[GitHub/mt8127/android_kernel_alcatel_ttab.git] / crypto / rmd256.c

/*
 * Cryptographic API.
 *
 * RIPEMD-256 - RACE Integrity Primitives Evaluation Message Digest.
 *
 * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC
 *
 * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option)
 * any later version.
 *
 */
#include <crypto/internal/hash.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <asm/byteorder.h>

#include "ripemd.h"

struct rmd256_ctx {
	u64 byte_count;
	u32 state[8];
	__le32 buffer[16];
};

#define K1  RMD_K1
#define K2  RMD_K2
#define K3  RMD_K3
#define K4  RMD_K4
#define KK1 RMD_K6
#define KK2 RMD_K7
#define KK3 RMD_K8
#define KK4 RMD_K1

#define F1(x, y, z) (x ^ y ^ z)		/* XOR */
#define F2(x, y, z) (z ^ (x & (y ^ z)))	/* x ? y : z */
#define F3(x, y, z) ((x | ~y) ^ z)
#define F4(x, y, z) (y ^ (z & (x ^ y)))	/* z ? x : y */

#define ROUND(a, b, c, d, f, k, x, s)  { \
	(a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
	(a) = rol32((a), (s)); \
}

static void rmd256_transform(u32 *state, const __le32 *in)
{
	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd, tmp;

	/* Initialize left lane */
	aa = state[0];
	bb = state[1];
	cc = state[2];
	dd = state[3];

	/* Initialize right lane */
	aaa = state[4];
	bbb = state[5];
	ccc = state[6];
	ddd = state[7];

	/* round 1: left lane */
	ROUND(aa, bb, cc, dd, F1, K1, in[0],  11);
	ROUND(dd, aa, bb, cc, F1, K1, in[1],  14);
	ROUND(cc, dd, aa, bb, F1, K1, in[2],  15);
	ROUND(bb, cc, dd, aa, F1, K1, in[3],  12);
	ROUND(aa, bb, cc, dd, F1, K1, in[4],   5);
	ROUND(dd, aa, bb, cc, F1, K1, in[5],   8);
	ROUND(cc, dd, aa, bb, F1, K1, in[6],   7);
	ROUND(bb, cc, dd, aa, F1, K1, in[7],   9);
	ROUND(aa, bb, cc, dd, F1, K1, in[8],  11);
	ROUND(dd, aa, bb, cc, F1, K1, in[9],  13);
	ROUND(cc, dd, aa, bb, F1, K1, in[10], 14);
	ROUND(bb, cc, dd, aa, F1, K1, in[11], 15);
	ROUND(aa, bb, cc, dd, F1, K1, in[12],  6);
	ROUND(dd, aa, bb, cc, F1, K1, in[13],  7);
	ROUND(cc, dd, aa, bb, F1, K1, in[14],  9);
	ROUND(bb, cc, dd, aa, F1, K1, in[15],  8);

	/* round 1: right lane */
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[5],   8);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[14],  9);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[7],   9);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[0],  11);
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[9],  13);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[2],  15);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[11], 15);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[4],   5);
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[13],  7);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[6],   7);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[15],  8);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[8],  11);
	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[1],  14);
	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[10], 14);
	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[3],  12);
	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[12],  6);

	/* Swap contents of "a" registers */
	tmp = aa; aa = aaa; aaa = tmp;

	/* round 2: left lane */
	ROUND(aa, bb, cc, dd, F2, K2, in[7],   7);
	ROUND(dd, aa, bb, cc, F2, K2, in[4],   6);
	ROUND(cc, dd, aa, bb, F2, K2, in[13],  8);
	ROUND(bb, cc, dd, aa, F2, K2, in[1],  13);
	ROUND(aa, bb, cc, dd, F2, K2, in[10], 11);
	ROUND(dd, aa, bb, cc, F2, K2, in[6],   9);
	ROUND(cc, dd, aa, bb, F2, K2, in[15],  7);
	ROUND(bb, cc, dd, aa, F2, K2, in[3],  15);
	ROUND(aa, bb, cc, dd, F2, K2, in[12],  7);
	ROUND(dd, aa, bb, cc, F2, K2, in[0],  12);
	ROUND(cc, dd, aa, bb, F2, K2, in[9],  15);
	ROUND(bb, cc, dd, aa, F2, K2, in[5],   9);
	ROUND(aa, bb, cc, dd, F2, K2, in[2],  11);
	ROUND(dd, aa, bb, cc, F2, K2, in[14],  7);
	ROUND(cc, dd, aa, bb, F2, K2, in[11], 13);
	ROUND(bb, cc, dd, aa, F2, K2, in[8],  12);

