	0xbe883108, 0xbe8a310a,
+	0xbe8c310c, 0xbe8e310e,
+	0xbf06807c, 0xbf84fff0,
+	0xb9782a05, 0x80788178,
+	0x907c9973, 0x877c817c,
+	0xbf06817c, 0xbf850002,
+	0x8f788978, 0xbf820001,
+	0x8f788a78, 0xb9721e06,
+	0x8f728a72, 0x80787278,
+	0x8078ff78, 0x00000200,
+	0xbef603ff, 0x01000000,
+	0xf4211bfa, 0xf0000000,
+	0x80788478, 0xf4211b3a,
 	0xf0000000, 0x80788478,
-	0xf4211b3a, 0xf0000000,
-	0x80788478, 0xf4211b7a,
+	0xf4211b7a, 0xf0000000,
+	0x80788478, 0xf4211eba,
 	0xf0000000, 0x80788478,
-	0xf4211eba, 0xf0000000,
-	0x80788478, 0xf4211efa,
+	0xf4211efa, 0xf0000000,
+	0x80788478, 0xf4211c3a,
 	0xf0000000, 0x80788478,
-	0xf4211c3a, 0xf0000000,
-	0x80788478, 0xf4211c7a,
+	0xf4211c7a, 0xf0000000,
+	0x80788478, 0xf4211e7a,
 	0xf0000000, 0x80788478,
-	0xf4211e7a, 0xf0000000,
-	0x80788478, 0xf4211cfa,
+	0xf4211cfa, 0xf0000000,
+	0x80788478, 0xf4211bba,
 	0xf0000000, 0x80788478,
+	0xbf8cc07f, 0xb9eef814,
 	0xf4211bba, 0xf0000000,
 	0x80788478, 0xbf8cc07f,
-	0xb9eef814, 0xf4211bba,
-	0xf0000000, 0x80788478,
-	0xbf8cc07f, 0xb9eef815,
-	0xbef2036d, 0x876dff72,
-	0x0000ffff, 0xbefc036f,
-	0xbefe037a, 0xbeff037b,
-	0x876f71ff, 0x000003ff,
-	0xb9ef4803, 0xb9f9f816,
-	0x876f71ff, 0xfffff800,
-	0x906f8b6f, 0xb9efa2c3,
-	0xb9f3f801, 0x876fff72,
-	0xfc000000, 0x906f9a6f,
-	0x8f6f906f, 0xbef30380,
+	0xb9eef815, 0xbef2036d,
+	0x876dff72, 0x0000ffff,
+	0xbefc036f, 0xbefe037a,
+	0xbeff037b, 0x876f71ff,
+	0x000003ff, 0xb9ef4803,
+	0xb9f9f816, 0x876f71ff,
+	0xfffff800, 0x906f8b6f,
+	0xb9efa2c3, 0xb9f3f801,
+	0x876fff72, 0xfc000000,
+	0x906f9a6f, 0x8f6f906f,
+	0xbef30380, 0x88736f73,
+	0x876fff72, 0x02000000,
+	0x906f996f, 0x8f6f8f6f,
 	0x88736f73, 0x876fff72,
-	0x02000000, 0x906f996f,
-	0x8f6f8f6f, 0x88736f73,
-	0x876fff72, 0x01000000,
-	0x906f986f, 0x8f6f996f,
-	0x88736f73, 0x876fff70,
-	0x00800000, 0x906f976f,
-	0xb9f3f807, 0x87fe7e7e,
-	0x87ea6a6a, 0xb9f0f802,
-	0xbf8a0000, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0x01000000, 0x906f986f,
+	0x8f6f996f, 0x88736f73,
+	0x876fff70, 0x00800000,
+	0x906f976f, 0xb9f3f807,
+	0x87fe7e7e, 0x87ea6a6a,
+	0xb9f0f802, 0xbf8a0000,
+	0xbe80226c, 0xbf810000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
+	0xbf9f0000, 0x00000000,
 };
 static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0xbf820001, 0xbf8202c4,
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 cdaa523..4433bda 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -758,6 +758,7 @@
 	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256
 	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*2
 	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*3
+	s_waitcnt	vmcnt(0)
 
 	/* restore SGPRs */
 	//will be 2+8+16*6
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 1d3cd5c..4a0ef92 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1664,6 +1664,7 @@
 	}
 
 	mutex_unlock(&p->mutex);
+	dma_buf_put(dmabuf);
 
 	args->handle = MAKE_HANDLE(args->gpu_id, idr_handle);
 
@@ -1673,6 +1674,7 @@
 	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem);
 err_unlock:
 	mutex_unlock(&p->mutex);
+	dma_buf_put(dmabuf);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 15c5230..673d5e3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -33,6 +33,11 @@
 
 	return single_open(file, show, NULL);
 }
+static int kfd_debugfs_hang_hws_read(struct seq_file *m, void *data)
+{
+	seq_printf(m, "echo gpu_id > hang_hws\n");
+	return 0;
+}
 
 static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
 	const char __user *user_buf, size_t size, loff_t *ppos)
@@ -93,8 +98,8 @@
 			    kfd_debugfs_hqds_by_device, &kfd_debugfs_fops);
 	debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 			    kfd_debugfs_rls_by_device, &kfd_debugfs_fops);
-	debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
-			    NULL, &kfd_debugfs_hang_hws_fops);
+	debugfs_create_file("hang_hws", S_IFREG | 0200, debugfs_root,
+			    kfd_debugfs_hang_hws_read, &kfd_debugfs_hang_hws_fops);
 }
 
 void kfd_debugfs_fini(void)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 0dc1084..ad9483b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -1112,9 +1112,9 @@
 	return 0;
 
 kfd_gtt_no_free_chunk:
-	pr_debug("Allocation failed with mem_obj = %p\n", mem_obj);
+	pr_debug("Allocation failed with mem_obj = %p\n", *mem_obj);
 	mutex_unlock(&kfd->gtt_sa_lock);
-	kfree(mem_obj);
+	kfree(*mem_obj);
 	return -ENOMEM;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index d985e31..723ec6c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1011,6 +1011,9 @@
 
 static int initialize_cpsch(struct device_queue_manager *dqm)
 {
+	uint64_t num_sdma_queues;
+	uint64_t num_xgmi_sdma_queues;
+
 	pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm));
 
 	mutex_init(&dqm->lock_hidden);
@@ -1019,8 +1022,18 @@
 	dqm->sdma_queue_count = 0;
 	dqm->xgmi_sdma_queue_count = 0;
 	dqm->active_runlist = false;
-	dqm->sdma_bitmap = ~0ULL >> (64 - get_num_sdma_queues(dqm));
-	dqm->xgmi_sdma_bitmap = ~0ULL >> (64 - get_num_xgmi_sdma_queues(dqm));
+
+	num_sdma_queues = get_num_sdma_queues(dqm);
+	if (num_sdma_queues >= BITS_PER_TYPE(dqm->sdma_bitmap))
+		dqm->sdma_bitmap = ULLONG_MAX;
+	else
+		dqm->sdma_bitmap = (BIT_ULL(num_sdma_queues) - 1);
+
+	num_xgmi_sdma_queues = get_num_xgmi_sdma_queues(dqm);
+	if (num_xgmi_sdma_queues >= BITS_PER_TYPE(dqm->xgmi_sdma_bitmap))
+		dqm->xgmi_sdma_bitmap = ULLONG_MAX;
+	else
+		dqm->xgmi_sdma_bitmap = (BIT_ULL(num_xgmi_sdma_queues) - 1);
 
 	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
@@ -1075,6 +1088,8 @@
 	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	dqm_unlock(dqm);
 
+	pm_release_ib(&dqm->packets);
+
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets);
 
@@ -1181,16 +1196,18 @@
 
 	list_add(&q->list, &qpd->queues_list);
 	qpd->queue_count++;
+
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
+		dqm->sdma_queue_count++;
+	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
+		dqm->xgmi_sdma_queue_count++;
+
 	if (q->properties.is_active) {
 		dqm->queue_count++;
 		retval = execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
-		dqm->sdma_queue_count++;
-	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
-		dqm->xgmi_sdma_queue_count++;
 	/*
 	 * Unconditionally increment this counter, regardless of the queue's
 	 * type or whether the queue is active.
@@ -1567,7 +1584,7 @@
 		struct qcm_process_device *qpd)
 {
 	int retval;
-	struct queue *q, *next;
+	struct queue *q;
 	struct kernel_queue *kq, *kq_next;
 	struct mqd_manager *mqd_mgr;
 	struct device_process_node *cur, *next_dpn;
@@ -1622,6 +1639,19 @@
 		qpd->reset_wavefronts = false;
 	}
 
+	/* Lastly, free mqd resources.
+	 * Do free_mqd() after dqm_unlock to avoid circular locking.
+	 */
+	while (!list_empty(&qpd->queues_list)) {
+		q = list_first_entry(&qpd->queues_list, struct queue, list);
+		mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
+				q->properties.type)];
+		list_del(&q->list);
+		qpd->queue_count--;
+		dqm_unlock(dqm);
+		mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
+		dqm_lock(dqm);
+	}
 	dqm_unlock(dqm);
 
 	/* Outside the DQM lock because under the DQM lock we can't do
@@ -1630,17 +1660,6 @@
 	if (found)
 		kfd_dec_compute_active(dqm->dev);
 
-	/* Lastly, free mqd resources.
-	 * Do free_mqd() after dqm_unlock to avoid circular locking.
-	 */
-	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
-		mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
-				q->properties.type)];
-		list_del(&q->list);
-		qpd->queue_count--;
-		mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
-	}
-
 	return retval;
 }
 
@@ -1676,7 +1695,8 @@
 	struct kfd_dev *dev = dqm->dev;
 	struct kfd_mem_obj *mem_obj = &dqm->hiq_sdma_mqd;
 	uint32_t size = dqm->mqd_mgrs[KFD_MQD_TYPE_SDMA]->mqd_size *
-		dev->device_info->num_sdma_engines *
+		(dev->device_info->num_sdma_engines +
+		dev->device_info->num_xgmi_sdma_engines) *
 		dev->device_info->num_sdma_queues_per_engine +
 		dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]->mqd_size;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
index 72e4d61..ad05933 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
@@ -58,8 +58,9 @@
 	/* check if sh_mem_config register already configured */
 	if (qpd->sh_mem_config == 0) {
 		qpd->sh_mem_config =
-				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
-					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
+			(SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+				SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
+			(3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
 #if 0
 		/* TODO:
 		 *    This shouldn't be an issue with Navi10.  Verify.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index c56ac47..bc47f6a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -62,6 +62,11 @@
 	}
 
 	kfd->ih_wq = alloc_workqueue("KFD IH", WQ_HIGHPRI, 1);
+	if (unlikely(!kfd->ih_wq)) {
+		kfifo_free(&kfd->ih_fifo);
+		dev_err(kfd_chardev(), "Failed to allocate KFD IH workqueue\n");
+		return -ENOMEM;
+	}
 	spin_lock_init(&kfd->interrupt_lock);
 
 	INIT_WORK(&kfd->interrupt_work, interrupt_wq);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 5f35df2..9266c8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -20,6 +20,10 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/kconfig.h>
+
+#if IS_REACHABLE(CONFIG_AMD_IOMMU_V2)
+
 #include <linux/printk.h>
 #include <linux/device.h>
 #include <linux/slab.h>
@@ -358,3 +362,5 @@
 
 	return 0;
 }
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.h b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.h
index dd23d9f..afd420b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.h
@@ -23,7 +23,9 @@
 #ifndef __KFD_IOMMU_H__
 #define __KFD_IOMMU_H__
 
-#if defined(CONFIG_AMD_IOMMU_V2_MODULE) || defined(CONFIG_AMD_IOMMU_V2)
+#include <linux/kconfig.h>
+
+#if IS_REACHABLE(CONFIG_AMD_IOMMU_V2)
 
 #define KFD_SUPPORT_IOMMU_V2
 
@@ -46,6 +48,9 @@
 }
 static inline int kfd_iommu_device_init(struct kfd_dev *kfd)
 {
+#if IS_MODULE(CONFIG_AMD_IOMMU_V2)
+	WARN_ONCE(1, "iommu_v2 module is not usable by built-in KFD");
+#endif
 	return 0;
 }
 
@@ -73,6 +78,6 @@
 	return 0;
 }
 
-#endif /* defined(CONFIG_AMD_IOMMU_V2) */
+#endif /* IS_REACHABLE(CONFIG_AMD_IOMMU_V2) */
 
 #endif /* __KFD_IOMMU_H__ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 88813da..c021519 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -98,36 +98,78 @@
 		uint32_t *se_mask)
 {
 	struct kfd_cu_info cu_info;
-	uint32_t cu_per_se[KFD_MAX_NUM_SE] = {0};
-	int i, se, sh, cu = 0;
-
+	uint32_t cu_per_sh[KFD_MAX_NUM_SE][KFD_MAX_NUM_SH_PER_SE] = {0};
+	int i, se, sh, cu;
 	amdgpu_amdkfd_get_cu_info(mm->dev->kgd, &cu_info);
 
 	if (cu_mask_count > cu_info.cu_active_number)
 		cu_mask_count = cu_info.cu_active_number;
 
+	/* Exceeding these bounds corrupts the stack and indicates a coding error.
+	 * Returning with no CU's enabled will hang the queue, which should be
+	 * attention grabbing.
+	 */
+	if (cu_info.num_shader_engines > KFD_MAX_NUM_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SE, chip reports %d\n", cu_info.num_shader_engines);
+		return;
+	}
+	if (cu_info.num_shader_arrays_per_engine > KFD_MAX_NUM_SH_PER_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SH, chip reports %d\n",
+			cu_info.num_shader_arrays_per_engine * cu_info.num_shader_engines);
+		return;
+	}
+	/* Count active CUs per SH.
+	 *
+	 * Some CUs in an SH may be disabled.	HW expects disabled CUs to be
+	 * represented in the high bits of each SH's enable mask (the upper and lower
+	 * 16 bits of se_mask) and will take care of the actual distribution of
+	 * disabled CUs within each SH automatically.
+	 * Each half of se_mask must be filled only on bits 0-cu_per_sh[se][sh]-1.
+	 *
+	 * See note on Arcturus cu_bitmap layout in gfx_v9_0_get_cu_info.
+	 */
 	for (se = 0; se < cu_info.num_shader_engines; se++)
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
-			cu_per_se[se] += hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
+			cu_per_sh[se][sh] = hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
 
-	/* Symmetrically map cu_mask to all SEs:
-	 * cu_mask[0] bit0 -> se_mask[0] bit0;
-	 * cu_mask[0] bit1 -> se_mask[1] bit0;
-	 * ... (if # SE is 4)
-	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+	/* Symmetrically map cu_mask to all SEs & SHs:
+	 * se_mask programs up to 2 SH in the upper and lower 16 bits.
+	 *
+	 * Examples
+	 * Assuming 1 SH/SE, 4 SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0
+	 * cu_mask[0] bit1 -> se_mask[1] bit0
 	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit1
+	 * ...
+	 *
+	 * Assuming 2 SH/SE, 4 SEs
+	 * cu_mask[0] bit0 -> se_mask[0] bit0 (SE0,SH0,CU0)
+	 * cu_mask[0] bit1 -> se_mask[1] bit0 (SE1,SH0,CU0)
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit16 (SE0,SH1,CU0)
+	 * cu_mask[0] bit5 -> se_mask[1] bit16 (SE1,SH1,CU0)
+	 * ...
+	 * cu_mask[0] bit8 -> se_mask[0] bit1 (SE0,SH0,CU1)
+	 * ...
+	 *
+	 * First ensure all CUs are disabled, then enable user specified CUs.
 	 */
-	se = 0;
-	for (i = 0; i < cu_mask_count; i++) {
-		if (cu_mask[i / 32] & (1 << (i % 32)))
-			se_mask[se] |= 1 << cu;
+	for (i = 0; i < cu_info.num_shader_engines; i++)
+		se_mask[i] = 0;
 
-		do {
-			se++;
-			if (se == cu_info.num_shader_engines) {
-				se = 0;
-				cu++;
+	i = 0;
+	for (cu = 0; cu < 16; cu++) {
+		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++) {
+			for (se = 0; se < cu_info.num_shader_engines; se++) {
+				if (cu_per_sh[se][sh] > cu) {
+					if (cu_mask[i / 32] & (1 << (i % 32)))
+						se_mask[se] |= 1 << (cu + sh * 16);
+					i++;
+					if (i == cu_mask_count)
+						return;
+				}
 			}
-		} while (cu >= cu_per_se[se] && cu < 32);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index fbdb164..4edc012 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -27,6 +27,7 @@
 #include "kfd_priv.h"
 
 #define KFD_MAX_NUM_SE 8
+#define KFD_MAX_NUM_SH_PER_SE 2
 
 /**
  * struct mqd_manager
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 40e3fc0..aa0a617 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -312,6 +312,7 @@
 					   (int)process->lead_thread->pid);
 		if (ret) {
 			pr_warn("Creating procfs pid directory failed");
+			kobject_put(process->kobj);
 			goto out;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 7551761..a49e2ab 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -612,8 +612,10 @@
 
 	ret = kobject_init_and_add(dev->kobj_node, &node_type,
 			sys_props.kobj_nodes, "%d", id);
-	if (ret < 0)
+	if (ret < 0) {
+		kobject_put(dev->kobj_node);
 		return ret;
+	}
 
 	dev->kobj_mem = kobject_create_and_add("mem_banks", dev->kobj_node);
 	if (!dev->kobj_mem)
@@ -660,8 +662,10 @@
 			return -ENOMEM;
 		ret = kobject_init_and_add(mem->kobj, &mem_type,
 				dev->kobj_mem, "%d", i);
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(mem->kobj);
 			return ret;
+		}
 
 		mem->attr.name = "properties";
 		mem->attr.mode = KFD_SYSFS_FILE_MODE;
@@ -679,8 +683,10 @@
 			return -ENOMEM;
 		ret = kobject_init_and_add(cache->kobj, &cache_type,
 				dev->kobj_cache, "%d", i);
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(cache->kobj);
 			return ret;
+		}
 
 		cache->attr.name = "properties";
 		cache->attr.mode = KFD_SYSFS_FILE_MODE;
@@ -698,8 +704,10 @@
 			return -ENOMEM;
 		ret = kobject_init_and_add(iolink->kobj, &iolink_type,
 				dev->kobj_iolink, "%d", i);
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(iolink->kobj);
 			return ret;
+		}
 
 		iolink->attr.name = "properties";
 		iolink->attr.mode = KFD_SYSFS_FILE_MODE;
@@ -779,8 +787,10 @@
 		ret = kobject_init_and_add(sys_props.kobj_topology,
 				&sysprops_type,  &kfd_device->kobj,
 				"topology");
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(sys_props.kobj_topology);
 			return ret;
+		}
 
 		sys_props.kobj_nodes = kobject_create_and_add("nodes",
 				sys_props.kobj_topology);
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 4139f12..0dc60fe 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -928,8 +928,13 @@
 	struct dmcu_iram_parameters params;
 	unsigned int linear_lut[16];
 	int i;
-	struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu;
-	bool ret = false;
+	struct dmcu *dmcu = NULL;
+	bool ret;
+
+	if (!adev->dm.fw_dmcu)
+		return detect_mst_link_for_all_connectors(adev->ddev);
+
+	dmcu = adev->dm.dc->res_pool->dmcu;
 
 	for (i = 0; i < 16; i++)
 		linear_lut[i] = 0xFFFF * i / 15;
@@ -940,13 +945,15 @@
 	params.backlight_lut_array_size = 16;
 	params.backlight_lut_array = linear_lut;
 
-	/* todo will enable for navi10 */
-	if (adev->asic_type <= CHIP_RAVEN) {
-		ret = dmcu_load_iram(dmcu, params);
+	/* Min backlight level after ABM reduction,  Don't allow below 1%
+	 * 0xFFFF x 0.01 = 0x28F
+	 */
+	params.min_abm_backlight = 0x28F;
 
-		if (!ret)
-			return -EINVAL;
-	}
+	ret = dmcu_load_iram(dmcu, params);
+
+	if (!ret)
+		return -EINVAL;
 
 	return detect_mst_link_for_all_connectors(adev->ddev);
 }
@@ -1086,8 +1093,8 @@
 	link->type = dc_connection_none;
 	prev_sink = link->local_sink;
 
-	if (prev_sink != NULL)
-		dc_sink_retain(prev_sink);
+	if (prev_sink)
+		dc_sink_release(prev_sink);
 
 	switch (link->connector_signal) {
 	case SIGNAL_TYPE_HDMI_TYPE_A: {
@@ -1410,24 +1417,30 @@
 		 * TODO: check if we still need the S3 mode update workaround.
 		 * If yes, put it here.
 		 */
-		if (aconnector->dc_sink)
+		if (aconnector->dc_sink) {
 			amdgpu_dm_update_freesync_caps(connector, NULL);
+			dc_sink_release(aconnector->dc_sink);
+		}
 
 		aconnector->dc_sink = sink;
 		dc_sink_retain(aconnector->dc_sink);
 		if (sink->dc_edid.length == 0) {
 			aconnector->edid = NULL;
-			drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux);
+			if (aconnector->dc_link->aux_mode) {
+				drm_dp_cec_unset_edid(
+					&aconnector->dm_dp_aux.aux);
+			}
 		} else {
 			aconnector->edid =
-				(struct edid *) sink->dc_edid.raw_edid;
-
+				(struct edid *)sink->dc_edid.raw_edid;
 
 			drm_connector_update_edid_property(connector,
-					aconnector->edid);
-			drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
-					    aconnector->edid);
+							   aconnector->edid);
+			if (aconnector->dc_link->aux_mode)
+				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
+						    aconnector->edid);
 		}
+
 		amdgpu_dm_update_freesync_caps(connector, aconnector->edid);
 
 	} else {
@@ -2030,12 +2043,18 @@
 				    &dm_atomic_state_funcs);
 
 	r = amdgpu_display_modeset_create_props(adev);
-	if (r)
+	if (r) {
+		dc_release_state(state->context);
+		kfree(state);
 		return r;
+	}
 
 	r = amdgpu_dm_audio_init(adev);
-	if (r)
+	if (r) {
+		dc_release_state(state->context);
+		kfree(state);
 		return r;
+	}
 
 	return 0;
 }
@@ -2051,6 +2070,8 @@
 #if defined(CONFIG_ACPI)
 	struct amdgpu_dm_backlight_caps caps;
 
+	memset(&caps, 0, sizeof(caps));
+
 	if (dm->backlight_caps.caps_valid)
 		return;
 
@@ -2611,6 +2632,40 @@
 	scaling_info->src_rect.x = state->src_x >> 16;
 	scaling_info->src_rect.y = state->src_y >> 16;
 
+	/*
+	 * For reasons we don't (yet) fully understand a non-zero
+	 * src_y coordinate into an NV12 buffer can cause a
+	 * system hang. To avoid hangs (and maybe be overly cautious)
+	 * let's reject both non-zero src_x and src_y.
+	 *
+	 * We currently know of only one use-case to reproduce a
+	 * scenario with non-zero src_x and src_y for NV12, which
+	 * is to gesture the YouTube Android app into full screen
+	 * on ChromeOS.
+	 */
+	if (state->fb &&
+	    state->fb->format->format == DRM_FORMAT_NV12 &&
+	    (scaling_info->src_rect.x != 0 ||
+	     scaling_info->src_rect.y != 0))
+		return -EINVAL;
+
+	/*
+	 * For reasons we don't (yet) fully understand a non-zero
+	 * src_y coordinate into an NV12 buffer can cause a
+	 * system hang. To avoid hangs (and maybe be overly cautious)
+	 * let's reject both non-zero src_x and src_y.
+	 *
+	 * We currently know of only one use-case to reproduce a
+	 * scenario with non-zero src_x and src_y for NV12, which
+	 * is to gesture the YouTube Android app into full screen
+	 * on ChromeOS.
+	 */
+	if (state->fb &&
+	    state->fb->format->format == DRM_FORMAT_NV12 &&
+	    (scaling_info->src_rect.x != 0 ||
+	     scaling_info->src_rect.y != 0))
+		return -EINVAL;
+
 	scaling_info->src_rect.width = state->src_w >> 16;
 	if (scaling_info->src_rect.width == 0)
 		return -EINVAL;
@@ -2693,7 +2748,8 @@
 			  const union dc_tiling_info *tiling_info,
 			  const uint64_t info,
 			  struct dc_plane_dcc_param *dcc,
-			  struct dc_plane_address *address)
+			  struct dc_plane_address *address,
+			  bool force_disable_dcc)
 {
 	struct dc *dc = adev->dm.dc;
 	struct dc_dcc_surface_param input;
@@ -2705,6 +2761,9 @@
 	memset(&input, 0, sizeof(input));
 	memset(&output, 0, sizeof(output));
 
+	if (force_disable_dcc)
+		return 0;
+
 	if (!offset)
 		return 0;
 
@@ -2754,7 +2813,8 @@
 			     union dc_tiling_info *tiling_info,
 			     struct plane_size *plane_size,
 			     struct dc_plane_dcc_param *dcc,
-			     struct dc_plane_address *address)
+			     struct dc_plane_address *address,
+			     bool force_disable_dcc)
 {
 	const struct drm_framebuffer *fb = &afb->base;
 	int ret;
@@ -2864,7 +2924,8 @@
 
 		ret = fill_plane_dcc_attributes(adev, afb, format, rotation,
 						plane_size, tiling_info,
-						tiling_flags, dcc, address);
+						tiling_flags, dcc, address,
+						force_disable_dcc);
 		if (ret)
 			return ret;
 	}
@@ -2956,7 +3017,8 @@
 			    const struct drm_plane_state *plane_state,
 			    const uint64_t tiling_flags,
 			    struct dc_plane_info *plane_info,
-			    struct dc_plane_address *address)
+			    struct dc_plane_address *address,
+			    bool force_disable_dcc)
 {
 	const struct drm_framebuffer *fb = plane_state->fb;
 	const struct amdgpu_framebuffer *afb =
@@ -3035,7 +3097,8 @@
 					   plane_info->rotation, tiling_flags,
 					   &plane_info->tiling_info,
 					   &plane_info->plane_size,
-					   &plane_info->dcc, address);
+					   &plane_info->dcc, address,
+					   force_disable_dcc);
 	if (ret)
 		return ret;
 
@@ -3058,6 +3121,7 @@
 	struct dc_plane_info plane_info;
 	uint64_t tiling_flags;
 	int ret;
+	bool force_disable_dcc = false;
 
 	ret = fill_dc_scaling_info(plane_state, &scaling_info);
 	if (ret)
@@ -3072,9 +3136,11 @@
 	if (ret)
 		return ret;
 
+	force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 	ret = fill_dc_plane_info_and_addr(adev, plane_state, tiling_flags,
 					  &plane_info,
-					  &dc_plane_state->address);
+					  &dc_plane_state->address,
+					  force_disable_dcc);
 	if (ret)
 		return ret;
 
@@ -3261,27 +3327,21 @@
 	return color_space;
 }
 
-static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
+static bool adjust_colour_depth_from_display_info(
+	struct dc_crtc_timing *timing_out,
+	const struct drm_display_info *info)
 {
-	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
-		return;
-
-	timing_out->display_color_depth--;
-}
-
-static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
-						const struct drm_display_info *info)
-{
+	enum dc_color_depth depth = timing_out->display_color_depth;
 	int normalized_clk;
-	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
-		return;
 	do {
 		normalized_clk = timing_out->pix_clk_100hz / 10;
 		/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
 		if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
 			normalized_clk /= 2;
 		/* Adjusting pix clock following on HDMI spec based on colour depth */
-		switch (timing_out->display_color_depth) {
+		switch (depth) {
+		case COLOR_DEPTH_888:
+			break;
 		case COLOR_DEPTH_101010:
 			normalized_clk = (normalized_clk * 30) / 24;
 			break;
@@ -3292,14 +3352,15 @@
 			normalized_clk = (normalized_clk * 48) / 24;
 			break;
 		default:
-			return;
+			/* The above depths are the only ones valid for HDMI. */
+			return false;
 		}
-		if (normalized_clk <= info->max_tmds_clock)
-			return;
-		reduce_mode_colour_depth(timing_out);
-
-	} while (timing_out->display_color_depth > COLOR_DEPTH_888);
-
+		if (normalized_clk <= info->max_tmds_clock) {
+			timing_out->display_color_depth = depth;
+			return true;
+		}
+	} while (--depth > COLOR_DEPTH_666);
+	return false;
 }
 
 static void fill_stream_properties_from_drm_display_mode(
@@ -3365,8 +3426,14 @@
 
 	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
 	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
-	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
-		adjust_colour_depth_from_display_info(timing_out, info);
+	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+		if (!adjust_colour_depth_from_display_info(timing_out, info) &&
+		    drm_mode_is_420_also(info, mode_in) &&
+		    timing_out->pixel_encoding != PIXEL_ENCODING_YCBCR420) {
+			timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+			adjust_colour_depth_from_display_info(timing_out, info);
+		}
+	}
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
@@ -3923,6 +3990,13 @@
 	struct amdgpu_device *adev = connector->dev->dev_private;
 	struct amdgpu_display_manager *dm = &adev->dm;
 
+	/*
+	 * Call only if mst_mgr was iniitalized before since it's not done
+	 * for all connector types.
+	 */
+	if (aconnector->mst_mgr.dev)
+		drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr);
+
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 
@@ -4266,19 +4340,6 @@
 {
 }
 
-static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state)
-{
-	struct drm_device *dev = new_crtc_state->crtc->dev;
-	struct drm_plane *plane;
-
-	drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) {
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
-			return true;
-	}
-
-	return false;
-}
-
 static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state)
 {
 	struct drm_atomic_state *state = new_crtc_state->state;
@@ -4358,19 +4419,20 @@
 		return ret;
 	}
 
+	/*
+	 * We require the primary plane to be enabled whenever the CRTC is, otherwise
+	 * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other
+	 * planes are disabled, which is not supported by the hardware. And there is legacy
+	 * userspace which stops using the HW cursor altogether in response to the resulting EINVAL.
+	 */
+	if (state->enable &&
+	    !(state->plane_mask & drm_plane_mask(crtc->primary)))
+		return -EINVAL;
+
 	/* In some use cases, like reset, no stream is attached */
 	if (!dm_crtc_state->stream)
 		return 0;
 
-	/*
-	 * We want at least one hardware plane enabled to use
-	 * the stream with a cursor enabled.
-	 */
-	if (state->enable && state->active &&
-	    does_crtc_have_active_cursor(state) &&
-	    dm_crtc_state->active_planes == 0)
-		return -EINVAL;
-
 	if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK)
 		return 0;
 
@@ -4475,6 +4537,7 @@
 	uint64_t tiling_flags;
 	uint32_t domain;
 	int r;
+	bool force_disable_dcc = false;
 
 	dm_plane_state_old = to_dm_plane_state(plane->state);
 	dm_plane_state_new = to_dm_plane_state(new_state);
@@ -4533,11 +4596,13 @@
 			dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) {
 		struct dc_plane_state *plane_state = dm_plane_state_new->dc_state;
 
+		force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 		fill_plane_buffer_attributes(
 			adev, afb, plane_state->format, plane_state->rotation,
 			tiling_flags, &plane_state->tiling_info,
 			&plane_state->plane_size, &plane_state->dcc,
-			&plane_state->address);
+			&plane_state->address,
+			force_disable_dcc);
 	}
 
 	return 0;
@@ -5341,10 +5406,6 @@
 	int x, y;
 	int xorigin = 0, yorigin = 0;
 
-	position->enable = false;
-	position->x = 0;
-	position->y = 0;
-
 	if (!crtc || !plane->state->fb)
 		return 0;
 
@@ -5396,7 +5457,7 @@
 	struct dm_crtc_state *crtc_state = crtc ? to_dm_crtc_state(crtc->state) : NULL;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	uint64_t address = afb ? afb->address : 0;
-	struct dc_cursor_position position;
+	struct dc_cursor_position position = {0};
 	struct dc_cursor_attributes attributes;
 	int ret;
 
@@ -5761,7 +5822,12 @@
 		fill_dc_plane_info_and_addr(
 			dm->adev, new_plane_state, tiling_flags,
 			&bundle->plane_infos[planes_count],
-			&bundle->flip_addrs[planes_count].address);
+			&bundle->flip_addrs[planes_count].address,
+			false);
+
+		DRM_DEBUG_DRIVER("plane: id=%d dcc_en=%d\n",
+				 new_plane_state->plane->index,
+				 bundle->plane_infos[planes_count].dcc.enable);
 
 		bundle->surface_updates[planes_count].plane_info =
 			&bundle->plane_infos[planes_count];
@@ -6429,14 +6495,14 @@
 
 	ret = PTR_ERR_OR_ZERO(conn_state);
 	if (ret)
-		goto err;
+		goto out;
 
 	/* Attach crtc to drm_atomic_state*/
 	crtc_state = drm_atomic_get_crtc_state(state, &disconnected_acrtc->base);
 
 	ret = PTR_ERR_OR_ZERO(crtc_state);
 	if (ret)
-		goto err;
+		goto out;
 
 	/* force a restore */
 	crtc_state->mode_changed = true;
@@ -6446,17 +6512,15 @@
 
 	ret = PTR_ERR_OR_ZERO(plane_state);
 	if (ret)
-		goto err;
-
+		goto out;
 
 	/* Call commit internally with the state we just constructed */
 	ret = drm_atomic_commit(state);
-	if (!ret)
-		return 0;
 
-err:
-	DRM_ERROR("Restoring old state failed with %i\n", ret);
+out:
 	drm_atomic_state_put(state);
+	if (ret)
+		DRM_ERROR("Restoring old state failed with %i\n", ret);
 
 	return ret;
 }
@@ -6785,7 +6849,8 @@
 	BUG_ON(dm_new_crtc_state->stream == NULL);
 
 	/* Scaling or underscan settings */
-	if (is_scaling_state_different(dm_old_conn_state, dm_new_conn_state))
+	if (is_scaling_state_different(dm_old_conn_state, dm_new_conn_state) ||
+				drm_atomic_crtc_needs_modeset(new_crtc_state))
 		update_stream_scaling_settings(
 			&new_crtc_state->mode, dm_new_conn_state, dm_new_crtc_state->stream);
 
@@ -6896,6 +6961,7 @@
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state;
 	struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state;
+	struct amdgpu_crtc *new_acrtc;
 	bool needs_reset;
 	int ret = 0;
 
@@ -6905,9 +6971,23 @@
 	dm_new_plane_state = to_dm_plane_state(new_plane_state);
 	dm_old_plane_state = to_dm_plane_state(old_plane_state);
 
-	/*TODO Implement atomic check for cursor plane */
-	if (plane->type == DRM_PLANE_TYPE_CURSOR)
+	/*TODO Implement better atomic check for cursor plane */
+	if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+		if (!enable || !new_plane_crtc ||
+			drm_atomic_plane_disabling(plane->state, new_plane_state))
+			return 0;
+
+		new_acrtc = to_amdgpu_crtc(new_plane_crtc);
+
+		if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) ||
+			(new_plane_state->crtc_h > new_acrtc->max_cursor_height)) {
+			DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n",
+							 new_plane_state->crtc_w, new_plane_state->crtc_h);
+			return -EINVAL;
+		}
+
 		return 0;
+	}
 
 	needs_reset = should_reset_plane(state, plane, old_plane_state,
 					 new_plane_state);
@@ -6940,8 +7020,7 @@
 				dm_old_plane_state->dc_state,
 				dm_state->context)) {
 
-			ret = EINVAL;
-			return ret;
+			return -EINVAL;
 		}
 
 
@@ -7132,7 +7211,8 @@
 				ret = fill_dc_plane_info_and_addr(
 					dm->adev, new_plane_state, tiling_flags,
 					&plane_info,
-					&flip_addr.address);
+					&flip_addr.address,
+					false);
 				if (ret)
 					goto cleanup;
 
@@ -7180,6 +7260,77 @@
 	*out_type = update_type;
 	return ret;
 }
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm_crtc *crtc)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct amdgpu_dm_connector *aconnector = NULL;
+	int i;
+	for_each_new_connector_in_state(state, connector, conn_state, i) {
+		if (conn_state->crtc != crtc)
+			continue;
+
+		aconnector = to_amdgpu_dm_connector(connector);
+		if (!aconnector->port || !aconnector->mst_port)
+			aconnector = NULL;
+		else
+			break;
+	}
+
+	if (!aconnector)
+		return 0;
+
+	return drm_dp_mst_add_affected_dsc_crtcs(state, &aconnector->mst_port->mst_mgr);
+}
+#endif
+
+static int validate_overlay(struct drm_atomic_state *state)
+{
+	int i;
+	struct drm_plane *plane;
+	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *primary_state, *overlay_state = NULL;
+
+	/* Check if primary plane is contained inside overlay */
+	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
+		if (plane->type == DRM_PLANE_TYPE_OVERLAY) {
+			if (drm_atomic_plane_disabling(plane->state, new_plane_state))
+				return 0;
+
+			overlay_state = new_plane_state;
+			continue;
+		}
+	}
+
+	/* check if we're making changes to the overlay plane */
+	if (!overlay_state)
+		return 0;
+
+	/* check if overlay plane is enabled */
+	if (!overlay_state->crtc)
+		return 0;
+
+	/* find the primary plane for the CRTC that the overlay is enabled on */
+	primary_state = drm_atomic_get_plane_state(state, overlay_state->crtc->primary);
+	if (IS_ERR(primary_state))
+		return PTR_ERR(primary_state);
+
+	/* check if primary plane is enabled */
+	if (!primary_state->crtc)
+		return 0;
+
+	/* Perform the bounds check to ensure the overlay plane covers the primary */
+	if (primary_state->crtc_x < overlay_state->crtc_x ||
+	    primary_state->crtc_y < overlay_state->crtc_y ||
+	    primary_state->crtc_x + primary_state->crtc_w > overlay_state->crtc_x + overlay_state->crtc_w ||
+	    primary_state->crtc_y + primary_state->crtc_h > overlay_state->crtc_y + overlay_state->crtc_h) {
+		DRM_DEBUG_ATOMIC("Overlay plane is enabled with hardware cursor but does not fully cover primary plane\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
 
 /**
  * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM.
@@ -7233,12 +7384,50 @@
 	if (ret)
 		goto fail;
 
+	/* Check connector changes */
+	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
+		struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state);
+		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
+
+		/* Skip connectors that are disabled or part of modeset already. */
+		if (!old_con_state->crtc && !new_con_state->crtc)
+			continue;
+
+		if (!new_con_state->crtc)
+			continue;
+
+		new_crtc_state = drm_atomic_get_crtc_state(state, new_con_state->crtc);
+		if (IS_ERR(new_crtc_state)) {
+			ret = PTR_ERR(new_crtc_state);
+			goto fail;
+		}
+
+		if (dm_old_con_state->abm_level !=
+		    dm_new_con_state->abm_level)
+			new_crtc_state->connectors_changed = true;
+	}
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (dc_resource_is_dsc_encoding_supported(dc)) {
+		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+			if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
+				ret = add_affected_mst_dsc_crtcs(state, crtc);
+				if (ret)
+					goto fail;
+			}
+		}
+	}
+#endif
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		if (!drm_atomic_crtc_needs_modeset(new_crtc_state) &&
 		    !new_crtc_state->color_mgmt_changed &&
 		    old_crtc_state->vrr_enabled == new_crtc_state->vrr_enabled)
 			continue;
 
+		ret = amdgpu_dm_verify_lut_sizes(new_crtc_state);
+		if (ret)
+			goto fail;
+
 		if (!new_crtc_state->enable)
 			continue;
 
@@ -7320,6 +7509,10 @@
 			goto fail;
 	}
 
+	ret = validate_overlay(state);
+	if (ret)
+		goto fail;
+
 	/* Add new/modified planes */
 	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		ret = dm_update_plane_state(dc, state, plane,
@@ -7416,20 +7609,38 @@
 		 * the same resource. If we have a new DC context as part of
 		 * the DM atomic state from validation we need to free it and
 		 * retain the existing one instead.
+		 *
+		 * Furthermore, since the DM atomic state only contains the DC
+		 * context and can safely be annulled, we can free the state
+		 * and clear the associated private object now to free
+		 * some memory and avoid a possible use-after-free later.
 		 */
-		struct dm_atomic_state *new_dm_state, *old_dm_state;
 
-		new_dm_state = dm_atomic_get_new_state(state);
-		old_dm_state = dm_atomic_get_old_state(state);
+		for (i = 0; i < state->num_private_objs; i++) {
+			struct drm_private_obj *obj = state->private_objs[i].ptr;
 
-		if (new_dm_state && old_dm_state) {
-			if (new_dm_state->context)
-				dc_release_state(new_dm_state->context);
+			if (obj->funcs == adev->dm.atomic_obj.funcs) {
+				int j = state->num_private_objs-1;
 
-			new_dm_state->context = old_dm_state->context;
+				dm_atomic_destroy_state(obj,
+						state->private_objs[i].state);
 
-			if (old_dm_state->context)
-				dc_retain_state(old_dm_state->context);
+				/* If i is not at the end of the array then the
+				 * last element needs to be moved to where i was
+				 * before the array can safely be truncated.
+				 */
+				if (i != j)
+					state->private_objs[i] =
+						state->private_objs[j];
+
+				state->private_objs[j].ptr = NULL;
+				state->private_objs[j].state = NULL;
+				state->private_objs[j].old_state = NULL;
+				state->private_objs[j].new_state = NULL;
+
+				state->num_private_objs = j;
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index c8c525a..54163c9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -387,6 +387,7 @@
 #define MAX_COLOR_LEGACY_LUT_ENTRIES 256
 
 void amdgpu_dm_init_color_mod(void);
+int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state);
 int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc);
 int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 				      struct dc_plane_state *dc_plane_state);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index b43bb7f..6acc460 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -210,6 +210,8 @@
 	res = mod_color_calculate_regamma_params(func, gamma, true, has_rom,
 						 NULL);
 
+	dc_gamma_release(&gamma);
+
 	return res ? 0 : -ENOMEM;
 }
 
@@ -276,6 +278,37 @@
 }
 
 /**
+ * Verifies that the Degamma and Gamma LUTs attached to the |crtc_state| are of
+ * the expected size.
+ * Returns 0 on success.
+ */
+int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state)
+{
+	const struct drm_color_lut *lut = NULL;
+	uint32_t size = 0;
+
+	lut = __extract_blob_lut(crtc_state->degamma_lut, &size);
+	if (lut && size != MAX_COLOR_LUT_ENTRIES) {
+		DRM_DEBUG_DRIVER(
+			"Invalid Degamma LUT size. Should be %u but got %u.\n",
+			MAX_COLOR_LUT_ENTRIES, size);
+		return -EINVAL;
+	}
+
+	lut = __extract_blob_lut(crtc_state->gamma_lut, &size);
+	if (lut && size != MAX_COLOR_LUT_ENTRIES &&
+	    size != MAX_COLOR_LEGACY_LUT_ENTRIES) {
+		DRM_DEBUG_DRIVER(
+			"Invalid Gamma LUT size. Should be %u (or %u for legacy) but got %u.\n",
+			MAX_COLOR_LUT_ENTRIES, MAX_COLOR_LEGACY_LUT_ENTRIES,
+			size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
  * amdgpu_dm_update_crtc_color_mgmt: Maps DRM color management to DC stream.
  * @crtc: amdgpu_dm crtc state
  *
@@ -309,14 +342,12 @@
 	bool is_legacy;
 	int r;
 
-	degamma_lut = __extract_blob_lut(crtc->base.degamma_lut, &degamma_size);
-	if (degamma_lut && degamma_size != MAX_COLOR_LUT_ENTRIES)
-		return -EINVAL;
+	r = amdgpu_dm_verify_lut_sizes(&crtc->base);
+	if (r)
+		return r;
 
+	degamma_lut = __extract_blob_lut(crtc->base.degamma_lut, &degamma_size);
 	regamma_lut = __extract_blob_lut(crtc->base.gamma_lut, &regamma_size);
-	if (regamma_lut && regamma_size != MAX_COLOR_LUT_ENTRIES &&
-	    regamma_size != MAX_COLOR_LEGACY_LUT_ENTRIES)
-		return -EINVAL;
 
 	has_degamma =
 		degamma_lut && !__is_lut_linear(degamma_lut, degamma_size);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index a549c7c..f0b001b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -113,7 +113,7 @@
 	mutex_lock(&adev->dm.dc_lock);
 
 	/* Enable CRTC CRC generation if necessary. */
-	if (dm_is_crc_source_crtc(source)) {
+	if (dm_is_crc_source_crtc(source) || source == AMDGPU_DM_PIPE_CRC_SOURCE_NONE) {
 		if (!dc_stream_configure_crc(stream_state->ctx->dc,
 					     stream_state, enable, enable)) {
 			ret = -EINVAL;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f3dfb28..2cdcefa 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -95,29 +95,29 @@
 
 	rd_buf_ptr = rd_buf;
 
-	str_len = strlen("Current:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+	str_len = strlen("Current:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  0x%x  %d  ",
 			link->cur_link_settings.lane_count,
 			link->cur_link_settings.link_rate,
 			link->cur_link_settings.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Verified:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+	str_len = strlen("Verified:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  0x%x  %d  ",
 			link->verified_link_cap.lane_count,
 			link->verified_link_cap.link_rate,
 			link->verified_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Reported:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+	str_len = strlen("Reported:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  0x%x  %d  ",
 			link->reported_link_cap.lane_count,
 			link->reported_link_cap.link_rate,
 			link->reported_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Preferred:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
+	str_len = strlen("Preferred:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  0x%x  %d\n",
 			link->preferred_link_setting.lane_count,
 			link->preferred_link_setting.link_rate,
 			link->preferred_link_setting.link_spread);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index ee1dc75..1d733b5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -247,7 +247,8 @@
 		drm_dp_mst_reset_vcpi_slots(mst_mgr, mst_port);
 	}
 
-	ret = drm_dp_update_payload_part1(mst_mgr);
+	/* It's OK for this to fail */
+	drm_dp_update_payload_part1(mst_mgr);
 
 	/* mst_mgr->->payloads are VC payload notify MST branch using DPCD or
 	 * AUX message. The sequence is slot 1-63 allocated sequence for each
@@ -256,9 +257,6 @@
 
 	get_payload_table(aconnector, proposed_table);
 
-	if (ret)
-		return false;
-
 	return true;
 }
 
@@ -316,7 +314,6 @@
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_dp_mst_topology_mgr *mst_mgr;
 	struct drm_dp_mst_port *mst_port;
-	int ret;
 
 	aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 
@@ -330,10 +327,8 @@
 	if (!mst_mgr->mst_state)
 		return false;
 
-	ret = drm_dp_update_payload_part2(mst_mgr);
-
-	if (ret)
-		return false;
+	/* It's OK for this to fail */
+	drm_dp_update_payload_part2(mst_mgr);
 
 	if (!enable)
 		drm_dp_mst_deallocate_vcpi(mst_mgr, mst_port);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 16218a2..2f85850 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -101,7 +101,7 @@
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
-	if (payload.write)
+	if (payload.write && result >= 0)
 		result = msg->size;
 
 	if (result < 0)
@@ -379,6 +379,7 @@
 					   aconnector->dc_sink);
 		dc_sink_release(aconnector->dc_sink);
 		aconnector->dc_sink = NULL;
+		aconnector->dc_link->cur_link_settings.lane_count = 0;
 	}
 
 	drm_connector_unregister(connector);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index f4cfa0c..7241d4c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -342,7 +342,8 @@
 	if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_clock_by_type) {
 		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
 			dc_to_pp_clock_type(clk_type), &pp_clks)) {
-		/* Error in pplib. Provide default values. */
+			/* Error in pplib. Provide default values. */
+			get_default_clock_levels(clk_type, dc_clks);
 			return true;
 		}
 	} else if (adev->smu.funcs && adev->smu.funcs->get_clock_by_type) {
@@ -529,6 +530,8 @@
 			&pp_clk_info);
 	else if (adev->smu.funcs)
 		ret = smu_get_current_clocks(&adev->smu, &pp_clk_info);
+	else
+		return false;
 	if (ret)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index 221e0f5..823843c 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -2543,7 +2543,6 @@
 
 	/* Sort voltage table from low to high*/
 	if (result == BP_RESULT_OK) {
-		struct clock_voltage_caps temp = {0, 0};
 		uint32_t i;
 		uint32_t j;
 
@@ -2553,10 +2552,8 @@
 						info->disp_clk_voltage[j].max_supported_clk <
 						info->disp_clk_voltage[j-1].max_supported_clk) {
 					/* swap j and j - 1*/
-					temp = info->disp_clk_voltage[j-1];
-					info->disp_clk_voltage[j-1] =
-							info->disp_clk_voltage[j];
-					info->disp_clk_voltage[j] = temp;
+					swap(info->disp_clk_voltage[j - 1],
+					     info->disp_clk_voltage[j]);
 				}
 			}
 		}
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 dff65c0..7873abe 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1613,8 +1613,6 @@
 
 	struct atom_common_table_header *header;
 	struct atom_data_revision revision;
-
-	struct clock_voltage_caps temp = {0, 0};
 	uint32_t i;
 	uint32_t j;
 
@@ -1644,10 +1642,8 @@
 				info->disp_clk_voltage[j-1].max_supported_clk
 				) {
 				/* swap j and j - 1*/
-				temp = info->disp_clk_voltage[j-1];
-				info->disp_clk_voltage[j-1] =
-					info->disp_clk_voltage[j];
-				info->disp_clk_voltage[j] = temp;
+				swap(info->disp_clk_voltage[j - 1],
+				     info->disp_clk_voltage[j]);
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 5815983..0d2e136 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -245,6 +245,23 @@
 					cntl->enable_dp_audio);
 	params.ucLaneNum = (uint8_t)(cntl->lanes_number);
 
+	switch (cntl->color_depth) {
+	case COLOR_DEPTH_888:
+		params.ucBitPerColor = PANEL_8BIT_PER_COLOR;
+		break;
+	case COLOR_DEPTH_101010:
+		params.ucBitPerColor = PANEL_10BIT_PER_COLOR;
+		break;
+	case COLOR_DEPTH_121212:
+		params.ucBitPerColor = PANEL_12BIT_PER_COLOR;
+		break;
+	case COLOR_DEPTH_161616:
+		params.ucBitPerColor = PANEL_16BIT_PER_COLOR;
+		break;
+	default:
+		break;
+	}
+
 	if (EXEC_BIOS_CMD_TABLE(DIGxEncoderControl, params))
 		result = BP_RESULT_OK;
 
@@ -274,6 +291,23 @@
 					cntl->enable_dp_audio));
 	params.ucLaneNum = (uint8_t)(cntl->lanes_number);
 
+	switch (cntl->color_depth) {
+	case COLOR_DEPTH_888:
+		params.ucBitPerColor = PANEL_8BIT_PER_COLOR;
+		break;
+	case COLOR_DEPTH_101010:
+		params.ucBitPerColor = PANEL_10BIT_PER_COLOR;
+		break;
+	case COLOR_DEPTH_121212:
+		params.ucBitPerColor = PANEL_12BIT_PER_COLOR;
+		break;
+	case COLOR_DEPTH_161616:
+		params.ucBitPerColor = PANEL_16BIT_PER_COLOR;
+		break;
+	default:
+		break;
+	}
+
 	if (EXEC_BIOS_CMD_TABLE(DIGxEncoderControl, params))
 		result = BP_RESULT_OK;
 
@@ -1057,6 +1091,19 @@
 		 * driver choose program it itself, i.e. here we program it
 		 * to 888 by default.
 		 */
+		if (bp_params->signal_type == SIGNAL_TYPE_HDMI_TYPE_A)
+			switch (bp_params->color_depth) {
+			case TRANSMITTER_COLOR_DEPTH_30:
+				/* yes this is correct, the atom define is wrong */
+				clk.sPCLKInput.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_32BPP;
+				break;
+			case TRANSMITTER_COLOR_DEPTH_36:
+				/* yes this is correct, the atom define is wrong */
+				clk.sPCLKInput.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
+				break;
+			default:
+				break;
+			}
 
 		if (EXEC_BIOS_CMD_TABLE(SetPixelClock, clk))
 			result = BP_RESULT_OK;
@@ -1135,6 +1182,20 @@
 		 * driver choose program it itself, i.e. here we pass required
 		 * target rate that includes deep color.
 		 */
+		if (bp_params->signal_type == SIGNAL_TYPE_HDMI_TYPE_A)
+			switch (bp_params->color_depth) {
+			case TRANSMITTER_COLOR_DEPTH_30:
+				clk.sPCLKInput.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP_V6;
+				break;
+			case TRANSMITTER_COLOR_DEPTH_36:
+				clk.sPCLKInput.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP_V6;
+				break;
+			case TRANSMITTER_COLOR_DEPTH_48:
+				clk.sPCLKInput.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
+				break;
+			default:
+				break;
+			}
 
 		if (EXEC_BIOS_CMD_TABLE(SetPixelClock, clk))
 			result = BP_RESULT_OK;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 9b2cb57..c9a241f 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1438,6 +1438,7 @@
 	struct dc_context *ctx = dc->ctx;
 	struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0};
 	bool res;
+	unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx;
 
 	/* TODO: This is not the proper way to obtain fabric_and_dram_bandwidth, should be min(fclk, memclk) */
 	res = dm_pp_get_clock_levels_by_type_with_voltage(
@@ -1449,17 +1450,28 @@
 		res = verify_clock_values(&fclks);
 
 	if (res) {
-		ASSERT(fclks.num_levels >= 3);
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (fclks.data[0].clocks_in_khz / 1000.0) / 1000.0;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = dc->dcn_soc->number_of_channels *
-				(fclks.data[fclks.num_levels - (fclks.num_levels > 2 ? 3 : 2)].clocks_in_khz / 1000.0)
-				* ddr4_dram_factor_single_Channel / 1000.0;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = dc->dcn_soc->number_of_channels *
-				(fclks.data[fclks.num_levels - 2].clocks_in_khz / 1000.0)
-				* ddr4_dram_factor_single_Channel / 1000.0;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = dc->dcn_soc->number_of_channels *
-				(fclks.data[fclks.num_levels - 1].clocks_in_khz / 1000.0)
-				* ddr4_dram_factor_single_Channel / 1000.0;
+		ASSERT(fclks.num_levels);
+
+		vmin0p65_idx = 0;
+		vmid0p72_idx = fclks.num_levels -
+			(fclks.num_levels > 2 ? 3 : (fclks.num_levels > 1 ? 2 : 1));
+		vnom0p8_idx = fclks.num_levels - (fclks.num_levels > 1 ? 2 : 1);
+		vmax0p9_idx = fclks.num_levels - 1;
+
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 =
+			32 * (fclks.data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 =
+			dc->dcn_soc->number_of_channels *
+			(fclks.data[vmid0p72_idx].clocks_in_khz / 1000.0)
+			* ddr4_dram_factor_single_Channel / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 =
+			dc->dcn_soc->number_of_channels *
+			(fclks.data[vnom0p8_idx].clocks_in_khz / 1000.0)
+			* ddr4_dram_factor_single_Channel / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 =
+			dc->dcn_soc->number_of_channels *
+			(fclks.data[vmax0p9_idx].clocks_in_khz / 1000.0)
+			* ddr4_dram_factor_single_Channel / 1000.0;
 	} else
 		BREAK_TO_DEBUGGER();
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index b864869c..6fa7422 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -91,6 +91,12 @@
 ###############################################################################
 CLK_MGR_DCN21 = rn_clk_mgr.o rn_clk_mgr_vbios_smu.o
 
+# prevent build errors regarding soft-float vs hard-float FP ABI tags
+# this code is currently unused on ppc64, as it applies to Renoir APUs only
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
+endif
+
 AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
index 47f529c..2718396 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
@@ -85,12 +85,77 @@
 	return disp_clk_threshold;
 }
 
-static void ramp_up_dispclk_with_dpp(struct clk_mgr_internal *clk_mgr, struct dc *dc, struct dc_clocks *new_clocks)
+static void ramp_up_dispclk_with_dpp(
+		struct clk_mgr_internal *clk_mgr,
+		struct dc *dc,
+		struct dc_clocks *new_clocks,
+		bool safe_to_lower)
 {
 	int i;
 	int dispclk_to_dpp_threshold = rv1_determine_dppclk_threshold(clk_mgr, new_clocks);
 	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
 
+	/* this function is to change dispclk, dppclk and dprefclk according to
+	 * bandwidth requirement. Its call stack is rv1_update_clocks -->
+	 * update_clocks --> dcn10_prepare_bandwidth / dcn10_optimize_bandwidth
+	 * --> prepare_bandwidth / optimize_bandwidth. before change dcn hw,
+	 * prepare_bandwidth will be called first to allow enough clock,
+	 * watermark for change, after end of dcn hw change, optimize_bandwidth
+	 * is executed to lower clock to save power for new dcn hw settings.
+	 *
+	 * below is sequence of commit_planes_for_stream:
+	 *
+	 * step 1: prepare_bandwidth - raise clock to have enough bandwidth
+	 * step 2: lock_doublebuffer_enable
+	 * step 3: pipe_control_lock(true) - make dchubp register change will
+	 * not take effect right way
+	 * step 4: apply_ctx_for_surface - program dchubp
+	 * step 5: pipe_control_lock(false) - dchubp register change take effect
+	 * step 6: optimize_bandwidth --> dc_post_update_surfaces_to_stream
+	 * for full_date, optimize clock to save power
+	 *
+	 * at end of step 1, dcn clocks (dprefclk, dispclk, dppclk) may be
+	 * changed for new dchubp configuration. but real dcn hub dchubps are
+	 * still running with old configuration until end of step 5. this need
+	 * clocks settings at step 1 should not less than that before step 1.
+	 * this is checked by two conditions: 1. if (should_set_clock(safe_to_lower
+	 * , new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) ||
+	 * new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz)
+	 * 2. request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz
+	 *
+	 * the second condition is based on new dchubp configuration. dppclk
+	 * for new dchubp may be different from dppclk before step 1.
+	 * for example, before step 1, dchubps are as below:
+	 * pipe 0: recout=(0,40,1920,980) viewport=(0,0,1920,979)
+	 * pipe 1: recout=(0,0,1920,1080) viewport=(0,0,1920,1080)
+	 * for dppclk for pipe0 need dppclk = dispclk
+	 *
+	 * new dchubp pipe split configuration:
+	 * pipe 0: recout=(0,0,960,1080) viewport=(0,0,960,1080)
+	 * pipe 1: recout=(960,0,960,1080) viewport=(960,0,960,1080)
+	 * dppclk only needs dppclk = dispclk /2.
+	 *
+	 * dispclk, dppclk are not lock by otg master lock. they take effect
+	 * after step 1. during this transition, dispclk are the same, but
+	 * dppclk is changed to half of previous clock for old dchubp
+	 * configuration between step 1 and step 6. This may cause p-state
+	 * warning intermittently.
+	 *
+	 * for new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz, we
+	 * need make sure dppclk are not changed to less between step 1 and 6.
+	 * for new_clocks->dispclk_khz > clk_mgr_base->clks.dispclk_khz,
+	 * new display clock is raised, but we do not know ratio of
+	 * new_clocks->dispclk_khz and clk_mgr_base->clks.dispclk_khz,
+	 * new_clocks->dispclk_khz /2 does not guarantee equal or higher than
+	 * old dppclk. we could ignore power saving different between
+	 * dppclk = displck and dppclk = dispclk / 2 between step 1 and step 6.
+	 * as long as safe_to_lower = false, set dpclk = dispclk to simplify
+	 * condition check.
+	 * todo: review this change for other asic.
+	 **/
+	if (!safe_to_lower)
+		request_dpp_div = false;
+
 	/* set disp clk to dpp clk threshold */
 
 	clk_mgr->funcs->set_dispclk(clk_mgr, dispclk_to_dpp_threshold);
@@ -206,7 +271,7 @@
 	/* program dispclk on = as a w/a for sleep resume clock ramping issues */
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)
 			|| new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz) {
-		ramp_up_dispclk_with_dpp(clk_mgr, dc, new_clocks);
+		ramp_up_dispclk_with_dpp(clk_mgr, dc, new_clocks, safe_to_lower);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		send_request_to_lower = true;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 3e8ac30..23ec283 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -320,6 +320,8 @@
 		struct dc_state *context,
 		bool safe_to_lower)
 {
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+
 	struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
 	/* Min fclk = 1.2GHz since all the extra scemi logic seems to run off of it */
 	int fclk_adj = new_clocks->fclk_khz > 1200000 ? new_clocks->fclk_khz : 1200000;
@@ -357,14 +359,18 @@
 		clk_mgr->clks.dispclk_khz = new_clocks->dispclk_khz;
 	}
 
-	/* Both fclk and dppclk ref are run on the same scemi clock so we
-	 * need to keep the same value for both
+	/* Both fclk and ref_dppclk run on the same scemi clock.
+	 * So take the higher value since the DPP DTO is typically programmed
+	 * such that max dppclk is 1:1 with ref_dppclk.
 	 */
 	if (clk_mgr->clks.fclk_khz > clk_mgr->clks.dppclk_khz)
 		clk_mgr->clks.dppclk_khz = clk_mgr->clks.fclk_khz;
 	if (clk_mgr->clks.dppclk_khz > clk_mgr->clks.fclk_khz)
 		clk_mgr->clks.fclk_khz = clk_mgr->clks.dppclk_khz;
 
+	// Both fclk and ref_dppclk run on the same scemi clock.
+	clk_mgr_int->dccg->ref_dppclk = clk_mgr->clks.fclk_khz;
+
 	dm_set_dcn_clocks(clk_mgr->ctx, &clk_mgr->clks);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 787f94d..9f301f8 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -91,8 +91,23 @@
 		rn_vbios_smu_set_min_deep_sleep_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz);
 	}
 
-	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
-		if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz)
+	// workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow.
+	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
+		if (new_clocks->dppclk_khz < 100000)
+			new_clocks->dppclk_khz = 100000;
+	}
+
+	/*
+	 * Temporally ignore thew 0 cases for disp and dpp clks.
+	 * We may have a new feature that requires 0 clks in the future.
+	 */
+	if (new_clocks->dppclk_khz == 0 || new_clocks->dispclk_khz == 0) {
+		new_clocks->dppclk_khz = clk_mgr_base->clks.dppclk_khz;
+		new_clocks->dispclk_khz = clk_mgr_base->clks.dispclk_khz;
+	}
+
+	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) {
+		if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz)
 			dpp_clock_lowered = true;
 		clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz;
 		update_dppclk = true;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
index 50984c1..468c6bb 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
@@ -33,7 +33,7 @@
 #include "mp/mp_12_0_0_sh_mask.h"
 
 #define REG(reg_name) \
-	(MP1_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
+	(MP0_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
 
 #define FN(reg_name, field) \
 	FD(reg_name##__##field)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 4b8819c..14dc1b8 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -283,6 +283,8 @@
 	int i = 0;
 	bool ret = false;
 
+	stream->adjust = *adjust;
+
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
@@ -905,15 +907,11 @@
 
 		/* set first pipe with plane as master */
 		for (j = 0; j < group_size; j++) {
-			struct pipe_ctx *temp;
-
 			if (pipe_set[j]->plane_state) {
 				if (j == 0)
 					break;
 
-				temp = pipe_set[0];
-				pipe_set[0] = pipe_set[j];
-				pipe_set[j] = temp;
+				swap(pipe_set[0], pipe_set[j]);
 				break;
 			}
 		}
@@ -1180,6 +1178,26 @@
 	return (result == DC_OK);
 }
 
+static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context)
+{
+	int i;
+	struct pipe_ctx *pipe;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->plane_state)
+			continue;
+
+		/* Must set to false to start with, due to OR in update function */
+		pipe->plane_state->status.is_flip_pending = false;
+		dc->hwss.update_pending_status(pipe);
+		if (pipe->plane_state->status.is_flip_pending)
+			return true;
+	}
+	return false;
+}
+
 bool dc_post_update_surfaces_to_stream(struct dc *dc)
 {
 	int i;
@@ -1190,6 +1208,9 @@
 
 	post_surface_trace(dc);
 
+	if (is_flip_pending_in_pipes(dc, context))
+		return true;
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (context->res_ctx.pipe_ctx[i].stream == NULL ||
 		    context->res_ctx.pipe_ctx[i].plane_state == NULL) {
@@ -1940,7 +1961,8 @@
 					if (pipe_ctx->stream_res.audio && !dc->debug.az_endpoint_mute_only)
 						pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
 
-					dc->hwss.optimize_bandwidth(dc, dc->current_state);
+					dc->optimized_required = true;
+
 				} else {
 					if (!dc->optimize_seamless_boot)
 						dc->hwss.prepare_bandwidth(dc, dc->current_state);
@@ -2028,6 +2050,10 @@
 						plane_state->triplebuffer_flips = true;
 				}
 			}
+			if (update_type == UPDATE_TYPE_FULL) {
+				/* force vsync flip when reconfiguring pipes to prevent underflow */
+				plane_state->flip_immediate = false;
+			}
 		}
 	}
 #endif
@@ -2152,7 +2178,7 @@
 	enum surface_update_type update_type;
 	struct dc_state *context;
 	struct dc_context *dc_ctx = dc->ctx;
-	int i;
+	int i, j;
 
 	stream_status = dc_stream_get_status(stream);
 	context = dc->current_state;
@@ -2190,10 +2216,29 @@
 
 		copy_surface_update_to_plane(surface, &srf_updates[i]);
 
+		if (update_type >= UPDATE_TYPE_MED) {
+			for (j = 0; j < dc->res_pool->pipe_count; j++) {
+				struct pipe_ctx *pipe_ctx =
+					&context->res_ctx.pipe_ctx[j];
+
+				if (pipe_ctx->plane_state != surface)
+					continue;
+
+				resource_build_scaling_params(pipe_ctx);
+			}
+		}
 	}
 
 	copy_stream_update_to_stream(dc, context, stream, stream_update);
 
+	if (update_type > UPDATE_TYPE_FAST) {
+		if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
+			DC_ERROR("Mode validation failed for stream update!\n");
+			dc_release_state(context);
+			return;
+		}
+	}
+
 	commit_planes_for_stream(
 				dc,
 				srf_updates,
@@ -2267,12 +2312,7 @@
 	enum dc_acpi_cm_power_state power_state)
 {
 	struct kref refcount;
-	struct display_mode_lib *dml = kzalloc(sizeof(struct display_mode_lib),
-						GFP_KERNEL);
-
-	ASSERT(dml);
-	if (!dml)
-		return;
+	struct display_mode_lib *dml;
 
 	switch (power_state) {
 	case DC_ACPI_CM_POWER_STATE_D0:
@@ -2294,6 +2334,12 @@
 		 * clean state, and dc hw programming optimizations will not
 		 * cause any trouble.
 		 */
+		dml = kzalloc(sizeof(struct display_mode_lib),
+				GFP_KERNEL);
+
+		ASSERT(dml);
+		if (!dml)
+			return;
 
 		/* Preserve refcount */
 		refcount = dc->current_state->refcount;
@@ -2307,10 +2353,10 @@
 		dc->current_state->refcount = refcount;
 		dc->current_state->bw_ctx.dml = *dml;
 
+		kfree(dml);
+
 		break;
 	}
-
-	kfree(dml);
 }
 
 void dc_resume(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index ca20b15..6b03267 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -373,7 +373,7 @@
 
 	if (GPIO_RESULT_OK != dal_ddc_open(
 		ddc, GPIO_MODE_INPUT, GPIO_DDC_CONFIG_TYPE_MODE_I2C)) {
-		dal_gpio_destroy_ddc(&ddc);
+		dal_ddc_close(ddc);
 
 		return present;
 	}
@@ -809,8 +809,8 @@
 		}
 
 		case SIGNAL_TYPE_EDP: {
-			read_edp_current_link_settings_on_detect(link);
 			detect_edp_sink_caps(link);
+			read_edp_current_link_settings_on_detect(link);
 			sink_caps.transaction_type =
 				DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
 			sink_caps.signal = SIGNAL_TYPE_EDP;
@@ -936,6 +936,24 @@
 			    dc_is_dvi_signal(link->connector_signal)) {
 				if (prev_sink != NULL)
 					dc_sink_release(prev_sink);
+				link_disconnect_sink(link);
+
+				return false;
+			}
+			/*
+			 * Abort detection for DP connectors if we have
+			 * no EDID and connector is active converter
+			 * as there are no display downstream
+			 *
+			 */
+			if (dc_is_dp_sst_signal(link->connector_signal) &&
+				(link->dpcd_caps.dongle_type ==
+						DISPLAY_DONGLE_DP_VGA_CONVERTER ||
+				link->dpcd_caps.dongle_type ==
+						DISPLAY_DONGLE_DP_DVI_CONVERTER)) {
+				if (prev_sink)
+					dc_sink_release(prev_sink);
+				link_disconnect_sink(link);
 
 				return false;
 			}
@@ -948,8 +966,7 @@
 			same_edid = is_same_edid(&prev_sink->dc_edid, &sink->dc_edid);
 
 		if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
-			sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX &&
-			reason != DETECT_REASON_HPDRX) {
+			sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX) {
 			/*
 			 * TODO debug why Dell 2413 doesn't like
 			 *  two link trainings
@@ -1304,6 +1321,11 @@
 		goto ddc_create_fail;
 	}
 
+	if (!link->ddc->ddc_pin) {
+		DC_ERROR("Failed to get I2C info for connector!\n");
+		goto ddc_create_fail;
+	}
+
 	link->ddc_hw_inst =
 		dal_ddc_get_line(
 			dal_ddc_service_get_ddc_pin(link->ddc));
@@ -1734,8 +1756,7 @@
 				slave_address, buffer[0], buffer[1], i2c_success?1:0);
 
 			if (!i2c_success)
-				/* Write failure */
-				ASSERT(i2c_success);
+				goto i2c_write_fail;
 
 			/* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A
 			 * needs to be set to 1 on every 0xA-0xC write.
@@ -1753,8 +1774,7 @@
 						pipe_ctx->stream->link->ddc,
 						slave_address, &offset, 1, &value, 1);
 					if (!i2c_success)
-						/* Write failure */
-						ASSERT(i2c_success);
+						goto i2c_write_fail;
 				}
 
 				buffer[0] = offset;
@@ -1766,8 +1786,7 @@
 					offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 					slave_address, buffer[0], buffer[1], i2c_success?1:0);
 				if (!i2c_success)
-					/* Write failure */
-					ASSERT(i2c_success);
+					goto i2c_write_fail;
 			}
 		}
 	}
@@ -1787,8 +1806,7 @@
 					slave_address, buffer[0], buffer[1], i2c_success?1:0);
 
 				if (!i2c_success)
-					/* Write failure */
-					ASSERT(i2c_success);
+					goto i2c_write_fail;
 
 				/* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A
 				 * needs to be set to 1 on every 0xA-0xC write.
@@ -1806,8 +1824,7 @@
 								pipe_ctx->stream->link->ddc,
 								slave_address, &offset, 1, &value, 1);
 						if (!i2c_success)
-							/* Write failure */
-							ASSERT(i2c_success);
+							goto i2c_write_fail;
 					}
 
 					buffer[0] = offset;
@@ -1819,8 +1836,7 @@
 						offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 						slave_address, buffer[0], buffer[1], i2c_success?1:0);
 					if (!i2c_success)
-						/* Write failure */
-						ASSERT(i2c_success);
+						goto i2c_write_fail;
 				}
 			}
 		}
@@ -1838,8 +1854,7 @@
 				offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 				slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
-			/* Write failure */
-			ASSERT(i2c_success);
+			goto i2c_write_fail;
 
 		/* Write offset 0x00 to 0x23 */
 		buffer[0] = 0x00;
@@ -1850,8 +1865,7 @@
 			offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
-			/* Write failure */
-			ASSERT(i2c_success);
+			goto i2c_write_fail;
 
 		/* Write offset 0xff to 0x00 */
 		buffer[0] = 0xff;
@@ -1862,10 +1876,14 @@
 			offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
-			/* Write failure */
-			ASSERT(i2c_success);
+			goto i2c_write_fail;
 
 	}
+
+	return;
+
+i2c_write_fail:
+	DC_LOG_DEBUG("Set retimer failed");
 }
 
 static void write_i2c_default_retimer_setting(
@@ -1890,8 +1908,7 @@
 		offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 		slave_address, buffer[0], buffer[1], i2c_success?1:0);
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		goto i2c_write_fail;
 
