[PATCH,RFC] ext3: Add support for non-native signed/unsigned htree hash algorithms

[Theodore Ts'o]

The original ext3 hash algorithms assumed that variables of type char
were signed, as God and K&R intended.  Unfortunately, this assumption
is not true on some architectures.  Userspace support for marking
filesystems with non-native signed/unsigned chars was added two years
ago, but the kernel-side support was never added (until now).

Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
Cc: akpm@xxxxxxxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
---
 fs/ext3/hash.c             |   42 +++++++++++++++++++++++++++++++++---------
 fs/ext3/namei.c            |    7 +++++++
 fs/ext3/super.c            |   15 +++++++++++++++
 include/linux/ext3_fs.h    |   28 +++++++++++++++++++++++++++-
 include/linux/ext3_fs_sb.h |    1 +
 5 files changed, 83 insertions(+), 10 deletions(-)

diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c
index c30e149..855eacb 100644
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -35,11 +35,20 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash (const char *name, int len, int unsigned_flag)
 {
-	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+ 	const unsigned char *ucp = (const unsigned char *) name;
+	const signed char *scp = (const signed char *) name;
+	int c;
+
 	while (len--) {
-		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+		if (unsigned_flag)
+			c = (int) *ucp++;
+		else
+			c = (int) *scp++;
+
+		hash = hash1 + (hash0 ^ (c * 7152373));
 
 		if (hash & 0x80000000) hash -= 0x7fffffff;
 		hash1 = hash0;
@@ -48,10 +57,13 @@ static __u32 dx_hack_hash (const char *name, int len)
 	return (hash0 << 1);
 }
 
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static void str2hashbuf(const char *msg, int len, __u32 *buf, int num,
+			int unsigned_flag)
 {
 	__u32	pad, val;
-	int	i;
+	int	i, c;
+	const unsigned char *ucp = (const unsigned char *) msg;
+	const signed char *scp = (const signed char *) msg;
 
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
@@ -62,7 +74,12 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
 	for (i=0; i < len; i++) {
 		if ((i % 4) == 0)
 			val = pad;
-		val = msg[i] + (val << 8);
+		if (unsigned_flag)
+			c = (int) ucp[i];
+		else
+			c = (int) scp[i];
+
+		val = c + (val << 8);
 		if ((i % 4) == 3) {
 			*buf++ = val;
 			val = pad;
@@ -95,6 +112,7 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	const char	*p;
 	int		i;
 	__u32		in[8], buf[4];
+	int		unsigned_flag = 0;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -113,13 +131,17 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	}
 
 	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY_UNSIGNED:
+		unsigned_flag++;
 	case DX_HASH_LEGACY:
-		hash = dx_hack_hash(name, len);
+		hash = dx_hack_hash(name, len, unsigned_flag);
 		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		unsigned_flag++;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 8);
+			str2hashbuf(p, len, in, 8, unsigned_flag);
 			half_md4_transform(buf, in);
 			len -= 32;
 			p += 32;
@@ -127,10 +149,12 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		minor_hash = buf[2];
 		hash = buf[1];
 		break;
+	case DX_HASH_TEA_UNSIGNED:
+		unsigned_flag++;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 4);
+			str2hashbuf(p, len, in, 4, unsigned_flag);
 			TEA_transform(buf, in);
 			len -= 16;
 			p += 16;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index de13e91..a688a47 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -369,6 +369,8 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 	if (dentry)
 		ext3fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo);
@@ -637,6 +639,9 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
 		hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT3_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);
@@ -1415,6 +1420,8 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	/* Initialize as for dx_probe */
 	hinfo.hash_version = root->info.hash_version;
+	if (hinfo.hash_version <= DX_HASH_TEA)
+		hinfo.hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 	ext3fs_dirhash(name, namelen, &hinfo);
 	frame = frames;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index f38a5af..fa706ea 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1727,6 +1727,21 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	for (i=0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
+	i = le32_to_cpu(es->s_flags);
+	if (i & EXT2_FLAGS_UNSIGNED_HASH)
+		sbi->s_hash_unsigned = 3;
+	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+		char	c;
+
+		c = (char) 255;
+		if (((int) c) == -1) {
+			es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+		} else {
+			es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+			sbi->s_hash_unsigned = 3;
+		}
+		sb->s_dirt = 1;
+	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
 		printk (KERN_ERR
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 8120fa1..57420c8 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -354,6 +354,13 @@ struct ext3_inode {
 #define	EXT3_ORPHAN_FS			0x0004	/* Orphans being recovered */
 
 /*
+ * Misc. filesystem flags
+ */
+#define EXT2_FLAGS_SIGNED_HASH		0x0001  /* Signed dirhash in use */
+#define EXT2_FLAGS_UNSIGNED_HASH	0x0002  /* Unsigned dirhash in use */
+#define EXT2_FLAGS_TEST_FILESYS		0x0004	/* to test development code */
+
+/*
  * Mount flags
  */
 #define EXT3_MOUNT_CHECK		0x00001	/* Do mount-time checks */
@@ -487,7 +494,23 @@ struct ext3_super_block {
 	__u16	s_reserved_word_pad;
 	__le32	s_default_mount_opts;
 	__le32	s_first_meta_bg;	/* First metablock block group */
-	__u32	s_reserved[190];	/* Padding to the end of the block */
+	__le32	s_mkfs_time;		/* When the filesystem was created */
+	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
+	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+/*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
+	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
+	__le32	s_free_blocks_count_hi;	/* Free blocks count */
+	__le16	s_min_extra_isize;	/* All inodes have at least # bytes */
+	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
+	__le32	s_flags;		/* Miscellaneous flags */
+	__le16  s_raid_stride;		/* RAID stride */
+	__le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
+	__le64  s_mmp_block;            /* Block for multi-mount protection */
+	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
+	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
+	__u8	s_reserved_char_pad2;
+	__le16  s_reserved_pad;
+	__u32   s_reserved[162];        /* Padding to the end of the block */
 };
 
 #ifdef __KERNEL__
@@ -692,6 +715,9 @@ static inline __le16 ext3_rec_len_to_disk(unsigned len)
 #define DX_HASH_LEGACY		0
 #define DX_HASH_HALF_MD4	1
 #define DX_HASH_TEA		2
+#define DX_HASH_LEGACY_UNSIGNED	3
+#define DX_HASH_HALF_MD4_UNSIGNED	4
+#define DX_HASH_TEA_UNSIGNED		5
 
 #ifdef __KERNEL__
 
diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
index b65f028..50dc80a 100644
--- a/include/linux/ext3_fs_sb.h
+++ b/include/linux/ext3_fs_sb.h
@@ -57,6 +57,7 @@ struct ext3_sb_info {
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
-- 
1.5.6.1.205.ge2c7.dirty

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/