Received-SPF: pass (google.com: domain of linux-kernel+bounces-31957-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
Precedence: bulk
MIME-Version: 1.0
References: <20240117031212.1104034-1-nunes.erico@gmail.com>
 <20240117031212.1104034-5-nunes.erico@gmail.com> <CAKGbVbv-4e7w8_8AGvFd358j-QcG8KJ1zdUZ3kit9odSCatZ5w@mail.gmail.com>
In-Reply-To: <CAKGbVbv-4e7w8_8AGvFd358j-QcG8KJ1zdUZ3kit9odSCatZ5w@mail.gmail.com>
From: Qiang Yu <yuq825@gmail.com>
Date: Sun, 21 Jan 2024 11:04:38 +0800
Message-ID: <CAKGbVbugkHADEw_EigJmrVJzc4NSaHRpvL-3HRdw6U_=5B5u7Q@mail.gmail.com>
Subject: Re: [PATCH v1 4/6] drm/lima: handle spurious timeouts due to high irq latency
To: Erico Nunes <nunes.erico@gmail.com>
Cc: dri-devel@lists.freedesktop.org, lima@lists.freedesktop.org, 
	anarsoul@gmail.com, Maarten Lankhorst <maarten.lankhorst@linux.intel.com>, 
	Maxime Ripard <mripard@kernel.org>, Thomas Zimmermann <tzimmermann@suse.de>, 
	David Airlie <airlied@gmail.com>, Daniel Vetter <daniel@ffwll.ch>, 
	Sumit Semwal <sumit.semwal@linaro.org>, christian.koenig@amd.com, 
	linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Fri, Jan 19, 2024 at 9:43=E2=80=AFAM Qiang Yu <yuq825@gmail.com> wrote:
>
> On Wed, Jan 17, 2024 at 11:12=E2=80=AFAM Erico Nunes <nunes.erico@gmail.c=
om> wrote:
> >
> > There are several unexplained and unreproduced cases of rendering
> > timeouts with lima, for which one theory is high IRQ latency coming fro=
m
> > 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@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/l=
ima_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@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 =3D &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 =3D dma_fence_get(task->fence);
> >
> >         pipe->current_task =3D 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 =3D to_lima_pipe(job->sched);
> >         struct lima_sched_task *task =3D to_lima_task(job);
> >         struct lima_device *ldev =3D pipe->ldev;
> > +       struct lima_ip *ip =3D 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;
> > +       }
> > +
> You may just remove this check and left the check after sync irq.
>
After more thinking, this is only for handling spurious timeouts more
efficiently, not for totally reliable timeout handling. So this check shoul=
d
be OK.

> > +       /*
> > +        * Lima IRQ handler may take a long time to process an interrup=
t
> > +        * if there is another IRQ handler hogging the processing.
> > +        * In order to catch such cases and not report spurious Lima jo=
b
> > +        * timeouts, synchronize the IRQ handler and re-check the fence
> > +        * status.
> > +        */
> > +       synchronize_irq(ip->irq);
> This should be done after drm_sched_stop() to prevent drm scheduler
> run more jobs. And we need to disable interrupt of GP/PP for no more
> running job triggered fresh INT.
This is OK too. We just need to solve reliable timeout handling after
drm_sched_stop() in another patch.

>
> PP may have more than one IRQ, so we need to wait on all of them.
>
> > +
> > +       if (dma_fence_is_signaled(task->done_fence)) {
> > +               DRM_WARN("%s unexpectedly high interrupt latency\n", li=
ma_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/l=
ima_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;
> > +
> >         /* pipe fence */
> >         struct dma_fence *fence;
> >  };
> > --
> > 2.43.0
> >