Import initial strongswan 2.7.0 version into SVN.

53 files changed, 10014 insertions, 0 deletions

diff --git a/lib/libcrypto/include/cbc_generic.h b/lib/libcrypto/include/cbc_generic.h
new file mode 100644
index 000000000..0dd3a77d6
--- /dev/null
+++ b/lib/libcrypto/include/cbc_generic.h
@@ -0,0 +1,110 @@
+#ifndef _CBC_GENERIC_H
+#define _CBC_GENERIC_H
+/*
+ * CBC macro helpers
+ *
+ * Author: JuanJo Ciarlante <jjo-ipsec@mendoza.gov.ar>
+ *
+ * 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.  See <http://www.fsf.org/copyleft/gpl.txt>.
+ * 
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ */
+
+/*
+ * 	Heavily inspired in loop_AES
+ */
+#define CBC_IMPL_BLK16(name, ctx_type, addr_type, enc_func, dec_func) \
+int name(ctx_type *ctx, const u_int8_t * in, u_int8_t * out, int ilen, const u_int8_t * iv, int encrypt) { \
+	int ret=ilen, pos; \
+	const u_int32_t *iv_i; \
+	if ((ilen) % 16) return 0; \
+	if (encrypt) { \
+		pos=0; \
+		while(pos<ilen) { \
+			if (pos==0) \
+				iv_i=(const u_int32_t*) iv; \
+			else \
+				iv_i=(const u_int32_t*) (out-16); \
+			*((u_int32_t *)(&out[ 0])) = iv_i[0]^*((const u_int32_t *)(&in[ 0])); \
+			*((u_int32_t *)(&out[ 4])) = iv_i[1]^*((const u_int32_t *)(&in[ 4])); \
+			*((u_int32_t *)(&out[ 8])) = iv_i[2]^*((const u_int32_t *)(&in[ 8])); \
+			*((u_int32_t *)(&out[12])) = iv_i[3]^*((const u_int32_t *)(&in[12])); \
+			enc_func(ctx, (addr_type) out, (addr_type) out); \
+			in+=16; \
+			out+=16; \
+			pos+=16; \
+		} \
+	} else { \
+		pos=ilen-16; \
+		in+=pos; \
+		out+=pos; \
+		while(pos>=0) { \
+			dec_func(ctx, (const addr_type) in, (addr_type) out); \
+			if (pos==0) \
+				iv_i=(const u_int32_t*) (iv); \
+			else \
+				iv_i=(const u_int32_t*) (in-16); \
+			*((u_int32_t *)(&out[ 0])) ^= iv_i[0]; \
+			*((u_int32_t *)(&out[ 4])) ^= iv_i[1]; \
+			*((u_int32_t *)(&out[ 8])) ^= iv_i[2]; \
+			*((u_int32_t *)(&out[12])) ^= iv_i[3]; \
+			in-=16; \
+			out-=16; \
+			pos-=16; \
+		} \
+	} \
+	return ret; \
+} 
+#define CBC_IMPL_BLK8(name, ctx_type, addr_type,  enc_func, dec_func) \
+int name(ctx_type *ctx, u_int8_t * in, u_int8_t * out, int ilen, const u_int8_t * iv, int encrypt) { \
+	int ret=ilen, pos; \
+	const u_int32_t *iv_i; \
+	if ((ilen) % 8) return 0; \
+	if (encrypt) { \
+		pos=0; \
+		while(pos<ilen) { \
+			if (pos==0) \
+				iv_i=(const u_int32_t*) iv; \
+			else \
+				iv_i=(const u_int32_t*) (out-8); \
+			*((u_int32_t *)(&out[ 0])) = iv_i[0]^*((const u_int32_t *)(&in[ 0])); \
+			*((u_int32_t *)(&out[ 4])) = iv_i[1]^*((const u_int32_t *)(&in[ 4])); \
+			enc_func(ctx, (addr_type)out, (addr_type)out); \
+			in+=8; \
+			out+=8; \
+			pos+=8; \
+		} \
+	} else { \
+		pos=ilen-8; \
+		in+=pos; \
+		out+=pos; \
+		while(pos>=0) { \
+			dec_func(ctx, (const addr_type)in, (addr_type)out); \
+			if (pos==0) \
+				iv_i=(const u_int32_t*) (iv); \
+			else \
+				iv_i=(const u_int32_t*) (in-8); \
+			*((u_int32_t *)(&out[ 0])) ^= iv_i[0]; \
+			*((u_int32_t *)(&out[ 4])) ^= iv_i[1]; \
+			in-=8; \
+			out-=8; \
+			pos-=8; \
+		} \
+	} \
+	return ret; \
+} 
+#define CBC_DECL(name, ctx_type) \
+int name(ctx_type *ctx, u_int8_t * in, u_int8_t * out, int ilen, const u_int8_t * iv, int encrypt)
+/*
+Eg.:
+CBC_IMPL_BLK16(AES_cbc_encrypt, aes_context, u_int8_t *, aes_encrypt, aes_decrypt);
+CBC_DECL(AES_cbc_encrypt, aes_context);
+*/
+#endif /* _CBC_GENERIC_H */
diff --git a/lib/libcrypto/include/hmac_generic.h b/lib/libcrypto/include/hmac_generic.h
new file mode 100644
index 000000000..a749228e3
--- /dev/null
+++ b/lib/libcrypto/include/hmac_generic.h
@@ -0,0 +1,60 @@
+#ifndef _HMAC_GENERIC_H
+#define _HMAC_GENERIC_H
+/*
+ * HMAC macro helpers
+ *
+ * Author: JuanJo Ciarlante <jjo-ipsec@mendoza.gov.ar>
+ *
+ * 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.  See <http://www.fsf.org/copyleft/gpl.txt>.
+ * 
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef DIVUP
+#define DIVUP(x,y) ((x + y -1) / y) /* divide, rounding upwards */
+#endif
+#ifndef HMAC_IPAD
+#define		HMAC_IPAD	0x36
+#define		HMAC_OPAD	0x5C
+#endif
+#define HMAC_SET_KEY_IMPL(func_name, hctx_t, blocksize, func_init, func_update) \
+void func_name(hctx_t *hctx, const u_int8_t * key, int keylen) { \
+	int i;\
+	u_int8_t kb[blocksize];		\
+	for (i = 0; i < DIVUP(keylen*8, 8); i++) {	\
+		kb[i] = key[i] ^ HMAC_IPAD;	\
+	}					\
+	for (; i < blocksize; i++) {		\
+		kb[i] = HMAC_IPAD;		\
+	}					\
+	func_init(&hctx->ictx);			\
+	func_update(&hctx->ictx, kb, blocksize);	\
+	for (i = 0; i < blocksize; i++) {	\
+		kb[i] ^= (HMAC_IPAD ^ HMAC_OPAD);	\
+	}					\
+	func_init(&hctx->octx);			\
+	func_update(&hctx->octx, kb, blocksize);	\
+}
+#define HMAC_HASH_IMPL(func_name, hctx_t, ctx_t, ahlen, func_update, func_result ) \
+void func_name(hctx_t *hctx, const u_int8_t * dat, int len, u_int8_t * hash, int hashlen) {	\
+	ctx_t ctx;	\
+	ctx=hctx->ictx;	\
+	if (dat) func_update(&ctx, dat, len);	\
+	if (hash) {				\
+		u_int8_t hash_buf[ahlen];			\
+		func_result(&ctx, hash_buf, ahlen);	\
+		ctx=hctx->octx;				\
+		func_update(&ctx, hash_buf, ahlen);	\
+		func_result(&ctx, hash, hashlen);	\
+		memset(&ctx, 0, sizeof (ctx));		\
+		memset(&hash_buf, 0, sizeof (hash_buf));\
+	}					\
+}
+#endif /* _HMAC_GENERIC_H */
diff --git a/lib/libcrypto/include/md32_common.h b/lib/libcrypto/include/md32_common.h
new file mode 100644
index 000000000..1a404a458
--- /dev/null
+++ b/lib/libcrypto/include/md32_common.h
@@ -0,0 +1,607 @@
+/* crypto/md32_common.h */
+/* ====================================================================
+ * Copyright (c) 1999 The OpenSSL Project.  All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer. 
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * 3. All advertising materials mentioning features or use of this
+ *    software must display the following acknowledgment:
+ *    "This product includes software developed by the OpenSSL Project
+ *    for use in the OpenSSL Toolkit. (http://www.OpenSSL.org/)"
+ *
+ * 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
+ *    endorse or promote products derived from this software without
+ *    prior written permission. For written permission, please contact
+ *    licensing@OpenSSL.org.
+ *
+ * 5. Products derived from this software may not be called "OpenSSL"
+ *    nor may "OpenSSL" appear in their names without prior written
+ *    permission of the OpenSSL Project.
+ *
+ * 6. Redistributions of any form whatsoever must retain the following
+ *    acknowledgment:
+ *    "This product includes software developed by the OpenSSL Project
+ *    for use in the OpenSSL Toolkit (http://www.OpenSSL.org/)"
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
+ * EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE OpenSSL PROJECT OR
+ * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+ * ====================================================================
+ *
+ * This product includes cryptographic software written by Eric Young
+ * (eay@cryptsoft.com).  This product includes software written by Tim
+ * Hudson (tjh@cryptsoft.com).
+ *
+ */
+
+/*
+ * This is a generic 32 bit "collector" for message digest algorithms.
+ * Whenever needed it collects input character stream into chunks of
+ * 32 bit values and invokes a block function that performs actual hash
+ * calculations.
+ *
+ * Porting guide.
+ *
+ * Obligatory macros:
+ *
+ * DATA_ORDER_IS_BIG_ENDIAN or DATA_ORDER_IS_LITTLE_ENDIAN
+ *	this macro defines byte order of input stream.
+ * HASH_CBLOCK
+ *	size of a unit chunk HASH_BLOCK operates on.
+ * HASH_LONG
+ *	has to be at lest 32 bit wide, if it's wider, then
+ *	HASH_LONG_LOG2 *has to* be defined along
+ * HASH_CTX
+ *	context structure that at least contains following
+ *	members:
+ *		typedef struct {
+ *			...
+ *			HASH_LONG	Nl,Nh;
+ *			HASH_LONG	data[HASH_LBLOCK];
+ *			int		num;
+ *			...
+ *			} HASH_CTX;
+ * HASH_UPDATE
+ *	name of "Update" function, implemented here.
+ * HASH_TRANSFORM
+ *	name of "Transform" function, implemented here.
+ * HASH_FINAL
+ *	name of "Final" function, implemented here.
+ * HASH_BLOCK_HOST_ORDER
+ *	name of "block" function treating *aligned* input message
+ *	in host byte order, implemented externally.
+ * HASH_BLOCK_DATA_ORDER
+ *	name of "block" function treating *unaligned* input message
+ *	in original (data) byte order, implemented externally (it
+ *	actually is optional if data and host are of the same
+ *	"endianess").
+ * HASH_MAKE_STRING
+ *	macro convering context variables to an ASCII hash string.
+ *
+ * Optional macros:
+ *
+ * B_ENDIAN or L_ENDIAN
+ *	defines host byte-order.
+ * HASH_LONG_LOG2
+ *	defaults to 2 if not states otherwise.
+ * HASH_LBLOCK
+ *	assumed to be HASH_CBLOCK/4 if not stated otherwise.
+ * HASH_BLOCK_DATA_ORDER_ALIGNED
+ *	alternative "block" function capable of treating
+ *	aligned input message in original (data) order,
+ *	implemented externally.
+ *
+ * MD5 example:
+ *
+ *	#define DATA_ORDER_IS_LITTLE_ENDIAN
+ *
+ *	#define HASH_LONG		MD5_LONG
+ *	#define HASH_LONG_LOG2		MD5_LONG_LOG2
+ *	#define HASH_CTX		MD5_CTX
+ *	#define HASH_CBLOCK		MD5_CBLOCK
+ *	#define HASH_LBLOCK		MD5_LBLOCK
+ *	#define HASH_UPDATE		MD5_Update
+ *	#define HASH_TRANSFORM		MD5_Transform
+ *	#define HASH_FINAL		MD5_Final
+ *	#define HASH_BLOCK_HOST_ORDER	md5_block_host_order
+ *	#define HASH_BLOCK_DATA_ORDER	md5_block_data_order
+ *
+ *					<appro@fy.chalmers.se>
+ */
+
+#if !defined(DATA_ORDER_IS_BIG_ENDIAN) && !defined(DATA_ORDER_IS_LITTLE_ENDIAN)
+#error "DATA_ORDER must be defined!"
+#endif
+
+#ifndef HASH_CBLOCK
+#error "HASH_CBLOCK must be defined!"
+#endif
+#ifndef HASH_LONG
+#error "HASH_LONG must be defined!"
+#endif
+#ifndef HASH_CTX
+#error "HASH_CTX must be defined!"
+#endif
+
+#ifndef HASH_UPDATE
+#error "HASH_UPDATE must be defined!"
+#endif
+#ifndef HASH_TRANSFORM
+#error "HASH_TRANSFORM must be defined!"
+#endif
+#ifndef HASH_FINAL
+#error "HASH_FINAL must be defined!"
+#endif
+
+#ifndef HASH_BLOCK_HOST_ORDER
+#error "HASH_BLOCK_HOST_ORDER must be defined!"
+#endif
+
+#if 0
+/*
+ * Moved below as it's required only if HASH_BLOCK_DATA_ORDER_ALIGNED
+ * isn't defined.
+ */
+#ifndef HASH_BLOCK_DATA_ORDER
+#error "HASH_BLOCK_DATA_ORDER must be defined!"
+#endif
+#endif
+
+#ifndef HASH_LBLOCK
+#define HASH_LBLOCK	(HASH_CBLOCK/4)
+#endif
+
+#ifndef HASH_LONG_LOG2
+#define HASH_LONG_LOG2	2
+#endif
+
+/*
+ * Engage compiler specific rotate intrinsic function if available.
+ */
+#undef ROTATE
+#ifndef PEDANTIC
+# if defined(_MSC_VER)
+#  define ROTATE(a,n)	_lrotl(a,n)
+# elif defined(__MWERKS__)
+#  if defined(__POWERPC__)
+#   define ROTATE(a,n)	__rlwinm(a,n,0,31)
+#  elif defined(__MC68K__)
+    /* Motorola specific tweak. <appro@fy.chalmers.se> */
+#   define ROTATE(a,n)	( n<24 ? __rol(a,n) : __ror(a,32-n) )
+#  else
+#   define ROTATE(a,n)	__rol(a,n)
+#  endif
+# elif defined(__GNUC__) && __GNUC__>=2 && !defined(NO_ASM) && !defined(NO_INLINE_ASM)
+  /*
+   * Some GNU C inline assembler templates. Note that these are
+   * rotates by *constant* number of bits! But that's exactly
+   * what we need here...
+   *
+   * 					<appro@fy.chalmers.se>
+   */
+#  if defined(__i386)
+#   define ROTATE(a,n)	({ register unsigned int ret;	\
+				asm (			\
+				"roll %1,%0"		\
+				: "=r"(ret)		\
+				: "I"(n), "0"(a)	\
+				: "cc");		\
+			   ret;				\
+			})
+#  elif defined(__powerpc) || defined(__ppc)
+#   define ROTATE(a,n)	({ register unsigned int ret;	\
+				asm (			\
+				"rlwinm %0,%1,%2,0,31"	\
+				: "=r"(ret)		\
+				: "r"(a), "I"(n));	\
+			   ret;				\
+			})
+#  endif
+# endif
+
+/*
+ * Engage compiler specific "fetch in reverse byte order"
+ * intrinsic function if available.
+ */
+# if defined(__GNUC__) && __GNUC__>=2 && !defined(NO_ASM) && !defined(NO_INLINE_ASM)
+  /* some GNU C inline assembler templates by <appro@fy.chalmers.se> */
+#  if defined(__i386) && !defined(I386_ONLY)
+#   define BE_FETCH32(a)	({ register unsigned int l=(a);\
+				asm (			\
+				"bswapl %0"		\
+				: "=r"(l) : "0"(l));	\
+			  l;				\
+			})
+#  elif defined(__powerpc)
+#   define LE_FETCH32(a)	({ register unsigned int l;	\
+				asm (			\
+				"lwbrx %0,0,%1"		\
+				: "=r"(l)		\
+				: "r"(a));		\
+			   l;				\
+			})
+
+#  elif defined(__sparc) && defined(ULTRASPARC)
+#  define LE_FETCH32(a)	({ register unsigned int l;		\
+				asm (				\
+				"lda [%1]#ASI_PRIMARY_LITTLE,%0"\
+				: "=r"(l)			\
+				: "r"(a));			\
+			   l;					\
+			})
+#  endif
+# endif
+#endif /* PEDANTIC */
+
+#if HASH_LONG_LOG2==2	/* Engage only if sizeof(HASH_LONG)== 4 */
+/* A nice byte order reversal from Wei Dai <weidai@eskimo.com> */
+#ifdef ROTATE
+/* 5 instructions with rotate instruction, else 9 */
+#define REVERSE_FETCH32(a,l)	(					\
+		l=*(const HASH_LONG *)(a),				\
+		((ROTATE(l,8)&0x00FF00FF)|(ROTATE((l&0x00FF00FF),24)))	\
+				)
+#else
+/* 6 instructions with rotate instruction, else 8 */
+#define REVERSE_FETCH32(a,l)	(				\
+		l=*(const HASH_LONG *)(a),			\
+		l=(((l>>8)&0x00FF00FF)|((l&0x00FF00FF)<<8)),	\
+		ROTATE(l,16)					\
+				)
+/*
+ * Originally the middle line started with l=(((l&0xFF00FF00)>>8)|...
+ * It's rewritten as above for two reasons:
+ *	- RISCs aren't good at long constants and have to explicitely
+ *	  compose 'em with several (well, usually 2) instructions in a
+ *	  register before performing the actual operation and (as you
+ *	  already realized:-) having same constant should inspire the
+ *	  compiler to permanently allocate the only register for it;
+ *	- most modern CPUs have two ALUs, but usually only one has
+ *	  circuitry for shifts:-( this minor tweak inspires compiler
+ *	  to schedule shift instructions in a better way...
+ *
+ *				<appro@fy.chalmers.se>
+ */
+#endif
+#endif
+
+#ifndef ROTATE
+#define ROTATE(a,n)     (((a)<<(n))|(((a)&0xffffffff)>>(32-(n))))
+#endif
+
+/*
+ * Make some obvious choices. E.g., HASH_BLOCK_DATA_ORDER_ALIGNED
+ * and HASH_BLOCK_HOST_ORDER ought to be the same if input data
+ * and host are of the same "endianess". It's possible to mask
+ * this with blank #define HASH_BLOCK_DATA_ORDER though...
+ *
+ *				<appro@fy.chalmers.se>
+ */
+#if defined(B_ENDIAN)
+#  if defined(DATA_ORDER_IS_BIG_ENDIAN)
+#    if !defined(HASH_BLOCK_DATA_ORDER_ALIGNED) && HASH_LONG_LOG2==2
+#      define HASH_BLOCK_DATA_ORDER_ALIGNED	HASH_BLOCK_HOST_ORDER
+#    endif
+#  elif defined(DATA_ORDER_IS_LITTLE_ENDIAN)
+#    ifndef HOST_FETCH32
+#      ifdef LE_FETCH32
+#        define HOST_FETCH32(p,l)	LE_FETCH32(p)
+#      elif defined(REVERSE_FETCH32)
+#        define HOST_FETCH32(p,l)	REVERSE_FETCH32(p,l)
+#      endif
+#    endif
+#  endif
+#elif defined(L_ENDIAN)
+#  if defined(DATA_ORDER_IS_LITTLE_ENDIAN)
+#    if !defined(HASH_BLOCK_DATA_ORDER_ALIGNED) && HASH_LONG_LOG2==2
+#      define HASH_BLOCK_DATA_ORDER_ALIGNED	HASH_BLOCK_HOST_ORDER
+#    endif
+#  elif defined(DATA_ORDER_IS_BIG_ENDIAN)
+#    ifndef HOST_FETCH32
+#      ifdef BE_FETCH32
+#        define HOST_FETCH32(p,l)	BE_FETCH32(p)
+#      elif defined(REVERSE_FETCH32)
+#        define HOST_FETCH32(p,l)	REVERSE_FETCH32(p,l)
+#      endif
+#    endif
+#  endif
+#endif
+
+#if !defined(HASH_BLOCK_DATA_ORDER_ALIGNED)
+#ifndef HASH_BLOCK_DATA_ORDER
+#error "HASH_BLOCK_DATA_ORDER must be defined!"
+#endif
+#endif
+
+#if defined(DATA_ORDER_IS_BIG_ENDIAN)
+
+#define HOST_c2l(c,l)	(l =(((unsigned long)(*((c)++)))<<24),		\
+			 l|=(((unsigned long)(*((c)++)))<<16),		\
+			 l|=(((unsigned long)(*((c)++)))<< 8),		\
+			 l|=(((unsigned long)(*((c)++)))    ),		\
+			 l)
+#define HOST_p_c2l(c,l,n)	{					\
+			switch (n) {					\
+			case 0: l =((unsigned long)(*((c)++)))<<24;	\
+			case 1: l|=((unsigned long)(*((c)++)))<<16;	\
+			case 2: l|=((unsigned long)(*((c)++)))<< 8;	\
+			case 3: l|=((unsigned long)(*((c)++)));		\
+				} }
+#define HOST_p_c2l_p(c,l,sc,len) {					\
+			switch (sc) {					\
+			case 0: l =((unsigned long)(*((c)++)))<<24;	\
+				if (--len == 0) break;			\
+			case 1: l|=((unsigned long)(*((c)++)))<<16;	\
+				if (--len == 0) break;			\
+			case 2: l|=((unsigned long)(*((c)++)))<< 8;	\
+				} }
+/* NOTE the pointer is not incremented at the end of this */
+#define HOST_c2l_p(c,l,n)	{					\
+			l=0; (c)+=n;					\
+			switch (n) {					\
+			case 3: l =((unsigned long)(*(--(c))))<< 8;	\
+			case 2: l|=((unsigned long)(*(--(c))))<<16;	\
+			case 1: l|=((unsigned long)(*(--(c))))<<24;	\
+				} }
+#define HOST_l2c(l,c)	(*((c)++)=(unsigned char)(((l)>>24)&0xff),	\
+			 *((c)++)=(unsigned char)(((l)>>16)&0xff),	\
+			 *((c)++)=(unsigned char)(((l)>> 8)&0xff),	\
+			 *((c)++)=(unsigned char)(((l)    )&0xff),	\
+			 l)
+
+#elif defined(DATA_ORDER_IS_LITTLE_ENDIAN)
+
+#define HOST_c2l(c,l)	(l =(((unsigned long)(*((c)++)))    ),		\
+			 l|=(((unsigned long)(*((c)++)))<< 8),		\
+			 l|=(((unsigned long)(*((c)++)))<<16),		\
+			 l|=(((unsigned long)(*((c)++)))<<24),		\
+			 l)
+#define HOST_p_c2l(c,l,n)	{					\
+			switch (n) {					\
+			case 0: l =((unsigned long)(*((c)++)));		\
+			case 1: l|=((unsigned long)(*((c)++)))<< 8;	\
+			case 2: l|=((unsigned long)(*((c)++)))<<16;	\
+			case 3: l|=((unsigned long)(*((c)++)))<<24;	\
+				} }
+#define HOST_p_c2l_p(c,l,sc,len) {					\
+			switch (sc) {					\
+			case 0: l =((unsigned long)(*((c)++)));		\
+				if (--len == 0) break;			\
+			case 1: l|=((unsigned long)(*((c)++)))<< 8;	\
+				if (--len == 0) break;			\
+			case 2: l|=((unsigned long)(*((c)++)))<<16;	\
+				} }
+/* NOTE the pointer is not incremented at the end of this */
+#define HOST_c2l_p(c,l,n)	{					\
+			l=0; (c)+=n;					\
+			switch (n) {					\
+			case 3: l =((unsigned long)(*(--(c))))<<16;	\
+			case 2: l|=((unsigned long)(*(--(c))))<< 8;	\
+			case 1: l|=((unsigned long)(*(--(c))));		\
+				} }
+#define HOST_l2c(l,c)	(*((c)++)=(unsigned char)(((l)    )&0xff),	\
+			 *((c)++)=(unsigned char)(((l)>> 8)&0xff),	\
+			 *((c)++)=(unsigned char)(((l)>>16)&0xff),	\
+			 *((c)++)=(unsigned char)(((l)>>24)&0xff),	\
+			 l)
+
+#endif
+
+/*
+ * Time for some action:-)
+ */
+
+void HASH_UPDATE (HASH_CTX *c, const void *data_, unsigned long len)
+	{
+	const unsigned char *data=data_;
+	register HASH_LONG * p;
+	register unsigned long l;
+	int sw,sc,ew,ec;
+
+	if (len==0) return;
+
+	l=(c->Nl+(len<<3))&0xffffffffL;
+	/* 95-05-24 eay Fixed a bug with the overflow handling, thanks to
+	 * Wei Dai <weidai@eskimo.com> for pointing it out. */
+	if (l < c->Nl) /* overflow */
+		c->Nh++;
+	c->Nh+=(len>>29);
+	c->Nl=l;
+
+	if (c->num != 0)
+		{
+		p=c->data;
+		sw=c->num>>2;
+		sc=c->num&0x03;
+
+		if ((c->num+len) >= HASH_CBLOCK)
+			{
+			l=p[sw]; HOST_p_c2l(data,l,sc); p[sw++]=l;
+			for (; sw<HASH_LBLOCK; sw++)
+				{
+				HOST_c2l(data,l); p[sw]=l;
+				}
+			HASH_BLOCK_HOST_ORDER (c,p,1);
+			len-=(HASH_CBLOCK-c->num);
+			c->num=0;
+			/* drop through and do the rest */
+			}
+		else
+			{
+			c->num+=len;
+			if ((sc+len) < 4) /* ugly, add char's to a word */
+				{
+				l=p[sw]; HOST_p_c2l_p(data,l,sc,len); p[sw]=l;
+				}
+			else
+				{
+				ew=(c->num>>2);
+				ec=(c->num&0x03);
+				l=p[sw]; HOST_p_c2l(data,l,sc); p[sw++]=l;
+				for (; sw < ew; sw++)
+					{
+					HOST_c2l(data,l); p[sw]=l;
+					}
+				if (ec)
+					{
+					HOST_c2l_p(data,l,ec); p[sw]=l;
+					}
+				}
+			return;
+			}
+		}
+
+	sw=len/HASH_CBLOCK;
+	if (sw > 0)
+		{
+#if defined(HASH_BLOCK_DATA_ORDER_ALIGNED)
+		/*
+		 * Note that HASH_BLOCK_DATA_ORDER_ALIGNED gets defined
+		 * only if sizeof(HASH_LONG)==4.
+		 */
+		if ((((unsigned long)data)%4) == 0)
+			{
+			/* data is properly aligned so that we can cast it: */
+			HASH_BLOCK_DATA_ORDER_ALIGNED (c,(HASH_LONG *)data,sw);
+			sw*=HASH_CBLOCK;
+			data+=sw;
+			len-=sw;
+			}
+		else
+#if !defined(HASH_BLOCK_DATA_ORDER)
+			while (sw--)
+				{
+				memcpy (p=c->data,data,HASH_CBLOCK);
+				HASH_BLOCK_DATA_ORDER_ALIGNED(c,p,1);
+				data+=HASH_CBLOCK;
+				len-=HASH_CBLOCK;
+				}
+#endif
+#endif
+#if defined(HASH_BLOCK_DATA_ORDER)
+			{
+			HASH_BLOCK_DATA_ORDER(c,data,sw);
+			sw*=HASH_CBLOCK;
+			data+=sw;
+			len-=sw;
+			}
+#endif
+		}
+
+	if (len!=0)
+		{
+		p = c->data;
+		c->num = len;
+		ew=len>>2;	/* words to copy */
+		ec=len&0x03;
+		for (; ew; ew--,p++)
+			{
+			HOST_c2l(data,l); *p=l;
+			}
+		HOST_c2l_p(data,l,ec);
+		*p=l;
+		}
+	}
+
+
+void HASH_TRANSFORM (HASH_CTX *c, const unsigned char *data)
+	{
+#if defined(HASH_BLOCK_DATA_ORDER_ALIGNED)
+	if ((((unsigned long)data)%4) == 0)
+		/* data is properly aligned so that we can cast it: */
+		HASH_BLOCK_DATA_ORDER_ALIGNED (c,(HASH_LONG *)data,1);
+	else
+#if !defined(HASH_BLOCK_DATA_ORDER)
+		{
+		memcpy (c->data,data,HASH_CBLOCK);
+		HASH_BLOCK_DATA_ORDER_ALIGNED (c,c->data,1);
+		}
+#endif
+#endif
+#if defined(HASH_BLOCK_DATA_ORDER)
+	HASH_BLOCK_DATA_ORDER (c,data,1);
+#endif
+	}
+
+
+void HASH_FINAL (unsigned char *md, HASH_CTX *c)
+	{
+	register HASH_LONG *p;
+	register unsigned long l;
+	register int i,j;
+	static const unsigned char end[4]={0x80,0x00,0x00,0x00};
+	const unsigned char *cp=end;
+
+	/* c->num should definitly have room for at least one more byte. */
+	p=c->data;
+	i=c->num>>2;
+	j=c->num&0x03;
+
+#if 0
+	/* purify often complains about the following line as an
+	 * Uninitialized Memory Read.  While this can be true, the
+	 * following p_c2l macro will reset l when that case is true.
+	 * This is because j&0x03 contains the number of 'valid' bytes
+	 * already in p[i].  If and only if j&0x03 == 0, the UMR will
+	 * occur but this is also the only time p_c2l will do
+	 * l= *(cp++) instead of l|= *(cp++)
+	 * Many thanks to Alex Tang <altitude@cic.net> for pickup this
+	 * 'potential bug' */
+#ifdef PURIFY
+	if (j==0) p[i]=0; /* Yeah, but that's not the way to fix it:-) */
+#endif
+	l=p[i];
+#else
+	l = (j==0) ? 0 : p[i];
+#endif
+	HOST_p_c2l(cp,l,j); p[i++]=l; /* i is the next 'undefined word' */
+
+	if (i>(HASH_LBLOCK-2)) /* save room for Nl and Nh */
+		{
+		if (i<HASH_LBLOCK) p[i]=0;
+		HASH_BLOCK_HOST_ORDER (c,p,1);
+		i=0;
+		}
+	for (; i<(HASH_LBLOCK-2); i++)
+		p[i]=0;
+
+#if   defined(DATA_ORDER_IS_BIG_ENDIAN)
+	p[HASH_LBLOCK-2]=c->Nh;
+	p[HASH_LBLOCK-1]=c->Nl;
+#elif defined(DATA_ORDER_IS_LITTLE_ENDIAN)
+	p[HASH_LBLOCK-2]=c->Nl;
+	p[HASH_LBLOCK-1]=c->Nh;
+#endif
+	HASH_BLOCK_HOST_ORDER (c,p,1);
+
+#ifndef HASH_MAKE_STRING
+#error "HASH_MAKE_STRING must be defined!"
+#else
+	HASH_MAKE_STRING(c,md);
+#endif
+
+	c->num=0;
+	/* clear stuff, HASH_BLOCK may be leaving some stuff on the stack
+	 * but I'm not worried :-)
+	memset((void *)c,0,sizeof(HASH_CTX));
+	 */
+	}
diff --git a/lib/libcrypto/libaes/Makefile b/lib/libcrypto/libaes/Makefile
new file mode 100644
index 000000000..7e4cff6e8
--- /dev/null
+++ b/lib/libcrypto/libaes/Makefile
@@ -0,0 +1,40 @@
+CFLAGS=-O3 -fomit-frame-pointer -D__KERNEL__  -Wall  -Wcast-qual $(EXTRA_CFLAGS)
+INC=-I../include 
+
+AES_CORE_OBJ:=aes.o
+
+ASM-$(ARCH_ASM):=1
+ASM_X86:=$(ASM-i586)$(ASM-i686)
+ifneq ($(strip $(ASM_X86)),)
+AES_CORE_OBJ:= asm/aes-i586.o
+endif
+
+LIBOBJ := aes_xcbc_mac.o aes_cbc.o $(AES_CORE_OBJ)
+LDLIBS := -laes
+LDFLAGS := -L.
+
+BLIB := libaes.a
+
+L_TARGET := $(BLIB)
+
+.c.o:
+	$(CC) $(CPPFLAGS) $(CFLAGS) $(INC) -c $< -o $@
+
+.S.o:
+	$(CC) $(AFLAGS) -c $< -o $@
+
+$(BLIB): $(LIBOBJ)
+	/bin/rm -f $(BLIB)
+	ar cr $(BLIB) $(LIBOBJ)
+	-if test -s /bin/ranlib; then /bin/ranlib $(BLIB); \
+	else if test -s /usr/bin/ranlib; then /usr/bin/ranlib $(BLIB); \
+	else exit 0; fi; fi
+
+testx: test_main_mac.o $(BLIB)
+	$(CC) -o $@ $^ 
+
+test: test_main.o $(BLIB)
+	$(CC) -o $@ $^ 
+
+clean:
+	rm -f *.[oa] asm/*.o core $(TARGET) test testx
diff --git a/lib/libcrypto/libaes/aes.c b/lib/libcrypto/libaes/aes.c
new file mode 100644
index 000000000..1748119ac
--- /dev/null
+++ b/lib/libcrypto/libaes/aes.c
@@ -0,0 +1,1415 @@
+// I retain copyright in this code but I encourage its free use provided
+// that I don't carry any responsibility for the results. I am especially 
+// happy to see it used in free and open source software. If you do use 
+// it I would appreciate an acknowledgement of its origin in the code or
+// the product that results and I would also appreciate knowing a little
+// about the use to which it is being put. I am grateful to Frank Yellin
+// for some ideas that are used in this implementation.
+//
+// Dr B. R. Gladman <brg@gladman.uk.net> 6th April 2001.
+//
+// This is an implementation of the AES encryption algorithm (Rijndael)
+// designed by Joan Daemen and Vincent Rijmen. This version is designed
+// to provide both fixed and dynamic block and key lengths and can also 
+// run with either big or little endian internal byte order (see aes.h). 
+// It inputs block and key lengths in bytes with the legal values being 
+// 16, 24 and 32.
+
+/*
+ * Modified by Jari Ruusu,  May 1 2001
+ *  - Fixed some compile warnings, code was ok but gcc warned anyway.
+ *  - Changed basic types: byte -> unsigned char, word -> u_int32_t
+ *  - Major name space cleanup: Names visible to outside now begin
+ *    with "aes_" or "AES_". A lot of stuff moved from aes.h to aes.c
+ *  - Removed C++ and DLL support as part of name space cleanup.
+ *  - Eliminated unnecessary recomputation of tables. (actual bug fix)
+ *  - Merged precomputed constant tables to aes.c file.
+ *  - Removed data alignment restrictions for portability reasons.
+ *  - Made block and key lengths accept bit count (128/192/256)
+ *    as well byte count (16/24/32).
+ *  - Removed all error checks. This change also eliminated the need
+ *    to preinitialize the context struct to zero.
+ *  - Removed some totally unused constants.
+ */
+
+#include "aes.h"
+
+// CONFIGURATION OPTIONS (see also aes.h)
+//
+// 1.  Define UNROLL for full loop unrolling in encryption and decryption.
+// 2.  Define PARTIAL_UNROLL to unroll two loops in encryption and decryption.
+// 3.  Define FIXED_TABLES for compiled rather than dynamic tables.
+// 4.  Define FF_TABLES to use tables for field multiplies and inverses.
+//     Do not enable this without understanding stack space requirements.
+// 5.  Define ARRAYS to use arrays to hold the local state block. If this
+//     is not defined, individually declared 32-bit words are used.
+// 6.  Define FAST_VARIABLE if a high speed variable block implementation
+//     is needed (essentially three separate fixed block size code sequences)
+// 7.  Define either ONE_TABLE or FOUR_TABLES for a fast table driven 
+//     version using 1 table (2 kbytes of table space) or 4 tables (8
+//     kbytes of table space) for higher speed.
+// 8.  Define either ONE_LR_TABLE or FOUR_LR_TABLES for a further speed 
+//     increase by using tables for the last rounds but with more table
+//     space (2 or 8 kbytes extra).
+// 9.  If neither ONE_TABLE nor FOUR_TABLES is defined, a compact but 
+//     slower version is provided.
+// 10. If fast decryption key scheduling is needed define ONE_IM_TABLE
+//     or FOUR_IM_TABLES for higher speed (2 or 8 kbytes extra).
+
+#define UNROLL
+//#define PARTIAL_UNROLL
+
+#define FIXED_TABLES
+//#define FF_TABLES
+//#define ARRAYS
+#define FAST_VARIABLE
+
+//#define ONE_TABLE
+#define FOUR_TABLES
+
+//#define ONE_LR_TABLE
+#define FOUR_LR_TABLES
+
+//#define ONE_IM_TABLE
+#define FOUR_IM_TABLES
+
+#if defined(UNROLL) && defined (PARTIAL_UNROLL)
+#error both UNROLL and PARTIAL_UNROLL are defined
+#endif
+
+#if defined(ONE_TABLE) && defined (FOUR_TABLES)
+#error both ONE_TABLE and FOUR_TABLES are defined
+#endif
+
+#if defined(ONE_LR_TABLE) && defined (FOUR_LR_TABLES)
+#error both ONE_LR_TABLE and FOUR_LR_TABLES are defined
+#endif
+
+#if defined(ONE_IM_TABLE) && defined (FOUR_IM_TABLES)
+#error both ONE_IM_TABLE and FOUR_IM_TABLES are defined
+#endif
+
+#if defined(AES_BLOCK_SIZE) && AES_BLOCK_SIZE != 16 && AES_BLOCK_SIZE != 24 && AES_BLOCK_SIZE != 32
+#error an illegal block size has been specified
+#endif  
+
+// upr(x,n): rotates bytes within words by n positions, moving bytes 
+// to higher index positions with wrap around into low positions
+// ups(x,n): moves bytes by n positions to higher index positions in 
+// words but without wrap around
+// bval(x,n): extracts a byte from a word
+
+#define upr(x,n)        (((x) << 8 * (n)) | ((x) >> (32 - 8 * (n))))
+#define ups(x,n)        ((x) << 8 * (n))
+#define bval(x,n)       ((unsigned char)((x) >> 8 * (n)))
+#define bytes2word(b0, b1, b2, b3)  \
+        ((u_int32_t)(b3) << 24 | (u_int32_t)(b2) << 16 | (u_int32_t)(b1) << 8 | (b0))
+
+
+/* little endian processor without data alignment restrictions: AES_LE_OK */
+/* original code: i386 */
+#if defined(i386) || defined(_I386) || defined(__i386__) || defined(__i386) 
+#define	AES_LE_OK 1
+/* added (tested): alpha  --jjo */
+#elif defined(__alpha__)|| defined (__alpha)
+#define AES_LE_OK 1
+/* added (tested): ia64  --jjo */
+#elif defined(__ia64__)|| defined (__ia64)
+#define AES_LE_OK 1
+#endif
+
+#ifdef AES_LE_OK
+/* little endian processor without data alignment restrictions */
+#define word_in(x)      *(u_int32_t*)(x)
+#define const_word_in(x)      *(const u_int32_t*)(x)
+#define word_out(x,v)   *(u_int32_t*)(x) = (v)
+#define const_word_out(x,v)   *(const u_int32_t*)(x) = (v)
+#else
+/* slower but generic big endian or with data alignment restrictions */
+/* some additional "const" touches to stop "gcc -Wcast-qual" complains --jjo */
+#define word_in(x)      ((u_int32_t)(((unsigned char *)(x))[0])|((u_int32_t)(((unsigned char *)(x))[1])<<8)|((u_int32_t)(((unsigned char *)(x))[2])<<16)|((u_int32_t)(((unsigned char *)(x))[3])<<24))
+#define const_word_in(x)      ((const u_int32_t)(((const unsigned char *)(x))[0])|((const u_int32_t)(((const unsigned char *)(x))[1])<<8)|((const u_int32_t)(((const unsigned char *)(x))[2])<<16)|((const u_int32_t)(((const unsigned char *)(x))[3])<<24))
+#define word_out(x,v)   ((unsigned char *)(x))[0]=(v),((unsigned char *)(x))[1]=((v)>>8),((unsigned char *)(x))[2]=((v)>>16),((unsigned char *)(x))[3]=((v)>>24)
+#define const_word_out(x,v)   ((const unsigned char *)(x))[0]=(v),((const unsigned char *)(x))[1]=((v)>>8),((const unsigned char *)(x))[2]=((v)>>16),((const unsigned char *)(x))[3]=((v)>>24)
+#endif
+
+// Disable at least some poor combinations of options
+
+#if !defined(ONE_TABLE) && !defined(FOUR_TABLES)
+#define FIXED_TABLES
+#undef  UNROLL
+#undef  ONE_LR_TABLE
+#undef  FOUR_LR_TABLES
+#undef  ONE_IM_TABLE
+#undef  FOUR_IM_TABLES
+#elif !defined(FOUR_TABLES)
+#ifdef  FOUR_LR_TABLES
+#undef  FOUR_LR_TABLES
+#define ONE_LR_TABLE
+#endif
+#ifdef  FOUR_IM_TABLES
+#undef  FOUR_IM_TABLES
+#define ONE_IM_TABLE
+#endif
+#elif !defined(AES_BLOCK_SIZE)
+#if defined(UNROLL)
+#define PARTIAL_UNROLL
+#undef UNROLL
+#endif
+#endif
+
+// the finite field modular polynomial and elements
+
+#define ff_poly 0x011b
+#define ff_hi   0x80
+
+// multiply four bytes in GF(2^8) by 'x' {02} in parallel
+
+#define m1  0x80808080
+#define m2  0x7f7f7f7f
+#define m3  0x0000001b
+#define FFmulX(x)  ((((x) & m2) << 1) ^ ((((x) & m1) >> 7) * m3))
+
+// The following defines provide alternative definitions of FFmulX that might
+// give improved performance if a fast 32-bit multiply is not available. Note
+// that a temporary variable u needs to be defined where FFmulX is used.
