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
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
|
/* gf128mul.c - GF(2^128) multiplication functions
*
* Copyright (c) 2003, Dr Brian Gladman, Worcester, UK.
* Copyright (c) 2006, Rik Snel <rsnel@cube.dyndns.org>
*
* Based on Dr Brian Gladman's (GPL'd) work published at
* http://gladman.plushost.co.uk/oldsite/cryptography_technology/index.php
* See the original copyright notice below.
*
* This program 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 2 of the License, or (at your option)
* any later version.
*/
/*
---------------------------------------------------------------------------
Copyright (c) 2003, Dr Brian Gladman, Worcester, UK. All rights reserved.
LICENSE TERMS
The free distribution and use of this software in both source and binary
form is allowed (with or without changes) provided that:
1. distributions of this source code include the above copyright
notice, this list of conditions and the following disclaimer;
2. distributions in binary form include the above copyright
notice, this list of conditions and the following disclaimer
in the documentation and/or other associated materials;
3. the copyright holder's name is not used to endorse products
built using this software without specific written permission.
ALTERNATIVELY, provided that this notice is retained in full, this product
may be distributed under the terms of the GNU General Public License (GPL),
in which case the provisions of the GPL apply INSTEAD OF those given above.
DISCLAIMER
This software is provided 'as is' with no explicit or implied warranties
in respect of its properties, including, but not limited to, correctness
and/or fitness for purpose.
---------------------------------------------------------------------------
Issue 31/01/2006
This file provides fast multiplication in GF(128) as required by several
cryptographic authentication modes
*/
#include <crypto/gf128mul.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
#define gf128mul_dat(q) { \
q(0x00), q(0x01), q(0x02), q(0x03), q(0x04), q(0x05), q(0x06), q(0x07),\
q(0x08), q(0x09), q(0x0a), q(0x0b), q(0x0c), q(0x0d), q(0x0e), q(0x0f),\
q(0x10), q(0x11), q(0x12), q(0x13), q(0x14), q(0x15), q(0x16), q(0x17),\
q(0x18), q(0x19), q(0x1a), q(0x1b), q(0x1c), q(0x1d), q(0x1e), q(0x1f),\
q(0x20), q(0x21), q(0x22), q(0x23), q(0x24), q(0x25), q(0x26), q(0x27),\
q(0x28), q(0x29), q(0x2a), q(0x2b), q(0x2c), q(0x2d), q(0x2e), q(0x2f),\
q(0x30), q(0x31), q(0x32), q(0x33), q(0x34), q(0x35), q(0x36), q(0x37),\
q(0x38), q(0x39), q(0x3a), q(0x3b), q(0x3c), q(0x3d), q(0x3e), q(0x3f),\
q(0x40), q(0x41), q(0x42), q(0x43), q(0x44), q(0x45), q(0x46), q(0x47),\
q(0x48), q(0x49), q(0x4a), q(0x4b), q(0x4c), q(0x4d), q(0x4e), q(0x4f),\
q(0x50), q(0x51), q(0x52), q(0x53), q(0x54), q(0x55), q(0x56), q(0x57),\
q(0x58), q(0x59), q(0x5a), q(0x5b), q(0x5c), q(0x5d), q(0x5e), q(0x5f),\
