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
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
|
/*
* Implement AES algorithm in Intel AES-NI instructions.
*
* The white paper of AES-NI instructions can be downloaded from:
* http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf
*
* Copyright (C) 2008, Intel Corp.
* Author: Huang Ying <ying.huang@intel.com>
* Vinodh Gopal <vinodh.gopal@intel.com>
* Kahraman Akdemir
*
* 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.
*/
/*
* Modified by Jari Ruusu, October 2009
* - Adapted for loop-AES
*/
/*
* Modified by Jari Ruusu, March 2010
* - Added parallelized 4x512 CBC encrypt
*/
#if !defined(ALIGN64BYTES)
# define ALIGN64BYTES 64
#endif
.file "aes-intel64.S"
.globl intel_aes_cbc_encrypt
.globl intel_aes_cbc_decrypt
.globl intel_aes_cbc_enc_4x512
.text
#define STATE1 %xmm0
#define STATE2 %xmm4
#define STATE3 %xmm5
#define STATE4 %xmm6
#define STATE STATE1
#define IN1 %xmm1
#define IN2 %xmm7
#define IN3 %xmm8
#define IN4 %xmm9
#define IN IN1
#define KEY %xmm2
#define IV %xmm3
#define KEYP %rdi
#define INP %rsi
#define OUTP %rdx
#define LEN %rcx
#define IVP %r8
#define NRND %r9d
#define TKEYP %r10
/*
* void intel_aes_cbc_encrypt(const aes_context *, void *src, void *dst, size_t len, void *iv)
*
* Parameters: %rdi = aes_context *
* %rsi = void *src
* %rdx = void *dst
* %rcx = size_t len
* %r8 = void *iv
*/
.align ALIGN64BYTES
intel_aes_cbc_encrypt:
mov 4(KEYP), NRND
add $8, KEYP
movups (IVP), STATE # load iv as initial state
.align 4
.Lcbc_enc_loop:
movups (INP), IN # load input
pxor IN, STATE
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE # round 0
add $0x30, TKEYP
cmp $12, NRND
jb .Lenc128
lea 0x20(TKEYP), TKEYP
je .Lenc192
add $0x20, TKEYP
movaps -0x60(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps -0x50(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
.align 4
.Lenc192:
movaps -0x40(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps -0x30(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
.align 4
.Lenc128:
movaps -0x20(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps -0x10(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps (TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x10(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x20(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x30(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x40(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x50(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x60(TKEYP), KEY
# aesenc KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc2
movaps 0x70(TKEYP), KEY
# aesenclast KEY, STATE # last round
.byte 0x66, 0x0f, 0x38, 0xdd, 0xc2
movups STATE, (OUTP) # store output
sub $16, LEN
add $16, INP
add $16, OUTP
cmp $16, LEN
jge .Lcbc_enc_loop
emms
ret
/*
* void intel_aes_cbc_decrypt(const aes_context *, void *src, void *dst, size_t len, void *iv)
*
* Parameters: %rdi = aes_context *
* %rsi = void *src
* %rdx = void *dst
* %rcx = size_t len
* %r8 = void *iv
*/
.align ALIGN64BYTES
intel_aes_cbc_decrypt:
mov 4(KEYP), NRND
add $264, KEYP
movups (IVP), IV
cmp $64, LEN
jb .Lcbc_dec_loop1
.align 4
.Lcbc_dec_loop4:
movups (INP), IN1
movaps IN1, STATE1
movups 0x10(INP), IN2
movaps IN2, STATE2
movups 0x20(INP), IN3
movaps IN3, STATE3
movups 0x30(INP), IN4
movaps IN4, STATE4
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE1 # round 0
pxor KEY, STATE2
pxor KEY, STATE3
pxor KEY, STATE4
add $0x30, TKEYP
cmp $12, NRND
jb .L4dec128
lea 0x20(TKEYP), TKEYP
