length feature of the code.  Include this section if you place more
    emphasis on speed rather than code size.
*/
#if 1
#define FAST_VARIABLE
#endif

/*  12. 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 NO_TABLES   0   /* DO NOT CHANGE */
#define ONE_TABLE   1   /* DO NOT CHANGE */
#define FOUR_TABLES 4   /* DO NOT CHANGE */
#define NONE        0   /* DO NOT CHANGE */
#define PARTIAL     1   /* DO NOT CHANGE */
#define FULL        2   /* DO NOT CHANGE */

#if defined(BLOCK_SIZE) && ((BLOCK_SIZE & 3) || BLOCK_SIZE < 16 || BLOCK_SIZE > 32)
#error An illegal block size has been specified.
#endif  

#if !defined(BLOCK_SIZE)
#define RC_LENGTH    29
#else
#define RC_LENGTH   5 * BLOCK_SIZE / 4 - (BLOCK_SIZE == 16 ? 10 : 11)
#endif

/* Disable at least some poor 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 (INTERNAL_BYTE_ORDER == AES_LITTLE_ENDIAN)
#if defined(_MSC_VER)
#define upr(x,n)        _lrotl((aes_32t)(x), 8 * (n))
#else
#define upr(x,n)        ((aes_32t)(x) << 8 * (n) | (aes_32t)(x) >> 32 - 8 * (n))
#endif
#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 (INTERNAL_BYTE_ORDER == AES_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)      bytes2word((x)[0], (x)[1], (x)[2], (x)[3])
#define word_out(x,v)   { (x)[0] = bval(v,0); (x)[1] = bval(v,1);   \
                          (x)[2] = bval(v,2); (x)[3] = bval(v,3);   }

#elif (INTERNAL_BYTE_ORDER == PLATFORM_BYTE_ORDER)

#define word_in(x)      *(aes_32t*)(x)
#define word_out(x,v)   *(aes_32t*)(x) = (v)

#else

#if !defined(bswap_32)
#if !defined(_MSC_VER)
#define _lrotl(x,n)     ((aes_32t)(x) <<  n | (aes_32t)(x) >> 32 - n)
#endif
#define bswap_32(x)     ((_lrotl((x),8) & 0x00ff00ff) | (_lrotl((x),24) & 0xff00ff00)) 
#endif

#define word_in(x)      bswap_32(*(aes_32t*)(x))
#define word_out(x,v)   *(aes_32t*)(x) = bswap_32(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 FFmulX(x)  ((((x) & m2) << 1) ^ ((((x) & m1) >> 7) * BPOLY))

/* The following defines provide alternative definitions of FFmulX that might
   give improved performance if a fast 32-bit multiply is not available. Note
   that a temporary variable u needs to be defined where FFmulX is used.

#define FFmulX(x) (u = (x) & m1, u |= (u >> 1), ((x) & m2) << 1) ^ ((u >> 3) | (u >> 6)) 
#define m4  (0x01010101 * BPOLY)
#define FFmulX(x) (u = (x) & m1, ((x) & m2) << 1) ^ ((u - (u >> 7)) & m4) 
*/

/* Work out which tables are needed for the different options   */

#ifdef  AES_ASM
#ifdef  ENC_ROUND
#undef  ENC_ROUND
#endif
#define ENC_ROUND   FOUR_TABLES
#ifdef  LAST_ENC_ROUND
#undef  LAST_ENC_ROUND
#endif
#define LAST_ENC_ROUND  FOUR_TABLES
#ifdef  DEC_ROUND
#undef  DEC_ROUND
#endif
#define DEC_ROUND   FOUR_TABLES
#ifdef  LAST_DEC_ROUND
#undef  LAST_DEC_ROUND
#endif
#define LAST_DEC_ROUND  FOUR_TABLES
#ifdef  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

#ifdef  FIXED_TABLES
#define prefx   extern const
#else
#define prefx   extern
extern aes_08t  tab_init;
void gen_tabs(void);
#endif

prefx aes_32t  rcon_tab[29];

#ifdef  SBX_SET
prefx aes_08t s_box[256];
#endif

#ifdef  ISB_SET
prefx aes_08t inv_s_box[256];
#endif

#ifdef  FT1_SET
prefx aes_32t ft_tab[256];
#endif

#ifdef  FT4_SET
prefx aes_32t ft_tab[4][256];
#endif

#ifdef  FL1_SET
prefx aes_32t fl_tab[256];
#endif

#ifdef  FL4_SET
prefx aes_32t fl_tab[4][256];
#endif

#ifdef  IT1_SET
prefx aes_32t it_tab[256];
#endif

#ifdef  IT4_SET
prefx aes_32t it_tab[4][256];
#endif

#ifdef  IL1_SET
prefx aes_32t il_tab[256];
#endif

#ifdef  IL4_SET
prefx aes_32t il_tab[4][256];
#endif

#ifdef  LS1_SET
#ifdef  FL1_SET
#undef  LS1_SET
#else
prefx aes_32t ls_tab[256];
#endif
#endif

#ifdef  LS4_SET
#ifdef  FL4_SET
#undef  LS4_SET
#else
prefx aes_32t ls_tab[4][256];
#endif
#endif

#ifdef  IM1_SET
prefx aes_32t im_tab[256];
#endif

#ifdef  IM4_SET
prefx aes_32t im_tab[4][256];
#endif

/* Set the number of columns in nc.  Note that it is important
   that nc is a constant which is known at compile time if the
   highest speed version of the code is needed.
*/

#if defined(BLOCK_SIZE)
#define nc  (BLOCK_SIZE >> 2)
#else
#define nc  (cx->n_blk >> 2)
#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)    ((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.  */

#define dec_fmvars
#if defined(FM4_SET)    /* not currently used */
#define fwd_mcol(x)     four_tables(x,fm_tab,vf1,rf1,0)
#elif defined(FM1_SET)  /* not currently used */
#define fwd_mcol(x)     one_table(x,upr,fm_tab,vf1,rf1,0)
#else
#undef  dec_fmvars
#define dec_fmvars      aes_32t f1, f2;
#define fwd_mcol(x)     (f1 = (x), f2 = FFmulX(f1), f2 ^ upr(f1 ^ f2, 3) ^ upr(f1, 2) ^ upr(f1, 1))
#endif

#define dec_imvars
#if defined(IM4_SET)
#define inv_mcol(x)     four_tables(x,im_tab,vf1,rf1,0)
#elif defined(IM1_SET)
#define inv_mcol(x)     one_table(x,upr,im_tab,vf1,rf1,0)
#else
#undef  dec_imvars
#define dec_imvars      aes_32t    f2, f4, f8, f9;
#define inv_mcol(x) \
    (f9 = (x), f2 = FFmulX(f9), f4 = FFmulX(f2), f8 = FFmulX(f4), f9 ^= f8, \
    f2 ^= f4 ^ f8 ^ upr(f2 ^ f9,3) ^ upr(f4 ^ f9,2) ^ upr(f9,1))
#endif

#if defined(FL4_SET)
#define ls_box(x,c)     four_tables(x,fl_tab,vf1,rf2,c)
#elif   defined(LS4_SET)
#define ls_box(x,c)     four_tables(x,ls_tab,vf1,rf2,c)
#elif defined(FL1_SET)
#define ls_box(x,c)     one_table(x,upr,fl_tab,vf1,rf2,c)
#elif defined(LS1_SET)
#define ls_box(x,c)     one_table(x,upr,ls_tab,vf1,rf2,c)
#else
#define ls_box(x,c)     no_table(x,s_box,vf1,rf2,c)
#endif

#endif