/*
* SM4
* (C) 2017 Ribose Inc
*
* Botan is released under the Simplified BSD License (see license.txt)
*/

#include <botan/sm4.h>
#include <botan/loadstor.h>

namespace Botan {

namespace SM4_F {

const uint8_t SBOX[256] = {
0xD6, 0x90, 0xE9, 0xFE, 0xCC, 0xE1, 0x3D, 0xB7, 0x16, 0xB6, 0x14, 0xC2, 0x28, 0xFB, 0x2C, 0x05,
0x2B, 0x67, 0x9A, 0x76, 0x2A, 0xBE, 0x04, 0xC3, 0xAA, 0x44, 0x13, 0x26, 0x49, 0x86, 0x06, 0x99,
0x9C, 0x42, 0x50, 0xF4, 0x91, 0xEF, 0x98, 0x7A, 0x33, 0x54, 0x0B, 0x43, 0xED, 0xCF, 0xAC, 0x62,
0xE4, 0xB3, 0x1C, 0xA9, 0xC9, 0x08, 0xE8, 0x95, 0x80, 0xDF, 0x94, 0xFA, 0x75, 0x8F, 0x3F, 0xA6,
0x47, 0x07, 0xA7, 0xFC, 0xF3, 0x73, 0x17, 0xBA, 0x83, 0x59, 0x3C, 0x19, 0xE6, 0x85, 0x4F, 0xA8,
0x68, 0x6B, 0x81, 0xB2, 0x71, 0x64, 0xDA, 0x8B, 0xF8, 0xEB, 0x0F, 0x4B, 0x70, 0x56, 0x9D, 0x35,
0x1E, 0x24, 0x0E, 0x5E, 0x63, 0x58, 0xD1, 0xA2, 0x25, 0x22, 0x7C, 0x3B, 0x01, 0x21, 0x78, 0x87,
0xD4, 0x00, 0x46, 0x57, 0x9F, 0xD3, 0x27, 0x52, 0x4C, 0x36, 0x02, 0xE7, 0xA0, 0xC4, 0xC8, 0x9E,
0xEA, 0xBF, 0x8A, 0xD2, 0x40, 0xC7, 0x38, 0xB5, 0xA3, 0xF7, 0xF2, 0xCE, 0xF9, 0x61, 0x15, 0xA1,
0xE0, 0xAE, 0x5D, 0xA4, 0x9B, 0x34, 0x1A, 0x55, 0xAD, 0x93, 0x32, 0x30, 0xF5, 0x8C, 0xB1, 0xE3,
0x1D, 0xF6, 0xE2, 0x2E, 0x82, 0x66, 0xCA, 0x60, 0xC0, 0x29, 0x23, 0xAB, 0x0D, 0x53, 0x4E, 0x6F,
0xD5, 0xDB, 0x37, 0x45, 0xDE, 0xFD, 0x8E, 0x2F, 0x03, 0xFF, 0x6A, 0x72, 0x6D, 0x6C, 0x5B, 0x51,
0x8D, 0x1B, 0xAF, 0x92, 0xBB, 0xDD, 0xBC, 0x7F, 0x11, 0xD9, 0x5C, 0x41, 0x1F, 0x10, 0x5A, 0xD8,
0x0A, 0xC1, 0x31, 0x88, 0xA5, 0xCD, 0x7B, 0xBD, 0x2D, 0x74, 0xD0, 0x12, 0xB8, 0xE5, 0xB4, 0xB0,
0x89, 0x69, 0x97, 0x4A, 0x0C, 0x96, 0x77, 0x7E, 0x65, 0xB9, 0xF1, 0x09, 0xC5, 0x6E, 0xC6, 0x84,
0x18, 0xF0, 0x7D, 0xEC, 0x3A, 0xDC, 0x4D, 0x20, 0x79, 0xEE, 0x5F, 0x3E, 0xD7, 0xCB, 0x39, 0x48
};

inline uint32_t T(uint32_t b)
   {
   /*
   TODO: could convert this to 4 8->32 bit tables combined with xor.
   It was about 66% faster (110 MiB->181 MiB) on an i7-6700k, but the
   large tables will be likely vulnerable to AES style cache attacks.
   */

   const uint8_t b0 = get_byte(0, b);
   const uint8_t b1 = get_byte(1, b);
   const uint8_t b2 = get_byte(2, b);
   const uint8_t b3 = get_byte(3, b);
   const uint32_t t = make_uint32(SBOX[b0], SBOX[b1], SBOX[b2], SBOX[b3]);

   // L linear transform
   return t ^ rotate_left(t, 2) ^ rotate_left(t, 10) ^ rotate_left(t, 18) ^ rotate_left(t, 24);
   }

