In some iommu, e.g. swiotlb, the available space can be quite limited.
So we employ a trial-and-error approach to seeing if our large
contiguous chunks can fit, and if that fails we try again with smaller
chunks after trying to free our own lazily allocated blobs. As we use a
trial-and-error approach, we do not want dma_map_sg() to emit a WARN of
its own accord, we want to gracefully report the error back to the caller
instead.
Note that our noisy culprit, swiotlb, doesn't honour the flag, yet.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Cc: Matthew Auld <matthew.auld@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c5f393870532..f2a0f556da21 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2335,9 +2335,10 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
struct sg_table *pages)
{
do {
- if (dma_map_sg(&obj->base.dev->pdev->dev,
- pages->sgl, pages->nents,
- PCI_DMA_BIDIRECTIONAL))
+ if (dma_map_sg_attrs(&obj->base.dev->pdev->dev,
+ pages->sgl, pages->nents,
+ PCI_DMA_BIDIRECTIONAL,
+ DMA_ATTR_NO_WARN))
return 0;
/* If the DMA remap fails, one cause can be that we have
--
2.15.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
