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

Roll -rc3 and current drm/fixes in.

This will also unstuck our for-next branch.

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

36 files changed, 222 insertions, 138 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 8975cf41a91a..48ad0c04aa72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -196,7 +196,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 			return -EINVAL;
 
 		vram_size = KFD_XCP_MEMORY_SIZE(adev, xcp_id);
-		if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+		if (adev->flags & AMD_IS_APU) {
 			system_mem_needed = size;
 			ttm_mem_needed = size;
 		}
@@ -233,7 +233,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	if (adev && xcp_id >= 0) {
 		adev->kfd.vram_used[xcp_id] += vram_needed;
 		adev->kfd.vram_used_aligned[xcp_id] +=
-				(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ?
+				(adev->flags & AMD_IS_APU) ?
 				vram_needed :
 				ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
 	}
@@ -261,7 +261,7 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 
 		if (adev) {
 			adev->kfd.vram_used[xcp_id] -= size;
-			if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+			if (adev->flags & AMD_IS_APU) {
 				adev->kfd.vram_used_aligned[xcp_id] -= size;
 				kfd_mem_limit.system_mem_used -= size;
 				kfd_mem_limit.ttm_mem_used -= size;
@@ -890,7 +890,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 	 * if peer device has large BAR. In contrast, access over xGMI is
 	 * allowed for both small and large BAR configurations of peer device
 	 */
-	if ((adev != bo_adev && !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)) &&
+	if ((adev != bo_adev && !(adev->flags & AMD_IS_APU)) &&
 	    ((mem->domain == AMDGPU_GEM_DOMAIN_VRAM) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) {
@@ -1658,7 +1658,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 		- atomic64_read(&adev->vram_pin_size)
 		- reserved_for_pt;
 
-	if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+	if (adev->flags & AMD_IS_APU) {
 		system_mem_available = no_system_mem_limit ?
 					kfd_mem_limit.max_system_mem_limit :
 					kfd_mem_limit.max_system_mem_limit -
@@ -1706,7 +1706,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-		if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+		if (adev->flags & AMD_IS_APU) {
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_flags = 0;
@@ -1953,7 +1953,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	if (size) {
 		if (!is_imported &&
 		   (mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_VRAM ||
-		   ((adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) &&
+		   ((adev->flags & AMD_IS_APU) &&
 		    mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT)))
 			*size = bo_size;
 		else
@@ -2376,7 +2376,7 @@ static int import_obj_create(struct amdgpu_device *adev,
 	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) &&
-			 !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ?
+			 !(adev->flags & AMD_IS_APU) ?
 			 AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
 
 	(*mem)->mapped_to_gpu_memory = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 861ccff78af9..932dc93b2e63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5944,13 +5944,18 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev,
 	*speed = PCI_SPEED_UNKNOWN;
 	*width = PCIE_LNK_WIDTH_UNKNOWN;
 
-	while ((parent = pci_upstream_bridge(parent))) {
-		/* skip upstream/downstream switches internal to dGPU*/
-		if (parent->vendor == PCI_VENDOR_ID_ATI)
-			continue;
-		*speed = pcie_get_speed_cap(parent);
-		*width = pcie_get_width_cap(parent);
-		break;
+	if (amdgpu_device_pcie_dynamic_switching_supported(adev)) {
+		while ((parent = pci_upstream_bridge(parent))) {
+			/* skip upstream/downstream switches internal to dGPU*/
+			if (parent->vendor == PCI_VENDOR_ID_ATI)
+				continue;
+			*speed = pcie_get_speed_cap(parent);
+			*width = pcie_get_width_cap(parent);
+			break;
+		}
+	} else {
+		/* use the current speeds rather than max if switching is not supported */
+		pcie_bandwidth_available(adev->pdev, NULL, speed, width);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index c8980d5f6540..7021c4a66fb5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -46,7 +46,7 @@ struct amdgpu_iv_entry;
 #define AMDGPU_RAS_GPU_ERR_HBM_BIST_TEST(x)		AMDGPU_GET_REG_FIELD(x, 7, 7)
 #define AMDGPU_RAS_GPU_ERR_SOCKET_ID(x)			AMDGPU_GET_REG_FIELD(x, 10, 8)
 #define AMDGPU_RAS_GPU_ERR_AID_ID(x)			AMDGPU_GET_REG_FIELD(x, 12, 11)
-#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 13, 13)
+#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 14, 13)
 #define AMDGPU_RAS_GPU_ERR_BOOT_STATUS(x)		AMDGPU_GET_REG_FIELD(x, 31, 31)
 
