Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (54 commits)
  crypto: gf128mul - remove leftover "(EXPERIMENTAL)" in Kconfig
  crypto: serpent-sse2 - remove unneeded LRW/XTS #ifdefs
  crypto: serpent-sse2 - select LRW and XTS
  crypto: twofish-x86_64-3way - remove unneeded LRW/XTS #ifdefs
  crypto: twofish-x86_64-3way - select LRW and XTS
  crypto: xts - remove dependency on EXPERIMENTAL
  crypto: lrw - remove dependency on EXPERIMENTAL
  crypto: picoxcell - fix boolean and / or confusion
  crypto: caam - remove DECO access initialization code
  crypto: caam - fix polarity of "propagate error" logic
  crypto: caam - more desc.h cleanups
  crypto: caam - desc.h - convert spaces to tabs
  crypto: talitos - convert talitos_error to struct device
  crypto: talitos - remove NO_IRQ references
  crypto: talitos - fix bad kfree
  crypto: convert drivers/crypto/* to use module_platform_driver()
  char: hw_random: convert drivers/char/hw_random/* to use module_platform_driver()
  crypto: serpent-sse2 - should select CRYPTO_CRYPTD
  crypto: serpent - rename serpent.c to serpent_generic.c
  crypto: serpent - cleanup checkpatch errors and warnings
  ...

14 files changed, 4194 insertions, 639 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index ae9c3ceb286..e6cfe1a2513 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -105,7 +105,7 @@ config CRYPTO_USER
 	depends on NET
 	select CRYPTO_MANAGER
 	help
-	  Userapace configuration for cryptographic instantiations such as
+	  Userspace configuration for cryptographic instantiations such as
 	  cbc(aes).
 
 config CRYPTO_MANAGER_DISABLE_TESTS
@@ -117,7 +117,7 @@ config CRYPTO_MANAGER_DISABLE_TESTS
 	  algorithm registration.
 
 config CRYPTO_GF128MUL
-	tristate "GF(2^128) multiplication functions (EXPERIMENTAL)"
+	tristate "GF(2^128) multiplication functions"
 	help
 	  Efficient table driven implementation of multiplications in the
 	  field GF(2^128).  This is needed by some cypher modes. This
@@ -241,8 +241,7 @@ config CRYPTO_ECB
 	  the input block by block.
 
 config CRYPTO_LRW
-	tristate "LRW support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	tristate "LRW support"
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_GF128MUL
@@ -262,8 +261,7 @@ config CRYPTO_PCBC
 	  This block cipher algorithm is required for RxRPC.
 
 config CRYPTO_XTS
-	tristate "XTS support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	tristate "XTS support"
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_GF128MUL
@@ -764,6 +762,46 @@ config CRYPTO_SERPENT
 	  See also:
 	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
 
+config CRYPTO_SERPENT_SSE2_X86_64
+	tristate "Serpent cipher algorithm (x86_64/SSE2)"
+	depends on X86 && 64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_SERPENT
+	select CRYPTO_LRW
+	select CRYPTO_XTS
+	help
+	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
+
+	  Keys are allowed to be from 0 to 256 bits in length, in steps
+	  of 8 bits.
+
+	  This module provides Serpent cipher algorithm that processes eigth
+	  blocks parallel using SSE2 instruction set.
+
+	  See also:
+	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
+
+config CRYPTO_SERPENT_SSE2_586
+	tristate "Serpent cipher algorithm (i586/SSE2)"
+	depends on X86 && !64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_SERPENT
+	select CRYPTO_LRW
+	select CRYPTO_XTS
+	help
+	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
+
+	  Keys are allowed to be from 0 to 256 bits in length, in steps
+	  of 8 bits.
+
+	  This module provides Serpent cipher algorithm that processes four
+	  blocks parallel using SSE2 instruction set.
+
+	  See also:
+	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
+
 config CRYPTO_TEA
 	tristate "TEA, XTEA and XETA cipher algorithms"
 	select CRYPTO_ALGAPI
@@ -840,6 +878,8 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
+	select CRYPTO_LRW
+	select CRYPTO_XTS
 	help
 	  Twofish cipher algorithm (x86_64, 3-way parallel).
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 9e6eee2c05d..f638063f4ea 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -65,7 +65,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH) += blowfish_generic.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_COMMON) += blowfish_common.o
 obj-$(CONFIG_CRYPTO_TWOFISH) += twofish_generic.o
 obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o
-obj-$(CONFIG_CRYPTO_SERPENT) += serpent.o
+obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia.o
 obj-$(CONFIG_CRYPTO_CAST5) += cast5.o
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 54dd4e33b5d..9d4a9fe913f 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -518,6 +518,35 @@ err:
 }
 EXPORT_SYMBOL_GPL(crypto_register_instance);
 
+int crypto_unregister_instance(struct crypto_alg *alg)
+{
+	int err;
+	struct crypto_instance *inst = (void *)alg;
+	struct crypto_template *tmpl = inst->tmpl;
+	LIST_HEAD(users);
+
+	if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE))
+		return -EINVAL;
+
+	BUG_ON(atomic_read(&alg->cra_refcnt) != 1);
+
+	down_write(&crypto_alg_sem);
+
+	hlist_del_init(&inst->list);
+	err = crypto_remove_alg(alg, &users);
+
+	up_write(&crypto_alg_sem);
+
+	if (err)
+		return err;
+
+	tmpl->free(inst);
+	crypto_remove_final(&users);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_instance);
+
 int crypto_init_spawn(struct crypto_spawn *spawn, struct crypto_alg *alg,
 		      struct crypto_instance *inst, u32 mask)
 {
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index ffa0245e2ab..6ddd99e6114 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -414,10 +414,18 @@ static int fips_cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
 static int fips_cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
 {
 	u8 rdata[DEFAULT_BLK_SZ];
+	u8 *key = seed + DEFAULT_BLK_SZ;
 	int rc;
 
 	struct prng_context *prng = crypto_rng_ctx(tfm);
 
+	if (slen < DEFAULT_PRNG_KSZ + DEFAULT_BLK_SZ)
+		return -EINVAL;
+
+	/* fips strictly requires seed != key */
+	if (!memcmp(seed, key, DEFAULT_PRNG_KSZ))
+		return -EINVAL;
+
 	rc = cprng_reset(tfm, seed, slen);
 
 	if (!rc)
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 0605a2bbba7..3ba6ef50886 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -298,7 +298,7 @@ static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (atomic_read(&alg->cra_refcnt) != 1)
 		return -EBUSY;
 
