arno
/
hashcat
mirror of https://github.com/hashcat/hashcat.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Vectorized LUKS and added support for long passwords

Browse Source
pull/1291/head
jsteube 7 years ago
parent b1a88da83e
commit 8f73d356f2
13 changed files with 1230 additions and 5537 deletions
Show Stats Download Patch File Download Diff File

470
OpenCL/m14611.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha1.cl"
#include "inc_cipher_aes.cl"
#include "inc_luks_af.cl"
@ -25,351 +25,6 @@
#define MAX_ENTROPY 7.0
void sha1_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 A = digest[0];
u32 B = digest[1];
u32 C = digest[2];
u32 D = digest[3];
u32 E = digest[4];
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
#undef K
#define K SHA1C00
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, w0_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w1_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w2_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w3_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w4_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, w5_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w6_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w7_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w8_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w9_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, wa_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, wb_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, wc_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, wd_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, we_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w3_t);
#undef K
#define K SHA1C01
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w7_t);
#undef K
#define K SHA1C02
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, wb_t);
#undef K
#define K SHA1C03
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (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 hmac_sha1_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = SHA1M_A;
ipad[1] = SHA1M_B;
ipad[2] = SHA1M_C;
ipad[3] = SHA1M_D;
ipad[4] = SHA1M_E;
sha1_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = SHA1M_A;
opad[1] = SHA1M_B;
opad[2] = SHA1M_C;
opad[3] = SHA1M_D;
opad[4] = SHA1M_E;
sha1_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha1_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
sha1_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0x80000000;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + 20) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
sha1_transform_S (w0, w1, w2, w3, digest);
}
void sha1_transform_V (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 hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
{
digest[0] = ipad[0];
@ -378,7 +33,7 @@ void hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[
digest[3] = ipad[3];
digest[4] = ipad[4];
sha1_transform_V (w0, w1, w2, w3, digest);
sha1_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -403,10 +58,10 @@ void hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[
digest[3] = opad[3];
digest[4] = opad[4];
sha1_transform_V (w0, w1, w2, w3, digest);
sha1_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14611_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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 m14611_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
/**
* base
@ -417,57 +72,27 @@ __kernel void m14611_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[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]);
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
@ -485,61 +110,66 @@ __kernel void m14611_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
u32 ipad[5];
u32 opad[5];
sha1_hmac_ctx_t sha1_hmac_ctx;
sha1_hmac_init (&sha1_hmac_ctx, w0, w1, w2, w3);
tmps[gid].ipad32[0] = sha1_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = sha1_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = sha1_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = sha1_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = sha1_hmac_ctx.ipad.h[4];
hmac_sha1_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].opad32[0] = sha1_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = sha1_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = sha1_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = sha1_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = sha1_hmac_ctx.opad.h[4];
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
sha1_hmac_update_global_swap (&sha1_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 5, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j;
w2[1] = 0x80000000;
sha1_hmac_ctx_t sha1_hmac_ctx2 = sha1_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + salt_len + 4) * 8;
w3[3] = 0;
u32 dgst[5];
sha1_hmac_update_64 (&sha1_hmac_ctx2, w0, w1, w2, w3, 4);
hmac_sha1_run_S (w0, w1, w2, w3, ipad, opad, dgst);
sha1_hmac_final (&sha1_hmac_ctx2);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 0] = sha1_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = sha1_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = sha1_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = sha1_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = sha1_hmac_ctx2.opad.h[4];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
}
}
__kernel void m14611_loop (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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 m14611_loop (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
const u32 gid = get_global_id (0);
@ -626,7 +256,7 @@ __kernel void m14611_loop (__global pw_t *pws, __global const kernel_rule_t *rul
}
}
__kernel void m14611_comp (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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 m14611_comp (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
{
const u32 gid = get_global_id (0);
const u32 lid = get_local_id (0);

464
OpenCL/m14612.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha1.cl"
#include "inc_cipher_serpent.cl"
#include "inc_luks_af.cl"
@ -25,351 +25,6 @@
#define MAX_ENTROPY 7.0
void sha1_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 A = digest[0];
u32 B = digest[1];
u32 C = digest[2];
u32 D = digest[3];
u32 E = digest[4];
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
#undef K
#define K SHA1C00
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, w0_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w1_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w2_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w3_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w4_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, w5_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w6_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w7_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w8_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w9_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, wa_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, wb_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, wc_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, wd_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, we_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w3_t);
#undef K
#define K SHA1C01
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w7_t);
#undef K
#define K SHA1C02
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, wb_t);
#undef K
#define K SHA1C03
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (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 hmac_sha1_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = SHA1M_A;
ipad[1] = SHA1M_B;
ipad[2] = SHA1M_C;
ipad[3] = SHA1M_D;
ipad[4] = SHA1M_E;
sha1_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = SHA1M_A;
opad[1] = SHA1M_B;
opad[2] = SHA1M_C;
opad[3] = SHA1M_D;
opad[4] = SHA1M_E;
sha1_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha1_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
sha1_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0x80000000;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + 20) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
sha1_transform_S (w0, w1, w2, w3, digest);
}
void sha1_transform_V (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 hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
{
digest[0] = ipad[0];
@ -378,7 +33,7 @@ void hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[
digest[3] = ipad[3];
digest[4] = ipad[4];
sha1_transform_V (w0, w1, w2, w3, digest);
sha1_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -403,7 +58,7 @@ void hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[
digest[3] = opad[3];
digest[4] = opad[4];
sha1_transform_V (w0, w1, w2, w3, digest);
sha1_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14612_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -417,57 +72,27 @@ __kernel void m14612_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[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]);
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
@ -485,57 +110,62 @@ __kernel void m14612_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
u32 ipad[5];
u32 opad[5];
sha1_hmac_ctx_t sha1_hmac_ctx;
sha1_hmac_init (&sha1_hmac_ctx, w0, w1, w2, w3);
tmps[gid].ipad32[0] = sha1_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = sha1_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = sha1_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = sha1_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = sha1_hmac_ctx.ipad.h[4];
hmac_sha1_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].opad32[0] = sha1_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = sha1_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = sha1_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = sha1_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = sha1_hmac_ctx.opad.h[4];
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
sha1_hmac_update_global_swap (&sha1_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 5, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j;
w2[1] = 0x80000000;
sha1_hmac_ctx_t sha1_hmac_ctx2 = sha1_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + salt_len + 4) * 8;
w3[3] = 0;
u32 dgst[5];
sha1_hmac_update_64 (&sha1_hmac_ctx2, w0, w1, w2, w3, 4);
hmac_sha1_run_S (w0, w1, w2, w3, ipad, opad, dgst);
sha1_hmac_final (&sha1_hmac_ctx2);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 0] = sha1_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = sha1_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = sha1_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = sha1_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = sha1_hmac_ctx2.opad.h[4];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
}
}

464
OpenCL/m14613.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha1.cl"
#include "inc_cipher_twofish.cl"
#include "inc_luks_af.cl"
@ -25,351 +25,6 @@
#define MAX_ENTROPY 7.0
void sha1_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 A = digest[0];
u32 B = digest[1];
u32 C = digest[2];
u32 D = digest[3];
u32 E = digest[4];
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
#undef K
#define K SHA1C00
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, w0_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w1_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w2_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w3_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w4_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, w5_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w6_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w7_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w8_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w9_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, wa_t);
SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, wb_t);
SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, wc_t);
SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, wd_t);
SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, we_t);
SHA1_STEP_S (SHA1_F0o, A, B, C, D, E, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F0o, E, A, B, C, D, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F0o, D, E, A, B, C, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F0o, C, D, E, A, B, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F0o, B, C, D, E, A, w3_t);
#undef K
#define K SHA1C01
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w7_t);
#undef K
#define K SHA1C02
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F2o, A, B, C, D, E, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F2o, E, A, B, C, D, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F2o, D, E, A, B, C, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F2o, C, D, E, A, B, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F2o, B, C, D, E, A, wb_t);
#undef K
#define K SHA1C03
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, wf_t);
w0_t = rotl32_S ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w0_t);
w1_t = rotl32_S ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w1_t);
w2_t = rotl32_S ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w2_t);
w3_t = rotl32_S ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w3_t);
w4_t = rotl32_S ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w4_t);
w5_t = rotl32_S ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, w5_t);
w6_t = rotl32_S ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, w6_t);
w7_t = rotl32_S ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, w7_t);
w8_t = rotl32_S ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, w8_t);
w9_t = rotl32_S ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, w9_t);
wa_t = rotl32_S ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP_S (SHA1_F1, B, C, D, E, A, wa_t);
wb_t = rotl32_S ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP_S (SHA1_F1, A, B, C, D, E, wb_t);
wc_t = rotl32_S ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP_S (SHA1_F1, E, A, B, C, D, wc_t);
wd_t = rotl32_S ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP_S (SHA1_F1, D, E, A, B, C, wd_t);
we_t = rotl32_S ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP_S (SHA1_F1, C, D, E, A, B, we_t);
wf_t = rotl32_S ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP_S (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 hmac_sha1_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = SHA1M_A;
ipad[1] = SHA1M_B;
ipad[2] = SHA1M_C;
ipad[3] = SHA1M_D;
ipad[4] = SHA1M_E;
sha1_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = SHA1M_A;
opad[1] = SHA1M_B;
opad[2] = SHA1M_C;
opad[3] = SHA1M_D;
opad[4] = SHA1M_E;
sha1_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha1_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
sha1_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0x80000000;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + 20) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
sha1_transform_S (w0, w1, w2, w3, digest);
}
void sha1_transform_V (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 hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
{
digest[0] = ipad[0];
@ -378,7 +33,7 @@ void hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[
digest[3] = ipad[3];
digest[4] = ipad[4];
sha1_transform_V (w0, w1, w2, w3, digest);
sha1_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -403,7 +58,7 @@ void hmac_sha1_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[
digest[3] = opad[3];
digest[4] = opad[4];
sha1_transform_V (w0, w1, w2, w3, digest);
sha1_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14613_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -417,57 +72,27 @@ __kernel void m14613_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[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]);
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
@ -485,57 +110,62 @@ __kernel void m14613_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
u32 ipad[5];
u32 opad[5];
sha1_hmac_ctx_t sha1_hmac_ctx;
sha1_hmac_init (&sha1_hmac_ctx, w0, w1, w2, w3);
tmps[gid].ipad32[0] = sha1_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = sha1_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = sha1_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = sha1_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = sha1_hmac_ctx.ipad.h[4];
hmac_sha1_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].opad32[0] = sha1_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = sha1_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = sha1_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = sha1_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = sha1_hmac_ctx.opad.h[4];
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
sha1_hmac_update_global_swap (&sha1_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 5, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j;
w2[1] = 0x80000000;
sha1_hmac_ctx_t sha1_hmac_ctx2 = sha1_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + salt_len + 4) * 8;
w3[3] = 0;
u32 dgst[5];
sha1_hmac_update_64 (&sha1_hmac_ctx2, w0, w1, w2, w3, 4);
hmac_sha1_run_S (w0, w1, w2, w3, ipad, opad, dgst);
sha1_hmac_final (&sha1_hmac_ctx2);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 0] = sha1_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = sha1_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = sha1_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = sha1_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = sha1_hmac_ctx2.opad.h[4];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
}
}

454
OpenCL/m14621.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha256.cl"
#include "inc_cipher_aes.cl"
#include "inc_luks_af.cl"
@ -25,303 +25,6 @@
#define MAX_ENTROPY 7.0
__constant u32a k_sha256[64] =
{
SHA256C00, SHA256C01, SHA256C02, SHA256C03,
SHA256C04, SHA256C05, SHA256C06, SHA256C07,
SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
SHA256C10, SHA256C11, SHA256C12, SHA256C13,
SHA256C14, SHA256C15, SHA256C16, SHA256C17,
SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
SHA256C20, SHA256C21, SHA256C22, SHA256C23,
SHA256C24, SHA256C25, SHA256C26, SHA256C27,
SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
SHA256C30, SHA256C31, SHA256C32, SHA256C33,
SHA256C34, SHA256C35, SHA256C36, SHA256C37,
SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
};
void sha256_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[8])
{
u32 a = digest[0];
u32 b = digest[1];
u32 c = digest[2];
u32 d = digest[3];
u32 e = digest[4];
u32 f = digest[5];
u32 g = digest[6];
u32 h = digest[7];
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
#define ROUND_EXPAND_S() \
{ \
w0_t = SHA256_EXPAND_S (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA256_EXPAND_S (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA256_EXPAND_S (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA256_EXPAND_S (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA256_EXPAND_S (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA256_EXPAND_S (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA256_EXPAND_S (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA256_EXPAND_S (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA256_EXPAND_S (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA256_EXPAND_S (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA256_EXPAND_S (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA256_EXPAND_S (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA256_EXPAND_S (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA256_EXPAND_S (wb_t, w6_t, we_t, wd_t); \
we_t = SHA256_EXPAND_S (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA256_EXPAND_S (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP_S(i) \
{ \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
}
ROUND_STEP_S (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 64; i += 16)
{
ROUND_EXPAND_S (); ROUND_STEP_S (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha256_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[8], u32 opad[8])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = SHA256M_A;
ipad[1] = SHA256M_B;
ipad[2] = SHA256M_C;
ipad[3] = SHA256M_D;
ipad[4] = SHA256M_E;
ipad[5] = SHA256M_F;
ipad[6] = SHA256M_G;
ipad[7] = SHA256M_H;
sha256_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = SHA256M_A;
opad[1] = SHA256M_B;
opad[2] = SHA256M_C;
opad[3] = SHA256M_D;
opad[4] = SHA256M_E;
opad[5] = SHA256M_F;
opad[6] = SHA256M_G;
opad[7] = SHA256M_H;
sha256_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha256_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[8], u32 opad[8], u32 digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
digest[5] = ipad[5];
digest[6] = ipad[6];
digest[7] = ipad[7];
sha256_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x80000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + 32) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
digest[5] = opad[5];
digest[6] = opad[6];
digest[7] = opad[7];
sha256_transform_S (w0, w1, w2, w3, digest);
}
void sha256_transform_V (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[8])
{
u32x a = digest[0];
u32x b = digest[1];
u32x c = digest[2];
u32x d = digest[3];
u32x e = digest[4];
u32x f = digest[5];
u32x g = digest[6];
u32x h = digest[7];
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];
#define ROUND_EXPAND() \
{ \
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP(i) \
{ \
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
}
ROUND_STEP (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 64; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8], u32x digest[8])
{
digest[0] = ipad[0];
@ -333,7 +36,7 @@ void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipa
digest[6] = ipad[6];
digest[7] = ipad[7];
sha256_transform_V (w0, w1, w2, w3, digest);
sha256_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -361,7 +64,7 @@ void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipa
digest[6] = opad[6];
digest[7] = opad[7];
sha256_transform_V (w0, w1, w2, w3, digest);
sha256_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14621_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -375,57 +78,27 @@ __kernel void m14621_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[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]);
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
@ -443,69 +116,74 @@ __kernel void m14621_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
u32 ipad[8];
u32 opad[8];
hmac_sha256_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
tmps[gid].ipad32[5] = ipad[5];
tmps[gid].ipad32[6] = ipad[6];
tmps[gid].ipad32[7] = ipad[7];
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
tmps[gid].opad32[5] = opad[5];
tmps[gid].opad32[6] = opad[6];
tmps[gid].opad32[7] = opad[7];
sha256_hmac_ctx_t sha256_hmac_ctx;
sha256_hmac_init (&sha256_hmac_ctx, w0, w1, w2, w3);
tmps[gid].ipad32[0] = sha256_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = sha256_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = sha256_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = sha256_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = sha256_hmac_ctx.ipad.h[4];
tmps[gid].ipad32[5] = sha256_hmac_ctx.ipad.h[5];
tmps[gid].ipad32[6] = sha256_hmac_ctx.ipad.h[6];
tmps[gid].ipad32[7] = sha256_hmac_ctx.ipad.h[7];
tmps[gid].opad32[0] = sha256_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = sha256_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = sha256_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = sha256_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = sha256_hmac_ctx.opad.h[4];
tmps[gid].opad32[5] = sha256_hmac_ctx.opad.h[5];
tmps[gid].opad32[6] = sha256_hmac_ctx.opad.h[6];
tmps[gid].opad32[7] = sha256_hmac_ctx.opad.h[7];
sha256_hmac_update_global_swap (&sha256_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 8, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j;
w2[1] = 0x80000000;
sha256_hmac_ctx_t sha256_hmac_ctx2 = sha256_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + salt_len + 4) * 8;
u32 dgst[8];
hmac_sha256_run_S (w0, w1, w2, w3, ipad, opad, dgst);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 5] = dgst[5];
tmps[gid].dgst32[i + 6] = dgst[6];
tmps[gid].dgst32[i + 7] = dgst[7];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 5] = dgst[5];
tmps[gid].out32[i + 6] = dgst[6];
tmps[gid].out32[i + 7] = dgst[7];
w3[3] = 0;
sha256_hmac_update_64 (&sha256_hmac_ctx2, w0, w1, w2, w3, 4);
sha256_hmac_final (&sha256_hmac_ctx2);
tmps[gid].dgst32[i + 0] = sha256_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = sha256_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = sha256_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = sha256_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = sha256_hmac_ctx2.opad.h[4];
tmps[gid].dgst32[i + 5] = sha256_hmac_ctx2.opad.h[5];
tmps[gid].dgst32[i + 6] = sha256_hmac_ctx2.opad.h[6];
tmps[gid].dgst32[i + 7] = sha256_hmac_ctx2.opad.h[7];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
tmps[gid].out32[i + 5] = tmps[gid].dgst32[i + 5];
tmps[gid].out32[i + 6] = tmps[gid].dgst32[i + 6];
tmps[gid].out32[i + 7] = tmps[gid].dgst32[i + 7];
}
}

453
OpenCL/m14622.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha256.cl"
#include "inc_cipher_serpent.cl"
#include "inc_luks_af.cl"
@ -25,302 +25,6 @@
#define MAX_ENTROPY 7.0
__constant u32a k_sha256[64] =
{
SHA256C00, SHA256C01, SHA256C02, SHA256C03,
SHA256C04, SHA256C05, SHA256C06, SHA256C07,
SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
SHA256C10, SHA256C11, SHA256C12, SHA256C13,
SHA256C14, SHA256C15, SHA256C16, SHA256C17,
SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
SHA256C20, SHA256C21, SHA256C22, SHA256C23,
SHA256C24, SHA256C25, SHA256C26, SHA256C27,
SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
SHA256C30, SHA256C31, SHA256C32, SHA256C33,
SHA256C34, SHA256C35, SHA256C36, SHA256C37,
SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
};
void sha256_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[8])
{
u32 a = digest[0];
u32 b = digest[1];
u32 c = digest[2];
u32 d = digest[3];
u32 e = digest[4];
u32 f = digest[5];
u32 g = digest[6];
u32 h = digest[7];
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
#define ROUND_EXPAND_S() \
{ \
w0_t = SHA256_EXPAND_S (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA256_EXPAND_S (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA256_EXPAND_S (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA256_EXPAND_S (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA256_EXPAND_S (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA256_EXPAND_S (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA256_EXPAND_S (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA256_EXPAND_S (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA256_EXPAND_S (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA256_EXPAND_S (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA256_EXPAND_S (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA256_EXPAND_S (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA256_EXPAND_S (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA256_EXPAND_S (wb_t, w6_t, we_t, wd_t); \
we_t = SHA256_EXPAND_S (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA256_EXPAND_S (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP_S(i) \
{ \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
}
ROUND_STEP_S (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 64; i += 16)
{
ROUND_EXPAND_S (); ROUND_STEP_S (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha256_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[8], u32 opad[8])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = SHA256M_A;
ipad[1] = SHA256M_B;
ipad[2] = SHA256M_C;
ipad[3] = SHA256M_D;
ipad[4] = SHA256M_E;
ipad[5] = SHA256M_F;
ipad[6] = SHA256M_G;
ipad[7] = SHA256M_H;
sha256_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = SHA256M_A;
opad[1] = SHA256M_B;
opad[2] = SHA256M_C;
opad[3] = SHA256M_D;
opad[4] = SHA256M_E;
opad[5] = SHA256M_F;
opad[6] = SHA256M_G;
opad[7] = SHA256M_H;
sha256_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha256_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[8], u32 opad[8], u32 digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
digest[5] = ipad[5];
digest[6] = ipad[6];
digest[7] = ipad[7];
sha256_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x80000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + 32) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
digest[5] = opad[5];
digest[6] = opad[6];
digest[7] = opad[7];
sha256_transform_S (w0, w1, w2, w3, digest);
}
void sha256_transform_V (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[8])
{
u32x a = digest[0];
u32x b = digest[1];
u32x c = digest[2];
u32x d = digest[3];
u32x e = digest[4];
u32x f = digest[5];
u32x g = digest[6];
u32x h = digest[7];
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];
#define ROUND_EXPAND() \
{ \
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP(i) \
{ \
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
}
ROUND_STEP (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 64; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8], u32x digest[8])
{
@ -333,7 +37,7 @@ void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipa
digest[6] = ipad[6];
digest[7] = ipad[7];
sha256_transform_V (w0, w1, w2, w3, digest);
sha256_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -361,7 +65,7 @@ void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipa
digest[6] = opad[6];
digest[7] = opad[7];
sha256_transform_V (w0, w1, w2, w3, digest);
sha256_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14622_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -375,57 +79,27 @@ __kernel void m14622_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[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]);
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
@ -443,69 +117,74 @@ __kernel void m14622_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
u32 ipad[8];
u32 opad[8];
hmac_sha256_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
tmps[gid].ipad32[5] = ipad[5];
tmps[gid].ipad32[6] = ipad[6];
tmps[gid].ipad32[7] = ipad[7];
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
tmps[gid].opad32[5] = opad[5];
tmps[gid].opad32[6] = opad[6];
tmps[gid].opad32[7] = opad[7];
sha256_hmac_ctx_t sha256_hmac_ctx;
sha256_hmac_init (&sha256_hmac_ctx, w0, w1, w2, w3);
tmps[gid].ipad32[0] = sha256_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = sha256_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = sha256_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = sha256_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = sha256_hmac_ctx.ipad.h[4];
tmps[gid].ipad32[5] = sha256_hmac_ctx.ipad.h[5];
tmps[gid].ipad32[6] = sha256_hmac_ctx.ipad.h[6];
tmps[gid].ipad32[7] = sha256_hmac_ctx.ipad.h[7];
tmps[gid].opad32[0] = sha256_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = sha256_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = sha256_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = sha256_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = sha256_hmac_ctx.opad.h[4];
tmps[gid].opad32[5] = sha256_hmac_ctx.opad.h[5];
tmps[gid].opad32[6] = sha256_hmac_ctx.opad.h[6];
tmps[gid].opad32[7] = sha256_hmac_ctx.opad.h[7];
sha256_hmac_update_global_swap (&sha256_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 8, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j;
w2[1] = 0x80000000;
sha256_hmac_ctx_t sha256_hmac_ctx2 = sha256_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + salt_len + 4) * 8;
u32 dgst[8];
hmac_sha256_run_S (w0, w1, w2, w3, ipad, opad, dgst);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 5] = dgst[5];
tmps[gid].dgst32[i + 6] = dgst[6];
tmps[gid].dgst32[i + 7] = dgst[7];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 5] = dgst[5];
tmps[gid].out32[i + 6] = dgst[6];
tmps[gid].out32[i + 7] = dgst[7];
w3[3] = 0;
sha256_hmac_update_64 (&sha256_hmac_ctx2, w0, w1, w2, w3, 4);
sha256_hmac_final (&sha256_hmac_ctx2);
tmps[gid].dgst32[i + 0] = sha256_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = sha256_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = sha256_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = sha256_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = sha256_hmac_ctx2.opad.h[4];
tmps[gid].dgst32[i + 5] = sha256_hmac_ctx2.opad.h[5];
tmps[gid].dgst32[i + 6] = sha256_hmac_ctx2.opad.h[6];
tmps[gid].dgst32[i + 7] = sha256_hmac_ctx2.opad.h[7];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
tmps[gid].out32[i + 5] = tmps[gid].dgst32[i + 5];
tmps[gid].out32[i + 6] = tmps[gid].dgst32[i + 6];
tmps[gid].out32[i + 7] = tmps[gid].dgst32[i + 7];
}
}

