Merge tag 'amd-drm-next-6.3-2023-01-20' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.3-2023-01-20:

amdgpu:
- Secure display fixes
- Fix scaling
- Misc code cleanups
- Display BW alloc logic updates
- DCN 3.2 fixes
- Fix power reporting on certain firmwares for CZN/RN
- SR-IOV fixes
- Link training cleanup and code rework
- HDCP fixes
- Reserved VMID fix
- Documentation updates
- Colorspace fixes
- RAS updates
- GC11.0 fixes
- VCN instance harvesting fixes
- DCN 3.1.4/5 workarounds for S/G displays
- Add PCIe info to the INFO IOCTL

amdkfd:
- XNACK fix

UAPI:
- Add PCIe gen/lanes info to the amdgpu INFO IOCTL
  Nesa ultimately plans to use this to make decisions about buffer placement optimizations
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20790

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230120234523.7610-1-alexander.deucher@amd.com

30 files changed, 715 insertions, 266 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 332cf8bda7a2..5df603192cdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -137,6 +137,7 @@ amdgpu-y += \
 	gfx_v10_0.o \
 	imu_v11_0.o \
 	gfx_v11_0.o \
+	gfx_v11_0_3.o \
 	imu_v11_0_3.o
 
 # add async DMA block
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 76a2b4a4de10..1257745fb202 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2076,6 +2076,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct pci_dev *parent;
 	int i, r;
+	bool total;
 
 	amdgpu_device_enable_virtual_display(adev);
 
@@ -2159,6 +2160,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)
 		adev->pm.pp_feature &= ~PP_OVERDRIVE_MASK;
 
+	total = true;
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if ((amdgpu_ip_block_mask & (1 << i)) == 0) {
 			DRM_ERROR("disabled ip block: %d <%s>\n",
@@ -2172,7 +2174,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 				} else if (r) {
 					DRM_ERROR("early_init of IP block <%s> failed %d\n",
 						  adev->ip_blocks[i].version->funcs->name, r);
-					return r;
+					total = false;
 				} else {
 					adev->ip_blocks[i].status.valid = true;
 				}
@@ -2203,6 +2205,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 
 		}
 	}
+	if (!total)
+		return -ENODEV;
 
 	adev->cg_flags &= amdgpu_cg_mask;
 	adev->pg_flags &= amdgpu_pg_mask;
@@ -5854,8 +5858,8 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
 int amdgpu_in_reset(struct amdgpu_device *adev)
 {
 	return atomic_read(&adev->reset_domain->in_gpu_reset);
-	}
-	
+}
+
 /**
  * amdgpu_device_halt() - bring hardware to some kind of halt state
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index e3fed38a0d90..7bb12a76631f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -106,9 +106,10 @@
  * - 3.49.0 - Add gang submit into CS IOCTL
  * - 3.50.0 - Update AMDGPU_INFO_DEV_INFO IOCTL for minimum engine and memory clock
  *            Update AMDGPU_INFO_SENSOR IOCTL for PEAK_PSTATE engine and memory clock
+ *   3.51.0 - Return the PCIe gen and lanes from the INFO ioctl
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	50
+#define KMS_DRIVER_MINOR	51
 #define KMS_DRIVER_PATCHLEVEL	0
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 42a939cd2eac..35ed46b9249c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -156,6 +156,9 @@ static bool amdgpu_gfx_is_compute_multipipe_capable(struct amdgpu_device *adev)
 		return amdgpu_compute_multipipe == 1;
 	}
 
+	if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))
+		return true;
+
 	/* FIXME: spreading the queues across pipes causes perf regressions
 	 * on POLARIS11 compute workloads */
 	if (adev->asic_type == CHIP_POLARIS11)
@@ -696,6 +699,50 @@ late_fini:
 	return r;
 }
 
+int amdgpu_gfx_ras_sw_init(struct amdgpu_device *adev)
+{
+	int err = 0;
+	struct amdgpu_gfx_ras *ras = NULL;
+
+	/* adev->gfx.ras is NULL, which means gfx does not
+	 * support ras function, then do nothing here.
+	 */
+	if (!adev->gfx.ras)
+		return 0;
+
+	ras = adev->gfx.ras;
+
+	err = amdgpu_ras_register_ras_block(adev, &ras->ras_block);
+	if (err) {
+		dev_err(adev->dev, "Failed to register gfx ras block!\n");
+		return err;
+	}
+
+	strcpy(ras->ras_block.ras_comm.name, "gfx");
+	ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__GFX;
+	ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+	adev->gfx.ras_if = &ras->ras_block.ras_comm;
+
+	/* If not define special ras_late_init function, use gfx default ras_late_init */
+	if (!ras->ras_block.ras_late_init)
+		ras->ras_block.ras_late_init = amdgpu_ras_block_late_init;
+
+	/* If not defined special ras_cb function, use default ras_cb */
+	if (!ras->ras_block.ras_cb)
+		ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb;
+
+	return 0;
+}
+
+int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev,
+						struct amdgpu_iv_entry *entry)
+{
+	if (adev->gfx.ras && adev->gfx.ras->poison_consumption_handler)
+		return adev->gfx.ras->poison_consumption_handler(adev, entry);
+
+	return 0;
+}
+
 int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
 		void *err_data,
 		struct amdgpu_iv_entry *entry)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index b3df4787877e..86ec9d0d12c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -210,6 +210,11 @@ struct amdgpu_gfx_ras {
 	struct amdgpu_ras_block_object  ras_block;
 	void (*enable_watchdog_timer)(struct amdgpu_device *adev);
 	bool (*query_utcl2_poison_status)(struct amdgpu_device *adev);
+	int (*rlc_gc_fed_irq)(struct amdgpu_device *adev,
+				struct amdgpu_irq_src *source,
+				struct amdgpu_iv_entry *entry);
+	int (*poison_consumption_handler)(struct amdgpu_device *adev,
+						struct amdgpu_iv_entry *entry);
 };
 
 struct amdgpu_gfx_funcs {
@@ -323,6 +328,7 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_inst_irq;
 	struct amdgpu_irq_src		cp_ecc_error_irq;
 	struct amdgpu_irq_src		sq_irq;
+	struct amdgpu_irq_src		rlc_gc_fed_irq;
 	struct sq_work			sq_work;
 
 	/* gfx status */
@@ -432,4 +438,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);
 int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev);
 void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, uint32_t ucode_id);
 
+int amdgpu_gfx_ras_sw_init(struct amdgpu_device *adev);
+int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev,
+						struct amdgpu_iv_entry *entry);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index fcb711a11a5b..3f07b1a2ce47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -497,6 +497,7 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
 	    !--id_mgr->reserved_use_count) {
 		/* give the reserved ID back to normal round robin */
 		list_add(&id_mgr->reserved->list, &id_mgr->ids_lru);
+		id_mgr->reserved = NULL;
 	}
 	vm->reserved_vmid[vmhub] = false;
 	mutex_unlock(&id_mgr->lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9e549923622b..c3d9d75143f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -161,8 +161,14 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	struct dma_fence *f;
 	unsigned i;
 
