[CRYPTO] ripemd: Add support for RIPEMD-256 and RIPEMD-320

This patch adds support for the extended RIPEMD hash
algorithms RIPEMD-256 and RIPEMD-320.

Signed-off-by: Adrian-Ken Rueegsegger <rueegsegger@swiss-it.ch>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

3 files changed, 777 insertions, 0 deletions

diff --git a/crypto/Makefile b/crypto/Makefile
index 1efb55635664..807656b64e02 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -29,6 +29,8 @@ obj-$(CONFIG_CRYPTO_MD4) += md4.o
 obj-$(CONFIG_CRYPTO_MD5) += md5.o
 obj-$(CONFIG_CRYPTO_RMD128) += rmd128.o
 obj-$(CONFIG_CRYPTO_RMD160) += rmd160.o
+obj-$(CONFIG_CRYPTO_RMD256) += rmd256.o
+obj-$(CONFIG_CRYPTO_RMD320) += rmd320.o
 obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o
 obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o
 obj-$(CONFIG_CRYPTO_SHA512) += sha512_generic.o
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
new file mode 100644
index 000000000000..060ee81cb8ad
--- /dev/null
+++ b/crypto/rmd256.c
@@ -0,0 +1,363 @@
+/*
+ * 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];
+	u32 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)) + (x) + (k); \
+	(a) = rol32((a), (s)); \
+}
+
+static void rmd256_transform(u32 *state, u32 const *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 inline void le32_to_cpu_array(u32 *buf, unsigned int words)
+{
+	while (words--) {
+		le32_to_cpus(buf);
+		buf++;
+	}
+}
+
+static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
+{
+	while (words--) {
+		cpu_to_le32s(buf);
+		buf++;
+	}
+}
+
+static inline void rmd256_transform_helper(struct rmd256_ctx *ctx)
+{
+	le32_to_cpu_array(ctx->buffer, sizeof(ctx->buffer) / sizeof(u32));
+	rmd256_transform(ctx->state, ctx->buffer);
+}
+
+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_helper(rctx);
+	data += avail;
+	len -= avail;
+
+	while (len >= sizeof(rctx->buffer)) {
+		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
+		rmd256_transform_helper(rctx);
+		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 index, padlen;
+	u64 bits;
+	static const u8 padding[64] = { 0x80, };
+	bits = 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 */
+	memcpy(out, rctx->state, sizeof(rctx->state));
+
+	/* 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");
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
new file mode 100644
index 000000000000..b39c0543a8fa
--- /dev/null
+++ b/crypto/rmd320.c
@@ -0,0 +1,412 @@
+/*
+ * Cryptographic API.
+ *
+ * RIPEMD-320 - 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 rmd320_ctx {
+	u64 byte_count;
+	u32 state[10];
+	u32 buffer[16];
+};
+
+#define K1  RMD_K1
+#define K2  RMD_K2
+#define K3  RMD_K3
+#define K4  RMD_K4
+#define K5  RMD_K5
+#define KK1 RMD_K6
+#define KK2 RMD_K7
+#define KK3 RMD_K8
+#define KK4 RMD_K9
+#define KK5 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 F5(x, y, z) (x ^ (y | ~z))
+
+#define ROUND(a, b, c, d, e, f, k, x, s)  { \
+	(a) += f((b), (c), (d)) + (x) + (k); \
+	(a) = rol32((a), (s)) + (e); \
+	(c) = rol32((c), 10); \
+}
+
+static void rmd320_transform(u32 *state, u32 const *in)
+{
+	u32 aa, bb, cc, dd, ee, aaa, bbb, ccc, ddd, eee, tmp;
+
+	/* Initialize left lane */
+	aa = state[0];
+	bb = state[1];
+	cc = state[2];
+	dd = state[3];
+	ee = state[4];
+
+	/* Initialize right lane */
+	aaa = state[5];
+	bbb = state[6];
+	ccc = state[7];
+	ddd = state[8];
+	eee = state[9];
+
+	/* round 1: left lane */
+	ROUND(aa, bb, cc, dd, ee, F1, K1, in[0],  11);
+	ROUND(ee, aa, bb, cc, dd, F1, K1, in[1],  14);
+	ROUND(dd, ee, aa, bb, cc, F1, K1, in[2],  15);
+	ROUND(cc, dd, ee, aa, bb, F1, K1, in[3],  12);
+	ROUND(bb, cc, dd, ee, aa, F1, K1, in[4],   5);
+	ROUND(aa, bb, cc, dd, ee, F1, K1, in[5],   8);
+	ROUND(ee, aa, bb, cc, dd, F1, K1, in[6],   7);
+	ROUND(dd, ee, aa, bb, cc, F1, K1, in[7],   9);
+	ROUND(cc, dd, ee, aa, bb, F1, K1, in[8],  11);
+	ROUND(bb, cc, dd, ee, aa, F1, K1, in[9],  13);
+	ROUND(aa, bb, cc, dd, ee, F1, K1, in[10], 14);
+	ROUND(ee, aa, bb, cc, dd, F1, K1, in[11], 15);
