md/raid1: Don't release reference to device while handling read error.

When we get a read error, we arrange for raid1d to handle it.
Currently we release the reference on the device.  This can result
in
   conf->mirrors[read_disk].rdev
being NULL in fix_read_error, if the device happens to get removed
before the read error is handled.

So instead keep the reference until the read error has been fully
handled.

Reported-by: hank <pyu@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 55ccf47..e913356 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -333,9 +333,10 @@ static void raid1_end_read_request(struct bio *bio, int error)
                spin_unlock_irqrestore(&conf->device_lock, flags);
        }
 
-       if (uptodate)
+       if (uptodate) {
                raid_end_bio_io(r1_bio);
-       else {
+               rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+       } else {
                /*
                 * oops, read error:
                 */
@@ -349,9 +350,8 @@ static void raid1_end_read_request(struct bio *bio, int error)
                        (unsigned long long)r1_bio->sector);
                set_bit(R1BIO_ReadError, &r1_bio->state);
                reschedule_retry(r1_bio);
+               /* don't drop the reference on read_disk yet */
        }
-
-       rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
 }
 
 static void close_write(struct r1bio *r1_bio)
@@ -2229,6 +2229,7 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
                unfreeze_array(conf);
        } else
                md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
+       rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
 
        bio = r1_bio->bios[r1_bio->read_disk];
        bdevname(bio->bi_bdev, b);