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
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
|
#! /usr/bin/env perl
# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
#
# Licensed under the Apache License 2.0 (the "License"). You may not use
# this file except in compliance with the License. You can obtain a copy
# in the file LICENSE in the source distribution or at
# https://www.openssl.org/source/license.html
#
# ====================================================================
# 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 NEON load and integer
# instructions. This has no effect on mighty Apple A7, where results
# are literally equal to the theoretical estimates based on AES
# instruction latencies and issue rates. On Cortex-A53, an in-order
# execution core, this costs up to 10-15%, which is partially
# compensated by implementing dedicated code path for 128-bit
# CBC encrypt case. On Cortex-A57 parallelizable mode performance
# seems to be limited by sheer amount of NEON instructions...
#
# April 2019
#
# Key to performance of parallelize-able modes is round instruction
# interleaving. But which factor to use? There is optimal one for
# each combination of instruction latency and issue rate, beyond
# which increasing interleave factor doesn't pay off. While on cons
# side we have code size increase and resource waste on platforms for
# which interleave factor is too high. In other words you want it to
# be just right. So far interleave factor of 3x was serving well all
# platforms. But for ThunderX2 optimal interleave factor was measured
# to be 5x...
#
# Performance in cycles per byte processed with 128-bit key:
#
# CBC enc CBC dec CTR
# Apple A7 2.39 1.20 1.20
# Cortex-A53 1.32 1.17/1.29(**) 1.36/1.46
# Cortex-A57(*) 1.95 0.82/0.85 0.89/0.93
# Cortex-A72 1.33 0.85/0.88 0.92/0.96
# Denver 1.96 0.65/0.86 0.76/0.80
# Mongoose 1.33 1.23/1.20 1.30/1.20
# Kryo 1.26 0.87/0.94 1.00/1.00
# ThunderX2 5.95 1.25 1.30
#
# (*) original 3.64/1.34/1.32 results were for r0p0 revision
# and are still same even for updated module;
# (**) numbers after slash are for 32-bit code, which is 3x-
# interleaved;
$flavour = shift;
$output = shift;
$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
die "can't locate arm-xlate.pl";
open OUT,"| \"$^X\" $xlate $flavour $output";
*STDOUT=*OUT;
$prefix="aes_v8";
$_byte = ($flavour =~ /win/ ? "DCB" : ".byte");
$code=<<___;
#include "arm_arch.h"
#if __ARM_MAX_ARCH__>=7
___
$code.=".arch armv8-a+crypto\n.text\n" if ($flavour =~ /64/);
$code.=<<___ if ($flavour !~ /64/);
.arch armv7-a // don't confuse not-so-latest binutils with argv8 :-)
.fpu neon
#ifdef __thumb2__
.syntax unified
.thumb
# define INST(a,b,c,d) $_byte c,d|0xc,a,b
#else
.code 32
# define INST(a,b,c,d) $_byte a,b,c,d
#endif
.text
___
# Assembler mnemonics are an eclectic mix of 32- and 64-bit syntax,
# NEON is mostly 32-bit mnemonics, integer - mostly 64. Goal is to
# maintain both 32- and 64-bit codes within single module and
# transliterate common code to either flavour with regex vodoo.
#
{{{
my ($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
.Lrcon:
.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.=<<___;
mov $ptr,#-1
cmp $inp,#0
b.eq .Lenc_key_abort
cmp $out,#0
b.eq .Lenc_key_abort
mov $ptr,#-2
cmp $bits,#128
b.lt .Lenc_key_abort
cmp $bits,#256
b.gt .Lenc_key_abort
tst $bits,#0x3f
b.ne .Lenc_key_abort
adr $ptr,.Lrcon
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]
mov $ptr,#0
.Lenc_key_abort:
mov x0,$ptr // 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/);
.inst 0xd503233f // paciasp
stp x29,x30,[sp,#-16]!
