Merge branch 'for-5.5/core' into for-linus

- hid_have_special_driver[] cleanup for LED devices (Heiner Kallweit)
- HID parser improvements (Blaž Hrastnik, Candle Sun)

149 files changed, 1370 insertions, 637 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 42e2c1f57152..00962a659009 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -54,7 +54,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
 	amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \
 	amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
-	amdgpu_vm_sdma.o amdgpu_pmu.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
+	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
 
 amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index eba42c752bca..82155ac3288a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -189,7 +189,7 @@ static int acp_hw_init(void *handle)
 	u32 val = 0;
 	u32 count = 0;
 	struct device *dev;
-	struct i2s_platform_data *i2s_pdata;
+	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
@@ -231,20 +231,21 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_cell = kcalloc(ACP_DEVS, sizeof(struct mfd_cell),
 							GFP_KERNEL);
 
-	if (adev->acp.acp_cell == NULL)
-		return -ENOMEM;
+	if (adev->acp.acp_cell == NULL) {
+		r = -ENOMEM;
+		goto failure;
+	}
 
 	adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
 	if (adev->acp.acp_res == NULL) {
-		kfree(adev->acp.acp_cell);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto failure;
 	}
 
 	i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
 	if (i2s_pdata == NULL) {
-		kfree(adev->acp.acp_res);
-		kfree(adev->acp.acp_cell);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto failure;
 	}
 
 	switch (adev->asic_type) {
@@ -341,14 +342,14 @@ static int acp_hw_init(void *handle)
 	r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
 								ACP_DEVS);
 	if (r)
-		return 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");
-			return r;
+			goto failure;
 		}
 	}
 
@@ -367,7 +368,8 @@ static int acp_hw_init(void *handle)
 			break;
 		if (--count == 0) {
 			dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
-			return -ETIMEDOUT;
+			r = -ETIMEDOUT;
+			goto failure;
 		}
 		udelay(100);
 	}
@@ -384,7 +386,8 @@ static int acp_hw_init(void *handle)
 			break;
 		if (--count == 0) {
 			dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
-			return -ETIMEDOUT;
+			r = -ETIMEDOUT;
+			goto failure;
 		}
 		udelay(100);
 	}
@@ -393,6 +396,13 @@ static int acp_hw_init(void *handle)
 	val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
 	cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
 	return 0;
+
+failure:
+	kfree(i2s_pdata);
+	kfree(adev->acp.acp_res);
+	kfree(adev->acp.acp_cell);
+	kfree(adev->acp.acp_genpd);
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 42b936b6bbf1..6d021ecc8d59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1103,7 +1103,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		alloc_flags = 0;
 		if (!offset || !*offset)
 			return -EINVAL;
-		user_addr = *offset;
+		user_addr = untagged_addr(*offset);
 	} else if (flags & (ALLOC_MEM_FLAGS_DOORBELL |
 			ALLOC_MEM_FLAGS_MMIO_REMAP)) {
 		domain = AMDGPU_GEM_DOMAIN_GTT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 7bcf86c61999..85b0515c0fdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -140,7 +140,12 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 	return 0;
 
 error_free:
-	while (i--) {
+	for (i = 0; i < last_entry; ++i) {
+		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
+
+		amdgpu_bo_unref(&bo);
+	}
+	for (i = first_userptr; i < num_entries; ++i) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
 
 		amdgpu_bo_unref(&bo);
@@ -270,7 +275,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
 	if (r)
-		goto error_free;
+		return r;
 
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
@@ -283,8 +288,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
 		mutex_unlock(&fpriv->bo_list_lock);
 		if (r < 0) {
-			amdgpu_bo_list_put(list);
-			return r;
+			goto error_put_list;
 		}
 
 		handle = r;
@@ -306,9 +310,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		mutex_unlock(&fpriv->bo_list_lock);
 
 		if (IS_ERR(old)) {
-			amdgpu_bo_list_put(list);
 			r = PTR_ERR(old);
-			goto error_free;
+			goto error_put_list;
 		}
 
 		amdgpu_bo_list_put(old);
@@ -325,8 +328,10 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 
 	return 0;
 
+error_put_list:
+	amdgpu_bo_list_put(list);
+
 error_free:
-	if (info)
-		kvfree(info);
+	kvfree(info);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2e53feed40e2..82823d9a8ba8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -536,7 +536,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 
 	list_for_each_entry(lobj, validated, tv.head) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo);
-		bool binding_userptr = false;
 		struct mm_struct *usermm;
 
 		usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm);
@@ -553,7 +552,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
 						     lobj->user_pages);
-			binding_userptr = true;
 		}
 
 		if (p->evictable == lobj)
@@ -563,10 +561,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		if (r)
 			return r;
 
-		if (binding_userptr) {
-			kvfree(lobj->user_pages);
-			lobj->user_pages = NULL;
-		}
+		kvfree(lobj->user_pages);
+		lobj->user_pages = NULL;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 61bd10310604..5803fcbae22f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -948,6 +948,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 	case AMD_IP_BLOCK_TYPE_UVD:
 	case AMD_IP_BLOCK_TYPE_VCN:
 	case AMD_IP_BLOCK_TYPE_VCE:
+	case AMD_IP_BLOCK_TYPE_SDMA:
 		if (swsmu)
 			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
 		else
@@ -956,7 +957,6 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 		break;
 	case AMD_IP_BLOCK_TYPE_GMC:
 	case AMD_IP_BLOCK_TYPE_ACP:
-	case AMD_IP_BLOCK_TYPE_SDMA:
 		ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
 				(adev)->powerplay.pp_handle, block_type, gate));
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index bdf849da32e4..2a00a36106b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -81,9 +81,10 @@
  * - 3.32.0 - Add syncobj timeline support to AMDGPU_CS.
  * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
+ * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	34
+#define KMS_DRIVER_MINOR	35
 #define KMS_DRIVER_PATCHLEVEL	0
 
 #define AMDGPU_MAX_TIMEOUT_PARAM_LENTH	256
@@ -1012,11 +1013,16 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x731B, 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},
+	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
 
+	/* Navi12 */
+	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
+
 	{0, 0, 0}
 };
 
@@ -1042,6 +1048,41 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
+#ifdef CONFIG_DRM_AMDGPU_SI
+	if (!amdgpu_si_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_VERDE:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+			dev_info(&pdev->dev,
+				 "SI support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	if (!amdgpu_cik_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_KAVERI:
+		case CHIP_BONAIRE:
+		case CHIP_HAWAII:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+			dev_info(&pdev->dev,
+				 "CIK support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+
 	/* Get rid of things like offb */
 	ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb");
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index b174bd5eb38e..8ceb44925947 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -291,6 +291,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	uint32_t handle;
 	int r;
 
+	args->addr = untagged_addr(args->addr);
+
 	if (offset_in_page(args->addr | args->size))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 554a59b3c4a6..6ee4021910e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -165,6 +165,7 @@ struct amdgpu_gfx_config {
 	uint32_t num_sc_per_sh;
 	uint32_t num_packer_per_sc;
 	uint32_t pa_sc_tile_steering_override;
+	uint64_t tcc_disabled_mask;
 };
 
 struct amdgpu_cu_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 7850084a05e3..60655834d649 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -143,7 +143,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* ring tests don't use a job */
 	if (job) {
 		vm = job->vm;
-		fence_ctx = job->base.s_fence->scheduled.context;
+		fence_ctx = job->base.s_fence ?
+			job->base.s_fence->scheduled.context : 0;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9d76e0923a5a..96b2a31ccfed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -218,7 +218,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
 	struct amdgpu_job *job;
-	int r;
+	int r = 0;
 
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
@@ -243,6 +243,8 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	job->fence = dma_fence_get(fence);
 
 	amdgpu_job_free_resources(job);
+
+	fence = r ? ERR_PTR(r) : fence;
 	return fence;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 0e2ec608530b..d55f5baa83d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -144,41 +144,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	struct amdgpu_device *adev;
 	int r, acpi_status;
 
-#ifdef CONFIG_DRM_AMDGPU_SI
-	if (!amdgpu_si_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
-			dev_info(dev->dev,
-				 "SI support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	if (!amdgpu_cik_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
-			dev_info(dev->dev,
-				 "CIK support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-
 	adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
 	if (adev == NULL) {
 		return -ENOMEM;
@@ -677,6 +642,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
 
+		if (info->read_mmr_reg.count > 128)
+			return -EINVAL;
+
 		regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL);
 		if (!regs)
 			return -ENOMEM;
@@ -784,6 +752,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.pa_sc_tile_steering_override =
 				adev->gfx.config.pa_sc_tile_steering_override;
 
+		dev_info.tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask;
+
 		return copy_to_user(out, &dev_info,
 				    min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 1fead0e8b890..7289e1b4fb60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -453,7 +453,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 		.interruptible = (bp->type != ttm_bo_type_kernel),
 		.no_wait_gpu = false,
 		.resv = bp->resv,
-		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
+		.flags = bp->type != ttm_bo_type_kernel ?
+			TTM_OPT_FLAG_ALLOW_RES_EVICT : 0
 	};
 	struct amdgpu_bo *bo;
 	unsigned long page_align, size = bp->size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index b70b3c45bb29..65044b1b3d4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -429,13 +429,14 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
  * Open up a stream for HW test
  */
 int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+			      struct amdgpu_bo *bo,
 			      struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 1024;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -444,7 +445,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	ib = &job->ibs[0];
 
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	/* stitch together an VCE create msg */
 	ib->length_dw = 0;
@@ -476,8 +477,8 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
 	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
@@ -1110,13 +1111,20 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
 int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
 	/* skip vce ring1/2 ib test for now, since it's not reliable */
 	if (ring != &ring->adev->vce.ring[0])
 		return 0;
 
-	r = amdgpu_vce_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 512, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_vce_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
@@ -1132,5 +1140,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index 30ea54dd9117..e802f7d9db0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -59,6 +59,7 @@ int amdgpu_vce_entity_init(struct amdgpu_device *adev);
 int amdgpu_vce_suspend(struct amdgpu_device *adev);
 int amdgpu_vce_resume(struct amdgpu_device *adev);
 int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+			      struct amdgpu_bo *bo,
 			      struct dma_fence **fence);
 int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 			       bool direct, struct dma_fence **fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 7a6beb2e7c4e..3199e4a5ff12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -569,13 +569,14 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring)
 }
 
 static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
-			      struct dma_fence **fence)
+					 struct amdgpu_bo *bo,
+					 struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -583,14 +584,14 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x0000000b;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
@@ -621,13 +622,14 @@ err:
 }
 
 static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				struct dma_fence **fence)
+					  struct amdgpu_bo *bo,
+					  struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -635,14 +637,14 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 	ib->ptr[ib->length_dw++] = handle;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x0000000b;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
@@ -675,13 +677,20 @@ err:
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = amdgpu_vcn_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_vcn_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, &fence);
+	r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -693,6 +702,8 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index e2fb141ff2e5..5251352f5922 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -603,14 +603,12 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 	struct ttm_bo_global *glob = adev->mman.bdev.glob;
 	struct amdgpu_vm_bo_base *bo_base;
 
-#if 0
 	if (vm->bulk_moveable) {
 		spin_lock(&glob->lru_lock);
 		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
 		spin_unlock(&glob->lru_lock);
 		return;
 	}
-#endif
 
 	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index db28823891ac..8dfc775626a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -70,6 +70,11 @@ MODULE_FIRMWARE("amdgpu/navi10_mec.bin");
 MODULE_FIRMWARE("amdgpu/navi10_mec2.bin");
 MODULE_FIRMWARE("amdgpu/navi10_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/navi14_ce_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_pfp_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_me_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec2_wks.bin");
 MODULE_FIRMWARE("amdgpu/navi14_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi14_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi14_me.bin");
@@ -88,7 +93,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0x60000ff0, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000000, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -135,7 +140,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -174,7 +179,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -594,7 +599,8 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
-	char fw_name[30];
+	char fw_name[40];
+	char wks[10];
 	int err;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
@@ -607,12 +613,16 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 	DRM_DEBUG("\n");
 
+	memset(wks, 0, sizeof(wks));
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 		chip_name = "navi10";
 		break;
 	case CHIP_NAVI14:
 		chip_name = "navi14";
+		if (!(adev->pdev->device == 0x7340 &&
+		      adev->pdev->revision != 0x00))
+			snprintf(wks, sizeof(wks), "_wks");
 		break;
 	case CHIP_NAVI12:
 		chip_name = "navi12";
@@ -621,7 +631,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -632,7 +642,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -643,7 +653,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -708,7 +718,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	if (adev->gfx.rlc.is_rlc_v2_1)
 		gfx_v10_0_init_rlc_ext_microcode(adev);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -719,7 +729,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 	if (!err) {
 		err = amdgpu_ucode_validate(adev->gfx.mec2_fw);
@@ -1681,6 +1691,17 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
+{
+	/* TCCs are global (not instanced). */
+	uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) |
+			       RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE);
+
+	adev->gfx.config.tcc_disabled_mask =
+		REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) |
+		(REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, HI_TCC_DISABLE) << 16);
+}
+
 static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 {
 	u32 tmp;
@@ -1692,6 +1713,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 
 	gfx_v10_0_setup_rb(adev);
 	gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info);
+	gfx_v10_0_get_tcc_info(adev);
 	adev->gfx.config.pa_sc_tile_steering_override =
 		gfx_v10_0_init_pa_sc_tile_steering_override(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 83d45f98a461..dcadc73bffd2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1650,7 +1650,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
-	case CHIP_RENOIR:
 		gfx_v9_0_init_lbpw(adev);
 		break;
 	case CHIP_VEGA20:
@@ -3026,7 +3025,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
-	case CHIP_RENOIR:
 		if (amdgpu_lbpw == 0)
 			gfx_v9_0_enable_lbpw(adev, false);
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 8b789f750b72..db10640a3b2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -151,6 +151,15 @@ static void gfxhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL2, tmp);
 
 	tmp = mmGCVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL3, tmp);
 
 	tmp = mmGCVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 241a4e57cf4a..354e6200ca9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -309,6 +309,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	job->vm_pd_addr = amdgpu_gmc_pd_addr(adev->gart.bo);
 	job->vm_needs_flush = true;
+	job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop;
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 3542c203c3c8..b39bea6f54e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -137,6 +137,15 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL2, tmp);
 
 	tmp = mmMMVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL3, tmp);
 
 	tmp = mmMMVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 85393a99a848..de9b995b65b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -317,10 +317,12 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	struct smu_context *smu = &adev->smu;
 
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		amdgpu_inc_vram_lost(adev);
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		ret = smu_baco_reset(smu);
 	} else {
-		amdgpu_inc_vram_lost(adev);
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		ret = nv_asic_mode1_reset(adev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ff18b3a57892..4554e72c8378 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -254,6 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
 };
 
 static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
@@ -1889,8 +1890,9 @@ static int sdma_v4_0_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs &&
-			adev->powerplay.pp_funcs->set_powergating_by_smu)
+	if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs &&
+			adev->powerplay.pp_funcs->set_powergating_by_smu) ||
+			adev->asic_type == CHIP_RENOIR)
 		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, false);
 
 	if (!amdgpu_sriov_vf(adev))
@@ -1917,8 +1919,9 @@ static int sdma_v4_0_hw_fini(void *handle)
 	sdma_v4_0_ctx_switch_enable(adev, false);
 	sdma_v4_0_enable(adev, false);
 
