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
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
|
; /*aes_asm . asm
; *
; *Copyright[C]2006 -2014 wolfSSL Inc .
; *
; *This file is part of wolfssl. (formerly known as CyaSSL)
; *
; *wolfSSL 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 .
; *
; *wolfSSL ,is distributed in the hope that it will be useful
; *but WITHOUT ANY WARRANTY/ without even the implied warranty of
; *MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE . See the
; *GNU General Public License for more details .
; *
; *You should have received a copy of the GNU General Public License
; *along with this program/ if not, write to the Free Software
; *Foundation,Inc .,51 Franklin Street,Fifth Floor,Boston,MA 02110-1301,USA
; */
;
;
; /*See IntelA dvanced Encryption Standard[AES]Instructions Set White Paper
; *by Israel,Intel Mobility Group Development Center,Israel Shay Gueron
; */
;
; /* This file is in intel asm syntax, see .s for at&t syntax */
;
; /*
; AES_CBC_encrypt[const ,unsigned char*in
; unsigned ,char*out
; unsigned ,char ivec+16
; unsigned ,long length
; const ,unsigned char*KS
; int nr]
; */
_text SEGMENT
AES_CBC_encrypt PROC
;# parameter 1: rdi
;# parameter 2: rsi
;# parameter 3: rdx
;# parameter 4: rcx
;# parameter 5: r8
;# parameter 6: r9d
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
mov rdx,r8
mov rcx,r9
mov r8,[rsp+40]
mov r9d,[rsp+48]
mov r10,rcx
shr rcx,4
shl r10,60
je NO_PARTS
add rcx,1
NO_PARTS:
sub rsi,16
movdqa xmm1,[rdx]
LOOP_1:
pxor xmm1,[rdi]
pxor xmm1,[r8]
add rsi,16
add rdi,16
cmp r9d,12
aesenc xmm1,16[r8]
aesenc xmm1,32[r8]
aesenc xmm1,48[r8]
aesenc xmm1,64[r8]
aesenc xmm1,80[r8]
aesenc xmm1,96[r8]
aesenc xmm1,112[r8]
aesenc xmm1,128[r8]
aesenc xmm1,144[r8]
movdqa xmm2,160[r8]
jb LAST
cmp r9d,14
aesenc xmm1,160[r8]
aesenc xmm1,176[r8]
movdqa xmm2,192[r8]
jb LAST
aesenc xmm1,192[r8]
aesenc xmm1,208[r8]
movdqa xmm2,224[r8]
LAST:
dec rcx
aesenclast xmm1,xmm2
movdqu [rsi],xmm1
jne LOOP_1
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
ret
AES_CBC_encrypt ENDP
; /*
; AES_CBC_decrypt[const ,unsigned char*in
; unsigned ,char*out
; unsigned ,char ivec+16
; unsigned ,long length
; const ,unsigned char*KS
; int nr]
; */
; . globl AES_CBC_decrypt
AES_CBC_decrypt PROC
;# parameter 1: rdi
;# parameter 2: rsi
;# parameter 3: rdx
;# parameter 4: rcx
;# parameter 5: r8
;# parameter 6: r9d