add x29,sp,#0
___
$code.=<<___ if ($flavour !~ /64/);
stmdb sp!,{r4,lr}
___
$code.=<<___;
bl .Lenc_key
cmp x0,#0
b.ne .Ldec_key_abort
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
.Ldec_key_abort:
___
$code.=<<___ if ($flavour !~ /64/);
ldmia sp!,{r4,pc}
___
$code.=<<___ if ($flavour =~ /64/);
ldp x29,x30,[sp],#16
.inst 0xd50323bf // autiasp
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
aes$mc $inout,$inout
vld1.32 {$rndkey0},[$key],#16
subs $rounds,$rounds,#2
aes$e $inout,$rndkey1
aes$mc $inout,$inout
vld1.32 {$rndkey1},[$key],#16
b.gt .Loop_${dir}c
aes$e $inout,$rndkey0
aes$mc $inout,$inout
vld1.32 {$rndkey0},[$key]
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);
my ($key4,$key5,$key6,$key7)=("x6","x12","x14",$key);
### 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
vld1.32 {$in0-$in1},[$key_]
add $key_,$key,#16
add $key4,$key,#16*4
add $key5,$key,#16*5
aese $dat,q8
aesmc $dat,$dat
add $key6,$key,#16*6
add $key7,$key,#16*7
b .Lenter_cbc_enc
.align 4
.Loop_cbc_enc:
aese $dat,q8
aesmc $dat,$dat
vst1.8 {$ivec},[$out],#16
.Lenter_cbc_enc:
aese $dat,q9
aesmc $dat,$dat
aese $dat,$in0
aesmc $dat,$dat
vld1.32 {q8},[$key4]
cmp $rounds,#4
aese $dat,$in1
aesmc $dat,$dat
vld1.32 {q9},[$key5]
b.eq .Lcbc_enc192
aese $dat,q8
aesmc $dat,$dat
vld1.32 {q8},[$key6]
aese $dat,q9
aesmc $dat,$dat
vld1.32 {q9},[$key7]
nop
.Lcbc_enc192:
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
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_] // re-pre-load rndkey[1]
aese $dat,q14
aesmc $dat,$dat
aese $dat,q15
veor $ivec,$dat,$rndlast
b.hs .Loop_cbc_enc
vst1.8 {$ivec},[$out],#16
b .Lcbc_done
.align 5
.Lcbc_enc128:
vld1.32 {$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},[$out],#16
b .Lcbc_done
___
{
my ($dat2,$in2,$tmp2)=map("q$_",(10,11,9));
my ($dat3,$in3,$tmp3); # used only in 64-bit mode
my ($dat4,$in4,$tmp4);
if ($flavour =~ /64/) {
($dat2,$dat3,$dat4,$in2,$in3,$in4,$tmp3,$tmp4)=map("q$_",(16..23));
}
$code.=<<___;
.align 5
.Lcbc_dec:
vld1.8 {$dat2},[$inp],#16
subs $len,$len,#32 // bias
add $cnt,$rounds,#2
vorr $in1,$dat,$dat
vorr $dat1,$dat,$dat
vorr $in2,$dat2,$dat2
b.lo .Lcbc_dec_tail
vorr $dat1,$dat2,$dat2
vld1.8 {$dat2},[$inp],#16
vorr $in0,$dat,$dat
vorr $in1,$dat1,$dat1
vorr $in2,$dat2,$dat2
___
$code.=<<___ if ($flavour =~ /64/);
cmp $len,#32
b.lo .Loop3x_cbc_dec
vld1.8 {$dat3},[$inp],#16
vld1.8 {$dat4},[$inp],#16
sub $len,$len,#32 // bias
mov $cnt,$rounds
vorr $in3,$dat3,$dat3
vorr $in4,$dat4,$dat4
.Loop5x_cbc_dec:
