Re: [PATCH v1 4/6] drm/lima: handle spurious timeouts due to high irq latency

[Hillf Danton <hdanton@sina.com>]

On Wed, 17 Jan 2024 04:12:10 +0100 Erico Nunes <nunes.erico@gmail.com>
>  
> @@ -401,9 +399,33 @@ static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job
>  	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
>  	struct lima_sched_task *task = to_lima_task(job);
>  	struct lima_device *ldev = pipe->ldev;
> +	struct lima_ip *ip = pipe->processor[0];
> +
> +	/*
> +	 * If the GPU managed to complete this jobs fence, the timeout is
> +	 * spurious. Bail out.
> +	 */
> +	if (dma_fence_is_signaled(task->done_fence)) {
> +		DRM_WARN("%s spurious timeout\n", lima_ip_name(ip));
> +		return DRM_GPU_SCHED_STAT_NOMINAL;
> +	}

Given 500ms in lima_sched_pipe_init(), no timeout is spurious by define,
and stop selling bandaid like this because you have options like locating
the reasons behind timeout.
> +
> +	/*
> +	 * Lima IRQ handler may take a long time to process an interrupt
> +	 * if there is another IRQ handler hogging the processing.
> +	 * In order to catch such cases and not report spurious Lima job
> +	 * timeouts, synchronize the IRQ handler and re-check the fence
> +	 * status.
> +	 */
> +	synchronize_irq(ip->irq);
> +
> +	if (dma_fence_is_signaled(task->done_fence)) {
> +		DRM_WARN("%s unexpectedly high interrupt latency\n", lima_ip_name(ip));
> +		return DRM_GPU_SCHED_STAT_NOMINAL;
> +	}
>  
>  	if (!pipe->error)
> -		DRM_ERROR("lima job timeout\n");
> +		DRM_ERROR("%s lima job timeout\n", lima_ip_name(ip));
>  
>  	drm_sched_stop(&pipe->base, &task->base);
>