/*********************************************************************
* Filename:   sha256.c
* Author:     Brad Conte (brad AT bradconte.com)
* Copyright:
* Disclaimer: This code is presented "as is" without any guarantees.
* Details:    Implementation of the SHA-256 hashing algorithm.
              SHA-256 is one of the three algorithms in the SHA2
              specification. The others, SHA-384 and SHA-512, are not
              offered in this implementation.
              Algorithm specification can be found here:
               * http://csrc.nist.gov/publications/fips/fips180-2/fips180-2withchangenotice.pdf
              This implementation uses little endian byte order.
*********************************************************************/
#include "libc/bits/safemacros.internal.h"
#include "libc/dce.h"
#include "libc/nexgen32e/x86feature.h"
#include "libc/str/internal.h"
#include "libc/str/sha256.h"

#define ROTLEFT(a, b)  (((a) << (b)) | ((a) >> (32 - (b))))
#define ROTRIGHT(a, b) (((a) >> (b)) | ((a) << (32 - (b))))
#define CH(x, y, z)    (((x) & (y)) ^ (~(x) & (z)))
#define MAJ(x, y, z)   (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
#define EP0(x)         (ROTRIGHT(x, 2) ^ ROTRIGHT(x, 13) ^ ROTRIGHT(x, 22))
#define EP1(x)         (ROTRIGHT(x, 6) ^ ROTRIGHT(x, 11) ^ ROTRIGHT(x, 25))
#define SIG0(x)        (ROTRIGHT(x, 7) ^ ROTRIGHT(x, 18) ^ ((x) >> 3))
#define SIG1(x)        (ROTRIGHT(x, 17) ^ ROTRIGHT(x, 19) ^ ((x) >> 10))

static void sha256_transform(uint32_t state[hasatleast 8],
                             const uint8_t data[hasatleast 64]) {
  size_t i;
  uint32_t a, b, c, d, e, f, g, h, t1, t2, m[64];
  for (i = 0; i < 16; ++i, data += 4) {
    m[i] = (uint32_t)data[0] << 24 | data[1] << 16 | data[2] << 8 | data[3];
  }
  for (; i < 64; ++i) {
    m[i] = SIG1(m[i - 2]) + m[i - 7] + SIG0(m[i - 15]) + m[i - 16];
  }
  a = state[0];
  b = state[1];
  c = state[2];
  d = state[3];
  e = state[4];
  f = state[5];
  g = state[6];
  h = state[7];
  for (i = 0; i < 64; ++i) {
    t1 = h + EP1(e) + CH(e, f, g) + kSha256Tab[i] + m[i];
    t2 = EP0(a) + MAJ(a, b, c);
    h = g;
    g = f;
    f = e;
    e = d + t1;
    d = c;
    c = b;
    b = a;
    a = t1 + t2;
  }
  state[0] += a;
  state[1] += b;
  state[2] += c;
  state[3] += d;
  state[4] += e;
  state[5] += f;
  state[6] += g;
  state[7] += h;
}

void sha256_init(struct Sha256Ctx *ctx) {
  ctx->datalen = 0;
  ctx->bitlen = 0;
  ctx->state[0] = 0x6a09e667;
  ctx->state[1] = 0xbb67ae85;
  ctx->state[2] = 0x3c6ef372;
  ctx->state[3] = 0xa54ff53a;
  ctx->state[4] = 0x510e527f;
  ctx->state[5] = 0x9b05688c;
  ctx->state[6] = 0x1f83d9ab;
  ctx->state[7] = 0x5be0cd19;
}

void sha256_update(struct Sha256Ctx *ctx, const uint8_t *data, size_t size) {
  size_t i;
  i = 0;
#if 0
  if (!IsTiny() && size >= 64 &&
      (X86_HAVE(SHA) && X86_HAVE(SSE4_1) && X86_HAVE(SSSE3))) {
    sha256$x86(ctx->state, data, size);
    i += rounddown(size, 16);
  }
#endif
  for (; i < size; ++i) {
    ctx->data[ctx->datalen] = data[i];
    ctx->datalen++;
    if (ctx->datalen == 64) {
      sha256_transform(ctx->state, ctx->data);
      ctx->bitlen += 512;
      ctx->datalen = 0;
    }
  }
}

void sha256_final(struct Sha256Ctx *ctx, uint8_t *hash) {
  size_t i;
  i = ctx->datalen;
  if (ctx->datalen < 56) {
    ctx->data[i++] = 0x80;
    while (i < 56) ctx->data[i++] = 0x00;
  } else {
    ctx->data[i++] = 0x80;
    while (i < 64) ctx->data[i++] = 0x00;
    sha256_transform(ctx->state, ctx->data);
    memset(ctx->data, 0, 56);
  }
  ctx->bitlen += ctx->datalen * 8;
  ctx->data[63] = ctx->bitlen;
  ctx->data[62] = ctx->bitlen >> 8;
  ctx->data[61] = ctx->bitlen >> 16;
  ctx->data[60] = ctx->bitlen >> 24;
  ctx->data[59] = ctx->bitlen >> 32;
  ctx->data[58] = ctx->bitlen >> 40;
  ctx->data[57] = ctx->bitlen >> 48;
  ctx->data[56] = ctx->bitlen >> 56;
  sha256_transform(ctx->state, ctx->data);
  for (i = 0; i < 4; ++i) {
    hash[i] = (ctx->state[0] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 4] = (ctx->state[1] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 8] = (ctx->state[2] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 12] = (ctx->state[3] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 16] = (ctx->state[4] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 20] = (ctx->state[5] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 24] = (ctx->state[6] >> (24 - i * 8)) & 0x000000ff;
    hash[i + 28] = (ctx->state[7] >> (24 - i * 8)) & 0x000000ff;
  }
}