diff options
Diffstat (limited to 'drivers/gpu/drm/scheduler/sched_main.c')
| -rw-r--r-- | drivers/gpu/drm/scheduler/sched_main.c | 34 |
1 files changed, 32 insertions, 2 deletions
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index dfb29e6eeff1..134e9106ebac 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -284,10 +284,21 @@ static void drm_sched_job_timedout(struct work_struct *work) unsigned long flags; sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work); + + /* Protects against concurrent deletion in drm_sched_get_cleanup_job */ + spin_lock_irqsave(&sched->job_list_lock, flags); job = list_first_entry_or_null(&sched->ring_mirror_list, struct drm_sched_job, node); if (job) { + /* + * Remove the bad job so it cannot be freed by concurrent + * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread + * is parked at which point it's safe. + */ + list_del_init(&job->node); + spin_unlock_irqrestore(&sched->job_list_lock, flags); + job->sched->ops->timedout_job(job); /* @@ -298,6 +309,8 @@ static void drm_sched_job_timedout(struct work_struct *work) job->sched->ops->free_job(job); sched->free_guilty = false; } + } else { + spin_unlock_irqrestore(&sched->job_list_lock, flags); } spin_lock_irqsave(&sched->job_list_lock, flags); @@ -370,6 +383,20 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) kthread_park(sched->thread); /* + * Reinsert back the bad job here - now it's safe as + * drm_sched_get_cleanup_job cannot race against us and release the + * bad job at this point - we parked (waited for) any in progress + * (earlier) cleanups and drm_sched_get_cleanup_job will not be called + * now until the scheduler thread is unparked. + */ + if (bad && bad->sched == sched) + /* + * Add at the head of the queue to reflect it was the earliest + * job extracted. + */ + list_add(&bad->node, &sched->ring_mirror_list); + + /* * Iterate the job list from later to earlier one and either deactive * their HW callbacks or remove them from mirror list if they already * signaled. @@ -496,8 +523,10 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) fence = sched->ops->run_job(s_job); if (IS_ERR_OR_NULL(fence)) { + if (IS_ERR(fence)) + dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); + s_job->s_fence->parent = NULL; - dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); } else { s_job->s_fence->parent = fence; } @@ -748,8 +777,9 @@ static int drm_sched_main(void *param) r); dma_fence_put(fence); } else { + if (IS_ERR(fence)) + dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); - dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); drm_sched_process_job(NULL, &sched_job->cb); } |