Merge tag 'amd-drm-next-5.17-2021-12-30' of ssh://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.17-2021-12-30:

amdgpu:
- Suspend/resume fixes
- Fence fix
- Misc code cleanups
- IP discovery fixes
- SRIOV fixes
- RAS fixes
- GMC 8 VRAM detection fix
- FRU fixes for Aldebaran
- Display fixes

amdkfd:
- SVM fixes
- IP discovery fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211230141032.613596-1-alexander.deucher@amd.com

23 files changed, 574 insertions, 354 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9eb7afa276f2..4f771f9eb0e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -812,6 +812,7 @@ struct amd_powerplay {
 
 #define AMDGPU_RESET_MAGIC_NUM 64
 #define AMDGPU_MAX_DF_PERFMONS 4
+#define AMDGPU_PRODUCT_NAME_LEN 64
 struct amdgpu_device {
 	struct device			*dev;
 	struct pci_dev			*pdev;
@@ -1082,7 +1083,7 @@ struct amdgpu_device {
 
 	/* Chip product information */
 	char				product_number[16];
-	char				product_name[32];
+	char				product_name[AMDGPU_PRODUCT_NAME_LEN];
 	char				serial[20];
 
 	atomic_t			throttling_logging_enabled;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 46cf48b3904a..776a947b45df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -721,13 +721,13 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev)
 	return adev->have_atomics_support;
 }
 
-void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev)
+void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, bool reset)
 {
 	struct ras_err_data err_data = {0, 0, 0, NULL};
 
 	/* CPU MCA will handle page retirement if connected_to_cpu is 1 */
 	if (!adev->gmc.xgmi.connected_to_cpu)
-		amdgpu_umc_process_ras_data_cb(adev, &err_data, NULL);
-	else
+		amdgpu_umc_poison_handler(adev, &err_data, reset);
+	else if (reset)
 		amdgpu_amdkfd_gpu_reset(adev);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index fcbc8a9c9e06..61f899e54fd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -296,7 +296,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev,
 				      uint64_t *mmap_offset);
 int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev,
 				struct tile_config *config);
-void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev);
+void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev,
+				bool reset);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index ddfe7aff919d..1abf662a0e91 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -166,7 +166,7 @@ int kgd_gfx_v9_init_interrupts(struct amdgpu_device *adev, uint32_t pipe_id)
 
 	lock_srbm(adev, mec, pipe, 0, 0);
 
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmCPC_INT_CNTL),
+	WREG32_SOC15(GC, 0, mmCPC_INT_CNTL,
 		CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK |
 		CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK);
 
@@ -279,7 +279,7 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd,
 		       lower_32_bits((uintptr_t)wptr));
 		WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uintptr_t)wptr));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
+		WREG32_SOC15(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1,
 		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
@@ -488,13 +488,13 @@ bool kgd_gfx_v9_hqd_is_occupied(struct amdgpu_device *adev,
 	uint32_t low, high;
 
 	acquire_queue(adev, pipe_id, queue_id);
-	act = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+	act = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
 	if (act) {
 		low = lower_32_bits(queue_address >> 8);
 		high = upper_32_bits(queue_address >> 8);
 
-		if (low == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE)) &&
-		   high == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE_HI)))
+		if (low == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE) &&
+		   high == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE_HI))
 			retval = true;
 	}
 	release_queue(adev);
@@ -556,7 +556,7 @@ int kgd_gfx_v9_hqd_destroy(struct amdgpu_device *adev, void *mqd,
 
 	end_jiffies = (utimeout * HZ / 1000) + jiffies;
 	while (true) {
-		temp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE));
+		temp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
 		if (!(temp & CP_HQD_ACTIVE__ACTIVE_MASK))
 			break;
 		if (time_after(jiffies, end_jiffies)) {
@@ -645,7 +645,7 @@ int kgd_gfx_v9_wave_control_execute(struct amdgpu_device *adev,
 	mutex_lock(&adev->grbm_idx_mutex);
 
 	WREG32_SOC15_RLC_SHADOW(GC, 0, mmGRBM_GFX_INDEX, gfx_index_val);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd);
+	WREG32_SOC15(GC, 0, mmSQ_CMD, sq_cmd);
 
 	data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
 		INSTANCE_BROADCAST_WRITES, 1);
@@ -722,7 +722,7 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
 	pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe;
 	queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe;
 	soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0);
-	reg_val = RREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
+	reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
 			 queue_slot);
 	*wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK;
 	if (*wave_cnt != 0)
@@ -809,8 +809,7 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid,
 		for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) {
 
 			gfx_v9_0_select_se_sh(adev, se_idx, sh_idx, 0xffffffff);
-			queue_map = RREG32(SOC15_REG_OFFSET(GC, 0,
-					   mmSPI_CSQ_WF_ACTIVE_STATUS));
+			queue_map = RREG32_SOC15(GC, 0, mmSPI_CSQ_WF_ACTIVE_STATUS);
 
 			/*
 			 * Assumption: queue map encodes following schema: four
@@ -860,17 +859,17 @@ void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev,
 	/*
 	 * Program TBA registers
 	 */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TBA_LO,
                         lower_32_bits(tba_addr >> 8));
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TBA_HI,
                         upper_32_bits(tba_addr >> 8));
 
 	/*
 	 * Program TMA registers
 	 */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TMA_LO,
 			lower_32_bits(tma_addr >> 8));
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+	WREG32_SOC15(GC, 0, mmSQ_SHADER_TMA_HI,
 			upper_32_bits(tma_addr >> 8));
 
 	unlock_srbm(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8219e40240ce..a8b08a72b71b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2317,6 +2317,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 
 		/* need to do gmc hw init early so we can allocate gpu mem */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+			/* Try to reserve bad pages early */
+			if (amdgpu_sriov_vf(adev))
+				amdgpu_virt_exchange_data(adev);
+
 			r = amdgpu_device_vram_scratch_init(adev);
 			if (r) {
 				DRM_ERROR("amdgpu_vram_scratch_init failed %d\n", r);
@@ -2348,7 +2352,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_init_data_exchange(adev);
+		amdgpu_virt_exchange_data(adev);
 
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
@@ -2615,11 +2619,10 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 	if (r)
 		DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
 
