md/raid1: close some possible races on write errors during resync

commit 58e94ae18478c08229626daece2fc108a4a23261 upstream.

commit 4367af556133723d0f443e14ca8170d9447317cb
   md/raid1: clear bad-block record when write succeeds.

Added a 'reschedule_retry' call possibility at the end of
end_sync_write, but didn't add matching code at the end of
sync_request_write.  So if the writes complete very quickly, or
scheduling makes it seem that way, then we can miss rescheduling
the request and the resync could hang.

Also commit 73d5c38a9536142e062c35997b044e89166e063b
    md: avoid races when stopping resync.

Fix a race condition in this same code in end_sync_write but didn't
make the change in sync_request_write.

This patch updates sync_request_write to fix both of those.
Patch is suitable for 3.1 and later kernels.

Reported-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Original-version-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 58f0055..2d97bf0 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1713,8 +1713,14 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 
        if (atomic_dec_and_test(&r1_bio->remaining)) {
                /* if we're here, all write(s) have completed, so clean up */
-               md_done_sync(mddev, r1_bio->sectors, 1);
-               put_buf(r1_bio);
+               int s = r1_bio->sectors;
+               if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
+                   test_bit(R1BIO_WriteError, &r1_bio->state))
+                       reschedule_retry(r1_bio);
+               else {
+                       put_buf(r1_bio);
+                       md_done_sync(mddev, s, 1);
+               }
        }
 }