+
+// #define FFmulX(x) (u = (x) & m1, u |= (u >> 1), ((x) & m2) << 1) ^ ((u >> 3) | (u >> 6)) 
+// #define m4  0x1b1b1b1b
+// #define FFmulX(x) (u = (x) & m1, ((x) & m2) << 1) ^ ((u - (u >> 7)) & m4) 
+
+// perform column mix operation on four bytes in parallel
+
+#define fwd_mcol(x) (f2 = FFmulX(x), f2 ^ upr(x ^ f2,3) ^ upr(x,2) ^ upr(x,1))
+
+#if defined(FIXED_TABLES)
+
+// the S-Box table
+
+static const unsigned char s_box[256] =
+{
+    0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5,
+    0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
+    0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0,
+    0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
+    0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc,
+    0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,
+    0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a,
+    0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75,
+    0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0,
+    0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84,
+    0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b,
+    0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf,
+    0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85,
+    0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8,
+    0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5,
+    0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2,
+    0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17,
+    0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73,
+    0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88,
+    0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb,
+    0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c,
+    0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79,
+    0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9,
+    0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08,
+    0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6,
+    0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a,
+    0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e,
+    0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e,
+    0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94,
+    0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf,
+    0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68,
+    0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+};
+
+// the inverse S-Box table
+
+static const unsigned char inv_s_box[256] =
+{
+    0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38,
+    0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
+    0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87,
+    0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
+    0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d,
+    0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
+    0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2,
+    0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
+    0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16,
+    0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
+    0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda,
+    0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
+    0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a,
+    0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
+    0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02,
+    0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
+    0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea,
+    0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
+    0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85,
+    0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
+    0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89,
+    0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
+    0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20,
+    0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
+    0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31,
+    0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
+    0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d,
+    0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
+    0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0,
+    0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
+    0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26,
+    0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+};
+
+#define w0(p)          0x000000##p
+
+// Number of elements required in this table for different
+// block and key lengths is:
+//
+// Nk =      4  6  8
+//        ----------
+// Nb = 4 | 10  8  7
+//      6 | 19 12 11
+//      8 | 29 19 14
+//
+// this table can be a table of bytes if the key schedule
+// code is adjusted accordingly
+
+static const u_int32_t rcon_tab[29] =
+{
+    w0(01), w0(02), w0(04), w0(08),
+    w0(10), w0(20), w0(40), w0(80),
+    w0(1b), w0(36), w0(6c), w0(d8),
+    w0(ab), w0(4d), w0(9a), w0(2f),
+    w0(5e), w0(bc), w0(63), w0(c6),
+    w0(97), w0(35), w0(6a), w0(d4),
+    w0(b3), w0(7d), w0(fa), w0(ef),
+    w0(c5)
+};
+
+#undef  w0
+
+#define r0(p,q,r,s) 0x##p##q##r##s
+#define r1(p,q,r,s) 0x##q##r##s##p
+#define r2(p,q,r,s) 0x##r##s##p##q
+#define r3(p,q,r,s) 0x##s##p##q##r
+#define w0(p)          0x000000##p
+#define w1(p)        0x0000##p##00
+#define w2(p)        0x00##p##0000
+#define w3(p)        0x##p##000000
+
+#if defined(FIXED_TABLES) && (defined(ONE_TABLE) || defined(FOUR_TABLES)) 
+
+//  data for forward tables (other than last round)
+
+#define f_table \
+    r(a5,63,63,c6), r(84,7c,7c,f8), r(99,77,77,ee), r(8d,7b,7b,f6),\
+    r(0d,f2,f2,ff), r(bd,6b,6b,d6), r(b1,6f,6f,de), r(54,c5,c5,91),\
+    r(50,30,30,60), r(03,01,01,02), r(a9,67,67,ce), r(7d,2b,2b,56),\
+    r(19,fe,fe,e7), r(62,d7,d7,b5), r(e6,ab,ab,4d), r(9a,76,76,ec),\
+    r(45,ca,ca,8f), r(9d,82,82,1f), r(40,c9,c9,89), r(87,7d,7d,fa),\
+    r(15,fa,fa,ef), r(eb,59,59,b2), r(c9,47,47,8e), r(0b,f0,f0,fb),\
+    r(ec,ad,ad,41), r(67,d4,d4,b3), r(fd,a2,a2,5f), r(ea,af,af,45),\
+    r(bf,9c,9c,23), r(f7,a4,a4,53), r(96,72,72,e4), r(5b,c0,c0,9b),\
+    r(c2,b7,b7,75), r(1c,fd,fd,e1), r(ae,93,93,3d), r(6a,26,26,4c),\
+    r(5a,36,36,6c), r(41,3f,3f,7e), r(02,f7,f7,f5), r(4f,cc,cc,83),\
+    r(5c,34,34,68), r(f4,a5,a5,51), r(34,e5,e5,d1), r(08,f1,f1,f9),\
+    r(93,71,71,e2), r(73,d8,d8,ab), r(53,31,31,62), r(3f,15,15,2a),\
+    r(0c,04,04,08), r(52,c7,c7,95), r(65,23,23,46), r(5e,c3,c3,9d),\
+    r(28,18,18,30), r(a1,96,96,37), r(0f,05,05,0a), r(b5,9a,9a,2f),\
+    r(09,07,07,0e), r(36,12,12,24), r(9b,80,80,1b), r(3d,e2,e2,df),\
+    r(26,eb,eb,cd), r(69,27,27,4e), r(cd,b2,b2,7f), r(9f,75,75,ea),\
+    r(1b,09,09,12), r(9e,83,83,1d), r(74,2c,2c,58), r(2e,1a,1a,34),\
+    r(2d,1b,1b,36), r(b2,6e,6e,dc), r(ee,5a,5a,b4), r(fb,a0,a0,5b),\
+    r(f6,52,52,a4), r(4d,3b,3b,76), r(61,d6,d6,b7), r(ce,b3,b3,7d),\
+    r(7b,29,29,52), r(3e,e3,e3,dd), r(71,2f,2f,5e), r(97,84,84,13),\
+    r(f5,53,53,a6), r(68,d1,d1,b9), r(00,00,00,00), r(2c,ed,ed,c1),\
+    r(60,20,20,40), r(1f,fc,fc,e3), r(c8,b1,b1,79), r(ed,5b,5b,b6),\
+    r(be,6a,6a,d4), r(46,cb,cb,8d), r(d9,be,be,67), r(4b,39,39,72),\
+    r(de,4a,4a,94), r(d4,4c,4c,98), r(e8,58,58,b0), r(4a,cf,cf,85),\
+    r(6b,d0,d0,bb), r(2a,ef,ef,c5), r(e5,aa,aa,4f), r(16,fb,fb,ed),\
+    r(c5,43,43,86), r(d7,4d,4d,9a), r(55,33,33,66), r(94,85,85,11),\
+    r(cf,45,45,8a), r(10,f9,f9,e9), r(06,02,02,04), r(81,7f,7f,fe),\
+    r(f0,50,50,a0), r(44,3c,3c,78), r(ba,9f,9f,25), r(e3,a8,a8,4b),\
+    r(f3,51,51,a2), r(fe,a3,a3,5d), r(c0,40,40,80), r(8a,8f,8f,05),\
+    r(ad,92,92,3f), r(bc,9d,9d,21), r(48,38,38,70), r(04,f5,f5,f1),\
+    r(df,bc,bc,63), r(c1,b6,b6,77), r(75,da,da,af), r(63,21,21,42),\
+    r(30,10,10,20), r(1a,ff,ff,e5), r(0e,f3,f3,fd), r(6d,d2,d2,bf),\
+    r(4c,cd,cd,81), r(14,0c,0c,18), r(35,13,13,26), r(2f,ec,ec,c3),\
+    r(e1,5f,5f,be), r(a2,97,97,35), r(cc,44,44,88), r(39,17,17,2e),\
+    r(57,c4,c4,93), r(f2,a7,a7,55), r(82,7e,7e,fc), r(47,3d,3d,7a),\
+    r(ac,64,64,c8), r(e7,5d,5d,ba), r(2b,19,19,32), r(95,73,73,e6),\
+    r(a0,60,60,c0), r(98,81,81,19), r(d1,4f,4f,9e), r(7f,dc,dc,a3),\
+    r(66,22,22,44), r(7e,2a,2a,54), r(ab,90,90,3b), r(83,88,88,0b),\
+    r(ca,46,46,8c), r(29,ee,ee,c7), r(d3,b8,b8,6b), r(3c,14,14,28),\
+    r(79,de,de,a7), r(e2,5e,5e,bc), r(1d,0b,0b,16), r(76,db,db,ad),\
+    r(3b,e0,e0,db), r(56,32,32,64), r(4e,3a,3a,74), r(1e,0a,0a,14),\
+    r(db,49,49,92), r(0a,06,06,0c), r(6c,24,24,48), r(e4,5c,5c,b8),\
+    r(5d,c2,c2,9f), r(6e,d3,d3,bd), r(ef,ac,ac,43), r(a6,62,62,c4),\
+    r(a8,91,91,39), r(a4,95,95,31), r(37,e4,e4,d3), r(8b,79,79,f2),\
+    r(32,e7,e7,d5), r(43,c8,c8,8b), r(59,37,37,6e), r(b7,6d,6d,da),\
+    r(8c,8d,8d,01), r(64,d5,d5,b1), r(d2,4e,4e,9c), r(e0,a9,a9,49),\
+    r(b4,6c,6c,d8), r(fa,56,56,ac), r(07,f4,f4,f3), r(25,ea,ea,cf),\
+    r(af,65,65,ca), r(8e,7a,7a,f4), r(e9,ae,ae,47), r(18,08,08,10),\
+    r(d5,ba,ba,6f), r(88,78,78,f0), r(6f,25,25,4a), r(72,2e,2e,5c),\
+    r(24,1c,1c,38), r(f1,a6,a6,57), r(c7,b4,b4,73), r(51,c6,c6,97),\
+    r(23,e8,e8,cb), r(7c,dd,dd,a1), r(9c,74,74,e8), r(21,1f,1f,3e),\
+    r(dd,4b,4b,96), r(dc,bd,bd,61), r(86,8b,8b,0d), r(85,8a,8a,0f),\
+    r(90,70,70,e0), r(42,3e,3e,7c), r(c4,b5,b5,71), r(aa,66,66,cc),\
+    r(d8,48,48,90), r(05,03,03,06), r(01,f6,f6,f7), r(12,0e,0e,1c),\
+    r(a3,61,61,c2), r(5f,35,35,6a), r(f9,57,57,ae), r(d0,b9,b9,69),\
+    r(91,86,86,17), r(58,c1,c1,99), r(27,1d,1d,3a), r(b9,9e,9e,27),\
+    r(38,e1,e1,d9), r(13,f8,f8,eb), r(b3,98,98,2b), r(33,11,11,22),\
+    r(bb,69,69,d2), r(70,d9,d9,a9), r(89,8e,8e,07), r(a7,94,94,33),\
+    r(b6,9b,9b,2d), r(22,1e,1e,3c), r(92,87,87,15), r(20,e9,e9,c9),\
+    r(49,ce,ce,87), r(ff,55,55,aa), r(78,28,28,50), r(7a,df,df,a5),\
+    r(8f,8c,8c,03), r(f8,a1,a1,59), r(80,89,89,09), r(17,0d,0d,1a),\
+    r(da,bf,bf,65), r(31,e6,e6,d7), r(c6,42,42,84), r(b8,68,68,d0),\
+    r(c3,41,41,82), r(b0,99,99,29), r(77,2d,2d,5a), r(11,0f,0f,1e),\
+    r(cb,b0,b0,7b), r(fc,54,54,a8), r(d6,bb,bb,6d), r(3a,16,16,2c)
+
+//  data for inverse tables (other than last round)
+
+#define i_table \
+    r(50,a7,f4,51), r(53,65,41,7e), r(c3,a4,17,1a), r(96,5e,27,3a),\
+    r(cb,6b,ab,3b), r(f1,45,9d,1f), r(ab,58,fa,ac), r(93,03,e3,4b),\
+    r(55,fa,30,20), r(f6,6d,76,ad), r(91,76,cc,88), r(25,4c,02,f5),\
+    r(fc,d7,e5,4f), r(d7,cb,2a,c5), r(80,44,35,26), r(8f,a3,62,b5),\
+    r(49,5a,b1,de), r(67,1b,ba,25), r(98,0e,ea,45), r(e1,c0,fe,5d),\
+    r(02,75,2f,c3), r(12,f0,4c,81), r(a3,97,46,8d), r(c6,f9,d3,6b),\
+    r(e7,5f,8f,03), r(95,9c,92,15), r(eb,7a,6d,bf), r(da,59,52,95),\
+    r(2d,83,be,d4), r(d3,21,74,58), r(29,69,e0,49), r(44,c8,c9,8e),\
+    r(6a,89,c2,75), r(78,79,8e,f4), r(6b,3e,58,99), r(dd,71,b9,27),\
+    r(b6,4f,e1,be), r(17,ad,88,f0), r(66,ac,20,c9), r(b4,3a,ce,7d),\
+    r(18,4a,df,63), r(82,31,1a,e5), r(60,33,51,97), r(45,7f,53,62),\
+    r(e0,77,64,b1), r(84,ae,6b,bb), r(1c,a0,81,fe), r(94,2b,08,f9),\
+    r(58,68,48,70), r(19,fd,45,8f), r(87,6c,de,94), r(b7,f8,7b,52),\
+    r(23,d3,73,ab), r(e2,02,4b,72), r(57,8f,1f,e3), r(2a,ab,55,66),\
+    r(07,28,eb,b2), r(03,c2,b5,2f), r(9a,7b,c5,86), r(a5,08,37,d3),\
+    r(f2,87,28,30), r(b2,a5,bf,23), r(ba,6a,03,02), r(5c,82,16,ed),\
+    r(2b,1c,cf,8a), r(92,b4,79,a7), r(f0,f2,07,f3), r(a1,e2,69,4e),\
+    r(cd,f4,da,65), r(d5,be,05,06), r(1f,62,34,d1), r(8a,fe,a6,c4),\
+    r(9d,53,2e,34), r(a0,55,f3,a2), r(32,e1,8a,05), r(75,eb,f6,a4),\
+    r(39,ec,83,0b), r(aa,ef,60,40), r(06,9f,71,5e), r(51,10,6e,bd),\
+    r(f9,8a,21,3e), r(3d,06,dd,96), r(ae,05,3e,dd), r(46,bd,e6,4d),\
+    r(b5,8d,54,91), r(05,5d,c4,71), r(6f,d4,06,04), r(ff,15,50,60),\
+    r(24,fb,98,19), r(97,e9,bd,d6), r(cc,43,40,89), r(77,9e,d9,67),\
+    r(bd,42,e8,b0), r(88,8b,89,07), r(38,5b,19,e7), r(db,ee,c8,79),\
+    r(47,0a,7c,a1), r(e9,0f,42,7c), r(c9,1e,84,f8), r(00,00,00,00),\
+    r(83,86,80,09), r(48,ed,2b,32), r(ac,70,11,1e), r(4e,72,5a,6c),\
+    r(fb,ff,0e,fd), r(56,38,85,0f), r(1e,d5,ae,3d), r(27,39,2d,36),\
+    r(64,d9,0f,0a), r(21,a6,5c,68), r(d1,54,5b,9b), r(3a,2e,36,24),\
+    r(b1,67,0a,0c), r(0f,e7,57,93), r(d2,96,ee,b4), r(9e,91,9b,1b),\
+    r(4f,c5,c0,80), r(a2,20,dc,61), r(69,4b,77,5a), r(16,1a,12,1c),\
+    r(0a,ba,93,e2), r(e5,2a,a0,c0), r(43,e0,22,3c), r(1d,17,1b,12),\
+    r(0b,0d,09,0e), r(ad,c7,8b,f2), r(b9,a8,b6,2d), r(c8,a9,1e,14),\
+    r(85,19,f1,57), r(4c,07,75,af), r(bb,dd,99,ee), r(fd,60,7f,a3),\
+    r(9f,26,01,f7), r(bc,f5,72,5c), r(c5,3b,66,44), r(34,7e,fb,5b),\
+    r(76,29,43,8b), r(dc,c6,23,cb), r(68,fc,ed,b6), r(63,f1,e4,b8),\
+    r(ca,dc,31,d7), r(10,85,63,42), r(40,22,97,13), r(20,11,c6,84),\
+    r(7d,24,4a,85), r(f8,3d,bb,d2), r(11,32,f9,ae), r(6d,a1,29,c7),\
+    r(4b,2f,9e,1d), r(f3,30,b2,dc), r(ec,52,86,0d), r(d0,e3,c1,77),\
+    r(6c,16,b3,2b), r(99,b9,70,a9), r(fa,48,94,11), r(22,64,e9,47),\
+    r(c4,8c,fc,a8), r(1a,3f,f0,a0), r(d8,2c,7d,56), r(ef,90,33,22),\
+    r(c7,4e,49,87), r(c1,d1,38,d9), r(fe,a2,ca,8c), r(36,0b,d4,98),\
+    r(cf,81,f5,a6), r(28,de,7a,a5), r(26,8e,b7,da), r(a4,bf,ad,3f),\
+    r(e4,9d,3a,2c), r(0d,92,78,50), r(9b,cc,5f,6a), r(62,46,7e,54),\
+    r(c2,13,8d,f6), r(e8,b8,d8,90), r(5e,f7,39,2e), r(f5,af,c3,82),\
+    r(be,80,5d,9f), r(7c,93,d0,69), r(a9,2d,d5,6f), r(b3,12,25,cf),\
+    r(3b,99,ac,c8), r(a7,7d,18,10), r(6e,63,9c,e8), r(7b,bb,3b,db),\
+    r(09,78,26,cd), r(f4,18,59,6e), r(01,b7,9a,ec), r(a8,9a,4f,83),\
+    r(65,6e,95,e6), r(7e,e6,ff,aa), r(08,cf,bc,21), r(e6,e8,15,ef),\
+    r(d9,9b,e7,ba), r(ce,36,6f,4a), r(d4,09,9f,ea), r(d6,7c,b0,29),\
+    r(af,b2,a4,31), r(31,23,3f,2a), r(30,94,a5,c6), r(c0,66,a2,35),\
+    r(37,bc,4e,74), r(a6,ca,82,fc), r(b0,d0,90,e0), r(15,d8,a7,33),\
+    r(4a,98,04,f1), r(f7,da,ec,41), r(0e,50,cd,7f), r(2f,f6,91,17),\
+    r(8d,d6,4d,76), r(4d,b0,ef,43), r(54,4d,aa,cc), r(df,04,96,e4),\
+    r(e3,b5,d1,9e), r(1b,88,6a,4c), r(b8,1f,2c,c1), r(7f,51,65,46),\
+    r(04,ea,5e,9d), r(5d,35,8c,01), r(73,74,87,fa), r(2e,41,0b,fb),\
+    r(5a,1d,67,b3), r(52,d2,db,92), r(33,56,10,e9), r(13,47,d6,6d),\
+    r(8c,61,d7,9a), r(7a,0c,a1,37), r(8e,14,f8,59), r(89,3c,13,eb),\
+    r(ee,27,a9,ce), r(35,c9,61,b7), r(ed,e5,1c,e1), r(3c,b1,47,7a),\
+    r(59,df,d2,9c), r(3f,73,f2,55), r(79,ce,14,18), r(bf,37,c7,73),\
+    r(ea,cd,f7,53), r(5b,aa,fd,5f), r(14,6f,3d,df), r(86,db,44,78),\
+    r(81,f3,af,ca), r(3e,c4,68,b9), r(2c,34,24,38), r(5f,40,a3,c2),\
+    r(72,c3,1d,16), r(0c,25,e2,bc), r(8b,49,3c,28), r(41,95,0d,ff),\
+    r(71,01,a8,39), r(de,b3,0c,08), r(9c,e4,b4,d8), r(90,c1,56,64),\
+    r(61,84,cb,7b), r(70,b6,32,d5), r(74,5c,6c,48), r(42,57,b8,d0)
+
+// generate the required tables in the desired endian format
+
+#undef  r
+#define r   r0
+
+#if defined(ONE_TABLE)
+static const u_int32_t ft_tab[256] =
+    {   f_table };
+#elif defined(FOUR_TABLES)
+static const u_int32_t ft_tab[4][256] =
+{   {   f_table },
+#undef  r
+#define r   r1
+    {   f_table },
+#undef  r
+#define r   r2
+    {   f_table },
+#undef  r
+#define r   r3
+    {   f_table }
+};
+#endif
+
+#undef  r
+#define r   r0
+#if defined(ONE_TABLE)
+static const u_int32_t it_tab[256] =
+    {   i_table };
+#elif defined(FOUR_TABLES)
+static const u_int32_t it_tab[4][256] =
+{   {   i_table },
+#undef  r
+#define r   r1
+    {   i_table },
+#undef  r
+#define r   r2
+    {   i_table },
+#undef  r
+#define r   r3
+    {   i_table }
+};
+#endif
+
+#endif
+
+#if defined(FIXED_TABLES) && (defined(ONE_LR_TABLE) || defined(FOUR_LR_TABLES)) 
+
+//  data for inverse tables (last round)
+
+#define li_table    \
+    w(52), w(09), w(6a), w(d5), w(30), w(36), w(a5), w(38),\
+    w(bf), w(40), w(a3), w(9e), w(81), w(f3), w(d7), w(fb),\
+    w(7c), w(e3), w(39), w(82), w(9b), w(2f), w(ff), w(87),\
+    w(34), w(8e), w(43), w(44), w(c4), w(de), w(e9), w(cb),\
+    w(54), w(7b), w(94), w(32), w(a6), w(c2), w(23), w(3d),\
+    w(ee), w(4c), w(95), w(0b), w(42), w(fa), w(c3), w(4e),\
+    w(08), w(2e), w(a1), w(66), w(28), w(d9), w(24), w(b2),\
+    w(76), w(5b), w(a2), w(49), w(6d), w(8b), w(d1), w(25),\
+    w(72), w(f8), w(f6), w(64), w(86), w(68), w(98), w(16),\
+    w(d4), w(a4), w(5c), w(cc), w(5d), w(65), w(b6), w(92),\
+    w(6c), w(70), w(48), w(50), w(fd), w(ed), w(b9), w(da),\
+    w(5e), w(15), w(46), w(57), w(a7), w(8d), w(9d), w(84),\
+    w(90), w(d8), w(ab), w(00), w(8c), w(bc), w(d3), w(0a),\
+    w(f7), w(e4), w(58), w(05), w(b8), w(b3), w(45), w(06),\
+    w(d0), w(2c), w(1e), w(8f), w(ca), w(3f), w(0f), w(02),\
+    w(c1), w(af), w(bd), w(03), w(01), w(13), w(8a), w(6b),\
+    w(3a), w(91), w(11), w(41), w(4f), w(67), w(dc), w(ea),\
+    w(97), w(f2), w(cf), w(ce), w(f0), w(b4), w(e6), w(73),\
+    w(96), w(ac), w(74), w(22), w(e7), w(ad), w(35), w(85),\
+    w(e2), w(f9), w(37), w(e8), w(1c), w(75), w(df), w(6e),\
+    w(47), w(f1), w(1a), w(71), w(1d), w(29), w(c5), w(89),\
+    w(6f), w(b7), w(62), w(0e), w(aa), w(18), w(be), w(1b),\
+    w(fc), w(56), w(3e), w(4b), w(c6), w(d2), w(79), w(20),\
+    w(9a), w(db), w(c0), w(fe), w(78), w(cd), w(5a), w(f4),\
+    w(1f), w(dd), w(a8), w(33), w(88), w(07), w(c7), w(31),\
+    w(b1), w(12), w(10), w(59), w(27), w(80), w(ec), w(5f),\
+    w(60), w(51), w(7f), w(a9), w(19), w(b5), w(4a), w(0d),\
+    w(2d), w(e5), w(7a), w(9f), w(93), w(c9), w(9c), w(ef),\
+    w(a0), w(e0), w(3b), w(4d), w(ae), w(2a), w(f5), w(b0),\
+    w(c8), w(eb), w(bb), w(3c), w(83), w(53), w(99), w(61),\
+    w(17), w(2b), w(04), w(7e), w(ba), w(77), w(d6), w(26),\
+    w(e1), w(69), w(14), w(63), w(55), w(21), w(0c), w(7d),
+
+// generate the required tables in the desired endian format
+
+#undef  r
+#define r(p,q,r,s)  w0(q)
+#if defined(ONE_LR_TABLE)
+static const u_int32_t fl_tab[256] =
+    {   f_table     };
+#elif defined(FOUR_LR_TABLES)
+static const u_int32_t fl_tab[4][256] =
+{   {   f_table    },
+#undef  r
+#define r(p,q,r,s)   w1(q)
+    {   f_table    },
+#undef  r
+#define r(p,q,r,s)   w2(q)
+    {   f_table    },
+#undef  r
+#define r(p,q,r,s)   w3(q)
+    {   f_table    }
+};
+#endif
+
+#undef  w
+#define w   w0
+#if defined(ONE_LR_TABLE)
+static const u_int32_t il_tab[256] =
+    {   li_table    };
+#elif defined(FOUR_LR_TABLES)
+static const u_int32_t il_tab[4][256] =
+{   {   li_table    },
+#undef  w
+#define w   w1
+    {   li_table    },
+#undef  w
+#define w   w2
+    {   li_table    },
+#undef  w
+#define w   w3
+    {   li_table    }
+};
+#endif
+
+#endif
+
+#if defined(FIXED_TABLES) && (defined(ONE_IM_TABLE) || defined(FOUR_IM_TABLES)) 
+
+#define m_table \
+    r(00,00,00,00), r(0b,0d,09,0e), r(16,1a,12,1c), r(1d,17,1b,12),\
+    r(2c,34,24,38), r(27,39,2d,36), r(3a,2e,36,24), r(31,23,3f,2a),\
+    r(58,68,48,70), r(53,65,41,7e), r(4e,72,5a,6c), r(45,7f,53,62),\
+    r(74,5c,6c,48), r(7f,51,65,46), r(62,46,7e,54), r(69,4b,77,5a),\
+    r(b0,d0,90,e0), r(bb,dd,99,ee), r(a6,ca,82,fc), r(ad,c7,8b,f2),\
+    r(9c,e4,b4,d8), r(97,e9,bd,d6), r(8a,fe,a6,c4), r(81,f3,af,ca),\
+    r(e8,b8,d8,90), r(e3,b5,d1,9e), r(fe,a2,ca,8c), r(f5,af,c3,82),\
+    r(c4,8c,fc,a8), r(cf,81,f5,a6), r(d2,96,ee,b4), r(d9,9b,e7,ba),\
+    r(7b,bb,3b,db), r(70,b6,32,d5), r(6d,a1,29,c7), r(66,ac,20,c9),\
+    r(57,8f,1f,e3), r(5c,82,16,ed), r(41,95,0d,ff), r(4a,98,04,f1),\
+    r(23,d3,73,ab), r(28,de,7a,a5), r(35,c9,61,b7), r(3e,c4,68,b9),\
+    r(0f,e7,57,93), r(04,ea,5e,9d), r(19,fd,45,8f), r(12,f0,4c,81),\
+    r(cb,6b,ab,3b), r(c0,66,a2,35), r(dd,71,b9,27), r(d6,7c,b0,29),\
+    r(e7,5f,8f,03), r(ec,52,86,0d), r(f1,45,9d,1f), r(fa,48,94,11),\
+    r(93,03,e3,4b), r(98,0e,ea,45), r(85,19,f1,57), r(8e,14,f8,59),\
+    r(bf,37,c7,73), r(b4,3a,ce,7d), r(a9,2d,d5,6f), r(a2,20,dc,61),\
+    r(f6,6d,76,ad), r(fd,60,7f,a3), r(e0,77,64,b1), r(eb,7a,6d,bf),\
+    r(da,59,52,95), r(d1,54,5b,9b), r(cc,43,40,89), r(c7,4e,49,87),\
+    r(ae,05,3e,dd), r(a5,08,37,d3), r(b8,1f,2c,c1), r(b3,12,25,cf),\
+    r(82,31,1a,e5), r(89,3c,13,eb), r(94,2b,08,f9), r(9f,26,01,f7),\
+    r(46,bd,e6,4d), r(4d,b0,ef,43), r(50,a7,f4,51), r(5b,aa,fd,5f),\
+    r(6a,89,c2,75), r(61,84,cb,7b), r(7c,93,d0,69), r(77,9e,d9,67),\
+    r(1e,d5,ae,3d), r(15,d8,a7,33), r(08,cf,bc,21), r(03,c2,b5,2f),\
+    r(32,e1,8a,05), r(39,ec,83,0b), r(24,fb,98,19), r(2f,f6,91,17),\
+    r(8d,d6,4d,76), r(86,db,44,78), r(9b,cc,5f,6a), r(90,c1,56,64),\
+    r(a1,e2,69,4e), r(aa,ef,60,40), r(b7,f8,7b,52), r(bc,f5,72,5c),\
+    r(d5,be,05,06), r(de,b3,0c,08), r(c3,a4,17,1a), r(c8,a9,1e,14),\
+    r(f9,8a,21,3e), r(f2,87,28,30), r(ef,90,33,22), r(e4,9d,3a,2c),\
+    r(3d,06,dd,96), r(36,0b,d4,98), r(2b,1c,cf,8a), r(20,11,c6,84),\
+    r(11,32,f9,ae), r(1a,3f,f0,a0), r(07,28,eb,b2), r(0c,25,e2,bc),\
+    r(65,6e,95,e6), r(6e,63,9c,e8), r(73,74,87,fa), r(78,79,8e,f4),\
+    r(49,5a,b1,de), r(42,57,b8,d0), r(5f,40,a3,c2), r(54,4d,aa,cc),\
+    r(f7,da,ec,41), r(fc,d7,e5,4f), r(e1,c0,fe,5d), r(ea,cd,f7,53),\
+    r(db,ee,c8,79), r(d0,e3,c1,77), r(cd,f4,da,65), r(c6,f9,d3,6b),\
+    r(af,b2,a4,31), r(a4,bf,ad,3f), r(b9,a8,b6,2d), r(b2,a5,bf,23),\
+    r(83,86,80,09), r(88,8b,89,07), r(95,9c,92,15), r(9e,91,9b,1b),\
+    r(47,0a,7c,a1), r(4c,07,75,af), r(51,10,6e,bd), r(5a,1d,67,b3),\
+    r(6b,3e,58,99), r(60,33,51,97), r(7d,24,4a,85), r(76,29,43,8b),\
+    r(1f,62,34,d1), r(14,6f,3d,df), r(09,78,26,cd), r(02,75,2f,c3),\
+    r(33,56,10,e9), r(38,5b,19,e7), r(25,4c,02,f5), r(2e,41,0b,fb),\
+    r(8c,61,d7,9a), r(87,6c,de,94), r(9a,7b,c5,86), r(91,76,cc,88),\
+    r(a0,55,f3,a2), r(ab,58,fa,ac), r(b6,4f,e1,be), r(bd,42,e8,b0),\
+    r(d4,09,9f,ea), r(df,04,96,e4), r(c2,13,8d,f6), r(c9,1e,84,f8),\
+    r(f8,3d,bb,d2), r(f3,30,b2,dc), r(ee,27,a9,ce), r(e5,2a,a0,c0),\
+    r(3c,b1,47,7a), r(37,bc,4e,74), r(2a,ab,55,66), r(21,a6,5c,68),\
+    r(10,85,63,42), r(1b,88,6a,4c), r(06,9f,71,5e), r(0d,92,78,50),\
+    r(64,d9,0f,0a), r(6f,d4,06,04), r(72,c3,1d,16), r(79,ce,14,18),\
+    r(48,ed,2b,32), r(43,e0,22,3c), r(5e,f7,39,2e), r(55,fa,30,20),\
+    r(01,b7,9a,ec), r(0a,ba,93,e2), r(17,ad,88,f0), r(1c,a0,81,fe),\
+    r(2d,83,be,d4), r(26,8e,b7,da), r(3b,99,ac,c8), r(30,94,a5,c6),\
+    r(59,df,d2,9c), r(52,d2,db,92), r(4f,c5,c0,80), r(44,c8,c9,8e),\
+    r(75,eb,f6,a4), r(7e,e6,ff,aa), r(63,f1,e4,b8), r(68,fc,ed,b6),\
+    r(b1,67,0a,0c), r(ba,6a,03,02), r(a7,7d,18,10), r(ac,70,11,1e),\
+    r(9d,53,2e,34), r(96,5e,27,3a), r(8b,49,3c,28), r(80,44,35,26),\
+    r(e9,0f,42,7c), r(e2,02,4b,72), r(ff,15,50,60), r(f4,18,59,6e),\
+    r(c5,3b,66,44), r(ce,36,6f,4a), r(d3,21,74,58), r(d8,2c,7d,56),\
+    r(7a,0c,a1,37), r(71,01,a8,39), r(6c,16,b3,2b), r(67,1b,ba,25),\
+    r(56,38,85,0f), r(5d,35,8c,01), r(40,22,97,13), r(4b,2f,9e,1d),\
+    r(22,64,e9,47), r(29,69,e0,49), r(34,7e,fb,5b), r(3f,73,f2,55),\
+    r(0e,50,cd,7f), r(05,5d,c4,71), r(18,4a,df,63), r(13,47,d6,6d),\
+    r(ca,dc,31,d7), r(c1,d1,38,d9), r(dc,c6,23,cb), r(d7,cb,2a,c5),\
+    r(e6,e8,15,ef), r(ed,e5,1c,e1), r(f0,f2,07,f3), r(fb,ff,0e,fd),\
+    r(92,b4,79,a7), r(99,b9,70,a9), r(84,ae,6b,bb), r(8f,a3,62,b5),\
+    r(be,80,5d,9f), r(b5,8d,54,91), r(a8,9a,4f,83), r(a3,97,46,8d)
+
+#undef r
+#define r   r0
+
+#if defined(ONE_IM_TABLE)
+static const u_int32_t im_tab[256] =
+    {   m_table };
+#elif defined(FOUR_IM_TABLES)
+static const u_int32_t im_tab[4][256] =
+{   {   m_table },
+#undef  r
+#define r   r1
+    {   m_table },
+#undef  r
+#define r   r2
+    {   m_table },
+#undef  r
+#define r   r3
+    {   m_table }
+};
+#endif
+
+#endif
+
+#else
+
+static int tab_gen = 0;
+
+static unsigned char  s_box[256];            // the S box
+static unsigned char  inv_s_box[256];        // the inverse S box
+static u_int32_t  rcon_tab[AES_RC_LENGTH];   // table of round constants
+
+#if defined(ONE_TABLE)
+static u_int32_t  ft_tab[256];
+static u_int32_t  it_tab[256];
+#elif defined(FOUR_TABLES)
+static u_int32_t  ft_tab[4][256];
+static u_int32_t  it_tab[4][256];
+#endif
+
+#if defined(ONE_LR_TABLE)
+static u_int32_t  fl_tab[256];
+static u_int32_t  il_tab[256];
+#elif defined(FOUR_LR_TABLES)
+static u_int32_t  fl_tab[4][256];
+static u_int32_t  il_tab[4][256];
+#endif
+
+#if defined(ONE_IM_TABLE)
+static u_int32_t  im_tab[256];
+#elif defined(FOUR_IM_TABLES)
+static u_int32_t  im_tab[4][256];
+#endif
+
+// Generate the tables for the dynamic table option
+
+#if !defined(FF_TABLES)
+
+// It will generally be sensible to use tables to compute finite 
+// field multiplies and inverses but where memory is scarse this 
+// code might sometimes be better.
+
+// return 2 ^ (n - 1) where n is the bit number of the highest bit
+// set in x with x in the range 1 < x < 0x00000200.   This form is
+// used so that locals within FFinv can be bytes rather than words
+
+static unsigned char hibit(const u_int32_t x)
+{   unsigned char r = (unsigned char)((x >> 1) | (x >> 2));
+    
+    r |= (r >> 2);
+    r |= (r >> 4);
+    return (r + 1) >> 1;
+}
+
+// return the inverse of the finite field element x
+
+static unsigned char FFinv(const unsigned char x)
+{   unsigned char    p1 = x, p2 = 0x1b, n1 = hibit(x), n2 = 0x80, v1 = 1, v2 = 0;
+
+    if(x < 2) return x;
+
+    for(;;)
+    {
+        if(!n1) return v1;
+
+        while(n2 >= n1)
+        {   
+            n2 /= n1; p2 ^= p1 * n2; v2 ^= v1 * n2; n2 = hibit(p2);
+        }
+        
+        if(!n2) return v2;
+
+        while(n1 >= n2)
+        {   
+            n1 /= n2; p1 ^= p2 * n1; v1 ^= v2 * n1; n1 = hibit(p1);
+        }
+    }
+}
+
+// define the finite field multiplies required for Rijndael
+
+#define FFmul02(x)  ((((x) & 0x7f) << 1) ^ ((x) & 0x80 ? 0x1b : 0))
+#define FFmul03(x)  ((x) ^ FFmul02(x))
+#define FFmul09(x)  ((x) ^ FFmul02(FFmul02(FFmul02(x))))
+#define FFmul0b(x)  ((x) ^ FFmul02((x) ^ FFmul02(FFmul02(x))))
+#define FFmul0d(x)  ((x) ^ FFmul02(FFmul02((x) ^ FFmul02(x))))
+#define FFmul0e(x)  FFmul02((x) ^ FFmul02((x) ^ FFmul02(x)))
+
+#else
+
+#define FFinv(x)    ((x) ? pow[255 - log[x]]: 0)
+
+#define FFmul02(x) (x ? pow[log[x] + 0x19] : 0)
+#define FFmul03(x) (x ? pow[log[x] + 0x01] : 0)
+#define FFmul09(x) (x ? pow[log[x] + 0xc7] : 0)
+#define FFmul0b(x) (x ? pow[log[x] + 0x68] : 0)
+#define FFmul0d(x) (x ? pow[log[x] + 0xee] : 0)
+#define FFmul0e(x) (x ? pow[log[x] + 0xdf] : 0)
+
+#endif
+
+// The forward and inverse affine transformations used in the S-box
+
+#define fwd_affine(x) \
+    (w = (u_int32_t)x, w ^= (w<<1)^(w<<2)^(w<<3)^(w<<4), 0x63^(unsigned char)(w^(w>>8)))
+
+#define inv_affine(x) \
+    (w = (u_int32_t)x, w = (w<<1)^(w<<3)^(w<<6), 0x05^(unsigned char)(w^(w>>8)))
+
+static void gen_tabs(void)
+{   u_int32_t  i, w;
+
+#if defined(FF_TABLES)
+
+    unsigned char  pow[512], log[256];
+
+    // log and power tables for GF(2^8) finite field with
+    // 0x011b as modular polynomial - the simplest primitive
+    // root is 0x03, used here to generate the tables
+
+    i = 0; w = 1; 
+    do
+    {   
+        pow[i] = (unsigned char)w;
+        pow[i + 255] = (unsigned char)w;
+        log[w] = (unsigned char)i++;
+        w ^=  (w << 1) ^ (w & ff_hi ? ff_poly : 0);
+    }
+    while (w != 1);
+
+#endif
+
+    for(i = 0, w = 1; i < AES_RC_LENGTH; ++i)
+    {
+        rcon_tab[i] = bytes2word(w, 0, 0, 0);
+        w = (w << 1) ^ (w & ff_hi ? ff_poly : 0);
+    }
+
+    for(i = 0; i < 256; ++i)
+    {   unsigned char    b;
+
+        s_box[i] = b = fwd_affine(FFinv((unsigned char)i));
+
+        w = bytes2word(b, 0, 0, 0);
+#if defined(ONE_LR_TABLE)
+        fl_tab[i] = w;
+#elif defined(FOUR_LR_TABLES)
+        fl_tab[0][i] = w;
+        fl_tab[1][i] = upr(w,1);
+        fl_tab[2][i] = upr(w,2);
+        fl_tab[3][i] = upr(w,3);
+#endif
+        w = bytes2word(FFmul02(b), b, b, FFmul03(b));
+#if defined(ONE_TABLE)
+        ft_tab[i] = w;
+#elif defined(FOUR_TABLES)
+        ft_tab[0][i] = w;
+        ft_tab[1][i] = upr(w,1);
+        ft_tab[2][i] = upr(w,2);
+        ft_tab[3][i] = upr(w,3);
+#endif
+        inv_s_box[i] = b = FFinv(inv_affine((unsigned char)i));
+
+        w = bytes2word(b, 0, 0, 0);
+#if defined(ONE_LR_TABLE)
+        il_tab[i] = w;
+#elif defined(FOUR_LR_TABLES)
+        il_tab[0][i] = w;
+        il_tab[1][i] = upr(w,1);
+        il_tab[2][i] = upr(w,2);
+        il_tab[3][i] = upr(w,3);
+#endif
+        w = bytes2word(FFmul0e(b), FFmul09(b), FFmul0d(b), FFmul0b(b));
+#if defined(ONE_TABLE)
+        it_tab[i] = w;
+#elif defined(FOUR_TABLES)
+        it_tab[0][i] = w;
+        it_tab[1][i] = upr(w,1);
+        it_tab[2][i] = upr(w,2);
+        it_tab[3][i] = upr(w,3);
+#endif
+#if defined(ONE_IM_TABLE)
+        im_tab[b] = w;
+#elif defined(FOUR_IM_TABLES)
+        im_tab[0][b] = w;
+        im_tab[1][b] = upr(w,1);
+        im_tab[2][b] = upr(w,2);
+        im_tab[3][b] = upr(w,3);
+#endif
+
+    }
+}
+
+#endif
+
+#define no_table(x,box,vf,rf,c) bytes2word( \
+    box[bval(vf(x,0,c),rf(0,c))], \
+    box[bval(vf(x,1,c),rf(1,c))], \
+    box[bval(vf(x,2,c),rf(2,c))], \
+    box[bval(vf(x,3,c),rf(3,c))])
+
+#define one_table(x,op,tab,vf,rf,c) \
+ (     tab[bval(vf(x,0,c),rf(0,c))] \
+  ^ op(tab[bval(vf(x,1,c),rf(1,c))],1) \
+  ^ op(tab[bval(vf(x,2,c),rf(2,c))],2) \
+  ^ op(tab[bval(vf(x,3,c),rf(3,c))],3))
+
+#define four_tables(x,tab,vf,rf,c) \
+ (  tab[0][bval(vf(x,0,c),rf(0,c))] \
+  ^ tab[1][bval(vf(x,1,c),rf(1,c))] \
+  ^ tab[2][bval(vf(x,2,c),rf(2,c))] \
+  ^ tab[3][bval(vf(x,3,c),rf(3,c))])
+
+#define vf1(x,r,c)  (x)
+#define rf1(r,c)    (r)
+#define rf2(r,c)    ((r-c)&3)
+
+#if defined(FOUR_LR_TABLES)
+#define ls_box(x,c)     four_tables(x,fl_tab,vf1,rf2,c)
+#elif defined(ONE_LR_TABLE)
+#define ls_box(x,c)     one_table(x,upr,fl_tab,vf1,rf2,c)
+#else
+#define ls_box(x,c)     no_table(x,s_box,vf1,rf2,c)
+#endif
+
+#if defined(FOUR_IM_TABLES)
+#define inv_mcol(x)     four_tables(x,im_tab,vf1,rf1,0)
+#elif defined(ONE_IM_TABLE)
+#define inv_mcol(x)     one_table(x,upr,im_tab,vf1,rf1,0)
+#else
+#define inv_mcol(x) \
+    (f9 = (x),f2 = FFmulX(f9), f4 = FFmulX(f2), f8 = FFmulX(f4), f9 ^= f8, \
+    f2 ^= f4 ^ f8 ^ upr(f2 ^ f9,3) ^ upr(f4 ^ f9,2) ^ upr(f9,1))
+#endif
+
+// Subroutine to set the block size (if variable) in bytes, legal
+// values being 16, 24 and 32.
+
+#if defined(AES_BLOCK_SIZE)
+#define nc   (AES_BLOCK_SIZE / 4)
+#else
+#define nc   (cx->aes_Ncol)
+
+void aes_set_blk(aes_context *cx, int n_bytes)
+{
+#if !defined(FIXED_TABLES)
+    if(!tab_gen) { gen_tabs(); tab_gen = 1; }
+#endif
+
+    switch(n_bytes) {
+    case 32:        /* bytes */
+    case 256:       /* bits */
+        nc = 8;
+        break;
+    case 24:        /* bytes */
+    case 192:       /* bits */
+        nc = 6;
+        break;
+    case 16:        /* bytes */
+    case 128:       /* bits */
+    default:
+        nc = 4;
+        break;
+    }
+}
+
+#endif
+
+// Initialise the key schedule from the user supplied key. The key
+// length is now specified in bytes - 16, 24 or 32 as appropriate.
+// This corresponds to bit lengths of 128, 192 and 256 bits, and
+// to Nk values of 4, 6 and 8 respectively.
+
+#define mx(t,f) (*t++ = inv_mcol(*f),f++)
+#define cp(t,f) *t++ = *f++
+
+#if   AES_BLOCK_SIZE == 16
+#define cpy(d,s)    cp(d,s); cp(d,s); cp(d,s); cp(d,s)
+#define mix(d,s)    mx(d,s); mx(d,s); mx(d,s); mx(d,s)
+#elif AES_BLOCK_SIZE == 24
+#define cpy(d,s)    cp(d,s); cp(d,s); cp(d,s); cp(d,s); \
+                    cp(d,s); cp(d,s)
+#define mix(d,s)    mx(d,s); mx(d,s); mx(d,s); mx(d,s); \
+                    mx(d,s); mx(d,s)
+#elif AES_BLOCK_SIZE == 32
+#define cpy(d,s)    cp(d,s); cp(d,s); cp(d,s); cp(d,s); \
+                    cp(d,s); cp(d,s); cp(d,s); cp(d,s)
+#define mix(d,s)    mx(d,s); mx(d,s); mx(d,s); mx(d,s); \
+                    mx(d,s); mx(d,s); mx(d,s); mx(d,s)
+#else
+
+#define cpy(d,s) \
+switch(nc) \
+{   case 8: cp(d,s); cp(d,s); \
+    case 6: cp(d,s); cp(d,s); \
+    case 4: cp(d,s); cp(d,s); \
+            cp(d,s); cp(d,s); \
+}
+
+#define mix(d,s) \
+switch(nc) \
+{   case 8: mx(d,s); mx(d,s); \
+    case 6: mx(d,s); mx(d,s); \
+    case 4: mx(d,s); mx(d,s); \
+            mx(d,s); mx(d,s); \
+}
+
+#endif
+
+void aes_set_key(aes_context *cx, const unsigned char in_key[], int n_bytes, const int f)
+{   u_int32_t    *kf, *kt, rci;
+
+#if !defined(FIXED_TABLES)
+    if(!tab_gen) { gen_tabs(); tab_gen = 1; }
+#endif
+
+    switch(n_bytes) {
+    case 32:                    /* bytes */
+    case 256:                   /* bits */
+        cx->aes_Nkey = 8;
+        break;
+    case 24:                    /* bytes */
+    case 192:                   /* bits */
+        cx->aes_Nkey = 6;
+        break;
+    case 16:                    /* bytes */
+    case 128:                   /* bits */
+    default:
+        cx->aes_Nkey = 4;
+        break;
+    }
+
+    cx->aes_Nrnd = (cx->aes_Nkey > nc ? cx->aes_Nkey : nc) + 6; 
+
+    cx->aes_e_key[0] = const_word_in(in_key     );
+    cx->aes_e_key[1] = const_word_in(in_key +  4);
+    cx->aes_e_key[2] = const_word_in(in_key +  8);
+    cx->aes_e_key[3] = const_word_in(in_key + 12);
+
+    kf = cx->aes_e_key; 
+    kt = kf + nc * (cx->aes_Nrnd + 1) - cx->aes_Nkey; 
+    rci = 0;
+
+    switch(cx->aes_Nkey)
+    {
+    case 4: do
+            {   kf[4] = kf[0] ^ ls_box(kf[3],3) ^ rcon_tab[rci++];
+                kf[5] = kf[1] ^ kf[4];
+                kf[6] = kf[2] ^ kf[5];
+                kf[7] = kf[3] ^ kf[6];
+                kf += 4;
+            }
+            while(kf < kt);
+            break;
+
+    case 6: cx->aes_e_key[4] = const_word_in(in_key + 16);
+            cx->aes_e_key[5] = const_word_in(in_key + 20);
+            do
+            {   kf[ 6] = kf[0] ^ ls_box(kf[5],3) ^ rcon_tab[rci++];
+                kf[ 7] = kf[1] ^ kf[ 6];
+                kf[ 8] = kf[2] ^ kf[ 7];
+                kf[ 9] = kf[3] ^ kf[ 8];
+                kf[10] = kf[4] ^ kf[ 9];
+                kf[11] = kf[5] ^ kf[10];
+                kf += 6;
+            }
+            while(kf < kt);
+            break;
+
+    case 8: cx->aes_e_key[4] = const_word_in(in_key + 16);
+            cx->aes_e_key[5] = const_word_in(in_key + 20);
+            cx->aes_e_key[6] = const_word_in(in_key + 24);
+            cx->aes_e_key[7] = const_word_in(in_key + 28);
+            do
+            {   kf[ 8] = kf[0] ^ ls_box(kf[7],3) ^ rcon_tab[rci++];
+                kf[ 9] = kf[1] ^ kf[ 8];
+                kf[10] = kf[2] ^ kf[ 9];
+                kf[11] = kf[3] ^ kf[10];
+                kf[12] = kf[4] ^ ls_box(kf[11],0);
+                kf[13] = kf[5] ^ kf[12];
+                kf[14] = kf[6] ^ kf[13];
+                kf[15] = kf[7] ^ kf[14];
+                kf += 8;
+            }
+            while (kf < kt);
+            break;
+    }
+
+    if(!f)
+    {   u_int32_t    i;
+        
+        kt = cx->aes_d_key + nc * cx->aes_Nrnd;
+        kf = cx->aes_e_key;
+        
+        cpy(kt, kf); kt -= 2 * nc;
+
+        for(i = 1; i < cx->aes_Nrnd; ++i)
+        { 
+#if defined(ONE_TABLE) || defined(FOUR_TABLES)
+#if !defined(ONE_IM_TABLE) && !defined(FOUR_IM_TABLES)
+            u_int32_t    f2, f4, f8, f9;
+#endif
+            mix(kt, kf);
+#else
+            cpy(kt, kf);
+#endif
+            kt -= 2 * nc;
+        }
+        
+        cpy(kt, kf);
+    }
+}
+
+// y = output word, x = input word, r = row, c = column
+// for r = 0, 1, 2 and 3 = column accessed for row r
+
+#if defined(ARRAYS)
+#define s(x,c) x[c]
+#else
+#define s(x,c) x##c
+#endif
+
+// I am grateful to Frank Yellin for the following constructions
+// which, given the column (c) of the output state variable that
+// is being computed, return the input state variables which are
+// needed for each row (r) of the state
+
+// For the fixed block size options, compilers reduce these two 
+// expressions to fixed variable references. For variable block 
+// size code conditional clauses will sometimes be returned
+
+#define unused  77  // Sunset Strip
+
+#define fwd_var(x,r,c) \
+ ( r==0 ?			\
+    ( c==0 ? s(x,0) \
+    : c==1 ? s(x,1) \
+    : c==2 ? s(x,2) \
+    : c==3 ? s(x,3) \
+    : c==4 ? s(x,4) \
+    : c==5 ? s(x,5) \
+    : c==6 ? s(x,6) \
+    : s(x,7))		\
+ : r==1 ?			\
+    ( c==0 ? s(x,1) \
+    : c==1 ? s(x,2) \
+    : c==2 ? s(x,3) \
+    : c==3 ? nc==4 ? s(x,0) : s(x,4) \
+    : c==4 ? s(x,5) \
+    : c==5 ? nc==8 ? s(x,6) : s(x,0) \
+    : c==6 ? s(x,7) \
+    : s(x,0))		\
+ : r==2 ?			\
+    ( c==0 ? nc==8 ? s(x,3) : s(x,2) \
+    : c==1 ? nc==8 ? s(x,4) : s(x,3) \
+    : c==2 ? nc==4 ? s(x,0) : nc==8 ? s(x,5) : s(x,4) \
+    : c==3 ? nc==4 ? s(x,1) : nc==8 ? s(x,6) : s(x,5) \
+    : c==4 ? nc==8 ? s(x,7) : s(x,0) \
+    : c==5 ? nc==8 ? s(x,0) : s(x,1) \
+    : c==6 ? s(x,1) \
+    : s(x,2))		\
+ :					\
+    ( c==0 ? nc==8 ? s(x,4) : s(x,3) \
+    : c==1 ? nc==4 ? s(x,0) : nc==8 ? s(x,5) : s(x,4) \
+    : c==2 ? nc==4 ? s(x,1) : nc==8 ? s(x,6) : s(x,5) \
+    : c==3 ? nc==4 ? s(x,2) : nc==8 ? s(x,7) : s(x,0) \
+    : c==4 ? nc==8 ? s(x,0) : s(x,1) \
+    : c==5 ? nc==8 ? s(x,1) : s(x,2) \
+    : c==6 ? s(x,2) \
+    : s(x,3)))
+
+#define inv_var(x,r,c) \
+ ( r==0 ?			\
+    ( c==0 ? s(x,0) \
+    : c==1 ? s(x,1) \
+    : c==2 ? s(x,2) \
+    : c==3 ? s(x,3) \
+    : c==4 ? s(x,4) \
+    : c==5 ? s(x,5) \
+    : c==6 ? s(x,6) \
+    : s(x,7))		\
+ : r==1 ?			\
+    ( c==0 ? nc==4 ? s(x,3) : nc==8 ? s(x,7) : s(x,5) \
+    : c==1 ? s(x,0) \
+    : c==2 ? s(x,1) \
+    : c==3 ? s(x,2) \
+    : c==4 ? s(x,3) \
+    : c==5 ? s(x,4) \
+    : c==6 ? s(x,5) \
+    : s(x,6))		\
+ : r==2 ?			\
+    ( c==0 ? nc==4 ? s(x,2) : nc==8 ? s(x,5) : s(x,4) \
+    : c==1 ? nc==4 ? s(x,3) : nc==8 ? s(x,6) : s(x,5) \
+    : c==2 ? nc==8 ? s(x,7) : s(x,0) \
+    : c==3 ? nc==8 ? s(x,0) : s(x,1) \
+    : c==4 ? nc==8 ? s(x,1) : s(x,2) \
+    : c==5 ? nc==8 ? s(x,2) : s(x,3) \
+    : c==6 ? s(x,3) \
+    : s(x,4))		\
+ :					\
+    ( c==0 ? nc==4 ? s(x,1) : nc==8 ? s(x,4) : s(x,3) \
+    : c==1 ? nc==4 ? s(x,2) : nc==8 ? s(x,5) : s(x,4) \
+    : c==2 ? nc==4 ? s(x,3) : nc==8 ? s(x,6) : s(x,5) \
+    : c==3 ? nc==8 ? s(x,7) : s(x,0) \
+    : c==4 ? nc==8 ? s(x,0) : s(x,1) \
+    : c==5 ? nc==8 ? s(x,1) : s(x,2) \
+    : c==6 ? s(x,2) \
+    : s(x,3)))
+
+#define si(y,x,k,c) s(y,c) = const_word_in(x + 4 * c) ^ k[c]
+#define so(y,x,c)   word_out(y + 4 * c, s(x,c))
+
+#if defined(FOUR_TABLES)
+#define fwd_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ four_tables(x,ft_tab,fwd_var,rf1,c)
+#define inv_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ four_tables(x,it_tab,inv_var,rf1,c)
+#elif defined(ONE_TABLE)
+#define fwd_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ one_table(x,upr,ft_tab,fwd_var,rf1,c)
+#define inv_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ one_table(x,upr,it_tab,inv_var,rf1,c)
+#else
+#define fwd_rnd(y,x,k,c)    s(y,c) = fwd_mcol(no_table(x,s_box,fwd_var,rf1,c)) ^ (k)[c]
+#define inv_rnd(y,x,k,c)    s(y,c) = inv_mcol(no_table(x,inv_s_box,inv_var,rf1,c) ^ (k)[c])
+#endif
+
+#if defined(FOUR_LR_TABLES)
+#define fwd_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ four_tables(x,fl_tab,fwd_var,rf1,c)
+#define inv_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ four_tables(x,il_tab,inv_var,rf1,c)
+#elif defined(ONE_LR_TABLE)
+#define fwd_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ one_table(x,ups,fl_tab,fwd_var,rf1,c)
+#define inv_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ one_table(x,ups,il_tab,inv_var,rf1,c)
+#else
+#define fwd_lrnd(y,x,k,c)   s(y,c) = no_table(x,s_box,fwd_var,rf1,c) ^ (k)[c]
+#define inv_lrnd(y,x,k,c)   s(y,c) = no_table(x,inv_s_box,inv_var,rf1,c) ^ (k)[c]
+#endif
+
+#if AES_BLOCK_SIZE == 16
+
+#if defined(ARRAYS)
+#define locals(y,x)     x[4],y[4]
+#else
+#define locals(y,x)     x##0,x##1,x##2,x##3,y##0,y##1,y##2,y##3
+// the following defines prevent the compiler requiring the declaration
+// of generated but unused variables in the fwd_var and inv_var macros
+#define b04 unused
+#define b05 unused
+#define b06 unused
+#define b07 unused
+#define b14 unused
+#define b15 unused
+#define b16 unused
+#define b17 unused
+#endif
+#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
+                        s(y,2) = s(x,2); s(y,3) = s(x,3);
+#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3)
+#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3)
+#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3)
+
+#elif AES_BLOCK_SIZE == 24
+
+#if defined(ARRAYS)
+#define locals(y,x)     x[6],y[6]
+#else
+#define locals(y,x)     x##0,x##1,x##2,x##3,x##4,x##5, \
+                        y##0,y##1,y##2,y##3,y##4,y##5
+#define b06 unused
+#define b07 unused
+#define b16 unused
+#define b17 unused
+#endif
+#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
+                        s(y,2) = s(x,2); s(y,3) = s(x,3); \
+                        s(y,4) = s(x,4); s(y,5) = s(x,5);
+#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); \
+                        si(y,x,k,3); si(y,x,k,4); si(y,x,k,5)
+#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); \
+                        so(y,x,3); so(y,x,4); so(y,x,5)
+#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); \
+                        rm(y,x,k,3); rm(y,x,k,4); rm(y,x,k,5)
+#else
+
+#if defined(ARRAYS)
+#define locals(y,x)     x[8],y[8]
+#else
+#define locals(y,x)     x##0,x##1,x##2,x##3,x##4,x##5,x##6,x##7, \
+                        y##0,y##1,y##2,y##3,y##4,y##5,y##6,y##7
+#endif
+#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
+                        s(y,2) = s(x,2); s(y,3) = s(x,3); \
+                        s(y,4) = s(x,4); s(y,5) = s(x,5); \
+                        s(y,6) = s(x,6); s(y,7) = s(x,7);
+
+#if AES_BLOCK_SIZE == 32
+
+#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3); \
+                        si(y,x,k,4); si(y,x,k,5); si(y,x,k,6); si(y,x,k,7)
+#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3); \
+                        so(y,x,4); so(y,x,5); so(y,x,6); so(y,x,7)
+#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3); \
+                        rm(y,x,k,4); rm(y,x,k,5); rm(y,x,k,6); rm(y,x,k,7)
+#else
+
+#define state_in(y,x,k) \
+switch(nc) \
+{   case 8: si(y,x,k,7); si(y,x,k,6); \
+    case 6: si(y,x,k,5); si(y,x,k,4); \
+    case 4: si(y,x,k,3); si(y,x,k,2); \
+            si(y,x,k,1); si(y,x,k,0); \
+}
+
+#define state_out(y,x) \
+switch(nc) \
+{   case 8: so(y,x,7); so(y,x,6); \
+    case 6: so(y,x,5); so(y,x,4); \
+    case 4: so(y,x,3); so(y,x,2); \
+            so(y,x,1); so(y,x,0); \
+}
+
+#if defined(FAST_VARIABLE)
+
+#define round(rm,y,x,k) \
+switch(nc) \
+{   case 8: rm(y,x,k,7); rm(y,x,k,6); \
+            rm(y,x,k,5); rm(y,x,k,4); \
+            rm(y,x,k,3); rm(y,x,k,2); \
+            rm(y,x,k,1); rm(y,x,k,0); \
+            break; \
+    case 6: rm(y,x,k,5); rm(y,x,k,4); \
+            rm(y,x,k,3); rm(y,x,k,2); \
+            rm(y,x,k,1); rm(y,x,k,0); \
+            break; \
+    case 4: rm(y,x,k,3); rm(y,x,k,2); \
+            rm(y,x,k,1); rm(y,x,k,0); \
+            break; \
+}
+#else
+
+#define round(rm,y,x,k) \
+switch(nc) \
+{   case 8: rm(y,x,k,7); rm(y,x,k,6); \
+    case 6: rm(y,x,k,5); rm(y,x,k,4); \
+    case 4: rm(y,x,k,3); rm(y,x,k,2); \
+            rm(y,x,k,1); rm(y,x,k,0); \
+}
+
+#endif
+
+#endif
+#endif
+
+void aes_encrypt(const aes_context *cx, const unsigned char in_blk[], unsigned char out_blk[])
+{   u_int32_t        locals(b0, b1);
+    const u_int32_t  *kp = cx->aes_e_key;
+
+#if !defined(ONE_TABLE) && !defined(FOUR_TABLES)
+    u_int32_t        f2;
+#endif
+
+    state_in(b0, in_blk, kp); kp += nc;
+
+#if defined(UNROLL)
+
+    switch(cx->aes_Nrnd)
+    {
+    case 14:    round(fwd_rnd,  b1, b0, kp         ); 
+                round(fwd_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
+    case 12:    round(fwd_rnd,  b1, b0, kp         ); 
+                round(fwd_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
+    case 10:    round(fwd_rnd,  b1, b0, kp         );             
+                round(fwd_rnd,  b0, b1, kp +     nc);
+                round(fwd_rnd,  b1, b0, kp + 2 * nc); 
+                round(fwd_rnd,  b0, b1, kp + 3 * nc);
+                round(fwd_rnd,  b1, b0, kp + 4 * nc); 
+                round(fwd_rnd,  b0, b1, kp + 5 * nc);
+                round(fwd_rnd,  b1, b0, kp + 6 * nc); 
+                round(fwd_rnd,  b0, b1, kp + 7 * nc);
+                round(fwd_rnd,  b1, b0, kp + 8 * nc);
+                round(fwd_lrnd, b0, b1, kp + 9 * nc);
+    }
+
+#elif defined(PARTIAL_UNROLL)
+    {   u_int32_t    rnd;
+
+        for(rnd = 0; rnd < (cx->aes_Nrnd >> 1) - 1; ++rnd)
+        {
+            round(fwd_rnd, b1, b0, kp); 
+            round(fwd_rnd, b0, b1, kp + nc); kp += 2 * nc;
+        }
+
+        round(fwd_rnd,  b1, b0, kp);
+        round(fwd_lrnd, b0, b1, kp + nc);
+    }
+#else
+    {   u_int32_t    rnd;
+
+        for(rnd = 0; rnd < cx->aes_Nrnd - 1; ++rnd)
+        {
+            round(fwd_rnd, b1, b0, kp); 
+            l_copy(b0, b1); kp += nc;
+        }
+
+        round(fwd_lrnd, b0, b1, kp);
+    }
+#endif
+
+    state_out(out_blk, b0);
+}
+
+void aes_decrypt(const aes_context *cx, const unsigned char in_blk[], unsigned char out_blk[])
+{   u_int32_t        locals(b0, b1);
+    const u_int32_t  *kp = cx->aes_d_key;
+
+#if !defined(ONE_TABLE) && !defined(FOUR_TABLES)
+    u_int32_t        f2, f4, f8, f9; 
+#endif
+
+    state_in(b0, in_blk, kp); kp += nc;
+
+#if defined(UNROLL)
+
+    switch(cx->aes_Nrnd)
+    {
+    case 14:    round(inv_rnd,  b1, b0, kp         );
+                round(inv_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
+    case 12:    round(inv_rnd,  b1, b0, kp         );
+                round(inv_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
+    case 10:    round(inv_rnd,  b1, b0, kp         );             
+                round(inv_rnd,  b0, b1, kp +     nc);
+                round(inv_rnd,  b1, b0, kp + 2 * nc); 
+                round(inv_rnd,  b0, b1, kp + 3 * nc);
+                round(inv_rnd,  b1, b0, kp + 4 * nc); 
+                round(inv_rnd,  b0, b1, kp + 5 * nc);
+                round(inv_rnd,  b1, b0, kp + 6 * nc); 
+                round(inv_rnd,  b0, b1, kp + 7 * nc);
+                round(inv_rnd,  b1, b0, kp + 8 * nc);
+                round(inv_lrnd, b0, b1, kp + 9 * nc);
+    }
+
+#elif defined(PARTIAL_UNROLL)
+    {   u_int32_t    rnd;
+
+        for(rnd = 0; rnd < (cx->aes_Nrnd >> 1) - 1; ++rnd)
+        {
+            round(inv_rnd, b1, b0, kp); 
+            round(inv_rnd, b0, b1, kp + nc); kp += 2 * nc;
+        }
+
+        round(inv_rnd,  b1, b0, kp);
+        round(inv_lrnd, b0, b1, kp + nc);
+    }
+#else
+    {   u_int32_t    rnd;
+
+        for(rnd = 0; rnd < cx->aes_Nrnd - 1; ++rnd)
+        {
+            round(inv_rnd, b1, b0, kp); 
+            l_copy(b0, b1); kp += nc;
+        }
+
+        round(inv_lrnd, b0, b1, kp);
+    }
+#endif
+
+    state_out(out_blk, b0);
+}
diff --git a/lib/libcrypto/libaes/aes.h b/lib/libcrypto/libaes/aes.h
new file mode 100644
index 000000000..4f1e3b335
--- /dev/null
+++ b/lib/libcrypto/libaes/aes.h
@@ -0,0 +1,97 @@
+// I retain copyright in this code but I encourage its free use provided
+// that I don't carry any responsibility for the results. I am especially 
+// happy to see it used in free and open source software. If you do use 
+// it I would appreciate an acknowledgement of its origin in the code or
+// the product that results and I would also appreciate knowing a little
+// about the use to which it is being put. I am grateful to Frank Yellin
+// for some ideas that are used in this implementation.
+//
+// Dr B. R. Gladman <brg@gladman.uk.net> 6th April 2001.
+//
+// This is an implementation of the AES encryption algorithm (Rijndael)
+// designed by Joan Daemen and Vincent Rijmen. This version is designed
+// to provide both fixed and dynamic block and key lengths and can also 
+// run with either big or little endian internal byte order (see aes.h). 
+// It inputs block and key lengths in bytes with the legal values being 
+// 16, 24 and 32.
+
+/*
+ * Modified by Jari Ruusu,  May 1 2001
+ *  - Fixed some compile warnings, code was ok but gcc warned anyway.
+ *  - Changed basic types: byte -> unsigned char, word -> u_int32_t
+ *  - Major name space cleanup: Names visible to outside now begin
+ *    with "aes_" or "AES_". A lot of stuff moved from aes.h to aes.c
+ *  - Removed C++ and DLL support as part of name space cleanup.
+ *  - Eliminated unnecessary recomputation of tables. (actual bug fix)
+ *  - Merged precomputed constant tables to aes.c file.
+ *  - Removed data alignment restrictions for portability reasons.
+ *  - Made block and key lengths accept bit count (128/192/256)
+ *    as well byte count (16/24/32).
+ *  - Removed all error checks. This change also eliminated the need
+ *    to preinitialize the context struct to zero.
+ *  - Removed some totally unused constants.
+ */
+
+#ifndef _AES_H
+#define _AES_H
+
+#if defined(__linux__) && defined(__KERNEL__)
+#  include <linux/types.h>
+#else 
+#  include <sys/types.h>
+#endif
+
+// CONFIGURATION OPTIONS (see also aes.c)
+//
+// Define AES_BLOCK_SIZE to set the cipher block size (16, 24 or 32) or
+// leave this undefined for dynamically variable block size (this will
+// result in much slower code).
+// IMPORTANT NOTE: AES_BLOCK_SIZE is in BYTES (16, 24, 32 or undefined). If
+// left undefined a slower version providing variable block length is compiled
+
+#define AES_BLOCK_SIZE  16
+
+// The number of key schedule words for different block and key lengths
+// allowing for method of computation which requires the length to be a
+// multiple of the key length
+//
+// Nk =       4   6   8
+//        -------------
+// Nb = 4 |  60  60  64
+//      6 |  96  90  96
+//      8 | 120 120 120
+
+#if !defined(AES_BLOCK_SIZE) || (AES_BLOCK_SIZE == 32)
+#define AES_KS_LENGTH   120
+#define AES_RC_LENGTH    29
+#else
+#define AES_KS_LENGTH   4 * AES_BLOCK_SIZE
+#define AES_RC_LENGTH   (9 * AES_BLOCK_SIZE) / 8 - 8
+#endif
+
+typedef struct
+{
+    u_int32_t    aes_Nkey;      // the number of words in the key input block
+    u_int32_t    aes_Nrnd;      // the number of cipher rounds
+    u_int32_t    aes_e_key[AES_KS_LENGTH];   // the encryption key schedule
+    u_int32_t    aes_d_key[AES_KS_LENGTH];   // the decryption key schedule
+#if !defined(AES_BLOCK_SIZE)
+    u_int32_t    aes_Ncol;      // the number of columns in the cipher state
+#endif
+} aes_context;
+
+// THE CIPHER INTERFACE
+
+#if !defined(AES_BLOCK_SIZE)
+extern void aes_set_blk(aes_context *, const int);
+#endif
+extern void aes_set_key(aes_context *, const unsigned char [], const int, const int);
+extern void aes_encrypt(const aes_context *, const unsigned char [], unsigned char []);
+extern void aes_decrypt(const aes_context *, const unsigned char [], unsigned char []);
+
+// The block length inputs to aes_set_block and aes_set_key are in numbers
+// of bytes or bits.  The calls to subroutines must be made in the above
+// order but multiple calls can be made without repeating earlier calls
+// if their parameters have not changed.
+
+#endif  // _AES_H
diff --git a/lib/libcrypto/libaes/aes_cbc.c b/lib/libcrypto/libaes/aes_cbc.c
new file mode 100644
index 000000000..962dd1a35
--- /dev/null
+++ b/lib/libcrypto/libaes/aes_cbc.c
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
+#include "aes_cbc.h"
+#include "cbc_generic.h"
+/* returns bool success */
+int AES_set_key(aes_context *aes_ctx, const u_int8_t *key, int keysize) {
+	aes_set_key(aes_ctx, key, keysize, 0);
+	return 1;	
+}
+CBC_IMPL_BLK16(AES_cbc_encrypt, aes_context, u_int8_t *, aes_encrypt, aes_decrypt);
diff --git a/lib/libcrypto/libaes/aes_cbc.h b/lib/libcrypto/libaes/aes_cbc.h
new file mode 100644
index 000000000..92f5d77f5
--- /dev/null
+++ b/lib/libcrypto/libaes/aes_cbc.h
@@ -0,0 +1,4 @@
+/* Glue header */
+#include "aes.h"
+int AES_set_key(aes_context *aes_ctx, const u_int8_t * key, int keysize);
+int AES_cbc_encrypt(aes_context *ctx, const u_int8_t * in, u_int8_t * out, int ilen, const u_int8_t * iv, int encrypt);
diff --git a/lib/libcrypto/libaes/aes_xcbc_mac.c b/lib/libcrypto/libaes/aes_xcbc_mac.c
new file mode 100644
index 000000000..89d7bc067
--- /dev/null
+++ b/lib/libcrypto/libaes/aes_xcbc_mac.c
@@ -0,0 +1,67 @@
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <linux/kernel.h>
+#define DEBUG(x) 
+#else
+#include <stdio.h>
+#include <sys/types.h>
+#define DEBUG(x) x
+#endif
+
+#include "aes.h"
+#include "aes_xcbc_mac.h"
+
+int AES_xcbc_mac_set_key(aes_context_mac *ctxm, const u_int8_t *key, int keylen)
+{
+	int ret=1;
+	aes_block kn[3] = { 
+		{ 0x01010101, 0x01010101, 0x01010101, 0x01010101 },
+		{ 0x02020202, 0x02020202, 0x02020202, 0x02020202 },
+		{ 0x03030303, 0x03030303, 0x03030303, 0x03030303 },
+	};
+	aes_set_key(&ctxm->ctx_k1, key, keylen, 0);
+	aes_encrypt(&ctxm->ctx_k1, (u_int8_t *) kn[0], (u_int8_t *) kn[0]);
+	aes_encrypt(&ctxm->ctx_k1, (u_int8_t *) kn[1], (u_int8_t *) ctxm->k2);
+	aes_encrypt(&ctxm->ctx_k1, (u_int8_t *) kn[2], (u_int8_t *) ctxm->k3);
+	aes_set_key(&ctxm->ctx_k1, (u_int8_t *) kn[0], 16, 0);
+	return ret;
+}
+static void do_pad_xor(u_int8_t *out, const u_int8_t *in, int len) {
+	int pos=0;
+	for (pos=1; pos <= 16; pos++, in++, out++) {
+		if (pos <= len)
+			*out ^= *in;
+		if (pos > len) {
+			DEBUG(printf("put 0x80 at pos=%d\n", pos));
+			*out ^= 0x80;
+			break;
+		}
+	}
+}
+static void xor_block(aes_block res, const aes_block op) {
+	res[0] ^= op[0];
+	res[1] ^= op[1];
+	res[2] ^= op[2];
+	res[3] ^= op[3];
+}
+int AES_xcbc_mac_hash(const aes_context_mac *ctxm, const u_int8_t * in, int ilen, u_int8_t hash[16]) {
+	int ret=ilen;
+	u_int32_t out[4] = { 0, 0, 0, 0 }; 
+	for (; ilen > 16 ; ilen-=16) {
+		xor_block(out, (const u_int32_t*) &in[0]);
+		aes_encrypt(&ctxm->ctx_k1, in, (u_int8_t *)&out[0]);
+		in+=16; 
+	}
+	do_pad_xor((u_int8_t *)&out, in, ilen);
+	if (ilen==16) {
+		DEBUG(printf("using k3\n"));
+		xor_block(out, ctxm->k3);
+	}
+	else 
+	{
+		DEBUG(printf("using k2\n"));
+		xor_block(out, ctxm->k2);
+	}
+	aes_encrypt(&ctxm->ctx_k1, (u_int8_t *)out, hash);
+	return ret;
+} 
diff --git a/lib/libcrypto/libaes/aes_xcbc_mac.h b/lib/libcrypto/libaes/aes_xcbc_mac.h
new file mode 100644
index 000000000..baf438cd4
--- /dev/null
+++ b/lib/libcrypto/libaes/aes_xcbc_mac.h
@@ -0,0 +1,12 @@
+#ifndef _AES_XCBC_MAC_H
+#define _AES_XCBC_MAC_H
+
+typedef u_int32_t aes_block[4];
+typedef struct {
+	aes_context ctx_k1;
+	aes_block k2;
+	aes_block k3;
+} aes_context_mac;
+int AES_xcbc_mac_set_key(aes_context_mac *ctxm, const u_int8_t *key, int keylen);
+int AES_xcbc_mac_hash(const aes_context_mac *ctxm, const u_int8_t * in, int ilen, u_int8_t hash[16]);
+#endif /* _AES_XCBC_MAC_H */
diff --git a/lib/libcrypto/libaes/asm/aes-i586.S b/lib/libcrypto/libaes/asm/aes-i586.S
new file mode 100644
index 000000000..df19d0d62
--- /dev/null
+++ b/lib/libcrypto/libaes/asm/aes-i586.S
@@ -0,0 +1,892 @@
+//
+// Copyright (c) 2001, Dr Brian Gladman <brg@gladman.uk.net>, Worcester, UK.
