Merge tag 'amd-drm-next-6.8-2024-01-05' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.8-2024-01-05:

amdgpu:
- VRR fixes
- PSR-SU fixes
- SubVP fixes
- DCN 3.5 fixes
- Documentation updates
- DMCUB fixes
- DML2 fixes
- UMC 12.0 updates
- GPUVM fix
- Misc code cleanups and whitespace cleanups
- DP MST fix
- Let KFD sync with GPUVM fences
- GFX11 reset fix
- SMU 13.0.6 fixes
- VSC fix for DP/eDP
- Navi12 display fix
- RN/CZN system aperture fix
- DCN 2.1 bandwidth validation fix
- DCN INIT cleanup

amdkfd:
- SVM fixes
- Revert TBA/TMA location change

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240105220522.4976-1-alexander.deucher@amd.com

30 files changed, 267 insertions, 68 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
index 02f4c6f9d4f6..576067d66bb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
@@ -330,6 +330,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 {
 	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
+	struct amdgpu_ras *con;
 	int r;
 
 	if (reset_device_list == NULL)
@@ -355,7 +356,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		 */
 		amdgpu_register_gpu_instance(tmp_adev);
 
-		/* Resume RAS */
+		/* Resume RAS, ecc_irq */
+		con = amdgpu_ras_get_context(tmp_adev);
+		if (!amdgpu_sriov_vf(tmp_adev) && con) {
+			if (tmp_adev->sdma.ras &&
+				tmp_adev->sdma.ras->ras_block.ras_late_init) {
+				r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->sdma.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+
+			if (tmp_adev->gfx.ras &&
+				tmp_adev->gfx.ras->ras_block.ras_late_init) {
+				r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->gfx.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+		}
+
 		amdgpu_ras_resume(tmp_adev);
 
 		/* Update PSP FW topology after reset */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 616b6c911767..9da14436a373 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -254,6 +254,8 @@ extern int amdgpu_agp;
 
 extern int amdgpu_wbrf;
 
+extern int fw_bo_location;
+
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
index 469785d33791..1ef758ac5076 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
@@ -90,7 +90,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
 		return NULL;
 
 	fence = container_of(f, struct amdgpu_amdkfd_fence, base);
-	if (fence && f->ops == &amdkfd_fence_ops)
+	if (f->ops == &amdkfd_fence_ops)
 		return fence;
 
 	return NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 96f63fd39b9e..9caba10315a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1103,7 +1103,7 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 			 * DDC line.  The latter is more complex because with DVI<->HDMI adapters
 			 * you don't really know what's connected to which port as both are digital.
 			 */
-			 amdgpu_connector_shared_ddc(&ret, connector, amdgpu_connector);
+			amdgpu_connector_shared_ddc(&ret, connector, amdgpu_connector);
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 440e9a6786fc..6adeddfb3d56 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -870,9 +870,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		struct amdgpu_bo *bo = e->bo;
 		int i;
 
-		e->user_pages = kvmalloc_array(bo->tbo.ttm->num_pages,
-					sizeof(struct page *),
-					GFP_KERNEL | __GFP_ZERO);
+		e->user_pages = kvcalloc(bo->tbo.ttm->num_pages,
+					 sizeof(struct page *),
+					 GFP_KERNEL);
 		if (!e->user_pages) {
 			DRM_ERROR("kvmalloc_array failure\n");
 			r = -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 2cebf2145d9a..e485dd3357c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -540,7 +540,11 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 	while (size) {
 		uint32_t value;
 
-		value = RREG32_PCIE(*pos);
+		if (upper_32_bits(*pos))
+			value = RREG32_PCIE_EXT(*pos);
+		else
+			value = RREG32_PCIE(*pos);
+
 		r = put_user(value, (uint32_t *)buf);
 		if (r)
 			goto out;
@@ -600,7 +604,10 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 		if (r)
 			goto out;
 
-		WREG32_PCIE(*pos, value);
+		if (upper_32_bits(*pos))
+			WREG32_PCIE_EXT(*pos, value);
+		else
+			WREG32_PCIE(*pos, value);
 
 		result += 4;
 		buf += 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 85ed0d66a029..5bb444bb36ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2251,15 +2251,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 
 	adev->firmware.gpu_info_fw = NULL;
 
-	if (adev->mman.discovery_bin) {
-		/*
-		 * FIXME: The bounding box is still needed by Navi12, so
-		 * temporarily read it from gpu_info firmware. Should be dropped
-		 * when DAL no longer needs it.
-		 */
-		if (adev->asic_type != CHIP_NAVI12)
-			return 0;
-	}
+	if (adev->mman.discovery_bin)
+		return 0;
 
 	switch (adev->asic_type) {
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 880137774b4e..852cec98ff26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -210,6 +210,7 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
+int fw_bo_location = -1;
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -989,6 +990,10 @@ MODULE_PARM_DESC(wbrf,
 	"Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)");
 module_param_named(wbrf, amdgpu_wbrf, int, 0444);
 
+MODULE_PARM_DESC(fw_bo_location,
+	"location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram");
+module_param(fw_bo_location, int, 0644);
+
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
index 210aea590a52..59fafb8392e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -218,6 +218,7 @@ static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, st
 int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, struct ras_err_data *err_data)
 {
 	struct amdgpu_smuio_mcm_config_info mcm_info;
+	struct ras_err_addr err_addr = {0};
 	struct mca_bank_set mca_set;
 	struct mca_bank_node *node;
 	struct mca_bank_entry *entry;
@@ -246,10 +247,18 @@ int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_blo
 		mcm_info.socket_id = entry->info.socket_id;
 		mcm_info.die_id = entry->info.aid;
 
+		if (blk == AMDGPU_RAS_BLOCK__UMC) {
+			err_addr.err_status = entry->regs[MCA_REG_IDX_STATUS];
+			err_addr.err_ipid = entry->regs[MCA_REG_IDX_IPID];
+			err_addr.err_addr = entry->regs[MCA_REG_IDX_ADDR];
+		}
+
 		if (type == AMDGPU_MCA_ERROR_TYPE_UE)
-			amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, (uint64_t)count);
+			amdgpu_ras_error_statistic_ue_count(err_data,
+				&mcm_info, &err_addr, (uint64_t)count);
 		else
-			amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, (uint64_t)count);
+			amdgpu_ras_error_statistic_ce_count(err_data,
+				&mcm_info, &err_addr, (uint64_t)count);
 	}
 
 out_mca_release:
@@ -351,6 +360,9 @@ int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_err
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
 	int count;
 
+	if (!mca_funcs || !mca_funcs->mca_get_mca_entry)
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case AMDGPU_MCA_ERROR_TYPE_UE:
 		count = mca_funcs->max_ue_count;
@@ -365,10 +377,7 @@ int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_err
 	if (idx >= count)
 		return -EINVAL;
 
-	if (mca_funcs && mca_funcs->mca_get_mca_entry)
-		return mca_funcs->mca_get_mca_entry(adev, type, idx, entry);
-
-	return -EOPNOTSUPP;
+	return mca_funcs->mca_get_mca_entry(adev, type, idx, entry);
 }
 
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 1bf975b8d083..2addbdf88394 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -466,7 +466,7 @@ static int psp_sw_init(void *handle)
 	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      amdgpu_sriov_vf(adev) ?
+				      (amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
 				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 				      &psp->fw_pri_bo,
 				      &psp->fw_pri_mc_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index bacb59d8b701..fc42fb6ee191 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1156,8 +1156,10 @@ static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, s
 		for_each_ras_error(err_node, err_data) {
 			err_info = &err_node->err_info;
 
-			amdgpu_ras_error_statistic_ce_count(&obj->err_data, &err_info->mcm_info, err_info->ce_count);
-			amdgpu_ras_error_statistic_ue_count(&obj->err_data, &err_info->mcm_info, err_info->ue_count);
+			amdgpu_ras_error_statistic_ce_count(&obj->err_data,
+					&err_info->mcm_info, NULL, err_info->ce_count);
+			amdgpu_ras_error_statistic_ue_count(&obj->err_data,
+					&err_info->mcm_info, NULL, err_info->ue_count);
 		}
 	} else {
 		/* for legacy asic path which doesn't has error source info */
@@ -1174,6 +1176,9 @@ static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev,
 	enum amdgpu_ras_block blk = info ? info->head.block : AMDGPU_RAS_BLOCK_COUNT;
 	struct amdgpu_ras_block_object *block_obj = NULL;
 