-	return crypto_unregister_alg(alg);
+	return crypto_unregister_instance(alg);
 }
 
 static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
diff --git a/crypto/lrw.c b/crypto/lrw.c
index 358f80be2bf..ba42acc4deb 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -3,7 +3,7 @@
  *
  * Copyright (c) 2006 Rik Snel <rsnel@cube.dyndns.org>
  *
- * Based om ecb.c
+ * Based on ecb.c
  * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -16,6 +16,7 @@
  * http://www.mail-archive.com/stds-p1619@listserv.ieee.org/msg00173.html
  *
  * The test vectors are included in the testing module tcrypt.[ch] */
+
 #include <crypto/algapi.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -26,21 +27,11 @@
 
 #include <crypto/b128ops.h>
 #include <crypto/gf128mul.h>
+#include <crypto/lrw.h>
 
 struct priv {
 	struct crypto_cipher *child;
-	/* optimizes multiplying a random (non incrementing, as at the
-	 * start of a new sector) value with key2, we could also have
-	 * used 4k optimization tables or no optimization at all. In the
-	 * latter case we would have to store key2 here */
-	struct gf128mul_64k *table;
-	/* stores:
-	 *  key2*{ 0,0,...0,0,0,0,1 }, key2*{ 0,0,...0,0,0,1,1 },
-	 *  key2*{ 0,0,...0,0,1,1,1 }, key2*{ 0,0,...0,1,1,1,1 }
-	 *  key2*{ 0,0,...1,1,1,1,1 }, etc
-	 * needed for optimized multiplication of incrementing values
-	 * with key2 */
-	be128 mulinc[128];
+	struct lrw_table_ctx table;
 };
 
 static inline void setbit128_bbe(void *b, int bit)
@@ -54,28 +45,16 @@ static inline void setbit128_bbe(void *b, int bit)
 			), b);
 }
 
-static int setkey(struct crypto_tfm *parent, const u8 *key,
-		  unsigned int keylen)
+int lrw_init_table(struct lrw_table_ctx *ctx, const u8 *tweak)
 {
-	struct priv *ctx = crypto_tfm_ctx(parent);
-	struct crypto_cipher *child = ctx->child;
-	int err, i;
 	be128 tmp = { 0 };
-	int bsize = crypto_cipher_blocksize(child);
-
-	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_cipher_set_flags(child, crypto_tfm_get_flags(parent) &
-				       CRYPTO_TFM_REQ_MASK);
-	if ((err = crypto_cipher_setkey(child, key, keylen - bsize)))
-		return err;
-	crypto_tfm_set_flags(parent, crypto_cipher_get_flags(child) &
-				     CRYPTO_TFM_RES_MASK);
+	int i;
 
 	if (ctx->table)
 		gf128mul_free_64k(ctx->table);
 
 	/* initialize multiplication table for Key2 */
-	ctx->table = gf128mul_init_64k_bbe((be128 *)(key + keylen - bsize));
+	ctx->table = gf128mul_init_64k_bbe((be128 *)tweak);
 	if (!ctx->table)
 		return -ENOMEM;
 
@@ -88,6 +67,34 @@ static int setkey(struct crypto_tfm *parent, const u8 *key,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(lrw_init_table);
+
+void lrw_free_table(struct lrw_table_ctx *ctx)
+{
+	if (ctx->table)
+		gf128mul_free_64k(ctx->table);
+}
+EXPORT_SYMBOL_GPL(lrw_free_table);
+
+static int setkey(struct crypto_tfm *parent, const u8 *key,
+		  unsigned int keylen)
+{
+	struct priv *ctx = crypto_tfm_ctx(parent);
+	struct crypto_cipher *child = ctx->child;
+	int err, bsize = LRW_BLOCK_SIZE;
+	const u8 *tweak = key + keylen - bsize;
+
+	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(child, crypto_tfm_get_flags(parent) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_cipher_setkey(child, key, keylen - bsize);
+	if (err)
+		return err;
+	crypto_tfm_set_flags(parent, crypto_cipher_get_flags(child) &
+				     CRYPTO_TFM_RES_MASK);
+
+	return lrw_init_table(&ctx->table, tweak);
+}
 
 struct sinfo {
 	be128 t;
@@ -134,7 +141,7 @@ static int crypt(struct blkcipher_desc *d,
 {
 	int err;
 	unsigned int avail;
-	const int bs = crypto_cipher_blocksize(ctx->child);
+	const int bs = LRW_BLOCK_SIZE;
 	struct sinfo s = {
 		.tfm = crypto_cipher_tfm(ctx->child),
 		.fn = fn
@@ -155,7 +162,7 @@ static int crypt(struct blkcipher_desc *d,
 	s.t = *iv;
 
 	/* T <- I*Key2 */
-	gf128mul_64k_bbe(&s.t, ctx->table);
+	gf128mul_64k_bbe(&s.t, ctx->table.table);
 
 	goto first;
 
@@ -163,7 +170,8 @@ static int crypt(struct blkcipher_desc *d,
 		do {
 			/* T <- I*Key2, using the optimization
 			 * discussed in the specification */
-			be128_xor(&s.t, &s.t, &ctx->mulinc[get_index128(iv)]);
+			be128_xor(&s.t, &s.t,
+				  &ctx->table.mulinc[get_index128(iv)]);
 			inc(iv);
 
 first:
@@ -206,6 +214,85 @@ static int decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		     crypto_cipher_alg(ctx->child)->cia_decrypt);
 }
 
