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
478
479
480
481
482
483
484
485
486
487
|
/*
-------------------------------------------------------------------------
Copyright (c) 2001, Dr Brian Gladman <brg@gladman.uk.net>, 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.
DISCLAIMER
This software is provided 'as is' with no explcit or implied warranties
in respect of any properties, including, but not limited to, correctness
and fitness for purpose.
-------------------------------------------------------------------------
Issue Date: 21/01/2002
This file contains the code for implementing encryption and decryption
for AES (Rijndael) for block and key sizes of 16, 20, 24, 28 and 32 bytes.
It can optionally be replaced by code written in assembler using NASM.
*/
#include "aesopt.h"
#define unused 77 /* Sunset Strip */
#define si(y,x,k,c) s(y,c) = word_in(x + 4 * c) ^ k[c]
#define so(y,x,c) word_out(y + 4 * c, s(x,c))
#if BLOCK_SIZE == 16
#if defined(ARRAYS)
#define locals(y,x) x[4],y[4]
#else
#define locals(y,x) x##0,x##1,x##2,x##3,y##0,y##1,y##2,y##3
/*
the following defines prevent the compiler requiring the declaration
of generated but unused variables in the fwd_var and inv_var macros
*/
#define b04 unused
#define b05 unused
#define b06 unused
#define b07 unused
#define b14 unused
#define b15 unused
#define b16 unused
#define b17 unused
#endif
#define l_copy(y, x) s(y,0) = s(x,0); s(y,1) = s(x,1); \
s(y,2) = s(x,2); s(y,3) = s(x,3);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3)
#define state_out(y,x) so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3)
#elif BLOCK_SIZE == 20
#if defined(ARRAYS)
#define locals(y,x) x[5],y[5]
#else
#define locals(y,x) x##0,x##1,x##2,x##3,x##4,y##0,y##1,y##2,y##3,y##4
#define b05 unused
#define b06 unused
#define b07 unused
#define b15 unused
#define b16 unused
#define b17 unused
#endif
#define l_copy(y, x) s(y,0) = s(x,0); s(y,1) = s(x,1); \
s(y,2) = s(x,2); s(y,3) = s(x,3); s(y,4) = s(x,4);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3); si(y,x,k,4)
#define state_out(y,x) so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3); so(y,x,4)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3); rm(y,x,k,4)
#elif BLOCK_SIZE == 24
#if defined(ARRAYS)
#define locals(y,x) x[6],y[6]
#else
#define locals(y,x) x##0,x##1,x##2,x##3,x##4,x##5, \
y##0,y##1,y##2,y##3,y##4,y##5
#define b06 unused
#define b07 unused
#define b16 unused
#define b17 unused
#endif
#define l_copy(y, x) s(y,0) = s(x,0); s(y,1) = s(x,1); \
s(y,2) = s(x,2); s(y,3) = s(x,3); \
s(y,4) = s(x,4); s(y,5) = s(x,5);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); \
si(y,x,k,3); si(y,x,k,4); si(y,x,k,5)
#define state_out(y,x) so(y,x,0); so(y,x,1); so(y,x,2); \
so(y,x,3); so(y,x,4); so(y,x,5)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); \
rm(y,x,k,3); rm(y,x,k,4); rm(y,x,k,5)
#elif BLOCK_SIZE == 28
#if defined(ARRAYS)
#define locals(y,x) x[7],y[7]
#else
#define locals(y,x) x##0,x##1,x##2,x##3,x##4,x##5,x##6 \
