Merge tag 'amd-drm-next-7.1-2026-04-01' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-7.1-2026-04-01:

amdgpu:
- UserQ fixes
- PASID handling fix
- S4 fix for smu11 chips
- devcoredump fixes
- RAS fixes
- Misc small fixes
- DCN 4.2 updates
- DVI fixes
- DML fixes
- DC pipe validation fixes
- eDP DSC seamless boot
- DC FP rework
- swsmu cleanups
- GC 11.5.4 updates
- Add DC idle state manager
- Add support for using multiple engines for buffer fills and clears
- Misc SMU7 fixes

amdkfd:
- Non-4K page fixes
- Logging cleanups
- sysfs fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20260401184456.3576660-1-alexander.deucher@amd.com

28 files changed, 555 insertions, 323 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 7f4751e5caaf..cd9aa5b45e94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -373,249 +373,280 @@ int amdgpu_atomfirmware_get_uma_carveout_info(struct amdgpu_device *adev,
 	return -ENODEV;
 }
 
-int
-amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
+int amdgpu_atomfirmware_get_integrated_system_info(struct amdgpu_device *adev,
 				  int *vram_width, int *vram_type,
 				  int *vram_vendor)
 {
 	struct amdgpu_mode_info *mode_info = &adev->mode_info;
-	int index, i = 0;
+	int index;
 	u16 data_offset, size;
 	union igp_info *igp_info;
-	union vram_info *vram_info;
-	union umc_info *umc_info;
-	union vram_module *vram_module;
 	u8 frev, crev;
 	u8 mem_type;
-	u8 mem_vendor;
 	u32 mem_channel_number;
 	u32 mem_channel_width;
-	u32 module_id;
 