+int lrw_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
+	      struct scatterlist *ssrc, unsigned int nbytes,
+	      struct lrw_crypt_req *req)
+{
+	const unsigned int bsize = LRW_BLOCK_SIZE;
+	const unsigned int max_blks = req->tbuflen / bsize;
+	struct lrw_table_ctx *ctx = req->table_ctx;
+	struct blkcipher_walk walk;
+	unsigned int nblocks;
+	be128 *iv, *src, *dst, *t;
+	be128 *t_buf = req->tbuf;
+	int err, i;
+
+	BUG_ON(max_blks < 1);
+
+	blkcipher_walk_init(&walk, sdst, ssrc, nbytes);
+
+	err = blkcipher_walk_virt(desc, &walk);
+	nbytes = walk.nbytes;
+	if (!nbytes)
+		return err;
+
+	nblocks = min(walk.nbytes / bsize, max_blks);
+	src = (be128 *)walk.src.virt.addr;
+	dst = (be128 *)walk.dst.virt.addr;
+
+	/* calculate first value of T */
+	iv = (be128 *)walk.iv;
+	t_buf[0] = *iv;
+
+	/* T <- I*Key2 */
+	gf128mul_64k_bbe(&t_buf[0], ctx->table);
+
+	i = 0;
+	goto first;
+
+	for (;;) {
+		do {
+			for (i = 0; i < nblocks; i++) {
+				/* T <- I*Key2, using the optimization
+				 * discussed in the specification */
+				be128_xor(&t_buf[i], t,
+						&ctx->mulinc[get_index128(iv)]);
+				inc(iv);
+first:
+				t = &t_buf[i];
+
+				/* PP <- T xor P */
+				be128_xor(dst + i, t, src + i);
+			}
+
+			/* CC <- E(Key2,PP) */
+			req->crypt_fn(req->crypt_ctx, (u8 *)dst,
+				      nblocks * bsize);
+
+			/* C <- T xor CC */
+			for (i = 0; i < nblocks; i++)
+				be128_xor(dst + i, dst + i, &t_buf[i]);
+
+			src += nblocks;
+			dst += nblocks;
+			nbytes -= nblocks * bsize;
+			nblocks = min(nbytes / bsize, max_blks);
+		} while (nblocks > 0);
+
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = walk.nbytes;
+		if (!nbytes)
+			break;
+
+		nblocks = min(nbytes / bsize, max_blks);
+		src = (be128 *)walk.src.virt.addr;
+		dst = (be128 *)walk.dst.virt.addr;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(lrw_crypt);
+
 static int init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_cipher *cipher;
@@ -218,8 +305,9 @@ static int init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	if (crypto_cipher_blocksize(cipher) != 16) {
+	if (crypto_cipher_blocksize(cipher) != LRW_BLOCK_SIZE) {
 		*flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
+		crypto_free_cipher(cipher);
 		return -EINVAL;
 	}
 
@@ -230,8 +318,8 @@ static int init_tfm(struct crypto_tfm *tfm)
 static void exit_tfm(struct crypto_tfm *tfm)
 {
 	struct priv *ctx = crypto_tfm_ctx(tfm);
-	if (ctx->table)
-		gf128mul_free_64k(ctx->table);
+
+	lrw_free_table(&ctx->table);
 	crypto_free_cipher(ctx->child);
 }
 