y##0,y##1,y##2,y##3,y##4,y##5,y##6
#define b07 unused
#define b17 unused
#endif
#define l_copy(y, x) s(y,0) = s(x,0); s(y,1) = s(x,1); \
s(y,2) = s(x,2); s(y,3) = s(x,3); \
s(y,4) = s(x,4); s(y,5) = s(x,5);; s(y,6) = s(x,6);
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); \
si(y,x,k,3); si(y,x,k,4); si(y,x,k,5); si(y,x,k,6)
#define state_out(y,x) so(y,x,0); so(y,x,1); so(y,x,2); \
so(y,x,3); so(y,x,4); so(y,x,5); so(y,x,6)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); \
rm(y,x,k,3); rm(y,x,k,4); rm(y,x,k,5); rm(y,x,k,6)
#else
#if defined(ARRAYS)
#define locals(y,x) x[8],y[8]
#else
#define locals(y,x) x##0,x##1,x##2,x##3,x##4,x##5,x##6,x##7, \
y##0,y##1,y##2,y##3,y##4,y##5,y##6,y##7
#endif
#define l_copy(y, x) s(y,0) = s(x,0); s(y,1) = s(x,1); \
s(y,2) = s(x,2); s(y,3) = s(x,3); \
s(y,4) = s(x,4); s(y,5) = s(x,5); \
s(y,6) = s(x,6); s(y,7) = s(x,7);
#if BLOCK_SIZE == 32
#define state_in(y,x,k) si(y,x,k,0); si(y,x,k,1); si(y,x,k,2); si(y,x,k,3); \
si(y,x,k,4); si(y,x,k,5); si(y,x,k,6); si(y,x,k,7)
#define state_out(y,x) so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3); \
so(y,x,4); so(y,x,5); so(y,x,6); so(y,x,7)
#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3); \
rm(y,x,k,4); rm(y,x,k,5); rm(y,x,k,6); rm(y,x,k,7)
#else
#define state_in(y,x,k) \
switch(nc) \
{ case 8: si(y,x,k,7); \
case 7: si(y,x,k,6); \
case 6: si(y,x,k,5); \
case 5: si(y,x,k,4); \
case 4: si(y,x,k,3); si(y,x,k,2); \
si(y,x,k,1); si(y,x,k,0); \
}
#define state_out(y,x) \
switch(nc) \
{ case 8: so(y,x,7); \
case 7: so(y,x,6); \
case 6: so(y,x,5); \
case 5: so(y,x,4); \
case 4: so(y,x,3); so(y,x,2); \
so(y,x,1); so(y,x,0); \
}
#if defined(FAST_VARIABLE)
#define round(rm,y,x,k) \
switch(nc) \
{ case 8: rm(y,x,k,7); rm(y,x,k,6); \
rm(y,x,k,5); rm(y,x,k,4); \
rm(y,x,k,3); rm(y,x,k,2); \
rm(y,x,k,1); rm(y,x,k,0); \
break; \
case 7: rm(y,x,k,6); rm(y,x,k,5); \
rm(y,x,k,4); rm(y,x,k,3); \
rm(y,x,k,2); rm(y,x,k,1); \
rm(y,x,k,0); \
break; \
case 6: rm(y,x,k,5); rm(y,x,k,4); \
rm(y,x,k,3); rm(y,x,k,2); \
rm(y,x,k,1); rm(y,x,k,0); \
break; \
case 5: rm(y,x,k,4); rm(y,x,k,3); \
rm(y,x,k,2); rm(y,x,k,1); \
rm(y,x,k,0); \
break; \
case 4: rm(y,x,k,3); rm(y,x,k,2); \
rm(y,x,k,1); rm(y,x,k,0); \
break; \
}
#else
#define round(rm,y,x,k) \
switch(nc) \
{ case 8: rm(y,x,k,7); \
case 7: rm(y,x,k,6); \
case 6: rm(y,x,k,5); \
case 5: rm(y,x,k,4); \
case 4: rm(y,x,k,3); rm(y,x,k,2); \
rm(y,x,k,1); rm(y,x,k,0); \
}
#endif
#endif
#endif
#if defined(ENCRYPTION)
/* I am grateful to Frank Yellin for the following construction
(and that for decryption) which, given the column (c) of the
output state variable, gives the input state variables which
are needed for each row (r) of the state.
For the fixed block size options, compilers should reduce these
two expressions to fixed variable references. But for variable
block size code conditional clauses will sometimes be returned.
y = output word, x = input word, r = row, c = column for r = 0,
1, 2 and 3 = column accessed for row r.
