Merge tag 'v6.17.8' into linux-6.17.ylinux-6.17.y

This is the 6.17.8 stable release

37 files changed, 561 insertions, 242 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index cbc40cad581b..9b3180449150 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -76,6 +76,7 @@ static void aca_banks_release(struct aca_banks *banks)
 	list_for_each_entry_safe(node, tmp, &banks->list, node) {
 		list_del(&node->node);
 		kvfree(node);
+		banks->nr_banks--;
 	}
 }
 
@@ -130,6 +131,27 @@ static void aca_smu_bank_dump(struct amdgpu_device *adev, int idx, int total, st
 		RAS_EVENT_LOG(adev, event_id, HW_ERR "hardware error logged by the scrubber\n");
 }
 
+static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
+{
+
+	struct aca_hwip *hwip;
+	int hwid, mcatype;
+	u64 ipid;
+
+	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
+		return false;
+
+	hwip = &aca_hwid_mcatypes[type];
+	if (!hwip->hwid)
+		return false;
+
+	ipid = bank->regs[ACA_REG_IDX_IPID];
+	hwid = ACA_REG__IPID__HARDWAREID(ipid);
+	mcatype = ACA_REG__IPID__MCATYPE(ipid);
+
+	return hwip->hwid == hwid && hwip->mcatype == mcatype;
+}
+
 static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_type type,
 				       int start, int count,
 				       struct aca_banks *banks, struct ras_query_context *qctx)
@@ -168,6 +190,15 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 
 		bank.smu_err_type = type;
 
+		/*
+		 * Poison being consumed when injecting a UE while running background workloads,
+		 * which are unexpected.
+		 */
+		if (type == ACA_SMU_TYPE_UE &&
+		    ACA_REG__STATUS__POISON(bank.regs[ACA_REG_IDX_STATUS]) &&
+		    !aca_bank_hwip_is_matched(&bank, ACA_HWIP_TYPE_UMC))
+			continue;
+
 		aca_smu_bank_dump(adev, i, count, &bank, qctx);
 
 		ret = aca_banks_add_bank(banks, &bank);
@@ -178,27 +209,6 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 	return 0;
 }
 
-static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
-{
-
-	struct aca_hwip *hwip;
-	int hwid, mcatype;
-	u64 ipid;
-
-	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
-		return false;
-
-	hwip = &aca_hwid_mcatypes[type];
-	if (!hwip->hwid)
-		return false;
-
-	ipid = bank->regs[ACA_REG_IDX_IPID];
-	hwid = ACA_REG__IPID__HARDWAREID(ipid);
-	mcatype = ACA_REG__IPID__MCATYPE(ipid);
-
-	return hwip->hwid == hwid && hwip->mcatype == mcatype;
-}
-
 static bool aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type)
 {
 	const struct aca_bank_ops *bank_ops = handle->bank_ops;
@@ -229,6 +239,7 @@ static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_
 
 	mutex_lock(&aerr->lock);
 	list_add_tail(&bank_error->node, &aerr->list);
+	aerr->nr_errors++;
 	mutex_unlock(&aerr->lock);
 
 	return bank_error;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 902eac2c685f..8994ed564f35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1263,6 +1263,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
 
+	/* VM entity stopped if process killed, don't clear freed pt bo */
+	if (!amdgpu_vm_ready(vm))
+		return 0;
+
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
@@ -2993,9 +2997,22 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 		struct amdgpu_device *adev = amdgpu_ttm_adev(
 			peer_vm->root.bo->tbo.bdev);
 
+		struct amdgpu_fpriv *fpriv =
+			container_of(peer_vm, struct amdgpu_fpriv, vm);
+
+		ret = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
+		if (ret) {
+			dev_dbg(adev->dev,
+				"Memory eviction: handle PRT moved failed, pid %8d. Try again.\n",
+				pid_nr(process_info->pid));
+			goto validate_map_fail;
+		}
+
 		ret = amdgpu_vm_handle_moved(adev, peer_vm, &exec.ticket);
 		if (ret) {
-			pr_debug("Memory eviction: handle moved failed. Try again\n");
+			dev_dbg(adev->dev,
+				"Memory eviction: handle moved failed, pid %8d. Try again.\n",
+				pid_nr(process_info->pid));
 			goto validate_map_fail;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 5e375e9c4f5d..bf38fc69c1cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1195,29 +1195,69 @@ static void amdgpu_connector_dvi_force(struct drm_connector *connector)
 		amdgpu_connector->use_digital = true;
 }
 
+/**
+ * amdgpu_max_hdmi_pixel_clock - Return max supported HDMI (TMDS) pixel clock
+ * @adev: pointer to amdgpu_device
+ *
+ * Return: maximum supported HDMI (TMDS) pixel clock in KHz.
+ */
+static int amdgpu_max_hdmi_pixel_clock(const struct amdgpu_device *adev)
+{
+	if (adev->asic_type >= CHIP_POLARIS10)
+		return 600000;
+	else if (adev->asic_type >= CHIP_TONGA)
+		return 300000;
+	else
+		return 297000;
+}
+
+/**
+ * amdgpu_connector_dvi_mode_valid - Validate a mode on DVI/HDMI connectors
+ * @connector: DRM connector to validate the mode on
+ * @mode: display mode to validate
+ *
+ * Validate the given display mode on DVI and HDMI connectors, including
+ * analog signals on DVI-I.
+ *
+ * Return: drm_mode_status indicating whether the mode is valid.
+ */
 static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector *connector,
 					    const struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
+	const int max_hdmi_pixel_clock = amdgpu_max_hdmi_pixel_clock(adev);
+	const int max_dvi_single_link_pixel_clock = 165000;
+	int max_digital_pixel_clock_khz;
 
 	/* XXX check mode bandwidth */
 
-	if (amdgpu_connector->use_digital && (mode->clock > 165000)) {
-		if ((amdgpu_connector->connector_object_id == CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I) ||
-		    (amdgpu_connector->connector_object_id == CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D) ||
-		    (amdgpu_connector->connector_object_id == CONNECTOR_OBJECT_ID_HDMI_TYPE_B)) {
-			return MODE_OK;
-		} else if (connector->display_info.is_hdmi) {
-			/* HDMI 1.3+ supports max clock of 340 Mhz */
-			if (mode->clock > 340000)
-				return MODE_CLOCK_HIGH;
-			else
-				return MODE_OK;
-		} else {
-			return MODE_CLOCK_HIGH;
+	if (amdgpu_connector->use_digital) {
+		switch (amdgpu_connector->connector_object_id) {
+		case CONNECTOR_OBJECT_ID_HDMI_TYPE_A:
+			max_digital_pixel_clock_khz = max_hdmi_pixel_clock;
+			break;
+		case CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_I:
+		case CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_D:
+			max_digital_pixel_clock_khz = max_dvi_single_link_pixel_clock;
+			break;
+		case CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I:
+		case CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D:
+		case CONNECTOR_OBJECT_ID_HDMI_TYPE_B:
+			max_digital_pixel_clock_khz = max_dvi_single_link_pixel_clock * 2;
+			break;
 		}
+
+		/* When the display EDID claims that it's an HDMI display,
+		 * we use the HDMI encoder mode of the display HW,
+		 * so we should verify against the max HDMI clock here.
+		 */
+		if (connector->display_info.is_hdmi)
+			max_digital_pixel_clock_khz = max_hdmi_pixel_clock;
+
+		if (mode->clock > max_digital_pixel_clock_khz)
+			return MODE_CLOCK_HIGH;
 	}
 
