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
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* SM4-GCM AEAD Algorithm using ARMv8 Crypto Extensions
* as specified in rfc8998
* https://datatracker.ietf.org/doc/html/rfc8998
*
* Copyright (C) 2016 Jussi Kivilinna <jussi.kivilinna@iki.fi>
* Copyright (C) 2022 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
*/
#include <linux/linkage.h>
#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
.arch armv8-a+crypto
.irp b, 0, 1, 2, 3, 24, 25, 26, 27, 28, 29, 30, 31
.set .Lv\b\().4s, \b
.endr
.macro sm4e, vd, vn
.inst 0xcec08400 | (.L\vn << 5) | .L\vd
.endm
/* Register macros */
/* Used for both encryption and decryption */
#define RHASH v21
#define RRCONST v22
#define RZERO v23
/* Helper macros. */
/*
* input: m0, m1
* output: r0:r1 (low 128-bits in r0, high in r1)
*/
#define PMUL_128x128(r0, r1, m0, m1, T0, T1) \
ext T0.16b, m1.16b, m1.16b, #8; \
pmull r0.1q, m0.1d, m1.1d; \
pmull T1.1q, m0.1d, T0.1d; \
pmull2 T0.1q, m0.2d, T0.2d; \
pmull2 r1.1q, m0.2d, m1.2d; \
eor T0.16b, T0.16b, T1.16b; \
ext T1.16b, RZERO.16b, T0.16b, #8; \
ext T0.16b, T0.16b, RZERO.16b, #8; \
eor r0.16b, r0.16b, T1.16b; \
eor r1.16b, r1.16b, T0.16b;
#define PMUL_128x128_4x(r0, r1, m0, m1, T0, T1, \
r2, r3, m2, m3, T2, T3, \
r4, r5, m4, m5, T4, T5, \
r6, r7, m6, m7, T6, T7) \
ext T0.16b, m1.16b, m1.16b, #8; \
ext T2.16b, m3.16b, m3.16b, #8; \
ext T4.16b, m5.16b, m5.16b, #8; \
ext T6.16b, m7.16b, m7.16b, #8; \
pmull r0.1q, m0.1d, m1.1d; \
pmull r2.1q, m2.1d, m3.1d; \
pmull r4.1q, m4.1d, m5.1d; \
pmull r6.1q, m6.1d, m7.1d; \
pmull T1.1q, m0.1d, T0.1d; \
pmull T3.1q, m2.1d, T2.1d; \
pmull T5.1q, m4.1d, T4.1d; \
pmull T7.1q, m6.1d, T6.1d; \
pmull2 T0.1q, m0.2d, T0.2d; \
pmull2 T2.1q, m2.2d, T2.2d; \
pmull2 T4.1q, m4.2d, T4.2d; \
pmull2 T6.1q, m6.2d, T6.2d; \
pmull2 r1.1q, m0.2d, m1.2d; \
pmull2 r3.1q, m2.2d, m3.2d; \
pmull2 r5.1q, m4.2d, m5.2d; \
pmull2 r7.1q, m6.2d, m7.2d; \
eor T0.16b, T0.16b, T1.16b; \
eor T2.16b, T2.16b, T3.16b; \
eor T4.16b, T4.16b, T5.16b; \
eor T6.16b, T6.16b, T7.16b; \
ext T1.16b, RZERO.16b, T0.16b, #8; \
ext T3.16b, RZERO.16b, T2.16b, #8; \
ext T5.16b, RZERO.16b, T4.16b, #8; \
ext T7.16b, RZERO.16b, T6.16b, #8; \
ext T0.16b, T0.16b, RZERO.16b, #8; \
ext T2.16b, T2.16b, RZERO.16b, #8; \
ext T4.16b, T4.16b, RZERO.16b, #8; \
ext T6.16b, T6.16b, RZERO.16b, #8; \
eor r0.16b, r0.16b, T1.16b; \
eor r2.16b, r2.16b, T3.16b; \
eor r4.16b, r4.16b, T5.16b; \
eor r6.16b, r6.16b, T7.16b; \
eor r1.16b, r1.16b, T0.16b; \
eor r3.16b, r3.16b, T2.16b; \
