summaryrefslogtreecommitdiff
path: root/arch/arm64/crypto/aes-neonbs-core.S
blob: baf450717b24ba37cac4644617e8081b25d1437d (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Bit sliced AES using NEON instructions
 *
 * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
 */

/*
 * The algorithm implemented here is described in detail by the paper
 * 'Faster and Timing-Attack Resistant AES-GCM' by Emilia Kaesper and
 * Peter Schwabe (https://eprint.iacr.org/2009/129.pdf)
 *
 * This implementation is based primarily on the OpenSSL implementation
 * for 32-bit ARM written by Andy Polyakov <appro@openssl.org>
 */

#include <linux/linkage.h>
#include <linux/cfi_types.h>
#include <asm/assembler.h>

	.text

	rounds		.req	x11
	bskey		.req	x12

	.macro		in_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
	eor		\b2, \b2, \b1
	eor		\b5, \b5, \b6
	eor		\b3, \b3, \b0
	eor		\b6, \b6, \b2
	eor		\b5, \b5, \b0
	eor		\b6, \b6, \b3
	eor		\b3, \b3, \b7
	eor		\b7, \b7, \b5
	eor		\b3, \b3, \b4
	eor		\b4, \b4, \b5
	eor		\b2, \b2, \b7
	eor		\b3, \b3, \b1
	eor		\b1, \b1, \b5
	.endm

	.macro		out_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
	eor		\b0, \b0, \b6
	eor		\b1, \b1, \b4
	eor		\b4, \b4, \b6
	eor		\b2, \b2, \b0
	eor		\b6, \b6, \b1
	eor		\b1, \b1, \b5
	eor		\b5, \b5, \b3
	eor		\b3, \b3, \b7
	eor		\b7, \b7, \b5
	eor		\b2, \b2, \b5
	eor		\b4, \b4, \b7
	.endm

	.macro		inv_in_bs_ch, b6, b1, b2, b4, b7, b0, b3, b5
	eor		\b1, \b1, \b7
	eor		\b4, \b4, \b7
	eor		\b7, \b7, \b5
	eor		\b1, \b1, \b3
	eor		\b2, \b2, \b5
	eor		\b3, \b3, \b7
	eor		\b6, \b6, \b1
	eor		\b2, \b2, \b0
	eor		\b5, \b5, \b3
	eor		\b4, \b4, \b6
	eor		\b0, \b0, \b6
	eor		\b1, \b1, \b4
	.endm

	.macro		inv_out_bs_ch, b6, b5, b0, b3, b7, b1, b4, b2
	eor		\b1, \b1, \b5
	eor		\b2, \b2, \b7
	eor		\b3, \b3, \b1
	eor		\b4, \b4, \b5
	eor		\b7, \b7, \b5
	eor		\b3, \b3, \b4
	eor 		\b5, \b5, \b0
	eor		\b3, \b3, \b7
	eor		\b6, \b6, \b2
	eor		\b2, \b2, \b1
	eor		\b6, \b6, \b3
	eor		\b3, \b3, \b0
	eor		\b5, \b5, \b6
	.endm

	.macro		mul_gf4, x0, x1, y0, y1, t0, t1
	eor 		\t0, \y0, \y1
	and		\t0, \t0, \x0
	eor		\x0, \x0, \x1
	and		\t1, \x1, \y0
	and		\x0, \x0, \y1
	eor		\x1, \t1, \t0
	eor		\x0, \x0, \t1
	.endm

	.macro		mul_gf4_n_gf4, x0, x1, y0, y1, t0, x2, x3, y2, y3, t1
	eor		\t0, \y0, \y1
	eor 		\t1, \y2, \y3
	and		\t0, \t0, \x0
	and		\t1, \t1, \x2
	eor		\x0, \x0, \x1
	eor		\x2, \x2, \x3
	and		\x1, \x1, \y0
	and		\x3, \x3, \y2
	and		\x0, \x0, \y1
	and		\x2, \x2, \y3
	eor		\x1, \x1, \x0
	eor		\x2, \x2, \x3
	eor		\x0, \x0, \t0
	eor		\x3, \x3, \t1
	.endm