454
OpenCL/m14623.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha256.cl"
#include "inc_cipher_twofish.cl"
#include "inc_luks_af.cl"
@ -25,303 +25,6 @@
#define MAX_ENTROPY 7.0
__constant u32a k_sha256[64] =
{
SHA256C00, SHA256C01, SHA256C02, SHA256C03,
SHA256C04, SHA256C05, SHA256C06, SHA256C07,
SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
SHA256C10, SHA256C11, SHA256C12, SHA256C13,
SHA256C14, SHA256C15, SHA256C16, SHA256C17,
SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
SHA256C20, SHA256C21, SHA256C22, SHA256C23,
SHA256C24, SHA256C25, SHA256C26, SHA256C27,
SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
SHA256C30, SHA256C31, SHA256C32, SHA256C33,
SHA256C34, SHA256C35, SHA256C36, SHA256C37,
SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
};
void sha256_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[8])
{
u32 a = digest[0];
u32 b = digest[1];
u32 c = digest[2];
u32 d = digest[3];
u32 e = digest[4];
u32 f = digest[5];
u32 g = digest[6];
u32 h = digest[7];
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
#define ROUND_EXPAND_S() \
{ \
w0_t = SHA256_EXPAND_S (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA256_EXPAND_S (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA256_EXPAND_S (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA256_EXPAND_S (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA256_EXPAND_S (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA256_EXPAND_S (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA256_EXPAND_S (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA256_EXPAND_S (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA256_EXPAND_S (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA256_EXPAND_S (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA256_EXPAND_S (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA256_EXPAND_S (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA256_EXPAND_S (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA256_EXPAND_S (wb_t, w6_t, we_t, wd_t); \
we_t = SHA256_EXPAND_S (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA256_EXPAND_S (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP_S(i) \
{ \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
SHA256_STEP_S (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
}
ROUND_STEP_S (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 64; i += 16)
{
ROUND_EXPAND_S (); ROUND_STEP_S (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha256_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[8], u32 opad[8])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = SHA256M_A;
ipad[1] = SHA256M_B;
ipad[2] = SHA256M_C;
ipad[3] = SHA256M_D;
ipad[4] = SHA256M_E;
ipad[5] = SHA256M_F;
ipad[6] = SHA256M_G;
ipad[7] = SHA256M_H;
sha256_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = SHA256M_A;
opad[1] = SHA256M_B;
opad[2] = SHA256M_C;
opad[3] = SHA256M_D;
opad[4] = SHA256M_E;
opad[5] = SHA256M_F;
opad[6] = SHA256M_G;
opad[7] = SHA256M_H;
sha256_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha256_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[8], u32 opad[8], u32 digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
digest[5] = ipad[5];
digest[6] = ipad[6];
digest[7] = ipad[7];
sha256_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x80000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + 32) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
digest[5] = opad[5];
digest[6] = opad[6];
digest[7] = opad[7];
sha256_transform_S (w0, w1, w2, w3, digest);
}
void sha256_transform_V (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[8])
{
u32x a = digest[0];
u32x b = digest[1];
u32x c = digest[2];
u32x d = digest[3];
u32x e = digest[4];
u32x f = digest[5];
u32x g = digest[6];
u32x h = digest[7];
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];
#define ROUND_EXPAND() \
{ \
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP(i) \
{ \
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
}
ROUND_STEP (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 64; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8], u32x digest[8])
{
digest[0] = ipad[0];
@ -333,7 +36,7 @@ void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipa
digest[6] = ipad[6];
digest[7] = ipad[7];
sha256_transform_V (w0, w1, w2, w3, digest);
sha256_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -361,7 +64,7 @@ void hmac_sha256_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipa
digest[6] = opad[6];
digest[7] = opad[7];
sha256_transform_V (w0, w1, w2, w3, digest);
sha256_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14623_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -375,57 +78,27 @@ __kernel void m14623_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[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]);
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
@ -443,69 +116,74 @@ __kernel void m14623_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
u32 ipad[8];
u32 opad[8];
hmac_sha256_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
tmps[gid].ipad32[5] = ipad[5];
tmps[gid].ipad32[6] = ipad[6];
tmps[gid].ipad32[7] = ipad[7];
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
tmps[gid].opad32[5] = opad[5];
tmps[gid].opad32[6] = opad[6];
tmps[gid].opad32[7] = opad[7];
sha256_hmac_ctx_t sha256_hmac_ctx;
sha256_hmac_init (&sha256_hmac_ctx, w0, w1, w2, w3);
tmps[gid].ipad32[0] = sha256_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = sha256_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = sha256_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = sha256_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = sha256_hmac_ctx.ipad.h[4];
tmps[gid].ipad32[5] = sha256_hmac_ctx.ipad.h[5];
tmps[gid].ipad32[6] = sha256_hmac_ctx.ipad.h[6];
tmps[gid].ipad32[7] = sha256_hmac_ctx.ipad.h[7];
tmps[gid].opad32[0] = sha256_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = sha256_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = sha256_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = sha256_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = sha256_hmac_ctx.opad.h[4];
tmps[gid].opad32[5] = sha256_hmac_ctx.opad.h[5];
tmps[gid].opad32[6] = sha256_hmac_ctx.opad.h[6];
tmps[gid].opad32[7] = sha256_hmac_ctx.opad.h[7];
sha256_hmac_update_global_swap (&sha256_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 8, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j;
w2[1] = 0x80000000;
sha256_hmac_ctx_t sha256_hmac_ctx2 = sha256_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (64 + salt_len + 4) * 8;
u32 dgst[8];
hmac_sha256_run_S (w0, w1, w2, w3, ipad, opad, dgst);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 5] = dgst[5];
tmps[gid].dgst32[i + 6] = dgst[6];
tmps[gid].dgst32[i + 7] = dgst[7];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 5] = dgst[5];
tmps[gid].out32[i + 6] = dgst[6];
tmps[gid].out32[i + 7] = dgst[7];
w3[3] = 0;
sha256_hmac_update_64 (&sha256_hmac_ctx2, w0, w1, w2, w3, 4);
sha256_hmac_final (&sha256_hmac_ctx2);
tmps[gid].dgst32[i + 0] = sha256_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = sha256_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = sha256_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = sha256_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = sha256_hmac_ctx2.opad.h[4];
tmps[gid].dgst32[i + 5] = sha256_hmac_ctx2.opad.h[5];
tmps[gid].dgst32[i + 6] = sha256_hmac_ctx2.opad.h[6];
tmps[gid].dgst32[i + 7] = sha256_hmac_ctx2.opad.h[7];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
tmps[gid].out32[i + 5] = tmps[gid].dgst32[i + 5];
tmps[gid].out32[i + 6] = tmps[gid].dgst32[i + 6];
tmps[gid].out32[i + 7] = tmps[gid].dgst32[i + 7];
}
}

696
OpenCL/m14631.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha512.cl"
#include "inc_cipher_aes.cl"
#include "inc_luks_af.cl"
@ -25,308 +25,7 @@
#define MAX_ENTROPY 7.0
__constant u64a k_sha512[80] =
{
SHA512C00, SHA512C01, SHA512C02, SHA512C03,
SHA512C04, SHA512C05, SHA512C06, SHA512C07,
SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
SHA512C10, SHA512C11, SHA512C12, SHA512C13,
SHA512C14, SHA512C15, SHA512C16, SHA512C17,
SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
SHA512C20, SHA512C21, SHA512C22, SHA512C23,
SHA512C24, SHA512C25, SHA512C26, SHA512C27,
SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
SHA512C30, SHA512C31, SHA512C32, SHA512C33,
SHA512C34, SHA512C35, SHA512C36, SHA512C37,
SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
SHA512C40, SHA512C41, SHA512C42, SHA512C43,
SHA512C44, SHA512C45, SHA512C46, SHA512C47,
SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
};
void sha512_transform_S (const u64 w0[4], const u64 w1[4], const u64 w2[4], const u64 w3[4], u64 digest[8])
{
u64 a = digest[0];
u64 b = digest[1];
u64 c = digest[2];
u64 d = digest[3];
u64 e = digest[4];
u64 f = digest[5];
u64 g = digest[6];
u64 h = digest[7];
u64 w0_t = w0[0];
u64 w1_t = w0[1];
u64 w2_t = w0[2];
u64 w3_t = w0[3];
u64 w4_t = w1[0];
u64 w5_t = w1[1];
u64 w6_t = w1[2];
u64 w7_t = w1[3];
u64 w8_t = w2[0];
u64 w9_t = w2[1];
u64 wa_t = w2[2];
u64 wb_t = w2[3];
u64 wc_t = w3[0];
u64 wd_t = w3[1];
u64 we_t = w3[2];
u64 wf_t = w3[3];
#define ROUND_EXPAND_S() \
{ \
w0_t = SHA512_EXPAND_S (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA512_EXPAND_S (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA512_EXPAND_S (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA512_EXPAND_S (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA512_EXPAND_S (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA512_EXPAND_S (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA512_EXPAND_S (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA512_EXPAND_S (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA512_EXPAND_S (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA512_EXPAND_S (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA512_EXPAND_S (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA512_EXPAND_S (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA512_EXPAND_S (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA512_EXPAND_S (wb_t, w6_t, we_t, wd_t); \
we_t = SHA512_EXPAND_S (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA512_EXPAND_S (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP_S(i) \
{ \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
}
ROUND_STEP_S (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND_S (); ROUND_STEP_S (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha512_pad_S (u64 w0[4], u64 w1[4], u64 w2[4], u64 w3[4], u64 ipad[8], u64 opad[8])
{
w0[0] = w0[0] ^ 0x3636363636363636;
w0[1] = w0[1] ^ 0x3636363636363636;
w0[2] = w0[2] ^ 0x3636363636363636;
w0[3] = w0[3] ^ 0x3636363636363636;
w1[0] = w1[0] ^ 0x3636363636363636;
w1[1] = w1[1] ^ 0x3636363636363636;
w1[2] = w1[2] ^ 0x3636363636363636;
w1[3] = w1[3] ^ 0x3636363636363636;
w2[0] = w2[0] ^ 0x3636363636363636;
w2[1] = w2[1] ^ 0x3636363636363636;
w2[2] = w2[2] ^ 0x3636363636363636;
w2[3] = w2[3] ^ 0x3636363636363636;
w3[0] = w3[0] ^ 0x3636363636363636;
w3[1] = w3[1] ^ 0x3636363636363636;
w3[2] = w3[2] ^ 0x3636363636363636;
w3[3] = w3[3] ^ 0x3636363636363636;
ipad[0] = SHA512M_A;
ipad[1] = SHA512M_B;
ipad[2] = SHA512M_C;
ipad[3] = SHA512M_D;
ipad[4] = SHA512M_E;
ipad[5] = SHA512M_F;
ipad[6] = SHA512M_G;
ipad[7] = SHA512M_H;
sha512_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a6a6a6a6a;
opad[0] = SHA512M_A;
opad[1] = SHA512M_B;
opad[2] = SHA512M_C;
opad[3] = SHA512M_D;
opad[4] = SHA512M_E;
opad[5] = SHA512M_F;
opad[6] = SHA512M_G;
opad[7] = SHA512M_H;
sha512_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha512_run_S (u64 w0[4], u64 w1[4], u64 w2[4], u64 w3[4], u64 ipad[8], u64 opad[8], u64 digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
digest[5] = ipad[5];
digest[6] = ipad[6];
digest[7] = ipad[7];
sha512_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
digest[5] = opad[5];
digest[6] = opad[6];
digest[7] = opad[7];
sha512_transform_S (w0, w1, w2, w3, digest);
}
void sha512_transform_V (const u64x w0[4], const u64x w1[4], const u64x w2[4], const u64x w3[4], u64x digest[8])
{
u64x a = digest[0];
u64x b = digest[1];
u64x c = digest[2];
u64x d = digest[3];
u64x e = digest[4];
u64x f = digest[5];
u64x g = digest[6];
u64x h = digest[7];
u64x w0_t = w0[0];
u64x w1_t = w0[1];
u64x w2_t = w0[2];
u64x w3_t = w0[3];
u64x w4_t = w1[0];
u64x w5_t = w1[1];
u64x w6_t = w1[2];
u64x w7_t = w1[3];
u64x w8_t = w2[0];
u64x w9_t = w2[1];
u64x wa_t = w2[2];
u64x wb_t = w2[3];
u64x wc_t = w3[0];
u64x wd_t = w3[1];
u64x we_t = w3[2];
u64x wf_t = w3[3];
#define ROUND_EXPAND() \
{ \
w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP(i) \
{ \
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
}
ROUND_STEP (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipad[8], u64x opad[8], u64x digest[8])
void hmac_sha512_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x w4[4], u32x w5[4], u32x w6[4], u32x w7[4], u64x ipad[8], u64x opad[8], u64x digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
@ -337,24 +36,40 @@ void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipa
digest[6] = ipad[6];
digest[7] = ipad[7];
sha512_transform_V (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
sha512_transform_vector (w0, w1, w2, w3, w4, w5, w6, w7, digest);
w0[0] = h32_from_64 (digest[0]);
w0[1] = l32_from_64 (digest[0]);
w0[2] = h32_from_64 (digest[1]);
w0[3] = l32_from_64 (digest[1]);
w1[0] = h32_from_64 (digest[2]);
w1[1] = l32_from_64 (digest[2]);
w1[2] = h32_from_64 (digest[3]);
w1[3] = l32_from_64 (digest[3]);
w2[0] = h32_from_64 (digest[4]);
w2[1] = l32_from_64 (digest[4]);
w2[2] = h32_from_64 (digest[5]);
w2[3] = l32_from_64 (digest[5]);
w3[0] = h32_from_64 (digest[6]);
w3[1] = l32_from_64 (digest[6]);
w3[2] = h32_from_64 (digest[7]);
w3[3] = l32_from_64 (digest[7]);
w4[0] = 0x80000000;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = (128 + 64) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
@ -365,7 +80,7 @@ void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipa
digest[6] = opad[6];
digest[7] = opad[7];
sha512_transform_V (w0, w1, w2, w3, digest);
sha512_transform_vector (w0, w1, w2, w3, w4, w5, w6, w7, digest);
}
__kernel void m14631_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -378,77 +93,116 @@ __kernel void m14631_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u64 w0[4];
u64 w1[4];
u64 w2[4];
u64 w3[4];
w0[0] = hl32_to_64_S (swap32_S (pws[gid].i[ 0]), swap32_S (pws[gid].i[ 1]));
w0[1] = hl32_to_64_S (swap32_S (pws[gid].i[ 2]), swap32_S (pws[gid].i[ 3]));
w0[2] = hl32_to_64_S (swap32_S (pws[gid].i[ 4]), swap32_S (pws[gid].i[ 5]));
w0[3] = hl32_to_64_S (swap32_S (pws[gid].i[ 6]), swap32_S (pws[gid].i[ 7]));
w1[0] = hl32_to_64_S (swap32_S (pws[gid].i[ 8]), swap32_S (pws[gid].i[ 9]));
w1[1] = hl32_to_64_S (swap32_S (pws[gid].i[10]), swap32_S (pws[gid].i[11]));
w1[2] = hl32_to_64_S (swap32_S (pws[gid].i[12]), swap32_S (pws[gid].i[13]));
w1[3] = hl32_to_64_S (swap32_S (pws[gid].i[14]), swap32_S (pws[gid].i[15]));
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = 0;
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u64 salt_buf0[4];
salt_buf0[0] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[0]), swap32_S (salt_bufs[salt_pos].salt_buf[1]));
salt_buf0[1] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[2]), swap32_S (salt_bufs[salt_pos].salt_buf[3]));
salt_buf0[2] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[4]), swap32_S (salt_bufs[salt_pos].salt_buf[5]));
salt_buf0[3] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[6]), swap32_S (salt_bufs[salt_pos].salt_buf[7]));
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
u64 ipad[8];
u64 opad[8];
hmac_sha512_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].ipad64[0] = ipad[0];
tmps[gid].ipad64[1] = ipad[1];
tmps[gid].ipad64[2] = ipad[2];
tmps[gid].ipad64[3] = ipad[3];
tmps[gid].ipad64[4] = ipad[4];
tmps[gid].ipad64[5] = ipad[5];
tmps[gid].ipad64[6] = ipad[6];
tmps[gid].ipad64[7] = ipad[7];
tmps[gid].opad64[0] = opad[0];
tmps[gid].opad64[1] = opad[1];
tmps[gid].opad64[2] = opad[2];
tmps[gid].opad64[3] = opad[3];
tmps[gid].opad64[4] = opad[4];
tmps[gid].opad64[5] = opad[5];
tmps[gid].opad64[6] = opad[6];
tmps[gid].opad64[7] = opad[7];
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[4];
u32 w4[4];
u32 w5[4];
u32 w6[4];
u32 w7[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];
w1[0] = pws[gid].i[ 4];
w1[1] = pws[gid].i[ 5];
w1[2] = pws[gid].i[ 6];
w1[3] = pws[gid].i[ 7];
w2[0] = pws[gid].i[ 8];
w2[1] = pws[gid].i[ 9];
w2[2] = pws[gid].i[10];
w2[3] = pws[gid].i[11];
w3[0] = pws[gid].i[12];
w3[1] = pws[gid].i[13];
w3[2] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
w4[0] = pws[gid].i[16];
w4[1] = pws[gid].i[17];
w4[2] = pws[gid].i[18];
w4[3] = pws[gid].i[19];
w5[0] = pws[gid].i[20];
w5[1] = pws[gid].i[21];
w5[2] = pws[gid].i[22];
w5[3] = pws[gid].i[23];
w6[0] = pws[gid].i[24];
w6[1] = pws[gid].i[25];
w6[2] = pws[gid].i[26];
w6[3] = pws[gid].i[27];
w7[0] = pws[gid].i[28];
w7[1] = pws[gid].i[29];
w7[2] = pws[gid].i[30];
w7[3] = pws[gid].i[31];
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
w0[3] = swap32_S (w0[3]);
w1[0] = swap32_S (w1[0]);
w1[1] = swap32_S (w1[1]);
w1[2] = swap32_S (w1[2]);
w1[3] = swap32_S (w1[3]);
w2[0] = swap32_S (w2[0]);
w2[1] = swap32_S (w2[1]);
w2[2] = swap32_S (w2[2]);
w2[3] = swap32_S (w2[3]);
w3[0] = swap32_S (w3[0]);
w3[1] = swap32_S (w3[1]);
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
w4[0] = swap32_S (w4[0]);
w4[1] = swap32_S (w4[1]);
w4[2] = swap32_S (w4[2]);
w4[3] = swap32_S (w4[3]);
w5[0] = swap32_S (w5[0]);
w5[1] = swap32_S (w5[1]);
w5[2] = swap32_S (w5[2]);
w5[3] = swap32_S (w5[3]);
w6[0] = swap32_S (w6[0]);
w6[1] = swap32_S (w6[1]);
w6[2] = swap32_S (w6[2]);
w6[3] = swap32_S (w6[3]);
w7[0] = swap32_S (w7[0]);
w7[1] = swap32_S (w7[1]);
w7[2] = swap32_S (w7[2]);
w7[3] = swap32_S (w7[3]);
sha512_hmac_ctx_t sha512_hmac_ctx;
sha512_hmac_init (&sha512_hmac_ctx, w0, w1, w2, w3, w5, w5, w6, w7);
tmps[gid].ipad64[0] = sha512_hmac_ctx.ipad.h[0];
tmps[gid].ipad64[1] = sha512_hmac_ctx.ipad.h[1];
tmps[gid].ipad64[2] = sha512_hmac_ctx.ipad.h[2];
tmps[gid].ipad64[3] = sha512_hmac_ctx.ipad.h[3];
tmps[gid].ipad64[4] = sha512_hmac_ctx.ipad.h[4];
tmps[gid].ipad64[5] = sha512_hmac_ctx.ipad.h[5];
tmps[gid].ipad64[6] = sha512_hmac_ctx.ipad.h[6];
tmps[gid].ipad64[7] = sha512_hmac_ctx.ipad.h[7];
tmps[gid].opad64[0] = sha512_hmac_ctx.opad.h[0];
tmps[gid].opad64[1] = sha512_hmac_ctx.opad.h[1];
tmps[gid].opad64[2] = sha512_hmac_ctx.opad.h[2];
tmps[gid].opad64[3] = sha512_hmac_ctx.opad.h[3];
tmps[gid].opad64[4] = sha512_hmac_ctx.opad.h[4];
tmps[gid].opad64[5] = sha512_hmac_ctx.opad.h[5];
tmps[gid].opad64[6] = sha512_hmac_ctx.opad.h[6];
tmps[gid].opad64[7] = sha512_hmac_ctx.opad.h[7];
sha512_hmac_update_global_swap (&sha512_hmac_ctx, salt_bufs[digests_offset].salt_buf, salt_bufs[salt_pos].salt_len);
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 16, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = hl32_to_64_S (j, 0x80000000);
sha512_hmac_ctx_t sha512_hmac_ctx2 = sha512_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
@ -459,29 +213,45 @@ __kernel void m14631_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + salt_len + 4) * 8;
u64 dgst[8];
hmac_sha512_run_S (w0, w1, w2, w3, ipad, opad, dgst);
tmps[gid].dgst64[i + 0] = dgst[0];
tmps[gid].dgst64[i + 1] = dgst[1];
tmps[gid].dgst64[i + 2] = dgst[2];
tmps[gid].dgst64[i + 3] = dgst[3];
tmps[gid].dgst64[i + 4] = dgst[4];
tmps[gid].dgst64[i + 5] = dgst[5];
tmps[gid].dgst64[i + 6] = dgst[6];
tmps[gid].dgst64[i + 7] = dgst[7];
tmps[gid].out64[i + 0] = dgst[0];
tmps[gid].out64[i + 1] = dgst[1];
tmps[gid].out64[i + 2] = dgst[2];
tmps[gid].out64[i + 3] = dgst[3];
tmps[gid].out64[i + 4] = dgst[4];
tmps[gid].out64[i + 5] = dgst[5];
tmps[gid].out64[i + 6] = dgst[6];
tmps[gid].out64[i + 7] = dgst[7];
w3[3] = 0;
w4[0] = 0;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = 0;
sha512_hmac_update_128 (&sha512_hmac_ctx2, w0, w1, w2, w3, w4, w5, w6, w7, 4);
sha512_hmac_final (&sha512_hmac_ctx2);
tmps[gid].dgst64[i + 0] = sha512_hmac_ctx2.opad.h[0];
tmps[gid].dgst64[i + 1] = sha512_hmac_ctx2.opad.h[1];
tmps[gid].dgst64[i + 2] = sha512_hmac_ctx2.opad.h[2];
tmps[gid].dgst64[i + 3] = sha512_hmac_ctx2.opad.h[3];
tmps[gid].dgst64[i + 4] = sha512_hmac_ctx2.opad.h[4];
tmps[gid].dgst64[i + 5] = sha512_hmac_ctx2.opad.h[5];
tmps[gid].dgst64[i + 6] = sha512_hmac_ctx2.opad.h[6];
tmps[gid].dgst64[i + 7] = sha512_hmac_ctx2.opad.h[7];
tmps[gid].out64[i + 0] = tmps[gid].dgst64[i + 0];
tmps[gid].out64[i + 1] = tmps[gid].dgst64[i + 1];
tmps[gid].out64[i + 2] = tmps[gid].dgst64[i + 2];
tmps[gid].out64[i + 3] = tmps[gid].dgst64[i + 3];
tmps[gid].out64[i + 4] = tmps[gid].dgst64[i + 4];
tmps[gid].out64[i + 5] = tmps[gid].dgst64[i + 5];
tmps[gid].out64[i + 6] = tmps[gid].dgst64[i + 6];
tmps[gid].out64[i + 7] = tmps[gid].dgst64[i + 7];
}
}
@ -539,29 +309,49 @@ __kernel void m14631_loop (__global pw_t *pws, __global const kernel_rule_t *rul
for (u32 j = 0; j < loop_cnt; j++)
{
u64x w0[4];
u64x w1[4];
u64x w2[4];
u64x w3[4];
w0[0] = dgst[0];
w0[1] = dgst[1];
w0[2] = dgst[2];
w0[3] = dgst[3];
w1[0] = dgst[4];
w1[1] = dgst[5];
w1[2] = dgst[6];
w1[3] = dgst[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
hmac_sha512_run_V (w0, w1, w2, w3, ipad, opad, dgst);
u32x w0[4];
u32x w1[4];
u32x w2[4];
u32x w3[4];
u32x w4[4];
u32x w5[4];
u32x w6[4];
u32x w7[4];
w0[0] = h32_from_64 (dgst[0]);
w0[1] = l32_from_64 (dgst[0]);
w0[2] = h32_from_64 (dgst[1]);
w0[3] = l32_from_64 (dgst[1]);
w1[0] = h32_from_64 (dgst[2]);
w1[1] = l32_from_64 (dgst[2]);
w1[2] = h32_from_64 (dgst[3]);
w1[3] = l32_from_64 (dgst[3]);
w2[0] = h32_from_64 (dgst[4]);
w2[1] = l32_from_64 (dgst[4]);
w2[2] = h32_from_64 (dgst[5]);
w2[3] = l32_from_64 (dgst[5]);
w3[0] = h32_from_64 (dgst[6]);
w3[1] = l32_from_64 (dgst[6]);
w3[2] = h32_from_64 (dgst[7]);
w3[3] = l32_from_64 (dgst[7]);
w4[0] = 0x80000000;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = (128 + 64) * 8;
hmac_sha512_run_V (w0, w1, w2, w3, w4, w5, w6, w7, ipad, opad, dgst);
out[0] ^= dgst[0];
out[1] ^= dgst[1];
@ -573,23 +363,23 @@ __kernel void m14631_loop (__global pw_t *pws, __global const kernel_rule_t *rul
out[7] ^= dgst[7];
}
unpackv (tmps, dgst64, gid, i + 0, dgst[0]);
unpackv (tmps, dgst64, gid, i + 1, dgst[1]);
unpackv (tmps, dgst64, gid, i + 2, dgst[2]);
unpackv (tmps, dgst64, gid, i + 3, dgst[3]);
unpackv (tmps, dgst64, gid, i + 4, dgst[4]);
unpackv (tmps, dgst64, gid, i + 5, dgst[5]);
unpackv (tmps, dgst64, gid, i + 6, dgst[6]);
unpackv (tmps, dgst64, gid, i + 7, dgst[7]);
unpackv (tmps, out64, gid, i + 0, out[0]);
unpackv (tmps, out64, gid, i + 1, out[1]);
unpackv (tmps, out64, gid, i + 2, out[2]);
unpackv (tmps, out64, gid, i + 3, out[3]);
unpackv (tmps, out64, gid, i + 4, out[4]);
unpackv (tmps, out64, gid, i + 5, out[5]);
unpackv (tmps, out64, gid, i + 6, out[6]);
unpackv (tmps, out64, gid, i + 7, out[7]);
unpack64v (tmps, dgst64, gid, i + 0, dgst[0]);
unpack64v (tmps, dgst64, gid, i + 1, dgst[1]);
unpack64v (tmps, dgst64, gid, i + 2, dgst[2]);
unpack64v (tmps, dgst64, gid, i + 3, dgst[3]);
unpack64v (tmps, dgst64, gid, i + 4, dgst[4]);
unpack64v (tmps, dgst64, gid, i + 5, dgst[5]);
unpack64v (tmps, dgst64, gid, i + 6, dgst[6]);
unpack64v (tmps, dgst64, gid, i + 7, dgst[7]);
unpack64v (tmps, out64, gid, i + 0, out[0]);
unpack64v (tmps, out64, gid, i + 1, out[1]);
unpack64v (tmps, out64, gid, i + 2, out[2]);
unpack64v (tmps, out64, gid, i + 3, out[3]);
unpack64v (tmps, out64, gid, i + 4, out[4]);
unpack64v (tmps, out64, gid, i + 5, out[5]);
unpack64v (tmps, out64, gid, i + 6, out[6]);
unpack64v (tmps, out64, gid, i + 7, out[7]);
}
}

