int blowfish_ecb_encrypt(const unsigned char *pt, unsigned char *ct, symmetric_key *skey)
#endif
{
ulong32 L, R;
int r;
#ifndef __GNUC__
ulong32 *S1, *S2, *S3, *S4;
#endif
LTC_ARGCHK(pt != NULL);
LTC_ARGCHK(ct != NULL);
LTC_ARGCHK(skey != NULL);
#ifndef __GNUC__
S1 = skey->blowfish.S[0];
S2 = skey->blowfish.S[1];
S3 = skey->blowfish.S[2];
S4 = skey->blowfish.S[3];
#endif
/* load it */
LOAD32H(L, &pt[0]);
LOAD32H(R, &pt[4]);
/* do 16 rounds */
for (r = 0; r < 16; ) {
L ^= skey->blowfish.K[r++]; R ^= F(L);
R ^= skey->blowfish.K[r++]; L ^= F(R);
L ^= skey->blowfish.K[r++]; R ^= F(L);
R ^= skey->blowfish.K[r++]; L ^= F(R);
}
/* last keying */
R ^= skey->blowfish.K[17];
L ^= skey->blowfish.K[16];
/* store */
STORE32H(R, &ct[0]);
STORE32H(L, &ct[4]);
return CRYPT_OK;
}
///////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// TransformFunction
//
// Compress 512-bits
///////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
static
void
TransformFunction
(
Sha256Context* Context,
uint8_t* Buffer
)
{
uint32_t S[8];
uint32_t W[64];
uint32_t t0;
uint32_t t1;
uint32_t t;
int i;
// Copy state into S
for( i=0; i<8; i++ )
{
S[i] = Context->state[i];
}
// Copy the state into 512-bits into W[0..15]
for( i=0; i<16; i++ )
{
LOAD32H( W[i], Buffer + (4*i) );
}
// Fill W[16..63]
for( i=16; i<64; i++ )
{
W[i] = Gamma1( W[i-2]) + W[i-7] + Gamma0( W[i-15] ) + W[i-16];
}
// Compress
for( i=0; i<64; i++ )
{
Sha256Round( S[0], S[1], S[2], S[3], S[4], S[5], S[6], S[7], i );
t = S[7];
S[7] = S[6];
S[6] = S[5];
S[5] = S[4];
S[4] = S[3];
S[3] = S[2];
S[2] = S[1];
S[1] = S[0];
S[0] = t;
}
// Feedback
for( i=0; i<8; i++ )
{
Context->state[i] = Context->state[i] + S[i];
}
}
INT blowfish_ecb_decrypt(const UCHAR *ct, UCHAR *pt, symmetric_key *skey)
#endif
{
ULONG L, R;
INT r;
#ifndef __GNUC__
ULONG *S1, *S2, *S3, *S4;
#endif
LTC_ARGCHK(pt != NULL);
LTC_ARGCHK(ct != NULL);
LTC_ARGCHK(skey != NULL);
#ifndef __GNUC__
S1 = skey->blowfish.S[0];
S2 = skey->blowfish.S[1];
S3 = skey->blowfish.S[2];
S4 = skey->blowfish.S[3];
#endif
/* load it */
LOAD32H(R, &ct[0]);
LOAD32H(L, &ct[4]);
/* undo last keying */
R ^= skey->blowfish.K[17];
L ^= skey->blowfish.K[16];
/* do 16 rounds */
for (r = 15; r > 0; ) {
L ^= F(R); R ^= skey->blowfish.K[r--];
R ^= F(L); L ^= skey->blowfish.K[r--];
L ^= F(R); R ^= skey->blowfish.K[r--];
R ^= F(L); L ^= skey->blowfish.K[r--];
}
/* store */
STORE32H(L, &pt[0]);
STORE32H(R, &pt[4]);
return CRYPT_OK;
}
void blowfish_ecb_decrypt(const unsigned char *ct, unsigned char *pt, symmetric_key *key)
#endif
{
ulong32 L, R;
int r;
#ifndef __GNUC__
ulong32 *S1, *S2, *S3, *S4;
#endif
_ARGCHK(pt != NULL);
_ARGCHK(ct != NULL);
_ARGCHK(key != NULL);
#ifndef __GNUC__
S1 = key->blowfish.S[0];
S2 = key->blowfish.S[1];
S3 = key->blowfish.S[2];
S4 = key->blowfish.S[3];
#endif
/* load it */
LOAD32H(R, &ct[0]);
LOAD32H(L, &ct[4]);
/* undo last keying */
R ^= key->blowfish.K[17];
L ^= key->blowfish.K[16];
/* do 16 rounds */
for (r = 15; r > 0; ) {
L ^= F(R); R ^= key->blowfish.K[r--];
R ^= F(L); L ^= key->blowfish.K[r--];
L ^= F(R); R ^= key->blowfish.K[r--];
R ^= F(L); L ^= key->blowfish.K[r--];
}
/* store */
STORE32H(L, &pt[0]);
STORE32H(R, &pt[4]);
}
int multi2_setup(const unsigned char *key, int keylen, int num_rounds, symmetric_key *skey)
{
ulong32 sk[8], dk[2];
int x;
LTC_ARGCHK(key != NULL);
LTC_ARGCHK(skey != NULL);
if (keylen != 40) return CRYPT_INVALID_KEYSIZE;
if (num_rounds == 0) num_rounds = 128;
skey->multi2.N = num_rounds;
for (x = 0; x < 8; x++) {
LOAD32H(sk[x], key + x*4);
}
LOAD32H(dk[0], key + 32);
LOAD32H(dk[1], key + 36);
setup(dk, sk, skey->multi2.uk);
zeromem(sk, sizeof(sk));
zeromem(dk, sizeof(dk));
return CRYPT_OK;
}
static void four_rounds(pelican_state *pelmac)
{
ulong32 s0, s1, s2, s3, t0, t1, t2, t3;
int r;
LOAD32H(s0, pelmac->state );
LOAD32H(s1, pelmac->state + 4);
LOAD32H(s2, pelmac->state + 8);
LOAD32H(s3, pelmac->state + 12);
for (r = 0; r < 4; r++) {
t0 =
Te0(byte(s0, 3)) ^
Te1(byte(s1, 2)) ^
Te2(byte(s2, 1)) ^
Te3(byte(s3, 0));
t1 =
Te0(byte(s1, 3)) ^
Te1(byte(s2, 2)) ^
Te2(byte(s3, 1)) ^
Te3(byte(s0, 0));
t2 =
Te0(byte(s2, 3)) ^
Te1(byte(s3, 2)) ^
Te2(byte(s0, 1)) ^
Te3(byte(s1, 0));
t3 =
Te0(byte(s3, 3)) ^
Te1(byte(s0, 2)) ^
Te2(byte(s1, 1)) ^
Te3(byte(s2, 0));
s0 = t0; s1 = t1; s2 = t2; s3 = t3;
}
STORE32H(s0, pelmac->state );
STORE32H(s1, pelmac->state + 4);
STORE32H(s2, pelmac->state + 8);
STORE32H(s3, pelmac->state + 12);
}
int crc32_test(void)
{
#ifndef LTC_TEST
return CRYPT_NOP;
#else
const void* in = "libtomcrypt";
const unsigned char crc32[] = { 0xef, 0x76, 0x73, 0xb3 };
unsigned char out[4];
crc32_state ctx;
crc32_init(&ctx);
crc32_update(&ctx, in, strlen(in));
crc32_finish(&ctx, out, 4);
if (XMEMCMP(crc32, out, 4)) {
#ifdef LTC_TEST_DBG
ulong32 _out, _crc32;
LOAD32H(_out, out);
LOAD32H(_crc32, crc32);
printf("crc32 fail! Is: 0x%x Should: 0x%x\n", _out, _crc32);
#endif
return CRYPT_FAIL_TESTVECTOR;
}
return CRYPT_OK;
#endif
}
static void sha256_compress(hash_state * md)
#endif
{
unsigned long S[8], W[64], t0, t1;
int i;
_ARGCHK(md != NULL);
/* copy state into S */
for (i = 0; i < 8; i++)
S[i] = md->sha256.state[i];
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], md->sha256.buf + (4*i));
}
/* fill W[16..63] */
for (i = 16; i < 64; i++) {
W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
}
/* Compress */
for (i = 0; i < 64; i++) {
t0 = S[7] + Sigma1(S[4]) + Ch(S[4], S[5], S[6]) + K[i] + W[i];