+// All rights reserved.
+//
+// TERMS
+//
+//  Redistribution and use in source and binary forms, with or without
+//  modification, are permitted subject to the following conditions:
+//
+//  1. Redistributions of source code must retain the above copyright
+//     notice, this list of conditions and the following disclaimer.
+//
+//  2. Redistributions in binary form must reproduce the above copyright
+//     notice, this list of conditions and the following disclaimer in the
+//     documentation and/or other materials provided with the distribution.
+//
+//  3. The copyright holder's name must not be used to endorse or promote
+//     any products derived from this software without his specific prior
+//     written permission.
+//
+//  This software is provided 'as is' with no express or implied warranties
+//  of correctness or fitness for purpose.
+
+// Modified by Jari Ruusu,  December 24 2001
+//  - Converted syntax to GNU CPP/assembler syntax
+//  - C programming interface converted back to "old" API
+//  - Minor portability cleanups and speed optimizations
+
+// An AES (Rijndael) implementation for the Pentium. This version only
+// implements the standard AES block length (128 bits, 16 bytes). This code
+// does not preserve the eax, ecx or edx registers or the artihmetic status
+// flags. However, the ebx, esi, edi, and ebp registers are preserved across
+// calls.
+
+// void aes_set_key(aes_context *cx, const unsigned char key[], const int key_len, const int f)
+// void aes_encrypt(const aes_context *cx, const unsigned char in_blk[], unsigned char out_blk[])
+// void aes_decrypt(const aes_context *cx, const unsigned char in_blk[], unsigned char out_blk[])
+
+#if defined(USE_UNDERLINE)
+# define aes_set_key _aes_set_key
+# define aes_encrypt _aes_encrypt
+# define aes_decrypt _aes_decrypt
+#endif
+#if !defined(ALIGN32BYTES)
+# define ALIGN32BYTES 32
+#endif
+
+	.file	"aes-i586.S"
+	.globl	aes_set_key
+	.globl	aes_encrypt
+	.globl	aes_decrypt
+
+#define tlen	1024	// length of each of 4 'xor' arrays (256 32-bit words)
+
+// offsets to parameters with one register pushed onto stack
+
+#define ctx	8	// AES context structure
+#define in_blk	12	// input byte array address parameter
+#define out_blk	16	// output byte array address parameter
+
+// offsets in context structure
+
+#define nkey	0	// key length, size 4
+#define nrnd	4	// number of rounds, size 4
+#define ekey	8	// encryption key schedule base address, size 256
+#define dkey	264	// decryption key schedule base address, size 256
+
+// This macro performs a forward encryption cycle. It is entered with
+// the first previous round column values in %eax, %ebx, %esi and %edi and
+// exits with the final values in the same registers.
+
+#define fwd_rnd(p1,p2)			 \
+	mov	%ebx,(%esp)		;\
+	movzbl	%al,%edx		;\
+	mov	%eax,%ecx		;\
+	mov	p2(%ebp),%eax		;\
+	mov	%edi,4(%esp)		;\
+	mov	p2+12(%ebp),%edi	;\
+	xor	p1(,%edx,4),%eax	;\
+	movzbl	%ch,%edx		;\
+	shr	$16,%ecx		;\
+	mov	p2+4(%ebp),%ebx		;\
+	xor	p1+tlen(,%edx,4),%edi	;\
+	movzbl	%cl,%edx		;\
+	movzbl	%ch,%ecx		;\
+	xor	p1+3*tlen(,%ecx,4),%ebx	;\
+	mov	%esi,%ecx		;\
+	mov	p1+2*tlen(,%edx,4),%esi	;\
+	movzbl	%cl,%edx		;\
+	xor	p1(,%edx,4),%esi	;\
+	movzbl	%ch,%edx		;\
+	shr	$16,%ecx		;\
+	xor	p1+tlen(,%edx,4),%ebx	;\
+	movzbl	%cl,%edx		;\
+	movzbl	%ch,%ecx		;\
+	xor	p1+2*tlen(,%edx,4),%eax	;\
+	mov	(%esp),%edx		;\
+	xor	p1+3*tlen(,%ecx,4),%edi ;\
+	movzbl	%dl,%ecx		;\
+	xor	p2+8(%ebp),%esi		;\
+	xor	p1(,%ecx,4),%ebx	;\
+	movzbl	%dh,%ecx		;\
+	shr	$16,%edx		;\
+	xor	p1+tlen(,%ecx,4),%eax	;\
+	movzbl	%dl,%ecx		;\
+	movzbl	%dh,%edx		;\
+	xor	p1+2*tlen(,%ecx,4),%edi	;\
+	mov	4(%esp),%ecx		;\
+	xor	p1+3*tlen(,%edx,4),%esi ;\
+	movzbl	%cl,%edx		;\
+	xor	p1(,%edx,4),%edi	;\
+	movzbl	%ch,%edx		;\
+	shr	$16,%ecx		;\
+	xor	p1+tlen(,%edx,4),%esi	;\
+	movzbl	%cl,%edx		;\
+	movzbl	%ch,%ecx		;\
+	xor	p1+2*tlen(,%edx,4),%ebx	;\
+	xor	p1+3*tlen(,%ecx,4),%eax
+
+// This macro performs an inverse encryption cycle. It is entered with
+// the first previous round column values in %eax, %ebx, %esi and %edi and
+// exits with the final values in the same registers.
+
+#define inv_rnd(p1,p2)			 \
+	movzbl	%al,%edx		;\
+	mov	%ebx,(%esp)		;\
+	mov	%eax,%ecx		;\
+	mov	p2(%ebp),%eax		;\
+	mov	%edi,4(%esp)		;\
+	mov	p2+4(%ebp),%ebx		;\
+	xor	p1(,%edx,4),%eax	;\
+	movzbl	%ch,%edx		;\
+	shr	$16,%ecx		;\
+	mov	p2+12(%ebp),%edi	;\
+	xor	p1+tlen(,%edx,4),%ebx	;\
+	movzbl	%cl,%edx		;\
+	movzbl	%ch,%ecx		;\
+	xor	p1+3*tlen(,%ecx,4),%edi	;\
+	mov	%esi,%ecx		;\
+	mov	p1+2*tlen(,%edx,4),%esi	;\
+	movzbl	%cl,%edx		;\
+	xor	p1(,%edx,4),%esi	;\
+	movzbl	%ch,%edx		;\
+	shr	$16,%ecx		;\
+	xor	p1+tlen(,%edx,4),%edi	;\
+	movzbl	%cl,%edx		;\
+	movzbl	%ch,%ecx		;\
+	xor	p1+2*tlen(,%edx,4),%eax	;\
+	mov	(%esp),%edx		;\
+	xor	p1+3*tlen(,%ecx,4),%ebx ;\
+	movzbl	%dl,%ecx		;\
+	xor	p2+8(%ebp),%esi		;\
+	xor	p1(,%ecx,4),%ebx	;\
+	movzbl	%dh,%ecx		;\
+	shr	$16,%edx		;\
+	xor	p1+tlen(,%ecx,4),%esi	;\
+	movzbl	%dl,%ecx		;\
+	movzbl	%dh,%edx		;\
+	xor	p1+2*tlen(,%ecx,4),%edi	;\
+	mov	4(%esp),%ecx		;\
+	xor	p1+3*tlen(,%edx,4),%eax ;\
+	movzbl	%cl,%edx		;\
+	xor	p1(,%edx,4),%edi	;\
+	movzbl	%ch,%edx		;\
+	shr	$16,%ecx		;\
+	xor	p1+tlen(,%edx,4),%eax	;\
+	movzbl	%cl,%edx		;\
+	movzbl	%ch,%ecx		;\
+	xor	p1+2*tlen(,%edx,4),%ebx	;\
+	xor	p1+3*tlen(,%ecx,4),%esi
+
+// AES (Rijndael) Encryption Subroutine
+
+	.text
+	.align	ALIGN32BYTES
+aes_encrypt:
+	push	%ebp
+	mov	ctx(%esp),%ebp		// pointer to context
+	mov	in_blk(%esp),%ecx
+	push	%ebx
+	push	%esi
+	push	%edi
+	mov	nrnd(%ebp),%edx		// number of rounds
+	lea	ekey+16(%ebp),%ebp	// key pointer
+
+// input four columns and xor in first round key
+
+	mov	(%ecx),%eax
+	mov	4(%ecx),%ebx
+	mov	8(%ecx),%esi
+	mov	12(%ecx),%edi
+	xor	-16(%ebp),%eax
+	xor	-12(%ebp),%ebx
+	xor	-8(%ebp),%esi
+	xor	-4(%ebp),%edi
+
+	sub	$8,%esp			// space for register saves on stack
+
+	sub	$10,%edx
+	je	aes_15
+	add	$32,%ebp
+	sub	$2,%edx
+	je	aes_13
+	add	$32,%ebp
+
+	fwd_rnd(aes_ft_tab,-64)		// 14 rounds for 256-bit key
+	fwd_rnd(aes_ft_tab,-48)
+aes_13:	fwd_rnd(aes_ft_tab,-32)		// 12 rounds for 192-bit key
+	fwd_rnd(aes_ft_tab,-16)
+aes_15:	fwd_rnd(aes_ft_tab,0)		// 10 rounds for 128-bit key
+	fwd_rnd(aes_ft_tab,16)
+	fwd_rnd(aes_ft_tab,32)
+	fwd_rnd(aes_ft_tab,48)
+	fwd_rnd(aes_ft_tab,64)
+	fwd_rnd(aes_ft_tab,80)
+	fwd_rnd(aes_ft_tab,96)
+	fwd_rnd(aes_ft_tab,112)
+	fwd_rnd(aes_ft_tab,128)
+	fwd_rnd(aes_fl_tab,144)		// last round uses a different table
+
+// move final values to the output array.
+
+	mov	out_blk+20(%esp),%ebp
+	add	$8,%esp
+	mov	%eax,(%ebp)
+	mov	%ebx,4(%ebp)
+	mov	%esi,8(%ebp)
+	mov	%edi,12(%ebp)
+	pop	%edi
+	pop	%esi
+	pop	%ebx
+	pop	%ebp
+	ret
+
+
+// AES (Rijndael) Decryption Subroutine
+
+	.align	ALIGN32BYTES
+aes_decrypt:
+	push	%ebp
+	mov	ctx(%esp),%ebp		// pointer to context
+	mov	in_blk(%esp),%ecx
+	push	%ebx
+	push	%esi
+	push	%edi
+	mov	nrnd(%ebp),%edx		// number of rounds
+	lea	dkey+16(%ebp),%ebp	// key pointer
+
+// input four columns and xor in first round key
+
+	mov	(%ecx),%eax
+	mov	4(%ecx),%ebx
+	mov	8(%ecx),%esi
+	mov	12(%ecx),%edi
+	xor	-16(%ebp),%eax
+	xor	-12(%ebp),%ebx
+	xor	-8(%ebp),%esi
+	xor	-4(%ebp),%edi
+
+	sub	$8,%esp			// space for register saves on stack
+
+	sub	$10,%edx
+	je	aes_25
+	add	$32,%ebp
+	sub	$2,%edx
+	je	aes_23
+	add	$32,%ebp
+
+	inv_rnd(aes_it_tab,-64)		// 14 rounds for 256-bit key
+	inv_rnd(aes_it_tab,-48)
+aes_23:	inv_rnd(aes_it_tab,-32)		// 12 rounds for 192-bit key
+	inv_rnd(aes_it_tab,-16)
+aes_25:	inv_rnd(aes_it_tab,0)		// 10 rounds for 128-bit key
+	inv_rnd(aes_it_tab,16)
+	inv_rnd(aes_it_tab,32)
+	inv_rnd(aes_it_tab,48)
+	inv_rnd(aes_it_tab,64)
+	inv_rnd(aes_it_tab,80)
+	inv_rnd(aes_it_tab,96)
+	inv_rnd(aes_it_tab,112)
+	inv_rnd(aes_it_tab,128)
+	inv_rnd(aes_il_tab,144)		// last round uses a different table
+
+// move final values to the output array.
+
+	mov	out_blk+20(%esp),%ebp
+	add	$8,%esp
+	mov	%eax,(%ebp)
+	mov	%ebx,4(%ebp)
+	mov	%esi,8(%ebp)
+	mov	%edi,12(%ebp)
+	pop	%edi
+	pop	%esi
+	pop	%ebx
+	pop	%ebp
+	ret
+
+// AES (Rijndael) Key Schedule Subroutine
+
+// input/output parameters
+
+#define aes_cx	12	// AES context
+#define in_key	16	// key input array address
+#define key_ln	20	// key length, bytes (16,24,32) or bits (128,192,256)
+#define ed_flg	24	// 0=create both encr/decr keys, 1=create encr key only
+
+// offsets for locals
+
+#define cnt	-4
+#define kpf	-8
+#define slen	8
+
+// This macro performs a column mixing operation on an input 32-bit
+// word to give a 32-bit result. It uses each of the 4 bytes in the
+// the input column to index 4 different tables of 256 32-bit words
+// that are xored together to form the output value.
+
+#define mix_col(p1)			 \
+	movzbl	%bl,%ecx		;\
+	mov	p1(,%ecx,4),%eax	;\
+	movzbl	%bh,%ecx		;\
+	ror	$16,%ebx		;\
+	xor	p1+tlen(,%ecx,4),%eax	;\
+	movzbl	%bl,%ecx		;\
+	xor	p1+2*tlen(,%ecx,4),%eax	;\
+	movzbl	%bh,%ecx		;\
+	xor	p1+3*tlen(,%ecx,4),%eax
+
+// Key Schedule Macros
+
+#define ksc4(p1)			 \
+	rol	$24,%ebx		;\
+	mix_col(aes_fl_tab)		;\
+	ror	$8,%ebx			;\
+	xor	4*p1+aes_rcon_tab,%eax	;\
+	xor	%eax,%esi		;\
+	xor	%esi,%ebp		;\
+	mov	%esi,16*p1(%edi)	;\
+	mov	%ebp,16*p1+4(%edi)	;\
+	xor	%ebp,%edx		;\
+	xor	%edx,%ebx		;\
+	mov	%edx,16*p1+8(%edi)	;\
+	mov	%ebx,16*p1+12(%edi)
+
+#define ksc6(p1)			 \
+	rol	$24,%ebx		;\
+	mix_col(aes_fl_tab)		;\
+	ror	$8,%ebx			;\
+	xor	4*p1+aes_rcon_tab,%eax	;\
+	xor	24*p1-24(%edi),%eax	;\
+	mov	%eax,24*p1(%edi)	;\
+	xor	24*p1-20(%edi),%eax	;\
+	mov	%eax,24*p1+4(%edi)	;\
+	xor	%eax,%esi		;\
+	xor	%esi,%ebp		;\
+	mov	%esi,24*p1+8(%edi)	;\
+	mov	%ebp,24*p1+12(%edi)	;\
+	xor	%ebp,%edx		;\
+	xor	%edx,%ebx		;\
+	mov	%edx,24*p1+16(%edi)	;\
+	mov	%ebx,24*p1+20(%edi)
+
+#define ksc8(p1)			 \
+	rol	$24,%ebx		;\
+	mix_col(aes_fl_tab)		;\
+	ror	$8,%ebx			;\
+	xor	4*p1+aes_rcon_tab,%eax	;\
+	xor	32*p1-32(%edi),%eax	;\
+	mov	%eax,32*p1(%edi)	;\
+	xor	32*p1-28(%edi),%eax	;\
+	mov	%eax,32*p1+4(%edi)	;\
+	xor	32*p1-24(%edi),%eax	;\
+	mov	%eax,32*p1+8(%edi)	;\
+	xor	32*p1-20(%edi),%eax	;\
+	mov	%eax,32*p1+12(%edi)	;\
+	push	%ebx			;\
+	mov	%eax,%ebx		;\
+	mix_col(aes_fl_tab)		;\
+	pop	%ebx			;\
+	xor	%eax,%esi		;\
+	xor	%esi,%ebp		;\
+	mov	%esi,32*p1+16(%edi)	;\
+	mov	%ebp,32*p1+20(%edi)	;\
+	xor	%ebp,%edx		;\
+	xor	%edx,%ebx		;\
+	mov	%edx,32*p1+24(%edi)	;\
+	mov	%ebx,32*p1+28(%edi)
+
+	.align	ALIGN32BYTES
+aes_set_key:
+	pushfl
+	push	%ebp
+	mov	%esp,%ebp
+	sub	$slen,%esp
+	push	%ebx
+	push	%esi
+	push	%edi
+
+	mov	aes_cx(%ebp),%edx	// edx -> AES context
+
+	mov	key_ln(%ebp),%ecx	// key length
+	cmpl	$128,%ecx
+	jb	aes_30
+	shr	$3,%ecx
+aes_30:	cmpl	$32,%ecx
+	je	aes_32
+	cmpl	$24,%ecx
+	je	aes_32
+	mov	$16,%ecx
+aes_32:	shr	$2,%ecx
+	mov	%ecx,nkey(%edx)
+
+	lea	6(%ecx),%eax		// 10/12/14 for 4/6/8 32-bit key length
+	mov	%eax,nrnd(%edx)
+
+	mov	in_key(%ebp),%esi	// key input array
+	lea	ekey(%edx),%edi		// key position in AES context
+	cld
+	push	%ebp
+	mov	%ecx,%eax		// save key length in eax
+	rep ;	movsl			// words in the key schedule
+	mov	-4(%esi),%ebx		// put some values in registers
+	mov	-8(%esi),%edx		// to allow faster code
+	mov	-12(%esi),%ebp
+	mov	-16(%esi),%esi
+
+	cmpl	$4,%eax			// jump on key size
+	je	aes_36
+	cmpl	$6,%eax
+	je	aes_35
+
+	ksc8(0)
+	ksc8(1)
+	ksc8(2)
+	ksc8(3)
+	ksc8(4)
+	ksc8(5)
+	ksc8(6)
+	jmp	aes_37
+aes_35:	ksc6(0)
+	ksc6(1)
+	ksc6(2)
+	ksc6(3)
+	ksc6(4)
+	ksc6(5)
+	ksc6(6)
+	ksc6(7)
+	jmp	aes_37
+aes_36:	ksc4(0)
+	ksc4(1)
+	ksc4(2)
+	ksc4(3)
+	ksc4(4)
+	ksc4(5)
+	ksc4(6)
+	ksc4(7)
+	ksc4(8)
+	ksc4(9)
+aes_37:	pop	%ebp
+	mov	aes_cx(%ebp),%edx	// edx -> AES context
+	cmpl	$0,ed_flg(%ebp)
+	jne	aes_39
+
+// compile decryption key schedule from encryption schedule - reverse
+// order and do mix_column operation on round keys except first and last
+
+	mov	nrnd(%edx),%eax		// kt = cx->d_key + nc * cx->Nrnd
+	shl	$2,%eax
+	lea	dkey(%edx,%eax,4),%edi
+	lea	ekey(%edx),%esi		// kf = cx->e_key
+
+	movsl				// copy first round key (unmodified)
+	movsl
+	movsl
+	movsl
+	sub	$32,%edi
+	movl	$1,cnt(%ebp)
+aes_38:					// do mix column on each column of
+	lodsl				// each round key
+	mov	%eax,%ebx
+	mix_col(aes_im_tab)
+	stosl
+	lodsl
+	mov	%eax,%ebx
+	mix_col(aes_im_tab)
+	stosl
+	lodsl
+	mov	%eax,%ebx
+	mix_col(aes_im_tab)
+	stosl
+	lodsl
+	mov	%eax,%ebx
+	mix_col(aes_im_tab)
+	stosl
+	sub	$32,%edi
+
+	incl	cnt(%ebp)
+	mov	cnt(%ebp),%eax
+	cmp	nrnd(%edx),%eax
+	jb	aes_38
+
+	movsl				// copy last round key (unmodified)
+	movsl
+	movsl
+	movsl
+aes_39:	pop	%edi
+	pop	%esi
+	pop	%ebx
+	mov	%ebp,%esp
+	pop	%ebp
+	popfl
+	ret
+
+
+// finite field multiplies by {02}, {04} and {08}
+
+#define f2(x)	((x<<1)^(((x>>7)&1)*0x11b))
+#define f4(x)	((x<<2)^(((x>>6)&1)*0x11b)^(((x>>6)&2)*0x11b))
+#define f8(x)	((x<<3)^(((x>>5)&1)*0x11b)^(((x>>5)&2)*0x11b)^(((x>>5)&4)*0x11b))
+
+// finite field multiplies required in table generation
+
+#define f3(x)	(f2(x) ^ x)
+#define f9(x)	(f8(x) ^ x)
+#define fb(x)	(f8(x) ^ f2(x) ^ x)
+#define fd(x)	(f8(x) ^ f4(x) ^ x)
+#define fe(x)	(f8(x) ^ f4(x) ^ f2(x))
+
+// These defines generate the forward table entries
+
+#define u0(x)	((f3(x) << 24) | (x << 16) | (x << 8) | f2(x))
+#define u1(x)	((x << 24) | (x << 16) | (f2(x) << 8) | f3(x))
+#define u2(x)	((x << 24) | (f2(x) << 16) | (f3(x) << 8) | x)
+#define u3(x)	((f2(x) << 24) | (f3(x) << 16) | (x << 8) | x)
+
+// These defines generate the inverse table entries
+
+#define v0(x)	((fb(x) << 24) | (fd(x) << 16) | (f9(x) << 8) | fe(x))
+#define v1(x)	((fd(x) << 24) | (f9(x) << 16) | (fe(x) << 8) | fb(x))
+#define v2(x)	((f9(x) << 24) | (fe(x) << 16) | (fb(x) << 8) | fd(x))
+#define v3(x)	((fe(x) << 24) | (fb(x) << 16) | (fd(x) << 8) | f9(x))
+
+// These defines generate entries for the last round tables
+
+#define w0(x)	(x)
+#define w1(x)	(x <<  8)
+#define w2(x)	(x << 16)
+#define w3(x)	(x << 24)
+
+// macro to generate inverse mix column tables (needed for the key schedule)
+
+#define im_data0(p1) \
+	.long	p1(0x00),p1(0x01),p1(0x02),p1(0x03),p1(0x04),p1(0x05),p1(0x06),p1(0x07) ;\
+	.long	p1(0x08),p1(0x09),p1(0x0a),p1(0x0b),p1(0x0c),p1(0x0d),p1(0x0e),p1(0x0f) ;\
+	.long	p1(0x10),p1(0x11),p1(0x12),p1(0x13),p1(0x14),p1(0x15),p1(0x16),p1(0x17) ;\
+	.long	p1(0x18),p1(0x19),p1(0x1a),p1(0x1b),p1(0x1c),p1(0x1d),p1(0x1e),p1(0x1f)
+#define im_data1(p1) \
+	.long	p1(0x20),p1(0x21),p1(0x22),p1(0x23),p1(0x24),p1(0x25),p1(0x26),p1(0x27) ;\
+	.long	p1(0x28),p1(0x29),p1(0x2a),p1(0x2b),p1(0x2c),p1(0x2d),p1(0x2e),p1(0x2f) ;\
+	.long	p1(0x30),p1(0x31),p1(0x32),p1(0x33),p1(0x34),p1(0x35),p1(0x36),p1(0x37) ;\
+	.long	p1(0x38),p1(0x39),p1(0x3a),p1(0x3b),p1(0x3c),p1(0x3d),p1(0x3e),p1(0x3f)
+#define im_data2(p1) \
+	.long	p1(0x40),p1(0x41),p1(0x42),p1(0x43),p1(0x44),p1(0x45),p1(0x46),p1(0x47) ;\
+	.long	p1(0x48),p1(0x49),p1(0x4a),p1(0x4b),p1(0x4c),p1(0x4d),p1(0x4e),p1(0x4f) ;\
+	.long	p1(0x50),p1(0x51),p1(0x52),p1(0x53),p1(0x54),p1(0x55),p1(0x56),p1(0x57) ;\
+	.long	p1(0x58),p1(0x59),p1(0x5a),p1(0x5b),p1(0x5c),p1(0x5d),p1(0x5e),p1(0x5f)
+#define im_data3(p1) \
+	.long	p1(0x60),p1(0x61),p1(0x62),p1(0x63),p1(0x64),p1(0x65),p1(0x66),p1(0x67) ;\
+	.long	p1(0x68),p1(0x69),p1(0x6a),p1(0x6b),p1(0x6c),p1(0x6d),p1(0x6e),p1(0x6f) ;\
+	.long	p1(0x70),p1(0x71),p1(0x72),p1(0x73),p1(0x74),p1(0x75),p1(0x76),p1(0x77) ;\
+	.long	p1(0x78),p1(0x79),p1(0x7a),p1(0x7b),p1(0x7c),p1(0x7d),p1(0x7e),p1(0x7f)
+#define im_data4(p1) \
+	.long	p1(0x80),p1(0x81),p1(0x82),p1(0x83),p1(0x84),p1(0x85),p1(0x86),p1(0x87) ;\
+	.long	p1(0x88),p1(0x89),p1(0x8a),p1(0x8b),p1(0x8c),p1(0x8d),p1(0x8e),p1(0x8f) ;\
+	.long	p1(0x90),p1(0x91),p1(0x92),p1(0x93),p1(0x94),p1(0x95),p1(0x96),p1(0x97) ;\
+	.long	p1(0x98),p1(0x99),p1(0x9a),p1(0x9b),p1(0x9c),p1(0x9d),p1(0x9e),p1(0x9f)
+#define im_data5(p1) \
+	.long	p1(0xa0),p1(0xa1),p1(0xa2),p1(0xa3),p1(0xa4),p1(0xa5),p1(0xa6),p1(0xa7) ;\
+	.long	p1(0xa8),p1(0xa9),p1(0xaa),p1(0xab),p1(0xac),p1(0xad),p1(0xae),p1(0xaf) ;\
+	.long	p1(0xb0),p1(0xb1),p1(0xb2),p1(0xb3),p1(0xb4),p1(0xb5),p1(0xb6),p1(0xb7) ;\
+	.long	p1(0xb8),p1(0xb9),p1(0xba),p1(0xbb),p1(0xbc),p1(0xbd),p1(0xbe),p1(0xbf)
+#define im_data6(p1) \
+	.long	p1(0xc0),p1(0xc1),p1(0xc2),p1(0xc3),p1(0xc4),p1(0xc5),p1(0xc6),p1(0xc7) ;\
+	.long	p1(0xc8),p1(0xc9),p1(0xca),p1(0xcb),p1(0xcc),p1(0xcd),p1(0xce),p1(0xcf) ;\
+	.long	p1(0xd0),p1(0xd1),p1(0xd2),p1(0xd3),p1(0xd4),p1(0xd5),p1(0xd6),p1(0xd7) ;\
+	.long	p1(0xd8),p1(0xd9),p1(0xda),p1(0xdb),p1(0xdc),p1(0xdd),p1(0xde),p1(0xdf)
+#define im_data7(p1) \
+	.long	p1(0xe0),p1(0xe1),p1(0xe2),p1(0xe3),p1(0xe4),p1(0xe5),p1(0xe6),p1(0xe7) ;\
+	.long	p1(0xe8),p1(0xe9),p1(0xea),p1(0xeb),p1(0xec),p1(0xed),p1(0xee),p1(0xef) ;\
+	.long	p1(0xf0),p1(0xf1),p1(0xf2),p1(0xf3),p1(0xf4),p1(0xf5),p1(0xf6),p1(0xf7) ;\
+	.long	p1(0xf8),p1(0xf9),p1(0xfa),p1(0xfb),p1(0xfc),p1(0xfd),p1(0xfe),p1(0xff)
+
+// S-box data - 256 entries
+
+#define sb_data0(p1) \
+	.long	p1(0x63),p1(0x7c),p1(0x77),p1(0x7b),p1(0xf2),p1(0x6b),p1(0x6f),p1(0xc5) ;\
+	.long	p1(0x30),p1(0x01),p1(0x67),p1(0x2b),p1(0xfe),p1(0xd7),p1(0xab),p1(0x76) ;\
+	.long	p1(0xca),p1(0x82),p1(0xc9),p1(0x7d),p1(0xfa),p1(0x59),p1(0x47),p1(0xf0) ;\
+	.long	p1(0xad),p1(0xd4),p1(0xa2),p1(0xaf),p1(0x9c),p1(0xa4),p1(0x72),p1(0xc0)
+#define sb_data1(p1) \
+	.long	p1(0xb7),p1(0xfd),p1(0x93),p1(0x26),p1(0x36),p1(0x3f),p1(0xf7),p1(0xcc) ;\
+	.long	p1(0x34),p1(0xa5),p1(0xe5),p1(0xf1),p1(0x71),p1(0xd8),p1(0x31),p1(0x15) ;\
+	.long	p1(0x04),p1(0xc7),p1(0x23),p1(0xc3),p1(0x18),p1(0x96),p1(0x05),p1(0x9a) ;\
+	.long	p1(0x07),p1(0x12),p1(0x80),p1(0xe2),p1(0xeb),p1(0x27),p1(0xb2),p1(0x75)
+#define sb_data2(p1) \
+	.long	p1(0x09),p1(0x83),p1(0x2c),p1(0x1a),p1(0x1b),p1(0x6e),p1(0x5a),p1(0xa0) ;\
+	.long	p1(0x52),p1(0x3b),p1(0xd6),p1(0xb3),p1(0x29),p1(0xe3),p1(0x2f),p1(0x84) ;\
+	.long	p1(0x53),p1(0xd1),p1(0x00),p1(0xed),p1(0x20),p1(0xfc),p1(0xb1),p1(0x5b) ;\
+	.long	p1(0x6a),p1(0xcb),p1(0xbe),p1(0x39),p1(0x4a),p1(0x4c),p1(0x58),p1(0xcf)
+#define sb_data3(p1) \
+	.long	p1(0xd0),p1(0xef),p1(0xaa),p1(0xfb),p1(0x43),p1(0x4d),p1(0x33),p1(0x85) ;\
+	.long	p1(0x45),p1(0xf9),p1(0x02),p1(0x7f),p1(0x50),p1(0x3c),p1(0x9f),p1(0xa8) ;\
+	.long	p1(0x51),p1(0xa3),p1(0x40),p1(0x8f),p1(0x92),p1(0x9d),p1(0x38),p1(0xf5) ;\
+	.long	p1(0xbc),p1(0xb6),p1(0xda),p1(0x21),p1(0x10),p1(0xff),p1(0xf3),p1(0xd2)
+#define sb_data4(p1) \
+	.long	p1(0xcd),p1(0x0c),p1(0x13),p1(0xec),p1(0x5f),p1(0x97),p1(0x44),p1(0x17) ;\
+	.long	p1(0xc4),p1(0xa7),p1(0x7e),p1(0x3d),p1(0x64),p1(0x5d),p1(0x19),p1(0x73) ;\
+	.long	p1(0x60),p1(0x81),p1(0x4f),p1(0xdc),p1(0x22),p1(0x2a),p1(0x90),p1(0x88) ;\
+	.long	p1(0x46),p1(0xee),p1(0xb8),p1(0x14),p1(0xde),p1(0x5e),p1(0x0b),p1(0xdb)
+#define sb_data5(p1) \
+	.long	p1(0xe0),p1(0x32),p1(0x3a),p1(0x0a),p1(0x49),p1(0x06),p1(0x24),p1(0x5c) ;\
+	.long	p1(0xc2),p1(0xd3),p1(0xac),p1(0x62),p1(0x91),p1(0x95),p1(0xe4),p1(0x79) ;\
+	.long	p1(0xe7),p1(0xc8),p1(0x37),p1(0x6d),p1(0x8d),p1(0xd5),p1(0x4e),p1(0xa9) ;\
+	.long	p1(0x6c),p1(0x56),p1(0xf4),p1(0xea),p1(0x65),p1(0x7a),p1(0xae),p1(0x08)
+#define sb_data6(p1) \
+	.long	p1(0xba),p1(0x78),p1(0x25),p1(0x2e),p1(0x1c),p1(0xa6),p1(0xb4),p1(0xc6) ;\
+	.long	p1(0xe8),p1(0xdd),p1(0x74),p1(0x1f),p1(0x4b),p1(0xbd),p1(0x8b),p1(0x8a) ;\
+	.long	p1(0x70),p1(0x3e),p1(0xb5),p1(0x66),p1(0x48),p1(0x03),p1(0xf6),p1(0x0e) ;\
+	.long	p1(0x61),p1(0x35),p1(0x57),p1(0xb9),p1(0x86),p1(0xc1),p1(0x1d),p1(0x9e)
+#define sb_data7(p1) \
+	.long	p1(0xe1),p1(0xf8),p1(0x98),p1(0x11),p1(0x69),p1(0xd9),p1(0x8e),p1(0x94) ;\
+	.long	p1(0x9b),p1(0x1e),p1(0x87),p1(0xe9),p1(0xce),p1(0x55),p1(0x28),p1(0xdf) ;\
+	.long	p1(0x8c),p1(0xa1),p1(0x89),p1(0x0d),p1(0xbf),p1(0xe6),p1(0x42),p1(0x68) ;\
+	.long	p1(0x41),p1(0x99),p1(0x2d),p1(0x0f),p1(0xb0),p1(0x54),p1(0xbb),p1(0x16)
+
+// Inverse S-box data - 256 entries
+
+#define ib_data0(p1) \
+	.long	p1(0x52),p1(0x09),p1(0x6a),p1(0xd5),p1(0x30),p1(0x36),p1(0xa5),p1(0x38) ;\
+	.long	p1(0xbf),p1(0x40),p1(0xa3),p1(0x9e),p1(0x81),p1(0xf3),p1(0xd7),p1(0xfb) ;\
+	.long	p1(0x7c),p1(0xe3),p1(0x39),p1(0x82),p1(0x9b),p1(0x2f),p1(0xff),p1(0x87) ;\
+	.long	p1(0x34),p1(0x8e),p1(0x43),p1(0x44),p1(0xc4),p1(0xde),p1(0xe9),p1(0xcb)
+#define ib_data1(p1) \
+	.long	p1(0x54),p1(0x7b),p1(0x94),p1(0x32),p1(0xa6),p1(0xc2),p1(0x23),p1(0x3d) ;\
+	.long	p1(0xee),p1(0x4c),p1(0x95),p1(0x0b),p1(0x42),p1(0xfa),p1(0xc3),p1(0x4e) ;\
+	.long	p1(0x08),p1(0x2e),p1(0xa1),p1(0x66),p1(0x28),p1(0xd9),p1(0x24),p1(0xb2) ;\
+	.long	p1(0x76),p1(0x5b),p1(0xa2),p1(0x49),p1(0x6d),p1(0x8b),p1(0xd1),p1(0x25)
+#define ib_data2(p1) \
+	.long	p1(0x72),p1(0xf8),p1(0xf6),p1(0x64),p1(0x86),p1(0x68),p1(0x98),p1(0x16) ;\
+	.long	p1(0xd4),p1(0xa4),p1(0x5c),p1(0xcc),p1(0x5d),p1(0x65),p1(0xb6),p1(0x92) ;\
+	.long	p1(0x6c),p1(0x70),p1(0x48),p1(0x50),p1(0xfd),p1(0xed),p1(0xb9),p1(0xda) ;\
+	.long	p1(0x5e),p1(0x15),p1(0x46),p1(0x57),p1(0xa7),p1(0x8d),p1(0x9d),p1(0x84)
+#define ib_data3(p1) \
+	.long	p1(0x90),p1(0xd8),p1(0xab),p1(0x00),p1(0x8c),p1(0xbc),p1(0xd3),p1(0x0a) ;\
+	.long	p1(0xf7),p1(0xe4),p1(0x58),p1(0x05),p1(0xb8),p1(0xb3),p1(0x45),p1(0x06) ;\
+	.long	p1(0xd0),p1(0x2c),p1(0x1e),p1(0x8f),p1(0xca),p1(0x3f),p1(0x0f),p1(0x02) ;\
+	.long	p1(0xc1),p1(0xaf),p1(0xbd),p1(0x03),p1(0x01),p1(0x13),p1(0x8a),p1(0x6b)
+#define ib_data4(p1) \
+	.long	p1(0x3a),p1(0x91),p1(0x11),p1(0x41),p1(0x4f),p1(0x67),p1(0xdc),p1(0xea) ;\
+	.long	p1(0x97),p1(0xf2),p1(0xcf),p1(0xce),p1(0xf0),p1(0xb4),p1(0xe6),p1(0x73) ;\
+	.long	p1(0x96),p1(0xac),p1(0x74),p1(0x22),p1(0xe7),p1(0xad),p1(0x35),p1(0x85) ;\
+	.long	p1(0xe2),p1(0xf9),p1(0x37),p1(0xe8),p1(0x1c),p1(0x75),p1(0xdf),p1(0x6e)
+#define ib_data5(p1) \
+	.long	p1(0x47),p1(0xf1),p1(0x1a),p1(0x71),p1(0x1d),p1(0x29),p1(0xc5),p1(0x89) ;\
+	.long	p1(0x6f),p1(0xb7),p1(0x62),p1(0x0e),p1(0xaa),p1(0x18),p1(0xbe),p1(0x1b) ;\
+	.long	p1(0xfc),p1(0x56),p1(0x3e),p1(0x4b),p1(0xc6),p1(0xd2),p1(0x79),p1(0x20) ;\
+	.long	p1(0x9a),p1(0xdb),p1(0xc0),p1(0xfe),p1(0x78),p1(0xcd),p1(0x5a),p1(0xf4)
+#define ib_data6(p1) \
+	.long	p1(0x1f),p1(0xdd),p1(0xa8),p1(0x33),p1(0x88),p1(0x07),p1(0xc7),p1(0x31) ;\
+	.long	p1(0xb1),p1(0x12),p1(0x10),p1(0x59),p1(0x27),p1(0x80),p1(0xec),p1(0x5f) ;\
+	.long	p1(0x60),p1(0x51),p1(0x7f),p1(0xa9),p1(0x19),p1(0xb5),p1(0x4a),p1(0x0d) ;\
+	.long	p1(0x2d),p1(0xe5),p1(0x7a),p1(0x9f),p1(0x93),p1(0xc9),p1(0x9c),p1(0xef)
+#define ib_data7(p1) \
+	.long	p1(0xa0),p1(0xe0),p1(0x3b),p1(0x4d),p1(0xae),p1(0x2a),p1(0xf5),p1(0xb0) ;\
+	.long	p1(0xc8),p1(0xeb),p1(0xbb),p1(0x3c),p1(0x83),p1(0x53),p1(0x99),p1(0x61) ;\
+	.long	p1(0x17),p1(0x2b),p1(0x04),p1(0x7e),p1(0xba),p1(0x77),p1(0xd6),p1(0x26) ;\
+	.long	p1(0xe1),p1(0x69),p1(0x14),p1(0x63),p1(0x55),p1(0x21),p1(0x0c),p1(0x7d)
+
+// The rcon_table (needed for the key schedule)
+//
+// Here is original Dr Brian Gladman's source code:
+//	_rcon_tab:
+//	%assign x   1
+//	%rep 29
+//	    dd  x
+//	%assign x f2(x)
+//	%endrep
+//
+// Here is precomputed output (it's more portable this way):
+
+	.align	ALIGN32BYTES
+aes_rcon_tab:
+	.long	0x01,0x02,0x04,0x08,0x10,0x20,0x40,0x80
+	.long	0x1b,0x36,0x6c,0xd8,0xab,0x4d,0x9a,0x2f
+	.long	0x5e,0xbc,0x63,0xc6,0x97,0x35,0x6a,0xd4
+	.long	0xb3,0x7d,0xfa,0xef,0xc5
+
+// The forward xor tables
+
+	.align	ALIGN32BYTES
+aes_ft_tab:
+	sb_data0(u0)
+	sb_data1(u0)
+	sb_data2(u0)
+	sb_data3(u0)
+	sb_data4(u0)
+	sb_data5(u0)
+	sb_data6(u0)
+	sb_data7(u0)
+
+	sb_data0(u1)
+	sb_data1(u1)
+	sb_data2(u1)
+	sb_data3(u1)
+	sb_data4(u1)
+	sb_data5(u1)
+	sb_data6(u1)
+	sb_data7(u1)
+
+	sb_data0(u2)
+	sb_data1(u2)
+	sb_data2(u2)
+	sb_data3(u2)
+	sb_data4(u2)
+	sb_data5(u2)
+	sb_data6(u2)
+	sb_data7(u2)
+
+	sb_data0(u3)
+	sb_data1(u3)
+	sb_data2(u3)
+	sb_data3(u3)
+	sb_data4(u3)
+	sb_data5(u3)
+	sb_data6(u3)
+	sb_data7(u3)
+
+	.align	ALIGN32BYTES
+aes_fl_tab:
+	sb_data0(w0)
+	sb_data1(w0)
+	sb_data2(w0)
+	sb_data3(w0)
+	sb_data4(w0)
+	sb_data5(w0)
+	sb_data6(w0)
+	sb_data7(w0)
+
+	sb_data0(w1)
+	sb_data1(w1)
+	sb_data2(w1)
+	sb_data3(w1)
+	sb_data4(w1)
+	sb_data5(w1)
+	sb_data6(w1)
+	sb_data7(w1)
+
+	sb_data0(w2)
+	sb_data1(w2)
+	sb_data2(w2)
+	sb_data3(w2)
+	sb_data4(w2)
+	sb_data5(w2)
+	sb_data6(w2)
+	sb_data7(w2)
+
+	sb_data0(w3)
+	sb_data1(w3)
+	sb_data2(w3)
+	sb_data3(w3)
+	sb_data4(w3)
+	sb_data5(w3)
+	sb_data6(w3)
+	sb_data7(w3)
+
+// The inverse xor tables
+
+	.align	ALIGN32BYTES
+aes_it_tab:
+	ib_data0(v0)
+	ib_data1(v0)
+	ib_data2(v0)
+	ib_data3(v0)
+	ib_data4(v0)
+	ib_data5(v0)
+	ib_data6(v0)
+	ib_data7(v0)
+
+	ib_data0(v1)
+	ib_data1(v1)
+	ib_data2(v1)
+	ib_data3(v1)
+	ib_data4(v1)
+	ib_data5(v1)
+	ib_data6(v1)
+	ib_data7(v1)
+
+	ib_data0(v2)
+	ib_data1(v2)
+	ib_data2(v2)
+	ib_data3(v2)
+	ib_data4(v2)
+	ib_data5(v2)
+	ib_data6(v2)
+	ib_data7(v2)
+
+	ib_data0(v3)
+	ib_data1(v3)
+	ib_data2(v3)
+	ib_data3(v3)
+	ib_data4(v3)
+	ib_data5(v3)
+	ib_data6(v3)
+	ib_data7(v3)
+
+	.align	ALIGN32BYTES
+aes_il_tab:
+	ib_data0(w0)
+	ib_data1(w0)
+	ib_data2(w0)
+	ib_data3(w0)
+	ib_data4(w0)
+	ib_data5(w0)
+	ib_data6(w0)
+	ib_data7(w0)
+
+	ib_data0(w1)
+	ib_data1(w1)
+	ib_data2(w1)
+	ib_data3(w1)
+	ib_data4(w1)
+	ib_data5(w1)
+	ib_data6(w1)
+	ib_data7(w1)
+
+	ib_data0(w2)
+	ib_data1(w2)
+	ib_data2(w2)
+	ib_data3(w2)
+	ib_data4(w2)
+	ib_data5(w2)
+	ib_data6(w2)
+	ib_data7(w2)
+
+	ib_data0(w3)
+	ib_data1(w3)
+	ib_data2(w3)
+	ib_data3(w3)
+	ib_data4(w3)
+	ib_data5(w3)
+	ib_data6(w3)
+	ib_data7(w3)
+
+// The inverse mix column tables
+
+	.align	ALIGN32BYTES
+aes_im_tab:
+	im_data0(v0)
+	im_data1(v0)
+	im_data2(v0)
+	im_data3(v0)
+	im_data4(v0)
+	im_data5(v0)
+	im_data6(v0)
+	im_data7(v0)
+
+	im_data0(v1)
+	im_data1(v1)
+	im_data2(v1)
+	im_data3(v1)
+	im_data4(v1)
+	im_data5(v1)
+	im_data6(v1)
+	im_data7(v1)
+
+	im_data0(v2)
+	im_data1(v2)
+	im_data2(v2)
+	im_data3(v2)
+	im_data4(v2)
+	im_data5(v2)
+	im_data6(v2)
+	im_data7(v2)
+
+	im_data0(v3)
+	im_data1(v3)
+	im_data2(v3)
+	im_data3(v3)
+	im_data4(v3)
+	im_data5(v3)
+	im_data6(v3)
+	im_data7(v3)
diff --git a/lib/libcrypto/libaes/test_main.c b/lib/libcrypto/libaes/test_main.c
new file mode 100644
index 000000000..5fd4599be
--- /dev/null
+++ b/lib/libcrypto/libaes/test_main.c
@@ -0,0 +1,41 @@
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include "aes_cbc.h"
+#define AES_BLOCK_SIZE	16
+#define KEY_SIZE 	128	/* bits */
+#define KEY 		"1234567890123456"
+#define STR 		"hola guaso como estaisss ... 012"
+#define STRSZ		(sizeof(STR)-1)
+
+#define EMT_AESCBC_BLKLEN AES_BLOCK_SIZE
+#define AES_CONTEXT_T  aes_context
+#define EMT_ESPAES_KEY_SZ 16
+int pretty_print(const unsigned char *buf, int count) {
+	int i=0;
+	for (;i<count;i++) {
+		if (i%8==0) putchar(' ');
+		if (i%16==0) putchar('\n');
+		printf ("%02hhx ", buf[i]);
+	}
+	putchar('\n');
+	return i;
+}
+//#define SIZE STRSZ/2
+#define SIZE STRSZ
+int main() {
+	int ret;
+	char buf0[SIZE+1], buf1[SIZE+1];
+	char IV[AES_BLOCK_SIZE]="\0\0\0\0\0\0\0\0" "\0\0\0\0\0\0\0\0";
+	aes_context ac;	
+	AES_set_key(&ac, KEY, KEY_SIZE);
+	//pretty_print((char *)&ac.aes_e_key, sizeof(ac.aes_e_key));
+	memset(buf0, 0, sizeof (buf0));
+	memset(buf1, 0, sizeof (buf1));
+	ret=AES_cbc_encrypt(&ac, STR, buf0, SIZE, IV, 1);
+	pretty_print(buf0, SIZE);
+	printf("size=%d ret=%d\n%s\n", SIZE, ret, buf0);
+	ret=AES_cbc_encrypt(&ac, buf0, buf1, SIZE, IV, 0);
+	printf("size=%d ret=%d\n%s\n", SIZE, ret, buf1);
+	return 0;
+}
diff --git a/lib/libcrypto/libaes/test_main_mac.c b/lib/libcrypto/libaes/test_main_mac.c
new file mode 100644
index 000000000..eea47dc9c
--- /dev/null
+++ b/lib/libcrypto/libaes/test_main_mac.c
@@ -0,0 +1,30 @@
+#include <stdio.h>
+#include <sys/types.h>
+#include <string.h>
+#include "aes.h"
+#include "aes_xcbc_mac.h"
+#define STR "Hola guasssso c|mo estais ...012"  
+void print_hash(const __u8 *hash) {
+	printf("%08x %08x %08x %08x\n", 
+			*(__u32*)(&hash[0]), 
+			*(__u32*)(&hash[4]), 
+			*(__u32*)(&hash[8]), 
+			*(__u32*)(&hash[12]));
+}
+int main(int argc, char *argv[]) {
+	aes_block key= { 0xdeadbeef, 0xceedcaca, 0xcafebabe, 0xff010204 };
+	__u8  hash[16];
+	char *str = argv[1];
+	aes_context_mac ctx;
+	if (str==NULL) {
+		fprintf(stderr, "pasame el str\n");
+		return 255;
+	}
+	AES_xcbc_mac_set_key(&ctx, (__u8 *)&key, sizeof(key));
+	AES_xcbc_mac_hash(&ctx, str, strlen(str), hash);
+	print_hash(hash);
+	str[2]='x';
+	AES_xcbc_mac_hash(&ctx, str, strlen(str), hash);
+	print_hash(hash);
+	return 0;
+}
diff --git a/lib/libcrypto/libblowfish/COPYRIGHT b/lib/libcrypto/libblowfish/COPYRIGHT
new file mode 100644
index 000000000..685722350
--- /dev/null
+++ b/lib/libcrypto/libblowfish/COPYRIGHT
@@ -0,0 +1,46 @@
+Copyright (C) 1995-1997 Eric Young (eay@cryptsoft.com)
+All rights reserved.
+
+This package is an Blowfish implementation written
+by Eric Young (eay@cryptsoft.com).
+
+This library is free for commercial and non-commercial use as long as
+the following conditions are aheared to.  The following conditions
+apply to all code found in this distribution.
+
+Copyright remains Eric Young's, and as such any Copyright notices in
+the code are not to be removed.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+1. Redistributions of source code must retain the copyright
+   notice, this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+3. All advertising materials mentioning features or use of this software
+   must display the following acknowledgement:
+   This product includes software developed by Eric Young (eay@cryptsoft.com)
+
+THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGE.
+
+The license and distribution terms for any publically available version or
+derivative of this code cannot be changed.  i.e. this code cannot simply be
+copied and put under another distrubution license
+[including the GNU Public License.]
+
+The reason behind this being stated in this direct manner is past
+experience in code simply being copied and the attribution removed
+from it and then being distributed as part of other packages. This
+implementation was a non-trivial and unpaid effort.
diff --git a/lib/libcrypto/libblowfish/INSTALL b/lib/libcrypto/libblowfish/INSTALL
new file mode 100644
index 000000000..3b2592353
--- /dev/null
+++ b/lib/libcrypto/libblowfish/INSTALL
@@ -0,0 +1,14 @@
+This Eric Young's blowfish implementation, taken from his SSLeay library
+and made available as a separate library.
+ 
+The version number (0.7.2m) is the SSLeay version that this library was
+taken from.
+ 
+To build, just unpack and type make.
+If you are not using gcc, edit the Makefile.
+If you are compiling for an x86 box, try the assembler (it needs improving).
+There are also some compile time options that can improve performance,
+these are documented in the Makefile.
+ 
+eric 15-Apr-1997
+ 
diff --git a/lib/libcrypto/libblowfish/Makefile b/lib/libcrypto/libblowfish/Makefile
new file mode 100644
index 000000000..62724042b
--- /dev/null
+++ b/lib/libcrypto/libblowfish/Makefile
@@ -0,0 +1,121 @@
+#
+# SSLeay/crypto/blowfish/Makefile
+#
+
+DIR=	bf
+TOP=	../..
+CC=	cc
+CPP=	$(CC) -E
+INC=-I ../include 
+CFLAG=-g -D__KERNEL__ -I/usr/src/linux/include
+INSTALL_PREFIX=
+OPENSSLDIR=     /usr/local/ssl
+INSTALLTOP=/usr/local/ssl
+MAKE=		make -f Makefile.ssl
+MAKEDEPEND=	$(TOP)/util/domd $(TOP)
+MAKEFILE=	Makefile.ssl
+AR=		ar r
+RANLIB=		ranlib
+PERL=		perl
+
+CFLAGS= $(INC) $(CFLAG)
+
+.c.o:
+	$(CC) $(CPPFLAGS) $(CFLAGS) $(INC) -c $< -o $@
+
+BF_ASM-i586 := bf-586.pl
+BF_ASM-i686 := bf-686.pl
+BF_ENC := bf_enc.o
+
+ASM-$(ARCH_ASM):=1
+ASM_X86:=$(ASM-i586)$(ASM-i686)
+ifneq ($(strip $(ASM_X86)),)
+	BF_ENC=	asm/bx86-elf.o
+	BF_ASM= $(BF_ASM-$(ARCH_ASM))
+endif
+
+
+GENERAL=Makefile
+TEST=bftest.c
+APPS=
+
+LIB=libblowfish.a
+LIBSRC=bf_skey.c bf_enc.c 
+LIBOBJ=bf_skey.o $(BF_ENC)
+
+SRC= $(LIBSRC)
+
+EXHEADER= blowfish.h
+HEADER=	bf_pi.h bf_locl.h $(EXHEADER)
+
+ALL=    $(GENERAL) $(SRC) $(HEADER)
+
+#top:
+#	(cd ../..; $(MAKE) DIRS=crypto SDIRS=$(DIR) sub_all)
+
+all:	lib
+
+lib:	$(LIB)
+
+$(LIB):	$(LIBOBJ)
+	$(AR) $(LIB) $(LIBOBJ)
+	$(RANLIB) $(LIB)
+
+# elf
+asm/bx86-elf.o: asm/bx86unix.cpp
+	$(CPP) -DELF -x c asm/bx86unix.cpp | as -o asm/bx86-elf.o
+
+# solaris
+asm/bx86-sol.o: asm/bx86unix.cpp
+	$(CC) -E -DSOL asm/bx86unix.cpp | sed 's/^#.*//' > asm/bx86-sol.s
+	as -o asm/bx86-sol.o asm/bx86-sol.s
+	rm -f asm/bx86-sol.s
+
+# a.out
+asm/bx86-out.o: asm/bx86unix.cpp
+	$(CPP) -DOUT asm/bx86unix.cpp | as -o asm/bx86-out.o
+
+# bsdi
+asm/bx86bsdi.o: asm/bx86unix.cpp
+	$(CPP) -DBSDI asm/bx86unix.cpp | sed 's/ :/:/' | as -o asm/bx86bsdi.o
+
+asm/bx86unix.cpp: asm/$(BF_ASM) ../perlasm/x86asm.pl ../perlasm/cbc.pl
+	(cd asm; $(PERL) $(BF_ASM) cpp $(PROCESSOR) >bx86unix.cpp)
+
+files:
+	$(PERL) $(TOP)/util/files.pl Makefile.ssl >> $(TOP)/MINFO
+
+links:
+	@$(TOP)/util/point.sh Makefile.ssl Makefile
+	@$(PERL) $(TOP)/util/mklink.pl ../../include/openssl $(EXHEADER)
+	@$(PERL) $(TOP)/util/mklink.pl ../../test $(TEST)
+	@$(PERL) $(TOP)/util/mklink.pl ../../apps $(APPS)
+
+install: installs
+
+installs:
+	@for i in $(EXHEADER) ; \
+	do  \
+	(cp $$i $(INSTALL_PREFIX)$(INSTALLTOP)/include/openssl/$$i; \
+	chmod 644 $(INSTALL_PREFIX)$(INSTALLTOP)/include/openssl/$$i ); \
+	done;
+
+tags:
+	ctags $(SRC)
+
+tests:
+
+lint:
+	lint -DLINT $(INCLUDES) $(SRC)>fluff
+
+depend:
+	$(MAKEDEPEND) $(INCLUDES) $(DEPFLAG) $(PROGS) $(LIBSRC)
+
+dclean:
+	$(PERL) -pe 'if (/^# DO NOT DELETE THIS LINE/) {print; exit(0);}' $(MAKEFILE) >Makefile.new
+	mv -f Makefile.new $(MAKEFILE)
+
+clean:
+	rm -f asm/bx86unix.cpp *.o asm/*.o *.obj $(LIB) tags core .pure .nfs* *.old *.bak fluff
+
+# DO NOT DELETE THIS LINE -- make depend depends on it.
diff --git a/lib/libcrypto/libblowfish/Makefile.ssl b/lib/libcrypto/libblowfish/Makefile.ssl
new file mode 100644
index 000000000..adc9eec3c
--- /dev/null
+++ b/lib/libcrypto/libblowfish/Makefile.ssl
@@ -0,0 +1,118 @@
+#
+# SSLeay/crypto/blowfish/Makefile
+#
+
+DIR=	bf
+TOP=	../..
+CC=	cc
+CPP=	$(CC) -E
+INCLUDES=
+CFLAG=-g
+INSTALL_PREFIX=
+OPENSSLDIR=     /usr/local/ssl
+INSTALLTOP=/usr/local/ssl
+MAKE=		make -f Makefile.ssl
+MAKEDEPEND=	$(TOP)/util/domd $(TOP)
+MAKEFILE=	Makefile.ssl
+AR=		ar r
+
+BF_ENC=		bf_enc.o
+# or use
+#DES_ENC=	bx86-elf.o
+
+CFLAGS= $(INCLUDES) $(CFLAG)
+
+GENERAL=Makefile
+TEST=bftest.c
+APPS=
+
+LIB=$(TOP)/libcrypto.a
+LIBSRC=bf_skey.c bf_ecb.c bf_enc.c bf_cfb64.c bf_ofb64.c 
+LIBOBJ=bf_skey.o bf_ecb.o $(BF_ENC) bf_cfb64.o bf_ofb64.o
+
+SRC= $(LIBSRC)
+
+EXHEADER= blowfish.h
+HEADER=	bf_pi.h bf_locl.h $(EXHEADER)
+
+ALL=    $(GENERAL) $(SRC) $(HEADER)
+
+top:
+	(cd ../..; $(MAKE) DIRS=crypto SDIRS=$(DIR) sub_all)
+
+all:	lib
+
+lib:	$(LIBOBJ)
+	$(AR) $(LIB) $(LIBOBJ)
+	$(RANLIB) $(LIB)
+	@touch lib
+
+# elf
+asm/bx86-elf.o: asm/bx86unix.cpp
+	$(CPP) -DELF -x c asm/bx86unix.cpp | as -o asm/bx86-elf.o
+
+# solaris
+asm/bx86-sol.o: asm/bx86unix.cpp
+	$(CC) -E -DSOL asm/bx86unix.cpp | sed 's/^#.*//' > asm/bx86-sol.s
+	as -o asm/bx86-sol.o asm/bx86-sol.s
+	rm -f asm/bx86-sol.s
+
+# a.out
+asm/bx86-out.o: asm/bx86unix.cpp
+	$(CPP) -DOUT asm/bx86unix.cpp | as -o asm/bx86-out.o
+
+# bsdi
+asm/bx86bsdi.o: asm/bx86unix.cpp
+	$(CPP) -DBSDI asm/bx86unix.cpp | sed 's/ :/:/' | as -o asm/bx86bsdi.o
+
+asm/bx86unix.cpp: asm/bf-586.pl ../perlasm/x86asm.pl ../perlasm/cbc.pl
+	(cd asm; $(PERL) bf-586.pl cpp $(PROCESSOR) >bx86unix.cpp)
+
+files:
+	$(PERL) $(TOP)/util/files.pl Makefile.ssl >> $(TOP)/MINFO
+
+links:
+	@$(TOP)/util/point.sh Makefile.ssl Makefile
+	@$(PERL) $(TOP)/util/mklink.pl ../../include/openssl $(EXHEADER)
+	@$(PERL) $(TOP)/util/mklink.pl ../../test $(TEST)
+	@$(PERL) $(TOP)/util/mklink.pl ../../apps $(APPS)
+
+install: installs
+
+installs:
+	@for i in $(EXHEADER) ; \
+	do  \
+	(cp $$i $(INSTALL_PREFIX)$(INSTALLTOP)/include/openssl/$$i; \
+	chmod 644 $(INSTALL_PREFIX)$(INSTALLTOP)/include/openssl/$$i ); \
+	done;
+
+tags:
+	ctags $(SRC)
+
+tests:
+
+lint:
+	lint -DLINT $(INCLUDES) $(SRC)>fluff
+
+depend:
+	$(MAKEDEPEND) $(INCLUDES) $(DEPFLAG) $(PROGS) $(LIBSRC)
+
+dclean:
+	$(PERL) -pe 'if (/^# DO NOT DELETE THIS LINE/) {print; exit(0);}' $(MAKEFILE) >Makefile.new
+	mv -f Makefile.new $(MAKEFILE)
+
+clean:
+	rm -f asm/bx86unix.cpp *.o asm/*.o *.obj lib tags core .pure .nfs* *.old *.bak fluff
+
+# DO NOT DELETE THIS LINE -- make depend depends on it.
+
+bf_cfb64.o: ../../include/openssl/blowfish.h
+bf_cfb64.o: ../../include/openssl/opensslconf.h bf_locl.h
+bf_ecb.o: ../../include/openssl/blowfish.h ../../include/openssl/opensslconf.h
+bf_ecb.o: ../../include/openssl/opensslv.h bf_locl.h
+bf_enc.o: ../../include/openssl/blowfish.h ../../include/openssl/opensslconf.h
+bf_enc.o: bf_locl.h
+bf_ofb64.o: ../../include/openssl/blowfish.h
+bf_ofb64.o: ../../include/openssl/opensslconf.h bf_locl.h
+bf_skey.o: ../../include/openssl/blowfish.h ../../include/openssl/opensslconf.h
+bf_skey.o: bf_locl.h bf_pi.h
diff --git a/lib/libcrypto/libblowfish/README b/lib/libcrypto/libblowfish/README
new file mode 100644
index 000000000..f2712fd0e
--- /dev/null
+++ b/lib/libcrypto/libblowfish/README
@@ -0,0 +1,8 @@
+This is a quick packaging up of my blowfish code into a library.
+It has been lifted from SSLeay.
+The copyright notices seem a little harsh because I have not spent the
+time to rewrite the conditions from the normal SSLeay ones.
+
+Basically if you just want to play with the library, not a problem.
+
+eric 15-Apr-1997
diff --git a/lib/libcrypto/libblowfish/VERSION b/lib/libcrypto/libblowfish/VERSION
new file mode 100644
index 000000000..be995855e
--- /dev/null
+++ b/lib/libcrypto/libblowfish/VERSION
@@ -0,0 +1,6 @@
+The version numbers will follow my SSL implementation
+
+0.7.2r - Some reasonable default compiler options from 
+	Peter Gutman <pgut001@cs.auckland.ac.nz>
+
+0.7.2m - the first release
diff --git a/lib/libcrypto/libblowfish/asm/bf-586.pl b/lib/libcrypto/libblowfish/asm/bf-586.pl
new file mode 100644
index 000000000..f00f3f4bf
--- /dev/null
+++ b/lib/libcrypto/libblowfish/asm/bf-586.pl
@@ -0,0 +1,136 @@
+#!/usr/bin/perl
+
+push(@INC,"perlasm","../../perlasm");
+require "x86asm.pl";
+require "cbc.pl";
+
+&asm_init($ARGV[0],"bf-586.pl",$ARGV[$#ARGV] eq "386");
+
+$BF_ROUNDS=16;
+$BF_OFF=($BF_ROUNDS+2)*4;
+$L="edi";
+$R="esi";
+$P="ebp";
+$tmp1="eax";
+$tmp2="ebx";
+$tmp3="ecx";
+$tmp4="edx";
+
+&BF_encrypt("BF_encrypt",1);
+&BF_encrypt("BF_decrypt",0);
+&cbc("BF_cbc_encrypt","BF_encrypt","BF_decrypt",1,4,5,3,-1,-1);
+&asm_finish();
+
+sub BF_encrypt
+	{
+	local($name,$enc)=@_;
+
+	&function_begin_B($name,"");
+
+	&comment("");
+
+	&push("ebp");
+	&push("ebx");
+	&mov($tmp2,&wparam(0));
+	&mov($P,&wparam(1));
+	&push("esi");
+	&push("edi");
+
+	&comment("Load the 2 words");
+	&mov($L,&DWP(0,$tmp2,"",0));
+	&mov($R,&DWP(4,$tmp2,"",0));
+
+	&xor(	$tmp1,	$tmp1);
+
+	# encrypting part
+
+	if ($enc)
+		{
+		 &mov($tmp2,&DWP(0,$P,"",0));
+		&xor(	$tmp3,	$tmp3);
+
+		&xor($L,$tmp2);
+		for ($i=0; $i<$BF_ROUNDS; $i+=2)
+			{
+			&comment("");
+			&comment("Round $i");
+			&BF_ENCRYPT($i+1,$R,$L,$P,$tmp1,$tmp2,$tmp3,$tmp4,1);
+
+			&comment("");
+			&comment("Round ".sprintf("%d",$i+1));
+			&BF_ENCRYPT($i+2,$L,$R,$P,$tmp1,$tmp2,$tmp3,$tmp4,1);
+			}
+		# &mov($tmp1,&wparam(0)); In last loop
+		&mov($tmp4,&DWP(($BF_ROUNDS+1)*4,$P,"",0));
+		}
+	else
+		{
+		 &mov($tmp2,&DWP(($BF_ROUNDS+1)*4,$P,"",0));
+		&xor(	$tmp3,	$tmp3);
+
+		&xor($L,$tmp2);
+		for ($i=$BF_ROUNDS; $i>0; $i-=2)
+			{
+			&comment("");
+			&comment("Round $i");
+			&BF_ENCRYPT($i,$R,$L,$P,$tmp1,$tmp2,$tmp3,$tmp4,0);
+			&comment("");
+			&comment("Round ".sprintf("%d",$i-1));
+			&BF_ENCRYPT($i-1,$L,$R,$P,$tmp1,$tmp2,$tmp3,$tmp4,0);
+			}
+		# &mov($tmp1,&wparam(0)); In last loop
+		&mov($tmp4,&DWP(0,$P,"",0));
+		}
+
+	&xor($R,$tmp4);
+	&mov(&DWP(4,$tmp1,"",0),$L);
+
+	&mov(&DWP(0,$tmp1,"",0),$R);
+	&function_end($name);
+	}
+
+sub BF_ENCRYPT
+	{
+	local($i,$L,$R,$P,$tmp1,$tmp2,$tmp3,$tmp4,$enc)=@_;
+
+	&mov(	$tmp4,		&DWP(&n2a($i*4),$P,"",0)); # for next round
+
+	&mov(	$tmp2,		$R);
+	&xor(	$L,		$tmp4);
+
+	&shr(	$tmp2,		16);
+	&mov(	$tmp4,		$R);
+
+	&movb(	&LB($tmp1),	&HB($tmp2));	# A
+	&and(	$tmp2,		0xff);		# B
+
+	&movb(	&LB($tmp3),	&HB($tmp4));	# C
+	&and(	$tmp4,		0xff);		# D
+
+	&mov(	$tmp1,		&DWP(&n2a($BF_OFF+0x0000),$P,$tmp1,4));
+	&mov(	$tmp2,		&DWP(&n2a($BF_OFF+0x0400),$P,$tmp2,4));
+
+	&add(	$tmp2,		$tmp1);
+	&mov(	$tmp1,		&DWP(&n2a($BF_OFF+0x0800),$P,$tmp3,4));
+
+	&xor(	$tmp2,		$tmp1);
+	&mov(	$tmp4,		&DWP(&n2a($BF_OFF+0x0C00),$P,$tmp4,4));
+
+	&add(	$tmp2,		$tmp4);
+	if (($enc && ($i != 16)) || ((!$enc) && ($i != 1)))
+		{ &xor(	$tmp1,		$tmp1); }
+	else
+		{
+		&comment("Load parameter 0 ($i) enc=$enc");
+		&mov($tmp1,&wparam(0));
+		} # In last loop
+
+	&xor(	$L,		$tmp2);
+	# delay
+	}
+
+sub n2a
+	{
+	sprintf("%d",$_[0]);
+	}
+
diff --git a/lib/libcrypto/libblowfish/asm/bf-686.pl b/lib/libcrypto/libblowfish/asm/bf-686.pl
new file mode 100644
index 000000000..9222f5e7a
--- /dev/null
+++ b/lib/libcrypto/libblowfish/asm/bf-686.pl
@@ -0,0 +1,127 @@
+#!/usr/bin/perl
+
+push(@INC,"perlasm","../../perlasm");
+require "x86asm.pl";
+require "cbc.pl";
+
+&asm_init($ARGV[0],"bf-686.pl");
+
+$BF_ROUNDS=16;
+$BF_OFF=($BF_ROUNDS+2)*4;
+$L="ecx";
+$R="edx";
+$P="edi";
+$tot="esi";
+$tmp1="eax";
+$tmp2="ebx";
+$tmp3="ebp";
+
+&des_encrypt("BF_encrypt",1);
+&des_encrypt("BF_decrypt",0);
+&cbc("BF_cbc_encrypt","BF_encrypt","BF_decrypt",1,4,5,3,-1,-1);
+
+&asm_finish();
+
+&file_end();
+
+sub des_encrypt
+	{
+	local($name,$enc)=@_;
+
+	&function_begin($name,"");
+
+	&comment("");
+	&comment("Load the 2 words");
+	&mov("eax",&wparam(0));
+	&mov($L,&DWP(0,"eax","",0));
+	&mov($R,&DWP(4,"eax","",0));
+
+	&comment("");
+	&comment("P pointer, s and enc flag");
+	&mov($P,&wparam(1));
+
+	&xor(	$tmp1,	$tmp1);
+	&xor(	$tmp2,	$tmp2);
+
+	# encrypting part
+
+	if ($enc)
+		{
+		&xor($L,&DWP(0,$P,"",0));
+		for ($i=0; $i<$BF_ROUNDS; $i+=2)
+			{
+			&comment("");
+			&comment("Round $i");
+			&BF_ENCRYPT($i+1,$R,$L,$P,$tot,$tmp1,$tmp2,$tmp3);
+
+			&comment("");
+			&comment("Round ".sprintf("%d",$i+1));
+			&BF_ENCRYPT($i+2,$L,$R,$P,$tot,$tmp1,$tmp2,$tmp3);
+			}
+		&xor($R,&DWP(($BF_ROUNDS+1)*4,$P,"",0));
+
+		&mov("eax",&wparam(0));
+		&mov(&DWP(0,"eax","",0),$R);
+		&mov(&DWP(4,"eax","",0),$L);
+		&function_end_A($name);
+		}
+	else
+		{
+		&xor($L,&DWP(($BF_ROUNDS+1)*4,$P,"",0));
+		for ($i=$BF_ROUNDS; $i>0; $i-=2)
+			{
+			&comment("");
+			&comment("Round $i");
+			&BF_ENCRYPT($i,$R,$L,$P,$tot,$tmp1,$tmp2,$tmp3);
+			&comment("");
+			&comment("Round ".sprintf("%d",$i-1));
+			&BF_ENCRYPT($i-1,$L,$R,$P,$tot,$tmp1,$tmp2,$tmp3);
+			}
+		&xor($R,&DWP(0,$P,"",0));
+
+		&mov("eax",&wparam(0));
+		&mov(&DWP(0,"eax","",0),$R);
+		&mov(&DWP(4,"eax","",0),$L);
+		&function_end_A($name);
+		}
+
+	&function_end_B($name);
+	}
+
+sub BF_ENCRYPT
+	{
+	local($i,$L,$R,$P,$tot,$tmp1,$tmp2,$tmp3)=@_;
+
+	&rotr(	$R,		16);
+	&mov(	$tot,		&DWP(&n2a($i*4),$P,"",0));
+
+	&movb(	&LB($tmp1),	&HB($R));
+	&movb(	&LB($tmp2),	&LB($R));
+
+	&rotr(	$R,		16);
+	&xor(	$L,		$tot);
+
+	&mov(	$tot,		&DWP(&n2a($BF_OFF+0x0000),$P,$tmp1,4));
+	&mov(	$tmp3,		&DWP(&n2a($BF_OFF+0x0400),$P,$tmp2,4));
+
+	&movb(	&LB($tmp1),	&HB($R));
+	&movb(	&LB($tmp2),	&LB($R));
+
+	&add(	$tot,		$tmp3);
+	&mov(	$tmp1,		&DWP(&n2a($BF_OFF+0x0800),$P,$tmp1,4)); # delay
+
+	&xor(	$tot,		$tmp1);
+	&mov(	$tmp3,		&DWP(&n2a($BF_OFF+0x0C00),$P,$tmp2,4));
+
+	&add(	$tot,		$tmp3);
+	&xor(	$tmp1,		$tmp1);
+
+	&xor(	$L,		$tot);					
+	# delay
+	}
+
+sub n2a
+	{
+	sprintf("%d",$_[0]);
+	}
+
diff --git a/lib/libcrypto/libblowfish/asm/readme b/lib/libcrypto/libblowfish/asm/readme
new file mode 100644
index 000000000..2385fa381
--- /dev/null
+++ b/lib/libcrypto/libblowfish/asm/readme
@@ -0,0 +1,10 @@
+There are blowfish assembler generation scripts.
+bf-586.pl version is for the pentium and
+bf-686.pl is my original version, which is faster on the pentium pro.
+
+When using a bf-586.pl, the pentium pro/II is %8 slower than using
+bf-686.pl.  When using a bf-686.pl, the pentium is %16 slower
+than bf-586.pl
+
+So the default is bf-586.pl
+
diff --git a/lib/libcrypto/libblowfish/bf_enc.c b/lib/libcrypto/libblowfish/bf_enc.c
new file mode 100644
index 000000000..aa6c79812
--- /dev/null
+++ b/lib/libcrypto/libblowfish/bf_enc.c
@@ -0,0 +1,306 @@
+/* crypto/bf/bf_enc.c */
+/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
+ * All rights reserved.
+ *
+ * This package is an SSL implementation written
+ * by Eric Young (eay@cryptsoft.com).
+ * The implementation was written so as to conform with Netscapes SSL.
+ * 
+ * This library is free for commercial and non-commercial use as long as
+ * the following conditions are aheared to.  The following conditions
+ * apply to all code found in this distribution, be it the RC4, RSA,
+ * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
+ * included with this distribution is covered by the same copyright terms
+ * except that the holder is Tim Hudson (tjh@cryptsoft.com).
+ * 
+ * Copyright remains Eric Young's, and as such any Copyright notices in
+ * the code are not to be removed.
+ * If this package is used in a product, Eric Young should be given attribution
+ * as the author of the parts of the library used.
+ * This can be in the form of a textual message at program startup or
+ * in documentation (online or textual) provided with the package.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from 
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ * 
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
+#include "blowfish.h"
+#include "bf_locl.h"
+
+/* Blowfish as implemented from 'Blowfish: Springer-Verlag paper'
+ * (From LECTURE NOTES IN COMPUTER SCIENCE 809, FAST SOFTWARE ENCRYPTION,
+ * CAMBRIDGE SECURITY WORKSHOP, CAMBRIDGE, U.K., DECEMBER 9-11, 1993)
+ */
+
+#if (BF_ROUNDS != 16) && (BF_ROUNDS != 20)
+#error If you set BF_ROUNDS to some value other than 16 or 20, you will have \
+to modify the code.
+#endif
+
+void BF_encrypt(BF_LONG *data, const BF_KEY *key)
+	{
+#ifndef BF_PTR2
+	const BF_LONG *p,*s;
+	BF_LONG l,r;
+
+	p=key->P;
+	s= &(key->S[0]);
+	l=data[0];
+	r=data[1];
+
+	l^=p[0];
+	BF_ENC(r,l,s,p[ 1]);
+	BF_ENC(l,r,s,p[ 2]);
+	BF_ENC(r,l,s,p[ 3]);
+	BF_ENC(l,r,s,p[ 4]);
+	BF_ENC(r,l,s,p[ 5]);
+	BF_ENC(l,r,s,p[ 6]);
+	BF_ENC(r,l,s,p[ 7]);
+	BF_ENC(l,r,s,p[ 8]);
+	BF_ENC(r,l,s,p[ 9]);
+	BF_ENC(l,r,s,p[10]);
+	BF_ENC(r,l,s,p[11]);
+	BF_ENC(l,r,s,p[12]);
+	BF_ENC(r,l,s,p[13]);
+	BF_ENC(l,r,s,p[14]);
+	BF_ENC(r,l,s,p[15]);
+	BF_ENC(l,r,s,p[16]);
+#if BF_ROUNDS == 20
+	BF_ENC(r,l,s,p[17]);
+	BF_ENC(l,r,s,p[18]);
+	BF_ENC(r,l,s,p[19]);
+	BF_ENC(l,r,s,p[20]);
+#endif
+	r^=p[BF_ROUNDS+1];
+
+	data[1]=l&0xffffffffL;
+	data[0]=r&0xffffffffL;
+#else
+	BF_LONG l,r,t,*k;
+
+	l=data[0];
+	r=data[1];
+	k=(BF_LONG*)key;
+
+	l^=k[0];
+	BF_ENC(r,l,k, 1);
+	BF_ENC(l,r,k, 2);
+	BF_ENC(r,l,k, 3);
+	BF_ENC(l,r,k, 4);
+	BF_ENC(r,l,k, 5);
+	BF_ENC(l,r,k, 6);
+	BF_ENC(r,l,k, 7);
+	BF_ENC(l,r,k, 8);
+	BF_ENC(r,l,k, 9);
+	BF_ENC(l,r,k,10);
+	BF_ENC(r,l,k,11);
+	BF_ENC(l,r,k,12);
+	BF_ENC(r,l,k,13);
+	BF_ENC(l,r,k,14);
+	BF_ENC(r,l,k,15);
+	BF_ENC(l,r,k,16);
+#if BF_ROUNDS == 20
+	BF_ENC(r,l,k,17);
+	BF_ENC(l,r,k,18);
+	BF_ENC(r,l,k,19);
+	BF_ENC(l,r,k,20);
+#endif
+	r^=k[BF_ROUNDS+1];
+
+	data[1]=l&0xffffffffL;
+	data[0]=r&0xffffffffL;
+#endif
+	}
+
+#ifndef BF_DEFAULT_OPTIONS
+
+void BF_decrypt(BF_LONG *data, const BF_KEY *key)
+	{
+#ifndef BF_PTR2
+	const BF_LONG *p,*s;
+	BF_LONG l,r;
+
+	p=key->P;
+	s= &(key->S[0]);
+	l=data[0];
+	r=data[1];
+
+	l^=p[BF_ROUNDS+1];
+#if BF_ROUNDS == 20
+	BF_ENC(r,l,s,p[20]);
+	BF_ENC(l,r,s,p[19]);
+	BF_ENC(r,l,s,p[18]);
+	BF_ENC(l,r,s,p[17]);
+#endif
+	BF_ENC(r,l,s,p[16]);
+	BF_ENC(l,r,s,p[15]);
+	BF_ENC(r,l,s,p[14]);
+	BF_ENC(l,r,s,p[13]);
+	BF_ENC(r,l,s,p[12]);
+	BF_ENC(l,r,s,p[11]);
+	BF_ENC(r,l,s,p[10]);
+	BF_ENC(l,r,s,p[ 9]);
+	BF_ENC(r,l,s,p[ 8]);
+	BF_ENC(l,r,s,p[ 7]);
+	BF_ENC(r,l,s,p[ 6]);
+	BF_ENC(l,r,s,p[ 5]);
+	BF_ENC(r,l,s,p[ 4]);
+	BF_ENC(l,r,s,p[ 3]);
+	BF_ENC(r,l,s,p[ 2]);
+	BF_ENC(l,r,s,p[ 1]);
+	r^=p[0];
+
+	data[1]=l&0xffffffffL;
+	data[0]=r&0xffffffffL;
+#else
+	BF_LONG l,r,t,*k;
+
+	l=data[0];
+	r=data[1];
+	k=(BF_LONG *)key;
+
+	l^=k[BF_ROUNDS+1];
+#if BF_ROUNDS == 20
+	BF_ENC(r,l,k,20);
+	BF_ENC(l,r,k,19);
+	BF_ENC(r,l,k,18);
+	BF_ENC(l,r,k,17);
+#endif
+	BF_ENC(r,l,k,16);
+	BF_ENC(l,r,k,15);
+	BF_ENC(r,l,k,14);
+	BF_ENC(l,r,k,13);
+	BF_ENC(r,l,k,12);
+	BF_ENC(l,r,k,11);
+	BF_ENC(r,l,k,10);
+	BF_ENC(l,r,k, 9);
+	BF_ENC(r,l,k, 8);
+	BF_ENC(l,r,k, 7);
+	BF_ENC(r,l,k, 6);
+	BF_ENC(l,r,k, 5);
+	BF_ENC(r,l,k, 4);
+	BF_ENC(l,r,k, 3);
+	BF_ENC(r,l,k, 2);
+	BF_ENC(l,r,k, 1);
+	r^=k[0];
+
+	data[1]=l&0xffffffffL;
+	data[0]=r&0xffffffffL;
+#endif
+	}
+
+void BF_cbc_encrypt(const unsigned char *in, unsigned char *out, long length,
+	     const BF_KEY *schedule, unsigned char *ivec, int encrypt)
+	{
+	BF_LONG tin0,tin1;
+	BF_LONG tout0,tout1,xor0,xor1;
+	long l=length;
+	BF_LONG tin[2];
+
+	if (encrypt)
+		{
+		n2l(ivec,tout0);
+		n2l(ivec,tout1);
+		ivec-=8;
+		for (l-=8; l>=0; l-=8)
+			{
+			n2l(in,tin0);
+			n2l(in,tin1);
+			tin0^=tout0;
+			tin1^=tout1;
+			tin[0]=tin0;
+			tin[1]=tin1;
+			BF_encrypt(tin,schedule);
+			tout0=tin[0];
+			tout1=tin[1];
+			l2n(tout0,out);
+			l2n(tout1,out);
+			}
+		if (l != -8)
+			{
+			n2ln(in,tin0,tin1,l+8);
+			tin0^=tout0;
+			tin1^=tout1;
+			tin[0]=tin0;
+			tin[1]=tin1;
+			BF_encrypt(tin,schedule);
+			tout0=tin[0];
+			tout1=tin[1];
+			l2n(tout0,out);
+			l2n(tout1,out);
+			}
+		l2n(tout0,ivec);
+		l2n(tout1,ivec);
+		}
+	else
+		{
+		n2l(ivec,xor0);
+		n2l(ivec,xor1);
+		ivec-=8;
+		for (l-=8; l>=0; l-=8)
+			{
+			n2l(in,tin0);
+			n2l(in,tin1);
+			tin[0]=tin0;
+			tin[1]=tin1;
+			BF_decrypt(tin,schedule);
+			tout0=tin[0]^xor0;
+			tout1=tin[1]^xor1;
+			l2n(tout0,out);
+			l2n(tout1,out);
+			xor0=tin0;
+			xor1=tin1;
+			}
+		if (l != -8)
+			{
+			n2l(in,tin0);
+			n2l(in,tin1);
+			tin[0]=tin0;
+			tin[1]=tin1;
+			BF_decrypt(tin,schedule);
+			tout0=tin[0]^xor0;
+			tout1=tin[1]^xor1;
+			l2nn(tout0,tout1,out,l+8);
+			xor0=tin0;
+			xor1=tin1;
+			}
+		l2n(xor0,ivec);
+		l2n(xor1,ivec);
+		}
+	tin0=tin1=tout0=tout1=xor0=xor1=0;
+	tin[0]=tin[1]=0;
+	}
+
+#endif
diff --git a/lib/libcrypto/libblowfish/bf_locl.h b/lib/libcrypto/libblowfish/bf_locl.h
new file mode 100644
index 000000000..283bf4c43
--- /dev/null
+++ b/lib/libcrypto/libblowfish/bf_locl.h
@@ -0,0 +1,218 @@
+/* crypto/bf/bf_locl.h */
+/* Copyright (C) 1995-1997 Eric Young (eay@cryptsoft.com)
+ * All rights reserved.
+ *
+ * This package is an SSL implementation written
+ * by Eric Young (eay@cryptsoft.com).
+ * The implementation was written so as to conform with Netscapes SSL.
+ * 
+ * This library is free for commercial and non-commercial use as long as
+ * the following conditions are aheared to.  The following conditions
+ * apply to all code found in this distribution, be it the RC4, RSA,
+ * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
+ * included with this distribution is covered by the same copyright terms
+ * except that the holder is Tim Hudson (tjh@cryptsoft.com).
+ * 
+ * Copyright remains Eric Young's, and as such any Copyright notices in
+ * the code are not to be removed.
+ * If this package is used in a product, Eric Young should be given attribution
+ * as the author of the parts of the library used.
+ * This can be in the form of a textual message at program startup or
+ * in documentation (online or textual) provided with the package.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from 
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ * 
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
+#ifndef HEADER_BF_LOCL_H
+#define HEADER_BF_LOCL_H
+
+#undef c2l
+#define c2l(c,l)	(l =((unsigned long)(*((c)++)))    , \
+			 l|=((unsigned long)(*((c)++)))<< 8L, \
+			 l|=((unsigned long)(*((c)++)))<<16L, \
+			 l|=((unsigned long)(*((c)++)))<<24L)
+
+/* NOTE - c is not incremented as per c2l */
+#undef c2ln
+#define c2ln(c,l1,l2,n)	{ \
+			c+=n; \
+			l1=l2=0; \
+			switch (n) { \
+			case 8: l2 =((unsigned long)(*(--(c))))<<24L; \
+			case 7: l2|=((unsigned long)(*(--(c))))<<16L; \
+			case 6: l2|=((unsigned long)(*(--(c))))<< 8L; \
+			case 5: l2|=((unsigned long)(*(--(c))));     \
+			case 4: l1 =((unsigned long)(*(--(c))))<<24L; \
+			case 3: l1|=((unsigned long)(*(--(c))))<<16L; \
+			case 2: l1|=((unsigned long)(*(--(c))))<< 8L; \
+			case 1: l1|=((unsigned long)(*(--(c))));     \
+				} \
+			}
+
+#undef l2c
+#define l2c(l,c)	(*((c)++)=(unsigned char)(((l)     )&0xff), \
+			 *((c)++)=(unsigned char)(((l)>> 8L)&0xff), \
+			 *((c)++)=(unsigned char)(((l)>>16L)&0xff), \
+			 *((c)++)=(unsigned char)(((l)>>24L)&0xff))
+
+/* NOTE - c is not incremented as per l2c */
+#undef l2cn
+#define l2cn(l1,l2,c,n)	{ \
+			c+=n; \
+			switch (n) { \
+			case 8: *(--(c))=(unsigned char)(((l2)>>24L)&0xff); \
+			case 7: *(--(c))=(unsigned char)(((l2)>>16L)&0xff); \
+			case 6: *(--(c))=(unsigned char)(((l2)>> 8L)&0xff); \
+			case 5: *(--(c))=(unsigned char)(((l2)     )&0xff); \
+			case 4: *(--(c))=(unsigned char)(((l1)>>24L)&0xff); \
+			case 3: *(--(c))=(unsigned char)(((l1)>>16L)&0xff); \
+			case 2: *(--(c))=(unsigned char)(((l1)>> 8L)&0xff); \
+			case 1: *(--(c))=(unsigned char)(((l1)     )&0xff); \
+				} \
+			}
+
+/* NOTE - c is not incremented as per n2l */
+#define n2ln(c,l1,l2,n)	{ \
+			c+=n; \
+			l1=l2=0; \
+			switch (n) { \
+			case 8: l2 =((unsigned long)(*(--(c))))    ; \
+			case 7: l2|=((unsigned long)(*(--(c))))<< 8; \
+			case 6: l2|=((unsigned long)(*(--(c))))<<16; \
+			case 5: l2|=((unsigned long)(*(--(c))))<<24; \
+			case 4: l1 =((unsigned long)(*(--(c))))    ; \
+			case 3: l1|=((unsigned long)(*(--(c))))<< 8; \
+			case 2: l1|=((unsigned long)(*(--(c))))<<16; \
+			case 1: l1|=((unsigned long)(*(--(c))))<<24; \
+				} \
+			}
+
+/* NOTE - c is not incremented as per l2n */
+#define l2nn(l1,l2,c,n)	{ \
+			c+=n; \
+			switch (n) { \
+			case 8: *(--(c))=(unsigned char)(((l2)    )&0xff); \
+			case 7: *(--(c))=(unsigned char)(((l2)>> 8)&0xff); \
+			case 6: *(--(c))=(unsigned char)(((l2)>>16)&0xff); \
+			case 5: *(--(c))=(unsigned char)(((l2)>>24)&0xff); \
+			case 4: *(--(c))=(unsigned char)(((l1)    )&0xff); \
+			case 3: *(--(c))=(unsigned char)(((l1)>> 8)&0xff); \
+			case 2: *(--(c))=(unsigned char)(((l1)>>16)&0xff); \
+			case 1: *(--(c))=(unsigned char)(((l1)>>24)&0xff); \
+				} \
+			}
+
+#undef n2l
+#define n2l(c,l)        (l =((unsigned long)(*((c)++)))<<24L, \
+                         l|=((unsigned long)(*((c)++)))<<16L, \
+                         l|=((unsigned long)(*((c)++)))<< 8L, \
+                         l|=((unsigned long)(*((c)++))))
+
+#undef l2n
+#define l2n(l,c)        (*((c)++)=(unsigned char)(((l)>>24L)&0xff), \
+                         *((c)++)=(unsigned char)(((l)>>16L)&0xff), \
+                         *((c)++)=(unsigned char)(((l)>> 8L)&0xff), \
+                         *((c)++)=(unsigned char)(((l)     )&0xff))
+
+/* This is actually a big endian algorithm, the most significant byte
+ * is used to lookup array 0 */
+
+#if defined(BF_PTR2)
+
+/*
+ * This is basically a special Intel version. Point is that Intel
+ * doesn't have many registers, but offers a reach choice of addressing
+ * modes. So we spare some registers by directly traversing BF_KEY
+ * structure and hiring the most decorated addressing mode. The code
+ * generated by EGCS is *perfectly* competitive with assembler
+ * implementation!
+ */
+#define BF_ENC(LL,R,KEY,Pi) (\
+	LL^=KEY[Pi], \
+	t=  KEY[BF_ROUNDS+2 +   0 + ((R>>24)&0xFF)], \
+	t+= KEY[BF_ROUNDS+2 + 256 + ((R>>16)&0xFF)], \
+	t^= KEY[BF_ROUNDS+2 + 512 + ((R>>8 )&0xFF)], \
+	t+= KEY[BF_ROUNDS+2 + 768 + ((R    )&0xFF)], \
+	LL^=t \
+	)
+
+#elif defined(BF_PTR)
+
+#ifndef BF_LONG_LOG2
+#define BF_LONG_LOG2  2       /* default to BF_LONG being 32 bits */
+#endif
+#define BF_M  (0xFF<<BF_LONG_LOG2)
+#define BF_0  (24-BF_LONG_LOG2)
+#define BF_1  (16-BF_LONG_LOG2)
+#define BF_2  ( 8-BF_LONG_LOG2)
+#define BF_3  BF_LONG_LOG2 /* left shift */
+
+/*
+ * This is normally very good on RISC platforms where normally you
+ * have to explicitly "multiply" array index by sizeof(BF_LONG)
+ * in order to calculate the effective address. This implementation
+ * excuses CPU from this extra work. Power[PC] uses should have most
+ * fun as (R>>BF_i)&BF_M gets folded into a single instruction, namely
+ * rlwinm. So let'em double-check if their compiler does it.
+ */
+
+#define BF_ENC(LL,R,S,P) ( \
+	LL^=P, \
+	LL^= (((*(BF_LONG *)((unsigned char *)&(S[  0])+((R>>BF_0)&BF_M))+ \
+		*(BF_LONG *)((unsigned char *)&(S[256])+((R>>BF_1)&BF_M)))^ \
+		*(BF_LONG *)((unsigned char *)&(S[512])+((R>>BF_2)&BF_M)))+ \
+		*(BF_LONG *)((unsigned char *)&(S[768])+((R<<BF_3)&BF_M))) \
+	)
+#else
+
+/*
+ * This is a *generic* version. Seem to perform best on platforms that
+ * offer explicit support for extraction of 8-bit nibbles preferably
+ * complemented with "multiplying" of array index by sizeof(BF_LONG).
+ * For the moment of this writing the list comprises Alpha CPU featuring
+ * extbl and s[48]addq instructions.
+ */
+
+#define BF_ENC(LL,R,S,P) ( \
+	LL^=P, \
+	LL^=(((	S[       ((int)(R>>24)&0xff)] + \
+		S[0x0100+((int)(R>>16)&0xff)])^ \
+		S[0x0200+((int)(R>> 8)&0xff)])+ \
+		S[0x0300+((int)(R    )&0xff)])&0xffffffffL \
+	)
+#endif
+
+#endif
diff --git a/lib/libcrypto/libblowfish/bf_pi.h b/lib/libcrypto/libblowfish/bf_pi.h
new file mode 100644
index 000000000..9949513c6
--- /dev/null
+++ b/lib/libcrypto/libblowfish/bf_pi.h
@@ -0,0 +1,325 @@
+/* crypto/bf/bf_pi.h */
+/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
+ * All rights reserved.
+ *
+ * This package is an SSL implementation written
+ * by Eric Young (eay@cryptsoft.com).
+ * The implementation was written so as to conform with Netscapes SSL.
+ * 
+ * This library is free for commercial and non-commercial use as long as
+ * the following conditions are aheared to.  The following conditions
+ * apply to all code found in this distribution, be it the RC4, RSA,
+ * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
+ * included with this distribution is covered by the same copyright terms
+ * except that the holder is Tim Hudson (tjh@cryptsoft.com).
+ * 
+ * Copyright remains Eric Young's, and as such any Copyright notices in
+ * the code are not to be removed.
+ * If this package is used in a product, Eric Young should be given attribution
+ * as the author of the parts of the library used.
+ * This can be in the form of a textual message at program startup or
+ * in documentation (online or textual) provided with the package.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from 
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ * 
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
+static const BF_KEY bf_init= {
+	{
+	0x243f6a88L, 0x85a308d3L, 0x13198a2eL, 0x03707344L,
+	0xa4093822L, 0x299f31d0L, 0x082efa98L, 0xec4e6c89L,
+	0x452821e6L, 0x38d01377L, 0xbe5466cfL, 0x34e90c6cL,
+	0xc0ac29b7L, 0xc97c50ddL, 0x3f84d5b5L, 0xb5470917L,
+	0x9216d5d9L, 0x8979fb1b
+	},{
+	0xd1310ba6L, 0x98dfb5acL, 0x2ffd72dbL, 0xd01adfb7L, 
+	0xb8e1afedL, 0x6a267e96L, 0xba7c9045L, 0xf12c7f99L, 
+	0x24a19947L, 0xb3916cf7L, 0x0801f2e2L, 0x858efc16L, 
+	0x636920d8L, 0x71574e69L, 0xa458fea3L, 0xf4933d7eL, 
+	0x0d95748fL, 0x728eb658L, 0x718bcd58L, 0x82154aeeL, 
+	0x7b54a41dL, 0xc25a59b5L, 0x9c30d539L, 0x2af26013L, 
+	0xc5d1b023L, 0x286085f0L, 0xca417918L, 0xb8db38efL, 
+	0x8e79dcb0L, 0x603a180eL, 0x6c9e0e8bL, 0xb01e8a3eL, 
+	0xd71577c1L, 0xbd314b27L, 0x78af2fdaL, 0x55605c60L, 
+	0xe65525f3L, 0xaa55ab94L, 0x57489862L, 0x63e81440L, 
+	0x55ca396aL, 0x2aab10b6L, 0xb4cc5c34L, 0x1141e8ceL, 
+	0xa15486afL, 0x7c72e993L, 0xb3ee1411L, 0x636fbc2aL, 
+	0x2ba9c55dL, 0x741831f6L, 0xce5c3e16L, 0x9b87931eL, 
+	0xafd6ba33L, 0x6c24cf5cL, 0x7a325381L, 0x28958677L, 
+	0x3b8f4898L, 0x6b4bb9afL, 0xc4bfe81bL, 0x66282193L, 
+	0x61d809ccL, 0xfb21a991L, 0x487cac60L, 0x5dec8032L, 
+	0xef845d5dL, 0xe98575b1L, 0xdc262302L, 0xeb651b88L, 
+	0x23893e81L, 0xd396acc5L, 0x0f6d6ff3L, 0x83f44239L, 
+	0x2e0b4482L, 0xa4842004L, 0x69c8f04aL, 0x9e1f9b5eL, 
+	0x21c66842L, 0xf6e96c9aL, 0x670c9c61L, 0xabd388f0L, 
+	0x6a51a0d2L, 0xd8542f68L, 0x960fa728L, 0xab5133a3L, 
+	0x6eef0b6cL, 0x137a3be4L, 0xba3bf050L, 0x7efb2a98L, 
+	0xa1f1651dL, 0x39af0176L, 0x66ca593eL, 0x82430e88L, 
+	0x8cee8619L, 0x456f9fb4L, 0x7d84a5c3L, 0x3b8b5ebeL, 
+	0xe06f75d8L, 0x85c12073L, 0x401a449fL, 0x56c16aa6L, 
+	0x4ed3aa62L, 0x363f7706L, 0x1bfedf72L, 0x429b023dL, 
+	0x37d0d724L, 0xd00a1248L, 0xdb0fead3L, 0x49f1c09bL, 
+	0x075372c9L, 0x80991b7bL, 0x25d479d8L, 0xf6e8def7L, 
+	0xe3fe501aL, 0xb6794c3bL, 0x976ce0bdL, 0x04c006baL, 
+	0xc1a94fb6L, 0x409f60c4L, 0x5e5c9ec2L, 0x196a2463L, 
+	0x68fb6fafL, 0x3e6c53b5L, 0x1339b2ebL, 0x3b52ec6fL, 
+	0x6dfc511fL, 0x9b30952cL, 0xcc814544L, 0xaf5ebd09L, 
+	0xbee3d004L, 0xde334afdL, 0x660f2807L, 0x192e4bb3L, 
+	0xc0cba857L, 0x45c8740fL, 0xd20b5f39L, 0xb9d3fbdbL, 
+	0x5579c0bdL, 0x1a60320aL, 0xd6a100c6L, 0x402c7279L, 
+	0x679f25feL, 0xfb1fa3ccL, 0x8ea5e9f8L, 0xdb3222f8L, 
+	0x3c7516dfL, 0xfd616b15L, 0x2f501ec8L, 0xad0552abL, 
+	0x323db5faL, 0xfd238760L, 0x53317b48L, 0x3e00df82L, 
+	0x9e5c57bbL, 0xca6f8ca0L, 0x1a87562eL, 0xdf1769dbL, 
+	0xd542a8f6L, 0x287effc3L, 0xac6732c6L, 0x8c4f5573L, 
+	0x695b27b0L, 0xbbca58c8L, 0xe1ffa35dL, 0xb8f011a0L, 
+	0x10fa3d98L, 0xfd2183b8L, 0x4afcb56cL, 0x2dd1d35bL, 
+	0x9a53e479L, 0xb6f84565L, 0xd28e49bcL, 0x4bfb9790L, 
+	0xe1ddf2daL, 0xa4cb7e33L, 0x62fb1341L, 0xcee4c6e8L, 
+	0xef20cadaL, 0x36774c01L, 0xd07e9efeL, 0x2bf11fb4L, 
+	0x95dbda4dL, 0xae909198L, 0xeaad8e71L, 0x6b93d5a0L, 
+	0xd08ed1d0L, 0xafc725e0L, 0x8e3c5b2fL, 0x8e7594b7L, 
+	0x8ff6e2fbL, 0xf2122b64L, 0x8888b812L, 0x900df01cL, 
+	0x4fad5ea0L, 0x688fc31cL, 0xd1cff191L, 0xb3a8c1adL, 
+	0x2f2f2218L, 0xbe0e1777L, 0xea752dfeL, 0x8b021fa1L, 
+	0xe5a0cc0fL, 0xb56f74e8L, 0x18acf3d6L, 0xce89e299L, 
+	0xb4a84fe0L, 0xfd13e0b7L, 0x7cc43b81L, 0xd2ada8d9L, 
+	0x165fa266L, 0x80957705L, 0x93cc7314L, 0x211a1477L, 
+	0xe6ad2065L, 0x77b5fa86L, 0xc75442f5L, 0xfb9d35cfL, 
+	0xebcdaf0cL, 0x7b3e89a0L, 0xd6411bd3L, 0xae1e7e49L, 
+	0x00250e2dL, 0x2071b35eL, 0x226800bbL, 0x57b8e0afL, 
+	0x2464369bL, 0xf009b91eL, 0x5563911dL, 0x59dfa6aaL, 
+	0x78c14389L, 0xd95a537fL, 0x207d5ba2L, 0x02e5b9c5L, 
+	0x83260376L, 0x6295cfa9L, 0x11c81968L, 0x4e734a41L, 
+	0xb3472dcaL, 0x7b14a94aL, 0x1b510052L, 0x9a532915L, 
+	0xd60f573fL, 0xbc9bc6e4L, 0x2b60a476L, 0x81e67400L, 
+	0x08ba6fb5L, 0x571be91fL, 0xf296ec6bL, 0x2a0dd915L, 
+	0xb6636521L, 0xe7b9f9b6L, 0xff34052eL, 0xc5855664L, 
+	0x53b02d5dL, 0xa99f8fa1L, 0x08ba4799L, 0x6e85076aL, 
+	0x4b7a70e9L, 0xb5b32944L, 0xdb75092eL, 0xc4192623L, 
+	0xad6ea6b0L, 0x49a7df7dL, 0x9cee60b8L, 0x8fedb266L, 
+	0xecaa8c71L, 0x699a17ffL, 0x5664526cL, 0xc2b19ee1L, 
+	0x193602a5L, 0x75094c29L, 0xa0591340L, 0xe4183a3eL, 
+	0x3f54989aL, 0x5b429d65L, 0x6b8fe4d6L, 0x99f73fd6L, 
+	0xa1d29c07L, 0xefe830f5L, 0x4d2d38e6L, 0xf0255dc1L, 
+	0x4cdd2086L, 0x8470eb26L, 0x6382e9c6L, 0x021ecc5eL, 
+	0x09686b3fL, 0x3ebaefc9L, 0x3c971814L, 0x6b6a70a1L, 
+	0x687f3584L, 0x52a0e286L, 0xb79c5305L, 0xaa500737L, 
+	0x3e07841cL, 0x7fdeae5cL, 0x8e7d44ecL, 0x5716f2b8L, 
+	0xb03ada37L, 0xf0500c0dL, 0xf01c1f04L, 0x0200b3ffL, 
+	0xae0cf51aL, 0x3cb574b2L, 0x25837a58L, 0xdc0921bdL, 
+	0xd19113f9L, 0x7ca92ff6L, 0x94324773L, 0x22f54701L, 
+	0x3ae5e581L, 0x37c2dadcL, 0xc8b57634L, 0x9af3dda7L, 
+	0xa9446146L, 0x0fd0030eL, 0xecc8c73eL, 0xa4751e41L, 
+	0xe238cd99L, 0x3bea0e2fL, 0x3280bba1L, 0x183eb331L, 
+	0x4e548b38L, 0x4f6db908L, 0x6f420d03L, 0xf60a04bfL, 
+	0x2cb81290L, 0x24977c79L, 0x5679b072L, 0xbcaf89afL, 
+	0xde9a771fL, 0xd9930810L, 0xb38bae12L, 0xdccf3f2eL, 
+	0x5512721fL, 0x2e6b7124L, 0x501adde6L, 0x9f84cd87L, 
+	0x7a584718L, 0x7408da17L, 0xbc9f9abcL, 0xe94b7d8cL, 
+	0xec7aec3aL, 0xdb851dfaL, 0x63094366L, 0xc464c3d2L, 
+	0xef1c1847L, 0x3215d908L, 0xdd433b37L, 0x24c2ba16L, 
+	0x12a14d43L, 0x2a65c451L, 0x50940002L, 0x133ae4ddL, 
+	0x71dff89eL, 0x10314e55L, 0x81ac77d6L, 0x5f11199bL, 
+	0x043556f1L, 0xd7a3c76bL, 0x3c11183bL, 0x5924a509L, 
+	0xf28fe6edL, 0x97f1fbfaL, 0x9ebabf2cL, 0x1e153c6eL, 
+	0x86e34570L, 0xeae96fb1L, 0x860e5e0aL, 0x5a3e2ab3L, 
+	0x771fe71cL, 0x4e3d06faL, 0x2965dcb9L, 0x99e71d0fL, 
+	0x803e89d6L, 0x5266c825L, 0x2e4cc978L, 0x9c10b36aL, 
+	0xc6150ebaL, 0x94e2ea78L, 0xa5fc3c53L, 0x1e0a2df4L, 
+	0xf2f74ea7L, 0x361d2b3dL, 0x1939260fL, 0x19c27960L, 
+	0x5223a708L, 0xf71312b6L, 0xebadfe6eL, 0xeac31f66L, 
+	0xe3bc4595L, 0xa67bc883L, 0xb17f37d1L, 0x018cff28L, 
+	0xc332ddefL, 0xbe6c5aa5L, 0x65582185L, 0x68ab9802L, 
+	0xeecea50fL, 0xdb2f953bL, 0x2aef7dadL, 0x5b6e2f84L, 
+	0x1521b628L, 0x29076170L, 0xecdd4775L, 0x619f1510L, 
+	0x13cca830L, 0xeb61bd96L, 0x0334fe1eL, 0xaa0363cfL, 
+	0xb5735c90L, 0x4c70a239L, 0xd59e9e0bL, 0xcbaade14L, 
+	0xeecc86bcL, 0x60622ca7L, 0x9cab5cabL, 0xb2f3846eL, 
+	0x648b1eafL, 0x19bdf0caL, 0xa02369b9L, 0x655abb50L, 
+	0x40685a32L, 0x3c2ab4b3L, 0x319ee9d5L, 0xc021b8f7L, 
+	0x9b540b19L, 0x875fa099L, 0x95f7997eL, 0x623d7da8L, 
+	0xf837889aL, 0x97e32d77L, 0x11ed935fL, 0x16681281L, 
+	0x0e358829L, 0xc7e61fd6L, 0x96dedfa1L, 0x7858ba99L, 
+	0x57f584a5L, 0x1b227263L, 0x9b83c3ffL, 0x1ac24696L, 
+	0xcdb30aebL, 0x532e3054L, 0x8fd948e4L, 0x6dbc3128L, 
+	0x58ebf2efL, 0x34c6ffeaL, 0xfe28ed61L, 0xee7c3c73L, 
+	0x5d4a14d9L, 0xe864b7e3L, 0x42105d14L, 0x203e13e0L, 
+	0x45eee2b6L, 0xa3aaabeaL, 0xdb6c4f15L, 0xfacb4fd0L, 
+	0xc742f442L, 0xef6abbb5L, 0x654f3b1dL, 0x41cd2105L, 
+	0xd81e799eL, 0x86854dc7L, 0xe44b476aL, 0x3d816250L, 
+	0xcf62a1f2L, 0x5b8d2646L, 0xfc8883a0L, 0xc1c7b6a3L, 
+	0x7f1524c3L, 0x69cb7492L, 0x47848a0bL, 0x5692b285L, 
+	0x095bbf00L, 0xad19489dL, 0x1462b174L, 0x23820e00L, 
+	0x58428d2aL, 0x0c55f5eaL, 0x1dadf43eL, 0x233f7061L, 
+	0x3372f092L, 0x8d937e41L, 0xd65fecf1L, 0x6c223bdbL, 
+	0x7cde3759L, 0xcbee7460L, 0x4085f2a7L, 0xce77326eL, 
+	0xa6078084L, 0x19f8509eL, 0xe8efd855L, 0x61d99735L, 
+	0xa969a7aaL, 0xc50c06c2L, 0x5a04abfcL, 0x800bcadcL, 
+	0x9e447a2eL, 0xc3453484L, 0xfdd56705L, 0x0e1e9ec9L, 
+	0xdb73dbd3L, 0x105588cdL, 0x675fda79L, 0xe3674340L, 
+	0xc5c43465L, 0x713e38d8L, 0x3d28f89eL, 0xf16dff20L, 
+	0x153e21e7L, 0x8fb03d4aL, 0xe6e39f2bL, 0xdb83adf7L, 
+	0xe93d5a68L, 0x948140f7L, 0xf64c261cL, 0x94692934L, 
+	0x411520f7L, 0x7602d4f7L, 0xbcf46b2eL, 0xd4a20068L, 
+	0xd4082471L, 0x3320f46aL, 0x43b7d4b7L, 0x500061afL, 
+	0x1e39f62eL, 0x97244546L, 0x14214f74L, 0xbf8b8840L, 
+	0x4d95fc1dL, 0x96b591afL, 0x70f4ddd3L, 0x66a02f45L, 
+	0xbfbc09ecL, 0x03bd9785L, 0x7fac6dd0L, 0x31cb8504L, 
+	0x96eb27b3L, 0x55fd3941L, 0xda2547e6L, 0xabca0a9aL, 
+	0x28507825L, 0x530429f4L, 0x0a2c86daL, 0xe9b66dfbL, 
+	0x68dc1462L, 0xd7486900L, 0x680ec0a4L, 0x27a18deeL, 
+	0x4f3ffea2L, 0xe887ad8cL, 0xb58ce006L, 0x7af4d6b6L, 
+	0xaace1e7cL, 0xd3375fecL, 0xce78a399L, 0x406b2a42L, 
+	0x20fe9e35L, 0xd9f385b9L, 0xee39d7abL, 0x3b124e8bL, 
+	0x1dc9faf7L, 0x4b6d1856L, 0x26a36631L, 0xeae397b2L, 
+	0x3a6efa74L, 0xdd5b4332L, 0x6841e7f7L, 0xca7820fbL, 
+	0xfb0af54eL, 0xd8feb397L, 0x454056acL, 0xba489527L, 
+	0x55533a3aL, 0x20838d87L, 0xfe6ba9b7L, 0xd096954bL, 
+	0x55a867bcL, 0xa1159a58L, 0xcca92963L, 0x99e1db33L, 
+	0xa62a4a56L, 0x3f3125f9L, 0x5ef47e1cL, 0x9029317cL, 
+	0xfdf8e802L, 0x04272f70L, 0x80bb155cL, 0x05282ce3L, 
+	0x95c11548L, 0xe4c66d22L, 0x48c1133fL, 0xc70f86dcL, 
+	0x07f9c9eeL, 0x41041f0fL, 0x404779a4L, 0x5d886e17L, 
+	0x325f51ebL, 0xd59bc0d1L, 0xf2bcc18fL, 0x41113564L, 
+	0x257b7834L, 0x602a9c60L, 0xdff8e8a3L, 0x1f636c1bL, 
+	0x0e12b4c2L, 0x02e1329eL, 0xaf664fd1L, 0xcad18115L, 
+	0x6b2395e0L, 0x333e92e1L, 0x3b240b62L, 0xeebeb922L, 
+	0x85b2a20eL, 0xe6ba0d99L, 0xde720c8cL, 0x2da2f728L, 
+	0xd0127845L, 0x95b794fdL, 0x647d0862L, 0xe7ccf5f0L, 
+	0x5449a36fL, 0x877d48faL, 0xc39dfd27L, 0xf33e8d1eL, 
+	0x0a476341L, 0x992eff74L, 0x3a6f6eabL, 0xf4f8fd37L, 
+	0xa812dc60L, 0xa1ebddf8L, 0x991be14cL, 0xdb6e6b0dL, 
+	0xc67b5510L, 0x6d672c37L, 0x2765d43bL, 0xdcd0e804L, 
+	0xf1290dc7L, 0xcc00ffa3L, 0xb5390f92L, 0x690fed0bL, 
+	0x667b9ffbL, 0xcedb7d9cL, 0xa091cf0bL, 0xd9155ea3L, 
+	0xbb132f88L, 0x515bad24L, 0x7b9479bfL, 0x763bd6ebL, 
+	0x37392eb3L, 0xcc115979L, 0x8026e297L, 0xf42e312dL, 
+	0x6842ada7L, 0xc66a2b3bL, 0x12754cccL, 0x782ef11cL, 
+	0x6a124237L, 0xb79251e7L, 0x06a1bbe6L, 0x4bfb6350L, 
+	0x1a6b1018L, 0x11caedfaL, 0x3d25bdd8L, 0xe2e1c3c9L, 
+	0x44421659L, 0x0a121386L, 0xd90cec6eL, 0xd5abea2aL, 
+	0x64af674eL, 0xda86a85fL, 0xbebfe988L, 0x64e4c3feL, 
+	0x9dbc8057L, 0xf0f7c086L, 0x60787bf8L, 0x6003604dL, 
+	0xd1fd8346L, 0xf6381fb0L, 0x7745ae04L, 0xd736fcccL, 
+	0x83426b33L, 0xf01eab71L, 0xb0804187L, 0x3c005e5fL, 
+	0x77a057beL, 0xbde8ae24L, 0x55464299L, 0xbf582e61L, 
+	0x4e58f48fL, 0xf2ddfda2L, 0xf474ef38L, 0x8789bdc2L, 
+	0x5366f9c3L, 0xc8b38e74L, 0xb475f255L, 0x46fcd9b9L, 
+	0x7aeb2661L, 0x8b1ddf84L, 0x846a0e79L, 0x915f95e2L, 
+	0x466e598eL, 0x20b45770L, 0x8cd55591L, 0xc902de4cL, 
+	0xb90bace1L, 0xbb8205d0L, 0x11a86248L, 0x7574a99eL, 
+	0xb77f19b6L, 0xe0a9dc09L, 0x662d09a1L, 0xc4324633L, 
+	0xe85a1f02L, 0x09f0be8cL, 0x4a99a025L, 0x1d6efe10L, 
+	0x1ab93d1dL, 0x0ba5a4dfL, 0xa186f20fL, 0x2868f169L, 
+	0xdcb7da83L, 0x573906feL, 0xa1e2ce9bL, 0x4fcd7f52L, 
+	0x50115e01L, 0xa70683faL, 0xa002b5c4L, 0x0de6d027L, 
+	0x9af88c27L, 0x773f8641L, 0xc3604c06L, 0x61a806b5L, 
+	0xf0177a28L, 0xc0f586e0L, 0x006058aaL, 0x30dc7d62L, 
+	0x11e69ed7L, 0x2338ea63L, 0x53c2dd94L, 0xc2c21634L, 
+	0xbbcbee56L, 0x90bcb6deL, 0xebfc7da1L, 0xce591d76L, 
+	0x6f05e409L, 0x4b7c0188L, 0x39720a3dL, 0x7c927c24L, 
+	0x86e3725fL, 0x724d9db9L, 0x1ac15bb4L, 0xd39eb8fcL, 
+	0xed545578L, 0x08fca5b5L, 0xd83d7cd3L, 0x4dad0fc4L, 
+	0x1e50ef5eL, 0xb161e6f8L, 0xa28514d9L, 0x6c51133cL, 
+	0x6fd5c7e7L, 0x56e14ec4L, 0x362abfceL, 0xddc6c837L, 
+	0xd79a3234L, 0x92638212L, 0x670efa8eL, 0x406000e0L, 
+	0x3a39ce37L, 0xd3faf5cfL, 0xabc27737L, 0x5ac52d1bL, 
+	0x5cb0679eL, 0x4fa33742L, 0xd3822740L, 0x99bc9bbeL, 
+	0xd5118e9dL, 0xbf0f7315L, 0xd62d1c7eL, 0xc700c47bL, 
+	0xb78c1b6bL, 0x21a19045L, 0xb26eb1beL, 0x6a366eb4L, 
+	0x5748ab2fL, 0xbc946e79L, 0xc6a376d2L, 0x6549c2c8L, 
+	0x530ff8eeL, 0x468dde7dL, 0xd5730a1dL, 0x4cd04dc6L, 
+	0x2939bbdbL, 0xa9ba4650L, 0xac9526e8L, 0xbe5ee304L, 
+	0xa1fad5f0L, 0x6a2d519aL, 0x63ef8ce2L, 0x9a86ee22L, 
+	0xc089c2b8L, 0x43242ef6L, 0xa51e03aaL, 0x9cf2d0a4L, 
+	0x83c061baL, 0x9be96a4dL, 0x8fe51550L, 0xba645bd6L, 
+	0x2826a2f9L, 0xa73a3ae1L, 0x4ba99586L, 0xef5562e9L, 
+	0xc72fefd3L, 0xf752f7daL, 0x3f046f69L, 0x77fa0a59L, 
+	0x80e4a915L, 0x87b08601L, 0x9b09e6adL, 0x3b3ee593L, 
+	0xe990fd5aL, 0x9e34d797L, 0x2cf0b7d9L, 0x022b8b51L, 
+	0x96d5ac3aL, 0x017da67dL, 0xd1cf3ed6L, 0x7c7d2d28L, 
+	0x1f9f25cfL, 0xadf2b89bL, 0x5ad6b472L, 0x5a88f54cL, 
+	0xe029ac71L, 0xe019a5e6L, 0x47b0acfdL, 0xed93fa9bL, 
+	0xe8d3c48dL, 0x283b57ccL, 0xf8d56629L, 0x79132e28L, 
+	0x785f0191L, 0xed756055L, 0xf7960e44L, 0xe3d35e8cL, 
+	0x15056dd4L, 0x88f46dbaL, 0x03a16125L, 0x0564f0bdL, 
+	0xc3eb9e15L, 0x3c9057a2L, 0x97271aecL, 0xa93a072aL, 
+	0x1b3f6d9bL, 0x1e6321f5L, 0xf59c66fbL, 0x26dcf319L, 
+	0x7533d928L, 0xb155fdf5L, 0x03563482L, 0x8aba3cbbL, 
+	0x28517711L, 0xc20ad9f8L, 0xabcc5167L, 0xccad925fL, 
+	0x4de81751L, 0x3830dc8eL, 0x379d5862L, 0x9320f991L, 
+	0xea7a90c2L, 0xfb3e7bceL, 0x5121ce64L, 0x774fbe32L, 
+	0xa8b6e37eL, 0xc3293d46L, 0x48de5369L, 0x6413e680L, 
+	0xa2ae0810L, 0xdd6db224L, 0x69852dfdL, 0x09072166L, 
+	0xb39a460aL, 0x6445c0ddL, 0x586cdecfL, 0x1c20c8aeL, 
+	0x5bbef7ddL, 0x1b588d40L, 0xccd2017fL, 0x6bb4e3bbL, 
+	0xdda26a7eL, 0x3a59ff45L, 0x3e350a44L, 0xbcb4cdd5L, 
+	0x72eacea8L, 0xfa6484bbL, 0x8d6612aeL, 0xbf3c6f47L, 
+	0xd29be463L, 0x542f5d9eL, 0xaec2771bL, 0xf64e6370L, 
+	0x740e0d8dL, 0xe75b1357L, 0xf8721671L, 0xaf537d5dL, 
+	0x4040cb08L, 0x4eb4e2ccL, 0x34d2466aL, 0x0115af84L, 
+	0xe1b00428L, 0x95983a1dL, 0x06b89fb4L, 0xce6ea048L, 
+	0x6f3f3b82L, 0x3520ab82L, 0x011a1d4bL, 0x277227f8L, 
+	0x611560b1L, 0xe7933fdcL, 0xbb3a792bL, 0x344525bdL, 
+	0xa08839e1L, 0x51ce794bL, 0x2f32c9b7L, 0xa01fbac9L, 
+	0xe01cc87eL, 0xbcc7d1f6L, 0xcf0111c3L, 0xa1e8aac7L, 
+	0x1a908749L, 0xd44fbd9aL, 0xd0dadecbL, 0xd50ada38L, 
+	0x0339c32aL, 0xc6913667L, 0x8df9317cL, 0xe0b12b4fL, 
+	0xf79e59b7L, 0x43f5bb3aL, 0xf2d519ffL, 0x27d9459cL, 
+	0xbf97222cL, 0x15e6fc2aL, 0x0f91fc71L, 0x9b941525L, 
+	0xfae59361L, 0xceb69cebL, 0xc2a86459L, 0x12baa8d1L, 
+	0xb6c1075eL, 0xe3056a0cL, 0x10d25065L, 0xcb03a442L, 
+	0xe0ec6e0eL, 0x1698db3bL, 0x4c98a0beL, 0x3278e964L, 
+	0x9f1f9532L, 0xe0d392dfL, 0xd3a0342bL, 0x8971f21eL, 
+	0x1b0a7441L, 0x4ba3348cL, 0xc5be7120L, 0xc37632d8L, 
+	0xdf359f8dL, 0x9b992f2eL, 0xe60b6f47L, 0x0fe3f11dL, 
+	0xe54cda54L, 0x1edad891L, 0xce6279cfL, 0xcd3e7e6fL, 
+	0x1618b166L, 0xfd2c1d05L, 0x848fd2c5L, 0xf6fb2299L, 
+	0xf523f357L, 0xa6327623L, 0x93a83531L, 0x56cccd02L, 
+	0xacf08162L, 0x5a75ebb5L, 0x6e163697L, 0x88d273ccL, 
+	0xde966292L, 0x81b949d0L, 0x4c50901bL, 0x71c65614L, 
+	0xe6c6c7bdL, 0x327a140aL, 0x45e1d006L, 0xc3f27b9aL, 
+	0xc9aa53fdL, 0x62a80f00L, 0xbb25bfe2L, 0x35bdd2f6L, 
+	0x71126905L, 0xb2040222L, 0xb6cbcf7cL, 0xcd769c2bL, 
+	0x53113ec0L, 0x1640e3d3L, 0x38abbd60L, 0x2547adf0L, 
+	0xba38209cL, 0xf746ce76L, 0x77afa1c5L, 0x20756060L, 
+	0x85cbfe4eL, 0x8ae88dd8L, 0x7aaaf9b0L, 0x4cf9aa7eL, 
+	0x1948c25cL, 0x02fb8a8cL, 0x01c36ae4L, 0xd6ebe1f9L, 
+	0x90d4f869L, 0xa65cdea0L, 0x3f09252dL, 0xc208e69fL, 
+	0xb74e6132L, 0xce77e25bL, 0x578fdfe3L, 0x3ac372e6L, 
+	}
+	};
+
diff --git a/lib/libcrypto/libblowfish/bf_skey.c b/lib/libcrypto/libblowfish/bf_skey.c
new file mode 100644
index 000000000..8cdbbd283
--- /dev/null
+++ b/lib/libcrypto/libblowfish/bf_skey.c
@@ -0,0 +1,122 @@
+/* crypto/bf/bf_skey.c */
+/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
+ * All rights reserved.