diff --git a/crypto/serpent.c b/crypto/serpent.c
deleted file mode 100644
index b651a55fa56..00000000000
--- a/crypto/serpent.c
+++ /dev/null
@@ -1,587 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Serpent Cipher Algorithm.
- *
- * Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no>
- *               2003 Herbert Valerio Riedel <hvr@gnu.org>
- *
- * Added tnepres support: Ruben Jesus Garcia Hernandez <ruben@ugr.es>, 18.10.2004
- *               Based on code by hvr
- *
- * 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/errno.h>
-#include <asm/byteorder.h>
-#include <linux/crypto.h>
-#include <linux/types.h>
-
-/* Key is padded to the maximum of 256 bits before round key generation.
- * Any key length <= 256 bits (32 bytes) is allowed by the algorithm.
- */
-
-#define SERPENT_MIN_KEY_SIZE		  0
-#define SERPENT_MAX_KEY_SIZE		 32
-#define SERPENT_EXPKEY_WORDS		132
-#define SERPENT_BLOCK_SIZE		 16
-
-#define PHI 0x9e3779b9UL
-
-#define keyiter(a,b,c,d,i,j) \
-        b ^= d; b ^= c; b ^= a; b ^= PHI ^ i; b = rol32(b,11); k[j] = b;
-
-#define loadkeys(x0,x1,x2,x3,i) \
-	x0=k[i]; x1=k[i+1]; x2=k[i+2]; x3=k[i+3];
-
-#define storekeys(x0,x1,x2,x3,i) \
-	k[i]=x0; k[i+1]=x1; k[i+2]=x2; k[i+3]=x3;
-
-#define K(x0,x1,x2,x3,i)				\
-	x3 ^= k[4*(i)+3];        x2 ^= k[4*(i)+2];	\
-	x1 ^= k[4*(i)+1];        x0 ^= k[4*(i)+0];
-
-#define LK(x0,x1,x2,x3,x4,i)				\
-					x0=rol32(x0,13);\
-	x2=rol32(x2,3);	x1 ^= x0;	x4  = x0 << 3;	\
-	x3 ^= x2;	x1 ^= x2;			\
-	x1=rol32(x1,1);	x3 ^= x4;			\
-	x3=rol32(x3,7);	x4  = x1;			\
-	x0 ^= x1;	x4 <<= 7;	x2 ^= x3;	\
-	x0 ^= x3;	x2 ^= x4;	x3 ^= k[4*i+3];	\
-	x1 ^= k[4*i+1];	x0=rol32(x0,5);	x2=rol32(x2,22);\
-	x0 ^= k[4*i+0];	x2 ^= k[4*i+2];
-
-#define KL(x0,x1,x2,x3,x4,i)				\
-	x0 ^= k[4*i+0];	x1 ^= k[4*i+1];	x2 ^= k[4*i+2];	\
-	x3 ^= k[4*i+3];	x0=ror32(x0,5);	x2=ror32(x2,22);\
-	x4 =  x1;	x2 ^= x3;	x0 ^= x3;	\
-	x4 <<= 7;	x0 ^= x1;	x1=ror32(x1,1);	\
-	x2 ^= x4;	x3=ror32(x3,7);	x4 = x0 << 3;	\
-	x1 ^= x0;	x3 ^= x4;	x0=ror32(x0,13);\
-	x1 ^= x2;	x3 ^= x2;	x2=ror32(x2,3);
-
-#define S0(x0,x1,x2,x3,x4)				\
-					x4  = x3;	\
-	x3 |= x0;	x0 ^= x4;	x4 ^= x2;	\
-	x4 =~ x4;	x3 ^= x1;	x1 &= x0;	\
-	x1 ^= x4;	x2 ^= x0;	x0 ^= x3;	\
-	x4 |= x0;	x0 ^= x2;	x2 &= x1;	\
-	x3 ^= x2;	x1 =~ x1;	x2 ^= x4;	\
-	x1 ^= x2;
-
-#define S1(x0,x1,x2,x3,x4)				\
-					x4  = x1;	\
-	x1 ^= x0;	x0 ^= x3;	x3 =~ x3;	\
-	x4 &= x1;	x0 |= x1;	x3 ^= x2;	\
-	x0 ^= x3;	x1 ^= x3;	x3 ^= x4;	\
-	x1 |= x4;	x4 ^= x2;	x2 &= x0;	\
-	x2 ^= x1;	x1 |= x0;	x0 =~ x0;	\
-	x0 ^= x2;	x4 ^= x1;
-
-#define S2(x0,x1,x2,x3,x4)				\
-					x3 =~ x3;	\
-	x1 ^= x0;	x4  = x0;	x0 &= x2;	\
-	x0 ^= x3;	x3 |= x4;	x2 ^= x1;	\
-	x3 ^= x1;	x1 &= x0;	x0 ^= x2;	\
-	x2 &= x3;	x3 |= x1;	x0 =~ x0;	\
-	x3 ^= x0;	x4 ^= x0;	x0 ^= x2;	\
-	x1 |= x2;
-
-#define S3(x0,x1,x2,x3,x4)				\
-					x4  = x1;	\
-	x1 ^= x3;	x3 |= x0;	x4 &= x0;	\
-	x0 ^= x2;	x2 ^= x1;	x1 &= x3;	\
-	x2 ^= x3;	x0 |= x4;	x4 ^= x3;	\
-	x1 ^= x0;	x0 &= x3;	x3 &= x4;	\
-	x3 ^= x2;	x4 |= x1;	x2 &= x1;	\
-	x4 ^= x3;	x0 ^= x3;	x3 ^= x2;
-
-#define S4(x0,x1,x2,x3,x4)				\
-					x4  = x3;	\
-	x3 &= x0;	x0 ^= x4;			\
-	x3 ^= x2;	x2 |= x4;	x0 ^= x1;	\
-	x4 ^= x3;	x2 |= x0;			\
-	x2 ^= x1;	x1 &= x0;			\
-	x1 ^= x4;	x4 &= x2;	x2 ^= x3;	\
-	x4 ^= x0;	x3 |= x1;	x1 =~ x1;	\
-	x3 ^= x0;
-
-#define S5(x0,x1,x2,x3,x4)				\
-	x4  = x1;	x1 |= x0;			\
-	x2 ^= x1;	x3 =~ x3;	x4 ^= x0;	\
-	x0 ^= x2;	x1 &= x4;	x4 |= x3;	\
-	x4 ^= x0;	x0 &= x3;	x1 ^= x3;	\
-	x3 ^= x2;	x0 ^= x1;	x2 &= x4;	\
-	x1 ^= x2;	x2 &= x0;			\
-	x3 ^= x2;
-
-#define S6(x0,x1,x2,x3,x4)				\
-					x4  = x1;	\
-	x3 ^= x0;	x1 ^= x2;	x2 ^= x0;	\
-	x0 &= x3;	x1 |= x3;	x4 =~ x4;	\
-	x0 ^= x1;	x1 ^= x2;			\