 	/* Write offset 0x0A to 0x17 */
 	buffer[0] = 0x0A;
@@ -1902,8 +1919,7 @@
 		offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 		slave_address, buffer[0], buffer[1], i2c_success?1:0);
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		goto i2c_write_fail;
 
 	/* Write offset 0x0B to 0xDA or 0xD8 */
 	buffer[0] = 0x0B;
@@ -1914,8 +1930,7 @@
 		offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 		slave_address, buffer[0], buffer[1], i2c_success?1:0);
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		goto i2c_write_fail;
 
 	/* Write offset 0x0A to 0x17 */
 	buffer[0] = 0x0A;
@@ -1926,8 +1941,7 @@
 		offset = 0x%x, reg_val= 0x%x, i2c_success = %d\n",
 		slave_address, buffer[0], buffer[1], i2c_success?1:0);
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		goto i2c_write_fail;
 
 	/* Write offset 0x0C to 0x1D or 0x91 */
 	buffer[0] = 0x0C;
@@ -1938,8 +1952,7 @@
 		offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 		slave_address, buffer[0], buffer[1], i2c_success?1:0);
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		goto i2c_write_fail;
 
 	/* Write offset 0x0A to 0x17 */
 	buffer[0] = 0x0A;
@@ -1950,8 +1963,7 @@
 		offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 		slave_address, buffer[0], buffer[1], i2c_success?1:0);
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		goto i2c_write_fail;
 
 
 	if (is_vga_mode) {
@@ -1966,8 +1978,7 @@
 			offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
-			/* Write failure */
-			ASSERT(i2c_success);
+			goto i2c_write_fail;
 
 		/* Write offset 0x00 to 0x23 */
 		buffer[0] = 0x00;
@@ -1978,8 +1989,7 @@
 			offset = 0x%x, reg_val= 0x%x, i2c_success = %d\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
-			/* Write failure */
-			ASSERT(i2c_success);
+			goto i2c_write_fail;
 
 		/* Write offset 0xff to 0x00 */
 		buffer[0] = 0xff;
@@ -1990,9 +2000,13 @@
 			offset = 0x%x, reg_val= 0x%x, i2c_success = %d end here\n",
 			slave_address, buffer[0], buffer[1], i2c_success?1:0);
 		if (!i2c_success)
-			/* Write failure */
-			ASSERT(i2c_success);
+			goto i2c_write_fail;
 	}
+
+	return;
+
+i2c_write_fail:
+	DC_LOG_DEBUG("Set default retimer failed");
 }
 
 static void write_i2c_redriver_setting(
@@ -2021,8 +2035,7 @@
 		slave_address, buffer[3], buffer[4], buffer[5], buffer[6], i2c_success?1:0);
 
 	if (!i2c_success)
-		/* Write failure */
-		ASSERT(i2c_success);
+		DC_LOG_DEBUG("Set redriver failed");
 }
 
 static void enable_link_hdmi(struct pipe_ctx *pipe_ctx)
@@ -2169,8 +2182,10 @@
 			dp_set_fec_ready(link, false);
 		}
 #endif
-	} else
-		link->link_enc->funcs->disable_output(link->link_enc, signal);
+	} else {
+		if (signal != SIGNAL_TYPE_VIRTUAL)
+			link->link_enc->funcs->disable_output(link->link_enc, signal);
+	}
 
 	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
 		/* MST disable link only when no stream use the link */
@@ -2217,7 +2232,7 @@
 		break;
 	}
 
-	if (dongle_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
+	if (dpcd_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
 		dongle_caps->extendedCapValid == false)
 		return true;
 
@@ -2276,7 +2291,7 @@
 	/* A hack to avoid failing any modes for EDID override feature on
 	 * topology change such as lower quality cable for DP or different dongle
 	 */
-	if (link->remote_sinks[0])
+	if (link->remote_sinks[0] && link->remote_sinks[0]->sink_signal == SIGNAL_TYPE_VIRTUAL)
 		return DC_OK;
 
 	/* Passive Dongle */
@@ -2917,8 +2932,12 @@
 
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (timing->flags.DSC) {
-		kbps = (timing->pix_clk_100hz * timing->dsc_cfg.bits_per_pixel);
-		kbps = kbps / 160 + ((kbps % 160) ? 1 : 0);
+		struct fixed31_32 link_bw_kbps;
+
+		link_bw_kbps = dc_fixpt_from_int(timing->pix_clk_100hz);
+		link_bw_kbps = dc_fixpt_div_int(link_bw_kbps, 160);
+		link_bw_kbps = dc_fixpt_mul_int(link_bw_kbps, timing->dsc_cfg.bits_per_pixel);
+		kbps = dc_fixpt_ceil(link_bw_kbps);
 		return kbps;
 	}
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 51991bf..4c90d68 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -126,22 +126,16 @@
 	struct vector payloads;
 };
 
-static struct i2c_payloads *dal_ddc_i2c_payloads_create(struct dc_context *ctx, uint32_t count)
+static bool dal_ddc_i2c_payloads_create(
+		struct dc_context *ctx,
+		struct i2c_payloads *payloads,
+		uint32_t count)
 {
-	struct i2c_payloads *payloads;
-
-	payloads = kzalloc(sizeof(struct i2c_payloads), GFP_KERNEL);
-
-	if (!payloads)
-		return NULL;
-
 	if (dal_vector_construct(
 		&payloads->payloads, ctx, count, sizeof(struct i2c_payload)))
-		return payloads;
+		return true;
 
-	kfree(payloads);
-	return NULL;
-
+	return false;
 }
 
 static struct i2c_payload *dal_ddc_i2c_payloads_get(struct i2c_payloads *p)
@@ -154,14 +148,12 @@
 	return p->payloads.count;
 }
 
-static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads **p)
+static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads *p)
 {
-	if (!p || !*p)
+	if (!p)
 		return;
-	dal_vector_destruct(&(*p)->payloads);
-	kfree(*p);
-	*p = NULL;
 
+	dal_vector_destruct(&p->payloads);
 }
 
 #define DDC_MIN(a, b) (((a) < (b)) ? (a) : (b))
@@ -521,9 +513,13 @@
 
 	uint32_t payloads_num = write_payloads + read_payloads;
 
+
 	if (write_size > EDID_SEGMENT_SIZE || read_size > EDID_SEGMENT_SIZE)
 		return false;
 
+	if (!payloads_num)
+		return false;
+
 	/*TODO: len of payload data for i2c and aux is uint8!!!!,
 	 *  but we want to read 256 over i2c!!!!*/
 	if (dal_ddc_service_is_in_aux_transaction_mode(ddc)) {
@@ -556,23 +552,25 @@
 
 		ret = dc_link_aux_transfer_with_retries(ddc, &read_payload);
 	} else {
-		struct i2c_payloads *payloads =
-			dal_ddc_i2c_payloads_create(ddc->ctx, payloads_num);
+		struct i2c_command command = {0};
+		struct i2c_payloads payloads;
 
-		struct i2c_command command = {
-			.payloads = dal_ddc_i2c_payloads_get(payloads),
-			.number_of_payloads = 0,
-			.engine = DDC_I2C_COMMAND_ENGINE,
-			.speed = ddc->ctx->dc->caps.i2c_speed_in_khz };
+		if (!dal_ddc_i2c_payloads_create(ddc->ctx, &payloads, payloads_num))
+			return false;
+
+		command.payloads = dal_ddc_i2c_payloads_get(&payloads);
+		command.number_of_payloads = 0;
+		command.engine = DDC_I2C_COMMAND_ENGINE;
+		command.speed = ddc->ctx->dc->caps.i2c_speed_in_khz;
 
 		dal_ddc_i2c_payloads_add(
-			payloads, address, write_size, write_buf, true);
+			&payloads, address, write_size, write_buf, true);
 
 		dal_ddc_i2c_payloads_add(
-			payloads, address, read_size, read_buf, false);
+			&payloads, address, read_size, read_buf, false);
 
 		command.number_of_payloads =
-			dal_ddc_i2c_payloads_get_count(payloads);
+			dal_ddc_i2c_payloads_get_count(&payloads);
 
 		ret = dm_helpers_submit_i2c(
 				ddc->ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index f574271..4bc95e9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1284,6 +1284,8 @@
 		link->type = dc_connection_single;
 		link->local_sink = link->remote_sinks[0];
 		link->local_sink->sink_signal = SIGNAL_TYPE_DISPLAY_PORT;
+		dc_sink_retain(link->local_sink);
+		dm_helpers_dp_mst_stop_top_mgr(link->ctx, link);
 	} else if (mst_enable == true &&
 			link->type == dc_connection_single &&
 			link->remote_sinks[0] != NULL) {
@@ -1914,6 +1916,9 @@
 			initial_link_setting;
 	uint32_t link_bw;
 
+	if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap))
+		return false;
+
 	/* search for the minimum link setting that:
 	 * 1. is supported according to the link training result
 	 * 2. could support the b/w requested by the timing
@@ -2545,6 +2550,7 @@
 	uint8_t data, struct dc_link *link)
 {
 	union dp_downstream_port_present ds_port = { .byte = data };
+	memset(&link->dpcd_caps.dongle_caps, 0, sizeof(link->dpcd_caps.dongle_caps));
 
 	/* decode converter info*/
 	if (!ds_port.fields.PORT_PRESENT) {
@@ -2691,6 +2697,7 @@
 		 * keep receiver powered all the time.*/
 		case DP_BRANCH_DEVICE_ID_0010FA:
 		case DP_BRANCH_DEVICE_ID_0080E1:
+		case DP_BRANCH_DEVICE_ID_00E04C:
 			link->wa_flags.dp_keep_receiver_powered = true;
 			break;
 
@@ -2877,6 +2884,17 @@
 		sink_id.ieee_device_id,
 		sizeof(sink_id.ieee_device_id));
 
+	/* Quirk Apple MBP 2017 15" Retina panel: Wrong DP_MAX_LINK_RATE */
+	{
+		uint8_t str_mbp_2017[] = { 101, 68, 21, 101, 98, 97 };
+
+		if ((link->dpcd_caps.sink_dev_id == 0x0010fa) &&
+		    !memcmp(link->dpcd_caps.sink_dev_id_str, str_mbp_2017,
+			    sizeof(str_mbp_2017))) {
+			link->reported_link_cap.link_rate = 0x0c;
+		}
+	}
+
 	core_link_read_dpcd(
 		link,
 		DP_SINK_HW_REVISION_START,
@@ -3365,7 +3383,7 @@
 
 		if (edp_config_set.bits.PANEL_MODE_EDP
 			!= panel_mode_edp) {
-			enum ddc_result result = DDC_RESULT_UNKNOWN;
+			enum dc_status result = DC_ERROR_UNEXPECTED;
 
 			edp_config_set.bits.PANEL_MODE_EDP =
 			panel_mode_edp;
@@ -3375,7 +3393,7 @@
 				&edp_config_set.raw,
 				sizeof(edp_config_set.raw));
 
-			ASSERT(result == DDC_RESULT_SUCESSFULL);
+			ASSERT(result == DC_OK);
 		}
 	}
 	DC_LOG_DETECTION_DP_CAPS("Link: %d eDP panel mode supported: %d "
@@ -3490,7 +3508,14 @@
 	if (link_enc->funcs->fec_set_enable &&
 			link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) {
 		if (link->fec_state == dc_link_fec_ready && enable) {
-			msleep(1);
+			/* Accord to DP spec, FEC enable sequence can first
+			 * be transmitted anytime after 1000 LL codes have
+			 * been transmitted on the link after link training
+			 * completion. Using 1 lane RBR should have the maximum
+			 * time for transmitting 1000 LL codes which is 6.173 us.
+			 * So use 7 microseconds delay instead.
+			 */
+			udelay(7);
 			link_enc->funcs->fec_set_enable(link_enc, true);
 			link->fec_state = dc_link_fec_enabled;
 		} else if (link->fec_state == dc_link_fec_enabled && !enable) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index 79438c4..5641a94 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -277,7 +277,8 @@
 		if (pipes[i].stream != NULL &&
 			!pipes[i].top_pipe && !pipes[i].prev_odm_pipe &&
 			pipes[i].stream->link != NULL &&
-			pipes[i].stream_res.stream_enc != NULL) {
+			pipes[i].stream_res.stream_enc != NULL &&
+			pipes[i].stream->link == link) {
 			udelay(100);
 
 			pipes[i].stream_res.stream_enc->funcs->dp_blank(
@@ -399,6 +400,7 @@
 		dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom;
 		dsc_cfg.pixel_encoding = stream->timing.pixel_encoding;
 		dsc_cfg.color_depth = stream->timing.display_color_depth;
+		dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false;
 		dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg;
 		ASSERT(dsc_cfg.dc_dsc_cfg.num_slices_h % opp_cnt == 0);
 		dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt;
@@ -495,11 +497,15 @@
 		struct dsc_config dsc_cfg;
 		uint8_t dsc_packed_pps[128];
 
+		memset(&dsc_cfg, 0, sizeof(dsc_cfg));
+		memset(dsc_packed_pps, 0, 128);
+
 		/* Enable DSC hw block */
 		dsc_cfg.pic_width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right;
 		dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom;
 		dsc_cfg.pixel_encoding = stream->timing.pixel_encoding;
 		dsc_cfg.color_depth = stream->timing.display_color_depth;
+		dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false;
 		dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg;
 
 		DC_LOG_DSC(" ");
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index bf1d7bb..bb09243 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -423,10 +423,10 @@
 
 		if (dwb->funcs->is_enabled(dwb)) {
 			/* writeback pipe already enabled, only need to update */
-			dc->hwss.update_writeback(dc, stream_status, wb_info);
+			dc->hwss.update_writeback(dc, stream_status, wb_info, dc->current_state);
 		} else {
 			/* Enable writeback pipe from scratch*/
-			dc->hwss.enable_writeback(dc, stream_status, wb_info);
+			dc->hwss.enable_writeback(dc, stream_status, wb_info, dc->current_state);
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
index 58bd131..7700a85 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
@@ -77,6 +77,9 @@
 	/* notifyDMCUMsg */
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
 
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0,
+			1, 80000);
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index c3f9f41..cf87723 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -386,7 +386,7 @@
 {
 	enum gpio_result result;
 
-	if (!is_engine_available(engine))
+	if ((engine == NULL) || !is_engine_available(engine))
 		return false;
 
 	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index f787a6b..eca67d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -871,6 +871,20 @@
 	bp_pc_params.flags.SET_EXTERNAL_REF_DIV_SRC =
 					pll_settings->use_external_clk;
 
+	switch (pix_clk_params->color_depth) {
+	case COLOR_DEPTH_101010:
+		bp_pc_params.color_depth = TRANSMITTER_COLOR_DEPTH_30;
+		break;
+	case COLOR_DEPTH_121212:
+		bp_pc_params.color_depth = TRANSMITTER_COLOR_DEPTH_36;
+		break;
+	case COLOR_DEPTH_161616:
+		bp_pc_params.color_depth = TRANSMITTER_COLOR_DEPTH_48;
+		break;
+	default:
+		break;
+	}
+
 	if (clk_src->bios->funcs->set_pixel_clock(
 			clk_src->bios, &bp_pc_params) != BP_RESULT_OK)
 		return false;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 6ed922a..c25840a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -563,6 +563,7 @@
 	cntl.enable_dp_audio = enable_audio;
 	cntl.pixel_clock = actual_pix_clk_khz;
 	cntl.lanes_number = LANE_COUNT_FOUR;
+	cntl.color_depth = crtc_timing->display_color_depth;
 
 	if (enc110->base.bp->funcs->encoder_control(
 			enc110->base.bp, &cntl) != BP_RESULT_OK)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index ab63d0d..6fd57cf 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -429,12 +429,12 @@
 		clamp_max = 0x3FC0;
 		break;
 	case COLOR_DEPTH_101010:
-		/* 10bit MSB aligned on 14 bit bus '11 1111 1111 1100' */
-		clamp_max = 0x3FFC;
+		/* 10bit MSB aligned on 14 bit bus '11 1111 1111 0000' */
+		clamp_max = 0x3FF0;
 		break;
 	case COLOR_DEPTH_121212:
-		/* 12bit MSB aligned on 14 bit bus '11 1111 1111 1111' */
-		clamp_max = 0x3FFF;
+		/* 12bit MSB aligned on 14 bit bus '11 1111 1111 1100' */
+		clamp_max = 0x3FFC;
 		break;
 	default:
 		clamp_max = 0x3FC0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index d67e0ab..11a89d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -484,10 +484,13 @@
 	int vtaps_c = scl_data->taps.v_taps_c;
 	int ceil_vratio = dc_fixpt_ceil(scl_data->ratios.vert);
 	int ceil_vratio_c = dc_fixpt_ceil(scl_data->ratios.vert_c);
-	enum lb_memory_config mem_cfg = LB_MEMORY_CONFIG_0;
 
-	if (dpp->base.ctx->dc->debug.use_max_lb)
-		return mem_cfg;
+	if (dpp->base.ctx->dc->debug.use_max_lb) {
+		if (scl_data->format == PIXEL_FORMAT_420BPP8
+				|| scl_data->format == PIXEL_FORMAT_420BPP10)
+			return LB_MEMORY_CONFIG_3;
+		return LB_MEMORY_CONFIG_0;
+	}
 
 	dpp->base.caps->dscl_calc_lb_num_partitions(
 			scl_data, LB_MEMORY_CONFIG_1, &num_part_y, &num_part_c);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index a02c10e..d163388 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -840,8 +840,8 @@
 
 	hubbub1_get_blk256_size(&blk256_width, &blk256_height, bpe);
 
-	swath_bytes_horz_wc = height * blk256_height * bpe;
-	swath_bytes_vert_wc = width * blk256_width * bpe;
+	swath_bytes_horz_wc = width * blk256_height * bpe;
+	swath_bytes_vert_wc = height * blk256_width * bpe;
 
 	*req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ?
 			false : /* full 256B request */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 60123db..bc5ebea 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -3264,13 +3264,12 @@
 	struct dc_clock_config clock_cfg = {0};
 	struct dc_clocks *current_clocks = &context->bw_ctx.bw.dcn.clk;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->get_clock)
-				dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
-						context, clock_type, &clock_cfg);
-
-	if (!dc->clk_mgr->funcs->get_clock)
+	if (!dc->clk_mgr || !dc->clk_mgr->funcs->get_clock)
 		return DC_FAIL_UNSUPPORTED_1;
 
+	dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
+		context, clock_type, &clock_cfg);
+
 	if (clk_khz > clock_cfg.max_clock_khz)
 		return DC_FAIL_CLK_EXCEED_MAX;
 
@@ -3288,7 +3287,7 @@
 	else
 		return DC_ERROR_UNEXPECTED;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->update_clocks)
+	if (dc->clk_mgr->funcs->update_clocks)
 				dc->clk_mgr->funcs->update_clocks(dc->clk_mgr,
 				context, true);
 	return DC_OK;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 1599bb9..e860ae0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1151,6 +1151,7 @@
 	bool video_large = false;
 	bool desktop_large = false;
 	bool dcc_disabled = false;
+	bool mpo_enabled = false;
 
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->stream_status[i].plane_count == 0)
@@ -1159,6 +1160,9 @@
 		if (context->stream_status[i].plane_count > 2)
 			return DC_FAIL_UNSUPPORTED_1;
 
+		if (context->stream_status[i].plane_count > 1)
+			mpo_enabled = true;
+
 		for (j = 0; j < context->stream_status[i].plane_count; j++) {
 			struct dc_plane_state *plane =
 				context->stream_status[i].plane_states[j];
@@ -1182,6 +1186,10 @@
 		}
 	}
 
+	/* Disable MPO in multi-display configurations. */
+	if (context->stream_count > 1 && mpo_enabled)
+		return DC_FAIL_UNSUPPORTED_1;
+
 	/*
 	 * Workaround: On DCN10 there is UMC issue that causes underflow when
 	 * playing 4k video on 4k desktop with video downscaled and single channel
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 9aa258f..6718777 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -121,35 +121,35 @@
 	switch (packet_index) {
 	case 0:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC0_FRAME_UPDATE, 1);
+				AFMT_GENERIC0_IMMEDIATE_UPDATE, 1);
 		break;
 	case 1:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC1_FRAME_UPDATE, 1);
+				AFMT_GENERIC1_IMMEDIATE_UPDATE, 1);
 		break;
 	case 2:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC2_FRAME_UPDATE, 1);
+				AFMT_GENERIC2_IMMEDIATE_UPDATE, 1);
 		break;
 	case 3:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC3_FRAME_UPDATE, 1);
+				AFMT_GENERIC3_IMMEDIATE_UPDATE, 1);
 		break;
 	case 4:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC4_FRAME_UPDATE, 1);
+				AFMT_GENERIC4_IMMEDIATE_UPDATE, 1);
 		break;
 	case 5:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC5_FRAME_UPDATE, 1);
+				AFMT_GENERIC5_IMMEDIATE_UPDATE, 1);
 		break;
 	case 6:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC6_FRAME_UPDATE, 1);
+				AFMT_GENERIC6_IMMEDIATE_UPDATE, 1);
 		break;
 	case 7:
 		REG_UPDATE(AFMT_VBI_PACKET_CONTROL1,
-				AFMT_GENERIC7_FRAME_UPDATE, 1);
+				AFMT_GENERIC7_IMMEDIATE_UPDATE, 1);
 		break;
 	default:
 		break;
@@ -898,10 +898,10 @@
 	 */
 	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_DIS_DEFER, 2);
 	/* Larger delay to wait until VBLANK - use max retry of
-	 * 10us*5000=50ms. This covers 41.7ms of minimum 24 Hz mode +
+	 * 10us*10200=102ms. This covers 100.0ms of minimum 10 Hz mode +
 	 * a little more because we may not trust delay accuracy.
 	 */
-	max_retries = DP_BLANK_MAX_RETRY * 250;
+	max_retries = DP_BLANK_MAX_RETRY * 501;
 
 	/* disable DP stream */
 	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
index a512cbe..b965661 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -275,7 +275,14 @@
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_IMMEDIATE_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_IMMEDIATE_UPDATE, mask_sh),\
+	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_IMMEDIATE_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\
 	SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\
@@ -339,7 +346,14 @@
 	type AFMT_GENERIC2_FRAME_UPDATE;\
 	type AFMT_GENERIC3_FRAME_UPDATE;\
 	type AFMT_GENERIC4_FRAME_UPDATE;\
+	type AFMT_GENERIC0_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC1_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC2_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC3_IMMEDIATE_UPDATE;\
 	type AFMT_GENERIC4_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC5_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC6_IMMEDIATE_UPDATE;\
+	type AFMT_GENERIC7_IMMEDIATE_UPDATE;\
 	type AFMT_GENERIC5_FRAME_UPDATE;\
 	type AFMT_GENERIC6_FRAME_UPDATE;\
 	type AFMT_GENERIC7_FRAME_UPDATE;\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
index 16476ed..2064366 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
@@ -119,32 +119,6 @@
 
 void dccg2_init(struct dccg *dccg)
 {
-	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
-
-	// Fallthrough intentional to program all available dpp_dto's
-	switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) {
-	case 6:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1);
-		/* Fall through */
-	case 5:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1);
-		/* Fall through */
-	case 4:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1);
-		/* Fall through */
-	case 3:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1);
-		/* Fall through */
-	case 2:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1);
-		/* Fall through */
-	case 1:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1);
-		break;
-	default:
-		ASSERT(false);
-		break;
-	}
 }
 
 static const struct dccg_funcs dccg2_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
index 1b41940..5c45c39 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
@@ -207,6 +207,9 @@
 	struct dsc_reg_values dsc_reg_vals;
 	struct dsc_optc_config dsc_optc_cfg;
 
+	memset(&dsc_reg_vals, 0, sizeof(dsc_reg_vals));
+	memset(&dsc_optc_cfg, 0, sizeof(dsc_optc_cfg));
+
 	DC_LOG_DSC("Getting packed DSC PPS for DSC Config:");
 	dsc_config_log(dsc, dsc_cfg);
 	DC_LOG_DSC("DSC Picture Parameter Set (PPS):");
@@ -348,6 +351,7 @@
 	dsc_reg_vals->pps.block_pred_enable = dsc_cfg->dc_dsc_cfg.block_pred_enable;
 	dsc_reg_vals->pps.line_buf_depth = dsc_cfg->dc_dsc_cfg.linebuf_depth;
 	dsc_reg_vals->alternate_ich_encoding_en = dsc_reg_vals->pps.dsc_version_minor == 1 ? 0 : 1;
+	dsc_reg_vals->ich_reset_at_eol = (dsc_cfg->is_odm || dsc_reg_vals->num_slices_h > 1) ? 0xF : 0;
 
 	// TODO: in addition to validating slice height (pic height must be divisible by slice height),
 	// see what happens when the same condition doesn't apply for slice_width/pic_width.
@@ -510,7 +514,6 @@
 		reg_vals->pps.rc_buf_thresh[i] = reg_vals->pps.rc_buf_thresh[i] >> 6;
 
 	reg_vals->rc_buffer_model_size = dsc_params->rc_buffer_model_size;
-	reg_vals->ich_reset_at_eol = reg_vals->num_slices_h == 1 ? 0 : 0xf;
 }
 
 static void dsc_write_to_registers(struct display_stream_compressor *dsc, const struct dsc_reg_values *reg_vals)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 69e2aae..b250ef7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2012-17 Advanced Micro Devices, Inc.
+ * Copyright 2012-2021 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -179,11 +179,14 @@
 	else
 		Set HUBP_VREADY_AT_OR_AFTER_VSYNC = 0
 	*/
-	if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width
-		+ pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) {
-		value = 1;
-	} else
-		value = 0;
+	if (pipe_dest->htotal != 0) {
+		if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width
+			+ pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) {
+			value = 1;
+		} else
+			value = 0;
+	}
+
 	REG_UPDATE(DCHUBP_CNTL, HUBP_VREADY_AT_OR_AFTER_VSYNC, value);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 1212da1..03a2e1d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -126,7 +126,7 @@
 	REG_WRITE(MILLISECOND_TIME_BASE_DIV, 0x1186a0);
 
 	/* This value is dependent on the hardware pipeline delay so set once per SOC */
-	REG_WRITE(DISPCLK_FREQ_CHANGE_CNTL, 0x801003c);
+	REG_WRITE(DISPCLK_FREQ_CHANGE_CNTL, 0xe01003c);
 }
 void dcn20_display_init(struct dc *dc)
 {
@@ -493,7 +493,6 @@
 	dpp->funcs->dpp_dppclk_control(dpp, false, false);
 
 	hubp->power_gated = true;
-	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
 	dc->hwss.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
@@ -1103,6 +1102,25 @@
 	if (pipe->plane_state != NULL)
 		flip_immediate = pipe->plane_state->flip_immediate;
 
+	if (flip_immediate && lock) {
+		const int TIMEOUT_FOR_FLIP_PENDING = 100000;
+		int i;
+
+		for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) {
+			if (!pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp))
+				break;
+			udelay(1);
+		}
+
+		if (pipe->bottom_pipe != NULL) {
+			for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) {
+				if (!pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp))
+					break;
+				udelay(1);
+			}
+		}
+	}
+
 	/* In flip immediate and pipe splitting case, we need to use GSL
 	 * for synchronization. Only do setup on locking and on flip type change.
 	 */
@@ -1337,7 +1355,8 @@
 static void dcn20_enable_writeback(
 		struct dc *dc,
 		const struct dc_stream_status *stream_status,
-		struct dc_writeback_info *wb_info)
+		struct dc_writeback_info *wb_info,
+		struct dc_state *context)
 {
 	struct dwbc *dwb;
 	struct mcif_wb *mcif_wb;
@@ -1354,7 +1373,7 @@
 	optc->funcs->set_dwb_source(optc, wb_info->dwb_pipe_inst);
 	/* set MCIF_WB buffer and arbitration configuration */
 	mcif_wb->funcs->config_mcif_buf(mcif_wb, &wb_info->mcif_buf_params, wb_info->dwb_params.dest_height);
-	mcif_wb->funcs->config_mcif_arb(mcif_wb, &dc->current_state->bw_ctx.bw.dcn.bw_writeback.mcif_wb_arb[wb_info->dwb_pipe_inst]);
+	mcif_wb->funcs->config_mcif_arb(mcif_wb, &context->bw_ctx.bw.dcn.bw_writeback.mcif_wb_arb[wb_info->dwb_pipe_inst]);
 	/* Enable MCIF_WB */
 	mcif_wb->funcs->enable_mcif(mcif_wb);
 	/* Enable DWB */
@@ -1996,7 +2015,8 @@
 
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2);
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
-	REG_WRITE(REFCLK_CNTL, 0);
+	if (REG(REFCLK_CNTL))
+		REG_WRITE(REFCLK_CNTL, 0);
 	//
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index 2137e2b..03e2073 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -233,12 +233,13 @@
 		struct dc_crtc_timing *timing)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
-	/* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192 */
 	int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right)
 			/ opp_cnt;
-	int memory_mask = mpcc_hactive <= 2560 ? 0x3 : 0xf;
+	uint32_t memory_mask;
 	uint32_t data_fmt = 0;
 
+	ASSERT(opp_cnt == 2);
+
 	/* TODO: In pseudocode but does not affect maximus, delete comment if we dont need on asic
 	 * REG_SET(OTG_GLOBAL_CONTROL2, 0, GLOBAL_UPDATE_LOCK_EN, 1);
 	 * Program OTG register MASTER_UPDATE_LOCK_DB_X/Y to the position before DP frame start
@@ -246,9 +247,17 @@
 	 *		MASTER_UPDATE_LOCK_DB_X, 160,
 	 *		MASTER_UPDATE_LOCK_DB_Y, 240);
 	 */
+
+	/* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192,
+	 * however, for ODM combine we can simplify by always using 4.
+	 * To make sure there's no overlap, each instance "reserves" 2 memories and
+	 * they are uniquely combined here.
+	 */
+	memory_mask = 0x3 << (opp_id[0] * 2) | 0x3 << (opp_id[1] * 2);
+
 	if (REG(OPTC_MEMORY_CONFIG))
 		REG_SET(OPTC_MEMORY_CONFIG, 0,
-			OPTC_MEM_SEL, memory_mask << (optc->inst * 4));
+			OPTC_MEM_SEL, memory_mask);
 
 	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
 		data_fmt = 1;
@@ -257,7 +266,6 @@
 
 	REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt);
 
-	ASSERT(opp_cnt == 2);
 	REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0,
 			OPTC_NUM_OF_INPUT_SEGMENT, 1,
 			OPTC_SEG0_SRC_SEL, opp_id[0],
@@ -287,6 +295,10 @@
 		*num_of_src_opp = 2;
 	else
 		*num_of_src_opp = 1;
+
+	/* Work around VBIOS not updating OPTC_NUM_OF_INPUT_SEGMENT */
+	if (*src_opp_id_1 == 0xf)
+		*num_of_src_opp = 1;
 }
 
 void optc2_set_dwb_source(struct timing_generator *optc,
@@ -350,7 +362,7 @@
 
 	REG_UPDATE_2(OTG_GLOBAL_CONTROL1,
 			MASTER_UPDATE_LOCK_DB_X,
-			h_blank_start - 200 - 1,
+			(h_blank_start - 200 - 1) / optc1->opp_count,
 			MASTER_UPDATE_LOCK_DB_Y,
 			v_blank_start - 1);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 6b2f2f1..d2ea4c0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -269,6 +269,117 @@
 	.use_urgent_burst_bw = 0
 };
 
+struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = {
+	.clock_limits = {
+			{
+				.state = 0,
+				.dcfclk_mhz = 560.0,
+				.fabricclk_mhz = 560.0,
+				.dispclk_mhz = 513.0,
+				.dppclk_mhz = 513.0,
+				.phyclk_mhz = 540.0,
+				.socclk_mhz = 560.0,
+				.dscclk_mhz = 171.0,
+				.dram_speed_mts = 8960.0,
+			},
+			{
+				.state = 1,
+				.dcfclk_mhz = 694.0,
+				.fabricclk_mhz = 694.0,
+				.dispclk_mhz = 642.0,
+				.dppclk_mhz = 642.0,
+				.phyclk_mhz = 600.0,
+				.socclk_mhz = 694.0,
+				.dscclk_mhz = 214.0,
+				.dram_speed_mts = 11104.0,
+			},
+			{
+				.state = 2,
+				.dcfclk_mhz = 875.0,
+				.fabricclk_mhz = 875.0,
+				.dispclk_mhz = 734.0,
+				.dppclk_mhz = 734.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 875.0,
+				.dscclk_mhz = 245.0,
+				.dram_speed_mts = 14000.0,
+			},
+			{
+				.state = 3,
+				.dcfclk_mhz = 1000.0,
+				.fabricclk_mhz = 1000.0,
+				.dispclk_mhz = 1100.0,
+				.dppclk_mhz = 1100.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 1000.0,
+				.dscclk_mhz = 367.0,
+				.dram_speed_mts = 16000.0,
+			},
+			{
+				.state = 4,
+				.dcfclk_mhz = 1200.0,
+				.fabricclk_mhz = 1200.0,
+				.dispclk_mhz = 1284.0,
+				.dppclk_mhz = 1284.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 1200.0,
+				.dscclk_mhz = 428.0,
+				.dram_speed_mts = 16000.0,
+			},
+			/*Extra state, no dispclk ramping*/
+			{
+				.state = 5,
+				.dcfclk_mhz = 1200.0,
+				.fabricclk_mhz = 1200.0,
+				.dispclk_mhz = 1284.0,
+				.dppclk_mhz = 1284.0,
+				.phyclk_mhz = 810.0,
+				.socclk_mhz = 1200.0,
+				.dscclk_mhz = 428.0,
+				.dram_speed_mts = 16000.0,
+			},
+		},
+	.num_states = 5,
+	.sr_exit_time_us = 11.6,
+	.sr_enter_plus_exit_time_us = 13.9,
+	.urgent_latency_us = 4.0,
+	.urgent_latency_pixel_data_only_us = 4.0,
+	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+	.urgent_latency_vm_data_only_us = 4.0,
+	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0,
+	.max_avg_sdp_bw_use_normal_percent = 40.0,
+	.max_avg_dram_bw_use_normal_percent = 40.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 40.0,
+	.max_request_size_bytes = 256,
+	.dram_channel_width_bytes = 2,
+	.fabric_datapath_to_dcn_data_return_bytes = 64,
+	.dcn_downspread_percent = 0.5,
+	.downspread_percent = 0.38,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 131,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 8,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 404.0,
+	.dummy_pstate_latency_us = 5.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+	.dispclk_dppclk_vco_speed_mhz = 3850,
+	.xfc_bus_transport_time_us = 20,
+	.xfc_xbuf_latency_tolerance_us = 4,
+	.use_urgent_burst_bw = 0
+};
+
 struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 };
 
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
@@ -1419,13 +1530,20 @@
 
 static void acquire_dsc(struct resource_context *res_ctx,
 			const struct resource_pool *pool,
-			struct display_stream_compressor **dsc)
+			struct display_stream_compressor **dsc,
+			int pipe_idx)
 {
 	int i;
 
 	ASSERT(*dsc == NULL);
 	*dsc = NULL;
 
+	if (pool->res_cap->num_dsc == pool->res_cap->num_opp) {
+		*dsc = pool->dscs[pipe_idx];
+		res_ctx->is_dsc_acquired[pipe_idx] = true;
+		return;
+	}
+
 	/* Find first free DSC */
 	for (i = 0; i < pool->res_cap->num_dsc; i++)
 		if (!res_ctx->is_dsc_acquired[i]) {
@@ -1468,7 +1586,7 @@
 		if (pipe_ctx->stream != dc_stream)
 			continue;
 
-		acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc);
+		acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc, i);
 
 		/* The number of DSCs can be less than the number of pipes */
 		if (!pipe_ctx->stream_res.dsc) {
@@ -1669,7 +1787,7 @@
 	next_odm_pipe->stream_res.opp = pool->opps[next_odm_pipe->pipe_idx];
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (next_odm_pipe->stream->timing.flags.DSC == 1) {
-		acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc);
+		acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc, next_odm_pipe->pipe_idx);
 		ASSERT(next_odm_pipe->stream_res.dsc);
 		if (next_odm_pipe->stream_res.dsc == NULL)
 			return false;
@@ -1765,7 +1883,7 @@
 			pipe_cnt = i;
 			continue;
 		}
-		if (!resource_are_streams_timing_synchronizable(
+		if (dc->debug.disable_timing_sync || !resource_are_streams_timing_synchronizable(
 				res_ctx->pipe_ctx[pipe_cnt].stream,
 				res_ctx->pipe_ctx[i].stream)) {
 			synchronized_vblank = false;
@@ -2114,7 +2232,7 @@
 				wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 				wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 			}
-			wb_arb_params->time_per_pixel = 16.0 / context->res_ctx.pipe_ctx[i].stream->phy_pix_clk; /* 4 bit fraction, ms */
+			wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
 			wb_arb_params->slice_lines = 32;
 			wb_arb_params->arbitration_slice = 2;
 			wb_arb_params->max_scaled_time = dcn20_calc_max_scaled_time(wb_arb_params->time_per_pixel,
@@ -2157,6 +2275,7 @@
 				+ stream->timing.v_border_bottom;
 		dsc_cfg.pixel_encoding = stream->timing.pixel_encoding;
 		dsc_cfg.color_depth = stream->timing.display_color_depth;
+		dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false;
 		dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg;
 		dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt;
 
@@ -2474,6 +2593,7 @@
 							&context->res_ctx, dc->res_pool,
 							pipe, hsplit_pipe))
 						goto validate_fail;
+					dcn20_build_mapped_resource(dc, context, pipe->stream);
 				} else
 					dcn20_split_stream_for_mpc(
 						&context->res_ctx, dc->res_pool,
@@ -2726,7 +2846,7 @@
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL);
+	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	BW_VAL_TRACE_COUNT();
@@ -2797,7 +2917,7 @@
 	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
 	dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
 
-	if (voltage_supported && dummy_pstate_supported) {
+	if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) {
 		context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
 		goto restore_dml_state;
 	}
@@ -3040,7 +3160,7 @@
 static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb,
 		struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states)
 {
-	struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES] = {0};
+	struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES];
 	int i;
 	int num_calculated_states = 0;
 	int min_dcfclk = 0;
@@ -3048,6 +3168,8 @@
 	if (num_states == 0)
 		return;
 
+	memset(calculated_states, 0, sizeof(calculated_states));
+
 	if (dc->bb_overrides.min_dcfclk_mhz > 0)
 		min_dcfclk = dc->bb_overrides.min_dcfclk_mhz;
 	else
@@ -3125,6 +3247,9 @@
 static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb(
 	uint32_t hw_internal_rev)
 {
+	if (ASICREV_IS_NAVI14_M(hw_internal_rev))
+		return &dcn2_0_nv14_soc;
+
 	if (ASICREV_IS_NAVI12_P(hw_internal_rev))
 		return &dcn2_0_nv12_soc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
index 5ab9d62..e95025b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
@@ -492,15 +492,23 @@
 				DP_VID_N_MUL, n_multiply);
 	}
 
-	/* set DIG_START to 0x1 to reset FIFO */
+	/* make sure stream is disabled before resetting steer fifo */
+	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, false);
+	REG_WAIT(DP_VID_STREAM_CNTL, DP_VID_STREAM_STATUS, 0, 10, 5000);
 
+	/* set DIG_START to 0x1 to reset FIFO */
 	REG_UPDATE(DIG_FE_CNTL, DIG_START, 1);
+	udelay(1);
 
 	/* write 0 to take the FIFO out of reset */
 
 	REG_UPDATE(DIG_FE_CNTL, DIG_START, 0);
 
-	/* switch DP encoder to CRTC data */
+	/* switch DP encoder to CRTC data, but reset it the fifo first. It may happen
+	 * that it overflows during mode transition, and sometimes doesn't recover.
+	 */
+	REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 1);
+	udelay(10);
 
 	REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
index d126674..f5f6b4a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
@@ -22,6 +22,7 @@
  * Authors: AMD
  *
  */
+#include <linux/delay.h>
 #include "dm_services.h"
 #include "dcn20/dcn20_hubbub.h"
 #include "dcn21_hubbub.h"
@@ -71,30 +72,39 @@
 void dcn21_dchvm_init(struct hubbub *hubbub)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+	uint32_t riommu_active;
+	int i;
 
 	//Init DCHVM block
 	REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1);
 
 	//Poll until RIOMMU_ACTIVE = 1
-	//TODO: Figure out interval us and retry count
-	REG_WAIT(DCHVM_RIOMMU_STAT0, RIOMMU_ACTIVE, 1, 5, 100);
+	for (i = 0; i < 100; i++) {
+		REG_GET(DCHVM_RIOMMU_STAT0, RIOMMU_ACTIVE, &riommu_active);
 
-	//Reflect the power status of DCHUBBUB
-	REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_POWERSTATUS, 1);
+		if (riommu_active)
+			break;
+		else
+			udelay(5);
+	}
 
-	//Start rIOMMU prefetching
-	REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_PREFETCH_REQ, 1);
+	if (riommu_active) {
+		//Reflect the power status of DCHUBBUB
+		REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_POWERSTATUS, 1);
 
-	// Enable dynamic clock gating
-	REG_UPDATE_4(DCHVM_CLK_CTRL,
-					HVM_DISPCLK_R_GATE_DIS, 0,
-					HVM_DISPCLK_G_GATE_DIS, 0,
-					HVM_DCFCLK_R_GATE_DIS, 0,
-					HVM_DCFCLK_G_GATE_DIS, 0);
+		//Start rIOMMU prefetching
+		REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_PREFETCH_REQ, 1);
 
-	//Poll until HOSTVM_PREFETCH_DONE = 1
-	//TODO: Figure out interval us and retry count
-	REG_WAIT(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, 1, 5, 100);
+		// Enable dynamic clock gating
+		REG_UPDATE_4(DCHVM_CLK_CTRL,
+						HVM_DISPCLK_R_GATE_DIS, 0,
+						HVM_DISPCLK_G_GATE_DIS, 0,
+						HVM_DCFCLK_R_GATE_DIS, 0,
+						HVM_DCFCLK_G_GATE_DIS, 0);
+
+		//Poll until HOSTVM_PREFETCH_DONE = 1
+		REG_WAIT(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, 1, 5, 100);
+	}
 }
 
 static int hubbub21_init_dchub(struct hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
index a00af51..c8f77bd 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
@@ -73,32 +73,47 @@
 		struct _vcs_dpi_display_dlg_regs_st *dlg_attr)
 {
 	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
-	uint32_t cur_value;
+	uint32_t refcyc_per_vm_group_vblank;
+	uint32_t refcyc_per_vm_req_vblank;
+	uint32_t refcyc_per_vm_group_flip;
+	uint32_t refcyc_per_vm_req_flip;
+	const uint32_t uninitialized_hw_default = 0;
 
-	REG_GET(VBLANK_PARAMETERS_5, REFCYC_PER_VM_GROUP_VBLANK, &cur_value);
-	if (cur_value > dlg_attr->refcyc_per_vm_group_vblank)
+	REG_GET(VBLANK_PARAMETERS_5,
+			REFCYC_PER_VM_GROUP_VBLANK, &refcyc_per_vm_group_vblank);
+
+	if (refcyc_per_vm_group_vblank == uninitialized_hw_default ||
+			refcyc_per_vm_group_vblank > dlg_attr->refcyc_per_vm_group_vblank)
 		REG_SET(VBLANK_PARAMETERS_5, 0,
 				REFCYC_PER_VM_GROUP_VBLANK, dlg_attr->refcyc_per_vm_group_vblank);
 
 	REG_GET(VBLANK_PARAMETERS_6,
-			REFCYC_PER_VM_REQ_VBLANK,
-			&cur_value);
-	if (cur_value > dlg_attr->refcyc_per_vm_req_vblank)
+			REFCYC_PER_VM_REQ_VBLANK, &refcyc_per_vm_req_vblank);
+
+	if (refcyc_per_vm_req_vblank == uninitialized_hw_default ||
+			refcyc_per_vm_req_vblank > dlg_attr->refcyc_per_vm_req_vblank)
 		REG_SET(VBLANK_PARAMETERS_6, 0,
 				REFCYC_PER_VM_REQ_VBLANK, dlg_attr->refcyc_per_vm_req_vblank);
 
-	REG_GET(FLIP_PARAMETERS_3, REFCYC_PER_VM_GROUP_FLIP, &cur_value);
-	if (cur_value > dlg_attr->refcyc_per_vm_group_flip)
+	REG_GET(FLIP_PARAMETERS_3,
+			REFCYC_PER_VM_GROUP_FLIP, &refcyc_per_vm_group_flip);
+
+	if (refcyc_per_vm_group_flip == uninitialized_hw_default ||
+			refcyc_per_vm_group_flip > dlg_attr->refcyc_per_vm_group_flip)
 		REG_SET(FLIP_PARAMETERS_3, 0,
 				REFCYC_PER_VM_GROUP_FLIP, dlg_attr->refcyc_per_vm_group_flip);
 
-	REG_GET(FLIP_PARAMETERS_4, REFCYC_PER_VM_REQ_FLIP, &cur_value);
-	if (cur_value > dlg_attr->refcyc_per_vm_req_flip)
+	REG_GET(FLIP_PARAMETERS_4,
+			REFCYC_PER_VM_REQ_FLIP, &refcyc_per_vm_req_flip);
+
+	if (refcyc_per_vm_req_flip == uninitialized_hw_default ||
+			refcyc_per_vm_req_flip > dlg_attr->refcyc_per_vm_req_flip)
 		REG_SET(FLIP_PARAMETERS_4, 0,
 					REFCYC_PER_VM_REQ_FLIP, dlg_attr->refcyc_per_vm_req_flip);
 
 	REG_SET(FLIP_PARAMETERS_5, 0,
 			REFCYC_PER_PTE_GROUP_FLIP_C, dlg_attr->refcyc_per_pte_group_flip_c);
+
 	REG_SET(FLIP_PARAMETERS_6, 0,
 			REFCYC_PER_META_CHUNK_FLIP_C, dlg_attr->refcyc_per_meta_chunk_flip_c);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index de18218..11a4c40 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -57,6 +57,7 @@
 #include "dcn20/dcn20_dccg.h"
 #include "dcn21_hubbub.h"
 #include "dcn10/dcn10_resource.h"
+#include "dce110/dce110_resource.h"
 
 #include "dcn20/dcn20_dwb.h"
 #include "dcn20/dcn20_mmhubbub.h"
@@ -246,7 +247,7 @@
 	.dram_channel_width_bytes = 4,
 	.fabric_datapath_to_dcn_data_return_bytes = 32,
 	.dcn_downspread_percent = 0.5,
-	.downspread_percent = 0.5,
+	.downspread_percent = 0.38,
 	.dram_page_open_time_ns = 50.0,
 	.dram_rw_turnaround_time_ns = 17.5,
 	.dram_return_buffer_per_channel_bytes = 8192,
@@ -258,7 +259,7 @@
 	.vmm_page_size_bytes = 4096,
 	.dram_clock_change_latency_us = 23.84,
 	.return_bus_width_bytes = 64,
-	.dispclk_dppclk_vco_speed_mhz = 3550,
+	.dispclk_dppclk_vco_speed_mhz = 3600,
 	.xfc_bus_transport_time_us = 4,
 	.xfc_xbuf_latency_tolerance_us = 4,
 	.use_urgent_burst_bw = 1,
@@ -824,6 +825,9 @@
 enum dcn20_clk_src_array_id {
 	DCN20_CLK_SRC_PLL0,
 	DCN20_CLK_SRC_PLL1,
+	DCN20_CLK_SRC_PLL2,
+	DCN20_CLK_SRC_PLL3,
+	DCN20_CLK_SRC_PLL4,
 	DCN20_CLK_SRC_TOTAL_DCN21
 };
 
@@ -1492,6 +1496,18 @@
 			dcn21_clock_source_create(ctx, ctx->dc_bios,
 				CLOCK_SOURCE_COMBO_PHY_PLL1,
 				&clk_src_regs[1], false);
+	pool->base.clock_sources[DCN20_CLK_SRC_PLL2] =
+			dcn21_clock_source_create(ctx, ctx->dc_bios,
+				CLOCK_SOURCE_COMBO_PHY_PLL2,
+				&clk_src_regs[2], false);
+	pool->base.clock_sources[DCN20_CLK_SRC_PLL3] =
+			dcn21_clock_source_create(ctx, ctx->dc_bios,
+				CLOCK_SOURCE_COMBO_PHY_PLL3,
+				&clk_src_regs[3], false);
+	pool->base.clock_sources[DCN20_CLK_SRC_PLL4] =
+			dcn21_clock_source_create(ctx, ctx->dc_bios,
+				CLOCK_SOURCE_COMBO_PHY_PLL4,
+				&clk_src_regs[4], false);
 
 	pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 6c6c486..945d23c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -3435,6 +3435,7 @@
 			mode_lib->vba.DCCEnabledInAnyPlane = true;
 		}
 	}
+	mode_lib->vba.UrgentLatency = mode_lib->vba.UrgentLatencyPixelDataOnly;
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->FabricAndDRAMBandwidthPerState[i] = dml_min(
 				mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 0fafd69..5b5ed1b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -3467,6 +3467,7 @@
 			mode_lib->vba.DCCEnabledInAnyPlane = true;
 		}
 	}
+	mode_lib->vba.UrgentLatency = mode_lib->vba.UrgentLatencyPixelDataOnly;
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->FabricAndDRAMBandwidthPerState[i] = dml_min(
 				mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
index b953b02..723af0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
@@ -24,7 +24,7 @@
  */
 
 #include "dml_common_defs.h"
-#include "../calcs/dcn_calc_math.h"
+#include "dcn_calc_math.h"
 
 #include "dml_inline_defs.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
index eca140d..ded71ea 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
@@ -27,7 +27,7 @@
 #define __DML_INLINE_DEFS_H__
 
 #include "dml_common_defs.h"
-#include "../calcs/dcn_calc_math.h"
+#include "dcn_calc_math.h"
 #include "dml_logger.h"
 
 static inline double dml_min(double a, double b)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
index f8f8549..8a6fb58 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
@@ -63,13 +63,13 @@
 	enum gpio_mode mode)
 {
 	if (gpio->pin) {
-		ASSERT_CRITICAL(false);
+		BREAK_TO_DEBUGGER();
 		return GPIO_RESULT_ALREADY_OPENED;
 	}
 
 	// No action if allocation failed during gpio construct
 	if (!gpio->hw_container.ddc) {
-		ASSERT_CRITICAL(false);
+		BREAK_TO_DEBUGGER();
 		return GPIO_RESULT_NON_SPECIFIC_ERROR;
 	}
 	gpio->mode = mode;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h
similarity index 100%
rename from drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h
rename to drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
index 1ddb1c6..75ecfdc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
@@ -36,6 +36,7 @@
 	uint32_t pic_height;
 	enum dc_pixel_encoding pixel_encoding;
 	enum dc_color_depth color_depth;  /* Bits per component */
+	bool is_odm;
 	struct dc_dsc_config dc_dsc_cfg;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 3a938cd..f6cc2d6 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -321,10 +321,12 @@
 			struct dc_state *context);
 	void (*update_writeback)(struct dc *dc,
 			const struct dc_stream_status *stream_status,
-			struct dc_writeback_info *wb_info);
+			struct dc_writeback_info *wb_info,
+			struct dc_state *context);
 	void (*enable_writeback)(struct dc *dc,
 			const struct dc_stream_status *stream_status,
-			struct dc_writeback_info *wb_info);
+			struct dc_writeback_info *wb_info,
+			struct dc_state *context);
 	void (*disable_writeback)(struct dc *dc,
 			unsigned int dwb_pipe_inst);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
index 5db29bf..70370b2 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
@@ -299,8 +299,8 @@
 	pflip_int_entry(1),
 	pflip_int_entry(2),
 	pflip_int_entry(3),
-	[DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(),
-	[DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(),
+	pflip_int_entry(4),
+	pflip_int_entry(5),
 	[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
 	gpio_pad_int_entry(0),
 	gpio_pad_int_entry(1),
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index cbe7818..623455c 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -168,6 +168,11 @@
 	.ack = NULL
 };
 
+static const struct irq_source_info_funcs vupdate_no_lock_irq_info_funcs = {
+	.set = NULL,
+	.ack = NULL
+};
+
 #undef BASE_INNER
 #define BASE_INNER(seg) DMU_BASE__INST0_SEG ## seg
 
@@ -230,6 +235,17 @@
 		.funcs = &vblank_irq_info_funcs\
 	}
 
+/* vupdate_no_lock_int_entry maps to DC_IRQ_SOURCE_VUPDATEx, to match semantic
+ * of DCE's DC_IRQ_SOURCE_VUPDATEx.
+ */
+#define vupdate_no_lock_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_VUPDATE1 + reg_num] = {\
+		IRQ_REG_ENTRY(OTG, reg_num,\
+			OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_INT_EN,\
+			OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_EVENT_CLEAR),\
+		.funcs = &vupdate_no_lock_irq_info_funcs\
+	}
+
 #define vblank_int_entry(reg_num)\
 	[DC_IRQ_SOURCE_VBLANK1 + reg_num] = {\
 		IRQ_REG_ENTRY(OTG, reg_num,\
@@ -338,6 +354,12 @@
 	vupdate_int_entry(3),
 	vupdate_int_entry(4),
 	vupdate_int_entry(5),
+	vupdate_no_lock_int_entry(0),
+	vupdate_no_lock_int_entry(1),
+	vupdate_no_lock_int_entry(2),
+	vupdate_no_lock_int_entry(3),
+	vupdate_no_lock_int_entry(4),
+	vupdate_no_lock_int_entry(5),
 	vblank_int_entry(0),
 	vblank_int_entry(1),
 	vblank_int_entry(2),
diff --git a/drivers/gpu/drm/amd/display/dc/irq_types.h b/drivers/gpu/drm/amd/display/dc/irq_types.h
index d0ccd81..ad3e562 100644
--- a/drivers/gpu/drm/amd/display/dc/irq_types.h
+++ b/drivers/gpu/drm/amd/display/dc/irq_types.h
@@ -163,7 +163,7 @@
 };
 
 #define DAL_VALID_IRQ_SRC_NUM(src) \
-	((src) <= DAL_IRQ_SOURCES_NUMBER && (src) > DC_IRQ_SOURCE_INVALID)
+	((src) < DAL_IRQ_SOURCES_NUMBER && (src) > DC_IRQ_SOURCE_INVALID)
 
 /* Number of Page Flip IRQ Sources. */
 #define DAL_PFLIP_IRQ_SRC_NUM \
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 30ec80a..8da3225 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -57,7 +57,7 @@
  * general debug capabilities
  *
  */
-#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)
+#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB))
 #define ASSERT_CRITICAL(expr) do {	\
 	if (WARN_ON(!(expr))) { \
 		kgdb_breakpoint(); \
diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
index 1896170..9ad49da 100644
--- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
@@ -31,6 +31,8 @@
 #define DP_BRANCH_DEVICE_ID_0022B9 0x0022B9
 #define DP_BRANCH_DEVICE_ID_00001A 0x00001A
 #define DP_BRANCH_DEVICE_ID_0080E1 0x0080e1
+#define DP_BRANCH_DEVICE_ID_90CC24 0x90CC24
+#define DP_BRANCH_DEVICE_ID_00E04C 0x00E04C
 
 enum ddc_result {
 	DDC_RESULT_UNKNOWN = 0,
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index 89ef9f6..16df2a4 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -431,6 +431,9 @@
  */
 static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2)
 {
+	if (arg1.value == 0)
+		return arg2.value == 0 ? dc_fixpt_one : dc_fixpt_zero;
+
 	return dc_fixpt_exp(
 		dc_fixpt_mul(
 			dc_fixpt_log(arg1),
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 2d8f14b..e042d8c 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -799,7 +799,7 @@
 	pow_buffer_ptr = -1; // reset back to no optimize
 	ret = true;
 release:
-	kfree(coeff);
+	kvfree(coeff);
 	return ret;
 }
 
@@ -1576,7 +1576,7 @@
 	struct pwl_float_data_ex *rgb = rgb_regamma;
 	const struct hw_x_point *coord_x = coordinates_x;
 
-	build_coefficients(&coeff, true);
+	build_coefficients(&coeff, TRANSFER_FUNCTION_SRGB);
 
 	i = 0;
 	while (i != hw_points_num + 1) {
@@ -1862,7 +1862,7 @@
 
 	kfree(rgb_regamma);
 rgb_regamma_alloc_fail:
-	kvfree(rgb_user);
+	kfree(rgb_user);
 rgb_user_alloc_fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index ec70c9b..7d67cb2 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -743,6 +743,10 @@
 	nominal_field_rate_in_uhz =
 			mod_freesync_calc_nominal_field_rate(stream);
 
+	/* Rounded to the nearest Hz */
+	nominal_field_rate_in_uhz = 1000000ULL *
+			div_u64(nominal_field_rate_in_uhz + 500000, 1000000);
+
 	min_refresh_in_uhz = in_config->min_refresh_in_uhz;
 	max_refresh_in_uhz = in_config->max_refresh_in_uhz;
 
@@ -799,6 +803,7 @@
 			2 * in_out_vrr->min_refresh_in_uhz)
 		in_out_vrr->btr.btr_enabled = false;
 
+	in_out_vrr->fixed.fixed_active = false;
 	in_out_vrr->btr.btr_active = false;
 	in_out_vrr->btr.inserted_duration_in_us = 0;
 	in_out_vrr->btr.frames_to_insert = 0;
@@ -818,6 +823,7 @@
 		in_out_vrr->adjust.v_total_max = stream->timing.v_total;
 	} else if (in_out_vrr->state == VRR_STATE_ACTIVE_VARIABLE &&
 			refresh_range >= MIN_REFRESH_RANGE_IN_US) {
+
 		in_out_vrr->adjust.v_total_min =
 			calc_v_total_from_refresh(stream,
 				in_out_vrr->max_refresh_in_uhz);
@@ -996,14 +1002,13 @@
 			const struct dc_stream_state *stream)
 {
 	unsigned long long nominal_field_rate_in_uhz = 0;
+	unsigned int total = stream->timing.h_total * stream->timing.v_total;
 
-	/* Calculate nominal field rate for stream */
+	/* Calculate nominal field rate for stream, rounded up to nearest integer */
 	nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz / 10;
 	nominal_field_rate_in_uhz *= 1000ULL * 1000ULL * 1000ULL;
-	nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz,
-						stream->timing.h_total);
-	nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz,
-						stream->timing.v_total);
+
+	nominal_field_rate_in_uhz =	div_u64(nominal_field_rate_in_uhz, total);
 
 	return nominal_field_rate_in_uhz;
 }
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 05e2be8..ba1aafe 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -115,7 +115,7 @@
 /* NOTE: iRAM is 256B in size */
 struct iram_table_v_2 {
 	/* flags                      */
-	uint16_t flags;							/* 0x00 U16  */
+	uint16_t min_abm_backlight;					/* 0x00 U16  */
 
 	/* parameters for ABM2.0 algorithm */
 	uint8_t min_reduction[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];		/* 0x02 U0.8 */
@@ -140,10 +140,10 @@
 
 	/* For reading PSR State directly from IRAM */
 	uint8_t psr_state;						/* 0xf0       */
-	uint8_t dmcu_mcp_interface_version;							/* 0xf1       */
-	uint8_t dmcu_abm_feature_version;							/* 0xf2       */
-	uint8_t dmcu_psr_feature_version;							/* 0xf3       */
-	uint16_t dmcu_version;										/* 0xf4       */
+	uint8_t dmcu_mcp_interface_version;				/* 0xf1       */
+	uint8_t dmcu_abm_feature_version;				/* 0xf2       */
+	uint8_t dmcu_psr_feature_version;				/* 0xf3       */
+	uint16_t dmcu_version;						/* 0xf4       */
 	uint8_t dmcu_state;						/* 0xf6       */
 
 	uint16_t blRampReduction;					/* 0xf7       */
@@ -164,42 +164,43 @@
 	uint8_t max_reduction[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];		/* 0x16 U0.8 */
 	uint8_t bright_pos_gain[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];	/* 0x2a U2.6 */
 	uint8_t dark_pos_gain[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];		/* 0x3e U2.6 */
-	uint8_t hybrid_factor[NUM_AGGR_LEVEL];						/* 0x52 U0.8 */
-	uint8_t contrast_factor[NUM_AGGR_LEVEL];					/* 0x56 U0.8 */
-	uint8_t deviation_gain[NUM_AGGR_LEVEL];						/* 0x5a U0.8 */
-	uint8_t iir_curve[NUM_AMBI_LEVEL];							/* 0x5e U0.8 */
-	uint8_t min_knee[NUM_AGGR_LEVEL];							/* 0x63 U0.8 */
-	uint8_t max_knee[NUM_AGGR_LEVEL];							/* 0x67 U0.8 */
-	uint8_t pad[21];											/* 0x6b U0.8 */
+	uint8_t hybrid_factor[NUM_AGGR_LEVEL];				/* 0x52 U0.8 */
+	uint8_t contrast_factor[NUM_AGGR_LEVEL];			/* 0x56 U0.8 */
+	uint8_t deviation_gain[NUM_AGGR_LEVEL];				/* 0x5a U0.8 */
+	uint8_t iir_curve[NUM_AMBI_LEVEL];				/* 0x5e U0.8 */
+	uint8_t min_knee[NUM_AGGR_LEVEL];				/* 0x63 U0.8 */
+	uint8_t max_knee[NUM_AGGR_LEVEL];				/* 0x67 U0.8 */
+	uint16_t min_abm_backlight;					/* 0x6b U16  */
+	uint8_t pad[19];						/* 0x6d U0.8 */
 
 	/* parameters for crgb conversion */
-	uint16_t crgb_thresh[NUM_POWER_FN_SEGS];					/* 0x80 U3.13 */
-	uint16_t crgb_offset[NUM_POWER_FN_SEGS];					/* 0x90 U1.15 */
-	uint16_t crgb_slope[NUM_POWER_FN_SEGS];						/* 0xa0 U4.12 */
+	uint16_t crgb_thresh[NUM_POWER_FN_SEGS];			/* 0x80 U3.13 */
+	uint16_t crgb_offset[NUM_POWER_FN_SEGS];			/* 0x90 U1.15 */
+	uint16_t crgb_slope[NUM_POWER_FN_SEGS];				/* 0xa0 U4.12 */
 
 	/* parameters for custom curve */
 	/* thresholds for brightness --> backlight */
-	uint16_t backlight_thresholds[NUM_BL_CURVE_SEGS];			/* 0xb0 U16.0 */
+	uint16_t backlight_thresholds[NUM_BL_CURVE_SEGS];		/* 0xb0 U16.0 */
 	/* offsets for brightness --> backlight */
-	uint16_t backlight_offsets[NUM_BL_CURVE_SEGS];				/* 0xd0 U16.0 */
+	uint16_t backlight_offsets[NUM_BL_CURVE_SEGS];			/* 0xd0 U16.0 */
 
 	/* For reading PSR State directly from IRAM */
-	uint8_t psr_state;											/* 0xf0       */
-	uint8_t dmcu_mcp_interface_version;							/* 0xf1       */
-	uint8_t dmcu_abm_feature_version;							/* 0xf2       */
-	uint8_t dmcu_psr_feature_version;							/* 0xf3       */
-	uint16_t dmcu_version;										/* 0xf4       */
-	uint8_t dmcu_state;											/* 0xf6       */
+	uint8_t psr_state;						/* 0xf0       */
+	uint8_t dmcu_mcp_interface_version;				/* 0xf1       */
+	uint8_t dmcu_abm_feature_version;				/* 0xf2       */
+	uint8_t dmcu_psr_feature_version;				/* 0xf3       */
+	uint16_t dmcu_version;						/* 0xf4       */
+	uint8_t dmcu_state;						/* 0xf6       */
 
-	uint8_t dummy1;												/* 0xf7       */
-	uint8_t dummy2;												/* 0xf8       */
-	uint8_t dummy3;												/* 0xf9       */
-	uint8_t dummy4;												/* 0xfa       */
-	uint8_t dummy5;												/* 0xfb       */
-	uint8_t dummy6;												/* 0xfc       */
-	uint8_t dummy7;												/* 0xfd       */
-	uint8_t dummy8;												/* 0xfe       */
-	uint8_t dummy9;												/* 0xff       */
+	uint8_t dummy1;							/* 0xf7       */
+	uint8_t dummy2;							/* 0xf8       */
+	uint8_t dummy3;							/* 0xf9       */
+	uint8_t dummy4;							/* 0xfa       */
+	uint8_t dummy5;							/* 0xfb       */
+	uint8_t dummy6;							/* 0xfc       */
+	uint8_t dummy7;							/* 0xfd       */
+	uint8_t dummy8;							/* 0xfe       */
+	uint8_t dummy9;							/* 0xff       */
 };
 #pragma pack(pop)
 
@@ -271,7 +272,8 @@
 {
 	unsigned int set = params.set;
 
-	ram_table->flags = 0x0;
+	ram_table->min_abm_backlight =
+			cpu_to_be16(params.min_abm_backlight);
 	ram_table->deviation_gain = 0xb3;
 
 	ram_table->blRampReduction =
@@ -445,6 +447,9 @@
 
 	ram_table->flags = 0x0;
 
+	ram_table->min_abm_backlight =
+			cpu_to_be16(params.min_abm_backlight);
+
 	ram_table->deviation_gain[0] = 0xb3;
 	ram_table->deviation_gain[1] = 0xa8;
 	ram_table->deviation_gain[2] = 0x98;
@@ -588,6 +593,10 @@
 	unsigned int set = params.set;
 
 	ram_table->flags = 0x0;
+
+	ram_table->min_abm_backlight =
+			cpu_to_be16(params.min_abm_backlight);
+
 	for (i = 0; i < NUM_AGGR_LEVEL; i++) {
 		ram_table->hybrid_factor[i] = abm_settings[set][i].brightness_gain;
 		ram_table->contrast_factor[i] = abm_settings[set][i].contrast_factor;
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 da5df00..e541570 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -38,6 +38,7 @@
 	unsigned int backlight_lut_array_size;
 	unsigned int backlight_ramping_reduction;
 	unsigned int backlight_ramping_start;
+	unsigned int min_abm_backlight;
 	unsigned int set;
 };
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
index b6f74bf..27bb8c1 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
@@ -7376,6 +7376,8 @@
 #define mmCRTC4_CRTC_DRR_CONTROL                                                                       0x0f3e
 #define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX                                                              2
 
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0                                                                  0x395d
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX                                                         2
 
 // addressBlock: dce_dc_fmt4_dispdec
 // base address: 0x2000
diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h
index 5dcb776..7ec4331 100644
--- a/drivers/gpu/drm/amd/include/discovery.h
+++ b/drivers/gpu/drm/amd/include/discovery.h
@@ -25,7 +25,6 @@
 #define _DISCOVERY_H_
 
 #define PSP_HEADER_SIZE                 256
-#define BINARY_MAX_SIZE                 (64 << 10)
 #define BINARY_SIGNATURE                0x28211407
 #define DISCOVERY_TABLE_SIGNATURE       0x53445049
 
diff --git a/drivers/gpu/drm/amd/include/navi10_enum.h b/drivers/gpu/drm/amd/include/navi10_enum.h
index d5ead96..84bcb96 100644
--- a/drivers/gpu/drm/amd/include/navi10_enum.h
+++ b/drivers/gpu/drm/amd/include/navi10_enum.h
@@ -430,7 +430,7 @@
  */
 
 typedef enum ENUM_NUM_SIMD_PER_CU {
-NUM_SIMD_PER_CU                          = 0x00000004,
+NUM_SIMD_PER_CU                          = 0x00000002,
 } ENUM_NUM_SIMD_PER_CU;
 
 /*
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index fa8ad7d..9eb3a0d 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -320,12 +320,12 @@
 		if (*level & profile_mode_mask) {
 			hwmgr->saved_dpm_level = hwmgr->dpm_level;
 			hwmgr->en_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-						AMD_IP_BLOCK_TYPE_GFX,
-						AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_GFX,
+						AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
@@ -1421,10 +1421,12 @@
 {
 	struct pp_hwmgr *hwmgr = handle;
 
+	*cap = false;
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_capability)
+	if (!(hwmgr->not_vf && amdgpu_dpm) ||
+		!hwmgr->hwmgr_func->get_asic_baco_capability)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1458,7 +1460,8 @@
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->set_asic_baco_state)
+	if (!(hwmgr->not_vf && amdgpu_dpm) ||
+		!hwmgr->hwmgr_func->set_asic_baco_state)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 4acf139..b51a124 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -844,6 +844,7 @@
 	smu->smu_baco.platform_support = false;
 
 	mutex_init(&smu->sensor_lock);
+	mutex_init(&smu->metrics_lock);
 
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
@@ -1344,7 +1345,10 @@
 	int ret;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = &adev->smu;
-	bool baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT);
+	bool baco_feature_is_enabled = false;
+
+	if(!(adev->flags & AMD_IS_APU))
+		baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT);
 
 	ret = smu_system_features_control(smu, false);
 	if (ret)
@@ -1537,12 +1541,12 @@
 		if (*level & profile_mode_mask) {
 			smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level;
 			smu_dpm_ctx->enable_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(smu->adev,
-							       AMD_IP_BLOCK_TYPE_GFX,
-							       AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(smu->adev,
+							       AMD_IP_BLOCK_TYPE_GFX,
+							       AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index d493a3f..08a717a 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -910,18 +910,21 @@
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
+	mutex_lock(&smu->metrics_lock);
 	if (!smu_table->metrics_time ||
 	     time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
 			return ret;
 		}
 		smu_table->metrics_time = jiffies;
 	}
 
 	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
 
 	return ret;
 }
@@ -1388,12 +1391,17 @@
 					"VR",
 					"COMPUTE",
 					"CUSTOM"};
+	static const char *title[] = {
+			"PROFILE_INDEX(NAME)"};
 	uint32_t i, size = 0;
 	int16_t workload_type = 0;
 
 	if (!smu->pm_enabled || !buf)
 		return -EINVAL;
 
+	size += sprintf(buf + size, "%16s\n",
+			title[0]);
+
 	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
 		/*
 		 * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
index 77c1467..719597c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
@@ -984,6 +984,32 @@
 			struct pp_hwmgr *hwmgr,
 			const ATOM_PPLIB_POWERPLAYTABLE *powerplay_table)
 {
+	hwmgr->thermal_controller.ucType =
+			powerplay_table->sThermalController.ucType;
+	hwmgr->thermal_controller.ucI2cLine =
+			powerplay_table->sThermalController.ucI2cLine;
+	hwmgr->thermal_controller.ucI2cAddress =
+			powerplay_table->sThermalController.ucI2cAddress;
+
+	hwmgr->thermal_controller.fanInfo.bNoFan =
+		(0 != (powerplay_table->sThermalController.ucFanParameters &
+			ATOM_PP_FANPARAMETERS_NOFAN));
+
+	hwmgr->thermal_controller.fanInfo.ucTachometerPulsesPerRevolution =
+		powerplay_table->sThermalController.ucFanParameters &
+		ATOM_PP_FANPARAMETERS_TACHOMETER_PULSES_PER_REVOLUTION_MASK;
+
+	hwmgr->thermal_controller.fanInfo.ulMinRPM
+		= powerplay_table->sThermalController.ucFanMinRPM * 100UL;
+	hwmgr->thermal_controller.fanInfo.ulMaxRPM
+		= powerplay_table->sThermalController.ucFanMaxRPM * 100UL;
+
+	set_hw_cap(hwmgr,
+		   ATOM_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType,
+		   PHM_PlatformCaps_ThermalController);
+
+	hwmgr->thermal_controller.use_hw_fan_control = 1;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 1115761..6322e57 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -209,8 +209,7 @@
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->need_min_deep_sleep_dcefclk &&
-		smu10_data->deep_sleep_dcefclk != clock) {
+	if (clock && smu10_data->deep_sleep_dcefclk != clock) {
 		smu10_data->deep_sleep_dcefclk = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetMinDeepSleepDcefclk,
@@ -223,8 +222,7 @@
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->dcf_actual_hard_min_freq &&
-		smu10_data->dcf_actual_hard_min_freq != clock) {
+	if (clock && smu10_data->dcf_actual_hard_min_freq != clock) {
 		smu10_data->dcf_actual_hard_min_freq = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetHardMinDcefclkByFreq,
@@ -237,8 +235,7 @@
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
 