+	if (blk == AMDGPU_RAS_BLOCK_COUNT)
+		return -EINVAL;
+
 	if (error_query_mode == AMDGPU_RAS_INVALID_ERROR_QUERY)
 		return -EINVAL;
 
@@ -2538,7 +2543,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 		return 0;
 
 	data = &con->eh_data;
-	*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
+	*data = kzalloc(sizeof(**data), GFP_KERNEL);
 	if (!*data) {
 		ret = -ENOMEM;
 		goto out;
@@ -2825,10 +2830,10 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 	if (con)
 		return 0;
 
-	con = kmalloc(sizeof(struct amdgpu_ras) +
+	con = kzalloc(sizeof(*con) +
 			sizeof(struct ras_manager) * AMDGPU_RAS_BLOCK_COUNT +
 			sizeof(struct ras_manager) * AMDGPU_RAS_MCA_BLOCK_COUNT,
-			GFP_KERNEL|__GFP_ZERO);
+			GFP_KERNEL);
 	if (!con)
 		return -ENOMEM;
 
@@ -3133,8 +3138,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-	/* enable MCA debug on APU device */
-	amdgpu_ras_set_mca_debug_mode(adev, !!(adev->flags & AMD_IS_APU));
+	amdgpu_ras_set_mca_debug_mode(adev, false);
 
 	list_for_each_entry_safe(node, tmp, &adev->ras_list, node) {
 		if (!node->ras_obj) {
@@ -3691,7 +3695,8 @@ static int ras_err_info_cmp(void *priv, const struct list_head *a, const struct
 }
 
 static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_data,
-						      struct amdgpu_smuio_mcm_config_info *mcm_info)
+				struct amdgpu_smuio_mcm_config_info *mcm_info,
+				struct ras_err_addr *err_addr)
 {
 	struct ras_err_node *err_node;
 
@@ -3705,6 +3710,9 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 
 	memcpy(&err_node->err_info.mcm_info, mcm_info, sizeof(*mcm_info));
 
+	if (err_addr)
+		memcpy(&err_node->err_info.err_addr, err_addr, sizeof(*err_addr));
+
 	err_data->err_list_count++;
 	list_add_tail(&err_node->node, &err_data->err_node_list);
 	list_sort(NULL, &err_data->err_node_list, ras_err_info_cmp);
@@ -3713,7 +3721,8 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 }
 
 int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count)
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -3723,7 +3732,7 @@ int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
 	if (!count)
 		return 0;
 
-	err_info = amdgpu_ras_error_get_info(err_data, mcm_info);
+	err_info = amdgpu_ras_error_get_info(err_data, mcm_info, err_addr);
 	if (!err_info)
 		return -EINVAL;
 
@@ -3734,7 +3743,8 @@ int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
 }
 
 int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count)
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -3744,7 +3754,7 @@ int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
 	if (!count)
 		return 0;
 
-	err_info = amdgpu_ras_error_get_info(err_data, mcm_info);
+	err_info = amdgpu_ras_error_get_info(err_data, mcm_info, err_addr);
 	if (!err_info)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 6a941eb8fb8f..76fb85628716 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -452,10 +452,17 @@ struct ras_fs_data {
 	char debugfs_name[32];
 };
 
+struct ras_err_addr {
+	uint64_t err_status;
+	uint64_t err_ipid;
+	uint64_t err_addr;
+};
+
 struct ras_err_info {
 	struct amdgpu_smuio_mcm_config_info mcm_info;
 	u64 ce_count;
 	u64 ue_count;
+	struct ras_err_addr err_addr;
 };
 
 struct ras_err_node {
@@ -806,8 +813,10 @@ void amdgpu_ras_inst_reset_ras_error_count(struct amdgpu_device *adev,
 int amdgpu_ras_error_data_init(struct ras_err_data *err_data);
 void amdgpu_ras_error_data_fini(struct ras_err_data *err_data);
 int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count);
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count);
 int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
-					struct amdgpu_smuio_mcm_config_info *mcm_info, u64 count);
+		struct amdgpu_smuio_mcm_config_info *mcm_info,
+		struct ras_err_addr *err_addr, u64 count);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
index 35e0ae9acadc..2c3675d91614 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -531,13 +531,12 @@ int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev,
 	if (version_major == 2 && version_minor == 1)
 		adev->gfx.rlc.is_rlc_v2_1 = true;
 