 	/* check against the max pixel clock */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
index 25252231a68a..54de38dbaf2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2025 Advanced Micro Devices, Inc.
  *
@@ -68,7 +68,6 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev,
 	hdr->error_severity		= sev;
 
 	hdr->valid_bits.platform_id	= 1;
-	hdr->valid_bits.partition_id	= 1;
 	hdr->valid_bits.timestamp	= 1;
 
 	amdgpu_cper_get_timestamp(&hdr->timestamp);
@@ -206,6 +205,7 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 {
 	struct cper_sec_desc *section_desc;
 	struct cper_sec_nonstd_err *section;
+	uint32_t socket_id;
 
 	section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx));
 	section = (struct cper_sec_nonstd_err *)((uint8_t *)hdr +
@@ -219,11 +219,17 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 	section->hdr.valid_bits.err_context_cnt = 1;
 
 	section->info.error_type = RUNTIME;
+	section->info.valid_bits.ms_chk = 1;
 	section->info.ms_chk_bits.err_type_valid = 1;
+	section->info.ms_chk_bits.err_type = 1;
+	section->info.ms_chk_bits.pcc = 1;
 	section->ctx.reg_ctx_type = CPER_CTX_TYPE_CRASH;
 	section->ctx.reg_arr_size = sizeof(section->ctx.reg_dump);
 
 	/* Hardcoded Reg dump for bad page threshold CPER */
+	socket_id = (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ?
+				adev->smuio.funcs->get_socket_id(adev) :
+				0;
 	section->ctx.reg_dump[CPER_ACA_REG_CTL_LO]    = 0x1;
 	section->ctx.reg_dump[CPER_ACA_REG_CTL_HI]    = 0x0;
 	section->ctx.reg_dump[CPER_ACA_REG_STATUS_LO] = 0x137;
@@ -234,8 +240,8 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 	section->ctx.reg_dump[CPER_ACA_REG_MISC0_HI]  = 0x0;
 	section->ctx.reg_dump[CPER_ACA_REG_CONFIG_LO] = 0x2;
 	section->ctx.reg_dump[CPER_ACA_REG_CONFIG_HI] = 0x1ff;
-	section->ctx.reg_dump[CPER_ACA_REG_IPID_LO]   = 0x0;
-	section->ctx.reg_dump[CPER_ACA_REG_IPID_HI]   = 0x96;
+	section->ctx.reg_dump[CPER_ACA_REG_IPID_LO]   = (socket_id / 4) & 0x01;
+	section->ctx.reg_dump[CPER_ACA_REG_IPID_HI]   = 0x096 | (((socket_id % 4) & 0x3) << 12);
 	section->ctx.reg_dump[CPER_ACA_REG_SYND_LO]   = 0x0;
 	section->ctx.reg_dump[CPER_ACA_REG_SYND_HI]   = 0x0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h
index bcb97d245673..353421807387 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2025 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d3f220be2ef9..1ce1fd0c87a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -286,7 +286,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
 		}
 	}
 
-	if (!p->gang_size) {
+	if (!p->gang_size || (amdgpu_sriov_vf(p->adev) && p->gang_size > 1)) {
 		ret = -EINVAL;
 		goto free_all_kdata;
 	}
@@ -1767,30 +1767,21 @@ int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	union drm_amdgpu_wait_fences *wait = data;
-	uint32_t fence_count = wait->in.fence_count;
-	struct drm_amdgpu_fence *fences_user;
 	struct drm_amdgpu_fence *fences;
 	int r;
 
 	/* Get the fences from userspace */
-	fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence),
-			GFP_KERNEL);
-	if (fences == NULL)
-		return -ENOMEM;
-
-	fences_user = u64_to_user_ptr(wait->in.fences);
-	if (copy_from_user(fences, fences_user,
-		sizeof(struct drm_amdgpu_fence) * fence_count)) {
-		r = -EFAULT;
-		goto err_free_fences;
-	}
+	fences = memdup_array_user(u64_to_user_ptr(wait->in.fences),
+				   wait->in.fence_count,
+				   sizeof(struct drm_amdgpu_fence));
+	if (IS_ERR(fences))
+		return PTR_ERR(fences);
 
 	if (wait->in.wait_all)
 		r = amdgpu_cs_wait_all_fences(adev, filp, wait, fences);
 	else
 		r = amdgpu_cs_wait_any_fence(adev, filp, wait, fences);
 
-err_free_fences:
 	kfree(fences);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c8459337fcb8..ddd0e7ab82be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -95,6 +95,7 @@ MODULE_FIRMWARE("amdgpu/picasso_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven2_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 #define AMDGPU_MAX_RETRY_LIMIT		2
@@ -2595,6 +2596,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 			return 0;
 		chip_name = "navi12";
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		chip_name = "cyan_skillfish";
+		break;
 	}
 
 	err = amdgpu_ucode_request(adev, &adev->firmware.gpu_info_fw,
@@ -3389,7 +3393,7 @@ static int amdgpu_device_enable_mgpu_fan_boost(void)
 	for (i = 0; i < mgpu_info.num_dgpu; i++) {
 		gpu_ins = &(mgpu_info.gpu_ins[i]);
 		adev = gpu_ins->adev;
-		if (!(adev->flags & AMD_IS_APU) &&
+		if (!(adev->flags & AMD_IS_APU || amdgpu_sriov_multi_vf_mode(adev)) &&
 		    !gpu_ins->mgpu_fan_enabled) {
 			ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
 			if (ret)
@@ -5012,6 +5016,10 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev)
 	if (!adev->in_s4 && (adev->flags & AMD_IS_APU))
 		return 0;
 
+	/* No need to evict when going to S5 through S4 callbacks */
+	if (system_state == SYSTEM_POWER_OFF)
+		return 0;
+
 	ret = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM);
 	if (ret) {
 		dev_warn(adev->dev, "evicting device resources failed\n");
@@ -6132,12 +6140,11 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle)
 	return ret;
 }
 
-static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
+static void amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 					  struct list_head *device_list,
 					  struct amdgpu_hive_info *hive)
 {
 	struct amdgpu_device *tmp_adev = NULL;
-	int r;
 
 	/*
 	 * Build list of devices to reset.
@@ -6157,14 +6164,6 @@ static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 	} else {
 		list_add_tail(&adev->reset_list, device_list);
 	}
-
-	if (!amdgpu_sriov_vf(adev) && (!adev->pcie_reset_ctx.occurs_dpc)) {
-		r = amdgpu_device_health_check(device_list);
-		if (r)
-			return r;
-	}
-
-	return 0;
 }
 
 static void amdgpu_device_recovery_get_reset_lock(struct amdgpu_device *adev,
@@ -6338,23 +6337,28 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 
-		if (tmp_adev->asic_reset_res)
-			r = tmp_adev->asic_reset_res;
-
-		tmp_adev->asic_reset_res = 0;
-
-		if (r) {
+		if (tmp_adev->asic_reset_res) {
 			/* bad news, how to tell it to userspace ?
 			 * for ras error, we should report GPU bad status instead of
 			 * reset failure
 			 */
 			if (reset_context->src != AMDGPU_RESET_SRC_RAS ||
 			    !amdgpu_ras_eeprom_check_err_threshold(tmp_adev))
-				dev_info(tmp_adev->dev, "GPU reset(%d) failed\n",
-					atomic_read(&tmp_adev->gpu_reset_counter));
-			amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+				dev_info(
+					tmp_adev->dev,
+					"GPU reset(%d) failed with error %d \n",
+					atomic_read(
+						&tmp_adev->gpu_reset_counter),
+					tmp_adev->asic_reset_res);
+			amdgpu_vf_error_put(tmp_adev,
+					    AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0,
+					    tmp_adev->asic_reset_res);
+			if (!r)
+				r = tmp_adev->asic_reset_res;
+			tmp_adev->asic_reset_res = 0;
 		} else {
-			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));
+			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n",
+				 atomic_read(&tmp_adev->gpu_reset_counter));
 			if (amdgpu_acpi_smart_shift_update(tmp_adev,
 							   AMDGPU_SS_DEV_D0))
 				dev_warn(tmp_adev->dev,
@@ -6457,8 +6461,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	reset_context->hive = hive;
 	INIT_LIST_HEAD(&device_list);
 
