diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
57 files changed, 2366 insertions, 176 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 5a283d12f8e1..6ad39cf71bdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -75,7 +75,7 @@ amdgpu-y += \ vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \ vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \ nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o soc21.o \ - nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o + sienna_cichlid.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o # add DF block amdgpu-y += \ @@ -89,7 +89,7 @@ amdgpu-y += \ gfxhub_v1_0.o mmhub_v1_0.o gmc_v9_0.o gfxhub_v1_1.o mmhub_v9_4.o \ gfxhub_v2_0.o mmhub_v2_0.o gmc_v10_0.o gfxhub_v2_1.o mmhub_v2_3.o \ mmhub_v1_7.o gfxhub_v3_0.o mmhub_v3_0.o mmhub_v3_0_2.o gmc_v11_0.o \ - mmhub_v3_0_1.o + mmhub_v3_0_1.o gfxhub_v3_0_3.o # add UMC block amdgpu-y += \ @@ -134,7 +134,8 @@ amdgpu-y += \ gfx_v9_4_2.o \ gfx_v10_0.o \ imu_v11_0.o \ - gfx_v11_0.o + gfx_v11_0.o \ + imu_v11_0_3.o # add async DMA block amdgpu-y += \ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d597e2656c47..79bb6fd83094 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -274,6 +274,9 @@ extern int amdgpu_vcnfw_log; #define AMDGPU_RESET_VCE (1 << 13) #define AMDGPU_RESET_VCE1 (1 << 14) +#define AMDGPU_RESET_LEVEL_SOFT_RECOVERY (1 << 0) +#define AMDGPU_RESET_LEVEL_MODE2 (1 << 1) + /* max cursor sizes (in pixels) */ #define CIK_CURSOR_WIDTH 128 #define CIK_CURSOR_HEIGHT 128 @@ -1060,6 +1063,9 @@ struct amdgpu_device { uint32_t scpm_status; struct work_struct reset_work; + + uint32_t amdgpu_reset_level_mask; + bool job_hang; }; static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 130060834b4e..55402d238919 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1066,6 +1066,12 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) (pm_suspend_target_state != PM_SUSPEND_TO_IDLE)) return false; + /* + * If ACPI_FADT_LOW_POWER_S0 is not set in the FADT, it is generally + * risky to do any special firmware-related preparations for entering + * S0ix even though the system is suspending to idle, so return false + * in that case. + */ if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) { dev_warn_once(adev->dev, "Power consumption will be higher as BIOS has not been configured for suspend-to-idle.\n" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 5e53a5293935..091415a4abf0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -135,6 +135,7 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work) reset_context.method = AMD_RESET_METHOD_NONE; reset_context.reset_req_dev = adev; clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags); amdgpu_device_gpu_recover(adev, NULL, &reset_context); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cbd593f7d553..2170db83e41d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1728,7 +1728,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr); if (user_addr) { - pr_debug("creating userptr BO for user_addr = %llu\n", user_addr); + pr_debug("creating userptr BO for user_addr = %llx\n", user_addr); ret = init_user_pages(*mem, user_addr, criu_resume); if (ret) goto allocate_init_user_pages_failed; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index afe22f83d4a6..3ea48385fab3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -402,7 +402,7 @@ static void amdgpu_ctx_fini(struct kref *ref) } } - if (drm_dev_enter(&adev->ddev, &idx)) { + if (drm_dev_enter(adev_to_drm(adev), &idx)) { amdgpu_ctx_set_stable_pstate(ctx, ctx->stable_pstate); drm_dev_exit(idx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index cb00c7d6f50b..6066aebf491c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1043,6 +1043,157 @@ err: } /** + * amdgpu_debugfs_gfxoff_residency_read - Read GFXOFF residency + * + * @f: open file handle + * @buf: User buffer to store read data