aesd $dat0,q8
aesimc $dat0,$dat0
aesd $dat1,q8
aesimc $dat1,$dat1
aesd $dat2,q8
aesimc $dat2,$dat2
aesd $dat3,q8
aesimc $dat3,$dat3
aesd $dat4,q8
aesimc $dat4,$dat4
vld1.32 {q8},[$key_],#16
subs $cnt,$cnt,#2
aesd $dat0,q9
aesimc $dat0,$dat0
aesd $dat1,q9
aesimc $dat1,$dat1
aesd $dat2,q9
aesimc $dat2,$dat2
aesd $dat3,q9
aesimc $dat3,$dat3
aesd $dat4,q9
aesimc $dat4,$dat4
vld1.32 {q9},[$key_],#16
b.gt .Loop5x_cbc_dec
aesd $dat0,q8
aesimc $dat0,$dat0
aesd $dat1,q8
aesimc $dat1,$dat1
aesd $dat2,q8
aesimc $dat2,$dat2
aesd $dat3,q8
aesimc $dat3,$dat3
aesd $dat4,q8
aesimc $dat4,$dat4
cmp $len,#0x40 // because .Lcbc_tail4x
sub $len,$len,#0x50
aesd $dat0,q9
aesimc $dat0,$dat0
aesd $dat1,q9
aesimc $dat1,$dat1
aesd $dat2,q9
aesimc $dat2,$dat2
aesd $dat3,q9
aesimc $dat3,$dat3
aesd $dat4,q9
aesimc $dat4,$dat4
csel x6,xzr,$len,gt // borrow x6, $cnt, "gt" is not typo
mov $key_,$key
aesd $dat0,q10
aesimc $dat0,$dat0
aesd $dat1,q10
aesimc $dat1,$dat1
aesd $dat2,q10
aesimc $dat2,$dat2
aesd $dat3,q10
aesimc $dat3,$dat3
aesd $dat4,q10
aesimc $dat4,$dat4
add $inp,$inp,x6 // $inp is adjusted in such way that
// at exit from the loop $dat1-$dat4
// are loaded with last "words"
add x6,$len,#0x60 // because .Lcbc_tail4x
aesd $dat0,q11
aesimc $dat0,$dat0
aesd $dat1,q11
aesimc $dat1,$dat1
aesd $dat2,q11
aesimc $dat2,$dat2
aesd $dat3,q11
aesimc $dat3,$dat3
aesd $dat4,q11
aesimc $dat4,$dat4
aesd $dat0,q12
aesimc $dat0,$dat0
aesd $dat1,q12
aesimc $dat1,$dat1
aesd $dat2,q12
aesimc $dat2,$dat2
aesd $dat3,q12
aesimc $dat3,$dat3
aesd $dat4,q12
aesimc $dat4,$dat4
aesd $dat0,q13
aesimc $dat0,$dat0
aesd $dat1,q13
aesimc $dat1,$dat1
aesd $dat2,q13
aesimc $dat2,$dat2
aesd $dat3,q13
aesimc $dat3,$dat3
aesd $dat4,q13
aesimc $dat4,$dat4
aesd $dat0,q14
aesimc $dat0,$dat0
aesd $dat1,q14
aesimc $dat1,$dat1
aesd $dat2,q14
aesimc $dat2,$dat2
aesd $dat3,q14
aesimc $dat3,$dat3
aesd $dat4,q14
aesimc $dat4,$dat4
veor $tmp0,$ivec,$rndlast
aesd $dat0,q15
veor $tmp1,$in0,$rndlast
vld1.8 {$in0},[$inp],#16
aesd $dat1,q15
veor $tmp2,$in1,$rndlast
vld1.8 {$in1},[$inp],#16
aesd $dat2,q15
veor $tmp3,$in2,$rndlast
vld1.8 {$in2},[$inp],#16
aesd $dat3,q15
veor $tmp4,$in3,$rndlast
vld1.8 {$in3},[$inp],#16
aesd $dat4,q15
vorr $ivec,$in4,$in4
vld1.8 {$in4},[$inp],#16
cbz x6,.Lcbc_tail4x
vld1.32 {q8},[$key_],#16 // re-pre-load rndkey[0]
veor $tmp0,$tmp0,$dat0
vorr $dat0,$in0,$in0
veor $tmp1,$tmp1,$dat1
vorr $dat1,$in1,$in1
veor $tmp2,$tmp2,$dat2
vorr $dat2,$in2,$in2
veor $tmp3,$tmp3,$dat3
vorr $dat3,$in3,$in3