*/
#define fwd_var(x,r,c) \
( r==0 ? \
( c==0 ? s(x,0) \
: c==1 ? s(x,1) \
: c==2 ? s(x,2) \
: c==3 ? s(x,3) \
: c==4 ? s(x,4) \
: c==5 ? s(x,5) \
: c==6 ? s(x,6) \
: s(x,7)) \
: r==1 ? \
( c==0 ? s(x,1) \
: c==1 ? s(x,2) \
: c==2 ? s(x,3) \
: c==3 ? nc==4 ? s(x,0) : s(x,4) \
: c==4 ? nc==5 ? s(x,0) : s(x,5) \
: c==5 ? nc==6 ? s(x,0) : s(x,6) \
: c==6 ? nc==7 ? s(x,0) : s(x,7) \
: s(x,0)) \
: r==2 ? \
( c==0 ? nc==8 ? s(x,3) : s(x,2) \
: c==1 ? nc==8 ? s(x,4) : s(x,3) \
: c==2 ? nc==8 ? s(x,5) : nc==4 ? s(x,0) : s(x,4) \
: c==3 ? nc==8 ? s(x,6) : nc==5 ? s(x,0) : nc==4 ? s(x,1) : s(x,5) \
: c==4 ? nc==8 ? s(x,7) : nc==7 ? s(x,6) : nc==6 ? s(x,0) : s(x,1) \
: c==5 ? nc==6 ? s(x,1) : s(x,0) \
: c==6 ? s(x,1) \
: s(x,2)) \
: \
( c==0 ? nc>6 ? s(x,4) : s(x,3) \
: c==1 ? nc>6 ? s(x,5) : nc==4 ? s(x,0) : s(x,4) \
: c==2 ? nc>6 ? s(x,6) : nc==6 ? s(x,5) : nc==5 ? s(x,0) : s(x,1) \
: c==3 ? nc==8 ? s(x,7) : nc==5 ? s(x,1) : nc==4 ? s(x,2) : s(x,0) \
: c==4 ? nc==8 ? s(x,0) : nc==5 ? s(x,2) : s(x,1) \
: c==5 ? nc==8 ? s(x,1) : s(x,2) \
: c==6 ? nc==8 ? s(x,2) : s(x,3) \
: s(x,3)))
#if defined(FT4_SET)
#undef dec_fmvars
#define dec_fmvars
#define fwd_rnd(y,x,k,c) s(y,c)= (k)[c] ^ four_tables(x,ft_tab,fwd_var,rf1,c)
#elif defined(FT1_SET)
#undef dec_fmvars
#define dec_fmvars
#define fwd_rnd(y,x,k,c) s(y,c)= (k)[c] ^ one_table(x,upr,ft_tab,fwd_var,rf1,c)
#else
#define fwd_rnd(y,x,k,c) s(y,c) = fwd_mcol(no_table(x,s_box,fwd_var,rf1,c)) ^ (k)[c]
#endif
#if defined(FL4_SET)
#define fwd_lrnd(y,x,k,c) s(y,c)= (k)[c] ^ four_tables(x,fl_tab,fwd_var,rf1,c)
#elif defined(FL1_SET)
#define fwd_lrnd(y,x,k,c) s(y,c)= (k)[c] ^ one_table(x,ups,fl_tab,fwd_var,rf1,c)
#else
#define fwd_lrnd(y,x,k,c) s(y,c) = no_table(x,s_box,fwd_var,rf1,c) ^ (k)[c]
#endif
aes_rval aes_enc_blk(const unsigned char in_blk[], unsigned char out_blk[], const aes_ctx cx[1])
{ uint32_t locals(b0, b1);
const uint32_t *kp = cx->k_sch;
dec_fmvars /* declare variables for fwd_mcol() if needed */
if(!(cx->n_blk & 1)) return aes_bad;
#if (ENC_UNROLL == FULL)
state_in((cx->n_rnd & 1 ? b1 : b0), in_blk, kp);
kp += (cx->n_rnd - 9) * nc;
switch(cx->n_rnd)
{