	/* round 2: right lane */
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[6],   9);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[11], 13);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[3],  15);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[7],   7);
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[0],  12);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[13],  8);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[5],   9);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[10], 11);
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[14],  7);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[15],  7);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[8],  12);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[12],  7);
	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[4],   6);
	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[9],  15);
	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[1],  13);
	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[2],  11);

	/* Swap contents of "b" registers */
	tmp = bb; bb = bbb; bbb = tmp;

	/* round 3: left lane */
	ROUND(aa, bb, cc, dd, F3, K3, in[3],  11);
	ROUND(dd, aa, bb, cc, F3, K3, in[10], 13);
	ROUND(cc, dd, aa, bb, F3, K3, in[14],  6);
	ROUND(bb, cc, dd, aa, F3, K3, in[4],   7);
	ROUND(aa, bb, cc, dd, F3, K3, in[9],  14);
	ROUND(dd, aa, bb, cc, F3, K3, in[15],  9);
	ROUND(cc, dd, aa, bb, F3, K3, in[8],  13);
	ROUND(bb, cc, dd, aa, F3, K3, in[1],  15);
	ROUND(aa, bb, cc, dd, F3, K3, in[2],  14);
	ROUND(dd, aa, bb, cc, F3, K3, in[7],   8);
	ROUND(cc, dd, aa, bb, F3, K3, in[0],  13);
	ROUND(bb, cc, dd, aa, F3, K3, in[6],   6);
	ROUND(aa, bb, cc, dd, F3, K3, in[13],  5);
	ROUND(dd, aa, bb, cc, F3, K3, in[11], 12);
	ROUND(cc, dd, aa, bb, F3, K3, in[5],   7);
	ROUND(bb, cc, dd, aa, F3, K3, in[12],  5);

	/* round 3: right lane */
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[15],  9);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[5],   7);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[1],  15);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[3],  11);
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[7],   8);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[14],  6);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[6],   6);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[9],  14);
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[11], 12);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[8],  13);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[12],  5);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[2],  14);
	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[10], 13);
	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[0],  13);
	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[4],   7);
	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[13],  5);

	/* Swap contents of "c" registers */
	tmp = cc; cc = ccc; ccc = tmp;

	/* round 4: left lane */
	ROUND(aa, bb, cc, dd, F4, K4, in[1],  11);
	ROUND(dd, aa, bb, cc, F4, K4, in[9],  12);
	ROUND(cc, dd, aa, bb, F4, K4, in[11], 14);
	ROUND(bb, cc, dd, aa, F4, K4, in[10], 15);
	ROUND(aa, bb, cc, dd, F4, K4, in[0],  14);
	ROUND(dd, aa, bb, cc, F4, K4, in[8],  15);
	ROUND(cc, dd, aa, bb, F4, K4, in[12],  9);
	ROUND(bb, cc, dd, aa, F4, K4, in[4],   8);
	ROUND(aa, bb, cc, dd, F4, K4, in[13],  9);
	ROUND(dd, aa, bb, cc, F4, K4, in[3],  14);
	ROUND(cc, dd, aa, bb, F4, K4, in[7],   5);
	ROUND(bb, cc, dd, aa, F4, K4, in[15],  6);
	ROUND(aa, bb, cc, dd, F4, K4, in[14],  8);
	ROUND(dd, aa, bb, cc, F4, K4, in[5],   6);
	ROUND(cc, dd, aa, bb, F4, K4, in[6],   5);
	ROUND(bb, cc, dd, aa, F4, K4, in[2],  12);

	/* round 4: right lane */
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[8],  15);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[6],   5);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[4],   8);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[1],  11);
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[3],  14);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[11], 14);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[15],  6);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[0],  14);
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[5],   6);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[12],  9);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[2],  12);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[13],  9);
	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[9],  12);
	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[7],   5);
	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[10], 15);
	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[14],  8);

	/* Swap contents of "d" registers */
	tmp = dd; dd = ddd; ddd = tmp;

