+++ /dev/null
-// Copyright (c) 2013 NovaCoin Developers
-
-#include <string.h>
-#include "pbkdf2.h"
-
-static inline uint32_t
-be32dec(const void *pp)
-{
- const uint8_t *p = (uint8_t const *)pp;
-
- return ((uint32_t)(p[3]) + ((uint32_t)(p[2]) << 8) +
- ((uint32_t)(p[1]) << 16) + ((uint32_t)(p[0]) << 24));
-}
-
-static inline void
-be32enc(void *pp, uint32_t x)
-{
- uint8_t * p = (uint8_t *)pp;
-
- p[3] = x & 0xff;
- p[2] = (x >> 8) & 0xff;
- p[1] = (x >> 16) & 0xff;
- p[0] = (x >> 24) & 0xff;
-}
-
-
-
-/* Initialize an HMAC-SHA256 operation with the given key. */
-void
-HMAC_SHA256_Init(HMAC_SHA256_CTX * ctx, const void * _K, size_t Klen)
-{
- unsigned char pad[64];
- unsigned char khash[32];
- const unsigned char * K = (const unsigned char *)_K;
- size_t i;
-
- /* If Klen > 64, the key is really SHA256(K). */
- if (Klen > 64) {
- SHA256_Init(&ctx->ictx);
- SHA256_Update(&ctx->ictx, K, Klen);
- SHA256_Final(khash, &ctx->ictx);
- K = khash;
- Klen = 32;
- }
-
- /* Inner SHA256 operation is SHA256(K xor [block of 0x36] || data). */
- SHA256_Init(&ctx->ictx);
- memset(pad, 0x36, 64);
- for (i = 0; i < Klen; i++)
- pad[i] ^= K[i];
- SHA256_Update(&ctx->ictx, pad, 64);
-
- /* Outer SHA256 operation is SHA256(K xor [block of 0x5c] || hash). */
- SHA256_Init(&ctx->octx);
- memset(pad, 0x5c, 64);
- for (i = 0; i < Klen; i++)
- pad[i] ^= K[i];
- SHA256_Update(&ctx->octx, pad, 64);
-
- /* Clean the stack. */
- memset(khash, 0, 32);
-}
-
-/* Add bytes to the HMAC-SHA256 operation. */
-void
-HMAC_SHA256_Update(HMAC_SHA256_CTX * ctx, const void *in, size_t len)
-{
-
- /* Feed data to the inner SHA256 operation. */
- SHA256_Update(&ctx->ictx, in, len);
-}
-
-/* Finish an HMAC-SHA256 operation. */
-void
-HMAC_SHA256_Final(unsigned char digest[32], HMAC_SHA256_CTX * ctx)
-{
- unsigned char ihash[32];
-
- /* Finish the inner SHA256 operation. */
- SHA256_Final(ihash, &ctx->ictx);
-
- /* Feed the inner hash to the outer SHA256 operation. */
- SHA256_Update(&ctx->octx, ihash, 32);
-
- /* Finish the outer SHA256 operation. */
- SHA256_Final(digest, &ctx->octx);
-
- /* Clean the stack. */
- memset(ihash, 0, 32);
-}
-
-/**
- * PBKDF2_SHA256(passwd, passwdlen, salt, saltlen, c, buf, dkLen):
- * Compute PBKDF2(passwd, salt, c, dkLen) using HMAC-SHA256 as the PRF, and
- * write the output to buf. The value dkLen must be at most 32 * (2^32 - 1).
