From 5a9a2ff2a6c04d48ecb949526c797d73f6d37fc7 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Thu, 18 Oct 2018 12:32:46 -0400 Subject: [PATCH 0710/2940] drm/sched: Add boolean to mark if sched is ready to work v5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Problem: A particular scheduler may become unsuable (underlying HW) after some event (e.g. GPU reset). If it's later chosen by the get free sched. policy a command will fail to be submitted. Fix: Add a driver specific callback to report the sched status so rq with bad sched can be avoided in favor of working one or none in which case job init will fail. v2: Switch from driver callback to flag in scheduler. v3: rebase v4: Remove ready paramter from drm_sched_init, set uncoditionally to true once init done. v5: fix missed change in v3d in v4 (Alex) Signed-off-by: Andrey Grodzovsky Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/scheduler/sched_entity.c | 9 ++++++++- drivers/gpu/drm/scheduler/sched_main.c | 6 ++++++ include/drm/gpu_scheduler.h | 3 +++ 3 files changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 4e5e95c0cab5..87738f91eee6 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -130,7 +130,14 @@ drm_sched_entity_get_free_sched(struct drm_sched_entity *entity) int i; for (i = 0; i < entity->num_rq_list; ++i) { - num_jobs = atomic_read(&entity->rq_list[i]->sched->num_jobs); + struct drm_gpu_scheduler *sched = entity->rq_list[i]->sched; + + if (!entity->rq_list[i]->sched->ready) { + DRM_WARN("sched%s is not ready, skipping", sched->name); + continue; + } + + num_jobs = atomic_read(&sched->num_jobs); if (num_jobs < min_jobs) { min_jobs = num_jobs; rq = entity->rq_list[i]; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 9ca741f3a0bc..b7e4572f811f 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -372,6 +372,9 @@ int drm_sched_job_init(struct drm_sched_job *job, struct drm_gpu_scheduler *sched; drm_sched_entity_select_rq(entity); + if (!entity->rq) + return -ENOENT; + sched = entity->rq->sched; job->sched = sched; @@ -585,6 +588,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, return PTR_ERR(sched->thread); } + sched->ready = true; return 0; } EXPORT_SYMBOL(drm_sched_init); @@ -600,5 +604,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) { if (sched->thread) kthread_stop(sched->thread); + + sched->ready = false; } EXPORT_SYMBOL(drm_sched_fini); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index bc6a2a1f00fc..63f74e95caff 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -262,6 +262,7 @@ struct drm_sched_backend_ops { * @hang_limit: once the hangs by a job crosses this limit then it is marked * guilty and it will be considered for scheduling further. * @num_jobs: the number of jobs in queue in the scheduler + * @ready: marks if the underlying HW is ready to work * * One scheduler is implemented for each hardware ring. */ @@ -280,12 +281,14 @@ struct drm_gpu_scheduler { spinlock_t job_list_lock; int hang_limit; atomic_t num_jobs; + bool ready; }; int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, uint32_t hw_submission, unsigned hang_limit, long timeout, const char *name); + void drm_sched_fini(struct drm_gpu_scheduler *sched); int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, -- 2.17.1