Re: commit 7ffb791423c7 breaks steam game

[Bert Karwatzki <spasswolf@web.de>]

Am Sonntag, dem 16.03.2025 um 14:09 +0100 schrieb Bert Karwatzki:
> This is related to the admgpu.gttsize. My laptop has the maximum amount 
> of memory (64G) and usually gttsize is half of main memory size. I just 
> tested with cmdline="nokaslr amdgpi.gttsize=2048" and the problem does 
> not occur. So I did some more testing with varying gttsize and got this
> for the built-in GPU
>
> 08:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI]
> Cezanne [Radeon Vega Series / Radeon Vega Mobile Series] (rev c5)
>
> (nokaslr is always enabeld)
> gttssize   input behaviour
>  2048		GOOD
>  2064		GOOD
>  2080		SEMIBAD (i.e. noticeable input lag but not as bad as below)
>  3072		BAD
>  4096		BAD
>  8192		BAD
> 16384		BAD
>
> As the build-in GPU has ~512 VRAM there seems to be problems when gttsize >
> 4*VRAM so I tested for the discrete GPU with 8G of VRAM
> gttsize   input behaviour
> 49152		GOOD
> 64000		GOOD
>
> So for the discrete GPU increasing gttsize does no reproduce the bug.
>
> Bert Karwatzki

So I was thinking the reason the bug does not show on the discrete GPU is that
it has too much VRAM so the GTT memory is not used in this case.
In order to test this I booted with amdgpu.vramlimit=512. Unfortunately
initialisation fails in this case:

[  T291] [drm:amdgpu_device_init.cold [amdgpu]] *ERROR* sw_init of IP block
<gmc_v10_0> failed -22

But using the parameter amdgpu.vramlimit fixes the problem for the built-in GPU,
even when the value is larger than the VRAM of the builtin-GPU (i.e. nokaslr
amdgpu.vramlimit=4096 does not give the buggy behaviour)

Bert Karwatzki