summaryrefslogtreecommitdiff
path: root/main/openssl/crypto/aes/asm/aesv8-armx.pl
blob: 415dc04a23d387348d165c1a9931ce0c481b238d (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
972
973
974
975
976
977
978
979
980
#!/usr/bin/env perl
#
# ====================================================================
# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
# project. The module is, however, dual licensed under OpenSSL and
# CRYPTOGAMS licenses depending on where you obtain it. For further
# details see http://www.openssl.org/~appro/cryptogams/.
# ====================================================================
#
# This module implements support for ARMv8 AES instructions. The
# module is endian-agnostic in sense that it supports both big- and
# little-endian cases. As does it support both 32- and 64-bit modes
# of operation. Latter is achieved by limiting amount of utilized
# registers to 16, which implies additional instructions. This has
# no effect on mighty Apple A7, as results are literally equal to
# the theoretical estimates based on instruction latencies and issue
# rate. It remains to be seen how does it affect other platforms...
#
# Performance in cycles per byte processed with 128-bit key:
#
#		CBC enc		CBC dec		CTR
# Apple A7	2.39		1.20		1.20
# Cortex-A5x	n/a		n/a		n/a

$flavour = shift;
open STDOUT,">".shift;

$prefix="aes_v8";

$code=<<___;
#include "arm_arch.h"

#if __ARM_ARCH__>=7
.text
___
$code.=".arch	armv8-a+crypto\n"	if ($flavour =~ /64/);
$code.=".fpu	neon\n.code	32\n"	if ($flavour !~ /64/);

# Assembler mnemonics are an eclectic mix of 32- and 64-bit syntax,
# NEON is mostly 32-bit mnemonics, integer - mostly 64. Goal is to
# maintain both 32- and 64-bit codes within single module and
# transliterate common code to either flavour with regex vodoo.
#
{{{
my ($inp,$bits,$out,$ptr,$rounds)=("x0","w1","x2","x3","w12");
my ($zero,$rcon,$mask,$in0,$in1,$tmp,$key)=
	$flavour=~/64/? map("q$_",(0..6)) : map("q$_",(0..3,8..10));


$code.=<<___;
.align	5
rcon:
.long	0x01,0x01,0x01,0x01
.long	0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d	// rotate-n-splat
.long	0x1b,0x1b,0x1b,0x1b

.globl	${prefix}_set_encrypt_key
.type	${prefix}_set_encrypt_key,%function
.align	5
${prefix}_set_encrypt_key:
.Lenc_key:
___
$code.=<<___	if ($flavour =~ /64/);
	stp	x29,x30,[sp,#-16]!
	add	x29,sp,#0
___
$code.=<<___;
	adr	$ptr,rcon
	cmp	$bits,#192

	veor	$zero,$zero,$zero
	vld1.8	{$in0},[$inp],#16
	mov	$bits,#8		// reuse $bits
	vld1.32	{$rcon,$mask},[$ptr],#32

	b.lt	.Loop128
	b.eq	.L192
	b	.L256

.align	4
.Loop128:
	vtbl.8	$key,{$in0},$mask
	vext.8	$tmp,$zero,$in0,#12
	vst1.32	{$in0},[$out],#16
	aese	$key,$zero
	subs	$bits,$bits,#1

	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	 veor	$key,$key,$rcon
	veor	$in0,$in0,$tmp
	vshl.u8	$rcon,$rcon,#1
	veor	$in0,$in0,$key
	b.ne	.Loop128

	vld1.32	{$rcon},[$ptr]

	vtbl.8	$key,{$in0},$mask
	vext.8	$tmp,$zero,$in0,#12
	vst1.32	{$in0},[$out],#16
	aese	$key,$zero

	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	 veor	$key,$key,$rcon
	veor	$in0,$in0,$tmp
	vshl.u8	$rcon,$rcon,#1
	veor	$in0,$in0,$key

	vtbl.8	$key,{$in0},$mask
	vext.8	$tmp,$zero,$in0,#12
	vst1.32	{$in0},[$out],#16
	aese	$key,$zero

