From 83d37ebeff8758dee0a7d74c6e40607c5ff95462 Mon Sep 17 00:00:00 2001 From: jsteube Date: Tue, 1 Aug 2017 14:16:27 +0200 Subject: [PATCH] Add pure kernels for FortiGate (FortiOS) --- OpenCL/m07000_a0.cl | 199 +++++++++++++++++++++++++++++++++++++++++ OpenCL/m07000_a1.cl | 170 +++++++++++++++++++++++++++++++++++ OpenCL/m07000_a3.cl | 212 ++++++++++++++++++++++++++++++++++++++++++++ src/interface.c | 2 +- 4 files changed, 582 insertions(+), 1 deletion(-) create mode 100644 OpenCL/m07000_a0.cl create mode 100644 OpenCL/m07000_a1.cl create mode 100644 OpenCL/m07000_a3.cl diff --git a/OpenCL/m07000_a0.cl b/OpenCL/m07000_a0.cl new file mode 100644 index 000000000..40201efbf --- /dev/null +++ b/OpenCL/m07000_a0.cl @@ -0,0 +1,199 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +//#define NEW_SIMD_CODE + +#include "inc_vendor.cl" +#include "inc_hash_constants.h" +#include "inc_hash_functions.cl" +#include "inc_types.cl" +#include "inc_common.cl" +#include "inc_rp.h" +#include "inc_rp.cl" +#include "inc_scalar.cl" +#include "inc_hash_sha1.cl" + +__kernel void m07000_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +{ + /** + * modifier + */ + + const u32 lid = get_local_id (0); + const u32 gid = get_global_id (0); + + if (gid >= gid_max) return; + + /** + * base + */ + + const u32 pw_len = pws[gid].pw_len; + + const u32 pw_lenv = ceil ((float) pw_len / 4); + + u32 w[64] = { 0 }; + + for (int idx = 0; idx < pw_lenv; idx++) + { + w[idx] = pws[gid].i[idx]; + + barrier (CLK_GLOBAL_MEM_FENCE); + } + + sha1_ctx_t ctx0; + + sha1_init (&ctx0); + + sha1_update_global_swap (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len); + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos++) + { + // todo: add rules engine + + sha1_ctx_t ctx = ctx0; + + sha1_update_swap (&ctx, w, pw_len); + + /** + * pepper + */ + + u32 p0[4]; + u32 p1[4]; + u32 p2[4]; + u32 p3[4]; + + p0[0] = swap32_S (FORTIGATE_A); + p0[1] = swap32_S (FORTIGATE_B); + p0[2] = swap32_S (FORTIGATE_C); + p0[3] = swap32_S (FORTIGATE_D); + p1[0] = swap32_S (FORTIGATE_E); + p1[1] = swap32_S (FORTIGATE_F); + p1[2] = 0; + p1[3] = 0; + p2[0] = 0; + p2[1] = 0; + p2[2] = 0; + p2[3] = 0; + p3[0] = 0; + p3[1] = 0; + p3[2] = 0; + p3[3] = 0; + + sha1_update_64 (&ctx, p0, p1, p2, p3, 24); + + sha1_final (&ctx); + + const u32 r0 = ctx.h[DGST_R0]; + const u32 r1 = ctx.h[DGST_R1]; + const u32 r2 = ctx.h[DGST_R2]; + const u32 r3 = ctx.h[DGST_R3]; + + COMPARE_M_SCALAR (r0, r1, r2, r3); + } +} + +__kernel void m07000_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +{ + /** + * modifier + */ + + const u32 lid = get_local_id (0); + const u32 gid = get_global_id (0); + + if (gid >= gid_max) return; + + /** + * digest + */ + + const u32 search[4] = + { + digests_buf[digests_offset].digest_buf[DGST_R0], + digests_buf[digests_offset].digest_buf[DGST_R1], + digests_buf[digests_offset].digest_buf[DGST_R2], + digests_buf[digests_offset].digest_buf[DGST_R3] + }; + + + /** + * base + */ + + const u32 