Merge branch 'for-5.17/core' into for-linus

- support for USI style pens (Tero Kristo, Mika Westerberg)
- quirk for devices that need inverted X/Y axes (Alistair Francis)
- small core code cleanups and deduplication (Benjamin Tissoires)

71 files changed, 763 insertions, 347 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 751557af09bb..a15a4787c7ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -297,7 +297,7 @@ void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd);
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm);
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo);
 void amdgpu_amdkfd_reserve_system_mem(uint64_t size);
 #else
 static inline
@@ -312,7 +312,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 }
 
 static inline
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
 {
 }
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 0e9cfe99ae9e..71acd577803e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -207,7 +207,7 @@ static void unreserve_mem_limit(struct amdgpu_device *adev,
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 }
 
-void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
+void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	u32 domain = bo->preferred_domains;
@@ -219,6 +219,8 @@ void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo)
 	}
 
 	unreserve_mem_limit(adev, amdgpu_bo_size(bo), domain, sg);
+
+	kfree(bo->kfd_bo);
 }
 
 
@@ -734,14 +736,19 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 		}
 
 		/* Add BO to VM internal data structures */
+		ret = amdgpu_bo_reserve(bo[i], false);
+		if (ret) {
+			pr_debug("Unable to reserve BO during memory attach");
+			goto unwind;
+		}
 		attachment[i]->bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+		amdgpu_bo_unreserve(bo[i]);
 		if (unlikely(!attachment[i]->bo_va)) {
 			ret = -ENOMEM;
 			pr_err("Failed to add BO object to VM. ret == %d\n",
 			       ret);
 			goto unwind;
 		}
-
 		attachment[i]->va = va;
 		attachment[i]->pte_flags = get_pte_flags(adev, mem);
 		attachment[i]->adev = adev;
@@ -757,7 +764,9 @@ unwind:
 		if (!attachment[i])
 			continue;
 		if (attachment[i]->bo_va) {
+			amdgpu_bo_reserve(bo[i], true);
 			amdgpu_vm_bo_rmv(adev, attachment[i]->bo_va);
+			amdgpu_bo_unreserve(bo[i]);
 			list_del(&attachment[i]->list);
 		}
 		if (bo[i])
@@ -1568,12 +1577,12 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va,
 		mem->va + bo_size * (1 + mem->aql_queue));
 
-	ret = unreserve_bo_and_vms(&ctx, false, false);
-
 	/* Remove from VM internal data structures */
 	list_for_each_entry_safe(entry, tmp, &mem->attachments, list)
 		kfd_mem_detach(entry);
 
+	ret = unreserve_bo_and_vms(&ctx, false, false);
+
 	/* Free the sync object */
 	amdgpu_sync_free(&mem->sync);
 
@@ -1600,9 +1609,13 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	drm_vma_node_revoke(&mem->bo->tbo.base.vma_node, drm_priv);
 	if (mem->dmabuf)
 		dma_buf_put(mem->dmabuf);
-	drm_gem_object_put(&mem->bo->tbo.base);
 	mutex_destroy(&mem->lock);
-	kfree(mem);
+
+	/* If this releases the last reference, it will end up calling
+	 * amdgpu_amdkfd_release_notify and kfree the mem struct. That's why
+	 * this needs to be the last call here.
+	 */
+	drm_gem_object_put(&mem->bo->tbo.base);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index b9c11c2b2885..0de66f59adb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -827,6 +827,7 @@ static int amdgpu_connector_vga_get_modes(struct drm_connector *connector)
 
 	amdgpu_connector_get_edid(connector);
 	ret = amdgpu_connector_ddc_get_modes(connector);
+	amdgpu_get_native_mode(connector);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e40cc1bc6dc..188accb71249 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2398,10 +2398,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
-	r = amdgpu_amdkfd_resume_iommu(adev);
-	if (r)
-		goto init_failed;
-
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -3171,11 +3167,21 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
 #if defined(CONFIG_DRM_AMD_DC)
-#if defined(CONFIG_DRM_AMD_DC_SI)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
 	case CHIP_VERDE:
 	case CHIP_OLAND:
+		/*
+		 * We have systems in the wild with these ASICs that require
+		 * LVDS and VGA support which is not supported with DC.
+		 *
+		 * Fallback to the non-DC driver here by default so as not to
+		 * cause regressions.
+		 */
+#if defined(CONFIG_DRM_AMD_DC_SI)
+		return amdgpu_dc > 0;
+#else
+		return false;
 #endif
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
@@ -3503,6 +3509,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		adev->rmmio_size = pci_resource_len(adev->pdev, 2);
 	}
 
+	for (i = 0; i < AMD_IP_BLOCK_TYPE_NUM; i++)
+		atomic_set(&adev->pm.pwr_state[i], POWER_STATE_UNKNOWN);
+
 	adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
 	if (adev->rmmio == NULL) {
 		return -ENOMEM;
@@ -4287,8 +4296,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
@@ -4850,6 +4857,9 @@ static void amdgpu_device_recheck_guilty_jobs(
 
 		/* clear job's guilty and depend the folowing step to decide the real one */
 		drm_sched_reset_karma(s_job);
+		/* for the real bad job, it will be resubmitted twice, adding a dma_fence_get
+		 * to make sure fence is balanced */
+		dma_fence_get(s_job->s_fence->parent);
 		drm_sched_resubmit_jobs_ext(&ring->sched, 1);
 
 		ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
@@ -4885,6 +4895,7 @@ retry:
 
 		/* got the hw fence, signal finished fence */
 		atomic_dec(ring->sched.score);
+		dma_fence_put(s_job->s_fence->parent);
 		dma_fence_get(&s_job->s_fence->finished);
 		dma_fence_signal(&s_job->s_fence->finished);
 		dma_fence_put(&s_job->s_fence->finished);
@@ -5020,8 +5031,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
 
-		if (!amdgpu_sriov_vf(tmp_adev))
-			amdgpu_amdkfd_pre_reset(tmp_adev);
+		amdgpu_amdkfd_pre_reset(tmp_adev);
 
 		/*
 		 * Mark these ASICs to be reseted as untracked first
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index d7c8d9e3c203..4e3669407518 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -587,6 +587,9 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add common ip block(GC_HWIP:0x%x)\n",
+			adev->ip_versions[GC_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -619,6 +622,9 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add gmc ip block(GC_HWIP:0x%x)\n",
+			adev->ip_versions[GC_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -648,6 +654,9 @@ static int amdgpu_discovery_set_ih_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add ih ip block(OSSSYS_HWIP:0x%x)\n",
+			adev->ip_versions[OSSSYS_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -688,6 +697,9 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add psp ip block(MP0_HWIP:0x%x)\n",
+			adev->ip_versions[MP0_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -726,6 +738,9 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add smu ip block(MP1_HWIP:0x%x)\n",
+			adev->ip_versions[MP1_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -753,6 +768,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add dm ip block(DCE_HWIP:0x%x)\n",
+				adev->ip_versions[DCE_HWIP][0]);
 			return -EINVAL;
 		}
 	} else if (adev->ip_versions[DCI_HWIP][0]) {
@@ -763,6 +781,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add dm ip block(DCI_HWIP:0x%x)\n",
+				adev->ip_versions[DCI_HWIP][0]);
 			return -EINVAL;
 		}
 #endif
@@ -796,6 +817,9 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add gfx ip block(GC_HWIP:0x%x)\n",
+			adev->ip_versions[GC_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -829,6 +853,9 @@ static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add sdma ip block(SDMA0_HWIP:0x%x)\n",
+			adev->ip_versions[SDMA0_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -845,6 +872,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 				amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add uvd v7 ip block(UVD_HWIP:0x%x)\n",
+				adev->ip_versions[UVD_HWIP][0]);
 			return -EINVAL;
 		}
 		switch (adev->ip_versions[VCE_HWIP][0]) {
@@ -855,6 +885,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 				amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add VCE v4 ip block(VCE_HWIP:0x%x)\n",
+				adev->ip_versions[VCE_HWIP][0]);
 			return -EINVAL;
 		}
 	} else {
@@ -867,7 +900,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 		case IP_VERSION(2, 0, 2):
 		case IP_VERSION(2, 2, 0):
 			amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
-			amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
+			if (!amdgpu_sriov_vf(adev))
+				amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 			break;
 		case IP_VERSION(2, 0, 3):
 			break;
@@ -881,6 +915,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 			break;
 		case IP_VERSION(3, 0, 0):
 		case IP_VERSION(3, 0, 16):
+		case IP_VERSION(3, 0, 64):
 		case IP_VERSION(3, 1, 1):
 		case IP_VERSION(3, 0, 2):
 			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
@@ -891,6 +926,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add vcn/jpeg ip block(UVD_HWIP:0x%x)\n",
+				adev->ip_versions[UVD_HWIP][0]);
 			return -EINVAL;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index a573424a6e0b..a1e63ba4c54a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -60,9 +60,10 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
 			goto unlock;
 		}
 
-		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
-					       TTM_BO_VM_NUM_PREFAULT, 1);
-		drm_dev_exit(idx);
+		 ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+						TTM_BO_VM_NUM_PREFAULT);
+
+		 drm_dev_exit(idx);
 	} else {
 		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index dfe667ea8b05..651c7abfde03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1423,6 +1423,8 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 	struct drm_amdgpu_info_firmware fw_info;
 	struct drm_amdgpu_query_fw query_fw;
 	struct atom_context *ctx = adev->mode_info.atom_context;
+	uint8_t smu_minor, smu_debug;
+	uint16_t smu_major;
 	int ret, i;
 
 	static const char *ta_fw_name[TA_FW_TYPE_MAX_INDEX] = {
@@ -1568,8 +1570,11 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
 	if (ret)
 		return ret;
-	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n",
-		   fw_info.feature, fw_info.ver);
+	smu_major = (fw_info.ver >> 16) & 0xffff;
+	smu_minor = (fw_info.ver >> 8) & 0xff;
+	smu_debug = (fw_info.ver >> 0) & 0xff;
+	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x (%d.%d.%d)\n",
+		   fw_info.feature, fw_info.ver, smu_major, smu_minor, smu_debug);
 
 	/* SDMA */
 	query_fw.fw_type = AMDGPU_INFO_FW_SDMA;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aeb92e5677ac..4fcfc2313b8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1274,7 +1274,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 	abo = ttm_to_amdgpu_bo(bo);
 
 	if (abo->kfd_bo)
-		amdgpu_amdkfd_unreserve_memory_limit(abo);
+		amdgpu_amdkfd_release_notify(abo);
 
 	/* We only remove the fence if the resv has individualized. */
 	WARN_ON_ONCE(bo->type == ttm_bo_type_kernel
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 2658414c503d..4f7c70845785 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -134,6 +134,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 			adev->vcn.indirect_sram = true;
 		break;
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 64):
 		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0))
 			fw_name = FIRMWARE_SIENNA_CICHLID;
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 978ac927ac11..567df2db23ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -386,6 +386,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 			"%s", "xgmi_hive_info");
 	if (ret) {
 		dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+		kobject_put(&hive->kobj);
 		kfree(hive);
 		hive = NULL;
 		goto pro_end;
@@ -806,9 +807,9 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
 		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
 			pcs_clear_status(adev,
 					 xgmi23_pcs_err_status_reg_aldebaran[i]);
-		for (i = 0; i < ARRAY_SIZE(xgmi23_pcs_err_status_reg_aldebaran); i++)
+		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++)
 			pcs_clear_status(adev,
-					 xgmi23_pcs_err_status_reg_aldebaran[i]);
+					 xgmi3x16_pcs_err_status_reg_aldebaran[i]);
 		for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++)
 			pcs_clear_status(adev,
 					 walf_pcs_err_status_reg_aldebaran[i]);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 90a834dc4008..e7dfeb466a0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -8249,6 +8249,9 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 reg, data;
+
+	amdgpu_gfx_off_ctrl(adev, false);
+
 	/* not for *_SOC15 */
 	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
@@ -8263,6 +8266,8 @@ static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
 	else
 		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev,
@@ -8316,11 +8321,8 @@ static void gfx_v10_cntl_power_gating(struct amdgpu_device *adev, bool enable)
 	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		switch (adev->ip_versions[GC_HWIP][0]) {
 		case IP_VERSION(10, 3, 1):
-			data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
-			WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
-			break;
 		case IP_VERSION(10, 3, 3):
-			data = 0x1388 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
+			data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
 			WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 37b4a3db6360..d17a6f399347 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3575,12 +3575,16 @@ static void gfx_v7_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 data;
 