	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	 veor	$key,$key,$rcon
	veor	$in0,$in0,$tmp
	veor	$in0,$in0,$key
	vst1.32	{$in0},[$out]
	add	$out,$out,#0x50

	mov	$rounds,#10
	b	.Ldone

.align	4
.L192:
	vld1.8	{$in1},[$inp],#8
	vmov.i8	$key,#8			// borrow $key
	vst1.32	{$in0},[$out],#16
	vsub.i8	$mask,$mask,$key	// adjust the mask

.Loop192:
	vtbl.8	$key,{$in1},$mask
	vext.8	$tmp,$zero,$in0,#12
	vst1.32	{$in1},[$out],#8
	aese	$key,$zero
	subs	$bits,$bits,#1

	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in0,$in0,$tmp

	vdup.32	$tmp,${in0}[3]
	veor	$tmp,$tmp,$in1
	 veor	$key,$key,$rcon
	vext.8	$in1,$zero,$in1,#12
	vshl.u8	$rcon,$rcon,#1
	veor	$in1,$in1,$tmp
	veor	$in0,$in0,$key
	veor	$in1,$in1,$key
	vst1.32	{$in0},[$out],#16
	b.ne	.Loop192

	mov	$rounds,#12
	add	$out,$out,#0x20
	b	.Ldone

.align	4
.L256:
	vld1.8	{$in1},[$inp]
	mov	$bits,#7
	mov	$rounds,#14
	vst1.32	{$in0},[$out],#16

.Loop256:
	vtbl.8	$key,{$in1},$mask
	vext.8	$tmp,$zero,$in0,#12
	vst1.32	{$in1},[$out],#16
	aese	$key,$zero
	subs	$bits,$bits,#1

	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in0,$in0,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	 veor	$key,$key,$rcon
	veor	$in0,$in0,$tmp
	vshl.u8	$rcon,$rcon,#1
	veor	$in0,$in0,$key
	vst1.32	{$in0},[$out],#16
	b.eq	.Ldone

	vdup.32	$key,${in0}[3]		// just splat
	vext.8	$tmp,$zero,$in1,#12
	aese	$key,$zero

	veor	$in1,$in1,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in1,$in1,$tmp
	vext.8	$tmp,$zero,$tmp,#12
	veor	$in1,$in1,$tmp

	veor	$in1,$in1,$key
	b	.Loop256

.Ldone:
	str	$rounds,[$out]

	eor	x0,x0,x0		// return value
	`"ldr	x29,[sp],#16"		if ($flavour =~ /64/)`
	ret
.size	${prefix}_set_encrypt_key,.-${prefix}_set_encrypt_key

.globl	${prefix}_set_decrypt_key
.type	${prefix}_set_decrypt_key,%function
.align	5
${prefix}_set_decrypt_key:
___
$code.=<<___	if ($flavour =~ /64/);
	stp	x29,x30,[sp,#-16]!
	add	x29,sp,#0
___
$code.=<<___	if ($flavour !~ /64/);
	stmdb	sp!,{r4,lr}
___
$code.=<<___;
	bl	.Lenc_key

	sub	$out,$out,#240		// restore original $out
	mov	x4,#-16
	add	$inp,$out,x12,lsl#4	// end of key schedule

	vld1.32	{v0.16b},[$out]
	vld1.32	{v1.16b},[$inp]
	vst1.32	{v0.16b},[$inp],x4
	vst1.32	{v1.16b},[$out],#16

.Loop_imc:
	vld1.32	{v0.16b},[$out]
	vld1.32	{v1.16b},[$inp]
	aesimc	v0.16b,v0.16b
	aesimc	v1.16b,v1.16b
	vst1.32	{v0.16b},[$inp],x4
	vst1.32	{v1.16b},[$out],#16
	cmp	$inp,$out
	b.hi	.Loop_imc

	vld1.32	{v0.16b},[$out]
	aesimc	v0.16b,v0.16b
	vst1.32	{v0.16b},[$inp]

	eor	x0,x0,x0		// return value
___
$code.=<<___	if ($flavour !~ /64/);
	ldmia	sp!,{r4,pc}
___
$code.=<<___	if ($flavour =~ /64/);
	ldp	x29,x30,[sp],#16
	ret
___
$code.=<<___;
.size	${prefix}_set_decrypt_key,.-${prefix}_set_decrypt_key
___
}}}
{{{
sub gen_block () {
my $dir = shift;
my ($e,$mc) = $dir eq "en" ? ("e","mc") : ("d","imc");
my ($inp,$out,$key)=map("x$_",(0..2));
my $rounds="w3";
my ($rndkey0,$rndkey1,$inout)=map("q$_",(0..3));

