1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
/*
#
# Copyright 2008-2011 Lukas Lueg, lukas.lueg@gmail.com
#
# This file is part of Pyrit.
#
# Pyrit is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Pyrit is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Pyrit. If not, see <http://www.gnu.org/licenses/>.
#
# Additional permission under GNU GPL version 3 section 7
#
# If you modify this Program, or any covered work, by linking or
# combining it with NVIDIA Corporation's CUDA libraries from the
# NVIDIA CUDA Toolkit (or a modified version of those libraries),
# containing parts covered by the terms of NVIDIA CUDA Toolkit
# EULA, the licensors of this Program grant you additional
# permission to convey the resulting work.
*/
#include "_cpyrit_cuda.h"
/* This is a 'special-version' of the SHA1 round function. *ctx is the current state,
that gets updated by *data. Notice the lack of endianess-changes here.
This SHA1-implementation follows the more-instructions-less-space paradigm, since registers
and (fast) memory on the device are precious, threads are not. Only the starting values
of W[0] to W[4] are defined by parameters. We fix the rest to invariant values and leave
the possible register allocation optimization to the compiler.
*/
__device__
void sha1_process( const SHA_DEV_CTX *ctx, SHA_DEV_CTX *data) {
uint32_t temp, W[16], A, B, C, D, E;
W[ 0] = data->h0; W[ 1] = data->h1;
W[ 2] = data->h2; W[ 3] = data->h3;
W[ 4] = data->h4; W[ 5] = 0x80000000;
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] = (64+20)*8;
A = ctx->h0;
B = ctx->h1;
C = ctx->h2;
D = ctx->h3;
E = ctx->h4;
#undef S
#define S(x,n) ((x << n) | (x >> (32 - n)))
#undef R
#define R(t) \
( \
temp = W[(t - 3) & 0x0F] ^ W[(t - 8) & 0x0F] ^ \
W[(t - 14) & 0x0F] ^ W[ t & 0x0F], \
( W[t & 0x0F] = S(temp,1) ) \
)
#undef P
#define P(a,b,c,d,e,x) \
{ \
e += S(a,5) + F(b,c,d) + K + x; b = S(b,30); \
}
#define F(x,y,z) (z ^ (x & (y ^ z)))
#define K 0x5A827999
P( A, B, C, D, E, W[0] );
P( E, A, B, C, D, W[1] );
P( D, E, A, B, C, W[2] );
P( C, D, E, A, B, W[3] );
P( B, C, D, E, A, W[4] );
P( A, B, C, D, E, W[5] );
P( E, A, B, C, D, W[6] );
P( D, E, A, B, C, W[7] );
P( C, D, E, A, B, W[8] );
P( B, C, D, E, A, W[9] );
P( A, B, C, D, E, W[10] );
P( E, A, B, C, D, W[11] );
P( D, E, A, B, C, W[12] );
P( C, D, E, A, B, W[13] );
P( B, C, D, E, A, W[14] );
P( A, B, C, D, E, W[15] );
P( E, A, B, C, D, R(16) );
P( D, E, A, B, C, R(17) );
P( C, D, E, A, B, R(18) );
P( B, C, D, E, A, R(19) );
#undef K
#undef F
#define F(x,y,z) (x ^ y ^ z)
#define K 0x6ED9EBA1
P( A, B, C, D, E, R(20) );
P( E, A, B, C, D, R(21) );
P( D, E, A, B, C, R(22) );
P( C, D, E, A, B, R(23) );
P( B, C, D, E, A, R(24) );
P( A, B, C, D, E, R(25) );