+ *
+ * This package is an SSL implementation written
+ * by Eric Young (eay@cryptsoft.com).
+ * The implementation was written so as to conform with Netscapes SSL.
+ * 
+ * This library is free for commercial and non-commercial use as long as
+ * the following conditions are aheared to.  The following conditions
+ * apply to all code found in this distribution, be it the RC4, RSA,
+ * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
+ * included with this distribution is covered by the same copyright terms
+ * except that the holder is Tim Hudson (tjh@cryptsoft.com).
+ * 
+ * Copyright remains Eric Young's, and as such any Copyright notices in
+ * the code are not to be removed.
+ * If this package is used in a product, Eric Young should be given attribution
+ * as the author of the parts of the library used.
+ * This can be in the form of a textual message at program startup or
+ * in documentation (online or textual) provided with the package.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from 
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ * 
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <linux/string.h>
+#else
+#include <stdio.h>
+#include <string.h>
+#endif
+
+#include "blowfish.h"
+#include "bf_locl.h"
+#include "bf_pi.h"
+
+void BF_set_key(BF_KEY *key, int len, const unsigned char *data)
+	{
+	int i;
+	BF_LONG *p,ri,in[2];
+	const unsigned char *d,*end;
+
+
+	memcpy((char *)key,(const char *)&bf_init,sizeof(BF_KEY));
+	p=key->P;
+
+	if (len > ((BF_ROUNDS+2)*4)) len=(BF_ROUNDS+2)*4;
+
+	d=data;
+	end= &(data[len]);
+	for (i=0; i<(BF_ROUNDS+2); i++)
+		{
+		ri= *(d++);
+		if (d >= end) d=data;
+
+		ri<<=8;
+		ri|= *(d++);
+		if (d >= end) d=data;
+
+		ri<<=8;
+		ri|= *(d++);
+		if (d >= end) d=data;
+
+		ri<<=8;
+		ri|= *(d++);
+		if (d >= end) d=data;
+
+		p[i]^=ri;
+		}
+
+	in[0]=0L;
+	in[1]=0L;
+	for (i=0; i<(BF_ROUNDS+2); i+=2)
+		{
+		BF_encrypt(in,key);
+		p[i  ]=in[0];
+		p[i+1]=in[1];
+		}
+
+	p=key->S;
+	for (i=0; i<4*256; i+=2)
+		{
+		BF_encrypt(in,key);
+		p[i  ]=in[0];
+		p[i+1]=in[1];
+		}
+	}
+
diff --git a/lib/libcrypto/libblowfish/blowfish.h b/lib/libcrypto/libblowfish/blowfish.h
new file mode 100644
index 000000000..ccb97e272
--- /dev/null
+++ b/lib/libcrypto/libblowfish/blowfish.h
@@ -0,0 +1,133 @@
+/* crypto/bf/blowfish.h */
+/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
+ * All rights reserved.
+ *
+ * This package is an SSL implementation written
+ * by Eric Young (eay@cryptsoft.com).
+ * The implementation was written so as to conform with Netscapes SSL.
+ * 
+ * This library is free for commercial and non-commercial use as long as
+ * the following conditions are aheared to.  The following conditions
+ * apply to all code found in this distribution, be it the RC4, RSA,
+ * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
+ * included with this distribution is covered by the same copyright terms
+ * except that the holder is Tim Hudson (tjh@cryptsoft.com).
+ * 
+ * Copyright remains Eric Young's, and as such any Copyright notices in
+ * the code are not to be removed.
+ * If this package is used in a product, Eric Young should be given attribution
+ * as the author of the parts of the library used.
+ * This can be in the form of a textual message at program startup or
+ * in documentation (online or textual) provided with the package.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from 
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ * 
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
+#ifndef HEADER_BLOWFISH_H
+#define HEADER_BLOWFISH_H
+
+#ifdef  __cplusplus
+extern "C" {
+#endif
+
+#ifdef NO_BF
+#error BF is disabled.
+#endif
+
+#define BF_ENCRYPT	1
+#define BF_DECRYPT	0
+
+/*
+ * !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+ * ! BF_LONG has to be at least 32 bits wide. If it's wider, then !
+ * ! BF_LONG_LOG2 has to be defined along.                        !
+ * !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+ */
+
+#if defined(WIN16) || defined(__LP32__)
+#define BF_LONG unsigned long
+#elif defined(_CRAY) || defined(__ILP64__)
+#define BF_LONG unsigned long
+#define BF_LONG_LOG2 3
+#endif
+/*
+ * _CRAY note. I could declare short, but I have no idea what impact
+ * does it have on performance on none-T3E machines. I could declare
+ * int, but at least on C90 sizeof(int) can be chosen at compile time.
+ * So I've chosen long...
+ *					<appro@fy.chalmers.se>
+ */
+	
+/* des.h-like hack <jjo-ipsec@mendoza.gov.ar> */
+#ifndef BF_LONG
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
+#define BF_LONG u_int32_t
+#endif
+
+#define BF_ROUNDS	16
+#define BF_BLOCK	8
+
+typedef struct bf_key_st
+	{
+	BF_LONG P[BF_ROUNDS+2];
+	BF_LONG S[4*256];
+	} BF_KEY;
+
+ 
+void BF_set_key(BF_KEY *key, int len, const unsigned char *data);
+
+void BF_encrypt(BF_LONG *data,const BF_KEY *key);
+void BF_decrypt(BF_LONG *data,const BF_KEY *key);
+
+void BF_ecb_encrypt(const unsigned char *in, unsigned char *out,
+	const BF_KEY *key, int enc);
+void BF_cbc_encrypt(const unsigned char *in, unsigned char *out, long length,
+	const BF_KEY *schedule, unsigned char *ivec, int enc);
+void BF_cfb64_encrypt(const unsigned char *in, unsigned char *out, long length,
+	const BF_KEY *schedule, unsigned char *ivec, int *num, int enc);
+void BF_ofb64_encrypt(const unsigned char *in, unsigned char *out, long length,
+	const BF_KEY *schedule, unsigned char *ivec, int *num);
+const char *BF_options(void);
+
+#ifdef  __cplusplus
+}
+#endif
+
+#endif
diff --git a/lib/libcrypto/libserpent/Makefile b/lib/libcrypto/libserpent/Makefile
new file mode 100644
index 000000000..51a1e0582
--- /dev/null
+++ b/lib/libcrypto/libserpent/Makefile
@@ -0,0 +1,20 @@
+CFLAGS=-O3 -fomit-frame-pointer -D__KERNEL__  -Wall $(EXTRA_CFLAGS)
+INC=-I../include 
+LIBOBJ=serpent.o serpent_cbc.o
+BLIB=libserpent.a
+
+.c.o:
+	$(CC) $(CPPFLAGS) $(CFLAGS) $(INC) -c $< -o $@
+
+$(BLIB): $(LIBOBJ)
+	/bin/rm -f $(BLIB)
+	ar cr $(BLIB) $(LIBOBJ)
+	-if test -s /bin/ranlib; then /bin/ranlib $(BLIB); \
+	else if test -s /usr/bin/ranlib; then /usr/bin/ranlib $(BLIB); \
+	else exit 0; fi; fi
+
+test: test_main.o $(BLIB)
+	$(CC) -o $@ $^ 
+
+clean:
+	rm -f *.[oa] core $(TARGET) test
diff --git a/lib/libcrypto/libserpent/serpent.c b/lib/libcrypto/libserpent/serpent.c
new file mode 100644
index 000000000..f2cea250e
--- /dev/null
+++ b/lib/libcrypto/libserpent/serpent.c
@@ -0,0 +1,995 @@
+
+/* Optimized implementation of the Serpent AES candidate algorithm
+ * Designed by Anderson, Biham and Knudsen and Implemented by 
+ * Gisle Sælensminde 2000. 
+ *
+ * The implementation is based on the pentium optimised sboxes of
+ * Dag Arne Osvik. Even these sboxes are designed to be optimal for x86 
+ * processors they are efficient on other processors as well, but the speedup 
+ * isn't so impressive compared to other implementations.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License
+ * as published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version. 
+ */
+
+#ifdef __KERNEL__
+#include <linux/init.h>
+#include <linux/types.h>
+
+#include <asm/byteorder.h>
+#else
+#include <sys/types.h>
+#include <asm/byteorder.h>
+#endif
+
+#include "serpent.h"
+
+#define rotl(reg, val) ((reg << val) | (reg >> (32 - val)))
+#define rotr(reg, val) ((reg >> val) | (reg << (32 - val)))
+ 
+#ifdef __cpu_to_be32
+#define BLOCK_SWAP
+#define io_swap(x)  __cpu_to_be32(x)
+#else
+#undef BLOCK_SWAP
+#endif
+
+/* The sbox functions. The first four parameters is the input bits, and 
+ * the last is a tempoary. These parameters are also used for output, but
+ * the bit order is permuted. The output bit order from S0 is
+ * (1 4 2 0 3), where 3 is the (now useless) tempoary. 
+ */
+
+#define S0(r0,r1,r2,r3,r4) \
+      r3 = r3 ^ r0; \
+      r4 = r1; \
+      r1 = r1 & r3; \
+      r4 = r4 ^ r2; \
+      r1 = r1 ^ r0; \
+      r0 = r0 | r3; \
+      r0 = r0 ^ r4; \
+      r4 = r4 ^ r3; \
+      r3 = r3 ^ r2; \
+      r2 = r2 | r1; \
+      r2 = r2 ^ r4; \
+      r4 = -1 ^ r4; \
+      r4 = r4 | r1; \
+      r1 = r1 ^ r3; \
+      r1 = r1 ^ r4; \
+      r3 = r3 | r0; \
+      r1 = r1 ^ r3; \
+      r4 = r4 ^ r3; 
+
+#define S1(r0,r1,r2,r3,r4) \
+      r1 = -1 ^ r1; \
+      r4 = r0; \
+      r0 = r0 ^ r1; \
+      r4 = r4 | r1; \
+      r4 = r4 ^ r3; \
+      r3 = r3 & r0; \
+      r2 = r2 ^ r4; \
+      r3 = r3 ^ r1; \
+      r3 = r3 | r2; \
+      r0 = r0 ^ r4; \
+      r3 = r3 ^ r0; \
+      r1 = r1 & r2; \
+      r0 = r0 | r1; \
+      r1 = r1 ^ r4; \
+      r0 = r0 ^ r2; \
+      r4 = r4 | r3; \
+      r0 = r0 ^ r4; \
+      r4 = -1 ^ r4; \
+      r1 = r1 ^ r3; \
+      r4 = r4 & r2; \
+      r1 = -1 ^ r1; \
+      r4 = r4 ^ r0; \
+      r1 = r1 ^ r4; 
+
+#define S2(r0,r1,r2,r3,r4) \
+      r4 = r0; \
+      r0 = r0 & r2; \
+      r0 = r0 ^ r3; \
+      r2 = r2 ^ r1; \
+      r2 = r2 ^ r0; \
+      r3 = r3 | r4; \
+      r3 = r3 ^ r1; \
+      r4 = r4 ^ r2; \
+      r1 = r3; \
+      r3 = r3 | r4; \
+      r3 = r3 ^ r0; \
+      r0 = r0 & r1; \
+      r4 = r4 ^ r0; \
+      r1 = r1 ^ r3; \
+      r1 = r1 ^ r4; \
+      r4 = -1 ^ r4; 
+
+#define S3(r0,r1,r2,r3,r4) \
+      r4 = r0 ; \
+      r0 = r0 | r3; \
+      r3 = r3 ^ r1; \
+      r1 = r1 & r4; \
+      r4 = r4 ^ r2; \
+      r2 = r2 ^ r3; \
+      r3 = r3 & r0; \
+      r4 = r4 | r1; \
+      r3 = r3 ^ r4; \
+      r0 = r0 ^ r1; \
+      r4 = r4 & r0; \
+      r1 = r1 ^ r3; \
+      r4 = r4 ^ r2; \
+      r1 = r1 | r0; \
+      r1 = r1 ^ r2; \
+      r0 = r0 ^ r3; \
+      r2 = r1; \
+      r1 = r1 | r3; \
+      r1 = r1 ^ r0; 
+
+#define S4(r0,r1,r2,r3,r4) \
+      r1 = r1 ^ r3; \
+      r3 = -1 ^ r3; \
+      r2 = r2 ^ r3; \
+      r3 = r3 ^ r0; \
+      r4 = r1; \
+      r1 = r1 & r3; \
+      r1 = r1 ^ r2; \
+      r4 = r4 ^ r3; \
+      r0 = r0 ^ r4; \
+      r2 = r2 & r4; \
+      r2 = r2 ^ r0; \
+      r0 = r0 & r1; \
+      r3 = r3 ^ r0; \
+      r4 = r4 | r1; \
+      r4 = r4 ^ r0; \
+      r0 = r0 | r3; \
+      r0 = r0 ^ r2; \
+      r2 = r2 & r3; \
+      r0 = -1 ^ r0; \
+      r4 = r4 ^ r2; 
+
+#define S5(r0,r1,r2,r3,r4) \
+      r0 = r0 ^ r1; \
+      r1 = r1 ^ r3; \
+      r3 = -1 ^ r3; \
+      r4 = r1; \
+      r1 = r1 & r0; \
+      r2 = r2 ^ r3; \
+      r1 = r1 ^ r2; \
+      r2 = r2 | r4; \
+      r4 = r4 ^ r3; \
+      r3 = r3 & r1; \
+      r3 = r3 ^ r0; \
+      r4 = r4 ^ r1; \
+      r4 = r4 ^ r2; \
+      r2 = r2 ^ r0; \
+      r0 = r0 & r3; \
+      r2 = -1 ^ r2; \
+      r0 = r0 ^ r4; \
+      r4 = r4 | r3; \
+      r2 = r2 ^ r4; 
+
+#define S6(r0,r1,r2,r3,r4) \
+      r2 = -1 ^ r2; \
+      r4 = r3; \
+      r3 = r3 & r0; \
+      r0 = r0 ^ r4; \
+      r3 = r3 ^ r2; \
+      r2 = r2 | r4; \
+      r1 = r1 ^ r3; \
+      r2 = r2 ^ r0; \
+      r0 = r0 | r1; \
+      r2 = r2 ^ r1; \
+      r4 = r4 ^ r0; \
+      r0 = r0 | r3; \
+      r0 = r0 ^ r2; \
+      r4 = r4 ^ r3; \
+      r4 = r4 ^ r0; \
+      r3 = -1 ^ r3; \
+      r2 = r2 & r4; \
+      r2 = r2 ^ r3; 
+
+#define S7(r0,r1,r2,r3,r4) \
+      r4 = r2; \
+      r2 = r2 & r1; \
+      r2 = r2 ^ r3; \
+      r3 = r3 & r1; \
+      r4 = r4 ^ r2; \
+      r2 = r2 ^ r1; \
+      r1 = r1 ^ r0; \
+      r0 = r0 | r4; \
+      r0 = r0 ^ r2; \
+      r3 = r3 ^ r1; \
+      r2 = r2 ^ r3; \
+      r3 = r3 & r0; \
+      r3 = r3 ^ r4; \
+      r4 = r4 ^ r2; \
+      r2 = r2 & r0; \
+      r4 = -1 ^ r4; \
+      r2 = r2 ^ r4; \
+      r4 = r4 & r0; \
+      r1 = r1 ^ r3; \
+      r4 = r4 ^ r1; 
+
+/* The inverse sboxes */
+
+#define I0(r0,r1,r2,r3,r4) \
+      r2 = r2 ^ -1; \
+      r4 = r1; \
+      r1 = r1 | r0; \
+      r4 = r4 ^ -1; \
+      r1 = r1 ^ r2; \
+      r2 = r2 | r4; \
+      r1 = r1 ^ r3; \
+      r0 = r0 ^ r4; \
+      r2 = r2 ^ r0; \
+      r0 = r0 & r3; \
+      r4 = r4 ^ r0; \
+      r0 = r0 | r1; \
+      r0 = r0 ^ r2; \
+      r3 = r3 ^ r4; \
+      r2 = r2 ^ r1; \
+      r3 = r3 ^ r0; \
+      r3 = r3 ^ r1; \
+      r2 = r2 & r3; \
+      r4 = r4 ^ r2; 
+ 
+#define I1(r0,r1,r2,r3,r4) \
+      r4 = r1; \
+      r1 = r1 ^ r3; \
+      r3 = r3 & r1; \
+      r4 = r4 ^ r2; \
+      r3 = r3 ^ r0; \
+      r0 = r0 | r1; \
+      r2 = r2 ^ r3; \
+      r0 = r0 ^ r4; \
+      r0 = r0 | r2; \
+      r1 = r1 ^ r3; \
+      r0 = r0 ^ r1; \
+      r1 = r1 | r3; \
+      r1 = r1 ^ r0; \
+      r4 = r4 ^ -1; \
+      r4 = r4 ^ r1; \
+      r1 = r1 | r0; \
+      r1 = r1 ^ r0; \
+      r1 = r1 | r4; \
+      r3 = r3 ^ r1; 
+
+#define I2(r0,r1,r2,r3,r4) \
+      r2 = r2 ^ r3; \
+      r3 = r3 ^ r0; \
+      r4 =  r3; \
+      r3 = r3 & r2; \
+      r3 = r3 ^ r1; \
+      r1 = r1 | r2; \
+      r1 = r1 ^ r4; \
+      r4 = r4 & r3; \
+      r2 = r2 ^ r3; \
+      r4 = r4 & r0; \
+      r4 = r4 ^ r2; \
+      r2 = r2 & r1; \
+      r2 = r2 | r0; \
+      r3 = r3 ^ -1; \
+      r2 = r2 ^ r3; \
+      r0 = r0 ^ r3; \
+      r0 = r0 & r1; \
+      r3 = r3 ^ r4; \
+      r3 = r3 ^ r0; 
+
+#define I3(r0,r1,r2,r3,r4) \
+      r4 =  r2; \
+      r2 = r2 ^ r1; \
+      r0 = r0 ^ r2; \
+      r4 = r4 & r2; \
+      r4 = r4 ^ r0; \
+      r0 = r0 & r1; \
+      r1 = r1 ^ r3; \
+      r3 = r3 | r4; \
+      r2 = r2 ^ r3; \
+      r0 = r0 ^ r3; \
+      r1 = r1 ^ r4; \
+      r3 = r3 & r2; \
+      r3 = r3 ^ r1; \
+      r1 = r1 ^ r0; \
+      r1 = r1 | r2; \
+      r0 = r0 ^ r3; \
+      r1 = r1 ^ r4; \
+      r0 = r0 ^ r1; 
+
+#define I4(r0,r1,r2,r3,r4) \
+      r4 =  r2; \
+      r2 = r2 & r3; \
+      r2 = r2 ^ r1; \
+      r1 = r1 | r3; \
+      r1 = r1 & r0; \
+      r4 = r4 ^ r2; \
+      r4 = r4 ^ r1; \
+      r1 = r1 & r2; \
+      r0 = r0 ^ -1; \
+      r3 = r3 ^ r4; \
+      r1 = r1 ^ r3; \
+      r3 = r3 & r0; \
+      r3 = r3 ^ r2; \
+      r0 = r0 ^ r1; \
+      r2 = r2 & r0; \
+      r3 = r3 ^ r0; \
+      r2 = r2 ^ r4; \
+      r2 = r2 | r3; \
+      r3 = r3 ^ r0; \
+      r2 = r2 ^ r1; 
+
+#define I5(r0,r1,r2,r3,r4) \
+      r1 = r1 ^ -1; \
+      r4 = r3; \
+      r2 = r2 ^ r1; \
+      r3 = r3 | r0; \
+      r3 = r3 ^ r2; \
+      r2 = r2 | r1; \
+      r2 = r2 & r0; \
+      r4 = r4 ^ r3; \
+      r2 = r2 ^ r4; \
+      r4 = r4 | r0; \
+      r4 = r4 ^ r1; \
+      r1 = r1 & r2; \
+      r1 = r1 ^ r3; \
+      r4 = r4 ^ r2; \
+      r3 = r3 & r4; \
+      r4 = r4 ^ r1; \
+      r3 = r3 ^ r0; \
+      r3 = r3 ^ r4; \
+      r4 = r4 ^ -1; 
+
+
+#define I6(r0,r1,r2,r3,r4) \
+      r0 = r0 ^ r2; \
+      r4 = r2; \
+      r2 = r2 & r0; \
+      r4 = r4 ^ r3; \
+      r2 = r2 ^ -1; \
+      r3 = r3 ^ r1; \
+      r2 = r2 ^ r3; \
+      r4 = r4 | r0; \
+      r0 = r0 ^ r2; \
+      r3 = r3 ^ r4; \
+      r4 = r4 ^ r1; \
+      r1 = r1 & r3; \
+      r1 = r1 ^ r0; \
+      r0 = r0 ^ r3; \
+      r0 = r0 | r2; \
+      r3 = r3 ^ r1; \
+      r4 = r4 ^ r0; 
+
+#define I7(r0,r1,r2,r3,r4) \
+      r4 = r2; \
+      r2 = r2 ^ r0; \
+      r0 = r0 & r3; \
+      r4 = r4 | r3; \
+      r2 = r2 ^ -1; \
+      r3 = r3 ^ r1; \
+      r1 = r1 | r0; \
+      r0 = r0 ^ r2; \
+      r2 = r2 & r4; \
+      r3 = r3 & r4; \
+      r1 = r1 ^ r2; \
+      r2 = r2 ^ r0; \
+      r0 = r0 | r2; \
+      r4 = r4 ^ r1; \
+      r0 = r0 ^ r3; \
+      r3 = r3 ^ r4; \
+      r4 = r4 | r0; \
+      r3 = r3 ^ r2; \
+      r4 = r4 ^ r2; 
+
+/* forward and inverse linear transformations */
+
+#define LINTRANS(r0,r1,r2,r3,r4) \
+      r0 = rotl(r0, 13); \
+      r2 = rotl(r2, 3); \
+      r3 = r3 ^ r2; \
+      r4 = r0 << 3; \
+      r1 = r1 ^ r0; \
+      r3 = r3 ^ r4; \
+      r1 = r1 ^ r2; \
+      r3 = rotl(r3, 7); \
+      r1 = rotl(r1, 1); \
+      r2 = r2 ^ r3; \
+      r4 = r1 << 7; \
+      r0 = r0 ^ r1; \
+      r2 = r2 ^ r4; \
+      r0 = r0 ^ r3; \
+      r2 = rotl(r2, 22); \
+      r0 = rotl(r0, 5);
+     
+#define ILINTRANS(r0,r1,r2,r3,r4) \
+      r2 = rotr(r2, 22); \
+      r0 = rotr(r0, 5); \
+      r2 = r2 ^ r3; \
+      r4 = r1 << 7; \
+      r0 = r0 ^ r1; \
+      r2 = r2 ^ r4; \
+      r0 = r0 ^ r3; \
+      r3 = rotr(r3, 7); \
+      r1 = rotr(r1, 1); \
+      r3 = r3 ^ r2; \
+      r4 = r0 << 3; \
+      r1 = r1 ^ r0; \
+      r3 = r3 ^ r4; \
+      r1 = r1 ^ r2; \
+      r2 = rotr(r2, 3); \
+      r0 = rotr(r0, 13); 
+
+
+#define KEYMIX(r0,r1,r2,r3,r4,IN) \
+      r0  = r0 ^ l_key[IN+8]; \
+      r1  = r1 ^ l_key[IN+9]; \
+      r2  = r2 ^ l_key[IN+10]; \
+      r3  = r3 ^ l_key[IN+11]; 
+
+#define GETKEY(r0, r1, r2, r3, IN) \
+      r0 = l_key[IN+8]; \
+      r1 = l_key[IN+9]; \
+      r2 = l_key[IN+10]; \
+      r3 = l_key[IN+11]; 
+
+#define SETKEY(r0, r1, r2, r3, IN) \
+      l_key[IN+8] = r0; \
+      l_key[IN+9] = r1; \
+      l_key[IN+10] = r2; \
+      l_key[IN+11] = r3;
+
+/* initialise the key schedule from the user supplied key   */
+
+int serpent_set_key(serpent_context *cx, const unsigned char *key, int key_len)
+{   const u32 *in_key = (const u32 *)key;
+    /* l_key - storage for the key schedule */
+    u32 *l_key   = cx->keyinfo;
+    u32  i,lk,r0,r1,r2,r3,r4;
+
+    if (key_len != 16 && key_len != 24 && key_len != 32)
+      return -1; /* unsupported key length */
+    
+    key_len *= 8;
+
+    i = 0; lk = (key_len + 31) / 32;
+    
+    while(i < lk)
+    {
+#ifdef  BLOCK_SWAP
+        l_key[i] = io_swap(in_key[lk - i - 1]);
+#else
+        l_key[i] = in_key[i];
+#endif  
+        i++;
+    }
+
+    if (key_len < 256)
+    {
+        while(i < 8)
+
+            l_key[i++] = 0;
+
+        i = key_len / 32; lk = 1 << key_len % 32; 
+
+        l_key[i] &= lk - 1;
+        l_key[i] |= lk;
+    }
+
+    for(i = 0; i < 132; ++i)
+    {
+        lk = l_key[i] ^ l_key[i + 3] ^ l_key[i + 5] 
+                                ^ l_key[i + 7] ^ 0x9e3779b9 ^ i;
+
+        l_key[i + 8] = (lk << 11) | (lk >> 21); 
+    }
+
+      GETKEY(r0, r1, r2, r3, 0);
+      S3(r0,r1,r2,r3,r4);
+      SETKEY(r1, r2, r3, r4, 0) 
+
+      GETKEY(r0, r1, r2, r3, 4);
+      S2(r0,r1,r2,r3,r4);
+      SETKEY(r2, r3, r1, r4, 4) 
+
+      GETKEY(r0, r1, r2, r3, 8);
+      S1(r0,r1,r2,r3,r4);
+      SETKEY(r3, r1, r2, r0, 8) 
+
+      GETKEY(r0, r1, r2, r3, 12);
+      S0(r0,r1,r2,r3,r4);
+      SETKEY(r1, r4, r2, r0, 12) 
+
+      GETKEY(r0, r1, r2, r3, 16);
+      S7(r0,r1,r2,r3,r4);
+      SETKEY(r2, r4, r3, r0, 16) 
+
+      GETKEY(r0, r1, r2, r3, 20);
+      S6(r0,r1,r2,r3,r4) 
+      SETKEY(r0, r1, r4, r2, 20) 
+
+      GETKEY(r0, r1, r2, r3, 24);
+      S5(r0,r1,r2,r3,r4);
+      SETKEY(r1, r3, r0, r2, 24) 
+
+      GETKEY(r0, r1, r2, r3, 28);
+      S4(r0,r1,r2,r3,r4) 
+      SETKEY(r1, r4, r0, r3, 28) 
+
+      GETKEY(r0, r1, r2, r3, 32);
+      S3(r0,r1,r2,r3,r4);
+      SETKEY(r1, r2, r3, r4, 32) 
+
+      GETKEY(r0, r1, r2, r3, 36);
+      S2(r0,r1,r2,r3,r4);
+      SETKEY(r2, r3, r1, r4, 36) 
+
+      GETKEY(r0, r1, r2, r3, 40);
+      S1(r0,r1,r2,r3,r4);
+      SETKEY(r3, r1, r2, r0, 40) 
+
+      GETKEY(r0, r1, r2, r3, 44);
+      S0(r0,r1,r2,r3,r4);
+      SETKEY(r1, r4, r2, r0, 44) 
+
+      GETKEY(r0, r1, r2, r3, 48);
+      S7(r0,r1,r2,r3,r4);
+      SETKEY(r2, r4, r3, r0, 48) 
+
+      GETKEY(r0, r1, r2, r3, 52);
+      S6(r0,r1,r2,r3,r4) 
+      SETKEY(r0, r1, r4, r2, 52) 
+
+      GETKEY(r0, r1, r2, r3, 56);
+      S5(r0,r1,r2,r3,r4);
+      SETKEY(r1, r3, r0, r2, 56) 
+
+      GETKEY(r0, r1, r2, r3, 60);
+      S4(r0,r1,r2,r3,r4) 
+      SETKEY(r1, r4, r0, r3, 60) 
+
+      GETKEY(r0, r1, r2, r3, 64);
+      S3(r0,r1,r2,r3,r4);
+      SETKEY(r1, r2, r3, r4, 64) 
+
+      GETKEY(r0, r1, r2, r3, 68);
+      S2(r0,r1,r2,r3,r4);
+      SETKEY(r2, r3, r1, r4, 68) 
+
+      GETKEY(r0, r1, r2, r3, 72);
+      S1(r0,r1,r2,r3,r4);
+      SETKEY(r3, r1, r2, r0, 72) 
+
+      GETKEY(r0, r1, r2, r3, 76);
+      S0(r0,r1,r2,r3,r4);
+      SETKEY(r1, r4, r2, r0, 76) 
+
+      GETKEY(r0, r1, r2, r3, 80);
+      S7(r0,r1,r2,r3,r4);
+      SETKEY(r2, r4, r3, r0, 80) 
+
+      GETKEY(r0, r1, r2, r3, 84);
+      S6(r0,r1,r2,r3,r4) 
+      SETKEY(r0, r1, r4, r2, 84) 
+
+      GETKEY(r0, r1, r2, r3, 88);
+      S5(r0,r1,r2,r3,r4);
+      SETKEY(r1, r3, r0, r2, 88) 
+
+      GETKEY(r0, r1, r2, r3, 92);
+      S4(r0,r1,r2,r3,r4) 
+      SETKEY(r1, r4, r0, r3, 92) 
+
+      GETKEY(r0, r1, r2, r3, 96);
+      S3(r0,r1,r2,r3,r4);
+      SETKEY(r1, r2, r3, r4, 96) 
+
+      GETKEY(r0, r1, r2, r3, 100);
+      S2(r0,r1,r2,r3,r4);
+      SETKEY(r2, r3, r1, r4, 100) 
+
+      GETKEY(r0, r1, r2, r3, 104);
+      S1(r0,r1,r2,r3,r4);
+      SETKEY(r3, r1, r2, r0, 104) 
+
+      GETKEY(r0, r1, r2, r3, 108);
+      S0(r0,r1,r2,r3,r4);
+      SETKEY(r1, r4, r2, r0, 108) 
+
+      GETKEY(r0, r1, r2, r3, 112);
+      S7(r0,r1,r2,r3,r4);
+      SETKEY(r2, r4, r3, r0, 112) 
+
+      GETKEY(r0, r1, r2, r3, 116);
+      S6(r0,r1,r2,r3,r4) 
+      SETKEY(r0, r1, r4, r2, 116) 
+
+      GETKEY(r0, r1, r2, r3, 120);
+      S5(r0,r1,r2,r3,r4);
+      SETKEY(r1, r3, r0, r2, 120) 
+
+      GETKEY(r0, r1, r2, r3, 124);
+      S4(r0,r1,r2,r3,r4) 
+      SETKEY(r1, r4, r0, r3, 124) 
+
+      GETKEY(r0, r1, r2, r3, 128);
+      S3(r0,r1,r2,r3,r4);
+      SETKEY(r1, r2, r3, r4, 128) 
+
+    return 0;
+};
+
+/* Encryption and decryption functions. The rounds are fully inlined. 
+ * The sboxes alters the bit order of the output, and the altered
+ * bit ordrer is used progressivly. */
+
+/* encrypt a block of text */
+
+int serpent_encrypt(serpent_context *cx, const u8 *in, 
+		    u8 *out)
+{    u32 *l_key = cx->keyinfo;
+     const u32 *in_blk = (const u32 *) in;
+     u32 *out_blk = (u32 *) out;
+     u32  r0,r1,r2,r3,r4;
+    
+#ifdef  BLOCK_SWAP
+    r0 = io_swap(in_blk[3]); r1 = io_swap(in_blk[2]); 
+    r2 = io_swap(in_blk[1]); r3 = io_swap(in_blk[0]);
+#else
+    r0 = in_blk[0]; r1 = in_blk[1]; r2 = in_blk[2]; r3 = in_blk[3];
+#endif
+
+      /* round 1  */
+      KEYMIX(r0,r1,r2,r3,r4,0);
+      S0(r0,r1,r2,r3,r4);
+      LINTRANS(r1,r4,r2,r0,r3);
+
+      /* round 2  */
+      KEYMIX(r1,r4,r2,r0,r3,4);
+      S1(r1,r4,r2,r0,r3);
+      LINTRANS(r0,r4,r2,r1,r3);
+
+      /* round 3  */
+      KEYMIX(r0,r4,r2,r1,r3,8);
+      S2(r0,r4,r2,r1,r3);
+      LINTRANS(r2,r1,r4,r3,r0);
+
+      /* round 4  */
+      KEYMIX(r2,r1,r4,r3,r0,12);
+      S3(r2,r1,r4,r3,r0);
+      LINTRANS(r1,r4,r3,r0,r2);
+
+      /* round 5  */
+      KEYMIX(r1,r4,r3,r0,r2,16);
+      S4(r1,r4,r3,r0,r2) 
+      LINTRANS(r4,r2,r1,r0,r3);
+
+      /* round 6  */
+      KEYMIX(r4,r2,r1,r0,r3,20);
+      S5(r4,r2,r1,r0,r3);
+      LINTRANS(r2,r0,r4,r1,r3);
+
+      /* round 7  */
+      KEYMIX(r2,r0,r4,r1,r3,24);
+      S6(r2,r0,r4,r1,r3) 
+      LINTRANS(r2,r0,r3,r4,r1);
+
+      /* round 8  */
+      KEYMIX(r2,r0,r3,r4,r1,28);
+      S7(r2,r0,r3,r4,r1);
+      LINTRANS(r3,r1,r4,r2,r0);
+
+      /* round 9  */
+      KEYMIX(r3,r1,r4,r2,r0,32);
+      S0(r3,r1,r4,r2,r0);
+      LINTRANS(r1,r0,r4,r3,r2);
+
+      /* round 10  */
+      KEYMIX(r1,r0,r4,r3,r2,36);
+      S1(r1,r0,r4,r3,r2);
+      LINTRANS(r3,r0,r4,r1,r2);
+
+      /* round 11  */
+      KEYMIX(r3,r0,r4,r1,r2,40);
+      S2(r3,r0,r4,r1,r2);
+      LINTRANS(r4,r1,r0,r2,r3);
+
+      /* round 12  */
+      KEYMIX(r4,r1,r0,r2,r3,44);
+      S3(r4,r1,r0,r2,r3);
+      LINTRANS(r1,r0,r2,r3,r4);
+
+      /* round 13  */
+      KEYMIX(r1,r0,r2,r3,r4,48);
+      S4(r1,r0,r2,r3,r4) 
+      LINTRANS(r0,r4,r1,r3,r2);
+
+      /* round 14  */
+      KEYMIX(r0,r4,r1,r3,r2,52);
+      S5(r0,r4,r1,r3,r2);
+      LINTRANS(r4,r3,r0,r1,r2);
+
+      /* round 15  */
+      KEYMIX(r4,r3,r0,r1,r2,56);
+      S6(r4,r3,r0,r1,r2) 
+      LINTRANS(r4,r3,r2,r0,r1);
+
+      /* round 16  */
+      KEYMIX(r4,r3,r2,r0,r1,60);
+      S7(r4,r3,r2,r0,r1);
+      LINTRANS(r2,r1,r0,r4,r3);
+
+      /* round 17  */
+      KEYMIX(r2,r1,r0,r4,r3,64);
+      S0(r2,r1,r0,r4,r3);
+      LINTRANS(r1,r3,r0,r2,r4);
+
+      /* round 18  */
+      KEYMIX(r1,r3,r0,r2,r4,68);
+      S1(r1,r3,r0,r2,r4);
+      LINTRANS(r2,r3,r0,r1,r4);
+
+      /* round 19  */
+      KEYMIX(r2,r3,r0,r1,r4,72);
+      S2(r2,r3,r0,r1,r4);
+      LINTRANS(r0,r1,r3,r4,r2);
+
+      /* round 20  */
+      KEYMIX(r0,r1,r3,r4,r2,76);
+      S3(r0,r1,r3,r4,r2);
+      LINTRANS(r1,r3,r4,r2,r0);
+
+      /* round 21  */
+      KEYMIX(r1,r3,r4,r2,r0,80);
+      S4(r1,r3,r4,r2,r0) 
+      LINTRANS(r3,r0,r1,r2,r4);
+
+      /* round 22  */
+      KEYMIX(r3,r0,r1,r2,r4,84);
+      S5(r3,r0,r1,r2,r4);
+      LINTRANS(r0,r2,r3,r1,r4);
+
+      /* round 23  */
+      KEYMIX(r0,r2,r3,r1,r4,88);
+      S6(r0,r2,r3,r1,r4) 
+      LINTRANS(r0,r2,r4,r3,r1);
+
+      /* round 24  */
+      KEYMIX(r0,r2,r4,r3,r1,92);
+      S7(r0,r2,r4,r3,r1);
+      LINTRANS(r4,r1,r3,r0,r2);
+
+      /* round 25  */
+      KEYMIX(r4,r1,r3,r0,r2,96);
+      S0(r4,r1,r3,r0,r2);
+      LINTRANS(r1,r2,r3,r4,r0);
+
+      /* round 26  */
+      KEYMIX(r1,r2,r3,r4,r0,100);
+      S1(r1,r2,r3,r4,r0);
+      LINTRANS(r4,r2,r3,r1,r0);
+
+      /* round 27  */
+      KEYMIX(r4,r2,r3,r1,r0,104);
+      S2(r4,r2,r3,r1,r0);
+      LINTRANS(r3,r1,r2,r0,r4);
+
+      /* round 28  */
+      KEYMIX(r3,r1,r2,r0,r4,108);
+      S3(r3,r1,r2,r0,r4);
+      LINTRANS(r1,r2,r0,r4,r3);
+
+      /* round 29  */
+      KEYMIX(r1,r2,r0,r4,r3,112);
+      S4(r1,r2,r0,r4,r3) 
+      LINTRANS(r2,r3,r1,r4,r0);
+
+      /* round 30  */
+      KEYMIX(r2,r3,r1,r4,r0,116);
+      S5(r2,r3,r1,r4,r0);
+      LINTRANS(r3,r4,r2,r1,r0);
+
+      /* round 31  */
+      KEYMIX(r3,r4,r2,r1,r0,120);
+      S6(r3,r4,r2,r1,r0) 
+      LINTRANS(r3,r4,r0,r2,r1);
+
+      /* round 32  */
+      KEYMIX(r3,r4,r0,r2,r1,124);
+      S7(r3,r4,r0,r2,r1);
+      KEYMIX(r0,r1,r2,r3,r4,128);
+
+    
+#ifdef  BLOCK_SWAP
+    out_blk[3] = io_swap(r0); out_blk[2] = io_swap(r1); 
+    out_blk[1] = io_swap(r2); out_blk[0] = io_swap(r3);
+#else
+    out_blk[0] = r0; out_blk[1] = r1; out_blk[2] = r2; out_blk[3] = r3;
+#endif
+    return 0;
+};
+
+/* decrypt a block of text  */
+
+int serpent_decrypt(serpent_context *cx, const u8 *in,
+		    u8 *out)
+{   u32 *l_key = cx->keyinfo;
+    const u32 *in_blk = (const u32 *)in;
+    u32 *out_blk = (u32 *)out;
+    u32  r0,r1,r2,r3,r4;
+    
+#ifdef  BLOCK_SWAP
+    r0 = io_swap(in_blk[3]); r1 = io_swap(in_blk[2]); 
+    r2 = io_swap(in_blk[1]); r3 = io_swap(in_blk[0]);
+#else
+    r0 = in_blk[0]; r1 = in_blk[1]; r2 = in_blk[2]; r3 = in_blk[3];
+#endif
+
+      /* round 1 */
+      KEYMIX(r0,r1,r2,r3,r4,128);
+      I7(r0,r1,r2,r3,r4);
+      KEYMIX(r3,r0,r1,r4,r2,124);
+
+      /* round 2  */
+      ILINTRANS(r3,r0,r1,r4,r2);
+      I6(r3,r0,r1,r4,r2);
+      KEYMIX(r0,r1,r2,r4,r3,120);
+
+      /* round 3  */
+      ILINTRANS(r0,r1,r2,r4,r3);
+      I5(r0,r1,r2,r4,r3);
+      KEYMIX(r1,r3,r4,r2,r0,116);
+
+      /* round 4  */
+      ILINTRANS(r1,r3,r4,r2,r0);
+      I4(r1,r3,r4,r2,r0);
+      KEYMIX(r1,r2,r4,r0,r3,112);
+
+      /* round 5  */
+      ILINTRANS(r1,r2,r4,r0,r3);
+      I3(r1,r2,r4,r0,r3);
+      KEYMIX(r4,r2,r0,r1,r3,108);
+
+      /* round 6  */
+      ILINTRANS(r4,r2,r0,r1,r3);
+      I2(r4,r2,r0,r1,r3);
+      KEYMIX(r2,r3,r0,r1,r4,104);
+
+      /* round 7  */
+      ILINTRANS(r2,r3,r0,r1,r4);
+      I1(r2,r3,r0,r1,r4);
+      KEYMIX(r4,r2,r1,r0,r3,100);
+
+      /* round 8  */
+      ILINTRANS(r4,r2,r1,r0,r3);
+      I0(r4,r2,r1,r0,r3);
+      KEYMIX(r4,r3,r2,r0,r1,96);
+
+      /* round 9  */
+      ILINTRANS(r4,r3,r2,r0,r1);
+      I7(r4,r3,r2,r0,r1);
+      KEYMIX(r0,r4,r3,r1,r2,92);
+
+      /* round 10  */
+      ILINTRANS(r0,r4,r3,r1,r2);
+      I6(r0,r4,r3,r1,r2);
+      KEYMIX(r4,r3,r2,r1,r0,88);
+
+      /* round 11  */
+      ILINTRANS(r4,r3,r2,r1,r0);
+      I5(r4,r3,r2,r1,r0);
+      KEYMIX(r3,r0,r1,r2,r4,84);
+
+      /* round 12  */
+      ILINTRANS(r3,r0,r1,r2,r4);
+      I4(r3,r0,r1,r2,r4);
+      KEYMIX(r3,r2,r1,r4,r0,80);
+
+      /* round 13  */
+      ILINTRANS(r3,r2,r1,r4,r0);
+      I3(r3,r2,r1,r4,r0);
+      KEYMIX(r1,r2,r4,r3,r0,76);
+
+      /* round 14  */
+      ILINTRANS(r1,r2,r4,r3,r0);
+      I2(r1,r2,r4,r3,r0);
+      KEYMIX(r2,r0,r4,r3,r1,72);
+
+      /* round 15  */
+      ILINTRANS(r2,r0,r4,r3,r1);
+      I1(r2,r0,r4,r3,r1);
+      KEYMIX(r1,r2,r3,r4,r0,68);
+
+      /* round 16  */
+      ILINTRANS(r1,r2,r3,r4,r0);
+      I0(r1,r2,r3,r4,r0);
+      KEYMIX(r1,r0,r2,r4,r3,64);
+
+      /* round 17  */
+      ILINTRANS(r1,r0,r2,r4,r3);
+      I7(r1,r0,r2,r4,r3);
+      KEYMIX(r4,r1,r0,r3,r2,60);
+
+      /* round 18  */
+      ILINTRANS(r4,r1,r0,r3,r2);
+      I6(r4,r1,r0,r3,r2);
+      KEYMIX(r1,r0,r2,r3,r4,56);
+
+      /* round 19  */
+      ILINTRANS(r1,r0,r2,r3,r4);
+      I5(r1,r0,r2,r3,r4);
+      KEYMIX(r0,r4,r3,r2,r1,52);
+
+      /* round 20  */
+      ILINTRANS(r0,r4,r3,r2,r1);
+      I4(r0,r4,r3,r2,r1);
+      KEYMIX(r0,r2,r3,r1,r4,48);
+
+      /* round 21  */
+      ILINTRANS(r0,r2,r3,r1,r4);
+      I3(r0,r2,r3,r1,r4);
+      KEYMIX(r3,r2,r1,r0,r4,44);
+
+      /* round 22  */
+      ILINTRANS(r3,r2,r1,r0,r4);
+      I2(r3,r2,r1,r0,r4);
+      KEYMIX(r2,r4,r1,r0,r3,40);
+
+      /* round 23  */
+      ILINTRANS(r2,r4,r1,r0,r3);
+      I1(r2,r4,r1,r0,r3);
+      KEYMIX(r3,r2,r0,r1,r4,36);
+
+      /* round 24  */
+      ILINTRANS(r3,r2,r0,r1,r4);
+      I0(r3,r2,r0,r1,r4);
+      KEYMIX(r3,r4,r2,r1,r0,32);
+
+      /* round 25  */
+      ILINTRANS(r3,r4,r2,r1,r0);
+      I7(r3,r4,r2,r1,r0);
+      KEYMIX(r1,r3,r4,r0,r2,28);
+
+      /* round 26  */
+      ILINTRANS(r1,r3,r4,r0,r2);
+      I6(r1,r3,r4,r0,r2);
+      KEYMIX(r3,r4,r2,r0,r1,24);
+
+      /* round 27  */
+      ILINTRANS(r3,r4,r2,r0,r1);
+      I5(r3,r4,r2,r0,r1);
+      KEYMIX(r4,r1,r0,r2,r3,20);
+
+      /* round 28  */
+      ILINTRANS(r4,r1,r0,r2,r3);
+      I4(r4,r1,r0,r2,r3);
+      KEYMIX(r4,r2,r0,r3,r1,16);
+
+      /* round 29  */
+      ILINTRANS(r4,r2,r0,r3,r1);
+      I3(r4,r2,r0,r3,r1);
+      KEYMIX(r0,r2,r3,r4,r1,12);
+
+      /* round 30  */
+      ILINTRANS(r0,r2,r3,r4,r1);
+      I2(r0,r2,r3,r4,r1);
+      KEYMIX(r2,r1,r3,r4,r0,8);
+
+      /* round 31  */
+      ILINTRANS(r2,r1,r3,r4,r0);
+      I1(r2,r1,r3,r4,r0);
+      KEYMIX(r0,r2,r4,r3,r1,4);
+
+      /* round 32  */
+      ILINTRANS(r0,r2,r4,r3,r1);
+      I0(r0,r2,r4,r3,r1);
+      KEYMIX(r0,r1,r2,r3,r4,0);
+    
+#ifdef  BLOCK_SWAP
+    out_blk[3] = io_swap(r0); out_blk[2] = io_swap(r1); 
+    out_blk[1] = io_swap(r2); out_blk[0] = io_swap(r3);
+#else
+    out_blk[0] = r0; out_blk[1] = r1; out_blk[2] = r2; out_blk[3] = r3;
+#endif
+    return 0;
+};
+
+
diff --git a/lib/libcrypto/libserpent/serpent.h b/lib/libcrypto/libserpent/serpent.h
new file mode 100644
index 000000000..6357f5bfa
--- /dev/null
+++ b/lib/libcrypto/libserpent/serpent.h
@@ -0,0 +1,17 @@
+#ifndef SERPENT_H
+#define SERPENT_H
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#define u32 u_int32_t
+#define u8 u_int8_t
+#endif
+struct serpent_context {
+	u32  keyinfo[140]; /* storage for the key schedule         */
+};
+typedef struct serpent_context serpent_context;
+int serpent_set_key(serpent_context *ctx, const u8 * in_key, int key_len);
+int serpent_decrypt(serpent_context *ctx, const u8 * in_blk, u8 * out_blk);
+int serpent_encrypt(serpent_context *ctx, const u8 * in_blk, u8 * out_blk);
+#endif /* SERPENT_H */
diff --git a/lib/libcrypto/libserpent/serpent_cbc.c b/lib/libcrypto/libserpent/serpent_cbc.c
new file mode 100644
index 000000000..3b546278a
--- /dev/null
+++ b/lib/libcrypto/libserpent/serpent_cbc.c
@@ -0,0 +1,8 @@
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
+#include "serpent_cbc.h"
+#include "cbc_generic.h"
+CBC_IMPL_BLK16(serpent_cbc_encrypt, serpent_context, u_int8_t *, serpent_encrypt, serpent_decrypt);
diff --git a/lib/libcrypto/libserpent/serpent_cbc.h b/lib/libcrypto/libserpent/serpent_cbc.h
new file mode 100644
index 000000000..3064fa3bc
--- /dev/null
+++ b/lib/libcrypto/libserpent/serpent_cbc.h
@@ -0,0 +1,3 @@
+/* Glue header */
+#include "serpent.h"
+int serpent_cbc_encrypt(serpent_context *ctx, const u_int8_t * in, u_int8_t * out, int ilen, const u_int8_t * iv, int encrypt);
diff --git a/lib/libcrypto/libserpent/test_main.c b/lib/libcrypto/libserpent/test_main.c
new file mode 100644
index 000000000..350068e60
--- /dev/null
+++ b/lib/libcrypto/libserpent/test_main.c
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <string.h>
+#include "serpent_cbc.h"
+#define BLOCK_SIZE	16
+#define KEY_SIZE 	128	/* bits */
+#define KEY 		"1234567890123456"
+#define STR 		"hola guaso como estaisss ... 012"
+#define STRSZ		(sizeof(STR)-1)
+
+#define BLKLEN 		BLOCK_SIZE
+#define CONTEXT_T  	serpent_context
+static int pretty_print(const unsigned char *buf, int count) {
+	int i=0;
+	for (;i<count;i++) printf ("%02hhx ", buf[i]);
+	putchar('\n');
+	return i;
+}
+//#define SIZE STRSZ/2
+#define SIZE STRSZ
+int main() {
+	int ret;
+	char buf0[SIZE+1], buf1[SIZE+1];
+	char IV[BLOCK_SIZE];
+	CONTEXT_T ac;	
+	serpent_set_key(&ac, (void *)KEY, KEY_SIZE);
+	memset(buf0, 0, sizeof (buf0));
+	memset(buf1, 0, sizeof (buf1));
+	serpent_cbc_encrypt(&ac, STR, buf0, SIZE, IV, 1);
+	pretty_print(buf0, SIZE);
+	printf("size=%d ret=%d\n%s\n", SIZE, ret, buf0);
+	ret=serpent_cbc_encrypt(&ac, buf0, buf1, SIZE, IV, 0);
+	printf("size=%d ret=%d\n%s\n", SIZE, ret, buf1);
+	return 0;
+}
diff --git a/lib/libcrypto/libsha2/Makefile b/lib/libcrypto/libsha2/Makefile
new file mode 100644
index 000000000..cee7e6109
--- /dev/null
+++ b/lib/libcrypto/libsha2/Makefile
@@ -0,0 +1,21 @@
+CFLAGS=-O3 -fomit-frame-pointer -I../include $(EXTRA_CFLAGS)
+
+LIBOBJ := hmac_sha2.o sha2.o
+
+BLIB := libsha2.a
+
+.S.o:
+	$(CC) $(AFLAGS) -c $< -o $@
+
+$(BLIB): $(LIBOBJ)
+	/bin/rm -f $(BLIB)
+	ar cr $(BLIB) $(LIBOBJ)
+	-if test -s /bin/ranlib; then /bin/ranlib $(BLIB); \
+	else if test -s /usr/bin/ranlib; then /usr/bin/ranlib $(BLIB); \
+	else exit 0; fi; fi
+
+test: test_main.o $(BLIB)
+	$(CC) -o $@ $^ 
+
+clean:
+	rm -f *.[oa] core $(TARGET) test
diff --git a/lib/libcrypto/libsha2/hmac_sha2.c b/lib/libcrypto/libsha2/hmac_sha2.c
new file mode 100644
index 000000000..ad107eb62
--- /dev/null
+++ b/lib/libcrypto/libsha2/hmac_sha2.c
@@ -0,0 +1,32 @@
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <linux/string.h>
+#else
+#include <sys/types.h>
+#include <string.h>
+#endif
+#include "hmac_generic.h"
+#include "sha2.h"
+#include "hmac_sha2.h"
+
+void inline sha256_result(sha256_context *ctx, u_int8_t * hash, int hashlen) {
+	sha256_final(ctx);
+	memcpy(hash, &ctx->sha_out[0], hashlen);
+}
+void inline sha512_result(sha512_context *ctx, u_int8_t * hash, int hashlen) {
+	sha512_final(ctx);
+	memcpy(hash, &ctx->sha_out[0], hashlen);
+}
+HMAC_SET_KEY_IMPL (sha256_hmac_set_key, 
+		sha256_hmac_context, SHA256_BLOCKSIZE, 
+		sha256_init, sha256_write)
+HMAC_HASH_IMPL (sha256_hmac_hash, 
+		sha256_hmac_context, sha256_context, SHA256_HASHLEN,
+		sha256_write, sha256_result)
+
+HMAC_SET_KEY_IMPL (sha512_hmac_set_key, 
+		sha512_hmac_context, SHA512_BLOCKSIZE, 
+		sha512_init, sha512_write)
+HMAC_HASH_IMPL (sha512_hmac_hash, 
+		sha512_hmac_context, sha512_context, SHA512_HASHLEN,
+		sha512_write, sha512_result)
diff --git a/lib/libcrypto/libsha2/hmac_sha2.h b/lib/libcrypto/libsha2/hmac_sha2.h
new file mode 100644
index 000000000..b7f8c747c
--- /dev/null
+++ b/lib/libcrypto/libsha2/hmac_sha2.h
@@ -0,0 +1,17 @@
+typedef struct {
+	sha256_context ictx,octx;
+} sha256_hmac_context;
+typedef struct {
+	sha512_context ictx,octx;
+} sha512_hmac_context;
+#define SHA256_BLOCKSIZE 64
+#define SHA256_HASHLEN   32
+#define SHA384_BLOCKSIZE 128	/* XXX ok? */
+#define SHA384_HASHLEN   48
+#define SHA512_BLOCKSIZE 128
+#define SHA512_HASHLEN   64
+
+void sha256_hmac_hash(sha256_hmac_context *hctx, const u_int8_t * dat, int len, u_int8_t * hash, int hashlen);
+void sha256_hmac_set_key(sha256_hmac_context *hctx, const u_int8_t * key, int keylen);
+void sha512_hmac_hash(sha512_hmac_context *hctx, const u_int8_t * dat, int len, u_int8_t * hash, int hashlen);
+void sha512_hmac_set_key(sha512_hmac_context *hctx, const u_int8_t * key, int keylen);
diff --git a/lib/libcrypto/libsha2/sha2.c b/lib/libcrypto/libsha2/sha2.c
new file mode 100644
index 000000000..4debdad67
--- /dev/null
+++ b/lib/libcrypto/libsha2/sha2.c
@@ -0,0 +1,437 @@
+/*
+ *  sha512.c
+ *
+ *  Written by Jari Ruusu, April 16 2001
+ *
+ *  Copyright 2001 by Jari Ruusu.