696
OpenCL/m14632.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha512.cl"
#include "inc_cipher_serpent.cl"
#include "inc_luks_af.cl"
@ -25,308 +25,7 @@
#define MAX_ENTROPY 7.0
__constant u64a k_sha512[80] =
{
SHA512C00, SHA512C01, SHA512C02, SHA512C03,
SHA512C04, SHA512C05, SHA512C06, SHA512C07,
SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
SHA512C10, SHA512C11, SHA512C12, SHA512C13,
SHA512C14, SHA512C15, SHA512C16, SHA512C17,
SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
SHA512C20, SHA512C21, SHA512C22, SHA512C23,
SHA512C24, SHA512C25, SHA512C26, SHA512C27,
SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
SHA512C30, SHA512C31, SHA512C32, SHA512C33,
SHA512C34, SHA512C35, SHA512C36, SHA512C37,
SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
SHA512C40, SHA512C41, SHA512C42, SHA512C43,
SHA512C44, SHA512C45, SHA512C46, SHA512C47,
SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
};
void sha512_transform_S (const u64 w0[4], const u64 w1[4], const u64 w2[4], const u64 w3[4], u64 digest[8])
{
u64 a = digest[0];
u64 b = digest[1];
u64 c = digest[2];
u64 d = digest[3];
u64 e = digest[4];
u64 f = digest[5];
u64 g = digest[6];
u64 h = digest[7];
u64 w0_t = w0[0];
u64 w1_t = w0[1];
u64 w2_t = w0[2];
u64 w3_t = w0[3];
u64 w4_t = w1[0];
u64 w5_t = w1[1];
u64 w6_t = w1[2];
u64 w7_t = w1[3];
u64 w8_t = w2[0];
u64 w9_t = w2[1];
u64 wa_t = w2[2];
u64 wb_t = w2[3];
u64 wc_t = w3[0];
u64 wd_t = w3[1];
u64 we_t = w3[2];
u64 wf_t = w3[3];
#define ROUND_EXPAND_S() \
{ \
w0_t = SHA512_EXPAND_S (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA512_EXPAND_S (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA512_EXPAND_S (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA512_EXPAND_S (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA512_EXPAND_S (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA512_EXPAND_S (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA512_EXPAND_S (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA512_EXPAND_S (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA512_EXPAND_S (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA512_EXPAND_S (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA512_EXPAND_S (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA512_EXPAND_S (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA512_EXPAND_S (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA512_EXPAND_S (wb_t, w6_t, we_t, wd_t); \
we_t = SHA512_EXPAND_S (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA512_EXPAND_S (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP_S(i) \
{ \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
}
ROUND_STEP_S (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND_S (); ROUND_STEP_S (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha512_pad_S (u64 w0[4], u64 w1[4], u64 w2[4], u64 w3[4], u64 ipad[8], u64 opad[8])
{
w0[0] = w0[0] ^ 0x3636363636363636;
w0[1] = w0[1] ^ 0x3636363636363636;
w0[2] = w0[2] ^ 0x3636363636363636;
w0[3] = w0[3] ^ 0x3636363636363636;
w1[0] = w1[0] ^ 0x3636363636363636;
w1[1] = w1[1] ^ 0x3636363636363636;
w1[2] = w1[2] ^ 0x3636363636363636;
w1[3] = w1[3] ^ 0x3636363636363636;
w2[0] = w2[0] ^ 0x3636363636363636;
w2[1] = w2[1] ^ 0x3636363636363636;
w2[2] = w2[2] ^ 0x3636363636363636;
w2[3] = w2[3] ^ 0x3636363636363636;
w3[0] = w3[0] ^ 0x3636363636363636;
w3[1] = w3[1] ^ 0x3636363636363636;
w3[2] = w3[2] ^ 0x3636363636363636;
w3[3] = w3[3] ^ 0x3636363636363636;
ipad[0] = SHA512M_A;
ipad[1] = SHA512M_B;
ipad[2] = SHA512M_C;
ipad[3] = SHA512M_D;
ipad[4] = SHA512M_E;
ipad[5] = SHA512M_F;
ipad[6] = SHA512M_G;
ipad[7] = SHA512M_H;
sha512_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a6a6a6a6a;
opad[0] = SHA512M_A;
opad[1] = SHA512M_B;
opad[2] = SHA512M_C;
opad[3] = SHA512M_D;
opad[4] = SHA512M_E;
opad[5] = SHA512M_F;
opad[6] = SHA512M_G;
opad[7] = SHA512M_H;
sha512_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha512_run_S (u64 w0[4], u64 w1[4], u64 w2[4], u64 w3[4], u64 ipad[8], u64 opad[8], u64 digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
digest[5] = ipad[5];
digest[6] = ipad[6];
digest[7] = ipad[7];
sha512_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
digest[5] = opad[5];
digest[6] = opad[6];
digest[7] = opad[7];
sha512_transform_S (w0, w1, w2, w3, digest);
}
void sha512_transform_V (const u64x w0[4], const u64x w1[4], const u64x w2[4], const u64x w3[4], u64x digest[8])
{
u64x a = digest[0];
u64x b = digest[1];
u64x c = digest[2];
u64x d = digest[3];
u64x e = digest[4];
u64x f = digest[5];
u64x g = digest[6];
u64x h = digest[7];
u64x w0_t = w0[0];
u64x w1_t = w0[1];
u64x w2_t = w0[2];
u64x w3_t = w0[3];
u64x w4_t = w1[0];
u64x w5_t = w1[1];
u64x w6_t = w1[2];
u64x w7_t = w1[3];
u64x w8_t = w2[0];
u64x w9_t = w2[1];
u64x wa_t = w2[2];
u64x wb_t = w2[3];
u64x wc_t = w3[0];
u64x wd_t = w3[1];
u64x we_t = w3[2];
u64x wf_t = w3[3];
#define ROUND_EXPAND() \
{ \
w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP(i) \
{ \
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
}
ROUND_STEP (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipad[8], u64x opad[8], u64x digest[8])
void hmac_sha512_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x w4[4], u32x w5[4], u32x w6[4], u32x w7[4], u64x ipad[8], u64x opad[8], u64x digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
@ -337,24 +36,40 @@ void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipa
digest[6] = ipad[6];
digest[7] = ipad[7];
sha512_transform_V (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
sha512_transform_vector (w0, w1, w2, w3, w4, w5, w6, w7, digest);
w0[0] = h32_from_64 (digest[0]);
w0[1] = l32_from_64 (digest[0]);
w0[2] = h32_from_64 (digest[1]);
w0[3] = l32_from_64 (digest[1]);
w1[0] = h32_from_64 (digest[2]);
w1[1] = l32_from_64 (digest[2]);
w1[2] = h32_from_64 (digest[3]);
w1[3] = l32_from_64 (digest[3]);
w2[0] = h32_from_64 (digest[4]);
w2[1] = l32_from_64 (digest[4]);
w2[2] = h32_from_64 (digest[5]);
w2[3] = l32_from_64 (digest[5]);
w3[0] = h32_from_64 (digest[6]);
w3[1] = l32_from_64 (digest[6]);
w3[2] = h32_from_64 (digest[7]);
w3[3] = l32_from_64 (digest[7]);
w4[0] = 0x80000000;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = (128 + 64) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
@ -365,7 +80,7 @@ void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipa
digest[6] = opad[6];
digest[7] = opad[7];
sha512_transform_V (w0, w1, w2, w3, digest);
sha512_transform_vector (w0, w1, w2, w3, w4, w5, w6, w7, digest);
}
__kernel void m14632_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -378,77 +93,116 @@ __kernel void m14632_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u64 w0[4];
u64 w1[4];
u64 w2[4];
u64 w3[4];
w0[0] = hl32_to_64_S (swap32_S (pws[gid].i[ 0]), swap32_S (pws[gid].i[ 1]));
w0[1] = hl32_to_64_S (swap32_S (pws[gid].i[ 2]), swap32_S (pws[gid].i[ 3]));
w0[2] = hl32_to_64_S (swap32_S (pws[gid].i[ 4]), swap32_S (pws[gid].i[ 5]));
w0[3] = hl32_to_64_S (swap32_S (pws[gid].i[ 6]), swap32_S (pws[gid].i[ 7]));
w1[0] = hl32_to_64_S (swap32_S (pws[gid].i[ 8]), swap32_S (pws[gid].i[ 9]));
w1[1] = hl32_to_64_S (swap32_S (pws[gid].i[10]), swap32_S (pws[gid].i[11]));
w1[2] = hl32_to_64_S (swap32_S (pws[gid].i[12]), swap32_S (pws[gid].i[13]));
w1[3] = hl32_to_64_S (swap32_S (pws[gid].i[14]), swap32_S (pws[gid].i[15]));
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = 0;
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u64 salt_buf0[4];
salt_buf0[0] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[0]), swap32_S (salt_bufs[salt_pos].salt_buf[1]));
salt_buf0[1] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[2]), swap32_S (salt_bufs[salt_pos].salt_buf[3]));
salt_buf0[2] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[4]), swap32_S (salt_bufs[salt_pos].salt_buf[5]));
salt_buf0[3] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[6]), swap32_S (salt_bufs[salt_pos].salt_buf[7]));
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
u64 ipad[8];
u64 opad[8];
hmac_sha512_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].ipad64[0] = ipad[0];
tmps[gid].ipad64[1] = ipad[1];
tmps[gid].ipad64[2] = ipad[2];
tmps[gid].ipad64[3] = ipad[3];
tmps[gid].ipad64[4] = ipad[4];
tmps[gid].ipad64[5] = ipad[5];
tmps[gid].ipad64[6] = ipad[6];
tmps[gid].ipad64[7] = ipad[7];
tmps[gid].opad64[0] = opad[0];
tmps[gid].opad64[1] = opad[1];
tmps[gid].opad64[2] = opad[2];
tmps[gid].opad64[3] = opad[3];
tmps[gid].opad64[4] = opad[4];
tmps[gid].opad64[5] = opad[5];
tmps[gid].opad64[6] = opad[6];
tmps[gid].opad64[7] = opad[7];
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[4];
u32 w4[4];
u32 w5[4];
u32 w6[4];
u32 w7[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];
w1[0] = pws[gid].i[ 4];
w1[1] = pws[gid].i[ 5];
w1[2] = pws[gid].i[ 6];
w1[3] = pws[gid].i[ 7];
w2[0] = pws[gid].i[ 8];
w2[1] = pws[gid].i[ 9];
w2[2] = pws[gid].i[10];
w2[3] = pws[gid].i[11];
w3[0] = pws[gid].i[12];
w3[1] = pws[gid].i[13];
w3[2] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
w4[0] = pws[gid].i[16];
w4[1] = pws[gid].i[17];
w4[2] = pws[gid].i[18];
w4[3] = pws[gid].i[19];
w5[0] = pws[gid].i[20];
w5[1] = pws[gid].i[21];
w5[2] = pws[gid].i[22];
w5[3] = pws[gid].i[23];
w6[0] = pws[gid].i[24];
w6[1] = pws[gid].i[25];
w6[2] = pws[gid].i[26];
w6[3] = pws[gid].i[27];
w7[0] = pws[gid].i[28];
w7[1] = pws[gid].i[29];
w7[2] = pws[gid].i[30];
w7[3] = pws[gid].i[31];
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
w0[3] = swap32_S (w0[3]);
w1[0] = swap32_S (w1[0]);
w1[1] = swap32_S (w1[1]);
w1[2] = swap32_S (w1[2]);
w1[3] = swap32_S (w1[3]);
w2[0] = swap32_S (w2[0]);
w2[1] = swap32_S (w2[1]);
w2[2] = swap32_S (w2[2]);
w2[3] = swap32_S (w2[3]);
w3[0] = swap32_S (w3[0]);
w3[1] = swap32_S (w3[1]);
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
w4[0] = swap32_S (w4[0]);
w4[1] = swap32_S (w4[1]);
w4[2] = swap32_S (w4[2]);
w4[3] = swap32_S (w4[3]);
w5[0] = swap32_S (w5[0]);
w5[1] = swap32_S (w5[1]);
w5[2] = swap32_S (w5[2]);
w5[3] = swap32_S (w5[3]);
w6[0] = swap32_S (w6[0]);
w6[1] = swap32_S (w6[1]);
w6[2] = swap32_S (w6[2]);
w6[3] = swap32_S (w6[3]);
w7[0] = swap32_S (w7[0]);
w7[1] = swap32_S (w7[1]);
w7[2] = swap32_S (w7[2]);
w7[3] = swap32_S (w7[3]);
sha512_hmac_ctx_t sha512_hmac_ctx;
sha512_hmac_init (&sha512_hmac_ctx, w0, w1, w2, w3, w5, w5, w6, w7);
tmps[gid].ipad64[0] = sha512_hmac_ctx.ipad.h[0];
tmps[gid].ipad64[1] = sha512_hmac_ctx.ipad.h[1];
tmps[gid].ipad64[2] = sha512_hmac_ctx.ipad.h[2];
tmps[gid].ipad64[3] = sha512_hmac_ctx.ipad.h[3];
tmps[gid].ipad64[4] = sha512_hmac_ctx.ipad.h[4];
tmps[gid].ipad64[5] = sha512_hmac_ctx.ipad.h[5];
tmps[gid].ipad64[6] = sha512_hmac_ctx.ipad.h[6];
tmps[gid].ipad64[7] = sha512_hmac_ctx.ipad.h[7];
tmps[gid].opad64[0] = sha512_hmac_ctx.opad.h[0];
tmps[gid].opad64[1] = sha512_hmac_ctx.opad.h[1];
tmps[gid].opad64[2] = sha512_hmac_ctx.opad.h[2];
tmps[gid].opad64[3] = sha512_hmac_ctx.opad.h[3];
tmps[gid].opad64[4] = sha512_hmac_ctx.opad.h[4];
tmps[gid].opad64[5] = sha512_hmac_ctx.opad.h[5];
tmps[gid].opad64[6] = sha512_hmac_ctx.opad.h[6];
tmps[gid].opad64[7] = sha512_hmac_ctx.opad.h[7];
sha512_hmac_update_global_swap (&sha512_hmac_ctx, salt_bufs[digests_offset].salt_buf, salt_bufs[salt_pos].salt_len);
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 16, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = hl32_to_64_S (j, 0x80000000);
sha512_hmac_ctx_t sha512_hmac_ctx2 = sha512_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
@ -459,29 +213,45 @@ __kernel void m14632_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + salt_len + 4) * 8;
u64 dgst[8];
hmac_sha512_run_S (w0, w1, w2, w3, ipad, opad, dgst);
tmps[gid].dgst64[i + 0] = dgst[0];
tmps[gid].dgst64[i + 1] = dgst[1];
tmps[gid].dgst64[i + 2] = dgst[2];
tmps[gid].dgst64[i + 3] = dgst[3];
tmps[gid].dgst64[i + 4] = dgst[4];
tmps[gid].dgst64[i + 5] = dgst[5];
tmps[gid].dgst64[i + 6] = dgst[6];
tmps[gid].dgst64[i + 7] = dgst[7];
tmps[gid].out64[i + 0] = dgst[0];
tmps[gid].out64[i + 1] = dgst[1];
tmps[gid].out64[i + 2] = dgst[2];
tmps[gid].out64[i + 3] = dgst[3];
tmps[gid].out64[i + 4] = dgst[4];
tmps[gid].out64[i + 5] = dgst[5];
tmps[gid].out64[i + 6] = dgst[6];
tmps[gid].out64[i + 7] = dgst[7];
w3[3] = 0;
w4[0] = 0;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = 0;
sha512_hmac_update_128 (&sha512_hmac_ctx2, w0, w1, w2, w3, w4, w5, w6, w7, 4);
sha512_hmac_final (&sha512_hmac_ctx2);
tmps[gid].dgst64[i + 0] = sha512_hmac_ctx2.opad.h[0];
tmps[gid].dgst64[i + 1] = sha512_hmac_ctx2.opad.h[1];
tmps[gid].dgst64[i + 2] = sha512_hmac_ctx2.opad.h[2];
tmps[gid].dgst64[i + 3] = sha512_hmac_ctx2.opad.h[3];
tmps[gid].dgst64[i + 4] = sha512_hmac_ctx2.opad.h[4];
tmps[gid].dgst64[i + 5] = sha512_hmac_ctx2.opad.h[5];
tmps[gid].dgst64[i + 6] = sha512_hmac_ctx2.opad.h[6];
tmps[gid].dgst64[i + 7] = sha512_hmac_ctx2.opad.h[7];
tmps[gid].out64[i + 0] = tmps[gid].dgst64[i + 0];
tmps[gid].out64[i + 1] = tmps[gid].dgst64[i + 1];
tmps[gid].out64[i + 2] = tmps[gid].dgst64[i + 2];
tmps[gid].out64[i + 3] = tmps[gid].dgst64[i + 3];
tmps[gid].out64[i + 4] = tmps[gid].dgst64[i + 4];
tmps[gid].out64[i + 5] = tmps[gid].dgst64[i + 5];
tmps[gid].out64[i + 6] = tmps[gid].dgst64[i + 6];
tmps[gid].out64[i + 7] = tmps[gid].dgst64[i + 7];
}
}
@ -539,29 +309,49 @@ __kernel void m14632_loop (__global pw_t *pws, __global const kernel_rule_t *rul
for (u32 j = 0; j < loop_cnt; j++)
{
u64x w0[4];
u64x w1[4];
u64x w2[4];
u64x w3[4];
w0[0] = dgst[0];
w0[1] = dgst[1];
w0[2] = dgst[2];
w0[3] = dgst[3];
w1[0] = dgst[4];
w1[1] = dgst[5];
w1[2] = dgst[6];
w1[3] = dgst[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
hmac_sha512_run_V (w0, w1, w2, w3, ipad, opad, dgst);
u32x w0[4];
u32x w1[4];
u32x w2[4];
u32x w3[4];
u32x w4[4];
u32x w5[4];
u32x w6[4];
u32x w7[4];
w0[0] = h32_from_64 (dgst[0]);
w0[1] = l32_from_64 (dgst[0]);
w0[2] = h32_from_64 (dgst[1]);
w0[3] = l32_from_64 (dgst[1]);
w1[0] = h32_from_64 (dgst[2]);
w1[1] = l32_from_64 (dgst[2]);
w1[2] = h32_from_64 (dgst[3]);
w1[3] = l32_from_64 (dgst[3]);
w2[0] = h32_from_64 (dgst[4]);
w2[1] = l32_from_64 (dgst[4]);
w2[2] = h32_from_64 (dgst[5]);
w2[3] = l32_from_64 (dgst[5]);
w3[0] = h32_from_64 (dgst[6]);
w3[1] = l32_from_64 (dgst[6]);
w3[2] = h32_from_64 (dgst[7]);
w3[3] = l32_from_64 (dgst[7]);
w4[0] = 0x80000000;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = (128 + 64) * 8;
hmac_sha512_run_V (w0, w1, w2, w3, w4, w5, w6, w7, ipad, opad, dgst);
out[0] ^= dgst[0];
out[1] ^= dgst[1];
@ -573,23 +363,23 @@ __kernel void m14632_loop (__global pw_t *pws, __global const kernel_rule_t *rul
out[7] ^= dgst[7];
}
unpackv (tmps, dgst64, gid, i + 0, dgst[0]);
unpackv (tmps, dgst64, gid, i + 1, dgst[1]);
unpackv (tmps, dgst64, gid, i + 2, dgst[2]);
unpackv (tmps, dgst64, gid, i + 3, dgst[3]);
unpackv (tmps, dgst64, gid, i + 4, dgst[4]);
unpackv (tmps, dgst64, gid, i + 5, dgst[5]);
unpackv (tmps, dgst64, gid, i + 6, dgst[6]);
unpackv (tmps, dgst64, gid, i + 7, dgst[7]);
unpackv (tmps, out64, gid, i + 0, out[0]);
unpackv (tmps, out64, gid, i + 1, out[1]);
unpackv (tmps, out64, gid, i + 2, out[2]);
unpackv (tmps, out64, gid, i + 3, out[3]);
unpackv (tmps, out64, gid, i + 4, out[4]);
unpackv (tmps, out64, gid, i + 5, out[5]);
unpackv (tmps, out64, gid, i + 6, out[6]);
unpackv (tmps, out64, gid, i + 7, out[7]);
unpack64v (tmps, dgst64, gid, i + 0, dgst[0]);
unpack64v (tmps, dgst64, gid, i + 1, dgst[1]);
unpack64v (tmps, dgst64, gid, i + 2, dgst[2]);
unpack64v (tmps, dgst64, gid, i + 3, dgst[3]);
unpack64v (tmps, dgst64, gid, i + 4, dgst[4]);
unpack64v (tmps, dgst64, gid, i + 5, dgst[5]);
unpack64v (tmps, dgst64, gid, i + 6, dgst[6]);
unpack64v (tmps, dgst64, gid, i + 7, dgst[7]);
unpack64v (tmps, out64, gid, i + 0, out[0]);
unpack64v (tmps, out64, gid, i + 1, out[1]);
unpack64v (tmps, out64, gid, i + 2, out[2]);
unpack64v (tmps, out64, gid, i + 3, out[3]);
unpack64v (tmps, out64, gid, i + 4, out[4]);
unpack64v (tmps, out64, gid, i + 5, out[5]);
unpack64v (tmps, out64, gid, i + 6, out[6]);
unpack64v (tmps, out64, gid, i + 7, out[7]);
}
}

