mirror of
https://github.com/hashcat/hashcat.git
synced 2024-12-16 11:48:15 +00:00
dad03e394d
1) SIMD code for all attack-mode Macro vector_accessible() was not refactored and missing completely. Had to rename variables rules_cnt, combs_cnt and bfs_cnt into il_cnt which was a good thing anyway as with new SIMD code they all act in the same way. 2) SIMD code for attack-mode 0 With new SIMD code, apply_rules_vect() has to return u32 not u32x. This has massive impact on all *_a0 kernels. I've rewritten most of them. Deep testing using test.sh is still required. Some kernel need more fixes: - Some are kind of completely incompatible like m10400 but they still use old check_* includes, we should get rid of them as they are no longer neccessary as we have simd.c - Some have a chance but require additional effort like m11500. We can use commented out "#define NEW_SIMD_CODE" to find them This change can have negative impact on -a0 performance for device that require vectorization. That is mostly CPU devices. New GPU's are all scalar, so they wont get hurt by this. This change also proofes that there's no way to efficiently vectorize kernel rules with new SIMD code, but it enables the addition of the rule functions like @ that we were missing for some long time. This is a TODO.
747 lines
24 KiB
Common Lisp
747 lines
24 KiB
Common Lisp
/**
|
|
* Author......: Jens Steube <jens.steube@gmail.com>
|
|
* License.....: MIT
|
|
*/
|
|
|
|
#define _MD5_
|
|
|
|
#include "include/constants.h"
|
|
#include "include/kernel_vendor.h"
|
|
|
|
#define DGST_R0 0
|
|
#define DGST_R1 3
|
|
#define DGST_R2 2
|
|
#define DGST_R3 1
|
|
|
|
#include "include/kernel_functions.c"
|
|
#include "OpenCL/types_ocl.c"
|
|
#include "OpenCL/common.c"
|
|
|
|
#define COMPARE_S "OpenCL/check_single_comp4.c"
|
|
#define COMPARE_M "OpenCL/check_multi_comp4.c"
|
|
|
|
__kernel void m03800_m04 (__global pw_t *pws, __global kernel_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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
/**
|
|
* modifier
|
|
*/
|
|
|
|
const u32 gid = get_global_id (0);
|
|
const u32 lid = get_local_id (0);
|
|
const u32 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
u32 wordl0[4];
|
|
|
|
wordl0[0] = pws[gid].i[ 0];
|
|
wordl0[1] = pws[gid].i[ 1];
|
|
wordl0[2] = pws[gid].i[ 2];
|
|
wordl0[3] = pws[gid].i[ 3];
|
|
|
|
u32 wordl1[4];
|
|
|
|
wordl1[0] = pws[gid].i[ 4];
|
|
wordl1[1] = pws[gid].i[ 5];
|
|
wordl1[2] = pws[gid].i[ 6];
|
|
wordl1[3] = pws[gid].i[ 7];
|
|
|
|
u32 wordl2[4];
|
|
|
|
wordl2[0] = 0;
|
|
wordl2[1] = 0;
|
|
wordl2[2] = 0;
|
|
wordl2[3] = 0;
|
|
|
|
u32 wordl3[4];
|
|
|
|
wordl3[0] = 0;
|
|
wordl3[1] = 0;
|
|
wordl3[2] = 0;
|
|
wordl3[3] = 0;
|
|
|
|
const u32 pw_l_len = pws[gid].pw_len;
|
|
|
|
if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
|
|
{
|
|
switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].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];
|
|
|
|
u32 salt_buf2[4];
|
|
|
|
salt_buf2[0] = 0;
|
|
salt_buf2[1] = 0;
|
|
salt_buf2[2] = 0;
|
|
salt_buf2[3] = 0;
|
|
|