-	if (amdgpu_device_recovery_prepare(adev, &device_list, hive))
-		goto end_reset;
+	amdgpu_device_recovery_prepare(adev, &device_list, hive);
+
+	if (!amdgpu_sriov_vf(adev)) {
+		r = amdgpu_device_health_check(&device_list);
+		if (r)
+			goto end_reset;
+	}
 
 	/* We need to lock reset domain only once both for XGMI and single device */
 	amdgpu_device_recovery_get_reset_lock(adev, &device_list);
@@ -6880,7 +6889,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
+	struct amdgpu_hive_info *hive __free(xgmi_put_hive) =
+		amdgpu_get_xgmi_hive(adev);
 	struct amdgpu_reset_context reset_context;
 	struct list_head device_list;
 
@@ -6911,10 +6921,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		amdgpu_device_recovery_get_reset_lock(adev, &device_list);
 		amdgpu_device_halt_activities(adev, NULL, &reset_context, &device_list,
 					      hive, false);
-		if (hive) {
+		if (hive)
 			mutex_unlock(&hive->hive_lock);
-			amdgpu_put_xgmi_hive(hive);
-		}
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		/* Permanent error, prepare for device removal */
@@ -6965,12 +6973,6 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	int r = 0, i;
 	u32 memsize;
 
-	/* PCI error slot reset should be skipped During RAS recovery */
-	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) &&
-	    amdgpu_ras_in_recovery(adev))
-		return PCI_ERS_RESULT_RECOVERED;
-
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index e814da2b1422..dd7b2b796427 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2126,7 +2126,6 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 5):
 	case IP_VERSION(11, 0, 9):
 	case IP_VERSION(11, 0, 7):
-	case IP_VERSION(11, 0, 8):
 	case IP_VERSION(11, 0, 11):
 	case IP_VERSION(11, 0, 12):
 	case IP_VERSION(11, 0, 13):
@@ -2134,6 +2133,10 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 2):
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		break;
+	case IP_VERSION(11, 0, 8):
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2)
+			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		break;
 	case IP_VERSION(12, 0, 0):
 	case IP_VERSION(12, 0, 1):
 		amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 65f4a76490ea..e60043ac9841 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2172,6 +2172,11 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN},
 
 	/* CYAN_SKILLFISH */
+	{0x1002, 0x13DB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13F9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13FA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13FB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13FC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 	{0x1002, 0x13FE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 	{0x1002, 0x143F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 
@@ -2597,6 +2602,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	else if (amdgpu_acpi_is_s3_active(adev))
 		adev->in_s3 = true;
 	if (!adev->in_s0ix && !adev->in_s3) {
+#if IS_ENABLED(CONFIG_SUSPEND)
 		/* don't allow going deep first time followed by s2idle the next time */
 		if (adev->last_suspend_state != PM_SUSPEND_ON &&
 		    adev->last_suspend_state != pm_suspend_target_state) {
@@ -2604,11 +2610,14 @@ static int amdgpu_pmops_suspend(struct device *dev)
 				     pm_suspend_target_state);
 			return -EINVAL;
 		}
+#endif
 		return 0;
 	}
 
+#if IS_ENABLED(CONFIG_SUSPEND)
 	/* cache the state last used for suspend */
 	adev->last_suspend_state = pm_suspend_target_state;
+#endif
 
 	return amdgpu_device_suspend(drm_dev, true);
 }
@@ -2933,11 +2942,14 @@ static int amdgpu_drm_release(struct inode *inode, struct file *filp)
 {
 	struct drm_file *file_priv = filp->private_data;
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
+	struct drm_device *dev = file_priv->minor->dev;
+	int idx;
 
-	if (fpriv) {
+	if (fpriv && drm_dev_enter(dev, &idx)) {
 		fpriv->evf_mgr.fd_closing = true;
 		amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
 		amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
+		drm_dev_exit(idx);
 	}
 
 	return drm_release(inode, filp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 82d58ac7afb0..5d5e9ee83a5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -121,10 +121,12 @@ static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
 			fences += amdgpu_fence_count_emitted(&adev->jpeg.inst[i].ring_dec[j]);
 	}
 
-	if (!fences && !atomic_read(&adev->jpeg.total_submission_cnt))
+	if (!fences && !atomic_read(&adev->jpeg.total_submission_cnt)) {
+		mutex_lock(&adev->jpeg.jpeg_pg_lock);
 		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
 						       AMD_PG_STATE_GATE);
-	else
+		mutex_unlock(&adev->jpeg.jpeg_pg_lock);
+	} else
 		schedule_delayed_work(&adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 540817e296da..893cae9813fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -122,7 +122,7 @@ const char *get_ras_block_str(struct ras_common_if *ras_block)
 /* typical ECC bad page rate is 1 bad page per 100MB VRAM */
 #define RAS_BAD_PAGE_COVER              (100 * 1024 * 1024ULL)
 
-#define MAX_UMC_POISON_POLLING_TIME_ASYNC  300  //ms
+#define MAX_UMC_POISON_POLLING_TIME_ASYNC  10
 
 #define AMDGPU_RAS_RETIRE_PAGE_INTERVAL 100  //ms
 
@@ -136,9 +136,9 @@ enum amdgpu_ras_retire_page_reservation {
 
 atomic_t amdgpu_ras_in_intr = ATOMIC_INIT(0);
 
-static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
+static int amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
 				uint64_t addr);
-static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
+static int amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
 				uint64_t addr);
 #ifdef CONFIG_X86_MCE_AMD
 static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev);
@@ -169,18 +169,16 @@ static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t addre
 	struct eeprom_table_record err_rec;
 	int ret;
 
-	if ((address >= adev->gmc.mc_vram_size) ||
-	    (address >= RAS_UMC_INJECT_ADDR_LIMIT)) {
+	ret = amdgpu_ras_check_bad_page(adev, address);
+	if (ret == -EINVAL) {
 		dev_warn(adev->dev,
-		         "RAS WARN: input address 0x%llx is invalid.\n",
-		         address);
+			"RAS WARN: input address 0x%llx is invalid.\n",
+			address);
 		return -EINVAL;
-	}
-
-	if (amdgpu_ras_check_bad_page(adev, address)) {
+	} else if (ret == 1) {
 		dev_warn(adev->dev,
-			 "RAS WARN: 0x%llx has already been marked as bad page!\n",
-			 address);
+			"RAS WARN: 0x%llx has already been marked as bad page!\n",
+			address);
 		return 0;
 	}
 
