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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
|
#include <tommath_private.h>
#ifdef BN_S_MP_EXPTMOD_C
/* LibTomMath, multiple-precision integer library -- Tom St Denis
*
* LibTomMath is a library that provides multiple-precision
* integer arithmetic as well as number theoretic functionality.
*
* The library was designed directly after the MPI library by
* Michael Fromberger but has been written from scratch with
* additional optimizations in place.
*
* The library is free for all purposes without any express
* guarantee it works.
*
* Tom St Denis, tstdenis82@gmail.com, http://libtom.org
*/
#ifdef MP_LOW_MEM
#define TAB_SIZE 32
#else
#define TAB_SIZE 256
#endif
int s_mp_exptmod (mp_int * G, mp_int * X, mp_int * P, mp_int * Y, int redmode)
{
mp_int M[TAB_SIZE], res, mu;
mp_digit buf;
int err, bitbuf, bitcpy, bitcnt, mode, digidx, x, y, winsize;
int (*redux)(mp_int*,mp_int*,mp_int*);
/* find window size */
x = mp_count_bits (X);
if (x <= 7) {
winsize = 2;
} else if (x <= 36) {
winsize = 3;
} else if (x <= 140) {
winsize = 4;
} else if (x <= 450) {
winsize = 5;
} else if (x <= 1303) {
winsize = 6;
} else if (x <= 3529) {
winsize = 7;
} else {
winsize = 8;
}
#ifdef MP_LOW_MEM
if (winsize > 5) {
winsize = 5;
}
#endif
/* init M array */
/* init first cell */
if ((err = mp_init(&M[1])) != MP_OKAY) {
return err;
}
/* now init the second half of the array */
for (x = 1<<(winsize-1); x < (1 << winsize); x++) {
if ((err = mp_init(&M[x])) != MP_OKAY) {
for (y = 1<<(winsize-1); y < x; y++) {
mp_clear (&M[y]);
}
mp_clear(&M[1]);
return err;
}
}
/* create mu, used for Barrett reduction */
if ((err = mp_init (&mu)) != MP_OKAY) {
goto LBL_M;
}
if (redmode == 0) {
if ((err = mp_reduce_setup (&mu, P)) != MP_OKAY) {
goto LBL_MU;
}
redux = mp_reduce;
} else {
if ((err = mp_reduce_2k_setup_l (P, &mu)) != MP_OKAY) {
goto LBL_MU;
}
redux = mp_reduce_2k_l;
}
/* create M table
*
* The M table contains powers of the base,
* e.g. M[x] = G**x mod P
*
* The first half of the table is not
* computed though accept for M[0] and M[1]
*/
if ((err = mp_mod (G, P, &M[1])) != MP_OKAY) {
goto LBL_MU;
}
/* compute the value at M[1<<(winsize-1)] by squaring
* M[1] (winsize-1) times
*/
if ((err = mp_copy (&M[1], &M[1 << (winsize - 1)])) != MP_OKAY) {
goto LBL_MU;
}
for (x = 0; x < (winsize - 1); x++) {
/* square it */
if ((err = mp_sqr (&M[1 << (winsize - 1)],
&M[1 << (winsize - 1)])) != MP_OKAY) {
goto LBL_MU;
}
/* reduce modulo P */
if ((err = redux (&M[1 << (winsize - 1)], P, &mu)) != MP_OKAY) {
goto LBL_MU;
}
}
/* create upper table, that is M[x] = M[x-1] * M[1] (mod P)
* for x = (2**(winsize - 1) + 1) to (2**winsize - 1)
*/
for (x = (1 << (winsize - 1)) + 1; x < (1 << winsize); x++) {
if ((err = mp_mul (&M[x - 1], &M[1], &M[x])) != MP_OKAY) {
goto LBL_MU;
}
if ((err = redux (&M[x], P, &mu)) != MP_OKAY) {
goto LBL_MU;
}
}
/* setup result */
if ((err = mp_init (&res)) != MP_OKAY) {
goto LBL_MU;
}
mp_set (&res, 1);
/* set initial mode and bit cnt */
mode = 0;
bitcnt = 1;
buf = 0;
digidx = X->used - 1;
bitcpy = 0;
bitbuf = 0;
for (;;) {
/* grab next digit as required */
if (--bitcnt == 0) {
/* if digidx == -1 we are out of digits */
if (digidx == -1) {
break;
}
/* read next digit and reset the bitcnt */
buf = X->dp[digidx--];
bitcnt = (int) DIGIT_BIT;
}
/* grab the next msb from the exponent */
y = (buf >> (mp_digit)(DIGIT_BIT - 1)) & 1;
buf <<= (mp_digit)1;
/* if the bit is zero and mode == 0 then we ignore it
* These represent the leading zero bits before the first 1 bit
* in the exponent. Technically this opt is not required but it
* does lower the # of trivial squaring/reductions used
*/
if ((mode == 0) && (y == 0)) {
continue;
}
/* if the bit is zero and mode == 1 then we square */
if ((mode == 1) && (y == 0)) {
if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
goto LBL_RES;
}
if ((err = redux (&res, P, &mu)) != MP_OKAY) {
goto LBL_RES;
}
continue;
}
/* else we add it to the window */
bitbuf |= (y << (winsize - ++bitcpy));
mode = 2;
if (bitcpy == winsize) {
/* ok window is filled so square as required and multiply */
/* square first */
for (x = 0; x < winsize; x++) {
if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
goto LBL_RES;
}
if ((err = redux (&res, P, &mu)) != MP_OKAY) {
goto LBL_RES;
}
}
/* then multiply */
if ((err = mp_mul (&res, &M[bitbuf], &res)) != MP_OKAY) {
goto LBL_RES;
}
if ((err = redux (&res, P, &mu)) != MP_OKAY) {
goto LBL_RES;
}
/* empty window and reset */
bitcpy = 0;
bitbuf = 0;
mode = 1;
}
}
/* if bits remain then square/multiply */
if ((mode == 2) && (bitcpy > 0)) {
/* square then multiply if the bit is set */
for (x = 0; x < bitcpy; x++) {
if ((err = mp_sqr (&res, &res)) != MP_OKAY) {
goto LBL_RES;
}
if ((err = redux (&res, P, &mu)) != MP_OKAY) {
goto LBL_RES;
}
bitbuf <<= 1;
if ((bitbuf & (1 << winsize)) != 0) {
/* then multiply */
if ((err = mp_mul (&res, &M[1], &res)) != MP_OKAY) {
goto LBL_RES;
}
if ((err = redux (&res, P, &mu)) != MP_OKAY) {
goto LBL_RES;
}
}
}
}
mp_exch (&res, Y);
err = MP_OKAY;
LBL_RES:mp_clear (&res);
LBL_MU:mp_clear (&mu);
LBL_M:
mp_clear(&M[1]);
for (x = 1<<(winsize-1); x < (1 << winsize); x++) {
mp_clear (&M[x]);
}
return err;
}
#endif
/* ref: tag: v1.0.1, master */
/* git commit: 5953f62e42b24af93748b1ee5e1d062e242c2546 */
/* commit time: 2017-08-29 22:27:36 +0200 */
|
