summaryrefslogtreecommitdiff
path: root/main/openssl/crypto/aes/asm/aesv8-armx.S
blob: 1637e4d4d3b6670fb442d5dbba2c22ef04b9bf28 (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
#include "arm_arch.h"

#if __ARM_ARCH__>=7
.text
.fpu	neon
.code	32
.align	5
rcon:
.long	0x01,0x01,0x01,0x01
.long	0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d	@ rotate-n-splat
.long	0x1b,0x1b,0x1b,0x1b

.globl	aes_v8_set_encrypt_key
.type	aes_v8_set_encrypt_key,%function
.align	5
aes_v8_set_encrypt_key:
.Lenc_key:
	adr	r3,rcon
	cmp	r1,#192

	veor	q0,q0,q0
	vld1.8	{q3},[r0]!
	mov	r1,#8		@ reuse r1
	vld1.32	{q1,q2},[r3]!

	blt	.Loop128
	beq	.L192
	b	.L256

.align	4
.Loop128:
	vtbl.8	d20,{q3},d4
	vtbl.8	d21,{q3},d5
	vext.8	q9,q0,q3,#12
	vst1.32	{q3},[r2]!
	.byte	0x00,0x43,0xf0,0xf3	@ aese q10,q0
	subs	r1,r1,#1

	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	 veor	q10,q10,q1
	veor	q3,q3,q9
	vshl.u8	q1,q1,#1
	veor	q3,q3,q10
	bne	.Loop128

	vld1.32	{q1},[r3]

	vtbl.8	d20,{q3},d4
	vtbl.8	d21,{q3},d5
	vext.8	q9,q0,q3,#12
	vst1.32	{q3},[r2]!
	.byte	0x00,0x43,0xf0,0xf3	@ aese q10,q0

	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	 veor	q10,q10,q1
	veor	q3,q3,q9
	vshl.u8	q1,q1,#1
	veor	q3,q3,q10

	vtbl.8	d20,{q3},d4
	vtbl.8	d21,{q3},d5
	vext.8	q9,q0,q3,#12
	vst1.32	{q3},[r2]!
	.byte	0x00,0x43,0xf0,0xf3	@ aese q10,q0

	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	 veor	q10,q10,q1
	veor	q3,q3,q9
	veor	q3,q3,q10
	vst1.32	{q3},[r2]
	add	r2,r2,#0x50

	mov	r12,#10
	b	.Ldone

.align	4
.L192:
	vld1.8	{d16},[r0]!
	vmov.i8	q10,#8			@ borrow q10
	vst1.32	{q3},[r2]!
	vsub.i8	q2,q2,q10	@ adjust the mask

.Loop192:
	vtbl.8	d20,{q8},d4
	vtbl.8	d21,{q8},d5
	vext.8	q9,q0,q3,#12
	vst1.32	{d16},[r2]!
	.byte	0x00,0x43,0xf0,0xf3	@ aese q10,q0
	subs	r1,r1,#1

	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	veor	q3,q3,q9

	vdup.32	q9,d7[1]
	veor	q9,q9,q8
	 veor	q10,q10,q1
	vext.8	q8,q0,q8,#12
	vshl.u8	q1,q1,#1
	veor	q8,q8,q9
	veor	q3,q3,q10
	veor	q8,q8,q10
	vst1.32	{q3},[r2]!
	bne	.Loop192

	mov	r12,#12
	add	r2,r2,#0x20
	b	.Ldone

.align	4
.L256:
	vld1.8	{q8},[r0]
	mov	r1,#7
	mov	r12,#14
	vst1.32	{q3},[r2]!

