diff --git a/Android.mk b/Android.mk
new file mode 100644
index 0000000..d8b4f73
--- /dev/null
+++ b/Android.mk
@@ -0,0 +1,12 @@
+LOCAL_PATH := $(call my-dir)
+
+include $(CLEAR_VARS)
+
+LOCAL_SRC_FILES :=  \
+    aescrypt.c      \
+    aeskey.c        \
+    aestab.c
+
+LOCAL_MODULE := libaes
+
+include $(BUILD_SHARED_LIBRARY)
diff --git a/MODULE_LICENSE_BSD_LIKE b/MODULE_LICENSE_BSD_LIKE
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/MODULE_LICENSE_BSD_LIKE
diff --git a/NOTICE b/NOTICE
new file mode 100644
index 0000000..988f05e
--- /dev/null
+++ b/NOTICE
@@ -0,0 +1,22 @@
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
diff --git a/aes.h b/aes.h
new file mode 100644
index 0000000..26079ef
--- /dev/null
+++ b/aes.h
@@ -0,0 +1,166 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+
+ This file contains the definitions required to use AES in C. See aesopt.h
+ for optimisation details.
+*/
+
+#if !defined( _AES_H )
+#define _AES_H
+
+/*  This include is used to find 8 & 32 bit unsigned integer types  */
+#include "limits.h"
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+
+#define AES_128          /* define if AES with 128 bit keys is needed    */
+/* #define AES_192 */    /* define if AES with 192 bit keys is needed    */
+/* #define AES_256 */    /* define if AES with 256 bit keys is needed    */
+/* #define AES_VAR */    /* define if a variable key size is needed      */
+
+/* The following must also be set in assembler files if being used  */
+
+#define AES_ENCRYPT      /* if support for encryption is needed          */
+#define AES_DECRYPT      /* if support for decryption is needed          */
+/* #define AES_ERR_CHK *//* for parameter checks & error return codes    */
+
+#if UCHAR_MAX == 0xff                   /* an unsigned 8 bit type   */
+  typedef unsigned char      aes_08t;
+#else
+#  error Please define aes_08t as an 8-bit unsigned integer type in aes.h
+#endif
+
+#if UINT_MAX == 4294967295              /* an unsigned 32 bit type  */
+  typedef   unsigned int     aes_32t;
+#elif ULONG_MAX == 4294967295ul
+  typedef   unsigned long    aes_32t;
+#else
+#  error Please define aes_32t as a 32-bit unsigned integer type in aes.h
+#endif
+
+#define AES_BLOCK_SIZE  16  /* the AES block size in bytes          */
+#define N_COLS           4  /* the number of columns in the state   */
+
+/* The key schedule length is 11, 13 or 15 16-byte blocks for 128,  */
+/* 192 or 256-bit keys respectively. That is 176, 208 or 240 bytes  */
+/* or 44, 52 or 60 32-bit words. For simplicity this code allocates */
+/* the maximum 60 word array for the key schedule for all key sizes */
+
+#if defined( AES_VAR ) || defined( AES_256 )
+#define KS_LENGTH       60
+#elif defined( AES_192 )
+#define KS_LENGTH       52
+#else
+#define KS_LENGTH       44
+#endif
+
+#if defined( AES_ERR_CHK )
+#define aes_ret     int
+#define aes_good    0
+#define aes_error  -1
+#else
+#define aes_ret     void
+#endif
+
+#if !defined( AES_DLL )                 /* implement normal/DLL functions   */
+#define aes_rval    aes_ret
+#else
+#define aes_rval    aes_ret __declspec(dllexport) _stdcall
+#endif
+
+typedef struct
+{   aes_32t ks[KS_LENGTH];
+    aes_32t rn;
+} aes_encrypt_ctx;
+
+typedef struct
+{   aes_32t ks[KS_LENGTH];
+    aes_32t rn;
+} aes_decrypt_ctx;
+
+/* This routine must be called before first use if non-static       */
+/* tables are being used                                            */
+
+void gen_tabs(void);
+
+/* The key length (klen) is input in bytes when it is in the range  */
+/* 16 <= klen <= 32 or in bits when in the range 128 <= klen <= 256 */
+
+#if defined( AES_ENCRYPT )
+
+#if defined(AES_128) || defined(AES_VAR)
+aes_rval aes_encrypt_key128(const unsigned char *in_key, aes_encrypt_ctx cx[1]);
+#endif
+
+#if defined(AES_192) || defined(AES_VAR)
+aes_rval aes_encrypt_key192(const unsigned char *in_key, aes_encrypt_ctx cx[1]);
+#endif
+
+#if defined(AES_256) || defined(AES_VAR)
+aes_rval aes_encrypt_key256(const unsigned char *in_key, aes_encrypt_ctx cx[1]);
+#endif
+
+#if defined(AES_VAR)
+aes_rval aes_encrypt_key(const unsigned char *in_key, int key_len, aes_encrypt_ctx cx[1]);
+#endif
+
+aes_rval aes_encrypt(const unsigned char *in_blk, unsigned char *out_blk, const aes_encrypt_ctx cx[1]);
+#endif
+
+#if defined( AES_DECRYPT )
+
+#if defined(AES_128) || defined(AES_VAR)
+aes_rval aes_decrypt_key128(const unsigned char *in_key, aes_decrypt_ctx cx[1]);
+#endif
+
+#if defined(AES_192) || defined(AES_VAR)
+aes_rval aes_decrypt_key192(const unsigned char *in_key, aes_decrypt_ctx cx[1]);
+#endif
+
+#if defined(AES_256) || defined(AES_VAR)
+aes_rval aes_decrypt_key256(const unsigned char *in_key, aes_decrypt_ctx cx[1]);
+#endif
+
+#if defined(AES_VAR)
+aes_rval aes_decrypt_key(const unsigned char *in_key, int key_len, aes_decrypt_ctx cx[1]);
+#endif
+
+aes_rval aes_decrypt(const unsigned char *in_blk,  unsigned char *out_blk, const aes_decrypt_ctx cx[1]);
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/aesaux.h b/aesaux.h
new file mode 100644
index 0000000..f9c9585
--- /dev/null
+++ b/aesaux.h
@@ -0,0 +1,74 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2002, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+*/
+
+#include <iostream>
+#include <fstream>
+#include <strstream>
+#include <iomanip>
+#include <cctype>
+
+typedef unsigned char   byte;
+typedef unsigned long   word;
+
+enum line_type { bad_line = 0, block_len, key_len, test_no, iv_val, key_val, pt_val, ct_val };
+#define NO_LTYPES   8
+#define BADL_STR    "BADLINE="
+#define BLEN_STR    "BLOCKSIZE="
+#define KLEN_STR    "KEYSIZE=  "
+#define TEST_STR    "TEST= "
+#define IV_STR      "IV=   "
+#define KEY_STR     "KEY=  "
+#define PT_STR      "PT=   "
+#define CT_STR      "CT=   "
+
+char      *file_name(char* buf, const word type, const word blen, const word klen);
+char      *copy_str(char *s, const char *fstr);
+bool      get_line(std::ifstream& inf, char s[]);
+void      block_out(const line_type ty, const byte b[], std::ofstream& outf, const word len);
+
+int       find_string(const char *s1, const char s2[]);
+line_type find_line(std::ifstream& inf, char str[]);
+
+word    rand32(void);
+byte    rand8(void);
+int     block_in(byte l[], const char *p);
+void    block_clear(byte l[], const word len);
+void    block_reverse(byte l[], const word len);
+void    block_copy(byte l[], const byte r[], const word len);
+void    block_xor(byte l[], const byte r[], const word len);
+bool    block_cmp(const byte l[], const byte r[], const word len);
+void    block_rndfill(byte l[], word len);
+
+void    put_dec(char *s, word val);
+word    get_dec(const char *s);
+int     cmp_nocase(const char *s1, const char *s2);
+bool    test_args(int argc, char *argv[], char des_chr, char tst_chr);
diff --git a/aescrypt.c b/aescrypt.c
new file mode 100644
index 0000000..3f78761
--- /dev/null
+++ b/aescrypt.c
@@ -0,0 +1,317 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+
+ This file contains the code for implementing encryption and decryption
+ for AES (Rijndael) for block and key sizes of 16, 24 and 32 bytes. It
+ can optionally be replaced by code written in assembler using NASM. For
+ further details see the file aesopt.h
+*/
+
+#include "aesopt.h"
+#include "aestab.h"
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+
+#define si(y,x,k,c) (s(y,c) = word_in(x, c) ^ (k)[c])
+#define so(y,x,c)   word_out(y, c, s(x,c))
+
+#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
+#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)
+
+#if defined(ENCRYPTION) && !defined(AES_ASM)
+
+/* Visual C++ .Net v7.1 provides the fastest encryption code when using
+   Pentium optimiation with small code but this is poor for decryption
+   so we need to control this with the following VC++ pragmas
+*/
+
+#if defined(_MSC_VER)
+#pragma optimize( "s", on )
+#endif
+
+/* Given the column (c) of the output state variable, the following
+   macros give the input state variables which are needed in its
+   computation for each row (r) of the state. All the alternative
+   macros give the same end values but expand into different ways
+   of calculating these values.  In particular the complex macro
+   used for dynamically variable block sizes is designed to expand
+   to a compile time constant whenever possible but will expand to
+   conditional clauses on some branches (I am grateful to Frank
+   Yellin for this construction)
+*/
+
+#define fwd_var(x,r,c)\
+ ( r == 0 ? ( c == 0 ? s(x,0) : c == 1 ? s(x,1) : c == 2 ? s(x,2) : s(x,3))\
+ : r == 1 ? ( c == 0 ? s(x,1) : c == 1 ? s(x,2) : c == 2 ? s(x,3) : s(x,0))\
+ : r == 2 ? ( c == 0 ? s(x,2) : c == 1 ? s(x,3) : c == 2 ? s(x,0) : s(x,1))\
+ :          ( c == 0 ? s(x,3) : c == 1 ? s(x,0) : c == 2 ? s(x,1) : s(x,2)))
+
+#if defined(FT4_SET)
+#undef  dec_fmvars
+#define fwd_rnd(y,x,k,c)    (s(y,c) = (k)[c] ^ four_tables(x,t_use(f,n),fwd_var,rf1,c))
+#elif defined(FT1_SET)
+#undef  dec_fmvars
+#define fwd_rnd(y,x,k,c)    (s(y,c) = (k)[c] ^ one_table(x,upr,t_use(f,n),fwd_var,rf1,c))
+#else
+#define fwd_rnd(y,x,k,c)    (s(y,c) = (k)[c] ^ fwd_mcol(no_table(x,t_use(s,box),fwd_var,rf1,c)))
+#endif
+
+#if defined(FL4_SET)
+#define fwd_lrnd(y,x,k,c)   (s(y,c) = (k)[c] ^ four_tables(x,t_use(f,l),fwd_var,rf1,c))
+#elif defined(FL1_SET)
+#define fwd_lrnd(y,x,k,c)   (s(y,c) = (k)[c] ^ one_table(x,ups,t_use(f,l),fwd_var,rf1,c))
+#else
+#define fwd_lrnd(y,x,k,c)   (s(y,c) = (k)[c] ^ no_table(x,t_use(s,box),fwd_var,rf1,c))
+#endif
+
+aes_rval aes_encrypt(const unsigned char *in,
+                        unsigned char *out, const aes_encrypt_ctx cx[1])
+{   aes_32t         locals(b0, b1);
+    const aes_32t   *kp = cx->ks;
+#if defined( dec_fmvars )
+    dec_fmvars; /* declare variables for fwd_mcol() if needed */
+#endif
+
+#if defined( AES_ERR_CHK )
+    if( cx->rn != 10 && cx->rn != 12 && cx->rn != 14 )
+        return aes_error;
+#endif
+
+    state_in(b0, in, kp);
+
+#if (ENC_UNROLL == FULL)
+
+    switch(cx->rn)
+    {