case 14: round(fwd_rnd, b1, b0, kp - 4 * nc);
case 13: round(fwd_rnd, b0, b1, kp - 3 * nc);
case 12: round(fwd_rnd, b1, b0, kp - 2 * nc);
case 11: round(fwd_rnd, b0, b1, kp - nc);
case 10: round(fwd_rnd, b1, b0, kp );
round(fwd_rnd, b0, b1, kp + nc);
round(fwd_rnd, b1, b0, kp + 2 * nc);
round(fwd_rnd, b0, b1, kp + 3 * nc);
round(fwd_rnd, b1, b0, kp + 4 * nc);
round(fwd_rnd, b0, b1, kp + 5 * nc);
round(fwd_rnd, b1, b0, kp + 6 * nc);
round(fwd_rnd, b0, b1, kp + 7 * nc);
round(fwd_rnd, b1, b0, kp + 8 * nc);
round(fwd_lrnd, b0, b1, kp + 9 * nc);
}
#else
{ uint32_t rnd;
state_in(b0, in_blk, kp);
#if (ENC_UNROLL == PARTIAL)
for(rnd = 0; rnd < (cx->n_rnd - 1) >> 1; ++rnd)
{
kp += nc;
round(fwd_rnd, b1, b0, kp);
kp += nc;
round(fwd_rnd, b0, b1, kp);
}
if(cx->n_rnd & 1)
{
l_copy(b1, b0);
}
else
{
kp += nc;
round(fwd_rnd, b1, b0, kp);
}
#else
for(rnd = 0; rnd < cx->n_rnd - 1; ++rnd)
{
kp += nc;
round(fwd_rnd, b1, b0, kp);
l_copy(b0, b1);
}
#endif
kp += nc;
round(fwd_lrnd, b0, b1, kp);
}
#endif
state_out(out_blk, b0);
return aes_good;
}
#endif
#if defined(DECRYPTION)
#define inv_var(x,r,c) \
( r==0 ? \
( c==0 ? s(x,0) \
: c==1 ? s(x,1) \
: c==2 ? s(x,2) \
: c==3 ? s(x,3) \
: c==4 ? s(x,4) \
: c==5 ? s(x,5) \
: c==6 ? s(x,6) \
: s(x,7)) \
: r==1 ? \
( c==0 ? nc==8 ? s(x,7) : nc==7 ? s(x,6) : nc==6 ? s(x,5) : nc==5 ? s(x,4) : s(x,3) \
: c==1 ? s(x,0) \
: c==2 ? s(x,1) \
: c==3 ? s(x,2) \
: c==4 ? s(x,3) \
: c==5 ? s(x,4) \
: c==6 ? s(x,5) \
: s(x,6)) \
: r==2 ? \
( c==0 ? nc>6 ? s(x,5) : nc==6 ? s(x,4) : nc==5 ? s(x,3) : s(x,2) \
: c==1 ? nc>6 ? s(x,6) : nc==6 ? s(x,5) : nc==5 ? s(x,4) : s(x,3) \
: c==2 ? nc==8 ? s(x,7) : s(x,0) \
: c==3 ? nc==8 ? s(x,0) : s(x,1) \
: c==4 ? nc==8 ? s(x,1) : s(x,2) \
: c==5 ? nc==8 ? s(x,2) : s(x,3) \
: c==6 ? nc==8 ? s(x,3) : s(x,4) \
: s(x,4)) \
: \
( c==0 ? nc==8 ? s(x,4) : nc==5 ? s(x,2) : nc==4 ? s(x,1) : s(x,3) \
: c==1 ? nc==8 ? s(x,5) : nc==5 ? s(x,3) : nc==4 ? s(x,2) : s(x,4) \
: c==2 ? nc==8 ? s(x,6) : nc==5 ? s(x,4) : nc==4 ? s(x,3) : s(x,5) \
: c==3 ? nc==8 ? s(x,7) : nc==7 ? s(x,6) : s(x,0) \
: c==4 ? nc>6 ? s(x,0) : s(x,1) \
: c==5 ? nc==6 ? s(x,2) : s(x,1) \
: c==6 ? s(x,2) \
: s(x,3)))
#if defined(IT4_SET)
#undef dec_imvars
#define dec_imvars
#define inv_rnd(y,x,k,c) s(y,c)= (k)[c] ^ four_tables(x,it_tab,inv_var,rf1,c)
#elif defined(IT1_SET)
#undef dec_imvars
#define dec_imvars
#define inv_rnd(y,x,k,c) s(y,c)= (k)[c] ^ one_table(x,upr,it_tab,inv_var,rf1,c)
#else
#define inv_rnd(y,x,k,c) s(y,c) = inv_mcol(no_table(x,inv_s_box,inv_var,rf1,c) ^ (k)[c])
#endif
#if defined(IL4_SET)
#define inv_lrnd(y,x,k,c) s(y,c)= (k)[c] ^ four_tables(x,il_tab,inv_var,rf1,c)
#elif defined(IL1_SET)
#define inv_lrnd(y,x,k,c) s(y,c)= (k)[c] ^ one_table(x,ups,il_tab,inv_var,rf1,c)
#else
#define inv_lrnd(y,x,k,c) s(y,c) = no_table(x,inv_s_box,inv_var,rf1,c) ^ (k)[c]
#endif
aes_rval aes_dec_blk(const unsigned char in_blk[], unsigned char out_blk[], const aes_ctx cx[1])
{ uint32_t locals(b0, b1);
const uint32_t *kp = cx->k_sch + nc * cx->n_rnd;
dec_imvars /* declare variables for inv_mcol() if needed */
if(!(cx->n_blk & 2)) return aes_bad;
#if (DEC_UNROLL == FULL)
state_in((cx->n_rnd & 1 ? b1 : b0), in_blk, kp);
kp = cx->k_sch + 9 * nc;
switch(cx->n_rnd)
{
case 14: round(inv_rnd, b1, b0, kp + 4 * nc);
case 13: round(inv_rnd, b0, b1, kp + 3 * nc);
case 12: round(inv_rnd, b1, b0, kp + 2 * nc);
case 11: round(inv_rnd, b0, b1, kp + nc);
case 10: round(inv_rnd, b1, b0, kp );
round(inv_rnd, b0, b1, kp - nc);
round(inv_rnd, b1, b0, kp - 2 * nc);
round(inv_rnd, b0, b1, kp - 3 * nc);
round(inv_rnd, b1, b0, kp - 4 * nc);
round(inv_rnd, b0, b1, kp - 5 * nc);
round(inv_rnd, b1, b0, kp - 6 * nc);
round(inv_rnd, b0, b1, kp - 7 * nc);
round(inv_rnd, b1, b0, kp - 8 * nc);
round(inv_lrnd, b0, b1, kp - 9 * nc);
}
#else
{ uint32_t rnd;
state_in(b0, in_blk, kp);
#if (DEC_UNROLL == PARTIAL)
for(rnd = 0; rnd < (cx->n_rnd - 1) >> 1; ++rnd)
{
kp -= nc;
round(inv_rnd, b1, b0, kp);
kp -= nc;
round(inv_rnd, b0, b1, kp);
}
if(cx->n_rnd & 1)
{
l_copy(b1, b0);
}
else
{
kp -= nc;
round(inv_rnd, b1, b0, kp);
}
#else
for(rnd = 0; rnd < cx->n_rnd - 1; ++rnd)
{
kp -= nc;
round(inv_rnd, b1, b0, kp);
l_copy(b0, b1);
}
#endif
kp -= nc;
round(inv_lrnd, b0, b1, kp);
}
#endif
state_out(out_blk, b0);
return aes_good;
}
#endif
|
