drm/amdgpu: Pop jobs from the queue more robustly

Replace a copy of DRM scheduler's to_drm_sched_job with a copy of a newly
added drm_sched_entity_queue_pop.

This allows breaking the hidden dependency that queue_node has to be the
first element in struct drm_sched_job.

A comment is also added with a reference to the mailing list discussion
explaining the copied helper will be removed when the whole broken
amdgpu_job_stop_all_jobs_on_sched is removed.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Philipp Stanner <phasta@kernel.org>
Cc: Zhang, Hawking <Hawking.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221105038.79665-3-tvrtko.ursulin@igalia.com

1 files changed, 19 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 100f04475943..1899c601c95c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -411,8 +411,24 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	return fence;
 }
 
-#define to_drm_sched_job(sched_job)		\
-		container_of((sched_job), struct drm_sched_job, queue_node)
+/*
+ * This is a duplicate function from DRM scheduler sched_internal.h.
+ * Plan is to remove it when amdgpu_job_stop_all_jobs_on_sched is removed, due
+ * latter being incorrect and racy.
+ *
+ * See https://lore.kernel.org/amd-gfx/44edde63-7181-44fb-a4f7-94e50514f539@amd.com/
+ */
+static struct drm_sched_job *
+drm_sched_entity_queue_pop(struct drm_sched_entity *entity)
+{
+	struct spsc_node *node;
+
+	node = spsc_queue_pop(&entity->job_queue);
+	if (!node)
+		return NULL;
+
+	return container_of(node, struct drm_sched_job, queue_node);
+}
 
 void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 {
@@ -425,7 +441,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 		struct drm_sched_rq *rq = sched->sched_rq[i];
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list) {
-			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {
+			while ((s_job = drm_sched_entity_queue_pop(s_entity))) {
 				struct drm_sched_fence *s_fence = s_job->s_fence;
 
 				dma_fence_signal(&s_fence->scheduled);