mirror of
https://github.com/hashcat/hashcat.git
synced 2025-07-05 06:12:35 +00:00
15ada5124e
Updated kernel declarations from "KERNEL_FQ void HC_ATTR_SEQ" to "KERNEL_FQ KERNEL_FA void". Please update your custom plugin kernels accordingly. Added spilling size as a factor in calculating usable memory per device. This is based on undocumented variables and may not be 100% accurate, but it works well in practice. Added a compiler hint to scrypt-based kernels indicating the guaranteed maximum thread count per kernel invocation. Removed redundant kernel code 29800, as it is identical to 27700, and updated the plugin.
1105 lines
38 KiB
Common Lisp
1105 lines
38 KiB
Common Lisp
/**
|
|
* Author......: See docs/credits.txt
|
|
* License.....: MIT
|
|
*/
|
|
|
|
#define NEW_SIMD_CODE
|
|
|
|
#ifdef KERNEL_STATIC
|
|
#include M2S(INCLUDE_PATH/inc_vendor.h)
|
|
#include M2S(INCLUDE_PATH/inc_types.h)
|
|
#include M2S(INCLUDE_PATH/inc_platform.cl)
|
|
#include M2S(INCLUDE_PATH/inc_common.h)
|
|
#include M2S(INCLUDE_PATH/inc_common.cl)
|
|
#include M2S(INCLUDE_PATH/inc_simd.cl)
|
|
#include M2S(INCLUDE_PATH/inc_hash_sha256.cl)
|
|
#include M2S(INCLUDE_PATH/inc_cipher_aes.h)
|
|
#include M2S(INCLUDE_PATH/inc_cipher_aes.cl)
|
|
#endif
|
|
|
|
typedef struct scrtv2
|
|
{
|
|
u32 ct_buf[64];
|
|
int ct_len;
|
|
|
|
} scrtv2_t;
|
|
|
|
DECLSPEC void shift_buffer_by_offset (PRIVATE_AS u32 *w0, const u32 offset)
|
|
{
|
|
const int offset_switch = offset / 4;
|
|
|
|
#if ((defined IS_AMD || defined IS_HIP) && HAS_VPERM == 0) || defined IS_GENERIC
|
|
switch (offset_switch)
|
|
{
|
|
case 0:
|
|
w0[3] = hc_bytealign_be_S (w0[2], w0[3], offset);
|
|
w0[2] = hc_bytealign_be_S (w0[1], w0[2], offset);
|
|
w0[1] = hc_bytealign_be_S (w0[0], w0[1], offset);
|
|
w0[0] = hc_bytealign_be_S ( 0, w0[0], offset);
|
|
break;
|
|
|
|
case 1:
|
|
w0[3] = hc_bytealign_be_S (w0[1], w0[2], offset);
|
|
w0[2] = hc_bytealign_be_S (w0[0], w0[1], offset);
|
|
w0[1] = hc_bytealign_be_S ( 0, w0[0], offset);
|
|
w0[0] = 0;
|
|
break;
|
|
|
|
case 2:
|
|
w0[3] = hc_bytealign_be_S (w0[0], w0[1], offset);
|
|
w0[2] = hc_bytealign_be_S ( 0, w0[0], offset);
|
|
w0[1] = 0;
|
|
w0[0] = 0;
|
|
break;
|
|
|
|
case 3:
|
|
w0[3] = hc_bytealign_be_S ( 0, w0[0], offset);
|
|
w0[2] = 0;
|
|
w0[1] = 0;
|
|
w0[0] = 0;
|
|
break;
|
|
|
|
default:
|
|
w0[3] = 0;
|
|
w0[2] = 0;
|
|
w0[1] = 0;
|
|
w0[0] = 0;
|
|
break;
|
|
}
|
|
#endif
|
|
|
|
#if ((defined IS_AMD || defined IS_HIP) && HAS_VPERM == 1) || defined IS_NV
|
|
|
|
#if defined IS_NV
|
|
const int selector = (0x76543210 >> ((offset & 3) * 4)) & 0xffff;
|
|
#endif
|
|
|
|
#if (defined IS_AMD || defined IS_HIP)
|
|
const int selector = l32_from_64_S(0x0706050403020100UL >> ((offset & 3) * 8));
|
|
#endif
|
|
|
|
switch (offset_switch)
|
|
{
|
|
case 0:
|
|
w0[3] = hc_byte_perm_S (w0[3], w0[2], selector);
|
|
w0[2] = hc_byte_perm_S (w0[2], w0[1], selector);
|
|
w0[1] = hc_byte_perm_S (w0[1], w0[0], selector);
|
|
w0[0] = hc_byte_perm_S (w0[0], 0, selector);
|
|
break;
|
|
|
|
case 1:
|
|
w0[3] = hc_byte_perm_S (w0[2], w0[1], selector);
|
|
w0[2] = hc_byte_perm_S (w0[1], w0[0], selector);
|
|
w0[1] = hc_byte_perm_S (w0[0], 0, selector);
|
|
w0[0] = 0;
|
|
break;
|
|
|
|
case 2:
|
|
w0[3] = hc_byte_perm_S (w0[1], w0[0], selector);
|
|
w0[2] = hc_byte_perm_S (w0[0], 0, selector);
|
|
w0[1] = 0;
|
|
w0[0] = 0;
|
|
break;
|
|
|
|
case 3:
|
|
w0[3] = hc_byte_perm_S (w0[0], 0, selector);
|
|
w0[2] = 0;
|
|
w0[1] = 0;
|
|
w0[0] = 0;
|
|
break;
|
|
|
|
default:
|
|