-	/* use sched fence if available */
-	f = job->base.s_fence ? &job->base.s_fence->finished :  &job->hw_fence;
+	/* Check if any fences where initialized */
+	if (job->base.s_fence && job->base.s_fence->finished.ops)
+		f = &job->base.s_fence->finished;
+	else if (job->hw_fence.ops)
+		f = &job->hw_fence;
+	else
+		f = NULL;
+
 	for (i = 0; i < job->num_ibs; ++i)
 		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 2947159d7d78..ca945055e683 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -43,6 +43,7 @@
 #include "amdgpu_gem.h"
 #include "amdgpu_display.h"
 #include "amdgpu_ras.h"
+#include "amd_pcie.h"
 
 void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev)
 {
@@ -767,6 +768,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	case AMDGPU_INFO_DEV_INFO: {
 		struct drm_amdgpu_info_device *dev_info;
 		uint64_t vm_size;
+		uint32_t pcie_gen_mask;
 		int ret;
 
 		dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL);
@@ -799,7 +801,6 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		dev_info->num_rb_pipes = adev->gfx.config.max_backends_per_se *
 			adev->gfx.config.max_shader_engines;
 		dev_info->num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts;
-		dev_info->_pad = 0;
 		dev_info->ids_flags = 0;
 		if (adev->flags & AMD_IS_APU)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
@@ -853,6 +854,17 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 		dev_info->tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask;
 
+		/* Combine the chip gen mask with the platform (CPU/mobo) mask. */
+		pcie_gen_mask = adev->pm.pcie_gen_mask & (adev->pm.pcie_gen_mask >> 16);
+		dev_info->pcie_gen = fls(pcie_gen_mask);
+		dev_info->pcie_num_lanes =
+			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 ? 32 :
+			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 ? 16 :
+			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 ? 12 :
+			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 ? 8 :
+			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 :
+			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1;
+
 		ret = copy_to_user(out, dev_info,
 				   min((size_t)size, sizeof(*dev_info))) ? -EFAULT : 0;
 		kfree(dev_info);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 25a68d8888e0..981010de0a28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1574,9 +1574,9 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m)
 	attachment = READ_ONCE(bo->tbo.base.import_attach);
 
 	if (attachment)
-		seq_printf(m, " imported from %p", dma_buf);
+		seq_printf(m, " imported from ino:%lu", file_inode(dma_buf->file)->i_ino);
 	else if (dma_buf)
-		seq_printf(m, " exported as %p", dma_buf);
+		seq_printf(m, " exported as ino:%lu", file_inode(dma_buf->file)->i_ino);
 
 	amdgpu_bo_print_flag(m, bo, CPU_ACCESS_REQUIRED);
 	amdgpu_bo_print_flag(m, bo, NO_CPU_ACCESS);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 0b59465b1494..a8391f269cd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -336,7 +336,7 @@ static bool psp_get_runtime_db_entry(struct amdgpu_device *adev,
 
 	if (db_header.cookie != PSP_RUNTIME_DB_COOKIE_ID) {
 		/* runtime db doesn't exist, exit */
-		dev_warn(adev->dev, "PSP runtime database doesn't exist\n");
+		dev_dbg(adev->dev, "PSP runtime database doesn't exist\n");
 		return false;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index d06beb884a16..6e543558386d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -920,9 +920,6 @@ static struct amdgpu_ras_block_object *amdgpu_ras_get_ras_block(struct amdgpu_de
 	if (block >= AMDGPU_RAS_BLOCK__LAST)
 		return NULL;
 
-	if (!amdgpu_ras_is_supported(adev, block))
-		return NULL;
-
 	list_for_each_entry_safe(node, tmp, &adev->ras_list, node) {
 		if (!node->ras_obj) {
 			dev_warn(adev->dev, "Warning: abnormal ras list node.\n");
@@ -1620,14 +1617,14 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager *
 	struct amdgpu_ras_block_object *block_obj =
 		amdgpu_ras_get_ras_block(adev, obj->head.block, 0);
 
-	if (!block_obj || !block_obj->hw_ops)
+	if (!block_obj)
 		return;
 
 	/* both query_poison_status and handle_poison_consumption are optional,
 	 * but at least one of them should be implemented if we need poison
 	 * consumption handler
 	 */
-	if (block_obj->hw_ops->query_poison_status) {
+	if (block_obj->hw_ops && block_obj->hw_ops->query_poison_status) {
 		poison_stat = block_obj->hw_ops->query_poison_status(adev);
 		if (!poison_stat) {
 			/* Not poison consumption interrupt, no need to handle it */
@@ -1641,7 +1638,7 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager *
 	if (!adev->gmc.xgmi.connected_to_cpu)
 		amdgpu_umc_poison_handler(adev, false);
 
-	if (block_obj->hw_ops->handle_poison_consumption)
+	if (block_obj->hw_ops && block_obj->hw_ops->handle_poison_consumption)
 		poison_stat = block_obj->hw_ops->handle_poison_consumption(adev);
 
 	/* gpu reset is fallback for failed and default cases */
@@ -1649,6 +1646,8 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager *
 		dev_info(adev->dev, "GPU reset for %s RAS poison consumption is issued!\n",
 				block_obj->ras_comm.name);
 		amdgpu_ras_reset_gpu(adev);
+	} else {
+		amdgpu_gfx_poison_consumption_handler(adev, entry);
 	}
 }
 
@@ -3023,11 +3022,26 @@ int amdgpu_ras_set_context(struct amdgpu_device *adev, struct amdgpu_ras *ras_co
 int amdgpu_ras_is_supported(struct amdgpu_device *adev,
 		unsigned int block)
 {
+	int ret = 0;
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	if (block >= AMDGPU_RAS_BLOCK_COUNT)
 		return 0;
-	return ras && (adev->ras_enabled & (1 << block));
+
+	ret = ras && (adev->ras_enabled & (1 << block));
+
+	/* For the special asic with mem ecc enabled but sram ecc
+	 * not enabled, even if the ras block is not supported on
+	 * .ras_enabled, if the asic supports poison mode and the
+	 * ras block has ras configuration, it can be considered
+	 * that the ras block supports ras function.
+	 */
+	if (!ret &&
+	    amdgpu_ras_is_poison_mode_supported(adev) &&
+	    amdgpu_ras_get_ras_block(adev, block, 0))
+		ret = 1;
+
+	return ret;
 }
 
 int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index e9b78739b9ff..231ca06bc9c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -305,3 +305,38 @@ void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev)
 		}
 	}
 }
+
+int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev)
+{
+	int err = 0;
+	struct amdgpu_sdma_ras *ras = NULL;
+
+	/* adev->sdma.ras is NULL, which means sdma does not
+	 * support ras function, then do nothing here.
+	 */
+	if (!adev->sdma.ras)
+		return 0;
+
+	ras = adev->sdma.ras;
+
+	err = amdgpu_ras_register_ras_block(adev, &ras->ras_block);
+	if (err) {
+		dev_err(adev->dev, "Failed to register sdma ras block!\n");
+		return err;
+	}
+
+	strcpy(ras->ras_block.ras_comm.name, "sdma");
+	ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__SDMA;
+	ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+	adev->sdma.ras_if = &ras->ras_block.ras_comm;
+
+	/* If not define special ras_late_init function, use default ras_late_init */
+	if (!ras->ras_block.ras_late_init)
+		ras->ras_block.ras_late_init = amdgpu_sdma_ras_late_init;
+
+	/* If not defined special ras_cb function, use default ras_cb */
+	if (!ras->ras_block.ras_cb)
+		ras->ras_block.ras_cb = amdgpu_sdma_process_ras_data_cb;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index 2d16e6d36728..fc8528812598 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -129,5 +129,6 @@ int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, u32 instance,
 void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev,
         bool duplicate);
 void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev);
+int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 677ad2016976..98d91ebf5c26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -153,10 +153,10 @@ TRACE_EVENT(amdgpu_cs,
 
