summaryrefslogtreecommitdiffstats
path: root/arch/arm64/crypto/poly1305-armv8.pl
blob: cbc980fb02e3357feb25aad8f93c1ec86c11247d (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
#!/usr/bin/env perl
# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
#
# ====================================================================
# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
# project.
# ====================================================================
#
# This module implements Poly1305 hash for ARMv8.
#
# June 2015
#
# Numbers are cycles per processed byte with poly1305_blocks alone.
#
#		IALU/gcc-4.9	NEON
#
# Apple A7	1.86/+5%	0.72
# Cortex-A53	2.69/+58%	1.47
# Cortex-A57	2.70/+7%	1.14
# Denver	1.64/+50%	1.18(*)
# X-Gene	2.13/+68%	2.27
# Mongoose	1.77/+75%	1.12
# Kryo		2.70/+55%	1.13
# ThunderX2	1.17/+95%	1.36
#
# (*)	estimate based on resources availability is less than 1.0,
#	i.e. measured result is worse than expected, presumably binary
#	translator is not almighty;

$flavour=shift;
$output=shift;

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";
}

my ($ctx,$inp,$len,$padbit) = map("x$_",(0..3));
my ($mac,$nonce)=($inp,$len);

my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14));

$code.=<<___;
#ifndef __KERNEL__
# include "arm_arch.h"
.extern	OPENSSL_armcap_P
#endif

.text

// forward "declarations" are required for Apple
.globl	poly1305_blocks
.globl	poly1305_emit

.globl	poly1305_init
.type	poly1305_init,%function
.align	5
poly1305_init:
	cmp	$inp,xzr
	stp	xzr,xzr,[$ctx]		// zero hash value
	stp	xzr,xzr,[$ctx,#16]	// [along with is_base2_26]

	csel	x0,xzr,x0,eq
	b.eq	.Lno_key

#ifndef	__KERNEL__
	adrp	x17,OPENSSL_armcap_P
	ldr	w17,[x17,#:lo12:OPENSSL_armcap_P]
#endif

	ldp	$r0,$r1,[$inp]		// load key
	mov	$s1,#0xfffffffc0fffffff
	movk	$s1,#0x0fff,lsl#48
#ifdef	__AARCH64EB__
	rev	$r0,$r0			// flip bytes
	rev	$r1,$r1
#endif
	and	$r0,$r0,$s1		// &=0ffffffc0fffffff
	and	$s1,$s1,#-4
	and	$r1,$r1,$s1		// &=0ffffffc0ffffffc
	mov	w#$s1,#-1
	stp	$r0,$r1,[$ctx,#32]	// save key value
	str	w#$s1,[$ctx,#48]	// impossible key power value

#ifndef	__KERNEL__
	tst	w17,#ARMV7_NEON

	adr	$d0,.Lpoly1305_blocks
	adr	$r0,.Lpoly1305_blocks_neon
	adr	$d1,.Lpoly1305_emit

	csel	$d0,$d0,$r0,eq

# ifdef	__ILP32__
	stp	w#$d0,w#$d1,[$len]
# else
	stp	$d0,$d1,[$len]
# endif
#endif
	mov	x0,#1
.Lno_key:
	ret
.size	poly1305_init,.-poly1305_init

.type	poly1305_blocks,%function
.align	5
poly1305_blocks:
.Lpoly1305_blocks:
	ands	$len,$len,#-16
	b.eq	.Lno_data

	ldp	$h0,$h1,[$ctx]		// load hash value
	ldp	$h2,x17,[$ctx,#16]	// [along with is_base2_26]
	ldp	$r0,$r1,[$ctx,#32]	// load key value

#ifdef	__AARCH64EB__
	lsr	$d0,$h0,#32
	mov	w#$d1,w#$h0
	lsr	$d2,$h1,#32
	mov	w15,w#$h1
	lsr	x16,$h2,#32
#else
	mov	w#$d0,w#$h0
	lsr	$d1,$h0,#32
	mov	w#$d2,w#$h1
	lsr	x15,$h1,#32
	mov	w16,w#$h2
#endif

	add	$d0,$d0,$d1,lsl#26	// base 2^26 -> base 2^64
	lsr	$d1,$d2,#12
	adds	$d0,$d0,$d2,lsl#52
	add	$d1,$d1,x15,lsl#14
	adc	$d1,$d1,xzr
	lsr	$d2,x16,#24
	adds	$d1,$d1,x16,lsl#40
	adc	$d2,$d2,xzr

	cmp	x17,#0			// is_base2_26?
	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
	csel	$h0,$h0,$d0,eq		// choose between radixes
	csel	$h1,$h1,$d1,eq
	csel	$h2,$h2,$d2,eq

