static void sha256_transform(uint32_t *state, const uint8_t buffer[64])
{
unsigned int i, a, b, c, d, e, f, g, h;
uint32_t block[64];
uint32_t T1;
a = state[0];
b = state[1];
c = state[2];
d = state[3];
e = state[4];
f = state[5];
g = state[6];
h = state[7];
#if CONFIG_SMALL
for (i = 0; i < 64; i++) {
uint32_t T2;
if (i < 16)
T1 = blk0(i);
else
T1 = blk(i);
T1 += h + Sigma1_256(e) + Ch(e, f, g) + K256[i];
T2 = Sigma0_256(a) + Maj(a, b, c);
h = g;
g = f;
f = e;
e = d + T1;
d = c;
c = b;
b = a;
a = T1 + T2;
}
#else
for (i = 0; i < 16;) {
ROUND256_0_TO_15(a, b, c, d, e, f, g, h);
ROUND256_0_TO_15(h, a, b, c, d, e, f, g);
ROUND256_0_TO_15(g, h, a, b, c, d, e, f);
ROUND256_0_TO_15(f, g, h, a, b, c, d, e);
ROUND256_0_TO_15(e, f, g, h, a, b, c, d);
ROUND256_0_TO_15(d, e, f, g, h, a, b, c);
ROUND256_0_TO_15(c, d, e, f, g, h, a, b);
ROUND256_0_TO_15(b, c, d, e, f, g, h, a);
}
for (; i < 64;) {
ROUND256_16_TO_63(a, b, c, d, e, f, g, h);
ROUND256_16_TO_63(h, a, b, c, d, e, f, g);
ROUND256_16_TO_63(g, h, a, b, c, d, e, f);
ROUND256_16_TO_63(f, g, h, a, b, c, d, e);
ROUND256_16_TO_63(e, f, g, h, a, b, c, d);
ROUND256_16_TO_63(d, e, f, g, h, a, b, c);
ROUND256_16_TO_63(c, d, e, f, g, h, a, b);
ROUND256_16_TO_63(b, c, d, e, f, g, h, a);
}
#endif
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 sha512_transform(uint64_t *state, const uint8_t buffer[128])
{
uint64_t a, b, c, d, e, f, g, h;
uint64_t block[80];
uint64_t T1;
int i;
a = state[0];
b = state[1];
c = state[2];
d = state[3];
e = state[4];
f = state[5];
g = state[6];
h = state[7];
#if CONFIG_SMALL
for (i = 0; i < 80; i++) {
uint64_t T2;
if (i < 16)
T1 = blk0(i);
else
T1 = blk(i);
T1 += h + Sigma1_512(e) + Ch(e, f, g) + K512[i];
T2 = Sigma0_512(a) + Maj(a, b, c);
h = g;
g = f;
f = e;
e = d + T1;
d = c;
c = b;
b = a;
a = T1 + T2;
}
#else
#define R512_0 \
ROUND512_0_TO_15(a, b, c, d, e, f, g, h); \
ROUND512_0_TO_15(h, a, b, c, d, e, f, g); \
ROUND512_0_TO_15(g, h, a, b, c, d, e, f); \
ROUND512_0_TO_15(f, g, h, a, b, c, d, e); \
ROUND512_0_TO_15(e, f, g, h, a, b, c, d); \
ROUND512_0_TO_15(d, e, f, g, h, a, b, c); \
ROUND512_0_TO_15(c, d, e, f, g, h, a, b); \
ROUND512_0_TO_15(b, c, d, e, f, g, h, a)
i = 0;
R512_0; R512_0;
#define R512_16 \
ROUND512_16_TO_80(a, b, c, d, e, f, g, h); \
ROUND512_16_TO_80(h, a, b, c, d, e, f, g); \
ROUND512_16_TO_80(g, h, a, b, c, d, e, f); \
ROUND512_16_TO_80(f, g, h, a, b, c, d, e); \
ROUND512_16_TO_80(e, f, g, h, a, b, c, d); \
ROUND512_16_TO_80(d, e, f, g, h, a, b, c); \
ROUND512_16_TO_80(c, d, e, f, g, h, a, b); \
ROUND512_16_TO_80(b, c, d, e, f, g, h, a)
R512_16; R512_16; R512_16; R512_16;
R512_16; R512_16; R512_16; R512_16;
#endif
state[0] += a;
state[1] += b;
state[2] += c;
state[3] += d;
state[4] += e;
state[5] += f;
state[6] += g;
state[7] += h;
}
/* transform one 512bit block. this is the core of the algorithm. */
