Re: [PATCH] drm/xe: Add process name and PID to job timedout message

[Matthew Brost <matthew.brost@intel.com>]

On Wed, Jul 10, 2024 at 02:31:49PM -0700, José Roberto de Souza wrote:
> This will be very helpful for Mesa CI, where it uses PID to match
> the exacly test that cause timedout/GPU hang and mark that test as
> failing.
> 
> Also printing the process name as it might be relavant for human
> readers.
> 

Always for adding useful debug info...

> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_guc_submit.c | 17 +++++++++++++++--
>  1 file changed, 15 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 6392381e8e697..8604055271156 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1060,7 +1060,10 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
>  	struct xe_exec_queue *q = job->q;
>  	struct xe_gpu_scheduler *sched = &q->guc->sched;
>  	struct xe_guc *guc = exec_queue_to_guc(q);
> +	const char *process_name = "no process";
> +	struct task_struct *task = NULL;
>  	int err = -ETIME;
> +	pid_t pid = -1;
>  	int i = 0;
>  	bool wedged, skip_timeout_check;
>  
> @@ -1157,9 +1160,19 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
>  		goto sched_enable;
>  	}
>  
> -	xe_gt_notice(guc_to_gt(guc), "Timedout job: seqno=%u, lrc_seqno=%u, guc_id=%d, flags=0x%lx",
> +	if (q->vm && q->vm->xef) {
> +		task = get_pid_task(q->vm->xef->drm->pid, PIDTYPE_PID);

We do something simliar in devcoredump_snapshot.

Would it be worth while to have a helper like this?

struct task_struct *task xe_exec_queue_get_pid_task(struct xe_exec_queue *q)
{
	if (q->vm && q->vm->xef)
		return get_pid_task(q->vm->xef->drm->pid, PIDTYPE_PID);;

	return NULL;
}

Matt

> +		if (task) {
> +			process_name = task->comm;
> +			pid = task->pid;
> +		}
> +	}
> +	xe_gt_notice(guc_to_gt(guc), "Timedout job: seqno=%u, lrc_seqno=%u, guc_id=%d, flags=0x%lx in %s [%d]",
>  		     xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),
> -		     q->guc->id, q->flags);
> +		     q->guc->id, q->flags, process_name, pid);
> +	if (task)
> +		put_task_struct(task);
> +
>  	trace_xe_sched_job_timedout(job);
>  
>  	if (!exec_queue_killed(q))
> -- 
> 2.45.2
>