drm/xe/guc_submit: add back fix

Daniele noticed that the fix in commit 2d2be279f1ca ("drm/xe: fix UAF
around queue destruction") looks to have been unintentionally removed as
part of handling a conflict in some past merge commit. Add it back.

Fixes: ac44ff7cec33 ("Merge tag 'drm-xe-fixes-2024-10-10' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes")
Reported-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250603174213.1543579-2-matthew.auld@intel.com
(cherry picked from commit 9d9fca62dc49d96f97045b6d8e7402a95f8cf92a)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 369be36..66a5a75 100644 (file)
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -229,6 +229,17 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
        struct xe_guc *guc = arg;
+       struct xe_device *xe = guc_to_xe(guc);
+       struct xe_gt *gt = guc_to_gt(guc);
+       int ret;
+
+       ret = wait_event_timeout(guc->submission_state.fini_wq,
+                                xa_empty(&guc->submission_state.exec_queue_lookup),
+                                HZ * 5);
+
+       drain_workqueue(xe->destroy_wq);
+
+       xe_gt_assert(gt, ret);
 
        xa_destroy(&guc->submission_state.exec_queue_lookup);
 }