696
OpenCL/m14633.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha512.cl"
#include "inc_cipher_twofish.cl"
#include "inc_luks_af.cl"
@ -25,308 +25,7 @@
#define MAX_ENTROPY 7.0
__constant u64a k_sha512[80] =
{
SHA512C00, SHA512C01, SHA512C02, SHA512C03,
SHA512C04, SHA512C05, SHA512C06, SHA512C07,
SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
SHA512C10, SHA512C11, SHA512C12, SHA512C13,
SHA512C14, SHA512C15, SHA512C16, SHA512C17,
SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
SHA512C20, SHA512C21, SHA512C22, SHA512C23,
SHA512C24, SHA512C25, SHA512C26, SHA512C27,
SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
SHA512C30, SHA512C31, SHA512C32, SHA512C33,
SHA512C34, SHA512C35, SHA512C36, SHA512C37,
SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
SHA512C40, SHA512C41, SHA512C42, SHA512C43,
SHA512C44, SHA512C45, SHA512C46, SHA512C47,
SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
};
void sha512_transform_S (const u64 w0[4], const u64 w1[4], const u64 w2[4], const u64 w3[4], u64 digest[8])
{
u64 a = digest[0];
u64 b = digest[1];
u64 c = digest[2];
u64 d = digest[3];
u64 e = digest[4];
u64 f = digest[5];
u64 g = digest[6];
u64 h = digest[7];
u64 w0_t = w0[0];
u64 w1_t = w0[1];
u64 w2_t = w0[2];
u64 w3_t = w0[3];
u64 w4_t = w1[0];
u64 w5_t = w1[1];
u64 w6_t = w1[2];
u64 w7_t = w1[3];
u64 w8_t = w2[0];
u64 w9_t = w2[1];
u64 wa_t = w2[2];
u64 wb_t = w2[3];
u64 wc_t = w3[0];
u64 wd_t = w3[1];
u64 we_t = w3[2];
u64 wf_t = w3[3];
#define ROUND_EXPAND_S() \
{ \
w0_t = SHA512_EXPAND_S (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA512_EXPAND_S (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA512_EXPAND_S (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA512_EXPAND_S (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA512_EXPAND_S (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA512_EXPAND_S (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA512_EXPAND_S (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA512_EXPAND_S (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA512_EXPAND_S (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA512_EXPAND_S (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA512_EXPAND_S (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA512_EXPAND_S (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA512_EXPAND_S (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA512_EXPAND_S (wb_t, w6_t, we_t, wd_t); \
we_t = SHA512_EXPAND_S (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA512_EXPAND_S (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP_S(i) \
{ \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
SHA512_STEP_S (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
}
ROUND_STEP_S (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND_S (); ROUND_STEP_S (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha512_pad_S (u64 w0[4], u64 w1[4], u64 w2[4], u64 w3[4], u64 ipad[8], u64 opad[8])
{
w0[0] = w0[0] ^ 0x3636363636363636;
w0[1] = w0[1] ^ 0x3636363636363636;
w0[2] = w0[2] ^ 0x3636363636363636;
w0[3] = w0[3] ^ 0x3636363636363636;
w1[0] = w1[0] ^ 0x3636363636363636;
w1[1] = w1[1] ^ 0x3636363636363636;
w1[2] = w1[2] ^ 0x3636363636363636;
w1[3] = w1[3] ^ 0x3636363636363636;
w2[0] = w2[0] ^ 0x3636363636363636;
w2[1] = w2[1] ^ 0x3636363636363636;
w2[2] = w2[2] ^ 0x3636363636363636;
w2[3] = w2[3] ^ 0x3636363636363636;
w3[0] = w3[0] ^ 0x3636363636363636;
w3[1] = w3[1] ^ 0x3636363636363636;
w3[2] = w3[2] ^ 0x3636363636363636;
w3[3] = w3[3] ^ 0x3636363636363636;
ipad[0] = SHA512M_A;
ipad[1] = SHA512M_B;
ipad[2] = SHA512M_C;
ipad[3] = SHA512M_D;
ipad[4] = SHA512M_E;
ipad[5] = SHA512M_F;
ipad[6] = SHA512M_G;
ipad[7] = SHA512M_H;
sha512_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a6a6a6a6a;
opad[0] = SHA512M_A;
opad[1] = SHA512M_B;
opad[2] = SHA512M_C;
opad[3] = SHA512M_D;
opad[4] = SHA512M_E;
opad[5] = SHA512M_F;
opad[6] = SHA512M_G;
opad[7] = SHA512M_H;
sha512_transform_S (w0, w1, w2, w3, opad);
}
void hmac_sha512_run_S (u64 w0[4], u64 w1[4], u64 w2[4], u64 w3[4], u64 ipad[8], u64 opad[8], u64 digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
digest[5] = ipad[5];
digest[6] = ipad[6];
digest[7] = ipad[7];
sha512_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
digest[5] = opad[5];
digest[6] = opad[6];
digest[7] = opad[7];
sha512_transform_S (w0, w1, w2, w3, digest);
}
void sha512_transform_V (const u64x w0[4], const u64x w1[4], const u64x w2[4], const u64x w3[4], u64x digest[8])
{
u64x a = digest[0];
u64x b = digest[1];
u64x c = digest[2];
u64x d = digest[3];
u64x e = digest[4];
u64x f = digest[5];
u64x g = digest[6];
u64x h = digest[7];
u64x w0_t = w0[0];
u64x w1_t = w0[1];
u64x w2_t = w0[2];
u64x w3_t = w0[3];
u64x w4_t = w1[0];
u64x w5_t = w1[1];
u64x w6_t = w1[2];
u64x w7_t = w1[3];
u64x w8_t = w2[0];
u64x w9_t = w2[1];
u64x wa_t = w2[2];
u64x wb_t = w2[3];
u64x wc_t = w3[0];
u64x wd_t = w3[1];
u64x we_t = w3[2];
u64x wf_t = w3[3];
#define ROUND_EXPAND() \
{ \
w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
}
#define ROUND_STEP(i) \
{ \
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
}
ROUND_STEP (0);
#ifdef _unroll
#pragma unroll
#endif
for (int i = 16; i < 80; i += 16)
{
ROUND_EXPAND (); ROUND_STEP (i);
}
digest[0] += a;
digest[1] += b;
digest[2] += c;
digest[3] += d;
digest[4] += e;
digest[5] += f;
digest[6] += g;
digest[7] += h;
}
void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipad[8], u64x opad[8], u64x digest[8])
void hmac_sha512_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x w4[4], u32x w5[4], u32x w6[4], u32x w7[4], u64x ipad[8], u64x opad[8], u64x digest[8])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
@ -337,24 +36,40 @@ void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipa
digest[6] = ipad[6];
digest[7] = ipad[7];
sha512_transform_V (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = digest[5];
w1[2] = digest[6];
w1[3] = digest[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
sha512_transform_vector (w0, w1, w2, w3, w4, w5, w6, w7, digest);
w0[0] = h32_from_64 (digest[0]);
w0[1] = l32_from_64 (digest[0]);
w0[2] = h32_from_64 (digest[1]);
w0[3] = l32_from_64 (digest[1]);
w1[0] = h32_from_64 (digest[2]);
w1[1] = l32_from_64 (digest[2]);
w1[2] = h32_from_64 (digest[3]);
w1[3] = l32_from_64 (digest[3]);
w2[0] = h32_from_64 (digest[4]);
w2[1] = l32_from_64 (digest[4]);
w2[2] = h32_from_64 (digest[5]);
w2[3] = l32_from_64 (digest[5]);
w3[0] = h32_from_64 (digest[6]);
w3[1] = l32_from_64 (digest[6]);
w3[2] = h32_from_64 (digest[7]);
w3[3] = l32_from_64 (digest[7]);
w4[0] = 0x80000000;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = (128 + 64) * 8;
digest[0] = opad[0];
digest[1] = opad[1];
@ -365,7 +80,7 @@ void hmac_sha512_run_V (u64x w0[4], u64x w1[4], u64x w2[4], u64x w3[4], u64x ipa
digest[6] = opad[6];
digest[7] = opad[7];
sha512_transform_V (w0, w1, w2, w3, digest);
sha512_transform_vector (w0, w1, w2, w3, w4, w5, w6, w7, digest);
}
__kernel void m14633_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -378,77 +93,116 @@ __kernel void m14633_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u64 w0[4];
u64 w1[4];
u64 w2[4];
u64 w3[4];
w0[0] = hl32_to_64_S (swap32_S (pws[gid].i[ 0]), swap32_S (pws[gid].i[ 1]));
w0[1] = hl32_to_64_S (swap32_S (pws[gid].i[ 2]), swap32_S (pws[gid].i[ 3]));
w0[2] = hl32_to_64_S (swap32_S (pws[gid].i[ 4]), swap32_S (pws[gid].i[ 5]));
w0[3] = hl32_to_64_S (swap32_S (pws[gid].i[ 6]), swap32_S (pws[gid].i[ 7]));
w1[0] = hl32_to_64_S (swap32_S (pws[gid].i[ 8]), swap32_S (pws[gid].i[ 9]));
w1[1] = hl32_to_64_S (swap32_S (pws[gid].i[10]), swap32_S (pws[gid].i[11]));
w1[2] = hl32_to_64_S (swap32_S (pws[gid].i[12]), swap32_S (pws[gid].i[13]));
w1[3] = hl32_to_64_S (swap32_S (pws[gid].i[14]), swap32_S (pws[gid].i[15]));
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = 0;
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u64 salt_buf0[4];
salt_buf0[0] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[0]), swap32_S (salt_bufs[salt_pos].salt_buf[1]));
salt_buf0[1] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[2]), swap32_S (salt_bufs[salt_pos].salt_buf[3]));
salt_buf0[2] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[4]), swap32_S (salt_bufs[salt_pos].salt_buf[5]));
salt_buf0[3] = hl32_to_64_S (swap32_S (salt_bufs[salt_pos].salt_buf[6]), swap32_S (salt_bufs[salt_pos].salt_buf[7]));
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
u64 ipad[8];
u64 opad[8];
hmac_sha512_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].ipad64[0] = ipad[0];
tmps[gid].ipad64[1] = ipad[1];
tmps[gid].ipad64[2] = ipad[2];
tmps[gid].ipad64[3] = ipad[3];
tmps[gid].ipad64[4] = ipad[4];
tmps[gid].ipad64[5] = ipad[5];
tmps[gid].ipad64[6] = ipad[6];
tmps[gid].ipad64[7] = ipad[7];
tmps[gid].opad64[0] = opad[0];
tmps[gid].opad64[1] = opad[1];
tmps[gid].opad64[2] = opad[2];
tmps[gid].opad64[3] = opad[3];
tmps[gid].opad64[4] = opad[4];
tmps[gid].opad64[5] = opad[5];
tmps[gid].opad64[6] = opad[6];
tmps[gid].opad64[7] = opad[7];
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[4];
u32 w4[4];
u32 w5[4];
u32 w6[4];
u32 w7[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];
w1[0] = pws[gid].i[ 4];
w1[1] = pws[gid].i[ 5];
w1[2] = pws[gid].i[ 6];
w1[3] = pws[gid].i[ 7];
w2[0] = pws[gid].i[ 8];
w2[1] = pws[gid].i[ 9];
w2[2] = pws[gid].i[10];
w2[3] = pws[gid].i[11];
w3[0] = pws[gid].i[12];
w3[1] = pws[gid].i[13];
w3[2] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
w4[0] = pws[gid].i[16];
w4[1] = pws[gid].i[17];
w4[2] = pws[gid].i[18];
w4[3] = pws[gid].i[19];
w5[0] = pws[gid].i[20];
w5[1] = pws[gid].i[21];
w5[2] = pws[gid].i[22];
w5[3] = pws[gid].i[23];
w6[0] = pws[gid].i[24];
w6[1] = pws[gid].i[25];
w6[2] = pws[gid].i[26];
w6[3] = pws[gid].i[27];
w7[0] = pws[gid].i[28];
w7[1] = pws[gid].i[29];
w7[2] = pws[gid].i[30];
w7[3] = pws[gid].i[31];
w0[0] = swap32_S (w0[0]);
w0[1] = swap32_S (w0[1]);
w0[2] = swap32_S (w0[2]);
w0[3] = swap32_S (w0[3]);
w1[0] = swap32_S (w1[0]);
w1[1] = swap32_S (w1[1]);
w1[2] = swap32_S (w1[2]);
w1[3] = swap32_S (w1[3]);
w2[0] = swap32_S (w2[0]);
w2[1] = swap32_S (w2[1]);
w2[2] = swap32_S (w2[2]);
w2[3] = swap32_S (w2[3]);
w3[0] = swap32_S (w3[0]);
w3[1] = swap32_S (w3[1]);
w3[2] = swap32_S (w3[2]);
w3[3] = swap32_S (w3[3]);
w4[0] = swap32_S (w4[0]);
w4[1] = swap32_S (w4[1]);
w4[2] = swap32_S (w4[2]);
w4[3] = swap32_S (w4[3]);
w5[0] = swap32_S (w5[0]);
w5[1] = swap32_S (w5[1]);
w5[2] = swap32_S (w5[2]);
w5[3] = swap32_S (w5[3]);
w6[0] = swap32_S (w6[0]);
w6[1] = swap32_S (w6[1]);
w6[2] = swap32_S (w6[2]);
w6[3] = swap32_S (w6[3]);
w7[0] = swap32_S (w7[0]);
w7[1] = swap32_S (w7[1]);
w7[2] = swap32_S (w7[2]);
w7[3] = swap32_S (w7[3]);
sha512_hmac_ctx_t sha512_hmac_ctx;
sha512_hmac_init (&sha512_hmac_ctx, w0, w1, w2, w3, w5, w5, w6, w7);
tmps[gid].ipad64[0] = sha512_hmac_ctx.ipad.h[0];
tmps[gid].ipad64[1] = sha512_hmac_ctx.ipad.h[1];
tmps[gid].ipad64[2] = sha512_hmac_ctx.ipad.h[2];
tmps[gid].ipad64[3] = sha512_hmac_ctx.ipad.h[3];
tmps[gid].ipad64[4] = sha512_hmac_ctx.ipad.h[4];
tmps[gid].ipad64[5] = sha512_hmac_ctx.ipad.h[5];
tmps[gid].ipad64[6] = sha512_hmac_ctx.ipad.h[6];
tmps[gid].ipad64[7] = sha512_hmac_ctx.ipad.h[7];
tmps[gid].opad64[0] = sha512_hmac_ctx.opad.h[0];
tmps[gid].opad64[1] = sha512_hmac_ctx.opad.h[1];
tmps[gid].opad64[2] = sha512_hmac_ctx.opad.h[2];
tmps[gid].opad64[3] = sha512_hmac_ctx.opad.h[3];
tmps[gid].opad64[4] = sha512_hmac_ctx.opad.h[4];
tmps[gid].opad64[5] = sha512_hmac_ctx.opad.h[5];
tmps[gid].opad64[6] = sha512_hmac_ctx.opad.h[6];
tmps[gid].opad64[7] = sha512_hmac_ctx.opad.h[7];
sha512_hmac_update_global_swap (&sha512_hmac_ctx, salt_bufs[digests_offset].salt_buf, salt_bufs[salt_pos].salt_len);
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 16, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = hl32_to_64_S (j, 0x80000000);
sha512_hmac_ctx_t sha512_hmac_ctx2 = sha512_hmac_ctx;
w0[0] = j;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
@ -459,29 +213,45 @@ __kernel void m14633_init (__global pw_t *pws, __global const kernel_rule_t *rul
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + salt_len + 4) * 8;
u64 dgst[8];
hmac_sha512_run_S (w0, w1, w2, w3, ipad, opad, dgst);
tmps[gid].dgst64[i + 0] = dgst[0];
tmps[gid].dgst64[i + 1] = dgst[1];
tmps[gid].dgst64[i + 2] = dgst[2];
tmps[gid].dgst64[i + 3] = dgst[3];
tmps[gid].dgst64[i + 4] = dgst[4];
tmps[gid].dgst64[i + 5] = dgst[5];
tmps[gid].dgst64[i + 6] = dgst[6];
tmps[gid].dgst64[i + 7] = dgst[7];
tmps[gid].out64[i + 0] = dgst[0];
tmps[gid].out64[i + 1] = dgst[1];
tmps[gid].out64[i + 2] = dgst[2];
tmps[gid].out64[i + 3] = dgst[3];
tmps[gid].out64[i + 4] = dgst[4];
tmps[gid].out64[i + 5] = dgst[5];
tmps[gid].out64[i + 6] = dgst[6];
tmps[gid].out64[i + 7] = dgst[7];
w3[3] = 0;
w4[0] = 0;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = 0;
sha512_hmac_update_128 (&sha512_hmac_ctx2, w0, w1, w2, w3, w4, w5, w6, w7, 4);
sha512_hmac_final (&sha512_hmac_ctx2);
tmps[gid].dgst64[i + 0] = sha512_hmac_ctx2.opad.h[0];
tmps[gid].dgst64[i + 1] = sha512_hmac_ctx2.opad.h[1];
tmps[gid].dgst64[i + 2] = sha512_hmac_ctx2.opad.h[2];
tmps[gid].dgst64[i + 3] = sha512_hmac_ctx2.opad.h[3];
tmps[gid].dgst64[i + 4] = sha512_hmac_ctx2.opad.h[4];
tmps[gid].dgst64[i + 5] = sha512_hmac_ctx2.opad.h[5];
tmps[gid].dgst64[i + 6] = sha512_hmac_ctx2.opad.h[6];
tmps[gid].dgst64[i + 7] = sha512_hmac_ctx2.opad.h[7];
tmps[gid].out64[i + 0] = tmps[gid].dgst64[i + 0];
tmps[gid].out64[i + 1] = tmps[gid].dgst64[i + 1];
tmps[gid].out64[i + 2] = tmps[gid].dgst64[i + 2];
tmps[gid].out64[i + 3] = tmps[gid].dgst64[i + 3];
tmps[gid].out64[i + 4] = tmps[gid].dgst64[i + 4];
tmps[gid].out64[i + 5] = tmps[gid].dgst64[i + 5];
tmps[gid].out64[i + 6] = tmps[gid].dgst64[i + 6];
tmps[gid].out64[i + 7] = tmps[gid].dgst64[i + 7];
}
}
@ -539,29 +309,49 @@ __kernel void m14633_loop (__global pw_t *pws, __global const kernel_rule_t *rul
for (u32 j = 0; j < loop_cnt; j++)
{
u64x w0[4];
u64x w1[4];
u64x w2[4];
u64x w3[4];
w0[0] = dgst[0];
w0[1] = dgst[1];
w0[2] = dgst[2];
w0[3] = dgst[3];
w1[0] = dgst[4];
w1[1] = dgst[5];
w1[2] = dgst[6];
w1[3] = dgst[7];
w2[0] = 0x8000000000000000;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = (128 + 64) * 8;
hmac_sha512_run_V (w0, w1, w2, w3, ipad, opad, dgst);
u32x w0[4];
u32x w1[4];
u32x w2[4];
u32x w3[4];
u32x w4[4];
u32x w5[4];
u32x w6[4];
u32x w7[4];
w0[0] = h32_from_64 (dgst[0]);
w0[1] = l32_from_64 (dgst[0]);
w0[2] = h32_from_64 (dgst[1]);
w0[3] = l32_from_64 (dgst[1]);
w1[0] = h32_from_64 (dgst[2]);
w1[1] = l32_from_64 (dgst[2]);
w1[2] = h32_from_64 (dgst[3]);
w1[3] = l32_from_64 (dgst[3]);
w2[0] = h32_from_64 (dgst[4]);
w2[1] = l32_from_64 (dgst[4]);
w2[2] = h32_from_64 (dgst[5]);
w2[3] = l32_from_64 (dgst[5]);
w3[0] = h32_from_64 (dgst[6]);
w3[1] = l32_from_64 (dgst[6]);
w3[2] = h32_from_64 (dgst[7]);
w3[3] = l32_from_64 (dgst[7]);
w4[0] = 0x80000000;
w4[1] = 0;
w4[2] = 0;
w4[3] = 0;
w5[0] = 0;
w5[1] = 0;
w5[2] = 0;
w5[3] = 0;
w6[0] = 0;
w6[1] = 0;
w6[2] = 0;
w6[3] = 0;
w7[0] = 0;
w7[1] = 0;
w7[2] = 0;
w7[3] = (128 + 64) * 8;
hmac_sha512_run_V (w0, w1, w2, w3, w4, w5, w6, w7, ipad, opad, dgst);
out[0] ^= dgst[0];
out[1] ^= dgst[1];
@ -573,23 +363,23 @@ __kernel void m14633_loop (__global pw_t *pws, __global const kernel_rule_t *rul
out[7] ^= dgst[7];
}
unpackv (tmps, dgst64, gid, i + 0, dgst[0]);
unpackv (tmps, dgst64, gid, i + 1, dgst[1]);
unpackv (tmps, dgst64, gid, i + 2, dgst[2]);
unpackv (tmps, dgst64, gid, i + 3, dgst[3]);
unpackv (tmps, dgst64, gid, i + 4, dgst[4]);
unpackv (tmps, dgst64, gid, i + 5, dgst[5]);
unpackv (tmps, dgst64, gid, i + 6, dgst[6]);
unpackv (tmps, dgst64, gid, i + 7, dgst[7]);
unpackv (tmps, out64, gid, i + 0, out[0]);
unpackv (tmps, out64, gid, i + 1, out[1]);
unpackv (tmps, out64, gid, i + 2, out[2]);
unpackv (tmps, out64, gid, i + 3, out[3]);
unpackv (tmps, out64, gid, i + 4, out[4]);
unpackv (tmps, out64, gid, i + 5, out[5]);
unpackv (tmps, out64, gid, i + 6, out[6]);
unpackv (tmps, out64, gid, i + 7, out[7]);
unpack64v (tmps, dgst64, gid, i + 0, dgst[0]);
unpack64v (tmps, dgst64, gid, i + 1, dgst[1]);
unpack64v (tmps, dgst64, gid, i + 2, dgst[2]);
unpack64v (tmps, dgst64, gid, i + 3, dgst[3]);
unpack64v (tmps, dgst64, gid, i + 4, dgst[4]);
unpack64v (tmps, dgst64, gid, i + 5, dgst[5]);
unpack64v (tmps, dgst64, gid, i + 6, dgst[6]);
unpack64v (tmps, dgst64, gid, i + 7, dgst[7]);
unpack64v (tmps, out64, gid, i + 0, out[0]);
unpack64v (tmps, out64, gid, i + 1, out[1]);
unpack64v (tmps, out64, gid, i + 2, out[2]);
unpack64v (tmps, out64, gid, i + 3, out[3]);
unpack64v (tmps, out64, gid, i + 4, out[4]);
unpack64v (tmps, out64, gid, i + 5, out[5]);
unpack64v (tmps, out64, gid, i + 6, out[6]);
unpack64v (tmps, out64, gid, i + 7, out[7]);
}
}

