Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Luben Tuikov <luben.tuikov@amd.com>
To: Matthew Brost <matthew.brost@intel.com>,
	dri-devel@lists.freedesktop.org,  intel-xe@lists.freedesktop.org
Cc: robdclark@chromium.org, sarah.walker@imgtec.com,
	ketil.johnsen@arm.com, Liviu.Dudau@arm.com, mcanal@igalia.com,
	frank.binns@imgtec.com, boris.brezillon@collabora.com,
	dakr@redhat.com, donald.robson@imgtec.com, daniel@ffwll.ch,
	lina@asahilina.net, airlied@gmail.com, christian.koenig@amd.com,
	faith.ekstrand@collabora.com
Subject: Re: [Intel-xe] [PATCH v4 07/10] drm/sched: Start submission before TDR in drm_sched_start
Date: Fri, 29 Sep 2023 17:53:10 -0400	[thread overview]
Message-ID: <24bc965f-61fb-4b92-9afa-360ca85a53af@amd.com> (raw)
In-Reply-To: <20230919050155.2647172-8-matthew.brost@intel.com>

Hi,

On 2023-09-19 01:01, Matthew Brost wrote:
> If the TDR is set to a very small value it can fire before the
> submission is started in the function drm_sched_start. The submission is
> expected to running when the TDR fires, fix this ordering so this
> expectation is always met.
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>  drivers/gpu/drm/scheduler/sched_main.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 09ef07b9e9d5..a5cc9b6c2faa 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -684,10 +684,10 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
>  			drm_sched_job_done(s_job, -ECANCELED);
>  	}
>  
> +	drm_sched_submit_start(sched);
> +
>  	if (full_recovery)
>  		drm_sched_start_timeout_unlocked(sched);
> -
> -	drm_sched_submit_start(sched);
>  }
>  EXPORT_SYMBOL(drm_sched_start);

No.

A timeout timer should be started before we submit anything down to the hardware.
See Message-ID: <ed3aca10-8a9f-4698-92f4-21558fa6cfe3@amd.com>,
and Message-ID: <8e5eab14-9e55-42c9-b6ea-02fcc591266d@amd.com>.

You shouldn't start TDR at an arbitrarily late time after job
submission to the hardware. To close this, the timer is started
before jobs are submitted to the hardware.

One possibility is to increase the timeout timer value.
-- 
Regards,
Luben


  reply	other threads:[~2023-09-29 21:53 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-19  5:01 [Intel-xe] [PATCH v4 00/10] DRM scheduler changes for Xe Matthew Brost
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 01/10] drm/sched: Add drm_sched_submit_* helpers Matthew Brost
2023-09-19  5:58   ` Christian König
2023-09-21  3:41     ` Luben Tuikov
2023-09-27  1:07   ` Luben Tuikov
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 02/10] drm/sched: Convert drm scheduler to use a work queue rather than kthread Matthew Brost
2023-09-27  3:32   ` Luben Tuikov
2023-10-05  3:33     ` Matthew Brost
2023-10-05  4:13       ` Luben Tuikov
2023-10-05 15:19         ` Matthew Brost
2023-10-06  7:59         ` Tvrtko Ursulin
2023-10-06 15:14           ` Matthew Brost
2023-10-06 23:43             ` Matthew Brost
2023-10-09  8:35               ` Tvrtko Ursulin
2023-10-11 23:19               ` Luben Tuikov
2023-10-11 23:11             ` Luben Tuikov
2023-10-11 23:10           ` Luben Tuikov
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 03/10] drm/sched: Move schedule policy to scheduler Matthew Brost
2023-09-24  1:18   ` kernel test robot
2023-09-27 12:13   ` Luben Tuikov
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 04/10] drm/sched: Add DRM_SCHED_POLICY_SINGLE_ENTITY scheduling policy Matthew Brost
2023-09-27 14:36   ` Luben Tuikov
2023-10-05  4:02     ` Matthew Brost
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 05/10] drm/sched: Split free_job into own work item Matthew Brost
2023-09-28 16:14   ` Luben Tuikov
2023-10-05  4:06     ` Matthew Brost
2023-10-11 23:29       ` Luben Tuikov
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 06/10] drm/sched: Add drm_sched_start_timeout_unlocked helper Matthew Brost
2023-09-29 21:23   ` Luben Tuikov
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 07/10] drm/sched: Start submission before TDR in drm_sched_start Matthew Brost
2023-09-29 21:53   ` Luben Tuikov [this message]
2023-09-30 19:48     ` Luben Tuikov
2023-10-05  3:11       ` Matthew Brost
2023-10-05  3:18         ` Luben Tuikov
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 08/10] drm/sched: Submit job before starting TDR Matthew Brost
2023-09-29 21:58   ` Luben Tuikov
2023-10-05  4:11     ` Matthew Brost
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 09/10] drm/sched: Add helper to queue TDR immediately for current and future jobs Matthew Brost
2023-09-29 22:44   ` Luben Tuikov
2023-10-05  3:22     ` Matthew Brost
2023-09-19  5:01 ` [Intel-xe] [PATCH v4 10/10] drm/sched: Update maintainers of GPU scheduler Matthew Brost
2023-09-19  5:32 ` [Intel-xe] ✗ CI.Patch_applied: failure for DRM scheduler changes for Xe (rev6) Patchwork
2023-09-19 11:44 ` [Intel-xe] [PATCH v4 00/10] DRM scheduler changes for Xe Danilo Krummrich
2023-09-25 21:47   ` Danilo Krummrich
2023-09-27  7:33 ` Boris Brezillon

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=24bc965f-61fb-4b92-9afa-360ca85a53af@amd.com \
    --to=luben.tuikov@amd.com \
    --cc=Liviu.Dudau@arm.com \
    --cc=airlied@gmail.com \
    --cc=boris.brezillon@collabora.com \
    --cc=christian.koenig@amd.com \
    --cc=dakr@redhat.com \
    --cc=daniel@ffwll.ch \
    --cc=donald.robson@imgtec.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=faith.ekstrand@collabora.com \
    --cc=frank.binns@imgtec.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=ketil.johnsen@arm.com \
    --cc=lina@asahilina.net \
    --cc=matthew.brost@intel.com \
    --cc=mcanal@igalia.com \
    --cc=robdclark@chromium.org \
    --cc=sarah.walker@imgtec.com \
    /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