mirror of
https://github.com/hashcat/hashcat.git
synced 2024-11-13 19:28:56 +00:00
0bf4e3c34a
- Some performance on low-end GPU may drop because of that, but only for a few hash-modes - Dropped scalar code (aka warp) since we do not have any vector datatypes anymore - Renamed C++ overloading functions memcat32_9 -> memcat_c32_w4x4_a3x4 - Still need to fix kernels to new function names, needs to be done manually - Temperature Management needs to be rewritten partially because of conflicting datatypes names - Added code to create different codepaths for NV on AMD in runtime in host (see data.vendor_id) - Added code to create different codepaths for NV on AMD in runtime in kernels (see IS_NV and IS_AMD) - First tests working for -m 0, for example - Great performance increases in general for NV so far - Tested amp_* and markov_* kernel - Migrated special NV optimizations for rule processor
579 lines
21 KiB
Common Lisp
579 lines
21 KiB
Common Lisp
/**
|
|
* Author......: Jens Steube <jens.steube@gmail.com>
|
|
* License.....: MIT
|
|
*/
|
|
|
|
#define _SHA1_
|
|
|
|
#include "include/constants.h"
|
|
#include "include/kernel_vendor.h"
|
|
|
|
#define DGST_R0 3
|
|
#define DGST_R1 4
|
|
#define DGST_R2 2
|
|
#define DGST_R3 1
|
|
|
|
#include "include/kernel_functions.c"
|
|
#include "types_ocl.c"
|
|
#include "common.c"
|
|
#include "include/rp_gpu.h"
|
|
#include "rp.c"
|
|
|
|
#define COMPARE_S "check_single_comp4.c"
|
|
#define COMPARE_M "check_multi_comp4.c"
|
|
|
|
static 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;
|
|
}
|
|
|
|
static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
|
|
{
|
|
w0[0] = w0[0] ^ 0x36363636;
|
|
w0[1] = w0[1] ^ 0x36363636;
|
|
w0[2] = w0[2] ^ 0x36363636;
|
|
w0[3] = w0[3] ^ 0x36363636;
|
|
w1[0] = w1[0] ^ 0x36363636;
|
|
w1[1] = w1[1] ^ 0x36363636;
|
|
w1[2] = w1[2] ^ 0x36363636;
|
|
w1[3] = w1[3] ^ 0x36363636;
|
|
w2[0] = w2[0] ^ 0x36363636;
|
|
w2[1] = w2[1] ^ 0x36363636;
|
|
w2[2] = w2[2] ^ 0x36363636;
|
|
w2[3] = w2[3] ^ 0x36363636;
|
|
w3[0] = w3[0] ^ 0x36363636;
|
|
w3[1] = w3[1] ^ 0x36363636;
|
|
w3[2] = w3[2] ^ 0x36363636;
|
|
w3[3] = w3[3] ^ 0x36363636;
|
|
|
|
ipad[0] = SHA1M_A;
|
|
ipad[1] = SHA1M_B;
|
|
ipad[2] = SHA1M_C;
|
|
ipad[3] = SHA1M_D;
|
|
ipad[4] = SHA1M_E;
|
|
|
|
sha1_transform (w0, w1, w2, w3, ipad);
|
|
|
|
w0[0] = w0[0] ^ 0x6a6a6a6a;
|
|
w0[1] = w0[1] ^ 0x6a6a6a6a;
|
|
w0[2] = w0[2] ^ 0x6a6a6a6a;
|
|
w0[3] = w0[3] ^ 0x6a6a6a6a;
|
|
w1[0] = w1[0] ^ 0x6a6a6a6a;
|
|
w1[1] = w1[1] ^ 0x6a6a6a6a;
|
|
w1[2] = w1[2] ^ 0x6a6a6a6a;
|
|
w1[3] = w1[3] ^ 0x6a6a6a6a;
|
|
w2[0] = w2[0] ^ 0x6a6a6a6a;
|
|
w2[1] = w2[1] ^ 0x6a6a6a6a;
|
|
w2[2] = w2[2] ^ 0x6a6a6a6a;
|
|
w2[3] = w2[3] ^ 0x6a6a6a6a;
|
|
w3[0] = w3[0] ^ 0x6a6a6a6a;
|
|
w3[1] = w3[1] ^ 0x6a6a6a6a;
|
|
w3[2] = w3[2] ^ 0x6a6a6a6a;
|
|
w3[3] = w3[3] ^ 0x6a6a6a6a;
|
|
|
|
opad[0] = SHA1M_A;
|
|
opad[1] = SHA1M_B;
|
|
opad[2] = SHA1M_C;
|
|
opad[3] = SHA1M_D;
|
|
opad[4] = SHA1M_E;
|
|
|
|
sha1_transform (w0, w1, w2, w3, opad);
|
|
}
|
|
|
|
static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
|
|
{
|
|
digest[0] = ipad[0];
|
|
digest[1] = ipad[1];
|
|
digest[2] = ipad[2];
|
|
digest[3] = ipad[3];
|
|
digest[4] = ipad[4];
|
|
|
|
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] = 0x80000000;
|
|
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] = (64 + 20) * 8;
|
|
|
|
digest[0] = opad[0];
|
|
digest[1] = opad[1];
|