 #define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT	1000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 7fdd306a48a0..f07647a9a9d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -706,11 +706,15 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params,
 			 struct amdgpu_vm_bo_base *entry)
 {
 	struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry);
-	struct amdgpu_bo *bo = parent->bo, *pbo;
+	struct amdgpu_bo *bo, *pbo;
 	struct amdgpu_vm *vm = params->vm;
 	uint64_t pde, pt, flags;
 	unsigned int level;
 
+	if (WARN_ON(!parent))
+		return -EINVAL;
+
+	bo = parent->bo;
 	for (level = 0, pbo = bo->parent; pbo; ++level)
 		pbo = pbo->parent;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 414ea3f560a7..d4e2aed2efa3 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -422,7 +422,7 @@ __aqua_vanjaram_get_auto_mode(struct amdgpu_xcp_mgr *xcp_mgr)
 
 	if (adev->gmc.num_mem_partitions == num_xcc / 2)
 		return (adev->flags & AMD_IS_APU) ? AMDGPU_TPX_PARTITION_MODE :
-						    AMDGPU_QPX_PARTITION_MODE;
+						    AMDGPU_CPX_PARTITION_MODE;
 
 	if (adev->gmc.num_mem_partitions == 2 && !(adev->flags & AMD_IS_APU))
 		return AMDGPU_DPX_PARTITION_MODE;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9596bca57212..afc57df421cd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -408,15 +408,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 			f2g = &gfx_v11_kfd2kgd;
 			break;
 		case IP_VERSION(11, 0, 3):
-			if ((adev->pdev->device == 0x7460 &&
-			     adev->pdev->revision == 0x00) ||
-			    (adev->pdev->device == 0x7461 &&
-			     adev->pdev->revision == 0x00))
-				/* Note: Compiler version is 11.0.5 while HW version is 11.0.3 */
-				gfx_target_version = 110005;
-			else
-				/* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */
-				gfx_target_version = 110001;
+			/* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */
+			gfx_target_version = 110001;
 			f2g = &gfx_v11_kfd2kgd;
 			break;
 		case IP_VERSION(11, 5, 0):
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 4816fcb9803a..8ee3d07ffbdf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -1023,7 +1023,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 0, 1))
 		return -EINVAL;
 
-	if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)
+	if (adev->flags & AMD_IS_APU)
 		return 0;
 
 	pgmap = &kfddev->pgmap;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 069b81eeea03..31e500859ab0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2619,8 +2619,7 @@ svm_range_best_restore_location(struct svm_range *prange,
 		return -1;
 	}
 
-	if (node->adev->gmc.is_app_apu ||
-	    node->adev->flags & AMD_IS_APU)
+	if (node->adev->flags & AMD_IS_APU)
 		return 0;
 
 	if (prange->preferred_loc == gpuid ||
@@ -3338,8 +3337,7 @@ svm_range_best_prefetch_location(struct svm_range *prange)
 		goto out;
 	}
 
-	if (bo_node->adev->gmc.is_app_apu ||
-	    bo_node->adev->flags & AMD_IS_APU) {
+	if (bo_node->adev->flags & AMD_IS_APU) {
 		best_loc = 0;
 		goto out;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 9c37bd0567ef..70c1776611c4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -201,7 +201,6 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s
  * is initialized to not 0 when page migration register device memory.
  */
 #define KFD_IS_SVM_API_SUPPORTED(adev) ((adev)->kfd.pgmap.type != 0 ||\
-					(adev)->gmc.is_app_apu ||\
 					((adev)->flags & AMD_IS_APU))
 
 void svm_range_bo_unref_async(struct svm_range_bo *svm_bo);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 35733d5c5193..a5e1a93ddaea 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -613,6 +613,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		&connector->base,
 		dev->mode_config.tile_property,
 		0);
+	connector->colorspace_property = master->base.colorspace_property;
+	if (connector->colorspace_property)
+		drm_connector_attach_colorspace_property(connector);
 
 	drm_connector_set_path_property(connector, pathprop);
 
