/*****************************************
* sha256 compression function *
* *
* H points to chaining input *
* in points to the message input *
* *
*****************************************/
void sha256_comp (hashblock res, const hashblock hash, const void *in)
{
uint32_t a,b,c,d,e,f,g,h,s0,s1,T1,T2;
uint32_t H[8];
uint32_t X[16],l;
int i;
// CHANGE type casting added due to c++
const unsigned char *data=static_cast<const unsigned char*>(in);
for (i = 0; i < SHA256_DIGEST_LENGTH/4; i++) {
HOST_c2l(hash, H[i]);
}
a = H[0]; b = H[1]; c = H[2]; d = H[3];
e = H[4]; f = H[5]; g = H[6]; h = H[7];
for (i=0;i<16;i++)
{
HOST_c2l(data,l); T1 = X[i] = l;
T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
T2 = Sigma0(a) + Maj(a,b,c);
h = g;
g = f;
f = e;
e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
for (;i<64;i++)
{
s0 = X[(i+1)&0x0f]; s0 = sigma0(s0);
s1 = X[(i+14)&0x0f]; s1 = sigma1(s1);
T1 = X[i&0xf] += s0 + s1 + X[(i+9)&0xf];
T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
T2 = Sigma0(a) + Maj(a,b,c);
h = g; g = f; f = e; e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
H[0] += a; H[1] += b; H[2] += c; H[3] += d;
H[4] += e; H[5] += f; H[6] += g; H[7] += h;
for (i = 0; i < SHA256_DIGEST_LENGTH/4; i++) {
HOST_l2c(H[i], res);
}
}
static void sha256_block (SHA256_CTX *ctx, const void *in, size_t num, int host)
{
unsigned MD32_REG_T a,b,c,d,e,f,g,h,s0,s1,T1,T2;
SHA_LONG X[16];
int i;
const unsigned char *data=in;
while (num--) {
a = ctx->h[0]; b = ctx->h[1]; c = ctx->h[2]; d = ctx->h[3];
e = ctx->h[4]; f = ctx->h[5]; g = ctx->h[6]; h = ctx->h[7];
if (host)
{
const SHA_LONG *W=(const SHA_LONG *)data;
for (i=0;i<16;i++)
{
T1 = X[i] = W[i];
T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
T2 = Sigma0(a) + Maj(a,b,c);
h = g; g = f; f = e; e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
data += SHA256_CBLOCK;
}
else
{
SHA_LONG l;
for (i=0;i<16;i++)
{
HOST_c2l(data,l); T1 = X[i] = l;
T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
T2 = Sigma0(a) + Maj(a,b,c);
h = g; g = f; f = e; e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
}
for (;i<64;i++)
{
s0 = X[(i+1)&0x0f]; s0 = sigma0(s0);
s1 = X[(i+14)&0x0f]; s1 = sigma1(s1);
T1 = X[i&0xf] += s0 + s1 + X[(i+9)&0xf];
T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
T2 = Sigma0(a) + Maj(a,b,c);
h = g; g = f; f = e; e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
ctx->h[0] += a; ctx->h[1] += b; ctx->h[2] += c; ctx->h[3] += d;
ctx->h[4] += e; ctx->h[5] += f; ctx->h[6] += g; ctx->h[7] += h;
}
}
void SHA1Provider::hash_block_data_order (const unsigned char* data, int num)
{
CRYPTO_U32 A, B, C, D, E, T, l;
int i;
CRYPTO_U32 X[16];
A = m_sha_ctx.h[0];
B = m_sha_ctx.h[1];
C = m_sha_ctx.h[2];
D = m_sha_ctx.h[3];
E = m_sha_ctx.h[4];
while (true)
{
for (i = 0; i < 16; i++)
{
HOST_c2l(data,l);
X[i]=l;
BODY_00_15(X[i]);
}
for (i = 0; i < 4; i++)
{
BODY_16_19(X[i], X[i+2], X[i+8], X[(i+13)&15]);
}
for (; i < 24; i++)
{
BODY_20_39(X[i&15], X[(i+2)&15], X[(i+8)&15], X[(i+13)&15]);
}
for (i = 0; i < 20; i++)
{
BODY_40_59(X[(i+8)&15], X[(i+10)&15], X[i&15], X[(i+5)&15]);
}
for (i = 4; i < 24; i++)
{
BODY_60_79(X[(i+8)&15], X[(i+10)&15], X[i&15], X[(i+5)&15]);
}
m_sha_ctx.h[0] = (m_sha_ctx.h[0] + A) & 0xffffffffL;
m_sha_ctx.h[1] = (m_sha_ctx.h[1] + B) & 0xffffffffL;
m_sha_ctx.h[2] = (m_sha_ctx.h[2] + C) & 0xffffffffL;
m_sha_ctx.h[3] = (m_sha_ctx.h[3] + D) & 0xffffffffL;
m_sha_ctx.h[4] = (m_sha_ctx.h[4] + E) & 0xffffffffL;
if (--num == 0) break;
A = m_sha_ctx.h[0];
B = m_sha_ctx.h[1];
C = m_sha_ctx.h[2];
D = m_sha_ctx.h[3];
E = m_sha_ctx.h[4];
}
}
void sha256_block_data_order (SHA256_CTX *ctx, const void *in)
{
unsigned MD32_REG_T a,b,c,d,e,f,g,h,s0,s1,T1,T2,t;
SHA_LONG X[16],l,Ki;
int i;
const unsigned char *data=in;
a = ctx->h[0]; b = ctx->h[1]; c = ctx->h[2]; d = ctx->h[3];
e = ctx->h[4]; f = ctx->h[5]; g = ctx->h[6]; h = ctx->h[7];
for (i=0;i<16;i++)
{
HOST_c2l(data,l); X[i] = l;
Ki=K256[i];
T1 = l + h + Sigma1(e) + Ch(e,f,g) + Ki;
T2 = Sigma0(a) + Maj(a,b,c);
h = g; g = f; f = e; e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
for (;i<64;i++)
{
s0 = X[(i+1)&0x0f]; s0 = sigma0(s0);
s1 = X[(i+14)&0x0f]; s1 = sigma1(s1);
T1 = X[i&0xf];
t = X[(i+9)&0xf];
T1 += s0 + s1 + t;
X[i&0xf] = T1;
Ki=K256[i];
T1 += h + Sigma1(e) + Ch(e,f,g) + Ki;
T2 = Sigma0(a) + Maj(a,b,c);
h = g; g = f; f = e; e = d + T1;
d = c; c = b; b = a; a = T1 + T2;
}
t=ctx->h[0]; ctx->h[0]=t+a;
t=ctx->h[1]; ctx->h[1]=t+b;
t=ctx->h[2]; ctx->h[2]=t+c;
t=ctx->h[3]; ctx->h[3]=t+d;
t=ctx->h[4]; ctx->h[4]=t+e;
t=ctx->h[5]; ctx->h[5]=t+f;
t=ctx->h[6]; ctx->h[6]=t+g;
t=ctx->h[7]; ctx->h[7]=t+h;
return;
}
void md4_block_data_order (MD4_CTX *c, const void *data_, size_t num)
{
const unsigned char *data=data_;
register unsigned MD32_REG_T A,B,C,D,l;
#ifndef MD32_XARRAY
/* See comment in crypto/sha/sha_locl.h for details. */
unsigned MD32_REG_T XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7,
XX8, XX9,XX10,XX11,XX12,XX13,XX14,XX15;
# define X(i) XX##i
#else
MD4_LONG XX[MD4_LBLOCK];
# define X(i) XX[i]
#endif
A=c->A;
B=c->B;
C=c->C;
D=c->D;
for (; num--;)
{
HOST_c2l(data,l);
X( 0)=l;
HOST_c2l(data,l);
X( 1)=l;
/* Round 0 */
R0(A,B,C,D,X( 0), 3,0);
HOST_c2l(data,l);
X( 2)=l;
R0(D,A,B,C,X( 1), 7,0);
HOST_c2l(data,l);
X( 3)=l;
R0(C,D,A,B,X( 2),11,0);
HOST_c2l(data,l);
X( 4)=l;
R0(B,C,D,A,X( 3),19,0);
HOST_c2l(data,l);
X( 5)=l;
R0(A,B,C,D,X( 4), 3,0);
HOST_c2l(data,l);
X( 6)=l;
R0(D,A,B,C,X( 5), 7,0);
HOST_c2l(data,l);
X( 7)=l;
R0(C,D,A,B,X( 6),11,0);
HOST_c2l(data,l);
X( 8)=l;
R0(B,C,D,A,X( 7),19,0);
HOST_c2l(data,l);
X( 9)=l;
R0(A,B,C,D,X( 8), 3,0);
HOST_c2l(data,l);
X(10)=l;
R0(D,A,B,C,X( 9), 7,0);
HOST_c2l(data,l);
X(11)=l;
R0(C,D,A,B,X(10),11,0);
HOST_c2l(data,l);
X(12)=l;
R0(B,C,D,A,X(11),19,0);
HOST_c2l(data,l);
X(13)=l;
R0(A,B,C,D,X(12), 3,0);
HOST_c2l(data,l);
X(14)=l;
R0(D,A,B,C,X(13), 7,0);
HOST_c2l(data,l);
X(15)=l;
R0(C,D,A,B,X(14),11,0);
R0(B,C,D,A,X(15),19,0);
/* Round 1 */
R1(A,B,C,D,X( 0), 3,0x5A827999L);
R1(D,A,B,C,X( 4), 5,0x5A827999L);
R1(C,D,A,B,X( 8), 9,0x5A827999L);
R1(B,C,D,A,X(12),13,0x5A827999L);
R1(A,B,C,D,X( 1), 3,0x5A827999L);
R1(D,A,B,C,X( 5), 5,0x5A827999L);
R1(C,D,A,B,X( 9), 9,0x5A827999L);
R1(B,C,D,A,X(13),13,0x5A827999L);
R1(A,B,C,D,X( 2), 3,0x5A827999L);
R1(D,A,B,C,X( 6), 5,0x5A827999L);
R1(C,D,A,B,X(10), 9,0x5A827999L);
R1(B,C,D,A,X(14),13,0x5A827999L);
R1(A,B,C,D,X( 3), 3,0x5A827999L);
R1(D,A,B,C,X( 7), 5,0x5A827999L);
R1(C,D,A,B,X(11), 9,0x5A827999L);
R1(B,C,D,A,X(15),13,0x5A827999L);
/* Round 2 */
R2(A,B,C,D,X( 0), 3,0x6ED9EBA1L);
R2(D,A,B,C,X( 8), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 4),11,0x6ED9EBA1L);
R2(B,C,D,A,X(12),15,0x6ED9EBA1L);
R2(A,B,C,D,X( 2), 3,0x6ED9EBA1L);
R2(D,A,B,C,X(10), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 6),11,0x6ED9EBA1L);
R2(B,C,D,A,X(14),15,0x6ED9EBA1L);
R2(A,B,C,D,X( 1), 3,0x6ED9EBA1L);
R2(D,A,B,C,X( 9), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 5),11,0x6ED9EBA1L);
