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
| /*
| * ChaCha/XChaCha NEON helper functions
| *
| * Copyright (C) 2016-2018 Linaro, Ltd. <ard.biesheuvel@linaro.org>
| *
| * This program is free software; you can redistribute it and/or modify
| * it under the terms of the GNU General Public License version 2 as
| * published by the Free Software Foundation.
| *
| * Originally based on:
| * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
| *
| * Copyright (C) 2015 Martin Willi
| *
| * This program is free software; you can redistribute it and/or modify
| * it under the terms of the GNU General Public License as published by
| * the Free Software Foundation; either version 2 of the License, or
| * (at your option) any later version.
| */
|
| #include <linux/linkage.h>
| #include <asm/assembler.h>
| #include <asm/cache.h>
|
| .text
| .align 6
|
| /*
| * chacha_permute - permute one block
| *
| * Permute one 64-byte block where the state matrix is stored in the four NEON
| * registers v0-v3. It performs matrix operations on four words in parallel,
| * but requires shuffling to rearrange the words after each round.
| *
| * The round count is given in w3.
| *
| * Clobbers: w3, x10, v4, v12
| */
| SYM_FUNC_START_LOCAL(chacha_permute)
|
| adr_l x10, ROT8
| ld1 {v12.4s}, [x10]
|
| .Ldoubleround:
| // x0 += x1, x3 = rotl32(x3 ^ x0, 16)
| add v0.4s, v0.4s, v1.4s
| eor v3.16b, v3.16b, v0.16b
| rev32 v3.8h, v3.8h
|
| // x2 += x3, x1 = rotl32(x1 ^ x2, 12)
| add v2.4s, v2.4s, v3.4s
| eor v4.16b, v1.16b, v2.16b
| shl v1.4s, v4.4s, #12
| sri v1.4s, v4.4s, #20
|
| // x0 += x1, x3 = rotl32(x3 ^ x0, 8)
| add v0.4s, v0.4s, v1.4s
| eor v3.16b, v3.16b, v0.16b
| tbl v3.16b, {v3.16b}, v12.16b
|
| // x2 += x3, x1 = rotl32(x1 ^ x2, 7)
| add v2.4s, v2.4s, v3.4s
| eor v4.16b, v1.16b, v2.16b
| shl v1.4s, v4.4s, #7
| sri v1.4s, v4.4s, #25
|
| // x1 = shuffle32(x1, MASK(0, 3, 2, 1))
| ext v1.16b, v1.16b, v1.16b, #4
| // x2 = shuffle32(x2, MASK(1, 0, 3, 2))
| ext v2.16b, v2.16b, v2.16b, #8
| // x3 = shuffle32(x3, MASK(2, 1, 0, 3))
| ext v3.16b, v3.16b, v3.16b, #12
|
| // x0 += x1, x3 = rotl32(x3 ^ x0, 16)
| add v0.4s, v0.4s, v1.4s
| eor v3.16b, v3.16b, v0.16b
| rev32 v3.8h, v3.8h
|
| // x2 += x3, x1 = rotl32(x1 ^ x2, 12)
| add v2.4s, v2.4s, v3.4s
| eor v4.16b, v1.16b, v2.16b
| shl v1.4s, v4.4s, #12
| sri v1.4s, v4.4s, #20
|
| // x0 += x1, x3 = rotl32(x3 ^ x0, 8)
| add v0.4s, v0.4s, v1.4s
| eor v3.16b, v3.16b, v0.16b
| tbl v3.16b, {v3.16b}, v12.16b
|
| // x2 += x3, x1 = rotl32(x1 ^ x2, 7)
| add v2.4s, v2.4s, v3.4s
| eor v4.16b, v1.16b, v2.16b
| shl v1.4s, v4.4s, #7
| sri v1.4s, v4.4s, #25
|
| // x1 = shuffle32(x1, MASK(2, 1, 0, 3))
| ext v1.16b, v1.16b, v1.16b, #12
| // x2 = shuffle32(x2, MASK(1, 0, 3, 2))
| ext v2.16b, v2.16b, v2.16b, #8
| // x3 = shuffle32(x3, MASK(0, 3, 2, 1))
| ext v3.16b, v3.16b, v3.16b, #4
|
| subs w3, w3, #2
| b.ne .Ldoubleround
|
| ret
| SYM_FUNC_END(chacha_permute)
|
| SYM_FUNC_START(chacha_block_xor_neon)
| // x0: Input state matrix, s
| // x1: 1 data block output, o
| // x2: 1 data block input, i
| // w3: nrounds
|
| stp x29, x30, [sp, #-16]!