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 1acb2d2c5597..571691837200 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -3583,7 +3583,7 @@ struct atom_gpio_voltage_object_v4
    uint8_t  phase_delay_us;                      // phase delay in unit of micro second
    uint8_t  reserved;   
    uint32_t gpio_mask_val;                         // GPIO Mask value
-   struct atom_voltage_gpio_map_lut voltage_gpio_lut[1];
+   struct atom_voltage_gpio_map_lut voltage_gpio_lut[] __counted_by(gpio_entry_num);
 };
 
 struct  atom_svid2_voltage_object_v4
diff --git a/drivers/gpu/drm/amd/include/pptable.h b/drivers/gpu/drm/amd/include/pptable.h
index 2e8e6c9875f6..f83ace2d7ec3 100644
--- a/drivers/gpu/drm/amd/include/pptable.h
+++ b/drivers/gpu/drm/amd/include/pptable.h
@@ -477,31 +477,30 @@ typedef struct _ATOM_PPLIB_STATE_V2
 } ATOM_PPLIB_STATE_V2;
 
 typedef struct _StateArray{
-    //how many states we have 
-    UCHAR ucNumEntries;
-    
-    ATOM_PPLIB_STATE_V2 states[1];
+	//how many states we have
+	UCHAR ucNumEntries;
+
+	ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */;
 }StateArray;
 
 
 typedef struct _ClockInfoArray{
-    //how many clock levels we have
-    UCHAR ucNumEntries;
-    
-    //sizeof(ATOM_PPLIB_CLOCK_INFO)
-    UCHAR ucEntrySize;
-    
-    UCHAR clockInfo[];
+	//how many clock levels we have
+	UCHAR ucNumEntries;
+
+	//sizeof(ATOM_PPLIB_CLOCK_INFO)
+	UCHAR ucEntrySize;
+
+	UCHAR clockInfo[];
 }ClockInfoArray;
 
 typedef struct _NonClockInfoArray{
+	//how many non-clock levels we have. normally should be same as number of states
+	UCHAR ucNumEntries;
+	//sizeof(ATOM_PPLIB_NONCLOCK_INFO)
+	UCHAR ucEntrySize;
 
-    //how many non-clock levels we have. normally should be same as number of states
-    UCHAR ucNumEntries;
-    //sizeof(ATOM_PPLIB_NONCLOCK_INFO)
-    UCHAR ucEntrySize;
-    
-    ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[];
+	ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries);
 }NonClockInfoArray;
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
@@ -513,8 +512,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Table
 {
-    UCHAR ucNumEntries;                                                // Number of entries.
-    ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[1];             // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_Clock_Voltage_Dependency_Table;
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record
@@ -529,8 +530,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Table
 {
-    UCHAR ucNumEntries;                                                // Number of entries.
-    ATOM_PPLIB_Clock_Voltage_Limit_Record entries[1];                  // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_Clock_Voltage_Limit_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_Clock_Voltage_Limit_Table;
 
 union _ATOM_PPLIB_CAC_Leakage_Record
@@ -553,8 +556,10 @@ typedef union _ATOM_PPLIB_CAC_Leakage_Record ATOM_PPLIB_CAC_Leakage_Record;
 
 typedef struct _ATOM_PPLIB_CAC_Leakage_Table
 {
-    UCHAR ucNumEntries;                                                 // Number of entries.
-    ATOM_PPLIB_CAC_Leakage_Record entries[1];                           // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_CAC_Leakage_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_CAC_Leakage_Table;
 
 typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record
@@ -568,8 +573,10 @@ typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record
 
 typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Table
 {
-    UCHAR ucNumEntries;                                                 // Number of entries.
-    ATOM_PPLIB_PhaseSheddingLimits_Record entries[1];                   // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_PhaseSheddingLimits_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_PhaseSheddingLimits_Table;
 
 typedef struct _VCEClockInfo{
@@ -580,8 +587,8 @@ typedef struct _VCEClockInfo{
 }VCEClockInfo;
 
 typedef struct _VCEClockInfoArray{
-    UCHAR ucNumEntries;
-    VCEClockInfo entries[1];
+	UCHAR ucNumEntries;
+	VCEClockInfo entries[] __counted_by(ucNumEntries);
 }VCEClockInfoArray;
 
 typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record
@@ -592,8 +599,8 @@ typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record
 
 typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table
 {
-    UCHAR numEntries;
-    ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_VCE_State_Record
@@ -604,8 +611,8 @@ typedef struct _ATOM_PPLIB_VCE_State_Record
 
 typedef struct _ATOM_PPLIB_VCE_State_Table
 {
-    UCHAR numEntries;
-    ATOM_PPLIB_VCE_State_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_VCE_State_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_VCE_State_Table;
 