-	if (adev->flags & AMD_IS_APU)
-		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
 						    integratedsysteminfo);
-	else {
-		switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-		case IP_VERSION(12, 0, 0):
-		case IP_VERSION(12, 0, 1):
-			index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, umc_info);
+	if (amdgpu_atom_parse_data_header(mode_info->atom_context,
+					  index, &size,
+					  &frev, &crev, &data_offset)) {
+		igp_info = (union igp_info *)
+			(mode_info->atom_context->bios + data_offset);
+		switch (frev) {
+		case 1:
+			switch (crev) {
+			case 11:
+			case 12:
+				mem_channel_number = igp_info->v11.umachannelnumber;
+				if (!mem_channel_number)
+					mem_channel_number = 1;
+				mem_type = igp_info->v11.memorytype;
+				if (mem_type == LpDdr5MemType)
+					mem_channel_width = 32;
+				else
+					mem_channel_width = 64;
+				if (vram_width)
+					*vram_width = mem_channel_number * mem_channel_width;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				break;
+			default:
+				return -EINVAL;
+			}
+			break;
+		case 2:
+			switch (crev) {
+			case 1:
+			case 2:
+				mem_channel_number = igp_info->v21.umachannelnumber;
+				if (!mem_channel_number)
+					mem_channel_number = 1;
+				mem_type = igp_info->v21.memorytype;
+				if (mem_type == LpDdr5MemType)
+					mem_channel_width = 32;
+				else
+					mem_channel_width = 64;
+				if (vram_width)
+					*vram_width = mem_channel_number * mem_channel_width;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				break;
+			case 3:
+				mem_channel_number = igp_info->v23.umachannelnumber;
+				if (!mem_channel_number)
+					mem_channel_number = 1;
+				mem_type = igp_info->v23.memorytype;
+				if (mem_type == LpDdr5MemType)
+					mem_channel_width = 32;
+				else
+					mem_channel_width = 64;
+				if (vram_width)
+					*vram_width = mem_channel_number * mem_channel_width;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				break;
+			default:
+				return -EINVAL;
+			}
 			break;
 		default:
-			index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, vram_info);
+			return -EINVAL;
 		}
+	} else {
+		return -EINVAL;
 	}
+	return 0;
+}
+
+int amdgpu_atomfirmware_get_umc_info(struct amdgpu_device *adev,
+				  int *vram_width, int *vram_type,
+				  int *vram_vendor)
+{
+	struct amdgpu_mode_info *mode_info = &adev->mode_info;
+	int index;
+	u16 data_offset, size;
+	union umc_info *umc_info;
+	u8 frev, crev;
+	u8 mem_type;
+	u8 mem_vendor;
+	u32 mem_channel_number;
+	u32 mem_channel_width;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, umc_info);
+
 	if (amdgpu_atom_parse_data_header(mode_info->atom_context,
 					  index, &size,
 					  &frev, &crev, &data_offset)) {
-		if (adev->flags & AMD_IS_APU) {
-			igp_info = (union igp_info *)
-				(mode_info->atom_context->bios + data_offset);
-			switch (frev) {
-			case 1:
-				switch (crev) {
-				case 11:
-				case 12:
-					mem_channel_number = igp_info->v11.umachannelnumber;
-					if (!mem_channel_number)
-						mem_channel_number = 1;
-					mem_type = igp_info->v11.memorytype;
-					if (mem_type == LpDdr5MemType)
-						mem_channel_width = 32;
-					else
-						mem_channel_width = 64;
-					if (vram_width)
-						*vram_width = mem_channel_number * mem_channel_width;
-					if (vram_type)
-						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-					break;
-				default:
-					return -EINVAL;
-				}
-				break;
-			case 2:
-				switch (crev) {
-				case 1:
-				case 2:
-					mem_channel_number = igp_info->v21.umachannelnumber;
-					if (!mem_channel_number)
-						mem_channel_number = 1;
-					mem_type = igp_info->v21.memorytype;
-					if (mem_type == LpDdr5MemType)
-						mem_channel_width = 32;
-					else
-						mem_channel_width = 64;
-					if (vram_width)
-						*vram_width = mem_channel_number * mem_channel_width;
-					if (vram_type)
-						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-					break;
-				case 3:
-					mem_channel_number = igp_info->v23.umachannelnumber;
-					if (!mem_channel_number)
-						mem_channel_number = 1;
-					mem_type = igp_info->v23.memorytype;
-					if (mem_type == LpDdr5MemType)
-						mem_channel_width = 32;
-					else
-						mem_channel_width = 64;
-					if (vram_width)
-						*vram_width = mem_channel_number * mem_channel_width;
-					if (vram_type)
-						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-					break;
-				default:
-					return -EINVAL;
-				}
+		umc_info = (union umc_info *)(mode_info->atom_context->bios + data_offset);
+
+		if (frev == 4) {
+			switch (crev) {
+			case 0:
+				mem_channel_number = le32_to_cpu(umc_info->v40.channel_num);
+				mem_type = le32_to_cpu(umc_info->v40.vram_type);
+				mem_channel_width = le32_to_cpu(umc_info->v40.channel_width);
+				mem_vendor = RREG32(adev->bios_scratch_reg_offset + 4) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
 				break;
 			default:
 				return -EINVAL;
 			}
 		} else {
-			switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
-			case IP_VERSION(12, 0, 0):
-			case IP_VERSION(12, 0, 1):
-				umc_info = (union umc_info *)(mode_info->atom_context->bios + data_offset);
-
-				if (frev == 4) {
-					switch (crev) {
-					case 0:
-						mem_channel_number = le32_to_cpu(umc_info->v40.channel_num);
-						mem_type = le32_to_cpu(umc_info->v40.vram_type);
-						mem_channel_width = le32_to_cpu(umc_info->v40.channel_width);
-						mem_vendor = RREG32(adev->bios_scratch_reg_offset + 4) & 0xF;
-						if (vram_vendor)
-							*vram_vendor = mem_vendor;
-						if (vram_type)
-							*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-						if (vram_width)
-							*vram_width = mem_channel_number * (1 << mem_channel_width);
-						break;
-					default:
-						return -EINVAL;
-					}
-				} else
-					return -EINVAL;
+			return -EINVAL;
+		}
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
+				  int *vram_width, int *vram_type,
+				  int *vram_vendor)
+{
+	struct amdgpu_mode_info *mode_info = &adev->mode_info;
+	int index, i = 0;
+	u16 data_offset, size;
+	union vram_info *vram_info;
+	union vram_module *vram_module;
+	u8 frev, crev;
+	u8 mem_type;
+	u8 mem_vendor;
+	u32 mem_channel_number;
+	u32 mem_channel_width;
+	u32 module_id;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, vram_info);
+
+	if (amdgpu_atom_parse_data_header(mode_info->atom_context,
+					  index, &size,
+					  &frev, &crev, &data_offset)) {
+		vram_info = (union vram_info *)
+			(mode_info->atom_context->bios + data_offset);
+
+		module_id = (RREG32(adev->bios_scratch_reg_offset + 4) & 0x00ff0000) >> 16;
+		if (frev == 3) {
+			switch (crev) {
+			/* v30 */
+			case 0:
+				vram_module = (union vram_module *)vram_info->v30.vram_module;
+				mem_vendor = (vram_module->v30.dram_vendor_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				mem_type = vram_info->v30.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_info->v30.channel_num;
+				mem_channel_width = vram_info->v30.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * 16;
 				break;
 			default:
-				vram_info = (union vram_info *)
-					(mode_info->atom_context->bios + data_offset);
-
-				module_id = (RREG32(adev->bios_scratch_reg_offset + 4) & 0x00ff0000) >> 16;
-				if (frev == 3) {
-					switch (crev) {
-					/* v30 */
-					case 0:
-						vram_module = (union vram_module *)vram_info->v30.vram_module;
-						mem_vendor = (vram_module->v30.dram_vendor_id) & 0xF;
-						if (vram_vendor)
-							*vram_vendor = mem_vendor;
-						mem_type = vram_info->v30.memory_type;
-						if (vram_type)
-							*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-						mem_channel_number = vram_info->v30.channel_num;
-						mem_channel_width = vram_info->v30.channel_width;
-						if (vram_width)
-							*vram_width = mem_channel_number * 16;
-						break;
-					default:
-						return -EINVAL;
-					}
-				} else if (frev == 2) {
-					switch (crev) {
-					/* v23 */
-					case 3:
-						if (module_id > vram_info->v23.vram_module_num)
-							module_id = 0;
-						vram_module = (union vram_module *)vram_info->v23.vram_module;
-						while (i < module_id) {
-							vram_module = (union vram_module *)
-								((u8 *)vram_module + vram_module->v9.vram_module_size);
-							i++;
-						}
-						mem_type = vram_module->v9.memory_type;
-						if (vram_type)
-							*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-						mem_channel_number = vram_module->v9.channel_num;
-						mem_channel_width = vram_module->v9.channel_width;
-						if (vram_width)
-							*vram_width = mem_channel_number * (1 << mem_channel_width);
-						mem_vendor = (vram_module->v9.vender_rev_id) & 0xF;
-						if (vram_vendor)
-							*vram_vendor = mem_vendor;
-						break;
-					/* v24 */
-					case 4:
-						if (module_id > vram_info->v24.vram_module_num)
-							module_id = 0;
-						vram_module = (union vram_module *)vram_info->v24.vram_module;
-						while (i < module_id) {
-							vram_module = (union vram_module *)
-								((u8 *)vram_module + vram_module->v10.vram_module_size);
-							i++;
-						}
-						mem_type = vram_module->v10.memory_type;
-						if (vram_type)
-							*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-						mem_channel_number = vram_module->v10.channel_num;
-						mem_channel_width = vram_module->v10.channel_width;
-						if (vram_width)
-							*vram_width = mem_channel_number * (1 << mem_channel_width);
-						mem_vendor = (vram_module->v10.vender_rev_id) & 0xF;
-						if (vram_vendor)
-							*vram_vendor = mem_vendor;
-						break;
-					/* v25 */
-					case 5:
-						if (module_id > vram_info->v25.vram_module_num)
-							module_id = 0;
-						vram_module = (union vram_module *)vram_info->v25.vram_module;
-						while (i < module_id) {
-							vram_module = (union vram_module *)
-								((u8 *)vram_module + vram_module->v11.vram_module_size);
-							i++;
-						}
-						mem_type = vram_module->v11.memory_type;
-						if (vram_type)
-							*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-						mem_channel_number = vram_module->v11.channel_num;
-						mem_channel_width = vram_module->v11.channel_width;
-						if (vram_width)
-							*vram_width = mem_channel_number * (1 << mem_channel_width);
-						mem_vendor = (vram_module->v11.vender_rev_id) & 0xF;
-						if (vram_vendor)
-							*vram_vendor = mem_vendor;
-						break;
-					/* v26 */
-					case 6:
-						if (module_id > vram_info->v26.vram_module_num)
-							module_id = 0;
-						vram_module = (union vram_module *)vram_info->v26.vram_module;
-						while (i < module_id) {
-							vram_module = (union vram_module *)
-								((u8 *)vram_module + vram_module->v9.vram_module_size);
-							i++;
-						}
-						mem_type = vram_module->v9.memory_type;
-						if (vram_type)
-							*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
-						mem_channel_number = vram_module->v9.channel_num;
-						mem_channel_width = vram_module->v9.channel_width;
-						if (vram_width)
-							*vram_width = mem_channel_number * (1 << mem_channel_width);
-						mem_vendor = (vram_module->v9.vender_rev_id) & 0xF;
-						if (vram_vendor)
-							*vram_vendor = mem_vendor;
-						break;
-					default:
-						return -EINVAL;
-					}
-				} else {
-					/* invalid frev */
-					return -EINVAL;
+				return -EINVAL;
+			}
+		} else if (frev == 2) {
+			switch (crev) {
+			/* v23 */
+			case 3:
+				if (module_id > vram_info->v23.vram_module_num)
+					module_id = 0;
+				vram_module = (union vram_module *)vram_info->v23.vram_module;
+				while (i < module_id) {
+					vram_module = (union vram_module *)
+						((u8 *)vram_module + vram_module->v9.vram_module_size);
+					i++;
 				}
+				mem_type = vram_module->v9.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_module->v9.channel_num;
+				mem_channel_width = vram_module->v9.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
+				mem_vendor = (vram_module->v9.vender_rev_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				break;
+			/* v24 */
+			case 4:
+				if (module_id > vram_info->v24.vram_module_num)
+					module_id = 0;
+				vram_module = (union vram_module *)vram_info->v24.vram_module;
+				while (i < module_id) {
+					vram_module = (union vram_module *)
+						((u8 *)vram_module + vram_module->v10.vram_module_size);
+					i++;
+				}
+				mem_type = vram_module->v10.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_module->v10.channel_num;
+				mem_channel_width = vram_module->v10.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
+				mem_vendor = (vram_module->v10.vender_rev_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				break;
+			/* v25 */
+			case 5:
+				if (module_id > vram_info->v25.vram_module_num)
+					module_id = 0;
+				vram_module = (union vram_module *)vram_info->v25.vram_module;
+				while (i < module_id) {
+					vram_module = (union vram_module *)
+						((u8 *)vram_module + vram_module->v11.vram_module_size);
+					i++;
+				}
+				mem_type = vram_module->v11.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_module->v11.channel_num;
+				mem_channel_width = vram_module->v11.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
+				mem_vendor = (vram_module->v11.vender_rev_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				break;
+			/* v26 */
+			case 6:
+				if (module_id > vram_info->v26.vram_module_num)
+					module_id = 0;
+				vram_module = (union vram_module *)vram_info->v26.vram_module;
+				while (i < module_id) {
+					vram_module = (union vram_module *)
+						((u8 *)vram_module + vram_module->v9.vram_module_size);
+					i++;
+				}
+				mem_type = vram_module->v9.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_module->v9.channel_num;
+				mem_channel_width = vram_module->v9.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
+				mem_vendor = (vram_module->v9.vender_rev_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				break;
+			default:
+				return -EINVAL;
 			}
+		} else {
+			/* invalid frev */
+			return -EINVAL;
 		}
+
+	} else {
+		return -EINVAL;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index 67c8d105729b..0760e4510513 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -30,6 +30,10 @@ uint32_t amdgpu_atomfirmware_query_firmware_capability(struct amdgpu_device *ade
 bool amdgpu_atomfirmware_gpu_virtualization_supported(struct amdgpu_device *adev);
 void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev);
+int amdgpu_atomfirmware_get_integrated_system_info(struct amdgpu_device *adev,
+	int *vram_width, int *vram_type, int *vram_vendor);
+int amdgpu_atomfirmware_get_umc_info(struct amdgpu_device *adev,
+	int *vram_width, int *vram_type, int *vram_vendor);
 int amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 	int *vram_width, int *vram_type, int *vram_vendor);
 int amdgpu_atomfirmware_get_uma_carveout_info(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index c048217615c1..b24d5d21be5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -908,9 +908,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			goto out_free_user_pages;
 
