#include "ecrypt-sync.h"

#define ROTATE(v,c) (ROTL32(v,c))
#define XOR(v,w) ((v) ^ (w))
#define PLUS(v,w) (U32V((v) + (w)))
#define PLUSONE(v) (PLUS((v),1))

static void salsa20_wordtobyte(u8 output[64],const u32 input[16])
{
  u32 x[16];
  int i;

  for (i = 0;i < 16;++i) x[i] = input[i];
  for (i = 20;i > 0;i -= 2) {
    x[ 4] = XOR(x[ 4],ROTATE(PLUS(x[ 0],x[12]), 7));
    x[ 8] = XOR(x[ 8],ROTATE(PLUS(x[ 4],x[ 0]), 9));
    x[12] = XOR(x[12],ROTATE(PLUS(x[ 8],x[ 4]),13));
    x[ 0] = XOR(x[ 0],ROTATE(PLUS(x[12],x[ 8]),18));
    x[ 9] = XOR(x[ 9],ROTATE(PLUS(x[ 5],x[ 1]), 7));
    x[13] = XOR(x[13],ROTATE(PLUS(x[ 9],x[ 5]), 9));
    x[ 1] = XOR(x[ 1],ROTATE(PLUS(x[13],x[ 9]),13));
    x[ 5] = XOR(x[ 5],ROTATE(PLUS(x[ 1],x[13]),18));
    x[14] = XOR(x[14],ROTATE(PLUS(x[10],x[ 6]), 7));
    x[ 2] = XOR(x[ 2],ROTATE(PLUS(x[14],x[10]), 9));
    x[ 6] = XOR(x[ 6],ROTATE(PLUS(x[ 2],x[14]),13));
    x[10] = XOR(x[10],ROTATE(PLUS(x[ 6],x[ 2]),18));
    x[ 3] = XOR(x[ 3],ROTATE(PLUS(x[15],x[11]), 7));
    x[ 7] = XOR(x[ 7],ROTATE(PLUS(x[ 3],x[15]), 9));
    x[11] = XOR(x[11],ROTATE(PLUS(x[ 7],x[ 3]),13));
    x[15] = XOR(x[15],ROTATE(PLUS(x[11],x[ 7]),18));
    x[ 1] = XOR(x[ 1],ROTATE(PLUS(x[ 0],x[ 3]), 7));
    x[ 2] = XOR(x[ 2],ROTATE(PLUS(x[ 1],x[ 0]), 9));
    x[ 3] = XOR(x[ 3],ROTATE(PLUS(x[ 2],x[ 1]),13));
    x[ 0] = XOR(x[ 0],ROTATE(PLUS(x[ 3],x[ 2]),18));
    x[ 6] = XOR(x[ 6],ROTATE(PLUS(x[ 5],x[ 4]), 7));
    x[ 7] = XOR(x[ 7],ROTATE(PLUS(x[ 6],x[ 5]), 9));
    x[ 4] = XOR(x[ 4],ROTATE(PLUS(x[ 7],x[ 6]),13));
    x[ 5] = XOR(x[ 5],ROTATE(PLUS(x[ 4],x[ 7]),18));
    x[11] = XOR(x[11],ROTATE(PLUS(x[10],x[ 9]), 7));
    x[ 8] = XOR(x[ 8],ROTATE(PLUS(x[11],x[10]), 9));
    x[ 9] = XOR(x[ 9],ROTATE(PLUS(x[ 8],x[11]),13));
    x[10] = XOR(x[10],ROTATE(PLUS(x[ 9],x[ 8]),18));
    x[12] = XOR(x[12],ROTATE(PLUS(x[15],x[14]), 7));
    x[13] = XOR(x[13],ROTATE(PLUS(x[12],x[15]), 9));
    x[14] = XOR(x[14],ROTATE(PLUS(x[13],x[12]),13));
    x[15] = XOR(x[15],ROTATE(PLUS(x[14],x[13]),18));
  }
  for (i = 0;i < 16;++i) x[i] = PLUS(x[i],input[i]);
  for (i = 0;i < 16;++i) U32TO8_LITTLE(output + 4 * i,x[i]);
}

void ECRYPT_init(void)
{
  return;
}

static const char sigma[16] = "expand 32-byte k";
static const char tau[16] = "expand 16-byte k";

void ECRYPT_keysetup(ECRYPT_ctx *x,const u8 *k,u32 kbits,u32 ivbits)
{
  int i;
  static const char *constants;

  x->input[1] = U8TO32_LITTLE(k + 0);
  x->input[2] = U8TO32_LITTLE(k + 4);
  x->input[3] = U8TO32_LITTLE(k + 8);
  x->input[4] = U8TO32_LITTLE(k + 12);
  if (kbits == 256) { /* recommended */
    k += 16;
    constants = sigma;
  } else { /* kbits == 128 */
    constants = tau;
  }
  x->input[11] = U8TO32_LITTLE(k + 0);
  x->input[12] = U8TO32_LITTLE(k + 4);
  x->input[13] = U8TO32_LITTLE(k + 8);
  x->input[14] = U8TO32_LITTLE(k + 12);
  x->input[0] = U8TO32_LITTLE(constants + 0);
  x->input[5] = U8TO32_LITTLE(constants + 4);
  x->input[10] = U8TO32_LITTLE(constants + 8);
  x->input[15] = U8TO32_LITTLE(constants + 12);
}

void ECRYPT_ivsetup(ECRYPT_ctx *x,const u8 *iv)
{
  x->input[6] = U8TO32_LITTLE(iv + 0);
  x->input[7] = U8TO32_LITTLE(iv + 4);
  x->input[8] = 0;
  x->input[9] = 0;
}

void ECRYPT_encrypt_bytes(ECRYPT_ctx *x,const u8 *m,u8 *c,u32 bytes)
{
  u8 output[64];
  int i;

  if (!bytes) return;
  for (;;) {
    salsa20_wordtobyte(output,x->input);
    x->input[8] = PLUSONE(x->input[8]);
    if (!x->input[8]) {
      x->input[9] = PLUSONE(x->input[9]);
      /* stopping at 2^70 bytes per nonce is user's responsibility */
    }
    if (bytes <= 64) {
      for (i = 0;i < bytes;++i) c[i] = m[i] ^ output[i];
      return;
    }
    for (i = 0;i < 64;++i) c[i] = m[i] ^ output[i];
    bytes -= 64;
    c += 64;
    m += 64;
  }
}

void ECRYPT_decrypt_bytes(ECRYPT_ctx *x,const u8 *c,u8 *m,u32 bytes)
{
  ECRYPT_encrypt_bytes(x,c,m,bytes);
}

void ECRYPT_keystream_bytes(ECRYPT_ctx *x,u8 *stream,u32 bytes)
{
  u32 i;
  for (i = 0;i < bytes;++i) stream[i] = 0;
  ECRYPT_encrypt_bytes(x,stream,stream,bytes);
}