-	/* For XGMI + passthrough configuration on arcturus, enable light SBR */
-	if (adev->asic_type == CHIP_ARCTURUS &&
-	    amdgpu_passthrough(adev) &&
-	    adev->gmc.xgmi.num_physical_nodes > 1)
-		smu_set_light_sbr(&adev->smu, true);
+	/* For passthrough configuration on arcturus and aldebaran, enable special handling SBR */
+	if (amdgpu_passthrough(adev) && ((adev->asic_type == CHIP_ARCTURUS && adev->gmc.xgmi.num_physical_nodes > 1)||
+			       adev->asic_type == CHIP_ALDEBARAN ))
+		smu_handle_passthrough_sbr(&adev->smu, true);
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1) {
 		mutex_lock(&mgpu_info.mutex);
@@ -3182,6 +3185,12 @@ static void amdgpu_device_detect_sriov_bios(struct amdgpu_device *adev)
 bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 {
 	switch (asic_type) {
+#ifdef CONFIG_DRM_AMDGPU_SI
+	case CHIP_HAINAN:
+#endif
+	case CHIP_TOPAZ:
+		/* chips with no display hardware */
+		return false;
 #if defined(CONFIG_DRM_AMD_DC)
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
@@ -3573,6 +3582,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	/* Need to get xgmi info early to decide the reset behavior*/
+	if (adev->gmc.xgmi.supported) {
+		r = adev->gfxhub.funcs->get_xgmi_info(adev);
+		if (r)
+			return r;
+	}
+
 	/* enable PCIE atomic ops */
 	if (amdgpu_sriov_vf(adev))
 		adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *)
@@ -3885,11 +3901,14 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 	amdgpu_irq_fini_hw(adev);
 
-	ttm_device_clear_dma_mappings(&adev->mman.bdev);
+	if (adev->mman.initialized)
+		ttm_device_clear_dma_mappings(&adev->mman.bdev);
 
 	amdgpu_gart_dummy_page_fini(adev);
 
-	amdgpu_device_unmap_mmio(adev);
+	if (drm_dev_is_unplugged(adev_to_drm(adev)))
+		amdgpu_device_unmap_mmio(adev);
+
 }
 
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)
@@ -4507,7 +4526,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 				 struct amdgpu_reset_context *reset_context)
 {
-	int i, j, r = 0;
+	int i, r = 0;
 	struct amdgpu_job *job = NULL;
 	bool need_full_reset =
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@@ -4529,15 +4548,8 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 
 		/*clear job fence from fence drv to avoid force_completion
 		 *leave NULL and vm flush fence in fence drv */
-		for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) {
-			struct dma_fence *old, **ptr;
+		amdgpu_fence_driver_clear_job_fences(ring);
 
-			ptr = &ring->fence_drv.fences[j];
-			old = rcu_dereference_protected(*ptr, 1);
-			if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) {
-				RCU_INIT_POINTER(*ptr, NULL);
-			}
-		}
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 5bc072220f03..028190d42bb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -565,10 +565,15 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 	}
 }
 
+union gc_info {
+	struct gc_info_v1_0 v1;
+	struct gc_info_v2_0 v2;
+};
+
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 {
 	struct binary_header *bhdr;
-	struct gc_info_v1_0 *gc_info;
+	union gc_info *gc_info;
 
 	if (!adev->mman.discovery_bin) {
 		DRM_ERROR("ip discovery uninitialized\n");
@@ -576,28 +581,55 @@ int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 	}
 
 	bhdr = (struct binary_header *)adev->mman.discovery_bin;
-	gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin +
+	gc_info = (union gc_info *)(adev->mman.discovery_bin +
 			le16_to_cpu(bhdr->table_list[GC].offset));
-
-	adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
-	adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) +
-					      le32_to_cpu(gc_info->gc_num_wgp1_per_sa));
-	adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se);
-	adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se);
-	adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c);
-	adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs);
-	adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds);
-	adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth);
-	adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth);
-	adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer);
-	adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size);
-	adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd);
-	adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu);
-	adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size);
-	adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) /
-					 le32_to_cpu(gc_info->gc_num_sa_per_se);
-	adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc);
-
+	switch (gc_info->v1.header.version_major) {
+	case 1:
+		adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v1.gc_num_se);
+		adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->v1.gc_num_wgp0_per_sa) +
+						      le32_to_cpu(gc_info->v1.gc_num_wgp1_per_sa));
+		adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+		adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v1.gc_num_rb_per_se);
+		adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v1.gc_num_gl2c);
+		adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v1.gc_num_gprs);
+		adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v1.gc_num_max_gs_thds);
+		adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v1.gc_gs_table_depth);
+		adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v1.gc_gsprim_buff_depth);
+		adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v1.gc_double_offchip_lds_buffer);
+		adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v1.gc_wave_size);
+		adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v1.gc_max_waves_per_simd);
+		adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v1.gc_max_scratch_slots_per_cu);
+		adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v1.gc_lds_size);
+		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v1.gc_num_sc_per_se) /
+			le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v1.gc_num_packer_per_sc);
+		break;
+	case 2:
+		adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se);
+		adev->gfx.config.max_cu_per_sh = le32_to_cpu(gc_info->v2.gc_num_cu_per_sh);
+		adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+		adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v2.gc_num_rb_per_se);
+		adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v2.gc_num_tccs);
+		adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v2.gc_num_gprs);
+		adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v2.gc_num_max_gs_thds);
+		adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v2.gc_gs_table_depth);
+		adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v2.gc_gsprim_buff_depth);
+		adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v2.gc_double_offchip_lds_buffer);
+		adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v2.gc_wave_size);
+		adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v2.gc_max_waves_per_simd);
+		adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v2.gc_max_scratch_slots_per_cu);
+		adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v2.gc_lds_size);
+		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) /
+			le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc);
+		break;
+	default:
+		dev_err(adev->dev,
+			"Unhandled GC info table %d.%d\n",
+			gc_info->v1.header.version_major,
+			gc_info->v1.header.version_minor);
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -992,7 +1024,7 @@ static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
 		break;
 	default:
-		break;;
+		break;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 02099058d0d6..04f6da98ee59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -330,10 +330,11 @@ module_param_named(aspm, amdgpu_aspm, int, 0444);
 
 /**
  * DOC: runpm (int)
- * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down
- * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality.
+ * Override for runtime power management control for dGPUs. The amdgpu driver can dynamically power down
+ * the dGPUs when they are idle if supported. The default is -1 (auto enable).
+ * Setting the value to 0 disables this functionality.
  */
-MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = PX only default)");
+MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = auto)");
 module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
 
 /**
@@ -2168,7 +2169,10 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	adev->in_s3 = true;
 	r = amdgpu_device_suspend(drm_dev, true);
 	adev->in_s3 = false;
-
+	if (r)
+		return r;
+	if (!adev->in_s0ix)
+		r = amdgpu_asic_reset(adev);
 	return r;
 }
 
@@ -2249,12 +2253,27 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 	if (amdgpu_device_supports_px(drm_dev))
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
+	/*
+	 * By setting mp1_state as PP_MP1_STATE_UNLOAD, MP1 will do some
+	 * proper cleanups and put itself into a state ready for PNP. That
+	 * can address some random resuming failure observed on BOCO capable
+	 * platforms.
+	 * TODO: this may be also needed for PX capable platform.
+	 */
+	if (amdgpu_device_supports_boco(drm_dev))
+		adev->mp1_state = PP_MP1_STATE_UNLOAD;
+
 	ret = amdgpu_device_suspend(drm_dev, false);
 	if (ret) {
 		adev->in_runpm = false;
+		if (amdgpu_device_supports_boco(drm_dev))
+			adev->mp1_state = PP_MP1_STATE_NONE;
 		return ret;
 	}
 
+	if (amdgpu_device_supports_boco(drm_dev))
+		adev->mp1_state = PP_MP1_STATE_NONE;
+
 	if (amdgpu_device_supports_px(drm_dev)) {
 		/* Only need to handle PCI state in the driver for ATPX
 		 * PCI core handles it for _PR3.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 3b7e86ea7167..9afd11ca2709 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -77,11 +77,13 @@ void amdgpu_fence_slab_fini(void)
  * Cast helper
  */
 static const struct dma_fence_ops amdgpu_fence_ops;
+static const struct dma_fence_ops amdgpu_job_fence_ops;
 static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f)
 {
 	struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
 
-	if (__f->base.ops == &amdgpu_fence_ops)
+	if (__f->base.ops == &amdgpu_fence_ops ||
+	    __f->base.ops == &amdgpu_job_fence_ops)
 		return __f;
 
 	return NULL;
@@ -158,19 +160,18 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 	}
 
 	seq = ++ring->fence_drv.sync_seq;
-	if (job != NULL && job->job_run_counter) {
+	if (job && job->job_run_counter) {
 		/* reinit seq for resubmitted jobs */
 		fence->seqno = seq;
 	} else {
-		dma_fence_init(fence, &amdgpu_fence_ops,
-				&ring->fence_drv.lock,
-				adev->fence_context + ring->idx,
-				seq);
-	}
-
-	if (job != NULL) {
-		/* mark this fence has a parent job */
-		set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags);
+		if (job)
+			dma_fence_init(fence, &amdgpu_job_fence_ops,
+				       &ring->fence_drv.lock,
+				       adev->fence_context + ring->idx, seq);
+		else
+			dma_fence_init(fence, &amdgpu_fence_ops,
+				       &ring->fence_drv.lock,
+				       adev->fence_context + ring->idx, seq);
 	}
 
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
@@ -621,6 +622,25 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 }
 
 /**
+ * amdgpu_fence_driver_clear_job_fences - clear job embedded fences of ring
+ *
+ * @ring: fence of the ring to be cleared
+ *
+ */
+void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
+{
+	int i;
+	struct dma_fence *old, **ptr;
+
+	for (i = 0; i <= ring->fence_drv.num_fences_mask; i++) {
+		ptr = &ring->fence_drv.fences[i];
+		old = rcu_dereference_protected(*ptr, 1);
+		if (old && old->ops == &amdgpu_job_fence_ops)
+			RCU_INIT_POINTER(*ptr, NULL);
+	}
+}
+
+/**
  * amdgpu_fence_driver_force_completion - force signal latest fence of ring
  *
  * @ring: fence of the ring to signal
@@ -643,16 +663,14 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence)
 
 static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 {
-	struct amdgpu_ring *ring;
+	return (const char *)to_amdgpu_fence(f)->ring->name;
+}
 
-	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
-		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
+{
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
 
-		ring = to_amdgpu_ring(job->base.sched);
-	} else {
-		ring = to_amdgpu_fence(f)->ring;
-	}
-	return (const char *)ring->name;
+	return (const char *)to_amdgpu_ring(job->base.sched)->name;
 }
 
 /**
@@ -665,18 +683,25 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
  */
 static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 {
-	struct amdgpu_ring *ring;
+	if (!timer_pending(&to_amdgpu_fence(f)->ring->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(to_amdgpu_fence(f)->ring);
 
-	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
-		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+	return true;
+}
 
-		ring = to_amdgpu_ring(job->base.sched);
-	} else {
-		ring = to_amdgpu_fence(f)->ring;
-	}
+/**
+ * amdgpu_job_fence_enable_signaling - enable signalling on job fence
+ * @f: fence
+ *
+ * This is the simliar function with amdgpu_fence_enable_signaling above, it
+ * only handles the job embedded fence.
+ */
+static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
+{
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
 
-	if (!timer_pending(&ring->fence_drv.fallback_timer))
-		amdgpu_fence_schedule_fallback(ring);
+	if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
 
 	return true;
 }
@@ -692,19 +717,23 @@ static void amdgpu_fence_free(struct rcu_head *rcu)
 {
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
 
-	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
-	/* free job if fence has a parent job */
-		struct amdgpu_job *job;
-
-		job = container_of(f, struct amdgpu_job, hw_fence);
-		kfree(job);
-	} else {
 	/* free fence_slab if it's separated fence*/
-		struct amdgpu_fence *fence;
+	kmem_cache_free(amdgpu_fence_slab, to_amdgpu_fence(f));
+}
 
-		fence = to_amdgpu_fence(f);
-		kmem_cache_free(amdgpu_fence_slab, fence);
-	}
+/**
+ * amdgpu_job_fence_free - free up the job with embedded fence
+ *
+ * @rcu: RCU callback head
+ *
+ * Free up the job with embedded fence after the RCU grace period.
+ */
+static void amdgpu_job_fence_free(struct rcu_head *rcu)
+{
+	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
+
+	/* free job if fence has a parent job */
+	kfree(container_of(f, struct amdgpu_job, hw_fence));
 }
 
 /**
@@ -720,6 +749,19 @@ static void amdgpu_fence_release(struct dma_fence *f)
 	call_rcu(&f->rcu, amdgpu_fence_free);
 }
 
+/**
+ * amdgpu_job_fence_release - callback that job embedded fence can be freed
+ *
+ * @f: fence
+ *
+ * This is the simliar function with amdgpu_fence_release above, it
+ * only handles the job embedded fence.
+ */
+static void amdgpu_job_fence_release(struct dma_fence *f)
+{
+	call_rcu(&f->rcu, amdgpu_job_fence_free);
+}
+
 static const struct dma_fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
@@ -727,6 +769,12 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
 	.release = amdgpu_fence_release,
 };
 
+static const struct dma_fence_ops amdgpu_job_fence_ops = {
+	.get_driver_name = amdgpu_fence_get_driver_name,
+	.get_timeline_name = amdgpu_job_fence_get_timeline_name,
+	.enable_signaling = amdgpu_job_fence_enable_signaling,
+	.release = amdgpu_job_fence_release,
+};
 
 /*
  * Fence debugfs
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
index 7709caeb233d..2a786e788627 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
@@ -56,6 +56,9 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 			return true;
 		else
 			return false;
+	case CHIP_ALDEBARAN:
+		/* All Aldebaran SKUs have the FRU */
+		return true;
 	default:
 		return false;
 	}
@@ -88,13 +91,17 @@ static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
 
 int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 {
-	unsigned char buff[34];
+	unsigned char buff[AMDGPU_PRODUCT_NAME_LEN+2];
 	u32 addrptr;
 	int size, len;
+	int offset = 2;
 
 	if (!is_fru_eeprom_supported(adev))
 		return 0;
 
+	if (adev->asic_type == CHIP_ALDEBARAN)
+		offset = 0;
+
 	/* If algo exists, it means that the i2c_adapter's initialized */
 	if (!adev->pm.smu_i2c.algo) {
 		DRM_WARN("Cannot access FRU, EEPROM accessor not initialized");
@@ -131,15 +138,13 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 	}
 
 	len = size;
-	/* Product name should only be 32 characters. Any more,
-	 * and something could be wrong. Cap it at 32 to be safe
-	 */
-	if (len >= sizeof(adev->product_name)) {
-		DRM_WARN("FRU Product Number is larger than 32 characters. This is likely a mistake");
-		len = sizeof(adev->product_name) - 1;
+	if (len >= AMDGPU_PRODUCT_NAME_LEN) {
+		DRM_WARN("FRU Product Name is larger than %d characters. This is likely a mistake",
+				AMDGPU_PRODUCT_NAME_LEN);
+		len = AMDGPU_PRODUCT_NAME_LEN - 1;
 	}
 	/* Start at 2 due to buff using fields 0 and 1 for the address */
-	memcpy(adev->product_name, &buff[2], len);
+	memcpy(adev->product_name, &buff[offset], len);
 	adev->product_name[len] = '\0';
 
 	addrptr += size + 1;
@@ -157,7 +162,7 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 		DRM_WARN("FRU Product Number is larger than 16 characters. This is likely a mistake");
 		len = sizeof(adev->product_number) - 1;
 	}
-	memcpy(adev->product_number, &buff[2], len);
+	memcpy(adev->product_number, &buff[offset], len);
 	adev->product_number[len] = '\0';
 
 	addrptr += size + 1;
@@ -184,7 +189,7 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 		DRM_WARN("FRU Serial Number is larger than 16 characters. This is likely a mistake");
 		len = sizeof(adev->serial) - 1;
 	}
-	memcpy(adev->serial, &buff[2], len);
+	memcpy(adev->serial, &buff[offset], len);
 	adev->serial[len] = '\0';
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index c0d8f40a5b45..9a6507af1670 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -264,6 +264,9 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str
 	    !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
 		vma->vm_flags &= ~VM_MAYWRITE;
 
+	if (bo->kfd_bo)
+		vma->vm_flags |= VM_DONTCOPY;
+
 	return drm_gem_ttm_mmap(obj, vma);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 4d380e79752c..fae7d185ad0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -53,9 +53,6 @@ enum amdgpu_ring_priority_level {
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
 #define AMDGPU_FENCE_FLAG_TC_WB_ONLY    (1 << 2)
 
-/* fence flag bit to indicate the face is embedded in job*/
-#define AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT		(DMA_FENCE_FLAG_USER_BITS + 1)
-
 #define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
 
 #define AMDGPU_IB_POOL_SIZE	(1024 * 1024)
@@ -114,6 +111,7 @@ struct amdgpu_fence_driver {
 	struct dma_fence		**fences;
 };
 
+void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
 void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index 6e4bea012ea4..46264a4002f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -23,74 +23,10 @@
 
 #include "amdgpu_ras.h"
 
-int amdgpu_umc_ras_late_init(struct amdgpu_device *adev)
-{
-	int r;
-	struct ras_fs_if fs_info = {
-		.sysfs_name = "umc_err_count",
-	};
-	struct ras_ih_if ih_info = {
-		.cb = amdgpu_umc_process_ras_data_cb,
-	};
-
-	if (!adev->umc.ras_if) {
-		adev->umc.ras_if =
-			kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
-		if (!adev->umc.ras_if)
-			return -ENOMEM;
-		adev->umc.ras_if->block = AMDGPU_RAS_BLOCK__UMC;
-		adev->umc.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
-		adev->umc.ras_if->sub_block_index = 0;
-	}
-	ih_info.head = fs_info.head = *adev->umc.ras_if;
-
-	r = amdgpu_ras_late_init(adev, adev->umc.ras_if,
-				 &fs_info, &ih_info);
-	if (r)
-		goto free;
-
-	if (amdgpu_ras_is_supported(adev, adev->umc.ras_if->block)) {
-		r = amdgpu_irq_get(adev, &adev->gmc.ecc_irq, 0);
-		if (r)
-			goto late_fini;
-	} else {
-		r = 0;
-		goto free;
-	}
-
-	/* ras init of specific umc version */
-	if (adev->umc.ras_funcs &&
-	    adev->umc.ras_funcs->err_cnt_init)
-		adev->umc.ras_funcs->err_cnt_init(adev);
-
-	return 0;
-
-late_fini:
-	amdgpu_ras_late_fini(adev, adev->umc.ras_if, &ih_info);
-free:
-	kfree(adev->umc.ras_if);
-	adev->umc.ras_if = NULL;
-	return r;
-}
-
-void amdgpu_umc_ras_fini(struct amdgpu_device *adev)
-{
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC) &&
-			adev->umc.ras_if) {
-		struct ras_common_if *ras_if = adev->umc.ras_if;
-		struct ras_ih_if ih_info = {
-			.head = *ras_if,
-			.cb = amdgpu_umc_process_ras_data_cb,
-		};
-
-		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
-		kfree(ras_if);
-	}
-}
-
-int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
+static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 		void *ras_error_status,
-		struct amdgpu_iv_entry *entry)
+		struct amdgpu_iv_entry *entry,
+		bool reset)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -164,13 +100,108 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 				adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.ras_num_recs);
 		}
 
-		amdgpu_ras_reset_gpu(adev);
+		if (reset)
+			amdgpu_ras_reset_gpu(adev);
 	}
 
 	kfree(err_data->err_addr);
 	return AMDGPU_RAS_SUCCESS;
 }
 
+int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
+		void *ras_error_status,
+		bool reset)
+{
+	int ret;
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	struct ras_common_if head = {
+		.block = AMDGPU_RAS_BLOCK__UMC,
+	};
+	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
+
+	ret =
+		amdgpu_umc_do_page_retirement(adev, ras_error_status, NULL, reset);
+
+	if (ret == AMDGPU_RAS_SUCCESS && obj) {
+		obj->err_data.ue_count += err_data->ue_count;
+		obj->err_data.ce_count += err_data->ce_count;
+	}
+
+	return ret;
+}
+
+static int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
+		void *ras_error_status,
+		struct amdgpu_iv_entry *entry)
+{
+	return amdgpu_umc_do_page_retirement(adev, ras_error_status, entry, true);
+}
+
+int amdgpu_umc_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "umc_err_count",
+	};
+	struct ras_ih_if ih_info = {
+		.cb = amdgpu_umc_process_ras_data_cb,
+	};
+
+	if (!adev->umc.ras_if) {
+		adev->umc.ras_if =
+			kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->umc.ras_if)
+			return -ENOMEM;
+		adev->umc.ras_if->block = AMDGPU_RAS_BLOCK__UMC;
+		adev->umc.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->umc.ras_if->sub_block_index = 0;
+	}
+	ih_info.head = fs_info.head = *adev->umc.ras_if;
+
+	r = amdgpu_ras_late_init(adev, adev->umc.ras_if,
+				 &fs_info, &ih_info);
+	if (r)
+		goto free;
+
+	if (amdgpu_ras_is_supported(adev, adev->umc.ras_if->block)) {
+		r = amdgpu_irq_get(adev, &adev->gmc.ecc_irq, 0);
+		if (r)
+			goto late_fini;
+	} else {
+		r = 0;
+		goto free;
+	}
+
+	/* ras init of specific umc version */
+	if (adev->umc.ras_funcs &&
+	    adev->umc.ras_funcs->err_cnt_init)
+		adev->umc.ras_funcs->err_cnt_init(adev);
+
+	return 0;
+
+late_fini:
+	amdgpu_ras_late_fini(adev, adev->umc.ras_if, &ih_info);
+free:
+	kfree(adev->umc.ras_if);
+	adev->umc.ras_if = NULL;
+	return r;
+}
+
+void amdgpu_umc_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC) &&
+			adev->umc.ras_if) {
+		struct ras_common_if *ras_if = adev->umc.ras_if;
+		struct ras_ih_if ih_info = {
+			.head = *ras_if,
+			.cb = amdgpu_umc_process_ras_data_cb,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
+
 int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
 		struct amdgpu_irq_src *source,
 		struct amdgpu_iv_entry *entry)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index 9e40bade0a68..b72194e8bfe5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -78,9 +78,9 @@ struct amdgpu_umc {
 
 int amdgpu_umc_ras_late_init(struct amdgpu_device *adev);
 void amdgpu_umc_ras_fini(struct amdgpu_device *adev);
-int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
+int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
 		void *ras_error_status,
-		struct amdgpu_iv_entry *entry);
+		bool reset);
 int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
 		struct amdgpu_irq_src *source,
 		struct amdgpu_iv_entry *entry);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 3fc49823f527..f8e574cc0e22 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -622,19 +622,37 @@ void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev)
 
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 {
-	uint64_t bp_block_offset = 0;
-	uint32_t bp_block_size = 0;
-	struct amd_sriov_msg_pf2vf_info *pf2vf_v2 = NULL;
-
 	adev->virt.fw_reserve.p_pf2vf = NULL;
 	adev->virt.fw_reserve.p_vf2pf = NULL;
 	adev->virt.vf2pf_update_interval_ms = 0;
 
-	if (adev->mman.fw_vram_usage_va != NULL) {
+	if (adev->bios != NULL) {
 		adev->virt.vf2pf_update_interval_ms = 2000;
 
 		adev->virt.fw_reserve.p_pf2vf =
 			(struct amd_sriov_msg_pf2vf_info_header *)
+			(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
+
+		amdgpu_virt_read_pf2vf_data(adev);
+	}
+
+	if (adev->virt.vf2pf_update_interval_ms != 0) {
+		INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
+		schedule_delayed_work(&(adev->virt.vf2pf_work), msecs_to_jiffies(adev->virt.vf2pf_update_interval_ms));
+	}
+}
+
+
+void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
+{
+	uint64_t bp_block_offset = 0;
+	uint32_t bp_block_size = 0;
+	struct amd_sriov_msg_pf2vf_info *pf2vf_v2 = NULL;
+
+	if (adev->mman.fw_vram_usage_va != NULL) {
+
+		adev->virt.fw_reserve.p_pf2vf =
+			(struct amd_sriov_msg_pf2vf_info_header *)
 			(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
 		adev->virt.fw_reserve.p_vf2pf =
 			(struct amd_sriov_msg_vf2pf_info_header *)
@@ -663,16 +681,10 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 			(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
 
 		amdgpu_virt_read_pf2vf_data(adev);
-
-		return;
-	}
-
-	if (adev->virt.vf2pf_update_interval_ms != 0) {
-		INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
-		schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms);
 	}
 }
 
+
 void amdgpu_detect_virtualization(struct amdgpu_device *adev)
 {
 	uint32_t reg;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 8d4c20bb71c5..9adfb8d63280 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -308,6 +308,7 @@ int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev);
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
+void amdgpu_virt_exchange_data(struct amdgpu_device *adev);
 void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev);
 void amdgpu_detect_virtualization(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index edb3e3b08eed..9189fb85a4dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -63,6 +63,13 @@
 #define mmGCEA_PROBE_MAP                        0x070c
 #define mmGCEA_PROBE_MAP_BASE_IDX               0
 
+#define GFX9_RLCG_GC_WRITE_OLD			(0x8 << 28)
+#define GFX9_RLCG_GC_WRITE			(0x0 << 28)
+#define GFX9_RLCG_GC_READ			(0x1 << 28)
+#define GFX9_RLCG_VFGATE_DISABLED		0x4000000
+#define GFX9_RLCG_WRONG_OPERATION_TYPE		0x2000000
+#define GFX9_RLCG_NOT_IN_RANGE			0x1000000
+
 MODULE_FIRMWARE("amdgpu/vega10_ce.bin");
 MODULE_FIRMWARE("amdgpu/vega10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/vega10_me.bin");
@@ -739,7 +746,7 @@ static const u32 GFX_RLC_SRM_INDEX_CNTL_DATA_OFFSETS[] =
 	mmRLC_SRM_INDEX_CNTL_DATA_7 - mmRLC_SRM_INDEX_CNTL_DATA_0,
 };
 
-static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag)
+static u32 gfx_v9_0_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32_t flag)
 {
 	static void *scratch_reg0;
 	static void *scratch_reg1;
@@ -748,21 +755,20 @@ static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 	static void *spare_int;
 	static uint32_t grbm_cntl;
 	static uint32_t grbm_idx;
+	uint32_t i = 0;
+	uint32_t retries = 50000;
+	u32 ret = 0;
+	u32 tmp;
 
 	scratch_reg0 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0)*4;
 	scratch_reg1 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG1)*4;
-	scratch_reg2 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG2)*4;
-	scratch_reg3 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG3)*4;
+	scratch_reg2 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG2_BASE_IDX] + mmSCRATCH_REG2)*4;
+	scratch_reg3 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG3_BASE_IDX] + mmSCRATCH_REG3)*4;
 	spare_int = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmRLC_SPARE_INT_BASE_IDX] + mmRLC_SPARE_INT)*4;
 
 	grbm_cntl = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_CNTL_BASE_IDX] + mmGRBM_GFX_CNTL;
 	grbm_idx = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_INDEX_BASE_IDX] + mmGRBM_GFX_INDEX;
 
-	if (amdgpu_sriov_runtime(adev)) {
-		pr_err("shouldn't call rlcg write register during runtime\n");
-		return;
-	}
-
 	if (offset == grbm_cntl || offset == grbm_idx) {
 		if (offset  == grbm_cntl)
 			writel(v, scratch_reg2);
@@ -771,41 +777,95 @@ static void gfx_v9_0_rlcg_w(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
 
 		writel(v, ((void __iomem *)adev->rmmio) + (offset * 4));
 	} else {
-		uint32_t i = 0;
-		uint32_t retries = 50000;
-
+		/*
+		 * SCRATCH_REG0 	= read/write value
+		 * SCRATCH_REG1[30:28]	= command
+		 * SCRATCH_REG1[19:0]	= address in dword
+		 * SCRATCH_REG1[26:24]	= Error reporting
+		 */
 		writel(v, scratch_reg0);
-		writel(offset | 0x80000000, scratch_reg1);
+		writel(offset | flag, scratch_reg1);
 		writel(1, spare_int);
-		for (i = 0; i < retries; i++) {
-			u32 tmp;
 
+		for (i = 0; i < retries; i++) {
 			tmp = readl(scratch_reg1);
-			if (!(tmp & 0x80000000))
+			if (!(tmp & flag))
 				break;
 
 			udelay(10);
 		}
-		if (i >= retries)
-			pr_err("timeout: rlcg program reg:0x%05x failed !\n", offset);
+
+		if (i >= retries) {
+			if (amdgpu_sriov_reg_indirect_gc(adev)) {
+				if (tmp & GFX9_RLCG_VFGATE_DISABLED)
+					pr_err("The vfgate is disabled, program reg:0x%05x failed!\n", offset);
+				else if (tmp & GFX9_RLCG_WRONG_OPERATION_TYPE)
+					pr_err("Wrong operation type, program reg:0x%05x failed!\n", offset);
+				else if (tmp & GFX9_RLCG_NOT_IN_RANGE)
+					pr_err("The register is not in range, program reg:0x%05x failed!\n", offset);
+				else
+					pr_err("Unknown error type, program reg:0x%05x failed!\n", offset);
+			} else
+				pr_err("timeout: rlcg program reg:0x%05x failed!\n", offset);
+		}
 	}
 
+	ret = readl(scratch_reg0);
+
+	return ret;
+}
+
+static bool gfx_v9_0_get_rlcg_flag(struct amdgpu_device *adev, u32 acc_flags, u32 hwip,
+				int write, u32 *rlcg_flag)
+{
+
+	switch (hwip) {
+	case GC_HWIP:
+		if (amdgpu_sriov_reg_indirect_gc(adev)) {
+			*rlcg_flag = write ? GFX9_RLCG_GC_WRITE : GFX9_RLCG_GC_READ;
+
+			return true;
+		/* only in new version, AMDGPU_REGS_NO_KIQ and AMDGPU_REGS_RLC enabled simultaneously */
+		} else if ((acc_flags & AMDGPU_REGS_RLC) && !(acc_flags & AMDGPU_REGS_NO_KIQ) && write) {
+			*rlcg_flag = GFX9_RLCG_GC_WRITE_OLD;
+			return true;
+		}
+
+		break;
+	default:
+		return false;
+	}
+
+	return false;
+}
+
+static u32 gfx_v9_0_sriov_rreg(struct amdgpu_device *adev, u32 offset, u32 acc_flags, u32 hwip)
+{
+	u32 rlcg_flag;
+
+	if (!amdgpu_sriov_runtime(adev) && gfx_v9_0_get_rlcg_flag(adev, acc_flags, hwip, 0, &rlcg_flag))
+		return gfx_v9_0_rlcg_rw(adev, offset, 0, rlcg_flag);
+
+	if (acc_flags & AMDGPU_REGS_NO_KIQ)
+		return RREG32_NO_KIQ(offset);
+	else
+		return RREG32(offset);
 }
 
 static void gfx_v9_0_sriov_wreg(struct amdgpu_device *adev, u32 offset,
-			       u32 v, u32 acc_flags, u32 hwip)
+			       u32 value, u32 acc_flags, u32 hwip)
 {
-	if ((acc_flags & AMDGPU_REGS_RLC) &&
-	    amdgpu_sriov_fullaccess(adev)) {
-		gfx_v9_0_rlcg_w(adev, offset, v, acc_flags);
+	u32 rlcg_flag;
 
+	if (!amdgpu_sriov_runtime(adev) && gfx_v9_0_get_rlcg_flag(adev, acc_flags, hwip, 1, &rlcg_flag)) {
+		gfx_v9_0_rlcg_rw(adev, offset, value, rlcg_flag);
 		return;
 	}
 
 	if (acc_flags & AMDGPU_REGS_NO_KIQ)
-		WREG32_NO_KIQ(offset, v);
+		WREG32_NO_KIQ(offset, value);
 	else
-		WREG32(offset, v);
+		WREG32(offset, value);
 }
 
 #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042
@@ -5135,7 +5195,7 @@ static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
 	else
-		data = RREG32(reg);
+		data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
 
 	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
@@ -5191,6 +5251,7 @@ static const struct amdgpu_rlc_funcs gfx_v9_0_rlc_funcs = {
 	.start = gfx_v9_0_rlc_start,
 	.update_spm_vmid = gfx_v9_0_update_spm_vmid,
 	.sriov_wreg = gfx_v9_0_sriov_wreg,
+	.sriov_rreg = gfx_v9_0_sriov_rreg,
 	.is_rlcg_access_range = gfx_v9_0_is_rlcg_access_range,
 };
 
@@ -5796,16 +5857,16 @@ static void gfx_v9_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev,
 
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_SOC15_IP(GC,mec_int_cntl_reg);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 0);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_SOC15_IP(GC, mec_int_cntl_reg, mec_int_cntl);
 		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_SOC15_IP(GC, mec_int_cntl_reg);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 1);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_SOC15_IP(GC, mec_int_cntl_reg, mec_int_cntl);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index ae46eb35b3d7..3d5d47a799e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -914,12 +914,6 @@ static int gmc_v10_0_sw_init(void *handle)
 		return r;
 	}
 
-	if (adev->gmc.xgmi.supported) {
-		r = adev->gfxhub.funcs->get_xgmi_info(adev);
-		if (r)
-			return r;
-	}
-
 	r = gmc_v10_0_mc_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 492ebed2915b..63b890f1e8af 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -515,10 +515,10 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev)
 static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 {
 	int r;
+	u32 tmp;
 
 	adev->gmc.vram_width = amdgpu_atombios_get_vram_width(adev);
 	if (!adev->gmc.vram_width) {
-		u32 tmp;
 		int chansize, numchan;
 
 		/* Get VRAM informations */
@@ -562,8 +562,15 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 		adev->gmc.vram_width = numchan * chansize;
 	}
 	/* size in MB on si */
-	adev->gmc.mc_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
-	adev->gmc.real_vram_size = RREG32(mmCONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+	tmp = RREG32(mmCONFIG_MEMSIZE);
+	/* some boards may have garbage in the upper 16 bits */
+	if (tmp & 0xffff0000) {
+		DRM_INFO("Probable bad vram size: 0x%08x\n", tmp);
+		if (tmp & 0xffff)
+			tmp &= 0xffff;
+	}
+	adev->gmc.mc_vram_size = tmp * 1024ULL * 1024ULL;
+	adev->gmc.real_vram_size = adev->gmc.mc_vram_size;
 
 	if (!(adev->flags & AMD_IS_APU)) {
 		r = amdgpu_device_resize_fb_bar(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index a5471923b3f6..57f2729a7bd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -478,9 +478,18 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 			hub = &adev->vmhub[j];
 			for (i = 0; i < 16; i++) {
 				reg = hub->vm_context0_cntl + i;
-				tmp = RREG32(reg);
+
+				if (j == AMDGPU_GFXHUB_0)
+					tmp = RREG32_SOC15_IP(GC, reg);
+				else
+					tmp = RREG32_SOC15_IP(MMHUB, reg);
+
 				tmp &= ~bits;
-				WREG32(reg, tmp);
+
+				if (j == AMDGPU_GFXHUB_0)
+					WREG32_SOC15_IP(GC, reg, tmp);
+				else
+					WREG32_SOC15_IP(MMHUB, reg, tmp);
 			}
 		}
 		break;
@@ -489,9 +498,18 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 			hub = &adev->vmhub[j];
 			for (i = 0; i < 16; i++) {
 				reg = hub->vm_context0_cntl + i;
-				tmp = RREG32(reg);
+
+				if (j == AMDGPU_GFXHUB_0)
+					tmp = RREG32_SOC15_IP(GC, reg);
+				else
+					tmp = RREG32_SOC15_IP(MMHUB, reg);
+
 				tmp |= bits;
-				WREG32(reg, tmp);
+
+				if (j == AMDGPU_GFXHUB_0)
+					WREG32_SOC15_IP(GC, reg, tmp);
+				else
+					WREG32_SOC15_IP(MMHUB, reg, tmp);
 			}
 		}
 		break;
@@ -788,9 +806,12 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
 	if (use_semaphore) {
 		for (j = 0; j < adev->usec_timeout; j++) {
-			/* a read return value of 1 means semaphore acuqire */
-			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-					    hub->eng_distance * eng);
+			/* a read return value of 1 means semaphore acquire */
+			if (vmhub == AMDGPU_GFXHUB_0)
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_sem + hub->eng_distance * eng);
+			else
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_sem + hub->eng_distance * eng);
+
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -801,8 +822,10 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	}
 
 	do {
-		WREG32_NO_KIQ(hub->vm_inv_eng0_req +
-			      hub->eng_distance * eng, inv_req);
+		if (vmhub == AMDGPU_GFXHUB_0)
+			WREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
+		else
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_req + hub->eng_distance * eng, inv_req);
 
 		/*
 		 * Issue a dummy read to wait for the ACK register to
@@ -815,8 +838,11 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 				      hub->eng_distance * eng);
 
 		for (j = 0; j < adev->usec_timeout; j++) {
-			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_ack +
-					    hub->eng_distance * eng);
+			if (vmhub == AMDGPU_GFXHUB_0)
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_ack + hub->eng_distance * eng);
+			else
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_ack + hub->eng_distance * eng);
+
 			if (tmp & (1 << vmid))
 				break;
 			udelay(1);
@@ -827,13 +853,16 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	} while (inv_req);
 
 	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
-	if (use_semaphore)
+	if (use_semaphore) {
 		/*
 		 * add semaphore release after invalidation,
 		 * write with 0 means semaphore release
 		 */
-		WREG32_NO_KIQ(hub->vm_inv_eng0_sem +
-			      hub->eng_distance * eng, 0);
+		if (vmhub == AMDGPU_GFXHUB_0)
+			WREG32_SOC15_IP_NO_KIQ(GC, hub->vm_inv_eng0_sem + hub->eng_distance * eng, 0);
+		else
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, hub->vm_inv_eng0_sem + hub->eng_distance * eng, 0);
+	}
 
 	spin_unlock(&adev->gmc.invalidate_lock);
 
@@ -1599,12 +1628,6 @@ static int gmc_v9_0_sw_init(void *handle)
 	}
 	adev->need_swiotlb = drm_need_swiotlb(44);
 
-	if (adev->gmc.xgmi.supported) {
-		r = adev->gfxhub.funcs->get_xgmi_info(adev);
-		if (r)
-			return r;
-	}
-
 	r = gmc_v9_0_mc_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 2176ef85f137..d0e76b36d4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -277,13 +277,15 @@ static bool psp_v11_0_is_sos_alive(struct psp_context *psp)
 	return sol_reg != 0x0;
 }
 
-static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
+static int psp_v11_0_bootloader_load_component(struct psp_context  	*psp,
+					       struct psp_bin_desc 	*bin_desc,
+					       enum psp_bootloader_cmd  bl_cmd)
 {
 	int ret;
 	uint32_t psp_gfxdrv_command_reg = 0;
 	struct amdgpu_device *adev = psp->adev;
 
-	/* Check tOS sign of life register to confirm sys driver and sOS
+	/* Check sOS sign of life register to confirm sys driver and sOS
 	 * are already been loaded.
 	 */
 	if (psp_v11_0_is_sos_alive(psp))
@@ -293,13 +295,13 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	/* Copy PSP KDB binary to memory */
-	psp_copy_fw(psp, psp->kdb.start_addr, psp->kdb.size_bytes);
+	/* Copy PSP System Driver binary to memory */
+	psp_copy_fw(psp, bin_desc->start_addr, bin_desc->size_bytes);
 
-	/* Provide the PSP KDB to bootloader */
+	/* Provide the sys driver to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
 	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
-	psp_gfxdrv_command_reg = PSP_BL__LOAD_KEY_DATABASE;
+	psp_gfxdrv_command_reg = bl_cmd;
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35,
 	       psp_gfxdrv_command_reg);
 
@@ -308,69 +310,19 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 	return ret;
 }
 
-static int psp_v11_0_bootloader_load_spl(struct psp_context *psp)
+static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 {
-	int ret;
-	uint32_t psp_gfxdrv_command_reg = 0;
-	struct amdgpu_device *adev = psp->adev;
-
-	/* Check tOS sign of life register to confirm sys driver and sOS
-	 * are already been loaded.
-	 */
-	if (psp_v11_0_is_sos_alive(psp))
-		return 0;
-
-	ret = psp_v11_0_wait_for_bootloader(psp);
-	if (ret)
-		return ret;
-
-	/* Copy PSP SPL binary to memory */
-	psp_copy_fw(psp, psp->spl.start_addr, psp->spl.size_bytes);
-
-	/* Provide the PSP SPL to bootloader */
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
-	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
-	psp_gfxdrv_command_reg = PSP_BL__LOAD_TOS_SPL_TABLE;
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35,
-	       psp_gfxdrv_command_reg);
-
-	ret = psp_v11_0_wait_for_bootloader(psp);
+	return psp_v11_0_bootloader_load_component(psp, &psp->kdb, PSP_BL__LOAD_KEY_DATABASE);
+}
 