R2(B,C,D,A,X(13),15,0x6ED9EBA1L);
R2(A,B,C,D,X( 3), 3,0x6ED9EBA1L);
R2(D,A,B,C,X(11), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 7),11,0x6ED9EBA1L);
R2(B,C,D,A,X(15),15,0x6ED9EBA1L);
A = c->A += A;
B = c->B += B;
C = c->C += C;
D = c->D += D;
}
}
static void sha256_block_data_order(SHA256_CTX *ctx, const void *in,
size_t num)
{
unsigned MD32_REG_T a, b, c, d, e, f, g, h, s0, s1, T1;
SHA_LONG X[16];
int i;
const unsigned char *data = in;
const union {
long one;
char little;
} is_endian = {
1
};
while (num--) {
a = ctx->h[0];
b = ctx->h[1];
c = ctx->h[2];
d = ctx->h[3];
e = ctx->h[4];
f = ctx->h[5];
g = ctx->h[6];
h = ctx->h[7];
if (!is_endian.little && sizeof(SHA_LONG) == 4
&& ((size_t)in % 4) == 0) {
const SHA_LONG *W = (const SHA_LONG *)data;
T1 = X[0] = W[0];
ROUND_00_15(0, a, b, c, d, e, f, g, h);
T1 = X[1] = W[1];
ROUND_00_15(1, h, a, b, c, d, e, f, g);
T1 = X[2] = W[2];
ROUND_00_15(2, g, h, a, b, c, d, e, f);
T1 = X[3] = W[3];
ROUND_00_15(3, f, g, h, a, b, c, d, e);
T1 = X[4] = W[4];
ROUND_00_15(4, e, f, g, h, a, b, c, d);
T1 = X[5] = W[5];
ROUND_00_15(5, d, e, f, g, h, a, b, c);
T1 = X[6] = W[6];
ROUND_00_15(6, c, d, e, f, g, h, a, b);
T1 = X[7] = W[7];
ROUND_00_15(7, b, c, d, e, f, g, h, a);
T1 = X[8] = W[8];
ROUND_00_15(8, a, b, c, d, e, f, g, h);
T1 = X[9] = W[9];
ROUND_00_15(9, h, a, b, c, d, e, f, g);
T1 = X[10] = W[10];
ROUND_00_15(10, g, h, a, b, c, d, e, f);
T1 = X[11] = W[11];
ROUND_00_15(11, f, g, h, a, b, c, d, e);
T1 = X[12] = W[12];
ROUND_00_15(12, e, f, g, h, a, b, c, d);
T1 = X[13] = W[13];
ROUND_00_15(13, d, e, f, g, h, a, b, c);
T1 = X[14] = W[14];
ROUND_00_15(14, c, d, e, f, g, h, a, b);
T1 = X[15] = W[15];
ROUND_00_15(15, b, c, d, e, f, g, h, a);
data += SHA256_CBLOCK;
} else {
SHA_LONG l;
HOST_c2l(data, l);
T1 = X[0] = l;
ROUND_00_15(0, a, b, c, d, e, f, g, h);
HOST_c2l(data, l);
T1 = X[1] = l;
ROUND_00_15(1, h, a, b, c, d, e, f, g);
HOST_c2l(data, l);
T1 = X[2] = l;
ROUND_00_15(2, g, h, a, b, c, d, e, f);
HOST_c2l(data, l);
T1 = X[3] = l;
ROUND_00_15(3, f, g, h, a, b, c, d, e);
HOST_c2l(data, l);
T1 = X[4] = l;
ROUND_00_15(4, e, f, g, h, a, b, c, d);
HOST_c2l(data, l);
T1 = X[5] = l;
ROUND_00_15(5, d, e, f, g, h, a, b, c);
HOST_c2l(data, l);
T1 = X[6] = l;
ROUND_00_15(6, c, d, e, f, g, h, a, b);
HOST_c2l(data, l);
T1 = X[7] = l;
ROUND_00_15(7, b, c, d, e, f, g, h, a);
HOST_c2l(data, l);
T1 = X[8] = l;
ROUND_00_15(8, a, b, c, d, e, f, g, h);
HOST_c2l(data, l);
T1 = X[9] = l;
ROUND_00_15(9, h, a, b, c, d, e, f, g);
HOST_c2l(data, l);
T1 = X[10] = l;
ROUND_00_15(10, g, h, a, b, c, d, e, f);
HOST_c2l(data, l);
T1 = X[11] = l;
ROUND_00_15(11, f, g, h, a, b, c, d, e);
HOST_c2l(data, l);
T1 = X[12] = l;
ROUND_00_15(12, e, f, g, h, a, b, c, d);
HOST_c2l(data, l);
T1 = X[13] = l;
ROUND_00_15(13, d, e, f, g, h, a, b, c);
HOST_c2l(data, l);
T1 = X[14] = l;
ROUND_00_15(14, c, d, e, f, g, h, a, b);
HOST_c2l(data, l);
T1 = X[15] = l;
ROUND_00_15(15, b, c, d, e, f, g, h, a);
}
for (i = 16; i < 64; i += 8) {
ROUND_16_63(i + 0, a, b, c, d, e, f, g, h, X);
ROUND_16_63(i + 1, h, a, b, c, d, e, f, g, X);
ROUND_16_63(i + 2, g, h, a, b, c, d, e, f, X);
ROUND_16_63(i + 3, f, g, h, a, b, c, d, e, X);
ROUND_16_63(i + 4, e, f, g, h, a, b, c, d, X);
ROUND_16_63(i + 5, d, e, f, g, h, a, b, c, X);
ROUND_16_63(i + 6, c, d, e, f, g, h, a, b, X);
ROUND_16_63(i + 7, b, c, d, e, f, g, h, a, X);
}
ctx->h[0] += a;
ctx->h[1] += b;
ctx->h[2] += c;
ctx->h[3] += d;
ctx->h[4] += e;
ctx->h[5] += f;
ctx->h[6] += g;
ctx->h[7] += h;
}
}
void md5_block_data_order (MD5_CTX *c, const void *data_, size_t num)
{
const unsigned char *data=data_;
register unsigned MD32_REG_T A,B,C,D,l;
#ifndef MD32_XARRAY
/* See comment in crypto/sha/sha_locl.h for details. */
unsigned MD32_REG_T XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7,
XX8, XX9,XX10,XX11,XX12,XX13,XX14,XX15;
# define X(i) XX##i
#else
MD5_LONG XX[MD5_LBLOCK];
# define X(i) XX[i]
#endif
A=c->A;
B=c->B;
C=c->C;
D=c->D;
for (;num--;)
{
HOST_c2l(data,l); X( 0)=l; HOST_c2l(data,l); X( 1)=l;
/* Round 0 */
R0(A,B,C,D,X( 0), 7,0xd76aa478L); HOST_c2l(data,l); X( 2)=l;
R0(D,A,B,C,X( 1),12,0xe8c7b756L); HOST_c2l(data,l); X( 3)=l;
R0(C,D,A,B,X( 2),17,0x242070dbL); HOST_c2l(data,l); X( 4)=l;
R0(B,C,D,A,X( 3),22,0xc1bdceeeL); HOST_c2l(data,l); X( 5)=l;
R0(A,B,C,D,X( 4), 7,0xf57c0fafL); HOST_c2l(data,l); X( 6)=l;
R0(D,A,B,C,X( 5),12,0x4787c62aL); HOST_c2l(data,l); X( 7)=l;
R0(C,D,A,B,X( 6),17,0xa8304613L); HOST_c2l(data,l); X( 8)=l;
R0(B,C,D,A,X( 7),22,0xfd469501L); HOST_c2l(data,l); X( 9)=l;
R0(A,B,C,D,X( 8), 7,0x698098d8L); HOST_c2l(data,l); X(10)=l;
R0(D,A,B,C,X( 9),12,0x8b44f7afL); HOST_c2l(data,l); X(11)=l;
R0(C,D,A,B,X(10),17,0xffff5bb1L); HOST_c2l(data,l); X(12)=l;
R0(B,C,D,A,X(11),22,0x895cd7beL); HOST_c2l(data,l); X(13)=l;
R0(A,B,C,D,X(12), 7,0x6b901122L); HOST_c2l(data,l); X(14)=l;
R0(D,A,B,C,X(13),12,0xfd987193L); HOST_c2l(data,l); X(15)=l;
R0(C,D,A,B,X(14),17,0xa679438eL);
R0(B,C,D,A,X(15),22,0x49b40821L);
/* Round 1 */
R1(A,B,C,D,X( 1), 5,0xf61e2562L);
R1(D,A,B,C,X( 6), 9,0xc040b340L);
R1(C,D,A,B,X(11),14,0x265e5a51L);
R1(B,C,D,A,X( 0),20,0xe9b6c7aaL);
R1(A,B,C,D,X( 5), 5,0xd62f105dL);
R1(D,A,B,C,X(10), 9,0x02441453L);
R1(C,D,A,B,X(15),14,0xd8a1e681L);
R1(B,C,D,A,X( 4),20,0xe7d3fbc8L);
R1(A,B,C,D,X( 9), 5,0x21e1cde6L);
R1(D,A,B,C,X(14), 9,0xc33707d6L);
R1(C,D,A,B,X( 3),14,0xf4d50d87L);
R1(B,C,D,A,X( 8),20,0x455a14edL);
R1(A,B,C,D,X(13), 5,0xa9e3e905L);
R1(D,A,B,C,X( 2), 9,0xfcefa3f8L);
R1(C,D,A,B,X( 7),14,0x676f02d9L);
R1(B,C,D,A,X(12),20,0x8d2a4c8aL);
/* Round 2 */
R2(A,B,C,D,X( 5), 4,0xfffa3942L);
R2(D,A,B,C,X( 8),11,0x8771f681L);
R2(C,D,A,B,X(11),16,0x6d9d6122L);
R2(B,C,D,A,X(14),23,0xfde5380cL);
R2(A,B,C,D,X( 1), 4,0xa4beea44L);
R2(D,A,B,C,X( 4),11,0x4bdecfa9L);
R2(C,D,A,B,X( 7),16,0xf6bb4b60L);
R2(B,C,D,A,X(10),23,0xbebfbc70L);
R2(A,B,C,D,X(13), 4,0x289b7ec6L);
R2(D,A,B,C,X( 0),11,0xeaa127faL);
R2(C,D,A,B,X( 3),16,0xd4ef3085L);
R2(B,C,D,A,X( 6),23,0x04881d05L);
R2(A,B,C,D,X( 9), 4,0xd9d4d039L);
R2(D,A,B,C,X(12),11,0xe6db99e5L);
R2(C,D,A,B,X(15),16,0x1fa27cf8L);
R2(B,C,D,A,X( 2),23,0xc4ac5665L);
/* Round 3 */
R3(A,B,C,D,X( 0), 6,0xf4292244L);
R3(D,A,B,C,X( 7),10,0x432aff97L);
R3(C,D,A,B,X(14),15,0xab9423a7L);
R3(B,C,D,A,X( 5),21,0xfc93a039L);
R3(A,B,C,D,X(12), 6,0x655b59c3L);
R3(D,A,B,C,X( 3),10,0x8f0ccc92L);
R3(C,D,A,B,X(10),15,0xffeff47dL);
R3(B,C,D,A,X( 1),21,0x85845dd1L);
R3(A,B,C,D,X( 8), 6,0x6fa87e4fL);
R3(D,A,B,C,X(15),10,0xfe2ce6e0L);
R3(C,D,A,B,X( 6),15,0xa3014314L);
R3(B,C,D,A,X(13),21,0x4e0811a1L);
R3(A,B,C,D,X( 4), 6,0xf7537e82L);
R3(D,A,B,C,X(11),10,0xbd3af235L);
R3(C,D,A,B,X( 2),15,0x2ad7d2bbL);
R3(B,C,D,A,X( 9),21,0xeb86d391L);
A = c->A += A;
B = c->B += B;
C = c->C += C;
D = c->D += D;
}
}
void md4_block_data_order(uint32_t *state, const uint8_t *data, size_t num) {
uint32_t A, B, C, D, l;
uint32_t X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15;