veor $tmp4,$tmp4,$dat4
vst1.8 {$tmp0},[$out],#16
vorr $dat4,$in4,$in4
vst1.8 {$tmp1},[$out],#16
mov $cnt,$rounds
vst1.8 {$tmp2},[$out],#16
vld1.32 {q9},[$key_],#16 // re-pre-load rndkey[1]
vst1.8 {$tmp3},[$out],#16
vst1.8 {$tmp4},[$out],#16
b.hs .Loop5x_cbc_dec
add $len,$len,#0x50
cbz $len,.Lcbc_done
add $cnt,$rounds,#2
subs $len,$len,#0x30
vorr $dat0,$in2,$in2
vorr $in0,$in2,$in2
vorr $dat1,$in3,$in3
vorr $in1,$in3,$in3
vorr $dat2,$in4,$in4
vorr $in2,$in4,$in4
b.lo .Lcbc_dec_tail
b .Loop3x_cbc_dec
.align 4
.Lcbc_tail4x:
veor $tmp1,$tmp0,$dat1
veor $tmp2,$tmp2,$dat2
veor $tmp3,$tmp3,$dat3
veor $tmp4,$tmp4,$dat4
vst1.8 {$tmp1},[$out],#16
vst1.8 {$tmp2},[$out],#16
vst1.8 {$tmp3},[$out],#16
vst1.8 {$tmp4},[$out],#16
b .Lcbc_done
.align 4
___
$code.=<<___;
.Loop3x_cbc_dec:
aesd $dat0,q8
aesimc $dat0,$dat0
aesd $dat1,q8
aesimc $dat1,$dat1
aesd $dat2,q8
aesimc $dat2,$dat2
vld1.32 {q8},[$key_],#16
subs $cnt,$cnt,#2
aesd $dat0,q9
aesimc $dat0,$dat0
aesd $dat1,q9
aesimc $dat1,$dat1
aesd $dat2,q9
aesimc $dat2,$dat2
vld1.32 {q9},[$key_],#16
b.gt .Loop3x_cbc_dec
aesd $dat0,q8
aesimc $dat0,$dat0
aesd $dat1,q8
aesimc $dat1,$dat1
aesd $dat2,q8
aesimc $dat2,$dat2
veor $tmp0,$ivec,$rndlast
subs $len,$len,#0x30
veor $tmp1,$in0,$rndlast
mov.lo x6,$len // x6, $cnt, is zero at this point
aesd $dat0,q9
aesimc $dat0,$dat0
aesd $dat1,q9
aesimc $dat1,$dat1
aesd $dat2,q9
aesimc $dat2,$dat2
veor $tmp2,$in1,$rndlast
add $inp,$inp,x6 // $inp is adjusted in such way that
// at exit from the loop $dat1-$dat2
// are loaded with last "words"
vorr $ivec,$in2,$in2
mov $key_,$key
aesd $dat0,q12
aesimc $dat0,$dat0
aesd $dat1,q12
aesimc $dat1,$dat1
aesd $dat2,q12
aesimc $dat2,$dat2
vld1.8 {$in0},[$inp],#16
aesd $dat0,q13
aesimc $dat0,$dat0
aesd $dat1,q13
aesimc $dat1,$dat1
aesd $dat2,q13
aesimc $dat2,$dat2
vld1.8 {$in1},[$inp],#16
aesd $dat0,q14
aesimc $dat0,$dat0
aesd $dat1,q14
aesimc $dat1,$dat1
aesd $dat2,q14
aesimc $dat2,$dat2
vld1.8 {$in2},[$inp],#16
aesd $dat0,q15
aesd $dat1,q15
aesd $dat2,q15
vld1.32 {q8},[$key_],#16 // re-pre-load rndkey[0]
add $cnt,$rounds,#2
veor $tmp0,$tmp0,$dat0
veor $tmp1,$tmp1,$dat1
veor $dat2,$dat2,$tmp2
vld1.32 {q9},[$key_],#16 // re-pre-load rndkey[1]
vst1.8 {$tmp0},[$out],#16
vorr $dat0,$in0,$in0
vst1.8 {$tmp1},[$out],#16
vorr $dat1,$in1,$in1
vst1.8 {$dat2},[$out],#16
vorr $dat2,$in2,$in2
b.hs .Loop3x_cbc_dec
cmn $len,#0x30
b.eq .Lcbc_done
nop
.Lcbc_dec_tail:
aesd $dat1,q8
aesimc $dat1,$dat1
aesd $dat2,q8
aesimc $dat2,$dat2
vld1.32 {q8},[$key_],#16