eor r5.16b, r5.16b, T4.16b; \
eor r7.16b, r7.16b, T6.16b;
/*
* input: r0:r1 (low 128-bits in r0, high in r1)
* output: a
*/
#define REDUCTION(a, r0, r1, rconst, T0, T1) \
pmull2 T0.1q, r1.2d, rconst.2d; \
ext T1.16b, T0.16b, RZERO.16b, #8; \
ext T0.16b, RZERO.16b, T0.16b, #8; \
eor r1.16b, r1.16b, T1.16b; \
eor r0.16b, r0.16b, T0.16b; \
pmull T0.1q, r1.1d, rconst.1d; \
eor a.16b, r0.16b, T0.16b;
#define SM4_CRYPT_PMUL_128x128_BLK(b0, r0, r1, m0, m1, T0, T1) \
rev32 b0.16b, b0.16b; \
ext T0.16b, m1.16b, m1.16b, #8; \
sm4e b0.4s, v24.4s; \
pmull r0.1q, m0.1d, m1.1d; \
sm4e b0.4s, v25.4s; \
pmull T1.1q, m0.1d, T0.1d; \
sm4e b0.4s, v26.4s; \
pmull2 T0.1q, m0.2d, T0.2d; \
sm4e b0.4s, v27.4s; \
pmull2 r1.1q, m0.2d, m1.2d; \
sm4e b0.4s, v28.4s; \
eor T0.16b, T0.16b, T1.16b; \
sm4e b0.4s, v29.4s; \
ext T1.16b, RZERO.16b, T0.16b, #8; \
sm4e b0.4s, v30.4s; \
ext T0.16b, T0.16b, RZERO.16b, #8; \
sm4e b0.4s, v31.4s; \
eor r0.16b, r0.16b, T1.16b; \
rev64 b0.4s, b0.4s; \
eor r1.16b, r1.16b, T0.16b; \
ext b0.16b, b0.16b, b0.16b, #8; \
rev32 b0.16b, b0.16b;
#define SM4_CRYPT_PMUL_128x128_BLK3(b0, b1, b2, \
r0, r1, m0, m1, T0, T1, \
r2, r3, m2, m3, T2, T3, \
r4, r5, m4, m5, T4, T5) \
rev32 b0.16b, b0.16b; \
rev32 b1.16b, b1.16b; \
rev32 b2.16b, b2.16b; \
ext T0.16b, m1.16b, m1.16b, #8; \
ext T2.16b, m3.16b, m3.16b, #8; \
ext T4.16b, m5.16b, m5.16b, #8; \
sm4e b0.4s, v24.4s; \
sm4e b1.4s, v24.4s; \
sm4e b2.4s, v24.4s; \
pmull r0.1q, m0.1d, m1.1d; \
pmull r2.1q, m2.1d, m3.1d; \
pmull r4.1q, m4.1d, m5.1d; \
sm4e b0.4s, v25.4s; \
sm4e b1.4s, v25.4s; \
sm4e b2.4s, v25.4s; \
pmull T1.1q, m0.1d, T0.1d; \
pmull T3.1q, m2.1d, T2.1d; \
pmull T5.1q, m4.1d, T4.1d; \
sm4e b0.4s, v26.4s; \
sm4e b1.4s, v26.4s; \
sm4e b2.4s, v26.4s; \
pmull2 T0.1q, m0.2d, T0.2d; \
pmull2 T2.1q, m2.2d, T2.2d; \
pmull2 T4.1q, m4.2d, T4.2d; \
sm4e b0.4s, v27.4s; \
sm4e b1.4s, v27.4s; \
sm4e b2.4s, v27.4s; \
pmull2 r1.1q, m0.2d, m1.2d; \
pmull2 r3.1q, m2.2d, m3.2d; \
pmull2 r5.1q, m4.2d, m5.2d; \
sm4e b0.4s, v28.4s; \
sm4e b1.4s, v28.4s; \
sm4e b2.4s, v28.4s; \
eor T0.16b, T0.16b, T1.16b; \
eor T2.16b, T2.16b, T3.16b; \
eor T4.16b, T4.16b, T5.16b; \
sm4e b0.4s, v29.4s; \
sm4e b1.4s, v29.4s; \
sm4e b2.4s, v29.4s; \
ext T1.16b, RZERO.16b, T0.16b, #8; \
ext T3.16b, RZERO.16b, T2.16b, #8; \
ext T5.16b, RZERO.16b, T4.16b, #8; \
sm4e b0.4s, v30.4s; \
sm4e b1.4s, v30.4s; \
sm4e b2.4s, v30.4s; \
ext T0.16b, T0.16b, RZERO.16b, #8; \
ext T2.16b, T2.16b, RZERO.16b, #8; \
ext T4.16b, T4.16b, RZERO.16b, #8; \
sm4e b0.4s, v31.4s; \
sm4e b1.4s, v31.4s; \