+ *  Redistribution of this file is permitted under the GNU Public License.
+ */
+
+#ifdef __KERNEL__
+#include <linux/string.h>
+#include <linux/types.h>
+#else
+#include <string.h>
+#include <sys/types.h>
+#endif
+#include "sha2.h"
+
+/* Define one or more of these. If none is defined, you get all of them */
+#if !defined(SHA256_NEEDED)&&!defined(SHA512_NEEDED)&&!defined(SHA384_NEEDED)
+# define SHA256_NEEDED  1
+# define SHA512_NEEDED  1
+# define SHA384_NEEDED  1
+#endif
+
+#if defined(SHA256_NEEDED)
+static const u_int32_t sha256_hashInit[8] = {
+    0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c,
+    0x1f83d9ab, 0x5be0cd19
+};
+static const u_int32_t sha256_K[64] = {
+    0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1,
+    0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+    0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786,
+    0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+    0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147,
+    0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+    0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b,
+    0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+    0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a,
+    0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+    0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+};
+#endif
+
+#if defined(SHA512_NEEDED)
+static const u_int64_t sha512_hashInit[8] = {
+    0x6a09e667f3bcc908ULL, 0xbb67ae8584caa73bULL, 0x3c6ef372fe94f82bULL,
+    0xa54ff53a5f1d36f1ULL, 0x510e527fade682d1ULL, 0x9b05688c2b3e6c1fULL,
+    0x1f83d9abfb41bd6bULL, 0x5be0cd19137e2179ULL
+};
+#endif
+
+#if defined(SHA384_NEEDED)
+static const u_int64_t sha384_hashInit[8] = {
+    0xcbbb9d5dc1059ed8ULL, 0x629a292a367cd507ULL, 0x9159015a3070dd17ULL,
+    0x152fecd8f70e5939ULL, 0x67332667ffc00b31ULL, 0x8eb44a8768581511ULL,
+    0xdb0c2e0d64f98fa7ULL, 0x47b5481dbefa4fa4ULL
+};
+#endif
+
+#if defined(SHA512_NEEDED) || defined(SHA384_NEEDED)
+static const u_int64_t sha512_K[80] = {
+    0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
+    0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
+    0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL, 0xd807aa98a3030242ULL,
+    0x12835b0145706fbeULL, 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
+    0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL, 0x9bdc06a725c71235ULL,
+    0xc19bf174cf692694ULL, 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
+    0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL, 0x2de92c6f592b0275ULL,
+    0x4a7484aa6ea6e483ULL, 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
+    0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL, 0xb00327c898fb213fULL,
+    0xbf597fc7beef0ee4ULL, 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
+    0x06ca6351e003826fULL, 0x142929670a0e6e70ULL, 0x27b70a8546d22ffcULL,
+    0x2e1b21385c26c926ULL, 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
+    0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL, 0x81c2c92e47edaee6ULL,
+    0x92722c851482353bULL, 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
+    0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL, 0xd192e819d6ef5218ULL,
+    0xd69906245565a910ULL, 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
+    0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL, 0x2748774cdf8eeb99ULL,
+    0x34b0bcb5e19b48a8ULL, 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
+    0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL, 0x748f82ee5defb2fcULL,
+    0x78a5636f43172f60ULL, 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
+    0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL, 0xbef9a3f7b2c67915ULL,
+    0xc67178f2e372532bULL, 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
+    0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL, 0x06f067aa72176fbaULL,
+    0x0a637dc5a2c898a6ULL, 0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
+    0x28db77f523047d84ULL, 0x32caab7b40c72493ULL, 0x3c9ebe0a15c9bebcULL,
+    0x431d67c49c100d4cULL, 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
+    0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
+};
+#endif
+
+#define Ch(x,y,z)   (((x) & (y)) ^ ((~(x)) & (z)))
+#define Maj(x,y,z)  (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
+#define R(x,y)      ((y) >> (x))
+
+#if defined(SHA256_NEEDED)
+void sha256_init(sha256_context *ctx)
+{
+    memcpy(&ctx->sha_H[0], &sha256_hashInit[0], sizeof(ctx->sha_H));
+    ctx->sha_blocks = 0;
+    ctx->sha_bufCnt = 0;
+}
+
+#define S(x,y)      (((y) >> (x)) | ((y) << (32 - (x))))
+#define uSig0(x)    ((S(2,(x))) ^ (S(13,(x))) ^ (S(22,(x))))
+#define uSig1(x)    ((S(6,(x))) ^ (S(11,(x))) ^ (S(25,(x))))
+#define lSig0(x)    ((S(7,(x))) ^ (S(18,(x))) ^ (R(3,(x))))
+#define lSig1(x)    ((S(17,(x))) ^ (S(19,(x))) ^ (R(10,(x))))
+
+static void sha256_transform(sha256_context *ctx, const unsigned char *datap)
+{
+    register int    j;
+    u_int32_t       a, b, c, d, e, f, g, h;
+    u_int32_t       T1, T2, W[64], Wm2, Wm15;
+
+    /* read the data, big endian byte order */
+    j = 0;
+    do {
+        W[j] = (((u_int32_t)(datap[0]))<<24) | (((u_int32_t)(datap[1]))<<16) |
+               (((u_int32_t)(datap[2]))<<8 ) | ((u_int32_t)(datap[3]));
+        datap += 4;
+    } while(++j < 16);
+    
+    /* initialize variables a...h */
+    a = ctx->sha_H[0];
+    b = ctx->sha_H[1];
+    c = ctx->sha_H[2];
+    d = ctx->sha_H[3];
+    e = ctx->sha_H[4];
+    f = ctx->sha_H[5];
+    g = ctx->sha_H[6];
+    h = ctx->sha_H[7];
+
+    /* apply compression function */
+    j = 0;
+    do {
+        if(j >= 16) {
+            Wm2 = W[j - 2];
+            Wm15 = W[j - 15];
+            W[j] = lSig1(Wm2) + W[j - 7] + lSig0(Wm15) + W[j - 16];
+        }
+        T1 = h + uSig1(e) + Ch(e,f,g) + sha256_K[j] + W[j];
+        T2 = uSig0(a) + Maj(a,b,c);
+        h = g; g = f; f = e;
+        e = d + T1;
+        d = c; c = b; b = a;
+        a = T1 + T2;
+    } while(++j < 64);
+
+    /* compute intermediate hash value */
+    ctx->sha_H[0] += a;
+    ctx->sha_H[1] += b;
+    ctx->sha_H[2] += c;
+    ctx->sha_H[3] += d;
+    ctx->sha_H[4] += e;
+    ctx->sha_H[5] += f;
+    ctx->sha_H[6] += g;
+    ctx->sha_H[7] += h;
+
+    ctx->sha_blocks++;
+}
+
+void sha256_write(sha256_context *ctx, const unsigned char *datap, int length)
+{
+    while(length > 0) {
+        if(!ctx->sha_bufCnt) {
+            while(length >= sizeof(ctx->sha_out)) {
+                sha256_transform(ctx, datap);
+                datap += sizeof(ctx->sha_out);
+                length -= sizeof(ctx->sha_out);
+            }
+            if(!length) return;
+        }
+        ctx->sha_out[ctx->sha_bufCnt] = *datap++;
+        length--;
+        if(++ctx->sha_bufCnt == sizeof(ctx->sha_out)) {
+            sha256_transform(ctx, &ctx->sha_out[0]);
+            ctx->sha_bufCnt = 0;
+        }
+    }
+}
+
+void sha256_final(sha256_context *ctx)
+{
+    register int    j;
+    u_int64_t       bitLength;
+    u_int32_t       i;
+    unsigned char   padByte, *datap;
+
+    bitLength = (ctx->sha_blocks << 9) | (ctx->sha_bufCnt << 3);
+    padByte = 0x80;
+    sha256_write(ctx, &padByte, 1);
+
+    /* pad extra space with zeroes */
+    padByte = 0;
+    while(ctx->sha_bufCnt != 56) {
+        sha256_write(ctx, &padByte, 1);
+    }
+
+    /* write bit length, big endian byte order */
+    ctx->sha_out[56] = bitLength >> 56;
+    ctx->sha_out[57] = bitLength >> 48;
+    ctx->sha_out[58] = bitLength >> 40;
+    ctx->sha_out[59] = bitLength >> 32;
+    ctx->sha_out[60] = bitLength >> 24;
+    ctx->sha_out[61] = bitLength >> 16;
+    ctx->sha_out[62] = bitLength >> 8;
+    ctx->sha_out[63] = bitLength;
+    sha256_transform(ctx, &ctx->sha_out[0]);
+    
+    /* return results in ctx->sha_out[0...31] */
+    datap = &ctx->sha_out[0];
+    j = 0;
+    do {
+        i = ctx->sha_H[j];
+        datap[0] = i >> 24;
+        datap[1] = i >> 16;
+        datap[2] = i >> 8;
+        datap[3] = i;
+        datap += 4;
+    } while(++j < 8);
+
+    /* clear sensitive information */
+    memset(&ctx->sha_out[32], 0, sizeof(sha256_context) - 32);
+}
+
+void sha256_hash_buffer(unsigned char *ib, int ile, unsigned char *ob, int ole)
+{
+    sha256_context ctx;
+
+    if(ole < 1) return;
+    memset(ob, 0, ole);
+    if(ole > 32) ole = 32;
+    sha256_init(&ctx);
+    sha256_write(&ctx, ib, ile);
+    sha256_final(&ctx);
+    memcpy(ob, &ctx.sha_out[0], ole);
+    memset(&ctx, 0, sizeof(ctx));
+}
+
+#endif
+
+#if defined(SHA512_NEEDED)
+void sha512_init(sha512_context *ctx)
+{
+    memcpy(&ctx->sha_H[0], &sha512_hashInit[0], sizeof(ctx->sha_H));
+    ctx->sha_blocks = 0;
+    ctx->sha_blocksMSB = 0;
+    ctx->sha_bufCnt = 0;
+}
+#endif
+
+#if defined(SHA512_NEEDED) || defined(SHA384_NEEDED)
+#undef S
+#undef uSig0
+#undef uSig1
+#undef lSig0
+#undef lSig1
+#define S(x,y)      (((y) >> (x)) | ((y) << (64 - (x))))
+#define uSig0(x)    ((S(28,(x))) ^ (S(34,(x))) ^ (S(39,(x))))
+#define uSig1(x)    ((S(14,(x))) ^ (S(18,(x))) ^ (S(41,(x))))
+#define lSig0(x)    ((S(1,(x))) ^ (S(8,(x))) ^ (R(7,(x))))
+#define lSig1(x)    ((S(19,(x))) ^ (S(61,(x))) ^ (R(6,(x))))
+
+static void sha512_transform(sha512_context *ctx, const unsigned char *datap)
+{
+    register int    j;
+    u_int64_t       a, b, c, d, e, f, g, h;
+    u_int64_t       T1, T2, W[80], Wm2, Wm15;
+
+    /* read the data, big endian byte order */
+    j = 0;
+    do {
+        W[j] = (((u_int64_t)(datap[0]))<<56) | (((u_int64_t)(datap[1]))<<48) |
+               (((u_int64_t)(datap[2]))<<40) | (((u_int64_t)(datap[3]))<<32) |
+               (((u_int64_t)(datap[4]))<<24) | (((u_int64_t)(datap[5]))<<16) |
+               (((u_int64_t)(datap[6]))<<8 ) | ((u_int64_t)(datap[7]));
+        datap += 8;
+    } while(++j < 16);
+    
+    /* initialize variables a...h */
+    a = ctx->sha_H[0];
+    b = ctx->sha_H[1];
+    c = ctx->sha_H[2];
+    d = ctx->sha_H[3];
+    e = ctx->sha_H[4];
+    f = ctx->sha_H[5];
+    g = ctx->sha_H[6];
+    h = ctx->sha_H[7];
+
+    /* apply compression function */
+    j = 0;
+    do {
+        if(j >= 16) {
+            Wm2 = W[j - 2];
+            Wm15 = W[j - 15];
+            W[j] = lSig1(Wm2) + W[j - 7] + lSig0(Wm15) + W[j - 16];
+        }
+        T1 = h + uSig1(e) + Ch(e,f,g) + sha512_K[j] + W[j];
+        T2 = uSig0(a) + Maj(a,b,c);
+        h = g; g = f; f = e;
+        e = d + T1;
+        d = c; c = b; b = a;
+        a = T1 + T2;
+    } while(++j < 80);
+
+    /* compute intermediate hash value */
+    ctx->sha_H[0] += a;
+    ctx->sha_H[1] += b;
+    ctx->sha_H[2] += c;
+    ctx->sha_H[3] += d;
+    ctx->sha_H[4] += e;
+    ctx->sha_H[5] += f;
+    ctx->sha_H[6] += g;
+    ctx->sha_H[7] += h;
+
+    ctx->sha_blocks++;
+    if(!ctx->sha_blocks) ctx->sha_blocksMSB++;
+}
+
+void sha512_write(sha512_context *ctx, const unsigned char *datap, int length)
+{
+    while(length > 0) {
+        if(!ctx->sha_bufCnt) {
+            while(length >= sizeof(ctx->sha_out)) {
+                sha512_transform(ctx, datap);
+                datap += sizeof(ctx->sha_out);
+                length -= sizeof(ctx->sha_out);
+            }
+            if(!length) return;
+        }
+        ctx->sha_out[ctx->sha_bufCnt] = *datap++;
+        length--;
+        if(++ctx->sha_bufCnt == sizeof(ctx->sha_out)) {
+            sha512_transform(ctx, &ctx->sha_out[0]);
+            ctx->sha_bufCnt = 0;
+        }
+    }
+}
+
+void sha512_final(sha512_context *ctx)
+{
+    register int    j;
+    u_int64_t       bitLength, bitLengthMSB;
+    u_int64_t       i;
+    unsigned char   padByte, *datap;
+
+    bitLength = (ctx->sha_blocks << 10) | (ctx->sha_bufCnt << 3);
+    bitLengthMSB = (ctx->sha_blocksMSB << 10) | (ctx->sha_blocks >> 54);
+    padByte = 0x80;
+    sha512_write(ctx, &padByte, 1);
+
+    /* pad extra space with zeroes */
+    padByte = 0;
+    while(ctx->sha_bufCnt != 112) {
+        sha512_write(ctx, &padByte, 1);
+    }
+
+    /* write bit length, big endian byte order */
+    ctx->sha_out[112] = bitLengthMSB >> 56;
+    ctx->sha_out[113] = bitLengthMSB >> 48;
+    ctx->sha_out[114] = bitLengthMSB >> 40;
+    ctx->sha_out[115] = bitLengthMSB >> 32;
+    ctx->sha_out[116] = bitLengthMSB >> 24;
+    ctx->sha_out[117] = bitLengthMSB >> 16;
+    ctx->sha_out[118] = bitLengthMSB >> 8;
+    ctx->sha_out[119] = bitLengthMSB;
+    ctx->sha_out[120] = bitLength >> 56;
+    ctx->sha_out[121] = bitLength >> 48;
+    ctx->sha_out[122] = bitLength >> 40;
+    ctx->sha_out[123] = bitLength >> 32;
+    ctx->sha_out[124] = bitLength >> 24;
+    ctx->sha_out[125] = bitLength >> 16;
+    ctx->sha_out[126] = bitLength >> 8;
+    ctx->sha_out[127] = bitLength;
+    sha512_transform(ctx, &ctx->sha_out[0]);
+    
+    /* return results in ctx->sha_out[0...63] */
+    datap = &ctx->sha_out[0];
+    j = 0;
+    do {
+        i = ctx->sha_H[j];
+        datap[0] = i >> 56;
+        datap[1] = i >> 48;
+        datap[2] = i >> 40;
+        datap[3] = i >> 32;
+        datap[4] = i >> 24;
+        datap[5] = i >> 16;
+        datap[6] = i >> 8;
+        datap[7] = i;
+        datap += 8;
+    } while(++j < 8);
+
+    /* clear sensitive information */
+    memset(&ctx->sha_out[64], 0, sizeof(sha512_context) - 64);
+}
+
+void sha512_hash_buffer(unsigned char *ib, int ile, unsigned char *ob, int ole)
+{
+    sha512_context ctx;
+
+    if(ole < 1) return;
+    memset(ob, 0, ole);
+    if(ole > 64) ole = 64;
+    sha512_init(&ctx);
+    sha512_write(&ctx, ib, ile);
+    sha512_final(&ctx);
+    memcpy(ob, &ctx.sha_out[0], ole);
+    memset(&ctx, 0, sizeof(ctx));
+}
+#endif
+
+#if defined(SHA384_NEEDED)
+void sha384_init(sha512_context *ctx)
+{
+    memcpy(&ctx->sha_H[0], &sha384_hashInit[0], sizeof(ctx->sha_H));
+    ctx->sha_blocks = 0;
+    ctx->sha_blocksMSB = 0;
+    ctx->sha_bufCnt = 0;
+}
+
+void sha384_hash_buffer(unsigned char *ib, int ile, unsigned char *ob, int ole)
+{
+    sha512_context ctx;
+
+    if(ole < 1) return;
+    memset(ob, 0, ole);
+    if(ole > 48) ole = 48;
+    sha384_init(&ctx);
+    sha512_write(&ctx, ib, ile);
+    sha512_final(&ctx);
+    memcpy(ob, &ctx.sha_out[0], ole);
+    memset(&ctx, 0, sizeof(ctx));
+}
+#endif
diff --git a/lib/libcrypto/libsha2/sha2.h b/lib/libcrypto/libsha2/sha2.h
new file mode 100644
index 000000000..2dc03cfa8
--- /dev/null
+++ b/lib/libcrypto/libsha2/sha2.h
@@ -0,0 +1,52 @@
+#ifndef _SHA2_H
+#define _SHA2_H
+/*
+ *  sha512.h
+ *
+ *  Written by Jari Ruusu, April 16 2001
+ *
+ *  Copyright 2001 by Jari Ruusu.
+ *  Redistribution of this file is permitted under the GNU Public License.
+ */
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
+
+typedef struct {
+    unsigned char   sha_out[64];    /* results are here, bytes 0...31 */
+    u_int32_t       sha_H[8];
+    u_int64_t       sha_blocks;
+    int             sha_bufCnt;
+} sha256_context;
+
+typedef struct {
+    unsigned char   sha_out[128];   /* results are here, bytes 0...63 */
+    u_int64_t       sha_H[8];
+    u_int64_t       sha_blocks;
+    u_int64_t       sha_blocksMSB;
+    int             sha_bufCnt;
+} sha512_context;
+
+/* no sha384_context, use sha512_context */
+
+/* 256 bit hash, provides 128 bits of security against collision attacks */
+extern void sha256_init(sha256_context *);
+extern void sha256_write(sha256_context *, const unsigned char *, int);
+extern void sha256_final(sha256_context *);
+extern void sha256_hash_buffer(unsigned char *, int, unsigned char *, int);
+
+/* 512 bit hash, provides 256 bits of security against collision attacks */
+extern void sha512_init(sha512_context *);
+extern void sha512_write(sha512_context *, const unsigned char *, int);
+extern void sha512_final(sha512_context *);
+extern void sha512_hash_buffer(unsigned char *, int, unsigned char *, int);
+
+/* 384 bit hash, provides 192 bits of security against collision attacks */
+extern void sha384_init(sha512_context *);
+/* no sha384_write(), use sha512_write() */
+/* no sha384_final(), use sha512_final(), result in ctx->sha_out[0...47]  */
+extern void sha384_hash_buffer(unsigned char *, int, unsigned char *, int);
+#endif /* _SHA2_H */
diff --git a/lib/libcrypto/libtwofish/Makefile b/lib/libcrypto/libtwofish/Makefile
new file mode 100644
index 000000000..714fd6115
--- /dev/null
+++ b/lib/libcrypto/libtwofish/Makefile
@@ -0,0 +1,21 @@
+CFLAGS=-O3 -fomit-frame-pointer -D__KERNEL__  -Wall $(EXTRA_CFLAGS)
+INC=-I../include 
+
+LIBOBJ=twofish.o twofish_cbc.o
+BLIB=libtwofish.a
+
+.c.o:
+	$(CC) $(CPPFLAGS) $(CFLAGS) $(INC) -c $< -o $@
+
+$(BLIB): $(LIBOBJ)
+	/bin/rm -f $(BLIB)
+	ar cr $(BLIB) $(LIBOBJ)
+	-if test -s /bin/ranlib; then /bin/ranlib $(BLIB); \
+	else if test -s /usr/bin/ranlib; then /usr/bin/ranlib $(BLIB); \
+	else exit 0; fi; fi
+
+test: test_main.o $(BLIB)
+	$(CC) -o $@ $^ 
+
+clean:
+	rm -f *.[oa] core $(TARGET) test
diff --git a/lib/libcrypto/libtwofish/test_main.c b/lib/libcrypto/libtwofish/test_main.c
new file mode 100644
index 000000000..1e8b0db56
--- /dev/null
+++ b/lib/libcrypto/libtwofish/test_main.c
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <string.h>
+#include "twofish_cbc.h"
+#define BLOCK_SIZE	16
+#define KEY_SIZE 	128	/* bits */
+#define KEY 		"1234567890123456"
+#define STR 		"hola guaso como estaisss ... 012"
+#define STRSZ		(sizeof(STR)-1)
+
+#define BLKLEN 		BLOCK_SIZE
+#define CONTEXT_T  	twofish_context
+static int pretty_print(const unsigned char *buf, int count) {
+	int i=0;
+	for (;i<count;i++) printf ("%02hhx ", buf[i]);
+	putchar('\n');
+	return i;
+}
+//#define SIZE STRSZ/2
+#define SIZE STRSZ
+int main() {
+	int ret;
+	char buf0[SIZE+1], buf1[SIZE+1];
+	char IV[BLOCK_SIZE];
+	CONTEXT_T ac;	
+	twofish_set_key(&ac, (void *)KEY, KEY_SIZE);
+	memset(buf0, 0, sizeof (buf0));
+	memset(buf1, 0, sizeof (buf1));
+	twofish_cbc_encrypt(&ac, STR, buf0, SIZE, IV, 1);
+	pretty_print(buf0, SIZE);
+	printf("size=%d ret=%d\n%s\n", SIZE, ret, buf0);
+	ret=twofish_cbc_encrypt(&ac, buf0, buf1, SIZE, IV, 0);
+	printf("size=%d ret=%d\n%s\n", SIZE, ret, buf1);
+	return 0;
+}
diff --git a/lib/libcrypto/libtwofish/twofish.c b/lib/libcrypto/libtwofish/twofish.c
new file mode 100644
index 000000000..0e01a92d2
--- /dev/null
+++ b/lib/libcrypto/libtwofish/twofish.c
@@ -0,0 +1,861 @@
+/* NOTE: This implementation has been changed from the original
+ * source. See ChangeLog for more information.
+ * Maintained by Marc Mutz <Marc@Mutz.com>
+ */
+
+/* Twofish for GPG
+ * By Matthew Skala <mskala@ansuz.sooke.bc.ca>, July 26, 1998
+ * 256-bit key length added March 20, 1999
+ * Some modifications to reduce the text size by Werner Koch, April, 1998
+ *
+ * The original author has disclaimed all copyright interest in this
+ * code and thus putting it in the public domain.
+ *
+ * This code is a "clean room" implementation, written from the paper
+ * _Twofish: A 128-Bit Block Cipher_ by Bruce Schneier, John Kelsey,
+ * Doug Whiting, David Wagner, Chris Hall, and Niels Ferguson, available
+ * through http://www.counterpane.com/twofish.html
+ *
+ * For background information on multiplication in finite fields, used for
+ * the matrix operations in the key schedule, see the book _Contemporary
+ * Abstract Algebra_ by Joseph A. Gallian, especially chapter 22 in the
+ * Third Edition.
+ *
+ * Only the 128- and 256-bit key sizes are supported.  This code is intended
+ * for GNU C on a 32-bit system, but it should work almost anywhere.  Loops
+ * are unrolled, precomputation tables are used, etc., for maximum speed at
+ * some cost in memory consumption. */
+
+#ifdef __KERNEL__
+#include <linux/init.h>
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#define u8 u_int8_t
+#define u32 u_int32_t
+#endif
+
+#if 0 /* shouldn't this be #ifdef rotl32 ?
+       * Look at wordops.h: It includes asm/wordops.h.
+       * Anyway, we have to search in the macros for rot's,
+       * since they seem to be defined in a generic way. */
+#define rotl rotl32
+#define rotr rotr32
+#else
+#define rotl generic_rotl32
+#define rotr generic_rotr32
+#endif
+
+#include "twofish.h"
+/* The large precomputed tables for the Twofish cipher (twofish.c)
+ * Taken from the same source as twofish.c
+ * Marc Mutz <Marc@Mutz.com>
+ */
+
+/* These two tables are the q0 and q1 permutations, exactly as described in
+ * the Twofish paper. */
+
+static const u8 q0[256] = {
+   0xA9, 0x67, 0xB3, 0xE8, 0x04, 0xFD, 0xA3, 0x76, 0x9A, 0x92, 0x80, 0x78,
+   0xE4, 0xDD, 0xD1, 0x38, 0x0D, 0xC6, 0x35, 0x98, 0x18, 0xF7, 0xEC, 0x6C,
+   0x43, 0x75, 0x37, 0x26, 0xFA, 0x13, 0x94, 0x48, 0xF2, 0xD0, 0x8B, 0x30,
+   0x84, 0x54, 0xDF, 0x23, 0x19, 0x5B, 0x3D, 0x59, 0xF3, 0xAE, 0xA2, 0x82,
+   0x63, 0x01, 0x83, 0x2E, 0xD9, 0x51, 0x9B, 0x7C, 0xA6, 0xEB, 0xA5, 0xBE,
+   0x16, 0x0C, 0xE3, 0x61, 0xC0, 0x8C, 0x3A, 0xF5, 0x73, 0x2C, 0x25, 0x0B,
+   0xBB, 0x4E, 0x89, 0x6B, 0x53, 0x6A, 0xB4, 0xF1, 0xE1, 0xE6, 0xBD, 0x45,
+   0xE2, 0xF4, 0xB6, 0x66, 0xCC, 0x95, 0x03, 0x56, 0xD4, 0x1C, 0x1E, 0xD7,
+   0xFB, 0xC3, 0x8E, 0xB5, 0xE9, 0xCF, 0xBF, 0xBA, 0xEA, 0x77, 0x39, 0xAF,
+   0x33, 0xC9, 0x62, 0x71, 0x81, 0x79, 0x09, 0xAD, 0x24, 0xCD, 0xF9, 0xD8,
+   0xE5, 0xC5, 0xB9, 0x4D, 0x44, 0x08, 0x86, 0xE7, 0xA1, 0x1D, 0xAA, 0xED,
+   0x06, 0x70, 0xB2, 0xD2, 0x41, 0x7B, 0xA0, 0x11, 0x31, 0xC2, 0x27, 0x90,
+   0x20, 0xF6, 0x60, 0xFF, 0x96, 0x5C, 0xB1, 0xAB, 0x9E, 0x9C, 0x52, 0x1B,
+   0x5F, 0x93, 0x0A, 0xEF, 0x91, 0x85, 0x49, 0xEE, 0x2D, 0x4F, 0x8F, 0x3B,
+   0x47, 0x87, 0x6D, 0x46, 0xD6, 0x3E, 0x69, 0x64, 0x2A, 0xCE, 0xCB, 0x2F,
+   0xFC, 0x97, 0x05, 0x7A, 0xAC, 0x7F, 0xD5, 0x1A, 0x4B, 0x0E, 0xA7, 0x5A,
+   0x28, 0x14, 0x3F, 0x29, 0x88, 0x3C, 0x4C, 0x02, 0xB8, 0xDA, 0xB0, 0x17,
+   0x55, 0x1F, 0x8A, 0x7D, 0x57, 0xC7, 0x8D, 0x74, 0xB7, 0xC4, 0x9F, 0x72,
+   0x7E, 0x15, 0x22, 0x12, 0x58, 0x07, 0x99, 0x34, 0x6E, 0x50, 0xDE, 0x68,
+   0x65, 0xBC, 0xDB, 0xF8, 0xC8, 0xA8, 0x2B, 0x40, 0xDC, 0xFE, 0x32, 0xA4,
+   0xCA, 0x10, 0x21, 0xF0, 0xD3, 0x5D, 0x0F, 0x00, 0x6F, 0x9D, 0x36, 0x42,
+   0x4A, 0x5E, 0xC1, 0xE0
+};
+
+static const u8 q1[256] = {
+   0x75, 0xF3, 0xC6, 0xF4, 0xDB, 0x7B, 0xFB, 0xC8, 0x4A, 0xD3, 0xE6, 0x6B,
+   0x45, 0x7D, 0xE8, 0x4B, 0xD6, 0x32, 0xD8, 0xFD, 0x37, 0x71, 0xF1, 0xE1,
+   0x30, 0x0F, 0xF8, 0x1B, 0x87, 0xFA, 0x06, 0x3F, 0x5E, 0xBA, 0xAE, 0x5B,
+   0x8A, 0x00, 0xBC, 0x9D, 0x6D, 0xC1, 0xB1, 0x0E, 0x80, 0x5D, 0xD2, 0xD5,
+   0xA0, 0x84, 0x07, 0x14, 0xB5, 0x90, 0x2C, 0xA3, 0xB2, 0x73, 0x4C, 0x54,
+   0x92, 0x74, 0x36, 0x51, 0x38, 0xB0, 0xBD, 0x5A, 0xFC, 0x60, 0x62, 0x96,
+   0x6C, 0x42, 0xF7, 0x10, 0x7C, 0x28, 0x27, 0x8C, 0x13, 0x95, 0x9C, 0xC7,
+   0x24, 0x46, 0x3B, 0x70, 0xCA, 0xE3, 0x85, 0xCB, 0x11, 0xD0, 0x93, 0xB8,
+   0xA6, 0x83, 0x20, 0xFF, 0x9F, 0x77, 0xC3, 0xCC, 0x03, 0x6F, 0x08, 0xBF,
+   0x40, 0xE7, 0x2B, 0xE2, 0x79, 0x0C, 0xAA, 0x82, 0x41, 0x3A, 0xEA, 0xB9,
+   0xE4, 0x9A, 0xA4, 0x97, 0x7E, 0xDA, 0x7A, 0x17, 0x66, 0x94, 0xA1, 0x1D,
+   0x3D, 0xF0, 0xDE, 0xB3, 0x0B, 0x72, 0xA7, 0x1C, 0xEF, 0xD1, 0x53, 0x3E,
+   0x8F, 0x33, 0x26, 0x5F, 0xEC, 0x76, 0x2A, 0x49, 0x81, 0x88, 0xEE, 0x21,
+   0xC4, 0x1A, 0xEB, 0xD9, 0xC5, 0x39, 0x99, 0xCD, 0xAD, 0x31, 0x8B, 0x01,
+   0x18, 0x23, 0xDD, 0x1F, 0x4E, 0x2D, 0xF9, 0x48, 0x4F, 0xF2, 0x65, 0x8E,
+   0x78, 0x5C, 0x58, 0x19, 0x8D, 0xE5, 0x98, 0x57, 0x67, 0x7F, 0x05, 0x64,
+   0xAF, 0x63, 0xB6, 0xFE, 0xF5, 0xB7, 0x3C, 0xA5, 0xCE, 0xE9, 0x68, 0x44,
+   0xE0, 0x4D, 0x43, 0x69, 0x29, 0x2E, 0xAC, 0x15, 0x59, 0xA8, 0x0A, 0x9E,
+   0x6E, 0x47, 0xDF, 0x34, 0x35, 0x6A, 0xCF, 0xDC, 0x22, 0xC9, 0xC0, 0x9B,
+   0x89, 0xD4, 0xED, 0xAB, 0x12, 0xA2, 0x0D, 0x52, 0xBB, 0x02, 0x2F, 0xA9,
+   0xD7, 0x61, 0x1E, 0xB4, 0x50, 0x04, 0xF6, 0xC2, 0x16, 0x25, 0x86, 0x56,
+   0x55, 0x09, 0xBE, 0x91
+};
+
+/* These MDS tables are actually tables of MDS composed with q0 and q1,
+ * because it is only ever used that way and we can save some time by
+ * precomputing.  Of course the main saving comes from precomputing the
+ * GF(2^8) multiplication involved in the MDS matrix multiply; by looking
+ * things up in these tables we reduce the matrix multiply to four lookups
+ * and three XORs.  Semi-formally, the definition of these tables is:
+ * mds[0][i] = MDS (q1[i] 0 0 0)^T  mds[1][i] = MDS (0 q0[i] 0 0)^T
+ * mds[2][i] = MDS (0 0 q1[i] 0)^T  mds[3][i] = MDS (0 0 0 q0[i])^T
+ * where ^T means "transpose", the matrix multiply is performed in GF(2^8)
+ * represented as GF(2)[x]/v(x) where v(x)=x^8+x^6+x^5+x^3+1 as described
+ * by Schneier et al, and I'm casually glossing over the byte/word
+ * conversion issues. */
+
+static const u32 mds[4][256] = {
+   {0xBCBC3275, 0xECEC21F3, 0x202043C6, 0xB3B3C9F4, 0xDADA03DB, 0x02028B7B,
+    0xE2E22BFB, 0x9E9EFAC8, 0xC9C9EC4A, 0xD4D409D3, 0x18186BE6, 0x1E1E9F6B,
+    0x98980E45, 0xB2B2387D, 0xA6A6D2E8, 0x2626B74B, 0x3C3C57D6, 0x93938A32,
+    0x8282EED8, 0x525298FD, 0x7B7BD437, 0xBBBB3771, 0x5B5B97F1, 0x474783E1,
+    0x24243C30, 0x5151E20F, 0xBABAC6F8, 0x4A4AF31B, 0xBFBF4887, 0x0D0D70FA,
+    0xB0B0B306, 0x7575DE3F, 0xD2D2FD5E, 0x7D7D20BA, 0x666631AE, 0x3A3AA35B,
+    0x59591C8A, 0x00000000, 0xCDCD93BC, 0x1A1AE09D, 0xAEAE2C6D, 0x7F7FABC1,
+    0x2B2BC7B1, 0xBEBEB90E, 0xE0E0A080, 0x8A8A105D, 0x3B3B52D2, 0x6464BAD5,
+    0xD8D888A0, 0xE7E7A584, 0x5F5FE807, 0x1B1B1114, 0x2C2CC2B5, 0xFCFCB490,
+    0x3131272C, 0x808065A3, 0x73732AB2, 0x0C0C8173, 0x79795F4C, 0x6B6B4154,
+    0x4B4B0292, 0x53536974, 0x94948F36, 0x83831F51, 0x2A2A3638, 0xC4C49CB0,
+    0x2222C8BD, 0xD5D5F85A, 0xBDBDC3FC, 0x48487860, 0xFFFFCE62, 0x4C4C0796,
+    0x4141776C, 0xC7C7E642, 0xEBEB24F7, 0x1C1C1410, 0x5D5D637C, 0x36362228,
+    0x6767C027, 0xE9E9AF8C, 0x4444F913, 0x1414EA95, 0xF5F5BB9C, 0xCFCF18C7,
+    0x3F3F2D24, 0xC0C0E346, 0x7272DB3B, 0x54546C70, 0x29294CCA, 0xF0F035E3,
+    0x0808FE85, 0xC6C617CB, 0xF3F34F11, 0x8C8CE4D0, 0xA4A45993, 0xCACA96B8,
+    0x68683BA6, 0xB8B84D83, 0x38382820, 0xE5E52EFF, 0xADAD569F, 0x0B0B8477,
+    0xC8C81DC3, 0x9999FFCC, 0x5858ED03, 0x19199A6F, 0x0E0E0A08, 0x95957EBF,
+    0x70705040, 0xF7F730E7, 0x6E6ECF2B, 0x1F1F6EE2, 0xB5B53D79, 0x09090F0C,
+    0x616134AA, 0x57571682, 0x9F9F0B41, 0x9D9D803A, 0x111164EA, 0x2525CDB9,
+    0xAFAFDDE4, 0x4545089A, 0xDFDF8DA4, 0xA3A35C97, 0xEAEAD57E, 0x353558DA,
+    0xEDEDD07A, 0x4343FC17, 0xF8F8CB66, 0xFBFBB194, 0x3737D3A1, 0xFAFA401D,
+    0xC2C2683D, 0xB4B4CCF0, 0x32325DDE, 0x9C9C71B3, 0x5656E70B, 0xE3E3DA72,
+    0x878760A7, 0x15151B1C, 0xF9F93AEF, 0x6363BFD1, 0x3434A953, 0x9A9A853E,
+    0xB1B1428F, 0x7C7CD133, 0x88889B26, 0x3D3DA65F, 0xA1A1D7EC, 0xE4E4DF76,
+    0x8181942A, 0x91910149, 0x0F0FFB81, 0xEEEEAA88, 0x161661EE, 0xD7D77321,
+    0x9797F5C4, 0xA5A5A81A, 0xFEFE3FEB, 0x6D6DB5D9, 0x7878AEC5, 0xC5C56D39,
+    0x1D1DE599, 0x7676A4CD, 0x3E3EDCAD, 0xCBCB6731, 0xB6B6478B, 0xEFEF5B01,
+    0x12121E18, 0x6060C523, 0x6A6AB0DD, 0x4D4DF61F, 0xCECEE94E, 0xDEDE7C2D,
+    0x55559DF9, 0x7E7E5A48, 0x2121B24F, 0x03037AF2, 0xA0A02665, 0x5E5E198E,
+    0x5A5A6678, 0x65654B5C, 0x62624E58, 0xFDFD4519, 0x0606F48D, 0x404086E5,
+    0xF2F2BE98, 0x3333AC57, 0x17179067, 0x05058E7F, 0xE8E85E05, 0x4F4F7D64,
+    0x89896AAF, 0x10109563, 0x74742FB6, 0x0A0A75FE, 0x5C5C92F5, 0x9B9B74B7,
+    0x2D2D333C, 0x3030D6A5, 0x2E2E49CE, 0x494989E9, 0x46467268, 0x77775544,
+    0xA8A8D8E0, 0x9696044D, 0x2828BD43, 0xA9A92969, 0xD9D97929, 0x8686912E,
+    0xD1D187AC, 0xF4F44A15, 0x8D8D1559, 0xD6D682A8, 0xB9B9BC0A, 0x42420D9E,
+    0xF6F6C16E, 0x2F2FB847, 0xDDDD06DF, 0x23233934, 0xCCCC6235, 0xF1F1C46A,
+    0xC1C112CF, 0x8585EBDC, 0x8F8F9E22, 0x7171A1C9, 0x9090F0C0, 0xAAAA539B,
+    0x0101F189, 0x8B8BE1D4, 0x4E4E8CED, 0x8E8E6FAB, 0xABABA212, 0x6F6F3EA2,
+    0xE6E6540D, 0xDBDBF252, 0x92927BBB, 0xB7B7B602, 0x6969CA2F, 0x3939D9A9,
+    0xD3D30CD7, 0xA7A72361, 0xA2A2AD1E, 0xC3C399B4, 0x6C6C4450, 0x07070504,
+    0x04047FF6, 0x272746C2, 0xACACA716, 0xD0D07625, 0x50501386, 0xDCDCF756,
+    0x84841A55, 0xE1E15109, 0x7A7A25BE, 0x1313EF91},
+
+   {0xA9D93939, 0x67901717, 0xB3719C9C, 0xE8D2A6A6, 0x04050707, 0xFD985252,
+    0xA3658080, 0x76DFE4E4, 0x9A084545, 0x92024B4B, 0x80A0E0E0, 0x78665A5A,
+    0xE4DDAFAF, 0xDDB06A6A, 0xD1BF6363, 0x38362A2A, 0x0D54E6E6, 0xC6432020,
+    0x3562CCCC, 0x98BEF2F2, 0x181E1212, 0xF724EBEB, 0xECD7A1A1, 0x6C774141,
+    0x43BD2828, 0x7532BCBC, 0x37D47B7B, 0x269B8888, 0xFA700D0D, 0x13F94444,
+    0x94B1FBFB, 0x485A7E7E, 0xF27A0303, 0xD0E48C8C, 0x8B47B6B6, 0x303C2424,
+    0x84A5E7E7, 0x54416B6B, 0xDF06DDDD, 0x23C56060, 0x1945FDFD, 0x5BA33A3A,
+    0x3D68C2C2, 0x59158D8D, 0xF321ECEC, 0xAE316666, 0xA23E6F6F, 0x82165757,
+    0x63951010, 0x015BEFEF, 0x834DB8B8, 0x2E918686, 0xD9B56D6D, 0x511F8383,
+    0x9B53AAAA, 0x7C635D5D, 0xA63B6868, 0xEB3FFEFE, 0xA5D63030, 0xBE257A7A,
+    0x16A7ACAC, 0x0C0F0909, 0xE335F0F0, 0x6123A7A7, 0xC0F09090, 0x8CAFE9E9,
+    0x3A809D9D, 0xF5925C5C, 0x73810C0C, 0x2C273131, 0x2576D0D0, 0x0BE75656,
+    0xBB7B9292, 0x4EE9CECE, 0x89F10101, 0x6B9F1E1E, 0x53A93434, 0x6AC4F1F1,
+    0xB499C3C3, 0xF1975B5B, 0xE1834747, 0xE66B1818, 0xBDC82222, 0x450E9898,
+    0xE26E1F1F, 0xF4C9B3B3, 0xB62F7474, 0x66CBF8F8, 0xCCFF9999, 0x95EA1414,
+    0x03ED5858, 0x56F7DCDC, 0xD4E18B8B, 0x1C1B1515, 0x1EADA2A2, 0xD70CD3D3,
+    0xFB2BE2E2, 0xC31DC8C8, 0x8E195E5E, 0xB5C22C2C, 0xE9894949, 0xCF12C1C1,
+    0xBF7E9595, 0xBA207D7D, 0xEA641111, 0x77840B0B, 0x396DC5C5, 0xAF6A8989,
+    0x33D17C7C, 0xC9A17171, 0x62CEFFFF, 0x7137BBBB, 0x81FB0F0F, 0x793DB5B5,
+    0x0951E1E1, 0xADDC3E3E, 0x242D3F3F, 0xCDA47676, 0xF99D5555, 0xD8EE8282,
+    0xE5864040, 0xC5AE7878, 0xB9CD2525, 0x4D049696, 0x44557777, 0x080A0E0E,
+    0x86135050, 0xE730F7F7, 0xA1D33737, 0x1D40FAFA, 0xAA346161, 0xED8C4E4E,
+    0x06B3B0B0, 0x706C5454, 0xB22A7373, 0xD2523B3B, 0x410B9F9F, 0x7B8B0202,
+    0xA088D8D8, 0x114FF3F3, 0x3167CBCB, 0xC2462727, 0x27C06767, 0x90B4FCFC,
+    0x20283838, 0xF67F0404, 0x60784848, 0xFF2EE5E5, 0x96074C4C, 0x5C4B6565,
+    0xB1C72B2B, 0xAB6F8E8E, 0x9E0D4242, 0x9CBBF5F5, 0x52F2DBDB, 0x1BF34A4A,
+    0x5FA63D3D, 0x9359A4A4, 0x0ABCB9B9, 0xEF3AF9F9, 0x91EF1313, 0x85FE0808,
+    0x49019191, 0xEE611616, 0x2D7CDEDE, 0x4FB22121, 0x8F42B1B1, 0x3BDB7272,
+    0x47B82F2F, 0x8748BFBF, 0x6D2CAEAE, 0x46E3C0C0, 0xD6573C3C, 0x3E859A9A,
+    0x6929A9A9, 0x647D4F4F, 0x2A948181, 0xCE492E2E, 0xCB17C6C6, 0x2FCA6969,
+    0xFCC3BDBD, 0x975CA3A3, 0x055EE8E8, 0x7AD0EDED, 0xAC87D1D1, 0x7F8E0505,
+    0xD5BA6464, 0x1AA8A5A5, 0x4BB72626, 0x0EB9BEBE, 0xA7608787, 0x5AF8D5D5,
+    0x28223636, 0x14111B1B, 0x3FDE7575, 0x2979D9D9, 0x88AAEEEE, 0x3C332D2D,
+    0x4C5F7979, 0x02B6B7B7, 0xB896CACA, 0xDA583535, 0xB09CC4C4, 0x17FC4343,
+    0x551A8484, 0x1FF64D4D, 0x8A1C5959, 0x7D38B2B2, 0x57AC3333, 0xC718CFCF,
+    0x8DF40606, 0x74695353, 0xB7749B9B, 0xC4F59797, 0x9F56ADAD, 0x72DAE3E3,
+    0x7ED5EAEA, 0x154AF4F4, 0x229E8F8F, 0x12A2ABAB, 0x584E6262, 0x07E85F5F,
+    0x99E51D1D, 0x34392323, 0x6EC1F6F6, 0x50446C6C, 0xDE5D3232, 0x68724646,
+    0x6526A0A0, 0xBC93CDCD, 0xDB03DADA, 0xF8C6BABA, 0xC8FA9E9E, 0xA882D6D6,
+    0x2BCF6E6E, 0x40507070, 0xDCEB8585, 0xFE750A0A, 0x328A9393, 0xA48DDFDF,
+    0xCA4C2929, 0x10141C1C, 0x2173D7D7, 0xF0CCB4B4, 0xD309D4D4, 0x5D108A8A,
+    0x0FE25151, 0x00000000, 0x6F9A1919, 0x9DE01A1A, 0x368F9494, 0x42E6C7C7,
+    0x4AECC9C9, 0x5EFDD2D2, 0xC1AB7F7F, 0xE0D8A8A8},
+
+   {0xBC75BC32, 0xECF3EC21, 0x20C62043, 0xB3F4B3C9, 0xDADBDA03, 0x027B028B,
+    0xE2FBE22B, 0x9EC89EFA, 0xC94AC9EC, 0xD4D3D409, 0x18E6186B, 0x1E6B1E9F,
+    0x9845980E, 0xB27DB238, 0xA6E8A6D2, 0x264B26B7, 0x3CD63C57, 0x9332938A,
+    0x82D882EE, 0x52FD5298, 0x7B377BD4, 0xBB71BB37, 0x5BF15B97, 0x47E14783,
+    0x2430243C, 0x510F51E2, 0xBAF8BAC6, 0x4A1B4AF3, 0xBF87BF48, 0x0DFA0D70,
+    0xB006B0B3, 0x753F75DE, 0xD25ED2FD, 0x7DBA7D20, 0x66AE6631, 0x3A5B3AA3,
+    0x598A591C, 0x00000000, 0xCDBCCD93, 0x1A9D1AE0, 0xAE6DAE2C, 0x7FC17FAB,
+    0x2BB12BC7, 0xBE0EBEB9, 0xE080E0A0, 0x8A5D8A10, 0x3BD23B52, 0x64D564BA,
+    0xD8A0D888, 0xE784E7A5, 0x5F075FE8, 0x1B141B11, 0x2CB52CC2, 0xFC90FCB4,
+    0x312C3127, 0x80A38065, 0x73B2732A, 0x0C730C81, 0x794C795F, 0x6B546B41,
+    0x4B924B02, 0x53745369, 0x9436948F, 0x8351831F, 0x2A382A36, 0xC4B0C49C,
+    0x22BD22C8, 0xD55AD5F8, 0xBDFCBDC3, 0x48604878, 0xFF62FFCE, 0x4C964C07,
+    0x416C4177, 0xC742C7E6, 0xEBF7EB24, 0x1C101C14, 0x5D7C5D63, 0x36283622,
+    0x672767C0, 0xE98CE9AF, 0x441344F9, 0x149514EA, 0xF59CF5BB, 0xCFC7CF18,
+    0x3F243F2D, 0xC046C0E3, 0x723B72DB, 0x5470546C, 0x29CA294C, 0xF0E3F035,
+    0x088508FE, 0xC6CBC617, 0xF311F34F, 0x8CD08CE4, 0xA493A459, 0xCAB8CA96,
+    0x68A6683B, 0xB883B84D, 0x38203828, 0xE5FFE52E, 0xAD9FAD56, 0x0B770B84,
+    0xC8C3C81D, 0x99CC99FF, 0x580358ED, 0x196F199A, 0x0E080E0A, 0x95BF957E,
+    0x70407050, 0xF7E7F730, 0x6E2B6ECF, 0x1FE21F6E, 0xB579B53D, 0x090C090F,
+    0x61AA6134, 0x57825716, 0x9F419F0B, 0x9D3A9D80, 0x11EA1164, 0x25B925CD,
+    0xAFE4AFDD, 0x459A4508, 0xDFA4DF8D, 0xA397A35C, 0xEA7EEAD5, 0x35DA3558,
+    0xED7AEDD0, 0x431743FC, 0xF866F8CB, 0xFB94FBB1, 0x37A137D3, 0xFA1DFA40,
+    0xC23DC268, 0xB4F0B4CC, 0x32DE325D, 0x9CB39C71, 0x560B56E7, 0xE372E3DA,
+    0x87A78760, 0x151C151B, 0xF9EFF93A, 0x63D163BF, 0x345334A9, 0x9A3E9A85,
+    0xB18FB142, 0x7C337CD1, 0x8826889B, 0x3D5F3DA6, 0xA1ECA1D7, 0xE476E4DF,
+    0x812A8194, 0x91499101, 0x0F810FFB, 0xEE88EEAA, 0x16EE1661, 0xD721D773,
+    0x97C497F5, 0xA51AA5A8, 0xFEEBFE3F, 0x6DD96DB5, 0x78C578AE, 0xC539C56D,
+    0x1D991DE5, 0x76CD76A4, 0x3EAD3EDC, 0xCB31CB67, 0xB68BB647, 0xEF01EF5B,
+    0x1218121E, 0x602360C5, 0x6ADD6AB0, 0x4D1F4DF6, 0xCE4ECEE9, 0xDE2DDE7C,
+    0x55F9559D, 0x7E487E5A, 0x214F21B2, 0x03F2037A, 0xA065A026, 0x5E8E5E19,
+    0x5A785A66, 0x655C654B, 0x6258624E, 0xFD19FD45, 0x068D06F4, 0x40E54086,
+    0xF298F2BE, 0x335733AC, 0x17671790, 0x057F058E, 0xE805E85E, 0x4F644F7D,
+    0x89AF896A, 0x10631095, 0x74B6742F, 0x0AFE0A75, 0x5CF55C92, 0x9BB79B74,
+    0x2D3C2D33, 0x30A530D6, 0x2ECE2E49, 0x49E94989, 0x46684672, 0x77447755,
+    0xA8E0A8D8, 0x964D9604, 0x284328BD, 0xA969A929, 0xD929D979, 0x862E8691,
+    0xD1ACD187, 0xF415F44A, 0x8D598D15, 0xD6A8D682, 0xB90AB9BC, 0x429E420D,
+    0xF66EF6C1, 0x2F472FB8, 0xDDDFDD06, 0x23342339, 0xCC35CC62, 0xF16AF1C4,
+    0xC1CFC112, 0x85DC85EB, 0x8F228F9E, 0x71C971A1, 0x90C090F0, 0xAA9BAA53,
+    0x018901F1, 0x8BD48BE1, 0x4EED4E8C, 0x8EAB8E6F, 0xAB12ABA2, 0x6FA26F3E,
+    0xE60DE654, 0xDB52DBF2, 0x92BB927B, 0xB702B7B6, 0x692F69CA, 0x39A939D9,
+    0xD3D7D30C, 0xA761A723, 0xA21EA2AD, 0xC3B4C399, 0x6C506C44, 0x07040705,
+    0x04F6047F, 0x27C22746, 0xAC16ACA7, 0xD025D076, 0x50865013, 0xDC56DCF7,
+    0x8455841A, 0xE109E151, 0x7ABE7A25, 0x139113EF},
+
+   {0xD939A9D9, 0x90176790, 0x719CB371, 0xD2A6E8D2, 0x05070405, 0x9852FD98,
+    0x6580A365, 0xDFE476DF, 0x08459A08, 0x024B9202, 0xA0E080A0, 0x665A7866,
+    0xDDAFE4DD, 0xB06ADDB0, 0xBF63D1BF, 0x362A3836, 0x54E60D54, 0x4320C643,
+    0x62CC3562, 0xBEF298BE, 0x1E12181E, 0x24EBF724, 0xD7A1ECD7, 0x77416C77,
+    0xBD2843BD, 0x32BC7532, 0xD47B37D4, 0x9B88269B, 0x700DFA70, 0xF94413F9,
+    0xB1FB94B1, 0x5A7E485A, 0x7A03F27A, 0xE48CD0E4, 0x47B68B47, 0x3C24303C,
+    0xA5E784A5, 0x416B5441, 0x06DDDF06, 0xC56023C5, 0x45FD1945, 0xA33A5BA3,
+    0x68C23D68, 0x158D5915, 0x21ECF321, 0x3166AE31, 0x3E6FA23E, 0x16578216,
+    0x95106395, 0x5BEF015B, 0x4DB8834D, 0x91862E91, 0xB56DD9B5, 0x1F83511F,
+    0x53AA9B53, 0x635D7C63, 0x3B68A63B, 0x3FFEEB3F, 0xD630A5D6, 0x257ABE25,
+    0xA7AC16A7, 0x0F090C0F, 0x35F0E335, 0x23A76123, 0xF090C0F0, 0xAFE98CAF,
+    0x809D3A80, 0x925CF592, 0x810C7381, 0x27312C27, 0x76D02576, 0xE7560BE7,
+    0x7B92BB7B, 0xE9CE4EE9, 0xF10189F1, 0x9F1E6B9F, 0xA93453A9, 0xC4F16AC4,
+    0x99C3B499, 0x975BF197, 0x8347E183, 0x6B18E66B, 0xC822BDC8, 0x0E98450E,
+    0x6E1FE26E, 0xC9B3F4C9, 0x2F74B62F, 0xCBF866CB, 0xFF99CCFF, 0xEA1495EA,
+    0xED5803ED, 0xF7DC56F7, 0xE18BD4E1, 0x1B151C1B, 0xADA21EAD, 0x0CD3D70C,
+    0x2BE2FB2B, 0x1DC8C31D, 0x195E8E19, 0xC22CB5C2, 0x8949E989, 0x12C1CF12,
+    0x7E95BF7E, 0x207DBA20, 0x6411EA64, 0x840B7784, 0x6DC5396D, 0x6A89AF6A,
+    0xD17C33D1, 0xA171C9A1, 0xCEFF62CE, 0x37BB7137, 0xFB0F81FB, 0x3DB5793D,
+    0x51E10951, 0xDC3EADDC, 0x2D3F242D, 0xA476CDA4, 0x9D55F99D, 0xEE82D8EE,
+    0x8640E586, 0xAE78C5AE, 0xCD25B9CD, 0x04964D04, 0x55774455, 0x0A0E080A,
+    0x13508613, 0x30F7E730, 0xD337A1D3, 0x40FA1D40, 0x3461AA34, 0x8C4EED8C,
+    0xB3B006B3, 0x6C54706C, 0x2A73B22A, 0x523BD252, 0x0B9F410B, 0x8B027B8B,
+    0x88D8A088, 0x4FF3114F, 0x67CB3167, 0x4627C246, 0xC06727C0, 0xB4FC90B4,
+    0x28382028, 0x7F04F67F, 0x78486078, 0x2EE5FF2E, 0x074C9607, 0x4B655C4B,
+    0xC72BB1C7, 0x6F8EAB6F, 0x0D429E0D, 0xBBF59CBB, 0xF2DB52F2, 0xF34A1BF3,
+    0xA63D5FA6, 0x59A49359, 0xBCB90ABC, 0x3AF9EF3A, 0xEF1391EF, 0xFE0885FE,
+    0x01914901, 0x6116EE61, 0x7CDE2D7C, 0xB2214FB2, 0x42B18F42, 0xDB723BDB,
+    0xB82F47B8, 0x48BF8748, 0x2CAE6D2C, 0xE3C046E3, 0x573CD657, 0x859A3E85,
+    0x29A96929, 0x7D4F647D, 0x94812A94, 0x492ECE49, 0x17C6CB17, 0xCA692FCA,
+    0xC3BDFCC3, 0x5CA3975C, 0x5EE8055E, 0xD0ED7AD0, 0x87D1AC87, 0x8E057F8E,
+    0xBA64D5BA, 0xA8A51AA8, 0xB7264BB7, 0xB9BE0EB9, 0x6087A760, 0xF8D55AF8,
+    0x22362822, 0x111B1411, 0xDE753FDE, 0x79D92979, 0xAAEE88AA, 0x332D3C33,
+    0x5F794C5F, 0xB6B702B6, 0x96CAB896, 0x5835DA58, 0x9CC4B09C, 0xFC4317FC,
+    0x1A84551A, 0xF64D1FF6, 0x1C598A1C, 0x38B27D38, 0xAC3357AC, 0x18CFC718,
+    0xF4068DF4, 0x69537469, 0x749BB774, 0xF597C4F5, 0x56AD9F56, 0xDAE372DA,
+    0xD5EA7ED5, 0x4AF4154A, 0x9E8F229E, 0xA2AB12A2, 0x4E62584E, 0xE85F07E8,
+    0xE51D99E5, 0x39233439, 0xC1F66EC1, 0x446C5044, 0x5D32DE5D, 0x72466872,
+    0x26A06526, 0x93CDBC93, 0x03DADB03, 0xC6BAF8C6, 0xFA9EC8FA, 0x82D6A882,
+    0xCF6E2BCF, 0x50704050, 0xEB85DCEB, 0x750AFE75, 0x8A93328A, 0x8DDFA48D,
+    0x4C29CA4C, 0x141C1014, 0x73D72173, 0xCCB4F0CC, 0x09D4D309, 0x108A5D10,
+    0xE2510FE2, 0x00000000, 0x9A196F9A, 0xE01A9DE0, 0x8F94368F, 0xE6C742E6,
+    0xECC94AEC, 0xFDD25EFD, 0xAB7FC1AB, 0xD8A8E0D8}
+};
+
+/* The exp_to_poly and poly_to_exp tables are used to perform efficient
+ * operations in GF(2^8) represented as GF(2)[x]/w(x) where
+ * w(x)=x^8+x^6+x^3+x^2+1.  We care about doing that because it's part of the
+ * definition of the RS matrix in the key schedule.  Elements of that field
+ * are polynomials of degree not greater than 7 and all coefficients 0 or 1,
+ * which can be represented naturally by bytes (just substitute x=2).  In that
+ * form, GF(2^8) addition is the same as bitwise XOR, but GF(2^8)
+ * multiplication is inefficient without hardware support.  To multiply
+ * faster, I make use of the fact x is a generator for the nonzero elements,
+ * so that every element p of GF(2)[x]/w(x) is either 0 or equal to (x)^n for
+ * some n in 0..254.  Note that that caret is exponentiation in GF(2^8),
+ * *not* polynomial notation.  So if I want to compute pq where p and q are
+ * in GF(2^8), I can just say:
+ *    1. if p=0 or q=0 then pq=0
+ *    2. otherwise, find m and n such that p=x^m and q=x^n
+ *    3. pq=(x^m)(x^n)=x^(m+n), so add m and n and find pq
+ * The translations in steps 2 and 3 are looked up in the tables
+ * poly_to_exp (for step 2) and exp_to_poly (for step 3).  To see this
+ * in action, look at the CALC_S macro.  As additional wrinkles, note that
+ * one of my operands is always a constant, so the poly_to_exp lookup on it
+ * is done in advance; I included the original values in the comments so
+ * readers can have some chance of recognizing that this *is* the RS matrix
+ * from the Twofish paper.  I've only included the table entries I actually
+ * need; I never do a lookup on a variable input of zero and the biggest
+ * exponents I'll ever see are 254 (variable) and 237 (constant), so they'll
+ * never sum to more than 491.	I'm repeating part of the exp_to_poly table
+ * so that I don't have to do mod-255 reduction in the exponent arithmetic.
