From: machion@disroot.org
To: Alex Deucher <alexdeucher@gmail.com>
Cc: stable@vger.kernel.org, regressions@lists.linux.dev,
amd-gfx@lists.freedesktop.org, alexander.deucher@amd.com,
christian.koenig@amd.com
Subject: Re: Unplayable framerates in game but specific kernel versions work, maybe amdgpu problem
Date: Fri, 10 Oct 2025 11:06:47 +0200 [thread overview]
Message-ID: <748446b7fa6a53f31c69a4e40257adae@disroot.org> (raw)
In-Reply-To: <fadf714ecdc2e3bd5bed0c3ee69177a1@disroot.org>
Hi again,
I have a question:
Would it be possible to make the "memory management/buffering" methodes
switchable through a conf file (obviously amdgpu.conf)?
So that I don't have to keep an old kernel version installed just to
play my game.
Marion
Am 2025-06-17 11:42, schrieb machion@disroot.org:
> I feared that.
>
> It seems a crazy problem, when many people are affected and in opposite
> ways.
> This ReBAR/UEFI thing is also new to me, but I don't have this on my
> system either (using BIOS/MBR).
>
> I hope, it can be fixed for all scenarios.
>
> Marion
>
> Am 2025-06-16 15:29, schrieb Alex Deucher:
>> On Fri, Jun 13, 2025 at 3:38 PM <machion@disroot.org> wrote:
>>>
>>> Hi,
>>> sorry for the delay.
>>> Besides less time, I had to make myself familiar with bisecting and
>>> again kernel compiling. Last time I compiled the kernel myself was
>>> around 2010 I think.
>>>
>>> Anyway it seems I found the bad commit. The result after bisecting 10
>>> commits is:
>>>
>>> a53d959fe660341788cb8dbc3ac3330d90a09ecf is the first bad commit
>>> commit a53d959fe660341788cb8dbc3ac3330d90a09ecf
>>> Author: Christian König <christian.koenig@amd.com>
>>> Date: Thu Mar 20 14:46:18 2025 +0100
>>>
>>> drm/amdgpu: immediately use GTT for new allocations
>>>
>>> commit a755906fb2b8370c43e91ba437ae1b3e228e8b02 upstream.
>>>
>>> Only use GTT as a fallback if we already have a backing store.
>>> This
>>> prevents evictions when an application constantly allocates and
>>> frees new
>>> memory.
>>>
>>> Partially fixes
>>>
>>> https://gitlab.freedesktop.org/drm/amd/-/issues/3844#note_2833985.
>>>
>>> Signed-off-by: Christian König <christian.koenig@amd.com>
>>> Fixes: 216c1282dde3 ("drm/amdgpu: use GTT only as fallback for
>>> VRAM|GTT")
>>> Acked-by: Alex Deucher <alexander.deucher@amd.com>
>>> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
>>> Cc: stable@vger.kernel.org
>>> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>>>
>>> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 ++--
>>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> Unfortunately reverting that commit will reintroduce a similar
>> performance issue for lots of other uses. See:
>> https://gitlab.freedesktop.org/drm/amd/-/issues/3844#note_2827990
>> for a description of the fundemental problem.
>>
>> Alex
>>
>>>
>>> Marion
>>>
>>>
>>> Am 2025-05-08 15:18, schrieb Alex Deucher:
>>> > On Thu, May 8, 2025 at 9:13 AM <machion@disroot.org> wrote:
>>> >>
>>> >> Hello kernel/driver developers,
>>> >>
>>> >> I hope, with my information it's possible to find a bug/problem in the
>>> >> kernel. Otherwise I am sorry, that I disturbed you.
>>> >> I only use LTS kernels, but I can narrow it down to a hand full of
>>> >> them,
>>> >> where it works.
>>> >>
>>> >> The PC: Manjaro Stable/Cinnamon/X11/AMD Ryzen 5 2600/Radeon HD
>>> >> 7790/8GB
>>> >> RAM
>>> >> I already asked the Manjaro community, but with no luck.
>>> >>
>>> >> The game: Hellpoint (GOG Linux latest version, Unity3D-Engine v2021),
>>> >> uses vulkan
>>> >>
>>> >> ---
>>> >>
>>> >> I came a long road of kernels. I had many versions of 5.4, 5.10, 5.15,
>>> >> 6.1 and 6.6 and and the game was always unplayable, because the frames
>>> >> where around 1fps (performance of PC is not the problem).
>>> >> I asked the mesa and cinnamon team for help in the past, but also with
>>> >> no luck.
>>> >> It never worked, till on 2025-03-29 when I installed 6.12.19 for the
>>> >> first time and it worked!
>>> >>
>>> >> But it only worked with 6.12.19, 6.12.20 and 6.12.21
>>> >> When I updated to 6.12.25, it was back to unplayable.
>>> >
>>> > Can you bisect to see what fixed it in 6.12.19 or what broke it in
>>> > 6.12.25? For example if it was working in 6.12.21 and not working in
>>> > 6.12.25, you can bisect between 6.12.21 and .25.
>>> >
>>> > Alex
>>> >
>>> >>
>>> >> For testing I installed 6.14.4 with the same result. It doesn't work.
>>> >>
>>> >> I also compared file /proc/config.gz of both kernels (6.12.21 <>
>>> >> 6.14.4), but can't seem to see drastic changes to the graphical part.
>>> >>
>>> >> I presume it has something to do with amdgpu.
>>> >>
>>> >> If you need more information, I would be happy to help.
>>> >>
>>> >> Kind regards,
>>> >> Marion
prev parent reply other threads:[~2025-10-10 9:06 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-07 13:10 Unplayable framerates in game but specific kernel versions work, maybe amdgpu problem machion
2025-05-08 13:18 ` Alex Deucher
2025-06-13 19:38 ` machion
2025-06-16 13:29 ` Alex Deucher
2025-06-17 9:42 ` machion
2025-10-10 9:06 ` machion [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=748446b7fa6a53f31c69a4e40257adae@disroot.org \
--to=machion@disroot.org \
--cc=alexander.deucher@amd.com \
--cc=alexdeucher@gmail.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=regressions@lists.linux.dev \
--cc=stable@vger.kernel.org \
/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