diff --git a/OpenCL/m13900_a0.cl b/OpenCL/m13900_a0.cl new file mode 100644 index 000000000..db75c69fc --- /dev/null +++ b/OpenCL/m13900_a0.cl @@ -0,0 +1,626 @@ +/** + * Authors.....: Jens Steube + * magnum + * Michael Sprecher + * + * License.....: MIT + */ + +#define _SHA1_ + +#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_rp.h" +#include "inc_rp.cl" +#include "inc_simd.cl" + +#if VECT_SIZE == 1 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)]) +#elif VECT_SIZE == 2 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1]) +#elif VECT_SIZE == 4 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3]) +#elif VECT_SIZE == 8 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7]) +#elif VECT_SIZE == 16 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf]) +#endif + +void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5]) +{ + u32x A = digest[0]; + u32x B = digest[1]; + u32x C = digest[2]; + u32x D = digest[3]; + u32x E = digest[4]; + + u32x w0_t = w0[0]; + u32x w1_t = w0[1]; + u32x w2_t = w0[2]; + u32x w3_t = w0[3]; + u32x w4_t = w1[0]; + u32x w5_t = w1[1]; + u32x w6_t = w1[2]; + u32x w7_t = w1[3]; + u32x w8_t = w2[0]; + u32x w9_t = w2[1]; + u32x wa_t = w2[2]; + u32x wb_t = w2[3]; + u32x wc_t = w3[0]; + u32x wd_t = w3[1]; + u32x we_t = w3[2]; + u32x 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; +} + +__kernel void m13900_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_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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 pw_buf0[4]; + u32 pw_buf1[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]; + 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[3]; + + salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]); + salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]); + salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]); + + const u32 salt_len = salt_bufs[salt_pos].salt_len; + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + u32x w0[4] = { 0 }; + u32x w1[4] = { 0 }; + u32x w2[4] = { 0 }; + u32x w3[4] = { 0 }; + + const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1); + + append_0x80_2x4_VV (w0, w1, out_len); + + /** + * SHA1($pass) + */ + + w0[0] = swap32 (w0[0]); + w0[1] = swap32 (w0[1]); + w0[2] = swap32 (w0[2]); + w0[3] = swap32 (w0[3]); + w1[0] = swap32 (w1[0]); + w1[1] = swap32 (w1[1]); + w1[2] = swap32 (w1[2]); + w1[3] = swap32 (w1[3]); + w2[0] = swap32 (w2[0]); + w2[1] = swap32 (w2[1]); + w2[2] = swap32 (w2[2]); + w2[3] = swap32 (w2[3]); + w3[0] = swap32 (w3[0]); + w3[1] = swap32 (w3[1]); + w3[2] = 0; + w3[3] = out_len * 8; + + u32x digest[5]; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($pass)) + */ + + u32x a; + u32x b; + u32x c; + u32x d; + u32x e; + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($salt.SHA1($pass))) + */ + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]); + } +} + +__kernel void m13900_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_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) +{ +} + +__kernel void m13900_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_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) +{ +} + +__kernel void m13900_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_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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 pw_buf0[4]; + u32 pw_buf1[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]; + 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[3]; + + salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]); + salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]); + salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]); + + 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 += VECT_SIZE) + { + u32x w0[4] = { 0 }; + u32x w1[4] = { 0 }; + u32x w2[4] = { 0 }; + u32x w3[4] = { 0 }; + + const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1); + + append_0x80_2x4_VV (w0, w1, out_len); + + /** + * SHA1($pass) + */ + + w0[0] = swap32 (w0[0]); + w0[1] = swap32 (w0[1]); + w0[2] = swap32 (w0[2]); + w0[3] = swap32 (w0[3]); + w1[0] = swap32 (w1[0]); + w1[1] = swap32 (w1[1]); + w1[2] = swap32 (w1[2]); + w1[3] = swap32 (w1[3]); + w2[0] = swap32 (w2[0]); + w2[1] = swap32 (w2[1]); + w2[2] = swap32 (w2[2]); + w2[3] = swap32 (w2[3]); + w3[0] = swap32 (w3[0]); + w3[1] = swap32 (w3[1]); + w3[2] = 0; + w3[3] = out_len * 8; + + u32x digest[5]; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($pass)) + */ + + u32x a; + u32x b; + u32x c; + u32x d; + u32x e; + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($salt.SHA1($pass))) + */ + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]); + } +} + +__kernel void m13900_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_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) +{ +} + +__kernel void m13900_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_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) +{ +} diff --git a/OpenCL/m13900_a1.cl b/OpenCL/m13900_a1.cl new file mode 100644 index 000000000..dab4155f4 --- /dev/null +++ b/OpenCL/m13900_a1.cl @@ -0,0 +1,738 @@ +/** + * Author......: Jens Steube + * Michael Sprecher + * License.....: MIT + */ + +#define _SHA1_ + +#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_simd.cl" + +#if VECT_SIZE == 1 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)]) +#elif VECT_SIZE == 2 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1]) +#elif VECT_SIZE == 4 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3]) +#elif VECT_SIZE == 8 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7]) +#elif VECT_SIZE == 16 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf]) +#endif + +void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5]) +{ + u32x A = digest[0]; + u32x B = digest[1]; + u32x C = digest[2]; + u32x D = digest[3]; + u32x E = digest[4]; + + u32x w0_t = w0[0]; + u32x w1_t = w0[1]; + u32x w2_t = w0[2]; + u32x w3_t = w0[3]; + u32x w4_t = w1[0]; + u32x w5_t = w1[1]; + u32x w6_t = w1[2]; + u32x w7_t = w1[3]; + u32x w8_t = w2[0]; + u32x w9_t = w2[1]; + u32x wa_t = w2[2]; + u32x wb_t = w2[3]; + u32x wc_t = w3[0]; + u32x wd_t = w3[1]; + u32x we_t = w3[2]; + u32x 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; +} + +__kernel void m13900_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_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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 pw_buf0[4]; + u32 pw_buf1[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]; + 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_l_len = pws[gid].pw_len; + + /** + * salt + */ + + u32 salt_buf0[3]; + + salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]); + salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]); + salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]); + + const u32 salt_len = salt_bufs[salt_pos].salt_len; + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos); + + const u32x pw_len = pw_l_len + pw_r_len; + + /** + * concat password candidate + */ + + u32x wordl0[4] = { 0 }; + u32x wordl1[4] = { 0 }; + u32x wordl2[4] = { 0 }; + u32x wordl3[4] = { 0 }; + + wordl0[0] = pw_buf0[0]; + wordl0[1] = pw_buf0[1]; + wordl0[2] = pw_buf0[2]; + wordl0[3] = pw_buf0[3]; + wordl1[0] = pw_buf1[0]; + wordl1[1] = pw_buf1[1]; + wordl1[2] = pw_buf1[2]; + wordl1[3] = pw_buf1[3]; + + u32x wordr0[4] = { 0 }; + u32x wordr1[4] = { 0 }; + u32x wordr2[4] = { 0 }; + u32x wordr3[4] = { 0 }; + + wordr0[0] = ix_create_combt (combs_buf, il_pos, 0); + wordr0[1] = ix_create_combt (combs_buf, il_pos, 1); + wordr0[2] = ix_create_combt (combs_buf, il_pos, 2); + wordr0[3] = ix_create_combt (combs_buf, il_pos, 3); + wordr1[0] = ix_create_combt (combs_buf, il_pos, 4); + wordr1[1] = ix_create_combt (combs_buf, il_pos, 5); + wordr1[2] = ix_create_combt (combs_buf, il_pos, 6); + wordr1[3] = ix_create_combt (combs_buf, il_pos, 7); + + if (combs_mode == COMBINATOR_MODE_BASE_LEFT) + { + switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len); + } + else + { + switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len); + } + + u32x w0[4]; + u32x w1[4]; + u32x w2[4]; + u32x w3[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]; + w1[0] = wordl1[0] | wordr1[0]; + w1[1] = wordl1[1] | wordr1[1]; + w1[2] = wordl1[2] | wordr1[2]; + w1[3] = wordl1[3] | wordr1[3]; + w2[0] = wordl2[0] | wordr2[0]; + w2[1] = wordl2[1] | wordr2[1]; + w2[2] = wordl2[2] | wordr2[2]; + w2[3] = wordl2[3] | wordr2[3]; + w3[0] = wordl3[0] | wordr3[0]; + w3[1] = wordl3[1] | wordr3[1]; + w3[2] = wordl3[2] | wordr3[2]; + w3[3] = wordl3[3] | wordr3[3]; + + /** + * SHA1($pass) + */ + + w0[0] = swap32 (w0[0]); + w0[1] = swap32 (w0[1]); + w0[2] = swap32 (w0[2]); + w0[3] = swap32 (w0[3]); + w1[0] = swap32 (w1[0]); + w1[1] = swap32 (w1[1]); + w1[2] = swap32 (w1[2]); + w1[3] = swap32 (w1[3]); + w2[0] = swap32 (w2[0]); + w2[1] = swap32 (w2[1]); + w2[2] = swap32 (w2[2]); + w2[3] = swap32 (w2[3]); + w3[0] = swap32 (w3[0]); + w3[1] = swap32 (w3[1]); + w3[2] = 0; + w3[3] = pw_len * 8; + + u32x digest[5]; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($pass)) + */ + + u32x a; + u32x b; + u32x c; + u32x d; + u32x e; + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($salt.SHA1($pass))) + */ + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]); + } +} + +__kernel void m13900_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_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) +{ +} + +__kernel void m13900_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_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) +{ +} + +__kernel void m13900_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_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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 pw_buf0[4]; + u32 pw_buf1[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]; + 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_l_len = pws[gid].pw_len; + + /** + * salt + */ + + u32 salt_buf0[3]; + + salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]); + salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]); + salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]); + + 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 += VECT_SIZE) + { + const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos); + + const u32x pw_len = pw_l_len + pw_r_len; + + /** + * concat password candidate + */ + + u32x wordl0[4] = { 0 }; + u32x wordl1[4] = { 0 }; + u32x wordl2[4] = { 0 }; + u32x wordl3[4] = { 0 }; + + wordl0[0] = pw_buf0[0]; + wordl0[1] = pw_buf0[1]; + wordl0[2] = pw_buf0[2]; + wordl0[3] = pw_buf0[3]; + wordl1[0] = pw_buf1[0]; + wordl1[1] = pw_buf1[1]; + wordl1[2] = pw_buf1[2]; + wordl1[3] = pw_buf1[3]; + + u32x wordr0[4] = { 0 }; + u32x wordr1[4] = { 0 }; + u32x wordr2[4] = { 0 }; + u32x wordr3[4] = { 0 }; + + wordr0[0] = ix_create_combt (combs_buf, il_pos, 0); + wordr0[1] = ix_create_combt (combs_buf, il_pos, 1); + wordr0[2] = ix_create_combt (combs_buf, il_pos, 2); + wordr0[3] = ix_create_combt (combs_buf, il_pos, 3); + wordr1[0] = ix_create_combt (combs_buf, il_pos, 4); + wordr1[1] = ix_create_combt (combs_buf, il_pos, 5); + wordr1[2] = ix_create_combt (combs_buf, il_pos, 6); + wordr1[3] = ix_create_combt (combs_buf, il_pos, 7); + + if (combs_mode == COMBINATOR_MODE_BASE_LEFT) + { + switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len); + } + else + { + switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len); + } + + u32x w0[4]; + u32x w1[4]; + u32x w2[4]; + u32x w3[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]; + w1[0] = wordl1[0] | wordr1[0]; + w1[1] = wordl1[1] | wordr1[1]; + w1[2] = wordl1[2] | wordr1[2]; + w1[3] = wordl1[3] | wordr1[3]; + w2[0] = wordl2[0] | wordr2[0]; + w2[1] = wordl2[1] | wordr2[1]; + w2[2] = wordl2[2] | wordr2[2]; + w2[3] = wordl2[3] | wordr2[3]; + w3[0] = wordl3[0] | wordr3[0]; + w3[1] = wordl3[1] | wordr3[1]; + w3[2] = wordl3[2] | wordr3[2]; + w3[3] = wordl3[3] | wordr3[3]; + + /** + * SHA1($pass) + */ + + w0[0] = swap32 (w0[0]); + w0[1] = swap32 (w0[1]); + w0[2] = swap32 (w0[2]); + w0[3] = swap32 (w0[3]); + w1[0] = swap32 (w1[0]); + w1[1] = swap32 (w1[1]); + w1[2] = swap32 (w1[2]); + w1[3] = swap32 (w1[3]); + w2[0] = swap32 (w2[0]); + w2[1] = swap32 (w2[1]); + w2[2] = swap32 (w2[2]); + w2[3] = swap32 (w2[3]); + w3[0] = swap32 (w3[0]); + w3[1] = swap32 (w3[1]); + w3[2] = 0; + w3[3] = pw_len * 8; + + u32x digest[5]; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($pass)) + */ + + u32x a; + u32x b; + u32x c; + u32x d; + u32x e; + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + /** + * SHA1($salt.SHA1($salt.SHA1($pass))) + */ + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2[2] = 0x80000000; + w2[3] = 0; + w3[0] = 0; + w3[1] = 0; + w3[2] = 0; + w3[3] = 0; + + switch_buffer_by_offset_be (w0, w1, w2, w3, 9); + + w0[0] |= salt_buf0[0]; + w0[1] |= salt_buf0[1]; + w0[2] |= salt_buf0[2]; + w3[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0, w1, w2, w3, digest); + + COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]); + } +} + +__kernel void m13900_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_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) +{ +} + +__kernel void m13900_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_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) +{ +} diff --git a/OpenCL/m13900_a3.cl b/OpenCL/m13900_a3.cl new file mode 100644 index 000000000..1ada9b3ab --- /dev/null +++ b/OpenCL/m13900_a3.cl @@ -0,0 +1,968 @@ +/** + * Authors.....: Jens Steube + * Gabriele Gristina + * magnum + * Michael Sprecher + * + * License.....: MIT + */ + +#define _SHA1_ + +#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_simd.cl" + +#if VECT_SIZE == 1 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)]) +#elif VECT_SIZE == 2 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1]) +#elif VECT_SIZE == 4 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3]) +#elif VECT_SIZE == 8 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7]) +#elif VECT_SIZE == 16 +#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf]) +#endif + +void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5]) +{ + u32x A = digest[0]; + u32x B = digest[1]; + u32x C = digest[2]; + u32x D = digest[3]; + u32x E = digest[4]; + + u32x w0_t = w0[0]; + u32x w1_t = w0[1]; + u32x w2_t = w0[2]; + u32x w3_t = w0[3]; + u32x w4_t = w1[0]; + u32x w5_t = w1[1]; + u32x w6_t = w1[2]; + u32x w7_t = w1[3]; + u32x w8_t = w2[0]; + u32x w9_t = w2[1]; + u32x wa_t = w2[2]; + u32x wb_t = w2[3]; + u32x wc_t = w3[0]; + u32x wd_t = w3[1]; + u32x we_t = w3[2]; + u32x 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; +} + +void m13900m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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_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, __local u32 *l_bin2asc) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + + /** + * salt + */ + + u32 salt_buf0[3]; + + salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[0]); + salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[1]); + salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[2]); + + const u32 salt_len = salt_bufs[salt_pos].salt_len; + + /** + * loop + */ + + u32 w0l = w0[0]; + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x w0r = ix_create_bft (bfs_buf, il_pos); + + const u32x w0lr = w0l | w0r; + + u32x w0_t[4]; + u32x w1_t[4]; + u32x w2_t[4]; + u32x w3_t[4]; + + w0_t[0] = w0lr; + w0_t[1] = w0[1]; + w0_t[2] = w0[2]; + w0_t[3] = w0[3]; + w1_t[0] = w1[0]; + w1_t[1] = w1[1]; + w1_t[2] = w1[2]; + w1_t[3] = w1[3]; + w2_t[0] = w2[0]; + w2_t[1] = w2[1]; + w2_t[2] = w2[2]; + w2_t[3] = w2[3]; + w3_t[0] = w3[0]; + w3_t[1] = w3[1]; + w3_t[2] = 0; + w3_t[3] = pw_len * 8; + + /** + * SHA1($pass) + */ + + u32x digest[5]; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + + /** + * SHA1($salt.SHA1($pass)) + */ + + u32x a; + u32x b; + u32x c; + u32x d; + u32x e; + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0_t[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0_t[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0_t[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0_t[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1_t[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1_t[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1_t[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1_t[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2_t[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2_t[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2_t[2] = 0x80000000; + w2_t[3] = 0; + w3_t[0] = 0; + w3_t[1] = 0; + w3_t[2] = 0; + w3_t[3] = 0; + + switch_buffer_by_offset_be (w0_t, w1_t, w2_t, w3_t, 9); + + w0_t[0] |= salt_buf0[0]; + w0_t[1] |= salt_buf0[1]; + w0_t[2] |= salt_buf0[2]; + w3_t[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + + /** + * SHA1($salt.SHA1($salt.SHA1($pass))) + */ + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0_t[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0_t[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0_t[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0_t[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1_t[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1_t[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1_t[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1_t[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2_t[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2_t[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2_t[2] = 0x80000000; + w2_t[3] = 0; + w3_t[0] = 0; + w3_t[1] = 0; + w3_t[2] = 0; + w3_t[3] = 0; + + switch_buffer_by_offset_be (w0_t, w1_t, w2_t, w3_t, 9); + + w0_t[0] |= salt_buf0[0]; + w0_t[1] |= salt_buf0[1]; + w0_t[2] |= salt_buf0[2]; + w3_t[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + + COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]); + } +} + +void m13900s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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_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, __local u32 *l_bin2asc) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + + /** + * salt + */ + + u32 salt_buf0[4]; + u32 salt_buf1[4]; + u32 salt_buf2[4]; + + salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]); + salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]); + salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]); + salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]); + salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]); + salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]); + salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]); + salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]); + salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]); + salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]); + salt_buf2[2] = 0; + salt_buf2[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 + */ + + u32 w0l = w0[0]; + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x w0r = ix_create_bft (bfs_buf, il_pos); + + const u32x w0lr = w0l | w0r; + + u32x w0_t[4]; + u32x w1_t[4]; + u32x w2_t[4]; + u32x w3_t[4]; + + w0_t[0] = w0lr; + w0_t[1] = w0[1]; + w0_t[2] = w0[2]; + w0_t[3] = w0[3]; + w1_t[0] = w1[0]; + w1_t[1] = w1[1]; + w1_t[2] = w1[2]; + w1_t[3] = w1[3]; + w2_t[0] = w2[0]; + w2_t[1] = w2[1]; + w2_t[2] = w2[2]; + w2_t[3] = w2[3]; + w3_t[0] = w3[0]; + w3_t[1] = w3[1]; + w3_t[2] = 0; + w3_t[3] = pw_len * 8; + + /** + * SHA1($pass) + */ + + u32x digest[5]; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + + /** + * SHA1($salt.SHA1($pass)) + */ + + u32x a; + u32x b; + u32x c; + u32x d; + u32x e; + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0_t[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0_t[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0_t[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0_t[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1_t[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1_t[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1_t[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1_t[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2_t[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2_t[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2_t[2] = 0x80000000; + w2_t[3] = 0; + w3_t[0] = 0; + w3_t[1] = 0; + w3_t[2] = 0; + w3_t[3] = 0; + + switch_buffer_by_offset_be (w0_t, w1_t, w2_t, w3_t, 9); + + w0_t[0] |= salt_buf0[0]; + w0_t[1] |= salt_buf0[1]; + w0_t[2] |= salt_buf0[2]; + w3_t[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + + /** + * SHA1($salt.SHA1($salt.SHA1($pass))) + */ + + a = digest[0]; + b = digest[1]; + c = digest[2]; + d = digest[3]; + e = digest[4]; + + w0_t[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 24) & 255) << 16; + w0_t[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((a >> 8) & 255) << 16; + w0_t[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 24) & 255) << 16; + w0_t[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((b >> 8) & 255) << 16; + w1_t[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 24) & 255) << 16; + w1_t[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((c >> 8) & 255) << 16; + w1_t[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 24) & 255) << 16; + w1_t[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((d >> 8) & 255) << 16; + w2_t[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 24) & 255) << 16; + w2_t[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 + | uint_to_hex_lower8_le ((e >> 8) & 255) << 16; + w2_t[2] = 0x80000000; + w2_t[3] = 0; + w3_t[0] = 0; + w3_t[1] = 0; + w3_t[2] = 0; + w3_t[3] = 0; + + switch_buffer_by_offset_be (w0_t, w1_t, w2_t, w3_t, 9); + + w0_t[0] |= salt_buf0[0]; + w0_t[1] |= salt_buf0[1]; + w0_t[2] |= salt_buf0[2]; + w3_t[3] = 49 * 8; + + digest[0] = SHA1M_A; + digest[1] = SHA1M_B; + digest[2] = SHA1M_C; + digest[3] = SHA1M_D; + digest[4] = SHA1M_E; + + sha1_transform (w0_t, w1_t, w2_t, w3_t, digest); + + COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]); + } +} + +__kernel void m13900_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 *ss, __global void *ess, __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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = 0; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + + 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 pw_len = pws[gid].pw_len; + + /** + * main + */ + + m13900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc); +} + +__kernel void m13900_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 *ss, __global void *ess, __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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + 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 pw_len = pws[gid].pw_len; + + /** + * main + */ + + m13900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc); +} + +__kernel void m13900_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 *ss, __global void *ess, __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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + u32 w2[4]; + + w2[0] = pws[gid].i[ 8]; + w2[1] = pws[gid].i[ 9]; + w2[2] = pws[gid].i[10]; + w2[3] = pws[gid].i[11]; + + u32 w3[4]; + + w3[0] = pws[gid].i[12]; + w3[1] = pws[gid].i[13]; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len; + + /** + * main + */ + + m13900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc); +} + +__kernel void m13900_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 *ss, __global void *ess, __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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = 0; + w1[1] = 0; + w1[2] = 0; + w1[3] = 0; + + 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 pw_len = pws[gid].pw_len; + + /** + * main + */ + + m13900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc); +} + +__kernel void m13900_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 *ss, __global void *ess, __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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + 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 pw_len = pws[gid].pw_len; + + /** + * main + */ + + m13900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc); +} + +__kernel void m13900_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 *ss, __global void *ess, __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) +{ + /** + * modifier + */ + + const u32 gid = get_global_id (0); + const u32 lid = get_local_id (0); + const u32 lsz = get_local_size (0); + + /** + * shared + */ + + __local u32 l_bin2asc[256]; + + for (u32 i = lid; i < 256; i += lsz) + { + const u32 i0 = (i >> 0) & 15; + const u32 i1 = (i >> 4) & 15; + + l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0 + | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8; + } + + barrier (CLK_LOCAL_MEM_FENCE); + + if (gid >= gid_max) return; + + /** + * base + */ + + u32 w0[4]; + + w0[0] = pws[gid].i[ 0]; + w0[1] = pws[gid].i[ 1]; + w0[2] = pws[gid].i[ 2]; + w0[3] = pws[gid].i[ 3]; + + u32 w1[4]; + + w1[0] = pws[gid].i[ 4]; + w1[1] = pws[gid].i[ 5]; + w1[2] = pws[gid].i[ 6]; + w1[3] = pws[gid].i[ 7]; + + u32 w2[4]; + + w2[0] = pws[gid].i[ 8]; + w2[1] = pws[gid].i[ 9]; + w2[2] = pws[gid].i[10]; + w2[3] = pws[gid].i[11]; + + u32 w3[4]; + + w3[0] = pws[gid].i[12]; + w3[1] = pws[gid].i[13]; + w3[2] = 0; + w3[3] = 0; + + const u32 pw_len = pws[gid].pw_len; + + /** + * main + */ + + m13900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV0_buf, d_scryptV1_buf, d_scryptV2_buf, d_scryptV3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, l_bin2asc); +} diff --git a/docs/changes.txt b/docs/changes.txt index 1cfe5113d..1f03156d5 100644 --- a/docs/changes.txt +++ b/docs/changes.txt @@ -35,6 +35,12 @@ - Fixed a bug where hashcat reported an invalid password for a zero-length password in LM - Fixed a bug where hashcat did not take into account how long it takes to prepare a session when auto-aborting with --runtime is in use +## +## Algorithms +## + +- Added new hash-mode 13900 = OpenCart + * changes v2.01 -> v3.00: This release markes the fusion of "hashcat" and "oclHashcat" into "hashcat". diff --git a/include/shared.h b/include/shared.h index a9696da33..8e5e8f653 100644 --- a/include/shared.h +++ b/include/shared.h @@ -369,6 +369,7 @@ extern hc_thread_mutex_t mux_display; #define HT_13500 "PeopleSoft PS_TOKEN" #define HT_13600 "WinZip" #define HT_13800 "Windows 8+ phone PIN/Password" +#define HT_13900 "OpenCart" #define HT_00011 "Joomla < 2.5.18" #define HT_00012 "PostgreSQL" @@ -733,6 +734,8 @@ extern hc_thread_mutex_t mux_display; #define DISPLAY_LEN_MAX_13600 6 + 1 + 1 + 1 + 1 + 1 + 1 + 1 + 32 + 1 + 4 + 1 + 4 + 1 + 8192 + 1 + 20 + 1 + 7 #define DISPLAY_LEN_MIN_13800 64 + 1 + 256 #define DISPLAY_LEN_MAX_13800 64 + 1 + 256 +#define DISPLAY_LEN_MIN_13900 40 + 1 + 9 +#define DISPLAY_LEN_MAX_13900 40 + 1 + 9 #define DISPLAY_LEN_MIN_11 32 + 1 + 16 #define DISPLAY_LEN_MAX_11 32 + 1 + 32 @@ -1005,6 +1008,7 @@ extern hc_thread_mutex_t mux_display; #define KERN_TYPE_PSTOKEN 13500 #define KERN_TYPE_ZIP2 13600 #define KERN_TYPE_WIN8PHONE 13800 +#define KERN_TYPE_OPENCART 13900 /** * signatures @@ -1667,6 +1671,7 @@ int veracrypt_parse_hash_500000 (char *input_buf, uint input_len, hash_t *hash int veracrypt_parse_hash_327661 (char *input_buf, uint input_len, hash_t *hash_buf); int veracrypt_parse_hash_655331 (char *input_buf, uint input_len, hash_t *hash_buf); int win8phone_parse_hash (char *input_buf, uint input_len, hash_t *hash_buf); +int opencart_parse_hash (char *input_buf, uint input_len, hash_t *hash_buf); void naive_replace (char *s, const u8 key_char, const u8 replace_char); void naive_escape (char *s, size_t s_max, const u8 key_char, const u8 escape_char); diff --git a/src/hashcat.c b/src/hashcat.c index d11921f6b..6e75b2d27 100644 --- a/src/hashcat.c +++ b/src/hashcat.c @@ -154,7 +154,7 @@ double TARGET_MS_PROFILE[4] = { 2, 12, 96, 480 }; #define MAX_DICTSTAT 10000 -#define NUM_DEFAULT_BENCHMARK_ALGORITHMS 143 +#define NUM_DEFAULT_BENCHMARK_ALGORITHMS 144 #define NVIDIA_100PERCENTCPU_WORKAROUND 100 @@ -218,6 +218,7 @@ static uint default_benchmark_algorithms[NUM_DEFAULT_BENCHMARK_ALGORITHMS] = 2711, 2811, 8400, + 13900, 11, 2612, 7900, @@ -539,6 +540,7 @@ const char *USAGE_BIG[] = " 10000 | Django (PBKDF2-SHA256) | Forums, CMS, E-Commerce, Frameworks", " 3711 | Mediawiki B type | Forums, CMS, E-Commerce, Frameworks", " 7600 | Redmine | Forums, CMS, E-Commerce, Frameworks", + " 13900 | OpenCart | Forums, CMS, E-Commerce, Frameworks", " 12 | PostgreSQL | Database Server", " 131 | MSSQL(2000) | Database Server", " 132 | MSSQL(2005) | Database Server", @@ -6896,7 +6898,7 @@ int main (int argc, char **argv) return -1; } - if (hash_mode_chgd && hash_mode > 13800) // just added to remove compiler warnings for hash_mode_chgd + if (hash_mode_chgd && hash_mode > 13900) // just added to remove compiler warnings for hash_mode_chgd { log_error ("ERROR: Invalid hash-type specified"); @@ -11655,6 +11657,25 @@ int main (int argc, char **argv) dgst_pos3 = 6; break; + case 13900: hash_type = HASH_TYPE_SHA1; + salt_type = SALT_TYPE_INTERN; + attack_exec = ATTACK_EXEC_INSIDE_KERNEL; + opts_type = OPTS_TYPE_PT_GENERATE_BE + | OPTS_TYPE_PT_ADD80 + | OPTS_TYPE_PT_ADDBITS15; + kern_type = KERN_TYPE_OPENCART; + dgst_size = DGST_SIZE_4_5; + parse_func = opencart_parse_hash; + sort_by_digest = sort_by_digest_4_5; + opti_type = OPTI_TYPE_ZERO_BYTE + | OPTI_TYPE_PRECOMPUTE_INIT + | OPTI_TYPE_NOT_ITERATED; + dgst_pos0 = 3; + dgst_pos1 = 4; + dgst_pos2 = 2; + dgst_pos3 = 1; + break; + default: usage_mini_print (PROGNAME); return -1; } diff --git a/src/shared.c b/src/shared.c index 8488463e6..d5fac61e9 100644 --- a/src/shared.c +++ b/src/shared.c @@ -6147,6 +6147,7 @@ char *strhashtype (const uint hash_mode) case 13762: return ((char *) HT_13762); break; case 13763: return ((char *) HT_13763); break; case 13800: return ((char *) HT_13800); break; + case 13900: return ((char *) HT_13900); break; } return ((char *) "Unknown"); @@ -14979,6 +14980,37 @@ int wbb3_parse_hash (char *input_buf, uint input_len, hash_t *hash_buf) return (PARSER_OK); } +int opencart_parse_hash (char *input_buf, uint input_len, hash_t *hash_buf) +{ + if ((input_len < DISPLAY_LEN_MIN_13900) || (input_len > DISPLAY_LEN_MAX_13900)) return (PARSER_GLOBAL_LENGTH); + + u32 *digest = (u32 *) hash_buf->digest; + + salt_t *salt = hash_buf->salt; + + digest[0] = hex_to_u32 ((const u8 *) &input_buf[ 0]); + digest[1] = hex_to_u32 ((const u8 *) &input_buf[ 8]); + digest[2] = hex_to_u32 ((const u8 *) &input_buf[16]); + digest[3] = hex_to_u32 ((const u8 *) &input_buf[24]); + digest[4] = hex_to_u32 ((const u8 *) &input_buf[32]); + + if (input_buf[40] != data.separator) return (PARSER_SEPARATOR_UNMATCHED); + + uint salt_len = input_len - 40 - 1; + + char *salt_buf = input_buf + 40 + 1; + + char *salt_buf_ptr = (char *) salt->salt_buf; + + salt_len = parse_and_store_salt (salt_buf_ptr, salt_buf, salt_len); + + if ((salt_len != 9) || (salt_len == UINT_MAX)) return (PARSER_SALT_LENGTH); + + salt->salt_len = salt_len; + + return (PARSER_OK); +} + int racf_parse_hash (char *input_buf, uint input_len, hash_t *hash_buf) { const u8 ascii_to_ebcdic[] = diff --git a/tools/test.pl b/tools/test.pl index ef8dc4a77..bc7ce72d3 100755 --- a/tools/test.pl +++ b/tools/test.pl @@ -45,7 +45,7 @@ my $hashcat = "./hashcat"; my $MAX_LEN = 55; -my @modes = (0, 10, 11, 12, 20, 21, 22, 23, 30, 40, 50, 60, 100, 101, 110, 111, 112, 120, 121, 122, 125, 130, 131, 132, 133, 140, 141, 150, 160, 200, 300, 400, 500, 900, 1000, 1100, 1400, 1410, 1420, 1430, 1440, 1441, 1450, 1460, 1500, 1600, 1700, 1710, 1711, 1720, 1730, 1740, 1722, 1731, 1750, 1760, 1800, 2100, 2400, 2410, 2500, 2600, 2611, 2612, 2711, 