|
digest[2] = opad[2];
|
|
digest[3] = opad[3];
|
|
digest[4] = opad[4];
|
|
|
|
sha1_transform (w0, w1, w2, w3, digest);
|
|
}
|
|
|
|
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00150_m04 (__global pw_t *pws, __global gpu_rule_t * rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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 rules_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];
|
|
|
|
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];
|
|
|
|
u32 pw_buf1[4];
|
|
|
|
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;
|
|
|
|
/**
|
|
* salt
|
|
*/
|
|
|
|
u32 salt_buf0[4];
|
|
|
|
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
|
|
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
|
|
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
|
|
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
|
|
|
|
u32 salt_buf1[4];
|
|
|
|
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
|
|
salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
|
|
salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
|
|
salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
|
|
|
|
const u32 salt_len = salt_bufs[salt_pos].salt_len;
|
|
|
|
/**
|
|
* loop
|
|
*/
|
|
|
|
for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
|
|
{
|
|
u32 w0[4];
|
|
|
|
w0[0] = pw_buf0[0];
|
|
w0[1] = pw_buf0[1];
|
|
w0[2] = pw_buf0[2];
|
|
w0[3] = pw_buf0[3];
|
|
|
|
u32 w1[4];
|
|
|
|
w1[0] = pw_buf1[0];
|
|
w1[1] = pw_buf1[1];
|
|
w1[2] = pw_buf1[2];
|
|
w1[3] = pw_buf1[3];
|
|
|
|
u32 w2[4];
|
|
|
|
w2[0] = 0;
|
|
w2[1] = 0;
|
|
w2[2] = 0;
|
|
w2[3] = 0;
|
|
|
|
u32 w3[4];
|
|
|
|
w3[0] = 0;
|
|
w3[1] = 0;
|
|
w3[2] = 0;
|
|
w3[3] = 0;
|
|
|
|
const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
|
|
|
|
/**
|
|
* pads
|
|
*/
|
|
|
|
u32 w0_t[4];
|
|
|
|
w0_t[0] = swap_workaround (w0[0]);
|
|
w0_t[1] = swap_workaround (w0[1]);
|
|
w0_t[2] = swap_workaround (w0[2]);
|
|
w0_t[3] = swap_workaround (w0[3]);
|
|
|
|
u32 w1_t[4];
|
|
|
|
w1_t[0] = swap_workaround (w1[0]);
|
|
w1_t[1] = swap_workaround (w1[1]);
|
|
w1_t[2] = swap_workaround (w1[2]);
|
|
w1_t[3] = swap_workaround (w1[3]);
|
|
|
|
u32 w2_t[4];
|
|
|
|
w2_t[0] = 0;
|
|
w2_t[1] = 0;
|
|
w2_t[2] = 0;
|
|
w2_t[3] = 0;
|
|
|
|
u32 w3_t[4];
|
|
|
|
w3_t[0] = 0;
|
|
w3_t[1] = 0;
|
|
w3_t[2] = 0;
|
|
w3_t[3] = 0;
|
|
|
|
u32 ipad[5];
|
|
u32 opad[5];
|
|
|
|
hmac_sha1_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
|
|
|
|
w0_t[0] = swap_workaround (salt_buf0[0]);
|
|
w0_t[1] = swap_workaround (salt_buf0[1]);
|
|
w0_t[2] = swap_workaround (salt_buf0[2]);
|
|
w0_t[3] = swap_workaround (salt_buf0[3]);
|
|
w1_t[0] = swap_workaround (salt_buf1[0]);
|
|
w1_t[1] = swap_workaround (salt_buf1[1]);
|
|
w1_t[2] = swap_workaround (salt_buf1[2]);
|
|
w1_t[3] = swap_workaround (salt_buf1[3]);
|
|
w2_t[0] = 0;
|
|
w2_t[1] = 0;
|
|
w2_t[2] = 0;
|
|
w2_t[3] = 0;
|
|
w3_t[0] = 0;
|
|
w3_t[1] = 0;
|
|
w3_t[2] = 0;
|
|
w3_t[3] = (64 + salt_len) * 8;
|
|
|
|
u32 digest[5];
|
|
|
|
hmac_sha1_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
|
|
|
|
const u32 r0 = digest[3];
|
|
const u32 r1 = digest[4];
|
|
const u32 r2 = digest[2];
|
|
const u32 r3 = digest[1];
|
|
|
|
#include COMPARE_M
|
|
}
|
|
}
|
|
|
|
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00150_m08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|
|
|
|
