Re: [PATCH] drm/xe: Nuke simple error capture

[John Harrison <john.c.harrison@intel.com>]

On 5/22/2024 13:34, José Roberto de Souza wrote:
> This error capture prints into dmesg HW state when a gpu hang happens.
> It was useful when we did not had devcoredump, now it is a incompleted
> version of devcoredump that has potential to flood dmesg.
>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: John Harrison <John.C.Harrison@Intel.com>
> Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>

> ---
>   drivers/gpu/drm/xe/Kconfig.debug   | 10 ------
>   drivers/gpu/drm/xe/xe_guc_submit.c | 53 +-----------------------------
>   drivers/gpu/drm/xe/xe_vm.c         | 49 ---------------------------
>   drivers/gpu/drm/xe/xe_vm.h         |  2 --
>   4 files changed, 1 insertion(+), 113 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/Kconfig.debug b/drivers/gpu/drm/xe/Kconfig.debug
> index df02e5d17d26f..bc177368af6c3 100644
> --- a/drivers/gpu/drm/xe/Kconfig.debug
> +++ b/drivers/gpu/drm/xe/Kconfig.debug
> @@ -61,16 +61,6 @@ config DRM_XE_DEBUG_MEM
>   
>   	  If in doubt, say "N".
>   
> -config DRM_XE_SIMPLE_ERROR_CAPTURE
> -	bool "Enable simple error capture to dmesg on job timeout"
> -	default n
> -	help
> -	  Choose this option when debugging an unexpected job timeout
> -
> -	  Recommended for driver developers only.
> -
> -	  If in doubt, say "N".
> -
>   config DRM_XE_KUNIT_TEST
>           tristate "KUnit tests for the drm xe driver" if !KUNIT_ALL_TESTS
>   	depends on DRM_XE && KUNIT && DEBUG_FS
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 23f73577facf6..f0a5215159003 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -815,55 +815,6 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
>   		       G2H_LEN_DW_DEREGISTER_CONTEXT, 2);
>   }
>   
> -static void guc_exec_queue_print(struct xe_exec_queue *q, struct drm_printer *p);
> -
> -#if IS_ENABLED(CONFIG_DRM_XE_SIMPLE_ERROR_CAPTURE)
> -static void simple_error_capture(struct xe_exec_queue *q)
> -{
> -	struct xe_guc *guc = exec_queue_to_guc(q);
> -	struct xe_device *xe = guc_to_xe(guc);
> -	struct drm_printer p = drm_err_printer(&xe->drm, NULL);
> -	struct xe_hw_engine *hwe;
> -	enum xe_hw_engine_id id;
> -	u32 adj_logical_mask = q->logical_mask;
> -	u32 width_mask = (0x1 << q->width) - 1;
> -	int i;
> -	bool cookie;
> -
> -	if (q->vm && !q->vm->error_capture.capture_once) {
> -		q->vm->error_capture.capture_once = true;
> -		cookie = dma_fence_begin_signalling();
> -		for (i = 0; q->width > 1 && i < XE_HW_ENGINE_MAX_INSTANCE;) {
> -			if (adj_logical_mask & BIT(i)) {
> -				adj_logical_mask |= width_mask << i;
> -				i += q->width;
> -			} else {
> -				++i;
> -			}
> -		}
> -
> -		if (xe_force_wake_get(gt_to_fw(guc_to_gt(guc)), XE_FORCEWAKE_ALL))
> -			xe_gt_info(guc_to_gt(guc),
> -				   "failed to get forcewake for error capture");
> -		xe_guc_ct_print(&guc->ct, &p, true);
> -		guc_exec_queue_print(q, &p);
> -		for_each_hw_engine(hwe, guc_to_gt(guc), id) {
> -			if (hwe->class != q->hwe->class ||
> -			    !(BIT(hwe->logical_instance) & adj_logical_mask))
> -				continue;
> -			xe_hw_engine_print(hwe, &p);
> -		}
> -		xe_analyze_vm(&p, q->vm, q->gt->info.id);
> -		xe_force_wake_put(gt_to_fw(guc_to_gt(guc)), XE_FORCEWAKE_ALL);
> -		dma_fence_end_signalling(cookie);
> -	}
> -}
> -#else
> -static void simple_error_capture(struct xe_exec_queue *q)
> -{
> -}
> -#endif
> -
>   static void xe_guc_exec_queue_trigger_cleanup(struct xe_exec_queue *q)
>   {
>   	struct xe_guc *guc = exec_queue_to_guc(q);
> @@ -995,10 +946,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
>   	xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q),
>   		   "VM job timed out on non-killed execqueue\n");
>   
> -	if (!exec_queue_killed(q)) {
> -		simple_error_capture(q);
> +	if (!exec_queue_killed(q))
>   		xe_devcoredump(job);
> -	}
>   
>   	trace_xe_sched_job_timedout(job);
>   
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index c5b1694b292fc..53f196cf447b4 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -3389,55 +3389,6 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
>   	return 0;
>   }
>   
> -int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id)
> -{
> -	struct drm_gpuva *gpuva;
> -	bool is_vram;
> -	uint64_t addr;
> -
> -	if (!down_read_trylock(&vm->lock)) {
> -		drm_printf(p, " Failed to acquire VM lock to dump capture");
> -		return 0;
> -	}
> -	if (vm->pt_root[gt_id]) {
> -		addr = xe_bo_addr(vm->pt_root[gt_id]->bo, 0, XE_PAGE_SIZE);
> -		is_vram = xe_bo_is_vram(vm->pt_root[gt_id]->bo);
> -		drm_printf(p, " VM root: A:0x%llx %s\n", addr,
> -			   is_vram ? "VRAM" : "SYS");
> -	}
> -
> -	drm_gpuvm_for_each_va(gpuva, &vm->gpuvm) {
> -		struct xe_vma *vma = gpuva_to_vma(gpuva);
> -		bool is_userptr = xe_vma_is_userptr(vma);
> -		bool is_null = xe_vma_is_null(vma);
> -
> -		if (is_null) {
> -			addr = 0;
> -		} else if (is_userptr) {
> -			struct sg_table *sg = to_userptr_vma(vma)->userptr.sg;
> -			struct xe_res_cursor cur;
> -
> -			if (sg) {
> -				xe_res_first_sg(sg, 0, XE_PAGE_SIZE, &cur);
> -				addr = xe_res_dma(&cur);
> -			} else {
> -				addr = 0;
> -			}
> -		} else {
> -			addr = __xe_bo_addr(xe_vma_bo(vma), 0, XE_PAGE_SIZE);
> -			is_vram = xe_bo_is_vram(xe_vma_bo(vma));
> -		}
> -		drm_printf(p, " [%016llx-%016llx] S:0x%016llx A:%016llx %s\n",
> -			   xe_vma_start(vma), xe_vma_end(vma) - 1,
> -			   xe_vma_size(vma),
> -			   addr, is_null ? "NULL" : is_userptr ? "USR" :
> -			   is_vram ? "VRAM" : "SYS");
> -	}
> -	up_read(&vm->lock);
> -
> -	return 0;
> -}
> -
>   struct xe_vm_snapshot {
>   	unsigned long num_snaps;
>   	struct {
> diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
> index 3ac9021f970e3..b481608b12f1b 100644
> --- a/drivers/gpu/drm/xe/xe_vm.h
> +++ b/drivers/gpu/drm/xe/xe_vm.h
> @@ -243,8 +243,6 @@ int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma);
>   
>   bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
>   
> -int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id);
> -
>   int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma);
>   
>   int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,