From: Fabricio Akio via B4 Relay <devnull+fabricioakio.gmail.com@kernel.org>
To: Rob Clark <robin.clark@oss.qualcomm.com>,
Sean Paul <sean@poorly.run>,
Konrad Dybcio <konradybcio@kernel.org>,
Akhil P Oommen <akhilpo@oss.qualcomm.com>,
Dmitry Baryshkov <lumag@kernel.org>,
Abhinav Kumar <abhinav.kumar@linux.dev>,
Jessica Zhang <jesszhan0024@gmail.com>,
Marijn Suijten <marijn.suijten@somainline.org>,
David Airlie <airlied@gmail.com>,
Simona Vetter <simona@ffwll.ch>,
Jordan Crouse <jordan@cosmicpenguin.net>
Cc: linux-arm-msm@vger.kernel.org, dri-devel@lists.freedesktop.org,
freedreno@lists.freedesktop.org, linux-kernel@vger.kernel.org,
Fabricio Akio <fabricioakio@gmail.com>
Subject: [PATCH 0/2] drm/msm: Per-submission GPU time on A5xx
Date: Sat, 31 Oct 2026 23:32:49 -0300 [thread overview]
Message-ID: <20261031-a5xx-submit-stats-v1-0-16a67ac96edd@gmail.com> (raw)
The GPU time and cycles msm records for each submission, reported in
the msm_gpu_submit_retired trace event and added to fdinfo, read zero
on A5xx, whose submit path never copies the counters they come from.
The second patch adds those copies, as a6xx has them.
The first fixes what is recorded for a submit killed by hangcheck, on
every generation that has these counters: its end stamps may never
have been written, and about three years of GPU time is then added to
the process's fdinfo. With the second patch alone, A5xx would start
reporting that.
Tested on a Motorola Moto X4 (SDM630, A508), whose board file is not
in mainline yet, on sdm660-mainline's 7.2 kernel with commit
b303e1d52811 ("drm/msm: Recover HW before retire hung submit"), which
the first patch needs. Its code is shared with a6xx and later, not
tested there.
---
Fabricio Akio (2):
drm/msm: Report no GPU time for a submit killed by hangcheck
drm/msm/a5xx: Record per-submission GPU time and cycles
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 22 ++++++++++++++++++++++
drivers/gpu/drm/msm/msm_gpu.c | 15 ++++++++++++++-
2 files changed, 36 insertions(+), 1 deletion(-)
---
base-commit: a39c950806213f6861d00f90729acaaa21f2d95a
change-id: 20261031-a5xx-submit-stats-fc108684922a
Best regards,
--
Fabricio Akio <fabricioakio@gmail.com>
next reply other threads:[~2026-11-01 2:32 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-01 2:32 Fabricio Akio via B4 Relay [this message]
2026-11-01 2:32 ` [PATCH 1/2] drm/msm: Report no GPU time for a submit killed by hangcheck Fabricio Akio via B4 Relay
2026-11-01 2:32 ` [PATCH 2/2] drm/msm/a5xx: Record per-submission GPU time and cycles Fabricio Akio via B4 Relay
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=20261031-a5xx-submit-stats-v1-0-16a67ac96edd@gmail.com \
--to=devnull+fabricioakio.gmail.com@kernel.org \
--cc=abhinav.kumar@linux.dev \
--cc=airlied@gmail.com \
--cc=akhilpo@oss.qualcomm.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=fabricioakio@gmail.com \
--cc=freedreno@lists.freedesktop.org \
--cc=jesszhan0024@gmail.com \
--cc=jordan@cosmicpenguin.net \
--cc=konradybcio@kernel.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lumag@kernel.org \
--cc=marijn.suijten@somainline.org \
--cc=robin.clark@oss.qualcomm.com \
--cc=sean@poorly.run \
--cc=simona@ffwll.ch \
/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
all inboxes | Powered by JetHome®