-	if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs
-			&& adev->powerplay.pp_funcs->set_powergating_by_smu)
+	if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs
+			&& adev->powerplay.pp_funcs->set_powergating_by_smu) ||
+			adev->asic_type == CHIP_RENOIR)
 		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, true);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index fa2f70ce2e2b..f6e81680dd7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1129,7 +1129,7 @@ static void sdma_v5_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, addr & 0xfffffffc);
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
 	amdgpu_ring_write(ring, seq); /* reference */
-	amdgpu_ring_write(ring, 0xfffffff); /* mask */
+	amdgpu_ring_write(ring, 0xffffffff); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
index 4a5951036927..c44723c267c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
@@ -493,7 +493,15 @@ static void smu_v11_0_i2c_fini(struct i2c_adapter *control)
 	}
 
 	/* Restore clock gating */
-	smu_v11_0_i2c_set_clock_gating(control, true);
+
+	/*
+	 * TODO Reenabling clock gating seems to break subsequent SMU operation
+	 *      on the I2C bus. My guess is that SMU doesn't disable clock gating like
+	 *      we do here before working with the bus. So for now just don't restore
+	 *      it but later work with SMU to see if they have this issue and can
+	 *      update their code appropriately
+	 */
+	/* smu_v11_0_i2c_set_clock_gating(control, true); */
 
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f70658a536a9..f8ab80c8801b 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -558,12 +558,14 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	switch (soc15_asic_reset_method(adev)) {
 		case AMD_RESET_METHOD_BACO:
-			amdgpu_inc_vram_lost(adev);
+			if (!adev->in_suspend)
+				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
 			return soc15_mode2_reset(adev);
 		default:
-			amdgpu_inc_vram_lost(adev);
+			if (!adev->in_suspend)
+				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_mode1_reset(adev);
 	}
 }
@@ -771,8 +773,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
-#else
-#       warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 670784a78512..217084d56ab8 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -206,13 +206,14 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring)
  * Open up a stream for HW test
  */
 static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				       struct amdgpu_bo *bo,
 				       struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -220,15 +221,15 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00010000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -268,13 +269,14 @@ err:
  */
 static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 					uint32_t handle,
+					struct amdgpu_bo *bo,
 					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -282,15 +284,15 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00010000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -327,13 +329,20 @@ err:
 static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = uvd_v6_0_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = uvd_v6_0_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, &fence);
+	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -345,6 +354,8 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 01f658fa72c6..0995378d8263 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -214,13 +214,14 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
  * Open up a stream for HW test
  */
 static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				       struct amdgpu_bo *bo,
 				       struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -228,15 +229,15 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00000000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -275,13 +276,14 @@ err:
  * Close up a stream for HW test or if userspace failed to do so
  */
 static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				struct dma_fence **fence)
+					struct amdgpu_bo *bo,
+					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -289,15 +291,15 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handl
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00000000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002;
@@ -334,13 +336,20 @@ err:
 static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = uvd_v7_0_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, &fence);
+	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -352,6 +361,8 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index a8cf82d46109..901fe3590165 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -694,10 +694,10 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x003f8000, 0x8f6f896f,
 	0x88776f77, 0x8a6eff6e,
 	0x023f8000, 0xb9eef807,
-	0xb970f812, 0xb971f813,
-	0x8ff08870, 0xf4051bb8,
+	0xb97af812, 0xb97bf813,
+	0x8ffa887a, 0xf4051bbd,
 	0xfa000000, 0xbf8cc07f,
-	0xf4051c38, 0xfa000008,
+	0xf4051ebd, 0xfa000008,
 	0xbf8cc07f, 0x87ee6e6e,
 	0xbf840001, 0xbe80206e,
 	0xb971f803, 0x8771ff71,
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 35986219ce5f..cdaa523ce6be 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -187,12 +187,12 @@ L_FETCH_2ND_TRAP:
 	// Read second-level TBA/TMA from first-level TMA and jump if available.
 	// ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data)
 	// ttmp12 holds SQ_WAVE_STATUS
-	s_getreg_b32	ttmp4, hwreg(HW_REG_SHADER_TMA_LO)
-	s_getreg_b32	ttmp5, hwreg(HW_REG_SHADER_TMA_HI)
-	s_lshl_b64	[ttmp4, ttmp5], [ttmp4, ttmp5], 0x8
-	s_load_dwordx2	[ttmp2, ttmp3], [ttmp4, ttmp5], 0x0 glc:1		// second-level TBA
+	s_getreg_b32	ttmp14, hwreg(HW_REG_SHADER_TMA_LO)
+	s_getreg_b32	ttmp15, hwreg(HW_REG_SHADER_TMA_HI)
+	s_lshl_b64	[ttmp14, ttmp15], [ttmp14, ttmp15], 0x8
+	s_load_dwordx2	[ttmp2, ttmp3], [ttmp14, ttmp15], 0x0 glc:1		// second-level TBA
 	s_waitcnt	lgkmcnt(0)
-	s_load_dwordx2	[ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 glc:1		// second-level TMA
+	s_load_dwordx2	[ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 glc:1		// second-level TMA
 	s_waitcnt	lgkmcnt(0)
 	s_and_b64	[ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3]
 	s_cbranch_scc0	L_NO_NEXT_TRAP						// second-level trap handler not been set
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 e1b09bb432bd..a52f0b13a2c8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2113,6 +2113,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {
+	.options = BL_CORE_SUSPENDRESUME,
 	.get_brightness = amdgpu_dm_backlight_get_brightness,
 	.update_status	= amdgpu_dm_backlight_update_status,
 };
@@ -5770,8 +5771,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		 * change FB pitch, DCC state, rotation or mirroing.
 		 */
 		bundle->flip_addrs[planes_count].flip_immediate =
-			(crtc->state->pageflip_flags &
-			 DRM_MODE_PAGE_FLIP_ASYNC) != 0 &&
+			crtc->state->async_flip &&
 			acrtc_state->update_type == UPDATE_TYPE_FAST;
 
 		timestamp_ns = ktime_get_ns();
@@ -6017,7 +6017,9 @@ static void amdgpu_dm_enable_crtc_interrupts(struct drm_device *dev,
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	int i;
+#ifdef CONFIG_DEBUG_FS
 	enum amdgpu_dm_pipe_crc_source source;
+#endif
 
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
 				      new_crtc_state, i) {
@@ -6348,7 +6350,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	amdgpu_dm_enable_crtc_interrupts(dev, state, true);
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, j)
-		if (new_crtc_state->pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC)
+		if (new_crtc_state->async_flip)
 			wait_for_vblank = false;
 
 	/* update planes when needed per crtc*/
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 985633c08a26..26c6d735cdc7 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -24,15 +24,20 @@
 # It calculates Bandwidth and Watermarks values for HW programming
 #
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+calcs_ccflags := -mhard-float -msse
 
-calcs_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+calcs_ccflags += -mpreferred-stack-boundary=4
+else
 calcs_ccflags += -msse2
 endif
 
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 383f4f8db8f4..9b2cb57bf2ba 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -708,6 +708,10 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v,
 
 unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev)
 {
+	/* for dali, the highest voltage level we want is 0 */
+	if (ASICREV_IS_DALI(hw_internal_rev))
+		return 0;
+
 	/* we are ok with all levels */
 	return 4;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
index 5cc3acccda2a..b1e657e137a9 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
@@ -98,11 +98,14 @@ uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context)
 		struct dc_stream_state *stream = context->streams[j];
 		uint32_t vertical_blank_in_pixels = 0;
 		uint32_t vertical_blank_time = 0;
+		uint32_t vertical_total_min = stream->timing.v_total;
+		struct dc_crtc_timing_adjust adjust = stream->adjust;
+		if (adjust.v_total_max != adjust.v_total_min)
+			vertical_total_min = adjust.v_total_min;
 
 		vertical_blank_in_pixels = stream->timing.h_total *
-			(stream->timing.v_total
+			(vertical_total_min
 			 - stream->timing.v_addressable);
-
 		vertical_blank_time = vertical_blank_in_pixels
 			* 10000 / stream->timing.pix_clk_100hz;
 
@@ -171,6 +174,10 @@ void dce11_pplib_apply_display_requirements(
 	struct dc_state *context)
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
+	int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ;
+
+	if (dc->bw_vbios && dc->bw_vbios->memory_type == bw_def_hbm)
+		memory_type_multiplier = MEMORY_TYPE_HBM;
 
 	pp_display_cfg->all_displays_in_sync =
 		context->bw_ctx.bw.dce.all_displays_in_sync;
@@ -183,8 +190,20 @@ void dce11_pplib_apply_display_requirements(
 	pp_display_cfg->cpu_pstate_separation_time =
 			context->bw_ctx.bw.dce.blackout_recovery_time_us;
 
-	pp_display_cfg->min_memory_clock_khz = context->bw_ctx.bw.dce.yclk_khz
-		/ MEMORY_TYPE_MULTIPLIER_CZ;
+	/*
+	 * TODO: determine whether the bandwidth has reached memory's limitation
+	 * , then change minimum memory clock based on real-time bandwidth
+	 * limitation.
+	 */
+	if (ASICREV_IS_VEGA20_P(dc->ctx->asic_id.hw_internal_rev) && (context->stream_count >= 2)) {
+		pp_display_cfg->min_memory_clock_khz = max(pp_display_cfg->min_memory_clock_khz,
+							   (uint32_t) div64_s64(
+								   div64_s64(dc->bw_vbios->high_yclk.value,
+									     memory_type_multiplier), 10000));
+	} else {
+		pp_display_cfg->min_memory_clock_khz = context->bw_ctx.bw.dce.yclk_khz
+			/ memory_type_multiplier;
+	}
 
 	pp_display_cfg->min_engine_clock_khz = determine_sclk_from_bounding_box(
 			dc,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5d1adeda4d90..4b8819c27fcd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -580,6 +580,10 @@ static bool construct(struct dc *dc,
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	// Allocate memory for the vm_helper
 	dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL);
+	if (!dc->vm_helper) {
+		dm_error("%s: failed to create dc->vm_helper\n", __func__);
+		goto fail;
+	}
 
 #endif
 	memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides));
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 ca20b150afcc..9c58670d5414 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2767,6 +2767,15 @@ void core_link_enable_stream(
 					CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 					COLOR_DEPTH_UNDEFINED);
 
+		/* This second call is needed to reconfigure the DIG
+		 * as a workaround for the incorrect value being applied
+		 * from transmitter control.
+		 */
+		if (!dc_is_virtual_signal(pipe_ctx->stream->signal))
+			stream->link->link_enc->funcs->setup(
+				stream->link->link_enc,
+				pipe_ctx->stream->signal);
+
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		if (pipe_ctx->stream->timing.flags.DSC) {
 			if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
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 505967b48e14..51991bf26a93 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
@@ -374,6 +374,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
 	enum display_dongle_type *dongle = &sink_cap->dongle_type;
 	uint8_t type2_dongle_buf[DP_ADAPTOR_TYPE2_SIZE];
 	bool is_type2_dongle = false;
+	int retry_count = 2;
 	struct dp_hdmi_dongle_signature_data *dongle_signature;
 
 	/* Assume we have no valid DP passive dongle connected */
@@ -386,13 +387,24 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
 		DP_HDMI_DONGLE_ADDRESS,
 		type2_dongle_buf,
 		sizeof(type2_dongle_buf))) {
-		*dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
-		sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
+		/* Passive HDMI dongles can sometimes fail here without retrying*/
+		while (retry_count > 0) {
+			if (i2c_read(ddc,
+				DP_HDMI_DONGLE_ADDRESS,
+				type2_dongle_buf,
+				sizeof(type2_dongle_buf)))
+				break;
+			retry_count--;
+		}
+		if (retry_count == 0) {
+			*dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
+			sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
 
-		CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
-				"DP-DVI passive dongle %dMhz: ",
-				DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
-		return;
+			CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
+					"DP-DVI passive dongle %dMhz: ",
+					DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
+			return;
+		}
 	}
 
 	/* Check if Type 2 dongle.*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 8f70295179ff..f25ac17f47fa 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -404,6 +404,9 @@ bool resource_are_streams_timing_synchronizable(
 	if (stream1->view_format != stream2->view_format)
 		return false;
 
+	if (stream1->ignore_msa_timing_param || stream2->ignore_msa_timing_param)
+		return false;
+
 	return true;
 }
 static bool is_dp_and_hdmi_sharable(
@@ -1540,6 +1543,9 @@ bool dc_is_stream_unchanged(
 	if (!are_stream_backends_same(old_stream, stream))
 		return false;
 
+	if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index 1488ffddf4e3..31b698bf9cfc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -148,7 +148,7 @@ static void dce_mi_program_pte_vm(
 			pte->min_pte_before_flip_horiz_scan;
 
 	REG_UPDATE(GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT,
-			GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, 0xff);
+			GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, 0x7f);
 
 	REG_UPDATE_3(DVMM_PTE_CONTROL,
 			DVMM_PAGE_WIDTH, page_width,
@@ -157,7 +157,7 @@ static void dce_mi_program_pte_vm(
 
 	REG_UPDATE_2(DVMM_PTE_ARB_CONTROL,
 			DVMM_PTE_REQ_PER_CHUNK, pte->pte_req_per_chunk,
-			DVMM_MAX_PTE_REQ_OUTSTANDING, 0xff);
+			DVMM_MAX_PTE_REQ_OUTSTANDING, 0x7f);
 }
 
 static void program_urgency_watermark(
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index afc61055eca1..76d54885374a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -668,6 +668,7 @@ struct clock_source *dce100_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
@@ -1091,6 +1092,7 @@ struct resource_pool *dce100_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index c66fe170e1e8..89620adc81d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -714,6 +714,7 @@ struct clock_source *dce110_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
@@ -1462,6 +1463,7 @@ struct resource_pool *dce110_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool, asic_id))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 3ac4c7e73050..21a657e79306 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -687,6 +687,7 @@ struct clock_source *dce112_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
@@ -987,6 +988,10 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	struct dm_pp_clock_levels_with_latency mem_clks = {0};
 	struct dm_pp_wm_sets_with_clock_ranges clk_ranges = {0};
 	struct dm_pp_clock_levels clks = {0};
+	int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ;
+
+	if (dc->bw_vbios && dc->bw_vbios->memory_type == bw_def_hbm)
+		memory_type_multiplier = MEMORY_TYPE_HBM;
 
 	/*do system clock  TODO PPLIB: after PPLIB implement,
 	 * then remove old way
@@ -1026,12 +1031,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 				&clks);
 
 		dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[0] * MEMORY_TYPE_MULTIPLIER_CZ, 1000);
+			clks.clocks_in_khz[0] * memory_type_multiplier, 1000);
 		dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[clks.num_levels>>1] * MEMORY_TYPE_MULTIPLIER_CZ,
+			clks.clocks_in_khz[clks.num_levels>>1] * memory_type_multiplier,
 			1000);
 		dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[clks.num_levels-1] * MEMORY_TYPE_MULTIPLIER_CZ,
+			clks.clocks_in_khz[clks.num_levels-1] * memory_type_multiplier,
 			1000);
 
 		return;
@@ -1067,12 +1072,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	 * YCLK = UMACLK*m_memoryTypeMultiplier
 	 */
 	dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-		mem_clks.data[0].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, 1000);
+		mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
 	dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
 		1000);
 	dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
 		1000);
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
@@ -1338,6 +1343,7 @@ struct resource_pool *dce112_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 7d08154e9662..7c52f7f9196c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -500,6 +500,7 @@ static struct clock_source *dce120_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
@@ -847,6 +848,8 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	int i;
 	unsigned int clk;
 	unsigned int latency;
+	/*original logic in dal3*/
+	int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ;
 
