[PATCH] drm/scheduler: put killed job cleanup to worker

[Lucas Stach]

drm_sched_entity_kill_jobs_cb() is called right from the last scheduled
job finished fence signaling. As this might happen from IRQ context we
now end up calling the GPU driver free_job callback in IRQ context, while
all other paths call it from normal process context.

Etnaviv in particular calls core kernel functions that are only valid to
be called from process context when freeing the job. Other drivers might
have similar issues, but I did not validate this. Fix this by punting
the cleanup work into a work item, so the driver expectations are met.

Signed-off-by: Lucas Stach <l.stach at pengutronix.de>
---
 drivers/gpu/drm/scheduler/sched_entity.c | 28 ++++++++++++++----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 35ddbec1375a..ba4eb66784b9 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -202,23 +202,23 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 }
 EXPORT_SYMBOL(drm_sched_entity_flush);
 
-/**
- * drm_sched_entity_kill_jobs - helper for drm_sched_entity_kill_jobs
- *
- * @f: signaled fence
- * @cb: our callback structure
- *
- * Signal the scheduler finished fence when the entity in question is killed.
- */
+static void drm_sched_entity_kill_work(struct work_struct *work)
+{
+	struct drm_sched_job *job = container_of(work, struct drm_sched_job,
+						 finish_work);
+
+	drm_sched_fence_finished(job->s_fence);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
 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);
 
-	drm_sched_fence_finished(job->s_fence);
-	WARN_ON(job->s_fence->parent);
-	job->sched->ops->free_job(job);
+	schedule_work(&job->finish_work);
 }
 
 /**
@@ -240,6 +240,12 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
 		drm_sched_fence_scheduled(s_fence);
 		dma_fence_set_error(&s_fence->finished, -ESRCH);
 
+		/*
+		 * Replace regular finish work function with one that just
+		 * kills the job.
+		 */
+		job->finish_work.func = drm_sched_entity_kill_work;
+
 		/*
 		 * When pipe is hanged by older entity, new entity might
 		 * not even have chance to submit it's first job to HW
-- 
2.20.1