|
|
|
/**
|
|
|
|
* Author......: See docs/credits.txt
|
|
|
|
* License.....: MIT
|
|
|
|
*/
|
|
|
|
|
|
|
|
//too much register pressure
|
|
|
|
//#define NEW_SIMD_CODE
|
|
|
|
|
|
|
|
#include "inc_vendor.cl"
|
|
|
|
#include "inc_hash_constants.h"
|
|
|
|
#include "inc_hash_functions.cl"
|
|
|
|
#include "inc_types.cl"
|
|
|
|
#include "inc_common.cl"
|
|
|
|
#include "inc_rp.h"
|
|
|
|
#include "inc_rp.cl"
|
|
|
|
#include "inc_simd.cl"
|
|
|
|
|
|
|
|
typedef struct
|
|
|
|
{
|
|
|
|
u8 S[256];
|
|
|
|
|
|
|
|
u32 wtf_its_faster;
|
|
|
|
|
|
|
|
} RC4_KEY;
|
|
|
|
|
|
|
|
void swap (__local RC4_KEY *rc4_key, const u8 i, const u8 j)
|
|
|
|
{
|
|
|
|
u8 tmp;
|
|
|
|
|
|
|
|
tmp = rc4_key->S[i];
|
|
|
|
rc4_key->S[i] = rc4_key->S[j];
|
|
|
|
rc4_key->S[j] = tmp;
|
|
|
|
}
|
|
|
|
|
|
|
|
void rc4_init_16 (__local RC4_KEY *rc4_key, const u32 data[4])
|
|
|
|
{
|
|
|
|
u32 v = 0x03020100;
|
|
|
|
u32 a = 0x04040404;
|
|
|
|
|
|
|
|
__local u32 *ptr = (__local u32 *) rc4_key->S;
|
|
|
|
|
|
|
|
#ifdef _unroll
|
|
|
|
#pragma unroll
|
|
|
|
#endif
|
|
|
|
for (u32 i = 0; i < 64; i++)
|
|
|
|
{
|
|
|
|
*ptr++ = v; v += a;
|
|
|
|
}
|
|
|
|
|
|
|
|
u32 j = 0;
|
|
|
|
|
|
|
|
for (u32 i = 0; i < 16; i++)
|
|
|
|
{
|
|
|
|
u32 idx = i * 16;
|
|
|
|
|
|
|
|
u32 v;
|
|
|
|
|
|
|
|
v = data[0];
|
|
|
|
|
|
|
|
j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j); idx++;
|
|
|
|
|
|
|
|
v = data[1];
|
|
|
|
|
|
|
|
j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j); idx++;
|
|
|
|
|
|
|
|
v = data[2];
|
|
|
|
|
|
|
|
j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j); idx++;
|
|
|
|
|
|
|
|
v = data[3];
|
|
|
|
|
|
|
|
j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j); idx++;
|
|
|
|
j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j); idx++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
u8 rc4_next_16 (__local RC4_KEY *rc4_key, u8 i, u8 j, const u32 in[4], u32 out[4])
|
|
|
|
{
|
|
|
|
#ifdef _unroll
|
|
|
|
#pragma unroll
|
|
|
|
#endif
|
|
|
|
for (u32 k = 0; k < 4; k++)
|
|
|
|
{
|
|
|
|
u32 xor4 = 0;
|
|
|
|
|
|
|
|
u8 idx;
|
|
|
|
|
|
|
|
i += 1;
|
|
|
|
j += rc4_key->S[i];
|
|
|
|
|
|
|
|
swap (rc4_key, i, j);
|
|
|
|
|
|
|
|
idx = rc4_key->S[i] + rc4_key->S[j];
|
|
|
|
|
|
|
|
xor4 |= rc4_key->S[idx] << 0;
|
|
|
|
|
|
|
|
i += 1;
|
|
|
|
j += rc4_key->S[i];
|
|
|
|
|
|
|
|
swap (rc4_key, i, j);
|
|
|
|
|
|
|
|
idx = rc4_key->S[i] + rc4_key->S[j];
|
|
|
|
|
|
|
|
xor4 |= rc4_key->S[idx] << 8;
|
|
|
|
|
|
|
|
i += 1;
|
|
|
|
j += rc4_key->S[i];
|
|
|
|
|
|
|
|
swap (rc4_key, i, j);
|
|
|
|
|
|
|
|
idx = rc4_key->S[i] + rc4_key->S[j];
|
|
|
|
|
|
|
|
xor4 |= rc4_key->S[idx] << 16;
|
|
|
|
|
|
|
|
i += 1;
|
|
|
|
j += rc4_key->S[i];
|
|
|
|
|
|
|
|
swap (rc4_key, i, j);
|
|
|
|
|
|
|
|
idx = rc4_key->S[i] + rc4_key->S[j];
|
|
|
|
|
|
|
|
xor4 |= rc4_key->S[idx] << 24;
|
|
|
|
|
|
|
|
out[k] = in[k] ^ xor4;
|
|
|
|
}
|
|
|
|
|
|
|
|
return j;
|
|
|
|
}
|
|
|
|
|
|
|
|
void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
|
|
|
|
{
|
|
|
|
u32 A = digest[0];
|
|
|
|
u32 B = digest[1];
|
|
|
|
u32 C = digest[2];
|
|
|
|
u32 D = digest[3];
|
|
|
|
u32 E = digest[4];
|
|
|