 	    TP_fast_assign(
 			   __entry->bo_list = p->bo_list;
-			   __entry->ring = to_amdgpu_ring(job->base.sched)->idx;
+			   __entry->ring = to_amdgpu_ring(job->base.entity->rq->sched)->idx;
 			   __entry->dw = ib->length_dw;
 			   __entry->fences = amdgpu_fence_count_emitted(
-				to_amdgpu_ring(job->base.sched));
+				to_amdgpu_ring(job->base.entity->rq->sched));
 			   ),
 	    TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
 		      __entry->bo_list, __entry->ring, __entry->dw,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 47549d659d9b..380b89114341 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -1072,7 +1072,6 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
 			default:
 				return NULL;
 			}
-			break;
 		case IP_VERSION(10, 0, 0):
 		case IP_VERSION(10, 0, 1):
 			if (adev->asic_type == CHIP_RAVEN) {
@@ -1087,6 +1086,8 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
 			return "navi10";
 		case IP_VERSION(11, 0, 2):
 			return "vega20";
+		case IP_VERSION(11, 0, 3):
+			return "renoir";
 		case IP_VERSION(11, 0, 4):
 			return "arcturus";
 		case IP_VERSION(11, 0, 5):
@@ -1104,12 +1105,7 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
 		case IP_VERSION(11, 5, 0):
 			return "vangogh";
 		case IP_VERSION(12, 0, 1):
-			if (adev->asic_type == CHIP_RENOIR) {
-				if (adev->apu_flags & AMD_APU_IS_RENOIR)
-					return "renoir";
-				return "green_sardine";
-			}
-			break;
+			return "green_sardine";
 		case IP_VERSION(13, 0, 2):
 			return "aldebaran";
 		case IP_VERSION(13, 0, 1):
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index a7eae84c7bf7..25217b05c0ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -36,26 +36,26 @@
 #include "soc15d.h"
 
 /* Firmware Names */
-#define FIRMWARE_RAVEN		"amdgpu/raven_vcn.bin"
-#define FIRMWARE_PICASSO	"amdgpu/picasso_vcn.bin"
-#define FIRMWARE_RAVEN2		"amdgpu/raven2_vcn.bin"
-#define FIRMWARE_ARCTURUS	"amdgpu/arcturus_vcn.bin"
-#define FIRMWARE_RENOIR		"amdgpu/renoir_vcn.bin"
-#define FIRMWARE_GREEN_SARDINE	"amdgpu/green_sardine_vcn.bin"
-#define FIRMWARE_NAVI10		"amdgpu/navi10_vcn.bin"
-#define FIRMWARE_NAVI14		"amdgpu/navi14_vcn.bin"
-#define FIRMWARE_NAVI12		"amdgpu/navi12_vcn.bin"
-#define FIRMWARE_SIENNA_CICHLID	"amdgpu/sienna_cichlid_vcn.bin"
-#define FIRMWARE_NAVY_FLOUNDER	"amdgpu/navy_flounder_vcn.bin"
-#define FIRMWARE_VANGOGH	"amdgpu/vangogh_vcn.bin"
+#define FIRMWARE_RAVEN			"amdgpu/raven_vcn.bin"
+#define FIRMWARE_PICASSO		"amdgpu/picasso_vcn.bin"
+#define FIRMWARE_RAVEN2			"amdgpu/raven2_vcn.bin"
+#define FIRMWARE_ARCTURUS		"amdgpu/arcturus_vcn.bin"
+#define FIRMWARE_RENOIR			"amdgpu/renoir_vcn.bin"
+#define FIRMWARE_GREEN_SARDINE		"amdgpu/green_sardine_vcn.bin"
+#define FIRMWARE_NAVI10			"amdgpu/navi10_vcn.bin"
+#define FIRMWARE_NAVI14			"amdgpu/navi14_vcn.bin"
+#define FIRMWARE_NAVI12			"amdgpu/navi12_vcn.bin"
+#define FIRMWARE_SIENNA_CICHLID		"amdgpu/sienna_cichlid_vcn.bin"
+#define FIRMWARE_NAVY_FLOUNDER		"amdgpu/navy_flounder_vcn.bin"
+#define FIRMWARE_VANGOGH		"amdgpu/vangogh_vcn.bin"
 #define FIRMWARE_DIMGREY_CAVEFISH	"amdgpu/dimgrey_cavefish_vcn.bin"
-#define FIRMWARE_ALDEBARAN	"amdgpu/aldebaran_vcn.bin"
-#define FIRMWARE_BEIGE_GOBY	"amdgpu/beige_goby_vcn.bin"
-#define FIRMWARE_YELLOW_CARP	"amdgpu/yellow_carp_vcn.bin"
-#define FIRMWARE_VCN_3_1_2	"amdgpu/vcn_3_1_2.bin"
-#define FIRMWARE_VCN4_0_0	"amdgpu/vcn_4_0_0.bin"
-#define FIRMWARE_VCN4_0_2	"amdgpu/vcn_4_0_2.bin"
-#define FIRMWARE_VCN4_0_4      "amdgpu/vcn_4_0_4.bin"
+#define FIRMWARE_ALDEBARAN		"amdgpu/aldebaran_vcn.bin"
+#define FIRMWARE_BEIGE_GOBY		"amdgpu/beige_goby_vcn.bin"
+#define FIRMWARE_YELLOW_CARP		"amdgpu/yellow_carp_vcn.bin"
+#define FIRMWARE_VCN_3_1_2		"amdgpu/vcn_3_1_2.bin"
+#define FIRMWARE_VCN4_0_0		"amdgpu/vcn_4_0_0.bin"
+#define FIRMWARE_VCN4_0_2		"amdgpu/vcn_4_0_2.bin"
+#define FIRMWARE_VCN4_0_4		"amdgpu/vcn_4_0_4.bin"
 
 MODULE_FIRMWARE(FIRMWARE_RAVEN);
 MODULE_FIRMWARE(FIRMWARE_PICASSO);
@@ -110,84 +110,9 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++)
 		atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
 
-	switch (adev->ip_versions[UVD_HWIP][0]) {
-	case IP_VERSION(1, 0, 0):
-	case IP_VERSION(1, 0, 1):
-	case IP_VERSION(2, 5, 0):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(2, 2, 0):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(2, 6, 0):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(2, 0, 0):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(2, 0, 2):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(3, 0, 0):
-	case IP_VERSION(3, 0, 64):
-	case IP_VERSION(3, 0, 192):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(3, 0, 2):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(3, 0, 16):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(3, 0, 33):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(3, 1, 1):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(3, 1, 2):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(4, 0, 0):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-			(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(4, 0, 2):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-			(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	case IP_VERSION(4, 0, 4):
-		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
-			(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = true;
-		break;
-	default:
-		return -EINVAL;
-	}
+	if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
+	    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
+		adev->vcn.indirect_sram = true;
 
 	hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 4b9e7b050ccd..4340d08f7607 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -29,13 +29,16 @@
 #include "df/df_3_6_offset.h"
 #include "xgmi/xgmi_4_0_0_smn.h"
 #include "xgmi/xgmi_4_0_0_sh_mask.h"
+#include "xgmi/xgmi_6_1_0_sh_mask.h"
 #include "wafl/wafl2_4_0_0_smn.h"
 #include "wafl/wafl2_4_0_0_sh_mask.h"
 
