summaryrefslogtreecommitdiff
path: root/arch/arm/crypto/aes-ce-core.S
blob: 312428d83eedb2aacd5380bd1e1d196133668ee6 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * aes-ce-core.S - AES in CBC/CTR/XTS mode using ARMv8 Crypto Extensions
 *
 * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
 */

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

	.text
	.arch		armv8-a
	.fpu		crypto-neon-fp-armv8
	.align		3

	.macro		enc_round, state, key
	aese.8		\state, \key
	aesmc.8		\state, \state
	.endm

	.macro		dec_round, state, key
	aesd.8		\state, \key
	aesimc.8	\state, \state
	.endm

	.macro		enc_dround, key1, key2
	enc_round	q0, \key1
	enc_round	q0, \key2
	.endm

	.macro		dec_dround, key1, key2
	dec_round	q0, \key1
	dec_round	q0, \key2
	.endm

	.macro		enc_fround, key1, key2, key3
	enc_round	q0, \key1
	aese.8		q0, \key2
	veor		q0, q0, \key3
	.endm

	.macro		dec_fround, key1, key2, key3
	dec_round	q0, \key1
	aesd.8		q0, \key2
	veor		q0, q0, \key3
	.endm

	.macro		enc_dround_4x, key1, key2
	enc_round	q0, \key1
	enc_round	q1, \key1
	enc_round	q2, \key1
	enc_round	q3, \key1
	enc_round	q0, \key2
	enc_round	q1, \key2
	enc_round	q2, \key2
	enc_round	q3, \key2
	.endm

	.macro		dec_dround_4x, key1, key2
	dec_round	q0, \key1
	dec_round	q1, \key1
	dec_round	q2, \key1
	dec_round	q3, \key1
	dec_round	q0, \key2
	dec_round	q1, \key2
	dec_round	q2, \key2
	dec_round	q3, \key2
	.endm

	.macro		enc_fround_4x, key1, key2, key3
	enc_round	q0, \key1
	enc_round	q1, \key1
	enc_round	q2, \key1
	enc_round	q3, \key1
	aese.8		q0, \key2
	aese.8		q1, \key2
	aese.8		q2, \key2
	aese.8		q3, \key2
	veor		q0, q0, \key3
	veor		q1, q1, \key3
	veor		q2, q2, \key3
	veor		q3, q3, \key3
	.endm

	.macro		dec_fround_4x, key1, key2, key3
	dec_round	q0, \key1
	dec_round	q1, \key1
	dec_round	q2, \key1
	dec_round	q3, \key1
	aesd.8		q0, \key2
	aesd.8		q1, \key2
	aesd.8		q2, \key2
	aesd.8		q3, \key2
	veor		q0, q0, \key3
	veor		q1, q1, \key3
	veor		q2, q2, \key3
	veor		q3, q3, \key3
	.endm

	.macro		do_block, dround, fround
	cmp		r3, #12			@ which key size?
	vld1.32		{q10-q11}, [ip]!
	\dround		q8, q9
	vld1.32		{q12-q13}, [ip]!
	\dround		q10, q11
	vld1.32		{q10-q11}, [ip]!
	\dround		q12, q13
	vld1.32		{q12-q13}, [ip]!
	\dround		q10, q11
	blo		0f			@ AES-128: 10 rounds
	vld1.32		{q10-q11}, [ip]!
	\dround		q12, q13
	beq		1f			@ AES-192: 12 rounds
	vld1.32		{q12-q13}, [ip]
	\dround		q10, q11
0:	\fround		q12, q13, q14
	bx		lr

1:	\fround		q10, q11, q14
	bx		lr
	.endm

	/*
	 * Internal, non-AAPCS compliant functions that implement the core AES
	 * transforms. These should preserve all registers except q0 - q2 and ip
	 * Arguments:
	 *   q0        : first in/output block
	 *   q1        : second in/output block (_4x version only)
	 *   q2        : third in/output block (_4x version only)
	 *   q3        : fourth in/output block (_4x version only)
	 *   q8        : first round key
	 *   q9        : secound round key
	 *   q14       : final round key
	 *   r2        : address of round key array
	 *   r3        : number of rounds
	 */
	.align		6
aes_encrypt:
	add		ip, r2, #32		@ 3rd round key
.Laes_encrypt_tweak:
	do_block	enc_dround, enc_fround
ENDPROC(aes_encrypt)