// Variant of T for key schedule
inline uint32_t Tp(uint32_t b)
   {
   const uint8_t b0 = get_byte(0, b);
   const uint8_t b1 = get_byte(1, b);
   const uint8_t b2 = get_byte(2, b);
   const uint8_t b3 = get_byte(3, b);
   const uint32_t t = make_uint32(SBOX[b0], SBOX[b1], SBOX[b2], SBOX[b3]);

   // L' linear transform
   return t ^ rotate_left(t, 13) ^ rotate_left(t, 23);
   }

}

/*
* SM4 Encryption
*/
void SM4::encrypt_n(const uint8_t in[], uint8_t out[], size_t blocks) const
   {
   for(size_t i = 0; i != blocks; ++i)
      {
      uint32_t B0 = load_be<uint32_t>(in, 0);
      uint32_t B1 = load_be<uint32_t>(in, 1);
      uint32_t B2 = load_be<uint32_t>(in, 2);
      uint32_t B3 = load_be<uint32_t>(in, 3);

      for(size_t r = 0; r != 32; r += 4)
         {
         B0 ^= SM4_F::T(B1 ^ B2 ^ B3 ^ m_RK[r + 0]);
         B1 ^= SM4_F::T(B0 ^ B2 ^ B3 ^ m_RK[r + 1]);
         B2 ^= SM4_F::T(B0 ^ B1 ^ B3 ^ m_RK[r + 2]);
         B3 ^= SM4_F::T(B0 ^ B1 ^ B2 ^ m_RK[r + 3]);
         }

      store_be(out, B3, B2, B1, B0);

      in += BLOCK_SIZE;
      out += BLOCK_SIZE;
      }
   }

/*
* SM4 Decryption
*/
void SM4::decrypt_n(const uint8_t in[], uint8_t out[], size_t blocks) const
   {
   for(size_t i = 0; i != blocks; ++i)
      {
      uint32_t B0 = load_be<uint32_t>(in, 0);
      uint32_t B1 = load_be<uint32_t>(in, 1);
      uint32_t B2 = load_be<uint32_t>(in, 2);
      uint32_t B3 = load_be<uint32_t>(in, 3);

      for(size_t r = 0; r != 32; r += 4)
         {
         B0 ^= SM4_F::T(B1 ^ B2 ^ B3 ^ m_RK[31 - (r + 0)]);
         B1 ^= SM4_F::T(B0 ^ B2 ^ B3 ^ m_RK[31 - (r + 1)]);
         B2 ^= SM4_F::T(B0 ^ B1 ^ B3 ^ m_RK[31 - (r + 2)]);
         B3 ^= SM4_F::T(B0 ^ B1 ^ B2 ^ m_RK[31 - (r + 3)]);
         }

      store_be(out, B3, B2, B1, B0);

      in += BLOCK_SIZE;
      out += BLOCK_SIZE;
      }
   }

/*
* SM4 Key Schedule
*/
void SM4::key_schedule(const uint8_t key[], size_t)
   {
   // System parameter or family key
   const uint32_t FK[4] = { 0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc };

   const uint32_t CK[32] = {
      0x00070E15, 0x1C232A31, 0x383F464D, 0x545B6269,
      0x70777E85, 0x8C939AA1, 0xA8AFB6BD, 0xC4CBD2D9,
      0xE0E7EEF5, 0xFC030A11, 0x181F262D, 0x343B4249,
      0x50575E65, 0x6C737A81, 0x888F969D, 0xA4ABB2B9,
      0xC0C7CED5, 0xDCE3EAF1, 0xF8FF060D, 0x141B2229,
      0x30373E45, 0x4C535A61, 0x686F767D, 0x848B9299,
      0xA0A7AEB5, 0xBCC3CAD1, 0xD8DFE6ED, 0xF4FB0209,
      0x10171E25, 0x2C333A41, 0x484F565D, 0x646B7279
   };

   secure_vector<uint32_t> K(4);
   K[0] = load_be<uint32_t>(key, 0) ^ FK[0];
   K[1] = load_be<uint32_t>(key, 1) ^ FK[1];
   K[2] = load_be<uint32_t>(key, 2) ^ FK[2];
   K[3] = load_be<uint32_t>(key, 3) ^ FK[3];

   m_RK.resize(32);
   for(size_t i = 0; i != 32; ++i)
      {
      K[i % 4] ^= SM4_F::Tp(K[(i+1)%4] ^ K[(i+2)%4] ^ K[(i+3)%4] ^ CK[i]);
      m_RK[i] = K[i % 4];
      }
   }

void SM4::clear()
   {
   zap(m_RK);
   }

}