[PATCH v8 3/7] dma-iommu: skip extra sync during unmap w/swiotlb

[David Stevens]

From: David Stevens <stevensd@xxxxxxxxxxxx>

Calling the iommu_dma_sync_*_for_cpu functions during unmap can cause
two copies out of the swiotlb buffer. Do the arch sync directly in
__iommu_dma_unmap_swiotlb instead to avoid this. This makes the call to
iommu_dma_sync_sg_for_cpu for untrusted devices in iommu_dma_unmap_sg no
longer necessary, so move that invocation later in the function.

Signed-off-by: David Stevens <stevensd@xxxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Robin Murphy <robin.murphy@xxxxxxx>
---
 drivers/iommu/dma-iommu.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 19bebacbf178..027b489714b7 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -521,6 +521,9 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
 	if (WARN_ON(!phys))
 		return;
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && !dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu(phys, size, dir);
+
 	__iommu_dma_unmap(dev, dma_addr, size);
 
 	if (unlikely(is_swiotlb_buffer(dev, phys)))
@@ -871,8 +874,6 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
 	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);
 }
 
@@ -1088,14 +1089,14 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	struct scatterlist *tmp;
 	int i;
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
-
 	if (dev_is_untrusted(dev)) {
 		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
 		return;
 	}
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+
 	/*
 	 * The scatterlist segments are mapped into a single
 	 * contiguous IOVA allocation, so this is incredibly easy.
-- 
2.33.0.685.g46640cef36-goog