The DMA API has different semantics on different architectures.
Currently on arm64, it can only provide memory from a small pool which
dries up quickly if we attempt to allocate big buffers from it.

Do not consider that option when running on non-x86, since regular TTM
buffers are the (current) best-fit for ARM platforms.

Signed-off-by: Alexandre Courbot <acour...@nvidia.com>
---
To be honest I am not too sure where this part of the code is useful ;
old GPUs with limited DMA capability maybe? If so maybe we can narrow
the test further so it only applies where absolutely needed?

 drm/nouveau/nouveau_bo.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drm/nouveau/nouveau_bo.c b/drm/nouveau/nouveau_bo.c
index e3acc35e3805..2cdaea58678d 100644
--- a/drm/nouveau/nouveau_bo.c
+++ b/drm/nouveau/nouveau_bo.c
@@ -1502,7 +1502,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm)
        }
 #endif
 
-#ifdef CONFIG_SWIOTLB
+#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86)
        if (swiotlb_nr_tbl()) {
                return ttm_dma_populate((void *)ttm, dev->dev);
        }
@@ -1570,7 +1570,7 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
        }
 #endif
 
-#ifdef CONFIG_SWIOTLB
+#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86)
        if (swiotlb_nr_tbl()) {
                ttm_dma_unpopulate((void *)ttm, dev->dev);
                return;
-- 
2.7.2

_______________________________________________
Nouveau mailing list
Nouveau@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/nouveau

Reply via email to