w0[3] = 0;
|
|
w0[2] = 0;
|
|
w0[1] = 0;
|
|
w0[0] = 0;
|
|
break;
|
|
}
|
|
#endif
|
|
}
|
|
|
|
DECLSPEC void aes256_scrt_format (PRIVATE_AS u32 *aes_ks, PRIVATE_AS u32 *pw, const u32 pw_len, PRIVATE_AS u32 *hash, PRIVATE_AS u32 *out, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4)
|
|
{
|
|
AES256_set_encrypt_key (aes_ks, hash, s_te0, s_te1, s_te2, s_te3);
|
|
|
|
shift_buffer_by_offset (hash, pw_len + 4);
|
|
|
|
hash[0] = hc_swap32_S (pw_len);
|
|
hash[1] |= hc_swap32_S (pw[0]);
|
|
hash[2] |= hc_swap32_S (pw[1]);
|
|
hash[3] |= hc_swap32_S (pw[2]);
|
|
|
|
AES256_encrypt (aes_ks, hash, out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
}
|
|
|
|
DECLSPEC void aes256_scrt_format_VV (PRIVATE_AS u32 *aes_ks, PRIVATE_AS u32x *w, const u32 pw_len, PRIVATE_AS u32x *h, PRIVATE_AS u32x *out, SHM_TYPE u32 *s_te0, SHM_TYPE u32 *s_te1, SHM_TYPE u32 *s_te2, SHM_TYPE u32 *s_te3, SHM_TYPE u32 *s_te4)
|
|
{
|
|
#if VECT_SIZE == 1
|
|
aes256_scrt_format (aes_ks, w, pw_len, h, out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
#endif
|
|
|
|
#if VECT_SIZE >= 2
|
|
u32 tmp_w[4];
|
|
u32 tmp_h[8];
|
|
u32 tmp_out[4];
|
|
|
|
//s0
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s0;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s0;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s0 = tmp_out[i];
|
|
|
|
//s1
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s1;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s1;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s1 = tmp_out[i];
|
|
|
|
#endif
|
|
|
|
#if VECT_SIZE >= 4
|
|
|
|
//s2
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s2;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s2;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s2 = tmp_out[i];
|
|
|
|
//s3
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s3;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s3;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s3 = tmp_out[i];
|
|
|
|
#endif
|
|
|
|
#if VECT_SIZE >= 8
|
|
|
|
//s4
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s4;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s4;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s4 = tmp_out[i];
|
|
|
|
//s5
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s5;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s5;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s5 = tmp_out[i];
|
|
|
|
//s6
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s6;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s6;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s6 = tmp_out[i];
|
|
|
|
//s7
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s7;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s7;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s7 = tmp_out[i];
|
|
|
|
#endif
|
|
|
|
#if VECT_SIZE >= 16
|
|
|
|
//s8
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s8;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s8;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s8 = tmp_out[i];
|
|
|
|
//s9
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].s9;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].s9;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].s9 = tmp_out[i];
|
|
|
|
//sa
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].sa;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].sa;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].sa = tmp_out[i];
|
|
|
|
//sb