.Loop256:
	vtbl.8	d20,{q8},d4
	vtbl.8	d21,{q8},d5
	vext.8	q9,q0,q3,#12
	vst1.32	{q8},[r2]!
	.byte	0x00,0x43,0xf0,0xf3	@ aese q10,q0
	subs	r1,r1,#1

	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	veor	q3,q3,q9
	vext.8	q9,q0,q9,#12
	 veor	q10,q10,q1
	veor	q3,q3,q9
	vshl.u8	q1,q1,#1
	veor	q3,q3,q10
	vst1.32	{q3},[r2]!
	beq	.Ldone

	vdup.32	q10,d7[1]
	vext.8	q9,q0,q8,#12
	.byte	0x00,0x43,0xf0,0xf3	@ aese q10,q0

	veor	q8,q8,q9
	vext.8	q9,q0,q9,#12
	veor	q8,q8,q9
	vext.8	q9,q0,q9,#12
	veor	q8,q8,q9

	veor	q8,q8,q10
	b	.Loop256

.Ldone:
	str	r12,[r2]

	eor	r0,r0,r0		@ return value
	
	bx	lr
.size	aes_v8_set_encrypt_key,.-aes_v8_set_encrypt_key

.globl	aes_v8_set_decrypt_key
.type	aes_v8_set_decrypt_key,%function
.align	5
aes_v8_set_decrypt_key:
	stmdb	sp!,{r4,lr}
	bl	.Lenc_key

	sub	r2,r2,#240		@ restore original r2
	mov	r4,#-16
	add	r0,r2,r12,lsl#4	@ end of key schedule

	vld1.32	{q0},[r2]
	vld1.32	{q1},[r0]
	vst1.32	{q0},[r0],r4
	vst1.32	{q1},[r2]!

.Loop_imc:
	vld1.32	{q0},[r2]
	vld1.32	{q1},[r0]
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	vst1.32	{q0},[r0],r4
	vst1.32	{q1},[r2]!
	cmp	r0,r2
	bhi	.Loop_imc

	vld1.32	{q0},[r2]
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	vst1.32	{q0},[r0]

	eor	r0,r0,r0		@ return value
	ldmia	sp!,{r4,pc}
.size	aes_v8_set_decrypt_key,.-aes_v8_set_decrypt_key
.globl	aes_v8_encrypt
.type	aes_v8_encrypt,%function
.align	5
aes_v8_encrypt:
	ldr	r3,[r2,#240]
	vld1.32	{q0},[r2]!
	vld1.8	{q2},[r0]
	sub	r3,r3,#2
	vld1.32	{q1},[r2]!

.Loop_enc:
	.byte	0x00,0x43,0xb0,0xf3	@ aese q2,q0
	vld1.32	{q0},[r2]!
	.byte	0x84,0x43,0xb0,0xf3	@ aesmc q2,q2
	subs	r3,r3,#2
	.byte	0x02,0x43,0xb0,0xf3	@ aese q2,q1
	vld1.32	{q1},[r2]!
	.byte	0x84,0x43,0xb0,0xf3	@ aesmc q2,q2
	bgt	.Loop_enc

	.byte	0x00,0x43,0xb0,0xf3	@ aese q2,q0
	vld1.32	{q0},[r2]
	.byte	0x84,0x43,0xb0,0xf3	@ aesmc q2,q2
	.byte	0x02,0x43,0xb0,0xf3	@ aese q2,q1
	veor	q2,q2,q0

	vst1.8	{q2},[r1]
	bx	lr
.size	aes_v8_encrypt,.-aes_v8_encrypt
.globl	aes_v8_decrypt
.type	aes_v8_decrypt,%function
.align	5
aes_v8_decrypt:
	ldr	r3,[r2,#240]
	vld1.32	{q0},[r2]!
	vld1.8	{q2},[r0]
	sub	r3,r3,#2
	vld1.32	{q1},[r2]!

.Loop_dec:
	.byte	0x40,0x43,0xb0,0xf3	@ aesd q2,q0
	vld1.32	{q0},[r2]!
	.byte	0xc4,0x43,0xb0,0xf3	@ aesimc q2,q2
	subs	r3,r3,#2
	.byte	0x42,0x43,0xb0,0xf3	@ aesd q2,q1
	vld1.32	{q1},[r2]!
	.byte	0xc4,0x43,0xb0,0xf3	@ aesimc q2,q2
	bgt	.Loop_dec

