/**
- * Author......: Jens Steube <jens.steube@gmail.com>
+ * Authors.....: Jens Steube <jens.steube@gmail.com>
+ * Gabriele Gristina <matrix@hashcat.net>
+ *
* License.....: MIT
*/
#define _SHA512_
-#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 "types_ocl.c"
-#include "common.c"
+#include "inc_vendor.cl"
+#include "inc_hash_constants.h"
+#include "inc_hash_functions.cl"
+#include "inc_types.cl"
+#include "inc_common.cl"
__constant u32 te0[256] =
{
0x1b000000, 0x36000000,
};
-static void AES256_ExpandKey (u32 *userkey, u32 *rek, __local u32 s_te0[256], __local u32 s_te1[256], __local u32 s_te2[256], __local u32 s_te3[256], __local u32 s_te4[256])
+void AES256_ExpandKey (u32 *userkey, u32 *rek, __local u32 *s_te0, __local u32 *s_te1, __local u32 *s_te2, __local u32 *s_te3, __local u32 *s_te4)
{
rek[0] = userkey[0];
rek[1] = userkey[1];
}
}
-static void AES256_InvertKey (u32 *rdk, __local u32 s_td0[256], __local u32 s_td1[256], __local u32 s_td2[256], __local u32 s_td3[256], __local u32 s_td4[256], __local u32 s_te0[256], __local u32 s_te1[256], __local u32 s_te2[256], __local u32 s_te3[256], __local u32 s_te4[256])
+void AES256_InvertKey (u32 *rdk, __local u32 *s_td0, __local u32 *s_td1, __local u32 *s_td2, __local u32 *s_td3, __local u32 *s_td4, __local u32 *s_te0, __local u32 *s_te1, __local u32 *s_te2, __local u32 *s_te3, __local u32 *s_te4)
{
for (u32 i = 0, j = 56; i < j; i += 4, j -= 4)
{
}
}
-static void AES256_decrypt (const u32 *in, u32 *out, const u32 *rdk, __local u32 s_td0[256], __local u32 s_td1[256], __local u32 s_td2[256], __local u32 s_td3[256], __local u32 s_td4[256])
+void AES256_decrypt (const u32 *in, u32 *out, const u32 *rdk, __local u32 *s_td0, __local u32 *s_td1, __local u32 *s_td2, __local u32 *s_td3, __local u32 *s_td4)
{
u32 s0 = in[0] ^ rdk[0];
u32 s1 = in[1] ^ rdk[1];
SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
};
-static void sha512_transform (const u64 w[16], u64 dgst[8])
+void sha512_transform (const u64 w[16], u64 dgst[8])
{
u64 a = dgst[0];
u64 b = dgst[1];
u64 g = dgst[6];
u64 h = dgst[7];
- volatile u64 w0_t = w[ 0];
- volatile u64 w1_t = w[ 1];
- volatile u64 w2_t = w[ 2];
- volatile u64 w3_t = w[ 3];
- volatile u64 w4_t = w[ 4];
- volatile u64 w5_t = w[ 5];
- volatile u64 w6_t = w[ 6];
- volatile u64 w7_t = w[ 7];
- volatile u64 w8_t = w[ 8];
- volatile u64 w9_t = w[ 9];
- volatile u64 wa_t = w[10];
- volatile u64 wb_t = w[11];
- volatile u64 wc_t = w[12];
- volatile u64 wd_t = w[13];
- volatile u64 we_t = w[14];
- volatile u64 wf_t = w[15];
+ u64 w0_t = w[ 0];
+ u64 w1_t = w[ 1];
+ u64 w2_t = w[ 2];
+ u64 w3_t = w[ 3];
+ u64 w4_t = w[ 4];
+ u64 w5_t = w[ 5];
+ u64 w6_t = w[ 6];
+ u64 w7_t = w[ 7];
+ u64 w8_t = w[ 8];
+ u64 w9_t = w[ 9];
+ u64 wa_t = w[10];
+ u64 wb_t = w[11];
+ u64 wc_t = w[12];
+ u64 wd_t = w[13];
+ u64 we_t = w[14];
+ u64 wf_t = w[15];
#define ROUND_EXPAND() \
{ \
ROUND_STEP (0);
+ #ifdef _unroll
#pragma unroll
+ #endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
dgst[7] += h;
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m11300_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bitcoin_wallet_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 bitcoin_wallet_t *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)
+__kernel void m11300_init (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bitcoin_wallet_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 bitcoin_wallet_t *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 u32 gid_max)
{
/**
* base
u32 salt_len = salt_bufs[salt_pos].salt_len;
- switch_buffer_by_offset (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_len);
+ switch_buffer_by_offset_le (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_len);
w0[0] |= salt_buf0[0];
w0[1] |= salt_buf0[1];
* init
*/
- w0[0] = swap_workaround (w0[0]);
- w0[1] = swap_workaround (w0[1]);
- w0[2] = swap_workaround (w0[2]);
- w0[3] = swap_workaround (w0[3]);
- w1[0] = swap_workaround (w1[0]);
- w1[1] = swap_workaround (w1[1]);
- w1[2] = swap_workaround (w1[2]);
- w1[3] = swap_workaround (w1[3]);
- w2[0] = swap_workaround (w2[0]);
- w2[1] = swap_workaround (w2[1]);
- w2[2] = swap_workaround (w2[2]);
- w2[3] = swap_workaround (w2[3]);
- w3[0] = swap_workaround (w3[0]);
- w3[1] = swap_workaround (w3[1]);
- w3[2] = swap_workaround (w3[2]);
- w3[3] = swap_workaround (w3[3]);
+ w0[0] = swap32 (w0[0]);
