On 2018å¹´03æ??27æ?¥ 21:44, Christian König wrote:
> How about we update the LRU only when we need to re-validate at least
> one BO?
I tried this just now, performance still isn't stable, sometime drop to
28fps by accident.
I also tried to check num_evictions, if eviction happens, then update
LRU, also sometime drop to 28fps by accident.
When BOs change, we not only need keep LRU order, but also validation
order in vm->evicted list. Any other ideas which can keep these order
but not increase submission overhead?
Regards,
David Zhou
>
> BTW: We can easily walk all BOs which belong to a VM, skipping over
> the few which aren't per VM BOs should be trivial.
>
> Christian.
>
> Am 27.03.2018 um 13:56 schrieb Zhou, David(ChunMing):
>> then how to keep unique lru order? any ideas?
>>
>> To stable performance, we have to keep unique lru order, otherwise
>> like the issue I look into, sometimes F1game is 40fps, sometimes
>> 28fps...even re-validate allowed domains BO.
>>
>> The left root cause is the moved BOs are not same.
>>
>> send from Smartisan Pro
>>
>> Christian Ké°?ig <ckoenig.leichtzumerken at gmail.com> äº? 2018å¹´3æ??27æ?¥
>> ä¸?å??6:50å??é??ï¼?
>>
>> NAK, we already tried that and it is really not a good idea because it
>> massively increases the per submission overhead.
>>
>> Christian.
>>
>> Am 27.03.2018 um 12:16 schrieb Chunming Zhou:
>> > Change-Id: Ibad84ed585b0746867a5f4cd1eadc2273e7cf596
>> > Signed-off-by: Chunming Zhou <david1.zhou at amd.com>
>> > ---
>> >Â Â drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c |Â 2 ++
>> >Â Â drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 15 +++++++++++++++
>> >Â Â drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h |Â 1 +
>> >Â Â 3 files changed, 18 insertions(+)
>> >
>> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>> > index 383bf2d31c92..414e61799236 100644
>> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
>> > @@ -919,6 +919,8 @@ static int amdgpu_bo_vm_update_pte(struct
>> amdgpu_cs_parser *p)
>> >Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â }
>> >Â Â Â Â Â Â Â }
>> >
>> > +Â Â Â Â amdgpu_vm_refresh_lru(adev, vm);
>> > +
>> >Â Â Â Â Â Â Â return r;
>> >Â Â }
>> >
>> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> > index 5e35e23511cf..8ad2bb705765 100644
>> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> > @@ -1902,6 +1902,21 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct
>> amdgpu_device *adev,
>> >Â Â Â Â Â Â Â return bo_va;
>> >Â Â }
>> >
>> > +void amdgpu_vm_refresh_lru(struct amdgpu_device *adev, struct
>> amdgpu_vm *vm)
>> > +{
>> > +Â Â Â Â struct ttm_bo_global *glob = adev->mman.bdev.glob;
>> > +Â Â Â Â struct amdgpu_vm_bo_base *bo_base;
>> > +
>> > +Â Â Â Â spin_lock(&vm->status_lock);
>> > +Â Â Â Â list_for_each_entry(bo_base, &vm->vm_bo_list, vm_bo) {
>> > +Â Â Â Â Â Â Â Â Â Â Â Â spin_lock(&glob->lru_lock);
>> > + ttm_bo_move_to_lru_tail(&bo_base->bo->tbo);
>> > +Â Â Â Â Â Â Â Â Â Â Â Â if (bo_base->bo->shadow)
>> > + ttm_bo_move_to_lru_tail(&bo_base->bo->shadow->tbo);
>> > +Â Â Â Â Â Â Â Â Â Â Â Â spin_unlock(&glob->lru_lock);
>> > +Â Â Â Â }
>> > +Â Â Â Â spin_unlock(&vm->status_lock);
>> > +}
>> >
>> >Â Â /**
>> >Â Â Â * amdgpu_vm_bo_insert_mapping - insert a new mapping
>> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
>> > index 1886a561c84e..e01895581489 100644
>> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
>> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
>> > @@ -285,6 +285,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device
>> *adev,
>> >Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â struct dma_fence **fence);
>> >Â Â int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
>> >Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â struct amdgpu_vm *vm);
>> > +void amdgpu_vm_refresh_lru(struct amdgpu_device *adev, struct
>> amdgpu_vm *vm);
>> >Â Â int amdgpu_vm_bo_update(struct amdgpu_device *adev,
>> >Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â struct amdgpu_bo_va *bo_va,
>> >Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â bool clear);
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20180328/7bcffb0c/attachment.html>