P( E, A, B, C, D, R(26) );
P( D, E, A, B, C, R(27) );
P( C, D, E, A, B, R(28) );
P( B, C, D, E, A, R(29) );
P( A, B, C, D, E, R(30) );
P( E, A, B, C, D, R(31) );
P( D, E, A, B, C, R(32) );
P( C, D, E, A, B, R(33) );
P( B, C, D, E, A, R(34) );
P( A, B, C, D, E, R(35) );
P( E, A, B, C, D, R(36) );
P( D, E, A, B, C, R(37) );
P( C, D, E, A, B, R(38) );
P( B, C, D, E, A, R(39) );
#undef K
#undef F
#define F(x,y,z) ((x & y) | (z & (x | y)))
#define K 0x8F1BBCDC
P( A, B, C, D, E, R(40) );
P( E, A, B, C, D, R(41) );
P( D, E, A, B, C, R(42) );
P( C, D, E, A, B, R(43) );
P( B, C, D, E, A, R(44) );
P( A, B, C, D, E, R(45) );
P( E, A, B, C, D, R(46) );
P( D, E, A, B, C, R(47) );
P( C, D, E, A, B, R(48) );
P( B, C, D, E, A, R(49) );
P( A, B, C, D, E, R(50) );
P( E, A, B, C, D, R(51) );
P( D, E, A, B, C, R(52) );
P( C, D, E, A, B, R(53) );
P( B, C, D, E, A, R(54) );
P( A, B, C, D, E, R(55) );
P( E, A, B, C, D, R(56) );
P( D, E, A, B, C, R(57) );
P( C, D, E, A, B, R(58) );
P( B, C, D, E, A, R(59) );
#undef K
#undef F
#define F(x,y,z) (x ^ y ^ z)
#define K 0xCA62C1D6
P( A, B, C, D, E, R(60) );
P( E, A, B, C, D, R(61) );
P( D, E, A, B, C, R(62) );
P( C, D, E, A, B, R(63) );
P( B, C, D, E, A, R(64) );
P( A, B, C, D, E, R(65) );
P( E, A, B, C, D, R(66) );
P( D, E, A, B, C, R(67) );
P( C, D, E, A, B, R(68) );
P( B, C, D, E, A, R(69) );
P( A, B, C, D, E, R(70) );
P( E, A, B, C, D, R(71) );
P( D, E, A, B, C, R(72) );
P( C, D, E, A, B, R(73) );
P( B, C, D, E, A, R(74) );
P( A, B, C, D, E, R(75) );
P( E, A, B, C, D, R(76) );
P( D, E, A, B, C, R(77) );
P( C, D, E, A, B, R(78) );
P( B, C, D, E, A, R(79) );
#undef K
#undef F
data->h0 = ctx->h0 + A;
data->h1 = ctx->h1 + B;
data->h2 = ctx->h2 + C;
data->h3 = ctx->h3 + D;
data->h4 = ctx->h4 + E;
}
/* This is the kernel called by the cpu. */
extern "C" __global__
void cuda_pmk_kernel( gpu_inbuffer *inbuffer, gpu_outbuffer *outbuffer) {
int i;
SHA_DEV_CTX temp_ctx, pmk_ctx;
const int idx = blockIdx.x * blockDim.x + threadIdx.x;
CPY_DEVCTX(inbuffer[idx].e1, temp_ctx);
CPY_DEVCTX(temp_ctx, pmk_ctx);
for( i = 0; i < 4096-1; i++ )
{
sha1_process( &inbuffer[idx].ctx_ipad, &temp_ctx);
sha1_process( &inbuffer[idx].ctx_opad, &temp_ctx);
pmk_ctx.h0 ^= temp_ctx.h0; pmk_ctx.h1 ^= temp_ctx.h1;
pmk_ctx.h2 ^= temp_ctx.h2; pmk_ctx.h3 ^= temp_ctx.h3;
pmk_ctx.h4 ^= temp_ctx.h4;
}
CPY_DEVCTX(pmk_ctx, outbuffer[idx].pmk1);
CPY_DEVCTX(inbuffer[idx].e2, temp_ctx);
CPY_DEVCTX(temp_ctx, pmk_ctx);
for( i = 0; i < 4096-1; i++ )
{
sha1_process( &inbuffer[idx].ctx_ipad, &temp_ctx);
sha1_process( &inbuffer[idx].ctx_opad, &temp_ctx);
pmk_ctx.h0 ^= temp_ctx.h0; pmk_ctx.h1 ^= temp_ctx.h1;
pmk_ctx.h2 ^= temp_ctx.h2; pmk_ctx.h3 ^= temp_ctx.h3;
pmk_ctx.h4 ^= temp_ctx.h4;
}
CPY_DEVCTX(pmk_ctx, outbuffer[idx].pmk2);
}
|
