[linux-block.git] / fs / ext4 / hash.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/hash.c
 *
 * Copyright (C) 2002 by Theodore Ts'o
 */

#include <linux/fs.h>
#include <linux/unicode.h>
#include <linux/compiler.h>
#include <linux/bitops.h>
#include "ext4.h"

#define DELTA 0x9E3779B9

static void TEA_transform(__u32 buf[4], __u32 const in[])
{
	__u32	sum = 0;
	__u32	b0 = buf[0], b1 = buf[1];
	__u32	a = in[0], b = in[1], c = in[2], d = in[3];
	int	n = 16;

	do {
		sum += DELTA;
		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
	} while (--n);

	buf[0] += b0;
	buf[1] += b1;
}

/* 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 = rol32(a, s))
#define K1 0
#define K2 013240474631UL
#define K3 015666365641UL

/*
 * Basic cut-down MD4 transform.  Returns only 32 bits of result.
 */
static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
{
	__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 */
}
#undef ROUND
#undef K1
#undef K2
#undef K3
#undef F
#undef G
#undef H

/* The old legacy hash */
static __u32 dx_hack_hash_unsigned(const char *name, int len)
{
	__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--) {
		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));

		if (hash & 0x80000000)
			hash -= 0x7fffffff;
		hash1 = hash0;
		hash0 = hash;
	}
	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++) {
		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_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;

	val = pad;
	if (len > num*4)
		len = num * 4;
	for (i = 0; i < len; i++) {
		val = ((int) ucp[i]) + (val << 8);
		if ((i % 4) == 3) {
			*buf++ = val;
			val = pad;
			num--;
		}
	}
	if (--num >= 0)
		*buf++ = val;
	while (--num >= 0)
		*buf++ = pad;
}

/*
 * 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.
 */
static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
			    struct dx_hash_info *hinfo)
{
	__u32	hash;
	__u32	minor_hash = 0;
	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;
	buf[1] = 0xefcdab89;
	buf[2] = 0x98badcfe;
	buf[3] = 0x10325476;

	/* Check to see if the seed is all zero's */
	if (hinfo->seed) {
		for (i = 0; i < 4; i++) {
			if (hinfo->seed[i]) {
				memcpy(buf, hinfo->seed, sizeof(buf));
				break;
			}
		}
	}

	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_signed(name, len);
		break;
	case DX_HASH_HALF_MD4_UNSIGNED:
		str2hashbuf = str2hashbuf_unsigned;
		fallthrough;
	case DX_HASH_HALF_MD4:
		p = name;
		while (len > 0) {
			(*str2hashbuf)(p, len, in, 8);
			half_md4_transform(buf, in);
			len -= 32;
			p += 32;
		}
		minor_hash = buf[2];
		hash = buf[1];
		break;
	case DX_HASH_TEA_UNSIGNED:
		str2hashbuf = str2hashbuf_unsigned;
		fallthrough;
	case DX_HASH_TEA:
		p = name;
		while (len > 0) {
			(*str2hashbuf)(p, len, in, 4);
			TEA_transform(buf, in);
			len -= 16;
			p += 16;
		}
		hash = buf[0];
		minor_hash = buf[1];
		break;
	case DX_HASH_SIPHASH:
	{
		struct qstr qname = QSTR_INIT(name, len);
		__u64	combined_hash;

		if (fscrypt_has_encryption_key(dir)) {
			combined_hash = fscrypt_fname_siphash(dir, &qname);
		} else {
			ext4_warning_inode(dir, "Siphash requires key");
			return -1;
		}

		hash = (__u32)(combined_hash >> 32);
		minor_hash = (__u32)combined_hash;
		break;
	}
	default:
		hinfo->hash = 0;
		hinfo->minor_hash = 0;
		ext4_warning(dir->i_sb,
			     "invalid/unsupported hash tree version %u",
			     hinfo->hash_version);
		return -EINVAL;
	}
	hash = hash & ~1;
	if (hash == (EXT4_HTREE_EOF_32BIT << 1))
		hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
	hinfo->hash = hash;
	hinfo->minor_hash = minor_hash;
	return 0;
}

int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
		   struct dx_hash_info *hinfo)
{
#if IS_ENABLED(CONFIG_UNICODE)
	const struct unicode_map *um = dir->i_sb->s_encoding;
	int r, dlen;
	unsigned char *buff;
	struct qstr qstr = {.name = name, .len = len };

	if (len && IS_CASEFOLDED(dir) && um &&
	   (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) {
		buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
		if (!buff)
			return -ENOMEM;