-	if (smu10_data->f_actual_hard_min_freq &&
-		smu10_data->f_actual_hard_min_freq != clock) {
+	if (clock && smu10_data->f_actual_hard_min_freq != clock) {
 		smu10_data->f_actual_hard_min_freq = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetHardMinFclkByFreq,
@@ -1026,12 +1023,15 @@
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk * 10;
-		clocks->data[i].latency_in_us = latency_required ?
-						smu10_get_mem_latency(hwmgr,
-						pclk_vol_table->entries[i].clk) :
-						0;
-		clocks->num_levels++;
+		if (pclk_vol_table->entries[i].clk) {
+			clocks->data[clocks->num_levels].clocks_in_khz =
+				pclk_vol_table->entries[i].clk * 10;
+			clocks->data[clocks->num_levels].latency_in_us = latency_required ?
+				smu10_get_mem_latency(hwmgr,
+						      pclk_vol_table->entries[i].clk) :
+				0;
+			clocks->num_levels++;
+		}
 	}
 
 	return 0;
@@ -1077,9 +1077,11 @@
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
-		clocks->data[i].voltage_in_mv = pclk_vol_table->entries[i].vol;
-		clocks->num_levels++;
+		if (pclk_vol_table->entries[i].clk) {
+			clocks->data[clocks->num_levels].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
+			clocks->data[clocks->num_levels].voltage_in_mv = pclk_vol_table->entries[i].vol;
+			clocks->num_levels++;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 203ce4b..7cde558 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -1533,6 +1533,10 @@
 	PP_ASSERT_WITH_CODE((tmp_result == 0),
 			"Failed to reset to default!", result = tmp_result);
 
+	tmp_result = smum_stop_smc(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to stop smc!", result = tmp_result);
+
 	tmp_result = smu7_force_switch_to_arbf0(hwmgr);
 	PP_ASSERT_WITH_CODE((tmp_result == 0),
 			"Failed to force to switch arbf0!", result = tmp_result);
@@ -2864,7 +2868,7 @@
 		if (hwmgr->is_kicker)
 			switch_limit_us = data->is_memory_gddr5 ? 450 : 150;
 		else
-			switch_limit_us = data->is_memory_gddr5 ? 190 : 150;
+			switch_limit_us = data->is_memory_gddr5 ? 200 : 150;
 		break;
 	case CHIP_VEGAM:
 		switch_limit_us = 30;
@@ -3575,7 +3579,8 @@
 	case AMDGPU_PP_SENSOR_GPU_POWER:
 		return smu7_get_gpu_power(hwmgr, (uint32_t *)value);
 	case AMDGPU_PP_SENSOR_VDDGFX:
-		if ((data->vr_config & 0xff) == 0x2)
+		if ((data->vr_config & VRCONF_VDDGFX_MASK) ==
+		    (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT))
 			val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device,
 					CGS_IND_REG__SMC, PWR_SVI2_STATUS, PLANE2_VID);
 		else
@@ -3805,9 +3810,12 @@
 {
 	uint32_t i;
 
+	/* force the trim if mclk_switching is disabled to prevent flicker */
+	bool force_trim = (low_limit == high_limit);
 	for (i = 0; i < dpm_table->count; i++) {
 	/*skip the trim if od is enabled*/
-		if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit
+		if ((!hwmgr->od_enabled || force_trim)
+			&& (dpm_table->dpm_levels[i].value < low_limit
 			|| dpm_table->dpm_levels[i].value > high_limit))
 			dpm_table->dpm_levels[i].enabled = false;
 		else
@@ -3983,6 +3991,13 @@
 			"Failed to populate and upload SCLK MCLK DPM levels!",
 			result = tmp_result);
 
+	/*
+	 * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag.
+	 * That effectively disables AVFS feature.
+	 */
+	if (hwmgr->hardcode_pp_table != NULL)
+		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
+
 	tmp_result = smu7_update_avfs(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to update avfs voltages!",
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index beacfff..ecbc9da 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3691,6 +3691,13 @@
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to upload PPtable!", return result);
 
+	/*
+	 * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag.
+	 * That effectively disables AVFS feature.
+	 */
+	if(hwmgr->hardcode_pp_table != NULL)
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
+
 	vega10_update_avfs(hwmgr);
 
 	/*
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
index ba8763d..e8d01ab 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c
@@ -364,17 +364,29 @@
 static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct phm_ppt_v2_information *pp_table_info =
+		(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct phm_tdp_table *tdp_table = pp_table_info->tdp_table;
 	struct amdgpu_device *adev = hwmgr->adev;
-	int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP;
+	int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (low < range->min)
-		low = range->min;
-	if (high > range->max)
-		high = range->max;
+	/* compare them in unit celsius degree */
+	if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)
+		low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
+	/*
+	 * As a common sense, usSoftwareShutdownTemp should be bigger
+	 * than ThotspotLimit. For any invalid usSoftwareShutdownTemp,
+	 * we will just use the max possible setting VEGA10_THERMAL_MAXIMUM_ALERT_TEMP
+	 * to avoid false alarms.
+	 */
+	if ((tdp_table->usSoftwareShutdownTemp >
+	     range->hotspot_crit_max / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)) {
+		if (high > tdp_table->usSoftwareShutdownTemp)
+			high = tdp_table->usSoftwareShutdownTemp;
+	}
 
 	if (low > high)
 		return -EINVAL;
@@ -383,8 +395,8 @@
 
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
 	val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) &
 			(~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) &
 			(~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
index 904eb2c..40e7c72 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
@@ -170,17 +170,18 @@
 static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct amdgpu_device *adev = hwmgr->adev;
-	int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP;
+	int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (low < range->min)
-		low = range->min;
-	if (high > range->max)
-		high = range->max;
+	/* compare them in unit celsius degree */
+	if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)
+		low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	if (high > pptable_information->us_software_shutdown_temp)
+		high = pptable_information->us_software_shutdown_temp;
 
 	if (low > high)
 		return -EINVAL;
@@ -189,8 +190,8 @@
 
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
+	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
 	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
index df6ff92..b068d1c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
@@ -29,7 +29,7 @@
 #include "vega20_baco.h"
 #include "vega20_smumgr.h"
 
-
+#include "amdgpu_ras.h"
 
 static const struct soc15_baco_cmd_entry clean_baco_tbl[] =
 {
@@ -74,6 +74,7 @@
 int vega20_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	enum BACO_STATE cur_state;
 	uint32_t data;
 
@@ -84,10 +85,11 @@
 		return 0;
 
 	if (state == BACO_STATE_IN) {
-		data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL);
-		data |= 0x80000000;
-		WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data);
-
+		if (!ras || !ras->supported) {
+			data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL);
+			data |= 0x80000000;
+			WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data);
+		}
 
 		if(smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_EnterBaco, 0))
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index f591530..947e4fa 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -981,27 +981,15 @@
 {
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
-	uint64_t features_enabled;
-	int i;
-	bool enabled;
-	int ret = 0;
+	int i, ret = 0;
 
 	PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_DisableAllSmuFeatures)) == 0,
 			"[DisableAllSMUFeatures] Failed to disable all smu features!",
 			return ret);
 
-	ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled);
-	PP_ASSERT_WITH_CODE(!ret,
-			"[DisableAllSMUFeatures] Failed to get enabled smc features!",
-			return ret);
-
-	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
-		enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ?
-			true : false;
-		data->smu_features[i].enabled = enabled;
-		data->smu_features[i].supported = enabled;
-	}
+	for (i = 0; i < GNLD_FEATURES_MAX; i++)
+		data->smu_features[i].enabled = 0;
 
 	return 0;
 }
@@ -1652,12 +1640,6 @@
 
 	data->uvd_power_gated = true;
 	data->vce_power_gated = true;
-
-	if (data->smu_features[GNLD_DPM_UVD].enabled)
-		data->uvd_power_gated = false;
-
-	if (data->smu_features[GNLD_DPM_VCE].enabled)
-		data->vce_power_gated = false;
 }
 
 static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
@@ -3211,10 +3193,11 @@
 
 static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfeature_masks)
 {
-	uint64_t features_enabled;
-	uint64_t features_to_enable;
-	uint64_t features_to_disable;
-	int ret = 0;
+	struct vega20_hwmgr *data =
+			(struct vega20_hwmgr *)(hwmgr->backend);
+	uint64_t features_enabled, features_to_enable, features_to_disable;
+	int i, ret = 0;
+	bool enabled;
 
 	if (new_ppfeature_masks >= (1ULL << GNLD_FEATURES_MAX))
 		return -EINVAL;
@@ -3243,6 +3226,17 @@
 			return ret;
 	}
 
+	/* Update the cached feature enablement state */
+	ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
+		enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ?
+			true : false;
+		data->smu_features[i].enabled = enabled;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
index ede54e8..ce56b93 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c
@@ -240,17 +240,18 @@
 static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *range)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct amdgpu_device *adev = hwmgr->adev;
-	int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP *
-			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP;
+	int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (low < range->min)
-		low = range->min;
-	if (high > range->max)
-		high = range->max;
+	/* compare them in unit celsius degree */
+	if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)
+		low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	if (high > pptable_information->us_software_shutdown_temp)
+		high = pptable_information->us_software_shutdown_temp;
 
 	if (low > high)
 		return -EINVAL;
@@ -259,8 +260,8 @@
 
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5);
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
-	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES));
+	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
+	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
 	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 23171a4..5ad9a78 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -345,6 +345,7 @@
 	const struct pptable_funcs	*ppt_funcs;
 	struct mutex			mutex;
 	struct mutex			sensor_lock;
+	struct mutex			metrics_lock;
 	uint64_t pool_size;
 
 	struct smu_table_context	smu_table;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 7bf9a14..f6490a1 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -229,6 +229,7 @@
 	bool (*is_hw_avfs_present)(struct pp_hwmgr  *hwmgr);
 	int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting);
 	int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */
+	int (*stop_smc)(struct pp_hwmgr *hwmgr);
 };
 
 struct pp_hwmgr_func {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index c528883..05a55e8 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -114,4 +114,6 @@
 
 extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw);
 
+extern int smum_stop_smc(struct pp_hwmgr *hwmgr);
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 328e258..7d913a0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -547,17 +547,20 @@
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
+	mutex_lock(&smu->metrics_lock);
 	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
 			return ret;
 		}
 		smu_table->metrics_time = jiffies;
 	}
 
 	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index e62bfba..9a083cd 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -183,11 +183,14 @@
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0;
 	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
-	SmuMetrics_t metrics = {0};
+	SmuMetrics_t metrics;
+	bool cur_value_match_level = false;
 
 	if (!clk_table || clk_type >= SMU_CLK_COUNT)
 		return -EINVAL;
 
+	memset(&metrics, 0, sizeof(metrics));
+
 	ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 			       (void *)&metrics, false);
 	if (ret)
@@ -241,8 +244,13 @@
 		GET_DPM_CUR_FREQ(clk_table, clk_type, i, value);
 		size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
 				cur_value == value ? "*" : "");
+		if (cur_value == value)
+			cur_value_match_level = true;
 	}
 
+	if (!cur_value_match_level)
+		size += sprintf(buf + size, "   %uMhz *\n", cur_value);
+
 	return size;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
index 2a390dd..89cd6da 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
@@ -37,7 +37,7 @@
 			freq = table->SocClocks[dpm_level].Freq;	\
 			break;						\
 		case SMU_MCLK:						\
-			freq = table->MemClocks[dpm_level].Freq;	\
+			freq = table->FClocks[dpm_level].Freq;	\
 			break;						\
 		case SMU_DCEFCLK:					\
 			freq = table->DcfClocks[dpm_level].Freq;	\
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index c5257ae..c4d8c52 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -171,7 +171,8 @@
 		chip_name = "navi12";
 		break;
 	default:
-		BUG();
+		dev_err(adev->dev, "Unsupported ASIC type %d\n", adev->asic_type);
+		return -EINVAL;
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
@@ -988,8 +989,12 @@
 	struct smu_11_0_max_sustainable_clocks *max_sustainable_clocks;
 	int ret = 0;
 
-	max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks),
+	if (!smu->smu_table.max_sustainable_clocks)
+		max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks),
 					 GFP_KERNEL);
+	else
+		max_sustainable_clocks = smu->smu_table.max_sustainable_clocks;
+
 	smu->smu_table.max_sustainable_clocks = (void *)max_sustainable_clocks;
 
 	max_sustainable_clocks->uclock = smu->smu_table.boot_values.uclk / 100;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 15590fd..42c8f87 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -239,7 +239,7 @@
 
 	switch (dev_id) {
 	case 0x67BA:
-	case 0x66B1:
+	case 0x67B1:
 		smu_data->power_tune_defaults = &defaults_hawaii_pro;
 		break;
 	case 0x67B8:
@@ -2933,6 +2933,29 @@
 	return 0;
 }
 
+static void ci_reset_smc(struct pp_hwmgr *hwmgr)
+{
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				  SMC_SYSCON_RESET_CNTL,
+				  rst_reg, 1);
+}
+
+
+static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr)
+{
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				  SMC_SYSCON_CLOCK_CNTL_0,
+				  ck_disable, 1);
+}
+
+static int ci_stop_smc(struct pp_hwmgr *hwmgr)
+{
+	ci_reset_smc(hwmgr);
+	ci_stop_smc_clock(hwmgr);
+
+	return 0;
+}
+
 const struct pp_smumgr_func ci_smu_funcs = {
 	.name = "ci_smu",
 	.smu_init = ci_smu_init,
@@ -2957,4 +2980,5 @@
 	.is_dpm_running = ci_is_dpm_running,
 	.update_dpm_settings = ci_update_dpm_settings,
 	.update_smc_table = ci_update_smc_table,
+	.stop_smc = ci_stop_smc,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index 4240aee..83d06f8 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -217,3 +217,11 @@
 
 	return -EINVAL;
 }
+
+int smum_stop_smc(struct pp_hwmgr *hwmgr)
+{
+	if (hwmgr->smumgr_funcs->stop_smc)
+		return hwmgr->smumgr_funcs->stop_smc(hwmgr);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index ae18fbc..86bdb01 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -642,9 +642,6 @@
 
 	/* sclk is bigger than max sclk in the dependence table */
 	*voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
-	vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
-			(dep_table->entries[i - 1].vddc -
-					(uint16_t)VDDC_VDDCI_DELTA));
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control)
 		*voltage |= (data->vbios_boot_state.vddci_bootup_value *
@@ -652,8 +649,13 @@
 	else if (dep_table->entries[i - 1].vddci)
 		*voltage |= (dep_table->entries[i - 1].vddci *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-	else
+	else {
+		vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
+				(dep_table->entries[i - 1].vddc -
+						(uint16_t)VDDC_VDDCI_DELTA));
+
 		*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+	}
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control)
 		*mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE;
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 92c393f..3c3f719 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -1691,17 +1691,20 @@
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
+	mutex_lock(&smu->metrics_lock);
 	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
 			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
 			return ret;
 		}
 		smu_table->metrics_time = jiffies;
 	}
 
 	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
index 624d257..52c4256 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
@@ -250,6 +250,7 @@
 {
 	komeda_crtc_prepare(to_kcrtc(crtc));
 	drm_crtc_vblank_on(crtc);
+	WARN_ON(drm_crtc_vblank_get(crtc));
 	komeda_crtc_do_flush(crtc, old);
 }
 
@@ -319,6 +320,7 @@
 		}
 	}
 
+	drm_crtc_vblank_put(crtc);
 	drm_crtc_vblank_off(crtc);
 	komeda_crtc_unprepare(kcrtc);
 }
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 875a3a9..7d0e7b0 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -56,7 +56,7 @@
 	return MODE_OK;
 }
 
-const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
 	.get_modes = malidp_mw_connector_get_modes,
 	.mode_valid = malidp_mw_connector_mode_valid,
 };
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 3c70a53..7bf348d 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -922,13 +922,18 @@
 	.atomic_disable = malidp_de_plane_disable,
 };
 
+static const uint64_t linear_only_modifiers[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 int malidp_de_planes_init(struct drm_device *drm)
 {
 	struct malidp_drm *malidp = drm->dev_private;
 	const struct malidp_hw_regmap *map = &malidp->dev->hw->map;
 	struct malidp_plane *plane = NULL;
 	enum drm_plane_type plane_type;
-	unsigned long crtcs = 1 << drm->mode_config.num_crtc;
+	unsigned long crtcs = BIT(drm->mode_config.num_crtc);
 	unsigned long flags = DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 |
 			      DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
 	unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) |
@@ -985,8 +990,8 @@
 		 */
 		ret = drm_universal_plane_init(drm, &plane->base, crtcs,
 				&malidp_de_plane_funcs, formats, n,
-				(id == DE_SMART) ? NULL : modifiers, plane_type,
-				NULL);
+				(id == DE_SMART) ? linear_only_modifiers : modifiers,
+				plane_type, NULL);
 
 		if (ret < 0)
 			goto cleanup;
diff --git a/drivers/gpu/drm/aspeed/Kconfig b/drivers/gpu/drm/aspeed/Kconfig
index 018383c..5e95bce 100644
--- a/drivers/gpu/drm/aspeed/Kconfig
+++ b/drivers/gpu/drm/aspeed/Kconfig
@@ -3,6 +3,7 @@
 	tristate "ASPEED BMC Display Controller"
 	depends on DRM && OF
 	depends on (COMPILE_TEST || ARCH_ASPEED)
+	depends on MMU
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DMA_CMA if HAVE_DMA_CONTIGUOUS
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index f2e73e6..1098513 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -73,7 +73,11 @@
 	unsigned long prate;
 	unsigned int mask = ATMEL_HLCDC_CLKDIV_MASK | ATMEL_HLCDC_CLKPOL;
 	unsigned int cfg = 0;
-	int div;
+	int div, ret;
+
+	ret = clk_prepare_enable(crtc->dc->hlcdc->sys_clk);
+	if (ret)
+		return;
 
 	vm.vfront_porch = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	vm.vback_porch = adj->crtc_vtotal - adj->crtc_vsync_end;
@@ -95,14 +99,14 @@
 		     (adj->crtc_hdisplay - 1) |
 		     ((adj->crtc_vdisplay - 1) << 16));
 
+	prate = clk_get_rate(crtc->dc->hlcdc->sys_clk);
+	mode_rate = adj->crtc_clock * 1000;
 	if (!crtc->dc->desc->fixed_clksrc) {
+		prate *= 2;
 		cfg |= ATMEL_HLCDC_CLKSEL;
 		mask |= ATMEL_HLCDC_CLKSEL;
 	}
 
-	prate = 2 * clk_get_rate(crtc->dc->hlcdc->sys_clk);
-	mode_rate = adj->crtc_clock * 1000;
-
 	div = DIV_ROUND_UP(prate, mode_rate);
 	if (div < 2) {
 		div = 2;
@@ -117,8 +121,8 @@
 		int div_low = prate / mode_rate;
 
 		if (div_low >= 2 &&
-		    ((prate / div_low - mode_rate) <
-		     10 * (mode_rate - prate / div)))
+		    (10 * (prate / div_low - mode_rate) <
+		     (mode_rate - prate / div)))
 			/*
 			 * At least 10 times better when using a higher
 			 * frequency than requested, instead of a lower.
@@ -147,6 +151,8 @@
 			   ATMEL_HLCDC_VSPSU | ATMEL_HLCDC_VSPHO |
 			   ATMEL_HLCDC_GUARDTIME_MASK | ATMEL_HLCDC_MODE_MASK,
 			   cfg);
+
+	clk_disable_unprepare(crtc->dc->hlcdc->sys_clk);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c
index e567bdf..bb13917 100644
--- a/drivers/gpu/drm/bochs/bochs_hw.c
+++ b/drivers/gpu/drm/bochs/bochs_hw.c
@@ -156,10 +156,8 @@
 		size = min(size, mem);
 	}
 
-	if (pci_request_region(pdev, 0, "bochs-drm") != 0) {
-		DRM_ERROR("Cannot request framebuffer\n");
-		return -EBUSY;
-	}
+	if (pci_request_region(pdev, 0, "bochs-drm") != 0)
+		DRM_WARN("Cannot request framebuffer, boot fb still active?\n");
 
 	bochs->fb_map = ioremap(addr, size);
 	if (bochs->fb_map == NULL) {
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 02a9c1e..fa50ab2 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -194,6 +194,7 @@
 	bochs->dev->mode_config.preferred_depth = 24;
 	bochs->dev->mode_config.prefer_shadow = 0;
 	bochs->dev->mode_config.prefer_shadow_fbdev = 1;
+	bochs->dev->mode_config.fbdev_use_iomem = true;
 	bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
 
 	bochs->dev->mode_config.funcs = &bochs_mode_funcs;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
index a428185..d05b303 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
@@ -19,13 +19,15 @@
 {
 	switch (fs) {
 	case 32000:
-		*n = 4096;
+	case 48000:
+	case 96000:
+	case 192000:
+		*n = fs * 128 / 1000;
 		break;
 	case 44100:
-		*n = 6272;
-		break;
-	case 48000:
-		*n = 6144;
+	case 88200:
+	case 176400:
+		*n = fs * 128 / 900;
 		break;
 	}
 
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index 3c7cc5a..56df07c 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -715,7 +715,9 @@
 	/* 1.0V digital core power regulator  */
 	pdata->dvdd10 = devm_regulator_get(dev, "dvdd10");
 	if (IS_ERR(pdata->dvdd10)) {
-		DRM_ERROR("DVDD10 regulator not found\n");
+		if (PTR_ERR(pdata->dvdd10) != -EPROBE_DEFER)
+			DRM_ERROR("DVDD10 regulator not found\n");
+
 		return PTR_ERR(pdata->dvdd10);
 	}
 
@@ -1332,7 +1334,9 @@
 
 	err = anx78xx_init_pdata(anx78xx);
 	if (err) {
-		DRM_ERROR("Failed to initialize pdata: %d\n", err);
+		if (err != -EPROBE_DEFER)
+			DRM_ERROR("Failed to initialize pdata: %d\n", err);
+
 		return err;
 	}
 
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 22885dc..1f26890 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1635,8 +1635,7 @@
 }
 
 struct analogix_dp_device *
-analogix_dp_bind(struct device *dev, struct drm_device *drm_dev,
-		 struct analogix_dp_plat_data *plat_data)
+analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct analogix_dp_device *dp;
@@ -1739,22 +1738,30 @@
 					irq_flags, "analogix-dp", dp);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to request irq\n");
-		goto err_disable_pm_runtime;
+		return ERR_PTR(ret);
 	}
 	disable_irq(dp->irq);
 
+	return dp;
+}
+EXPORT_SYMBOL_GPL(analogix_dp_probe);
+
+int analogix_dp_bind(struct analogix_dp_device *dp, struct drm_device *drm_dev)
+{
+	int ret;
+
 	dp->drm_dev = drm_dev;
 	dp->encoder = dp->plat_data->encoder;
 
 	dp->aux.name = "DP-AUX";
 	dp->aux.transfer = analogix_dpaux_transfer;
-	dp->aux.dev = &pdev->dev;
+	dp->aux.dev = dp->dev;
 
 	ret = drm_dp_aux_register(&dp->aux);
 	if (ret)
-		return ERR_PTR(ret);
+		return ret;
 
-	pm_runtime_enable(dev);
+	pm_runtime_enable(dp->dev);
 
 	ret = analogix_dp_create_bridge(drm_dev, dp);
 	if (ret) {
@@ -1762,13 +1769,12 @@
 		goto err_disable_pm_runtime;
 	}
 
-	return dp;
+	return 0;
 
 err_disable_pm_runtime:
+	pm_runtime_disable(dp->dev);
 
-	pm_runtime_disable(dev);
-
-	return ERR_PTR(ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(analogix_dp_bind);
 
@@ -1785,10 +1791,15 @@
 
 	drm_dp_aux_unregister(&dp->aux);
 	pm_runtime_disable(dp->dev);
-	clk_disable_unprepare(dp->clock);
 }
 EXPORT_SYMBOL_GPL(analogix_dp_unbind);
 
+void analogix_dp_remove(struct analogix_dp_device *dp)
+{
+	clk_disable_unprepare(dp->clock);
+}
+EXPORT_SYMBOL_GPL(analogix_dp_remove);
+
 #ifdef CONFIG_PM
 int analogix_dp_suspend(struct analogix_dp_device *dp)
 {
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index 6166dca..0cb9dd6 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -1026,7 +1026,7 @@
 	struct mipi_dsi_packet packet;
 	int ret, i, tx_len, rx_len;
 
-	ret = pm_runtime_get_sync(host->dev);
+	ret = pm_runtime_resume_and_get(host->dev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
index 6e81e5d..b050fd1 100644
--- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
+++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
@@ -295,8 +295,12 @@
 				       const struct i2c_device_id *id)
 {
 	struct device *dev = &stdp4028_i2c->dev;
+	int ret;
 
-	ge_b850v3_lvds_init(dev);
+	ret = ge_b850v3_lvds_init(dev);
+
+	if (ret)
+		return ret;
 
 	ge_b850v3_lvds_ptr->stdp4028_i2c = stdp4028_i2c;
 	i2c_set_clientdata(stdp4028_i2c, ge_b850v3_lvds_ptr);
@@ -354,8 +358,12 @@
 				       const struct i2c_device_id *id)
 {
 	struct device *dev = &stdp2690_i2c->dev;
+	int ret;
 
-	ge_b850v3_lvds_init(dev);
+	ret = ge_b850v3_lvds_init(dev);
+
+	if (ret)
+		return ret;
 
 	ge_b850v3_lvds_ptr->stdp2690_i2c = stdp2690_i2c;
 	i2c_set_clientdata(stdp2690_i2c, ge_b850v3_lvds_ptr);
diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c
index bd3165e..04431db 100644
--- a/drivers/gpu/drm/bridge/sil-sii8620.c
+++ b/drivers/gpu/drm/bridge/sil-sii8620.c
@@ -177,7 +177,7 @@
 
 static u8 sii8620_readb(struct sii8620 *ctx, u16 addr)
 {
-	u8 ret;
+	u8 ret = 0;
 
 	sii8620_read_buf(ctx, addr, &ret, 1);
 	return ret;
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 521d689..41bf4aa 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -36,6 +36,7 @@
 #include "dw-hdmi-cec.h"
 #include "dw-hdmi.h"
 
+#define DDC_CI_ADDR		0x37
 #define DDC_SEGMENT_ADDR	0x30
 
 #define HDMI_EDID_LEN		512
@@ -398,6 +399,15 @@
 	u8 addr = msgs[0].addr;
 	int i, ret = 0;
 
+	if (addr == DDC_CI_ADDR)
+		/*
+		 * The internal I2C controller does not support the multi-byte
+		 * read and write operations needed for DDC/CI.
+		 * TOFIX: Blacklist the DDC/CI address until we filter out
+		 * unsupported I2C operations.
+		 */
+		return -EOPNOTSUPP;
+
 	dev_dbg(hdmi->dev, "xfer: num: %d, addr: %#x\n", num, addr);
 
 	for (i = 0; i < num; i++) {
@@ -1566,28 +1576,34 @@
 		frame.colorspace = HDMI_COLORSPACE_RGB;
 
 	/* Set up colorimetry */
-	switch (hdmi->hdmi_data.enc_out_encoding) {
-	case V4L2_YCBCR_ENC_601:
-		if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601)
-			frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
-		else
+	if (!hdmi_bus_fmt_is_rgb(hdmi->hdmi_data.enc_out_bus_format)) {
+		switch (hdmi->hdmi_data.enc_out_encoding) {
+		case V4L2_YCBCR_ENC_601:
+			if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601)
+				frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
+			else
+				frame.colorimetry = HDMI_COLORIMETRY_ITU_601;
+			frame.extended_colorimetry =
+					HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
+			break;
+		case V4L2_YCBCR_ENC_709:
+			if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709)
+				frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
+			else
+				frame.colorimetry = HDMI_COLORIMETRY_ITU_709;
+			frame.extended_colorimetry =
+					HDMI_EXTENDED_COLORIMETRY_XV_YCC_709;
+			break;
+		default: /* Carries no data */
 			frame.colorimetry = HDMI_COLORIMETRY_ITU_601;
+			frame.extended_colorimetry =
+					HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
+			break;
+		}
+	} else {
+		frame.colorimetry = HDMI_COLORIMETRY_NONE;
 		frame.extended_colorimetry =
-				HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
-		break;
-	case V4L2_YCBCR_ENC_709:
-		if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709)
-			frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
-		else
-			frame.colorimetry = HDMI_COLORIMETRY_ITU_709;
-		frame.extended_colorimetry =
-				HDMI_EXTENDED_COLORIMETRY_XV_YCC_709;
-		break;
-	default: /* Carries no data */
-		frame.colorimetry = HDMI_COLORIMETRY_ITU_601;
-		frame.extended_colorimetry =
-				HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
-		break;
+			HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
 	}
 
 	frame.scan_mode = HDMI_SCAN_MODE_NONE;
@@ -2023,7 +2039,7 @@
 
 		/* HDMI Initialization Step E - Configure audio */
 		hdmi_clk_regenerator_update_pixel_clock(hdmi);
-		hdmi_enable_audio_clk(hdmi, true);
+		hdmi_enable_audio_clk(hdmi, hdmi->audio_enable);
 	}
 
 	/* not for DVI mode */
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index 675442b..77384c4 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -365,7 +365,6 @@
 	if (lpm)
 		val |= CMD_MODE_ALL_LP;
 
-	dsi_write(dsi, DSI_LPCLK_CTRL, lpm ? 0 : PHY_TXREQUESTCLKHS);
 	dsi_write(dsi, DSI_CMD_MODE_CFG, val);
 }
 
@@ -541,16 +540,22 @@
 static void dw_mipi_dsi_set_mode(struct dw_mipi_dsi *dsi,
 				 unsigned long mode_flags)
 {
+	u32 val;
+
 	dsi_write(dsi, DSI_PWR_UP, RESET);
 
 	if (mode_flags & MIPI_DSI_MODE_VIDEO) {
 		dsi_write(dsi, DSI_MODE_CFG, ENABLE_VIDEO_MODE);
 		dw_mipi_dsi_video_mode_config(dsi);
-		dsi_write(dsi, DSI_LPCLK_CTRL, PHY_TXREQUESTCLKHS);
 	} else {
 		dsi_write(dsi, DSI_MODE_CFG, ENABLE_CMD_MODE);
 	}
 
+	val = PHY_TXREQUESTCLKHS;
+	if (dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)
+		val |= AUTO_CLKLANE_CTRL;
+	dsi_write(dsi, DSI_LPCLK_CTRL, val);
+
 	dsi_write(dsi, DSI_PWR_UP, POWERUP);
 }
 
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 8a8d605..0454675 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -294,7 +294,7 @@
 
 static int tc_aux_wait_busy(struct tc_data *tc)
 {
-	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000);
+	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000);
 }
 
 static int tc_aux_write_data(struct tc_data *tc, const void *data,
@@ -637,7 +637,7 @@
 	if (ret)
 		goto err;
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000);
 	if (ret == -ETIMEDOUT) {
 		dev_err(tc->dev, "Timeout waiting for PHY to become ready");
 		return ret;
@@ -861,7 +861,7 @@
 	int ret;
 
 	ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE,
-			      LT_LOOPDONE, 1, 1000);
+			      LT_LOOPDONE, 500, 100000);
 	if (ret) {
 		dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n");
 		return ret;
@@ -934,7 +934,7 @@
 	dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST);
 	ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl);
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000);
 	if (ret) {
 		dev_err(dev, "timeout waiting for phy become ready");
 		return ret;
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 0a58095..f1de4bb 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -647,6 +647,12 @@
 				     buf[i]);
 	}
 
+	/* Clear old status bits before start so we don't get confused */
+	regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG,
+		     AUX_IRQ_STATUS_NAT_I2C_FAIL |
+		     AUX_IRQ_STATUS_AUX_RPLY_TOUT |
+		     AUX_IRQ_STATUS_AUX_SHORT);
+
 	regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND);
 
 	ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val,
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 2dd2cd8..5e906ea 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2948,7 +2948,7 @@
 
 	ret = handle_conflicting_encoders(state, true);
 	if (ret)
-		return ret;
+		goto fail;
 
 	ret = drm_atomic_commit(state);
 
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index cc9acd9..4f785a7 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -268,9 +268,10 @@
 void drm_master_release(struct drm_file *file_priv)
 {
 	struct drm_device *dev = file_priv->minor->dev;
-	struct drm_master *master = file_priv->master;
+	struct drm_master *master;
 
 	mutex_lock(&dev->master_mutex);
+	master = file_priv->master;
 	if (file_priv->magic)
 		idr_remove(&file_priv->master->magic_map, file_priv->magic);
 
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index c8922b7..bf1bdb0 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -880,7 +880,8 @@
 	 * depending on the hardware this may require the framebuffer
 	 * to be in a specific tiling format.
 	 */
-	if ((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180 ||
+	if (((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_0 &&
+	     (*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180) ||
 	    !plane->rotation_property)
 		return false;
 
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 4c76662..2337b38 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -27,6 +27,7 @@
 #include <drm/drm_print.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
+#include <drm/drm_sysfs.h>
 
 #include <linux/uaccess.h>
 
@@ -511,6 +512,10 @@
 	drm_mode_object_register(connector->dev, &connector->base);
 
 	connector->registration_state = DRM_CONNECTOR_REGISTERED;
+
+	/* Let userspace know we have a new connector */
+	drm_sysfs_hotplug_event(connector->dev);
+
 	goto unlock;
 
 err_debugfs:
diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c
index 8230dac..3a4126d 100644
--- a/drivers/gpu/drm/drm_damage_helper.c
+++ b/drivers/gpu/drm/drm_damage_helper.c
@@ -212,8 +212,14 @@
 	drm_for_each_plane(plane, fb->dev) {
 		struct drm_plane_state *plane_state;
 
-		if (plane->state->fb != fb)
+		ret = drm_modeset_lock(&plane->mutex, state->acquire_ctx);
+		if (ret)
+			goto out;
+
+		if (plane->state->fb != fb) {
+			drm_modeset_unlock(&plane->mutex);
 			continue;
+		}
 
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index eab0f26..0ba9242 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -91,6 +91,7 @@
 	mutex_lock(&dev->filelist_mutex);
 	list_for_each_entry_reverse(priv, &dev->filelist, lhead) {
 		struct task_struct *task;
+		bool is_current_master = drm_is_current_master(priv);
 
 		rcu_read_lock(); /* locks pid_task()->comm */
 		task = pid_task(priv->pid, PIDTYPE_PID);
@@ -99,7 +100,7 @@
 			   task ? task->comm : "<unknown>",
 			   pid_vnr(priv->pid),
 			   priv->minor->index,
-			   drm_is_current_master(priv) ? 'y' : 'n',
+			   is_current_master ? 'y' : 'n',
 			   priv->authenticated ? 'y' : 'n',
 			   from_kuid_munged(seq_user_ns(m), uid),
 			   priv->magic);
@@ -337,13 +338,13 @@
 
 	buf[len] = '\0';
 
-	if (!strcmp(buf, "on"))
+	if (sysfs_streq(buf, "on"))
 		connector->force = DRM_FORCE_ON;
-	else if (!strcmp(buf, "digital"))
+	else if (sysfs_streq(buf, "digital"))
 		connector->force = DRM_FORCE_ON_DIGITAL;
-	else if (!strcmp(buf, "off"))
+	else if (sysfs_streq(buf, "off"))
 		connector->force = DRM_FORCE_OFF;
-	else if (!strcmp(buf, "unspecified"))
+	else if (sysfs_streq(buf, "unspecified"))
 		connector->force = DRM_FORCE_UNSPECIFIED;
 	else
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index be1b7ba..f6598c5 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -140,12 +140,14 @@
 	if (IS_ERR(source))
 		return PTR_ERR(source);
 
-	if (source[len] == '\n')
-		source[len] = '\0';
+	if (source[len - 1] == '\n')
+		source[len - 1] = '\0';
 
 	ret = crtc->funcs->verify_crc_source(crtc, source, &values_cnt);
-	if (ret)
+	if (ret) {
+		kfree(source);
 		return ret;
+	}
 
 	spin_lock_irq(&crc->lock);
 
diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c
index 0cfb386..0d7f90c00 100644
--- a/drivers/gpu/drm/drm_dp_aux_dev.c
+++ b/drivers/gpu/drm/drm_dp_aux_dev.c
@@ -63,7 +63,7 @@
 
 	mutex_lock(&aux_idr_mutex);
 	aux_dev = idr_find(&aux_idr, index);
-	if (!kref_get_unless_zero(&aux_dev->refcount))
+	if (aux_dev && !kref_get_unless_zero(&aux_dev->refcount))
 		aux_dev = NULL;
 	mutex_unlock(&aux_idr_mutex);
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 82add73..2de1eeb 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -27,6 +27,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
+#include <linux/iopoll.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -339,7 +340,7 @@
 			memcpy(&buf[idx], req->u.i2c_read.transactions[i].bytes, req->u.i2c_read.transactions[i].num_bytes);
 			idx += req->u.i2c_read.transactions[i].num_bytes;
 
-			buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 5;
+			buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 4;
 			buf[idx] |= (req->u.i2c_read.transactions[i].i2c_transaction_delay & 0xf);
 			idx++;
 		}
@@ -2465,9 +2466,11 @@
 			drm_dp_mst_topology_put_port(port);
 	}
 
-	for (i = 0; i < mgr->max_payloads; i++) {
-		if (mgr->payloads[i].payload_state != DP_PAYLOAD_DELETE_LOCAL)
+	for (i = 0; i < mgr->max_payloads; /* do nothing */) {
+		if (mgr->payloads[i].payload_state != DP_PAYLOAD_DELETE_LOCAL) {
+			i++;
 			continue;
+		}
 
 		DRM_DEBUG_KMS("removing payload %d\n", i);
 		for (j = i; j < mgr->max_payloads - 1; j++) {
@@ -2694,6 +2697,7 @@
 	int ret = 0;
 	struct drm_dp_mst_branch *mstb = NULL;
 
+	mutex_lock(&mgr->payload_lock);
 	mutex_lock(&mgr->lock);
 	if (mst_state == mgr->mst_state)
 		goto out_unlock;
@@ -2752,7 +2756,10 @@
 		/* this can fail if the device is gone */
 		drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, 0);
 		ret = 0;
-		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
+		memset(mgr->payloads, 0,
+		       mgr->max_payloads * sizeof(mgr->payloads[0]));
+		memset(mgr->proposed_vcpis, 0,
+		       mgr->max_payloads * sizeof(mgr->proposed_vcpis[0]));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
 		mgr->vcpi_mask = 0;
@@ -2760,6 +2767,7 @@
 
 out_unlock:
 	mutex_unlock(&mgr->lock);
+	mutex_unlock(&mgr->payload_lock);
 	if (mstb)
 		drm_dp_mst_topology_put_mstb(mstb);
 	return ret;
@@ -3361,11 +3369,11 @@
 {
 	int ret;
 
-	port = drm_dp_mst_topology_get_port_validated(mgr, port);
-	if (!port)
+	if (slots < 0)
 		return false;
 
-	if (slots < 0)
+	port = drm_dp_mst_topology_get_port_validated(mgr, port);
+	if (!port)
 		return false;
 
 	if (port->vcpi.vcpi > 0) {
@@ -3381,6 +3389,7 @@
 	if (ret) {
 		DRM_DEBUG_KMS("failed to init vcpi slots=%d max=63 ret=%d\n",
 			      DIV_ROUND_UP(pbn, mgr->pbn_div), ret);
+		drm_dp_mst_topology_put_port(port);
 		goto out;
 	}
 	DRM_DEBUG_KMS("initing vcpi for pbn=%d slots=%d\n",
@@ -3491,6 +3500,17 @@
 	return ret;
 }
 
+static int do_get_act_status(struct drm_dp_aux *aux)
+{
+	int ret;
+	u8 status;
+
+	ret = drm_dp_dpcd_readb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status);
+	if (ret < 0)
+		return ret;
+
+	return status;
+}
 
 /**
  * drm_dp_check_act_status() - Check ACT handled status.
@@ -3500,33 +3520,29 @@
  */
 int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr)
 {
-	u8 status;
-	int ret;
-	int count = 0;
+	/*
+	 * There doesn't seem to be any recommended retry count or timeout in
+	 * the MST specification. Since some hubs have been observed to take
+	 * over 1 second to update their payload allocations under certain
+	 * conditions, we use a rather large timeout value.
+	 */
+	const int timeout_ms = 3000;
+	int ret, status;
 
-	do {
-		ret = drm_dp_dpcd_readb(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status);
-
-		if (ret < 0) {
-			DRM_DEBUG_KMS("failed to read payload table status %d\n", ret);
-			goto fail;
-		}
-
-		if (status & DP_PAYLOAD_ACT_HANDLED)
-			break;
-		count++;
-		udelay(100);
-
-	} while (count < 30);
-
-	if (!(status & DP_PAYLOAD_ACT_HANDLED)) {
-		DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n", status, count);
-		ret = -EINVAL;
-		goto fail;
+	ret = readx_poll_timeout(do_get_act_status, mgr->aux, status,
+				 status & DP_PAYLOAD_ACT_HANDLED || status < 0,
+				 200, timeout_ms * USEC_PER_MSEC);
+	if (ret < 0 && status >= 0) {
+		DRM_DEBUG_KMS("Failed to get ACT after %dms, last status: %02x\n",
+			      timeout_ms, status);
+		return -EINVAL;
+	} else if (status < 0) {
+		DRM_DEBUG_KMS("Failed to read payload table status: %d\n",
+			      status);
+		return status;
 	}
+
 	return 0;
-fail:
-	return ret;
 }
 EXPORT_SYMBOL(drm_dp_check_act_status);
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 6b01771..9b69e55 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -191,10 +191,11 @@
 	{ "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP },
 	{ "HVR", 0xaa02, EDID_QUIRK_NON_DESKTOP },
 
-	/* Oculus Rift DK1, DK2, and CV1 VR Headsets */
+	/* Oculus Rift DK1, DK2, CV1 and Rift S VR Headsets */
 	{ "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP },
 	{ "OVR", 0x0003, EDID_QUIRK_NON_DESKTOP },
 	{ "OVR", 0x0004, EDID_QUIRK_NON_DESKTOP },
+	{ "OVR", 0x0012, EDID_QUIRK_NON_DESKTOP },
 
 	/* Windows Mixed Reality Headsets */
 	{ "ACR", 0x7fce, EDID_QUIRK_NON_DESKTOP },
@@ -3722,7 +3723,7 @@
 		if (*end < 4 || *end > 127)
 			return -ERANGE;
 	} else {
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -4191,7 +4192,7 @@
 
 	if (cea_revision(cea) < 3) {
 		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if (cea_db_offsets(cea, &start, &end)) {
@@ -4252,7 +4253,7 @@
 
 	if (cea_revision(cea) < 3) {
 		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if (cea_db_offsets(cea, &start, &end)) {
@@ -4743,7 +4744,7 @@
 	struct drm_display_mode *mode;
 	unsigned pixel_clock = (timings->pixel_clock[0] |
 				(timings->pixel_clock[1] << 8) |
-				(timings->pixel_clock[2] << 16));
+				(timings->pixel_clock[2] << 16)) + 1;
 	unsigned hactive = (timings->hactive[0] | timings->hactive[1] << 8) + 1;
 	unsigned hblank = (timings->hblank[0] | timings->hblank[1] << 8) + 1;
 	unsigned hsync = (timings->hsync[0] | (timings->hsync[1] & 0x7f) << 8) + 1;
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index cf80438..d50a788 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -84,7 +84,7 @@
 
 	err = encoder_drv->encoder_init(client, dev, encoder);
 	if (err)
-		goto fail_unregister;
+		goto fail_module_put;
 
 	if (info->platform_data)
 		encoder->slave_funcs->set_config(&encoder->base,
@@ -92,9 +92,10 @@
 
 	return 0;
 
+fail_module_put:
+	module_put(module);
 fail_unregister:
 	i2c_unregister_device(client);
-	module_put(module);
 fail:
 	return err;
 }
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index a7ba5b4..02ffde5 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -390,7 +390,11 @@
 	unsigned int y;
 
 	for (y = clip->y1; y < clip->y2; y++) {
-		memcpy(dst, src, len);
+		if (!fb_helper->dev->mode_config.fbdev_use_iomem)
+			memcpy(dst, src, len);
+		else
+			memcpy_toio((void __iomem *)dst, src, len);
+
 		src += fb->pitches[0];
 		dst += fb->pitches[0];
 	}
@@ -961,11 +965,15 @@
 	drm_modeset_lock_all(fb_helper->dev);
 	drm_client_for_each_modeset(modeset, &fb_helper->client) {
 		crtc = modeset->crtc;
-		if (!crtc->funcs->gamma_set || !crtc->gamma_size)
-			return -EINVAL;
+		if (!crtc->funcs->gamma_set || !crtc->gamma_size) {
+			ret = -EINVAL;
+			goto out;
+		}
 
-		if (cmap->start + cmap->len > crtc->gamma_size)
-			return -EINVAL;
+		if (cmap->start + cmap->len > crtc->gamma_size) {
+			ret = -EINVAL;
+			goto out;
+		}
 
 		r = crtc->gamma_store;
 		g = r + crtc->gamma_size;
@@ -978,8 +986,9 @@
 		ret = crtc->funcs->gamma_set(crtc, r, g, b,
 					     crtc->gamma_size, NULL);
 		if (ret)
-			return ret;
+			goto out;
 	}
+out:
 	drm_modeset_unlock_all(fb_helper->dev);
 
 	return ret;
@@ -1320,7 +1329,7 @@
 	 * Changes struct fb_var_screeninfo are currently not pushed back
 	 * to KMS, hence fail if different settings are requested.
 	 */
-	if (var->bits_per_pixel != fb->format->cpp[0] * 8 ||
+	if (var->bits_per_pixel > fb->format->cpp[0] * 8 ||
 	    var->xres > fb->width || var->yres > fb->height ||
 	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
 		DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
@@ -1346,6 +1355,11 @@
 	}
 
 	/*
+	 * Likewise, bits_per_pixel should be rounded up to a supported value.
+	 */
+	var->bits_per_pixel = fb->format->cpp[0] * 8;
+
+	/*
 	 * drm fbdev emulation doesn't support changing the pixel format at all,
 	 * so reject all pixel format changing requests.
 	 */
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 6854f58..1fdc85a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -710,6 +710,8 @@
 	if (!objs)
 		return -ENOMEM;
 
+	*objs_out = objs;
+
 	handles = kvmalloc_array(count, sizeof(u32), GFP_KERNEL);
 	if (!handles) {
 		ret = -ENOMEM;
@@ -723,8 +725,6 @@
 	}
 
 	ret = objects_lookup(filp, handles, count, objs);
-	*objs_out = objs;
-
 out:
 	kvfree(handles);
 	return ret;
@@ -872,9 +872,6 @@
  * @file_priv: drm file-private structure
  *
  * Open an object using the global name, returning a handle and the size.
- *
- * This handle (of course) holds a reference to the object, so the object
- * will not go away until the handle is deleted.
  */
 int
 drm_gem_open_ioctl(struct drm_device *dev, void *data,
@@ -899,14 +896,15 @@
 
 	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
 	ret = drm_gem_handle_create_tail(file_priv, obj, &handle);
-	drm_gem_object_put_unlocked(obj);
 	if (ret)
-		return ret;
+		goto err;
 
 	args->handle = handle;
 	args->size = obj->size;
 
-	return 0;
+err:
+	drm_gem_object_put_unlocked(obj);
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index f591870..d88f423 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -474,14 +474,28 @@
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	loff_t num_pages = obj->size >> PAGE_SHIFT;
+	vm_fault_t ret;
 	struct page *page;
+	pgoff_t page_offset;
 
-	if (vmf->pgoff >= num_pages || WARN_ON_ONCE(!shmem->pages))
-		return VM_FAULT_SIGBUS;
+	/* We don't use vmf->pgoff since that has the fake offset */
+	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
-	page = shmem->pages[vmf->pgoff];
+	mutex_lock(&shmem->pages_lock);
 
-	return vmf_insert_page(vma, vmf->address, page);
+	if (page_offset >= num_pages ||
+	    WARN_ON_ONCE(!shmem->pages) ||
+	    shmem->madv < 0) {
+		ret = VM_FAULT_SIGBUS;
+	} else {
+		page = shmem->pages[page_offset];
+
+		ret = vmf_insert_page(vma, vmf->address, page);
+	}
+
+	mutex_unlock(&shmem->pages_lock);
+
+	return ret;
 }
 
 static void drm_gem_shmem_vm_open(struct vm_area_struct *vma)
@@ -549,9 +563,6 @@
 	vma->vm_flags &= ~VM_PFNMAP;
 	vma->vm_flags |= VM_MIXEDMAP;
 
-	/* Remove the fake offset */
-	vma->vm_pgoff -= drm_vma_node_start(&shmem->base.vma_node);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(drm_gem_shmem_mmap);
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index 22c7fd7..1c691bd 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -99,6 +99,8 @@
 	if (copy_from_user(&v32, (void __user *)arg, sizeof(v32)))
 		return -EFAULT;
 
+	memset(&v, 0, sizeof(v));
+
 	v = (struct drm_version) {
 		.name_len = v32.name_len,
 		.name = compat_ptr(v32.name),
@@ -137,6 +139,9 @@
 
 	if (copy_from_user(&uq32, (void __user *)arg, sizeof(uq32)))
 		return -EFAULT;
+
+	memset(&uq, 0, sizeof(uq));
+
 	uq = (struct drm_unique){
 		.unique_len = uq32.unique_len,
 		.unique = compat_ptr(uq32.unique),
@@ -265,6 +270,8 @@
 	if (copy_from_user(&c32, argp, sizeof(c32)))
 		return -EFAULT;
 
+	memset(&client, 0, sizeof(client));
+
 	client.idx = c32.idx;
 
 	err = drm_ioctl_kernel(file, drm_getclient, &client, 0);
@@ -850,12 +857,12 @@
 	if (copy_from_user(&req32, argp, sizeof(req32)))
 		return -EFAULT;
 
+	memset(&req, 0, sizeof(req));
+
 	req.request.type = req32.request.type;
 	req.request.sequence = req32.request.sequence;
 	req.request.signal = req32.request.signal;
 	err = drm_ioctl_kernel(file, drm_wait_vblank_ioctl, &req, DRM_UNLOCKED);
-	if (err)
-		return err;
 
 	req32.reply.type = req.reply.type;
 	req32.reply.sequence = req.reply.sequence;
@@ -864,7 +871,7 @@
 	if (copy_to_user(argp, &req32, sizeof(req32)))
 		return -EFAULT;
 
-	return 0;
+	return err;
 }
 
 #if defined(CONFIG_X86)
@@ -887,6 +894,8 @@
 	struct drm_mode_fb_cmd2 req64;
 	int err;
 
+	memset(&req64, 0, sizeof(req64));
+
 	if (copy_from_user(&req64, argp,
 			   offsetof(drm_mode_fb_cmd232_t, modifier)))
 		return -EFAULT;
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index fcd728d..76b6676 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -118,17 +118,18 @@
 		  struct drm_file *file_priv)
 {
 	struct drm_unique *u = data;
-	struct drm_master *master = file_priv->master;
+	struct drm_master *master;
 
-	mutex_lock(&master->dev->master_mutex);
+	mutex_lock(&dev->master_mutex);
+	master = file_priv->master;
 	if (u->unique_len >= master->unique_len) {
 		if (copy_to_user(u->unique, master->unique, master->unique_len)) {
-			mutex_unlock(&master->dev->master_mutex);
+			mutex_unlock(&dev->master_mutex);
 			return -EFAULT;
 		}
 	}
 	u->unique_len = master->unique_len;
-	mutex_unlock(&master->dev->master_mutex);
+	mutex_unlock(&dev->master_mutex);
 
 	return 0;
 }
@@ -825,6 +826,9 @@
 	if (drm_dev_is_unplugged(dev))
 		return -ENODEV;
 
+       if (DRM_IOCTL_TYPE(cmd) != DRM_IOCTL_BASE)
+               return -ENOTTY;
+
 	is_driver_ioctl = nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END;
 
 	if (is_driver_ioctl) {
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index b481caf..825abe3 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -542,10 +542,12 @@
 	}
 
 	DRM_DEBUG_LEASE("Creating lease\n");
+	/* lessee will take the ownership of leases */
 	lessee = drm_lease_create(lessor, &leases);
 
 	if (IS_ERR(lessee)) {
 		ret = PTR_ERR(lessee);
+		idr_destroy(&leases);
 		goto out_leases;
 	}
 
@@ -580,7 +582,6 @@
 
 out_leases:
 	put_unused_fd(fd);
-	idr_destroy(&leases);
 
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl failed: %d\n", ret);
 	return ret;
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index 1961f71..4042f5b 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -367,9 +367,9 @@
 	memset(dbidev->tx_buf, 0, len);
 
 	mipi_dbi_command(dbi, MIPI_DCS_SET_COLUMN_ADDRESS, 0, 0,
-			 (width >> 8) & 0xFF, (width - 1) & 0xFF);
+			 ((width - 1) >> 8) & 0xFF, (width - 1) & 0xFF);
 	mipi_dbi_command(dbi, MIPI_DCS_SET_PAGE_ADDRESS, 0, 0,
-			 (height >> 8) & 0xFF, (height - 1) & 0xFF);
+			 ((height - 1) >> 8) & 0xFF, (height - 1) & 0xFF);
 	mipi_dbi_command_buf(dbi, MIPI_DCS_WRITE_MEMORY_START,
 			     (u8 *)dbidev->tx_buf, len);
 
@@ -937,7 +937,7 @@
 			}
 		}
 
-		tr.len = chunk;
+		tr.len = chunk * 2;
 		len -= chunk;
 
 		ret = spi_sync(spi, &m);
@@ -955,7 +955,7 @@
 	int ret;
 
 	if (mipi_dbi_command_is_read(dbi, *cmd))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	MIPI_DBI_DEBUG_COMMAND(*cmd, parameters, num);
 
@@ -1187,8 +1187,7 @@
 	struct mipi_dbi_dev *dbidev = m->private;
 	u8 val, cmd = 0, parameters[64];
 	char *buf, *pos, *token;
-	unsigned int i;
-	int ret, idx;
+	int i, ret, idx;
 
 	if (!drm_dev_enter(&dbidev->drm, &idx))
 		return -ENODEV;
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index bd2498b..b99f96d 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -1029,11 +1029,11 @@
  */
 int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline)
 {
-	u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, scanline >> 8,
-			  scanline & 0xff };
+	u8 payload[2] = { scanline >> 8, scanline & 0xff };
 	ssize_t err;
 
-	err = mipi_dsi_generic_write(dsi, payload, sizeof(payload));
+	err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_TEAR_SCANLINE, payload,
+				 sizeof(payload));
 	if (err < 0)
 		return err;
 
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 8823269..3fd35e6 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1672,6 +1672,13 @@
 		}
 	}
 
+	if (!(rotation & DRM_MODE_ROTATE_MASK))
+		rotation |= DRM_MODE_ROTATE_0;
+
+	/* Make sure there is exactly one rotation defined */
+	if (!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK))
+		return -EINVAL;
+
 	mode->rotation_reflection = rotation;
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index ffd95bf..f6bdec7 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -30,12 +30,6 @@
 	int orientation;
 };
 
-static const struct drm_dmi_panel_orientation_data acer_s1003 = {
-	.width = 800,
-	.height = 1280,
-	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
-};
-
 static const struct drm_dmi_panel_orientation_data asus_t100ha = {
 	.width = 800,
 	.height = 1280,
@@ -90,6 +84,13 @@
 	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
 };
 
+static const struct drm_dmi_panel_orientation_data onegx1_pro = {
+	.width = 1200,
+	.height = 1920,
+	.bios_dates = (const char * const []){ "12/17/2020", NULL },
+	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
+};
+
 static const struct drm_dmi_panel_orientation_data lcd720x1280_rightside_up = {
 	.width = 720,
 	.height = 1280,
@@ -114,13 +115,25 @@
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"),
 		},
-		.driver_data = (void *)&acer_s1003,
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* Asus T100HA */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"),
 		},
 		.driver_data = (void *)&asus_t100ha,
+	}, {	/* Asus T101HA */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Asus T103HAF */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* GPD MicroPC (generic strings, also match on bios date) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
@@ -205,6 +218,13 @@
 		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"),
 		},
 		.driver_data = (void *)&lcd1200x1920_rightside_up,
+	}, {	/* OneGX1 Pro */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SYSTEM_MANUFACTURER"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SYSTEM_PRODUCT_NAME"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Default string"),
+		},
+		.driver_data = (void *)&onegx1_pro,
 	}, {	/* VIOS LTH17 */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "VIOS"),
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index a86a3ab..235729f 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -51,8 +51,6 @@
 drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align)
 {
 	drm_dma_handle_t *dmah;
-	unsigned long addr;
-	size_t sz;
 
 	/* pci_alloc_consistent only guarantees alignment to the smallest
 	 * PAGE_SIZE order which is greater than or equal to the requested size.
@@ -68,20 +66,13 @@
 	dmah->size = size;
 	dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
 					 &dmah->busaddr,
-					 GFP_KERNEL | __GFP_COMP);
+					 GFP_KERNEL);
 
 	if (dmah->vaddr == NULL) {
 		kfree(dmah);
 		return NULL;
 	}
 
-	/* XXX - Is virt_to_page() legal for consistent mem? */
-	/* Reserve */
-	for (addr = (unsigned long)dmah->vaddr, sz = size;
-	     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-		SetPageReserved(virt_to_page((void *)addr));
-	}
-
 	return dmah;
 }
 
@@ -94,19 +85,9 @@
  */
 void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
-	unsigned long addr;
-	size_t sz;
-
-	if (dmah->vaddr) {
-		/* XXX - Is virt_to_page() legal for consistent mem? */
-		/* Unreserve */
-		for (addr = (unsigned long)dmah->vaddr, sz = dmah->size;
-		     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-			ClearPageReserved(virt_to_page((void *)addr));
-		}
+	if (dmah->vaddr)
 		dma_free_coherent(&dev->pdev->dev, dmah->size, dmah->vaddr,
 				  dmah->busaddr);
-	}
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index 892ce63..6ee0480 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -561,7 +561,7 @@
 	struct drm_property_blob *blob;
 	int ret;
 
-	if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob))
+	if (!length || length > INT_MAX - sizeof(struct drm_property_blob))
 		return ERR_PTR(-EINVAL);
 
 	blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
diff --git a/drivers/gpu/drm/drm_rect.c b/drivers/gpu/drm/drm_rect.c
index b8363aa..818738e 100644
--- a/drivers/gpu/drm/drm_rect.c
+++ b/drivers/gpu/drm/drm_rect.c
@@ -54,7 +54,12 @@
 
 static u32 clip_scaled(u32 src, u32 dst, u32 clip)
 {
-	u64 tmp = mul_u32_u32(src, dst - clip);
+	u64 tmp;
+
+	if (dst == 0)
+		return 0;
+
+	tmp = mul_u32_u32(src, dst - clip);
 
 	/*
 	 * Round toward 1.0 when clipping so that we don't accidentally
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 4b5c7b0..8fdb271 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -326,19 +326,18 @@
 		return -ENOENT;
 
 	*fence = drm_syncobj_fence_get(syncobj);
-	drm_syncobj_put(syncobj);
 
 	if (*fence) {
 		ret = dma_fence_chain_find_seqno(fence, point);
 		if (!ret)
-			return 0;
+			goto out;
 		dma_fence_put(*fence);
 	} else {
 		ret = -EINVAL;
 	}
 
 	if (!(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT))
-		return ret;
+		goto out;
 
 	memset(&wait, 0, sizeof(wait));
 	wait.task = current;
@@ -370,6 +369,9 @@
 	if (wait.node.next)
 		drm_syncobj_remove_wait(syncobj, &wait);
 
+out:
+	drm_syncobj_put(syncobj);
+
 	return ret;
 }
 EXPORT_SYMBOL(drm_syncobj_find_fence);
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index dd2bc85..4fd2f6c 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -293,9 +293,6 @@
 		return PTR_ERR(connector->kdev);
 	}
 
-	/* Let userspace know we have a new connector */
-	drm_sysfs_hotplug_event(dev);
-
 	if (connector->ddc)
 		return sysfs_create_link(&connector->kdev->kobj,
 				 &connector->ddc->dev.kobj, "ddc");
diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c
index fd1fbc7..552ec82 100644
--- a/drivers/gpu/drm/drm_vblank.c
+++ b/drivers/gpu/drm/drm_vblank.c
@@ -1581,7 +1581,7 @@
 	unsigned int flags, pipe, high_pipe;
 
 	if (!dev->irq_enabled)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	if (vblwait->request.type & _DRM_VBLANK_SIGNAL)
 		return -EINVAL;
@@ -1838,7 +1838,7 @@
 		return -EOPNOTSUPP;
 
 	if (!dev->irq_enabled)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	crtc = drm_crtc_find(dev, file_priv, get_seq->crtc_id);
 	if (!crtc)
@@ -1896,7 +1896,7 @@
 		return -EOPNOTSUPP;
 
 	if (!dev->irq_enabled)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	crtc = drm_crtc_find(dev, file_priv, queue_seq->crtc_id);
 	if (!crtc)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index 7e4e295..35225ff 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -12,6 +12,7 @@
 
 #include "common.xml.h"
 #include "state.xml.h"
+#include "state_blt.xml.h"
 #include "state_hi.xml.h"
 #include "state_3d.xml.h"
 #include "cmdstream.xml.h"
@@ -233,6 +234,8 @@
 	struct etnaviv_cmdbuf *buffer = &gpu->buffer;
 	unsigned int waitlink_offset = buffer->user_size - 16;
 	u32 link_target, flush = 0;
+	bool has_blt = !!(gpu->identity.minor_features5 &
+			  chipMinorFeatures5_BLT_ENGINE);
 
 	lockdep_assert_held(&gpu->lock);
 
@@ -248,16 +251,38 @@
 	if (flush) {
 		unsigned int dwords = 7;
 
+		if (has_blt)
+			dwords += 10;
+
 		link_target = etnaviv_buffer_reserve(gpu, buffer, dwords);
 
 		CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
 		CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
+		if (has_blt) {
+			CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x1);
+			CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_BLT);
+			CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_BLT);
+			CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x0);
+		}
 		CMD_LOAD_STATE(buffer, VIVS_GL_FLUSH_CACHE, flush);
-		if (gpu->exec_state == ETNA_PIPE_3D)
-			CMD_LOAD_STATE(buffer, VIVS_TS_FLUSH_CACHE,
-				       VIVS_TS_FLUSH_CACHE_FLUSH);
+		if (gpu->exec_state == ETNA_PIPE_3D) {
+			if (has_blt) {
+				CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x1);
+				CMD_LOAD_STATE(buffer, VIVS_BLT_SET_COMMAND, 0x1);
+				CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x0);
+			} else {
+				CMD_LOAD_STATE(buffer, VIVS_TS_FLUSH_CACHE,
+					       VIVS_TS_FLUSH_CACHE_FLUSH);
+			}
+		}
 		CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
 		CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
+		if (has_blt) {
+			CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x1);
+			CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_BLT);
+			CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_BLT);
+			CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x0);
+		}
 		CMD_END(buffer);
 
 		etnaviv_buffer_replace_wait(buffer, waitlink_offset,
@@ -323,6 +348,8 @@
 	bool switch_mmu_context = gpu->mmu_context != mmu_context;
 	unsigned int new_flush_seq = READ_ONCE(gpu->mmu_context->flush_seq);
 	bool need_flush = switch_mmu_context || gpu->flush_seq != new_flush_seq;
+	bool has_blt = !!(gpu->identity.minor_features5 &
+			  chipMinorFeatures5_BLT_ENGINE);
 
 	lockdep_assert_held(&gpu->lock);
 
@@ -370,8 +397,7 @@
 		if (switch_mmu_context) {
 			struct etnaviv_iommu_context *old_context = gpu->mmu_context;
 
-			etnaviv_iommu_context_get(mmu_context);
-			gpu->mmu_context = mmu_context;
+			gpu->mmu_context = etnaviv_iommu_context_get(mmu_context);
 			etnaviv_iommu_context_put(old_context);
 		}
 
@@ -433,6 +459,15 @@
 	 * 2 semaphore stall + 1 event + 1 wait + 1 link.
 	 */
 	return_dwords = 7;
+
+	/*
+	 * When the BLT engine is present we need 6 more dwords in the return
+	 * target: 3 enable/flush/disable + 4 enable/semaphore stall/disable,
+	 * but we don't need the normal TS flush state.
+	 */
+	if (has_blt)
+		return_dwords += 6;
+
 	return_target = etnaviv_buffer_reserve(gpu, buffer, return_dwords);
 	CMD_LINK(cmdbuf, return_dwords, return_target);
 
@@ -447,11 +482,25 @@
 		CMD_LOAD_STATE(buffer, VIVS_GL_FLUSH_CACHE,
 				       VIVS_GL_FLUSH_CACHE_DEPTH |
 				       VIVS_GL_FLUSH_CACHE_COLOR);
-		CMD_LOAD_STATE(buffer, VIVS_TS_FLUSH_CACHE,
-				       VIVS_TS_FLUSH_CACHE_FLUSH);
+		if (has_blt) {
+			CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x1);
+			CMD_LOAD_STATE(buffer, VIVS_BLT_SET_COMMAND, 0x1);
+			CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x0);
+		} else {
+			CMD_LOAD_STATE(buffer, VIVS_TS_FLUSH_CACHE,
+					       VIVS_TS_FLUSH_CACHE_FLUSH);
+		}
 	}
 	CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
 	CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
+
+	if (has_blt) {
+		CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x1);
+		CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_BLT);
+		CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_BLT);
+		CMD_LOAD_STATE(buffer, VIVS_BLT_ENABLE, 0x0);
+	}
+
 	CMD_LOAD_STATE(buffer, VIVS_GL_EVENT, VIVS_GL_EVENT_EVENT_ID(event) |
 		       VIVS_GL_EVENT_FROM_PE);
 	CMD_WAIT(buffer);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index cb1faaa..5199486 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -304,8 +304,7 @@
 		list_del(&mapping->obj_node);
 	}
 
-	etnaviv_iommu_context_get(mmu_context);
-	mapping->context = mmu_context;
+	mapping->context = etnaviv_iommu_context_get(mmu_context);
 	mapping->use = 1;
 
 	ret = etnaviv_iommu_map_gem(mmu_context, etnaviv_obj,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index aa3e4c3..7085b08 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -240,8 +240,10 @@
 		}
 
 		if ((submit->flags & ETNA_SUBMIT_SOFTPIN) &&
-		     submit->bos[i].va != mapping->iova)
+		     submit->bos[i].va != mapping->iova) {
+			etnaviv_gem_mapping_unreference(mapping);
 			return -EINVAL;
+		}
 
 		atomic_inc(&etnaviv_obj->gpu_active);
 
@@ -532,8 +534,7 @@
 		goto err_submit_objects;
 
 	submit->ctx = file->driver_priv;
-	etnaviv_iommu_context_get(submit->ctx->mmu);
-	submit->mmu_context = submit->ctx->mmu;
+	submit->mmu_context = etnaviv_iommu_context_get(submit->ctx->mmu);
 	submit->exec_state = args->exec_state;
 	submit->flags = args->flags;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index d47d1a8..db35736 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -545,6 +545,12 @@
 	/* We rely on the GPU running, so program the clock */
 	etnaviv_gpu_update_clock(gpu);
 
+	gpu->fe_running = false;
+	gpu->exec_state = -1;
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = NULL;
+
 	return 0;
 }
 
@@ -607,19 +613,23 @@
 			  VIVS_MMUv2_SEC_COMMAND_CONTROL_ENABLE |
 			  VIVS_MMUv2_SEC_COMMAND_CONTROL_PREFETCH(prefetch));
 	}
+
+	gpu->fe_running = true;
 }
 
-static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu)
+static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu,
+					  struct etnaviv_iommu_context *context)
 {
-	u32 address = etnaviv_cmdbuf_get_va(&gpu->buffer,
-				&gpu->mmu_context->cmdbuf_mapping);
 	u16 prefetch;
+	u32 address;
 
 	/* setup the MMU */
-	etnaviv_iommu_restore(gpu, gpu->mmu_context);
+	etnaviv_iommu_restore(gpu, context);
 
 	/* Start command processor */
 	prefetch = etnaviv_buffer_init(gpu);
+	address = etnaviv_cmdbuf_get_va(&gpu->buffer,
+					&gpu->mmu_context->cmdbuf_mapping);
 
 	etnaviv_gpu_start_fe(gpu, address, prefetch);
 }
@@ -713,7 +723,7 @@
 	ret = pm_runtime_get_sync(gpu->dev);
 	if (ret < 0) {
 		dev_err(gpu->dev, "Failed to enable GPU power domain\n");
-		return ret;
+		goto pm_put;
 	}
 
 	etnaviv_hw_identify(gpu);
@@ -790,7 +800,6 @@
 	/* Now program the hardware */
 	mutex_lock(&gpu->lock);
 	etnaviv_gpu_hw_init(gpu);
-	gpu->exec_state = -1;
 	mutex_unlock(&gpu->lock);
 
 	pm_runtime_mark_last_busy(gpu->dev);
@@ -802,6 +811,7 @@
 
 fail:
 	pm_runtime_mark_last_busy(gpu->dev);
+pm_put:
 	pm_runtime_put_autosuspend(gpu->dev);
 
 	return ret;
@@ -842,7 +852,7 @@
 
 	ret = pm_runtime_get_sync(gpu->dev);
 	if (ret < 0)
-		return ret;
+		goto pm_put;
 
 	dma_lo = gpu_read(gpu, VIVS_FE_DMA_LOW);
 	dma_hi = gpu_read(gpu, VIVS_FE_DMA_HIGH);
@@ -965,6 +975,7 @@
 	ret = 0;
 
 	pm_runtime_mark_last_busy(gpu->dev);
+pm_put:
 	pm_runtime_put_autosuspend(gpu->dev);
 
 	return ret;
@@ -978,7 +989,7 @@
 	dev_err(gpu->dev, "recover hung GPU!\n");
 
 	if (pm_runtime_get_sync(gpu->dev) < 0)
-		return;
+		goto pm_put;
 
 	mutex_lock(&gpu->lock);
 
@@ -992,11 +1003,10 @@
 	spin_unlock(&gpu->event_spinlock);
 
 	etnaviv_gpu_hw_init(gpu);
-	gpu->exec_state = -1;
-	gpu->mmu_context = NULL;
 
 	mutex_unlock(&gpu->lock);
 	pm_runtime_mark_last_busy(gpu->dev);
+pm_put:
 	pm_runtime_put_autosuspend(gpu->dev);
 }
 
@@ -1269,8 +1279,10 @@
 
 	if (!submit->runtime_resumed) {
 		ret = pm_runtime_get_sync(gpu->dev);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_noidle(gpu->dev);
 			return NULL;
+		}
 		submit->runtime_resumed = true;
 	}
 
@@ -1287,6 +1299,7 @@
 	ret = event_alloc(gpu, nr_events, event);
 	if (ret) {
 		DRM_ERROR("no free events\n");
+		pm_runtime_put_noidle(gpu->dev);
 		return NULL;
 	}
 