 #include "amdgpu_reset.h"
 
 #define smnPCS_XGMI3X16_PCS_ERROR_STATUS 0x11a0020c
+#define smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK   0x11a00218
 #define smnPCS_GOPX1_PCS_ERROR_STATUS    0x12200210
+#define smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK      0x12200218
 
 static DEFINE_MUTEX(xgmi_mutex);
 
@@ -79,11 +82,27 @@ static const int xgmi3x16_pcs_err_status_reg_aldebaran[] = {
 	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x700000
 };
 
+static const int xgmi3x16_pcs_err_noncorrectable_mask_reg_aldebaran[] = {
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x100000,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x200000,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x300000,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x400000,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x500000,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x600000,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x700000
+};
+
 static const int walf_pcs_err_status_reg_aldebaran[] = {
 	smnPCS_GOPX1_PCS_ERROR_STATUS,
 	smnPCS_GOPX1_PCS_ERROR_STATUS + 0x100000
 };
 
+static const int walf_pcs_err_noncorrectable_mask_reg_aldebaran[] = {
+	smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK,
+	smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK + 0x100000
+};
+
 static const struct amdgpu_pcs_ras_field xgmi_pcs_ras_fields[] = {
 	{"XGMI PCS DataLossErr",
 	 SOC15_REG_FIELD(XGMI0_PCS_GOPX16_PCS_ERROR_STATUS, DataLossErr)},
@@ -162,6 +181,67 @@ static const struct amdgpu_pcs_ras_field wafl_pcs_ras_fields[] = {
 	 SOC15_REG_FIELD(PCS_GOPX1_0_PCS_GOPX1_PCS_ERROR_STATUS, RecoveryRelockAttemptErr)},
 };
 
+static const struct amdgpu_pcs_ras_field xgmi3x16_pcs_ras_fields[] = {
+	{"XGMI3X16 PCS DataLossErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DataLossErr)},
+	{"XGMI3X16 PCS TrainingErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, TrainingErr)},
+	{"XGMI3X16 PCS FlowCtrlAckErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, FlowCtrlAckErr)},
+	{"XGMI3X16 PCS RxFifoUnderflowErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxFifoUnderflowErr)},
+	{"XGMI3X16 PCS RxFifoOverflowErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxFifoOverflowErr)},
+	{"XGMI3X16 PCS CRCErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, CRCErr)},
+	{"XGMI3X16 PCS BERExceededErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, BERExceededErr)},
+	{"XGMI3X16 PCS TxVcidDataErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, TxVcidDataErr)},
+	{"XGMI3X16 PCS ReplayBufParityErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayBufParityErr)},
+	{"XGMI3X16 PCS DataParityErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DataParityErr)},
+	{"XGMI3X16 PCS ReplayFifoOverflowErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayFifoOverflowErr)},
+	{"XGMI3X16 PCS ReplayFifoUnderflowErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayFifoUnderflowErr)},
+	{"XGMI3X16 PCS ElasticFifoOverflowErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ElasticFifoOverflowErr)},
+	{"XGMI3X16 PCS DeskewErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DeskewErr)},
+	{"XGMI3X16 PCS FlowCtrlCRCErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, FlowCtrlCRCErr)},
+	{"XGMI3X16 PCS DataStartupLimitErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DataStartupLimitErr)},
+	{"XGMI3X16 PCS FCInitTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, FCInitTimeoutErr)},
+	{"XGMI3X16 PCS RecoveryTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RecoveryTimeoutErr)},
+	{"XGMI3X16 PCS ReadySerialTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReadySerialTimeoutErr)},
+	{"XGMI3X16 PCS ReadySerialAttemptErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReadySerialAttemptErr)},
+	{"XGMI3X16 PCS RecoveryAttemptErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RecoveryAttemptErr)},
+	{"XGMI3X16 PCS RecoveryRelockAttemptErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RecoveryRelockAttemptErr)},
+	{"XGMI3X16 PCS ReplayAttemptErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayAttemptErr)},
+	{"XGMI3X16 PCS SyncHdrErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, SyncHdrErr)},
+	{"XGMI3X16 PCS TxReplayTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, TxReplayTimeoutErr)},
+	{"XGMI3X16 PCS RxReplayTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxReplayTimeoutErr)},
+	{"XGMI3X16 PCS LinkSubTxTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, LinkSubTxTimeoutErr)},
+	{"XGMI3X16 PCS LinkSubRxTimeoutErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, LinkSubRxTimeoutErr)},
+	{"XGMI3X16 PCS RxCMDPktErr",
+	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxCMDPktErr)},
+};
+
 /**
  * DOC: AMDGPU XGMI Support
  *
@@ -809,39 +889,47 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
 
 static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
 					      uint32_t value,
+						  uint32_t mask_value,
 					      uint32_t *ue_count,
 					      uint32_t *ce_count,
-					      bool is_xgmi_pcs)
+					      bool is_xgmi_pcs,
+						  bool check_mask)
 {
 	int i;
-	int ue_cnt;
+	int ue_cnt = 0;
+	const struct amdgpu_pcs_ras_field *pcs_ras_fields = NULL;
+	uint32_t field_array_size = 0;
 
 	if (is_xgmi_pcs) {
-		/* query xgmi pcs error status,
-		 * only ue is supported */
-		for (i = 0; i < ARRAY_SIZE(xgmi_pcs_ras_fields); i ++) {
-			ue_cnt = (value &
-				  xgmi_pcs_ras_fields[i].pcs_err_mask) >>
-				  xgmi_pcs_ras_fields[i].pcs_err_shift;
-			if (ue_cnt) {
-				dev_info(adev->dev, "%s detected\n",
-					 xgmi_pcs_ras_fields[i].err_name);
-				*ue_count += ue_cnt;
-			}
+		if (adev->ip_versions[XGMI_HWIP][0] == IP_VERSION(6, 1, 0)) {
+			pcs_ras_fields = &xgmi3x16_pcs_ras_fields[0];
+			field_array_size = ARRAY_SIZE(xgmi3x16_pcs_ras_fields);
+		} else {
+			pcs_ras_fields = &xgmi_pcs_ras_fields[0];
+			field_array_size = ARRAY_SIZE(xgmi_pcs_ras_fields);
 		}
 	} else {
-		/* query wafl pcs error status,
-		 * only ue is supported */
-		for (i = 0; i < ARRAY_SIZE(wafl_pcs_ras_fields); i++) {
-			ue_cnt = (value &
-				  wafl_pcs_ras_fields[i].pcs_err_mask) >>
-				  wafl_pcs_ras_fields[i].pcs_err_shift;
-			if (ue_cnt) {
-				dev_info(adev->dev, "%s detected\n",
-					 wafl_pcs_ras_fields[i].err_name);
-				*ue_count += ue_cnt;
-			}
+		pcs_ras_fields = &wafl_pcs_ras_fields[0];
+		field_array_size = ARRAY_SIZE(wafl_pcs_ras_fields);
+	}
+
+	if (check_mask)
+		value = value & ~mask_value;
+
+	/* query xgmi/walf pcs error status,
+	 * only ue is supported */
+	for (i = 0; value && i < field_array_size; i++) {
+		ue_cnt = (value &
+				pcs_ras_fields[i].pcs_err_mask) >>
+				pcs_ras_fields[i].pcs_err_shift;
+		if (ue_cnt) {
+			dev_info(adev->dev, "%s detected\n",
+				 pcs_ras_fields[i].err_name);
+			*ue_count += ue_cnt;
 		}
+
+		/* reset bit value if the bit is checked */
+		value &= ~(pcs_ras_fields[i].pcs_err_mask);
 	}
 
 	return 0;
@@ -852,7 +940,7 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 	int i;
-	uint32_t data;
+	uint32_t data, mask_data = 0;
 	uint32_t ue_cnt = 0, ce_cnt = 0;
 
 	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL))
@@ -867,15 +955,15 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 		for (i = 0; i < ARRAY_SIZE(xgmi_pcs_err_status_reg_arct); i++) {
 			data = RREG32_PCIE(xgmi_pcs_err_status_reg_arct[i]);
 			if (data)
-				amdgpu_xgmi_query_pcs_error_status(adev,
-						data, &ue_cnt, &ce_cnt, true);
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, true, false);
 		}
 		/* check wafl pcs error */
 		for (i = 0; i < ARRAY_SIZE(wafl_pcs_err_status_reg_arct); i++) {
 			data = RREG32_PCIE(wafl_pcs_err_status_reg_arct[i]);
 			if (data)
-				amdgpu_xgmi_query_pcs_error_status(adev,
-						data, &ue_cnt, &ce_cnt, false);
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, false, false);
 		}
 		break;
 	case CHIP_VEGA20:
@@ -883,31 +971,35 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 		for (i = 0; i < ARRAY_SIZE(xgmi_pcs_err_status_reg_vg20); i++) {
 			data = RREG32_PCIE(xgmi_pcs_err_status_reg_vg20[i]);
 			if (data)
-				amdgpu_xgmi_query_pcs_error_status(adev,
-						data, &ue_cnt, &ce_cnt, true);
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, true, false);
 		}
 		/* check wafl pcs error */
 		for (i = 0; i < ARRAY_SIZE(wafl_pcs_err_status_reg_vg20); i++) {
 			data = RREG32_PCIE(wafl_pcs_err_status_reg_vg20[i]);
 			if (data)
-				amdgpu_xgmi_query_pcs_error_status(adev,
-						data, &ue_cnt, &ce_cnt, false);
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, false, false);
 		}
 		break;
 	case CHIP_ALDEBARAN:
 		/* check xgmi3x16 pcs error */
 		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++) {
 			data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_aldebaran[i]);
+			mask_data =
+				RREG32_PCIE(xgmi3x16_pcs_err_noncorrectable_mask_reg_aldebaran[i]);
 			if (data)
-				amdgpu_xgmi_query_pcs_error_status(adev,
-						data, &ue_cnt, &ce_cnt, true);
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, true, true);
 		}
 		/* check wafl pcs error */
 		for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++) {
 			data = RREG32_PCIE(walf_pcs_err_status_reg_aldebaran[i]);
+			mask_data =
+				RREG32_PCIE(walf_pcs_err_noncorrectable_mask_reg_aldebaran[i]);
 			if (data)
-				amdgpu_xgmi_query_pcs_error_status(adev,
-						data, &ue_cnt, &ce_cnt, false);
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, false, true);
 		}
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 985fe704203e..c621b2ad7ba3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -46,6 +46,7 @@
 #include "clearstate_gfx11.h"
 #include "v11_structs.h"
 #include "gfx_v11_0.h"
+#include "gfx_v11_0_3.h"
 #include "nbio_v4_3.h"
 #include "mes_v11_0.h"
 
@@ -815,7 +816,14 @@ static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev)
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 2):
+		adev->gfx.config.max_hw_contexts = 8;
+		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
+		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
+		adev->gfx.config.sc_hiz_tile_fifo_size = 0;
+		adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0;
+		break;
 	case IP_VERSION(11, 0, 3):
+		adev->gfx.ras = &gfx_v11_0_3_ras;
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -1251,10 +1259,8 @@ static int gfx_v11_0_sw_init(void *handle)
 
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
-	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
-	case IP_VERSION(11, 0, 4):
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
@@ -1262,6 +1268,15 @@ static int gfx_v11_0_sw_init(void *handle)
 		adev->gfx.mec.num_pipe_per_mec = 4;
 		adev->gfx.mec.num_queue_per_pipe = 4;
 		break;
+	case IP_VERSION(11, 0, 1):
+	case IP_VERSION(11, 0, 4):
+		adev->gfx.me.num_me = 1;
+		adev->gfx.me.num_pipe_per_me = 1;
+		adev->gfx.me.num_queue_per_pipe = 1;
+		adev->gfx.mec.num_mec = 1;
+		adev->gfx.mec.num_pipe_per_mec = 4;
+		adev->gfx.mec.num_queue_per_pipe = 4;
+		break;
 	default:
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
@@ -1293,6 +1308,20 @@ static int gfx_v11_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	/* ECC error */
+	r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP,
+				  GFX_11_0_0__SRCID__CP_ECC_ERROR,
+				  &adev->gfx.cp_ecc_error_irq);
+	if (r)
+		return r;
+
+	/* FED error */
+	r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GFX,
+				  GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT,
+				  &adev->gfx.rlc_gc_fed_irq);
+	if (r)
+		return r;
+
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
 	if (adev->gfx.imu.funcs) {
@@ -1380,6 +1409,11 @@ static int gfx_v11_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	if (amdgpu_gfx_ras_sw_init(adev)) {
+		dev_err(adev->dev, "Failed to initialize gfx ras block!\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -4372,6 +4406,7 @@ static int gfx_v11_0_hw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
+	amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
@@ -5803,6 +5838,36 @@ static void gfx_v11_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev
 	}
 }
 
+#define CP_ME1_PIPE_INST_ADDR_INTERVAL  0x1
+#define SET_ECC_ME_PIPE_STATE(reg_addr, state) \
+	do { \
+		uint32_t tmp = RREG32_SOC15_IP(GC, reg_addr); \
+		tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, state); \
+		WREG32_SOC15_IP(GC, reg_addr, tmp); \
+	} while (0)
+
+static int gfx_v11_0_set_cp_ecc_error_state(struct amdgpu_device *adev,
+							struct amdgpu_irq_src *source,
+							unsigned type,
+							enum amdgpu_interrupt_state state)
+{
+	uint32_t ecc_irq_state = 0;
+	uint32_t pipe0_int_cntl_addr = 0;
+	int i = 0;
+
+	ecc_irq_state = (state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0;
+
+	pipe0_int_cntl_addr = SOC15_REG_OFFSET(GC, 0, regCP_ME1_PIPE0_INT_CNTL);
+
+	WREG32_FIELD15_PREREG(GC, 0, CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, ecc_irq_state);
+
+	for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; i++)
+		SET_ECC_ME_PIPE_STATE(pipe0_int_cntl_addr + i * CP_ME1_PIPE_INST_ADDR_INTERVAL,
+					ecc_irq_state);
+
+	return 0;
+}
+
 static int gfx_v11_0_set_eop_interrupt_state(struct amdgpu_device *adev,
 					    struct amdgpu_irq_src *src,
 					    unsigned type,
@@ -5979,6 +6044,16 @@ static int gfx_v11_0_priv_inst_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v11_0_rlc_gc_fed_irq(struct amdgpu_device *adev,
+				  struct amdgpu_irq_src *source,
+				  struct amdgpu_iv_entry *entry)
+{
+	if (adev->gfx.ras && adev->gfx.ras->rlc_gc_fed_irq)
+		return adev->gfx.ras->rlc_gc_fed_irq(adev, source, entry);
+
+	return 0;
+}
+
 #if 0
 static int gfx_v11_0_kiq_set_interrupt_state(struct amdgpu_device *adev,
 					     struct amdgpu_irq_src *src,
@@ -6209,6 +6284,15 @@ static const struct amdgpu_irq_src_funcs gfx_v11_0_priv_inst_irq_funcs = {
 	.process = gfx_v11_0_priv_inst_irq,
 };
 
