ubifs: Rename whiteout atomically

Currently, rename whiteout has 3 steps:
  1. create tmpfile(which associates old dentry to tmpfile inode) for
     whiteout, and store tmpfile to disk
  2. link whiteout, associate whiteout inode to old dentry agagin and
     store old dentry, old inode, new dentry on disk
  3. writeback dirty whiteout inode to disk

Suddenly power-cut or error occurring(eg. ENOSPC returned by budget,
memory allocation failure) during above steps may cause kinds of problems:
  Problem 1: ENOSPC returned by whiteout space budget (before step 2),
	     old dentry will disappear after rename syscall, whiteout file
	     cannot be found either.

	     ls dir  // we get file, whiteout
	     rename(dir/file, dir/whiteout, REANME_WHITEOUT)
	     ENOSPC = ubifs_budget_space(&wht_req) // return
	     ls dir  // empty (no file, no whiteout)
  Problem 2: Power-cut happens before step 3, whiteout inode with 'nlink=1'
	     is not stored on disk, whiteout dentry(old dentry) is written
	     on disk, whiteout file is lost on next mount (We get "dead
	     directory entry" after executing 'ls -l' on whiteout file).

Now, we use following 3 steps to finish rename whiteout:
  1. create an in-mem inode with 'nlink = 1' as whiteout
  2. ubifs_jnl_rename (Write on disk to finish associating old dentry to
     whiteout inode, associating new dentry with old inode)
  3. iput(whiteout)

Rely writing in-mem inode on disk by ubifs_jnl_rename() to finish rename
whiteout, which avoids middle disk state caused by suddenly power-cut
and error occurring.

Fixes: 9e0a1fff8db56ea ("ubifs: Implement RENAME_WHITEOUT")
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Signed-off-by: Richard Weinberger <richard@nod.at>

1 files changed, 44 insertions, 8 deletions

diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 8ea680dba61e..75dab0ae3939 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -1207,9 +1207,9 @@ out_free:
  * @sync: non-zero if the write-buffer has to be synchronized
  *
  * This function implements the re-name operation which may involve writing up
- * to 4 inodes and 2 directory entries. It marks the written inodes as clean
- * and returns zero on success. In case of failure, a negative error code is
- * returned.
+ * to 4 inodes(new inode, whiteout inode, old and new parent directory inodes)
+ * and 2 directory entries. It marks the written inodes as clean and returns
+ * zero on success. In case of failure, a negative error code is returned.
  */
 int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		     const struct inode *old_inode,
@@ -1222,14 +1222,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	void *p;
 	union ubifs_key key;
 	struct ubifs_dent_node *dent, *dent2;
-	int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0;
+	int err, dlen1, dlen2, ilen, wlen, lnum, offs, len, orphan_added = 0;
 	int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ;
 	int last_reference = !!(new_inode && new_inode->i_nlink == 0);
 	int move = (old_dir != new_dir);
-	struct ubifs_inode *new_ui;
+	struct ubifs_inode *new_ui, *whiteout_ui;
 	u8 hash_old_dir[UBIFS_HASH_ARR_SZ];
 	u8 hash_new_dir[UBIFS_HASH_ARR_SZ];
 	u8 hash_new_inode[UBIFS_HASH_ARR_SZ];
+	u8 hash_whiteout_inode[UBIFS_HASH_ARR_SZ];
 	u8 hash_dent1[UBIFS_HASH_ARR_SZ];
 	u8 hash_dent2[UBIFS_HASH_ARR_SZ];
 
@@ -1249,9 +1250,20 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	} else
 		ilen = 0;
 
+	if (whiteout) {
+		whiteout_ui = ubifs_inode(whiteout);
+		ubifs_assert(c, mutex_is_locked(&whiteout_ui->ui_mutex));
+		ubifs_assert(c, whiteout->i_nlink == 1);
+		ubifs_assert(c, !whiteout_ui->dirty);
+		wlen = UBIFS_INO_NODE_SZ;
+		wlen += whiteout_ui->data_len;
+	} else
+		wlen = 0;
+
 	aligned_dlen1 = ALIGN(dlen1, 8);
 	aligned_dlen2 = ALIGN(dlen2, 8);
-	len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8);
+	len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) +
+	      ALIGN(wlen, 8) + ALIGN(plen, 8);
 	if (move)
 		len += plen;
 
@@ -1313,6 +1325,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		p += ALIGN(ilen, 8);
 	}
 
+	if (whiteout) {
+		pack_inode(c, p, whiteout, 0);
+		err = ubifs_node_calc_hash(c, p, hash_whiteout_inode);
+		if (err)
+			goto out_release;
+
+		p += ALIGN(wlen, 8);
+	}
+
 	if (!move) {
 		pack_inode(c, p, old_dir, 1);
 		err = ubifs_node_calc_hash(c, p, hash_old_dir);
@@ -1352,6 +1373,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		if (new_inode)
 			ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
 						  new_inode->i_ino);
+		if (whiteout)
+			ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
+						  whiteout->i_ino);
 	}
 	release_head(c, BASEHD);
 
@@ -1368,8 +1392,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, old_nm);
 		if (err)
 			goto out_ro;
-
-		ubifs_delete_orphan(c, whiteout->i_ino);
 	} else {
 		err = ubifs_add_dirt(c, lnum, dlen2);
 		if (err)
@@ -1390,6 +1412,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		offs += ALIGN(ilen, 8);
 	}
 
+	if (whiteout) {
+		ino_key_init(c, &key, whiteout->i_ino);
+		err = ubifs_tnc_add(c, &key, lnum, offs, wlen,
+				    hash_whiteout_inode);
+		if (err)
+			goto out_ro;
+		offs += ALIGN(wlen, 8);
+	}
+
 	ino_key_init(c, &key, old_dir->i_ino);
 	err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_old_dir);
 	if (err)
@@ -1410,6 +1441,11 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		new_ui->synced_i_size = new_ui->ui_size;
 		spin_unlock(&new_ui->ui_lock);
 	}
+	/*
+	 * No need to mark whiteout inode clean.
+	 * Whiteout doesn't have non-zero size, no need to update
+	 * synced_i_size for whiteout_ui.
+	 */
 	mark_inode_clean(c, ubifs_inode(old_dir));
 	if (move)
 		mark_inode_clean(c, ubifs_inode(new_dir));