		dlen = utf8_casefold(um, &qstr, buff, PATH_MAX);
		if (dlen < 0) {
			kfree(buff);
			goto opaque_seq;
		}

		r = __ext4fs_dirhash(dir, buff, dlen, hinfo);

		kfree(buff);
		return r;
	}
opaque_seq:
#endif
	return __ext4fs_dirhash(dir, name, len, hinfo);
}
Commit	Line	Data
f5166768	1	// SPDX-License-Identifier: GPL-2.0
ac27a0ec	2	/*
617ba13b	3	* linux/fs/ext4/hash.c
ac27a0ec DK	4	*
ac27a0ec DK	5	* Copyright (C) 2002 by Theodore Ts'o
ac27a0ec DK	6	*/
	7
	8	#include <linux/fs.h>
b886ee3e	9	#include <linux/unicode.h>
1c83a9aa JD	10	#include <linux/compiler.h>
1c83a9aa JD	11	#include <linux/bitops.h>
3dcf5451	12	#include "ext4.h"
ac27a0ec DK	13
	14	#define DELTA 0x9E3779B9
	15
	16	static void TEA_transform(__u32 buf[4], __u32 const in[])
	17	{
	18	__u32 sum = 0;
	19	__u32 b0 = buf[0], b1 = buf[1];
	20	__u32 a = in[0], b = in[1], c = in[2], d = in[3];
	21	int n = 16;
	22
	23	do {
	24	sum += DELTA;
	25	b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
	26	b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
af5bc92d	27	} while (--n);
ac27a0ec DK	28
	29	buf[0] += b0;
	30	buf[1] += b1;
	31	}
	32
1c83a9aa JD	33	/* F, G and H are basic MD4 functions: selection, majority, parity */
	34	#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
	35	#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
	36	#define H(x, y, z) ((x) ^ (y) ^ (z))
	37
	38	/*
	39	* The generic round function. The application is so specific that
	40	* we don't bother protecting all the arguments with parens, as is generally
	41	* good macro practice, in favor of extra legibility.
	42	* Rotation is separate from addition to prevent recomputation
	43	*/
	44	#define ROUND(f, a, b, c, d, x, s) \
	45	(a += f(b, c, d) + x, a = rol32(a, s))
	46	#define K1 0
	47	#define K2 013240474631UL
	48	#define K3 015666365641UL
	49
	50	/*
	51	* Basic cut-down MD4 transform. Returns only 32 bits of result.
	52	*/
	53	static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
	54	{
	55	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
	56
	57	/* Round 1 */
	58	ROUND(F, a, b, c, d, in[0] + K1, 3);
	59	ROUND(F, d, a, b, c, in[1] + K1, 7);
	60	ROUND(F, c, d, a, b, in[2] + K1, 11);
	61	ROUND(F, b, c, d, a, in[3] + K1, 19);
	62	ROUND(F, a, b, c, d, in[4] + K1, 3);
	63	ROUND(F, d, a, b, c, in[5] + K1, 7);
	64	ROUND(F, c, d, a, b, in[6] + K1, 11);
	65	ROUND(F, b, c, d, a, in[7] + K1, 19);
	66
	67	/* Round 2 */
	68	ROUND(G, a, b, c, d, in[1] + K2, 3);
	69	ROUND(G, d, a, b, c, in[3] + K2, 5);
	70	ROUND(G, c, d, a, b, in[5] + K2, 9);
	71	ROUND(G, b, c, d, a, in[7] + K2, 13);
	72	ROUND(G, a, b, c, d, in[0] + K2, 3);
	73	ROUND(G, d, a, b, c, in[2] + K2, 5);
	74	ROUND(G, c, d, a, b, in[4] + K2, 9);
	75	ROUND(G, b, c, d, a, in[6] + K2, 13);
	76
	77	/* Round 3 */
	78	ROUND(H, a, b, c, d, in[3] + K3, 3);
	79	ROUND(H, d, a, b, c, in[7] + K3, 9);
	80	ROUND(H, c, d, a, b, in[2] + K3, 11);
	81	ROUND(H, b, c, d, a, in[6] + K3, 15);
	82	ROUND(H, a, b, c, d, in[1] + K3, 3);
	83	ROUND(H, d, a, b, c, in[5] + K3, 9);
	84	ROUND(H, c, d, a, b, in[0] + K3, 11);
	85	ROUND(H, b, c, d, a, in[4] + K3, 15);
	86
	87	buf[0] += a;
	88	buf[1] += b;
	89	buf[2] += c;
	90	buf[3] += d;
	91
	92	return buf[1]; /* "most hashed" word */
	93	}
	94	#undef ROUND
	95	#undef K1
	96	#undef K2
97	#undef K3