	.align		6
aes_decrypt:
	add		ip, r2, #32		@ 3rd round key
	do_block	dec_dround, dec_fround
ENDPROC(aes_decrypt)

	.align		6
aes_encrypt_4x:
	add		ip, r2, #32		@ 3rd round key
	do_block	enc_dround_4x, enc_fround_4x
ENDPROC(aes_encrypt_4x)

	.align		6
aes_decrypt_4x:
	add		ip, r2, #32		@ 3rd round key
	do_block	dec_dround_4x, dec_fround_4x
ENDPROC(aes_decrypt_4x)

	.macro		prepare_key, rk, rounds
	add		ip, \rk, \rounds, lsl #4
	vld1.32		{q8-q9}, [\rk]		@ load first 2 round keys
	vld1.32		{q14}, [ip]		@ load last round key
	.endm

	/*
	 * aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
	 *		   int blocks)
	 * aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
	 *		   int blocks)
	 */
ENTRY(ce_aes_ecb_encrypt)
	push		{r4, lr}
	ldr		r4, [sp, #8]
	prepare_key	r2, r3
.Lecbencloop4x:
	subs		r4, r4, #4
	bmi		.Lecbenc1x
	vld1.8		{q0-q1}, [r1]!
	vld1.8		{q2-q3}, [r1]!
	bl		aes_encrypt_4x
	vst1.8		{q0-q1}, [r0]!
	vst1.8		{q2-q3}, [r0]!
	b		.Lecbencloop4x
.Lecbenc1x:
	adds		r4, r4, #4
	beq		.Lecbencout
.Lecbencloop:
	vld1.8		{q0}, [r1]!
	bl		aes_encrypt
	vst1.8		{q0}, [r0]!
	subs		r4, r4, #1
	bne		.Lecbencloop
.Lecbencout:
	pop		{r4, pc}
ENDPROC(ce_aes_ecb_encrypt)

ENTRY(ce_aes_ecb_decrypt)
	push		{r4, lr}
	ldr		r4, [sp, #8]
	prepare_key	r2, r3
.Lecbdecloop4x:
	subs		r4, r4, #4
	bmi		.Lecbdec1x
	vld1.8		{q0-q1}, [r1]!
	vld1.8		{q2-q3}, [r1]!
	bl		aes_decrypt_4x
	vst1.8		{q0-q1}, [r0]!
	vst1.8		{q2-q3}, [r0]!
	b		.Lecbdecloop4x
.Lecbdec1x:
	adds		r4, r4, #4
	beq		.Lecbdecout
.Lecbdecloop:
	vld1.8		{q0}, [r1]!
	bl		aes_decrypt
	vst1.8		{q0}, [r0]!
	subs		r4, r4, #1
	bne		.Lecbdecloop
.Lecbdecout:
	pop		{r4, pc}
ENDPROC(ce_aes_ecb_decrypt)

	/*
	 * aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
	 *		   int blocks, u8 iv[])
	 * aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
	 *		   int blocks, u8 iv[])
	 */
ENTRY(ce_aes_cbc_encrypt)
	push		{r4-r6, lr}
	ldrd		r4, r5, [sp, #16]
	vld1.8		{q0}, [r5]
	prepare_key	r2, r3
.Lcbcencloop:
	vld1.8		{q1}, [r1]!		@ get next pt block
	veor		q0, q0, q1		@ ..and xor with iv
	bl		aes_encrypt
	vst1.8		{q0}, [r0]!
	subs		r4, r4, #1
	bne		.Lcbcencloop
	vst1.8		{q0}, [r5]
	pop		{r4-r6, pc}
ENDPROC(ce_aes_cbc_encrypt)