.Loop:
	ldp	$t0,$t1,[$inp],#16	// load input
	sub	$len,$len,#16
#ifdef	__AARCH64EB__
	rev	$t0,$t0
	rev	$t1,$t1
#endif
	adds	$h0,$h0,$t0		// accumulate input
	adcs	$h1,$h1,$t1

	mul	$d0,$h0,$r0		// h0*r0
	adc	$h2,$h2,$padbit
	umulh	$d1,$h0,$r0

	mul	$t0,$h1,$s1		// h1*5*r1
	umulh	$t1,$h1,$s1

	adds	$d0,$d0,$t0
	mul	$t0,$h0,$r1		// h0*r1
	adc	$d1,$d1,$t1
	umulh	$d2,$h0,$r1

	adds	$d1,$d1,$t0
	mul	$t0,$h1,$r0		// h1*r0
	adc	$d2,$d2,xzr
	umulh	$t1,$h1,$r0

	adds	$d1,$d1,$t0
	mul	$t0,$h2,$s1		// h2*5*r1
	adc	$d2,$d2,$t1
	mul	$t1,$h2,$r0		// h2*r0

	adds	$d1,$d1,$t0
	adc	$d2,$d2,$t1

	and	$t0,$d2,#-4		// final reduction
	and	$h2,$d2,#3
	add	$t0,$t0,$d2,lsr#2
	adds	$h0,$d0,$t0
	adcs	$h1,$d1,xzr
	adc	$h2,$h2,xzr

	cbnz	$len,.Loop

	stp	$h0,$h1,[$ctx]		// store hash value
	stp	$h2,xzr,[$ctx,#16]	// [and clear is_base2_26]

.Lno_data:
	ret
.size	poly1305_blocks,.-poly1305_blocks

.type	poly1305_emit,%function
.align	5
poly1305_emit:
.Lpoly1305_emit:
	ldp	$h0,$h1,[$ctx]		// load hash base 2^64
	ldp	$h2,$r0,[$ctx,#16]	// [along with is_base2_26]
	ldp	$t0,$t1,[$nonce]	// load nonce

#ifdef	__AARCH64EB__
	lsr	$d0,$h0,#32
	mov	w#$d1,w#$h0
	lsr	$d2,$h1,#32
	mov	w15,w#$h1
	lsr	x16,$h2,#32
#else
	mov	w#$d0,w#$h0
	lsr	$d1,$h0,#32
	mov	w#$d2,w#$h1
	lsr	x15,$h1,#32
	mov	w16,w#$h2
#endif

	add	$d0,$d0,$d1,lsl#26	// base 2^26 -> base 2^64
	lsr	$d1,$d2,#12
	adds	$d0,$d0,$d2,lsl#52
	add	$d1,$d1,x15,lsl#14
	adc	$d1,$d1,xzr
	lsr	$d2,x16,#24
	adds	$d1,$d1,x16,lsl#40
	adc	$d2,$d2,xzr

	cmp	$r0,#0			// is_base2_26?
	csel	$h0,$h0,$d0,eq		// choose between radixes
	csel	$h1,$h1,$d1,eq
	csel	$h2,$h2,$d2,eq

	adds	$d0,$h0,#5		// compare to modulus
	adcs	$d1,$h1,xzr
	adc	$d2,$h2,xzr

	tst	$d2,#-4			// see if it's carried/borrowed

	csel	$h0,$h0,$d0,eq
	csel	$h1,$h1,$d1,eq

#ifdef	__AARCH64EB__
	ror	$t0,$t0,#32		// flip nonce words
	ror	$t1,$t1,#32
#endif
	adds	$h0,$h0,$t0		// accumulate nonce
	adc	$h1,$h1,$t1
#ifdef	__AARCH64EB__
	rev	$h0,$h0			// flip output bytes
	rev	$h1,$h1
#endif
	stp	$h0,$h1,[$mac]		// write result

