Merge branch 'mana-shared' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Leon Romanovsky says:

====================
net: mana: Allow variable size indirection table

Like we talked, I created new shared branch for this patch:
https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git/log/?h=mana-shared

* 'mana-shared' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
   net: mana: Allow variable size indirection table
====================

Link: https://lore.kernel.org/all/20240612183051.GE4966@unreal
Signed-off-by: Leon Romanovsky <leon@kernel.org>

45 files changed, 310 insertions, 209 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/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 94f8c34fc293..6a8e45e9d0ec 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -239,7 +239,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
 	if (size < chunk_size)
 		return -EINVAL;
 
-	if (chunk_size < PAGE_SIZE)
+	if (chunk_size < SZ_4K)
 		return -EINVAL;
 
 	if (!is_power_of_2(chunk_size))
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 177773bcdbfd..53c003983ad1 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -233,6 +233,8 @@ int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem)
 
 	dma_resv_assert_held(shmem->base.resv);
 
+	drm_WARN_ON(shmem->base.dev, shmem->base.import_attach);
+
 	ret = drm_gem_shmem_get_pages(shmem);
 
 	return ret;
@@ -611,6 +613,9 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct
 		return ret;
 	}
 
+	if (is_cow_mapping(vma->vm_flags))
+		return -EINVAL;
+
 	dma_resv_lock(shmem->base.resv, NULL);
 	ret = drm_gem_shmem_get_pages(shmem);
 	dma_resv_unlock(shmem->base.resv);
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/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
index 7ea244d876ca..9bb997dbb4b9 100644
--- a/drivers/gpu/drm/lima/lima_gem.c
+++ b/drivers/gpu/drm/lima/lima_gem.c
@@ -185,7 +185,7 @@ static int lima_gem_pin(struct drm_gem_object *obj)
 	if (bo->heap_size)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(&bo->base);
+	return drm_gem_shmem_pin_locked(&bo->base);
 }
 
 static int lima_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map)
diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py
index fc3bfdc991d2..3926485bb197 100644
--- a/drivers/gpu/drm/msm/registers/gen_header.py
+++ b/drivers/gpu/drm/msm/registers/gen_header.py
@@ -538,7 +538,7 @@ class Parser(object):
 		self.variants.add(reg.domain)
 
 	def do_validate(self, schemafile):
-		if self.validate == False:
+		if not self.validate:
 			return
 
 		try:
@@ -948,7 +948,8 @@ def main():
 	parser = argparse.ArgumentParser()
 	parser.add_argument('--rnn', type=str, required=True)
 	parser.add_argument('--xml', type=str, required=True)
-	parser.add_argument('--validate', action=argparse.BooleanOptionalAction)
+	parser.add_argument('--validate', default=False, action='store_true')
+	parser.add_argument('--no-validate', dest='validate', action='store_false')
 
 	subparsers = parser.add_subparsers()
 	subparsers.required = True
diff --git a/drivers/gpu/drm/nouveau/nvif/object.c b/drivers/gpu/drm/nouveau/nvif/object.c
index 4d1aaee8fe15..1d19c87eaec1 100644
--- a/drivers/gpu/drm/nouveau/nvif/object.c
+++ b/drivers/gpu/drm/nouveau/nvif/object.c
@@ -142,11 +142,16 @@ nvif_object_mthd(struct nvif_object *object, u32 mthd, void *data, u32 size)
 		struct nvif_ioctl_v0 ioctl;
 		struct nvif_ioctl_mthd_v0 mthd;
 	} *args;
+	u32 args_size;
 	u8 stack[128];
 	int ret;
 