+ w0[1] = swap32 (w0[1]);
+ w0[2] = swap32 (w0[2]);
+ w0[3] = swap32 (w0[3]);
+ w1[0] = swap32 (w1[0]);
+ w1[1] = swap32 (w1[1]);
+ w1[2] = swap32 (w1[2]);
+ w1[3] = swap32 (w1[3]);
+ w2[0] = swap32 (w2[0]);
+ w2[1] = swap32 (w2[1]);
+ w2[2] = swap32 (w2[2]);
+ w2[3] = swap32 (w2[3]);
+ w3[0] = swap32 (w3[0]);
+ w3[1] = swap32 (w3[1]);
+ w3[2] = swap32 (w3[2]);
+ w3[3] = swap32 (w3[3]);
u64 w[16];
tmps[gid].dgst[7] = dgst[7];
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m11300_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bitcoin_wallet_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 bitcoin_wallet_t *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)
+__kernel void m11300_loop (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bitcoin_wallet_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 bitcoin_wallet_t *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 u32 gid_max)
{
const u32 gid = get_global_id (0);
tmps[gid].dgst[7] = dgst[7];
}
-__kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m11300_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bitcoin_wallet_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 bitcoin_wallet_t *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)
+__kernel void m11300_comp (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bitcoin_wallet_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 bitcoin_wallet_t *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 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);
/**
* aes shared
*/
- const u32 lid4 = lid * 4;
-
__local u32 s_td0[256];
__local u32 s_td1[256];
__local u32 s_td2[256];
__local u32 s_te3[256];
__local u32 s_te4[256];
- s_td0[lid4 + 0] = td0[lid4 + 0];
- s_td0[lid4 + 1] = td0[lid4 + 1];
- s_td0[lid4 + 2] = td0[lid4 + 2];
- s_td0[lid4 + 3] = td0[lid4 + 3];
-
- s_td1[lid4 + 0] = td1[lid4 + 0];
- s_td1[lid4 + 1] = td1[lid4 + 1];
- s_td1[lid4 + 2] = td1[lid4 + 2];
- s_td1[lid4 + 3] = td1[lid4 + 3];
-
- s_td2[lid4 + 0] = td2[lid4 + 0];
- s_td2[lid4 + 1] = td2[lid4 + 1];
- s_td2[lid4 + 2] = td2[lid4 + 2];
- s_td2[lid4 + 3] = td2[lid4 + 3];
-
- s_td3[lid4 + 0] = td3[lid4 + 0];
- s_td3[lid4 + 1] = td3[lid4 + 1];
- s_td3[lid4 + 2] = td3[lid4 + 2];
- s_td3[lid4 + 3] = td3[lid4 + 3];
-
- s_td4[lid4 + 0] = td4[lid4 + 0];
- s_td4[lid4 + 1] = td4[lid4 + 1];
- s_td4[lid4 + 2] = td4[lid4 + 2];
- s_td4[lid4 + 3] = td4[lid4 + 3];
-
- s_te0[lid4 + 0] = te0[lid4 + 0];
- s_te0[lid4 + 1] = te0[lid4 + 1];
- s_te0[lid4 + 2] = te0[lid4 + 2];
- s_te0[lid4 + 3] = te0[lid4 + 3];
-
- s_te1[lid4 + 0] = te1[lid4 + 0];
- s_te1[lid4 + 1] = te1[lid4 + 1];
- s_te1[lid4 + 2] = te1[lid4 + 2];
- s_te1[lid4 + 3] = te1[lid4 + 3];
-
- s_te2[lid4 + 0] = te2[lid4 + 0];
- s_te2[lid4 + 1] = te2[lid4 + 1];
- s_te2[lid4 + 2] = te2[lid4 + 2];
- s_te2[lid4 + 3] = te2[lid4 + 3];
-
- s_te3[lid4 + 0] = te3[lid4 + 0];
- s_te3[lid4 + 1] = te3[lid4 + 1];
- s_te3[lid4 + 2] = te3[lid4 + 2];
- s_te3[lid4 + 3] = te3[lid4 + 3];
-
- s_te4[lid4 + 0] = te4[lid4 + 0];
- s_te4[lid4 + 1] = te4[lid4 + 1];
- s_te4[lid4 + 2] = te4[lid4 + 2];
- s_te4[lid4 + 3] = te4[lid4 + 3];
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ s_td0[i] = td0[i];
+ s_td1[i] = td1[i];
+ s_td2[i] = td2[i];
+ s_td3[i] = td3[i];
+ s_td4[i] = td4[i];
+
+ s_te0[i] = te0[i];
+ s_te1[i] = te1[i];
+ s_te2[i] = te2[i];
+ s_te3[i] = te3[i];
+ s_te4[i] = te4[i];
+ }
barrier (CLK_LOCAL_MEM_FENCE);
{
u32 data[4];
- data[0] = swap_workaround (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 0]);
- data[1] = swap_workaround (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 1]);
- data[2] = swap_workaround (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 2]);
- data[3] = swap_workaround (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 3]);
+ data[0] = swap32 (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 0]);
+ data[1] = swap32 (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 1]);
+ data[2] = swap32 (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 2]);
+ data[3] = swap32 (esalt_bufs[salt_pos].cry_master_buf[(i / 4) + 3]);
AES256_decrypt (data, out, rk, s_td0, s_td1, s_td2, s_td3, s_td4);
&& (out[2] == 0x10101010)
&& (out[3] == 0x10101010))
{
- mark_hash (plains_buf, hashes_shown, digests_offset + 0, gid, 0);
-
- d_return_buf[lid] = 1;
+ mark_hash (plains_buf, d_return_buf, salt_pos, 0, digests_offset + 0, gid, 0);
}
}