MIPS: make dma_sync_*_for_cpu a little less overzealous

When transferring DMA ownership back to the CPU there should never
be any writeback from the cache, as the buffer was owned by the
device until now.  Instead it should just be invalidated for the
mapping directions where the device could have written data.
Note that the changes rely on the fact that kmap_atomic is stubbed
out for the !HIGHMEM case to simplify the code a bit.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>

arch/mips/mm/dma-noncoherent.c

@@ -55,22 +55,34 @@ void *arch_dma_set_uncached(void *addr, size_t size)
 	return (void *)(__pa(addr) + UNCAC_BASE);
 }
 
-static inline void dma_sync_virt(void *addr, size_t size,
+static inline void dma_sync_virt_for_device(void *addr, size_t size,
 		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		dma_cache_wback((unsigned long)addr, size);
 		break;
-
 	case DMA_FROM_DEVICE:
 		dma_cache_inv((unsigned long)addr, size);
 		break;
-
 	case DMA_BIDIRECTIONAL:
 		dma_cache_wback_inv((unsigned long)addr, size);
 		break;
+	default:
+		BUG();
+	}
+}
 
+static inline void dma_sync_virt_for_cpu(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
 	default:
 		BUG();
 	}
@@ -82,7 +94,7 @@ static inline void dma_sync_virt(void *addr, size_t size,
  * configured then the bulk of this loop gets optimized out.
  */
 static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+		enum dma_data_direction dir, bool for_device)
 {
 	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
 	unsigned long offset = paddr & ~PAGE_MASK;
@@ -90,18 +102,20 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 
 	do {
 		size_t len = left;
+		void *addr;
 
 		if (PageHighMem(page)) {
-			void *addr;
-
 			if (offset + len > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
+		}
+
+		addr = kmap_atomic(page);
+		if (for_device)
+			dma_sync_virt_for_device(addr + offset, len, dir);
+		else
+			dma_sync_virt_for_cpu(addr + offset, len, dir);
+		kunmap_atomic(addr);
 
-			addr = kmap_atomic(page);
-			dma_sync_virt(addr + offset, len, dir);
-			kunmap_atomic(addr);
-		} else
-			dma_sync_virt(page_address(page) + offset, size, dir);
 		offset = 0;
 		page++;
 		left -= len;
@@ -111,7 +125,7 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	dma_sync_phys(paddr, size, dir);
+	dma_sync_phys(paddr, size, dir, true);
 }
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
@@ -119,16 +133,14 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
 	if (cpu_needs_post_dma_flush())
-		dma_sync_phys(paddr, size, dir);
+		dma_sync_phys(paddr, size, dir, false);
 }
 #endif
 
 void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
-
-	dma_sync_virt(vaddr, size, direction);
+	dma_sync_virt_for_device(vaddr, size, direction);
 }
 
 #ifdef CONFIG_DMA_PERDEV_COHERENT