t1 = Sigma0(S[0]) + Maj(S[0], S[1], S[2]);
S[7] = S[6];
S[6] = S[5];
S[5] = S[4];
S[4] = S[3] + t0;
S[3] = S[2];
S[2] = S[1];
S[1] = S[0];
S[0] = t0 + t1;
}
/* feedback */
for (i = 0; i < 8; i++) {
md->sha256.state[i] = md->sha256.state[i] + S[i];
}
}
static void sha256_compress(sha256_state * md, unsigned char *buf)
{
unsigned long S[8], W[64], t0, t1;
unsigned long t;
int i;
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = md->state[i];
}
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], buf + (4*i));
}
/* fill W[16..63] */
for (i = 16; i < 64; i++) {
W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
}
/* Compress */
#define RND(a,b,c,d,e,f,g,h,i) \
t0 = h + Sigma1(e) + Ch(e, f, g) + K[i] + W[i]; \
t1 = Sigma0(a) + Maj(a, b, c); \
d += t0; \
h = t0 + t1;
for (i = 0; i < 64; ++i) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i);
t = S[7]; S[7] = S[6]; S[6] = S[5]; S[5] = S[4];
S[4] = S[3]; S[3] = S[2]; S[2] = S[1]; S[1] = S[0]; S[0] = t;
}
/* feedback */
for (i = 0; i < 8; i++) {
md->state[i] = md->state[i] + S[i];
}
}
int cast5_setup(const unsigned char *key, int keylen, int num_rounds, symmetric_key *skey)
#endif
{
ulong32 x[4], z[4];
unsigned char buf[16];
int y, i;
LTC_ARGCHK(key != NULL);
LTC_ARGCHK(skey != NULL);
if (num_rounds != 12 && num_rounds != 16 && num_rounds != 0) {
return CRYPT_INVALID_ROUNDS;
}
if (num_rounds == 12 && keylen > 10) {
return CRYPT_INVALID_ROUNDS;
}
if (keylen < 5 || keylen > 16) {
return CRYPT_INVALID_KEYSIZE;
}
/* extend the key as required */
zeromem(buf, sizeof(buf));
XMEMCPY(buf, key, (size_t)keylen);
/* load and start the awful looking network */
for (y = 0; y < 4; y++) {
LOAD32H(x[3-y],buf+4*y);
}
for (i = y = 0; y < 2; y++) {
z[3] = x[3] ^ S5[GB(x, 0xD)] ^ S6[GB(x, 0xF)] ^ S7[GB(x, 0xC)] ^ S8[GB(x, 0xE)] ^ S7[GB(x, 0x8)];
z[2] = x[1] ^ S5[GB(z, 0x0)] ^ S6[GB(z, 0x2)] ^ S7[GB(z, 0x1)] ^ S8[GB(z, 0x3)] ^ S8[GB(x, 0xA)];
z[1] = x[0] ^ S5[GB(z, 0x7)] ^ S6[GB(z, 0x6)] ^ S7[GB(z, 0x5)] ^ S8[GB(z, 0x4)] ^ S5[GB(x, 0x9)];
z[0] = x[2] ^ S5[GB(z, 0xA)] ^ S6[GB(z, 0x9)] ^ S7[GB(z, 0xb)] ^ S8[GB(z, 0x8)] ^ S6[GB(x, 0xB)];
skey->cast5.K[i++] = S5[GB(z, 0x8)] ^ S6[GB(z, 0x9)] ^ S7[GB(z, 0x7)] ^ S8[GB(z, 0x6)] ^ S5[GB(z, 0x2)];
skey->cast5.K[i++] = S5[GB(z, 0xA)] ^ S6[GB(z, 0xB)] ^ S7[GB(z, 0x5)] ^ S8[GB(z, 0x4)] ^ S6[GB(z, 0x6)];
skey->cast5.K[i++] = S5[GB(z, 0xC)] ^ S6[GB(z, 0xd)] ^ S7[GB(z, 0x3)] ^ S8[GB(z, 0x2)] ^ S7[GB(z, 0x9)];
skey->cast5.K[i++] = S5[GB(z, 0xE)] ^ S6[GB(z, 0xF)] ^ S7[GB(z, 0x1)] ^ S8[GB(z, 0x0)] ^ S8[GB(z, 0xc)];
x[3] = z[1] ^ S5[GB(z, 0x5)] ^ S6[GB(z, 0x7)] ^ S7[GB(z, 0x4)] ^ S8[GB(z, 0x6)] ^ S7[GB(z, 0x0)];
x[2] = z[3] ^ S5[GB(x, 0x0)] ^ S6[GB(x, 0x2)] ^ S7[GB(x, 0x1)] ^ S8[GB(x, 0x3)] ^ S8[GB(z, 0x2)];
x[1] = z[2] ^ S5[GB(x, 0x7)] ^ S6[GB(x, 0x6)] ^ S7[GB(x, 0x5)] ^ S8[GB(x, 0x4)] ^ S5[GB(z, 0x1)];
x[0] = z[0] ^ S5[GB(x, 0xA)] ^ S6[GB(x, 0x9)] ^ S7[GB(x, 0xb)] ^ S8[GB(x, 0x8)] ^ S6[GB(z, 0x3)];
skey->cast5.K[i++] = S5[GB(x, 0x3)] ^ S6[GB(x, 0x2)] ^ S7[GB(x, 0xc)] ^ S8[GB(x, 0xd)] ^ S5[GB(x, 0x8)];
skey->cast5.K[i++] = S5[GB(x, 0x1)] ^ S6[GB(x, 0x0)] ^ S7[GB(x, 0xe)] ^ S8[GB(x, 0xf)] ^ S6[GB(x, 0xd)];
skey->cast5.K[i++] = S5[GB(x, 0x7)] ^ S6[GB(x, 0x6)] ^ S7[GB(x, 0x8)] ^ S8[GB(x, 0x9)] ^ S7[GB(x, 0x3)];
skey->cast5.K[i++] = S5[GB(x, 0x5)] ^ S6[GB(x, 0x4)] ^ S7[GB(x, 0xa)] ^ S8[GB(x, 0xb)] ^ S8[GB(x, 0x7)];
/* second half */
z[3] = x[3] ^ S5[GB(x, 0xD)] ^ S6[GB(x, 0xF)] ^ S7[GB(x, 0xC)] ^ S8[GB(x, 0xE)] ^ S7[GB(x, 0x8)];
z[2] = x[1] ^ S5[GB(z, 0x0)] ^ S6[GB(z, 0x2)] ^ S7[GB(z, 0x1)] ^ S8[GB(z, 0x3)] ^ S8[GB(x, 0xA)];
z[1] = x[0] ^ S5[GB(z, 0x7)] ^ S6[GB(z, 0x6)] ^ S7[GB(z, 0x5)] ^ S8[GB(z, 0x4)] ^ S5[GB(x, 0x9)];
z[0] = x[2] ^ S5[GB(z, 0xA)] ^ S6[GB(z, 0x9)] ^ S7[GB(z, 0xb)] ^ S8[GB(z, 0x8)] ^ S6[GB(x, 0xB)];
skey->cast5.K[i++] = S5[GB(z, 0x3)] ^ S6[GB(z, 0x2)] ^ S7[GB(z, 0xc)] ^ S8[GB(z, 0xd)] ^ S5[GB(z, 0x9)];
skey->cast5.K[i++] = S5[GB(z, 0x1)] ^ S6[GB(z, 0x0)] ^ S7[GB(z, 0xe)] ^ S8[GB(z, 0xf)] ^ S6[GB(z, 0xc)];
skey->cast5.K[i++] = S5[GB(z, 0x7)] ^ S6[GB(z, 0x6)] ^ S7[GB(z, 0x8)] ^ S8[GB(z, 0x9)] ^ S7[GB(z, 0x2)];
skey->cast5.K[i++] = S5[GB(z, 0x5)] ^ S6[GB(z, 0x4)] ^ S7[GB(z, 0xa)] ^ S8[GB(z, 0xb)] ^ S8[GB(z, 0x6)];
x[3] = z[1] ^ S5[GB(z, 0x5)] ^ S6[GB(z, 0x7)] ^ S7[GB(z, 0x4)] ^ S8[GB(z, 0x6)] ^ S7[GB(z, 0x0)];
x[2] = z[3] ^ S5[GB(x, 0x0)] ^ S6[GB(x, 0x2)] ^ S7[GB(x, 0x1)] ^ S8[GB(x, 0x3)] ^ S8[GB(z, 0x2)];
x[1] = z[2] ^ S5[GB(x, 0x7)] ^ S6[GB(x, 0x6)] ^ S7[GB(x, 0x5)] ^ S8[GB(x, 0x4)] ^ S5[GB(z, 0x1)];
x[0] = z[0] ^ S5[GB(x, 0xA)] ^ S6[GB(x, 0x9)] ^ S7[GB(x, 0xb)] ^ S8[GB(x, 0x8)] ^ S6[GB(z, 0x3)];
skey->cast5.K[i++] = S5[GB(x, 0x8)] ^ S6[GB(x, 0x9)] ^ S7[GB(x, 0x7)] ^ S8[GB(x, 0x6)] ^ S5[GB(x, 0x3)];
skey->cast5.K[i++] = S5[GB(x, 0xa)] ^ S6[GB(x, 0xb)] ^ S7[GB(x, 0x5)] ^ S8[GB(x, 0x4)] ^ S6[GB(x, 0x7)];
skey->cast5.K[i++] = S5[GB(x, 0xc)] ^ S6[GB(x, 0xd)] ^ S7[GB(x, 0x3)] ^ S8[GB(x, 0x2)] ^ S7[GB(x, 0x8)];
skey->cast5.K[i++] = S5[GB(x, 0xe)] ^ S6[GB(x, 0xf)] ^ S7[GB(x, 0x1)] ^ S8[GB(x, 0x0)] ^ S8[GB(x, 0xd)];
}
skey->cast5.keylen = keylen;
#ifdef LTC_CLEAN_STACK
zeromem(buf, sizeof(buf));
zeromem(x, sizeof(x));
zeromem(z, sizeof(z));
#endif
return CRYPT_OK;
}
/**
Initialize the AES (Rijndael) block cipher
@param key The symmetric key you wish to pass
@param keylen The key length in bytes
@param num_rounds The number of rounds desired (0 for default)
@param skey The key in as scheduled by this function.