+	ROUND(dd, ee, aa, bb, cc, F1, K1, in[12],  6);
+	ROUND(cc, dd, ee, aa, bb, F1, K1, in[13],  7);
+	ROUND(bb, cc, dd, ee, aa, F1, K1, in[14],  9);
+	ROUND(aa, bb, cc, dd, ee, F1, K1, in[15],  8);
+
+	/* round 1: right lane */
+	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[5],   8);
+	ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[14],  9);
+	ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[7],   9);
+	ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[0],  11);
+	ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[9],  13);
+	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[2],  15);
+	ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[11], 15);
+	ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[4],   5);
+	ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[13],  7);
+	ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[6],   7);
+	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[15],  8);
+	ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[8],  11);
+	ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[1],  14);
+	ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[10], 14);
+	ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[3],  12);
+	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[12],  6);
+
+	/* Swap contents of "a" registers */
+	tmp = aa; aa = aaa; aaa = tmp;
+
+	/* round 2: left lane" */
+	ROUND(ee, aa, bb, cc, dd, F2, K2, in[7],   7);
+	ROUND(dd, ee, aa, bb, cc, F2, K2, in[4],   6);
+	ROUND(cc, dd, ee, aa, bb, F2, K2, in[13],  8);
+	ROUND(bb, cc, dd, ee, aa, F2, K2, in[1],  13);
+	ROUND(aa, bb, cc, dd, ee, F2, K2, in[10], 11);
+	ROUND(ee, aa, bb, cc, dd, F2, K2, in[6],   9);
+	ROUND(dd, ee, aa, bb, cc, F2, K2, in[15],  7);
+	ROUND(cc, dd, ee, aa, bb, F2, K2, in[3],  15);
+	ROUND(bb, cc, dd, ee, aa, F2, K2, in[12],  7);
+	ROUND(aa, bb, cc, dd, ee, F2, K2, in[0],  12);
+	ROUND(ee, aa, bb, cc, dd, F2, K2, in[9],  15);
+	ROUND(dd, ee, aa, bb, cc, F2, K2, in[5],   9);
+	ROUND(cc, dd, ee, aa, bb, F2, K2, in[2],  11);
+	ROUND(bb, cc, dd, ee, aa, F2, K2, in[14],  7);
+	ROUND(aa, bb, cc, dd, ee, F2, K2, in[11], 13);
+	ROUND(ee, aa, bb, cc, dd, F2, K2, in[8],  12);
+
+	/* round 2: right lane */
+	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[6],   9);
+	ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[11], 13);
+	ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[3],  15);
+	ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[7],   7);
+	ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[0],  12);
+	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[13],  8);
+	ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[5],   9);
+	ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[10], 11);
+	ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[14],  7);
+	ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[15],  7);
+	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[8],  12);
+	ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[12],  7);
+	ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[4],   6);
+	ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[9],  15);
+	ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[1],  13);
+	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[2],  11);
+
+	/* Swap contents of "b" registers */
+	tmp = bb; bb = bbb; bbb = tmp;
+
+	/* round 3: left lane" */
+	ROUND(dd, ee, aa, bb, cc, F3, K3, in[3],  11);
+	ROUND(cc, dd, ee, aa, bb, F3, K3, in[10], 13);
+	ROUND(bb, cc, dd, ee, aa, F3, K3, in[14],  6);
+	ROUND(aa, bb, cc, dd, ee, F3, K3, in[4],   7);
+	ROUND(ee, aa, bb, cc, dd, F3, K3, in[9],  14);
+	ROUND(dd, ee, aa, bb, cc, F3, K3, in[15],  9);
+	ROUND(cc, dd, ee, aa, bb, F3, K3, in[8],  13);
+	ROUND(bb, cc, dd, ee, aa, F3, K3, in[1],  15);
+	ROUND(aa, bb, cc, dd, ee, F3, K3, in[2],  14);
+	ROUND(ee, aa, bb, cc, dd, F3, K3, in[7],   8);
+	ROUND(dd, ee, aa, bb, cc, F3, K3, in[0],  13);
+	ROUND(cc, dd, ee, aa, bb, F3, K3, in[6],   6);
+	ROUND(bb, cc, dd, ee, aa, F3, K3, in[13],  5);
+	ROUND(aa, bb, cc, dd, ee, F3, K3, in[11], 12);