|
u32 salt_buf3[4];
|
|
|
|
salt_buf3[0] = 0;
|
|
salt_buf3[1] = 0;
|
|
salt_buf3[2] = 0;
|
|
salt_buf3[3] = 0;
|
|
|
|
const u32 salt_len = salt_bufs[salt_pos].salt_len;
|
|
|
|
/**
|
|
* loop
|
|
*/
|
|
|
|
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
|
{
|
|
const u32 pw_r_len = combs_buf[il_pos].pw_len;
|
|
|
|
const u32 pw_len = pw_l_len + pw_r_len;
|
|
|
|
u32 wordr0[4];
|
|
|
|
wordr0[0] = combs_buf[il_pos].i[0];
|
|
wordr0[1] = combs_buf[il_pos].i[1];
|
|
wordr0[2] = combs_buf[il_pos].i[2];
|
|
wordr0[3] = combs_buf[il_pos].i[3];
|
|
|
|
u32 wordr1[4];
|
|
|
|
wordr1[0] = combs_buf[il_pos].i[4];
|
|
wordr1[1] = combs_buf[il_pos].i[5];
|
|
wordr1[2] = combs_buf[il_pos].i[6];
|
|
wordr1[3] = combs_buf[il_pos].i[7];
|
|
|
|
u32 wordr2[4];
|
|
|
|
wordr2[0] = 0;
|
|
wordr2[1] = 0;
|
|
wordr2[2] = 0;
|
|
wordr2[3] = 0;
|
|
|
|
u32 wordr3[4];
|
|
|
|
wordr3[0] = 0;
|
|
wordr3[1] = 0;
|
|
wordr3[2] = 0;
|
|
wordr3[3] = 0;
|
|
|
|
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
|
{
|
|
switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
|
}
|
|
|
|
u32 w0[4];
|
|
|
|
w0[0] = wordl0[0] | wordr0[0];
|
|
w0[1] = wordl0[1] | wordr0[1];
|
|
w0[2] = wordl0[2] | wordr0[2];
|
|
w0[3] = wordl0[3] | wordr0[3];
|
|
|
|
u32 w1[4];
|
|
|
|
w1[0] = wordl1[0] | wordr1[0];
|
|
w1[1] = wordl1[1] | wordr1[1];
|
|
w1[2] = wordl1[2] | wordr1[2];
|
|
w1[3] = wordl1[3] | wordr1[3];
|
|
|
|
u32 w2[4];
|
|
|
|
w2[0] = wordl2[0] | wordr2[0];
|
|
w2[1] = wordl2[1] | wordr2[1];
|
|
w2[2] = wordl2[2] | wordr2[2];
|
|
w2[3] = wordl2[3] | wordr2[3];
|
|
|
|
u32 w3[4];
|
|
|
|
w3[0] = wordl3[0] | wordr3[0];
|
|
w3[1] = wordl3[1] | wordr3[1];
|
|
w3[2] = 0;
|
|
w3[3] = 0;
|
|
|
|
/**
|
|
* prepend salt
|
|
*/
|
|
|
|
u32 w0_t[4];
|
|
|
|
w0_t[0] = w0[0];
|
|
w0_t[1] = w0[1];
|
|
w0_t[2] = w0[2];
|
|
w0_t[3] = w0[3];
|
|
|
|
u32 w1_t[4];
|
|
|
|
w1_t[0] = w1[0];
|
|
w1_t[1] = w1[1];
|
|
w1_t[2] = w1[2];
|
|
w1_t[3] = w1[3];
|
|
|
|
u32 w2_t[4];
|
|
|
|
w2_t[0] = w2[0];
|
|
w2_t[1] = w2[1];
|
|
w2_t[2] = w2[2];
|
|
w2_t[3] = w2[3];
|
|
|
|
u32 w3_t[4];
|
|
|
|
w3_t[0] = w3[0];
|
|
w3_t[1] = w3[1];
|
|
w3_t[2] = w3[2];
|
|
w3_t[3] = w3[3];
|
|
|
|
switch_buffer_by_offset_le (w0_t, w1_t, w2_t, w3_t, salt_len);
|
|
|
|
w0_t[0] |= salt_buf0[0];
|
|
w0_t[1] |= salt_buf0[1];
|
|
w0_t[2] |= salt_buf0[2];
|
|
w0_t[3] |= salt_buf0[3];
|
|
w1_t[0] |= salt_buf1[0];
|
|
w1_t[1] |= salt_buf1[1];
|
|
w1_t[2] |= salt_buf1[2];
|
|
w1_t[3] |= salt_buf1[3];
|
|
w2_t[0] |= salt_buf2[0];
|
|
w2_t[1] |= salt_buf2[1];
|
|
w2_t[2] |= salt_buf2[2];
|
|
w2_t[3] |= salt_buf2[3];
|
|
w3_t[0] |= salt_buf3[0];
|
|
w3_t[1] |= salt_buf3[1];
|
|
w3_t[2] |= salt_buf3[2];
|
|
w3_t[3] |= salt_buf3[3];
|
|
|
|
/**
|
|
* append salt
|
|
*/
|
|
|
|
u32 s0[4];
|
|
|
|
s0[0] = salt_buf0[0];
|
|
s0[1] = salt_buf0[1];
|
|
s0[2] = salt_buf0[2];
|
|
s0[3] = salt_buf0[3];
|
|
|
|
u32 s1[4];
|
|
|
|
s1[0] = salt_buf1[0];
|
|
s1[1] = salt_buf1[1];
|
|
s1[2] = salt_buf1[2];
|
|
s1[3] = salt_buf1[3];
|
|
|
|
u32 s2[4];
|
|
|
|
s2[0] = 0;
|
|
s2[1] = 0;
|
|
s2[2] = 0;
|
|