@return CRYPT_OK if successful
*/
int rijndael_setup(const unsigned char *key, int keylen, int num_rounds, rijndael_key *rijndael)
{
int i, j;
unsigned long temp, *rk;
unsigned long *rrk;
LTC_ARGCHK(key != NULL);
LTC_ARGCHK(rijndael != NULL);
if (keylen != 16 && keylen != 24 && keylen != 32)
return CRYPT_INVALID_KEYSIZE;
if (num_rounds != 0 && num_rounds != (10 + ((keylen / 8) - 2) * 2))
return CRYPT_INVALID_ROUNDS;
rijndael->Nr = 10 + ((keylen / 8) - 2) * 2;
/* setup the forward key */
i = 0;
rk = rijndael->eK;
LOAD32H(rk[0], key);
LOAD32H(rk[1], key + 4);
LOAD32H(rk[2], key + 8);
LOAD32H(rk[3], key + 12);
if (keylen == 16)
{
j = 44;
for (;;)
{
temp = rk[3];
rk[4] = rk[0] ^ setup_mix(temp) ^ rcon[i];
rk[5] = rk[1] ^ rk[4];
rk[6] = rk[2] ^ rk[5];
rk[7] = rk[3] ^ rk[6];
if (++i == 10)
break;
rk += 4;
}
}
else if (keylen == 24)
{
j = 52;
LOAD32H(rk[4], key + 16);
LOAD32H(rk[5], key + 20);
for (;;)
{
temp = rijndael->eK[rk - rijndael->eK + 5];
rk[6] = rk[0] ^ setup_mix(temp) ^ rcon[i];
rk[7] = rk[1] ^ rk[6];
rk[8] = rk[2] ^ rk[7];
rk[9] = rk[3] ^ rk[8];
if (++i == 8)
break;
rk[10] = rk[4] ^ rk[9];
rk[11] = rk[5] ^ rk[10];
rk += 6;
}
}
else if (keylen == 32)
{
j = 60;
LOAD32H(rk[4], key + 16);
LOAD32H(rk[5], key + 20);
LOAD32H(rk[6], key + 24);
LOAD32H(rk[7], key + 28);
for (;;)
{
temp = rijndael->eK[rk - rijndael->eK + 7];
rk[8] = rk[0] ^ setup_mix(temp) ^ rcon[i];
rk[9] = rk[1] ^ rk[8];
rk[10] = rk[2] ^ rk[9];
rk[11] = rk[3] ^ rk[10];
if (++i == 7)
{
break;
}
temp = rk[11];
rk[12] = rk[4] ^ setup_mix(RORc(temp, 8));
rk[13] = rk[5] ^ rk[12];
rk[14] = rk[6] ^ rk[13];
rk[15] = rk[7] ^ rk[14];
rk += 8;
}
}
else
{
/* this can't happen */
return CRYPT_ERROR;
}
/* setup the inverse key now */
rk = rijndael->dK;
rrk = rijndael->eK + j - 4;
/* apply the inverse MixColumn transform to all round keys but the first and the last: */
/* copy first */
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk = *rrk;
rk -= 3; rrk -= 3;
for (i = 1; i < rijndael->Nr; i++)
{
rrk -= 4;
rk += 4;
temp = rrk[0];
rk[0] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[1];
rk[1] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[2];
rk[2] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[3];
rk[3] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
}
/* copy last */
rrk -= 4;
rk += 4;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk = *rrk;
return CRYPT_OK;
}
/**
Decrypts a block of text with AES
@param ct The input ciphertext (16 bytes)
@param pt The output plaintext (16 bytes)
@param skey The key as scheduled
@return CRYPT_OK if successful
*/
int rijndael_ecb_decrypt(const unsigned char *ct, unsigned char *pt, rijndael_key *rijndael)
{
unsigned long s0, s1, s2, s3, t0, t1, t2, t3, *rk;
int Nr, r;
LTC_ARGCHK(pt != NULL);
LTC_ARGCHK(ct != NULL);
LTC_ARGCHK(rijndael != NULL);
Nr = rijndael->Nr;
rk = rijndael->dK;
/*
* map byte array block to cipher state
* and add initial round key:
*/
LOAD32H(s0, ct); s0 ^= rk[0];
LOAD32H(s1, ct + 4); s1 ^= rk[1];
LOAD32H(s2, ct + 8); s2 ^= rk[2];
LOAD32H(s3, ct + 12); s3 ^= rk[3];
/*
* Nr - 1 full rounds:
*/
r = Nr >> 1;
for (;;)
{
t0 =
Td0(byte(s0, 3)) ^
Td1(byte(s3, 2)) ^
Td2(byte(s2, 1)) ^
Td3(byte(s1, 0)) ^
rk[4];
t1 =
Td0(byte(s1, 3)) ^
Td1(byte(s0, 2)) ^
Td2(byte(s3, 1)) ^
Td3(byte(s2, 0)) ^
rk[5];
t2 =
Td0(byte(s2, 3)) ^
Td1(byte(s1, 2)) ^
Td2(byte(s0, 1)) ^
Td3(byte(s3, 0)) ^
rk[6];
t3 =
Td0(byte(s3, 3)) ^
Td1(byte(s2, 2)) ^
Td2(byte(s1, 1)) ^
Td3(byte(s0, 0)) ^
rk[7];
rk += 8;
if (--r == 0)
break;
s0 =
Td0(byte(t0, 3)) ^
Td1(byte(t3, 2)) ^
Td2(byte(t2, 1)) ^
Td3(byte(t1, 0)) ^
rk[0];
s1 =
Td0(byte(t1, 3)) ^
Td1(byte(t0, 2)) ^
Td2(byte(t3, 1)) ^
Td3(byte(t2, 0)) ^
rk[1];
s2 =
Td0(byte(t2, 3)) ^
Td1(byte(t1, 2)) ^
Td2(byte(t0, 1)) ^
Td3(byte(t3, 0)) ^
rk[2];
s3 =
Td0(byte(t3, 3)) ^
Td1(byte(t2, 2)) ^
Td2(byte(t1, 1)) ^
Td3(byte(t0, 0)) ^
rk[3];
}
/*
* apply last round and
* map cipher state to byte array block:
*/
s0 =
(Td4[byte(t0, 3)] & 0xff000000) ^
(Td4[byte(t3, 2)] & 0x00ff0000) ^
(Td4[byte(t2, 1)] & 0x0000ff00) ^
(Td4[byte(t1, 0)] & 0x000000ff) ^
rk[0];
STORE32H(s0, pt);
s1 =
(Td4[byte(t1, 3)] & 0xff000000) ^
(Td4[byte(t0, 2)] & 0x00ff0000) ^
(Td4[byte(t3, 1)] & 0x0000ff00) ^
(Td4[byte(t2, 0)] & 0x000000ff) ^
rk[1];
STORE32H(s1, pt + 4);
s2 =
(Td4[byte(t2, 3)] & 0xff000000) ^
(Td4[byte(t1, 2)] & 0x00ff0000) ^
(Td4[byte(t0, 1)] & 0x0000ff00) ^
(Td4[byte(t3, 0)] & 0x000000ff) ^
rk[2];
STORE32H(s2, pt + 8);
s3 =
(Td4[byte(t3, 3)] & 0xff000000) ^
(Td4[byte(t2, 2)] & 0x00ff0000) ^
(Td4[byte(t1, 1)] & 0x0000ff00) ^
(Td4[byte(t0, 0)] & 0x000000ff) ^
rk[3];
STORE32H(s3, pt + 12);
return CRYPT_OK;
}
static void sha1_compress(struct sha1_state *sha1, unsigned char *buf)
{
SHA1_INT32 a,b,c,d,e,W[80],i;
/** copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], buf + (4*i));
}
/** copy state */
a = sha1->state[0];
b = sha1->state[1];
c = sha1->state[2];
d = sha1->state[3];
e = sha1->state[4];
/** expand it */
for (i = 16; i < 80; i++) {
W[i] = ROL(W[i-3] ^ W[i-8] ^ W[i-14] ^ W[i-16], 1);
}
/** compress */
/** round one */
#define FF0(a,b,c,d,e,i) e = (ROLc(a, 5) + F0(b,c,d) + e + W[i] + 0x5a827999UL); b = ROLc(b, 30);
#define FF1(a,b,c,d,e,i) e = (ROLc(a, 5) + F1(b,c,d) + e + W[i] + 0x6ed9eba1UL); b = ROLc(b, 30);
#define FF2(a,b,c,d,e,i) e = (ROLc(a, 5) + F2(b,c,d) + e + W[i] + 0x8f1bbcdcUL); b = ROLc(b, 30);
#define FF3(a,b,c,d,e,i) e = (ROLc(a, 5) + F3(b,c,d) + e + W[i] + 0xca62c1d6UL); b = ROLc(b, 30);
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++);
FF0(e,a,b,c,d,i++);
FF0(d,e,a,b,c,i++);
FF0(c,d,e,a,b,i++);
FF0(b,c,d,e,a,i++);
}
/** round two */
for (; i < 40; ) {
FF1(a,b,c,d,e,i++);
FF1(e,a,b,c,d,i++);
FF1(d,e,a,b,c,i++);
FF1(c,d,e,a,b,i++);
FF1(b,c,d,e,a,i++);
}
/** round three */
for (; i < 60; ) {
FF2(a,b,c,d,e,i++);
FF2(e,a,b,c,d,i++);
FF2(d,e,a,b,c,i++);
FF2(c,d,e,a,b,i++);
FF2(b,c,d,e,a,i++);
}
/** round four */
for (; i < 80; ) {
FF3(a,b,c,d,e,i++);
FF3(e,a,b,c,d,i++);
FF3(d,e,a,b,c,i++);
FF3(c,d,e,a,b,i++);