+	amdgpu_gfx_off_ctrl(adev, false);
+
 	data = RREG32(mmRLC_SPM_VMID);
 
 	data &= ~RLC_SPM_VMID__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_VMID__RLC_SPM_VMID_MASK) << RLC_SPM_VMID__RLC_SPM_VMID__SHIFT;
 
 	WREG32(mmRLC_SPM_VMID, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index e0302c23e9a7..5f112efda634 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5624,6 +5624,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 data;
 
+	amdgpu_gfx_off_ctrl(adev, false);
+
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(mmRLC_SPM_VMID);
 	else
@@ -5636,6 +5638,8 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_NO_KIQ(mmRLC_SPM_VMID, data);
 	else
 		WREG32(mmRLC_SPM_VMID, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static const struct amdgpu_rlc_funcs iceland_rlc_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 7f944bb11298..b4b80f27b894 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2462,7 +2462,9 @@ static int gfx_v9_0_sw_fini(void *handle)
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v9_0_mec_fini(adev);
-	amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj);
+	amdgpu_bo_free_kernel(&adev->gfx.rlc.clear_state_obj,
+				&adev->gfx.rlc.clear_state_gpu_addr,
+				(void **)&adev->gfx.rlc.cs_ptr);
 	if (adev->flags & AMD_IS_APU) {
 		amdgpu_bo_free_kernel(&adev->gfx.rlc.cp_table_obj,
 				&adev->gfx.rlc.cp_table_gpu_addr,
@@ -5102,6 +5104,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 reg, data;
 
+	amdgpu_gfx_off_ctrl(adev, false);
+
 	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
@@ -5115,6 +5119,8 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
 	else
 		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static bool gfx_v9_0_check_rlcg_range(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index bda1542ef1dd..480e41847d7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -348,6 +348,10 @@ static void gfxhub_v1_0_gart_disable(struct amdgpu_device *adev)
 		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT0_CNTL,
 				    i * hub->ctx_distance, 0);
 
+	if (amdgpu_sriov_vf(adev))
+		/* Avoid write to GMC registers */
+		return;
+
 	/* Setup TLB control */
 	tmp = RREG32_SOC15(GC, 0, mmMC_VM_MX_L1_TLB_CNTL);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index 497b86c376c6..90f0aefbdb39 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -54,15 +54,17 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		seg_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE_ALDE),
 			MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+		max_region =
+			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE, PF_MAX_REGION);
 	} else {
 		xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
 		seg_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE),
 			MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+		max_region =
+			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
 	}
 
-	max_region =
-		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
 
 
 	switch (adev->asic_type) {
@@ -89,9 +91,15 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
 			return -EINVAL;
 
-		adev->gmc.xgmi.physical_node_id =
-		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
-			      PF_LFB_REGION);
+		if (adev->asic_type == CHIP_ALDEBARAN) {
+			adev->gmc.xgmi.physical_node_id =
+				REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE,
+						PF_LFB_REGION);
+		} else {
+			adev->gmc.xgmi.physical_node_id =
+				REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
+						PF_LFB_REGION);
+		}
 
 		if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index febc903adf58..59eafa31c626 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -182,6 +182,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 {
 	switch (adev->ip_versions[UVD_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 64):
 		if (amdgpu_sriov_vf(adev)) {
 			if (encode)
 				*codecs = &sriov_sc_video_codecs_encode;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index d5d023a24269..2d558c2f417d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -534,6 +534,19 @@ static int uvd_v6_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
+	if (RREG32(mmUVD_STATUS) != 0)
+		uvd_v6_0_stop(adev);
+
+	return 0;
+}
+
+static int uvd_v6_0_suspend(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
 	/*
 	 * Proper cleanups before halting the HW engine:
 	 *   - cancel the delayed idle work
@@ -558,17 +571,6 @@ static int uvd_v6_0_hw_fini(void *handle)
 						       AMD_CG_STATE_GATE);
 	}
 
-	if (RREG32(mmUVD_STATUS) != 0)
-		uvd_v6_0_stop(adev);
-
-	return 0;
-}
-
-static int uvd_v6_0_suspend(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
 	r = uvd_v6_0_hw_fini(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 0fffaf859c59..3b119db16003 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -406,7 +406,7 @@ static const struct kfd_device_info aldebaran_device_info = {
 static const struct kfd_device_info renoir_device_info = {
 	.asic_family = CHIP_RENOIR,
 	.asic_name = "renoir",
-	.gfx_target_version = 90002,
+	.gfx_target_version = 90012,
 	.max_pasid_bits = 16,
 	.max_no_of_hqd  = 24,
 	.doorbell_size  = 8,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 533b27b35fc9..93e33dd84dd4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1226,6 +1226,11 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	bool hanging;
 
 	dqm_lock(dqm);
+	if (!dqm->sched_running) {
+		dqm_unlock(dqm);
+		return 0;
+	}
+
 	if (!dqm->is_hws_hang)
 		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	hanging = dqm->is_hws_hang || dqm->is_resetting;
@@ -1430,7 +1435,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 
 	if (!dqm->sched_running)
 		return 0;
-	if (dqm->is_hws_hang)
+	if (dqm->is_hws_hang || dqm->is_resetting)
 		return -EIO;
 	if (!dqm->active_runlist)
 		return retval;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index 2e86692def19..d1388896f9c1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -308,7 +308,7 @@
  * 16MB are reserved for kernel use (CWSR trap handler and kernel IB
  * for now).
  */
-#define SVM_USER_BASE 0x1000000ull
+#define SVM_USER_BASE (u64)(KFD_CWSR_TBA_TMA_SIZE + 2*PAGE_SIZE)
 #define SVM_CWSR_BASE (SVM_USER_BASE - KFD_CWSR_TBA_TMA_SIZE)
 #define SVM_IB_BASE   (SVM_CWSR_BASE - PAGE_SIZE)
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 6d8634e40b3b..9b9c2b9bf2ef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -281,6 +281,19 @@ static unsigned long svm_migrate_successful_pages(struct migrate_vma *migrate)
 	return cpages;
 }
 
+static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate)
+{
+	unsigned long upages = 0;
+	unsigned long i;
+
+	for (i = 0; i < migrate->npages; i++) {
+		if (migrate->src[i] & MIGRATE_PFN_VALID &&
+		    !(migrate->src[i] & MIGRATE_PFN_MIGRATE))
+			upages++;
+	}
+	return upages;
+}
+
 static int
 svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
@@ -317,7 +330,6 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
 			svm_migrate_get_vram_page(prange, migrate->dst[i]);
 			migrate->dst[i] = migrate_pfn(migrate->dst[i]);
-			migrate->dst[i] |= MIGRATE_PFN_LOCKED;
 			src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE,
 					      DMA_TO_DEVICE);
 			r = dma_mapping_error(dev, src[i]);
@@ -610,7 +622,6 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 				     dst[i] >> PAGE_SHIFT, page_to_pfn(dpage));
 
 		migrate->dst[i] = migrate_pfn(page_to_pfn(dpage));
-		migrate->dst[i] |= MIGRATE_PFN_LOCKED;
 		j++;
 	}
 
@@ -634,10 +645,11 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 		       struct vm_area_struct *vma, uint64_t start, uint64_t end)
 {
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
+	unsigned long upages = npages;
+	unsigned long cpages = 0;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
 	struct migrate_vma migrate;
-	unsigned long cpages = 0;
 	dma_addr_t *scratch;
 	size_t size;
 	void *buf;
@@ -671,6 +683,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	if (!cpages) {
 		pr_debug("failed collect migrate device pages [0x%lx 0x%lx]\n",
 			 prange->start, prange->last);
+		upages = svm_migrate_unsuccessful_pages(&migrate);
 		goto out_free;
 	}
 	if (cpages != npages)
@@ -683,8 +696,9 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 				    scratch, npages);
 	migrate_vma_pages(&migrate);
 
-	pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
-		svm_migrate_successful_pages(&migrate), cpages, migrate.npages);
+	upages = svm_migrate_unsuccessful_pages(&migrate);
+	pr_debug("unsuccessful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
+		 upages, cpages, migrate.npages);
 
 	svm_migrate_copy_done(adev, mfence);
 	migrate_vma_finalize(&migrate);
@@ -698,9 +712,9 @@ out:
 		if (pdd)
 			WRITE_ONCE(pdd->page_out, pdd->page_out + cpages);
 
-		return cpages;
+		return upages;
 	}
-	return r;
+	return r ? r : upages;
 }
 
 /**
@@ -720,7 +734,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
 	unsigned long addr;
 	unsigned long start;
 	unsigned long end;
-	unsigned long cpages = 0;
+	unsigned long upages = 0;
 	long r = 0;
 
 	if (!prange->actual_loc) {
@@ -756,12 +770,12 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
 			pr_debug("failed %ld to migrate\n", r);
 			break;
 		} else {
-			cpages += r;
+			upages += r;
 		}
 		addr = next;
 	}
 
-	if (cpages) {
+	if (!upages) {
 		svm_range_vram_node_free(prange);
 		prange->actual_loc = 0;
 	}
@@ -784,7 +798,7 @@ static int
 svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 			 struct mm_struct *mm)
 {
-	int r;
+	int r, retries = 3;
 
 	/*
 	 * TODO: for both devices with PCIe large bar or on same xgmi hive, skip
@@ -793,9 +807,14 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 
 	pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc);
 
-	r = svm_migrate_vram_to_ram(prange, mm);
-	if (r)
-		return r;
+	do {
+		r = svm_migrate_vram_to_ram(prange, mm);
+		if (r)
+			return r;
+	} while (prange->actual_loc && --retries);
+
+	if (prange->actual_loc)
+		return -EDEADLK;
 
 	return svm_migrate_ram_to_vram(prange, best_loc, mm);
 }
@@ -840,6 +859,11 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf)
 		pr_debug("failed find process at fault address 0x%lx\n", addr);
 		return VM_FAULT_SIGBUS;
 	}
+	if (READ_ONCE(p->svms.faulting_task) == current) {
+		pr_debug("skipping ram migration\n");
+		kfd_unref_process(p);
+		return 0;
+	}
 	addr >>= PAGE_SHIFT;
 	pr_debug("CPU page fault svms 0x%p address 0x%lx\n", &p->svms, addr);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 4104b167e721..94e92c0812db 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -766,8 +766,10 @@ struct svm_range_list {
 	struct list_head		deferred_range_list;
 	spinlock_t			deferred_list_lock;
 	atomic_t			evicted_ranges;
+	bool				drain_pagefaults;
 	struct delayed_work		restore_work;
 	DECLARE_BITMAP(bitmap_supported, MAX_GPU_INSTANCE);
+	struct task_struct 		*faulting_task;
 };
 