| mov x29, sp
|
| // x0..3 = s0..3
| ld1 {v0.4s-v3.4s}, [x0]
| ld1 {v8.4s-v11.4s}, [x0]
|
| bl chacha_permute
|
| ld1 {v4.16b-v7.16b}, [x2]
|
| // o0 = i0 ^ (x0 + s0)
| add v0.4s, v0.4s, v8.4s
| eor v0.16b, v0.16b, v4.16b
|
| // o1 = i1 ^ (x1 + s1)
| add v1.4s, v1.4s, v9.4s
| eor v1.16b, v1.16b, v5.16b
|
| // o2 = i2 ^ (x2 + s2)
| add v2.4s, v2.4s, v10.4s
| eor v2.16b, v2.16b, v6.16b
|
| // o3 = i3 ^ (x3 + s3)
| add v3.4s, v3.4s, v11.4s
| eor v3.16b, v3.16b, v7.16b
|
| st1 {v0.16b-v3.16b}, [x1]
|
| ldp x29, x30, [sp], #16
| ret
| SYM_FUNC_END(chacha_block_xor_neon)
|
| SYM_FUNC_START(hchacha_block_neon)
| // x0: Input state matrix, s
| // x1: output (8 32-bit words)
| // w2: nrounds
|
| stp x29, x30, [sp, #-16]!
| mov x29, sp
|
| ld1 {v0.4s-v3.4s}, [x0]
|
| mov w3, w2
| bl chacha_permute
|
| st1 {v0.4s}, [x1], #16
| st1 {v3.4s}, [x1]
|
| ldp x29, x30, [sp], #16
| ret
| SYM_FUNC_END(hchacha_block_neon)
|
| a0 .req w12
| a1 .req w13
| a2 .req w14
| a3 .req w15
| a4 .req w16
| a5 .req w17
| a6 .req w19
| a7 .req w20
| a8 .req w21
| a9 .req w22
| a10 .req w23
| a11 .req w24
| a12 .req w25
| a13 .req w26
| a14 .req w27
| a15 .req w28
|
| .align 6
| SYM_FUNC_START(chacha_4block_xor_neon)
| frame_push 10
|
| // x0: Input state matrix, s
| // x1: 4 data blocks output, o
| // x2: 4 data blocks input, i
| // w3: nrounds
| // x4: byte count
|
| adr_l x10, .Lpermute
| and x5, x4, #63
| add x10, x10, x5
| add x11, x10, #64
|
| //
| // This function encrypts four consecutive ChaCha blocks by loading
| // the state matrix in NEON registers four times. The algorithm performs
| // each operation on the corresponding word of each state matrix, hence
| // requires no word shuffling. For final XORing step we transpose the
| // matrix by interleaving 32- and then 64-bit words, which allows us to
| // do XOR in NEON registers.
| //
| // At the same time, a fifth block is encrypted in parallel using
| // scalar registers
| //
| adr_l x9, CTRINC // ... and ROT8
| ld1 {v30.4s-v31.4s}, [x9]
|
| // x0..15[0-3] = s0..3[0..3]
| add x8, x0, #16
| ld4r { v0.4s- v3.4s}, [x0]
| ld4r { v4.4s- v7.4s}, [x8], #16
| ld4r { v8.4s-v11.4s}, [x8], #16
| ld4r {v12.4s-v15.4s}, [x8]
|
| mov a0, v0.s[0]
| mov a1, v1.s[0]
| mov a2, v2.s[0]
| mov a3, v3.s[0]
| mov a4, v4.s[0]
| mov a5, v5.s[0]
| mov a6, v6.s[0]
| mov a7, v7.s[0]
| mov a8, v8.s[0]
| mov a9, v9.s[0]
| mov a10, v10.s[0]
| mov a11, v11.s[0]
| mov a12, v12.s[0]
| mov a13, v13.s[0]
| mov a14, v14.s[0]
| mov a15, v15.s[0]
|