@@ -1300,14 +1313,12 @@
 		goto out_unlock;
 	}
 
-	if (!gpu->mmu_context) {
-		etnaviv_iommu_context_get(submit->mmu_context);
-		gpu->mmu_context = submit->mmu_context;
-		etnaviv_gpu_start_fe_idleloop(gpu);
-	} else {
-		etnaviv_iommu_context_get(gpu->mmu_context);
-		submit->prev_mmu_context = gpu->mmu_context;
-	}
+	if (!gpu->fe_running)
+		etnaviv_gpu_start_fe_idleloop(gpu, submit->mmu_context);
+
+	if (submit->prev_mmu_context)
+		etnaviv_iommu_context_put(submit->prev_mmu_context);
+	submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context);
 
 	if (submit->nr_pmrs) {
 		gpu->event[event[1]].sync_point = &sync_point_perfmon_sample_pre;
@@ -1457,7 +1468,7 @@
 	if (gpu->clk_bus) {
 		ret = clk_prepare_enable(gpu->clk_bus);
 		if (ret)
-			return ret;
+			goto disable_clk_reg;
 	}
 
 	if (gpu->clk_core) {
@@ -1480,6 +1491,9 @@
 disable_clk_bus:
 	if (gpu->clk_bus)
 		clk_disable_unprepare(gpu->clk_bus);
+disable_clk_reg:
+	if (gpu->clk_reg)
+		clk_disable_unprepare(gpu->clk_reg);
 
 	return ret;
 }
@@ -1521,7 +1535,7 @@
 
 static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu)
 {
-	if (gpu->initialized && gpu->mmu_context) {
+	if (gpu->initialized && gpu->fe_running) {
 		/* Replace the last WAIT with END */
 		mutex_lock(&gpu->lock);
 		etnaviv_buffer_end(gpu);
@@ -1534,8 +1548,7 @@
 		 */
 		etnaviv_gpu_wait_idle(gpu, 100);
 
-		etnaviv_iommu_context_put(gpu->mmu_context);
-		gpu->mmu_context = NULL;
+		gpu->fe_running = false;
 	}
 
 	gpu->exec_state = -1;
@@ -1683,6 +1696,9 @@
 	etnaviv_gpu_hw_suspend(gpu);
 #endif
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+
 	if (gpu->initialized) {
 		etnaviv_cmdbuf_free(&gpu->buffer);
 		etnaviv_iommu_global_fini(gpu);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 8f9bd4e..02478c7 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -101,6 +101,7 @@
 	struct workqueue_struct *wq;
 	struct drm_gpu_scheduler sched;
 	bool initialized;
+	bool fe_running;
 
 	/* 'ring'-buffer: */
 	struct etnaviv_cmdbuf buffer;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
index 1a7c89a..afe5dd6 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c
@@ -92,6 +92,10 @@
 	struct etnaviv_iommuv1_context *v1_context = to_v1_context(context);
 	u32 pgtable;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	/* set base addresses */
 	gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_RA, context->global->memory_base);
 	gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_FE, context->global->memory_base);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index f8bf488..d664ae2 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -172,6 +172,10 @@
 	if (gpu_read(gpu, VIVS_MMUv2_CONTROL) & VIVS_MMUv2_CONTROL_ENABLE)
 		return;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	prefetch = etnaviv_buffer_config_mmuv2(gpu,
 				(u32)v2_context->mtlb_dma,
 				(u32)context->global->bad_page_dma);
@@ -192,6 +196,10 @@
 	if (gpu_read(gpu, VIVS_MMUv2_SEC_CONTROL) & VIVS_MMUv2_SEC_CONTROL_ENABLE)
 		return;
 
+	if (gpu->mmu_context)
+		etnaviv_iommu_context_put(gpu->mmu_context);
+	gpu->mmu_context = etnaviv_iommu_context_get(context);
+
 	gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_LOW,
 		  lower_32_bits(context->global->v2.pta_dma));
 	gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_HIGH,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 3607d34..707f5c1 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -204,6 +204,7 @@
 		 */
 		list_for_each_entry_safe(m, n, &list, scan_node) {
 			etnaviv_iommu_remove_mapping(context, m);
+			etnaviv_iommu_context_put(m->context);
 			m->context = NULL;
 			list_del_init(&m->mmu_node);
 			list_del_init(&m->scan_node);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
index d1d6902..e4a0b7d 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
@@ -105,9 +105,11 @@
 struct etnaviv_iommu_context *
 etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
 			   struct etnaviv_cmdbuf_suballoc *suballoc);
-static inline void etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
+static inline struct etnaviv_iommu_context *
+etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
 {
 	kref_get(&ctx->refcount);
+	return ctx;
 }
 void etnaviv_iommu_context_put(struct etnaviv_iommu_context *ctx);
 void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
index 8adbf28..75f9db8 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
@@ -32,6 +32,7 @@
 };
 
 struct etnaviv_pm_domain_meta {
+	unsigned int feature;
 	const struct etnaviv_pm_domain *domains;
 	u32 nr_domains;
 };
@@ -410,36 +411,78 @@
 
 static const struct etnaviv_pm_domain_meta doms_meta[] = {
 	{
+		.feature = chipFeatures_PIPE_3D,
 		.nr_domains = ARRAY_SIZE(doms_3d),
 		.domains = &doms_3d[0]
 	},
 	{
+		.feature = chipFeatures_PIPE_2D,
 		.nr_domains = ARRAY_SIZE(doms_2d),
 		.domains = &doms_2d[0]
 	},
 	{
+		.feature = chipFeatures_PIPE_VG,
 		.nr_domains = ARRAY_SIZE(doms_vg),
 		.domains = &doms_vg[0]
 	}
 };
 
+static unsigned int num_pm_domains(const struct etnaviv_gpu *gpu)
+{
+	unsigned int num = 0, i;
+
+	for (i = 0; i < ARRAY_SIZE(doms_meta); i++) {
+		const struct etnaviv_pm_domain_meta *meta = &doms_meta[i];
+
+		if (gpu->identity.features & meta->feature)
+			num += meta->nr_domains;
+	}
+
+	return num;
+}
+
+static const struct etnaviv_pm_domain *pm_domain(const struct etnaviv_gpu *gpu,
+	unsigned int index)
+{
+	const struct etnaviv_pm_domain *domain = NULL;
+	unsigned int offset = 0, i;
+
+	for (i = 0; i < ARRAY_SIZE(doms_meta); i++) {
+		const struct etnaviv_pm_domain_meta *meta = &doms_meta[i];
+
+		if (!(gpu->identity.features & meta->feature))
+			continue;
+
+		if (index - offset >= meta->nr_domains) {
+			offset += meta->nr_domains;
+			continue;
+		}
+
+		domain = meta->domains + (index - offset);
+	}
+
+	return domain;
+}
+
 int etnaviv_pm_query_dom(struct etnaviv_gpu *gpu,
 	struct drm_etnaviv_pm_domain *domain)
 {
-	const struct etnaviv_pm_domain_meta *meta = &doms_meta[domain->pipe];
+	const unsigned int nr_domains = num_pm_domains(gpu);
 	const struct etnaviv_pm_domain *dom;
 
-	if (domain->iter >= meta->nr_domains)
+	if (domain->iter >= nr_domains)
 		return -EINVAL;
 
-	dom = meta->domains + domain->iter;
+	dom = pm_domain(gpu, domain->iter);
+	if (!dom)
+		return -EINVAL;
 
 	domain->id = domain->iter;
 	domain->nr_signals = dom->nr_signals;
 	strncpy(domain->name, dom->name, sizeof(domain->name));
 
 	domain->iter++;
-	if (domain->iter == meta->nr_domains)
+	if (domain->iter == nr_domains)
 		domain->iter = 0xff;
 
 	return 0;
@@ -448,14 +491,16 @@
 int etnaviv_pm_query_sig(struct etnaviv_gpu *gpu,
 	struct drm_etnaviv_pm_signal *signal)
 {
-	const struct etnaviv_pm_domain_meta *meta = &doms_meta[signal->pipe];
+	const unsigned int nr_domains = num_pm_domains(gpu);
 	const struct etnaviv_pm_domain *dom;
 	const struct etnaviv_pm_signal *sig;
 
-	if (signal->domain >= meta->nr_domains)
+	if (signal->domain >= nr_domains)
 		return -EINVAL;
 
-	dom = meta->domains + signal->domain;
+	dom = pm_domain(gpu, signal->domain);
+	if (!dom)
+		return -EINVAL;
 
 	if (signal->iter >= dom->nr_signals)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/etnaviv/state_blt.xml.h b/drivers/gpu/drm/etnaviv/state_blt.xml.h
index daae559..0e8bcf9 100644
--- a/drivers/gpu/drm/etnaviv/state_blt.xml.h
+++ b/drivers/gpu/drm/etnaviv/state_blt.xml.h
@@ -46,6 +46,8 @@
 
 /* This is a cut-down version of the state_blt.xml.h file */
 
+#define VIVS_BLT_SET_COMMAND					0x000140ac
+
 #define VIVS_BLT_ENABLE						0x000140b8
 #define VIVS_BLT_ENABLE_ENABLE					0x00000001
 
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 2d5cbfd..9c262da 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -55,6 +55,7 @@
 struct decon_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -644,7 +645,7 @@
 
 	decon_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, dev);
+	return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static void decon_unbind(struct device *dev, struct device *master, void *data)
@@ -654,7 +655,7 @@
 	decon_disable(ctx->crtc);
 
 	/* detach this sub driver from iommu mapping if supported. */
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static const struct component_ops decon_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f064095..6fd4041 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -40,6 +40,7 @@
 struct decon_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -127,13 +128,13 @@
 
 	decon_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, ctx->dev);
+	return exynos_drm_register_dma(drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static void decon_ctx_remove(struct decon_context *ctx)
 {
 	/* detach this sub driver from iommu mapping if supported. */
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static u32 decon_calc_clkdiv(struct decon_context *ctx,
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 3a0f0ba..e0cfae7 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -158,15 +158,8 @@
 	struct drm_device *drm_dev = data;
 	int ret;
 
-	dp->dev = dev;
 	dp->drm_dev = drm_dev;
 
-	dp->plat_data.dev_type = EXYNOS_DP;
-	dp->plat_data.power_on_start = exynos_dp_poweron;
-	dp->plat_data.power_off = exynos_dp_poweroff;
-	dp->plat_data.attach = exynos_dp_bridge_attach;
-	dp->plat_data.get_modes = exynos_dp_get_modes;
-
 	if (!dp->plat_data.panel && !dp->ptn_bridge) {
 		ret = exynos_dp_dt_parse_panel(dp);
 		if (ret)
@@ -184,13 +177,11 @@
 
 	dp->plat_data.encoder = encoder;
 
-	dp->adp = analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data);
-	if (IS_ERR(dp->adp)) {
+	ret = analogix_dp_bind(dp->adp, dp->drm_dev);
+	if (ret)
 		dp->encoder.funcs->destroy(&dp->encoder);
-		return PTR_ERR(dp->adp);
-	}
 
-	return 0;
+	return ret;
 }
 
 static void exynos_dp_unbind(struct device *dev, struct device *master,
@@ -221,6 +212,7 @@
 	if (!dp)
 		return -ENOMEM;
 
+	dp->dev = dev;
 	/*
 	 * We just use the drvdata until driver run into component
 	 * add function, and then we would set drvdata to null, so
@@ -246,16 +238,29 @@
 
 	/* The remote port can be either a panel or a bridge */
 	dp->plat_data.panel = panel;
+	dp->plat_data.dev_type = EXYNOS_DP;
+	dp->plat_data.power_on_start = exynos_dp_poweron;
+	dp->plat_data.power_off = exynos_dp_poweroff;
+	dp->plat_data.attach = exynos_dp_bridge_attach;
+	dp->plat_data.get_modes = exynos_dp_get_modes;
 	dp->plat_data.skip_connector = !!bridge;
+
 	dp->ptn_bridge = bridge;
 
 out:
+	dp->adp = analogix_dp_probe(dev, &dp->plat_data);
+	if (IS_ERR(dp->adp))
+		return PTR_ERR(dp->adp);
+
 	return component_add(&pdev->dev, &exynos_dp_ops);
 }
 
 static int exynos_dp_remove(struct platform_device *pdev)
 {
+	struct exynos_dp_device *dp = platform_get_drvdata(pdev);
+
 	component_del(&pdev->dev, &exynos_dp_ops);
+	analogix_dp_remove(dp->adp);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 9ebc027..a3c9d8b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -58,10 +58,10 @@
  * mapping.
  */
 static int drm_iommu_attach_device(struct drm_device *drm_dev,
-				struct device *subdrv_dev)
+				struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
-	int ret;
+	int ret = 0;
 
 	if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) {
 		DRM_DEV_ERROR(subdrv_dev, "Device %s lacks support for IOMMU\n",
@@ -74,7 +74,14 @@
 		return ret;
 
 	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) {
-		if (to_dma_iommu_mapping(subdrv_dev))
+		/*
+		 * Keep the original DMA mapping of the sub-device and
+		 * restore it on Exynos DRM detach, otherwise the DMA
+		 * framework considers it as IOMMU-less during the next
+		 * probe (in case of deferred probe or modular build)
+		 */
+		*dma_priv = to_dma_iommu_mapping(subdrv_dev);
+		if (*dma_priv)
 			arm_iommu_detach_device(subdrv_dev);
 
 		ret = arm_iommu_attach_device(subdrv_dev, priv->mapping);
@@ -85,7 +92,7 @@
 	if (ret)
 		clear_dma_max_seg_size(subdrv_dev);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -98,19 +105,21 @@
  * mapping
  */
 static void drm_iommu_detach_device(struct drm_device *drm_dev,
-				struct device *subdrv_dev)
+				    struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 
-	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
+	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) {
 		arm_iommu_detach_device(subdrv_dev);
-	else if (IS_ENABLED(CONFIG_IOMMU_DMA))
+		arm_iommu_attach_device(subdrv_dev, *dma_priv);
+	} else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 		iommu_detach_device(priv->mapping, subdrv_dev);
 
 	clear_dma_max_seg_size(subdrv_dev);
 }
 
-int exynos_drm_register_dma(struct drm_device *drm, struct device *dev)
+int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
+			    void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm->dev_private;
 
@@ -131,19 +140,22 @@
 				EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE);
 		else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 			mapping = iommu_get_domain_for_dev(priv->dma_dev);
+		else
+			mapping = ERR_PTR(-ENODEV);
 
 		if (IS_ERR(mapping))
 			return PTR_ERR(mapping);
 		priv->mapping = mapping;
 	}
 
-	return drm_iommu_attach_device(drm, dev);
+	return drm_iommu_attach_device(drm, dev, dma_priv);
 }
 
-void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev)
+void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev,
+			       void **dma_priv)
 {
 	if (IS_ENABLED(CONFIG_EXYNOS_IOMMU))
-		drm_iommu_detach_device(drm, dev);
+		drm_iommu_detach_device(drm, dev, dma_priv);
 }
 
 void exynos_drm_cleanup_dma(struct drm_device *drm)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index d4014ba..735f436 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -223,8 +223,10 @@
 	return priv->mapping ? true : false;
 }
 
-int exynos_drm_register_dma(struct drm_device *drm, struct device *dev);
-void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev);
+int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
+			    void **dma_priv);
+void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev,
+			       void **dma_priv);
 void exynos_drm_cleanup_dma(struct drm_device *drm);
 
 #ifdef CONFIG_DRM_EXYNOS_DPI
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 6926cee..b83acd6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1741,17 +1741,14 @@
 	dsi->dev = dev;
 	dsi->driver_data = of_device_get_match_data(dev);
 
-	ret = exynos_dsi_parse_dt(dsi);
-	if (ret)
-		return ret;
-
 	dsi->supplies[0].supply = "vddcore";
 	dsi->supplies[1].supply = "vddio";
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies),
 				      dsi->supplies);
 	if (ret) {
-		dev_info(dev, "failed to get regulators: %d\n", ret);
-		return -EPROBE_DEFER;
+		if (ret != -EPROBE_DEFER)
+			dev_info(dev, "failed to get regulators: %d\n", ret);
+		return ret;
 	}
 
 	dsi->clks = devm_kcalloc(dev,
@@ -1764,9 +1761,10 @@
 		dsi->clks[i] = devm_clk_get(dev, clk_names[i]);
 		if (IS_ERR(dsi->clks[i])) {
 			if (strcmp(clk_names[i], "sclk_mipi") == 0) {
-				strcpy(clk_names[i], OLD_SCLK_MIPI_CLK_NAME);
-				i--;
-				continue;
+				dsi->clks[i] = devm_clk_get(dev,
+							OLD_SCLK_MIPI_CLK_NAME);
+				if (!IS_ERR(dsi->clks[i]))
+					continue;
 			}
 
 			dev_info(dev, "failed to get the clock: %s\n",
@@ -1803,11 +1801,25 @@
 		return ret;
 	}
 
+	ret = exynos_dsi_parse_dt(dsi);
+	if (ret)
+		return ret;
+
 	platform_set_drvdata(pdev, &dsi->encoder);
 
 	pm_runtime_enable(dev);
 
-	return component_add(dev, &exynos_dsi_component_ops);
+	ret = component_add(dev, &exynos_dsi_component_ops);
+	if (ret)
+		goto err_disable_runtime;
+
+	return 0;
+
+err_disable_runtime:
+	pm_runtime_disable(dev);
+	of_node_put(dsi->in_bridge_node);
+
+	return ret;
 }
 
 static int exynos_dsi_remove(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 8ea2e1d..29ab8be 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -97,6 +97,7 @@
 struct fimc_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	struct exynos_drm_ipp_task	*task;
 	struct exynos_drm_ipp_formats	*formats;
@@ -1133,7 +1134,7 @@
 
 	ctx->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -1153,7 +1154,7 @@
 	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(drm_dev, dev);
+	exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static const struct component_ops fimc_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 8d0a929..34e6b22 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -167,6 +167,7 @@
 struct fimd_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -1090,7 +1091,7 @@
 	if (is_drm_iommu_supported(drm_dev))
 		fimd_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, dev);
+	return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static void fimd_unbind(struct device *dev, struct device *master,
@@ -1100,7 +1101,7 @@
 
 	fimd_disable(ctx->crtc);
 
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 
 	if (ctx->encoder)
 		exynos_dpi_remove(ctx->encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 2a3382d..fcee33a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -232,6 +232,7 @@
 
 struct g2d_data {
 	struct device			*dev;
+	void				*dma_priv;
 	struct clk			*gate_clk;
 	void __iomem			*regs;
 	int				irq;
@@ -1409,7 +1410,7 @@
 		return ret;
 	}
 
-	ret = exynos_drm_register_dma(drm_dev, dev);
+	ret = exynos_drm_register_dma(drm_dev, dev, &g2d->dma_priv);
 	if (ret < 0) {
 		dev_err(dev, "failed to enable iommu.\n");
 		g2d_fini_cmdlist(g2d);
@@ -1434,7 +1435,7 @@
 	priv->g2d_dev = NULL;
 
 	cancel_work_sync(&g2d->runqueue_work);
-	exynos_drm_unregister_dma(g2d->drm_dev, dev);
+	exynos_drm_unregister_dma(g2d->drm_dev, dev, &g2d->dma_priv);
 }
 
 static const struct component_ops g2d_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 7ae087b..45e9aee 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -97,6 +97,7 @@
 struct gsc_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	struct exynos_drm_ipp_task	*task;
 	struct exynos_drm_ipp_formats	*formats;
@@ -1169,7 +1170,7 @@
 
 	ctx->drm_dev = drm_dev;
 	ctx->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -1189,7 +1190,7 @@
 	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(drm_dev, dev);
+	exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static const struct component_ops gsc_component_ops = {
@@ -1313,6 +1314,7 @@
 {
 	struct device *dev = &pdev->dev;
 
+	component_del(dev, &gsc_component_ops);
 	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index b78e8c5..2aff986 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -268,8 +268,10 @@
 		goto unlock;
 
 	ret = pm_runtime_get_sync(mic->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mic->dev);
 		goto unlock;
+	}
 
 	mic_set_path(mic, 1);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index b984829..dafa87b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -56,6 +56,7 @@
 struct rot_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	void __iomem	*regs;
 	struct clk	*clock;
@@ -243,7 +244,7 @@
 
 	rot->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &rot->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			   DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE,
@@ -261,7 +262,7 @@
 	struct exynos_drm_ipp *ipp = &rot->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(rot->drm_dev, rot->dev);
+	exynos_drm_unregister_dma(rot->drm_dev, rot->dev, &rot->dma_priv);
 }
 
 static const struct component_ops rotator_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
index 497973e..93c43c8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -39,6 +39,7 @@
 struct scaler_context {
 	struct exynos_drm_ipp		ipp;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct device			*dev;
 	void __iomem			*regs;
 	struct clk			*clock[SCALER_MAX_CLK];
@@ -450,7 +451,7 @@
 
 	scaler->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &scaler->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -470,7 +471,8 @@
 	struct exynos_drm_ipp *ipp = &scaler->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev);
+	exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev,
+				  &scaler->dma_priv);
 }
 
 static const struct component_ops scaler_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index bc1565f..0073a2b 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -852,6 +852,10 @@
 
 static void hdmi_connector_destroy(struct drm_connector *connector)
 {
+	struct hdmi_context *hdata = connector_to_hdmi(connector);
+
+	cec_notifier_conn_unregister(hdata->notifier);
+
 	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
 }
@@ -935,6 +939,7 @@
 {
 	struct hdmi_context *hdata = encoder_to_hdmi(encoder);
 	struct drm_connector *connector = &hdata->connector;
+	struct cec_connector_info conn_info;
 	int ret;
 
 	connector->interlace_allowed = true;
@@ -957,6 +962,15 @@
 			DRM_DEV_ERROR(hdata->dev, "Failed to attach bridge\n");
 	}
 
+	cec_fill_conn_info_from_drm(&conn_info, connector);
+
+	hdata->notifier = cec_notifier_conn_register(hdata->dev, NULL,
+						     &conn_info);
+	if (!hdata->notifier) {
+		ret = -ENOMEM;
+		DRM_DEV_ERROR(hdata->dev, "Failed to allocate CEC notifier\n");
+	}
+
 	return ret;
 }
 
@@ -1528,8 +1542,8 @@
 		 */
 		mutex_unlock(&hdata->mutex);
 		cancel_delayed_work(&hdata->hotplug_work);
-		cec_notifier_set_phys_addr(hdata->notifier,
-					   CEC_PHYS_ADDR_INVALID);
+		if (hdata->notifier)
+			cec_notifier_phys_addr_invalidate(hdata->notifier);
 		return;
 	}
 
@@ -1788,18 +1802,10 @@
 
 	hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en");
 
-	if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) {
+	if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV)
 		if (IS_ERR(hdata->reg_hdmi_en))
 			return PTR_ERR(hdata->reg_hdmi_en);
 
-		ret = regulator_enable(hdata->reg_hdmi_en);
-		if (ret) {
-			DRM_DEV_ERROR(dev,
-				      "failed to enable hdmi-en regulator\n");
-			return ret;
-		}
-	}
-
 	return hdmi_bridge_init(hdata);
 }
 
@@ -2006,10 +2012,13 @@
 		}
 	}
 
-	hdata->notifier = cec_notifier_get(&pdev->dev);
-	if (hdata->notifier == NULL) {
-		ret = -ENOMEM;
-		goto err_hdmiphy;
+	if (!IS_ERR(hdata->reg_hdmi_en)) {
+		ret = regulator_enable(hdata->reg_hdmi_en);
+		if (ret) {
+			DRM_DEV_ERROR(dev,
+			      "failed to enable hdmi-en regulator\n");
+			goto err_hdmiphy;
+		}
 	}
 
 	pm_runtime_enable(dev);
@@ -2023,7 +2032,7 @@
 
 	ret = hdmi_register_audio_device(hdata);
 	if (ret)
-		goto err_notifier_put;
+		goto err_rpm_disable;
 
 	ret = component_add(&pdev->dev, &hdmi_component_ops);
 	if (ret)
@@ -2034,10 +2043,10 @@
 err_unregister_audio:
 	platform_device_unregister(hdata->audio.pdev);
 
-err_notifier_put:
-	cec_notifier_put(hdata->notifier);
+err_rpm_disable:
 	pm_runtime_disable(dev);
-
+	if (!IS_ERR(hdata->reg_hdmi_en))
+		regulator_disable(hdata->reg_hdmi_en);
 err_hdmiphy:
 	if (hdata->hdmiphy_port)
 		put_device(&hdata->hdmiphy_port->dev);
@@ -2054,12 +2063,10 @@
 	struct hdmi_context *hdata = platform_get_drvdata(pdev);
 
 	cancel_delayed_work_sync(&hdata->hotplug_work);
-	cec_notifier_set_phys_addr(hdata->notifier, CEC_PHYS_ADDR_INVALID);
 
 	component_del(&pdev->dev, &hdmi_component_ops);
 	platform_device_unregister(hdata->audio.pdev);
 
-	cec_notifier_put(hdata->notifier);
 	pm_runtime_disable(&pdev->dev);
 
 	if (!IS_ERR(hdata->reg_hdmi_en))
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 7b24338..22f4941 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -94,6 +94,7 @@
 	struct platform_device *pdev;
 	struct device		*dev;
 	struct drm_device	*drm_dev;
+	void			*dma_priv;
 	struct exynos_drm_crtc	*crtc;
 	struct exynos_drm_plane	planes[MIXER_WIN_NR];
 	unsigned long		flags;
@@ -894,12 +895,14 @@
 		}
 	}
 
-	return exynos_drm_register_dma(drm_dev, mixer_ctx->dev);
+	return exynos_drm_register_dma(drm_dev, mixer_ctx->dev,
+				       &mixer_ctx->dma_priv);
 }
 
 static void mixer_ctx_remove(struct mixer_context *mixer_ctx)
 {
-	exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev);
+	exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev,
+				  &mixer_ctx->dma_priv);
 }
 
 static int mixer_enable_vblank(struct exynos_drm_crtc *crtc)
diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c
index f56852a..8b78494 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_display.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_display.c
@@ -405,6 +405,8 @@
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct gma_clock_t clock;
 
+	memset(&clock, 0, sizeof(clock));
+
 	switch (refclk) {
 	case 27000:
 		if (target < 200000) {
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 570b595..8773865 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -2120,12 +2120,12 @@
 					       intel_dp->dpcd,
 					       sizeof(intel_dp->dpcd));
 		cdv_intel_edp_panel_vdd_off(gma_encoder);
-		if (ret == 0) {
+		if (ret <= 0) {
 			/* if this fails, presume the device is a ghost */
 			DRM_INFO("failed to retrieve link info, disabling eDP\n");
 			cdv_intel_dp_encoder_destroy(encoder);
 			cdv_intel_dp_destroy(connector);
-			goto err_priv;
+			goto err_connector;
 		} else {
         		DRM_DEBUG_KMS("DPCD: Rev=%x LN_Rate=%x LN_CNT=%x LN_DOWNSP=%x\n",
 				intel_dp->dpcd[0], intel_dp->dpcd[1], 
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 218f3bb..90237ab 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -462,6 +462,7 @@
 		container_of(helper, struct psb_fbdev, psb_fb_helper);
 	struct drm_device *dev = psb_fbdev->psb_fb_helper.dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	unsigned int fb_size;
 	int bytespp;
 
 	bytespp = sizes->surface_bpp / 8;
@@ -471,8 +472,11 @@
 	/* If the mode will not fit in 32bit then switch to 16bit to get
 	   a console on full resolution. The X mode setting server will
 	   allocate its own 32bit GEM framebuffer */
-	if (ALIGN(sizes->fb_width * bytespp, 64) * sizes->fb_height >
-	                dev_priv->vram_stolen_size) {
+	fb_size = ALIGN(sizes->surface_width * bytespp, 64) *
+		  sizes->surface_height;
+	fb_size = ALIGN(fb_size, PAGE_SIZE);
+
+	if (fb_size > dev_priv->vram_stolen_size) {
                 sizes->surface_bpp = 16;
                 sizes->surface_depth = 16;
         }
diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c
index 167c107..900e549 100644
--- a/drivers/gpu/drm/gma500/oaktrail_crtc.c
+++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c
@@ -129,6 +129,7 @@
 	s32 freq_error, min_error = 100000;
 
 	memset(best_clock, 0, sizeof(*best_clock));
+	memset(&clock, 0, sizeof(clock));
 
 	for (clock.m = limit->m.min; clock.m <= limit->m.max; clock.m++) {
 		for (clock.n = limit->n.min; clock.n <= limit->n.max;
@@ -185,6 +186,7 @@
 	int err = target;
 
 	memset(best_clock, 0, sizeof(*best_clock));
+	memset(&clock, 0, sizeof(clock));
 
 	for (clock.m = limit->m.min; clock.m <= limit->m.max; clock.m++) {
 		for (clock.p1 = limit->p1.min; clock.p1 <= limit->p1.max;
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
index e281070..fc9a34e 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi_i2c.c
@@ -279,11 +279,8 @@
 	hdmi_dev = pci_get_drvdata(dev);
 
 	i2c_dev = kzalloc(sizeof(struct hdmi_i2c_dev), GFP_KERNEL);
-	if (i2c_dev == NULL) {
-		DRM_ERROR("Can't allocate interface\n");
-		ret = -ENOMEM;
-		goto exit;
-	}
+	if (!i2c_dev)
+		return -ENOMEM;
 
 	i2c_dev->adap = &oaktrail_hdmi_i2c_adapter;
 	i2c_dev->status = I2C_STAT_INIT;
@@ -300,16 +297,23 @@
 			  oaktrail_hdmi_i2c_adapter.name, hdmi_dev);
 	if (ret) {
 		DRM_ERROR("Failed to request IRQ for I2C controller\n");
-		goto err;
+		goto free_dev;
 	}
 
 	/* Adapter registration */
 	ret = i2c_add_numbered_adapter(&oaktrail_hdmi_i2c_adapter);
-	return ret;
+	if (ret) {
+		DRM_ERROR("Failed to add I2C adapter\n");
+		goto free_irq;
+	}
 
-err:
+	return 0;
+
+free_irq:
+	free_irq(dev->irq, hdmi_dev);
+free_dev:
 	kfree(i2c_dev);
-exit:
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 7005f8f..d414525 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -313,6 +313,8 @@
 	if (ret)
 		goto out_err;
 
+	ret = -ENOMEM;
+
 	dev_priv->mmu = psb_mmu_driver_init(dev, 1, 0, 0);
 	if (!dev_priv->mmu)
 		goto out_err;
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index e6265fb..56bb34d 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -337,6 +337,7 @@
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
+	unsigned int i;
 
 	spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
 
@@ -349,20 +350,12 @@
 	PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R);
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank[0].enabled)
-		psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[1].enabled)
-		psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[2].enabled)
-		psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+	for (i = 0; i < dev->num_crtcs; ++i) {
+		if (dev->vblank[i].enabled)
+			psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+		else
+			psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+	}
 
 	if (dev_priv->ops->hotplug_enable)
 		dev_priv->ops->hotplug_enable(dev, true);
@@ -375,6 +368,7 @@
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
+	unsigned int i;
 
 	spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
 
@@ -383,14 +377,10 @@
 
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank[0].enabled)
-		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[1].enabled)
-		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[2].enabled)
-		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+	for (i = 0; i < dev->num_crtcs; ++i) {
+		if (dev->vblank[i].enabled)
+			psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+	}
 
 	dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG |
 				  _PSB_IRQ_MSVDX_FLAG |
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index c103005..a34ef5e 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -376,7 +376,6 @@
 
 	drm_dev_unregister(dev);
 	hibmc_unload(dev);
-	drm_dev_put(dev);
 }
 
 static struct pci_device_id hibmc_pci_table[] = {
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h b/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h
index 0da8602..e2ac098 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h
@@ -83,7 +83,6 @@
 #define VSIZE_OFST			20
 #define LDI_INT_EN			0x741C
 #define FRAME_END_INT_EN_OFST		1
-#define UNDERFLOW_INT_EN_OFST		2
 #define LDI_CTRL			0x7420
 #define BPP_OFST			3
 #define DATA_GATE_EN			BIT(2)
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
index 73cd28a..8600012 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
@@ -46,7 +46,6 @@
 	struct clk *media_noc_clk;
 	struct clk *ade_pix_clk;
 	struct reset_control *reset;
-	struct work_struct display_reset_wq;
 	bool power_on;
 	int irq;
 
@@ -136,7 +135,6 @@
 	 */
 	ade_update_bits(base + ADE_CTRL, FRM_END_START_OFST,
 			FRM_END_START_MASK, REG_EFFECTIVE_IN_ADEEN_FRMEND);
-	ade_update_bits(base + LDI_INT_EN, UNDERFLOW_INT_EN_OFST, MASK(1), 1);
 }
 
 static bool ade_crtc_mode_fixup(struct drm_crtc *crtc,
@@ -304,17 +302,6 @@
 			MASK(1), 0);
 }
 
-static void drm_underflow_wq(struct work_struct *work)
-{
-	struct ade_hw_ctx *ctx = container_of(work, struct ade_hw_ctx,
-					      display_reset_wq);
-	struct drm_device *drm_dev = ctx->crtc->dev;
-	struct drm_atomic_state *state;
-
-	state = drm_atomic_helper_suspend(drm_dev);
-	drm_atomic_helper_resume(drm_dev, state);
-}
-
 static irqreturn_t ade_irq_handler(int irq, void *data)
 {
 	struct ade_hw_ctx *ctx = data;
@@ -331,12 +318,6 @@
 				MASK(1), 1);
 		drm_crtc_handle_vblank(crtc);
 	}
-	if (status & BIT(UNDERFLOW_INT_EN_OFST)) {
-		ade_update_bits(base + LDI_INT_CLR, UNDERFLOW_INT_EN_OFST,
-				MASK(1), 1);
-		DRM_ERROR("LDI underflow!");
-		schedule_work(&ctx->display_reset_wq);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -919,7 +900,6 @@
 	if (ret)
 		return ERR_PTR(-EIO);
 
-	INIT_WORK(&ctx->display_reset_wq, drm_underflow_wq);
 	ctx->crtc = crtc;
 
 	return ctx;
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index 2a77823..e66c383 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -728,7 +728,7 @@
 	if (nbox > I810_NR_SAREA_CLIPRECTS)
 		nbox = I810_NR_SAREA_CLIPRECTS;
 
-	if (used > 4 * 1024)
+	if (used < 0 || used > 4 * 1024)
 		used = 0;
 
 	if (sarea_priv->dirty)
@@ -1048,7 +1048,7 @@
 	if (u != I810_BUF_CLIENT)
 		DRM_DEBUG("MC found buffer that isn't mine!\n");
 
-	if (used > 4 * 1024)
+	if (used < 0 || used > 4 * 1024)
 		used = 0;
 
 	sarea_priv->dirty = 0x7f;
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 0d21402..3317798 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -75,9 +75,8 @@
 	help
 	  This option enables capturing the GPU state when a hang is detected.
 	  This information is vital for triaging hangs and assists in debugging.
-	  Please report any hang to
-            https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
-	  for triaging.
+	  Please report any hang for triaging according to:
+	    https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 
 	  If in doubt, say "Y".
 
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 00786a1..41c8e39 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -7,7 +7,6 @@
         # We use the dependency on !COMPILE_TEST to not be enabled in
         # allmodconfig or allyesconfig configurations
         depends on !COMPILE_TEST
-	select HEADER_TEST
         default n
         help
           Add -Werror to the build flags for (and only for) i915.ko.
diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c
index 3456d33..ce8182b 100644
--- a/drivers/gpu/drm/i915/display/intel_acpi.c
+++ b/drivers/gpu/drm/i915/display/intel_acpi.c
@@ -83,13 +83,31 @@
 		return;
 	}
 
+	if (!pkg->package.count) {
+		DRM_DEBUG_DRIVER("no connection in _DSM\n");
+		return;
+	}
+
 	connector_count = &pkg->package.elements[0];
 	DRM_DEBUG_DRIVER("MUX info connectors: %lld\n",
 		  (unsigned long long)connector_count->integer.value);
 	for (i = 1; i < pkg->package.count; i++) {
 		union acpi_object *obj = &pkg->package.elements[i];
-		union acpi_object *connector_id = &obj->package.elements[0];
-		union acpi_object *info = &obj->package.elements[1];
+		union acpi_object *connector_id;
+		union acpi_object *info;
+
+		if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < 2) {
+			DRM_DEBUG_DRIVER("Invalid object for MUX #%d\n", i);
+			continue;
+		}
+
+		connector_id = &obj->package.elements[0];
+		info = &obj->package.elements[1];
+		if (info->type != ACPI_TYPE_BUFFER || info->buffer.length < 4) {
+			DRM_DEBUG_DRIVER("Invalid info for MUX obj #%d\n", i);
+			continue;
+		}
+
 		DRM_DEBUG_DRIVER("Connector id: 0x%016llx\n",
 			  (unsigned long long)connector_id->integer.value);
 		DRM_DEBUG_DRIVER("  port id: %s\n",
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 8eb2b3e..b3c77c9 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2124,7 +2124,11 @@
 		return;
 
 	dig_port = enc_to_dig_port(&encoder->base);
-	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
+
+	if (!intel_phy_is_tc(dev_priv, phy) ||
+	    dig_port->tc_mode != TC_PORT_TBT_ALT)
+		intel_display_power_get(dev_priv,
+					dig_port->ddi_io_power_domain);
 
 	/*
 	 * AUX power is only needed for (e)DP mode, and for HDMI mode on TC
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index af50f05..4e1c228 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -10510,7 +10510,7 @@
 	u32 base;
 
 	if (INTEL_INFO(dev_priv)->display.cursor_needs_physical)
-		base = obj->phys_handle->busaddr;
+		base = sg_dma_address(obj->mm.pages->sgl);
 	else
 		base = intel_plane_ggtt_offset(plane_state);
 
@@ -11893,10 +11893,11 @@
 	case 10 ... 11:
 		bpp = 10 * 3;
 		break;
-	case 12:
+	case 12 ... 16:
 		bpp = 12 * 3;
 		break;
 	default:
+		MISSING_CASE(conn_state->max_bpc);
 		return -EINVAL;
 	}
 
@@ -16860,8 +16861,11 @@
 
 static void intel_early_display_was(struct drm_i915_private *dev_priv)
 {
-	/* Display WA #1185 WaDisableDARBFClkGating:cnl,glk */
-	if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+	/*
+	 * Display WA #1185 WaDisableDARBFClkGating:cnl,glk,icl,ehl,tgl
+	 * Also known as Wa_14010480278.
+	 */
+	if (IS_GEN_RANGE(dev_priv, 10, 12) || IS_GEMINILAKE(dev_priv))
 		I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 			   DARBF_GATING_DIS);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index c002f23..2422af6 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -4205,13 +4205,19 @@
 
 static void icl_mbus_init(struct drm_i915_private *dev_priv)
 {
-	u32 val;
+	u32 mask, val;
 
-	val = MBUS_ABOX_BT_CREDIT_POOL1(16) |
-	      MBUS_ABOX_BT_CREDIT_POOL2(16) |
-	      MBUS_ABOX_B_CREDIT(1) |
-	      MBUS_ABOX_BW_CREDIT(1);
+	mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK |
+		MBUS_ABOX_BT_CREDIT_POOL2_MASK |
+		MBUS_ABOX_B_CREDIT_MASK |
+		MBUS_ABOX_BW_CREDIT_MASK;
 
+	val = I915_READ(MBUS_ABOX_CTL);
+	val &= ~mask;
+	val |= MBUS_ABOX_BT_CREDIT_POOL1(16) |
+		MBUS_ABOX_BT_CREDIT_POOL2(16) |
+		MBUS_ABOX_B_CREDIT(1) |
+		MBUS_ABOX_BW_CREDIT(1);
 	I915_WRITE(MBUS_ABOX_CTL, val);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 9b15ac4..abc8c42 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -567,7 +567,7 @@
 		return 0;
 	}
 	/* Also take into account max slice width */
-	min_slice_count = min_t(u8, min_slice_count,
+	min_slice_count = max_t(u8, min_slice_count,
 				DIV_ROUND_UP(mode_hdisplay,
 					     max_slice_width));
 
@@ -1292,8 +1292,7 @@
 	bool is_tc_port = intel_phy_is_tc(i915, phy);
 	i915_reg_t ch_ctl, ch_data[5];
 	u32 aux_clock_divider;
-	enum intel_display_power_domain aux_domain =
-		intel_aux_power_domain(intel_dig_port);
+	enum intel_display_power_domain aux_domain;
 	intel_wakeref_t aux_wakeref;
 	intel_wakeref_t pps_wakeref;
 	int i, ret, recv_bytes;
@@ -1308,6 +1307,8 @@
 	if (is_tc_port)
 		intel_tc_port_lock(intel_dig_port);
 
+	aux_domain = intel_aux_power_domain(intel_dig_port);
+
 	aux_wakeref = intel_display_power_get(i915, aux_domain);
 	pps_wakeref = pps_lock(intel_dp);
 
@@ -3633,7 +3634,7 @@
  * link status information
  */
 bool
-intel_dp_get_link_status(struct intel_dp *intel_dp, u8 link_status[DP_LINK_STATUS_SIZE])
+intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status)
 {
 	return drm_dp_dpcd_read(&intel_dp->aux, DP_LANE0_1_STATUS, link_status,
 				DP_LINK_STATUS_SIZE) == DP_LINK_STATUS_SIZE;
@@ -4705,7 +4706,18 @@
 	bool bret;
 
 	if (intel_dp->is_mst) {
-		u8 esi[DP_DPRX_ESI_LEN] = { 0 };
+		/*
+		 * The +2 is because DP_DPRX_ESI_LEN is 14, but we then
+		 * pass in "esi+10" to drm_dp_channel_eq_ok(), which
+		 * takes a 6-byte array. So we actually need 16 bytes
+		 * here.
+		 *
+		 * Somebody who knows what the limits actually are
+		 * should check this, but for now this is at least
+		 * harmless and avoids a valid compiler warning about
+		 * using more of the array than we have allocated.
+		 */
+		u8 esi[DP_DPRX_ESI_LEN+2] = {};
 		int ret = 0;
 		int retry;
 		bool handled;
@@ -7218,11 +7230,8 @@
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
 
 	/* init MST on ports that can support it */
-	if (HAS_DP_MST(dev_priv) && !intel_dp_is_edp(intel_dp) &&
-	    (port == PORT_B || port == PORT_C ||
-	     port == PORT_D || port == PORT_F))
-		intel_dp_mst_encoder_init(intel_dig_port,
-					  intel_connector->base.base.id);
+	intel_dp_mst_encoder_init(intel_dig_port,
+				  intel_connector->base.base.id);
 
 	if (!intel_edp_init_connector(intel_dp, intel_connector)) {
 		intel_dp_aux_fini(intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 600873c..74d45a0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -653,21 +653,31 @@
 int
 intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_base_id)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct drm_device *dev = intel_dig_port->base.base.dev;
+	enum port port = intel_dig_port->base.port;
 	int ret;
 
-	intel_dp->can_mst = true;
+	if (!HAS_DP_MST(i915) || intel_dp_is_edp(intel_dp))
+		return 0;
+
+	if (INTEL_GEN(i915) < 12 && port == PORT_A)
+		return 0;
+
+	if (INTEL_GEN(i915) < 11 && port == PORT_E)
+		return 0;
+
 	intel_dp->mst_mgr.cbs = &mst_cbs;
 
 	/* create encoders */
 	intel_dp_create_fake_mst_encoders(intel_dig_port);
-	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, dev,
+	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, &i915->drm,
 					   &intel_dp->aux, 16, 3, conn_base_id);
-	if (ret) {
-		intel_dp->can_mst = false;
+	if (ret)
 		return ret;
-	}
+
+	intel_dp->can_mst = true;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 16ed44b..caf6166 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -504,8 +504,7 @@
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
-		DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
-
+		DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
 	fbc->threshold = ret;
@@ -1284,7 +1283,7 @@
 		return 0;
 
 	/* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
-	if (IS_GEMINILAKE(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		return 0;
 
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index b030f7a..4cf95e8 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2129,7 +2129,11 @@
 	if (clock > hdmi_port_clock_limit(hdmi, respect_downstream_limits, force_dvi))
 		return MODE_CLOCK_HIGH;
 
-	/* BXT DPLL can't generate 223-240 MHz */
+	/* GLK DPLL can't generate 446-480 MHz */
+	if (IS_GEMINILAKE(dev_priv) && clock > 446666 && clock < 480000)
+		return MODE_CLOCK_RANGE;
+
+	/* BXT/GLK DPLL can't generate 223-240 MHz */
 	if (IS_GEN9_LP(dev_priv) && clock > 223333 && clock < 240000)
 		return MODE_CLOCK_RANGE;
 
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index bc14e9c..23edc1b 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -1603,20 +1603,21 @@
 		val = pch_get_backlight(connector);
 	else
 		val = lpt_get_backlight(connector);
-	val = intel_panel_compute_brightness(connector, val);
-	panel->backlight.level = clamp(val, panel->backlight.min,
-				       panel->backlight.max);
 
 	if (cpu_mode) {
 		DRM_DEBUG_KMS("CPU backlight register was enabled, switching to PCH override\n");
 
 		/* Write converted CPU PWM value to PCH override register */
-		lpt_set_backlight(connector->base.state, panel->backlight.level);
+		lpt_set_backlight(connector->base.state, val);
 		I915_WRITE(BLC_PWM_PCH_CTL1, pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
 
 		I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2 & ~BLM_PWM_ENABLE);
 	}
 
+	val = intel_panel_compute_brightness(connector, val);
+	panel->backlight.level = clamp(val, panel->backlight.min,
+				       panel->backlight.max);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index a71b22b..7f329d8 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -797,10 +797,20 @@
 	if (intel_dsi->gpio_panel)
 		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
 
-	/* Deassert reset */
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+	/*
+	 * Give the panel time to power-on and then deassert its reset.
+	 * Depending on the VBT MIPI sequences version the deassert-seq
+	 * may contain the necessary delay, intel_dsi_msleep() will skip
+	 * the delay in that case. If there is no deassert-seq, then an
+	 * unconditional msleep is used to give the panel time to power-on.
+	 */
+	if (dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) {
+		intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+	} else {
+		msleep(intel_dsi->panel_on_delay);
+	}
 
 	if (IS_GEMINILAKE(dev_priv)) {
 		glk_cold_boot = glk_dsi_enable_io(encoder);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
index 3d4f577..25235ef 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
@@ -9,16 +9,16 @@
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
 
-static __always_inline u32 __busy_read_flag(u8 id)
+static __always_inline u32 __busy_read_flag(u16 id)
 {
-	if (id == (u8)I915_ENGINE_CLASS_INVALID)
+	if (id == (u16)I915_ENGINE_CLASS_INVALID)
 		return 0xffff0000u;
 
 	GEM_BUG_ON(id >= 16);
 	return 0x10000u << id;
 }
 
-static __always_inline u32 __busy_write_id(u8 id)
+static __always_inline u32 __busy_write_id(u16 id)
 {
 	/*
 	 * The uABI guarantees an active writer is also amongst the read
@@ -29,14 +29,14 @@
 	 * last_read - hence we always set both read and write busy for
 	 * last_write.
 	 */
-	if (id == (u8)I915_ENGINE_CLASS_INVALID)
+	if (id == (u16)I915_ENGINE_CLASS_INVALID)
 		return 0xffffffffu;
 
 	return (id + 1) | __busy_read_flag(id);
 }
 
 static __always_inline unsigned int
-__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id))
+__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
 {
 	const struct i915_request *rq;
 
@@ -57,7 +57,7 @@
 		return 0;
 
 	/* Beware type-expansion follies! */
-	BUILD_BUG_ON(!typecheck(u8, rq->engine->uabi_class));
+	BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
 	return flag(rq->engine->uabi_class);
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index e41fd94..b3d2b91 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -2094,8 +2094,7 @@
 	ext_data.fpriv = file->driver_priv;
 	if (client_is_banned(ext_data.fpriv)) {
 		DRM_DEBUG("client %s[%d] banned from creating ctx\n",
-			  current->comm,
-			  pid_nr(get_task_pid(current, PIDTYPE_PID)));
+			  current->comm, task_pid_nr(current));
 		return -EIO;
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 9c58e8f..a4b48c9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -606,21 +606,6 @@
 		return -ENOENT;
 
 	/*
-	 * Already in the desired write domain? Nothing for us to do!
-	 *
-	 * We apply a little bit of cunning here to catch a broader set of
-	 * no-ops. If obj->write_domain is set, we must be in the same
-	 * obj->read_domains, and only that domain. Therefore, if that
-	 * obj->write_domain matches the request read_domains, we are
-	 * already in the same read/write domain and can skip the operation,
-	 * without having to further check the requested write_domain.
-	 */
-	if (READ_ONCE(obj->write_domain) == read_domains) {
-		err = 0;
-		goto out;
-	}
-
-	/*
 	 * Try to flush the object off the GPU without holding the lock.
 	 * We will repeat the flush holding the lock in the normal manner
 	 * to catch cases where we are gazumped.
@@ -657,6 +642,19 @@
 	if (err)
 		goto out;
 
+	/*
+	 * Already in the desired write domain? Nothing for us to do!
+	 *
+	 * We apply a little bit of cunning here to catch a broader set of
+	 * no-ops. If obj->write_domain is set, we must be in the same
+	 * obj->read_domains, and only that domain. Therefore, if that
+	 * obj->write_domain matches the request read_domains, we are
+	 * already in the same read/write domain and can skip the operation,
+	 * without having to further check the requested write_domain.
+	 */
+	if (READ_ONCE(obj->write_domain) == read_domains)
+		goto out_unpin;
+
 	err = i915_gem_object_lock_interruptible(obj);
 	if (err)
 		goto out_unpin;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index e635e1e..198a91c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -367,7 +367,7 @@
 		return true;
 
 	if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) &&
-	    (vma->node.start + vma->node.size - 1) >> 32)
+	    (vma->node.start + vma->node.size + 4095) >> 32)
 		return true;
 
 	if (flags & __EXEC_OBJECT_NEEDS_MAP &&
@@ -439,7 +439,8 @@
 	if (unlikely(entry->flags & eb->invalid_flags))
 		return -EINVAL;
 
-	if (unlikely(entry->alignment && !is_power_of_2(entry->alignment)))
+	if (unlikely(entry->alignment &&
+		     !is_power_of_2_u64(entry->alignment)))
 		return -EINVAL;
 
 	/*
@@ -930,11 +931,13 @@
 
 static void reloc_gpu_flush(struct reloc_cache *cache)
 {
-	GEM_BUG_ON(cache->rq_size >= cache->rq->batch->obj->base.size / sizeof(u32));
+	struct drm_i915_gem_object *obj = cache->rq->batch->obj;
+
+	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
 	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
 
-	__i915_gem_object_flush_map(cache->rq->batch->obj, 0, cache->rq_size);
-	i915_gem_object_unpin_map(cache->rq->batch->obj);
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
 
 	intel_gt_chipset_flush(cache->rq->engine->gt);
 
@@ -1160,6 +1163,8 @@
 		goto out_pool;
 	}
 
+	memset32(cmd, 0, pool->obj->base.size / sizeof(u32));
+
 	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 05289ed..876f590 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -181,7 +181,7 @@
 	struct i915_ggtt_view view;
 
 	if (i915_gem_object_is_tiled(obj))
-		chunk = roundup(chunk, tile_row_pages(obj));
+		chunk = roundup(chunk, tile_row_pages(obj) ?: 1);
 
 	view.type = I915_GGTT_VIEW_PARTIAL;
 	view.partial.offset = rounddown(page_offset, chunk);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 646859f..08b3558 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -240,9 +240,6 @@
 
 		void *gvt_info;
 	};
-
-	/** for phys allocated objects */
-	struct drm_dma_handle *phys_handle;
 };
 
 static inline struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 7683569..0cfe9bd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -21,88 +21,87 @@
 static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 {
 	struct address_space *mapping = obj->base.filp->f_mapping;
-	struct drm_dma_handle *phys;
-	struct sg_table *st;
 	struct scatterlist *sg;
-	char *vaddr;
+	struct sg_table *st;
+	dma_addr_t dma;
+	void *vaddr;
+	void *dst;
 	int i;
-	int err;
 
 	if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj)))
 		return -EINVAL;
 
-	/* Always aligning to the object size, allows a single allocation
+	/*
+	 * Always aligning to the object size, allows a single allocation
 	 * to handle all possible callers, and given typical object sizes,
 	 * the alignment of the buddy allocation will naturally match.
 	 */
-	phys = drm_pci_alloc(obj->base.dev,
-			     roundup_pow_of_two(obj->base.size),
-			     roundup_pow_of_two(obj->base.size));
-	if (!phys)
+	vaddr = dma_alloc_coherent(&obj->base.dev->pdev->dev,
+				   roundup_pow_of_two(obj->base.size),
+				   &dma, GFP_KERNEL);
+	if (!vaddr)
 		return -ENOMEM;
 
-	vaddr = phys->vaddr;
-	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
-		struct page *page;
-		char *src;
-
-		page = shmem_read_mapping_page(mapping, i);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			goto err_phys;
-		}
-
-		src = kmap_atomic(page);
-		memcpy(vaddr, src, PAGE_SIZE);
-		drm_clflush_virt_range(vaddr, PAGE_SIZE);
-		kunmap_atomic(src);
-
-		put_page(page);
-		vaddr += PAGE_SIZE;
-	}
-
-	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
-
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st) {
-		err = -ENOMEM;
-		goto err_phys;
-	}
+	if (!st)
+		goto err_pci;
 
-	if (sg_alloc_table(st, 1, GFP_KERNEL)) {
-		kfree(st);
-		err = -ENOMEM;
-		goto err_phys;
-	}
+	if (sg_alloc_table(st, 1, GFP_KERNEL))
+		goto err_st;
 
 	sg = st->sgl;
 	sg->offset = 0;
 	sg->length = obj->base.size;
 
-	sg_dma_address(sg) = phys->busaddr;
+	sg_assign_page(sg, (struct page *)vaddr);
+	sg_dma_address(sg) = dma;
 	sg_dma_len(sg) = obj->base.size;
 
-	obj->phys_handle = phys;
+	dst = vaddr;
+	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
+		struct page *page;
+		void *src;
+
+		page = shmem_read_mapping_page(mapping, i);
+		if (IS_ERR(page))
+			goto err_st;
+
+		src = kmap_atomic(page);
+		memcpy(dst, src, PAGE_SIZE);
+		drm_clflush_virt_range(dst, PAGE_SIZE);
+		kunmap_atomic(src);
+
+		put_page(page);
+		dst += PAGE_SIZE;
+	}
+
+	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
 
 	__i915_gem_object_set_pages(obj, st, sg->length);
 
 	return 0;
 
-err_phys:
-	drm_pci_free(obj->base.dev, phys);
-
-	return err;
+err_st:
+	kfree(st);
+err_pci:
+	dma_free_coherent(&obj->base.dev->pdev->dev,
+			  roundup_pow_of_two(obj->base.size),
+			  vaddr, dma);
+	return -ENOMEM;
 }
 
 static void
 i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
+	dma_addr_t dma = sg_dma_address(pages->sgl);
+	void *vaddr = sg_page(pages->sgl);
+
 	__i915_gem_object_release_shmem(obj, pages, false);
 
 	if (obj->mm.dirty) {
 		struct address_space *mapping = obj->base.filp->f_mapping;
-		char *vaddr = obj->phys_handle->vaddr;
+		void *src = vaddr;
 		int i;
 
 		for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
@@ -114,15 +113,16 @@
 				continue;
 
 			dst = kmap_atomic(page);
-			drm_clflush_virt_range(vaddr, PAGE_SIZE);
-			memcpy(dst, vaddr, PAGE_SIZE);
+			drm_clflush_virt_range(src, PAGE_SIZE);
+			memcpy(dst, src, PAGE_SIZE);
 			kunmap_atomic(dst);
 
 			set_page_dirty(page);
 			if (obj->mm.madv == I915_MADV_WILLNEED)
 				mark_page_accessed(page);
 			put_page(page);
-			vaddr += PAGE_SIZE;
+
+			src += PAGE_SIZE;
 		}
 		obj->mm.dirty = false;
 	}
@@ -130,7 +130,9 @@
 	sg_free_table(pages);
 	kfree(pages);
 
-	drm_pci_free(obj->base.dev, obj->phys_handle);
+	dma_free_coherent(&obj->base.dev->pdev->dev,
+			  roundup_pow_of_two(obj->base.size),
+			  vaddr, dma);
 }
 
 static void phys_release(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 4c4954e..3f875ae 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -36,7 +36,6 @@
 	unsigned long last_pfn = 0;	/* suppress gcc warning */
 	unsigned int max_segment = i915_sg_segment_size();
 	unsigned int sg_page_sizes;
-	struct pagevec pvec;
 	gfp_t noreclaim;
 	int ret;
 
@@ -188,13 +187,17 @@
 	sg_mark_end(sg);
 err_pages:
 	mapping_clear_unevictable(mapping);
-	pagevec_init(&pvec);
-	for_each_sgt_page(page, sgt_iter, st) {
-		if (!pagevec_add(&pvec, page))
+	if (sg != st->sgl) {
+		struct pagevec pvec;
+
+		pagevec_init(&pvec);
+		for_each_sgt_page(page, sgt_iter, st) {
+			if (!pagevec_add(&pvec, page))
+				check_release_pagevec(&pvec);
+		}
+		if (pagevec_count(&pvec))
 			check_release_pagevec(&pvec);
 	}
-	if (pagevec_count(&pvec))
-		check_release_pagevec(&pvec);
 	sg_free_table(st);
 	kfree(st);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index abfbac4..6d0cc90 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -427,7 +427,7 @@
 
 static struct sg_table *
 __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
-			       struct page **pvec, int num_pages)
+			       struct page **pvec, unsigned long num_pages)
 {
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
@@ -473,9 +473,10 @@
 {
 	struct get_pages_work *work = container_of(_work, typeof(*work), work);
 	struct drm_i915_gem_object *obj = work->obj;
-	const int npages = obj->base.size >> PAGE_SHIFT;
+	const unsigned long npages = obj->base.size >> PAGE_SHIFT;
+	unsigned long pinned;
 	struct page **pvec;
-	int pinned, ret;
+	int ret;
 
 	ret = -ENOMEM;
 	pinned = 0;
@@ -578,7 +579,7 @@
 
 static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 {
-	const int num_pages = obj->base.size >> PAGE_SHIFT;
+	const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
 	struct mm_struct *mm = obj->userptr.mm->mm;
 	struct page **pvec;
 	struct sg_table *pages;
@@ -618,6 +619,14 @@
 				      GFP_KERNEL |
 				      __GFP_NORETRY |
 				      __GFP_NOWARN);
+		/*
+		 * Using __get_user_pages_fast() with a read-only
+		 * access is questionable. A read-only page may be
+		 * COW-broken, and then this might end up giving
+		 * the wrong side of the COW..
+		 *
+		 * We may or may not care.
+		 */
 		if (pvec) /* defer to worker if malloc fails */
 			pinned = __get_user_pages_fast(obj->userptr.ptr,
 						       num_pages,
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 1d27bab..dc9d3a5 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -375,7 +375,7 @@
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		return false;
 
 	err = create_mmap_offset(obj);
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 22aab85..926272b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -250,6 +250,14 @@
 	return pos & (ring->size - 1);
 }
 
+static inline int intel_ring_direction(const struct intel_ring *ring,
+				       u32 next, u32 prev)
+{
+	typecheck(typeof(ring->size), next);
+	typecheck(typeof(ring->size), prev);
+	return (next - prev) << ring->wrap;
+}
+
 static inline bool
 intel_ring_offset_valid(const struct intel_ring *ring,
 			unsigned int pos)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 4ce8626..8073758 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -354,7 +354,8 @@
 		 * instances.
 		 */
 		if ((INTEL_GEN(i915) >= 11 &&
-		     RUNTIME_INFO(i915)->vdbox_sfc_access & engine->mask) ||
+		     (RUNTIME_INFO(i915)->vdbox_sfc_access &
+		      BIT(engine->instance))) ||
 		    (INTEL_GEN(i915) >= 9 && engine->instance == 0))
 			engine->uabi_capabilities |=
 				I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 9dd8c29..c77c951 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -107,6 +107,7 @@
 
 	u32 space;
 	u32 size;
+	u32 wrap;
 	u32 effective_size;
 };
 
@@ -300,8 +301,8 @@
 	u8 class;
 	u8 instance;
 
-	u8 uabi_class;
-	u8 uabi_instance;
+	u16 uabi_class;
+	u16 uabi_instance;
 
 	u32 context_size;
 	u32 mmio_base;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 06a506c..398068b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -471,12 +471,6 @@
 	return desc;
 }
 
-static void unwind_wa_tail(struct i915_request *rq)
-{
-	rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES);
-	assert_ring_tail_valid(rq->ring, rq->tail);
-}
-
 static struct i915_request *
 __unwind_incomplete_requests(struct intel_engine_cs *engine)
 {
@@ -495,7 +489,6 @@
 			continue; /* XXX */
 
 		__i915_request_unsubmit(rq);
-		unwind_wa_tail(rq);
 
 		/*
 		 * Push the request back into the queue for later resubmission.
@@ -525,7 +518,8 @@
 			 */
 			if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 				     &rq->fence.flags)) {
-				spin_lock(&rq->lock);
+				spin_lock_nested(&rq->lock,
+						 SINGLE_DEPTH_NESTING);
 				i915_request_cancel_breadcrumb(rq);
 				spin_unlock(&rq->lock);
 			}
@@ -649,13 +643,35 @@
 	i915_request_put(rq);
 }
 
-static u64 execlists_update_context(const struct i915_request *rq)
+static u64 execlists_update_context(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->hw_context;
-	u64 desc;
+	u64 desc = ce->lrc_desc;
+	u32 tail, prev;
 
-	ce->lrc_reg_state[CTX_RING_TAIL + 1] =
-		intel_ring_set_tail(rq->ring, rq->tail);
+	/*
+	 * WaIdleLiteRestore:bdw,skl
+	 *
+	 * We should never submit the context with the same RING_TAIL twice
+	 * just in case we submit an empty ring, which confuses the HW.
+	 *
+	 * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of
+	 * the normal request to be able to always advance the RING_TAIL on
+	 * subsequent resubmissions (for lite restore). Should that fail us,
+	 * and we try and submit the same tail again, force the context
+	 * reload.
+	 *
+	 * If we need to return to a preempted context, we need to skip the
+	 * lite-restore and force it to reload the RING_TAIL. Otherwise, the
+	 * HW has a tendency to ignore us rewinding the TAIL to the end of
+	 * an earlier request.
+	 */
+	tail = intel_ring_set_tail(rq->ring, rq->tail);
+	prev = ce->lrc_reg_state[CTX_RING_TAIL + 1];
+	if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
+		desc |= CTX_DESC_FORCE_RESTORE;
+	ce->lrc_reg_state[CTX_RING_TAIL + 1] = tail;
+	rq->tail = rq->wa_tail;
 
 	/*
 	 * Make sure the context image is complete before we submit it to HW.
@@ -674,7 +690,6 @@
 	 */
 	mb();
 
-	desc = ce->lrc_desc;
 	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
 
 	return desc;
@@ -918,6 +933,11 @@
 	return *last;
 }
 
+#define for_each_waiter(p__, rq__) \
+	list_for_each_entry_lockless(p__, \
+				     &(rq__)->sched.waiters_list, \
+				     wait_link)
+
 static void defer_request(struct i915_request *rq, struct list_head * const pl)
 {
 	LIST_HEAD(list);
@@ -935,7 +955,7 @@
 		GEM_BUG_ON(i915_request_is_active(rq));
 		list_move_tail(&rq->sched.link, pl);
 
-		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+		for_each_waiter(p, rq) {
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
@@ -1101,14 +1121,6 @@
 			 */
 			__unwind_incomplete_requests(engine);
 
-			/*
-			 * If we need to return to the preempted context, we
-			 * need to skip the lite-restore and force it to
-			 * reload the RING_TAIL. Otherwise, the HW has a
-			 * tendency to ignore us rewinding the TAIL to the
-			 * end of an earlier request.
-			 */
-			last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   !timer_pending(&engine->execlists.timer)) {
@@ -1149,16 +1161,6 @@
 			if (!list_is_last(&last->sched.link,
 					  &engine->active.requests))
 				return;
-
-			/*
-			 * WaIdleLiteRestore:bdw,skl
-			 * Apply the wa NOOPs to prevent
-			 * ring:HEAD == rq:TAIL as we resubmit the
-			 * request. See gen8_emit_fini_breadcrumb() for
-			 * where we prepare the padding after the
-			 * end of the request.
-			 */
-			last->tail = last->wa_tail;
 		}
 	}
 
@@ -1572,6 +1574,9 @@
 			if (!inject_preempt_hang(execlists))
 				ring_set_paused(engine, 0);
 
+			/* XXX Magic delay for tgl */
+			ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
 			WRITE_ONCE(execlists->pending[0], NULL);
 			break;
 
@@ -2131,6 +2136,14 @@
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
 	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
+	/* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */
+	batch = gen8_emit_pipe_control(batch,
+				       PIPE_CONTROL_FLUSH_L3 |
+				       PIPE_CONTROL_GLOBAL_GTT_IVB |
+				       PIPE_CONTROL_CS_STALL |
+				       PIPE_CONTROL_QW_WRITE,
+				       slm_offset(engine));
+
 	batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
 
 	/* WaMediaPoolStateCmdInWABB:bxt,glk */
@@ -2232,6 +2245,9 @@
 static void lrc_destroy_wa_ctx(struct intel_engine_cs *engine)
 {
 	i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0);
+
+	/* Called on error unwind, clear all flags to prevent further use */
+	memset(&engine->wa_ctx, 0, sizeof(engine->wa_ctx));
 }
 
 typedef u32 *(*wa_bb_func_t)(struct intel_engine_cs *engine, u32 *batch);
@@ -3715,9 +3731,11 @@
 	ve->base.i915 = ctx->i915;
 	ve->base.gt = siblings[0]->gt;
 	ve->base.id = -1;
+
 	ve->base.class = OTHER_CLASS;
 	ve->base.uabi_class = I915_ENGINE_CLASS_INVALID;
 	ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
+	ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
 
 	/*
 	 * The decision on whether to submit a request using semaphores
@@ -3739,6 +3757,7 @@
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 
 	intel_engine_init_execlists(&ve->base);
+	ve->base.breadcrumbs.irq_armed = true; /* fake HW, used for irq_work */
 
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index cea184a..e97a2aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -130,7 +130,19 @@
 	GEN9_MOCS_ENTRIES,
 	MOCS_ENTRY(I915_MOCS_CACHED,
 		   LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3),
-		   L3_3_WB)
+		   L3_3_WB),
+
+	/*
+	 * mocs:63
+	 * - used by the L3 for all of its evictions.
+	 *   Thus it is expected to allow LLC cacheability to enable coherent
+	 *   flows to be maintained.
+	 * - used to force L3 uncachable cycles.
+	 *   Thus it is expected to make the surface L3 uncacheable.
+	 */
+	MOCS_ENTRY(63,
+		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
+		   L3_1_UC)
 };
 
 /* NOTE: the LE_TGT_CACHE is not used on Broxton */
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index bacaa7b..eee9fcb 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1312,6 +1312,8 @@
 	kref_init(&ring->ref);
 
 	ring->size = size;
+	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
+
 	/* Workaround an erratum on the i830 which causes a hang if
 	 * the TAIL pointer points to within the last 2 cachelines
 	 * of the buffer.
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 9cb01d9..c970e3d 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -289,6 +289,14 @@
 		i915_gem_object_unpin_map(timeline->hwsp_ggtt->obj);
 
 	i915_vma_put(timeline->hwsp_ggtt);
+
+	/*
+	 * A small race exists between intel_gt_retire_requests_timeout and
+	 * intel_timeline_exit which could result in the syncmap not getting
+	 * free'd. Rather than work to hard to seal this race, simply cleanup
+	 * the syncmap on fini.
+	 */
+	i915_syncmap_free(&timeline->sync);
 }
 
 struct intel_timeline *
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index e753b1e..56cd14c 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -963,18 +963,6 @@
 	int i, ret = 0;
 	int cmd_len = cmd_length(s);
 	struct intel_gvt *gvt = s->vgpu->gvt;
-	u32 valid_len = CMD_LEN(1);
-
-	/*
-	 * Official intel docs are somewhat sloppy , check the definition of
-	 * MI_LOAD_REGISTER_IMM.
-	 */
-	#define MAX_VALID_LEN 127
-	if ((cmd_len < valid_len) || (cmd_len > MAX_VALID_LEN)) {
-		gvt_err("len is not valid:  len=%u  valid_len=%u\n",
-			cmd_len, valid_len);
-		return -EFAULT;
-	}
 
 	for (i = 1; i < cmd_len; i += 2) {
 		if (IS_BROADWELL(gvt->dev_priv) && s->ring_id != RCS0) {
@@ -1597,9 +1585,9 @@
 	if (!(cmd_val(s, 0) & (1 << 22)))
 		return ret;
 
-	/* check if QWORD */
-	if (DWORD_FIELD(0, 20, 19) == 1)
-		valid_len += 8;
+	/* check inline data */
+	if (cmd_val(s, 0) & BIT(18))
+		valid_len = CMD_LEN(9);
 	ret = gvt_check_valid_cmd_length(cmd_length(s),
 			valid_len);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index e1c313d..21a562c 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -172,21 +172,176 @@
 	int pipe;
 
 	if (IS_BROXTON(dev_priv)) {
+		enum transcoder trans;
+		enum port port;
+
+		/* Clear PIPE, DDI, PHY, HPD before setting new */
 		vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~(BXT_DE_PORT_HP_DDIA |
 			BXT_DE_PORT_HP_DDIB |
 			BXT_DE_PORT_HP_DDIC);
 
+		for_each_pipe(dev_priv, pipe) {
+			vgpu_vreg_t(vgpu, PIPECONF(pipe)) &=
+				~(PIPECONF_ENABLE | I965_PIPECONF_ACTIVE);
+			vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE;
+			vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE;
+			vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~MCURSOR_MODE;
+			vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= MCURSOR_MODE_DISABLE;
+		}
+
+		for (trans = TRANSCODER_A; trans <= TRANSCODER_EDP; trans++) {
+			vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(trans)) &=
+				~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
+				  TRANS_DDI_PORT_MASK | TRANS_DDI_FUNC_ENABLE);
+		}
+		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
+			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
+			  TRANS_DDI_PORT_MASK);
+
+		for (port = PORT_A; port <= PORT_C; port++) {
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(port)) &=
+				~BXT_PHY_LANE_ENABLED;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(port)) |=
+				(BXT_PHY_CMNLANE_POWERDOWN_ACK |
+				 BXT_PHY_LANE_POWERDOWN_ACK);
+
+			vgpu_vreg_t(vgpu, BXT_PORT_PLL_ENABLE(port)) &=
+				~(PORT_PLL_POWER_STATE | PORT_PLL_POWER_ENABLE |
+				  PORT_PLL_REF_SEL | PORT_PLL_LOCK |
+				  PORT_PLL_ENABLE);
+
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) &=
+				~(DDI_INIT_DISPLAY_DETECTED |
+				  DDI_BUF_CTL_ENABLE);
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) |= DDI_BUF_IS_IDLE;
+		}
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTA_HOTPLUG_ENABLE | PORTA_HOTPLUG_STATUS_MASK);
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTB_HOTPLUG_ENABLE | PORTB_HOTPLUG_STATUS_MASK);
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTC_HOTPLUG_ENABLE | PORTC_HOTPLUG_STATUS_MASK);
+		/* No hpd_invert set in vgpu vbt, need to clear invert mask */
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= ~BXT_DDI_HPD_INVERT_MASK;
+		vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~BXT_DE_PORT_HOTPLUG_MASK;
+
+		vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1));
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
+			~PHY_POWER_GOOD;
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) &=
+			~PHY_POWER_GOOD;
+		vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY0)) &= ~BIT(30);
+		vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY1)) &= ~BIT(30);
+
+		vgpu_vreg_t(vgpu, SFUSE_STRAP) &= ~SFUSE_STRAP_DDIB_DETECTED;
+		vgpu_vreg_t(vgpu, SFUSE_STRAP) &= ~SFUSE_STRAP_DDIC_DETECTED;
+
+		/*
+		 * Only 1 PIPE enabled in current vGPU display and PIPE_A is
+		 *  tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A,
+		 *   TRANSCODER_A can be enabled. PORT_x depends on the input of
+		 *   setup_virtual_dp_monitor.
+		 */
+		vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
+		vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= I965_PIPECONF_ACTIVE;
+
+		/*
+		 * Golden M/N are calculated based on:
+		 *   24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID),
+		 *   DP link clk 1620 MHz and non-constant_n.
+		 * TODO: calculate DP link symbol clk and stream clk m/n.
+		 */
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT;
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e;
+		vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000;
+		vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e;
+		vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000;
+
+		/* Enable per-DDI/PORT vreg */
 		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+			vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) |= BIT(1);
+			vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) |=
+				PHY_POWER_GOOD;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY1)) |=
+				BIT(30);
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_A)) |=
+				BXT_PHY_LANE_ENABLED;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_A)) &=
+				~(BXT_PHY_CMNLANE_POWERDOWN_ACK |
+				  BXT_PHY_LANE_POWERDOWN_ACK);
+			vgpu_vreg_t(vgpu, BXT_PORT_PLL_ENABLE(PORT_A)) |=
+				(PORT_PLL_POWER_STATE | PORT_PLL_POWER_ENABLE |
+				 PORT_PLL_REF_SEL | PORT_PLL_LOCK |
+				 PORT_PLL_ENABLE);
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(PORT_A)) |=
+				(DDI_BUF_CTL_ENABLE | DDI_INIT_DISPLAY_DETECTED);
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(PORT_A)) &=
+				~DDI_BUF_IS_IDLE;
+			vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)) |=
+				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTA_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				BXT_DE_PORT_HP_DDIA;
 		}
 
