Am 14.09.21 um 20:19 schrieb Mikhail Gavrilov:
> On Wed, 14 Apr 2021 at 11:48, Christian König 
> <ckoenig.leichtzumerken@gmail.com 
> <mailto:ckoenig.leichtzumerken@gmail.com>> wrote:
>
>
>     That is expected behavior, the application is just buggy and
>     causing a
>     page fault on the GPU.
>
>     The kernel should just not crash with a backtrace.
>
>     Regards,
>     Christian.
>
>
> If after it GPU hangs with the message 
> "[drm:amdgpu_dm_atomic_commit_tail [amdgpu]] *ERROR* Waiting for 
> fences timed out!" is it also expected behavior?

Yes, absolutely. You should see GPU resets and recovery in the system 
log after that.

Regards,
Christian.

> Kernel log: https://pastebin.com/WkhATKXX 
> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpastebin.com%2FWkhATKXX&data=04%7C01%7Cchristian.koenig%40amd.com%7C83d3316107ce4c9fe42a08d977ac2ea3%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637672405000225872%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C2000&sdata=BSCdZefdxpQPBdKzrcII8e9LDR8nN%2BbMkswE%2FEkaXv8%3D&reserved=0>
>
>
> -- 
> Best Regards,
> Mike Gavrilov.