aes.c

简单好用的AES算法

#define cpy(d,s) \
switch(nc) \
{   case 8: cp(d,s); cp(d,s); \
    case 6: cp(d,s); cp(d,s); \
    case 4: cp(d,s); cp(d,s); \
            cp(d,s); cp(d,s); \
}

#define mix(d,s) \
switch(nc) \
{   case 8: mx(d,s); mx(d,s); \
    case 6: mx(d,s); mx(d,s); \
    case 4: mx(d,s); mx(d,s); \
            mx(d,s); mx(d,s); \
}

#endif

cf_dec c_name(set_key)(const byte in_key[], const word n_bytes, const enum aes_key f, c_name(aes) *cx)
{   word    *kf, *kt, rci;

#if !defined(FIXED_TABLES)
    if(!(cx->mode & 0x08)) { gen_tabs(); cx->mode = 0x08; }
#endif

#if !defined(BLOCK_SIZE)
    if(!(cx->mode & 0x04)) c_name(set_blk)(16, cx);
#endif

    if((n_bytes & 7) || n_bytes < 16 || n_bytes > 32 || !(f & 1) && !(f & 2)) 
	{     
        return (n_bytes ? cx->mode &= ~0x03, aes_bad : (aes_ret)(cx->Nkey << 2));
    }

    cx->mode = cx->mode & ~0x03 | (byte)f & 0x03;      
    cx->Nkey = n_bytes >> 2;
    cx->Nrnd = Nr(cx->Nkey, nc);

    cx->e_key[0] = word_in(in_key     );
    cx->e_key[1] = word_in(in_key +  4);
    cx->e_key[2] = word_in(in_key +  8);
    cx->e_key[3] = word_in(in_key + 12);

    kf = cx->e_key; 
    kt = kf + nc * (cx->Nrnd + 1) - cx->Nkey; 
    rci = 0;

    switch(cx->Nkey)
    {
    case 4: do
            {   kf[4] = kf[0] ^ ls_box(kf[3],3) ^ rcon_tab[rci++];
                kf[5] = kf[1] ^ kf[4];
                kf[6] = kf[2] ^ kf[5];
                kf[7] = kf[3] ^ kf[6];
                kf += 4;
            }
            while(kf < kt);
            break;

    case 6: cx->e_key[4] = word_in(in_key + 16);
            cx->e_key[5] = word_in(in_key + 20);
            do
            {   kf[ 6] = kf[0] ^ ls_box(kf[5],3) ^ rcon_tab[rci++];
                kf[ 7] = kf[1] ^ kf[ 6];
                kf[ 8] = kf[2] ^ kf[ 7];
                kf[ 9] = kf[3] ^ kf[ 8];
                kf[10] = kf[4] ^ kf[ 9];
                kf[11] = kf[5] ^ kf[10];
                kf += 6;
            }
            while(kf < kt);
            break;

    case 8: cx->e_key[4] = word_in(in_key + 16);
            cx->e_key[5] = word_in(in_key + 20);
            cx->e_key[6] = word_in(in_key + 24);
            cx->e_key[7] = word_in(in_key + 28);
            do
            {   kf[ 8] = kf[0] ^ ls_box(kf[7],3) ^ rcon_tab[rci++];
                kf[ 9] = kf[1] ^ kf[ 8];
                kf[10] = kf[2] ^ kf[ 9];
                kf[11] = kf[3] ^ kf[10];
                kf[12] = kf[4] ^ ls_box(kf[11],0);
                kf[13] = kf[5] ^ kf[12];
                kf[14] = kf[6] ^ kf[13];
                kf[15] = kf[7] ^ kf[14];
                kf += 8;
            }
            while (kf < kt);
            break;
    }

    if((cx->mode & 3) != enc)
    {   word    i;
        
        kt = cx->d_key + nc * cx->Nrnd;
        kf = cx->e_key;
        
        cpy(kt, kf); kt -= 2 * nc;

        for(i = 1; i < cx->Nrnd; ++i)
        { 
#if defined(ONE_TABLE) || defined(FOUR_TABLES)
#if !defined(ONE_IM_TABLE) && !defined(FOUR_IM_TABLES)
            word    f2, f4, f8, f9;
#endif
            mix(kt, kf);
#else
            cpy(kt, kf);
#endif
            kt -= 2 * nc;
        }
        
        cpy(kt, kf);
    }

    return aes_good;
}

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

#if defined(ARRAYS)
#define s(x,c) x[c]
#else
#define s(x,c) x##c
#endif

 /*
   I am grateful to Frank Yellin for the following constructions
   which, given the column (c) of the output state variable, give
   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.
 */