	.byte	0x40,0x43,0xb0,0xf3	@ aesd q2,q0
	vld1.32	{q0},[r2]
	.byte	0xc4,0x43,0xb0,0xf3	@ aesimc q2,q2
	.byte	0x42,0x43,0xb0,0xf3	@ aesd q2,q1
	veor	q2,q2,q0

	vst1.8	{q2},[r1]
	bx	lr
.size	aes_v8_decrypt,.-aes_v8_decrypt
.globl	aes_v8_cbc_encrypt
.type	aes_v8_cbc_encrypt,%function
.align	5
aes_v8_cbc_encrypt:
	mov	ip,sp
	stmdb	sp!,{r4-r8,lr}
	vstmdb	sp!,{d8-d15}            @ ABI specification says so
	ldmia	ip,{r4-r5}		@ load remaining args
	subs	r2,r2,#16
	mov	r8,#16
	blo	.Lcbc_abort
	moveq	r8,#0

	cmp	r5,#0			@ en- or decrypting?
	ldr	r5,[r3,#240]
	and	r2,r2,#-16
	vld1.8	{q6},[r4]
	vld1.8	{q0},[r0],r8

	vld1.32	{q8-q9},[r3]		@ load key schedule...
	sub	r5,r5,#6
	add	r7,r3,r5,lsl#4	@ pointer to last 7 round keys
	sub	r5,r5,#2
	vld1.32	{q10-q11},[r7]!
	vld1.32	{q12-q13},[r7]!
	vld1.32	{q14-q15},[r7]!
	vld1.32	{q7},[r7]

	add	r7,r3,#32
	mov	r6,r5
	beq	.Lcbc_dec

	cmp	r5,#2
	veor	q0,q0,q6
	veor	q5,q8,q7
	beq	.Lcbc_enc128

.Loop_cbc_enc:
	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	vld1.32	{q8},[r7]!
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	subs	r6,r6,#2
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	vld1.32	{q9},[r7]!
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	bgt	.Loop_cbc_enc

	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 subs	r2,r2,#16
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 moveq	r8,#0
	.byte	0x24,0x03,0xb0,0xf3	@ aese q0,q10
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 add	r7,r3,#16
	.byte	0x26,0x03,0xb0,0xf3	@ aese q0,q11
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 vld1.8	{q8},[r0],r8
	.byte	0x28,0x03,0xb0,0xf3	@ aese q0,q12
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 veor	q8,q8,q5
	.byte	0x2a,0x03,0xb0,0xf3	@ aese q0,q13
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 vld1.32 {q9},[r7]!	@ re-pre-load rndkey[1]
	.byte	0x2c,0x03,0xb0,0xf3	@ aese q0,q14
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x2e,0x03,0xb0,0xf3	@ aese q0,q15

	 mov	r6,r5
	veor	q6,q0,q7
	vst1.8	{q6},[r1]!
	bhs	.Loop_cbc_enc

	b	.Lcbc_done

.align	5
.Lcbc_enc128:
	vld1.32	{q2-q3},[r7]
	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	b	.Lenter_cbc_enc128
.Loop_cbc_enc128:
	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 vst1.8	{q6},[r1]!
.Lenter_cbc_enc128:
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 subs	r2,r2,#16
	.byte	0x04,0x03,0xb0,0xf3	@ aese q0,q2
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 moveq	r8,#0
	.byte	0x06,0x03,0xb0,0xf3	@ aese q0,q3
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x24,0x03,0xb0,0xf3	@ aese q0,q10
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x26,0x03,0xb0,0xf3	@ aese q0,q11
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 vld1.8	{q8},[r0],r8
	.byte	0x28,0x03,0xb0,0xf3	@ aese q0,q12
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x2a,0x03,0xb0,0xf3	@ aese q0,q13
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x2c,0x03,0xb0,0xf3	@ aese q0,q14
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 veor	q8,q8,q5
	.byte	0x2e,0x03,0xb0,0xf3	@ aese q0,q15
	veor	q6,q0,q7
	bhs	.Loop_cbc_enc128

	vst1.8	{q6},[r1]!
	b	.Lcbc_done

.align	5
.Lcbc_dec128:
	vld1.32	{q4-q5},[r7]
	veor	q6,q6,q7
	veor	q2,q0,q7
	mov	r12,r8

.Loop2x_cbc_dec128:
	.byte	0x60,0x03,0xb0,0xf3	@ aesd q0,q8
	.byte	0x60,0x23,0xb0,0xf3	@ aesd q1,q8
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 subs	r2,r2,#32
	.byte	0x62,0x03,0xb0,0xf3	@ aesd q0,q9
	.byte	0x62,0x23,0xb0,0xf3	@ aesd q1,q9
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 movlo	r8,#0
	.byte	0x48,0x03,0xb0,0xf3	@ aesd q0,q4
	.byte	0x48,0x23,0xb0,0xf3	@ aesd q1,q4
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 movls	r12,#0
	.byte	0x4a,0x03,0xb0,0xf3	@ aesd q0,q5
	.byte	0x4a,0x23,0xb0,0xf3	@ aesd q1,q5
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	.byte	0x64,0x03,0xb0,0xf3	@ aesd q0,q10
	.byte	0x64,0x23,0xb0,0xf3	@ aesd q1,q10
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	.byte	0x66,0x03,0xb0,0xf3	@ aesd q0,q11
	.byte	0x66,0x23,0xb0,0xf3	@ aesd q1,q11
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	.byte	0x68,0x03,0xb0,0xf3	@ aesd q0,q12
	.byte	0x68,0x23,0xb0,0xf3	@ aesd q1,q12
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	.byte	0x6a,0x03,0xb0,0xf3	@ aesd q0,q13
	.byte	0x6a,0x23,0xb0,0xf3	@ aesd q1,q13
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	.byte	0x6c,0x03,0xb0,0xf3	@ aesd q0,q14
	.byte	0x6c,0x23,0xb0,0xf3	@ aesd q1,q14
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	.byte	0x6e,0x03,0xb0,0xf3	@ aesd q0,q15
	.byte	0x6e,0x23,0xb0,0xf3	@ aesd q1,q15

	veor	q6,q6,q0
	vld1.8	{q0},[r0],r8
	veor	q2,q2,q1
	vld1.8	{q1},[r0],r12
	vst1.8	{q6},[r1]!
	veor	q6,q3,q7
	vst1.8	{q2},[r1]!
	veor	q2,q0,q7
	vorr	q3,q1,q1
	bhs	.Loop2x_cbc_dec128

	adds	r2,r2,#32
	veor	q6,q6,q7
	beq	.Lcbc_done
	veor	q2,q2,q7
	b	.Lcbc_dec_tail

.align	5
.Lcbc_dec:
	subs	r2,r2,#16
	vorr	q2,q0,q0
	blo	.Lcbc_dec_tail

	moveq	r8,#0
	cmp	r5,#2
	vld1.8	{q1},[r0],r8
	vorr	q3,q1,q1
	beq	.Lcbc_dec128

.Loop2x_cbc_dec:
	.byte	0x60,0x03,0xb0,0xf3	@ aesd q0,q8
	.byte	0x60,0x23,0xb0,0xf3	@ aesd q1,q8
	vld1.32	{q8},[r7]!
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	subs	r6,r6,#2
	.byte	0x62,0x03,0xb0,0xf3	@ aesd q0,q9
	.byte	0x62,0x23,0xb0,0xf3	@ aesd q1,q9
	vld1.32	{q9},[r7]!
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	bgt	.Loop2x_cbc_dec

