ARM: DMA-mapping: mark all !DMA_TO_DEVICE pages in unmapping as clean

It is common for one sg to include many pages, so mark all these
pages as clean to avoid unnecessary flushing on them in
set_pte_at() or update_mmu_cache().

The patch might improve loading performance of applciation code a bit.

On the below test code to read file(~1GByte size) from usb mass storage
disk to buffer created with mmap(PROT_READ | PROT_EXEC) on
Pandaboard, average ~1% improvement can be observed with the patch on
10 times test.

unsigned int sum = 0;

static unsigned long tv_diff(struct timeval *tv1, struct timeval *tv2)
{
	return (tv2->tv_sec - tv1->tv_sec) * 1000000 +
		(tv2->tv_usec - tv1->tv_usec);
}

int main(int argc, char *argv[])
{
	char *mbuffer;
	int fd;
	int i;
	unsigned long page_size, size;
	struct stat stat;
	struct timeval t1, t2;

	page_size = getpagesize();
	fd = open(argv[1], O_RDONLY);
	assert(fd >= 0);

	fstat(fd, &stat);
	size = stat.st_size;
	printf("%s: file %s, file size %lu, page size %lu\n", argv[0],
		read_filename, size, page_size);

	gettimeofday(&t1, NULL);
	mbuffer = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_SHARED, fd, 0);
	for (i = 0 ; i < size ; i += page_size)
		sum += mbuffer[i];
	munmap(mbuffer, page_size);
	gettimeofday(&t2, NULL);
	printf("\tread mmaped time: %luus\n", tv_diff(&t1, &t2));

	close(fd);
}
Acked-by: NNicolas Pitre <nicolas.pitre@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Russell King <linux@arm.linux.org.uk>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NMarek Szyprowski <m.szyprowski@samsung.com>

arch/arm/mm/dma-mapping.c

@@ -880,10 +880,24 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
 
 	/*
-	 * Mark the D-cache clean for this page to avoid extra flushing.
+	 * Mark the D-cache clean for these pages to avoid extra flushing.
 	 */
-	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
-		set_bit(PG_dcache_clean, &page->flags);
+	if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+		unsigned long pfn;
+		size_t left = size;
+
+		pfn = page_to_pfn(page) + off / PAGE_SIZE;
+		off %= PAGE_SIZE;
+		if (off) {
+			pfn++;
+			left -= PAGE_SIZE - off;
+		}
+		while (left >= PAGE_SIZE) {
+			page = pfn_to_page(pfn++);
+			set_bit(PG_dcache_clean, &page->flags);
+			left -= PAGE_SIZE;
+		}
+	}
 }
 
 /**