-	if (sizeof(*args) + size > sizeof(stack)) {
-		if (!(args = kmalloc(sizeof(*args) + size, GFP_KERNEL)))
+	if (check_add_overflow(sizeof(*args), size, &args_size))
+		return -ENOMEM;
+
+	if (args_size > sizeof(stack)) {
+		args = kmalloc(args_size, GFP_KERNEL);
+		if (!args)
 			return -ENOMEM;
 	} else {
 		args = (void *)stack;
@@ -157,7 +162,7 @@ nvif_object_mthd(struct nvif_object *object, u32 mthd, void *data, u32 size)
 	args->mthd.method = mthd;
 
 	memcpy(args->mthd.data, data, size);
-	ret = nvif_object_ioctl(object, args, sizeof(*args) + size, NULL);
+	ret = nvif_object_ioctl(object, args, args_size, NULL);
 	memcpy(data, args->mthd.data, size);
 	if (args != (void *)stack)
 		kfree(args);
@@ -276,7 +281,15 @@ nvif_object_ctor(struct nvif_object *parent, const char *name, u32 handle,
 	object->map.size = 0;
 
 	if (parent) {
-		if (!(args = kmalloc(sizeof(*args) + size, GFP_KERNEL))) {
+		u32 args_size;
+
+		if (check_add_overflow(sizeof(*args), size, &args_size)) {
+			nvif_object_dtor(object);
+			return -ENOMEM;
+		}
+
+		args = kmalloc(args_size, GFP_KERNEL);
+		if (!args) {
 			nvif_object_dtor(object);
 			return -ENOMEM;
 		}
@@ -293,8 +306,7 @@ nvif_object_ctor(struct nvif_object *parent, const char *name, u32 handle,
 		args->new.oclass = oclass;
 
 		memcpy(args->new.data, data, size);
-		ret = nvif_object_ioctl(parent, args, sizeof(*args) + size,
-					&object->priv);
+		ret = nvif_object_ioctl(parent, args, args_size, &object->priv);
 		memcpy(data, args->new.data, size);
 		kfree(args);
 		if (ret == 0)
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 982324ef5a41..2ae0eb0638f3 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -340,6 +340,8 @@ config DRM_PANEL_LG_SW43408
 	depends on OF
 	depends on DRM_MIPI_DSI
 	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_DISPLAY_DP_HELPER
+	select DRM_DISPLAY_HELPER
 	help
 	  Say Y here if you want to enable support for LG sw43408 panel.
 	  The panel has a 1080x2160@60Hz resolution and uses 24 bit RGB per
diff --git a/drivers/gpu/drm/panel/panel-lg-sw43408.c b/drivers/gpu/drm/panel/panel-lg-sw43408.c
index 115f4702d59f..2b3a73696dce 100644
--- a/drivers/gpu/drm/panel/panel-lg-sw43408.c
+++ b/drivers/gpu/drm/panel/panel-lg-sw43408.c
@@ -182,7 +182,7 @@ static int sw43408_backlight_update_status(struct backlight_device *bl)
 	return mipi_dsi_dcs_set_display_brightness_large(dsi, brightness);
 }
 
-const struct backlight_ops sw43408_backlight_ops = {
+static const struct backlight_ops sw43408_backlight_ops = {
 	.update_status = sw43408_backlight_update_status,
 };
 
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 88e80fe98112..28bfc48a9127 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -282,15 +282,15 @@ static const struct drm_display_mode et028013dma_mode = {
 static const struct drm_display_mode jt240mhqs_hwt_ek_e3_mode = {
 	.clock = 6000,
 	.hdisplay = 240,
-	.hsync_start = 240 + 28,
-	.hsync_end = 240 + 28 + 10,
-	.htotal = 240 + 28 + 10 + 10,
+	.hsync_start = 240 + 38,
+	.hsync_end = 240 + 38 + 10,
+	.htotal = 240 + 38 + 10 + 10,
 	.vdisplay = 280,
-	.vsync_start = 280 + 8,
-	.vsync_end = 280 + 8 + 4,
-	.vtotal = 280 + 8 + 4 + 4,
-	.width_mm = 43,
-	.height_mm = 37,
+	.vsync_start = 280 + 48,
+	.vsync_end = 280 + 48 + 4,
+	.vtotal = 280 + 48 + 4 + 4,
+	.width_mm = 37,
+	.height_mm = 43,
 	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
 };
 
@@ -643,7 +643,9 @@ static int st7789v_probe(struct spi_device *spi)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to get backlight\n");
 
-	of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation);
+	ret = of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation);
+	if (ret)
+		return dev_err_probe(&spi->dev, ret, "Failed to get orientation\n");
 
 	drm_panel_add(&ctx->panel);
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index d47b40b82b0b..8e0ff3efede7 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -192,7 +192,7 @@ static int panfrost_gem_pin(struct drm_gem_object *obj)
 	if (bo->is_heap)
 		return -EINVAL;
 