| // x12 += counter values 1-4
| add v12.4s, v12.4s, v30.4s
|
| .Ldoubleround4:
| // x0 += x4, x12 = rotl32(x12 ^ x0, 16)
| // x1 += x5, x13 = rotl32(x13 ^ x1, 16)
| // x2 += x6, x14 = rotl32(x14 ^ x2, 16)
| // x3 += x7, x15 = rotl32(x15 ^ x3, 16)
| add v0.4s, v0.4s, v4.4s
| add a0, a0, a4
| add v1.4s, v1.4s, v5.4s
| add a1, a1, a5
| add v2.4s, v2.4s, v6.4s
| add a2, a2, a6
| add v3.4s, v3.4s, v7.4s
| add a3, a3, a7
|
| eor v12.16b, v12.16b, v0.16b
| eor a12, a12, a0
| eor v13.16b, v13.16b, v1.16b
| eor a13, a13, a1
| eor v14.16b, v14.16b, v2.16b
| eor a14, a14, a2
| eor v15.16b, v15.16b, v3.16b
| eor a15, a15, a3
|
| rev32 v12.8h, v12.8h
| ror a12, a12, #16
| rev32 v13.8h, v13.8h
| ror a13, a13, #16
| rev32 v14.8h, v14.8h
| ror a14, a14, #16
| rev32 v15.8h, v15.8h
| ror a15, a15, #16
|
| // x8 += x12, x4 = rotl32(x4 ^ x8, 12)
| // x9 += x13, x5 = rotl32(x5 ^ x9, 12)
| // x10 += x14, x6 = rotl32(x6 ^ x10, 12)
| // x11 += x15, x7 = rotl32(x7 ^ x11, 12)
| add v8.4s, v8.4s, v12.4s
| add a8, a8, a12
| add v9.4s, v9.4s, v13.4s
| add a9, a9, a13
| add v10.4s, v10.4s, v14.4s
| add a10, a10, a14
| add v11.4s, v11.4s, v15.4s
| add a11, a11, a15
|
| eor v16.16b, v4.16b, v8.16b
| eor a4, a4, a8
| eor v17.16b, v5.16b, v9.16b
| eor a5, a5, a9
| eor v18.16b, v6.16b, v10.16b
| eor a6, a6, a10
| eor v19.16b, v7.16b, v11.16b
| eor a7, a7, a11
|
| shl v4.4s, v16.4s, #12
| shl v5.4s, v17.4s, #12
| shl v6.4s, v18.4s, #12
| shl v7.4s, v19.4s, #12
|
| sri v4.4s, v16.4s, #20
| ror a4, a4, #20
| sri v5.4s, v17.4s, #20
| ror a5, a5, #20
| sri v6.4s, v18.4s, #20
| ror a6, a6, #20
| sri v7.4s, v19.4s, #20
| ror a7, a7, #20
|
| // x0 += x4, x12 = rotl32(x12 ^ x0, 8)
| // x1 += x5, x13 = rotl32(x13 ^ x1, 8)
| // x2 += x6, x14 = rotl32(x14 ^ x2, 8)
| // x3 += x7, x15 = rotl32(x15 ^ x3, 8)
| add v0.4s, v0.4s, v4.4s
| add a0, a0, a4
| add v1.4s, v1.4s, v5.4s
| add a1, a1, a5
| add v2.4s, v2.4s, v6.4s
| add a2, a2, a6
| add v3.4s, v3.4s, v7.4s
| add a3, a3, a7
|
| eor v12.16b, v12.16b, v0.16b
| eor a12, a12, a0
| eor v13.16b, v13.16b, v1.16b
| eor a13, a13, a1
| eor v14.16b, v14.16b, v2.16b
| eor a14, a14, a2
| eor v15.16b, v15.16b, v3.16b
| eor a15, a15, a3
|
| tbl v12.16b, {v12.16b}, v31.16b
| ror a12, a12, #24
| tbl v13.16b, {v13.16b}, v31.16b
| ror a13, a13, #24
| tbl v14.16b, {v14.16b}, v31.16b
| ror a14, a14, #24
| tbl v15.16b, {v15.16b}, v31.16b
| ror a15, a15, #24
|
| // x8 += x12, x4 = rotl32(x4 ^ x8, 7)
| // x9 += x13, x5 = rotl32(x5 ^ x9, 7)
| // x10 += x14, x6 = rotl32(x6 ^ x10, 7)
