static void Transform(Sha256* sha256)
{
word32 S[8], W[64], t0, t1;
int i;
/* Copy context->state[] to working vars */
for (i = 0; i < 8; i++)
S[i] = sha256->digest[i];
for (i = 0; i < 16; i++)
W[i] = sha256->buffer[i];
for (i = 16; i < 64; i++)
W[i] = Gamma1(W[i-2]) + W[i-7] + Gamma0(W[i-15]) + W[i-16];
for (i = 0; i < 64; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
/* Add the working vars back into digest state[] */
for (i = 0; i < 8; i++) {
sha256->digest[i] += S[i];
}
}
/* compress 512-bits */
static int sha256_compress(struct 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++)
W[i] = WPA_GET_BE32(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];
}
return 0;
}
void sha512_compress(psDigestContext_t * md, unsigned char *buf)
#endif
{
uint64 S[8], W[80], t0, t1;
int i;
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = md->sha512.state[i];
}
/* copy the state into 1024-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD64H(W[i], buf + (8*i));
}
/* fill W[16..79] */
for (i = 16; i < 80; i++) {
W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
}
/* Compress */
#ifndef PS_SHA512_IMPROVE_PERF_INCREASE_CODESIZE
for (i = 0; i < 80; 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;
}
#else
#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 < 80; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
#endif /* PS_SHA512_IMPROVE_PERF_INCREASE_CODESIZE */
/* feedback */
for (i = 0; i < 8; i++) {
md->sha512.state[i] = md->sha512.state[i] + S[i];
}
}
///////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// 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];
}
}
/* compress 1024-bits */
static int sha512_compress(sha512_context *md, unsigned char *buf)
{
u64 S[8], W[80], t0, t1;
int i;
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = md->state[i];
}
/* copy the state into 1024-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD64H(W[i], buf + (8*i));
}
/* fill W[16..79] */
for (i = 16; i < 80; 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 < 80; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
#undef RND
/* feedback */
for (i = 0; i < 8; i++) {
md->state[i] = md->state[i] + S[i];
}
return 0;
}
static int Transform(Sha256* sha256)
{
word32 S[8], t0, t1;
int i;
#ifdef WOLFSSL_SMALL_STACK
word32* W;
W = (word32*) XMALLOC(sizeof(word32) * 64, NULL, DYNAMIC_TYPE_TMP_BUFFER);
if (W == NULL)
return MEMORY_E;
#else
word32 W[64];
#endif
/* Copy context->state[] to working vars */
for (i = 0; i < 8; i++)
S[i] = sha256->digest[i];
for (i = 0; i < 16; i++)
W[i] = sha256->buffer[i];
for (i = 16; i < 64; i++)
W[i] = Gamma1(W[i-2]) + W[i-7] + Gamma0(W[i-15]) + W[i-16];
for (i = 0; i < 64; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
/* Add the working vars back into digest state[] */
for (i = 0; i < 8; i++) {
sha256->digest[i] += S[i];
}
#ifdef WOLFSSL_SMALL_STACK
XFREE(W, NULL, DYNAMIC_TYPE_TMP_BUFFER);
#endif
return 0;
}
/* compress 1024-bits */
static void sha512_compress(sha512_ctx *ctx, const unsigned char *buf)
{
u64 S[8], W[80], t0, t1;
int i;
/* copy state into S */
memcpy(S, ctx->hash, sizeof(S));
/* copy the state into 1024-bits into W[0..15] */
for (i = 0; i < 16; i++) {
W[i] = BE64(p64(buf)[i]);
}
/* fill W[16..79] */
for (i = 16; i < 80; 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 < 80; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
ctx->hash[0] += S[0]; ctx->hash[1] += S[1];
ctx->hash[2] += S[2]; ctx->hash[3] += S[3];
ctx->hash[4] += S[4]; ctx->hash[5] += S[5];
ctx->hash[6] += S[6]; ctx->hash[7] += S[7];
/* prevent leaks */
burn(&S, sizeof(S));
burn(&W, sizeof(W));
}
/* compress 1024-bits */
void sha512_transform(SilcUInt64 *state, unsigned char *buf)
{
ulong64 S[8], W[80], t0, t1;
int i;
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = state[i];
}
/* copy the state into 1024-bits into W[0..15] */
for (i = 0; i < 16; i++)
SILC_GET64_MSB(W[i], buf + (8 * i));
/* fill W[16..79] */
for (i = 16; i < 80; 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 < 80; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
/* feedback */
for (i = 0; i < 8; i++) {
state[i] = state[i] + S[i];
}
}
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 int Transform(Sha256 *sha256)