2811, 3000, 3100, 3200, 3710, 3711, 3300, 3500, 3610, 3720, 3800, 3910, 4010, 4110, 4210, 4300, 4400, 4500, 4600, 4700, 4800, 4900, 5000, 5100, 5300, 5400, 5500, 5600, 5700, 5800, 6000, 6100, 6300, 6400, 6500, 6600, 6700, 6800, 6900, 7100, 7200, 7300, 7400, 7500, 7600, 7700, 7800, 7900, 8000, 8100, 8200, 8300, 8400, 8500, 8600, 8700, 8900, 9100, 9200, 9300, 9400, 9500, 9600, 9700, 9800, 9900, 10000, 10100, 10200, 10300, 10400, 10500, 10600, 10700, 10800, 10900, 11000, 11100, 11200, 11300, 11400, 11500, 11600, 11900, 12000, 12100, 12200, 12300, 12400, 12600, 12700, 12800, 12900, 13000, 13100, 13200, 13300, 13400, 13500, 13600, 13800); +my @modes = (0, 10, 11, 12, 20, 21, 22, 23, 30, 40, 50, 60, 100, 101, 110, 111, 112, 120, 121, 122, 125, 130, 131, 132, 133, 140, 141, 150, 160, 200, 300, 400, 500, 900, 1000, 1100, 1400, 1410, 1420, 1430, 1440, 1441, 1450, 1460, 1500, 1600, 1700, 1710, 1711, 1720, 1730, 1740, 1722, 1731, 1750, 1760, 1800, 2100, 2400, 2410, 2500, 2600, 2611, 2612, 2711, 2811, 3000, 3100, 3200, 3710, 3711, 3300, 3500, 3610, 3720, 3800, 3910, 4010, 4110, 4210, 4300, 4400, 4500, 4600, 4700, 4800, 4900, 5000, 5100, 5300, 5400, 5500, 5600, 5700, 5800, 6000, 6100, 6300, 6400, 6500, 6600, 6700, 6800, 6900, 7100, 7200, 7300, 7400, 7500, 7600, 7700, 7800, 7900, 8000, 8100, 8200, 8300, 8400, 8500, 8600, 8700, 8900, 9100, 9200, 9300, 9400, 9500, 9600, 9700, 9800, 9900, 10000, 10100, 10200, 10300, 10400, 10500, 10600, 10700, 10800, 10900, 11000, 11100, 11200, 11300, 11400, 11500, 11600, 11900, 12000, 12100, 12200, 12300, 12400, 12600, 12700, 12800, 12900, 13000, 13100, 13200, 13300, 13400, 13500, 13600, 13800, 13900); my %is_unicode = map { $_ => 1 } qw(30 40 130 131 132 133 140 141 1000 1100 1430 1440 1441 1730 1740 1731 5500 5600 8000 9400 9500 9600 9700 9800 11600 13500 13800); my %less_fifteen = map { $_ => 1 } qw(500 1600 1800 2400 2410 3200 6300 7400 10500 10700); @@ -226,7 +226,7 @@ sub verify $word = substr ($line, $index + 1); } # hash:salt - elsif ($mode == 10 || $mode == 11 || $mode == 12 || $mode == 20 || $mode == 21 || $mode == 22 || $mode == 23 || $mode == 30 || $mode == 40 || $mode == 50 || $mode == 60 || $mode == 110 || $mode == 112 || $mode == 120 || $mode == 121 || $mode == 130 || $mode == 140 || $mode == 150 || $mode == 160 || $mode == 1100 || $mode == 1410 || $mode == 1420 || $mode == 1430 || $mode == 1440 || $mode == 1450 || $mode == 1460 || $mode == 1710 || $mode == 1720 || $mode == 1730 || $mode == 1740 || $mode == 1750 || $mode == 1760 || $mode == 2410 || $mode == 2611 || $mode == 2711 || $mode == 2811 || $mode == 3100 || $mode == 3610 || $mode == 3710 || $mode == 3720 || $mode == 3800 || $mode == 3910 || $mode == 4010 || $mode == 4110 || $mode == 4210 || $mode == 4900 || $mode == 5800 || $mode == 7600 || $mode == 8400 || $mode == 11000 || $mode == 12600 || $mode == 13500 || $mode == 13800) + elsif ($mode == 10 || $mode == 11 || $mode == 12 || $mode == 20 || $mode == 21 || $mode == 22 || $mode == 23 || $mode == 30 || $mode == 40 || $mode == 50 || $mode == 60 || $mode == 110 || $mode == 112 || $mode == 120 || $mode == 121 || $mode == 130 || $mode == 140 || $mode == 150 || $mode == 160 || $mode == 1100 || $mode == 1410 || $mode == 1420 || $mode == 1430 || $mode == 1440 || $mode == 1450 || $mode == 1460 || $mode == 1710 || $mode == 1720 || $mode == 1730 || $mode == 1740 || $mode == 1750 || $mode == 1760 || $mode == 2410 || $mode == 2611 || $mode == 2711 || $mode == 2811 || $mode == 3100 || $mode == 3610 || $mode == 3710 || $mode == 3720 || $mode == 3800 || $mode == 3910 || $mode == 4010 || $mode == 4110 || $mode == 4210 || $mode == 4900 || $mode == 5800 || $mode == 7600 || $mode == 8400 || $mode == 11000 || $mode == 12600 || $mode == 13500 || $mode == 13800 || $mode == 13900) { # get hash my $index1 = index ($line, ":"); @@ -3163,6 +3163,10 @@ sub passthrough { $tmp_hash = gen_hash ($mode, $word_buf, substr ($salt_buf, 0, 256)); } + elsif ($mode == 13900) + { + $tmp_hash = gen_hash ($mode, $word_buf, substr ($salt_buf, 0, 9)); + } else { print "ERROR: Unsupported hash type\n"; @@ -3974,6 +3978,20 @@ sub single } } } + elsif ($mode == 13900) + { + for (my $i = 1; $i < 32; $i++) + { + if ($len != 0) + { + rnd ($mode, $len, 9); + } + else + { + rnd ($mode, $i, 9); + } + } + } } } @@ -5405,7 +5423,7 @@ sub gen_hash $tmp_hash = sprintf ("%s:%s:%s:%d", $hash_buf, $domain, $salt_hex, $iterations); } - elsif ($mode == 8400) + elsif ($mode == 8400 || $mode == 13900) { $hash_buf = sha1_hex ($salt_buf . sha1_hex ($salt_buf . sha1_hex ($word_buf)));