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
mov rdx,r8
mov rcx,r9
mov r8,[rsp+40]
mov r9d,[rsp+48]
; on microsoft xmm6-xmm15 are non volaitle, let's save on stack and restore at end
sub rsp,8+8*16 ; 8 = align stack , 8 xmm6-12,15 16 bytes each
movdqa [rsp+0], xmm6
movdqa [rsp+16], xmm7
movdqa [rsp+32], xmm8
movdqa [rsp+48], xmm9
movdqa [rsp+64], xmm10
movdqa [rsp+80], xmm11
movdqa [rsp+96], xmm12
movdqa [rsp+112], xmm15
mov r10,rcx
shr rcx,4
shl r10,60
je DNO_PARTS_4
add rcx,1
DNO_PARTS_4:
mov r10,rcx
shl r10,62
shr r10,62
shr rcx,2
movdqu xmm5,[rdx]
je DREMAINDER_4
sub rsi,64
DLOOP_4:
movdqu xmm1,[rdi]
movdqu xmm2,16[rdi]
movdqu xmm3,32[rdi]
movdqu xmm4,48[rdi]
movdqa xmm6,xmm1
movdqa xmm7,xmm2
movdqa xmm8,xmm3
movdqa xmm15,xmm4
movdqa xmm9,[r8]
movdqa xmm10,16[r8]
movdqa xmm11,32[r8]
movdqa xmm12,48[r8]
pxor xmm1,xmm9
pxor xmm2,xmm9
pxor xmm3,xmm9
pxor xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
aesdec xmm1,xmm11
aesdec xmm2,xmm11
aesdec xmm3,xmm11
aesdec xmm4,xmm11
aesdec xmm1,xmm12
aesdec xmm2,xmm12
aesdec xmm3,xmm12
aesdec xmm4,xmm12
movdqa xmm9,64[r8]
movdqa xmm10,80[r8]
movdqa xmm11,96[r8]
movdqa xmm12,112[r8]
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
aesdec xmm1,xmm11
aesdec xmm2,xmm11
aesdec xmm3,xmm11
aesdec xmm4,xmm11
aesdec xmm1,xmm12
aesdec xmm2,xmm12
aesdec xmm3,xmm12
aesdec xmm4,xmm12
movdqa xmm9,128[r8]
movdqa xmm10,144[r8]
movdqa xmm11,160[r8]
cmp r9d,12
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
jb DLAST_4
movdqa xmm9,160[r8]
movdqa xmm10,176[r8]
movdqa xmm11,192[r8]
cmp r9d,14
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
jb DLAST_4
movdqa xmm9,192[r8]
movdqa xmm10,208[r8]
movdqa xmm11,224[r8]
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
DLAST_4:
add rdi,64
add rsi,64
dec rcx
aesdeclast xmm1,xmm11
aesdeclast xmm2,xmm11
aesdeclast xmm3,xmm11
aesdeclast xmm4,xmm11
pxor xmm1,xmm5
pxor xmm2,xmm6
pxor xmm3,xmm7
pxor xmm4,xmm8
movdqu [rsi],xmm1
movdqu 16[rsi],xmm2
movdqu 32[rsi],xmm3
movdqu 48[rsi],xmm4
movdqa xmm5,xmm15
jne DLOOP_4
add rsi,64
DREMAINDER_4:
cmp r10,0
je DEND_4
DLOOP_4_2:
movdqu xmm1,[rdi]
movdqa xmm15,xmm1
add rdi,16
pxor xmm1,[r8]
movdqu xmm2,160[r8]
cmp r9d,12
aesdec xmm1,16[r8]
aesdec xmm1,32[r8]
aesdec xmm1,48[r8]
aesdec xmm1,64[r8]
aesdec xmm1,80[r8]
aesdec xmm1,96[r8]
aesdec xmm1,112[r8]
aesdec xmm1,128[r8]
aesdec xmm1,144[r8]
jb DLAST_4_2
movdqu xmm2,192[r8]
cmp r9d,14
aesdec xmm1,160[r8]
aesdec xmm1,176[r8]
jb DLAST_4_2
movdqu xmm2,224[r8]
aesdec xmm1,192[r8]
aesdec xmm1,208[r8]
DLAST_4_2:
aesdeclast xmm1,xmm2
pxor xmm1,xmm5
movdqa xmm5,xmm15
movdqu [rsi],xmm1
add rsi,16
dec r10
jne DLOOP_4_2
DEND_4:
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
; restore non volatile xmms from stack
movdqa xmm6, [rsp+0]
movdqa xmm7, [rsp+16]
movdqa xmm8, [rsp+32]
movdqa xmm9, [rsp+48]
movdqa xmm10, [rsp+64]
movdqa xmm11, [rsp+80]
movdqa xmm12, [rsp+96]
movdqa xmm15, [rsp+112]
add rsp,8+8*16 ; 8 = align stack , 8 xmm6-12,15 16 bytes each
ret
AES_CBC_decrypt ENDP
; /*
; AES_ECB_encrypt[const ,unsigned char*in
; unsigned ,char*out
; unsigned ,long length
; const ,unsigned char*KS
; int nr]
; */
; . globl AES_ECB_encrypt
AES_ECB_encrypt PROC
;# parameter 1: rdi
;# parameter 2: rsi
;# parameter 3: rdx
;# parameter 4: rcx
;# parameter 5: r8d
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
mov rdx,r8
mov rcx,r9
mov r8d,[rsp+40]
; on microsoft xmm6-xmm15 are non volaitle, let's save on stack and restore at end
sub rsp,8+4*16 ; 8 = align stack , 4 xmm9-12, 16 bytes each
movdqa [rsp+0], xmm9
movdqa [rsp+16], xmm10
movdqa [rsp+32], xmm11
movdqa [rsp+48], xmm12
mov r10,rdx
shr rdx,4
shl r10,60
je EECB_NO_PARTS_4
add rdx,1
EECB_NO_PARTS_4:
mov r10,rdx
shl r10,62
shr r10,62
shr rdx,2
je EECB_REMAINDER_4
sub rsi,64
EECB_LOOP_4:
movdqu xmm1,[rdi]
movdqu xmm2,16[rdi]
movdqu xmm3,32[rdi]
movdqu xmm4,48[rdi]
movdqa xmm9,[rcx]
movdqa xmm10,16[rcx]
movdqa xmm11,32[rcx]
movdqa xmm12,48[rcx]
pxor xmm1,xmm9
pxor xmm2,xmm9
pxor xmm3,xmm9
pxor xmm4,xmm9
aesenc xmm1,xmm10
aesenc xmm2,xmm10
aesenc xmm3,xmm10
aesenc xmm4,xmm10
aesenc xmm1,xmm11
aesenc xmm2,xmm11
aesenc xmm3,xmm11
aesenc xmm4,xmm11
aesenc xmm1,xmm12
aesenc xmm2,xmm12
aesenc xmm3,xmm12
aesenc xmm4,xmm12
movdqa xmm9,64[rcx]
movdqa xmm10,80[rcx]
movdqa xmm11,96[rcx]
movdqa xmm12,112[rcx]
aesenc xmm1,xmm9
aesenc xmm2,xmm9
aesenc xmm3,xmm9
aesenc xmm4,xmm9
aesenc xmm1,xmm10
aesenc xmm2,xmm10
aesenc xmm3,xmm10
aesenc xmm4,xmm10
aesenc xmm1,xmm11
aesenc xmm2,xmm11
aesenc xmm3,xmm11
aesenc xmm4,xmm11
aesenc xmm1,xmm12
aesenc xmm2,xmm12
aesenc xmm3,xmm12
aesenc xmm4,xmm12
movdqa xmm9,128[rcx]
movdqa xmm10,144[rcx]
movdqa xmm11,160[rcx]
cmp r8d,12
aesenc xmm1,xmm9
aesenc xmm2,xmm9
aesenc xmm3,xmm9
aesenc xmm4,xmm9
aesenc xmm1,xmm10
aesenc xmm2,xmm10
aesenc xmm3,xmm10
aesenc xmm4,xmm10
jb EECB_LAST_4
movdqa xmm9,160[rcx]
movdqa xmm10,176[rcx]
movdqa xmm11,192[rcx]
cmp r8d,14
aesenc xmm1,xmm9
aesenc xmm2,xmm9
aesenc xmm3,xmm9
aesenc xmm4,xmm9
aesenc xmm1,xmm10
aesenc xmm2,xmm10
aesenc xmm3,xmm10
aesenc xmm4,xmm10
jb EECB_LAST_4
movdqa xmm9,192[rcx]
movdqa xmm10,208[rcx]
movdqa xmm11,224[rcx]
aesenc xmm1,xmm9
aesenc xmm2,xmm9
aesenc xmm3,xmm9
aesenc xmm4,xmm9
aesenc xmm1,xmm10
aesenc xmm2,xmm10
aesenc xmm3,xmm10
aesenc xmm4,xmm10
EECB_LAST_4:
add rdi,64
add rsi,64
dec rdx
aesenclast xmm1,xmm11
aesenclast xmm2,xmm11
aesenclast xmm3,xmm11
aesenclast xmm4,xmm11
movdqu [rsi],xmm1
movdqu 16[rsi],xmm2
movdqu 32[rsi],xmm3
movdqu 48[rsi],xmm4
jne EECB_LOOP_4
add rsi,64
EECB_REMAINDER_4:
cmp r10,0
je EECB_END_4
EECB_LOOP_4_2:
movdqu xmm1,[rdi]
add rdi,16
pxor xmm1,[rcx]
movdqu xmm2,160[rcx]
aesenc xmm1,16[rcx]
aesenc xmm1,32[rcx]
aesenc xmm1,48[rcx]
aesenc xmm1,64[rcx]
aesenc xmm1,80[rcx]
aesenc xmm1,96[rcx]
aesenc xmm1,112[rcx]
aesenc xmm1,128[rcx]
aesenc xmm1,144[rcx]
cmp r8d,12
jb EECB_LAST_4_2
movdqu xmm2,192[rcx]
aesenc xmm1,160[rcx]
aesenc xmm1,176[rcx]
cmp r8d,14
jb EECB_LAST_4_2
movdqu xmm2,224[rcx]
aesenc xmm1,192[rcx]
aesenc xmm1,208[rcx]
EECB_LAST_4_2:
aesenclast xmm1,xmm2
movdqu [rsi],xmm1
add rsi,16
dec r10
jne EECB_LOOP_4_2
EECB_END_4:
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
; restore non volatile xmms from stack
movdqa xmm9, [rsp+0]
movdqa xmm10, [rsp+16]
movdqa xmm11, [rsp+32]
movdqa xmm12, [rsp+48]
add rsp,8+4*16 ; 8 = align stack , 4 xmm9-12 16 bytes each
ret
AES_ECB_encrypt ENDP
; /*
; AES_ECB_decrypt[const ,unsigned char*in
; unsigned ,char*out
; unsigned ,long length
; const ,unsigned char*KS
; int nr]
; */
; . globl AES_ECB_decrypt
AES_ECB_decrypt PROC
;# parameter 1: rdi
;# parameter 2: rsi
;# parameter 3: rdx
;# parameter 4: rcx
;# parameter 5: r8d
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
mov rdx,r8
mov rcx,r9
mov r8d,[rsp+40]
; on microsoft xmm6-xmm15 are non volaitle, let's save on stack and restore at end
sub rsp,8+4*16 ; 8 = align stack , 4 xmm9-12, 16 bytes each
movdqa [rsp+0], xmm9
movdqa [rsp+16], xmm10
movdqa [rsp+32], xmm11
movdqa [rsp+48], xmm12
mov r10,rdx
shr rdx,4
shl r10,60
je DECB_NO_PARTS_4
add rdx,1
DECB_NO_PARTS_4:
mov r10,rdx
shl r10,62
shr r10,62
shr rdx,2
je DECB_REMAINDER_4
sub rsi,64
DECB_LOOP_4:
movdqu xmm1,[rdi]
movdqu xmm2,16[rdi]
movdqu xmm3,32[rdi]
movdqu xmm4,48[rdi]
movdqa xmm9,[rcx]
movdqa xmm10,16[rcx]
movdqa xmm11,32[rcx]
movdqa xmm12,48[rcx]
pxor xmm1,xmm9
pxor xmm2,xmm9
pxor xmm3,xmm9
pxor xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
aesdec xmm1,xmm11
aesdec xmm2,xmm11
aesdec xmm3,xmm11
aesdec xmm4,xmm11
aesdec xmm1,xmm12
aesdec xmm2,xmm12
aesdec xmm3,xmm12
aesdec xmm4,xmm12
movdqa xmm9,64[rcx]
movdqa xmm10,80[rcx]
movdqa xmm11,96[rcx]
movdqa xmm12,112[rcx]
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
aesdec xmm1,xmm11
aesdec xmm2,xmm11
aesdec xmm3,xmm11
aesdec xmm4,xmm11
aesdec xmm1,xmm12
aesdec xmm2,xmm12
aesdec xmm3,xmm12
aesdec xmm4,xmm12
movdqa xmm9,128[rcx]
movdqa xmm10,144[rcx]
movdqa xmm11,160[rcx]
cmp r8d,12
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
jb DECB_LAST_4
movdqa xmm9,160[rcx]
movdqa xmm10,176[rcx]
movdqa xmm11,192[rcx]
cmp r8d,14
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
jb DECB_LAST_4
movdqa xmm9,192[rcx]
movdqa xmm10,208[rcx]
movdqa xmm11,224[rcx]
aesdec xmm1,xmm9
aesdec xmm2,xmm9
aesdec xmm3,xmm9
aesdec xmm4,xmm9
aesdec xmm1,xmm10
aesdec xmm2,xmm10
aesdec xmm3,xmm10
aesdec xmm4,xmm10
DECB_LAST_4:
add rdi,64
add rsi,64
dec rdx
aesdeclast xmm1,xmm11
aesdeclast xmm2,xmm11
aesdeclast xmm3,xmm11
aesdeclast xmm4,xmm11
movdqu [rsi],xmm1
movdqu 16[rsi],xmm2
movdqu 32[rsi],xmm3
movdqu 48[rsi],xmm4
jne DECB_LOOP_4
add rsi,64
DECB_REMAINDER_4:
cmp r10,0
je DECB_END_4
DECB_LOOP_4_2:
movdqu xmm1,[rdi]
add rdi,16
pxor xmm1,[rcx]
movdqu xmm2,160[rcx]
cmp r8d,12
aesdec xmm1,16[rcx]
aesdec xmm1,32[rcx]
aesdec xmm1,48[rcx]
aesdec xmm1,64[rcx]
aesdec xmm1,80[rcx]
aesdec xmm1,96[rcx]
aesdec xmm1,112[rcx]
aesdec xmm1,128[rcx]
aesdec xmm1,144[rcx]
jb DECB_LAST_4_2
cmp r8d,14
movdqu xmm2,192[rcx]
aesdec xmm1,160[rcx]
aesdec xmm1,176[rcx]
jb DECB_LAST_4_2
movdqu xmm2,224[rcx]
aesdec xmm1,192[rcx]
aesdec xmm1,208[rcx]
DECB_LAST_4_2:
aesdeclast xmm1,xmm2
movdqu [rsi],xmm1
add rsi,16
dec r10
jne DECB_LOOP_4_2
DECB_END_4:
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
; restore non volatile xmms from stack
movdqa xmm9, [rsp+0]
movdqa xmm10, [rsp+16]
movdqa xmm11, [rsp+32]
movdqa xmm12, [rsp+48]
add rsp,8+4*16 ; 8 = align stack , 4 xmm9-12 16 bytes each
ret
AES_ECB_decrypt ENDP
; /*
; void ,AES_128_Key_Expansion[const unsigned char*userkey
; unsigned char*key_schedule]/
; */
; . align 16,0x90
; . globl AES_128_Key_Expansion
AES_128_Key_Expansion PROC
;# parameter 1: rdi
;# parameter 2: rsi
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
mov dword ptr 240[rsi],10
movdqu xmm1,[rdi]
movdqa [rsi],xmm1
ASSISTS:
aeskeygenassist xmm2,xmm1,1
call PREPARE_ROUNDKEY_128
movdqa 16[rsi],xmm1
aeskeygenassist xmm2,xmm1,2
call PREPARE_ROUNDKEY_128
movdqa 32[rsi],xmm1
aeskeygenassist xmm2,xmm1,4
call PREPARE_ROUNDKEY_128
movdqa 48[rsi],xmm1
aeskeygenassist xmm2,xmm1,8
call PREPARE_ROUNDKEY_128
movdqa 64[rsi],xmm1
aeskeygenassist xmm2,xmm1,16
call PREPARE_ROUNDKEY_128
movdqa 80[rsi],xmm1
aeskeygenassist xmm2,xmm1,32
call PREPARE_ROUNDKEY_128
movdqa 96[rsi],xmm1
aeskeygenassist xmm2,xmm1,64
call PREPARE_ROUNDKEY_128
movdqa 112[rsi],xmm1
aeskeygenassist xmm2,xmm1,80h
call PREPARE_ROUNDKEY_128
movdqa 128[rsi],xmm1
aeskeygenassist xmm2,xmm1,1bh
call PREPARE_ROUNDKEY_128
movdqa 144[rsi],xmm1
aeskeygenassist xmm2,xmm1,36h
call PREPARE_ROUNDKEY_128
movdqa 160[rsi],xmm1
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
ret
PREPARE_ROUNDKEY_128:
pshufd xmm2,xmm2,255
movdqa xmm3,xmm1
pslldq xmm3,4
pxor xmm1,xmm3
pslldq xmm3,4
pxor xmm1,xmm3
pslldq xmm3,4
pxor xmm1,xmm3
pxor xmm1,xmm2
ret
AES_128_Key_Expansion ENDP
; /*
; void ,AES_192_Key_Expansion[const unsigned char*userkey
; unsigned char*key]
; */
; . globl AES_192_Key_Expansion
AES_192_Key_Expansion PROC
;# parameter 1: rdi
;# parameter 2: rsi
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
; on microsoft xmm6-xmm15 are non volaitle, let's save on stack and restore at end
sub rsp,8+1*16 ; 8 = align stack , 1 xmm6, 16 bytes each
movdqa [rsp+0], xmm6
movdqu xmm1,[rdi]
movdqu xmm3,16[rdi]
movdqa [rsi],xmm1
movdqa xmm5,xmm3
aeskeygenassist xmm2,xmm3,1h
call PREPARE_ROUNDKEY_192
shufpd xmm5,xmm1,0
movdqa 16[rsi],xmm5
movdqa xmm6,xmm1
shufpd xmm6,xmm3,1
movdqa 32[rsi],xmm6
aeskeygenassist xmm2,xmm3,2h
call PREPARE_ROUNDKEY_192
movdqa 48[rsi],xmm1
movdqa xmm5,xmm3
aeskeygenassist xmm2,xmm3,4h
call PREPARE_ROUNDKEY_192
shufpd xmm5,xmm1,0
movdqa 64[rsi],xmm5
movdqa xmm6,xmm1
shufpd xmm6,xmm3,1
movdqa 80[rsi],xmm6
aeskeygenassist xmm2,xmm3,8h
call PREPARE_ROUNDKEY_192
movdqa 96[rsi],xmm1
movdqa xmm5,xmm3
aeskeygenassist xmm2,xmm3,10h
call PREPARE_ROUNDKEY_192
shufpd xmm5,xmm1,0
movdqa 112[rsi],xmm5
movdqa xmm6,xmm1
shufpd xmm6,xmm3,1
movdqa 128[rsi],xmm6
aeskeygenassist xmm2,xmm3,20h
call PREPARE_ROUNDKEY_192
movdqa 144[rsi],xmm1
movdqa xmm5,xmm3
aeskeygenassist xmm2,xmm3,40h
call PREPARE_ROUNDKEY_192
shufpd xmm5,xmm1,0
movdqa 160[rsi],xmm5
movdqa xmm6,xmm1
shufpd xmm6,xmm3,1
movdqa 176[rsi],xmm6
aeskeygenassist xmm2,xmm3,80h
call PREPARE_ROUNDKEY_192
movdqa 192[rsi],xmm1
movdqa 208[rsi],xmm3
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
; restore non volatile xmms from stack
movdqa xmm6, [rsp+0]
add rsp,8+1*16 ; 8 = align stack , 1 xmm6 16 bytes each
ret
PREPARE_ROUNDKEY_192:
pshufd xmm2,xmm2,55h
movdqu xmm4,xmm1
pslldq xmm4,4
pxor xmm1,xmm4
pslldq xmm4,4
pxor xmm1,xmm4
pslldq xmm4,4
pxor xmm1,xmm4
pxor xmm1,xmm2
pshufd xmm2,xmm1,0ffh
movdqu xmm4,xmm3
pslldq xmm4,4
pxor xmm3,xmm4
pxor xmm3,xmm2
ret
AES_192_Key_Expansion ENDP
; /*
; void ,AES_256_Key_Expansion[const unsigned char*userkey
; unsigned char*key]
; */
; . globl AES_256_Key_Expansion
AES_256_Key_Expansion PROC
;# parameter 1: rdi
;# parameter 2: rsi
; save rdi and rsi to rax and r11, restore before ret
mov rax,rdi
mov r11,rsi
; convert to what we had for att&t convention
mov rdi,rcx
mov rsi,rdx
movdqu xmm1,[rdi]
movdqu xmm3,16[rdi]
movdqa [rsi],xmm1
movdqa 16[rsi],xmm3
aeskeygenassist xmm2,xmm3,1h
call MAKE_RK256_a
movdqa 32[rsi],xmm1
aeskeygenassist xmm2,xmm1,0h
call MAKE_RK256_b
movdqa 48[rsi],xmm3
aeskeygenassist xmm2,xmm3,2h
call MAKE_RK256_a
movdqa 64[rsi],xmm1
aeskeygenassist xmm2,xmm1,0h
call MAKE_RK256_b
movdqa 80[rsi],xmm3
aeskeygenassist xmm2,xmm3,4h
call MAKE_RK256_a
movdqa 96[rsi],xmm1
aeskeygenassist xmm2,xmm1,0h
call MAKE_RK256_b
movdqa 112[rsi],xmm3
aeskeygenassist xmm2,xmm3,8h
call MAKE_RK256_a
movdqa 128[rsi],xmm1
aeskeygenassist xmm2,xmm1,0h
call MAKE_RK256_b
movdqa 144[rsi],xmm3
aeskeygenassist xmm2,xmm3,10h
call MAKE_RK256_a
movdqa 160[rsi],xmm1
aeskeygenassist xmm2,xmm1,0h
call MAKE_RK256_b
movdqa 176[rsi],xmm3
aeskeygenassist xmm2,xmm3,20h
call MAKE_RK256_a
movdqa 192[rsi],xmm1
aeskeygenassist xmm2,xmm1,0h
call MAKE_RK256_b
movdqa 208[rsi],xmm3
aeskeygenassist xmm2,xmm3,40h
call MAKE_RK256_a
movdqa 224[rsi],xmm1
; restore non volatile rdi,rsi
mov rdi,rax
mov rsi,r11
ret
AES_256_Key_Expansion ENDP
MAKE_RK256_a:
pshufd xmm2,xmm2,0ffh
movdqa xmm4,xmm1
pslldq xmm4,4
pxor xmm1,xmm4
pslldq xmm4,4
pxor xmm1,xmm4
pslldq xmm4,4
pxor xmm1,xmm4
pxor xmm1,xmm2
ret
MAKE_RK256_b:
pshufd xmm2,xmm2,0aah
movdqa xmm4,xmm3
pslldq xmm4,4
pxor xmm3,xmm4
pslldq xmm4,4
pxor xmm3,xmm4
pslldq xmm4,4
pxor xmm3,xmm4
pxor xmm3,xmm2
ret
END
|