632
OpenCL/m14641.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_ripemd160.cl"
#include "inc_cipher_aes.cl"
#include "inc_luks_af.cl"
@ -25,523 +25,6 @@
#define MAX_ENTROPY 7.0
void ripemd160_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
u32 a1 = digest[0];
u32 b1 = digest[1];
u32 c1 = digest[2];
u32 d1 = digest[3];
u32 e1 = digest[4];
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, w0_t, RIPEMD160C00, RIPEMD160S00);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, w1_t, RIPEMD160C00, RIPEMD160S01);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, w2_t, RIPEMD160C00, RIPEMD160S02);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, w3_t, RIPEMD160C00, RIPEMD160S03);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, w4_t, RIPEMD160C00, RIPEMD160S04);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, w5_t, RIPEMD160C00, RIPEMD160S05);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, w6_t, RIPEMD160C00, RIPEMD160S06);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, w7_t, RIPEMD160C00, RIPEMD160S07);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, w8_t, RIPEMD160C00, RIPEMD160S08);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, w9_t, RIPEMD160C00, RIPEMD160S09);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, wa_t, RIPEMD160C00, RIPEMD160S0A);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, wb_t, RIPEMD160C00, RIPEMD160S0B);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, wc_t, RIPEMD160C00, RIPEMD160S0C);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, wd_t, RIPEMD160C00, RIPEMD160S0D);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, we_t, RIPEMD160C00, RIPEMD160S0E);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, wf_t, RIPEMD160C00, RIPEMD160S0F);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w7_t, RIPEMD160C10, RIPEMD160S10);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, w4_t, RIPEMD160C10, RIPEMD160S11);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, wd_t, RIPEMD160C10, RIPEMD160S12);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, w1_t, RIPEMD160C10, RIPEMD160S13);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, wa_t, RIPEMD160C10, RIPEMD160S14);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w6_t, RIPEMD160C10, RIPEMD160S15);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, wf_t, RIPEMD160C10, RIPEMD160S16);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, w3_t, RIPEMD160C10, RIPEMD160S17);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, wc_t, RIPEMD160C10, RIPEMD160S18);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, w0_t, RIPEMD160C10, RIPEMD160S19);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w9_t, RIPEMD160C10, RIPEMD160S1A);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, w5_t, RIPEMD160C10, RIPEMD160S1B);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, w2_t, RIPEMD160C10, RIPEMD160S1C);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, we_t, RIPEMD160C10, RIPEMD160S1D);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, wb_t, RIPEMD160C10, RIPEMD160S1E);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w8_t, RIPEMD160C10, RIPEMD160S1F);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, w3_t, RIPEMD160C20, RIPEMD160S20);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, wa_t, RIPEMD160C20, RIPEMD160S21);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, we_t, RIPEMD160C20, RIPEMD160S22);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, w4_t, RIPEMD160C20, RIPEMD160S23);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w9_t, RIPEMD160C20, RIPEMD160S24);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, wf_t, RIPEMD160C20, RIPEMD160S25);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, w8_t, RIPEMD160C20, RIPEMD160S26);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, w1_t, RIPEMD160C20, RIPEMD160S27);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, w2_t, RIPEMD160C20, RIPEMD160S28);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w7_t, RIPEMD160C20, RIPEMD160S29);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, w0_t, RIPEMD160C20, RIPEMD160S2A);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, w6_t, RIPEMD160C20, RIPEMD160S2B);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, wd_t, RIPEMD160C20, RIPEMD160S2C);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, wb_t, RIPEMD160C20, RIPEMD160S2D);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w5_t, RIPEMD160C20, RIPEMD160S2E);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, wc_t, RIPEMD160C20, RIPEMD160S2F);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w1_t, RIPEMD160C30, RIPEMD160S30);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, w9_t, RIPEMD160C30, RIPEMD160S31);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, wb_t, RIPEMD160C30, RIPEMD160S32);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, wa_t, RIPEMD160C30, RIPEMD160S33);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w0_t, RIPEMD160C30, RIPEMD160S34);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w8_t, RIPEMD160C30, RIPEMD160S35);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, wc_t, RIPEMD160C30, RIPEMD160S36);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, w4_t, RIPEMD160C30, RIPEMD160S37);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, wd_t, RIPEMD160C30, RIPEMD160S38);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w3_t, RIPEMD160C30, RIPEMD160S39);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w7_t, RIPEMD160C30, RIPEMD160S3A);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, wf_t, RIPEMD160C30, RIPEMD160S3B);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, we_t, RIPEMD160C30, RIPEMD160S3C);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, w5_t, RIPEMD160C30, RIPEMD160S3D);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w6_t, RIPEMD160C30, RIPEMD160S3E);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w2_t, RIPEMD160C30, RIPEMD160S3F);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, w4_t, RIPEMD160C40, RIPEMD160S40);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w0_t, RIPEMD160C40, RIPEMD160S41);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, w5_t, RIPEMD160C40, RIPEMD160S42);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, w9_t, RIPEMD160C40, RIPEMD160S43);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, w7_t, RIPEMD160C40, RIPEMD160S44);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, wc_t, RIPEMD160C40, RIPEMD160S45);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w2_t, RIPEMD160C40, RIPEMD160S46);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, wa_t, RIPEMD160C40, RIPEMD160S47);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, we_t, RIPEMD160C40, RIPEMD160S48);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, w1_t, RIPEMD160C40, RIPEMD160S49);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, w3_t, RIPEMD160C40, RIPEMD160S4A);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w8_t, RIPEMD160C40, RIPEMD160S4B);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, wb_t, RIPEMD160C40, RIPEMD160S4C);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, w6_t, RIPEMD160C40, RIPEMD160S4D);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, wf_t, RIPEMD160C40, RIPEMD160S4E);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, wd_t, RIPEMD160C40, RIPEMD160S4F);
u32 a2 = digest[0];
u32 b2 = digest[1];
u32 c2 = digest[2];
u32 d2 = digest[3];
u32 e2 = digest[4];
RIPEMD160_STEP_S_WORKAROUND_BUG (RIPEMD160_J , a2, b2, c2, d2, e2, w5_t, RIPEMD160C50, RIPEMD160S50);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, we_t, RIPEMD160C50, RIPEMD160S51);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w7_t, RIPEMD160C50, RIPEMD160S52);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, w0_t, RIPEMD160C50, RIPEMD160S53);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w9_t, RIPEMD160C50, RIPEMD160S54);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, w2_t, RIPEMD160C50, RIPEMD160S55);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, wb_t, RIPEMD160C50, RIPEMD160S56);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w4_t, RIPEMD160C50, RIPEMD160S57);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, wd_t, RIPEMD160C50, RIPEMD160S58);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w6_t, RIPEMD160C50, RIPEMD160S59);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, wf_t, RIPEMD160C50, RIPEMD160S5A);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, w8_t, RIPEMD160C50, RIPEMD160S5B);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w1_t, RIPEMD160C50, RIPEMD160S5C);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, wa_t, RIPEMD160C50, RIPEMD160S5D);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w3_t, RIPEMD160C50, RIPEMD160S5E);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, wc_t, RIPEMD160C50, RIPEMD160S5F);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w6_t, RIPEMD160C60, RIPEMD160S60);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, wb_t, RIPEMD160C60, RIPEMD160S61);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, w3_t, RIPEMD160C60, RIPEMD160S62);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, w7_t, RIPEMD160C60, RIPEMD160S63);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, w0_t, RIPEMD160C60, RIPEMD160S64);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, wd_t, RIPEMD160C60, RIPEMD160S65);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, w5_t, RIPEMD160C60, RIPEMD160S66);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, wa_t, RIPEMD160C60, RIPEMD160S67);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, we_t, RIPEMD160C60, RIPEMD160S68);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, wf_t, RIPEMD160C60, RIPEMD160S69);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w8_t, RIPEMD160C60, RIPEMD160S6A);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, wc_t, RIPEMD160C60, RIPEMD160S6B);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, w4_t, RIPEMD160C60, RIPEMD160S6C);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, w9_t, RIPEMD160C60, RIPEMD160S6D);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, w1_t, RIPEMD160C60, RIPEMD160S6E);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w2_t, RIPEMD160C60, RIPEMD160S6F);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wf_t, RIPEMD160C70, RIPEMD160S70);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w5_t, RIPEMD160C70, RIPEMD160S71);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, w1_t, RIPEMD160C70, RIPEMD160S72);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, w3_t, RIPEMD160C70, RIPEMD160S73);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w7_t, RIPEMD160C70, RIPEMD160S74);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, we_t, RIPEMD160C70, RIPEMD160S75);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w6_t, RIPEMD160C70, RIPEMD160S76);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, w9_t, RIPEMD160C70, RIPEMD160S77);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, wb_t, RIPEMD160C70, RIPEMD160S78);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w8_t, RIPEMD160C70, RIPEMD160S79);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wc_t, RIPEMD160C70, RIPEMD160S7A);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w2_t, RIPEMD160C70, RIPEMD160S7B);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, wa_t, RIPEMD160C70, RIPEMD160S7C);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, w0_t, RIPEMD160C70, RIPEMD160S7D);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w4_t, RIPEMD160C70, RIPEMD160S7E);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wd_t, RIPEMD160C70, RIPEMD160S7F);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, w8_t, RIPEMD160C80, RIPEMD160S80);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, w6_t, RIPEMD160C80, RIPEMD160S81);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w4_t, RIPEMD160C80, RIPEMD160S82);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w1_t, RIPEMD160C80, RIPEMD160S83);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, w3_t, RIPEMD160C80, RIPEMD160S84);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, wb_t, RIPEMD160C80, RIPEMD160S85);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, wf_t, RIPEMD160C80, RIPEMD160S86);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w0_t, RIPEMD160C80, RIPEMD160S87);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w5_t, RIPEMD160C80, RIPEMD160S88);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, wc_t, RIPEMD160C80, RIPEMD160S89);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, w2_t, RIPEMD160C80, RIPEMD160S8A);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, wd_t, RIPEMD160C80, RIPEMD160S8B);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w9_t, RIPEMD160C80, RIPEMD160S8C);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w7_t, RIPEMD160C80, RIPEMD160S8D);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, wa_t, RIPEMD160C80, RIPEMD160S8E);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, we_t, RIPEMD160C80, RIPEMD160S8F);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wc_t, RIPEMD160C90, RIPEMD160S90);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, wf_t, RIPEMD160C90, RIPEMD160S91);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, wa_t, RIPEMD160C90, RIPEMD160S92);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w4_t, RIPEMD160C90, RIPEMD160S93);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w1_t, RIPEMD160C90, RIPEMD160S94);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, w5_t, RIPEMD160C90, RIPEMD160S95);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, w8_t, RIPEMD160C90, RIPEMD160S96);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, w7_t, RIPEMD160C90, RIPEMD160S97);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w6_t, RIPEMD160C90, RIPEMD160S98);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w2_t, RIPEMD160C90, RIPEMD160S99);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wd_t, RIPEMD160C90, RIPEMD160S9A);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, we_t, RIPEMD160C90, RIPEMD160S9B);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, w0_t, RIPEMD160C90, RIPEMD160S9C);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w3_t, RIPEMD160C90, RIPEMD160S9D);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w9_t, RIPEMD160C90, RIPEMD160S9E);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wb_t, RIPEMD160C90, RIPEMD160S9F);
const u32 a = digest[1] + c1 + d2;
const u32 b = digest[2] + d1 + e2;
const u32 c = digest[3] + e1 + a2;
const u32 d = digest[4] + a1 + b2;
const u32 e = digest[0] + b1 + c2;
digest[0] = a;
digest[1] = b;
digest[2] = c;
digest[3] = d;
digest[4] = e;
}
void hmac_ripemd160_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = RIPEMD160M_A;
ipad[1] = RIPEMD160M_B;
ipad[2] = RIPEMD160M_C;
ipad[3] = RIPEMD160M_D;
ipad[4] = RIPEMD160M_E;
ripemd160_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = RIPEMD160M_A;
opad[1] = RIPEMD160M_B;
opad[2] = RIPEMD160M_C;
opad[3] = RIPEMD160M_D;
opad[4] = RIPEMD160M_E;
ripemd160_transform_S (w0, w1, w2, w3, opad);
}
void hmac_ripemd160_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
ripemd160_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0x80;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = (64 + 20) * 8;
w3[3] = 0;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
ripemd160_transform_S (w0, w1, w2, w3, digest);
}
void ripemd160_transform_V (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
{
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];
u32x a1 = digest[0];
u32x b1 = digest[1];
u32x c1 = digest[2];
u32x d1 = digest[3];
u32x e1 = digest[4];
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, w0_t, RIPEMD160C00, RIPEMD160S00);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, w1_t, RIPEMD160C00, RIPEMD160S01);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, w2_t, RIPEMD160C00, RIPEMD160S02);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, w3_t, RIPEMD160C00, RIPEMD160S03);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, w4_t, RIPEMD160C00, RIPEMD160S04);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, w5_t, RIPEMD160C00, RIPEMD160S05);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, w6_t, RIPEMD160C00, RIPEMD160S06);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, w7_t, RIPEMD160C00, RIPEMD160S07);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, w8_t, RIPEMD160C00, RIPEMD160S08);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, w9_t, RIPEMD160C00, RIPEMD160S09);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, wa_t, RIPEMD160C00, RIPEMD160S0A);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, wb_t, RIPEMD160C00, RIPEMD160S0B);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, wc_t, RIPEMD160C00, RIPEMD160S0C);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, wd_t, RIPEMD160C00, RIPEMD160S0D);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, we_t, RIPEMD160C00, RIPEMD160S0E);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, wf_t, RIPEMD160C00, RIPEMD160S0F);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w7_t, RIPEMD160C10, RIPEMD160S10);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, w4_t, RIPEMD160C10, RIPEMD160S11);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, wd_t, RIPEMD160C10, RIPEMD160S12);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, w1_t, RIPEMD160C10, RIPEMD160S13);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, wa_t, RIPEMD160C10, RIPEMD160S14);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w6_t, RIPEMD160C10, RIPEMD160S15);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, wf_t, RIPEMD160C10, RIPEMD160S16);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, w3_t, RIPEMD160C10, RIPEMD160S17);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, wc_t, RIPEMD160C10, RIPEMD160S18);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, w0_t, RIPEMD160C10, RIPEMD160S19);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w9_t, RIPEMD160C10, RIPEMD160S1A);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, w5_t, RIPEMD160C10, RIPEMD160S1B);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, w2_t, RIPEMD160C10, RIPEMD160S1C);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, we_t, RIPEMD160C10, RIPEMD160S1D);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, wb_t, RIPEMD160C10, RIPEMD160S1E);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w8_t, RIPEMD160C10, RIPEMD160S1F);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, w3_t, RIPEMD160C20, RIPEMD160S20);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, wa_t, RIPEMD160C20, RIPEMD160S21);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, we_t, RIPEMD160C20, RIPEMD160S22);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, w4_t, RIPEMD160C20, RIPEMD160S23);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w9_t, RIPEMD160C20, RIPEMD160S24);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, wf_t, RIPEMD160C20, RIPEMD160S25);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, w8_t, RIPEMD160C20, RIPEMD160S26);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, w1_t, RIPEMD160C20, RIPEMD160S27);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, w2_t, RIPEMD160C20, RIPEMD160S28);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w7_t, RIPEMD160C20, RIPEMD160S29);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, w0_t, RIPEMD160C20, RIPEMD160S2A);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, w6_t, RIPEMD160C20, RIPEMD160S2B);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, wd_t, RIPEMD160C20, RIPEMD160S2C);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, wb_t, RIPEMD160C20, RIPEMD160S2D);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w5_t, RIPEMD160C20, RIPEMD160S2E);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, wc_t, RIPEMD160C20, RIPEMD160S2F);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w1_t, RIPEMD160C30, RIPEMD160S30);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, w9_t, RIPEMD160C30, RIPEMD160S31);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, wb_t, RIPEMD160C30, RIPEMD160S32);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, wa_t, RIPEMD160C30, RIPEMD160S33);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w0_t, RIPEMD160C30, RIPEMD160S34);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w8_t, RIPEMD160C30, RIPEMD160S35);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, wc_t, RIPEMD160C30, RIPEMD160S36);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, w4_t, RIPEMD160C30, RIPEMD160S37);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, wd_t, RIPEMD160C30, RIPEMD160S38);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w3_t, RIPEMD160C30, RIPEMD160S39);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w7_t, RIPEMD160C30, RIPEMD160S3A);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, wf_t, RIPEMD160C30, RIPEMD160S3B);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, we_t, RIPEMD160C30, RIPEMD160S3C);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, w5_t, RIPEMD160C30, RIPEMD160S3D);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w6_t, RIPEMD160C30, RIPEMD160S3E);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w2_t, RIPEMD160C30, RIPEMD160S3F);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, w4_t, RIPEMD160C40, RIPEMD160S40);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w0_t, RIPEMD160C40, RIPEMD160S41);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, w5_t, RIPEMD160C40, RIPEMD160S42);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, w9_t, RIPEMD160C40, RIPEMD160S43);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, w7_t, RIPEMD160C40, RIPEMD160S44);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, wc_t, RIPEMD160C40, RIPEMD160S45);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w2_t, RIPEMD160C40, RIPEMD160S46);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, wa_t, RIPEMD160C40, RIPEMD160S47);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, we_t, RIPEMD160C40, RIPEMD160S48);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, w1_t, RIPEMD160C40, RIPEMD160S49);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, w3_t, RIPEMD160C40, RIPEMD160S4A);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w8_t, RIPEMD160C40, RIPEMD160S4B);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, wb_t, RIPEMD160C40, RIPEMD160S4C);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, w6_t, RIPEMD160C40, RIPEMD160S4D);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, wf_t, RIPEMD160C40, RIPEMD160S4E);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, wd_t, RIPEMD160C40, RIPEMD160S4F);
u32x a2 = digest[0];
u32x b2 = digest[1];
u32x c2 = digest[2];
u32x d2 = digest[3];
u32x e2 = digest[4];
RIPEMD160_STEP_WORKAROUND_BUG (RIPEMD160_J , a2, b2, c2, d2, e2, w5_t, RIPEMD160C50, RIPEMD160S50);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, we_t, RIPEMD160C50, RIPEMD160S51);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w7_t, RIPEMD160C50, RIPEMD160S52);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, w0_t, RIPEMD160C50, RIPEMD160S53);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w9_t, RIPEMD160C50, RIPEMD160S54);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, w2_t, RIPEMD160C50, RIPEMD160S55);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, wb_t, RIPEMD160C50, RIPEMD160S56);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w4_t, RIPEMD160C50, RIPEMD160S57);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, wd_t, RIPEMD160C50, RIPEMD160S58);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w6_t, RIPEMD160C50, RIPEMD160S59);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, wf_t, RIPEMD160C50, RIPEMD160S5A);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, w8_t, RIPEMD160C50, RIPEMD160S5B);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w1_t, RIPEMD160C50, RIPEMD160S5C);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, wa_t, RIPEMD160C50, RIPEMD160S5D);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w3_t, RIPEMD160C50, RIPEMD160S5E);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, wc_t, RIPEMD160C50, RIPEMD160S5F);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w6_t, RIPEMD160C60, RIPEMD160S60);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, wb_t, RIPEMD160C60, RIPEMD160S61);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, w3_t, RIPEMD160C60, RIPEMD160S62);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, w7_t, RIPEMD160C60, RIPEMD160S63);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, w0_t, RIPEMD160C60, RIPEMD160S64);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, wd_t, RIPEMD160C60, RIPEMD160S65);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, w5_t, RIPEMD160C60, RIPEMD160S66);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, wa_t, RIPEMD160C60, RIPEMD160S67);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, we_t, RIPEMD160C60, RIPEMD160S68);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, wf_t, RIPEMD160C60, RIPEMD160S69);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w8_t, RIPEMD160C60, RIPEMD160S6A);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, wc_t, RIPEMD160C60, RIPEMD160S6B);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, w4_t, RIPEMD160C60, RIPEMD160S6C);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, w9_t, RIPEMD160C60, RIPEMD160S6D);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, w1_t, RIPEMD160C60, RIPEMD160S6E);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w2_t, RIPEMD160C60, RIPEMD160S6F);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wf_t, RIPEMD160C70, RIPEMD160S70);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w5_t, RIPEMD160C70, RIPEMD160S71);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, w1_t, RIPEMD160C70, RIPEMD160S72);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, w3_t, RIPEMD160C70, RIPEMD160S73);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w7_t, RIPEMD160C70, RIPEMD160S74);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, we_t, RIPEMD160C70, RIPEMD160S75);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w6_t, RIPEMD160C70, RIPEMD160S76);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, w9_t, RIPEMD160C70, RIPEMD160S77);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, wb_t, RIPEMD160C70, RIPEMD160S78);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w8_t, RIPEMD160C70, RIPEMD160S79);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wc_t, RIPEMD160C70, RIPEMD160S7A);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w2_t, RIPEMD160C70, RIPEMD160S7B);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, wa_t, RIPEMD160C70, RIPEMD160S7C);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, w0_t, RIPEMD160C70, RIPEMD160S7D);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w4_t, RIPEMD160C70, RIPEMD160S7E);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wd_t, RIPEMD160C70, RIPEMD160S7F);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, w8_t, RIPEMD160C80, RIPEMD160S80);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, w6_t, RIPEMD160C80, RIPEMD160S81);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w4_t, RIPEMD160C80, RIPEMD160S82);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w1_t, RIPEMD160C80, RIPEMD160S83);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, w3_t, RIPEMD160C80, RIPEMD160S84);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, wb_t, RIPEMD160C80, RIPEMD160S85);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, wf_t, RIPEMD160C80, RIPEMD160S86);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w0_t, RIPEMD160C80, RIPEMD160S87);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w5_t, RIPEMD160C80, RIPEMD160S88);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, wc_t, RIPEMD160C80, RIPEMD160S89);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, w2_t, RIPEMD160C80, RIPEMD160S8A);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, wd_t, RIPEMD160C80, RIPEMD160S8B);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w9_t, RIPEMD160C80, RIPEMD160S8C);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w7_t, RIPEMD160C80, RIPEMD160S8D);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, wa_t, RIPEMD160C80, RIPEMD160S8E);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, we_t, RIPEMD160C80, RIPEMD160S8F);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wc_t, RIPEMD160C90, RIPEMD160S90);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, wf_t, RIPEMD160C90, RIPEMD160S91);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, wa_t, RIPEMD160C90, RIPEMD160S92);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w4_t, RIPEMD160C90, RIPEMD160S93);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w1_t, RIPEMD160C90, RIPEMD160S94);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, w5_t, RIPEMD160C90, RIPEMD160S95);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, w8_t, RIPEMD160C90, RIPEMD160S96);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, w7_t, RIPEMD160C90, RIPEMD160S97);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w6_t, RIPEMD160C90, RIPEMD160S98);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w2_t, RIPEMD160C90, RIPEMD160S99);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wd_t, RIPEMD160C90, RIPEMD160S9A);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, we_t, RIPEMD160C90, RIPEMD160S9B);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, w0_t, RIPEMD160C90, RIPEMD160S9C);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w3_t, RIPEMD160C90, RIPEMD160S9D);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w9_t, RIPEMD160C90, RIPEMD160S9E);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wb_t, RIPEMD160C90, RIPEMD160S9F);
const u32x a = digest[1] + c1 + d2;
const u32x b = digest[2] + d1 + e2;
const u32x c = digest[3] + e1 + a2;
const u32x d = digest[4] + a1 + b2;
const u32x e = digest[0] + b1 + c2;
digest[0] = a;
digest[1] = b;
digest[2] = c;
digest[3] = d;
digest[4] = e;
}
void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
{
digest[0] = ipad[0];
@ -550,7 +33,7 @@ void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x
digest[3] = ipad[3];
digest[4] = ipad[4];
ripemd160_transform_V (w0, w1, w2, w3, digest);
ripemd160_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -575,7 +58,7 @@ void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x
digest[3] = opad[3];
digest[4] = opad[4];
ripemd160_transform_V (w0, w1, w2, w3, digest);
ripemd160_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14641_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -589,108 +72,83 @@ __kernel void m14641_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[4];
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
ripemd160_hmac_ctx_t ripemd160_hmac_ctx;
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
ripemd160_hmac_init (&ripemd160_hmac_ctx, w0, w1, w2, w3);
u32 ipad[5];
u32 opad[5];
tmps[gid].ipad32[0] = ripemd160_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = ripemd160_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = ripemd160_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = ripemd160_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = ripemd160_hmac_ctx.ipad.h[4];
hmac_ripemd160_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].opad32[0] = ripemd160_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = ripemd160_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = ripemd160_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = ripemd160_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = ripemd160_hmac_ctx.opad.h[4];
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
ripemd160_hmac_update_global (&ripemd160_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 5, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j << 24;
w2[1] = 0x80;
ripemd160_hmac_ctx_t ripemd160_hmac_ctx2 = ripemd160_hmac_ctx;
w0[0] = j << 24;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = (64 + salt_len + 4) * 8;
w3[2] = 0;
w3[3] = 0;
u32 dgst[5];
ripemd160_hmac_update_64 (&ripemd160_hmac_ctx2, w0, w1, w2, w3, 4);
hmac_ripemd160_run_S (w0, w1, w2, w3, ipad, opad, dgst);
ripemd160_hmac_final (&ripemd160_hmac_ctx2);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 0] = ripemd160_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = ripemd160_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = ripemd160_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = ripemd160_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = ripemd160_hmac_ctx2.opad.h[4];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
}
}

