1
0
mirror of https://github.com/hashcat/hashcat.git synced 2024-12-27 17:08:12 +00:00
hashcat/nv/m00200_a3.cu
2015-12-04 15:47:52 +01:00

491 lines
17 KiB
Plaintext

/**
* Author......: Jens Steube <jens.steube@gmail.com>
* License.....: MIT
*/
#define _MYSQL323_
#define _SCALAR_
#include "include/constants.h"
#include "include/kernel_vendor.h"
#ifdef VLIW1
#define VECT_SIZE1
#endif
#ifdef VLIW2
#define VECT_SIZE4
#endif
#define DGST_R0 0
#define DGST_R1 1
#define DGST_R2 2
#define DGST_R3 3
#include "include/kernel_functions.c"
#include "types_nv.c"
#include "common_nv.c"
#ifdef VECT_SIZE1
#define VECT_COMPARE_S "check_single_vect1_comp4_warp.c"
#define VECT_COMPARE_M "check_multi_vect1_comp4_warp.c"
#endif
#ifdef VECT_SIZE2
#define VECT_COMPARE_S "check_single_vect2_comp4_warp.c"
#define VECT_COMPARE_M "check_multi_vect2_comp4_warp.c"
#endif
#ifdef VECT_SIZE4
#define VECT_COMPARE_S "check_single_vect4_comp4_warp.c"
#define VECT_COMPARE_M "check_multi_vect4_comp4_warp.c"
#endif
__device__ __constant__ u32x c_bfs[1024];
__device__ static void m00200m (u32 w[16], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
{
/**
* modifier
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
const u32 lid = threadIdx.x;
/**
* loop
*/
const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
u32x w0l = w[0];
for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
{
const u32x w0r = c_bfs[il_pos];
const u32x w0 = w0l | w0r;
u32x a = MYSQL323_A;
u32x b = MYSQL323_B;
u32x add = 7;
#define ROUND(v) \
{ \
a ^= (((a & 0x3f) + add) * (v)) + (a << 8); \
b += (b << 8) ^ a; \
add += v; \
}
if (pw_len >= 4)
{
ROUND ((w0 >> 0) & 0xff);
ROUND ((w0 >> 8) & 0xff);
ROUND ((w0 >> 16) & 0xff);
ROUND ((w0 >> 24) & 0xff);
}
else if (pw_len == 3)
{
ROUND ((w0 >> 0) & 0xff);
ROUND ((w0 >> 8) & 0xff);
ROUND ((w0 >> 16) & 0xff);
}
else if (pw_len == 2)
{
ROUND ((w0 >> 0) & 0xff);
ROUND ((w0 >> 8) & 0xff);
}
else if (pw_len == 1)
{
ROUND ((w0 >> 0) & 0xff);
}
int i;
int j;
for (i = 4, j = 1; i <= (int) pw_len - 4; i += 4, j += 1)
{
const u32 wj = w[j];
ROUND ((wj >> 0) & 0xff);
ROUND ((wj >> 8) & 0xff);
ROUND ((wj >> 16) & 0xff);
ROUND ((wj >> 24) & 0xff);
}
const u32 wj = w[j];
const u32 left = pw_len - i;
if (left == 3)
{
ROUND ((wj >> 0) & 0xff);
ROUND ((wj >> 8) & 0xff);
ROUND ((wj >> 16) & 0xff);
}
else if (left == 2)
{
ROUND ((wj >> 0) & 0xff);
ROUND ((wj >> 8) & 0xff);
}
else if (left == 1)
{
ROUND ((wj >> 0) & 0xff);
}
a &= 0x7fffffff;
b &= 0x7fffffff;
const u32x r0 = a;
const u32x r1 = b;
const u32x r2 = 0;
const u32x r3 = 0;
#include VECT_COMPARE_M
}
}
__device__ static void m00200s (u32 w[16], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
{
/**
* modifier
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
const u32 lid = threadIdx.x;
/**
* 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
*/
const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
u32x w0l = w[0];
for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
{
const u32x w0r = c_bfs[il_pos];
const u32x w0 = w0l | w0r;
u32x a = MYSQL323_A;
u32x b = MYSQL323_B;
u32x add = 7;
#define ROUND(v) \
{ \
a ^= (((a & 0x3f) + add) * (v)) + (a << 8); \
b += (b << 8) ^ a; \
add += v; \
}
if (pw_len >= 4)
{
ROUND ((w0 >> 0) & 0xff);
ROUND ((w0 >> 8) & 0xff);
ROUND ((w0 >> 16) & 0xff);
ROUND ((w0 >> 24) & 0xff);
}
else if (pw_len == 3)
{
ROUND ((w0 >> 0) & 0xff);
ROUND ((w0 >> 8) & 0xff);
ROUND ((w0 >> 16) & 0xff);
}
else if (pw_len == 2)
{
ROUND ((w0 >> 0) & 0xff);
ROUND ((w0 >> 8) & 0xff);
}
else if (pw_len == 1)
{
ROUND ((w0 >> 0) & 0xff);
}
int i;
int j;
for (i = 4, j = 1; i <= (int) pw_len - 4; i += 4, j += 1)
{
const u32 wj = w[j];
ROUND ((wj >> 0) & 0xff);
ROUND ((wj >> 8) & 0xff);
ROUND ((wj >> 16) & 0xff);
ROUND ((wj >> 24) & 0xff);
}
const u32 wj = w[j];
const u32 left = pw_len - i;
if (left == 3)
{
ROUND ((wj >> 0) & 0xff);
ROUND ((wj >> 8) & 0xff);
ROUND ((wj >> 16) & 0xff);
}
else if (left == 2)
{
ROUND ((wj >> 0) & 0xff);
ROUND ((wj >> 8) & 0xff);
}
else if (left == 1)
{
ROUND ((wj >> 0) & 0xff);
}
a &= 0x7fffffff;
b &= 0x7fffffff;
const u32x r0 = a;
const u32x r1 = b;
const u32x r2 = 0;
const u32x r3 = 0;
#include VECT_COMPARE_S
}
}
extern "C" __global__ void __launch_bounds__ (256, 1) m00200_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = 0;
w[ 5] = 0;
w[ 6] = 0;
w[ 7] = 0;
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00200m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
extern "C" __global__ void __launch_bounds__ (256, 1) m00200_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00200m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
extern "C" __global__ void __launch_bounds__ (256, 1) m00200_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = pws[gid].i[ 8];
w[ 9] = pws[gid].i[ 9];
w[10] = pws[gid].i[10];
w[11] = pws[gid].i[11];
w[12] = pws[gid].i[12];
w[13] = pws[gid].i[13];
w[14] = pws[gid].i[14];
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00200m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
extern "C" __global__ void __launch_bounds__ (256, 1) m00200_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = 0;
w[ 5] = 0;
w[ 6] = 0;
w[ 7] = 0;
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00200s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
extern "C" __global__ void __launch_bounds__ (256, 1) m00200_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = 0;
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00200s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}
extern "C" __global__ void __launch_bounds__ (256, 1) m00200_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, u32 *d_scryptV_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
*/
const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
if (gid >= gid_max) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = pws[gid].i[ 8];
w[ 9] = pws[gid].i[ 9];
w[10] = pws[gid].i[10];
w[11] = pws[gid].i[11];
w[12] = pws[gid].i[12];
w[13] = pws[gid].i[13];
w[14] = pws[gid].i[14];
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len;
/**
* main
*/
m00200s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
}