1 files changed, 75 insertions, 9 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index b6dfe7af7a1f..fc4c14a72366 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2272,8 +2272,10 @@ again:
 			nritems = btrfs_header_nritems(path->nodes[0]);
 			if (path->slots[0] >= nritems) {
 				ret = btrfs_next_leaf(root, path);
-				if (ret)
+				if (ret == 1)
 					break;
+				else if (ret < 0)
+					goto out;
 			}
 			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
 					      path->slots[0]);
@@ -2377,13 +2379,41 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 			if (ret)
 				break;
 
-			/* for regular files, make sure corresponding
-			 * orphan item exist. extents past the new EOF
-			 * will be truncated later by orphan cleanup.
+			/*
+			 * Before replaying extents, truncate the inode to its
+			 * size. We need to do it now and not after log replay
+			 * because before an fsync we can have prealloc extents
+			 * added beyond the inode's i_size. If we did it after,
+			 * through orphan cleanup for example, we would drop
+			 * those prealloc extents just after replaying them.
 			 */
 			if (S_ISREG(mode)) {
-				ret = insert_orphan_item(wc->trans, root,
-							 key.objectid);
+				struct inode *inode;
+				u64 from;
+
+				inode = read_one_inode(root, key.objectid);
+				if (!inode) {
+					ret = -EIO;
+					break;
+				}
+				from = ALIGN(i_size_read(inode),
+					     root->fs_info->sectorsize);
+				ret = btrfs_drop_extents(wc->trans, root, inode,
+							 from, (u64)-1, 1);
+				/*
+				 * If the nlink count is zero here, the iput
+				 * will free the inode.  We bump it to make
+				 * sure it doesn't get freed until the link
+				 * count fixup is done.
+				 */
+				if (!ret) {
+					if (inode->i_nlink == 0)
+						inc_nlink(inode);
+					/* Update link count and nbytes. */
+					ret = btrfs_update_inode(wc->trans,
+								 root, inode);
+				}
+				iput(inode);
 				if (ret)
 					break;
 			}
@@ -3432,8 +3462,11 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		 * from this directory and from this transaction
 		 */
 		ret = btrfs_next_leaf(root, path);
-		if (ret == 1) {
-			last_offset = (u64)-1;
+		if (ret) {
+			if (ret == 1)
+				last_offset = (u64)-1;
+			else
+				err = ret;
 			goto done;
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
@@ -3885,6 +3918,7 @@ fill_holes:
 			ASSERT(ret == 0);
 			src = src_path->nodes[0];
 			i = 0;
+			need_find_last_extent = true;
 		}
 
 		btrfs_item_key_to_cpu(src, &key, i);
@@ -4234,6 +4268,31 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		num++;
 	}
 
+	/*
+	 * Add all prealloc extents beyond the inode's i_size to make sure we
+	 * don't lose them after doing a fast fsync and replaying the log.
+	 */
+	if (inode->flags & BTRFS_INODE_PREALLOC) {
+		struct rb_node *node;
+
+		for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
+			em = rb_entry(node, struct extent_map, rb_node);
+			if (em->start < i_size_read(&inode->vfs_inode))
+				break;
+			if (!list_empty(&em->list))
+				continue;
+			/* Same as above loop. */
+			if (++num > 32768) {
+				list_del_init(&tree->modified_extents);
+				ret = -EFBIG;
+				goto process;
+			}
+			refcount_inc(&em->refs);
+			set_bit(EXTENT_FLAG_LOGGING, &em->flags);
+			list_add_tail(&em->list, &extents);
+		}
+	}
+
 	list_sort(NULL, &extents, extent_cmp);
 	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
 	/*
@@ -4669,6 +4728,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 logged_isize = 0;
 	bool need_log_inode_item = true;
+	bool xattrs_logged = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -4971,6 +5031,7 @@ next_key:
 	err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
 	if (err)
 		goto out_unlock;
+	xattrs_logged = true;
 	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
 		btrfs_release_path(path);
 		btrfs_release_path(dst_path);
@@ -4983,6 +5044,11 @@ log_extents:
 	btrfs_release_path(dst_path);
 	if (need_log_inode_item) {
 		err = log_inode_item(trans, log, dst_path, inode);
+		if (!err && !xattrs_logged) {
+			err = btrfs_log_all_xattrs(trans, root, inode, path,
+						   dst_path);
+			btrfs_release_path(path);
+		}
 		if (err)
 			goto out_unlock;
 	}
@@ -5881,7 +5947,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	 * this will force the logging code to walk the dentry chain
 	 * up for the file
 	 */
-	if (S_ISREG(inode->vfs_inode.i_mode))
+	if (!S_ISDIR(inode->vfs_inode.i_mode))
 		inode->last_unlink_trans = trans->transid;
 
 	/*