subs $cnt,$cnt,#2
aesd $dat1,q9
aesimc $dat1,$dat1
aesd $dat2,q9
aesimc $dat2,$dat2
vld1.32 {q9},[$key_],#16
b.gt .Lcbc_dec_tail
aesd $dat1,q8
aesimc $dat1,$dat1
aesd $dat2,q8
aesimc $dat2,$dat2
aesd $dat1,q9
aesimc $dat1,$dat1
aesd $dat2,q9
aesimc $dat2,$dat2
aesd $dat1,q12
aesimc $dat1,$dat1
aesd $dat2,q12
aesimc $dat2,$dat2
cmn $len,#0x20
aesd $dat1,q13
aesimc $dat1,$dat1
aesd $dat2,q13
aesimc $dat2,$dat2
veor $tmp1,$ivec,$rndlast
aesd $dat1,q14
aesimc $dat1,$dat1
aesd $dat2,q14
aesimc $dat2,$dat2
veor $tmp2,$in1,$rndlast
aesd $dat1,q15
aesd $dat2,q15
b.eq .Lcbc_dec_one
veor $tmp1,$tmp1,$dat1
veor $tmp2,$tmp2,$dat2
vorr $ivec,$in2,$in2
vst1.8 {$tmp1},[$out],#16
vst1.8 {$tmp2},[$out],#16
b .Lcbc_done
.Lcbc_dec_one:
veor $tmp1,$tmp1,$dat2
vorr $ivec,$in2,$in2
vst1.8 {$tmp1},[$out],#16
.Lcbc_done:
vst1.8 {$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,$key_)=("w5","w6","x7");
my ($ctr,$tctr0,$tctr1,$tctr2)=map("w$_",(8..10,12));
my $step="x12"; # aliases with $tctr2
my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7));
my ($dat2,$in2,$tmp2)=map("q$_",(10,11,9));
# used only in 64-bit mode...
my ($dat3,$dat4,$in3,$in4)=map("q$_",(16..23));
my ($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,#4
mov $step,#16
cmp $len,#2
add $key_,$key,x5,lsl#4 // pointer to last 5 round keys
sub $rounds,$rounds,#2
vld1.32 {q12-q13},[$key_],#32
vld1.32 {q14-q15},[$key_],#32
vld1.32 {$rndlast},[$key_]
add $key_,$key,#32
mov $cnt,$rounds
cclr $step,lo
#ifndef __ARMEB__
rev $ctr, $ctr
#endif
vorr $dat1,$dat0,$dat0
add $tctr1, $ctr, #1
vorr $dat2,$dat0,$dat0
add $ctr, $ctr, #2
vorr $ivec,$dat0,$dat0
rev $tctr1, $tctr1
vmov.32 ${dat1}[3],$tctr1
b.ls .Lctr32_tail
rev $tctr2, $ctr
sub $len,$len,#3 // bias
vmov.32 ${dat2}[3],$tctr2
___
$code.=<<___ if ($flavour =~ /64/);
cmp $len,#2
b.lo .Loop3x_ctr32
add w13,$ctr,#1
add w14,$ctr,#2
vorr $dat3,$dat0,$dat0
rev w13,w13
vorr $dat4,$dat0,$dat0
rev w14,w14
vmov.32 ${dat3}[3],w13
sub $len,$len,#2 // bias
vmov.32 ${dat4}[3],w14
add $ctr,$ctr,#2
b .Loop5x_ctr32
.align 4
.Loop5x_ctr32:
aese $dat0,q8
aesmc $dat0,$dat0
aese $dat1,q8
aesmc $dat1,$dat1
aese $dat2,q8
aesmc $dat2,$dat2
aese $dat3,q8
aesmc $dat3,$dat3
aese $dat4,q8
aesmc $dat4,$dat4
vld1.32 {q8},[$key_],#16
subs $cnt,$cnt,#2
aese $dat0,q9
aesmc $dat0,$dat0
aese $dat1,q9
aesmc $dat1,$dat1
aese $dat2,q9
aesmc $dat2,$dat2
aese $dat3,q9
aesmc $dat3,$dat3
aese $dat4,q9
aesmc $dat4,$dat4
vld1.32 {q9},[$key_],#16
b.gt .Loop5x_ctr32
mov $key_,$key
aese $dat0,q8