 
@@ -626,8 +633,8 @@ typedef struct _UVDClockInfo{
 }UVDClockInfo;
 
 typedef struct _UVDClockInfoArray{
-    UCHAR ucNumEntries;
-    UVDClockInfo entries[1];
+	UCHAR ucNumEntries;
+	UVDClockInfo entries[] __counted_by(ucNumEntries);
 }UVDClockInfoArray;
 
 typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record
@@ -638,8 +645,8 @@ typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record
 
 typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table
 {
-    UCHAR numEntries;
-    ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_UVD_Table
@@ -657,8 +664,8 @@ typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Record
 }ATOM_PPLIB_SAMClk_Voltage_Limit_Record;
 
 typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Table{
-    UCHAR numEntries;
-    ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[];
+	UCHAR numEntries;
+	ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_SAMClk_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_SAMU_Table
@@ -675,8 +682,8 @@ typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Record
 }ATOM_PPLIB_ACPClk_Voltage_Limit_Record;
 
 typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Table{
-    UCHAR numEntries;
-    ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_ACPClk_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_ACP_Table
@@ -743,9 +750,9 @@ typedef struct ATOM_PPLIB_VQ_Budgeting_Record{
 } ATOM_PPLIB_VQ_Budgeting_Record;
 
 typedef struct ATOM_PPLIB_VQ_Budgeting_Table {
-    UCHAR revid;
-    UCHAR numEntries;
-    ATOM_PPLIB_VQ_Budgeting_Record         entries[1];
+	UCHAR revid;
+	UCHAR numEntries;
+	ATOM_PPLIB_VQ_Budgeting_Record entries[] __counted_by(numEntries);
 } ATOM_PPLIB_VQ_Budgeting_Table;
 
 #pragma pack()
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
index bc241b593db1..b6257f34a7c6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
@@ -226,15 +226,17 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en)
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	if (!en && adev->in_s4) {
-		/* Adds a GFX reset as workaround just before sending the
-		 * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering
-		 * an invalid state.
-		 */
-		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset,
-						      SMU_RESET_MODE_2, NULL);
-		if (ret)
-			return ret;
+	if (!en && !adev->in_s0ix) {
+		if (adev->in_s4) {
+			/* Adds a GFX reset as workaround just before sending the
+			 * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering
+			 * an invalid state.
+			 */
+			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset,
+							      SMU_RESET_MODE_2, NULL);
+			if (ret)
+				return ret;
+		}
 
 		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL);
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 706265220292..90703f4542ab 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1562,7 +1562,6 @@ static int smu_v14_0_2_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v14_0_2_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
index d8e449e6ebda..50cb8f7ee6b2 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
@@ -72,11 +72,6 @@ struct gamma_curve_sector {
 	u32 segment_width;
 };
 
-struct gamma_curve_segment {
-	u32 start;
-	u32 end;
-};
-
 static struct gamma_curve_sector sector_tbl[] = {
 	{ 0,    4,  4   },
 	{ 16,   4,  4   },
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index f48c4343f469..3e6d4c6aa877 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -285,7 +285,6 @@ struct platform_driver dp_driver = {
 	.remove_new	= exynos_dp_remove,
 	.driver		= {
 		.name	= "exynos-dp",
-		.owner	= THIS_MODULE,
 		.pm	= pm_ptr(&exynos_dp_pm_ops),
 		.of_match_table = exynos_dp_match,
 	},
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index fab135308b70..11a720fef32b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector)
 	struct vidi_context *ctx = ctx_from_connector(connector);
 	struct edid *edid;
 	int edid_len;
+	int count;
 
 	/*
 	 * the edid data comes from user side and it would be set
@@ -328,7 +329,11 @@ static int vidi_get_modes(struct drm_connector *connector)
 
 	drm_connector_update_edid_property(connector, edid);
 