ENTRY(ce_aes_cbc_decrypt)
	push		{r4-r6, lr}
	ldrd		r4, r5, [sp, #16]
	vld1.8		{q15}, [r5]		@ keep iv in q15
	prepare_key	r2, r3
.Lcbcdecloop4x:
	subs		r4, r4, #4
	bmi		.Lcbcdec1x
	vld1.8		{q0-q1}, [r1]!
	vld1.8		{q2-q3}, [r1]!
	vmov		q4, q0
	vmov		q5, q1
	vmov		q6, q2
	vmov		q7, q3
	bl		aes_decrypt_4x
	veor		q0, q0, q15
	veor		q1, q1, q4
	veor		q2, q2, q5
	veor		q3, q3, q6
	vmov		q15, q7
	vst1.8		{q0-q1}, [r0]!
	vst1.8		{q2-q3}, [r0]!
	b		.Lcbcdecloop4x
.Lcbcdec1x:
	adds		r4, r4, #4
	beq		.Lcbcdecout
	vmov		q6, q14			@ preserve last round key
.Lcbcdecloop:
	vld1.8		{q0}, [r1]!		@ get next ct block
	veor		q14, q15, q6		@ combine prev ct with last key
	vmov		q15, q0
	bl		aes_decrypt
	vst1.8		{q0}, [r0]!
	subs		r4, r4, #1
	bne		.Lcbcdecloop
.Lcbcdecout:
	vst1.8		{q15}, [r5]		@ keep iv in q15
	pop		{r4-r6, pc}
ENDPROC(ce_aes_cbc_decrypt)


	/*
	 * ce_aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
	 *			  int rounds, int bytes, u8 const iv[])
	 * ce_aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
	 *			  int rounds, int bytes, u8 const iv[])
	 */

ENTRY(ce_aes_cbc_cts_encrypt)
	push		{r4-r6, lr}
	ldrd		r4, r5, [sp, #16]

	movw		ip, :lower16:.Lcts_permute_table
	movt		ip, :upper16:.Lcts_permute_table
	sub		r4, r4, #16
	add		lr, ip, #32
	add		ip, ip, r4
	sub		lr, lr, r4
	vld1.8		{q5}, [ip]
	vld1.8		{q6}, [lr]

	add		ip, r1, r4
	vld1.8		{q0}, [r1]			@ overlapping loads
	vld1.8		{q3}, [ip]

	vld1.8		{q1}, [r5]			@ get iv
	prepare_key	r2, r3

	veor		q0, q0, q1			@ xor with iv
	bl		aes_encrypt

	vtbl.8		d4, {d0-d1}, d10
	vtbl.8		d5, {d0-d1}, d11
	vtbl.8		d2, {d6-d7}, d12
	vtbl.8		d3, {d6-d7}, d13

	veor		q0, q0, q1
	bl		aes_encrypt

	add		r4, r0, r4
	vst1.8		{q2}, [r4]			@ overlapping stores
	vst1.8		{q0}, [r0]

	pop		{r4-r6, pc}
ENDPROC(ce_aes_cbc_cts_encrypt)

ENTRY(ce_aes_cbc_cts_decrypt)
	push		{r4-r6, lr}
	ldrd		r4, r5, [sp, #16]

	movw		ip, :lower16:.Lcts_permute_table
	movt		ip, :upper16:.Lcts_permute_table
	sub		r4, r4, #16
	add		lr, ip, #32
	add		ip, ip, r4
	sub		lr, lr, r4
	vld1.8		{q5}, [ip]
	vld1.8		{q6}, [lr]

	add		ip, r1, r4
	vld1.8		{q0}, [r1]			@ overlapping loads
	vld1.8		{q1}, [ip]

	vld1.8		{q3}, [r5]			@ get iv
	prepare_key	r2, r3

	bl		aes_decrypt

	vtbl.8		d4, {d0-d1}, d10
	vtbl.8		d5, {d0-d1}, d11
	vtbx.8		d0, {d2-d3}, d12
	vtbx.8		d1, {d2-d3}, d13

	veor		q1, q1, q2
	bl		aes_decrypt
	veor		q0, q0, q3			@ xor with iv

	add		r4, r0, r4
	vst1.8		{q1}, [r4]			@ overlapping stores
	vst1.8		{q0}, [r0]

	pop		{r4-r6, pc}
ENDPROC(ce_aes_cbc_cts_decrypt)