632
OpenCL/m14642.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_ripemd160.cl"
#include "inc_cipher_serpent.cl"
#include "inc_luks_af.cl"
@ -25,523 +25,6 @@
#define MAX_ENTROPY 7.0
void ripemd160_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
u32 a1 = digest[0];
u32 b1 = digest[1];
u32 c1 = digest[2];
u32 d1 = digest[3];
u32 e1 = digest[4];
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, w0_t, RIPEMD160C00, RIPEMD160S00);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, w1_t, RIPEMD160C00, RIPEMD160S01);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, w2_t, RIPEMD160C00, RIPEMD160S02);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, w3_t, RIPEMD160C00, RIPEMD160S03);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, w4_t, RIPEMD160C00, RIPEMD160S04);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, w5_t, RIPEMD160C00, RIPEMD160S05);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, w6_t, RIPEMD160C00, RIPEMD160S06);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, w7_t, RIPEMD160C00, RIPEMD160S07);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, w8_t, RIPEMD160C00, RIPEMD160S08);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, w9_t, RIPEMD160C00, RIPEMD160S09);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, wa_t, RIPEMD160C00, RIPEMD160S0A);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, wb_t, RIPEMD160C00, RIPEMD160S0B);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, wc_t, RIPEMD160C00, RIPEMD160S0C);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, wd_t, RIPEMD160C00, RIPEMD160S0D);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, we_t, RIPEMD160C00, RIPEMD160S0E);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, wf_t, RIPEMD160C00, RIPEMD160S0F);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w7_t, RIPEMD160C10, RIPEMD160S10);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, w4_t, RIPEMD160C10, RIPEMD160S11);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, wd_t, RIPEMD160C10, RIPEMD160S12);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, w1_t, RIPEMD160C10, RIPEMD160S13);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, wa_t, RIPEMD160C10, RIPEMD160S14);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w6_t, RIPEMD160C10, RIPEMD160S15);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, wf_t, RIPEMD160C10, RIPEMD160S16);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, w3_t, RIPEMD160C10, RIPEMD160S17);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, wc_t, RIPEMD160C10, RIPEMD160S18);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, w0_t, RIPEMD160C10, RIPEMD160S19);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w9_t, RIPEMD160C10, RIPEMD160S1A);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, w5_t, RIPEMD160C10, RIPEMD160S1B);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, w2_t, RIPEMD160C10, RIPEMD160S1C);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, we_t, RIPEMD160C10, RIPEMD160S1D);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, wb_t, RIPEMD160C10, RIPEMD160S1E);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w8_t, RIPEMD160C10, RIPEMD160S1F);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, w3_t, RIPEMD160C20, RIPEMD160S20);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, wa_t, RIPEMD160C20, RIPEMD160S21);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, we_t, RIPEMD160C20, RIPEMD160S22);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, w4_t, RIPEMD160C20, RIPEMD160S23);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w9_t, RIPEMD160C20, RIPEMD160S24);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, wf_t, RIPEMD160C20, RIPEMD160S25);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, w8_t, RIPEMD160C20, RIPEMD160S26);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, w1_t, RIPEMD160C20, RIPEMD160S27);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, w2_t, RIPEMD160C20, RIPEMD160S28);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w7_t, RIPEMD160C20, RIPEMD160S29);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, w0_t, RIPEMD160C20, RIPEMD160S2A);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, w6_t, RIPEMD160C20, RIPEMD160S2B);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, wd_t, RIPEMD160C20, RIPEMD160S2C);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, wb_t, RIPEMD160C20, RIPEMD160S2D);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w5_t, RIPEMD160C20, RIPEMD160S2E);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, wc_t, RIPEMD160C20, RIPEMD160S2F);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w1_t, RIPEMD160C30, RIPEMD160S30);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, w9_t, RIPEMD160C30, RIPEMD160S31);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, wb_t, RIPEMD160C30, RIPEMD160S32);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, wa_t, RIPEMD160C30, RIPEMD160S33);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w0_t, RIPEMD160C30, RIPEMD160S34);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w8_t, RIPEMD160C30, RIPEMD160S35);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, wc_t, RIPEMD160C30, RIPEMD160S36);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, w4_t, RIPEMD160C30, RIPEMD160S37);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, wd_t, RIPEMD160C30, RIPEMD160S38);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w3_t, RIPEMD160C30, RIPEMD160S39);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w7_t, RIPEMD160C30, RIPEMD160S3A);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, wf_t, RIPEMD160C30, RIPEMD160S3B);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, we_t, RIPEMD160C30, RIPEMD160S3C);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, w5_t, RIPEMD160C30, RIPEMD160S3D);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w6_t, RIPEMD160C30, RIPEMD160S3E);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w2_t, RIPEMD160C30, RIPEMD160S3F);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, w4_t, RIPEMD160C40, RIPEMD160S40);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w0_t, RIPEMD160C40, RIPEMD160S41);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, w5_t, RIPEMD160C40, RIPEMD160S42);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, w9_t, RIPEMD160C40, RIPEMD160S43);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, w7_t, RIPEMD160C40, RIPEMD160S44);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, wc_t, RIPEMD160C40, RIPEMD160S45);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w2_t, RIPEMD160C40, RIPEMD160S46);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, wa_t, RIPEMD160C40, RIPEMD160S47);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, we_t, RIPEMD160C40, RIPEMD160S48);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, w1_t, RIPEMD160C40, RIPEMD160S49);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, w3_t, RIPEMD160C40, RIPEMD160S4A);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w8_t, RIPEMD160C40, RIPEMD160S4B);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, wb_t, RIPEMD160C40, RIPEMD160S4C);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, w6_t, RIPEMD160C40, RIPEMD160S4D);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, wf_t, RIPEMD160C40, RIPEMD160S4E);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, wd_t, RIPEMD160C40, RIPEMD160S4F);
u32 a2 = digest[0];
u32 b2 = digest[1];
u32 c2 = digest[2];
u32 d2 = digest[3];
u32 e2 = digest[4];
RIPEMD160_STEP_S_WORKAROUND_BUG (RIPEMD160_J , a2, b2, c2, d2, e2, w5_t, RIPEMD160C50, RIPEMD160S50);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, we_t, RIPEMD160C50, RIPEMD160S51);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w7_t, RIPEMD160C50, RIPEMD160S52);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, w0_t, RIPEMD160C50, RIPEMD160S53);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w9_t, RIPEMD160C50, RIPEMD160S54);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, w2_t, RIPEMD160C50, RIPEMD160S55);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, wb_t, RIPEMD160C50, RIPEMD160S56);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w4_t, RIPEMD160C50, RIPEMD160S57);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, wd_t, RIPEMD160C50, RIPEMD160S58);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w6_t, RIPEMD160C50, RIPEMD160S59);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, wf_t, RIPEMD160C50, RIPEMD160S5A);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, w8_t, RIPEMD160C50, RIPEMD160S5B);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w1_t, RIPEMD160C50, RIPEMD160S5C);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, wa_t, RIPEMD160C50, RIPEMD160S5D);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w3_t, RIPEMD160C50, RIPEMD160S5E);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, wc_t, RIPEMD160C50, RIPEMD160S5F);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w6_t, RIPEMD160C60, RIPEMD160S60);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, wb_t, RIPEMD160C60, RIPEMD160S61);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, w3_t, RIPEMD160C60, RIPEMD160S62);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, w7_t, RIPEMD160C60, RIPEMD160S63);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, w0_t, RIPEMD160C60, RIPEMD160S64);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, wd_t, RIPEMD160C60, RIPEMD160S65);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, w5_t, RIPEMD160C60, RIPEMD160S66);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, wa_t, RIPEMD160C60, RIPEMD160S67);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, we_t, RIPEMD160C60, RIPEMD160S68);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, wf_t, RIPEMD160C60, RIPEMD160S69);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w8_t, RIPEMD160C60, RIPEMD160S6A);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, wc_t, RIPEMD160C60, RIPEMD160S6B);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, w4_t, RIPEMD160C60, RIPEMD160S6C);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, w9_t, RIPEMD160C60, RIPEMD160S6D);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, w1_t, RIPEMD160C60, RIPEMD160S6E);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w2_t, RIPEMD160C60, RIPEMD160S6F);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wf_t, RIPEMD160C70, RIPEMD160S70);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w5_t, RIPEMD160C70, RIPEMD160S71);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, w1_t, RIPEMD160C70, RIPEMD160S72);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, w3_t, RIPEMD160C70, RIPEMD160S73);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w7_t, RIPEMD160C70, RIPEMD160S74);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, we_t, RIPEMD160C70, RIPEMD160S75);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w6_t, RIPEMD160C70, RIPEMD160S76);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, w9_t, RIPEMD160C70, RIPEMD160S77);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, wb_t, RIPEMD160C70, RIPEMD160S78);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w8_t, RIPEMD160C70, RIPEMD160S79);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wc_t, RIPEMD160C70, RIPEMD160S7A);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w2_t, RIPEMD160C70, RIPEMD160S7B);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, wa_t, RIPEMD160C70, RIPEMD160S7C);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, w0_t, RIPEMD160C70, RIPEMD160S7D);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w4_t, RIPEMD160C70, RIPEMD160S7E);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wd_t, RIPEMD160C70, RIPEMD160S7F);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, w8_t, RIPEMD160C80, RIPEMD160S80);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, w6_t, RIPEMD160C80, RIPEMD160S81);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w4_t, RIPEMD160C80, RIPEMD160S82);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w1_t, RIPEMD160C80, RIPEMD160S83);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, w3_t, RIPEMD160C80, RIPEMD160S84);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, wb_t, RIPEMD160C80, RIPEMD160S85);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, wf_t, RIPEMD160C80, RIPEMD160S86);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w0_t, RIPEMD160C80, RIPEMD160S87);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w5_t, RIPEMD160C80, RIPEMD160S88);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, wc_t, RIPEMD160C80, RIPEMD160S89);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, w2_t, RIPEMD160C80, RIPEMD160S8A);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, wd_t, RIPEMD160C80, RIPEMD160S8B);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w9_t, RIPEMD160C80, RIPEMD160S8C);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w7_t, RIPEMD160C80, RIPEMD160S8D);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, wa_t, RIPEMD160C80, RIPEMD160S8E);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, we_t, RIPEMD160C80, RIPEMD160S8F);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wc_t, RIPEMD160C90, RIPEMD160S90);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, wf_t, RIPEMD160C90, RIPEMD160S91);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, wa_t, RIPEMD160C90, RIPEMD160S92);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w4_t, RIPEMD160C90, RIPEMD160S93);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w1_t, RIPEMD160C90, RIPEMD160S94);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, w5_t, RIPEMD160C90, RIPEMD160S95);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, w8_t, RIPEMD160C90, RIPEMD160S96);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, w7_t, RIPEMD160C90, RIPEMD160S97);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w6_t, RIPEMD160C90, RIPEMD160S98);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w2_t, RIPEMD160C90, RIPEMD160S99);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wd_t, RIPEMD160C90, RIPEMD160S9A);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, we_t, RIPEMD160C90, RIPEMD160S9B);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, w0_t, RIPEMD160C90, RIPEMD160S9C);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w3_t, RIPEMD160C90, RIPEMD160S9D);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w9_t, RIPEMD160C90, RIPEMD160S9E);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wb_t, RIPEMD160C90, RIPEMD160S9F);
const u32 a = digest[1] + c1 + d2;
const u32 b = digest[2] + d1 + e2;
const u32 c = digest[3] + e1 + a2;
const u32 d = digest[4] + a1 + b2;
const u32 e = digest[0] + b1 + c2;
digest[0] = a;
digest[1] = b;
digest[2] = c;
digest[3] = d;
digest[4] = e;
}
void hmac_ripemd160_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = RIPEMD160M_A;
ipad[1] = RIPEMD160M_B;
ipad[2] = RIPEMD160M_C;
ipad[3] = RIPEMD160M_D;
ipad[4] = RIPEMD160M_E;
ripemd160_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = RIPEMD160M_A;
opad[1] = RIPEMD160M_B;
opad[2] = RIPEMD160M_C;
opad[3] = RIPEMD160M_D;
opad[4] = RIPEMD160M_E;
ripemd160_transform_S (w0, w1, w2, w3, opad);
}
void hmac_ripemd160_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
ripemd160_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0x80;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = (64 + 20) * 8;
w3[3] = 0;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
ripemd160_transform_S (w0, w1, w2, w3, digest);
}
void ripemd160_transform_V (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
{
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];
u32x a1 = digest[0];
u32x b1 = digest[1];
u32x c1 = digest[2];
u32x d1 = digest[3];
u32x e1 = digest[4];
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, w0_t, RIPEMD160C00, RIPEMD160S00);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, w1_t, RIPEMD160C00, RIPEMD160S01);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, w2_t, RIPEMD160C00, RIPEMD160S02);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, w3_t, RIPEMD160C00, RIPEMD160S03);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, w4_t, RIPEMD160C00, RIPEMD160S04);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, w5_t, RIPEMD160C00, RIPEMD160S05);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, w6_t, RIPEMD160C00, RIPEMD160S06);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, w7_t, RIPEMD160C00, RIPEMD160S07);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, w8_t, RIPEMD160C00, RIPEMD160S08);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, w9_t, RIPEMD160C00, RIPEMD160S09);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, wa_t, RIPEMD160C00, RIPEMD160S0A);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, wb_t, RIPEMD160C00, RIPEMD160S0B);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, wc_t, RIPEMD160C00, RIPEMD160S0C);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, wd_t, RIPEMD160C00, RIPEMD160S0D);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, we_t, RIPEMD160C00, RIPEMD160S0E);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, wf_t, RIPEMD160C00, RIPEMD160S0F);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w7_t, RIPEMD160C10, RIPEMD160S10);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, w4_t, RIPEMD160C10, RIPEMD160S11);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, wd_t, RIPEMD160C10, RIPEMD160S12);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, w1_t, RIPEMD160C10, RIPEMD160S13);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, wa_t, RIPEMD160C10, RIPEMD160S14);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w6_t, RIPEMD160C10, RIPEMD160S15);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, wf_t, RIPEMD160C10, RIPEMD160S16);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, w3_t, RIPEMD160C10, RIPEMD160S17);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, wc_t, RIPEMD160C10, RIPEMD160S18);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, w0_t, RIPEMD160C10, RIPEMD160S19);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w9_t, RIPEMD160C10, RIPEMD160S1A);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, w5_t, RIPEMD160C10, RIPEMD160S1B);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, w2_t, RIPEMD160C10, RIPEMD160S1C);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, we_t, RIPEMD160C10, RIPEMD160S1D);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, wb_t, RIPEMD160C10, RIPEMD160S1E);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w8_t, RIPEMD160C10, RIPEMD160S1F);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, w3_t, RIPEMD160C20, RIPEMD160S20);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, wa_t, RIPEMD160C20, RIPEMD160S21);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, we_t, RIPEMD160C20, RIPEMD160S22);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, w4_t, RIPEMD160C20, RIPEMD160S23);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w9_t, RIPEMD160C20, RIPEMD160S24);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, wf_t, RIPEMD160C20, RIPEMD160S25);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, w8_t, RIPEMD160C20, RIPEMD160S26);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, w1_t, RIPEMD160C20, RIPEMD160S27);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, w2_t, RIPEMD160C20, RIPEMD160S28);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w7_t, RIPEMD160C20, RIPEMD160S29);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, w0_t, RIPEMD160C20, RIPEMD160S2A);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, w6_t, RIPEMD160C20, RIPEMD160S2B);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, wd_t, RIPEMD160C20, RIPEMD160S2C);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, wb_t, RIPEMD160C20, RIPEMD160S2D);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w5_t, RIPEMD160C20, RIPEMD160S2E);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, wc_t, RIPEMD160C20, RIPEMD160S2F);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w1_t, RIPEMD160C30, RIPEMD160S30);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, w9_t, RIPEMD160C30, RIPEMD160S31);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, wb_t, RIPEMD160C30, RIPEMD160S32);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, wa_t, RIPEMD160C30, RIPEMD160S33);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w0_t, RIPEMD160C30, RIPEMD160S34);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w8_t, RIPEMD160C30, RIPEMD160S35);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, wc_t, RIPEMD160C30, RIPEMD160S36);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, w4_t, RIPEMD160C30, RIPEMD160S37);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, wd_t, RIPEMD160C30, RIPEMD160S38);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w3_t, RIPEMD160C30, RIPEMD160S39);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w7_t, RIPEMD160C30, RIPEMD160S3A);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, wf_t, RIPEMD160C30, RIPEMD160S3B);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, we_t, RIPEMD160C30, RIPEMD160S3C);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, w5_t, RIPEMD160C30, RIPEMD160S3D);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w6_t, RIPEMD160C30, RIPEMD160S3E);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w2_t, RIPEMD160C30, RIPEMD160S3F);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, w4_t, RIPEMD160C40, RIPEMD160S40);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w0_t, RIPEMD160C40, RIPEMD160S41);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, w5_t, RIPEMD160C40, RIPEMD160S42);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, w9_t, RIPEMD160C40, RIPEMD160S43);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, w7_t, RIPEMD160C40, RIPEMD160S44);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, wc_t, RIPEMD160C40, RIPEMD160S45);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w2_t, RIPEMD160C40, RIPEMD160S46);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, wa_t, RIPEMD160C40, RIPEMD160S47);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, we_t, RIPEMD160C40, RIPEMD160S48);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, w1_t, RIPEMD160C40, RIPEMD160S49);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, w3_t, RIPEMD160C40, RIPEMD160S4A);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w8_t, RIPEMD160C40, RIPEMD160S4B);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, wb_t, RIPEMD160C40, RIPEMD160S4C);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, w6_t, RIPEMD160C40, RIPEMD160S4D);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, wf_t, RIPEMD160C40, RIPEMD160S4E);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, wd_t, RIPEMD160C40, RIPEMD160S4F);
u32x a2 = digest[0];
u32x b2 = digest[1];
u32x c2 = digest[2];
u32x d2 = digest[3];
u32x e2 = digest[4];
RIPEMD160_STEP_WORKAROUND_BUG (RIPEMD160_J , a2, b2, c2, d2, e2, w5_t, RIPEMD160C50, RIPEMD160S50);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, we_t, RIPEMD160C50, RIPEMD160S51);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w7_t, RIPEMD160C50, RIPEMD160S52);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, w0_t, RIPEMD160C50, RIPEMD160S53);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w9_t, RIPEMD160C50, RIPEMD160S54);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, w2_t, RIPEMD160C50, RIPEMD160S55);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, wb_t, RIPEMD160C50, RIPEMD160S56);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w4_t, RIPEMD160C50, RIPEMD160S57);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, wd_t, RIPEMD160C50, RIPEMD160S58);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w6_t, RIPEMD160C50, RIPEMD160S59);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, wf_t, RIPEMD160C50, RIPEMD160S5A);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, w8_t, RIPEMD160C50, RIPEMD160S5B);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w1_t, RIPEMD160C50, RIPEMD160S5C);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, wa_t, RIPEMD160C50, RIPEMD160S5D);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w3_t, RIPEMD160C50, RIPEMD160S5E);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, wc_t, RIPEMD160C50, RIPEMD160S5F);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w6_t, RIPEMD160C60, RIPEMD160S60);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, wb_t, RIPEMD160C60, RIPEMD160S61);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, w3_t, RIPEMD160C60, RIPEMD160S62);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, w7_t, RIPEMD160C60, RIPEMD160S63);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, w0_t, RIPEMD160C60, RIPEMD160S64);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, wd_t, RIPEMD160C60, RIPEMD160S65);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, w5_t, RIPEMD160C60, RIPEMD160S66);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, wa_t, RIPEMD160C60, RIPEMD160S67);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, we_t, RIPEMD160C60, RIPEMD160S68);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, wf_t, RIPEMD160C60, RIPEMD160S69);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w8_t, RIPEMD160C60, RIPEMD160S6A);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, wc_t, RIPEMD160C60, RIPEMD160S6B);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, w4_t, RIPEMD160C60, RIPEMD160S6C);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, w9_t, RIPEMD160C60, RIPEMD160S6D);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, w1_t, RIPEMD160C60, RIPEMD160S6E);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w2_t, RIPEMD160C60, RIPEMD160S6F);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wf_t, RIPEMD160C70, RIPEMD160S70);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w5_t, RIPEMD160C70, RIPEMD160S71);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, w1_t, RIPEMD160C70, RIPEMD160S72);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, w3_t, RIPEMD160C70, RIPEMD160S73);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w7_t, RIPEMD160C70, RIPEMD160S74);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, we_t, RIPEMD160C70, RIPEMD160S75);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w6_t, RIPEMD160C70, RIPEMD160S76);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, w9_t, RIPEMD160C70, RIPEMD160S77);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, wb_t, RIPEMD160C70, RIPEMD160S78);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w8_t, RIPEMD160C70, RIPEMD160S79);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wc_t, RIPEMD160C70, RIPEMD160S7A);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w2_t, RIPEMD160C70, RIPEMD160S7B);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, wa_t, RIPEMD160C70, RIPEMD160S7C);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, w0_t, RIPEMD160C70, RIPEMD160S7D);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w4_t, RIPEMD160C70, RIPEMD160S7E);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wd_t, RIPEMD160C70, RIPEMD160S7F);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, w8_t, RIPEMD160C80, RIPEMD160S80);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, w6_t, RIPEMD160C80, RIPEMD160S81);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w4_t, RIPEMD160C80, RIPEMD160S82);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w1_t, RIPEMD160C80, RIPEMD160S83);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, w3_t, RIPEMD160C80, RIPEMD160S84);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, wb_t, RIPEMD160C80, RIPEMD160S85);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, wf_t, RIPEMD160C80, RIPEMD160S86);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w0_t, RIPEMD160C80, RIPEMD160S87);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w5_t, RIPEMD160C80, RIPEMD160S88);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, wc_t, RIPEMD160C80, RIPEMD160S89);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, w2_t, RIPEMD160C80, RIPEMD160S8A);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, wd_t, RIPEMD160C80, RIPEMD160S8B);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w9_t, RIPEMD160C80, RIPEMD160S8C);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w7_t, RIPEMD160C80, RIPEMD160S8D);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, wa_t, RIPEMD160C80, RIPEMD160S8E);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, we_t, RIPEMD160C80, RIPEMD160S8F);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wc_t, RIPEMD160C90, RIPEMD160S90);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, wf_t, RIPEMD160C90, RIPEMD160S91);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, wa_t, RIPEMD160C90, RIPEMD160S92);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w4_t, RIPEMD160C90, RIPEMD160S93);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w1_t, RIPEMD160C90, RIPEMD160S94);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, w5_t, RIPEMD160C90, RIPEMD160S95);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, w8_t, RIPEMD160C90, RIPEMD160S96);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, w7_t, RIPEMD160C90, RIPEMD160S97);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w6_t, RIPEMD160C90, RIPEMD160S98);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w2_t, RIPEMD160C90, RIPEMD160S99);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wd_t, RIPEMD160C90, RIPEMD160S9A);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, we_t, RIPEMD160C90, RIPEMD160S9B);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, w0_t, RIPEMD160C90, RIPEMD160S9C);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w3_t, RIPEMD160C90, RIPEMD160S9D);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w9_t, RIPEMD160C90, RIPEMD160S9E);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wb_t, RIPEMD160C90, RIPEMD160S9F);
const u32x a = digest[1] + c1 + d2;
const u32x b = digest[2] + d1 + e2;
const u32x c = digest[3] + e1 + a2;
const u32x d = digest[4] + a1 + b2;
const u32x e = digest[0] + b1 + c2;
digest[0] = a;
digest[1] = b;
digest[2] = c;
digest[3] = d;
digest[4] = e;
}
void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
{
digest[0] = ipad[0];
@ -550,7 +33,7 @@ void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x
digest[3] = ipad[3];
digest[4] = ipad[4];
ripemd160_transform_V (w0, w1, w2, w3, digest);
ripemd160_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -575,7 +58,7 @@ void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x
digest[3] = opad[3];
digest[4] = opad[4];
ripemd160_transform_V (w0, w1, w2, w3, digest);
ripemd160_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14642_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -589,108 +72,83 @@ __kernel void m14642_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[4];
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
ripemd160_hmac_ctx_t ripemd160_hmac_ctx;
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
ripemd160_hmac_init (&ripemd160_hmac_ctx, w0, w1, w2, w3);
u32 ipad[5];
u32 opad[5];
tmps[gid].ipad32[0] = ripemd160_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = ripemd160_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = ripemd160_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = ripemd160_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = ripemd160_hmac_ctx.ipad.h[4];
hmac_ripemd160_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].opad32[0] = ripemd160_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = ripemd160_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = ripemd160_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = ripemd160_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = ripemd160_hmac_ctx.opad.h[4];
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
ripemd160_hmac_update_global (&ripemd160_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 5, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j << 24;
w2[1] = 0x80;
ripemd160_hmac_ctx_t ripemd160_hmac_ctx2 = ripemd160_hmac_ctx;
w0[0] = j << 24;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = (64 + salt_len + 4) * 8;
w3[2] = 0;
w3[3] = 0;
u32 dgst[5];
ripemd160_hmac_update_64 (&ripemd160_hmac_ctx2, w0, w1, w2, w3, 4);
hmac_ripemd160_run_S (w0, w1, w2, w3, ipad, opad, dgst);
ripemd160_hmac_final (&ripemd160_hmac_ctx2);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 0] = ripemd160_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = ripemd160_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = ripemd160_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = ripemd160_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = ripemd160_hmac_ctx2.opad.h[4];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
}
}

