ext4: Fix to read empty directory blocks correctly in 64k

(cherry picked from commit 7be2baaa0322c59ba888aa5260a8c130666acd41)

The rec_len field in the directory entry is 16 bits, so there was a
problem representing rec_len for filesystems with a 64k block size in
the case where the directory entry takes the entire 64k block.
Unfortunately, there were two schemes that were proposed; one where
all zeros meant 65536 and one where all ones (65535) meant 65536.
E2fsprogs used 0, whereas the kernel used 65535.  Oops.  Fortunately
this case happens extremely rarely, with the most common case being
the lost+found directory, created by mke2fs.

So we will be liberal in what we accept, and accept both encodings,
but we will continue to encode 65536 as 65535.  This will require a
change in e2fsprogs, but with fortunately ext4 filesystems normally
have the dir_index feature enabled, which precludes having a
completely empty directory block.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 85f58aff9f0bae1096f51625b9a369ec3f47ddb2..f613d57aef7ccd0eb871c9aa36e57af109b7d4ed 100644 (file)
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -860,7 +860,7 @@ static inline unsigned ext4_rec_len_from_disk(__le16 dlen)
 {
        unsigned len = le16_to_cpu(dlen);
 
-       if (len == EXT4_MAX_REC_LEN)
+       if (len == EXT4_MAX_REC_LEN || len == 0)
                return 1 << 16;
        return len;
 }