Commit bf8bbaef authored by Philipp Stanner's avatar Philipp Stanner
Browse files

drm/sched: Avoid memory leaks with cancel_job() callback 



Since its inception, the GPU scheduler can leak memory if the driver
calls drm_sched_fini() while there are still jobs in flight.

The simplest way to solve this in a backwards compatible manner is by
adding a new callback, drm_sched_backend_ops.cancel_job(), which
instructs the driver to signal the hardware fence associated with the
job. Afterwards, the scheduler can safely use the established free_job()
callback for freeing the job.

Implement the new backend_ops callback cancel_job().

Suggested-by: default avatarTvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://lore.kernel.org/dri-devel/20250418113211.69956-1-tvrtko.ursulin@igalia.com/


Reviewed-by: default avatarMaíra Canal <mcanal@igalia.com>
Acked-by: default avatarTvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: default avatarPhilipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250710125412.128476-4-phasta@kernel.org
parent fe69a391

drivers/gpu/drm/scheduler/sched_main.c

+21 −13
Original line number Diff line number Diff line
@@ -1352,6 +1352,18 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_ 
}

EXPORT_SYMBOL(drm_sched_init);



static void drm_sched_cancel_remaining_jobs(struct drm_gpu_scheduler *sched)

{

	struct drm_sched_job *job, *tmp;



	/* All other accessors are stopped. No locking necessary. */

	list_for_each_entry_safe_reverse(job, tmp, &sched->pending_list, list) {

		sched->ops->cancel_job(job);

		list_del(&job->list);

		sched->ops->free_job(job);

	}

}



/**

 * drm_sched_fini - Destroy a gpu scheduler

 *
@@ -1359,19 +1371,11 @@ EXPORT_SYMBOL(drm_sched_init); 
 *

 * Tears down and cleans up the scheduler.

 *

 * This stops submission of new jobs to the hardware through

 * drm_sched_backend_ops.run_job(). Consequently, drm_sched_backend_ops.free_job()

 * will not be called for all jobs still in drm_gpu_scheduler.pending_list.

 * There is no solution for this currently. Thus, it is up to the driver to make

 * sure that:

 *

 *  a) drm_sched_fini() is only called after for all submitted jobs

 *     drm_sched_backend_ops.free_job() has been called or that

 *  b) the jobs for which drm_sched_backend_ops.free_job() has not been called

 *     after drm_sched_fini() ran are freed manually.

 *

 * FIXME: Take care of the above problem and prevent this function from leaking

 * the jobs in drm_gpu_scheduler.pending_list under any circumstances.

 * This stops submission of new jobs to the hardware through &struct

 * drm_sched_backend_ops.run_job. If &struct drm_sched_backend_ops.cancel_job

 * is implemented, all jobs will be canceled through it and afterwards cleaned

 * up through &struct drm_sched_backend_ops.free_job. If cancel_job is not

 * implemented, memory could leak.

 */

void drm_sched_fini(struct drm_gpu_scheduler *sched)

{
@@ -1401,6 +1405,10 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) 
	/* Confirm no work left behind accessing device structures */

	cancel_delayed_work_sync(&sched->work_tdr);



	/* Avoid memory leaks if supported by the driver. */

	if (sched->ops->cancel_job)

		drm_sched_cancel_remaining_jobs(sched);



	if (sched->own_submit_wq)

		destroy_workqueue(sched->submit_wq);

	sched->ready = false;

include/drm/gpu_scheduler.h

+18 −0
Original line number Diff line number Diff line
@@ -512,6 +512,24 @@ struct drm_sched_backend_ops { 
         * and it's time to clean it up.

	 */

	void (*free_job)(struct drm_sched_job *sched_job);



	/**

	 * @cancel_job: Used by the scheduler to guarantee remaining jobs' fences

	 * get signaled in drm_sched_fini().

	 *

	 * Used by the scheduler to cancel all jobs that have not been executed

	 * with &struct drm_sched_backend_ops.run_job by the time

	 * drm_sched_fini() gets invoked.

	 *

	 * Drivers need to signal the passed job's hardware fence with an

	 * appropriate error code (e.g., -ECANCELED) in this callback. They

	 * must not free the job.

	 *

	 * The scheduler will only call this callback once it stopped calling

	 * all other callbacks forever, with the exception of &struct

	 * drm_sched_backend_ops.free_job.

	 */

	void (*cancel_job)(struct drm_sched_job *sched_job);

};



/**