- */
-void
-PBKDF2_SHA256(const uint8_t * passwd, size_t passwdlen, const uint8_t * salt,
- size_t saltlen, uint64_t c, uint8_t * buf, size_t dkLen)
-{
- HMAC_SHA256_CTX PShctx, hctx;
- size_t i;
- uint8_t ivec[4];
- uint8_t U[32];
- uint8_t T[32];
- uint64_t j;
- int k;
- size_t clen;
-
- /* Compute HMAC state after processing P and S. */
- HMAC_SHA256_Init(&PShctx, passwd, passwdlen);
- HMAC_SHA256_Update(&PShctx, salt, saltlen);
-
- /* Iterate through the blocks. */
- for (i = 0; i * 32 < dkLen; i++) {
- /* Generate INT(i + 1). */
- be32enc(ivec, (uint32_t)(i + 1));
-
- /* Compute U_1 = PRF(P, S || INT(i)). */
- memcpy(&hctx, &PShctx, sizeof(HMAC_SHA256_CTX));
- HMAC_SHA256_Update(&hctx, ivec, 4);
- HMAC_SHA256_Final(U, &hctx);
-
- /* T_i = U_1 ... */
- memcpy(T, U, 32);
-
- for (j = 2; j <= c; j++) {
- /* Compute U_j. */
- HMAC_SHA256_Init(&hctx, passwd, passwdlen);
- HMAC_SHA256_Update(&hctx, U, 32);
- HMAC_SHA256_Final(U, &hctx);
-
- /* ... xor U_j ... */
- for (k = 0; k < 32; k++)
- T[k] ^= U[k];
- }
-
- /* Copy as many bytes as necessary into buf. */
- clen = dkLen - i * 32;
- if (clen > 32)
- clen = 32;
- memcpy(&buf[i * 32], T, clen);
- }
-
- /* Clean PShctx, since we never called _Final on it. */
- memset(&PShctx, 0, sizeof(HMAC_SHA256_CTX));
-}
-
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
-#include "pbkdf2.h"
+#include <openssl/evp.h>
#include <emmintrin.h>
static inline void xor_salsa8_sse2(__m128i B[4], const __m128i Bx[4])
{
- __m128i X0, X1, X2, X3;
- __m128i T;
- int i;
-
- X0 = B[0] = _mm_xor_si128(B[0], Bx[0]);
- X1 = B[1] = _mm_xor_si128(B[1], Bx[1]);
- X2 = B[2] = _mm_xor_si128(B[2], Bx[2]);
- X3 = B[3] = _mm_xor_si128(B[3], Bx[3]);
-
- for (i = 0; i < 8; i += 2) {
- /* Operate on "columns". */
- T = _mm_add_epi32(X0, X3);
- X1 = _mm_xor_si128(X1, _mm_slli_epi32(T, 7));
- X1 = _mm_xor_si128(X1, _mm_srli_epi32(T, 25));
- T = _mm_add_epi32(X1, X0);
- X2 = _mm_xor_si128(X2, _mm_slli_epi32(T, 9));
- X2 = _mm_xor_si128(X2, _mm_srli_epi32(T, 23));
- T = _mm_add_epi32(X2, X1);
- X3 = _mm_xor_si128(X3, _mm_slli_epi32(T, 13));
- X3 = _mm_xor_si128(X3, _mm_srli_epi32(T, 19));
- T = _mm_add_epi32(X3, X2);
- X0 = _mm_xor_si128(X0, _mm_slli_epi32(T, 18));
- X0 = _mm_xor_si128(X0, _mm_srli_epi32(T, 14));
-
- /* Rearrange data. */
- X1 = _mm_shuffle_epi32(X1, 0x93);
- X2 = _mm_shuffle_epi32(X2, 0x4E);