	ret
.size	poly1305_emit,.-poly1305_emit
___
my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("v$_.4s",(0..8));
my ($IN01_0,$IN01_1,$IN01_2,$IN01_3,$IN01_4) = map("v$_.2s",(9..13));
my ($IN23_0,$IN23_1,$IN23_2,$IN23_3,$IN23_4) = map("v$_.2s",(14..18));
my ($ACC0,$ACC1,$ACC2,$ACC3,$ACC4) = map("v$_.2d",(19..23));
my ($H0,$H1,$H2,$H3,$H4) = map("v$_.2s",(24..28));
my ($T0,$T1,$MASK) = map("v$_",(29..31));

my ($in2,$zeros)=("x16","x17");
my $is_base2_26 = $zeros;		# borrow

$code.=<<___;
.type	poly1305_mult,%function
.align	5
poly1305_mult:
	mul	$d0,$h0,$r0		// h0*r0
	umulh	$d1,$h0,$r0

	mul	$t0,$h1,$s1		// h1*5*r1
	umulh	$t1,$h1,$s1

	adds	$d0,$d0,$t0
	mul	$t0,$h0,$r1		// h0*r1
	adc	$d1,$d1,$t1
	umulh	$d2,$h0,$r1

	adds	$d1,$d1,$t0
	mul	$t0,$h1,$r0		// h1*r0
	adc	$d2,$d2,xzr
	umulh	$t1,$h1,$r0

	adds	$d1,$d1,$t0
	mul	$t0,$h2,$s1		// h2*5*r1
	adc	$d2,$d2,$t1
	mul	$t1,$h2,$r0		// h2*r0

	adds	$d1,$d1,$t0
	adc	$d2,$d2,$t1

	and	$t0,$d2,#-4		// final reduction
	and	$h2,$d2,#3
	add	$t0,$t0,$d2,lsr#2
	adds	$h0,$d0,$t0
	adcs	$h1,$d1,xzr
	adc	$h2,$h2,xzr

	ret
.size	poly1305_mult,.-poly1305_mult

.type	poly1305_splat,%function
.align	4
poly1305_splat:
	and	x12,$h0,#0x03ffffff	// base 2^64 -> base 2^26
	ubfx	x13,$h0,#26,#26
	extr	x14,$h1,$h0,#52
	and	x14,x14,#0x03ffffff
	ubfx	x15,$h1,#14,#26
	extr	x16,$h2,$h1,#40

	str	w12,[$ctx,#16*0]	// r0
	add	w12,w13,w13,lsl#2	// r1*5
	str	w13,[$ctx,#16*1]	// r1
	add	w13,w14,w14,lsl#2	// r2*5
	str	w12,[$ctx,#16*2]	// s1
	str	w14,[$ctx,#16*3]	// r2
	add	w14,w15,w15,lsl#2	// r3*5
	str	w13,[$ctx,#16*4]	// s2
	str	w15,[$ctx,#16*5]	// r3
	add	w15,w16,w16,lsl#2	// r4*5
	str	w14,[$ctx,#16*6]	// s3
	str	w16,[$ctx,#16*7]	// r4
	str	w15,[$ctx,#16*8]	// s4

	ret
.size	poly1305_splat,.-poly1305_splat

#ifdef	__KERNEL__
.globl	poly1305_blocks_neon
#endif
.type	poly1305_blocks_neon,%function
.align	5
poly1305_blocks_neon:
.Lpoly1305_blocks_neon:
	ldr	$is_base2_26,[$ctx,#24]
	cmp	$len,#128
	b.lo	.Lpoly1305_blocks