sm4e b2.4s, v31.4s; \
eor r0.16b, r0.16b, T1.16b; \
eor r2.16b, r2.16b, T3.16b; \
eor r4.16b, r4.16b, T5.16b; \
rev64 b0.4s, b0.4s; \
rev64 b1.4s, b1.4s; \
rev64 b2.4s, b2.4s; \
eor r1.16b, r1.16b, T0.16b; \
eor r3.16b, r3.16b, T2.16b; \
eor r5.16b, r5.16b, T4.16b; \
ext b0.16b, b0.16b, b0.16b, #8; \
ext b1.16b, b1.16b, b1.16b, #8; \
ext b2.16b, b2.16b, b2.16b, #8; \
eor r0.16b, r0.16b, r2.16b; \
eor r1.16b, r1.16b, r3.16b; \
rev32 b0.16b, b0.16b; \
rev32 b1.16b, b1.16b; \
rev32 b2.16b, b2.16b; \
eor r0.16b, r0.16b, r4.16b; \
eor r1.16b, r1.16b, r5.16b;
#define inc32_le128(vctr) \
mov vctr.d[1], x9; \
add w6, w9, #1; \
mov vctr.d[0], x8; \
bfi x9, x6, #0, #32; \
rev64 vctr.16b, vctr.16b;
#define GTAG_HASH_LENGTHS(vctr0, vlen) \
ld1 {vlen.16b}, [x7]; \
/* construct CTR0 */ \
/* the lower 32-bits of initial IV is always be32(1) */ \
mov x6, #0x1; \
bfi x9, x6, #0, #32; \
mov vctr0.d[0], x8; \
mov vctr0.d[1], x9; \
rbit vlen.16b, vlen.16b; \
rev64 vctr0.16b, vctr0.16b; \
/* authtag = GCTR(CTR0, GHASH) */ \
eor RHASH.16b, RHASH.16b, vlen.16b; \
SM4_CRYPT_PMUL_128x128_BLK(vctr0, RR0, RR1, RHASH, RH1, \
RTMP0, RTMP1); \
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP2, RTMP3); \
rbit RHASH.16b, RHASH.16b; \
eor RHASH.16b, RHASH.16b, vctr0.16b;
/* Register macros for encrypt and ghash */
/* can be the same as input v0-v3 */
#define RR1 v0
#define RR3 v1
#define RR5 v2
#define RR7 v3
#define RR0 v4
#define RR2 v5
#define RR4 v6
#define RR6 v7
#define RTMP0 v8
#define RTMP1 v9
#define RTMP2 v10
#define RTMP3 v11
#define RTMP4 v12
#define RTMP5 v13
#define RTMP6 v14
#define RTMP7 v15
#define RH1 v16
#define RH2 v17
#define RH3 v18
#define RH4 v19
.align 3
SYM_FUNC_START(sm4_ce_pmull_ghash_setup)
/* input:
* x0: round key array, CTX
* x1: ghash table
*/
SM4_PREPARE(x0)
adr_l x2, .Lghash_rconst
ld1r {RRCONST.2d}, [x2]
eor RZERO.16b, RZERO.16b, RZERO.16b
/* H = E(K, 0^128) */
rev32 v0.16b, RZERO.16b
SM4_CRYPT_BLK_BE(v0)
/* H ^ 1 */
rbit RH1.16b, v0.16b
/* H ^ 2 */
PMUL_128x128(RR0, RR1, RH1, RH1, RTMP0, RTMP1)
REDUCTION(RH2, RR0, RR1, RRCONST, RTMP2, RTMP3)
/* H ^ 3 */
PMUL_128x128(RR0, RR1, RH2, RH1, RTMP0, RTMP1)
REDUCTION(RH3, RR0, RR1, RRCONST, RTMP2, RTMP3)
/* H ^ 4 */
PMUL_128x128(RR0, RR1, RH2, RH2, RTMP0, RTMP1)
REDUCTION(RH4, RR0, RR1, RRCONST, RTMP2, RTMP3)
st1 {RH1.16b-RH4.16b}, [x1]
ret
SYM_FUNC_END(sm4_ce_pmull_ghash_setup)
.align 3
SYM_FUNC_START(pmull_ghash_update)
/* input:
* x0: ghash table
* x1: ghash result
* x2: src
* w3: nblocks
*/
ld1 {RH1.16b-RH4.16b}, [x0]
ld1 {RHASH.16b}, [x1]
