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
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
|
[bits 64]
[CPU intelnop]
; Copyright (c) 2010, Intel Corporation
; All rights reserved.
;
; Redistribution and use in source and binary forms, with or without
; modification, are permitted provided that the following conditions are met:
;
; * Redistributions of source code must retain the above copyright notice,
; this list of conditions and the following disclaimer.
; * Redistributions in binary form must reproduce the above copyright notice,
; this list of conditions and the following disclaimer in the documentation
; and/or other materials provided with the distribution.
; * Neither the name of Intel Corporation nor the names of its contributors
; may be used to endorse or promote products derived from this software
; without specific prior written permission.
;
; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
; ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
; WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
; IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
; INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
; BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
; DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
; LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
; OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
; ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
%define iEncExpandKey128 k5_iEncExpandKey128
%define iEncExpandKey256 k5_iEncExpandKey256
%define iDecExpandKey128 k5_iDecExpandKey128
%define iDecExpandKey256 k5_iDecExpandKey256
%define iEnc128_CBC k5_iEnc128_CBC
%define iEnc256_CBC k5_iEnc256_CBC
%define iDec128_CBC k5_iDec128_CBC
%define iDec256_CBC k5_iDec256_CBC
%macro linux_setup 0
%ifdef __linux__
mov rcx, rdi
mov rdx, rsi
%endif
%endmacro
%macro inversekey 1
movdqu xmm1,%1
aesimc xmm0,xmm1
movdqu %1,xmm0
%endmacro
%macro aesdeclast1 1
aesdeclast xmm0,%1
%endmacro
%macro aesenclast1 1
aesenclast xmm0,%1
%endmacro
%macro aesdec1 1
aesdec xmm0,%1
%endmacro
%macro aesenc1 1
aesenc xmm0,%1
%endmacro
%macro aesdeclast1_u 1
movdqu xmm4,%1
aesdeclast xmm0,xmm4
%endmacro
%macro aesenclast1_u 1
movdqu xmm4,%1
aesenclast xmm0,xmm4
%endmacro
%macro aesdec1_u 1
movdqu xmm4,%1
aesdec xmm0,xmm4
%endmacro
%macro aesenc1_u 1
movdqu xmm4,%1
aesenc xmm0,xmm4
%endmacro
%macro aesdec4 1
movdqa xmm4,%1
aesdec xmm0,xmm4
aesdec xmm1,xmm4
aesdec xmm2,xmm4
aesdec xmm3,xmm4
%endmacro
%macro aesdeclast4 1
movdqa xmm4,%1
aesdeclast xmm0,xmm4
aesdeclast xmm1,xmm4
aesdeclast xmm2,xmm4
aesdeclast xmm3,xmm4
%endmacro
%macro aesenc4 1
movdqa xmm4,%1
aesenc xmm0,xmm4
aesenc xmm1,xmm4
aesenc xmm2,xmm4
aesenc xmm3,xmm4
%endmacro
%macro aesenclast4 1
movdqa xmm4,%1
aesenclast xmm0,xmm4
aesenclast xmm1,xmm4
aesenclast xmm2,xmm4
aesenclast xmm3,xmm4
%endmacro
%macro load_and_inc4 1
movdqa xmm4,%1
movdqa xmm0,xmm5
pshufb xmm0, xmm6 ; byte swap counter back
movdqa xmm1,xmm5
paddd xmm1,[counter_add_one wrt rip]
pshufb xmm1, xmm6 ; byte swap counter back
movdqa xmm2,xmm5
paddd xmm2,[counter_add_two wrt rip]
pshufb xmm2, xmm6 ; byte swap counter back
movdqa xmm3,xmm5
paddd xmm3,[counter_add_three wrt rip]
pshufb xmm3, xmm6 ; byte swap counter back
pxor xmm0,xmm4
paddd xmm5,[counter_add_four wrt rip]
pxor xmm1,xmm4
pxor xmm2,xmm4
pxor xmm3,xmm4
%endmacro
%macro xor_with_input4 1
movdqu xmm4,[%1]
pxor xmm0,xmm4
movdqu xmm4,[%1+16]
pxor xmm1,xmm4
movdqu xmm4,[%1+32]
pxor xmm2,xmm4
movdqu xmm4,[%1+48]
pxor xmm3,xmm4
%endmacro
%macro load_and_xor4 2
movdqa xmm4,%2
movdqu xmm0,[%1 + 0*16]
pxor xmm0,xmm4
movdqu xmm1,[%1 + 1*16]
pxor xmm1,xmm4
movdqu xmm2,[%1 + 2*16]
pxor xmm2,xmm4
movdqu xmm3,[%1 + 3*16]
pxor xmm3,xmm4
%endmacro
%macro store4 1
movdqu [%1 + 0*16],xmm0
movdqu [%1 + 1*16],xmm1
movdqu [%1 + 2*16],xmm2
movdqu [%1 + 3*16],xmm3
%endmacro
%macro copy_round_keys 3
movdqu xmm4,[%2 + ((%3)*16)]
movdqa [%1 + ((%3)*16)],xmm4
%endmacro
%macro key_expansion_1_192 1
;; Assumes the xmm3 includes all zeros at this point.