-	x3 ^= x4;	x4 ^= x0;	x2 &= x0;	\
-	x4 ^= x1;	x2 ^= x3;	x3 &= x1;	\
-	x3 ^= x0;	x1 ^= x2;
-
-#define S7(x0,x1,x2,x3,x4)				\
-					x1 =~ x1;	\
-	x4  = x1;	x0 =~ x0;	x1 &= x2;	\
-	x1 ^= x3;	x3 |= x4;	x4 ^= x2;	\
-	x2 ^= x3;	x3 ^= x0;	x0 |= x1;	\
-	x2 &= x0;	x0 ^= x4;	x4 ^= x3;	\
-	x3 &= x0;	x4 ^= x1;			\
-	x2 ^= x4;	x3 ^= x1;	x4 |= x0;	\
-	x4 ^= x1;
-
-#define SI0(x0,x1,x2,x3,x4)				\
-			x4  = x3;	x1 ^= x0;	\
-	x3 |= x1;	x4 ^= x1;	x0 =~ x0;	\
-	x2 ^= x3;	x3 ^= x0;	x0 &= x1;	\
-	x0 ^= x2;	x2 &= x3;	x3 ^= x4;	\
-	x2 ^= x3;	x1 ^= x3;	x3 &= x0;	\
-	x1 ^= x0;	x0 ^= x2;	x4 ^= x3;
-
-#define SI1(x0,x1,x2,x3,x4)				\
-	x1 ^= x3;	x4  = x0;			\
-	x0 ^= x2;	x2 =~ x2;	x4 |= x1;	\
-	x4 ^= x3;	x3 &= x1;	x1 ^= x2;	\
-	x2 &= x4;	x4 ^= x1;	x1 |= x3;	\
-	x3 ^= x0;	x2 ^= x0;	x0 |= x4;	\
-	x2 ^= x4;	x1 ^= x0;			\
-	x4 ^= x1;
-
-#define SI2(x0,x1,x2,x3,x4)				\
-	x2 ^= x1;	x4  = x3;	x3 =~ x3;	\
-	x3 |= x2;	x2 ^= x4;	x4 ^= x0;	\
-	x3 ^= x1;	x1 |= x2;	x2 ^= x0;	\
-	x1 ^= x4;	x4 |= x3;	x2 ^= x3;	\
-	x4 ^= x2;	x2 &= x1;			\
-	x2 ^= x3;	x3 ^= x4;	x4 ^= x0;
-
-#define SI3(x0,x1,x2,x3,x4)				\
-					x2 ^= x1;	\
-	x4  = x1;	x1 &= x2;			\
-	x1 ^= x0;	x0 |= x4;	x4 ^= x3;	\
-	x0 ^= x3;	x3 |= x1;	x1 ^= x2;	\
-	x1 ^= x3;	x0 ^= x2;	x2 ^= x3;	\
-	x3 &= x1;	x1 ^= x0;	x0 &= x2;	\
-	x4 ^= x3;	x3 ^= x0;	x0 ^= x1;
-
-#define SI4(x0,x1,x2,x3,x4)				\
-	x2 ^= x3;	x4  = x0;	x0 &= x1;	\
-	x0 ^= x2;	x2 |= x3;	x4 =~ x4;	\
-	x1 ^= x0;	x0 ^= x2;	x2 &= x4;	\
-	x2 ^= x0;	x0 |= x4;			\
-	x0 ^= x3;	x3 &= x2;			\
-	x4 ^= x3;	x3 ^= x1;	x1 &= x0;	\
-	x4 ^= x1;	x0 ^= x3;
-
-#define SI5(x0,x1,x2,x3,x4)				\
-			x4  = x1;	x1 |= x2;	\
-	x2 ^= x4;	x1 ^= x3;	x3 &= x4;	\
-	x2 ^= x3;	x3 |= x0;	x0 =~ x0;	\
-	x3 ^= x2;	x2 |= x0;	x4 ^= x1;	\
-	x2 ^= x4;	x4 &= x0;	x0 ^= x1;	\
-	x1 ^= x3;	x0 &= x2;	x2 ^= x3;	\
-	x0 ^= x2;	x2 ^= x4;	x4 ^= x3;
-
-#define SI6(x0,x1,x2,x3,x4)				\
-			x0 ^= x2;			\
-	x4  = x0;	x0 &= x3;	x2 ^= x3;	\
-	x0 ^= x2;	x3 ^= x1;	x2 |= x4;	\
-	x2 ^= x3;	x3 &= x0;	x0 =~ x0;	\
-	x3 ^= x1;	x1 &= x2;	x4 ^= x0;	\
-	x3 ^= x4;	x4 ^= x2;	x0 ^= x1;	\
-	x2 ^= x0;
-
-#define SI7(x0,x1,x2,x3,x4)				\
-	x4  = x3;	x3 &= x0;	x0 ^= x2;	\
-	x2 |= x4;	x4 ^= x1;	x0 =~ x0;	\
-	x1 |= x3;	x4 ^= x0;	x0 &= x2;	\
-	x0 ^= x1;	x1 &= x2;	x3 ^= x2;	\
-	x4 ^= x3;	x2 &= x3;	x3 |= x0;	\
-	x1 ^= x4;	x3 ^= x4;	x4 &= x0;	\
-	x4 ^= x2;
-
-struct serpent_ctx {
-	u32 expkey[SERPENT_EXPKEY_WORDS];
-};
-
-
-static int serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
-			  unsigned int keylen)
-{
-	struct serpent_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *k = ctx->expkey;
-	u8  *k8 = (u8 *)k;
-	u32 r0,r1,r2,r3,r4;
-	int i;
-
-	/* Copy key, add padding */
-
-	for (i = 0; i < keylen; ++i)
-		k8[i] = key[i];
-	if (i < SERPENT_MAX_KEY_SIZE)
-		k8[i++] = 1;
-	while (i < SERPENT_MAX_KEY_SIZE)
-		k8[i++] = 0;
-
-	/* Expand key using polynomial */
-
-	r0 = le32_to_cpu(k[3]);
-	r1 = le32_to_cpu(k[4]);
-	r2 = le32_to_cpu(k[5]);
-	r3 = le32_to_cpu(k[6]);
-	r4 = le32_to_cpu(k[7]);
-
-	keyiter(le32_to_cpu(k[0]),r0,r4,r2,0,0);
-	keyiter(le32_to_cpu(k[1]),r1,r0,r3,1,1);
-	keyiter(le32_to_cpu(k[2]),r2,r1,r4,2,2);
-	keyiter(le32_to_cpu(k[3]),r3,r2,r0,3,3);
-	keyiter(le32_to_cpu(k[4]),r4,r3,r1,4,4);
-	keyiter(le32_to_cpu(k[5]),r0,r4,r2,5,5);
-	keyiter(le32_to_cpu(k[6]),r1,r0,r3,6,6);
-	keyiter(le32_to_cpu(k[7]),r2,r1,r4,7,7);
-
-	keyiter(k[  0],r3,r2,r0,  8,  8); keyiter(k[  1],r4,r3,r1,  9,  9);
-	keyiter(k[  2],r0,r4,r2, 10, 10); keyiter(k[  3],r1,r0,r3, 11, 11);
-	keyiter(k[  4],r2,r1,r4, 12, 12); keyiter(k[  5],r3,r2,r0, 13, 13);
-	keyiter(k[  6],r4,r3,r1, 14, 14); keyiter(k[  7],r0,r4,r2, 15, 15);
-	keyiter(k[  8],r1,r0,r3, 16, 16); keyiter(k[  9],r2,r1,r4, 17, 17);