-	return drm_add_edid_modes(connector, edid);
+	count = drm_add_edid_modes(connector, edid);
+
+	kfree(edid);
+
+	return count;
 }
 
 static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index e968824a4c72..1e26cd4f8347 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (!hdata->ddc_adpt)
-		return 0;
+		goto no_edid;
 
 	edid = drm_get_edid(connector, hdata->ddc_adpt);
 	if (!edid)
-		return 0;
+		goto no_edid;
 
 	hdata->dvi_mode = !connector->display_info.is_hdmi;
 	DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n",
@@ -906,6 +906,9 @@ static int hdmi_get_modes(struct drm_connector *connector)
 	kfree(edid);
 
 	return ret;
+
+no_edid:
+	return drm_add_modes_noedid(connector, 640, 480);
 }
 
 static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock)
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index ed81e1466c4b..40e7d862675e 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -1252,17 +1252,6 @@ static const struct component_ops i915_audio_component_bind_ops = {
 static void i915_audio_component_init(struct drm_i915_private *i915)
 {
 	u32 aud_freq, aud_freq_init;
-	int ret;
-
-	ret = component_add_typed(i915->drm.dev,
-				  &i915_audio_component_bind_ops,
-				  I915_COMPONENT_AUDIO);
-	if (ret < 0) {
-		drm_err(&i915->drm,
-			"failed to add audio component (%d)\n", ret);
-		/* continue with reduced functionality */
-		return;
-	}
 
 	if (DISPLAY_VER(i915) >= 9) {
 		aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL);
@@ -1285,6 +1274,21 @@ static void i915_audio_component_init(struct drm_i915_private *i915)
 
 	/* init with current cdclk */
 	intel_audio_cdclk_change_post(i915);
+}
+
+static void i915_audio_component_register(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = component_add_typed(i915->drm.dev,
+				  &i915_audio_component_bind_ops,
+				  I915_COMPONENT_AUDIO);
+	if (ret < 0) {
+		drm_err(&i915->drm,
+			"failed to add audio component (%d)\n", ret);
+		/* continue with reduced functionality */
+		return;
+	}
 
 	i915->display.audio.component_registered = true;
 }
@@ -1317,6 +1321,12 @@ void intel_audio_init(struct drm_i915_private *i915)
 		i915_audio_component_init(i915);
 }
 
+void intel_audio_register(struct drm_i915_private *i915)
+{
+	if (!i915->display.audio.lpe.platdev)
+		i915_audio_component_register(i915);
+}
+
 /**
  * intel_audio_deinit() - deinitialize the audio driver
  * @i915: the i915 drm device private data
diff --git a/drivers/gpu/drm/i915/display/intel_audio.h b/drivers/gpu/drm/i915/display/intel_audio.h
index 9327954b801e..576c061d72a4 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.h
+++ b/drivers/gpu/drm/i915/display/intel_audio.h
@@ -28,6 +28,7 @@ void intel_audio_codec_get_config(struct intel_encoder *encoder,
 void intel_audio_cdclk_change_pre(struct drm_i915_private *dev_priv);
 void intel_audio_cdclk_change_post(struct drm_i915_private *dev_priv);
 void intel_audio_init(struct drm_i915_private *dev_priv);
+void intel_audio_register(struct drm_i915_private *i915);
 void intel_audio_deinit(struct drm_i915_private *dev_priv);
 void intel_audio_sdp_split_update(const struct intel_crtc_state *crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c
index 89bd032ed995..794b4af38055 100644
--- a/drivers/gpu/drm/i915/display/intel_display_driver.c
+++ b/drivers/gpu/drm/i915/display/intel_display_driver.c
@@ -540,6 +540,8 @@ void intel_display_driver_register(struct drm_i915_private *i915)
 
 	intel_display_driver_enable_user_access(i915);
 
+	intel_audio_register(i915);
+
 	intel_display_debugfs_register(i915);
 
 	/*
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 42619fc05de4..090724fa766c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -255,6 +255,7 @@ struct i915_execbuffer {
 	struct intel_context *context; /* logical state for the request */
 	struct i915_gem_context *gem_context; /** caller's context */
 	intel_wakeref_t wakeref;
+	intel_wakeref_t wakeref_gt0;
 
 	/** our requests to build */
 	struct i915_request *requests[MAX_ENGINE_INSTANCE + 1];
@@ -2685,6 +2686,7 @@ static int
 eb_select_engine(struct i915_execbuffer *eb)
 {
 	struct intel_context *ce, *child;
+	struct intel_gt *gt;
 	unsigned int idx;
 	int err;
 