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].sb;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].sb;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].sb = tmp_out[i];
|
|
|
|
//sc
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].sc;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].sc;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].sc = tmp_out[i];
|
|
|
|
//sd
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].sd;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].sd;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].sd = tmp_out[i];
|
|
|
|
//se
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].se;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].se;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].se = tmp_out[i];
|
|
|
|
//sf
|
|
|
|
for (u32 i = 0; i < 4; i++) tmp_w[i] = w[i].sf;
|
|
for (u32 i = 0; i < 8; i++) tmp_h[i] = h[i].sf;
|
|
|
|
aes256_scrt_format (aes_ks, tmp_w, pw_len, tmp_h, tmp_out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
for (u32 i = 0; i < 4; i++) out[i].sf = tmp_out[i];
|
|
|
|
#endif
|
|
}
|
|
|
|
DECLSPEC void m31400m (SHM_TYPE u32a *s_te0, SHM_TYPE u32a *s_te1, SHM_TYPE u32a *s_te2, SHM_TYPE u32a *s_te3, SHM_TYPE u32a *s_te4, PRIVATE_AS u32 *w, const u32 pw_len, KERN_ATTR_FUNC_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* modifiers are taken from args
|
|
*/
|
|
|
|
/**
|
|
* loop
|
|
*/
|
|
|
|
u32 ks[60];
|
|
|
|
u32x wt[4];
|
|
|
|
u32 w0l = w[0];
|
|
|
|
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos += VECT_SIZE)
|
|
{
|
|
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
|
|
|
const u32x w0 = w0l | w0r;
|
|
|
|
wt[0] = w0;
|
|
wt[1] = w[1];
|
|
wt[2] = w[2];
|
|
wt[3] = w[3];
|
|
|
|
u32x ww0[4];
|
|
u32x ww1[4];
|
|
u32x ww2[4];
|
|
u32x ww3[4];
|
|
|
|
ww0[0] = hc_swap32 (w0);
|
|
ww0[1] = hc_swap32 (w[1]);
|
|
ww0[2] = hc_swap32 (w[2]);
|
|
ww0[3] = hc_swap32 (w[3]);
|
|
ww1[0] = hc_swap32 (w[4]);
|
|
ww1[1] = hc_swap32 (w[5]);
|
|
ww1[2] = hc_swap32 (w[6]);
|
|
ww1[3] = hc_swap32 (w[7]);
|
|
ww2[0] = hc_swap32 (w[8]);
|
|
ww2[1] = hc_swap32 (w[9]);
|
|
ww2[2] = hc_swap32 (w[10]);
|
|
ww2[3] = hc_swap32 (w[11]);
|
|
ww3[0] = hc_swap32 (w[12]);
|
|
ww3[1] = hc_swap32 (w[13]);
|
|
ww3[2] = hc_swap32 (w[14]);
|
|
ww3[3] = hc_swap32 (w[15]);
|
|
|
|
const int off = pw_len & 63;
|
|
|
|
append_0x80_4x4 (ww0, ww1, ww2, ww3, off ^ 3);
|
|
|
|
ww3[2] = 0;
|
|
ww3[3] = pw_len * 8;
|
|
|
|
u32x w0_t = ww0[0];
|
|
u32x w1_t = ww0[1];
|
|
u32x w2_t = ww0[2];
|
|
u32x w3_t = ww0[3];
|
|
u32x w4_t = ww1[0];
|
|
u32x w5_t = ww1[1];
|
|
u32x w6_t = ww1[2];
|
|
u32x w7_t = ww1[3];
|
|
u32x w8_t = ww2[0];
|
|
u32x w9_t = ww2[1];
|
|
u32x wa_t = ww2[2];
|
|
u32x wb_t = ww2[3];
|
|
u32x wc_t = ww3[0];
|
|
u32x wd_t = ww3[1];
|
|
u32x we_t = ww3[2];
|
|
u32x wf_t = ww3[3];
|
|
|
|
// sha256
|
|
|
|
u32x a = SHA256M_A;
|
|
u32x b = SHA256M_B;
|
|
u32x c = SHA256M_C;
|
|
u32x d = SHA256M_D;
|
|
u32x e = SHA256M_E;
|
|
u32x f = SHA256M_F;
|
|
u32x g = SHA256M_G;
|
|
u32x h = SHA256M_H;
|
|
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
|
|
|
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
|
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
|
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
|
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
|
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
|
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
|
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
|
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
|
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
