arch/powerpc: 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/20161110113534.76501.86492.stgit@ahduyck-blue-test.jf.intel.comSigned-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

arch/powerpc/kernel/dma.c

@@ -203,6 +203,10 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg) + get_dma_offset(dev);
 		sg->dma_length = sg->length;
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
 	}
 
@@ -235,7 +239,10 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 					     unsigned long attrs)
 {
 	BUG_ON(dir == DMA_NONE);
-	__dma_sync_page(page, offset, size, dir);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync_page(page, offset, size, dir);
+
 	return page_to_phys(page) + offset + get_dma_offset(dev);
 }