| // x11 += x15, x7 = rotl32(x7 ^ x11, 7)
| add v8.4s, v8.4s, v12.4s
| add a8, a8, a12
| add v9.4s, v9.4s, v13.4s
| add a9, a9, a13
| add v10.4s, v10.4s, v14.4s
| add a10, a10, a14
| add v11.4s, v11.4s, v15.4s
| add a11, a11, a15
|
| eor v16.16b, v4.16b, v8.16b
| eor a4, a4, a8
| eor v17.16b, v5.16b, v9.16b
| eor a5, a5, a9
| eor v18.16b, v6.16b, v10.16b
| eor a6, a6, a10
| eor v19.16b, v7.16b, v11.16b
| eor a7, a7, a11
|
| shl v4.4s, v16.4s, #7
| shl v5.4s, v17.4s, #7
| shl v6.4s, v18.4s, #7
| shl v7.4s, v19.4s, #7
|
| sri v4.4s, v16.4s, #25
| ror a4, a4, #25
| sri v5.4s, v17.4s, #25
| ror a5, a5, #25
| sri v6.4s, v18.4s, #25
| ror a6, a6, #25
| sri v7.4s, v19.4s, #25
| ror a7, a7, #25
|
| // x0 += x5, x15 = rotl32(x15 ^ x0, 16)
| // x1 += x6, x12 = rotl32(x12 ^ x1, 16)
| // x2 += x7, x13 = rotl32(x13 ^ x2, 16)
| // x3 += x4, x14 = rotl32(x14 ^ x3, 16)
| add v0.4s, v0.4s, v5.4s
| add a0, a0, a5
| add v1.4s, v1.4s, v6.4s
| add a1, a1, a6
| add v2.4s, v2.4s, v7.4s
| add a2, a2, a7
| add v3.4s, v3.4s, v4.4s
| add a3, a3, a4
|
| eor v15.16b, v15.16b, v0.16b
| eor a15, a15, a0
| eor v12.16b, v12.16b, v1.16b
| eor a12, a12, a1
| eor v13.16b, v13.16b, v2.16b
| eor a13, a13, a2
| eor v14.16b, v14.16b, v3.16b
| eor a14, a14, a3
|
| rev32 v15.8h, v15.8h
| ror a15, a15, #16
| rev32 v12.8h, v12.8h
| ror a12, a12, #16
| rev32 v13.8h, v13.8h
| ror a13, a13, #16
| rev32 v14.8h, v14.8h
| ror a14, a14, #16
|
| // x10 += x15, x5 = rotl32(x5 ^ x10, 12)
| // x11 += x12, x6 = rotl32(x6 ^ x11, 12)
| // x8 += x13, x7 = rotl32(x7 ^ x8, 12)
| // x9 += x14, x4 = rotl32(x4 ^ x9, 12)
| add v10.4s, v10.4s, v15.4s
| add a10, a10, a15
| add v11.4s, v11.4s, v12.4s
| add a11, a11, a12
| add v8.4s, v8.4s, v13.4s
| add a8, a8, a13
| add v9.4s, v9.4s, v14.4s
| add a9, a9, a14
|
| eor v16.16b, v5.16b, v10.16b
| eor a5, a5, a10
| eor v17.16b, v6.16b, v11.16b
| eor a6, a6, a11
| eor v18.16b, v7.16b, v8.16b
| eor a7, a7, a8
| eor v19.16b, v4.16b, v9.16b
| eor a4, a4, a9
|
| shl v5.4s, v16.4s, #12
| shl v6.4s, v17.4s, #12
| shl v7.4s, v18.4s, #12
| shl v4.4s, v19.4s, #12
|
| sri v5.4s, v16.4s, #20
| ror a5, a5, #20
| sri v6.4s, v17.4s, #20
| ror a6, a6, #20
| sri v7.4s, v18.4s, #20
| ror a7, a7, #20
| sri v4.4s, v19.4s, #20
| ror a4, a4, #20
|
| // x0 += x5, x15 = rotl32(x15 ^ x0, 8)
| // x1 += x6, x12 = rotl32(x12 ^ x1, 8)
| // x2 += x7, x13 = rotl32(x13 ^ x2, 8)
| // x3 += x4, x14 = rotl32(x14 ^ x3, 8)
| add v0.4s, v0.4s, v5.4s
| add a0, a0, a5
| add v1.4s, v1.4s, v6.4s
