drm/xe/xe_guc_submit: Fix exec queue stop race condition

[ Upstream commit 1564d411e17f51e2f64655b4e4da015be1ba7eaa ]

Reorder the xe_sched_tdr_queue_imm and set_exec_queue_banned calls in
guc_exec_queue_stop.  This prevents a possible race condition between
the two events in which it's possible for xe_sched_tdr_queue_imm to
wake the ufence waiter before the exec queue is banned, causing the
ufence waiter to miss the banned state.

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240510194540.3246991-1-jonathan.cavitt@intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index e4e3658e6a1384b9d2936de133dcd322065392e2..0f42971ff0a831e841e882515df48b0baa2e0589 100644 (file)
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1429,8 +1429,8 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
                            !xe_sched_job_completed(job)) ||
                            xe_sched_invalidate_job(job, 2)) {
                                trace_xe_sched_job_ban(job);
-                               xe_sched_tdr_queue_imm(&q->guc->sched);
                                set_exec_queue_banned(q);
+                               xe_sched_tdr_queue_imm(&q->guc->sched);
                        }
                }
        }