-	keyiter(k[ 10],r3,r2,r0, 18, 18); keyiter(k[ 11],r4,r3,r1, 19, 19);
-	keyiter(k[ 12],r0,r4,r2, 20, 20); keyiter(k[ 13],r1,r0,r3, 21, 21);
-	keyiter(k[ 14],r2,r1,r4, 22, 22); keyiter(k[ 15],r3,r2,r0, 23, 23);
-	keyiter(k[ 16],r4,r3,r1, 24, 24); keyiter(k[ 17],r0,r4,r2, 25, 25);
-	keyiter(k[ 18],r1,r0,r3, 26, 26); keyiter(k[ 19],r2,r1,r4, 27, 27);
-	keyiter(k[ 20],r3,r2,r0, 28, 28); keyiter(k[ 21],r4,r3,r1, 29, 29);
-	keyiter(k[ 22],r0,r4,r2, 30, 30); keyiter(k[ 23],r1,r0,r3, 31, 31);
-
-	k += 50;
-
-	keyiter(k[-26],r2,r1,r4, 32,-18); keyiter(k[-25],r3,r2,r0, 33,-17);
-	keyiter(k[-24],r4,r3,r1, 34,-16); keyiter(k[-23],r0,r4,r2, 35,-15);
-	keyiter(k[-22],r1,r0,r3, 36,-14); keyiter(k[-21],r2,r1,r4, 37,-13);
-	keyiter(k[-20],r3,r2,r0, 38,-12); keyiter(k[-19],r4,r3,r1, 39,-11);
-	keyiter(k[-18],r0,r4,r2, 40,-10); keyiter(k[-17],r1,r0,r3, 41, -9);
-	keyiter(k[-16],r2,r1,r4, 42, -8); keyiter(k[-15],r3,r2,r0, 43, -7);
-	keyiter(k[-14],r4,r3,r1, 44, -6); keyiter(k[-13],r0,r4,r2, 45, -5);
-	keyiter(k[-12],r1,r0,r3, 46, -4); keyiter(k[-11],r2,r1,r4, 47, -3);
-	keyiter(k[-10],r3,r2,r0, 48, -2); keyiter(k[ -9],r4,r3,r1, 49, -1);
-	keyiter(k[ -8],r0,r4,r2, 50,  0); keyiter(k[ -7],r1,r0,r3, 51,  1);
-	keyiter(k[ -6],r2,r1,r4, 52,  2); keyiter(k[ -5],r3,r2,r0, 53,  3);
-	keyiter(k[ -4],r4,r3,r1, 54,  4); keyiter(k[ -3],r0,r4,r2, 55,  5);
-	keyiter(k[ -2],r1,r0,r3, 56,  6); keyiter(k[ -1],r2,r1,r4, 57,  7);
-	keyiter(k[  0],r3,r2,r0, 58,  8); keyiter(k[  1],r4,r3,r1, 59,  9);
-	keyiter(k[  2],r0,r4,r2, 60, 10); keyiter(k[  3],r1,r0,r3, 61, 11);
-	keyiter(k[  4],r2,r1,r4, 62, 12); keyiter(k[  5],r3,r2,r0, 63, 13);
-	keyiter(k[  6],r4,r3,r1, 64, 14); keyiter(k[  7],r0,r4,r2, 65, 15);
-	keyiter(k[  8],r1,r0,r3, 66, 16); keyiter(k[  9],r2,r1,r4, 67, 17);
-	keyiter(k[ 10],r3,r2,r0, 68, 18); keyiter(k[ 11],r4,r3,r1, 69, 19);
-	keyiter(k[ 12],r0,r4,r2, 70, 20); keyiter(k[ 13],r1,r0,r3, 71, 21);
-	keyiter(k[ 14],r2,r1,r4, 72, 22); keyiter(k[ 15],r3,r2,r0, 73, 23);
-	keyiter(k[ 16],r4,r3,r1, 74, 24); keyiter(k[ 17],r0,r4,r2, 75, 25);
-	keyiter(k[ 18],r1,r0,r3, 76, 26); keyiter(k[ 19],r2,r1,r4, 77, 27);
-	keyiter(k[ 20],r3,r2,r0, 78, 28); keyiter(k[ 21],r4,r3,r1, 79, 29);
-	keyiter(k[ 22],r0,r4,r2, 80, 30); keyiter(k[ 23],r1,r0,r3, 81, 31);
-
-	k += 50;
-
-	keyiter(k[-26],r2,r1,r4, 82,-18); keyiter(k[-25],r3,r2,r0, 83,-17);
-	keyiter(k[-24],r4,r3,r1, 84,-16); keyiter(k[-23],r0,r4,r2, 85,-15);
-	keyiter(k[-22],r1,r0,r3, 86,-14); keyiter(k[-21],r2,r1,r4, 87,-13);
-	keyiter(k[-20],r3,r2,r0, 88,-12); keyiter(k[-19],r4,r3,r1, 89,-11);
-	keyiter(k[-18],r0,r4,r2, 90,-10); keyiter(k[-17],r1,r0,r3, 91, -9);
-	keyiter(k[-16],r2,r1,r4, 92, -8); keyiter(k[-15],r3,r2,r0, 93, -7);
-	keyiter(k[-14],r4,r3,r1, 94, -6); keyiter(k[-13],r0,r4,r2, 95, -5);
-	keyiter(k[-12],r1,r0,r3, 96, -4); keyiter(k[-11],r2,r1,r4, 97, -3);
-	keyiter(k[-10],r3,r2,r0, 98, -2); keyiter(k[ -9],r4,r3,r1, 99, -1);
-	keyiter(k[ -8],r0,r4,r2,100,  0); keyiter(k[ -7],r1,r0,r3,101,  1);
-	keyiter(k[ -6],r2,r1,r4,102,  2); keyiter(k[ -5],r3,r2,r0,103,  3);
-	keyiter(k[ -4],r4,r3,r1,104,  4); keyiter(k[ -3],r0,r4,r2,105,  5);
-	keyiter(k[ -2],r1,r0,r3,106,  6); keyiter(k[ -1],r2,r1,r4,107,  7);
-	keyiter(k[  0],r3,r2,r0,108,  8); keyiter(k[  1],r4,r3,r1,109,  9);
-	keyiter(k[  2],r0,r4,r2,110, 10); keyiter(k[  3],r1,r0,r3,111, 11);
-	keyiter(k[  4],r2,r1,r4,112, 12); keyiter(k[  5],r3,r2,r0,113, 13);
-	keyiter(k[  6],r4,r3,r1,114, 14); keyiter(k[  7],r0,r4,r2,115, 15);
-	keyiter(k[  8],r1,r0,r3,116, 16); keyiter(k[  9],r2,r1,r4,117, 17);
-	keyiter(k[ 10],r3,r2,r0,118, 18); keyiter(k[ 11],r4,r3,r1,119, 19);