|
|
|
|
|
u32 w0_t = w0[0];
|
|
|
|
u32 w1_t = w0[1];
|
|
|
|
u32 w2_t = w0[2];
|
|
|
|
u32 w3_t = w0[3];
|
|
|
|
u32 w4_t = w1[0];
|
|
|
|
u32 w5_t = w1[1];
|
|
|
|
u32 w6_t = w1[2];
|
|
|
|
u32 w7_t = w1[3];
|
|
|
|
u32 w8_t = w2[0];
|
|
|
|
u32 w9_t = w2[1];
|
|
|
|
u32 wa_t = w2[2];
|
|
|
|
u32 wb_t = w2[3];
|
|
|
|
u32 wc_t = w3[0];
|
|
|
|
u32 wd_t = w3[1];
|
|
|
|
u32 we_t = w3[2];
|
|
|
|
u32 wf_t = w3[3];
|
|
|
|
|
|
|
|
#undef K
|
|
|
|
#define K SHA1C00
|
|
|
|
|
|
|
|
SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
|
|
|
|
SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
|
|
|
|
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
|
|
|
|
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
|
|
|
|
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
|
|
|
|
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
|
|
|
|
|
|
|
|
#undef K
|
|
|
|
#define K SHA1C01
|
|
|
|
|
|
|
|
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
|
|
|
|
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
|
|
|
|
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
|
|
|
|
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
|
|
|
|
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
|
|
|
|
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
|
|
|
|
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
|
|
|
|
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
|
|
|
|
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
|
|
|
|
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
|
|
|
|
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
|
|
|
|
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
|
|
|
|
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
|
|
|
|
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
|
|
|
|
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
|
|
|
|
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
|
|
|
|
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
|
|
|
|
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
|
|
|
|
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
|
|
|
|
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
|
|
|
|
|
|
|
|
#undef K
|
|
|
|
#define K SHA1C02
|
|
|
|
|
|
|
|
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
|
|
|
|
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
|
|
|
|
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
|
|
|
|
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
|
|
|
|
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
|
|
|
|
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
|
|
|
|
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
|
|
|
|
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
|
|
|
|
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
|
|
|
|
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
|
|
|
|
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
|
|
|
|
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
|
|
|
|
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
|
|
|
|
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
|
|
|
|
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
|
|
|
|
