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

[Qiang Yu]

On Wed, Jan 17, 2024 at 11:12 AM Erico Nunes <nunes.erico at gmail.com> wrote:
>
> There are several unexplained and unreproduced cases of rendering
> timeouts with lima, for which one theory is high IRQ latency coming from
> somewhere else in the system.
> This kind of occurrence may cause applications to trigger unnecessary
> resets of the GPU or even applications to hang if it hits an issue in
> the recovery path.
> Panfrost already does some special handling to account for such
> "spurious timeouts", it makes sense to have this in lima too to reduce
> the chance that it hit users.
>
> Signed-off-by: Erico Nunes <nunes.erico at gmail.com>
> ---
>  drivers/gpu/drm/lima/lima_sched.c | 32 ++++++++++++++++++++++++++-----
>  drivers/gpu/drm/lima/lima_sched.h |  2 ++
>  2 files changed, 29 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
> index 66317296d831..9449b81bcd5b 100644
> --- a/drivers/gpu/drm/lima/lima_sched.c
> +++ b/drivers/gpu/drm/lima/lima_sched.c
> @@ -1,6 +1,7 @@
>  // SPDX-License-Identifier: GPL-2.0 OR MIT
>  /* Copyright 2017-2019 Qiang Yu <yuq825 at gmail.com> */
>
> +#include <linux/hardirq.h>
>  #include <linux/iosys-map.h>
>  #include <linux/kthread.h>
>  #include <linux/slab.h>
> @@ -223,10 +224,7 @@ static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job)
>
>         task->fence = &fence->base;
>
> -       /* for caller usage of the fence, otherwise irq handler
> -        * may consume the fence before caller use it
> -        */
> -       dma_fence_get(task->fence);
> +       task->done_fence = dma_fence_get(task->fence);
>
>         pipe->current_task = task;
>
> @@ -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;
> +       }
> +
> +       /*
> +        * 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);
>
> diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h
> index 6a11764d87b3..34050facb110 100644
> --- a/drivers/gpu/drm/lima/lima_sched.h
> +++ b/drivers/gpu/drm/lima/lima_sched.h
> @@ -29,6 +29,8 @@ struct lima_sched_task {
>         bool recoverable;
>         struct lima_bo *heap;
>
> +       struct dma_fence *done_fence;
This is same as the following fence, do we really need a duplicated one?

> +
>         /* pipe fence */
>         struct dma_fence *fence;
>  };
> --
> 2.43.0
>