Btrfs: fix tree corruption after multi-thread snapshots and inode_cache flush

[pandora-kernel.git] / fs / btrfs / ctree.c

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0fe615e..dede441 100644 (file)
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -514,10 +514,25 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
                                   struct btrfs_root *root,
                                   struct extent_buffer *buf)
 {
+       /* ensure we can see the force_cow */
+       smp_rmb();
+
+       /*
+        * We do not need to cow a block if
+        * 1) this block is not created or changed in this transaction;
+        * 2) this block does not belong to TREE_RELOC tree;
+        * 3) the root is not forced COW.
+        *
+        * What is forced COW:
+        *    when we create snapshot during commiting the transaction,
+        *    after we've finished coping src root, we must COW the shared
+        *    block to ensure the metadata consistency.
+        */
        if (btrfs_header_generation(buf) == trans->transid &&
            !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
            !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
-             btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+             btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
+           !root->force_cow)
                return 0;
        return 1;
 }