A = state[0];
B = state[1];
C = state[2];
D = state[3];
for (; num--;) {
HOST_c2l(data, l);
X0 = l;
HOST_c2l(data, l);
X1 = l;
/* Round 0 */
R0(A, B, C, D, X0, 3, 0);
HOST_c2l(data, l);
X2 = l;
R0(D, A, B, C, X1, 7, 0);
HOST_c2l(data, l);
X3 = l;
R0(C, D, A, B, X2, 11, 0);
HOST_c2l(data, l);
X4 = l;
R0(B, C, D, A, X3, 19, 0);
HOST_c2l(data, l);
X5 = l;
R0(A, B, C, D, X4, 3, 0);
HOST_c2l(data, l);
X6 = l;
R0(D, A, B, C, X5, 7, 0);
HOST_c2l(data, l);
X7 = l;
R0(C, D, A, B, X6, 11, 0);
HOST_c2l(data, l);
X8 = l;
R0(B, C, D, A, X7, 19, 0);
HOST_c2l(data, l);
X9 = l;
R0(A, B, C, D, X8, 3, 0);
HOST_c2l(data, l);
X10 = l;
R0(D, A, B, C, X9, 7, 0);
HOST_c2l(data, l);
X11 = l;
R0(C, D, A, B, X10, 11, 0);
HOST_c2l(data, l);
X12 = l;
R0(B, C, D, A, X11, 19, 0);
HOST_c2l(data, l);
X13 = l;
R0(A, B, C, D, X12, 3, 0);
HOST_c2l(data, l);
X14 = l;
R0(D, A, B, C, X13, 7, 0);
HOST_c2l(data, l);
X15 = l;
R0(C, D, A, B, X14, 11, 0);
R0(B, C, D, A, X15, 19, 0);
/* Round 1 */
R1(A, B, C, D, X0, 3, 0x5A827999L);
R1(D, A, B, C, X4, 5, 0x5A827999L);
R1(C, D, A, B, X8, 9, 0x5A827999L);
R1(B, C, D, A, X12, 13, 0x5A827999L);
R1(A, B, C, D, X1, 3, 0x5A827999L);
R1(D, A, B, C, X5, 5, 0x5A827999L);
R1(C, D, A, B, X9, 9, 0x5A827999L);
R1(B, C, D, A, X13, 13, 0x5A827999L);
R1(A, B, C, D, X2, 3, 0x5A827999L);
R1(D, A, B, C, X6, 5, 0x5A827999L);
R1(C, D, A, B, X10, 9, 0x5A827999L);
R1(B, C, D, A, X14, 13, 0x5A827999L);
R1(A, B, C, D, X3, 3, 0x5A827999L);
R1(D, A, B, C, X7, 5, 0x5A827999L);
R1(C, D, A, B, X11, 9, 0x5A827999L);
R1(B, C, D, A, X15, 13, 0x5A827999L);
/* Round 2 */
R2(A, B, C, D, X0, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X8, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X4, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X12, 15, 0x6ED9EBA1L);
R2(A, B, C, D, X2, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X10, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X6, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X14, 15, 0x6ED9EBA1L);
R2(A, B, C, D, X1, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X9, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X5, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X13, 15, 0x6ED9EBA1L);
R2(A, B, C, D, X3, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X11, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X7, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X15, 15, 0x6ED9EBA1L);
A = state[0] += A;
B = state[1] += B;
C = state[2] += C;
D = state[3] += D;
}
}
void md4_block_data_order(MD4_CTX *c, const void *data_, size_t num) {
const uint8_t *data = data_;
uint32_t A, B, C, D, l;
uint32_t X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X12, X13, X14, X15;
A = c->A;
B = c->B;
C = c->C;
D = c->D;
for (; num--;) {
HOST_c2l(data, l);
X0 = l;
HOST_c2l(data, l);
X1 = l;
/* Round 0 */
R0(A, B, C, D, X0, 3, 0);
HOST_c2l(data, l);
X2 = l;
R0(D, A, B, C, X1, 7, 0);
HOST_c2l(data, l);
X3 = l;
R0(C, D, A, B, X2, 11, 0);
HOST_c2l(data, l);
X4 = l;
R0(B, C, D, A, X3, 19, 0);
HOST_c2l(data, l);
X5 = l;
R0(A, B, C, D, X4, 3, 0);
HOST_c2l(data, l);
X6 = l;
R0(D, A, B, C, X5, 7, 0);
HOST_c2l(data, l);
X7 = l;
R0(C, D, A, B, X6, 11, 0);
HOST_c2l(data, l);
X8 = l;
R0(B, C, D, A, X7, 19, 0);
HOST_c2l(data, l);
X9 = l;
R0(A, B, C, D, X8, 3, 0);
HOST_c2l(data, l);
X10 = l;
R0(D, A, B, C, X9, 7, 0);
HOST_c2l(data, l);
X11 = l;
R0(C, D, A, B, X10, 11, 0);
HOST_c2l(data, l);
X12 = l;
R0(B, C, D, A, X11, 19, 0);
HOST_c2l(data, l);
X13 = l;
R0(A, B, C, D, X12, 3, 0);
HOST_c2l(data, l);
X14 = l;
R0(D, A, B, C, X13, 7, 0);
HOST_c2l(data, l);
X15 = l;
R0(C, D, A, B, X14, 11, 0);
R0(B, C, D, A, X15, 19, 0);
/* Round 1 */
R1(A, B, C, D, X0, 3, 0x5A827999L);
R1(D, A, B, C, X4, 5, 0x5A827999L);
R1(C, D, A, B, X8, 9, 0x5A827999L);
R1(B, C, D, A, X12, 13, 0x5A827999L);
R1(A, B, C, D, X1, 3, 0x5A827999L);
R1(D, A, B, C, X5, 5, 0x5A827999L);
R1(C, D, A, B, X9, 9, 0x5A827999L);
R1(B, C, D, A, X13, 13, 0x5A827999L);
R1(A, B, C, D, X2, 3, 0x5A827999L);
R1(D, A, B, C, X6, 5, 0x5A827999L);
R1(C, D, A, B, X10, 9, 0x5A827999L);
R1(B, C, D, A, X14, 13, 0x5A827999L);
R1(A, B, C, D, X3, 3, 0x5A827999L);
R1(D, A, B, C, X7, 5, 0x5A827999L);
R1(C, D, A, B, X11, 9, 0x5A827999L);
R1(B, C, D, A, X15, 13, 0x5A827999L);
/* Round 2 */
R2(A, B, C, D, X0, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X8, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X4, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X12, 15, 0x6ED9EBA1L);
R2(A, B, C, D, X2, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X10, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X6, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X14, 15, 0x6ED9EBA1L);
R2(A, B, C, D, X1, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X9, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X5, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X13, 15, 0x6ED9EBA1L);
R2(A, B, C, D, X3, 3, 0x6ED9EBA1L);
R2(D, A, B, C, X11, 9, 0x6ED9EBA1L);
R2(C, D, A, B, X7, 11, 0x6ED9EBA1L);
R2(B, C, D, A, X15, 15, 0x6ED9EBA1L);
A = c->A += A;
B = c->B += B;
C = c->C += C;
D = c->D += D;
}
}
void md5_block_data_order (MD5_CTX *c, const void *data_, int num)
{
const unsigned char *data=data_;
register unsigned long A,B,C,D,l;
/*
* In case you wonder why A-D are declared as long and not
* as MD5_LONG. Doing so results in slight performance
* boost on LP64 architectures. The catch is we don't
* really care if 32 MSBs of a 64-bit register get polluted
* with eventual overflows as we *save* only 32 LSBs in
* *either* case. Now declaring 'em long excuses the compiler
* from keeping 32 MSBs zeroed resulting in 13% performance
* improvement under SPARC Solaris7/64 and 5% under AlphaLinux.
* Well, to be honest it should say that this *prevents*
* performance degradation.
*
* <*****@*****.**>
*/
#ifndef MD32_XARRAY
/* See comment in crypto/sha/sha_locl.h for details. */
unsigned long XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7,
XX8, XX9,XX10,XX11,XX12,XX13,XX14,XX15;
# define X(i) XX##i
#else
MD5_LONG XX[MD5_LBLOCK];
# define X(i) XX[i]
#endif
A=c->A;
B=c->B;
C=c->C;
D=c->D;
for (;num--;)
{
HOST_c2l(data,l); X( 0)=l; HOST_c2l(data,l); X( 1)=l;
/* Round 0 */
R0(A,B,C,D,X( 0), 7,0xd76aa478L); HOST_c2l(data,l); X( 2)=l;
R0(D,A,B,C,X( 1),12,0xe8c7b756L); HOST_c2l(data,l); X( 3)=l;
R0(C,D,A,B,X( 2),17,0x242070dbL); HOST_c2l(data,l); X( 4)=l;
R0(B,C,D,A,X( 3),22,0xc1bdceeeL); HOST_c2l(data,l); X( 5)=l;
R0(A,B,C,D,X( 4), 7,0xf57c0fafL); HOST_c2l(data,l); X( 6)=l;
R0(D,A,B,C,X( 5),12,0x4787c62aL); HOST_c2l(data,l); X( 7)=l;
R0(C,D,A,B,X( 6),17,0xa8304613L); HOST_c2l(data,l); X( 8)=l;
R0(B,C,D,A,X( 7),22,0xfd469501L); HOST_c2l(data,l); X( 9)=l;
R0(A,B,C,D,X( 8), 7,0x698098d8L); HOST_c2l(data,l); X(10)=l;
R0(D,A,B,C,X( 9),12,0x8b44f7afL); HOST_c2l(data,l); X(11)=l;
R0(C,D,A,B,X(10),17,0xffff5bb1L); HOST_c2l(data,l); X(12)=l;
R0(B,C,D,A,X(11),22,0x895cd7beL); HOST_c2l(data,l); X(13)=l;