| add a1, a1, a6
| add v2.4s, v2.4s, v7.4s
| add a2, a2, a7
| add v3.4s, v3.4s, v4.4s
| add a3, a3, a4
|
| eor v15.16b, v15.16b, v0.16b
| eor a15, a15, a0
| eor v12.16b, v12.16b, v1.16b
| eor a12, a12, a1
| eor v13.16b, v13.16b, v2.16b
| eor a13, a13, a2
| eor v14.16b, v14.16b, v3.16b
| eor a14, a14, a3
|
| tbl v15.16b, {v15.16b}, v31.16b
| ror a15, a15, #24
| tbl v12.16b, {v12.16b}, v31.16b
| ror a12, a12, #24
| tbl v13.16b, {v13.16b}, v31.16b
| ror a13, a13, #24
| tbl v14.16b, {v14.16b}, v31.16b
| ror a14, a14, #24
|
| // x10 += x15, x5 = rotl32(x5 ^ x10, 7)
| // x11 += x12, x6 = rotl32(x6 ^ x11, 7)
| // x8 += x13, x7 = rotl32(x7 ^ x8, 7)
| // x9 += x14, x4 = rotl32(x4 ^ x9, 7)
| add v10.4s, v10.4s, v15.4s
| add a10, a10, a15
| add v11.4s, v11.4s, v12.4s
| add a11, a11, a12
| add v8.4s, v8.4s, v13.4s
| add a8, a8, a13
| add v9.4s, v9.4s, v14.4s
| add a9, a9, a14
|
| eor v16.16b, v5.16b, v10.16b
| eor a5, a5, a10
| eor v17.16b, v6.16b, v11.16b
| eor a6, a6, a11
| eor v18.16b, v7.16b, v8.16b
| eor a7, a7, a8
| eor v19.16b, v4.16b, v9.16b
| eor a4, a4, a9
|
| shl v5.4s, v16.4s, #7
| shl v6.4s, v17.4s, #7
| shl v7.4s, v18.4s, #7
| shl v4.4s, v19.4s, #7
|
| sri v5.4s, v16.4s, #25
| ror a5, a5, #25
| sri v6.4s, v17.4s, #25
| ror a6, a6, #25
| sri v7.4s, v18.4s, #25
| ror a7, a7, #25
| sri v4.4s, v19.4s, #25
| ror a4, a4, #25
|
| subs w3, w3, #2
| b.ne .Ldoubleround4
|
| ld4r {v16.4s-v19.4s}, [x0], #16
| ld4r {v20.4s-v23.4s}, [x0], #16
|
| // x12 += counter values 0-3
| add v12.4s, v12.4s, v30.4s
|
| // x0[0-3] += s0[0]
| // x1[0-3] += s0[1]
| // x2[0-3] += s0[2]
| // x3[0-3] += s0[3]
| add v0.4s, v0.4s, v16.4s
| mov w6, v16.s[0]
| mov w7, v17.s[0]
| add v1.4s, v1.4s, v17.4s
| mov w8, v18.s[0]
| mov w9, v19.s[0]
| add v2.4s, v2.4s, v18.4s
| add a0, a0, w6
| add a1, a1, w7
| add v3.4s, v3.4s, v19.4s
| add a2, a2, w8
| add a3, a3, w9
| CPU_BE( rev a0, a0 )
| CPU_BE( rev a1, a1 )
| CPU_BE( rev a2, a2 )
| CPU_BE( rev a3, a3 )
|
| ld4r {v24.4s-v27.4s}, [x0], #16
| ld4r {v28.4s-v31.4s}, [x0]
|
| // x4[0-3] += s1[0]
| // x5[0-3] += s1[1]
| // x6[0-3] += s1[2]
| // x7[0-3] += s1[3]
| add v4.4s, v4.4s, v20.4s
| mov w6, v20.s[0]
| mov w7, v21.s[0]
| add v5.4s, v5.4s, v21.4s
| mov w8, v22.s[0]
| mov w9, v23.s[0]
| add v6.4s, v6.4s, v22.4s
| add a4, a4, w6
| add a5, a5, w7
| add v7.4s, v7.4s, v23.4s
| add a6, a6, w8
| add a7, a7, w9
| CPU_BE( rev a4, a4 )
| CPU_BE( rev a5, a5 )
| CPU_BE( rev a6, a6 )
| CPU_BE( rev a7, a7 )
|
| // x8[0-3] += s2[0]
