介紹

SM4.0（原名SMS4.0）是中華人民共和國政府採用的一種分組密碼標準，由國家密碼管理局於2012年3月21日發佈。相關標準爲“GM/T 0002-2012《SM4分組密碼算法》（原SMS4分組密碼算法）”。在商用密碼體系中，SM4主要用於數據加密，其算法公開，分組長度與密鑰長度均爲128bit，加密算法與密鑰擴展算法都採用32輪非線性迭代結構，S盒爲固定的8比特輸入8比特輸出。SM4.0中的指令長度被提升到大於64K（即64×1024）的水平，這是SM 3.0規格（渲染指令長度允許大於512）的128倍。

加密過程

這裏我簡要介紹一下SM4算法，詳細的過程可以查看參考鏈接，首先我們要知道SM4是一個對稱加密算法，也就是說加密和解密的密鑰相同，首先我們要清楚下面幾個概念

SM4是分組密碼，所以我們要將明文分組，將明文分成128位一組

S(Sbox)盒負責置換我們的明文

因爲SM4面向的是32bit的字(word)，S盒處理的是兩個16進制數也就是8bit的字節，所以我們要用4個S盒來置換
輪函數F的概念如下圖，以字爲單位進行加密運算，稱一次迭代運算爲一輪變換
合成置換T就是非線性變換和線性變換的一個組合過程

瞭解上述一些概念之後加密解密的過程如下圖

在SM4算法中，輪祕鑰的產生是通過用戶選擇主祕鑰作爲基本的祕鑰數據，在通過一些算法生成輪祕鑰，在密鑰拓展中，我們通過一些常數對用戶選擇的主鑰進行操作，增大隨機性。密鑰擴展算法如下

實現

代碼出自這裏

sm4.c加密解密函數的實現

// sm4.c
// Test vector 1
// plain: 01 23 45 67 89 ab cd ef fe dc ba 98 76 54 32 10
// key:   01 23 45 67 89 ab cd ef fe dc ba 98 76 54 32 10
// 	   round key and temp computing result:
// 	   rk[ 0] = f12186f9 X[ 0] = 27fad345
// 		   rk[ 1] = 41662b61 X[ 1] = a18b4cb2
// 		   rk[ 2] = 5a6ab19a X[ 2] = 11c1e22a
// 		   rk[ 3] = 7ba92077 X[ 3] = cc13e2ee
// 		   rk[ 4] = 367360f4 X[ 4] = f87c5bd5
// 		   rk[ 5] = 776a0c61 X[ 5] = 33220757
// 		   rk[ 6] = b6bb89b3 X[ 6] = 77f4c297
// 		   rk[ 7] = 24763151 X[ 7] = 7a96f2eb
// 		   rk[ 8] = a520307c X[ 8] = 27dac07f
// 		   rk[ 9] = b7584dbd X[ 9] = 42dd0f19
// 		   rk[10] = c30753ed X[10] = b8a5da02
// 		   rk[11] = 7ee55b57 X[11] = 907127fa
// 		   rk[12] = 6988608c X[12] = 8b952b83
// 		   rk[13] = 30d895b7 X[13] = d42b7c59
// 		   rk[14] = 44ba14af X[14] = 2ffc5831
// 		   rk[15] = 104495a1 X[15] = f69e6888
// 		   rk[16] = d120b428 X[16] = af2432c4
// 		   rk[17] = 73b55fa3 X[17] = ed1ec85e
// 		   rk[18] = cc874966 X[18] = 55a3ba22
// 		   rk[19] = 92244439 X[19] = 124b18aa
// 		   rk[20] = e89e641f X[20] = 6ae7725f
// 		   rk[21] = 98ca015a X[21] = f4cba1f9
// 		   rk[22] = c7159060 X[22] = 1dcdfa10
// 		   rk[23] = 99e1fd2e X[23] = 2ff60603
// 		   rk[24] = b79bd80c X[24] = eff24fdc
// 		   rk[25] = 1d2115b0 X[25] = 6fe46b75
// 		   rk[26] = 0e228aeb X[26] = 893450ad
// 		   rk[27] = f1780c81 X[27] = 7b938f4c
// 		   rk[28] = 428d3654 X[28] = 536e4246
// 		   rk[29] = 62293496 X[29] = 86b3e94f
// 		   rk[30] = 01cf72e5 X[30] = d206965e
// 		   rk[31] = 9124a012 X[31] = 681edf34
// cypher: 68 1e df 34 d2 06 96 5e 86 b3 e9 4f 53 6e 42 46
// 		
// test vector 2
// the same key and plain 1000000 times coumpting 
// plain:  01 23 45 67 89 ab cd ef fe dc ba 98 76 54 32 10
// key:    01 23 45 67 89 ab cd ef fe dc ba 98 76 54 32 10
// cypher: 59 52 98 c7 c6 fd 27 1f 04 02 f8 04 c3 3d 3f 66