 		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-			/* One fence for TTM and one for each CS job */
 			r = drm_exec_prepare_obj(&p->exec, &e->bo->tbo.base,
-						 1 + p->gang_size);
+						 TTM_NUM_MOVE_FENCES + p->gang_size);
 			drm_exec_retry_on_contention(&p->exec);
 			if (unlikely(r))
 				goto out_free_user_pages;
@@ -920,7 +919,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 		if (p->uf_bo) {
 			r = drm_exec_prepare_obj(&p->exec, &p->uf_bo->tbo.base,
-						 1 + p->gang_size);
+						 TTM_NUM_MOVE_FENCES + p->gang_size);
 			drm_exec_retry_on_contention(&p->exec);
 			if (unlikely(r))
 				goto out_free_user_pages;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
index 2b54a67437c2..fddf4e1252bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
@@ -35,6 +35,9 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check,
 void amdgpu_coredump_init(struct amdgpu_device *adev)
 {
 }
+void amdgpu_coredump_fini(struct amdgpu_device *adev)
+{
+}
 #else
 
 #define AMDGPU_CORE_DUMP_SIZE_MAX (256 * 1024 * 1024)
@@ -192,12 +195,16 @@ static void amdgpu_devcoredump_fw_info(struct amdgpu_device *adev,
 	drm_printf(p, "VPE feature version: %u, fw version: 0x%08x\n",
 		   adev->vpe.feature_version, adev->vpe.fw_version);
 