|
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
|
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
|
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
|
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
|
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
|
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
|
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
|
|
|
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
|
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
|
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
|
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
|
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
|
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
|
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
|
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
|
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
|
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
|
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
|
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
|
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
|
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
|
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
|
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
|
|
|
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
|
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
|
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
|
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
|
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
|
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
|
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
|
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
|
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
|
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
|
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
|
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
|
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
|
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
|
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
|
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
|
|
|
u32x digest[8];
|
|
|
|
digest[0] = a + make_u32x (SHA256M_A);
|
|
digest[1] = b + make_u32x (SHA256M_B);
|
|
digest[2] = c + make_u32x (SHA256M_C);
|
|
digest[3] = d + make_u32x (SHA256M_D);
|
|
digest[4] = e + make_u32x (SHA256M_E);
|
|
digest[5] = f + make_u32x (SHA256M_F);
|
|
digest[6] = g + make_u32x (SHA256M_G);
|
|
digest[7] = h + make_u32x (SHA256M_H);
|
|
|
|
u32x out[4] = { 0 };
|
|
|
|
aes256_scrt_format_VV (ks, wt, pw_len, digest, out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
const u32x r0 = out[DGST_R0];
|
|
const u32x r1 = out[DGST_R1];
|
|
const u32x r2 = out[DGST_R2];
|
|
const u32x r3 = out[DGST_R3];
|
|
|
|
COMPARE_M_SIMD (r0, r1, r2, r3);
|
|
}
|
|
}
|
|
|
|
KERNEL_FQ KERNEL_FA void m31400_m04 (KERN_ATTR_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
const u64 lid = get_local_id (0);
|
|
const u64 gid = get_global_id (0);
|
|
const u64 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* aes shared
|
|
*/
|
|
|
|
#ifdef REAL_SHM
|
|
|
|
LOCAL_VK u32 s_te0[256];
|
|
LOCAL_VK u32 s_te1[256];
|
|
LOCAL_VK u32 s_te2[256];
|
|
LOCAL_VK u32 s_te3[256];
|
|
LOCAL_VK u32 s_te4[256];
|
|
|
|
for (u32 i = lid; i < 256; i += lsz)
|
|
{
|
|
s_te0[i] = te0[i];
|
|
s_te1[i] = te1[i];
|
|
s_te2[i] = te2[i];
|
|
s_te3[i] = te3[i];
|
|
s_te4[i] = te4[i];
|
|
