/* LibTomCrypt, modular cryptographic library -- Tom St Denis
 *
 * LibTomCrypt is a library that provides various cryptographic
 * algorithms in a highly modular and flexible manner.
 *
 * The library is free for all purposes without any express
 * guarantee it works.
 */
#include "tomcrypt.h"

/**
  @file sha256.c
  LTC_SHA256 by Tom St Denis
*/

#ifdef LTC_SHA256

const struct ltc_hash_descriptor sha256_desc =
{
    "sha256",
    0,
    32,
    64,

    /* OID */
   { 2, 16, 840, 1, 101, 3, 4, 2, 1,  },
   9,

    &sha256_init,
    &sha256_process,
    &sha256_done,
    &sha256_test,
    NULL
};

#ifdef LTC_SMALL_CODE
/* the K array */
static const ulong32 K[64] = {
    0x428a2f98UL, 0x71374491UL, 0xb5c0fbcfUL, 0xe9b5dba5UL, 0x3956c25bUL,
    0x59f111f1UL, 0x923f82a4UL, 0xab1c5ed5UL, 0xd807aa98UL, 0x12835b01UL,
    0x243185beUL, 0x550c7dc3UL, 0x72be5d74UL, 0x80deb1feUL, 0x9bdc06a7UL,
    0xc19bf174UL, 0xe49b69c1UL, 0xefbe4786UL, 0x0fc19dc6UL, 0x240ca1ccUL,
    0x2de92c6fUL, 0x4a7484aaUL, 0x5cb0a9dcUL, 0x76f988daUL, 0x983e5152UL,
    0xa831c66dUL, 0xb00327c8UL, 0xbf597fc7UL, 0xc6e00bf3UL, 0xd5a79147UL,
    0x06ca6351UL, 0x14292967UL, 0x27b70a85UL, 0x2e1b2138UL, 0x4d2c6dfcUL,
    0x53380d13UL, 0x650a7354UL, 0x766a0abbUL, 0x81c2c92eUL, 0x92722c85UL,
    0xa2bfe8a1UL, 0xa81a664bUL, 0xc24b8b70UL, 0xc76c51a3UL, 0xd192e819UL,
    0xd6990624UL, 0xf40e3585UL, 0x106aa070UL, 0x19a4c116UL, 0x1e376c08UL,
    0x2748774cUL, 0x34b0bcb5UL, 0x391c0cb3UL, 0x4ed8aa4aUL, 0x5b9cca4fUL,
    0x682e6ff3UL, 0x748f82eeUL, 0x78a5636fUL, 0x84c87814UL, 0x8cc70208UL,
    0x90befffaUL, 0xa4506cebUL, 0xbef9a3f7UL, 0xc67178f2UL
};
#endif

/* Various logical functions */
#define Ch(x,y,z)       (z ^ (x & (y ^ z)))
#define Maj(x,y,z)      (((x | y) & z) | (x & y))
#define S(x, n)         RORc((x),(n))
#define R(x, n)         (((x)&0xFFFFFFFFUL)>>(n))
#define Sigma0(x)       (S(x, 2) ^ S(x, 13) ^ S(x, 22))
#define Sigma1(x)       (S(x, 6) ^ S(x, 11) ^ S(x, 25))
#define Gamma0(x)       (S(x, 7) ^ S(x, 18) ^ R(x, 3))
#define Gamma1(x)       (S(x, 17) ^ S(x, 19) ^ R(x, 10))

/* compress 512-bits */
#ifdef LTC_CLEAN_STACK
static int _sha256_compress(hash_state * md, unsigned char *buf)
#else
static int  sha256_compress(hash_state * md, unsigned char *buf)
#endif
{
    ulong32 S[8], W[64], t0, t1;
#ifdef LTC_SMALL_CODE
    ulong32 t;
#endif
    int i;

    /* copy state into S */
    for (i = 0; i < 8; i++) {
        S[i] = md->sha256.state[i];
    }

    /* copy the state into 512-bits into W[0..15] */
    for (i = 0; i < 16; i++) {
        LOAD32H(W[i], buf + (4*i));
    }

    /* fill W[16..63] */
    for (i = 16; i < 64; i++) {
        W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
    }

    /* Compress */
#ifdef LTC_SMALL_CODE
#define RND(a,b,c,d,e,f,g,h,i)                         \
     t0 = h + Sigma1(e) + Ch(e, f, g) + K[i] + W[i];   \
     t1 = Sigma0(a) + Maj(a, b, c);                    \
     d += t0;                                          \
     h  = t0 + t1;

     for (i = 0; i < 64; ++i) {
         RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i);
         t = S[7]; S[7] = S[6]; S[6] = S[5]; S[5] = S[4];
         S[4] = S[3]; S[3] = S[2]; S[2] = S[1]; S[1] = S[0]; S[0] = t;
     }
#else
#define RND(a,b,c,d,e,f,g,h,i,ki)                    \
     t0 = h + Sigma1(e) + Ch(e, f, g) + ki + W[i];   \
     t1 = Sigma0(a) + Maj(a, b, c);                  \
     d += t0;                                        \
     h  = t0 + t1;

    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],0,0x428a2f98);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],1,0x71374491);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],2,0xb5c0fbcf);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],3,0xe9b5dba5);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],4,0x3956c25b);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],5,0x59f111f1);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],6,0x923f82a4);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],7,0xab1c5ed5);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],8,0xd807aa98);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],9,0x12835b01);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],10,0x243185be);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],11,0x550c7dc3);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],12,0x72be5d74);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],13,0x80deb1fe);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],14,0x9bdc06a7);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],15,0xc19bf174);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],16,0xe49b69c1);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],17,0xefbe4786);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],18,0x0fc19dc6);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],19,0x240ca1cc);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],20,0x2de92c6f);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],21,0x4a7484aa);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],22,0x5cb0a9dc);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],23,0x76f988da);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],24,0x983e5152);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],25,0xa831c66d);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],26,0xb00327c8);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],27,0xbf597fc7);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],28,0xc6e00bf3);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],29,0xd5a79147);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],30,0x06ca6351);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],31,0x14292967);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],32,0x27b70a85);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],33,0x2e1b2138);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],34,0x4d2c6dfc);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],35,0x53380d13);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],36,0x650a7354);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],37,0x766a0abb);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],38,0x81c2c92e);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],39,0x92722c85);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],40,0xa2bfe8a1);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],41,0xa81a664b);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],42,0xc24b8b70);