q(0x60), q(0x61), q(0x62), q(0x63), q(0x64), q(0x65), q(0x66), q(0x67),\
q(0x68), q(0x69), q(0x6a), q(0x6b), q(0x6c), q(0x6d), q(0x6e), q(0x6f),\
q(0x70), q(0x71), q(0x72), q(0x73), q(0x74), q(0x75), q(0x76), q(0x77),\
q(0x78), q(0x79), q(0x7a), q(0x7b), q(0x7c), q(0x7d), q(0x7e), q(0x7f),\
q(0x80), q(0x81), q(0x82), q(0x83), q(0x84), q(0x85), q(0x86), q(0x87),\
q(0x88), q(0x89), q(0x8a), q(0x8b), q(0x8c), q(0x8d), q(0x8e), q(0x8f),\
q(0x90), q(0x91), q(0x92), q(0x93), q(0x94), q(0x95), q(0x96), q(0x97),\
q(0x98), q(0x99), q(0x9a), q(0x9b), q(0x9c), q(0x9d), q(0x9e), q(0x9f),\
q(0xa0), q(0xa1), q(0xa2), q(0xa3), q(0xa4), q(0xa5), q(0xa6), q(0xa7),\
q(0xa8), q(0xa9), q(0xaa), q(0xab), q(0xac), q(0xad), q(0xae), q(0xaf),\
q(0xb0), q(0xb1), q(0xb2), q(0xb3), q(0xb4), q(0xb5), q(0xb6), q(0xb7),\
q(0xb8), q(0xb9), q(0xba), q(0xbb), q(0xbc), q(0xbd), q(0xbe), q(0xbf),\
q(0xc0), q(0xc1), q(0xc2), q(0xc3), q(0xc4), q(0xc5), q(0xc6), q(0xc7),\
q(0xc8), q(0xc9), q(0xca), q(0xcb), q(0xcc), q(0xcd), q(0xce), q(0xcf),\
q(0xd0), q(0xd1), q(0xd2), q(0xd3), q(0xd4), q(0xd5), q(0xd6), q(0xd7),\
q(0xd8), q(0xd9), q(0xda), q(0xdb), q(0xdc), q(0xdd), q(0xde), q(0xdf),\
q(0xe0), q(0xe1), q(0xe2), q(0xe3), q(0xe4), q(0xe5), q(0xe6), q(0xe7),\
q(0xe8), q(0xe9), q(0xea), q(0xeb), q(0xec), q(0xed), q(0xee), q(0xef),\
q(0xf0), q(0xf1), q(0xf2), q(0xf3), q(0xf4), q(0xf5), q(0xf6), q(0xf7),\
q(0xf8), q(0xf9), q(0xfa), q(0xfb), q(0xfc), q(0xfd), q(0xfe), q(0xff) \
}
/* Given the value i in 0..255 as the byte overflow when a field element
in GHASH is multipled by x^8, this function will return the values that
are generated in the lo 16-bit word of the field value by applying the
modular polynomial. The values lo_byte and hi_byte are returned via the
macro xp_fun(lo_byte, hi_byte) so that the values can be assembled into
memory as required by a suitable definition of this macro operating on
the table above
*/
#define xx(p, q) 0x##p##q
#define xda_bbe(i) ( \
(i & 0x80 ? xx(43, 80) : 0) ^ (i & 0x40 ? xx(21, c0) : 0) ^ \
(i & 0x20 ? xx(10, e0) : 0) ^ (i & 0x10 ? xx(08, 70) : 0) ^ \
(i & 0x08 ? xx(04, 38) : 0) ^ (i & 0x04 ? xx(02, 1c) : 0) ^ \
(i & 0x02 ? xx(01, 0e) : 0) ^ (i & 0x01 ? xx(00, 87) : 0) \
)
#define xda_lle(i) ( \
(i & 0x80 ? xx(e1, 00) : 0) ^ (i & 0x40 ? xx(70, 80) : 0) ^ \
(i & 0x20 ? xx(38, 40) : 0) ^ (i & 0x10 ? xx(1c, 20) : 0) ^ \
(i & 0x08 ? xx(0e, 10) : 0) ^ (i & 0x04 ? xx(07, 08) : 0) ^ \
(i & 0x02 ? xx(03, 84) : 0) ^ (i & 0x01 ? xx(01, c2) : 0) \
)
static const u16 gf128mul_table_lle[256] = gf128mul_dat(xda_lle);
static const u16 gf128mul_table_bbe[256] = gf128mul_dat(xda_bbe);
/* These functions multiply a field element by x, by x^4 and by x^8
* in the polynomial field representation. It uses 32-bit word operations
* to gain speed but compensates for machine endianess and hence works
* correctly on both styles of machine.