 		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+			vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
+			vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) |= BIT(0);
+			vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) |=
+				PHY_POWER_GOOD;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY0)) |=
+				BIT(30);
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_B)) |=
+				BXT_PHY_LANE_ENABLED;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_B)) &=
+				~(BXT_PHY_CMNLANE_POWERDOWN_ACK |
+				  BXT_PHY_LANE_POWERDOWN_ACK);
+			vgpu_vreg_t(vgpu, BXT_PORT_PLL_ENABLE(PORT_B)) |=
+				(PORT_PLL_POWER_STATE | PORT_PLL_POWER_ENABLE |
+				 PORT_PLL_REF_SEL | PORT_PLL_LOCK |
+				 PORT_PLL_ENABLE);
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(PORT_B)) |=
+				DDI_BUF_CTL_ENABLE;
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(PORT_B)) &=
+				~DDI_BUF_IS_IDLE;
+			vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
+				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+				 (PORT_B << TRANS_DDI_PORT_SHIFT) |
+				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTB_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				BXT_DE_PORT_HP_DDIB;
 		}
 
 		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+			vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED;
+			vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) |= BIT(0);
+			vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) |=
+				PHY_POWER_GOOD;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY0)) |=
+				BIT(30);
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) |=
+				BXT_PHY_LANE_ENABLED;
+			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) &=
+				~(BXT_PHY_CMNLANE_POWERDOWN_ACK |
+				  BXT_PHY_LANE_POWERDOWN_ACK);
+			vgpu_vreg_t(vgpu, BXT_PORT_PLL_ENABLE(PORT_C)) |=
+				(PORT_PLL_POWER_STATE | PORT_PLL_POWER_ENABLE |
+				 PORT_PLL_REF_SEL | PORT_PLL_LOCK |
+				 PORT_PLL_ENABLE);
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(PORT_C)) |=
+				DDI_BUF_CTL_ENABLE;
+			vgpu_vreg_t(vgpu, DDI_BUF_CTL(PORT_C)) &=
+				~DDI_BUF_IS_IDLE;
+			vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
+				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+				 (PORT_B << TRANS_DDI_PORT_SHIFT) |
+				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTC_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				BXT_DE_PORT_HP_DDIC;
 		}
@@ -207,14 +362,41 @@
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG0) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG1) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG2);
-		vgpu_vreg_t(vgpu, LCPLL1_CTL) |=
-				LCPLL_PLL_ENABLE |
-				LCPLL_PLL_LOCK;
-		vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE;
-
+		/*
+		 * Only 1 PIPE enabled in current vGPU display and PIPE_A is
+		 *  tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A,
+		 *   TRANSCODER_A can be enabled. PORT_x depends on the input of
+		 *   setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x
+		 *   so we fixed to DPLL0 here.
+		 * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode
+		 */
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) =
+			DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) |=
+			DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, LCPLL1_CTL) =
+			LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK;
+		vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0);
+		/*
+		 * Golden M/N are calculated based on:
+		 *   24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID),
+		 *   DP link clk 1620 MHz and non-constant_n.
+		 * TODO: calculate DP link symbol clk and stream clk m/n.
+		 */
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT;
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e;
+		vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000;
+		vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e;
+		vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000;
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B);
 		vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -235,6 +417,12 @@
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -255,6 +443,12 @@
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -457,7 +651,8 @@
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
 	/* TODO: add more platforms support */
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+		IS_COFFEELAKE(dev_priv)) {
 		if (connected) {
 			vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
 				SFUSE_STRAP_DDID_DETECTED;
@@ -471,6 +666,63 @@
 		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
 				PORTD_HOTPLUG_STATUS_MASK;
 		intel_vgpu_trigger_virtual_event(vgpu, DP_D_HOTPLUG);
+	} else if (IS_BROXTON(dev_priv)) {
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+			if (connected) {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+					BXT_DE_PORT_HP_DDIA;
+			} else {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+					~BXT_DE_PORT_HP_DDIA;
+			}
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				BXT_DE_PORT_HP_DDIA;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTA_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTA_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_A_HOTPLUG);
+		}
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+			if (connected) {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+					BXT_DE_PORT_HP_DDIB;
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
+					SFUSE_STRAP_DDIB_DETECTED;
+			} else {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+					~BXT_DE_PORT_HP_DDIB;
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
+					~SFUSE_STRAP_DDIB_DETECTED;
+			}
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				BXT_DE_PORT_HP_DDIB;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTB_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTB_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
+		}
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+			if (connected) {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+					BXT_DE_PORT_HP_DDIC;
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
+					SFUSE_STRAP_DDIC_DETECTED;
+			} else {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+					~BXT_DE_PORT_HP_DDIC;
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
+					~SFUSE_STRAP_DDIC_DETECTED;
+			}
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				BXT_DE_PORT_HP_DDIC;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTC_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTC_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_C_HOTPLUG);
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 4bfaefd..c034795 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -96,12 +96,12 @@
 			dmabuf_obj = container_of(pos,
 					struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {
+				list_del(pos);
 				intel_gvt_hypervisor_put_vfio_device(vgpu);
 				idr_remove(&vgpu->object_idr,
 					   dmabuf_obj->dmabuf_id);
 				kfree(dmabuf_obj->info);
 				kfree(dmabuf_obj);
-				list_del(pos);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4b04af5..7dc7bb8 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1956,7 +1956,11 @@
 
 	if (mm->type == INTEL_GVT_MM_PPGTT) {
 		list_del(&mm->ppgtt_mm.list);
+
+		mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
 		list_del(&mm->ppgtt_mm.lru_list);
+		mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
+
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 8f37eef..a738c7e 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -128,7 +128,7 @@
 	return true;
 }
 
-static bool intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt)
+static int intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt)
 {
 	int i, j;
 	struct intel_vgpu_type *type;
@@ -146,7 +146,7 @@
 		gvt_vgpu_type_groups[i] = group;
 	}
 
-	return true;
+	return 0;
 
 unwind:
 	for (j = 0; j < i; j++) {
@@ -154,7 +154,7 @@
 		kfree(group);
 	}
 
-	return false;
+	return -ENOMEM;
 }
 
 static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt)
@@ -362,7 +362,7 @@
 		goto out_clean_thread;
 
 	ret = intel_gvt_init_vgpu_type_groups(gvt);
-	if (ret == false) {
+	if (ret) {
 		gvt_err("failed to init vgpu type groups: %d\n", ret);
 		goto out_clean_types;
 	}
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 25f7819..245c20d 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1632,6 +1632,34 @@
 	return 0;
 }
 
+/**
+ * FixMe:
+ * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did:
+ * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.)
+ * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing
+ * these MI_BATCH_BUFFER.
+ * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT
+ * PML4 PTE: PAT(0) PCD(1) PWT(1).
+ * The performance is still expected to be low, will need further improvement.
+ */
+static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset,
+			      void *p_data, unsigned int bytes)
+{
+	u64 pat =
+		GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(1, 0) |
+		GEN8_PPAT(2, 0) |
+		GEN8_PPAT(3, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+	vgpu_vreg(vgpu, offset) = lower_32_bits(pat);
+
+	return 0;
+}
+
 static int mmio_read_from_hw(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
@@ -2778,7 +2806,7 @@
 
 	MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
 
-	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
+	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT);
 	MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
 
 	MMIO_D(GAMTARBMODE, D_BDW_PLUS);
@@ -3103,8 +3131,8 @@
 	MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		 NULL, NULL);
 
-	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL);
-	MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL);
+	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT);
 
 	return 0;
 }
@@ -3278,9 +3306,17 @@
 	MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
 	MMIO_D(GEN6_GFXPAUSE, D_BXT);
 	MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_F(HSW_CS_GPR(0), 0x40, F_CMD_ACCESS, 0, 0, D_BXT, NULL, NULL);
+	MMIO_F(_MMIO(0x12600), 0x40, F_CMD_ACCESS, 0, 0, D_BXT, NULL, NULL);
+	MMIO_F(BCS_GPR(0), 0x40, F_CMD_ACCESS, 0, 0, D_BXT, NULL, NULL);
+	MMIO_F(_MMIO(0x1a600), 0x40, F_CMD_ACCESS, 0, 0, D_BXT, NULL, NULL);
 
 	MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index a551788..e0e7adc 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -271,6 +271,11 @@
 			vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) |=
 				    BXT_PHY_CMNLANE_POWERDOWN_ACK |
 				    BXT_PHY_LANE_POWERDOWN_ACK;
+			vgpu_vreg_t(vgpu, SKL_FUSE_STATUS) |=
+				SKL_FUSE_DOWNLOAD_STATUS |
+				SKL_FUSE_PG_DIST_STATUS(SKL_PG0) |
+				SKL_FUSE_PG_DIST_STATUS(SKL_PG1) |
+				SKL_FUSE_PG_DIST_STATUS(SKL_PG2);
 		}
 	} else {
 #define GVT_GEN8_MMIO_RESET_OFFSET		(0x44200)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 6c79d16..058dcd5 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -374,7 +374,11 @@
 		for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) {
 			struct i915_page_directory * const pd =
 				i915_pd_entry(ppgtt->pd, i);
-
+			/* skip now as current i915 ppgtt alloc won't allocate
+			   top level pdp for non 4-level table, won't impact
+			   shadow ppgtt. */
+			if (!pd)
+				break;
 			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index d5a6e4e..4deb7fe 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -272,10 +272,17 @@
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 
-	mutex_lock(&vgpu->vgpu_lock);
-
 	WARN(vgpu->active, "vGPU is still active!\n");
 
+	/*
+	 * remove idr first so later clean can judge if need to stop
+	 * service if no active vgpu.
+	 */
+	mutex_lock(&gvt->lock);
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
+	mutex_unlock(&gvt->lock);
+
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_gvt_debugfs_remove_vgpu(vgpu);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_submission(vgpu);
@@ -290,7 +297,6 @@
 	mutex_unlock(&vgpu->vgpu_lock);
 
 	mutex_lock(&gvt->lock);
-	idr_remove(&gvt->vgpu_idr, vgpu->id);
 	if (idr_is_empty(&gvt->vgpu_idr))
 		intel_gvt_clean_irq(gvt);
 	intel_gvt_update_vgpu_types(gvt);
@@ -426,8 +432,9 @@
 	if (ret)
 		goto out_clean_sched_policy;
 
-	/*TODO: add more platforms support */
-	if (IS_SKYLAKE(gvt->dev_priv) || IS_KABYLAKE(gvt->dev_priv))
+	if (IS_BROADWELL(gvt->dev_priv) || IS_BROXTON(gvt->dev_priv))
+		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
+	else
 		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
 	if (ret)
 		goto out_clean_sched_policy;
@@ -560,9 +567,9 @@
 
 		intel_vgpu_reset_mmio(vgpu, dmlr);
 		populate_pvinfo_page(vgpu);
-		intel_vgpu_reset_display(vgpu);
 
 		if (dmlr) {
+			intel_vgpu_reset_display(vgpu);
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 48e16ad..51dc875 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -121,7 +121,7 @@
 #endif
 
 static void
-__active_retire(struct i915_active *ref)
+__active_retire(struct i915_active *ref, bool lock)
 {
 	struct active_node *it, *n;
 	struct rb_root root;
@@ -138,7 +138,8 @@
 		retire = true;
 	}
 
-	mutex_unlock(&ref->mutex);
+	if (likely(lock))
+		mutex_unlock(&ref->mutex);
 	if (!retire)
 		return;
 
@@ -153,21 +154,28 @@
 }
 
 static void
-active_retire(struct i915_active *ref)
+active_retire(struct i915_active *ref, bool lock)
 {
 	GEM_BUG_ON(!atomic_read(&ref->count));
 	if (atomic_add_unless(&ref->count, -1, 1))
 		return;
 
 	/* One active may be flushed from inside the acquire of another */
-	mutex_lock_nested(&ref->mutex, SINGLE_DEPTH_NESTING);
-	__active_retire(ref);
+	if (likely(lock))
+		mutex_lock_nested(&ref->mutex, SINGLE_DEPTH_NESTING);
+	__active_retire(ref, lock);
 }
 
 static void
 node_retire(struct i915_active_request *base, struct i915_request *rq)
 {
-	active_retire(node_from_active(base)->ref);
+	active_retire(node_from_active(base)->ref, true);
+}
+
+static void
+node_retire_nolock(struct i915_active_request *base, struct i915_request *rq)
+{
+	active_retire(node_from_active(base)->ref, false);
 }
 
 static struct i915_active_request *
@@ -364,7 +372,7 @@
 void i915_active_release(struct i915_active *ref)
 {
 	debug_active_assert(ref);
-	active_retire(ref);
+	active_retire(ref, true);
 }
 
 static void __active_ungrab(struct i915_active *ref)
@@ -391,7 +399,7 @@
 {
 	GEM_BUG_ON(!test_bit(I915_ACTIVE_GRAB_BIT, &ref->flags));
 
-	active_retire(ref);
+	active_retire(ref, true);
 	__active_ungrab(ref);
 }
 
@@ -421,12 +429,13 @@
 			break;
 		}
 
-		err = i915_active_request_retire(&it->base, BKL(ref));
+		err = i915_active_request_retire(&it->base, BKL(ref),
+						 node_retire_nolock);
 		if (err)
 			break;
 	}
 
-	__active_retire(ref);
+	__active_retire(ref, true);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index f95058f..0ad7ef6 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -309,7 +309,7 @@
  */
 static inline int __must_check
 i915_active_request_retire(struct i915_active_request *active,
-			   struct mutex *mutex)
+			   struct mutex *mutex, i915_active_retire_fn retire)
 {
 	struct i915_request *request;
 	long ret;
@@ -327,7 +327,7 @@
 	list_del_init(&active->link);
 	RCU_INIT_POINTER(active->request, NULL);
 
-	active->retire(active, request);
+	retire(active, request);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index f24096e..a9a6976 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -572,6 +572,9 @@
 #define REG32(_reg, ...) \
 	{ .addr = (_reg), __VA_ARGS__ }
 
+#define REG32_IDX(_reg, idx) \
+	{ .addr = _reg(idx) }
+
 /*
  * Convenience macro for adding 64-bit registers.
  *
@@ -669,6 +672,7 @@
 	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
 	REG32(BCS_SWCTRL),
 	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
+	REG32_IDX(RING_CTX_TIMESTAMP, BLT_RING_BASE),
 	REG64_IDX(BCS_GPR, 0),
 	REG64_IDX(BCS_GPR, 1),
 	REG64_IDX(BCS_GPR, 2),
@@ -1203,6 +1207,12 @@
 	return dst;
 }
 
+static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc,
+			       const u32 cmd)
+{
+	return desc->cmd.value == (cmd & desc->cmd.mask);
+}
+
 static bool check_cmd(const struct intel_engine_cs *engine,
 		      const struct drm_i915_cmd_descriptor *desc,
 		      const u32 *cmd, u32 length)
@@ -1241,19 +1251,19 @@
 			 * allowed mask/value pair given in the whitelist entry.
 			 */
 			if (reg->mask) {
-				if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) {
 					DRM_DEBUG_DRIVER("CMD: Rejected LRM to masked register 0x%08X\n",
 							 reg_addr);
 					return false;
 				}
 
-				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) {
 					DRM_DEBUG_DRIVER("CMD: Rejected LRR to masked register 0x%08X\n",
 							 reg_addr);
 					return false;
 				}
 
-				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
+				if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
 					DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",
@@ -1484,7 +1494,7 @@
 			goto err;
 		}
 
-		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+		if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) {
 			ret = check_bbstart(ctx, cmd, offset, length,
 					    batch_len, batch_start,
 					    shadow_batch_start);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 89b6112..00335a1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -33,6 +33,8 @@
 #include <uapi/drm/i915_drm.h>
 #include <uapi/drm/drm_fourcc.h>
 
+#include <asm/hypervisor.h>
+
 #include <linux/io-mapping.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
@@ -1892,7 +1894,7 @@
 {
 	const unsigned int pi = __platform_mask_index(info, p);
 
-	return info->platform_mask[pi] & INTEL_SUBPLATFORM_BITS;
+	return info->platform_mask[pi] & ((1 << INTEL_SUBPLATFORM_BITS) - 1);
 }
 
 static __always_inline bool
@@ -2197,7 +2199,9 @@
 	if (intel_iommu_gfx_mapped)
 		return true;
 #endif
-	return false;
+
+	/* Running as a guest, we assume the host is enforcing VT'd */
+	return !hypervisor_is_type(X86_HYPER_NATIVE);
 }
 
 static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 98305d9..4d561da 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -136,7 +136,7 @@
 		     struct drm_i915_gem_pwrite *args,
 		     struct drm_file *file)
 {
-	void *vaddr = obj->phys_handle->vaddr + args->offset;
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
 
 	/*
@@ -802,10 +802,10 @@
 		ret = i915_gem_gtt_pwrite_fast(obj, args);
 
 	if (ret == -EFAULT || ret == -ENOSPC) {
-		if (obj->phys_handle)
-			ret = i915_gem_phys_pwrite(obj, args, file);
-		else
+		if (i915_gem_object_has_struct_page(obj))
 			ret = i915_gem_shmem_pwrite(obj, args);
+		else
+			ret = i915_gem_phys_pwrite(obj, args, file);
 	}
 
 	i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index b1a7a8b..f614646 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1178,6 +1178,7 @@
 	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 	do {
+		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
 		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
 
 		iter->dma += I915_GTT_PAGE_SIZE;
@@ -1657,6 +1658,7 @@
 
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
 	do {
+		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
 
 		iter.dma += I915_GTT_PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index e284bd7..b9af329 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -307,6 +307,8 @@
 
 		if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK)
 			return -EIO;
+
+		cond_resched();
 	} while (zstream->avail_in);
 
 	/* Fallback to uncompressed if we increase size? */
@@ -392,6 +394,7 @@
 	if (!i915_memcpy_from_wc(ptr, src, PAGE_SIZE))
 		memcpy(ptr, src, PAGE_SIZE);
 	dst->pages[dst->page_count++] = ptr;
+	cond_resched();
 
 	return 0;
 }
@@ -1768,7 +1771,8 @@
 	if (!xchg(&warned, true) &&
 	    ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
 		pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
-		pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+		pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n");
+		pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n");
 		pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
 		pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n");
 		pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n",
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 37e3dd3..4193a99 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3500,6 +3500,7 @@
 
 	val = I915_READ(GEN11_DE_HPD_IMR);
 	val &= ~hotplug_irqs;
+	val |= ~enabled_irqs & hotplug_irqs;
 	I915_WRITE(GEN11_DE_HPD_IMR, val);
 	POSTING_READ(GEN11_DE_HPD_IMR);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f8ee9ab..7b6e68f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4049,7 +4049,13 @@
 #define  GWUNIT_CLKGATE_DIS		(1 << 16)
 
 #define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
-#define  VFUNIT_CLKGATE_DIS		(1 << 20)
+#define   VFUNIT_CLKGATE_DIS		REG_BIT(20)
+#define   HSUNIT_CLKGATE_DIS		REG_BIT(8)
+#define   VSUNIT_CLKGATE_DIS		REG_BIT(3)
+
+#define UNSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x94e4)
+#define   VSUNIT_CLKGATE_DIS_TGL	REG_BIT(19)
+#define   PSDUNIT_CLKGATE_DIS		REG_BIT(5)
 
 #define INF_UNIT_LEVEL_CLKGATE		_MMIO(0x9560)
 #define   CGPSF_CLKGATE_DIS		(1 << 3)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 1c55068..49d4988 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -560,19 +560,31 @@
 	return NOTIFY_DONE;
 }
 
+static void irq_semaphore_cb(struct irq_work *wrk)
+{
+	struct i915_request *rq =
+		container_of(wrk, typeof(*rq), semaphore_work);
+
+	i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE);
+	i915_request_put(rq);
+}
+
 static int __i915_sw_fence_call
 semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {
-	struct i915_request *request =
-		container_of(fence, typeof(*request), semaphore);
+	struct i915_request *rq = container_of(fence, typeof(*rq), semaphore);
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
+		if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) {
+			i915_request_get(rq);
+			init_irq_work(&rq->semaphore_work, irq_semaphore_cb);
+			irq_work_queue(&rq->semaphore_work);
+		}
 		break;
 
 	case FENCE_FREE:
-		i915_request_put(request);
+		i915_request_put(rq);
 		break;
 	}
 
@@ -882,8 +894,10 @@
 	GEM_BUG_ON(to == from);
 	GEM_BUG_ON(to->timeline == from->timeline);
 
-	if (i915_request_completed(from))
+	if (i915_request_completed(from)) {
+		i915_sw_fence_set_error_once(&to->submit, from->fence.error);
 		return 0;
+	}
 
 	if (to->engine->schedule) {
 		ret = i915_sched_node_add_dependency(&to->sched, &from->sched);
@@ -1215,9 +1229,9 @@
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
-	i915_sw_fence_commit(&rq->semaphore);
 	if (attr && rq->engine->schedule)
 		rq->engine->schedule(rq, attr);
+	i915_sw_fence_commit(&rq->semaphore);
 	i915_sw_fence_commit(&rq->submit);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index e4dd013..3a3e7bb 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -26,6 +26,7 @@
 #define I915_REQUEST_H
 
 #include <linux/dma-fence.h>
+#include <linux/irq_work.h>
 #include <linux/lockdep.h>
 
 #include "gt/intel_context_types.h"
@@ -147,6 +148,7 @@
 	};
 	struct list_head execute_cb;
 	struct i915_sw_fence semaphore;
+	struct irq_work semaphore_work;
 
 	/*
 	 * A list of everyone we wait upon, and everyone who waits upon us.
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 3eba8a2..0ef205f 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -418,8 +418,6 @@
 
 	if (!node_signaled(signal)) {
 		INIT_LIST_HEAD(&dep->dfs_link);
-		list_add(&dep->wait_link, &signal->waiters_list);
-		list_add(&dep->signal_link, &node->signalers_list);
 		dep->signaler = signal;
 		dep->waiter = node;
 		dep->flags = flags;
@@ -429,6 +427,10 @@
 		    !node_started(signal))
 			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 
+		/* All set, now publish. Beware the lockless walkers. */
+		list_add(&dep->signal_link, &node->signalers_list);
+		list_add_rcu(&dep->wait_link, &signal->waiters_list);
+
 		/*
 		 * As we do not allow WAIT to preempt inflight requests,
 		 * once we have executed a request, along with triggering
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 6a88db2..b3fd6ff 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -158,9 +158,13 @@
 
 		do {
 			list_for_each_entry_safe(pos, next, &x->head, entry) {
-				pos->func(pos,
-					  TASK_NORMAL, fence->error,
-					  &extra);
+				int wake_flags;
+
+				wake_flags = fence->error;
+				if (pos->func == autoremove_wake_function)
+					wake_flags = 0;
+
+				pos->func(pos, TASK_NORMAL, wake_flags, &extra);
 			}
 
 			if (list_empty(&extra))
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index 16acdf7..17cfeef 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -8,9 +8,8 @@
 #include "i915_drv.h"
 #include "i915_utils.h"
 
-#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
-#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
-		    "providing the dmesg log by booting with drm.debug=0xf"
+#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs"
+#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details."
 
 void
 __i915_printk(struct drm_i915_private *dev_priv, const char *level,
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 562f756..5b1622a 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -233,6 +233,11 @@
 	__idx;								\
 })
 
+static inline bool is_power_of_2_u64(u64 n)
+{
+	return (n != 0 && ((n & (n - 1)) == 0));
+}
+
 static inline void __list_del_many(struct list_head *head,
 				   struct list_head *first)
 {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2efe1d1..91afeca 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2966,7 +2966,7 @@
 
 static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
 				   const char *name,
-				   const u16 wm[8])
+				   const u16 wm[])
 {
 	int level, max_level = ilk_wm_max_level(dev_priv);
 
@@ -4784,7 +4784,7 @@
 	 * WaIncreaseLatencyIPCEnabled: kbl,cfl
 	 * Display WA #1141: kbl,cfl
 	 */
-	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) ||
+	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) &&
 	    dev_priv->ipc_enabled)
 		latency += 4;
 
@@ -9194,6 +9194,17 @@
 	/* WaEnable32PlaneMode:icl */
 	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
 		   _MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE));
+
+	/*
+	 * Wa_1408615072:icl,ehl  (vsunit)
+	 * Wa_1407596294:icl,ehl  (hsunit)
+	 */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE,
+			 0, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
+	/* Wa_1407352427:icl,ehl */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+			 0, PSDUNIT_CLKGATE_DIS);
 }
 
 static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 9e583f1..62f8a47 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1124,6 +1124,18 @@
 		spin_unlock(&uncore->debug->lock);
 }
 
+#define __vgpu_read(x) \
+static u##x \
+vgpu_read##x(struct intel_uncore *uncore, i915_reg_t reg, bool trace) { \
+	u##x val = __raw_uncore_read##x(uncore, reg); \
+	trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \
+	return val; \
+}
+__vgpu_read(8)
+__vgpu_read(16)
+__vgpu_read(32)
+__vgpu_read(64)
+
 #define GEN2_READ_HEADER(x) \
 	u##x val = 0; \
 	assert_rpm_wakelock_held(uncore->rpm);
@@ -1327,6 +1339,16 @@
 #undef GEN6_WRITE_FOOTER
 #undef GEN6_WRITE_HEADER
 
+#define __vgpu_write(x) \
+static void \
+vgpu_write##x(struct intel_uncore *uncore, i915_reg_t reg, u##x val, bool trace) { \
+	trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \
+	__raw_uncore_write##x(uncore, reg, val); \
+}
+__vgpu_write(8)
+__vgpu_write(16)
+__vgpu_write(32)
+
 #define ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, x) \
 do { \
 	(uncore)->funcs.mmio_writeb = x##_write8; \
@@ -1647,7 +1669,10 @@
 {
 	GEM_BUG_ON(intel_uncore_has_forcewake(uncore));
 
-	if (IS_GEN(uncore->i915, 5)) {
+	if (intel_vgpu_active(uncore->i915)) {
+		ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, vgpu);
+		ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, vgpu);
+	} else if (IS_GEN(uncore->i915, 5)) {
 		ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, gen5);
 		ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, gen5);
 	} else {
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 8e1ff9c..22335ce 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -25,6 +25,7 @@
 #ifndef __I915_SELFTESTS_RANDOM_H__
 #define __I915_SELFTESTS_RANDOM_H__
 
+#include <linux/math64.h>
 #include <linux/random.h>
 
 #include "../i915_selftest.h"
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index f22cfbf..2e12a4a 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -212,9 +212,8 @@
 	if (!pdev->dev.of_node)
 		return -ENODEV;
 
-	hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
-	if (!hdmi)
-		return -ENOMEM;
+	hdmi = dev_get_drvdata(dev);
+	memset(hdmi, 0, sizeof(*hdmi));
 
 	match = of_match_node(dw_hdmi_imx_dt_ids, pdev->dev.of_node);
 	plat_data = match->data;
@@ -239,8 +238,6 @@
 	drm_encoder_init(drm, encoder, &dw_hdmi_imx_encoder_funcs,
 			 DRM_MODE_ENCODER_TMDS, NULL);
 
-	platform_set_drvdata(pdev, hdmi);
-
 	hdmi->hdmi = dw_hdmi_bind(pdev, encoder, plat_data);
 
 	/*
@@ -270,6 +267,14 @@
 
 static int dw_hdmi_imx_probe(struct platform_device *pdev)
 {
+	struct imx_hdmi *hdmi;
+
+	hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
+	if (!hdmi)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, hdmi);
+
 	return component_add(&pdev->dev, &dw_hdmi_imx_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index da87c70..881c36d 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -281,9 +281,10 @@
 
 	drm_kms_helper_poll_fini(drm);
 
+	component_unbind_all(drm->dev, drm);
+
 	drm_mode_config_cleanup(drm);
 
-	component_unbind_all(drm->dev, drm);
 	dev_set_drvdata(dev, NULL);
 
 	drm_dev_put(drm);
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 695f307..116473c 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -197,6 +197,11 @@
 	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
 
+	if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+		dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+		return;
+	}
+
 	drm_panel_prepare(imx_ldb_ch->panel);
 
 	if (dual) {
@@ -255,6 +260,11 @@
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
 	u32 bus_format = imx_ldb_ch->bus_format;
 
+	if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+		dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+		return;
+	}
+
 	if (mode->clock > 170000) {
 		dev_warn(ldb->dev,
 			 "%s: mode exceeds 170 MHz pixel clock\n", __func__);
@@ -302,18 +312,19 @@
 {
 	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
+	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
 	int mux, ret;
 
 	drm_panel_disable(imx_ldb_ch->panel);
 
-	if (imx_ldb_ch == &ldb->channel[0])
+	if (imx_ldb_ch == &ldb->channel[0] || dual)
 		ldb->ldb_ctrl &= ~LDB_CH0_MODE_EN_MASK;
-	else if (imx_ldb_ch == &ldb->channel[1])
+	if (imx_ldb_ch == &ldb->channel[1] || dual)
 		ldb->ldb_ctrl &= ~LDB_CH1_MODE_EN_MASK;
 
 	regmap_write(ldb->regmap, IOMUXC_GPR2, ldb->ldb_ctrl);
 
-	if (ldb->ldb_ctrl & LDB_SPLIT_MODE_EN) {
+	if (dual) {
 		clk_disable_unprepare(ldb->clk[0]);
 		clk_disable_unprepare(ldb->clk[1]);
 	}
@@ -593,9 +604,8 @@
 	int ret;
 	int i;
 
-	imx_ldb = devm_kzalloc(dev, sizeof(*imx_ldb), GFP_KERNEL);
-	if (!imx_ldb)
-		return -ENOMEM;
+	imx_ldb = dev_get_drvdata(dev);
+	memset(imx_ldb, 0, sizeof(*imx_ldb));
 
 	imx_ldb->regmap = syscon_regmap_lookup_by_phandle(np, "gpr");
 	if (IS_ERR(imx_ldb->regmap)) {
@@ -703,8 +713,6 @@
 		}
 	}
 
-	dev_set_drvdata(dev, imx_ldb);
-
 	return 0;
 
 free_child:
@@ -736,6 +744,14 @@
 
 static int imx_ldb_probe(struct platform_device *pdev)
 {
+	struct imx_ldb *imx_ldb;
+
+	imx_ldb = devm_kzalloc(&pdev->dev, sizeof(*imx_ldb), GFP_KERNEL);
+	if (!imx_ldb)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, imx_ldb);
+
 	return component_add(&pdev->dev, &imx_ldb_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 5bbfaa2..f91c3eb 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -494,6 +494,13 @@
 	return 0;
 }
 
+static void imx_tve_disable_regulator(void *data)
+{
+	struct imx_tve *tve = data;
+
+	regulator_disable(tve->dac_reg);
+}
+
 static bool imx_tve_readable_reg(struct device *dev, unsigned int reg)
 {
 	return (reg % 4 == 0) && (reg <= 0xdc);
@@ -546,9 +553,8 @@
 	int irq;
 	int ret;
 
-	tve = devm_kzalloc(dev, sizeof(*tve), GFP_KERNEL);
-	if (!tve)
-		return -ENOMEM;
+	tve = dev_get_drvdata(dev);
+	memset(tve, 0, sizeof(*tve));
 
 	tve->dev = dev;
 	spin_lock_init(&tve->lock);
@@ -618,6 +624,9 @@
 		ret = regulator_enable(tve->dac_reg);
 		if (ret)
 			return ret;
+		ret = devm_add_action_or_reset(dev, imx_tve_disable_regulator, tve);
+		if (ret)
+			return ret;
 	}
 
 	tve->clk = devm_clk_get(dev, "tve");
@@ -659,27 +668,23 @@
 	if (ret)
 		return ret;
 
-	dev_set_drvdata(dev, tve);
-
 	return 0;
 }
 
-static void imx_tve_unbind(struct device *dev, struct device *master,
-	void *data)
-{
-	struct imx_tve *tve = dev_get_drvdata(dev);
-
-	if (!IS_ERR(tve->dac_reg))
-		regulator_disable(tve->dac_reg);
-}
-
 static const struct component_ops imx_tve_ops = {
 	.bind	= imx_tve_bind,
-	.unbind	= imx_tve_unbind,
 };
 
 static int imx_tve_probe(struct platform_device *pdev)
 {
+	struct imx_tve *tve;
+
+	tve = devm_kzalloc(&pdev->dev, sizeof(*tve), GFP_KERNEL);
+	if (!tve)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, tve);
+
 	return component_add(&pdev->dev, &imx_tve_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 63c0284..2256c97 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -438,21 +438,13 @@
 	struct ipu_client_platformdata *pdata = dev->platform_data;
 	struct drm_device *drm = data;
 	struct ipu_crtc *ipu_crtc;
-	int ret;
 
-	ipu_crtc = devm_kzalloc(dev, sizeof(*ipu_crtc), GFP_KERNEL);
-	if (!ipu_crtc)
-		return -ENOMEM;
+	ipu_crtc = dev_get_drvdata(dev);
+	memset(ipu_crtc, 0, sizeof(*ipu_crtc));
 
 	ipu_crtc->dev = dev;
 
-	ret = ipu_crtc_init(ipu_crtc, pdata, drm);
-	if (ret)
-		return ret;
-
-	dev_set_drvdata(dev, ipu_crtc);
-
-	return 0;
+	return ipu_crtc_init(ipu_crtc, pdata, drm);
 }
 
 static void ipu_drm_unbind(struct device *dev, struct device *master,
@@ -474,6 +466,7 @@
 static int ipu_drm_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct ipu_crtc *ipu_crtc;
 	int ret;
 
 	if (!dev->platform_data)
@@ -483,6 +476,12 @@
 	if (ret)
 		return ret;
 
+	ipu_crtc = devm_kzalloc(dev, sizeof(*ipu_crtc), GFP_KERNEL);
+	if (!ipu_crtc)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, ipu_crtc);
+
 	return component_add(dev, &ipu_crtc_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index e7ce175..be55548 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -204,9 +204,8 @@
 	u32 bus_format = 0;
 	const char *fmt;
 
-	imxpd = devm_kzalloc(dev, sizeof(*imxpd), GFP_KERNEL);
-	if (!imxpd)
-		return -ENOMEM;
+	imxpd = dev_get_drvdata(dev);
+	memset(imxpd, 0, sizeof(*imxpd));
 
 	edidp = of_get_property(np, "edid", &imxpd->edid_len);
 	if (edidp)
@@ -236,8 +235,6 @@
 	if (ret)
 		return ret;
 
-	dev_set_drvdata(dev, imxpd);
-
 	return 0;
 }
 
@@ -259,6 +256,14 @@
 
 static int imx_pd_probe(struct platform_device *pdev)
 {
+	struct imx_parallel_display *imxpd;
+
+	imxpd = devm_kzalloc(&pdev->dev, sizeof(*imxpd), GFP_KERNEL);
+	if (!imxpd)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, imxpd);
+
 	return component_add(&pdev->dev, &imx_pd_ops);
 }
 
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c
index 2e2ed65..7e6179f 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm.c
@@ -371,14 +371,18 @@
 	struct ingenic_drm *priv = drm_plane_get_priv(plane);
 	struct drm_plane_state *state = plane->state;
 	unsigned int width, height, cpp;
+	dma_addr_t addr;
 
-	width = state->crtc->state->adjusted_mode.hdisplay;
-	height = state->crtc->state->adjusted_mode.vdisplay;
-	cpp = state->fb->format->cpp[plane->index];
+	if (state && state->fb) {
+		addr = drm_fb_cma_get_gem_addr(state->fb, state, 0);
+		width = state->src_w >> 16;
+		height = state->src_h >> 16;
+		cpp = state->fb->format->cpp[0];
 
-	priv->dma_hwdesc->addr = drm_fb_cma_get_gem_addr(state->fb, state, 0);
-	priv->dma_hwdesc->cmd = width * height * cpp / 4;
-	priv->dma_hwdesc->cmd |= JZ_LCD_CMD_EOF_IRQ;
+		priv->dma_hwdesc->addr = addr;
+		priv->dma_hwdesc->cmd = width * height * cpp / 4;
+		priv->dma_hwdesc->cmd |= JZ_LCD_CMD_EOF_IRQ;
+	}
 }
 
 static void ingenic_drm_encoder_atomic_mode_set(struct drm_encoder *encoder,
@@ -463,7 +467,7 @@
 
 static irqreturn_t ingenic_drm_irq_handler(int irq, void *arg)
 {
-	struct ingenic_drm *priv = arg;
+	struct ingenic_drm *priv = drm_device_get_priv(arg);
 	unsigned int state;
 
 	regmap_read(priv->map, JZ_REG_LCD_STATE, &state);
@@ -820,6 +824,7 @@
 	{ .compatible = "ingenic,jz4725b-lcd", .data = &jz4725b_soc_info },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, ingenic_drm_of_match);
 
 static struct platform_driver ingenic_drm_driver = {
 	.driver = {
diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c
index 751454a..28ed506 100644
--- a/drivers/gpu/drm/mcde/mcde_display.c
+++ b/drivers/gpu/drm/mcde/mcde_display.c
@@ -946,6 +946,7 @@
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_device *drm = crtc->dev;
 	struct mcde *mcde = drm->dev_private;
+	struct drm_pending_vblank_event *event;
 
 	if (mcde->te_sync)
 		drm_crtc_vblank_off(crtc);
@@ -953,6 +954,15 @@
 	/* Disable FIFO A flow */
 	mcde_disable_fifo(mcde, MCDE_FIFO_A, true);
 
+	event = crtc->state->event;
+	if (event) {
+		crtc->state->event = NULL;
+
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
+
 	dev_info(drm->dev, "MCDE display is disabled\n");
 }
 
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index 9a09eba..82946ff 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -215,7 +215,6 @@
 
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
-	drm_fbdev_generic_setup(drm, 32);
 
 	return 0;
 
@@ -282,6 +281,8 @@
 	if (ret < 0)
 		goto unbind;
 
+	drm_fbdev_generic_setup(drm, 32);
+
 	return 0;
 
 unbind:
@@ -409,8 +410,8 @@
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
-		ret = -EINVAL;
+	if (irq < 0) {
+		ret = irq;
 		goto clk_disable;
 	}
 
@@ -484,7 +485,8 @@
 	}
 	if (!match) {
 		dev_err(dev, "no matching components\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto clk_disable;
 	}
 	if (IS_ERR(match)) {
 		dev_err(dev, "could not create component match\n");
diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c
index f9c9e32..8c8c92f 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi.c
+++ b/drivers/gpu/drm/mcde/mcde_dsi.c
@@ -935,13 +935,14 @@
 	for_each_available_child_of_node(dev->of_node, child) {
 		panel = of_drm_find_panel(child);
 		if (IS_ERR(panel)) {
-			dev_err(dev, "failed to find panel try bridge (%lu)\n",
+			dev_err(dev, "failed to find panel try bridge (%ld)\n",
 				PTR_ERR(panel));
+			panel = NULL;
+
 			bridge = of_drm_find_bridge(child);
-			if (IS_ERR(bridge)) {
-				dev_err(dev, "failed to find bridge (%lu)\n",
-					PTR_ERR(bridge));
-				return PTR_ERR(bridge);
+			if (!bridge) {
+				dev_err(dev, "failed to find bridge\n");
+				return -EINVAL;
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index be6d95c..48de07e 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -10,7 +10,9 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/of_graph.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
 
@@ -73,6 +75,9 @@
 	enum mtk_dpi_out_yc_map yc_map;
 	enum mtk_dpi_out_bit_num bit_num;
 	enum mtk_dpi_out_channel_swap channel_swap;
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_gpio;
+	struct pinctrl_state *pins_dpi;
 	int refcount;
 };
 
@@ -378,6 +383,9 @@
 	if (--dpi->refcount != 0)
 		return;
 
+	if (dpi->pinctrl && dpi->pins_gpio)
+		pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio);
+
 	mtk_dpi_disable(dpi);
 	clk_disable_unprepare(dpi->pixel_clk);
 	clk_disable_unprepare(dpi->engine_clk);
@@ -402,6 +410,9 @@
 		goto err_pixel;
 	}
 
+	if (dpi->pinctrl && dpi->pins_dpi)
+		pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi);
+
 	mtk_dpi_enable(dpi);
 	return 0;
 
@@ -689,6 +700,26 @@
 	dpi->dev = dev;
 	dpi->conf = (struct mtk_dpi_conf *)of_device_get_match_data(dev);
 
+	dpi->pinctrl = devm_pinctrl_get(&pdev->dev);
+	if (IS_ERR(dpi->pinctrl)) {
+		dpi->pinctrl = NULL;
+		dev_dbg(&pdev->dev, "Cannot find pinctrl!\n");
+	}
+	if (dpi->pinctrl) {
+		dpi->pins_gpio = pinctrl_lookup_state(dpi->pinctrl, "sleep");
+		if (IS_ERR(dpi->pins_gpio)) {
+			dpi->pins_gpio = NULL;
+			dev_dbg(&pdev->dev, "Cannot find pinctrl idle!\n");
+		}
+		if (dpi->pins_gpio)
+			pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio);
+
+		dpi->pins_dpi = pinctrl_lookup_state(dpi->pinctrl, "default");
+		if (IS_ERR(dpi->pins_dpi)) {
+			dpi->pins_dpi = NULL;
+			dev_dbg(&pdev->dev, "Cannot find pinctrl active!\n");
+		}
+	}
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dpi->regs = devm_ioremap_resource(dev, mem);
 	if (IS_ERR(dpi->regs)) {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 34a7317..f370d41 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -240,7 +240,7 @@
 		drm_connector_list_iter_end(&conn_iter);
 	}
 
-	ret = pm_runtime_get_sync(crtc->dev->dev);
+	ret = pm_runtime_resume_and_get(crtc->dev->dev);
 	if (ret < 0) {
 		DRM_ERROR("Failed to enable power domain: %d\n", ret);
 		return ret;
@@ -298,6 +298,7 @@
 static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_device *drm = mtk_crtc->base.dev;
+	struct drm_crtc *crtc = &mtk_crtc->base;
 	int i;
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
@@ -319,6 +320,13 @@
 	mtk_disp_mutex_unprepare(mtk_crtc->mutex);
 
 	pm_runtime_put(drm->dev);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
 static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
@@ -488,10 +496,18 @@
 
 static int mtk_drm_crtc_init(struct drm_device *drm,
 			     struct mtk_drm_crtc *mtk_crtc,
-			     struct drm_plane *primary,
-			     struct drm_plane *cursor, unsigned int pipe)
+			     unsigned int pipe)
 {
-	int ret;
+	struct drm_plane *primary = NULL;
+	struct drm_plane *cursor = NULL;
+	int i, ret;
+
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_PRIMARY)
+			primary = &mtk_crtc->planes[i];
+		else if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_CURSOR)
+			cursor = &mtk_crtc->planes[i];
+	}
 
 	ret = drm_crtc_init_with_planes(drm, &mtk_crtc->base, primary, cursor,
 					&mtk_crtc_funcs, NULL);
@@ -529,6 +545,7 @@
 	int pipe = priv->num_pipes;
 	int ret;
 	int i;
+	uint gamma_lut_size = 0;
 
 	if (!path)
 		return 0;
@@ -579,6 +596,9 @@
 		}
 
 		mtk_crtc->ddp_comp[i] = comp;
+
+		if (comp->funcs && comp->funcs->gamma_set)
+			gamma_lut_size = MTK_LUT_SIZE;
 	}
 
 	mtk_crtc->layer_nr = mtk_ddp_comp_layer_nr(mtk_crtc->ddp_comp[0]);
@@ -596,13 +616,13 @@
 			return ret;
 	}
 
-	ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, &mtk_crtc->planes[0],
-				mtk_crtc->layer_nr > 1 ? &mtk_crtc->planes[1] :
-				NULL, pipe);
+	ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, pipe);
 	if (ret < 0)
 		return ret;
-	drm_mode_crtc_set_gamma_size(&mtk_crtc->base, MTK_LUT_SIZE);
-	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, MTK_LUT_SIZE);
+
+	if (gamma_lut_size)
+		drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size);
+	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, gamma_lut_size);
 	priv->num_pipes++;
 
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 352b81a..f98bb2e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -594,8 +594,13 @@
 	pm_runtime_disable(dev);
 err_node:
 	of_node_put(private->mutex_node);
-	for (i = 0; i < DDP_COMPONENT_ID_MAX; i++)
+	for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) {
 		of_node_put(private->comp_node[i]);
+		if (private->ddp_comp[i]) {
+			put_device(private->ddp_comp[i]->larb_dev);
+			private->ddp_comp[i] = NULL;
+		}
+	}
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 584a9ec..b7592b1 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -101,6 +101,16 @@
 						   true, true);
 }
 
+static void mtk_plane_atomic_disable(struct drm_plane *plane,
+				     struct drm_plane_state *old_state)
+{
+	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+	state->pending.enable = false;
+	wmb(); /* Make sure the above parameter is set before update */
+	state->pending.dirty = true;
+}
+
 static void mtk_plane_atomic_update(struct drm_plane *plane,
 				    struct drm_plane_state *old_state)
 {
@@ -115,6 +125,11 @@
 	if (!crtc || WARN_ON(!fb))
 		return;
 
+	if (!plane->state->visible) {
+		mtk_plane_atomic_disable(plane, old_state);
+		return;
+	}
+
 	gem = fb->obj[0];
 	mtk_gem = to_mtk_gem_obj(gem);
 	addr = mtk_gem->dma_addr;
@@ -136,16 +151,6 @@
 	state->pending.dirty = true;
 }
 
-static void mtk_plane_atomic_disable(struct drm_plane *plane,
-				     struct drm_plane_state *old_state)
-{
-	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
-
-	state->pending.enable = false;
-	wmb(); /* Make sure the above parameter is set before update */
-	state->pending.dirty = true;
-}
-
 static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 	.prepare_fb = drm_gem_fb_prepare_fb,
 	.atomic_check = mtk_plane_atomic_check,
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index ce91b61..6b22fd6 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1482,25 +1482,30 @@
 		dev_err(dev,
 			"Failed to get system configuration registers: %d\n",
 			ret);
-		return ret;
+		goto put_device;
 	}
 	hdmi->sys_regmap = regmap;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hdmi->regs = devm_ioremap_resource(dev, mem);
-	if (IS_ERR(hdmi->regs))
-		return PTR_ERR(hdmi->regs);
+	if (IS_ERR(hdmi->regs)) {
+		ret = PTR_ERR(hdmi->regs);
+		goto put_device;
+	}
 
 	remote = of_graph_get_remote_node(np, 1, 0);
-	if (!remote)
-		return -EINVAL;
+	if (!remote) {
+		ret = -EINVAL;
+		goto put_device;
+	}
 
 	if (!of_device_is_compatible(remote, "hdmi-connector")) {
 		hdmi->next_bridge = of_drm_find_bridge(remote);
 		if (!hdmi->next_bridge) {
 			dev_err(dev, "Waiting for external bridge\n");
 			of_node_put(remote);
-			return -EPROBE_DEFER;
+			ret = -EPROBE_DEFER;
+			goto put_device;
 		}
 	}
 
@@ -1509,7 +1514,8 @@
 		dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n",
 			remote);
 		of_node_put(remote);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_device;
 	}
 	of_node_put(remote);
 
@@ -1517,10 +1523,14 @@
 	of_node_put(i2c_np);
 	if (!hdmi->ddc_adpt) {
 		dev_err(dev, "Failed to get ddc i2c adapter by node\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_device;
 	}
 
 	return 0;
+put_device:
+	put_device(hdmi->cec_dev);
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c
index 5223498..23a74eb 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c
@@ -84,8 +84,9 @@
 	    hdmi_phy->conf->hdmi_phy_disable_tmds)
 		return &mtk_hdmi_phy_dev_ops;
 
-	dev_err(hdmi_phy->dev, "Failed to get dev ops of phy\n");
-		return NULL;
+	if (hdmi_phy)
+		dev_err(hdmi_phy->dev, "Failed to get dev ops of phy\n");
+	return NULL;
 }
 
 static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy,
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index a24f8de..61a6536 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -420,6 +420,17 @@
 	return count;
 }
 
+static void meson_drv_shutdown(struct platform_device *pdev)
+{
+	struct meson_drm *priv = dev_get_drvdata(&pdev->dev);
+
+	if (!priv)
+		return;
+
+	drm_kms_helper_poll_fini(priv->drm);
+	drm_atomic_helper_shutdown(priv->drm);
+}
+
 static int meson_drv_probe(struct platform_device *pdev)
 {
 	struct component_match *match = NULL;
@@ -469,6 +480,7 @@
 
 static struct platform_driver meson_drm_platform_driver = {
 	.probe      = meson_drv_probe,
+	.shutdown   = meson_drv_shutdown,
 	.driver     = {
 		.name	= "meson-drm",
 		.of_match_table = dt_match,
diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h
index 05fce48..f7da816 100644
--- a/drivers/gpu/drm/meson/meson_registers.h
+++ b/drivers/gpu/drm/meson/meson_registers.h
@@ -590,6 +590,11 @@
 #define VPP_WRAP_OSD3_MATRIX_PRE_OFFSET2 0x3dbc
 #define VPP_WRAP_OSD3_MATRIX_EN_CTRL 0x3dbd
 
+/* osd1 HDR */
+#define OSD1_HDR2_CTRL 0x38a0
+#define OSD1_HDR2_CTRL_VDIN0_HDR2_TOP_EN       BIT(13)
+#define OSD1_HDR2_CTRL_REG_ONLY_MAT            BIT(16)
+
 /* osd2 scaler */
 #define OSD2_VSC_PHASE_STEP 0x3d00
 #define OSD2_VSC_INI_PHASE 0x3d01
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index ac491a7..f690793 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -638,13 +638,18 @@
 		if (frac >= HDMI_FRAC_MAX_GXBB)
 			return false;
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
-		   meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL) ||
-		   meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+		   meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) {
 		/* Empiric supported min/max dividers */
 		if (m < 106 || m > 247)
 			return false;
 		if (frac >= HDMI_FRAC_MAX_GXL)
 			return false;
+	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+		/* Empiric supported min/max dividers */
+		if (m < 106 || m > 247)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_G12A)
+			return false;
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c
index 9ab27ae..1bd6b6d 100644
--- a/drivers/gpu/drm/meson/meson_venc_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c
@@ -64,6 +64,25 @@
 	},
 };
 
+static const struct meson_cvbs_mode *
+meson_cvbs_get_mode(const struct drm_display_mode *req_mode)
+{
+	int i;
+
+	for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) {
+		struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i];
+
+		if (drm_mode_match(req_mode, &meson_mode->mode,
+				   DRM_MODE_MATCH_TIMINGS |
+				   DRM_MODE_MATCH_CLOCK |
+				   DRM_MODE_MATCH_FLAGS |
+				   DRM_MODE_MATCH_3D_FLAGS))
+			return meson_mode;
+	}
+
+	return NULL;
+}
+
 /* Connector */
 
 static void meson_cvbs_connector_destroy(struct drm_connector *connector)
@@ -136,14 +155,8 @@
 					struct drm_crtc_state *crtc_state,
 					struct drm_connector_state *conn_state)
 {
-	int i;
-
-	for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) {
-		struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i];
-
-		if (drm_mode_equal(&crtc_state->mode, &meson_mode->mode))
-			return 0;
-	}
+	if (meson_cvbs_get_mode(&crtc_state->mode))
+		return 0;
 
 	return -EINVAL;
 }
@@ -191,24 +204,17 @@
 				   struct drm_display_mode *mode,
 				   struct drm_display_mode *adjusted_mode)
 {
+	const struct meson_cvbs_mode *meson_mode = meson_cvbs_get_mode(mode);
 	struct meson_venc_cvbs *meson_venc_cvbs =
 					encoder_to_meson_venc_cvbs(encoder);
 	struct meson_drm *priv = meson_venc_cvbs->priv;
-	int i;
 
-	for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) {
-		struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i];
+	if (meson_mode) {
+		meson_venci_cvbs_mode_set(priv, meson_mode->enci);
 
-		if (drm_mode_equal(mode, &meson_mode->mode)) {
-			meson_venci_cvbs_mode_set(priv,
-						  meson_mode->enci);
-
-			/* Setup 27MHz vclk2 for ENCI and VDAC */
-			meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS,
-					 MESON_VCLK_CVBS, MESON_VCLK_CVBS,
-					 MESON_VCLK_CVBS, true);
-			break;
-		}
+		/* Setup 27MHz vclk2 for ENCI and VDAC */
+		meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS, MESON_VCLK_CVBS,
+				 MESON_VCLK_CVBS, MESON_VCLK_CVBS, true);
 	}
 }
 
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 68cf2c2..3369881 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -356,9 +356,14 @@
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
 	    meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL))
 		meson_viu_load_matrix(priv);
-	else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+	else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
 		meson_viu_set_g12a_osd1_matrix(priv, RGB709_to_YUV709l_coeff,
 					       true);
+		/* fix green/pink color distortion from vendor u-boot */
+		writel_bits_relaxed(OSD1_HDR2_CTRL_REG_ONLY_MAT |
+				OSD1_HDR2_CTRL_VDIN0_HDR2_TOP_EN, 0,
+				priv->io_base + _REG(OSD1_HDR2_CTRL));
+	}
 
 	/* Initialize OSD1 fifo control register */
 	reg = VIU_OSD_DDR_PRIORITY_URGENT |
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index afd9119..c96c439 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -30,7 +30,8 @@
 static struct drm_driver driver;
 
 static const struct pci_device_id pciidlist[] = {
-	{ PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_A },
+	{ PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		G200_SE_A | MGAG200_FLAG_HW_BUG_NO_STARTADD},
 	{ PCI_VENDOR_ID_MATROX, 0x524, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_B },
 	{ PCI_VENDOR_ID_MATROX, 0x530, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_EV },
 	{ PCI_VENDOR_ID_MATROX, 0x532, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_WB },
@@ -63,6 +64,35 @@
 	DRM_VRAM_MM_FILE_OPERATIONS
 };
 
+static bool mgag200_pin_bo_at_0(const struct mga_device *mdev)
+{
+	return mdev->flags & MGAG200_FLAG_HW_BUG_NO_STARTADD;
+}
+
+int mgag200_driver_dumb_create(struct drm_file *file,
+			       struct drm_device *dev,
+			       struct drm_mode_create_dumb *args)
+{
+	struct mga_device *mdev = dev->dev_private;
+	unsigned long pg_align;
+
+	if (WARN_ONCE(!dev->vram_mm, "VRAM MM not initialized"))
+		return -EINVAL;
+
+	pg_align = 0ul;
+
+	/*
+	 * Aligning scanout buffers to the size of the video ram forces
+	 * placement at offset 0. Works around a bug where HW does not
+	 * respect 'startadd' field.
+	 */
+	if (mgag200_pin_bo_at_0(mdev))
+		pg_align = PFN_UP(mdev->mc.vram_size);
+
+	return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev,
+					     pg_align, false, args);
+}
+
 static struct drm_driver driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET,
 	.load = mgag200_driver_load,
@@ -74,7 +104,9 @@
 	.major = DRIVER_MAJOR,
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
-	DRM_GEM_VRAM_DRIVER
+	.dumb_create = mgag200_driver_dumb_create,
+	.dumb_map_offset = drm_gem_vram_driver_dumb_mmap_offset,
+	.gem_prime_mmap = drm_gem_prime_mmap,
 };
 
 static struct pci_driver mgag200_pci_driver = {
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 1c93f8d..7cc1a24 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -159,6 +159,12 @@
 	G200_EW3,
 };
 
+/* HW does not handle 'startadd' field correct. */
+#define MGAG200_FLAG_HW_BUG_NO_STARTADD	(1ul << 8)
+
+#define MGAG200_TYPE_MASK	(0x000000ff)
+#define MGAG200_FLAG_MASK	(0x00ffff00)
+
 #define IS_G200_SE(mdev) (mdev->type == G200_SE_A || mdev->type == G200_SE_B)
 
 struct mga_device {
@@ -188,6 +194,18 @@
 	u32 unique_rev_id;
 };
 
+static inline enum mga_type
+mgag200_type_from_driver_data(kernel_ulong_t driver_data)
+{
+	return (enum mga_type)(driver_data & MGAG200_TYPE_MASK);
+}
+
+static inline unsigned long
+mgag200_flags_from_driver_data(kernel_ulong_t driver_data)
+{
+	return driver_data & MGAG200_FLAG_MASK;
+}
+
 				/* mgag200_mode.c */
 int mgag200_modeset_init(struct mga_device *mdev);
 void mgag200_modeset_fini(struct mga_device *mdev);
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index a977333..388212b 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -94,7 +94,8 @@
 	struct mga_device *mdev = dev->dev_private;
 	int ret, option;
 
-	mdev->type = flags;
+	mdev->flags = mgag200_flags_from_driver_data(flags);
+	mdev->type = mgag200_type_from_driver_data(flags);
 
 	/* Hardcode the number of CRTCs to 1 */
 	mdev->num_crtc = 1;
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
index 1f83bc1..80f3b1d 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -164,6 +164,11 @@
 	if (ret)
 		return ret;
 
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* NOTE: PM4/micro-engine firmware registers look to be the same
 	 * for a2xx and a3xx.. we could possibly push that part down to
 	 * adreno_gpu base class.  Or push both PM4 and PFP but
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 5f7e980..eeba2de 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -215,6 +215,16 @@
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* setup access protection: */
 	gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007);
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index ab2b752..05cfa81 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -265,6 +265,16 @@
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_A4XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* Load PM4: */
 	ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data);
 	len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index e9c55d1..e3579e5 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -581,8 +581,6 @@
 	if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI)
 		gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8));
 
-	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0xc0200100);
-
 	/* Enable USE_RETENTION_FLOPS */
 	gpu_write(gpu, REG_A5XX_CP_CHICKEN_DBG, 0x02000000);
 
@@ -677,14 +675,21 @@
 	if (ret)
 		return ret;
 
-	a5xx_preempt_hw_init(gpu);
-
 	a5xx_gpmu_ucode_init(gpu);
 
 	ret = a5xx_ucode_init(gpu);
 	if (ret)
 		return ret;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	a5xx_preempt_hw_init(gpu);
+
 	/* Disable the interrupts through the initial bringup stage */
 	gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK);
 
@@ -726,11 +731,18 @@
 		gpu->funcs->flush(gpu, gpu->rb[0]);
 		if (!a5xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	} else {
+		return ret;
 	}
 
 	/* Last step - yield the ringbuffer */
@@ -1119,8 +1131,8 @@
 
 static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 {
-	*value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO,
-		REG_A5XX_RBBM_PERFCTR_CP_0_HI);
+	*value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO,
+		REG_A5XX_RBBM_ALWAYSON_COUNTER_HI);
 
 	return 0;
 }
@@ -1352,6 +1364,10 @@
 {
 	u64 busy_cycles, busy_time;
 
+	/* Only read the gpu busy if the hardware is already active */
+	if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
+		return 0;
+
 	busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
 			REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
 
@@ -1360,6 +1376,8 @@
 
 	gpu->devfreq.busy_cycles = busy_cycles;
 
+	pm_runtime_put(&gpu->pdev->dev);
+
 	if (WARN_ON(busy_time > ~0LU))
 		return ~0LU;
 
@@ -1394,18 +1412,31 @@
 static void check_speed_bin(struct device *dev)
 {
 	struct nvmem_cell *cell;
-	u32 bin, val;
+	u32 val;
+
+	/*
+	 * If the OPP table specifies a opp-supported-hw property then we have
+	 * to set something with dev_pm_opp_set_supported_hw() or the table
+	 * doesn't get populated so pick an arbitrary value that should
+	 * ensure the default frequencies are selected but not conflict with any
+	 * actual bins
+	 */
+	val = 0x80;
 
 	cell = nvmem_cell_get(dev, "speed_bin");
 
-	/* If a nvmem cell isn't defined, nothing to do */
-	if (IS_ERR(cell))
-		return;
+	if (!IS_ERR(cell)) {
+		void *buf = nvmem_cell_read(cell, NULL);
 
-	bin = *((u32 *) nvmem_cell_read(cell, NULL));
-	nvmem_cell_put(cell);
+		if (!IS_ERR(buf)) {
+			u8 bin = *((u8 *) buf);
 
-	val = (1 << bin);
+			val = (1 << bin);
+			kfree(buf);
+		}
+
+		nvmem_cell_put(cell);
+	}
 
 	dev_pm_opp_set_supported_hw(dev, &val, 1);
 }
@@ -1438,7 +1469,8 @@
 
 	check_speed_bin(&pdev->dev);
 
-	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4);
+	/* Restricting nr_rings to 1 to temporarily disable preemption */
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a5xx_destroy(&(a5xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index a3a06db..ee3ff32 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -300,7 +300,7 @@
 	/* Set up the limits management */
 	if (adreno_is_a530(adreno_gpu))
 		a530_lm_setup(gpu);
-	else
+	else if (adreno_is_a540(adreno_gpu))
 		a540_lm_setup(gpu);
 
 	/* Set up SP/TP power collpase */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 85f14fe..40431a0 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -107,6 +107,13 @@
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	int ret;
 
+	/*
+	 * This can get called from devfreq while the hardware is idle. Don't
+	 * bring up the power if it isn't already active
+	 */
+	if (pm_runtime_get_if_in_use(gmu->dev) == 0)
+		return;
+
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0);
 
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING,
@@ -133,6 +140,7 @@
 	 * for now leave it at max so that the performance is nominal.
 	 */
 	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+	pm_runtime_put(gmu->dev);
 }
 
 void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
@@ -191,12 +199,22 @@
 {
 	int ret;
 	u32 val;
+	u32 mask, reset_val;
+
+	val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8);
+	if (val <= 0x20010004) {
+		mask = 0xffffffff;
+		reset_val = 0xbabeface;
+	} else {
+		mask = 0x1ff;
+		reset_val = 0x100;
+	}
 
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0);
 
 	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val,
-		val == 0xbabeface, 100, 10000);
+		(val & mask) == reset_val, 100, 10000);
 
 	if (ret)
 		DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n");
@@ -705,10 +723,19 @@
 	/* Turn on the resources */
 	pm_runtime_get_sync(gmu->dev);
 
+	/*
+	 * "enable" the GX power domain which won't actually do anything but it
+	 * will make sure that the refcounting is correct in case we need to
+	 * bring down the GX after a GMU failure
+	 */
+	if (!IS_ERR_OR_NULL(gmu->gxpd))
+		pm_runtime_get_sync(gmu->gxpd);
+
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
+		pm_runtime_put(gmu->gxpd);
 		pm_runtime_put(gmu->dev);
 		return ret;
 	}
@@ -744,19 +771,12 @@
 	/* Set the GPU to the highest power frequency */
 	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
 
-	/*
-	 * "enable" the GX power domain which won't actually do anything but it
-	 * will make sure that the refcounting is correct in case we need to
-	 * bring down the GX after a GMU failure
-	 */
-	if (!IS_ERR_OR_NULL(gmu->gxpd))
-		pm_runtime_get(gmu->gxpd);
-
 out:
 	/* On failure, shut down the GMU to leave it in a good state */
 	if (ret) {
 		disable_irq(gmu->gmu_irq);
 		a6xx_rpmh_stop(gmu);
+		pm_runtime_put(gmu->gxpd);
 		pm_runtime_put(gmu->dev);
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index dc8ec2c..df2656e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -512,6 +512,13 @@
 	if (ret)
 		goto out;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A6XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
@@ -537,12 +544,19 @@
 		a6xx_flush(gpu, gpu->rb[0]);
 		if (!a6xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
 		ret = 0;
+	} else {
+		return ret;
 	}
 
 out:
@@ -759,8 +773,8 @@
 	/* Force the GPU power on so we can read this register */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
-	*value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
-		REG_A6XX_RBBM_PERFCTR_CP_0_HI);
+	*value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
+		REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
 
 	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 	return 0;
@@ -796,6 +810,11 @@
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	u64 busy_cycles, busy_time;
 
+
+	/* Only read the gpu busy if the hardware is already active */
+	if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
+		return 0;
+
 	busy_cycles = gmu_read64(&a6xx_gpu->gmu,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
@@ -805,6 +824,8 @@
 
 	gpu->devfreq.busy_cycles = busy_cycles;
 
+	pm_runtime_put(a6xx_gpu->gmu.dev);
+
 	if (WARN_ON(busy_time > ~0LU))
 		return ~0LU;
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index e686331..dfcbb2b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -352,26 +352,26 @@
 		cxdbg = ioremap(res->start, resource_size(res));
 
 	if (cxdbg) {
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLT,
 			A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf));
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLM,
 			A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf));
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_0, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_1, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_2, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_3, 0);
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_0,
 			0x76543210);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1,
 			0xFEDCBA98);
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_0, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_1, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_2, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_3, 0);
 	}
 
 	a6xx_state->debugbus = state_kcalloc(a6xx_state,
@@ -834,7 +834,7 @@
 	int i;
 
 	a6xx_state->indexed_regs = state_kcalloc(a6xx_state, count,
-		sizeof(a6xx_state->indexed_regs));
+		sizeof(*a6xx_state->indexed_regs));
 	if (!a6xx_state->indexed_regs)
 		return;
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 048c8be..3802ad3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -350,30 +350,10 @@
 		ring->next = ring->start;
 
 		/* reset completed fence seqno: */
-		ring->memptrs->fence = ring->seqno;
+		ring->memptrs->fence = ring->fctx->completed_fence;
 		ring->memptrs->rptr = 0;
 	}
 
-	/*
-	 * Setup REG_CP_RB_CNTL.  The same value is used across targets (with
-	 * the excpetion of A430 that disables the RPTR shadow) - the cacluation
-	 * for the ringbuffer size and block size is moved to msm_gpu.h for the
-	 * pre-processor to deal with and the A430 variant is ORed in here
-	 */
-	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
-		MSM_GPU_RB_CNTL_DEFAULT |
-		(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
-
-	/* Setup ringbuffer address - use ringbuffer[0] for GPU init */
-	adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE,
-		REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova);
-
-	if (!adreno_is_a430(adreno_gpu)) {
-		adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR,
-			REG_ADRENO_CP_RB_RPTR_ADDR_HI,
-			rbmemptr(gpu->rb[0], rptr));
-	}
-
 	return 0;
 }
 
@@ -381,11 +361,8 @@
 static uint32_t get_rptr(struct adreno_gpu *adreno_gpu,
 		struct msm_ringbuffer *ring)
 {
-	if (adreno_is_a430(adreno_gpu))
-		return ring->memptrs->rptr = adreno_gpu_read(
-			adreno_gpu, REG_ADRENO_CP_RB_RPTR);
-	else
-		return ring->memptrs->rptr;
+	return ring->memptrs->rptr = adreno_gpu_read(
+		adreno_gpu, REG_ADRENO_CP_RB_RPTR);
 }
 
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index ce59adf..4aed5e9 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -381,7 +381,7 @@
 	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
 
 	if (!fevent) {
-		DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event);
+		DRM_ERROR_RATELIMITED("crtc%d event %d overflow\n", crtc->base.id, event);
 		return;
 	}
 
@@ -819,7 +819,7 @@
 	struct drm_plane *plane;
 	struct drm_display_mode *mode;
 
-	int cnt = 0, rc = 0, mixer_width, i, z_pos;
+	int cnt = 0, rc = 0, mixer_width = 0, i, z_pos;
 
 	struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2];
 	int multirect_count = 0;
@@ -852,9 +852,11 @@
 
 	memset(pipe_staged, 0, sizeof(pipe_staged));
 
-	mixer_width = mode->hdisplay / cstate->num_mixers;
+	if (cstate->num_mixers) {
+		mixer_width = mode->hdisplay / cstate->num_mixers;
 
-	_dpu_crtc_setup_lm_bounds(crtc, state);
+		_dpu_crtc_setup_lm_bounds(crtc, state);
+	}
 
 	crtc_rect.x2 = mode->hdisplay;
 	crtc_rect.y2 = mode->vdisplay;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index d82ea99..99d449c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2185,7 +2185,6 @@
 
 	dpu_enc = to_dpu_encoder_virt(enc);
 
-	mutex_init(&dpu_enc->enc_lock);
 	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info);
 	if (ret)
 		goto fail;
@@ -2200,7 +2199,6 @@
 				0);
 
 
-	mutex_init(&dpu_enc->rc_lock);
 	INIT_DELAYED_WORK(&dpu_enc->delayed_off_work,
 			dpu_encoder_off_work);
 	dpu_enc->idle_timeout = IDLE_TIMEOUT;
@@ -2232,7 +2230,7 @@
 
 	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
 	if (!dpu_enc)
-		return ERR_PTR(ENOMEM);
+		return ERR_PTR(-ENOMEM);
 
 	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
 			drm_enc_mode, NULL);
@@ -2245,6 +2243,8 @@
 
 	spin_lock_init(&dpu_enc->enc_spinlock);
 	dpu_enc->enabled = false;
+	mutex_init(&dpu_enc->enc_lock);
+	mutex_init(&dpu_enc->rc_lock);
 
 	return &dpu_enc->base;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 24ab624..6f420cc 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -255,13 +255,13 @@
 
 	INTERLEAVED_RGB_FMT(RGB565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
 	INTERLEAVED_RGB_FMT(BGR565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index 179e8d5..a08ca7a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -281,10 +281,12 @@
 	int i;
 
 	for (i = 0; i < ctx->mixer_count; i++) {
-		DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0);
+		enum dpu_lm mixer_id = ctx->mixer_hw_caps[i].id;
+
+		DPU_REG_WRITE(c, CTL_LAYER(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(mixer_id), 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 58d5acb..b984baf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -853,9 +853,9 @@
 		crtc_state = drm_atomic_get_new_crtc_state(state->state,
 							   state->crtc);
 
-	min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxdwnscale);
+	min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxupscale);
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, min_scale,
-					  pdpu->pipe_sblk->maxupscale << 16,
+					  pdpu->pipe_sblk->maxdwnscale << 16,
 					  true, true);
 	if (ret) {
 		DPU_ERROR_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
index 772f075..aaf2f26 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
@@ -121,7 +121,7 @@
 	if (mdp4_dsi_encoder->enabled)
 		return;
 
-	 mdp4_crtc_set_config(encoder->crtc,
+	mdp4_crtc_set_config(encoder->crtc,
 			MDP4_DMA_CONFIG_PACK_ALIGN_MSB |
 			MDP4_DMA_CONFIG_DEFLKR_EN |
 			MDP4_DMA_CONFIG_DITHER_EN |
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 50711cc..4f0c6d5 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -88,8 +88,6 @@
 	if (mdp4_kms->rev > 1)
 		mdp4_write(mdp4_kms, REG_MDP4_RESET_STATUS, 1);
 
-	dev->mode_config.allow_fb_modifiers = true;
-
 out:
 	pm_runtime_put_sync(dev->dev);
 
