summaryrefslogtreecommitdiff
path: root/fs/btrfs/transaction.c
diff options
context:
space:
mode:
authorJosef Bacik <josef@redhat.com>2011-06-15 00:22:15 +0400
committerJosef Bacik <josef@redhat.com>2011-06-15 21:24:47 +0400
commited0ca14021e5ae3147602128641aa7f742ab227c (patch)
tree22f9a66f0f99770edb483963ff308982424f2e53 /fs/btrfs/transaction.c
parent8351583e3f6e430ce8f71913909a96ad5cc6a2f6 (diff)
downloadlinux-ed0ca14021e5ae3147602128641aa7f742ab227c.tar.xz
Btrfs: set no_trans_join after trying to expand the transaction
We can lockup if we try to allow new writers join the transaction and we have flushoncommit set or have a pending snapshot. This is because we set no_trans_join and then loop around and try to wait for ordered extents again. The problem is the ordered endio stuff needs to join the transaction, which it can't do because no_trans_join is set. So instead wait until after this loop to set no_trans_join and then make sure to wait for num_writers == 1 in case anybody got started in between us exiting the loop and setting no_trans_join. This could easily be reproduced by mounting -o flushoncommit and running xfstest 13. It cannot be reproduced with this patch. Thanks, Reported-by: Jim Schutt <jaschut@sandia.gov> Signed-off-by: Josef Bacik <josef@redhat.com>
Diffstat (limited to 'fs/btrfs/transaction.c')
-rw-r--r--fs/btrfs/transaction.c14
1 files changed, 11 insertions, 3 deletions
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 2b3590b9fe98..56695595e036 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1241,12 +1241,20 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
schedule_timeout(1);
finish_wait(&cur_trans->writer_wait, &wait);
- spin_lock(&root->fs_info->trans_lock);
- root->fs_info->trans_no_join = 1;
- spin_unlock(&root->fs_info->trans_lock);
} while (atomic_read(&cur_trans->num_writers) > 1 ||
(should_grow && cur_trans->num_joined != joined));
+ /*
+ * Ok now we need to make sure to block out any other joins while we
+ * commit the transaction. We could have started a join before setting
+ * no_join so make sure to wait for num_writers to == 1 again.
+ */
+ spin_lock(&root->fs_info->trans_lock);
+ root->fs_info->trans_no_join = 1;
+ spin_unlock(&root->fs_info->trans_lock);
+ wait_event(cur_trans->writer_wait,
+ atomic_read(&cur_trans->num_writers) == 1);
+
ret = create_pending_snapshots(trans, root->fs_info);
BUG_ON(ret);