+    case 14:
+        round(fwd_rnd,  b1, b0, kp + 1 * N_COLS);
+        round(fwd_rnd,  b0, b1, kp + 2 * N_COLS);
+        kp += 2 * N_COLS;
+    case 12:
+        round(fwd_rnd,  b1, b0, kp + 1 * N_COLS);
+        round(fwd_rnd,  b0, b1, kp + 2 * N_COLS);
+        kp += 2 * N_COLS;
+    case 10:
+        round(fwd_rnd,  b1, b0, kp + 1 * N_COLS);
+        round(fwd_rnd,  b0, b1, kp + 2 * N_COLS);
+        round(fwd_rnd,  b1, b0, kp + 3 * N_COLS);
+        round(fwd_rnd,  b0, b1, kp + 4 * N_COLS);
+        round(fwd_rnd,  b1, b0, kp + 5 * N_COLS);
+        round(fwd_rnd,  b0, b1, kp + 6 * N_COLS);
+        round(fwd_rnd,  b1, b0, kp + 7 * N_COLS);
+        round(fwd_rnd,  b0, b1, kp + 8 * N_COLS);
+        round(fwd_rnd,  b1, b0, kp + 9 * N_COLS);
+        round(fwd_lrnd, b0, b1, kp +10 * N_COLS);
+    }
+
+#else
+
+#if (ENC_UNROLL == PARTIAL)
+    {   aes_32t    rnd;
+        for(rnd = 0; rnd < (cx->rn >> 1) - 1; ++rnd)
+        {
+            kp += N_COLS;
+            round(fwd_rnd, b1, b0, kp);
+            kp += N_COLS;
+            round(fwd_rnd, b0, b1, kp);
+        }
+        kp += N_COLS;
+        round(fwd_rnd,  b1, b0, kp);
+        /* Modify these two sentences to here just for compiling success, and the logic is the same as original open source */
+        kp += N_COLS;
+        round(fwd_lrnd, b0, b1, kp);
+    }
+#else
+    {   aes_32t    rnd;
+        for(rnd = 0; rnd < cx->rn - 1; ++rnd)
+        {
+            kp += N_COLS;
+            round(fwd_rnd, b1, b0, kp);
+            l_copy(b0, b1);
+        }
+        /* Modify these two sentences to here just for compiling success, and the logic is the same as original open source */
+        kp += N_COLS;
+        round(fwd_lrnd, b0, b1, kp);
+    }
+#endif
+
+#endif
+
+    state_out(out, b0);
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(DECRYPTION) && !defined(AES_ASM)
+
+/* Visual C++ .Net v7.1 provides the fastest encryption code when using
+   Pentium optimiation with small code but this is poor for decryption
+   so we need to control this with the following VC++ pragmas
+*/
+
+#if defined(_MSC_VER)
+#pragma optimize( "t", on )
+#endif
+
+/* Given the column (c) of the output state variable, the following
+   macros give the input state variables which are needed in its
+   computation for each row (r) of the state. All the alternative
+   macros give the same end values but expand into different ways
+   of calculating these values.  In particular the complex macro
+   used for dynamically variable block sizes is designed to expand
+   to a compile time constant whenever possible but will expand to
+   conditional clauses on some branches (I am grateful to Frank
+   Yellin for this construction)
+*/
+
+#define inv_var(x,r,c)\
+ ( r == 0 ? ( c == 0 ? s(x,0) : c == 1 ? s(x,1) : c == 2 ? s(x,2) : s(x,3))\
+ : r == 1 ? ( c == 0 ? s(x,3) : c == 1 ? s(x,0) : c == 2 ? s(x,1) : s(x,2))\
+ : r == 2 ? ( c == 0 ? s(x,2) : c == 1 ? s(x,3) : c == 2 ? s(x,0) : s(x,1))\
+ :          ( c == 0 ? s(x,1) : c == 1 ? s(x,2) : c == 2 ? s(x,3) : s(x,0)))
+
+#if defined(IT4_SET)
+#undef  dec_imvars
+#define inv_rnd(y,x,k,c)    (s(y,c) = (k)[c] ^ four_tables(x,t_use(i,n),inv_var,rf1,c))
+#elif defined(IT1_SET)
+#undef  dec_imvars
+#define inv_rnd(y,x,k,c)    (s(y,c) = (k)[c] ^ one_table(x,upr,t_use(i,n),inv_var,rf1,c))
+#else
+#define inv_rnd(y,x,k,c)    (s(y,c) = inv_mcol((k)[c] ^ no_table(x,t_use(i,box),inv_var,rf1,c)))
+#endif
+
+#if defined(IL4_SET)
+#define inv_lrnd(y,x,k,c)   (s(y,c) = (k)[c] ^ four_tables(x,t_use(i,l),inv_var,rf1,c))
+#elif defined(IL1_SET)
+#define inv_lrnd(y,x,k,c)   (s(y,c) = (k)[c] ^ one_table(x,ups,t_use(i,l),inv_var,rf1,c))
+#else
+#define inv_lrnd(y,x,k,c)   (s(y,c) = (k)[c] ^ no_table(x,t_use(i,box),inv_var,rf1,c))
+#endif
+
+aes_rval aes_decrypt(const unsigned char *in,
+                        unsigned char *out, const aes_decrypt_ctx cx[1])
+{   aes_32t        locals(b0, b1);
+#if defined( dec_imvars )
+    dec_imvars; /* declare variables for inv_mcol() if needed */
+#endif
+    const aes_32t *kp = cx->ks + cx->rn * N_COLS;
+
+#if defined( AES_ERR_CHK )
+    if( cx->rn != 10 && cx->rn != 12 && cx->rn != 14 )
+        return aes_error;
+#endif
+
+    state_in(b0, in, kp);
+
+#if (DEC_UNROLL == FULL)
+
+    switch(cx->rn)
+    {
+    case 14:
+        round(inv_rnd,  b1, b0, kp -  1 * N_COLS);
+        round(inv_rnd,  b0, b1, kp -  2 * N_COLS);
+        kp -= 2 * N_COLS;
+    case 12:
+        round(inv_rnd,  b1, b0, kp -  1 * N_COLS);
+        round(inv_rnd,  b0, b1, kp -  2 * N_COLS);
+        kp -= 2 * N_COLS;
+    case 10:
+        round(inv_rnd,  b1, b0, kp -  1 * N_COLS);
+        round(inv_rnd,  b0, b1, kp -  2 * N_COLS);
+        round(inv_rnd,  b1, b0, kp -  3 * N_COLS);
+        round(inv_rnd,  b0, b1, kp -  4 * N_COLS);
+        round(inv_rnd,  b1, b0, kp -  5 * N_COLS);
+        round(inv_rnd,  b0, b1, kp -  6 * N_COLS);
+        round(inv_rnd,  b1, b0, kp -  7 * N_COLS);
+        round(inv_rnd,  b0, b1, kp -  8 * N_COLS);
+        round(inv_rnd,  b1, b0, kp -  9 * N_COLS);
+        round(inv_lrnd, b0, b1, kp - 10 * N_COLS);
+    }
+
+#else
+
+#if (DEC_UNROLL == PARTIAL)
+    {   aes_32t    rnd;
+        for(rnd = 0; rnd < (cx->rn >> 1) - 1; ++rnd)
+        {
+            kp -= N_COLS;
+            round(inv_rnd, b1, b0, kp);
+            kp -= N_COLS;
+            round(inv_rnd, b0, b1, kp);
+        }
+        kp -= N_COLS;
+        round(inv_rnd, b1, b0, kp);
+        /* Modify these two sentences to here just for compiling success, and the logic is the same as original open source */
+        kp -= N_COLS;
+        round(inv_lrnd, b0, b1, kp);
+    }
+#else
+    {   aes_32t    rnd;
+        for(rnd = 0; rnd < cx->rn - 1; ++rnd)
+        {
+            kp -= N_COLS;
+            round(inv_rnd, b1, b0, kp);
+            l_copy(b0, b1);
+        }
+        /* Modify these two sentences to here just for compiling success, and the logic is the same as original open source */
+        kp -= N_COLS;
+        round(inv_lrnd, b0, b1, kp);
+    }
+#endif
+
+#endif
+
+    state_out(out, b0);
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
diff --git a/aeskey.c b/aeskey.c
new file mode 100644
index 0000000..0120e0c
--- /dev/null
+++ b/aeskey.c
@@ -0,0 +1,455 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue Date: 26/08/2003
+
+ This file contains the code for implementing the key schedule for AES
+ (Rijndael) for block and key sizes of 16, 24, and 32 bytes. See aesopt.h
+ for further details including optimisation.
+*/
+
+#include "aesopt.h"
+#include "aestab.h"
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+
+/* Initialise the key schedule from the user supplied key. The key
+   length can be specified in bytes, with legal values of 16, 24
+   and 32, or in bits, with legal values of 128, 192 and 256. These
+   values correspond with Nk values of 4, 6 and 8 respectively.
+
+   The following macros implement a single cycle in the key
+   schedule generation process. The number of cycles needed
+   for each cx->n_col and nk value is:
+
+    nk =             4  5  6  7  8
+    ------------------------------
+    cx->n_col = 4   10  9  8  7  7
+    cx->n_col = 5   14 11 10  9  9
+    cx->n_col = 6   19 15 12 11 11
+    cx->n_col = 7   21 19 16 13 14
+    cx->n_col = 8   29 23 19 17 14
+*/
+
+#define ke4(k,i) \
+{   k[4*(i)+4] = ss[0] ^= ls_box(ss[3],3) ^ t_use(r,c)[i]; k[4*(i)+5] = ss[1] ^= ss[0]; \
+    k[4*(i)+6] = ss[2] ^= ss[1]; k[4*(i)+7] = ss[3] ^= ss[2]; \
+}
+#define kel4(k,i) \
+{   k[4*(i)+4] = ss[0] ^= ls_box(ss[3],3) ^ t_use(r,c)[i]; k[4*(i)+5] = ss[1] ^= ss[0]; \
+    k[4*(i)+6] = ss[2] ^= ss[1]; k[4*(i)+7] = ss[3] ^= ss[2]; \
+}
+
+#define ke6(k,i) \
+{   k[6*(i)+ 6] = ss[0] ^= ls_box(ss[5],3) ^ t_use(r,c)[i]; k[6*(i)+ 7] = ss[1] ^= ss[0]; \
+    k[6*(i)+ 8] = ss[2] ^= ss[1]; k[6*(i)+ 9] = ss[3] ^= ss[2]; \
+    k[6*(i)+10] = ss[4] ^= ss[3]; k[6*(i)+11] = ss[5] ^= ss[4]; \
+}
+#define kel6(k,i) \
+{   k[6*(i)+ 6] = ss[0] ^= ls_box(ss[5],3) ^ t_use(r,c)[i]; k[6*(i)+ 7] = ss[1] ^= ss[0]; \
+    k[6*(i)+ 8] = ss[2] ^= ss[1]; k[6*(i)+ 9] = ss[3] ^= ss[2]; \
+}
+
+#define ke8(k,i) \
+{   k[8*(i)+ 8] = ss[0] ^= ls_box(ss[7],3) ^ t_use(r,c)[i]; k[8*(i)+ 9] = ss[1] ^= ss[0]; \
+    k[8*(i)+10] = ss[2] ^= ss[1]; k[8*(i)+11] = ss[3] ^= ss[2]; \
+    k[8*(i)+12] = ss[4] ^= ls_box(ss[3],0); k[8*(i)+13] = ss[5] ^= ss[4]; \
+    k[8*(i)+14] = ss[6] ^= ss[5]; k[8*(i)+15] = ss[7] ^= ss[6]; \
+}
+#define kel8(k,i) \
+{   k[8*(i)+ 8] = ss[0] ^= ls_box(ss[7],3) ^ t_use(r,c)[i]; k[8*(i)+ 9] = ss[1] ^= ss[0]; \
+    k[8*(i)+10] = ss[2] ^= ss[1]; k[8*(i)+11] = ss[3] ^= ss[2]; \
+}
+
+#if defined(ENCRYPTION_KEY_SCHEDULE)
+
+#if defined(AES_128) || defined(AES_VAR)
+
+aes_rval aes_encrypt_key128(const unsigned char *key, aes_encrypt_ctx cx[1])
+{   aes_32t    ss[4];
+
+    cx->ks[0] = ss[0] = word_in(key, 0);
+    cx->ks[1] = ss[1] = word_in(key, 1);
+    cx->ks[2] = ss[2] = word_in(key, 2);
+    cx->ks[3] = ss[3] = word_in(key, 3);
+
+#if ENC_UNROLL == NONE
+    {   aes_32t i;
+
+        for(i = 0; i < ((11 * N_COLS - 5) / 4); ++i)
+            ke4(cx->ks, i);
+    }
+#else
+    ke4(cx->ks, 0);  ke4(cx->ks, 1);
+    ke4(cx->ks, 2);  ke4(cx->ks, 3);
+    ke4(cx->ks, 4);  ke4(cx->ks, 5);
+    ke4(cx->ks, 6);  ke4(cx->ks, 7);
+    ke4(cx->ks, 8);
+#endif
+    kel4(cx->ks, 9);
+    cx->rn = 10;
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(AES_192) || defined(AES_VAR)
+
+aes_rval aes_encrypt_key192(const unsigned char *key, aes_encrypt_ctx cx[1])
+{   aes_32t    ss[6];
+
+    cx->ks[0] = ss[0] = word_in(key, 0);
+    cx->ks[1] = ss[1] = word_in(key, 1);
+    cx->ks[2] = ss[2] = word_in(key, 2);
+    cx->ks[3] = ss[3] = word_in(key, 3);
+    cx->ks[4] = ss[4] = word_in(key, 4);
+    cx->ks[5] = ss[5] = word_in(key, 5);
+
+#if ENC_UNROLL == NONE
+    {   aes_32t i;
+
+        for(i = 0; i < (13 * N_COLS - 7) / 6; ++i)
+            ke6(cx->ks, i);
+    }
+#else
+    ke6(cx->ks, 0);  ke6(cx->ks, 1);