	/* combine results */
	state[0] += aa;
	state[1] += bb;
	state[2] += cc;
	state[3] += dd;
	state[4] += aaa;
	state[5] += bbb;
	state[6] += ccc;
	state[7] += ddd;

	return;
}

static int rmd256_init(struct shash_desc *desc)
{
	struct rmd256_ctx *rctx = shash_desc_ctx(desc);

	rctx->byte_count = 0;

	rctx->state[0] = RMD_H0;
	rctx->state[1] = RMD_H1;
	rctx->state[2] = RMD_H2;
	rctx->state[3] = RMD_H3;
	rctx->state[4] = RMD_H5;
	rctx->state[5] = RMD_H6;
	rctx->state[6] = RMD_H7;
	rctx->state[7] = RMD_H8;

	memset(rctx->buffer, 0, sizeof(rctx->buffer));

	return 0;
}

static int rmd256_update(struct shash_desc *desc, const u8 *data,
			 unsigned int len)
{
	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
	const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f);

	rctx->byte_count += len;

	/* Enough space in buffer? If so copy and we're done */
	if (avail > len) {
		memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
		       data, len);
		goto out;
	}

	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
	       data, avail);

	rmd256_transform(rctx->state, rctx->buffer);
	data += avail;
	len -= avail;

	while (len >= sizeof(rctx->buffer)) {
		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
		rmd256_transform(rctx->state, rctx->buffer);
		data += sizeof(rctx->buffer);
		len -= sizeof(rctx->buffer);
	}

	memcpy(rctx->buffer, data, len);

out:
	return 0;
}

/* Add padding and return the message digest. */
static int rmd256_final(struct shash_desc *desc, u8 *out)
{
	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
	u32 i, index, padlen;
	__le64 bits;
	__le32 *dst = (__le32 *)out;
	static const u8 padding[64] = { 0x80, };

	bits = cpu_to_le64(rctx->byte_count << 3);

	/* Pad out to 56 mod 64 */
	index = rctx->byte_count & 0x3f;
	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
	rmd256_update(desc, padding, padlen);

	/* Append length */
	rmd256_update(desc, (const u8 *)&bits, sizeof(bits));

	/* Store state in digest */
	for (i = 0; i < 8; i++)
		dst[i] = cpu_to_le32p(&rctx->state[i]);

	/* Wipe context */
	memset(rctx, 0, sizeof(*rctx));

	return 0;
}

static struct shash_alg alg = {
	.digestsize	=	RMD256_DIGEST_SIZE,
	.init		=	rmd256_init,
	.update		=	rmd256_update,
	.final		=	rmd256_final,
	.descsize	=	sizeof(struct rmd256_ctx),
	.base		=	{
		.cra_name	 =	"rmd256",
		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	 =	RMD256_BLOCK_SIZE,
		.cra_module	 =	THIS_MODULE,
	}
};