| // x9[0-3] += s2[1]
| // x10[0-3] += s2[2]
| // x11[0-3] += s2[3]
| add v8.4s, v8.4s, v24.4s
| mov w6, v24.s[0]
| mov w7, v25.s[0]
| add v9.4s, v9.4s, v25.4s
| mov w8, v26.s[0]
| mov w9, v27.s[0]
| add v10.4s, v10.4s, v26.4s
| add a8, a8, w6
| add a9, a9, w7
| add v11.4s, v11.4s, v27.4s
| add a10, a10, w8
| add a11, a11, w9
| CPU_BE( rev a8, a8 )
| CPU_BE( rev a9, a9 )
| CPU_BE( rev a10, a10 )
| CPU_BE( rev a11, a11 )
|
| // x12[0-3] += s3[0]
| // x13[0-3] += s3[1]
| // x14[0-3] += s3[2]
| // x15[0-3] += s3[3]
| add v12.4s, v12.4s, v28.4s
| mov w6, v28.s[0]
| mov w7, v29.s[0]
| add v13.4s, v13.4s, v29.4s
| mov w8, v30.s[0]
| mov w9, v31.s[0]
| add v14.4s, v14.4s, v30.4s
| add a12, a12, w6
| add a13, a13, w7
| add v15.4s, v15.4s, v31.4s
| add a14, a14, w8
| add a15, a15, w9
| CPU_BE( rev a12, a12 )
| CPU_BE( rev a13, a13 )
| CPU_BE( rev a14, a14 )
| CPU_BE( rev a15, a15 )
|
| // interleave 32-bit words in state n, n+1
| ldp w6, w7, [x2], #64
| zip1 v16.4s, v0.4s, v1.4s
| ldp w8, w9, [x2, #-56]
| eor a0, a0, w6
| zip2 v17.4s, v0.4s, v1.4s
| eor a1, a1, w7
| zip1 v18.4s, v2.4s, v3.4s
| eor a2, a2, w8
| zip2 v19.4s, v2.4s, v3.4s
| eor a3, a3, w9
| ldp w6, w7, [x2, #-48]
| zip1 v20.4s, v4.4s, v5.4s
| ldp w8, w9, [x2, #-40]
| eor a4, a4, w6
| zip2 v21.4s, v4.4s, v5.4s
| eor a5, a5, w7
| zip1 v22.4s, v6.4s, v7.4s
| eor a6, a6, w8
| zip2 v23.4s, v6.4s, v7.4s
| eor a7, a7, w9
| ldp w6, w7, [x2, #-32]
| zip1 v24.4s, v8.4s, v9.4s
| ldp w8, w9, [x2, #-24]
| eor a8, a8, w6
| zip2 v25.4s, v8.4s, v9.4s
| eor a9, a9, w7
| zip1 v26.4s, v10.4s, v11.4s
| eor a10, a10, w8
| zip2 v27.4s, v10.4s, v11.4s
| eor a11, a11, w9
| ldp w6, w7, [x2, #-16]
| zip1 v28.4s, v12.4s, v13.4s
| ldp w8, w9, [x2, #-8]
| eor a12, a12, w6
| zip2 v29.4s, v12.4s, v13.4s
| eor a13, a13, w7
| zip1 v30.4s, v14.4s, v15.4s
| eor a14, a14, w8
| zip2 v31.4s, v14.4s, v15.4s
| eor a15, a15, w9
|
| mov x3, #64
| subs x5, x4, #128
| add x6, x5, x2
| csel x3, x3, xzr, ge
| csel x2, x2, x6, ge
|
| // interleave 64-bit words in state n, n+2
| zip1 v0.2d, v16.2d, v18.2d
| zip2 v4.2d, v16.2d, v18.2d
| stp a0, a1, [x1], #64
| zip1 v8.2d, v17.2d, v19.2d
| zip2 v12.2d, v17.2d, v19.2d
| stp a2, a3, [x1, #-56]
| ld1 {v16.16b-v19.16b}, [x2], x3
|
| subs x6, x4, #192
| ccmp x3, xzr, #4, lt
| add x7, x6, x2
| csel x3, x3, xzr, eq
| csel x2, x2, x7, eq
|
| zip1 v1.2d, v20.2d, v22.2d
| zip2 v5.2d, v20.2d, v22.2d
| stp a4, a5, [x1, #-48]
| zip1 v9.2d, v21.2d, v23.2d
| zip2 v13.2d, v21.2d, v23.2d
| stp a6, a7, [x1, #-40]