	/*
	 * aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
	 *		   int blocks, u8 ctr[])
	 */
ENTRY(ce_aes_ctr_encrypt)
	push		{r4-r6, lr}
	ldrd		r4, r5, [sp, #16]
	vld1.8		{q7}, [r5]		@ load ctr
	prepare_key	r2, r3
	vmov		r6, s31			@ keep swabbed ctr in r6
	rev		r6, r6
	cmn		r6, r4			@ 32 bit overflow?
	bcs		.Lctrloop
.Lctrloop4x:
	subs		r4, r4, #4
	bmi		.Lctr1x

	/*
	 * NOTE: the sequence below has been carefully tweaked to avoid
	 * a silicon erratum that exists in Cortex-A57 (#1742098) and
	 * Cortex-A72 (#1655431) cores, where AESE/AESMC instruction pairs
	 * may produce an incorrect result if they take their input from a
	 * register of which a single 32-bit lane has been updated the last
	 * time it was modified. To work around this, the lanes of registers
	 * q0-q3 below are not manipulated individually, and the different
	 * counter values are prepared by successive manipulations of q7.
	 */
	add		ip, r6, #1
	vmov		q0, q7
	rev		ip, ip
	add		lr, r6, #2
	vmov		s31, ip			@ set lane 3 of q1 via q7
	add		ip, r6, #3
	rev		lr, lr
	vmov		q1, q7
	vmov		s31, lr			@ set lane 3 of q2 via q7
	rev		ip, ip
	vmov		q2, q7
	vmov		s31, ip			@ set lane 3 of q3 via q7
	add		r6, r6, #4
	vmov		q3, q7

	vld1.8		{q4-q5}, [r1]!
	vld1.8		{q6}, [r1]!
	vld1.8		{q15}, [r1]!
	bl		aes_encrypt_4x
	veor		q0, q0, q4
	veor		q1, q1, q5
	veor		q2, q2, q6
	veor		q3, q3, q15
	rev		ip, r6
	vst1.8		{q0-q1}, [r0]!
	vst1.8		{q2-q3}, [r0]!
	vmov		s31, ip
	b		.Lctrloop4x
.Lctr1x:
	adds		r4, r4, #4
	beq		.Lctrout
.Lctrloop:
	vmov		q0, q7
	bl		aes_encrypt

	adds		r6, r6, #1		@ increment BE ctr
	rev		ip, r6
	vmov		s31, ip
	bcs		.Lctrcarry

.Lctrcarrydone:
	subs		r4, r4, #1
	bmi		.Lctrtailblock		@ blocks < 0 means tail block
	vld1.8		{q3}, [r1]!
	veor		q3, q0, q3
	vst1.8		{q3}, [r0]!
	bne		.Lctrloop

.Lctrout:
	vst1.8		{q7}, [r5]		@ return next CTR value
	pop		{r4-r6, pc}

.Lctrtailblock:
	vst1.8		{q0}, [r0, :64]		@ return the key stream
	b		.Lctrout

.Lctrcarry:
	.irp		sreg, s30, s29, s28
	vmov		ip, \sreg		@ load next word of ctr
	rev		ip, ip			@ ... to handle the carry
	adds		ip, ip, #1
	rev		ip, ip
	vmov		\sreg, ip
	bcc		.Lctrcarrydone
	.endr
	b		.Lctrcarrydone
ENDPROC(ce_aes_ctr_encrypt)

	/*
	 * aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds,
	 *		   int bytes, u8 iv[], u32 const rk2[], int first)
	 * aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds,
	 *		   int bytes, u8 iv[], u32 const rk2[], int first)
	 */

