drm/nouveau: sched: fix leaking memory of timedout job

Always stop and re-start the scheduler in order to let the scheduler
free up the timedout job in case it got signaled. In case of exec jobs
the job type specific callback will take care to signal all fences and
tear down the channel.

Fixes: b88baab ("drm/nouveau: implement new VM_BIND uAPI")
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230916162835.5719-1-dakr@redhat.com

Author: dakr

drivers/gpu/drm/nouveau/nouveau_exec.c

@@ -213,7 +213,7 @@ nouveau_exec_job_timeout(struct nouveau_job *job)
 
 	nouveau_sched_entity_fini(job->entity);
 
-	return DRM_GPU_SCHED_STAT_ENODEV;
+	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 
 static struct nouveau_job_ops nouveau_exec_job_ops = {

drivers/gpu/drm/nouveau/nouveau_sched.c

@@ -375,14 +375,20 @@ nouveau_sched_run_job(struct drm_sched_job *sched_job)
 static enum drm_gpu_sched_stat
 nouveau_sched_timedout_job(struct drm_sched_job *sched_job)
 {
+	struct drm_gpu_scheduler *sched = sched_job->sched;
 	struct nouveau_job *job = to_nouveau_job(sched_job);
+	enum drm_gpu_sched_stat stat = DRM_GPU_SCHED_STAT_NOMINAL;
 
-	NV_PRINTK(warn, job->cli, "Job timed out.\n");
+	drm_sched_stop(sched, sched_job);
 
 	if (job->ops->timeout)
-		return job->ops->timeout(job);
+		stat = job->ops->timeout(job);
+	else
+		NV_PRINTK(warn, job->cli, "Generic job timeout.\n");
+
+	drm_sched_start(sched, true);
 
-	return DRM_GPU_SCHED_STAT_ENODEV;
+	return stat;
 }
 
 static void