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
|
|
|
|
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
|
|
|
|
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
|
|
|
|
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
|
|
|
|
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
|
|
|
|
|
|
|
|
#undef K
|
|
|
|
#define K SHA1C03
|
|
|
|
|
|
|
|
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
|
|
|
|
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
|
|
|
|
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
|
|
|
|
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
|
|
|
|
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
|
|
|
|
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
|
|
|
|
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
|
|
|
|
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
|
|
|
|
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
|
|
|
|
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
|
|
|
|
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
|
|
|
|
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
|
|
|
|
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
|
|
|
|
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
|
|
|
|
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
|
|
|
|
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
|
|
|
|
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
|
|
|
|
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
|
|
|
|
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
|
|
|
|
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
|
|
|
|
|
|
|
|
digest[0] += A;
|
|
|
|
digest[1] += B;
|
|
|
|
digest[2] += C;
|
|
|
|
digest[3] += D;
|
|
|
|
digest[4] += E;
|
|
|
|
}
|
|
|
|
|
|
|
|
__kernel void m09810_m04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const comb_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global oldoffice34_t *oldoffice34_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
|
|
{
|
|
|
|
/**
|
|
|
|
* modifier
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 lid = get_local_id (0);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* base
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 gid = get_global_id (0);
|
|
|
|
|
|
|
|
if (gid >= gid_max) return;
|
|
|
|
|
|
|
|
u32 pw_buf0[4];
|
|
|
|
u32 pw_buf1[4];
|
|
|
|
|
|
|
|
pw_buf0[0] = pws[gid].i[ 0];
|
|
|
|
pw_buf0[1] = pws[gid].i[ 1];
|
|
|
|
pw_buf0[2] = pws[gid].i[ 2];
|
|
|
|
pw_buf0[3] = pws[gid].i[ 3];
|
|
|
|
pw_buf1[0] = pws[gid].i[ 4];
|
|
|
|
pw_buf1[1] = pws[gid].i[ 5];
|
|
|
|
pw_buf1[2] = pws[gid].i[ 6];
|
|
|
|
pw_buf1[3] = pws[gid].i[ 7];
|
|
|
|
|
|
|
|
const u32 pw_len = pws[gid].pw_len;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* shared
|
|
|
|
*/
|
|
|
|
|
|
|
|
__local RC4_KEY rc4_keys[64];
|
|
|
|
|
|
|
|
__local RC4_KEY *rc4_key = &rc4_keys[lid];
|
|
|
|
|
|
|
|
/**
|
|
|
|
* esalt
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 version = oldoffice34_bufs[digests_offset].version;
|
|
|
|
|
|
|
|
u32 encryptedVerifier[4];
|
|
|
|
|
|
|
|
encryptedVerifier[0] = oldoffice34_bufs[digests_offset].encryptedVerifier[0];
|
|
|
|