#define unused  77  /* Sunset Strip */

#define fwd_var(x,r,c) \
 ( r==0 ?			\
    ( c==0 ? s(x,0) \
    : c==1 ? s(x,1) \
    : c==2 ? s(x,2) \
    : c==3 ? s(x,3) \
    : c==4 ? s(x,4) \
    : c==5 ? s(x,5) \
    : c==6 ? s(x,6) \
    : s(x,7))		\
 : r==1 ?			\
    ( c==0 ? s(x,1) \
    : c==1 ? s(x,2) \
    : c==2 ? s(x,3) \
    : c==3 ? nc==4 ? s(x,0) : s(x,4) \
    : c==4 ? s(x,5) \
    : c==5 ? nc==8 ? s(x,6) : s(x,0) \
    : c==6 ? s(x,7) \
    : s(x,0))		\
 : r==2 ?			\
    ( c==0 ? nc==8 ? s(x,3) : s(x,2) \
    : c==1 ? nc==8 ? s(x,4) : s(x,3) \
    : c==2 ? nc==4 ? s(x,0) : nc==8 ? s(x,5) : s(x,4) \
    : c==3 ? nc==4 ? s(x,1) : nc==8 ? s(x,6) : s(x,5) \
    : c==4 ? nc==8 ? s(x,7) : s(x,0) \
    : c==5 ? nc==8 ? s(x,0) : s(x,1) \
    : c==6 ? s(x,1) \
    : s(x,2))		\
 :					\
    ( c==0 ? nc==8 ? s(x,4) : s(x,3) \
    : c==1 ? nc==4 ? s(x,0) : nc==8 ? s(x,5) : s(x,4) \
    : c==2 ? nc==4 ? s(x,1) : nc==8 ? s(x,6) : s(x,5) \
    : c==3 ? nc==4 ? s(x,2) : nc==8 ? s(x,7) : s(x,0) \
    : c==4 ? nc==8 ? s(x,0) : s(x,1) \
    : c==5 ? nc==8 ? s(x,1) : s(x,2) \
    : c==6 ? s(x,2) \
    : s(x,3)))

#define inv_var(x,r,c) \
 ( r==0 ?			\
    ( c==0 ? s(x,0) \
    : c==1 ? s(x,1) \
    : c==2 ? s(x,2) \
    : c==3 ? s(x,3) \
    : c==4 ? s(x,4) \
    : c==5 ? s(x,5) \
    : c==6 ? s(x,6) \
    : s(x,7))		\
 : r==1 ?			\
    ( c==0 ? nc==4 ? s(x,3) : nc==8 ? s(x,7) : s(x,5) \
    : c==1 ? s(x,0) \
    : c==2 ? s(x,1) \
    : c==3 ? s(x,2) \
    : c==4 ? s(x,3) \
    : c==5 ? s(x,4) \
    : c==6 ? s(x,5) \
    : s(x,6))		\
 : r==2 ?			\
    ( c==0 ? nc==4 ? s(x,2) : nc==8 ? s(x,5) : s(x,4) \
    : c==1 ? nc==4 ? s(x,3) : nc==8 ? s(x,6) : s(x,5) \
    : c==2 ? nc==8 ? s(x,7) : s(x,0) \
    : c==3 ? nc==8 ? s(x,0) : s(x,1) \
    : c==4 ? nc==8 ? s(x,1) : s(x,2) \
    : c==5 ? nc==8 ? s(x,2) : s(x,3) \
    : c==6 ? s(x,3) \
    : s(x,4))		\
 :					\
    ( c==0 ? nc==4 ? s(x,1) : nc==8 ? s(x,4) : s(x,3) \
    : c==1 ? nc==4 ? s(x,2) : nc==8 ? s(x,5) : s(x,4) \
    : c==2 ? nc==4 ? s(x,3) : nc==8 ? s(x,6) : s(x,5) \
    : c==3 ? nc==8 ? s(x,7) : s(x,0) \
    : c==4 ? nc==8 ? s(x,0) : s(x,1) \
    : c==5 ? nc==8 ? s(x,1) : s(x,2) \
    : c==6 ? s(x,2) \
    : s(x,3)))

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

#if defined(FOUR_TABLES)
#define fwd_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ four_tables(x,ft_tab,fwd_var,rf1,c)
#define inv_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ four_tables(x,it_tab,inv_var,rf1,c)
#elif defined(ONE_TABLE)
#define fwd_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ one_table(x,upr,ft_tab,fwd_var,rf1,c)
#define inv_rnd(y,x,k,c)    s(y,c)= (k)[c] ^ one_table(x,upr,it_tab,inv_var,rf1,c)
#else
#define fwd_rnd(y,x,k,c)    s(y,c) = fwd_mcol(no_table(x,s_box,fwd_var,rf1,c)) ^ (k)[c]
#define inv_rnd(y,x,k,c)    s(y,c) = inv_mcol(no_table(x,inv_s_box,inv_var,rf1,c) ^ (k)[c])
#endif

#if defined(FOUR_LR_TABLES)
#define fwd_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ four_tables(x,fl_tab,fwd_var,rf1,c)
#define inv_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ four_tables(x,il_tab,inv_var,rf1,c)
#elif defined(ONE_LR_TABLE)
#define fwd_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ one_table(x,ups,fl_tab,fwd_var,rf1,c)
#define inv_lrnd(y,x,k,c)   s(y,c)= (k)[c] ^ one_table(x,ups,il_tab,inv_var,rf1,c)
#else
#define fwd_lrnd(y,x,k,c)   s(y,c) = no_table(x,s_box,fwd_var,rf1,c) ^ (k)[c]
#define inv_lrnd(y,x,k,c)   s(y,c) = no_table(x,inv_s_box,inv_var,rf1,c) ^ (k)[c]
#endif

