Re: [PATCH] drm/xe: Invert runnable_state / pending enable check and assert

[John Harrison <john.c.harrison@intel.com>]

On 6/12/2024 19:34, Matthew Brost wrote:
> Rather than checking for pending enable and asserting runnable_state ==
> 1 in sched done handler, invert these. This is more robust code taking
> action based on the G2H message and asserting KMD tracking state is
> correct.
>
> Suggested-by: John Harrison <John.C.Harrison@Intel.com>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>

> ---
>   drivers/gpu/drm/xe/xe_guc_submit.c | 4 ++--
>   1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 74552391dc5a..373447758a60 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1782,8 +1782,8 @@ static void handle_sched_done(struct xe_guc *guc, struct xe_exec_queue *q,
>   {
>   	trace_xe_exec_queue_scheduling_done(q);
>   
> -	if (exec_queue_pending_enable(q)) {
> -		xe_gt_assert(guc_to_gt(guc), runnable_state == 1);
> +	if (runnable_state == 1) {
> +		xe_gt_assert(guc_to_gt(guc), exec_queue_pending_enable(q));
>   
>   		q->guc->resume_time = ktime_get();
>   		clear_exec_queue_pending_enable(q);