rbit RHASH.16b, RHASH.16b
adr_l x4, .Lghash_rconst
ld1r {RRCONST.2d}, [x4]
eor RZERO.16b, RZERO.16b, RZERO.16b
.Lghash_loop_4x:
cmp w3, #4
blt .Lghash_loop_1x
sub w3, w3, #4
ld1 {v0.16b-v3.16b}, [x2], #64
rbit v0.16b, v0.16b
rbit v1.16b, v1.16b
rbit v2.16b, v2.16b
rbit v3.16b, v3.16b
/*
* (in0 ^ HASH) * H^4 => rr0:rr1
* (in1) * H^3 => rr2:rr3
* (in2) * H^2 => rr4:rr5
* (in3) * H^1 => rr6:rr7
*/
eor RHASH.16b, RHASH.16b, v0.16b
PMUL_128x128_4x(RR0, RR1, RHASH, RH4, RTMP0, RTMP1,
RR2, RR3, v1, RH3, RTMP2, RTMP3,
RR4, RR5, v2, RH2, RTMP4, RTMP5,
RR6, RR7, v3, RH1, RTMP6, RTMP7)
eor RR0.16b, RR0.16b, RR2.16b
eor RR1.16b, RR1.16b, RR3.16b
eor RR0.16b, RR0.16b, RR4.16b
eor RR1.16b, RR1.16b, RR5.16b
eor RR0.16b, RR0.16b, RR6.16b
eor RR1.16b, RR1.16b, RR7.16b
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP0, RTMP1)
cbz w3, .Lghash_end
b .Lghash_loop_4x
.Lghash_loop_1x:
sub w3, w3, #1
ld1 {v0.16b}, [x2], #16
rbit v0.16b, v0.16b
eor RHASH.16b, RHASH.16b, v0.16b
PMUL_128x128(RR0, RR1, RHASH, RH1, RTMP0, RTMP1)
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP2, RTMP3)
cbnz w3, .Lghash_loop_1x
.Lghash_end:
rbit RHASH.16b, RHASH.16b
st1 {RHASH.2d}, [x1]
ret
SYM_FUNC_END(pmull_ghash_update)
.align 3
SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
* x2: src
* x3: ctr (big endian, 128 bit)
* w4: nbytes
* x5: ghash result
* x6: ghash table
* x7: lengths (only for last block)
*/
SM4_PREPARE(x0)
ldp x8, x9, [x3]
rev x8, x8
rev x9, x9
ld1 {RH1.16b-RH4.16b}, [x6]
ld1 {RHASH.16b}, [x5]
rbit RHASH.16b, RHASH.16b
adr_l x6, .Lghash_rconst
ld1r {RRCONST.2d}, [x6]
eor RZERO.16b, RZERO.16b, RZERO.16b
cbz w4, .Lgcm_enc_hash_len
.Lgcm_enc_loop_4x:
cmp w4, #(4 * 16)
blt .Lgcm_enc_loop_1x
sub w4, w4, #(4 * 16)
/* construct CTRs */
inc32_le128(v0) /* +0 */
inc32_le128(v1) /* +1 */
inc32_le128(v2) /* +2 */
inc32_le128(v3) /* +3 */
ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64
SM4_CRYPT_BLK4(v0, v1, v2, v3)
eor v0.16b, v0.16b, RTMP0.16b
eor v1.16b, v1.16b, RTMP1.16b
eor v2.16b, v2.16b, RTMP2.16b
eor v3.16b, v3.16b, RTMP3.16b
st1 {v0.16b-v3.16b}, [x1], #64
/* ghash update */
rbit v0.16b, v0.16b
rbit v1.16b, v1.16b
rbit v2.16b, v2.16b
rbit v3.16b, v3.16b
/*
* (in0 ^ HASH) * H^4 => rr0:rr1
* (in1) * H^3 => rr2:rr3
* (in2) * H^2 => rr4:rr5
* (in3) * H^1 => rr6:rr7
*/
eor RHASH.16b, RHASH.16b, v0.16b
PMUL_128x128_4x(RR0, RR1, RHASH, RH4, RTMP0, RTMP1,
RR2, RR3, v1, RH3, RTMP2, RTMP3,
RR4, RR5, v2, RH2, RTMP4, RTMP5,
RR6, RR7, v3, RH1, RTMP6, RTMP7)
eor RR0.16b, RR0.16b, RR2.16b
eor RR1.16b, RR1.16b, RR3.16b