-	return drm_gem_shmem_pin(&bo->base);
+	return drm_gem_shmem_pin_locked(&bo->base);
 }
 
 static enum drm_gem_object_status panfrost_gem_status(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index b3be68b03610..dd8fb9f8341a 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -505,8 +505,8 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 	 * Eventually we will have a fully 50% fragmented mm.
 	 */
 
-	mm_size = PAGE_SIZE << max_order;
-	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, PAGE_SIZE),
+	mm_size = SZ_4K << max_order;
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
 			       "buddy_init failed\n");
 
 	KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
@@ -520,7 +520,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 		}
 
 		for (order = top; order--;) {
-			size = get_size(order, PAGE_SIZE);
+			size = get_size(order, mm.chunk_size);
 			KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start,
 									    mm_size, size, size,
 										&tmp, flags),
@@ -534,7 +534,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 		}
 
 		/* There should be one final page for this sub-allocation */
-		size = get_size(0, PAGE_SIZE);
+		size = get_size(0, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM for hole\n");
@@ -544,7 +544,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 
 		list_move_tail(&block->link, &holes);
 
-		size = get_size(top, PAGE_SIZE);
+		size = get_size(top, mm.chunk_size);
 		KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								   size, size, &tmp, flags),
 							  "buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!",
@@ -555,7 +555,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
 
 	/* Nothing larger than blocks of chunk_size now available */
 	for (order = 1; order <= max_order; order++) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								   size, size, &tmp, flags),
 							  "buddy_alloc unexpectedly succeeded at order %d, it should be full!",
@@ -584,14 +584,14 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 	 * page left.
 	 */
 
-	mm_size = PAGE_SIZE << max_order;
-	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, PAGE_SIZE),
+	mm_size = SZ_4K << max_order;
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
 			       "buddy_init failed\n");
 
 	KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
 
 	for (order = 0; order < max_order; order++) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM with order=%d\n",
@@ -604,7 +604,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 	}
 
 	/* And now the last remaining block available */
-	size = get_size(0, PAGE_SIZE);
+	size = get_size(0, mm.chunk_size);
 	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 							    size, size, &tmp, flags),
 						   "buddy_alloc hit -ENOMEM on final alloc\n");
@@ -616,7 +616,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 
 	/* Should be completely full! */
 	for (order = max_order; order--;) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								   size, size, &tmp, flags),
 							  "buddy_alloc unexpectedly succeeded, it should be full!");
@@ -632,7 +632,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 		list_del(&block->link);
 		drm_buddy_free_block(&mm, block);
 
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM with order=%d\n",
@@ -647,7 +647,7 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
 	}
 
 	/* To confirm, now the whole mm should be available */
-	size = get_size(max_order, PAGE_SIZE);
+	size = get_size(max_order, mm.chunk_size);
 	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 							    size, size, &tmp, flags),
 						   "buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
@@ -678,15 +678,15 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
 	 * try to allocate them all.
 	 */
 
-	mm_size = PAGE_SIZE * ((1 << (max_order + 1)) - 1);
+	mm_size = SZ_4K * ((1 << (max_order + 1)) - 1);
 
-	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, PAGE_SIZE),
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
 			       "buddy_init failed\n");
 
 	KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
 
 	for (order = 0; order <= max_order; order++) {
-		size = get_size(order, PAGE_SIZE);
+		size = get_size(order, mm.chunk_size);
 		KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 								    size, size, &tmp, flags),
 							   "buddy_alloc hit -ENOMEM with order=%d\n",
@@ -699,7 +699,7 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
 	}
 
 	/* Should be completely full! */
-	size = get_size(0, PAGE_SIZE);
+	size = get_size(0, mm.chunk_size);
 	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
 							   size, size, &tmp, flags),
 						  "buddy_alloc unexpectedly succeeded, it should be full!");
@@ -716,7 +716,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 	LIST_HEAD(allocated);
 	struct drm_buddy mm;
 
-	KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, size, PAGE_SIZE));
+	KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, size, SZ_4K));
 
