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
|
/*
* ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions
*
* Copyright (C) 2016 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.
*
* 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>
.text
.align 6
ENTRY(chacha20_block_xor_neon)
// x0: Input state matrix, s
// x1: 1 data block output, o
// x2: 1 data block input, i
//
// This function encrypts one ChaCha20 block by loading the state matrix
// in four NEON registers. It performs matrix operation on four words in
// parallel, but requires shuffling to rearrange the words after each
// round.
//
// x0..3 = s0..3
adr x3, ROT8
ld1 {v0.4s-v3.4s}, [x0]
ld1 {v8.4s-v11.4s}, [x0]
ld1 {v12.4s}, [x3]
mov x3, #10
.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 x3, x3, #1
b.ne .Ldoubleround
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]
ret
ENDPROC(chacha20_block_xor_neon)
.align 6
ENTRY(chacha20_4block_xor_neon)
// x0: Input state matrix, s
// x1: 4 data blocks output, o
// x2: 4 data blocks input, i
//
// This function encrypts four consecutive ChaCha20 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.
//
adr x3, CTRINC // ... and ROT8
ld1 {v30.4s-v31.4s}, [x3]
// x0..15[0-3] = s0..3[0..3]
mov x4, x0
ld4r { v0.4s- v3.4s}, [x4], #16
ld4r { v4.4s- v7.4s}, [x4], #16
ld4r { v8.4s-v11.4s}, [x4], #16
ld4r {v12.4s-v15.4s}, [x4]
// x12 += counter values 0-3
add v12.4s, v12.4s, v30.4s
mov x3, #10
.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 v1.4s, v1.4s, v5.4s
add v2.4s, v2.4s, v6.4s
add v3.4s, v3.4s, v7.4s
eor v12.16b, v12.16b, v0.16b
eor v13.16b, v13.16b, v1.16b
eor v14.16b, v14.16b, v2.16b
eor v15.16b, v15.16b, v3.16b
rev32 v12.8h, v12.8h
rev32 v13.8h, v13.8h
rev32 v14.8h, v14.8h
rev32 v15.8h, v15.8h
// 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 v9.4s, v9.4s, v13.4s
add v10.4s, v10.4s, v14.4s
add v11.4s, v11.4s, v15.4s
eor v16.16b, v4.16b, v8.16b
eor v17.16b, v5.16b, v9.16b
eor v18.16b, v6.16b, v10.16b
eor v19.16b, v7.16b, v11.16b
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
sri v5.4s, v17.4s, #20
sri v6.4s, v18.4s, #20
sri v7.4s, v19.4s, #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 v1.4s, v1.4s, v5.4s
add v2.4s, v2.4s, v6.4s
add v3.4s, v3.4s, v7.4s
eor v12.16b, v12.16b, v0.16b
eor v13.16b, v13.16b, v1.16b
eor v14.16b, v14.16b, v2.16b
eor v15.16b, v15.16b, v3.16b
tbl v12.16b, {v12.16b}, v31.16b
tbl v13.16b, {v13.16b}, v31.16b
tbl v14.16b, {v14.16b}, v31.16b
tbl v15.16b, {v15.16b}, v31.16b
// 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 v9.4s, v9.4s, v13.4s
add v10.4s, v10.4s, v14.4s
add v11.4s, v11.4s, v15.4s
eor v16.16b, v4.16b, v8.16b
eor v17.16b, v5.16b, v9.16b
eor v18.16b, v6.16b, v10.16b
eor v19.16b, v7.16b, v11.16b
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
sri v5.4s, v17.4s, #25
sri v6.4s, v18.4s, #25
sri v7.4s, v19.4s, #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 v1.4s, v1.4s, v6.4s
add v2.4s, v2.4s, v7.4s
add v3.4s, v3.4s, v4.4s
eor v15.16b, v15.16b, v0.16b
eor v12.16b, v12.16b, v1.16b
eor v13.16b, v13.16b, v2.16b
eor v14.16b, v14.16b, v3.16b
rev32 v15.8h, v15.8h
rev32 v12.8h, v12.8h
rev32 v13.8h, v13.8h
rev32 v14.8h, v14.8h
// 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 v11.4s,
|