s2[3] = 0;
|
|
|
|
u32 s3[4];
|
|
|
|
s3[0] = 0;
|
|
s3[1] = 0;
|
|
s3[2] = 0;
|
|
s3[3] = 0;
|
|
|
|
switch_buffer_by_offset_le (s0, s1, s2, s3, salt_len + pw_len);
|
|
|
|
w0_t[0] |= s0[0];
|
|
w0_t[1] |= s0[1];
|
|
w0_t[2] |= s0[2];
|
|
w0_t[3] |= s0[3];
|
|
w1_t[0] |= s1[0];
|
|
w1_t[1] |= s1[1];
|
|
w1_t[2] |= s1[2];
|
|
w1_t[3] |= s1[3];
|
|
w2_t[0] |= s2[0];
|
|
w2_t[1] |= s2[1];
|
|
w2_t[2] |= s2[2];
|
|
w2_t[3] |= s2[3];
|
|
w3_t[0] |= s3[0];
|
|
w3_t[1] |= s3[1];
|
|
w3_t[2] |= s3[2];
|
|
w3_t[3] |= s3[3];
|
|
|
|
const u32 pw_salt_len = salt_len + pw_len + salt_len;
|
|
|
|
append_0x80_4x4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
|
|
|
|
w3_t[2] = pw_salt_len * 8;
|
|
|
|
/**
|
|
* md5
|
|
*/
|
|
|
|
u32 a = MD5M_A;
|
|
u32 b = MD5M_B;
|
|
u32 c = MD5M_C;
|
|
u32 d = MD5M_D;
|
|
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
|
|
|
|
MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
|
|
MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
|
|
MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
|
|
MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
|
|
|
|
MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
|
|
MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
|
|
MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
|
|
MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
|
|
|
|
MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
|
|
MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
|
|
MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
|
|
MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
|
|
|
|
MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
|
|
|
|
const u32 r0 = a;
|
|
const u32 r1 = d;
|
|
const u32 r2 = c;
|
|
const u32 r3 = b;
|
|
|
|
#include COMPARE_M
|
|
}
|
|
}
|
|
|
|
__kernel void m03800_m08 (__global pw_t *pws, __global kernel_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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|
|
|
|
__kernel void m03800_m16 (__global pw_t *pws, __global kernel_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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|
|
|
|
__kernel void m03800_s04 (__global pw_t *pws, __global kernel_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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
/**
|
|
* modifier
|
|
*/
|
|
|
|
const u32 gid = get_global_id (0);
|
|
const u32 lid = get_local_id (0);
|
|
const u32 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
u32 wordl0[4];
|
|
|
|
wordl0[0] = pws[gid].i[ 0];
|
|
wordl0[1] = pws[gid].i[ 1];
|
|
wordl0[2] = pws[gid].i[ 2];
|
|
wordl0[3] = pws[gid].i[ 3];
|
|
|
|
u32 wordl1[4];
|
|
|
|
wordl1[0] = pws[gid].i[ 4];
|
|
wordl1[1] = pws[gid].i[ 5];
|
|
wordl1[2] = pws[gid].i[ 6];
|
|
wordl1[3] = pws[gid].i[ 7];
|
|
|
|
u32 wordl2[4];
|
|
|
|
wordl2[0] = 0;
|
|
wordl2[1] = 0;
|
|
wordl2[2] = 0;
|
|
wordl2[3] = 0;
|
|
|
|
u32 wordl3[4];
|
|
|
|
wordl3[0] = 0;
|
|
wordl3[1] = 0;
|
|
wordl3[2] = 0;
|
|
wordl3[3] = 0;
|
|
|
|
const u32 pw_l_len = pws[gid].pw_len;
|
|
|
|