+    ke6(cx->ks, 2);  ke6(cx->ks, 3);
+    ke6(cx->ks, 4);  ke6(cx->ks, 5);
+    ke6(cx->ks, 6);
+#endif
+    kel6(cx->ks, 7);
+    cx->rn = 12;
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(AES_256) || defined(AES_VAR)
+
+aes_rval aes_encrypt_key256(const unsigned char *key, aes_encrypt_ctx cx[1])
+{   aes_32t    ss[8];
+
+    cx->ks[0] = ss[0] = word_in(key, 0);
+    cx->ks[1] = ss[1] = word_in(key, 1);
+    cx->ks[2] = ss[2] = word_in(key, 2);
+    cx->ks[3] = ss[3] = word_in(key, 3);
+    cx->ks[4] = ss[4] = word_in(key, 4);
+    cx->ks[5] = ss[5] = word_in(key, 5);
+    cx->ks[6] = ss[6] = word_in(key, 6);
+    cx->ks[7] = ss[7] = word_in(key, 7);
+
+#if ENC_UNROLL == NONE
+    {   aes_32t i;
+
+        for(i = 0; i < (15 * N_COLS - 9) / 8; ++i)
+            ke8(cx->ks,  i);
+    }
+#else
+    ke8(cx->ks, 0); ke8(cx->ks, 1);
+    ke8(cx->ks, 2); ke8(cx->ks, 3);
+    ke8(cx->ks, 4); ke8(cx->ks, 5);
+#endif
+    kel8(cx->ks, 6);
+    cx->rn = 14;
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(AES_VAR)
+
+aes_rval aes_encrypt_key(const unsigned char *key, int key_len, aes_encrypt_ctx cx[1])
+{
+    switch(key_len)
+    {
+#if defined( AES_ERR_CHK )
+    case 16: case 128: return aes_encrypt_key128(key, cx);
+    case 24: case 192: return aes_encrypt_key192(key, cx);
+    case 32: case 256: return aes_encrypt_key256(key, cx);
+    default: return aes_error;
+#else
+    case 16: case 128: aes_encrypt_key128(key, cx); return;
+    case 24: case 192: aes_encrypt_key192(key, cx); return;
+    case 32: case 256: aes_encrypt_key256(key, cx); return;
+#endif
+    }
+}
+
+#endif
+
+#endif
+
+#if defined(DECRYPTION_KEY_SCHEDULE)
+
+#if DEC_ROUND == NO_TABLES
+#define ff(x)   (x)
+#else
+#define ff(x)   inv_mcol(x)
+#if defined( dec_imvars )
+#define d_vars  dec_imvars
+#endif
+#endif
+
+#if 1
+#define kdf4(k,i) \
+{   ss[0] = ss[0] ^ ss[2] ^ ss[1] ^ ss[3]; ss[1] = ss[1] ^ ss[3]; ss[2] = ss[2] ^ ss[3]; ss[3] = ss[3]; \
+    ss[4] = ls_box(ss[(i+3) % 4], 3) ^ t_use(r,c)[i]; ss[i % 4] ^= ss[4]; \
+    ss[4] ^= k[4*(i)];   k[4*(i)+4] = ff(ss[4]); ss[4] ^= k[4*(i)+1]; k[4*(i)+5] = ff(ss[4]); \
+    ss[4] ^= k[4*(i)+2]; k[4*(i)+6] = ff(ss[4]); ss[4] ^= k[4*(i)+3]; k[4*(i)+7] = ff(ss[4]); \
+}
+#define kd4(k,i) \
+{   ss[4] = ls_box(ss[(i+3) % 4], 3) ^ t_use(r,c)[i]; ss[i % 4] ^= ss[4]; ss[4] = ff(ss[4]); \
+    k[4*(i)+4] = ss[4] ^= k[4*(i)]; k[4*(i)+5] = ss[4] ^= k[4*(i)+1]; \
+    k[4*(i)+6] = ss[4] ^= k[4*(i)+2]; k[4*(i)+7] = ss[4] ^= k[4*(i)+3]; \
+}
+#define kdl4(k,i) \
+{   ss[4] = ls_box(ss[(i+3) % 4], 3) ^ t_use(r,c)[i]; ss[i % 4] ^= ss[4]; \
+    k[4*(i)+4] = (ss[0] ^= ss[1]) ^ ss[2] ^ ss[3]; k[4*(i)+5] = ss[1] ^ ss[3]; \
+    k[4*(i)+6] = ss[0]; k[4*(i)+7] = ss[1]; \
+}
+#else
+#define kdf4(k,i) \
+{   ss[0] ^= ls_box(ss[3],3) ^ t_use(r,c)[i]; k[4*(i)+ 4] = ff(ss[0]); ss[1] ^= ss[0]; k[4*(i)+ 5] = ff(ss[1]); \
+    ss[2] ^= ss[1]; k[4*(i)+ 6] = ff(ss[2]); ss[3] ^= ss[2]; k[4*(i)+ 7] = ff(ss[3]); \
+}
+#define kd4(k,i) \
+{   ss[4] = ls_box(ss[3],3) ^ t_use(r,c)[i]; \
+    ss[0] ^= ss[4]; ss[4] = ff(ss[4]); k[4*(i)+ 4] = ss[4] ^= k[4*(i)]; \
+    ss[1] ^= ss[0]; k[4*(i)+ 5] = ss[4] ^= k[4*(i)+ 1]; \
+    ss[2] ^= ss[1]; k[4*(i)+ 6] = ss[4] ^= k[4*(i)+ 2]; \
+    ss[3] ^= ss[2]; k[4*(i)+ 7] = ss[4] ^= k[4*(i)+ 3]; \
+}
+#define kdl4(k,i) \
+{   ss[0] ^= ls_box(ss[3],3) ^ t_use(r,c)[i]; k[4*(i)+ 4] = ss[0]; ss[1] ^= ss[0]; k[4*(i)+ 5] = ss[1]; \
+    ss[2] ^= ss[1]; k[4*(i)+ 6] = ss[2]; ss[3] ^= ss[2]; k[4*(i)+ 7] = ss[3]; \
+}
+#endif
+
+#define kdf6(k,i) \
+{   ss[0] ^= ls_box(ss[5],3) ^ t_use(r,c)[i]; k[6*(i)+ 6] = ff(ss[0]); ss[1] ^= ss[0]; k[6*(i)+ 7] = ff(ss[1]); \
+    ss[2] ^= ss[1]; k[6*(i)+ 8] = ff(ss[2]); ss[3] ^= ss[2]; k[6*(i)+ 9] = ff(ss[3]); \
+    ss[4] ^= ss[3]; k[6*(i)+10] = ff(ss[4]); ss[5] ^= ss[4]; k[6*(i)+11] = ff(ss[5]); \
+}
+#define kd6(k,i) \
+{   ss[6] = ls_box(ss[5],3) ^ t_use(r,c)[i]; \
+    ss[0] ^= ss[6]; ss[6] = ff(ss[6]); k[6*(i)+ 6] = ss[6] ^= k[6*(i)]; \
+    ss[1] ^= ss[0]; k[6*(i)+ 7] = ss[6] ^= k[6*(i)+ 1]; \
+    ss[2] ^= ss[1]; k[6*(i)+ 8] = ss[6] ^= k[6*(i)+ 2]; \
+    ss[3] ^= ss[2]; k[6*(i)+ 9] = ss[6] ^= k[6*(i)+ 3]; \
+    ss[4] ^= ss[3]; k[6*(i)+10] = ss[6] ^= k[6*(i)+ 4]; \
+    ss[5] ^= ss[4]; k[6*(i)+11] = ss[6] ^= k[6*(i)+ 5]; \
+}
+#define kdl6(k,i) \
+{   ss[0] ^= ls_box(ss[5],3) ^ t_use(r,c)[i]; k[6*(i)+ 6] = ss[0]; ss[1] ^= ss[0]; k[6*(i)+ 7] = ss[1]; \
+    ss[2] ^= ss[1]; k[6*(i)+ 8] = ss[2]; ss[3] ^= ss[2]; k[6*(i)+ 9] = ss[3]; \
+}
+
+#define kdf8(k,i) \
+{   ss[0] ^= ls_box(ss[7],3) ^ t_use(r,c)[i]; k[8*(i)+ 8] = ff(ss[0]); ss[1] ^= ss[0]; k[8*(i)+ 9] = ff(ss[1]); \
+    ss[2] ^= ss[1]; k[8*(i)+10] = ff(ss[2]); ss[3] ^= ss[2]; k[8*(i)+11] = ff(ss[3]); \
+    ss[4] ^= ls_box(ss[3],0); k[8*(i)+12] = ff(ss[4]); ss[5] ^= ss[4]; k[8*(i)+13] = ff(ss[5]); \
+    ss[6] ^= ss[5]; k[8*(i)+14] = ff(ss[6]); ss[7] ^= ss[6]; k[8*(i)+15] = ff(ss[7]); \
+}
+#define kd8(k,i) \
+{   aes_32t g = ls_box(ss[7],3) ^ t_use(r,c)[i]; \
+    ss[0] ^= g; g = ff(g); k[8*(i)+ 8] = g ^= k[8*(i)]; \
+    ss[1] ^= ss[0]; k[8*(i)+ 9] = g ^= k[8*(i)+ 1]; \
+    ss[2] ^= ss[1]; k[8*(i)+10] = g ^= k[8*(i)+ 2]; \
+    ss[3] ^= ss[2]; k[8*(i)+11] = g ^= k[8*(i)+ 3]; \
+    g = ls_box(ss[3],0); \
+    ss[4] ^= g; g = ff(g); k[8*(i)+12] = g ^= k[8*(i)+ 4]; \
+    ss[5] ^= ss[4]; k[8*(i)+13] = g ^= k[8*(i)+ 5]; \
+    ss[6] ^= ss[5]; k[8*(i)+14] = g ^= k[8*(i)+ 6]; \
+    ss[7] ^= ss[6]; k[8*(i)+15] = g ^= k[8*(i)+ 7]; \
+}
+#define kdl8(k,i) \
+{   ss[0] ^= ls_box(ss[7],3) ^ t_use(r,c)[i]; k[8*(i)+ 8] = ss[0]; ss[1] ^= ss[0]; k[8*(i)+ 9] = ss[1]; \
+    ss[2] ^= ss[1]; k[8*(i)+10] = ss[2]; ss[3] ^= ss[2]; k[8*(i)+11] = ss[3]; \
+}
+
+#if defined(AES_128) || defined(AES_VAR)
+
+aes_rval aes_decrypt_key128(const unsigned char *key, aes_decrypt_ctx cx[1])
+{   aes_32t    ss[5];
+#if defined( d_vars )
+        d_vars;
+#endif
+    cx->ks[0] = ss[0] = word_in(key, 0);
+    cx->ks[1] = ss[1] = word_in(key, 1);
+    cx->ks[2] = ss[2] = word_in(key, 2);
+    cx->ks[3] = ss[3] = word_in(key, 3);
+
+#if DEC_UNROLL == NONE
+    {   aes_32t i;
+
+        for(i = 0; i < (11 * N_COLS - 5) / 4; ++i)
+            ke4(cx->ks, i);
+        kel4(cx->ks, 9);
+#if !(DEC_ROUND == NO_TABLES)
+        for(i = N_COLS; i < 10 * N_COLS; ++i)
+            cx->ks[i] = inv_mcol(cx->ks[i]);
+#endif
+    }
+#else
+    kdf4(cx->ks, 0);  kd4(cx->ks, 1);
+     kd4(cx->ks, 2);  kd4(cx->ks, 3);
+     kd4(cx->ks, 4);  kd4(cx->ks, 5);
+     kd4(cx->ks, 6);  kd4(cx->ks, 7);
+     kd4(cx->ks, 8); kdl4(cx->ks, 9);
+#endif
+    cx->rn = 10;
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(AES_192) || defined(AES_VAR)
+
+aes_rval aes_decrypt_key192(const unsigned char *key, aes_decrypt_ctx cx[1])
+{   aes_32t    ss[7];
+#if defined( d_vars )
+        d_vars;
+#endif
+    cx->ks[0] = ss[0] = word_in(key, 0);
+    cx->ks[1] = ss[1] = word_in(key, 1);
+    cx->ks[2] = ss[2] = word_in(key, 2);
+    cx->ks[3] = ss[3] = word_in(key, 3);
+
+#if DEC_UNROLL == NONE
+    cx->ks[4] = ss[4] = word_in(key, 4);
+    cx->ks[5] = ss[5] = word_in(key, 5);
+    {   aes_32t i;
+
+        for(i = 0; i < (13 * N_COLS - 7) / 6; ++i)
+            ke6(cx->ks, i);
+        kel6(cx->ks, 7);
+#if !(DEC_ROUND == NO_TABLES)
+        for(i = N_COLS; i < 12 * N_COLS; ++i)
+            cx->ks[i] = inv_mcol(cx->ks[i]);
+#endif
+    }
+#else
+    cx->ks[4] = ff(ss[4] = word_in(key, 4));
+    cx->ks[5] = ff(ss[5] = word_in(key, 5));
+    kdf6(cx->ks, 0); kd6(cx->ks, 1);
+    kd6(cx->ks, 2);  kd6(cx->ks, 3);
+    kd6(cx->ks, 4);  kd6(cx->ks, 5);
+    kd6(cx->ks, 6); kdl6(cx->ks, 7);
+#endif
+    cx->rn = 12;
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(AES_256) || defined(AES_VAR)
+
+aes_rval aes_decrypt_key256(const unsigned char *key, aes_decrypt_ctx cx[1])
+{   aes_32t    ss[8];
+#if defined( d_vars )
+        d_vars;
+#endif
+    cx->ks[0] = ss[0] = word_in(key, 0);
+    cx->ks[1] = ss[1] = word_in(key, 1);
+    cx->ks[2] = ss[2] = word_in(key, 2);
+    cx->ks[3] = ss[3] = word_in(key, 3);
+
+#if DEC_UNROLL == NONE
+    cx->ks[4] = ss[4] = word_in(key, 4);
+    cx->ks[5] = ss[5] = word_in(key, 5);
+    cx->ks[6] = ss[6] = word_in(key, 6);
+    cx->ks[7] = ss[7] = word_in(key, 7);
+    {   aes_32t i;
+
+        for(i = 0; i < (15 * N_COLS - 9) / 8; ++i)
+            ke8(cx->ks,  i);
+        kel8(cx->ks,  i);
+#if !(DEC_ROUND == NO_TABLES)
+        for(i = N_COLS; i < 14 * N_COLS; ++i)
+            cx->ks[i] = inv_mcol(cx->ks[i]);
+
+#endif
+    }
+#else
+    cx->ks[4] = ff(ss[4] = word_in(key, 4));
+    cx->ks[5] = ff(ss[5] = word_in(key, 5));
+    cx->ks[6] = ff(ss[6] = word_in(key, 6));
+    cx->ks[7] = ff(ss[7] = word_in(key, 7));
+    kdf8(cx->ks, 0); kd8(cx->ks, 1);
+    kd8(cx->ks, 2);  kd8(cx->ks, 3);
+    kd8(cx->ks, 4);  kd8(cx->ks, 5);
+    kdl8(cx->ks, 6);
+#endif
+    cx->rn = 14;
+#if defined( AES_ERR_CHK )
+    return aes_good;
+#endif
+}
+
+#endif
+
+#if defined(AES_VAR)
+
+aes_rval aes_decrypt_key(const unsigned char *key, int key_len, aes_decrypt_ctx cx[1])
+{
+    switch(key_len)
+    {
+#if defined( AES_ERR_CHK )
+    case 16: case 128: return aes_decrypt_key128(key, cx);
+    case 24: case 192: return aes_decrypt_key192(key, cx);
+    case 32: case 256: return aes_decrypt_key256(key, cx);
+    default: return aes_error;
+#else
+    case 16: case 128: aes_decrypt_key128(key, cx); return;
+    case 24: case 192: aes_decrypt_key192(key, cx); return;
+    case 32: case 256: aes_decrypt_key256(key, cx); return;
+#endif
+    }
+}
+
+#endif
+
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
diff --git a/aesopt.h b/aesopt.h
new file mode 100644
index 0000000..d1acc68
--- /dev/null
+++ b/aesopt.h
@@ -0,0 +1,732 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+
+ My thanks go to Dag Arne Osvik for devising the schemes used here for key
+ length derivation from the form of the key schedule
+
+ This file contains the compilation options for AES (Rijndael) and code
+ that is common across encryption, key scheduling and table generation.