98	#undef F
99	#undef G
100	#undef H
ac27a0ec DK	101
ac27a0ec DK	102	/* The old legacy hash */
f99b2589	103	static __u32 dx_hack_hash_unsigned(const char *name, int len)
ac27a0ec	104	{
f99b2589 TT	105	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
	106	const unsigned char ucp = (const unsigned char ) name;
	107
	108	while (len--) {
	109	hash = hash1 + (hash0 ^ (((int) ucp++) 7152373));
	110
	111	if (hash & 0x80000000)
	112	hash -= 0x7fffffff;
	113	hash1 = hash0;
	114	hash0 = hash;
	115	}
	116	return hash0 << 1;
	117	}
	118
	119	static __u32 dx_hack_hash_signed(const char *name, int len)
	120	{
	121	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
	122	const signed char scp = (const signed char ) name;
	123
ac27a0ec	124	while (len--) {
f99b2589	125	hash = hash1 + (hash0 ^ (((int) scp++) 7152373));
ac27a0ec	126
f99b2589 TT	127	if (hash & 0x80000000)
f99b2589 TT	128	hash -= 0x7fffffff;
ac27a0ec DK	129	hash1 = hash0;
	130	hash0 = hash;
	131	}
f99b2589 TT	132	return hash0 << 1;
	133	}
	134
	135	static void str2hashbuf_signed(const char msg, int len, __u32 buf, int num)
	136	{
	137	__u32 pad, val;
	138	int i;
	139	const signed char scp = (const signed char ) msg;
	140
	141	pad = (__u32)len \| ((__u32)len << 8);
	142	pad \|= pad << 16;
	143
	144	val = pad;
	145	if (len > num*4)
	146	len = num * 4;
	147	for (i = 0; i < len; i++) {
f99b2589 TT	148	val = ((int) scp[i]) + (val << 8);
	149	if ((i % 4) == 3) {
	150	*buf++ = val;
	151	val = pad;
	152	num--;
	153	}
	154	}
	155	if (--num >= 0)
	156	*buf++ = val;
	157	while (--num >= 0)
	158	*buf++ = pad;
ac27a0ec DK	159	}
ac27a0ec DK	160
f99b2589	161	static void str2hashbuf_unsigned(const char msg, int len, __u32 buf, int num)
ac27a0ec DK	162	{
	163	__u32 pad, val;
	164	int i;
f99b2589	165	const unsigned char ucp = (const unsigned char ) msg;
ac27a0ec DK	166
	167	pad = (__u32)len \| ((__u32)len << 8);
	168	pad \|= pad << 16;
	169
	170	val = pad;
	171	if (len > num*4)
	172	len = num * 4;
af5bc92d	173	for (i = 0; i < len; i++) {
f99b2589	174	val = ((int) ucp[i]) + (val << 8);
ac27a0ec DK	175	if ((i % 4) == 3) {
	176	*buf++ = val;
	177	val = pad;
	178	num--;
	179	}
	180	}
	181	if (--num >= 0)
	182	*buf++ = val;
	183	while (--num >= 0)
	184	*buf++ = pad;
	185	}
	186
	187	/*
	188	* Returns the hash of a filename. If len is 0 and name is NULL, then
	189	* this function can be used to test whether or not a hash version is
	190	* supported.
	191	*
	192	* The seed is an 4 longword (32 bits) "secret" which can be used to
	193	* uniquify a hash. If the seed is all zero's, then some default seed
	194	* may be used.
	195	*
	196	* A particular hash version specifies whether or not the seed is
	197	* represented, and whether or not the returned hash is 32 bits or 64
	198	* bits. 32 bit hashes will return 0 for the minor hash.
	199	*/
471fbbea	200	static int __ext4fs_dirhash(const struct inode dir, const char name, int len,
b886ee3e	201	struct dx_hash_info *hinfo)
ac27a0ec DK	202	{
	203	__u32 hash;
	204	__u32 minor_hash = 0;
	205	const char *p;
	206	int i;
	207	__u32 in[8], buf[4];
f99b2589 TT	208	void (str2hashbuf)(const char , int, __u32 *, int) =
f99b2589 TT	209	str2hashbuf_signed;
ac27a0ec DK	210
	211	/* Initialize the default seed for the hash checksum functions */
