[PATCH v4 1/3] drm/xe/xe_guc_submit: Fix exec queue stop race condition

[Summers, Stuart]

On Fri, 2024-04-05 at 10:55 -0700, Jonathan Cavitt wrote:
> 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 at intel.com>
> Signed-off-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
> Reviewed-by: Matthew Brost <matthew.brost at intel.com>

Reviewed-by: Stuart Summers <stuart.summers at intel.com>

> ---
> 
> v2: Expand on cause of race condition
> 
>  drivers/gpu/drm/xe/xe_guc_submit.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c
> b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 9c30bd9ac8c06..1a6abb10a960e 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1430,8 +1430,8 @@ 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);
>                         }
>                 }
>         }