On Thu, Aug 05, 2021 at 02:26:10PM +0900, David Stevens wrote: > On Mon, Aug 2, 2021 at 10:54 PM Will Deacon <[email protected]> wrote: > > > > On Fri, Jul 09, 2021 at 12:35:01PM +0900, David Stevens wrote: > > > From: David Stevens <[email protected]> > > > > > > If SKIP_CPU_SYNC isn't already set, then iommu_dma_unmap_(page|sg) has > > > already called iommu_dma_sync_(single|sg)_for_cpu, so there is no need > > > to copy from the bounce buffer again. > > > > > > Signed-off-by: David Stevens <[email protected]> > > > --- > > > drivers/iommu/dma-iommu.c | 3 ++- > > > 1 file changed, 2 insertions(+), 1 deletion(-) > > > > > > diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c > > > index e79e274d2dc5..0a9a9a343e64 100644 > > > --- a/drivers/iommu/dma-iommu.c > > > +++ b/drivers/iommu/dma-iommu.c > > > @@ -505,7 +505,8 @@ static void __iommu_dma_unmap_swiotlb(struct device > > > *dev, dma_addr_t dma_addr, > > > __iommu_dma_unmap(dev, dma_addr, size); > > > > > > if (unlikely(is_swiotlb_buffer(phys))) > > > - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); > > > + swiotlb_tbl_unmap_single(dev, phys, size, dir, > > > + attrs | DMA_ATTR_SKIP_CPU_SYNC); > > > } > > > > I think it would be cleaner to drop DMA_ATTR_SKIP_CPU_SYNC in the callers > > once they've called iommu_dma_sync_*_for_cpu(). > > Dropping that flag in iommu_dma_unmap_* would result in always copying > from the swiotlb here, which is the opposite direction of what this > patch is trying to do.
Sorry, probably poor wording on my part. What I mean is, rather than add DMA_ATTR_SKIP_CPU_SYNC here, how about having the callers include it in attrs instead, since they're the ones doing the initial sync? Will _______________________________________________ iommu mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/iommu
