Add support for the half-MD4 HTREE hash.

Add HTREE root node tests.

4 files changed, 144 insertions, 6 deletions

diff --git a/lib/ext2fs/ChangeLog b/lib/ext2fs/ChangeLog
index b84275a5..afe6f95b 100644
--- a/lib/ext2fs/ChangeLog
+++ b/lib/ext2fs/ChangeLog
@@ -1,3 +1,10 @@
+2002-06-26  Theodore Ts'o  <tytso@mit.edu>
+
+	* dirhash.c (ext2fs_dirhash): Change function signature to support
+		a hash seed, and to return the minor hash (for 64-bit hash
+		support).   Add support for the half MD4, half MD4 with
+		seed, and half MD4 with seed and 64 bits.
+
 2002-06-15  Theodore Ts'o  <tytso@mit.edu>
 
 	* ext2_fs.h (EXT2_DIRSYNC_FL): Add new file.
diff --git a/lib/ext2fs/dirhash.c b/lib/ext2fs/dirhash.c
index 87e86d94..113d182e 100644
--- a/lib/ext2fs/dirhash.c
+++ b/lib/ext2fs/dirhash.c
@@ -16,6 +16,78 @@
 #include "ext2_fs.h"
 #include "ext2fs.h"
 
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function.  The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s)	\
+	(a += f(b, c, d) + x, a = (a << s) | (a >> (32-s)))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform.  Returns only 32 bits of result.
+ */
+static __u32 halfMD4Transform (__u32 buf[4], __u32 const in[])
+{
+	__u32	a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+	/* Round 1 */
+	ROUND(F, a, b, c, d, in[0] + K1,  3);
+	ROUND(F, d, a, b, c, in[1] + K1,  7);
+	ROUND(F, c, d, a, b, in[2] + K1, 11);
+	ROUND(F, b, c, d, a, in[3] + K1, 19);
+	ROUND(F, a, b, c, d, in[4] + K1,  3);
+	ROUND(F, d, a, b, c, in[5] + K1,  7);
+	ROUND(F, c, d, a, b, in[6] + K1, 11);
+	ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+	/* Round 2 */
+	ROUND(G, a, b, c, d, in[1] + K2,  3);
+	ROUND(G, d, a, b, c, in[3] + K2,  5);
+	ROUND(G, c, d, a, b, in[5] + K2,  9);
+	ROUND(G, b, c, d, a, in[7] + K2, 13);
+	ROUND(G, a, b, c, d, in[0] + K2,  3);
+	ROUND(G, d, a, b, c, in[2] + K2,  5);
+	ROUND(G, c, d, a, b, in[4] + K2,  9);
+	ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+	/* Round 3 */
+	ROUND(H, a, b, c, d, in[3] + K3,  3);
+	ROUND(H, d, a, b, c, in[7] + K3,  9);
+	ROUND(H, c, d, a, b, in[2] + K3, 11);
+	ROUND(H, b, c, d, a, in[6] + K3, 15);
+	ROUND(H, a, b, c, d, in[1] + K3,  3);
+	ROUND(H, d, a, b, c, in[5] + K3,  9);
+	ROUND(H, c, d, a, b, in[0] + K3, 11);
+	ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+	buf[0] += a;
+	buf[1] += b;
+	buf[2] += c;
+	buf[3] += d;
+
+	return buf[1];	/* "most hashed" word */
+	/* Alternative: return sum of all words? */
+}
+
+#undef ROUND
+#undef F
+#undef G
+#undef H
+#undef K1
+#undef K2
+#undef K3
+
+/* The old legacy hash */
 static ext2_dirhash_t dx_hack_hash (const char *name, int len)
 {
 	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
@@ -33,19 +105,69 @@ static ext2_dirhash_t dx_hack_hash (const char *name, int len)
  * Returns the hash of a filename.  If len is 0 and name is NULL, then
  * this function can be used to test whether or not a hash version is
  * supported.
+ * 
+ * The seed is an 4 longword (32 bits) "secret" which can be used to
+ * uniquify a hash.  If the seed is all zero's, then some default seed
+ * may be used.
+ * 
+ * A particular hash version specifies whether or not the seed is
+ * represented, and whether or not the returned hash is 32 bits or 64
+ * bits.  32 bit hashes will return 0 for the minor hash.
  */
 errcode_t ext2fs_dirhash(int version, const char *name, int len,
-			 ext2_dirhash_t *ret_hash)
+			 const __u32 seed[4],
+			 ext2_dirhash_t *ret_hash,
+			 ext2_dirhash_t *ret_minor_hash)
 {
 	__u32	hash;
+	__u32	minor_hash = 0;
+	char	*p;
+	int	i;
 