static int __init rmd256_mod_init(void)
{
	return crypto_register_shash(&alg);
}

static void __exit rmd256_mod_fini(void)
{
	crypto_unregister_shash(&alg);
}

module_init(rmd256_mod_init);
module_exit(rmd256_mod_fini);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
MODULE_ALIAS_CRYPTO("rmd256");
Commit	Line	Data
c555c28d AKR	1	/*
	2	* Cryptographic API.
	3	*
	4	* RIPEMD-256 - RACE Integrity Primitives Evaluation Message Digest.
	5	*
	6	* Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC
	7	*
3181c225	8	* Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch>
c555c28d AKR	9	*
	10	* This program is free software; you can redistribute it and/or modify it
	11	* under the terms of the GNU General Public License as published by the Free
	12	* Software Foundation; either version 2 of the License, or (at your option)
	13	* any later version.
	14	*
	15	*/
d8a5e2e9	16	#include <crypto/internal/hash.h>
c555c28d AKR	17	#include <linux/init.h>
	18	#include <linux/module.h>
	19	#include <linux/mm.h>
c555c28d AKR	20	#include <linux/types.h>
	21	#include <asm/byteorder.h>
	22
	23	#include "ripemd.h"
	24
	25	struct rmd256_ctx {
	26	u64 byte_count;
	27	u32 state[8];
caee1688	28	__le32 buffer[16];
c555c28d AKR	29	};
	30
	31	#define K1 RMD_K1
	32	#define K2 RMD_K2
	33	#define K3 RMD_K3
	34	#define K4 RMD_K4
	35	#define KK1 RMD_K6
	36	#define KK2 RMD_K7
	37	#define KK3 RMD_K8
	38	#define KK4 RMD_K1
	39
	40	#define F1(x, y, z) (x ^ y ^ z) /* XOR */
	41	#define F2(x, y, z) (z ^ (x & (y ^ z))) /* x ? y : z */
	42	#define F3(x, y, z) ((x \| ~y) ^ z)
	43	#define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */
	44
	45	#define ROUND(a, b, c, d, f, k, x, s) { \
5cdcc22f	46	(a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
c555c28d AKR	47	(a) = rol32((a), (s)); \
	48	}
	49
caee1688	50	static void rmd256_transform(u32 state, const __le32 in)
c555c28d AKR	51	{
	52	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd, tmp;
	53
	54	/* Initialize left lane */
	55	aa = state[0];
	56	bb = state[1];
	57	cc = state[2];
	58	dd = state[3];
	59
	60	/* Initialize right lane */
	61	aaa = state[4];
	62	bbb = state[5];
	63	ccc = state[6];
	64	ddd = state[7];
	65
	66	/* round 1: left lane */
	67	ROUND(aa, bb, cc, dd, F1, K1, in[0], 11);
	68	ROUND(dd, aa, bb, cc, F1, K1, in[1], 14);
	69	ROUND(cc, dd, aa, bb, F1, K1, in[2], 15);
	70	ROUND(bb, cc, dd, aa, F1, K1, in[3], 12);
	71	ROUND(aa, bb, cc, dd, F1, K1, in[4], 5);
	72	ROUND(dd, aa, bb, cc, F1, K1, in[5], 8);
	73	ROUND(cc, dd, aa, bb, F1, K1, in[6], 7);
	74	ROUND(bb, cc, dd, aa, F1, K1, in[7], 9);
	75	ROUND(aa, bb, cc, dd, F1, K1, in[8], 11);
	76	ROUND(dd, aa, bb, cc, F1, K1, in[9], 13);
	77	ROUND(cc, dd, aa, bb, F1, K1, in[10], 14);
	78	ROUND(bb, cc, dd, aa, F1, K1, in[11], 15);
	79	ROUND(aa, bb, cc, dd, F1, K1, in[12], 6);
	80	ROUND(dd, aa, bb, cc, F1, K1, in[13], 7);
	81	ROUND(cc, dd, aa, bb, F1, K1, in[14], 9);
	82	ROUND(bb, cc, dd, aa, F1, K1, in[15], 8);
	83
	84	/* round 1: right lane */
	85	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[5], 8);
	86	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[14], 9);
	87	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[7], 9);
	88	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[0], 11);
	89	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[9], 13);
	90	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[2], 15);
	91	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[11], 15);
	92	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[4], 5);
	93	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[13], 7);
	94	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[6], 7);
	95	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[15], 8);
	96	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[8], 11);
	97	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[1], 14);
	98	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[10], 14);
	99	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[3], 12);
	100	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[12], 6);
	101
	102	/* Swap contents of "a" registers */
	103	tmp = aa; aa = aaa; aaa = tmp;
	104
	105	/* round 2: left lane */
	106	ROUND(aa, bb, cc, dd, F2, K2, in[7], 7);
	107	ROUND(dd, aa, bb, cc, F2, K2, in[4], 6);
	108	ROUND(cc, dd, aa, bb, F2, K2, in[13], 8);
	109	ROUND(bb, cc, dd, aa, F2, K2, in[1], 13);
	110	ROUND(aa, bb, cc, dd, F2, K2, in[10], 11);
	111	ROUND(dd, aa, bb, cc, F2, K2, in[6], 9);
	112	ROUND(cc, dd, aa, bb, F2, K2, in[15], 7);
	113	ROUND(bb, cc, dd, aa, F2, K2, in[3], 15);
	114	ROUND(aa, bb, cc, dd, F2, K2, in[12], 7);
115	ROUND(dd, aa, bb, cc, F2, K2, in[0], 12);