@@ -2708,10 +2710,17 @@ eb_select_engine(struct i915_execbuffer *eb)
 		}
 	}
 	eb->num_batches = ce->parallel.number_children + 1;
+	gt = ce->engine->gt;
 
 	for_each_child(ce, child)
 		intel_context_get(child);
 	eb->wakeref = intel_gt_pm_get(ce->engine->gt);
+	/*
+	 * Keep GT0 active on MTL so that i915_vma_parked() doesn't
+	 * free VMAs while execbuf ioctl is validating VMAs.
+	 */
+	if (gt->info.id)
+		eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915));
 
 	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
 		err = intel_context_alloc_state(ce);
@@ -2750,6 +2759,9 @@ eb_select_engine(struct i915_execbuffer *eb)
 	return err;
 
 err:
+	if (gt->info.id)
+		intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0);
+
 	intel_gt_pm_put(ce->engine->gt, eb->wakeref);
 	for_each_child(ce, child)
 		intel_context_put(child);
@@ -2763,6 +2775,12 @@ eb_put_engine(struct i915_execbuffer *eb)
 	struct intel_context *child;
 
 	i915_vm_put(eb->context->vm);
+	/*
+	 * This works in conjunction with eb_select_engine() to prevent
+	 * i915_vma_parked() from interfering while execbuf validates vmas.
+	 */
+	if (eb->gt->info.id)
+		intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0);
 	intel_gt_pm_put(eb->context->engine->gt, eb->wakeref);
 	for_each_child(eb->context, child)
 		intel_context_put(child);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 3560a062d287..5d7446a48ae7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -284,7 +284,9 @@ bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj);
 static inline bool
 i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj)
 {
-	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE);
+	/* TODO: make DPT shrinkable when it has no bound vmas */
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE) &&
+		!obj->is_dpt;
 }
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index 65a931ea80e9..3527b8f446fe 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -196,7 +196,7 @@ static int verify_access(struct drm_i915_private *i915,
 	if (err)
 		goto out_file;
 
-	mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, true);
+	mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, false);
 	vaddr = i915_gem_object_pin_map_unlocked(native_obj, mode);
 	if (IS_ERR(vaddr)) {
 		err = PTR_ERR(vaddr);
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index d650beb8ed22..20b9b04ec1e0 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -263,8 +263,13 @@ static void signal_irq_work(struct irq_work *work)
 		i915_request_put(rq);
 	}
 
+	/* Lazy irq enabling after HW submission */
 	if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers))
 		intel_breadcrumbs_arm_irq(b);
+
+	/* And confirm that we still want irqs enabled before we yield */
+	if (READ_ONCE(b->irq_armed) && !atomic_read(&b->active))
+		intel_breadcrumbs_disarm_irq(b);
 }
 
 struct intel_breadcrumbs *
@@ -315,13 +320,7 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b)
 		return;
 
 	/* Kick the work once more to drain the signalers, and disarm the irq */
-	irq_work_sync(&b->irq_work);
-	while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) {
-		local_irq_disable();
-		signal_irq_work(&b->irq_work);
-		local_irq_enable();
-		cond_resched();
-	}
+	irq_work_queue(&b->irq_work);
 }
 
 void intel_breadcrumbs_free(struct kref *kref)
@@ -404,7 +403,7 @@ static void insert_breadcrumb(struct i915_request *rq)
 	 * the request as it may have completed and raised the interrupt as
 	 * we were attaching it into the lists.
 	 */
-	if (!b->irq_armed || __i915_request_is_complete(rq))
+	if (!READ_ONCE(b->irq_armed) || __i915_request_is_complete(rq))
 		irq_work_queue(&b->irq_work);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5c8e9ee3b008..3b740ca25000 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -885,6 +885,12 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 	if (IS_DG2(gt->i915)) {
 		u8 first_ccs = __ffs(CCS_MASK(gt));
 
+		/*
+		 * Store the number of active cslices before
+		 * changing the CCS engine configuration
+		 */
+		gt->ccs.cslices = CCS_MASK(gt);
+
 		/* Mask off all the CCS engine */
 		info->engine_mask &= ~GENMASK(CCS3, CCS0);
 		/* Put back in the first CCS engine */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
index 99b71bb7da0a..3c62a44e9106 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -19,7 +19,7 @@ unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt)
 