#include "sm4.h"
#include <string.h>
#include <stdio.h>

/*
* 32-bit integer manipulation macros (big endian)
*/
#ifndef GET_ULONG_BE
#define GET_ULONG_BE(n,b,i)                             \
{                                                       \
    (n) = ( (unsigned long) (b)[(i)    ] << 24 )        \
        | ( (unsigned long) (b)[(i) + 1] << 16 )        \
        | ( (unsigned long) (b)[(i) + 2] <<  8 )        \
        | ( (unsigned long) (b)[(i) + 3]       );       \
}
#endif

#ifndef PUT_ULONG_BE
#define PUT_ULONG_BE(n,b,i)                             \
{                                                       \
    (b)[(i)    ] = (unsigned char) ( (n) >> 24 );       \
    (b)[(i) + 1] = (unsigned char) ( (n) >> 16 );       \
    (b)[(i) + 2] = (unsigned char) ( (n) >>  8 );       \
    (b)[(i) + 3] = (unsigned char) ( (n)       );       \
}
#endif

/*
*rotate shift left marco definition
*
*/
#define  SHL(x,n) (((x) & 0xFFFFFFFF) << n)
#define ROTL(x,n) (SHL((x),n) | ((x) >> (32 - n)))

#define SWAP(a,b) { unsigned long t = a; a = b; b = t; t = 0; }

/*
* Expanded SM4 S-boxes
/* Sbox table: 8bits input convert to 8 bits output*/

static const unsigned char SboxTable[16][16] =
{
	{ 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 }
};

/* System parameter */
static const unsigned long FK[4] = { 0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc };

/* fixed parameter */
static const unsigned long 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
};


/*
* private function:
* look up in SboxTable and get the related value.
* args:    [in] inch: 0x00~0xFF (8 bits unsigned value).
*/
static unsigned char sm4Sbox(unsigned char inch)
{
	unsigned char *pTable = (unsigned char *)SboxTable;
	unsigned char retVal = (unsigned char)(pTable[inch]);
	return retVal;
}

/*
* private F(Lt) function:
* "T algorithm" == "L algorithm" + "t algorithm".
* args:    [in] a: a is a 32 bits unsigned value;
* return: c: c is calculated with line algorithm "L" and nonline algorithm "t"
*/
static unsigned long sm4Lt(unsigned long ka)
{
	unsigned long bb = 0;
	unsigned long c = 0;
	unsigned char a[4];
	unsigned char b[4];
	PUT_ULONG_BE(ka, a, 0)
		b[0] = sm4Sbox(a[0]);
	b[1] = sm4Sbox(a[1]);
	b[2] = sm4Sbox(a[2]);
	b[3] = sm4Sbox(a[3]);
	GET_ULONG_BE(bb, b, 0)
		c = bb ^ (ROTL(bb, 2)) ^ (ROTL(bb, 10)) ^ (ROTL(bb, 18)) ^ (ROTL(bb, 24));
	return c;
}

/*
* private F function:
* Calculating and getting encryption/decryption contents.
* args:    [in] x0: original contents;
* args:    [in] x1: original contents;
* args:    [in] x2: original contents;
* args:    [in] x3: original contents;
* args:    [in] rk: encryption/decryption key;
* return the contents of encryption/decryption contents.
*/
static unsigned long sm4F(unsigned long x0, unsigned long x1, unsigned long x2, unsigned long x3, unsigned long rk)
{
	return (x0^sm4Lt(x1^x2^x3^rk));
}


/* private function:
* Calculating round encryption key.
* args:    [in] a: a is a 32 bits unsigned value;
* return: sk[i]: i{0,1,2,3,...31}.
*/
static unsigned long sm4CalciRK(unsigned long ka)
{
	unsigned long bb = 0;
	unsigned long rk = 0;
	unsigned char a[4];
	unsigned char b[4];
	PUT_ULONG_BE(ka, a, 0)
		b[0] = sm4Sbox(a[0]);
	b[1] = sm4Sbox(a[1]);
	b[2] = sm4Sbox(a[2]);
	b[3] = sm4Sbox(a[3]);
	GET_ULONG_BE(bb, b, 0)
		rk = bb ^ (ROTL(bb, 13)) ^ (ROTL(bb, 23));
	return rk;
}

static void sm4_setkey(unsigned long SK[32], unsigned char key[16])
{
	unsigned long MK[4];
	unsigned long k[36];
	unsigned long i = 0;