}
|
|
|
|
SYNC_THREADS ();
|
|
|
|
#else
|
|
|
|
CONSTANT_AS u32a *s_te0 = te0;
|
|
CONSTANT_AS u32a *s_te1 = te1;
|
|
CONSTANT_AS u32a *s_te2 = te2;
|
|
CONSTANT_AS u32a *s_te3 = te3;
|
|
CONSTANT_AS u32a *s_te4 = te4;
|
|
|
|
#endif
|
|
|
|
if (gid >= GID_CNT) return;
|
|
|
|
u32 w[16];
|
|
|
|
w[ 0] = pws[gid].i[ 0];
|
|
w[ 1] = pws[gid].i[ 1];
|
|
w[ 2] = pws[gid].i[ 2];
|
|
w[ 3] = pws[gid].i[ 3];
|
|
w[ 4] = 0;
|
|
w[ 5] = 0;
|
|
w[ 6] = 0;
|
|
w[ 7] = 0;
|
|
w[ 8] = 0;
|
|
w[ 9] = 0;
|
|
w[10] = 0;
|
|
w[11] = 0;
|
|
w[12] = 0;
|
|
w[13] = 0;
|
|
w[14] = 0;
|
|
w[15] = pws[gid].i[15];
|
|
|
|
const u32 pw_len = pws[gid].pw_len & 63;
|
|
|
|
/**
|
|
* main
|
|
*/
|
|
|
|
m31400m (s_te0, s_te1, s_te2, s_te3, s_te4, w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
|
|
}
|
|
|
|
KERNEL_FQ KERNEL_FA void m31400_m08 (KERN_ATTR_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
const u64 lid = get_local_id (0);
|
|
const u64 gid = get_global_id (0);
|
|
const u64 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* aes shared
|
|
*/
|
|
|
|
#ifdef REAL_SHM
|
|
|
|
LOCAL_VK u32 s_te0[256];
|
|
LOCAL_VK u32 s_te1[256];
|
|
LOCAL_VK u32 s_te2[256];
|
|
LOCAL_VK u32 s_te3[256];
|
|
LOCAL_VK u32 s_te4[256];
|
|
|
|
for (u32 i = lid; i < 256; i += lsz)
|
|
{
|
|
s_te0[i] = te0[i];
|
|
s_te1[i] = te1[i];
|
|
s_te2[i] = te2[i];
|
|
s_te3[i] = te3[i];
|
|
s_te4[i] = te4[i];
|
|
}
|
|
|
|
SYNC_THREADS ();
|
|
|
|
#else
|
|
|
|
CONSTANT_AS u32a *s_te0 = te0;
|
|
CONSTANT_AS u32a *s_te1 = te1;
|
|
CONSTANT_AS u32a *s_te2 = te2;
|
|
CONSTANT_AS u32a *s_te3 = te3;
|
|
CONSTANT_AS u32a *s_te4 = te4;
|
|
|
|
#endif
|
|
|
|
if (gid >= GID_CNT) return;
|
|
|
|
u32 w[16];
|
|
|
|
w[ 0] = pws[gid].i[ 0];
|
|
w[ 1] = pws[gid].i[ 1];
|
|
w[ 2] = pws[gid].i[ 2];
|
|
w[ 3] = pws[gid].i[ 3];
|
|
w[ 4] = pws[gid].i[ 4];
|
|
w[ 5] = pws[gid].i[ 5];
|
|
w[ 6] = pws[gid].i[ 6];
|
|
w[ 7] = pws[gid].i[ 7];
|
|
w[ 8] = 0;
|
|
w[ 9] = 0;
|
|
w[10] = 0;
|
|
w[11] = 0;
|
|
w[12] = 0;
|
|
w[13] = 0;
|
|
w[14] = 0;
|
|
w[15] = pws[gid].i[15];
|
|
|
|
const u32 pw_len = pws[gid].pw_len & 63;
|
|
|
|
/**
|
|
* main
|
|
*/
|
|
|
|
m31400m (s_te0, s_te1, s_te2, s_te3, s_te4, w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
|
|
}
|
|
|
|
KERNEL_FQ KERNEL_FA void m31400_m16 (KERN_ATTR_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
const u64 lid = get_local_id (0);
|
|
const u64 gid = get_global_id (0);
|
|
const u64 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* aes shared
|
|
*/
|
|
|
|
#ifdef REAL_SHM
|
|
|
|
LOCAL_VK u32 s_te0[256];
|
|
LOCAL_VK u32 s_te1[256];
|
|
LOCAL_VK u32 s_te2[256];
|
|
LOCAL_VK u32 s_te3[256];
|
|
LOCAL_VK u32 s_te4[256];
|
|
|
|
for (u32 i = lid; i < 256; i += lsz)
|
|
{
|
|
s_te0[i] = te0[i];
|
|
s_te1[i] = te1[i];
|
|
s_te2[i] = te2[i];
|
|
s_te3[i] = te3[i];
|
|
s_te4[i] = te4[i];
|
|
}
|
|
|
|
SYNC_THREADS ();
|
|
|
|
#else
|
|
|
|
CONSTANT_AS u32a *s_te0 = te0;
|
|
CONSTANT_AS u32a *s_te1 = te1;
|
|
CONSTANT_AS u32a *s_te2 = te2;
|
|
CONSTANT_AS u32a *s_te3 = te3;
|
|
CONSTANT_AS u32a *s_te4 = te4;
|
|
|
|
#endif
|
|
|
|
if (gid >= GID_CNT) return;
|
|
|
|
u32 w[16];
|
|
|
|
w[ 0] = pws[gid].i[ 0];
|
|
w[ 1] = pws[gid].i[ 1];
|
|
w[ 2] = pws[gid].i[ 2];
|
|
w[ 3] = pws[gid].i[ 3];
|
|
w[ 4] = pws[gid].i[ 4];
|
|
w[ 5] = pws[gid].i[ 5];
|
|
w[ 6] = pws[gid].i[ 6];
|
|
w[ 7] = pws[gid].i[ 7];
|
|
w[ 8] = pws[gid].i[ 8];
|
|
w[ 9] = pws[gid].i[ 9];
|
|
w[10] = pws[gid].i[10];
|
|
w[11] = pws[gid].i[11];
|
|
w[12] = pws[gid].i[12];