{
word32 S[8], t0, t1;
int i;
word32 *W;
W = (word32 *)kalloc(sizeof(word32) * 64);
if (W == NULL)
return -1;
/* Copy context->state[] to working vars */
for (i = 0; i < 8; i++)
S[i] = sha256->digest[i];
for (i = 0; i < 16; i++)
W[i] = sha256->buffer[i];
for (i = 16; i < 64; i++)
W[i] = Gamma1(W[i-2]) + W[i-7] + Gamma0(W[i-15]) + W[i-16];
for (i = 0; i < 64; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
/* Add the working vars back into digest state[] */
for (i = 0; i < 8; i++) {
sha256->digest[i] += S[i];
}
kfree(W);
return 0;
}
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 int sha512_compress(hash_state * md, unsigned char *buf)
#endif
{
ulong64 S[8], W[80], t0, t1;
int i;
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = md->sha512.state[i];
}
/* copy the state into 1024-bits into W[0..15] */
for (i = 0; i < 16; i++) {
LOAD64H(W[i], buf + (8*i));
}
/* fill W[16..79] */
for (i = 16; i < 80; i++) {
W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
}
/* Compress */
#ifdef LTC_SMALL_CODE
for (i = 0; i < 80; 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;
}
#else
#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 < 80; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
#endif
/* feedback */
for (i = 0; i < 8; i++) {
md->sha512.state[i] = md->sha512.state[i] + S[i];
}
return CRYPT_OK;
}
/* compress 1024-bits */
void ccsha512_ltc_compress(ccdigest_state_t state, unsigned long nblocks, const void *in)
{
uint64_t S[8], W[80], t0, t1;
int i;
uint64_t *s = ccdigest_u64(state);
const unsigned char *buf = in;
while(nblocks--) {
/* copy state into S */
for (i = 0; i < 8; i++) {
S[i] = s[i];
}
/* copy the state into 1024-bits into W[0..15] */
for (i = 0; i < 16; i++) {
CC_LOAD64_BE(W[i], buf + (8*i));
}
/* fill W[16..79] */
for (i = 16; i < 80; i++) {
W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];
}
/* Compress */
#ifdef CC_SMALL_CODE
for (i = 0; i < 80; 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;
}
#else
#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 < 80; i += 8) {
RND(S[0],S[1],S[2],S[3],S[4],S[5],S[6],S[7],i+0);
RND(S[7],S[0],S[1],S[2],S[3],S[4],S[5],S[6],i+1);
RND(S[6],S[7],S[0],S[1],S[2],S[3],S[4],S[5],i+2);
RND(S[5],S[6],S[7],S[0],S[1],S[2],S[3],S[4],i+3);
RND(S[4],S[5],S[6],S[7],S[0],S[1],S[2],S[3],i+4);
RND(S[3],S[4],S[5],S[6],S[7],S[0],S[1],S[2],i+5);
RND(S[2],S[3],S[4],S[5],S[6],S[7],S[0],S[1],i+6);
RND(S[1],S[2],S[3],S[4],S[5],S[6],S[7],S[0],i+7);
}
#endif
/* feedback */
for (i = 0; i < 8; i++) {
s[i] = s[i] + S[i];
}
buf+=CCSHA512_BLOCK_SIZE;
}
}
/**
* sha256_compress - Compress 512-bits.
* @md: Pointer to the element holding hash state.
* @msgBuf: Pointer to the buffer containing the data to be hashed.
* @pScratchMem: Scratch memory; At least 288 bytes of free memory *
*
*/
int
sha256_compress(void *priv, struct sha256_state *md,
UINT8 *msgBuf, UINT8 *pScratchMem)
{
phostsa_private psapriv = (phostsa_private)priv;
hostsa_util_fns *util_fns = &psapriv->util_fns;
UINT32 *pW; /* was UINT32 W[64] */
UINT32 *pS; /* was UINT32 S[8] */
UINT32 t0;
UINT32 t1;
UINT32 t;
UINT32 i;
UINT32 *ptrU32;
/* pW = (64 * 4) = 256 ** pS = (8 * 4) = 32 ** ----- ** 288 */
ptrU32 = pW = (UINT32 *)pScratchMem;
pS = pW + 64;
/* copy state into S */
memcpy(util_fns, (UINT8 *)pS, (UINT8 *)md->state, 32);
/* copy the a message block of 512-bits into pW[0..15] */
for (i = 16; i > 0; i--) {
int a0, a1;
a0 = *msgBuf++;
a1 = *msgBuf++;
a0 <<= 8;
a0 |= a1;
a1 = *msgBuf++;
a0 <<= 8;
a0 |= a1;
a1 = *msgBuf++;
a0 <<= 8;
*ptrU32++ = a0 | a1;
}
/* fill pW[16..63] */
for (i = 48; i > 0; i--) {
*ptrU32 =
(Gamma1(ptrU32[-2]) + ptrU32[-7] + Gamma0(ptrU32[-15]) +
ptrU32[-16]);
ptrU32++;
}
/* Compress */
#define RND(a,b,c,d,e,f,g,h,i) \
t0 = h + Sigma1(e) + Ch(e, f, g) + K[i] + pW[i]; \
t1 = Sigma0(a) + Maj(a, b, c); \
d += t0; \
h = t0 + t1;
for (i = 0; i < 64; ++i) {
RND(pS[0], pS[1], pS[2], pS[3], pS[4], pS[5], pS[6], pS[7], i);
t = pS[7];
pS[7] = pS[6];
pS[6] = pS[5];
pS[5] = pS[4];
pS[4] = pS[3];
pS[3] = pS[2];
pS[2] = pS[1];
pS[1] = pS[0];
pS[0] = t;
}
/* feedback */
for (i = 0; i < 8; i++) {
md->state[i] = md->state[i] + pS[i];
}
return 0;
}