arch/microblaze: 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/20161110113508.76501.77583.stgit@ahduyck-blue-test.jf.intel.com
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Michal Simek <monstr@monstr.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/microblaze/kernel/dma.c

@@ -61,6 +61,10 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	/* FIXME this part of code is untested */
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		__dma_sync(page_to_phys(sg_page(sg)) + sg->offset,
 							sg->length, direction);
 	}
@@ -80,7 +84,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 					     enum dma_data_direction direction,
 					     unsigned long attrs)
 {
-	__dma_sync(page_to_phys(page) + offset, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync(page_to_phys(page) + offset, size, direction);
 	return page_to_phys(page) + offset;
 }
 
@@ -95,7 +100,8 @@ static inline void dma_direct_unmap_page(struct device *dev,
  * phys_to_virt is here because in __dma_sync_page is __virt_to_phys and
  * dma_address is physical address
  */
-	__dma_sync(dma_address, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync(dma_address, size, direction);
 }
 
 static inline void