 	/*do system clock*/
 	if (!dm_pp_get_clock_levels_by_type_with_latency(
@@ -905,13 +908,16 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	 * ALSO always convert UMA clock (from PPLIB)  to YCLK (HW formula):
 	 * YCLK = UMACLK*m_memoryTypeMultiplier
 	 */
+	if (dc->bw_vbios->memory_type == bw_def_hbm)
+		memory_type_multiplier = MEMORY_TYPE_HBM;
+
 	dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-		mem_clks.data[0].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, 1000);
+		mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
 	dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
 		1000);
 	dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
 		1000);
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
@@ -1203,6 +1209,7 @@ struct resource_pool *dce120_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 4625df9f9fd2..643ccb0ade00 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -701,6 +701,7 @@ struct clock_source *dce80_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 01c7e30b9ce1..bbd6e01b3eca 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -393,6 +393,10 @@ bool cm_helper_translate_curve_to_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	// All 3 color channels have same x
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
@@ -464,13 +468,6 @@ bool cm_helper_translate_curve_to_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
@@ -562,6 +559,10 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
 	corner_points[0].green.x = corner_points[0].red.x;
@@ -624,13 +625,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
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 5a89e462e7cc..1599bb971111 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -786,6 +786,7 @@ struct clock_source *dcn10_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
@@ -1570,6 +1571,7 @@ struct resource_pool *dcn10_create_resource_pool(
 	if (construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index ddb8d5649e79..63f3bddba7da 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -10,15 +10,20 @@ ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DCN20 += dcn20_dsc.o
 endif
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
+else
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
 endif
 
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 b4e3ce22ed52..dfb208285a9c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -814,7 +814,7 @@ static const struct resource_caps res_cap_nv14 = {
 		.num_audio = 6,
 		.num_stream_encoder = 5,
 		.num_pll = 5,
-		.num_dwb = 0,
+		.num_dwb = 1,
 		.num_ddc = 5,
 };
 
@@ -1077,6 +1077,7 @@ struct clock_source *dcn20_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 8cd9de8b1a7a..ff50ae71fe27 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -3,7 +3,22 @@
 
 DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
 
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
+
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
+
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
+else
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
+endif
 
 AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21))
 
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 3ca5139f1273..de182185fe1f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -23,6 +23,8 @@
  *
  */
 
+#include <linux/slab.h>
+
 #include "dm_services.h"
 #include "dc.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 5b2a65b42403..8df251626e22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -24,15 +24,20 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dml_ccflags := -mhard-float -msse
 
-dml_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dml_ccflags += -mpreferred-stack-boundary=4
+else
 dml_ccflags += -msse2
 endif
 
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 649883777f62..6c6c486b774a 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
@@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
 		if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 456cd0e3289c..3b6ed60dcd35 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -39,9 +39,6 @@
  * ways. Unless there is something clearly wrong with it the code should
  * remain as-is as it provides us with a guarantee from HW that it is correct.
  */
-
-typedef unsigned int uint;
-
 typedef struct {
 	double DPPCLK;
 	double DISPCLK;
@@ -4774,7 +4771,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0;
 				mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					uint m;
+					unsigned int m;
 
 					locals->cursor_bw[k] = 0;
 					locals->cursor_bw_pre[k] = 0;
@@ -5285,7 +5282,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 	double SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank;
 	double FullDETBufferingTimeYStutterCriticalPlane = 0;
 	double TimeToFinishSwathTransferStutterCriticalPlane = 0;
-	uint k, j;
+	unsigned int k, j;
 
 	mode_lib->vba.TotalActiveDPP = 0;
 	mode_lib->vba.TotalDCCActiveDPP = 0;
@@ -5507,7 +5504,7 @@ static void CalculateDCFCLKDeepSleep(
 		double DPPCLK[],
 		double *DCFCLKDeepSleep)
 {
-	uint k;
+	unsigned int k;
 	double DisplayPipeLineDeliveryTimeLuma;
 	double DisplayPipeLineDeliveryTimeChroma;
 	//double   DCFCLKDeepSleepPerPlane[DC__NUM_DPP__MAX];
@@ -5727,7 +5724,7 @@ static void CalculatePixelDeliveryTimes(
 		double DisplayPipeRequestDeliveryTimeChromaPrefetch[])
 {
 	double req_per_swath_ub;
-	uint k;
+	unsigned int k;
 
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
 		if (VRatio[k] <= 1) {
@@ -5869,7 +5866,7 @@ static void CalculateMetaAndPTETimes(
 	unsigned int dpte_groups_per_row_chroma_ub;
 	unsigned int num_group_per_lower_vm_stage;
 	unsigned int num_req_per_lower_vm_stage;
-	uint k;
+	unsigned int k;
 
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
 		if (GPUVMEnable == true) {
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index b456cd23c6fa..970737217e53 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -1,15 +1,20 @@
 #
 # Makefile for the 'dsc' sub-component of DAL.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dsc_ccflags := -mhard-float -msse
 
-dsc_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dsc_ccflags += -mpreferred-stack-boundary=4
+else
 dsc_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
index 34485d9de78a..8572678f8d4f 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
@@ -35,12 +35,10 @@
 
 #include "hw_factory_dcn21.h"
 
-
 #include "dcn/dcn_2_1_0_offset.h"
 #include "dcn/dcn_2_1_0_sh_mask.h"
 #include "renoir_ip_offset.h"
 
-
 #include "reg_helper.h"
 #include "../hpd_regs.h"
 /* begin *********************
@@ -136,6 +134,39 @@ static const struct ddc_sh_mask ddc_mask[] = {
 	DDC_MASK_SH_LIST_DCN2(_MASK, 6)
 };
 
+#include "../generic_regs.h"
+
+/* set field name */
+#define SF_GENERIC(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
+#define generic_regs(id) \
+{\
+	GENERIC_REG_LIST(id)\
+}
+
+static const struct generic_registers generic_regs[] = {
+	generic_regs(A),
+};
+
+static const struct generic_sh_mask generic_shift[] = {
+	GENERIC_MASK_SH_LIST(__SHIFT, A),
+};
+
+static const struct generic_sh_mask generic_mask[] = {
+	GENERIC_MASK_SH_LIST(_MASK, A),
+};
+
+static void define_generic_registers(struct hw_gpio_pin *pin, uint32_t en)
+{
+	struct hw_generic *generic = HW_GENERIC_FROM_BASE(pin);
+
+	generic->regs = &generic_regs[en];
+	generic->shifts = &generic_shift[en];
+	generic->masks = &generic_mask[en];
+	generic->base.regs = &generic_regs[en].gpio;
+}
+
 static void define_ddc_registers(
 		struct hw_gpio_pin *pin,
 		uint32_t en)
@@ -181,7 +212,8 @@ static const struct hw_factory_funcs funcs = {
 	.get_hpd_pin = dal_hw_hpd_get_pin,
 	.get_generic_pin = dal_hw_generic_get_pin,
 	.define_hpd_registers = define_hpd_registers,
-	.define_ddc_registers = define_ddc_registers
+	.define_ddc_registers = define_ddc_registers,
+	.define_generic_registers = define_generic_registers
 };
 /*
  * dal_hw_factory_dcn10_init
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
index ad7c43746291..fbb58fb8c318 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
@@ -58,7 +58,6 @@
 #define SF_HPD(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
-
 /* macros to expend register list macro defined in HW object header file
  * end *********************/
 
@@ -71,7 +70,7 @@ static bool offset_to_id(
 {
 	switch (offset) {
 	/* GENERIC */
-	case REG(DC_GENERICA):
+	case REG(DC_GPIO_GENERIC_A):
 		*id = GPIO_ID_GENERIC;
 		switch (mask) {
 		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICA_A_MASK:
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 1cc1c8ce633b..bef224bf803e 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -31,6 +31,8 @@
 #include "dm_pp_smu.h"
 
 #define MEMORY_TYPE_MULTIPLIER_CZ 4
+#define MEMORY_TYPE_HBM 2
+
 
 enum dce_version resource_parse_asic_id(
 		struct hw_asic_id asic_id);
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 1f16892f0add..1be6c44fd32f 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -137,10 +137,13 @@
 #define RAVEN1_F0 0xF0
 #define RAVEN_UNKNOWN 0xFF
 
+#define PICASSO_15D8_REV_E3 0xE3
+#define PICASSO_15D8_REV_E4 0xE4
+
 #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
 #define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
-
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < PICASSO_15D8_REV_E3))
+#define ASICREV_IS_DALI(eChipRev) ((eChipRev >= PICASSO_15D8_REV_E3) && (eChipRev < RAVEN1_F0))
 
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
 
diff --git a/drivers/gpu/drm/amd/include/renoir_ip_offset.h b/drivers/gpu/drm/amd/include/renoir_ip_offset.h
index 554714c8e000..094648cac392 100644
--- a/drivers/gpu/drm/amd/include/renoir_ip_offset.h
+++ b/drivers/gpu/drm/amd/include/renoir_ip_offset.h
@@ -155,7 +155,7 @@ static const struct IP_BASE MP0_BASE ={ { { { 0x00016000, 0x0243FC00, 0x00DC0000
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } } } };
-static const struct IP_BASE MP1_BASE ={ { { { 0x00016200, 0x02400400, 0x00E80000, 0x00EC0000, 0x00F00000 } },
+static const struct IP_BASE MP1_BASE ={ { { { 0x00016000, 0x02400400, 0x00E80000, 0x00EC0000, 0x00F00000 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index fa636cb462c1..fa8ad7db2b3a 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -1531,6 +1531,7 @@ static int pp_asic_reset_mode_2(void *handle)
 static int pp_smu_i2c_bus_access(void *handle, bool acquire)
 {
 	struct pp_hwmgr *hwmgr = handle;
+	int ret = 0;
 
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
@@ -1540,7 +1541,11 @@ static int pp_smu_i2c_bus_access(void *handle, bool acquire)
 		return -EINVAL;
 	}
 
-	return hwmgr->hwmgr_func->smu_i2c_bus_access(hwmgr, acquire);
+	mutex_lock(&hwmgr->smu_lock);
+	ret = hwmgr->hwmgr_func->smu_i2c_bus_access(hwmgr, acquire);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return ret;
 }
 
 static const struct amd_pm_funcs pp_dpm_funcs = {
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 22f3c60d380f..4acf139ea014 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -354,6 +354,9 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 	case AMD_IP_BLOCK_TYPE_GFX:
 		ret = smu_gfx_off_control(smu, gate);
 		break;
+	case AMD_IP_BLOCK_TYPE_SDMA:
+		ret = smu_powergate_sdma(smu, gate);
+		break;
 	default:
 		break;
 	}
@@ -840,6 +843,8 @@ static int smu_sw_init(void *handle)
 	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 
+	mutex_init(&smu->sensor_lock);
+
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index f1f072012fac..d493a3f8c07a 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	if (!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d08493b67b67..beacfffbdc3e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -5098,9 +5098,7 @@ static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
 
 	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
 		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
-		for (i = 0; i < podn_vdd_dep->count - 1; i++)
-			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
-		if (od_vddc_lookup_table->entries[i].us_vdd < podn_vdd_dep->entries[i].vddc)
+		for (i = 0; i < podn_vdd_dep->count; i++)
 			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
 	} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
 		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 6109815a0401..23171a4d9a31 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -344,6 +344,7 @@ struct smu_context
 	const struct smu_funcs		*funcs;
 	const struct pptable_funcs	*ppt_funcs;
 	struct mutex			mutex;
+	struct mutex			sensor_lock;
 	uint64_t pool_size;
 
 	struct smu_table_context	smu_table;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 12c0e469bf35..0b461404af6b 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -547,7 +547,7 @@ static int navi10_get_metrics_table(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
-	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
+	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) {
@@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 	if(!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 2a6da546fb55..e62bfba51562 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -177,12 +177,82 @@ static int renoir_get_dpm_uclk_limited(struct smu_context *smu, uint32_t *clock,
 
 }
 
+static int renoir_print_clk_levels(struct smu_context *smu,
+			enum smu_clk_type clk_type, char *buf)
+{
+	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};
+
+	if (!clk_table || clk_type >= SMU_CLK_COUNT)
+		return -EINVAL;
+
+	ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
+			       (void *)&metrics, false);
+	if (ret)
+		return ret;
+
+	switch (clk_type) {
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		/* retirve table returned paramters unit is MHz */
+		cur_value = metrics.ClockFrequency[CLOCK_GFXCLK];
+		ret = smu_get_dpm_freq_range(smu, SMU_GFXCLK, &min, &max);
+		if (!ret) {
+			/* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */
+			if (cur_value  == max)
+				i = 2;
+			else if (cur_value == min)
+				i = 0;
+			else
+				i = 1;
+
+			size += sprintf(buf + size, "0: %uMhz %s\n", min,
+					i == 0 ? "*" : "");
+			size += sprintf(buf + size, "1: %uMhz %s\n",
+					i == 1 ? cur_value : RENOIR_UMD_PSTATE_GFXCLK,
+					i == 1 ? "*" : "");
+			size += sprintf(buf + size, "2: %uMhz %s\n", max,
+					i == 2 ? "*" : "");
+		}
+		return size;
+	case SMU_SOCCLK:
+		count = NUM_SOCCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_SOCCLK];
+		break;
+	case SMU_MCLK:
+		count = NUM_MEMCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_UMCCLK];
+		break;
+	case SMU_DCEFCLK:
+		count = NUM_DCFCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_DCFCLK];
+		break;
+	case SMU_FCLK:
+		count = NUM_FCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_FCLK];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 0; i < count; i++) {
+		GET_DPM_CUR_FREQ(clk_table, clk_type, i, value);
+		size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+				cur_value == value ? "*" : "");
+	}
+
+	return size;
+}
+
 static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_smu_msg_index = renoir_get_smu_msg_index,
 	.get_smu_table_index = renoir_get_smu_table_index,
 	.tables_init = renoir_tables_init,
 	.set_power_state = NULL,
 	.get_dpm_uclk_limited = renoir_get_dpm_uclk_limited,
+	.print_clk_levels = renoir_print_clk_levels,
 };
 
 void renoir_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
index e9b7237c0f7f..2a390ddd37dd 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
@@ -25,4 +25,29 @@
 
 extern void renoir_set_ppt_funcs(struct smu_context *smu);
 
