block: fix bio_add_page for non trivial merge_bvec_fn case

commit 1d6165851cd8e3f919d446cd6da35dee44e8837e upstream.

We have to properly decrease bi_size in order to merge_bvec_fn return
right result.  Otherwise this result in false merge rejects for two
absolutely valid bio_vecs.  This may cause significant performance
penalty for example fs_block_size == 1k and block device is raid0 with
small chunk_size = 8k. Then it is impossible to merge 7-th fs-block in
to bio which already has 6 fs-blocks.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

1 files changed, 6 insertions, 1 deletions

diff --git a/fs/bio.c b/fs/bio.c
index 12da5db8682..e0c9e71cc40 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -542,13 +542,18 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 
 		if (page == prev->bv_page &&
 		    offset == prev->bv_offset + prev->bv_len) {
+			unsigned int prev_bv_len = prev->bv_len;
 			prev->bv_len += len;
 
 			if (q->merge_bvec_fn) {
 				struct bvec_merge_data bvm = {
+					/* prev_bvec is already charged in
+					   bi_size, discharge it in order to
+					   simulate merging updated prev_bvec
+					   as new bvec. */
 					.bi_bdev = bio->bi_bdev,
 					.bi_sector = bio->bi_sector,
-					.bi_size = bio->bi_size,
+					.bi_size = bio->bi_size - prev_bv_len,
 					.bi_rw = bio->bi_rw,
 				};