@@ -110,13 +108,6 @@
 
 static void mdp4_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
-	int i;
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *crtc_state;
-
-	/* see 119ecb7fd */
-	for_each_new_crtc_in_state(state, crtc, crtc_state, i)
-		drm_crtc_vblank_get(crtc);
 }
 
 static void mdp4_flush_commit(struct msm_kms *kms, unsigned crtc_mask)
@@ -135,12 +126,6 @@
 
 static void mdp4_complete_commit(struct msm_kms *kms, unsigned crtc_mask)
 {
-	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
-	struct drm_crtc *crtc;
-
-	/* see 119ecb7fd */
-	for_each_crtc_mask(mdp4_kms->dev, crtc, crtc_mask)
-		drm_crtc_vblank_put(crtc);
 }
 
 static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
@@ -420,6 +405,7 @@
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct mdp4_platform_config *config = mdp4_get_config(pdev);
+	struct msm_drm_private *priv = dev->dev_private;
 	struct mdp4_kms *mdp4_kms;
 	struct msm_kms *kms = NULL;
 	struct msm_gem_address_space *aspace;
@@ -434,7 +420,8 @@
 
 	mdp_kms_init(&mdp4_kms->base, &kms_funcs);
 
-	kms = &mdp4_kms->base.base;
+	priv->kms = &mdp4_kms->base.base;
+	kms = priv->kms;
 
 	mdp4_kms->dev = dev;
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index da3cc1d..ee1dbb2 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -347,6 +347,12 @@
 	return mdp4_plane->pipe;
 }
 
+static const uint64_t supported_format_modifiers[] = {
+	DRM_FORMAT_MOD_SAMSUNG_64_32_TILE,
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 /* initialize plane */
 struct drm_plane *mdp4_plane_init(struct drm_device *dev,
 		enum mdp4_pipe pipe_id, bool private_plane)
@@ -375,7 +381,7 @@
 	type = private_plane ? DRM_PLANE_TYPE_PRIMARY : DRM_PLANE_TYPE_OVERLAY;
 	ret = drm_universal_plane_init(dev, plane, 0xff, &mdp4_plane_funcs,
 				 mdp4_plane->formats, mdp4_plane->nformats,
-				 NULL, type, NULL);
+				 supported_format_modifiers, type, NULL);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c
index eeef41f..0425400 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c
@@ -41,7 +41,7 @@
 {
 	struct mdp5_kms *mdp5_kms = get_kms(encoder);
 	struct device *dev = encoder->dev->dev;
-	u32 total_lines_x100, vclks_line, cfg;
+	u32 total_lines, vclks_line, cfg;
 	long vsync_clk_speed;
 	struct mdp5_hw_mixer *mixer = mdp5_crtc_get_mixer(encoder->crtc);
 	int pp_id = mixer->pp;
@@ -51,8 +51,8 @@
 		return -EINVAL;
 	}
 
-	total_lines_x100 = mode->vtotal * drm_mode_vrefresh(mode);
-	if (!total_lines_x100) {
+	total_lines = mode->vtotal * drm_mode_vrefresh(mode);
+	if (!total_lines) {
 		DRM_DEV_ERROR(dev, "%s: vtotal(%d) or vrefresh(%d) is 0\n",
 			      __func__, mode->vtotal, drm_mode_vrefresh(mode));
 		return -EINVAL;
@@ -64,15 +64,23 @@
 							vsync_clk_speed);
 		return -EINVAL;
 	}
-	vclks_line = vsync_clk_speed * 100 / total_lines_x100;
+	vclks_line = vsync_clk_speed / total_lines;
 
 	cfg = MDP5_PP_SYNC_CONFIG_VSYNC_COUNTER_EN
 		| MDP5_PP_SYNC_CONFIG_VSYNC_IN_EN;
 	cfg |= MDP5_PP_SYNC_CONFIG_VSYNC_COUNT(vclks_line);
 
+	/*
+	 * Tearcheck emits a blanking signal every vclks_line * vtotal * 2 ticks on
+	 * the vsync_clk equating to roughly half the desired panel refresh rate.
+	 * This is only necessary as stability fallback if interrupts from the
+	 * panel arrive too late or not at all, but is currently used by default
+	 * because these panel interrupts are not wired up yet.
+	 */
 	mdp5_write(mdp5_kms, REG_MDP5_PP_SYNC_CONFIG_VSYNC(pp_id), cfg);
 	mdp5_write(mdp5_kms,
-		REG_MDP5_PP_SYNC_CONFIG_HEIGHT(pp_id), 0xfff0);
+		REG_MDP5_PP_SYNC_CONFIG_HEIGHT(pp_id), (2 * mode->vtotal));
+
 	mdp5_write(mdp5_kms,
 		REG_MDP5_PP_VSYNC_INIT_VAL(pp_id), mode->vdisplay);
 	mdp5_write(mdp5_kms, REG_MDP5_PP_RD_PTR_IRQ(pp_id), mode->vdisplay + 1);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index eb0b4b7..3951468 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1099,7 +1099,7 @@
 	struct mdp5_crtc *mdp5_crtc = container_of(irq, struct mdp5_crtc,
 								pp_done);
 
-	complete(&mdp5_crtc->pp_completion);
+	complete_all(&mdp5_crtc->pp_completion);
 }
 
 static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc)
@@ -1112,8 +1112,8 @@
 	ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion,
 						msecs_to_jiffies(50));
 	if (ret == 0)
-		dev_warn(dev->dev, "pp done time out, lm=%d\n",
-			 mdp5_cstate->pipeline.mixer->lm);
+		dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n",
+				     mdp5_cstate->pipeline.mixer->lm);
 }
 
 static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 91cd76a..77823cc 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -1037,7 +1037,8 @@
 
 	return 0;
 fail:
-	mdp5_destroy(pdev);
+	if (mdp5_kms)
+		mdp5_destroy(pdev);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 55ea4bc..0d37ae5 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -26,8 +26,10 @@
 	}
 
 	phy_pdev = of_find_device_by_node(phy_node);
-	if (phy_pdev)
+	if (phy_pdev) {
 		msm_dsi->phy = platform_get_drvdata(phy_pdev);
+		msm_dsi->phy_dev = &phy_pdev->dev;
+	}
 
 	of_node_put(phy_node);
 
@@ -36,8 +38,6 @@
 		return -EPROBE_DEFER;
 	}
 
-	msm_dsi->phy_dev = get_device(&phy_pdev->dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 271aa7b..7312794 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -336,7 +336,7 @@
 	return num;
 }
 
-static int dsi_mgr_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	int id = dsi_mgr_connector_get_id(connector);
@@ -479,6 +479,7 @@
 	struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
+	struct msm_dsi_pll *src_pll;
 	bool is_dual_dsi = IS_DUAL_DSI();
 	int ret;
 
@@ -519,6 +520,10 @@
 								id, ret);
 	}
 
+	/* Save PLL status if it is a clock source */
+	src_pll = msm_dsi_phy_get_pll(msm_dsi->phy);
+	msm_dsi_pll_save_state(src_pll);
+
 	ret = msm_dsi_host_power_off(host);
 	if (ret)
 		pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 3522863..2151922 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -724,10 +724,6 @@
 	if (!phy || !phy->cfg->ops.disable)
 		return;
 
-	/* Save PLL status if it is a clock source */
-	if (phy->usecase != MSM_DSI_PHY_SLAVE)
-		msm_dsi_pll_save_state(phy->pll);
-
 	phy->cfg->ops.disable(phy);
 
 	dsi_phy_regulator_disable(phy);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
index 1afb7c5..eca86bf 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
@@ -139,7 +139,7 @@
 		.disable = dsi_20nm_phy_disable,
 		.init = msm_dsi_phy_init_common,
 	},
-	.io_start = { 0xfd998300, 0xfd9a0300 },
+	.io_start = { 0xfd998500, 0xfd9a0500 },
 	.num_dsi_phy = 2,
 };
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index 8f6100d..33033b9 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -411,6 +411,12 @@
 	if (pll_10nm->slave)
 		dsi_pll_enable_pll_bias(pll_10nm->slave);
 
+	rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
+	if (rc) {
+		pr_err("vco_set_rate failed, rc=%d\n", rc);
+		return rc;
+	}
+
 	/* Start PLL */
 	pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL,
 		  0x01);
@@ -553,6 +559,7 @@
 	struct pll_10nm_cached_state *cached = &pll_10nm->cached_state;
 	void __iomem *phy_base = pll_10nm->phy_cmn_mmio;
 	u32 val;
+	int ret;
 
 	val = pll_read(pll_10nm->mmio + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE);
 	val &= ~0x3;
@@ -567,6 +574,13 @@
 	val |= cached->pll_mux;
 	pll_write(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, val);
 
+	ret = dsi_pll_10nm_vco_set_rate(&pll->clk_hw, pll_10nm->vco_current_rate, pll_10nm->vco_ref_clk_rate);
+	if (ret) {
+		DRM_DEV_ERROR(&pll_10nm->pdev->dev,
+			"restore vco rate failed. ret=%d\n", ret);
+		return ret;
+	}
+
 	DBG("DSI PLL%d", pll_10nm->id);
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 5ccfad7..561bfa4 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -27,6 +27,34 @@
 	return msm_framebuffer_prepare(new_state->fb, kms->aspace);
 }
 
+/*
+ * Helpers to control vblanks while we flush.. basically just to ensure
+ * that vblank accounting is switched on, so we get valid seqn/timestamp
+ * on pageflip events (if requested)
+ */
+
+static void vblank_get(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+		drm_crtc_vblank_get(crtc);
+	}
+}
+
+static void vblank_put(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+		drm_crtc_vblank_put(crtc);
+	}
+}
+
 static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 {
 	unsigned crtc_mask = BIT(crtc_idx);
@@ -44,6 +72,8 @@
 
 	kms->funcs->enable_commit(kms);
 
+	vblank_get(kms, crtc_mask);
+
 	/*
 	 * Flush hardware updates:
 	 */
@@ -58,6 +88,8 @@
 	kms->funcs->wait_flush(kms, crtc_mask);
 	trace_msm_atomic_wait_flush_finish(crtc_mask);
 
+	vblank_put(kms, crtc_mask);
+
 	mutex_lock(&kms->commit_lock);
 	kms->funcs->complete_commit(kms, crtc_mask);
 	mutex_unlock(&kms->commit_lock);
@@ -221,6 +253,8 @@
 	 */
 	kms->pending_crtc_mask &= ~crtc_mask;
 
+	vblank_get(kms, crtc_mask);
+
 	/*
 	 * Flush hardware updates:
 	 */
@@ -235,6 +269,8 @@
 	kms->funcs->wait_flush(kms, crtc_mask);
 	trace_msm_atomic_wait_flush_finish(crtc_mask);
 
+	vblank_put(kms, crtc_mask);
+
 	mutex_lock(&kms->commit_lock);
 	kms->funcs->complete_commit(kms, crtc_mask);
 	mutex_unlock(&kms->commit_lock);
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 6be8795..1c74381 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -47,12 +47,8 @@
 	struct msm_gpu_show_priv *show_priv = m->private;
 	struct msm_drm_private *priv = show_priv->dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
-	int ret;
 
-	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
-	if (ret)
-		return ret;
-
+	mutex_lock(&show_priv->dev->struct_mutex);
 	gpu->funcs->gpu_state_put(show_priv->state);
 	mutex_unlock(&show_priv->dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index c84f0a8..7443df7 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -432,14 +432,24 @@
 
 	drm_mode_config_init(ddev);
 
+	ret = msm_init_vram(ddev);
+	if (ret)
+		goto err_destroy_mdss;
+
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
 	if (ret)
 		goto err_destroy_mdss;
 
-	ret = msm_init_vram(ddev);
-	if (ret)
-		goto err_msm_uninit;
+	if (!dev->dma_parms) {
+		dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms),
+					      GFP_KERNEL);
+		if (!dev->dma_parms) {
+			ret = -ENOMEM;
+			goto err_msm_uninit;
+		}
+	}
+	dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
 
 	msm_gem_shrinker_init(ddev);
 
@@ -557,6 +567,7 @@
 	kfree(priv);
 err_put_drm_dev:
 	drm_dev_put(ddev);
+	platform_set_drvdata(pdev, NULL);
 	return ret;
 }
 
@@ -1313,6 +1324,17 @@
 	return 0;
 }
 
+static void msm_pdev_shutdown(struct platform_device *pdev)
+{
+	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct msm_drm_private *priv = drm ? drm->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return;
+
+	drm_atomic_helper_shutdown(drm);
+}
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
 	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
@@ -1324,6 +1346,7 @@
 static struct platform_driver msm_platform_driver = {
 	.probe      = msm_pdev_probe,
 	.remove     = msm_pdev_remove,
+	.shutdown   = msm_pdev_shutdown,
 	.driver     = {
 		.name   = "msm",
 		.of_match_table = dt_match,
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index ad27036..cd59a59 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -45,7 +45,7 @@
 	int ret;
 
 	if (fence > fctx->last_fence) {
-		DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n",
+		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
 				fctx->name, fence, fctx->last_fence);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 5a6a79f..d92a0ff 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -977,10 +977,8 @@
 
 static int msm_gem_new_impl(struct drm_device *dev,
 		uint32_t size, uint32_t flags,
-		struct drm_gem_object **obj,
-		bool struct_mutex_locked)
+		struct drm_gem_object **obj)
 {
-	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
 
 	switch (flags & MSM_BO_CACHE_MASK) {
@@ -1006,15 +1004,6 @@
 	INIT_LIST_HEAD(&msm_obj->submit_entry);
 	INIT_LIST_HEAD(&msm_obj->vmas);
 
-	if (struct_mutex_locked) {
-		WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-	} else {
-		mutex_lock(&dev->struct_mutex);
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-		mutex_unlock(&dev->struct_mutex);
-	}
-
 	*obj = &msm_obj->base;
 
 	return 0;
@@ -1024,6 +1013,7 @@
 		uint32_t size, uint32_t flags, bool struct_mutex_locked)
 {
 	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gem_object *msm_obj;
 	struct drm_gem_object *obj = NULL;
 	bool use_vram = false;
 	int ret;
@@ -1044,14 +1034,15 @@
 	if (size == 0)
 		return ERR_PTR(-EINVAL);
 
-	ret = msm_gem_new_impl(dev, size, flags, &obj, struct_mutex_locked);
+	ret = msm_gem_new_impl(dev, size, flags, &obj);
 	if (ret)
 		goto fail;
 
+	msm_obj = to_msm_bo(obj);
+
 	if (use_vram) {
 		struct msm_gem_vma *vma;
 		struct page **pages;
-		struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 		mutex_lock(&msm_obj->lock);
 
@@ -1086,6 +1077,15 @@
 		mapping_set_gfp_mask(obj->filp->f_mapping, GFP_HIGHUSER);
 	}
 
+	if (struct_mutex_locked) {
+		WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	} else {
+		mutex_lock(&dev->struct_mutex);
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+		mutex_unlock(&dev->struct_mutex);
+	}
+
 	return obj;
 
 fail:
@@ -1108,6 +1108,7 @@
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt)
 {
+	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
 	struct drm_gem_object *obj;
 	uint32_t size;
@@ -1121,7 +1122,7 @@
 
 	size = PAGE_ALIGN(dmabuf->size);
 
-	ret = msm_gem_new_impl(dev, size, MSM_BO_WC, &obj, false);
+	ret = msm_gem_new_impl(dev, size, MSM_BO_WC, &obj);
 	if (ret)
 		goto fail;
 
@@ -1146,6 +1147,11 @@
 	}
 
 	mutex_unlock(&msm_obj->lock);
+
+	mutex_lock(&dev->struct_mutex);
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	mutex_unlock(&dev->struct_mutex);
+
 	return obj;
 
 fail:
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index a052364..edd45f4 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -16,6 +16,7 @@
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/devcoredump.h>
+#include <linux/sched/task.h>
 
 /*
  * Power Management:
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index e397c44..39ecb5a 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -27,7 +27,8 @@
 	ring->id = id;
 
 	ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ,
-		MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova);
+		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo,
+		&ring->iova);
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 001fbf5..a1d94be 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -71,8 +71,10 @@
 	queue->flags = flags;
 
 	if (priv->gpu) {
-		if (prio >= priv->gpu->nr_rings)
+		if (prio >= priv->gpu->nr_rings) {
+			kfree(queue);
 			return -EINVAL;
+		}
 
 		queue->prio = prio;
 	}
diff --git a/drivers/gpu/drm/mxsfb/Kconfig b/drivers/gpu/drm/mxsfb/Kconfig
index 0dca8f2..33916b7 100644
--- a/drivers/gpu/drm/mxsfb/Kconfig
+++ b/drivers/gpu/drm/mxsfb/Kconfig
@@ -10,7 +10,6 @@
 	depends on COMMON_CLK
 	select DRM_MXS
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_PANEL
 	help
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index e850633..1694a7d 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -26,6 +26,7 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_irq.h>
@@ -87,8 +88,26 @@
 		clk_disable_unprepare(mxsfb->clk_axi);
 }
 
+static struct drm_framebuffer *
+mxsfb_fb_create(struct drm_device *dev, struct drm_file *file_priv,
+		const struct drm_mode_fb_cmd2 *mode_cmd)
+{
+	const struct drm_format_info *info;
+
+	info = drm_get_format_info(dev, mode_cmd);
+	if (!info)
+		return ERR_PTR(-EINVAL);
+
+	if (mode_cmd->width * info->cpp[0] != mode_cmd->pitches[0]) {
+		dev_dbg(dev->dev, "Invalid pitch: fb width must match pitch\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return drm_gem_fb_create(dev, file_priv, mode_cmd);
+}
+
 static const struct drm_mode_config_funcs mxsfb_mode_config_funcs = {
-	.fb_create		= drm_gem_fb_create,
+	.fb_create		= mxsfb_fb_create,
 	.atomic_check		= drm_atomic_helper_check,
 	.atomic_commit		= drm_atomic_helper_commit,
 };
diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h
index 43df86c..24f7700 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/atom.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h
@@ -114,6 +114,7 @@
 		u8 nhsync:1;
 		u8 nvsync:1;
 		u8 depth:4;
+		u8 bpc;
 	} or;
 
 	/* Currently only used for MST */
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b46be8a..daa79d3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -132,7 +132,7 @@
 
 int
 nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
-		 const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
+		 const s32 *oclass, u8 head, void *data, u32 size, s64 syncbuf,
 		 struct nv50_dmac *dmac)
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
@@ -167,7 +167,7 @@
 	if (ret)
 		return ret;
 
-	if (!syncbuf)
+	if (syncbuf < 0)
 		return 0;
 
 	ret = nvif_object_init(&dmac->base.user, 0xf0000000, NV_DMA_IN_MEMORY,
@@ -326,9 +326,9 @@
 			 * same size as the native one (e.g. different
 			 * refresh rate)
 			 */
-			if (adjusted_mode->hdisplay == native_mode->hdisplay &&
-			    adjusted_mode->vdisplay == native_mode->vdisplay &&
-			    adjusted_mode->type & DRM_MODE_TYPE_DRIVER)
+			if (mode->hdisplay == native_mode->hdisplay &&
+			    mode->vdisplay == native_mode->vdisplay &&
+			    mode->type & DRM_MODE_TYPE_DRIVER)
 				break;
 			mode = native_mode;
 			asyc->scaler.full = true;
@@ -353,10 +353,20 @@
 		       struct drm_crtc_state *crtc_state,
 		       struct drm_connector_state *conn_state)
 {
-	struct nouveau_connector *nv_connector =
-		nouveau_connector(conn_state->connector);
-	return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
-					   nv_connector->native_mode);
+	struct drm_connector *connector = conn_state->connector;
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
+	struct nv50_head_atom *asyh = nv50_head_atom(crtc_state);
+	int ret;
+
+	ret = nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
+					  nv_connector->native_mode);
+	if (ret)
+		return ret;
+
+	if (crtc_state->mode_changed || crtc_state->connectors_changed)
+		asyh->or.bpc = connector->display_info.bpc;
+
+	return 0;
 }
 
 /******************************************************************************
@@ -770,32 +780,54 @@
 	struct nv50_mstm *mstm = mstc->mstm;
 	struct nv50_head_atom *asyh = nv50_head_atom(crtc_state);
 	int slots;
+	int ret;
 
-	if (crtc_state->mode_changed || crtc_state->connectors_changed) {
+	ret = nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
+					  mstc->native);
+	if (ret)
+		return ret;
+
+	if (!crtc_state->mode_changed && !crtc_state->connectors_changed)
+		return 0;
+
+	/*
+	 * When restoring duplicated states, we need to make sure that the bw
+	 * remains the same and avoid recalculating it, as the connector's bpc
+	 * may have changed after the state was duplicated
+	 */
+	if (!state->duplicated) {
+		const int clock = crtc_state->adjusted_mode.clock;
+
 		/*
-		 * When restoring duplicated states, we need to make sure that
-		 * the bw remains the same and avoid recalculating it, as the
-		 * connector's bpc may have changed after the state was
-		 * duplicated
+		 * XXX: Since we don't use HDR in userspace quite yet, limit
+		 * the bpc to 8 to save bandwidth on the topology. In the
+		 * future, we'll want to properly fix this by dynamically
+		 * selecting the highest possible bpc that would fit in the
+		 * topology
 		 */
-		if (!state->duplicated) {
-			const int bpp = connector->display_info.bpc * 3;
-			const int clock = crtc_state->adjusted_mode.clock;
-
-			asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, bpp);
-		}
-
-		slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr,
-						      mstc->port,
-						      asyh->dp.pbn);
-		if (slots < 0)
-			return slots;
-
-		asyh->dp.tu = slots;
+		asyh->or.bpc = min(connector->display_info.bpc, 8U);
+		asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3);
 	}
 
-	return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state,
-					   mstc->native);
+	slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port,
+					      asyh->dp.pbn);
+	if (slots < 0)
+		return slots;
+
+	asyh->dp.tu = slots;
+
+	return 0;
+}
+
+static u8
+nv50_dp_bpc_to_depth(unsigned int bpc)
+{
+	switch (bpc) {
+	case  6: return 0x2;
+	case  8: return 0x5;
+	case 10: /* fall-through */
+	default: return 0x6;
+	}
 }
 
 static void
@@ -808,7 +840,7 @@
 	struct nv50_mstm *mstm = NULL;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
-	u8 proto, depth;
+	u8 proto;
 	bool r;
 
 	drm_connector_list_iter_begin(encoder->dev, &conn_iter);
@@ -837,14 +869,8 @@
 	else
 		proto = 0x9;
 
-	switch (mstc->connector.display_info.bpc) {
-	case  6: depth = 0x2; break;
-	case  8: depth = 0x5; break;
-	case 10:
-	default: depth = 0x6; break;
-	}
-
-	mstm->outp->update(mstm->outp, head->base.index, armh, proto, depth);
+	mstm->outp->update(mstm->outp, head->base.index, armh, proto,
+			   nv50_dp_bpc_to_depth(armh->or.bpc));
 
 	msto->head = head;
 	msto->mstc = mstc;
@@ -1006,8 +1032,10 @@
 		return connector_status_disconnected;
 
 	ret = pm_runtime_get_sync(connector->dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(connector->dev->dev);
 		return connector_status_disconnected;
+	}
 
 	conn_status = drm_dp_mst_detect_port(connector, mstc->port->mgr,
 					     mstc->port);
@@ -1498,20 +1526,14 @@
 					lvds.lvds.script |= 0x0200;
 			}
 
-			if (nv_connector->base.display_info.bpc == 8)
+			if (asyh->or.bpc == 8)
 				lvds.lvds.script |= 0x0200;
 		}
 
 		nvif_mthd(&disp->disp->object, 0, &lvds, sizeof(lvds));
 		break;
 	case DCB_OUTPUT_DP:
-		if (nv_connector->base.display_info.bpc == 6)
-			depth = 0x2;
-		else
-		if (nv_connector->base.display_info.bpc == 8)
-			depth = 0x5;
-		else
-			depth = 0x6;
+		depth = nv50_dp_bpc_to_depth(asyh->or.bpc);
 
 		if (nv_encoder->link & 1)
 			proto = 0x8;
@@ -1662,7 +1684,7 @@
 	nv50_outp_acquire(nv_encoder);
 
 	nv_connector = nouveau_encoder_connector_get(nv_encoder);
-	switch (nv_connector->base.display_info.bpc) {
+	switch (asyh->or.bpc) {
 	case 10: asyh->or.depth = 0x6; break;
 	case  8: asyh->or.depth = 0x5; break;
 	case  6: asyh->or.depth = 0x2; break;
@@ -2012,8 +2034,10 @@
 	int ret, i;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_atomic_helper_setup_commit(state, nonblock);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 7c41b05..284068f 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -70,7 +70,7 @@
 
 int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 		     const s32 *oclass, u8 head, void *data, u32 size,
-		     u64 syncbuf, struct nv50_dmac *dmac);
+		     s64 syncbuf, struct nv50_dmac *dmac);
 void nv50_dmac_destroy(struct nv50_dmac *);
 
 u32 *evo_wait(struct nv50_dmac *, int nr);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index 71c23bf..4657810 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -81,21 +81,22 @@
 			      struct nv50_head_atom *asyh,
 			      struct nouveau_conn_atom *asyc)
 {
-	struct drm_connector *connector = asyc->state.connector;
 	u32 mode = 0x00;
 
-	if (asyc->dither.mode == DITHERING_MODE_AUTO) {
-		if (asyh->base.depth > connector->display_info.bpc * 3)
-			mode = DITHERING_MODE_DYNAMIC2X2;
-	} else {
-		mode = asyc->dither.mode;
-	}
+	if (asyc->dither.mode) {
+		if (asyc->dither.mode == DITHERING_MODE_AUTO) {
+			if (asyh->base.depth > asyh->or.bpc * 3)
+				mode = DITHERING_MODE_DYNAMIC2X2;
+		} else {
+			mode = asyc->dither.mode;
+		}
 
-	if (asyc->dither.depth == DITHERING_DEPTH_AUTO) {
-		if (connector->display_info.bpc >= 8)
-			mode |= DITHERING_DEPTH_8BPC;
-	} else {
-		mode |= asyc->dither.depth;
+		if (asyc->dither.depth == DITHERING_DEPTH_AUTO) {
+			if (asyh->or.bpc >= 8)
+				mode |= DITHERING_DEPTH_8BPC;
+		} else {
+			mode |= asyc->dither.depth;
+		}
 	}
 
 	asyh->dither.enable = mode;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
index f7dbd96..b49a212 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
@@ -68,7 +68,7 @@
 	int ret;
 
 	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
-			       &oclass, 0, &args, sizeof(args), 0,
+			       &oclass, 0, &args, sizeof(args), -1,
 			       &wndw->wimm);
 	if (ret) {
 		NV_ERROR(drm, "wimm%04x allocation failed: %d\n", oclass, ret);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 5193b62..b856e87 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -451,6 +451,8 @@
 		asyw->clr.ntfy = armw->ntfy.handle != 0;
 		asyw->clr.sema = armw->sema.handle != 0;
 		asyw->clr.xlut = armw->xlut.handle != 0;
+		if (asyw->clr.xlut && asyw->visible)
+			asyw->set.xlut = asyw->xlut.handle != 0;
 		asyw->clr.csc  = armw->csc.valid;
 		if (wndw->func->image_clr)
 			asyw->clr.image = armw->image.handle[0] != 0;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h
index f5f5926..d1beaad 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h
@@ -14,6 +14,7 @@
 	DCB_CONNECTOR_LVDS_SPWG = 0x41,
 	DCB_CONNECTOR_DP = 0x46,
 	DCB_CONNECTOR_eDP = 0x47,
+	DCB_CONNECTOR_mDP = 0x48,
 	DCB_CONNECTOR_HDMI_0 = 0x60,
 	DCB_CONNECTOR_HDMI_1 = 0x61,
 	DCB_CONNECTOR_HDMI_C = 0x63,
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index f8015e0..f7603be 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -542,7 +542,7 @@
 	struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm;
 	int i;
 
-	if (!ttm_dma)
+	if (!ttm_dma || !ttm_dma->dma_address)
 		return;
 
 	/* Don't waste time looping if the object is coherent */
@@ -562,7 +562,7 @@
 	struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm;
 	int i;
 
-	if (!ttm_dma)
+	if (!ttm_dma || !ttm_dma->dma_address)
 		return;
 
 	/* Don't waste time looping if the object is coherent */
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 282fd90..9ce7b0d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -497,6 +497,7 @@
 	if (ret) {
 		NV_PRINTK(err, cli, "channel failed to initialise, %d\n", ret);
 		nouveau_channel_del(pchan);
+		goto done;
 	}
 
 	ret = nouveau_svmm_join((*pchan)->vmm->svmm, (*pchan)->inst);
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 94dfa2e..496e7dc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -245,14 +245,22 @@
 void
 nouveau_conn_reset(struct drm_connector *connector)
 {
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_conn_atom *asyc;
 
-	if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL))))
-		return;
+	if (drm_drv_uses_atomic_modeset(connector->dev)) {
+		if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL))))
+			return;
 
-	if (connector->state)
-		nouveau_conn_atomic_destroy_state(connector, connector->state);
-	__drm_atomic_helper_connector_reset(connector, &asyc->state);
+		if (connector->state)
+			nouveau_conn_atomic_destroy_state(connector,
+							  connector->state);
+
+		__drm_atomic_helper_connector_reset(connector, &asyc->state);
+	} else {
+		asyc = &nv_connector->properties_state;
+	}
+
 	asyc->dither.mode = DITHERING_MODE_AUTO;
 	asyc->dither.depth = DITHERING_DEPTH_AUTO;
 	asyc->scaler.mode = DRM_MODE_SCALE_NONE;
@@ -276,8 +284,14 @@
 nouveau_conn_attach_properties(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct nouveau_conn_atom *armc = nouveau_conn_atom(connector->state);
 	struct nouveau_display *disp = nouveau_display(dev);
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
+	struct nouveau_conn_atom *armc;
+
+	if (drm_drv_uses_atomic_modeset(connector->dev))
+		armc = nouveau_conn_atom(connector->state);
+	else
+		armc = &nv_connector->properties_state;
 
 	/* Init DVI-I specific properties. */
 	if (connector->connector_type == DRM_MODE_CONNECTOR_DVII)
@@ -554,8 +568,10 @@
 		pm_runtime_get_noresume(dev->dev);
 	} else {
 		ret = pm_runtime_get_sync(dev->dev);
-		if (ret < 0 && ret != -EACCES)
+		if (ret < 0 && ret != -EACCES) {
+			pm_runtime_put_autosuspend(dev->dev);
 			return conn_status;
+		}
 	}
 
 	nv_encoder = nouveau_connector_ddc_detect(connector);
@@ -749,9 +765,9 @@
 nouveau_connector_set_property(struct drm_connector *connector,
 			       struct drm_property *property, uint64_t value)
 {
-	struct nouveau_conn_atom *asyc = nouveau_conn_atom(connector->state);
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder;
+	struct nouveau_conn_atom *asyc = &nv_connector->properties_state;
 	struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
 	int ret;
 
@@ -1131,6 +1147,16 @@
 	const char *name = connector->name;
 	struct nouveau_encoder *nv_encoder;
 	int ret;
+	bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG);
+
+	if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) {
+		NV_DEBUG(drm, "service %s\n", name);
+		drm_dp_cec_irq(&nv_connector->aux);
+		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP)))
+			nv50_mstm_service(nv_encoder->dp.mstm);
+
+		return NVIF_NOTIFY_KEEP;
+	}
 
 	ret = pm_runtime_get(drm->dev->dev);
 	if (ret == 0) {
@@ -1151,25 +1177,16 @@
 		return NVIF_NOTIFY_DROP;
 	}
 
-	if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) {
-		NV_DEBUG(drm, "service %s\n", name);
-		drm_dp_cec_irq(&nv_connector->aux);
-		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP)))
-			nv50_mstm_service(nv_encoder->dp.mstm);
-	} else {
-		bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG);
-
+	if (!plugged)
+		drm_dp_cec_unset_edid(&nv_connector->aux);
+	NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name);
+	if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) {
 		if (!plugged)
-			drm_dp_cec_unset_edid(&nv_connector->aux);
-		NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name);
-		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) {
-			if (!plugged)
-				nv50_mstm_remove(nv_encoder->dp.mstm);
-		}
-
-		drm_helper_hpd_irq_event(connector->dev);
+			nv50_mstm_remove(nv_encoder->dp.mstm);
 	}
 
+	drm_helper_hpd_irq_event(connector->dev);
+
 	pm_runtime_mark_last_busy(drm->dev->dev);
 	pm_runtime_put_autosuspend(drm->dev->dev);
 	return NVIF_NOTIFY_KEEP;
@@ -1223,6 +1240,7 @@
 	case DCB_CONNECTOR_DMS59_DP0:
 	case DCB_CONNECTOR_DMS59_DP1:
 	case DCB_CONNECTOR_DP       :
+	case DCB_CONNECTOR_mDP      :
 	case DCB_CONNECTOR_USB_C    : return DRM_MODE_CONNECTOR_DisplayPort;
 	case DCB_CONNECTOR_eDP      : return DRM_MODE_CONNECTOR_eDP;
 	case DCB_CONNECTOR_HDMI_0   :
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index f43a8d6..de84fb4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -29,6 +29,7 @@
 
 #include <nvif/notify.h>
 
+#include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_dp_helper.h>
@@ -44,6 +45,60 @@
 struct nouveau_backlight;
 #endif
 
+#define nouveau_conn_atom(p)                                                   \
+	container_of((p), struct nouveau_conn_atom, state)
+
+struct nouveau_conn_atom {
+	struct drm_connector_state state;
+
+	struct {
+		/* The enum values specifically defined here match nv50/gf119
+		 * hw values, and the code relies on this.
+		 */
+		enum {
+			DITHERING_MODE_OFF = 0x00,
+			DITHERING_MODE_ON = 0x01,
+			DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON,
+			DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON,
+			DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON,
+			DITHERING_MODE_AUTO
+		} mode;
+		enum {
+			DITHERING_DEPTH_6BPC = 0x00,
+			DITHERING_DEPTH_8BPC = 0x02,
+			DITHERING_DEPTH_AUTO
+		} depth;
+	} dither;
+
+	struct {
+		int mode;	/* DRM_MODE_SCALE_* */
+		struct {
+			enum {
+				UNDERSCAN_OFF,
+				UNDERSCAN_ON,
+				UNDERSCAN_AUTO,
+			} mode;
+			u32 hborder;
+			u32 vborder;
+		} underscan;
+		bool full;
+	} scaler;
+
+	struct {
+		int color_vibrance;
+		int vibrant_hue;
+	} procamp;
+
+	union {
+		struct {
+			bool dither:1;
+			bool scaler:1;
+			bool procamp:1;
+		};
+		u8 mask;
+	} set;
+};
+
 struct nouveau_connector {
 	struct drm_connector base;
 	enum dcb_connector_type type;
@@ -63,6 +118,12 @@
 #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
 	struct nouveau_backlight *backlight;
 #endif
+	/*
+	 * Our connector property code expects a nouveau_conn_atom struct
+	 * even on pre-nv50 where we do not support atomic. This embedded
+	 * version gets used in the non atomic modeset case.
+	 */
+	struct nouveau_conn_atom properties_state;
 };
 
 static inline struct nouveau_connector *nouveau_connector(
@@ -121,61 +182,6 @@
 extern int nouveau_duallink;
 extern int nouveau_hdmimhz;
 
-#include <drm/drm_crtc.h>
-#define nouveau_conn_atom(p)                                                   \
-	container_of((p), struct nouveau_conn_atom, state)
-
-struct nouveau_conn_atom {
-	struct drm_connector_state state;
-
-	struct {
-		/* The enum values specifically defined here match nv50/gf119
-		 * hw values, and the code relies on this.
-		 */
-		enum {
-			DITHERING_MODE_OFF = 0x00,
-			DITHERING_MODE_ON = 0x01,
-			DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON,
-			DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON,
-			DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON,
-			DITHERING_MODE_AUTO
-		} mode;
-		enum {
-			DITHERING_DEPTH_6BPC = 0x00,
-			DITHERING_DEPTH_8BPC = 0x02,
-			DITHERING_DEPTH_AUTO
-		} depth;
-	} dither;
-
-	struct {
-		int mode;	/* DRM_MODE_SCALE_* */
-		struct {
-			enum {
-				UNDERSCAN_OFF,
-				UNDERSCAN_ON,
-				UNDERSCAN_AUTO,
-			} mode;
-			u32 hborder;
-			u32 vborder;
-		} underscan;
-		bool full;
-	} scaler;
-
-	struct {
-		int color_vibrance;
-		int vibrant_hue;
-	} procamp;
-
-	union {
-		struct {
-			bool dither:1;
-			bool scaler:1;
-			bool procamp:1;
-		};
-		u8 mask;
-	} set;
-};
-
 void nouveau_conn_attach_properties(struct drm_connector *);
 void nouveau_conn_reset(struct drm_connector *);
 struct drm_connector_state *
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 7dfbbbc..3b13fec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -54,8 +54,10 @@
 	int ret;
 
 	ret = pm_runtime_get_sync(drm->dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(drm->dev->dev);
 		return ret;
+	}
 
 	seq_printf(m, "0x%08x\n",
 		   nvif_rd32(&drm->client.device.object, 0x101000));
@@ -181,8 +183,11 @@
 	}
 
 	ret = pm_runtime_get_sync(drm->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(drm->dev);
 		return ret;
+	}
+
 	ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
 	pm_runtime_put_autosuspend(drm->dev);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index fa14399..0ad5d87 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -635,10 +635,10 @@
 	unsigned long c, i;
 	int ret = -ENOMEM;
 
-	args.src = kcalloc(max, sizeof(args.src), GFP_KERNEL);
+	args.src = kcalloc(max, sizeof(*args.src), GFP_KERNEL);
 	if (!args.src)
 		goto out;
-	args.dst = kcalloc(max, sizeof(args.dst), GFP_KERNEL);
+	args.dst = kcalloc(max, sizeof(*args.dst), GFP_KERNEL);
 	if (!args.dst)
 		goto out_free_src;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 2cd8384..5347e5b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -618,6 +618,64 @@
 	kfree(drm);
 }
 
+/*
+ * On some Intel PCIe bridge controllers doing a
+ * D0 -> D3hot -> D3cold -> D0 sequence causes Nvidia GPUs to not reappear.
+ * Skipping the intermediate D3hot step seems to make it work again. This is
+ * probably caused by not meeting the expectation the involved AML code has
+ * when the GPU is put into D3hot state before invoking it.
+ *
+ * This leads to various manifestations of this issue:
+ *  - AML code execution to power on the GPU hits an infinite loop (as the
+ *    code waits on device memory to change).
+ *  - kernel crashes, as all PCI reads return -1, which most code isn't able
+ *    to handle well enough.
+ *
+ * In all cases dmesg will contain at least one line like this:
+ * 'nouveau 0000:01:00.0: Refused to change power state, currently in D3'
+ * followed by a lot of nouveau timeouts.
+ *
+ * In the \_SB.PCI0.PEG0.PG00._OFF code deeper down writes bit 0x80 to the not
+ * documented PCI config space register 0x248 of the Intel PCIe bridge
+ * controller (0x1901) in order to change the state of the PCIe link between
+ * the PCIe port and the GPU. There are alternative code paths using other
+ * registers, which seem to work fine (executed pre Windows 8):
+ *  - 0xbc bit 0x20 (publicly available documentation claims 'reserved')
+ *  - 0xb0 bit 0x10 (link disable)
+ * Changing the conditions inside the firmware by poking into the relevant
+ * addresses does resolve the issue, but it seemed to be ACPI private memory
+ * and not any device accessible memory at all, so there is no portable way of
+ * changing the conditions.
+ * On a XPS 9560 that means bits [0,3] on \CPEX need to be cleared.
+ *
+ * The only systems where this behavior can be seen are hybrid graphics laptops
+ * with a secondary Nvidia Maxwell, Pascal or Turing GPU. It's unclear whether
+ * this issue only occurs in combination with listed Intel PCIe bridge
+ * controllers and the mentioned GPUs or other devices as well.
+ *
+ * documentation on the PCIe bridge controller can be found in the
+ * "7th Generation Intel® Processor Families for H Platforms Datasheet Volume 2"
+ * Section "12 PCI Express* Controller (x16) Registers"
+ */
+
+static void quirk_broken_nv_runpm(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct pci_dev *bridge = pci_upstream_bridge(pdev);
+
+	if (!bridge || bridge->vendor != PCI_VENDOR_ID_INTEL)
+		return;
+
+	switch (bridge->device) {
+	case 0x1901:
+		drm->old_pm_cap = pdev->pm_cap;
+		pdev->pm_cap = 0;
+		NV_INFO(drm, "Disabling PCI power management to avoid bug\n");
+		break;
+	}
+}
+
 static int nouveau_drm_probe(struct pci_dev *pdev,
 			     const struct pci_device_id *pent)
 {
@@ -699,6 +757,7 @@
 	if (ret)
 		goto fail_drm_dev_init;
 
+	quirk_broken_nv_runpm(pdev);
 	return 0;
 
 fail_drm_dev_init:
@@ -736,7 +795,11 @@
 nouveau_drm_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct nouveau_drm *drm = nouveau_drm(dev);
 
+	/* revert our workaround */
+	if (drm->old_pm_cap)
+		pdev->pm_cap = drm->old_pm_cap;
 	nouveau_drm_device_remove(dev);
 }
 
@@ -989,8 +1052,10 @@
 
 	/* need to bring up power immediately if opening device */
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
@@ -1072,8 +1137,10 @@
 	long ret;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	switch (_IOC_NR(cmd) - DRM_COMMAND_BASE) {
 	case DRM_NOUVEAU_NVIF:
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 70f34ca..8104e38 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -138,6 +138,8 @@
 
 	struct list_head clients;
 
+	u8 old_pm_cap;
+
 	struct {
 		struct agp_bridge_data *bridge;
 		u32 base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index f439f0a..c09ea35 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -189,8 +189,10 @@
 	struct nouveau_fbdev *fbcon = info->par;
 	struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
 	int ret = pm_runtime_get_sync(drm->dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put(drm->dev->dev);
 		return ret;
+	}
 	return 0;
 }
 
@@ -315,7 +317,7 @@
 	struct nouveau_framebuffer *fb;
 	struct nouveau_channel *chan;
 	struct nouveau_bo *nvbo;
-	struct drm_mode_fb_cmd2 mode_cmd;
+	struct drm_mode_fb_cmd2 mode_cmd = {};
 	int ret;
 
 	mode_cmd.width = sizes->surface_width;
@@ -592,6 +594,7 @@
 	drm_fb_helper_fini(&fbcon->helper);
 free:
 	kfree(fbcon);
+	drm->fbcon = NULL;
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 9118df0..70bb6bb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -156,7 +156,7 @@
 
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
-		if (nouveau_fence_update(fence->channel, fctx))
+		if (nouveau_fence_update(chan, fctx))
 			ret = NVIF_NOTIFY_DROP;
 	}
 	spin_unlock_irqrestore(&fctx->lock, flags);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 1324c19..2dd9fca 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -45,8 +45,10 @@
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (WARN_ON(ret < 0 && ret != -EACCES))
+	if (WARN_ON(ret < 0 && ret != -EACCES)) {
+		pm_runtime_put_autosuspend(dev);
 		return;
+	}
 
 	if (gem->import_attach)
 		drm_prime_gem_destroy(gem, nvbo->bo.sg);
@@ -76,8 +78,10 @@
 		return ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev);
 		goto out;
+	}
 
 	ret = nouveau_vma_new(nvbo, vmm, &vma);
 	pm_runtime_mark_last_busy(dev);
@@ -193,7 +197,8 @@
 	 * to the caller, instead of a normal nouveau_bo ttm reference. */
 	ret = drm_gem_object_init(drm->dev, &nvbo->bo.base, size);
 	if (ret) {
-		nouveau_bo_ref(NULL, &nvbo);
+		drm_gem_object_release(&nvbo->bo.base);
+		kfree(nvbo);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index c002f89..9682f30 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -176,6 +176,8 @@
 nouveau_mem_del(struct ttm_mem_reg *reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(reg);
+	if (!mem)
+		return;
 	nouveau_mem_fini(mem);
 	kfree(reg->mm_node);
 	reg->mm_node = NULL;
diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
index bae6a3e..f9ee562 100644
--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
+++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
@@ -112,7 +112,22 @@
 	if (ret)
 		return -EINVAL;
 
-	return 0;
+	ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL);
+	if (ret)
+		goto error;
+
+	if (nvbo->bo.moving)
+		ret = dma_fence_wait(nvbo->bo.moving, true);
+
+	ttm_bo_unreserve(&nvbo->bo);
+	if (ret)
+		goto error;
+
+	return ret;
+
+error:
+	nouveau_bo_unpin(nvbo);
+	return ret;
 }
 
 void nouveau_gem_prime_unpin(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index feaac90..34403b8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -96,12 +96,9 @@
 	else
 		nvbe->ttm.ttm.func = &nv50_sgdma_backend;
 
-	if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags))
-		/*
-		 * A failing ttm_dma_tt_init() will call ttm_tt_destroy()
-		 * and thus our nouveau_sgdma_destroy() hook, so we don't need
-		 * to free nvbe here.
-		 */
+	if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags)) {
+		kfree(nvbe);
 		return NULL;
+	}
 	return &nvbe->ttm.ttm;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 668d4bd..8556804 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -112,11 +112,11 @@
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct drm_nouveau_svm_bind *args = data;
 	unsigned target, cmd, priority;
-	unsigned long addr, end, size;
+	unsigned long addr, end;
 	struct mm_struct *mm;
 
 	args->va_start &= PAGE_MASK;
-	args->va_end &= PAGE_MASK;
+	args->va_end = ALIGN(args->va_end, PAGE_SIZE);
 
 	/* Sanity check arguments */
 	if (args->reserved0 || args->reserved1)
@@ -125,8 +125,6 @@
 		return -EINVAL;
 	if (args->va_start >= args->va_end)
 		return -EINVAL;
-	if (!args->npages)
-		return -EINVAL;
 
 	cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT;
 	cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK;
@@ -158,12 +156,6 @@
 	if (args->stride)
 		return -EINVAL;
 
-	size = ((unsigned long)args->npages) << PAGE_SHIFT;
-	if ((args->va_start + size) <= args->va_start)
-		return -EINVAL;
-	if ((args->va_start + size) > args->va_end)
-		return -EINVAL;
-
 	/*
 	 * Ok we are ask to do something sane, for now we only support migrate
 	 * commands but we will add things like memory policy (what to do on
@@ -173,7 +165,12 @@
 	mm = get_task_mm(current);
 	down_read(&mm->mmap_sem);
 
-	for (addr = args->va_start, end = args->va_start + size; addr < end;) {
+	if (!cli->svm.svmm) {
+		up_read(&mm->mmap_sem);
+		return -EINVAL;
+	}
+
+	for (addr = args->va_start, end = args->va_end; addr < end;) {
 		struct vm_area_struct *vma;
 		unsigned long next;
 
@@ -181,6 +178,7 @@
 		if (!vma)
 			break;
 
+		addr = max(addr, vma->vm_start);
 		next = min(vma->vm_end, end);
 		/* This is a best effort so we ignore errors */
 		nouveau_dmem_migrate_vma(cli->drm, vma, addr, next);
@@ -308,6 +306,10 @@
 	struct drm_nouveau_svm_init *args = data;
 	int ret;
 
+	/* We need to fail if svm is disabled */
+	if (!cli->drm->svm)
+		return -ENOSYS;
+
 	/* Allocate tracking for SVM-enabled VMM. */
 	if (!(svmm = kzalloc(sizeof(*svmm), GFP_KERNEL)))
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index f0daf95..621d28f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -63,14 +63,12 @@
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	if (drm->client.device.info.ram_size == 0)
 		return -ENOMEM;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
@@ -103,11 +101,9 @@
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/memory.c b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
index e85a08e..4cc1862 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/memory.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
@@ -91,8 +91,8 @@
 	}
 
 	refcount_set(&tags->refcount, 1);
+	*ptags = memory->tags = tags;
 	mutex_unlock(&fb->subdev.mutex);
-	*ptags = tags;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index bcf32d9..50e3539 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -74,6 +74,8 @@
 
 	if (debug > subdev->debug)
 		return;
+	if (!mthd)
+		return;
 
 	for (i = 0; (list = mthd->data[i].mthd) != NULL; i++) {
 		u32 base = chan->head * mthd->addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 818d21b..1d2837c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -419,7 +419,7 @@
 	return ret;
 }
 
-static void
+void
 nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior)
 {
 	struct nvkm_dp *dp = nvkm_dp(outp);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h
index 428b3f4..e484d0c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h
@@ -32,6 +32,7 @@
 
 int nvkm_dp_new(struct nvkm_disp *, int index, struct dcb_output *,
 		struct nvkm_outp **);
+void nvkm_dp_disable(struct nvkm_outp *, struct nvkm_ior *);
 
 /* DPCD Receiver Capabilities */
 #define DPCD_RC00_DPCD_REV                                              0x00000
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c
index 9b16a08..bf6d41f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c
@@ -27,10 +27,10 @@
 gm200_hdmi_scdc(struct nvkm_ior *ior, int head, u8 scdc)
 {
 	struct nvkm_device *device = ior->disp->engine.subdev.device;
-	const u32 hoff = head * 0x800;
+	const u32 soff = nv50_ior_base(ior);
 	const u32 ctrl = scdc & 0x3;
 
-	nvkm_mask(device, 0x61c5bc + hoff, 0x00000003, ctrl);
+	nvkm_mask(device, 0x61c5bc + soff, 0x00000003, ctrl);
 
 	ior->tmds.high_speed = !!(scdc & 0x2);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
index c62030c..4b1c72f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "outp.h"
+#include "dp.h"
 #include "ior.h"
 
 #include <subdev/bios.h>
@@ -216,6 +217,14 @@
 	if (!ior->arm.head || ior->arm.proto != proto) {
 		OUTP_DBG(outp, "no heads (%x %d %d)", ior->arm.head,
 			 ior->arm.proto, proto);
+
+		/* The EFI GOP driver on Ampere can leave unused DP links routed,
+		 * which we don't expect.  The DisableLT IED script *should* get
+		 * us back to where we need to be.
+		 */
+		if (ior->func->route.get && !ior->arm.head && outp->info.type == DCB_OUTPUT_DP)
+			nvkm_dp_disable(outp, ior);
+
 		return;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index c578deb..c71606a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -1988,8 +1988,34 @@
 {
 	struct gf100_gr *gr = gf100_gr(base);
 	struct nvkm_subdev *subdev = &base->engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	bool reset = device->chipset == 0x137 || device->chipset == 0x138;
 	u32 ret;
 
+	/* On certain GP107/GP108 boards, we trigger a weird issue where
+	 * GR will stop responding to PRI accesses after we've asked the
+	 * SEC2 RTOS to boot the GR falcons.  This happens with far more
+	 * frequency when cold-booting a board (ie. returning from D3).
+	 *
+	 * The root cause for this is not known and has proven difficult
+	 * to isolate, with many avenues being dead-ends.
+	 *
+	 * A workaround was discovered by Karol, whereby putting GR into
+	 * reset for an extended period right before initialisation
+	 * prevents the problem from occuring.
+	 *
+	 * XXX: As RM does not require any such workaround, this is more
+	 *      of a hack than a true fix.
+	 */
+	reset = nvkm_boolopt(device->cfgopt, "NvGrResetWar", reset);
+	if (reset) {
+		nvkm_mask(device, 0x000200, 0x00001000, 0x00000000);
+		nvkm_rd32(device, 0x000200);
+		msleep(50);
+		nvkm_mask(device, 0x000200, 0x00001000, 0x00001000);
+		nvkm_rd32(device, 0x000200);
+	}
+
 	nvkm_pmu_pgob(gr->base.engine.subdev.device->pmu, false);
 
 	ret = nvkm_falcon_get(gr->fecs.falcon, subdev);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
index 500cb08..b57ab5c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
@@ -143,23 +143,24 @@
 
 	nent = (fuc.size / sizeof(struct gk20a_fw_av));
 
-	pack = vzalloc((sizeof(*pack) * max_classes) +
-		       (sizeof(*init) * (nent + 1)));
+	pack = vzalloc((sizeof(*pack) * (max_classes + 1)) +
+		       (sizeof(*init) * (nent + max_classes + 1)));
 	if (!pack) {
 		ret = -ENOMEM;
 		goto end;
 	}
 
-	init = (void *)(pack + max_classes);
+	init = (void *)(pack + max_classes + 1);
 
-	for (i = 0; i < nent; i++) {
-		struct gf100_gr_init *ent = &init[i];
+	for (i = 0; i < nent; i++, init++) {
 		struct gk20a_fw_av *av = &((struct gk20a_fw_av *)fuc.data)[i];
 		u32 class = av->addr & 0xffff;
 		u32 addr = (av->addr & 0xffff0000) >> 14;
 
 		if (prevclass != class) {
-			pack[classidx].init = ent;
+			if (prevclass) /* Add terminator to the method list. */
+				init++;
+			pack[classidx].init = init;
 			pack[classidx].type = class;
 			prevclass = class;
 			if (++classidx >= max_classes) {
@@ -169,10 +170,10 @@
 			}
 		}
 
-		ent->addr = addr;
-		ent->data = av->data;
-		ent->count = 1;
-		ent->pitch = 1;
+		init->addr = addr;
+		init->data = av->data;
+		init->count = 1;
+		init->pitch = 1;
 	}
 
 	*ppack = pack;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 7deb81b..4b571cc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -75,7 +75,7 @@
 	nvkm_debug(subdev, "%08x: type %02x, %d bytes\n",
 		   image.base, image.type, image.size);
 
-	if (!shadow_fetch(bios, mthd, image.size)) {
+	if (!shadow_fetch(bios, mthd, image.base + image.size)) {
 		nvkm_debug(subdev, "%08x: fetch failed\n", image.base);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c
index 9b91da0..8d9812a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c
@@ -101,9 +101,13 @@
 	else
 		return ERR_PTR(-ENODEV);
 
+	if (!pdev->rom || pdev->romlen == 0)
+		return ERR_PTR(-ENODEV);
+
 	if ((priv = kmalloc(sizeof(*priv), GFP_KERNEL))) {
+		priv->size = pdev->romlen;
 		if (ret = -ENODEV,
-		    (priv->rom = pci_platform_rom(pdev, &priv->size)))
+		    (priv->rom = ioremap(pdev->rom, pdev->romlen)))
 			return priv;
 		kfree(priv);
 	}
@@ -111,11 +115,20 @@
 	return ERR_PTR(ret);
 }
 
+static void
+platform_fini(void *data)
+{
+	struct priv *priv = data;
+
+	iounmap(priv->rom);
+	kfree(priv);
+}
+
 const struct nvbios_source
 nvbios_platform = {
 	.name = "PLATFORM",
 	.init = platform_init,
-	.fini = (void(*)(void *))kfree,
+	.fini = platform_fini,
 	.read = pcirom_read,
 	.rw = true,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
index ca25156..bb4a426 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -146,6 +146,7 @@
 	struct nvkm_fault *fault = nvkm_fault(subdev);
 	int i;
 
+	nvkm_notify_fini(&fault->nrpfb);
 	nvkm_event_fini(&fault->event);
 
 	for (i = 0; i < fault->buffer_nr; i++) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index c8ab1b5..db7769c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -118,10 +118,10 @@
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00e4e4 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00e4e4 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index 7ef6089..d0e80ad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -33,7 +33,7 @@
 gm200_i2c_aux_fini(struct gm200_i2c_aux *aux)
 {
 	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
-	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00310000, 0x00000000);
+	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00710000, 0x00000000);
 }
 
 static int
@@ -54,10 +54,10 @@
 			AUX_ERR(&aux->base, "begin idle timeout %08x", ctrl);
 			return -EBUSY;
 		}
-	} while (ctrl & 0x03010000);
+	} while (ctrl & 0x07010000);
 
 	/* set some magic, and wait up to 1ms for it to appear */
-	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00300000, ureq);
+	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00700000, ureq);
 	timeout = 1000;
 	do {
 		ctrl = nvkm_rd32(device, 0x00d954 + (aux->ch * 0x50));
@@ -67,7 +67,7 @@
 			gm200_i2c_aux_fini(aux);
 			return -EBUSY;
 		}
-	} while ((ctrl & 0x03000000) != urep);
+	} while ((ctrl & 0x07000000) != urep);
 
 	return 0;
 }
@@ -118,10 +118,10 @@
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00d954 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00d954 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
index d80dbc8..55a4ea4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "priv.h"
+#include <subdev/timer.h>
 
 static void
 gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@
 	u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0400));
 	nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x122128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 static void
@@ -42,7 +42,6 @@
 	u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0400));
 	nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x124128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 static void
@@ -53,7 +52,6 @@
 	u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0400));
 	nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x128128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 void
@@ -90,6 +88,12 @@
 			intr1 &= ~stat;
 		}
 	}
+
+	nvkm_mask(device, 0x121c4c, 0x0000003f, 0x00000002);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x121c4c) & 0x0000003f))
+			break;
+	);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
index 9025ed1..4caf3ef 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "priv.h"
+#include <subdev/timer.h>
 
 static void
 gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@
 	u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0800));
 	nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x122128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 static void
@@ -42,7 +42,6 @@
 	u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0800));
 	nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x124128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 static void
@@ -53,7 +52,6 @@
 	u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0800));
 	nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x128128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 void
@@ -90,6 +88,12 @@
 			intr1 &= ~stat;
 		}
 	}
+
+	nvkm_mask(device, 0x12004c, 0x0000003f, 0x00000002);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x12004c) & 0x0000003f))
+			break;
+	);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
index ee11cca..cb51e24 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
@@ -316,9 +316,9 @@
 {
 	struct nvkm_device *device = mmu->subdev.device;
 	struct nvkm_mm *mm = &device->fb->ram->vram;
-	const u32 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
-	const u32 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
-	const u32 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
+	const u64 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
+	const u64 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
+	const u64 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
 	u8 type = NVKM_MEM_KIND * !!mmu->func->kind;
 	u8 heap = NVKM_MEM_VRAM;
 	int heapM, heapN, heapU;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
index df8b919..ace6fef 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
@@ -108,6 +108,7 @@
 	struct gm200_secboot *gsb;
 	struct nvkm_acr *acr;
 
+	*psb = NULL;
 	acr = acr_r352_new(BIT(NVKM_SECBOOT_FALCON_FECS) |
 			   BIT(NVKM_SECBOOT_FALCON_PMU));
 	if (IS_ERR(acr))
@@ -116,10 +117,8 @@
 	acr->optional_falcons = BIT(NVKM_SECBOOT_FALCON_PMU);
 
 	gsb = kzalloc(sizeof(*gsb), GFP_KERNEL);
-	if (!gsb) {
-		psb = NULL;
+	if (!gsb)
 		return -ENOMEM;
-	}
 	*psb = &gsb->base;
 
 	ret = nvkm_secboot_ctor(&gm20b_secboot, acr, device, index, &gsb->base);
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index 4bdd63b..ac93dae 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1151,6 +1151,31 @@
 	.has_lcd_clk_src	=	true,
 };
 
+static void __dss_uninit_ports(struct dss_device *dss, unsigned int num_ports)
+{
+	struct platform_device *pdev = dss->pdev;
+	struct device_node *parent = pdev->dev.of_node;
+	struct device_node *port;
+	unsigned int i;
+
+	for (i = 0; i < num_ports; i++) {
+		port = of_graph_get_port_by_id(parent, i);
+		if (!port)
+			continue;
+
+		switch (dss->feat->ports[i]) {
+		case OMAP_DISPLAY_TYPE_DPI:
+			dpi_uninit_port(port);
+			break;
+		case OMAP_DISPLAY_TYPE_SDI:
+			sdi_uninit_port(port);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
 static int dss_init_ports(struct dss_device *dss)
 {
 	struct platform_device *pdev = dss->pdev;
@@ -1168,13 +1193,13 @@
 		case OMAP_DISPLAY_TYPE_DPI:
 			r = dpi_init_port(dss, pdev, port, dss->feat->model);
 			if (r)
-				return r;
+				goto error;
 			break;
 
 		case OMAP_DISPLAY_TYPE_SDI:
 			r = sdi_init_port(dss, pdev, port);
 			if (r)
-				return r;
+				goto error;
 			break;
 
 		default:
@@ -1183,31 +1208,15 @@
 	}
 
 	return 0;
+
+error:
+	__dss_uninit_ports(dss, i);
+	return r;
 }
 
 static void dss_uninit_ports(struct dss_device *dss)
 {
-	struct platform_device *pdev = dss->pdev;
-	struct device_node *parent = pdev->dev.of_node;
-	struct device_node *port;
-	int i;
-
-	for (i = 0; i < dss->feat->num_ports; i++) {
-		port = of_graph_get_port_by_id(parent, i);
-		if (!port)
-			continue;
-
-		switch (dss->feat->ports[i]) {
-		case OMAP_DISPLAY_TYPE_DPI:
-			dpi_uninit_port(port);
-			break;
-		case OMAP_DISPLAY_TYPE_SDI:
-			sdi_uninit_port(port);
-			break;
-		default:
-			break;
-		}
-	}
+	__dss_uninit_ports(dss, dss->feat->num_ports);
 }
 
 static int dss_video_pll_probe(struct dss_device *dss)
diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c
index 3150285..ce67891 100644
--- a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c
+++ b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c
@@ -192,7 +192,7 @@
 	dss = of_find_matching_node(NULL, omapdss_of_match);
 
 	if (dss == NULL || !of_device_is_available(dss))
-		return 0;
+		goto put_node;
 
 	omapdss_walk_device(dss, true);
 
@@ -217,6 +217,8 @@
 		kfree(n);
 	}
 
+put_node:
+	of_node_put(dss);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c
index 3c5ddbf..f5e1880 100644
--- a/drivers/gpu/drm/omapdrm/omap_crtc.c
+++ b/drivers/gpu/drm/omapdrm/omap_crtc.c
@@ -451,11 +451,12 @@
 	if (omap_state->manually_updated)
 		return;
 
-	spin_lock_irq(&crtc->dev->event_lock);
 	drm_crtc_vblank_on(crtc);
+
 	ret = drm_crtc_vblank_get(crtc);
 	WARN_ON(ret != 0);
 
+	spin_lock_irq(&crtc->dev->event_lock);
 	omap_crtc_arm_event(crtc);
 	spin_unlock_irq(&crtc->dev->event_lock);
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index 252f5eb..3dd6c00 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -891,6 +891,7 @@
 					   &omap_dmm->refill_pa, GFP_KERNEL);
 	if (!omap_dmm->refill_va) {
 		dev_err(&dev->dev, "could not allocate refill memory\n");
+		ret = -ENOMEM;
 		goto fail;
 	}
 
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index ad47cc9..bf5fcc3 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -197,7 +197,6 @@
 static int panel_lvds_probe(struct platform_device *pdev)
 {
 	struct panel_lvds *lvds;
-	struct device_node *np;
 	int ret;
 
 	lvds = devm_kzalloc(&pdev->dev, sizeof(*lvds), GFP_KERNEL);
@@ -243,14 +242,9 @@
 		return ret;
 	}
 
-	np = of_parse_phandle(lvds->dev->of_node, "backlight", 0);
-	if (np) {
-		lvds->backlight = of_find_backlight_by_node(np);
-		of_node_put(np);
-
-		if (!lvds->backlight)
-			return -EPROBE_DEFER;
-	}
+	lvds->backlight = devm_of_find_backlight(lvds->dev);
+	if (IS_ERR(lvds->backlight))
+		return PTR_ERR(lvds->backlight);
 
 	/*
 	 * TODO: Handle all power supplies specified in the DT node in a generic
@@ -266,14 +260,10 @@
 
 	ret = drm_panel_add(&lvds->panel);
 	if (ret < 0)
-		goto error;
+		return ret;
 
 	dev_set_drvdata(lvds->dev, lvds);
 	return 0;
-
-error:
-	put_device(&lvds->backlight->dev);
-	return ret;
 }
 
 static int panel_lvds_remove(struct platform_device *pdev)
@@ -284,9 +274,6 @@
 
 	panel_lvds_disable(&lvds->panel);
 
-	if (lvds->backlight)
-		put_device(&lvds->backlight->dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
index b5b14aa..bdb4d59 100644
--- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
+++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
@@ -426,6 +426,7 @@
 		return PTR_ERR(ts->dsi);
 	}
 
+	drm_panel_init(&ts->base);
 	ts->base.dev = dev;
 	ts->base.funcs = &rpi_touchscreen_funcs;
 
@@ -452,7 +453,6 @@
 	drm_panel_remove(&ts->base);
 
 	mipi_dsi_device_unregister(ts->dsi);
-	kfree(ts->dsi);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 28fa6ba..f0ea782 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1935,7 +1935,7 @@
 static const struct panel_desc lg_lb070wv8 = {
 	.modes = &lg_lb070wv8_mode,
 	.num_modes = 1,
-	.bpc = 16,
+	.bpc = 8,
 	.size = {
 		.width = 151,
 		.height = 91,
@@ -2048,6 +2048,40 @@
 	.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
 };
 
+static const struct drm_display_mode logicpd_type_28_mode = {
+	.clock = 9000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 3,
+	.hsync_end = 480 + 3 + 42,
+	.htotal = 480 + 3 + 42 + 2,
+
+	.vdisplay = 272,
+	.vsync_start = 272 + 2,
+	.vsync_end = 272 + 2 + 11,
+	.vtotal = 272 + 2 + 11 + 3,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+};
+
+static const struct panel_desc logicpd_type_28 = {
+	.modes = &logicpd_type_28_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 105,
+		.height = 67,
+	},
+	.delay = {
+		.prepare = 200,
+		.enable = 200,
+		.unprepare = 200,
+		.disable = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE |
+		     DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE,
+};
+
 static const struct panel_desc mitsubishi_aa070mc01 = {
 	.modes = &mitsubishi_aa070mc01_mode,
 	.num_modes = 1,
@@ -2348,12 +2382,12 @@
 static const struct panel_desc ortustech_com43h4m85ulc = {
 	.modes = &ortustech_com43h4m85ulc_mode,
 	.num_modes = 1,
-	.bpc = 8,
+	.bpc = 6,
 	.size = {
 		.width = 56,
 		.height = 93,
 	},
-	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE,
 };
 
@@ -3265,6 +3299,9 @@
 		.compatible = "lg,lp129qe",
 		.data = &lg_lp129qe,
 	}, {
+		.compatible = "logicpd,type28",
+		.data = &logicpd_type_28,
+	}, {
 		.compatible = "mitsubishi,aa070mc01-ca1",
 		.data = &mitsubishi_aa070mc01,
 	}, {
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 5e3e92e..3b2612a 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -381,6 +381,7 @@
 	spi_set_drvdata(spi, ctx);
 	ctx->spi = spi;
 
+	drm_panel_init(&ctx->panel);
 	ctx->panel.dev = &spi->dev;
 	ctx->panel.funcs = &st7789v_drm_funcs;
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 12ff77d..c1eb8cf 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -53,8 +53,10 @@
 	if (err) {
 		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
 			err);
-		regulator_set_voltage(pfdev->regulator, pfdev->devfreq.cur_volt,
-				      pfdev->devfreq.cur_volt);
+		if (pfdev->regulator)
+			regulator_set_voltage(pfdev->regulator,
+					      pfdev->devfreq.cur_volt,
+					      pfdev->devfreq.cur_volt);
 		return err;
 	}
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c
index 238fb6d..413bf31 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.c
+++ b/drivers/gpu/drm/panfrost/panfrost_device.c
@@ -59,7 +59,8 @@
 	if (IS_ERR(pfdev->bus_clock)) {
 		dev_err(pfdev->dev, "get bus_clock failed %ld\n",
 			PTR_ERR(pfdev->bus_clock));
-		return PTR_ERR(pfdev->bus_clock);
+		err = PTR_ERR(pfdev->bus_clock);
+		goto disable_clock;
 	}
 
 	if (pfdev->bus_clock) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index f21bc8a..f57dd19 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -78,8 +78,10 @@
 static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
 		struct drm_file *file)
 {
+	struct panfrost_file_priv *priv = file->driver_priv;
 	struct panfrost_gem_object *bo;
 	struct drm_panfrost_create_bo *args = data;
+	struct panfrost_gem_mapping *mapping;
 
 	if (!args->size || args->pad ||
 	    (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
@@ -95,7 +97,14 @@
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
-	args->offset = bo->node.start << PAGE_SHIFT;
+	mapping = panfrost_gem_mapping_get(bo, priv);
+	if (!mapping) {
+		drm_gem_object_put_unlocked(&bo->base.base);
+		return -EINVAL;
+	}
+
+	args->offset = mapping->mmnode.start << PAGE_SHIFT;
+	panfrost_gem_mapping_put(mapping);
 
 	return 0;
 }
@@ -119,6 +128,11 @@
 		  struct drm_panfrost_submit *args,
 		  struct panfrost_job *job)
 {
+	struct panfrost_file_priv *priv = file_priv->driver_priv;
+	struct panfrost_gem_object *bo;
+	unsigned int i;
+	int ret;
+
 	job->bo_count = args->bo_handle_count;
 
 	if (!job->bo_count)
@@ -130,9 +144,33 @@
 	if (!job->implicit_fences)
 		return -ENOMEM;
 
-	return drm_gem_objects_lookup(file_priv,
-				      (void __user *)(uintptr_t)args->bo_handles,
-				      job->bo_count, &job->bos);
+	ret = drm_gem_objects_lookup(file_priv,
+				     (void __user *)(uintptr_t)args->bo_handles,
+				     job->bo_count, &job->bos);
+	if (ret)
+		return ret;
+
+	job->mappings = kvmalloc_array(job->bo_count,
+				       sizeof(struct panfrost_gem_mapping *),
+				       GFP_KERNEL | __GFP_ZERO);
+	if (!job->mappings)
+		return -ENOMEM;
+
+	for (i = 0; i < job->bo_count; i++) {
+		struct panfrost_gem_mapping *mapping;
+
+		bo = to_panfrost_bo(job->bos[i]);
+		mapping = panfrost_gem_mapping_get(bo, priv);
+		if (!mapping) {
+			ret = -EINVAL;
+			break;
+		}
+
+		atomic_inc(&bo->gpu_usecount);
+		job->mappings[i] = mapping;
+	}
+
+	return ret;
 }
 
 /**
@@ -303,21 +341,26 @@
 	}
 
 	/* Don't allow mmapping of heap objects as pages are not pinned. */
-	if (to_panfrost_bo(gem_obj)->is_heap)
-		return -EINVAL;
+	if (to_panfrost_bo(gem_obj)->is_heap) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	ret = drm_gem_create_mmap_offset(gem_obj);
 	if (ret == 0)
 		args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node);
-	drm_gem_object_put_unlocked(gem_obj);
 
+out:
+	drm_gem_object_put_unlocked(gem_obj);
 	return ret;
 }
 
 static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv)
 {
+	struct panfrost_file_priv *priv = file_priv->driver_priv;
 	struct drm_panfrost_get_bo_offset *args = data;
+	struct panfrost_gem_mapping *mapping;
 	struct drm_gem_object *gem_obj;
 	struct panfrost_gem_object *bo;
 
@@ -328,18 +371,26 @@
 	}
 	bo = to_panfrost_bo(gem_obj);
 
-	args->offset = bo->node.start << PAGE_SHIFT;
-
+	mapping = panfrost_gem_mapping_get(bo, priv);
 	drm_gem_object_put_unlocked(gem_obj);
+
+	if (!mapping)
+		return -EINVAL;
+
+	args->offset = mapping->mmnode.start << PAGE_SHIFT;
+	panfrost_gem_mapping_put(mapping);
 	return 0;
 }
 
 static int panfrost_ioctl_madvise(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv)
 {
+	struct panfrost_file_priv *priv = file_priv->driver_priv;
 	struct drm_panfrost_madvise *args = data;
 	struct panfrost_device *pfdev = dev->dev_private;
 	struct drm_gem_object *gem_obj;
+	struct panfrost_gem_object *bo;
+	int ret = 0;
 
 	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
 	if (!gem_obj) {
@@ -347,23 +398,48 @@
 		return -ENOENT;
 	}
 