if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
|
|
{
|
|
switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].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];
|
|
|
|
u32 salt_buf2[4];
|
|
|
|
salt_buf2[0] = 0;
|
|
salt_buf2[1] = 0;
|
|
salt_buf2[2] = 0;
|
|
salt_buf2[3] = 0;
|
|
|
|
u32 salt_buf3[4];
|
|
|
|
salt_buf3[0] = 0;
|
|
salt_buf3[1] = 0;
|
|
salt_buf3[2] = 0;
|
|
salt_buf3[3] = 0;
|
|
|
|
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 < il_cnt; il_pos++)
|
|
{
|
|
const u32 pw_r_len = combs_buf[il_pos].pw_len;
|
|
|
|
const u32 pw_len = pw_l_len + pw_r_len;
|
|
|
|
u32 wordr0[4];
|
|
|
|
wordr0[0] = combs_buf[il_pos].i[0];
|
|
wordr0[1] = combs_buf[il_pos].i[1];
|
|
wordr0[2] = combs_buf[il_pos].i[2];
|
|
wordr0[3] = combs_buf[il_pos].i[3];
|
|
|
|
u32 wordr1[4];
|
|
|
|
wordr1[0] = combs_buf[il_pos].i[4];
|
|
wordr1[1] = combs_buf[il_pos].i[5];
|
|
wordr1[2] = combs_buf[il_pos].i[6];
|
|
wordr1[3] = combs_buf[il_pos].i[7];
|
|
|
|
u32 wordr2[4];
|
|
|
|
wordr2[0] = 0;
|
|
wordr2[1] = 0;
|
|
wordr2[2] = 0;
|
|
wordr2[3] = 0;
|
|
|
|
u32 wordr3[4];
|
|
|
|
wordr3[0] = 0;
|
|
wordr3[1] = 0;
|
|
wordr3[2] = 0;
|
|
wordr3[3] = 0;
|
|
|
|
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
|
|
{
|
|
switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
|
|
}
|
|
|
|
u32 w0[4];
|
|
|
|
w0[0] = wordl0[0] | wordr0[0];
|
|
w0[1] = wordl0[1] | wordr0[1];
|
|
w0[2] = wordl0[2] | wordr0[2];
|
|
w0[3] = wordl0[3] | wordr0[3];
|
|
|
|
u32 w1[4];
|
|
|
|
w1[0] = wordl1[0] | wordr1[0];
|
|
w1[1] = wordl1[1] | wordr1[1];
|
|
w1[2] = wordl1[2] | wordr1[2];
|
|
w1[3] = wordl1[3] | wordr1[3];
|
|
|
|
u32 w2[4];
|
|
|
|
w2[0] = wordl2[0] | wordr2[0];
|
|
w2[1] = wordl2[1] | wordr2[1];
|
|
w2[2] = wordl2[2] | wordr2[2];
|
|
w2[3] = wordl2[3] | wordr2[3];
|
|
|
|
u32 w3[4];
|
|
|
|
w3[0] = wordl3[0] | wordr3[0];
|
|
w3[1] = wordl3[1] | wordr3[1];
|
|
w3[2] = 0;
|
|
w3[3] = 0;
|
|
|
|
/**
|
|
* prepend salt
|
|
*/
|
|
|
|
u32 w0_t[4];
|
|
|
|
w0_t[0] = w0[0];
|
|
w0_t[1] = w0[1];
|
|
w0_t[2] = w0[2];
|
|
w0_t[3] = w0[3];
|
|
|
|
u32 w1_t[4];
|
|
|
|
w1_t[0] = w1[0];
|
|
w1_t[1] = w1[1];
|
|
w1_t[2] = w1[2];
|
|
w1_t[3] = w1[3];
|
|
|
|
u32 w2_t[4];
|
|
|
|
w2_t[0] = w2[0];
|
|
w2_t[1] = w2[1];
|
|
w2_t[2] = w2[2];
|
|
w2_t[3] = w2[3];
|
|
|
|
u32 w3_t[4];
|
|
|
|
w3_t[0] = w3[0];
|
|
w3_t[1] = w3[1];
|
|
w3_t[2] = w3[2];
|
|
w3_t[3] = w3[3];
|
|
|
|
switch_buffer_by_offset_le (w0_t, w1_t, w2_t, w3_t, salt_len);
|
|
|
|
w0_t[0] |= salt_buf0[0];
|
|
w0_t[1] |= salt_buf0[1];
|
|
w0_t[2] |= salt_buf0[2];
|
|
w0_t[3] |= salt_buf0[3];
|
|
w1_t[0] |= salt_buf1[0];
|
|
w1_t[1] |= salt_buf1[1];
|
|
w1_t[2] |= salt_buf1[2];
|
|
w1_t[3] |= salt_buf1[3];
|
|
w2_t[0] |= salt_buf2[0];
|
|
w2_t[1] |= salt_buf2[1];
|
|
w2_t[2] |= salt_buf2[2];
|
|
w2_t[3] |= salt_buf2[3];
|
|
w3_t[0] |= salt_buf3[0];
|
|
w3_t[1] |= salt_buf3[1];
|
|
w3_t[2] |= salt_buf3[2];
|
|
w3_t[3] |= salt_buf3[3];
|
|
|
|
/**
|
|
* append salt
|
|
*/
|
|
|
|
u32 s0[4];
|
|
|
|
s0[0] = salt_buf0[0];
|
|
s0[1] = salt_buf0[1];
|
|
s0[2] = salt_buf0[2];
|
|