 	/* Build the value for the fixed CCS load balancing */
 	for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
-		if (CCS_MASK(gt) & BIT(cslice))
+		if (gt->ccs.cslices & BIT(cslice))
 			/*
 			 * If available, assign the cslice
 			 * to the first available engine...
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index def7dd0eb6f1..cfdd2ad5e954 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -207,6 +207,14 @@ struct intel_gt {
 					    [MAX_ENGINE_INSTANCE + 1];
 	enum intel_submission_method submission_method;
 
+	struct {
+		/*
+		 * Mask of the non fused CCS slices
+		 * to be used for the load balancing
+		 */
+		intel_engine_mask_t cslices;
+	} ccs;
+
 	/*
 	 * Default address space (either GGTT or ppGTT depending on arch).
 	 *
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
index bebf28e3c479..525587cfe1af 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
@@ -29,9 +29,9 @@
  */
 
 #define GUC_KLV_LEN_MIN				1u
-#define GUC_KLV_0_KEY				(0xffff << 16)
-#define GUC_KLV_0_LEN				(0xffff << 0)
-#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+#define GUC_KLV_0_KEY				(0xffffu << 16)
+#define GUC_KLV_0_LEN				(0xffffu << 0)
+#define GUC_KLV_n_VALUE				(0xffffffffu << 0)
 
 /**
  * DOC: GuC Self Config KLVs
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index 8fc0f3f6ecc5..944770fb2daf 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -147,6 +147,13 @@ static const struct attribute *gt_idle_attrs[] = {
 static void gt_idle_sysfs_fini(struct drm_device *drm, void *arg)
 {
 	struct kobject *kobj = arg;
+	struct xe_gt *gt = kobj_to_gt(kobj->parent);
+
+	if (gt_to_xe(gt)->info.skip_guc_pc) {
+		XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FW_GT));
+		xe_gt_idle_disable_c6(gt);
+		xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+	}
 
 	sysfs_remove_files(kobj, gt_idle_attrs);
 	kobject_put(kobj);
@@ -199,7 +206,7 @@ void xe_gt_idle_enable_c6(struct xe_gt *gt)
 void xe_gt_idle_disable_c6(struct xe_gt *gt)
 {
 	xe_device_assert_mem_access(gt_to_xe(gt));
-	xe_force_wake_assert_held(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);
 
 	xe_mmio_write32(gt, PG_ENABLE, 0);
 	xe_mmio_write32(gt, RC_CONTROL, 0);
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 79116ad58620..6c2cfc54442c 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1274,6 +1274,9 @@ static void pf_reset_vf_lmtt(struct xe_device *xe, unsigned int vfid)
 	struct xe_tile *tile;
 	unsigned int tid;
 
+	xe_assert(xe, IS_DGFX(xe));
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
 	for_each_tile(tile, xe, tid) {
 		lmtt = &tile->sriov.pf.lmtt;
 		xe_lmtt_drop_pages(lmtt, vfid);
@@ -1292,6 +1295,9 @@ static int pf_update_vf_lmtt(struct xe_device *xe, unsigned int vfid)
 	unsigned int tid;
 	int err;
 
+	xe_assert(xe, IS_DGFX(xe));
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
 	total = 0;
 	for_each_tile(tile, xe, tid)
 		total += pf_get_vf_config_lmem(tile->primary_gt, vfid);
@@ -1337,6 +1343,7 @@ fail:
 
 static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config)
 {
+	xe_gt_assert(gt, IS_DGFX(gt_to_xe(gt)));
 	xe_gt_assert(gt, !xe_gt_is_media_type(gt));
 	lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
 
@@ -1355,6 +1362,7 @@ static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size)
 	int err;
 
 	xe_gt_assert(gt, vfid);
+	xe_gt_assert(gt, IS_DGFX(xe));
 	xe_gt_assert(gt, !xe_gt_is_media_type(gt));
 
 	size = round_up(size, pf_get_lmem_alignment(gt));
@@ -1745,10 +1753,14 @@ static void pf_reset_config_sched(struct xe_gt *gt, struct xe_gt_sriov_config *c
 static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid)
 {
 	struct xe_gt_sriov_config *config = pf_pick_vf_config(gt, vfid);
+	struct xe_device *xe = gt_to_xe(gt);
 
 	if (!xe_gt_is_media_type(gt)) {
 		pf_release_vf_config_ggtt(gt, config);
-		pf_release_vf_config_lmem(gt, config);
+		if (IS_DGFX(xe)) {
+			pf_release_vf_config_lmem(gt, config);
+			pf_update_vf_lmtt(xe, vfid);
+		}
 	}
 	pf_release_config_ctxs(gt, config);
 	pf_release_config_dbs(gt, config);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 509649d0e65e..23382ced4ea7 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -895,12 +895,6 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc)
 static void xe_guc_pc_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc_pc *pc = arg;
-	struct xe_device *xe = pc_to_xe(pc);
-
-	if (xe->info.skip_guc_pc) {
-		xe_gt_idle_disable_c6(pc_to_gt(pc));
-		return;
-	}
 