encryptedVerifier[1] = oldoffice34_bufs[digests_offset].encryptedVerifier[1];
|
|
|
|
encryptedVerifier[2] = oldoffice34_bufs[digests_offset].encryptedVerifier[2];
|
|
|
|
encryptedVerifier[3] = oldoffice34_bufs[digests_offset].encryptedVerifier[3];
|
|
|
|
|
|
|
|
/**
|
|
|
|
* loop
|
|
|
|
*/
|
|
|
|
|
|
|
|
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
|
|
|
{
|
|
|
|
u32x w0[4] = { 0 };
|
|
|
|
u32x w1[4] = { 0 };
|
|
|
|
u32x w2[4] = { 0 };
|
|
|
|
u32x w3[4] = { 0 };
|
|
|
|
|
|
|
|
apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* RC4 + SHA1
|
|
|
|
*/
|
|
|
|
|
|
|
|
u32 key[4];
|
|
|
|
|
|
|
|
key[0] = w0[0];
|
|
|
|
key[1] = w0[1] & 0xff;
|
|
|
|
key[2] = 0;
|
|
|
|
key[3] = 0;
|
|
|
|
|
|
|
|
rc4_init_16 (rc4_key, key);
|
|
|
|
|
|
|
|
u32 out[4];
|
|
|
|
|
|
|
|
u8 j = rc4_next_16 (rc4_key, 0, 0, encryptedVerifier, out);
|
|
|
|
|
|
|
|
w0[0] = swap32 (out[0]);
|
|
|
|
w0[1] = swap32 (out[1]);
|
|
|
|
w0[2] = swap32 (out[2]);
|
|
|
|
w0[3] = swap32 (out[3]);
|
|
|
|
w1[0] = 0x80000000;
|
|
|
|
w1[1] = 0;
|
|
|
|
w1[2] = 0;
|
|
|
|
w1[3] = 0;
|
|
|
|
w2[0] = 0;
|
|
|
|
w2[1] = 0;
|
|
|
|
w2[2] = 0;
|
|
|
|
w2[3] = 0;
|
|
|
|
w3[0] = 0;
|
|
|
|
w3[1] = 0;
|
|
|
|
w3[2] = 0;
|
|
|
|
w3[3] = 16 * 8;
|
|
|
|
|
|
|
|
u32 digest[5];
|
|
|
|
|
|
|
|
digest[0] = SHA1M_A;
|
|
|
|
digest[1] = SHA1M_B;
|
|
|
|
digest[2] = SHA1M_C;
|
|
|
|
digest[3] = SHA1M_D;
|
|
|
|
digest[4] = SHA1M_E;
|
|
|
|
|
|
|
|
sha1_transform (w0, w1, w2, w3, digest);
|
|
|
|
|
|
|
|
digest[0] = swap32 (digest[0]);
|
|
|
|
digest[1] = swap32 (digest[1]);
|
|
|
|
digest[2] = swap32 (digest[2]);
|
|
|
|
digest[3] = swap32 (digest[3]);
|
|
|
|
|
|
|
|
rc4_next_16 (rc4_key, 16, j, digest, out);
|
|
|
|
|
|
|
|
COMPARE_M_SIMD (out[0], out[1], out[2], out[3]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
__kernel void m09810_m08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const comb_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global oldoffice34_t *oldoffice34_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
__kernel void m09810_m16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const comb_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global oldoffice34_t *oldoffice34_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
__kernel void m09810_s04 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const comb_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global oldoffice34_t *oldoffice34_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
|
|
{
|
|
|
|
/**
|
|
|
|
* modifier
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 lid = get_local_id (0);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* base
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 gid = get_global_id (0);
|
|
|
|
|
|
|
|
if (gid >= gid_max) return;
|
|
|
|
|
|
|
|
u32 pw_buf0[4];
|
|
|
|
u32 pw_buf1[4];
|
|
|
|
|
|
|
|
pw_buf0[0] = pws[gid].i[ 0];
|
|
|
|
pw_buf0[1] = pws[gid].i[ 1];
|
|
|
|
pw_buf0[2] = pws[gid].i[ 2];
|
|
|
|
pw_buf0[3] = pws[gid].i[ 3];
|
|
|
|
pw_buf1[0] = pws[gid].i[ 4];
|
|
|
|
pw_buf1[1] = pws[gid].i[ 5];
|
|
|
|
pw_buf1[2] = pws[gid].i[ 6];
|
|
|
|
pw_buf1[3] = pws[gid].i[ 7];
|
|
|
