ext4: Add support for non-native signed/unsigned htree hash algorithms

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@mit.edu>

5 files changed, 90 insertions, 10 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b0537c8..8370ffd 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -891,6 +891,9 @@ static inline __le16 ext4_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/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
index b21f167..ad7ea09b 100644
--- a/fs/ext4/ext4_sb.h
+++ b/fs/ext4/ext4_sb.h
@@ -57,6 +57,7 @@ struct ext4_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;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 556ca8e..ac8f168 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -35,23 +35,71 @@ 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_unsigned(const char *name, int len)
 {
-	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const unsigned char *ucp = (const unsigned char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
 	while (len--) {
-		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
 
-		if (hash & 0x80000000) hash -= 0x7fffffff;
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
 		hash1 = hash0;
 		hash0 = hash;
 	}
-	return (hash0 << 1);
+	return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const signed char *scp = (const signed char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) scp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
 }
 
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
 {
 	__u32	pad, val;
 	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
 
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
@@ -62,7 +110,7 @@ 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);
+		val = ((int) ucp[i]) + (val << 8);
 		if ((i % 4) == 3) {
 			*buf++ = val;
 			val = pad;
@@ -95,6 +143,8 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	const char	*p;
 	int		i;
 	__u32		in[8], buf[4];
+	void		(*str2hashbuf)(const char *, int, __u32 *, int) =
+				str2hashbuf_signed;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -113,13 +163,18 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	}
 
 	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY_UNSIGNED:
+		hash = dx_hack_hash_unsigned(name, len);
+		break;
 	case DX_HASH_LEGACY:
-		hash = dx_hack_hash(name, len);
+		hash = dx_hack_hash_signed(name, len);
 		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 8);
+			(*str2hashbuf)(p, len, in, 8);
 			half_md4_transform(buf, in);
 			len -= 32;
 			p += 32;
@@ -127,10 +182,12 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		minor_hash = buf[2];
 		hash = buf[1];
 		break;
+	case DX_HASH_TEA_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 4);
+			(*str2hashbuf)(p, len, in, 4);
 			TEA_transform(buf, in);
 			len -= 16;
 			p += 16;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 9fd2a5e..315858d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -372,6 +372,8 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	if (d_name)
 		ext4fs_dirhash(d_name->name, d_name->len, hinfo);
@@ -641,6 +643,9 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
 		hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT4_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);
@@ -1408,6 +1413,8 @@ 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 += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	ext4fs_dirhash(name, namelen, &hinfo);
 	frame = frames;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 04158ad..08fc86a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2118,6 +2118,18 @@ static int ext4_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) {
+#ifdef __CHAR_UNSIGNED__
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+		sbi->s_hash_unsigned = 3;
+#else
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+		sb->s_dirt = 1;
+	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
 		printk(KERN_ERR