-	keyiter(k[ 12],r0,r4,r2,120, 20); keyiter(k[ 13],r1,r0,r3,121, 21);
-	keyiter(k[ 14],r2,r1,r4,122, 22); keyiter(k[ 15],r3,r2,r0,123, 23);
-	keyiter(k[ 16],r4,r3,r1,124, 24); keyiter(k[ 17],r0,r4,r2,125, 25);
-	keyiter(k[ 18],r1,r0,r3,126, 26); keyiter(k[ 19],r2,r1,r4,127, 27);
-	keyiter(k[ 20],r3,r2,r0,128, 28); keyiter(k[ 21],r4,r3,r1,129, 29);
-	keyiter(k[ 22],r0,r4,r2,130, 30); keyiter(k[ 23],r1,r0,r3,131, 31);
-
-	/* Apply S-boxes */
-
-	S3(r3,r4,r0,r1,r2); storekeys(r1,r2,r4,r3, 28); loadkeys(r1,r2,r4,r3, 24);
-	S4(r1,r2,r4,r3,r0); storekeys(r2,r4,r3,r0, 24); loadkeys(r2,r4,r3,r0, 20);
-	S5(r2,r4,r3,r0,r1); storekeys(r1,r2,r4,r0, 20); loadkeys(r1,r2,r4,r0, 16);
-	S6(r1,r2,r4,r0,r3); storekeys(r4,r3,r2,r0, 16); loadkeys(r4,r3,r2,r0, 12);
-	S7(r4,r3,r2,r0,r1); storekeys(r1,r2,r0,r4, 12); loadkeys(r1,r2,r0,r4,  8);
-	S0(r1,r2,r0,r4,r3); storekeys(r0,r2,r4,r1,  8); loadkeys(r0,r2,r4,r1,  4);
-	S1(r0,r2,r4,r1,r3); storekeys(r3,r4,r1,r0,  4); loadkeys(r3,r4,r1,r0,  0);
-	S2(r3,r4,r1,r0,r2); storekeys(r2,r4,r3,r0,  0); loadkeys(r2,r4,r3,r0, -4);
-	S3(r2,r4,r3,r0,r1); storekeys(r0,r1,r4,r2, -4); loadkeys(r0,r1,r4,r2, -8);
-	S4(r0,r1,r4,r2,r3); storekeys(r1,r4,r2,r3, -8); loadkeys(r1,r4,r2,r3,-12);
-	S5(r1,r4,r2,r3,r0); storekeys(r0,r1,r4,r3,-12); loadkeys(r0,r1,r4,r3,-16);
-	S6(r0,r1,r4,r3,r2); storekeys(r4,r2,r1,r3,-16); loadkeys(r4,r2,r1,r3,-20);
-	S7(r4,r2,r1,r3,r0); storekeys(r0,r1,r3,r4,-20); loadkeys(r0,r1,r3,r4,-24);
-	S0(r0,r1,r3,r4,r2); storekeys(r3,r1,r4,r0,-24); loadkeys(r3,r1,r4,r0,-28);
-	k -= 50;
-	S1(r3,r1,r4,r0,r2); storekeys(r2,r4,r0,r3, 22); loadkeys(r2,r4,r0,r3, 18);
-	S2(r2,r4,r0,r3,r1); storekeys(r1,r4,r2,r3, 18); loadkeys(r1,r4,r2,r3, 14);
-	S3(r1,r4,r2,r3,r0); storekeys(r3,r0,r4,r1, 14); loadkeys(r3,r0,r4,r1, 10);
-	S4(r3,r0,r4,r1,r2); storekeys(r0,r4,r1,r2, 10); loadkeys(r0,r4,r1,r2,  6);
-	S5(r0,r4,r1,r2,r3); storekeys(r3,r0,r4,r2,  6); loadkeys(r3,r0,r4,r2,  2);
-	S6(r3,r0,r4,r2,r1); storekeys(r4,r1,r0,r2,  2); loadkeys(r4,r1,r0,r2, -2);
-	S7(r4,r1,r0,r2,r3); storekeys(r3,r0,r2,r4, -2); loadkeys(r3,r0,r2,r4, -6);
-	S0(r3,r0,r2,r4,r1); storekeys(r2,r0,r4,r3, -6); loadkeys(r2,r0,r4,r3,-10);
-	S1(r2,r0,r4,r3,r1); storekeys(r1,r4,r3,r2,-10); loadkeys(r1,r4,r3,r2,-14);
-	S2(r1,r4,r3,r2,r0); storekeys(r0,r4,r1,r2,-14); loadkeys(r0,r4,r1,r2,-18);
-	S3(r0,r4,r1,r2,r3); storekeys(r2,r3,r4,r0,-18); loadkeys(r2,r3,r4,r0,-22);
-	k -= 50;
-	S4(r2,r3,r4,r0,r1); storekeys(r3,r4,r0,r1, 28); loadkeys(r3,r4,r0,r1, 24);
-	S5(r3,r4,r0,r1,r2); storekeys(r2,r3,r4,r1, 24); loadkeys(r2,r3,r4,r1, 20);
-	S6(r2,r3,r4,r1,r0); storekeys(r4,r0,r3,r1, 20); loadkeys(r4,r0,r3,r1, 16);
-	S7(r4,r0,r3,r1,r2); storekeys(r2,r3,r1,r4, 16); loadkeys(r2,r3,r1,r4, 12);
-	S0(r2,r3,r1,r4,r0); storekeys(r1,r3,r4,r2, 12); loadkeys(r1,r3,r4,r2,  8);
-	S1(r1,r3,r4,r2,r0); storekeys(r0,r4,r2,r1,  8); loadkeys(r0,r4,r2,r1,  4);
-	S2(r0,r4,r2,r1,r3); storekeys(r3,r4,r0,r1,  4); loadkeys(r3,r4,r0,r1,  0);
-	S3(r3,r4,r0,r1,r2); storekeys(r1,r2,r4,r3,  0);
-
-	return 0;
-}
-
-static void serpent_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	struct serpent_ctx *ctx = crypto_tfm_ctx(tfm);
-	const u32
-		*k = ctx->expkey;
-	const __le32 *s = (const __le32 *)src;
-	__le32	*d = (__le32 *)dst;
-	u32	r0, r1, r2, r3, r4;
-
-/*
- * Note: The conversions between u8* and u32* might cause trouble
- * on architectures with stricter alignment rules than x86
- */
-
-	r0 = le32_to_cpu(s[0]);
-	r1 = le32_to_cpu(s[1]);
-	r2 = le32_to_cpu(s[2]);
-	r3 = le32_to_cpu(s[3]);
-
-				 K(r0,r1,r2,r3,0);
-	S0(r0,r1,r2,r3,r4);	LK(r2,r1,r3,r0,r4,1);
-	S1(r2,r1,r3,r0,r4);	LK(r4,r3,r0,r2,r1,2);
