block: use on-stack page vec for <= UIO_FASTIOV

Avoid a kmalloc+kfree for each page array, if we only have a few pages
that are mapped. An alloc+free for each IO is quite expensive, and
it's pretty pointless if we're only dealing with 1 or a few vecs.

Use UIO_FASTIOV like we do in other spots to set a sane limit for how
big of an IO we want to avoid allocations for.

Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 11 insertions, 3 deletions

diff --git a/block/blk-map.c b/block/blk-map.c
index 16153fdc478f..f3768876d618 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -268,12 +268,19 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	}
 
 	while (iov_iter_count(iter)) {
-		struct page **pages;
+		struct page **pages, *stack_pages[UIO_FASTIOV];
 		ssize_t bytes;
 		size_t offs, added = 0;
 		int npages;
 
-		bytes = iov_iter_get_pages_alloc2(iter, &pages, LONG_MAX, &offs);
+		if (nr_vecs <= ARRAY_SIZE(stack_pages)) {
+			pages = stack_pages;
+			bytes = iov_iter_get_pages2(iter, pages, LONG_MAX,
+							nr_vecs, &offs);
+		} else {
+			bytes = iov_iter_get_pages_alloc2(iter, &pages,
+							LONG_MAX, &offs);
+		}
 		if (unlikely(bytes <= 0)) {
 			ret = bytes ? bytes : -EFAULT;
 			goto out_unmap;
@@ -309,7 +316,8 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		 */
 		while (j < npages)
 			put_page(pages[j++]);
-		kvfree(pages);
+		if (pages != stack_pages)
+			kvfree(pages);
 		/* couldn't stuff something into bio? */
 		if (bytes) {
 			iov_iter_revert(iter, bytes);