summaryrefslogtreecommitdiffstats
path: root/security/nss/lib/freebl/intel-aes-x64-masm.asm
blob: ef5c76ba28370882583003116b9aeeb3505e256d (plain)
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
; LICENSE:
; This submission to NSS is to be made available under the terms of the
; Mozilla Public License, v. 2.0. You can obtain one at http:
; //mozilla.org/MPL/2.0/.
;###############################################################################
; Copyright(c) 2014, Intel Corp.
; Developers and authors:
; Shay Gueron and Vlad Krasnov
; Intel Corporation, Israel Development Centre, Haifa, Israel
; Please send feedback directly to crypto.feedback.alias@intel.com


.DATA
ALIGN 16
Lmask dd 0c0f0e0dh,0c0f0e0dh,0c0f0e0dh,0c0f0e0dh
Lmask192 dd 004070605h, 004070605h, 004070605h, 004070605h
Lmask256 dd 00c0f0e0dh, 00c0f0e0dh, 00c0f0e0dh, 00c0f0e0dh
Lcon1 dd 1,1,1,1
Lcon2 dd 1bh,1bh,1bh,1bh

.CODE

ctx     textequ <rcx>
output  textequ <rdx>
input   textequ <r8>
inputLen textequ <r9d>


aes_rnd MACRO i
    movdqu  xmm8, [i*16 + ctx]
    aesenc  xmm0, xmm8
    aesenc  xmm1, xmm8
    aesenc  xmm2, xmm8
    aesenc  xmm3, xmm8
    aesenc  xmm4, xmm8
    aesenc  xmm5, xmm8
    aesenc  xmm6, xmm8
    aesenc  xmm7, xmm8
    ENDM

aes_last_rnd MACRO i
    movdqu  xmm8, [i*16 + ctx]
    aesenclast  xmm0, xmm8
    aesenclast  xmm1, xmm8
    aesenclast  xmm2, xmm8
    aesenclast  xmm3, xmm8
    aesenclast  xmm4, xmm8
    aesenclast  xmm5, xmm8
    aesenclast  xmm6, xmm8
    aesenclast  xmm7, xmm8
    ENDM

aes_dec_rnd MACRO i
    movdqu  xmm8, [i*16 + ctx]
    aesdec  xmm0, xmm8
    aesdec  xmm1, xmm8
    aesdec  xmm2, xmm8
    aesdec  xmm3, xmm8
    aesdec  xmm4, xmm8
    aesdec  xmm5, xmm8
    aesdec  xmm6, xmm8
    aesdec  xmm7, xmm8
    ENDM

aes_dec_last_rnd MACRO i
    movdqu  xmm8, [i*16 + ctx]
    aesdeclast  xmm0, xmm8
    aesdeclast  xmm1, xmm8
    aesdeclast  xmm2, xmm8
    aesdeclast  xmm3, xmm8
    aesdeclast  xmm4, xmm8
    aesdeclast  xmm5, xmm8
    aesdeclast  xmm6, xmm8
    aesdeclast  xmm7, xmm8
    ENDM


gen_aes_ecb_func MACRO enc, rnds

LOCAL   loop8
LOCAL   loop1
LOCAL   bail

        xor     inputLen, inputLen
        mov     input,      [rsp + 1*8 + 8*4]
        mov     inputLen,   [rsp + 1*8 + 8*5]

        sub     rsp, 3*16

        movdqu  [rsp + 0*16], xmm6
        movdqu  [rsp + 1*16], xmm7
        movdqu  [rsp + 2*16], xmm8

        lea     ctx, [48+ctx]

loop8:
        cmp     inputLen, 8*16
        jb      loop1

        movdqu  xmm0, [0*16 + input]
        movdqu  xmm1, [1*16 + input]
        movdqu  xmm2, [2*16 + input]
        movdqu  xmm3, [3*16 + input]
        movdqu  xmm4, [4*16 + input]
        movdqu  xmm5, [5*16 + input]
        movdqu  xmm6, [6*16 + input]
        movdqu  xmm7, [7*16 + input]

        movdqu  xmm8, [0*16 + ctx]
        pxor    xmm0, xmm8
        pxor    xmm1, xmm8
        pxor    xmm2, xmm8
        pxor    xmm3, xmm8
        pxor    xmm4, xmm8
        pxor    xmm5, xmm8
        pxor    xmm6, xmm8
        pxor    xmm7, xmm8

