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

83 files changed, 1814 insertions, 747 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-&g