3 files changed, 26 insertions, 1 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0fe615e4ea38..dede441bdeee 100644
--- 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;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b9ba59ff9292..b1cb3c052484 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1271,6 +1271,8 @@ struct btrfs_root {
          * for stat.  It may be used for more later
          */
         dev_t anon_dev;
+
+        int force_cow;
 };
 
 struct btrfs_ioctl_defrag_range_args {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6a0574e923bc..81376d94cd3c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -785,6 +785,10 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 
                         btrfs_save_ino_cache(root, trans);
 
+                        /* see comments in should_cow_block() */
+                        root->force_cow = 0;
+                        smp_wmb();
+
                         if (root->commit_root != root->node) {
                                 mutex_lock(&root->fs_commit_mutex);
                                 switch_commit_root(root);
@@ -947,6 +951,10 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         btrfs_tree_unlock(old);
         free_extent_buffer(old);
 
+        /* see comments in should_cow_block() */
+        root->force_cow = 1;
+        smp_wmb();
+
         btrfs_set_root_node(new_root_item, tmp);
         /* record when the snapshot was created in key.offset */
         key.offset = trans->transid;