aesmc $dat0,$dat0
aese $dat1,q8
aesmc $dat1,$dat1
aese $dat2,q8
aesmc $dat2,$dat2
aese $dat3,q8
aesmc $dat3,$dat3
aese $dat4,q8
aesmc $dat4,$dat4
vld1.32 {q8},[$key_],#16 // re-pre-load rndkey[0]
aese $dat0,q9
aesmc $dat0,$dat0
aese $dat1,q9
aesmc $dat1,$dat1
aese $dat2,q9
aesmc $dat2,$dat2
aese $dat3,q9
aesmc $dat3,$dat3
aese $dat4,q9
aesmc $dat4,$dat4
vld1.32 {q9},[$key_],#16 // re-pre-load rndkey[1]
aese $dat0,q12
aesmc $dat0,$dat0
add $tctr0,$ctr,#1
add $tctr1,$ctr,#2
aese $dat1,q12
aesmc $dat1,$dat1
add $tctr2,$ctr,#3
add w13,$ctr,#4
aese $dat2,q12
aesmc $dat2,$dat2
add w14,$ctr,#5
rev $tctr0,$tctr0
aese $dat3,q12
aesmc $dat3,$dat3
rev $tctr1,$tctr1
rev $tctr2,$tctr2
aese $dat4,q12
aesmc $dat4,$dat4
rev w13,w13
rev w14,w14
aese $dat0,q13
aesmc $dat0,$dat0
aese $dat1,q13
aesmc $dat1,$dat1
aese $dat2,q13
aesmc $dat2,$dat2
aese $dat3,q13
aesmc $dat3,$dat3
aese $dat4,q13
aesmc $dat4,$dat4
aese $dat0,q14
aesmc $dat0,$dat0
vld1.8 {$in0},[$inp],#16
aese $dat1,q14
aesmc $dat1,$dat1
vld1.8 {$in1},[$inp],#16
aese $dat2,q14
aesmc $dat2,$dat2
vld1.8 {$in2},[$inp],#16
aese $dat3,q14
aesmc $dat3,$dat3
vld1.8 {$in3},[$inp],#16
aese $dat4,q14
aesmc $dat4,$dat4
vld1.8 {$in4},[$inp],#16
aese $dat0,q15
veor $in0,$in0,$rndlast
aese $dat1,q15
veor $in1,$in1,$rndlast
aese $dat2,q15
veor $in2,$in2,$rndlast
aese $dat3,q15
veor $in3,$in3,$rndlast
aese $dat4,q15
veor $in4,$in4,$rndlast
veor $in0,$in0,$dat0
vorr $dat0,$ivec,$ivec
veor $in1,$in1,$dat1
vorr $dat1,$ivec,$ivec
veor $in2,$in2,$dat2
vorr $dat2,$ivec,$ivec
veor $in3,$in3,$dat3
vorr $dat3,$ivec,$ivec
veor $in4,$in4,$dat4
vorr $dat4,$ivec,$ivec
vst1.8 {$in0},[$out],#16
vmov.32 ${dat0}[3],$tctr0
vst1.8 {$in1},[$out],#16
vmov.32 ${dat1}[3],$tctr1
vst1.8 {$in2},[$out],#16
vmov.32 ${dat2}[3],$tctr2
vst1.8 {$in3},[$out],#16
vmov.32 ${dat3}[3],w13
vst1.8 {$in4},[$out],#16
vmov.32 ${dat4}[3],w14
mov $cnt,$rounds
cbz $len,.Lctr32_done
add $ctr,$ctr,#5
subs $len,$len,#5
b.hs .Loop5x_ctr32
add $len,$len,#5
sub $ctr,$ctr,#5
cmp $len,#2
mov $step,#16
cclr $step,lo
b.ls .Lctr32_tail
sub $len,$len,#3 // bias
add $ctr,$ctr,#3
___
$code.=<<___;
b .Loop3x_ctr32
.align 4
.Loop3x_ctr32:
aese $dat0,q8
aesmc $dat0,$dat0
aese $dat1,q8
aesmc $dat1,$dat1
aese $dat2,q8
aesmc $dat2,$dat2
vld1.32 {q8},[$key_],#16
subs $cnt,$cnt,#2
aese $dat0,q9
aesmc $dat0,$dat0
aese $dat1,q9
aesmc $dat1,$dat1
aese $dat2,q9
aesmc $dat2,$dat2
vld1.32 {q9},[$key_],#16
b.gt .Loop3x_ctr32
aese $dat0,q8
aesmc $tmp0,$dat0
aese $dat1,q8
aesmc $tmp1,$dat1
