[mirror_ubuntu-bionic-kernel.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 <rueegsegger (at) swiss-it.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 <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/crypto.h>
#include <linux/cryptohash.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 void rmd256_init(struct crypto_tfm *tfm)
{
	struct rmd256_ctx *rctx = crypto_tfm_ctx(tfm);

	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));
}

static void rmd256_update(struct crypto_tfm *tfm, const u8 *data,
			  unsigned int len)
{
	struct rmd256_ctx *rctx = crypto_tfm_ctx(tfm);
	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);
		return;
	}

	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);
}

/* Add padding and return the message digest. */
static void rmd256_final(struct crypto_tfm *tfm, u8 *out)
{
	struct rmd256_ctx *rctx = crypto_tfm_ctx(tfm);
	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(tfm, padding, padlen);

	/* Append length */
	rmd256_update(tfm, (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));
}

static struct crypto_alg alg = {
	.cra_name	 =	"rmd256",
	.cra_driver_name =	"rmd256",
	.cra_flags	 =	CRYPTO_ALG_TYPE_DIGEST,
	.cra_blocksize	 =	RMD256_BLOCK_SIZE,
	.cra_ctxsize	 =	sizeof(struct rmd256_ctx),
	.cra_module	 =	THIS_MODULE,
	.cra_list	 =	LIST_HEAD_INIT(alg.cra_list),
	.cra_u		 =	{ .digest = {
	.dia_digestsize	 =	RMD256_DIGEST_SIZE,
	.dia_init	 =	rmd256_init,
	.dia_update	 =	rmd256_update,
	.dia_final	 =	rmd256_final } }
};

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

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

module_init(rmd256_mod_init);
module_exit(rmd256_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("RIPEMD-256 Message Digest");

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