@@ -513,22 +511,16 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f,
 		ret = amdgpu_ras_feature_enable(adev, &data.head, 1);
 		break;
 	case 2:
-		if ((data.inject.address >= adev->gmc.mc_vram_size &&
-		    adev->gmc.mc_vram_size) ||
-		    (data.inject.address >= RAS_UMC_INJECT_ADDR_LIMIT)) {
-			dev_warn(adev->dev, "RAS WARN: input address "
-					"0x%llx is invalid.",
+		/* umc ce/ue error injection for a bad page is not allowed */
+		if (data.head.block == AMDGPU_RAS_BLOCK__UMC)
+			ret = amdgpu_ras_check_bad_page(adev, data.inject.address);
+		if (ret == -EINVAL) {
+			dev_warn(adev->dev, "RAS WARN: input address 0x%llx is invalid.",
 					data.inject.address);
-			ret = -EINVAL;
 			break;
-		}
-
-		/* umc ce/ue error injection for a bad page is not allowed */
-		if ((data.head.block == AMDGPU_RAS_BLOCK__UMC) &&
-		    amdgpu_ras_check_bad_page(adev, data.inject.address)) {
-			dev_warn(adev->dev, "RAS WARN: inject: 0x%llx has "
-				 "already been marked as bad!\n",
-				 data.inject.address);
+		} else if (ret == 1) {
+			dev_warn(adev->dev, "RAS WARN: inject: 0x%llx has already been marked as bad!\n",
+					data.inject.address);
 			break;
 		}
 
@@ -3134,18 +3126,24 @@ out:
 	return ret;
 }
 
-static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
+static int amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
 				uint64_t addr)
 {
 	struct ras_err_handler_data *data = con->eh_data;
+	struct amdgpu_device *adev = con->adev;
 	int i;
 
+	if ((addr >= adev->gmc.mc_vram_size &&
+	    adev->gmc.mc_vram_size) ||
+	    (addr >= RAS_UMC_INJECT_ADDR_LIMIT))
+		return -EINVAL;
+
 	addr >>= AMDGPU_GPU_PAGE_SHIFT;
 	for (i = 0; i < data->count; i++)
 		if (addr == data->bps[i].retired_page)
-			return true;
+			return 1;
 
-	return false;
+	return 0;
 }
 
 /*
@@ -3153,11 +3151,11 @@ static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
  *
  * Note: this check is only for umc block
  */
-static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
+static int amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
 				uint64_t addr)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	bool ret = false;
+	int ret = 0;
 
 	if (!con || !con->eh_data)
 		return ret;
@@ -3241,7 +3239,7 @@ static void amdgpu_ras_ecc_log_init(struct ras_ecc_log_info *ecc_log)
 
 	INIT_RADIX_TREE(&ecc_log->de_page_tree, GFP_KERNEL);
 	ecc_log->de_queried_count = 0;
-	ecc_log->prev_de_queried_count = 0;
+	ecc_log->consumption_q_count = 0;
 }
 
 static void amdgpu_ras_ecc_log_fini(struct ras_ecc_log_info *ecc_log)
@@ -3261,7 +3259,7 @@ static void amdgpu_ras_ecc_log_fini(struct ras_ecc_log_info *ecc_log)
 
 	mutex_destroy(&ecc_log->lock);
 	ecc_log->de_queried_count = 0;
-	ecc_log->prev_de_queried_count = 0;
+	ecc_log->consumption_q_count = 0;
 }
 
 static bool amdgpu_ras_schedule_retirement_dwork(struct amdgpu_ras *con,
@@ -3287,7 +3285,6 @@ static void amdgpu_ras_do_page_retirement(struct work_struct *work)
 					      page_retirement_dwork.work);
 	struct amdgpu_device *adev = con->adev;
 	struct ras_err_data err_data;
-	unsigned long err_cnt;
 
 	/* If gpu reset is ongoing, delay retiring the bad pages */
 	if (amdgpu_in_reset(adev) || amdgpu_ras_in_recovery(adev)) {
@@ -3299,13 +3296,9 @@ static void amdgpu_ras_do_page_retirement(struct work_struct *work)
 	amdgpu_ras_error_data_init(&err_data);
 
 	amdgpu_umc_handle_bad_pages(adev, &err_data);
-	err_cnt = err_data.err_addr_cnt;
 
 	amdgpu_ras_error_data_fini(&err_data);
 
-	if (err_cnt && amdgpu_ras_is_rma(adev))
-		amdgpu_ras_reset_gpu(adev);
-
 	amdgpu_ras_schedule_retirement_dwork(con,
 			AMDGPU_RAS_RETIRE_PAGE_INTERVAL);
 }
@@ -3316,49 +3309,39 @@ static int amdgpu_ras_poison_creation_handler(struct amdgpu_device *adev,
 	int ret = 0;
 	struct ras_ecc_log_info *ecc_log;
 	struct ras_query_if info;
-	uint32_t timeout = 0;
+	u32 timeout = MAX_UMC_POISON_POLLING_TIME_ASYNC;
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
-	uint64_t de_queried_count;
-	uint32_t new_detect_count, total_detect_count;
-	uint32_t need_query_count = poison_creation_count;
+	u64 de_queried_count;
+	u64 consumption_q_count;
 	enum ras_event_type type = RAS_EVENT_TYPE_POISON_CREATION;
 
 	memset(&info, 0, sizeof(info));
 	info.head.block = AMDGPU_RAS_BLOCK__UMC;
 
 	ecc_log = &ras->umc_ecc_log;
-	total_detect_count = 0;
+	ecc_log->de_queried_count = 0;
+	ecc_log->consumption_q_count = 0;
+
 	do {
 		ret = amdgpu_ras_query_error_status_with_event(adev, &info, type);
 		if (ret)
 			return ret;
 
 		de_queried_count = ecc_log->de_queried_count;
-		if (de_queried_count > ecc_log->prev_de_queried_count) {
-			new_detect_count = de_queried_count - ecc_log->prev_de_queried_count;
-			ecc_log->prev_de_queried_count = de_queried_count;
-			timeout = 0;
-		} else {
-			new_detect_count = 0;
-		}
+		consumption_q_count = ecc_log->consumption_q_count;
 
-		if (new_detect_count) {
-			total_detect_count += new_detect_count;
-		} else {
-			if (!timeout && need_query_count)
-				timeout = MAX_UMC_POISON_POLLING_TIME_ASYNC;
+		if (de_queried_count && consumption_q_count)
+			break;
 
-			if (timeout) {
-				if (!--timeout)
-					break;
-				msleep(1);
-			}
-		}
-	} while (total_detect_count < need_query_count);
+		msleep(100);
+	} while (--timeout);
 
-	if (total_detect_count)
+	if (de_queried_count)
 		schedule_delayed_work(&ras->page_retirement_dwork, 0);
 
+	if (amdgpu_ras_is_rma(adev) && atomic_cmpxchg(&ras->rma_in_recovery, 0, 1) == 0)
+		amdgpu_ras_reset_gpu(adev);
+
 	return 0;
 }
 
@@ -3394,6 +3377,12 @@ static int amdgpu_ras_poison_consumption_handler(struct amdgpu_device *adev,
 		reset_flags |= msg.reset;
 	}
 
+	/*
+	 * Try to ensure poison creation handler is completed first
+	 * to set rma if bad page exceed threshold.
+	 */
+	flush_delayed_work(&con->page_retirement_dwork);
+
 	/* for RMA, amdgpu_ras_poison_creation_handler will trigger gpu reset */
 	if (reset_flags && !amdgpu_ras_is_rma(adev)) {
 		if (reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET)
@@ -3403,8 +3392,6 @@ static int amdgpu_ras_poison_consumption_handler(struct amdgpu_device *adev,
 		else
 			reset = reset_flags;
 
-		flush_delayed_work(&con->page_retirement_dwork);
-
 		con->gpu_reset_flags |= reset;
 		amdgpu_ras_reset_gpu(adev);
 