+	bo = to_panfrost_bo(gem_obj);
+
+	mutex_lock(&pfdev->shrinker_lock);
+	mutex_lock(&bo->mappings.lock);
+	if (args->madv == PANFROST_MADV_DONTNEED) {
+		struct panfrost_gem_mapping *first;
+
+		first = list_first_entry(&bo->mappings.list,
+					 struct panfrost_gem_mapping,
+					 node);
+
+		/*
+		 * If we want to mark the BO purgeable, there must be only one
+		 * user: the caller FD.
+		 * We could do something smarter and mark the BO purgeable only
+		 * when all its users have marked it purgeable, but globally
+		 * visible/shared BOs are likely to never be marked purgeable
+		 * anyway, so let's not bother.
+		 */
+		if (!list_is_singular(&bo->mappings.list) ||
+		    WARN_ON_ONCE(first->mmu != &priv->mmu)) {
+			ret = -EINVAL;
+			goto out_unlock_mappings;
+		}
+	}
+
 	args->retained = drm_gem_shmem_madvise(gem_obj, args->madv);
 
 	if (args->retained) {
-		struct panfrost_gem_object *bo = to_panfrost_bo(gem_obj);
-
-		mutex_lock(&pfdev->shrinker_lock);
-
 		if (args->madv == PANFROST_MADV_DONTNEED)
-			list_add_tail(&bo->base.madv_list, &pfdev->shrinker_list);
+			list_add_tail(&bo->base.madv_list,
+				      &pfdev->shrinker_list);
 		else if (args->madv == PANFROST_MADV_WILLNEED)
 			list_del_init(&bo->base.madv_list);
-
-		mutex_unlock(&pfdev->shrinker_lock);
 	}
 
+out_unlock_mappings:
+	mutex_unlock(&bo->mappings.lock);
+	mutex_unlock(&pfdev->shrinker_lock);
+
 	drm_gem_object_put_unlocked(gem_obj);
-	return 0;
+	return ret;
 }
 
 int panfrost_unstable_ioctl_check(void)
@@ -443,7 +519,7 @@
 {
 	struct panfrost_file_priv *panfrost_priv = file->driver_priv;
 
-	panfrost_perfcnt_close(panfrost_priv);
+	panfrost_perfcnt_close(file);
 	panfrost_job_close(panfrost_priv);
 
 	panfrost_mmu_pgtable_free(panfrost_priv);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index acb07fe..ac9de37 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -19,6 +19,22 @@
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	struct panfrost_device *pfdev = obj->dev->dev_private;
 
+	/*
+	 * Make sure the BO is no longer inserted in the shrinker list before
+	 * taking care of the destruction itself. If we don't do that we have a
+	 * race condition between this function and what's done in
+	 * panfrost_gem_shrinker_scan().
+	 */
+	mutex_lock(&pfdev->shrinker_lock);
+	list_del_init(&bo->base.madv_list);
+	mutex_unlock(&pfdev->shrinker_lock);
+
+	/*
+	 * If we still have mappings attached to the BO, there's a problem in
+	 * our refcounting.
+	 */
+	WARN_ON_ONCE(!list_empty(&bo->mappings.list));
+
 	if (bo->sgts) {
 		int i;
 		int n_sgt = bo->base.base.size / SZ_2M;
@@ -30,18 +46,74 @@
 				sg_free_table(&bo->sgts[i]);
 			}
 		}
-		kfree(bo->sgts);
+		kvfree(bo->sgts);
 	}
 
-	mutex_lock(&pfdev->shrinker_lock);
-	if (!list_empty(&bo->base.madv_list))
-		list_del(&bo->base.madv_list);
-	mutex_unlock(&pfdev->shrinker_lock);
-
 	drm_gem_shmem_free_object(obj);
 }
 
-static int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
+struct panfrost_gem_mapping *
+panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
+			 struct panfrost_file_priv *priv)
+{
+	struct panfrost_gem_mapping *iter, *mapping = NULL;
+
+	mutex_lock(&bo->mappings.lock);
+	list_for_each_entry(iter, &bo->mappings.list, node) {
+		if (iter->mmu == &priv->mmu) {
+			kref_get(&iter->refcount);
+			mapping = iter;
+			break;
+		}
+	}
+	mutex_unlock(&bo->mappings.lock);
+
+	return mapping;
+}
+
+static void
+panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping)
+{
+	struct panfrost_file_priv *priv;
+
+	if (mapping->active)
+		panfrost_mmu_unmap(mapping);
+
+	priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu);
+	spin_lock(&priv->mm_lock);
+	if (drm_mm_node_allocated(&mapping->mmnode))
+		drm_mm_remove_node(&mapping->mmnode);
+	spin_unlock(&priv->mm_lock);
+}
+
+static void panfrost_gem_mapping_release(struct kref *kref)
+{
+	struct panfrost_gem_mapping *mapping;
+
+	mapping = container_of(kref, struct panfrost_gem_mapping, refcount);
+
+	panfrost_gem_teardown_mapping(mapping);
+	drm_gem_object_put_unlocked(&mapping->obj->base.base);
+	kfree(mapping);
+}
+
+void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping)
+{
+	if (!mapping)
+		return;
+
+	kref_put(&mapping->refcount, panfrost_gem_mapping_release);
+}
+
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo)
+{
+	struct panfrost_gem_mapping *mapping;
+
+	list_for_each_entry(mapping, &bo->mappings.list, node)
+		panfrost_gem_teardown_mapping(mapping);
+}
+
+int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
 {
 	int ret;
 	size_t size = obj->size;
@@ -49,6 +121,16 @@
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	unsigned long color = bo->noexec ? PANFROST_BO_NOEXEC : 0;
 	struct panfrost_file_priv *priv = file_priv->driver_priv;
+	struct panfrost_gem_mapping *mapping;
+
+	mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
+	if (!mapping)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&mapping->node);
+	kref_init(&mapping->refcount);
+	drm_gem_object_get(obj);
+	mapping->obj = bo;
 
 	/*
 	 * Executable buffers cannot cross a 16MB boundary as the program
@@ -61,37 +143,48 @@
 	else
 		align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0;
 
-	bo->mmu = &priv->mmu;
+	mapping->mmu = &priv->mmu;
 	spin_lock(&priv->mm_lock);
-	ret = drm_mm_insert_node_generic(&priv->mm, &bo->node,
+	ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode,
 					 size >> PAGE_SHIFT, align, color, 0);
 	spin_unlock(&priv->mm_lock);
 	if (ret)
-		return ret;
+		goto err;
 
 	if (!bo->is_heap) {
-		ret = panfrost_mmu_map(bo);
-		if (ret) {
-			spin_lock(&priv->mm_lock);
-			drm_mm_remove_node(&bo->node);
-			spin_unlock(&priv->mm_lock);
-		}
+		ret = panfrost_mmu_map(mapping);
+		if (ret)
+			goto err;
 	}
+
+	mutex_lock(&bo->mappings.lock);
+	WARN_ON(bo->base.madv != PANFROST_MADV_WILLNEED);
+	list_add_tail(&mapping->node, &bo->mappings.list);
+	mutex_unlock(&bo->mappings.lock);
+
+err:
+	if (ret)
+		panfrost_gem_mapping_put(mapping);
 	return ret;
 }
 
-static void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv)
+void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv)
 {
-	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	struct panfrost_file_priv *priv = file_priv->driver_priv;
+	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+	struct panfrost_gem_mapping *mapping = NULL, *iter;
 
-	if (bo->is_mapped)
-		panfrost_mmu_unmap(bo);
+	mutex_lock(&bo->mappings.lock);
+	list_for_each_entry(iter, &bo->mappings.list, node) {
+		if (iter->mmu == &priv->mmu) {
+			mapping = iter;
+			list_del(&iter->node);
+			break;
+		}
+	}
+	mutex_unlock(&bo->mappings.lock);
 
-	spin_lock(&priv->mm_lock);
-	if (drm_mm_node_allocated(&bo->node))
-		drm_mm_remove_node(&bo->node);
-	spin_unlock(&priv->mm_lock);
+	panfrost_gem_mapping_put(mapping);
 }
 
 static int panfrost_gem_pin(struct drm_gem_object *obj)
@@ -131,6 +224,8 @@
 	if (!obj)
 		return NULL;
 
+	INIT_LIST_HEAD(&obj->mappings.list);
+	mutex_init(&obj->mappings.lock);
 	obj->base.base.funcs = &panfrost_gem_funcs;
 
 	return &obj->base.base;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index 5092081..8088d5f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -13,23 +13,52 @@
 	struct drm_gem_shmem_object base;
 	struct sg_table *sgts;
 
-	struct panfrost_mmu *mmu;
-	struct drm_mm_node node;
-	bool is_mapped		:1;
+	/*
+	 * Use a list for now. If searching a mapping ever becomes the
+	 * bottleneck, we should consider using an RB-tree, or even better,
+	 * let the core store drm_gem_object_mapping entries (where we
+	 * could place driver specific data) instead of drm_gem_object ones
+	 * in its drm_file->object_idr table.
+	 *
+	 * struct drm_gem_object_mapping {
+	 *	struct drm_gem_object *obj;
+	 *	void *driver_priv;
+	 * };
+	 */
+	struct {
+		struct list_head list;
+		struct mutex lock;
+	} mappings;
+
+	/*
+	 * Count the number of jobs referencing this BO so we don't let the
+	 * shrinker reclaim this object prematurely.
+	 */
+	atomic_t gpu_usecount;
+
 	bool noexec		:1;
 	bool is_heap		:1;
 };
 
+struct panfrost_gem_mapping {
+	struct list_head node;
+	struct kref refcount;
+	struct panfrost_gem_object *obj;
+	struct drm_mm_node mmnode;
+	struct panfrost_mmu *mmu;
+	bool active		:1;
+};
+
 static inline
 struct  panfrost_gem_object *to_panfrost_bo(struct drm_gem_object *obj)
 {
 	return container_of(to_drm_gem_shmem_obj(obj), struct panfrost_gem_object, base);
 }
 
-static inline
-struct  panfrost_gem_object *drm_mm_node_to_panfrost_bo(struct drm_mm_node *node)
+static inline struct panfrost_gem_mapping *
+drm_mm_node_to_panfrost_mapping(struct drm_mm_node *node)
 {
-	return container_of(node, struct panfrost_gem_object, node);
+	return container_of(node, struct panfrost_gem_mapping, mmnode);
 }
 
 struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t size);
@@ -45,6 +74,16 @@
 				u32 flags,
 				uint32_t *handle);
 
+int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv);
+void panfrost_gem_close(struct drm_gem_object *obj,
+			struct drm_file *file_priv);
+
+struct panfrost_gem_mapping *
+panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
+			 struct panfrost_file_priv *priv);
+void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo);
+
 void panfrost_gem_shrinker_init(struct drm_device *dev);
 void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index 458f0fa..1b9f68d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -39,15 +39,27 @@
 static bool panfrost_gem_purge(struct drm_gem_object *obj)
 {
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+	bool ret = false;
 
-	if (!mutex_trylock(&shmem->pages_lock))
+	if (atomic_read(&bo->gpu_usecount))
 		return false;
 
-	panfrost_mmu_unmap(to_panfrost_bo(obj));
+	if (!mutex_trylock(&bo->mappings.lock))
+		return false;
+
+	if (!mutex_trylock(&shmem->pages_lock))
+		goto unlock_mappings;
+
+	panfrost_gem_teardown_mappings_locked(bo);
 	drm_gem_shmem_purge_locked(obj);
+	ret = true;
 
 	mutex_unlock(&shmem->pages_lock);
-	return true;
+
+unlock_mappings:
+	mutex_unlock(&bo->mappings.lock);
+	return ret;
 }
 
 static unsigned long
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 8822ec1..0d39a20 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -75,6 +75,17 @@
 	return 0;
 }
 
+void panfrost_gpu_amlogic_quirk(struct panfrost_device *pfdev)
+{
+	/*
+	 * The Amlogic integrated Mali-T820, Mali-G31 & Mali-G52 needs
+	 * these undocumented bits in GPU_PWR_OVERRIDE1 to be set in order
+	 * to operate correctly.
+	 */
+	gpu_write(pfdev, GPU_PWR_KEY, GPU_PWR_KEY_UNLOCK);
+	gpu_write(pfdev, GPU_PWR_OVERRIDE1, 0xfff | (0x20 << 16));
+}
+
 static void panfrost_gpu_init_quirks(struct panfrost_device *pfdev)
 {
 	u32 quirks = 0;
@@ -304,6 +315,8 @@
 	int ret;
 	u32 val;
 
+	panfrost_gpu_init_quirks(pfdev);
+
 	/* Just turn on everything for now */
 	gpu_write(pfdev, L2_PWRON_LO, pfdev->features.l2_present);
 	ret = readl_relaxed_poll_timeout(pfdev->iomem + L2_READY_LO,
@@ -357,7 +370,6 @@
 		return err;
 	}
 
-	panfrost_gpu_init_quirks(pfdev);
 	panfrost_gpu_power_on(pfdev);
 
 	return 0;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.h b/drivers/gpu/drm/panfrost/panfrost_gpu.h
index 4112412..468c51e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.h
@@ -16,4 +16,6 @@
 void panfrost_gpu_power_on(struct panfrost_device *pfdev);
 void panfrost_gpu_power_off(struct panfrost_device *pfdev);
 
+void panfrost_gpu_amlogic_quirk(struct panfrost_device *pfdev);
+
 #endif
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 21f34d4..9f770d4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -269,9 +269,25 @@
 	dma_fence_put(job->done_fence);
 	dma_fence_put(job->render_done_fence);
 
+	if (job->mappings) {
+		for (i = 0; i < job->bo_count; i++) {
+			if (!job->mappings[i])
+				break;
+
+			atomic_dec(&job->mappings[i]->obj->gpu_usecount);
+			panfrost_gem_mapping_put(job->mappings[i]);
+		}
+		kvfree(job->mappings);
+	}
+
 	if (job->bos) {
-		for (i = 0; i < job->bo_count; i++)
+		struct panfrost_gem_object *bo;
+
+		for (i = 0; i < job->bo_count; i++) {
+			bo = to_panfrost_bo(job->bos[i]);
 			drm_gem_object_put_unlocked(job->bos[i]);
+		}
+
 		kvfree(job->bos);
 	}
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h b/drivers/gpu/drm/panfrost/panfrost_job.h
index 6245412..bbd3ba9 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.h
+++ b/drivers/gpu/drm/panfrost/panfrost_job.h
@@ -32,6 +32,7 @@
 
 	/* Exclusive fences we have taken from the BOs to wait for */
 	struct dma_fence **implicit_fences;
+	struct panfrost_gem_mapping **mappings;
 	struct drm_gem_object **bos;
 	u32 bo_count;
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index a3ed64a..8a014dc 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -52,25 +52,16 @@
 }
 
 static void lock_region(struct panfrost_device *pfdev, u32 as_nr,
-			u64 iova, size_t size)
+			u64 iova, u64 size)
 {
 	u8 region_width;
 	u64 region = iova & PAGE_MASK;
-	/*
-	 * fls returns:
-	 * 1 .. 32
-	 *
-	 * 10 + fls(num_pages)
-	 * results in the range (11 .. 42)
+
+	/* The size is encoded as ceil(log2) minus(1), which may be calculated
+	 * with fls. The size must be clamped to hardware bounds.
 	 */
-
-	size = round_up(size, PAGE_SIZE);
-
-	region_width = 10 + fls(size >> PAGE_SHIFT);
-	if ((size >> PAGE_SHIFT) != (1ul << (region_width - 11))) {
-		/* not pow2, so must go up to the next pow2 */
-		region_width += 1;
-	}
+	size = max_t(u64, size, AS_LOCK_REGION_MIN_SIZE);
+	region_width = fls64(size - 1) - 1;
 	region |= region_width;
 
 	/* Lock the region that needs to be updated */
@@ -81,7 +72,7 @@
 
 
 static int mmu_hw_do_operation_locked(struct panfrost_device *pfdev, int as_nr,
-				      u64 iova, size_t size, u32 op)
+				      u64 iova, u64 size, u32 op)
 {
 	if (as_nr < 0)
 		return 0;
@@ -98,7 +89,7 @@
 
 static int mmu_hw_do_operation(struct panfrost_device *pfdev,
 			       struct panfrost_mmu *mmu,
-			       u64 iova, size_t size, u32 op)
+			       u64 iova, u64 size, u32 op)
 {
 	int ret;
 
@@ -115,7 +106,7 @@
 	u64 transtab = cfg->arm_mali_lpae_cfg.transtab;
 	u64 memattr = cfg->arm_mali_lpae_cfg.memattr;
 
-	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0ULL, AS_COMMAND_FLUSH_MEM);
 
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), transtab & 0xffffffffUL);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), transtab >> 32);
@@ -131,7 +122,7 @@
 
 static void panfrost_mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
 {
-	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0ULL, AS_COMMAND_FLUSH_MEM);
 
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), 0);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), 0);
@@ -151,7 +142,12 @@
 	as = mmu->as;
 	if (as >= 0) {
 		int en = atomic_inc_return(&mmu->as_count);
-		WARN_ON(en >= NUM_JOB_SLOTS);
+
+		/*
+		 * AS can be retained by active jobs or a perfcnt context,
+		 * hence the '+ 1' here.
+		 */
+		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
 
 		list_move(&mmu->list, &pfdev->as_lru_list);
 		goto out;
@@ -226,7 +222,7 @@
 
 static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
 				     struct panfrost_mmu *mmu,
-				     u64 iova, size_t size)
+				     u64 iova, u64 size)
 {
 	if (mmu->as < 0)
 		return;
@@ -269,14 +265,15 @@
 	return 0;
 }
 
-int panfrost_mmu_map(struct panfrost_gem_object *bo)
+int panfrost_mmu_map(struct panfrost_gem_mapping *mapping)
 {
+	struct panfrost_gem_object *bo = mapping->obj;
 	struct drm_gem_object *obj = &bo->base.base;
 	struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
 	struct sg_table *sgt;
 	int prot = IOMMU_READ | IOMMU_WRITE;
 
-	if (WARN_ON(bo->is_mapped))
+	if (WARN_ON(mapping->active))
 		return 0;
 
 	if (bo->noexec)
@@ -286,25 +283,28 @@
 	if (WARN_ON(IS_ERR(sgt)))
 		return PTR_ERR(sgt);
 
-	mmu_map_sg(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, prot, sgt);
-	bo->is_mapped = true;
+	mmu_map_sg(pfdev, mapping->mmu, mapping->mmnode.start << PAGE_SHIFT,
+		   prot, sgt);
+	mapping->active = true;
 
 	return 0;
 }
 
-void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
+void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping)
 {
+	struct panfrost_gem_object *bo = mapping->obj;
 	struct drm_gem_object *obj = &bo->base.base;
 	struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
-	struct io_pgtable_ops *ops = bo->mmu->pgtbl_ops;
-	u64 iova = bo->node.start << PAGE_SHIFT;
-	size_t len = bo->node.size << PAGE_SHIFT;
+	struct io_pgtable_ops *ops = mapping->mmu->pgtbl_ops;
+	u64 iova = mapping->mmnode.start << PAGE_SHIFT;
+	size_t len = mapping->mmnode.size << PAGE_SHIFT;
 	size_t unmapped_len = 0;
 
-	if (WARN_ON(!bo->is_mapped))
+	if (WARN_ON(!mapping->active))
 		return;
 
-	dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", bo->mmu->as, iova, len);
+	dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx",
+		mapping->mmu->as, iova, len);
 
 	while (unmapped_len < len) {
 		size_t unmapped_page;
@@ -318,8 +318,9 @@
 		unmapped_len += pgsize;
 	}
 
-	panfrost_mmu_flush_range(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, len);
-	bo->is_mapped = false;
+	panfrost_mmu_flush_range(pfdev, mapping->mmu,
+				 mapping->mmnode.start << PAGE_SHIFT, len);
+	mapping->active = false;
 }
 
 static void mmu_tlb_inv_context_s1(void *cookie)
@@ -394,10 +395,10 @@
 	free_io_pgtable_ops(mmu->pgtbl_ops);
 }
 
-static struct panfrost_gem_object *
-addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
+static struct panfrost_gem_mapping *
+addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 {
-	struct panfrost_gem_object *bo = NULL;
+	struct panfrost_gem_mapping *mapping = NULL;
 	struct panfrost_file_priv *priv;
 	struct drm_mm_node *node;
 	u64 offset = addr >> PAGE_SHIFT;
@@ -418,8 +419,9 @@
 	drm_mm_for_each_node(node, &priv->mm) {
 		if (offset >= node->start &&
 		    offset < (node->start + node->size)) {
-			bo = drm_mm_node_to_panfrost_bo(node);
-			drm_gem_object_get(&bo->base.base);
+			mapping = drm_mm_node_to_panfrost_mapping(node);
+
+			kref_get(&mapping->refcount);
 			break;
 		}
 	}
@@ -427,7 +429,7 @@
 	spin_unlock(&priv->mm_lock);
 out:
 	spin_unlock(&pfdev->as_lock);
-	return bo;
+	return mapping;
 }
 
 #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
@@ -436,28 +438,30 @@
 				       u64 addr)
 {
 	int ret, i;
+	struct panfrost_gem_mapping *bomapping;
 	struct panfrost_gem_object *bo;
 	struct address_space *mapping;
 	pgoff_t page_offset;
 	struct sg_table *sgt;
 	struct page **pages;
 
-	bo = addr_to_drm_mm_node(pfdev, as, addr);
-	if (!bo)
+	bomapping = addr_to_mapping(pfdev, as, addr);
+	if (!bomapping)
 		return -ENOENT;
 
+	bo = bomapping->obj;
 	if (!bo->is_heap) {
 		dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)",
-			 bo->node.start << PAGE_SHIFT);
+			 bomapping->mmnode.start << PAGE_SHIFT);
 		ret = -EINVAL;
 		goto err_bo;
 	}
-	WARN_ON(bo->mmu->as != as);
+	WARN_ON(bomapping->mmu->as != as);
 
 	/* Assume 2MB alignment and size multiple */
 	addr &= ~((u64)SZ_2M - 1);
 	page_offset = addr >> PAGE_SHIFT;
-	page_offset -= bo->node.start;
+	page_offset -= bomapping->mmnode.start;
 
 	mutex_lock(&bo->base.pages_lock);
 
@@ -473,7 +477,7 @@
 		pages = kvmalloc_array(bo->base.base.size >> PAGE_SHIFT,
 				       sizeof(struct page *), GFP_KERNEL | __GFP_ZERO);
 		if (!pages) {
-			kfree(bo->sgts);
+			kvfree(bo->sgts);
 			bo->sgts = NULL;
 			mutex_unlock(&bo->base.pages_lock);
 			ret = -ENOMEM;
@@ -481,8 +485,14 @@
 		}
 		bo->base.pages = pages;
 		bo->base.pages_use_count = 1;
-	} else
+	} else {
 		pages = bo->base.pages;
+		if (pages[page_offset]) {
+			/* Pages are already mapped, bail out. */
+			mutex_unlock(&bo->base.pages_lock);
+			goto out;
+		}
+	}
 
 	mapping = bo->base.base.filp->f_mapping;
 	mapping_set_unevictable(mapping);
@@ -509,13 +519,15 @@
 		goto err_map;
 	}
 
-	mmu_map_sg(pfdev, bo->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);
+	mmu_map_sg(pfdev, bomapping->mmu, addr,
+		   IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);
 
-	bo->is_mapped = true;
+	bomapping->active = true;
 
 	dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr);
 
-	drm_gem_object_put_unlocked(&bo->base.base);
+out:
+	panfrost_gem_mapping_put(bomapping);
 
 	return 0;
 
@@ -586,37 +598,31 @@
 		access_type = (fault_status >> 8) & 0x3;
 		source_id = (fault_status >> 16);
 
-		/* Page fault only */
-		if ((status & mask) == BIT(i)) {
-			WARN_ON(exception_type < 0xC1 || exception_type > 0xC4);
-
-			ret = panfrost_mmu_map_fault_addr(pfdev, i, addr);
-			if (!ret) {
-				mmu_write(pfdev, MMU_INT_CLEAR, BIT(i));
-				status &= ~mask;
-				continue;
-			}
-		}
-
-		/* terminal fault, print info about the fault */
-		dev_err(pfdev->dev,
-			"Unhandled Page fault in AS%d at VA 0x%016llX\n"
-			"Reason: %s\n"
-			"raw fault status: 0x%X\n"
-			"decoded fault status: %s\n"
-			"exception type 0x%X: %s\n"
-			"access type 0x%X: %s\n"
-			"source id 0x%X\n",
-			i, addr,
-			"TODO",
-			fault_status,
-			(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
-			exception_type, panfrost_exception_name(pfdev, exception_type),
-			access_type, access_type_name(pfdev, fault_status),
-			source_id);
-
 		mmu_write(pfdev, MMU_INT_CLEAR, mask);
 
+		/* Page fault only */
+		ret = -1;
+		if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0)
+			ret = panfrost_mmu_map_fault_addr(pfdev, i, addr);
+
+		if (ret)
+			/* terminal fault, print info about the fault */
+			dev_err(pfdev->dev,
+				"Unhandled Page fault in AS%d at VA 0x%016llX\n"
+				"Reason: %s\n"
+				"raw fault status: 0x%X\n"
+				"decoded fault status: %s\n"
+				"exception type 0x%X: %s\n"
+				"access type 0x%X: %s\n"
+				"source id 0x%X\n",
+				i, addr,
+				"TODO",
+				fault_status,
+				(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
+				exception_type, panfrost_exception_name(pfdev, exception_type),
+				access_type, access_type_name(pfdev, fault_status),
+				source_id);
+
 		status &= ~mask;
 	}
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h
index 7c5b677..44fc2ed 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.h
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h
@@ -4,12 +4,12 @@
 #ifndef __PANFROST_MMU_H__
 #define __PANFROST_MMU_H__
 
-struct panfrost_gem_object;
+struct panfrost_gem_mapping;
 struct panfrost_file_priv;
 struct panfrost_mmu;
 
-int panfrost_mmu_map(struct panfrost_gem_object *bo);
-void panfrost_mmu_unmap(struct panfrost_gem_object *bo);
+int panfrost_mmu_map(struct panfrost_gem_mapping *mapping);
+void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping);
 
 int panfrost_mmu_init(struct panfrost_device *pfdev);
 void panfrost_mmu_fini(struct panfrost_device *pfdev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 2dba192..6913578 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -25,7 +25,7 @@
 #define V4_SHADERS_PER_COREGROUP	4
 
 struct panfrost_perfcnt {
-	struct panfrost_gem_object *bo;
+	struct panfrost_gem_mapping *mapping;
 	size_t bosize;
 	void *buf;
 	struct panfrost_file_priv *user;
@@ -49,7 +49,7 @@
 	int ret;
 
 	reinit_completion(&pfdev->perfcnt->dump_comp);
-	gpuva = pfdev->perfcnt->bo->node.start << PAGE_SHIFT;
+	gpuva = pfdev->perfcnt->mapping->mmnode.start << PAGE_SHIFT;
 	gpu_write(pfdev, GPU_PERFCNT_BASE_LO, gpuva);
 	gpu_write(pfdev, GPU_PERFCNT_BASE_HI, gpuva >> 32);
 	gpu_write(pfdev, GPU_INT_CLEAR,
@@ -67,12 +67,13 @@
 }
 
 static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
-					  struct panfrost_file_priv *user,
+					  struct drm_file *file_priv,
 					  unsigned int counterset)
 {
+	struct panfrost_file_priv *user = file_priv->driver_priv;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 	struct drm_gem_shmem_object *bo;
-	u32 cfg;
+	u32 cfg, as;
 	int ret;
 
 	if (user == perfcnt->user)
@@ -88,17 +89,22 @@
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
-	perfcnt->bo = to_panfrost_bo(&bo->base);
-
 	/* Map the perfcnt buf in the address space attached to file_priv. */
-	ret = panfrost_mmu_map(perfcnt->bo);
+	ret = panfrost_gem_open(&bo->base, file_priv);
 	if (ret)
 		goto err_put_bo;
 
+	perfcnt->mapping = panfrost_gem_mapping_get(to_panfrost_bo(&bo->base),
+						    user);
+	if (!perfcnt->mapping) {
+		ret = -EINVAL;
+		goto err_close_bo;
+	}
+
 	perfcnt->buf = drm_gem_shmem_vmap(&bo->base);
 	if (IS_ERR(perfcnt->buf)) {
 		ret = PTR_ERR(perfcnt->buf);
-		goto err_put_bo;
+		goto err_put_mapping;
 	}
 
 	/*
@@ -120,12 +126,8 @@
 
 	perfcnt->user = user;
 
-	/*
-	 * Always use address space 0 for now.
-	 * FIXME: this needs to be updated when we start using different
-	 * address space.
-	 */
-	cfg = GPU_PERFCNT_CFG_AS(0) |
+	as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu);
+	cfg = GPU_PERFCNT_CFG_AS(as) |
 	      GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL);
 
 	/*
@@ -153,18 +155,26 @@
 	if (panfrost_has_hw_issue(pfdev, HW_ISSUE_8186))
 		gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0xffffffff);
 
+	/* The BO ref is retained by the mapping. */
+	drm_gem_object_put_unlocked(&bo->base);
+
 	return 0;
 
 err_vunmap:
-	drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf);
+	drm_gem_shmem_vunmap(&bo->base, perfcnt->buf);
+err_put_mapping:
+	panfrost_gem_mapping_put(perfcnt->mapping);
+err_close_bo:
+	panfrost_gem_close(&bo->base, file_priv);
 err_put_bo:
 	drm_gem_object_put_unlocked(&bo->base);
 	return ret;
 }
 
 static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev,
-					   struct panfrost_file_priv *user)
+					   struct drm_file *file_priv)
 {
+	struct panfrost_file_priv *user = file_priv->driver_priv;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 
 	if (user != perfcnt->user)
@@ -178,10 +188,12 @@
 		  GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF));
 
 	perfcnt->user = NULL;
-	drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf);
+	drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf);
 	perfcnt->buf = NULL;
-	drm_gem_object_put_unlocked(&perfcnt->bo->base.base);
-	perfcnt->bo = NULL;
+	panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
+	panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
+	panfrost_gem_mapping_put(perfcnt->mapping);
+	perfcnt->mapping = NULL;
 	pm_runtime_mark_last_busy(pfdev->dev);
 	pm_runtime_put_autosuspend(pfdev->dev);
 
@@ -191,7 +203,6 @@
 int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv)
 {
-	struct panfrost_file_priv *pfile = file_priv->driver_priv;
 	struct panfrost_device *pfdev = dev->dev_private;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 	struct drm_panfrost_perfcnt_enable *req = data;
@@ -207,10 +218,10 @@
 
 	mutex_lock(&perfcnt->lock);
 	if (req->enable)
-		ret = panfrost_perfcnt_enable_locked(pfdev, pfile,
+		ret = panfrost_perfcnt_enable_locked(pfdev, file_priv,
 						     req->counterset);
 	else
-		ret = panfrost_perfcnt_disable_locked(pfdev, pfile);
+		ret = panfrost_perfcnt_disable_locked(pfdev, file_priv);
 	mutex_unlock(&perfcnt->lock);
 
 	return ret;
@@ -248,15 +259,16 @@
 	return ret;
 }
 
-void panfrost_perfcnt_close(struct panfrost_file_priv *pfile)
+void panfrost_perfcnt_close(struct drm_file *file_priv)
 {
+	struct panfrost_file_priv *pfile = file_priv->driver_priv;
 	struct panfrost_device *pfdev = pfile->pfdev;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 
 	pm_runtime_get_sync(pfdev->dev);
 	mutex_lock(&perfcnt->lock);
 	if (perfcnt->user == pfile)
-		panfrost_perfcnt_disable_locked(pfdev, pfile);
+		panfrost_perfcnt_disable_locked(pfdev, file_priv);
 	mutex_unlock(&perfcnt->lock);
 	pm_runtime_mark_last_busy(pfdev->dev);
 	pm_runtime_put_autosuspend(pfdev->dev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.h b/drivers/gpu/drm/panfrost/panfrost_perfcnt.h
index 13b8fda..8bbcf5f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.h
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.h
@@ -9,7 +9,7 @@
 void panfrost_perfcnt_clean_cache_done(struct panfrost_device *pfdev);
 int panfrost_perfcnt_init(struct panfrost_device *pfdev);
 void panfrost_perfcnt_fini(struct panfrost_device *pfdev);
-void panfrost_perfcnt_close(struct panfrost_file_priv *pfile);
+void panfrost_perfcnt_close(struct drm_file *file_priv);
 int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 int panfrost_ioctl_perfcnt_dump(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index ea38ac6..2ae3a4d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -51,6 +51,10 @@
 #define GPU_STATUS			0x34
 #define   GPU_STATUS_PRFCNT_ACTIVE	BIT(2)
 #define GPU_LATEST_FLUSH_ID		0x38
+#define GPU_PWR_KEY			0x50	/* (WO) Power manager key register */
+#define  GPU_PWR_KEY_UNLOCK		0x2968A819
+#define GPU_PWR_OVERRIDE0		0x54	/* (RW) Power manager override settings */
+#define GPU_PWR_OVERRIDE1		0x58	/* (RW) Power manager override settings */
 #define GPU_FAULT_STATUS		0x3C
 #define GPU_FAULT_ADDRESS_LO		0x40
 #define GPU_FAULT_ADDRESS_HI		0x44
@@ -314,6 +318,8 @@
 #define AS_FAULTSTATUS_ACCESS_TYPE_READ		(0x2 << 8)
 #define AS_FAULTSTATUS_ACCESS_TYPE_WRITE	(0x3 << 8)
 
+#define AS_LOCK_REGION_MIN_SIZE                 (1ULL << 15)
+
 #define gpu_write(dev, reg, data) writel(data, dev->iomem + reg)
 #define gpu_read(dev, reg) readl(dev->iomem + reg)
 
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index ef09dc6..d082c19 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -480,9 +480,10 @@
 		return ret;
 
 	ret = qxl_release_reserve_list(release, true);
-	if (ret)
+	if (ret) {
+		qxl_release_free(qdev, release);
 		return ret;
-
+	}
 	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_SURFACE_CMD_CREATE;
 	cmd->flags = QXL_SURF_FLAG_KEEP_DATA;
@@ -499,8 +500,8 @@
 	/* no need to add a release to the fence for this surface bo,
 	   since it is only released when we ask to destroy the surface
 	   and it would never signal otherwise */
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
 	surf->hw_surf_alloc = true;
 	spin_lock(&qdev->surf_id_idr_lock);
@@ -542,9 +543,8 @@
 	cmd->surface_id = id;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
-
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 16d73b2..a6ee10c 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -325,6 +325,7 @@
 
 	head.id = i;
 	head.flags = 0;
+	head.surface_id = 0;
 	oldcount = qdev->monitors_config->count;
 	if (crtc->state->active) {
 		struct drm_display_mode *mode = &crtc->mode;
@@ -523,8 +524,8 @@
 	cmd->u.set.visible = 1;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 
 	return ret;
 
@@ -665,8 +666,8 @@
 	cmd->u.position.y = plane->state->crtc_y + fb->hot_y;
 
 	qxl_release_unmap(qdev, release, &cmd->release_info);
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 
 	if (old_cursor_bo != NULL)
 		qxl_bo_unpin(old_cursor_bo);
@@ -713,8 +714,8 @@
 	cmd->type = QXL_CURSOR_HIDE;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 }
 
 static void qxl_update_dumb_head(struct qxl_device *qdev,
@@ -1236,6 +1237,10 @@
 
 void qxl_modeset_fini(struct qxl_device *qdev)
 {
+	if (qdev->dumb_shadow_bo) {
+		drm_gem_object_put(&qdev->dumb_shadow_bo->tbo.base);
+		qdev->dumb_shadow_bo = NULL;
+	}
 	qxl_destroy_monitors_object(qdev);
 	drm_mode_config_cleanup(&qdev->ddev);
 }
diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c
index 5bebf1e..3599db0 100644
--- a/drivers/gpu/drm/qxl/qxl_draw.c
+++ b/drivers/gpu/drm/qxl/qxl_draw.c
@@ -209,9 +209,10 @@
 		goto out_release_backoff;
 
 	rects = drawable_set_clipping(qdev, num_clips, clips_bo);
-	if (!rects)
+	if (!rects) {
+		ret = -EINVAL;
 		goto out_release_backoff;
-
+	}
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
 
 	drawable->clip.type = SPICE_CLIP_TYPE_RECTS;
@@ -242,8 +243,8 @@
 	}
 	qxl_bo_kunmap(clips_bo);
 
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
 
 out_release_backoff:
 	if (ret)
diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c
index 272d19b..4a0dc13 100644
--- a/drivers/gpu/drm/qxl/qxl_dumb.c
+++ b/drivers/gpu/drm/qxl/qxl_dumb.c
@@ -58,6 +58,8 @@
 	surf.height = args->height;
 	surf.stride = pitch;
 	surf.format = format;
+	surf.data = 0;
+
 	r = qxl_gem_object_create_with_handle(qdev, file_priv,
 					      QXL_GEM_DOMAIN_SURFACE,
 					      args->size, &surf, &qobj,
diff --git a/drivers/gpu/drm/qxl/qxl_image.c b/drivers/gpu/drm/qxl/qxl_image.c
index 43688ec..60ab715 100644
--- a/drivers/gpu/drm/qxl/qxl_image.c
+++ b/drivers/gpu/drm/qxl/qxl_image.c
@@ -212,7 +212,8 @@
 		break;
 	default:
 		DRM_ERROR("unsupported image bit depth\n");
-		return -EINVAL; /* TODO: cleanup */
+		qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr);
+		return -EINVAL;
 	}
 	image->u.bitmap.flags = QXL_BITMAP_TOP_DOWN;
 	image->u.bitmap.x = width;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 8117a45..72f3f1b 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -261,11 +261,8 @@
 			apply_surf_reloc(qdev, &reloc_info[i]);
 	}
 
+	qxl_release_fence_buffer_objects(release);
 	ret = qxl_push_command_ring_release(qdev, release, cmd->type, true);
-	if (ret)
-		qxl_release_backoff_reserve_list(release);
-	else
-		qxl_release_fence_buffer_objects(release);
 
 out_free_bos:
 out_free_release:
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index 611cbe7..9bdbe0d 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -184,7 +184,7 @@
 
 	if (!qxl_check_device(qdev)) {
 		r = -ENODEV;
-		goto surface_mapping_free;
+		goto rom_unmap;
 	}
 
 	r = qxl_bo_init(qdev);
@@ -218,7 +218,7 @@
 				&(qdev->ram_header->cursor_ring_hdr),
 				sizeof(struct qxl_command),
 				QXL_CURSOR_RING_SIZE,
-				qdev->io_base + QXL_IO_NOTIFY_CMD,
+				qdev->io_base + QXL_IO_NOTIFY_CURSOR,
 				false,
 				&qdev->cursor_event);
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index c6fd123..1e62e7b 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -4366,7 +4366,7 @@
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			if (!pi->mem_gddr5) {
@@ -5578,6 +5578,7 @@
 	if (!rdev->pm.dpm.ps)
 		return -ENOMEM;
 	power_state_offset = (u8 *)state_array->states;
+	rdev->pm.dpm.num_ps = 0;
 	for (i = 0; i < state_array->ucNumEntries; i++) {
 		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
@@ -5587,10 +5588,8 @@
 		if (!rdev->pm.power_state[i].clock_info)
 			return -EINVAL;
 		ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL);
-		if (ps == NULL) {
-			kfree(rdev->pm.dpm.ps);
+		if (ps == NULL)
 			return -ENOMEM;
-		}
 		rdev->pm.dpm.ps[i].ps_priv = ps;
 		ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 					      non_clock_info,
@@ -5612,8 +5611,8 @@
 			k++;
 		}
 		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+		rdev->pm.dpm.num_ps = i + 1;
 	}
-	rdev->pm.dpm.num_ps = state_array->ucNumEntries;
 
 	/* fill in the vce power states */
 	for (i = 0; i < RADEON_MAX_VCE_LEVELS; i++) {
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 62eab82..8974427 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -6969,8 +6969,8 @@
 	}
 
 	/* setup interrupt control */
-	/* XXX this should actually be a bus address, not an MC address. same on older asics */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index d9e62ca..bd2e577 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2128,7 +2128,7 @@
 		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
 			ret = -EINVAL;
 
-		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
+		if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT))
 			ret = -EINVAL;
 
 		if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT))
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 7089dfc..110fb38 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1826,8 +1826,8 @@
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & RADEON_TXFORMAT_CUBIC_MAP_ENABLE)
 			track->textures[i].tex_coord_type = 2;
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index 8404014..f5f2ffe 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -476,8 +476,8 @@
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & R200_TXFORMAT_LOOKUP_DISABLE)
 			track->textures[i].lookup_disable = true;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index e937cc0..033bc46 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3696,8 +3696,8 @@
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index d59b004..147087a 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1554,6 +1554,7 @@
 	void                    *priv;
 	u32			new_active_crtcs;
 	int			new_active_crtc_count;
+	int			high_pixelclock_count;
 	u32			current_active_crtcs;
 	int			current_active_crtc_count;
 	bool single_display;
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 226a7bf..9e0aa35 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -2136,11 +2136,14 @@
 		return state_index;
 	/* last mode is usually default, array is low to high */
 	for (i = 0; i < num_modes; i++) {
-		rdev->pm.power_state[state_index].clock_info =
-			kcalloc(1, sizeof(struct radeon_pm_clock_info),
-				GFP_KERNEL);
+		/* avoid memory leaks from invalid modes or unknown frev. */
+		if (!rdev->pm.power_state[state_index].clock_info) {
+			rdev->pm.power_state[state_index].clock_info =
+				kzalloc(sizeof(struct radeon_pm_clock_info),
+					GFP_KERNEL);
+		}
 		if (!rdev->pm.power_state[state_index].clock_info)
-			return state_index;
+			goto out;
 		rdev->pm.power_state[state_index].num_clock_modes = 1;
 		rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE;
 		switch (frev) {
@@ -2259,17 +2262,24 @@
 			break;
 		}
 	}
+out:
+	/* free any unused clock_info allocation. */
+	if (state_index && state_index < num_modes) {
+		kfree(rdev->pm.power_state[state_index].clock_info);
+		rdev->pm.power_state[state_index].clock_info = NULL;
+	}
+
 	/* last mode is usually default */
-	if (rdev->pm.default_power_state_index == -1) {
+	if (state_index && rdev->pm.default_power_state_index == -1) {
 		rdev->pm.power_state[state_index - 1].type =
 			POWER_STATE_TYPE_DEFAULT;
 		rdev->pm.default_power_state_index = state_index - 1;
 		rdev->pm.power_state[state_index - 1].default_clock_mode =
 			&rdev->pm.power_state[state_index - 1].clock_info[0];
-		rdev->pm.power_state[state_index].flags &=
+		rdev->pm.power_state[state_index - 1].flags &=
 			~RADEON_PM_STATE_SINGLE_DISPLAY_ONLY;
-		rdev->pm.power_state[state_index].misc = 0;
-		rdev->pm.power_state[state_index].misc2 = 0;
+		rdev->pm.power_state[state_index - 1].misc = 0;
+		rdev->pm.power_state[state_index - 1].misc2 = 0;
 	}
 	return state_index;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 4d1490f..756a50e 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -108,25 +108,33 @@
 
 static bool radeon_read_platform_bios(struct radeon_device *rdev)
 {
-	uint8_t __iomem *bios;
-	size_t size;
+	phys_addr_t rom = rdev->pdev->rom;
+	size_t romlen = rdev->pdev->romlen;
+	void __iomem *bios;
 
 	rdev->bios = NULL;
 
-	bios = pci_platform_rom(rdev->pdev, &size);
-	if (!bios) {
+	if (!rom || romlen == 0)
 		return false;
-	}
 
-	if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) {
+	rdev->bios = kzalloc(romlen, GFP_KERNEL);
+	if (!rdev->bios)
 		return false;
-	}
-	rdev->bios = kmemdup(bios, size, GFP_KERNEL);
-	if (rdev->bios == NULL) {
-		return false;
-	}
+
+	bios = ioremap(rom, romlen);
+	if (!bios)
+		goto free_bios;
+
+	memcpy_fromio(rdev->bios, bios, romlen);
+	iounmap(bios);
+
+	if (rdev->bios[0] != 0x55 || rdev->bios[1] != 0xaa)
+		goto free_bios;
 
 	return true;
+free_bios:
+	kfree(rdev->bios);
+	return false;
 }
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index b684cd7..bc63f4c 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -883,8 +883,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (encoder) {
@@ -1029,8 +1031,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	encoder = radeon_best_single_encoder(connector);
@@ -1167,8 +1171,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	encoder = radeon_best_single_encoder(connector);
@@ -1251,8 +1257,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (radeon_connector->detected_hpd_without_ddc) {
@@ -1666,8 +1674,10 @@
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (!force && radeon_check_hpd_status_unchanged(connector)) {
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index e81b01f..27b1689 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -127,6 +127,8 @@
 
 	DRM_DEBUG_KMS("%d\n", radeon_crtc->crtc_id);
 
+	msleep(10);
+
 	WREG32(NI_INPUT_CSC_CONTROL + radeon_crtc->crtc_offset,
 	       (NI_INPUT_CSC_GRPH_MODE(NI_INPUT_CSC_BYPASS) |
 		NI_INPUT_CSC_OVL_MODE(NI_INPUT_CSC_BYPASS)));
@@ -629,8 +631,10 @@
 	dev = set->crtc->dev;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_crtc_helper_set_config(set, ctx);
 
@@ -1329,6 +1333,7 @@
 	/* Handle is imported dma-buf, so cannot be migrated to VRAM for scanout */
 	if (obj->import_attach) {
 		DRM_DEBUG_KMS("Cannot create framebuffer from imported dma_buf\n");
+		drm_gem_object_put(obj);
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 4528f4d..c257309 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -37,6 +37,7 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/mmu_notifier.h>
 
+#include <drm/drm_agpsupport.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_helper.h>
@@ -173,12 +174,7 @@
 int radeon_modeset = -1;
 int radeon_dynclks = -1;
 int radeon_r4xx_atom = 0;
-#ifdef __powerpc__
-/* Default to PCI on PowerPC (fdo #95017) */
 int radeon_agpmode = -1;
-#else
-int radeon_agpmode = 0;
-#endif
 int radeon_vram_limit = 0;
 int radeon_gart_size = -1; /* auto */
 int radeon_benchmarking = 0;
@@ -325,6 +321,7 @@
 			    const struct pci_device_id *ent)
 {
 	unsigned long flags = 0;
+	struct drm_device *dev;
 	int ret;
 
 	if (!ent)
@@ -365,7 +362,44 @@
 	if (ret)
 		return ret;
 
-	return drm_get_pci_dev(pdev, ent, &kms_driver);
+	dev = drm_dev_alloc(&kms_driver, &pdev->dev);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		goto err_free;
+
+	dev->pdev = pdev;
+#ifdef __alpha__
+	dev->hose = pdev->sysdata;
+#endif
+
+	pci_set_drvdata(pdev, dev);
+
+	if (pci_find_capability(dev->pdev, PCI_CAP_ID_AGP))
+		dev->agp = drm_agp_init(dev);
+	if (dev->agp) {
+		dev->agp->agp_mtrr = arch_phys_wc_add(
+			dev->agp->agp_info.aper_base,
+			dev->agp->agp_info.aper_size *
+			1024 * 1024);
+	}
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_agp;
+
+	return 0;
+
+err_agp:
+	if (dev->agp)
+		arch_phys_wc_del(dev->agp->agp_mtrr);
+	kfree(dev->agp);
+	pci_disable_device(pdev);
+err_free:
+	drm_dev_put(dev);
+	return ret;
 }
 
 static void
@@ -516,8 +550,10 @@
 	long ret;
 	dev = file_priv->minor->dev;
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_ioctl(filp, cmd, arg);
 	
@@ -578,7 +614,7 @@
 
 static struct drm_driver kms_driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_GEM | DRIVER_RENDER,
+	    DRIVER_GEM | DRIVER_RENDER,
 	.load = radeon_driver_load_kms,
 	.open = radeon_driver_open_kms,
 	.postclose = radeon_driver_postclose_kms,
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index e85c554..03d3550 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -31,6 +31,7 @@
 #include <linux/uaccess.h>
 #include <linux/vga_switcheroo.h>
 
+#include <drm/drm_agpsupport.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
@@ -77,6 +78,11 @@
 	radeon_modeset_fini(rdev);
 	radeon_device_fini(rdev);
 
+	if (dev->agp)
+		arch_phys_wc_del(dev->agp->agp_mtrr);
+	kfree(dev->agp);
+	dev->agp = NULL;
+
 done_free:
 	kfree(rdev);
 	dev->dev_private = NULL;
@@ -506,6 +512,7 @@
 			*value = rdev->config.si.backend_enable_mask;
 		} else {
 			DRM_DEBUG_KMS("BACKEND_ENABLED_MASK is si+ only!\n");
+			return -EINVAL;
 		}
 		break;
 	case RADEON_INFO_MAX_SCLK:
@@ -632,8 +639,10 @@
 	file_priv->driver_priv = NULL;
 
 	r = pm_runtime_get_sync(dev->dev);
-	if (r < 0)
+	if (r < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return r;
+	}
 
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN) {
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 5d10e11..c9ae12b 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1720,6 +1720,7 @@
 	struct drm_device *ddev = rdev->ddev;
 	struct drm_crtc *crtc;
 	struct radeon_crtc *radeon_crtc;
+	struct radeon_connector *radeon_connector;
 
 	if (!rdev->pm.dpm_enabled)
 		return;
@@ -1729,6 +1730,7 @@
 	/* update active crtc counts */
 	rdev->pm.dpm.new_active_crtcs = 0;
 	rdev->pm.dpm.new_active_crtc_count = 0;
+	rdev->pm.dpm.high_pixelclock_count = 0;
 	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
 		list_for_each_entry(crtc,
 				    &ddev->mode_config.crtc_list, head) {
@@ -1736,6 +1738,12 @@
 			if (crtc->enabled) {
 				rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id);
 				rdev->pm.dpm.new_active_crtc_count++;
+				if (!radeon_crtc->connector)
+					continue;
+
+				radeon_connector = to_radeon_connector(radeon_crtc->connector);
+				if (radeon_connector->pixelclock_for_modeset > 297000)
+					rdev->pm.dpm.high_pixelclock_count++;
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index b906e8f..7bc33a8 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -94,9 +94,19 @@
 
 	/* pin buffer into GTT */
 	ret = radeon_bo_pin(bo, RADEON_GEM_DOMAIN_GTT, NULL);
-	if (likely(ret == 0))
-		bo->prime_shared_count++;
+	if (unlikely(ret))
+		goto error;
 
+	if (bo->tbo.moving) {
+		ret = dma_fence_wait(bo->tbo.moving, false);
+		if (unlikely(ret)) {
+			radeon_bo_unpin(bo);
+			goto error;
+		}
+	}
+
+	bo->prime_shared_count++;
+error:
 	radeon_bo_unreserve(bo);
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 1ad5c3b..a18bf70 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -286,7 +286,7 @@
 	if (rdev->uvd.vcpu_bo == NULL)
 		return -EINVAL;
 
-	memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
+	memcpy_toio((void __iomem *)rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
 
 	size = radeon_bo_size(rdev->uvd.vcpu_bo);
 	size -= rdev->uvd_fw->size;
@@ -294,7 +294,7 @@
 	ptr = rdev->uvd.cpu_addr;
 	ptr += rdev->uvd_fw->size;
 
-	memset(ptr, 0, size);
+	memset_io((void __iomem *)ptr, 0, size);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 05894d1..1d8efb0 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5997,8 +5997,8 @@
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index a0b382a..97bab44 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3002,6 +3002,9 @@
 		    (rdev->pdev->device == 0x6605)) {
 			max_sclk = 75000;
 		}
+
+		if (rdev->pm.dpm.high_pixelclock_count > 1)
+			disable_sclk_switching = true;
 	}
 
 	if (rps->vce_active) {
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 1529849..7cdba77 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -23,6 +23,7 @@
 config DRM_RCAR_LVDS
 	tristate "R-Car DU LVDS Encoder Support"
 	depends on DRM && DRM_BRIDGE && OF
+	select DRM_KMS_HELPER
 	select DRM_PANEL
 	select OF_FLATTREE
 	select OF_OVERLAY
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index c643002..a0021fc 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -785,13 +785,15 @@
 
 		drm_plane_create_alpha_property(&plane->plane);
 
-		if (type == DRM_PLANE_TYPE_PRIMARY)
-			continue;
-
-		drm_object_attach_property(&plane->plane.base,
-					   rcdu->props.colorkey,
-					   RCAR_DU_COLORKEY_NONE);
-		drm_plane_create_zpos_property(&plane->plane, 1, 1, 7);
+		if (type == DRM_PLANE_TYPE_PRIMARY) {
+			drm_plane_create_zpos_immutable_property(&plane->plane,
+								 0);
+		} else {
+			drm_object_attach_property(&plane->plane.base,
+						   rcdu->props.colorkey,
+						   RCAR_DU_COLORKEY_NONE);
+			drm_plane_create_zpos_property(&plane->plane, 1, 1, 7);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index 5e4faf2..f1a81c9 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -392,12 +392,14 @@
 		drm_plane_helper_add(&plane->plane,
 				     &rcar_du_vsp_plane_helper_funcs);
 
-		if (type == DRM_PLANE_TYPE_PRIMARY)
-			continue;
-
-		drm_plane_create_alpha_property(&plane->plane);
-		drm_plane_create_zpos_property(&plane->plane, 1, 1,
-					       vsp->num_planes - 1);
+		if (type == DRM_PLANE_TYPE_PRIMARY) {
+			drm_plane_create_zpos_immutable_property(&plane->plane,
+								 0);
+		} else {
+			drm_plane_create_alpha_property(&plane->plane);
+			drm_plane_create_zpos_property(&plane->plane, 1, 1,
+						       vsp->num_planes - 1);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 3fc7e68..50c11a7 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -16,6 +16,7 @@
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/sys_soc.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -842,8 +843,23 @@
 	return 0;
 }
 
+static const struct rcar_lvds_device_info rcar_lvds_r8a7790es1_info = {
+	.gen = 2,
+	.quirks = RCAR_LVDS_QUIRK_LANES,
+	.pll_setup = rcar_lvds_pll_setup_gen2,
+};
+
+static const struct soc_device_attribute lvds_quirk_matches[] = {
+	{
+		.soc_id = "r8a7790", .revision = "ES1.*",
+		.data = &rcar_lvds_r8a7790es1_info,
+	},
+	{ /* sentinel */ }
+};
+
 static int rcar_lvds_probe(struct platform_device *pdev)
 {
+	const struct soc_device_attribute *attr;
 	struct rcar_lvds *lvds;
 	struct resource *mem;
 	int ret;
@@ -857,6 +873,10 @@
 	lvds->dev = &pdev->dev;
 	lvds->info = of_device_get_match_data(&pdev->dev);
 
+	attr = soc_device_match(lvds_quirk_matches);
+	if (attr)
+		lvds->info = attr->data;
+
 	ret = rcar_lvds_parse_dt(lvds);
 	if (ret < 0)
 		return ret;
@@ -893,12 +913,6 @@
 	.pll_setup = rcar_lvds_pll_setup_gen2,
 };
 
-static const struct rcar_lvds_device_info rcar_lvds_r8a7790_info = {
-	.gen = 2,
-	.quirks = RCAR_LVDS_QUIRK_LANES,
-	.pll_setup = rcar_lvds_pll_setup_gen2,
-};
-
 static const struct rcar_lvds_device_info rcar_lvds_gen3_info = {
 	.gen = 3,
 	.quirks = RCAR_LVDS_QUIRK_PWD,
@@ -930,7 +944,7 @@
 	{ .compatible = "renesas,r8a7744-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a774a1-lvds", .data = &rcar_lvds_gen3_info },
 	{ .compatible = "renesas,r8a774c0-lvds", .data = &rcar_lvds_r8a77990_info },
-	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_r8a7790_info },
+	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7791-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7793-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7795-lvds", .data = &rcar_lvds_gen3_info },
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index f38f5e1..ce98c08 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -325,15 +325,9 @@
 			    void *data)
 {
 	struct rockchip_dp_device *dp = dev_get_drvdata(dev);
-	const struct rockchip_dp_chip_data *dp_data;
 	struct drm_device *drm_dev = data;
 	int ret;
 
-	dp_data = of_device_get_match_data(dev);
-	if (!dp_data)
-		return -ENODEV;
-
-	dp->data = dp_data;
 	dp->drm_dev = drm_dev;
 
 	ret = rockchip_dp_drm_create_encoder(dp);
@@ -344,16 +338,9 @@
 
 	dp->plat_data.encoder = &dp->encoder;
 
-	dp->plat_data.dev_type = dp->data->chip_type;
-	dp->plat_data.power_on_start = rockchip_dp_poweron_start;
-	dp->plat_data.power_off = rockchip_dp_powerdown;
-	dp->plat_data.get_modes = rockchip_dp_get_modes;
-
-	dp->adp = analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data);
-	if (IS_ERR(dp->adp)) {
-		ret = PTR_ERR(dp->adp);
+	ret = analogix_dp_bind(dp->adp, drm_dev);
+	if (ret)
 		goto err_cleanup_encoder;
-	}
 
 	return 0;
 err_cleanup_encoder:
@@ -368,8 +355,6 @@
 
 	analogix_dp_unbind(dp->adp);
 	dp->encoder.funcs->destroy(&dp->encoder);
-
-	dp->adp = ERR_PTR(-ENODEV);
 }
 
 static const struct component_ops rockchip_dp_component_ops = {
@@ -380,10 +365,15 @@
 static int rockchip_dp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	const struct rockchip_dp_chip_data *dp_data;
 	struct drm_panel *panel = NULL;
 	struct rockchip_dp_device *dp;
 	int ret;
 
+	dp_data = of_device_get_match_data(dev);
+	if (!dp_data)
+		return -ENODEV;
+
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL);
 	if (ret < 0)
 		return ret;
@@ -394,7 +384,12 @@
 
 	dp->dev = dev;
 	dp->adp = ERR_PTR(-ENODEV);
+	dp->data = dp_data;
 	dp->plat_data.panel = panel;
+	dp->plat_data.dev_type = dp->data->chip_type;
+	dp->plat_data.power_on_start = rockchip_dp_poweron_start;
+	dp->plat_data.power_off = rockchip_dp_powerdown;
+	dp->plat_data.get_modes = rockchip_dp_get_modes;
 
 	ret = rockchip_dp_of_probe(dp);
 	if (ret < 0)
@@ -402,12 +397,19 @@
 
 	platform_set_drvdata(pdev, dp);
 
+	dp->adp = analogix_dp_probe(dev, &dp->plat_data);
+	if (IS_ERR(dp->adp))
+		return PTR_ERR(dp->adp);
+
 	return component_add(dev, &rockchip_dp_component_ops);
 }
 
 static int rockchip_dp_remove(struct platform_device *pdev)
 {
+	struct rockchip_dp_device *dp = platform_get_drvdata(pdev);
+
 	component_del(&pdev->dev, &rockchip_dp_component_ops);
+	analogix_dp_remove(dp->adp);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index d505ea7..8f299d7 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -72,6 +72,7 @@
 	ret = regmap_write(dp->grf, reg, val);
 	if (ret) {
 		DRM_DEV_ERROR(dp->dev, "Could not write to GRF: %d\n", ret);
+		clk_disable_unprepare(dp->grf_clk);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
index bc073ec..8dc91c2 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
@@ -231,7 +231,6 @@
 	struct dw_mipi_dsi *dmd;
 	const struct rockchip_dw_dsi_chip_data *cdata;
 	struct dw_mipi_dsi_plat_data pdata;
-	int devcnt;
 };
 
 struct dphy_pll_parameter_map {
@@ -564,13 +563,8 @@
 	.get_lane_mbps = dw_mipi_dsi_get_lane_mbps,
 };
 
-static void dw_mipi_dsi_rockchip_config(struct dw_mipi_dsi_rockchip *dsi,
-					int mux)
+static void dw_mipi_dsi_rockchip_config(struct dw_mipi_dsi_rockchip *dsi)
 {
-	if (dsi->cdata->lcdsel_grf_reg)
-		regmap_write(dsi->grf_regmap, dsi->cdata->lcdsel_grf_reg,
-			mux ? dsi->cdata->lcdsel_lit : dsi->cdata->lcdsel_big);
-
 	if (dsi->cdata->lanecfg1_grf_reg)
 		regmap_write(dsi->grf_regmap, dsi->cdata->lanecfg1_grf_reg,
 					      dsi->cdata->lanecfg1);
@@ -584,6 +578,13 @@
 					      dsi->cdata->enable);
 }
 
+static void dw_mipi_dsi_rockchip_set_lcdsel(struct dw_mipi_dsi_rockchip *dsi,
+					    int mux)
+{
+	regmap_write(dsi->grf_regmap, dsi->cdata->lcdsel_grf_reg,
+		mux ? dsi->cdata->lcdsel_lit : dsi->cdata->lcdsel_big);
+}
+
 static int
 dw_mipi_dsi_encoder_atomic_check(struct drm_encoder *encoder,
 				 struct drm_crtc_state *crtc_state,
@@ -639,9 +640,9 @@
 		return;
 	}
 
-	dw_mipi_dsi_rockchip_config(dsi, mux);
+	dw_mipi_dsi_rockchip_set_lcdsel(dsi, mux);
 	if (dsi->slave)
-		dw_mipi_dsi_rockchip_config(dsi->slave, mux);
+		dw_mipi_dsi_rockchip_set_lcdsel(dsi->slave, mux);
 
 	clk_disable_unprepare(dsi->grf_clk);
 }
@@ -800,6 +801,24 @@
 		return ret;
 	}
 
+	/*
+	 * With the GRF clock running, write lane and dual-mode configurations
+	 * that won't change immediately. If we waited until enable() to do
+	 * this, things like panel preparation would not be able to send
+	 * commands over DSI.
+	 */
+	ret = clk_prepare_enable(dsi->grf_clk);
+	if (ret) {
+		DRM_DEV_ERROR(dsi->dev, "Failed to enable grf_clk: %d\n", ret);
+		return ret;
+	}
+
+	dw_mipi_dsi_rockchip_config(dsi);
+	if (dsi->slave)
+		dw_mipi_dsi_rockchip_config(dsi->slave);
+
+	clk_disable_unprepare(dsi->grf_clk);
+
 	ret = rockchip_dsi_drm_create_encoder(dsi, drm_dev);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "Failed to create drm encoder\n");
@@ -981,9 +1000,6 @@
 {
 	struct dw_mipi_dsi_rockchip *dsi = platform_get_drvdata(pdev);
 
-	if (dsi->devcnt == 0)
-		component_del(dsi->dev, &dw_mipi_dsi_rockchip_ops);
-
 	dw_mipi_dsi_remove(dsi->dmd);
 
 	return 0;
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 613404f..84e3dec 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1040,10 +1040,41 @@
 				struct drm_display_mode *adjusted_mode)
 {
 	struct vop *vop = to_vop(crtc);
+	unsigned long rate;
 
-	adjusted_mode->clock =
-		DIV_ROUND_UP(clk_round_rate(vop->dclk,
-					    adjusted_mode->clock * 1000), 1000);
+	/*
+	 * Clock craziness.
+	 *
+	 * Key points:
+	 *
+	 * - DRM works in in kHz.
+	 * - Clock framework works in Hz.
+	 * - Rockchip's clock driver picks the clock rate that is the
+	 *   same _OR LOWER_ than the one requested.
+	 *
+	 * Action plan:
+	 *
+	 * 1. When DRM gives us a mode, we should add 999 Hz to it.  That way
+	 *    if the clock we need is 60000001 Hz (~60 MHz) and DRM tells us to
+	 *    make 60000 kHz then the clock framework will actually give us
+	 *    the right clock.
+	 *
+	 *    NOTE: if the PLL (maybe through a divider) could actually make
+	 *    a clock rate 999 Hz higher instead of the one we want then this
+	 *    could be a problem.  Unfortunately there's not much we can do
+	 *    since it's baked into DRM to use kHz.  It shouldn't matter in
+	 *    practice since Rockchip PLLs are controlled by tables and
+	 *    even if there is a divider in the middle I wouldn't expect PLL
+	 *    rates in the table that are just a few kHz different.
+	 *
+	 * 2. Get the clock framework to round the rate for us to tell us
+	 *    what it will actually make.
+	 *
+	 * 3. Store the rounded up rate so that we don't need to worry about
+	 *    this in the actual clk_set_rate().
+	 */
+	rate = clk_round_rate(vop->dclk, adjusted_mode->clock * 1000 + 999);
+	adjusted_mode->clock = DIV_ROUND_UP(rate, 1000);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 1a51531..57f9baa 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -235,11 +235,16 @@
 static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
 {
 	struct drm_sched_job *job;
+	struct dma_fence *f;
 	int r;
 
 	while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) {
 		struct drm_sched_fence *s_fence = job->s_fence;
 
+		/* Wait for all dependencies to avoid data corruptions */
+		while ((f = job->sched->ops->dependency(job, entity)))
+			dma_fence_wait(f, false);
+
 		drm_sched_fence_scheduled(s_fence);
 		dma_fence_set_error(&s_fence->finished, -ESRCH);
 
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index f39b97e..3767950 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -284,10 +284,21 @@
 	unsigned long flags;
 
 	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
+
+	/* Protects against concurrent deletion in drm_sched_get_cleanup_job */
+	spin_lock_irqsave(&sched->job_list_lock, flags);
 	job = list_first_entry_or_null(&sched->ring_mirror_list,
 				       struct drm_sched_job, node);
 
 	if (job) {
+		/*
+		 * Remove the bad job so it cannot be freed by concurrent
+		 * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread
+		 * is parked at which point it's safe.
+		 */
+		list_del_init(&job->node);
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
 		job->sched->ops->timedout_job(job);
 
 		/*
@@ -298,6 +309,8 @@
 			job->sched->ops->free_job(job);
 			sched->free_guilty = false;
 		}
+	} else {
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
 	}
 
 	spin_lock_irqsave(&sched->job_list_lock, flags);
@@ -370,6 +383,20 @@
 	kthread_park(sched->thread);
 
 	/*
+	 * Reinsert back the bad job here - now it's safe as
+	 * drm_sched_get_cleanup_job cannot race against us and release the
+	 * bad job at this point - we parked (waited for) any in progress
+	 * (earlier) cleanups and drm_sched_get_cleanup_job will not be called
+	 * now until the scheduler thread is unparked.
+	 */
+	if (bad && bad->sched == sched)
+		/*
+		 * Add at the head of the queue to reflect it was the earliest
+		 * job extracted.
+		 */
+		list_add(&bad->node, &sched->ring_mirror_list);
+
+	/*
 	 * Iterate the job list from later to  earlier one and either deactive
 	 * their HW callbacks or remove them from mirror list if they already
 	 * signaled.
@@ -496,8 +523,10 @@
 		fence = sched->ops->run_job(s_job);
 
 		if (IS_ERR_OR_NULL(fence)) {
+			if (IS_ERR(fence))
+				dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+
 			s_job->s_fence->parent = NULL;
-			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 		} else {
 			s_job->s_fence->parent = fence;
 		}
@@ -627,48 +656,48 @@
 
 	trace_drm_sched_process_job(s_fence);
 
+	dma_fence_get(&s_fence->finished);
 	drm_sched_fence_finished(s_fence);
+	dma_fence_put(&s_fence->finished);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
 
 /**
- * drm_sched_cleanup_jobs - destroy finished jobs
+ * drm_sched_get_cleanup_job - fetch the next finished job to be destroyed
  *
  * @sched: scheduler instance
  *
- * Remove all finished jobs from the mirror list and destroy them.
+ * Returns the next finished job from the mirror list (if there is one)
+ * ready for it to be destroyed.
  */
-static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched)
+static struct drm_sched_job *
+drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 {
+	struct drm_sched_job *job;
 	unsigned long flags;
 
 	/* Don't destroy jobs while the timeout worker is running */
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
 	    !cancel_delayed_work(&sched->work_tdr))
-		return;
+		return NULL;
 
+	spin_lock_irqsave(&sched->job_list_lock, flags);
 
-	while (!list_empty(&sched->ring_mirror_list)) {
-		struct drm_sched_job *job;
-
-		job = list_first_entry(&sched->ring_mirror_list,
+	job = list_first_entry_or_null(&sched->ring_mirror_list,
 				       struct drm_sched_job, node);
-		if (!dma_fence_is_signaled(&job->s_fence->finished))
-			break;
 
-		spin_lock_irqsave(&sched->job_list_lock, flags);
+	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from ring_mirror_list */
 		list_del_init(&job->node);
-		spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
-		sched->ops->free_job(job);
+	} else {
+		job = NULL;
+		/* queue timeout for next job */
+		drm_sched_start_timeout(sched);
 	}
 
-	/* queue timeout for next job */
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	drm_sched_start_timeout(sched);
 	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 
+	return job;
 }
 
 /**
@@ -708,12 +737,19 @@
 		struct drm_sched_fence *s_fence;
 		struct drm_sched_job *sched_job;
 		struct dma_fence *fence;
+		struct drm_sched_job *cleanup_job = NULL;
 
 		wait_event_interruptible(sched->wake_up_worker,
-					 (drm_sched_cleanup_jobs(sched),
+					 (cleanup_job = drm_sched_get_cleanup_job(sched)) ||
 					 (!drm_sched_blocked(sched) &&
 					  (entity = drm_sched_select_entity(sched))) ||
-					 kthread_should_stop()));
+					 kthread_should_stop());
+
+		if (cleanup_job) {
+			sched->ops->free_job(cleanup_job);
+			/* queue timeout for next job */
+			drm_sched_start_timeout(sched);
+		}
 
 		if (!entity)
 			continue;
@@ -741,8 +777,9 @@
 					  r);
 			dma_fence_put(fence);
 		} else {
+			if (IS_ERR(fence))
+				dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 
-			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 			drm_sched_process_job(NULL, &sched_job->cb);
 		}
 
@@ -814,6 +851,9 @@
 	if (sched->thread)
 		kthread_stop(sched->thread);
 
+	/* Confirm no work left behind accessing device structures */
+	cancel_delayed_work_sync(&sched->work_tdr);
+
 	sched->ready = false;
 }
 EXPORT_SYMBOL(drm_sched_fini);
diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
index 6d61a0e..84e6bc0 100644
--- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
@@ -53,6 +53,7 @@
 cmdline_test(drm_cmdline_test_rotate_90)
 cmdline_test(drm_cmdline_test_rotate_180)
 cmdline_test(drm_cmdline_test_rotate_270)
+cmdline_test(drm_cmdline_test_rotate_multiple)
 cmdline_test(drm_cmdline_test_rotate_invalid_val)
 cmdline_test(drm_cmdline_test_rotate_truncated)
 cmdline_test(drm_cmdline_test_hmirror)
diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
index 013de9d..035f86c 100644
--- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
+++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
@@ -856,6 +856,17 @@
 	return 0;
 }
 
+static int drm_cmdline_test_rotate_multiple(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(drm_mode_parse_command_line_for_connector("720x480,rotate=0,rotate=90",
+							  &no_connector,
+							  &mode));
+
+	return 0;
+}
+
 static int drm_cmdline_test_rotate_invalid_val(void *ignored)
 {
 	struct drm_cmdline_mode mode = { };
@@ -888,7 +899,7 @@
 	FAIL_ON(!mode.specified);
 	FAIL_ON(mode.xres != 720);
 	FAIL_ON(mode.yres != 480);
-	FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_X);
+	FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X));
 
 	FAIL_ON(mode.refresh_specified);
 
@@ -913,7 +924,7 @@
 	FAIL_ON(!mode.specified);
 	FAIL_ON(mode.xres != 720);
 	FAIL_ON(mode.yres != 480);
-	FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_Y);
+	FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y));
 
 	FAIL_ON(mode.refresh_specified);
 
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index 3ab4fbf..51571f7 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -424,9 +424,12 @@
 				    struct drm_crtc_state *old_state)
 {
 	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
+	struct drm_device *ddev = crtc->dev;
 
 	DRM_DEBUG_DRIVER("\n");
 
+	pm_runtime_get_sync(ddev->dev);
+
 	/* Sets the background color value */
 	reg_write(ldev->regs, LTDC_BCCR, BCCR_BCBLACK);
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 4e29f4f..99f081c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -589,8 +589,7 @@
 
