From 9f1ecfc5dcb47a7ca37be47b0eaca0f37f1ae93d Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 23 Nov 2022 03:13:03 +0300 Subject: [PATCH] drm/scheduler: Fix lockup in drm_sched_entity_kill() MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit 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 Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20221123001303.533968-1-dmitry.osipenko@collabora.com --- drivers/gpu/drm/scheduler/sched_entity.c | 2 +- drivers/gpu/drm/scheduler/sched_main.c | 4 ++-- 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 fe09e5b..15d04a0 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 6ce04c2..857ec20 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1026,7 +1026,7 @@ 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; } @@ -1037,7 +1037,7 @@ 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)) { -- 2.7.4