@@ -3446,7 +3433,8 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 				atomic_sub(poison_creation_count, &con->poison_creation_count);
 				atomic_sub(poison_creation_count, &con->page_retirement_req_cnt);
 			}
-		} while (atomic_read(&con->poison_creation_count));
+		} while (atomic_read(&con->poison_creation_count) &&
+			!atomic_read(&con->poison_consumption_count));
 
 		if (ret != -EIO) {
 			msg_count = kfifo_len(&con->poison_fifo);
@@ -3463,6 +3451,7 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 			/* gpu mode-1 reset is ongoing or just completed ras mode-1 reset */
 			/* Clear poison creation request */
 			atomic_set(&con->poison_creation_count, 0);
+			atomic_set(&con->poison_consumption_count, 0);
 
 			/* Clear poison fifo */
 			amdgpu_ras_clear_poison_fifo(adev);
@@ -3487,6 +3476,8 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 				atomic_sub(msg_count, &con->page_retirement_req_cnt);
 			}
 
+			atomic_set(&con->poison_consumption_count, 0);
+
 			/* Wake up work to save bad pages to eeprom */
 			schedule_delayed_work(&con->page_retirement_dwork, 0);
 		}
@@ -3572,6 +3563,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
 	mutex_init(&con->recovery_lock);
 	INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
 	atomic_set(&con->in_recovery, 0);
+	atomic_set(&con->rma_in_recovery, 0);
 	con->eeprom_control.bad_channel_bitmap = 0;
 
 	max_eeprom_records_count = amdgpu_ras_eeprom_max_record_count(&con->eeprom_control);
@@ -3589,6 +3581,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
 	init_waitqueue_head(&con->page_retirement_wq);
 	atomic_set(&con->page_retirement_req_cnt, 0);
 	atomic_set(&con->poison_creation_count, 0);
+	atomic_set(&con->poison_consumption_count, 0);
 	con->page_retirement_thread =
 		kthread_run(amdgpu_ras_page_retirement_thread, adev, "umc_page_retirement");
 	if (IS_ERR(con->page_retirement_thread)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 927d6bff734a..96cb62a44a35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -492,8 +492,8 @@ struct ras_ecc_err {
 struct ras_ecc_log_info {
 	struct mutex lock;
 	struct radix_tree_root de_page_tree;
-	uint64_t	de_queried_count;
-	uint64_t	prev_de_queried_count;
+	uint64_t de_queried_count;
+	uint64_t consumption_q_count;
 };
 
 struct amdgpu_ras {
@@ -515,6 +515,7 @@ struct amdgpu_ras {
 	/* gpu recovery */
 	struct work_struct recovery_work;
 	atomic_t in_recovery;
+	atomic_t rma_in_recovery;
 	struct amdgpu_device *adev;
 	/* error handler data */
 	struct ras_err_handler_data *eh_data;
@@ -557,6 +558,7 @@ struct amdgpu_ras {
 	struct mutex page_retirement_lock;
 	atomic_t page_retirement_req_cnt;
 	atomic_t poison_creation_count;
+	atomic_t poison_consumption_count;
 	struct mutex page_rsv_lock;
 	DECLARE_KFIFO(poison_fifo, struct ras_poison_msg, 128);
 	struct ras_ecc_log_info  umc_ecc_log;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 9bda9ad13f88..88ded6296be3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -774,9 +774,10 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 				control->tbl_rai.health_percent = 0;
 			}
 			ras->is_rma = true;
-			/* ignore the -ENOTSUPP return value */
-			amdgpu_dpm_send_rma_reason(adev);
 		}
+
+		/* ignore the -ENOTSUPP return value */
+		amdgpu_dpm_send_rma_reason(adev);
 	}
 
 	if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index c92b8794aa73..2e039fb778ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -252,6 +252,7 @@ int amdgpu_umc_pasid_poison_handler(struct amdgpu_device *adev,
 				block, pasid, pasid_fn, data, reset);
 			if (!ret) {
 				atomic_inc(&con->page_retirement_req_cnt);
+				atomic_inc(&con->poison_consumption_count);
 				wake_up(&con->page_retirement_wq);
 			}
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 8190c24a649a..a0fb13172e8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -44,6 +44,39 @@ u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev)
 	return userq_ip_mask;
 }
 
+int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr,
+				   u64 expected_size)
+{
+	struct amdgpu_bo_va_mapping *va_map;
+	u64 user_addr;
+	u64 size;
+	int r = 0;
+
+	user_addr = (addr & AMDGPU_GMC_HOLE_MASK) >> AMDGPU_GPU_PAGE_SHIFT;
+	size = expected_size >> AMDGPU_GPU_PAGE_SHIFT;
+
+	r = amdgpu_bo_reserve(vm->root.bo, false);
+	if (r)
+		return r;
+
+	va_map = amdgpu_vm_bo_lookup_mapping(vm, user_addr);
+	if (!va_map) {
+		r = -EINVAL;
+		goto out_err;
+	}
+	/* Only validate the userq whether resident in the VM mapping range */
+	if (user_addr >= va_map->start  &&
+	    va_map->last - user_addr + 1 >= size) {
+		amdgpu_bo_unreserve(vm->root.bo);
+		return 0;
+	}
+
+	r = -EINVAL;
+out_err:
+	amdgpu_bo_unreserve(vm->root.bo);
+	return r;
+}
+
 static int
 amdgpu_userq_unmap_helper(struct amdgpu_userq_mgr *uq_mgr,
 			  struct amdgpu_usermode_queue *queue)
@@ -404,27 +437,10 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		(args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK) >>
 		AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_SHIFT;
 
-	/* Usermode queues are only supported for GFX IP as of now */
-	if (args->in.ip_type != AMDGPU_HW_IP_GFX &&
-	    args->in.ip_type != AMDGPU_HW_IP_DMA &&
-	    args->in.ip_type != AMDGPU_HW_IP_COMPUTE) {
-		drm_file_err(uq_mgr->file, "Usermode queue doesn't support IP type %u\n",
-			     args->in.ip_type);
-		return -EINVAL;
-	}
-
 	r = amdgpu_userq_priority_permit(filp, priority);
 	if (r)
 		return r;
 
-	if ((args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE) &&
-	    (args->in.ip_type != AMDGPU_HW_IP_GFX) &&
-	    (args->in.ip_type != AMDGPU_HW_IP_COMPUTE) &&
-	    !amdgpu_is_tmz(adev)) {
-		drm_file_err(uq_mgr->file, "Secure only supported on GFX/Compute queues\n");
-		return -EINVAL;
-	}
-
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		drm_file_err(uq_mgr->file, "pm_runtime_get_sync() failed for userqueue create\n");
@@ -456,6 +472,15 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		r = -ENOMEM;
 		goto unlock;
 	}
+
+	/* Validate the userq virtual address.*/
+	if (amdgpu_userq_input_va_validate(&fpriv->vm, args->in.queue_va, args->in.queue_size) ||
+	    amdgpu_userq_input_va_validate(&fpriv->vm, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) ||
+	    amdgpu_userq_input_va_validate(&fpriv->vm, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) {
+		r = -EINVAL;
+		kfree(queue);
+		goto unlock;
+	}
 	queue->doorbell_handle = args->in.doorbell_handle;
 	queue->queue_type = args->in.ip_type;
 	queue->vm = &fpriv->vm;
@@ -543,22 +568,45 @@ unlock:
 	return r;
 }
 