-	S2(r4,r3,r0,r2,r1);	LK(r1,r3,r4,r2,r0,3);
-	S3(r1,r3,r4,r2,r0);	LK(r2,r0,r3,r1,r4,4);
-	S4(r2,r0,r3,r1,r4);	LK(r0,r3,r1,r4,r2,5);
-	S5(r0,r3,r1,r4,r2);	LK(r2,r0,r3,r4,r1,6);
-	S6(r2,r0,r3,r4,r1);	LK(r3,r1,r0,r4,r2,7);
-	S7(r3,r1,r0,r4,r2);	LK(r2,r0,r4,r3,r1,8);
-	S0(r2,r0,r4,r3,r1);	LK(r4,r0,r3,r2,r1,9);
-	S1(r4,r0,r3,r2,r1);	LK(r1,r3,r2,r4,r0,10);
-	S2(r1,r3,r2,r4,r0);	LK(r0,r3,r1,r4,r2,11);
-	S3(r0,r3,r1,r4,r2);	LK(r4,r2,r3,r0,r1,12);
-	S4(r4,r2,r3,r0,r1);	LK(r2,r3,r0,r1,r4,13);
-	S5(r2,r3,r0,r1,r4);	LK(r4,r2,r3,r1,r0,14);
-	S6(r4,r2,r3,r1,r0);	LK(r3,r0,r2,r1,r4,15);
-	S7(r3,r0,r2,r1,r4);	LK(r4,r2,r1,r3,r0,16);
-	S0(r4,r2,r1,r3,r0);	LK(r1,r2,r3,r4,r0,17);
-	S1(r1,r2,r3,r4,r0);	LK(r0,r3,r4,r1,r2,18);
-	S2(r0,r3,r4,r1,r2);	LK(r2,r3,r0,r1,r4,19);
-	S3(r2,r3,r0,r1,r4);	LK(r1,r4,r3,r2,r0,20);
-	S4(r1,r4,r3,r2,r0);	LK(r4,r3,r2,r0,r1,21);
-	S5(r4,r3,r2,r0,r1);	LK(r1,r4,r3,r0,r2,22);
-	S6(r1,r4,r3,r0,r2);	LK(r3,r2,r4,r0,r1,23);
-	S7(r3,r2,r4,r0,r1);	LK(r1,r4,r0,r3,r2,24);
-	S0(r1,r4,r0,r3,r2);	LK(r0,r4,r3,r1,r2,25);
-	S1(r0,r4,r3,r1,r2);	LK(r2,r3,r1,r0,r4,26);
-	S2(r2,r3,r1,r0,r4);	LK(r4,r3,r2,r0,r1,27);
-	S3(r4,r3,r2,r0,r1);	LK(r0,r1,r3,r4,r2,28);
-	S4(r0,r1,r3,r4,r2);	LK(r1,r3,r4,r2,r0,29);
-	S5(r1,r3,r4,r2,r0);	LK(r0,r1,r3,r2,r4,30);
-	S6(r0,r1,r3,r2,r4);	LK(r3,r4,r1,r2,r0,31);
-	S7(r3,r4,r1,r2,r0);	 K(r0,r1,r2,r3,32);
-
-	d[0] = cpu_to_le32(r0);
-	d[1] = cpu_to_le32(r1);
-	d[2] = cpu_to_le32(r2);
-	d[3] = cpu_to_le32(r3);
-}
-
-static void serpent_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	struct serpent_ctx *ctx = crypto_tfm_ctx(tfm);
-	const u32
-		*k = ((struct serpent_ctx *)ctx)->expkey;
-	const __le32 *s = (const __le32 *)src;
-	__le32	*d = (__le32 *)dst;
-	u32	r0, r1, r2, r3, r4;
-
-	r0 = le32_to_cpu(s[0]);
-	r1 = le32_to_cpu(s[1]);
-	r2 = le32_to_cpu(s[2]);
-	r3 = le32_to_cpu(s[3]);
-
-				K(r0,r1,r2,r3,32);
-	SI7(r0,r1,r2,r3,r4);	KL(r1,r3,r0,r4,r2,31);
-	SI6(r1,r3,r0,r4,r2);	KL(r0,r2,r4,r1,r3,30);
-	SI5(r0,r2,r4,r1,r3);	KL(r2,r3,r0,r4,r1,29);
-	SI4(r2,r3,r0,r4,r1);	KL(r2,r0,r1,r4,r3,28);
-	SI3(r2,r0,r1,r4,r3);	KL(r1,r2,r3,r4,r0,27);
-	SI2(r1,r2,r3,r4,r0);	KL(r2,r0,r4,r3,r1,26);
-	SI1(r2,r0,r4,r3,r1);	KL(r1,r0,r4,r3,r2,25);
-	SI0(r1,r0,r4,r3,r2);	KL(r4,r2,r0,r1,r3,24);
-	SI7(r4,r2,r0,r1,r3);	KL(r2,r1,r4,r3,r0,23);
-	SI6(r2,r1,r4,r3,r0);	KL(r4,r0,r3,r2,r1,22);
-	SI5(r4,r0,r3,r2,r1);	KL(r0,r1,r4,r3,r2,21);
-	SI4(r0,r1,r4,r3,r2);	KL(r0,r4,r2,r3,r1,20);
-	SI3(r0,r4,r2,r3,r1);	KL(r2,r0,r1,r3,r4,19);
-	SI2(r2,r0,r1,r3,r4);	KL(r0,r4,r3,r1,r2,18);
-	SI1(r0,r4,r3,r1,r2);	KL(r2,r4,r3,r1,r0,17);
-	SI0(r2,r4,r3,r1,r0);	KL(r3,r0,r4,r2,r1,16);
-	SI7(r3,r0,r4,r2,r1);	KL(r0,r2,r3,r1,r4,15);
-	SI6(r0,r2,r3,r1,r4);	KL(r3,r4,r1,r0,r2,14);
-	SI5(r3,r4,r1,r0,r2);	KL(r4,r2,r3,r1,r0,13);
-	SI4(r4,r2,r3,r1,r0);	KL(r4,r3,r0,r1,r2,12);
-	SI3(r4,r3,r0,r1,r2);	KL(r0,r4,r2,r1,r3,11);
-	SI2(r0,r4,r2,r1,r3);	KL(r4,r3,r1,r2,r0,10);
-	SI1(r4,r3,r1,r2,r0);	KL(r0,r3,r1,r2,r4,9);
-	SI0(r0,r3,r1,r2,r4);	KL(r1,r4,r3,r0,r2,8);
-	SI7(r1,r4,r3,r0,r2);	KL(r4,r0,r1,r2,r3,7);
-	SI6(r4,r0,r1,r2,r3);	KL(r1,r3,r2,r4,r0,6);
-	SI5(r1,r3,r2,r4,r0);	KL(r3,r0,r1,r2,r4,5);
-	SI4(r3,r0,r1,r2,r4);	KL(r3,r1,r4,r2,r0,4);
-	SI3(r3,r1,r4,r2,r0);	KL(r4,r3,r0,r2,r1,3);
-	SI2(r4,r3,r0,r2,r1);	KL(r3,r1,r2,r0,r4,2);
-	SI1(r3,r1,r2,r0,r4);	KL(r4,r1,r2,r0,r3,1);
-	SI0(r4,r1,r2,r0,r3);	K(r2,r3,r1,r4,0);
-
-	d[0] = cpu_to_le32(r2);
-	d[1] = cpu_to_le32(r3);
-	d[2] = cpu_to_le32(r1);
-	d[3] = cpu_to_le32(r4);
-}
-
-static struct crypto_alg serpent_alg = {
-	.cra_name		=	"serpent",
-	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		=	SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct serpent_ctx),
-	.cra_alignma