arm64: Add support for DMA_ATTR_SKIP_CPU_SYNC attribute to swiotlb

This patch adds support for DMA_ATTR_SKIP_CPU_SYNC attribute for
dma_{un}map_{page,sg} functions family to swiotlb.

DMA_ATTR_SKIP_CPU_SYNC allows platform code to skip synchronization of
the CPU cache for the given buffer assuming that it has been already
transferred to 'device' domain.

Ported from IOMMU .{un}map_{sg,page} ops.

Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/mm/dma-mapping.c

@@ -211,7 +211,8 @@ static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
 	dma_addr_t dev_addr;
 
 	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
-	if (!is_device_dma_coherent(dev))
+	if (!is_device_dma_coherent(dev) &&
+	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
 
 	return dev_addr;
@@ -222,7 +223,8 @@ static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
 				 size_t size, enum dma_data_direction dir,
 				 unsigned long attrs)
 {
-	if (!is_device_dma_coherent(dev))
+	if (!is_device_dma_coherent(dev) &&
+	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
 	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
 }
@@ -235,7 +237,8 @@ static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
 	int i, ret;
 
 	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
-	if (!is_device_dma_coherent(dev))
+	if (!is_device_dma_coherent(dev) &&
+	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		for_each_sg(sgl, sg, ret, i)
 			__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
 				       sg->length, dir);
@@ -251,7 +254,8 @@ static void __swiotlb_unmap_sg_attrs(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (!is_device_dma_coherent(dev))
+	if (!is_device_dma_coherent(dev) &&
+	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		for_each_sg(sgl, sg, nelems, i)
 			__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
 					 sg->length, dir);