$code.=<<___;
.globl	${prefix}_${dir}crypt
.type	${prefix}_${dir}crypt,%function
.align	5
${prefix}_${dir}crypt:
	ldr	$rounds,[$key,#240]
	vld1.32	{$rndkey0},[$key],#16
	vld1.8	{$inout},[$inp]
	sub	$rounds,$rounds,#2
	vld1.32	{$rndkey1},[$key],#16

.Loop_${dir}c:
	aes$e	$inout,$rndkey0
	vld1.32	{$rndkey0},[$key],#16
	aes$mc	$inout,$inout
	subs	$rounds,$rounds,#2
	aes$e	$inout,$rndkey1
	vld1.32	{$rndkey1},[$key],#16
	aes$mc	$inout,$inout
	b.gt	.Loop_${dir}c

	aes$e	$inout,$rndkey0
	vld1.32	{$rndkey0},[$key]
	aes$mc	$inout,$inout
	aes$e	$inout,$rndkey1
	veor	$inout,$inout,$rndkey0

	vst1.8	{$inout},[$out]
	ret
.size	${prefix}_${dir}crypt,.-${prefix}_${dir}crypt
___
}
&gen_block("en");
&gen_block("de");
}}}
{{{
my ($inp,$out,$len,$key,$ivp)=map("x$_",(0..4)); my $enc="w5";
my ($rounds,$cnt,$key_,$step,$step1)=($enc,"w6","x7","x8","x12");
my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7));

my ($dat,$tmp,$rndzero_n_last)=($dat0,$tmp0,$tmp1);

### q8-q15	preloaded key schedule

$code.=<<___;
.globl	${prefix}_cbc_encrypt
.type	${prefix}_cbc_encrypt,%function
.align	5
${prefix}_cbc_encrypt:
___
$code.=<<___	if ($flavour =~ /64/);
	stp	x29,x30,[sp,#-16]!
	add	x29,sp,#0
___
$code.=<<___	if ($flavour !~ /64/);
	mov	ip,sp
	stmdb	sp!,{r4-r8,lr}
	vstmdb	sp!,{d8-d15}            @ ABI specification says so
	ldmia	ip,{r4-r5}		@ load remaining args
___
$code.=<<___;
	subs	$len,$len,#16
	mov	$step,#16
	b.lo	.Lcbc_abort
	cclr	$step,eq

	cmp	$enc,#0			// en- or decrypting?
	ldr	$rounds,[$key,#240]
	and	$len,$len,#-16
	vld1.8	{$ivec},[$ivp]
	vld1.8	{$dat},[$inp],$step

	vld1.32	{q8-q9},[$key]		// load key schedule...
	sub	$rounds,$rounds,#6
	add	$key_,$key,x5,lsl#4	// pointer to last 7 round keys
	sub	$rounds,$rounds,#2
	vld1.32	{q10-q11},[$key_],#32
	vld1.32	{q12-q13},[$key_],#32
	vld1.32	{q14-q15},[$key_],#32
	vld1.32	{$rndlast},[$key_]

	add	$key_,$key,#32
	mov	$cnt,$rounds
	b.eq	.Lcbc_dec

	cmp	$rounds,#2
	veor	$dat,$dat,$ivec
	veor	$rndzero_n_last,q8,$rndlast
	b.eq	.Lcbc_enc128