116	ROUND(cc, dd, aa, bb, F2, K2, in[9], 15);
117	ROUND(bb, cc, dd, aa, F2, K2, in[5], 9);
118	ROUND(aa, bb, cc, dd, F2, K2, in[2], 11);
119	ROUND(dd, aa, bb, cc, F2, K2, in[14], 7);
120	ROUND(cc, dd, aa, bb, F2, K2, in[11], 13);
121	ROUND(bb, cc, dd, aa, F2, K2, in[8], 12);
122
123	/* round 2: right lane */
124	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[6], 9);
125	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[11], 13);
126	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[3], 15);
127	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[7], 7);
128	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[0], 12);
129	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[13], 8);
130	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[5], 9);
131	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[10], 11);
132	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[14], 7);
133	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[15], 7);
134	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[8], 12);
135	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[12], 7);
136	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[4], 6);
137	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[9], 15);
138	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[1], 13);
139	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[2], 11);
140
141	/* Swap contents of "b" registers */
142	tmp = bb; bb = bbb; bbb = tmp;
143
144	/* round 3: left lane */
145	ROUND(aa, bb, cc, dd, F3, K3, in[3], 11);
146	ROUND(dd, aa, bb, cc, F3, K3, in[10], 13);
147	ROUND(cc, dd, aa, bb, F3, K3, in[14], 6);
148	ROUND(bb, cc, dd, aa, F3, K3, in[4], 7);
149	ROUND(aa, bb, cc, dd, F3, K3, in[9], 14);
150	ROUND(dd, aa, bb, cc, F3, K3, in[15], 9);
151	ROUND(cc, dd, aa, bb, F3, K3, in[8], 13);
152	ROUND(bb, cc, dd, aa, F3, K3, in[1], 15);
153	ROUND(aa, bb, cc, dd, F3, K3, in[2], 14);
154	ROUND(dd, aa, bb, cc, F3, K3, in[7], 8);
155	ROUND(cc, dd, aa, bb, F3, K3, in[0], 13);
156	ROUND(bb, cc, dd, aa, F3, K3, in[6], 6);
157	ROUND(aa, bb, cc, dd, F3, K3, in[13], 5);
158	ROUND(dd, aa, bb, cc, F3, K3, in[11], 12);
159	ROUND(cc, dd, aa, bb, F3, K3, in[5], 7);
160	ROUND(bb, cc, dd, aa, F3, K3, in[12], 5);
161
162	/* round 3: right lane */
163	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[15], 9);
164	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[5], 7);
165	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[1], 15);
166	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[3], 11);
167	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[7], 8);
168	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[14], 6);
169	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[6], 6);
170	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[9], 14);
171	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[11], 12);
172	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[8], 13);
173	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[12], 5);
174	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[2], 14);
175	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[10], 13);
176	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[0], 13);
177	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[4], 7);
178	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[13], 5);
179
180	/* Swap contents of "c" registers */
181	tmp = cc; cc = ccc; ccc = tmp;
182
183	/* round 4: left lane */
184	ROUND(aa, bb, cc, dd, F4, K4, in[1], 11);
185	ROUND(dd, aa, bb, cc, F4, K4, in[9], 12);
186	ROUND(cc, dd, aa, bb, F4, K4, in[11], 14);
187	ROUND(bb, cc, dd, aa, F4, K4, in[10], 15);
188	ROUND(aa, bb, cc, dd, F4, K4, in[0], 14);
189	ROUND(dd, aa, bb, cc, F4, K4, in[8], 15);
190	ROUND(cc, dd, aa, bb, F4, K4, in[12], 9);
191	ROUND(bb, cc, dd, aa, F4, K4, in[4], 8);
192	ROUND(aa, bb, cc, dd, F4, K4, in[13], 9);
193	ROUND(dd, aa, bb, cc, F4, K4, in[3], 14);
194	ROUND(cc, dd, aa, bb, F4, K4, in[7], 5);
195	ROUND(bb, cc, dd, aa, F4, K4, in[15], 6);
196	ROUND(aa, bb, cc, dd, F4, K4, in[14], 8);
197	ROUND(dd, aa, bb, cc, F4, K4, in[5], 6);
198	ROUND(cc, dd, aa, bb, F4, K4, in[6], 5);
199	ROUND(bb, cc, dd, aa, F4, K4, in[2], 12);
200
201	/* round 4: right lane */
202	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[8], 15);
203	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[6], 5);
204	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[4], 8);
205	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[1], 11);
206	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[3], 14);
207	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[11], 14);