	.macro		mul_gf16_2, x0, x1, x2, x3, x4, x5, x6, x7, \
				    y0, y1, y2, y3, t0, t1, t2, t3
	eor		\t0, \x0, \x2
	eor		\t1, \x1, \x3
	mul_gf4  	\x0, \x1, \y0, \y1, \t2, \t3
	eor		\y0, \y0, \y2
	eor		\y1, \y1, \y3
	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x2, \x3, \y2, \y3, \t2
	eor		\x0, \x0, \t0
	eor		\x2, \x2, \t0
	eor		\x1, \x1, \t1
	eor		\x3, \x3, \t1
	eor		\t0, \x4, \x6
	eor		\t1, \x5, \x7
	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x6, \x7, \y2, \y3, \t2
	eor		\y0, \y0, \y2
	eor		\y1, \y1, \y3
	mul_gf4  	\x4, \x5, \y0, \y1, \t2, \t3
	eor		\x4, \x4, \t0
	eor		\x6, \x6, \t0
	eor		\x5, \x5, \t1
	eor		\x7, \x7, \t1
	.endm

	.macro		inv_gf256, x0, x1, x2, x3, x4, x5, x6, x7, \
				   t0, t1, t2, t3, s0, s1, s2, s3
	eor		\t3, \x4, \x6
	eor		\t0, \x5, \x7
	eor		\t1, \x1, \x3
	eor		\s1, \x7, \x6
	eor		\s0, \x0, \x2
	eor		\s3, \t3, \t0
	orr		\t2, \t0, \t1
	and		\s2, \t3, \s0
	orr		\t3, \t3, \s0
	eor		\s0, \s0, \t1
	and		\t0, \t0, \t1
	eor		\t1, \x3, \x2
	and		\s3, \s3, \s0
	and		\s1, \s1, \t1
	eor		\t1, \x4, \x5
	eor		\s0, \x1, \x0
	eor		\t3, \t3, \s1
	eor		\t2, \t2, \s1
	and		\s1, \t1, \s0
	orr		\t1, \t1, \s0
	eor		\t3, \t3, \s3
	eor		\t0, \t0, \s1
	eor		\t2, \t2, \s2
	eor		\t1, \t1, \s3
	eor		\t0, \t0, \s2
	and		\s0, \x7, \x3
	eor		\t1, \t1, \s2
	and		\s1, \x6, \x2
	and		\s2, \x5, \x1
	orr		\s3, \x4, \x0
	eor		\t3, \t3, \s0
	eor		\t1, \t1, \s2
	eor		\s0, \t0, \s3
	eor		\t2, \t2, \s1
	and		\s2, \t3, \t1
	eor		\s1, \t2, \s2
	eor		\s3, \s0, \s2
	bsl		\s1, \t1, \s0
	not		\t0, \s0
	bsl		\s0, \s1, \s3
	bsl		\t0, \s1, \s3
	bsl		\s3, \t3, \t2
	eor		\t3, \t3, \t2
	and		\s2, \s0, \s3
	eor		\t1, \t1, \t0
	eor		\s2, \s2, \t3
	mul_gf16_2	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
			\s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3
	.endm

	.macro		sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
			      t0, t1, t2, t3, s0, s1, s2, s3
	in_bs_ch	\b0\().16b, \b1\().16b, \b2\().16b, \b3\().16b, \
			\b4\().16b, \b5\().16b, \b6\().16b, \b7\().16b
	inv_gf256	\b6\().16b, \b5\().16b, \b0\().16b, \b3\().16b, \
			\b7\().16b, \b1\().16b, \b4\().16b, \b2\().16b, \
			\t0\().16b, \t1\().16b, \t2\().16b, \t3\().16b, \
			\s0\().16b, \s1\().16b, \s2\().16b, \s3\().16b
	out_bs_ch	\b7\().16b, \b1\().16b, \b4\().16b, \b2\().16b, \
			\b6\().16b, \b5\().16b, \b0\().16b, \b3\().16b
	.endm

	.macro		inv_sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
				  t0, t1, t2, t3, s0, s1, s2, s3
	inv_in_bs_ch	\b0\().16b, \b1\().16b, \b2\().16b, \b3\().16b, \
			\b4\().16b, \b5\().16b, \b6\().16b, \b7\().16b
	inv_gf256	\b5\().16b, \b1\().16b, \b2\().16b, \b6\().16b, \
			\b3\().16b, \b7\().16b, \b0\().16b, \b4\().16b, \
			\t0\().16b, \t1\().16b, \t2\().16b, \t3\().16b, \
			\s0\().16b, \s1\().16b, \s2\().16b, \s3\().16b
	inv_out_bs_ch	\b3\().16b, \b7\().16b, \b0\().16b, \b4\().16b, \
			\b5\().16b, \b1\().16b, \b2\().16b, \b6\().16b
	.endm

	.macro		enc_next_rk
	ldp		q16, q17, [bskey], #128
	ldp		q18, q19, [bskey, #-96]
	ldp		q20, q21, [bskey, #-64]
	ldp		q22, q23, [bskey, #-32]
	.endm