je .L4dec192
add $0x20, TKEYP
movaps -0x60(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps -0x50(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
.align 4
.L4dec192:
movaps -0x40(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps -0x30(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
.align 4
.L4dec128:
movaps -0x20(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps -0x10(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps (TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x10(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x20(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x30(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x40(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x50(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x60(TKEYP), KEY
# aesdec KEY, STATE1
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
# aesdec KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xde, 0xe2
# aesdec KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xde, 0xea
# aesdec KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xde, 0xf2
movaps 0x70(TKEYP), KEY
# aesdeclast KEY, STATE1 # last round
.byte 0x66, 0x0f, 0x38, 0xdf, 0xc2
# aesdeclast KEY, STATE2
.byte 0x66, 0x0f, 0x38, 0xdf, 0xe2
# aesdeclast KEY, STATE3
.byte 0x66, 0x0f, 0x38, 0xdf, 0xea
# aesdeclast KEY, STATE4
.byte 0x66, 0x0f, 0x38, 0xdf, 0xf2
pxor IV, STATE1
pxor IN1, STATE2
pxor IN2, STATE3
pxor IN3, STATE4
movaps IN4, IV
movups STATE1, (OUTP)
movups STATE2, 0x10(OUTP)
movups STATE3, 0x20(OUTP)
movups STATE4, 0x30(OUTP)
sub $64, LEN
add $64, INP
add $64, OUTP
cmp $64, LEN
jge .Lcbc_dec_loop4
cmp $16, LEN
jb .Lcbc_dec_ret
.align 4
.Lcbc_dec_loop1:
movups (INP), IN
movaps IN, STATE
movaps (KEYP), KEY # key
mov KEYP, TKEYP
pxor KEY, STATE # round 0
add $0x30, TKEYP
cmp $12, NRND
jb .Ldec128
lea 0x20(TKEYP), TKEYP
je .Ldec192
add $0x20, TKEYP
movaps -0x60(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps -0x50(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
.align 4
.Ldec192:
movaps -0x40(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps -0x30(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
.align 4
.Ldec128:
movaps -0x20(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps -0x10(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps (TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x10(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x20(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x30(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x40(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x50(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x60(TKEYP), KEY
# aesdec KEY, STATE
.byte 0x66, 0x0f, 0x38, 0xde, 0xc2
movaps 0x70(TKEYP), KEY
# aesdeclast KEY, STATE # last round
.byte 0x66, 0x0f, 0x38, 0xdf, 0xc2
pxor IV, STATE
movups STATE, (OUTP)
movaps IN, IV
sub $16, LEN
add $16, INP
add $16, OUTP
cmp $16, LEN
jge .Lcbc_dec_loop1
.Lcbc_dec_ret:
emms
ret
/*
* void intel_aes_cbc_enc_4x512(aes_context **, void *src, void *dst, void *iv)
*
* Parameters: %rdi = aes_context **
* %rsi = void *src
* %rdx = void *dst
* %rcx = void *iv
*/
.align ALIGN64BYTES
intel_aes_cbc_enc_4x512:
mov (%rdi),%rax # pointer to context struct 1
mov 8(%rdi),%r8 # pointer to context struct 2
mov 16(%rdi),%r9 # pointer to context struct 3
mov 24(%rdi),%r10 # pointer to context struct 4
mov 4(%rax),%edi # number of rounds (10/12/14)
movups (%rcx),%xmm0 # load IV as initial state
movups 0x10(%rcx),%xmm1
movups 0x20(%rcx),%xmm2
movups 0x30(%rcx),%xmm3
sub $10,%edi
mov $0x200,%ecx # 512 byte CBC chain
shl $4,%edi
add $0x38,%edi # 0x38 / 0x58 / 0x78
.align 4
.Lcbc_enc_loop4:
movups (%rsi),%xmm4 # load input
movups 0x200(%rsi),%xmm5
movups 0x400(%rsi),%xmm6
movups 0x600(%rsi),%xmm7
add $16,%rsi
pxor %xmm4,%xmm0 # CBC-mode XOR
pxor %xmm5,%xmm1
pxor %xmm6,%xmm2
pxor %xmm7,%xmm3
movaps 0x08(%rax),%xmm4 # round 0 key
movaps 0x08(%r8),%xmm5
movaps 0x08(%r9),%xmm6
movaps 0x08(%r10),%xmm7
pxor %xmm4,%xmm0 # round 0 XOR
pxor %xmm5,%xmm1
pxor %xmm6,%xmm2
pxor %xmm7,%xmm3
cmp $0x58,%edi
jb .L4enc128
je .L4enc192
movaps -0x60(%rax,%rdi,1),%xmm4
movaps -0x60(%r8,%rdi,1),%xmm5
movaps -0x60(%r9,%rdi,1),%xmm6
movaps -0x60(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps -0x50(%rax,%rdi,1),%xmm4
movaps -0x50(%r8,%rdi,1),%xmm5
movaps -0x50(%r9,%rdi,1),%xmm6
movaps -0x50(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
.align 4
.L4enc192:
movaps -0x40(%rax,%rdi,1),%xmm4
movaps -0x40(%r8,%rdi,1),%xmm5
movaps -0x40(%r9,%rdi,1),%xmm6
movaps -0x40(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps -0x30(%rax,%rdi,1),%xmm4
movaps -0x30(%r8,%rdi,1),%xmm5
movaps -0x30(%r9,%rdi,1),%xmm6
movaps -0x30(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
.align 4
.L4enc128:
movaps -0x20(%rax,%rdi,1),%xmm4
movaps -0x20(%r8,%rdi,1),%xmm5
movaps -0x20(%r9,%rdi,1),%xmm6
movaps -0x20(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps -0x10(%rax,%rdi,1),%xmm4
movaps -0x10(%r8,%rdi,1),%xmm5
movaps -0x10(%r9,%rdi,1),%xmm6
movaps -0x10(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps (%rax,%rdi,1),%xmm4
movaps (%r8,%rdi,1),%xmm5
movaps (%r9,%rdi,1),%xmm6
movaps (%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x10(%rax,%rdi,1),%xmm4
movaps 0x10(%r8,%rdi,1),%xmm5
movaps 0x10(%r9,%rdi,1),%xmm6
movaps 0x10(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x20(%rax,%rdi,1),%xmm4
movaps 0x20(%r8,%rdi,1),%xmm5
movaps 0x20(%r9,%rdi,1),%xmm6
movaps 0x20(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x30(%rax,%rdi,1),%xmm4
movaps 0x30(%r8,%rdi,1),%xmm5
movaps 0x30(%r9,%rdi,1),%xmm6
movaps 0x30(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x40(%rax,%rdi,1),%xmm4
movaps 0x40(%r8,%rdi,1),%xmm5
movaps 0x40(%r9,%rdi,1),%xmm6
movaps 0x40(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x50(%rax,%rdi,1),%xmm4
movaps 0x50(%r8,%rdi,1),%xmm5
movaps 0x50(%r9,%rdi,1),%xmm6
movaps 0x50(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x60(%rax,%rdi,1),%xmm4
movaps 0x60(%r8,%rdi,1),%xmm5
movaps 0x60(%r9,%rdi,1),%xmm6
movaps 0x60(%r10,%rdi,1),%xmm7
# aesenc %xmm4,%xmm0
.byte 0x66, 0x0f, 0x38, 0xdc, 0xc4
# aesenc %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdc, 0xcd
# aesenc %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdc, 0xd6
# aesenc %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdc, 0xdf
movaps 0x70(%rax,%rdi,1),%xmm4
movaps 0x70(%r8,%rdi,1),%xmm5
movaps 0x70(%r9,%rdi,1),%xmm6
movaps 0x70(%r10,%rdi,1),%xmm7
# aesenclast %xmm4,%xmm0 # last round
.byte 0x66, 0x0f, 0x38, 0xdd, 0xc4
# aesenclast %xmm5,%xmm1
.byte 0x66, 0x0f, 0x38, 0xdd, 0xcd
# aesenclast %xmm6,%xmm2
.byte 0x66, 0x0f, 0x38, 0xdd, 0xd6
# aesenclast %xmm7,%xmm3
.byte 0x66, 0x0f, 0x38, 0xdd, 0xdf
sub $16,%ecx
movups %xmm0,(%rdx) # store output
movups %xmm1,0x200(%rdx)
movups %xmm2,0x400(%rdx)
movups %xmm3,0x600(%rdx)
add $16,%rdx
cmp $16,%ecx
jge .Lcbc_enc_loop4
emms
ret
#if defined(__ELF__) && defined(SECTION_NOTE_GNU_STACK)
.section .note.GNU-stack,"",@progbits
#endif
|