-int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
-		       struct drm_file *filp)
+static int amdgpu_userq_input_args_validate(struct drm_device *dev,
+					union drm_amdgpu_userq *args,
+					struct drm_file *filp)
 {
-	union drm_amdgpu_userq *args = data;
-	int r;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	switch (args->in.op) {
 	case AMDGPU_USERQ_OP_CREATE:
 		if (args->in.flags & ~(AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK |
 				       AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE))
 			return -EINVAL;
-		r = amdgpu_userq_create(filp, args);
-		if (r)
-			drm_file_err(filp, "Failed to create usermode queue\n");
-		break;
+		/* Usermode queues are only supported for GFX IP as of now */
+		if (args->in.ip_type != AMDGPU_HW_IP_GFX &&
+		    args->in.ip_type != AMDGPU_HW_IP_DMA &&
+		    args->in.ip_type != AMDGPU_HW_IP_COMPUTE) {
+			drm_file_err(filp, "Usermode queue doesn't support IP type %u\n",
+				     args->in.ip_type);
+			return -EINVAL;
+		}
+
+		if ((args->in.flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE) &&
+		    (args->in.ip_type != AMDGPU_HW_IP_GFX) &&
+		    (args->in.ip_type != AMDGPU_HW_IP_COMPUTE) &&
+		    !amdgpu_is_tmz(adev)) {
+			drm_file_err(filp, "Secure only supported on GFX/Compute queues\n");
+			return -EINVAL;
+		}
 
+		if (args->in.queue_va == AMDGPU_BO_INVALID_OFFSET ||
+		    args->in.queue_va == 0 ||
+		    args->in.queue_size == 0) {
+			drm_file_err(filp, "invalidate userq queue va or size\n");
+			return -EINVAL;
+		}
+		if (!args->in.wptr_va || !args->in.rptr_va) {
+			drm_file_err(filp, "invalidate userq queue rptr or wptr\n");
+			return -EINVAL;
+		}
+		break;
 	case AMDGPU_USERQ_OP_FREE:
 		if (args->in.ip_type ||
 		    args->in.doorbell_handle ||
@@ -572,6 +620,31 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 		    args->in.mqd ||
 		    args->in.mqd_size)
 			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *filp)
+{
+	union drm_amdgpu_userq *args = data;
+	int r;
+
+	if (amdgpu_userq_input_args_validate(dev, args, filp) < 0)
+		return -EINVAL;
+
+	switch (args->in.op) {
+	case AMDGPU_USERQ_OP_CREATE:
+		r = amdgpu_userq_create(filp, args);
+		if (r)
+			drm_file_err(filp, "Failed to create usermode queue\n");
+		break;
+
+	case AMDGPU_USERQ_OP_FREE:
 		r = amdgpu_userq_destroy(filp, args->in.queue_id);
 		if (r)
 			drm_file_err(filp, "Failed to destroy usermode queue\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
index b1ca91b7cda4..8603c31320f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
@@ -133,4 +133,6 @@ int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev,
 int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev,
 						   u32 idx);
 
+int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr,
+				   u64 expected_size);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index c2a983ff23c9..b372baae3979 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -276,7 +276,7 @@ static int amdgpu_userq_fence_create(struct amdgpu_usermode_queue *userq,
 
 	/* Check if hardware has already processed the job */
 	spin_lock_irqsave(&fence_drv->fence_list_lock, flags);
-	if (!dma_fence_is_signaled_locked(fence))
+	if (!dma_fence_is_signaled(fence))
 		list_add_tail(&userq_fence->link, &fence_drv->fences);
 	else
 		dma_fence_put(fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 3da3ebb1d9a1..58accf2259b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -267,7 +267,8 @@ struct amdgpu_virt {
 	struct amdgpu_irq_src		rcv_irq;
 
 	struct work_struct		flr_work;
-	struct work_struct		bad_pages_work;
+	struct work_struct		req_bad_pages_work;
+	struct work_struct		handle_bad_pages_work;
 
 	struct amdgpu_mm_table		mm_table;
 	const struct amdgpu_virt_ops	*ops;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 121ee17b522b..118fbe38b33a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -322,6 +322,26 @@ static int vpe_early_init(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
+static bool vpe_need_dpm0_at_power_down(struct amdgpu_device *adev)
+{
+	switch (amdgpu_ip_version(adev, VPE_HWIP, 0)) {
+	case IP_VERSION(6, 1, 1):
+		return adev->pm.fw_version < 0x0a640500;
+	default:
+		return false;
+	}
+}
+
+static int vpe_get_dpm_level(struct amdgpu_device *adev)
+{
+	struct amdgpu_vpe *vpe = &adev->vpe;
+
+	if (!adev->pm.dpm_enabled)
+		return 0;
+
+	return RREG32(vpe_get_reg_offset(vpe, 0, vpe->regs.dpm_request_lv));
+}
+
 static void vpe_idle_work_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
@@ -329,11 +349,17 @@ static void vpe_idle_work_handler(struct work_struct *work)
 	unsigned int fences = 0;
 
 	fences += amdgpu_fence_count_emitted(&adev->vpe.ring);
+	if (fences)
+		goto reschedule;
+
+	if (vpe_need_dpm0_at_power_down(adev) && vpe_get_dpm_level(adev) != 0)
+		goto reschedule;
 
-	if (fences == 0)
-		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE, AMD_PG_STATE_GATE);
-	else
-		schedule_delayed_work(&adev->vpe.idle_work, VPE_IDLE_TIMEOUT);
+	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE, AMD_PG_STATE_GATE);
+	return;
+
+reschedule:
+	schedule_delayed_work(&adev->vpe.idle_work, VPE_IDLE_TIMEOUT);
 }
 
 static int vpe_common_init(struct amdgpu_vpe *vpe)
@@ -435,6 +461,8 @@ static int vpe_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	struct amdgpu_vpe *vpe = &adev->vpe;
 
+	cancel_delayed_work_sync(&adev->vpe.idle_work);
+
 	vpe_ring_stop(vpe);
 
 	/* Power off VPE */
@@ -445,10 +473,6 @@ static int vpe_hw_fini(struct amdgpu_ip_block *ip_block)
 
 static int vpe_suspend(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-
-	cancel_delayed_work_sync(&adev->vpe.idle_work);
-
 	return vpe_hw_fini(ip_block);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index c417f8689220..699acc1b46b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -406,6 +406,7 @@ void amdgpu_xcp_dev_unplug(struct amdgpu_device *adev)
 		p_ddev->primary->dev = adev->xcp_mgr->xcp[i].pdev;
 		p_ddev->driver =  adev->xcp_mgr->xcp[i].driver;
 		p_ddev->vma_offset_manager = adev->xcp_mgr->xcp[i].vma_offset_manager;
+		amdgpu_xcp_drm_dev_free(p_ddev);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index bba0b26fee8f..5f36aff17e79 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -126,4 +126,8 @@ uint32_t amdgpu_xgmi_get_max_bandwidth(struct amdgpu_device *adev);
 
 void amgpu_xgmi_set_max_speed_width(struct amdgpu_device *adev,
 				    uint16_t max_speed, uint8_t max_width);
+
+/* Cleanup macro for use with __free(xgmi_put_hive) */
+DEFINE_FREE(xgmi_put_hive, struct amdgpu_hive_info *, if (_T) amdgpu_put_xgmi_hive(_T))
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index 427b073de2fc..1a7591ca2f9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -1246,6 +1246,10 @@ static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index,
 	ectx.last_jump_jiffies = 0;
 	if (ws) {
 		ectx.ws = kcalloc(4, ws, GFP_KERNEL);
+		if (!ectx.ws) {
+			ret = -ENOMEM;
+			goto free;
+		}
 		ectx.ws_size = ws;
 	} else {
 		ectx.ws = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 51babf5c78c8..f06bc94cf6e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3562,6 +3562,7 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[ring->xcc_id];
 	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	int reset_mode = AMDGPU_RESET_TYPE_PER_QUEUE;
 	unsigned long flags;
 	int r;
 