	.macro		dec_next_rk
	ldp		q16, q17, [bskey, #-128]!
	ldp		q18, q19, [bskey, #32]
	ldp		q20, q21, [bskey, #64]
	ldp		q22, q23, [bskey, #96]
	.endm

	.macro		add_round_key, x0, x1, x2, x3, x4, x5, x6, x7
	eor		\x0\().16b, \x0\().16b, v16.16b
	eor		\x1\().16b, \x1\().16b, v17.16b
	eor		\x2\().16b, \x2\().16b, v18.16b
	eor		\x3\().16b, \x3\().16b, v19.16b
	eor		\x4\().16b, \x4\().16b, v20.16b
	eor		\x5\().16b, \x5\().16b, v21.16b
	eor		\x6\().16b, \x6\().16b, v22.16b
	eor		\x7\().16b, \x7\().16b, v23.16b
	.endm

	.macro		shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, mask
	tbl		\x0\().16b, {\x0\().16b}, \mask\().16b
	tbl		\x1\().16b, {\x1\().16b}, \mask\().16b
	tbl		\x2\().16b, {\x2\().16b}, \mask\().16b
	tbl		\x3\().16b, {\x3\().16b}, \mask\().16b
	tbl		\x4\().16b, {\x4\().16b}, \mask\().16b
	tbl		\x5\().16b, {\x5\().16b}, \mask\().16b
	tbl		\x6\().16b, {\x6\().16b}, \mask\().16b
	tbl		\x7\().16b, {\x7\().16b}, \mask\().16b
	.endm

	.macro		mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
				  t0, t1, t2, t3, t4, t5, t6, t7, inv
	ext		\t0\().16b, \x0\().16b, \x0\().16b, #12
	ext		\t1\().16b, \x1\().16b, \x1\().16b, #12
	eor		\x0\().16b, \x0\().16b, \t0\().16b
	ext		\t2\().16b, \x2\().16b, \x2\().16b, #12
	eor		\x1\().16b, \x1\().16b, \t1\().16b
	ext		\t3\().16b, \x3\().16b, \x3\().16b, #12
	eor		\x2\().16b, \x2\().16b, \t2\().16b
	ext		\t4\().16b, \x4\().16b, \x4\().16b, #12
	eor		\x3\().16b, \x3\().16b, \t3\().16b
	ext		\t5\().16b, \x5\().16b, \x5\().16b, #12
	eor		\x4\().16b, \x4\().16b, \t4\().16b
	ext		\t6\().16b, \x6\().16b, \x6\().16b, #12
	eor		\x5\().16b, \x5\().16b, \t5\().16b
	ext		\t7\().16b, \x7\().16b, \x7\().16b, #12
	eor		\x6\().16b, \x6\().16b, \t6\().16b
	eor		\t1\().16b, \t1\().16b, \x0\().16b
	eor		\x7\().16b, \x7\().16b, \t7\().16b
	ext		\x0\().16b, \x0\().16b, \x0\().16b, #8
	eor		\t2\().16b, \t2\().16b, \x1\().16b
	eor		\t0\().16b, \t0\().16b, \x7\().16b
	eor		\t1\().16b, \t1\().16b, \x7\().16b
	ext		\x1\().16b, \x1\().16b, \x1\().16b, #8
	eor		\t5\().16b, \t5\().16b, \x4\().16b
	eor		\x0\().16b, \x0\().16b, \t0\().16b
	eor		\t6\().16b, \t6\().16b, \x5\().16b
	eor		\x1\().16b, \x1\().16b, \t1\().16b
	ext		\t0\().16b, \x4\().16b, \x4\().16b, #8
	eor		\t4\().16b, \t4\().16b, \x3\().16b
	ext		\t1\().16b, \x5\().16b, \x5\().16b, #8
	eor		\t7\().16b, \t7\().16b, \x6\().16b
	ext		\x4\().16b, \x3\().16b, \x3\().16b, #8
	eor		\t3\().16b, \t3\().16b, \x2\().16b
	ext		\x5\().16b, \x7\().16b, \x7\().16b, #8
	eor		\t4\().16b, \t4\().16b, \x7\().16b
	ext		\x3\().16b, \x6\().16b, \x6\().16b, #8
	eor		\t3\().16b, \t3\().16b, \x7\().16b
	ext		\x6\().16b, \x2\().16b, \x2\().16b, #8
	eor		\x7\().16b, \t1\().16b, \t5\().16b
	.ifb		\inv
	eor		\x2\().16b, \t0\().16b, \t4\().16b
	eor		\x4\().16b, \x4\().16b, \t3\().16b
	eor		\x5\().16b, \x5\().16b, \t7\().16b
	eor		\x3\().16b, \x3\().16b, \t6\().16b
	eor		\x6\().16b, \x6\().16b, \t2\().16b
	.else
	eor		\t3\().16b, \t3\().16b, \x4\().16b
	eor		\x5\().16b, \x5\().16b, \t7\().16b
	eor		\x2\().16b, \x3\().16b, \t6\().16b
	eor		\x3\().16b, \t0\().16b, \t4\().16b
	eor		\x4\().16b, \x6\().16b, \t2\().16b
	mov		\x6\().16b, \t3\().16b
	.endif
	.endm

	.macro		inv_mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
				      t0, t1, t2, t3, t4, t5, t6, t7
	ext		\t0\().16b, \x0\().16b, \x0\().16b, #8
	ext		\t6\().16b, \x6\().16b, \x6\().16b, #8
	ext		\t7\().16b, \x7\().16b, \x7\().16b, #8
	eor		\t0\().16b, \t0\().16b, \x0\().16b
	ext		\t1\().16b, \x1\().16b, \x1\().16b, #8
	eor		\t6\().16b, \t6\().16b, \x6\().16b
	ext		\t2\().16b, \x2\().16b, \x2\().16b, #8
	eor		\t7\().16b, \t7\().16b, \x7\().16b
	ext		\t3\().16b, \x3\().16b, \x3\().16b, #8
	eor		\t1\().16b, \t1\().16b, \x1\().16b
	ext		\t4\().16b, \x4\().16b, \x4\().16b, #8
	eor		\t2\().16b, \t2\().16b, \x2\().16b
	ext		\t5\().16b, \x5\().16b, \x5\().16b, #8
	eor		\t3\().16b, \t3\().16b, \x3\().16b
	eor		\t4\().16b, \t4\().16b, \x4\().16b
	eor		\t5\().16b, \t5\().16b, \x5\().16b
	eor		\x0\().16b, \x0\().16b, \t6\().16b
	eor		\x1\().16b, \x1\().16b, \t6\().16b
	eor		\x2\().16b, \x2\().16b, \t0\().16b
	eor		\x4\().16b, \x4\().16b, \t2\().16b
	eor		\x3\().16b, \x3\().16b, \t1\().16b
	eor		\x1\().16b, \x1\().16b, \t7\().16b
	eor		\x2\().16b, \x2\().16b, \t7\().16b
	eor		\x4\().16b, \x4\().16b, \t6\().16b
	eor		\x5\().16b, \x5\().16b, \t3\().16b
	eor		\x3\().16b, \x3\().16b, \t6\().16b
	eor		\x6\().16b, \x6\().16b, \t4\().16b
	eor		\x4\().16b, \x4\().16b, \t7\().16b
	eor		\x5\().16b, \x5\().16b, \t7\().16b
	eor		\x7\().16b, \x7\().16b, \t5\().16b
	mix_cols	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
			\t0, \t1, \t2, \t3, \t4, \t5, \t6, \t7, 1
	.endm

	.macro		swapmove_2x, a0, b0, a1, b1, n, mask, t0, t1
	ushr		\t0\().2d, \b0\().2d, #\n
	ushr		\t1\().2d, \b1\().2d, #\n
	eor		\t0\().16b, \t0\().16b, \a0\().16b
	eor		\t1\().16b, \t1\().16b, \a1\().16b
	and		\t0\().16b, \t0\().16b, \mask\().16b
	and		\t1\().16b, \t1\().16b, \mask\().16b
	eor		\a0\().16b, \a0\().16b, \t0\().16b
	shl		\t0\().2d, \t0\().2d, #\n
	eor		\a1\().16b, \a1\().16b, \t1\().16b
	shl		\t1\().2d, \t1\().2d, #\n
	eor		\b0\().16b, \b0\().16b, \t0\().16b
	eor		\b1\().16b, \b1\().16b, \t1\().16b
	.endm

	.macro		bitslice, x7, x6, x5, x4, x3, x2, x1, x0, t0, t1, t2, t3
	movi		\t0\().16b, #0x55
	movi		\t1\().16b, #0x33
	swapmove_2x	\x0, \x1, \x2, \x3, 1, \t0, \t2, \t3
	swapmove_2x	\x4, \x5, \x6, \x7, 1, \t0, \t2, \t3
	movi		\t0\().16b, #0x0f
	swapmove_2x	\x0, \x2, \x1, \x3, 2, \t1, \t2, \t3
	swapmove_2x	\x4, \x6, \x5, \x7, 2, \t1, \t2, \t3
	swapmove_2x	\x0, \x4, \x1, \x5, 4, \t0, \t2, \t3
	swapmove_2x	\x2, \x6, \x3, \x7, 4, \t0, \t2, \t3
	.endm