 	/* We can't have an alpha plane at the lowest position */
 	if (!backend->quirks->supports_lowest_plane_alpha &&
-	    (plane_states[0]->fb->format->has_alpha ||
-	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE)))
+	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE))
 		return -EINVAL;
 
 	for (i = 1; i < num_planes; i++) {
@@ -986,7 +985,6 @@
 
 static const struct sun4i_backend_quirks sun7i_backend_quirks = {
 	.needs_output_muxing = true,
-	.supports_lowest_plane_alpha = true,
 };
 
 static const struct sun4i_backend_quirks sun8i_a33_backend_quirks = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index a5757b1..5b54eff 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -85,7 +85,6 @@
 	}
 
 	drm_mode_config_init(drm);
-	drm->mode_config.allow_fb_modifiers = true;
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c
index ec2a032..7186ba7 100644
--- a/drivers/gpu/drm/sun4i/sun4i_frontend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c
@@ -407,6 +407,7 @@
 	struct drm_framebuffer *fb = state->fb;
 	const struct drm_format_info *format = fb->format;
 	uint64_t modifier = fb->modifier;
+	unsigned int ch1_phase_idx;
 	u32 out_fmt_val;
 	u32 in_fmt_val, in_mod_val, in_ps_val;
 	unsigned int i;
@@ -442,18 +443,19 @@
 	 * I have no idea what this does exactly, but it seems to be
 	 * related to the scaler FIR filter phase parameters.
 	 */
+	ch1_phase_idx = (format->num_planes > 1) ? 1 : 0;
 	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZPHASE_REG,
-		     frontend->data->ch_phase[0].horzphase);
+		     frontend->data->ch_phase[0]);
 	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZPHASE_REG,
-		     frontend->data->ch_phase[1].horzphase);
+		     frontend->data->ch_phase[ch1_phase_idx]);
 	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE0_REG,
-		     frontend->data->ch_phase[0].vertphase[0]);
+		     frontend->data->ch_phase[0]);
 	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE0_REG,
-		     frontend->data->ch_phase[1].vertphase[0]);
+		     frontend->data->ch_phase[ch1_phase_idx]);
 	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE1_REG,
-		     frontend->data->ch_phase[0].vertphase[1]);
+		     frontend->data->ch_phase[0]);
 	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE1_REG,
-		     frontend->data->ch_phase[1].vertphase[1]);
+		     frontend->data->ch_phase[ch1_phase_idx]);
 
 	/*
 	 * Checking the input format is sufficient since we currently only
@@ -687,30 +689,12 @@
 };
 
 static const struct sun4i_frontend_data sun4i_a10_frontend = {
-	.ch_phase		= {
-		{
-			.horzphase = 0,
-			.vertphase = { 0, 0 },
-		},
-		{
-			.horzphase = 0xfc000,
-			.vertphase = { 0xfc000, 0xfc000 },
-		},
-	},
+	.ch_phase		= { 0x000, 0xfc000 },
 	.has_coef_rdy		= true,
 };
 
 static const struct sun4i_frontend_data sun8i_a33_frontend = {
-	.ch_phase		= {
-		{
-			.horzphase = 0x400,
-			.vertphase = { 0x400, 0x400 },
-		},
-		{
-			.horzphase = 0x400,
-			.vertphase = { 0x400, 0x400 },
-		},
-	},
+	.ch_phase		= { 0x400, 0xfc400 },
 	.has_coef_access_ctrl	= true,
 };
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.h b/drivers/gpu/drm/sun4i/sun4i_frontend.h
index 0c382c1..2e7b76e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_frontend.h
+++ b/drivers/gpu/drm/sun4i/sun4i_frontend.h
@@ -115,11 +115,7 @@
 struct sun4i_frontend_data {
 	bool	has_coef_access_ctrl;
 	bool	has_coef_rdy;
-
-	struct {
-		u32	horzphase;
-		u32	vertphase[2];
-	} ch_phase[2];
+	u32	ch_phase[2];
 };
 
 struct sun4i_frontend {
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
index 7ad3f06..00ca35f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
@@ -148,7 +148,7 @@
 #define SUN4I_HDMI_DDC_CMD_IMPLICIT_WRITE	3
 
 #define SUN4I_HDMI_DDC_CLK_REG		0x528
-#define SUN4I_HDMI_DDC_CLK_M(m)			(((m) & 0x7) << 3)
+#define SUN4I_HDMI_DDC_CLK_M(m)			(((m) & 0xf) << 3)
 #define SUN4I_HDMI_DDC_CLK_N(n)			((n) & 0x7)
 
 #define SUN4I_HDMI_DDC_LINE_CTRL_REG	0x540
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
index 2ff7801..12430b9 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
@@ -33,7 +33,7 @@
 	unsigned long best_rate = 0;
 	u8 best_m = 0, best_n = 0, _m, _n;
 
-	for (_m = 0; _m < 8; _m++) {
+	for (_m = 0; _m < 16; _m++) {
 		for (_n = 0; _n < 8; _n++) {
 			unsigned long tmp_rate;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index eb8071a..4acdfa6 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -262,9 +262,8 @@
 	struct sun4i_hdmi *hdmi = drm_connector_to_sun4i_hdmi(connector);
 	unsigned long reg;
 
-	if (readl_poll_timeout(hdmi->base + SUN4I_HDMI_HPD_REG, reg,
-			       reg & SUN4I_HDMI_HPD_HIGH,
-			       0, 500000)) {
+	reg = readl(hdmi->base + SUN4I_HDMI_HPD_REG);
+	if (!(reg & SUN4I_HDMI_HPD_HIGH)) {
 		cec_phys_addr_invalidate(hdmi->cec_adap);
 		return connector_status_disconnected;
 	}
@@ -683,8 +682,6 @@
 	struct sun4i_hdmi *hdmi = dev_get_drvdata(dev);
 
 	cec_unregister_adapter(hdmi->cec_adap);
-	drm_connector_cleanup(&hdmi->connector);
-	drm_encoder_cleanup(&hdmi->encoder);
 	i2c_del_adapter(hdmi->i2c);
 	i2c_put_adapter(hdmi->ddc_i2c);
 	clk_disable_unprepare(hdmi->mod_clk);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index b89439e..eb3b235 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -488,7 +488,7 @@
 
 	WARN_ON(!tcon->quirks->has_channel_0);
 
-	tcon->dclk_min_div = 1;
+	tcon->dclk_min_div = tcon->quirks->dclk_min_div;
 	tcon->dclk_max_div = 127;
 	sun4i_tcon0_mode_set_common(tcon, mode);
 
@@ -545,30 +545,13 @@
 	if (info->bus_flags & DRM_BUS_FLAG_DE_LOW)
 		val |= SUN4I_TCON0_IO_POL_DE_NEGATIVE;
 
-	/*
-	 * On A20 and similar SoCs, the only way to achieve Positive Edge
-	 * (Rising Edge), is setting dclk clock phase to 2/3(240°).
-	 * By default TCON works in Negative Edge(Falling Edge),
-	 * this is why phase is set to 0 in that case.
-	 * Unfortunately there's no way to logically invert dclk through
-	 * IO_POL register.
-	 * The only acceptable way to work, triple checked with scope,
-	 * is using clock phase set to 0° for Negative Edge and set to 240°
-	 * for Positive Edge.
-	 * On A33 and similar SoCs there would be a 90° phase option,
-	 * but it divides also dclk by 2.
-	 * Following code is a way to avoid quirks all around TCON
-	 * and DOTCLOCK drivers.
-	 */
-	if (info->bus_flags & DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE)
-		clk_set_phase(tcon->dclk, 240);
-
 	if (info->bus_flags & DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE)
-		clk_set_phase(tcon->dclk, 0);
+		val |= SUN4I_TCON0_IO_POL_DCLK_DRIVE_NEGEDGE;
 
 	regmap_update_bits(tcon->regs, SUN4I_TCON0_IO_POL_REG,
 			   SUN4I_TCON0_IO_POL_HSYNC_POSITIVE |
 			   SUN4I_TCON0_IO_POL_VSYNC_POSITIVE |
+			   SUN4I_TCON0_IO_POL_DCLK_DRIVE_NEGEDGE |
 			   SUN4I_TCON0_IO_POL_DE_NEGATIVE,
 			   val);
 
@@ -665,6 +648,30 @@
 		     SUN4I_TCON1_BASIC5_V_SYNC(vsync) |
 		     SUN4I_TCON1_BASIC5_H_SYNC(hsync));
 
+	/* Setup the polarity of multiple signals */
+	if (tcon->quirks->polarity_in_ch0) {
+		val = 0;
+
+		if (mode->flags & DRM_MODE_FLAG_PHSYNC)
+			val |= SUN4I_TCON0_IO_POL_HSYNC_POSITIVE;
+
+		if (mode->flags & DRM_MODE_FLAG_PVSYNC)
+			val |= SUN4I_TCON0_IO_POL_VSYNC_POSITIVE;
+
+		regmap_write(tcon->regs, SUN4I_TCON0_IO_POL_REG, val);
+	} else {
+		/* according to vendor driver, this bit must be always set */
+		val = SUN4I_TCON1_IO_POL_UNKNOWN;
+
+		if (mode->flags & DRM_MODE_FLAG_PHSYNC)
+			val |= SUN4I_TCON1_IO_POL_HSYNC_POSITIVE;
+
+		if (mode->flags & DRM_MODE_FLAG_PVSYNC)
+			val |= SUN4I_TCON1_IO_POL_VSYNC_POSITIVE;
+
+		regmap_write(tcon->regs, SUN4I_TCON1_IO_POL_REG, val);
+	}
+
 	/* Map output pins to channel 1 */
 	regmap_update_bits(tcon->regs, SUN4I_TCON_GCTL_REG,
 			   SUN4I_TCON_GCTL_IOMAP_MASK,
@@ -1409,14 +1416,18 @@
 	if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
 	    encoder->encoder_type == DRM_MODE_ENCODER_TMDS) {
 		ret = sun8i_tcon_top_set_hdmi_src(&pdev->dev, id);
-		if (ret)
+		if (ret) {
+			put_device(&pdev->dev);
 			return ret;
+		}
 	}
 
 	if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP)) {
 		ret = sun8i_tcon_top_de_config(&pdev->dev, tcon->id, id);
-		if (ret)
+		if (ret) {
+			put_device(&pdev->dev);
 			return ret;
+		}
 	}
 
 	return 0;
@@ -1425,12 +1436,14 @@
 static const struct sun4i_tcon_quirks sun4i_a10_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
+	.dclk_min_div		= 4,
 	.set_mux		= sun4i_a10_tcon_set_mux,
 };
 
 static const struct sun4i_tcon_quirks sun5i_a13_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
+	.dclk_min_div		= 4,
 	.set_mux		= sun5i_a13_tcon_set_mux,
 };
 
@@ -1439,6 +1452,7 @@
 	.has_channel_1		= true,
 	.has_lvds_alt		= true,
 	.needs_de_be_mux	= true,
+	.dclk_min_div		= 1,
 	.set_mux		= sun6i_tcon_set_mux,
 };
 
@@ -1446,11 +1460,13 @@
 	.has_channel_0		= true,
 	.has_channel_1		= true,
 	.needs_de_be_mux	= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun7i_a20_quirks = {
 	.has_channel_0		= true,
 	.has_channel_1		= true,
+	.dclk_min_div		= 4,
 	/* Same display pipeline structure as A10 */
 	.set_mux		= sun4i_a10_tcon_set_mux,
 };
@@ -1458,11 +1474,13 @@
 static const struct sun4i_tcon_quirks sun8i_a33_quirks = {
 	.has_channel_0		= true,
 	.has_lvds_alt		= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun8i_a83t_lcd_quirks = {
 	.supports_lvds		= true,
 	.has_channel_0		= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun8i_a83t_tv_quirks = {
@@ -1471,16 +1489,19 @@
 
 static const struct sun4i_tcon_quirks sun8i_r40_tv_quirks = {
 	.has_channel_1		= true,
+	.polarity_in_ch0	= true,
 	.set_mux		= sun8i_r40_tcon_tv_set_mux,
 };
 
 static const struct sun4i_tcon_quirks sun8i_v3s_quirks = {
 	.has_channel_0		= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun9i_a80_tcon_lcd_quirks = {
-	.has_channel_0	= true,
-	.needs_edp_reset = true,
+	.has_channel_0		= true,
+	.needs_edp_reset	= true,
+	.dclk_min_div		= 1,
 };
 
 static const struct sun4i_tcon_quirks sun9i_a80_tcon_tv_quirks = {
@@ -1495,6 +1516,8 @@
 	{ .compatible = "allwinner,sun6i-a31-tcon", .data = &sun6i_a31_quirks },
 	{ .compatible = "allwinner,sun6i-a31s-tcon", .data = &sun6i_a31s_quirks },
 	{ .compatible = "allwinner,sun7i-a20-tcon", .data = &sun7i_a20_quirks },
+	{ .compatible = "allwinner,sun7i-a20-tcon0", .data = &sun7i_a20_quirks },
+	{ .compatible = "allwinner,sun7i-a20-tcon1", .data = &sun7i_a20_quirks },
 	{ .compatible = "allwinner,sun8i-a23-tcon", .data = &sun8i_a33_quirks },
 	{ .compatible = "allwinner,sun8i-a33-tcon", .data = &sun8i_a33_quirks },
 	{ .compatible = "allwinner,sun8i-a83t-tcon-lcd", .data = &sun8i_a83t_lcd_quirks },
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h
index f9f1fe8..ce500c8 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.h
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h
@@ -113,6 +113,7 @@
 #define SUN4I_TCON0_IO_POL_REG			0x88
 #define SUN4I_TCON0_IO_POL_DCLK_PHASE(phase)		((phase & 3) << 28)
 #define SUN4I_TCON0_IO_POL_DE_NEGATIVE			BIT(27)
+#define SUN4I_TCON0_IO_POL_DCLK_DRIVE_NEGEDGE		BIT(26)
 #define SUN4I_TCON0_IO_POL_HSYNC_POSITIVE		BIT(25)
 #define SUN4I_TCON0_IO_POL_VSYNC_POSITIVE		BIT(24)
 
@@ -153,6 +154,11 @@
 #define SUN4I_TCON1_BASIC5_V_SYNC(height)		(((height) - 1) & 0x3ff)
 
 #define SUN4I_TCON1_IO_POL_REG			0xf0
+/* there is no documentation about this bit */
+#define SUN4I_TCON1_IO_POL_UNKNOWN			BIT(26)
+#define SUN4I_TCON1_IO_POL_HSYNC_POSITIVE		BIT(25)
+#define SUN4I_TCON1_IO_POL_VSYNC_POSITIVE		BIT(24)
+
 #define SUN4I_TCON1_IO_TRI_REG			0xf4
 
 #define SUN4I_TCON_ECC_FIFO_REG			0xf8
@@ -224,6 +230,8 @@
 	bool	needs_de_be_mux; /* sun6i needs mux to select backend */
 	bool    needs_edp_reset; /* a80 edp reset needed for tcon0 access */
 	bool	supports_lvds;   /* Does the TCON support an LVDS output? */
+	bool	polarity_in_ch0; /* some tcon1 channels have polarity bits in tcon0 pol register */
+	u8	dclk_min_div;	/* minimum divider for TCON0 DCLK */
 
 	/* callback to handle tcon muxing options */
 	int	(*set_mux)(struct sun4i_tcon *, const struct drm_encoder *);
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 1636344..f2b2880 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -437,9 +437,9 @@
 			     SUN6I_DSI_BURST_LINE_SYNC_POINT(SUN6I_DSI_SYNC_POINT));
 
 		val = SUN6I_DSI_TCON_DRQ_ENABLE_MODE;
-	} else if ((mode->hsync_end - mode->hdisplay) > 20) {
+	} else if ((mode->hsync_start - mode->hdisplay) > 20) {
 		/* Maaaaaagic */
-		u16 drq = (mode->hsync_end - mode->hdisplay) - 20;
+		u16 drq = (mode->hsync_start - mode->hdisplay) - 20;
 
 		drq *= mipi_dsi_pixel_format_to_bpp(device->format);
 		drq /= 32;
@@ -718,7 +718,7 @@
 	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder);
 	struct mipi_dsi_device *device = dsi->device;
-	union phy_configure_opts opts = { 0 };
+	union phy_configure_opts opts = { };
 	struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy;
 	u16 delay;
 
@@ -867,7 +867,7 @@
 	regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0),
 		     sun6i_dsi_dcs_build_pkt_hdr(dsi, msg));
 
-	bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL);
+	bounce = kzalloc(ALIGN(msg->tx_len + sizeof(crc), 4), GFP_KERNEL);
 	if (!bounce)
 		return -ENOMEM;
 
@@ -878,7 +878,7 @@
 	memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc));
 	len += sizeof(crc);
 
-	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len);
+	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, DIV_ROUND_UP(len, 4));
 	regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1);
 	kfree(bounce);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h
index f42441b..a55a38a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_csc.h
+++ b/drivers/gpu/drm/sun4i/sun8i_csc.h
@@ -12,7 +12,7 @@
 
 /* VI channel CSC units offsets */
 #define CCSC00_OFFSET 0xAA050
-#define CCSC01_OFFSET 0xFA000
+#define CCSC01_OFFSET 0xFA050
 #define CCSC10_OFFSET 0xA0000
 #define CCSC11_OFFSET 0xF0000
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index a44dca4..8f721be 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -49,11 +49,9 @@
 {
 	/*
 	 * Controller support maximum of 594 MHz, which correlates to
-	 * 4K@60Hz 4:4:4 or RGB. However, for frequencies greater than
-	 * 340 MHz scrambling has to be enabled. Because scrambling is
-	 * not yet implemented, just limit to 340 MHz for now.
+	 * 4K@60Hz 4:4:4 or RGB.
 	 */
-	if (mode->clock > 340000)
+	if (mode->clock > 594000)
 		return MODE_CLOCK_HIGH;
 
 	return MODE_OK;
@@ -209,6 +207,7 @@
 	phy_node = of_parse_phandle(dev->of_node, "phys", 0);
 	if (!phy_node) {
 		dev_err(dev, "Can't found PHY phandle\n");
+		ret = -EINVAL;
 		goto err_disable_clk_tmds;
 	}
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index 43643ad..a4012ec 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -104,29 +104,21 @@
 
 static const struct dw_hdmi_curr_ctrl sun50i_h6_cur_ctr[] = {
 	/* pixelclk    bpp8    bpp10   bpp12 */
-	{ 25175000,  { 0x0000, 0x0000, 0x0000 }, },
 	{ 27000000,  { 0x0012, 0x0000, 0x0000 }, },
-	{ 59400000,  { 0x0008, 0x0008, 0x0008 }, },
-	{ 72000000,  { 0x0008, 0x0008, 0x001b }, },
-	{ 74250000,  { 0x0013, 0x0013, 0x0013 }, },
-	{ 90000000,  { 0x0008, 0x001a, 0x001b }, },
-	{ 118800000, { 0x001b, 0x001a, 0x001b }, },
-	{ 144000000, { 0x001b, 0x001a, 0x0034 }, },
-	{ 180000000, { 0x001b, 0x0033, 0x0034 }, },
-	{ 216000000, { 0x0036, 0x0033, 0x0034 }, },
-	{ 237600000, { 0x0036, 0x0033, 0x001b }, },
-	{ 288000000, { 0x0036, 0x001b, 0x001b }, },
-	{ 297000000, { 0x0019, 0x001b, 0x0019 }, },
-	{ 330000000, { 0x0036, 0x001b, 0x001b }, },
-	{ 594000000, { 0x003f, 0x001b, 0x001b }, },
+	{ 74250000,  { 0x0013, 0x001a, 0x001b }, },
+	{ 148500000, { 0x0019, 0x0033, 0x0034 }, },
+	{ 297000000, { 0x0019, 0x001b, 0x001b }, },
+	{ 594000000, { 0x0010, 0x001b, 0x001b }, },
 	{ ~0UL,      { 0x0000, 0x0000, 0x0000 }, }
 };
 
 static const struct dw_hdmi_phy_config sun50i_h6_phy_config[] = {
 	/*pixelclk   symbol   term   vlev*/
-	{ 74250000,  0x8009, 0x0004, 0x0232},
-	{ 148500000, 0x8029, 0x0004, 0x0273},
-	{ 594000000, 0x8039, 0x0004, 0x014a},
+	{ 27000000,  0x8009, 0x0007, 0x02b0 },
+	{ 74250000,  0x8009, 0x0006, 0x022d },
+	{ 148500000, 0x8029, 0x0006, 0x0270 },
+	{ 297000000, 0x8039, 0x0005, 0x01ab },
+	{ 594000000, 0x8029, 0x0000, 0x008a },
 	{ ~0UL,	     0x0000, 0x0000, 0x0000}
 };
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 8b803eb..12b99ba 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -107,48 +107,128 @@
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XRGB4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ABGR4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XBGR4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_RGBA4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_RGBX4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_BGRA4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_BGRX4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ARGB1555,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XRGB1555,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ABGR1555,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XBGR1555,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_RGBA5551,
 		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_RGBX5551,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_BGRA5551,
 		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_BGRX5551,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_ARGB2101010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB2101010,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_ABGR2101010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR2101010,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_RGBA1010102,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA1010102,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_BGRA1010102,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA1010102,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_UYVY,
 		.de2_fmt = SUN8I_MIXER_FBFMT_UYVY,
 		.rgb = false,
@@ -197,12 +277,6 @@
 		.csc = SUN8I_CSC_MODE_YUV2RGB,
 	},
 	{
-		.drm_fmt = DRM_FORMAT_YUV444,
-		.de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
-		.rgb = true,
-		.csc = SUN8I_CSC_MODE_YUV2RGB,
-	},
-	{
 		.drm_fmt = DRM_FORMAT_YUV422,
 		.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
 		.rgb = false,
@@ -221,12 +295,6 @@
 		.csc = SUN8I_CSC_MODE_YUV2RGB,
 	},
 	{
-		.drm_fmt = DRM_FORMAT_YVU444,
-		.de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
-		.rgb = true,
-		.csc = SUN8I_CSC_MODE_YVU2RGB,
-	},
-	{
 		.drm_fmt = DRM_FORMAT_YVU422,
 		.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
 		.rgb = false,
@@ -244,6 +312,18 @@
 		.rgb = false,
 		.csc = SUN8I_CSC_MODE_YVU2RGB,
 	},
+	{
+		.drm_fmt = DRM_FORMAT_P010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_P010_YUV,
+		.rgb = false,
+		.csc = SUN8I_CSC_MODE_YUV2RGB,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_P210,
+		.de2_fmt = SUN8I_MIXER_FBFMT_P210_YUV,
+		.rgb = false,
+		.csc = SUN8I_CSC_MODE_YUV2RGB,
+	},
 };
 
 const struct de2_fmt_info *sun8i_mixer_format_info(u32 format)
@@ -316,7 +396,7 @@
 	.reg_bits	= 32,
 	.val_bits	= 32,
 	.reg_stride	= 4,
-	.max_register	= 0xbfffc, /* guessed */
+	.max_register	= 0xffffc, /* guessed */
 };
 
 static int sun8i_mixer_of_get_id(struct device_node *node)
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index c6cc940..345b28b 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -93,6 +93,10 @@
 #define SUN8I_MIXER_FBFMT_ABGR1555	17
 #define SUN8I_MIXER_FBFMT_RGBA5551	18
 #define SUN8I_MIXER_FBFMT_BGRA5551	19
+#define SUN8I_MIXER_FBFMT_ARGB2101010	20
+#define SUN8I_MIXER_FBFMT_ABGR2101010	21
+#define SUN8I_MIXER_FBFMT_RGBA1010102	22
+#define SUN8I_MIXER_FBFMT_BGRA1010102	23
 
 #define SUN8I_MIXER_FBFMT_YUYV		0
 #define SUN8I_MIXER_FBFMT_UYVY		1
@@ -109,6 +113,13 @@
 /* format 12 is semi-planar YUV411 UVUV */
 /* format 13 is semi-planar YUV411 VUVU */
 #define SUN8I_MIXER_FBFMT_YUV411	14
+/* format 15 doesn't exist */
+/* format 16 is P010 YVU */
+#define SUN8I_MIXER_FBFMT_P010_YUV	17
+/* format 18 is P210 YVU */
+#define SUN8I_MIXER_FBFMT_P210_YUV	19
+/* format 20 is packed YVU444 10-bit */
+/* format 21 is packed YUV444 10-bit */
 
 /*
  * Sub-engines listed bellow are unused for now. The EN registers are here only
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 42d445d..b8398ca 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -398,26 +398,26 @@
 };
 
 /*
- * While all RGB formats are supported, VI planes don't support
- * alpha blending, so there is no point having formats with alpha
- * channel if their opaque analog exist.
+ * While DE2 VI layer supports same RGB formats as UI layer, alpha
+ * channel is ignored. This structure lists all unique variants
+ * where alpha channel is replaced with "don't care" (X) channel.
  */
 static const u32 sun8i_vi_layer_formats[] = {
-	DRM_FORMAT_ABGR1555,
-	DRM_FORMAT_ABGR4444,
-	DRM_FORMAT_ARGB1555,
-	DRM_FORMAT_ARGB4444,
 	DRM_FORMAT_BGR565,
 	DRM_FORMAT_BGR888,
-	DRM_FORMAT_BGRA5551,
-	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_BGRX4444,
+	DRM_FORMAT_BGRX5551,
 	DRM_FORMAT_BGRX8888,
 	DRM_FORMAT_RGB565,
 	DRM_FORMAT_RGB888,
-	DRM_FORMAT_RGBA4444,
-	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_RGBX4444,
+	DRM_FORMAT_RGBX5551,
 	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_XBGR4444,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_XRGB4444,
 	DRM_FORMAT_XRGB8888,
 
 	DRM_FORMAT_NV16,
@@ -431,11 +431,53 @@
 	DRM_FORMAT_YUV411,
 	DRM_FORMAT_YUV420,
 	DRM_FORMAT_YUV422,
-	DRM_FORMAT_YUV444,
 	DRM_FORMAT_YVU411,
 	DRM_FORMAT_YVU420,
 	DRM_FORMAT_YVU422,
-	DRM_FORMAT_YVU444,
+};
+
+static const u32 sun8i_vi_layer_de3_formats[] = {
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_BGRA1010102,
+	DRM_FORMAT_BGRA5551,
+	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_RGBA1010102,
+	DRM_FORMAT_RGBA4444,
+	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB8888,
+
+	DRM_FORMAT_NV16,
+	DRM_FORMAT_NV12,
+	DRM_FORMAT_NV21,
+	DRM_FORMAT_NV61,
+	DRM_FORMAT_P010,
+	DRM_FORMAT_P210,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_YUV411,
+	DRM_FORMAT_YUV420,
+	DRM_FORMAT_YUV422,
+	DRM_FORMAT_YVU411,
+	DRM_FORMAT_YVU420,
+	DRM_FORMAT_YVU422,
 };
 
 struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
@@ -443,19 +485,27 @@
 					       int index)
 {
 	u32 supported_encodings, supported_ranges;
+	unsigned int plane_cnt, format_count;
 	struct sun8i_vi_layer *layer;
-	unsigned int plane_cnt;
+	const u32 *formats;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
 	if (!layer)
 		return ERR_PTR(-ENOMEM);
 
+	if (mixer->cfg->is_de3) {
+		formats = sun8i_vi_layer_de3_formats;
+		format_count = ARRAY_SIZE(sun8i_vi_layer_de3_formats);
+	} else {
+		formats = sun8i_vi_layer_formats;
+		format_count = ARRAY_SIZE(sun8i_vi_layer_formats);
+	}
+
 	/* possible crtcs are set later */
 	ret = drm_universal_plane_init(drm, &layer->plane, 0,
 				       &sun8i_vi_layer_funcs,
-				       sun8i_vi_layer_formats,
-				       ARRAY_SIZE(sun8i_vi_layer_formats),
+				       formats, format_count,
 				       NULL, DRM_PLANE_TYPE_OVERLAY, NULL);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't initialize layer\n");
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index fbf57bc..c410221 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -919,6 +919,11 @@
 	.atomic_disable = tegra_cursor_atomic_disable,
 };
 
+static const uint64_t linear_modifiers[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm,
 						      struct tegra_dc *dc)
 {
@@ -947,7 +952,7 @@
 
 	err = drm_universal_plane_init(drm, &plane->base, possible_crtcs,
 				       &tegra_plane_funcs, formats,
-				       num_formats, NULL,
+				       num_formats, linear_modifiers,
 				       DRM_PLANE_TYPE_CURSOR, NULL);
 	if (err < 0) {
 		kfree(plane);
@@ -1065,7 +1070,8 @@
 
 	err = drm_universal_plane_init(drm, &plane->base, possible_crtcs,
 				       &tegra_plane_funcs, formats,
-				       num_formats, NULL, type, NULL);
+				       num_formats, linear_modifiers,
+				       type, NULL);
 	if (err < 0) {
 		kfree(plane);
 		return ERR_PTR(err);
@@ -1667,6 +1673,11 @@
 			dev_err(dc->dev,
 				"failed to set clock rate to %lu Hz\n",
 				state->pclk);
+
+		err = clk_set_rate(dc->clk, state->pclk);
+		if (err < 0)
+			dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
+				dc->clk, state->pclk, err);
 	}
 
 	DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk),
@@ -1677,11 +1688,6 @@
 		value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1;
 		tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
 	}
-
-	err = clk_set_rate(dc->clk, state->pclk);
-	if (err < 0)
-		dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
-			dc->clk, state->pclk, err);
 }
 
 static void tegra_dc_stop(struct tegra_dc *dc)
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 6fb7d74..c2ab7cf 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -122,8 +122,6 @@
 	drm->mode_config.max_width = 4096;
 	drm->mode_config.max_height = 4096;
 
-	drm->mode_config.allow_fb_modifiers = true;
-
 	drm->mode_config.normalize_zpos = true;
 
 	drm->mode_config.funcs = &tegra_drm_mode_config_funcs;
@@ -201,19 +199,19 @@
 	if (tegra->hub)
 		tegra_display_hub_cleanup(tegra->hub);
 device:
-	host1x_device_exit(device);
-fbdev:
-	drm_kms_helper_poll_fini(drm);
-	tegra_drm_fb_free(drm);
-config:
-	drm_mode_config_cleanup(drm);
-
 	if (tegra->domain) {
 		mutex_destroy(&tegra->mm_lock);
 		drm_mm_takedown(&tegra->mm);
 		put_iova_domain(&tegra->carveout.domain);
 		iova_cache_put();
 	}
+
+	host1x_device_exit(device);
+fbdev:
+	drm_kms_helper_poll_fini(drm);
+	tegra_drm_fb_free(drm);
+config:
+	drm_mode_config_cleanup(drm);
 domain:
 	if (tegra->domain)
 		iommu_domain_free(tegra->domain);
@@ -256,7 +254,7 @@
 	if (!fpriv)
 		return -ENOMEM;
 
-	idr_init(&fpriv->contexts);
+	idr_init_base(&fpriv->contexts, 1);
 	mutex_init(&fpriv->lock);
 	filp->driver_priv = fpriv;
 
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 839b49c..767fb44 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -141,7 +141,9 @@
 	for (i = 0; i < hub->soc->num_wgrps; i++) {
 		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-		tegra_windowgroup_enable(wgrp);
+		/* Skip orphaned window group whose parent DC is disabled */
+		if (wgrp->parent)
+			tegra_windowgroup_enable(wgrp);
 	}
 
 	return 0;
@@ -158,7 +160,9 @@
 	for (i = 0; i < hub->soc->num_wgrps; i++) {
 		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-		tegra_windowgroup_disable(wgrp);
+		/* Skip orphaned window group whose parent DC is disabled */
+		if (wgrp->parent)
+			tegra_windowgroup_disable(wgrp);
 	}
 }
 
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index e1669ad..0419b61 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -2875,21 +2875,21 @@
 		if (err < 0) {
 			dev_err(sor->dev, "failed to acquire SOR reset: %d\n",
 				err);
-			return err;
+			goto rpm_put;
 		}
 
 		err = reset_control_assert(sor->rst);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to assert SOR reset: %d\n",
 				err);
-			return err;
+			goto rpm_put;
 		}
 	}
 
 	err = clk_prepare_enable(sor->clk);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to enable clock: %d\n", err);
-		return err;
+		goto rpm_put;
 	}
 
 	usleep_range(1000, 3000);
@@ -2899,19 +2899,25 @@
 		if (err < 0) {
 			dev_err(sor->dev, "failed to deassert SOR reset: %d\n",
 				err);
-			return err;
+			clk_disable_unprepare(sor->clk);
+			goto rpm_put;
 		}
 
 		reset_control_release(sor->rst);
 	}
 
 	err = clk_prepare_enable(sor->clk_safe);
-	if (err < 0)
+	if (err < 0) {
+		clk_disable_unprepare(sor->clk);
 		return err;
+	}
 
 	err = clk_prepare_enable(sor->clk_dp);
-	if (err < 0)
+	if (err < 0) {
+		clk_disable_unprepare(sor->clk_safe);
+		clk_disable_unprepare(sor->clk);
 		return err;
+	}
 
 	/*
 	 * Enable and unmask the HDA codec SCRATCH0 register interrupt. This
@@ -2923,6 +2929,12 @@
 	tegra_sor_writel(sor, value, SOR_INT_MASK);
 
 	return 0;
+
+rpm_put:
+	if (sor->rst)
+		pm_runtime_put(sor->dev);
+
+	return err;
 }
 
 static int tegra_sor_exit(struct host1x_client *client)
@@ -3200,6 +3212,11 @@
 		 * earlier
 		 */
 		sor->pad = TEGRA_IO_PAD_HDMI_DP0 + sor->index;
+	} else {
+		if (sor->soc->supports_edp)
+			sor->index = 0;
+		else
+			sor->index = 1;
 	}
 
 	err = of_property_read_u32_array(np, "nvidia,xbar-cfg", xbar_cfg, 5);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 5584e65..8c4fd1a 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -143,12 +143,16 @@
 	int i;
 
 	for (i = 0; i < timings->num_timings; i++) {
-		struct drm_display_mode *mode = drm_mode_create(dev);
+		struct drm_display_mode *mode;
 		struct videomode vm;
 
 		if (videomode_from_timings(timings, &vm, i))
 			break;
 
+		mode = drm_mode_create(dev);
+		if (!mode)
+			break;
+
 		drm_display_mode_from_videomode(&vm, mode);
 
 		mode->type = DRM_MODE_TYPE_DRIVER;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 9881946..3ffcbaa 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -517,8 +517,10 @@
 
 		dma_resv_unlock(bo->base.resv);
 	}
-	if (bo->base.resv != &bo->base._resv)
+	if (bo->base.resv != &bo->base._resv) {
+		ttm_bo_flush_all_fences(bo);
 		dma_resv_unlock(&bo->base._resv);
+	}
 
 error:
 	kref_get(&bo->list_kref);
@@ -759,7 +761,7 @@
 	/* Don't evict this BO if it's outside of the
 	 * requested placement range
 	 */
-	if (place->fpfn >= (bo->mem.start + bo->mem.size) ||
+	if (place->fpfn >= (bo->mem.start + bo->mem.num_pages) ||
 	    (place->lpfn && place->lpfn <= bo->mem.start))
 		return false;
 
@@ -926,7 +928,8 @@
  */
 static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 				 struct ttm_mem_type_manager *man,
-				 struct ttm_mem_reg *mem)
+				 struct ttm_mem_reg *mem,
+				 bool no_wait_gpu)
 {
 	struct dma_fence *fence;
 	int ret;
@@ -935,19 +938,24 @@
 	fence = dma_fence_get(man->move);
 	spin_unlock(&man->move_lock);
 
-	if (fence) {
-		dma_resv_add_shared_fence(bo->base.resv, fence);
+	if (!fence)
+		return 0;
 
-		ret = dma_resv_reserve_shared(bo->base.resv, 1);
-		if (unlikely(ret)) {
-			dma_fence_put(fence);
-			return ret;
-		}
-
-		dma_fence_put(bo->moving);
-		bo->moving = fence;
+	if (no_wait_gpu) {
+		dma_fence_put(fence);
+		return -EBUSY;
 	}
 
+	dma_resv_add_shared_fence(bo->base.resv, fence);
+
+	ret = dma_resv_reserve_shared(bo->base.resv, 1);
+	if (unlikely(ret)) {
+		dma_fence_put(fence);
+		return ret;
+	}
+
+	dma_fence_put(bo->moving);
+	bo->moving = fence;
 	return 0;
 }
 
@@ -978,7 +986,7 @@
 			return ret;
 	} while (1);
 
-	return ttm_bo_add_move_fence(bo, man, mem);
+	return ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
 }
 
 static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
@@ -1120,14 +1128,18 @@
 		if (unlikely(ret))
 			goto error;
 
-		if (mem->mm_node) {
-			ret = ttm_bo_add_move_fence(bo, man, mem);
-			if (unlikely(ret)) {
-				(*man->func->put_node)(man, mem);
-				goto error;
-			}
-			return 0;
+		if (!mem->mm_node)
+			continue;
+
+		ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
+		if (unlikely(ret)) {
+			(*man->func->put_node)(man, mem);
+			if (ret == -EBUSY)
+				continue;
+
+			goto error;
 		}
+		return 0;
 	}
 
 	for (i = 0; i < placement->num_busy_placement; ++i) {
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 46dc3de..f2bad14 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -358,8 +358,10 @@
 static int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
 			    void *buf, int len, int write)
 {
-	unsigned long offset = (addr) - vma->vm_start;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
+	unsigned long offset = (addr) - vma->vm_start +
+		((vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node))
+		 << PAGE_SHIFT);
 	int ret;
 
 	if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->num_pages)
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index e0e9b4f..c770ec7 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -241,7 +241,6 @@
 	ttm_tt_init_fields(ttm, bo, page_flags);
 
 	if (ttm_tt_alloc_page_directory(ttm)) {
-		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
 	}
@@ -265,7 +264,6 @@
 
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	if (ttm_dma_tt_alloc_page_directory(ttm_dma)) {
-		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
 	}
@@ -287,7 +285,6 @@
 	else
 		ret = ttm_dma_tt_alloc_page_directory(ttm_dma);
 	if (ret) {
-		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c
index d733bbc..17ff24d 100644
--- a/drivers/gpu/drm/tve200/tve200_display.c
+++ b/drivers/gpu/drm/tve200/tve200_display.c
@@ -14,6 +14,7 @@
 #include <linux/version.h>
 #include <linux/dma-buf.h>
 #include <linux/of_graph.h>
+#include <linux/delay.h>
 
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fourcc.h>
@@ -130,9 +131,25 @@
 	struct drm_connector *connector = priv->connector;
 	u32 format = fb->format->format;
 	u32 ctrl1 = 0;
+	int retries;
 
 	clk_prepare_enable(priv->clk);
 
+	/* Reset the TVE200 and wait for it to come back online */
+	writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4);
+	for (retries = 0; retries < 5; retries++) {
+		usleep_range(30000, 50000);
+		if (readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET)
+			continue;
+		else
+			break;
+	}
+	if (retries == 5 &&
+	    readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) {
+		dev_err(drm->dev, "can't get hardware out of reset\n");
+		return;
+	}
+
 	/* Function 1 */
 	ctrl1 |= TVE200_CTRL_CSMODE;
 	/* Interlace mode for CCIR656: parameterize? */
@@ -230,8 +247,9 @@
 
 	drm_crtc_vblank_off(crtc);
 
-	/* Disable and Power Down */
+	/* Disable put into reset and Power Down */
 	writel(0, priv->regs + TVE200_CTRL);
+	writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4);
 
 	clk_disable_unprepare(priv->clk);
 }
@@ -279,6 +297,8 @@
 	struct drm_device *drm = crtc->dev;
 	struct tve200_drm_dev_private *priv = drm->dev_private;
 
+	/* Clear any IRQs and enable */
+	writel(0xFF, priv->regs + TVE200_INT_CLR);
 	writel(TVE200_INT_V_STATUS, priv->regs + TVE200_INT_EN);
 	return 0;
 }
diff --git a/drivers/gpu/drm/tve200/tve200_drv.c b/drivers/gpu/drm/tve200/tve200_drv.c
index 416f248..02836d4 100644
--- a/drivers/gpu/drm/tve200/tve200_drv.c
+++ b/drivers/gpu/drm/tve200/tve200_drv.c
@@ -210,8 +210,8 @@
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
-		ret = -EINVAL;
+	if (irq < 0) {
+		ret = irq;
 		goto clk_disable;
 	}
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 5e6fb6c..0d78ba0 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -309,6 +309,7 @@
 	component_unbind_all(dev, drm);
 gem_destroy:
 	vc4_gem_destroy(drm);
+	drm_mode_config_cleanup(drm);
 	vc4_bo_cache_destroy(drm);
 dev_put:
 	drm_dev_put(drm);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 6627b20..3ddaa81 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -750,7 +750,7 @@
 void vc4_crtc_handle_vblank(struct vc4_crtc *crtc);
 void vc4_crtc_txp_armed(struct drm_crtc_state *state);
 void vc4_crtc_get_margins(struct drm_crtc_state *state,
-			  unsigned int *right, unsigned int *left,
+			  unsigned int *left, unsigned int *right,
 			  unsigned int *top, unsigned int *bottom);
 
 /* vc4_debugfs.c */
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index ee7d4e7..54435b7 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -681,11 +681,23 @@
 vc4_hdmi_encoder_mode_valid(struct drm_encoder *crtc,
 			    const struct drm_display_mode *mode)
 {
-	/* HSM clock must be 108% of the pixel clock.  Additionally,
-	 * the AXI clock needs to be at least 25% of pixel clock, but
-	 * HSM ends up being the limiting factor.
+	/*
+	 * As stated in RPi's vc4 firmware "HDMI state machine (HSM) clock must
+	 * be faster than pixel clock, infinitesimally faster, tested in
+	 * simulation. Otherwise, exact value is unimportant for HDMI
+	 * operation." This conflicts with bcm2835's vc4 documentation, which
+	 * states HSM's clock has to be at least 108% of the pixel clock.
+	 *
+	 * Real life tests reveal that vc4's firmware statement holds up, and
+	 * users are able to use pixel clocks closer to HSM's, namely for
+	 * 1920x1200@60Hz. So it was decided to have leave a 1% margin between
+	 * both clocks. Which, for RPi0-3 implies a maximum pixel clock of
+	 * 162MHz.
+	 *
+	 * Additionally, the AXI clock needs to be at least 25% of
+	 * pixel clock, but HSM ends up being the limiting factor.
 	 */
-	if (mode->clock > HSM_CLOCK_FREQ / (1000 * 108 / 100))
+	if (mode->clock > HSM_CLOCK_FREQ / (1000 * 101 / 100))
 		return MODE_CLOCK_HIGH;
 
 	return MODE_OK;
@@ -1113,6 +1125,7 @@
 	card->num_links = 1;
 	card->name = "vc4-hdmi";
 	card->dev = dev;
+	card->owner = THIS_MODULE;
 
 	/*
 	 * Be careful, snd_soc_register_card() calls dev_set_drvdata() and
@@ -1285,6 +1298,9 @@
 
 static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 {
+#ifdef CONFIG_DRM_VC4_HDMI_CEC
+	struct cec_connector_info conn_info;
+#endif
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dev *vc4 = drm->dev_private;
@@ -1403,13 +1419,15 @@
 #ifdef CONFIG_DRM_VC4_HDMI_CEC
 	hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops,
 					      vc4, "vc4",
-					      CEC_CAP_TRANSMIT |
-					      CEC_CAP_LOG_ADDRS |
-					      CEC_CAP_PASSTHROUGH |
-					      CEC_CAP_RC, 1);
+					      CEC_CAP_DEFAULTS |
+					      CEC_CAP_CONNECTOR_INFO, 1);
 	ret = PTR_ERR_OR_ZERO(hdmi->cec_adap);
 	if (ret < 0)
 		goto err_destroy_conn;
+
+	cec_fill_conn_info_from_drm(&conn_info, hdmi->connector);
+	cec_s_conn_info(hdmi->cec_adap, &conn_info);
+
 	HDMI_WRITE(VC4_HDMI_CPU_MASK_SET, 0xffffffff);
 	value = HDMI_READ(VC4_HDMI_CEC_CNTRL_1);
 	value &= ~VC4_HDMI_CEC_DIV_CLK_CNT_MASK;
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 5e5f908..363f456 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -205,7 +205,7 @@
 	__drm_atomic_helper_plane_reset(plane, &vc4_state->base);
 }
 
-static void vc4_dlist_write(struct vc4_plane_state *vc4_state, u32 val)
+static void vc4_dlist_counter_increment(struct vc4_plane_state *vc4_state)
 {
 	if (vc4_state->dlist_count == vc4_state->dlist_size) {
 		u32 new_size = max(4u, vc4_state->dlist_count * 2);
@@ -220,7 +220,15 @@
 		vc4_state->dlist_size = new_size;
 	}
 
-	vc4_state->dlist[vc4_state->dlist_count++] = val;
+	vc4_state->dlist_count++;
+}
+
+static void vc4_dlist_write(struct vc4_plane_state *vc4_state, u32 val)
+{
+	unsigned int idx = vc4_state->dlist_count;
+
+	vc4_dlist_counter_increment(vc4_state);
+	vc4_state->dlist[idx] = val;
 }
 
 /* Returns the scl0/scl1 field based on whether the dimensions need to
@@ -871,8 +879,10 @@
 		 * be set when calling vc4_plane_allocate_lbm().
 		 */
 		if (vc4_state->y_scaling[0] != VC4_SCALING_NONE ||
-		    vc4_state->y_scaling[1] != VC4_SCALING_NONE)
-			vc4_state->lbm_offset = vc4_state->dlist_count++;
+		    vc4_state->y_scaling[1] != VC4_SCALING_NONE) {
+			vc4_state->lbm_offset = vc4_state->dlist_count;
+			vc4_dlist_counter_increment(vc4_state);
+		}
 
 		if (num_planes > 1) {
 			/* Emit Cb/Cr as channel 0 and Y as channel
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 5bd60de..204d1df 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -196,9 +196,10 @@
 		return ERR_CAST(obj);
 
 	ret = drm_gem_handle_create(file, &obj->base, handle);
-	drm_gem_object_put_unlocked(&obj->base);
-	if (ret)
+	if (ret) {
+		drm_gem_object_put_unlocked(&obj->base);
 		return ERR_PTR(ret);
+	}
 
 	return &obj->base;
 }
@@ -221,37 +222,13 @@
 	args->size = gem_object->size;
 	args->pitch = pitch;
 
-	DRM_DEBUG("Created object of size %lld\n", size);
+	drm_gem_object_put_unlocked(gem_object);
+
+	DRM_DEBUG("Created object of size %llu\n", args->size);
 
 	return 0;
 }
 
-static int vgem_gem_dumb_map(struct drm_file *file, struct drm_device *dev,
-			     uint32_t handle, uint64_t *offset)
-{
-	struct drm_gem_object *obj;
-	int ret;
-
-	obj = drm_gem_object_lookup(file, handle);
-	if (!obj)
-		return -ENOENT;
-
-	if (!obj->filp) {
-		ret = -EINVAL;
-		goto unref;
-	}
-
-	ret = drm_gem_create_mmap_offset(obj);
-	if (ret)
-		goto unref;
-
-	*offset = drm_vma_node_offset_addr(&obj->vma_node);
-unref:
-	drm_gem_object_put_unlocked(obj);
-
-	return ret;
-}
-
 static struct drm_ioctl_desc vgem_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VGEM_FENCE_ATTACH, vgem_fence_attach_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VGEM_FENCE_SIGNAL, vgem_fence_signal_ioctl, DRM_RENDER_ALLOW),
@@ -445,7 +422,6 @@
 	.fops				= &vgem_driver_fops,
 
 	.dumb_create			= vgem_gem_dumb_create,
-	.dumb_map_offset		= vgem_gem_dumb_map,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c
index c190702..4f855b2 100644
--- a/drivers/gpu/drm/virtio/virtgpu_kms.c
+++ b/drivers/gpu/drm/virtio/virtgpu_kms.c
@@ -96,8 +96,10 @@
 					 vgdev->capsets[i].id > 0, 5 * HZ);
 		if (ret == 0) {
 			DRM_ERROR("timed out waiting for cap set %d\n", i);
+			spin_lock(&vgdev->display_info_lock);
 			kfree(vgdev->capsets);
 			vgdev->capsets = NULL;
+			spin_unlock(&vgdev->display_info_lock);
 			return;
 		}
 		DRM_INFO("cap set %d: id %d, max-version %d, max-size %d\n",
@@ -216,6 +218,7 @@
 err_vbufs:
 	vgdev->vdev->config->del_vqs(vgdev->vdev);
 err_vqs:
+	dev->dev_private = NULL;
 	kfree(vgdev);
 	return ret;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 09b5265..8de93cc 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -23,38 +23,44 @@
  * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/moduleparam.h>
+
 #include <drm/ttm/ttm_execbuf_util.h>
 
 #include "virtgpu_drv.h"
 
+static int virtio_gpu_virglrenderer_workaround = 1;
+module_param_named(virglhack, virtio_gpu_virglrenderer_workaround, int, 0400);
+
 static int virtio_gpu_resource_id_get(struct virtio_gpu_device *vgdev,
 				       uint32_t *resid)
 {
-#if 0
-	int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);
-
-	if (handle < 0)
-		return handle;
-#else
-	static int handle;
-
-	/*
-	 * FIXME: dirty hack to avoid re-using IDs, virglrenderer
-	 * can't deal with that.  Needs fixing in virglrenderer, also
-	 * should figure a better way to handle that in the guest.
-	 */
-	handle++;
-#endif
-
-	*resid = handle + 1;
+	if (virtio_gpu_virglrenderer_workaround) {
+		/*
+		 * Hack to avoid re-using resource IDs.
+		 *
+		 * virglrenderer versions up to (and including) 0.7.0
+		 * can't deal with that.  virglrenderer commit
+		 * "f91a9dd35715 Fix unlinking resources from hash
+		 * table." (Feb 2019) fixes the bug.
+		 */
+		static atomic_t seqno = ATOMIC_INIT(0);
+		int handle = atomic_inc_return(&seqno);
+		*resid = handle + 1;
+	} else {
+		int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);
+		if (handle < 0)
+			return handle;
+		*resid = handle + 1;
+	}
 	return 0;
 }
 
 static void virtio_gpu_resource_id_put(struct virtio_gpu_device *vgdev, uint32_t id)
 {
-#if 0
-	ida_free(&vgdev->resource_ida, id - 1);
-#endif
+	if (!virtio_gpu_virglrenderer_workaround) {
+		ida_free(&vgdev->resource_ida, id - 1);
+	}
 }
 
 static void virtio_gpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 7ac2049..bb46e7a 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -572,9 +572,13 @@
 	int i = le32_to_cpu(cmd->capset_index);
 
 	spin_lock(&vgdev->display_info_lock);
-	vgdev->capsets[i].id = le32_to_cpu(resp->capset_id);
-	vgdev->capsets[i].max_version = le32_to_cpu(resp->capset_max_version);
-	vgdev->capsets[i].max_size = le32_to_cpu(resp->capset_max_size);
+	if (vgdev->capsets) {
+		vgdev->capsets[i].id = le32_to_cpu(resp->capset_id);
+		vgdev->capsets[i].max_version = le32_to_cpu(resp->capset_max_version);
+		vgdev->capsets[i].max_size = le32_to_cpu(resp->capset_max_size);
+	} else {
+		DRM_ERROR("invalid capset memory.");
+	}
 	spin_unlock(&vgdev->display_info_lock);
 	wake_up(&vgdev->resp_wq);
 }
@@ -988,8 +992,9 @@
 	}
 
 	/* gets freed when the ring has consumed it */
-	ents = kmalloc_array(nents, sizeof(struct virtio_gpu_mem_entry),
-			     GFP_KERNEL);
+	ents = kvmalloc_array(nents,
+			      sizeof(struct virtio_gpu_mem_entry),
+			      GFP_KERNEL);
 	if (!ents) {
 		DRM_ERROR("failed to allocate ent list\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index d558569..45d6ebb 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -33,7 +33,7 @@
 				     + (i * composer->pitch)
 				     + (j * composer->cpp);
 			/* XRGB format ignores Alpha channel */
-			memset(vaddr_out + src_offset + 24, 0,  8);
+			bitmap_clear(vaddr_out + src_offset, 24, 8);
 			crc = crc32_le(crc, vaddr_out + src_offset,
 				       sizeof(u32));
 		}
diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
index 927dafa..8b01fae 100644
--- a/drivers/gpu/drm/vkms/vkms_crtc.c
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -20,7 +20,8 @@
 
 	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
 					  output->period_ns);
-	WARN_ON(ret_overrun != 1);
+	if (ret_overrun != 1)
+		pr_warn("%s: vblank timer overrun\n", __func__);
 
 	ret = drm_crtc_handle_vblank(crtc);
 	if (!ret)
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index 5a95100..03b05c5 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -121,11 +121,6 @@
 				  enum drm_plane_type type, int index);
 
 /* Gem stuff */
-struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
-				       struct drm_file *file,
-				       u32 *handle,
-				       u64 size);
-
 vm_fault_t vkms_gem_fault(struct vm_fault *vmf);
 
 int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c
index 6489bfe..8ba8b87 100644
--- a/drivers/gpu/drm/vkms/vkms_gem.c
+++ b/drivers/gpu/drm/vkms/vkms_gem.c
@@ -95,10 +95,10 @@
 	return ret;
 }
 
-struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
-				       struct drm_file *file,
-				       u32 *handle,
-				       u64 size)
+static struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+					      struct drm_file *file,
+					      u32 *handle,
+					      u64 size)
 {
 	struct vkms_gem_object *obj;
 	int ret;
@@ -111,7 +111,6 @@
 		return ERR_CAST(obj);
 
 	ret = drm_gem_handle_create(file, &obj->gem, handle);
-	drm_gem_object_put_unlocked(&obj->gem);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -140,6 +139,8 @@
 	args->size = gem_obj->size;
 	args->pitch = pitch;
 
+	drm_gem_object_put_unlocked(gem_obj);
+
 	DRM_DEBUG_DRIVER("Created object of size %lld\n", size);
 
 	return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index 4ac55fc..44d858c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -209,8 +209,10 @@
 
 	cres->hash.key = user_key | (res_type << 24);
 	ret = drm_ht_insert_item(&man->resources, &cres->hash);
-	if (unlikely(ret != 0))
+	if (unlikely(ret != 0)) {
+		kfree(cres);
 		goto out_invalid_key;
+	}
 
 	cres->state = VMW_CMDBUF_RES_ADD;
 	cres->res = vmw_resource_reference(res);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index f47d571..33b1519 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2666,7 +2666,7 @@
 		++i;
 	}
 
-	if (i != unit) {
+	if (&con->head == &dev_priv->dev->mode_config.connector_list) {
 		DRM_ERROR("Could not find initial display unit.\n");
 		ret = -EINVAL;
 		goto out_unlock;
@@ -2690,13 +2690,13 @@
 			break;
 	}
 
-	if (mode->type & DRM_MODE_TYPE_PREFERRED)
-		*p_mode = mode;
-	else {
+	if (&mode->head == &con->modes) {
 		WARN_ONCE(true, "Could not find initial preferred mode.\n");
 		*p_mode = list_first_entry(&con->modes,
 					   struct drm_display_mode,
 					   head);
+	} else {
+		*p_mode = mode;
 	}
 
  out_unlock:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 5702219..7b54c1f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -81,7 +81,7 @@
 	struct vmw_legacy_display_unit *entry;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_crtc *crtc = NULL;
-	int i = 0;
+	int i;
 
 	/* If there is no display topology the host just assumes
 	 * that the guest will set the same layout as the host.
@@ -92,12 +92,11 @@
 			crtc = &entry->base.crtc;
 			w = max(w, crtc->x + crtc->mode.hdisplay);
 			h = max(h, crtc->y + crtc->mode.vdisplay);
-			i++;
 		}
 
 		if (crtc == NULL)
 			return 0;
-		fb = entry->base.crtc.primary->state->fb;
+		fb = crtc->primary->state->fb;
 
 		return vmw_kms_write_svga(dev_priv, w, h, fb->pitches[0],
 					  fb->format->cpp[0] * 8,
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 4be49c1..09894a1 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -400,7 +400,7 @@
 	args->size = args->pitch * args->height;
 
 	obj = xen_drm_front_gem_create(dev, args->size);
-	if (IS_ERR_OR_NULL(obj)) {
+	if (IS_ERR(obj)) {
 		ret = PTR_ERR(obj);
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index f0b85e0..4ec8a49 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -83,7 +83,7 @@
 
 	size = round_up(size, PAGE_SIZE);
 	xen_obj = gem_create_obj(dev, size);
-	if (IS_ERR_OR_NULL(xen_obj))
+	if (IS_ERR(xen_obj))
 		return xen_obj;
 
 	if (drm_info->front_info->cfg.be_alloc) {
@@ -117,7 +117,7 @@
 	 */
 	xen_obj->num_pages = DIV_ROUND_UP(size, PAGE_SIZE);
 	xen_obj->pages = drm_gem_get_pages(&xen_obj->base);
-	if (IS_ERR_OR_NULL(xen_obj->pages)) {
+	if (IS_ERR(xen_obj->pages)) {
 		ret = PTR_ERR(xen_obj->pages);
 		xen_obj->pages = NULL;
 		goto fail;
@@ -136,7 +136,7 @@
 	struct xen_gem_object *xen_obj;
 
 	xen_obj = gem_create(dev, size);
-	if (IS_ERR_OR_NULL(xen_obj))
+	if (IS_ERR(xen_obj))
 		return ERR_CAST(xen_obj);
 
 	return &xen_obj->base;
@@ -194,7 +194,7 @@
 
 	size = attach->dmabuf->size;
 	xen_obj = gem_create_obj(dev, size);
-	if (IS_ERR_OR_NULL(xen_obj))
+	if (IS_ERR(xen_obj))
 		return ERR_CAST(xen_obj);
 
 	ret = gem_alloc_pages_array(xen_obj, size);
diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c
index 21ad1c3..e4dedbb 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_kms.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c
@@ -60,7 +60,7 @@
 	int ret;
 
 	fb = drm_gem_fb_create_with_funcs(dev, filp, mode_cmd, &fb_funcs);
-	if (IS_ERR_OR_NULL(fb))
+	if (IS_ERR(fb))
 		return fb;
 
 	gem_obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]);
diff --git a/drivers/gpu/drm/zte/Kconfig b/drivers/gpu/drm/zte/Kconfig
index 90ebaed..aa85941 100644
--- a/drivers/gpu/drm/zte/Kconfig
+++ b/drivers/gpu/drm/zte/Kconfig
@@ -3,7 +3,6 @@
 	tristate "DRM Support for ZTE SoCs"
 	depends on DRM && ARCH_ZX
 	select DRM_KMS_CMA_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_HELPER
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select VIDEOMODE_HELPERS
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 742aa9f..fcda862 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -686,8 +686,17 @@
  */
 void host1x_driver_unregister(struct host1x_driver *driver)
 {
+	struct host1x *host1x;
+
 	driver_unregister(&driver->driver);
 
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list)
+		host1x_detach_driver(host1x, driver);
+
+	mutex_unlock(&devices_lock);
+
 	mutex_lock(&drivers_lock);
 	list_del_init(&driver->list);
 	mutex_unlock(&drivers_lock);
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index c039267..1b4997b 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/drivers/gpu/host1x/debug.c
@@ -16,6 +16,8 @@
 #include "debug.h"
 #include "channel.h"
 
+static DEFINE_MUTEX(debug_lock);
+
 unsigned int host1x_debug_trace_cmdbuf;
 
 static pid_t host1x_debug_force_timeout_pid;
@@ -52,12 +54,14 @@
 	struct output *o = data;
 
 	mutex_lock(&ch->cdma.lock);
+	mutex_lock(&debug_lock);
 
 	if (show_fifo)
 		host1x_hw_show_channel_fifo(m, ch, o);
 
 	host1x_hw_show_channel_cdma(m, ch, o);
 
+	mutex_unlock(&debug_lock);
 	mutex_unlock(&ch->cdma.lock);
 
 	return 0;
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index eaa5c33..2255967 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -436,7 +436,8 @@
 	return err;
 }
 
-static inline int copy_gathers(struct host1x_job *job, struct device *dev)
+static inline int copy_gathers(struct device *host, struct host1x_job *job,
+			       struct device *dev)
 {
 	struct host1x_firewall fw;
 	size_t size = 0;
@@ -459,12 +460,12 @@
 	 * Try a non-blocking allocation from a higher priority pools first,
 	 * as awaiting for the allocation here is a major performance hit.
 	 */
-	job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy,
+	job->gather_copy_mapped = dma_alloc_wc(host, size, &job->gather_copy,
 					       GFP_NOWAIT);
 
 	/* the higher priority allocation failed, try the generic-blocking */
 	if (!job->gather_copy_mapped)
-		job->gather_copy_mapped = dma_alloc_wc(dev, size,
+		job->gather_copy_mapped = dma_alloc_wc(host, size,
 						       &job->gather_copy,
 						       GFP_KERNEL);
 	if (!job->gather_copy_mapped)
@@ -512,7 +513,7 @@
 		goto out;
 
 	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) {
-		err = copy_gathers(job, dev);
+		err = copy_gathers(host->dev, job, dev);
 		if (err)
 			goto out;
 	}
@@ -573,7 +574,7 @@
 	job->num_unpins = 0;
 
 	if (job->gather_copy_size)
-		dma_free_wc(job->channel->dev, job->gather_copy_size,
+		dma_free_wc(host->dev, job->gather_copy_size,
 			    job->gather_copy_mapped, job->gather_copy);
 }
 EXPORT_SYMBOL(host1x_job_unpin);
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index ee2a025..b3dae9e 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -124,6 +124,8 @@
 	case V4L2_PIX_FMT_RGBX32:
 	case V4L2_PIX_FMT_ARGB32:
 	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_BGR32:
 		return IPUV3_COLORSPACE_RGB;
 	default:
 		return IPUV3_COLORSPACE_UNKNOWN;
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index a1c85d1..82b244c 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -585,21 +585,21 @@
 	.bits_per_pixel = 16,
 };
 
-#define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
-#define U_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * ((y) / 2) / 2) + (x) / 2)
-#define V_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * pix->height / 4) +	\
-				 (pix->width * ((y) / 2) / 2) + (x) / 2)
-#define U2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * (y) / 2) + (x) / 2)
-#define V2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * pix->height / 2) +	\
-				 (pix->width * (y) / 2) + (x) / 2)
-#define UV_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
-				 (pix->width * ((y) / 2)) + (x))
-#define UV2_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
-				 (pix->width * y) + (x))
+#define Y_OFFSET(pix, x, y)	((x) + pix->bytesperline * (y))
+#define U_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * ((y) / 2) / 2) + (x) / 2)
+#define V_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * pix->height / 4) + \
+				 (pix->bytesperline * ((y) / 2) / 2) + (x) / 2)
+#define U2_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * (y) / 2) + (x) / 2)
+#define V2_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * pix->height / 2) + \
+				 (pix->bytesperline * (y) / 2) + (x) / 2)
+#define UV_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * ((y) / 2)) + (x))
+#define UV2_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * y) + (x))
 
 #define NUM_ALPHA_CHANNELS	7
 
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index eeca50d..aa1d4b6 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -137,6 +137,17 @@
 struct ipu_image_convert_chan;
 struct ipu_image_convert_priv;
 
+enum eof_irq_mask {
+	EOF_IRQ_IN      = BIT(0),
+	EOF_IRQ_ROT_IN  = BIT(1),
+	EOF_IRQ_OUT     = BIT(2),
+	EOF_IRQ_ROT_OUT = BIT(3),
+};
+
+#define EOF_IRQ_COMPLETE (EOF_IRQ_IN | EOF_IRQ_OUT)
+#define EOF_IRQ_ROT_COMPLETE (EOF_IRQ_IN | EOF_IRQ_OUT |	\
+			      EOF_IRQ_ROT_IN | EOF_IRQ_ROT_OUT)
+
 struct ipu_image_convert_ctx {
 	struct ipu_image_convert_chan *chan;
 
@@ -173,6 +184,9 @@
 	/* where to place converted tile in dest image */
 	unsigned int out_tile_map[MAX_TILES];
 
+	/* mask of completed EOF irqs at every tile conversion */
+	enum eof_irq_mask eof_mask;
+
 	struct list_head list;
 };
 
@@ -189,6 +203,8 @@
 	struct ipuv3_channel *rotation_out_chan;
 
 	/* the IPU end-of-frame irqs */
+	int in_eof_irq;
+	int rot_in_eof_irq;
 	int out_eof_irq;
 	int rot_out_eof_irq;
 
@@ -1380,6 +1396,9 @@
 	dev_dbg(priv->ipu->dev, "%s: task %u: starting ctx %p run %p tile %u -> %u\n",
 		__func__, chan->ic_task, ctx, run, tile, dst_tile);
 
+	/* clear EOF irq mask */
+	ctx->eof_mask = 0;
+
 	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
 		/* swap width/height for resizer */
 		dest_width = d_image->tile[dst_tile].height;
@@ -1615,7 +1634,7 @@
 }
 
 /* hold irqlock when calling */
-static irqreturn_t do_irq(struct ipu_image_convert_run *run)
+static irqreturn_t do_tile_complete(struct ipu_image_convert_run *run)
 {
 	struct ipu_image_convert_ctx *ctx = run->ctx;
 	struct ipu_image_convert_chan *chan = ctx->chan;
@@ -1700,6 +1719,7 @@
 		ctx->cur_buf_num ^= 1;
 	}
 
+	ctx->eof_mask = 0; /* clear EOF irq mask for next tile */
 	ctx->next_tile++;
 	return IRQ_HANDLED;
 done:
@@ -1709,45 +1729,15 @@
 	return IRQ_WAKE_THREAD;
 }
 
-static irqreturn_t norotate_irq(int irq, void *data)
-{
-	struct ipu_image_convert_chan *chan = data;
-	struct ipu_image_convert_ctx *ctx;
-	struct ipu_image_convert_run *run;
-	unsigned long flags;
-	irqreturn_t ret;
-
-	spin_lock_irqsave(&chan->irqlock, flags);
-
-	/* get current run and its context */
-	run = chan->current_run;
-	if (!run) {
-		ret = IRQ_NONE;
-		goto out;
-	}
-
-	ctx = run->ctx;
-
-	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
-		/* this is a rotation operation, just ignore */
-		spin_unlock_irqrestore(&chan->irqlock, flags);
-		return IRQ_HANDLED;
-	}
-
-	ret = do_irq(run);
-out:
-	spin_unlock_irqrestore(&chan->irqlock, flags);
-	return ret;
-}
-
-static irqreturn_t rotate_irq(int irq, void *data)
+static irqreturn_t eof_irq(int irq, void *data)
 {
 	struct ipu_image_convert_chan *chan = data;
 	struct ipu_image_convert_priv *priv = chan->priv;
 	struct ipu_image_convert_ctx *ctx;
 	struct ipu_image_convert_run *run;
+	irqreturn_t ret = IRQ_HANDLED;
+	bool tile_complete = false;
 	unsigned long flags;
-	irqreturn_t ret;
 
 	spin_lock_irqsave(&chan->irqlock, flags);
 
@@ -1760,14 +1750,33 @@
 
 	ctx = run->ctx;
 
-	if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
-		/* this was NOT a rotation operation, shouldn't happen */
-		dev_err(priv->ipu->dev, "Unexpected rotation interrupt\n");
-		spin_unlock_irqrestore(&chan->irqlock, flags);
-		return IRQ_HANDLED;
+	if (irq == chan->in_eof_irq) {
+		ctx->eof_mask |= EOF_IRQ_IN;
+	} else if (irq == chan->out_eof_irq) {
+		ctx->eof_mask |= EOF_IRQ_OUT;
+	} else if (irq == chan->rot_in_eof_irq ||
+		   irq == chan->rot_out_eof_irq) {
+		if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
+			/* this was NOT a rotation op, shouldn't happen */
+			dev_err(priv->ipu->dev,
+				"Unexpected rotation interrupt\n");
+			goto out;
+		}
+		ctx->eof_mask |= (irq == chan->rot_in_eof_irq) ?
+			EOF_IRQ_ROT_IN : EOF_IRQ_ROT_OUT;
+	} else {
+		dev_err(priv->ipu->dev, "Received unknown irq %d\n", irq);
+		ret = IRQ_NONE;
+		goto out;
 	}
 
-	ret = do_irq(run);
+	if (ipu_rot_mode_is_irt(ctx->rot_mode))
+		tile_complete =	(ctx->eof_mask == EOF_IRQ_ROT_COMPLETE);
+	else
+		tile_complete = (ctx->eof_mask == EOF_IRQ_COMPLETE);
+
+	if (tile_complete)
+		ret = do_tile_complete(run);
 out:
 	spin_unlock_irqrestore(&chan->irqlock, flags);
 	return ret;
@@ -1801,6 +1810,10 @@
 
 static void release_ipu_resources(struct ipu_image_convert_chan *chan)
 {
+	if (chan->in_eof_irq >= 0)
+		free_irq(chan->in_eof_irq, chan);
+	if (chan->rot_in_eof_irq >= 0)
+		free_irq(chan->rot_in_eof_irq, chan);
 	if (chan->out_eof_irq >= 0)
 		free_irq(chan->out_eof_irq, chan);
 	if (chan->rot_out_eof_irq >= 0)
@@ -1819,7 +1832,27 @@
 
 	chan->in_chan = chan->out_chan = chan->rotation_in_chan =
 		chan->rotation_out_chan = NULL;
-	chan->out_eof_irq = chan->rot_out_eof_irq = -1;
+	chan->in_eof_irq = -1;
+	chan->rot_in_eof_irq = -1;
+	chan->out_eof_irq = -1;
+	chan->rot_out_eof_irq = -1;
+}
+
+static int get_eof_irq(struct ipu_image_convert_chan *chan,
+		       struct ipuv3_channel *channel)
+{
+	struct ipu_image_convert_priv *priv = chan->priv;
+	int ret, irq;
+
+	irq = ipu_idmac_channel_irq(priv->ipu, channel, IPU_IRQ_EOF);
+
+	ret = request_threaded_irq(irq, eof_irq, do_bh, 0, "ipu-ic", chan);
+	if (ret < 0) {
+		dev_err(priv->ipu->dev, "could not acquire irq %d\n", irq);
+		return ret;
+	}
+
+	return irq;
 }
 
 static int get_ipu_resources(struct ipu_image_convert_chan *chan)
@@ -1855,31 +1888,33 @@
 	}
 
 	/* acquire the EOF interrupts */
-	chan->out_eof_irq = ipu_idmac_channel_irq(priv->ipu,
-						  chan->out_chan,
-						  IPU_IRQ_EOF);
-
-	ret = request_threaded_irq(chan->out_eof_irq, norotate_irq, do_bh,
-				   0, "ipu-ic", chan);
+	ret = get_eof_irq(chan, chan->in_chan);
 	if (ret < 0) {
-		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
-			 chan->out_eof_irq);
+		chan->in_eof_irq = -1;
+		goto err;
+	}
+	chan->in_eof_irq = ret;
+
+	ret = get_eof_irq(chan, chan->rotation_in_chan);
+	if (ret < 0) {
+		chan->rot_in_eof_irq = -1;
+		goto err;
+	}
+	chan->rot_in_eof_irq = ret;
+
+	ret = get_eof_irq(chan, chan->out_chan);
+	if (ret < 0) {
 		chan->out_eof_irq = -1;
 		goto err;
 	}
+	chan->out_eof_irq = ret;
 
-	chan->rot_out_eof_irq = ipu_idmac_channel_irq(priv->ipu,
-						     chan->rotation_out_chan,
-						     IPU_IRQ_EOF);
-
-	ret = request_threaded_irq(chan->rot_out_eof_irq, rotate_irq, do_bh,
-				   0, "ipu-ic", chan);
+	ret = get_eof_irq(chan, chan->rotation_out_chan);
 	if (ret < 0) {
-		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
-			chan->rot_out_eof_irq);
 		chan->rot_out_eof_irq = -1;
 		goto err;
 	}
+	chan->rot_out_eof_irq = ret;
 
 	return 0;
 err:
@@ -2458,6 +2493,8 @@
 		chan->ic_task = i;
 		chan->priv = priv;
 		chan->dma_ch = &image_convert_dma_chan[i];
+		chan->in_eof_irq = -1;
+		chan->rot_in_eof_irq = -1;
 		chan->out_eof_irq = -1;
 		chan->rot_out_eof_irq = -1;