s0[3] = salt_buf0[3];
|
|
|
|
u32 s1[4];
|
|
|
|
s1[0] = salt_buf1[0];
|
|
s1[1] = salt_buf1[1];
|
|
s1[2] = salt_buf1[2];
|
|
s1[3] = salt_buf1[3];
|
|
|
|
u32 s2[4];
|
|
|
|
s2[0] = 0;
|
|
s2[1] = 0;
|
|
s2[2] = 0;
|
|
s2[3] = 0;
|
|
|
|
u32 s3[4];
|
|
|
|
s3[0] = 0;
|
|
s3[1] = 0;
|
|
s3[2] = 0;
|
|
s3[3] = 0;
|
|
|
|
switch_buffer_by_offset_le (s0, s1, s2, s3, salt_len + pw_len);
|
|
|
|
w0_t[0] |= s0[0];
|
|
w0_t[1] |= s0[1];
|
|
w0_t[2] |= s0[2];
|
|
w0_t[3] |= s0[3];
|
|
w1_t[0] |= s1[0];
|
|
w1_t[1] |= s1[1];
|
|
w1_t[2] |= s1[2];
|
|
w1_t[3] |= s1[3];
|
|
w2_t[0] |= s2[0];
|
|
w2_t[1] |= s2[1];
|
|
w2_t[2] |= s2[2];
|
|
w2_t[3] |= s2[3];
|
|
w3_t[0] |= s3[0];
|
|
w3_t[1] |= s3[1];
|
|
w3_t[2] |= s3[2];
|
|
w3_t[3] |= s3[3];
|
|
|
|
const u32 pw_salt_len = salt_len + pw_len + salt_len;
|
|
|
|
append_0x80_4x4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
|
|
|
|
w3_t[2] = pw_salt_len * 8;
|
|
|
|
/**
|
|
* md5
|
|
*/
|
|
|
|
u32 a = MD5M_A;
|
|
u32 b = MD5M_B;
|
|
u32 c = MD5M_C;
|
|
u32 d = MD5M_D;
|
|
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
|
|
MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
|
|
MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
|
|
MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
|
|
MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
|
|
|
|
MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
|
|
MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
|
|
MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
|
|
MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
|
|
MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
|
|
MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
|
|
MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
|
|
|
|
MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
|
|
MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
|
|
MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
|
|
MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
|
|
MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
|
|
MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
|
|
MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
|
|
|
|
MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
|
|
MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
|
|
MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
|
|
MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
|
|
MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
|
|
MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
|
|
MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
|
|
|
|
const u32 r0 = a;
|
|
const u32 r1 = d;
|
|
const u32 r2 = c;
|
|
const u32 r3 = b;
|
|
|
|
#include COMPARE_S
|
|
}
|
|
}
|
|
|
|
__kernel void m03800_s08 (__global pw_t *pws, __global kernel_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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|
|
|
|
__kernel void m03800_s16 (__global pw_t *pws, __global kernel_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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
|
{
|
|
}
|