-	if (version == 0)
+	/* Check to see if the seed is all zero's */
+	for (i=0; i < 4; i++) {
+		if (seed[i])
+			break;
+	}
+	
+	if (version == EXT2_HASH_LEGACY)
 		hash = dx_hack_hash(name, len);
-	else {
+	else if ((version == EXT2_HASH_HALF_MD4) ||
+		 (version == EXT2_HASH_HALF_MD4_SEED) ||
+		 (version == EXT2_HASH_HALF_MD4_64)) {
+		char in[32];
+		__u32 buf[4];
+
+		if ((i == 4) || (version == EXT2_HASH_HALF_MD4)) {
+			buf[0] = 0x67452301;
+			buf[1] = 0xefcdab89;
+			buf[2] = 0x98badcfe;
+			buf[3] = 0x10325476;
+		} else
+			memcpy(buf, in, sizeof(buf));
+		while (len) {
+			if (len < 32) {
+				memcpy(in, name, len);
+				memset(in+len, 0, 32-len);
+				hash = halfMD4Transform(buf, (__u32 *) in);
+				break;
+			}
+			hash = halfMD4Transform(buf, (__u32 *) p);
+			len -= 32;
+			p += 32;
+		}
+		if (version == EXT2_HASH_HALF_MD4_64)
+			minor_hash = buf[2];
+	} else {
 		*ret_hash = 0;
 		return EXT2_ET_DIRHASH_UNSUPP;
 	}
 	*ret_hash = hash;
+	if (ret_minor_hash)
+		*ret_minor_hash = minor_hash;
 	return 0;
 		
 }
+
+
+
diff --git a/lib/ext2fs/ext2_fs.h b/lib/ext2fs/ext2_fs.h
index c47b59b4..9e6a9753 100644
--- a/lib/ext2fs/ext2_fs.h
+++ b/lib/ext2fs/ext2_fs.h
@@ -167,6 +167,13 @@ struct ext2_dx_root_info {
 	__u8 unused_flags;
 };
 
+#define EXT2_HASH_LEGACY	0
+#define EXT2_HASH_HALF_MD4	1
+#define EXT2_HASH_HALF_MD4_SEED	2
+#define EXT2_HASH_HALF_MD4_64	3 	/* SEED & 64 */
+
+#define EXT2_HASH_FLAG_INCOMPAT	0x1
+
 struct ext2_dx_entry {
 	__u32 hash;
 	__u32 block;
@@ -428,8 +435,8 @@ struct ext2_super_block {
 	__u32	s_journal_inum;		/* inode number of journal file */
 	__u32	s_journal_dev;		/* device number of journal file */
 	__u32	s_last_orphan;		/* start of list of inodes to delete */
-
-	__u32	s_reserved[197];	/* Padding to the end of the block */
+	__u32	s_hash_seed[4];		/* HTREE hash */
+	__u32	s_reserved[193];	/* Padding to the end of the block */
 };
 
 /*
diff --git a/lib/ext2fs/ext2fs.h b/lib/ext2fs/ext2fs.h
index d6e91947..2763e682 100644
--- a/lib/ext2fs/ext2fs.h
+++ b/lib/ext2fs/ext2fs.h
@@ -612,7 +612,9 @@ extern errcode_t ext2fs_write_dir_block2(ext2_filsys fs, blk_t block,
 
 /* dirhash.c */
 extern errcode_t ext2fs_dirhash(int version, const char *name, int len,
-				ext2_dirhash_t *ret_hash);
+				const __u32 seed[4],
+				ext2_dirhash_t *ret_hash,
+				ext2_dirhash_t *ret_minor_hash);
 
 
 /* dir_iterate.c */