+	ROUND(ee, aa, bb, cc, dd, F3, K3, in[5],   7);
+	ROUND(dd, ee, aa, bb, cc, F3, K3, in[12],  5);
+
+	/* round 3: right lane */
+	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[15],  9);
+	ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[5],   7);
+	ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[1],  15);
+	ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[3],  11);
+	ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[7],   8);
+	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[14],  6);
+	ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[6],   6);
+	ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[9],  14);
+	ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[11], 12);
+	ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[8],  13);
+	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[12],  5);
+	ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[2],  14);
+	ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[10], 13);
+	ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[0],  13);
+	ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[4],   7);
+	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[13],  5);
+
+	/* Swap contents of "c" registers */
+	tmp = cc; cc = ccc; ccc = tmp;
+
+	/* round 4: left lane" */
+	ROUND(cc, dd, ee, aa, bb, F4, K4, in[1],  11);
+	ROUND(bb, cc, dd, ee, aa, F4, K4, in[9],  12);
+	ROUND(aa, bb, cc, dd, ee, F4, K4, in[11], 14);
+	ROUND(ee, aa, bb, cc, dd, F4, K4, in[10], 15);
+	ROUND(dd, ee, aa, bb, cc, F4, K4, in[0],  14);
+	ROUND(cc, dd, ee, aa, bb, F4, K4, in[8],  15);
+	ROUND(bb, cc, dd, ee, aa, F4, K4, in[12],  9);
+	ROUND(aa, bb, cc, dd, ee, F4, K4, in[4],   8);
+	ROUND(ee, aa, bb, cc, dd, F4, K4, in[13],  9);
+	ROUND(dd, ee, aa, bb, cc, F4, K4, in[3],  14);
+	ROUND(cc, dd, ee, aa, bb, F4, K4, in[7],   5);
+	ROUND(bb, cc, dd, ee, aa, F4, K4, in[15],  6);
+	ROUND(aa, bb, cc, dd, ee, F4, K4, in[14],  8);
+	ROUND(ee, aa, bb, cc, dd, F4, K4, in[5],   6);
+	ROUND(dd, ee, aa, bb, cc, F4, K4, in[6],   5);
+	ROUND(cc, dd, ee, aa, bb, F4, K4, in[2],  12);
+
+	/* round 4: right lane */
+	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[8],  15);
+	ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[6],   5);
+	ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[4],   8);
+	ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[1],  11);
+	ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[3],  14);
+	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[11], 14);
+	ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[15],  6);
+	ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[0],  14);
+	ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[5],   6);
+	ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[12],  9);
+	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[2],  12);
+	ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[13],  9);
+	ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[9],  12);
+	ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[7],   5);
+	ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[10], 15);
+	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[14],  8);
+
+	/* Swap contents of "d" registers */
+	tmp = dd; dd = ddd; ddd = tmp;
+
+	/* round 5: left lane" */
+	ROUND(bb, cc, dd, ee, aa, F5, K5, in[4],   9);
+	ROUND(aa, bb, cc, dd, ee, F5, K5, in[0],  15);
+	ROUND(ee, aa, bb, cc, dd, F5, K5, in[5],   5);
+	ROUND(dd, ee, aa, bb, cc, F5, K5, in[9],  11);
+	ROUND(cc, dd, ee, aa, bb, F5, K5, in[7],   6);
+	ROUND(bb, cc, dd, ee, aa, F5, K5, in[12],  8);
+	ROUND(aa, bb, cc, dd, ee, F5, K5, in[2],  13);
+	ROUND(ee, aa, bb, cc, dd, F5, K5, in[10], 12);
+	ROUND(dd, ee, aa, bb, cc, F5, K5, in[14],  5);
+	ROUND(cc, dd, ee, aa, bb, F5, K5, in[1],  12);
+	ROUND(bb, cc, dd, ee, aa, F5, K5, in[3],  13);
+	ROUND(aa, bb, cc, dd, ee, F5, K5, in[8],  14);
+	ROUND(ee, aa, bb, cc, dd, F5, K5, in[11], 11);
+	ROUND(dd, ee, aa, bb, cc, F5, K5, in[6],   8);
+	ROUND(cc, dd, ee, aa, bb, F5, K5, in[15],  5);
+	ROUND(bb, cc, dd, ee, aa, F5, K5, in[13],  6);
+