.Loop_cbc_enc:
	aese	$dat,q8
	vld1.32	{q8},[$key_],#16
	aesmc	$dat,$dat
	subs	$cnt,$cnt,#2
	aese	$dat,q9
	vld1.32	{q9},[$key_],#16
	aesmc	$dat,$dat
	b.gt	.Loop_cbc_enc

	aese	$dat,q8
	aesmc	$dat,$dat
	 subs	$len,$len,#16
	aese	$dat,q9
	aesmc	$dat,$dat
	 cclr	$step,eq
	aese	$dat,q10
	aesmc	$dat,$dat
	 add	$key_,$key,#16
	aese	$dat,q11
	aesmc	$dat,$dat
	 vld1.8	{q8},[$inp],$step
	aese	$dat,q12
	aesmc	$dat,$dat
	 veor	q8,q8,$rndzero_n_last
	aese	$dat,q13
	aesmc	$dat,$dat
	 vld1.32 {q9},[$key_],#16	// re-pre-load rndkey[1]
	aese	$dat,q14
	aesmc	$dat,$dat
	aese	$dat,q15

	 mov	$cnt,$rounds
	veor	$ivec,$dat,$rndlast
	vst1.8	{$ivec},[$out],#16
	b.hs	.Loop_cbc_enc

	b	.Lcbc_done

.align	5
.Lcbc_enc128:
	vld1.32	{$in0-$in1},[$key_]
	aese	$dat,q8
	aesmc	$dat,$dat
	b	.Lenter_cbc_enc128
.Loop_cbc_enc128:
	aese	$dat,q8
	aesmc	$dat,$dat
	 vst1.8	{$ivec},[$out],#16
.Lenter_cbc_enc128:
	aese	$dat,q9
	aesmc	$dat,$dat
	 subs	$len,$len,#16
	aese	$dat,$in0
	aesmc	$dat,$dat
	 cclr	$step,eq
	aese	$dat,$in1
	aesmc	$dat,$dat
	aese	$dat,q10
	aesmc	$dat,$dat
	aese	$dat,q11
	aesmc	$dat,$dat
	 vld1.8	{q8},[$inp],$step
	aese	$dat,q12
	aesmc	$dat,$dat
	aese	$dat,q13
	aesmc	$dat,$dat
	aese	$dat,q14
	aesmc	$dat,$dat
	 veor	q8,q8,$rndzero_n_last
	aese	$dat,q15
	veor	$ivec,$dat,$rndlast
	b.hs	.Loop_cbc_enc128

	vst1.8	{$ivec},[$out],#16
	b	.Lcbc_done

.align	5
.Lcbc_dec128:
	vld1.32	{$tmp0-$tmp1},[$key_]
	veor	$ivec,$ivec,$rndlast
	veor	$in0,$dat0,$rndlast
	mov	$step1,$step

.Loop2x_cbc_dec128:
	aesd	$dat0,q8
	aesd	$dat1,q8
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 subs	$len,$len,#32
	aesd	$dat0,q9
	aesd	$dat1,q9
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 cclr	$step,lo
	aesd	$dat0,$tmp0
	aesd	$dat1,$tmp0
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 cclr	$step1,ls
	aesd	$dat0,$tmp1
	aesd	$dat1,$tmp1
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	aesd	$dat0,q10
	aesd	$dat1,q10
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	aesd	$dat0,q11
	aesd	$dat1,q11
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	aesd	$dat0,q12
	aesd	$dat1,q12
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	aesd	$dat0,q13
	aesd	$dat1,q13
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	aesd	$dat0,q14
	aesd	$dat1,q14
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	aesd	$dat0,q15
	aesd	$dat1,q15

	veor	$ivec,$ivec,$dat0
	vld1.8	{$dat0},[$inp],$step
	veor	$in0,$in0,$dat1
	vld1.8	{$dat1},[$inp],$step1
	vst1.8	{$ivec},[$out],#16
	veor	$ivec,$in1,$rndlast
	vst1.8	{$in0},[$out],#16
	veor	$in0,$dat0,$rndlast
	vorr	$in1,$dat1,$dat1
	b.hs	.Loop2x_cbc_dec128

	adds	$len,$len,#32
	veor	$ivec,$ivec,$rndlast
	b.eq	.Lcbc_done
	veor	$in0,$in0,$rndlast
	b	.Lcbc_dec_tail

.align	5
.Lcbc_dec:
	subs	$len,$len,#16
	vorr	$in0,$dat,$dat
	b.lo	.Lcbc_dec_tail

	cclr	$step,eq
	cmp	$rounds,#2
	vld1.8	{$dat1},[$inp],$step
	vorr	$in1,$dat1,$dat1
	b.eq	.Lcbc_dec128