	.inst	0xd503233f		// paciasp
	stp	x29,x30,[sp,#-80]!
	add	x29,sp,#0

	stp	d8,d9,[sp,#16]		// meet ABI requirements
	stp	d10,d11,[sp,#32]
	stp	d12,d13,[sp,#48]
	stp	d14,d15,[sp,#64]

	cbz	$is_base2_26,.Lbase2_64_neon

	ldp	w10,w11,[$ctx]		// load hash value base 2^26
	ldp	w12,w13,[$ctx,#8]
	ldr	w14,[$ctx,#16]

	tst	$len,#31
	b.eq	.Leven_neon

	ldp	$r0,$r1,[$ctx,#32]	// load key value

	add	$h0,x10,x11,lsl#26	// base 2^26 -> base 2^64
	lsr	$h1,x12,#12
	adds	$h0,$h0,x12,lsl#52
	add	$h1,$h1,x13,lsl#14
	adc	$h1,$h1,xzr
	lsr	$h2,x14,#24
	adds	$h1,$h1,x14,lsl#40
	adc	$d2,$h2,xzr		// can be partially reduced...

	ldp	$d0,$d1,[$inp],#16	// load input
	sub	$len,$len,#16
	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)

#ifdef	__AARCH64EB__
	rev	$d0,$d0
	rev	$d1,$d1
#endif
	adds	$h0,$h0,$d0		// accumulate input
	adcs	$h1,$h1,$d1
	adc	$h2,$h2,$padbit

	bl	poly1305_mult

	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
	ubfx	x11,$h0,#26,#26
	extr	x12,$h1,$h0,#52
	and	x12,x12,#0x03ffffff
	ubfx	x13,$h1,#14,#26
	extr	x14,$h2,$h1,#40

	b	.Leven_neon

.align	4
.Lbase2_64_neon:
	ldp	$r0,$r1,[$ctx,#32]	// load key value

	ldp	$h0,$h1,[$ctx]		// load hash value base 2^64
	ldr	$h2,[$ctx,#16]

	tst	$len,#31
	b.eq	.Linit_neon

	ldp	$d0,$d1,[$inp],#16	// load input
	sub	$len,$len,#16
	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
#ifdef	__AARCH64EB__
	rev	$d0,$d0
	rev	$d1,$d1
#endif
	adds	$h0,$h0,$d0		// accumulate input
	adcs	$h1,$h1,$d1
	adc	$h2,$h2,$padbit

	bl	poly1305_mult

.Linit_neon:
	ldr	w17,[$ctx,#48]		// first table element
	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
	ubfx	x11,$h0,#26,#26
	extr	x12,$h1,$h0,#52
	and	x12,x12,#0x03ffffff
	ubfx	x13,$h1,#14,#26
	extr	x14,$h2,$h1,#40

	cmp	w17,#-1			// is value impossible?
	b.ne	.Leven_neon

	fmov	${H0},x10
	fmov	${H1},x11
	fmov	${H2},x12
	fmov	${H3},x13
	fmov	${H4},x14

	////////////////////////////////// initialize r^n table
	mov	$h0,$r0			// r^1
	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
	mov	$h1,$r1
	mov	$h2,xzr
	add	$ctx,$ctx,#48+12
	bl	poly1305_splat

	bl	poly1305_mult		// r^2
	sub	$ctx,$ctx,#4
	bl	poly1305_splat

	bl	poly1305_mult		// r^3
	sub	$ctx,$ctx,#4
	bl	poly1305_splat

	bl	poly1305_mult		// r^4
	sub	$ctx,$ctx,#4
	bl	poly1305_splat
	sub	$ctx,$ctx,#48		// restore original $ctx
	b	.Ldo_neon

.align	4
.Leven_neon:
	fmov	${H0},x10
	fmov	${H1},x11
	fmov	${H2},x12
	fmov	${H3},x13
	fmov	${H4},x14

.Ldo_neon:
	ldp	x8,x12,[$inp,#32]	// inp[2:3]
	subs	$len,$len,#64
	ldp	x9,x13,[$inp,#48]
	add	$in2,$inp,#96
	adr	$zeros,.Lzeros

	lsl	$padbit,$padbit,#24
	add	x15,$ctx,#48

#ifdef	__AARCH64EB__
	rev	x8,x8
	rev	x12,x12
	rev	x9,x9
	rev	x13,x13
#endif
	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
	and	x5,x9,#0x03ffffff
	ubfx	x6,x8,#26,#26
	ubfx	x7,x9,#26,#26
	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
	extr	x8,x12,x8,#52
	extr	x9,x13,x9,#52
	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
	fmov	$IN23_0,x4
	and	x8,x8,#0x03ffffff
	and	x9,x9,#0x03ffffff
	ubfx	x10,x12,#14,#26
	ubfx	x11,x13,#14,#26
	add	x12,$padbit,x12,lsr#40
	add	x13,$padbit,x13,lsr#40
	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
	fmov	$IN23_1,x6
	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
	fmov	$IN23_2,x8
	fmov	$IN23_3,x10
	fmov	$IN23_4,x12

	ldp	x8,x12,[$inp],#16	// inp[0:1]
	ldp	x9,x13,[$inp],#48

	ld1	{$R0,$R1,$S1,$R2},[x15],#64
	ld1	{$S2,$R3,$S3,$R4},[x15],#64
	ld1	{$S4},[x15]

#ifdef	__AARCH64EB__
	rev	x8,x8
	rev	x12,x12
	rev	x9,x9
	rev	x13,x13
#endif
	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
	and	x5,x9,#0x03ffffff
	ubfx	x6,x8,#26,#26
	ubfx	x7,x9,#26,#26
	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
	extr	x8,x12,x8,#52
	extr	x9,x13,x9,#52
	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
	fmov	$IN01_0,x4
	and	x8,x8,#0x03ffffff
	and	x9,x9,#0x03ffffff
	ubfx	x10,x12,#14,#26
	ubfx	x11,x13,#14,#26
	add	x12,$padbit,x12,lsr#40
	add	x13,$padbit,x13,lsr#40
	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
	fmov	$IN01_1,x6
	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
	movi	$MASK.2d,#-1
	fmov	$IN01_2,x8
	fmov	$IN01_3,x10
	fmov	$IN01_4,x12
	ushr	$MASK.2d,$MASK.2d,#38

	b.ls	.Lskip_loop

.align	4
.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 = h0*r4 + h1*r3   + h2*r2   + h3*r1   + h4*r0
	// d3 = h0*r3 + h1*r2   + h2*r1   + h3*r0   + h4*5*r4
	// d2 = h0*r2 + h1*r1   + h2*r0   + h3*5*r4 + h4*5*r3
	// d1 = h0*r1 + h1*r0   + h2*5*r4 + h3*5*r3 + h4*5*r2
	// d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1

	subs	$len,$len,#64
	umull	$ACC4,$IN23_0,${R4}[2]
	csel	$in2,$zeros,$in2,lo
	umull	$ACC3,$IN23_0,${R3}[2]
	umull	$ACC2,$IN23_0,${R2}[2]
	 ldp	x8,x12,[$in2],#16	// inp[2:3] (or zero)
	umull	$ACC1,$IN23_0,${R1}[2]
	 ldp	x9,x13,[$in2],#48
	umull	$ACC0,$IN23_0,${R0}[2]
#ifdef	__AARCH64EB__
	 rev	x8,x8
	 rev	x12,x12
	 rev	x9,x9
	 rev	x13,x13
#endif

	umlal	$ACC4,$IN23_1,${R3}[2]
	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
	umlal	$ACC3,$IN23_1,${R2}[2]
	 and	x5,x9,#0x03ffffff
	umlal	$ACC2,$IN23_1,${R1}[2]
	 ubfx	x6,x8,#26,#26
	umlal	$ACC1,$IN23_1,${R0}[2]
	 ubfx	x7,x9,#26,#26
	umlal	$ACC0,$IN23_1,${S4}[2]
	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32

	umlal	$ACC4,$IN23_2,${R2}[2]
	 extr	x8,x12,x8,#52
	umlal	$ACC3,$IN23_2,${R1}[2]
	 extr	x9,x13,x9,#52
	umlal	$ACC2,$IN23_2,${R0}[2]
	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
	umlal	$ACC1,$IN23_2,${S4}[2]
	 fmov	$IN23_0,x4
	umlal	$ACC0,$IN23_2,${S3}[2]
	 and	x8,x8,#0x03ffffff

	umlal	$ACC4,$IN23_3,${R1}[2]
	 and	x9,x9,#0x03ffffff
	umlal	$ACC3,$IN23_3,${R0}[2]
	 ubfx	x10,x12,#14,#26
	umlal	$ACC2,$IN23_3,${S4}[2]
	 ubfx	x11,x13,#14,#26
	umlal	$ACC1,$IN23_3,${S3}[2]
	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
	umlal	$ACC0,$IN23_3,${S2}[2]
	 fmov	$IN23_1,x6

	add	$IN01_2,$IN01_2,$H2
	 add	x12,$padbit,x12,lsr#40
	umlal	$ACC4,$IN23_4,${R0}[2]
	 add	x13,$padbit,x13,lsr#40
	umlal	$ACC3,$IN23_4,${S4}[2]
	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
	umlal	$ACC2,$IN23_4,${S3}[2]
	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
	umlal	$ACC1,$IN23_4,${S2}[2]
	 fmov	$IN23_2,x8
	umlal	$ACC0,$IN23_4,${S1}[2]
	 fmov	$IN23_3,x10

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

	add	$IN01_0,$IN01_0,$H0
	 fmov	$IN23_4,x12
	umlal	$ACC3,$IN01_2,${R1}[0]
	 ldp	x8,x12,[$inp],#16	// inp[0:1]
	umlal	$ACC0,$IN01_2,${S3}[0]
	 ldp	x9,x13,[$inp],#48
	umlal	$ACC4,$IN01_2,${R2}[0]
	umlal	$ACC1,$IN01_2,${S4}[0]
	umlal	$ACC2,$IN01_2,${R0}[0]
#ifdef	__AARCH64EB__
	 rev	x8,x8
	 rev	x12,x12
	 rev	x9,x9
	 rev	x13,x13
#endif

	add	$IN01_1,$IN01_1,$H1
	umlal	$ACC3,$IN01_0,${R3}[0]
	umlal	$ACC4,$IN01_0,${R4}[0]
	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
	umlal	$ACC2,$IN01_0,${R2}[0]
	 and	x5,x9,#0x03ffffff
	umlal	$ACC0,$IN01_0,${R0}[0]
	 ubfx	x6,x8,#26,#26
	umlal	$ACC1,$IN01_0,${R1}[0]
	 ubfx	x7,x9,#26,#26

	add	$IN01_3,$IN01_3,$H3
	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
	umlal	$ACC3,$IN01_1,${R2}[0]
	 extr	x8,x12,x8,#52
	umlal	$ACC4,$IN01_1,${R3}[0]
	 extr	x9,x13,x9,#52
	umlal	$ACC0,$IN01_1,${S4}[0]
	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
	umlal	$ACC2,$IN01_1,${R1}[0]
	 fmov	$IN01_0,x4
	umlal	$ACC1,$IN01_1,${R0}[0]
	 and	x8,x8,#0x03ffffff

	add	$IN01_4,$IN01_4,$H4
	 and	x9,x9,#0x03ffffff
	umlal	$ACC3,$IN01_3,${R0}[0]
	 ubfx	x10,x12,#14,#26
	umlal	$ACC0,$IN01_3,${S2}[0]
	 ubfx	x11,x13,#14,#26
	umlal	$ACC4,$IN01_3,${R1}[0]
	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
	umlal	$ACC1,$IN01_3,${S3}[0]
	 fmov	$IN01_1,x6
	umlal	$ACC2,$IN01_3,${S4}[0]
	 add	x12,$padbit,x12,lsr#40

	umlal	$ACC3,$IN01_4,${S4}[0]
	 add	x13,$padbit,x13,lsr#40
	umlal	$ACC0,$IN01_4,${S1}[0]
	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
	umlal	$ACC4,$IN01_4,${R0}[0]
	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
	umlal	$ACC1,$IN01_4,${S2}[0]
	 fmov	$IN01_2,x8
	umlal	$ACC2,$IN01_4,${S3}[0]
	 fmov	$IN01_3,x10
	 fmov	$IN01_4,x12

	/////////////////////////////////////////////////////////////////
	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
	// and P. Schwabe
	//
	// [see discussion in poly1305-armv4 module]

	ushr	$T0.2d,$ACC3,#26
	xtn	$H3,$ACC3
	 ushr	$T1.2d,$ACC0,#26
	 and	$ACC0,$ACC0,$MASK.2d
	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
	bic	$H3,#0xfc,lsl#24	// &=0x03ffffff
	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1

	ushr	$T0.2d,$ACC4,#26
	xtn	$H4,$ACC4
	 ushr	$T1.2d,$ACC1,#26
	 xtn	$H1,$ACC1
	bic	$H4,#0xfc,lsl#24
	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2

	add	$ACC0,$ACC0,$T0.2d
	shl	$T0.2d,$T0.2d,#2
	 shrn	$T1.2s,$ACC2,#26
	 xtn	$H2,$ACC2
	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
	 bic	$H1,#0xfc,lsl#24
	 add	$H3,$H3,$T1.2s		// h2 -> h3
	 bic	$H2,#0xfc,lsl#24

	shrn	$T0.2s,$ACC0,#26
	xtn	$H0,$ACC0
	 ushr	$T1.2s,$H3,#26
	 bic	$H3,#0xfc,lsl#24
	 bic	$H0,#0xfc,lsl#24
	add	$H1,$H1,$T0.2s		// h0 -> h1
	 add	$H4,$H4,$T1.2s		// h3 -> h4

	b.hi	.Loop_neon

.Lskip_loop:
	dup	$IN23_2,${IN23_2}[0]
	add	$IN01_2,$IN01_2,$H2

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

	adds	$len,$len,#32
	b.ne	.Long_tail

	dup	$IN23_2,${IN01_2}[0]
	add	$IN23_0,$IN01_0,$H0
	add	$IN23_3,$IN01_3,$H3
	add	$IN23_1,$IN01_1,$H1
	add	$IN23_4,$IN01_4,$H4

.Long_tail:
	dup	$IN23_0,${IN23_0}[0]
	umull2	$ACC0,$IN23_2,${S3}
	umull2	$ACC3,$IN23_2,${R1}
	umull2	$ACC4,$IN23_2,${R2}
	umull2	$ACC2,$IN23_2,${R0}
	umull2	$ACC1,$IN23_2,${S4}

	dup	$IN23_1,${IN23_1}[0]
	umlal2	$ACC0,$IN23_0,${R0}
	umlal2	$ACC2,$IN23_0,${R2}
	umlal2	$ACC3,$IN23_0,${R3}
	umlal2	$ACC4,$IN23_0,${R4}
	umlal2	$ACC1,$IN23_0,${R1}

	dup	$IN23_3,${IN23_3}[0]
	umlal2	$ACC0,$IN23_1,${S4}
	umlal2	$ACC3,$IN23_1,${R2}
	umlal2	$ACC2,$IN23_1,${R1}
	umlal2	$ACC4,$IN23_1,${R3}
	umlal2	$ACC1,$IN23_1,${R0}

	dup	$IN23_4,${IN23_4}[0]
	umlal2	$ACC3,$IN23_3,${R0}
	umlal2	$ACC4,$IN23_3,${R1}
	umlal2	$ACC0,$IN23_3,${S2}
	umlal2	$ACC1,$IN23_3,${S3}
	umlal2	$ACC2,$IN23_3,${S4}

	umlal2	$ACC3,$IN23_4,${S4}
	umlal2	$ACC0,$IN23_4,${S1}
	umlal2	$ACC4,$IN23_4,${R0}
	umlal2	$ACC1,$IN23_4,${S2}
	umlal2	$ACC2,$IN23_4,${S3}

	b.eq	.Lshort_tail

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

	add	$IN01_0,$IN01_0,$H0
	umlal	$ACC3,$IN01_2,${R1}
	umlal	$ACC0,$IN01_2,${S3}
	umlal	$ACC4,$IN01_2,${R2}
	umlal	$ACC1,$IN01_2,${S4}
	umlal	$ACC2,$IN01_2,${R0}

	add	$IN01_1,$IN01_1,$H1
	umlal	$ACC3,$IN01_0,${R3}
	umlal	$ACC0,$IN01_0,${R0}
	umlal	$ACC4,$IN01_0,${R4}
	umlal	$ACC1,$IN01_0,${R1}
	umlal	$ACC2,$IN01_0,${R2}

	add	$IN01_3,$IN01_3,$H3
	umlal	$ACC3,$IN01_1,${R2}
	umlal	$ACC0,$IN01_1,${S4}
	umlal	$ACC4,$IN01_1,${R3}
	umlal	$ACC1,$IN01_1,${R0}
	umlal	$ACC2,$IN01_1,${R1}

	add	$IN01_4,$IN01_4,$H4
	umlal	$ACC3,$IN01_3,${R0}
	umlal	$ACC0,$IN01_3,${S2}
	umlal	$ACC4,$IN01_3,${R1}
	umlal	$ACC1,$IN01_3,${S3}
	umlal	$ACC2,$IN01_3,${S4}

	umlal	$ACC3,$IN01_4,${S4}
	umlal	$ACC0,$IN01_4,${S1}
	umlal	$ACC4,$IN01_4,${R0}
	umlal	$ACC1,$IN01_4,${S2}
	umlal	$ACC2,$IN01_4,${S3}

.Lshort_tail:
	////////////////////////////////////////////////////////////////
	// horizontal add

	addp	$ACC3,$ACC3,$ACC3
	 ldp	d8,d9,[sp,#16]		// meet ABI requirements
	addp	$ACC0,$ACC0,$ACC0
	 ldp	d10,d11,[sp,#32]
	addp	$ACC4,$ACC4,$ACC4
	 ldp	d12,d13,[sp,#48]
	addp	$ACC1,$ACC1,$ACC1
	 ldp	d14,d15,[sp,#64]
	addp	$ACC2,$ACC2,$ACC2
	 ldr	x30,[sp,#8]

	////////////////////////////////////////////////////////////////
	// lazy reduction, but without narrowing

	ushr	$T0.2d,$ACC3,#26
	and	$ACC3,$ACC3,$MASK.2d
	 ushr	$T1.2d,$ACC0,#26
	 and	$ACC0,$ACC0,$MASK.2d

	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1

	ushr	$T0.2d,$ACC4,#26
	and	$ACC4,$ACC4,$MASK.2d
	 ushr	$T1.2d,$ACC1,#26
	 and	$ACC1,$ACC1,$MASK.2d
	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2

	add	$ACC0,$ACC0,$T0.2d
	shl	$T0.2d,$T0.2d,#2
	 ushr	$T1.2d,$ACC2,#26
	 and	$ACC2,$ACC2,$MASK.2d
	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
	 add	$ACC3,$ACC3,$T1.2d	// h2 -> h3

	ushr	$T0.2d,$ACC0,#26
	and	$ACC0,$ACC0,$MASK.2d
	 ushr	$T1.2d,$ACC3,#26
	 and	$ACC3,$ACC3,$MASK.2d
	add	$ACC1,$ACC1,$T0.2d	// h0 -> h1
	 add	$ACC4,$ACC4,$T1.2d	// h3 -> h4

	////////////////////////////////////////////////////////////////
	// write the result, can be partially reduced

	st4	{$ACC0,$ACC1,$ACC2,$ACC3}[0],[$ctx],#16
	mov	x4,#1
	st1	{$ACC4}[0],[$ctx]
	str	x4,[$ctx,#8]		// set is_base2_26

	ldr	x29,[sp],#80
	 .inst	0xd50323bf		// autiasp
	ret
.size	poly1305_blocks_neon,.-poly1305_blocks_neon

.align	5
.Lzeros:
.long	0,0,0,0,0,0,0,0
.asciz	"Poly1305 for ARMv8, CRYPTOGAMS by \@dot-asm"
.align	2
#if !defined(__KERNEL__) && !defined(_WIN64)
.comm	OPENSSL_armcap_P,4,4
.hidden	OPENSSL_armcap_P
#endif
___

foreach (split("\n",$code)) {
	s/\b(shrn\s+v[0-9]+)\.[24]d/$1.2s/			or
	s/\b(fmov\s+)v([0-9]+)[^,]*,\s*x([0-9]+)/$1d$2,x$3/	or
	(m/\bdup\b/ and (s/\.[24]s/.2d/g or 1))			or
	(m/\b(eor|and)/ and (s/\.[248][sdh]/.16b/g or 1))	or
	(m/\bum(ul|la)l\b/ and (s/\.4s/.2s/g or 1))		or
	(m/\bum(ul|la)l2\b/ and (s/\.2s/.4s/g or 1))		or
	(m/\bst[1-4]\s+{[^}]+}\[/ and (s/\.[24]d/.s/g or 1));

	s/\.[124]([sd])\[/.$1\[/;
	s/w#x([0-9]+)/w$1/g;

	print $_,"\n";
}
close STDOUT;