-	if (version_minor >= 0) {
-		err = amdgpu_gfx_rlc_init_microcode_v2_0(adev);
-		if (err) {
-			dev_err(adev->dev, "fail to init rlc v2_0 microcode\n");
-			return err;
-		}
+	err = amdgpu_gfx_rlc_init_microcode_v2_0(adev);
+	if (err) {
+		dev_err(adev->dev, "fail to init rlc v2_0 microcode\n");
+		return err;
 	}
+
 	if (version_minor >= 1)
 		amdgpu_gfx_rlc_init_microcode_v2_1(adev);
 	if (version_minor >= 2)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index dcd8c066bc1f..1b013a44ca99 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -191,7 +191,8 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev,
 
 	/* Never sync to VM updates either. */
 	if (fence_owner == AMDGPU_FENCE_OWNER_VM &&
-	    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
+	    owner != AMDGPU_FENCE_OWNER_UNDEFINED &&
+	    owner != AMDGPU_FENCE_OWNER_KFD)
 		return false;
 
 	/* Ignore fences depending on the sync mode */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index b14127429f30..d334e42fe0eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1062,7 +1062,8 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
 {
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
 		amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
-			amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
+			(amdgpu_sriov_vf(adev) || fw_bo_location == 1) ?
+			AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
 			&adev->firmware.fw_buf,
 			&adev->firmware.fw_buf_mc,
 			&adev->firmware.fw_buf_ptr);
@@ -1397,9 +1398,13 @@ int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw,
 
 	if (err)
 		return -ENODEV;
+
 	err = amdgpu_ucode_validate(*fw);
-	if (err)
+	if (err) {
 		dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name);
+		release_firmware(*fw);
+		*fw = NULL;
+	}
 
 	return err;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 7da71b6a9dc6..b8fcb6c55698 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -285,6 +285,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = vm_bo->bo;
 
+		vm_bo->moved = true;
 		if (!bo || bo->tbo.type != ttm_bo_type_kernel)
 			list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
 		else if (bo->parent)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 9a95b9f226b8..a6c88f2fe6e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -1313,10 +1313,10 @@ static void __xgmi_v6_4_0_query_error_count(struct amdgpu_device *adev, struct a
 
 	switch (xgmi_v6_4_0_pcs_mca_get_error_type(adev, status)) {
 	case AMDGPU_MCA_ERROR_TYPE_UE:
-		amdgpu_ras_error_statistic_ue_count(err_data, mcm_info, 1ULL);
+		amdgpu_ras_error_statistic_ue_count(err_data, mcm_info, NULL, 1ULL);
 		break;
 	case AMDGPU_MCA_ERROR_TYPE_CE:
-		amdgpu_ras_error_statistic_ce_count(err_data, mcm_info, 1ULL);
+		amdgpu_ras_error_statistic_ce_count(err_data, mcm_info, NULL, 1ULL);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index 2c221000782c..a33e890c70d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -395,7 +395,6 @@ static void atom_skip_src_int(atom_exec_context *ctx, uint8_t attr, int *ptr)
 			(*ptr)++;
 			return;
 		}
-		return;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index bdcf96df69e6..2fbcd9765980 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -4474,11 +4474,43 @@ static int gfx_v11_0_wait_for_idle(void *handle)
 	return -ETIMEDOUT;
 }
 