	.align		6
M0:	.octa		0x0004080c0105090d02060a0e03070b0f

M0SR:	.octa		0x0004080c05090d010a0e02060f03070b
SR:	.octa		0x0f0e0d0c0a09080b0504070600030201
SRM0:	.octa		0x01060b0c0207080d0304090e00050a0f

M0ISR:	.octa		0x0004080c0d0105090a0e0206070b0f03
ISR:	.octa		0x0f0e0d0c080b0a090504070602010003
ISRM0:	.octa		0x0306090c00070a0d01040b0e0205080f

	/*
	 * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
	 */
SYM_FUNC_START(aesbs_convert_key)
	ld1		{v7.4s}, [x1], #16		// load round 0 key
	ld1		{v17.4s}, [x1], #16		// load round 1 key

	movi		v8.16b,  #0x01			// bit masks
	movi		v9.16b,  #0x02
	movi		v10.16b, #0x04
	movi		v11.16b, #0x08
	movi		v12.16b, #0x10
	movi		v13.16b, #0x20
	movi		v14.16b, #0x40
	movi		v15.16b, #0x80
	ldr		q16, M0

	sub		x2, x2, #1
	str		q7, [x0], #16		// save round 0 key

.Lkey_loop:
	tbl		v7.16b ,{v17.16b}, v16.16b
	ld1		{v17.4s}, [x1], #16		// load next round key

	cmtst		v0.16b, v7.16b, v8.16b
	cmtst		v1.16b, v7.16b, v9.16b
	cmtst		v2.16b, v7.16b, v10.16b
	cmtst		v3.16b, v7.16b, v11.16b
	cmtst		v4.16b, v7.16b, v12.16b
	cmtst		v5.16b, v7.16b, v13.16b
	cmtst		v6.16b, v7.16b, v14.16b
	cmtst		v7.16b, v7.16b, v15.16b
	not		v0.16b, v0.16b
	not		v1.16b, v1.16b
	not		v5.16b, v5.16b
	not		v6.16b, v6.16b

	subs		x2, x2, #1
	stp		q0, q1, [x0], #128
	stp		q2, q3, [x0, #-96]
	stp		q4, q5, [x0, #-64]
	stp		q6, q7, [x0, #-32]
	b.ne		.Lkey_loop

	movi		v7.16b, #0x63			// compose .L63
	eor		v17.16b, v17.16b, v7.16b
	str		q17, [x0]
	ret
SYM_FUNC_END(aesbs_convert_key)

	.align		4
SYM_FUNC_START_LOCAL(aesbs_encrypt8)
	ldr		q9, [bskey], #16		// round 0 key
	ldr		q8, M0SR
	ldr		q24, SR

	eor		v10.16b, v0.16b, v9.16b		// xor with round0 key
	eor		v11.16b, v1.16b, v9.16b
	tbl		v0.16b, {v10.16b}, v8.16b
	eor		v12.16b, v2.16b, v9.16b
	tbl		v1.16b, {v11.16b}, v8.16b
	eor		v13.16b, v3.16b, v9.16b
	tbl		v2.16b, {v12.16b}, v8.16b
	eor		v14.16b, v4.16b, v9.16b
	tbl		v3.16b, {v13.16b}, v8.16b
	eor		v15.16b, v5.16b, v9.16b
	tbl		v4.16b, {v14.16b}, v8.16b
	eor		v10.16b, v6.16b, v9.16b
	tbl		v5.16b, {v15.16b}, v8.16b
	eor		v11.16b, v7.16b, v9.16b
	tbl		v6.16b, {v10.16b}, v8.16b
	tbl		v7.16b, {v11.16b}, v8.16b

	bitslice	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11

	sub		rounds, rounds, #1
	b		.Lenc_sbox

.Lenc_loop:
	shift_rows	v0, v1, v2, v3, v4, v5, v6, v7, v24
.Lenc_sbox:
	sbox		v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, \
								v13, v14, v15
	subs		rounds, rounds, #1
	b.cc		.Lenc_done

	enc_next_rk

	mix_cols	v0, v1, v4, v6, v3, v7, v2, v5, v8, v9, v10, v11, v12, \
								v13, v14, v15

	add_round_key	v0, v1, v2, v3, v4, v5, v6, v7

	b.ne		.Lenc_loop
	ldr		q24, SRM0
	b		.Lenc_loop

.Lenc_done:
	ldr		q12, [bskey]			// last round key

	bitslice	v0, v1, v4, v6, v3, v7, v2, v5, v8, v9, v10, v11

	eor		v0.16b, v0.16b, v12.16b
	eor		v1.16b, v1.16b, v12.16b
	eor		v4.16b, v4.16b, v12.16b
	eor		v6.16b, v6.16b, v12.16b
	eor		v3.16b, v3.16b, v12.16b
	eor		v7.16b, v7.16b, v12.16b
	eor		v2.16b, v2.16b, v12.16b
	eor		v5.16b, v5.16b, v12.16b
	ret
SYM_FUNC_END(aesbs_encrypt8)