| ld1 {v20.16b-v23.16b}, [x2], x3
|
| subs x7, x4, #256
| ccmp x3, xzr, #4, lt
| add x8, x7, x2
| csel x3, x3, xzr, eq
| csel x2, x2, x8, eq
|
| zip1 v2.2d, v24.2d, v26.2d
| zip2 v6.2d, v24.2d, v26.2d
| stp a8, a9, [x1, #-32]
| zip1 v10.2d, v25.2d, v27.2d
| zip2 v14.2d, v25.2d, v27.2d
| stp a10, a11, [x1, #-24]
| ld1 {v24.16b-v27.16b}, [x2], x3
|
| subs x8, x4, #320
| ccmp x3, xzr, #4, lt
| add x9, x8, x2
| csel x2, x2, x9, eq
|
| zip1 v3.2d, v28.2d, v30.2d
| zip2 v7.2d, v28.2d, v30.2d
| stp a12, a13, [x1, #-16]
| zip1 v11.2d, v29.2d, v31.2d
| zip2 v15.2d, v29.2d, v31.2d
| stp a14, a15, [x1, #-8]
| ld1 {v28.16b-v31.16b}, [x2]
|
| // xor with corresponding input, write to output
| tbnz x5, #63, 0f
| eor v16.16b, v16.16b, v0.16b
| eor v17.16b, v17.16b, v1.16b
| eor v18.16b, v18.16b, v2.16b
| eor v19.16b, v19.16b, v3.16b
| st1 {v16.16b-v19.16b}, [x1], #64
| cbz x5, .Lout
|
| tbnz x6, #63, 1f
| eor v20.16b, v20.16b, v4.16b
| eor v21.16b, v21.16b, v5.16b
| eor v22.16b, v22.16b, v6.16b
| eor v23.16b, v23.16b, v7.16b
| st1 {v20.16b-v23.16b}, [x1], #64
| cbz x6, .Lout
|
| tbnz x7, #63, 2f
| eor v24.16b, v24.16b, v8.16b
| eor v25.16b, v25.16b, v9.16b
| eor v26.16b, v26.16b, v10.16b
| eor v27.16b, v27.16b, v11.16b
| st1 {v24.16b-v27.16b}, [x1], #64
| cbz x7, .Lout
|
| tbnz x8, #63, 3f
| eor v28.16b, v28.16b, v12.16b
| eor v29.16b, v29.16b, v13.16b
| eor v30.16b, v30.16b, v14.16b
| eor v31.16b, v31.16b, v15.16b
| st1 {v28.16b-v31.16b}, [x1]
|
| .Lout: frame_pop
| ret
|
| // fewer than 128 bytes of in/output
| 0: ld1 {v8.16b}, [x10]
| ld1 {v9.16b}, [x11]
| movi v10.16b, #16
| sub x2, x1, #64
| add x1, x1, x5
| ld1 {v16.16b-v19.16b}, [x2]
| tbl v4.16b, {v0.16b-v3.16b}, v8.16b
| tbx v20.16b, {v16.16b-v19.16b}, v9.16b
| add v8.16b, v8.16b, v10.16b
| add v9.16b, v9.16b, v10.16b
| tbl v5.16b, {v0.16b-v3.16b}, v8.16b
| tbx v21.16b, {v16.16b-v19.16b}, v9.16b
| add v8.16b, v8.16b, v10.16b
| add v9.16b, v9.16b, v10.16b
| tbl v6.16b, {v0.16b-v3.16b}, v8.16b
| tbx v22.16b, {v16.16b-v19.16b}, v9.16b
| add v8.16b, v8.16b, v10.16b
| add v9.16b, v9.16b, v10.16b
| tbl v7.16b, {v0.16b-v3.16b}, v8.16b
| tbx v23.16b, {v16.16b-v19.16b}, v9.16b
|
| eor v20.16b, v20.16b, v4.16b
| eor v21.16b, v21.16b, v5.16b
| eor v22.16b, v22.16b, v6.16b
| eor v23.16b, v23.16b, v7.16b
| st1 {v20.16b-v23.16b}, [x1]
| b .Lout
|
| // fewer than 192 bytes of in/output
| 1: ld1 {v8.16b}, [x10]
| ld1 {v9.16b}, [x11]
| movi v10.16b, #16
| add x1, x1, x6
| tbl v0.16b, {v4.16b-v7.16b}, v8.16b