	.byte	0x60,0x03,0xb0,0xf3	@ aesd q0,q8
	.byte	0x60,0x23,0xb0,0xf3	@ aesd q1,q8
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 veor	q4,q6,q7
	 veor	q5,q2,q7
	.byte	0x62,0x03,0xb0,0xf3	@ aesd q0,q9
	.byte	0x62,0x23,0xb0,0xf3	@ aesd q1,q9
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 vorr	q6,q3,q3
	 subs	r2,r2,#32
	.byte	0x64,0x03,0xb0,0xf3	@ aesd q0,q10
	.byte	0x64,0x23,0xb0,0xf3	@ aesd q1,q10
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	 movlo	r8,#0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 mov	r7,r3
	.byte	0x66,0x03,0xb0,0xf3	@ aesd q0,q11
	.byte	0x66,0x23,0xb0,0xf3	@ aesd q1,q11
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	 vld1.8	{q2},[r0],r8
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 movls	r8,#0
	.byte	0x68,0x03,0xb0,0xf3	@ aesd q0,q12
	.byte	0x68,0x23,0xb0,0xf3	@ aesd q1,q12
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 vld1.8	{q3},[r0],r8
	.byte	0x6a,0x03,0xb0,0xf3	@ aesd q0,q13
	.byte	0x6a,0x23,0xb0,0xf3	@ aesd q1,q13
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 vld1.32 {q8},[r7]!	@ re-pre-load rndkey[0]
	.byte	0x6c,0x03,0xb0,0xf3	@ aesd q0,q14
	.byte	0x6c,0x23,0xb0,0xf3	@ aesd q1,q14
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0xc2,0x23,0xb0,0xf3	@ aesimc q1,q1
	 vld1.32 {q9},[r7]!	@ re-pre-load rndkey[1]
	.byte	0x6e,0x03,0xb0,0xf3	@ aesd q0,q15
	.byte	0x6e,0x23,0xb0,0xf3	@ aesd q1,q15

	 mov	r6,r5
	veor	q4,q4,q0
	veor	q5,q5,q1
	 vorr	q0,q2,q2
	vst1.8	{q4},[r1]!
	 vorr	q1,q3,q3
	vst1.8	{q5},[r1]!
	bhs	.Loop2x_cbc_dec

	adds	r2,r2,#32
	beq	.Lcbc_done

.Lcbc_dec_tail:
	.byte	0x60,0x03,0xb0,0xf3	@ aesd q0,q8
	vld1.32	{q8},[r7]!
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	subs	r6,r6,#2
	.byte	0x62,0x03,0xb0,0xf3	@ aesd q0,q9
	vld1.32	{q9},[r7]!
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	bgt	.Lcbc_dec_tail

	.byte	0x60,0x03,0xb0,0xf3	@ aesd q0,q8
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0x62,0x03,0xb0,0xf3	@ aesd q0,q9
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	 veor	q4,q6,q7
	.byte	0x64,0x03,0xb0,0xf3	@ aesd q0,q10
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	 vorr	q6,q2,q2
	.byte	0x66,0x03,0xb0,0xf3	@ aesd q0,q11
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0x68,0x03,0xb0,0xf3	@ aesd q0,q12
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0x6a,0x03,0xb0,0xf3	@ aesd q0,q13
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0x6c,0x03,0xb0,0xf3	@ aesd q0,q14
	.byte	0xc0,0x03,0xb0,0xf3	@ aesimc q0,q0
	.byte	0x6e,0x03,0xb0,0xf3	@ aesd q0,q15

	veor	q4,q4,q0
	vst1.8	{q4},[r1]!

.Lcbc_done:
	vst1.8	{q6},[r4]
.Lcbc_abort:
	vldmia	sp!,{d8-d15}
	ldmia	sp!,{r4-r8,pc}
.size	aes_v8_cbc_encrypt,.-aes_v8_cbc_encrypt
.globl	aes_v8_ctr32_encrypt_blocks
.type	aes_v8_ctr32_encrypt_blocks,%function
.align	5
aes_v8_ctr32_encrypt_blocks:
	mov		ip,sp
	stmdb		sp!,{r4-r10,lr}
	vstmdb		sp!,{d8-d15}            @ ABI specification says so
	ldr		r4, [ip]		@ load remaining arg
	ldr		r5,[r3,#240]

	ldr		r8, [r4, #12]
	vld1.32		{q0},[r4]

	vld1.32		{q8-q9},[r3]		@ load key schedule...
	sub		r5,r5,#6
	add		r7,r3,r5,lsl#4	@ pointer to last 7 round keys
	sub		r5,r5,#2
	vld1.32		{q10-q11},[r7]!
	vld1.32		{q12-q13},[r7]!
	vld1.32		{q14-q15},[r7]!
	vld1.32		{q7},[r7]

	add		r7,r3,#32
	mov		r6,r5

	subs		r2,r2,#2
	blo		.Lctr32_tail

#ifndef __ARMEB__
	rev		r8, r8
#endif
	vorr		q1,q0,q0
	add		r8, r8, #1
	vorr		q6,q0,q0
	rev		r10, r8
	cmp		r5,#2
	vmov.32	d3[1],r10
	beq		.Lctr32_128