	GET_ULONG_BE(MK[0], key, 0);
	GET_ULONG_BE(MK[1], key, 4);
	GET_ULONG_BE(MK[2], key, 8);
	GET_ULONG_BE(MK[3], key, 12);
	k[0] = MK[0] ^ FK[0];
	k[1] = MK[1] ^ FK[1];
	k[2] = MK[2] ^ FK[2];
	k[3] = MK[3] ^ FK[3];
	for (; i<32; i++)
	{
		k[i + 4] = k[i] ^ (sm4CalciRK(k[i + 1] ^ k[i + 2] ^ k[i + 3] ^ CK[i]));
		SK[i] = k[i + 4];
	}

}

/*
* SM4 standard one round processing
*
*/
static void sm4_one_round(unsigned long sk[32],
	unsigned char input[16],
	unsigned char output[16])
{
	unsigned long i = 0;
	unsigned long ulbuf[36];

	memset(ulbuf, 0, sizeof(ulbuf));
	GET_ULONG_BE(ulbuf[0], input, 0)
		GET_ULONG_BE(ulbuf[1], input, 4)
		GET_ULONG_BE(ulbuf[2], input, 8)
		GET_ULONG_BE(ulbuf[3], input, 12)
		while (i<32)
		{
			ulbuf[i + 4] = sm4F(ulbuf[i], ulbuf[i + 1], ulbuf[i + 2], ulbuf[i + 3], sk[i]);
			// #ifdef _DEBUG
			//        	printf("rk(%02d) = 0x%08x,  X(%02d) = 0x%08x \n",i,sk[i], i, ulbuf[i+4] );
			// #endif
			i++;
		}
	PUT_ULONG_BE(ulbuf[35], output, 0);
	PUT_ULONG_BE(ulbuf[34], output, 4);
	PUT_ULONG_BE(ulbuf[33], output, 8);
	PUT_ULONG_BE(ulbuf[32], output, 12);
}

/*
* SM4 key schedule (128-bit, encryption)
*/
void sm4_setkey_enc(sm4_context *ctx, unsigned char key[16])
{
	ctx->mode = SM4_ENCRYPT;
	sm4_setkey(ctx->sk, key);
}

/*
* SM4 key schedule (128-bit, decryption)
*/
void sm4_setkey_dec(sm4_context *ctx, unsigned char key[16])
{
	int i;
	ctx->mode = SM4_ENCRYPT;
	sm4_setkey(ctx->sk, key);
	for (i = 0; i < 16; i++)
	{
		SWAP(ctx->sk[i], ctx->sk[31 - i]);
	}
}


/*
* SM4-ECB block encryption/decryption
*/

void sm4_crypt_ecb(sm4_context *ctx,
	int mode,
	int length,
	unsigned char *input,
	unsigned char *output)
{
	while (length > 0)
	{
		sm4_one_round(ctx->sk, input, output);
		input += 16;
		output += 16;
		length -= 16;
	}

}

/*
* SM4-CBC buffer encryption/decryption
*/
void sm4_crypt_cbc(sm4_context *ctx,
	int mode,
	int length,
	unsigned char iv[16],
	unsigned char *input,
	unsigned char *output)
{
	int i;
	unsigned char temp[16];

	if (mode == SM4_ENCRYPT)
	{
		while (length > 0)
		{
			for (i = 0; i < 16; i++)
				output[i] = (unsigned char)(input[i] ^ iv[i]);

			sm4_one_round(ctx->sk, output, output);
			memcpy(iv, output, 16);

			input += 16;
			output += 16;
			length -= 16;
		}
	}
	else /* SM4_DECRYPT */
	{
		while (length > 0)
		{
			memcpy(temp, input, 16);
			sm4_one_round(ctx->sk, input, output);

			for (i = 0; i < 16; i++)
				output[i] = (unsigned char)(output[i] ^ iv[i]);

			memcpy(iv, temp, 16);

			input += 16;
			output += 16;
			length -= 16;
		}
	}
}

sm4.h頭文件，mode選擇加密模式

/**
* \file sm4.h
*/
#ifndef XYSSL_SM4_H
#define XYSSL_SM4_H

#define SM4_ENCRYPT     1
#define SM4_DECRYPT     0

/**
* \brief          SM4 context structure
*/
typedef struct
{
	int mode;                   /*!<  encrypt/decrypt   */
	unsigned long sk[32];       /*!<  SM4 subkeys       */
}
sm4_context;


