dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Boris Brezillon <boris.brezillon@collabora.com>
To: "Adrián Larumbe" <adrian.larumbe@collabora.com>
Cc: Rob Herring <robh@kernel.org>,
	Steven Price <steven.price@arm.com>,
	Maarten Lankhorst <maarten.lankhorst@linux.intel.com>,
	Maxime Ripard <mripard@kernel.org>,
	Thomas Zimmermann <tzimmermann@suse.de>,
	David Airlie <airlied@gmail.com>, Simona Vetter <simona@ffwll.ch>,
	Faith Ekstrand <faith.ekstrand@collabora.com>,
	"Marty E. Plummer" <hanetzer@startmail.com>,
	Tomeu Vizoso <tomeu@tomeuvizoso.net>,
	Eric Anholt <eric@anholt.net>,
	Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>,
	Robin Murphy <robin.murphy@arm.com>,
	Philipp Zabel <p.zabel@pengutronix.de>,
	dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
	Collabora Kernel Team <kernel@collabora.com>,
	Neil Armstrong <neil.armstrong@linaro.org>
Subject: Re: [PATCH v7 14/17] drm/panfrost: Avoid cache flush after perfcnt sample in fully coherent systems
Date: Wed, 2 Sep 2026 18:33:46 +0200	[thread overview]
Message-ID: <20260902183346.208eb43d@fedora-21.home> (raw)
In-Reply-To: <aphEMSV5NGlldxBQ@sobremesa>

On Wed, 2 Sep 2026 16:44:24 +0100
Adrián Larumbe <adrian.larumbe@collabora.com> wrote:

> On 01.09.2026 15:37, Boris Brezillon wrote:
> > On Fri, 28 Aug 2026 21:56:54 +0100
> > Adrián Larumbe <adrian.larumbe@collabora.com> wrote:
> >   
> > > If the GPU and CPU are fully coherent, then there's no need to flush the
> > > GPU caches after a perfcnt sample is made available.
> > > 
> > > Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
> > > ---
> > >  drivers/gpu/drm/panfrost/panfrost_perfcnt.c | 5 ++++-
> > >  1 file changed, 4 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
> > > index ffc77121070e..b3f71d7fd82a 100644
> > > --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
> > > +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
> > > @@ -52,7 +52,10 @@ void panfrost_perfcnt_clean_cache_done(struct panfrost_device *pfdev)
> > >  
> > >  void panfrost_perfcnt_sample_done(struct panfrost_device *pfdev)
> > >  {
> > > -	gpu_write(pfdev, GPU_CMD, GPU_CMD_CLEAN_CACHES);
> > > +	if (pfdev->features.selected_coherency != COHERENCY_ACE)  
> > 
> > I think ACE_LITE would allow us to skip the flush to, so  
> 
> I thought ACE_LITE means the GPU can snoop CPU caches but not the other way round, so at the end of a
> sample, we still have to flush GPU caches for the CPU to see counter data.

You're absolutely right, sorry for the brainfart.