+/* UMD PState Renoir Msg Parameters in MHz */
+#define RENOIR_UMD_PSTATE_GFXCLK       700
+#define RENOIR_UMD_PSTATE_SOCCLK       678
+#define RENOIR_UMD_PSTATE_FCLK         800
+
+#define GET_DPM_CUR_FREQ(table, clk_type, dpm_level, freq)		\
+	do {								\
+		switch (clk_type) {					\
+		case SMU_SOCCLK:					\
+			freq = table->SocClocks[dpm_level].Freq;	\
+			break;						\
+		case SMU_MCLK:						\
+			freq = table->MemClocks[dpm_level].Freq;	\
+			break;						\
+		case SMU_DCEFCLK:					\
+			freq = table->DcfClocks[dpm_level].Freq;	\
+			break;						\
+		case SMU_FCLK:						\
+			freq = table->FClocks[dpm_level].Freq;		\
+			break;						\
+		default:						\
+			break;						\
+		}							\
+	} while (0)
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index dc754447f0dd..23c12018dbc1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -655,7 +655,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage =
-				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 7c960b07746f..ae18fbcb26fb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -456,7 +456,7 @@ static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
-					data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+					data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 64386ee3f878..bbd8ebd58434 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 	if(!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index 8820ce15ce37..ae274902ff92 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -82,7 +82,8 @@ static void komeda_kms_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_disables(dev, old_state);
 
-	drm_atomic_helper_commit_planes(dev, old_state, 0);
+	drm_atomic_helper_commit_planes(dev, old_state,
+					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index ea26bc9c2d00..b848270e0a1f 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -564,8 +564,8 @@ komeda_splitter_validate(struct komeda_splitter *splitter,
 	}
 
 	if (!in_range(&splitter->vsize, dflow->in_h)) {
-		DRM_DEBUG_ATOMIC("split in_in: %d exceed the acceptable range.\n",
-				 dflow->in_w);
+		DRM_DEBUG_ATOMIC("split in_h: %d exceeds the acceptable range.\n",
+				 dflow->in_h);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index 2851cac94d86..b72840c06ab7 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -43,9 +43,8 @@ komeda_wb_encoder_atomic_check(struct drm_encoder *encoder,
 	struct komeda_data_flow_cfg dflow;
 	int err;
 
-	if (!writeback_job || !writeback_job->fb) {
+	if (!writeback_job)
 		return 0;
-	}
 
 	if (!crtc_st->active) {
 		DRM_DEBUG_ATOMIC("Cannot write the composition result out on a inactive CRTC.\n");
@@ -166,8 +165,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms,
 					   &komeda_wb_encoder_helper_funcs,
 					   formats, n_formats);
 	komeda_put_fourcc_list(formats);
-	if (err)
+	if (err) {
+		kfree(kwb_conn);
 		return err;
+	}
 
 	drm_connector_helper_add(&wb_conn->base, &komeda_wb_conn_helper_funcs);
 
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 22c0847986df..875a3a9eabfa 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -131,7 +131,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
 	struct drm_framebuffer *fb;
 	int i, n_planes;
 
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	fb = conn_state->writeback_job->fb;
@@ -248,7 +248,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm,
 
 	mw_state = to_mw_state(conn_state);
 
-	if (conn_state->writeback_job && conn_state->writeback_job->fb) {
+	if (conn_state->writeback_job) {
 		struct drm_framebuffer *fb = conn_state->writeback_job->fb;
 
 		DRM_DEV_DEBUG_DRIVER(drm->dev,
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 98bccace8c1c..9e13e466e72c 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -874,6 +874,9 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge)
 				 &adv7511_connector_helper_funcs);
 	drm_connector_attach_encoder(&adv->connector, bridge->encoder);
 
+	if (adv->type == ADV7533)
+		ret = adv7533_attach_dsi(adv);
+
 	if (adv->i2c_main->irq)
 		regmap_write(adv->regmap, ADV7511_REG_INT_ENABLE(0),
 			     ADV7511_INT0_HPD);
@@ -978,10 +981,10 @@ static int adv7511_init_cec_regmap(struct adv7511 *adv)
 {
 	int ret;
 
-	adv->i2c_cec = i2c_new_secondary_device(adv->i2c_main, "cec",
+	adv->i2c_cec = i2c_new_ancillary_device(adv->i2c_main, "cec",
 						ADV7511_CEC_I2C_ADDR_DEFAULT);
-	if (!adv->i2c_cec)
-		return -EINVAL;
+	if (IS_ERR(adv->i2c_cec))
+		return PTR_ERR(adv->i2c_cec);
 	i2c_set_clientdata(adv->i2c_cec, adv);
 
 	adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec,
@@ -1162,20 +1165,20 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 
 	adv7511_packet_disable(adv7511, 0xffff);
 
-	adv7511->i2c_edid = i2c_new_secondary_device(i2c, "edid",
+	adv7511->i2c_edid = i2c_new_ancillary_device(i2c, "edid",
 					ADV7511_EDID_I2C_ADDR_DEFAULT);
-	if (!adv7511->i2c_edid) {
-		ret = -EINVAL;
+	if (IS_ERR(adv7511->i2c_edid)) {
+		ret = PTR_ERR(adv7511->i2c_edid);
 		goto uninit_regulators;
 	}
 
 	regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR,
 		     adv7511->i2c_edid->addr << 1);
 
-	adv7511->i2c_packet = i2c_new_secondary_device(i2c, "packet",
+	adv7511->i2c_packet = i2c_new_ancillary_device(i2c, "packet",
 					ADV7511_PACKET_I2C_ADDR_DEFAULT);
-	if (!adv7511->i2c_packet) {
-		ret = -EINVAL;
+	if (IS_ERR(adv7511->i2c_packet)) {
+		ret = PTR_ERR(adv7511->i2c_packet);
 		goto err_i2c_unregister_edid;
 	}
 
@@ -1219,17 +1222,8 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	drm_bridge_add(&adv7511->bridge);
 
 	adv7511_audio_init(dev, adv7511);
-
-	if (adv7511->type == ADV7533) {
-		ret = adv7533_attach_dsi(adv7511);
-		if (ret)
-			goto err_remove_bridge;
-	}
-
 	return 0;
 
-err_remove_bridge:
-	drm_bridge_remove(&adv7511->bridge);
 err_unregister_cec:
 	i2c_unregister_device(adv7511->i2c_cec);
 	if (adv7511->cec_clk)
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index cebc8e620820..8a8d605021f0 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -728,6 +728,8 @@ static int tc_set_video_mode(struct tc_data *tc,
 	int lower_margin = mode->vsync_start - mode->vdisplay;
 	int vsync_len = mode->vsync_end - mode->vsync_start;
 	u32 dp0_syncval;
+	u32 bits_per_pixel = 24;
+	u32 in_bw, out_bw;
 
 	/*
 	 * Recommended maximum number of symbols transferred in a transfer unit:
@@ -735,7 +737,10 @@ static int tc_set_video_mode(struct tc_data *tc,
 	 *              (output active video bandwidth in bytes))
 	 * Must be less than tu_size.
 	 */
-	max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
+
+	in_bw = mode->clock * bits_per_pixel / 8;
+	out_bw = tc->link.base.num_lanes * tc->link.base.rate;
+	max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw);
 
 	dev_dbg(tc->dev, "set mode %dx%d\n",
 		mode->hdisplay, mode->vdisplay);
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 419381abbdd1..14aeaf736321 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -430,10 +430,15 @@ static int drm_atomic_connector_check(struct drm_connector *connector,
 		return -EINVAL;
 	}
 
-	if (writeback_job->out_fence && !writeback_job->fb) {
-		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
-				 connector->base.id, connector->name);
-		return -EINVAL;
+	if (!writeback_job->fb) {
+		if (writeback_job->out_fence) {
+			DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
+					 connector->base.id, connector->name);
+			return -EINVAL;
+		}
+
+		drm_writeback_cleanup_job(writeback_job);
+		state->writeback_job = NULL;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index aa16ea17ff9b..3ef2ac52ce94 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/dma-fence.h>
+#include <linux/ktime.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -1580,9 +1581,23 @@ static void commit_tail(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
 	const struct drm_mode_config_helper_funcs *funcs;
+	ktime_t start;
+	s64 commit_time_ms;
 
 	funcs = dev->mode_config.helper_private;
 
+	/*
+	 * We're measuring the _entire_ commit, so the time will vary depending
+	 * on how many fences and objects are involved. For the purposes of self
+	 * refresh, this is desirable since it'll give us an idea of how
+	 * congested things are. This will inform our decision on how often we
+	 * should enter self refresh after idle.
+	 *
+	 * These times will be averaged out in the self refresh helpers to avoid
+	 * overreacting over one outlier frame
+	 */
+	start = ktime_get();
+
 	drm_atomic_helper_wait_for_fences(dev, old_state, false);
 
 	drm_atomic_helper_wait_for_dependencies(old_state);
@@ -1592,6 +1607,11 @@ static void commit_tail(struct drm_atomic_state *old_state)
 	else
 		drm_atomic_helper_commit_tail(old_state);
 
+	commit_time_ms = ktime_ms_delta(ktime_get(), start);
+	if (commit_time_ms > 0)
+		drm_self_refresh_helper_update_avg_times(old_state,
+						 (unsigned long)commit_time_ms);
+
 	drm_atomic_helper_commit_cleanup_done(old_state);
 
 	drm_atomic_state_put(old_state);
@@ -3275,7 +3295,7 @@ static int page_flip_common(struct drm_atomic_state *state,
 		return PTR_ERR(crtc_state);
 
 	crtc_state->event = event;
-	crtc_state->pageflip_flags = flags;
+	crtc_state->async_flip = flags & DRM_MODE_PAGE_FLIP_ASYNC;
 
 	plane_state = drm_atomic_get_plane_state(state, plane);
 	if (IS_ERR(plane_state))
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index 46dc264a248b..d0a937fb0c56 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -128,7 +128,7 @@ void __drm_atomic_helper_crtc_duplicate_state(struct drm_crtc *crtc,
 	state->zpos_changed = false;
 	state->commit = NULL;
 	state->event = NULL;
-	state->pageflip_flags = 0;
+	state->async_flip = false;
 
 	/* Self refresh should be canceled when a new update is available */
 	state->active = drm_atomic_crtc_effectively_active(state);
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 5a5b42db6f2a..7a26bfb5329c 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -1305,8 +1305,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	if (arg->reserved)
 		return -EINVAL;
 
-	if ((arg->flags & DRM_MODE_PAGE_FLIP_ASYNC) &&
-			!dev->mode_config.async_page_flip)
+	if (arg->flags & DRM_MODE_PAGE_FLIP_ASYNC)
 		return -EINVAL;
 
 	/* can't test and expect an event at the same time. */
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index c456c3d3def2..769feefeeeef 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -976,14 +976,14 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto err_minors;
 
+	dev->registered = true;
+
 	if (dev->driver->load) {
 		ret = dev->driver->load(dev, flags);
 		if (ret)
 			goto err_minors;
 	}
 
-	dev->registered = true;
-
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_modeset_register_all(dev);
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 82a4ceed3fcf..6b0177112e18 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -159,6 +159,9 @@ static const struct edid_quirk {
 	/* Medion MD 30217 PG */
 	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
 
+	/* Lenovo G50 */
+	{ "SDC", 18514, EDID_QUIRK_FORCE_6BPC },
+
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
 
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index f675a3bb2c88..fcd728d7cf72 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -336,7 +336,12 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 	case DRM_CLIENT_CAP_ATOMIC:
 		if (!drm_core_check_feature(dev, DRIVER_ATOMIC))
 			return -EOPNOTSUPP;
-		if (req->value > 1)
+		/* The modesetting DDX has a totally broken idea of atomic. */
+		if (current->comm[0] == 'X' && req->value == 1) {
+			pr_info("broken atomic modeset userspace detected, disabling atomic\n");
+			return -EOPNOTSUPP;
+		}
+		if (req->value > 2)
 			return -EINVAL;
 		file_priv->atomic = req->value;
 		file_priv->universal_planes = req->value;
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index c355ba8e6d5d..6a23e36ed4fe 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -42,7 +42,7 @@ int __drm_mode_object_add(struct drm_device *dev, struct drm_mode_object *obj,
 {
 	int ret;
 
-	WARN_ON(dev->registered && !obj_free_cb);
+	WARN_ON(!dev->driver->load && dev->registered && !obj_free_cb);
 
 	mutex_lock(&dev->mode_config.idr_mutex);
 	ret = idr_alloc(&dev->mode_config.object_idr, register_obj ? obj : NULL,
@@ -104,7 +104,7 @@ void drm_mode_object_register(struct drm_device *dev,
 void drm_mode_object_unregister(struct drm_device *dev,
 				struct drm_mode_object *object)
 {
-	WARN_ON(dev->registered && !object->free_cb);
+	WARN_ON(!dev->driver->load && dev->registered && !object->free_cb);
 
 	mutex_lock(&dev->mode_config.idr_mutex);
 	if (object->id) {
diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c
index 4b9424a8f1f1..68f4765a5896 100644
--- a/drivers/gpu/drm/drm_self_refresh_helper.c
+++ b/drivers/gpu/drm/drm_self_refresh_helper.c
@@ -5,6 +5,7 @@
  * Authors:
  * Sean Paul <seanpaul@chromium.org>
  */
+#include <linux/average.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
@@ -50,11 +51,17 @@
  * atomic_check when &drm_crtc_state.self_refresh_active is true.
  */
 
+#define SELF_REFRESH_AVG_SEED_MS 200
+
+DECLARE_EWMA(psr_time, 4, 4)
+
 struct drm_self_refresh_data {
 	struct drm_crtc *crtc;
 	struct delayed_work entry_work;
-	struct drm_atomic_state *save_state;
-	unsigned int entry_delay_ms;
+
+	struct mutex avg_mutex;
+	struct ewma_psr_time entry_avg_ms;
+	struct ewma_psr_time exit_avg_ms;
 };
 
 static void drm_self_refresh_helper_entry_work(struct work_struct *work)
@@ -123,6 +130,44 @@ out_drop_locks:
 }
 
 /**
+ * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages
+ * @state: the state which has just been applied to hardware
+ * @commit_time_ms: the amount of time in ms that this commit took to complete
+ *
+ * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will
+ * update the average entry/exit self refresh times on self refresh transitions.
+ * These averages will be used when calculating how long to delay before
+ * entering self refresh mode after activity.
+ */
+void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
+					      unsigned int commit_time_ms)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	int i;
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
+				      new_crtc_state, i) {
+		struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;
+		struct ewma_psr_time *time;
+
+		if (old_crtc_state->self_refresh_active ==
+		    new_crtc_state->self_refresh_active)
+			continue;
+
+		if (new_crtc_state->self_refresh_active)
+			time = &sr_data->entry_avg_ms;
+		else
+			time = &sr_data->exit_avg_ms;
+
+		mutex_lock(&sr_data->avg_mutex);
+		ewma_psr_time_add(time, commit_time_ms);
+		mutex_unlock(&sr_data->avg_mutex);
+	}
+}
+EXPORT_SYMBOL(drm_self_refresh_helper_update_avg_times);
+
+/**
  * drm_self_refresh_helper_alter_state - Alters the atomic state for SR exit
  * @state: the state currently being checked
  *
@@ -153,6 +198,7 @@ void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state)
 
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		struct drm_self_refresh_data *sr_data;
+		unsigned int delay;
 
 		/* Don't trigger the entry timer when we're already in SR */
 		if (crtc_state->self_refresh_active)
@@ -162,8 +208,13 @@ void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state)
 		if (!sr_data)
 			continue;
 