.Loop2x_ctr32:
	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x20,0x23,0xb0,0xf3	@ aese q1,q8
	vld1.32		{q8},[r7]!
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	subs		r6,r6,#2
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	.byte	0x22,0x23,0xb0,0xf3	@ aese q1,q9
	vld1.32		{q9},[r7]!
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	bgt		.Loop2x_ctr32

	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x20,0x23,0xb0,0xf3	@ aese q1,q8
	.byte	0x80,0x83,0xb0,0xf3	@ aesmc q4,q0
	 vorr		q0,q6,q6
	.byte	0x82,0xa3,0xb0,0xf3	@ aesmc q5,q1
	 vorr		q1,q6,q6
	.byte	0x22,0x83,0xb0,0xf3	@ aese q4,q9
	.byte	0x22,0xa3,0xb0,0xf3	@ aese q5,q9
	 vld1.8		{q2},[r0]!
	.byte	0x88,0x83,0xb0,0xf3	@ aesmc q4,q4
	 vld1.8		{q3},[r0]!
	.byte	0x8a,0xa3,0xb0,0xf3	@ aesmc q5,q5
	 add		r8,r8,#1
	.byte	0x24,0x83,0xb0,0xf3	@ aese q4,q10
	.byte	0x24,0xa3,0xb0,0xf3	@ aese q5,q10
	 rev		r9,r8
	.byte	0x88,0x83,0xb0,0xf3	@ aesmc q4,q4
	.byte	0x8a,0xa3,0xb0,0xf3	@ aesmc q5,q5
	 add		r8,r8,#1
	.byte	0x26,0x83,0xb0,0xf3	@ aese q4,q11
	.byte	0x26,0xa3,0xb0,0xf3	@ aese q5,q11
	 veor		q2,q2,q7
	 rev		r10,r8
	.byte	0x88,0x83,0xb0,0xf3	@ aesmc q4,q4
	.byte	0x8a,0xa3,0xb0,0xf3	@ aesmc q5,q5
	 veor		q3,q3,q7
	 mov		r7,r3
	.byte	0x28,0x83,0xb0,0xf3	@ aese q4,q12
	.byte	0x28,0xa3,0xb0,0xf3	@ aese q5,q12
	 subs		r2,r2,#2
	.byte	0x88,0x83,0xb0,0xf3	@ aesmc q4,q4
	.byte	0x8a,0xa3,0xb0,0xf3	@ aesmc q5,q5
	 vld1.32	 {q8-q9},[r7]!	@ re-pre-load rndkey[0-1]
	.byte	0x2a,0x83,0xb0,0xf3	@ aese q4,q13
	.byte	0x2a,0xa3,0xb0,0xf3	@ aese q5,q13
	.byte	0x88,0x83,0xb0,0xf3	@ aesmc q4,q4
	.byte	0x8a,0xa3,0xb0,0xf3	@ aesmc q5,q5
	.byte	0x2c,0x83,0xb0,0xf3	@ aese q4,q14
	.byte	0x2c,0xa3,0xb0,0xf3	@ aese q5,q14
	 vmov.32	d1[1], r9
	.byte	0x88,0x83,0xb0,0xf3	@ aesmc q4,q4
	 vmov.32	d3[1], r10
	.byte	0x8a,0xa3,0xb0,0xf3	@ aesmc q5,q5
	.byte	0x2e,0x83,0xb0,0xf3	@ aese q4,q15
	.byte	0x2e,0xa3,0xb0,0xf3	@ aese q5,q15

	 mov		r6,r5
	veor		q2,q2,q4
	veor		q3,q3,q5
	vst1.8		{q2},[r1]!
	vst1.8		{q3},[r1]!
	bhs		.Loop2x_ctr32

	adds		r2,r2,#2
	beq		.Lctr32_done
	b		.Lctr32_tail

.Lctr32_128:
	vld1.32		{q4-q5},[r7]