+static int gfx_v11_0_request_gfx_index_mutex(struct amdgpu_device *adev,
+					     int req)
+{
+	u32 i, tmp, val;
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		/* Request with MeId=2, PipeId=0 */
+		tmp = REG_SET_FIELD(0, CP_GFX_INDEX_MUTEX, REQUEST, req);
+		tmp = REG_SET_FIELD(tmp, CP_GFX_INDEX_MUTEX, CLIENTID, 4);
+		WREG32_SOC15(GC, 0, regCP_GFX_INDEX_MUTEX, tmp);
+
+		val = RREG32_SOC15(GC, 0, regCP_GFX_INDEX_MUTEX);
+		if (req) {
+			if (val == tmp)
+				break;
+		} else {
+			tmp = REG_SET_FIELD(tmp, CP_GFX_INDEX_MUTEX,
+					    REQUEST, 1);
+
+			/* unlocked or locked by firmware */
+			if (val != tmp)
+				break;
+		}
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int gfx_v11_0_soft_reset(void *handle)
 {
 	u32 grbm_soft_reset = 0;
 	u32 tmp;
-	int i, j, k;
+	int r, i, j, k;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	tmp = RREG32_SOC15(GC, 0, regCP_INT_CNTL);
@@ -4518,6 +4550,13 @@ static int gfx_v11_0_soft_reset(void *handle)
 		}
 	}
 
+	/* Try to acquire the gfx mutex before access to CP_VMID_RESET */
+	r = gfx_v11_0_request_gfx_index_mutex(adev, 1);
+	if (r) {
+		DRM_ERROR("Failed to acquire the gfx mutex during soft reset\n");
+		return r;
+	}
+
 	WREG32_SOC15(GC, 0, regCP_VMID_RESET, 0xfffffffe);
 
 	// Read CP_VMID_RESET register three times.
@@ -4526,6 +4565,13 @@ static int gfx_v11_0_soft_reset(void *handle)
 	RREG32_SOC15(GC, 0, regCP_VMID_RESET);
 	RREG32_SOC15(GC, 0, regCP_VMID_RESET);
 
+	/* release the gfx mutex */
+	r = gfx_v11_0_request_gfx_index_mutex(adev, 0);
+	if (r) {
+		DRM_ERROR("Failed to release the gfx mutex during soft reset\n");
+		return r;
+	}
+
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (!RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) &&
 		    !RREG32_SOC15(GC, 0, regCP_GFX_HQD_ACTIVE))
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 00b21ece081f..131cddbdda0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3828,8 +3828,8 @@ static void gfx_v9_4_3_inst_query_ras_err_count(struct amdgpu_device *adev,
 	/* the caller should make sure initialize value of
 	 * err_data->ue_count and err_data->ce_count
 	 */
-	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, ue_count);
-	amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, ce_count);
+	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, NULL, ue_count);
+	amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, NULL, ce_count);
 }
 
 static void gfx_v9_4_3_inst_reset_ras_err_count(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 53a2ba5fcf4b..22175da0e16a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -102,7 +102,9 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+		if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+				       AMD_APU_IS_RENOIR |
+				       AMD_APU_IS_GREEN_SARDINE))
 		       /*
 			* Raven2 has a HW issue that it is unable to use the
 			* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 55423ff1bb49..95d06da544e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -139,7 +139,9 @@ gfxhub_v1_2_xcc_init_system_aperture_regs(struct amdgpu_device *adev,
 			WREG32_SOC15_RLC(GC, GET_INST(GC, i), regMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 				min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-			if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+					       AMD_APU_IS_RENOIR |
+					       AMD_APU_IS_GREEN_SARDINE))
 			       /*
 				* Raven2 has a HW issue that it is unable to use the
 				* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index a5a05c16c10d..6c5185608854 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1041,6 +1041,10 @@ static int gmc_v10_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 23d7b548d13f..c9c653cfc765 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -941,6 +941,11 @@ static int gmc_v11_0_hw_fini(void *handle)
 	}
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
+
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	gmc_v11_0_gart_disable(adev);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 473a774294ce..f9039d64ff2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -2380,6 +2380,10 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 843219a91736..e3ddd22aa172 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -96,7 +96,9 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-	if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+	if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+			       AMD_APU_IS_RENOIR |
+			       AMD_APU_IS_GREEN_SARDINE))
 		/*
 		 * Raven2 has a HW issue that it is unable to use the vram which
 		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
index 9b0146732e13..fb53aacdcba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
@@ -652,8 +652,8 @@ static void mmhub_v1_8_inst_query_ras_error_count(struct amdgpu_device *adev,
 					AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
 					&ue_count);
 