@@ -3599,6 +3600,7 @@ pipe_reset:
 		if (!(adev->gfx.compute_supported_reset & AMDGPU_RESET_TYPE_PER_PIPE))
 			return -EOPNOTSUPP;
 		r = gfx_v9_4_3_reset_hw_pipe(ring);
+		reset_mode = AMDGPU_RESET_TYPE_PER_PIPE;
 		dev_info(adev->dev, "ring: %s pipe reset :%s\n", ring->name,
 				r ? "failed" : "successfully");
 		if (r)
@@ -3621,10 +3623,20 @@ pipe_reset:
 	r = amdgpu_ring_test_ring(kiq_ring);
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
+		if (reset_mode == AMDGPU_RESET_TYPE_PER_QUEUE)
+			goto pipe_reset;
+
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
 	}
 
+	if (reset_mode == AMDGPU_RESET_TYPE_PER_QUEUE) {
+		r = amdgpu_ring_test_ring(ring);
+		if (r)
+			goto pipe_reset;
+	}
+
+
 	return amdgpu_ring_reset_helper_end(ring, timedout_fence);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 54523dc1f702..7731ef262d39 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -196,6 +196,14 @@ static int jpeg_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG)) {
+		r = amdgpu_jpeg_ras_sw_init(adev);
+		if (r) {
+			dev_err(adev->dev, "Failed to initialize jpeg ras block!\n");
+			return r;
+		}
+	}
+
 	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_5_0_1, ARRAY_SIZE(jpeg_reg_list_5_0_1));
 	if (r)
 		return r;
@@ -307,7 +315,7 @@ static int jpeg_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
 			ret = jpeg_v5_0_1_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
 	}
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG))
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG) && !amdgpu_sriov_vf(adev))
 		amdgpu_irq_put(adev, &adev->jpeg.inst->ras_poison_irq, 0);
 
 	return ret;
@@ -1058,6 +1066,11 @@ static int jpeg_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_comm
 	if (r)
 		return r;
 
+	r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__JPEG,
+				&jpeg_v5_0_1_aca_info, NULL);
+	if (r)
+		goto late_fini;
+
 	if (amdgpu_ras_is_supported(adev, ras_block->block) &&
 		adev->jpeg.inst->ras_poison_irq.funcs) {
 		r = amdgpu_irq_get(adev, &adev->jpeg.inst->ras_poison_irq, 0);
@@ -1065,11 +1078,6 @@ static int jpeg_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_comm
 			goto late_fini;
 	}
 
-	r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__JPEG,
-				&jpeg_v5_0_1_aca_info, NULL);
-	if (r)
-		goto late_fini;
-
 	return 0;
 
 late_fini:
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
index d6f50b13e2ba..ef54d211214f 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -206,6 +206,7 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 	struct amdgpu_mqd *mqd_hw_default = &adev->mqds[queue->queue_type];
 	struct drm_amdgpu_userq_in *mqd_user = args_in;
 	struct amdgpu_mqd_prop *userq_props;
+	struct amdgpu_gfx_shadow_info shadow_info;
 	int r;
 
 	/* Structure to initialize MQD for userqueue using generic MQD init function */
@@ -215,13 +216,6 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 		return -ENOMEM;
 	}
 
-	if (!mqd_user->wptr_va || !mqd_user->rptr_va ||
-	    !mqd_user->queue_va || mqd_user->queue_size == 0) {
-		DRM_ERROR("Invalid MQD parameters for userqueue\n");
-		r = -EINVAL;
-		goto free_props;
-	}
-
 	r = amdgpu_userq_create_object(uq_mgr, &queue->mqd, mqd_hw_default->mqd_size);
 	if (r) {
 		DRM_ERROR("Failed to create MQD object for userqueue\n");
@@ -238,6 +232,8 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 	userq_props->doorbell_index = queue->doorbell_index;
 	userq_props->fence_address = queue->fence_drv->gpu_addr;
 
+	if (adev->gfx.funcs->get_gfx_shadow_info)
+		adev->gfx.funcs->get_gfx_shadow_info(adev, &shadow_info, true);
 	if (queue->queue_type == AMDGPU_HW_IP_COMPUTE) {
 		struct drm_amdgpu_userq_mqd_compute_gfx11 *compute_mqd;
 
@@ -254,6 +250,10 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 			goto free_mqd;
 		}
 
+		if (amdgpu_userq_input_va_validate(queue->vm, compute_mqd->eop_va,
+		    max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE)))
+			goto free_mqd;
+
 		userq_props->eop_gpu_addr = compute_mqd->eop_va;
 		userq_props->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_NORMAL;
 		userq_props->hqd_queue_priority = AMDGPU_GFX_QUEUE_PRIORITY_MINIMUM;
@@ -281,6 +281,11 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 		userq_props->csa_addr = mqd_gfx_v11->csa_va;
 		userq_props->tmz_queue =
 			mqd_user->flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE;
+
+		if (amdgpu_userq_input_va_validate(queue->vm, mqd_gfx_v11->shadow_va,
+		    shadow_info.shadow_size))
+			goto free_mqd;
+
 		kfree(mqd_gfx_v11);
 	} else if (queue->queue_type == AMDGPU_HW_IP_DMA) {
 		struct drm_amdgpu_userq_mqd_sdma_gfx11 *mqd_sdma_v11;
@@ -298,6 +303,10 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 			goto free_mqd;
 		}
 
+		if (amdgpu_userq_input_va_validate(queue->vm, mqd_sdma_v11->csa_va,
+		    shadow_info.csa_size))
+			goto free_mqd;
+
 		userq_props->csa_addr = mqd_sdma_v11->csa_va;
 		kfree(mqd_sdma_v11);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 48101a34e049..9a40107a0869 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -292,14 +292,32 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	}
 }
 
-static void xgpu_ai_mailbox_bad_pages_work(struct work_struct *work)
+static void xgpu_ai_mailbox_req_bad_pages_work(struct work_struct *work)
 {
-	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, bad_pages_work);
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, req_bad_pages_work);
 	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
 
 	if (down_read_trylock(&adev->reset_domain->sem)) {
 		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_request_bad_pages(adev);
+		up_read(&adev->reset_domain->sem);
+	}
+}
+
+/**
+ * xgpu_ai_mailbox_handle_bad_pages_work - Reinitialize the data exchange region to get fresh bad page information
+ * @work: pointer to the work_struct
+ *
+ * This work handler is triggered when bad pages are ready, and it reinitializes
+ * the data exchange region to retrieve updated bad page information from the host.
+ */
+static void xgpu_ai_mailbox_handle_bad_pages_work(struct work_struct *work)
+{
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, handle_bad_pages_work);
+	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
+
+	if (down_read_trylock(&adev->reset_domain->sem)) {
+		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_init_data_exchange(adev);
 		up_read(&adev->reset_domain->sem);
 	}
@@ -327,10 +345,15 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (event) {
+	case IDH_RAS_BAD_PAGES_READY:
+		xgpu_ai_mailbox_send_ack(adev);
+		if (amdgpu_sriov_runtime(adev))
+			schedule_work(&adev->virt.handle_bad_pages_work);
+		break;
 	case IDH_RAS_BAD_PAGES_NOTIFICATION:
 		xgpu_ai_mailbox_send_ack(adev);
 		if (amdgpu_sriov_runtime(adev))
-			schedule_work(&adev->virt.bad_pages_work);
+			schedule_work(&adev->virt.req_bad_pages_work);
 		break;
 	case IDH_UNRECOV_ERR_NOTIFICATION:
 		xgpu_ai_mailbox_send_ack(adev);
@@ -415,7 +438,8 @@ int xgpu_ai_mailbox_get_irq(struct amdgpu_device *adev)
 	}
 
