From: Qiang Yu <yuq825@gmail.com>
To: Erico Nunes <nunes.erico@gmail.com>
Cc: anarsoul@gmail.com, christian.koenig@amd.com,
dri-devel@lists.freedesktop.org, lima@lists.freedesktop.org,
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>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 5/8] drm/lima: handle spurious timeouts due to high irq latency
Date: Wed, 24 Jan 2024 20:38:02 +0800 [thread overview]
Message-ID: <CAKGbVbsjNdnoNW2JnxCiyZg-wjU0UK+jgsG18OFaHjdkdOWRQA@mail.gmail.com> (raw)
In-Reply-To: <20240124025947.2110659-6-nunes.erico@gmail.com>
On Wed, Jan 24, 2024 at 11:00 AM Erico Nunes <nunes.erico@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@gmail.com>
> ---
> drivers/gpu/drm/lima/lima_sched.c | 31 ++++++++++++++++++++++++++++---
> 1 file changed, 28 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
> index c3bf8cda8498..814428564637 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>
> @@ -401,9 +402,35 @@ 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];
> + int i;
> +
> + /*
> + * If the GPU managed to complete this jobs fence, the timeout is
> + * spurious. Bail out.
> + */
> + if (dma_fence_is_signaled(task->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.
> + */
> + for (i = 0; i < pipe->num_processor; i++)
> + synchronize_irq(pipe->processor[i]->irq);
> +
I have a question, this timeout handler will be called when GP/PP error IRQ.
If we call synchronize_irq() in the IRQ handler, will we block ourselves here?
> + if (dma_fence_is_signaled(task->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 job timeout\n", lima_ip_name(ip));
>
> drm_sched_stop(&pipe->base, &task->base);
>
> @@ -417,8 +444,6 @@ static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job
> if (pipe->bcast_mmu)
> lima_mmu_page_fault_resume(pipe->bcast_mmu);
> else {
> - int i;
> -
> for (i = 0; i < pipe->num_mmu; i++)
> lima_mmu_page_fault_resume(pipe->mmu[i]);
> }
> --
> 2.43.0
>
next prev parent reply other threads:[~2024-01-24 12:38 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-24 2:59 [PATCH v2 0/8] drm/lima: fixes and improvements to error recovery Erico Nunes
2024-01-24 2:59 ` [PATCH v2 1/8] drm/lima: reset async_reset on pp hard reset Erico Nunes
2024-01-24 2:59 ` [PATCH v2 2/8] drm/lima: reset async_reset on gp " Erico Nunes
2024-01-24 2:59 ` [PATCH v2 3/8] drm/lima: set pp bus_stop bit before " Erico Nunes
2024-01-24 2:59 ` [PATCH v2 4/8] drm/lima: set gp " Erico Nunes
2024-01-24 2:59 ` [PATCH v2 5/8] drm/lima: handle spurious timeouts due to high irq latency Erico Nunes
2024-01-24 12:38 ` Qiang Yu [this message]
2024-01-29 22:55 ` Erico Nunes
2024-01-30 1:05 ` Qiang Yu
2024-01-24 2:59 ` [PATCH v2 6/8] drm/lima: remove guilty drm_sched context handling Erico Nunes
2024-01-24 2:59 ` [PATCH v2 7/8] drm/lima: increase default job timeout to 10s Erico Nunes
2024-01-24 2:59 ` [PATCH v2 8/8] drm/lima: standardize debug messages by ip name Erico Nunes
2024-01-30 1:07 ` [PATCH v2 0/8] drm/lima: fixes and improvements to error recovery Qiang Yu
2024-02-12 8:40 ` Qiang Yu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAKGbVbsjNdnoNW2JnxCiyZg-wjU0UK+jgsG18OFaHjdkdOWRQA@mail.gmail.com \
--to=yuq825@gmail.com \
--cc=airlied@gmail.com \
--cc=anarsoul@gmail.com \
--cc=christian.koenig@amd.com \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=lima@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maarten.lankhorst@linux.intel.com \
--cc=mripard@kernel.org \
--cc=nunes.erico@gmail.com \
--cc=sumit.semwal@linaro.org \
--cc=tzimmermann@suse.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).