#ifdef __cplusplus
extern "C" {
#endif

	/**
	* \brief          SM4 key schedule (128-bit, encryption)
	*
	* \param ctx      SM4 context to be initialized
	* \param key      16-byte secret key
	*/
	void sm4_setkey_enc(sm4_context *ctx, unsigned char key[16]);

	/**
	* \brief          SM4 key schedule (128-bit, decryption)
	*
	* \param ctx      SM4 context to be initialized
	* \param key      16-byte secret key
	*/
	void sm4_setkey_dec(sm4_context *ctx, unsigned char key[16]);

	/**
	* \brief          SM4-ECB block encryption/decryption
	* \param ctx      SM4 context
	* \param mode     SM4_ENCRYPT or SM4_DECRYPT
	* \param length   length of the input data
	* \param input    input block
	* \param output   output block
	*/
	void sm4_crypt_ecb(sm4_context *ctx,
		int mode,
		int length,
		unsigned char *input,
		unsigned char *output);

	/**
	* \brief          SM4-CBC buffer encryption/decryption
	* \param ctx      SM4 context
	* \param mode     SM4_ENCRYPT or SM4_DECRYPT
	* \param length   length of the input data
	* \param iv       initialization vector (updated after use)
	* \param input    buffer holding the input data
	* \param output   buffer holding the output data
	*/
	void sm4_crypt_cbc(sm4_context *ctx,
		int mode,
		int length,
		unsigned char iv[16],
		unsigned char *input,
		unsigned char *output);

#ifdef __cplusplus
}
#endif

#endif /* sm4.h */

測試代碼

// test.c
#include <string.h>
#include <stdio.h>
#include "sm4.h"

int main()
{
	unsigned char key[16] = { 0x01, 0x23, 0x45, 0x67, 0x89, 0xab, 0xcd, 0xef, 0xfe, 0xdc, 0xba, 0x98, 0x76, 0x54, 0x32, 0x10 };
	unsigned char input[16] = { 0x01, 0x23, 0x45, 0x67, 0x89, 0xab, 0xcd, 0xef, 0xfe, 0xdc, 0xba, 0x98, 0x76, 0x54, 0x32, 0x10 };
	unsigned char output[16];
	sm4_context ctx;
	unsigned long i;

	//encrypt standard testing vector
	sm4_setkey_enc(&ctx, key);
	sm4_crypt_ecb(&ctx, 1, 16, input, output);
	for (i = 0; i<16; i++)
		printf("%02x ", output[i]);
	printf("\n");

	//解密測試
	sm4_setkey_dec(&ctx, key);
	sm4_crypt_ecb(&ctx, 0, 16, output, output);
	for (i = 0; i<16; i++)
		printf("%02x ", output[i]);
	printf("\n");

	//decrypt 1M times testing vector based on standards.
	i = 0;
	sm4_setkey_enc(&ctx, key);
	while (i<1000000)
	{
		sm4_crypt_ecb(&ctx, 1, 16, input, input);
		i++;
	}
	for (i = 0; i<16; i++)
		printf("%02x ", input[i]);
	printf("\n");

	return 0;
}

運行結果如下

C:\Users\thunder>"D:\AlgorithmTest.exe"
68 1e df 34 d2 06 96 5e 86 b3 e9 4f 53 6e 42 46
01 23 45 67 89 ab cd ef fe dc ba 98 76 54 32 10
59 52 98 c7 c6 fd 27 1f 04 02 f8 04 c3 3d 3f 66

解密

pysm4是國密SM4算法的Python實現，這裏下載

>>> from pysm4 import encrypt, decrypt
# 明文
>>> clear_num = 0x0123456789abcdeffedcba9876543210
# 密鑰
>>> mk = 0x0123456789abcdeffedcba9876543210
# 加密
>>> cipher_num = encrypt(clear_num, mk)
>>> hex(cipher_num)[2:].replace('L', '')
'681edf34d206965e86b3e94f536e4246'
# 解密
>>> clear_num == decrypt(cipher_num, mk)
True
>>>

辨別

CTF逆向可以通過判斷S盒的值來猜測SM4算法，通過S盒生成4個8位的字符，我們將上面實現代碼放入IDA中查看，我們可以通過輸入明文密鑰的格式來猜測SM4算法

__int64 main()
{
  int v0; // edx
  __int64 v1; // ST0C_8
  unsigned int i; // [esp+D0h] [ebp-E0h]
  sm4_context ctx; // [esp+DCh] [ebp-D4h]
  char output[16]; // [esp+168h] [ebp-48h]
  char input[16]; // [esp+180h] [ebp-30h]
  char key[16]; // [esp+198h] [ebp-18h]