R0(A,B,C,D,X(12), 7,0x6b901122L); HOST_c2l(data,l); X(14)=l;
R0(D,A,B,C,X(13),12,0xfd987193L); HOST_c2l(data,l); X(15)=l;
R0(C,D,A,B,X(14),17,0xa679438eL);
R0(B,C,D,A,X(15),22,0x49b40821L);
/* Round 1 */
R1(A,B,C,D,X( 1), 5,0xf61e2562L);
R1(D,A,B,C,X( 6), 9,0xc040b340L);
R1(C,D,A,B,X(11),14,0x265e5a51L);
R1(B,C,D,A,X( 0),20,0xe9b6c7aaL);
R1(A,B,C,D,X( 5), 5,0xd62f105dL);
R1(D,A,B,C,X(10), 9,0x02441453L);
R1(C,D,A,B,X(15),14,0xd8a1e681L);
R1(B,C,D,A,X( 4),20,0xe7d3fbc8L);
R1(A,B,C,D,X( 9), 5,0x21e1cde6L);
R1(D,A,B,C,X(14), 9,0xc33707d6L);
R1(C,D,A,B,X( 3),14,0xf4d50d87L);
R1(B,C,D,A,X( 8),20,0x455a14edL);
R1(A,B,C,D,X(13), 5,0xa9e3e905L);
R1(D,A,B,C,X( 2), 9,0xfcefa3f8L);
R1(C,D,A,B,X( 7),14,0x676f02d9L);
R1(B,C,D,A,X(12),20,0x8d2a4c8aL);
/* Round 2 */
R2(A,B,C,D,X( 5), 4,0xfffa3942L);
R2(D,A,B,C,X( 8),11,0x8771f681L);
R2(C,D,A,B,X(11),16,0x6d9d6122L);
R2(B,C,D,A,X(14),23,0xfde5380cL);
R2(A,B,C,D,X( 1), 4,0xa4beea44L);
R2(D,A,B,C,X( 4),11,0x4bdecfa9L);
R2(C,D,A,B,X( 7),16,0xf6bb4b60L);
R2(B,C,D,A,X(10),23,0xbebfbc70L);
R2(A,B,C,D,X(13), 4,0x289b7ec6L);
R2(D,A,B,C,X( 0),11,0xeaa127faL);
R2(C,D,A,B,X( 3),16,0xd4ef3085L);
R2(B,C,D,A,X( 6),23,0x04881d05L);
R2(A,B,C,D,X( 9), 4,0xd9d4d039L);
R2(D,A,B,C,X(12),11,0xe6db99e5L);
R2(C,D,A,B,X(15),16,0x1fa27cf8L);
R2(B,C,D,A,X( 2),23,0xc4ac5665L);
/* Round 3 */
R3(A,B,C,D,X( 0), 6,0xf4292244L);
R3(D,A,B,C,X( 7),10,0x432aff97L);
R3(C,D,A,B,X(14),15,0xab9423a7L);
R3(B,C,D,A,X( 5),21,0xfc93a039L);
R3(A,B,C,D,X(12), 6,0x655b59c3L);
R3(D,A,B,C,X( 3),10,0x8f0ccc92L);
R3(C,D,A,B,X(10),15,0xffeff47dL);
R3(B,C,D,A,X( 1),21,0x85845dd1L);
R3(A,B,C,D,X( 8), 6,0x6fa87e4fL);
R3(D,A,B,C,X(15),10,0xfe2ce6e0L);
R3(C,D,A,B,X( 6),15,0xa3014314L);
R3(B,C,D,A,X(13),21,0x4e0811a1L);
R3(A,B,C,D,X( 4), 6,0xf7537e82L);
R3(D,A,B,C,X(11),10,0xbd3af235L);
R3(C,D,A,B,X( 2),15,0x2ad7d2bbL);
R3(B,C,D,A,X( 9),21,0xeb86d391L);
A = c->A += A;
B = c->B += B;
C = c->C += C;
D = c->D += D;
}
}
static void sha256_block_data_order(SHA256_CTX *ctx, const void *in,
size_t num)
{
unsigned MD32_REG_T a, b, c, d, e, f, g, h, s0, s1, T1;
SHA_LONG X[16];
int i;
const unsigned char *data = in;
const union {
long one;
char little;
} is_endian = {
1
};
while (num--) {
a = ctx->h[0];
b = ctx->h[1];
c = ctx->h[2];
d = ctx->h[3];
e = ctx->h[4];
f = ctx->h[5];
g = ctx->h[6];
h = ctx->h[7];
if (!is_endian.little && sizeof(SHA_LONG) == 4
&& ((size_t)in % 4) == 0) {
const SHA_LONG *W = (const SHA_LONG *)data;
T1 = X[0] = W[0];
ROUND_00_15(0, a, b, c, d, e, f, g, h);
T1 = X[1] = W[1];
ROUND_00_15(1, h, a, b, c, d, e, f, g);
T1 = X[2] = W[2];
ROUND_00_15(2, g, h, a, b, c, d, e, f);
T1 = X[3] = W[3];
ROUND_00_15(3, f, g, h, a, b, c, d, e);
T1 = X[4] = W[4];
ROUND_00_15(4, e, f, g, h, a, b, c, d);
T1 = X[5] = W[5];
ROUND_00_15(5, d, e, f, g, h, a, b, c);
T1 = X[6] = W[6];
ROUND_00_15(6, c, d, e, f, g, h, a, b);
T1 = X[7] = W[7];
ROUND_00_15(7, b, c, d, e, f, g, h, a);
T1 = X[8] = W[8];
ROUND_00_15(8, a, b, c, d, e, f, g, h);
T1 = X[9] = W[9];
ROUND_00_15(9, h, a, b, c, d, e, f, g);
T1 = X[10] = W[10];
ROUND_00_15(10, g, h, a, b, c, d, e, f);
T1 = X[11] = W[11];
ROUND_00_15(11, f, g, h, a, b, c, d, e);
T1 = X[12] = W[12];
ROUND_00_15(12, e, f, g, h, a, b, c, d);
T1 = X[13] = W[13];
ROUND_00_15(13, d, e, f, g, h, a, b, c);
T1 = X[14] = W[14];
ROUND_00_15(14, c, d, e, f, g, h, a, b);
T1 = X[15] = W[15];
ROUND_00_15(15, b, c, d, e, f, g, h, a);
data += SHA256_CBLOCK;
} else {
SHA_LONG l;
E(DBF_ALWAYS, "LITTLE ENDIAN BRANCH!!!: is_endian.little = %ld, in=%08lx, (in %% 4) = %ld, sizeof(SHA_LONG) = %ld", is_endian.little, in, ((size_t)in % 4), sizeof(SHA_LONG));
E(DBF_ALWAYS, "a=%08lx b=%08lx c=%08lx d=%08lx e=%08lx f=%08lx g=%08lx h=%08lx", a, b, c, d, e, f, g, h);
#if defined(DEBUG)
for(i=0; i < 16; i++)
{
const unsigned char *d = data + (i*4);
D(DBF_ALWAYS, "%ld: %02lx %02lx %02lx %02lx", i, d[0], d[1], d[2], d[3]);
}
#endif
(void)HOST_c2l(data, l);
T1 = X[0] = l;
ROUND_00_15(0, a, b, c, d, e, f, g, h);
(void)HOST_c2l(data, l);
T1 = X[1] = l;
ROUND_00_15(1, h, a, b, c, d, e, f, g);
(void)HOST_c2l(data, l);
T1 = X[2] = l;
ROUND_00_15(2, g, h, a, b, c, d, e, f);
(void)HOST_c2l(data, l);
T1 = X[3] = l;
ROUND_00_15(3, f, g, h, a, b, c, d, e);
(void)HOST_c2l(data, l);
T1 = X[4] = l;
ROUND_00_15(4, e, f, g, h, a, b, c, d);
(void)HOST_c2l(data, l);
T1 = X[5] = l;
ROUND_00_15(5, d, e, f, g, h, a, b, c);
(void)HOST_c2l(data, l);
T1 = X[6] = l;
ROUND_00_15(6, c, d, e, f, g, h, a, b);
(void)HOST_c2l(data, l);
T1 = X[7] = l;
ROUND_00_15(7, b, c, d, e, f, g, h, a);
(void)HOST_c2l(data, l);
T1 = X[8] = l;
ROUND_00_15(8, a, b, c, d, e, f, g, h);
(void)HOST_c2l(data, l);
T1 = X[9] = l;
ROUND_00_15(9, h, a, b, c, d, e, f, g);
(void)HOST_c2l(data, l);
T1 = X[10] = l;
ROUND_00_15(10, g, h, a, b, c, d, e, f);
(void)HOST_c2l(data, l);
T1 = X[11] = l;
ROUND_00_15(11, f, g, h, a, b, c, d, e);
(void)HOST_c2l(data, l);
T1 = X[12] = l;
ROUND_00_15(12, e, f, g, h, a, b, c, d);
(void)HOST_c2l(data, l);
T1 = X[13] = l;
ROUND_00_15(13, d, e, f, g, h, a, b, c);
(void)HOST_c2l(data, l);
T1 = X[14] = l;
ROUND_00_15(14, c, d, e, f, g, h, a, b);
(void)HOST_c2l(data, l);
T1 = X[15] = l;
ROUND_00_15(15, b, c, d, e, f, g, h, a);
E(DBF_ALWAYS, "a=%08lx b=%08lx c=%08lx d=%08lx e=%08lx f=%08lx g=%08lx h=%08lx", a, b, c, d, e, f, g, h);
#if defined(DEBUG)
for(i=0; i < 16; i++)
D(DBF_ALWAYS, "X[%ld] = %08lx", i, X[i]);
#endif
}
for (i = 16; i < 64; i += 8) {
ROUND_16_63(i + 0, a, b, c, d, e, f, g, h, X);
ROUND_16_63(i + 1, h, a, b, c, d, e, f, g, X);
ROUND_16_63(i + 2, g, h, a, b, c, d, e, f, X);
ROUND_16_63(i + 3, f, g, h, a, b, c, d, e, X);
ROUND_16_63(i + 4, e, f, g, h, a, b, c, d, X);
ROUND_16_63(i + 5, d, e, f, g, h, a, b, c, X);
ROUND_16_63(i + 6, c, d, e, f, g, h, a, b, X);
ROUND_16_63(i + 7, b, c, d, e, f, g, h, a, X);
}
E(DBF_ALWAYS, "FINAL: a=%08lx b=%08lx c=%08lx d=%08lx e=%08lx f=%08lx g=%08lx h=%08lx", a, b, c, d, e, f, g, h);
ctx->h[0] += a;
ctx->h[1] += b;
ctx->h[2] += c;
ctx->h[3] += d;
ctx->h[4] += e;
ctx->h[5] += f;
ctx->h[6] += g;
ctx->h[7] += h;
}
}
static void sha256_block_data_order(uint32_t *state, const uint8_t *data,
size_t num) {
uint32_t a, b, c, d, e, f, g, h, s0, s1, T1;
uint32_t X[16];
int i;
while (num--) {
a = state[0];
b = state[1];
c = state[2];
d = state[3];
e = state[4];
f = state[5];
g = state[6];
h = state[7];
uint32_t l;
HOST_c2l(data, l);
T1 = X[0] = l;
ROUND_00_15(0, a, b, c, d, e, f, g, h);
HOST_c2l(data, l);
T1 = X[1] = l;
ROUND_00_15(1, h, a, b, c, d, e, f, g);
HOST_c2l(data, l);
T1 = X[2] = l;
ROUND_00_15(2, g, h, a, b, c, d, e, f);
HOST_c2l(data, l);
T1 = X[3] = l;
ROUND_00_15(3, f, g, h, a, b, c, d, e);
HOST_c2l(data, l);
T1 = X[4] = l;
ROUND_00_15(4, e, f, g, h, a, b, c, d);
HOST_c2l(data, l);
T1 = X[5] = l;
ROUND_00_15(5, d, e, f, g, h, a, b, c);
HOST_c2l(data, l);
T1 = X[6] = l;
ROUND_00_15(6, c, d, e, f, g, h, a, b);
HOST_c2l(data, l);
T1 = X[7] = l;
ROUND_00_15(7, b, c, d, e, f, g, h, a);