.Loop2x_cbc_dec:
	aesd	$dat0,q8
	aesd	$dat1,q8
	vld1.32	{q8},[$key_],#16
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	subs	$cnt,$cnt,#2
	aesd	$dat0,q9
	aesd	$dat1,q9
	vld1.32	{q9},[$key_],#16
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	b.gt	.Loop2x_cbc_dec

	aesd	$dat0,q8
	aesd	$dat1,q8
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 veor	$tmp0,$ivec,$rndlast
	 veor	$tmp1,$in0,$rndlast
	aesd	$dat0,q9
	aesd	$dat1,q9
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 vorr	$ivec,$in1,$in1
	 subs	$len,$len,#32
	aesd	$dat0,q10
	aesd	$dat1,q10
	aesimc	$dat0,$dat0
	 cclr	$step,lo
	aesimc	$dat1,$dat1
	 mov	$key_,$key
	aesd	$dat0,q11
	aesd	$dat1,q11
	aesimc	$dat0,$dat0
	 vld1.8	{$in0},[$inp],$step
	aesimc	$dat1,$dat1
	 cclr	$step,ls
	aesd	$dat0,q12
	aesd	$dat1,q12
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 vld1.8	{$in1},[$inp],$step
	aesd	$dat0,q13
	aesd	$dat1,q13
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 vld1.32 {q8},[$key_],#16	// re-pre-load rndkey[0]
	aesd	$dat0,q14
	aesd	$dat1,q14
	aesimc	$dat0,$dat0
	aesimc	$dat1,$dat1
	 vld1.32 {q9},[$key_],#16	// re-pre-load rndkey[1]
	aesd	$dat0,q15
	aesd	$dat1,q15

	 mov	$cnt,$rounds
	veor	$tmp0,$tmp0,$dat0
	veor	$tmp1,$tmp1,$dat1
	 vorr	$dat0,$in0,$in0
	vst1.8	{$tmp0},[$out],#16
	 vorr	$dat1,$in1,$in1
	vst1.8	{$tmp1},[$out],#16
	b.hs	.Loop2x_cbc_dec

	adds	$len,$len,#32
	b.eq	.Lcbc_done

.Lcbc_dec_tail:
	aesd	$dat,q8
	vld1.32	{q8},[$key_],#16
	aesimc	$dat,$dat
	subs	$cnt,$cnt,#2
	aesd	$dat,q9
	vld1.32	{q9},[$key_],#16
	aesimc	$dat,$dat
	b.gt	.Lcbc_dec_tail

	aesd	$dat,q8
	aesimc	$dat,$dat
	aesd	$dat,q9
	aesimc	$dat,$dat
	 veor	$tmp,$ivec,$rndlast
	aesd	$dat,q10
	aesimc	$dat,$dat
	 vorr	$ivec,$in0,$in0
	aesd	$dat,q11
	aesimc	$dat,$dat
	aesd	$dat,q12
	aesimc	$dat,$dat
	aesd	$dat,q13
	aesimc	$dat,$dat
	aesd	$dat,q14
	aesimc	$dat,$dat
	aesd	$dat,q15

	veor	$tmp,$tmp,$dat
	vst1.8	{$tmp},[$out],#16

.Lcbc_done:
	vst1.8	{$ivec},[$ivp]
.Lcbc_abort:
___
$code.=<<___	if ($flavour !~ /64/);
	vldmia	sp!,{d8-d15}
	ldmia	sp!,{r4-r8,pc}
___
$code.=<<___	if ($flavour =~ /64/);
	ldr	x29,[sp],#16
	ret
___
$code.=<<___;
.size	${prefix}_cbc_encrypt,.-${prefix}_cbc_encrypt
___
}}}
{{{
my ($inp,$out,$len,$key,$ivp)=map("x$_",(0..4));
my ($rounds,$cnt,$key_,$ctr,$tctr,$tctr1)=("w5","w6","x7","w8","w9","w10");
my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7));

my ($dat,$tmp)=($dat0,$tmp0);