|
|
w[13] = pws[gid].i[13];
|
|
w[14] = pws[gid].i[14];
|
|
w[15] = pws[gid].i[15];
|
|
|
|
const u32 pw_len = pws[gid].pw_len & 63;
|
|
|
|
/**
|
|
* main
|
|
*/
|
|
|
|
m31400m (s_te0, s_te1, s_te2, s_te3, s_te4, w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
|
|
}
|
|
|
|
DECLSPEC void m31400s (SHM_TYPE u32a *s_te0, SHM_TYPE u32a *s_te1, SHM_TYPE u32a *s_te2, SHM_TYPE u32a *s_te3, SHM_TYPE u32a *s_te4, PRIVATE_AS u32 *w, const u32 pw_len, KERN_ATTR_FUNC_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* modifiers are taken from args
|
|
*/
|
|
|
|
/**
|
|
* digest
|
|
*/
|
|
|
|
const u32 search[4] =
|
|
{
|
|
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
|
|
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
|
|
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
|
|
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
|
|
};
|
|
|
|
/**
|
|
* loop
|
|
*/
|
|
|
|
u32 ks[60];
|
|
|
|
u32x wt[4];
|
|
|
|
u32 w0l = w[0];
|
|
|
|
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos += VECT_SIZE)
|
|
{
|
|
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
|
|
|
const u32x w0 = w0l | w0r;
|
|
|
|
wt[0] = w0;
|
|
wt[1] = w[1];
|
|
wt[2] = w[2];
|
|
wt[3] = w[3];
|
|
|
|
u32x ww0[4];
|
|
u32x ww1[4];
|
|
u32x ww2[4];
|
|
u32x ww3[4];
|
|
|
|
ww0[0] = hc_swap32 (w0);
|
|
ww0[1] = hc_swap32 (w[1]);
|
|
ww0[2] = hc_swap32 (w[2]);
|
|
ww0[3] = hc_swap32 (w[3]);
|
|
ww1[0] = hc_swap32 (w[4]);
|
|
ww1[1] = hc_swap32 (w[5]);
|
|
ww1[2] = hc_swap32 (w[6]);
|
|
ww1[3] = hc_swap32 (w[7]);
|
|
ww2[0] = hc_swap32 (w[8]);
|
|
ww2[1] = hc_swap32 (w[9]);
|
|
ww2[2] = hc_swap32 (w[10]);
|
|
ww2[3] = hc_swap32 (w[11]);
|
|
ww3[0] = hc_swap32 (w[12]);
|
|
ww3[1] = hc_swap32 (w[13]);
|
|
ww3[2] = hc_swap32 (w[14]);
|
|
ww3[3] = hc_swap32 (w[15]);
|
|
|
|
const int off = pw_len & 63;
|
|
|
|
append_0x80_4x4 (ww0, ww1, ww2, ww3, off ^ 3);
|
|
|
|
ww3[2] = 0;
|
|
ww3[3] = pw_len * 8;
|
|
|
|
u32x w0_t = ww0[0];
|
|
u32x w1_t = ww0[1];
|
|
u32x w2_t = ww0[2];
|
|
u32x w3_t = ww0[3];
|
|
u32x w4_t = ww1[0];
|
|
u32x w5_t = ww1[1];
|
|
u32x w6_t = ww1[2];
|
|
u32x w7_t = ww1[3];
|
|
u32x w8_t = ww2[0];
|
|
u32x w9_t = ww2[1];
|
|
u32x wa_t = ww2[2];
|
|
u32x wb_t = ww2[3];
|
|
u32x wc_t = ww3[0];
|
|
u32x wd_t = ww3[1];
|
|
u32x we_t = ww3[2];
|
|
u32x wf_t = ww3[3];
|
|
|
|
// sha256
|
|
|
|
u32x a = SHA256M_A;
|
|
u32x b = SHA256M_B;
|
|
u32x c = SHA256M_C;
|
|
u32x d = SHA256M_D;
|
|
u32x e = SHA256M_E;
|
|
u32x f = SHA256M_F;
|
|
u32x g = SHA256M_G;
|
|
u32x h = SHA256M_H;
|
|
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
|
|
SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
|
|
|
|
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
|
|
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
|
|
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
|
|
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
|
|
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
|
|
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
|
|
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
|
|
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
|
|
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
|
|
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
|
|
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
|
|
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
|
|
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
|
|
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
|
|
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