vld1.8 {$in0},[$inp],#16
vorr $dat0,$ivec,$ivec
aese $dat2,q8
aesmc $dat2,$dat2
vld1.8 {$in1},[$inp],#16
vorr $dat1,$ivec,$ivec
aese $tmp0,q9
aesmc $tmp0,$tmp0
aese $tmp1,q9
aesmc $tmp1,$tmp1
vld1.8 {$in2},[$inp],#16
mov $key_,$key
aese $dat2,q9
aesmc $tmp2,$dat2
vorr $dat2,$ivec,$ivec
add $tctr0,$ctr,#1
aese $tmp0,q12
aesmc $tmp0,$tmp0
aese $tmp1,q12
aesmc $tmp1,$tmp1
veor $in0,$in0,$rndlast
add $tctr1,$ctr,#2
aese $tmp2,q12
aesmc $tmp2,$tmp2
veor $in1,$in1,$rndlast
add $ctr,$ctr,#3
aese $tmp0,q13
aesmc $tmp0,$tmp0
aese $tmp1,q13
aesmc $tmp1,$tmp1
veor $in2,$in2,$rndlast
rev $tctr0,$tctr0
aese $tmp2,q13
aesmc $tmp2,$tmp2
vmov.32 ${dat0}[3], $tctr0
rev $tctr1,$tctr1
aese $tmp0,q14
aesmc $tmp0,$tmp0
aese $tmp1,q14
aesmc $tmp1,$tmp1
vmov.32 ${dat1}[3], $tctr1
rev $tctr2,$ctr
aese $tmp2,q14
aesmc $tmp2,$tmp2
vmov.32 ${dat2}[3], $tctr2
subs $len,$len,#3
aese $tmp0,q15
aese $tmp1,q15
aese $tmp2,q15
veor $in0,$in0,$tmp0
vld1.32 {q8},[$key_],#16 // re-pre-load rndkey[0]
vst1.8 {$in0},[$out],#16
veor $in1,$in1,$tmp1
mov $cnt,$rounds
vst1.8 {$in1},[$out],#16
veor $in2,$in2,$tmp2
vld1.32 {q9},[$key_],#16 // re-pre-load rndkey[1]
vst1.8 {$in2},[$out],#16
b.hs .Loop3x_ctr32
adds $len,$len,#3
b.eq .Lctr32_done
cmp $len,#1
mov $step,#16
cclr $step,eq
.Lctr32_tail:
aese $dat0,q8
aesmc $dat0,$dat0
aese $dat1,q8
aesmc $dat1,$dat1
vld1.32 {q8},[$key_],#16
subs $cnt,$cnt,#2
aese $dat0,q9
aesmc $dat0,$dat0
aese $dat1,q9
aesmc $dat1,$dat1
vld1.32 {q9},[$key_],#16
b.gt .Lctr32_tail
aese $dat0,q8
aesmc $dat0,$dat0
aese $dat1,q8
aesmc $dat1,$dat1
aese $dat0,q9
aesmc $dat0,$dat0
aese $dat1,q9
aesmc $dat1,$dat1
vld1.8 {$in0},[$inp],$step
aese $dat0,q12
aesmc $dat0,$dat0
aese $dat1,q12
aesmc $dat1,$dat1
vld1.8 {$in1},[$inp]
aese $dat0,q13
aesmc $dat0,$dat0
aese $dat1,q13
aesmc $dat1,$dat1
veor $in0,$in0,$rndlast
aese $dat0,q14
aesmc $dat0,$dat0
aese $dat1,q14
aesmc $dat1,$dat1
veor $in1,$in1,$rndlast
aese $dat0,q15
aese $dat1,q15
cmp $len,#1
veor $in0,$in0,$dat0
veor $in1,$in1,$dat1
vst1.8 {$in0},[$out],#16
b.eq .Lctr32_done
vst1.8 {$in1},[$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/mov\.([a-z]+)\s+([wx][0-9]+),\s*([wx][0-9]+)/csel $2,$3,$2,$1/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 remaining 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 "INST(0x%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 remaining 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;
if (s/^(\s+)mov\.([a-z]+)/$1mov$2/) {
print " it $2\n";
}
print $_,"\n";
}
}
close STDOUT;
|