+static const struct amdgpu_irq_src_funcs gfx_v11_0_cp_ecc_error_irq_funcs = {
+	.set = gfx_v11_0_set_cp_ecc_error_state,
+	.process = amdgpu_gfx_cp_ecc_error_irq,
+};
+
+static const struct amdgpu_irq_src_funcs gfx_v11_0_rlc_gc_fed_irq_funcs = {
+	.process = gfx_v11_0_rlc_gc_fed_irq,
+};
+
 static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->gfx.eop_irq.num_types = AMDGPU_CP_IRQ_LAST;
@@ -6219,6 +6303,13 @@ static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev)
 
 	adev->gfx.priv_inst_irq.num_types = 1;
 	adev->gfx.priv_inst_irq.funcs = &gfx_v11_0_priv_inst_irq_funcs;
+
+	adev->gfx.cp_ecc_error_irq.num_types = 1; /* CP ECC error */
+	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v11_0_cp_ecc_error_irq_funcs;
+
+	adev->gfx.rlc_gc_fed_irq.num_types = 1; /* 0x80 FED error */
+	adev->gfx.rlc_gc_fed_irq.funcs = &gfx_v11_0_rlc_gc_fed_irq_funcs;
+
 }
 
 static void gfx_v11_0_set_imu_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c
new file mode 100644
index 000000000000..b07a72ca25d9
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c
@@ -0,0 +1,88 @@
+/*
+ * Copyright 2023 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "soc21.h"
+#include "gc/gc_11_0_3_offset.h"
+#include "gc/gc_11_0_3_sh_mask.h"
+#include "ivsrcid/gfx/irqsrcs_gfx_11_0_0.h"
+#include "soc15.h"
+#include "soc15d.h"
+#include "gfx_v11_0.h"
+
+
+static int gfx_v11_0_3_rlc_gc_fed_irq(struct amdgpu_device *adev,
+				  struct amdgpu_irq_src *source,
+				  struct amdgpu_iv_entry *entry)
+{
+	uint32_t rlc_status0 = 0, rlc_status1 = 0;
+	struct ras_common_if *ras_if = NULL;
+	struct ras_dispatch_if ih_data = {
+		.entry = entry,
+	};
+
+	rlc_status0 = RREG32(SOC15_REG_OFFSET(GC, 0, regRLC_RLCS_FED_STATUS_0));
+	rlc_status1 = RREG32(SOC15_REG_OFFSET(GC, 0, regRLC_RLCS_FED_STATUS_1));
+
+	if (!rlc_status0 && !rlc_status1) {
+		dev_warn(adev->dev, "RLC_GC_FED irq is generated, but rlc_status0 and rlc_status1 are empty!\n");
+		return 0;
+	}
+
+	/* Use RLC_RLCS_FED_STATUS_0/1 to distinguish FED error block. */
+	if (REG_GET_FIELD(rlc_status0, RLC_RLCS_FED_STATUS_0, SDMA0_FED_ERR) ||
+	    REG_GET_FIELD(rlc_status0, RLC_RLCS_FED_STATUS_0, SDMA1_FED_ERR))
+		ras_if = adev->sdma.ras_if;
+	else
+		ras_if = adev->gfx.ras_if;
+
+	if (!ras_if) {
+		dev_err(adev->dev, "Gfx or sdma ras block not initialized, rlc_status0:0x%x.\n",
+				rlc_status0);
+		return -EINVAL;
+	}
+
+	ih_data.head = *ras_if;
+
+	dev_warn(adev->dev, "RLC %s FED IRQ\n", ras_if->name);
+	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
+
+	return 0;
+}
+
+static int gfx_v11_0_3_poison_consumption_handler(struct amdgpu_device *adev,
+					struct amdgpu_iv_entry *entry)
+{
+	/* Workaround: when vmid and pasid are both zero, trigger gpu reset in KGD. */
+	if (entry && (entry->client_id == SOC21_IH_CLIENTID_GFX) &&
+	    (entry->src_id == GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT) &&
+	     !entry->vmid && !entry->pasid)
+		amdgpu_ras_reset_gpu(adev);
+
+	return 0;
+}
+
+struct amdgpu_gfx_ras gfx_v11_0_3_ras = {
+	.rlc_gc_fed_irq = gfx_v11_0_3_rlc_gc_fed_irq,
+	.poison_consumption_handler = gfx_v11_0_3_poison_consumption_handler,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.h b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.h
new file mode 100644
index 000000000000..672c7920b3d0
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2023 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __GFX_V11_0_3_H__
+#define __GFX_V11_0_3_H__
+
+extern struct amdgpu_gfx_ras gfx_v11_0_3_ras;
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 4fb577d047fd..b1f2684d854a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1003,7 +1003,7 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
 		err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name);
 		if (err == -ENODEV) {
 			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
-		err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name);
+			err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name);
 		}
 	} else {
 		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e80685d1e6c6..8ad5c03506f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1345,7 +1345,7 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev,
 
 	err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name);
 	if (err)
-		return err;
+		goto out;
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1);
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT);
 
@@ -1355,13 +1355,14 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev,
 		else
 			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
 
+		/* ignore failures to load */
 		err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name);
 		if (!err) {
 			amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
 			amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);
 		} else {
 			err = 0;
-			adev->gfx.mec2_fw = NULL;
+			amdgpu_ucode_release(&adev->gfx.mec2_fw);
 		}
 	} else {
 		adev->gfx.mec2_fw_version = adev->gfx.mec_fw_version;
@@ -1370,10 +1371,10 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev,
 
 	gfx_v9_0_check_if_need_gfxoff(adev);
 	gfx_v9_0_check_fw_write_wait(adev);
-	if (err) {
+
+out:
+	if (err)
 		amdgpu_ucode_release(&adev->gfx.mec_fw);
-		amdgpu_ucode_release(&adev->gfx.mec2_fw);
-	}
 	return err;
 }
 
@@ -1935,27 +1936,6 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 		break;
 	}
 