.Loop2x_ctr32_128:
	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x20,0x23,0xb0,0xf3	@ aese q1,q8
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 vld1.8		{q2},[r0]!
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	 vld1.8		{q3},[r0]!
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	.byte	0x22,0x23,0xb0,0xf3	@ aese q1,q9
	 add		r8,r8,#1
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	 rev		r9,r8
	.byte	0x08,0x03,0xb0,0xf3	@ aese q0,q4
	.byte	0x08,0x23,0xb0,0xf3	@ aese q1,q4
	 add		r8,r8,#1
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	 rev		r10,r8
	.byte	0x0a,0x03,0xb0,0xf3	@ aese q0,q5
	.byte	0x0a,0x23,0xb0,0xf3	@ aese q1,q5
	 subs		r2,r2,#2
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	.byte	0x24,0x03,0xb0,0xf3	@ aese q0,q10
	.byte	0x24,0x23,0xb0,0xf3	@ aese q1,q10
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	.byte	0x26,0x03,0xb0,0xf3	@ aese q0,q11
	.byte	0x26,0x23,0xb0,0xf3	@ aese q1,q11
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	.byte	0x28,0x03,0xb0,0xf3	@ aese q0,q12
	.byte	0x28,0x23,0xb0,0xf3	@ aese q1,q12
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	.byte	0x2a,0x03,0xb0,0xf3	@ aese q0,q13
	.byte	0x2a,0x23,0xb0,0xf3	@ aese q1,q13
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	.byte	0x2c,0x03,0xb0,0xf3	@ aese q0,q14
	.byte	0x2c,0x23,0xb0,0xf3	@ aese q1,q14
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x82,0x23,0xb0,0xf3	@ aesmc q1,q1
	 veor		q2,q2,q7
	.byte	0x2e,0x03,0xb0,0xf3	@ aese q0,q15
	 veor		q3,q3,q7
	.byte	0x2e,0x23,0xb0,0xf3	@ aese q1,q15

	veor		q2,q2,q0
	vorr		q0,q6,q6
	veor		q3,q3,q1
	vorr		q1,q6,q6
	vst1.8		{q2},[r1]!
	vmov.32	d1[1], r9
	vst1.8		{q3},[r1]!
	vmov.32	d3[1], r10
	bhs		.Loop2x_ctr32_128

	adds		r2,r2,#2
	beq		.Lctr32_done

.Lctr32_tail:
	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	vld1.32		{q8},[r7]!
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	subs		r6,r6,#2
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	vld1.32		{q9},[r7]!
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	bgt		.Lctr32_tail

	.byte	0x20,0x03,0xb0,0xf3	@ aese q0,q8
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x22,0x03,0xb0,0xf3	@ aese q0,q9
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 vld1.8		{q2},[r0]
	.byte	0x24,0x03,0xb0,0xf3	@ aese q0,q10
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x26,0x03,0xb0,0xf3	@ aese q0,q11
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x28,0x03,0xb0,0xf3	@ aese q0,q12
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x2a,0x03,0xb0,0xf3	@ aese q0,q13
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	.byte	0x2c,0x03,0xb0,0xf3	@ aese q0,q14
	.byte	0x80,0x03,0xb0,0xf3	@ aesmc q0,q0
	 veor		q2,q2,q7
	.byte	0x2e,0x03,0xb0,0xf3	@ aese q0,q15

	veor		q2,q2,q0
	vst1.8		{q2},[r1]

.Lctr32_done:
	vldmia		sp!,{d8-d15}
	ldmia		sp!,{r4-r10,pc}
.size	aes_v8_ctr32_encrypt_blocks,.-aes_v8_ctr32_encrypt_blocks
#endif