in + * @size: Number of bytes to read + * @pos: Offset to seek to + * + * Read the last residency value logged. It doesn't auto update, one needs to + * stop logging before getting the current value. + */ +static ssize_t amdgpu_debugfs_gfxoff_residency_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_device *adev = file_inode(f)->i_private; + ssize_t result = 0; + int r; + + if (size & 0x3 || *pos & 0x3) + return -EINVAL; + + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); + if (r < 0) { + pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); + return r; + } + + while (size) { + uint32_t value; + + r = amdgpu_get_gfx_off_residency(adev, &value); + if (r) + goto out; + + r = put_user(value, (uint32_t *)buf); + if (r) + goto out; + + result += 4; + buf += 4; + *pos += 4; + size -= 4; + } + + r = result; +out: + pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); + pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); + + return r; +} + +/** + * amdgpu_debugfs_gfxoff_residency_write - Log GFXOFF Residency + * + * @f: open file handle + * @buf: User buffer to write data from + * @size: Number of bytes to write + * @pos: Offset to seek to + * + * Write a 32-bit non-zero to start logging; write a 32-bit zero to stop + */ +static ssize_t amdgpu_debugfs_gfxoff_residency_write(struct file *f, const char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_device *adev = file_inode(f)->i_private; + ssize_t result = 0; + int r; + + if (size & 0x3 || *pos & 0x3) + return -EINVAL; + + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); + if (r < 0) { + pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); + return r; + } + + while (size) { + u32 value; + + r = get_user(value, (uint32_t *)buf); + if (r) + goto out; + + amdgpu_set_gfx_off_residency(adev, value ? true : false); + + result += 4; + buf += 4; + *pos += 4; + size -= 4; + } + + r = result; +out: + pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); + pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); + + return r; +} + + +/** + * amdgpu_debugfs_gfxoff_count_read - Read GFXOFF entry count + * + * @f: open file handle + * @buf: User buffer to store read data in + * @size: Number of bytes to read + * @pos: Offset to seek to + */ +static ssize_t amdgpu_debugfs_gfxoff_count_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_device *adev = file_inode(f)->i_private; + ssize_t result = 0; + int r; + + if (size & 0x3 || *pos & 0x3) + return -EINVAL; + + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); + if (r < 0) { + pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); + return r; + } + + while (size) { + u64 value = 0; + + r = amdgpu_get_gfx_off_entrycount(adev, &value); + if (r) + goto out; + + r = put_user(value, (u64 *)buf); + if (r) + goto out; + + result += 4; + buf += 4; + *pos += 4; + size -= 4; + } + + r = result; +out: + pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); + pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); + + return r; +} + +/** * amdgpu_debugfs_gfxoff_write - Enable/disable GFXOFF * * @f: open file handle @@ -1249,6 +1400,19 @@ static const struct file_operations amdgpu_debugfs_gfxoff_status_fops = { .llseek = default_llseek }; +static const struct file_operations amdgpu_debugfs_gfxoff_count_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_gfxoff_count_read, + .llseek = default_llseek +}; + +static const struct file_operations amdgpu_debugfs_gfxoff_residency_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_gfxoff_residency_read, + .write = amdgpu_debugfs_gfxoff_residency_write, + .llseek = default_llseek +}; + static const struct file_operations *debugfs_regs[] = { &amdgpu_debugfs_regs_fops, &amdgpu_debugfs_regs2_fops, @@ -1261,6 +1425,8 @@ static const struct file_operations *debugfs_regs[] = { &amdgpu_debugfs_gpr_fops, &amdgpu_debugfs_gfxoff_fops, &amdgpu_debugfs_gfxoff_status_fops, + &amdgpu_debugfs_gfxoff_count_fops, + &amdgpu_debugfs_gfxoff_residency_fops, }; static const char *debugfs_regs_names[] = { @@ -1275,6 +1441,8 @@ static const char *debugfs_regs_names[] = { "amdgpu_gpr", "amdgpu_gfxoff", "amdgpu_gfxoff_status", + "amdgpu_gfxoff_count", + "amdgpu_gfxoff_residency", }; /** @@ -1786,6 +1954,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) return PTR_ERR(ent); } + debugfs_create_u32("amdgpu_reset_level", 0600, root, &adev->amdgpu_reset_level_mask); + /* Register debugfs entries for amdgpu_ttm */ amdgpu_ttm_debugfs_init(adev); amdgpu_debugfs_pm_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e8a0b19b7398..62b26f0e37b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2456,12 +2456,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (!hive->reset_domain || !amdgpu_reset_get_reset_domain(hive->reset_domain)) { r = -ENOENT; + amdgpu_put_xgmi_hive(hive); goto init_failed; } /* Drop the early temporary reset domain we created for device */ amdgpu_reset_put_reset_domain(adev->reset_domain); adev->reset_domain = hive->reset_domain; + amdgpu_put_xgmi_hive(hive); } } @@ -3577,6 +3579,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func); adev->gfx.gfx_off_req_count = 1; + adev->gfx.gfx_off_residency = 0; + adev->gfx.gfx_off_entrycount = 0; adev->pm.ac_power = power_supply_is_system_supplied() > 0; atomic_set(&adev->throttling_logging_enabled, 1); @@ -3965,8 +3969,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_gart_dummy_page_fini(adev); - if (drm_dev_is_unplugged(adev_to_drm(adev))) - amdgpu_device_unmap_mmio(adev); + amdgpu_device_unmap_mmio(adev); } @@ -4413,8 +4416,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, retry: amdgpu_amdkfd_pre_reset(adev); - amdgpu_amdkfd_pre_reset(adev); - if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else @@ -4509,14 +4510,15 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev) */ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev) { - if (!amdgpu_device_ip_check_soft_reset(adev)) { - dev_info(adev->dev, "Timeout, but no hardware hang detected.\n"); - return false; - } if (amdgpu_gpu_recovery == 0) goto disabled; + if (!amdgpu_device_ip_check_soft_reset(adev)) { + dev_info(adev->dev,"Timeout, but no hardware hang detected.\n"); + return false; + } + if (amdgpu_sriov_vf(adev)) return true; @@ -4641,7 +4643,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, if (!need_full_reset) need_full_reset = amdgpu_device_ip_need_full_reset(adev); - if (!need_full_reset) { + if (!need_full_reset && amdgpu_gpu_recovery) { amdgpu_device_ip_pre_soft_reset(adev); r = amdgpu_device_ip_soft_reset(adev); amdgpu_device_ip_post_soft_reset(adev); @@ -5039,6 +5041,7 @@ static void amdgpu_device_recheck_guilty_jobs( /* set guilty */ drm_sched_increase_karma(s_job); + amdgpu_reset_prepare_hwcontext(adev, reset_context); retry: /* do hw reset */ if (amdgpu_sriov_vf(adev)) { @@ -5148,6 +5151,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, reset_context->job = job; reset_context->hive = hive; + /* * Build list of devices to reset. * In case we are in XGMI hive mode, resort the device list @@ -5267,8 +5271,11 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ amdgpu_ras_resume(adev); } else { r = amdgpu_do_asic_reset(device_list_handle, reset_context); - if (r && r == -EAGAIN) + if (r && r == -EAGAIN) { + set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags); + adev->asic_reset_res = 0; goto retry; + } } skip_hw_reset: @@ -5524,7 +5531,8 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev, ~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1); resource_size_t aper_limit = adev->gmc.aper_base + adev->gmc.aper_size - 1; - bool p2p_access = !(pci_p2pdma_distance_many(adev->pdev, + bool p2p_access = !adev->gmc.xgmi.connected_to_cpu && + !