	.align		4
SYM_FUNC_START_LOCAL(aesbs_decrypt8)
	lsl		x9, rounds, #7
	add		bskey, bskey, x9

	ldr		q9, [bskey, #-112]!		// round 0 key
	ldr		q8, M0ISR
	ldr		q24, ISR

	eor		v10.16b, v0.16b, v9.16b		// xor with round0 key
	eor		v11.16b, v1.16b, v9.16b
	tbl		v0.16b, {v10.16b}, v8.16b
	eor		v12.16b, v2.16b, v9.16b
	tbl		v1.16b, {v11.16b}, v8.16b
	eor		v13.16b, v3.16b, v9.16b
	tbl		v2.16b, {v12.16b}, v8.16b
	eor		v14.16b, v4.16b, v9.16b
	tbl		v3.16b, {v13.16b}, v8.16b
	eor		v15.16b, v5.16b, v9.16b
	tbl		v4.16b, {v14.16b}, v8.16b
	eor		v10.16b, v6.16b, v9.16b
	tbl		v5.16b, {v15.16b}, v8.16b
	eor		v11.16b, v7.16b, v9.16b
	tbl		v6.16b, {v10.16b}, v8.16b
	tbl		v7.16b, {v11.16b}, v8.16b

	bitslice	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11

	sub		rounds, rounds, #1
	b		.Ldec_sbox

.Ldec_loop:
	shift_rows	v0, v1, v2, v3, v4, v5, v6, v7, v24
.Ldec_sbox:
	inv_sbox	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, \
								v13, v14, v15
	subs		rounds, rounds, #1
	b.cc		.Ldec_done

	dec_next_rk

	add_round_key	v0, v1, v6, v4, v2, v7, v3, v5

	inv_mix_cols	v0, v1, v6, v4, v2, v7, v3, v5, v8, v9, v10, v11, v12, \
								v13, v14, v15

	b.ne		.Ldec_loop
	ldr		q24, ISRM0
	b		.Ldec_loop
.Ldec_done:
	ldr		q12, [bskey, #-16]		// last round key

	bitslice	v0, v1, v6, v4, v2, v7, v3, v5, v8, v9, v10, v11

	eor		v0.16b, v0.16b, v12.16b
	eor		v1.16b, v1.16b, v12.16b
	eor		v6.16b, v6.16b, v12.16b
	eor		v4.16b, v4.16b, v12.16b
	eor		v2.16b, v2.16b, v12.16b
	eor		v7.16b, v7.16b, v12.16b
	eor		v3.16b, v3.16b, v12.16b
	eor		v5.16b, v5.16b, v12.16b
	ret
SYM_FUNC_END(aesbs_decrypt8)

	/*
	 * aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
	 *		     int blocks)
	 * aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
	 *		     int blocks)
	 */
	.macro		__ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
	frame_push	5

	mov		x19, x0
	mov		x20, x1
	mov		x21, x2
	mov		x22, x3
	mov		x23, x4

99:	mov		x5, #1
	lsl		x5, x5, x23
	subs		w23, w23, #8
	csel		x23, x23, xzr, pl
	csel		x5, x5, xzr, mi

	ld1		{v0.16b}, [x20], #16
	tbnz		x5, #1, 0f
	ld1		{v1.16b}, [x20], #16
	tbnz		x5, #2, 0f
	ld1		{v2.16b}, [x20], #16
	tbnz		x5, #3, 0f
	ld1		{v3.16b}, [x20], #16
	tbnz		x5, #4, 0f
	ld1		{v4.16b}, [x20], #16
	tbnz		x5, #5, 0f
	ld1		{v5.16b}, [x20], #16
	tbnz		x5, #6, 0f
	ld1		{v6.16b}, [x20], #16
	tbnz		x5, #7, 0f
	ld1		{v7.16b}, [x20], #16