+
+ OPERATION
+
+ These source code files implement the AES algorithm Rijndael designed by
+ Joan Daemen and Vincent Rijmen. This version is designed for the standard
+ block size of 16 bytes and for key sizes of 128, 192 and 256 bits (16, 24
+ and 32 bytes).
+
+ This version is designed for flexibility and speed using operations on
+ 32-bit words rather than operations on bytes.  It can be compiled with
+ either big or little endian internal byte order but is faster when the
+ native byte order for the processor is used.
+
+ THE CIPHER INTERFACE
+
+ The cipher interface is implemented as an array of bytes in which lower
+ AES bit sequence indexes map to higher numeric significance within bytes.
+
+  aes_08t                 (an unsigned  8-bit type)
+  aes_32t                 (an unsigned 32-bit type)
+  struct aes_encrypt_ctx  (structure for the cipher encryption context)
+  struct aes_decrypt_ctx  (structure for the cipher decryption context)
+  aes_rval                the function return type
+
+  C subroutine calls:
+
+  aes_rval aes_encrypt_key128(const unsigned char *key, aes_encrypt_ctx cx[1]);
+  aes_rval aes_encrypt_key192(const unsigned char *key, aes_encrypt_ctx cx[1]);
+  aes_rval aes_encrypt_key256(const unsigned char *key, aes_encrypt_ctx cx[1]);
+  aes_rval aes_encrypt(const unsigned char *in, unsigned char *out,
+                                                  const aes_encrypt_ctx cx[1]);
+
+  aes_rval aes_decrypt_key128(const unsigned char *key, aes_decrypt_ctx cx[1]);
+  aes_rval aes_decrypt_key192(const unsigned char *key, aes_decrypt_ctx cx[1]);
+  aes_rval aes_decrypt_key256(const unsigned char *key, aes_decrypt_ctx cx[1]);
+  aes_rval aes_decrypt(const unsigned char *in, unsigned char *out,
+                                                  const aes_decrypt_ctx cx[1]);
+
+ IMPORTANT NOTE: If you are using this C interface with dynamic tables make sure that
+ you call genTabs() before AES is used so that the tables are initialised.
+
+ C++ aes class subroutines:
+
+     Class AESencrypt  for encryption
+
+      Construtors:
+          AESencrypt(void)
+          AESencrypt(const unsigned char *key) - 128 bit key
+      Members:
+          aes_rval key128(const unsigned char *key)
+          aes_rval key192(const unsigned char *key)
+          aes_rval key256(const unsigned char *key)
+          aes_rval encrypt(const unsigned char *in, unsigned char *out) const
+
+      Class AESdecrypt  for encryption
+      Construtors:
+          AESdecrypt(void)
+          AESdecrypt(const unsigned char *key) - 128 bit key
+      Members:
+          aes_rval key128(const unsigned char *key)
+          aes_rval key192(const unsigned char *key)
+          aes_rval key256(const unsigned char *key)
+          aes_rval decrypt(const unsigned char *in, unsigned char *out) const
+
+    COMPILATION
+
+    The files used to provide AES (Rijndael) are
+
+    a. aes.h for the definitions needed for use in C.
+    b. aescpp.h for the definitions needed for use in C++.
+    c. aesopt.h for setting compilation options (also includes common code).
+    d. aescrypt.c for encryption and decrytpion, or
+    e. aeskey.c for key scheduling.
+    f. aestab.c for table loading or generation.
+    g. aescrypt.asm for encryption and decryption using assembler code.
+    h. aescrypt.mmx.asm for encryption and decryption using MMX assembler.
+
+    To compile AES (Rijndael) for use in C code use aes.h and set the
+    defines here for the facilities you need (key lengths, encryption
+    and/or decryption). Do not define AES_DLL or AES_CPP.  Set the options
+    for optimisations and table sizes here.
+
+    To compile AES (Rijndael) for use in in C++ code use aescpp.h but do
+    not define AES_DLL
+
+    To compile AES (Rijndael) in C as a Dynamic Link Library DLL) use
+    aes.h and include the AES_DLL define.
+
+    CONFIGURATION OPTIONS (here and in aes.h)
+
+    a. set AES_DLL in aes.h if AES (Rijndael) is to be compiled as a DLL
+    b. You may need to set PLATFORM_BYTE_ORDER to define the byte order.
+    c. If you want the code to run in a specific internal byte order, then
+       ALGORITHM_BYTE_ORDER must be set accordingly.
+    d. set other configuration options decribed below.
+*/
+
+#if !defined( _AESOPT_H )
+#define _AESOPT_H
+
+#include "aes.h"
+
+/*  CONFIGURATION - USE OF DEFINES
+
+    Later in this section there are a number of defines that control the
+    operation of the code.  In each section, the purpose of each define is
+    explained so that the relevant form can be included or excluded by
+    setting either 1's or 0's respectively on the branches of the related
+    #if clauses.
+
+    PLATFORM SPECIFIC INCLUDES AND BYTE ORDER IN 32-BIT WORDS
+
+    To obtain the highest speed on processors with 32-bit words, this code
+    needs to determine the byte order of the target machine. The following
+    block of code is an attempt to capture the most obvious ways in which
+    various environemnts define byte order. It may well fail, in which case
+    the definitions will need to be set by editing at the points marked
+    **** EDIT HERE IF NECESSARY **** below.  My thanks go to Peter Gutmann
+    for his assistance with this endian detection nightmare.
+*/
+
+#define BRG_LITTLE_ENDIAN   1234 /* byte 0 is least significant (i386) */
+#define BRG_BIG_ENDIAN      4321 /* byte 0 is most significant (mc68k) */
+
+#if defined(__GNUC__) || defined(__GNU_LIBRARY__)
+#  if defined(__FreeBSD__) || defined(__OpenBSD__)
+#    include <sys/endian.h>
+#  elif defined( BSD ) && BSD >= 199103
+#      include <machine/endian.h>
+#  elif defined(__APPLE__)
+#    if defined(__BIG_ENDIAN__) && !defined( BIG_ENDIAN )
+#      define BIG_ENDIAN
+#    elif defined(__LITTLE_ENDIAN__) && !defined( LITTLE_ENDIAN )
+#      define LITTLE_ENDIAN
+#    endif
+#  else
+#    include <stdio.h>  /* for detecting newlib */
+#    if defined(_NEWLIB_VERSION)
+#      include <sys/param.h> /* doesn't help with newlib 1.13 because it doesnt define LITTLE/BIG_ENDIAN */
+#    else
+#      include <endian.h>
+#    endif
+#    if defined(__BEOS__)
+#      include <byteswap.h>
+#    endif
+#  endif
+#endif
+
+#if !defined(PLATFORM_BYTE_ORDER)
+#  if defined(LITTLE_ENDIAN) || defined(BIG_ENDIAN)
+#    if    defined(LITTLE_ENDIAN) && !defined(BIG_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#    elif !defined(LITTLE_ENDIAN) &&  defined(BIG_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#    elif defined(BYTE_ORDER) && (BYTE_ORDER == LITTLE_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#    elif defined(BYTE_ORDER) && (BYTE_ORDER == BIG_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#    endif
+#  elif defined(_LITTLE_ENDIAN) || defined(_BIG_ENDIAN)
+#    if    defined(_LITTLE_ENDIAN) && !defined(_BIG_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#    elif !defined(_LITTLE_ENDIAN) &&  defined(_BIG_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#    elif defined(_BYTE_ORDER) && (_BYTE_ORDER == _LITTLE_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#    elif defined(_BYTE_ORDER) && (_BYTE_ORDER == _BIG_ENDIAN)
+#      define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#   endif
+#  elif defined(__LITTLE_ENDIAN__) || defined(__BIG_ENDIAN__)
+#    if    defined(__LITTLE_ENDIAN__) && !defined(__BIG_ENDIAN__)
+#      define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#    elif !defined(__LITTLE_ENDIAN__) &&  defined(__BIG_ENDIAN__)
+#      define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#    elif defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __LITTLE_ENDIAN__)
+#      define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#    elif defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __BIG_ENDIAN__)
+#      define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#    endif
+#  endif
+#endif
+
+/*  if the platform is still unknown, try to find its byte order    */
+/*  from commonly used machine defines                              */
+
+#if !defined(PLATFORM_BYTE_ORDER)
+
+#if   defined( __alpha__ ) || defined( __alpha ) || defined( i386 )       || \
+      defined( __i386__ )  || defined( _M_I86 )  || defined( _M_IX86 )    || \
+      defined( __OS2__ )   || defined( sun386 )  || defined( __TURBOC__ ) || \
+      defined( vax )       || defined( vms )     || defined( VMS )        || \
+      defined( __VMS )
+#  define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+
+#elif defined( AMIGA )    || defined( applec )  || defined( __AS400__ )  || \
+      defined( _CRAY )    || defined( __hppa )  || defined( __hp9000 )   || \
+      defined( ibm370 )   || defined( mc68000 ) || defined( m68k )       || \
+      defined( __MRC__ )  || defined( __MVS__ ) || defined( __MWERKS__ ) || \
+      defined( sparc )    || defined( __sparc)  || defined( SYMANTEC_C ) || \
+      defined( __TANDEM ) || defined( THINK_C ) || defined( __VMCMS__ )
+#  define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+
+#elif defined(_WIN32_WCE) || !defined(JBED_BIG_ENDIAN)    /* **** EDIT HERE IF NECESSARY **** */
+#  define PLATFORM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#elif defined(JBED_BIG_ENDIAN)     /* **** EDIT HERE IF NECESSARY **** */
+#  define PLATFORM_BYTE_ORDER BRG_BIG_ENDIAN
+#else
+#  error Please edit aesopt.h (line 239 or 241) to set the platform byte order
+#endif
+
+#endif
+
+/*  SOME LOCAL DEFINITIONS  */
+
+#define NO_TABLES              0
+#define ONE_TABLE              1
+#define FOUR_TABLES            4
+#define NONE                   0
+#define PARTIAL                1
+#define FULL                   2
+
+#if defined(bswap32)
+#define aes_sw32    bswap32
+#elif defined(bswap_32)
+#define aes_sw32    bswap_32
+#else
+#define brot(x,n)   (((aes_32t)(x) <<  n) | ((aes_32t)(x) >> (32 - n)))
+#define aes_sw32(x) ((brot((x),8) & 0x00ff00ff) | (brot((x),24) & 0xff00ff00))
+#endif
+
+/*  1. FUNCTIONS REQUIRED
+
+    This implementation provides subroutines for encryption, decryption
+    and for setting the three key lengths (separately) for encryption
+    and decryption. When the assembler code is not being used the following
+    definition blocks allow the selection of the routines that are to be
+    included in the compilation.