	.macro		next_tweak, out, in, const, tmp
	vshr.s64	\tmp, \in, #63
	vand		\tmp, \tmp, \const
	vadd.u64	\out, \in, \in
	vext.8		\tmp, \tmp, \tmp, #8
	veor		\out, \out, \tmp
	.endm

ce_aes_xts_init:
	vmov.i32	d30, #0x87		@ compose tweak mask vector
	vmovl.u32	q15, d30
	vshr.u64	d30, d31, #7

	ldrd		r4, r5, [sp, #16]	@ load args
	ldr		r6, [sp, #28]
	vld1.8		{q0}, [r5]		@ load iv
	teq		r6, #1			@ start of a block?
	bxne		lr

	@ Encrypt the IV in q0 with the second AES key. This should only
	@ be done at the start of a block.
	ldr		r6, [sp, #24]		@ load AES key 2
	prepare_key	r6, r3
	add		ip, r6, #32		@ 3rd round key of key 2
	b		.Laes_encrypt_tweak	@ tail call
ENDPROC(ce_aes_xts_init)

ENTRY(ce_aes_xts_encrypt)
	push		{r4-r6, lr}

	bl		ce_aes_xts_init		@ run shared prologue
	prepare_key	r2, r3
	vmov		q4, q0

	teq		r6, #0			@ start of a block?
	bne		.Lxtsenc4x

.Lxtsencloop4x:
	next_tweak	q4, q4, q15, q10
.Lxtsenc4x:
	subs		r4, r4, #64
	bmi		.Lxtsenc1x
	vld1.8		{q0-q1}, [r1]!		@ get 4 pt blocks
	vld1.8		{q2-q3}, [r1]!
	next_tweak	q5, q4, q15, q10
	veor		q0, q0, q4
	next_tweak	q6, q5, q15, q10
	veor		q1, q1, q5
	next_tweak	q7, q6, q15, q10
	veor		q2, q2, q6
	veor		q3, q3, q7
	bl		aes_encrypt_4x
	veor		q0, q0, q4
	veor		q1, q1, q5
	veor		q2, q2, q6
	veor		q3, q3, q7
	vst1.8		{q0-q1}, [r0]!		@ write 4 ct blocks
	vst1.8		{q2-q3}, [r0]!
	vmov		q4, q7
	teq		r4, #0
	beq		.Lxtsencret
	b		.Lxtsencloop4x
.Lxtsenc1x:
	adds		r4, r4, #64
	beq		.Lxtsencout
	subs		r4, r4, #16
	bmi		.LxtsencctsNx
.Lxtsencloop:
	vld1.8		{q0}, [r1]!
.Lxtsencctsout:
	veor		q0, q0, q4
	bl		aes_encrypt
	veor		q0, q0, q4
	teq		r4, #0
	beq		.Lxtsencout
	subs		r4, r4, #16
	next_tweak	q4, q4, q15, q6
	bmi		.Lxtsenccts
	vst1.8		{q0}, [r0]!
	b		.Lxtsencloop
.Lxtsencout:
	vst1.8		{q0}, [r0]
.Lxtsencret:
	vst1.8		{q4}, [r5]
	pop		{r4-r6, pc}

.LxtsencctsNx:
	vmov		q0, q3
	sub		r0, r0, #16
.Lxtsenccts:
	movw		ip, :lower16:.Lcts_permute_table
	movt		ip, :upper16:.Lcts_permute_table

	add		r1, r1, r4		@ rewind input pointer
	add		r4, r4, #16		@ # bytes in final block
	add		lr, ip, #32
	add		ip, ip, r4
	sub		lr, lr, r4
	add		r4, r0, r4		@ output address of final block

	vld1.8		{q1}, [r1]		@ load final partial block
	vld1.8		{q2}, [ip]
	vld1.8		{q3}, [lr]

	vtbl.8		d4, {d0-d1}, d4
	vtbl.8		d5, {d0-d1}, d5
	vtbx.8		d0, {d2-d3}, d6
	vtbx.8		d1, {d2-d3}, d7

	vst1.8		{q2}, [r4]		@ overlapping stores
	mov		r4, #0
	b		.Lxtsencctsout
ENDPROC(ce_aes_xts_encrypt)


