/*
 -------------------------------------------------------------------------
 Copyright (c) 2001, Dr Brian Gladman <brg@gladman.me.uk>, 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. 

 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 fitness for purpose.
 -------------------------------------------------------------------------
 Issue Date: 29/07/2002

 This file contains the code for implementing encryption and decryption
 for AES (Rijndael) for block and key sizes of 16, 20, 24, 28 and 32 bytes.
 It can optionally be replaced by code written in assembler using NASM.
*/

#include "aesopt.h"

#define unused  77  /* Sunset Strip */

#define si(y,x,k,c) s(y,c) = word_in(x + 4 * c) ^ k[c]
#define so(y,x,c)   word_out(y + 4 * c, s(x,c))

#if BLOCK_SIZE == 16

#if defined(ARRAYS)
#define locals(y,x)     x[4],y[4]
#else
#define locals(y,x)     x##0,x##1,x##2,x##3,y##0,y##1,y##2,y##3
 /* 
   the following defines prevent the compiler requiring the declaration
   of generated but unused variables in the fwd_var and inv_var macros
 */
#define b04 unused
#define b05 unused
#define b06 unused
#define b07 unused
#define b14 unused
#define b15 unused
#define b16 unused
#define b17 unused
#endif
#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
                        s(y,2) = s(x,2); s(y,3) = s(x,3);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3)
#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3)

#elif BLOCK_SIZE == 20

#if defined(ARRAYS)
#define locals(y,x)     x[5],y[5]
#else
#define locals(y,x)     x##0,x##1,x##2,x##3,x##4,y##0,y##1,y##2,y##3,y##4
#define b05 unused
#define b06 unused
#define b07 unused
#define b15 unused
#define b16 unused
#define b17 unused
#endif
#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
                        s(y,2) = s(x,2); s(y,3) = s(x,3); s(y,4) = s(x,4); 
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3); si(y,x,k,4)
#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3); so(y,x,4)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3); rm(y,x,k,4)

#elif BLOCK_SIZE == 24

#if defined(ARRAYS)
#define locals(y,x)     x[6],y[6]
#else
#define locals(y,x)     x##0,x##1,x##2,x##3,x##4,x##5, \
                        y##0,y##1,y##2,y##3,y##4,y##5
#define b06 unused
#define b07 unused
#define b16 unused
#define b17 unused
#endif
#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
                        s(y,2) = s(x,2); s(y,3) = s(x,3); \
                        s(y,4) = s(x,4); s(y,5) = s(x,5);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); \
                        si(y,x,k,3); si(y,x,k,4); si(y,x,k,5)
#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); \
                        so(y,x,3); so(y,x,4); so(y,x,5)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); \
                        rm(y,x,k,3); rm(y,x,k,4); rm(y,x,k,5)

#elif BLOCK_SIZE == 28

#if defined(ARRAYS)
#define locals(y,x)     x[7],y[7]
#else
#define locals(y,x)     x##0,x##1,x##2,x##3,x##4,x##5,x##6 \
                        y##0,y##1,y##2,y##3,y##4,y##5,y##6
#define b07 unused
#define b17 unused
#endif
#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
                        s(y,2) = s(x,2); s(y,3) = s(x,3); \
                        s(y,4) = s(x,4); s(y,5) = s(x,5);; s(y,6) = s(x,6);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); \
                        si(y,x,k,3); si(y,x,k,4); si(y,x,k,5); si(y,x,k,6)
#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); \
                        so(y,x,3); so(y,x,4); so(y,x,5); so(y,x,6)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); \
                        rm(y,x,k,3); rm(y,x,k,4); rm(y,x,k,5); rm(y,x,k,6)
#else

#if defined(ARRAYS)
#define locals(y,x)     x[8],y[8]
#else
#define locals(y,x)     x##0,x##1,x##2,x##3,x##4,x##5,x##6,x##7, \
                        y##0,y##1,y##2,y##3,y##4,y##5,y##6,y##7
#endif
#define l_copy(y, x)    s(y,0) = s(x,0); s(y,1) = s(x,1); \
                        s(y,2) = s(x,2); s(y,3) = s(x,3); \
                        s(y,4) = s(x,4); s(y,5) = s(x,5); \
                        s(y,6) = s(x,6); s(y,7) = s(x,7);