+*/
+#if defined( AES_ENCRYPT )
+#define ENCRYPTION
+#define ENCRYPTION_KEY_SCHEDULE
+#endif
+
+#if defined( AES_DECRYPT )
+#define DECRYPTION
+#define DECRYPTION_KEY_SCHEDULE
+#endif
+
+/*  2. ASSEMBLER SUPPORT
+
+    This define (which can be on the command line) enables the use of the
+    assembler code routines for encryption and decryption with the C code
+    only providing key scheduling
+*/
+#if 0 && !defined(AES_ASM)
+#define AES_ASM
+#endif
+
+/*  3. BYTE ORDER WITHIN 32 BIT WORDS
+
+    The fundamental data processing units in Rijndael are 8-bit bytes. The
+    input, output and key input are all enumerated arrays of bytes in which
+    bytes are numbered starting at zero and increasing to one less than the
+    number of bytes in the array in question. This enumeration is only used
+    for naming bytes and does not imply any adjacency or order relationship
+    from one byte to another. When these inputs and outputs are considered
+    as bit sequences, bits 8*n to 8*n+7 of the bit sequence are mapped to
+    byte[n] with bit 8n+i in the sequence mapped to bit 7-i within the byte.
+    In this implementation bits are numbered from 0 to 7 starting at the
+    numerically least significant end of each byte (bit n represents 2^n).
+
+    However, Rijndael can be implemented more efficiently using 32-bit
+    words by packing bytes into words so that bytes 4*n to 4*n+3 are placed
+    into word[n]. While in principle these bytes can be assembled into words
+    in any positions, this implementation only supports the two formats in
+    which bytes in adjacent positions within words also have adjacent byte
+    numbers. This order is called big-endian if the lowest numbered bytes
+    in words have the highest numeric significance and little-endian if the
+    opposite applies.
+
+    This code can work in either order irrespective of the order used by the
+    machine on which it runs. Normally the internal byte order will be set
+    to the order of the processor on which the code is to be run but this
+    define can be used to reverse this in special situations
+
+    NOTE: Assembler code versions rely on PLATFORM_BYTE_ORDER being set
+*/
+#if 1 || defined(AES_ASM)
+#define ALGORITHM_BYTE_ORDER PLATFORM_BYTE_ORDER
+#elif 0
+#define ALGORITHM_BYTE_ORDER BRG_LITTLE_ENDIAN
+#elif 0
+#define ALGORITHM_BYTE_ORDER BRG_BIG_ENDIAN
+#else
+#error The algorithm byte order is not defined
+#endif
+
+/*  4. FAST INPUT/OUTPUT OPERATIONS.
+
+    On some machines it is possible to improve speed by transferring the
+    bytes in the input and output arrays to and from the internal 32-bit
+    variables by addressing these arrays as if they are arrays of 32-bit
+    words.  On some machines this will always be possible but there may
+    be a large performance penalty if the byte arrays are not aligned on
+    the normal word boundaries. On other machines this technique will
+    lead to memory access errors when such 32-bit word accesses are not
+    properly aligned. The option SAFE_IO avoids such problems but will
+    often be slower on those machines that support misaligned access
+    (especially so if care is taken to align the input  and output byte
+    arrays on 32-bit word boundaries). If SAFE_IO is not defined it is
+    assumed that access to byte arrays as if they are arrays of 32-bit
+    words will not cause problems when such accesses are misaligned.
+*/
+#if 1 && !defined(_MSC_VER)
+#define SAFE_IO
+#endif
+
+/*  5. LOOP UNROLLING
+
+    The code for encryption and decrytpion cycles through a number of rounds
+    that can be implemented either in a loop or by expanding the code into a
+    long sequence of instructions, the latter producing a larger program but
+    one that will often be much faster. The latter is called loop unrolling.
+    There are also potential speed advantages in expanding two iterations in
+    a loop with half the number of iterations, which is called partial loop
+    unrolling.  The following options allow partial or full loop unrolling
+    to be set independently for encryption and decryption
+*/
+#if 1
+#define ENC_UNROLL  FULL
+#elif 0
+#define ENC_UNROLL  PARTIAL
+#else
+#define ENC_UNROLL  NONE
+#endif
+
+#if 1
+#define DEC_UNROLL  FULL
+#elif 0
+#define DEC_UNROLL  PARTIAL
+#else
+#define DEC_UNROLL  NONE
+#endif
+
+/*  6. FAST FINITE FIELD OPERATIONS
+
+    If this section is included, tables are used to provide faster finite
+    field arithmetic (this has no effect if FIXED_TABLES is defined).
+*/
+#if 1
+#define FF_TABLES
+#endif
+
+/*  7. INTERNAL STATE VARIABLE FORMAT
+
+    The internal state of Rijndael is stored in a number of local 32-bit
+    word varaibles which can be defined either as an array or as individual
+    names variables. Include this section if you want to store these local
+    varaibles in arrays. Otherwise individual local variables will be used.
+*/
+#if 1
+#define ARRAYS
+#endif
+
+/* In this implementation the columns of the state array are each held in
+   32-bit words. The state array can be held in various ways: in an array
+   of words, in a number of individual word variables or in a number of
+   processor registers. The following define maps a variable name x and
+   a column number c to the way the state array variable is to be held.
+   The first define below maps the state into an array x[c] whereas the
+   second form maps the state into a number of individual variables x0,
+   x1, etc.  Another form could map individual state colums to machine
+   register names.
+*/
+
+#if defined(ARRAYS)
+#define s(x,c) x[c]
+#else
+#define s(x,c) x##c
+#endif
+
+/*  8. FIXED OR DYNAMIC TABLES
+
+    When this section is included the tables used by the code are compiled
+    statically into the binary file.  Otherwise the subroutine gen_tabs()
+    must be called to compute them before the code is first used.
+*/
+#if 1
+#define FIXED_TABLES
+#endif
+
+/*  9. TABLE ALIGNMENT
+
+    On some sytsems speed will be improved by aligning the AES large lookup
+    tables on particular boundaries. This define should be set to a power of
+    two giving the desired alignment. It can be left undefined if alignment
+    is not needed.  This option is specific to the Microsft VC++ compiler -
+    it seems to sometimes cause trouble for the VC++ version 6 compiler.
+*/
+
+#if 0 && defined(_MSC_VER) && (_MSC_VER >= 1300)
+#define TABLE_ALIGN 64
+#endif
+
+/*  10. INTERNAL TABLE CONFIGURATION
+
+    This cipher proceeds by repeating in a number of cycles known as 'rounds'
+    which are implemented by a round function which can optionally be speeded
+    up using tables.  The basic tables are each 256 32-bit words, with either
+    one or four tables being required for each round function depending on
+    how much speed is required. The encryption and decryption round functions
+    are different and the last encryption and decrytpion round functions are
+    different again making four different round functions in all.
+
+    This means that:
+      1. Normal encryption and decryption rounds can each use either 0, 1
+         or 4 tables and table spaces of 0, 1024 or 4096 bytes each.
+      2. The last encryption and decryption rounds can also use either 0, 1
+         or 4 tables and table spaces of 0, 1024 or 4096 bytes each.
+
+    Include or exclude the appropriate definitions below to set the number
+    of tables used by this implementation.
+*/
+
+#if 1   /* set tables for the normal encryption round */
+#define ENC_ROUND   FOUR_TABLES
+#elif 0
+#define ENC_ROUND   ONE_TABLE
+#else
+#define ENC_ROUND   NO_TABLES
+#endif
+
+#if 1   /* set tables for the last encryption round */
+#define LAST_ENC_ROUND  FOUR_TABLES
+#elif 0
+#define LAST_ENC_ROUND  ONE_TABLE
+#else
+#define LAST_ENC_ROUND  NO_TABLES
+#endif
+
+#if 1   /* set tables for the normal decryption round */
+#define DEC_ROUND   FOUR_TABLES
+#elif 0
+#define DEC_ROUND   ONE_TABLE
+#else
+#define DEC_ROUND   NO_TABLES
+#endif
+
+#if 1   /* set tables for the last decryption round */
+#define LAST_DEC_ROUND  FOUR_TABLES
+#elif 0
+#define LAST_DEC_ROUND  ONE_TABLE
+#else
+#define LAST_DEC_ROUND  NO_TABLES
+#endif
+
+/*  The decryption key schedule can be speeded up with tables in the same
+    way that the round functions can.  Include or exclude the following
+    defines to set this requirement.
+*/
+#if 1
+#define KEY_SCHED   FOUR_TABLES
+#elif 0
+#define KEY_SCHED   ONE_TABLE
+#else
+#define KEY_SCHED   NO_TABLES
+#endif
+
+/* END OF CONFIGURATION OPTIONS */
+
+#define RC_LENGTH   (5 * (AES_BLOCK_SIZE / 4 - 2))
+
+/* Disable or report errors on some combinations of options */
+
+#if ENC_ROUND == NO_TABLES && LAST_ENC_ROUND != NO_TABLES
+#undef  LAST_ENC_ROUND
+#define LAST_ENC_ROUND  NO_TABLES
+#elif ENC_ROUND == ONE_TABLE && LAST_ENC_ROUND == FOUR_TABLES
+#undef  LAST_ENC_ROUND
+#define LAST_ENC_ROUND  ONE_TABLE
+#endif
+
+#if ENC_ROUND == NO_TABLES && ENC_UNROLL != NONE
+#undef  ENC_UNROLL
+#define ENC_UNROLL  NONE
+#endif
+
+#if DEC_ROUND == NO_TABLES && LAST_DEC_ROUND != NO_TABLES
+#undef  LAST_DEC_ROUND
+#define LAST_DEC_ROUND  NO_TABLES
+#elif DEC_ROUND == ONE_TABLE && LAST_DEC_ROUND == FOUR_TABLES
+#undef  LAST_DEC_ROUND
+#define LAST_DEC_ROUND  ONE_TABLE
+#endif
+
+#if DEC_ROUND == NO_TABLES && DEC_UNROLL != NONE
+#undef  DEC_UNROLL
+#define DEC_UNROLL  NONE
+#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
+
+    NOTE:      The definitions given here are intended only for use with
+               unsigned variables and with shift counts that are compile
+               time constants
+*/
+
+#if (ALGORITHM_BYTE_ORDER == BRG_LITTLE_ENDIAN)
+#define upr(x,n)        (((aes_32t)(x) << (8 * (n))) | ((aes_32t)(x) >> (32 - 8 * (n))))
+#define ups(x,n)        ((aes_32t) (x) << (8 * (n)))
+#define bval(x,n)       ((aes_08t)((x) >> (8 * (n))))
+#define bytes2word(b0, b1, b2, b3)  \
+        (((aes_32t)(b3) << 24) | ((aes_32t)(b2) << 16) | ((aes_32t)(b1) << 8) | (b0))
+#endif
+
+#if (ALGORITHM_BYTE_ORDER == BRG_BIG_ENDIAN)
+#define upr(x,n)        (((aes_32t)(x) >> (8 * (n))) | ((aes_32t)(x) << (32 - 8 * (n))))
+#define ups(x,n)        ((aes_32t) (x) >> (8 * (n))))
+#define bval(x,n)       ((aes_08t)((x) >> (24 - 8 * (n))))
+#define bytes2word(b0, b1, b2, b3)  \
+        (((aes_32t)(b0) << 24) | ((aes_32t)(b1) << 16) | ((aes_32t)(b2) << 8) | (b3))
+#endif
+
+#if defined(SAFE_IO)
+
+#define word_in(x,c)    bytes2word(((aes_08t*)(x)+4*c)[0], ((aes_08t*)(x)+4*c)[1], \
+                                   ((aes_08t*)(x)+4*c)[2], ((aes_08t*)(x)+4*c)[3])
+#define word_out(x,c,v) { ((aes_08t*)(x)+4*c)[0] = bval(v,0); ((aes_08t*)(x)+4*c)[1] = bval(v,1); \
+                          ((aes_08t*)(x)+4*c)[2] = bval(v,2); ((aes_08t*)(x)+4*c)[3] = bval(v,3); }
+
+#elif (ALGORITHM_BYTE_ORDER == PLATFORM_BYTE_ORDER)
+
+#define word_in(x,c)    (*((aes_32t*)(x)+(c)))
+#define word_out(x,c,v) (*((aes_32t*)(x)+(c)) = (v))
+
+#else
+
+#define word_in(x,c)    aes_sw32(*((aes_32t*)(x)+(c)))
+#define word_out(x,c,v) (*((aes_32t*)(x)+(c)) = aes_sw32(v))
+
+#endif
+
+/* the finite field modular polynomial and elements */
+
+#define WPOLY   0x011b
+#define BPOLY     0x1b
+
+/* multiply four bytes in GF(2^8) by 'x' {02} in parallel */
+
+#define m1  0x80808080
+#define m2  0x7f7f7f7f
+#define gf_mulx(x)  ((((x) & m2) << 1) ^ ((((x) & m1) >> 7) * BPOLY))
+
+/* The following defines provide alternative definitions of gf_mulx 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 gf_mulx is used.
+
+#define gf_mulx(x) (u = (x) & m1, u |= (u >> 1), ((x) & m2) << 1) ^ ((u >> 3) | (u >> 6))
+#define m4  (0x01010101 * BPOLY)
+#define gf_mulx(x) (u = (x) & m1, ((x) & m2) << 1) ^ ((u - (u >> 7)) & m4)
+*/
+
+/* Work out which tables are needed for the different options   */
+
+#if defined( AES_ASM )
+#if defined( ENC_ROUND )
+#undef  ENC_ROUND
+#endif
+#define ENC_ROUND   FOUR_TABLES
+#if defined( LAST_ENC_ROUND )
+#undef  LAST_ENC_ROUND
+#endif
+#define LAST_ENC_ROUND  FOUR_TABLES
+#if defined( DEC_ROUND )
+#undef  DEC_ROUND
+#endif
+#define DEC_ROUND   FOUR_TABLES
+#if defined( LAST_DEC_ROUND )
+#undef  LAST_DEC_ROUND
+#endif
+#define LAST_DEC_ROUND  FOUR_TABLES
+#if defined( KEY_SCHED )
+#undef  KEY_SCHED
+#define KEY_SCHED   FOUR_TABLES
+#endif
+#endif
+
+#if defined(ENCRYPTION) || defined(AES_ASM)
+#if ENC_ROUND == ONE_TABLE
+#define FT1_SET
+#elif ENC_ROUND == FOUR_TABLES
+#define FT4_SET
+#else
+#define SBX_SET
+#endif
+#if LAST_ENC_ROUND == ONE_TABLE
+#define FL1_SET
+#elif LAST_ENC_ROUND == FOUR_TABLES
+#define FL4_SET
+#elif !defined(SBX_SET)
+#define SBX_SET
+#endif
+#endif
+
+#if defined(DECRYPTION) || defined(AES_ASM)
+#if DEC_ROUND == ONE_TABLE
+#define IT1_SET
+#elif DEC_ROUND == FOUR_TABLES
+#define IT4_SET
+#else
+#define ISB_SET
+#endif
+#if LAST_DEC_ROUND == ONE_TABLE
+#define IL1_SET
+#elif LAST_DEC_ROUND == FOUR_TABLES
+#define IL4_SET
+#elif !defined(ISB_SET)
+#define ISB_SET
+#endif
+#endif
+
+#if defined(ENCRYPTION_KEY_SCHEDULE) || defined(DECRYPTION_KEY_SCHEDULE)
+#if KEY_SCHED == ONE_TABLE
+#define LS1_SET
+#define IM1_SET
+#elif KEY_SCHED == FOUR_TABLES
+#define LS4_SET
+#define IM4_SET
+#elif !defined(SBX_SET)
+#define SBX_SET
+#endif
+#endif
+
+/* generic definitions of Rijndael macros that use tables    */
+
+#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)    ((8+r-c)&3)
+
+/* perform forward and inverse column mix operation on four bytes in long word x in */
+/* parallel. NOTE: x must be a simple variable, NOT an expression in these macros.  */
+
+#if defined(FM4_SET)    /* not currently used */
+#define fwd_mcol(x)     four_tables(x,t_use(f,m),vf1,rf1,0)
+#elif defined(FM1_SET)  /* not currently used */
+#define fwd_mcol(x)     one_table(x,upr,t_use(f,m),vf1,rf1,0)
+#else
+#define dec_fmvars      aes_32t g2
+#define fwd_mcol(x)     (g2 = gf_mulx(x), g2 ^ upr((x) ^ g2, 3) ^ upr((x), 2) ^ upr((x), 1))
+#endif
+
+#if defined(IM4_SET)
+#define inv_mcol(x)     four_tables(x,t_use(i,m),vf1,rf1,0)
+#elif defined(IM1_SET)
+#define inv_mcol(x)     one_table(x,upr,t_use(i,m),vf1,rf1,0)
+#else
+#define dec_imvars      aes_32t g2, g4, g9
+#define inv_mcol(x)     (g2 = gf_mulx(x), g4 = gf_mulx(g2), g9 = (x) ^ gf_mulx(g4), g4 ^= g9, \
+                        (x) ^ g2 ^ g4 ^ upr(g2 ^ g9, 3) ^ upr(g4, 2) ^ upr(g9, 1))
+#endif
+
+#if defined(FL4_SET)
+#define ls_box(x,c)     four_tables(x,t_use(f,l),vf1,rf2,c)
+#elif   defined(LS4_SET)
+#define ls_box(x,c)     four_tables(x,t_use(l,s),vf1,rf2,c)
+#elif defined(FL1_SET)
+#define ls_box(x,c)     one_table(x,upr,t_use(f,l),vf1,rf2,c)
+#elif defined(LS1_SET)
+#define ls_box(x,c)     one_table(x,upr,t_use(l,s),vf1,rf2,c)
+#else
+#define ls_box(x,c)     no_table(x,t_use(s,box),vf1,rf2,c)
+#endif
+
+#endif
diff --git a/aestab.c b/aestab.c
new file mode 100644
index 0000000..7997f29
--- /dev/null
+++ b/aestab.c
@@ -0,0 +1,384 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+
+*/
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+
+#define DO_TABLES
+
+#include "aesopt.h"
+
+#if defined(FIXED_TABLES)
+
+#define sb_data(w) {\
+    w(0x63), w(0x7c), w(0x77), w(0x7b), w(0xf2), w(0x6b), w(0x6f), w(0xc5),\
+    w(0x30), w(0x01), w(0x67), w(0x2b), w(0xfe), w(0xd7), w(0xab), w(0x76),\
+    w(0xca), w(0x82), w(0xc9), w(0x7d), w(0xfa), w(0x59), w(0x47), w(0xf0),\
+    w(0xad), w(0xd4), w(0xa2), w(0xaf), w(0x9c), w(0xa4), w(0x72), w(0xc0),\
+    w(0xb7), w(0xfd), w(0x93), w(0x26), w(0x36), w(0x3f), w(0xf7), w(0xcc),\
+    w(0x34), w(0xa5), w(0xe5), w(0xf1), w(0x71), w(0xd8), w(0x31), w(0x15),\
+    w(0x04), w(0xc7), w(0x23), w(0xc3), w(0x18), w(0x96), w(0x05), w(0x9a),\
+    w(0x07), w(0x12), w(0x80), w(0xe2), w(0xeb), w(0x27), w(0xb2), w(0x75),\
+    w(0x09), w(0x83), w(0x2c), w(0x1a), w(0x1b), w(0x6e), w(0x5a), w(0xa0),\
+    w(0x52), w(0x3b), w(0xd6), w(0xb3), w(0x29), w(0xe3), w(0x2f), w(0x84),\
+    w(0x53), w(0xd1), w(0x00), w(0xed), w(0x20), w(0xfc), w(0xb1), w(0x5b),\
+    w(0x6a), w(0xcb), w(0xbe), w(0x39), w(0x4a), w(0x4c), w(0x58), w(0xcf),\
+    w(0xd0), w(0xef), w(0xaa), w(0xfb), w(0x43), w(0x4d), w(0x33), w(0x85),\
+    w(0x45), w(0xf9), w(0x02), w(0x7f), w(0x50), w(0x3c), w(0x9f), w(0xa8),\
+    w(0x51), w(0xa3), w(0x40), w(0x8f), w(0x92), w(0x9d), w(0x38), w(0xf5),\
+    w(0xbc), w(0xb6), w(0xda), w(0x21), w(0x10), w(0xff), w(0xf3), w(0xd2),\
+    w(0xcd), w(0x0c), w(0x13), w(0xec), w(0x5f), w(0x97), w(0x44), w(0x17),\
+    w(0xc4), w(0xa7), w(0x7e), w(0x3d), w(0x64), w(0x5d), w(0x19), w(0x73),\
+    w(0x60), w(0x81), w(0x4f), w(0xdc), w(0x22), w(0x2a), w(0x90), w(0x88),\
+    w(0x46), w(0xee), w(0xb8), w(0x14), w(0xde), w(0x5e), w(0x0b), w(0xdb),\
+    w(0xe0), w(0x32), w(0x3a), w(0x0a), w(0x49), w(0x06), w(0x24), w(0x5c),\
+    w(0xc2), w(0xd3), w(0xac), w(0x62), w(0x91), w(0x95), w(0xe4), w(0x79),\
+    w(0xe7), w(0xc8), w(0x37), w(0x6d), w(0x8d), w(0xd5), w(0x4e), w(0xa9),\
+    w(0x6c), w(0x56), w(0xf4), w(0xea), w(0x65), w(0x7a), w(0xae), w(0x08),\
+    w(0xba), w(0x78), w(0x25), w(0x2e), w(0x1c), w(0xa6), w(0xb4), w(0xc6),\
+    w(0xe8), w(0xdd), w(0x74), w(0x1f), w(0x4b), w(0xbd), w(0x8b), w(0x8a),\
+    w(0x70), w(0x3e), w(0xb5), w(0x66), w(0x48), w(0x03), w(0xf6), w(0x0e),\
+    w(0x61), w(0x35), w(0x57), w(0xb9), w(0x86), w(0xc1), w(0x1d), w(0x9e),\
+    w(0xe1), w(0xf8), w(0x98), w(0x11), w(0x69), w(0xd9), w(0x8e), w(0x94),\
+    w(0x9b), w(0x1e), w(0x87), w(0xe9), w(0xce), w(0x55), w(0x28), w(0xdf),\
+    w(0x8c), w(0xa1), w(0x89), w(0x0d), w(0xbf), w(0xe6), w(0x42), w(0x68),\
+    w(0x41), w(0x99), w(0x2d), w(0x0f), w(0xb0), w(0x54), w(0xbb), w(0x16) }
+
+#define isb_data(w) {\
+    w(0x52), w(0x09), w(0x6a), w(0xd5), w(0x30), w(0x36), w(0xa5), w(0x38),\
+    w(0xbf), w(0x40), w(0xa3), w(0x9e), w(0x81), w(0xf3), w(0xd7), w(0xfb),\
+    w(0x7c), w(0xe3), w(0x39), w(0x82), w(0x9b), w(0x2f), w(0xff), w(0x87),\
+    w(0x34), w(0x8e), w(0x43), w(0x44), w(0xc4), w(0xde), w(0xe9), w(0xcb),\
+    w(0x54), w(0x7b), w(0x94), w(0x32), w(0xa6), w(0xc2), w(0x23), w(0x3d),\
+    w(0xee), w(0x4c), w(0x95), w(0x0b), w(0x42), w(0xfa), w(0xc3), w(0x4e),\
+    w(0x08), w(0x2e), w(0xa1), w(0x66), w(0x28), w(0xd9), w(0x24), w(0xb2),\
+    w(0x76), w(0x5b), w(0xa2), w(0x49), w(0x6d), w(0x8b), w(0xd1), w(0x25),\
+    w(0x72), w(0xf8), w(0xf6), w(0x64), w(0x86), w(0x68), w(0x98), w(0x16),\
+    w(0xd4), w(0xa4), w(0x5c), w(0xcc), w(0x5d), w(0x65), w(0xb6), w(0x92),\
+    w(0x6c), w(0x70), w(0x48), w(0x50), w(0xfd), w(0xed), w(0xb9), w(0xda),\
+    w(0x5e), w(0x15), w(0x46), w(0x57), w(0xa7), w(0x8d), w(0x9d), w(0x84),\
+    w(0x90), w(0xd8), w(0xab), w(0x00), w(0x8c), w(0xbc), w(0xd3), w(0x0a),\
+    w(0xf7), w(0xe4), w(0x58), w(0x05), w(0xb8), w(0xb3), w(0x45), w(0x06),\
+    w(0xd0), w(0x2c), w(0x1e), w(0x8f), w(0xca), w(0x3f), w(0x0f), w(0x02),\
+    w(0xc1), w(0xaf), w(0xbd), w(0x03), w(0x01), w(0x13), w(0x8a), w(0x6b),\
+    w(0x3a), w(0x91), w(0x11), w(0x41), w(0x4f), w(0x67), w(0xdc), w(0xea),\
+    w(0x97), w(0xf2), w(0xcf), w(0xce), w(0xf0), w(0xb4), w(0xe6), w(0x73),\
+    w(0x96), w(0xac), w(0x74), w(0x22), w(0xe7), w(0xad), w(0x35), w(0x85),\
+    w(0xe2), w(0xf9), w(0x37), w(0xe8), w(0x1c), w(0x75), w(0xdf), w(0x6e),\
+    w(0x47), w(0xf1), w(0x1a), w(0x71), w(0x1d), w(0x29), w(0xc5), w(0x89),\
+    w(0x6f), w(0xb7), w(0x62), w(0x0e), w(0xaa), w(0x18), w(0xbe), w(0x1b),\
+    w(0xfc), w(0x56), w(0x3e), w(0x4b), w(0xc6), w(0xd2), w(0x79), w(0x20),\
+    w(0x9a), w(0xdb), w(0xc0), w(0xfe), w(0x78), w(0xcd), w(0x5a), w(0xf4),\
+    w(0x1f), w(0xdd), w(0xa8), w(0x33), w(0x88), w(0x07), w(0xc7), w(0x31),\
+    w(0xb1), w(0x12), w(0x10), w(0x59), w(0x27), w(0x80), w(0xec), w(0x5f),\
+    w(0x60), w(0x51), w(0x7f), w(0xa9), w(0x19), w(0xb5), w(0x4a), w(0x0d),\
+    w(0x2d), w(0xe5), w(0x7a), w(0x9f), w(0x93), w(0xc9), w(0x9c), w(0xef),\
+    w(0xa0), w(0xe0), w(0x3b), w(0x4d), w(0xae), w(0x2a), w(0xf5), w(0xb0),\
+    w(0xc8), w(0xeb), w(0xbb), w(0x3c), w(0x83), w(0x53), w(0x99), w(0x61),\
+    w(0x17), w(0x2b), w(0x04), w(0x7e), w(0xba), w(0x77), w(0xd6), w(0x26),\
+    w(0xe1), w(0x69), w(0x14), w(0x63), w(0x55), w(0x21), w(0x0c), w(0x7d) }
+
+#define mm_data(w) {\