 	KUNIT_EXPECT_EQ_MSG(test, mm.max_order, DRM_BUDDY_MAX_ORDER,
 			    "mm.max_order(%d) != %d\n", mm.max_order,
@@ -724,7 +724,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 
 	size = mm.chunk_size << mm.max_order;
 	KUNIT_EXPECT_FALSE(test, drm_buddy_alloc_blocks(&mm, start, size, size,
-							PAGE_SIZE, &allocated, flags));
+							mm.chunk_size, &allocated, flags));
 
 	block = list_first_entry_or_null(&allocated, struct drm_buddy_block, link);
 	KUNIT_EXPECT_TRUE(test, block);
@@ -734,10 +734,10 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 						drm_buddy_block_order(block), mm.max_order);
 
 	KUNIT_EXPECT_EQ_MSG(test, drm_buddy_block_size(&mm, block),
-			    BIT_ULL(mm.max_order) * PAGE_SIZE,
+			    BIT_ULL(mm.max_order) * mm.chunk_size,
 						"block size(%llu) != %llu\n",
 						drm_buddy_block_size(&mm, block),
-						BIT_ULL(mm.max_order) * PAGE_SIZE);
+						BIT_ULL(mm.max_order) * mm.chunk_size);
 
 	drm_buddy_free_list(&mm, &allocated, 0);
 	drm_buddy_fini(&mm);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 8f1730aeacc9..823d8d2da17c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -746,7 +746,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		dev->vram_size = pci_resource_len(pdev, 2);
 
 		drm_info(&dev->drm,
-			"Register MMIO at 0x%pa size is %llu kiB\n",
+			"Register MMIO at 0x%pa size is %llu KiB\n",
 			 &rmmio_start, (uint64_t)rmmio_size / 1024);
 		dev->rmmio = devm_ioremap(dev->drm.dev,
 					  rmmio_start,
@@ -765,7 +765,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		fifo_size = pci_resource_len(pdev, 2);
 
 		drm_info(&dev->drm,
-			 "FIFO at %pa size is %llu kiB\n",
+			 "FIFO at %pa size is %llu KiB\n",
 			 &fifo_start, (uint64_t)fifo_size / 1024);
 		dev->fifo_mem = devm_memremap(dev->drm.dev,
 					      fifo_start,
@@ -790,7 +790,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 	 * SVGA_REG_VRAM_SIZE.
 	 */
 	drm_info(&dev->drm,
-		 "VRAM at %pa size is %llu kiB\n",
+		 "VRAM at %pa size is %llu KiB\n",
 		 &dev->vram_start, (uint64_t)dev->vram_size / 1024);
 
 	return 0;
@@ -960,13 +960,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 				vmw_read(dev_priv,
 					 SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB);
 
-		/*
-		 * Workaround for low memory 2D VMs to compensate for the
-		 * allocation taken by fbdev
-		 */
-		if (!(dev_priv->capabilities & SVGA_CAP_3D))
-			mem_size *= 3;
-
 		dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE;
 		dev_priv->max_primary_mem =
 			vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM);
@@ -991,13 +984,13 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 		dev_priv->max_primary_mem = dev_priv->vram_size;
 	}
 	drm_info(&dev_priv->drm,
-		 "Legacy memory limits: VRAM = %llu kB, FIFO = %llu kB, surface = %u kB\n",
+		 "Legacy memory limits: VRAM = %llu KiB, FIFO = %llu KiB, surface = %u KiB\n",
 		 (u64)dev_priv->vram_size / 1024,
 		 (u64)dev_priv->fifo_mem_size / 1024,
 		 dev_priv->memory_size / 1024);
 
 	drm_info(&dev_priv->drm,
-		 "MOB limits: max mob size = %u kB, max mob pages = %u\n",
+		 "MOB limits: max mob size = %u KiB, max mob pages = %u\n",
 		 dev_priv->max_mob_size / 1024, dev_priv->max_mob_pages);
 
 	ret = vmw_dma_masks(dev_priv);
@@ -1015,7 +1008,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 			 (unsigned)dev_priv->max_gmr_pages);
 	}
 	drm_info(&dev_priv->drm,
-		 "Maximum display memory size is %llu kiB\n",
+		 "Maximum display memory size is %llu KiB\n",
 		 (uint64_t)dev_priv->max_primary_mem / 1024);
 