ENTRY(ce_aes_xts_decrypt)
	push		{r4-r6, lr}

	bl		ce_aes_xts_init		@ run shared prologue
	prepare_key	r2, r3
	vmov		q4, q0

	/* subtract 16 bytes if we are doing CTS */
	tst		r4, #0xf
	subne		r4, r4, #0x10

	teq		r6, #0			@ start of a block?
	bne		.Lxtsdec4x

.Lxtsdecloop4x:
	next_tweak	q4, q4, q15, q10
.Lxtsdec4x:
	subs		r4, r4, #64
	bmi		.Lxtsdec1x
	vld1.8		{q0-q1}, [r1]!		@ get 4 ct blocks
	vld1.8		{q2-q3}, [r1]!
	next_tweak	q5, q4, q15, q10
	veor		q0, q0, q4
	next_tweak	q6, q5, q15, q10
	veor		q1, q1, q5
	next_tweak	q7, q6, q15, q10
	veor		q2, q2, q6
	veor		q3, q3, q7
	bl		aes_decrypt_4x
	veor		q0, q0, q4
	veor		q1, q1, q5
	veor		q2, q2, q6
	veor		q3, q3, q7
	vst1.8		{q0-q1}, [r0]!		@ write 4 pt blocks
	vst1.8		{q2-q3}, [r0]!
	vmov		q4, q7
	teq		r4, #0
	beq		.Lxtsdecout
	b		.Lxtsdecloop4x
.Lxtsdec1x:
	adds		r4, r4, #64
	beq		.Lxtsdecout
	subs		r4, r4, #16
.Lxtsdecloop:
	vld1.8		{q0}, [r1]!
	bmi		.Lxtsdeccts
.Lxtsdecctsout:
	veor		q0, q0, q4
	bl		aes_decrypt
	veor		q0, q0, q4
	vst1.8		{q0}, [r0]!
	teq		r4, #0
	beq		.Lxtsdecout
	subs		r4, r4, #16
	next_tweak	q4, q4, q15, q6
	b		.Lxtsdecloop
.Lxtsdecout:
	vst1.8		{q4}, [r5]
	pop		{r4-r6, pc}

.Lxtsdeccts:
	movw		ip, :lower16:.Lcts_permute_table
	movt		ip, :upper16:.Lcts_permute_table

	add		r1, r1, r4		@ rewind input pointer
	add		r4, r4, #16		@ # bytes in final block
	add		lr, ip, #32
	add		ip, ip, r4
	sub		lr, lr, r4
	add		r4, r0, r4		@ output address of final block

	next_tweak	q5, q4, q15, q6

	vld1.8		{q1}, [r1]		@ load final partial block
	vld1.8		{q2}, [ip]
	vld1.8		{q3}, [lr]

	veor		q0, q0, q5
	bl		aes_decrypt
	veor		q0, q0, q5

	vtbl.8		d4, {d0-d1}, d4
	vtbl.8		d5, {d0-d1}, d5
	vtbx.8		d0, {d2-d3}, d6
	vtbx.8		d1, {d2-d3}, d7

	vst1.8		{q2}, [r4]		@ overlapping stores
	mov		r4, #0
	b		.Lxtsdecctsout
ENDPROC(ce_aes_xts_decrypt)

	/*
	 * u32 ce_aes_sub(u32 input) - use the aese instruction to perform the
	 *                             AES sbox substitution on each byte in
	 *                             'input'
	 */
ENTRY(ce_aes_sub)
	vdup.32		q1, r0
	veor		q0, q0, q0
	aese.8		q0, q1
	vmov		r0, s0
	bx		lr
ENDPROC(ce_aes_sub)

	/*
	 * void ce_aes_invert(u8 *dst, u8 *src) - perform the Inverse MixColumns
	 *                                        operation on round key *src
	 */
ENTRY(ce_aes_invert)
	vld1.32		{q0}, [r1]
	aesimc.8	q0, q0
	vst1.32		{q0}, [r0]
	bx		lr
ENDPROC(ce_aes_invert)

	.section	".rodata", "a"
	.align		6
.Lcts_permute_table:
	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff