public inbox for linux-media@vger.kernel.org
 help / color / mirror / Atom feed
From: Pekka Paalanen <ppaalanen@gmail.com>
To: Rob Clark <robdclark@gmail.com>
Cc: dri-devel@lists.freedesktop.org, freedreno@lists.freedesktop.org,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Christian König" <ckoenig.leichtzumerken@gmail.com>,
	"Michel Dänzer" <michel@daenzer.net>,
	"Tvrtko Ursulin" <tvrtko.ursulin@intel.com>,
	"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Simon Ser" <contact@emersion.fr>,
	"Rob Clark" <robdclark@chromium.org>,
	"Sumit Semwal" <sumit.semwal@linaro.org>,
	"Gustavo Padovan" <gustavo@padovan.org>,
	"Christian König" <christian.koenig@amd.com>,
	linux-media@vger.kernel.org (open list:SYNC FILE FRAMEWORK),
	linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER
	SHARING FRAMEWORK), linux-kernel@vger.kernel.org (open list)
Subject: Re: [PATCH v4 06/14] dma-buf/sync_file: Support (E)POLLPRI
Date: Mon, 20 Feb 2023 10:53:45 +0200	[thread overview]
Message-ID: <20230220105345.70e46fa5@eldfell> (raw)
In-Reply-To: <20230218211608.1630586-7-robdclark@gmail.com>

[-- Attachment #1: Type: text/plain, Size: 1902 bytes --]

On Sat, 18 Feb 2023 13:15:49 -0800
Rob Clark <robdclark@gmail.com> wrote:

> From: Rob Clark <robdclark@chromium.org>
> 
> Allow userspace to use the EPOLLPRI/POLLPRI flag to indicate an urgent
> wait (as opposed to a "housekeeping" wait to know when to cleanup after
> some work has completed).  Usermode components of GPU driver stacks
> often poll() on fence fd's to know when it is safe to do things like
> free or reuse a buffer, but they can also poll() on a fence fd when
> waiting to read back results from the GPU.  The EPOLLPRI/POLLPRI flag
> lets the kernel differentiate these two cases.
> 
> Signed-off-by: Rob Clark <robdclark@chromium.org>

Hi,

where would the UAPI documentation of this go?
It seems to be missing.

If a Wayland compositor is polling application fences to know which
client buffer to use in its rendering, should the compositor poll with
PRI or not? If a compositor polls with PRI, then all fences from all
applications would always be PRI. Would that be harmful somehow or
would it be beneficial?


Thanks,
pq

> ---
>  drivers/dma-buf/sync_file.c | 8 ++++++++
>  1 file changed, 8 insertions(+)
> 
> diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
> index fb6ca1032885..c30b2085ee0a 100644
> --- a/drivers/dma-buf/sync_file.c
> +++ b/drivers/dma-buf/sync_file.c
> @@ -192,6 +192,14 @@ static __poll_t sync_file_poll(struct file *file, poll_table *wait)
>  {
>  	struct sync_file *sync_file = file->private_data;
>  
> +	/*
> +	 * The POLLPRI/EPOLLPRI flag can be used to signal that
> +	 * userspace wants the fence to signal ASAP, express this
> +	 * as an immediate deadline.
> +	 */
> +	if (poll_requested_events(wait) & EPOLLPRI)
> +		dma_fence_set_deadline(sync_file->fence, ktime_get());
> +
>  	poll_wait(file, &sync_file->wq, wait);
>  
>  	if (list_empty(&sync_file->cb.node) &&


