Re: [PATCH v3 19/28] drm/ttm: rework pipelined eviction fence handling

[Maarten Lankhorst <maarten.lankhorst@linux.intel.com>]

Hey,

Den 2025-11-26 kl. 16:48, skrev Christian König:
> On 11/26/25 16:39, Maarten Lankhorst wrote:
>> Hey,
>>
>> Den 2025-11-26 kl. 16:36, skrev Christian König:
>>> On 11/26/25 16:34, Maarten Lankhorst wrote:
>>>> Hey,
>>>>
>>>> Den 2025-11-21 kl. 16:12, skrev Christian König:
>>>>> On 11/21/25 11:12, Pierre-Eric Pelloux-Prayer wrote:
>>>>>> Until now ttm stored a single pipelined eviction fence which means
>>>>>> drivers had to use a single entity for these evictions.
>>>>>>
>>>>>> To lift this requirement, this commit allows up to 8 entities to
>>>>>> be used.
>>>>>>
>>>>>> Ideally a dma_resv object would have been used as a container of
>>>>>> the eviction fences, but the locking rules makes it complex.
>>>>>> dma_resv all have the same ww_class, which means "Attempting to
>>>>>> lock more mutexes after ww_acquire_done." is an error.
>>>>>>
>>>>>> One alternative considered was to introduced a 2nd ww_class for
>>>>>> specific resv to hold a single "transient" lock (= the resv lock
>>>>>> would only be held for a short period, without taking any other
>>>>>> locks).
>>>>>>
>>>>>> The other option, is to statically reserve a fence array, and
>>>>>> extend the existing code to deal with N fences, instead of 1.
>>>>>>
>>>>>> The driver is still responsible to reserve the correct number
>>>>>> of fence slots.
>>>>>>
>>>>>> ---
>>>>>> v2:
>>>>>> - simplified code
>>>>>> - dropped n_fences
>>>>>> - name changes
>>>>>> v3: use ttm_resource_manager_cleanup
>>>>>> ---
>>>>>>
>>>>>> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
>>>>>
>>>>> Reviewed-by: Christian König <christian.koenig@amd.com>
>>>>>
>>>>> Going to push separately to drm-misc-next on Monday.
>>>>>
>>>> Pushing this broke drm-tip, the amd driver fails to build, as it's not using the eviction_fences array.
>>>
>>> Thanks for the note! But hui? We changed amdgpu to not touch the move fence.
>>>
>>> Give me a second.commit 13bec21f5f4cdabdf06725e5a8dee0b9b56ff671 (HEAD -> drm-tip, drm-tip/drm-tip, drm-tip/HEAD)
>>
>> Author: Christian König <christian.koenig@amd.com>
>> Date:   Wed Nov 26 13:13:03 2025 +0100
>>
>>     drm-tip: 2025y-11m-26d-12h-12m-41s UTC integration manifest
>>
>> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:2188:34: error: ‘struct ttm_resource_manager’ has no member named ‘move’
>>  2188 |                 dma_fence_put(man->move);
>>       |                                  ^~
>> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:2189:20: error: ‘struct ttm_resource_manager’ has no member named ‘move’
>>  2189 |                 man->move = NULL;
>>       |                    ^~
>>
>> Is what I see.
> 
> Ah, crap, I know what's going on.
> 
> The patch to remove those lines is queued up to go upstream through amd-staging-drm-next instead of drm-misc-next.
> 
> I will push this patch to drm-misc-next and sync up with Alex that it shouldn't go upstream through amd-staging-drm-next.
> 
> Going to build test drm-tip the next time.
Thank you, drm-tip now builds cleanly again!

> 
> Thanks,
> Christian.
> 
> 

Kind regards,
~Maarten Lankhorst