X-Git-Url: https://repo.jachan.dev/J-linux.git/blobdiff_plain/3ca06e90a7ceb06aaba8a9dc1c59d970824dab23..b95264cf75bd8840b10733c50678d154c02b5431:/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 094498a0964b..054d1837e566 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -117,9 +117,10 @@ * - 3.56.0 - Update IB start address and size alignment for decode and encode * - 3.57.0 - Compute tunneling on GFX10+ * - 3.58.0 - Add GFX12 DCC support + * - 3.59.0 - Cleared VRAM */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 58 +#define KMS_DRIVER_MINOR 59 #define KMS_DRIVER_PATCHLEVEL 0 /* @@ -131,6 +132,7 @@ enum AMDGPU_DEBUG_MASK { AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2), AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3), AMDGPU_DEBUG_ENABLE_RAS_ACA = BIT(4), + AMDGPU_DEBUG_ENABLE_EXP_RESETS = BIT(5), }; unsigned int amdgpu_vram_limit = UINT_MAX; @@ -168,6 +170,16 @@ uint amdgpu_sdma_phase_quantum = 32; char *amdgpu_disable_cu; char *amdgpu_virtual_display; bool enforce_isolation; + +/* Specifies the default granularity for SVM, used in buffer + * migration and restoration of backing memory when handling + * recoverable page faults. + * + * The value is given as log(numPages(buffer)); for a 2 MiB + * buffer it computes to be 9 + */ +uint amdgpu_svm_default_granularity = 9; + /* * OverDrive(bit 14) disabled by default * GFX DCS(bit 19) disabled by default @@ -219,8 +231,6 @@ int amdgpu_wbrf = -1; int amdgpu_damage_clips = -1; /* auto */ int amdgpu_umsch_mm_fwlog; -static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); - DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", "DRM_UT_DRIVER", @@ -235,9 +245,6 @@ DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), - .delayed_reset_work = __DELAYED_WORK_INITIALIZER( - mgpu_info.delayed_reset_work, - amdgpu_drv_delayed_reset_work_handler, 0), }; int amdgpu_ras_enable = -1; uint amdgpu_ras_mask = 0xffffffff; @@ -319,6 +326,13 @@ module_param_named(pcie_gen2, amdgpu_pcie_gen2, int, 0444); MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)"); module_param_named(msi, amdgpu_msi, int, 0444); +/** + * DOC: svm_default_granularity (uint) + * Used in buffer migration and handling of recoverable page faults + */ +MODULE_PARM_DESC(svm_default_granularity, "SVM's default granularity in log(2^Pages), default 9 = 2^9 = 2 MiB"); +module_param_named(svm_default_granularity, amdgpu_svm_default_granularity, uint, 0644); + /** * DOC: lockup_timeout (string) * Set GPU scheduler timeout value in ms. @@ -873,7 +887,7 @@ module_param_named(visualconfirm, amdgpu_dc_visual_confirm, uint, 0444); * the ABM algorithm, with 1 being the least reduction and 4 being the most * reduction. * - * Defaults to -1, or disabled. Userspace can only override this level after + * Defaults to -1, or auto. Userspace can only override this level after * boot if it's set to auto. */ int amdgpu_dm_abm_level = -1; @@ -2199,6 +2213,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev) pr_info("debug: enable RAS ACA\n"); adev->debug_enable_ras_aca = true; } + + if (amdgpu_debug_mask & AMDGPU_DEBUG_ENABLE_EXP_RESETS) { + pr_info("debug: enable experimental reset features\n"); + adev->debug_exp_resets = true; + } } static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags) @@ -2410,6 +2429,7 @@ amdgpu_pci_remove(struct pci_dev *pdev) struct amdgpu_device *adev = drm_to_adev(dev); amdgpu_xcp_dev_unplug(adev); + amdgpu_gmc_prepare_nps_mode_change(adev); drm_dev_unplug(dev); if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) { @@ -2448,82 +2468,6 @@ amdgpu_pci_shutdown(struct pci_dev *pdev) adev->mp1_state = PP_MP1_STATE_NONE; } -/** - * amdgpu_drv_delayed_reset_work_handler - work handler for reset - * - * @work: work_struct. - */ -static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) -{ - struct list_head device_list; - struct amdgpu_device *adev; - int i, r; - struct amdgpu_reset_context reset_context; - - memset(&reset_context, 0, sizeof(reset_context)); - - mutex_lock(&mgpu_info.mutex); - if (mgpu_info.pending_reset == true) { - mutex_unlock(&mgpu_info.mutex); - return; - } - mgpu_info.pending_reset = true; - mutex_unlock(&mgpu_info.mutex); - - /* Use a common context, just need to make sure full reset is done */ - reset_context.method = AMD_RESET_METHOD_NONE; - set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); - - for (i = 0; i < mgpu_info.num_dgpu; i++) { - adev = mgpu_info.gpu_ins[i].adev; - reset_context.reset_req_dev = adev; - r = amdgpu_device_pre_asic_reset(adev, &reset_context); - if (r) { - dev_err(adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ", - r, adev_to_drm(adev)->unique); - } - if (!queue_work(system_unbound_wq, &adev->xgmi_reset_work)) - r = -EALREADY; - } - for (i = 0; i < mgpu_info.num_dgpu; i++) { - adev = mgpu_info.gpu_ins[i].adev; - flush_work(&adev->xgmi_reset_work); - adev->gmc.xgmi.pending_reset = false; - } - - /* reset function will rebuild the xgmi hive info , clear it now */ - for (i = 0; i < mgpu_info.num_dgpu; i++) - amdgpu_xgmi_remove_device(mgpu_info.gpu_ins[i].adev); - - INIT_LIST_HEAD(&device_list); - - for (i = 0; i < mgpu_info.num_dgpu; i++) - list_add_tail(&mgpu_info.gpu_ins[i].adev->reset_list, &device_list); - - /* unregister the GPU first, reset function will add them back */ - list_for_each_entry(adev, &device_list, reset_list) - amdgpu_unregister_gpu_instance(adev); - - /* Use a common context, just need to make sure full reset is done */ - set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags); - set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags); - r = amdgpu_do_asic_reset(&device_list, &reset_context); - - if (r) { - DRM_ERROR("reinit gpus failure"); - return; - } - for (i = 0; i < mgpu_info.num_dgpu; i++) { - adev = mgpu_info.gpu_ins[i].adev; - if (!adev->kfd.init_complete) { - kgd2kfd_init_zone_device(adev); - amdgpu_amdkfd_device_init(adev); - amdgpu_amdkfd_drm_client_create(adev); - } - amdgpu_ttm_set_buffer_funcs_status(adev, true); - } -} - static int amdgpu_pmops_prepare(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); @@ -2556,7 +2500,6 @@ static int amdgpu_pmops_suspend(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - adev->suspend_complete = false; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) @@ -2571,7 +2514,6 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - adev->suspend_complete = true; if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); @@ -2953,7 +2895,6 @@ static const struct drm_driver amdgpu_kms_driver = { DRIVER_SYNCOBJ_TIMELINE, .open = amdgpu_driver_open_kms, .postclose = amdgpu_driver_postclose_kms, - .lastclose = amdgpu_driver_lastclose_kms, .ioctls = amdgpu_ioctls_kms, .num_ioctls = ARRAY_SIZE(amdgpu_ioctls_kms), .dumb_create = amdgpu_mode_dumb_create, @@ -2980,7 +2921,6 @@ const struct drm_driver amdgpu_partition_driver = { DRIVER_SYNCOBJ_TIMELINE, .open = amdgpu_driver_open_kms, .postclose = amdgpu_driver_postclose_kms, - .lastclose = amdgpu_driver_lastclose_kms, .ioctls = amdgpu_ioctls_kms, .num_ioctls = ARRAY_SIZE(amdgpu_ioctls_kms), .dumb_create = amdgpu_mode_dumb_create, @@ -3045,6 +2985,12 @@ static int __init amdgpu_init(void) /* Ignore KFD init failures. Normal when CONFIG_HSA_AMD is not set. */ amdgpu_amdkfd_init(); + if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) { + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + pr_crit("Overdrive is enabled, please disable it before " + "reporting any bugs unrelated to overdrive.\n"); + } + /* let modprobe override vga console setting */ return pci_register_driver(&amdgpu_kms_pci_driver);