eor RR0.16b, RR0.16b, RR4.16b
eor RR1.16b, RR1.16b, RR5.16b
eor RR0.16b, RR0.16b, RR6.16b
eor RR1.16b, RR1.16b, RR7.16b
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP0, RTMP1)
cbz w4, .Lgcm_enc_hash_len
b .Lgcm_enc_loop_4x
.Lgcm_enc_loop_1x:
cmp w4, #16
blt .Lgcm_enc_tail
sub w4, w4, #16
/* construct CTRs */
inc32_le128(v0)
ld1 {RTMP0.16b}, [x2], #16
SM4_CRYPT_BLK(v0)
eor v0.16b, v0.16b, RTMP0.16b
st1 {v0.16b}, [x1], #16
/* ghash update */
rbit v0.16b, v0.16b
eor RHASH.16b, RHASH.16b, v0.16b
PMUL_128x128(RR0, RR1, RHASH, RH1, RTMP0, RTMP1)
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP2, RTMP3)
cbz w4, .Lgcm_enc_hash_len
b .Lgcm_enc_loop_1x
.Lgcm_enc_tail:
/* construct CTRs */
inc32_le128(v0)
SM4_CRYPT_BLK(v0)
/* load permute table */
adr_l x0, .Lcts_permute_table
add x0, x0, #32
sub x0, x0, w4, uxtw
ld1 {v3.16b}, [x0]
.Lgcm_enc_tail_loop:
/* do encrypt */
ldrb w0, [x2], #1 /* get 1 byte from input */
umov w6, v0.b[0] /* get top crypted byte */
eor w6, w6, w0 /* w6 = CTR ^ input */
strb w6, [x1], #1 /* store out byte */
/* shift right out one byte */
ext v0.16b, v0.16b, v0.16b, #1
/* the last ciphertext is placed in high bytes */
ins v0.b[15], w6
subs w4, w4, #1
bne .Lgcm_enc_tail_loop
/* padding last block with zeros */
tbl v0.16b, {v0.16b}, v3.16b
/* ghash update */
rbit v0.16b, v0.16b
eor RHASH.16b, RHASH.16b, v0.16b
PMUL_128x128(RR0, RR1, RHASH, RH1, RTMP0, RTMP1)
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP2, RTMP3)
.Lgcm_enc_hash_len:
cbz x7, .Lgcm_enc_end
GTAG_HASH_LENGTHS(v1, v3)
b .Lgcm_enc_ret
.Lgcm_enc_end:
/* store new CTR */
rev x8, x8
rev x9, x9
stp x8, x9, [x3]
rbit RHASH.16b, RHASH.16b
.Lgcm_enc_ret:
/* store new MAC */
st1 {RHASH.2d}, [x5]
ret
SYM_FUNC_END(sm4_ce_pmull_gcm_enc)
#undef RR1
#undef RR3
#undef RR5
#undef RR7
#undef RR0
#undef RR2
#undef RR4
#undef RR6
#undef RTMP0
#undef RTMP1
#undef RTMP2
#undef RTMP3
#undef RTMP4
#undef RTMP5
#undef RTMP6
#undef RTMP7
#undef RH1
#undef RH2
#undef RH3
#undef RH4
/* Register macros for decrypt */
/* v0-v2 for building CTRs, v3-v5 for saving inputs */
#define RR1 v6
#define RR3 v7
#define RR5 v8
#define RR0 v9
#define RR2 v10
#define RR4 v11
#define RTMP0 v12
#define RTMP1 v13
#define RTMP2 v14
#define RTMP3 v15
#define RTMP4 v16
#define RTMP5 v17
#define RH1 v18
#define RH2 v19
#define RH3 v20
.align 3
SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
* x2: src
* x3: ctr (big endian, 128 bit)
* w4: nbytes
* x5: ghash result
* x6: ghash table
* x7: lengths (only for last block)
*/
SM4_PREPARE(x0)
