[PATCH] drm/amdgpu: flush the fence on the bo after we individualize

Christian König ckoenig.leichtzumerken at gmail.com
Wed Jan 15 13:19:18 UTC 2020


Am 15.01.20 um 07:26 schrieb Pan, Xinhui:
> As we move the ttm_bo_individualize_resv() upwards, we need flush the
> copied fence too. Otherwise the driver keeps waiting for fence.
>
> run&Kill kfdtest, then perf top.
>
>    25.53%  [ttm]                     [k] ttm_bo_delayed_delete
>    24.29%  [kernel]                  [k] dma_resv_test_signaled_rcu
>    19.72%  [kernel]                  [k] ww_mutex_lock
>
> Fix: 378e2d5b("drm/ttm: fix ttm_bo_cleanup_refs_or_queue once more")
> Signed-off-by: xinhui pan <xinhui.pan at amd.com>

That's indeed a rather nice idea. Reviewed-by: Christian König 
<christian.koenig at amd.com>

I'm going to pick that up for inclusion in drm-misc-next. Please send 
TTM patches also to the dri-devel mailing list in the future.

Christian.

> ---
>   drivers/gpu/drm/ttm/ttm_bo.c | 4 +++-
>   1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 8d91b0428af1..1494aebb8128 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -499,8 +499,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
>   
>   		dma_resv_unlock(bo->base.resv);
>   	}
> -	if (bo->base.resv != &bo->base._resv)
> +	if (bo->base.resv != &bo->base._resv) {
> +		ttm_bo_flush_all_fences(bo);
>   		dma_resv_unlock(&bo->base._resv);
> +	}
>   
>   error:
>   	kref_get(&bo->list_kref);



More information about the amd-gfx mailing list