-	amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, ce_count);
-	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, ue_count);
+	amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, NULL, ce_count);
+	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, NULL, ue_count);
 }
 
 static void mmhub_v1_8_query_ras_error_count(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 0f24af6f2810..2d688dca26be 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -2156,7 +2156,7 @@ static void sdma_v4_4_2_inst_query_ras_error_count(struct amdgpu_device *adev,
 					AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
 					&ue_count);
 
-	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, ue_count);
+	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, NULL, ue_count);
 }
 
 static void sdma_v4_4_2_query_ras_error_count(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index e9c2ff74f0bc..7458a218e89d 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "umc/umc_12_0_0_offset.h"
 #include "umc/umc_12_0_0_sh_mask.h"
+#include "mp/mp_13_0_6_sh_mask.h"
 
 const uint32_t
 	umc_v12_0_channel_idx_tbl[]
@@ -88,16 +89,26 @@ static void umc_v12_0_reset_error_count(struct amdgpu_device *adev)
 		umc_v12_0_reset_error_count_per_channel, NULL);
 }
 
-bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status)
+bool umc_v12_0_is_uncorrectable_error(struct amdgpu_device *adev, uint64_t mc_umc_status)
 {
+	if (amdgpu_ras_is_poison_mode_supported(adev) &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1))
+		return true;
+
 	return ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
 		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
 		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
 		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1));
 }
 
-bool umc_v12_0_is_correctable_error(uint64_t mc_umc_status)
+bool umc_v12_0_is_correctable_error(struct amdgpu_device *adev, uint64_t mc_umc_status)
 {
+	if (amdgpu_ras_is_poison_mode_supported(adev) &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1))
+		return false;
+
 	return (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1 ||
 		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 &&
@@ -105,7 +116,7 @@ bool umc_v12_0_is_correctable_error(uint64_t mc_umc_status)
 		/* Identify data parity error in replay mode */
 		((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, ErrorCodeExt) == 0x5 ||
 		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, ErrorCodeExt) == 0xb) &&
-		!(umc_v12_0_is_uncorrectable_error(mc_umc_status)))));
+		!(umc_v12_0_is_uncorrectable_error(adev, mc_umc_status)))));
 }
 
 static void umc_v12_0_query_correctable_error_count(struct amdgpu_device *adev,
@@ -124,7 +135,7 @@ static void umc_v12_0_query_correctable_error_count(struct amdgpu_device *adev,
 	mc_umc_status =
 		RREG64_PCIE_EXT((mc_umc_status_addr + umc_reg_offset) * 4);
 
-	if (umc_v12_0_is_correctable_error(mc_umc_status))
+	if (umc_v12_0_is_correctable_error(adev, mc_umc_status))
 		*error_count += 1;
 }
 
@@ -142,7 +153,7 @@ static void umc_v12_0_query_uncorrectable_error_count(struct amdgpu_device *adev
 	mc_umc_status =
 		RREG64_PCIE_EXT((mc_umc_status_addr + umc_reg_offset) * 4);
 
-	if (umc_v12_0_is_uncorrectable_error(mc_umc_status))
+	if (umc_v12_0_is_uncorrectable_error(adev, mc_umc_status))
 		*error_count += 1;
 }
 
@@ -166,8 +177,8 @@ static int umc_v12_0_query_error_count(struct amdgpu_device *adev,
 	umc_v12_0_query_correctable_error_count(adev, umc_reg_offset, &ce_count);
 	umc_v12_0_query_uncorrectable_error_count(adev, umc_reg_offset, &ue_count);
 
