drbd: fix potential data corruption and protocol error

We assumed only bios with bi_idx == 0 would end up
in drbd_make_request().

That is wrong.

At least device mapper, in __clone_and_map(), may submit
clones only covering a partial bio, but sharing
the original bvec, by adjusting bi_idx and relevant
other bio members of the clone.

We used __bio_for_each_segment() in various places,
even though that is documented as
 * drivers should not use the __ version unless they _really_ want to
 * run through the entire bio and not just pending pieces

Impact: we would send the full bio bvec, even for the clone
with bi_idx > 0, which will cause data corruption on the
peer (because we submit wrong data at the clone offset),
and will cause a DRBD protocol error, disconnect/reconnect
and resync (thus fixing the corruption),
because the next package header would be expected right
in the middle of the sent data, causing DRBD magic mismatch.

Fix: drop the assert, and use bio_for_each_segment()
instead of the __ version.

Conflicts:

	drbd/drbd_tracing.c

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 8ca8925..f6cfc45 100644 (file)
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2734,7 +2734,7 @@ static int _drbd_send_bio(struct drbd_conf *mdev, struct bio *bio)
        struct bio_vec *bvec;
        int i;
        /* hint all but last page with MSG_MORE */
-       __bio_for_each_segment(bvec, bio, i, 0) {
+       bio_for_each_segment(bvec, bio, i) {
                if (!_drbd_no_send_page(mdev, bvec->bv_page,
                                     bvec->bv_offset, bvec->bv_len,
                                     i == bio->bi_vcnt -1 ? 0 : MSG_MORE))
@@ -2748,7 +2748,7 @@ static int _drbd_send_zc_bio(struct drbd_conf *mdev, struct bio *bio)
        struct bio_vec *bvec;
        int i;
        /* hint all but last page with MSG_MORE */
-       __bio_for_each_segment(bvec, bio, i, 0) {
+       bio_for_each_segment(bvec, bio, i) {
                if (!_drbd_send_page(mdev, bvec->bv_page,
                                     bvec->bv_offset, bvec->bv_len,
                                     i == bio->bi_vcnt -1 ? 0 : MSG_MORE))

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 4fc7f98..de319ba 100644 (file)
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1106,7 +1106,6 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
         */
        D_ASSERT(bio->bi_size > 0);
        D_ASSERT((bio->bi_size & 0x1ff) == 0);
-       D_ASSERT(bio->bi_idx == 0);
 
        /* to make some things easier, force alignment of requests within the
         * granularity of our hash tables */

diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 56fd69e..14aa4a2 100644 (file)
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -308,7 +308,7 @@ void drbd_csum_bio(struct drbd_conf *mdev, struct crypto_hash *tfm, struct bio *
        sg_init_table(&sg, 1);
        crypto_hash_init(&desc);
 
-       __bio_for_each_segment(bvec, bio, i, 0) {
+       bio_for_each_segment(bvec, bio, i) {
                sg_set_page(&sg, bvec->bv_page, bvec->bv_len, bvec->bv_offset);
                crypto_hash_update(&desc, &sg, sg.length);
        }