国密算法SM4实现

---

前言

SM4是国内采用的一种分组密码标准，有国家密码管理局于2012年3月21日发布，相关标准为“GM/T 0002-2012《SM4分组密码算法》（原SMS4分组密码算法）”。2016年8月，成为中国国家密码标准（GB/T 32907-2016）。
SM4主要用于数据加密，其算法公开，分组长度与密钥长度均为128bit，加密算法与密钥扩展算法都采用32轮非线性迭代结构，S盒为固定的8比特输入8比特输出。

---

术语和定义

分组长度 block length: 一个信息分组的比特位数

密钥长度key length：密钥的比特位数

密钥扩展算法 key expansion algorithm: 将密钥变换为轮密钥的运算单元

轮数 rounds：轮函数的迭代次数

字 word：长度为32比特的组（串）

S 盒 S-box：S盒为固定的8比特输入8比特输出的置换，记为Sbox(.)

⊕ 32位异或

SM4密码算法是一个分组算法。该算法的分组长度为128比特(16字节)，密钥长度为128比特。加密算法与密钥扩展算法都采用32轮非线性迭代结构。数据解密和数据加密的算法结构相同，只是轮密钥的使用顺序相反，解密轮密钥是加密轮密钥的逆序。

密钥及密钥参量

算法实现

一次加密16个字节，密钥大小为16字节。
轮转密钥有32个，每个轮转密钥为16字节，由密钥循环生成32个轮转密钥。
加密按照正向的顺序每次使用一个轮转密钥，循环32次后的到最终加密。
解密过程和加密过程一样，只不过轮转密钥的使用顺序是和加密反向的。

#include <stdio.h>
#include <stdint.h>
#include <assert.h>

#define SHIFT(input, n) (input << n | input >> (32-n))

static const uint32_t FK[4] = {
	0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc,
};

static 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,
};

static const uint8_t S_BOX[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,
};

static inline uint32_t sBox(uint32_t box_input)
{
    uint8_t* s_input = (uint8_t*)&box_input;
    uint8_t s_output[4] = {0};
    s_output[0] = S_BOX[s_input[0]];
    s_output[1] = S_BOX[s_input[1]];
    s_output[2] = S_BOX[s_input[2]];
    s_output[3] = S_BOX[s_input[3]];
    return *(uint32_t*)s_output;
}
static inline uint32_t join_bytes(uint8_t byte_0, uint8_t byte_1, uint8_t byte_2, uint8_t byte_3)
{
    return (((uint32_t)byte_0) << 24) | (((uint32_t)byte_1) << 16) | (((uint32_t)byte_2) << 8) | ((uint32_t)byte_3);
}
static void sm4_core(uint8_t input[16], uint8_t key[16], int mod, uint8_t ouput[16])
{
    uint32_t* text = (uint32_t*)ouput;  // uint32_t text[4];
    uint32_t key_r[32], key_temp[4];
    uint32_t box_input, box_output;
    for (size_t i = 0; i < 4; i++)
    {
        text[i] = join_bytes(input[4 * i], input[4 * i + 1], input[4 * i + 2], input[4 * i + 3]);
    }
    for (size_t i = 0; i < 4; i++)
    {
        key_temp[i] = join_bytes(key[4 * i], key[4 * i + 1], key[4 * i + 2], key[4 * i + 3]);
        key_temp[i] ^= FK[i];
    }
    // gen key round
    for (size_t i = 0; i < 32; i++)
    {
        box_input = key_temp[1] ^ key_temp[2] ^ key_temp[3] ^ CK[i];
        box_output = sBox(box_input);
        key_r[i] = key_temp[0] ^ box_output ^ SHIFT(box_output, 13) ^ SHIFT(box_output, 23);
        key_temp[0] = key_temp[1];
        key_temp[1] = key_temp[2];
        key_temp[2] = key_temp[3];
        key_temp[3] = key_r[i];
    }
    // encrypt decrypt
    for (size_t i = 0; i < 32; i++)
    {
        size_t index = (mod == 0) ? i : (31 - i);
        box_input = text[1] ^ text[2] ^ text[3] ^ key_r[index];
        box_output = sBox(box_input);
        int temp = text[0] ^ box_output ^ SHIFT(box_output, 2) ^ SHIFT(box_output, 10) ^ SHIFT(box_output, 18) ^ SHIFT(box_output, 24);
        text[0] = text[1];
        text[1] = text[2];
        text[2] = text[3];
        text[3] = temp;
    }
    for (size_t i = 0; i < 8; i++)
    {
        ouput[i] ^= ouput[15-i] ^= ouput[i] ^= ouput[15-i];
    }

///test
#ifdef SM4_DEBUG
    for (size_t i = 0; i < 16; i++)
    {
        printf("%02x ", ouput[i]);
    }
    putchar('\n');
#endif
}

void test_sm4_core()
{
    
    uint8_t input[16] = {0x01, 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF, 0xFE, 0xDC, 0xBA, 0x98, 0x76, 0x54, 0x32, 0x10};
    uint8_t key[16] = {0x01, 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF, 0xFE, 0xDC, 0xBA, 0x98, 0x76, 0x54, 0x32, 0x10};
    uint8_t ouput[16];
    sm4_core(input, key, 0, ouput);
    uint8_t input_copy[16] = {0};
    sm4_core(ouput, key, 1, input_copy);
    for (size_t i = 0; i < 16; i++)
    {
        assert(input[i] == input_copy[i]);
    }
    
}

int main()
{
    test_sm4_core();
}

---

reference

该园友有多篇密码学相关文章：https://www.cnblogs.com/kentle/p/14135865.html
国密局文档：http://www.gmbz.org.cn/main/viewfile/20180108015408199368.html
北京大学国产商用密码开源库 https://github.com/guanzhi/GmSSL