*/
static void gf128mul_x_lle(be128 *r, const be128 *x)
{
u64 a = be64_to_cpu(x->a);
u64 b = be64_to_cpu(x->b);
u64 _tt = gf128mul_table_lle[(b << 7) & 0xff];
r->b = cpu_to_be64((b >> 1) | (a << 63));
r->a = cpu_to_be64((a >> 1) ^ (_tt << 48));
}
static void gf128mul_x_bbe(be128 *r, const be128 *x)
{
u64 a = be64_to_cpu(x->a);
u64 b = be64_to_cpu(x->b);
u64 _tt = gf128mul_table_bbe[a >> 63];
r->a = cpu_to_be64((a << 1) | (b >> 63));
r->b = cpu_to_be64((b << 1) ^ _tt);
}
void gf128mul_x_ble(be128 *r, const be128 *x)
{
u64 a = le64_to_cpu(x->a);
u64 b = le64_to_cpu(x->b);
u64 _tt = gf128mul_table_bbe[b >> 63];
r->a = cpu_to_le64((a << 1) ^ _tt);
r->b = cpu_to_le64((b << 1) | (a >> 63));
}
EXPORT_SYMBOL(gf128mul_x_ble);
static void gf128mul_x8_lle(be128 *x)
{
u64 a = be64_to_cpu(x->a);
u64 b = be64_to_cpu(x->b);
u64 _tt = gf128mul_table_lle[b & 0xff];
x->b = cpu_to_be64((b >> 8) | (a << 56));
x->a = cpu_to_be64((a >> 8) ^ (_tt << 48));
}
static void gf128mul_x8_bbe(be128 *x)
{
u64 a = be64_to_cpu(x->a);
u64 b = be64_to_cpu(x->b);
u64 _tt = gf128mul_table_bbe[a >> 56];
x->a = cpu_to_be64((a << 8) | (b >> 56));
x->b = cpu_to_be64((b << 8) ^ _tt);
}
void gf128mul_lle(be128 *r, const be128 *b)
{
be128 p[8];
int i;
p[0] = *r;
for (i = 0; i < 7; ++i)
gf128mul_x_lle(&p[i + 1], &p[i]);
memset(r, 0, sizeof(r));
for (i = 0;;) {
u8 ch = ((u8 *)b)[15 - i];
if (ch & 0x80)
be128_xor(r, r, &p[0]);
if (ch & 0x40)
be128_xor(r, r, &p[1]);
if (ch & 0x20)
be128_xor(r, r, &p[2]);
if (ch & 0x10)
be128_xor(r, r, &p[3]);
if (ch & 0x08)
be128_xor(r, r, &p[4]);
if (ch & 0x04)
be128_xor(r, r, &p[5]);
if (ch & 0x02)
be128_xor(r, r, &p[6]);
if (ch & 0x01)
be128_xor(r, r, &p[7]);
if (++i >= 16)
break;
gf128mul_x8_lle(r);
}
}
EXPORT_SYMBOL(gf128mul_lle);
void gf128mul_bbe(be128 *r, const be128 *b)
{
be128 p[8];
int i;
p[0] = *r;
for (i = 0; i < 7; ++i)
gf128mul_x_bbe(&p[i + 1], &p[i]);
memset(r, 0, sizeof(r));
for (i = 0;;) {
u8 ch = ((u8 *)b)[i];
if (ch & 0x80)
be128_xor(r, r, &p[7]);
if (ch & 0x40)
be128_xor(r, r, &p[6]);
if (ch & 0x20)
be128_xor(r, r, &p[5]);
if (ch & 0x10)
be128_xor(r, r, &p[4]);
if (ch & 0x08)
be128_xor(r, r, &p[3]);
if (ch & 0x04)
be128_xor(r, r, &p[2]);
if (ch & 0x02)
be128_xor(r, r, &p[1]);
if (ch & 0x01)
be128_xor(r, r, &p[0]);
if (++i >= 16)
break;
gf128mul_x8_bbe(r);
}
}
EXPORT_SYMBOL(gf128mul_bbe);
/* This version uses 64k bytes of table space.
A 16 byte buffer has to be multiplied by a 16 byte key
value in GF(128). If we consider a GF(128) value in
the buffer's lowest byte, we can construct a table of
the 256 16 byte values that result from the 256 values
of this byte. This requires 4096 bytes. But we also
need tables for each of the 16 higher bytes in the
buffer as well, which makes 64 kbytes in total.
*/
/* additional explanation
* t[0][BYTE] contains g*BYTE
* t[1][BYTE] contains g*x^8*BYTE
*
|