1
0
mirror of https://github.com/hashcat/hashcat.git synced 2024-12-23 15:18:16 +00:00
hashcat/OpenCL/m09800_a0-optimized.cl

553 lines
17 KiB
Common Lisp

/**
* 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_optimized.h"
#include "inc_rp_optimized.cl"
#include "inc_simd.cl"
#include "inc_hash_sha1.cl"
typedef struct
{
u8 S[256];
u32 wtf_its_faster;
} RC4_KEY;
DECLSPEC 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;
}
DECLSPEC 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++;
}
}
DECLSPEC 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;
}
__kernel void m09800_m04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_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 u64 gid_max)
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
/**
* base
*/
const u64 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];
/**
* salt
*/
u32 salt_buf[4];
salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
/**
* 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 };
const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_0x80_2x4_VV (w0, w1, out_len);
/**
* sha1
*/
make_utf16le (w1, w2, w3);
make_utf16le (w0, w0, w1);
const u32x pw_salt_len = (out_len * 2) + 16;
w3[3] = pw_salt_len * 8;
w3[2] = 0;
w3[1] = swap32 (w2[1]);
w3[0] = swap32 (w2[0]);
w2[3] = swap32 (w1[3]);
w2[2] = swap32 (w1[2]);
w2[1] = swap32 (w1[1]);
w2[0] = swap32 (w1[0]);
w1[3] = swap32 (w0[3]);
w1[2] = swap32 (w0[2]);
w1[1] = swap32 (w0[1]);
w1[0] = swap32 (w0[0]);
w0[3] = salt_buf[3];
w0[2] = salt_buf[2];
w0[1] = salt_buf[1];
w0[0] = salt_buf[0];
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);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0;
w1[2] = 0x80000000;
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] = (20 + 4) * 8;
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]);
if (version == 3)
{
digest[1] &= 0xff;
digest[2] = 0;
digest[3] = 0;
}
rc4_init_16 (rc4_key, digest);
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;
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 m09800_m08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_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 u64 gid_max)
{
}
__kernel void m09800_m16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_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 u64 gid_max)
{
}
__kernel void m09800_s04 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_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 u64 gid_max)
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
/**
* base
*/
const u64 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];
/**
* salt
*/
u32 salt_buf[4];
salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
/**
* 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 };
const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_0x80_2x4_VV (w0, w1, out_len);
/**
* sha1
*/
make_utf16le (w1, w2, w3);
make_utf16le (w0, w0, w1);
const u32x pw_salt_len = (out_len * 2) + 16;
w3[3] = pw_salt_len * 8;
w3[2] = 0;
w3[1] = swap32 (w2[1]);
w3[0] = swap32 (w2[0]);
w2[3] = swap32 (w1[3]);
w2[2] = swap32 (w1[2]);
w2[1] = swap32 (w1[1]);
w2[0] = swap32 (w1[0]);
w1[3] = swap32 (w0[3]);
w1[2] = swap32 (w0[2]);
w1[1] = swap32 (w0[1]);
w1[0] = swap32 (w0[0]);
w0[3] = salt_buf[3];
w0[2] = salt_buf[2];
w0[1] = salt_buf[1];
w0[0] = salt_buf[0];
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);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0;
w1[2] = 0x80000000;
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] = (20 + 4) * 8;
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]);
if (version == 3)
{
digest[1] &= 0xff;
digest[2] = 0;
digest[3] = 0;
}
rc4_init_16 (rc4_key, digest);
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;
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 m09800_s08 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_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 u64 gid_max)
{
}
__kernel void m09800_s16 (__global pw_t *pws, __constant const kernel_rule_t *rules_buf, __global const pw_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 u64 gid_max)
{
}