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

  parent reply	other threads:[~2023-02-20  8:53 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-18 21:15 [PATCH v4 00/14] dma-fence: Deadline awareness Rob Clark
2023-02-18 21:15 ` [PATCH v4 01/14] dma-buf/dma-fence: Add deadline awareness Rob Clark
2023-02-22 10:23   ` Tvrtko Ursulin
2023-02-22 15:28     ` Christian König
2023-02-22 17:04       ` Tvrtko Ursulin
2023-02-22 17:16         ` Rob Clark
2023-02-22 17:33           ` Tvrtko Ursulin
2023-02-22 18:57             ` Rob Clark
2023-02-22 11:01   ` Luben Tuikov
2023-02-18 21:15 ` [PATCH v4 02/14] dma-buf/fence-array: Add fence deadline support Rob Clark
2023-02-18 21:15 ` [PATCH v4 03/14] dma-buf/fence-chain: " Rob Clark
2023-02-22 10:27   ` Tvrtko Ursulin
2023-02-22 15:55     ` Rob Clark
2023-02-18 21:15 ` [PATCH v4 04/14] dma-buf/dma-resv: Add a way to set fence deadline Rob Clark
2023-02-20  8:16   ` Christian König
2023-02-18 21:15 ` [PATCH v4 05/14] dma-buf/sync_file: Add SET_DEADLINE ioctl Rob Clark
2023-02-20  8:27   ` Christian König
2023-02-20 16:09     ` Rob Clark
2023-02-21  8:41       ` Pekka Paalanen
2023-02-23  9:19       ` Christian König
2023-02-20  8:48   ` Pekka Paalanen
2023-02-18 21:15 ` [PATCH v4 06/14] dma-buf/sync_file: Support (E)POLLPRI Rob Clark
2023-02-20  8:31   ` Christian König
2023-02-21  8:38     ` Pekka Paalanen
2023-02-20  8:53   ` Pekka Paalanen [this message]
2023-02-20 16:14     ` Rob Clark
2023-02-21  8:37       ` Pekka Paalanen
2023-02-21 16:01         ` Sebastian Wick
2023-02-21 17:55           ` Rob Clark
2023-02-21 16:48       ` Luben Tuikov
2023-02-21 17:53         ` Rob Clark
2023-02-22  9:49           ` Pekka Paalanen
2023-02-22 10:26             ` Luben Tuikov
2023-02-22 15:37             ` Rob Clark
2023-02-23  9:38               ` Pekka Paalanen
2023-02-23 18:51                 ` Rob Clark
2023-02-24  9:26                   ` Pekka Paalanen
2023-02-24  9:41                     ` Tvrtko Ursulin
2023-02-24 10:24                       ` Pekka Paalanen
2023-02-24 10:50                         ` Tvrtko Ursulin
2023-02-24 11:00                           ` Pekka Paalanen
2023-02-24 11:37                             ` Tvrtko Ursulin
2023-02-24 15:26                               ` Luben Tuikov
2023-02-24 17:59                                 ` Rob Clark
2023-02-27 21:35                                   ` Rodrigo Vivi
2023-02-27 22:20                                     ` Rob Clark
2023-02-27 22:44                                       ` Sebastian Wick
2023-02-27 23:48                                         ` Rob Clark
2023-02-28 14:30                                           ` Sebastian Wick
2023-02-28 22:52                                             ` Rob Clark
2023-03-01 15:31                                               ` Sebastian Wick
2023-03-01 16:02                                                 ` Rob Clark
2023-03-01 15:45                                       ` Rodrigo Vivi
2023-02-24 16:59                         ` Rob Clark
2023-02-24 19:44                         ` Rob Clark
2023-02-27  9:34                           ` Pekka Paalanen
2023-02-27 18:43                             ` Rob Clark
2023-02-18 21:15 ` [PATCH v4 07/14] dma-buf/sw_sync: Add fence deadline support Rob Clark
2023-02-20  8:29   ` Christian König
2023-02-18 21:15 ` [PATCH v4 08/14] drm/scheduler: " Rob Clark
2023-02-21 19:40   ` Luben Tuikov
2023-02-18 21:15 ` [PATCH v4 12/14] drm/msm: Add deadline based boost support Rob Clark
2023-02-18 21:15 ` [PATCH v4 14/14] drm/i915: " Rob Clark
2023-02-20 15:46   ` Tvrtko Ursulin

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=20230220105345.70e46fa5@eldfell \
    --to=ppaalanen@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=christian.koenig@amd.com \
    --cc=ckoenig.leichtzumerken@gmail.com \
    --cc=contact@emersion.fr \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=freedreno@lists.freedesktop.org \
    --cc=gustavo@padovan.org \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=michel@daenzer.net \
    --cc=robdclark@chromium.org \
    --cc=robdclark@gmail.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=sumit.semwal@linaro.org \
    --cc=tvrtko.ursulin@intel.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