drm/sched: Set error to s_fence if HW job submission failed.

Problem:
When run_job fails and HW fence returned is NULL we still signal
the s_fence to avoid hangs but the user has no way of knowing if
the actual HW job was ran and finished.

Fix:
Allow .run_job implementations to return ERR_PTR in the fence pointer
returned and then set this error for s_fence->finished fence so whoever
wait on this fence can inspect the signaled fence for an error.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Andrey Grodzovsky 2019-10-24 15:39:06 -04:00 committed by Alex Deucher
parent 47661f6dad
commit 167bf96014
1 changed files with 16 additions and 3 deletions

View File

@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
struct drm_sched_job *s_job, *tmp;
uint64_t guilty_context;
bool found_guilty = false;
struct dma_fence *fence;
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
struct drm_sched_fence *s_fence = s_job->s_fence;
@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
dma_fence_set_error(&s_fence->finished, -ECANCELED);
dma_fence_put(s_job->s_fence->parent);
s_job->s_fence->parent = sched->ops->run_job(s_job);
fence = sched->ops->run_job(s_job);
if (IS_ERR_OR_NULL(fence)) {
s_job->s_fence->parent = NULL;
dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
} else {
s_job->s_fence->parent = fence;
}
}
}
EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@ -720,7 +730,7 @@ static int drm_sched_main(void *param)
fence = sched->ops->run_job(sched_job);
drm_sched_fence_scheduled(s_fence);
if (fence) {
if (!IS_ERR_OR_NULL(fence)) {
s_fence->parent = dma_fence_get(fence);
r = dma_fence_add_callback(fence, &sched_job->cb,
drm_sched_process_job);
@ -730,8 +740,11 @@ static int drm_sched_main(void *param)
DRM_ERROR("fence add callback failed (%d)\n",
r);
dma_fence_put(fence);
} else
} else {
dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
drm_sched_process_job(NULL, &sched_job->cb);
}
wake_up(&sched->job_scheduled);
}