 	/* Need mmio memory to check for fifo pitchlock cap. */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 4ecaea0026fc..a1ce41e1c468 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1043,9 +1043,6 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 int vmw_kms_write_svga(struct vmw_private *vmw_priv,
 		       unsigned width, unsigned height, unsigned pitch,
 		       unsigned bpp, unsigned depth);
-bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv,
-				uint32_t pitch,
-				uint32_t height);
 int vmw_kms_present(struct vmw_private *dev_priv,
 		    struct drm_file *file_priv,
 		    struct vmw_framebuffer *vfb,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index a0b47c9b33f5..5bd967fbcf55 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -94,14 +94,14 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man,
 			} else
 				new_max_pages = gman->max_gmr_pages * 2;
 			if (new_max_pages > gman->max_gmr_pages && new_max_pages >= gman->used_gmr_pages) {
-				DRM_WARN("vmwgfx: increasing guest mob limits to %u kB.\n",
+				DRM_WARN("vmwgfx: increasing guest mob limits to %u KiB.\n",
 					 ((new_max_pages) << (PAGE_SHIFT - 10)));
 
 				gman->max_gmr_pages = new_max_pages;
 			} else {
 				char buf[256];
 				snprintf(buf, sizeof(buf),
-					 "vmwgfx, error: guest graphics is out of memory (mob limit at: %ukB).\n",
+					 "vmwgfx, error: guest graphics is out of memory (mob limit at: %u KiB).\n",
 					 ((gman->max_gmr_pages) << (PAGE_SHIFT - 10)));
 				vmw_host_printf(buf);
 				DRM_WARN("%s", buf);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 13b2820cae51..00c4ff684130 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -224,7 +224,7 @@ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps,
 	new_image = vmw_du_cursor_plane_acquire_image(new_vps);
 
 	changed = false;
-	if (old_image && new_image)
+	if (old_image && new_image && old_image != new_image)
 		changed = memcmp(old_image, new_image, size) != 0;
 
 	return changed;
@@ -2171,13 +2171,12 @@ int vmw_kms_write_svga(struct vmw_private *vmw_priv,
 	return 0;
 }
 
+static
 bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv,
-				uint32_t pitch,
-				uint32_t height)
+				u64 pitch,
+				u64 height)
 {
-	return ((u64) pitch * (u64) height) < (u64)
-		((dev_priv->active_display_unit == vmw_du_screen_target) ?
-		 dev_priv->max_primary_mem : dev_priv->vram_size);
+	return (pitch * height) < (u64)dev_priv->vram_size;
 }
 
 /**
@@ -2873,25 +2872,18 @@ out_unref:
 enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector,
 					      struct drm_display_mode *mode)
 {
+	enum drm_mode_status ret;
 	struct drm_device *dev = connector->dev;
 	struct vmw_private *dev_priv = vmw_priv(dev);
-	u32 max_width = dev_priv->texture_max_width;
-	u32 max_height = dev_priv->texture_max_height;
 	u32 assumed_cpp = 4;
 
 	if (dev_priv->assume_16bpp)
 		assumed_cpp = 2;
 
-	if (dev_priv->active_display_unit == vmw_du_screen_target) {
-		max_width  = min(dev_priv->stdu_max_width,  max_width);
-		max_height = min(dev_priv->stdu_max_height, max_height);
-	}
-
-	if (max_width < mode->hdisplay)
-		return MODE_BAD_HVALUE;
-
-	if (max_height < mode->vdisplay)
-		return MODE_BAD_VVALUE;
+	ret = drm_mode_validate_size(mode, dev_priv->texture_max_width,
+				     dev_priv->texture_max_height);
+	if (ret != MODE_OK)
+		return ret;
 
 	if (!vmw_kms_validate_mode_vram(dev_priv,
 					mode->hdisplay * assumed_cpp,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 2041c4d48daa..a04e0736318d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -43,7 +43,14 @@
 #define vmw_connector_to_stdu(x) \
 	container_of(x, struct vmw_screen_target_display_unit, base.connector)
 