632
OpenCL/m14643.cl
Unescape View File

@ -11,7 +11,7 @@
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_ripemd160.cl"
#include "inc_cipher_twofish.cl"
#include "inc_luks_af.cl"
@ -25,523 +25,6 @@
#define MAX_ENTROPY 7.0
void ripemd160_transform_S (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
{
u32 w0_t = w0[0];
u32 w1_t = w0[1];
u32 w2_t = w0[2];
u32 w3_t = w0[3];
u32 w4_t = w1[0];
u32 w5_t = w1[1];
u32 w6_t = w1[2];
u32 w7_t = w1[3];
u32 w8_t = w2[0];
u32 w9_t = w2[1];
u32 wa_t = w2[2];
u32 wb_t = w2[3];
u32 wc_t = w3[0];
u32 wd_t = w3[1];
u32 we_t = w3[2];
u32 wf_t = w3[3];
u32 a1 = digest[0];
u32 b1 = digest[1];
u32 c1 = digest[2];
u32 d1 = digest[3];
u32 e1 = digest[4];
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, w0_t, RIPEMD160C00, RIPEMD160S00);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, w1_t, RIPEMD160C00, RIPEMD160S01);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, w2_t, RIPEMD160C00, RIPEMD160S02);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, w3_t, RIPEMD160C00, RIPEMD160S03);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, w4_t, RIPEMD160C00, RIPEMD160S04);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, w5_t, RIPEMD160C00, RIPEMD160S05);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, w6_t, RIPEMD160C00, RIPEMD160S06);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, w7_t, RIPEMD160C00, RIPEMD160S07);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, w8_t, RIPEMD160C00, RIPEMD160S08);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, w9_t, RIPEMD160C00, RIPEMD160S09);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, wa_t, RIPEMD160C00, RIPEMD160S0A);
RIPEMD160_STEP_S (RIPEMD160_F , e1, a1, b1, c1, d1, wb_t, RIPEMD160C00, RIPEMD160S0B);
RIPEMD160_STEP_S (RIPEMD160_F , d1, e1, a1, b1, c1, wc_t, RIPEMD160C00, RIPEMD160S0C);
RIPEMD160_STEP_S (RIPEMD160_F , c1, d1, e1, a1, b1, wd_t, RIPEMD160C00, RIPEMD160S0D);
RIPEMD160_STEP_S (RIPEMD160_F , b1, c1, d1, e1, a1, we_t, RIPEMD160C00, RIPEMD160S0E);
RIPEMD160_STEP_S (RIPEMD160_F , a1, b1, c1, d1, e1, wf_t, RIPEMD160C00, RIPEMD160S0F);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w7_t, RIPEMD160C10, RIPEMD160S10);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, w4_t, RIPEMD160C10, RIPEMD160S11);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, wd_t, RIPEMD160C10, RIPEMD160S12);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, w1_t, RIPEMD160C10, RIPEMD160S13);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, wa_t, RIPEMD160C10, RIPEMD160S14);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w6_t, RIPEMD160C10, RIPEMD160S15);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, wf_t, RIPEMD160C10, RIPEMD160S16);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, w3_t, RIPEMD160C10, RIPEMD160S17);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, wc_t, RIPEMD160C10, RIPEMD160S18);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, w0_t, RIPEMD160C10, RIPEMD160S19);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w9_t, RIPEMD160C10, RIPEMD160S1A);
RIPEMD160_STEP_S (RIPEMD160_Go, d1, e1, a1, b1, c1, w5_t, RIPEMD160C10, RIPEMD160S1B);
RIPEMD160_STEP_S (RIPEMD160_Go, c1, d1, e1, a1, b1, w2_t, RIPEMD160C10, RIPEMD160S1C);
RIPEMD160_STEP_S (RIPEMD160_Go, b1, c1, d1, e1, a1, we_t, RIPEMD160C10, RIPEMD160S1D);
RIPEMD160_STEP_S (RIPEMD160_Go, a1, b1, c1, d1, e1, wb_t, RIPEMD160C10, RIPEMD160S1E);
RIPEMD160_STEP_S (RIPEMD160_Go, e1, a1, b1, c1, d1, w8_t, RIPEMD160C10, RIPEMD160S1F);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, w3_t, RIPEMD160C20, RIPEMD160S20);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, wa_t, RIPEMD160C20, RIPEMD160S21);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, we_t, RIPEMD160C20, RIPEMD160S22);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, w4_t, RIPEMD160C20, RIPEMD160S23);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w9_t, RIPEMD160C20, RIPEMD160S24);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, wf_t, RIPEMD160C20, RIPEMD160S25);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, w8_t, RIPEMD160C20, RIPEMD160S26);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, w1_t, RIPEMD160C20, RIPEMD160S27);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, w2_t, RIPEMD160C20, RIPEMD160S28);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w7_t, RIPEMD160C20, RIPEMD160S29);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, w0_t, RIPEMD160C20, RIPEMD160S2A);
RIPEMD160_STEP_S (RIPEMD160_H , c1, d1, e1, a1, b1, w6_t, RIPEMD160C20, RIPEMD160S2B);
RIPEMD160_STEP_S (RIPEMD160_H , b1, c1, d1, e1, a1, wd_t, RIPEMD160C20, RIPEMD160S2C);
RIPEMD160_STEP_S (RIPEMD160_H , a1, b1, c1, d1, e1, wb_t, RIPEMD160C20, RIPEMD160S2D);
RIPEMD160_STEP_S (RIPEMD160_H , e1, a1, b1, c1, d1, w5_t, RIPEMD160C20, RIPEMD160S2E);
RIPEMD160_STEP_S (RIPEMD160_H , d1, e1, a1, b1, c1, wc_t, RIPEMD160C20, RIPEMD160S2F);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w1_t, RIPEMD160C30, RIPEMD160S30);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, w9_t, RIPEMD160C30, RIPEMD160S31);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, wb_t, RIPEMD160C30, RIPEMD160S32);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, wa_t, RIPEMD160C30, RIPEMD160S33);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w0_t, RIPEMD160C30, RIPEMD160S34);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w8_t, RIPEMD160C30, RIPEMD160S35);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, wc_t, RIPEMD160C30, RIPEMD160S36);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, w4_t, RIPEMD160C30, RIPEMD160S37);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, wd_t, RIPEMD160C30, RIPEMD160S38);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w3_t, RIPEMD160C30, RIPEMD160S39);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w7_t, RIPEMD160C30, RIPEMD160S3A);
RIPEMD160_STEP_S (RIPEMD160_Io, b1, c1, d1, e1, a1, wf_t, RIPEMD160C30, RIPEMD160S3B);
RIPEMD160_STEP_S (RIPEMD160_Io, a1, b1, c1, d1, e1, we_t, RIPEMD160C30, RIPEMD160S3C);
RIPEMD160_STEP_S (RIPEMD160_Io, e1, a1, b1, c1, d1, w5_t, RIPEMD160C30, RIPEMD160S3D);
RIPEMD160_STEP_S (RIPEMD160_Io, d1, e1, a1, b1, c1, w6_t, RIPEMD160C30, RIPEMD160S3E);
RIPEMD160_STEP_S (RIPEMD160_Io, c1, d1, e1, a1, b1, w2_t, RIPEMD160C30, RIPEMD160S3F);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, w4_t, RIPEMD160C40, RIPEMD160S40);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w0_t, RIPEMD160C40, RIPEMD160S41);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, w5_t, RIPEMD160C40, RIPEMD160S42);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, w9_t, RIPEMD160C40, RIPEMD160S43);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, w7_t, RIPEMD160C40, RIPEMD160S44);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, wc_t, RIPEMD160C40, RIPEMD160S45);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w2_t, RIPEMD160C40, RIPEMD160S46);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, wa_t, RIPEMD160C40, RIPEMD160S47);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, we_t, RIPEMD160C40, RIPEMD160S48);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, w1_t, RIPEMD160C40, RIPEMD160S49);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, w3_t, RIPEMD160C40, RIPEMD160S4A);
RIPEMD160_STEP_S (RIPEMD160_J , a1, b1, c1, d1, e1, w8_t, RIPEMD160C40, RIPEMD160S4B);
RIPEMD160_STEP_S (RIPEMD160_J , e1, a1, b1, c1, d1, wb_t, RIPEMD160C40, RIPEMD160S4C);
RIPEMD160_STEP_S (RIPEMD160_J , d1, e1, a1, b1, c1, w6_t, RIPEMD160C40, RIPEMD160S4D);
RIPEMD160_STEP_S (RIPEMD160_J , c1, d1, e1, a1, b1, wf_t, RIPEMD160C40, RIPEMD160S4E);
RIPEMD160_STEP_S (RIPEMD160_J , b1, c1, d1, e1, a1, wd_t, RIPEMD160C40, RIPEMD160S4F);
u32 a2 = digest[0];
u32 b2 = digest[1];
u32 c2 = digest[2];
u32 d2 = digest[3];
u32 e2 = digest[4];
RIPEMD160_STEP_S_WORKAROUND_BUG (RIPEMD160_J , a2, b2, c2, d2, e2, w5_t, RIPEMD160C50, RIPEMD160S50);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, we_t, RIPEMD160C50, RIPEMD160S51);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w7_t, RIPEMD160C50, RIPEMD160S52);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, w0_t, RIPEMD160C50, RIPEMD160S53);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w9_t, RIPEMD160C50, RIPEMD160S54);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, w2_t, RIPEMD160C50, RIPEMD160S55);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, wb_t, RIPEMD160C50, RIPEMD160S56);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w4_t, RIPEMD160C50, RIPEMD160S57);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, wd_t, RIPEMD160C50, RIPEMD160S58);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w6_t, RIPEMD160C50, RIPEMD160S59);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, wf_t, RIPEMD160C50, RIPEMD160S5A);
RIPEMD160_STEP_S (RIPEMD160_J , e2, a2, b2, c2, d2, w8_t, RIPEMD160C50, RIPEMD160S5B);
RIPEMD160_STEP_S (RIPEMD160_J , d2, e2, a2, b2, c2, w1_t, RIPEMD160C50, RIPEMD160S5C);
RIPEMD160_STEP_S (RIPEMD160_J , c2, d2, e2, a2, b2, wa_t, RIPEMD160C50, RIPEMD160S5D);
RIPEMD160_STEP_S (RIPEMD160_J , b2, c2, d2, e2, a2, w3_t, RIPEMD160C50, RIPEMD160S5E);
RIPEMD160_STEP_S (RIPEMD160_J , a2, b2, c2, d2, e2, wc_t, RIPEMD160C50, RIPEMD160S5F);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w6_t, RIPEMD160C60, RIPEMD160S60);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, wb_t, RIPEMD160C60, RIPEMD160S61);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, w3_t, RIPEMD160C60, RIPEMD160S62);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, w7_t, RIPEMD160C60, RIPEMD160S63);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, w0_t, RIPEMD160C60, RIPEMD160S64);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, wd_t, RIPEMD160C60, RIPEMD160S65);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, w5_t, RIPEMD160C60, RIPEMD160S66);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, wa_t, RIPEMD160C60, RIPEMD160S67);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, we_t, RIPEMD160C60, RIPEMD160S68);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, wf_t, RIPEMD160C60, RIPEMD160S69);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w8_t, RIPEMD160C60, RIPEMD160S6A);
RIPEMD160_STEP_S (RIPEMD160_Io, d2, e2, a2, b2, c2, wc_t, RIPEMD160C60, RIPEMD160S6B);
RIPEMD160_STEP_S (RIPEMD160_Io, c2, d2, e2, a2, b2, w4_t, RIPEMD160C60, RIPEMD160S6C);
RIPEMD160_STEP_S (RIPEMD160_Io, b2, c2, d2, e2, a2, w9_t, RIPEMD160C60, RIPEMD160S6D);
RIPEMD160_STEP_S (RIPEMD160_Io, a2, b2, c2, d2, e2, w1_t, RIPEMD160C60, RIPEMD160S6E);
RIPEMD160_STEP_S (RIPEMD160_Io, e2, a2, b2, c2, d2, w2_t, RIPEMD160C60, RIPEMD160S6F);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wf_t, RIPEMD160C70, RIPEMD160S70);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w5_t, RIPEMD160C70, RIPEMD160S71);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, w1_t, RIPEMD160C70, RIPEMD160S72);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, w3_t, RIPEMD160C70, RIPEMD160S73);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w7_t, RIPEMD160C70, RIPEMD160S74);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, we_t, RIPEMD160C70, RIPEMD160S75);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w6_t, RIPEMD160C70, RIPEMD160S76);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, w9_t, RIPEMD160C70, RIPEMD160S77);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, wb_t, RIPEMD160C70, RIPEMD160S78);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w8_t, RIPEMD160C70, RIPEMD160S79);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wc_t, RIPEMD160C70, RIPEMD160S7A);
RIPEMD160_STEP_S (RIPEMD160_H , c2, d2, e2, a2, b2, w2_t, RIPEMD160C70, RIPEMD160S7B);
RIPEMD160_STEP_S (RIPEMD160_H , b2, c2, d2, e2, a2, wa_t, RIPEMD160C70, RIPEMD160S7C);
RIPEMD160_STEP_S (RIPEMD160_H , a2, b2, c2, d2, e2, w0_t, RIPEMD160C70, RIPEMD160S7D);
RIPEMD160_STEP_S (RIPEMD160_H , e2, a2, b2, c2, d2, w4_t, RIPEMD160C70, RIPEMD160S7E);
RIPEMD160_STEP_S (RIPEMD160_H , d2, e2, a2, b2, c2, wd_t, RIPEMD160C70, RIPEMD160S7F);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, w8_t, RIPEMD160C80, RIPEMD160S80);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, w6_t, RIPEMD160C80, RIPEMD160S81);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w4_t, RIPEMD160C80, RIPEMD160S82);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w1_t, RIPEMD160C80, RIPEMD160S83);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, w3_t, RIPEMD160C80, RIPEMD160S84);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, wb_t, RIPEMD160C80, RIPEMD160S85);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, wf_t, RIPEMD160C80, RIPEMD160S86);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w0_t, RIPEMD160C80, RIPEMD160S87);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w5_t, RIPEMD160C80, RIPEMD160S88);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, wc_t, RIPEMD160C80, RIPEMD160S89);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, w2_t, RIPEMD160C80, RIPEMD160S8A);
RIPEMD160_STEP_S (RIPEMD160_Go, b2, c2, d2, e2, a2, wd_t, RIPEMD160C80, RIPEMD160S8B);
RIPEMD160_STEP_S (RIPEMD160_Go, a2, b2, c2, d2, e2, w9_t, RIPEMD160C80, RIPEMD160S8C);
RIPEMD160_STEP_S (RIPEMD160_Go, e2, a2, b2, c2, d2, w7_t, RIPEMD160C80, RIPEMD160S8D);
RIPEMD160_STEP_S (RIPEMD160_Go, d2, e2, a2, b2, c2, wa_t, RIPEMD160C80, RIPEMD160S8E);
RIPEMD160_STEP_S (RIPEMD160_Go, c2, d2, e2, a2, b2, we_t, RIPEMD160C80, RIPEMD160S8F);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wc_t, RIPEMD160C90, RIPEMD160S90);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, wf_t, RIPEMD160C90, RIPEMD160S91);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, wa_t, RIPEMD160C90, RIPEMD160S92);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w4_t, RIPEMD160C90, RIPEMD160S93);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w1_t, RIPEMD160C90, RIPEMD160S94);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, w5_t, RIPEMD160C90, RIPEMD160S95);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, w8_t, RIPEMD160C90, RIPEMD160S96);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, w7_t, RIPEMD160C90, RIPEMD160S97);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w6_t, RIPEMD160C90, RIPEMD160S98);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w2_t, RIPEMD160C90, RIPEMD160S99);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wd_t, RIPEMD160C90, RIPEMD160S9A);
RIPEMD160_STEP_S (RIPEMD160_F , a2, b2, c2, d2, e2, we_t, RIPEMD160C90, RIPEMD160S9B);
RIPEMD160_STEP_S (RIPEMD160_F , e2, a2, b2, c2, d2, w0_t, RIPEMD160C90, RIPEMD160S9C);
RIPEMD160_STEP_S (RIPEMD160_F , d2, e2, a2, b2, c2, w3_t, RIPEMD160C90, RIPEMD160S9D);
RIPEMD160_STEP_S (RIPEMD160_F , c2, d2, e2, a2, b2, w9_t, RIPEMD160C90, RIPEMD160S9E);
RIPEMD160_STEP_S (RIPEMD160_F , b2, c2, d2, e2, a2, wb_t, RIPEMD160C90, RIPEMD160S9F);
const u32 a = digest[1] + c1 + d2;
const u32 b = digest[2] + d1 + e2;
const u32 c = digest[3] + e1 + a2;
const u32 d = digest[4] + a1 + b2;
const u32 e = digest[0] + b1 + c2;
digest[0] = a;
digest[1] = b;
digest[2] = c;
digest[3] = d;
digest[4] = e;
}
void hmac_ripemd160_pad_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
{
w0[0] = w0[0] ^ 0x36363636;
w0[1] = w0[1] ^ 0x36363636;
w0[2] = w0[2] ^ 0x36363636;
w0[3] = w0[3] ^ 0x36363636;
w1[0] = w1[0] ^ 0x36363636;
w1[1] = w1[1] ^ 0x36363636;
w1[2] = w1[2] ^ 0x36363636;
w1[3] = w1[3] ^ 0x36363636;
w2[0] = w2[0] ^ 0x36363636;
w2[1] = w2[1] ^ 0x36363636;
w2[2] = w2[2] ^ 0x36363636;
w2[3] = w2[3] ^ 0x36363636;
w3[0] = w3[0] ^ 0x36363636;
w3[1] = w3[1] ^ 0x36363636;
w3[2] = w3[2] ^ 0x36363636;
w3[3] = w3[3] ^ 0x36363636;
ipad[0] = RIPEMD160M_A;
ipad[1] = RIPEMD160M_B;
ipad[2] = RIPEMD160M_C;
ipad[3] = RIPEMD160M_D;
ipad[4] = RIPEMD160M_E;
ripemd160_transform_S (w0, w1, w2, w3, ipad);
w0[0] = w0[0] ^ 0x6a6a6a6a;
w0[1] = w0[1] ^ 0x6a6a6a6a;
w0[2] = w0[2] ^ 0x6a6a6a6a;
w0[3] = w0[3] ^ 0x6a6a6a6a;
w1[0] = w1[0] ^ 0x6a6a6a6a;
w1[1] = w1[1] ^ 0x6a6a6a6a;
w1[2] = w1[2] ^ 0x6a6a6a6a;
w1[3] = w1[3] ^ 0x6a6a6a6a;
w2[0] = w2[0] ^ 0x6a6a6a6a;
w2[1] = w2[1] ^ 0x6a6a6a6a;
w2[2] = w2[2] ^ 0x6a6a6a6a;
w2[3] = w2[3] ^ 0x6a6a6a6a;
w3[0] = w3[0] ^ 0x6a6a6a6a;
w3[1] = w3[1] ^ 0x6a6a6a6a;
w3[2] = w3[2] ^ 0x6a6a6a6a;
w3[3] = w3[3] ^ 0x6a6a6a6a;
opad[0] = RIPEMD160M_A;
opad[1] = RIPEMD160M_B;
opad[2] = RIPEMD160M_C;
opad[3] = RIPEMD160M_D;
opad[4] = RIPEMD160M_E;
ripemd160_transform_S (w0, w1, w2, w3, opad);
}
void hmac_ripemd160_run_S (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
{
digest[0] = ipad[0];
digest[1] = ipad[1];
digest[2] = ipad[2];
digest[3] = ipad[3];
digest[4] = ipad[4];
ripemd160_transform_S (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
w0[2] = digest[2];
w0[3] = digest[3];
w1[0] = digest[4];
w1[1] = 0x80;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = (64 + 20) * 8;
w3[3] = 0;
digest[0] = opad[0];
digest[1] = opad[1];
digest[2] = opad[2];
digest[3] = opad[3];
digest[4] = opad[4];
ripemd160_transform_S (w0, w1, w2, w3, digest);
}
void ripemd160_transform_V (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
{
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];
u32x a1 = digest[0];
u32x b1 = digest[1];
u32x c1 = digest[2];
u32x d1 = digest[3];
u32x e1 = digest[4];
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, w0_t, RIPEMD160C00, RIPEMD160S00);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, w1_t, RIPEMD160C00, RIPEMD160S01);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, w2_t, RIPEMD160C00, RIPEMD160S02);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, w3_t, RIPEMD160C00, RIPEMD160S03);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, w4_t, RIPEMD160C00, RIPEMD160S04);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, w5_t, RIPEMD160C00, RIPEMD160S05);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, w6_t, RIPEMD160C00, RIPEMD160S06);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, w7_t, RIPEMD160C00, RIPEMD160S07);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, w8_t, RIPEMD160C00, RIPEMD160S08);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, w9_t, RIPEMD160C00, RIPEMD160S09);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, wa_t, RIPEMD160C00, RIPEMD160S0A);
RIPEMD160_STEP (RIPEMD160_F , e1, a1, b1, c1, d1, wb_t, RIPEMD160C00, RIPEMD160S0B);
RIPEMD160_STEP (RIPEMD160_F , d1, e1, a1, b1, c1, wc_t, RIPEMD160C00, RIPEMD160S0C);
