/**
- * Author......: Jens Steube <jens.steube@gmail.com>
+ * Authors.....: Jens Steube <jens.steube@gmail.com>
+ * Gabriele Gristina <matrix@hashcat.net>
+ *
* License.....: MIT
*/
#define _LOTUS8_
-#include "include/constants.h"
-#include "include/kernel_vendor.h"
-
-#define DGST_R0 0
-#define DGST_R1 1
-#define DGST_R2 2
-#define DGST_R3 3
-
-#include "include/kernel_functions.c"
+#include "inc_vendor.cl"
+#include "inc_hash_constants.h"
+#include "inc_hash_functions.cl"
#undef _SHA1_
-#include "types_ocl.c"
-#include "common.c"
+#include "inc_types.cl"
+#include "inc_common.cl"
-#define COMPARE_S "check_single_comp4.c"
-#define COMPARE_M "check_multi_comp4.c"
+#define COMPARE_S "inc_comp_single.cl"
+#define COMPARE_M "inc_comp_multi.cl"
__constant char lotus64_table[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz+/";
+#define uint_to_hex_upper8(i) l_bin2asc[(i)]
+
__constant u32 lotus_magic_table[256] =
{
0xbd, 0x56, 0xea, 0xf2, 0xa2, 0xf1, 0xac, 0x2a,
0x29, 0x39, 0xb9, 0xe9, 0x4c, 0xff, 0x43, 0xab,
};
-#define BOX(S,i) (S)[(i)]
-
-#define uint_to_hex_upper8(i) l_bin2asc[(i)]
-
-static void lotus_mix (u32 *in, __local u32 s_lotus_magic_table[256])
+#if VECT_SIZE == 1
+#define BOX1(S,i) (S)[(i)]
+#elif VECT_SIZE == 2
+#define BOX1(S,i) (u32x) ((S)[(i).s0], (S)[(i).s1])
+#elif VECT_SIZE == 4
+#define BOX1(S,i) (u32x) ((S)[(i).s0], (S)[(i).s1], (S)[(i).s2], (S)[(i).s3])
+#elif VECT_SIZE == 8
+#define BOX1(S,i) (u32x) ((S)[(i).s0], (S)[(i).s1], (S)[(i).s2], (S)[(i).s3], (S)[(i).s4], (S)[(i).s5], (S)[(i).s6], (S)[(i).s7])
+#elif VECT_SIZE == 16
+#define BOX1(S,i) (u32x) ((S)[(i).s0], (S)[(i).s1], (S)[(i).s2], (S)[(i).s3], (S)[(i).s4], (S)[(i).s5], (S)[(i).s6], (S)[(i).s7], (S)[(i).s8], (S)[(i).s9], (S)[(i).sa], (S)[(i).sb], (S)[(i).sc], (S)[(i).sd], (S)[(i).se], (S)[(i).sf])
+#endif
+
+void lotus_mix (u32x *in, __local u32 *s_lotus_magic_table)
{
- u32 p = 0;
+ u32x p = 0;
for (int i = 0; i < 18; i++)
{
u32 s = 48;
- #pragma unroll 12
for (int j = 0; j < 12; j++)
{
- u32 tmp_in = in[j];
- u32 tmp_out = 0;
+ u32x tmp_in = in[j];
+ u32x tmp_out = 0;
- p = (p + s--) & 0xff; p = ((tmp_in >> 0) & 0xff) ^ BOX (s_lotus_magic_table, p); tmp_out |= p << 0;
- p = (p + s--) & 0xff; p = ((tmp_in >> 8) & 0xff) ^ BOX (s_lotus_magic_table, p); tmp_out |= p << 8;
- p = (p + s--) & 0xff; p = ((tmp_in >> 16) & 0xff) ^ BOX (s_lotus_magic_table, p); tmp_out |= p << 16;
- p = (p + s--) & 0xff; p = ((tmp_in >> 24) & 0xff) ^ BOX (s_lotus_magic_table, p); tmp_out |= p << 24;
+ p = (p + s--) & 0xff; p = ((tmp_in >> 0) & 0xff) ^ BOX1 (s_lotus_magic_table, p); tmp_out |= p << 0;
+ p = (p + s--) & 0xff; p = ((tmp_in >> 8) & 0xff) ^ BOX1 (s_lotus_magic_table, p); tmp_out |= p << 8;
+ p = (p + s--) & 0xff; p = ((tmp_in >> 16) & 0xff) ^ BOX1 (s_lotus_magic_table, p); tmp_out |= p << 16;
+ p = (p + s--) & 0xff; p = ((tmp_in >> 24) & 0xff) ^ BOX1 (s_lotus_magic_table, p); tmp_out |= p << 24;
in[j] = tmp_out;
}
}
}
-static void lotus_transform_password (u32 in[4], u32 out[4], __local u32 s_lotus_magic_table[256])
+void lotus_transform_password (u32x in[4], u32x out[4], __local u32 *s_lotus_magic_table)
{
- u32 t = out[3] >> 24;
+ u32x t = out[3] >> 24;
- u32 c;
+ u32x c;
- #pragma unroll 4
+ #ifdef _unroll
+ #pragma unroll
+ #endif
for (int i = 0; i < 4; i++)
{
- t ^= (in[i] >> 0) & 0xff; c = BOX (s_lotus_magic_table, t); out[i] ^= c << 0; t = ((out[i] >> 0) & 0xff);