HOST_c2l(data, l);
T1 = X[8] = l;
ROUND_00_15(8, a, b, c, d, e, f, g, h);
HOST_c2l(data, l);
T1 = X[9] = l;
ROUND_00_15(9, h, a, b, c, d, e, f, g);
HOST_c2l(data, l);
T1 = X[10] = l;
ROUND_00_15(10, g, h, a, b, c, d, e, f);
HOST_c2l(data, l);
T1 = X[11] = l;
ROUND_00_15(11, f, g, h, a, b, c, d, e);
HOST_c2l(data, l);
T1 = X[12] = l;
ROUND_00_15(12, e, f, g, h, a, b, c, d);
HOST_c2l(data, l);
T1 = X[13] = l;
ROUND_00_15(13, d, e, f, g, h, a, b, c);
HOST_c2l(data, l);
T1 = X[14] = l;
ROUND_00_15(14, c, d, e, f, g, h, a, b);
HOST_c2l(data, l);
T1 = X[15] = l;
ROUND_00_15(15, b, c, d, e, f, g, h, a);
for (i = 16; i < 64; i += 8) {
ROUND_16_63(i + 0, a, b, c, d, e, f, g, h, X);
ROUND_16_63(i + 1, h, a, b, c, d, e, f, g, X);
ROUND_16_63(i + 2, g, h, a, b, c, d, e, f, X);
ROUND_16_63(i + 3, f, g, h, a, b, c, d, e, X);
ROUND_16_63(i + 4, e, f, g, h, a, b, c, d, X);
ROUND_16_63(i + 5, d, e, f, g, h, a, b, c, X);
ROUND_16_63(i + 6, c, d, e, f, g, h, a, b, X);
ROUND_16_63(i + 7, b, c, d, e, f, g, h, a, X);
}
state[0] += a;
state[1] += b;
state[2] += c;
state[3] += d;
state[4] += e;
state[5] += f;
state[6] += g;
state[7] += h;
}
}
static void sha1_compress(ccdigest_state_t s, size_t num, const void *buf)
{
const unsigned char *data=buf;
register uint32_t A,B,C,D,E,T,l;
#ifndef MD32_XARRAY
uint32_t XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7,
XX8, XX9,XX10,XX11,XX12,XX13,XX14,XX15;
#else
uint32_t XX[16];
#endif
uint32_t *state=ccdigest_u32(s);
A=state[0];
B=state[1];
C=state[2];
D=state[3];
E=state[4];
for (;;)
{
HOST_c2l(data,l); X( 0)=l; HOST_c2l(data,l); X( 1)=l;
BODY_00_15( 0,A,B,C,D,E,T,X( 0)); HOST_c2l(data,l); X( 2)=l;
BODY_00_15( 1,T,A,B,C,D,E,X( 1)); HOST_c2l(data,l); X( 3)=l;
BODY_00_15( 2,E,T,A,B,C,D,X( 2)); HOST_c2l(data,l); X( 4)=l;
BODY_00_15( 3,D,E,T,A,B,C,X( 3)); HOST_c2l(data,l); X( 5)=l;
BODY_00_15( 4,C,D,E,T,A,B,X( 4)); HOST_c2l(data,l); X( 6)=l;
BODY_00_15( 5,B,C,D,E,T,A,X( 5)); HOST_c2l(data,l); X( 7)=l;
BODY_00_15( 6,A,B,C,D,E,T,X( 6)); HOST_c2l(data,l); X( 8)=l;
BODY_00_15( 7,T,A,B,C,D,E,X( 7)); HOST_c2l(data,l); X( 9)=l;
BODY_00_15( 8,E,T,A,B,C,D,X( 8)); HOST_c2l(data,l); X(10)=l;
BODY_00_15( 9,D,E,T,A,B,C,X( 9)); HOST_c2l(data,l); X(11)=l;
BODY_00_15(10,C,D,E,T,A,B,X(10)); HOST_c2l(data,l); X(12)=l;
BODY_00_15(11,B,C,D,E,T,A,X(11)); HOST_c2l(data,l); X(13)=l;
BODY_00_15(12,A,B,C,D,E,T,X(12)); HOST_c2l(data,l); X(14)=l;
BODY_00_15(13,T,A,B,C,D,E,X(13)); HOST_c2l(data,l); X(15)=l;
BODY_00_15(14,E,T,A,B,C,D,X(14));
BODY_00_15(15,D,E,T,A,B,C,X(15));
BODY_16_19(16,C,D,E,T,A,B,X( 0),X( 0),X( 2),X( 8),X(13));
BODY_16_19(17,B,C,D,E,T,A,X( 1),X( 1),X( 3),X( 9),X(14));
BODY_16_19(18,A,B,C,D,E,T,X( 2),X( 2),X( 4),X(10),X(15));
BODY_16_19(19,T,A,B,C,D,E,X( 3),X( 3),X( 5),X(11),X( 0));
BODY_20_31(20,E,T,A,B,C,D,X( 4),X( 4),X( 6),X(12),X( 1));
BODY_20_31(21,D,E,T,A,B,C,X( 5),X( 5),X( 7),X(13),X( 2));
BODY_20_31(22,C,D,E,T,A,B,X( 6),X( 6),X( 8),X(14),X( 3));
BODY_20_31(23,B,C,D,E,T,A,X( 7),X( 7),X( 9),X(15),X( 4));
BODY_20_31(24,A,B,C,D,E,T,X( 8),X( 8),X(10),X( 0),X( 5));
BODY_20_31(25,T,A,B,C,D,E,X( 9),X( 9),X(11),X( 1),X( 6));
BODY_20_31(26,E,T,A,B,C,D,X(10),X(10),X(12),X( 2),X( 7));
BODY_20_31(27,D,E,T,A,B,C,X(11),X(11),X(13),X( 3),X( 8));
BODY_20_31(28,C,D,E,T,A,B,X(12),X(12),X(14),X( 4),X( 9));
BODY_20_31(29,B,C,D,E,T,A,X(13),X(13),X(15),X( 5),X(10));
BODY_20_31(30,A,B,C,D,E,T,X(14),X(14),X( 0),X( 6),X(11));
BODY_20_31(31,T,A,B,C,D,E,X(15),X(15),X( 1),X( 7),X(12));
BODY_32_39(32,E,T,A,B,C,D,X( 0),X( 2),X( 8),X(13));
BODY_32_39(33,D,E,T,A,B,C,X( 1),X( 3),X( 9),X(14));
BODY_32_39(34,C,D,E,T,A,B,X( 2),X( 4),X(10),X(15));
BODY_32_39(35,B,C,D,E,T,A,X( 3),X( 5),X(11),X( 0));
BODY_32_39(36,A,B,C,D,E,T,X( 4),X( 6),X(12),X( 1));
BODY_32_39(37,T,A,B,C,D,E,X( 5),X( 7),X(13),X( 2));
BODY_32_39(38,E,T,A,B,C,D,X( 6),X( 8),X(14),X( 3));
BODY_32_39(39,D,E,T,A,B,C,X( 7),X( 9),X(15),X( 4));
BODY_40_59(40,C,D,E,T,A,B,X( 8),X(10),X( 0),X( 5));
BODY_40_59(41,B,C,D,E,T,A,X( 9),X(11),X( 1),X( 6));
BODY_40_59(42,A,B,C,D,E,T,X(10),X(12),X( 2),X( 7));
BODY_40_59(43,T,A,B,C,D,E,X(11),X(13),X( 3),X( 8));
BODY_40_59(44,E,T,A,B,C,D,X(12),X(14),X( 4),X( 9));
BODY_40_59(45,D,E,T,A,B,C,X(13),X(15),X( 5),X(10));
BODY_40_59(46,C,D,E,T,A,B,X(14),X( 0),X( 6),X(11));
BODY_40_59(47,B,C,D,E,T,A,X(15),X( 1),X( 7),X(12));
BODY_40_59(48,A,B,C,D,E,T,X( 0),X( 2),X( 8),X(13));
BODY_40_59(49,T,A,B,C,D,E,X( 1),X( 3),X( 9),X(14));
BODY_40_59(50,E,T,A,B,C,D,X( 2),X( 4),X(10),X(15));
BODY_40_59(51,D,E,T,A,B,C,X( 3),X( 5),X(11),X( 0));
BODY_40_59(52,C,D,E,T,A,B,X( 4),X( 6),X(12),X( 1));
BODY_40_59(53,B,C,D,E,T,A,X( 5),X( 7),X(13),X( 2));
BODY_40_59(54,A,B,C,D,E,T,X( 6),X( 8),X(14),X( 3));
BODY_40_59(55,T,A,B,C,D,E,X( 7),X( 9),X(15),X( 4));
BODY_40_59(56,E,T,A,B,C,D,X( 8),X(10),X( 0),X( 5));
BODY_40_59(57,D,E,T,A,B,C,X( 9),X(11),X( 1),X( 6));
BODY_40_59(58,C,D,E,T,A,B,X(10),X(12),X( 2),X( 7));
BODY_40_59(59,B,C,D,E,T,A,X(11),X(13),X( 3),X( 8));
BODY_60_79(60,A,B,C,D,E,T,X(12),X(14),X( 4),X( 9));
BODY_60_79(61,T,A,B,C,D,E,X(13),X(15),X( 5),X(10));
BODY_60_79(62,E,T,A,B,C,D,X(14),X( 0),X( 6),X(11));
BODY_60_79(63,D,E,T,A,B,C,X(15),X( 1),X( 7),X(12));
BODY_60_79(64,C,D,E,T,A,B,X( 0),X( 2),X( 8),X(13));
BODY_60_79(65,B,C,D,E,T,A,X( 1),X( 3),X( 9),X(14));
BODY_60_79(66,A,B,C,D,E,T,X( 2),X( 4),X(10),X(15));
BODY_60_79(67,T,A,B,C,D,E,X( 3),X( 5),X(11),X( 0));
BODY_60_79(68,E,T,A,B,C,D,X( 4),X( 6),X(12),X( 1));
BODY_60_79(69,D,E,T,A,B,C,X( 5),X( 7),X(13),X( 2));
BODY_60_79(70,C,D,E,T,A,B,X( 6),X( 8),X(14),X( 3));
BODY_60_79(71,B,C,D,E,T,A,X( 7),X( 9),X(15),X( 4));
BODY_60_79(72,A,B,C,D,E,T,X( 8),X(10),X( 0),X( 5));
BODY_60_79(73,T,A,B,C,D,E,X( 9),X(11),X( 1),X( 6));
BODY_60_79(74,E,T,A,B,C,D,X(10),X(12),X( 2),X( 7));
BODY_60_79(75,D,E,T,A,B,C,X(11),X(13),X( 3),X( 8));
BODY_60_79(76,C,D,E,T,A,B,X(12),X(14),X( 4),X( 9));
BODY_60_79(77,B,C,D,E,T,A,X(13),X(15),X( 5),X(10));
BODY_60_79(78,A,B,C,D,E,T,X(14),X( 0),X( 6),X(11));
BODY_60_79(79,T,A,B,C,D,E,X(15),X( 1),X( 7),X(12));
state[0]=(state[0]+E)&0xffffffff;
state[1]=(state[1]+T)&0xffffffff;
state[2]=(state[2]+A)&0xffffffff;
state[3]=(state[3]+B)&0xffffffff;
state[4]=(state[4]+C)&0xffffffff;
if (--num <= 0) break;
A=state[0];
B=state[1];
C=state[2];
D=state[3];
E=state[4];
}
}
void rtsmb_md4_block_data_order (RTSMB_MD4_CTX *c, const void *data_, int num)
{
const unsigned char *data;
register unsigned long A,B,C,D,l;
/*
* In case you wonder why A-D are declared as long and not
* as RTSMB_MD4_LONG. Doing so results in slight performance
* boost on LP64 architectures. The catch is we don't
* really care if 32 MSBs of a 64-bit register get polluted
* with eventual overflows as we *save* only 32 LSBs in
* *either* case. Now declaring 'em long excuses the compiler
* from keeping 32 MSBs zeroed resulting in 13% performance
* improvement under SPARC Solaris7/64 and 5% under AlphaLinux.
* Well, to be honest it should say that this *prevents*
* performance degradation.