### q8-q15	preloaded key schedule

$code.=<<___;
.globl	${prefix}_ctr32_encrypt_blocks
.type	${prefix}_ctr32_encrypt_blocks,%function
.align	5
${prefix}_ctr32_encrypt_blocks:
___
$code.=<<___	if ($flavour =~ /64/);
	stp		x29,x30,[sp,#-16]!
	add		x29,sp,#0
___
$code.=<<___	if ($flavour !~ /64/);
	mov		ip,sp
	stmdb		sp!,{r4-r10,lr}
	vstmdb		sp!,{d8-d15}            @ ABI specification says so
	ldr		r4, [ip]		@ load remaining arg
___
$code.=<<___;
	ldr		$rounds,[$key,#240]

	ldr		$ctr, [$ivp, #12]
	vld1.32		{$dat0},[$ivp]

	vld1.32		{q8-q9},[$key]		// load key schedule...
	sub		$rounds,$rounds,#6
	add		$key_,$key,x5,lsl#4	// pointer to last 7 round keys
	sub		$rounds,$rounds,#2
	vld1.32		{q10-q11},[$key_],#32
	vld1.32		{q12-q13},[$key_],#32
	vld1.32		{q14-q15},[$key_],#32
	vld1.32		{$rndlast},[$key_]

	add		$key_,$key,#32
	mov		$cnt,$rounds

	subs		$len,$len,#2
	b.lo		.Lctr32_tail

#ifndef __ARMEB__
	rev		$ctr, $ctr
#endif
	vorr		$dat1,$dat0,$dat0
	add		$ctr, $ctr, #1
	vorr		$ivec,$dat0,$dat0
	rev		$tctr1, $ctr
	cmp		$rounds,#2
	vmov.32		${dat1}[3],$tctr1
	b.eq		.Lctr32_128

.Loop2x_ctr32:
	aese		$dat0,q8
	aese		$dat1,q8
	vld1.32		{q8},[$key_],#16
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	subs		$cnt,$cnt,#2
	aese		$dat0,q9
	aese		$dat1,q9
	vld1.32		{q9},[$key_],#16
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	b.gt		.Loop2x_ctr32

	aese		$dat0,q8
	aese		$dat1,q8
	aesmc		$tmp0,$dat0
	 vorr		$dat0,$ivec,$ivec
	aesmc		$tmp1,$dat1
	 vorr		$dat1,$ivec,$ivec
	aese		$tmp0,q9
	aese		$tmp1,q9
	 vld1.8		{$in0},[$inp],#16
	aesmc		$tmp0,$tmp0
	 vld1.8		{$in1},[$inp],#16
	aesmc		$tmp1,$tmp1
	 add		$ctr,$ctr,#1
	aese		$tmp0,q10
	aese		$tmp1,q10
	 rev		$tctr,$ctr
	aesmc		$tmp0,$tmp0
	aesmc		$tmp1,$tmp1
	 add		$ctr,$ctr,#1
	aese		$tmp0,q11
	aese		$tmp1,q11
	 veor		$in0,$in0,$rndlast
	 rev		$tctr1,$ctr
	aesmc		$tmp0,$tmp0
	aesmc		$tmp1,$tmp1
	 veor		$in1,$in1,$rndlast
	 mov		$key_,$key
	aese		$tmp0,q12
	aese		$tmp1,q12
	 subs		$len,$len,#2
	aesmc		$tmp0,$tmp0
	aesmc		$tmp1,$tmp1
	 vld1.32	 {q8-q9},[$key_],#32	// re-pre-load rndkey[0-1]
	aese		$tmp0,q13
	aese		$tmp1,q13
	aesmc		$tmp0,$tmp0
	aesmc		$tmp1,$tmp1
	aese		$tmp0,q14
	aese		$tmp1,q14
	 vmov.32	${dat0}[3], $tctr
	aesmc		$tmp0,$tmp0
	 vmov.32	${dat1}[3], $tctr1
	aesmc		$tmp1,$tmp1
	aese		$tmp0,q15
	aese		$tmp1,q15

	 mov		$cnt,$rounds
	veor		$in0,$in0,$tmp0
	veor		$in1,$in1,$tmp1
	vst1.8		{$in0},[$out],#16
	vst1.8		{$in1},[$out],#16
	b.hs		.Loop2x_ctr32

	adds		$len,$len,#2
	b.eq		.Lctr32_done
	b		.Lctr32_tail

.Lctr32_128:
	vld1.32		{$tmp0-$tmp1},[$key_]

