1
mirror of https://github.com/hashcat/hashcat synced 2024-12-27 05:13:45 +01:00
hashcat/OpenCL/m11750_a1-pure.cl
R. Yushaev 47bd838e25 Add VeraCrypt Streebog support
VeraCrypt added the possibility to use Streebog-512 as hashing algorithm
for the key derivation. This commit adds the necessary VeraCrypt kernels
as well as additional HMAC-Streebog kernels.

 - Add hash-mode 13771: VeraCrypt PBKDF2-HMAC-Streebog-512 + XTS 512 bit
 - Add hash-mode 13772: VeraCrypt PBKDF2-HMAC-Streebog-512 + XTS 1024 bit
 - Add hash-mode 13773: VeraCrypt PBKDF2-HMAC-Streebog-512 + XTS 1536 bit
 - Add hash-mode 11750: HMAC-Streebog-256 (key = $pass), big-endian
 - Add hash-mode 11760: HMAC-Streebog-256 (key = $salt), big-endian
 - Add hash-mode 11860: HMAC-Streebog-512 (key = $salt), big-endian
 - Add test suite for hash-modes 11750, 11760 and 11860
 - Improve pure Streebog kernels
2018-11-08 11:46:31 +01:00

241 lines
6.6 KiB
Common Lisp

/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
//#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_scalar.cl"
#include "inc_hash_streebog256.cl"
__kernel void m11750_mxx (__global pw_t *pws, __global 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 const void *esalt_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 gid = get_global_id (0);
const u64 lid = get_local_id (0);
const u64 lsz = get_local_size (0);
/**
* shared lookup table
*/
#ifdef REAL_SHM
__local u64a s_sbob_sl64[8][256];
for (MAYBE_VOLATILE u32 i = lid; i < 256; i += lsz)
{
s_sbob_sl64[0][i] = sbob_sl64[0][i];
s_sbob_sl64[1][i] = sbob_sl64[1][i];
s_sbob_sl64[2][i] = sbob_sl64[2][i];
s_sbob_sl64[3][i] = sbob_sl64[3][i];
s_sbob_sl64[4][i] = sbob_sl64[4][i];
s_sbob_sl64[5][i] = sbob_sl64[5][i];
s_sbob_sl64[6][i] = sbob_sl64[6][i];
s_sbob_sl64[7][i] = sbob_sl64[7][i];
}
barrier (CLK_LOCAL_MEM_FENCE);
#else
__constant u64a (*s_sbob_sl64)[256] = sbob_sl64;
#endif
if (gid >= gid_max) return;
/**
* base
*/
const u32 pw_len = pws[gid].pw_len;
u32 w[64] = { 0 };
for (int i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
{
w[idx] = swap32_S (pws[gid].i[idx]);
}
const u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 s[64] = { 0 };
for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
{
s[idx] = swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
}
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
const u32 comb_len = combs_buf[il_pos].pw_len;
u32 c[64];
#ifdef _unroll
#pragma unroll
#endif
for (int idx = 0; idx < 64; idx++)
{
c[idx] = swap32_S (combs_buf[il_pos].i[idx]);
}
switch_buffer_by_offset_1x64_be_S (c, pw_len);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 0; i < 64; i++)
{
c[i] |= w[i];
}
streebog256_hmac_ctx_t ctx;
streebog256_hmac_init (&ctx, c, pw_len + comb_len, s_sbob_sl64);
streebog256_hmac_update (&ctx, s, salt_len);
streebog256_hmac_final (&ctx);
const u32 r0 = l32_from_64_S (ctx.opad.h[0]);
const u32 r1 = h32_from_64_S (ctx.opad.h[0]);
const u32 r2 = l32_from_64_S (ctx.opad.h[1]);
const u32 r3 = h32_from_64_S (ctx.opad.h[1]);
COMPARE_M_SCALAR (r0, r1, r2, r3);
}
}
__kernel void m11750_sxx (__global pw_t *pws, __global 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 const void *esalt_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 gid = get_global_id (0);
const u64 lid = get_local_id (0);
const u64 lsz = get_local_size (0);
/**
* shared lookup table
*/
#ifdef REAL_SHM
__local u64a s_sbob_sl64[8][256];
for (MAYBE_VOLATILE u32 i = lid; i < 256; i += lsz)
{
s_sbob_sl64[0][i] = sbob_sl64[0][i];
s_sbob_sl64[1][i] = sbob_sl64[1][i];
s_sbob_sl64[2][i] = sbob_sl64[2][i];
s_sbob_sl64[3][i] = sbob_sl64[3][i];
s_sbob_sl64[4][i] = sbob_sl64[4][i];
s_sbob_sl64[5][i] = sbob_sl64[5][i];
s_sbob_sl64[6][i] = sbob_sl64[6][i];
s_sbob_sl64[7][i] = sbob_sl64[7][i];
}
barrier (CLK_LOCAL_MEM_FENCE);
#else
__constant u64a (*s_sbob_sl64)[256] = sbob_sl64;
#endif
if (gid >= gid_max) return;
/**
* 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]
};
/**
* base
*/
const u32 pw_len = pws[gid].pw_len;
u32 w[64] = { 0 };
for (int i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
{
w[idx] = swap32_S (pws[gid].i[idx]);
}
const u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 s[64] = { 0 };
for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
{
s[idx] = swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
}
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
const u32 comb_len = combs_buf[il_pos].pw_len;
u32 c[64];
#ifdef _unroll
#pragma unroll
#endif
for (int idx = 0; idx < 64; idx++)
{
c[idx] = swap32_S (combs_buf[il_pos].i[idx]);
}
switch_buffer_by_offset_1x64_be_S (c, pw_len);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 0; i < 64; i++)
{
c[i] |= w[i];
}
streebog256_hmac_ctx_t ctx;
streebog256_hmac_init (&ctx, c, pw_len + comb_len, s_sbob_sl64);
streebog256_hmac_update (&ctx, s, salt_len);
streebog256_hmac_final (&ctx);
const u32 r0 = l32_from_64_S (ctx.opad.h[0]);
const u32 r1 = h32_from_64_S (ctx.opad.h[0]);
const u32 r2 = l32_from_64_S (ctx.opad.h[1]);
const u32 r3 = h32_from_64_S (ctx.opad.h[1]);
COMPARE_S_SCALAR (r0, r1, r2, r3);
}
}