FF3(b,c,d,e,a,i++);
}
#undef FF0
#undef FF1
#undef FF2
#undef FF3
/** store */
sha1->state[0] = sha1->state[0] + a;
sha1->state[1] = sha1->state[1] + b;
sha1->state[2] = sha1->state[2] + c;
sha1->state[3] = sha1->state[3] + d;
sha1->state[4] = sha1->state[4] + e;
}
int ECB_DEC(const unsigned char *ct, unsigned char *pt, symmetric_key *skey)
#endif
{
ulong32 s0, s1, s2, s3, t0, t1, t2, t3, *rk;
int Nr, r;
LTC_ARGCHK(pt != NULL);
LTC_ARGCHK(ct != NULL);
LTC_ARGCHK(skey != NULL);
Nr = skey->rijndael.Nr;
rk = skey->rijndael.dK;
/*
* map byte array block to cipher state
* and add initial round key:
*/
LOAD32H(s0, ct ); s0 ^= rk[0];
LOAD32H(s1, ct + 4); s1 ^= rk[1];
LOAD32H(s2, ct + 8); s2 ^= rk[2];
LOAD32H(s3, ct + 12); s3 ^= rk[3];
#ifdef LTC_SMALL_CODE
for (r = 0; ; r++) {
rk += 4;
t0 =
Td0(byte(s0, 3)) ^
Td1(byte(s3, 2)) ^
Td2(byte(s2, 1)) ^
Td3(byte(s1, 0)) ^
rk[0];
t1 =
Td0(byte(s1, 3)) ^
Td1(byte(s0, 2)) ^
Td2(byte(s3, 1)) ^
Td3(byte(s2, 0)) ^
rk[1];
t2 =
Td0(byte(s2, 3)) ^
Td1(byte(s1, 2)) ^
Td2(byte(s0, 1)) ^
Td3(byte(s3, 0)) ^
rk[2];
t3 =
Td0(byte(s3, 3)) ^
Td1(byte(s2, 2)) ^
Td2(byte(s1, 1)) ^
Td3(byte(s0, 0)) ^
rk[3];
if (r == Nr-2) {
break;
}
s0 = t0; s1 = t1; s2 = t2; s3 = t3;
}
rk += 4;
#else
/*
* Nr - 1 full rounds:
*/
r = Nr >> 1;
for (;;) {
t0 =
Td0(byte(s0, 3)) ^
Td1(byte(s3, 2)) ^
Td2(byte(s2, 1)) ^
Td3(byte(s1, 0)) ^
rk[4];
t1 =
Td0(byte(s1, 3)) ^
Td1(byte(s0, 2)) ^
Td2(byte(s3, 1)) ^
Td3(byte(s2, 0)) ^
rk[5];
t2 =
Td0(byte(s2, 3)) ^
Td1(byte(s1, 2)) ^
Td2(byte(s0, 1)) ^
Td3(byte(s3, 0)) ^
rk[6];
t3 =
Td0(byte(s3, 3)) ^
Td1(byte(s2, 2)) ^
Td2(byte(s1, 1)) ^
Td3(byte(s0, 0)) ^
rk[7];
rk += 8;
if (--r == 0) {
break;
}
s0 =
Td0(byte(t0, 3)) ^
Td1(byte(t3, 2)) ^
Td2(byte(t2, 1)) ^
Td3(byte(t1, 0)) ^
rk[0];
s1 =
Td0(byte(t1, 3)) ^
Td1(byte(t0, 2)) ^
Td2(byte(t3, 1)) ^
Td3(byte(t2, 0)) ^
rk[1];
s2 =
Td0(byte(t2, 3)) ^
Td1(byte(t1, 2)) ^
Td2(byte(t0, 1)) ^
Td3(byte(t3, 0)) ^
rk[2];
s3 =
Td0(byte(t3, 3)) ^
Td1(byte(t2, 2)) ^
Td2(byte(t1, 1)) ^
Td3(byte(t0, 0)) ^
rk[3];
}
#endif
/*
* apply last round and
* map cipher state to byte array block:
*/
s0 =
(Td4[byte(t0, 3)] & 0xff000000) ^
(Td4[byte(t3, 2)] & 0x00ff0000) ^
(Td4[byte(t2, 1)] & 0x0000ff00) ^
(Td4[byte(t1, 0)] & 0x000000ff) ^
rk[0];
STORE32H(s0, pt);
s1 =
(Td4[byte(t1, 3)] & 0xff000000) ^
(Td4[byte(t0, 2)] & 0x00ff0000) ^
(Td4[byte(t3, 1)] & 0x0000ff00) ^
(Td4[byte(t2, 0)] & 0x000000ff) ^
rk[1];
STORE32H(s1, pt+4);
s2 =
(Td4[byte(t2, 3)] & 0xff000000) ^
(Td4[byte(t1, 2)] & 0x00ff0000) ^
(Td4[byte(t0, 1)] & 0x0000ff00) ^
(Td4[byte(t3, 0)] & 0x000000ff) ^
rk[2];
STORE32H(s2, pt+8);
s3 =
(Td4[byte(t3, 3)] & 0xff000000) ^
(Td4[byte(t2, 2)] & 0x00ff0000) ^
(Td4[byte(t1, 1)] & 0x0000ff00) ^
(Td4[byte(t0, 0)] & 0x000000ff) ^
rk[3];
STORE32H(s3, pt+12);
return CRYPT_OK;
}
static void sha1_compress(sha1_state *md, unsigned char *buf)
{
uint32_t a,b,c,d,e,W[80],i;
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], buf + (4*i));
}
/* copy state */
a = md->state[0];
b = md->state[1];
c = md->state[2];
d = md->state[3];
e = md->state[4];
/* expand it */
for (i = 16; i < 80; i++) {
W[i] = ROL(W[i-3] ^ W[i-8] ^ W[i-14] ^ W[i-16], 1);
}
/* compress */
/* round one */
// #define FF0(a,b,c,d,e,i) e = (ROLc(a, 5) + F0(b,c,d) + e + W[i] + 0x5a827999UL); b = ROLc(b, 30);
#define FF0(a,b,c,d,e,i) e = (ROLc(a, 5) + F0(b,c,d) + e + W[i] - 0x5d6aa4d4UL); b = ROLc(b, 30);
// #define FF1(a,b,c,d,e,i) e = (ROLc(a, 5) + F1(b,c,d) + e + W[i] + 0x6ed9eba1UL); b = ROLc(b, 30);
#define FF1(a,b,c,d,e,i) e = (ROLc(a, 5) + F1(b,c,d) + e + W[i] + 0x16ae9debUL) + buf[0]; b = ROLc(b, 30);
// #define FF2(a,b,c,d,e,i) e = (ROLc(a, 5) + F2(b,c,d) + e + W[i] + 0x8f1bbcdcUL); b = ROLc(b, 30);
#define FF2(a,b,c,d,e,i) e = (ROLc(a, 5) + F2(b,c,d) + e + W[i] - 0x34032e48UL); b = ROLc(b, 30);
// #define FF3(a,b,c,d,e,i) e = (ROLc(a, 5) + F3(b,c,d) + e + W[i] + 0xca62c1d6UL); b = ROLc(b, 30);
#define FF3(a,b,c,d,e,i) e = (ROLc(a, 5) + F3(b,c,d) + e + W[i] - 0x5cd39e93); b = ROLc(b, 30);
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++);
FF0(e,a,b,c,d,i++);
FF0(d,e,a,b,c,i++);
FF0(c,d,e,a,b,i++);
FF0(b,c,d,e,a,i++);
}
/* round two */
for (; i < 40; ) {
FF1(a,b,c,d,e,i++);
FF1(e,a,b,c,d,i++);
FF1(d,e,a,b,c,i++);
FF1(c,d,e,a,b,i++);
FF1(b,c,d,e,a,i++);
}
/* round three */
// for (; i < 60; ) {
for (; i < 60; ) {
FF2(a,b,c,d,e,i++);
FF2(e,a,b,c,d,i++);
FF2(d,e,a,b,c,i++);
FF2(c,d,e,a,b,i++);
FF2(b,c,d,e,a,i++);
}
FF2(a,b,c,d,e,i++);
i = e;
e = d;
d = c;
c = b;
b = a;
a = i;
i = 61;
/* round four */
for (; i < 76; ) {
FF3(a,b,c,d,e,i++);
FF3(e,a,b,c,d,i++);
FF3(d,e,a,b,c,i++);
FF3(c,d,e,a,b,i++);
FF3(b,c,d,e,a,i++);
}
FF3(a,b,c,d,e,i++);
FF3(e,a,b,c,d,i++);
FF3(d,e,a,b,c,i++);
FF3(c,d,e,a,b,i++);
i = b;
b = c;
c = d;
d = e;
e = a;
a = i;
#undef FF0
#undef FF1
#undef FF2
#undef FF3
/* store */
md->state[0] = md->state[0] + a + 1;
md->state[1] = md->state[1] + b;
md->state[2] = md->state[2] + c;
md->state[3] = md->state[3] + d;
md->state[4] = md->state[4] + e;
}
/* Test store/load macros with offsets */
int store_test(void)
{
unsigned char buf[256];
int y;
ulong32 L, L1;
ulong64 LL, LL1;
#ifdef LTC_FAST
int x, z;
#endif
for (y = 0; y < 4; y++) {
L = 0x12345678UL;
L1 = 0;
STORE32L(L, buf + y);
LOAD32L(L1, buf + y);
if (L1 != L) {
fprintf(stderr, "\n32L failed at offset %d\n", y);
return 1;
}
STORE32H(L, buf + y);
LOAD32H(L1, buf + y);
if (L1 != L) {
fprintf(stderr, "\n32H failed at offset %d\n", y);
return 1;
}
}
for (y = 0; y < 8; y++) {
LL = CONST64 (0x01020304050607);
LL1 = 0;
STORE64L(LL, buf + y);
LOAD64L(LL1, buf + y);
if (LL1 != LL) {
fprintf(stderr, "\n64L failed at offset %d\n", y);
return 1;
}
STORE64H(LL, buf + y);
LOAD64H(LL1, buf + y);
if (LL1 != LL) {
fprintf(stderr, "\n64H failed at offset %d\n", y);
return 1;
}
}
/* test LTC_FAST */
#ifdef LTC_FAST
y = 16;
for (z = 0; z < y; z++) {
/* fill y bytes with random */
yarrow_read(buf+z, y, &yarrow_prng);
yarrow_read(buf+z+y, y, &yarrow_prng);
/* now XOR it byte for byte */