.Loop2x_ctr32_128:
	aese		$dat0,q8
	aese		$dat1,q8
	aesmc		$dat0,$dat0
	 vld1.8		{$in0},[$inp],#16
	aesmc		$dat1,$dat1
	 vld1.8		{$in1},[$inp],#16
	aese		$dat0,q9
	aese		$dat1,q9
	 add		$ctr,$ctr,#1
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	 rev		$tctr,$ctr
	aese		$dat0,$tmp0
	aese		$dat1,$tmp0
	 add		$ctr,$ctr,#1
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	 rev		$tctr1,$ctr
	aese		$dat0,$tmp1
	aese		$dat1,$tmp1
	 subs		$len,$len,#2
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	aese		$dat0,q10
	aese		$dat1,q10
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	aese		$dat0,q11
	aese		$dat1,q11
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	aese		$dat0,q12
	aese		$dat1,q12
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	aese		$dat0,q13
	aese		$dat1,q13
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	aese		$dat0,q14
	aese		$dat1,q14
	aesmc		$dat0,$dat0
	aesmc		$dat1,$dat1
	 veor		$in0,$in0,$rndlast
	aese		$dat0,q15
	 veor		$in1,$in1,$rndlast
	aese		$dat1,q15

	veor		$in0,$in0,$dat0
	vorr		$dat0,$ivec,$ivec
	veor		$in1,$in1,$dat1
	vorr		$dat1,$ivec,$ivec
	vst1.8		{$in0},[$out],#16
	vmov.32		${dat0}[3], $tctr
	vst1.8		{$in1},[$out],#16
	vmov.32		${dat1}[3], $tctr1
	b.hs		.Loop2x_ctr32_128

	adds		$len,$len,#2
	b.eq		.Lctr32_done

.Lctr32_tail:
	aese		$dat,q8
	vld1.32		{q8},[$key_],#16
	aesmc		$dat,$dat
	subs		$cnt,$cnt,#2
	aese		$dat,q9
	vld1.32		{q9},[$key_],#16
	aesmc		$dat,$dat
	b.gt		.Lctr32_tail

	aese		$dat,q8
	aesmc		$dat,$dat
	aese		$dat,q9
	aesmc		$dat,$dat
	 vld1.8		{$in0},[$inp]
	aese		$dat,q10
	aesmc		$dat,$dat
	aese		$dat,q11
	aesmc		$dat,$dat
	aese		$dat,q12
	aesmc		$dat,$dat
	aese		$dat,q13
	aesmc		$dat,$dat
	aese		$dat,q14
	aesmc		$dat,$dat
	 veor		$in0,$in0,$rndlast
	aese		$dat,q15

	veor		$in0,$in0,$dat
	vst1.8		{$in0},[$out]

.Lctr32_done:
___
$code.=<<___	if ($flavour !~ /64/);
	vldmia		sp!,{d8-d15}
	ldmia		sp!,{r4-r10,pc}
___
$code.=<<___	if ($flavour =~ /64/);
	ldr		x29,[sp],#16
	ret
___
$code.=<<___;
.size	${prefix}_ctr32_encrypt_blocks,.-${prefix}_ctr32_encrypt_blocks
___
}}}
$code.=<<___;
#endif
___
########################################
if ($flavour =~ /64/) {			######## 64-bit code
    my %opcode = (
	"aesd"	=>	0x4e285800,	"aese"	=>	0x4e284800,
	"aesimc"=>	0x4e287800,	"aesmc"	=>	0x4e286800	);

    local *unaes = sub {
	my ($mnemonic,$arg)=@_;