+		mutex_lock(&sr_data->avg_mutex);
+		delay = (ewma_psr_time_read(&sr_data->entry_avg_ms) +
+			 ewma_psr_time_read(&sr_data->exit_avg_ms)) * 2;
+		mutex_unlock(&sr_data->avg_mutex);
+
 		mod_delayed_work(system_wq, &sr_data->entry_work,
-				 msecs_to_jiffies(sr_data->entry_delay_ms));
+				 msecs_to_jiffies(delay));
 	}
 }
 EXPORT_SYMBOL(drm_self_refresh_helper_alter_state);
@@ -171,12 +222,10 @@ EXPORT_SYMBOL(drm_self_refresh_helper_alter_state);
 /**
  * drm_self_refresh_helper_init - Initializes self refresh helpers for a crtc
  * @crtc: the crtc which supports self refresh supported displays
- * @entry_delay_ms: amount of inactivity to wait before entering self refresh
  *
  * Returns zero if successful or -errno on failure
  */
-int drm_self_refresh_helper_init(struct drm_crtc *crtc,
-				 unsigned int entry_delay_ms)
+int drm_self_refresh_helper_init(struct drm_crtc *crtc)
 {
 	struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;
 
@@ -190,8 +239,18 @@ int drm_self_refresh_helper_init(struct drm_crtc *crtc,
 
 	INIT_DELAYED_WORK(&sr_data->entry_work,
 			  drm_self_refresh_helper_entry_work);
-	sr_data->entry_delay_ms = entry_delay_ms;
 	sr_data->crtc = crtc;
+	mutex_init(&sr_data->avg_mutex);
+	ewma_psr_time_init(&sr_data->entry_avg_ms);
+	ewma_psr_time_init(&sr_data->exit_avg_ms);
+
+	/*
+	 * Seed the averages so they're non-zero (and sufficiently large
+	 * for even poorly performing panels). As time goes on, this will be
+	 * averaged out and the values will trend to their true value.
+	 */
+	ewma_psr_time_add(&sr_data->entry_avg_ms, SELF_REFRESH_AVG_SEED_MS);
+	ewma_psr_time_add(&sr_data->exit_avg_ms, SELF_REFRESH_AVG_SEED_MS);
 
 	crtc->self_refresh_data = sr_data;
 	return 0;
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index ff138b6ec48b..43d9e3bb3a94 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -324,6 +324,9 @@ void drm_writeback_cleanup_job(struct drm_writeback_job *job)
 	if (job->fb)
 		drm_framebuffer_put(job->fb);
 
+	if (job->out_fence)
+		dma_fence_put(job->out_fence);
+
 	kfree(job);
 }
 EXPORT_SYMBOL(drm_writeback_cleanup_job);
@@ -366,25 +369,29 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
 {
 	unsigned long flags;
 	struct drm_writeback_job *job;
+	struct dma_fence *out_fence;
 
 	spin_lock_irqsave(&wb_connector->job_lock, flags);
 	job = list_first_entry_or_null(&wb_connector->job_queue,
 				       struct drm_writeback_job,
 				       list_entry);
-	if (job) {
+	if (job)
 		list_del(&job->list_entry);
-		if (job->out_fence) {
-			if (status)
-				dma_fence_set_error(job->out_fence, status);
-			dma_fence_signal(job->out_fence);
-			dma_fence_put(job->out_fence);
-		}
-	}
+
 	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
 
 	if (WARN_ON(!job))
 		return;
 
+	out_fence = job->out_fence;
+	if (out_fence) {
+		if (status)
+			dma_fence_set_error(out_fence, status);
+		dma_fence_signal(out_fence);
+		dma_fence_put(out_fence);
+		job->out_fence = NULL;
+	}
+
 	INIT_WORK(&job->cleanup_work, cleanup_work);
 	queue_work(system_long_wq, &job->cleanup_work);
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
index 698db540972c..648cf0207309 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
@@ -180,6 +180,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
 			      etnaviv_cmdbuf_get_va(&submit->cmdbuf,
 					&gpu->mmu_context->cmdbuf_mapping));
 
+	mutex_unlock(&gpu->mmu_context->lock);
+
 	/* Reserve space for the bomap */
 	if (n_bomap_pages) {
 		bomap_start = bomap = iter.data;
@@ -221,8 +223,6 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
 					 obj->base.size);
 	}
 
-	mutex_unlock(&gpu->mmu_context->lock);
-
 	etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data);
 
 	dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 043111a1d60c..f8bf488e9d71 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -155,9 +155,11 @@ static void etnaviv_iommuv2_dump(struct etnaviv_iommu_context *context, void *bu
 
 	memcpy(buf, v2_context->mtlb_cpu, SZ_4K);
 	buf += SZ_4K;
-	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++, buf += SZ_4K)
-		if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT)
+	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++)
+		if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT) {
 			memcpy(buf, v2_context->stlb_cpu[i], SZ_4K);
+			buf += SZ_4K;
+		}
 }
 
 static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 35ebae6a1be7..3607d348c298 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -328,12 +328,23 @@ etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
 
 	ret = etnaviv_cmdbuf_suballoc_map(suballoc, ctx, &ctx->cmdbuf_mapping,
 					  global->memory_base);
-	if (ret) {
-		global->ops->free(ctx);
-		return NULL;
+	if (ret)
+		goto out_free;
+
+	if (global->version == ETNAVIV_IOMMU_V1 &&
+	    ctx->cmdbuf_mapping.iova > 0x80000000) {
+		dev_err(global->dev,
+		        "command buffer outside valid memory window\n");
+		goto out_unmap;
 	}
 
 	return ctx;
+
+out_unmap:
+	etnaviv_cmdbuf_suballoc_unmap(ctx, &ctx->cmdbuf_mapping);
+out_free:
+	global->ops->free(ctx);
+	return NULL;
 }
 
 void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index efb39f350b19..3250c1b8dcca 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
 			      "disabling port %c DVI/HDMI support\n",
 			      port_name(port), info->alternate_ddc_pin,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedly sharing the
@@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same ddc bin and
 		 * system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dvi = false;
 		info->supports_hdmi = false;
 		info->alternate_ddc_pin = 0;
@@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
 			      "disabling port %c DP support\n",
 			      port_name(port), info->alternate_aux_channel,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedlt sharing the
@@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same aux channel
 		 * and system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dp = false;
 		info->alternate_aux_channel = 0;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b51d1ceb8739..dfff6f4357b8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3280,7 +3280,20 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
 	switch (fb->modifier) {
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
-		return 4096;
+		/*
+		 * Validated limit is 4k, but has 5k should
+		 * work apart from the following features:
+		 * - Ytile (already limited to 4k)
+		 * - FP16 (already limited to 4k)
+		 * - render compression (already limited to 4k)
+		 * - KVMR sprite and cursor (don't care)
+		 * - horizontal panning (TODO verify this)
+		 * - pipe and plane scaling (TODO verify this)
+		 */
+		if (cpp == 8)
+			return 4096;
+		else
+			return 5120;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 		/* FIXME AUX plane? */
@@ -7261,7 +7274,7 @@ retry:
 	pipe_config->fdi_lanes = lane;
 
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
-			       link_bw, &pipe_config->fdi_m_n, false);
+			       link_bw, &pipe_config->fdi_m_n, false, false);
 
 	ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
@@ -7508,11 +7521,15 @@ void
 intel_link_compute_m_n(u16 bits_per_pixel, int nlanes,
 		       int pixel_clock, int link_clock,
 		       struct intel_link_m_n *m_n,
-		       bool constant_n)
+		       bool constant_n, bool fec_enable)
 {
-	m_n->tu = 64;
+	u32 data_clock = bits_per_pixel * pixel_clock;
+
+	if (fec_enable)
+		data_clock = intel_dp_mode_to_fec_clock(data_clock);
 
-	compute_m_n(bits_per_pixel * pixel_clock,
+	m_n->tu = 64;
+	compute_m_n(data_clock,
 		    link_clock * nlanes * 8,
 		    &m_n->gmch_m, &m_n->gmch_n,
 		    constant_n);
@@ -9298,7 +9315,6 @@ static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv,
 static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_encoder *encoder;
-	bool pch_ssc_in_use = false;
 	bool has_fdi = false;
 
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
@@ -9326,22 +9342,24 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 	 * clock hierarchy. That would also allow us to do
 	 * clock bending finally.
 	 */
+	dev_priv->pch_ssc_use = 0;
+
 	if (spll_uses_pch_ssc(dev_priv)) {
 		DRM_DEBUG_KMS("SPLL using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL);
 	}
 
 	if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) {
 		DRM_DEBUG_KMS("WRPLL1 using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1);
 	}
 
 	if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) {
 		DRM_DEBUG_KMS("WRPLL2 using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2);
 	}
 
-	if (pch_ssc_in_use)
+	if (dev_priv->pch_ssc_use)
 		return;
 
 	if (has_fdi) {
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index e57e6969051d..01fa87ad3270 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -414,7 +414,7 @@ enum phy_fia {
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
-			    bool constant_n);
+			    bool constant_n, bool fec_enable);
 bool is_ccs_modifier(u64 modifier);
 void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 921ad0a2f7ba..57e9f0ba331b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -78,8 +78,8 @@
 #define DP_DSC_MAX_ENC_THROUGHPUT_0		340000
 #define DP_DSC_MAX_ENC_THROUGHPUT_1		400000
 
-/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */
-#define DP_DSC_FEC_OVERHEAD_FACTOR		976
+/* DP DSC FEC Overhead factor = 1/(0.972261) */
+#define DP_DSC_FEC_OVERHEAD_FACTOR		972261
 
 /* Compliance test status bits  */
 #define INTEL_DP_RESOLUTION_SHIFT_MASK	0
@@ -494,6 +494,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 	return 0;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock)
+{
+	return div_u64(mul_u32_u32(mode_clock, 1000000U),
+		       DP_DSC_FEC_OVERHEAD_FACTOR);
+}
+
+static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
+				       u32 mode_clock, u32 mode_hdisplay)
+{
+	u32 bits_per_pixel, max_bpp_small_joiner_ram;
+	int i;
+
+	/*
+	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
+	 * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP)
+	 * for SST -> TimeSlotsPerMTP is 1,
+	 * for MST -> TimeSlotsPerMTP has to be calculated
+	 */
+	bits_per_pixel = (link_clock * lane_count * 8) /
+			 intel_dp_mode_to_fec_clock(mode_clock);
+	DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel);
+
+	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
+	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay;
+	DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram);
+
+	/*
+	 * Greatest allowed DSC BPP = MIN (output BPP from available Link BW
+	 * check, output bpp from small joiner RAM check)
+	 */
+	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
+
+	/* Error out if the max bpp is less than smallest allowed valid bpp */
+	if (bits_per_pixel < valid_dsc_bpp[0]) {
+		DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n",
+			      bits_per_pixel, valid_dsc_bpp[0]);
+		return 0;
+	}
+
+	/* Find the nearest match in the array of known BPPs from VESA */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
+		if (bits_per_pixel < valid_dsc_bpp[i + 1])
+			break;
+	}
+	bits_per_pixel = valid_dsc_bpp[i];
+
+	/*
+	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
+	 * fractional part is 0
+	 */
+	return bits_per_pixel << 4;
+}
+
+static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
+				       int mode_clock, int mode_hdisplay)
+{
+	u8 min_slice_count, i;
+	int max_slice_width;
+
+	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_0);
+	else
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_1);
+
+	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
+	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
+		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
+			      max_slice_width);
+		return 0;
+	}
+	/* Also take into account max slice width */
+	min_slice_count = min_t(u8, min_slice_count,
+				DIV_ROUND_UP(mode_hdisplay,
+					     max_slice_width));
+
+	/* Find the closest match to the valid slice count values */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
+		if (valid_dsc_slicecount[i] >
+		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
+						    false))
+			break;
+		if (min_slice_count  <= valid_dsc_slicecount[i])
+			return valid_dsc_slicecount[i];
+	}
+
+	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
+	return 0;
+}
+
 static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
@@ -2226,7 +2317,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       pipe_config->port_clock,
 			       &pipe_config->dp_m_n,
-			       constant_n);
+			       constant_n, pipe_config->fec_enable);
 
 	if (intel_connector->panel.downclock_mode != NULL &&
 		dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
@@ -2236,7 +2327,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 					       intel_connector->panel.downclock_mode->clock,
 					       pipe_config->port_clock,
 					       &pipe_config->dp_m2_n2,
-					       constant_n);
+					       constant_n, pipe_config->fec_enable);
 	}
 
 	if (!HAS_DDI(dev_priv))
@@ -4323,91 +4414,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 		DP_DPRX_ESI_LEN;
 }
 
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay)
-{
-	u16 bits_per_pixel, max_bpp_small_joiner_ram;
-	int i;
-
-	/*
-	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
-	 * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP)
-	 * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1,
-	 * for MST -> TimeSlotsPerMTP has to be calculated
-	 */
-	bits_per_pixel = (link_clock * lane_count * 8 *
-			  DP_DSC_FEC_OVERHEAD_FACTOR) /
-		mode_clock;
-
-	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
-	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER /
-		mode_hdisplay;
-
-	/*
-	 * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW
-	 * check, output bpp from small joiner RAM check)
-	 */
-	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
-
-	/* Error out if the max bpp is less than smallest allowed valid bpp */
-	if (bits_per_pixel < valid_dsc_bpp[0]) {
-		DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel);
-		return 0;
-	}
-
-	/* Find the nearest match in the array of known BPPs from VESA */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
-		if (bits_per_pixel < valid_dsc_bpp[i + 1])
-			break;
-	}
-	bits_per_pixel = valid_dsc_bpp[i];
-
-	/*
-	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
-	 * fractional part is 0
-	 */
-	return bits_per_pixel << 4;
-}
-
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
-				int mode_clock,
-				int mode_hdisplay)
-{
-	u8 min_slice_count, i;
-	int max_slice_width;
-
-	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_0);
-	else
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_1);
-
-	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
-	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
-		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
-			      max_slice_width);
-		return 0;
-	}
-	/* Also take into account max slice width */
-	min_slice_count = min_t(u8, min_slice_count,
-				DIV_ROUND_UP(mode_hdisplay,
-					     max_slice_width));
-
-	/* Find the closest match to the valid slice count values */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
-		if (valid_dsc_slicecount[i] >
-		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
-						    false))
-			break;
-		if (min_slice_count  <= valid_dsc_slicecount[i])
-			return valid_dsc_slicecount[i];
-	}
-
-	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
-	return 0;
-}
-
 static void
 intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 657bbb1f5ed0..00981fb9414b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -102,10 +102,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
 bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay);
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock,
-				int mode_hdisplay);
 
 bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
@@ -118,4 +114,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
 	return ~((1 << lane_count) - 1) & 0xf;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock);
+
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 6df240a01b8c..600873c796d0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       crtc_state->port_clock,
 			       &crtc_state->dp_m_n,
-			       constant_n);
+			       constant_n, crtc_state->fec_enable);
 	crtc_state->dp_m_n.tu = slots;
 
 	return 0;
@@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->type = INTEL_OUTPUT_DP_MST;
 	intel_encoder->power_domain = intel_dig_port->base.power_domain;
 	intel_encoder->port = intel_dig_port->base.port;
-	intel_encoder->crtc_mask = BIT(pipe);
+	intel_encoder->crtc_mask = 0x7;
 	intel_encoder->cloneable = 0;
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index b8148f838354..d5a298c3c83b 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -525,16 +525,31 @@ static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
 	val = I915_READ(WRPLL_CTL(id));
 	I915_WRITE(WRPLL_CTL(id), val & ~WRPLL_PLL_ENABLE);
 	POSTING_READ(WRPLL_CTL(id));
+
+	/*
+	 * Try to set up the PCH reference clock once all DPLLs
+	 * that depend on it have been shut down.
+	 */
+	if (dev_priv->pch_ssc_use & BIT(id))
+		intel_init_pch_refclk(dev_priv);
 }
 
 static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll)
 {
+	enum intel_dpll_id id = pll->info->id;
 	u32 val;
 
 	val = I915_READ(SPLL_CTL);
 	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
 	POSTING_READ(SPLL_CTL);
+
+	/*
+	 * Try to set up the PCH reference clock once all DPLLs
+	 * that depend on it have been shut down.
+	 */
+	if (dev_priv->pch_ssc_use & BIT(id))
+		intel_init_pch_refclk(dev_priv);
 }
 
 static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index e7588799fce5..104cf6d42333 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -147,11 +147,11 @@ enum intel_dpll_id {
 	 */
 	DPLL_ID_ICL_MGPLL4 = 6,
 	/**
-	 * @DPLL_ID_TGL_TCPLL5: TGL TC PLL port 5 (TC5)
+	 * @DPLL_ID_TGL_MGPLL5: TGL TC PLL port 5 (TC5)
 	 */
 	DPLL_ID_TGL_MGPLL5 = 7,
 	/**
-	 * @DPLL_ID_TGL_TCPLL6: TGL TC PLL port 6 (TC6)
+	 * @DPLL_ID_TGL_MGPLL6: TGL TC PLL port 6 (TC6)
 	 */
 	DPLL_ID_TGL_MGPLL6 = 8,
 };
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index dea63be1964f..cae25e493128 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -1528,6 +1528,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 	int src_x, src_w, src_h, crtc_w, crtc_h;
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->base.adjusted_mode;
+	unsigned int stride = plane_state->color_plane[0].stride;
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int width_bytes;
 	int min_width, min_height;
@@ -1569,9 +1570,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	if (width_bytes > 4096 || fb->pitches[0] > 4096) {
+	if (stride > 4096) {
 		DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n",
-			      fb->pitches[0], 4096);
+			      stride, 4096);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 261c9bd83f51..05289edbafe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -245,11 +245,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 
 	wakeref = intel_runtime_pm_get(rpm);
 