 	INIT_WORK(&adev->virt.flr_work, xgpu_ai_mailbox_flr_work);
-	INIT_WORK(&adev->virt.bad_pages_work, xgpu_ai_mailbox_bad_pages_work);
+	INIT_WORK(&adev->virt.req_bad_pages_work, xgpu_ai_mailbox_req_bad_pages_work);
+	INIT_WORK(&adev->virt.handle_bad_pages_work, xgpu_ai_mailbox_handle_bad_pages_work);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index f6d8597452ed..457972aa5632 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -202,9 +202,6 @@ send_request:
 	case IDH_REQ_RAS_CPER_DUMP:
 		event = IDH_RAS_CPER_DUMP_READY;
 		break;
-	case IDH_REQ_RAS_BAD_PAGES:
-		event = IDH_RAS_BAD_PAGES_READY;
-		break;
 	default:
 		break;
 	}
@@ -359,14 +356,32 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	}
 }
 
-static void xgpu_nv_mailbox_bad_pages_work(struct work_struct *work)
+static void xgpu_nv_mailbox_req_bad_pages_work(struct work_struct *work)
 {
-	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, bad_pages_work);
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, req_bad_pages_work);
 	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
 
 	if (down_read_trylock(&adev->reset_domain->sem)) {
 		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_request_bad_pages(adev);
+		up_read(&adev->reset_domain->sem);
+	}
+}
+
+/**
+ * xgpu_nv_mailbox_handle_bad_pages_work - Reinitialize the data exchange region to get fresh bad page information
+ * @work: pointer to the work_struct
+ *
+ * This work handler is triggered when bad pages are ready, and it reinitializes
+ * the data exchange region to retrieve updated bad page information from the host.
+ */
+static void xgpu_nv_mailbox_handle_bad_pages_work(struct work_struct *work)
+{
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, handle_bad_pages_work);
+	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
+
+	if (down_read_trylock(&adev->reset_domain->sem)) {
+		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_init_data_exchange(adev);
 		up_read(&adev->reset_domain->sem);
 	}
@@ -397,10 +412,15 @@ static int xgpu_nv_mailbox_rcv_irq(struct amdgpu_device *adev,
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (event) {
+	case IDH_RAS_BAD_PAGES_READY:
+		xgpu_nv_mailbox_send_ack(adev);
+		if (amdgpu_sriov_runtime(adev))
+			schedule_work(&adev->virt.handle_bad_pages_work);
+		break;
 	case IDH_RAS_BAD_PAGES_NOTIFICATION:
 		xgpu_nv_mailbox_send_ack(adev);
 		if (amdgpu_sriov_runtime(adev))
-			schedule_work(&adev->virt.bad_pages_work);
+			schedule_work(&adev->virt.req_bad_pages_work);
 		break;
 	case IDH_UNRECOV_ERR_NOTIFICATION:
 		xgpu_nv_mailbox_send_ack(adev);
@@ -485,7 +505,8 @@ int xgpu_nv_mailbox_get_irq(struct amdgpu_device *adev)
 	}
 
 	INIT_WORK(&adev->virt.flr_work, xgpu_nv_mailbox_flr_work);
-	INIT_WORK(&adev->virt.bad_pages_work, xgpu_nv_mailbox_bad_pages_work);
+	INIT_WORK(&adev->virt.req_bad_pages_work, xgpu_nv_mailbox_req_bad_pages_work);
+	INIT_WORK(&adev->virt.handle_bad_pages_work, xgpu_nv_mailbox_handle_bad_pages_work);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 9e74c9822e62..9785fada4fa7 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -741,7 +741,6 @@ static void soc15_reg_base_init(struct amdgpu_device *adev)
 void soc15_set_virt_ops(struct amdgpu_device *adev)
 {
 	adev->virt.ops = &xgpu_ai_virt_ops;
-
 	/* init soc15 reg base early enough so we can
 	 * request request full access for sriov before
 	 * set_ip_blocks. */
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index e590cbdd8de9..8dc32787d625 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -536,8 +536,11 @@ static int umc_v12_0_update_ecc_status(struct amdgpu_device *adev,
 	hwid = REG_GET_FIELD(ipid, MCMP1_IPIDT0, HardwareID);
 	mcatype = REG_GET_FIELD(ipid, MCMP1_IPIDT0, McaType);
 
-	if ((hwid != MCA_UMC_HWID_V12_0) || (mcatype != MCA_UMC_MCATYPE_V12_0))
+	/* The IP block decode of consumption is SMU */
+	if (hwid != MCA_UMC_HWID_V12_0 || mcatype != MCA_UMC_MCATYPE_V12_0) {
+		con->umc_ecc_log.consumption_q_count++;
 		return 0;
+	}
 
 	if (!status)
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 68b4371df0f1..d1481e6d57ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -865,6 +865,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
+	int ret;
 
 	vcn_v2_0_enable_static_power_gating(vinst);
 
@@ -948,8 +949,13 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 		UVD, 0, mmUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, 0, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, 0, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	/* force RBC into idle state */
 	rb_bufsz = order_base_2(ring->ring_size);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index f13ed3c1e29c..fdd8e33916f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -1012,6 +1012,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), 1,
@@ -1102,8 +1103,13 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 		VCN, 0, mmUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_dec;
 	/* force RBC into idle state */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 866222fc10a0..b7c4fcca18bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1041,6 +1041,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), 1,
@@ -1133,8 +1134,13 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, inst_idx, mmUVD_VCPU_CNTL), tmp, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_dec;
 	/* force RBC into idle state */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index ac55549e20be..082def4a6bdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1012,6 +1012,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 1,
@@ -1094,8 +1095,13 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index ba944a96c070..2e985c4a288a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -849,7 +849,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared =
 						adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
-	int vcn_inst;
+	int vcn_inst, ret;
 	uint32_t tmp;
 
 	vcn_inst = GET_INST(VCN, inst_idx);
@@ -942,8 +942,13 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, 0, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 11fec716e846..3ce49dfd3897 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -924,6 +924,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 1,
@@ -1004,8 +1005,13 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, inst_idx, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 07a6e9582880..f9dbd2757d83 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -713,6 +713,7 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 1,
@@ -766,8 +767,13 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, inst_idx, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "%s: vcn sram load failed %d\n", __func__, ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index cdefd7fcb0da..8ef4a8b2fae9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -284,7 +284,7 @@ static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
 			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 	}
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN) && !amdgpu_sriov_vf(adev))
 		amdgpu_irq_put(adev, &adev->vcn.inst->ras_poison_irq, 0);
 
 	return 0;
@@ -605,7 +605,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__PAUSE};
-	int vcn_inst;
+	int vcn_inst, ret;
 	uint32_t tmp;
 
 	vcn_inst = GET_INST(VCN, inst_idx);
@@ -666,8 +666,13 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, 0, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	/* resetting ring, fw should not check RB ring */
 	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
@@ -1603,6 +1608,13 @@ static int vcn_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_commo
 	if (r)
 		goto late_fini;
 
+	if (amdgpu_ras_is_supported(adev, ras_block->block) &&
+		adev->vcn.inst->ras_poison_irq.funcs) {
+		r = amdgpu_irq_get(adev, &adev->vcn.inst->ras_poison_irq, 0);
+		if (r)
+			goto late_fini;
+	}
+
 	return 0;
 
 late_fini: