diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
38 files changed, 706 insertions, 535 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..6ca1db3c243f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -514,13 +514,6 @@ out_put: return r; } -uint64_t amdgpu_amdkfd_get_vram_usage(struct amdgpu_device *adev) -{ - struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); - - return amdgpu_vram_mgr_usage(vram_man); -} - uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst, struct amdgpu_device *src) { @@ -721,13 +714,13 @@ 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..ac841ae8f5cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -223,7 +223,6 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd, uint64_t *bo_size, void *metadata_buffer, size_t buffer_size, uint32_t *metadata_size, uint32_t *flags); -uint64_t amdgpu_amdkfd_get_vram_usage(struct amdgpu_device *adev); uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst, struct amdgpu_device *src); int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst, @@ -296,7 +295,8 @@ 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_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 0311d799a010..06d07502a1f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -298,7 +298,6 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev, { s64 time_us, increment_us; u64 free_vram, total_vram, used_vram; - struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); /* Allow a maximum of 200 accumulated ms. This is basically per-IB * throttling. * @@ -315,7 +314,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev, } total_vram = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size); - used_vram = amdgpu_vram_mgr_usage(vram_man); + used_vram = amdgpu_vram_mgr_usage(&adev->mman.vram_mgr); free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram; spin_lock(&adev->mm_stats.lock); @@ -362,7 +361,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev, if (!amdgpu_gmc_vram_full_visible(&adev->gmc)) { u64 total_vis_vram = adev->gmc.visible_vram_size; u64 used_vis_vram = - amdgpu_vram_mgr_vis_usage(vram_man); + amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr); if (used_vis_vram < total_vis_vram) { u64 free_vis_vram = total_vis_vram - used_vis_vram; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8219e40240ce..cf7fad88c138 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -552,7 +552,7 @@ void amdgpu_device_wreg(struct amdgpu_device *adev, } /** - * amdgpu_mm_wreg_mmio_rlc - write register either with mmio or with RLC path if in range + * amdgpu_mm_wreg_mmio_rlc - write register either with direct/indirect mmio or with RLC path if in range * * this function is invoked only the debugfs register access */ @@ -567,6 +567,8 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, adev->gfx.rlc.funcs->is_rlcg_access_range) { if (adev->gfx.rlc.funcs->is_rlcg_access_range(adev, reg)) return adev->gfx.rlc.funcs->sriov_wreg(adev, reg, v, 0, 0); + } else if ((reg * 4) >= adev->rmmio_size) { + adev->pcie_wreg(adev, reg * 4, v); } else { writel(v, ((void __iomem *)adev->rmmio) + (reg * 4)); } @@ -1448,7 +1450,7 @@ static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev) adev->apu_flags |= AMD_APU_IS_CYAN_SKILLFISH2; break; default: - return -EINVAL; + break; } return 0; @@ -2317,6 +2319,10 @@ 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 +2354,7 @@ 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 +2621,10 @@ 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 +3187,12 @@ 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: @@ -3487,9 +3498,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, mutex_init(&adev->psp.mutex); mutex_init(&adev->notifier_lock); - r = amdgpu_device_init_apu_flags(adev); - if (r) - return r; + amdgpu_device_init_apu_flags(adev); r = amdgpu_device_check_arguments(adev); if (r) @@ -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 *) @@ -3817,6 +3833,7 @@ failed: static void amdgpu_device_unmap_mmio(struct amdgpu_device *adev) { + /* Clear all CPU mappings pointing to this device */ unmap_mapping_range(adev->ddev.anon_inode->i_mapping, 0, 0, 1); @@ -3885,15 +3902,20 @@ 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) { + int idx; + amdgpu_fence_driver_sw_fini(adev); amdgpu_device_ip_fini(adev); release_firmware(adev->firmware.gpu_info_fw); @@ -3918,6 +3940,14 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA) vga_client_unregister(adev->pdev); + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + + iounmap(adev->rmmio); + adev->rmmio = NULL; + amdgpu_device_doorbell_fini(adev); + drm_dev_exit(idx); + } + if (IS_ENABLED(CONFIG_PERF_EVENTS)) amdgpu_pmu_fini(adev); if (adev->mman.discovery_bin) @@ -3938,8 +3968,8 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) */ static void amdgpu_device_evict_resources(struct amdgpu_device *adev) { - /* No need to evict vram on APUs for suspend to ram */ - if (adev->in_s3 && (adev->flags & AMD_IS_APU)) + /* No need to evict vram on APUs for suspend to ram or s2idle */ + if ((adev->in_s3 || adev->in_s0ix) && (adev->flags & AMD_IS_APU)) return; if (amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM)) @@ -3986,16 +4016,11 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) if (!adev->in_s0ix) amdgpu_amdkfd_suspend(adev, adev->in_runpm); - /* First evict vram memory */ amdgpu_device_evict_resources(adev); amdgpu_fence_driver_hw_fini(adev); amdgpu_device_ip_suspend_phase2(adev); - /* This second call to evict device resources is to evict - * the gart page table using the CPU. - */ - amdgpu_device_evict_resources(adev); return 0; } @@ -4340,8 +4365,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, goto error; amdgpu_virt_init_data_exchange(adev); - /* we need recover gart prior to run SMC/CP/SDMA resume */ - amdgpu_gtt_mgr_recover(ttm_manager_type(&adev->mman.bdev, TTM_PL_TT)); r = amdgpu_device_fw_loading(adev); if (r) @@ -4507,7 +4530,7 @@ 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 +4552,8 @@ 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); } @@ -4668,10 +4684,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, amdgpu_inc_vram_lost(tmp_adev); } - r = amdgpu_gtt_mgr_recover(ttm_manager_type(&tmp_adev->mman.bdev, TTM_PL_TT)); - if (r) - goto out; - r = amdgpu_device_fw_loading(tmp_adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 5bc072220f03..be45650250fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -550,7 +550,8 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) } /* some IP discovery tables on Navy Flounder don't have this set correctly */ if ((adev->ip_versions[UVD_HWIP][1] == IP_VERSION(3, 0, 1)) && - (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2))) + (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2)) && + (adev->pdev->revision != 0xFF)) adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1; if (vcn_harvest_count == adev->vcn.num_vcn_inst) { adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; @@ -565,10 +566,15 @@ 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 +582,55 @@ 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 +1025,7 @@ 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_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 4896c876ffec..579adfafe4d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -381,7 +381,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) struct amdgpu_vm_bo_base *bo_base; int r; - if (bo->tbo.resource->mem_type == TTM_PL_SYSTEM) + if (!bo->tbo.resource || bo->tbo.resource->mem_type == TTM_PL_SYSTEM) return; r = ttm_bo_validate(&bo->tbo, &placement, &ctx); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 02099058d0d6..366e475056bd 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); /** @@ -2165,10 +2166,13 @@ static int amdgpu_pmops_suspend(struct device *dev) if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; - adev->in_s3 = true; + else + 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; } @@ -2185,6 +2189,8 @@ static int amdgpu_pmops_resume(struct device *dev) r = amdgpu_device_resume(drm_dev, true); if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = false; + else + adev->in_s3 = false; return r; } @@ -2249,12 +2255,27 @@ 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_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index d3e4203f6217..645950a653a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -114,80 +114,12 @@ void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev) */ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev) { - int r; - - if (adev->gart.bo == NULL) { - struct amdgpu_bo_param bp; - - memset(&bp, 0, sizeof(bp)); - bp.size = adev->gart.table_size; - bp.byte_align = PAGE_SIZE; - bp.domain = AMDGPU_GEM_DOMAIN_VRAM; - bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | - AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - bp.type = ttm_bo_type_kernel; - bp.resv = NULL; - bp.bo_ptr_size = sizeof(struct amdgpu_bo); - - r = amdgpu_bo_create(adev, &bp, &adev->gart.bo); - if (r) { - return r; - } - } - return 0; -} - -/** - * amdgpu_gart_table_vram_pin - pin gart page table in vram - * - * @adev: amdgpu_device pointer - * - * Pin the GART page table in vram so it will not be moved - * by the memory manager (pcie r4xx, r5xx+). These asics require the - * gart table to be in video memory. - * Returns 0 for success, error for failure. - */ -int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gart.bo, false); - if (unlikely(r != 0)) - return r; - r = amdgpu_bo_pin(adev->gart.bo, AMDGPU_GEM_DOMAIN_VRAM); - if (r) { - amdgpu_bo_unreserve(adev->gart.bo); - return r; - } - r = amdgpu_bo_kmap(adev->gart.bo, &adev->gart.ptr); - if (r) - amdgpu_bo_unpin(adev->gart.bo); - amdgpu_bo_unreserve(adev->gart.bo); - return r; -} - -/** - * amdgpu_gart_table_vram_unpin - unpin gart page table in vram - * - * @adev: amdgpu_device pointer - * - * Unpin the GART page table in vram (pcie r4xx, r5xx+). - * These asics require the gart table to be in video memory. - */ -void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev) -{ - int r; + if (adev->gart.bo != NULL) + return 0; - if (adev->gart.bo == NULL) { - return; - } - r = amdgpu_bo_reserve(adev->gart.bo, true); - if (likely(r == 0)) { - amdgpu_bo_kunmap(adev->gart.bo); - amdgpu_bo_unpin(adev->gart.bo); - amdgpu_bo_unreserve(adev->gart.bo); - adev->gart.ptr = NULL; - } + return amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, + NULL, (void *)&adev->gart.ptr); } /** @@ -201,11 +133,7 @@ void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev) */ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev) { - if (adev->gart.bo == NULL) { - return; - } - amdgpu_bo_unref(&adev->gart.bo); - adev->gart.ptr = NULL; + amdgpu_bo_free_kernel(&adev->gart.bo, NULL, (void *)&adev->gart.ptr); } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index 675a72ef305d..72022df264f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -77,10 +77,8 @@ static ssize_t amdgpu_mem_info_gtt_used_show(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - struct ttm_resource_manager *man; - man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT); - return sysfs_emit(buf, "%llu\n", amdgpu_gtt_mgr_usage(man)); + return sysfs_emit(buf, "%llu\n", amdgpu_gtt_mgr_usage(&adev->mman.gtt_mgr)); } static DEVICE_ATTR(mem_info_gtt_total, S_IRUGO, @@ -206,30 +204,27 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, /** * amdgpu_gtt_mgr_usage - return usage of GTT domain * - * @man: TTM memory type manager + * @mgr: amdgpu_gtt_mgr pointer * * Return how many bytes are used in the GTT domain */ -uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man) +uint64_t amdgpu_gtt_mgr_usage(struct amdgpu_gtt_mgr *mgr) { - struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); - return atomic64_read(&mgr->used) * PAGE_SIZE; } /** * amdgpu_gtt_mgr_recover - re-init gart * - * @man: TTM memory type manager + * @mgr: amdgpu_gtt_mgr pointer * * Re-init the gart for each known BO in the GTT. */ -int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man) +int amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr) { - struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); - struct amdgpu_device *adev; struct amdgpu_gtt_node *node; struct drm_mm_node *mm_node; + struct amdgpu_device *adev; int r = 0; adev = container_of(mgr, typeof(*adev), mman.gtt_mgr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 651c7abfde03..289521aafb79 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -672,13 +672,13 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ui64 = atomic64_read(&adev->num_vram_cpu_page_faults); return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_VRAM_USAGE: - ui64 = amdgpu_vram_mgr_usage(ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM)); + ui64 = amdgpu_vram_mgr_usage(&adev->mman.vram_mgr); return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_VIS_VRAM_USAGE: - ui64 = amdgpu_vram_mgr_vis_usage(ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM)); + ui64 = amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr); return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_GTT_USAGE: - ui64 = amdgpu_gtt_mgr_usage(ttm_manager_type(&adev->mman.bdev, TTM_PL_TT)); + ui64 = amdgpu_gtt_mgr_usage(&adev->mman.gtt_mgr); return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_GDS_CONFIG: { struct drm_amdgpu_info_gds gds_info; @@ -709,8 +709,6 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) } case AMDGPU_INFO_MEMORY: { struct drm_amdgpu_memory_info mem; - struct ttm_resource_manager *vram_man = - ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); struct ttm_resource_manager *gtt_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT); memset(&mem, 0, sizeof(mem)); @@ -719,7 +717,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) atomic64_read(&adev->vram_pin_size) - AMDGPU_VM_RESERVED_VRAM; mem.vram.heap_usage = - amdgpu_vram_mgr_usage(vram_man); + amdgpu_vram_mgr_usage(&adev->mman.vram_mgr); mem.vram.max_allocation = mem.vram.usable_heap_size * 3 / 4; mem.cpu_accessible_vram.total_heap_size = @@ -729,7 +727,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) atomic64_read(&adev->visible_pin_size), mem.vram.usable_heap_size); mem.cpu_accessible_vram.heap_usage = - amdgpu_vram_mgr_vis_usage(vram_man); + amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr); mem.cpu_accessible_vram.max_allocation = mem.cpu_accessible_vram.usable_heap_size * 3 / 4; @@ -738,7 +736,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) mem.gtt.usable_heap_size = mem.gtt.total_heap_size - atomic64_read(&adev->gart_pin_size); mem.gtt.heap_usage = - amdgpu_gtt_mgr_usage(gtt_man); + amdgpu_gtt_mgr_usage(&adev->mman.gtt_mgr); mem.gtt.max_allocation = mem.gtt.usable_heap_size * 3 / 4; return copy_to_user(out, &mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 3a7b56e57cec..5661b82d84d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/dma-buf.h> +#include <drm/drm_drv.h> #include <drm/amdgpu_drm.h> #include <drm/drm_cache.h> #include "amdgpu.h" @@ -1061,7 +1062,18 @@ int amdgpu_bo_init(struct amdgpu_device *adev) */ void amdgpu_bo_fini(struct amdgpu_device *adev) { + int idx; + amdgpu_ttm_fini(adev); + + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + + if (!adev->gmc.xgmi.connected_to_cpu) { + arch_phys_wc_del(adev->gmc.vram_mtrr); + arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size); + } + drm_dev_exit(idx); + } } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index cd9e5914944b..586a30ad13e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1592,6 +1592,7 @@ static void amdgpu_ras_interrupt_handler(struct ras_manager *obj) /* Let IP handle its data, maybe we need get the output * from the callback to udpate the error type/count, etc */ + memset(&err_data, 0, sizeof(err_data)); ret = data->cb(obj->adev, &err_data, &entry); /* ue will trigger an interrupt, and in that case * we need do a reset to recovery the whole system. @@ -1838,8 +1839,7 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev, .size = AMDGPU_GPU_PAGE_SIZE, .flags = AMDGPU_RAS_RETIRE_PAGE_RESERVED, }; - status = amdgpu_vram_mgr_query_page_status( - ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM), + status = amdgpu_vram_mgr_query_page_status(&adev->mman.vram_mgr, data->bps[i].retired_page); if (status == -EBUSY) (*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_PENDING; @@ -1940,8 +1940,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, goto out; } - amdgpu_vram_mgr_reserve_range( - ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM), + amdgpu_vram_mgr_reserve_range(&adev->mman.vram_mgr, bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT, AMDGPU_GPU_PAGE_SIZE); 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_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index fb0d8bffdce2..5c3f24069f2a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -43,6 +43,7 @@ #include <linux/sizes.h> #include <linux/module.h> +#include <drm/drm_drv.h> #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> @@ -1804,6 +1805,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) */ void amdgpu_ttm_fini(struct amdgpu_device *adev) { + int idx; if (!adev->mman.initialized) return; @@ -1818,6 +1820,15 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) NULL, NULL); amdgpu_ttm_fw_reserve_vram_fini(adev); + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + + if (adev->mman.aper_base_kaddr) + iounmap(adev->mman.aper_base_kaddr); + adev->mman.aper_base_kaddr = NULL; + + drm_dev_exit(idx); + } + amdgpu_vram_mgr_fini(adev); amdgpu_gtt_mgr_fini(adev); amdgpu_preempt_mgr_fini(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 7346ecff4438..f8f48be16d80 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -114,8 +114,8 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev); void amdgpu_vram_mgr_fini(struct amdgpu_device *adev); bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem); -uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man); -int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man); +uint64_t amdgpu_gtt_mgr_usage(struct amdgpu_gtt_mgr *mgr); +int amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr); uint64_t amdgpu_preempt_mgr_usage(struct ttm_resource_manager *man); @@ -129,11 +129,11 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, void amdgpu_vram_mgr_free_sgt(struct device *dev, enum dma_data_direction dir, struct sg_table *sgt); -uint64_t amdgpu_vram_mgr_usage(struct ttm_resource_manager *man); -uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_resource_manager *man); -int amdgpu_vram_mgr_reserve_range(struct ttm_resource_manager *man, +uint64_t amdgpu_vram_mgr_usage(struct amdgpu_vram_mgr *mgr); +uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr); +int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, uint64_t start, uint64_t size); -int amdgpu_vram_mgr_query_page_status(struct ttm_resource_manager *man, +int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); int amdgpu_ttm_init(struct amdgpu_device *adev); 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..894444ab0032 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -553,7 +553,6 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev) static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) { struct amd_sriov_msg_vf2pf_info *vf2pf_info; - struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); vf2pf_info = (struct amd_sriov_msg_vf2pf_info *) adev->virt.fw_reserve.p_vf2pf; @@ -576,8 +575,8 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) vf2pf_info->driver_cert = 0; vf2pf_info->os_info.all = 0; - vf2pf_info->fb_usage = amdgpu_vram_mgr_usage(vram_man) >> 20; - vf2pf_info->fb_vis_usage = amdgpu_vram_mgr_vis_usage(vram_man) >> 20; + vf2pf_info->fb_usage = amdgpu_vram_mgr_usage(&adev->mman.vram_mgr) >> 20; + vf2pf_info->fb_vis_usage = amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr) >> 20; vf2pf_info->fb_size = adev->gmc.real_vram_size >> 20; vf2pf_info->fb_vis_size = adev->gmc.visible_vram_size >> 20; @@ -622,19 +621,37 @@ 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 +680,10 @@ 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; @@ -715,6 +726,10 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) vi_set_virt_ops(adev); break; case CHIP_VEGA10: + soc15_set_virt_ops(adev); + /* send a dummy GPU_INIT_DATA request to host on vega10 */ + amdgpu_virt_request_init_data(adev); + break; case CHIP_VEGA20: case CHIP_ARCTURUS: case CHIP_ALDEBARAN: 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/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 2dcc68e04e84..d99c8779b51e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -144,15 +144,16 @@ static void amdgpu_vkms_crtc_atomic_disable(struct drm_crtc *crtc, static void amdgpu_vkms_crtc_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_state *state) { + unsigned long flags; if (crtc->state->event) { - spin_lock(&crtc->dev->event_lock); + spin_lock_irqsave(&crtc->dev->event_lock, flags); if (drm_crtc_vblank_get(crtc) != 0) drm_crtc_send_vblank_event(crtc, crtc->state->event); else drm_crtc_arm_vblank_event(crtc, crtc->state->event); - spin_unlock(&crtc->dev->event_lock); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); crtc->state->event = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 7b2b0980ec41..7a2b487db57c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -96,10 +96,9 @@ static ssize_t amdgpu_mem_info_vram_used_show(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - struct ttm_resource_manager *man; - man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); - return sysfs_emit(buf, "%llu\n", amdgpu_vram_mgr_usage(man)); + return sysfs_emit(buf, "%llu\n", + amdgpu_vram_mgr_usage(&adev->mman.vram_mgr)); } /** @@ -116,10 +115,9 @@ static ssize_t amdgpu_mem_info_vis_vram_used_show(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - struct ttm_resource_manager *man; - man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); - return sysfs_emit(buf, "%llu\n", amdgpu_vram_mgr_vis_usage(man)); + return sysfs_emit(buf, "%llu\n", + amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr)); } /** @@ -263,16 +261,15 @@ static void amdgpu_vram_mgr_do_reserve(struct ttm_resource_manager *man) /** * amdgpu_vram_mgr_reserve_range - Reserve a range from VRAM * - * @man: TTM memory type manager + * @mgr: amdgpu_vram_mgr pointer * @start: start address of the range in VRAM * @size: size of the range * - * Reserve memory from start addess with the specified size in VRAM + * Reserve memory from start address with the specified size in VRAM */ -int amdgpu_vram_mgr_reserve_range(struct ttm_resource_manager *man, +int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, uint64_t start, uint64_t size) { - struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_vram_reservation *rsv; rsv = kzalloc(sizeof(*rsv), GFP_KERNEL); @@ -285,7 +282,7 @@ int amdgpu_vram_mgr_reserve_range(struct ttm_resource_manager *man, spin_lock(&mgr->lock); list_add_tail(&mgr->reservations_pending, &rsv->node); - amdgpu_vram_mgr_do_reserve(man); + amdgpu_vram_mgr_do_reserve(&mgr->manager); spin_unlock(&mgr->lock); return 0; @@ -294,7 +291,7 @@ int amdgpu_vram_mgr_reserve_range(struct ttm_resource_manager *man, /** * amdgpu_vram_mgr_query_page_status - query the reservation status * - * @man: TTM memory type manager + * @mgr: amdgpu_vram_mgr pointer * @start: start address of a page in VRAM * * Returns: @@ -302,10 +299,9 @@ int amdgpu_vram_mgr_reserve_range(struct ttm_resource_manager *man, * 0: the page has been reserved * -ENOENT: the input page is not a reservation */ -int amdgpu_vram_mgr_query_page_status(struct ttm_resource_manager *man, +int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start) { - struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_vram_reservation *rsv; int ret; @@ -632,28 +628,24 @@ void amdgpu_vram_mgr_free_sgt(struct device *dev, /** * amdgpu_vram_mgr_usage - how many bytes are used in this domain * - * @man: TTM memory type manager + * @mgr: amdgpu_vram_mgr pointer * * Returns how many bytes are used in this domain. */ -uint64_t amdgpu_vram_mgr_usage(struct ttm_resource_manager *man) +uint64_t amdgpu_vram_mgr_usage(struct amdgpu_vram_mgr *mgr) { - struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); - return atomic64_read(&mgr->usage); } /** * amdgpu_vram_mgr_vis_usage - how many bytes are used in the visible part * - * @man: TTM memory type manager + * @mgr: amdgpu_vram_mgr pointer * * Returns how many bytes are used in the visible part of VRAM */ -uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_resource_manager *man) +uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr) { - struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); - return atomic64_read(&mgr->vis_usage); } @@ -675,8 +667,8 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man, spin_unlock(&mgr->lock); drm_printf(printer, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n", - man->size, amdgpu_vram_mgr_usage(man) >> 20, - amdgpu_vram_mgr_vis_usage(man) >> 20); + man->size, amdgpu_vram_mgr_usage(mgr) >> 20, + amdgpu_vram_mgr_vis_usage(mgr) >> 20); } static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index a38c6a747fa4..e8b8f28c2f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -208,6 +208,7 @@ static struct attribute *amdgpu_xgmi_hive_attrs[] = { &amdgpu_xgmi_hive_id, NULL }; +ATTRIBUTE_GROUPS(amdgpu_xgmi_hive); static ssize_t amdgpu_xgmi_show_attrs(struct kobject *kobj, struct attribute *attr, char *buf) @@ -237,7 +238,7 @@ static const struct sysfs_ops amdgpu_xgmi_hive_ops = { struct kobj_type amdgpu_xgmi_hive_type = { .release = amdgpu_xgmi_hive_release, .sysfs_ops = &amdgpu_xgmi_hive_ops, - .default_attrs = amdgpu_xgmi_hive_attrs, + .default_groups = amdgpu_xgmi_hive_groups, }; static ssize_t amdgpu_xgmi_show_device_id(struct device *dev, 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..38bb42727715 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; @@ -995,7 +989,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev) && amdgpu_in_reset(adev)) goto skip_pin_bo; - r = amdgpu_gart_table_vram_pin(adev); + r = amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); if (r) return r; @@ -1066,7 +1060,6 @@ static void gmc_v10_0_gart_disable(struct amdgpu_device *adev) { adev->gfxhub.funcs->gart_disable(adev); adev->mmhub.funcs->gart_disable(adev); - amdgpu_gart_table_vram_unpin(adev); } static int gmc_v10_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 0fe714f54cca..cd6c38e083d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -476,7 +476,7 @@ static int gmc_v6_0_gart_enable(struct amdgpu_device *adev) dev_err(adev->dev, "No VRAM object for PCIE GART.\n"); return -EINVAL; } - r = amdgpu_gart_table_vram_pin(adev); + r = amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); if (r) return r; @@ -608,7 +608,6 @@ static void gmc_v6_0_gart_disable(struct amdgpu_device *adev) WREG32(mmVM_L2_CNTL3, VM_L2_CNTL3__L2_CACHE_BIGK_ASSOCIATIVITY_MASK | (0UL << VM_L2_CNTL3__L2_CACHE_BIGK_FRAGMENT_SIZE__SHIFT)); - amdgpu_gart_table_vram_unpin(adev); } static void gmc_v6_0_vm_decode_fault(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 0a50fdaced7e..ab8adbff9e2d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -620,7 +620,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) dev_err(adev->dev, "No VRAM object for PCIE GART.\n"); return -EINVAL; } - r = amdgpu_gart_table_vram_pin(adev); + r = amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); if (r) return r; @@ -758,7 +758,6 @@ static void gmc_v7_0_gart_disable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0); WREG32(mmVM_L2_CNTL, tmp); WREG32(mmVM_L2_CNTL2, 0); - amdgpu_gart_table_vram_unpin(adev); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 492ebed2915b..054733838292 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); @@ -837,7 +844,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev) dev_err(adev->dev, "No VRAM object for PCIE GART.\n"); return -EINVAL; } - r = amdgpu_gart_table_vram_pin(adev); + r = amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); if (r) return r; @@ -992,7 +999,6 @@ static void gmc_v8_0_gart_disable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_CACHE, 0); WREG32(mmVM_L2_CNTL, tmp); WREG32(mmVM_L2_CNTL2, 0); - amdgpu_gart_table_vram_unpin(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..88c1eb9ad068 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -72,6 +72,9 @@ #define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0 0x049d #define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX 2 +#define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_DCN2 0x05ea +#define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_DCN2_BASE_IDX 2 + static const char *gfxhub_client_ids[] = { "CB", @@ -478,9 +481,18 @@ 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 +501,18 @@ 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 +809,12 @@ 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 +825,10 @@ 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 +841,11 @@ 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 +856,16 @@ 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); @@ -1105,6 +1137,8 @@ static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev) u32 d1vga_control = RREG32_SOC15(DCE, 0, mmD1VGA_CONTROL); unsigned size; + /* TODO move to DC so GMC doesn't need to hard-code DCN registers */ + if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) { size = AMDGPU_VBIOS_VGA_ALLOCATION; } else { @@ -1113,7 +1147,6 @@ static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev) switch (adev->ip_versions[DCE_HWIP][0]) { case IP_VERSION(1, 0, 0): case IP_VERSION(1, 0, 1): - case IP_VERSION(2, 1, 0): viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION); size = (REG_GET_FIELD(viewport, HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) * @@ -1121,6 +1154,14 @@ static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev) HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH) * 4); break; + case IP_VERSION(2, 1, 0): + viewport = RREG32_SOC15(DCE, 0, mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_DCN2); + size = (REG_GET_FIELD(viewport, + HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) * + REG_GET_FIELD(viewport, + HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_WIDTH) * + 4); + break; default: viewport = RREG32_SOC15(DCE, 0, mmSCL0_VIEWPORT_SIZE); size = (REG_GET_FIELD(viewport, SCL0_VIEWPORT_SIZE, VIEWPORT_HEIGHT) * @@ -1599,12 +1640,6 @@ 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; @@ -1720,7 +1755,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev) && amdgpu_in_reset(adev)) goto skip_pin_bo; - r = amdgpu_gart_table_vram_pin(adev); + r = amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); if (r) return r; @@ -1798,7 +1833,6 @@ static void gmc_v9_0_gart_disable(struct amdgpu_device *adev) { adev->gfxhub.funcs->gart_disable(adev); adev->mmhub.funcs->gart_disable(adev); - amdgpu_gart_table_vram_unpin(adev); } static int gmc_v9_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 0077e738db31..56da5ab82987 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -180,6 +180,11 @@ static int xgpu_ai_send_access_requests(struct amdgpu_device *adev, RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_MAILBOX_MSGBUF_RCV_DW2)); } + } else if (req == IDH_REQ_GPU_INIT_DATA){ + /* Dummy REQ_GPU_INIT_DATA handling */ + r = xgpu_ai_poll_msg(adev, IDH_REQ_GPU_INIT_DATA_READY); + /* version set to 0 since dummy */ + adev->virt.req_init_data_ver = 0; } return 0; @@ -381,10 +386,16 @@ void xgpu_ai_mailbox_put_irq(struct amdgpu_device *adev) amdgpu_irq_put(adev, &adev->virt.rcv_irq, 0); } +static int xgpu_ai_request_init_data(struct amdgpu_device *adev) +{ + return xgpu_ai_send_access_requests(adev, IDH_REQ_GPU_INIT_DATA); +} + const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, .reset_gpu = xgpu_ai_request_reset, .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, + .req_init_data = xgpu_ai_request_init_data, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h index f9aa4d0bb638..fa7e13e0459e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h @@ -35,6 +35,7 @@ enum idh_request { IDH_REQ_GPU_FINI_ACCESS, IDH_REL_GPU_FINI_ACCESS, IDH_REQ_GPU_RESET_ACCESS, + IDH_REQ_GPU_INIT_DATA, IDH_LOG_VF_ERROR = 200, IDH_READY_TO_RESET = 201, @@ -48,6 +49,7 @@ enum idh_event { IDH_SUCCESS, IDH_FAIL, IDH_QUERY_ALIVE, + IDH_REQ_GPU_INIT_DATA_READY, IDH_TEXT_MESSAGE = 255, }; 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) |