 	XE_WARN_ON(xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL));
 	XE_WARN_ON(xe_guc_pc_gucrc_disable(pc));
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index c7d38469fb46..e4e3658e6a13 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1240,6 +1240,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	return 0;
 
 err_entity:
+	mutex_unlock(&guc->submission_state.lock);
 	xe_sched_entity_fini(&ge->entity);
 err_sched:
 	xe_sched_fini(&ge->sched);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 9f6e9b7f11c8..65e5a3f4c340 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -34,7 +34,6 @@
 #include "xe_sync.h"
 #include "xe_trace.h"
 #include "xe_vm.h"
-#include "xe_wa.h"
 
 /**
  * struct xe_migrate - migrate context.
@@ -300,10 +299,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 }
 
 /*
- * Due to workaround 16017236439, odd instance hardware copy engines are
- * faster than even instance ones.
- * This function returns the mask involving all fast copy engines and the
- * reserved copy engine to be used as logical mask for migrate engine.
  * Including the reserved copy engine is required to avoid deadlocks due to
  * migrate jobs servicing the faults gets stuck behind the job that faulted.
  */
@@ -317,8 +312,7 @@ static u32 xe_migrate_usm_logical_mask(struct xe_gt *gt)
 		if (hwe->class != XE_ENGINE_CLASS_COPY)
 			continue;
 
-		if (!XE_WA(gt, 16017236439) ||
-		    xe_gt_is_usm_hwe(gt, hwe) || hwe->instance & 1)
+		if (xe_gt_is_usm_hwe(gt, hwe))
 			logical_mask |= BIT(hwe->logical_instance);
 	}
 
@@ -369,6 +363,10 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 		if (!hwe || !logical_mask)
 			return ERR_PTR(-EINVAL);
 
+		/*
+		 * XXX: Currently only reserving 1 (likely slow) BCS instance on
+		 * PVC, may want to revisit if performance is needed.
+		 */
 		m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
 					    EXEC_QUEUE_FLAG_KERNEL |
 					    EXEC_QUEUE_FLAG_PERMANENT |
diff --git a/drivers/gpu/drm/xe/xe_pcode.c b/drivers/gpu/drm/xe/xe_pcode.c
index c010ef16fbf5..a5e7da8cf944 100644
--- a/drivers/gpu/drm/xe/xe_pcode.c
+++ b/drivers/gpu/drm/xe/xe_pcode.c
@@ -191,7 +191,7 @@ int xe_pcode_request(struct xe_gt *gt, u32 mbox, u32 request,
 	drm_WARN_ON_ONCE(&gt_to_xe(gt)->drm, timeout_base_ms > 1);
 	preempt_disable();
 	ret = pcode_try_request(gt, mbox, request, reply_mask, reply, &status,
-				true, timeout_base_ms * 1000, true);
+				true, 50 * 1000, true);
 	preempt_enable();
 
 out:
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index d42b3f33bd7a..aca7a9af6e84 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -80,6 +80,16 @@ static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i)
 	return i;
 }
 
+static int emit_flush_dw(u32 *dw, int i)
+{
+	dw[i++] = MI_FLUSH_DW | MI_FLUSH_IMM_DW;
+	dw[i++] = 0;
+	dw[i++] = 0;
+	dw[i++] = 0;
+
+	return i;
+}
+
 static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb,
 			       u32 *dw, int i)
 {
@@ -234,10 +244,12 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
-	if (job->user_fence.used)
+	if (job->user_fence.used) {
+		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
 						job->user_fence.value,
 						dw, i);
+	}
 
 	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
 
@@ -293,10 +305,12 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
-	if (job->user_fence.used)
+	if (job->user_fence.used) {
+		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
 						job->user_fence.value,
 						dw, i);
+	}
 
 	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);