+	/* round 5: right lane */
+	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[12],  8);
+	ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[15],  5);
+	ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[10], 12);
+	ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[4],   9);
+	ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[1],  12);
+	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[5],   5);
+	ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[8],  14);
+	ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[7],   6);
+	ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[6],   8);
+	ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[2],  13);
+	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[13],  6);
+	ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[14],  5);
+	ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[0],  15);
+	ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[3],  13);
+	ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[9],  11);
+	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[11], 11);
+
+	/* Swap contents of "e" registers */
+	tmp = ee; ee = eee; eee = tmp;
+
+	/* combine results */
+	state[0] += aa;
+	state[1] += bb;
+	state[2] += cc;
+	state[3] += dd;
+	state[4] += ee;
+	state[5] += aaa;
+	state[6] += bbb;
+	state[7] += ccc;
+	state[8] += ddd;
+	state[9] += eee;
+
+	return;
+}
+
+static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
+{
+	while (words--) {
+		le32_to_cpus(buf);
+		buf++;
+	}
+}
+
+static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
+{
+	while (words--) {
+		cpu_to_le32s(buf);
+		buf++;
+	}
+}
+
+static inline void rmd320_transform_helper(struct rmd320_ctx *ctx)
+{
+	le32_to_cpu_array(ctx->buffer, sizeof(ctx->buffer) / sizeof(u32));
+	rmd320_transform(ctx->state, ctx->buffer);
+}
+
+static void rmd320_init(struct crypto_tfm *tfm)
+{
+	struct rmd320_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_H4;
+	rctx->state[5] = RMD_H5;
+	rctx->state[6] = RMD_H6;
+	rctx->state[7] = RMD_H7;
+	rctx->state[8] = RMD_H8;
+	rctx->state[9] = RMD_H9;
+
+	memset(rctx->buffer, 0, sizeof(rctx->buffer));
+}
+
+static void rmd320_update(struct crypto_tfm *tfm, const u8 *data,
+			  unsigned int len)
+{
+	struct rmd320_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);
+
+	rmd320_transform_helper(rctx);
+	data += avail;
+	len -= avail;
+
+	while (len >= sizeof(rctx->buffer)) {
+		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
+		rmd320_transform_helper(rctx);
+		data += sizeof(rctx->buffer);
+		len -= sizeof(rctx->buffer);
+	}
+
+	memcpy(rctx->buffer, data, len);
+}
+
+/* Add padding and return the message digest. */
+static void rmd320_final(struct crypto_tfm *tfm, u8 *out)
+{
+	struct rmd320_ctx *rctx = crypto_tfm_ctx(tfm);
+	u32 index, padlen;
+	u64 bits;
+	static const u8 padding[64] = { 0x80, };
+	bits = rctx->byte_count << 3;
+
+	/* Pad out to 56 mod 64 */
+	index = rctx->byte_count & 0x3f;
+	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
+	rmd320_update(tfm, padding, padlen);
+
+	/* Append length */
+	rmd320_update(tfm, (const u8 *)&bits, sizeof(bits));
+
+	/* Store state in digest */
+	memcpy(out, rctx->state, sizeof(rctx->state));
+
+	/* Wipe context */
+	memset(rctx, 0, sizeof(*rctx));
+}
+
+static struct crypto_alg alg = {
+	.cra_name	 =	"rmd320",
+	.cra_driver_name =	"rmd320",
+	.cra_flags	 =	CRYPTO_ALG_TYPE_DIGEST,
+	.cra_blocksize	 =	RMD320_BLOCK_SIZE,
+	.cra_ctxsize	 =	sizeof(struct rmd320_ctx),
+	.cra_module	 =	THIS_MODULE,
+	.cra_list	 =	LIST_HEAD_INIT(alg.cra_list),
+	.cra_u		 =	{ .digest = {
+	.dia_digestsize	 =	RMD320_DIGEST_SIZE,
+	.dia_init	 =	rmd320_init,
+	.dia_update	 =	rmd320_update,
+	.dia_final	 =	rmd320_final } }
+};
+
+static int __init rmd320_mod_init(void)
+{
+	return crypto_register_alg(&alg);
+}
+
+static void __exit rmd320_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+module_init(rmd320_mod_init);
+module_exit(rmd320_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RIPEMD-320 Message Digest");
+
+MODULE_ALIAS("rmd320");