	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)/o	&&
	sprintf ".inst\t0x%08x\t//%s %s",
			$opcode{$mnemonic}|$1|($2<<5),
			$mnemonic,$arg;
    };

    foreach(split("\n",$code)) {
        s/\`([^\`]*)\`/eval($1)/geo;

	s/\bq([0-9]+)\b/"v".($1<8?$1:$1+8).".16b"/geo;	# old->new registers
        s/@\s/\/\//o;			# old->new style commentary

	#s/[v]?(aes\w+)\s+([qv].*)/unaes($1,$2)/geo	or
	s/cclr\s+([wx])([^,]+),\s*([a-z]+)/csel	$1$2,$1zr,$1$2,$3/o	or
        s/vmov\.i8/movi/o	or	# fix up legacy mnemonics
        s/vext\.8/ext/o		or
        s/vrev32\.8/rev32/o	or
        s/vtst\.8/cmtst/o	or
        s/vshr/ushr/o		or
        s/^(\s+)v/$1/o		or	# strip off v prefix
	s/\bbx\s+lr\b/ret/o;

	# fix up remainig legacy suffixes
	s/\.[ui]?8//o;
	m/\],#8/o and s/\.16b/\.8b/go;
        s/\.[ui]?32//o and s/\.16b/\.4s/go;
        s/\.[ui]?64//o and s/\.16b/\.2d/go;
	s/\.[42]([sd])\[([0-3])\]/\.$1\[$2\]/o;

        print $_,"\n";
    }
} else {				######## 32-bit code
    my %opcode = (
	"aesd"	=>	0xf3b00340,	"aese"	=>	0xf3b00300,
	"aesimc"=>	0xf3b003c0,	"aesmc"	=>	0xf3b00380	);

    local *unaes = sub {
	my ($mnemonic,$arg)=@_;

	if ($arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)/o) {
	    my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19)
					 |(($2&7)<<1) |(($2&8)<<2);
	    # since ARMv7 instructions are always encoded little-endian.
	    # correct solution is to use .inst directive, but older
	    # assemblers don't implement it:-(
	    sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s",
			$word&0xff,($word>>8)&0xff,
			($word>>16)&0xff,($word>>24)&0xff,
			$mnemonic,$arg;
	}
    };

    sub unvtbl {
	my $arg=shift;

	$arg =~ m/q([0-9]+),\s*\{q([0-9]+)\},\s*q([0-9]+)/o &&
	sprintf	"vtbl.8	d%d,{q%d},d%d\n\t".
		"vtbl.8	d%d,{q%d},d%d", 2*$1,$2,2*$3, 2*$1+1,$2,2*$3+1;	
    }

    sub unvdup32 {
	my $arg=shift;

	$arg =~ m/q([0-9]+),\s*q([0-9]+)\[([0-3])\]/o &&
	sprintf	"vdup.32	q%d,d%d[%d]",$1,2*$2+($3>>1),$3&1;	
    }

    sub unvmov32 {
	my $arg=shift;

	$arg =~ m/q([0-9]+)\[([0-3])\],(.*)/o &&
	sprintf	"vmov.32	d%d[%d],%s",2*$1+($2>>1),$2&1,$3;	
    }

    foreach(split("\n",$code)) {
        s/\`([^\`]*)\`/eval($1)/geo;

	s/\b[wx]([0-9]+)\b/r$1/go;		# new->old registers
	s/\bv([0-9])\.[12468]+[bsd]\b/q$1/go;	# new->old registers
        s/\/\/\s?/@ /o;				# new->old style commentary

	# fix up remainig new-style suffixes
	s/\{q([0-9]+)\},\s*\[(.+)\],#8/sprintf "{d%d},[$2]!",2*$1/eo	or
	s/\],#[0-9]+/]!/o;

	s/[v]?(aes\w+)\s+([qv].*)/unaes($1,$2)/geo	or
	s/cclr\s+([^,]+),\s*([a-z]+)/mov$2	$1,#0/o	or
	s/vtbl\.8\s+(.*)/unvtbl($1)/geo			or
	s/vdup\.32\s+(.*)/unvdup32($1)/geo		or
	s/vmov\.32\s+(.*)/unvmov32($1)/geo		or
	s/^(\s+)b\./$1b/o				or
	s/^(\s+)ret/$1bx\tlr/o;

        print $_,"\n";
    }
}

close STDOUT;