+    w(0x00), w(0x01), w(0x02), w(0x03), w(0x04), w(0x05), w(0x06), w(0x07),\
+    w(0x08), w(0x09), w(0x0a), w(0x0b), w(0x0c), w(0x0d), w(0x0e), w(0x0f),\
+    w(0x10), w(0x11), w(0x12), w(0x13), w(0x14), w(0x15), w(0x16), w(0x17),\
+    w(0x18), w(0x19), w(0x1a), w(0x1b), w(0x1c), w(0x1d), w(0x1e), w(0x1f),\
+    w(0x20), w(0x21), w(0x22), w(0x23), w(0x24), w(0x25), w(0x26), w(0x27),\
+    w(0x28), w(0x29), w(0x2a), w(0x2b), w(0x2c), w(0x2d), w(0x2e), w(0x2f),\
+    w(0x30), w(0x31), w(0x32), w(0x33), w(0x34), w(0x35), w(0x36), w(0x37),\
+    w(0x38), w(0x39), w(0x3a), w(0x3b), w(0x3c), w(0x3d), w(0x3e), w(0x3f),\
+    w(0x40), w(0x41), w(0x42), w(0x43), w(0x44), w(0x45), w(0x46), w(0x47),\
+    w(0x48), w(0x49), w(0x4a), w(0x4b), w(0x4c), w(0x4d), w(0x4e), w(0x4f),\
+    w(0x50), w(0x51), w(0x52), w(0x53), w(0x54), w(0x55), w(0x56), w(0x57),\
+    w(0x58), w(0x59), w(0x5a), w(0x5b), w(0x5c), w(0x5d), w(0x5e), w(0x5f),\
+    w(0x60), w(0x61), w(0x62), w(0x63), w(0x64), w(0x65), w(0x66), w(0x67),\
+    w(0x68), w(0x69), w(0x6a), w(0x6b), w(0x6c), w(0x6d), w(0x6e), w(0x6f),\
+    w(0x70), w(0x71), w(0x72), w(0x73), w(0x74), w(0x75), w(0x76), w(0x77),\
+    w(0x78), w(0x79), w(0x7a), w(0x7b), w(0x7c), w(0x7d), w(0x7e), w(0x7f),\
+    w(0x80), w(0x81), w(0x82), w(0x83), w(0x84), w(0x85), w(0x86), w(0x87),\
+    w(0x88), w(0x89), w(0x8a), w(0x8b), w(0x8c), w(0x8d), w(0x8e), w(0x8f),\
+    w(0x90), w(0x91), w(0x92), w(0x93), w(0x94), w(0x95), w(0x96), w(0x97),\
+    w(0x98), w(0x99), w(0x9a), w(0x9b), w(0x9c), w(0x9d), w(0x9e), w(0x9f),\
+    w(0xa0), w(0xa1), w(0xa2), w(0xa3), w(0xa4), w(0xa5), w(0xa6), w(0xa7),\
+    w(0xa8), w(0xa9), w(0xaa), w(0xab), w(0xac), w(0xad), w(0xae), w(0xaf),\
+    w(0xb0), w(0xb1), w(0xb2), w(0xb3), w(0xb4), w(0xb5), w(0xb6), w(0xb7),\
+    w(0xb8), w(0xb9), w(0xba), w(0xbb), w(0xbc), w(0xbd), w(0xbe), w(0xbf),\
+    w(0xc0), w(0xc1), w(0xc2), w(0xc3), w(0xc4), w(0xc5), w(0xc6), w(0xc7),\
+    w(0xc8), w(0xc9), w(0xca), w(0xcb), w(0xcc), w(0xcd), w(0xce), w(0xcf),\
+    w(0xd0), w(0xd1), w(0xd2), w(0xd3), w(0xd4), w(0xd5), w(0xd6), w(0xd7),\
+    w(0xd8), w(0xd9), w(0xda), w(0xdb), w(0xdc), w(0xdd), w(0xde), w(0xdf),\
+    w(0xe0), w(0xe1), w(0xe2), w(0xe3), w(0xe4), w(0xe5), w(0xe6), w(0xe7),\
+    w(0xe8), w(0xe9), w(0xea), w(0xeb), w(0xec), w(0xed), w(0xee), w(0xef),\
+    w(0xf0), w(0xf1), w(0xf2), w(0xf3), w(0xf4), w(0xf5), w(0xf6), w(0xf7),\
+    w(0xf8), w(0xf9), w(0xfa), w(0xfb), w(0xfc), w(0xfd), w(0xfe), w(0xff) }
+
+#define rc_data(w) {\
+    w(0x01), w(0x02), w(0x04), w(0x08), w(0x10),w(0x20), w(0x40), w(0x80),\
+    w(0x1b), w(0x36) }
+
+#define h0(x)   (x)
+
+#define w0(p)   bytes2word(p, 0, 0, 0)
+#define w1(p)   bytes2word(0, p, 0, 0)
+#define w2(p)   bytes2word(0, 0, p, 0)
+#define w3(p)   bytes2word(0, 0, 0, p)
+
+#define u0(p)   bytes2word(f2(p), p, p, f3(p))
+#define u1(p)   bytes2word(f3(p), f2(p), p, p)
+#define u2(p)   bytes2word(p, f3(p), f2(p), p)
+#define u3(p)   bytes2word(p, p, f3(p), f2(p))
+
+#define v0(p)   bytes2word(fe(p), f9(p), fd(p), fb(p))
+#define v1(p)   bytes2word(fb(p), fe(p), f9(p), fd(p))
+#define v2(p)   bytes2word(fd(p), fb(p), fe(p), f9(p))
+#define v3(p)   bytes2word(f9(p), fd(p), fb(p), fe(p))
+
+#endif
+
+#if defined(FIXED_TABLES) || !defined(FF_TABLES)
+
+#define f2(x)   ((x<<1) ^ (((x>>7) & 1) * WPOLY))
+#define f4(x)   ((x<<2) ^ (((x>>6) & 1) * WPOLY) ^ (((x>>6) & 2) * WPOLY))
+#define f8(x)   ((x<<3) ^ (((x>>5) & 1) * WPOLY) ^ (((x>>5) & 2) * WPOLY) \
+                        ^ (((x>>5) & 4) * WPOLY))
+#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))
+
+#else
+
+#define f2(x) ((x) ? pow[log[x] + 0x19] : 0)
+#define f3(x) ((x) ? pow[log[x] + 0x01] : 0)
+#define f9(x) ((x) ? pow[log[x] + 0xc7] : 0)
+#define fb(x) ((x) ? pow[log[x] + 0x68] : 0)
+#define fd(x) ((x) ? pow[log[x] + 0xee] : 0)
+#define fe(x) ((x) ? pow[log[x] + 0xdf] : 0)
+#define fi(x) ((x) ? pow[ 255 - log[x]] : 0)
+
+#endif
+
+#include "aestab.h"
+
+#if defined(FIXED_TABLES)
+
+/* implemented in case of wrong call for fixed tables */
+
+void gen_tabs(void)
+{
+}
+
+#else   /* dynamic table generation */
+
+#if !defined(FF_TABLES)
+
+/*  Generate the tables for the dynamic table option
+
+    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. But it only has effect during
+    initialisation so its pretty unimportant in overall terms.
+*/
+
+/*  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 fi can be bytes rather than words
+*/
+
+static aes_08t hibit(const aes_32t x)
+{   aes_08t r = (aes_08t)((x >> 1) | (x >> 2));
+
+    r |= (r >> 2);
+    r |= (r >> 4);
+    return (r + 1) >> 1;
+}
+
+/* return the inverse of the finite field element x */
+
+static aes_08t fi(const aes_08t x)
+{   aes_08t p1 = x, p2 = BPOLY, 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);
+        }
+    }
+}
+
+#endif
+
+/* The forward and inverse affine transformations used in the S-box */
+
+#define fwd_affine(x) \
+    (w = (aes_32t)x, w ^= (w<<1)^(w<<2)^(w<<3)^(w<<4), 0x63^(aes_08t)(w^(w>>8)))
+
+#define inv_affine(x) \
+    (w = (aes_32t)x, w = (w<<1)^(w<<3)^(w<<6), 0x05^(aes_08t)(w^(w>>8)))
+
+static int init = 0;
+
+void gen_tabs(void)
+{   aes_32t  i, w;
+
+#if defined(FF_TABLES)
+
+    aes_08t  pow[512], log[256];
+
+    if(init) return;
+    /*  log and power tables for GF(2^8) finite field with
+        WPOLY as modular polynomial - the simplest primitive
+        root is 0x03, used here to generate the tables
+    */
+
+    i = 0; w = 1;
+    do
+    {
+        pow[i] = (aes_08t)w;
+        pow[i + 255] = (aes_08t)w;
+        log[w] = (aes_08t)i++;
+        w ^=  (w << 1) ^ (w & 0x80 ? WPOLY : 0);
+    }
+    while (w != 1);
+
+#else
+    if(init) return;
+#endif
+
+    for(i = 0, w = 1; i < RC_LENGTH; ++i)
+    {
+        t_set(r,c)[i] = bytes2word(w, 0, 0, 0);
+        w = f2(w);
+    }
+
+    for(i = 0; i < 256; ++i)
+    {   aes_08t    b;
+
+        b = fwd_affine(fi((aes_08t)i));
+        w = bytes2word(f2(b), b, b, f3(b));
+
+#if defined( SBX_SET )
+        t_set(s,box)[i] = b;
+#endif
+
+#if defined( FT1_SET )                 /* tables for a normal encryption round */
+        t_set(f,n)[i] = w;
+#endif
+#if defined( FT4_SET )
+        t_set(f,n)[0][i] = w;
+        t_set(f,n)[1][i] = upr(w,1);
+        t_set(f,n)[2][i] = upr(w,2);
+        t_set(f,n)[3][i] = upr(w,3);
+#endif
+        w = bytes2word(b, 0, 0, 0);
+
+#if defined( FL1_SET )                 /* tables for last encryption round (may also   */
+        t_set(f,l)[i] = w;        /* be used in the key schedule)                 */
+#endif
+#if defined( FL4_SET )
+        t_set(f,l)[0][i] = w;
+        t_set(f,l)[1][i] = upr(w,1);
+        t_set(f,l)[2][i] = upr(w,2);
+        t_set(f,l)[3][i] = upr(w,3);
+#endif
+
+#if defined( LS1_SET )                 /* table for key schedule if t_set(f,l) above is    */
+        t_set(l,s)[i] = w;      /* not of the required form                     */
+#endif
+#if defined( LS4_SET )
+        t_set(l,s)[0][i] = w;
+        t_set(l,s)[1][i] = upr(w,1);
+        t_set(l,s)[2][i] = upr(w,2);
+        t_set(l,s)[3][i] = upr(w,3);
+#endif
+
+        b = fi(inv_affine((aes_08t)i));
+        w = bytes2word(fe(b), f9(b), fd(b), fb(b));
+
+#if defined( IM1_SET )                 /* tables for the inverse mix column operation  */
+        t_set(i,m)[b] = w;
+#endif
+#if defined( IM4_SET )
+        t_set(i,m)[0][b] = w;
+        t_set(i,m)[1][b] = upr(w,1);
+        t_set(i,m)[2][b] = upr(w,2);
+        t_set(i,m)[3][b] = upr(w,3);
+#endif
+
+#if defined( ISB_SET )
+        t_set(i,box)[i] = b;
+#endif
+#if defined( IT1_SET )                 /* tables for a normal decryption round */
+        t_set(i,n)[i] = w;
+#endif
+#if defined( IT4_SET )
+        t_set(i,n)[0][i] = w;
+        t_set(i,n)[1][i] = upr(w,1);
+        t_set(i,n)[2][i] = upr(w,2);
+        t_set(i,n)[3][i] = upr(w,3);
+#endif
+        w = bytes2word(b, 0, 0, 0);
+#if defined( IL1_SET )                 /* tables for last decryption round */
+        t_set(i,l)[i] = w;
+#endif
+#if defined( IL4_SET )
+        t_set(i,l)[0][i] = w;
+        t_set(i,l)[1][i] = upr(w,1);
+        t_set(i,l)[2][i] = upr(w,2);
+        t_set(i,l)[3][i] = upr(w,3);
+#endif
+    }
+    init = 1;
+}
+
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
diff --git a/aestab.h b/aestab.h
new file mode 100644
index 0000000..c610f9d
--- /dev/null
+++ b/aestab.h
@@ -0,0 +1,175 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+
+ This file contains the code for declaring the tables needed to implement
+ AES. The file aesopt.h is assumed to be included before this header file.