pw_len = pws[gid].pw_len; + + const u32 pw_lenv = ceil ((float) pw_len / 4); + + u32 w[64] = { 0 }; + + for (int idx = 0; idx < pw_lenv; idx++) + { + w[idx] = pws[gid].i[idx]; + + barrier (CLK_GLOBAL_MEM_FENCE); + } + + sha1_ctx_t ctx0; + + sha1_init (&ctx0); + + sha1_update_global_swap (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len); + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos++) + { + // todo: add rules engine + + sha1_ctx_t ctx = ctx0; + + sha1_update_swap (&ctx, w, pw_len); + + /** + * pepper + */ + + u32 p0[4]; + u32 p1[4]; + u32 p2[4]; + u32 p3[4]; + + p0[0] = swap32_S (FORTIGATE_A); + p0[1] = swap32_S (FORTIGATE_B); + p0[2] = swap32_S (FORTIGATE_C); + p0[3] = swap32_S (FORTIGATE_D); + p1[0] = swap32_S (FORTIGATE_E); + p1[1] = swap32_S (FORTIGATE_F); + p1[2] = 0; + p1[3] = 0; + p2[0] = 0; + p2[1] = 0; + p2[2] = 0; + p2[3] = 0; + p3[0] = 0; + p3[1] = 0; + p3[2] = 0; + p3[3] = 0; + + sha1_update_64 (&ctx, p0, p1, p2, p3, 24); + + sha1_final (&ctx); + + const u32 r0 = ctx.h[DGST_R0]; + const u32 r1 = ctx.h[DGST_R1]; + const u32 r2 = ctx.h[DGST_R2]; + const u32 r3 = ctx.h[DGST_R3]; + + COMPARE_S_SCALAR (r0, r1, r2, r3); + } +} diff --git a/OpenCL/m07000_a1.cl b/OpenCL/m07000_a1.cl new file mode 100644 index 000000000..34e434180 --- /dev/null +++ b/OpenCL/m07000_a1.cl @@ -0,0 +1,170 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +//#define NEW_SIMD_CODE + +#include "inc_vendor.cl" +#include "inc_hash_constants.h" +#include "inc_hash_functions.cl" +#include "inc_types.cl" +#include "inc_common.cl" +#include "inc_scalar.cl" +#include "inc_hash_sha1.cl" + +__kernel void m07000_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +{ + /** + * modifier + */ + + const u32 lid = get_local_id (0); + const u32 gid = get_global_id (0); + + if (gid >= gid_max) return; + + /** + * base + */ + + sha1_ctx_t ctx0; + + sha1_init (&ctx0); + + sha1_update_global_swap (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len); + + sha1_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len); + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos++) + { + sha1_ctx_t ctx = ctx0; + + sha1_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len); + + /** + * pepper + */ + + u32 p0[4]; + u32 p1[4]; + u32 p2[4]; + u32 p3[4]; + + p0[0] = swap32_S (FORTIGATE_A); + p0[1] = swap32_S (FORTIGATE_B); + p0[2] = swap32_S (FORTIGATE_C); + p0[3] = swap32_S (FORTIGATE_D); + p1[0] = swap32_S (FORTIGATE_E); + p1[1] = swap32_S (FORTIGATE_F); + p1[2] = 0; + p1[3] = 0; + p2[0] = 0; + p2[1] = 0; + p2[2] = 0; + p2[3] = 0; + p3[0] = 0; + p3[1] = 0; + p3[2] = 0; + p3[3] = 0; + + sha1_update_64 (&ctx, p0, p1, p2, p3, 24); + + sha1_final (&ctx); + + const u32 r0 = ctx.h[DGST_R0]; + const u32 r1 = ctx.h[DGST_R1]; + const u32 r2 = ctx.h[DGST_R2]; + const u32 r3 = ctx.h[DGST_R3]; + + COMPARE_M_SCALAR (r0, r1, r2, r3); + } +} + +__kernel void m07000_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +{ + /** + * modifier + */ + + const u32 lid = get_local_id (0); + const u32 gid = get_global_id (0); + + if (gid >= gid_max) return; + + /** + * digest + */ + + const u32 search[4] = + { + digests_buf[digests_offset].digest_buf[DGST_R0], + digests_buf[digests_offset].digest_buf[DGST_R1], + digests_buf[digests_offset].digest_buf[DGST_R2], + digests_buf[digests_offset].digest_buf[DGST_R3] + }; + + /** + * base + */ + + sha1_ctx_t ctx0; + + sha1_init (&ctx0); + + sha1_update_global_swap (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len); + + sha1_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len); + + /** + * loop + */ + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos++) + { + sha1_ctx_t ctx = ctx0; + + sha1_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len); + + /** + * pepper + */ + + u32 p0[4]; + u32 p1[4]; + u32 p2[4]; + u32 p3[4]; + + p0[0] = swap32_S (FORTIGATE_A); + p0[1] = swap32_S (FORTIGATE_B); + p0[2] = swap32_S (FORTIGATE_C); + p0[3] = swap32_S (FORTIGATE_D); + p1[0] = swap32_S (FORTIGATE_E); + p1[1] = swap32_S (FORTIGATE_F); + p1[2] = 0; + p1[3] = 0; + p2[0] = 0; + p2[1] = 0; + p2[2] = 0; + p2[3] = 0; + p3[0] = 0; + p3[1] = 0; + p3[2] = 0; + p3[3] = 0; + + sha1_update_64 (&ctx, p0, p1, p2, p3, 24); + + sha1_final (&ctx); + + const u32 r0 = ctx.h[DGST_R0]; + const u32 r1 = ctx.h[DGST_R1]; + const u32 r2 = ctx.h[DGST_R2]; + const u32 r3 = ctx.h[DGST_R3]; + + COMPARE_S_SCALAR (r0, r1, r2, r3); + } +} diff --git a/OpenCL/m07000_a3.cl b/OpenCL/m07000_a3.cl new file mode 100644 index 000000000..e80136832 --- /dev/null +++ b/OpenCL/m07000_a3.cl @@ -0,0 +1,212 @@ +/** + * Author......: See docs/credits.txt + * License.....: MIT + */ + +#define NEW_SIMD_CODE + +#include "inc_vendor.cl" +#include "inc_hash_constants.h" +#include "inc_hash_functions.cl" +#include "inc_types.cl" +#include "inc_common.cl" +#include "inc_simd.cl" +#include "inc_hash_sha1.cl" + +__kernel void m07000_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32x *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +{ + /** + * modifier + */ + + const u32 lid = get_local_id (0); + const u32 gid = get_global_id (0); + + if (gid >= gid_max) return; + + /** + * base + */ + + const u32 pw_len = pws[gid].pw_len; + + const u32 pw_lenv = ceil ((float) pw_len / 4); + + u32x w[64] = { 0 }; + + for (int idx = 0; idx < pw_lenv; idx++) + { + w[idx] = pws[gid].i[idx]; + + barrier (CLK_GLOBAL_MEM_FENCE); + } + + sha1_ctx_t ctx0; + + sha1_init (&ctx0); + + sha1_update_global_swap (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len); + + /** + * loop + */ + + u32x w0l = w[0]; + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x w0r = words_buf_r[il_pos / VECT_SIZE]; + + const u32x w0 = w0l | w0r; + + w[0] = w0; + + sha1_ctx_vector_t ctx; + + sha1_init_vector_from_scalar (&ctx, &ctx0); + + sha1_update_vector_swap (&ctx, w, pw_len); + + /** + * pepper + */ + + u32x p0[4]; + u32x p1[4]; + u32x p2[4]; + u32x p3[4]; + + p0[0] = swap32 (FORTIGATE_A); + p0[1] = swap32 (FORTIGATE_B); + p0[2] = swap32 (FORTIGATE_C); + p0[3] = swap32 (FORTIGATE_D); + p1[0] = swap32 (FORTIGATE_E); + p1[1] = swap32 (FORTIGATE_F); + p1[2] = 0; + p1[3] = 0; + p2[0] = 0; + p2[1] = 0; + p2[2] = 0; + p2[3] = 0; + p3[0] = 0; + p3[1] = 0; + p3[2] = 0; + p3[3] = 0; + + sha1_update_vector_64 (&ctx, p0, p1, p2, p3, 24); + + sha1_final_vector (&ctx); + + const u32x r0 = ctx.h[DGST_R0]; + const u32x r1 = ctx.h[DGST_R1]; + const u32x r2 = ctx.h[DGST_R2]; + const u32x r3 = ctx.h[DGST_R3]; + + COMPARE_M_SIMD (r0, r1, r2, r3); + } +} + +__kernel void m07000_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32x *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max) +{ + /** + * modifier + */ + + const u32 lid = get_local_id (0); + const u32 gid = get_global_id (0); + + if (gid >= gid_max) return; + + /** + * digest + */ + + const u32 search[4] = + { + digests_buf[digests_offset].digest_buf[DGST_R0], + digests_buf[digests_offset].digest_buf[DGST_R1], + digests_buf[digests_offset].digest_buf[DGST_R2], + digests_buf[digests_offset].digest_buf[DGST_R3] + }; + + /** + * base + */ + + const u32 pw_len = pws[gid].pw_len; + + const u32 pw_lenv = ceil ((float) pw_len / 4); + + u32x w[64] = { 0 }; + + for (int idx = 0; idx < pw_lenv; idx++) + { + w[idx] = pws[gid].i[idx]; + + barrier (CLK_GLOBAL_MEM_FENCE); + } + + sha1_ctx_t ctx0; + + sha1_init (&ctx0); + + sha1_update_global_swap (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len); + + /** + * loop + */ + + u32x w0l = w[0]; + + for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE) + { + const u32x w0r = words_buf_r[il_pos / VECT_SIZE]; + + const u32x w0 = w0l | w0r; + + w[0] = w0; + + sha1_ctx_vector_t ctx; + + sha1_init_vector_from_scalar (&ctx, &ctx0); + + sha1_update_vector_swap (&ctx, w, pw_len); + + /** + * pepper + */ + + u32x p0[4]; + u32x p1[4]; + u32x p2[4]; + u32x p3[4]; + + p0[0] = swap32 (FORTIGATE_A); + p0[1] = swap32 (FORTIGATE_B); + p0[2] = swap32 (FORTIGATE_C); + p0[3] = swap32 (FORTIGATE_D); + p1[0] = swap32 (FORTIGATE_E); + p1[1] = swap32 (FORTIGATE_F); + p1[2] = 0; + p1[3] = 0; + p2[0] = 0; + p2[1] = 0; + p2[2] = 0; + p2[3] = 0; + p3[0] = 0; + p3[1] = 0; + p3[2] = 0; + p3[3] = 0; + + sha1_update_vector_64 (&ctx, p0, p1, p2, p3, 24); + + sha1_final_vector (&ctx); + + const u32x r0 = ctx.h[DGST_R0]; + const u32x r1 = ctx.h[DGST_R1]; + const u32x r2 = ctx.h[DGST_R2]; + const u32x r3 = ctx.h[DGST_R3]; + + COMPARE_S_SIMD (r0, r1, r2, r3); + } +} diff --git a/src/interface.c b/src/interface.c index 435353242..d5aca61ca 100644 --- a/src/interface.c +++ b/src/interface.c @@ -24680,7 +24680,7 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx) break; case 6900: hashconfig->pw_max = MIN (hashconfig->pw_max, 32); // todo break; - case 7000: hashconfig->pw_max = MIN (hashconfig->pw_max, 19); // todo + case 7000: hashconfig->pw_max = MIN (hashconfig->pw_max, 19); // pure kernel available break; case 7400: hashconfig->pw_max = MIN (hashconfig->pw_max, 15); // pure kernel available break;