1 files changed, 58 insertions, 11 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 67382621b429..719b1a6dbb90 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -48,9 +48,11 @@
 #include <linux/wait.h>
 #include <linux/sched.h>
 #include <linux/completion.h>
+#include <linux/dma-resv.h>
 #include <uapi/linux/sched/types.h>
 
 #include <drm/drm_print.h>
+#include <drm/drm_gem.h>
 #include <drm/gpu_scheduler.h>
 #include <drm/spsc_queue.h>
 
@@ -564,7 +566,6 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext);
 
 /**
  * drm_sched_job_init - init a scheduler job
- *
  * @job: scheduler job to init
  * @entity: scheduler entity to use
  * @owner: job owner for debugging
@@ -572,27 +573,28 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext);
  * Refer to drm_sched_entity_push_job() documentation
  * for locking considerations.
  *
+ * Drivers must make sure drm_sched_job_cleanup() if this function returns
+ * successfully, even when @job is aborted before drm_sched_job_arm() is called.
+ *
+ * WARNING: amdgpu abuses &drm_sched.ready to signal when the hardware
+ * has died, which can mean that there's no valid runqueue for a @entity.
+ * This function returns -ENOENT in this case (which probably should be -EIO as
+ * a more meanigful return value).
+ *
  * Returns 0 for success, negative error code otherwise.
  */
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
-	struct drm_gpu_scheduler *sched;
-
 	drm_sched_entity_select_rq(entity);
 	if (!entity->rq)
 		return -ENOENT;
 
-	sched = entity->rq->sched;
-
-	job->sched = sched;
 	job->entity = entity;
-	job->s_priority = entity->rq - sched->sched_rq;
-	job->s_fence = drm_sched_fence_create(entity, owner);
+	job->s_fence = drm_sched_fence_alloc(entity, owner);
 	if (!job->s_fence)
 		return -ENOMEM;
-	job->id = atomic64_inc_return(&sched->job_id_count);
 
 	INIT_LIST_HEAD(&job->list);
 
@@ -601,13 +603,58 @@ int drm_sched_job_init(struct drm_sched_job *job,
 EXPORT_SYMBOL(drm_sched_job_init);
 
 /**
- * drm_sched_job_cleanup - clean up scheduler job resources
+ * drm_sched_job_arm - arm a scheduler job for execution
+ * @job: scheduler job to arm
+ *
+ * This arms a scheduler job for execution. Specifically it initializes the
+ * &drm_sched_job.s_fence of @job, so that it can be attached to struct dma_resv
+ * or other places that need to track the completion of this job.
+ *
+ * Refer to drm_sched_entity_push_job() documentation for locking
+ * considerations.
  *
+ * This can only be called if drm_sched_job_init() succeeded.
+ */
+void drm_sched_job_arm(struct drm_sched_job *job)
+{
+	struct drm_gpu_scheduler *sched;
+	struct drm_sched_entity *entity = job->entity;
+
+	BUG_ON(!entity);
+
+	sched = entity->rq->sched;
+
+	job->sched = sched;
+	job->s_priority = entity->rq - sched->sched_rq;
+	job->id = atomic64_inc_return(&sched->job_id_count);
+
+	drm_sched_fence_init(job->s_fence, job->entity);
+}
+EXPORT_SYMBOL(drm_sched_job_arm);
+
+/**
+ * drm_sched_job_cleanup - clean up scheduler job resources
  * @job: scheduler job to clean up
+ *
+ * Cleans up the resources allocated with drm_sched_job_init().
+ *
+ * Drivers should call this from their error unwind code if @job is aborted
+ * before drm_sched_job_arm() is called.
+ *
+ * After that point of no return @job is committed to be executed by the
+ * scheduler, and this function should be called from the
+ * &drm_sched_backend_ops.free_job callback.
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
-	dma_fence_put(&job->s_fence->finished);
+	if (kref_read(&job->s_fence->finished.refcount)) {
+		/* drm_sched_job_arm() has been called */
+		dma_fence_put(&job->s_fence->finished);
+	} else {
+		/* aborted job before committing to run it */
+		drm_sched_fence_free(&job->s_fence->finished.rcu);
+	}
+
 	job->s_fence = NULL;
 }
 EXPORT_SYMBOL(drm_sched_job_cleanup);