-
+/*
+ * Some renderers such as llvmpipe will align the width and height of their
+ * buffers to match their tile size. We need to keep this in mind when exposing
+ * modes to userspace so that this possible over-allocation will not exceed
+ * graphics memory. 64x64 pixels seems to be a reasonable upper bound for the
+ * tile size of current renderers.
+ */
+#define GPU_TILE_SIZE 64
 
 enum stdu_content_type {
 	SAME_AS_DISPLAY = 0,
@@ -85,11 +92,6 @@ struct vmw_stdu_update {
 	SVGA3dCmdUpdateGBScreenTarget body;
 };
 
-struct vmw_stdu_dma {
-	SVGA3dCmdHeader     header;
-	SVGA3dCmdSurfaceDMA body;
-};
-
 struct vmw_stdu_surface_copy {
 	SVGA3dCmdHeader      header;
 	SVGA3dCmdSurfaceCopy body;
@@ -414,6 +416,7 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc,
 {
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
+	struct drm_crtc_state *new_crtc_state;
 	int ret;
 
 	if (!crtc) {
@@ -423,6 +426,7 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	stdu     = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
+	new_crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 
 	if (dev_priv->vkms_enabled)
 		drm_crtc_vblank_off(crtc);
@@ -434,6 +438,14 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc,
 
 		(void) vmw_stdu_update_st(dev_priv, stdu);
 
+		/* Don't destroy the Screen Target if we are only setting the
+		 * display as inactive
+		 */
+		if (new_crtc_state->enable &&
+		    !new_crtc_state->active &&
+		    !new_crtc_state->mode_changed)
+			return;
+
 		ret = vmw_stdu_destroy_st(dev_priv, stdu);
 		if (ret)
 			DRM_ERROR("Failed to destroy Screen Target\n");
@@ -829,7 +841,41 @@ static void vmw_stdu_connector_destroy(struct drm_connector *connector)
 	vmw_stdu_destroy(vmw_connector_to_stdu(connector));
 }
 
+static enum drm_mode_status
+vmw_stdu_connector_mode_valid(struct drm_connector *connector,
+			      struct drm_display_mode *mode)
+{
+	enum drm_mode_status ret;
+	struct drm_device *dev = connector->dev;
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	u64 assumed_cpp = dev_priv->assume_16bpp ? 2 : 4;
+	/* Align width and height to account for GPU tile over-alignment */
+	u64 required_mem = ALIGN(mode->hdisplay, GPU_TILE_SIZE) *
+			   ALIGN(mode->vdisplay, GPU_TILE_SIZE) *
+			   assumed_cpp;
+	required_mem = ALIGN(required_mem, PAGE_SIZE);
+
+	ret = drm_mode_validate_size(mode, dev_priv->stdu_max_width,
+				     dev_priv->stdu_max_height);
+	if (ret != MODE_OK)
+		return ret;
+
+	ret = drm_mode_validate_size(mode, dev_priv->texture_max_width,
+				     dev_priv->texture_max_height);
+	if (ret != MODE_OK)
+		return ret;
 
+	if (required_mem > dev_priv->max_primary_mem)
+		return MODE_MEM;
+
+	if (required_mem > dev_priv->max_mob_pages * PAGE_SIZE)
+		return MODE_MEM;
+
+	if (required_mem > dev_priv->max_mob_size)
+		return MODE_MEM;
+
+	return MODE_OK;
+}
 
 static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
 	.dpms = vmw_du_connector_dpms,
@@ -845,7 +891,7 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
 static const struct
 drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = {
 	.get_modes = vmw_connector_get_modes,
-	.mode_valid = vmw_connector_mode_valid
+	.mode_valid = vmw_stdu_connector_mode_valid
 };
 
 
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..476d613333a9 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1749,6 +1749,7 @@ static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid)
 	if (!xe_gt_is_media_type(gt)) {
 		pf_release_vf_config_ggtt(gt, config);
 		pf_release_vf_config_lmem(gt, config);
+		pf_update_vf_lmtt(gt_to_xe(gt), vfid);
 	}
 	pf_release_config_ctxs(gt, config);
 	pf_release_config_dbs(gt, config);
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: