aboutsummaryrefslogtreecommitdiffstats
path: root/lib/zinc/poly1305/poly1305-arm.pl
blob: 468f41b76fbd2156704f594cd8cdcda5f411f6bb (plain) (blame)
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
#!/usr/bin/env perl
# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
#
# This code is taken from the OpenSSL project but the author, Andy Polyakov,
# has relicensed it under the licenses specified in the SPDX header above.
# The original headers, including the original license headers, are
# included below for completeness.
#
# ====================================================================
# 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/.
# ====================================================================
#
#			IALU(*)/gcc-4.4		NEON
#
# ARM11xx(ARMv6)	7.78/+100%		-
# Cortex-A5		6.35/+130%		3.00
# Cortex-A8		6.25/+115%		2.36
# Cortex-A9		5.10/+95%		2.55
# Cortex-A15		3.85/+85%		1.25(**)
# Snapdragon S4		5.70/+100%		1.48(**)
#
# (*)	this is for -march=armv6, i.e. with bunch of ldrb loading data;
# (**)	these are trade-off results, they can be improved by ~8% but at
#	the cost of 15/12% regression on Cortex-A5/A7, it's even possible
#	to improve Cortex-A9 result, but then A5/A7 loose more than 20%;

$flavour = shift;
if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }

if ($flavour && $flavour ne "void") {
    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $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 STDOUT,"| \"$^X\" $xlate $flavour $output";
} else {
    open STDOUT,">$output";
}

($ctx,$inp,$len,$padbit)=map("r$_",(0..3));

$code.=<<___;
#ifndef	__KERNEL__
# include "arm_arch.h"
#else
# define __ARM_ARCH__ __LINUX_ARM_ARCH__
# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
# define poly1305_init   poly1305_init_arm
# define poly1305_blocks poly1305_blocks_arm
# define poly1305_emit   poly1305_emit_arm
#endif

.text
#if defined(__thumb2__)
.syntax	unified
.thumb
#else
.code	32
#endif

.globl	poly1305_emit
.globl	poly1305_blocks
.globl	poly1305_init
.type	poly1305_init,%function
.align	5
poly1305_init:
.Lpoly1305_init:
	stmdb	sp!,{r4-r11}

	eor	r3,r3,r3
	cmp	$inp,#0
	str	r3,[$ctx,#0]		@ zero hash value
	str	r3,[$ctx,#4]
	str	r3,[$ctx,#8]
	str	r3,[$ctx,#12]
	str	r3,[$ctx,#16]
	str	r3,[$ctx,#36]		@ is_base2_26
	add	$ctx,$ctx,#20

#ifdef	__thumb2__
	it	eq
#endif
	moveq	r0,#0
	beq	.Lno_key

#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
	adr	r11,.Lpoly1305_init
	ldr	r12,.LOPENSSL_armcap
#endif
	ldrb	r4,[$inp,#0]
	mov	r10,#0x0fffffff
	ldrb	r5,[$inp,#1]
	and	r3,r10,#-4		@ 0x0ffffffc
	ldrb	r6,[$inp,#2]
	ldrb	r7,[$inp,#3]
	orr	r4,r4,r5,lsl#8
	ldrb	r5,[$inp,#4]
	orr	r4,r4,r6,lsl#16
	ldrb	r6,[$inp,#5]
	orr	r4,r4,r7,lsl#24
	ldrb	r7,[$inp,#6]
	and	r4,r4,r10

#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
# ifdef	__APPLE__
	ldr	r12,[r12]
# endif
#endif
	ldrb	r8,[$inp,#7]
	orr	r5,r5,r6,lsl#8
	ldrb	r6,[$inp,#8]
	orr	r5,r5,r7,lsl#16
	ldrb	r7,[$inp,#9]
	orr	r5,r5,r8,lsl#24
	ldrb	r8,[$inp,#10]
	and	r5,r5,r3

#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
	tst	r12,#ARMV7_NEON		@ check for NEON
# ifdef	__APPLE__
	adr	r9,poly1305_blocks_neon
	adr	r11,poly1305_blocks
#  ifdef __thumb2__
	it	ne
#  endif
	movne	r11,r9
	adr	r12,poly1305_emit
	adr	r10,poly1305_emit_neon
#  ifdef __thumb2__
	it	ne
#  endif
	movne	r12,r10
# else
#  ifdef __thumb2__
	itete	eq
#  endif
	addeq	r12,r11,#(poly1305_emit-.Lpoly1305_init)
	addne	r12,r11,#(poly1305_emit_neon-.Lpoly1305_init)
	addeq	r11,r11,#(poly1305_blocks-.Lpoly1305_init)
	addne	r11,r11,#(poly1305_blocks_neon-.Lpoly1305_init)
# endif
# ifdef	__thumb2__
	orr	r12,r12,#1	@ thumb-ify address
	orr	r11,r11,#1
# endif
#endif
	ldrb	r9,[$inp,#11]
	orr	r6,r6,r7,lsl#8
	ldrb	r7,[$inp,#12]
	orr	r6,r6,r8,lsl#16
	ldrb	r8,[$inp,#13]
	orr	r6,r6,r9,lsl#24
	ldrb	r9,[$inp,#14]
	and	r6,r6,r3

	ldrb	r10,[$inp,#15]
	orr	r7,r7,r8,lsl#8
	str	r4,[$ctx,#0]
	orr	r7,r7,r9,lsl#16
	str	r5,[$ctx,#4]
	orr	r7,r7,r10,lsl#24
	str	r6,[$ctx,#8]
	and	r7,r7,r3
	str	r7,[$ctx,#12]
#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
	stmia	r2,{r11,r12}		@ fill functions table
	mov	r0,#1
#else
	mov	r0,#0
#endif
.Lno_key:
	ldmia	sp!,{r4-r11}
#if	__ARM_ARCH__>=5
	ret				@ bx	lr
#else
	tst	lr,#1
	moveq	pc,lr			@ be binary compatible with V4, yet
	bx	lr			@ interoperable with Thumb ISA:-)
#endif
.size	poly1305_init,.-poly1305_init
___
{
my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
my ($s1,$s2,$s3)=($r1,$r2,$r3);

$code.=<<___;
.type	poly1305_blocks,%function
.align	5
poly1305_blocks:
.Lpoly1305_blocks:
	stmdb	sp!,{r3-r11,lr}

	ands	$len,$len,#-16
	beq	.Lno_data

	cmp	$padbit,#0
	add	$len,$len,$inp		@ end pointer
	sub	sp,sp,#32

	ldmia	$ctx,{$h0-$r3}		@ load context

	str	$ctx,[sp,#12]		@ offload stuff
	mov	lr,$inp
	str	$len,[sp,#16]
	str	$r1,[sp,#20]
	str	$r2,[sp,#24]
	str	$r3,[sp,#28]
	b	.Loop

.Loop:
#if __ARM_ARCH__<7
	ldrb	r0,[lr],#16		@ load input
# ifdef	__thumb2__
	it	hi
# endif
	addhi	$h4,$h4,#1		@ 1<<128
	ldrb	r1,[lr,#-15]
	ldrb	r2,[lr,#-14]
	ldrb	r3,[lr,#-13]
	orr	r1,r0,r1,lsl#8
	ldrb	r0,[lr,#-12]
	orr	r2,r1,r2,lsl#16
	ldrb	r1,[lr,#-11]
	orr	r3,r2,r3,lsl#24
	ldrb	r2,[lr,#-10]
	adds	$h0,$h0,r3		@ accumulate input

	ldrb	r3,[lr,#-9]
	orr	r1,r0,r1,lsl#8
	ldrb	r0,[lr,#-8]
	orr	r2,r1,r2,lsl#16
	ldrb	r1,[lr,#-7]
	orr	r3,r2,r3,lsl#24
	ldrb	r2,[lr,#-6]
	adcs	$h1,$h1,r3

	ldrb	r3,[lr,#-5]
	orr	r1,r0,r1,lsl#8
	ldrb	r0,[lr,#-4]
	orr	r2,r1,r2,lsl#16
	ldrb	r1,[lr,#-3]
	orr	r3,r2,r3,lsl#24
	ldrb	r2,[lr,#-2]
	adcs	$h2,$h2,r3

	ldrb	r3,[lr,#-1]
	orr	r1,r0,r1,lsl#8
	str	lr,[sp,#8]		@ offload input pointer
	orr	r2,r1,r2,lsl#16
	add	$s1,$r1,$r1,lsr#2
	orr	r3,r2,r3,lsl#24
#else
	ldr	r0,[lr],#16		@ load input
# ifdef	__thumb2__
	it	hi
# endif
	addhi	$h4,$h4,#1		@ padbit
	ldr	r1,[lr,#-12]
	ldr	r2,[lr,#-8]
	ldr	r3,[lr,#-4]
# ifdef	__ARMEB__
	rev	r0,r0
	rev	r1,r1
	rev	r2,r2
	rev	r3,r3
# endif
	adds	$h0,$h0,r0		@ accumulate input
	str	lr,[sp,#8]		@ offload input pointer
	adcs	$h1,$h1,r1
	add	$s1,$r1,$r1,lsr#2
	adcs	$h2,$h2,r2
#endif
	add	$s2,$r2,$r2,lsr#2
	adcs	$h3,$h3,r3
	add	$s3,$r3,$r3,lsr#2

	umull	r2,r3,$h1,$r0
	 adc	$h4,$h4,#0
	umull	r0,r1,$h0,$r0
	umlal	r2,r3,$h4,$s1
	umlal	r0,r1,$h3,$s1
	ldr	$r1,[sp,#20]		@ reload $r1
	umlal	r2,r3,$h2,$s3
	umlal	r0,r1,$h1,$s3
	umlal	r2,r3,$h3,$s2
	umlal	r0,r1,$h2,$s2
	umlal	r2,r3,$h0,$r1
	str	r0,[sp,#0]		@ future $h0
	 mul	r0,$s2,$h4
	ldr	$r2,[sp,#24]		@ reload $r2
	adds	r2,r2,r1		@ d1+=d0>>32
	 eor	r1,r1,r1
	adc	lr,r3,#0		@ future $h2
	str	r2,[sp,#4]		@ future $h1

	mul	r2,$s3,$h4
	eor	r3,r3,r3
	umlal	r0,r1,$h3,$s3
	ldr	$r3,[sp,#28]		@ reload $r3
	umlal	r2,r3,$h3,$r0
	umlal	r0,r1,$h2,$r0
	umlal	r2,r3,$h2,$r1
	umlal	r0,r1,$h1,$r1
	umlal	r2,r3,$h1,$r2
	umlal	r0,r1,$h0,$r2
	umlal	r2,r3,$h0,$r3
	ldr	$h0,[sp,#0]
	mul	$h4,$r0,$h4
	ldr	$h1,[sp,#4]

	adds	$h2,lr,r0		@ d2+=d1>>32
	ldr	lr,[sp,#8]		@ reload input pointer
	adc	r1,r1,#0
	adds	$h3,r2,r1		@ d3+=d2>>32
	ldr	r0,[sp,#16]		@ reload end pointer
	adc	r3,r3,#0
	add	$h4,$h4,r3		@ h4+=d3>>32

	and	r1,$h4,#-4
	and	$h4,$h4,#3
	add	r1,r1,r1,lsr#2		@ *=5
	adds	$h0,$h0,r1
	adcs	$h1,$h1,#0
	adcs	$h2,$h2,#0
	adcs	$h3,$h3,#0
	adc	$h4,$h4,#0

	cmp	r0,lr			@ done yet?
	bhi	.Loop

	ldr	$ctx,[sp,#12]
	add	sp,sp,#32
	stmia	$ctx,{$h0-$h4}		@ store the result

.Lno_data:
#if	__ARM_ARCH__>=5
	ldmia	sp!,{r3-r11,pc}
#else
	ldmia	sp!,{r3-r11,lr}
	tst	lr,#1
	moveq	pc,lr			@ be binary compatible with V4, yet
	bx	lr			@ interoperable with Thumb ISA:-)
#endif
.size	poly1305_blocks,.-poly1305_blocks
___
}
{
my ($ctx,$mac,$nonce)=map("r$_",(0..2));
my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
my $g4=$h4;

$code.=<<___;
.type	poly1305_emit,%function
.align	5
poly1305_emit:
	stmdb	sp!,{r4-r11}
.Lpoly1305_emit_enter:

	ldmia	$ctx,{$h0-$h4}
	adds	$g0,$h0,#5		@ compare to modulus
	adcs	$g1,$h1,#0
	adcs	$g2,$h2,#0
	adcs	$g3,$h3,#0
	adc	$g4,$h4,#0
	tst	$g4,#4			@ did it carry/borrow?

#ifdef	__thumb2__
	it	ne
#endif
	movne	$h0,$g0
	ldr	$g0,[$nonce,#0]
#ifdef	__thumb2__
	it	ne
#endif
	movne	$h1,$g1
	ldr	$g1,[$nonce,#4]
#ifdef	__thumb2__
	it	ne
#endif
	movne	$h2,$g2
	ldr	$g2,[$nonce,#8]
#ifdef	__thumb2__
	it	ne
#endif
	movne	$h3,$g3
	ldr	$g3,[$nonce,#12]

	adds	$h0,$h0,$g0
	adcs	$h1,$h1,$g1
	adcs	$h2,$h2,$g2
	adc	$h3,$h3,$g3

#if __ARM_ARCH__>=7
# ifdef __ARMEB__
	rev	$h0,$h0
	rev	$h1,$h1
	rev	$h2,$h2
	rev	$h3,$h3
# endif
	str	$h0,[$mac,#0]
	str	$h1,[$mac,#4]
	str	$h2,[$mac,#8]
	str	$h3,[$mac,#12]
#else
	strb	$h0,[$mac,#0]
	mov	$h0,$h0,lsr#8
	strb	$h1,[$mac,#4]
	mov	$h1,$h1,lsr#8
	strb	$h2,[$mac,#8]
	mov	$h2,$h2,lsr#8
	strb	$h3,[$mac,#12]
	mov	$h3,$h3,lsr#8

	strb	$h0,[$mac,#1]
	mov	$h0,$h0,lsr#8
	strb	$h1,[$mac,#5]
	mov	$h1,$h1,lsr#8
	strb	$h2,[$mac,#9]
	mov	$h2,$h2,lsr#8
	strb	$h3,[$mac,#13]
	mov	$h3,$h3,lsr#8

	strb	$h0,[$mac,#2]
	mov	$h0,$h0,lsr#8
	strb	$h1,[$mac,#6]
	mov	$h1,$h1,lsr#8
	strb	$h2,[$mac,#10]
	mov	$h2,$h2,lsr#8
	strb	$h3,[$mac,#14]
	mov	$h3,$h3,lsr#8

	strb	$h0,[$mac,#3]
	strb	$h1,[$mac,#7]
	strb	$h2,[$mac,#11]
	strb	$h3,[$mac,#15]
#endif
	ldmia	sp!,{r4-r11}
#if	__ARM_ARCH__>=5
	ret				@ bx	lr
#else
	tst	lr,#1
	moveq	pc,lr			@ be binary compatible with V4, yet
	bx	lr			@ interoperable with Thumb ISA:-)
#endif
.size	poly1305_emit,.-poly1305_emit
___
{
my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
my ($T0,$T1,$MASK) = map("q$_",(15,4,0));

my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));

$code.=<<___;
#if (defined(__KERNEL__) && defined(CONFIG_KERNEL_MODE_NEON)) || (!defined(__KERNEL__) && __ARM_MAX_ARCH__>=7)
.fpu	neon

.type	poly1305_init_neon,%function
.align	5
poly1305_init_neon:
.Lpoly1305_init_neon:
	ldr	r4,[$ctx,#20]		@ load key base 2^32
	ldr	r5,[$ctx,#24]
	ldr	r6,[$ctx,#28]
	ldr	r7,[$ctx,#32]

	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
	mov	r3,r4,lsr#26
	mov	r4,r5,lsr#20
	orr	r3,r3,r5,lsl#6
	mov	r5,r6,lsr#14
	orr	r4,r4,r6,lsl#12
	mov	r6,r7,lsr#8
	orr	r5,r5,r7,lsl#18
	and	r3,r3,#0x03ffffff
	and	r4,r4,#0x03ffffff
	and	r5,r5,#0x03ffffff

	vdup.32	$R0,r2			@ r^1 in both lanes
	add	r2,r3,r3,lsl#2		@ *5
	vdup.32	$R1,r3
	add	r3,r4,r4,lsl#2
	vdup.32	$S1,r2
	vdup.32	$R2,r4
	add	r4,r5,r5,lsl#2
	vdup.32	$S2,r3
	vdup.32	$R3,r5
	add	r5,r6,r6,lsl#2
	vdup.32	$S3,r4
	vdup.32	$R4,r6
	vdup.32	$S4,r5

	mov	$zeros,#2		@ counter

.Lsquare_neon:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4

	vmull.u32	$D0,$R0,${R0}[1]
	vmull.u32	$D1,$R1,${R0}[1]
	vmull.u32	$D2,$R2,${R0}[1]
	vmull.u32	$D3,$R3,${R0}[1]
	vmull.u32	$D4,$R4,${R0}[1]

	vmlal.u32	$D0,$R4,${S1}[1]
	vmlal.u32	$D1,$R0,${R1}[1]
	vmlal.u32	$D2,$R1,${R1}[1]
	vmlal.u32	$D3,$R2,${R1}[1]
	vmlal.u32	$D4,$R3,${R1}[1]

	vmlal.u32	$D0,$R3,${S2}[1]
	vmlal.u32	$D1,$R4,${S2}[1]
	vmlal.u32	$D3,$R1,${R2}[1]
	vmlal.u32	$D2,$R0,${R2}[1]
	vmlal.u32	$D4,$R2,${R2}[1]

	vmlal.u32	$D0,$R2,${S3}[1]
	vmlal.u32	$D3,$R0,${R3}[1]
	vmlal.u32	$D1,$R3,${S3}[1]
	vmlal.u32	$D2,$R4,${S3}[1]
	vmlal.u32	$D4,$R1,${R3}[1]

	vmlal.u32	$D3,$R4,${S4}[1]
	vmlal.u32	$D0,$R1,${S4}[1]
	vmlal.u32	$D1,$R2,${S4}[1]
	vmlal.u32	$D2,$R3,${S4}[1]
	vmlal.u32	$D4,$R0,${R4}[1]

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
	@ and P. Schwabe
	@
	@ H0>>+H1>>+H2>>+H3>>+H4
	@ H3>>+H4>>*5+H0>>+H1
	@
	@ Trivia.
	@
	@ Result of multiplication of n-bit number by m-bit number is
	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
	@ m-bit number multiplied by 2^n is still n+m bits wide.
	@
	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
	@ one is n+1 bits wide.
	@
	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
	@ can be 27. However! In cases when their width exceeds 26 bits
	@ they are limited by 2^26+2^6. This in turn means that *sum*
	@ of the products with these values can still be viewed as sum
	@ of 52-bit numbers as long as the amount of addends is not a
	@ power of 2. For example,
	@
	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
	@
	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
	@ which is less than 32 * (2^52) or 2^57. And when processing
	@ data we are looking at triple as many addends...
	@
	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
	@ This means that result of reduction have to be compressed upon
	@ loop wrap-around. This can be done in the process of reduction
	@ to minimize amount of instructions [as well as amount of
	@ 128-bit instructions, which benefits low-end processors], but
	@ one has to watch for H2 (which is narrower than H0) and 5*H4
	@ not being wider than 58 bits, so that result of right shift
	@ by 26 bits fits in 32 bits. This is also useful on x86,
	@ because it allows to use paddd in place for paddq, which
	@ benefits Atom, where paddq is ridiculously slow.

	vshr.u64	$T0,$D3,#26
	vmovn.i64	$D3#lo,$D3
	 vshr.u64	$T1,$D0,#26
	 vmovn.i64	$D0#lo,$D0
	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
	vbic.i32	$D3#lo,#0xfc000000	@ &=0x03ffffff
	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
	 vbic.i32	$D0#lo,#0xfc000000

	vshrn.u64	$T0#lo,$D4,#26
	vmovn.i64	$D4#lo,$D4
	 vshr.u64	$T1,$D1,#26
	 vmovn.i64	$D1#lo,$D1
	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
	vbic.i32	$D4#lo,#0xfc000000
	 vbic.i32	$D1#lo,#0xfc000000

	vadd.i32	$D0#lo,$D0#lo,$T0#lo
	vshl.u32	$T0#lo,$T0#lo,#2
	 vshrn.u64	$T1#lo,$D2,#26
	 vmovn.i64	$D2#lo,$D2
	vadd.i32	$D0#lo,$D0#lo,$T0#lo	@ h4 -> h0
	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
	 vbic.i32	$D2#lo,#0xfc000000

	vshr.u32	$T0#lo,$D0#lo,#26
	vbic.i32	$D0#lo,#0xfc000000
	 vshr.u32	$T1#lo,$D3#lo,#26
	 vbic.i32	$D3#lo,#0xfc000000
	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4

	subs		$zeros,$zeros,#1
	beq		.Lsquare_break_neon

	add		$tbl0,$ctx,#(48+0*9*4)
	add		$tbl1,$ctx,#(48+1*9*4)

	vtrn.32		$R0,$D0#lo		@ r^2:r^1
	vtrn.32		$R2,$D2#lo
	vtrn.32		$R3,$D3#lo
	vtrn.32		$R1,$D1#lo
	vtrn.32		$R4,$D4#lo

	vshl.u32	$S2,$R2,#2		@ *5
	vshl.u32	$S3,$R3,#2
	vshl.u32	$S1,$R1,#2
	vshl.u32	$S4,$R4,#2
	vadd.i32	$S2,$S2,$R2
	vadd.i32	$S1,$S1,$R1
	vadd.i32	$S3,$S3,$R3
	vadd.i32	$S4,$S4,$R4

	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vst1.32		{${S4}[0]},[$tbl0,:32]
	vst1.32		{${S4}[1]},[$tbl1,:32]

	b		.Lsquare_neon

.align	4
.Lsquare_break_neon:
	add		$tbl0,$ctx,#(48+2*4*9)
	add		$tbl1,$ctx,#(48+3*4*9)

	vmov		$R0,$D0#lo		@ r^4:r^3
	vshl.u32	$S1,$D1#lo,#2		@ *5
	vmov		$R1,$D1#lo
	vshl.u32	$S2,$D2#lo,#2
	vmov		$R2,$D2#lo
	vshl.u32	$S3,$D3#lo,#2
	vmov		$R3,$D3#lo
	vshl.u32	$S4,$D4#lo,#2
	vmov		$R4,$D4#lo
	vadd.i32	$S1,$S1,$D1#lo
	vadd.i32	$S2,$S2,$D2#lo
	vadd.i32	$S3,$S3,$D3#lo
	vadd.i32	$S4,$S4,$D4#lo

	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vst1.32		{${S4}[0]},[$tbl0]
	vst1.32		{${S4}[1]},[$tbl1]

	ret				@ bx	lr
.size	poly1305_init_neon,.-poly1305_init_neon

#ifdef __KERNEL__
.globl	poly1305_blocks_neon
#endif
.type	poly1305_blocks_neon,%function
.align	5
poly1305_blocks_neon:
	ldr	ip,[$ctx,#36]		@ is_base2_26
	ands	$len,$len,#-16
	beq	.Lno_data_neon

	cmp	$len,#64
	bhs	.Lenter_neon
	tst	ip,ip			@ is_base2_26?
	beq	.Lpoly1305_blocks

.Lenter_neon:
	stmdb	sp!,{r4-r7}
	vstmdb	sp!,{d8-d15}		@ ABI specification says so

	tst	ip,ip			@ is_base2_26?
	bne	.Lbase2_26_neon

	stmdb	sp!,{r1-r3,lr}
	bl	.Lpoly1305_init_neon

	ldr	r4,[$ctx,#0]		@ load hash value base 2^32
	ldr	r5,[$ctx,#4]
	ldr	r6,[$ctx,#8]
	ldr	r7,[$ctx,#12]
	ldr	ip,[$ctx,#16]

	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
	mov	r3,r4,lsr#26
	 veor	$D0#lo,$D0#lo,$D0#lo
	mov	r4,r5,lsr#20
	orr	r3,r3,r5,lsl#6
	 veor	$D1#lo,$D1#lo,$D1#lo
	mov	r5,r6,lsr#14
	orr	r4,r4,r6,lsl#12
	 veor	$D2#lo,$D2#lo,$D2#lo
	mov	r6,r7,lsr#8
	orr	r5,r5,r7,lsl#18
	 veor	$D3#lo,$D3#lo,$D3#lo
	and	r3,r3,#0x03ffffff
	orr	r6,r6,ip,lsl#24
	 veor	$D4#lo,$D4#lo,$D4#lo
	and	r4,r4,#0x03ffffff
	mov	r1,#1
	and	r5,r5,#0x03ffffff
	str	r1,[$ctx,#36]		@ is_base2_26

	vmov.32	$D0#lo[0],r2
	vmov.32	$D1#lo[0],r3
	vmov.32	$D2#lo[0],r4
	vmov.32	$D3#lo[0],r5
	vmov.32	$D4#lo[0],r6
	adr	$zeros,.Lzeros

	ldmia	sp!,{r1-r3,lr}
	b	.Lbase2_32_neon

.align	4
.Lbase2_26_neon:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ load hash value

	veor		$D0#lo,$D0#lo,$D0#lo
	veor		$D1#lo,$D1#lo,$D1#lo
	veor		$D2#lo,$D2#lo,$D2#lo
	veor		$D3#lo,$D3#lo,$D3#lo
	veor		$D4#lo,$D4#lo,$D4#lo
	vld4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
	adr		$zeros,.Lzeros
	vld1.32		{$D4#lo[0]},[$ctx]
	sub		$ctx,$ctx,#16		@ rewind

.Lbase2_32_neon:
	add		$in2,$inp,#32
	mov		$padbit,$padbit,lsl#24
	tst		$len,#31
	beq		.Leven

	vld4.32		{$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
	vmov.32		$H4#lo[0],$padbit
	sub		$len,$len,#16
	add		$in2,$inp,#32

# ifdef	__ARMEB__
	vrev32.8	$H0,$H0
	vrev32.8	$H3,$H3
	vrev32.8	$H1,$H1
	vrev32.8	$H2,$H2
# endif
	vsri.u32	$H4#lo,$H3#lo,#8	@ base 2^32 -> base 2^26
	vshl.u32	$H3#lo,$H3#lo,#18

	vsri.u32	$H3#lo,$H2#lo,#14
	vshl.u32	$H2#lo,$H2#lo,#12
	vadd.i32	$H4#hi,$H4#lo,$D4#lo	@ add hash value and move to #hi

	vbic.i32	$H3#lo,#0xfc000000
	vsri.u32	$H2#lo,$H1#lo,#20
	vshl.u32	$H1#lo,$H1#lo,#6

	vbic.i32	$H2#lo,#0xfc000000
	vsri.u32	$H1#lo,$H0#lo,#26
	vadd.i32	$H3#hi,$H3#lo,$D3#lo

	vbic.i32	$H0#lo,#0xfc000000
	vbic.i32	$H1#lo,#0xfc000000
	vadd.i32	$H2#hi,$H2#lo,$D2#lo

	vadd.i32	$H0#hi,$H0#lo,$D0#lo
	vadd.i32	$H1#hi,$H1#lo,$D1#lo

	mov		$tbl1,$zeros
	add		$tbl0,$ctx,#48

	cmp		$len,$len
	b		.Long_tail

.align	4
.Leven:
	subs		$len,$len,#64
	it		lo
	movlo		$in2,$zeros

	vmov.i32	$H4,#1<<24		@ padbit, yes, always
	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
	add		$inp,$inp,#64
	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
	add		$in2,$in2,#64
	itt		hi
	addhi		$tbl1,$ctx,#(48+1*9*4)
	addhi		$tbl0,$ctx,#(48+3*9*4)

# ifdef	__ARMEB__
	vrev32.8	$H0,$H0
	vrev32.8	$H3,$H3
	vrev32.8	$H1,$H1
	vrev32.8	$H2,$H2
# endif
	vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
	vshl.u32	$H3,$H3,#18

	vsri.u32	$H3,$H2,#14
	vshl.u32	$H2,$H2,#12

	vbic.i32	$H3,#0xfc000000
	vsri.u32	$H2,$H1,#20
	vshl.u32	$H1,$H1,#6

	vbic.i32	$H2,#0xfc000000
	vsri.u32	$H1,$H0,#26

	vbic.i32	$H0,#0xfc000000
	vbic.i32	$H1,#0xfc000000

	bls		.Lskip_loop

	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^2
	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	b		.Loop_neon

.align	5
.Loop_neon:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
	@   \___________________/
	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
	@   \___________________/ \____________________/
	@
	@ Note that we start with inp[2:3]*r^2. This is because it
	@ doesn't depend on reduction in previous iteration.
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ inp[2:3]*r^2

	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ accumulate inp[0:1]
	vmull.u32	$D2,$H2#hi,${R0}[1]
	vadd.i32	$H0#lo,$H0#lo,$D0#lo
	vmull.u32	$D0,$H0#hi,${R0}[1]
	vadd.i32	$H3#lo,$H3#lo,$D3#lo
	vmull.u32	$D3,$H3#hi,${R0}[1]
	vmlal.u32	$D2,$H1#hi,${R1}[1]
	vadd.i32	$H1#lo,$H1#lo,$D1#lo
	vmull.u32	$D1,$H1#hi,${R0}[1]

	vadd.i32	$H4#lo,$H4#lo,$D4#lo
	vmull.u32	$D4,$H4#hi,${R0}[1]
	subs		$len,$len,#64
	vmlal.u32	$D0,$H4#hi,${S1}[1]
	it		lo
	movlo		$in2,$zeros
	vmlal.u32	$D3,$H2#hi,${R1}[1]
	vld1.32		${S4}[1],[$tbl1,:32]
	vmlal.u32	$D1,$H0#hi,${R1}[1]
	vmlal.u32	$D4,$H3#hi,${R1}[1]

	vmlal.u32	$D0,$H3#hi,${S2}[1]
	vmlal.u32	$D3,$H1#hi,${R2}[1]
	vmlal.u32	$D4,$H2#hi,${R2}[1]
	vmlal.u32	$D1,$H4#hi,${S2}[1]
	vmlal.u32	$D2,$H0#hi,${R2}[1]

	vmlal.u32	$D3,$H0#hi,${R3}[1]
	vmlal.u32	$D0,$H2#hi,${S3}[1]
	vmlal.u32	$D4,$H1#hi,${R3}[1]
	vmlal.u32	$D1,$H3#hi,${S3}[1]
	vmlal.u32	$D2,$H4#hi,${S3}[1]

	vmlal.u32	$D3,$H4#hi,${S4}[1]
	vmlal.u32	$D0,$H1#hi,${S4}[1]
	vmlal.u32	$D4,$H0#hi,${R4}[1]
	vmlal.u32	$D1,$H2#hi,${S4}[1]
	vmlal.u32	$D2,$H3#hi,${S4}[1]

	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
	add		$in2,$in2,#64

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ (hash+inp[0:1])*r^4 and accumulate

	vmlal.u32	$D3,$H3#lo,${R0}[0]
	vmlal.u32	$D0,$H0#lo,${R0}[0]
	vmlal.u32	$D4,$H4#lo,${R0}[0]
	vmlal.u32	$D1,$H1#lo,${R0}[0]
	vmlal.u32	$D2,$H2#lo,${R0}[0]
	vld1.32		${S4}[0],[$tbl0,:32]

	vmlal.u32	$D3,$H2#lo,${R1}[0]
	vmlal.u32	$D0,$H4#lo,${S1}[0]
	vmlal.u32	$D4,$H3#lo,${R1}[0]
	vmlal.u32	$D1,$H0#lo,${R1}[0]
	vmlal.u32	$D2,$H1#lo,${R1}[0]

	vmlal.u32	$D3,$H1#lo,${R2}[0]
	vmlal.u32	$D0,$H3#lo,${S2}[0]
	vmlal.u32	$D4,$H2#lo,${R2}[0]
	vmlal.u32	$D1,$H4#lo,${S2}[0]
	vmlal.u32	$D2,$H0#lo,${R2}[0]

	vmlal.u32	$D3,$H0#lo,${R3}[0]
	vmlal.u32	$D0,$H2#lo,${S3}[0]
	vmlal.u32	$D4,$H1#lo,${R3}[0]
	vmlal.u32	$D1,$H3#lo,${S3}[0]
	vmlal.u32	$D3,$H4#lo,${S4}[0]

	vmlal.u32	$D2,$H4#lo,${S3}[0]
	vmlal.u32	$D0,$H1#lo,${S4}[0]
	vmlal.u32	$D4,$H0#lo,${R4}[0]
	vmov.i32	$H4,#1<<24		@ padbit, yes, always
	vmlal.u32	$D1,$H2#lo,${S4}[0]
	vmlal.u32	$D2,$H3#lo,${S4}[0]

	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
	add		$inp,$inp,#64
# ifdef	__ARMEB__
	vrev32.8	$H0,$H0
	vrev32.8	$H1,$H1
	vrev32.8	$H2,$H2
	vrev32.8	$H3,$H3
# endif

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
	@ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.

	vshr.u64	$T0,$D3,#26
	vmovn.i64	$D3#lo,$D3
	 vshr.u64	$T1,$D0,#26
	 vmovn.i64	$D0#lo,$D0
	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
	vbic.i32	$D3#lo,#0xfc000000
	  vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
	  vshl.u32	$H3,$H3,#18
	 vbic.i32	$D0#lo,#0xfc000000

	vshrn.u64	$T0#lo,$D4,#26
	vmovn.i64	$D4#lo,$D4
	 vshr.u64	$T1,$D1,#26
	 vmovn.i64	$D1#lo,$D1
	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
	  vsri.u32	$H3,$H2,#14
	vbic.i32	$D4#lo,#0xfc000000
	  vshl.u32	$H2,$H2,#12
	 vbic.i32	$D1#lo,#0xfc000000

	vadd.i32	$D0#lo,$D0#lo,$T0#lo
	vshl.u32	$T0#lo,$T0#lo,#2
	  vbic.i32	$H3,#0xfc000000
	 vshrn.u64	$T1#lo,$D2,#26
	 vmovn.i64	$D2#lo,$D2
	vaddl.u32	$D0,$D0#lo,$T0#lo	@ h4 -> h0 [widen for a sec]
	  vsri.u32	$H2,$H1,#20
	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
	  vshl.u32	$H1,$H1,#6
	 vbic.i32	$D2#lo,#0xfc000000
	  vbic.i32	$H2,#0xfc000000

	vshrn.u64	$T0#lo,$D0,#26		@ re-narrow
	vmovn.i64	$D0#lo,$D0
	  vsri.u32	$H1,$H0,#26
	  vbic.i32	$H0,#0xfc000000
	 vshr.u32	$T1#lo,$D3#lo,#26
	 vbic.i32	$D3#lo,#0xfc000000
	vbic.i32	$D0#lo,#0xfc000000
	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
	  vbic.i32	$H1,#0xfc000000

	bhi		.Loop_neon

.Lskip_loop:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1

	add		$tbl1,$ctx,#(48+0*9*4)
	add		$tbl0,$ctx,#(48+1*9*4)
	adds		$len,$len,#32
	it		ne
	movne		$len,#0
	bne		.Long_tail

	vadd.i32	$H2#hi,$H2#lo,$D2#lo	@ add hash value and move to #hi
	vadd.i32	$H0#hi,$H0#lo,$D0#lo
	vadd.i32	$H3#hi,$H3#lo,$D3#lo
	vadd.i32	$H1#hi,$H1#lo,$D1#lo
	vadd.i32	$H4#hi,$H4#lo,$D4#lo

.Long_tail:
	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^1
	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^2

	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ can be redundant
	vmull.u32	$D2,$H2#hi,$R0
	vadd.i32	$H0#lo,$H0#lo,$D0#lo
	vmull.u32	$D0,$H0#hi,$R0
	vadd.i32	$H3#lo,$H3#lo,$D3#lo
	vmull.u32	$D3,$H3#hi,$R0
	vadd.i32	$H1#lo,$H1#lo,$D1#lo
	vmull.u32	$D1,$H1#hi,$R0
	vadd.i32	$H4#lo,$H4#lo,$D4#lo
	vmull.u32	$D4,$H4#hi,$R0

	vmlal.u32	$D0,$H4#hi,$S1
	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vmlal.u32	$D3,$H2#hi,$R1
	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vmlal.u32	$D1,$H0#hi,$R1
	vmlal.u32	$D4,$H3#hi,$R1
	vmlal.u32	$D2,$H1#hi,$R1

	vmlal.u32	$D3,$H1#hi,$R2
	vld1.32		${S4}[1],[$tbl1,:32]
	vmlal.u32	$D0,$H3#hi,$S2
	vld1.32		${S4}[0],[$tbl0,:32]
	vmlal.u32	$D4,$H2#hi,$R2
	vmlal.u32	$D1,$H4#hi,$S2
	vmlal.u32	$D2,$H0#hi,$R2

	vmlal.u32	$D3,$H0#hi,$R3
	 it		ne
	 addne		$tbl1,$ctx,#(48+2*9*4)
	vmlal.u32	$D0,$H2#hi,$S3
	 it		ne
	 addne		$tbl0,$ctx,#(48+3*9*4)
	vmlal.u32	$D4,$H1#hi,$R3
	vmlal.u32	$D1,$H3#hi,$S3
	vmlal.u32	$D2,$H4#hi,$S3

	vmlal.u32	$D3,$H4#hi,$S4
	 vorn		$MASK,$MASK,$MASK	@ all-ones, can be redundant
	vmlal.u32	$D0,$H1#hi,$S4
	 vshr.u64	$MASK,$MASK,#38
	vmlal.u32	$D4,$H0#hi,$R4
	vmlal.u32	$D1,$H2#hi,$S4
	vmlal.u32	$D2,$H3#hi,$S4

	beq		.Lshort_tail

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ (hash+inp[0:1])*r^4:r^3 and accumulate

	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^3
	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4

	vmlal.u32	$D2,$H2#lo,$R0
	vmlal.u32	$D0,$H0#lo,$R0
	vmlal.u32	$D3,$H3#lo,$R0
	vmlal.u32	$D1,$H1#lo,$R0
	vmlal.u32	$D4,$H4#lo,$R0

	vmlal.u32	$D0,$H4#lo,$S1
	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vmlal.u32	$D3,$H2#lo,$R1
	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vmlal.u32	$D1,$H0#lo,$R1
	vmlal.u32	$D4,$H3#lo,$R1
	vmlal.u32	$D2,$H1#lo,$R1

	vmlal.u32	$D3,$H1#lo,$R2
	vld1.32		${S4}[1],[$tbl1,:32]
	vmlal.u32	$D0,$H3#lo,$S2
	vld1.32		${S4}[0],[$tbl0,:32]
	vmlal.u32	$D4,$H2#lo,$R2
	vmlal.u32	$D1,$H4#lo,$S2
	vmlal.u32	$D2,$H0#lo,$R2

	vmlal.u32	$D3,$H0#lo,$R3
	vmlal.u32	$D0,$H2#lo,$S3
	vmlal.u32	$D4,$H1#lo,$R3
	vmlal.u32	$D1,$H3#lo,$S3
	vmlal.u32	$D2,$H4#lo,$S3

	vmlal.u32	$D3,$H4#lo,$S4
	 vorn		$MASK,$MASK,$MASK	@ all-ones
	vmlal.u32	$D0,$H1#lo,$S4
	 vshr.u64	$MASK,$MASK,#38
	vmlal.u32	$D4,$H0#lo,$R4
	vmlal.u32	$D1,$H2#lo,$S4
	vmlal.u32	$D2,$H3#lo,$S4

.Lshort_tail:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ horizontal addition

	vadd.i64	$D3#lo,$D3#lo,$D3#hi
	vadd.i64	$D0#lo,$D0#lo,$D0#hi
	vadd.i64	$D4#lo,$D4#lo,$D4#hi
	vadd.i64	$D1#lo,$D1#lo,$D1#hi
	vadd.i64	$D2#lo,$D2#lo,$D2#hi

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ lazy reduction, but without narrowing

	vshr.u64	$T0,$D3,#26
	vand.i64	$D3,$D3,$MASK
	 vshr.u64	$T1,$D0,#26
	 vand.i64	$D0,$D0,$MASK
	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1

	vshr.u64	$T0,$D4,#26
	vand.i64	$D4,$D4,$MASK
	 vshr.u64	$T1,$D1,#26
	 vand.i64	$D1,$D1,$MASK
	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2

	vadd.i64	$D0,$D0,$T0
	vshl.u64	$T0,$T0,#2
	 vshr.u64	$T1,$D2,#26
	 vand.i64	$D2,$D2,$MASK
	vadd.i64	$D0,$D0,$T0		@ h4 -> h0
	 vadd.i64	$D3,$D3,$T1		@ h2 -> h3

	vshr.u64	$T0,$D0,#26
	vand.i64	$D0,$D0,$MASK
	 vshr.u64	$T1,$D3,#26
	 vand.i64	$D3,$D3,$MASK
	vadd.i64	$D1,$D1,$T0		@ h0 -> h1
	 vadd.i64	$D4,$D4,$T1		@ h3 -> h4

	cmp		$len,#0
	bne		.Leven

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ store hash value

	vst4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
	vst1.32		{$D4#lo[0]},[$ctx]

	vldmia	sp!,{d8-d15}			@ epilogue
	ldmia	sp!,{r4-r7}
.Lno_data_neon:
	ret					@ bx	lr
.size	poly1305_blocks_neon,.-poly1305_blocks_neon

#ifdef __KERNEL__
.globl	poly1305_emit_neon
#endif
.type	poly1305_emit_neon,%function
.align	5
poly1305_emit_neon:
	ldr	ip,[$ctx,#36]		@ is_base2_26

	stmdb	sp!,{r4-r11}

	tst	ip,ip
	beq	.Lpoly1305_emit_enter

	ldmia	$ctx,{$h0-$h4}
	eor	$g0,$g0,$g0

	adds	$h0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
	mov	$h1,$h1,lsr#6
	adcs	$h1,$h1,$h2,lsl#20
	mov	$h2,$h2,lsr#12
	adcs	$h2,$h2,$h3,lsl#14
	mov	$h3,$h3,lsr#18
	adcs	$h3,$h3,$h4,lsl#8
	adc	$h4,$g0,$h4,lsr#24	@ can be partially reduced ...

	and	$g0,$h4,#-4		@ ... so reduce
	and	$h4,$h3,#3
	add	$g0,$g0,$g0,lsr#2	@ *= 5
	adds	$h0,$h0,$g0
	adcs	$h1,$h1,#0
	adcs	$h2,$h2,#0
	adcs	$h3,$h3,#0
	adc	$h4,$h4,#0

	adds	$g0,$h0,#5		@ compare to modulus
	adcs	$g1,$h1,#0
	adcs	$g2,$h2,#0
	adcs	$g3,$h3,#0
	adc	$g4,$h4,#0
	tst	$g4,#4			@ did it carry/borrow?

	it	ne
	movne	$h0,$g0
	ldr	$g0,[$nonce,#0]
	it	ne
	movne	$h1,$g1
	ldr	$g1,[$nonce,#4]
	it	ne
	movne	$h2,$g2
	ldr	$g2,[$nonce,#8]
	it	ne
	movne	$h3,$g3
	ldr	$g3,[$nonce,#12]

	adds	$h0,$h0,$g0		@ accumulate nonce
	adcs	$h1,$h1,$g1
	adcs	$h2,$h2,$g2
	adc	$h3,$h3,$g3

# ifdef __ARMEB__
	rev	$h0,$h0
	rev	$h1,$h1
	rev	$h2,$h2
	rev	$h3,$h3
# endif
	str	$h0,[$mac,#0]		@ store the result
	str	$h1,[$mac,#4]
	str	$h2,[$mac,#8]
	str	$h3,[$mac,#12]

	ldmia	sp!,{r4-r11}
	ret				@ bx	lr
.size	poly1305_emit_neon,.-poly1305_emit_neon

.align	5
.Lzeros:
.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
# ifndef __KERNEL__
.LOPENSSL_armcap:
.word	OPENSSL_armcap_P-.Lpoly1305_init
# endif
#endif
___
}	}
$code.=<<___;
.align	2
#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
.comm   OPENSSL_armcap_P,4,4
#endif
___

open SELF,$0;
while(<SELF>) {
	next if (/^#!/);
	last if (!s/^#/@/ and !/^$/);
	print;
}
close SELF;

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

	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo	or
	s/\bret\b/bx	lr/go						or
	s/\bbx\s+lr\b/.word\t0xe12fff1e/go;	# make it possible to compile with -march=armv4

	print $_,"\n";
}
close STDOUT; # enforce flush