From 98114659e0d467e2c0ee6f24f2429329328fc312 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fusionio.com>
Date: Fri, 14 Sep 2012 11:22:38 -0400
Subject: [PATCH] Btrfs: fix race with freeze and free space inodes
So we start our freeze, somebody comes in and does an fsync() on a file
where we have to commit a transaction for whatever reason, and we will
deadlock because the freeze is waiting on FS_FREEZE people to stop writing
to the file system, but the transaction is waiting for its free space inodes
to be written out, which are in turn waiting on sb_start_intwrite while
trying to write the file extents. To fix this we'll just skip the
sb_start_intwrite() if we TRANS_JOIN_NOLOCK since we're being waited on by a
transaction commit so we're safe wrt to freeze and this will keep us from
deadlocking. Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
---
fs/btrfs/transaction.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c9265a603488c..a4fe5494d01bd 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -342,7 +342,15 @@ again:
if (!h)
return ERR_PTR(-ENOMEM);
- if (!__sb_start_write(root->fs_info->sb, SB_FREEZE_FS, false)) {
+ /*
+ * If we are JOIN_NOLOCK we're already committing a transaction and
+ * waiting on this guy, so we don't need to do the sb_start_intwrite
+ * because we're already holding a ref. We need this because we could
+ * have raced in and did an fsync() on a file which can kick a commit
+ * and then we deadlock with somebody doing a freeze.
+ */
+ if (type != TRANS_JOIN_NOLOCK &&
+ !__sb_start_write(root->fs_info->sb, SB_FREEZE_FS, false)) {
if (type == TRANS_JOIN_FREEZE)
return ERR_PTR(-EPERM);
sb_start_intwrite(root->fs_info->sb);
@@ -601,7 +609,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
}
}
- sb_end_intwrite(root->fs_info->sb);
+ if (lock)
+ sb_end_intwrite(root->fs_info->sb);
WARN_ON(cur_trans != info->running_transaction);
WARN_ON(atomic_read(&cur_trans->num_writers) < 1);
--
2.30.2