|
|
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
|
|
|
|
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
|
|
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
|
|
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
|
|
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
|
|
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
|
|
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
|
|
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
|
|
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
|
|
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
|
|
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
|
|
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
|
|
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
|
|
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
|
|
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
|
|
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
|
|
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
|
|
|
|
w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
|
|
w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
|
|
w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
|
|
w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
|
|
w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
|
|
w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
|
|
w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
|
|
w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
|
|
w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
|
|
w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
|
|
wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
|
|
wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
|
|
wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
|
|
wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
|
|
we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
|
|
wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
|
|
|
|
u32x digest[8];
|
|
|
|
digest[0] = a + make_u32x (SHA256M_A);
|
|
digest[1] = b + make_u32x (SHA256M_B);
|
|
digest[2] = c + make_u32x (SHA256M_C);
|
|
digest[3] = d + make_u32x (SHA256M_D);
|
|
digest[4] = e + make_u32x (SHA256M_E);
|
|
digest[5] = f + make_u32x (SHA256M_F);
|
|
digest[6] = g + make_u32x (SHA256M_G);
|
|
digest[7] = h + make_u32x (SHA256M_H);
|
|
|
|
u32x out[4] = { 0 };
|
|
|
|
aes256_scrt_format_VV (ks, wt, pw_len, digest, out, s_te0, s_te1, s_te2, s_te3, s_te4);
|
|
|
|
const u32x r0 = out[DGST_R0];
|
|
const u32x r1 = out[DGST_R1];
|
|
const u32x r2 = out[DGST_R2];
|
|
const u32x r3 = out[DGST_R3];
|
|
|
|
COMPARE_S_SIMD (r0, r1, r2, r3);
|
|
}
|
|
}
|
|
|
|
KERNEL_FQ KERNEL_FA void m31400_s04 (KERN_ATTR_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
const u64 lid = get_local_id (0);
|
|
const u64 gid = get_global_id (0);
|
|
const u64 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* aes shared
|
|
*/
|
|
|
|
#ifdef REAL_SHM
|
|
|
|
LOCAL_VK u32 s_te0[256];
|
|
LOCAL_VK u32 s_te1[256];
|
|
LOCAL_VK u32 s_te2[256];
|
|
LOCAL_VK u32 s_te3[256];
|
|
LOCAL_VK u32 s_te4[256];
|
|
|
|
for (u32 i = lid; i < 256; i += lsz)
|
|
{
|
|
s_te0[i] = te0[i];
|
|
s_te1[i] = te1[i];
|
|
s_te2[i] = te2[i];
|
|
s_te3[i] = te3[i];
|
|
s_te4[i] = te4[i];
|
|
}
|
|
|
|
SYNC_THREADS ();
|
|
|
|
#else
|
|
|
|
CONSTANT_AS u32a *s_te0 = te0;
|
|
CONSTANT_AS u32a *s_te1 = te1;
|
|
CONSTANT_AS u32a *s_te2 = te2;
|
|
CONSTANT_AS u32a *s_te3 = te3;
|
|
CONSTANT_AS u32a *s_te4 = te4;
|
|
|
|
#endif
|
|
|
|
if (gid >= GID_CNT) return;
|
