[Intel-gfx] [PATCH] drm/i915/gt: Report the currently active execlists request

[Mika Kuoppala]

Chris Wilson <chris at chris-wilson.co.uk> writes:

> Since commit 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy"), we
> prune the engine->active.requests list prior to preemption, thus
> removing the trace of the currently executing request. If that request
> hangs rather than be preempted, we conclude that no active request was
> on the GPU. Fortunately, this only impacts our debugging, and not our
> means of hang detection or recovery.
>
> References: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_engine_cs.c | 29 ++++++++++++++++++-----
>  1 file changed, 23 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> index 06ff7695fa29..93878fd42a7a 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> @@ -1643,7 +1643,7 @@ static bool match_ring(struct i915_request *rq)
>  struct i915_request *
>  intel_engine_find_active_request(struct intel_engine_cs *engine)
>  {
> -	struct i915_request *request, *active = NULL;
> +	struct i915_request *rq, *active = NULL;
>  
>  	/*
>  	 * We are called by the error capture, reset and to dump engine
> @@ -1657,18 +1657,35 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
>  	 * we only care about the snapshot of this moment.
>  	 */
>  	lockdep_assert_held(&engine->active.lock);
> -	list_for_each_entry(request, &engine->active.requests, sched.link) {
> -		if (i915_request_completed(request))
> +
> +	rcu_read_lock();
> +	rq = execlists_active(&engine->execlists);
> +	if (rq) {
> +		struct intel_timeline *tl = rq->context->timeline;
> +
> +		list_for_each_entry_continue_reverse(rq, &tl->requests, link) {
> +			if (i915_request_completed(rq))
> +				break;

This will be active - 1. So it makes me think that
we should first check that the real active has not completed.

-Mika

> +
> +			active = rq;
> +		}
> +	}
> +	rcu_read_unlock();
> +	if (active)
> +		return active;
> +
> +	list_for_each_entry(rq, &engine->active.requests, sched.link) {
> +		if (i915_request_completed(rq))
>  			continue;
>  
> -		if (!i915_request_started(request))
> +		if (!i915_request_started(rq))
>  			continue;
>  
>  		/* More than one preemptible request may match! */
> -		if (!match_ring(request))
> +		if (!match_ring(rq))
>  			continue;
>  
> -		active = request;
> +		active = rq;
>  		break;
>  	}
>  
> -- 
> 2.25.0