arch/parisc: 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/20161110113529.76501.44762.stgit@ahduyck-blue-test.jf.intel.com
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Helge Deller <deller@gmx.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/parisc/kernel/pci-dma.c

@@ -459,7 +459,9 @@ static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
 	void *addr = page_address(page) + offset;
 	BUG_ON(direction == DMA_NONE);
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		flush_kernel_dcache_range((unsigned long) addr, size);
+
 	return virt_to_phys(addr);
 }
 
@@ -469,6 +471,9 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 {
 	BUG_ON(direction == DMA_NONE);
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	if (direction == DMA_TO_DEVICE)
 		return;
 
@@ -479,7 +484,6 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 	 */
 
 	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size);
-	return;
 }
 
 static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -496,6 +500,10 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
 		sg_dma_len(sg) = sg->length;
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		flush_kernel_dcache_range(vaddr, sg->length);
 	}
 	return nents;
@@ -510,6 +518,9 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	BUG_ON(direction == DMA_NONE);
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	if (direction == DMA_TO_DEVICE)
 		return;
 
@@ -517,7 +528,6 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i)
 		flush_kernel_vmap_range(sg_virt(sg), sg->length);
-	return;
 }
 
 static void pa11_dma_sync_single_for_cpu(struct device *dev,