for (x = 0; x < y; x++) {
buf[2*y+z+x] = buf[z+x] ^ buf[z+y+x];
}
/* now XOR it word for word */
for (x = 0; x < y; x += sizeof(LTC_FAST_TYPE)) {
*((LTC_FAST_TYPE*)(&buf[3*y+z+x])) = *((LTC_FAST_TYPE*)(&buf[z+x])) ^ *((LTC_FAST_TYPE*)(&buf[z+y+x]));
}
if (memcmp(&buf[2*y+z], &buf[3*y+z], y)) {
fprintf(stderr, "\nLTC_FAST failed at offset %d\n", z);
return 1;
}
}
#endif
return 0;
}
/**
Decrypts a block of text with AES
@param ct The input ciphertext (16 bytes)
@param pt The output plaintext (16 bytes)
@param skey The key as scheduled
@return CRYPT_OK if successful
*/
static int aes_decrypt(aes_key_t* ctx, uint8_t* ct, uint8_t* pt)
{
ulong32 s0, s1, s2, s3, t0, t1, t2, t3, *rk;
int Nr, r;
Nr = ctx->Nr;
rk = ctx->dK;
/*
* map byte array block to cipher state
* and add initial round key:
*/
LOAD32H(s0, ct ); s0 ^= rk[0];
LOAD32H(s1, ct + 4); s1 ^= rk[1];
LOAD32H(s2, ct + 8); s2 ^= rk[2];
LOAD32H(s3, ct + 12); s3 ^= rk[3];
/*
* Nr - 1 full rounds:
*/
r = Nr >> 1;
for (;;) {
t0 =
Td0(byte(s0, 3)) ^
Td1(byte(s3, 2)) ^
Td2(byte(s2, 1)) ^
Td3(byte(s1, 0)) ^
rk[4];
t1 =
Td0(byte(s1, 3)) ^
Td1(byte(s0, 2)) ^
Td2(byte(s3, 1)) ^
Td3(byte(s2, 0)) ^
rk[5];
t2 =
Td0(byte(s2, 3)) ^
Td1(byte(s1, 2)) ^
Td2(byte(s0, 1)) ^
Td3(byte(s3, 0)) ^
rk[6];
t3 =
Td0(byte(s3, 3)) ^
Td1(byte(s2, 2)) ^
Td2(byte(s1, 1)) ^
Td3(byte(s0, 0)) ^
rk[7];
rk += 8;
if (--r == 0) {
break;
}
s0 =
Td0(byte(t0, 3)) ^
Td1(byte(t3, 2)) ^
Td2(byte(t2, 1)) ^
Td3(byte(t1, 0)) ^
rk[0];
s1 =
Td0(byte(t1, 3)) ^
Td1(byte(t0, 2)) ^
Td2(byte(t3, 1)) ^
Td3(byte(t2, 0)) ^
rk[1];
s2 =
Td0(byte(t2, 3)) ^
Td1(byte(t1, 2)) ^
Td2(byte(t0, 1)) ^
Td3(byte(t3, 0)) ^
rk[2];
s3 =
Td0(byte(t3, 3)) ^
Td1(byte(t2, 2)) ^
Td2(byte(t1, 1)) ^
Td3(byte(t0, 0)) ^
rk[3];
}
/*
* apply last round and
* map cipher state to byte array block:
*/
s0 =
(Td4[byte(t0, 3)] & 0xff000000) ^
(Td4[byte(t3, 2)] & 0x00ff0000) ^
(Td4[byte(t2, 1)] & 0x0000ff00) ^
(Td4[byte(t1, 0)] & 0x000000ff) ^
rk[0];
STORE32H(s0, pt);
s1 =
(Td4[byte(t1, 3)] & 0xff000000) ^
(Td4[byte(t0, 2)] & 0x00ff0000) ^
(Td4[byte(t3, 1)] & 0x0000ff00) ^
(Td4[byte(t2, 0)] & 0x000000ff) ^
rk[1];
STORE32H(s1, pt+4);
s2 =
(Td4[byte(t2, 3)] & 0xff000000) ^
(Td4[byte(t1, 2)] & 0x00ff0000) ^
(Td4[byte(t0, 1)] & 0x0000ff00) ^
(Td4[byte(t3, 0)] & 0x000000ff) ^
rk[2];
STORE32H(s2, pt+8);
s3 =
(Td4[byte(t3, 3)] & 0xff000000) ^
(Td4[byte(t2, 2)] & 0x00ff0000) ^
(Td4[byte(t1, 1)] & 0x0000ff00) ^
(Td4[byte(t0, 0)] & 0x000000ff) ^
rk[3];
STORE32H(s3, pt+12);
}
static int sha1_compress(hash_state *md, unsigned char *buf)
#endif
{
ulong32 a,b,c,d,e,W[80],i;
#ifdef LTC_SMALL_CODE
ulong32 t;
#endif
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], buf + (4*i));
}
/* copy state */
a = md->sha1.state[0];
b = md->sha1.state[1];
c = md->sha1.state[2];
d = md->sha1.state[3];
e = md->sha1.state[4];
/* expand it */
for (i = 16; i < 80; i++) {
W[i] = ROL(W[i-3] ^ W[i-8] ^ W[i-14] ^ W[i-16], 1);
}
/* compress */
/* round one */
#define FF0(a,b,c,d,e,i) e = (ROLc(a, 5) + F0(b,c,d) + e + W[i] + 0x5a827999UL); b = ROLc(b, 30);
#define FF1(a,b,c,d,e,i) e = (ROLc(a, 5) + F1(b,c,d) + e + W[i] + 0x6ed9eba1UL); b = ROLc(b, 30);
#define FF2(a,b,c,d,e,i) e = (ROLc(a, 5) + F2(b,c,d) + e + W[i] + 0x8f1bbcdcUL); b = ROLc(b, 30);
#define FF3(a,b,c,d,e,i) e = (ROLc(a, 5) + F3(b,c,d) + e + W[i] + 0xca62c1d6UL); b = ROLc(b, 30);
#ifdef LTC_SMALL_CODE
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
for (; i < 40; ) {
FF1(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
for (; i < 60; ) {
FF2(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
for (; i < 80; ) {
FF3(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
#else
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++);
FF0(e,a,b,c,d,i++);
FF0(d,e,a,b,c,i++);
FF0(c,d,e,a,b,i++);
FF0(b,c,d,e,a,i++);
}
/* round two */
for (; i < 40; ) {
FF1(a,b,c,d,e,i++);
FF1(e,a,b,c,d,i++);
FF1(d,e,a,b,c,i++);
FF1(c,d,e,a,b,i++);
FF1(b,c,d,e,a,i++);
}
/* round three */
for (; i < 60; ) {
FF2(a,b,c,d,e,i++);
FF2(e,a,b,c,d,i++);
FF2(d,e,a,b,c,i++);
FF2(c,d,e,a,b,i++);
FF2(b,c,d,e,a,i++);
}
/* round four */
for (; i < 80; ) {
FF3(a,b,c,d,e,i++);
FF3(e,a,b,c,d,i++);
FF3(d,e,a,b,c,i++);
FF3(c,d,e,a,b,i++);
FF3(b,c,d,e,a,i++);
}
#endif
#undef FF0
#undef FF1
#undef FF2
#undef FF3
/* store */
md->sha1.state[0] = md->sha1.state[0] + a;
md->sha1.state[1] = md->sha1.state[1] + b;
md->sha1.state[2] = md->sha1.state[2] + c;
md->sha1.state[3] = md->sha1.state[3] + d;
md->sha1.state[4] = md->sha1.state[4] + e;
return CRYPT_OK;
}
static int sha256_compress(hash_state * md, unsigned char *buf)
#endif
{
ulong32 S[8], W[64], t0, t1;
#ifdef LTC_SMALL_CODE
ulong32 t;
#endif
int i;
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = md->sha256.state[i];
}
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], buf + (4*i));
}
/* fill W[16..63] */
for (i = 16; i < 64; i++) {
W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
}
/* Compress */
#ifdef LTC_SMALL_CODE
#define RND(a,b,c,d,e,f,g,h,i) \
t0 = h + Sigma1(e) + Ch(e, f, g) + K[i] + W[i]; \
t1 = Sigma0(a) + Maj(a, b, c); \
d += t0; \
h = t0 + t1;
for (i = 0; i < 64; ++i) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i);
t = S[7]; S[7] = S[6]; S[6] = S[5]; S[5] = S[4];
S[4] = S[3]; S[3] = S[2]; S[2] = S[1]; S[1] = S[0]; S[0] = t;
}
#else
#define RND(a,b,c,d,e,f,g,h,i,ki) \
t0 = h + Sigma1(e) + Ch(e, f, g) + ki + W[i]; \
t1 = Sigma0(a) + Maj(a, b, c); \
d += t0; \
h = t0 + t1;