-	if (adev->gfx.ras) {
-		err = amdgpu_ras_register_ras_block(adev, &adev->gfx.ras->ras_block);
-		if (err) {
-			DRM_ERROR("Failed to register gfx ras block!\n");
-			return err;
-		}
-
-		strcpy(adev->gfx.ras->ras_block.ras_comm.name, "gfx");
-		adev->gfx.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__GFX;
-		adev->gfx.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
-		adev->gfx.ras_if = &adev->gfx.ras->ras_block.ras_comm;
-
-		/* If not define special ras_late_init function, use gfx default ras_late_init */
-		if (!adev->gfx.ras->ras_block.ras_late_init)
-			adev->gfx.ras->ras_block.ras_late_init = amdgpu_gfx_ras_late_init;
-
-		/* If not defined special ras_cb function, use default ras_cb */
-		if (!adev->gfx.ras->ras_block.ras_cb)
-			adev->gfx.ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb;
-	}
-
 	adev->gfx.config.gb_addr_config = gb_addr_config;
 
 	adev->gfx.config.gb_addr_config_fields.num_pipes = 1 <<
@@ -2197,6 +2177,11 @@ static int gfx_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	if (amdgpu_gfx_ras_sw_init(adev)) {
+		dev_err(adev->dev, "Failed to initialize gfx ras block!\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c
index e9dcd6fcde7f..ae9cd1a4cfee 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c
@@ -169,23 +169,23 @@ static void mmhub_v3_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	uint64_t value;
 	uint32_t tmp;
 
-	if (!amdgpu_sriov_vf(adev)) {
-		/*
-		 * the new L1 policy will block SRIOV guest from writing
-		 * these regs, and they will be programed at host.
-		 * so skip programing these regs.
-		 */
-		/* Disable AGP. */
-		WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BASE, 0);
-		WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_TOP, 0);
-		WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BOT, 0x00FFFFFF);
-
-		/* Program the system aperture low logical page number. */
-		WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_LOW_ADDR,
-			     adev->gmc.vram_start >> 18);
-		WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     adev->gmc.vram_end >> 18);
-	}
+	if (amdgpu_sriov_vf(adev))
+		return;
+
+	/*
+	 * the new L1 policy will block SRIOV guest from writing
+	 * these regs, and they will be programed at host.
+	 * so skip programing these regs.
+	 */
+	/* Disable AGP. */
+	WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BASE, 0);
+	WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_TOP, 0);
+	WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BOT, 0x00FFFFFF);
+	/* Program the system aperture low logical page number. */
+	WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_LOW_ADDR,
+		     adev->gmc.vram_start >> 18);
+	WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+		     adev->gmc.vram_end >> 18);
 
 	/* Set default page address. */
 	value = adev->mem_scratch.gpu_addr - adev->gmc.vram_start +
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 6853b93ac82e..d972025f0d20 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -98,7 +98,7 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode =
 };
 
 /* Sienna Cichlid */
-static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] =
+static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] =
 {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
@@ -110,10 +110,27 @@ static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] =
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
-static const struct amdgpu_video_codecs sc_video_codecs_decode =
+static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn1[] =
 {
-	.codec_count = ARRAY_SIZE(sc_video_codecs_decode_array),
-	.codec_array = sc_video_codecs_decode_array,
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+};
+
+static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn0 =
+{
+	.codec_count = ARRAY_SIZE(sc_video_codecs_decode_array_vcn0),
+	.codec_array = sc_video_codecs_decode_array_vcn0,
+};
+
+static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 =
+{
+	.codec_count = ARRAY_SIZE(sc_video_codecs_decode_array_vcn1),
+	.codec_array = sc_video_codecs_decode_array_vcn1,
 };
 
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
@@ -123,7 +140,7 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] =
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
-static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] =
+static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] =
 {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
@@ -135,16 +152,33 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] =
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
+static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn1[] =
+{
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+};
+
 static struct amdgpu_video_codecs sriov_sc_video_codecs_encode =
 {
 	.codec_count = ARRAY_SIZE(sriov_sc_video_codecs_encode_array),
 	.codec_array = sriov_sc_video_codecs_encode_array,
 };
 
-static struct amdgpu_video_codecs sriov_sc_video_codecs_decode =
+static struct amdgpu_video_codecs sriov_sc_video_codecs_decode_vcn0 =
 {
-	.codec_count = ARRAY_SIZE(sriov_sc_video_codecs_decode_array),
-	.codec_array = sriov_sc_video_codecs_decode_array,
+	.codec_count = ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn0),
+	.codec_array = sriov_sc_video_codecs_decode_array_vcn0,
+};
+
+static struct amdgpu_video_codecs sriov_sc_video_codecs_decode_vcn1 =
+{
+	.codec_count = ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1),
+	.codec_array = sriov_sc_video_codecs_decode_array_vcn1,
 };
 
 /* Beige Goby*/
@@ -181,20 +215,37 @@ static const struct amdgpu_video_codecs yc_video_codecs_decode = {
 static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 				 const struct amdgpu_video_codecs **codecs)
 {
+	if (adev->vcn.num_vcn_inst == hweight8(adev->vcn.harvest_config))
+		return -EINVAL;
+
 	switch (adev->ip_versions[UVD_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
 	case IP_VERSION(3, 0, 64):
 	case IP_VERSION(3, 0, 192):
 		if (amdgpu_sriov_vf(adev)) {
-			if (encode)
-				*codecs = &sriov_sc_video_codecs_encode;
-			else
-				*codecs = &sriov_sc_video_codecs_decode;
+			if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) {
+				if (encode)
+					*codecs = &sriov_sc_video_codecs_encode;
+				else
+					*codecs = &sriov_sc_video_codecs_decode_vcn1;
+			} else {
+				if (encode)
+					*codecs = &sriov_sc_video_codecs_encode;
+				else
+					*codecs = &sriov_sc_video_codecs_decode_vcn0;
+			}
 		} else {
-			if (encode)
-				*codecs = &nv_video_codecs_encode;
-			else
-				*codecs = &sc_video_codecs_decode;
+			if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) {
+				if (encode)
+					*codecs = &nv_video_codecs_encode;
+				else
+					*codecs = &sc_video_codecs_decode_vcn1;
+			} else {
+				if (encode)
+					*codecs = &nv_video_codecs_encode;
+				else
+					*codecs = &sc_video_codecs_decode_vcn0;
+			}
 		}
 		return 0;
 	case IP_VERSION(3, 0, 16):
@@ -202,7 +253,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 		if (encode)
 			*codecs = &nv_video_codecs_encode;
 		else
-			*codecs = &sc_video_codecs_decode;
+			*codecs = &sc_video_codecs_decode_vcn0;
 		return 0;
 	case IP_VERSION(3, 1, 1):
 	case IP_VERSION(3, 1, 2):
@@ -993,9 +1044,19 @@ static int nv_common_late_init(void *handle)
 
 	if (amdgpu_sriov_vf(adev)) {
 		xgpu_nv_mailbox_get_irq(adev);
-		amdgpu_virt_update_sriov_video_codec(adev,
-				sriov_sc_video_codecs_encode_array, ARRAY_SIZE(sriov_sc_video_codecs_encode_array),
-				sriov_sc_video_codecs_decode_array, ARRAY_SIZE(sriov_sc_video_codecs_decode_array));
+		if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) {
+			amdgpu_virt_update_sriov_video_codec(adev,
+							     sriov_sc_video_codecs_encode_array,
+							     ARRAY_SIZE(sriov_sc_video_codecs_encode_array),
+							     sriov_sc_video_codecs_decode_array_vcn1,
+							     ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1));
+		} else {
+			amdgpu_virt_update_sriov_video_codec(adev,
+							     sriov_sc_video_codecs_encode_array,
+							     ARRAY_SIZE(sriov_sc_video_codecs_encode_array),
+							     sriov_sc_video_codecs_decode_array_vcn1,
+							     ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1));
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 017ae298558e..b5affba22156 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1851,6 +1851,11 @@ static int sdma_v4_0_sw_init(void *handle)
 		}
 	}
 