- X3 = _mm_shuffle_epi32(X3, 0x39);
-
- /* Operate on "rows". */
- T = _mm_add_epi32(X0, X1);
- X3 = _mm_xor_si128(X3, _mm_slli_epi32(T, 7));
- X3 = _mm_xor_si128(X3, _mm_srli_epi32(T, 25));
- T = _mm_add_epi32(X3, X0);
- X2 = _mm_xor_si128(X2, _mm_slli_epi32(T, 9));
- X2 = _mm_xor_si128(X2, _mm_srli_epi32(T, 23));
- T = _mm_add_epi32(X2, X3);
- X1 = _mm_xor_si128(X1, _mm_slli_epi32(T, 13));
- X1 = _mm_xor_si128(X1, _mm_srli_epi32(T, 19));
- T = _mm_add_epi32(X1, X2);
- X0 = _mm_xor_si128(X0, _mm_slli_epi32(T, 18));
- X0 = _mm_xor_si128(X0, _mm_srli_epi32(T, 14));
-
- /* Rearrange data. */
- X1 = _mm_shuffle_epi32(X1, 0x39);
- X2 = _mm_shuffle_epi32(X2, 0x4E);
- X3 = _mm_shuffle_epi32(X3, 0x93);
- }
-
- B[0] = _mm_add_epi32(B[0], X0);
- B[1] = _mm_add_epi32(B[1], X1);
- B[2] = _mm_add_epi32(B[2], X2);
- B[3] = _mm_add_epi32(B[3], X3);
+ __m128i X0, X1, X2, X3;
+ __m128i T;
+ int i;
+
+ X0 = B[0] = _mm_xor_si128(B[0], Bx[0]);
+ X1 = B[1] = _mm_xor_si128(B[1], Bx[1]);
+ X2 = B[2] = _mm_xor_si128(B[2], Bx[2]);
+ X3 = B[3] = _mm_xor_si128(B[3], Bx[3]);
+
+ for (i = 0; i < 8; i += 2) {
+ /* Operate on "columns". */
+ T = _mm_add_epi32(X0, X3);
+ X1 = _mm_xor_si128(X1, _mm_slli_epi32(T, 7));
+ X1 = _mm_xor_si128(X1, _mm_srli_epi32(T, 25));
+ T = _mm_add_epi32(X1, X0);
+ X2 = _mm_xor_si128(X2, _mm_slli_epi32(T, 9));
+ X2 = _mm_xor_si128(X2, _mm_srli_epi32(T, 23));
+ T = _mm_add_epi32(X2, X1);
+ X3 = _mm_xor_si128(X3, _mm_slli_epi32(T, 13));
+ X3 = _mm_xor_si128(X3, _mm_srli_epi32(T, 19));
+ T = _mm_add_epi32(X3, X2);
+ X0 = _mm_xor_si128(X0, _mm_slli_epi32(T, 18));
+ X0 = _mm_xor_si128(X0, _mm_srli_epi32(T, 14));
+
+ /* Rearrange data. */
+ X1 = _mm_shuffle_epi32(X1, 0x93);
+ X2 = _mm_shuffle_epi32(X2, 0x4E);
+ X3 = _mm_shuffle_epi32(X3, 0x39);
+
+ /* Operate on "rows". */
+ T = _mm_add_epi32(X0, X1);
+ X3 = _mm_xor_si128(X3, _mm_slli_epi32(T, 7));
+ X3 = _mm_xor_si128(X3, _mm_srli_epi32(T, 25));
+ T = _mm_add_epi32(X3, X0);
+ X2 = _mm_xor_si128(X2, _mm_slli_epi32(T, 9));
+ X2 = _mm_xor_si128(X2, _mm_srli_epi32(T, 23));
+ T = _mm_add_epi32(X2, X3);
+ X1 = _mm_xor_si128(X1, _mm_slli_epi32(T, 13));
+ X1 = _mm_xor_si128(X1, _mm_srli_epi32(T, 19));
+ T = _mm_add_epi32(X1, X2);
+ X0 = _mm_xor_si128(X0, _mm_slli_epi32(T, 18));
+ X0 = _mm_xor_si128(X0, _mm_srli_epi32(T, 14));
+
+ /* Rearrange data. */
+ X1 = _mm_shuffle_epi32(X1, 0x39);
+ X2 = _mm_shuffle_epi32(X2, 0x4E);