|
|
|
u32 w[16];
|
|
w[ 0] = pws[gid].i[ 0];
|
|
w[ 1] = pws[gid].i[ 1];
|
|
w[ 2] = pws[gid].i[ 2];
|
|
w[ 3] = pws[gid].i[ 3];
|
|
w[ 4] = 0;
|
|
w[ 5] = 0;
|
|
w[ 6] = 0;
|
|
w[ 7] = 0;
|
|
w[ 8] = 0;
|
|
w[ 9] = 0;
|
|
w[10] = 0;
|
|
w[11] = 0;
|
|
w[12] = 0;
|
|
w[13] = 0;
|
|
w[14] = 0;
|
|
w[15] = pws[gid].i[15];
|
|
|
|
const u32 pw_len = pws[gid].pw_len & 63;
|
|
|
|
/**
|
|
* main
|
|
*/
|
|
|
|
m31400s (s_te0, s_te1, s_te2, s_te3, s_te4, w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
|
|
}
|
|
|
|
KERNEL_FQ KERNEL_FA void m31400_s08 (KERN_ATTR_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
const u64 lid = get_local_id (0);
|
|
const u64 gid = get_global_id (0);
|
|
const u64 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* aes shared
|
|
*/
|
|
|
|
#ifdef REAL_SHM
|
|
|
|
LOCAL_VK u32 s_te0[256];
|
|
LOCAL_VK u32 s_te1[256];
|
|
LOCAL_VK u32 s_te2[256];
|
|
LOCAL_VK u32 s_te3[256];
|
|
LOCAL_VK u32 s_te4[256];
|
|
|
|
for (u32 i = lid; i < 256; i += lsz)
|
|
{
|
|
s_te0[i] = te0[i];
|
|
s_te1[i] = te1[i];
|
|
s_te2[i] = te2[i];
|
|
s_te3[i] = te3[i];
|
|
s_te4[i] = te4[i];
|
|
}
|
|
|
|
SYNC_THREADS ();
|
|
|
|
#else
|
|
|
|
CONSTANT_AS u32a *s_te0 = te0;
|
|
CONSTANT_AS u32a *s_te1 = te1;
|
|
CONSTANT_AS u32a *s_te2 = te2;
|
|
CONSTANT_AS u32a *s_te3 = te3;
|
|
CONSTANT_AS u32a *s_te4 = te4;
|
|
|
|
#endif
|
|
|
|
if (gid >= GID_CNT) return;
|
|
|
|
u32 w[16];
|
|
|
|
w[ 0] = pws[gid].i[ 0];
|
|
w[ 1] = pws[gid].i[ 1];
|
|
w[ 2] = pws[gid].i[ 2];
|
|
w[ 3] = pws[gid].i[ 3];
|
|
w[ 4] = pws[gid].i[ 4];
|
|
w[ 5] = pws[gid].i[ 5];
|
|
w[ 6] = pws[gid].i[ 6];
|
|
w[ 7] = pws[gid].i[ 7];
|
|
w[ 8] = 0;
|
|
w[ 9] = 0;
|
|
w[10] = 0;
|
|
w[11] = 0;
|
|
w[12] = 0;
|
|
w[13] = 0;
|
|
w[14] = 0;
|
|
w[15] = pws[gid].i[15];
|
|
|
|
const u32 pw_len = pws[gid].pw_len & 63;
|
|
|
|
/**
|
|
* main
|
|
*/
|
|
|
|
m31400s (s_te0, s_te1, s_te2, s_te3, s_te4, w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
|
|
}
|
|
|
|
KERNEL_FQ KERNEL_FA void m31400_s16 (KERN_ATTR_VECTOR_ESALT (scrtv2_t))
|
|
{
|
|
/**
|
|
* base
|
|
*/
|
|
|
|
const u64 lid = get_local_id (0);
|
|
const u64 gid = get_global_id (0);
|
|
const u64 lsz = get_local_size (0);
|
|
|
|
/**
|
|
* aes shared
|
|
*/
|
|
|
|
#ifdef REAL_SHM
|
|
|
|
LOCAL_VK u32 s_te0[256];
|
|
LOCAL_VK u32 s_te1[256];
|
|
LOCAL_VK u32 s_te2[256];
|
|
LOCAL_VK u32 s_te3[256];
|
|
LOCAL_VK u32 s_te4[256];
|
|
|
|
for (u32 i = lid; i < 256; i += lsz)
|
|
{
|
|
s_te0[i] = te0[i];
|
|
s_te1[i] = te1[i];
|
|
s_te2[i] = te2[i];
|
|
s_te3[i] = te3[i];
|
|
s_te4[i] = te4[i];
|
|
}
|
|
|
|
SYNC_THREADS ();
|
|
|
|
#else
|
|
|
|
CONSTANT_AS u32a *s_te0 = te0;
|
|
CONSTANT_AS u32a *s_te1 = te1;
|
|
CONSTANT_AS u32a *s_te2 = te2;
|
|
CONSTANT_AS u32a *s_te3 = te3;
|
|
CONSTANT_AS u32a *s_te4 = te4;
|
|
|
|
#endif
|
|
|
|
if (gid >= GID_CNT) return;
|
|
|
|
u32 w[16];
|
|
|
|
w[ 0] = pws[gid].i[ 0];
|
|
w[ 1] = pws[gid].i[ 1];
|
|
w[ 2] = pws[gid].i[ 2];
|
|
w[ 3] = pws[gid].i[ 3];
|
|
w[ 4] = pws[gid].i[ 4];
|
|
w[ 5] = pws[gid].i[ 5];
|
|
w[ 6] = pws[gid].i[ 6];
|
|
w[ 7] = pws[gid].i[ 7];
|
|
w[ 8] = pws[gid].i[ 8];
|
|
w[ 9] = pws[gid].i[ 9];
|
|
w[10] = pws[gid].i[10];
|
|
w[11] = pws[gid].i[11];
|
|
w[12] = pws[gid].i[12];
|
|
w[13] = pws[gid].i[13];
|
|
w[14] = pws[gid].i[14];
|
|
w[15] = pws[gid].i[15];
|
|
|
|
const u32 pw_len = pws[gid].pw_len & 63;
|
|
|
|
/**
|
|
* main
|
|
*/
|
|
|
|
m31400s (s_te0, s_te1, s_te2, s_te3, s_te4, w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
|
|
}
|