  key[0] = 1;
  key[1] = 0x23;
  key[2] = 0x45;
  key[3] = 0x67;
  key[4] = 0x89u;
  key[5] = 0xABu;
  key[6] = 0xCDu;
  key[7] = 0xEFu;
  key[8] = 0xFEu;
  key[9] = 0xDCu;
  key[10] = 0xBAu;
  key[11] = 0x98u;
  key[12] = 0x76;
  key[13] = 0x54;
  key[14] = 0x32;
  key[15] = 0x10;
  input[0] = 1;
  input[1] = 0x23;
  input[2] = 0x45;
  input[3] = 0x67;
  input[4] = 0x89u;
  input[5] = 0xABu;
  input[6] = 0xCDu;
  input[7] = 0xEFu;
  input[8] = 0xFEu;
  input[9] = 0xDCu;
  input[10] = 0xBAu;
  input[11] = 0x98u;
  input[12] = 0x76;
  input[13] = 0x54;
  input[14] = 0x32;
  input[15] = 0x10;
  j__sm4_setkey_enc(&ctx, key);
  j__sm4_crypt_ecb(&ctx, 1, 16, input, output);
  for ( i = 0; i < 0x10; ++i )
    _printf("%02x ", (unsigned __int8)output[i]);
  _printf("\n");
  j__sm4_setkey_dec(&ctx, key);
  j__sm4_crypt_ecb(&ctx, 0, 16, output, output);
  for ( i = 0; i < 0x10; ++i )
    _printf("%02x ", (unsigned __int8)output[i]);
  _printf("\n");
  i = 0;
  j__sm4_setkey_enc(&ctx, key);
  while ( i < 0xF4240 )
  {
    j__sm4_crypt_ecb(&ctx, 1, 16, input, input);
    ++i;
  }
  for ( i = 0; i < 0x10; ++i )
    _printf("%02x ", (unsigned __int8)input[i]);
  _printf("\n");
  HIDWORD(v1) = v0;
  LODWORD(v1) = 0;
  return v1;
}

算法中的T變換觀察返回值也有很明顯的特徵

unsigned int __cdecl sm4F(unsigned int x0, unsigned int x1, unsigned int x2, unsigned int x3, unsigned int rk)
{
  return x0 ^ (unsigned __int64)sm4Lt(rk ^ x3 ^ x2 ^ x1); //返回多組異或
}

/************************************************************************************************/

__int64 __cdecl sm4Lt(unsigned int ka)
{
  unsigned __int8 b; // STD8_1
  unsigned __int8 b_1; // STD9_1
  unsigned __int8 b_2; // STDA_1
  unsigned __int8 v4; // al
  unsigned int bb; // STFC_4
  __int64 v6; // ST00_8

  b = sm4Sbox(SHIBYTE(ka));
  b_1 = sm4Sbox(SBYTE2(ka));
  b_2 = sm4Sbox(SBYTE1(ka));
  v4 = sm4Sbox(ka);
  bb = v4 | (b_2 << 8) | (b_1 << 16) | (b << 24); // 分4組每組8位計算
  HIDWORD(v6) = (bb >> 8) | (bb << 24);
  LODWORD(v6) = HIDWORD(v6) ^ ((bb >> 14) | (bb << 18)) ^ ((bb >> 22) | (bb << 10)) ^ bb ^ ((bb >> 30) | 4 * bb);
  return v6;
}

例題

2019ciscn-bbvvmm

下面的代碼和上面的對比可以很容易的猜到SM4

unsigned __int64 __fastcall sub_400EE2(__int64 a1, __int64 a2, __int64 a3, __int64 a4, __int64 a5)
{
  return a1 ^ sub_400D87(a5 ^ a4 ^ a3 ^ a2);
}

/************************************************************************************************/

__int64 __cdecl sm4Lt(unsigned int ka)
{
  unsigned __int8 b; // STD8_1
  unsigned __int8 b_1; // STD9_1
  unsigned __int8 b_2; // STDA_1
  unsigned __int8 v4; // al
  unsigned int bb; // STFC_4
  __int64 v6; // ST00_8

  b = sm4Sbox(SHIBYTE(ka));
  b_1 = sm4Sbox(SBYTE2(ka));
  b_2 = sm4Sbox(SBYTE1(ka));
  v4 = sm4Sbox(ka);
  bb = v4 | (b_2 << 8) | (b_1 << 16) | (b << 24);
  HIDWORD(v6) = (bb >> 8) | (bb << 24);
  LODWORD(v6) = HIDWORD(v6) ^ ((bb >> 14) | (bb << 18)) ^ ((bb >> 22) | (bb << 10)) ^ bb ^ ((bb >> 30) | 4 * bb);
  return v6;
}