  reply	other threads:[~2026-09-02 16:33 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-28 20:56 [PATCH v7 00/17] Collection of fixes for Panfrost: Perfcnt, RPM, refactorings Adrián Larumbe
2026-08-28 20:56 ` [PATCH v7 01/17] drm/panfrost: Move shrinker initialization and unplug one level down Adrián Larumbe
2026-09-01 11:28   ` Boris Brezillon
2026-09-02 15:36     ` Adrián Larumbe
2026-08-28 20:56 ` [PATCH v7 02/17] drm/panfrost: Move all DRM device initialisation into device_init() Adrián Larumbe
2026-09-01 11:49   ` Boris Brezillon
2026-09-02 15:38     ` Adrián Larumbe
2026-09-02 15:50       ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 03/17] drm/panfrost: Move lock and modparam initialisations into their subsystems Adrián Larumbe
2026-08-28 21:14   ` sashiko-bot
2026-09-01 12:10   ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 04/17] drm/panfrost: Move debugfs initialisation to relevant subsystems Adrián Larumbe
2026-09-01 12:30   ` Boris Brezillon
2026-09-02 15:40     ` Adrián Larumbe
2026-08-28 20:56 ` [PATCH v7 05/17] drm/panfrost: Skip NULL checks for clock enable/disabling Adrián Larumbe
2026-09-01 12:31   ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 06/17] drm/panfrost: Consolidate device clock management and reset Adrián Larumbe
2026-09-01 12:38   ` Boris Brezillon
2026-09-02 15:41     ` Adrián Larumbe
2026-08-28 20:56 ` [PATCH v7 07/17] drm/panfrost: Stop all jobs before commencing device teardown Adrián Larumbe
2026-08-28 21:16   ` sashiko-bot
2026-09-01 12:58   ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 08/17] drm/panfrost: Split subsystem init/reset from interrupt enablement Adrián Larumbe
2026-08-28 21:11   ` sashiko-bot
2026-09-01 13:08   ` Boris Brezillon
2026-09-02 15:41     ` Adrián Larumbe
2026-09-02 16:05       ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 09/17] drm/panfrost: Fix PM refcnt and autosuspend issues at device probe/remove Adrián Larumbe
2026-08-28 21:09   ` sashiko-bot
2026-09-01 13:18   ` Boris Brezillon
2026-09-02 15:42     ` Adrián Larumbe
2026-09-02 16:14       ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 10/17] drm/panfrost: Add warning messages to fatal error conditions Adrián Larumbe
2026-08-28 21:10   ` sashiko-bot
2026-09-01 13:20   ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 11/17] drm/panfrost: Add debugfs knob for manually triggering a GPU reset Adrián Larumbe
2026-08-28 21:12   ` sashiko-bot
2026-09-01 13:27   ` Boris Brezillon
2026-09-02 15:42     ` Adrián Larumbe
2026-09-02 16:23       ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 12/17] drm/panfrost: Move perfcnt GPU disable sequence into a helper Adrián Larumbe
2026-08-28 20:56 ` [PATCH v7 13/17] drm/panfrost: Skip cache flush/invalidate when enabling perfcnt Adrián Larumbe
2026-09-01 13:32   ` Boris Brezillon
2026-09-02 15:43     ` Adrián Larumbe
2026-09-02 16:29       ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 14/17] drm/panfrost: Avoid cache flush after perfcnt sample in fully coherent systems Adrián Larumbe
2026-08-28 21:14   ` sashiko-bot
2026-09-01 13:37   ` Boris Brezillon
2026-09-02 15:44     ` Adrián Larumbe
2026-09-02 16:33       ` Boris Brezillon [this message]
2026-09-02 16:34   ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 15/17] drm/panfrost: Introduce a reset lock Adrián Larumbe
2026-08-28 20:56 ` [PATCH v7 16/17] drm/panfrost: Fix races between perfcnt and reset sequence Adrián Larumbe
2026-08-28 21:17   ` sashiko-bot
2026-09-01 14:03   ` Boris Brezillon
2026-09-02 15:45     ` Adrián Larumbe
2026-09-02 16:51       ` Boris Brezillon
2026-08-28 20:56 ` [PATCH v7 17/17] drm/panfrost: Bump driver minor to reflect new DUMP IOCTL req field Adrián Larumbe

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=20260902183346.208eb43d@fedora-21.home \
    --to=boris.brezillon@collabora.com \
    --cc=adrian.larumbe@collabora.com \
    --cc=airlied@gmail.com \
    --cc=alyssa.rosenzweig@collabora.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=eric@anholt.net \
    --cc=faith.ekstrand@collabora.com \
    --cc=hanetzer@startmail.com \
    --cc=kernel@collabora.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=mripard@kernel.org \
    --cc=neil.armstrong@linaro.org \
    --cc=p.zabel@pengutronix.de \
    --cc=robh@kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=simona@ffwll.ch \
    --cc=steven.price@arm.com \
    --cc=tomeu@tomeuvizoso.net \
    --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