*
* <*****@*****.**>
*/
#ifndef MD32_XARRAY
/* See comment in crypto/sha/sha_locl.h for details. */
unsigned long XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7,
XX8, XX9,XX10,XX11,XX12,XX13,XX14,XX15;
# define X(i) XX##i
#else
RTSMB_MD4_LONG XX[RTSMB_MD4_LBLOCK];
# define X(i) XX[i]
#endif
data =data_;
A=c->A;
B=c->B;
C=c->C;
D=c->D;
for (;num--;)
{
HOST_c2l(data,l); X( 0)=l; HOST_c2l(data,l); X( 1)=l;
/* Round 0 */
R0(A,B,C,D,X( 0), 3,0); HOST_c2l(data,l); X( 2)=l;
R0(D,A,B,C,X( 1), 7,0); HOST_c2l(data,l); X( 3)=l;
R0(C,D,A,B,X( 2),11,0); HOST_c2l(data,l); X( 4)=l;
R0(B,C,D,A,X( 3),19,0); HOST_c2l(data,l); X( 5)=l;
R0(A,B,C,D,X( 4), 3,0); HOST_c2l(data,l); X( 6)=l;
R0(D,A,B,C,X( 5), 7,0); HOST_c2l(data,l); X( 7)=l;
R0(C,D,A,B,X( 6),11,0); HOST_c2l(data,l); X( 8)=l;
R0(B,C,D,A,X( 7),19,0); HOST_c2l(data,l); X( 9)=l;
R0(A,B,C,D,X( 8), 3,0); HOST_c2l(data,l); X(10)=l;
R0(D,A,B,C,X( 9), 7,0); HOST_c2l(data,l); X(11)=l;
R0(C,D,A,B,X(10),11,0); HOST_c2l(data,l); X(12)=l;
R0(B,C,D,A,X(11),19,0); HOST_c2l(data,l); X(13)=l;
R0(A,B,C,D,X(12), 3,0); HOST_c2l(data,l); X(14)=l;
R0(D,A,B,C,X(13), 7,0); HOST_c2l(data,l); X(15)=l;
R0(C,D,A,B,X(14),11,0);
R0(B,C,D,A,X(15),19,0);
/* Round 1 */
R1(A,B,C,D,X( 0), 3,0x5A827999L);
R1(D,A,B,C,X( 4), 5,0x5A827999L);
R1(C,D,A,B,X( 8), 9,0x5A827999L);
R1(B,C,D,A,X(12),13,0x5A827999L);
R1(A,B,C,D,X( 1), 3,0x5A827999L);
R1(D,A,B,C,X( 5), 5,0x5A827999L);
R1(C,D,A,B,X( 9), 9,0x5A827999L);
R1(B,C,D,A,X(13),13,0x5A827999L);
R1(A,B,C,D,X( 2), 3,0x5A827999L);
R1(D,A,B,C,X( 6), 5,0x5A827999L);
R1(C,D,A,B,X(10), 9,0x5A827999L);
R1(B,C,D,A,X(14),13,0x5A827999L);
R1(A,B,C,D,X( 3), 3,0x5A827999L);
R1(D,A,B,C,X( 7), 5,0x5A827999L);
R1(C,D,A,B,X(11), 9,0x5A827999L);
R1(B,C,D,A,X(15),13,0x5A827999L);
/* Round 2 */
R2(A,B,C,D,X( 0), 3,0x6ED9EBA1L);
R2(D,A,B,C,X( 8), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 4),11,0x6ED9EBA1L);
R2(B,C,D,A,X(12),15,0x6ED9EBA1L);
R2(A,B,C,D,X( 2), 3,0x6ED9EBA1L);
R2(D,A,B,C,X(10), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 6),11,0x6ED9EBA1L);
R2(B,C,D,A,X(14),15,0x6ED9EBA1L);
R2(A,B,C,D,X( 1), 3,0x6ED9EBA1L);
R2(D,A,B,C,X( 9), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 5),11,0x6ED9EBA1L);
R2(B,C,D,A,X(13),15,0x6ED9EBA1L);
R2(A,B,C,D,X( 3), 3,0x6ED9EBA1L);
R2(D,A,B,C,X(11), 9,0x6ED9EBA1L);
R2(C,D,A,B,X( 7),11,0x6ED9EBA1L);
R2(B,C,D,A,X(15),15,0x6ED9EBA1L);
A = c->A += A;
B = c->B += B;
C = c->C += C;
D = c->D += D;
}
}
static void HASH_BLOCK_DATA_ORDER(SHA_CTX *c, const void *p, size_t num) {
const uint8_t *data = p;
register unsigned MD32_REG_T A, B, C, D, E, T, l;
unsigned MD32_REG_T XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7, XX8, XX9, XX10,
XX11, XX12, XX13, XX14, XX15;
A = c->h0;
B = c->h1;
C = c->h2;
D = c->h3;
E = c->h4;
for (;;) {
const union {
long one;
char little;
} is_endian = {1};
if (!is_endian.little && ((size_t)p % 4) == 0) {
const uint32_t *W = (const uint32_t *)data;
X(0) = W[0];
X(1) = W[1];
BODY_00_15(0, A, B, C, D, E, T, X(0));
X(2) = W[2];
BODY_00_15(1, T, A, B, C, D, E, X(1));
X(3) = W[3];
BODY_00_15(2, E, T, A, B, C, D, X(2));
X(4) = W[4];
BODY_00_15(3, D, E, T, A, B, C, X(3));
X(5) = W[5];
BODY_00_15(4, C, D, E, T, A, B, X(4));
X(6) = W[6];
BODY_00_15(5, B, C, D, E, T, A, X(5));
X(7) = W[7];
BODY_00_15(6, A, B, C, D, E, T, X(6));
X(8) = W[8];
BODY_00_15(7, T, A, B, C, D, E, X(7));
X(9) = W[9];
BODY_00_15(8, E, T, A, B, C, D, X(8));
X(10) = W[10];
BODY_00_15(9, D, E, T, A, B, C, X(9));
X(11) = W[11];
BODY_00_15(10, C, D, E, T, A, B, X(10));
X(12) = W[12];
BODY_00_15(11, B, C, D, E, T, A, X(11));
X(13) = W[13];
BODY_00_15(12, A, B, C, D, E, T, X(12));
X(14) = W[14];
BODY_00_15(13, T, A, B, C, D, E, X(13));
X(15) = W[15];
BODY_00_15(14, E, T, A, B, C, D, X(14));
BODY_00_15(15, D, E, T, A, B, C, X(15));
data += HASH_CBLOCK;
} else {
(void)HOST_c2l(data, l);
X(0) = l;
(void)HOST_c2l(data, l);
X(1) = l;
BODY_00_15(0, A, B, C, D, E, T, X(0));
(void)HOST_c2l(data, l);
X(2) = l;
BODY_00_15(1, T, A, B, C, D, E, X(1));
(void)HOST_c2l(data, l);
X(3) = l;
BODY_00_15(2, E, T, A, B, C, D, X(2));
(void)HOST_c2l(data, l);
X(4) = l;
BODY_00_15(3, D, E, T, A, B, C, X(3));
(void)HOST_c2l(data, l);
X(5) = l;
BODY_00_15(4, C, D, E, T, A, B, X(4));
(void)HOST_c2l(data, l);
X(6) = l;
BODY_00_15(5, B, C, D, E, T, A, X(5));
(void)HOST_c2l(data, l);
X(7) = l;
BODY_00_15(6, A, B, C, D, E, T, X(6));
(void)HOST_c2l(data, l);
X(8) = l;
BODY_00_15(7, T, A, B, C, D, E, X(7));
(void)HOST_c2l(data, l);
X(9) = l;
BODY_00_15(8, E, T, A, B, C, D, X(8));
(void)HOST_c2l(data, l);
X(10) = l;
BODY_00_15(9, D, E, T, A, B, C, X(9));
(void)HOST_c2l(data, l);
X(11) = l;
BODY_00_15(10, C, D, E, T, A, B, X(10));
(void)HOST_c2l(data, l);
X(12) = l;
BODY_00_15(11, B, C, D, E, T, A, X(11));
(void)HOST_c2l(data, l);
X(13) = l;
BODY_00_15(12, A, B, C, D, E, T, X(12));
(void)HOST_c2l(data, l);
X(14) = l;
BODY_00_15(13, T, A, B, C, D, E, X(13));
(void)HOST_c2l(data, l);
X(15) = l;
BODY_00_15(14, E, T, A, B, C, D, X(14));
BODY_00_15(15, D, E, T, A, B, C, X(15));
}
BODY_16_19(16, C, D, E, T, A, B, X(0), X(0), X(2), X(8), X(13));
BODY_16_19(17, B, C, D, E, T, A, X(1), X(1), X(3), X(9), X(14));
BODY_16_19(18, A, B, C, D, E, T, X(2), X(2), X(4), X(10), X(15));
BODY_16_19(19, T, A, B, C, D, E, X(3), X(3), X(5), X(11), X(0));
BODY_20_31(20, E, T, A, B, C, D, X(4), X(4), X(6), X(12), X(1));
BODY_20_31(21, D, E, T, A, B, C, X(5), X(5), X(7), X(13), X(2));
BODY_20_31(22, C, D, E, T, A, B, X(6), X(6), X(8), X(14), X(3));
BODY_20_31(23, B, C, D, E, T, A, X(7), X(7), X(9), X(15), X(4));
BODY_20_31(24, A, B, C, D, E, T, X(8), X(8), X(10), X(0), X(5));
BODY_20_31(25, T, A, B, C, D, E, X(9), X(9), X(11), X(1), X(6));
BODY_20_31(26, E, T, A, B, C, D, X(10), X(10), X(12), X(2), X(7));
BODY_20_31(27, D, E, T, A, B, C, X(11), X(11), X(13), X(3), X(8));
BODY_20_31(28, C, D, E, T, A, B, X(12), X(12), X(14), X(4), X(9));
BODY_20_31(29, B, C, D, E, T, A, X(13), X(13), X(15), X(5), X(10));
BODY_20_31(30, A, B, C, D, E, T, X(14), X(14), X(0), X(6), X(11));
BODY_20_31(31, T, A, B, C, D, E, X(15), X(15), X(1), X(7), X(12));
BODY_32_39(32, E, T, A, B, C, D, X(0), X(2), X(8), X(13));
BODY_32_39(33, D, E, T, A, B, C, X(1), X(3), X(9), X(14));
BODY_32_39(34, C, D, E, T, A, B, X(2), X(4), X(10), X(15));
BODY_32_39(35, B, C, D, E, T, A, X(3), X(5), X(11), X(0));
BODY_32_39(36, A, B, C, D, E, T, X(4), X(6), X(12), X(1));
BODY_32_39(37, T, A, B, C, D, E, X(5), X(7), X(13), X(2));
BODY_32_39(38, E, T, A, B, C, D, X(6), X(8), X(14), X(3));
BODY_32_39(39, D, E, T, A, B, C, X(7), X(9), X(15), X(4));
BODY_40_59(40, C, D, E, T, A, B, X(8), X(10), X(0), X(5));
BODY_40_59(41, B, C, D, E, T, A, X(9), X(11), X(1), X(6));
BODY_40_59(42, A, B, C, D, E, T, X(10), X(12), X(2), X(7));
BODY_40_59(43, T, A, B, C, D, E, X(11), X(13), X(3), X(8));
BODY_40_59(44, E, T, A, B, C, D, X(12), X(14), X(4), X(9));
BODY_40_59(45, D, E, T, A, B, C, X(13), X(15), X(5), X(10));
BODY_40_59(46, C, D, E, T, A, B, X(14), X(0), X(6), X(11));
BODY_40_59(47, B, C, D, E, T, A, X(15), X(1), X(7), X(12));
BODY_40_59(48, A, B, C, D, E, T, X(0), X(2), X(8), X(13));
BODY_40_59(49, T, A, B, C, D, E, X(1), X(3), X(9), X(14));
BODY_40_59(50, E, T, A, B, C, D, X(2), X(4), X(10), X(15));
BODY_40_59(51, D, E, T, A, B, C, X(3), X(5), X(11), X(0));
BODY_40_59(52, C, D, E, T, A, B, X(4), X(6), X(12), X(1));
BODY_40_59(53, B, C, D, E, T, A, X(5), X(7), X(13), X(2));
BODY_40_59(54, A, B, C, D, E, T, X(6), X(8), X(14), X(3));
BODY_40_59(55, T, A, B, C, D, E, X(7), X(9), X(15), X(4));
BODY_40_59(56, E, T, A, B, C, D, X(8), X(10), X(0), X(5));
BODY_40_59(57, D, E, T, A, B, C, X(9), X(11), X(1), X(6));
BODY_40_59(58, C, D, E, T, A, B, X(10), X(12), X(2), X(7));
BODY_40_59(59, B, C, D, E, T, A, X(11), X(13), X(3), X(8));
BODY_60_79(60, A, B, C, D, E, T, X(12), X(14), X(4), X(9));
BODY_60_79(61, T, A, B, C, D, E, X(13), X(15), X(5), X(10));
BODY_60_79(62, E, T, A, B, C, D, X(14), X(0), X(6), X(11));
BODY_60_79(63, D, E, T, A, B, C, X(15), X(1), X(7), X(12));
BODY_60_79(64, C, D, E, T, A, B, X(0), X(2), X(8), X(13));
BODY_60_79(65, B, C, D, E, T, A, X(1), X(3), X(9), X(14));
BODY_60_79(66, A, B, C, D, E, T, X(2), X(4), X(10), X(15));
BODY_60_79(67, T, A, B, C, D, E, X(3), X(5), X(11), X(0));
BODY_60_79(68, E, T, A, B, C, D, X(4), X(6), X(12), X(1));
BODY_60_79(69, D, E, T, A, B, C, X(5), X(7), X(13), X(2));
BODY_60_79(70, C, D, E, T, A, B, X(6), X(8), X(14), X(3));
BODY_60_79(71, B, C, D, E, T, A, X(7), X(9), X(15), X(4));
BODY_60_79(72, A, B, C, D, E, T, X(8), X(10), X(0), X(5));
BODY_60_79(73, T, A, B, C, D, E, X(9), X(11), X(1), X(6));
BODY_60_79(74, E, T, A, B, C, D, X(10), X(12), X(2), X(7));
BODY_60_79(75, D, E, T, A, B, C, X(11), X(13), X(3), X(8));
BODY_60_79(76, C, D, E, T, A, B, X(12), X(14), X(4), X(9));
BODY_60_79(77, B, C, D, E, T, A, X(13), X(15), X(5), X(10));
BODY_60_79(78, A, B, C, D, E, T, X(14), X(0), X(6), X(11));
BODY_60_79(79, T, A, B, C, D, E, X(15), X(1), X(7), X(12));
c->h0 = (c->h0 + E) & 0xffffffffL;
c->h1 = (c->h1 + T) & 0xffffffffL;
c->h2 = (c->h2 + A) & 0xffffffffL;
c->h3 = (c->h3 + B) & 0xffffffffL;
c->h4 = (c->h4 + C) & 0xffffffffL;
if (--num == 0)
break;
A = c->h0;
B = c->h1;
C = c->h2;
D = c->h3;
E = c->h4;
}
}
//MD4 Block data order setting
void __fastcall MD4_BlockDataOrder(
MD4_CTX *c,
const void *data_,
size_t num)
{
const unsigned char *data = (const unsigned char *)data_;
register uint32_t A = 0, B = 0, C = 0, D = 0, l = 0;
uint32_t XX0 = 0, XX1 = 0, XX2 = 0, XX3 = 0, XX4 = 0, XX5 = 0, XX6 = 0, XX7 = 0, XX8 = 0, XX9 = 0, XX10 = 0, XX11 = 0, XX12 = 0, XX13 = 0, XX14 = 0, XX15 = 0;
#define X(i) XX ## i
A = c->A;
B = c->B;
C = c->C;
D = c->D;
for (;num--;)
{
(void)HOST_c2l(data, l); X(0) = l;
(void)HOST_c2l(data, l); X(1) = l;
//Round 0
R0(A, B, C, D, X(0), 3, 0); (void)HOST_c2l(data, l); X(2) = l;
R0(D, A, B, C, X(1), 7, 0); (void)HOST_c2l(data, l); X(3) = l;
R0(C, D, A, B, X(2), 11, 0); (void)HOST_c2l(data, l); X(4) = l;
R0(B, C, D, A, X(3), 19, 0); (void)HOST_c2l(data, l); X(5) = l;
R0(A, B, C, D, X(4), 3, 0); (void)HOST_c2l(data, l); X(6) = l;
R0(D, A, B, C, X(5), 7, 0); (void)HOST_c2l(data, l); X(7) = l;
R0(C, D, A, B, X(6), 11, 0); (void)HOST_c2l(data, l); X(8) = l;
R0(B, C, D, A, X(7), 19, 0); (void)HOST_c2l(data, l); X(9) = l;
R0(A, B, C, D, X(8), 3, 0); (void)HOST_c2l(data, l); X(10) = l;
R0(D, A, B, C, X(9), 7, 0); (void)HOST_c2l(data, l); X(11) = l;
R0(C, D, A, B, X(10), 11, 0); (void)HOST_c2l(data, l); X(12) = l;
R0(B, C, D, A, X(11), 19, 0); (void)HOST_c2l(data, l); X(13) = l;
R0(A, B, C, D, X(12), 3, 0); (void)HOST_c2l(data, l); X(14) = l;
R0(D, A, B, C, X(13), 7, 0); (void)HOST_c2l(data, l); X(15) = l;
R0(C, D, A, B, X(14), 11, 0);
R0(B, C, D, A, X(15), 19, 0);
//Round 1
R1(A, B, C, D, X(0), 3, 0x5A827999L);
R1(D, A, B, C, X(4), 5, 0x5A827999L);
R1(C, D, A, B, X(8), 9, 0x5A827999L);
R1(B, C, D, A, X(12), 13, 0x5A827999L);
R1(A, B, C, D, X(1), 3, 0x5A827999L);
R1(D, A, B, C, X(5), 5, 0x5A827999L);
R1(C, D, A, B, X(9), 9, 0x5A827999L);
R1(B, C, D, A, X(13), 13, 0x5A827999L);
R1(A, B, C, D, X(2), 3, 0x5A827999L);
R1(D, A, B, C, X(6), 5, 0x5A827999L);
R1(C, D, A, B, X(10), 9, 0x5A827999L);
R1(B, C, D, A, X(14), 13, 0x5A827999L);
R1(A, B, C, D, X(3), 3, 0x5A827999L);
R1(D, A, B, C, X(7), 5, 0x5A827999L);
R1(C, D, A, B, X(11), 9, 0x5A827999L);
R1(B, C, D, A, X(15), 13, 0x5A827999L);
//Round 2
R2(A, B, C, D, X(0), 3, 0x6ED9EBA1L);
R2(D, A, B, C, X(8), 9, 0x6ED9EBA1L);
R2(C, D, A, B, X(4), 11, 0x6ED9EBA1L);
R2(B, C, D, A, X(12), 15, 0x6ED9EBA1L);
R2(A, B, C, D, X(2), 3, 0x6ED9EBA1L);
R2(D, A, B, C, X(10), 9, 0x6ED9EBA1L);
R2(C, D, A, B, X(6), 11, 0x6ED9EBA1L);
R2(B, C, D, A, X(14), 15, 0x6ED9EBA1L);
R2(A, B, C, D, X(1), 3, 0x6ED9EBA1L);
R2(D, A, B, C, X(9), 9, 0x6ED9EBA1L);
R2(C, D, A, B, X(5), 11, 0x6ED9EBA1L);
R2(B, C, D, A, X(13), 15, 0x6ED9EBA1L);
R2(A, B, C, D, X(3), 3, 0x6ED9EBA1L);
R2(D, A, B, C, X(11), 9, 0x6ED9EBA1L);
R2(C, D, A, B, X(7), 11, 0x6ED9EBA1L);
R2(B, C, D, A, X(15), 15, 0x6ED9EBA1L);
A = c->A += A;
B = c->B += B;
C = c->C += C;
D = c->D += D;
}
return;
}
void ripemd160_block_data_order (RIPEMD160_CTX *ctx, const void *p, size_t num)
{
const unsigned char *data=p;
register unsigned MD32_REG_T A,B,C,D,E;
unsigned MD32_REG_T a,b,c,d,e,l;
#ifndef MD32_XARRAY
/* See comment in crypto/sha/sha_locl.h for details. */
unsigned MD32_REG_T XX0, XX1, XX2, XX3, XX4, XX5, XX6, XX7,
XX8, XX9,XX10,XX11,XX12,XX13,XX14,XX15;
# define X(i) XX##i
#else
RIPEMD160_LONG XX[16];
# define X(i) XX[i]
#endif
for (;num--;)
{
A=ctx->A; B=ctx->B; C=ctx->C; D=ctx->D; E=ctx->E;
(void)HOST_c2l(data,l); X( 0)=l;(void)HOST_c2l(data,l); X( 1)=l;
RIP1(A,B,C,D,E,WL00,SL00); (void)HOST_c2l(data,l); X( 2)=l;
RIP1(E,A,B,C,D,WL01,SL01); (void)HOST_c2l(data,l); X( 3)=l;
RIP1(D,E,A,B,C,WL02,SL02); (void)HOST_c2l(data,l); X( 4)=l;
RIP1(C,D,E,A,B,WL03,SL03); (void)HOST_c2l(data,l); X( 5)=l;
RIP1(B,C,D,E,A,WL04,SL04); (void)HOST_c2l(data,l); X( 6)=l;
RIP1(A,B,C,D,E,WL05,SL05); (void)HOST_c2l(data,l); X( 7)=l;
RIP1(E,A,B,C,D,WL06,SL06); (void)HOST_c2l(data,l); X( 8)=l;
RIP1(D,E,A,B,C,WL07,SL07); (void)HOST_c2l(data,l); X( 9)=l;
RIP1(C,D,E,A,B,WL08,SL08); (void)HOST_c2l(data,l); X(10)=l;
RIP1(B,C,D,E,A,WL09,SL09); (void)HOST_c2l(data,l); X(11)=l;
RIP1(A,B,C,D,E,WL10,SL10); (void)HOST_c2l(data,l); X(12)=l;
RIP1(E,A,B,C,D,WL11,SL11); (void)HOST_c2l(data,l); X(13)=l;
RIP1(D,E,A,B,C,WL12,SL12); (void)HOST_c2l(data,l); X(14)=l;
RIP1(C,D,E,A,B,WL13,SL13); (void)HOST_c2l(data,l); X(15)=l;
RIP1(B,C,D,E,A,WL14,SL14);
RIP1(A,B,C,D,E,WL15,SL15);
RIP2(E,A,B,C,D,WL16,SL16,KL1);
RIP2(D,E,A,B,C,WL17,SL17,KL1);
RIP2(C,D,E,A,B,WL18,SL18,KL1);
RIP2(B,C,D,E,A,WL19,SL19,KL1);
RIP2(A,B,C,D,E,WL20,SL20,KL1);
RIP2(E,A,B,C,D,WL21,SL21,KL1);
RIP2(D,E,A,B,C,WL22,SL22,KL1);
RIP2(C,D,E,A,B,WL23,SL23,KL1);
RIP2(B,C,D,E,A,WL24,SL24,KL1);
RIP2(A,B,C,D,E,WL25,SL25,KL1);
RIP2(E,A,B,C,D,WL26,SL26,KL1);
RIP2(D,E,A,B,C,WL27,SL27,KL1);
RIP2(C,D,E,A,B,WL28,SL28,KL1);