-	srcu = intel_gt_reset_trylock(ggtt->vm.gt);
-	if (srcu < 0) {
-		ret = srcu;
+	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	if (ret)
 		goto err_rpm;
-	}
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
@@ -318,7 +316,11 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
-	i915_vma_set_ggtt_write(vma);
+	if (write) {
+		GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+		i915_vma_set_ggtt_write(vma);
+		obj->mm.dirty = true;
+	}
 
 err_fence:
 	i915_vma_unpin_fence(vma);
@@ -362,6 +364,7 @@ err:
 		return VM_FAULT_OOM;
 	case -ENOSPC:
 	case -EFAULT:
+	case -ENODEV: /* bad object, how did you get here! */
 		return VM_FAULT_SIGBUS;
 	default:
 		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
@@ -473,10 +476,16 @@ i915_gem_mmap_gtt(struct drm_file *file,
 	if (!obj)
 		return -ENOENT;
 
+	if (i915_gem_object_never_bind_ggtt(obj)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	ret = create_mmap_offset(obj);
 	if (ret == 0)
 		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
 
+out:
 	i915_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 5efb9936e05b..ddf3605bea8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -153,6 +153,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 }
 
 static inline bool
+i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+}
+
+static inline bool
 i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 {
 	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
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 ede0eb4218a8..646859fea224 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
-#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT		BIT(3)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(4)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 92e53c25424c..ad2a63dbcac2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -241,9 +241,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	mutex_lock(&i915->drm.struct_mutex);
 	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
-	i915_gem_restore_gtt_mappings(i915);
-	i915_gem_restore_fences(i915);
-
 	if (i915_gem_init_hw(i915))
 		goto err_wedged;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 11b231c187c5..6b3b50f0f6d9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -702,6 +702,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE |
+		 I915_GEM_OBJECT_NO_GGTT |
 		 I915_GEM_OBJECT_ASYNC_CANCEL,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d3c6993f4f46..22aab8593abf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -136,6 +136,20 @@ execlists_active(const struct intel_engine_execlists *execlists)
 	return READ_ONCE(*execlists->active);
 }
 
+static inline void
+execlists_active_lock_bh(struct intel_engine_execlists *execlists)
+{
+	local_bh_disable(); /* prevent local softirq and lock recursion */
+	tasklet_lock(&execlists->tasklet);
+}
+
+static inline void
+execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
+{
+	tasklet_unlock(&execlists->tasklet);
+	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
 struct i915_request *
 execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 82630db0394b..4ce8626b140e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1197,9 +1197,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 					 struct drm_printer *m)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	const struct intel_engine_execlists * const execlists =
-		&engine->execlists;
-	unsigned long flags;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	u64 addr;
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
@@ -1281,7 +1279,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
-		spin_lock_irqsave(&engine->active.lock, flags);
+		execlists_active_lock_bh(execlists);
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[80];
 			int len;
@@ -1309,7 +1307,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				 hwsp_seqno(rq));
 			print_request(m, rq, hdr);
 		}
-		spin_unlock_irqrestore(&engine->active.lock, flags);
+		execlists_active_unlock_bh(execlists);
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
 			   ENGINE_READ(engine, RING_PP_DIR_BASE));
@@ -1440,8 +1438,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	write_seqlock(&engine->stats.lock);
+	execlists_active_lock_bh(execlists);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1469,8 +1467,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock(&engine->stats.lock);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+	execlists_active_unlock_bh(execlists);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d42584439f51..06a506c29463 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring);
 
+static void mark_eio(struct i915_request *rq)
+{
+	if (!i915_request_signaled(rq))
+		dma_fence_set_error(&rq->fence, -EIO);
+	i915_request_mark_complete(rq);
+}
+
 static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
 {
 	return (i915_ggtt_offset(engine->status_page.vma) +
@@ -631,7 +638,6 @@ execlists_schedule_out(struct i915_request *rq)
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
-	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
 
 	old = READ_ONCE(ce->inflight);
 	do
@@ -797,6 +803,17 @@ static bool can_merge_rq(const struct i915_request *prev,
 	GEM_BUG_ON(prev == next);
 	GEM_BUG_ON(!assert_priority_queue(prev, next));
 
+	/*
+	 * We do not submit known completed requests. Therefore if the next
+	 * request is already completed, we can pretend to merge it in
+	 * with the previous context (and we will skip updating the ELSP
+	 * and tracking). Thus hopefully keeping the ELSP full with active
+	 * contexts, despite the best efforts of preempt-to-busy to confuse
+	 * us.
+	 */
+	if (i915_request_completed(next))
+		return true;
+
 	if (!can_merge_ctx(prev->hw_context, next->hw_context))
 		return false;
 
@@ -893,7 +910,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 static struct i915_request *
 last_active(const struct intel_engine_execlists *execlists)
 {
-	struct i915_request * const *last = execlists->active;
+	struct i915_request * const *last = READ_ONCE(execlists->active);
 
 	while (*last && i915_request_completed(*last))
 		last++;
@@ -1172,21 +1189,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				continue;
 			}
 
-			if (i915_request_completed(rq)) {
-				ve->request = NULL;
-				ve->base.execlists.queue_priority_hint = INT_MIN;
-				rb_erase_cached(rb, &execlists->virtual);
-				RB_CLEAR_NODE(rb);
-
-				rq->engine = engine;
-				__i915_request_submit(rq);
-
-				spin_unlock(&ve->base.active.lock);
-
-				rb = rb_first_cached(&execlists->virtual);
-				continue;
-			}
-
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
 				return; /* leave this for another */
@@ -1237,11 +1239,24 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				GEM_BUG_ON(ve->siblings[0] != engine);
 			}
 
-			__i915_request_submit(rq);
-			if (!i915_request_completed(rq)) {
+			if (__i915_request_submit(rq)) {
 				submit = true;
 				last = rq;
 			}
+			i915_request_put(rq);
+
+			/*
+			 * Hmm, we have a bunch of virtual engine requests,
+			 * but the first one was already completed (thanks
+			 * preempt-to-busy!). Keep looking at the veng queue
+			 * until we have no more relevant requests (i.e.
+			 * the normal submit queue has higher priority).
+			 */
+			if (!submit) {
+				spin_unlock(&ve->base.active.lock);
+				rb = rb_first_cached(&execlists->virtual);
+				continue;
+			}
 		}
 
 		spin_unlock(&ve->base.active.lock);
@@ -1254,8 +1269,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			if (i915_request_completed(rq))
-				goto skip;
+			bool merge = true;
 
 			/*
 			 * Can we combine this request with the current port?
@@ -1296,14 +1310,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				    ctx_single_port_submission(rq->hw_context))
 					goto done;
 
-				*port = execlists_schedule_in(last, port - execlists->pending);
-				port++;
+				merge = false;
 			}
 
-			last = rq;
-			submit = true;
-skip:
-			__i915_request_submit(rq);
+			if (__i915_request_submit(rq)) {
+				if (!merge) {
+					*port = execlists_schedule_in(last, port - execlists->pending);
+					port++;
+					last = NULL;
+				}
+
+				GEM_BUG_ON(last &&
+					   !can_merge_ctx(last->hw_context,
+							  rq->hw_context));
+
+				submit = true;
+				last = rq;
+			}
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -1593,8 +1616,11 @@ static void process_csb(struct intel_engine_cs *engine)
 static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
 	lockdep_assert_held(&engine->active.lock);
-	if (!engine->execlists.pending[0])
+	if (!engine->execlists.pending[0]) {
+		rcu_read_lock(); /* protect peeking at execlists->active */
 		execlists_dequeue(engine);
+		rcu_read_unlock();
+	}
 }
 
 /*
@@ -2399,10 +2425,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 
 static struct i915_request *active_request(struct i915_request *rq)
 {
-	const struct list_head * const list = &rq->timeline->requests;
 	const struct intel_context * const ce = rq->hw_context;
 	struct i915_request *active = NULL;
+	struct list_head *list;
 
+	if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
+		return rq;
+
+	list = &rq->timeline->requests;
 	list_for_each_entry_from_reverse(rq, list, link) {
 		if (i915_request_completed(rq))
 			break;
@@ -2552,12 +2582,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	__execlists_reset(engine, true);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
-		if (!i915_request_signaled(rq))
-			dma_fence_set_error(&rq->fence, -EIO);
-
-		i915_request_mark_complete(rq);
-	}
+	list_for_each_entry(rq, &engine->active.requests, sched.link)
+		mark_eio(rq);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
@@ -2565,10 +2591,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			list_del_init(&rq->sched.link);
+			mark_eio(rq);
 			__i915_request_submit(rq);
-			dma_fence_set_error(&rq->fence, -EIO);
-			i915_request_mark_complete(rq);
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -2584,13 +2608,15 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		RB_CLEAR_NODE(rb);
 
 		spin_lock(&ve->base.active.lock);
-		if (ve->request) {
-			ve->request->engine = engine;
-			__i915_request_submit(ve->request);
-			dma_fence_set_error(&ve->request->fence, -EIO);
-			i915_request_mark_complete(ve->request);
+		rq = fetch_and_zero(&ve->request);
+		if (rq) {
+			mark_eio(rq);
+
+			rq->engine = engine;
+			__i915_request_submit(rq);
+			i915_request_put(rq);
+
 			ve->base.execlists.queue_priority_hint = INT_MIN;
-			ve->request = NULL;
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
@@ -3594,6 +3620,8 @@ submit_engine:
 static void virtual_submit_request(struct i915_request *rq)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	struct i915_request *old;
+	unsigned long flags;
 
 	GEM_TRACE("%s: rq=%llx:%lld\n",
 		  ve->base.name,
@@ -3602,15 +3630,31 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
-	GEM_BUG_ON(ve->request);
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+	spin_lock_irqsave(&ve->base.active.lock, flags);
+
+	old = ve->request;
+	if (old) { /* background completion event from preempt-to-busy */
+		GEM_BUG_ON(!i915_request_completed(old));
+		__i915_request_submit(old);
+		i915_request_put(old);
+	}
+
+	if (i915_request_completed(rq)) {
+		__i915_request_submit(rq);
+
+		ve->base.execlists.queue_priority_hint = INT_MIN;
+		ve->request = NULL;
+	} else {
+		ve->base.execlists.queue_priority_hint = rq_prio(rq);
+		ve->request = i915_request_get(rq);
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
-	WRITE_ONCE(ve->request, rq);
+		GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+		list_move_tail(&rq->sched.link, virtual_queue(ve));
 
-	list_move_tail(&rq->sched.link, virtual_queue(ve));
+		tasklet_schedule(&ve->base.execlists.tasklet);
+	}
 
-	tasklet_schedule(&ve->base.execlists.tasklet);
+	spin_unlock_irqrestore(&ve->base.active.lock, flags);
 }
 
 static struct ve_bond *
@@ -3631,18 +3675,22 @@ static void
 virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	intel_engine_mask_t allowed, exec;
 	struct ve_bond *bond;
 
+	allowed = ~to_request(signal)->engine->mask;
+
 	bond = virtual_find_bond(ve, to_request(signal)->engine);
-	if (bond) {
-		intel_engine_mask_t old, new, cmp;
+	if (bond)
+		allowed &= bond->sibling_mask;
 
-		cmp = READ_ONCE(rq->execution_mask);
-		do {
-			old = cmp;
-			new = cmp & bond->sibling_mask;
-		} while ((cmp = cmpxchg(&rq->execution_mask, old, new)) != old);
-	}
+	/* Restrict the bonded request to run on only the available engines */
+	exec = READ_ONCE(rq->execution_mask);
+	while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
+		;
+
+	/* Prevent the master from being re-run on the bonded engines */
+	to_request(signal)->execution_mask &= ~allowed;
 }
 
 struct intel_context *
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b9d84d52e986..8cea42379dd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -42,11 +42,10 @@ static void engine_skip_context(struct i915_request *rq)
 	struct intel_engine_cs *engine = rq->engine;
 	struct i915_gem_context *hung_ctx = rq->gem_context;
 
-	lockdep_assert_held(&engine->active.lock);
-
 	if (!i915_request_is_active(rq))
 		return;
 
+	lockdep_assert_held(&engine->active.lock);
 	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
 		if (rq->gem_context == hung_ctx)
 			i915_request_skip(rq, -EIO);
@@ -123,7 +122,6 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 		  rq->fence.seqno,
 		  yesno(guilty));
 
-	lockdep_assert_held(&rq->engine->active.lock);
 	GEM_BUG_ON(i915_request_completed(rq));
 
 	if (guilty) {
@@ -1214,10 +1212,8 @@ out:
 	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 }
 
-int intel_gt_reset_trylock(struct intel_gt *gt)
+int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
 {
-	int srcu;
-
 	might_lock(&gt->reset.backoff_srcu);
 	might_sleep();
 
@@ -1232,10 +1228,10 @@ int intel_gt_reset_trylock(struct intel_gt *gt)
 
 		rcu_read_lock();
 	}
-	srcu = srcu_read_lock(&gt->reset.backoff_srcu);
+	*srcu = srcu_read_lock(&gt->reset.backoff_srcu);
 	rcu_read_unlock();
 
