drm/xe: Return first unsignaled job first pending job helper

In all cases where the first pending job helper is called, we only want
to retrieve the first unsignaled pending job, as this helper is used
exclusively in recovery flows. It is possible for signaled jobs to
remain in the pending list as the scheduler is stopped, so those should
be skipped.

Also, add kernel documentation to clarify this behavior.

v8:
 - Split out into own patch (Auld)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20251008214532.3442967-6-matthew.brost@intel.com

1 files changed, 17 insertions, 4 deletions

diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index e548b2aed95a..3a9ff78d9346 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -77,17 +77,30 @@ static inline void xe_sched_add_pending_job(struct xe_gpu_scheduler *sched,
 	spin_unlock(&sched->base.job_list_lock);
 }
 
+/**
+ * xe_sched_first_pending_job() - Find first pending job which is unsignaled
+ * @sched: Xe GPU scheduler
+ *
+ * Return first unsignaled job in pending list or NULL
+ */
 static inline
 struct xe_sched_job *xe_sched_first_pending_job(struct xe_gpu_scheduler *sched)
 {
-	struct xe_sched_job *job;
+	struct xe_sched_job *job, *r_job = NULL;
 
 	spin_lock(&sched->base.job_list_lock);
-	job = list_first_entry_or_null(&sched->base.pending_list,
-				       struct xe_sched_job, drm.list);
+	list_for_each_entry(job, &sched->base.pending_list, drm.list) {
+		struct drm_sched_fence *s_fence = job->drm.s_fence;
+		struct dma_fence *hw_fence = s_fence->parent;
+
+		if (hw_fence && !dma_fence_is_signaled(hw_fence)) {
+			r_job = job;
+			break;
+		}
+	}
 	spin_unlock(&sched->base.job_list_lock);
 
-	return job;
+	return r_job;
 }
 
 static inline int