0:	mov		bskey, x21
	mov		rounds, x22
	bl		\do8

	st1		{\o0\().16b}, [x19], #16
	tbnz		x5, #1, 1f
	st1		{\o1\().16b}, [x19], #16
	tbnz		x5, #2, 1f
	st1		{\o2\().16b}, [x19], #16
	tbnz		x5, #3, 1f
	st1		{\o3\().16b}, [x19], #16
	tbnz		x5, #4, 1f
	st1		{\o4\().16b}, [x19], #16
	tbnz		x5, #5, 1f
	st1		{\o5\().16b}, [x19], #16
	tbnz		x5, #6, 1f
	st1		{\o6\().16b}, [x19], #16
	tbnz		x5, #7, 1f
	st1		{\o7\().16b}, [x19], #16

	cbz		x23, 1f
	b		99b

1:	frame_pop
	ret
	.endm

	.align		4
SYM_TYPED_FUNC_START(aesbs_ecb_encrypt)
	__ecb_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
SYM_FUNC_END(aesbs_ecb_encrypt)

	.align		4
SYM_TYPED_FUNC_START(aesbs_ecb_decrypt)
	__ecb_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
SYM_FUNC_END(aesbs_ecb_decrypt)

	/*
	 * aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
	 *		     int blocks, u8 iv[])
	 */
	.align		4
SYM_FUNC_START(aesbs_cbc_decrypt)
	frame_push	6

	mov		x19, x0
	mov		x20, x1
	mov		x21, x2
	mov		x22, x3
	mov		x23, x4
	mov		x24, x5

99:	mov		x6, #1
	lsl		x6, x6, x23
	subs		w23, w23, #8
	csel		x23, x23, xzr, pl
	csel		x6, x6, xzr, mi

	ld1		{v0.16b}, [x20], #16
	mov		v25.16b, v0.16b
	tbnz		x6, #1, 0f
	ld1		{v1.16b}, [x20], #16
	mov		v26.16b, v1.16b
	tbnz		x6, #2, 0f
	ld1		{v2.16b}, [x20], #16
	mov		v27.16b, v2.16b
	tbnz		x6, #3, 0f
	ld1		{v3.16b}, [x20], #16
	mov		v28.16b, v3.16b
	tbnz		x6, #4, 0f
	ld1		{v4.16b}, [x20], #16
	mov		v29.16b, v4.16b
	tbnz		x6, #5, 0f
	ld1		{v5.16b}, [x20], #16
	mov		v30.16b, v5.16b
	tbnz		x6, #6, 0f
	ld1		{v6.16b}, [x20], #16
	mov		v31.16b, v6.16b
	tbnz		x6, #7, 0f
	ld1		{v7.16b}, [x20]

0:	mov		bskey, x21
	mov		rounds, x22
	bl		aesbs_decrypt8

	ld1		{v24.16b}, [x24]		// load IV

	eor		v1.16b, v1.16b, v25.16b
	eor		v6.16b, v6.16b, v26.16b
	eor		v4.16b, v4.16b, v27.16b
	eor		v2.16b, v2.16b, v28.16b
	eor		v7.16b, v7.16b, v29.16b
	eor		v0.16b, v0.16b, v24.16b
	eor		v3.16b, v3.16b, v30.16b
	eor		v5.16b, v5.16b, v31.16b

	st1		{v0.16b}, [x19], #16
	mov		v24.16b, v25.16b
	tbnz		x6, #1, 1f
	st1		{v1.16b}, [x19], #16
	mov		v24.16b, v26.16b
	tbnz		x6, #2, 1f
	st1		{v6.16b}, [x19], #16
	mov		v24.16b, v27.16b
	tbnz		x6, #3, 1f
	st1		{v4.16b}, [x19], #16
	mov		v24.16b, v28.16b
	tbnz		x6, #4, 1f
	st1		{v2.16b}, [x19], #16
	mov		v24.16b, v29.16b
	tbnz		x6, #5, 1f
	st1		{v7.16b}, [x19], #16
	mov		v24.16b, v30.16b
	tbnz		x6, #6, 1f
	st1		{v3.16b}, [x19], #16
	mov		v24.16b, v31.16b
	tbnz		x6, #7, 1f
	ld1		{v24.16b}, [x20], #16
	st1		{v5.16b}, [x19], #16
1:	st1		{v24.16b}, [x24]		// store IV

	cbz		x23, 2f
	b		99b

2:	frame_pop
	ret
SYM_FUNC_END(aesbs_cbc_decrypt)

	.macro		next_tweak, out, in, const, tmp
	sshr		\tmp\().2d,  \in\().2d,   #63
	and		\tmp\().16b, \tmp\().16b, \const\().16b
	add		\out\().2d,  \in\().2d,   \in\().2d
	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
	eor		\out\().16b, \out\().16b, \tmp\().16b
	.endm

	/*
	 * aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
	 *		     int blocks, u8 iv[])
	 * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
	 *		     int blocks, u8 iv[])
	 */
SYM_FUNC_START_LOCAL(__xts_crypt8)
	movi		v18.2s, #0x1
	movi		v19.2s, #0x87
	uzp1		v18.4s, v18.4s, v19.4s

	ld1		{v0.16b-v3.16b}, [x1], #64
	ld1		{v4.16b-v7.16b}, [x1], #64

	next_tweak	v26, v25, v18, v19
	next_tweak	v27, v26, v18, v19
	next_tweak	v28, v27, v18, v19
	next_tweak	v29, v28, v18, v19
	next_tweak	v30, v29, v18, v19
	next_tweak	v31, v30, v18, v19
	next_tweak	v16, v31, v18, v19
	next_tweak	v17, v16, v18, v19

	eor		v0.16b, v0.16b, v25.16b
	eor		v1.16b, v1.16b, v26.16b
	eor		v2.16b, v2.16b, v27.16b
	eor		v3.16b, v3.16b, v28.16b
	eor		v4.16b, v4.16b, v29.16b
	eor		v5.16b, v5.16b, v30.16b
	eor		v6.16b, v6.16b, v31.16b
	eor		v7.16b, v7.16b, v16.16b

	stp		q16, q17, [x6]

	mov		bskey, x2
	mov		rounds, x3
	br		x16
SYM_FUNC_END(__xts_crypt8)

	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
	frame_push	0, 32
	add		x6, sp, #.Lframe_local_offset

	ld1		{v25.16b}, [x5]

0:	adr		x16, \do8
	bl		__xts_crypt8

	eor		v16.16b, \o0\().16b, v25.16b
	eor		v17.16b, \o1\().16b, v26.16b
	eor		v18.16b, \o2\().16b, v27.16b
	eor		v19.16b, \o3\().16b, v28.16b

	ldp		q24, q25, [x6]

	eor		v20.16b, \o4\().16b, v29.16b
	eor		v21.16b, \o5\().16b, v30.16b
	eor		v22.16b, \o6\().16b, v31.16b
	eor		v23.16b, \o7\().16b, v24.16b

	st1		{v16.16b-v19.16b}, [x0], #64
	st1		{v20.16b-v23.16b}, [x0], #64

	subs		x4, x4, #8
	b.gt		0b

	st1		{v25.16b}, [x5]
	frame_pop
	ret
	.endm

SYM_TYPED_FUNC_START(aesbs_xts_encrypt)
	__xts_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
SYM_FUNC_END(aesbs_xts_encrypt)

SYM_TYPED_FUNC_START(aesbs_xts_decrypt)
	__xts_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
SYM_FUNC_END(aesbs_xts_decrypt)

	.macro		next_ctr, v
	mov		\v\().d[1], x8
	adds		x8, x8, #1
	mov		\v\().d[0], x7
	adc		x7, x7, xzr
	rev64		\v\().16b, \v\().16b
	.endm

	/*
	 * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
	 *		     int rounds, int blocks, u8 iv[])
	 */
SYM_FUNC_START(aesbs_ctr_encrypt)
	frame_push	0
	ldp		x7, x8, [x5]
	ld1		{v0.16b}, [x5]
CPU_LE(	rev		x7, x7		)
CPU_LE(	rev		x8, x8		)
	adds		x8, x8, #1
	adc		x7, x7, xzr

0:	next_ctr	v1
	next_ctr	v2
	next_ctr	v3
	next_ctr	v4
	next_ctr	v5
	next_ctr	v6
	next_ctr	v7

	mov		bskey, x2
	mov		rounds, x3
	bl		aesbs_encrypt8

	ld1		{ v8.16b-v11.16b}, [x1], #64
	ld1		{v12.16b-v15.16b}, [x1], #64

	eor		v8.16b, v0.16b, v8.16b
	eor		v9.16b, v1.16b, v9.16b
	eor		v10.16b, v4.16b, v10.16b
	eor		v11.16b, v6.16b, v11.16b
	eor		v12.16b, v3.16b, v12.16b
	eor		v13.16b, v7.16b, v13.16b
	eor		v14.16b, v2.16b, v14.16b
	eor		v15.16b, v5.16b, v15.16b

	st1		{ v8.16b-v11.16b}, [x0], #64
	st1		{v12.16b-v15.16b}, [x0], #64

	next_ctr	v0
	subs		x4, x4, #8
	b.gt		0b

	st1		{v0.16b}, [x5]
	frame_pop
	ret
SYM_FUNC_END(aesbs_ctr_encrypt)