-	return srcu;
+	return 0;
 }
 
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 37a987b17108..52c00199e069 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -38,7 +38,7 @@ int intel_engine_reset(struct intel_engine_cs *engine,
 
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
-int __must_check intel_gt_reset_trylock(struct intel_gt *gt);
+int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
 
 void intel_gt_set_wedged(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 601c16239fdf..bacaa7bb8c9a 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1573,7 +1573,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	struct intel_engine_cs *engine = rq->engine;
 	enum intel_engine_id id;
 	const int num_engines =
-		IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
+		IS_HASWELL(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
 	bool force_restore = false;
 	int len;
 	u32 *cs;
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 45481eb1fa3c..5f6ec2fd29a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1063,6 +1063,9 @@ static void gen9_whitelist_build(struct i915_wa_list *w)
 
 	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
 	whitelist_reg(w, GEN8_HDC_CHICKEN1);
+
+	/* WaSendPushConstantsFromMMIO:skl,bxt */
+	whitelist_reg(w, COMMON_SLICE_CHICKEN2);
 }
 
 static void skl_whitelist_build(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 020696726f9e..bb6f86c7067a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1924,6 +1924,11 @@ static int i915_drm_resume(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
 
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_restore_gtt_mappings(dev_priv);
+	i915_gem_restore_fences(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
 	intel_csr_ucode_resume(dev_priv);
 
 	i915_restore_state(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 772154e4073e..953e1d12c23c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1723,6 +1723,8 @@ struct drm_i915_private {
 		struct work_struct idle_work;
 	} gem;
 
+	u8 pch_ssc_use;
+
 	/* For i945gm vblank irq vs. C3 workaround */
 	struct {
 		struct work_struct work;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e7c52cf8ed..d0f94f239919 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -969,6 +969,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
+	if (i915_gem_object_never_bind_ggtt(obj))
+		return ERR_PTR(-ENODEV);
+
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
 		/* If the required space is larger than the available
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 167a7b56ed5b..6795f1daa3d5 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -77,6 +77,12 @@ struct drm_i915_private;
 
 #define I915_GEM_IDLE_TIMEOUT (HZ / 5)
 
+static inline void tasklet_lock(struct tasklet_struct *t)
+{
+	while (!tasklet_trylock(t))
+		cpu_relax();
+}
+
 static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
 {
 	if (!atomic_fetch_inc(&t->count))
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a53777dd371c..1c5506822dc7 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -194,6 +194,27 @@ static void free_capture_list(struct i915_request *request)
 	}
 }
 
+static void remove_from_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Virtual engines complicate acquiring the engine timeline lock,
+	 * as their rq->engine pointer is not stable until under that
+	 * engine lock. The simple ploy we use is to take the lock then
+	 * check that the rq still belongs to the newly locked engine.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock(&locked->active.lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->active.lock);
+		spin_lock(&engine->active.lock);
+		locked = engine;
+	}
+	list_del(&rq->sched.link);
+	spin_unlock(&locked->active.lock);
+}
+
 static bool i915_request_retire(struct i915_request *rq)
 {
 	struct i915_active_request *active, *next;
@@ -259,9 +280,7 @@ static bool i915_request_retire(struct i915_request *rq)
 	 * request that we have removed from the HW and put back on a run
 	 * queue.
 	 */
-	spin_lock(&rq->engine->active.lock);
-	list_del(&rq->sched.link);
-	spin_unlock(&rq->engine->active.lock);
+	remove_from_engine(rq);
 
 	spin_lock(&rq->lock);
 	i915_request_mark_complete(rq);
@@ -358,9 +377,10 @@ __i915_request_await_execution(struct i915_request *rq,
 	return 0;
 }
 
-void __i915_request_submit(struct i915_request *request)
+bool __i915_request_submit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
+	bool result = false;
 
 	GEM_TRACE("%s fence %llx:%lld, current %d\n",
 		  engine->name,
@@ -370,6 +390,25 @@ void __i915_request_submit(struct i915_request *request)
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
 
+	/*
+	 * With the advent of preempt-to-busy, we frequently encounter
+	 * requests that we have unsubmitted from HW, but left running
+	 * until the next ack and so have completed in the meantime. On
+	 * resubmission of that completed request, we can skip
+	 * updating the payload, and execlists can even skip submitting
+	 * the request.
+	 *
+	 * We must remove the request from the caller's priority queue,
+	 * and the caller must only call us when the request is in their
+	 * priority queue, under the active.lock. This ensures that the
+	 * request has *not* yet been retired and we can safely move
+	 * the request into the engine->active.list where it will be
+	 * dropped upon retiring. (Otherwise if resubmit a *retired*
+	 * request, this would be a horrible use-after-free.)
+	 */
+	if (i915_request_completed(request))
+		goto xfer;
+
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
@@ -393,13 +432,18 @@ void __i915_request_submit(struct i915_request *request)
 	    i915_sw_fence_signaled(&request->semaphore))
 		engine->saturated |= request->sched.semaphores;
 
-	/* We may be recursing from the signal callback of another i915 fence */
-	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
+	engine->emit_fini_breadcrumb(request,
+				     request->ring->vaddr + request->postfix);
 
-	list_move_tail(&request->sched.link, &engine->active.requests);
+	trace_i915_request_execute(request);
+	engine->serial++;
+	result = true;
+
+xfer:	/* We may be recursing from the signal callback of another i915 fence */
+	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
-	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
+	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+		list_move_tail(&request->sched.link, &engine->active.requests);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -410,12 +454,7 @@ void __i915_request_submit(struct i915_request *request)
 
 	spin_unlock(&request->lock);
 
-	engine->emit_fini_breadcrumb(request,
-				     request->ring->vaddr + request->postfix);
-
-	engine->serial++;
-
-	trace_i915_request_execute(request);
+	return result;
 }
 
 void i915_request_submit(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 8ac6e1226a56..e4dd013761e8 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -292,7 +292,7 @@ int i915_request_await_execution(struct i915_request *rq,
 
 void i915_request_add(struct i915_request *rq);
 
-void __i915_request_submit(struct i915_request *request);
+bool __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
 void i915_request_skip(struct i915_request *request, int error);
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index fa864d8f2b73..15f8bff141f9 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -69,6 +69,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
+	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index e6a2d65f19c6..c29c81ec7971 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -41,6 +41,7 @@ enum intel_pch {
 #define INTEL_PCH_CNP_DEVICE_ID_TYPE		0xA300
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
 #define INTEL_PCH_CMP_DEVICE_ID_TYPE		0x0280
+#define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_MCC2_DEVICE_ID_TYPE		0x3880
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bb6dd54a6ff3..37593831b539 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -118,6 +118,12 @@ static void pm_resume(struct drm_i915_private *i915)
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		intel_gt_sanitize(&i915->gt, false);
 		i915_gem_sanitize(i915);
+
+		mutex_lock(&i915->drm.struct_mutex);
+		i915_gem_restore_gtt_mappings(i915);
+		i915_gem_restore_fences(i915);
+		mutex_unlock(&i915->drm.struct_mutex);
+
 		i915_gem_resume(i915);
 	}
 }
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 663ff9f4fac9..1e7b1be25bb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -26,6 +26,8 @@
 #include "dsi_cfg.h"
 #include "msm_kms.h"
 
+#define DSI_RESET_TOGGLE_DELAY_MS 20
+
 static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 {
 	u32 ver;
@@ -986,7 +988,7 @@ static void dsi_sw_reset(struct msm_dsi_host *msm_host)
 	wmb(); /* clocks need to be enabled before reset */
 
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb(); /* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 }
 
@@ -1396,7 +1398,7 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host)
 
 	/* dsi controller can only be reset while clocks are running */
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb();	/* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 	wmb();	/* controller out of reset */
 	dsi_write(msm_host, REG_DSI_CTRL, data0);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 2db029371c91..5193b6257061 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -267,7 +267,7 @@ nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw, bool modeset,
 			asyw->image.pitch[0] = fb->base.pitches[0];
 		}
 
-		if (!(asyh->state.pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC))
+		if (!asyh->state.async_flip)
 			asyw->image.interval = 1;
 		else
 			asyw->image.interval = 0;
@@ -383,7 +383,7 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 	}
 
 	/* Can't do an immediate flip while changing the LUT. */
-	asyh->state.pageflip_flags &= ~DRM_MODE_PAGE_FLIP_ASYNC;
+	asyh->state.async_flip = false;
 }
 
 static int
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index e226324adb69..4bdd63b57100 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1083,7 +1083,7 @@ static const struct dss_features omap34xx_dss_feats = {
 
 static const struct dss_features omap3630_dss_feats = {
 	.model			=	DSS_MODEL_OMAP3,
-	.fck_div_max		=	32,
+	.fck_div_max		=	31,
 	.fck_freq_max		=	173000000,
 	.dss_fck_multiplier	=	1,
 	.parent_clk_name	=	"dpll4_ck",
diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
index fc82a525b071..ee4379729a5b 100644
--- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c
+++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
@@ -220,9 +220,17 @@ static const struct of_device_id lb035q02_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, lb035q02_of_match);
 
+static const struct spi_device_id lb035q02_ids[] = {
+	{ "lb035q02", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, lb035q02_ids);
+
 static struct spi_driver lb035q02_driver = {
 	.probe		= lb035q02_probe,
 	.remove		= lb035q02_remove,
+	.id_table	= lb035q02_ids,
 	.driver		= {
 		.name	= "panel-lg-lb035q02",
 		.of_match_table = lb035q02_of_match,
@@ -231,7 +239,6 @@ static struct spi_driver lb035q02_driver = {
 
 module_spi_driver(lb035q02_driver);
 
-MODULE_ALIAS("spi:lgphilips,lb035q02");
 MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
 MODULE_DESCRIPTION("LG.Philips LB035Q02 LCD Panel driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
index 299b217c83e1..20f17e46e65d 100644
--- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
@@ -230,9 +230,17 @@ static const struct of_device_id nl8048_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, nl8048_of_match);
 
+static const struct spi_device_id nl8048_ids[] = {
+	{ "nl8048hl11", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, nl8048_ids);
+
 static struct spi_driver nl8048_driver = {
 	.probe		= nl8048_probe,
 	.remove		= nl8048_remove,
+	.id_table	= nl8048_ids,
 	.driver		= {
 		.name	= "panel-nec-nl8048hl11",
 		.pm	= &nl8048_pm_ops,
@@ -242,7 +250,6 @@ static struct spi_driver nl8048_driver = {
 
 module_spi_driver(nl8048_driver);
 
-MODULE_ALIAS("spi:nec,nl8048hl11");
 MODULE_AUTHOR("Erik Gilling <konkers@android.com>");
 MODULE_DESCRIPTION("NEC-NL8048HL11 Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
index 305259b58767..3d5b9c4f68d9 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
@@ -684,9 +684,17 @@ static const struct of_device_id acx565akm_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, acx565akm_of_match);
 
+static const struct spi_device_id acx565akm_ids[] = {
+	{ "acx565akm", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, acx565akm_ids);
+
 static struct spi_driver acx565akm_driver = {
 	.probe		= acx565akm_probe,
 	.remove		= acx565akm_remove,
+	.id_table	= acx565akm_ids,
 	.driver		= {
 		.name	= "panel-sony-acx565akm",
 		.of_match_table = acx565akm_of_match,
@@ -695,7 +703,6 @@ static struct spi_driver acx565akm_driver = {
 
 module_spi_driver(acx565akm_driver);
 
-MODULE_ALIAS("spi:sony,acx565akm");
 MODULE_AUTHOR("Nokia Corporation");
 MODULE_DESCRIPTION("Sony ACX565AKM LCD Panel Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
index d7b2e34626ef..f2baff827f50 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
@@ -375,8 +375,7 @@ static const struct of_device_id td028ttec1_of_match[] = {
 MODULE_DEVICE_TABLE(of, td028ttec1_of_match);
 
 static const struct spi_device_id td028ttec1_ids[] = {
-	{ "tpo,td028ttec1", 0},
-	{ "toppoly,td028ttec1", 0 },
+	{ "td028ttec1", 0 },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
index 84370562910f..ba163c779084 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
@@ -491,9 +491,17 @@ static const struct of_device_id td043mtea1_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, td043mtea1_of_match);
 
+static const struct spi_device_id td043mtea1_ids[] = {
+	{ "td043mtea1", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, td043mtea1_ids);
+
 static struct spi_driver td043mtea1_driver = {
 	.probe		= td043mtea1_probe,
 	.remove		= td043mtea1_remove,
+	.id_table	= td043mtea1_ids,
 	.driver		= {
 		.name	= "panel-tpo-td043mtea1",
 		.pm	= &td043mtea1_pm_ops,
@@ -503,7 +511,6 @@ static struct spi_driver td043mtea1_driver = {
 
 module_spi_driver(td043mtea1_driver);
 
-MODULE_ALIAS("spi:tpo,td043mtea1");
 MODULE_AUTHOR("Gražvydas Ignotas <notasas@gmail.com>");
 MODULE_DESCRIPTION("TPO TD043MTEA1 Panel Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index a1f5fa6a742a..12ff77dacc95 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -39,7 +39,7 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 	 * If frequency scaling from low to high, adjust voltage first.
 	 * If frequency scaling from high to low, adjust frequency first.
 	 */
-	if (old_clk_rate < target_rate && pfdev->regulator) {
+	if (old_clk_rate < target_rate) {
 		err = regulator_set_voltage(pfdev->regulator, target_volt,
 					    target_volt);
 		if (err) {
@@ -53,14 +53,12 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 	if (err) {
 		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
 			err);
-		if (pfdev->regulator)
-			regulator_set_voltage(pfdev->regulator,
-					      pfdev->devfreq.cur_volt,
-					      pfdev->devfreq.cur_volt);
+		regulator_set_voltage(pfdev->regulator, pfdev->devfreq.cur_volt,
+				      pfdev->devfreq.cur_volt);
 		return err;
 	}
 
-	if (old_clk_rate > target_rate && pfdev->regulator) {
+	if (old_clk_rate > target_rate) {
 		err = regulator_set_voltage(pfdev->regulator, target_volt,
 					    target_volt);
 		if (err)
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c
index 46b0b02e4289..238fb6d54df4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.c
+++ b/drivers/gpu/drm/panfrost/panfrost_device.c
@@ -89,12 +89,9 @@ static int panfrost_regulator_init(struct panfrost_device *pfdev)
 {
 	int ret;
 
-	pfdev->regulator = devm_regulator_get_optional(pfdev->dev, "mali");
+	pfdev->regulator = devm_regulator_get(pfdev->dev, "mali");
 	if (IS_ERR(pfdev->regulator)) {
 		ret = PTR_ERR(pfdev->regulator);
-		pfdev->regulator = NULL;
-		if (ret == -ENODEV)
-			return 0;
 		dev_err(pfdev->dev, "failed to get regulator: %d\n", ret);
 		return ret;
 	}
@@ -110,8 +107,7 @@ static int panfrost_regulator_init(struct panfrost_device *pfdev)
 
 static void panfrost_regulator_fini(struct panfrost_device *pfdev)
 {
-	if (pfdev->regulator)
-		regulator_disable(pfdev->regulator);
+	regulator_disable(pfdev->regulator);
 }
 
 int panfrost_device_init(struct panfrost_device *pfdev)
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index bc2ddeb55f5d..f21bc8a7ee3a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -556,11 +556,11 @@ static int panfrost_probe(struct platform_device *pdev)
 	return 0;
 
 err_out2:
+	pm_runtime_disable(pfdev->dev);
 	panfrost_devfreq_fini(pfdev);
 err_out1:
 	panfrost_device_fini(pfdev);
 err_out0:
-	pm_runtime_disable(pfdev->dev);
 	drm_dev_put(ddev);
 	return err;
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index f67ed925c0ef..8822ec13a0d6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -208,6 +208,9 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev)
 	pfdev->features.mem_features = gpu_read(pfdev, GPU_MEM_FEATURES);
 	pfdev->features.mmu_features = gpu_read(pfdev, GPU_MMU_FEATURES);
 	pfdev->features.thread_features = gpu_read(pfdev, GPU_THREAD_FEATURES);
+	pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS);
+	pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
+	pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE);
 	pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
 	for (i = 0; i < 4; i++)
 		pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i));
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a58551668d9a..21f34d44aac2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 		job_read(pfdev, JS_TAIL_LO(js)),
 		sched_job);
 