#if 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 == 24

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

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

#if BLOCK_SIZE == 32

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

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

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

#if defined(FAST_VARIABLE)

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

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

#endif

#endif
#endif

cf_dec c_name(encrypt)(const byte in_blk[], byte out_blk[], const c_name(aes) *cx)
{   word        locals(b0, b1);
    const word  *kp = cx->e_key;

#if !defined(ONE_TABLE) && !defined(FOUR_TABLES)
    word        f2;
#endif

    if(!(cx->mode & 0x01)) return aes_bad;

    state_in(b0, in_blk, kp); kp += nc;

#if defined(UNROLL)

    switch(cx->Nrnd)
    {
    case 14:    round(fwd_rnd,  b1, b0, kp         ); 
                round(fwd_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
    case 12:    round(fwd_rnd,  b1, b0, kp         ); 
                round(fwd_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
    case 10:    round(fwd_rnd,  b1, b0, kp         );             
                round(fwd_rnd,  b0, b1, kp +     nc);
                round(fwd_rnd,  b1, b0, kp + 2 * nc); 
                round(fwd_rnd,  b0, b1, kp + 3 * nc);
                round(fwd_rnd,  b1, b0, kp + 4 * nc); 
                round(fwd_rnd,  b0, b1, kp + 5 * nc);
                round(fwd_rnd,  b1, b0, kp + 6 * nc); 
                round(fwd_rnd,  b0, b1, kp + 7 * nc);
                round(fwd_rnd,  b1, b0, kp + 8 * nc);
                round(fwd_lrnd, b0, b1, kp + 9 * nc);
    }
#elif defined(PARTIAL_UNROLL)
    {   word    rnd;

        for(rnd = 0; rnd < (cx->Nrnd >> 1) - 1; ++rnd)
        {
            round(fwd_rnd, b1, b0, kp); 
            round(fwd_rnd, b0, b1, kp + nc); kp += 2 * nc;
        }

        round(fwd_rnd,  b1, b0, kp);
        round(fwd_lrnd, b0, b1, kp + nc);
    }
#else
    {   word    rnd;

        for(rnd = 0; rnd < cx->Nrnd - 1; ++rnd)
        {
            round(fwd_rnd, b1, b0, kp); 
            l_copy(b0, b1); kp += nc;
        }

        round(fwd_lrnd, b0, b1, kp);
    }
#endif

    state_out(out_blk, b0);
    return aes_good;
}

cf_dec c_name(decrypt)(const byte in_blk[], byte out_blk[], const c_name(aes) *cx)
{   word        locals(b0, b1);
    const word  *kp = cx->d_key;

#if !defined(ONE_TABLE) && !defined(FOUR_TABLES)
    word        f2, f4, f8, f9; 
#endif

    if(!(cx->mode & 0x02)) return aes_bad;

    state_in(b0, in_blk, kp); kp += nc;

#if defined(UNROLL)

    switch(cx->Nrnd)
    {
    case 14:    round(inv_rnd,  b1, b0, kp         );
                round(inv_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
    case 12:    round(inv_rnd,  b1, b0, kp         );
                round(inv_rnd,  b0, b1, kp + nc    ); kp += 2 * nc;
    case 10:    round(inv_rnd,  b1, b0, kp         );             
                round(inv_rnd,  b0, b1, kp +     nc);
                round(inv_rnd,  b1, b0, kp + 2 * nc); 
                round(inv_rnd,  b0, b1, kp + 3 * nc);
                round(inv_rnd,  b1, b0, kp + 4 * nc); 
                round(inv_rnd,  b0, b1, kp + 5 * nc);
                round(inv_rnd,  b1, b0, kp + 6 * nc); 
                round(inv_rnd,  b0, b1, kp + 7 * nc);
                round(inv_rnd,  b1, b0, kp + 8 * nc);
                round(inv_lrnd, b0, b1, kp + 9 * nc);
    }
#elif defined(PARTIAL_UNROLL)
    {   word    rnd;

        for(rnd = 0; rnd < (cx->Nrnd >> 1) - 1; ++rnd)
        {
            round(inv_rnd, b1, b0, kp); 
            round(inv_rnd, b0, b1, kp + nc); kp += 2 * nc;
        }

        round(inv_rnd,  b1, b0, kp);
        round(inv_lrnd, b0, b1, kp + nc);
    }
#else
    {   word    rnd;

        for(rnd = 0; rnd < cx->Nrnd - 1; ++rnd)
        {
            round(inv_rnd, b1, b0, kp); 
            l_copy(b0, b1); kp += nc;
        }

        round(inv_lrnd, b0, b1, kp);
    }
#endif

    state_out(out_blk, b0);
    return aes_good;
}