208	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[15], 6);
209	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[0], 14);
210	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[5], 6);
211	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[12], 9);
212	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[2], 12);
213	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[13], 9);
214	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[9], 12);
215	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[7], 5);
216	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[10], 15);
217	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[14], 8);
218
219	/* Swap contents of "d" registers */
220	tmp = dd; dd = ddd; ddd = tmp;
221
222	/* combine results */
223	state[0] += aa;
224	state[1] += bb;
225	state[2] += cc;
226	state[3] += dd;
227	state[4] += aaa;
228	state[5] += bbb;
229	state[6] += ccc;
230	state[7] += ddd;
231
232	return;
233	}
234
d8a5e2e9	235	static int rmd256_init(struct shash_desc *desc)
c555c28d	236	{
d8a5e2e9	237	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
c555c28d AKR	238
	239	rctx->byte_count = 0;
	240
	241	rctx->state[0] = RMD_H0;
	242	rctx->state[1] = RMD_H1;
	243	rctx->state[2] = RMD_H2;
	244	rctx->state[3] = RMD_H3;
	245	rctx->state[4] = RMD_H5;
	246	rctx->state[5] = RMD_H6;
	247	rctx->state[6] = RMD_H7;
	248	rctx->state[7] = RMD_H8;
	249
	250	memset(rctx->buffer, 0, sizeof(rctx->buffer));
d8a5e2e9 HX	251
d8a5e2e9 HX	252	return 0;
c555c28d AKR	253	}
c555c28d AKR	254
d8a5e2e9 HX	255	static int rmd256_update(struct shash_desc desc, const u8 data,
d8a5e2e9 HX	256	unsigned int len)
c555c28d	257	{
d8a5e2e9	258	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
c555c28d AKR	259	const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f);
	260
	261	rctx->byte_count += len;
	262
	263	/* Enough space in buffer? If so copy and we're done */
	264	if (avail > len) {
	265	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
	266	data, len);
d8a5e2e9	267	goto out;
c555c28d AKR	268	}
	269
	270	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
	271	data, avail);
	272
2952ff1a	273	rmd256_transform(rctx->state, rctx->buffer);
c555c28d AKR	274	data += avail;
	275	len -= avail;
	276
	277	while (len >= sizeof(rctx->buffer)) {
	278	memcpy(rctx->buffer, data, sizeof(rctx->buffer));
2952ff1a	279	rmd256_transform(rctx->state, rctx->buffer);
c555c28d AKR	280	data += sizeof(rctx->buffer);
	281	len -= sizeof(rctx->buffer);
	282	}
	283
	284	memcpy(rctx->buffer, data, len);
d8a5e2e9 HX	285
	286	out:
	287	return 0;
c555c28d AKR	288	}
	289
	290	/* Add padding and return the message digest. */
d8a5e2e9	291	static int rmd256_final(struct shash_desc desc, u8 out)
c555c28d	292	{
d8a5e2e9	293	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
2952ff1a	294	u32 i, index, padlen;
caee1688 HH	295	__le64 bits;
caee1688 HH	296	__le32 dst = (__le32 )out;
c555c28d	297	static const u8 padding[64] = { 0x80, };
2952ff1a AKR	298
2952ff1a AKR	299	bits = cpu_to_le64(rctx->byte_count << 3);
c555c28d AKR	300
	301	/* Pad out to 56 mod 64 */
	302	index = rctx->byte_count & 0x3f;
	303	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
d8a5e2e9	304	rmd256_update(desc, padding, padlen);
c555c28d AKR	305
c555c28d AKR	306	/* Append length */
d8a5e2e9	307	rmd256_update(desc, (const u8 *)&bits, sizeof(bits));
c555c28d AKR	308
c555c28d AKR	309	/* Store state in digest */
2952ff1a	310	for (i = 0; i < 8; i++)
5cdcc22f	311	dst[i] = cpu_to_le32p(&rctx->state[i]);
c555c28d AKR	312
	313	/* Wipe context */
	314	memset(rctx, 0, sizeof(*rctx));
d8a5e2e9 HX	315
d8a5e2e9 HX	316	return 0;
c555c28d AKR	317	}
c555c28d AKR	318
d8a5e2e9 HX	319	static struct shash_alg alg = {
	320	.digestsize = RMD256_DIGEST_SIZE,
	321	.init = rmd256_init,
	322	.update = rmd256_update,
	323	.final = rmd256_final,
	324	.descsize = sizeof(struct rmd256_ctx),
	325	.base = {
	326	.cra_name = "rmd256",
	327	.cra_flags = CRYPTO_ALG_TYPE_SHASH,
	328	.cra_blocksize = RMD256_BLOCK_SIZE,
	329	.cra_module = THIS_MODULE,
	330	}
c555c28d AKR	331	};
	332
	333	static int __init rmd256_mod_init(void)
	334	{
d8a5e2e9	335	return crypto_register_shash(&alg);
c555c28d AKR	336	}
	337
	338	static void __exit rmd256_mod_fini(void)
	339	{
d8a5e2e9	340	crypto_unregister_shash(&alg);
c555c28d AKR	341	}
	342
	343	module_init(rmd256_mod_init);
	344	module_exit(rmd256_mod_fini);
	345
	346	MODULE_LICENSE("GPL");
3181c225	347	MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
c555c28d	348	MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
e635e0d5	349	MODULE_ALIAS_CRYPTO("rmd256");