-	drm_printf(p, "\nVBIOS Information\n");
-	drm_printf(p, "vbios name       : %s\n", ctx->name);
-	drm_printf(p, "vbios pn         : %s\n", ctx->vbios_pn);
-	drm_printf(p, "vbios version    : %d\n", ctx->version);
-	drm_printf(p, "vbios ver_str    : %s\n", ctx->vbios_ver_str);
-	drm_printf(p, "vbios date       : %s\n", ctx->date);
+	if (adev->bios) {
+		drm_printf(p, "\nVBIOS Information\n");
+		drm_printf(p, "vbios name       : %s\n", ctx->name);
+		drm_printf(p, "vbios pn         : %s\n", ctx->vbios_pn);
+		drm_printf(p, "vbios version    : %d\n", ctx->version);
+		drm_printf(p, "vbios ver_str    : %s\n", ctx->vbios_ver_str);
+		drm_printf(p, "vbios date       : %s\n", ctx->date);
+	}else {
+		drm_printf(p, "\nVBIOS Information: NA\n");
+	}
 }
 
 static ssize_t
@@ -436,4 +443,10 @@ void amdgpu_coredump_init(struct amdgpu_device *adev)
 {
 	INIT_WORK(&adev->coredump_work, amdgpu_devcoredump_deferred_work);
 }
+
+void amdgpu_coredump_fini(struct amdgpu_device *adev)
+{
+	/* Finish deferred coredump formatting before HW/IP teardown. */
+	flush_work(&adev->coredump_work);
+}
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h
index b3582d0b4ca4..f8f2f4df129b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.h
@@ -50,4 +50,5 @@ struct amdgpu_coredump_info {
 void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check,
 		     bool vram_lost, struct amdgpu_job *job);
 void amdgpu_coredump_init(struct amdgpu_device *adev);
+void amdgpu_coredump_fini(struct amdgpu_device *adev);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a7038f039b10..9c936519bb2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4225,6 +4225,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	if (pci_dev_is_disconnected(adev->pdev))
 		amdgpu_amdkfd_device_fini_sw(adev);
 
+	amdgpu_coredump_fini(adev);
 	amdgpu_device_ip_fini_early(adev);
 
 	amdgpu_irq_fini_hw(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index a44baa9ee78d..8ed637f92322 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2683,8 +2683,12 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	if (r)
 		return r;
 
-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index e2d32c29668a..bc772ca3dab7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -404,6 +404,50 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
 }
 
 /**
+ * amdgpu_gart_map_gfx9_mqd - map mqd and ctrl_stack dma_addresses into GART entries
+ *
+ * @adev: amdgpu_device pointer
+ * @offset: offset into the GPU's gart aperture
+ * @pages: number of pages to bind
+ * @dma_addr: DMA addresses of pages
+ * @flags: page table entry flags
+ *
+ * Map the MQD and control stack addresses into GART entries with the correct
+ * memory types on gfxv9. The MQD occupies the first 4KB and is followed by
+ * the control stack. The MQD uses UC (uncached) memory, while the control stack
+ * uses NC (non-coherent) memory.
+ */
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags)
+{
+	uint64_t page_base;
+	unsigned int i, j, t;
+	int idx;
+	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
+	void *dst;
+
+	if (!adev->gart.ptr)
+		return;
+
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return;
+
+	t = offset / AMDGPU_GPU_PAGE_SIZE;
+	dst = adev->gart.ptr;
+	for (i = 0; i < pages; i++) {
+		page_base = dma_addr[i];
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
+			if ((i == 0) && (j == 0))
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
+			else
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, ctrl_flags);
+			page_base += AMDGPU_GPU_PAGE_SIZE;
+		}
+	}
+	drm_dev_exit(idx);
+}
+
+/**
  * amdgpu_gart_bind - bind pages into the gart page table
  *
  * @adev: amdgpu_device pointer
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index d3118275ddae..6ebd2da32ea6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -62,6 +62,8 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, dma_addr_t *dma_addr, uint64_t flags,
 		     void *dst);
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		      int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 860a4405f7dd..ec74f3971732 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -34,6 +34,7 @@
 #include "amdgpu_ras.h"
 #include "amdgpu_reset.h"
 #include "amdgpu_xgmi.h"
+#include "amdgpu_atomfirmware.h"
 
 #include <drm/drm_drv.h>
 #include <drm/ttm/ttm_tt.h>
@@ -1747,3 +1748,31 @@ int amdgpu_gmc_init_mem_ranges(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+int amdgpu_gmc_get_vram_info(struct amdgpu_device *adev,
+		int *vram_width, int *vram_type, int *vram_vendor)
+{
+	int ret = 0;
+
+	if (adev->flags & AMD_IS_APU)
+		return amdgpu_atomfirmware_get_integrated_system_info(adev,
+							vram_width, vram_type, vram_vendor);
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(12, 0, 0):
+	case IP_VERSION(12, 0, 1):
+		return amdgpu_atomfirmware_get_umc_info(adev,
+								vram_width, vram_type, vram_vendor);
+	case IP_VERSION(9, 5, 0):
+	case IP_VERSION(9, 4, 4):
+	case IP_VERSION(9, 4, 3):
+		ret = amdgpu_atomfirmware_get_umc_info(adev,
+								vram_width, vram_type, vram_vendor);
+		if (vram_width && !ret)
+			*vram_width *= hweight32(adev->aid_mask);
+		return ret;
+	default:
+		return amdgpu_atomfirmware_get_vram_info(adev,
+								vram_width, vram_type, vram_vendor);
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index b9fdc3276e81..32e73e8ba778 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -482,4 +482,6 @@ amdgpu_gmc_query_memory_partition(struct amdgpu_device *adev);
 int amdgpu_gmc_init_mem_ranges(struct amdgpu_device *adev);
 void amdgpu_gmc_init_sw_mem_ranges(struct amdgpu_device *adev,
 				   struct amdgpu_mem_partition_info *mem_ranges);
+int amdgpu_gmc_get_vram_info(struct amdgpu_device *adev,
+		int *vram_width, int *vram_type, int *vram_vendor);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index d88523568b62..569c5a89ff10 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -68,8 +68,11 @@ int amdgpu_pasid_alloc(unsigned int bits)
 		return -EINVAL;
 
 	spin_lock(&amdgpu_pasid_idr_lock);
+	/* TODO: Need to replace the idr with an xarry, and then
+	 * handle the internal locking with ATOMIC safe paths.
+	 */
 	pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1,
-				 1U << bits, GFP_KERNEL);
+				 1U << bits, GFP_ATOMIC);
 	spin_unlock(&amdgpu_pasid_idr_lock);
 
 	if (pasid >= 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 90352284c5ee..51ab1a332615 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -44,6 +44,7 @@
 #include <drm/display/drm_dp_mst_helper.h>
 #include "modules/inc/mod_freesync.h"
 #include "amdgpu_dm_irq_params.h"
+#include "amdgpu_dm_ism.h"
 
 struct amdgpu_bo;
 struct amdgpu_device;
@@ -486,6 +487,10 @@ struct amdgpu_crtc {
 	int deferred_flip_completion;
 	/* parameters access from DM IRQ handler */
 	struct dm_irq_params dm_irq_params;
+
+	/* DM idle state manager */
+	struct amdgpu_dm_ism ism;
+
 	/* pll sharing */
 	struct amdgpu_atom_ss ss;
 	bool ss_enabled;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index cc004830a8a2..27f7567df7bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1325,7 +1325,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	if (r)
 		goto out;
 
-	r = amdgpu_fill_buffer(&adev->mman.clear_entity, abo, 0, &bo->base._resv,
+	r = amdgpu_fill_buffer(amdgpu_ttm_next_clear_entity(adev),
+			       abo, 0, &bo->base._resv,
 			       &fence, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
 	if (WARN_ON(r))
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 44fba4b6aa92..cdf4909592d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1558,6 +1558,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 	unsigned char buf[RAS_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int dev_var = adev->pdev->device & 0xF;
+	uint32_t vram_type = adev->gmc.vram_type;
 	int res;
 
 	if (amdgpu_ras_smu_eeprom_supported(adev))
@@ -1597,6 +1599,12 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		return amdgpu_ras_eeprom_reset_table(control);
 	}
 
+	if (!(adev->flags & AMD_IS_APU) && (dev_var == 0x5) &&
+	    (vram_type == AMDGPU_VRAM_TYPE_HBM3E) &&
+	    (hdr->version < RAS_TABLE_VER_V3)) {
+		return amdgpu_ras_eeprom_reset_table(control);
+	}
+
 	switch (hdr->version) {
 	case RAS_TABLE_VER_V2_1:
 	case RAS_TABLE_VER_V3:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b4ab309bf08a..afaaab6496de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -387,9 +387,11 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
+	struct amdgpu_ttm_buffer_entity *entity;
 	struct amdgpu_copy_mem src, dst;
 	struct dma_fence *fence = NULL;
 	int r;
+	u32 e;
 
 	src.bo = bo;
 	dst.bo = bo;
@@ -398,8 +400,12 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 	src.offset = 0;
 	dst.offset = 0;
 
+	e = atomic_inc_return(&adev->mman.next_move_entity) %
+			      adev->mman.num_move_entities;
+	entity = &adev->mman.move_entities[e];
+
 	r = amdgpu_ttm_copy_mem_to_mem(adev,
-				       &adev->mman.move_entity,
+				       entity,
 				       &src, &dst,
 				       new_mem->size,
 				       amdgpu_bo_encrypted(abo),
@@ -411,9 +417,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 	if (old_mem->mem_type == TTM_PL_VRAM &&
 	    (abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) {
 		struct dma_fence *wipe_fence = NULL;
-
-		r = amdgpu_fill_buffer(&adev->mman.move_entity,
-				       abo, 0, NULL, &wipe_fence,
+		r = amdgpu_fill_buffer(entity, abo, 0, NULL, &wipe_fence,
 				       AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
 		if (r) {
 			goto error;
@@ -854,25 +858,15 @@ static void amdgpu_ttm_gart_bind_gfx9_mqd(struct amdgpu_device *adev,
 	int num_xcc = max(1U, adev->gfx.num_xcc_per_xcp);
 	uint64_t page_idx, pages_per_xcc;
 	int i;
-	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
 
 	pages_per_xcc = total_pages;
 	do_div(pages_per_xcc, num_xcc);
 
 	for (i = 0, page_idx = 0; i < num_xcc; i++, page_idx += pages_per_xcc) {
-		/* MQD page: use default flags */
-		amdgpu_gart_bind(adev,
+		amdgpu_gart_map_gfx9_mqd(adev,
 				gtt->offset + (page_idx << PAGE_SHIFT),
-				1, &gtt->ttm.dma_address[page_idx], flags);
-		/*
-		 * Ctrl pages - modify the memory type to NC (ctrl_flags) from
-		 * the second page of the BO onward.
-		 */
-		amdgpu_gart_bind(adev,
-				gtt->offset + ((page_idx + 1) << PAGE_SHIFT),
-				pages_per_xcc - 1,
-				&gtt->ttm.dma_address[page_idx + 1],
-				ctrl_flags);
+				pages_per_xcc, &gtt->ttm.dma_address[page_idx],
+				flags);
 	}
 }
 
@@ -2345,8 +2339,9 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	u32 num_clear_entities, num_move_entities;
 	uint64_t size;
-	int r;
+	int r, i, j;
 
 	if (!adev->mman.initialized || amdgpu_in_reset(adev) ||
 	    adev->mman.buffer_funcs_enabled == enable || adev->gmc.is_app_apu)
@@ -2361,6 +2356,8 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 			return;
 		}
 
+		num_clear_entities = 1;
+		num_move_entities = 1;
 		ring = adev->mman.buffer_funcs_ring;
 		sched = &ring->sched;
 		r = amdgpu_ttm_buffer_entity_init(&adev->mman.gtt_mgr,
@@ -2373,36 +2370,64 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 			return;
 		}
 
-		r = amdgpu_ttm_buffer_entity_init(&adev->mman.gtt_mgr,
-						  &adev->mman.clear_entity,
-						  DRM_SCHED_PRIORITY_NORMAL,
-						  &sched, 1, 1);
-		if (r < 0) {
-			dev_err(adev->dev,
-				"Failed setting up TTM BO clear entity (%d)\n", r);
+		adev->mman.clear_entities = kcalloc(num_clear_entities,
+						    sizeof(struct amdgpu_ttm_buffer_entity),
+						    GFP_KERNEL);
+		atomic_set(&adev->mman.next_clear_entity, 0);
+		if (!adev->mman.clear_entities)
 			goto error_free_default_entity;
+
+		adev->mman.num_clear_entities = num_clear_entities;
+
+		for (i = 0; i < num_clear_entities; i++) {
+			r = amdgpu_ttm_buffer_entity_init(
+				&adev->mman.gtt_mgr, &adev->mman.clear_entities[i],
+				DRM_SCHED_PRIORITY_NORMAL, &sched, 1, 1);
+
+			if (r < 0) {
+				for (j = 0; j < i; j++)
+					amdgpu_ttm_buffer_entity_fini(
+						&adev->mman.gtt_mgr, &adev->mman.clear_entities[j]);
+				kfree(adev->mman.clear_entities);
+				adev->mman.num_clear_entities = 0;
+				adev->mman.clear_entities = NULL;
+				goto error_free_default_entity;
+			}
 		}
 
-		r = amdgpu_ttm_buffer_entity_init(&adev->mman.gtt_mgr,
-						  &adev->mman.move_entity,
-						  DRM_SCHED_PRIORITY_NORMAL,
-						  &sched, 1, 2);
-		if (r < 0) {
-			dev_err(adev->dev,
-				"Failed setting up TTM BO move entity (%d)\n", r);
-			goto error_free_clear_entity;
+		adev->mman.num_move_entities = num_move_entities;
+		atomic_set(&adev->mman.next_move_entity, 0);
+		for (i = 0; i < num_move_entities; i++) {
+			r = amdgpu_ttm_buffer_entity_init(
+				&adev->mman.gtt_mgr,
+				&adev->mman.move_entities[i],
+				DRM_SCHED_PRIORITY_NORMAL, &sched, 1, 2);
+
+			if (r < 0) {
+				for (j = 0; j < i; j++)
+					amdgpu_ttm_buffer_entity_fini(
+						&adev->mman.gtt_mgr, &adev->mman.move_entities[j]);
+				adev->mman.num_move_entities = 0;
+				goto error_free_clear_entities;
+			}
 		}
 	} else {
 		amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
 					      &adev->mman.default_entity);
-		amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
-					      &adev->mman.clear_entity);
-		amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
-					      &adev->mman.move_entity);
+		for (i = 0; i < adev->mman.num_clear_entities; i++)
+			amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
+						      &adev->mman.clear_entities[i]);
+		for (i = 0; i < adev->mman.num_move_entities; i++)
+			amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
+						      &adev->mman.move_entities[i]);
 		/* Drop all the old fences since re-creating the scheduler entities
 		 * will allocate new contexts.
 		 */
 		ttm_resource_manager_cleanup(man);
+		kfree(adev->mman.clear_entities);
+		adev->mman.clear_entities = NULL;
+		adev->mman.num_clear_entities = 0;
+		adev->mman.num_move_entities = 0;
 	}
 
 	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
@@ -2415,9 +2440,13 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 
 	return;
 
-error_free_clear_entity:
-	amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
-				      &adev->mman.clear_entity);
+error_free_clear_entities:
+	for (i = 0; i < adev->mman.num_clear_entities; i++)
+		amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
+					      &adev->mman.clear_entities[i]);
+	kfree(adev->mman.clear_entities);
+	adev->mman.clear_entities = NULL;
+	adev->mman.num_clear_entities = 0;
 error_free_default_entity:
 	amdgpu_ttm_buffer_entity_fini(&adev->mman.gtt_mgr,
 				      &adev->mman.default_entity);
@@ -2567,8 +2596,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
 
 	if (!fence)
 		return -EINVAL;
-
-	entity = &adev->mman.clear_entity;
+	entity = &adev->mman.clear_entities[0];
 	*fence = dma_fence_get_stub();
 
 	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
@@ -2620,11 +2648,8 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
 	struct amdgpu_res_cursor dst;
 	int r;
 
-	if (!adev->mman.buffer_funcs_enabled) {
-		dev_err(adev->dev,
-			"Trying to clear memory with ring turned off.\n");
+	if (!entity)
 		return -EINVAL;
-	}
 
 	amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &dst);
 
@@ -2660,6 +2685,20 @@ error:
 	return r;
 }
 
+struct amdgpu_ttm_buffer_entity *
+amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev)
+{
+	struct amdgpu_mman *mman = &adev->mman;
+	u32 i;
+
+	if (mman->num_clear_entities == 0)
+		return NULL;
+
+	i = atomic_inc_return(&mman->next_clear_entity) %
+			      mman->num_clear_entities;
+	return &mman->clear_entities[i];
+}
+
 /**
  * amdgpu_ttm_evict_resources - evict memory buffers
  * @adev: amdgpu device object
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index bf101215757e..3b1973611446 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -72,8 +72,12 @@ struct amdgpu_mman {
 
 	/* @default_entity: for workarounds, has no gart windows */
 	struct amdgpu_ttm_buffer_entity default_entity;
-	struct amdgpu_ttm_buffer_entity clear_entity;
-	struct amdgpu_ttm_buffer_entity move_entity;
+	struct amdgpu_ttm_buffer_entity *clear_entities;
+	atomic_t next_clear_entity;
+	u32 num_clear_entities;
+	struct amdgpu_ttm_buffer_entity move_entities[TTM_NUM_MOVE_FENCES];
+	atomic_t next_move_entity;
+	u32 num_move_entities;
 
 	struct amdgpu_vram_mgr vram_mgr;
 	struct amdgpu_gtt_mgr gtt_mgr;
@@ -191,6 +195,7 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
 		       struct dma_resv *resv,
 		       struct dma_fence **f,
 		       u64 k_job_id);
+struct amdgpu_ttm_buffer_entity *amdgpu_ttm_next_clear_entity(struct amdgpu_device *adev);
 
 int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo);
 void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 7f64b783954a..366728ed03e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -600,6 +600,13 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 		goto unpin_bo;
 	}
 
+	/* Validate doorbell_offset is within the doorbell BO */
+	if ((u64)db_info->doorbell_offset * db_size + db_size >
+	    amdgpu_bo_size(db_obj->obj)) {
+		r = -EINVAL;
+		goto unpin_bo;
+	}
+
 	index = amdgpu_doorbell_index_on_bar(uq_mgr->adev, db_obj->obj,
 					     db_info->doorbell_offset, db_size);
 	drm_dbg_driver(adev_to_drm(uq_mgr->adev),
@@ -997,6 +1004,7 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 	unsigned long queue_id;
 	int ret = 0, r;
 
+	mutex_lock(&uq_mgr->userq_mutex);
 	/* Resume all the queues for this process */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
 
@@ -1012,6 +1020,7 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 			ret = r;
 
 	}
+	mutex_unlock(&uq_mgr->userq_mutex);
 
 	if (ret)
 		drm_file_err(uq_mgr->file, "Failed to map all the queues\n");
@@ -1215,23 +1224,21 @@ static void amdgpu_userq_restore_worker(struct work_struct *work)
 	struct dma_fence *ev_fence;
 	int ret;
 
-	mutex_lock(&uq_mgr->userq_mutex);
 	ev_fence = amdgpu_evf_mgr_get_fence(&fpriv->evf_mgr);
 	if (!dma_fence_is_signaled(ev_fence))
-		goto unlock;
+		goto put_fence;
 
 	ret = amdgpu_userq_vm_validate(uq_mgr);
 	if (ret) {
 		drm_file_err(uq_mgr->file, "Failed to validate BOs to restore\n");
-		goto unlock;
+		goto put_fence;
 	}
 
 	ret = amdgpu_userq_restore_all(uq_mgr);
 	if (ret)
 		drm_file_err(uq_mgr->file, "Failed to restore all queues\n");
 
-unlock:
-	mutex_unlock(&uq_mgr->userq_mutex);
+put_fence:
 	dma_fence_put(ev_fence);
 }
 
@@ -1454,17 +1461,19 @@ int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev,
 
 	if (!adev->userq_halt_for_enforce_isolation)
 		dev_warn(adev->dev, "userq scheduling already started!\n");
+
 	adev->userq_halt_for_enforce_isolation = false;
+
 	xa_for_each(&adev->userq_doorbell_xa, queue_id, queue) {
 		uqm = queue->userq_mgr;
 		mutex_lock(&uqm->userq_mutex);
-			if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
-			     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
-			    (queue->xcp_id == idx)) {
+		if (((queue->queue_type == AMDGPU_HW_IP_GFX) ||
+		     (queue->queue_type == AMDGPU_HW_IP_COMPUTE)) &&
+		    (queue->xcp_id == idx)) {
 			r = amdgpu_userq_restore_helper(queue);
 			if (r)
 				ret = r;
-			}
+		}
 		mutex_unlock(&uqm->userq_mutex);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index 5cef8cd14148..e54295b56282 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -328,11 +328,9 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane,
 		return r;
 	}
 
-	r = dma_resv_reserve_fences(rbo->tbo.base.resv, 1);
-	if (r) {
-		dev_err(adev->dev, "allocating fence slot failed (%d)\n", r);
+	r = dma_resv_reserve_fences(rbo->tbo.base.resv, TTM_NUM_MOVE_FENCES);
+	if (r)
 		goto error_unlock;
-	}
 
 	if (plane->type != DRM_PLANE_TYPE_CURSOR)
 		domain = amdgpu_display_supported_domains(adev, rbo->flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 641fe91b4f03..3b32f41c3655 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -173,7 +173,7 @@ struct amdgpu_bo_vm;
 #define AMDGPU_VA_RESERVED_SEQ64_SIZE		(2ULL << 20)
 #define AMDGPU_VA_RESERVED_SEQ64_START(adev)	(AMDGPU_VA_RESERVED_CSA_START(adev) \
 						 - AMDGPU_VA_RESERVED_SEQ64_SIZE)
-#define AMDGPU_VA_RESERVED_TRAP_SIZE		(2ULL << 12)
+#define AMDGPU_VA_RESERVED_TRAP_SIZE		(1ULL << 16)
 #define AMDGPU_VA_RESERVED_TRAP_START(adev)	(AMDGPU_VA_RESERVED_SEQ64_START(adev) \
 						 - AMDGPU_VA_RESERVED_TRAP_SIZE)
 #define AMDGPU_VA_RESERVED_BOTTOM		(1ULL << 16)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 78d1f3eb522e..ae39b9e1f7d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1722,6 +1722,20 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 			}
 		}
 		break;
+	case IP_VERSION(11, 5, 4):
+		adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex;
+		adev->gfx.cleaner_shader_size = sizeof(gfx_11_0_3_cleaner_shader_hex);
+		if (adev->gfx.me_fw_version  >= 4 &&
+		    adev->gfx.pfp_fw_version >= 7 &&
+		    adev->gfx.mec_fw_version >= 5) {
+			adev->gfx.enable_cleaner_shader = true;
+			r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
+			if (r) {
+				adev->gfx.enable_cleaner_shader = false;
+				dev_err(adev->dev, "Failed to initialize cleaner shader\n");
+			}
+		}
+		break;
 	default:
 		adev->gfx.enable_cleaner_shader = false;
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 2568eeaae945..fd691b2a6e21 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -767,7 +767,7 @@ static int gmc_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
 		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_GDDR6;
 		adev->gmc.vram_width = 1 * 128; /* numchan * chansize */
 	} else {
-		r = amdgpu_atomfirmware_get_vram_info(adev,
+		r = amdgpu_gmc_get_vram_info(adev,
 				&vram_width, &vram_type, &vram_vendor);
 		adev->gmc.vram_width = vram_width;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 6349e239a367..e6db87b94eb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -751,7 +751,7 @@ static int gmc_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
-	r = amdgpu_atomfirmware_get_vram_info(adev,
+	r = amdgpu_gmc_get_vram_info(adev,
 					      &vram_width, &vram_type, &vram_vendor);
 	adev->gmc.vram_width = vram_width;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index f1079bd8cf00..6e184ea069ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -825,7 +825,7 @@ static int gmc_v12_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(12, 1, 0)) {
 		gmc_v12_1_init_vram_info(adev);
 	} else {
-		r = amdgpu_atomfirmware_get_vram_info(adev,
+		r = amdgpu_gmc_get_vram_info(adev,
 			      &vram_width, &vram_type, &vram_vendor);
 		adev->gmc.vram_width = vram_width;
 		adev->gmc.vram_type = vram_type;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 1ca0202cfdea..d865059e884a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1823,24 +1823,37 @@ static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
 		adev->gmc.sdpif_register = RREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0);
 }
 
-static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
+static void gmc_v9_0_init_vram_info(struct amdgpu_device *adev)
 {
 	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
+	int dev_var = adev->pdev->device & 0xF;
 	u32 vram_info;
 
-	adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
-	adev->gmc.vram_width = 128 * 64;
-
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
-		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM3E;
-
-	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) &&
-		adev->rev_id == 0x3)
-		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM3E;
-
-	if (!(adev->flags & AMD_IS_APU) && !amdgpu_sriov_vf(adev)) {
-		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
-		adev->gmc.vram_vendor = vram_info & 0xF;
+	if (adev->gmc.is_app_apu) {
+		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
+		adev->gmc.vram_width = 128 * 64;
+	} else if (adev->flags & AMD_IS_APU) {
+		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_DDR4;
+		adev->gmc.vram_width = 64 * 64;
+	} else if (amdgpu_is_multi_aid(adev)) {
+		adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
+		adev->gmc.vram_width = 128 * 64;
+
+		if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+			adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM3E;
+
+		if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) &&
+		    adev->rev_id == 0x3)
+			adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM3E;
+
+		if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) &&
+		    (dev_var == 0x5))
+			adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM3E;
+
+		if (!(adev->flags & AMD_IS_APU) && !amdgpu_sriov_vf(adev)) {
+			vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
+			adev->gmc.vram_vendor = vram_info & 0xF;
+		}
 	}
 }
 
@@ -1856,19 +1869,11 @@ static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
-	if (amdgpu_is_multi_aid(adev)) {
-		gmc_v9_4_3_init_vram_info(adev);
-	} else if (!adev->bios) {
-		if (adev->flags & AMD_IS_APU) {
-			adev->gmc.vram_type = AMDGPU_VRAM_TYPE_DDR4;
-			adev->gmc.vram_width = 64 * 64;
-		} else {
-			adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
-			adev->gmc.vram_width = 128 * 64;
-		}
+	if (!adev->bios) {
+		gmc_v9_0_init_vram_info(adev);
 	} else {
-		r = amdgpu_atomfirmware_get_vram_info(adev,
-			&vram_width, &vram_type, &vram_vendor);
+		r = amdgpu_gmc_get_vram_info(adev,
+				&vram_width, &vram_type, &vram_vendor);
 		if (amdgpu_sriov_vf(adev))
 			/* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN,
 			 * and DF related registers is not readable, seems hardcord is the
@@ -1896,6 +1901,7 @@ static int gmc_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 		adev->gmc.vram_type = vram_type;
 		adev->gmc.vram_vendor = vram_vendor;
 	}
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 1, 0):
 	case IP_VERSION(9, 2, 2):
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
index 8c74894254f7..faac21ee5739 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -324,8 +324,10 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		r = amdgpu_userq_input_va_validate(adev, queue, compute_mqd->eop_va,
 						   2048);
-		if (r)
+		if (r) {
+			kfree(compute_mqd);
 			goto free_mqd;
+		}
 
 		userq_props->eop_gpu_addr = compute_mqd->eop_va;
 		userq_props->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_NORMAL;
@@ -365,12 +367,16 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_gfx_v11->shadow_va,
 						   shadow_info.shadow_size);
-		if (r)
+		if (r) {
+			kfree(mqd_gfx_v11);
 			goto free_mqd;
+		}
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_gfx_v11->csa_va,
 						   shadow_info.csa_size);
-		if (r)
+		if (r) {
+			kfree(mqd_gfx_v11);
 			goto free_mqd;
+		}
 
 		kfree(mqd_gfx_v11);
 	} else if (queue->queue_type == AMDGPU_HW_IP_DMA) {
@@ -390,8 +396,10 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 		}
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_sdma_v11->csa_va,
 						   32);
-		if (r)
+		if (r) {
+			kfree(mqd_sdma_v11);
 			goto free_mqd;
+		}
 
 		userq_props->csa_addr = mqd_sdma_v11->csa_va;
 		kfree(mqd_sdma_v11);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 9aa988982304..fb7aaf5ae05c 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -170,7 +170,8 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
 	int retry_loop;
 
 	/* For a reset done at the end of S3, only wait for TOS to be unloaded */
-	if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev))
+	if ((adev->in_s4 || adev->in_s3) && !(adev->flags & AMD_IS_APU) &&
+	    amdgpu_in_reset(adev))
 		return psp_v11_wait_for_tos_unload(psp);
 
 	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 73ce3d211ed6..8a9ba2276275 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -93,6 +93,11 @@ static void uvd_v4_2_ring_set_wptr(struct amdgpu_ring *ring)
 static int uvd_v4_2_early_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+
+	/* UVD doesn't work without DPM, it needs DPM to ungate it. */
+	if (!amdgpu_dpm)
+		return -ENOENT;
+
 	adev->uvd.num_uvd_inst = 1;
 
 	uvd_v4_2_set_ring_funcs(adev);