(pci_p2pdma_distance_many(adev->pdev, &peer_adev->dev, 1, true) < 0); return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size && @@ -5699,6 +5707,7 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) reset_context.reset_req_dev = adev; set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags); + set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags); adev->no_hw_access = true; r = amdgpu_device_pre_asic_reset(adev, &reset_context); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 95d34590cad1..9fa2a5ceb77d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1506,6 +1506,7 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): + case IP_VERSION(11, 0, 3): amdgpu_device_ip_block_add(adev, &soc21_common_ip_block); break; default: @@ -1549,6 +1550,7 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): + case IP_VERSION(11, 0, 3): amdgpu_device_ip_block_add(adev, &gmc_v11_0_ip_block); break; default: @@ -1633,6 +1635,7 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(13, 0, 5): case IP_VERSION(13, 0, 7): case IP_VERSION(13, 0, 8): + case IP_VERSION(13, 0, 10): amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block); break; case IP_VERSION(13, 0, 4): @@ -1682,6 +1685,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(13, 0, 5): case IP_VERSION(13, 0, 7): case IP_VERSION(13, 0, 8): + case IP_VERSION(13, 0, 10): amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block); break; default: @@ -1780,6 +1784,7 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): + case IP_VERSION(11, 0, 3): amdgpu_device_ip_block_add(adev, &gfx_v11_0_ip_block); break; default: @@ -1823,6 +1828,7 @@ static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(6, 0, 0): case IP_VERSION(6, 0, 1): case IP_VERSION(6, 0, 2): + case IP_VERSION(6, 0, 3): amdgpu_device_ip_block_add(adev, &sdma_v6_0_ip_block); break; default: @@ -1903,7 +1909,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(4, 0, 2): case IP_VERSION(4, 0, 4): amdgpu_device_ip_block_add(adev, &vcn_v4_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v4_0_ip_block); + if (!amdgpu_sriov_vf(adev)) + amdgpu_device_ip_block_add(adev, &jpeg_v4_0_ip_block); break; default: dev_err(adev->dev, @@ -1940,6 +1947,7 @@ static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): + case IP_VERSION(11, 0, 3): amdgpu_device_ip_block_add(adev, &mes_v11_0_ip_block); adev->enable_mes = true; adev->enable_mes_kiq = true; @@ -2165,6 +2173,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 2): + case IP_VERSION(11, 0, 3): adev->family = AMDGPU_FAMILY_GC_11_0_0; break; case IP_VERSION(11, 0, 1): @@ -2234,7 +2243,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; case IP_VERSION(4, 3, 0): case IP_VERSION(4, 3, 1): - adev->nbio.funcs = &nbio_v4_3_funcs; + if (amdgpu_sriov_vf(adev)) + adev->nbio.funcs = &nbio_v4_3_sriov_funcs; + else + adev->nbio.funcs = &nbio_v4_3_funcs; adev->nbio.hdp_flush_reg = &nbio_v4_3_hdp_flush_reg; break; case IP_VERSION(7, 7, 0): @@ -2332,6 +2344,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(6, 0, 0): case IP_VERSION(6, 0, 1): case IP_VERSION(6, 0, 2): + case IP_VERSION(6, 0, 3): adev->lsdma.funcs = &lsdma_v6_0_funcs; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 429fcdf28836..728a0933ea6f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2181,8 +2181,6 @@ amdgpu_pci_remove(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); struct amdgpu_device *adev = drm_to_adev(dev); - drm_dev_unplug(dev); - if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) { pm_runtime_get_sync(dev->dev); pm_runtime_forbid(dev->dev); @@ -2190,6 +2188,8 @@ amdgpu_pci_remove(struct pci_dev *pdev) amdgpu_driver_unload_kms(dev); + drm_dev_unplug(dev); + /* * Flush any in flight DMA operations from device. * Clear the Bus Master Enable bit and then wait on the PCIe Device @@ -2563,8 +2563,11 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) amdgpu_device_baco_exit(drm_dev); } < |