diff options
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 56 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 |
7 files changed, 45 insertions, 25 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dff0e80c5aa1..eaebd2884503 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1098,6 +1098,10 @@ struct amdgpu_device { bool dc_enabled; /* Mask of active clusters */ uint32_t aid_mask; + + /* Debug */ + bool debug_vm; + bool debug_largebar; }; static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 4de6f53aea38..122472d88756 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1151,7 +1151,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); } - if (amdgpu_vm_debug) { + if (adev->debug_vm) { /* Invalidate all BOs to test for userspace bugs */ amdgpu_bo_list_for_each_entry(e, p->bo_list) { struct amdgpu_bo *bo = e->bo; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 49b1506c4722..745174d196d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -118,6 +118,14 @@ #define KMS_DRIVER_MINOR 54 #define KMS_DRIVER_PATCHLEVEL 0 +/* + * amdgpu.debug module options. Are all disabled by default + */ +enum AMDGPU_DEBUG_MASK { + AMDGPU_DEBUG_VM = BIT(0), + AMDGPU_DEBUG_LARGEBAR = BIT(1), +}; + unsigned int amdgpu_vram_limit = UINT_MAX; int amdgpu_vis_vram_limit; int amdgpu_gart_size = -1; /* auto */ @@ -140,7 +148,6 @@ int amdgpu_vm_size = -1; int amdgpu_vm_fragment_size = -1; int amdgpu_vm_block_size = -1; int amdgpu_vm_fault_stop; -int amdgpu_vm_debug; int amdgpu_vm_update_mode = -1; int amdgpu_exp_hw_support; int amdgpu_dc = -1; @@ -195,6 +202,7 @@ int amdgpu_vcnfw_log; int amdgpu_sg_display = -1; /* auto */ int amdgpu_user_partt_mode = AMDGPU_AUTO_COMPUTE_PARTITION_MODE; int amdgpu_umsch_mm; +uint amdgpu_debug_mask; static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -407,13 +415,6 @@ MODULE_PARM_DESC(vm_fault_stop, "Stop on VM fault (0 = never (default), 1 = prin module_param_named(vm_fault_stop, amdgpu_vm_fault_stop, int, 0444); /** - * DOC: vm_debug (int) - * Debug VM handling (0 = disabled, 1 = enabled). The default is 0 (Disabled). - */ -MODULE_PARM_DESC(vm_debug, "Debug VM handling (0 = disabled (default), 1 = enabled)"); -module_param_named(vm_debug, amdgpu_vm_debug, int, 0644); - -/** * DOC: vm_update_mode (int) * Override VM update mode. VM updated by using CPU (0 = never, 1 = Graphics only, 2 = Compute only, 3 = Both). The default * is -1 (Only in large BAR(LB) systems Compute VM tables will be updated by CPU, otherwise 0, never). @@ -745,18 +746,6 @@ MODULE_PARM_DESC(send_sigterm, "Send sigterm to HSA process on unhandled exception (0 = disable, 1 = enable)"); /** - * DOC: debug_largebar (int) - * Set debug_largebar as 1 to enable simulating large-bar capability on non-large bar - * system. This limits the VRAM size reported to ROCm applications to the visible - * size, usually 256MB. - * Default value is 0, diabled. - */ -int debug_largebar; -module_param(debug_largebar, int, 0444); -MODULE_PARM_DESC(debug_largebar, - "Debug large-bar flag used to simulate large-bar capability on non-large bar machine (0 = disable, 1 = enable)"); - -/** * DOC: halt_if_hws_hang (int) * Halt if HWS hang is detected. Default value, 0, disables the halt on hang. * Setting 1 enables halt on hang. @@ -948,6 +937,18 @@ module_param_named(user_partt_mode, amdgpu_user_partt_mode, uint, 0444); module_param(enforce_isolation, bool, 0444); MODULE_PARM_DESC(enforce_isolation, "enforce process isolation between graphics and compute . enforce_isolation = on"); +/** + * DOC: debug_mask (uint) + * Debug options for amdgpu, work as a binary mask with the following options: + * + * - 0x1: Debug VM handling + * - 0x2: Enable simulating large-bar capability on non-large bar system. This + * limits the VRAM size reported to ROCm applications to the visible + * size, usually 256MB. + */ +MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default"); +module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444); + /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ @@ -2052,6 +2053,19 @@ static void amdgpu_get_secondary_funcs(struct amdgpu_device *adev) } } +static void amdgpu_init_debug_options(struct amdgpu_device *adev) +{ + if (amdgpu_debug_mask & AMDGPU_DEBUG_VM) { + pr_info("debug: VM handling debug enabled\n"); + adev->debug_vm = true; + } + + if (amdgpu_debug_mask & AMDGPU_DEBUG_LARGEBAR) { + pr_info("debug: enabled simulating large-bar capability on non-large bar system\n"); + adev->debug_largebar = true; + } +} + static int amdgpu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2230,6 +2244,8 @@ retry_init: amdgpu_get_secondary_funcs(adev); } + amdgpu_init_debug_options(adev); + return 0; err_pci: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index ca4d2d430e28..b1ce22a9b186 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -791,7 +791,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, default: break; } - if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && !amdgpu_vm_debug) + if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && !adev->debug_vm) amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va, args->operation); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 3be07c6410d2..231f5d9e5791 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1403,7 +1403,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, spin_unlock(&vm->status_lock); /* Try to reserve the BO to avoid clearing its ptes */ - if (!amdgpu_vm_debug && dma_resv_trylock(resv)) + if (!adev->debug_vm && dma_resv_trylock(resv)) clear = false; /* Somebody else is using the BO right now */ else diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index c37f1fcd2165..bd762f6cd12b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1021,7 +1021,7 @@ err_drm_file: bool kfd_dev_is_large_bar(struct kfd_node *dev) { - if (debug_largebar) { + if (dev->kfd->adev->debug_largebar) { pr_debug("Simulate large-bar allocation on non large-bar machine\n"); return true; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 950810bb5c71..9459603804b9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -2116,7 +2116,7 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image, sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr + sub_type_hdr->length); - if (debug_largebar) + if (kdev->adev->debug_largebar) local_mem_info.local_mem_size_private = 0; if (local_mem_info.local_mem_size_private == 0) |