The deadlock happened when we mount degraded filesystem, the reproduced
steps are following:
# mkfs.btrfs -f -m raid1 -d raid1 <dev0> <dev1>
# echo 1 > /sys/block/`basename <dev0>`/device/delete
# mount -o degraded <dev1> <mnt>
The reason was that the counter -- bi_remaining was wrong. If the missing
or unwriteable device was the last device in the mapping array, we would
not submit the original bio, so we shouldn't increase bi_remaining of it
in btrfs_end_bio(), or we would skip the final endio handle.
Fix this problem by adding a flag into btrfs bio structure. If we submit
the original bio, we will set the flag, and we increase bi_remaining counter,
or we don't.
Though there is another way to fix it -- decrease bi_remaining counter of the
original bio when we make sure the original bio is not submitted, this method
need add more check and is easy to make mistake.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
set_bit(BIO_UPTODATE, &bio->bi_flags);
err = 0;
}
+
+ if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED))
+ bio_endio_nodec(bio, err);
+ else
+ bio_endio(bio, err);
kfree(bbio);
- bio_endio_nodec(bio, err);
} else if (!is_orig_bio) {
bio_put(bio);
}
BUG_ON(!bio); /* -ENOMEM */
} else {
bio = first_bio;
+ bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED;
}
submit_stripe_bio(root, bbio, bio,
struct btrfs_bio;
typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
+#define BTRFS_BIO_ORIG_BIO_SUBMITTED 0x1
+
struct btrfs_bio {
atomic_t stripes_pending;
struct btrfs_fs_info *fs_info;
bio_end_io_t *end_io;
struct bio *orig_bio;
+ unsigned long flags;
void *private;
atomic_t error;
int max_errors;