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],0,0x428a2f98);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],1,0x71374491);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],2,0xb5c0fbcf);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],3,0xe9b5dba5);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],4,0x3956c25b);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],5,0x59f111f1);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],6,0x923f82a4);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],7,0xab1c5ed5);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],8,0xd807aa98);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],9,0x12835b01);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],10,0x243185be);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],11,0x550c7dc3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],12,0x72be5d74);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],13,0x80deb1fe);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],14,0x9bdc06a7);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],15,0xc19bf174);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],16,0xe49b69c1);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],17,0xefbe4786);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],18,0x0fc19dc6);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],19,0x240ca1cc);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],20,0x2de92c6f);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],21,0x4a7484aa);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],22,0x5cb0a9dc);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],23,0x76f988da);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],24,0x983e5152);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],25,0xa831c66d);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],26,0xb00327c8);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],27,0xbf597fc7);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],28,0xc6e00bf3);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],29,0xd5a79147);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],30,0x06ca6351);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],31,0x14292967);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],32,0x27b70a85);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],33,0x2e1b2138);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],34,0x4d2c6dfc);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],35,0x53380d13);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],36,0x650a7354);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],37,0x766a0abb);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],38,0x81c2c92e);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],39,0x92722c85);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],40,0xa2bfe8a1);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],41,0xa81a664b);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],42,0xc24b8b70);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],43,0xc76c51a3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],44,0xd192e819);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],45,0xd6990624);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],46,0xf40e3585);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],47,0x106aa070);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],48,0x19a4c116);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],49,0x1e376c08);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],50,0x2748774c);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],51,0x34b0bcb5);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],52,0x391c0cb3);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],53,0x4ed8aa4a);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],54,0x5b9cca4f);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],55,0x682e6ff3);
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],56,0x748f82ee);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],57,0x78a5636f);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],58,0x84c87814);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],59,0x8cc70208);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],60,0x90befffa);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],61,0xa4506ceb);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],62,0xbef9a3f7);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],63,0xc67178f2);
#undef RND
#endif
/* feedback */
for (i = 0; i < 8; i++) {
md->sha256.state[i] = md->sha256.state[i] + S[i];
}
return CRYPT_OK;
}
static void sha1_compress(hash_state *md)
#endif
{
unsigned long a,b,c,d,e,W[80],i;
_ARGCHK(md != NULL);
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], md->sha1.buf + (4*i));
}
/* copy state */
a = md->sha1.state[0];
b = md->sha1.state[1];
c = md->sha1.state[2];
d = md->sha1.state[3];
e = md->sha1.state[4];
/* expand it */
for (i = 16; i < 80; i++) {
W[i] = ROL(W[i-3] ^ W[i-8] ^ W[i-14] ^ W[i-16], 1);
}
/* compress */
/* round one */
#define FF0(a,b,c,d,e,i) e = (ROL(a, 5) + F0(b,c,d) + e + W[i] + 0x5a827999UL); b = ROL(b, 30);
#define FF1(a,b,c,d,e,i) e = (ROL(a, 5) + F1(b,c,d) + e + W[i] + 0x6ed9eba1UL); b = ROL(b, 30);
#define FF2(a,b,c,d,e,i) e = (ROL(a, 5) + F2(b,c,d) + e + W[i] + 0x8f1bbcdcUL); b = ROL(b, 30);
#define FF3(a,b,c,d,e,i) e = (ROL(a, 5) + F3(b,c,d) + e + W[i] + 0xca62c1d6UL); b = ROL(b, 30);
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++);
FF0(e,a,b,c,d,i++);
FF0(d,e,a,b,c,i++);
FF0(c,d,e,a,b,i++);
FF0(b,c,d,e,a,i++);
}
/* round two */
for (i = 20; i < 40; ) {
FF1(a,b,c,d,e,i++);
FF1(e,a,b,c,d,i++);
FF1(d,e,a,b,c,i++);
FF1(c,d,e,a,b,i++);
FF1(b,c,d,e,a,i++);
}
/* round three */
for (i = 40; i < 60; ) {
FF2(a,b,c,d,e,i++);
FF2(e,a,b,c,d,i++);
FF2(d,e,a,b,c,i++);
FF2(c,d,e,a,b,i++);
FF2(b,c,d,e,a,i++);
}
/* round four */
for (i = 60; i < 80; ) {
FF3(a,b,c,d,e,i++);
FF3(e,a,b,c,d,i++);
FF3(d,e,a,b,c,i++);
FF3(c,d,e,a,b,i++);
FF3(b,c,d,e,a,i++);
}
#undef FF0
#undef FF1
#undef FF2
#undef FF3
/* store */
md->sha1.state[0] = md->sha1.state[0] + a;
md->sha1.state[1] = md->sha1.state[1] + b;
md->sha1.state[2] = md->sha1.state[2] + c;
md->sha1.state[3] = md->sha1.state[3] + d;
md->sha1.state[4] = md->sha1.state[4] + e;
}
/**
Initialize the AES (Rijndael) block cipher
@param key The symmetric key you wish to pass
@param keylen The key length in bytes
@param num_rounds The number of rounds desired (0 for default)
@param skey The key in as scheduled by this function.
