From: Daniel Vetter <daniel@ffwll.ch>
To: "Christian König" <deathsimple@vodafone.de>
Cc: "Michel Dänzer" <michel@daenzer.net>,
dri-devel <dri-devel@lists.freedesktop.org>,
"amd-gfx list" <amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH] drm/i915: Before pageflip, also wait for shared dmabuf fences.
Date: Thu, 22 Sep 2016 08:36:25 +0200 [thread overview]
Message-ID: <20160922063625.GD22164@dvetter-linux.ger.corp.intel.com> (raw)
In-Reply-To: <3f4643cb-52a9-d7ae-439b-5f6fc6e718cc@vodafone.de>
On Wed, Sep 21, 2016 at 06:23:35PM +0200, Christian König wrote:
> For a quick workaround I suggest to just serialize all accesses to BO shared
> with different drivers, but essentially I think it is a perfectly valid
> requirement to have multiple writers to one BO.
It is, but it's not possible with implicit sync. If you want parallel
write access to the same shared buffer, you _must_ carry around some
explicit fences. Within amdgpu you can use driver-specific cookies, for
shared buffer we now have sync_file. But multiple writers with implicit
sync simply fundamentally doesn't work. Because you have no idea with which
writer, touching the same subrange you want to touch.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2016-09-22 14:55 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-08 0:14 [PATCH] drm/i915: Before pageflip, also wait for shared dmabuf fences Mario Kleiner
2016-09-08 6:30 ` Chris Wilson
2016-09-08 15:21 ` Mario Kleiner
2016-09-08 16:23 ` Chris Wilson
[not found] ` <20160908162346.GA5479-aII6DKEyn0pWYbfKqPwjAkR8Iwp7RQ6xAL8bYrjMMd8@public.gmane.org>
2016-09-09 1:15 ` Michel Dänzer
[not found] ` <abccc8ac-10c6-ab22-c59d-f43ee48ba78d-otUistvHUpPR7s880joybQ@public.gmane.org>
2016-09-13 8:44 ` Christian König
2016-09-13 9:39 ` Chris Wilson
[not found] ` <20160913093945.GA25204-aII6DKEyn0pWYbfKqPwjAkR8Iwp7RQ6xAL8bYrjMMd8@public.gmane.org>
2016-09-13 12:52 ` Christian König
2016-09-21 9:56 ` Michel Dänzer
[not found] ` <7aafce92-8bcf-1c5c-45de-9e8ecda85239-otUistvHUpPR7s880joybQ@public.gmane.org>
2016-09-21 10:30 ` Christian König
2016-09-21 11:04 ` Daniel Vetter
[not found] ` <CAKMK7uG3j54NzwjxmWuSmP787r+QN-Cu5T8R-naX6S9RvvKemw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-09-21 11:19 ` Christian König
2016-09-21 12:56 ` Daniel Vetter
[not found] ` <CAKMK7uH6N2Kgwkf-11iwdqDAUrFmreYKLLeTGXmEh+N0DQ4tJg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-09-21 15:07 ` Michel Dänzer
[not found] ` <9d1f4872-cabd-bd1b-7f10-6e4230a1f58c-otUistvHUpPR7s880joybQ@public.gmane.org>
2016-09-21 15:15 ` Christian König
[not found] ` <5c2048ff-0e20-ddf3-2d73-9a3acb38e7ff-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-09-21 15:29 ` Michel Dänzer
2016-09-21 16:23 ` Christian König
2016-09-22 6:36 ` Daniel Vetter [this message]
[not found] ` <20160922063625.GD22164-XQyZGdhdUcTMwUGJfOwWj/ooFf0ArEBIu+b9c/7xato@public.gmane.org>
2016-09-22 10:55 ` Christian König
2016-09-22 12:26 ` Daniel Vetter
2016-09-22 12:44 ` Christian König
2016-09-22 13:05 ` Daniel Vetter
2016-09-22 13:22 ` Christian König
[not found] ` <d2430ff8-43bd-bff2-9b02-847cabfd56c0-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-09-23 10:00 ` Michel Dänzer
2016-09-23 12:09 ` Daniel Vetter
2016-09-26 0:48 ` Michel Dänzer
2016-09-26 8:04 ` Daniel Vetter
[not found] ` <20160926080419.GV20761-dv86pmgwkMBes7Z6vYuT8azUEOm+Xw19@public.gmane.org>
2016-10-07 12:34 ` Mike Lothian
[not found] ` <CAHbf0-HZ6EotqwgvkxRTdRF97xB3qBA=DRKAzaAXguV_PR_P8w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-10-11 3:58 ` Michel Dänzer
[not found] ` <d74d34a7-5221-d282-d9d1-b0e1007fc0c7-otUistvHUpPR7s880joybQ@public.gmane.org>
2016-10-11 12:04 ` Christian König
[not found] ` <c77a2cb9-1f0e-f1a3-aedd-a111cd6ba8e8-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-10-12 0:40 ` Michel Dänzer
2016-10-27 13:33 ` Mike Lothian
[not found] ` <CAHbf0-GGMWZrhB+PKpc-QbD__6fqB4pQVFfN+gzLWNhi+DuG3Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-10-28 1:34 ` Michel Dänzer
2016-10-28 17:37 ` Mario Kleiner
2016-10-28 18:37 ` Mike Lothian
2016-10-29 13:58 ` Mike Lothian
[not found] ` <CAHbf0-EY2OM_HgxTjmMi4-f5TQ8fkqf5XYBxHZtJVsnSpxPyyA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2016-10-31 6:44 ` Michel Dänzer
[not found] ` <c45e2f4c-c075-47b6-7e02-3bd98748c83a-otUistvHUpPR7s880joybQ@public.gmane.org>
2016-10-31 8:00 ` Christian König
2016-10-31 8:06 ` Michel Dänzer
[not found] ` <7eb19a73-a558-d2e6-bd8d-34fe95045dfd-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2016-10-28 17:48 ` Christian König
2016-11-05 1:17 ` Mario Kleiner
2016-10-31 6:41 ` Michel Dänzer
2016-09-22 6:33 ` Daniel Vetter
2016-09-21 15:13 ` Michel Dänzer
[not found] ` <f0e034f9-db22-6577-97c7-dd8d3e851226-otUistvHUpPR7s880joybQ@public.gmane.org>
2016-09-21 15:21 ` Christian König
2016-09-21 15:28 ` Michel Dänzer
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=20160922063625.GD22164@dvetter-linux.ger.corp.intel.com \
--to=daniel@ffwll.ch \
--cc=amd-gfx@lists.freedesktop.org \
--cc=deathsimple@vodafone.de \
--cc=dri-devel@lists.freedesktop.org \
--cc=michel@daenzer.net \
/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