ldp x8, x9, [x3]
rev x8, x8
rev x9, x9
ld1 {RH1.16b-RH3.16b}, [x6]
ld1 {RHASH.16b}, [x5]
rbit RHASH.16b, RHASH.16b
adr_l x6, .Lghash_rconst
ld1r {RRCONST.2d}, [x6]
eor RZERO.16b, RZERO.16b, RZERO.16b
cbz w4, .Lgcm_dec_hash_len
.Lgcm_dec_loop_3x:
cmp w4, #(3 * 16)
blt .Lgcm_dec_loop_1x
sub w4, w4, #(3 * 16)
ld1 {v3.16b-v5.16b}, [x2], #(3 * 16)
/* construct CTRs */
inc32_le128(v0) /* +0 */
rbit v6.16b, v3.16b
inc32_le128(v1) /* +1 */
rbit v7.16b, v4.16b
inc32_le128(v2) /* +2 */
rbit v8.16b, v5.16b
eor RHASH.16b, RHASH.16b, v6.16b
/* decrypt & ghash update */
SM4_CRYPT_PMUL_128x128_BLK3(v0, v1, v2,
RR0, RR1, RHASH, RH3, RTMP0, RTMP1,
RR2, RR3, v7, RH2, RTMP2, RTMP3,
RR4, RR5, v8, RH1, RTMP4, RTMP5)
eor v0.16b, v0.16b, v3.16b
eor v1.16b, v1.16b, v4.16b
eor v2.16b, v2.16b, v5.16b
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP0, RTMP1)
st1 {v0.16b-v2.16b}, [x1], #(3 * 16)
cbz w4, .Lgcm_dec_hash_len
b .Lgcm_dec_loop_3x
.Lgcm_dec_loop_1x:
cmp w4, #16
blt .Lgcm_dec_tail
sub w4, w4, #16
ld1 {v3.16b}, [x2], #16
/* construct CTRs */
inc32_le128(v0)
rbit v6.16b, v3.16b
eor RHASH.16b, RHASH.16b, v6.16b
SM4_CRYPT_PMUL_128x128_BLK(v0, RR0, RR1, RHASH, RH1, RTMP0, RTMP1)
eor v0.16b, v0.16b, v3.16b
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP2, RTMP3)
st1 {v0.16b}, [x1], #16
cbz w4, .Lgcm_dec_hash_len
b .Lgcm_dec_loop_1x
.Lgcm_dec_tail:
/* construct CTRs */
inc32_le128(v0)
SM4_CRYPT_BLK(v0)
/* load permute table */
adr_l x0, .Lcts_permute_table
add x0, x0, #32
sub x0, x0, w4, uxtw
ld1 {v3.16b}, [x0]
.Lgcm_dec_tail_loop:
/* do decrypt */
ldrb w0, [x2], #1 /* get 1 byte from input */
umov w6, v0.b[0] /* get top crypted byte */
eor w6, w6, w0 /* w6 = CTR ^ input */
strb w6, [x1], #1 /* store out byte */
/* shift right out one byte */
ext v0.16b, v0.16b, v0.16b, #1
/* the last ciphertext is placed in high bytes */
ins v0.b[15], w0
subs w4, w4, #1
bne .Lgcm_dec_tail_loop
/* padding last block with zeros */
tbl v0.16b, {v0.16b}, v3.16b
/* ghash update */
rbit v0.16b, v0.16b
eor RHASH.16b, RHASH.16b, v0.16b
PMUL_128x128(RR0, RR1, RHASH, RH1, RTMP0, RTMP1)
REDUCTION(RHASH, RR0, RR1, RRCONST, RTMP2, RTMP3)
.Lgcm_dec_hash_len:
cbz x7, .Lgcm_dec_end
GTAG_HASH_LENGTHS(v1, v3)
b .Lgcm_dec_ret
.Lgcm_dec_end:
/* store new CTR */
rev x8, x8
rev x9, x9
stp x8, x9, [x3]
rbit RHASH.16b, RHASH.16b
.Lgcm_dec_ret:
/* store new MAC */
st1 {RHASH.2d}, [x5]
ret
SYM_FUNC_END(sm4_ce_pmull_gcm_dec)
.section ".rodata", "a"
.align 4
.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
.Lghash_rconst:
.quad 0x87
|