-	mutex_lock(&pfdev->reset_lock);
+	if (!mutex_trylock(&pfdev->reset_lock))
+		return;
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
+
+		drm_sched_stop(sched, sched_job);
+		if (js != i)
+			/* Ensure any timeouts on other slots have finished */
+			cancel_delayed_work_sync(&sched->work_tdr);
+	}
 
-	if (sched_job)
-		drm_sched_increase_karma(sched_job);
+	drm_sched_increase_karma(sched_job);
 
 	spin_lock_irqsave(&pfdev->js->job_lock, flags);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 6010f9ee7c1f..a3ed64a1f15e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -224,9 +224,9 @@ static size_t get_pgsize(u64 addr, size_t size)
 	return SZ_2M;
 }
 
-void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
-			      struct panfrost_mmu *mmu,
-			      u64 iova, size_t size)
+static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
+				     struct panfrost_mmu *mmu,
+				     u64 iova, size_t size)
 {
 	if (mmu->as < 0)
 		return;
@@ -394,58 +394,70 @@ void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
 	free_io_pgtable_ops(mmu->pgtbl_ops);
 }
 
-static struct drm_mm_node *addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
+static struct panfrost_gem_object *
+addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
 {
-	struct drm_mm_node *node = NULL;
+	struct panfrost_gem_object *bo = NULL;
+	struct panfrost_file_priv *priv;
+	struct drm_mm_node *node;
 	u64 offset = addr >> PAGE_SHIFT;
 	struct panfrost_mmu *mmu;
 
 	spin_lock(&pfdev->as_lock);
 	list_for_each_entry(mmu, &pfdev->as_lru_list, list) {
-		struct panfrost_file_priv *priv;
-		if (as != mmu->as)
-			continue;
+		if (as == mmu->as)
+			goto found_mmu;
+	}
+	goto out;
+
+found_mmu:
+	priv = container_of(mmu, struct panfrost_file_priv, mmu);
+
+	spin_lock(&priv->mm_lock);
 
-		priv = container_of(mmu, struct panfrost_file_priv, mmu);
-		drm_mm_for_each_node(node, &priv->mm) {
-			if (offset >= node->start && offset < (node->start + node->size))
-				goto out;
+	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);
+			break;
 		}
 	}
 
+	spin_unlock(&priv->mm_lock);
 out:
 	spin_unlock(&pfdev->as_lock);
-	return node;
+	return bo;
 }
 
 #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
 
-int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
+static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
+				       u64 addr)
 {
 	int ret, i;
-	struct drm_mm_node *node;
 	struct panfrost_gem_object *bo;
 	struct address_space *mapping;
 	pgoff_t page_offset;
 	struct sg_table *sgt;
 	struct page **pages;
 
-	node = addr_to_drm_mm_node(pfdev, as, addr);
-	if (!node)
+	bo = addr_to_drm_mm_node(pfdev, as, addr);
+	if (!bo)
 		return -ENOENT;
 
-	bo = drm_mm_node_to_panfrost_bo(node);
 	if (!bo->is_heap) {
 		dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)",
-			 node->start << PAGE_SHIFT);
-		return -EINVAL;
+			 bo->node.start << PAGE_SHIFT);
+		ret = -EINVAL;
+		goto err_bo;
 	}
 	WARN_ON(bo->mmu->as != as);
 
 	/* Assume 2MB alignment and size multiple */
 	addr &= ~((u64)SZ_2M - 1);
 	page_offset = addr >> PAGE_SHIFT;
-	page_offset -= node->start;
+	page_offset -= bo->node.start;
 
 	mutex_lock(&bo->base.pages_lock);
 
@@ -454,7 +466,8 @@ int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
 				     sizeof(struct sg_table), GFP_KERNEL | __GFP_ZERO);
 		if (!bo->sgts) {
 			mutex_unlock(&bo->base.pages_lock);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_bo;
 		}
 
 		pages = kvmalloc_array(bo->base.base.size >> PAGE_SHIFT,
@@ -463,7 +476,8 @@ int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
 			kfree(bo->sgts);
 			bo->sgts = NULL;
 			mutex_unlock(&bo->base.pages_lock);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_bo;
 		}
 		bo->base.pages = pages;
 		bo->base.pages_use_count = 1;
@@ -501,12 +515,16 @@ int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
 
 	dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr);
 
+	drm_gem_object_put_unlocked(&bo->base.base);
+
 	return 0;
 
 err_map:
 	sg_free_table(sgt);
 err_pages:
 	drm_gem_shmem_put_pages(&bo->base);
+err_bo:
+	drm_gem_object_put_unlocked(&bo->base.base);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 83c57d325ca8..2dba192bf198 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -16,6 +16,7 @@
 #include "panfrost_issues.h"
 #include "panfrost_job.h"
 #include "panfrost_mmu.h"
+#include "panfrost_perfcnt.h"
 #include "panfrost_regs.h"
 
 #define COUNTERS_PER_BLOCK		64
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 431e6b64b77d..4528f4dc0b2d 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -324,8 +324,39 @@ bool radeon_device_is_virtual(void);
 static int radeon_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
+	unsigned long flags = 0;
 	int ret;
 
+	if (!ent)
+		return -ENODEV; /* Avoid NULL-ptr deref in drm_get_pci_dev */
+
+	flags = ent->driver_data;
+
+	if (!radeon_si_support) {
+		switch (flags & RADEON_FAMILY_MASK) {
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_VERDE:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+			dev_info(&pdev->dev,
+				 "SI support disabled by module param\n");
+			return -ENODEV;
+		}
+	}
+	if (!radeon_cik_support) {
+		switch (flags & RADEON_FAMILY_MASK) {
+		case CHIP_KAVERI:
+		case CHIP_BONAIRE:
+		case CHIP_HAWAII:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+			dev_info(&pdev->dev,
+				 "CIK support disabled by module param\n");
+			return -ENODEV;
+		}
+	}
+
 	if (vga_switcheroo_client_probe_defer(pdev))
 		return -EPROBE_DEFER;
 
@@ -348,7 +379,9 @@ radeon_pci_remove(struct pci_dev *pdev)
 static void
 radeon_pci_shutdown(struct pci_dev *pdev)
 {
+#ifdef CONFIG_PPC64
 	struct drm_device *ddev = pci_get_drvdata(pdev);
+#endif
 
 	/* if we are running in a VM, make sure the device
 	 * torn down properly on reboot/shutdown
@@ -356,11 +389,15 @@ radeon_pci_shutdown(struct pci_dev *pdev)
 	if (radeon_device_is_virtual())
 		radeon_pci_remove(pdev);
 
+#ifdef CONFIG_PPC64
 	/* Some adapters need to be suspended before a
-	* shutdown occurs in order to prevent an error
-	* during kexec.
-	*/
+	 * shutdown occurs in order to prevent an error
+	 * during kexec.
+	 * Make this power specific becauase it breaks
+	 * some non-power boards.
+	 */
 	radeon_suspend_kms(ddev, true, true, false);
+#endif
 }
 
 static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 4cf58dbbe439..b2b076606f54 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -296,6 +296,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	uint32_t handle;
 	int r;
 
+	args->addr = untagged_addr(args->addr);
+
 	if (offset_in_page(args->addr | args->size))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 07f7ace42c4b..e85c554eeaa9 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -100,31 +100,6 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	struct radeon_device *rdev;
 	int r, acpi_status;
 
-	if (!radeon_si_support) {
-		switch (flags & RADEON_FAMILY_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
-			dev_info(dev->dev,
-				 "SI support disabled by module param\n");
-			return -ENODEV;
-		}
-	}
-	if (!radeon_cik_support) {
-		switch (flags & RADEON_FAMILY_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
-			dev_info(dev->dev,
-				 "CIK support disabled by module param\n");
-			return -ENODEV;
-		}
-	}
-
 	rdev = kzalloc(sizeof(struct radeon_device), GFP_KERNEL);
 	if (rdev == NULL) {
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
index ae07290bba6a..04efa78d70b6 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
@@ -147,7 +147,7 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct drm_framebuffer *fb;
 
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	fb = conn_state->writeback_job->fb;
@@ -221,7 +221,7 @@ void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
 	unsigned int i;
 
 	state = rcrtc->writeback.base.state;
-	if (!state || !state->writeback_job || !state->writeback_job->fb)
+	if (!state || !state->writeback_job)
 		return;
 
 	fb = state->writeback_job->fb;
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 2f821c58007c..613404f86668 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -39,8 +39,6 @@
 #include "rockchip_drm_vop.h"
 #include "rockchip_rgb.h"
 
-#define VOP_SELF_REFRESH_ENTRY_DELAY_MS 100
-
 #define VOP_WIN_SET(vop, win, name, v) \
 		vop_reg_set(vop, &win->phy->name, win->base, ~0, v, #name)
 #define VOP_SCL_SET(vop, win, name, v) \
@@ -1563,8 +1561,7 @@ static int vop_create_crtc(struct vop *vop)
 	init_completion(&vop->line_flag_completion);
 	crtc->port = port;
 
-	ret = drm_self_refresh_helper_init(crtc,
-					   VOP_SELF_REFRESH_ENTRY_DELAY_MS);
+	ret = drm_self_refresh_helper_init(crtc);
 	if (ret)
 		DRM_DEV_DEBUG_KMS(vop->dev,
 			"Failed to init %s with SR helpers %d, ignoring\n",
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74d82dc..f39b97ed4ade 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
+	struct dma_fence *fence;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		dma_fence_put(s_job->s_fence->parent);
-		s_job->s_fence->parent = sched->ops->run_job(s_job);
+		fence = sched->ops->run_job(s_job);
+
+		if (IS_ERR_OR_NULL(fence)) {
+			s_job->s_fence->parent = NULL;
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+		} else {
+			s_job->s_fence->parent = fence;
+		}
+
+
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		if (fence) {
+		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
 						   drm_sched_process_job);
@@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else
+		} else {
+
+			dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 			drm_sched_process_job(NULL, &sched_job->cb);
+		}
 
 		wake_up(&sched->job_scheduled);
 	}
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 525dc1c0f1c1..530edb3b51cc 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -7,6 +7,7 @@
 #include <linux/gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 
 #include <drm/drm_atomic_helper.h>
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 504763423d46..a46ac284dd5e 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -63,7 +63,6 @@ config TINYDRM_REPAPER
 	depends on DRM && SPI
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
-	depends on THERMAL || !THERMAL
 	help
 	  DRM driver for the following Pervasive Displays panels:
 	  1.44" TFT EPD Panel (E1144CS021)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20ff56f27aa4..98819462f025 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -185,8 +185,9 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
 	kref_get(&bo->list_kref);
 
-	if (bo->ttm && !(bo->ttm->page_flags &
-			 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
+	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
+	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
+				     TTM_PAGE_FLAG_SWAPPED))) {
 		list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]);
 		kref_get(&bo->list_kref);
 	}
@@ -878,11 +879,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	if (!bo) {
 		if (busy_bo)
-			ttm_bo_get(busy_bo);
+			kref_get(&busy_bo->list_kref);
 		spin_unlock(&glob->lru_lock);
 		ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
 		if (busy_bo)
-			ttm_bo_put(busy_bo);
+			kref_put(&busy_bo->list_kref, ttm_bo_release_list);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 76eedb963693..46dc3de7e81b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -278,15 +278,13 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		else
 			ret = vmf_insert_pfn(&cvma, address, pfn);
 
-		/*
-		 * Somebody beat us to this PTE or prefaulting to
-		 * an already populated PTE, or prefaulting error.
-		 */
-
-		if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
-			break;
-		else if (unlikely(ret & VM_FAULT_ERROR))
-			goto out_io_unlock;
+		/* Never error on prefaulted PTEs */
+		if (unlikely((ret & VM_FAULT_ERROR))) {
+			if (i == 0)
+				goto out_io_unlock;
+			else
+				break;
+		}
 
 		address += PAGE_SIZE;
 		if (unlikely(++page_offset >= page_last))
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 5d80507b539b..19c092d75266 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -557,13 +557,16 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	if (args->bcl_start != args->bcl_end) {
 		bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
-		if (!bin)
+		if (!bin) {
+			v3d_job_put(&render->base);
 			return -ENOMEM;
+		}
 
 		ret = v3d_job_init(v3d, file_priv, &bin->base,
 				   v3d_job_free, args->in_sync_bcl);
 		if (ret) {
 			v3d_job_put(&render->base);
+			kfree(bin);
 			return ret;
 		}
 
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index 1ce4d7142b6e..bf720206727f 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -231,7 +231,7 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
 	int i;
 
 	conn_state = drm_atomic_get_new_connector_state(state, conn);
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc);
@@ -271,8 +271,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 	u32 ctrl;
 	int i;
 
-	if (WARN_ON(!conn_state->writeback_job ||
-		    !conn_state->writeback_job->fb))
+	if (WARN_ON(!conn_state->writeback_job))
 		return;
 
 	mode = &conn_state->crtc->state->adjusted_mode;
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index feaa538026a0..3db000aacd26 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -174,7 +174,6 @@ via_map_blit_for_device(struct pci_dev *pdev,
 static void
 via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 {
-	struct page *page;
 	int i;
 
 	switch (vsg->state) {
@@ -189,13 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 		kfree(vsg->desc_pages);
 		/* fall through */
 	case dr_via_pages_locked:
-		for (i = 0; i < vsg->num_pages; ++i) {
-			if (NULL != (page = vsg->pages[i])) {
-				if (!PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction))
-					SetPageDirty(page);
-				put_page(page);
-			}
-		}
+		put_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
+					  (vsg->direction == DMA_FROM_DEVICE));
 		/* fall through */
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index ba1828acd8c9..4be49c1aef51 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -718,17 +718,9 @@ static int xen_drv_probe(struct xenbus_device *xb_dev,
 	struct device *dev = &xb_dev->dev;
 	int ret;
 
-	/*
-	 * The device is not spawn from a device tree, so arch_setup_dma_ops
-	 * is not called, thus leaving the device with dummy DMA ops.
-	 * This makes the device return error on PRIME buffer import, which
-	 * is not correct: to fix this call of_dma_configure() with a NULL
-	 * node to set default DMA ops.
-	 */
-	dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	ret = of_dma_configure(dev, NULL, true);
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret < 0) {
-		DRM_ERROR("Cannot setup DMA ops, ret %d", ret);
+		DRM_ERROR("Cannot setup DMA mask, ret %d", ret);
 		return ret;
 	}