RIPEMD160_STEP (RIPEMD160_F , c1, d1, e1, a1, b1, wd_t, RIPEMD160C00, RIPEMD160S0D);
RIPEMD160_STEP (RIPEMD160_F , b1, c1, d1, e1, a1, we_t, RIPEMD160C00, RIPEMD160S0E);
RIPEMD160_STEP (RIPEMD160_F , a1, b1, c1, d1, e1, wf_t, RIPEMD160C00, RIPEMD160S0F);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w7_t, RIPEMD160C10, RIPEMD160S10);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, w4_t, RIPEMD160C10, RIPEMD160S11);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, wd_t, RIPEMD160C10, RIPEMD160S12);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, w1_t, RIPEMD160C10, RIPEMD160S13);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, wa_t, RIPEMD160C10, RIPEMD160S14);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w6_t, RIPEMD160C10, RIPEMD160S15);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, wf_t, RIPEMD160C10, RIPEMD160S16);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, w3_t, RIPEMD160C10, RIPEMD160S17);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, wc_t, RIPEMD160C10, RIPEMD160S18);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, w0_t, RIPEMD160C10, RIPEMD160S19);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w9_t, RIPEMD160C10, RIPEMD160S1A);
RIPEMD160_STEP (RIPEMD160_Go, d1, e1, a1, b1, c1, w5_t, RIPEMD160C10, RIPEMD160S1B);
RIPEMD160_STEP (RIPEMD160_Go, c1, d1, e1, a1, b1, w2_t, RIPEMD160C10, RIPEMD160S1C);
RIPEMD160_STEP (RIPEMD160_Go, b1, c1, d1, e1, a1, we_t, RIPEMD160C10, RIPEMD160S1D);
RIPEMD160_STEP (RIPEMD160_Go, a1, b1, c1, d1, e1, wb_t, RIPEMD160C10, RIPEMD160S1E);
RIPEMD160_STEP (RIPEMD160_Go, e1, a1, b1, c1, d1, w8_t, RIPEMD160C10, RIPEMD160S1F);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, w3_t, RIPEMD160C20, RIPEMD160S20);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, wa_t, RIPEMD160C20, RIPEMD160S21);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, we_t, RIPEMD160C20, RIPEMD160S22);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, w4_t, RIPEMD160C20, RIPEMD160S23);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w9_t, RIPEMD160C20, RIPEMD160S24);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, wf_t, RIPEMD160C20, RIPEMD160S25);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, w8_t, RIPEMD160C20, RIPEMD160S26);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, w1_t, RIPEMD160C20, RIPEMD160S27);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, w2_t, RIPEMD160C20, RIPEMD160S28);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w7_t, RIPEMD160C20, RIPEMD160S29);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, w0_t, RIPEMD160C20, RIPEMD160S2A);
RIPEMD160_STEP (RIPEMD160_H , c1, d1, e1, a1, b1, w6_t, RIPEMD160C20, RIPEMD160S2B);
RIPEMD160_STEP (RIPEMD160_H , b1, c1, d1, e1, a1, wd_t, RIPEMD160C20, RIPEMD160S2C);
RIPEMD160_STEP (RIPEMD160_H , a1, b1, c1, d1, e1, wb_t, RIPEMD160C20, RIPEMD160S2D);
RIPEMD160_STEP (RIPEMD160_H , e1, a1, b1, c1, d1, w5_t, RIPEMD160C20, RIPEMD160S2E);
RIPEMD160_STEP (RIPEMD160_H , d1, e1, a1, b1, c1, wc_t, RIPEMD160C20, RIPEMD160S2F);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w1_t, RIPEMD160C30, RIPEMD160S30);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, w9_t, RIPEMD160C30, RIPEMD160S31);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, wb_t, RIPEMD160C30, RIPEMD160S32);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, wa_t, RIPEMD160C30, RIPEMD160S33);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w0_t, RIPEMD160C30, RIPEMD160S34);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w8_t, RIPEMD160C30, RIPEMD160S35);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, wc_t, RIPEMD160C30, RIPEMD160S36);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, w4_t, RIPEMD160C30, RIPEMD160S37);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, wd_t, RIPEMD160C30, RIPEMD160S38);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w3_t, RIPEMD160C30, RIPEMD160S39);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w7_t, RIPEMD160C30, RIPEMD160S3A);
RIPEMD160_STEP (RIPEMD160_Io, b1, c1, d1, e1, a1, wf_t, RIPEMD160C30, RIPEMD160S3B);
RIPEMD160_STEP (RIPEMD160_Io, a1, b1, c1, d1, e1, we_t, RIPEMD160C30, RIPEMD160S3C);
RIPEMD160_STEP (RIPEMD160_Io, e1, a1, b1, c1, d1, w5_t, RIPEMD160C30, RIPEMD160S3D);
RIPEMD160_STEP (RIPEMD160_Io, d1, e1, a1, b1, c1, w6_t, RIPEMD160C30, RIPEMD160S3E);
RIPEMD160_STEP (RIPEMD160_Io, c1, d1, e1, a1, b1, w2_t, RIPEMD160C30, RIPEMD160S3F);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, w4_t, RIPEMD160C40, RIPEMD160S40);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w0_t, RIPEMD160C40, RIPEMD160S41);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, w5_t, RIPEMD160C40, RIPEMD160S42);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, w9_t, RIPEMD160C40, RIPEMD160S43);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, w7_t, RIPEMD160C40, RIPEMD160S44);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, wc_t, RIPEMD160C40, RIPEMD160S45);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w2_t, RIPEMD160C40, RIPEMD160S46);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, wa_t, RIPEMD160C40, RIPEMD160S47);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, we_t, RIPEMD160C40, RIPEMD160S48);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, w1_t, RIPEMD160C40, RIPEMD160S49);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, w3_t, RIPEMD160C40, RIPEMD160S4A);
RIPEMD160_STEP (RIPEMD160_J , a1, b1, c1, d1, e1, w8_t, RIPEMD160C40, RIPEMD160S4B);
RIPEMD160_STEP (RIPEMD160_J , e1, a1, b1, c1, d1, wb_t, RIPEMD160C40, RIPEMD160S4C);
RIPEMD160_STEP (RIPEMD160_J , d1, e1, a1, b1, c1, w6_t, RIPEMD160C40, RIPEMD160S4D);
RIPEMD160_STEP (RIPEMD160_J , c1, d1, e1, a1, b1, wf_t, RIPEMD160C40, RIPEMD160S4E);
RIPEMD160_STEP (RIPEMD160_J , b1, c1, d1, e1, a1, wd_t, RIPEMD160C40, RIPEMD160S4F);
u32x a2 = digest[0];
u32x b2 = digest[1];
u32x c2 = digest[2];
u32x d2 = digest[3];
u32x e2 = digest[4];
RIPEMD160_STEP_WORKAROUND_BUG (RIPEMD160_J , a2, b2, c2, d2, e2, w5_t, RIPEMD160C50, RIPEMD160S50);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, we_t, RIPEMD160C50, RIPEMD160S51);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w7_t, RIPEMD160C50, RIPEMD160S52);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, w0_t, RIPEMD160C50, RIPEMD160S53);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w9_t, RIPEMD160C50, RIPEMD160S54);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, w2_t, RIPEMD160C50, RIPEMD160S55);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, wb_t, RIPEMD160C50, RIPEMD160S56);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w4_t, RIPEMD160C50, RIPEMD160S57);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, wd_t, RIPEMD160C50, RIPEMD160S58);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w6_t, RIPEMD160C50, RIPEMD160S59);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, wf_t, RIPEMD160C50, RIPEMD160S5A);
RIPEMD160_STEP (RIPEMD160_J , e2, a2, b2, c2, d2, w8_t, RIPEMD160C50, RIPEMD160S5B);
RIPEMD160_STEP (RIPEMD160_J , d2, e2, a2, b2, c2, w1_t, RIPEMD160C50, RIPEMD160S5C);
RIPEMD160_STEP (RIPEMD160_J , c2, d2, e2, a2, b2, wa_t, RIPEMD160C50, RIPEMD160S5D);
RIPEMD160_STEP (RIPEMD160_J , b2, c2, d2, e2, a2, w3_t, RIPEMD160C50, RIPEMD160S5E);
RIPEMD160_STEP (RIPEMD160_J , a2, b2, c2, d2, e2, wc_t, RIPEMD160C50, RIPEMD160S5F);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w6_t, RIPEMD160C60, RIPEMD160S60);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, wb_t, RIPEMD160C60, RIPEMD160S61);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, w3_t, RIPEMD160C60, RIPEMD160S62);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, w7_t, RIPEMD160C60, RIPEMD160S63);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, w0_t, RIPEMD160C60, RIPEMD160S64);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, wd_t, RIPEMD160C60, RIPEMD160S65);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, w5_t, RIPEMD160C60, RIPEMD160S66);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, wa_t, RIPEMD160C60, RIPEMD160S67);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, we_t, RIPEMD160C60, RIPEMD160S68);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, wf_t, RIPEMD160C60, RIPEMD160S69);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w8_t, RIPEMD160C60, RIPEMD160S6A);
RIPEMD160_STEP (RIPEMD160_Io, d2, e2, a2, b2, c2, wc_t, RIPEMD160C60, RIPEMD160S6B);
RIPEMD160_STEP (RIPEMD160_Io, c2, d2, e2, a2, b2, w4_t, RIPEMD160C60, RIPEMD160S6C);
RIPEMD160_STEP (RIPEMD160_Io, b2, c2, d2, e2, a2, w9_t, RIPEMD160C60, RIPEMD160S6D);
RIPEMD160_STEP (RIPEMD160_Io, a2, b2, c2, d2, e2, w1_t, RIPEMD160C60, RIPEMD160S6E);
RIPEMD160_STEP (RIPEMD160_Io, e2, a2, b2, c2, d2, w2_t, RIPEMD160C60, RIPEMD160S6F);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wf_t, RIPEMD160C70, RIPEMD160S70);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w5_t, RIPEMD160C70, RIPEMD160S71);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, w1_t, RIPEMD160C70, RIPEMD160S72);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, w3_t, RIPEMD160C70, RIPEMD160S73);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w7_t, RIPEMD160C70, RIPEMD160S74);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, we_t, RIPEMD160C70, RIPEMD160S75);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w6_t, RIPEMD160C70, RIPEMD160S76);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, w9_t, RIPEMD160C70, RIPEMD160S77);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, wb_t, RIPEMD160C70, RIPEMD160S78);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w8_t, RIPEMD160C70, RIPEMD160S79);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wc_t, RIPEMD160C70, RIPEMD160S7A);
RIPEMD160_STEP (RIPEMD160_H , c2, d2, e2, a2, b2, w2_t, RIPEMD160C70, RIPEMD160S7B);
RIPEMD160_STEP (RIPEMD160_H , b2, c2, d2, e2, a2, wa_t, RIPEMD160C70, RIPEMD160S7C);
RIPEMD160_STEP (RIPEMD160_H , a2, b2, c2, d2, e2, w0_t, RIPEMD160C70, RIPEMD160S7D);
RIPEMD160_STEP (RIPEMD160_H , e2, a2, b2, c2, d2, w4_t, RIPEMD160C70, RIPEMD160S7E);
RIPEMD160_STEP (RIPEMD160_H , d2, e2, a2, b2, c2, wd_t, RIPEMD160C70, RIPEMD160S7F);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, w8_t, RIPEMD160C80, RIPEMD160S80);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, w6_t, RIPEMD160C80, RIPEMD160S81);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w4_t, RIPEMD160C80, RIPEMD160S82);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w1_t, RIPEMD160C80, RIPEMD160S83);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, w3_t, RIPEMD160C80, RIPEMD160S84);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, wb_t, RIPEMD160C80, RIPEMD160S85);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, wf_t, RIPEMD160C80, RIPEMD160S86);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w0_t, RIPEMD160C80, RIPEMD160S87);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w5_t, RIPEMD160C80, RIPEMD160S88);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, wc_t, RIPEMD160C80, RIPEMD160S89);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, w2_t, RIPEMD160C80, RIPEMD160S8A);
RIPEMD160_STEP (RIPEMD160_Go, b2, c2, d2, e2, a2, wd_t, RIPEMD160C80, RIPEMD160S8B);
RIPEMD160_STEP (RIPEMD160_Go, a2, b2, c2, d2, e2, w9_t, RIPEMD160C80, RIPEMD160S8C);
RIPEMD160_STEP (RIPEMD160_Go, e2, a2, b2, c2, d2, w7_t, RIPEMD160C80, RIPEMD160S8D);
RIPEMD160_STEP (RIPEMD160_Go, d2, e2, a2, b2, c2, wa_t, RIPEMD160C80, RIPEMD160S8E);
RIPEMD160_STEP (RIPEMD160_Go, c2, d2, e2, a2, b2, we_t, RIPEMD160C80, RIPEMD160S8F);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wc_t, RIPEMD160C90, RIPEMD160S90);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, wf_t, RIPEMD160C90, RIPEMD160S91);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, wa_t, RIPEMD160C90, RIPEMD160S92);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w4_t, RIPEMD160C90, RIPEMD160S93);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w1_t, RIPEMD160C90, RIPEMD160S94);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, w5_t, RIPEMD160C90, RIPEMD160S95);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, w8_t, RIPEMD160C90, RIPEMD160S96);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, w7_t, RIPEMD160C90, RIPEMD160S97);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w6_t, RIPEMD160C90, RIPEMD160S98);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w2_t, RIPEMD160C90, RIPEMD160S99);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wd_t, RIPEMD160C90, RIPEMD160S9A);
RIPEMD160_STEP (RIPEMD160_F , a2, b2, c2, d2, e2, we_t, RIPEMD160C90, RIPEMD160S9B);
RIPEMD160_STEP (RIPEMD160_F , e2, a2, b2, c2, d2, w0_t, RIPEMD160C90, RIPEMD160S9C);
RIPEMD160_STEP (RIPEMD160_F , d2, e2, a2, b2, c2, w3_t, RIPEMD160C90, RIPEMD160S9D);
RIPEMD160_STEP (RIPEMD160_F , c2, d2, e2, a2, b2, w9_t, RIPEMD160C90, RIPEMD160S9E);
RIPEMD160_STEP (RIPEMD160_F , b2, c2, d2, e2, a2, wb_t, RIPEMD160C90, RIPEMD160S9F);
const u32x a = digest[1] + c1 + d2;
const u32x b = digest[2] + d1 + e2;
const u32x c = digest[3] + e1 + a2;
const u32x d = digest[4] + a1 + b2;
const u32x e = digest[0] + b1 + c2;
digest[0] = a;
digest[1] = b;
digest[2] = c;
digest[3] = d;
digest[4] = e;
}
void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
{
digest[0] = ipad[0];
@ -550,7 +33,7 @@ void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x
digest[3] = ipad[3];
digest[4] = ipad[4];
ripemd160_transform_V (w0, w1, w2, w3, digest);
ripemd160_transform_vector (w0, w1, w2, w3, digest);
w0[0] = digest[0];
w0[1] = digest[1];
@ -575,7 +58,7 @@ void hmac_ripemd160_run_V (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x
digest[3] = opad[3];
digest[4] = opad[4];
ripemd160_transform_V (w0, w1, w2, w3, digest);
ripemd160_transform_vector (w0, w1, w2, w3, digest);
}
__kernel void m14643_init (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global luks_tmp_t *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 luks_t *luks_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)
@ -589,108 +72,83 @@ __kernel void m14643_init (__global pw_t *pws, __global const kernel_rule_t *rul
if (gid >= gid_max) return;
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[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] = pws[gid].i[14];
w3[3] = pws[gid].i[15];
/**
* salt
*/
u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 salt_buf0[4];
u32 salt_buf1[4];
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
ripemd160_hmac_ctx_t ripemd160_hmac_ctx;
u32 key_size = luks_bufs[digests_offset].key_size;
/**
* pads
*/
ripemd160_hmac_init (&ripemd160_hmac_ctx, w0, w1, w2, w3);
u32 ipad[5];
u32 opad[5];
tmps[gid].ipad32[0] = ripemd160_hmac_ctx.ipad.h[0];
tmps[gid].ipad32[1] = ripemd160_hmac_ctx.ipad.h[1];
tmps[gid].ipad32[2] = ripemd160_hmac_ctx.ipad.h[2];
tmps[gid].ipad32[3] = ripemd160_hmac_ctx.ipad.h[3];
tmps[gid].ipad32[4] = ripemd160_hmac_ctx.ipad.h[4];
hmac_ripemd160_pad_S (w0, w1, w2, w3, ipad, opad);
tmps[gid].opad32[0] = ripemd160_hmac_ctx.opad.h[0];
tmps[gid].opad32[1] = ripemd160_hmac_ctx.opad.h[1];
tmps[gid].opad32[2] = ripemd160_hmac_ctx.opad.h[2];
tmps[gid].opad32[3] = ripemd160_hmac_ctx.opad.h[3];
tmps[gid].opad32[4] = ripemd160_hmac_ctx.opad.h[4];
tmps[gid].ipad32[0] = ipad[0];
tmps[gid].ipad32[1] = ipad[1];
tmps[gid].ipad32[2] = ipad[2];
tmps[gid].ipad32[3] = ipad[3];
tmps[gid].ipad32[4] = ipad[4];
ripemd160_hmac_update_global (&ripemd160_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
tmps[gid].opad32[0] = opad[0];
tmps[gid].opad32[1] = opad[1];
tmps[gid].opad32[2] = opad[2];
tmps[gid].opad32[3] = opad[3];
tmps[gid].opad32[4] = opad[4];
const u32 key_size = luks_bufs[digests_offset].key_size;
for (u32 i = 0, j = 1; i < ((key_size / 8) / 4); i += 5, j += 1)
{
w0[0] = salt_buf0[0];
w0[1] = salt_buf0[1];
w0[2] = salt_buf0[2];
w0[3] = salt_buf0[3];
w1[0] = salt_buf1[0];
w1[1] = salt_buf1[1];
w1[2] = salt_buf1[2];
w1[3] = salt_buf1[3];
w2[0] = j << 24;
w2[1] = 0x80;
ripemd160_hmac_ctx_t ripemd160_hmac_ctx2 = ripemd160_hmac_ctx;
w0[0] = j << 24;
w0[1] = 0;
w0[2] = 0;
w0[3] = 0;
w1[0] = 0;
w1[1] = 0;
w1[2] = 0;
w1[3] = 0;
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = (64 + salt_len + 4) * 8;
w3[2] = 0;
w3[3] = 0;
u32 dgst[5];
ripemd160_hmac_update_64 (&ripemd160_hmac_ctx2, w0, w1, w2, w3, 4);
hmac_ripemd160_run_S (w0, w1, w2, w3, ipad, opad, dgst);
ripemd160_hmac_final (&ripemd160_hmac_ctx2);
tmps[gid].dgst32[i + 0] = dgst[0];
tmps[gid].dgst32[i + 1] = dgst[1];
tmps[gid].dgst32[i + 2] = dgst[2];
tmps[gid].dgst32[i + 3] = dgst[3];
tmps[gid].dgst32[i + 4] = dgst[4];
tmps[gid].dgst32[i + 0] = ripemd160_hmac_ctx2.opad.h[0];
tmps[gid].dgst32[i + 1] = ripemd160_hmac_ctx2.opad.h[1];
tmps[gid].dgst32[i + 2] = ripemd160_hmac_ctx2.opad.h[2];
tmps[gid].dgst32[i + 3] = ripemd160_hmac_ctx2.opad.h[3];
tmps[gid].dgst32[i + 4] = ripemd160_hmac_ctx2.opad.h[4];
tmps[gid].out32[i + 0] = dgst[0];
tmps[gid].out32[i + 1] = dgst[1];
tmps[gid].out32[i + 2] = dgst[2];
tmps[gid].out32[i + 3] = dgst[3];
tmps[gid].out32[i + 4] = dgst[4];
tmps[gid].out32[i + 0] = tmps[gid].dgst32[i + 0];
tmps[gid].out32[i + 1] = tmps[gid].dgst32[i + 1];
tmps[gid].out32[i + 2] = tmps[gid].dgst32[i + 2];
tmps[gid].out32[i + 3] = tmps[gid].dgst32[i + 3];
tmps[gid].out32[i + 4] = tmps[gid].dgst32[i + 4];
}
}

24
src/interface.c
Unescape View File

@ -24844,6 +24844,30 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
break;
case 14100: hashconfig->pw_max = 24; // 3DES max
break;
case 14611: hashconfig->pw_max = 64; // PBKDF2-HMAC-SHA1 max
break;
case 14612: hashconfig->pw_max = 64; // PBKDF2-HMAC-SHA1 max
break;
case 14613: hashconfig->pw_max = 64; // PBKDF2-HMAC-SHA1 max
break;
case 14621: hashconfig->pw_max = 64; // PBKDF2-HMAC-SHA256 max
break;
case 14622: hashconfig->pw_max = 64; // PBKDF2-HMAC-SHA256 max
break;
case 14623: hashconfig->pw_max = 64; // PBKDF2-HMAC-SHA256 max
break;
case 14631: hashconfig->pw_max = 128; // PBKDF2-HMAC-SHA512 max
break;
case 14632: hashconfig->pw_max = 128; // PBKDF2-HMAC-SHA512 max
break;
case 14633: hashconfig->pw_max = 128; // PBKDF2-HMAC-SHA512 max
break;
case 14641: hashconfig->pw_max = 64; // PBKDF2-HMAC-RipeMD160 max
break;
case 14642: hashconfig->pw_max = 64; // PBKDF2-HMAC-RipeMD160 max
break;
case 14643: hashconfig->pw_max = 64; // PBKDF2-HMAC-RipeMD160 max
break;
case 14900: hashconfig->pw_max = 10; // Skip32 max
break;
}

Write Preview
Loading…
Cancel
Save