From: Danilo Krummrich <dakr@kernel.org>
To: "Christian König" <ckoenig.leichtzumerken@gmail.com>
Cc: phasta@mailbox.org, tvrtko.ursulin@igalia.com,
dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org
Subject: Re: Try to fix amdgpu's error handling
Date: Tue, 18 Mar 2025 13:36:54 +0100 [thread overview]
Message-ID: <Z9lo5tUhBgRqHk4n@pollux> (raw)
In-Reply-To: <20250318120313.19099-1-christian.koenig@amd.com>
On Tue, Mar 18, 2025 at 01:03:11PM +0100, Christian König wrote:
> Hi guys,
>
> as partially discussed on the list already amdgpu has a bug in it's gang
> submission code.
>
> Basic problem is to add the correct dependency to the gang leader we
> need to arm the other gang members first, but that is a point of no
> return and it is possible that adding the dependencies fails with
> ENOMEM.
>
> Try to fix that by allowing drivers to preallocate dependency slots. Not
> sure if that is a good approach, but of hand I don't see much
> alternative.
I think that's reasonable, in GPUVM we have a similar problem where we have to
preallocate in order to avoid allocations under a mutex used in the fence
signalling critical path.
Unfortunately, this even prevented us from using the maple tree, since it can't
preallocate for multiple entries ahead of time.
From my side,
Acked-by: Danilo Krummrich <dakr@kernel.org>
prev parent reply other threads:[~2025-03-18 12:37 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-18 12:03 Try to fix amdgpu's error handling Christian König
2025-03-18 12:03 ` [PATCH 1/2] drm/sched: add drm_sched_prealloc_dependency_slots Christian König
2025-03-18 12:39 ` Danilo Krummrich
2025-03-19 11:14 ` Christian König
2025-03-18 12:39 ` Philipp Stanner
2025-03-19 11:23 ` Christian König
2025-03-20 11:49 ` Tvrtko Ursulin
2025-03-21 8:20 ` Philipp Stanner
2025-03-21 13:25 ` Christian König
2025-03-18 13:03 ` Tvrtko Ursulin
2025-03-18 12:03 ` [PATCH 2/2] drm/amdgpu: fix gang submission error handling Christian König
2025-03-18 12:55 ` Tvrtko Ursulin
2025-03-18 12:36 ` Danilo Krummrich [this message]
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=Z9lo5tUhBgRqHk4n@pollux \
--to=dakr@kernel.org \
--cc=amd-gfx@lists.freedesktop.org \
--cc=ckoenig.leichtzumerken@gmail.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=phasta@mailbox.org \
--cc=tvrtko.ursulin@igalia.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.