-	return ret;
+static int psp_v11_0_bootloader_load_spl(struct psp_context *psp)
+{
+	return psp_v11_0_bootloader_load_component(psp, &psp->spl, PSP_BL__LOAD_TOS_SPL_TABLE);
 }
 
 static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 {
-	int ret;
-	uint32_t psp_gfxdrv_command_reg = 0;
-	struct amdgpu_device *adev = psp->adev;
-
-	/* Check sOS sign of life register to confirm sys driver and sOS
-	 * are already been loaded.
-	 */
-	if (psp_v11_0_is_sos_alive(psp))
-		return 0;
-
-	ret = psp_v11_0_wait_for_bootloader(psp);
-	if (ret)
-		return ret;
-
-	/* Copy PSP System Driver binary to memory */
-	psp_copy_fw(psp, psp->sys.start_addr, psp->sys.size_bytes);
-
-	/* Provide the sys driver to bootloader */
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
-	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
-	psp_gfxdrv_command_reg = PSP_BL__LOAD_SYSDRV;
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35,
-	       psp_gfxdrv_command_reg);
-
-	/* there might be handshake issue with hardware which needs delay */
-	mdelay(20);
-
-	ret = psp_v11_0_wait_for_bootloader(psp);
-
-	return ret;
+	return psp_v11_0_bootloader_load_component(psp, &psp->sys, PSP_BL__LOAD_SYSDRV);
 }
 
 static int psp_v11_0_bootloader_load_sos(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 4f546f632223..d3d6d5b045b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -542,9 +542,6 @@ static void sdma_v5_2_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 	}
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
-		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
-				AUTO_CTXSW_ENABLE, enable ? 1 : 0);
 		if (enable && amdgpu_sdma_phase_quantum) {
 			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE0_QUANTUM),
 			       phase_quantum);
@@ -553,7 +550,13 @@ static void sdma_v5_2_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_PHASE2_QUANTUM),
 			       phase_quantum);
 		}
-		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
+
+		if (!amdgpu_sriov_vf(adev)) {
+			f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
+					AUTO_CTXSW_ENABLE, enable ? 1 : 0);
+			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), f32_cntl);
+		}
 	}
 
 }
@@ -576,10 +579,12 @@ static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable)
 		sdma_v5_2_rlc_stop(adev);
 	}
 
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
-		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, enable ? 0 : 1);
-		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), f32_cntl);
+	if (!amdgpu_sriov_vf(adev)) {
+		for (i = 0; i < adev->sdma.num_instances; i++) {
+			f32_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
+			f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, enable ? 0 : 1);
+			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), f32_cntl);
+		}
 	}
 }
 
@@ -608,7 +613,8 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 		ring = &adev->sdma.instance[i].ring;
 		wb_offset = (ring->rptr_offs * 4);
 
-		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
+		if (!amdgpu_sriov_vf(adev))
+			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_SEM_WAIT_FAIL_TIMER_CNTL), 0);
 
 		/* Set ring buffer size in dwords */
 		rb_bufsz = order_base_2(ring->ring_size / 4);
@@ -683,32 +689,34 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 			sdma_v5_2_ring_set_wptr(ring);
 
 		/* set minor_ptr_update to 0 after wptr programed */
-		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
 
-		/* set utc l1 enable flag always to 1 */
-		temp = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
-		temp = REG_SET_FIELD(temp, SDMA0_CNTL, UTC_L1_ENABLE, 1);
-
-		/* enable MCBP */
-		temp = REG_SET_FIELD(temp, SDMA0_CNTL, MIDCMD_PREEMPT_ENABLE, 1);
-		WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), temp);
-
-		/* Set up RESP_MODE to non-copy addresses */
-		temp = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_CNTL));
-		temp = REG_SET_FIELD(temp, SDMA0_UTCL1_CNTL, RESP_MODE, 3);
-		temp = REG_SET_FIELD(temp, SDMA0_UTCL1_CNTL, REDO_DELAY, 9);
-		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_CNTL), temp);
-
-		/* program default cache read and write policy */
-		temp = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_PAGE));
-		/* clean read policy and write policy bits */
-		temp &= 0xFF0FFF;
-		temp |= ((CACHE_READ_POLICY_L2__DEFAULT << 12) |
-			 (CACHE_WRITE_POLICY_L2__DEFAULT << 14) |
-			 SDMA0_UTCL1_PAGE__LLC_NOALLOC_MASK);
-		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_PAGE), temp);
+		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 0);
 
+		/* SRIOV VF has no control of any of registers below */
 		if (!amdgpu_sriov_vf(adev)) {
+			/* set utc l1 enable flag always to 1 */
+			temp = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL));
+			temp = REG_SET_FIELD(temp, SDMA0_CNTL, UTC_L1_ENABLE, 1);
+
+			/* enable MCBP */
+			temp = REG_SET_FIELD(temp, SDMA0_CNTL, MIDCMD_PREEMPT_ENABLE, 1);
+			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_CNTL), temp);
+
+			/* Set up RESP_MODE to non-copy addresses */
+			temp = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_CNTL));
+			temp = REG_SET_FIELD(temp, SDMA0_UTCL1_CNTL, RESP_MODE, 3);
+			temp = REG_SET_FIELD(temp, SDMA0_UTCL1_CNTL, REDO_DELAY, 9);
+			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_CNTL), temp);
+
+			/* program default cache read and write policy */
+			temp = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_PAGE));
+			/* clean read policy and write policy bits */
+			temp &= 0xFF0FFF;
+			temp |= ((CACHE_READ_POLICY_L2__DEFAULT << 12) |
+				 (CACHE_WRITE_POLICY_L2__DEFAULT << 14) |
+				 SDMA0_UTCL1_PAGE__LLC_NOALLOC_MASK);
+			WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_UTCL1_PAGE), temp);
+
 			/* unhalt engine */
 			temp = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
 			temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
@@ -1436,13 +1444,14 @@ static int sdma_v5_2_set_trap_irq_state(struct amdgpu_device *adev,
 					enum amdgpu_interrupt_state state)
 {
 	u32 sdma_cntl;
-
 	u32 reg_offset = sdma_v5_2_get_reg_offset(adev, type, mmSDMA0_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/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 8a9ca87d8663..473767e03676 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -51,6 +51,8 @@
 
 #define RREG32_SOC15_IP(ip, reg) __RREG32_SOC15_RLC__(reg, 0, ip##_HWIP)
 
+#define RREG32_SOC15_IP_NO_KIQ(ip, reg) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP)
+
 #define RREG32_SOC15_NO_KIQ(ip, inst, reg) \
 	__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
 			 AMDGPU_REGS_NO_KIQ, ip##_HWIP)
@@ -65,6 +67,9 @@
 #define WREG32_SOC15_IP(ip, reg, value) \
 	 __WREG32_SOC15_RLC__(reg, value, 0, ip##_HWIP)
 
+#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value) \
+	 __WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP)
+
 #define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
 	__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
 			     value, AMDGPU_REGS_NO_KIQ, ip##_HWIP)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index d54d720b3cf6..3799226defc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -246,6 +246,13 @@ static int vcn_v1_0_suspend(void *handle)
 {
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool idle_work_unexecuted;
+
+	idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work);
+	if (idle_work_unexecuted) {
+		if (adev->pm.dpm_enabled)
+			amdgpu_dpm_enable_uvd(adev, false);
+	}
 
 	r = vcn_v1_0_hw_fini(adev);
 	if (r)