	212	buf[0] = 0x67452301;
	213	buf[1] = 0xefcdab89;
	214	buf[2] = 0x98badcfe;
	215	buf[3] = 0x10325476;
	216
	217	/* Check to see if the seed is all zero's */
	218	if (hinfo->seed) {
af5bc92d	219	for (i = 0; i < 4; i++) {
0e79537d CD	220	if (hinfo->seed[i]) {
0e79537d CD	221	memcpy(buf, hinfo->seed, sizeof(buf));
ac27a0ec	222	break;
0e79537d	223	}
ac27a0ec	224	}
ac27a0ec DK	225	}
	226
	227	switch (hinfo->hash_version) {
f99b2589 TT	228	case DX_HASH_LEGACY_UNSIGNED:
	229	hash = dx_hack_hash_unsigned(name, len);
	230	break;
ac27a0ec	231	case DX_HASH_LEGACY:
f99b2589	232	hash = dx_hack_hash_signed(name, len);
ac27a0ec	233	break;
f99b2589 TT	234	case DX_HASH_HALF_MD4_UNSIGNED:
f99b2589 TT	235	str2hashbuf = str2hashbuf_unsigned;
70d7ced2	236	fallthrough;
ac27a0ec DK	237	case DX_HASH_HALF_MD4:
	238	p = name;
	239	while (len > 0) {
f99b2589	240	(*str2hashbuf)(p, len, in, 8);
ac27a0ec DK	241	half_md4_transform(buf, in);
	242	len -= 32;
	243	p += 32;
	244	}
	245	minor_hash = buf[2];
	246	hash = buf[1];
	247	break;
f99b2589 TT	248	case DX_HASH_TEA_UNSIGNED:
f99b2589 TT	249	str2hashbuf = str2hashbuf_unsigned;
70d7ced2	250	fallthrough;
ac27a0ec DK	251	case DX_HASH_TEA:
	252	p = name;
	253	while (len > 0) {
f99b2589	254	(*str2hashbuf)(p, len, in, 4);
ac27a0ec DK	255	TEA_transform(buf, in);
	256	len -= 16;
	257	p += 16;
	258	}
	259	hash = buf[0];
	260	minor_hash = buf[1];
	261	break;
471fbbea DR	262	case DX_HASH_SIPHASH:
	263	{
	264	struct qstr qname = QSTR_INIT(name, len);
	265	__u64 combined_hash;
	266
	267	if (fscrypt_has_encryption_key(dir)) {
	268	combined_hash = fscrypt_fname_siphash(dir, &qname);
	269	} else {
	270	ext4_warning_inode(dir, "Siphash requires key");
	271	return -1;
	272	}
	273
	274	hash = (__u32)(combined_hash >> 32);
	275	minor_hash = (__u32)combined_hash;
	276	break;
	277	}
ac27a0ec DK	278	default:
ac27a0ec DK	279	hinfo->hash = 0;
4b3cb1d1 TT	280	hinfo->minor_hash = 0;
	281	ext4_warning(dir->i_sb,
	282	"invalid/unsupported hash tree version %u",
	283	hinfo->hash_version);
	284	return -EINVAL;
ac27a0ec DK	285	}
ac27a0ec DK	286	hash = hash & ~1;
d1f5273e FY	287	if (hash == (EXT4_HTREE_EOF_32BIT << 1))
d1f5273e FY	288	hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
ac27a0ec DK	289	hinfo->hash = hash;
	290	hinfo->minor_hash = minor_hash;
	291	return 0;
	292	}
b886ee3e GKB	293
	294	int ext4fs_dirhash(const struct inode dir, const char name, int len,
	295	struct dx_hash_info *hinfo)
	296	{
5298d4bf	297	#if IS_ENABLED(CONFIG_UNICODE)
f8f4acb6	298	const struct unicode_map *um = dir->i_sb->s_encoding;
b886ee3e GKB	299	int r, dlen;
	300	unsigned char *buff;
	301	struct qstr qstr = {.name = name, .len = len };
	302
471fbbea DR	303	if (len && IS_CASEFOLDED(dir) && um &&
471fbbea DR	304	(!IS_ENCRYPTED(dir) \|\| fscrypt_has_encryption_key(dir))) {
b886ee3e GKB	305	buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
	306	if (!buff)
	307	return -ENOMEM;
	308
	309	dlen = utf8_casefold(um, &qstr, buff, PATH_MAX);
	310	if (dlen < 0) {
	311	kfree(buff);
	312	goto opaque_seq;
	313	}
	314
471fbbea	315	r = __ext4fs_dirhash(dir, buff, dlen, hinfo);
b886ee3e GKB	316
	317	kfree(buff);
	318	return r;
	319	}
	320	opaque_seq:
	321	#endif
471fbbea	322	return __ext4fs_dirhash(dir, name, len, hinfo);
b886ee3e	323	}