- t ^= (in[i] >> 8) & 0xff; c = BOX (s_lotus_magic_table, t); out[i] ^= c << 8; t = ((out[i] >> 8) & 0xff);
- t ^= (in[i] >> 16) & 0xff; c = BOX (s_lotus_magic_table, t); out[i] ^= c << 16; t = ((out[i] >> 16) & 0xff);
- t ^= (in[i] >> 24) & 0xff; c = BOX (s_lotus_magic_table, t); out[i] ^= c << 24; t = ((out[i] >> 24) & 0xff);
+ t ^= (in[i] >> 0) & 0xff; c = BOX1 (s_lotus_magic_table, t); out[i] ^= c << 0; t = ((out[i] >> 0) & 0xff);
+ t ^= (in[i] >> 8) & 0xff; c = BOX1 (s_lotus_magic_table, t); out[i] ^= c << 8; t = ((out[i] >> 8) & 0xff);
+ t ^= (in[i] >> 16) & 0xff; c = BOX1 (s_lotus_magic_table, t); out[i] ^= c << 16; t = ((out[i] >> 16) & 0xff);
+ t ^= (in[i] >> 24) & 0xff; c = BOX1 (s_lotus_magic_table, t); out[i] ^= c << 24; t = ((out[i] >> 24) & 0xff);
}
}
-static void pad (u32 w[4], const u32 len)
+void pad (u32 w[4], const u32 len)
{
const u32 val = 16 - len;
}
}
-static void mdtransform_norecalc (u32 state[4], u32 block[4], __local u32 s_lotus_magic_table[256])
+void mdtransform_norecalc (u32x state[4], u32x block[4], __local u32 *s_lotus_magic_table)
{
- u32 x[12];
+ u32x x[12];
x[ 0] = state[0];
x[ 1] = state[1];
state[3] = x[3];
}
-static void mdtransform (u32 state[4], u32 checksum[4], u32 block[4], __local u32 s_lotus_magic_table[256])
+void mdtransform (u32x state[4], u32x checksum[4], u32x block[4], __local u32 *s_lotus_magic_table)
{
mdtransform_norecalc (state, block, s_lotus_magic_table);
lotus_transform_password (block, checksum, s_lotus_magic_table);
}
-static void domino_big_md (const u32 saved_key[16], const u32 size, u32 state[4], __local u32 s_lotus_magic_table[256])
+void domino_big_md (const u32x saved_key[16], const u32 size, u32x state[4], __local u32 *s_lotus_magic_table)
{
- u32 checksum[4];
+ u32x checksum[4];
checksum[0] = 0;
checksum[1] = 0;
checksum[2] = 0;
checksum[3] = 0;
- u32 block[4];
+ u32x block[4];
block[0] = 0;
block[1] = 0;
mdtransform (state, checksum, block, s_lotus_magic_table);
}
- u32 left = size - curpos;
-
block[0] = saved_key[idx + 0];
block[1] = saved_key[idx + 1];
block[2] = saved_key[idx + 2];
mdtransform_norecalc (state, checksum, s_lotus_magic_table);
}
-static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
+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];
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])
+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;
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])
+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];
sha1_transform (w0, w1, w2, w3, digest);
}
-static void base64_encode (u8 *base64_hash, const u32 len, const u8 *base64_plain)
+void base64_encode (u8 *base64_hash, const u32 len, const u8 *base64_plain)
{
u8 *out_ptr = (u8 *) base64_hash;
u8 *in_ptr = (u8 *) base64_plain;
}
}
-static void lotus6_base64_encode (u8 base64_hash[24], const u32 salt0, const u32 salt1, u32 a, u32 b, u32 c)
+void lotus6_base64_encode (u8 base64_hash[24], const u32 salt0, const u32 salt1, u32 a, u32 b, u32 c)
{
uchar4 salt0c = as_uchar4 (salt0);
uchar4 salt1c = as_uchar4 (salt1);
base64_hash[21] = ')';
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09100_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global lotus8_tmp_t *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 wpa_t *wpa_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)