|
|
|
|
|
const u32 pw_len = pws[gid].pw_len;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* shared
|
|
|
|
*/
|
|
|
|
|
|
|
|
__local RC4_KEY rc4_keys[64];
|
|
|
|
|
|
|
|
__local RC4_KEY *rc4_key = &rc4_keys[lid];
|
|
|
|
|
|
|
|
/**
|
|
|
|
* esalt
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 version = oldoffice34_bufs[digests_offset].version;
|
|
|
|
|
|
|
|
u32 encryptedVerifier[4];
|
|
|
|
|
|
|
|
encryptedVerifier[0] = oldoffice34_bufs[digests_offset].encryptedVerifier[0];
|
|
|
|
encryptedVerifier[1] = oldoffice34_bufs[digests_offset].encryptedVerifier[1];
|
|
|
|
encryptedVerifier[2] = oldoffice34_bufs[digests_offset].encryptedVerifier[2];
|
|
|
|
encryptedVerifier[3] = oldoffice34_bufs[digests_offset].encryptedVerifier[3];
|
|
|
|
|
|
|
|
/**
|
|
|
|
* digest
|
|
|
|
*/
|
|
|
|
|
|
|
|
const u32 search[4] =
|
|
|
|
{
|
|
|
|
digests_buf[digests_offset].digest_buf[DGST_R0],
|
|
|
|
digests_buf[digests_offset].digest_buf[DGST_R1],
|
|
|
|
digests_buf[digests_offset].digest_buf[DGST_R2],
|
|
|
|
digests_buf[digests_offset].digest_buf[DGST_R3]
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* loop
|
|
|
|
*/
|
|
|
|
|
|
|
|
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
|
|
|
{
|
|
|
|
u32x w0[4] = { 0 };
|
|
|
|
u32x w1[4] = { 0 };
|
|
|
|
u32x w2[4] = { 0 };
|
|
|
|
u32x w3[4] = { 0 };
|
|
|
|
|
|
|
|
apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* RC4 + SHA1
|
|
|
|
*/
|
|
|
|
|
|
|
|
u32 key[4];
|
|
|
|
|
|
|
|
key[0] = w0[0];
|
|
|
|
key[1] = w0[1] & 0xff;
|
|
|
|
key[2] = 0;
|
|
|
|
key[3] = 0;
|
|
|
|
|
|
|
|
rc4_init_16 (rc4_key, key);
|
|
|
|
|
|
|
|
u32 out[4];
|
|
|
|
|
|
|
|
u8 j = rc4_next_16 (rc4_key, 0, 0, encryptedVerifier, out);
|
|
|
|
|
|
|
|
w0[0] = swap32 (out[0]);
|
|
|
|
w0[1] = swap32 (out[1]);
|
|
|
|
w0[2] = swap32 (out[2]);
|
|
|
|
w0[3] = swap32 (out[3]);
|
|
|
|
w1[0] = 0x80000000;
|
|
|
|
w1[1] = 0;
|
|
|
|
w1[2] = 0;
|
|
|
|
w1[3] = 0;
|
|
|
|
w2[0] = 0;
|
|
|
|
w2[1] = 0;
|
|
|
|
w2[2] = 0;
|
|
|
|
w2[3] = 0;
|
|
|
|
w3[0] = 0;
|
|
|
|
w3[1] = 0;
|
|
|
|
w3[2] = 0;
|
|
|
|
w3[3] = 16 * 8;
|
|
|
|
|
|
|
|
u32 digest[5];
|
|
|
|
|
|
|
|
digest[0] = SHA1M_A;
|
|
|
|
digest[1] = SHA1M_B;
|
|
|
|
digest[2] = SHA1M_C;
|
|
|
|
digest[3] = SHA1M_D;
|
|
|
|
digest[4] = SHA1M_E;
|
|
|
|
|
|
|
|
sha1_transform (w0, w1, w2, w3, digest);
|
|
|
|
|
|
|
|
digest[0] = swap32 (digest[0]);
|
|
|
|
digest[1] = swap32 (digest[1]);
|
|
|
|
digest[2] = swap32 (digest[2]);
|
|
|
|
digest[3] = swap32 (digest[3]);
|
|
|
|
|
|
|
|
rc4_next_16 (rc4_key, 16, j, digest, out);
|
|
|
|
|
|
|
|
COMPARE_S_SIMD (out[0], out[1], out[2], out[3]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
__kernel void m09810_s08 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const comb_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global oldoffice34_t *oldoffice34_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
__kernel void m09810_s16 (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const comb_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global oldoffice34_t *oldoffice34_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
|
|
{
|
|
|
|
}
|