+ If there are no global variables, the definitions here can be used to put
+ the AES tables in a structure so that a pointer can then be added to the
+ AES context to pass them to the AES routines that need them.   If this
+ facility is used, the calling program has to ensure that this pointer is
+ managed appropriately.  In particular, the value of the t_dec(in,it) item
+ in the table structure must be set to zero in order to ensure that the
+ tables are initialised. In practice the three code sequences in aeskey.c
+ that control the calls to gen_tabs() and the gen_tabs() routine itself will
+ have to be changed for a specific implementation. If global variables are
+ available it will generally be preferable to use them with the precomputed
+ FIXED_TABLES option that uses static global tables.
+
+ The following defines can be used to control the way the tables
+ are defined, initialised and used in embedded environments that
+ require special features for these purposes
+
+    the 't_dec' construction is used to declare fixed table arrays
+    the 't_set' construction is used to set fixed table values
+    the 't_use' construction is used to access fixed table values
+
+    256 byte tables:
+
+        t_xxx(s,box)    => forward S box
+        t_xxx(i,box)    => inverse S box
+
+    256 32-bit word OR 4 x 256 32-bit word tables:
+
+        t_xxx(f,n)      => forward normal round
+        t_xxx(f,l)      => forward last round
+        t_xxx(i,n)      => inverse normal round
+        t_xxx(i,l)      => inverse last round
+        t_xxx(l,s)      => key schedule table
+        t_xxx(i,m)      => key schedule table
+
+    Other variables and tables:
+
+        t_xxx(r,c)      => the rcon table
+*/
+
+#if !defined( _AESTAB_H )
+#define _AESTAB_H
+
+#define t_dec(m,n) t_##m##n
+#define t_set(m,n) t_##m##n
+#define t_use(m,n) t_##m##n
+
+#if defined(FIXED_TABLES)
+#define Const const
+#else
+#define Const
+#endif
+
+#if defined(DO_TABLES)
+#define Extern
+#else
+#define Extern extern
+#endif
+
+#if defined(_MSC_VER) && defined(TABLE_ALIGN)
+#define Align __declspec(align(TABLE_ALIGN))
+#else
+#define Align
+#endif
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+
+#if defined(DO_TABLES) && defined(FIXED_TABLES)
+#define d_1(t,n,b,e)       Align Const t n[256]    =   b(e)
+#define d_4(t,n,b,e,f,g,h) Align Const t n[4][256] = { b(e), b(f), b(g), b(h) }
+Extern Align Const aes_32t t_dec(r,c)[RC_LENGTH] = rc_data(w0);
+#else
+#define d_1(t,n,b,e)       Extern Align Const t n[256]
+#define d_4(t,n,b,e,f,g,h) Extern Align Const t n[4][256]
+Extern Align Const aes_32t t_dec(r,c)[RC_LENGTH];
+#endif
+
+#if defined( SBX_SET )
+    d_1(aes_08t, t_dec(s,box), sb_data, h0);
+#endif
+#if defined( ISB_SET )
+    d_1(aes_08t, t_dec(i,box), isb_data, h0);
+#endif
+
+#if defined( FT1_SET )
+    d_1(aes_32t, t_dec(f,n), sb_data, u0);
+#endif
+#if defined( FT4_SET )
+    d_4(aes_32t, t_dec(f,n), sb_data, u0, u1, u2, u3);
+#endif
+
+#if defined( FL1_SET )
+    d_1(aes_32t, t_dec(f,l), sb_data, w0);
+#endif
+#if defined( FL4_SET )
+    d_4(aes_32t, t_dec(f,l), sb_data, w0, w1, w2, w3);
+#endif
+
+#if defined( IT1_SET )
+    d_1(aes_32t, t_dec(i,n), isb_data, v0);
+#endif
+#if defined( IT4_SET )
+    d_4(aes_32t, t_dec(i,n), isb_data, v0, v1, v2, v3);
+#endif
+
+#if defined( IL1_SET )
+    d_1(aes_32t, t_dec(i,l), isb_data, w0);
+#endif
+#if defined( IL4_SET )
+    d_4(aes_32t, t_dec(i,l), isb_data, w0, w1, w2, w3);
+#endif
+
+#if defined( LS1_SET )
+#if defined( FL1_SET )
+#undef  LS1_SET
+#else
+    d_1(aes_32t, t_dec(l,s), sb_data, w0);
+#endif
+#endif
+
+#if defined( LS4_SET )
+#if defined( FL4_SET )
+#undef  LS4_SET
+#else
+    d_4(aes_32t, t_dec(l,s), sb_data, w0, w1, w2, w3);
+#endif
+#endif
+
+#if defined( IM1_SET )
+    d_1(aes_32t, t_dec(i,m), mm_data, v0);
+#endif
+#if defined( IM4_SET )
+    d_4(aes_32t, t_dec(i,m), mm_data, v0, v1, v2, v3);
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/aestst.h b/aestst.h
new file mode 100644
index 0000000..c1ad235
--- /dev/null
+++ b/aestst.h
@@ -0,0 +1,133 @@
+/*
+ ---------------------------------------------------------------------------
+ Copyright (c) 2002, Dr Brian Gladman, Worcester, UK.   All rights reserved.
+
+ LICENSE TERMS
+
+ The free distribution and use of this software in both source and binary
+ form is allowed (with or without changes) provided that:
+
+   1. distributions of this source code include the above copyright
+      notice, this list of conditions and the following disclaimer;
+
+   2. distributions in binary form include the above copyright
+      notice, this list of conditions and the following disclaimer
+      in the documentation and/or other associated materials;
+
+   3. the copyright holder's name is not used to endorse products
+      built using this software without specific written permission.
+
+ ALTERNATIVELY, provided that this notice is retained in full, this product
+ may be distributed under the terms of the GNU General Public License (GPL),
+ in which case the provisions of the GPL apply INSTEAD OF those given above.
+
+ DISCLAIMER
+
+ This software is provided 'as is' with no explicit or implied warranties
+ in respect of its properties, including, but not limited to, correctness
+ and/or fitness for purpose.
+ ---------------------------------------------------------------------------
+ Issue 28/01/2004
+*/
+
+// The following definitions are required for testing only, They are not needed
+// for AES (Rijndael) implementation.  They are used to allow C, C++ and DLL
+// data access and subroutine calls to be expressed in the same form in the
+// testing code.
+
+#define ref_path    "..\\testvals\\"                // path for test vector files
+#define out_path    "..\\outvals\\"                 // path for output files
+#define dll_path    "..\\aes_dll\\release\\aes"     // path for DLL
+
+#if defined(AES_CPP)
+
+#define f_ectx              AESencrypt
+#define f_enc_key128(a,b)   (a)->key128((b))
+#define f_enc_key192(a,b)   (a)->key192((b))
+#define f_enc_key256(a,b)   (a)->key256((b))
+#define f_enc_key(a,b,c)    (a)->key((b),(c))
+#define f_enc_blk(a,b,c)    (a)->encrypt((b),(c))
+
+#define f_dctx              AESdecrypt
+#define f_dec_key128(a,b)   (a)->key128((b))
+#define f_dec_key192(a,b)   (a)->key192((b))
+#define f_dec_key256(a,b)   (a)->key256((b))
+#define f_dec_key(a,b,c)    (a)->key((b),(c))
+#define f_dec_blk(a,b,c)    (a)->decrypt((b),(c))
+
+#elif !defined(AES_DLL)
+
+#define f_ectx              aes_encrypt_ctx
+#define f_enc_key128(a,b)   aes_encrypt_key128((b),(a))
+#define f_enc_key192(a,b)   aes_encrypt_key192((b),(a))
+#define f_enc_key256(a,b)   aes_encrypt_key256((b),(a))
+#define f_enc_key(a,b,c)    aes_encrypt_key((b),(c),(a))
+#define f_enc_blk(a,b,c)    aes_encrypt((b),(c),(a))
+
+#define f_dctx              aes_decrypt_ctx
+#define f_dec_key128(a,b)   aes_decrypt_key128((b),(a))
+#define f_dec_key192(a,b)   aes_decrypt_key192((b),(a))
+#define f_dec_key256(a,b)   aes_decrypt_key256((b),(a))
+#define f_dec_key(a,b,c)    aes_decrypt_key((b),(c),(a))
+#define f_dec_blk(a,b,c)    aes_decrypt((b),(c),(a))
+
+#define ek_name128          "aes_encrypt_key128"
+#define ek_name192          "aes_encrypt_key192"
+#define ek_name256          "aes_encrypt_key256"
+#define ek_name             "aes_encrypt_key"
+#define ec_name             "aes_encrypt"
+
+#define dk_name128          "aes_decrypt_key128"
+#define dk_name192          "aes_decrypt_key192"
+#define dk_name256          "aes_decrypt_key256"
+#define dk_name             "aes_decrypt_key"
+#define dc_name             "aes_decrypt"
+
+#else
+
+#define f_ectx              aes_encrypt_ctx
+#define f_dctx              aes_decrypt_ctx
+typedef aes_rval g_enc_key(const unsigned char*, aes_encrypt_ctx[1]);
+typedef aes_rval g_dec_key(const unsigned char*, aes_decrypt_ctx[1]);
+typedef aes_rval g_enc_keyv(const unsigned char*, int, aes_encrypt_ctx[1]);
+typedef aes_rval g_dec_keyv(const unsigned char*, int, aes_decrypt_ctx[1]);
+typedef aes_rval g_enc_blk(const unsigned char*, unsigned char*, const aes_encrypt_ctx[1]);
+typedef aes_rval g_dec_blk(const unsigned char*, unsigned char*, const aes_decrypt_ctx[1]);
+
+typedef struct  // initialised with subroutine addresses when the DLL is loaded
+{
+    g_enc_key    *fn_enc_key128;
+    g_enc_key    *fn_enc_key192;
+    g_enc_key    *fn_enc_key256;
+    g_enc_keyv   *fn_enc_key;
+    g_enc_blk    *fn_enc_blk;
+    g_dec_key    *fn_dec_key128;
+    g_dec_key    *fn_dec_key192;
+    g_dec_key    *fn_dec_key256;
+    g_dec_keyv   *fn_dec_key;
+    g_dec_blk    *fn_dec_blk;
+} fn_ptrs;
+
+#define f_dat(a,b)          (a->b)
+#define f_enc_key128(a,b)   (fn.fn_enc_key128)((b),(a))
+#define f_enc_key192(a,b)   (fn.fn_enc_key192)((b),(a))
+#define f_enc_key256(a,b)   (fn.fn_enc_key256)((b),(a))
+#define f_enc_key(a,b,c)    (fn.fn_enc_key)((b),(c),(a))
+#define f_enc_blk(a,b,c)    (fn.fn_enc_blk)((b),(c),(a))
+#define f_dec_key128(a,b)   (fn.fn_dec_key128)((b),(a))
+#define f_dec_key192(a,b)   (fn.fn_dec_key192)((b),(a))
+#define f_dec_key256(a,b)   (fn.fn_dec_key256)((b),(a))
+#define f_dec_key(a,b,c)    (fn.fn_dec_key)((b),(c),(a))
+#define f_dec_blk(a,b,c)    (fn.fn_dec_blk)((b),(c),(a))
+#define ek_name128          "_aes_encrypt_key128@8"
+#define ek_name192          "_aes_encrypt_key192@8"
+#define ek_name256          "_aes_encrypt_key256@8"
+#define ek_name             "_aes_encrypt_key@12"
+#define ec_name             "_aes_encrypt@12"
+#define dk_name128          "_aes_decrypt_key128@8"
+#define dk_name192          "_aes_decrypt_key192@8"
+#define dk_name256          "_aes_decrypt_key256@8"
+#define dk_name             "_aes_decrypt_key@12"
+#define dc_name             "_aes_decrypt@12"
+
+#endif