+ * Since I know my constant operands are never zero, I only have to worry
+ * about zero values in the variable operand, and I do it with a simple
+ * conditional branch.	I know conditionals are expensive, but I couldn't
+ * see a non-horrible way of avoiding them, and I did manage to group the
+ * statements so that each if covers four group multiplications. */
+
+static const u8 poly_to_exp[255] = {
+   0x00, 0x01, 0x17, 0x02, 0x2E, 0x18, 0x53, 0x03, 0x6A, 0x2F, 0x93, 0x19,
+   0x34, 0x54, 0x45, 0x04, 0x5C, 0x6B, 0xB6, 0x30, 0xA6, 0x94, 0x4B, 0x1A,
+   0x8C, 0x35, 0x81, 0x55, 0xAA, 0x46, 0x0D, 0x05, 0x24, 0x5D, 0x87, 0x6C,
+   0x9B, 0xB7, 0xC1, 0x31, 0x2B, 0xA7, 0xA3, 0x95, 0x98, 0x4C, 0xCA, 0x1B,
+   0xE6, 0x8D, 0x73, 0x36, 0xCD, 0x82, 0x12, 0x56, 0x62, 0xAB, 0xF0, 0x47,
+   0x4F, 0x0E, 0xBD, 0x06, 0xD4, 0x25, 0xD2, 0x5E, 0x27, 0x88, 0x66, 0x6D,
+   0xD6, 0x9C, 0x79, 0xB8, 0x08, 0xC2, 0xDF, 0x32, 0x68, 0x2C, 0xFD, 0xA8,
+   0x8A, 0xA4, 0x5A, 0x96, 0x29, 0x99, 0x22, 0x4D, 0x60, 0xCB, 0xE4, 0x1C,
+   0x7B, 0xE7, 0x3B, 0x8E, 0x9E, 0x74, 0xF4, 0x37, 0xD8, 0xCE, 0xF9, 0x83,
+   0x6F, 0x13, 0xB2, 0x57, 0xE1, 0x63, 0xDC, 0xAC, 0xC4, 0xF1, 0xAF, 0x48,
+   0x0A, 0x50, 0x42, 0x0F, 0xBA, 0xBE, 0xC7, 0x07, 0xDE, 0xD5, 0x78, 0x26,
+   0x65, 0xD3, 0xD1, 0x5F, 0xE3, 0x28, 0x21, 0x89, 0x59, 0x67, 0xFC, 0x6E,
+   0xB1, 0xD7, 0xF8, 0x9D, 0xF3, 0x7A, 0x3A, 0xB9, 0xC6, 0x09, 0x41, 0xC3,
+   0xAE, 0xE0, 0xDB, 0x33, 0x44, 0x69, 0x92, 0x2D, 0x52, 0xFE, 0x16, 0xA9,
+   0x0C, 0x8B, 0x80, 0xA5, 0x4A, 0x5B, 0xB5, 0x97, 0xC9, 0x2A, 0xA2, 0x9A,
+   0xC0, 0x23, 0x86, 0x4E, 0xBC, 0x61, 0xEF, 0xCC, 0x11, 0xE5, 0x72, 0x1D,
+   0x3D, 0x7C, 0xEB, 0xE8, 0xE9, 0x3C, 0xEA, 0x8F, 0x7D, 0x9F, 0xEC, 0x75,
+   0x1E, 0xF5, 0x3E, 0x38, 0xF6, 0xD9, 0x3F, 0xCF, 0x76, 0xFA, 0x1F, 0x84,
+   0xA0, 0x70, 0xED, 0x14, 0x90, 0xB3, 0x7E, 0x58, 0xFB, 0xE2, 0x20, 0x64,
+   0xD0, 0xDD, 0x77, 0xAD, 0xDA, 0xC5, 0x40, 0xF2, 0x39, 0xB0, 0xF7, 0x49,
+   0xB4, 0x0B, 0x7F, 0x51, 0x15, 0x43, 0x91, 0x10, 0x71, 0xBB, 0xEE, 0xBF,
+   0x85, 0xC8, 0xA1
+};
+
+static const u8 exp_to_poly[492] = {
+   0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x4D, 0x9A, 0x79, 0xF2,
+   0xA9, 0x1F, 0x3E, 0x7C, 0xF8, 0xBD, 0x37, 0x6E, 0xDC, 0xF5, 0xA7, 0x03,
+   0x06, 0x0C, 0x18, 0x30, 0x60, 0xC0, 0xCD, 0xD7, 0xE3, 0x8B, 0x5B, 0xB6,
+   0x21, 0x42, 0x84, 0x45, 0x8A, 0x59, 0xB2, 0x29, 0x52, 0xA4, 0x05, 0x0A,
+   0x14, 0x28, 0x50, 0xA0, 0x0D, 0x1A, 0x34, 0x68, 0xD0, 0xED, 0x97, 0x63,
+   0xC6, 0xC1, 0xCF, 0xD3, 0xEB, 0x9B, 0x7B, 0xF6, 0xA1, 0x0F, 0x1E, 0x3C,
+   0x78, 0xF0, 0xAD, 0x17, 0x2E, 0x5C, 0xB8, 0x3D, 0x7A, 0xF4, 0xA5, 0x07,
+   0x0E, 0x1C, 0x38, 0x70, 0xE0, 0x8D, 0x57, 0xAE, 0x11, 0x22, 0x44, 0x88,
+   0x5D, 0xBA, 0x39, 0x72, 0xE4, 0x85, 0x47, 0x8E, 0x51, 0xA2, 0x09, 0x12,
+   0x24, 0x48, 0x90, 0x6D, 0xDA, 0xF9, 0xBF, 0x33, 0x66, 0xCC, 0xD5, 0xE7,
+   0x83, 0x4B, 0x96, 0x61, 0xC2, 0xC9, 0xDF, 0xF3, 0xAB, 0x1B, 0x36, 0x6C,
+   0xD8, 0xFD, 0xB7, 0x23, 0x46, 0x8C, 0x55, 0xAA, 0x19, 0x32, 0x64, 0xC8,
+   0xDD, 0xF7, 0xA3, 0x0B, 0x16, 0x2C, 0x58, 0xB0, 0x2D, 0x5A, 0xB4, 0x25,
+   0x4A, 0x94, 0x65, 0xCA, 0xD9, 0xFF, 0xB3, 0x2B, 0x56, 0xAC, 0x15, 0x2A,
+   0x54, 0xA8, 0x1D, 0x3A, 0x74, 0xE8, 0x9D, 0x77, 0xEE, 0x91, 0x6F, 0xDE,
+   0xF1, 0xAF, 0x13, 0x26, 0x4C, 0x98, 0x7D, 0xFA, 0xB9, 0x3F, 0x7E, 0xFC,
+   0xB5, 0x27, 0x4E, 0x9C, 0x75, 0xEA, 0x99, 0x7F, 0xFE, 0xB1, 0x2F, 0x5E,
+   0xBC, 0x35, 0x6A, 0xD4, 0xE5, 0x87, 0x43, 0x86, 0x41, 0x82, 0x49, 0x92,
+   0x69, 0xD2, 0xE9, 0x9F, 0x73, 0xE6, 0x81, 0x4F, 0x9E, 0x71, 0xE2, 0x89,
+   0x5F, 0xBE, 0x31, 0x62, 0xC4, 0xC5, 0xC7, 0xC3, 0xCB, 0xDB, 0xFB, 0xBB,
+   0x3B, 0x76, 0xEC, 0x95, 0x67, 0xCE, 0xD1, 0xEF, 0x93, 0x6B, 0xD6, 0xE1,
+   0x8F, 0x53, 0xA6, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x4D,
+   0x9A, 0x79, 0xF2, 0xA9, 0x1F, 0x3E, 0x7C, 0xF8, 0xBD, 0x37, 0x6E, 0xDC,
+   0xF5, 0xA7, 0x03, 0x06, 0x0C, 0x18, 0x30, 0x60, 0xC0, 0xCD, 0xD7, 0xE3,
+   0x8B, 0x5B, 0xB6, 0x21, 0x42, 0x84, 0x45, 0x8A, 0x59, 0xB2, 0x29, 0x52,
+   0xA4, 0x05, 0x0A, 0x14, 0x28, 0x50, 0xA0, 0x0D, 0x1A, 0x34, 0x68, 0xD0,
+   0xED, 0x97, 0x63, 0xC6, 0xC1, 0xCF, 0xD3, 0xEB, 0x9B, 0x7B, 0xF6, 0xA1,
+   0x0F, 0x1E, 0x3C, 0x78, 0xF0, 0xAD, 0x17, 0x2E, 0x5C, 0xB8, 0x3D, 0x7A,
+   0xF4, 0xA5, 0x07, 0x0E, 0x1C, 0x38, 0x70, 0xE0, 0x8D, 0x57, 0xAE, 0x11,
+   0x22, 0x44, 0x88, 0x5D, 0xBA, 0x39, 0x72, 0xE4, 0x85, 0x47, 0x8E, 0x51,
+   0xA2, 0x09, 0x12, 0x24, 0x48, 0x90, 0x6D, 0xDA, 0xF9, 0xBF, 0x33, 0x66,
+   0xCC, 0xD5, 0xE7, 0x83, 0x4B, 0x96, 0x61, 0xC2, 0xC9, 0xDF, 0xF3, 0xAB,
+   0x1B, 0x36, 0x6C, 0xD8, 0xFD, 0xB7, 0x23, 0x46, 0x8C, 0x55, 0xAA, 0x19,
+   0x32, 0x64, 0xC8, 0xDD, 0xF7, 0xA3, 0x0B, 0x16, 0x2C, 0x58, 0xB0, 0x2D,
+   0x5A, 0xB4, 0x25, 0x4A, 0x94, 0x65, 0xCA, 0xD9, 0xFF, 0xB3, 0x2B, 0x56,
+   0xAC, 0x15, 0x2A, 0x54, 0xA8, 0x1D, 0x3A, 0x74, 0xE8, 0x9D, 0x77, 0xEE,
+   0x91, 0x6F, 0xDE, 0xF1, 0xAF, 0x13, 0x26, 0x4C, 0x98, 0x7D, 0xFA, 0xB9,
+   0x3F, 0x7E, 0xFC, 0xB5, 0x27, 0x4E, 0x9C, 0x75, 0xEA, 0x99, 0x7F, 0xFE,
+   0xB1, 0x2F, 0x5E, 0xBC, 0x35, 0x6A, 0xD4, 0xE5, 0x87, 0x43, 0x86, 0x41,
+   0x82, 0x49, 0x92, 0x69, 0xD2, 0xE9, 0x9F, 0x73, 0xE6, 0x81, 0x4F, 0x9E,
+   0x71, 0xE2, 0x89, 0x5F, 0xBE, 0x31, 0x62, 0xC4, 0xC5, 0xC7, 0xC3, 0xCB
+};
+
+
+/* The table constants are indices of
+ * S-box entries, preprocessed through q0 and q1. */
+static const u8 calc_sb_tbl[512] = {
+    0xA9, 0x75, 0x67, 0xF3, 0xB3, 0xC6, 0xE8, 0xF4,
+    0x04, 0xDB, 0xFD, 0x7B, 0xA3, 0xFB, 0x76, 0xC8,
+    0x9A, 0x4A, 0x92, 0xD3, 0x80, 0xE6, 0x78, 0x6B,
+    0xE4, 0x45, 0xDD, 0x7D, 0xD1, 0xE8, 0x38, 0x4B,
+    0x0D, 0xD6, 0xC6, 0x32, 0x35, 0xD8, 0x98, 0xFD,
+    0x18, 0x37, 0xF7, 0x71, 0xEC, 0xF1, 0x6C, 0xE1,
+    0x43, 0x30, 0x75, 0x0F, 0x37, 0xF8, 0x26, 0x1B,
+    0xFA, 0x87, 0x13, 0xFA, 0x94, 0x06, 0x48, 0x3F,
+    0xF2, 0x5E, 0xD0, 0xBA, 0x8B, 0xAE, 0x30, 0x5B,
+    0x84, 0x8A, 0x54, 0x00, 0xDF, 0xBC, 0x23, 0x9D,
+    0x19, 0x6D, 0x5B, 0xC1, 0x3D, 0xB1, 0x59, 0x0E,
+    0xF3, 0x80, 0xAE, 0x5D, 0xA2, 0xD2, 0x82, 0xD5,
+    0x63, 0xA0, 0x01, 0x84, 0x83, 0x07, 0x2E, 0x14,
+    0xD9, 0xB5, 0x51, 0x90, 0x9B, 0x2C, 0x7C, 0xA3,
+    0xA6, 0xB2, 0xEB, 0x73, 0xA5, 0x4C, 0xBE, 0x54,
+    0x16, 0x92, 0x0C, 0x74, 0xE3, 0x36, 0x61, 0x51,
+    0xC0, 0x38, 0x8C, 0xB0, 0x3A, 0xBD, 0xF5, 0x5A,
+    0x73, 0xFC, 0x2C, 0x60, 0x25, 0x62, 0x0B, 0x96,
+    0xBB, 0x6C, 0x4E, 0x42, 0x89, 0xF7, 0x6B, 0x10,
+    0x53, 0x7C, 0x6A, 0x28, 0xB4, 0x27, 0xF1, 0x8C,
+    0xE1, 0x13, 0xE6, 0x95, 0xBD, 0x9C, 0x45, 0xC7,
+    0xE2, 0x24, 0xF4, 0x46, 0xB6, 0x3B, 0x66, 0x70,
+    0xCC, 0xCA, 0x95, 0xE3, 0x03, 0x85, 0x56, 0xCB,
+    0xD4, 0x11, 0x1C, 0xD0, 0x1E, 0x93, 0xD7, 0xB8,
+    0xFB, 0xA6, 0xC3, 0x83, 0x8E, 0x20, 0xB5, 0xFF,
+    0xE9, 0x9F, 0xCF, 0x77, 0xBF, 0xC3, 0xBA, 0xCC,
+    0xEA, 0x03, 0x77, 0x6F, 0x39, 0x08, 0xAF, 0xBF,
+    0x33, 0x40, 0xC9, 0xE7, 0x62, 0x2B, 0x71, 0xE2,
+    0x81, 0x79, 0x79, 0x0C, 0x09, 0xAA, 0xAD, 0x82,
+    0x24, 0x41, 0xCD, 0x3A, 0xF9, 0xEA, 0xD8, 0xB9,
+    0xE5, 0xE4, 0xC5, 0x9A, 0xB9, 0xA4, 0x4D, 0x97,
+    0x44, 0x7E, 0x08, 0xDA, 0x86, 0x7A, 0xE7, 0x17,
+    0xA1, 0x66, 0x1D, 0x94, 0xAA, 0xA1, 0xED, 0x1D,
+    0x06, 0x3D, 0x70, 0xF0, 0xB2, 0xDE, 0xD2, 0xB3,
+    0x41, 0x0B, 0x7B, 0x72, 0xA0, 0xA7, 0x11, 0x1C,
+    0x31, 0xEF, 0xC2, 0xD1, 0x27, 0x53, 0x90, 0x3E,
+    0x20, 0x8F, 0xF6, 0x33, 0x60, 0x26, 0xFF, 0x5F,
+    0x96, 0xEC, 0x5C, 0x76, 0xB1, 0x2A, 0xAB, 0x49,
+    0x9E, 0x81, 0x9C, 0x88, 0x52, 0xEE, 0x1B, 0x21,
+    0x5F, 0xC4, 0x93, 0x1A, 0x0A, 0xEB, 0xEF, 0xD9,
+    0x91, 0xC5, 0x85, 0x39, 0x49, 0x99, 0xEE, 0xCD,
+    0x2D, 0xAD, 0x4F, 0x31, 0x8F, 0x8B, 0x3B, 0x01,
+    0x47, 0x18, 0x87, 0x23, 0x6D, 0xDD, 0x46, 0x1F,
+    0xD6, 0x4E, 0x3E, 0x2D, 0x69, 0xF9, 0x64, 0x48,
+    0x2A, 0x4F, 0xCE, 0xF2, 0xCB, 0x65, 0x2F, 0x8E,
+    0xFC, 0x78, 0x97, 0x5C, 0x05, 0x58, 0x7A, 0x19,
+    0xAC, 0x8D, 0x7F, 0xE5, 0xD5, 0x98, 0x1A, 0x57,
+    0x4B, 0x67, 0x0E, 0x7F, 0xA7, 0x05, 0x5A, 0x64,
+    0x28, 0xAF, 0x14, 0x63, 0x3F, 0xB6, 0x29, 0xFE,
+    0x88, 0xF5, 0x3C, 0xB7, 0x4C, 0x3C, 0x02, 0xA5,
+    0xB8, 0xCE, 0xDA, 0xE9, 0xB0, 0x68, 0x17, 0x44,
+    0x55, 0xE0, 0x1F, 0x4D, 0x8A, 0x43, 0x7D, 0x69,
+    0x57, 0x29, 0xC7, 0x2E, 0x8D, 0xAC, 0x74, 0x15,
+    0xB7, 0x59, 0xC4, 0xA8, 0x9F, 0x0A, 0x72, 0x9E,
+    0x7E, 0x6E, 0x15, 0x47, 0x22, 0xDF, 0x12, 0x34,
+    0x58, 0x35, 0x07, 0x6A, 0x99, 0xCF, 0x34, 0xDC,
+    0x6E, 0x22, 0x50, 0xC9, 0xDE, 0xC0, 0x68, 0x9B,
+    0x65, 0x89, 0xBC, 0xD4, 0xDB, 0xED, 0xF8, 0xAB,
+    0xC8, 0x12, 0xA8, 0xA2, 0x2B, 0x0D, 0x40, 0x52,
+    0xDC, 0xBB, 0xFE, 0x02, 0x32, 0x2F, 0xA4, 0xA9,
+    0xCA, 0xD7, 0x10, 0x61, 0x21, 0x1E, 0xF0, 0xB4,
+    0xD3, 0x50, 0x5D, 0x04, 0x0F, 0xF6, 0x00, 0xC2,
+    0x6F, 0x16, 0x9D, 0x25, 0x36, 0x86, 0x42, 0x56,
+    0x4A, 0x55, 0x5E, 0x09, 0xC1, 0xBE, 0xE0, 0x91
+};
+
+/* Macro to perform one column of the RS matrix multiplication.  The
+ * parameters a, b, c, and d are the four bytes of output; i is the index
+ * of the key bytes, and w, x, y, and z, are the column of constants from
+ * the RS matrix, preprocessed through the poly_to_exp table. */
+
+#define CALC_S(a, b, c, d, i, w, x, y, z) \
+   if (key[i]) { \
+      tmp = poly_to_exp[key[i] - 1]; \
+      (a) ^= exp_to_poly[tmp + (w)]; \
+      (b) ^= exp_to_poly[tmp + (x)]; \
+      (c) ^= exp_to_poly[tmp + (y)]; \
+      (d) ^= exp_to_poly[tmp + (z)]; \
+   }
+
+/* Macros to calculate the key-dependent S-boxes for a 128-bit key using
+ * the S vector from CALC_S.  CALC_SB_2 computes a single entry in all
+ * four S-boxes, where i is the index of the entry to compute, and a and b
+ * are the index numbers preprocessed through the q0 and q1 tables
+ * respectively. */
+
+#define CALC_SB_2(i, a, b) \
+   ctx->s[0][i] = mds[0][q0[(a) ^ sa] ^ se]; \
+   ctx->s[1][i] = mds[1][q0[(b) ^ sb] ^ sf]; \
+   ctx->s[2][i] = mds[2][q1[(a) ^ sc] ^ sg]; \
+   ctx->s[3][i] = mds[3][q1[(b) ^ sd] ^ sh]
+
+/* Macro exactly like CALC_SB_2, but for 192-bit keys. */
+
+#define CALC_SB192_2(i, a, b) \
+   ctx->s[0][i] = mds[0][q0[q0[(b) ^ sa] ^ se] ^ si]; \
+   ctx->s[1][i] = mds[1][q0[q1[(b) ^ sb] ^ sf] ^ sj]; \
+   ctx->s[2][i] = mds[2][q1[q0[(a) ^ sc] ^ sg] ^ sk]; \
+   ctx->s[3][i] = mds[3][q1[q1[(a) ^ sd] ^ sh] ^ sl];
+
+/* Macro exactly like CALC_SB_2, but for 256-bit keys. */
+
+#define CALC_SB256_2(i, a, b) \
+   ctx->s[0][i] = mds[0][q0[q0[q1[(b) ^ sa] ^ se] ^ si] ^ sm]; \
+   ctx->s[1][i] = mds[1][q0[q1[q1[(a) ^ sb] ^ sf] ^ sj] ^ sn]; \
+   ctx->s[2][i] = mds[2][q1[q0[q0[(a) ^ sc] ^ sg] ^ sk] ^ so]; \
+   ctx->s[3][i] = mds[3][q1[q1[q0[(b) ^ sd] ^ sh] ^ sl] ^ sp];
+
+/* Macros to calculate the whitening and round subkeys.  CALC_K_2 computes the
+ * last two stages of the h() function for a given index (either 2i or 2i+1).
+ * a, b, c, and d are the four bytes going into the last two stages.  For
+ * 128-bit keys, this is the entire h() function and a and c are the index
+ * preprocessed through q0 and q1 respectively; for longer keys they are the
+ * output of previous stages.  j is the index of the first key byte to use.
+ * CALC_K computes a pair of subkeys for 128-bit Twofish, by calling CALC_K_2
+ * twice, doing the Psuedo-Hadamard Transform, and doing the necessary
+ * rotations.  Its parameters are: a, the array to write the results into,
+ * j, the index of the first output entry, k and l, the preprocessed indices
+ * for index 2i, and m and n, the preprocessed indices for index 2i+1.
+ * CALC_K192_2 expands CALC_K_2 to handle 192-bit keys, by doing an
+ * additional lookup-and-XOR stage.  The parameters a, b, c and d are the
+ * four bytes going into the last three stages.  For 192-bit keys, c = d
+ * are the index preprocessed through q0, and a = b are the index
+ * preprocessed through q1; j is the index of the first key byte to use.
+ * CALC_K192 is identical to CALC_K but for using the CALC_K192_2 macro
+ * instead of CALC_K_2.
+ * CALC_K256_2 expands CALC_K192_2 to handle 256-bit keys, by doing an
+ * additional lookup-and-XOR stage.  The parameters a and b are the index
+ * preprocessed through q0 and q1 respectively; j is the index of the first
+ * key byte to use.  CALC_K256 is identical to CALC_K but for using the
+ * CALC_K256_2 macro instead of CALC_K_2. */
+
+#define CALC_K_2(a, b, c, d, j) \
+     mds[0][q0[a ^ key[(j) + 8]] ^ key[j]] \
+   ^ mds[1][q0[b ^ key[(j) + 9]] ^ key[(j) + 1]] \
+   ^ mds[2][q1[c ^ key[(j) + 10]] ^ key[(j) + 2]] \
+   ^ mds[3][q1[d ^ key[(j) + 11]] ^ key[(j) + 3]]
+
+#define CALC_K(a, j, k, l, m, n) \
+   x = CALC_K_2 (k, l, k, l, 0); \
+   y = CALC_K_2 (m, n, m, n, 4); \
+   y = (y << 8) + (y >> 24); \
+   x += y; y += x; ctx->a[j] = x; \
+   ctx->a[(j) + 1] = (y << 9) + (y >> 23)
+
+#define CALC_K192_2(a, b, c, d, j) \
+   CALC_K_2 (q0[a ^ key[(j) + 16]], \
+	     q1[b ^ key[(j) + 17]], \
+	     q0[c ^ key[(j) + 18]], \
+	     q1[d ^ key[(j) + 19]], j)
+
+#define CALC_K192(a, j, k, l, m, n) \
+   x = CALC_K192_2 (l, l, k, k, 0); \
+   y = CALC_K192_2 (n, n, m, m, 4); \
+   y = (y << 8) + (y >> 24); \
+   x += y; y += x; ctx->a[j] = x; \
+   ctx->a[(j) + 1] = (y << 9) + (y >> 23)
+
+#define CALC_K256_2(a, b, j) \
+   CALC_K192_2 (q1[b ^ key[(j) + 24]], \
+	        q1[a ^ key[(j) + 25]], \
+	        q0[a ^ key[(j) + 26]], \
+	        q0[b ^ key[(j) + 27]], j)
+
+#define CALC_K256(a, j, k, l, m, n) \
+   x = CALC_K256_2 (k, l, 0); \
+   y = CALC_K256_2 (m, n, 4); \
+   y = (y << 8) + (y >> 24); \
+   x += y; y += x; ctx->a[j] = x; \
+   ctx->a[(j) + 1] = (y << 9) + (y >> 23)
+
+/* Perform the key setup. */
+
+int twofish_set_key (TWOFISH_context *ctx,
+			    const unsigned char *key, int key_len)
+{
+
+	int i, j, k;
+
+	/* Temporaries for CALC_K. */
+	u32 x, y;
+
+	/* The S vector used to key the S-boxes, split up into individual bytes.
+	 * 128-bit keys use only sa through sh; 256-bit use all of them. */
+	u8 sa = 0, sb = 0, sc = 0, sd = 0, se = 0, sf = 0, sg = 0, sh = 0;
+	u8 si = 0, sj = 0, sk = 0, sl = 0, sm = 0, sn = 0, so = 0, sp = 0;
+
+	/* Temporary for CALC_S. */
+	u8 tmp;
+
+	/* Check key length. */
+	if (key_len != 16 && key_len != 24 && key_len != 32)
+		return -1; /* unsupported key length */
+
+	/* Compute the first two words of the S vector.  The magic numbers are
+	 * the entries of the RS matrix, preprocessed through poly_to_exp. The
+	 * numbers in the comments are the original (polynomial form) matrix
+	 * entries. */
+	CALC_S (sa, sb, sc, sd, 0, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */
+	CALC_S (sa, sb, sc, sd, 1, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */
+	CALC_S (sa, sb, sc, sd, 2, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */
+	CALC_S (sa, sb, sc, sd, 3, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */
+	CALC_S (sa, sb, sc, sd, 4, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */
+	CALC_S (sa, sb, sc, sd, 5, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */
+	CALC_S (sa, sb, sc, sd, 6, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */
+	CALC_S (sa, sb, sc, sd, 7, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */
+	CALC_S (se, sf, sg, sh, 8, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */
+	CALC_S (se, sf, sg, sh, 9, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */
+	CALC_S (se, sf, sg, sh, 10, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */
+	CALC_S (se, sf, sg, sh, 11, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */
+	CALC_S (se, sf, sg, sh, 12, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */
+	CALC_S (se, sf, sg, sh, 13, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */
+	CALC_S (se, sf, sg, sh, 14, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */
+	CALC_S (se, sf, sg, sh, 15, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */
+
+	if (key_len == 24 || key_len == 32) { /* 192- or 256-bit key */
+		/* Calculate the third word of the S vector */
+		CALC_S (si, sj, sk, sl, 16, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */
+		CALC_S (si, sj, sk, sl, 17, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */
+		CALC_S (si, sj, sk, sl, 18, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */
+		CALC_S (si, sj, sk, sl, 19, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */
+		CALC_S (si, sj, sk, sl, 20, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */
+		CALC_S (si, sj, sk, sl, 21, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */
+		CALC_S (si, sj, sk, sl, 22, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */
+		CALC_S (si, sj, sk, sl, 23, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */
+	}
+
+	if (key_len == 32) { /* 256-bit key */
+		/* Calculate the fourth word of the S vector */
+		CALC_S (sm, sn, so, sp, 24, 0x00, 0x2D, 0x01, 0x2D); /* 01 A4 02 A4 */
+		CALC_S (sm, sn, so, sp, 25, 0x2D, 0xA4, 0x44, 0x8A); /* A4 56 A1 55 */
+		CALC_S (sm, sn, so, sp, 26, 0x8A, 0xD5, 0xBF, 0xD1); /* 55 82 FC 87 */
+		CALC_S (sm, sn, so, sp, 27, 0xD1, 0x7F, 0x3D, 0x99); /* 87 F3 C1 5A */
+		CALC_S (sm, sn, so, sp, 28, 0x99, 0x46, 0x66, 0x96); /* 5A 1E 47 58 */
+		CALC_S (sm, sn, so, sp, 29, 0x96, 0x3C, 0x5B, 0xED); /* 58 C6 AE DB */
+		CALC_S (sm, sn, so, sp, 30, 0xED, 0x37, 0x4F, 0xE0); /* DB 68 3D 9E */
+		CALC_S (sm, sn, so, sp, 31, 0xE0, 0xD0, 0x8C, 0x17); /* 9E E5 19 03 */
+
+		/* Compute the S-boxes. */
+		for ( i = j = 0, k = 1; i < 256; i++, j += 2, k += 2 ) {
+			CALC_SB256_2( i, calc_sb_tbl[j], calc_sb_tbl[k] );
+		}
+
+		/* Calculate whitening and round subkeys.  The constants are
+		 * indices of subkeys, preprocessed through q0 and q1. */
+		CALC_K256 (w, 0, 0xA9, 0x75, 0x67, 0xF3);
+		CALC_K256 (w, 2, 0xB3, 0xC6, 0xE8, 0xF4);
+		CALC_K256 (w, 4, 0x04, 0xDB, 0xFD, 0x7B);
+		CALC_K256 (w, 6, 0xA3, 0xFB, 0x76, 0xC8);
+		CALC_K256 (k, 0, 0x9A, 0x4A, 0x92, 0xD3);
+		CALC_K256 (k, 2, 0x80, 0xE6, 0x78, 0x6B);
+		CALC_K256 (k, 4, 0xE4, 0x45, 0xDD, 0x7D);
+		CALC_K256 (k, 6, 0xD1, 0xE8, 0x38, 0x4B);
+		CALC_K256 (k, 8, 0x0D, 0xD6, 0xC6, 0x32);
+		CALC_K256 (k, 10, 0x35, 0xD8, 0x98, 0xFD);
+		CALC_K256 (k, 12, 0x18, 0x37, 0xF7, 0x71);
+		CALC_K256 (k, 14, 0xEC, 0xF1, 0x6C, 0xE1);
+		CALC_K256 (k, 16, 0x43, 0x30, 0x75, 0x0F);
+		CALC_K256 (k, 18, 0x37, 0xF8, 0x26, 0x1B);
+		CALC_K256 (k, 20, 0xFA, 0x87, 0x13, 0xFA);
+		CALC_K256 (k, 22, 0x94, 0x06, 0x48, 0x3F);
+		CALC_K256 (k, 24, 0xF2, 0x5E, 0xD0, 0xBA);
+		CALC_K256 (k, 26, 0x8B, 0xAE, 0x30, 0x5B);
+		CALC_K256 (k, 28, 0x84, 0x8A, 0x54, 0x00);
+		CALC_K256 (k, 30, 0xDF, 0xBC, 0x23, 0x9D);
+	} else if (key_len == 24) { /* 192-bit key */
+		/* Compute the S-boxes. */
+		for ( i = j = 0, k = 1; i < 256; i++, j += 2, k += 2 ) {
+		        CALC_SB192_2( i, calc_sb_tbl[j], calc_sb_tbl[k] );
+		}
+
+		/* Calculate whitening and round subkeys.  The constants are
+		 * indices of subkeys, preprocessed through q0 and q1. */
+		CALC_K192 (w, 0, 0xA9, 0x75, 0x67, 0xF3);
+		CALC_K192 (w, 2, 0xB3, 0xC6, 0xE8, 0xF4);
+		CALC_K192 (w, 4, 0x04, 0xDB, 0xFD, 0x7B);
+		CALC_K192 (w, 6, 0xA3, 0xFB, 0x76, 0xC8);
+		CALC_K192 (k, 0, 0x9A, 0x4A, 0x92, 0xD3);
+		CALC_K192 (k, 2, 0x80, 0xE6, 0x78, 0x6B);
+		CALC_K192 (k, 4, 0xE4, 0x45, 0xDD, 0x7D);
+		CALC_K192 (k, 6, 0xD1, 0xE8, 0x38, 0x4B);
+		CALC_K192 (k, 8, 0x0D, 0xD6, 0xC6, 0x32);
+		CALC_K192 (k, 10, 0x35, 0xD8, 0x98, 0xFD);
+		CALC_K192 (k, 12, 0x18, 0x37, 0xF7, 0x71);
+		CALC_K192 (k, 14, 0xEC, 0xF1, 0x6C, 0xE1);
+		CALC_K192 (k, 16, 0x43, 0x30, 0x75, 0x0F);
+		CALC_K192 (k, 18, 0x37, 0xF8, 0x26, 0x1B);
+		CALC_K192 (k, 20, 0xFA, 0x87, 0x13, 0xFA);
+		CALC_K192 (k, 22, 0x94, 0x06, 0x48, 0x3F);
+		CALC_K192 (k, 24, 0xF2, 0x5E, 0xD0, 0xBA);
+		CALC_K192 (k, 26, 0x8B, 0xAE, 0x30, 0x5B);
+		CALC_K192 (k, 28, 0x84, 0x8A, 0x54, 0x00);
+		CALC_K192 (k, 30, 0xDF, 0xBC, 0x23, 0x9D);
+	} else { /* 128-bit key */
+		/* Compute the S-boxes. */
+		for ( i = j = 0, k = 1; i < 256; i++, j += 2, k += 2 ) {
+			CALC_SB_2( i, calc_sb_tbl[j], calc_sb_tbl[k] );
+		}
+
+		/* Calculate whitening and round subkeys.  The constants are
+		 * indices of subkeys, preprocessed through q0 and q1. */
+		CALC_K (w, 0, 0xA9, 0x75, 0x67, 0xF3);
+		CALC_K (w, 2, 0xB3, 0xC6, 0xE8, 0xF4);
+		CALC_K (w, 4, 0x04, 0xDB, 0xFD, 0x7B);
+		CALC_K (w, 6, 0xA3, 0xFB, 0x76, 0xC8);
+		CALC_K (k, 0, 0x9A, 0x4A, 0x92, 0xD3);
+		CALC_K (k, 2, 0x80, 0xE6, 0x78, 0x6B);
+		CALC_K (k, 4, 0xE4, 0x45, 0xDD, 0x7D);
+		CALC_K (k, 6, 0xD1, 0xE8, 0x38, 0x4B);
+		CALC_K (k, 8, 0x0D, 0xD6, 0xC6, 0x32);
+		CALC_K (k, 10, 0x35, 0xD8, 0x98, 0xFD);
+		CALC_K (k, 12, 0x18, 0x37, 0xF7, 0x71);
+		CALC_K (k, 14, 0xEC, 0xF1, 0x6C, 0xE1);
+		CALC_K (k, 16, 0x43, 0x30, 0x75, 0x0F);
+		CALC_K (k, 18, 0x37, 0xF8, 0x26, 0x1B);
+		CALC_K (k, 20, 0xFA, 0x87, 0x13, 0xFA);
+		CALC_K (k, 22, 0x94, 0x06, 0x48, 0x3F);
+		CALC_K (k, 24, 0xF2, 0x5E, 0xD0, 0xBA);
+		CALC_K (k, 26, 0x8B, 0xAE, 0x30, 0x5B);
+		CALC_K (k, 28, 0x84, 0x8A, 0x54, 0x00);
+		CALC_K (k, 30, 0xDF, 0xBC, 0x23, 0x9D);
+	}
+
+	return 0;
+}
+
+/* Macros to compute the g() function in the encryption and decryption
+ * rounds.  G1 is the straight g() function; G2 includes the 8-bit
+ * rotation for the high 32-bit word. */
+
+#define G1(a) \
+     (ctx->s[0][(a) & 0xFF]) ^ (ctx->s[1][((a) >> 8) & 0xFF]) \
+   ^ (ctx->s[2][((a) >> 16) & 0xFF]) ^ (ctx->s[3][(a) >> 24])
+
+#define G2(b) \
+     (ctx->s[1][(b) & 0xFF]) ^ (ctx->s[2][((b) >> 8) & 0xFF]) \
+   ^ (ctx->s[3][((b) >> 16) & 0xFF]) ^ (ctx->s[0][(b) >> 24])
+
+/* Encryption and decryption Feistel rounds.  Each one calls the two g()
+ * macros, does the PHT, and performs the XOR and the appropriate bit
+ * rotations.  The parameters are the round number (used to select subkeys),
+ * and the four 32-bit chunks of the text. */
+
+#define ENCROUND(n, a, b, c, d) \
+   x = G1 (a); y = G2 (b); \
+   x += y; y += x + ctx->k[2 * (n) + 1]; \
+   (c) ^= x + ctx->k[2 * (n)]; \
+   (c) = ((c) >> 1) + ((c) << 31); \
+   (d) = (((d) << 1)+((d) >> 31)) ^ y
+
+#define DECROUND(n, a, b, c, d) \
+   x = G1 (a); y = G2 (b); \
+   x += y; y += x; \
+   (d) ^= y + ctx->k[2 * (n) + 1]; \
+   (d) = ((d) >> 1) + ((d) << 31); \
+   (c) = (((c) << 1)+((c) >> 31)); \
+   (c) ^= (x + ctx->k[2 * (n)])
+
+/* Encryption and decryption cycles; each one is simply two Feistel rounds
+ * with the 32-bit chunks re-ordered to simulate the "swap" */
+
+#define ENCCYCLE(n) \
+   ENCROUND (2 * (n), a, b, c, d); \
+   ENCROUND (2 * (n) + 1, c, d, a, b)
+
+#define DECCYCLE(n) \
+   DECROUND (2 * (n) + 1, c, d, a, b); \
+   DECROUND (2 * (n), a, b, c, d)
+
+/* Macros to convert the input and output bytes into 32-bit words,
+ * and simultaneously perform the whitening step.  INPACK packs word
+ * number n into the variable named by x, using whitening subkey number m.
+ * OUTUNPACK unpacks word number n from the variable named by x, using
+ * whitening subkey number m. */
+
+#define INPACK(n, x, m) \
+   x = in[4 * (n)] ^ (in[4 * (n) + 1] << 8) \
+     ^ (in[4 * (n) + 2] << 16) ^ (in[4 * (n) + 3] << 24) ^ ctx->w[m]
+
+#define OUTUNPACK(n, x, m) \
+   x ^= ctx->w[m]; \
+   out[4 * (n)] = x; out[4 * (n) + 1] = x >> 8; \
+   out[4 * (n) + 2] = x >> 16; out[4 * (n) + 3] = x >> 24
+
+/* Encrypt one block.  in and out may be the same. */
+
+int twofish_encrypt (TWOFISH_context *ctx,
+			    const u8 *in, u8 *out)
+{
+	/* The four 32-bit chunks of the text. */
+	u32 a, b, c, d;
+	
+	/* Temporaries used by the round function. */
+	u32 x, y;
+	
+	/* Input whitening and packing. */
+	INPACK (0, a, 0);
+	INPACK (1, b, 1);
+	INPACK (2, c, 2);
+	INPACK (3, d, 3);
+	
+	/* Encryption Feistel cycles. */
+	ENCCYCLE (0);
+	ENCCYCLE (1);
+	ENCCYCLE (2);
+	ENCCYCLE (3);
+	ENCCYCLE (4);
+	ENCCYCLE (5);
+	ENCCYCLE (6);
+	ENCCYCLE (7);
+	
+	/* Output whitening and unpacking. */
+	OUTUNPACK (0, c, 4);
+	OUTUNPACK (1, d, 5);
+	OUTUNPACK (2, a, 6);
+	OUTUNPACK (3, b, 7);
+	
+	return 0;
+}
+
+/* Decrypt one block.  in and out may be the same. */
+
+int twofish_decrypt (TWOFISH_context *ctx,
+			    const u8 *in, u8 *out)
+{
+	/* The four 32-bit chunks of the text. */
+	u32 a, b, c, d;
+	
+	/* Temporaries used by the round function. */
+	u32 x, y;
+	
+	/* Input whitening and packing. */
+	INPACK (0, c, 4);
+	INPACK (1, d, 5);
+	INPACK (2, a, 6);
+	INPACK (3, b, 7);
+	
+	/* Encryption Feistel cycles. */
+	DECCYCLE (7);
+	DECCYCLE (6);
+	DECCYCLE (5);
+	DECCYCLE (4);
+	DECCYCLE (3);
+	DECCYCLE (2);
+	DECCYCLE (1);
+	DECCYCLE (0);
+
+	/* Output whitening and unpacking. */
+	OUTUNPACK (0, a, 0);
+	OUTUNPACK (1, b, 1);
+	OUTUNPACK (2, c, 2);
+	OUTUNPACK (3, d, 3);
+
+	return 0;
+}
+
+/* eof */
diff --git a/lib/libcrypto/libtwofish/twofish.h b/lib/libcrypto/libtwofish/twofish.h
new file mode 100644
index 000000000..9b289f265
--- /dev/null
+++ b/lib/libcrypto/libtwofish/twofish.h
@@ -0,0 +1,20 @@
+#ifndef TWOFISH_H
+#define TWOFISH_H
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
+/* Structure for an expanded Twofish key.  s contains the key-dependent
+ * S-boxes composed with the MDS matrix; w contains the eight "whitening"
+ * subkeys, K[0] through K[7].	k holds the remaining, "round" subkeys.  Note
+ * that k[i] corresponds to what the Twofish paper calls K[i+8]. */
+typedef struct {
+   u_int32_t s[4][256], w[8], k[32];
+} TWOFISH_context;
+
+typedef TWOFISH_context twofish_context;
+int twofish_set_key(twofish_context *tf_ctx, const u_int8_t * in_key, int key_len);
+int twofish_encrypt(twofish_context *tf_ctx, const u_int8_t * in, u_int8_t * out);
+int twofish_decrypt(twofish_context * tf_ctx, const u_int8_t * in, u_int8_t * out);
+#endif /* TWOFISH_H */
diff --git a/lib/libcrypto/libtwofish/twofish_cbc.c b/lib/libcrypto/libtwofish/twofish_cbc.c
new file mode 100644
index 000000000..6e5cf9025
--- /dev/null
+++ b/lib/libcrypto/libtwofish/twofish_cbc.c
@@ -0,0 +1,8 @@
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <sys/types.h>
+#endif
+#include "twofish_cbc.h"
+#include "cbc_generic.h"
+CBC_IMPL_BLK16(twofish_cbc_encrypt, twofish_context, u_int8_t *, twofish_encrypt, twofish_decrypt);
diff --git a/lib/libcrypto/libtwofish/twofish_cbc.h b/lib/libcrypto/libtwofish/twofish_cbc.h
new file mode 100644
index 000000000..9fdea3526
--- /dev/null
+++ b/lib/libcrypto/libtwofish/twofish_cbc.h
@@ -0,0 +1,3 @@
+/* Glue header */
+#include "twofish.h"
+int twofish_cbc_encrypt(twofish_context *ctx, const u_int8_t * in, u_int8_t * out, int ilen, const u_int8_t* iv, int encrypt);
diff --git a/lib/libcrypto/perlasm/LICENSE b/lib/libcrypto/perlasm/LICENSE
new file mode 100644
index 000000000..3fd259ac3
--- /dev/null
+++ b/lib/libcrypto/perlasm/LICENSE
@@ -0,0 +1,127 @@
+
+  LICENSE ISSUES
+  ==============
+
+  The OpenSSL toolkit stays under a dual license, i.e. both the conditions of
+  the OpenSSL License and the original SSLeay license apply to the toolkit.
+  See below for the actual license texts. Actually both licenses are BSD-style
+  Open Source licenses. In case of any license issues related to OpenSSL
+  please contact openssl-core@openssl.org.
+
+  OpenSSL License
+  ---------------
+
+/* ====================================================================
+ * Copyright (c) 1998-2001 The OpenSSL Project.  All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer. 
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * 3. All advertising materials mentioning features or use of this
+ *    software must display the following acknowledgment:
+ *    "This product includes software developed by the OpenSSL Project
+ *    for use in the OpenSSL Toolkit. (http://www.openssl.org/)"
+ *
+ * 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
+ *    endorse or promote products derived from this software without
+ *    prior written permission. For written permission, please contact
+ *    openssl-core@openssl.org.
+ *
+ * 5. Products derived from this software may not be called "OpenSSL"
+ *    nor may "OpenSSL" appear in their names without prior written
+ *    permission of the OpenSSL Project.
+ *
+ * 6. Redistributions of any form whatsoever must retain the following
+ *    acknowledgment:
+ *    "This product includes software developed by the OpenSSL Project
+ *    for use in the OpenSSL Toolkit (http://www.openssl.org/)"
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
+ * EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE OpenSSL PROJECT OR
+ * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+ * ====================================================================
+ *
+ * This product includes cryptographic software written by Eric Young
+ * (eay@cryptsoft.com).  This product includes software written by Tim
+ * Hudson (tjh@cryptsoft.com).
+ *
+ */
+
+ Original SSLeay License
+ -----------------------
+
+/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
+ * All rights reserved.
+ *
+ * This package is an SSL implementation written
+ * by Eric Young (eay@cryptsoft.com).
+ * The implementation was written so as to conform with Netscapes SSL.
+ * 
+ * This library is free for commercial and non-commercial use as long as
+ * the following conditions are aheared to.  The following conditions
+ * apply to all code found in this distribution, be it the RC4, RSA,
+ * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
+ * included with this distribution is covered by the same copyright terms
+ * except that the holder is Tim Hudson (tjh@cryptsoft.com).
+ * 
+ * Copyright remains Eric Young's, and as such any Copyright notices in
+ * the code are not to be removed.
+ * If this package is used in a product, Eric Young should be given attribution
+ * as the author of the parts of the library used.
+ * This can be in the form of a textual message at program startup or
+ * in documentation (online or textual) provided with the package.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *    "This product includes cryptographic software written by
+ *     Eric Young (eay@cryptsoft.com)"
+ *    The word 'cryptographic' can be left out if the rouines from the library
+ *    being used are not cryptographic related :-).
+ * 4. If you include any Windows specific code (or a derivative thereof) from 
+ *    the apps directory (application code) you must include an acknowledgement:
+ *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
+ * 
+ * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * The licence and distribution terms for any publically available version or
+ * derivative of this code cannot be changed.  i.e. this code cannot simply be
+ * copied and put under another distribution licence
+ * [including the GNU Public Licence.]
+ */
+
diff --git a/lib/libcrypto/perlasm/alpha.pl b/lib/libcrypto/perlasm/alpha.pl
new file mode 100644
index 000000000..fe69ca5a3
--- /dev/null
+++ b/lib/libcrypto/perlasm/alpha.pl
@@ -0,0 +1,434 @@
+#!/usr/bin/perl
+
+package alpha;
+use Carp qw(croak cluck);
+
+$label="100";
+
+$n_debug=0;
+$smear_regs=1;
+$reg_alloc=1;
+
+$align="3";
+$com_start="#";
+
+sub main'asm_init_output { @out=(); }
+sub main'asm_get_output { return(@out); }
+sub main'get_labels { return(@labels); }
+sub main'external_label { push(@labels,@_); }
+
+# General registers
+
+%regs=(	'r0',	'$0',
+	'r1',	'$1',
+	'r2',	'$2',
+	'r3',	'$3',
+	'r4',	'$4',
+	'r5',	'$5',
+	'r6',	'$6',
+	'r7',	'$7',
+	'r8',	'$8',
+	'r9',	'$22',
+	'r10',	'$23',
+	'r11',	'$24',
+	'r12',	'$25',
+	'r13',	'$27',
+	'r14',	'$28',
+	'r15',	'$21', # argc == 5
+	'r16',	'$20', # argc == 4
+	'r17',	'$19', # argc == 3
+	'r18',	'$18', # argc == 2
+	'r19',	'$17', # argc == 1
+	'r20',	'$16', # argc == 0
+	'r21',	'$9',  # save 0
+	'r22',	'$10', # save 1
+	'r23',	'$11', # save 2
+	'r24',	'$12', # save 3
+	'r25',	'$13', # save 4
+	'r26',	'$14', # save 5
+
+	'a0',	'$16',
+	'a1',	'$17',
+	'a2',	'$18',
+	'a3',	'$19',
+	'a4',	'$20',
+	'a5',	'$21',
+
+	's0',	'$9',
+	's1',	'$10',
+	's2',	'$11',
+	's3',	'$12',
+	's4',	'$13',
+	's5',	'$14',
+	'zero',	'$31',
+	'sp',	'$30',
+	);
+
+$main'reg_s0="r21";
+$main'reg_s1="r22";
+$main'reg_s2="r23";
+$main'reg_s3="r24";
+$main'reg_s4="r25";
+$main'reg_s5="r26";
+
+@reg=(  '$0', '$1' ,'$2' ,'$3' ,'$4' ,'$5' ,'$6' ,'$7' ,'$8',
+	'$22','$23','$24','$25','$20','$21','$27','$28');
+
+
+sub main'sub	{ &out3("subq",@_); }
+sub main'add	{ &out3("addq",@_); }
+sub main'mov	{ &out3("bis",$_[0],$_[0],$_[1]); }
+sub main'or	{ &out3("bis",@_); }
+sub main'bis	{ &out3("bis",@_); }
+sub main'br	{ &out1("br",@_); }
+sub main'ld	{ &out2("ldq",@_); }
+sub main'st	{ &out2("stq",@_); }
+sub main'cmpult	{ &out3("cmpult",@_); }
+sub main'cmplt	{ &out3("cmplt",@_); }
+sub main'bgt	{ &out2("bgt",@_); }
+sub main'ble	{ &out2("ble",@_); }
+sub main'blt	{ &out2("blt",@_); }
+sub main'mul	{ &out3("mulq",@_); }
+sub main'muh	{ &out3("umulh",@_); }
+
+$main'QWS=8;
+
+sub main'asm_add
+	{
+	push(@out,@_);
+	}
+
+sub main'asm_finish
+	{
+	&main'file_end();
+	print &main'asm_get_output();
+	}
+
+sub main'asm_init
+	{
+	($type,$fn)=@_;
+	$filename=$fn;
+
+	&main'asm_init_output();
+	&main'comment("Don't even think of reading this code");
+	&main'comment("It was automatically generated by $filename");
+	&main'comment("Which is a perl program used to generate the alpha assember.");
+	&main'comment("eric <eay\@cryptsoft.com>");
+	&main'comment("");
+
+	$filename =~ s/\.pl$//;
+	&main'file($filename);
+	}
+
+sub conv
+	{
+	local($r)=@_;
+	local($v);
+
+	return($regs{$r}) if defined($regs{$r});
+	return($r);
+	}
+
+sub main'QWPw
+	{
+	local($off,$reg)=@_;
+
+	return(&main'QWP($off*8,$reg));
+	}
+
+sub main'QWP
+	{
+	local($off,$reg)=@_;
+
+	$ret="$off(".&conv($reg).")";
+	return($ret);
+	}
+
+sub out3
+	{
+	local($name,$p1,$p2,$p3)=@_;
+
+	$p1=&conv($p1);
+	$p2=&conv($p2);
+	$p3=&conv($p3);
+	push(@out,"\t$name\t");
+	$l=length($p1)+1;
+	push(@out,$p1.",");
+	$ll=3-($l+9)/8;
+	$tmp1=sprintf("\t" x $ll);
+	push(@out,$tmp1);
+
+	$l=length($p2)+1;
+	push(@out,$p2.",");
+	$ll=3-($l+9)/8;
+	$tmp1=sprintf("\t" x $ll);
+	push(@out,$tmp1);
+
+	push(@out,&conv($p3)."\n");
+	}
+
+sub out2
+	{
+	local($name,$p1,$p2,$p3)=@_;
+
+	$p1=&conv($p1);
+	$p2=&conv($p2);
+	push(@out,"\t$name\t");
+	$l=length($p1)+1;
+	push(@out,$p1.",");
+	$ll=3-($l+9)/8;
+	$tmp1=sprintf("\t" x $ll);
+	push(@out,$tmp1);
+
+	push(@out,&conv($p2)."\n");
+	}
+
+sub out1
+	{
+	local($name,$p1)=@_;
+
+	$p1=&conv($p1);
+	push(@out,"\t$name\t".$p1."\n");
+	}
+
+sub out0
+	{
+	push(@out,"\t$_[0]\n");
+	}
+
+sub main'file
+	{
+	local($file)=@_;
+
+	local($tmp)=<<"EOF";
+ # DEC Alpha assember
+ # Generated from perl scripts contains in SSLeay
+	.file	1 "$file.s"
+	.set noat
+EOF
+	push(@out,$tmp);
+	}
+
+sub main'function_begin
+	{
+	local($func)=@_;
+
+print STDERR "$func\n";
+	local($tmp)=<<"EOF";
+	.text
+	.align $align
+	.globl $func
+	.ent $func
+${func}:
+${func}..ng:
+	.frame \$30,0,\$26,0
+	.prologue 0
+EOF
+	push(@out,$tmp);
+	$stack=0;
+	}
+
+sub main'function_end
+	{
+	local($func)=@_;
+
+	local($tmp)=<<"EOF";
+	ret	\$31,(\$26),1
+	.end $func
+EOF
+	push(@out,$tmp);
+	$stack=0;
+	%label=();
+	}
+
+sub main'function_end_A
+	{
+	local($func)=@_;
+
+	local($tmp)=<<"EOF";
+	ret	\$31,(\$26),1
+EOF
+	push(@out,$tmp);
+	}
+
+sub main'function_end_B
+	{
+	local($func)=@_;
+
+	$func=$under.$func;
+
+	push(@out,"\t.end $func\n");
+	$stack=0;
+	%label=();
+	}
+
+sub main'wparam
+	{
+	local($num)=@_;
+
+	if ($num < 6)
+		{
+		$num=20-$num;
+		return("r$num");
+		}
+	else
+		{ return(&main'QWP($stack+$num*8,"sp")); }
+	}
+
+sub main'stack_push
+	{
+	local($num)=@_;
+	$stack+=$num*8;
+	&main'sub("sp",$num*8,"sp");
+	}
+
+sub main'stack_pop
+	{
+	local($num)=@_;
+	$stack-=$num*8;
+	&main'add("sp",$num*8,"sp");
+	}
+
+sub main'swtmp
+	{
+	return(&main'QWP(($_[0])*8,"sp"));
+	}
+
+# Should use swtmp, which is above sp.  Linix can trash the stack above esp
+#sub main'wtmp
+#	{
+#	local($num)=@_;
+#
+#	return(&main'QWP(-($num+1)*4,"esp","",0));
+#	}
+
+sub main'comment
+	{
+	foreach (@_)
+		{
+		if (/^\s*$/)
+			{ push(@out,"\n"); }
+		else
+			{ push(@out,"\t$com_start $_ $com_end\n"); }
+		}
+	}
+
+sub main'label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}=$label;
+		$label++;
+		}
+	return('$'.$label{$_[0]});
+	}
+
+sub main'set_label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}=$label;
+		$label++;
+		}
+#	push(@out,".align $align\n") if ($_[1] != 0);
+	push(@out,'$'."$label{$_[0]}:\n");
+	}
+
+sub main'file_end
+	{
+	}
+
+sub main'data_word
+	{
+	push(@out,"\t.long $_[0]\n");
+	}
+
+@pool_free=();
+@pool_taken=();
+$curr_num=0;
+$max=0;
+
+sub main'init_pool
+	{
+	local($args)=@_;
+	local($i);
+
+	@pool_free=();
+	for ($i=(14+(6-$args)); $i >= 0; $i--)
+		{
+		push(@pool_free,"r$i");
+		}
+	print STDERR "START :register pool:@pool_free\n";
+	$curr_num=$max=0;
+	}
+
+sub main'fin_pool
+	{
+	printf STDERR "END %2d:register pool:@pool_free\n",$max;
+	}
+
+sub main'GR
+	{
+	local($r)=@_;
+	local($i,@n,$_);
+
+	foreach (@pool_free)
+		{
+		if ($r ne $_)
+			{ push(@n,$_); }
+		else
+			{
+			$curr_num++;
+			$max=$curr_num if ($curr_num > $max);
+			}
+		}
+	@pool_free=@n;
+print STDERR "GR:@pool_free\n" if $reg_alloc;
+	return(@_);
+	}
+
+sub main'NR
+	{
+	local($num)=@_;
+	local(@ret);
+
+	$num=1 if $num == 0;
+	($#pool_free >= ($num-1)) || croak "out of registers: want $num, have @pool_free";
+	while ($num > 0)
+		{
+		push(@ret,pop @pool_free);
+		$curr_num++;
+		$max=$curr_num if ($curr_num > $max);
+		$num--
+		}
+	print STDERR "nr @ret\n" if $n_debug;
+print STDERR "NR:@pool_free\n" if $reg_alloc;
+	return(@ret);
+
+	}
+
+sub main'FR
+	{
+	local(@r)=@_;
+	local(@a,$v,$w);
+
+	print STDERR "fr @r\n" if $n_debug;
+#	cluck "fr @r";
+	for $w (@pool_free)
+		{
+		foreach $v (@r)
+			{
+			croak "double register free of $v (@pool_free)" if $w eq $v;
+			}
+		}
+	foreach $v (@r)
+		{
+		croak "bad argument to FR" if ($v !~ /^r\d+$/);
+		if ($smear_regs)
+			{ unshift(@pool_free,$v); }
+		else	{ push(@pool_free,$v); }
+		$curr_num--;
+		}
+print STDERR "FR:@pool_free\n" if $reg_alloc;
+	}
+1;
diff --git a/lib/libcrypto/perlasm/cbc.pl b/lib/libcrypto/perlasm/cbc.pl
new file mode 100644
index 000000000..278930579
--- /dev/null
+++ b/lib/libcrypto/perlasm/cbc.pl
@@ -0,0 +1,342 @@
+#!/usr/bin/perl
+
+# void des_ncbc_encrypt(input, output, length, schedule, ivec, enc)
+# des_cblock (*input);
+# des_cblock (*output);
+# long length;
+# des_key_schedule schedule;
+# des_cblock (*ivec);
+# int enc;
+#
+# calls 
+# des_encrypt((DES_LONG *)tin,schedule,DES_ENCRYPT);
+#
+
+#&cbc("des_ncbc_encrypt","des_encrypt",0);
+#&cbc("BF_cbc_encrypt","BF_encrypt","BF_encrypt",
+#	1,4,5,3,5,-1);
+#&cbc("des_ncbc_encrypt","des_encrypt","des_encrypt",
+#	0,4,5,3,5,-1);
+#&cbc("des_ede3_cbc_encrypt","des_encrypt3","des_decrypt3",
+#	0,6,7,3,4,5);
+#
+# When doing a cipher that needs bigendian order,
+# for encrypt, the iv is kept in bigendian form,
+# while for decrypt, it is kept in little endian.