IF enc eq 1
        rnd textequ <aes_rnd>
        lastrnd textequ <aes_last_rnd>
        aesinst textequ <aesenc>
        aeslastinst textequ <aesenclast>
ELSE
        rnd textequ <aes_dec_rnd>
        lastrnd textequ <aes_dec_last_rnd>
        aesinst textequ <aesdec>
        aeslastinst textequ <aesdeclast>
ENDIF

        i = 1
        WHILE i LT rnds
            rnd i
            i = i+1
            ENDM
        lastrnd rnds

        movdqu  [0*16 + output], xmm0
        movdqu  [1*16 + output], xmm1
        movdqu  [2*16 + output], xmm2
        movdqu  [3*16 + output], xmm3
        movdqu  [4*16 + output], xmm4
        movdqu  [5*16 + output], xmm5
        movdqu  [6*16 + output], xmm6
        movdqu  [7*16 + output], xmm7

        lea input, [8*16 + input]
        lea output, [8*16 + output]
        sub inputLen, 8*16
        jmp loop8

loop1:
        cmp     inputLen, 1*16
        jb      bail

        movdqu  xmm0, [input]
        movdqu  xmm7, [0*16 + ctx]
        pxor    xmm0, xmm7

        i = 1
    WHILE i LT rnds
            movdqu  xmm7, [i*16 + ctx]
            aesinst  xmm0, xmm7
            i = i+1
        ENDM
        movdqu  xmm7, [rnds*16 + ctx]
        aeslastinst xmm0, xmm7

        movdqu  [output], xmm0

        lea input, [1*16 + input]
        lea output, [1*16 + output]
        sub inputLen, 1*16
        jmp loop1

bail:
        xor rax, rax

        movdqu  xmm6, [rsp + 0*16]
        movdqu  xmm7, [rsp + 1*16]
        movdqu  xmm8, [rsp + 2*16]
        add     rsp, 3*16
        ret
ENDM

intel_aes_encrypt_ecb_128 PROC
gen_aes_ecb_func 1, 10
intel_aes_encrypt_ecb_128 ENDP

intel_aes_encrypt_ecb_192 PROC
gen_aes_ecb_func 1, 12
intel_aes_encrypt_ecb_192 ENDP

intel_aes_encrypt_ecb_256 PROC
gen_aes_ecb_func 1, 14
intel_aes_encrypt_ecb_256 ENDP

intel_aes_decrypt_ecb_128 PROC
gen_aes_ecb_func 0, 10
intel_aes_decrypt_ecb_128 ENDP

intel_aes_decrypt_ecb_192 PROC
gen_aes_ecb_func 0, 12
intel_aes_decrypt_ecb_192 ENDP

intel_aes_decrypt_ecb_256 PROC
gen_aes_ecb_func 0, 14
intel_aes_decrypt_ecb_256 ENDP


KEY textequ <rcx>
KS  textequ <rdx>
ITR textequ <r8>

intel_aes_encrypt_init_128  PROC

    movdqu  xmm1, [KEY]
    movdqu  [KS], xmm1
    movdqa  xmm2, xmm1

    lea ITR, Lcon1
    movdqa  xmm0, [ITR]
    lea ITR, Lmask
    movdqa  xmm4, [ITR]

    mov ITR, 8

Lenc_128_ks_loop:
        lea KS, [16 + KS]
        dec ITR

        pshufb  xmm2, xmm4
        aesenclast  xmm2, xmm0
        pslld   xmm0, 1
        movdqa  xmm3, xmm1
        pslldq  xmm3, 4
        pxor    xmm1, xmm3
        pslldq  xmm3, 4
        pxor    xmm1, xmm3
        pslldq  xmm3, 4
        pxor    xmm1, xmm3
        pxor    xmm1, xmm2
        movdqu  [KS], xmm1
        movdqa  xmm2, xmm1

        jne Lenc_128_ks_loop

    lea ITR, Lcon2
    movdqa  xmm0, [ITR]

    pshufb  xmm2, xmm4
    aesenclast  xmm2, xmm0
    pslld   xmm0, 1
    movdqa  xmm3, xmm1
    pslldq  xmm3, 4
    pxor    xmm1, xmm3
    pslldq  xmm3, 4
    pxor    xmm1, xmm3
    pslldq  xmm3, 4
    pxor    xmm1, xmm3
    pxor    xmm1, xmm2
    movdqu  [16 + KS], xmm1
    movdqa  xmm2, xmm1

    pshufb  xmm2, xmm4
    aesenclast  xmm2, xmm0
    movdqa  xmm3, xmm1
    pslldq  xmm3, 4
    pxor    xmm1, xmm3
    pslldq  xmm3, 4
    pxor    xmm1, xmm3
    pslldq  xmm3, 4
    pxor    xmm1, xmm3
    pxor    xmm1, xmm2
    movdqu  [32 + KS], xmm1
    movdqa  xmm2, xmm1

    ret
intel_aes_encrypt_init_128  ENDP


intel_aes_decrypt_init_128  PROC

    push    KS
    push    KEY

    call    intel_aes_encrypt_init_128

    pop     KEY
    pop     KS

    movdqu  xmm0, [0*16 + KS]
    movdqu  xmm1, [10*16 + KS]
    movdqu  [10*16 + KS], xmm0
    movdqu  [0*16 + KS], xmm1

    i = 1
    WHILE i LT 5
        movdqu  xmm0, [i*16 + KS]
        movdqu  xmm1, [(10-i)*16 + KS]

        aesimc  xmm0, xmm0
        aesimc  xmm1, xmm1

        movdqu  [(10-i)*16 + KS], xmm0
        movdqu  [i*16 + KS], xmm1

        i = i+1
    ENDM

    movdqu  xmm0, [5*16 + KS]
    aesimc  xmm0, xmm0
    movdqu  [5*16 + KS], xmm0
    ret
intel_aes_decrypt_init_128  ENDP


intel_aes_encrypt_init_192  PROC

    sub     rsp, 16*2
    movdqu  [16*0 + rsp], xmm6
    movdqu  [16*1 + rsp], xmm7

    movdqu  xmm1, [KEY]
    mov     ITR, [16 + KEY]
    movd    xmm3, ITR

    movdqu  [KS], xmm1
    movdqa  xmm5, xmm3

    lea ITR, Lcon1
    movdqu  xmm0, [ITR]
    lea ITR, Lmask192
    movdqu  xmm4, [ITR]

    mov ITR, 4

Lenc_192_ks_loop:
        movdqa  xmm2, xmm3
        pshufb  xmm2, xmm4
        aesenclast xmm2, xmm0
        pslld   xmm0, 1

        movdqa  xmm6, xmm1
        movdqa  xmm7, xmm3
        pslldq  xmm6, 4
        pslldq  xmm7, 4
        pxor    xmm1, xmm6
        pxor    xmm3, xmm7
        pslldq  xmm6, 4
        pxor    xmm1, xmm6
        pslldq  xmm6, 4
        pxor    xmm1, xmm6
        pxor    xmm1, xmm2
        pshufd  xmm2, xmm1, 0ffh
        pxor    xmm3, xmm2

        movdqa  xmm6, xmm1
        shufpd  xmm5, xmm1, 00h
        shufpd  xmm6, xmm3, 01h

        movdqu  [16 + KS], xmm5
        movdqu  [32 + KS], xmm6

        movdqa  xmm2, xmm3
        pshufb  xmm2, xmm4
        aesenclast  xmm2, xmm0
        pslld   xmm0, 1

        movdqa  xmm6, xmm1
        movdqa  xmm7, xmm3
        pslldq  xmm6, 4
        pslldq  xmm7, 4
        pxor    xmm1, xmm6
        pxor    xmm3, xmm7
        pslldq  xmm6, 4
        pxor    xmm1, xmm6
        pslldq  xmm6, 4
        pxor    xmm1, xmm6
        pxor    xmm1, xmm2
        pshufd  xmm2, xmm1, 0ffh
        pxor    xmm3, xmm2

        movdqu  [48 + KS], xmm1
        movdqa  xmm5, xmm3

        lea KS, [48 + KS]

