arch/sh: add option to skip DMA sync as a part of mapping

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/20161110113539.76501.6539.stgit@ahduyck-blue-test.jf.intel.com
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/sh/kernel/dma-nommu.c

@@ -18,7 +18,9 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
 	dma_addr_t addr = page_to_phys(page) + offset;
 
 	WARN_ON(size == 0);
-	dma_cache_sync(dev, page_address(page) + offset, size, dir);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_cache_sync(dev, page_address(page) + offset, size, dir);
 
 	return addr;
 }
@@ -35,7 +37,8 @@ static int nommu_map_sg(struct device *dev, struct scatterlist *sg,
 	for_each_sg(sg, s, nents, i) {
 		BUG_ON(!sg_page(s));
 
-		dma_cache_sync(dev, sg_virt(s), s->length, dir);
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			dma_cache_sync(dev, sg_virt(s), s->length, dir);
 
 		s->dma_address = sg_phys(s);
 		s->dma_length = s->length;