search for: zero_alloc

...create(bo, true); if (ret) return ret; diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 9aa4fbe386e6..1ccf1ef050d6 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -50,6 +50,9 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) dma_resv_assert_held(bo->base.resv); + if (bo->ttm) + return 0; + if (bdev->need_dma32) page_flags |= TTM_PAGE_FLAG_DMA32; @@ -67,7 +70,6 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) page_flags |= TTM_PAGE_FLAG_SG; break; default: - bo->ttm...

Hi guys, I already tried this a few month ago, but since I don't have NVidia hardware its rather hard to test for me (need to get some ordered). Dave brought up the topic that we should probably try to move the handling into Nouveau once more, so I tried to fix the problem Ben reported and rebased on top of current drm-misc-next. Dave can you test this? At least in theory the approach