+__kernel void m09100_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global lotus8_tmp_t *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 wpa_t *wpa_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 u32 gid_max)
{
/**
* base
const u32 gid = get_global_id (0);
const u32 lid = get_local_id (0);
+ const u32 lsz = get_local_size (0);
/**
- * bin2asc table
+ * sbox
*/
- __local u32 l_bin2asc[256];
-
- const u32 lid4 = lid * 4;
-
- const u32 lid40 = lid4 + 0;
- const u32 lid41 = lid4 + 1;
- const u32 lid42 = lid4 + 2;
- const u32 lid43 = lid4 + 3;
-
- const u32 v400 = (lid40 >> 0) & 15;
- const u32 v401 = (lid40 >> 4) & 15;
- const u32 v410 = (lid41 >> 0) & 15;
- const u32 v411 = (lid41 >> 4) & 15;
- const u32 v420 = (lid42 >> 0) & 15;
- const u32 v421 = (lid42 >> 4) & 15;
- const u32 v430 = (lid43 >> 0) & 15;
- const u32 v431 = (lid43 >> 4) & 15;
-
- l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'A' - 10 + v400) << 8
- | ((v401 < 10) ? '0' + v401 : 'A' - 10 + v401) << 0;
- l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'A' - 10 + v410) << 8
- | ((v411 < 10) ? '0' + v411 : 'A' - 10 + v411) << 0;
- l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'A' - 10 + v420) << 8
- | ((v421 < 10) ? '0' + v421 : 'A' - 10 + v421) << 0;
- l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'A' - 10 + v430) << 8
- | ((v431 < 10) ? '0' + v431 : 'A' - 10 + v431) << 0;
+ __local u32 s_lotus_magic_table[256];
- barrier (CLK_LOCAL_MEM_FENCE);
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ s_lotus_magic_table[i] = lotus_magic_table[i];
+ }
- /**
- * sbox
- */
+ __local u32 l_bin2asc[256];
- __local u32 s_lotus_magic_table[256];
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
- s_lotus_magic_table[lid4 + 0] = lotus_magic_table[lid4 + 0];
- s_lotus_magic_table[lid4 + 1] = lotus_magic_table[lid4 + 1];
- s_lotus_magic_table[lid4 + 2] = lotus_magic_table[lid4 + 2];
- s_lotus_magic_table[lid4 + 3] = lotus_magic_table[lid4 + 3];
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'A' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'A' - 10 + i1) << 0;
+ }
barrier (CLK_LOCAL_MEM_FENCE);
if (gid >= gid_max) return;
+ /**
+ * base
+ */
u32 w[16];
salt_buf3[3] = 0;
const u32 salt0 = salt_buf0[0];
- const u32 salt1 = salt_buf0[1] & 0xff | '(' << 8;
+ const u32 salt1 = (salt_buf0[1] & 0xff) | ('(' << 8);
/**
* Lotus 6 hash - SEC_pwddigest_V2
tmps[gid].out[4] = dgst[4];
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09100_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global lotus8_tmp_t *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 wpa_t *wpa_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)
+__kernel void m09100_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global lotus8_tmp_t *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 wpa_t *wpa_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 u32 gid_max)
{
const u32 gid = get_global_id (0);
tmps[gid].out[4] = out[4];
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m09100_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global lotus8_tmp_t *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 wpa_t *wpa_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)
+__kernel void m09100_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global lotus8_tmp_t *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 wpa_t *wpa_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 u32 gid_max)
{
/**
* base