 /* Process data */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 457863861d6f..b993011cfa64 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1715,7 +1715,11 @@ int kfd_process_evict_queues(struct kfd_process *p)
 
 		r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm,
 							    &pdd->qpd);
-		if (r) {
+		/* evict return -EIO if HWS is hang or asic is resetting, in this case
+		 * we would like to set all the queues to be in evicted state to prevent
+		 * them been add back since they actually not be saved right now.
+		 */
+		if (r && r != -EIO) {
 			pr_err("Failed to evict process queues\n");
 			goto fail;
 		}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index b691c8495d66..16137c4247bb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1496,9 +1496,11 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 
 		next = min(vma->vm_end, end);
 		npages = (next - addr) >> PAGE_SHIFT;
+		WRITE_ONCE(p->svms.faulting_task, current);
 		r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
 					       addr, npages, &hmm_range,
 					       readonly, true, owner);
+		WRITE_ONCE(p->svms.faulting_task, NULL);
 		if (r) {
 			pr_debug("failed %d to get svm range pages\n", r);
 			goto unreserve_out;
@@ -2000,20 +2002,28 @@ static void svm_range_deferred_list_work(struct work_struct *work)
 		pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange,
 			 prange->start, prange->last, prange->work_item.op);
 
-		/* Make sure no stale retry fault coming after range is freed */
-		if (prange->work_item.op == SVM_OP_UNMAP_RANGE)
-			svm_range_drain_retry_fault(prange->svms);
-
 		mm = prange->work_item.mm;
+retry:
 		mmap_write_lock(mm);
 		mutex_lock(&svms->lock);
 
-		/* Remove from deferred_list must be inside mmap write lock,
+		/* Checking for the need to drain retry faults must be in
+		 * mmap write lock to serialize with munmap notifiers.
+		 *
+		 * Remove from deferred_list must be inside mmap write lock,
 		 * otherwise, svm_range_list_lock_and_flush_work may hold mmap
 		 * write lock, and continue because deferred_list is empty, then
 		 * deferred_list handle is blocked by mmap write lock.
 		 */
 		spin_lock(&svms->deferred_list_lock);
+		if (unlikely(svms->drain_pagefaults)) {
+			svms->drain_pagefaults = false;
+			spin_unlock(&svms->deferred_list_lock);
+			mutex_unlock(&svms->lock);
+			mmap_write_unlock(mm);
+			svm_range_drain_retry_fault(svms);
+			goto retry;
+		}
 		list_del_init(&prange->deferred_list);
 		spin_unlock(&svms->deferred_list_lock);
 
@@ -2046,6 +2056,12 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
 			struct mm_struct *mm, enum svm_work_list_ops op)
 {
 	spin_lock(&svms->deferred_list_lock);
+	/* Make sure pending page faults are drained in the deferred worker
+	 * before the range is freed to avoid straggler interrupts on
+	 * unmapped memory causing "phantom faults".
+	 */
+	if (op == SVM_OP_UNMAP_RANGE)
+		svms->drain_pagefaults = true;
 	/* if prange is on the deferred list */
 	if (!list_empty(&prange->deferred_list)) {
 		pr_debug("update exist prange 0x%p work op %d\n", prange, op);
@@ -2261,7 +2277,7 @@ svm_range_from_addr(struct svm_range_list *svms, unsigned long addr,
  * migration if actual loc is not best location, then update GPU page table
  * mapping to the best location.
  *
- * If vm fault gpu is range preferred loc, the best_loc is preferred loc.
+ * If the preferred loc is accessible by faulting GPU, use preferred loc.
  * If vm fault gpu idx is on range ACCESSIBLE bitmap, best_loc is vm fault gpu
  * If vm fault gpu idx is on range ACCESSIBLE_IN_PLACE bitmap, then
  *    if range actual loc is cpu, best_loc is cpu
@@ -2278,7 +2294,7 @@ svm_range_best_restore_location(struct svm_range *prange,
 				struct amdgpu_device *adev,
 				int32_t *gpuidx)
 {
-	struct amdgpu_device *bo_adev;
+	struct amdgpu_device *bo_adev, *preferred_adev;
 	struct kfd_process *p;
 	uint32_t gpuid;
 	int r;
@@ -2291,8 +2307,16 @@ svm_range_best_restore_location(struct svm_range *prange,
 		return -1;
 	}
 
-	if (prange->preferred_loc == gpuid)
+	if (prange->preferred_loc == gpuid ||
+	    prange->preferred_loc == KFD_IOCTL_SVM_LOCATION_SYSMEM) {
 		return prange->preferred_loc;
+	} else if (prange->preferred_loc != KFD_IOCTL_SVM_LOCATION_UNDEFINED) {
+		preferred_adev = svm_range_get_adev_by_id(prange,
+							prange->preferred_loc);
+		if (amdgpu_xgmi_same_hive(adev, preferred_adev))
+			return prange->preferred_loc;
+		/* fall through */
+	}
 
 	if (test_bit(*gpuidx, prange->bitmap_access))
 		return gpuid;
@@ -2313,7 +2337,8 @@ svm_range_best_restore_location(struct svm_range *prange,
 
 static int
 svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
-				unsigned long *start, unsigned long *last)
+			       unsigned long *start, unsigned long *last,
+			       bool *is_heap_stack)
 {
 	struct vm_area_struct *vma;
 	struct interval_tree_node *node;
@@ -2324,6 +2349,12 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 		pr_debug("VMA does not exist in address [0x%llx]\n", addr);
 		return -EFAULT;
 	}
+
+	*is_heap_stack = (vma->vm_start <= vma->vm_mm->brk &&
+			  vma->vm_end >= vma->vm_mm->start_brk) ||
+			 (vma->vm_start <= vma->vm_mm->start_stack &&
+			  vma->vm_end >= vma->vm_mm->start_stack);
+
 	start_limit = max(vma->vm_start >> PAGE_SHIFT,
 		      (unsigned long)ALIGN_DOWN(addr, 2UL << 8));
 	end_limit = min(vma->vm_end >> PAGE_SHIFT,
@@ -2353,9 +2384,9 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 	*start = start_limit;
 	*last = end_limit - 1;
 
-	pr_debug("vma start: 0x%lx start: 0x%lx vma end: 0x%lx last: 0x%lx\n",
-		  vma->vm_start >> PAGE_SHIFT, *start,
-		  vma->vm_end >> PAGE_SHIFT, *last);
+	pr_debug("vma [0x%lx 0x%lx] range [0x%lx 0x%lx] is_heap_stack %d\n",
+		 vma->vm_start >> PAGE_SHIFT, vma->vm_end >> PAGE_SHIFT,
+		 *start, *last, *is_heap_stack);
 
 	return 0;
 }
@@ -2420,11 +2451,13 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev,
 	struct svm_range *prange = NULL;
 	unsigned long start, last;
 	uint32_t gpuid, gpuidx;
+	bool is_heap_stack;
 	uint64_t bo_s = 0;
 	uint64_t bo_l = 0;
 	int r;
 
-	if (svm_range_get_range_boundaries(p, addr, &start, &last))
+	if (svm_range_get_range_boundaries(p, addr, &start, &last,
+					   &is_heap_stack))
 		return NULL;
 
 	r = svm_range_check_vm(p, start, last, &bo_s, &bo_l);
@@ -2451,6 +2484,9 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev,
 		return NULL;
 	}
 
+	if (is_heap_stack)
+		prange->preferred_loc = KFD_IOCTL_SVM_LOCATION_SYSMEM;
+
 	svm_range_add_to_svms(prange);
 	svm_range_add_notifier_locked(mm, prange);
 
@@ -3076,6 +3112,8 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 		struct svm_range *prange =
 				list_first_entry(&svm_bo->range_list,
 						struct svm_range, svm_bo_list);
+		int retries = 3;
+
 		list_del_init(&prange->svm_bo_list);
 		spin_unlock(&svm_bo->list_lock);
 
@@ -3083,7 +3121,11 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 			 prange->start, prange->last);
 
 		mutex_lock(&prange->migrate_mutex);
-		svm_migrate_vram_to_ram(prange, svm_bo->eviction_fence->mm);
+		do {
+			svm_migrate_vram_to_ram(prange,
+						svm_bo->eviction_fence->mm);
+		} while (prange->actual_loc && --retries);
+		WARN(prange->actual_loc, "Migration failed during eviction");
 
 		mutex_lock(&prange->lock);
 		prange->svm_bo = NULL;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 43e983e42c0f..c27cb47bc988 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -217,6 +217,7 @@ static const struct drm_format_info *
 amd_get_format_info(const struct drm_mode_fb_cmd2 *cmd);
 
 static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector);
+static void handle_hpd_rx_irq(void *param);
 
 static bool
 is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state,
@@ -619,7 +620,7 @@ static void dm_dcn_vertical_interrupt0_high_irq(void *interrupt_params)
 
 	amdgpu_dm_crtc_handle_crc_window_irq(&acrtc->base);
 }
-#endif
+#endif /* CONFIG_DRM_AMD_SECURE_DISPLAY */
 
 /**
  * dmub_aux_setconfig_reply_callback - Callback for AUX or SET_CONFIG command.
@@ -669,10 +670,7 @@ void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *not
 		return;
 	}
 
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-
 	link_index = notify->link_index;
-
 	link = adev->dm.dc->links[link_index];
 
 	drm_connector_list_iter_begin(dev, &iter);
@@ -685,10 +683,13 @@ void dmub_hpd_callback(struct amdgpu_device *adev, struct dmub_notification *not
 		}
 	}
 	drm_connector_list_iter_end(&iter);
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 
-	if (hpd_aconnector)
-		handle_hpd_irq_helper(hpd_aconnector);
+	if (hpd_aconnector) {
+		if (notify->type == DMUB_NOTIFICATION_HPD)
+			handle_hpd_irq_helper(hpd_aconnector);
+		else if (notify->type == DMUB_NOTIFICATION_HPD_IRQ)
+			handle_hpd_rx_irq(hpd_aconnector);
+	}
 }
 
 /**
@@ -764,6 +765,10 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params)
 				DRM_ERROR("DM: notify type %d invalid!", notify.type);
 				continue;
 			}
+			if (!dm->dmub_callback[notify.type]) {
+				DRM_DEBUG_DRIVER("DMUB notification skipped, no handler: type=%d\n", notify.type);
+				continue;
+			}
 			if (dm->dmub_thread_offload[notify.type] == true) {
 				dmub_hpd_wrk = kzalloc(sizeof(*dmub_hpd_wrk), GFP_ATOMIC);
 				if (!dmub_hpd_wrk) {
@@ -813,7 +818,7 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params)
 	if (count > DMUB_TRACE_MAX_READ)
 		DRM_DEBUG_DRIVER("Warning : count > DMUB_TRACE_MAX_READ");
 }
-#endif
+#endif /* CONFIG_DRM_AMD_DC_DCN */
 
 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
@@ -1410,7 +1415,15 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		switch (adev->ip_versions[DCE_HWIP][0]) {
 		case IP_VERSION(2, 1, 0):
 			init_data.flags.gpu_vm_support = true;
-			init_data.flags.disable_dmcu = true;
+			switch (adev->dm.dmcub_fw_version) {
+			case 0: /* development */
+			case 0x1: /* linux-firmware.git hash 6d9f399 */
+			case 0x01000000: /* linux-firmware.git hash 9a0b0f4 */
+				init_data.flags.disable_dmcu = false;
+				break;
+			default:
+				init_data.flags.disable_dmcu = true;
+			}
 			break;
 		case IP_VERSION(1, 0, 0):
 		case IP_VERSION(1, 0, 1):
@@ -1556,7 +1569,11 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
 			goto error;
 		}
-#endif
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) {
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+			goto error;
+		}
+#endif /* CONFIG_DRM_AMD_DC_DCN */
 	}
 
 	if (amdgpu_dm_initialize_drm_device(adev)) {
@@ -4225,7 +4242,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		} else if (dc_link_detect(link, DETECT_REASON_BOOT)) {
 			amdgpu_dm_update_connector_after_detect(aconnector);
 			register_backlight_device(dm, link);
-
+			if (dm->num_of_edps)
+				update_connector_ext_caps(aconnector);
 			if (psr_feature_enabled)
 				amdgpu_dm_set_psr_caps(link);
 		}
@@ -4565,7 +4583,8 @@ static void get_min_max_dc_plane_scaling(struct drm_device *dev,
 }
 