static void
sha1_transform(uint32_t state[5], char buf[SHA1_BLOCKSIZE])
{
uint32_t a, b, c, d, e;
uint32_t *block = (uint32_t *)buf;
#ifdef SHA1_SHORTCODE
uint8_t i;
#endif
/* copy state to working vars */
a = state[0];
b = state[1];
c = state[2];
d = state[3];
e = state[4];
#ifdef SHA1_SHORTCODE
for (i = 0; i < 80; i++) {
uint32_t t;
if (i < 20)
t = ((b & (c ^ d)) ^ d) + 0x5A827999;
else if (i < 40)
t = (b ^ c ^ d) + 0x6ED9EBA1;
else if (i < 60)
t = (((b | c) & d) | (b & c)) + 0x8F1BBCDC;
else
t = (b ^ c ^ d) + 0xCA62C1D6;
t += (i < 16) ? blk0(i) : blk(i);
t += e + rol(a, 5);
e = d;
d = c;
c = rol(b, 30);
b = a;
a = t;
}
#else
/* R0 and R1, R2, R3, R4 are the different operations used in SHA1 */
#define R0(v,w,x,y,z,i) \
z += ((w&(x^y))^y) + blk0(i) + 0x5A827999 + rol(v, 5); w = rol(w, 30)
#define R1(v,w,x,y,z,i) \
z += ((w&(x^y))^y) + blk(i) + 0x5A827999 + rol(v, 5); w = rol(w, 30)
#define R2(v,w,x,y,z,i) \
z += (w^x^y) + blk(i) + 0x6ED9EBA1 + rol(v, 5); w = rol(w, 30)
#define R3(v,w,x,y,z,i) \
z += (((w|x)&y)|(w&x)) + blk(i) + 0x8F1BBCDC + rol(v, 5); w = rol(w, 30)
#define R4(v,w,x,y,z,i) \
z += (w^x^y) + blk(i) + 0xCA62C1D6 + rol(v, 5); w = rol(w, 30)
/* 4 rounds of 20 operations each. loop unrolled. */
R0(a,b,c,d,e, 0); R0(e,a,b,c,d, 1); R0(d,e,a,b,c, 2); R0(c,d,e,a,b, 3);
R0(b,c,d,e,a, 4); R0(a,b,c,d,e, 5); R0(e,a,b,c,d, 6); R0(d,e,a,b,c, 7);
R0(c,d,e,a,b, 8); R0(b,c,d,e,a, 9); R0(a,b,c,d,e,10); R0(e,a,b,c,d,11);
R0(d,e,a,b,c,12); R0(c,d,e,a,b,13); R0(b,c,d,e,a,14); R0(a,b,c,d,e,15);
R1(e,a,b,c,d,16); R1(d,e,a,b,c,17); R1(c,d,e,a,b,18); R1(b,c,d,e,a,19);
R2(a,b,c,d,e,20); R2(e,a,b,c,d,21); R2(d,e,a,b,c,22); R2(c,d,e,a,b,23);
R2(b,c,d,e,a,24); R2(a,b,c,d,e,25); R2(e,a,b,c,d,26); R2(d,e,a,b,c,27);
R2(c,d,e,a,b,28); R2(b,c,d,e,a,29); R2(a,b,c,d,e,30); R2(e,a,b,c,d,31);
R2(d,e,a,b,c,32); R2(c,d,e,a,b,33); R2(b,c,d,e,a,34); R2(a,b,c,d,e,35);
R2(e,a,b,c,d,36); R2(d,e,a,b,c,37); R2(c,d,e,a,b,38); R2(b,c,d,e,a,39);
R3(a,b,c,d,e,40); R3(e,a,b,c,d,41); R3(d,e,a,b,c,42); R3(c,d,e,a,b,43);
R3(b,c,d,e,a,44); R3(a,b,c,d,e,45); R3(e,a,b,c,d,46); R3(d,e,a,b,c,47);
R3(c,d,e,a,b,48); R3(b,c,d,e,a,49); R3(a,b,c,d,e,50); R3(e,a,b,c,d,51);
R3(d,e,a,b,c,52); R3(c,d,e,a,b,53); R3(b,c,d,e,a,54); R3(a,b,c,d,e,55);
R3(e,a,b,c,d,56); R3(d,e,a,b,c,57); R3(c,d,e,a,b,58); R3(b,c,d,e,a,59);
R4(a,b,c,d,e,60); R4(e,a,b,c,d,61); R4(d,e,a,b,c,62); R4(c,d,e,a,b,63);
R4(b,c,d,e,a,64); R4(a,b,c,d,e,65); R4(e,a,b,c,d,66); R4(d,e,a,b,c,67);
R4(c,d,e,a,b,68); R4(b,c,d,e,a,69); R4(a,b,c,d,e,70); R4(e,a,b,c,d,71);
R4(d,e,a,b,c,72); R4(c,d,e,a,b,73); R4(b,c,d,e,a,74); R4(a,b,c,d,e,75);
R4(e,a,b,c,d,76); R4(d,e,a,b,c,77); R4(c,d,e,a,b,78); R4(b,c,d,e,a,79);
#endif
/* add the working vars back into state */
state[0] += a;
state[1] += b;
state[2] += c;
state[3] += d;
state[4] += e;
}
