[PATCH] md: Fix 'rdev->nr_pending' count when retrying barrier requests

When retrying a failed BIO_RW_BARRIER request, we need to keep the reference
in ->nr_pending over the whole retry.  Currently, we only hold the reference
if the failed request is the *last* one to finish - which is silly, because it
would normally be the first to finish.

So move the rdev_dec_pending call up into the didn't-fail branch.  As the rdev
isn't used in the later code, calling rdev_dec_pending earlier doesn't hurt.

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index b8c13c897ccbb0d9a1ff08a5ffe686d559a4e5fb..4070eff6f0f8aca1d1c931a1505431c3d6cc1a2b 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -319,6 +319,7 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
                set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
                set_bit(R1BIO_BarrierRetry, &r1_bio->state);
                r1_bio->mddev->barriers_work = 0;
+               /* Don't rdev_dec_pending in this branch - keep it for the retry */
        } else {
                /*
                 * this branch is our 'one mirror IO has finished' event handler:
@@ -365,6 +366,7 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
                                }
                        }
                }
+               rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
        }
        /*
         *
@@ -374,11 +376,9 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
        if (atomic_dec_and_test(&r1_bio->remaining)) {
                if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
                        reschedule_retry(r1_bio);
-                       /* Don't dec_pending yet, we want to hold
-                        * the reference over the retry
-                        */
                        goto out;
                }
+               /* it really is the end of this request */
                if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
                        /* free extra copy of the data pages */
                        int i = bio->bi_vcnt;
@@ -393,8 +393,6 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
                md_write_end(r1_bio->mddev);
                raid_end_bio_io(r1_bio);
        }
-
-       rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
  out:
        if (to_put)
                bio_put(to_put);
@@ -1414,6 +1412,7 @@ static void raid1d(mddev_t *mddev)
                         * Better resubmit without the barrier.
                         * We know which devices to resubmit for, because
                         * all others have had their bios[] entry cleared.
+                        * We already have a nr_pending reference on these rdevs.
                         */
                        int i;
                        clear_bit(R1BIO_BarrierRetry, &r1_bio->state);