summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDmitry Osipenko <dmitry.osipenko@collabora.com>2022-11-23 03:13:03 +0300
committerDmitry Osipenko <dmitry.osipenko@collabora.com>2023-01-03 14:49:59 +0300
commit69555549cfa42e10f2fdd2699ed4e34d9d4f392b (patch)
tree78ff141b0cf4f63f99b210054139a90f8bd8124f
parent2c55d703391acf7e9101da596d0c15ee03b318a3 (diff)
drm/scheduler: Fix lockup in drm_sched_entity_kill()drm-misc-fixes-2023-01-05
The drm_sched_entity_kill() is invoked twice by drm_sched_entity_destroy() while userspace process is exiting or being killed. First time it's invoked when sched entity is flushed and second time when entity is released. This causes a lockup within wait_for_completion(entity_idle) due to how completion API works. Calling wait_for_completion() more times than complete() was invoked is a error condition that causes lockup because completion internally uses counter for complete/wait calls. The complete_all() must be used instead in such cases. This patch fixes lockup of Panfrost driver that is reproducible by killing any application in a middle of 3d drawing operation. Fixes: 2fdb8a8f07c2 ("drm/scheduler: rework entity flush, kill and fini") Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> Reviewed-by: Christian König <christian.koenig@amd.com> Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com> # Steam Deck Link: https://patchwork.freedesktop.org/patch/msgid/20221123001303.533968-1-dmitry.osipenko@collabora.com
-rw-r--r--drivers/gpu/drm/scheduler/sched_entity.c2
-rw-r--r--drivers/gpu/drm/scheduler/sched_main.c4
2 files changed, 3 insertions, 3 deletions
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index fe09e5be79bd..15d04a0ec623 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -81,7 +81,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
init_completion(&entity->entity_idle);
/* We start in an idle state. */
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
spin_lock_init(&entity->rq_lock);
spsc_queue_init(&entity->job_queue);
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 31f3a1267be4..fd22d753b4ed 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -987,7 +987,7 @@ static int drm_sched_main(void *param)
sched_job = drm_sched_entity_pop_job(entity);
if (!sched_job) {
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
continue;
}
@@ -998,7 +998,7 @@ static int drm_sched_main(void *param)
trace_drm_run_job(sched_job, entity);
fence = sched->ops->run_job(sched_job);
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
drm_sched_fence_scheduled(s_fence);
if (!IS_ERR_OR_NULL(fence)) {