arch/tile: add option to skip DMA sync as a part of map and unmap

This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to
avoid invoking cache line invalidation if the driver will just handle it
via a sync_for_cpu or sync_for_device call.

Link: http://lkml.kernel.org/r/20161110113550.76501.73060.stgit@ahduyck-blue-test.jf.intel.com
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/tile/kernel/pci-dma.c

@@ -213,10 +213,12 @@ static int tile_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		__dma_prep_pa_range(sg->dma_address, sg->length, direction);
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 		sg->dma_length = sg->length;
 #endif
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+		__dma_prep_pa_range(sg->dma_address, sg->length, direction);
 	}
 
 	return nents;
@@ -232,6 +234,8 @@ static void tile_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	BUG_ON(!valid_dma_direction(direction));
 	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
 		__dma_complete_pa_range(sg->dma_address, sg->length,
 					direction);
 	}
@@ -245,6 +249,7 @@ static dma_addr_t tile_dma_map_page(struct device *dev, struct page *page,
 	BUG_ON(!valid_dma_direction(direction));
 
 	BUG_ON(offset + size > PAGE_SIZE);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		__dma_prep_page(page, offset, size, direction);
 
 	return page_to_pa(page) + offset;
@@ -256,6 +261,9 @@ static void tile_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 {
 	BUG_ON(!valid_dma_direction(direction));
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	__dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)),
 			    dma_address & (PAGE_SIZE - 1), size, direction);
 }