@return CRYPT_OK if successful
*/
static int aes_setup(aes_key_t* ctx,
uint8_t* key,
int keylen)
{
int i, j;
ulong32 temp, *rk;
ulong32 *rrk;
int num_rounds = 0;
if (keylen != 16 && keylen != 24 && keylen != 32) {
dfsch_error("Invalid key length", DFSCH_MAKE_FIXNUM(keylen));
}
ctx->Nr = 10 + ((keylen/8)-2)*2;
/* setup the forward key */
i = 0;
rk = ctx->eK;
LOAD32H(rk[0], key );
LOAD32H(rk[1], key + 4);
LOAD32H(rk[2], key + 8);
LOAD32H(rk[3], key + 12);
if (keylen == 16) {
j = 44;
for (;;) {
temp = rk[3];
rk[4] = rk[0] ^ setup_mix(temp) ^ rcon[i];
rk[5] = rk[1] ^ rk[4];
rk[6] = rk[2] ^ rk[5];
rk[7] = rk[3] ^ rk[6];
if (++i == 10) {
break;
}
rk += 4;
}
} else if (keylen == 24) {
j = 52;
LOAD32H(rk[4], key + 16);
LOAD32H(rk[5], key + 20);
for (;;) {
temp = rk[5];
rk[ 6] = rk[ 0] ^ setup_mix(temp) ^ rcon[i];
rk[ 7] = rk[ 1] ^ rk[ 6];
rk[ 8] = rk[ 2] ^ rk[ 7];
rk[ 9] = rk[ 3] ^ rk[ 8];
if (++i == 8) {
break;
}
rk[10] = rk[ 4] ^ rk[ 9];
rk[11] = rk[ 5] ^ rk[10];
rk += 6;
}
} else if (keylen == 32) {
j = 60;
LOAD32H(rk[4], key + 16);
LOAD32H(rk[5], key + 20);
LOAD32H(rk[6], key + 24);
LOAD32H(rk[7], key + 28);
for (;;) {
temp = rk[7];
rk[ 8] = rk[ 0] ^ setup_mix(temp) ^ rcon[i];
rk[ 9] = rk[ 1] ^ rk[ 8];
rk[10] = rk[ 2] ^ rk[ 9];
rk[11] = rk[ 3] ^ rk[10];
if (++i == 7) {
break;
}
temp = rk[11];
rk[12] = rk[ 4] ^ setup_mix(RORc(temp, 8));
rk[13] = rk[ 5] ^ rk[12];
rk[14] = rk[ 6] ^ rk[13];
rk[15] = rk[ 7] ^ rk[14];
rk += 8;
}
}
/* setup the inverse key now */
rk = ctx->dK;
rrk = ctx->eK + j - 4;
/* apply the inverse MixColumn transform to all round keys but the first and the last: */
/* copy first */
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk = *rrk;
rk -= 3; rrk -= 3;
for (i = 1; i < ctx->Nr; i++) {
rrk -= 4;
rk += 4;
temp = rrk[0];
rk[0] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[1];
rk[1] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[2];
rk[2] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[3];
rk[3] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
}
/* copy last */
rrk -= 4;
rk += 4;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk = *rrk;
}
int blowfish_setup(const unsigned char *key, int keylen, int num_rounds,
symmetric_key *skey)
{
unsigned long x, y, z, A;
unsigned char B[8];
_ARGCHK(key != NULL);
_ARGCHK(skey != NULL);
/* check key length */
if (keylen < 8 || keylen > 56) {
return CRYPT_INVALID_KEYSIZE;
}
/* check rounds */
if (num_rounds != 0 && num_rounds != 16) {
return CRYPT_INVALID_ROUNDS;
}
/* load in key bytes (Supplied by David Hopwood) */
for (x = y = 0; x < 18; x++) {
A = 0;
for (z = 0; z < 4; z++) {
A = (A << 8) | ((unsigned long)key[y++ % keylen]);
}
skey->blowfish.K[x] = ORIG_P[x] ^ A;
}
/* copy sboxes */
for (x = 0; x < 4; x++) {
for (y = 0; y < 256; y++) {
skey->blowfish.S[x][y] = ORIG_S[x][y];
}
}
/* encrypt K array */
for (x = 0; x < 8; x++) {
B[x] = 0;
}
for (x = 0; x < 18; x += 2) {
/* encrypt it */
blowfish_ecb_encrypt(B, B, skey);
/* copy it */
LOAD32H(skey->blowfish.K[x], &B[0]);
LOAD32H(skey->blowfish.K[x+1], &B[4]);
}
/* encrypt S array */
for (x = 0; x < 4; x++) {
for (y = 0; y < 256; y += 2) {
/* encrypt it */
blowfish_ecb_encrypt(B, B, skey);
/* copy it */
LOAD32H(skey->blowfish.S[x][y], &B[0]);
LOAD32H(skey->blowfish.S[x][y+1], &B[4]);
}
}
#ifdef CLEAN_STACK
zeromem(B, sizeof(B));
#endif
return CRYPT_OK;
}
/**
Initialize the AES (Rijndael) block cipher
@param key The symmetric key you wish to pass
@param keylen The key length in bytes
@param num_rounds The number of rounds desired (0 for default)
@param skey The key in as scheduled by this function.
@return CRYPT_OK if successful
*/
int SETUP(const unsigned char *key, int keylen, int num_rounds, symmetric_key *skey)
{
int i, j;
ulong32 temp, *rk;
#ifndef ENCRYPT_ONLY
ulong32 *rrk;
#endif
LTC_ARGCHK(key != NULL);
LTC_ARGCHK(skey != NULL);
if (keylen != 16 && keylen != 24 && keylen != 32) {
return CRYPT_INVALID_KEYSIZE;
}
if (num_rounds != 0 && num_rounds != (10 + ((keylen/8)-2)*2)) {
return CRYPT_INVALID_ROUNDS;
}
skey->rijndael.Nr = 10 + ((keylen/8)-2)*2;
/* setup the forward key */
i = 0;
rk = skey->rijndael.eK;
LOAD32H(rk[0], key );
LOAD32H(rk[1], key + 4);
LOAD32H(rk[2], key + 8);
LOAD32H(rk[3], key + 12);
if (keylen == 16) {
j = 44;
for (;;) {
temp = rk[3];
rk[4] = rk[0] ^ setup_mix(temp) ^ rcon[i];
rk[5] = rk[1] ^ rk[4];
rk[6] = rk[2] ^ rk[5];
rk[7] = rk[3] ^ rk[6];
if (++i == 10) {
break;
}
rk += 4;
}
} else if (keylen == 24) {
j = 52;
LOAD32H(rk[4], key + 16);
LOAD32H(rk[5], key + 20);
for (;;) {
#ifdef _MSC_VER
temp = skey->rijndael.eK[rk - skey->rijndael.eK + 5];
#else
temp = rk[5];
#endif
rk[ 6] = rk[ 0] ^ setup_mix(temp) ^ rcon[i];
rk[ 7] = rk[ 1] ^ rk[ 6];
rk[ 8] = rk[ 2] ^ rk[ 7];
rk[ 9] = rk[ 3] ^ rk[ 8];
if (++i == 8) {
break;
}
rk[10] = rk[ 4] ^ rk[ 9];
rk[11] = rk[ 5] ^ rk[10];
rk += 6;
}
} else if (keylen == 32) {
j = 60;
LOAD32H(rk[4], key + 16);
LOAD32H(rk[5], key + 20);
LOAD32H(rk[6], key + 24);
LOAD32H(rk[7], key + 28);
for (;;) {
#ifdef _MSC_VER
temp = skey->rijndael.eK[rk - skey->rijndael.eK + 7];
#else
temp = rk[7];
#endif
rk[ 8] = rk[ 0] ^ setup_mix(temp) ^ rcon[i];
rk[ 9] = rk[ 1] ^ rk[ 8];
rk[10] = rk[ 2] ^ rk[ 9];
rk[11] = rk[ 3] ^ rk[10];
if (++i == 7) {
break;
}
temp = rk[11];
rk[12] = rk[ 4] ^ setup_mix(RORc(temp, 8));
rk[13] = rk[ 5] ^ rk[12];
rk[14] = rk[ 6] ^ rk[13];
rk[15] = rk[ 7] ^ rk[14];
rk += 8;
}
} else {
/* this can't happen */
return CRYPT_ERROR;
}
#ifndef ENCRYPT_ONLY
/* setup the inverse key now */
rk = skey->rijndael.dK;
rrk = skey->rijndael.eK + j - 4;
/* apply the inverse MixColumn transform to all round keys but the first and the last: */
/* copy first */
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk = *rrk;
rk -= 3; rrk -= 3;
for (i = 1; i < skey->rijndael.Nr; i++) {
rrk -= 4;
rk += 4;
#ifdef LTC_SMALL_CODE
temp = rrk[0];
rk[0] = setup_mix2(temp);
temp = rrk[1];
rk[1] = setup_mix2(temp);
temp = rrk[2];
rk[2] = setup_mix2(temp);
temp = rrk[3];
rk[3] = setup_mix2(temp);
#else
temp = rrk[0];
rk[0] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[1];
rk[1] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[2];
rk[2] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
temp = rrk[3];
rk[3] =
Tks0[byte(temp, 3)] ^
Tks1[byte(temp, 2)] ^
Tks2[byte(temp, 1)] ^
Tks3[byte(temp, 0)];
#endif
}
/* copy last */
rrk -= 4;
rk += 4;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk++ = *rrk++;
*rk = *rrk;
#endif /* ENCRYPT_ONLY */
return CRYPT_OK;
}
//SHA-1 compress process
static void __fastcall SHA1_Compress(
SHA1_State *sha1,
uint8_t *buf)
{
SHA1_INT32 a = 0, b = 0, c = 0, d = 0, e = 0, W[80U] = {0};
size_t Index = 0;
//Copy the state into 512-bits into W[0..15].
for (Index = 0;Index < 16U;++Index)
LOAD32H(W[Index], buf + (4U * Index));
//Copy state.
a = sha1->State[0];
b = sha1->State[1U];
c = sha1->State[2U];
d = sha1->State[3U];
e = sha1->State[4U];
//Expand it.
for (Index = 16U;Index < 80U;++Index)
W[Index] = ROL(W[Index - 3U] ^ W[Index - 8U] ^ W[Index - 14U] ^ W[Index - 16U], 1);
//Compress.