+	if (amdgpu_sdma_ras_sw_init(adev)) {
+		dev_err(adev->dev, "Failed to initialize sdma ras block!\n");
+		return -EINVAL;
+	}
+
 	return r;
 }
 
@@ -2688,22 +2693,6 @@ static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev)
 		break;
 	}
 
-	if (adev->sdma.ras) {
-		amdgpu_ras_register_ras_block(adev, &adev->sdma.ras->ras_block);
-
-		strcpy(adev->sdma.ras->ras_block.ras_comm.name, "sdma");
-		adev->sdma.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__SDMA;
-		adev->sdma.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
-		adev->sdma.ras_if = &adev->sdma.ras->ras_block.ras_comm;
-
-		/* If don't define special ras_late_init function, use default ras_late_init */
-		if (!adev->sdma.ras->ras_block.ras_late_init)
-			adev->sdma.ras->ras_block.ras_late_init = amdgpu_sdma_ras_late_init;
-
-		/* If not defined special ras_cb function, use default ras_cb */
-		if (!adev->sdma.ras->ras_block.ras_cb)
-			adev->sdma.ras->ras_block.ras_cb = amdgpu_sdma_process_ras_data_cb;
-	}
 }
 
 const struct amdgpu_ip_block_version sdma_v4_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index bf1fa5e8d2f9..3d36329be384 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1211,6 +1211,24 @@ static void sdma_v6_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
 	amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask);
 }
 
+static struct amdgpu_sdma_ras sdma_v6_0_3_ras = {
+	.ras_block = {
+		.ras_late_init = amdgpu_ras_block_late_init,
+	},
+};
+
+static void sdma_v6_0_set_ras_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	case IP_VERSION(6, 0, 3):
+		adev->sdma.ras = &sdma_v6_0_3_ras;
+		break;
+	default:
+		break;
+	}
+
+}
+
 static int sdma_v6_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1220,6 +1238,7 @@ static int sdma_v6_0_early_init(void *handle)
 	sdma_v6_0_set_vm_pte_funcs(adev);
 	sdma_v6_0_set_irq_funcs(adev);
 	sdma_v6_0_set_mqd_funcs(adev);
+	sdma_v6_0_set_ras_funcs(adev);
 
 	return 0;
 }
@@ -1264,6 +1283,11 @@ static int sdma_v6_0_sw_init(void *handle)
 			return r;
 	}
 
+	if (amdgpu_sdma_ras_sw_init(adev)) {
+		dev_err(adev->dev, "Failed to initialize sdma ras block!\n");
+		return -EINVAL;
+	}
+
 	return r;
 }
 
@@ -1403,10 +1427,12 @@ static int sdma_v6_0_set_trap_irq_state(struct amdgpu_device *adev,
 
 	u32 reg_offset = sdma_v6_0_get_reg_offset(adev, type, regSDMA0_CNTL);
 
-	sdma_cntl = RREG32(reg_offset);
-	sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA0_CNTL, TRAP_ENABLE,
-		       state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0);
-	WREG32(reg_offset, sdma_cntl);
+	if (!amdgpu_sriov_vf(adev)) {
+		sdma_cntl = RREG32(reg_offset);
+		sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA0_CNTL, TRAP_ENABLE,
+				state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0);
+		WREG32(reg_offset, sdma_cntl);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 5562670b7b52..9c4a29d50f1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -48,19 +48,31 @@
 static const struct amd_ip_funcs soc21_common_ip_funcs;
 
 /* SOC21 */
-static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array[] =
+static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] =
 {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
-static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode =
+static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] =
 {
-	.codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_encode_array),
-	.codec_array = vcn_4_0_0_video_codecs_encode_array,
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+};
+
+static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 =
+{
+	.codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_encode_array_vcn0),
+	.codec_array = vcn_4_0_0_video_codecs_encode_array_vcn0,
 };
 
-static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array[] =
+static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn1 =
+{
+	.codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_encode_array_vcn1),
+	.codec_array = vcn_4_0_0_video_codecs_encode_array_vcn1,
+};
+
+static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array_vcn0[] =
 {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
@@ -69,23 +81,46 @@ static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array[
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
-static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode =
+static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array_vcn1[] =
+{
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+};
+
+static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn0 =
 {
-	.codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_decode_array),
-	.codec_array = vcn_4_0_0_video_codecs_decode_array,
+	.codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_decode_array_vcn0),
+	.codec_array = vcn_4_0_0_video_codecs_decode_array_vcn0,
+};
+
+static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 =
+{
+	.codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_decode_array_vcn1),
+	.codec_array = vcn_4_0_0_video_codecs_decode_array_vcn1,
 };
 
 static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode,
 				 const struct amdgpu_video_codecs **codecs)
 {
-	switch (adev->ip_versions[UVD_HWIP][0]) {
+	if (adev->vcn.num_vcn_inst == hweight8(adev->vcn.harvest_config))
+		return -EINVAL;
 
+	switch (adev->ip_versions[UVD_HWIP][0]) {
 	case IP_VERSION(4, 0, 0):
 	case IP_VERSION(4, 0, 2):
-		if (encode)
-			*codecs = &vcn_4_0_0_video_codecs_encode;
-		else
-			*codecs = &vcn_4_0_0_video_codecs_decode;
+		if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) {
+			if (encode)
+				*codecs = &vcn_4_0_0_video_codecs_encode_vcn1;
+			else
+				*codecs = &vcn_4_0_0_video_codecs_decode_vcn1;
+		} else {
+			if (encode)
+				*codecs = &vcn_4_0_0_video_codecs_encode_vcn0;
+			else
+				*codecs = &vcn_4_0_0_video_codecs_decode_vcn0;
+		}
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 72fd963f178b..e08e25a3a1a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -57,13 +57,6 @@ static inline uint32_t get_umc_v6_7_reg_offset(struct amdgpu_device *adev,
 	return adev->umc.channel_offs * ch_inst + UMC_V6_7_INST_DIST * umc_inst;
 }
 
-static inline uint32_t get_umc_v6_7_channel_index(struct amdgpu_device *adev,
-					      uint32_t umc_inst,
-					      uint32_t ch_inst)
-{
-	return adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst];
-}
-
 static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev,
 						  uint64_t mc_umc_status, uint32_t umc_reg_offset)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index bd228512424a..66439388faee 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1771,6 +1771,10 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p,
 	if (atomic_read(&job->base.entity->fence_seq))
 		return -EINVAL;
 
+	/* if VCN0 is harvested, we can't support AV1 */
+	if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)
+		return -EINVAL;
+
 	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC]
 		[AMDGPU_RING_PRIO_DEFAULT].sched;
 	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index a79b6088374b..efb22d0975b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1632,6 +1632,10 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p,
 	if (atomic_read(&job->base.entity->fence_seq))
 		return -EINVAL;
 
+	/* if VCN0 is harvested, we can't support AV1 */
+	if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)
+		return -EINVAL;
+
 	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC]
 		[AMDGPU_RING_PRIO_0].sched;
 	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);