| tbx v20.16b, {v16.16b-v19.16b}, v9.16b
| add v8.16b, v8.16b, v10.16b
| add v9.16b, v9.16b, v10.16b
| tbl v1.16b, {v4.16b-v7.16b}, v8.16b
| tbx v21.16b, {v16.16b-v19.16b}, v9.16b
| add v8.16b, v8.16b, v10.16b
| add v9.16b, v9.16b, v10.16b
| tbl v2.16b, {v4.16b-v7.16b}, v8.16b
| tbx v22.16b, {v16.16b-v19.16b}, v9.16b
| add v8.16b, v8.16b, v10.16b
| add v9.16b, v9.16b, v10.16b
| tbl v3.16b, {v4.16b-v7.16b}, v8.16b
| tbx v23.16b, {v16.16b-v19.16b}, v9.16b
|
| eor v20.16b, v20.16b, v0.16b
| eor v21.16b, v21.16b, v1.16b
| eor v22.16b, v22.16b, v2.16b
| eor v23.16b, v23.16b, v3.16b
| st1 {v20.16b-v23.16b}, [x1]
| b .Lout
|
| // fewer than 256 bytes of in/output
| 2: ld1 {v4.16b}, [x10]
| ld1 {v5.16b}, [x11]
| movi v6.16b, #16
| add x1, x1, x7
| tbl v0.16b, {v8.16b-v11.16b}, v4.16b
| tbx v24.16b, {v20.16b-v23.16b}, v5.16b
| add v4.16b, v4.16b, v6.16b
| add v5.16b, v5.16b, v6.16b
| tbl v1.16b, {v8.16b-v11.16b}, v4.16b
| tbx v25.16b, {v20.16b-v23.16b}, v5.16b
| add v4.16b, v4.16b, v6.16b
| add v5.16b, v5.16b, v6.16b
| tbl v2.16b, {v8.16b-v11.16b}, v4.16b
| tbx v26.16b, {v20.16b-v23.16b}, v5.16b
| add v4.16b, v4.16b, v6.16b
| add v5.16b, v5.16b, v6.16b
| tbl v3.16b, {v8.16b-v11.16b}, v4.16b
| tbx v27.16b, {v20.16b-v23.16b}, v5.16b
|
| eor v24.16b, v24.16b, v0.16b
| eor v25.16b, v25.16b, v1.16b
| eor v26.16b, v26.16b, v2.16b
| eor v27.16b, v27.16b, v3.16b
| st1 {v24.16b-v27.16b}, [x1]
| b .Lout
|
| // fewer than 320 bytes of in/output
| 3: ld1 {v4.16b}, [x10]
| ld1 {v5.16b}, [x11]
| movi v6.16b, #16
| add x1, x1, x8
| tbl v0.16b, {v12.16b-v15.16b}, v4.16b
| tbx v28.16b, {v24.16b-v27.16b}, v5.16b
| add v4.16b, v4.16b, v6.16b
| add v5.16b, v5.16b, v6.16b
| tbl v1.16b, {v12.16b-v15.16b}, v4.16b
| tbx v29.16b, {v24.16b-v27.16b}, v5.16b
| add v4.16b, v4.16b, v6.16b
| add v5.16b, v5.16b, v6.16b
| tbl v2.16b, {v12.16b-v15.16b}, v4.16b
| tbx v30.16b, {v24.16b-v27.16b}, v5.16b
| add v4.16b, v4.16b, v6.16b
| add v5.16b, v5.16b, v6.16b
| tbl v3.16b, {v12.16b-v15.16b}, v4.16b
| tbx v31.16b, {v24.16b-v27.16b}, v5.16b
|
| eor v28.16b, v28.16b, v0.16b
| eor v29.16b, v29.16b, v1.16b
| eor v30.16b, v30.16b, v2.16b
| eor v31.16b, v31.16b, v3.16b
| st1 {v28.16b-v31.16b}, [x1]
| b .Lout
| SYM_FUNC_END(chacha_4block_xor_neon)
|
| .section ".rodata", "a", %progbits
| .align L1_CACHE_SHIFT
| .Lpermute:
| .set .Li, 0
| .rept 192
| .byte (.Li - 64)
| .set .Li, .Li + 1
| .endr
|
| CTRINC: .word 1, 2, 3, 4
| ROT8: .word 0x02010003, 0x06050407, 0x0a09080b, 0x0e0d0c0f
|
|