+sub cbc
+	{
+	local($name,$enc_func,$dec_func,$swap,$iv_off,$enc_off,$p1,$p2,$p3)=@_;
+	# name is the function name
+	# enc_func and dec_func and the functions to call for encrypt/decrypt
+	# swap is true if byte order needs to be reversed
+	# iv_off is parameter number for the iv 
+	# enc_off is parameter number for the encrypt/decrypt flag
+	# p1,p2,p3 are the offsets for parameters to be passed to the
+	# underlying calls.
+
+	&function_begin_B($name,"");
+	&comment("");
+
+	$in="esi";
+	$out="edi";
+	$count="ebp";
+
+	&push("ebp");
+	&push("ebx");
+	&push("esi");
+	&push("edi");
+
+	$data_off=4;
+	$data_off+=4 if ($p1 > 0);
+	$data_off+=4 if ($p2 > 0);
+	$data_off+=4 if ($p3 > 0);
+
+	&mov($count,	&wparam(2));	# length
+
+	&comment("getting iv ptr from parameter $iv_off");
+	&mov("ebx",	&wparam($iv_off));	# Get iv ptr
+
+	&mov($in,	&DWP(0,"ebx","",0));#	iv[0]
+	&mov($out,	&DWP(4,"ebx","",0));#	iv[1]
+
+	&push($out);
+	&push($in);
+	&push($out);	# used in decrypt for iv[1]
+	&push($in);	# used in decrypt for iv[0]
+
+	&mov("ebx",	"esp");		# This is the address of tin[2]
+
+	&mov($in,	&wparam(0));	# in
+	&mov($out,	&wparam(1));	# out
+
+	# We have loaded them all, how lets push things
+	&comment("getting encrypt flag from parameter $enc_off");
+	&mov("ecx",	&wparam($enc_off));	# Get enc flag
+	if ($p3 > 0)
+		{
+		&comment("get and push parameter $p3");
+		if ($enc_off != $p3)
+			{ &mov("eax",	&wparam($p3)); &push("eax"); }
+		else	{ &push("ecx"); }
+		}
+	if ($p2 > 0)
+		{
+		&comment("get and push parameter $p2");
+		if ($enc_off != $p2)
+			{ &mov("eax",	&wparam($p2)); &push("eax"); }
+		else	{ &push("ecx"); }
+		}
+	if ($p1 > 0)
+		{
+		&comment("get and push parameter $p1");
+		if ($enc_off != $p1)
+			{ &mov("eax",	&wparam($p1)); &push("eax"); }
+		else	{ &push("ecx"); }
+		}
+	&push("ebx");		# push data/iv
+
+	&cmp("ecx",0);
+	&jz(&label("decrypt"));
+
+	&and($count,0xfffffff8);
+	&mov("eax",	&DWP($data_off,"esp","",0));	# load iv[0]
+	&mov("ebx",	&DWP($data_off+4,"esp","",0));	# load iv[1]
+
+	&jz(&label("encrypt_finish"));
+
+	#############################################################
+
+	&set_label("encrypt_loop");
+	# encrypt start 
+	# "eax" and "ebx" hold iv (or the last cipher text)
+
+	&mov("ecx",	&DWP(0,$in,"",0));	# load first 4 bytes
+	&mov("edx",	&DWP(4,$in,"",0));	# second 4 bytes
+
+	&xor("eax",	"ecx");
+	&xor("ebx",	"edx");
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov(&DWP($data_off,"esp","",0),	"eax");	# put in array for call
+	&mov(&DWP($data_off+4,"esp","",0),	"ebx");	#
+
+	&call($enc_func);
+
+	&mov("eax",	&DWP($data_off,"esp","",0));
+	&mov("ebx",	&DWP($data_off+4,"esp","",0));
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov(&DWP(0,$out,"",0),"eax");
+	&mov(&DWP(4,$out,"",0),"ebx");
+
+	# eax and ebx are the next iv.
+
+	&add($in,	8);
+	&add($out,	8);
+
+	&sub($count,	8);
+	&jnz(&label("encrypt_loop"));
+
+###################################################################3
+	&set_label("encrypt_finish");
+	&mov($count,	&wparam(2));	# length
+	&and($count,	7);
+	&jz(&label("finish"));
+	&xor("ecx","ecx");
+	&xor("edx","edx");
+	&mov($count,&DWP(&label("cbc_enc_jmp_table"),"",$count,4));
+	&jmp_ptr($count);
+
+&set_label("ej7");
+	&xor("edx",		"edx") if $ppro; # ppro friendly
+	&movb(&HB("edx"),	&BP(6,$in,"",0));
+	&shl("edx",8);
+&set_label("ej6");
+	&movb(&HB("edx"),	&BP(5,$in,"",0));
+&set_label("ej5");
+	&movb(&LB("edx"),	&BP(4,$in,"",0));
+&set_label("ej4");
+	&mov("ecx",		&DWP(0,$in,"",0));
+	&jmp(&label("ejend"));
+&set_label("ej3");
+	&movb(&HB("ecx"),	&BP(2,$in,"",0));
+	&xor("ecx",		"ecx") if $ppro; # ppro friendly
+	&shl("ecx",8);
+&set_label("ej2");
+	&movb(&HB("ecx"),	&BP(1,$in,"",0));
+&set_label("ej1");
+	&movb(&LB("ecx"),	&BP(0,$in,"",0));
+&set_label("ejend");
+
+	&xor("eax",	"ecx");
+	&xor("ebx",	"edx");
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov(&DWP($data_off,"esp","",0),	"eax");	# put in array for call
+	&mov(&DWP($data_off+4,"esp","",0),	"ebx");	#
+
+	&call($enc_func);
+
+	&mov("eax",	&DWP($data_off,"esp","",0));
+	&mov("ebx",	&DWP($data_off+4,"esp","",0));
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov(&DWP(0,$out,"",0),"eax");
+	&mov(&DWP(4,$out,"",0),"ebx");
+
+	&jmp(&label("finish"));
+
+	#############################################################
+	#############################################################
+	&set_label("decrypt",1);
+	# decrypt start 
+	&and($count,0xfffffff8);
+	# The next 2 instructions are only for if the jz is taken
+	&mov("eax",	&DWP($data_off+8,"esp","",0));	# get iv[0]
+	&mov("ebx",	&DWP($data_off+12,"esp","",0));	# get iv[1]
+	&jz(&label("decrypt_finish"));
+
+	&set_label("decrypt_loop");
+	&mov("eax",	&DWP(0,$in,"",0));	# load first 4 bytes
+	&mov("ebx",	&DWP(4,$in,"",0));	# second 4 bytes
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov(&DWP($data_off,"esp","",0),	"eax");	# put back
+	&mov(&DWP($data_off+4,"esp","",0),	"ebx");	#
+
+	&call($dec_func);
+
+	&mov("eax",	&DWP($data_off,"esp","",0));	# get return
+	&mov("ebx",	&DWP($data_off+4,"esp","",0));	#
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov("ecx",	&DWP($data_off+8,"esp","",0));	# get iv[0]
+	&mov("edx",	&DWP($data_off+12,"esp","",0));	# get iv[1]
+
+	&xor("ecx",	"eax");
+	&xor("edx",	"ebx");
+
+	&mov("eax",	&DWP(0,$in,"",0));	# get old cipher text,
+	&mov("ebx",	&DWP(4,$in,"",0));	# next iv actually
+
+	&mov(&DWP(0,$out,"",0),"ecx");
+	&mov(&DWP(4,$out,"",0),"edx");
+
+	&mov(&DWP($data_off+8,"esp","",0),	"eax");	# save iv
+	&mov(&DWP($data_off+12,"esp","",0),	"ebx");	#
+
+	&add($in,	8);
+	&add($out,	8);
+
+	&sub($count,	8);
+	&jnz(&label("decrypt_loop"));
+############################ ENDIT #######################3
+	&set_label("decrypt_finish");
+	&mov($count,	&wparam(2));	# length
+	&and($count,	7);
+	&jz(&label("finish"));
+
+	&mov("eax",	&DWP(0,$in,"",0));	# load first 4 bytes
+	&mov("ebx",	&DWP(4,$in,"",0));	# second 4 bytes
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov(&DWP($data_off,"esp","",0),	"eax");	# put back
+	&mov(&DWP($data_off+4,"esp","",0),	"ebx");	#
+
+	&call($dec_func);
+
+	&mov("eax",	&DWP($data_off,"esp","",0));	# get return
+	&mov("ebx",	&DWP($data_off+4,"esp","",0));	#
+
+	&bswap("eax")	if $swap;
+	&bswap("ebx")	if $swap;
+
+	&mov("ecx",	&DWP($data_off+8,"esp","",0));	# get iv[0]
+	&mov("edx",	&DWP($data_off+12,"esp","",0));	# get iv[1]
+
+	&xor("ecx",	"eax");
+	&xor("edx",	"ebx");
+
+	# this is for when we exit
+	&mov("eax",	&DWP(0,$in,"",0));	# get old cipher text,
+	&mov("ebx",	&DWP(4,$in,"",0));	# next iv actually
+
+&set_label("dj7");
+	&rotr("edx",	16);
+	&movb(&BP(6,$out,"",0),	&LB("edx"));
+	&shr("edx",16);
+&set_label("dj6");
+	&movb(&BP(5,$out,"",0),	&HB("edx"));
+&set_label("dj5");
+	&movb(&BP(4,$out,"",0),	&LB("edx"));
+&set_label("dj4");
+	&mov(&DWP(0,$out,"",0),	"ecx");
+	&jmp(&label("djend"));
+&set_label("dj3");
+	&rotr("ecx",	16);
+	&movb(&BP(2,$out,"",0),	&LB("ecx"));
+	&shl("ecx",16);
+&set_label("dj2");
+	&movb(&BP(1,$in,"",0),	&HB("ecx"));
+&set_label("dj1");
+	&movb(&BP(0,$in,"",0),	&LB("ecx"));
+&set_label("djend");
+
+	# final iv is still in eax:ebx
+	&jmp(&label("finish"));
+
+
+############################ FINISH #######################3
+	&set_label("finish",1);
+	&mov("ecx",	&wparam($iv_off));	# Get iv ptr
+
+	#################################################
+	$total=16+4;
+	$total+=4 if ($p1 > 0);
+	$total+=4 if ($p2 > 0);
+	$total+=4 if ($p3 > 0);
+	&add("esp",$total);
+
+	&mov(&DWP(0,"ecx","",0),	"eax");	# save iv
+	&mov(&DWP(4,"ecx","",0),	"ebx");	# save iv
+
+	&function_end_A($name);
+
+	&set_label("cbc_enc_jmp_table",1);
+	&data_word("0");
+	&data_word(&label("ej1"));
+	&data_word(&label("ej2"));
+	&data_word(&label("ej3"));
+	&data_word(&label("ej4"));
+	&data_word(&label("ej5"));
+	&data_word(&label("ej6"));
+	&data_word(&label("ej7"));
+	&set_label("cbc_dec_jmp_table",1);
+	&data_word("0");
+	&data_word(&label("dj1"));
+	&data_word(&label("dj2"));
+	&data_word(&label("dj3"));
+	&data_word(&label("dj4"));
+	&data_word(&label("dj5"));
+	&data_word(&label("dj6"));
+	&data_word(&label("dj7"));
+
+	&function_end_B($name);
+	
+	}
+
+1;
diff --git a/lib/libcrypto/perlasm/readme b/lib/libcrypto/perlasm/readme
new file mode 100644
index 000000000..f02bbee75
--- /dev/null
+++ b/lib/libcrypto/perlasm/readme
@@ -0,0 +1,124 @@
+The perl scripts in this directory are my 'hack' to generate
+multiple different assembler formats via the one origional script.
+
+The way to use this library is to start with adding the path to this directory
+and then include it.
+
+push(@INC,"perlasm","../../perlasm");
+require "x86asm.pl";
+
+The first thing we do is setup the file and type of assember
+
+&asm_init($ARGV[0],$0);
+
+The first argument is the 'type'.  Currently
+'cpp', 'sol', 'a.out', 'elf' or 'win32'.
+Argument 2 is the file name.
+
+The reciprocal function is
+&asm_finish() which should be called at the end.
+
+There are 2 main 'packages'. x86ms.pl, which is the microsoft assembler,
+and x86unix.pl which is the unix (gas) version.
+
+Functions of interest are:
+&external_label("des_SPtrans");	declare and external variable
+&LB(reg);			Low byte for a register
+&HB(reg);			High byte for a register
+&BP(off,base,index,scale)	Byte pointer addressing
+&DWP(off,base,index,scale)	Word pointer addressing
+&stack_push(num)		Basically a 'sub esp, num*4' with extra
+&stack_pop(num)			inverse of stack_push
+&function_begin(name,extra)	Start a function with pushing of
+				edi, esi, ebx and ebp.  extra is extra win32
+				external info that may be required.
+&function_begin_B(name,extra)	Same as norma function_begin but no pushing.
+&function_end(name)		Call at end of function.
+&function_end_A(name)		Standard pop and ret, for use inside functions
+&function_end_B(name)		Call at end but with poping or 'ret'.
+&swtmp(num)			Address on stack temp word.
+&wparam(num)			Parameter number num, that was push
+				in C convention.  This all works over pushes
+				and pops.
+&comment("hello there")		Put in a comment.
+&label("loop")			Refer to a label, normally a jmp target.
+&set_label("loop")		Set a label at this point.
+&data_word(word)		Put in a word of data.
+
+So how does this all hold together?  Given
+
+int calc(int len, int *data)
+	{
+	int i,j=0;
+
+	for (i=0; i<len; i++)
+		{
+		j+=other(data[i]);
+		}
+	}
+
+So a very simple version of this function could be coded as
+
+	push(@INC,"perlasm","../../perlasm");
+	require "x86asm.pl";
+	
+	&asm_init($ARGV[0],"cacl.pl");
+
+	&external_label("other");
+
+	$tmp1=	"eax";
+	$j=	"edi";
+	$data=	"esi";
+	$i=	"ebp";
+
+	&comment("a simple function");
+	&function_begin("calc");
+	&mov(	$data,		&wparam(1)); # data
+	&xor(	$j,		$j);
+	&xor(	$i,		$i);
+
+	&set_label("loop");
+	&cmp(	$i,		&wparam(0));
+	&jge(	&label("end"));
+
+	&mov(	$tmp1,		&DWP(0,$data,$i,4));
+	&push(	$tmp1);
+	&call(	"other");
+	&add(	$j,		"eax");
+	&pop(	$tmp1);
+	&inc(	$i);
+	&jmp(	&label("loop"));
+
+	&set_label("end");
+	&mov(	"eax",		$j);
+
+	&function_end("calc");
+
+	&asm_finish();
+
+The above example is very very unoptimised but gives an idea of how
+things work.
+
+There is also a cbc mode function generator in cbc.pl
+
+&cbc(	$name,
+	$encrypt_function_name,
+	$decrypt_function_name,
+	$true_if_byte_swap_needed,
+	$parameter_number_for_iv,
+	$parameter_number_for_encrypt_flag,
+	$first_parameter_to_pass,
+	$second_parameter_to_pass,
+	$third_parameter_to_pass);
+
+So for example, given
+void BF_encrypt(BF_LONG *data,BF_KEY *key);
+void BF_decrypt(BF_LONG *data,BF_KEY *key);
+void BF_cbc_encrypt(unsigned char *in, unsigned char *out, long length,
+        BF_KEY *ks, unsigned char *iv, int enc);
+
+&cbc("BF_cbc_encrypt","BF_encrypt","BF_encrypt",1,4,5,3,-1,-1);
+
+&cbc("des_ncbc_encrypt","des_encrypt","des_encrypt",0,4,5,3,5,-1);
+&cbc("des_ede3_cbc_encrypt","des_encrypt3","des_decrypt3",0,6,7,3,4,5);
+
diff --git a/lib/libcrypto/perlasm/version b/lib/libcrypto/perlasm/version
new file mode 100644
index 000000000..5e62822b4
--- /dev/null
+++ b/lib/libcrypto/perlasm/version
@@ -0,0 +1,5 @@
+version,v 1.1.2.1 2003/11/21 18:12:23 jjo Exp
+
+This version of perlasm was copied from the openssl 0.9.6c distribution
+
+The license applying to it is enclose in the LICENSE file
diff --git a/lib/libcrypto/perlasm/x86asm.pl b/lib/libcrypto/perlasm/x86asm.pl
new file mode 100644
index 000000000..8af0fd17f
--- /dev/null
+++ b/lib/libcrypto/perlasm/x86asm.pl
@@ -0,0 +1,118 @@
+#!/usr/bin/perl
+
+# require 'x86asm.pl';
+# &asm_init("cpp","des-586.pl");
+# XXX
+# XXX
+# main'asm_finish
+
+sub main'asm_finish
+	{
+	&file_end();
+	&asm_finish_cpp() if $cpp;
+	print &asm_get_output();
+	}
+
+sub main'asm_init
+	{
+	($type,$fn,$i386)=@_;
+	$filename=$fn;
+
+	$cpp=$sol=$aout=$win32=$gaswin=0;
+	if (	($type eq "elf"))
+		{ require "x86unix.pl"; }
+	elsif (	($type eq "a.out"))
+		{ $aout=1; require "x86unix.pl"; }
+	elsif (	($type eq "gaswin"))
+		{ $gaswin=1; $aout=1; require "x86unix.pl"; }
+	elsif (	($type eq "sol"))
+		{ $sol=1; require "x86unix.pl"; }
+	elsif (	($type eq "cpp"))
+		{ $cpp=1; require "x86unix.pl"; }
+	elsif (	($type eq "win32"))
+		{ $win32=1; require "x86ms.pl"; }
+	elsif (	($type eq "win32n"))
+		{ $win32=1; require "x86nasm.pl"; }
+	else
+		{
+		print STDERR <<"EOF";
+Pick one target type from
+	elf	- linux, FreeBSD etc
+	a.out	- old linux
+	sol	- x86 solaris
+	cpp	- format so x86unix.cpp can be used
+	win32	- Windows 95/Windows NT
+	win32n	- Windows 95/Windows NT NASM format
+EOF
+		exit(1);
+		}
+
+	&asm_init_output();
+
+&comment("Don't even think of reading this code");
+&comment("It was automatically generated by $filename");
+&comment("Which is a perl program used to generate the x86 assember for");
+&comment("any of elf, a.out, BSDI, Win32, gaswin (for GNU as on Win32) or Solaris");
+&comment("eric <eay\@cryptsoft.com>");
+&comment("");
+
+	$filename =~ s/\.pl$//;
+	&file($filename);
+	}
+
+sub asm_finish_cpp
+	{
+	return unless $cpp;
+
+	local($tmp,$i);
+	foreach $i (&get_labels())
+		{
+		$tmp.="#define $i _$i\n";
+		}
+	print <<"EOF";
+/* Run the C pre-processor over this file with one of the following defined
+ * ELF - elf object files,
+ * OUT - a.out object files,
+ * BSDI - BSDI style a.out object files
+ * SOL - Solaris style elf
+ */
+
+#define TYPE(a,b)       .type   a,b
+#define SIZE(a,b)       .size   a,b
+
+#if defined(OUT) || (defined(BSDI) && !defined(ELF))
+$tmp
+#endif
+
+#ifdef OUT
+#define OK	1
+#define ALIGN	4
+#endif
+
+#if defined(BSDI) && !defined(ELF)
+#define OK              1
+#define ALIGN           4
+#undef SIZE
+#undef TYPE
+#define SIZE(a,b)
+#define TYPE(a,b)
+#endif
+
+#if defined(ELF) || defined(SOL)
+#define OK              1
+#define ALIGN           16
+#endif
+
+#ifndef OK
+You need to define one of
+ELF - elf systems - linux-elf, NetBSD and DG-UX
+OUT - a.out systems - linux-a.out and FreeBSD
+SOL - solaris systems, which are elf with strange comment lines
+BSDI - a.out with a very primative version of as.
+#endif
+
+/* Let the Assembler begin :-) */
+EOF
+	}
+
+1;
diff --git a/lib/libcrypto/perlasm/x86ms.pl b/lib/libcrypto/perlasm/x86ms.pl
new file mode 100644
index 000000000..c6212f434
--- /dev/null
+++ b/lib/libcrypto/perlasm/x86ms.pl
@@ -0,0 +1,365 @@
+#!/usr/bin/perl
+
+package x86ms;
+
+$label="L000";
+
+%lb=(	'eax',	'al',
+	'ebx',	'bl',
+	'ecx',	'cl',
+	'edx',	'dl',
+	'ax',	'al',
+	'bx',	'bl',
+	'cx',	'cl',
+	'dx',	'dl',
+	);
+
+%hb=(	'eax',	'ah',
+	'ebx',	'bh',
+	'ecx',	'ch',
+	'edx',	'dh',
+	'ax',	'ah',
+	'bx',	'bh',
+	'cx',	'ch',
+	'dx',	'dh',
+	);
+
+sub main'asm_init_output { @out=(); }
+sub main'asm_get_output { return(@out); }
+sub main'get_labels { return(@labels); }
+sub main'external_label { push(@labels,@_); }
+
+sub main'LB
+	{
+	(defined($lb{$_[0]})) || die "$_[0] does not have a 'low byte'\n";
+	return($lb{$_[0]});
+	}
+
+sub main'HB
+	{
+	(defined($hb{$_[0]})) || die "$_[0] does not have a 'high byte'\n";
+	return($hb{$_[0]});
+	}
+
+sub main'BP
+	{
+	&get_mem("BYTE",@_);
+	}
+
+sub main'DWP
+	{
+	&get_mem("DWORD",@_);
+	}
+
+sub main'BC
+	{
+	return @_;
+	}
+
+sub main'DWC
+	{
+	return @_;
+	}
+
+sub main'stack_push
+	{
+	local($num)=@_;
+	$stack+=$num*4;
+	&main'sub("esp",$num*4);
+	}
+
+sub main'stack_pop
+	{
+	local($num)=@_;
+	$stack-=$num*4;
+	&main'add("esp",$num*4);
+	}
+
+sub get_mem
+	{
+	local($size,$addr,$reg1,$reg2,$idx)=@_;
+	local($t,$post);
+	local($ret)="$size PTR ";
+
+	$addr =~ s/^\s+//;
+	if ($addr =~ /^(.+)\+(.+)$/)
+		{
+		$reg2=&conv($1);
+		$addr="_$2";
+		}
+	elsif ($addr =~ /^[_a-zA-Z]/)
+		{
+		$addr="_$addr";
+		}
+
+	$reg1="$regs{$reg1}" if defined($regs{$reg1});
+	$reg2="$regs{$reg2}" if defined($regs{$reg2});
+	if (($addr ne "") && ($addr ne 0))
+		{
+		if ($addr !~ /^-/)
+			{ $ret.=$addr; }
+		else	{ $post=$addr; }
+		}
+	if ($reg2 ne "")
+		{
+		$t="";
+		$t="*$idx" if ($idx != 0);
+		$reg1="+".$reg1 if ("$reg1$post" ne "");
+		$ret.="[$reg2$t$reg1$post]";
+		}
+	else
+		{
+		$ret.="[$reg1$post]"
+		}
+	return($ret);
+	}
+
+sub main'mov	{ &out2("mov",@_); }
+sub main'movb	{ &out2("mov",@_); }
+sub main'and	{ &out2("and",@_); }
+sub main'or	{ &out2("or",@_); }
+sub main'shl	{ &out2("shl",@_); }
+sub main'shr	{ &out2("shr",@_); }
+sub main'xor	{ &out2("xor",@_); }
+sub main'xorb	{ &out2("xor",@_); }
+sub main'add	{ &out2("add",@_); }
+sub main'adc	{ &out2("adc",@_); }
+sub main'sub	{ &out2("sub",@_); }
+sub main'rotl	{ &out2("rol",@_); }
+sub main'rotr	{ &out2("ror",@_); }
+sub main'exch	{ &out2("xchg",@_); }
+sub main'cmp	{ &out2("cmp",@_); }
+sub main'lea	{ &out2("lea",@_); }
+sub main'mul	{ &out1("mul",@_); }
+sub main'div	{ &out1("div",@_); }
+sub main'dec	{ &out1("dec",@_); }
+sub main'inc	{ &out1("inc",@_); }
+sub main'jmp	{ &out1("jmp",@_); }
+sub main'jmp_ptr { &out1p("jmp",@_); }
+sub main'je	{ &out1("je",@_); }
+sub main'jle	{ &out1("jle",@_); }
+sub main'jz	{ &out1("jz",@_); }
+sub main'jge	{ &out1("jge",@_); }
+sub main'jl	{ &out1("jl",@_); }
+sub main'jb	{ &out1("jb",@_); }
+sub main'jc	{ &out1("jc",@_); }
+sub main'jnc	{ &out1("jnc",@_); }
+sub main'jnz	{ &out1("jnz",@_); }
+sub main'jne	{ &out1("jne",@_); }
+sub main'jno	{ &out1("jno",@_); }
+sub main'push	{ &out1("push",@_); $stack+=4; }
+sub main'pop	{ &out1("pop",@_); $stack-=4; }
+sub main'bswap	{ &out1("bswap",@_); &using486(); }
+sub main'not	{ &out1("not",@_); }
+sub main'call	{ &out1("call",'_'.$_[0]); }
+sub main'ret	{ &out0("ret"); }
+sub main'nop	{ &out0("nop"); }
+
+sub out2
+	{
+	local($name,$p1,$p2)=@_;
+	local($l,$t);
+
+	push(@out,"\t$name\t");
+	$t=&conv($p1).",";
+	$l=length($t);
+	push(@out,$t);
+	$l=4-($l+9)/8;
+	push(@out,"\t" x $l);
+	push(@out,&conv($p2));
+	push(@out,"\n");
+	}
+
+sub out0
+	{
+	local($name)=@_;
+
+	push(@out,"\t$name\n");
+	}
+
+sub out1
+	{
+	local($name,$p1)=@_;
+	local($l,$t);
+
+	push(@out,"\t$name\t".&conv($p1)."\n");
+	}
+
+sub conv
+	{
+	local($p)=@_;
+
+	$p =~ s/0x([0-9A-Fa-f]+)/0$1h/;
+	return $p;
+	}
+
+sub using486
+	{
+	return if $using486;
+	$using486++;
+	grep(s/\.386/\.486/,@out);
+	}
+
+sub main'file
+	{
+	local($file)=@_;
+
+	local($tmp)=<<"EOF";
+	TITLE	$file.asm
+        .386
+.model FLAT
+EOF
+	push(@out,$tmp);
+	}
+
+sub main'function_begin
+	{
+	local($func,$extra)=@_;
+
+	push(@labels,$func);
+
+	local($tmp)=<<"EOF";
+_TEXT	SEGMENT
+PUBLIC	_$func
+$extra
+_$func PROC NEAR
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+EOF
+	push(@out,$tmp);
+	$stack=20;
+	}
+
+sub main'function_begin_B
+	{
+	local($func,$extra)=@_;
+
+	local($tmp)=<<"EOF";
+_TEXT	SEGMENT
+PUBLIC	_$func
+$extra
+_$func PROC NEAR
+EOF
+	push(@out,$tmp);
+	$stack=4;
+	}
+
+sub main'function_end
+	{
+	local($func)=@_;
+
+	local($tmp)=<<"EOF";
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
+_$func ENDP
+_TEXT	ENDS
+EOF
+	push(@out,$tmp);
+	$stack=0;
+	%label=();
+	}
+
+sub main'function_end_B
+	{
+	local($func)=@_;
+
+	local($tmp)=<<"EOF";
+_$func ENDP
+_TEXT	ENDS
+EOF
+	push(@out,$tmp);
+	$stack=0;
+	%label=();
+	}
+
+sub main'function_end_A
+	{
+	local($func)=@_;
+
+	local($tmp)=<<"EOF";
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
+EOF
+	push(@out,$tmp);
+	}
+
+sub main'file_end
+	{
+	push(@out,"END\n");
+	}
+
+sub main'wparam
+	{
+	local($num)=@_;
+
+	return(&main'DWP($stack+$num*4,"esp","",0));
+	}
+
+sub main'swtmp
+	{
+	return(&main'DWP($_[0]*4,"esp","",0));
+	}
+
+# Should use swtmp, which is above esp.  Linix can trash the stack above esp
+#sub main'wtmp
+#	{
+#	local($num)=@_;
+#
+#	return(&main'DWP(-(($num+1)*4),"esp","",0));
+#	}
+
+sub main'comment
+	{
+	foreach (@_)
+		{
+		push(@out,"\t; $_\n");
+		}
+	}
+
+sub main'label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}="\$${label}${_[0]}";
+		$label++;
+		}
+	return($label{$_[0]});
+	}
+
+sub main'set_label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}="${label}${_[0]}";
+		$label++;
+		}
+	if((defined $_[2]) && ($_[2] == 1))
+		{
+		push(@out,"$label{$_[0]}::\n");
+		}
+	else
+		{
+		push(@out,"$label{$_[0]}:\n");
+		}
+	}
+
+sub main'data_word
+	{
+	push(@out,"\tDD\t$_[0]\n");
+	}
+
+sub out1p
+	{
+	local($name,$p1)=@_;
+	local($l,$t);
+
+	push(@out,"\t$name\t ".&conv($p1)."\n");
+	}
diff --git a/lib/libcrypto/perlasm/x86nasm.pl b/lib/libcrypto/perlasm/x86nasm.pl
new file mode 100644
index 000000000..90d27fca9
--- /dev/null
+++ b/lib/libcrypto/perlasm/x86nasm.pl
@@ -0,0 +1,366 @@
+#!/usr/bin/perl
+
+package x86nasm;
+
+$label="L000";
+
+%lb=(	'eax',	'al',
+	'ebx',	'bl',
+	'ecx',	'cl',
+	'edx',	'dl',
+	'ax',	'al',
+	'bx',	'bl',
+	'cx',	'cl',
+	'dx',	'dl',
+	);
+
+%hb=(	'eax',	'ah',
+	'ebx',	'bh',
+	'ecx',	'ch',
+	'edx',	'dh',
+	'ax',	'ah',
+	'bx',	'bh',
+	'cx',	'ch',
+	'dx',	'dh',
+	);
+
+%regs=(	'eax',	'eax',
+	'ebx',	'ebx',
+	'ecx',	'ecx',
+	'edx',	'edx',
+	'esi',	'esi',
+	'edi',	'edi',
+	'ebp',	'ebp',
+	'esp',	'esp',
+	'mm0',  'mm0',
+	'mm1',  'mm1',
+	);
+
+sub main::asm_init_output { @out=(); }
+sub main::asm_get_output { return(@out); }
+sub main::get_labels { return(@labels); }
+
+sub main::external_label
+{
+	push(@labels,@_);
+	foreach (@_) {
+		push(@out, "extern\t_$_\n");
+	}
+}
+
+sub main::LB
+	{
+	(defined($lb{$_[0]})) || die "$_[0] does not have a 'low byte'\n";
+	return($lb{$_[0]});
+	}
+
+sub main::HB
+	{
+	(defined($hb{$_[0]})) || die "$_[0] does not have a 'high byte'\n";
+	return($hb{$_[0]});
+	}
+
+sub main::BP
+	{
+	&get_mem("BYTE",@_);
+	}
+
+sub main::DWP
+	{
+	&get_mem("DWORD",@_);
+	}
+
+sub main::BC
+	{
+	return "BYTE @_";
+	}
+
+sub main::DWC
+	{
+	return "DWORD @_";
+	}
+
+sub main::stack_push
+	{
+	my($num)=@_;
+	$stack+=$num*4;
+	&main::sub("esp",$num*4);
+	}
+
+sub main::stack_pop
+	{
+	my($num)=@_;
+	$stack-=$num*4;
+	&main::add("esp",$num*4);
+	}
+
+sub get_mem
+	{
+	my($size,$addr,$reg1,$reg2,$idx)=@_;
+	my($t,$post);
+	my($ret)="[";
+	$addr =~ s/^\s+//;
+	if ($addr =~ /^(.+)\+(.+)$/)
+		{
+		if (defined($regs{$reg2})) {
+		    $addr=join('+', &conv($1), "_$2");
+		} else {
+		    $reg2=&conv($1);
+		    $addr="_$2";
+		}
+		}
+	elsif ($addr =~ /^[_a-zA-Z]/)
+		{
+		$addr="_$addr";
+		}
+
+	$reg1="$regs{$reg1}" if defined($regs{$reg1});
+	$reg2="$regs{$reg2}" if defined($regs{$reg2});
+	if (($addr ne "") && ($addr ne 0))
+		{
+		if ($addr !~ /^-/)
+			{ $ret.="${addr}+"; }
+		else	{ $post=$addr; }
+		}
+	if ($reg2 ne "")
+		{
+		$t="";
+		$t="*$idx" if ($idx != 0);
+		$reg1="+".$reg1 if ("$reg1$post" ne "");
+		$ret.="$reg2$t$reg1$post]";
+		}
+	else
+		{
+		$ret.="$reg1$post]"
+		}
+	return($ret);
+	}
+
+sub main::mov	{ &out2("mov",@_); }
+sub main::movb	{ &out2("mov",@_); }
+sub main::and	{ &out2("and",@_); }
+sub main::or	{ &out2("or",@_); }
+sub main::shl	{ &out2("shl",@_); }
+sub main::shr	{ &out2("shr",@_); }
+sub main::xor	{ &out2("xor",@_); }
+sub main::xorb	{ &out2("xor",@_); }
+sub main::add	{ &out2("add",@_); }
+sub main::adc	{ &out2("adc",@_); }
+sub main::sub	{ &out2("sub",@_); }
+sub main::rotl	{ &out2("rol",@_); }
+sub main::rotr	{ &out2("ror",@_); }
+sub main::exch	{ &out2("xchg",@_); }
+sub main::cmp	{ &out2("cmp",@_); }
+sub main::lea	{ &out2("lea",@_); }
+sub main::mul	{ &out1("mul",@_); }
+sub main::div	{ &out1("div",@_); }
+sub main::dec	{ &out1("dec",@_); }
+sub main::inc	{ &out1("inc",@_); }
+sub main::jmp	{ &out1("jmp",@_); }
+sub main::jmp_ptr { &out1p("jmp",@_); }
+
+# This is a bit of a kludge: declare all branches as NEAR.
+sub main::je	{ &out1("je NEAR",@_); }
+sub main::jle	{ &out1("jle NEAR",@_); }
+sub main::jz	{ &out1("jz NEAR",@_); }
+sub main::jge	{ &out1("jge NEAR",@_); }
+sub main::jl	{ &out1("jl NEAR",@_); }
+sub main::jb	{ &out1("jb NEAR",@_); }
+sub main::jc	{ &out1("jc NEAR",@_); }
+sub main::jnc	{ &out1("jnc NEAR",@_); }
+sub main::jnz	{ &out1("jnz NEAR",@_); }
+sub main::jne	{ &out1("jne NEAR",@_); }
+sub main::jno	{ &out1("jno NEAR",@_); }
+
+sub main::push	{ &out1("push",@_); $stack+=4; }
+sub main::pop	{ &out1("pop",@_); $stack-=4; }
+sub main::bswap	{ &out1("bswap",@_); &using486(); }
+sub main::not	{ &out1("not",@_); }
+sub main::call	{ &out1("call",'_'.$_[0]); }
+sub main::ret	{ &out0("ret"); }
+sub main::nop	{ &out0("nop"); }
+
+sub out2
+	{
+	my($name,$p1,$p2)=@_;
+	my($l,$t);
+
+	push(@out,"\t$name\t");
+	$t=&conv($p1).",";
+	$l=length($t);
+	push(@out,$t);
+	$l=4-($l+9)/8;
+	push(@out,"\t" x $l);
+	push(@out,&conv($p2));
+	push(@out,"\n");
+	}
+
+sub out0
+	{
+	my($name)=@_;
+
+	push(@out,"\t$name\n");
+	}
+
+sub out1
+	{
+	my($name,$p1)=@_;
+	my($l,$t);
+	push(@out,"\t$name\t".&conv($p1)."\n");
+	}
+
+sub conv
+	{
+	my($p)=@_;
+	$p =~ s/0x([0-9A-Fa-f]+)/0$1h/;
+	return $p;
+	}
+
+sub using486
+	{
+	return if $using486;
+	$using486++;
+	grep(s/\.386/\.486/,@out);
+	}
+
+sub main::file
+	{
+	push(@out, "segment .text\n");
+	}
+
+sub main::function_begin
+	{
+	my($func,$extra)=@_;
+
+	push(@labels,$func);
+	my($tmp)=<<"EOF";
+global	_$func
+_$func:
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+EOF
+	push(@out,$tmp);
+	$stack=20;
+	}
+
+sub main::function_begin_B
+	{
+	my($func,$extra)=@_;
+	my($tmp)=<<"EOF";
+global	_$func
+_$func:
+EOF
+	push(@out,$tmp);
+	$stack=4;
+	}
+
+sub main::function_end
+	{
+	my($func)=@_;
+
+	my($tmp)=<<"EOF";
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
+EOF
+	push(@out,$tmp);
+	$stack=0;
+	%label=();
+	}
+
+sub main::function_end_B
+	{
+	$stack=0;
+	%label=();
+	}
+
+sub main::function_end_A
+	{
+	my($func)=@_;
+
+	my($tmp)=<<"EOF";
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
+EOF
+	push(@out,$tmp);
+	}
+
+sub main::file_end
+	{
+	}
+
+sub main::wparam
+	{
+	my($num)=@_;
+
+	return(&main::DWP($stack+$num*4,"esp","",0));
+	}
+
+sub main::swtmp
+	{
+	return(&main::DWP($_[0]*4,"esp","",0));
+	}
+
+# Should use swtmp, which is above esp.  Linix can trash the stack above esp
+#sub main::wtmp
+#	{
+#	my($num)=@_;
+#
+#	return(&main::DWP(-(($num+1)*4),"esp","",0));
+#	}
+
+sub main::comment
+	{
+	foreach (@_)
+		{
+		push(@out,"\t; $_\n");
+		}
+	}
+
+sub main::label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}="\$${label}${_[0]}";
+		$label++;
+		}
+	return($label{$_[0]});
+	}
+
+sub main::set_label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}="${label}${_[0]}";
+		$label++;
+		}
+	push(@out,"$label{$_[0]}:\n");
+	}
+
+sub main::data_word
+	{
+	push(@out,"\tDD\t$_[0]\n");
+	}
+
+sub out1p
+	{
+	my($name,$p1)=@_;
+	my($l,$t);
+
+	push(@out,"\t$name\t ".&conv($p1)."\n");
+	}
+
+##
+## Additional functions required for MMX and other ops
+##
+sub main::testb { &out2('test', @_) }
+sub main::movzx { &out2('movzx', @_) }
+sub main::movd { &out2('movd', @_) }
+sub main::emms { &out0('emms', @_) }
diff --git a/lib/libcrypto/perlasm/x86unix.pl b/lib/libcrypto/perlasm/x86unix.pl
new file mode 100644
index 000000000..f804b91c9
--- /dev/null
+++ b/lib/libcrypto/perlasm/x86unix.pl
@@ -0,0 +1,472 @@
+#!/usr/bin/perl
+
+package x86unix;
+
+$label="L000";
+
+$align=($main::aout)?"4":"16";
+$under=($main::aout)?"_":"";
+$com_start=($main::sol)?"/":"#";
+
+sub main::asm_init_output { @out=(); }
+sub main::asm_get_output { return(@out); }
+sub main::get_labels { return(@labels); }
+sub main::external_label { push(@labels,@_); }
+
+if ($main::cpp)
+	{
+	$align="ALIGN";
+	$under="";
+	$com_start='/*';
+	$com_end='*/';
+	}
+
+%lb=(	'eax',	'%al',
+	'ebx',	'%bl',
+	'ecx',	'%cl',
+	'edx',	'%dl',
+	'ax',	'%al',
+	'bx',	'%bl',
+	'cx',	'%cl',
+	'dx',	'%dl',
+	);
+
+%hb=(	'eax',	'%ah',
+	'ebx',	'%bh',
+	'ecx',	'%ch',
+	'edx',	'%dh',
+	'ax',	'%ah',
+	'bx',	'%bh',
+	'cx',	'%ch',
+	'dx',	'%dh',
+	);
+
+%regs=(	'eax',	'%eax',
+	'ebx',	'%ebx',
+	'ecx',	'%ecx',
+	'edx',	'%edx',
+	'esi',	'%esi',
+	'edi',	'%edi',
+	'ebp',	'%ebp',
+	'esp',	'%esp',
+	'mm0',  '%mm0',
+	'mm1',  '%mm1',
+	);
+
+%reg_val=(
+	'eax',	0x00,
+	'ebx',	0x03,
+	'ecx',	0x01,
+	'edx',	0x02,
+	'esi',	0x06,
+	'edi',	0x07,
+	'ebp',	0x05,
+	'esp',	0x04,
+	);
+
+sub main::LB
+	{
+	(defined($lb{$_[0]})) || die "$_[0] does not have a 'low byte'\n";
+	return($lb{$_[0]});
+	}
+
+sub main::HB
+	{
+	(defined($hb{$_[0]})) || die "$_[0] does not have a 'high byte'\n";
+	return($hb{$_[0]});
+	}
+
+sub main::DWP
+	{
+	local($addr,$reg1,$reg2,$idx)=@_;
+
+	$ret="";
+	$addr =~ s/(^|[+ \t])([A-Za-z_]+[A-Za-z0-9_]+)($|[+ \t])/$1$under$2$3/;
+	$reg1="$regs{$reg1}" if defined($regs{$reg1});
+	$reg2="$regs{$reg2}" if defined($regs{$reg2});
+	$ret.=$addr if ($addr ne "") && ($addr ne 0);
+	if ($reg2 ne "")
+		{
+		if($idx ne "")
+		    { $ret.="($reg1,$reg2,$idx)"; }
+		else
+		    { $ret.="($reg1,$reg2)"; }
+	        }
+	else
+		{ $ret.="($reg1)" }
+	return($ret);
+	}
+
+sub main::BP
+	{
+	return(&main::DWP(@_));
+	}
+
+sub main::BC
+	{
+	return @_;
+	}
+
+sub main::DWC
+	{
+	return @_;
+	}
+
+#sub main::BP
+#	{
+#	local($addr,$reg1,$reg2,$idx)=@_;
+#
+#	$ret="";
+#
+#	$addr =~ s/(^|[+ \t])([A-Za-z_]+)($|[+ \t])/$1$under$2$3/;
+#	$reg1="$regs{$reg1}" if defined($regs{$reg1});
+#	$reg2="$regs{$reg2}" if defined($regs{$reg2});
+#	$ret.=$addr if ($addr ne "") && ($addr ne 0);
+#	if ($reg2 ne "")
+#		{ $ret.="($reg1,$reg2,$idx)"; }
+#	else
+#		{ $ret.="($reg1)" }
+#	return($ret);
+#	}
+
+sub main::mov	{ &out2("movl",@_); }
+sub main::movb	{ &out2("movb",@_); }
+sub main::and	{ &out2("andl",@_); }
+sub main::or	{ &out2("orl",@_); }
+sub main::shl	{ &out2("sall",@_); }
+sub main::shr	{ &out2("shrl",@_); }
+sub main::xor	{ &out2("xorl",@_); }
+sub main::xorb	{ &out2("xorb",@_); }
+sub main::add	{ &out2("addl",@_); }
+sub main::adc	{ &out2("adcl",@_); }
+sub main::sub	{ &out2("subl",@_); }
+sub main::rotl	{ &out2("roll",@_); }
+sub main::rotr	{ &out2("rorl",@_); }
+sub main::exch	{ &out2("xchg",@_); }
+sub main::cmp	{ &out2("cmpl",@_); }
+sub main::lea	{ &out2("leal",@_); }
+sub main::mul	{ &out1("mull",@_); }
+sub main::div	{ &out1("divl",@_); }
+sub main::jmp	{ &out1("jmp",@_); }
+sub main::jmp_ptr { &out1p("jmp",@_); }
+sub main::je	{ &out1("je",@_); }
+sub main::jle	{ &out1("jle",@_); }
+sub main::jne	{ &out1("jne",@_); }
+sub main::jnz	{ &out1("jnz",@_); }
+sub main::jz	{ &out1("jz",@_); }
+sub main::jge	{ &out1("jge",@_); }
+sub main::jl	{ &out1("jl",@_); }
+sub main::jb	{ &out1("jb",@_); }
+sub main::jc	{ &out1("jc",@_); }
+sub main::jnc	{ &out1("jnc",@_); }
+sub main::jno	{ &out1("jno",@_); }
+sub main::dec	{ &out1("decl",@_); }
+sub main::inc	{ &out1("incl",@_); }
+sub main::push	{ &out1("pushl",@_); $stack+=4; }
+sub main::pop	{ &out1("popl",@_); $stack-=4; }
+sub main::not	{ &out1("notl",@_); }
+sub main::call	{ &out1("call",$under.$_[0]); }
+sub main::ret	{ &out0("ret"); }
+sub main::nop	{ &out0("nop"); }
+
+# The bswapl instruction is new for the 486. Emulate if i386.
+sub main::bswap
+	{
+	if ($main::i386)
+		{
+		&main::comment("bswapl @_");
+		&main::exch(main::HB(@_),main::LB(@_));
+		&main::rotr(@_,16);
+		&main::exch(main::HB(@_),main::LB(@_));
+		}
+	else
+		{
+		&out1("bswapl",@_);
+		}
+	}
+
+sub out2
+	{
+	local($name,$p1,$p2)=@_;
+	local($l,$ll,$t);
+	local(%special)=(	"roll",0xD1C0,"rorl",0xD1C8,
+				"rcll",0xD1D0,"rcrl",0xD1D8,
+				"shll",0xD1E0,"shrl",0xD1E8,
+				"sarl",0xD1F8);
+	
+	if ((defined($special{$name})) && defined($regs{$p1}) && ($p2 == 1))
+		{
+		$op=$special{$name}|$reg_val{$p1};
+		$tmp1=sprintf(".byte %d\n",($op>>8)&0xff);
+		$tmp2=sprintf(".byte %d\t",$op     &0xff);
+		push(@out,$tmp1);
+		push(@out,$tmp2);
+
+		$p2=&conv($p2);
+		$p1=&conv($p1);
+		&main::comment("$name $p2 $p1");
+		return;
+		}
+
+	push(@out,"\t$name\t");
+	$t=&conv($p2).",";
+	$l=length($t);
+	push(@out,$t);
+	$ll=4-($l+9)/8;
+	$tmp1=sprintf("\t" x $ll);
+	push(@out,$tmp1);
+	push(@out,&conv($p1)."\n");
+	}
+
+sub out1
+	{
+	local($name,$p1)=@_;
+	local($l,$t);
+	local(%special)=("bswapl",0x0FC8);
+
+	if ((defined($special{$name})) && defined($regs{$p1}))
+		{
+		$op=$special{$name}|$reg_val{$p1};
+		$tmp1=sprintf(".byte %d\n",($op>>8)&0xff);
+		$tmp2=sprintf(".byte %d\t",$op     &0xff);
+		push(@out,$tmp1);
+		push(@out,$tmp2);
+
+		$p2=&conv($p2);
+		$p1=&conv($p1);
+		&main::comment("$name $p2 $p1");
+		return;
+		}
+
+	push(@out,"\t$name\t".&conv($p1)."\n");
+	}
+
+sub out1p
+	{
+	local($name,$p1)=@_;
+	local($l,$t);
+
+	push(@out,"\t$name\t*".&conv($p1)."\n");
+	}
+
+sub out0
+	{
+	push(@out,"\t$_[0]\n");
+	}
+
+sub conv
+	{
+	local($p)=@_;
+
+#	$p =~ s/0x([0-9A-Fa-f]+)/0$1h/;
+
+	$p=$regs{$p} if (defined($regs{$p}));
+
+	$p =~ s/^(-{0,1}[0-9A-Fa-f]+)$/\$$1/;
+	$p =~ s/^(0x[0-9A-Fa-f]+)$/\$$1/;
+	return $p;
+	}
+
+sub main::file
+	{
+	local($file)=@_;
+
+	local($tmp)=<<"EOF";
+	.file	"$file.s"
+	.version	"01.01"
+EOF
+# Removed the next line from previous infile
+#gcc2_compiled.:
+	push(@out,$tmp);
+	}
+
+sub main::function_begin
+	{
+	local($func)=@_;
+
+	&main::external_label($func);
+	$func=$under.$func;
+
+	local($tmp)=<<"EOF";
+.text
+	.align $align
+.globl $func
+EOF
+	push(@out,$tmp);
+	if ($main::cpp)
+		{ $tmp=push(@out,"\tTYPE($func,\@function)\n"); }
+	elsif ($main::gaswin)
+		{ $tmp=push(@out,"\t.def\t$func;\t.scl\t2;\t.type\t32;\t.endef\n"); }
+	else	{ $tmp=push(@out,"\t.type\t$func,\@function\n"); }
+	push(@out,"$func:\n");
+	$tmp=<<"EOF";
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+
+EOF
+	push(@out,$tmp);
+	$stack=20;
+	}
+
+sub main::function_begin_B
+	{
+	local($func,$extra)=@_;
+
+	&main::external_label($func);
+	$func=$under.$func;
+
+	local($tmp)=<<"EOF";
+.text
+	.align $align
+.globl $func
+EOF
+	push(@out,$tmp);
+	if ($main::cpp)
+		{ push(@out,"\tTYPE($func,\@function)\n"); }
+	elsif ($main::gaswin)
+		{ $tmp=push(@out,"\t.def\t$func;\t.scl\t2;\t.type\t32;\t.endef\n"); }
+	else	{ push(@out,"\t.type	$func,\@function\n"); }
+	push(@out,"$func:\n");
+	$stack=4;
+	}
+
+sub main::function_end
+	{
+	local($func)=@_;
+
+	$func=$under.$func;
+
+	local($tmp)=<<"EOF";
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.${func}_end:
+EOF
+	push(@out,$tmp);
+	if ($main::cpp)
+		{ push(@out,"\tSIZE($func,.${func}_end-$func)\n"); }
+	elsif ($main::gaswin)
+                { $tmp=push(@out,"\t.align 4\n"); }
+	else	{ push(@out,"\t.size\t$func,.${func}_end-$func\n"); }
+	push(@out,".ident	\"$func\"\n");
+	$stack=0;
+	%label=();
+	}
+
+sub main::function_end_A
+	{
+	local($func)=@_;
+
+	local($tmp)=<<"EOF";
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+EOF
+	push(@out,$tmp);
+	}
+
+sub main::function_end_B
+	{
+	local($func)=@_;
+
+	$func=$under.$func;
+
+	push(@out,".L_${func}_end:\n");
+	if ($main::cpp)
+		{ push(@out,"\tSIZE($func,.L_${func}_end-$func)\n"); }
+        elsif ($main::gaswin)
+                { push(@out,"\t.align 4\n"); }
+	else	{ push(@out,"\t.size\t$func,.L_${func}_end-$func\n"); }
+	push(@out,".ident	\"desasm.pl\"\n");
+	$stack=0;
+	%label=();
+	}
+
+sub main::wparam
+	{
+	local($num)=@_;
+
+	return(&main::DWP($stack+$num*4,"esp","",0));
+	}
+
+sub main::stack_push
+	{
+	local($num)=@_;
+	$stack+=$num*4;
+	&main::sub("esp",$num*4);
+	}
+
+sub main::stack_pop
+	{
+	local($num)=@_;
+	$stack-=$num*4;
+	&main::add("esp",$num*4);
+	}
+
+sub main::swtmp
+	{
+	return(&main::DWP($_[0]*4,"esp","",0));
+	}
+
+# Should use swtmp, which is above esp.  Linix can trash the stack above esp
+#sub main::wtmp
+#	{
+#	local($num)=@_;
+#
+#	return(&main::DWP(-($num+1)*4,"esp","",0));
+#	}
+
+sub main::comment
+	{
+	foreach (@_)
+		{
+		if (/^\s*$/)
+			{ push(@out,"\n"); }
+		else
+			{ push(@out,"\t$com_start $_ $com_end\n"); }
+		}
+	}
+
+sub main::label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}=".${label}${_[0]}";
+		$label++;
+		}
+	return($label{$_[0]});
+	}
+
+sub main::set_label
+	{
+	if (!defined($label{$_[0]}))
+		{
+		$label{$_[0]}=".${label}${_[0]}";
+		$label++;
+		}
+	push(@out,".align $align\n") if ($_[1] != 0);
+	push(@out,"$label{$_[0]}:\n");
+	}
+
+sub main::file_end
+	{
+	}
+
+sub main::data_word
+	{
+	push(@out,"\t.long $_[0]\n");
+	}
+
+##
+## Additional functions required for MMX and other ops
+##
+sub main::testb { &out2('testb', @_) }
+sub main::movzx { &out2('movzx', @_) }
+sub main::movd { &out2('movd', @_) }
+sub main::emms { &out0('emms', @_) }