diff options
Diffstat (limited to 'drivers/gpu/drm/scheduler')
| -rw-r--r-- | drivers/gpu/drm/scheduler/sched_entity.c | 40 | ||||
| -rw-r--r-- | drivers/gpu/drm/scheduler/sched_main.c | 33 | ||||
| -rw-r--r-- | drivers/gpu/drm/scheduler/tests/sched_tests.h | 3 |
3 files changed, 47 insertions, 29 deletions
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 5a4697f636f2..fe174a4857be 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -70,6 +70,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, entity->guilty = guilty; entity->num_sched_list = num_sched_list; entity->priority = priority; + entity->last_user = current->group_leader; /* * It's perfectly valid to initialize an entity without having a valid * scheduler attached. It's just not valid to use the scheduler before it @@ -172,26 +173,15 @@ int drm_sched_entity_error(struct drm_sched_entity *entity) } EXPORT_SYMBOL(drm_sched_entity_error); +static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, + struct dma_fence_cb *cb); + static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk) { struct drm_sched_job *job = container_of(wrk, typeof(*job), work); - - drm_sched_fence_scheduled(job->s_fence, NULL); - drm_sched_fence_finished(job->s_fence, -ESRCH); - WARN_ON(job->s_fence->parent); - job->sched->ops->free_job(job); -} - -/* Signal the scheduler finished fence when the entity in question is killed. */ -static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, - struct dma_fence_cb *cb) -{ - struct drm_sched_job *job = container_of(cb, struct drm_sched_job, - finish_cb); + struct dma_fence *f; unsigned long index; - dma_fence_put(f); - /* Wait for all dependencies to avoid data corruptions */ xa_for_each(&job->dependencies, index, f) { struct drm_sched_fence *s_fence = to_drm_sched_fence(f); @@ -219,6 +209,21 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, dma_fence_put(f); } + drm_sched_fence_scheduled(job->s_fence, NULL); + drm_sched_fence_finished(job->s_fence, -ESRCH); + WARN_ON(job->s_fence->parent); + job->sched->ops->free_job(job); +} + +/* Signal the scheduler finished fence when the entity in question is killed. */ +static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, + struct dma_fence_cb *cb) +{ + struct drm_sched_job *job = container_of(cb, struct drm_sched_job, + finish_cb); + + dma_fence_put(f); + INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work); schedule_work(&job->work); } @@ -302,7 +307,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) /* For a killed process disallow further enqueueing of jobs. */ last_user = cmpxchg(&entity->last_user, current->group_leader, NULL); - if ((!last_user || last_user == current->group_leader) && + if (last_user == current->group_leader && (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) drm_sched_entity_kill(entity); @@ -552,10 +557,11 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity) drm_sched_rq_remove_entity(entity->rq, entity); entity->rq = rq; } - spin_unlock(&entity->lock); if (entity->num_sched_list == 1) entity->sched_list = NULL; + + spin_unlock(&entity->lock); } /** diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 46119aacb809..1d4f1b822e7b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -965,13 +965,14 @@ int drm_sched_job_add_resv_dependencies(struct drm_sched_job *job, dma_resv_assert_held(resv); dma_resv_for_each_fence(&cursor, resv, usage, fence) { - /* Make sure to grab an additional ref on the added fence */ - dma_fence_get(fence); - ret = drm_sched_job_add_dependency(job, fence); - if (ret) { - dma_fence_put(fence); + /* + * As drm_sched_job_add_dependency always consumes the fence + * reference (even when it fails), and dma_resv_for_each_fence + * is not obtaining one, we need to grab one before calling. + */ + ret = drm_sched_job_add_dependency(job, dma_fence_get(fence)); + if (ret) return ret; - } } return 0; } @@ -1236,8 +1237,13 @@ static void drm_sched_run_job_work(struct work_struct *w) /* Find entity with a ready job */ entity = drm_sched_select_entity(sched); - if (!entity) - return; /* No more work */ + if (!entity) { + /* + * Either no more work to do, or the next ready job needs more + * credits than the scheduler has currently available. + */ + return; + } sched_job = drm_sched_entity_pop_job(entity); if (!sched_job) { @@ -1314,7 +1320,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_ sched->name = args->name; sched->timeout = args->timeout; sched->hang_limit = args->hang_limit; - sched->timeout_wq = args->timeout_wq ? args->timeout_wq : system_wq; + sched->timeout_wq = args->timeout_wq ? args->timeout_wq : system_percpu_wq; sched->score = args->score ? args->score : &sched->_score; sched->dev = args->dev; @@ -1419,7 +1425,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) struct drm_sched_rq *rq = sched->sched_rq[i]; spin_lock(&rq->lock); - list_for_each_entry(s_entity, &rq->entities, list) + list_for_each_entry(s_entity, &rq->entities, list) { /* * Prevents reinsertion and marks job_queue as idle, * it will be removed from the rq in drm_sched_entity_fini() @@ -1440,8 +1446,15 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) * For now, this remains a potential race in all * drivers that keep entities alive for longer than * the scheduler. + * + * The READ_ONCE() is there to make the lockless read + * (warning about the lockless write below) slightly + * less broken... */ + if (!READ_ONCE(s_entity->stopped)) + dev_warn(sched->dev, "Tearing down scheduler with active entities!\n"); s_entity->stopped = true; + } spin_unlock(&rq->lock); kfree(sched->sched_rq[i]); } diff --git a/drivers/gpu/drm/scheduler/tests/sched_tests.h b/drivers/gpu/drm/scheduler/tests/sched_tests.h index 7f31d35780cc..553d45abd057 100644 --- a/drivers/gpu/drm/scheduler/tests/sched_tests.h +++ b/drivers/gpu/drm/scheduler/tests/sched_tests.h @@ -31,9 +31,8 @@ * * @base: DRM scheduler base class * @test: Backpointer to owning the kunit test case - * @lock: Lock to protect the simulated @hw_timeline, @job_list and @done_list + * @lock: Lock to protect the simulated @hw_timeline and @job_list * @job_list: List of jobs submitted to the mock GPU - * @done_list: List of jobs completed by the mock GPU * @hw_timeline: Simulated hardware timeline has a @context, @next_seqno and * @cur_seqno for implementing a struct dma_fence signaling the * simulated job completion. |