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 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];
T1 = X[0] = from_be_u32_ptr(data);
ROUND_00_15(0, a, b, c, d, e, f, g, h);
T1 = X[1] = from_be_u32_ptr(data + (4 * 1));
ROUND_00_15(1, h, a, b, c, d, e, f, g);
T1 = X[2] = from_be_u32_ptr(data + (4 * 2));
ROUND_00_15(2, g, h, a, b, c, d, e, f);
T1 = X[3] = from_be_u32_ptr(data + (4 * 3));
ROUND_00_15(3, f, g, h, a, b, c, d, e);
T1 = X[4] = from_be_u32_ptr(data + (4 * 4));
ROUND_00_15(4, e, f, g, h, a, b, c, d);
T1 = X[5] = from_be_u32_ptr(data + (4 * 5));
ROUND_00_15(5, d, e, f, g, h, a, b, c);
T1 = X[6] = from_be_u32_ptr(data + (4 * 6));
ROUND_00_15(6, c, d, e, f, g, h, a, b);
T1 = X[7] = from_be_u32_ptr(data + (4 * 7));
ROUND_00_15(7, b, c, d, e, f, g, h, a);
T1 = X[8] = from_be_u32_ptr(data + (4 * 8));
ROUND_00_15(8, a, b, c, d, e, f, g, h);
T1 = X[9] = from_be_u32_ptr(data + (4 * 9));
ROUND_00_15(9, h, a, b, c, d, e, f, g);
T1 = X[10] = from_be_u32_ptr(data + (4 * 10));
ROUND_00_15(10, g, h, a, b, c, d, e, f);
T1 = X[11] = from_be_u32_ptr(data + (4 * 11));
ROUND_00_15(11, f, g, h, a, b, c, d, e);
T1 = X[12] = from_be_u32_ptr(data + (4 * 12));
ROUND_00_15(12, e, f, g, h, a, b, c, d);
T1 = X[13] = from_be_u32_ptr(data + (4 * 13));
ROUND_00_15(13, d, e, f, g, h, a, b, c);
T1 = X[14] = from_be_u32_ptr(data + (4 * 14));
ROUND_00_15(14, c, d, e, f, g, h, a, b);
T1 = X[15] = from_be_u32_ptr(data + (4 * 15));
ROUND_00_15(15, b, c, d, e, f, g, h, a);
data += 64;
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 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 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 (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;
}
}