pshufd xmm2, xmm2, 11111111b
shufps xmm3, xmm1, 00010000b
pxor xmm1, xmm3
shufps xmm3, xmm1, 10001100b
pxor xmm1, xmm3
pxor xmm1, xmm2
movdqu [rdx+%1], xmm1
%endmacro
; Calculate w10 and w11 using calculated w9 and known w4-w5
%macro key_expansion_2_192 1
movdqa xmm5, xmm4
pslldq xmm5, 4
shufps xmm6, xmm1, 11110000b
pxor xmm6, xmm5
pxor xmm4, xmm6
pshufd xmm7, xmm4, 00001110b
movdqu [rdx+%1], xmm7
%endmacro
section .data
align 16
shuffle_mask:
DD 0FFFFFFFFh
DD 03020100h
DD 07060504h
DD 0B0A0908h
byte_swap_16:
DDQ 0x000102030405060708090A0B0C0D0E0F
align 16
counter_add_one:
DD 1
DD 0
DD 0
DD 0
counter_add_two:
DD 2
DD 0
DD 0
DD 0
counter_add_three:
DD 3
DD 0
DD 0
DD 0
counter_add_four:
DD 4
DD 0
DD 0
DD 0
section .text
align 16
key_expansion256:
pshufd xmm2, xmm2, 011111111b
movdqa xmm4, xmm1
pshufb xmm4, xmm5
pxor xmm1, xmm4
pshufb xmm4, xmm5
pxor xmm1, xmm4
pshufb xmm4, xmm5
pxor xmm1, xmm4
pxor xmm1, xmm2
movdqu [rdx], xmm1
add rdx, 0x10
aeskeygenassist xmm4, xmm1, 0
pshufd xmm2, xmm4, 010101010b
movdqa xmm4, xmm3
pshufb xmm4, xmm5
pxor xmm3, xmm4
pshufb xmm4, xmm5
pxor xmm3, xmm4
pshufb xmm4, xmm5
pxor xmm3, xmm4
pxor xmm3, xmm2
movdqu [rdx], xmm3
add rdx, 0x10
ret
align 16
key_expansion128:
pshufd xmm2, xmm2, 0xFF;
movdqa xmm3, xmm1
pshufb xmm3, xmm5
pxor xmm1, xmm3
pshufb xmm3, xmm5
pxor xmm1, xmm3
pshufb xmm3, xmm5
pxor xmm1, xmm3
pxor xmm1, xmm2
; storing the result in the key schedule array
movdqu [rdx], xmm1
add rdx, 0x10
ret
align 16
global iEncExpandKey128
iEncExpandKey128:
linux_setup
movdqu xmm1, [rcx] ; loading the key
movdqu [rdx], xmm1
movdqa xmm5, [shuffle_mask wrt rip]
add rdx,16
aeskeygenassist xmm2, xmm1, 0x1 ; Generating round key 1
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x2 ; Generating round key 2
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x4 ; Generating round key 3
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x8 ; Generating round key 4
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x10 ; Generating round key 5
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x20 ; Generating round key 6
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x40 ; Generating round key 7
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x80 ; Generating round key 8
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x1b ; Generating round key 9
call key_expansion128
aeskeygenassist xmm2, xmm1, 0x36 ; Generating round key 10
call key_expansion128
ret
align 16
global iDecExpandKey128
iDecExpandKey128:
linux_setup
push rcx
push rdx
sub rsp,16+8
call iEncExpandKey128
add rsp,16+8
pop rdx
pop rcx
inversekey [rdx + 1*16]
inversekey [rdx + 2*16]
inversekey [rdx + 3*16]
inversekey [rdx + 4*16]
inversekey [rdx + 5*16]
inversekey [rdx + 6*16]
inversekey [rdx + 7*16]
inversekey [rdx + 8*16]
inversekey [rdx + 9*16]
ret
align 16
global iDecExpandKey256
iDecExpandKey256:
linux_setup
push rcx
push rdx
sub rsp,16+8
call iEncExpandKey256
add rsp,16+8
pop rdx
pop rcx
inversekey [rdx + 1*16]
inversekey [rdx + 2*16]
inversekey [rdx + 3*16]
inversekey [rdx + 4*16]
inversekey [rdx + 5*16]
inversekey [rdx + 6*16]
inversekey [rdx + 7*16]
inversekey [rdx + 8*16]
inversekey [rdx + 9*16]
inversekey [rdx + 10*16]
inversekey [rdx + 11*16]
inversekey [rdx + 12*16]
inversekey [rdx + 13*16]
ret
align 16
global iEncExpandKey256
iEncExpandKey256:
linux_setup
movdqu xmm1, [rcx] ; loading the key
movdqu xmm3, [rcx+16]
movdqu [rdx], xmm1 ; Storing key in memory where all key schedule will be stored
movdqu [rdx+16], xmm3
add rdx,32
movdqa xmm5, [shuffle_mask wrt rip] ; this mask is used by key_expansion
aeskeygenassist xmm2, xmm3, 0x1 ;
call key_expansion256
aeskeygenassist xmm2, xmm3, 0x2 ;
call key_expansion256
aeskeygenassist xmm2, xmm3, 0x4 ;
call key_expansion256
aeskeygenassist xmm2, xmm3, 0x8 ;
call key_expansion256
aeskeygenassist xmm2, xmm3, 0x10 ;
call key_expansion256
aeskeygenassist xmm2, xmm3, 0x20 ;
call key_expansion256
aeskeygenassist xmm2, xmm3, 0x40 ;
; call key_expansion256
pshufd xmm2, xmm2, 011111111b
movdqa xmm4, xmm1
pshufb xmm4, xmm5
pxor xmm1, xmm4
pshufb xmm4, xmm5
pxor xmm1, xmm4
pshufb xmm4, xmm5
pxor xmm1, xmm4
pxor xmm1, xmm2
movdqu [rdx], xmm1
ret
align 16
global iDec128_CBC
iDec128_CBC:
linux_setup
sub rsp,16*16+8
mov r9,rcx
mov rax,[rcx+24]
movdqu xmm5,[rax]
mov eax,[rcx+32] ; numblocks
mov rdx,[rcx]
mov r8,[rcx+8]
mov rcx,[rcx+16]
sub r8,rdx
test eax,eax
jz end_dec128_CBC
cmp eax,4
jl lp128decsingle_CBC
test rcx,0xf
jz lp128decfour_CBC
copy_round_keys rsp,rcx,0
copy_round_keys rsp,rcx,1
copy_round_keys rsp,rcx,2
copy_round_keys rsp,rcx,3
copy_round_keys rsp,rcx,4
copy_round_keys rsp,rcx,5
copy_round_keys rsp,rcx,6
copy_round_keys rsp,rcx,7
copy_round_keys rsp,rcx,8
copy_round_keys rsp,rcx,9
copy_round_keys rsp,rcx,10
mov rcx,rsp
align 16
lp128decfour_CBC:
test eax,eax
jz end_dec128_CBC
cmp eax,4
jl lp128decsingle_CBC
load_and_xor4 rdx, [rcx+10*16]
add rdx,16*4
aesdec4 [rcx+9*16]
aesdec4 [rcx+8*16]
aesdec4 [rcx+7*16]
aesdec4 [rcx+6*16]
aesdec4 [rcx+5*16]
aesdec4 [rcx+4*16]
aesdec4 [rcx+3*16]
aesdec4 [rcx+2*16]
aesdec4 [rcx+1*16]
aesdeclast4 [rcx+0*16]
pxor xmm0,xmm5
movdqu xmm4,[rdx - 16*4 + 0*16]
pxor xmm1,xmm4
movdqu xmm4,[rdx - 16*4 + 1*16]
pxor xmm2,xmm4
movdqu xmm4,[rdx - 16*4 + 2*16]
pxor xmm3,xmm4
movdqu xmm5,[rdx - 16*4 + 3*16]
sub eax,4
store4 r8+rdx-(16*4)
jmp lp128decfour_CBC
align 16
lp128decsingle_CBC:
movdqu xmm0, [rdx]
movdqa xmm1,xmm0
movdqu xmm4,[rcx+10*16]
pxor xmm0, xmm4
aesdec1_u [rcx+9*16]
aesdec1_u [rcx+8*16]
aesdec1_u [rcx+7*16]
aesdec1_u [rcx+6*16]
aesdec1_u [rcx+5*16]
aesdec1_u [rcx+4*16]
aesdec1_u [rcx+3*16]
aesdec1_u [rcx+2*16]
aesdec1_u [rcx+1*16]
aesdeclast1_u [rcx+0*16]
pxor xmm0,xmm5
movdqa xmm5,xmm1
add rdx, 16
movdqu [r8 + rdx - 16], xmm0
dec eax
jnz lp128decsingle_CBC
end_dec128_CBC:
mov r9,[r9+24]
movdqu [r9],xmm5
add rsp,16*16+8
ret
align 16
global iDec256_CBC
iDec256_CBC:
linux_setup
sub rsp,16*16+8
mov r9,rcx
mov rax,[rcx+24]
movdqu xmm5,[rax]
mov eax,[rcx+32] ; numblocks
mov rdx,[rcx]
mov r8,[rcx+8]
mov rcx,[rcx+16]
sub r8,rdx
test eax,eax
jz end_dec256_CBC
cmp eax,4
jl lp256decsingle_CBC
test rcx,0xf
jz lp256decfour_CBC
copy_round_keys rsp,rcx,0
copy_round_keys rsp,rcx,1
copy_round_keys rsp,rcx,2
copy_round_keys rsp,rcx,3
copy_round_keys rsp,rcx,4
copy_round_keys rsp,rcx,5
copy_round_keys rsp,rcx,6
copy_round_keys rsp,rcx,7
copy_round_keys rsp,rcx,8
copy_round_keys rsp,rcx,9
copy_round_keys rsp,rcx,10
copy_round_keys rsp,rcx,11
copy_round_keys rsp,rcx,12
copy_round_keys rsp,rcx,13
copy_round_keys rsp,rcx,14
mov rcx,rsp
align 16
lp256decfour_CBC:
test eax,eax
jz end_dec256_CBC
cmp eax,4
jl lp256decsingle_CBC
load_and_xor4 rdx, [rcx+14*16]
add rdx,16*4
aesdec4 [rcx+13*16]
aesdec4 [rcx+12*16]
aesdec4 [rcx+11*16]
aesdec4 [rcx+10*16]
aesdec4 [rcx+9*16]
aesdec4 [rcx+8*16]
aesdec4 [rcx+7*16]
aesdec4 [rcx+6*16]
aesdec4 [rcx+5*16]
aesdec4 [rcx+4*16]
aesdec4 [rcx+3*16]
aesdec4 [rcx+2*16]
aesdec4 [rcx+1*16]
aesdeclast4 [rcx+0*16]
pxor xmm0,xmm5
movdqu xmm4,[rdx - 16*4 + 0*16]
pxor xmm1,xmm4
movdqu xmm4,[rdx - 16*4 + 1*16]
pxor xmm2,xmm4
movdqu xmm4,[rdx - 16*4 + 2*16]
pxor xmm3,xmm4
movdqu xmm5,[rdx - 16*4 + 3*16]
sub eax,4
store4 r8+rdx-(16*4)
jmp lp256decfour_CBC
align 16
lp256decsingle_CBC:
movdqu xmm0, [rdx]
movdqu xmm4,[rcx+14*16]
movdqa xmm1,xmm0
pxor xmm0, xmm4
aesdec1_u [rcx+13*16]
aesdec1_u [rcx+12*16]
aesdec1_u [rcx+11*16]
aesdec1_u [rcx+10*16]
aesdec1_u [rcx+9*16]
aesdec1_u [rcx+8*16]
aesdec1_u [rcx+7*16]
aesdec1_u [rcx+6*16]
aesdec1_u [rcx+5*16]
aesdec1_u [rcx+4*16]
aesdec1_u [rcx+3*16]
aesdec1_u [rcx+2*16]
aesdec1_u [rcx+1*16]
aesdeclast1_u [rcx+0*16]
pxor xmm0,xmm5
movdqa xmm5,xmm1
add rdx, 16
movdqu [r8 + rdx - 16], xmm0
dec eax
jnz lp256decsingle_CBC
end_dec256_CBC:
mov r9,[r9+24]
movdqu [r9],xmm5
add rsp,16*16+8
ret
align 16
global iEnc128_CBC
iEnc128_CBC:
linux_setup
sub rsp,16*16+8
mov r9,rcx
mov rax,[rcx+24]
movdqu xmm1,[rax]
mov eax,[rcx+32] ; numblocks
mov rdx,[rcx]
mov r8,[rcx+8]
mov rcx,[rcx+16]
sub r8,rdx
test rcx,0xf
jz lp128encsingle_CBC
copy_round_keys rsp,rcx,0
copy_round_keys rsp,rcx,1
copy_round_keys rsp,rcx,2
copy_round_keys rsp,rcx,3
copy_round_keys rsp,rcx,4
copy_round_keys rsp,rcx,5
copy_round_keys rsp,rcx,6
copy_round_keys rsp,rcx,7
copy_round_keys rsp,rcx,8
copy_round_keys rsp,rcx,9
copy_round_keys rsp,rcx,10
mov rcx,rsp
align 16
lp128encsingle_CBC:
movdqu xmm0, [rdx]
movdqu xmm4,[rcx+0*16]
add rdx, 16
pxor xmm0, xmm1
pxor xmm0, xmm4
aesenc1 [rcx+1*16]
aesenc1 [rcx+2*16]
aesenc1 [rcx+3*16]
aesenc1 [rcx+4*16]
aesenc1 [rcx+5*16]
aesenc1 [rcx+6*16]
aesenc1 [rcx+7*16]
aesenc1 [rcx+8*16]
aesenc1 [rcx+9*16]
aesenclast1 [rcx+10*16]
movdqa xmm1,xmm0
; Store output encrypted data into CIPHERTEXT array
movdqu [r8+rdx-16], xmm0
dec eax
jnz lp128encsingle_CBC
mov r9,[r9+24]
movdqu [r9],xmm1
add rsp,16*16+8
ret
align 16
global iEnc256_CBC
iEnc256_CBC:
linux_setup
sub rsp,16*16+8
mov r9,rcx
mov rax,[rcx+24]
movdqu xmm1,[rax]
mov eax,[rcx+32] ; numblocks
mov rdx,[rcx]
mov r8,[rcx+8]
mov rcx,[rcx+16]
sub r8,rdx
test rcx,0xf
jz lp256encsingle_CBC
copy_round_keys rsp,rcx,0
copy_round_keys rsp,rcx,1
copy_round_keys rsp,rcx,2
copy_round_keys rsp,rcx,3
copy_round_keys rsp,rcx,4
copy_round_keys rsp,rcx,5
copy_round_keys rsp,rcx,6
copy_round_keys rsp,rcx,7
copy_round_keys rsp,rcx,8
copy_round_keys rsp,rcx,9
copy_round_keys rsp,rcx,10
copy_round_keys rsp,rcx,11
copy_round_keys rsp,rcx,12
copy_round_keys rsp,rcx,13
copy_round_keys rsp,rcx,14
mov rcx,rsp
align 16
lp256encsingle_CBC:
movdqu xmm0, [rdx]
movdqu xmm4, [rcx+0*16]
add rdx, 16
pxor xmm0, xmm1
pxor xmm0, xmm4
aesenc1 [rcx+1*16]
aesenc1 [rcx+2*16]
aesenc1 [rcx+3*16]
aesenc1 [rcx+4*16]
aesenc1 [rcx+5*16]
aesenc1 [rcx+6*16]
aesenc1 [rcx+7*16]
aesenc1 [rcx+8*16]
aesenc1 [rcx+9*16]
aesenc1 [rcx+10*16]
aesenc1 [rcx+11*16]
aesenc1 [rcx+12*16]
aesenc1 [rcx+13*16]
aesenclast1 [rcx+14*16]
movdqa xmm1,xmm0
; Store output encrypted data into CIPHERTEXT array
movdqu [r8+rdx-16], xmm0
dec eax
jnz lp256encsingle_CBC
mov r9,[r9+24]
movdqu [r9],xmm1
add rsp,16*16+8
ret
|