#if BLOCK_SIZE == 32

#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3); \
                        si(y,x,k,4); si(y,x,k,5); si(y,x,k,6); si(y,x,k,7)
#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3); \
                        so(y,x,4); so(y,x,5); so(y,x,6); so(y,x,7)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3); \
                        rm(y,x,k,4); rm(y,x,k,5); rm(y,x,k,6); rm(y,x,k,7)
#else

#define state_in(y,x,k) \
switch(nc) \
{   case 8: si(y,x,k,7); \
    case 7: si(y,x,k,6); \
    case 6: si(y,x,k,5); \
    case 5: si(y,x,k,4); \
    case 4: si(y,x,k,3); si(y,x,k,2); \
            si(y,x,k,1); si(y,x,k,0); \
}

#define state_out(y,x) \
switch(nc) \
{   case 8: so(y,x,7); \
    case 7: so(y,x,6); \
    case 6: so(y,x,5); \
    case 5: so(y,x,4); \
    case 4: so(y,x,3); so(y,x,2); \
            so(y,x,1); so(y,x,0); \
}

#if defined(FAST_VARIABLE)

#define round(rm,y,x,k) \
switch(nc) \
{   case 8: rm(y,x,k,7); rm(y,x,k,6); \
            rm(y,x,k,5); rm(y,x,k,4); \
            rm(y,x,k,3); rm(y,x,k,2); \
            rm(y,x,k,1); rm(y,x,k,0); \
            break; \
    case 7: rm(y,x,k,6); rm(y,x,k,5); \
            rm(y,x,k,4); rm(y,x,k,3); \
            rm(y,x,k,2); rm(y,x,k,1); \
            rm(y,x,k,0); \
            break; \
    case 6: rm(y,x,k,5); rm(y,x,k,4); \
            rm(y,x,k,3); rm(y,x,k,2); \
            rm(y,x,k,1); rm(y,x,k,0); \
            break; \
    case 5: rm(y,x,k,4); rm(y,x,k,3); \
            rm(y,x,k,2); rm(y,x,k,1); \
            rm(y,x,k,0); \
            break; \
    case 4: rm(y,x,k,3); rm(y,x,k,2); \
            rm(y,x,k,1); rm(y,x,k,0); \
            break; \
}
#else

#define round(rm,y,x,k) \
switch(nc) \
{   case 8: rm(y,x,k,7); \
    case 7: rm(y,x,k,6); \
    case 6: rm(y,x,k,5); \
    case 5: rm(y,x,k,4); \
    case 4: rm(y,x,k,3); rm(y,x,k,2); \
            rm(y,x,k,1); rm(y,x,k,0); \
}

#endif

#endif
#endif

#if defined(ENCRYPTION)

/* I am grateful to Frank Yellin for the following construction
   (and that for decryption) which, given the column (c) of the 
   output state variable, gives the input state variables which 
   are needed for each row (r) of the state.

   For the fixed block size options, compilers should reduce these 
   two expressions to fixed variable references. But for variable 
   block size code conditional clauses will sometimes be returned.

   y = output word, x = input word, r = row, c = column for r = 0, 
   1, 2 and 3 = column accessed for row r.
*/

#define fwd_var(x,r,c)\
 ( r == 0 ?           \
    ( c == 0 ? s(x,0) \
    : c == 1 ? s(x,1) \
    : c == 2 ? s(x,2) \
    : c == 3 ? s(x,3) \
    : c == 4 ? s(x,4) \
    : c == 5 ? s(x,5) \
    : c == 6 ? s(x,6) \
    :          s(x,7))\
 : r == 1 ?           \
    ( c == 0 ? s(x,1) \
    : c == 1 ? s(x,2) \
    : c == 2 ? s(x,3) \
    : c == 3 ? nc == 4 ? s(x,0) : s(x,4) \
    : c == 4 ? nc == 5 ? s(x,0) : s(x,5) \
    : c == 5 ? nc == 6 ? s(x,0) : s(x,6) \
    : c == 6 ? nc == 7 ? s(x,0) : s(x,7) \