[PATCH v4 3/6] dma-iommu: skip extra sync during unmap w/swiotlb

[David Stevens <stevensd@chromium.org>]

From: David Stevens <stevensd@chromium.org>

Calling the iommu_dma_sync_*_for_cpu functions during unmap can cause
two copies out of the swiotlb buffer. Fold __iommu_dma_unmap_swiotlb
into iommu_dma_unmap_page, and directly call arch_sync_dma_for_cpu
instead of iommu_dma_sync_single_for_cpu to avoid this double sync. With
this refactor, calling iommu_dma_sync_sg_for_cpu for untrusted devices
in iommu_dma_unmap_sg is also no longer necessary, so move that
invocation later in the function.

Signed-off-by: David Stevens <stevensd@chromium.org>
---
 drivers/iommu/dma-iommu.c | 42 +++++++++++++++++----------------------
 1 file changed, 18 insertions(+), 24 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index e9119ff93535..f7da4934f7e6 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -493,23 +493,6 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	iommu_dma_free_iova(cookie, dma_addr, size, iotlb_gather.freelist);
 }
 
-static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	phys_addr_t phys;
-
-	phys = iommu_iova_to_phys(domain, dma_addr);
-	if (WARN_ON(!phys))
-		return;
-
-	__iommu_dma_unmap(dev, dma_addr, size);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
-}
-
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 		size_t size, int prot, u64 dma_mask)
 {
@@ -845,9 +828,20 @@ 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);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	phys_addr_t phys;
+
+	phys = iommu_iova_to_phys(domain, dma_handle);
+	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_handle, size);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 
 /*
@@ -932,7 +926,7 @@ static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *s
 	int i;
 
 	for_each_sg(sg, s, nents, i)
-		__iommu_dma_unmap_swiotlb(dev, sg_dma_address(s),
+		iommu_dma_unmap_page(dev, sg_dma_address(s),
 				sg_dma_len(s), dir, attrs);
 }
 
@@ -1053,14 +1047,14 @@ 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.rc1.237.g0d66db33f3-goog