        dec ITR
        jnz Lenc_192_ks_loop

    movdqu  [16 + KS], xmm5

    movdqu  xmm7, [16*1 + rsp]
    movdqu  xmm6, [16*0 + rsp]
    add rsp, 16*2
    ret
intel_aes_encrypt_init_192  ENDP

intel_aes_decrypt_init_192  PROC
    push    KS
    push    KEY

    call    intel_aes_encrypt_init_192

    pop     KEY
    pop     KS

    movdqu  xmm0, [0*16 + KS]
    movdqu  xmm1, [12*16 + KS]
    movdqu  [12*16 + KS], xmm0
    movdqu  [0*16 + KS], xmm1

    i = 1
    WHILE i LT 6
        movdqu  xmm0, [i*16 + KS]
        movdqu  xmm1, [(12-i)*16 + KS]

        aesimc  xmm0, xmm0
        aesimc  xmm1, xmm1

        movdqu  [(12-i)*16 + KS], xmm0
        movdqu  [i*16 + KS], xmm1

        i = i+1
    ENDM

    movdqu  xmm0, [6*16 + KS]
    aesimc  xmm0, xmm0
    movdqu  [6*16 + KS], xmm0
    ret
intel_aes_decrypt_init_192  ENDP


intel_aes_encrypt_init_256  PROC
    sub     rsp, 16*2
    movdqu  [16*0 + rsp], xmm6
    movdqu  [16*1 + rsp], xmm7

    movdqu  xmm1, [16*0 + KEY]
    movdqu  xmm3, [16*1 + KEY]

    movdqu  [16*0 + KS], xmm1
    movdqu  [16*1 + KS], xmm3

    lea ITR, Lcon1
    movdqu  xmm0, [ITR]
    lea ITR, Lmask256
    movdqu  xmm5, [ITR]

    pxor    xmm6, xmm6

    mov ITR, 6

Lenc_256_ks_loop:

        movdqa  xmm2, xmm3
        pshufb  xmm2, xmm5
        aesenclast  xmm2, xmm0
        pslld   xmm0, 1
        movdqa  xmm4, xmm1
        pslldq  xmm4, 4
        pxor    xmm1, xmm4
        pslldq  xmm4, 4
        pxor    xmm1, xmm4
        pslldq  xmm4, 4
        pxor    xmm1, xmm4
        pxor    xmm1, xmm2
        movdqu  [16*2 + KS], xmm1

        pshufd  xmm2, xmm1, 0ffh
        aesenclast  xmm2, xmm6
        movdqa  xmm4, xmm3
        pslldq  xmm4, 4
        pxor    xmm3, xmm4
        pslldq  xmm4, 4
        pxor    xmm3, xmm4
        pslldq  xmm4, 4
        pxor    xmm3, xmm4
        pxor    xmm3, xmm2
        movdqu  [16*3 + KS], xmm3

        lea KS, [32 + KS]
        dec ITR
        jnz Lenc_256_ks_loop

    movdqa  xmm2, xmm3
    pshufb  xmm2, xmm5
    aesenclast  xmm2, xmm0
    movdqa  xmm4, xmm1
    pslldq  xmm4, 4
    pxor    xmm1, xmm4
    pslldq  xmm4, 4
    pxor    xmm1, xmm4
    pslldq  xmm4, 4
    pxor    xmm1, xmm4
    pxor    xmm1, xmm2
    movdqu  [16*2 + KS], xmm1

    movdqu  xmm7, [16*1 + rsp]
    movdqu  xmm6, [16*0 + rsp]
    add rsp, 16*2
    ret

intel_aes_encrypt_init_256  ENDP


intel_aes_decrypt_init_256  PROC
    push    KS
    push    KEY

    call    intel_aes_encrypt_init_256

    pop     KEY
    pop     KS

    movdqu  xmm0, [0*16 + KS]
    movdqu  xmm1, [14*16 + KS]
    movdqu  [14*16 + KS], xmm0
    movdqu  [0*16 + KS], xmm1

    i = 1
    WHILE i LT 7
        movdqu  xmm0, [i*16 + KS]
        movdqu  xmm1, [(14-i)*16 + KS]

        aesimc  xmm0, xmm0
        aesimc  xmm1, xmm1

        movdqu  [(14-i)*16 + KS], xmm0
        movdqu  [i*16 + KS], xmm1

        i = i+1
    ENDM

    movdqu  xmm0, [7*16 + KS]
    aesimc  xmm0, xmm0
    movdqu  [7*16 + KS], xmm0
    ret
intel_aes_decrypt_init_256  ENDP



gen_aes_cbc_enc_func MACRO rnds

LOCAL   loop1
LOCAL   bail

        mov     input,      [rsp + 1*8 + 8*4]
        mov     inputLen,   [rsp + 1*8 + 8*5]

        sub     rsp, 3*16

        movdqu  [rsp + 0*16], xmm6
        movdqu  [rsp + 1*16], xmm7
        movdqu  [rsp + 2*16], xmm8

        lea     ctx, [48+ctx]

        movdqu  xmm0, [-32+ctx]

        movdqu  xmm2, [0*16 + ctx]
        movdqu  xmm3, [1*16 + ctx]
        movdqu  xmm4, [2*16 + ctx]
        movdqu  xmm5, [3*16 + ctx]
        movdqu  xmm6, [4*16 + ctx]
        movdqu  xmm7, [5*16 + ctx]

loop1:
        cmp     inputLen, 1*16
        jb      bail

        movdqu  xmm1, [input]
        pxor    xmm1, xmm2
        pxor    xmm0, xmm1

        aesenc  xmm0, xmm3
        aesenc  xmm0, xmm4
        aesenc  xmm0, xmm5
        aesenc  xmm0, xmm6
        aesenc  xmm0, xmm7

        i = 6
    WHILE i LT rnds
            movdqu  xmm8, [i*16 + ctx]
            aesenc  xmm0, xmm8
            i = i+1
        ENDM
        movdqu  xmm8, [rnds*16 + ctx]
        aesenclast xmm0, xmm8

        movdqu  [output], xmm0

        lea input, [1*16 + input]
        lea output, [1*16 + output]
        sub inputLen, 1*16
        jmp loop1

bail:
        movdqu  [-32+ctx], xmm0

        xor rax, rax

        movdqu  xmm6, [rsp + 0*16]
        movdqu  xmm7, [rsp + 1*16]
        movdqu  xmm8, [rsp + 2*16]
        add     rsp, 3*16
        ret

ENDM

gen_aes_cbc_dec_func MACRO rnds

LOCAL   loop8
LOCAL   loop1
LOCAL   dec1
LOCAL   bail

        mov     input,      [rsp + 1*8 + 8*4]
        mov     inputLen,   [rsp + 1*8 + 8*5]

        sub     rsp, 3*16

        movdqu  [rsp + 0*16], xmm6
        movdqu  [rsp + 1*16], xmm7
        movdqu  [rsp + 2*16], xmm8

        lea     ctx, [48+ctx]

loop8:
        cmp     inputLen, 8*16
        jb      dec1

        movdqu  xmm0, [0*16 + input]
        movdqu  xmm1, [1*16 + input]
        movdqu  xmm2, [2*16 + input]
        movdqu  xmm3, [3*16 + input]
        movdqu  xmm4, [4*16 + input]
        movdqu  xmm5, [5*16 + input]
        movdqu  xmm6, [6*16 + input]
        movdqu  xmm7, [7*16 + input]

        movdqu  xmm8, [0*16 + ctx]
        pxor    xmm0, xmm8
        pxor    xmm1, xmm8
        pxor    xmm2, xmm8
        pxor    xmm3, xmm8
        pxor    xmm4, xmm8
        pxor    xmm5, xmm8
        pxor    xmm6, xmm8
        pxor    xmm7, xmm8

        i = 1
        WHILE i LT rnds
            aes_dec_rnd i
            i = i+1
            ENDM
        aes_dec_last_rnd rnds

        movdqu  xmm8, [-32 + ctx]
        pxor    xmm0, xmm8
        movdqu  xmm8, [0*16 + input]
        pxor    xmm1, xmm8
        movdqu  xmm8, [1*16 + input]
        pxor    xmm2, xmm8
        movdqu  xmm8, [2*16 + input]
        pxor    xmm3, xmm8
        movdqu  xmm8, [3*16 + input]
        pxor    xmm4, xmm8
        movdqu  xmm8, [4*16 + input]
        pxor    xmm5, xmm8
        movdqu  xmm8, [5*16 + input]
        pxor    xmm6, xmm8
        movdqu  xmm8, [6*16 + input]
        pxor    xmm7, xmm8
        movdqu  xmm8, [7*16 + input]

        movdqu  [0*16 + output], xmm0
        movdqu  [1*16 + output], xmm1
        movdqu  [2*16 + output], xmm2
        movdqu  [3*16 + output], xmm3
        movdqu  [4*16 + output], xmm4
        movdqu  [5*16 + output], xmm5
        movdqu  [6*16 + output], xmm6
        movdqu  [7*16 + output], xmm7
        movdqu  [-32 + ctx], xmm8

        lea input, [8*16 + input]
        lea output, [8*16 + output]
        sub inputLen, 8*16
        jmp loop8
dec1:

        movdqu  xmm3, [-32 + ctx]

loop1:
        cmp     inputLen, 1*16
        jb      bail

        movdqu  xmm0, [input]
        movdqa  xmm4, xmm0
        movdqu  xmm7, [0*16 + ctx]
        pxor    xmm0, xmm7

        i = 1
    WHILE i LT rnds
            movdqu  xmm7, [i*16 + ctx]
            aesdec  xmm0, xmm7
            i = i+1
        ENDM
        movdqu  xmm7, [rnds*16 + ctx]
        aesdeclast xmm0, xmm7
        pxor    xmm3, xmm0

        movdqu  [output], xmm3
        movdqa  xmm3, xmm4

        lea input, [1*16 + input]
        lea output, [1*16 + output]
        sub inputLen, 1*16
        jmp loop1

bail:
        movdqu  [-32 + ctx], xmm3
        xor rax, rax

        movdqu  xmm6, [rsp + 0*16]
        movdqu  xmm7, [rsp + 1*16]
        movdqu  xmm8, [rsp + 2*16]
        add     rsp, 3*16
        ret
ENDM

intel_aes_encrypt_cbc_128 PROC
gen_aes_cbc_enc_func  10
intel_aes_encrypt_cbc_128 ENDP

intel_aes_encrypt_cbc_192 PROC
gen_aes_cbc_enc_func  12
intel_aes_encrypt_cbc_192 ENDP

intel_aes_encrypt_cbc_256 PROC
gen_aes_cbc_enc_func  14
intel_aes_encrypt_cbc_256 ENDP

intel_aes_decrypt_cbc_128 PROC
gen_aes_cbc_dec_func  10
intel_aes_decrypt_cbc_128 ENDP

intel_aes_decrypt_cbc_192 PROC
gen_aes_cbc_dec_func  12
intel_aes_decrypt_cbc_192 ENDP

intel_aes_decrypt_cbc_256 PROC
gen_aes_cbc_dec_func  14
intel_aes_decrypt_cbc_256 ENDP



ctrCtx textequ <r10>
CTR textequ <r11d>
CTRSave textequ <eax>

gen_aes_ctr_func MACRO rnds

LOCAL   loop8
LOCAL   loop1
LOCAL   enc1
LOCAL   bail

        mov     input,      [rsp + 8*1 + 4*8]
        mov     inputLen,   [rsp + 8*1 + 5*8]

        mov     ctrCtx, ctx
        mov     ctx, [8+ctrCtx]
        lea     ctx, [48+ctx]

        sub     rsp, 3*16
        movdqu  [rsp + 0*16], xmm6
        movdqu  [rsp + 1*16], xmm7
        movdqu  [rsp + 2*16], xmm8


        push    rbp
        mov     rbp, rsp
        sub     rsp, 8*16
        and     rsp, -16


        movdqu  xmm0, [16+ctrCtx]
        mov     CTRSave, DWORD PTR [ctrCtx + 16 + 3*4]
        bswap   CTRSave
        movdqu  xmm1, [ctx + 0*16]

        pxor    xmm0, xmm1

        movdqa  [rsp + 0*16], xmm0
        movdqa  [rsp + 1*16], xmm0
        movdqa  [rsp + 2*16], xmm0
        movdqa  [rsp + 3*16], xmm0
        movdqa  [rsp + 4*16], xmm0
        movdqa  [rsp + 5*16], xmm0
        movdqa  [rsp + 6*16], xmm0
        movdqa  [rsp + 7*16], xmm0

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 1*16 + 3*4], CTR

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 2*16 + 3*4], CTR

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 3*16 + 3*4], CTR

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 4*16 + 3*4], CTR

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 5*16 + 3*4], CTR

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 6*16 + 3*4], CTR

        inc     CTRSave
        mov     CTR, CTRSave
        bswap   CTR
        xor     CTR, DWORD PTR [ctx + 3*4]
        mov     DWORD PTR [rsp + 7*16 + 3*4], CTR


loop8:
        cmp     inputLen, 8*16
        jb      loop1

        movdqu  xmm0, [0*16 + rsp]
        movdqu  xmm1, [1*16 + rsp]
        movdqu  xmm2, [2*16 + rsp]
        movdqu  xmm3, [3*16 + rsp]
        movdqu  xmm4, [4*16 + rsp]
        movdqu  xmm5, [5*16 + rsp]
        movdqu  xmm6, [6*16 + rsp]
        movdqu  xmm7, [7*16 + rsp]

        i = 1
        WHILE i LE 8
            aes_rnd i

            inc     CTRSave
            mov     CTR, CTRSave
            bswap   CTR
            xor     CTR, DWORD PTR [ctx + 3*4]
            mov     DWORD PTR [rsp + (i-1)*16 + 3*4], CTR

            i = i+1
        ENDM
        WHILE i LT rnds
            aes_rnd i
            i = i+1
            ENDM
        aes_last_rnd rnds

        movdqu  xmm8, [0*16 + input]
        pxor    xmm0, xmm8
        movdqu  xmm8, [1*16 + input]
        pxor    xmm1, xmm8
        movdqu  xmm8, [2*16 + input]
        pxor    xmm2, xmm8
        movdqu  xmm8, [3*16 + input]
        pxor    xmm3, xmm8
        movdqu  xmm8, [4*16 + input]
        pxor    xmm4, xmm8
        movdqu  xmm8, [5*16 + input]
        pxor    xmm5, xmm8
        movdqu  xmm8, [6*16 + input]
        pxor    xmm6, xmm8
        movdqu  xmm8, [7*16 + input]
        pxor    xmm7, xmm8

        movdqu  [0*16 + output], xmm0
        movdqu  [1*16 + output], xmm1
        movdqu  [2*16 + output], xmm2
        movdqu  [3*16 + output], xmm3
        movdqu  [4*16 + output], xmm4
        movdqu  [5*16 + output], xmm5
        movdqu  [6*16 + output], xmm6
        movdqu  [7*16 + output], xmm7

        lea input, [8*16 + input]
        lea output, [8*16 + output]
        sub inputLen, 8*16
        jmp loop8


loop1:
        cmp     inputLen, 1*16
        jb      bail

        movdqu  xmm0, [rsp]
        add     rsp, 16

        i = 1
    WHILE i LT rnds
            movdqu  xmm7, [i*16 + ctx]
            aesenc  xmm0, xmm7
            i = i+1
        ENDM
        movdqu  xmm7, [rnds*16 + ctx]
        aesenclast xmm0, xmm7

        movdqu  xmm7, [input]
        pxor    xmm0, xmm7
        movdqu  [output], xmm0

        lea input, [1*16 + input]
        lea output, [1*16 + output]
        sub inputLen, 1*16
        jmp loop1

bail:

        movdqu  xmm0, [rsp]
        movdqu  xmm1, [ctx + 0*16]
        pxor    xmm0, xmm1
        movdqu  [16+ctrCtx], xmm0


        xor     rax, rax
        mov     rsp, rbp
        pop     rbp

        movdqu  xmm6, [rsp + 0*16]
        movdqu  xmm7, [rsp + 1*16]
        movdqu  xmm8, [rsp + 2*16]
        add     rsp, 3*16

        ret
ENDM


intel_aes_encrypt_ctr_128 PROC
gen_aes_ctr_func  10
intel_aes_encrypt_ctr_128 ENDP

intel_aes_encrypt_ctr_192 PROC
gen_aes_ctr_func  12
intel_aes_encrypt_ctr_192 ENDP

intel_aes_encrypt_ctr_256 PROC
gen_aes_ctr_func  14
intel_aes_encrypt_ctr_256 ENDP


END