-	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, ue_count);
-	amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, ce_count);
+	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, NULL, ue_count);
+	amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, NULL, ce_count);
 
 	return 0;
 }
@@ -360,6 +371,59 @@ static int umc_v12_0_err_cnt_init_per_channel(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void umc_v12_0_ecc_info_query_ras_error_count(struct amdgpu_device *adev,
+					void *ras_error_status)
+{
+	amdgpu_mca_smu_log_ras_error(adev,
+		AMDGPU_RAS_BLOCK__UMC, AMDGPU_MCA_ERROR_TYPE_CE, ras_error_status);
+	amdgpu_mca_smu_log_ras_error(adev,
+		AMDGPU_RAS_BLOCK__UMC, AMDGPU_MCA_ERROR_TYPE_UE, ras_error_status);
+}
+
+static void umc_v12_0_ecc_info_query_ras_error_address(struct amdgpu_device *adev,
+					void *ras_error_status)
+{
+	struct ras_err_node *err_node;
+	uint64_t mc_umc_status;
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+
+	for_each_ras_error(err_node, err_data) {
+		mc_umc_status = err_node->err_info.err_addr.err_status;
+		if (!mc_umc_status)
+			continue;
+
+		if (umc_v12_0_is_uncorrectable_error(adev, mc_umc_status)) {
+			uint64_t mca_addr, err_addr, mca_ipid;
+			uint32_t InstanceIdLo;
+			struct amdgpu_smuio_mcm_config_info *mcm_info;
+
+			mcm_info = &err_node->err_info.mcm_info;
+			mca_addr = err_node->err_info.err_addr.err_addr;
+			mca_ipid = err_node->err_info.err_addr.err_ipid;
+
+			err_addr =  REG_GET_FIELD(mca_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr);
+			InstanceIdLo = REG_GET_FIELD(mca_ipid, MCMP1_IPIDT0, InstanceIdLo);
+
+			dev_info(adev->dev, "UMC:IPID:0x%llx, aid:%d, inst:%d, ch:%d, err_addr:0x%llx\n",
+				mca_ipid,
+				mcm_info->die_id,
+				MCA_IPID_LO_2_UMC_INST(InstanceIdLo),
+				MCA_IPID_LO_2_UMC_CH(InstanceIdLo),
+				err_addr);
+
+			umc_v12_0_convert_error_address(adev,
+				err_data, err_addr,
+				MCA_IPID_LO_2_UMC_CH(InstanceIdLo),
+				MCA_IPID_LO_2_UMC_INST(InstanceIdLo),
+				mcm_info->die_id);
+
+			/* Clear umc error address content */
+			memset(&err_node->err_info.err_addr,
+				0, sizeof(err_node->err_info.err_addr));
+		}
+	}
+}
+
 static void umc_v12_0_err_cnt_init(struct amdgpu_device *adev)
 {
 	amdgpu_umc_loop_channels(adev,
@@ -386,4 +450,6 @@ struct amdgpu_umc_ras umc_v12_0_ras = {
 	},
 	.err_cnt_init = umc_v12_0_err_cnt_init,
 	.query_ras_poison_mode = umc_v12_0_query_ras_poison_mode,
+	.ecc_info_query_ras_error_count = umc_v12_0_ecc_info_query_ras_error_count,
+	.ecc_info_query_ras_error_address = umc_v12_0_ecc_info_query_ras_error_address,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h
index b34b1e358f8b..e8de3a92251a 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h
@@ -117,8 +117,12 @@
 		(pa) |= (UMC_V12_0_CHANNEL_HASH_CH6(channel_idx, pa) << UMC_V12_0_PA_CH6_BIT); \
 	} while (0)
 
-bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status);
-bool umc_v12_0_is_correctable_error(uint64_t mc_umc_status);
+#define MCA_IPID_LO_2_UMC_CH(_ipid_lo) (((((_ipid_lo) >> 20) & 0x1) * 4) + \
+			(((_ipid_lo) >> 12) & 0xF))
+#define MCA_IPID_LO_2_UMC_INST(_ipid_lo) (((_ipid_lo) >> 21) & 0x7)
+
+bool umc_v12_0_is_uncorrectable_error(struct amdgpu_device *adev, uint64_t mc_umc_status);
+bool umc_v12_0_is_correctable_error(struct amdgpu_device *adev, uint64_t mc_umc_status);
 
 extern const uint32_t
 	umc_v12_0_channel_idx_tbl[]