 
-static int fill_dc_scaling_info(const struct drm_plane_state *state,
+static int fill_dc_scaling_info(struct amdgpu_device *adev,
+				const struct drm_plane_state *state,
 				struct dc_scaling_info *scaling_info)
 {
 	int scale_w, scale_h, min_downscale, max_upscale;
@@ -4579,7 +4598,8 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state,
 	/*
 	 * For reasons we don't (yet) fully understand a non-zero
 	 * src_y coordinate into an NV12 buffer can cause a
-	 * system hang. To avoid hangs (and maybe be overly cautious)
+	 * system hang on DCN1x.
+	 * To avoid hangs (and maybe be overly cautious)
 	 * let's reject both non-zero src_x and src_y.
 	 *
 	 * We currently know of only one use-case to reproduce a
@@ -4587,10 +4607,10 @@ static int fill_dc_scaling_info(const struct drm_plane_state *state,
 	 * is to gesture the YouTube Android app into full screen
 	 * on ChromeOS.
 	 */
-	if (state->fb &&
-	    state->fb->format->format == DRM_FORMAT_NV12 &&
-	    (scaling_info->src_rect.x != 0 ||
-	     scaling_info->src_rect.y != 0))
+	if (((adev->ip_versions[DCE_HWIP][0] == IP_VERSION(1, 0, 0)) ||
+	    (adev->ip_versions[DCE_HWIP][0] == IP_VERSION(1, 0, 1))) &&
+	    (state->fb && state->fb->format->format == DRM_FORMAT_NV12 &&
+	    (scaling_info->src_rect.x != 0 || scaling_info->src_rect.y != 0)))
 		return -EINVAL;
 
 	scaling_info->src_rect.width = state->src_w >> 16;
@@ -5496,7 +5516,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	int ret;
 	bool force_disable_dcc = false;
 
-	ret = fill_dc_scaling_info(plane_state, &scaling_info);
+	ret = fill_dc_scaling_info(adev, plane_state, &scaling_info);
 	if (ret)
 		return ret;
 
@@ -6070,7 +6090,7 @@ static void apply_dsc_policy_for_stream(struct amdgpu_dm_connector *aconnector,
 	if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_bits_per_pixel)
 		stream->timing.dsc_cfg.bits_per_pixel = aconnector->dsc_settings.dsc_bits_per_pixel;
 }
-#endif
+#endif /* CONFIG_DRM_AMD_DC_DCN */
 
 /**
  * DOC: FreeSync Video
@@ -7241,8 +7261,8 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 	struct drm_connector_state *new_con_state;
 	struct amdgpu_dm_connector *aconnector;
 	struct dm_connector_state *dm_conn_state;
-	int i, j, clock;
-	int vcpi, pbn_div, pbn = 0;
+	int i, j;
+	int vcpi, pbn_div, pbn, slot_num = 0;
 
 	for_each_new_connector_in_state(state, connector, new_con_state, i) {
 
@@ -7270,17 +7290,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 		if (!stream)
 			continue;
 
-		if (stream->timing.flags.DSC != 1) {
-			drm_dp_mst_atomic_enable_dsc(state,
-						     aconnector->port,
-						     dm_conn_state->pbn,
-						     0,
-						     false);
-			continue;
-		}
-
 		pbn_div = dm_mst_get_pbn_divider(stream->link);
-		clock = stream->timing.pix_clk_100hz / 10;
 		/* pbn is calculated by compute_mst_dsc_configs_for_state*/
 		for (j = 0; j < dc_state->stream_count; j++) {
 			if (vars[j].aconnector == aconnector) {
@@ -7289,6 +7299,23 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
 			}
 		}
 
+		if (j == dc_state->stream_count)
+			continue;
+
+		slot_num = DIV_ROUND_UP(pbn, pbn_div);
+
+		if (stream->timing.flags.DSC != 1) {
+			dm_conn_state->pbn = pbn;
+			dm_conn_state->vcpi_slots = slot_num;
+
+			drm_dp_mst_atomic_enable_dsc(state,
+						     aconnector->port,
+						     dm_conn_state->pbn,
+						     0,
+						     false);
+			continue;
+		}
+
 		vcpi = drm_dp_mst_atomic_enable_dsc(state,
 						    aconnector->port,
 						    pbn, pbn_div,
@@ -7552,7 +7579,7 @@ static int dm_plane_atomic_check(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
-	ret = fill_dc_scaling_info(new_plane_state, &scaling_info);
+	ret = fill_dc_scaling_info(adev, new_plane_state, &scaling_info);
 	if (ret)
 		return ret;
 
@@ -9000,7 +9027,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			bundle->surface_updates[planes_count].gamut_remap_matrix = &dc_plane->gamut_remap_matrix;
 		}
 
-		fill_dc_scaling_info(new_plane_state,
+		fill_dc_scaling_info(dm->adev, new_plane_state,
 				     &bundle->scaling_infos[planes_count]);
 
 		bundle->surface_updates[planes_count].scaling_info =
@@ -10787,7 +10814,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 
 		ret = drm_atomic_add_affected_connectors(state, crtc);
 		if (ret)
-			return ret;
+			goto fail;
 
 		ret = drm_atomic_add_affected_planes(state, crtc);
 		if (ret)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 3655663e079b..9d43ecb1f692 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -78,12 +78,10 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size,
 
 	wr_buf_ptr = wr_buf;
 
-	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
-
-		/* r is bytes not be copied */
-	if (r >= wr_buf_size) {
-		DRM_DEBUG_DRIVER("user data not be read\n");
-		return -EINVAL;
+	/* r is bytes not be copied */
+	if (copy_from_user(wr_buf_ptr, buf, wr_buf_size)) {
+		DRM_DEBUG_DRIVER("user data could not be read successfully\n");
+		return -EFAULT;
 	}
 
 	/* check number of parameters. isspace could not differ space and \n */
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 874a49b605c7..32a5ce09a62a 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
@@ -534,13 +534,14 @@ static int kbps_to_peak_pbn(int kbps)
 
 static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params,
 		struct dsc_mst_fairness_vars *vars,
-		int count)
+		int count,
+		int k)
 {
 	int i;
 
 	for (i = 0; i < count; i++) {
 		memset(&params[i].timing->dsc_cfg, 0, sizeof(params[i].timing->dsc_cfg));
-		if (vars[i].dsc_enabled && dc_dsc_compute_config(
+		if (vars[i + k].dsc_enabled && dc_dsc_compute_config(
 					params[i].sink->ctx->dc->res_pool->dscs[0],
 					&params[i].sink->dsc_caps.dsc_dec_caps,
 					params[i].sink->ctx->dc->debug.dsc_min_slice_height_override,
@@ -553,7 +554,7 @@ static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *p
 			if (params[i].bpp_overwrite)
 				params[i].timing->dsc_cfg.bits_per_pixel = params[i].bpp_overwrite;
 			else
-				params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
+				params[i].timing->dsc_cfg.bits_per_pixel = vars[i + k].bpp_x16;
 
 			if (params[i].num_slices_h)
 				params[i].timing->dsc_cfg.num_slices_h = params[i].num_slices_h;
@@ -586,7 +587,8 @@ static void increase_dsc_bpp(struct drm_atomic_state *state,
 			     struct dc_link *dc_link,
 			     struct dsc_mst_fairness_params *params,
 			     struct dsc_mst_fairness_vars *vars,
-			     int count)
+			     int count,
+			     int k)
 {
 	int i;
 	bool bpp_increased[MAX_PIPES];
@@ -601,8 +603,9 @@ static void increase_dsc_bpp(struct drm_atomic_state *state,
 	pbn_per_timeslot = dm_mst_get_pbn_divider(dc_link);
 
 	for (i = 0; i < count; i++) {
-		if (vars[i].dsc_enabled) {
-			initial_slack[i] = kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i].pbn;
+		if (vars[i + k].dsc_enabled) {
+			initial_slack[i] =
+			kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn;
 			bpp_increased[i] = false;
 			remaining_to_increase += 1;
 		} else {
@@ -629,7 +632,7 @@ static void increase_dsc_bpp(struct drm_atomic_state *state,
 		link_timeslots_used = 0;
 
 		for (i = 0; i < count; i++)
-			link_timeslots_used += DIV_ROUND_UP(vars[i].pbn, pbn_per_timeslot);
+			link_timeslots_used += DIV_ROUND_UP(vars[i + k].pbn, pbn_per_timeslot);
 
 		fair_pbn_alloc = (63 - link_timeslots_used) / remaining_to_increase * pbn_per_timeslot;
 
@@ -682,7 +685,8 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 			    struct dc_link *dc_link,
 			    struct dsc_mst_fairness_params *params,
 			    struct dsc_mst_fairness_vars *vars,
-			    int count)
+			    int count,
+			    int k)
 {
 	int i;
 	bool tried[MAX_PIPES];
@@ -692,8 +696,8 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 	int remaining_to_try = 0;
 
 	for (i = 0; i < count; i++) {
-		if (vars[i].dsc_enabled
-				&& vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16
+		if (vars[i + k].dsc_enabled
+				&& vars[i + k].bpp_x16 == params[i].bw_range.max_target_bpp_x16
 				&& params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) {
 			kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps;
 			tried[i] = false;
@@ -748,9 +752,10 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 					     struct dc_state *dc_state,
 					     struct dc_link *dc_link,
-					     struct dsc_mst_fairness_vars *vars)
+					     struct dsc_mst_fairness_vars *vars,
+					     int *link_vars_start_index)
 {
-	int i;
+	int i, k;
 	struct dc_stream_state *stream;
 	struct dsc_mst_fairness_params params[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
@@ -768,11 +773,17 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		if (stream->link != dc_link)
 			continue;
 
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+		if (!aconnector)
+			continue;
+
+		if (!aconnector->port)
+			continue;
+
 		stream->timing.flags.DSC = 0;
 
 		params[count].timing = &stream->timing;
 		params[count].sink = stream->sink;
-		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 		params[count].aconnector = aconnector;
 		params[count].port = aconnector->port;
 		params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable;
@@ -794,44 +805,55 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 
 		count++;
 	}
+
+	if (count == 0) {
+		ASSERT(0);
+		return true;
+	}
+
+	/* k is start index of vars for current phy link used by mst hub */
+	k = *link_vars_start_index;
+	/* set vars start index for next mst hub phy link */
+	*link_vars_start_index += count;
+
 	/* Try no compression */
 	for (i = 0; i < count; i++) {
-		vars[i].aconnector = params[i].aconnector;
-		vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
-		vars[i].dsc_enabled = false;
-		vars[i].bpp_x16 = 0;
+		vars[i + k].aconnector = params[i].aconnector;
+		vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+		vars[i + k].dsc_enabled = false;
+		vars[i + k].bpp_x16 = 0;
 		if (drm_dp_atomic_find_vcpi_slots(state,
 						 params[i].port->mgr,
 						 params[i].port,
-						 vars[i].pbn,
+						 vars[i + k].pbn,
 						 dm_mst_get_pbn_divider(dc_link)) < 0)
 			return false;
 	}
 	if (!drm_dp_mst_atomic_check(state) && !debugfs_overwrite) {
-		set_dsc_configs_from_fairness_vars(params, vars, count);
+		set_dsc_configs_from_fairness_vars(params, vars, count, k);
 		return true;
 	}
 
 	/* Try max compression */
 	for (i = 0; i < count; i++) {
 		if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) {
-			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
-			vars[i].dsc_enabled = true;
-			vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
+			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
+			vars[i + k].dsc_enabled = true;
+			vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
 			if (drm_dp_atomic_find_vcpi_slots(state,
 							  params[i].port->mgr,
 							  params[i].port,
-							  vars[i].pbn,
+							  vars[i + k].pbn,
 							  dm_mst_get_pbn_divider(dc_link)) < 0)
 				return false;
 		} else {
-			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
-			vars[i].dsc_enabled = false;
-			vars[i].bpp_x16 = 0;
+			vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+			vars[i + k].dsc_enabled = false;
+			vars[i + k].bpp_x16 = 0;
 			if (drm_dp_atomic_find_vcpi_slots(state,
 							  params[i].port->mgr,
 							  params[i].port,
-							  vars[i].pbn,
+							  vars[i + k].pbn,
 							  dm_mst_get_pbn_divider(dc_link)) < 0)
 				return false;
 		}
@@ -840,15 +862,76 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		return false;
 
 	/* Optimize degree of compression */
-	increase_dsc_bpp(state, dc_link, params, vars, count);
+	increase_dsc_bpp(state, dc_link, params, vars, count, k);
 
-	try_disable_dsc(state, dc_link, params, vars, count);
+	try_disable_dsc(state, dc_link, params, vars, count, k);
 
-	set_dsc_configs_from_fairness_vars(params, vars, count);
+	set_dsc_configs_from_fairness_vars(params, vars, count, k);
 
 	return true;
 }
 
+static bool is_dsc_need_re_compute(
+	struct drm_atomic_state *state,
+	struct dc_state *dc_state,
+	struct dc_link *dc_link)
+{
+	int i;
+	bool is_dsc_need_re_compute = false;
+
+	/* only check phy used by mst branch */
+	if (dc_link->type != dc_connection_mst_branch)
+		return false;
+
+	/* check if there is mode change in new request */
+	for (i = 0; i < dc_state->stream_count; i++) {
+		struct amdgpu_dm_connector *aconnector;
+		struct dc_stream_state *stream;
+		struct drm_crtc_state *new_crtc_state;
+		struct drm_connector_state *new_conn_state;
+
+		stream = dc_state->streams[i];
+
+		if (!stream)
+			continue;
+
+		/* check if stream using the same link for mst */
+		if (stream->link != dc_link)
+			continue;
+
+		aconnector = (struct amdgpu_dm_connector *) stream->dm_stream_context;
+		if (!aconnector)
+			continue;
+
+		new_conn_state = drm_atomic_get_new_connector_state(state, &aconnector->base);
+
+		if (!new_conn_state)
+			continue;
+
+		if (IS_ERR(new_conn_state))
+			continue;
+
+		if (!new_conn_state->crtc)
+			continue;
+
+		new_crtc_state = drm_atomic_get_new_crtc_state(state, new_conn_state->crtc);
+
+		if (!new_crtc_state)
+			continue;
+
+		if (IS_ERR(new_crtc_state))
+			continue;
+
+		if (new_crtc_state->enable && new_crtc_state->active) {
+			if (new_crtc_state->mode_changed || new_crtc_state->active_changed ||
+				new_crtc_state->connectors_changed)
+				is_dsc_need_re_compute = true;
+		}
+	}
+
+	return is_dsc_need_re_compute;
+}
+
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 				       struct dc_state *dc_state,
 				       struct dsc_mst_fairness_vars *vars)
@@ -857,6 +940,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 	struct dc_stream_state *stream;
 	bool computed_streams[MAX_PIPES];
 	struct amdgpu_dm_connector *aconnector;
+	int link_vars_start_index = 0;
 
 	for (i = 0; i < dc_state->stream_count; i++)
 		computed_streams[i] = false;
@@ -881,8 +965,12 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 		if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK)
 			return false;
 
+		if (!is_dsc_need_re_compute(state, dc_state, stream->link))
+			continue;
+
 		mutex_lock(&aconnector->mst_mgr.lock);
-		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars)) {
+		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link,
+			vars, &link_vars_start_index)) {
 			mutex_unlock(&aconnector->mst_mgr.lock);
 			return false;
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 12e5470fa567..0ded4decee05 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1085,6 +1085,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 		struct dc_stream_state *old_stream =
 				dc->current_state->res_ctx.pipe_ctx[i].stream;
 		bool should_disable = true;
+		bool pipe_split_change =
+			context->res_ctx.pipe_ctx[i].top_pipe != dc->current_state->res_ctx.pipe_ctx[i].top_pipe;
 
 		for (j = 0; j < context->stream_count; j++) {
 			if (old_stream == context->streams[j]) {
@@ -1092,6 +1094,9 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 				break;
 			}
 		}
+		if (!should_disable && pipe_split_change)
+			should_disable = true;
+
 		if (should_disable && old_stream) {
 			dc_rem_all_planes_for_stream(dc, old_stream, dangling_context);
 			disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context);
@@ -1887,6 +1892,7 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context)
 	return false;
 }
 
+#ifdef CONFIG_DRM_AMD_DC_DCN
 /* Perform updates here which need to be deferred until next vupdate
  *
  * i.e. blnd lut, 3dlut, and shaper lut bypass regs are double buffered
@@ -1896,7 +1902,6 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context)
  */
 static void process_deferred_updates(struct dc *dc)
 {
-#ifdef CONFIG_DRM_AMD_DC_DCN
 	int i = 0;
 
 	if (dc->debug.enable_mem_low_power.bits.cm) {
@@ -1905,8 +1910,8 @@ static void process_deferred_updates(struct dc *dc)
 			if (dc->res_pool->dpps[i]->funcs->dpp_deferred_update)
 				dc->res_pool->dpps[i]->funcs->dpp_deferred_update(dc->res_pool->dpps[i]);
 	}
-#endif
 }
+#endif /* CONFIG_DRM_AMD_DC_DCN */
 
 void dc_post_update_surfaces_to_stream(struct dc *dc)
 {
@@ -1933,7 +1938,9 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 			dc->hwss.disable_plane(dc, &context->res_ctx.pipe_ctx[i]);
 		}
 
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	process_deferred_updates(dc);
+#endif
 
 	dc->hwss.optimize_bandwidth(dc, context);
 
@@ -3603,7 +3610,8 @@ bool dc_enable_dmub_notifications(struct dc *dc)
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* YELLOW_CARP B0 USB4 DPIA needs dmub notifications for interrupts */
 	if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP &&
-	    dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0)
+	    dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 &&
+	    !dc->debug.dpia_debug.bits.disable_dpia)
 		return true;
 #endif
 	/* dmub aux needs dmub notifications to be enabled */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 2796bdd17de1..60544788e911 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -4279,6 +4279,8 @@ void core_link_enable_stream(
 			 */
 			if (status != DC_FAIL_DP_LINK_TRAINING ||
 					pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+				if (false == stream->link->link_status.link_active)
+					disable_link(stream->link, pipe_ctx->stream->signal);
 				BREAK_TO_DEBUGGER();
 				return;
 			}
@@ -4768,7 +4770,7 @@ uint32_t dc_bandwidth_in_kbps_from_timing(
 				timing->dsc_cfg.bits_per_pixel,
 				timing->dsc_cfg.num_slices_h,
 				timing->dsc_cfg.is_dp);
-#endif
+#endif /* CONFIG_DRM_AMD_DC_DCN */
 
 	switch (timing->display_color_depth) {
 	case COLOR_DEPTH_666:
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index cc25ba0ec7db..cb7bf9148904 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -5329,6 +5329,14 @@ bool dc_link_dp_set_test_pattern(
 			return false;
 
 		if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+			if (test_pattern == DP_TEST_PATTERN_SQUARE_PULSE)
+				core_link_write_dpcd(link,
+						DP_LINK_SQUARE_PATTERN,
+						p_custom_pattern,
+						1);
+
+#endif
 			/* tell receiver that we are sending qualification
 			 * pattern DP 1.2 or later - DP receiver's link quality
 			 * pattern is set using DPCD LINK_QUAL_LANEx_SET
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
index 72b0f8594b4a..25e48a8cbb78 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
@@ -236,6 +236,23 @@ static struct link_encoder *get_link_enc_used_by_link(
 
 	return link_enc;
 }
+/* Clear all link encoder assignments. */
+static void clear_enc_assignments(struct dc_state *state)
+{
+	int i;
+	enum engine_id eng_id;
+	struct dc_stream_state *stream;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].valid = false;
+		eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].eng_id;
+		stream = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i].stream;
+		if (eng_id != ENGINE_ID_UNKNOWN)
+			state->res_ctx.link_enc_cfg_ctx.link_enc_avail[eng_id - ENGINE_ID_DIGA] = eng_id;
+		if (stream)
+			stream->link_enc = NULL;
+	}
+}
 
 void link_enc_cfg_init(
 		struct dc *dc,
@@ -250,6 +267,8 @@ void link_enc_cfg_init(
 			state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i] = ENGINE_ID_UNKNOWN;
 	}
 
+	clear_enc_assignments(state);
+
 	state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_STEADY;
 }
 
@@ -265,6 +284,9 @@ void link_enc_cfg_link_encs_assign(
 
 	ASSERT(state->stream_count == stream_count);
 
+	if (stream_count == 0)
+		clear_enc_assignments(state);
+
 	/* Release DIG link encoder resources before running assignment algorithm. */
 	for (i = 0; i < stream_count; i++)
 		dc->res_pool->funcs->link_enc_unassign(state, streams[i]);
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index a5339796902a..3aac3f4a2852 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -47,7 +47,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.159"
+#define DC_VER "3.2.160"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -675,6 +675,7 @@ struct dc_debug_options {
 #endif
 	union mem_low_power_enable_options enable_mem_low_power;
 	union root_clock_optimization_options root_clock_optimization;
+	bool hpo_optimization;
 	bool force_vblank_alignment;
 
 	/* Enable dmub aux for legacy ddc */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index bc87ea0adf94..e68e9a86a4d9 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -898,6 +898,9 @@ struct dpcd_usb4_dp_tunneling_info {
 #ifndef DP_DFP_CAPABILITY_EXTENSION_SUPPORT
 #define DP_DFP_CAPABILITY_EXTENSION_SUPPORT		0x0A3
 #endif
+#ifndef DP_LINK_SQUARE_PATTERN
+#define DP_LINK_SQUARE_PATTERN				0x10F
+#endif
 #ifndef DP_DSC_CONFIGURATION
 #define DP_DSC_CONFIGURATION				0x161
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 989f5b6907e2..a3fee929cd12 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -671,6 +671,7 @@ struct dce_hwseq_registers {
 	uint32_t MC_VM_FB_LOCATION_BASE;
 	uint32_t MC_VM_FB_LOCATION_TOP;
 	uint32_t MC_VM_FB_OFFSET;
+	uint32_t HPO_TOP_HW_CONTROL;
 };
  /* set field name */
 #define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@@ -1152,7 +1153,8 @@ struct dce_hwseq_registers {
 	type DOMAIN_PGFSM_PWR_STATUS;\
 	type HPO_HDMISTREAMCLK_G_GATE_DIS;\
 	type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;\
-	type I2C_LIGHT_SLEEP_FORCE;
+	type I2C_LIGHT_SLEEP_FORCE;\
+	type HPO_IO_EN;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index af3e68d3e747..24e47df526f6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1244,6 +1244,12 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 #endif
 	if (dc_is_dp_signal(pipe_ctx->stream->signal))
 		dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_DISCONNECT_DIG_FE_BE);
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (dc->hwseq->funcs.setup_hpo_hw_control && is_dp_128b_132b_signal(pipe_ctx))
+		dc->hwseq->funcs.setup_hpo_hw_control(dc->hwseq, false);
+#endif
+
 }
 
 void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index a25732d07222..0b788d794fb3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -231,7 +231,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 
 		if (!s->blank_en)
 			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
-				"%  8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
+				"  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh"
 				"  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
 				pool->hubps[i]->inst, dlg_regs->refcyc_h_blank_end, dlg_regs->dlg_vblank_end, dlg_regs->min_dst_y_next_start,
 				dlg_regs->refcyc_per_htotal, dlg_regs->refcyc_x_after_scaler, dlg_regs->dst_y_after_scaler,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index cfee456c6c9a..4f88376a118f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -2397,6 +2397,9 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	 * BY this, it is logic clean to separate stream and link
 	 */
 	if (is_dp_128b_132b_signal(pipe_ctx)) {
+		if (pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control)
+			pipe_ctx->stream->ctx->dc->hwseq->funcs.setup_hpo_hw_control(
+				pipe_ctx->stream->ctx->dc->hwseq, true);
 		setup_dp_hpo_stream(pipe_ctx, true);
 		pipe_ctx->stream_res.hpo_dp_stream_enc->funcs->enable_stream(
 				pipe_ctx->stream_res.hpo_dp_stream_enc);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
index a82319f4d081..95149734378b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@@ -1381,13 +1381,11 @@ int mpcc3_release_rmu(struct mpc *mpc, int mpcc_id)
 
 }
 
-static void mpc3_mpc_init(struct mpc *mpc)
+static void mpc3_set_mpc_mem_lp_mode(struct mpc *mpc)
 {
 	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
 	int mpcc_id;
 
-	mpc1_mpc_init(mpc);
-
 	if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) {
 		if (mpc30->mpc_mask->MPC_RMU0_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPC_RMU1_MEM_LOW_PWR_MODE) {
 			REG_UPDATE(MPC_RMU_MEM_PWR_CTRL, MPC_RMU0_MEM_LOW_PWR_MODE, 3);
@@ -1405,7 +1403,7 @@ const struct mpc_funcs dcn30_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
-	.mpc_init = mpc3_mpc_init,
+	.mpc_init = mpc1_mpc_init,
 	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
 	.cursor_lock = mpc1_cursor_lock,
@@ -1432,6 +1430,7 @@ const struct mpc_funcs dcn30_mpc_funcs = {
 	.power_on_mpc_mem_pwr = mpc3_power_on_ogam_lut,
 	.get_mpc_out_mux = mpc1_get_mpc_out_mux,
 	.set_bg_color = mpc1_set_bg_color,
+	.set_mpc_mem_lp_mode = mpc3_set_mpc_mem_lp_mode,
 };
 
 void dcn30_mpc_construct(struct dcn30_mpc *mpc30,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index e50c695e3c96..79a66e0c4303 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -2128,10 +2128,10 @@ static noinline void dcn30_calculate_wm_and_dlg_fp(
 		int pipe_cnt,
 		int vlevel)
 {
+	int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb;
 	int i, pipe_idx;
-	double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
-	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] !=
-			dm_dram_clock_change_unsupported;
+	double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][maxMpcComb];
+	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] != dm_dram_clock_change_unsupported;
 
 	if (context->bw_ctx.dml.soc.min_dcfclk > dcfclk)
 		dcfclk = context->bw_ctx.dml.soc.min_dcfclk;
@@ -2207,6 +2207,7 @@ static noinline void dcn30_calculate_wm_and_dlg_fp(
 		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us;
 		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us;
 	}
+
 	context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index d24ad7754d71..5dd1ce9ddb53 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -66,6 +66,45 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
+static void enable_memory_low_power(struct dc *dc)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	if (dc->debug.enable_mem_low_power.bits.dmcu) {
+		// Force ERAM to shutdown if DMCU is not enabled
+		if (dc->debug.disable_dmcu || dc->config.disable_dmcu) {
+			REG_UPDATE(DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, 3);
+		}
+	}
+
+	// Set default OPTC memory power states
+	if (dc->debug.enable_mem_low_power.bits.optc) {
+		// Shutdown when unassigned and light sleep in VBLANK
+		REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1);
+	}
+
+	if (dc->debug.enable_mem_low_power.bits.vga) {
+		// Power down VGA memory
+		REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1);
+	}
+
+	if (dc->debug.enable_mem_low_power.bits.mpc)
+		dc->res_pool->mpc->funcs->set_mpc_mem_lp_mode(dc->res_pool->mpc);
+
+
+	if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) {
+		// Power down VPGs
+		for (i = 0; i < dc->res_pool->stream_enc_count; i++)
+			dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg);
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++)
+			dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg);
+#endif
+	}
+
+}
+
 void dcn31_init_hw(struct dc *dc)
 {
 	struct abm **abms = dc->res_pool->multiple_abms;
@@ -108,35 +147,7 @@ void dcn31_init_hw(struct dc *dc)
 	if (res_pool->dccg->funcs->dccg_init)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);
 
-	if (dc->debug.enable_mem_low_power.bits.dmcu) {
-		// Force ERAM to shutdown if DMCU is not enabled
-		if (dc->debug.disable_dmcu || dc->config.disable_dmcu) {
-			REG_UPDATE(DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, 3);
-		}
-	}
-
-	// Set default OPTC memory power states
-	if (dc->debug.enable_mem_low_power.bits.optc) {
-		// Shutdown when unassigned and light sleep in VBLANK
-		REG_SET_2(ODM_MEM_PWR_CTRL3, 0, ODM_MEM_UNASSIGNED_PWR_MODE, 3, ODM_MEM_VBLANK_PWR_MODE, 1);
-	}
-
-	if (dc->debug.enable_mem_low_power.bits.vga) {
-		// Power down VGA memory
-		REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1);
-	}
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-	if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) {
-		// Power down VPGs
-		for (i = 0; i < dc->res_pool->stream_enc_count; i++)
-			dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg);
-#if defined(CONFIG_DRM_AMD_DC_DP2_0)
-		for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++)
-			dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg);
-#endif
-	}
-#endif
+	enable_memory_low_power(dc);
 
 	if (dc->ctx->dc_bios->fw_info_valid) {
 		res_pool->ref_clocks.xtalin_clock_inKhz =
@@ -264,6 +275,9 @@ void dcn31_init_hw(struct dc *dc)
 	if (dc->debug.enable_mem_low_power.bits.i2c)
 		REG_UPDATE(DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, 1);
 
+	if (hws->funcs.setup_hpo_hw_control)
+		hws->funcs.setup_hpo_hw_control(hws, false);
+
 	if (!dc->debug.disable_clock_gate) {
 		/* enable all DCN clock gating */
 		REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
@@ -597,3 +611,9 @@ void dcn31_reset_hw_ctx_wrap(
 	/* New dc_state in the process of being applied to hardware. */
 	dc->current_state->res_ctx.link_enc_cfg_ctx.mode = LINK_ENC_CFG_TRANSIENT;
 }
+
+void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable)
+{
+	if (hws->ctx->dc->debug.hpo_optimization)
+		REG_UPDATE(HPO_TOP_HW_CONTROL, HPO_IO_EN, !!enable);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
index 7ae45dd202d9..edfc01d6ad73 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
@@ -54,5 +54,6 @@ void dcn31_reset_hw_ctx_wrap(
 bool dcn31_is_abm_supported(struct dc *dc,
 		struct dc_state *context, struct dc_stream_state *stream);
 void dcn31_init_pipes(struct dc *dc, struct dc_state *context);
+void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable);
 
 #endif /* __DC_HWSS_DCN31_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index c6a737781ad1..05335a8c3c2d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -137,6 +137,7 @@ static const struct hwseq_private_funcs dcn31_private_funcs = {
 	.dccg_init = dcn20_dccg_init,
 	.set_blend_lut = dcn30_set_blend_lut,
 	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
+	.setup_hpo_hw_control = dcn31_setup_hpo_hw_control,
 };
 
 void dcn31_hw_sequencer_construct(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 87b2c2428842..18896294ae12 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -860,7 +860,8 @@ static const struct dccg_mask dccg_mask = {
 	SR(D6VGA_CONTROL), \
 	SR(DC_IP_REQUEST_CNTL), \
 	SR(AZALIA_AUDIO_DTO), \
-	SR(AZALIA_CONTROLLER_CLOCK_GATING)
+	SR(AZALIA_CONTROLLER_CLOCK_GATING), \
+	SR(HPO_TOP_HW_CONTROL)
 
 static const struct dce_hwseq_registers hwseq_reg = {
 		HWSEQ_DCN31_REG_LIST()
@@ -898,7 +899,8 @@ static const struct dce_hwseq_registers hwseq_reg = {
 	HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_UNASSIGNED_PWR_MODE, mask_sh), \
 	HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_VBLANK_PWR_MODE, mask_sh), \
 	HWS_SF(, MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, mask_sh), \
-	HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+	HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh), \
+	HWS_SF(, HPO_TOP_HW_CONTROL, HPO_IO_EN, mask_sh)
 
 static const struct dce_hwseq_shift hwseq_shift = {
 		HWSEQ_DCN31_MASK_SH_LIST(__SHIFT)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index e3d9f1decdfc..f47d82da115c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -3576,16 +3576,9 @@ static double TruncToValidBPP(
 		MinDSCBPP = 8;
 		MaxDSCBPP = 3 * DSCInputBitPerComponent - 1.0 / 16;
 	} else {
-		if (Output == dm_hdmi) {
-			NonDSCBPP0 = 24;
-			NonDSCBPP1 = 24;
-			NonDSCBPP2 = 24;
-		}
-		else {
-			NonDSCBPP0 = 16;
-			NonDSCBPP1 = 20;
-			NonDSCBPP2 = 24;
-		}
+		NonDSCBPP0 = 16;
+		NonDSCBPP1 = 20;
+		NonDSCBPP2 = 24;
 
 		if (Format == dm_n422) {
 			MinDSCBPP = 7;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index d58925cff420..7e937bdcea00 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -3892,15 +3892,11 @@ static double TruncToValidBPP(
 		MinDSCBPP = 8;
 		MaxDSCBPP = 3 * DSCInputBitPerComponent - 1.0 / 16;
 	} else {
-		if (Output == dm_hdmi) {
-			NonDSCBPP0 = 24;
-			NonDSCBPP1 = 24;
-			NonDSCBPP2 = 24;
-		} else {
-			NonDSCBPP0 = 16;
-			NonDSCBPP1 = 20;
-			NonDSCBPP2 = 24;
-		}
+
+		NonDSCBPP0 = 16;
+		NonDSCBPP1 = 20;
+		NonDSCBPP2 = 24;
+
 		if (Format == dm_n422) {
 			MinDSCBPP = 7;
 			MaxDSCBPP = 2 * DSCInputBitPerComponent - 1.0 / 16.0;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 04d6ec3f021f..f5fd2a067323 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -367,6 +367,7 @@ struct mpc_funcs {
 	void (*set_bg_color)(struct mpc *mpc,
 			struct tg_color *bg_color,
 			int mpcc_id);
+	void (*set_mpc_mem_lp_mode)(struct mpc *mpc);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
index f324285394be..c2008258c50a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -143,6 +143,7 @@ struct hwseq_private_funcs {
 			const struct dc_plane_state *plane_state);
 	void (*PLAT_58856_wa)(struct dc_state *context,
 			struct pipe_ctx *pipe_ctx);
+	void (*setup_hpo_hw_control)(const struct dce_hwseq *hws, bool enable);
 };
 
 struct dce_hwseq {
diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 717c0e572d2f..cd204eef073b 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -238,6 +238,7 @@ struct dmub_srv_hw_params {
 	bool load_inst_const;
 	bool skip_panel_power_sequence;
 	bool disable_z10;
+	bool power_optimization;
 	bool dpia_supported;
 	bool disable_dpia;
 };
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 0293c58f0701..c29a67ccef17 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -46,10 +46,10 @@
 
 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0x9525efb5
+#define DMUB_FW_VERSION_GIT_HASH 0x1d82d23e
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 90
+#define DMUB_FW_VERSION_REVISION 91
 #define DMUB_FW_VERSION_TEST 0
 #define DMUB_FW_VERSION_VBIOS 0
 #define DMUB_FW_VERSION_HOTFIX 0
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 10ebf20eaa41..fa0569174aec 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -340,6 +340,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu
 	boot_options.bits.z10_disable = params->disable_z10;
 	boot_options.bits.dpia_supported = params->dpia_supported;
 	boot_options.bits.enable_dpia = params->disable_dpia ? 0 : 1;
+	boot_options.bits.power_optimization = params->power_optimization;
 
 	boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0;
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index f1a46d16f7ea..4b9e68a79f06 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -98,7 +98,8 @@ enum amd_ip_block_type {
 	AMD_IP_BLOCK_TYPE_ACP,
 	AMD_IP_BLOCK_TYPE_VCN,
 	AMD_IP_BLOCK_TYPE_MES,
-	AMD_IP_BLOCK_TYPE_JPEG
+	AMD_IP_BLOCK_TYPE_JPEG,
+	AMD_IP_BLOCK_TYPE_NUM,
 };
 
 enum amd_clockgating_state {
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 03581d5b1836..08362d506534 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -927,6 +927,13 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 {
 	int ret = 0;
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON;
+
+	if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state) {
+		dev_dbg(adev->dev, "IP block%d already in the target %s state!",
+				block_type, gate ? "gate" : "ungate");
+		return 0;
+	}
 
 	switch (block_type) {
 	case AMD_IP_BLOCK_TYPE_UVD:
@@ -979,6 +986,9 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 		break;
 	}
 
+	if (!ret)
+		atomic_set(&adev->pm.pwr_state[block_type], pwr_state);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 49fe4155c374..41472ed99253 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2094,6 +2094,10 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	} else if (DEVICE_ATTR_IS(pp_dpm_dclk)) {
 		if (!(asic_type == CHIP_VANGOGH || asic_type == CHIP_SIENNA_CICHLID))
 			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(pp_power_profile_mode)) {
+		if (!adev->powerplay.pp_funcs->get_power_profile_mode ||
+		    amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP)
+			*states = ATTR_STATE_UNSUPPORTED;
 	}
 
 	switch (asic_type) {
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 98f1b3d8c1d5..16e3f72d31b9 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -417,6 +417,12 @@ struct amdgpu_dpm {
 	enum amd_dpm_forced_level forced_level;
 };
 
+enum ip_power_state {
+	POWER_STATE_UNKNOWN,
+	POWER_STATE_ON,
+	POWER_STATE_OFF,
+};
+
 struct amdgpu_pm {
 	struct mutex		mutex;
 	u32                     current_sclk;
@@ -452,6 +458,8 @@ struct amdgpu_pm {
 	struct i2c_adapter smu_i2c;
 	struct mutex		smu_i2c_mutex;
 	struct list_head	pm_attr_list;
+
+	atomic_t		pwr_state[AMD_IP_BLOCK_TYPE_NUM];
 };
 
 #define R600_SSTU_DFLT                               0
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h
index 1d3447991d0c..fc9198846e70 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_ppsmc.h
@@ -51,7 +51,7 @@
 #define PPSMC_MSG_PowerUpVcn                    0x07 ///< Power up VCN; VCN is power gated by default
 #define PPSMC_MSG_SetHardMinVcn                 0x08 ///< For wireless display
 #define PPSMC_MSG_SetSoftMinGfxclk              0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz
-#define PPSMC_MSG_ActiveProcessNotify           0x0A ///< Set active work load type
+#define PPSMC_MSG_ActiveProcessNotify           0x0A ///< Deprecated (Not to be used)
 #define PPSMC_MSG_ForcePowerDownGfx             0x0B ///< Force power down GFX, i.e. enter GFXOFF
 #define PPSMC_MSG_PrepareMp1ForUnload           0x0C ///< Prepare PMFW for GFX driver unload
 #define PPSMC_MSG_SetDriverDramAddrHigh         0x0D ///< Set high 32 bits of DRAM address for Driver table transfer
@@ -63,7 +63,7 @@
 #define PPSMC_MSG_SetHardMinSocclkByFreq        0x13 ///< Set hard min for SOC CLK
 #define PPSMC_MSG_SetSoftMinFclk                0x14 ///< Set hard min for FCLK
 #define PPSMC_MSG_SetSoftMinVcn                 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK)
-#define PPSMC_MSG_SPARE0                        0x16 ///< Spared
+#define PPSMC_MSG_SPARE                         0x16 ///< Spare
 #define PPSMC_MSG_GetGfxclkFrequency            0x17 ///< Get GFX clock frequency
 #define PPSMC_MSG_GetFclkFrequency              0x18 ///< Get FCLK frequency
 #define PPSMC_MSG_AllowGfxOff                   0x19 ///< Inform PMFW of allowing GFXOFF entry
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index 321215003643..8d796ed3b7d1 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -875,34 +875,30 @@ pp_dpm_get_vce_clock_state(void *handle, unsigned idx)
 static int pp_get_power_profile_mode(void *handle, char *buf)
 {
 	struct pp_hwmgr *hwmgr = handle;
+	int ret;
 
-	if (!hwmgr || !hwmgr->pm_en || !buf)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->hwmgr_func->get_power_profile_mode)
+		return -EOPNOTSUPP;
+	if (!buf)
 		return -EINVAL;
 
-	if (hwmgr->hwmgr_func->get_power_profile_mode == NULL) {
-		pr_info_ratelimited("%s was not implemented.\n", __func__);
-		return snprintf(buf, PAGE_SIZE, "\n");
-	}
-
-	return hwmgr->hwmgr_func->get_power_profile_mode(hwmgr, buf);
+	mutex_lock(&hwmgr->smu_lock);
+	ret = hwmgr->hwmgr_func->get_power_profile_mode(hwmgr, buf);
+	mutex_unlock(&hwmgr->smu_lock);
+	return ret;
 }
 
 static int pp_set_power_profile_mode(void *handle, long *input, uint32_t size)
 {
 	struct pp_hwmgr *hwmgr = handle;
-	int ret = -EINVAL;
+	int ret = -EOPNOTSUPP;
 
-	if (!hwmgr || !hwmgr->pm_en)
-		return ret;
-
-	if (hwmgr->hwmgr_func->set_power_profile_mode == NULL) {
-		pr_info_ratelimited("%s was not implemented.\n", __func__);
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->hwmgr_func->set_power_profile_mode)
 		return ret;
-	}
 
 	if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) {
 		pr_debug("power profile setting is for manual dpm mode only.\n");
-		return ret;
+		return -EINVAL;
 	}
 
 	mutex_lock(&hwmgr->smu_lock);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 1de3ae77e03e..258c573acc97 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -1024,6 +1024,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	uint32_t min_freq, max_freq = 0;
 	uint32_t ret = 0;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now);
@@ -1065,7 +1067,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;
 
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -1081,7 +1083,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;
 
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				min_freq, max_freq);
 		}
@@ -1456,6 +1458,8 @@ static int smu10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0],
 			title[1], title[2], title[3], title[4], title[5]);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index e7803ce8f67a..aceebf584225 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -4914,6 +4914,8 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int size = 0;
 	uint32_t i, now, clock, pcie_speed;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_API_GetSclkFrequency, &clock);
@@ -4963,7 +4965,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			for (i = 0; i < odn_sclk_table->num_of_pl; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
 					i, odn_sclk_table->entries[i].clock/100,
@@ -4972,7 +4974,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 			for (i = 0; i < odn_mclk_table->num_of_pl; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
 					i, odn_mclk_table->entries[i].clock/100,
@@ -4981,7 +4983,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.sclk_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
@@ -5518,6 +5520,8 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%s %16s %16s %16s %16s %16s %16s %16s\n",
 			title[0], title[1], title[2], title[3],
 			title[4], title[5], title[6], title[7]);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
index b94a77e4e714..8e28a8eecefc 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
@@ -1550,6 +1550,8 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 	uint32_t i, now;
 	int size = 0;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		now = PHM_GET_FIELD(cgs_read_ind_register(hwmgr->device,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
index ad33983a8064..2a75da1e9f03 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.h
@@ -109,6 +109,19 @@ int phm_irq_process(struct amdgpu_device *adev,
 			   struct amdgpu_irq_src *source,
 			   struct amdgpu_iv_entry *entry);
 
+/*
+ * Helper function to make sysfs_emit_at() happy. Align buf to
+ * the current page boundary and record the offset.
+ */
+static inline void phm_get_sysfs_buf(char **buf, int *offset)
+{
+	if (!*buf || !offset)
+		return;
+
+	*offset = offset_in_page(*buf);
+	*buf -= *offset;
+}
+
 int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr);
 
 void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index c152a61ddd2c..c981fc2882f0 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -4548,6 +4548,8 @@ static int vega10_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 	int ret = 0;
 	int size = 0;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	ret = vega10_get_enabled_smc_features(hwmgr, &features_enabled);
 	PP_ASSERT_WITH_CODE(!ret,
 			"[EnableAllSmuFeatures] Failed to get enabled smc features!",
@@ -4637,6 +4639,8 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 
 	int i, now, size = 0, count = 0;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		if (data->registry_data.sclk_dpm_key_disabled)
@@ -4717,7 +4721,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
@@ -4727,7 +4731,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
 				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
@@ -4737,7 +4741,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.gfx_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
@@ -5112,6 +5116,8 @@ static int vega10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%s %16s %s %s %s %s\n",title[0],
 			title[1], title[2], title[3], title[4], title[5]);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index 8558718e15a8..f7e783e1c888 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2141,6 +2141,8 @@ static int vega12_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 	int ret = 0;
 	int size = 0;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	ret = vega12_get_enabled_smc_features(hwmgr, &features_enabled);
 	PP_ASSERT_WITH_CODE(!ret,
 		"[EnableAllSmuFeatures] Failed to get enabled smc features!",
@@ -2244,6 +2246,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int i, now, size = 0;
 	struct pp_clock_levels_with_latency clocks;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		PP_ASSERT_WITH_CODE(
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 0cf39c1244b1..03e63be4ee27 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -3238,6 +3238,8 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 	int ret = 0;
 	int size = 0;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled);
 	PP_ASSERT_WITH_CODE(!ret,
 			"[EnableAllSmuFeatures] Failed to get enabled smc features!",
@@ -3364,6 +3366,8 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int ret = 0;
 	uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	switch (type) {
 	case PP_SCLK:
 		ret = vega20_get_current_clk_freq(hwmgr, PPCLK_GFXCLK, &now);
@@ -3479,7 +3483,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	case OD_SCLK:
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
-			size = sysfs_emit(buf, "%s:\n", "OD_SCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
 				od_table->GfxclkFmin);
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
@@ -3489,7 +3493,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 
 	case OD_MCLK:
 		if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) {
-			size = sysfs_emit(buf, "%s:\n", "OD_MCLK");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
 				od_table->UclkFmax);
 		}
@@ -3503,7 +3507,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) {
-			size = sysfs_emit(buf, "%s:\n", "OD_VDDC_CURVE");
+			size += sysfs_emit_at(buf, size, "%s:\n", "OD_VDDC_CURVE");
 			size += sysfs_emit_at(buf, size, "0: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq1,
 				od_table->GfxclkVolt1 / VOLTAGE_SCALE);
@@ -3518,7 +3522,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 
 	case OD_RANGE:
-		size = sysfs_emit(buf, "%s:\n", "OD_RANGE");
+		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
@@ -4003,6 +4007,8 @@ static int vega20_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	if (!buf)
 		return -EINVAL;
 
+	phm_get_sysfs_buf(&buf, &size);
+
 	size += sysfs_emit_at(buf, size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
 			title[0], title[1], title[2], title[3], title[4], title[5],
 			title[6], title[7], title[8], title[9], title[10]);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index b06c59dcc1b4..01168b8955bf 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1468,7 +1468,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 			dev_err(adev->dev, "Failed to disable smu features.\n");
 	}
 
-	if (adev->ip_versions[MP1_HWIP][0] >= IP_VERSION(11, 0, 0) &&
+	if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0) &&
 	    adev->gfx.rlc.funcs->stop)
 		adev->gfx.rlc.funcs->stop(adev);
 
@@ -2534,13 +2534,15 @@ static int smu_get_power_profile_mode(void *handle, char *buf)
 	struct smu_context *smu = handle;
 	int ret = 0;
 
-	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled ||
+	    !smu->ppt_funcs->get_power_profile_mode)
 		return -EOPNOTSUPP;
+	if (!buf)
+		return -EINVAL;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->get_power_profile_mode)
-		ret = smu->ppt_funcs->get_power_profile_mode(smu, buf);
+	ret = smu->ppt_funcs->get_power_profile_mode(smu, buf);
 
 	mutex_unlock(&smu->mutex);
 
@@ -2554,7 +2556,8 @@ static int smu_set_power_profile_mode(void *handle,
 	struct smu_context *smu = handle;
 	int ret = 0;
 
-	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled ||
+	    !smu->ppt_funcs->set_power_profile_mode)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
index cbc3f99e8573..2238ee19c222 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
@@ -309,6 +309,7 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
 {
 	int ret = 0, size = 0;
 	uint32_t cur_value = 0;
+	int i;
 
 	smu_cmn_get_sysfs_buf(&buf, &size);
 
@@ -334,8 +335,6 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
 		size += sysfs_emit_at(buf, size, "VDDC: %7umV  %10umV\n",
 						CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
 		break;
-	case SMU_GFXCLK:
-	case SMU_SCLK:
 	case SMU_FCLK:
 	case SMU_MCLK:
 	case SMU_SOCCLK:
@@ -346,6 +345,25 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
 			return ret;
 		size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
 		break;
+	case SMU_SCLK:
+	case SMU_GFXCLK:
+		ret = cyan_skillfish_get_current_clk_freq(smu, clk_type, &cur_value);
+		if (ret)
+			return ret;
+		if (cur_value  == CYAN_SKILLFISH_SCLK_MAX)
+			i = 2;
+		else if (cur_value == CYAN_SKILLFISH_SCLK_MIN)
+			i = 0;
+		else
+			i = 1;
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", CYAN_SKILLFISH_SCLK_MIN,
+				i == 0 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+				i == 1 ? cur_value : cyan_skillfish_sclk_default,
+				i == 1 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", CYAN_SKILLFISH_SCLK_MAX,
+				i == 2 ? "*" : "");
+		break;
 	default:
 		dev_warn(smu->adev->dev, "Unsupported clock type\n");
 		return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 71161f6b78fe..60a557068ea4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1265,7 +1265,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			enum smu_clk_type clk_type, char *buf)
 {
 	uint16_t *curve_settings;
-	int i, size = 0, ret = 0;
+	int i, levels, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t freq_values[3] = {0};
 	uint32_t mark_index = 0;
@@ -1319,14 +1319,17 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			freq_values[1] = cur_value;
 			mark_index = cur_value == freq_values[0] ? 0 :
 				     cur_value == freq_values[2] ? 2 : 1;
-			if (mark_index != 1)
-				freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
 
-			for (i = 0; i < 3; i++) {
+			levels = 3;
+			if (mark_index != 1) {
+				levels = 2;
+				freq_values[1] = freq_values[2];
+			}
+
+			for (i = 0; i < levels; i++) {
 				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, freq_values[i],
 						i == mark_index ? "*" : "");
 			}
-
 		}
 		break;
 	case SMU_PCIE:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 421f38e8dada..c02ed65ffa38 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -683,6 +683,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	bool cur_value_match_level = false;
+	uint32_t min, max;
 
 	memset(&metrics, 0, sizeof(metrics));
 
@@ -743,6 +744,13 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		if (ret)
 			return ret;
 		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetGfxclkFrequency, 0, &cur_value);
+		if (ret) {
+			return ret;
+		}
+		break;
 	default:
 		break;
 	}
@@ -768,6 +776,24 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		if (!cur_value_match_level)
 			size += sysfs_emit_at(buf, size, "   %uMhz *\n", cur_value);
 		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
+		max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
+		if (cur_value  == max)
+			i = 2;
+		else if (cur_value == min)
+			i = 0;
+		else
+			i = 1;
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
+				i == 0 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+				i == 1 ? cur_value : VANGOGH_UMD_PSTATE_STANDARD_GFXCLK,
+				i == 1 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
+				i == 2 ? "*" : "");
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index a403657151ba..caf1775d48ef 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -64,7 +64,6 @@ static struct cmn2asic_msg_mapping yellow_carp_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(PowerDownVcn,                   PPSMC_MSG_PowerDownVcn,			1),
 	MSG_MAP(PowerUpVcn,                     PPSMC_MSG_PowerUpVcn,			1),
 	MSG_MAP(SetHardMinVcn,                  PPSMC_MSG_SetHardMinVcn,		1),
-	MSG_MAP(ActiveProcessNotify,            PPSMC_MSG_ActiveProcessNotify,		1),
 	MSG_MAP(PrepareMp1ForUnload,            PPSMC_MSG_PrepareMp1ForUnload,      1),
 	MSG_MAP(SetDriverDramAddrHigh,          PPSMC_MSG_SetDriverDramAddrHigh,	1),
 	MSG_MAP(SetDriverDramAddrLow,           PPSMC_MSG_SetDriverDramAddrLow,		1),
@@ -135,14 +134,6 @@ static struct cmn2asic_mapping yellow_carp_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP_VALID(CUSTOM_DPM),
 	TAB_MAP_VALID(DPMCLOCKS),
 };
-
-static struct cmn2asic_mapping yellow_carp_workload_map[PP_SMC_POWER_PROFILE_COUNT] = {
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_FULLSCREEN3D,		WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO,		WORKLOAD_PPLIB_VIDEO_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR,			WORKLOAD_PPLIB_VR_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_COMPUTE_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
-};
 	
 static int yellow_carp_init_smc_tables(struct smu_context *smu)
 {
@@ -543,81 +534,6 @@ static int yellow_carp_set_watermarks_table(struct smu_context *smu,
 	return 0;
 }
 
-static int yellow_carp_get_power_profile_mode(struct smu_context *smu,
-						char *buf)
-{
-	static const char *profile_name[] = {
-					"BOOTUP_DEFAULT",
-					"3D_FULL_SCREEN",
-					"POWER_SAVING",
-					"VIDEO",
-					"VR",
-					"COMPUTE",
-					"CUSTOM"};
-	uint32_t i, size = 0;
-	int16_t workload_type = 0;
-
-	if (!buf)
-		return -EINVAL;
-
-	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
-		/*
-		 * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT.
-		 * Not all profile modes are supported on yellow carp.
-		 */
-		workload_type = smu_cmn_to_asic_specific_index(smu,
-							       CMN2ASIC_MAPPING_WORKLOAD,
-							       i);
-
-		if (workload_type < 0)
-			continue;
-
-		size += sysfs_emit_at(buf, size, "%2d %14s%s\n",
-			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
-	}
-
-	return size;
-}
-
-static int yellow_carp_set_power_profile_mode(struct smu_context *smu,
-						long *input, uint32_t size)
-{
-	int workload_type, ret;
-	uint32_t profile_mode = input[size];
-
-	if (profile_mode > PP_SMC_POWER_PROFILE_CUSTOM) {
-		dev_err(smu->adev->dev, "Invalid power profile mode %d\n", profile_mode);
-		return -EINVAL;
-	}
-
-	if (profile_mode == PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT ||
-			profile_mode == PP_SMC_POWER_PROFILE_POWERSAVING)
-		return 0;
-
-	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
-	workload_type = smu_cmn_to_asic_specific_index(smu,
-						       CMN2ASIC_MAPPING_WORKLOAD,
-						       profile_mode);
-	if (workload_type < 0) {
-		dev_dbg(smu->adev->dev, "Unsupported power profile mode %d on YELLOWCARP\n",
-					profile_mode);
-		return -EINVAL;
-	}
-
-	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
-				    1 << workload_type,
-				    NULL);
-	if (ret) {
-		dev_err_once(smu->adev->dev, "Fail to set workload type %d\n",
-					workload_type);
-		return ret;
-	}
-
-	smu->power_profile_mode = profile_mode;
-
-	return 0;
-}
-
 static ssize_t yellow_carp_get_gpu_metrics(struct smu_context *smu,
 						void **table)
 {
@@ -781,6 +697,11 @@ static int yellow_carp_get_current_clk_freq(struct smu_context *smu,
 	case SMU_FCLK:
 		return smu_cmn_send_smc_msg_with_param(smu,
 				SMU_MSG_GetFclkFrequency, 0, value);
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		return smu_cmn_send_smc_msg_with_param(smu,
+				SMU_MSG_GetGfxclkFrequency, 0, value);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1051,6 +972,7 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 {
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
+	uint32_t min, max;
 
 	smu_cmn_get_sysfs_buf(&buf, &size);
 
@@ -1089,6 +1011,27 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 					cur_value == value ? "*" : "");
 		}
 		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		ret = yellow_carp_get_current_clk_freq(smu, clk_type, &cur_value);
+		if (ret)
+			goto print_clk_out;
+		min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
+		max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
+		if (cur_value  == max)
+			i = 2;
+		else if (cur_value == min)
+			i = 0;
+		else
+			i = 1;
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
+				i == 0 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+				i == 1 ? cur_value : YELLOW_CARP_UMD_PSTATE_GFXCLK,
+				i == 1 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
+				i == 2 ? "*" : "");
+		break;
 	default:
 		break;
 	}
@@ -1238,8 +1181,6 @@ static const struct pptable_funcs yellow_carp_ppt_funcs = {
 	.read_sensor = yellow_carp_read_sensor,
 	.is_dpm_running = yellow_carp_is_dpm_running,
 	.set_watermarks_table = yellow_carp_set_watermarks_table,
-	.get_power_profile_mode = yellow_carp_get_power_profile_mode,
-	.set_power_profile_mode = yellow_carp_set_power_profile_mode,
 	.get_gpu_metrics = yellow_carp_get_gpu_metrics,
 	.get_enabled_mask = smu_cmn_get_enabled_32_bits_mask,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
@@ -1261,6 +1202,5 @@ void yellow_carp_set_ppt_funcs(struct smu_context *smu)
 	smu->message_map = yellow_carp_message_map;
 	smu->feature_map = yellow_carp_feature_mask_map;
 	smu->table_map = yellow_carp_table_map;
-	smu->workload_map = yellow_carp_workload_map;
 	smu->is_apu = true;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
index b3ad8352c68a..a9205a8ea3ad 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
@@ -24,5 +24,6 @@
 #define __YELLOW_CARP_PPT_H__
 
 extern void yellow_carp_set_ppt_funcs(struct smu_context *smu);
+#define YELLOW_CARP_UMD_PSTATE_GFXCLK       1100
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 843d2cbfc71d..ea6f50c08c5f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -139,9 +139,13 @@ static void __smu_cmn_reg_print_error(struct smu_context *smu,
 	const char *message = smu_get_message_name(smu, msg);
 
 	switch (reg_c2pmsg_90) {
-	case SMU_RESP_NONE:
+	case SMU_RESP_NONE: {
+		u32 msg_idx = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66);
+		u32 prm     = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 		dev_err_ratelimited(adev->dev,
-				    "SMU: I'm not done with your previous command!");
+				    "SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x%08X SMN_C2PMSG_82:0x%08X",
+				    msg_idx, prm);
+	}
 		break;
 	case SMU_RESP_OK:
 		/* The SMU executed the command. It completed with a