#include "mycrypt.h"

#ifdef SHA256 

const struct _hash_descriptor sha256_desc =
{
    "sha256",
    0,
    32,
    64,
    &sha256_init,
    &sha256_process,
    &sha256_done,
    &sha256_test
};

/* the K array */
static const unsigned long 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
};

/* 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)         ROR((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 CLEAN_STACK
static void _sha256_compress(hash_state * md)
#else
static void sha256_compress(hash_state * md)
#endif
{
    unsigned long S[8], W[64], t0, t1;
    int i;

    _ARGCHK(md != NULL);

    /* 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], md->sha256.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 SMALL_CODE   
    for (i = 0; i < 64; i++) {
        t0 = S[7] + Sigma1(S[4]) + Ch(S[4], S[5], S[6]) + K[i] + W[i];
        t1 = Sigma0(S[0]) + Maj(S[0], S[1], S[2]);
        S[7] = S[6];
        S[6] = S[5];
        S[5] = S[4];
        S[4] = S[3] + t0;
        S[3] = S[2];
        S[2] = S[1];
        S[1] = S[0];
        S[0] = t0 + t1;
    }
#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);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],43,0xc76c51a3);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],44,0xd192e819);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],45,0xd6990624);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],46,0xf40e3585);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],47,0x106aa070);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],48,0x19a4c116);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],49,0x1e376c08);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],50,0x2748774c);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],51,0x34b0bcb5);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],52,0x391c0cb3);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],53,0x4ed8aa4a);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],54,0x5b9cca4f);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],55,0x682e6ff3);
    RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],56,0x748f82ee);
    RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],57,0x78a5636f);
    RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],58,0x84c87814);
    RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],59,0x8cc70208);
    RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],60,0x90befffa);
    RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],61,0xa4506ceb);
    RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],62,0xbef9a3f7);
    RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],63,0xc67178f2);

#undef RND     
    
#endif     

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

}

#ifdef CLEAN_STACK
static void sha256_compress(hash_state * md)
{
    _sha256_compress(md);
    burn_stack(sizeof(unsigned long) * 74);
}
#endif

/* init the sha256 state */
void sha256_init(hash_state * md)
{
    _ARGCHK(md != NULL);

    md->sha256.curlen = 0;
    md->sha256.length = 0;
    md->sha256.state[0] = 0x6A09E667UL;
    md->sha256.state[1] = 0xBB67AE85UL;
    md->sha256.state[2] = 0x3C6EF372UL;
    md->sha256.state[3] = 0xA54FF53AUL;
    md->sha256.state[4] = 0x510E527FUL;
    md->sha256.state[5] = 0x9B05688CUL;
    md->sha256.state[6] = 0x1F83D9ABUL;
    md->sha256.state[7] = 0x5BE0CD19UL;
}

void sha256_process(hash_state * md, const unsigned char *buf, unsigned long len)
{
    unsigned long n;
    _ARGCHK(md != NULL);
    _ARGCHK(buf != NULL);

    while (len > 0) {
        n = MIN(len, (64 - md->sha256.curlen));
        memcpy(md->sha256.buf + md->sha256.curlen, buf, (size_t)n);
        md->sha256.curlen += n;
        buf            += n;
        len            -= n;

        /* is 64 bytes full? */
        if (md->sha256.curlen == 64) {
            sha256_compress(md);
            md->sha256.length += 512;
            md->sha256.curlen = 0;
        }
    }
}

void sha256_done(hash_state * md, unsigned char *hash)
{
    int i;

    _ARGCHK(md != NULL);
    _ARGCHK(hash != NULL);

    /* increase the length of the message */
    md->sha256.length += md->sha256.curlen * 8;

    /* append the '1' bit */
    md->sha256.buf[md->sha256.curlen++] = (unsigned char)0x80;

    /* if the length is currently above 56 bytes we append zeros
     * then compress.  Then we can fall back to padding zeros and length
     * encoding like normal.
     */
    if (md->sha256.curlen > 56) {
        while (md->sha256.curlen < 64) {
            md->sha256.buf[md->sha256.curlen++] = (unsigned char)0;
        }
        sha256_compress(md);
        md->sha256.curlen = 0;
    }

    /* pad upto 56 bytes of zeroes */
    while (md->sha256.curlen < 56) {
        md->sha256.buf[md->sha256.curlen++] = (unsigned char)0;
    }

    /* store length */
    STORE64H(md->sha256.length, md->sha256.buf+56);
    sha256_compress(md);

    /* copy output */
    for (i = 0; i < 8; i++) {
        STORE32H(md->sha256.state[i], hash+(4*i));
    }
#ifdef CLEAN_STACK
    zeromem(md, sizeof(hash_state));
#endif
}

int  sha256_test(void)
{
 #ifndef LTC_TEST
    return CRYPT_NOP;
 #else    
  static const struct {
       char *msg;
      unsigned char hash[32];
  } tests[] = {
    { "abc",
      { 0xba, 0x78, 0x16, 0xbf, 0x8f, 0x01, 0xcf, 0xea,
        0x41, 0x41, 0x40, 0xde, 0x5d, 0xae, 0x22, 0x23,
        0xb0, 0x03, 0x61, 0xa3, 0x96, 0x17, 0x7a, 0x9c,
        0xb4, 0x10, 0xff, 0x61, 0xf2, 0x00, 0x15, 0xad }
    },
    { "abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq",
      { 0x24, 0x8d, 0x6a, 0x61, 0xd2, 0x06, 0x38, 0xb8, 
        0xe5, 0xc0, 0x26, 0x93, 0x0c, 0x3e, 0x60, 0x39,
        0xa3, 0x3c, 0xe4, 0x59, 0x64, 0xff, 0x21, 0x67, 
        0xf6, 0xec, 0xed, 0xd4, 0x19, 0xdb, 0x06, 0xc1 }
    },
  };

  int i;
  unsigned char tmp[32];
  hash_state md;

  for (i = 0; i < (int)(sizeof(tests) / sizeof(tests[0])); i++) {
      sha256_init(&md);
      sha256_process(&md, (unsigned char*)tests[i].msg, (unsigned long)strlen(tests[i].msg));
      sha256_done(&md, tmp);
      if (memcmp(tmp, tests[i].hash, 32) != 0) {
         return CRYPT_FAIL_TESTVECTOR;
      }
  }
  return CRYPT_OK;
 #endif
}

#endif