+ X3 = _mm_shuffle_epi32(X3, 0x93);
+ }
+
+ B[0] = _mm_add_epi32(B[0], X0);
+ B[1] = _mm_add_epi32(B[1], X1);
+ B[2] = _mm_add_epi32(B[2], X2);
+ B[3] = _mm_add_epi32(B[3], X3);
}
uint256 scrypt_blockhash__sse2(const uint8_t* input)
{
uint256 result = 0;
uint8_t scratchpad[SCRYPT_BUFFER_SIZE];
- uint8_t B[128];
- union {
- __m128i i128[8];
- uint32_t u32[32];
- } X;
- __m128i *V;
- uint32_t i, j, k;
-
- V = (__m128i *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
-
- PBKDF2_SHA256((const uint8_t *)input, 80, (const uint8_t *)input, 80, 1, B, 128);
-
- for (k = 0; k < 2; k++) {
- for (i = 0; i < 16; i++) {
- X.u32[k * 16 + i] = le32dec(&B[(k * 16 + (i * 5 % 16)) * 4]);
- }
- }
-
- for (i = 0; i < 1024; i++) {
- for (k = 0; k < 8; k++)
- V[i * 8 + k] = X.i128[k];
- xor_salsa8_sse2(&X.i128[0], &X.i128[4]);
- xor_salsa8_sse2(&X.i128[4], &X.i128[0]);
- }
- for (i = 0; i < 1024; i++) {
- j = 8 * (X.u32[16] & 1023);
- for (k = 0; k < 8; k++)
- X.i128[k] = _mm_xor_si128(X.i128[k], V[j + k]);
- xor_salsa8_sse2(&X.i128[0], &X.i128[4]);
- xor_salsa8_sse2(&X.i128[4], &X.i128[0]);
- }
-
- for (k = 0; k < 2; k++) {
- for (i = 0; i < 16; i++) {
- le32enc(&B[(k * 16 + (i * 5 % 16)) * 4], X.u32[k * 16 + i]);
- }
- }
-
- PBKDF2_SHA256((const uint8_t *)input, 80, B, 128, 1, (uint8_t *)&result, 32);
+ uint8_t B[128];
+ union {
+ __m128i i128[8];
+ uint32_t u32[32];
+ } X;
+ __m128i *V;
+ uint32_t i, j, k;
+
+ V = (__m128i *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
+
+ PKCS5_PBKDF2_HMAC((const int8_t *)input, 80, (const int8_t *)input, 80, 1, EVP_sha256(), 128, B);
+
+ for (k = 0; k < 2; k++) {
+ for (i = 0; i < 16; i++) {
+ X.u32[k * 16 + i] = le32dec(&B[(k * 16 + (i * 5 % 16)) * 4]);
+ }
+ }
+
+ for (i = 0; i < 1024; i++) {
+ for (k = 0; k < 8; k++)
+ V[i * 8 + k] = X.i128[k];
+ xor_salsa8_sse2(&X.i128[0], &X.i128[4]);
+ xor_salsa8_sse2(&X.i128[4], &X.i128[0]);
+ }
+ for (i = 0; i < 1024; i++) {
+ j = 8 * (X.u32[16] & 1023);
+ for (k = 0; k < 8; k++)
+ X.i128[k] = _mm_xor_si128(X.i128[k], V[j + k]);
+ xor_salsa8_sse2(&X.i128[0], &X.i128[4]);
+ xor_salsa8_sse2(&X.i128[4], &X.i128[0]);
+ }
+
+ for (k = 0; k < 2; k++) {
+ for (i = 0; i < 16; i++) {
+ le32enc(&B[(k * 16 + (i * 5 % 16)) * 4], X.u32[k * 16 + i]);
+ }
+ }
+
+ PKCS5_PBKDF2_HMAC((const int8_t *)input, 80, B, 128, 1, EVP_sha256(), 32, (int8_t*)&result);
return result;
}