RIP2(B,C,D,E,A,WL29,SL29,KL1);
RIP2(A,B,C,D,E,WL30,SL30,KL1);
RIP2(E,A,B,C,D,WL31,SL31,KL1);
RIP3(D,E,A,B,C,WL32,SL32,KL2);
RIP3(C,D,E,A,B,WL33,SL33,KL2);
RIP3(B,C,D,E,A,WL34,SL34,KL2);
RIP3(A,B,C,D,E,WL35,SL35,KL2);
RIP3(E,A,B,C,D,WL36,SL36,KL2);
RIP3(D,E,A,B,C,WL37,SL37,KL2);
RIP3(C,D,E,A,B,WL38,SL38,KL2);
RIP3(B,C,D,E,A,WL39,SL39,KL2);
RIP3(A,B,C,D,E,WL40,SL40,KL2);
RIP3(E,A,B,C,D,WL41,SL41,KL2);
RIP3(D,E,A,B,C,WL42,SL42,KL2);
RIP3(C,D,E,A,B,WL43,SL43,KL2);
RIP3(B,C,D,E,A,WL44,SL44,KL2);
RIP3(A,B,C,D,E,WL45,SL45,KL2);
RIP3(E,A,B,C,D,WL46,SL46,KL2);
RIP3(D,E,A,B,C,WL47,SL47,KL2);
RIP4(C,D,E,A,B,WL48,SL48,KL3);
RIP4(B,C,D,E,A,WL49,SL49,KL3);
RIP4(A,B,C,D,E,WL50,SL50,KL3);
RIP4(E,A,B,C,D,WL51,SL51,KL3);
RIP4(D,E,A,B,C,WL52,SL52,KL3);
RIP4(C,D,E,A,B,WL53,SL53,KL3);
RIP4(B,C,D,E,A,WL54,SL54,KL3);
RIP4(A,B,C,D,E,WL55,SL55,KL3);
RIP4(E,A,B,C,D,WL56,SL56,KL3);
RIP4(D,E,A,B,C,WL57,SL57,KL3);
RIP4(C,D,E,A,B,WL58,SL58,KL3);
RIP4(B,C,D,E,A,WL59,SL59,KL3);
RIP4(A,B,C,D,E,WL60,SL60,KL3);
RIP4(E,A,B,C,D,WL61,SL61,KL3);
RIP4(D,E,A,B,C,WL62,SL62,KL3);
RIP4(C,D,E,A,B,WL63,SL63,KL3);
RIP5(B,C,D,E,A,WL64,SL64,KL4);
RIP5(A,B,C,D,E,WL65,SL65,KL4);
RIP5(E,A,B,C,D,WL66,SL66,KL4);
RIP5(D,E,A,B,C,WL67,SL67,KL4);
RIP5(C,D,E,A,B,WL68,SL68,KL4);
RIP5(B,C,D,E,A,WL69,SL69,KL4);
RIP5(A,B,C,D,E,WL70,SL70,KL4);
RIP5(E,A,B,C,D,WL71,SL71,KL4);
RIP5(D,E,A,B,C,WL72,SL72,KL4);
RIP5(C,D,E,A,B,WL73,SL73,KL4);
RIP5(B,C,D,E,A,WL74,SL74,KL4);
RIP5(A,B,C,D,E,WL75,SL75,KL4);
RIP5(E,A,B,C,D,WL76,SL76,KL4);
RIP5(D,E,A,B,C,WL77,SL77,KL4);
RIP5(C,D,E,A,B,WL78,SL78,KL4);
RIP5(B,C,D,E,A,WL79,SL79,KL4);
a=A; b=B; c=C; d=D; e=E;
/* Do other half */
A=ctx->A; B=ctx->B; C=ctx->C; D=ctx->D; E=ctx->E;
RIP5(A,B,C,D,E,WR00,SR00,KR0);
RIP5(E,A,B,C,D,WR01,SR01,KR0);
RIP5(D,E,A,B,C,WR02,SR02,KR0);
RIP5(C,D,E,A,B,WR03,SR03,KR0);
RIP5(B,C,D,E,A,WR04,SR04,KR0);
RIP5(A,B,C,D,E,WR05,SR05,KR0);
RIP5(E,A,B,C,D,WR06,SR06,KR0);
RIP5(D,E,A,B,C,WR07,SR07,KR0);
RIP5(C,D,E,A,B,WR08,SR08,KR0);
RIP5(B,C,D,E,A,WR09,SR09,KR0);
RIP5(A,B,C,D,E,WR10,SR10,KR0);
RIP5(E,A,B,C,D,WR11,SR11,KR0);
RIP5(D,E,A,B,C,WR12,SR12,KR0);
RIP5(C,D,E,A,B,WR13,SR13,KR0);
RIP5(B,C,D,E,A,WR14,SR14,KR0);
RIP5(A,B,C,D,E,WR15,SR15,KR0);
RIP4(E,A,B,C,D,WR16,SR16,KR1);
RIP4(D,E,A,B,C,WR17,SR17,KR1);
RIP4(C,D,E,A,B,WR18,SR18,KR1);
RIP4(B,C,D,E,A,WR19,SR19,KR1);
RIP4(A,B,C,D,E,WR20,SR20,KR1);
RIP4(E,A,B,C,D,WR21,SR21,KR1);
RIP4(D,E,A,B,C,WR22,SR22,KR1);
RIP4(C,D,E,A,B,WR23,SR23,KR1);
RIP4(B,C,D,E,A,WR24,SR24,KR1);
RIP4(A,B,C,D,E,WR25,SR25,KR1);
RIP4(E,A,B,C,D,WR26,SR26,KR1);
RIP4(D,E,A,B,C,WR27,SR27,KR1);
RIP4(C,D,E,A,B,WR28,SR28,KR1);
RIP4(B,C,D,E,A,WR29,SR29,KR1);
RIP4(A,B,C,D,E,WR30,SR30,KR1);
RIP4(E,A,B,C,D,WR31,SR31,KR1);
RIP3(D,E,A,B,C,WR32,SR32,KR2);
RIP3(C,D,E,A,B,WR33,SR33,KR2);
RIP3(B,C,D,E,A,WR34,SR34,KR2);
RIP3(A,B,C,D,E,WR35,SR35,KR2);
RIP3(E,A,B,C,D,WR36,SR36,KR2);
RIP3(D,E,A,B,C,WR37,SR37,KR2);
RIP3(C,D,E,A,B,WR38,SR38,KR2);
RIP3(B,C,D,E,A,WR39,SR39,KR2);
RIP3(A,B,C,D,E,WR40,SR40,KR2);
RIP3(E,A,B,C,D,WR41,SR41,KR2);
RIP3(D,E,A,B,C,WR42,SR42,KR2);
RIP3(C,D,E,A,B,WR43,SR43,KR2);
RIP3(B,C,D,E,A,WR44,SR44,KR2);
RIP3(A,B,C,D,E,WR45,SR45,KR2);
RIP3(E,A,B,C,D,WR46,SR46,KR2);
RIP3(D,E,A,B,C,WR47,SR47,KR2);
RIP2(C,D,E,A,B,WR48,SR48,KR3);
RIP2(B,C,D,E,A,WR49,SR49,KR3);
RIP2(A,B,C,D,E,WR50,SR50,KR3);
RIP2(E,A,B,C,D,WR51,SR51,KR3);
RIP2(D,E,A,B,C,WR52,SR52,KR3);
RIP2(C,D,E,A,B,WR53,SR53,KR3);
RIP2(B,C,D,E,A,WR54,SR54,KR3);
RIP2(A,B,C,D,E,WR55,SR55,KR3);
RIP2(E,A,B,C,D,WR56,SR56,KR3);
RIP2(D,E,A,B,C,WR57,SR57,KR3);
RIP2(C,D,E,A,B,WR58,SR58,KR3);
RIP2(B,C,D,E,A,WR59,SR59,KR3);
RIP2(A,B,C,D,E,WR60,SR60,KR3);
RIP2(E,A,B,C,D,WR61,SR61,KR3);
RIP2(D,E,A,B,C,WR62,SR62,KR3);
RIP2(C,D,E,A,B,WR63,SR63,KR3);
RIP1(B,C,D,E,A,WR64,SR64);
RIP1(A,B,C,D,E,WR65,SR65);
RIP1(E,A,B,C,D,WR66,SR66);
RIP1(D,E,A,B,C,WR67,SR67);
RIP1(C,D,E,A,B,WR68,SR68);
RIP1(B,C,D,E,A,WR69,SR69);
RIP1(A,B,C,D,E,WR70,SR70);
RIP1(E,A,B,C,D,WR71,SR71);
RIP1(D,E,A,B,C,WR72,SR72);
RIP1(C,D,E,A,B,WR73,SR73);
RIP1(B,C,D,E,A,WR74,SR74);
RIP1(A,B,C,D,E,WR75,SR75);
RIP1(E,A,B,C,D,WR76,SR76);
RIP1(D,E,A,B,C,WR77,SR77);
RIP1(C,D,E,A,B,WR78,SR78);
RIP1(B,C,D,E,A,WR79,SR79);
D =ctx->B+c+D;
ctx->B=ctx->C+d+E;
ctx->C=ctx->D+e+A;
ctx->D=ctx->E+a+B;
ctx->E=ctx->A+b+C;
ctx->A=D;
}
}
static void sha256_block (SHA256_CTX *ctx, const void *in, size_t num, int host)
{
uint32_t a,b,c,d,e,f,g,h,s0,s1,T1;
uint32_t X[16];
int i;
const unsigned char *data=in;
while (num--) {
a = ctx->h[0]; b = ctx->h[1]; c = ctx->h[2]; d = ctx->h[3];
e = ctx->h[4]; f = ctx->h[5]; g = ctx->h[6]; h = ctx->h[7];
if (host)
{
const uint32_t *W=(const uint32_t *)data;
T1 = X[0] = W[0]; ROUND_00_15(0,a,b,c,d,e,f,g,h);
T1 = X[1] = W[1]; ROUND_00_15(1,h,a,b,c,d,e,f,g);
T1 = X[2] = W[2]; ROUND_00_15(2,g,h,a,b,c,d,e,f);
T1 = X[3] = W[3]; ROUND_00_15(3,f,g,h,a,b,c,d,e);
T1 = X[4] = W[4]; ROUND_00_15(4,e,f,g,h,a,b,c,d);
T1 = X[5] = W[5]; ROUND_00_15(5,d,e,f,g,h,a,b,c);
T1 = X[6] = W[6]; ROUND_00_15(6,c,d,e,f,g,h,a,b);
T1 = X[7] = W[7]; ROUND_00_15(7,b,c,d,e,f,g,h,a);
T1 = X[8] = W[8]; ROUND_00_15(8,a,b,c,d,e,f,g,h);
T1 = X[9] = W[9]; ROUND_00_15(9,h,a,b,c,d,e,f,g);
T1 = X[10] = W[10]; ROUND_00_15(10,g,h,a,b,c,d,e,f);
T1 = X[11] = W[11]; ROUND_00_15(11,f,g,h,a,b,c,d,e);
T1 = X[12] = W[12]; ROUND_00_15(12,e,f,g,h,a,b,c,d);
T1 = X[13] = W[13]; ROUND_00_15(13,d,e,f,g,h,a,b,c);
T1 = X[14] = W[14]; ROUND_00_15(14,c,d,e,f,g,h,a,b);
T1 = X[15] = W[15]; ROUND_00_15(15,b,c,d,e,f,g,h,a);
data += SHA256_CBLOCK;
}
else
{
uint32_t l;
HOST_c2l(data,l); T1 = X[0] = l; ROUND_00_15(0,a,b,c,d,e,f,g,h);
HOST_c2l(data,l); T1 = X[1] = l; ROUND_00_15(1,h,a,b,c,d,e,f,g);
HOST_c2l(data,l); T1 = X[2] = l; ROUND_00_15(2,g,h,a,b,c,d,e,f);
HOST_c2l(data,l); T1 = X[3] = l; ROUND_00_15(3,f,g,h,a,b,c,d,e);
HOST_c2l(data,l); T1 = X[4] = l; ROUND_00_15(4,e,f,g,h,a,b,c,d);
HOST_c2l(data,l); T1 = X[5] = l; ROUND_00_15(5,d,e,f,g,h,a,b,c);
HOST_c2l(data,l); T1 = X[6] = l; ROUND_00_15(6,c,d,e,f,g,h,a,b);
HOST_c2l(data,l); T1 = X[7] = l; ROUND_00_15(7,b,c,d,e,f,g,h,a);
HOST_c2l(data,l); T1 = X[8] = l; ROUND_00_15(8,a,b,c,d,e,f,g,h);
HOST_c2l(data,l); T1 = X[9] = l; ROUND_00_15(9,h,a,b,c,d,e,f,g);
HOST_c2l(data,l); T1 = X[10] = l; ROUND_00_15(10,g,h,a,b,c,d,e,f);
HOST_c2l(data,l); T1 = X[11] = l; ROUND_00_15(11,f,g,h,a,b,c,d,e);
HOST_c2l(data,l); T1 = X[12] = l; ROUND_00_15(12,e,f,g,h,a,b,c,d);
HOST_c2l(data,l); T1 = X[13] = l; ROUND_00_15(13,d,e,f,g,h,a,b,c);
HOST_c2l(data,l); T1 = X[14] = l; ROUND_00_15(14,c,d,e,f,g,h,a,b);
HOST_c2l(data,l); T1 = X[15] = l; ROUND_00_15(15,b,c,d,e,f,g,h,a);
}
for (i=16;i<64;i+=8)
{
ROUND_16_63(i+0,a,b,c,d,e,f,g,h,X);
ROUND_16_63(i+1,h,a,b,c,d,e,f,g,X);
ROUND_16_63(i+2,g,h,a,b,c,d,e,f,X);
ROUND_16_63(i+3,f,g,h,a,b,c,d,e,X);
ROUND_16_63(i+4,e,f,g,h,a,b,c,d,X);
ROUND_16_63(i+5,d,e,f,g,h,a,b,c,X);
ROUND_16_63(i+6,c,d,e,f,g,h,a,b,X);
ROUND_16_63(i+7,b,c,d,e,f,g,h,a,X);
}
ctx->h[0] += a; ctx->h[1] += b; ctx->h[2] += c; ctx->h[3] += d;
ctx->h[4] += e; ctx->h[5] += f; ctx->h[6] += g; ctx->h[7] += h;
}
}
