Btrfs: fix corrupted metadata in the snapshot

When we delete a inode, we will remove all the delayed items including delayed
inode update, and then truncate all the relative metadata. If there is lots of
metadata, we will end the current transaction, and start a new transaction to
truncate the left metadata. In this way, we will leave a inode item that its
link counter is > 0, and also may leave some directory index items in fs/file tree
after the current transaction ends. In other words, the metadata in this fs/file tree
is inconsistent. If we create a snapshot for this tree now, we will find a inode with
corrupted metadata in the new snapshot, and we won't continue to drop the left metadata,
because its link counter is not 0.

We fix this problem by updating the inode item before the current transaction ends.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>

1 files changed, 21 insertions, 8 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index a86fc723aad..f8ae448ebec 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -290,7 +290,8 @@ static int may_wait_transaction(struct btrfs_root *root, int type)
 }
 
 static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
-                                                    u64 num_items, int type)
+                                                    u64 num_items, int type,
+                                                    int noflush)
 {
         struct btrfs_trans_handle *h;
         struct btrfs_transaction *cur_trans;
@@ -324,9 +325,14 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
                 }
 
                 num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
-                ret = btrfs_block_rsv_add(root,
-                                          &root->fs_info->trans_block_rsv,
-                                          num_bytes);
+                if (noflush)
+                        ret = btrfs_block_rsv_add_noflush(root,
+                                                &root->fs_info->trans_block_rsv,
+                                                num_bytes);
+                else
+                        ret = btrfs_block_rsv_add(root,
+                                                &root->fs_info->trans_block_rsv,
+                                                num_bytes);
                 if (ret)
                         return ERR_PTR(ret);
         }
@@ -393,21 +399,28 @@ got_it:
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
                                                    int num_items)
 {
-        return start_transaction(root, num_items, TRANS_START);
+        return start_transaction(root, num_items, TRANS_START, 0);
 }
+
+struct btrfs_trans_handle *btrfs_start_transaction_noflush(
+                                        struct btrfs_root *root, int num_items)
+{
+        return start_transaction(root, num_items, TRANS_START, 1);
+}
+
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
-        return start_transaction(root, 0, TRANS_JOIN);
+        return start_transaction(root, 0, TRANS_JOIN, 0);
 }
 
 struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
-        return start_transaction(root, 0, TRANS_JOIN_NOLOCK);
+        return start_transaction(root, 0, TRANS_JOIN_NOLOCK, 0);
 }
 
 struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
-        return start_transaction(root, 0, TRANS_USERSPACE);
+        return start_transaction(root, 0, TRANS_USERSPACE, 0);
 }
 
 /* wait for a transaction commit to be fully complete */