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00150_m16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|
|
|
|
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00150_s04 (__global pw_t *pws, __global gpu_rule_t * rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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 rules_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];
|
|
|
|
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];
|
|
|
|
u32 pw_buf1[4];
|
|
|
|
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;
|
|
|
|
/**
|
|
* salt
|
|
*/
|
|
|
|
u32 salt_buf0[4];
|
|
|
|
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
|
|
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
|
|
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
|
|
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
|
|
|
|
u32 salt_buf1[4];
|
|
|
|
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
|
|
salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
|
|
salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
|
|
salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
|
|
|
|
const u32 salt_len = salt_bufs[salt_pos].salt_len;
|
|
|
|
/**
|
|
* 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 < rules_cnt; il_pos++)
|
|
{
|
|
u32 w0[4];
|
|
|
|
w0[0] = pw_buf0[0];
|
|
w0[1] = pw_buf0[1];
|
|
w0[2] = pw_buf0[2];
|
|
w0[3] = pw_buf0[3];
|
|
|
|
u32 w1[4];
|
|
|
|
w1[0] = pw_buf1[0];
|
|
w1[1] = pw_buf1[1];
|
|
w1[2] = pw_buf1[2];
|
|
w1[3] = pw_buf1[3];
|
|
|
|
u32 w2[4];
|
|
|
|
w2[0] = 0;
|
|
w2[1] = 0;
|
|
w2[2] = 0;
|
|
w2[3] = 0;
|
|
|
|
u32 w3[4];
|
|
|
|
w3[0] = 0;
|
|
w3[1] = 0;
|
|
w3[2] = 0;
|
|
w3[3] = 0;
|
|
|
|
const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
|
|
|
|
/**
|
|
* pads
|
|
*/
|
|
|
|
u32 w0_t[4];
|
|
|
|
w0_t[0] = swap_workaround (w0[0]);
|
|
w0_t[1] = swap_workaround (w0[1]);
|
|
w0_t[2] = swap_workaround (w0[2]);
|
|
w0_t[3] = swap_workaround (w0[3]);
|
|
|
|
u32 w1_t[4];
|
|
|
|
w1_t[0] = swap_workaround (w1[0]);
|
|
w1_t[1] = swap_workaround (w1[1]);
|
|
w1_t[2] = swap_workaround (w1[2]);
|
|
w1_t[3] = swap_workaround (w1[3]);
|
|
|
|
u32 w2_t[4];
|
|
|
|
w2_t[0] = 0;
|
|
w2_t[1] = 0;
|
|
w2_t[2] = 0;
|
|
w2_t[3] = 0;
|
|
|
|
u32 w3_t[4];
|
|
|
|
w3_t[0] = 0;
|
|
w3_t[1] = 0;
|
|
w3_t[2] = 0;
|
|
w3_t[3] = 0;
|
|
|
|
u32 ipad[5];
|
|
u32 opad[5];
|
|
|
|
hmac_sha1_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
|
|
|
|
w0_t[0] = swap_workaround (salt_buf0[0]);
|
|
w0_t[1] = swap_workaround (salt_buf0[1]);
|
|
w0_t[2] = swap_workaround (salt_buf0[2]);
|
|
w0_t[3] = swap_workaround (salt_buf0[3]);
|
|
w1_t[0] = swap_workaround (salt_buf1[0]);
|
|
w1_t[1] = swap_workaround (salt_buf1[1]);
|
|
w1_t[2] = swap_workaround (salt_buf1[2]);
|
|
w1_t[3] = swap_workaround (salt_buf1[3]);
|
|
w2_t[0] = 0;
|
|
w2_t[1] = 0;
|
|
w2_t[2] = 0;
|
|
w2_t[3] = 0;
|
|
w3_t[0] = 0;
|
|
w3_t[1] = 0;
|
|
w3_t[2] = 0;
|
|
w3_t[3] = (64 + salt_len) * 8;
|
|
|
|
u32 digest[5];
|
|
|
|
hmac_sha1_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
|
|
|
|
const u32 r0 = digest[3];
|
|
const u32 r1 = digest[4];
|
|
const u32 r2 = digest[2];
|
|
const u32 r3 = digest[1];
|
|
|
|
#include COMPARE_S
|
|
}
|
|
}
|
|
|
|
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00150_s08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|
|
|
|
__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00150_s16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|