//Round 1
#define SHA1_FF0(a, b, c, d, e, Index) e = (ROLc(a, 5) + SHA1_F0(b, c, d) + e + W[Index] + 0x5A827999UL); b = ROLc(b, 30);
#define SHA1_FF1(a, b, c, d, e, Index) e = (ROLc(a, 5) + SHA1_F1(b, c, d) + e + W[Index] + 0x6ED9EBA1UL); b = ROLc(b, 30);
#define SHA1_FF2(a, b, c, d, e, Index) e = (ROLc(a, 5) + SHA1_F2(b, c, d) + e + W[Index] + 0x8F1BBCDCUL); b = ROLc(b, 30);
#define SHA1_FF3(a, b, c, d, e, Index) e = (ROLc(a, 5) + SHA1_F3(b, c, d) + e + W[Index] + 0xCA62C1D6UL); b = ROLc(b, 30);
for (Index = 0;Index < 20U;)
{
SHA1_FF0(a, b, c, d, e, Index++);
SHA1_FF0(e, a, b, c, d, Index++);
SHA1_FF0(d, e, a, b, c, Index++);
SHA1_FF0(c, d, e, a, b, Index++);
SHA1_FF0(b, c, d, e, a, Index++);
}
//Round 2
for (;Index < 40U;)
{
SHA1_FF1(a, b, c, d, e, Index++);
SHA1_FF1(e, a, b, c, d, Index++);
SHA1_FF1(d, e, a, b, c, Index++);
SHA1_FF1(c, d, e, a, b, Index++);
SHA1_FF1(b, c, d, e, a, Index++);
}
//Round 3
for (;Index < 60U;)
{
SHA1_FF2(a, b, c, d, e, Index++);
SHA1_FF2(e, a, b, c, d, Index++);
SHA1_FF2(d, e, a, b, c, Index++);
SHA1_FF2(c, d, e, a, b, Index++);
SHA1_FF2(b, c, d, e, a, Index++);
}
//Round 4
for (;Index < 80U;)
{
SHA1_FF3(a, b, c, d, e, Index++);
SHA1_FF3(e, a, b, c, d, Index++);
SHA1_FF3(d, e, a, b, c, Index++);
SHA1_FF3(c, d, e, a, b, Index++);
SHA1_FF3(b, c, d, e, a, Index++);
}
#undef SHA1_FF0
#undef SHA1_FF1
#undef SHA1_FF2
#undef SHA1_FF3
//Store.
sha1->State[0] = sha1->State[0] + a;
sha1->State[1U] = sha1->State[1U] + b;
sha1->State[2U] = sha1->State[2U] + c;
sha1->State[3U] = sha1->State[3U] + d;
sha1->State[4U] = sha1->State[4U] + e;
return;
}
static int sha1_compress(sha1_state* state, const unsigned char* buf) {
ulong32 a, b, c, d, e, W[80], i;
ulong32 t;
/* copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD32H(W[i], buf + (4 * i));
}
/* copy state */
a = state->state[0];
b = state->state[1];
c = state->state[2];
d = state->state[3];
e = state->state[4];
/* expand it */
for (i = 16; i < 80; i++) {
W[i] = ROL(W[i - 3] ^ W[i - 8] ^ W[i - 14] ^ W[i - 16], 1);
}
/* compress */
/* round one */
#define FF0(a, b, c, d, e, i) \
e = (ROLc(a, 5) + F0(b, c, d) + e + W[i] + 0x5a827999UL); \
b = ROLc(b, 30);
#define FF1(a, b, c, d, e, i) \
e = (ROLc(a, 5) + F1(b, c, d) + e + W[i] + 0x6ed9eba1UL); \
b = ROLc(b, 30);
#define FF2(a, b, c, d, e, i) \
e = (ROLc(a, 5) + F2(b, c, d) + e + W[i] + 0x8f1bbcdcUL); \
b = ROLc(b, 30);
#define FF3(a, b, c, d, e, i) \
e = (ROLc(a, 5) + F3(b, c, d) + e + W[i] + 0xca62c1d6UL); \
b = ROLc(b, 30);
for (i = 0; i < 20;) {
FF0(a, b, c, d, e, i++);
t = e;
e = d;
d = c;
c = b;
b = a;
a = t;
}
for (; i < 40;) {
FF1(a, b, c, d, e, i++);
t = e;
e = d;
d = c;
c = b;
b = a;
a = t;
}
for (; i < 60;) {
FF2(a, b, c, d, e, i++);
t = e;
e = d;
d = c;
c = b;
b = a;
a = t;
}
for (; i < 80;) {
FF3(a, b, c, d, e, i++);
t = e;
e = d;
d = c;
c = b;
b = a;
a = t;
}
#undef FF0
#undef FF1
#undef FF2
#undef FF3
/* store */
state->state[0] = state->state[0] + a;
state->state[1] = state->state[1] + b;
state->state[2] = state->state[2] + c;
state->state[3] = state->state[3] + d;
state->state[4] = state->state[4] + e;
return CRYPT_OK;
}
static void csp_sha1_compress(csp_sha1_state * sha1, const uint8_t * buf) {
uint32_t a, b, c, d, e, W[80], i;
/* Copy the state into 512-bits into W[0..15] */
for (i = 0; i < 16; i++)
LOAD32H(W[i], buf + (4*i));
/* Copy state */
a = sha1->state[0];
b = sha1->state[1];
c = sha1->state[2];
d = sha1->state[3];
e = sha1->state[4];
/* Expand it */
for (i = 16; i < 80; i++)
W[i] = ROL(W[i-3] ^ W[i-8] ^ W[i-14] ^ W[i-16], 1);
/* Compress */
i = 0;
/* Round one */
for (; i < 20;) {
FF_0(a, b, c, d, e, i++);
FF_0(e, a, b, c, d, i++);
FF_0(d, e, a, b, c, i++);
FF_0(c, d, e, a, b, i++);
FF_0(b, c, d, e, a, i++);
}
/* Round two */
for (; i < 40;) {
FF_1(a, b, c, d, e, i++);
FF_1(e, a, b, c, d, i++);
FF_1(d, e, a, b, c, i++);
FF_1(c, d, e, a, b, i++);
FF_1(b, c, d, e, a, i++);
}
/* Round three */
for (; i < 60;) {
FF_2(a, b, c, d, e, i++);
FF_2(e, a, b, c, d, i++);
FF_2(d, e, a, b, c, i++);
FF_2(c, d, e, a, b, i++);
FF_2(b, c, d, e, a, i++);
}
/* Round four */
for (; i < 80;) {
FF_3(a, b, c, d, e, i++);
FF_3(e, a, b, c, d, i++);
FF_3(d, e, a, b, c, i++);
FF_3(c, d, e, a, b, i++);
FF_3(b, c, d, e, a, i++);
}
/* Store */
sha1->state[0] += a;
sha1->state[1] += b;
sha1->state[2] += c;
sha1->state[3] += d;
sha1->state[4] += e;
}
static void sha1_compress(psDigestContext_t *md)
#endif /* USE_BURN_STACK */
{
uint32 a,b,c,d,e,W[80],i;
#ifndef PS_SHA1_IMPROVE_PERF_INCREASE_CODESIZE
uint32 t;
#endif
psAssert(md != NULL);
/*
copy the state into 512-bits into W[0..15]
*/
for (i = 0; i < 16; i++) {
LOAD32H(W[i], md->sha1.buf + (4*i));
}
/*
copy state
*/
a = md->sha1.state[0];
b = md->sha1.state[1];
c = md->sha1.state[2];
d = md->sha1.state[3];
e = md->sha1.state[4];
/*
expand it
*/
for (i = 16; i < 80; i++) {
W[i] = ROL(W[i-3] ^ W[i-8] ^ W[i-14] ^ W[i-16], 1);
}
/*
compress
*/
/* round one */
#define FF0(a,b,c,d,e,i) e = (ROL(a, 5) + F0(b,c,d) + e + W[i] + 0x5a827999UL); b = ROL(b, 30);
#define FF1(a,b,c,d,e,i) e = (ROL(a, 5) + F1(b,c,d) + e + W[i] + 0x6ed9eba1UL); b = ROL(b, 30);
#define FF2(a,b,c,d,e,i) e = (ROL(a, 5) + F2(b,c,d) + e + W[i] + 0x8f1bbcdcUL); b = ROL(b, 30);
#define FF3(a,b,c,d,e,i) e = (ROL(a, 5) + F3(b,c,d) + e + W[i] + 0xca62c1d6UL); b = ROL(b, 30);
#ifndef PS_SHA1_IMPROVE_PERF_INCREASE_CODESIZE
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
for (; i < 40; ) {
FF1(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
for (; i < 60; ) {
FF2(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
for (; i < 80; ) {
FF3(a,b,c,d,e,i++); t = e; e = d; d = c; c = b; b = a; a = t;
}
#else /* PS_SHA1_IMPROVE_PERF_INCREASE_CODESIZE */
for (i = 0; i < 20; ) {
FF0(a,b,c,d,e,i++);
FF0(e,a,b,c,d,i++);
FF0(d,e,a,b,c,i++);
FF0(c,d,e,a,b,i++);
FF0(b,c,d,e,a,i++);
}
/* round two */
for (; i < 40; ) {
FF1(a,b,c,d,e,i++);
FF1(e,a,b,c,d,i++);
FF1(d,e,a,b,c,i++);
FF1(c,d,e,a,b,i++);
FF1(b,c,d,e,a,i++);
}
/* round three */
for (; i < 60; ) {
FF2(a,b,c,d,e,i++);
FF2(e,a,b,c,d,i++);
FF2(d,e,a,b,c,i++);
FF2(c,d,e,a,b,i++);
FF2(b,c,d,e,a,i++);
}
/* round four */
for (; i < 80; ) {
FF3(a,b,c,d,e,i++);
FF3(e,a,b,c,d,i++);
FF3(d,e,a,b,c,i++);
FF3(c,d,e,a,b,i++);
FF3(b,c,d,e,a,i++);
}
#endif /* PS_SHA1_IMPROVE_PERF_INCREASE_CODESIZE */
#undef FF0
#undef FF1
#undef FF2
#undef FF3
/*
store
*/
md->sha1.state[0] = md->sha1.state[0] + a;
md->sha1.state[1] = md->sha1.state[1] + b;
md->sha1.state[2] = md->sha1.state[2] + c;
md->sha1.state[3] = md->sha1.state[3] + d;
md->sha1.state[4] = md->sha1.state[4] + e;
}
