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
|
// SPDX-License-Identifier: GPL-2.0
/*
* NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
*
* Copyright (c) 2018 Google, Inc
*
* Author: Eric Biggers <ebiggers@google.com>
*/
#include <linux/linkage.h>
.text
.fpu neon
// arguments
ROUND_KEYS .req r0 // const {u64,u32} *round_keys
NROUNDS .req r1 // int nrounds
DST .req r2 // void *dst
SRC .req r3 // const void *src
NBYTES .req r4 // unsigned int nbytes
TWEAK .req r5 // void *tweak
// registers which hold the data being encrypted/decrypted
X0 .req q0
X0_L .req d0
X0_H .req d1
Y0 .req q1
Y0_H .req d3
X1 .req q2
X1_L .req d4
X1_H .req d5
Y1 .req q3
Y1_H .req d7
X2 .req q4
X2_L .req d8
X2_H .req d9
Y2 .req q5
Y2_H .req d11
X3 .req q6
X3_L .req d12
X3_H .req d13
Y3 .req q7
Y3_H .req d15
// the round key, duplicated in all lanes
ROUND_KEY .req q8
ROUND_KEY_L .req d16
ROUND_KEY_H .req d17
// index vector for vtbl-based 8-bit rotates
ROTATE_TABLE .req d18
// multiplication table for updating XTS tweaks
GF128MUL_TABLE .req d19
GF64MUL_TABLE .req d19
// current XTS tweak value(s)
TWEAKV .req q10
TWEAKV_L .req d20
TWEAKV_H .req d21
TMP0 .req q12
TMP0_L .req d24
TMP0_H .req d25
TMP1 .req q13
TMP2 .req q14
TMP3 .req q15
.align 4
.Lror64_8_table:
.byte 1, 2, 3, 4, 5, 6, 7, 0
.Lror32_8_table:
.byte 1, 2, 3, 0, 5, 6, 7, 4
.Lrol64_8_table:
.byte 7, 0, 1, 2, 3, 4, 5, 6
.Lrol32_8_table:
.byte 3, 0, 1, 2, 7, 4, 5, 6
.Lgf128mul_table:
.byte 0, 0x87
.fill 14
.Lgf64mul_table:
.byte 0, 0x1b, (0x1b << 1), (0x1b << 1) ^ 0x1b
.fill 12
/*
* _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
*
* Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
* Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
* of ROUND_KEY. 'n' is the lane size: 64 for Speck128, or 32 for Speck64.
*
* The 8-bit rotates are implemented using vtbl instead of vshr + vsli because
* the vtbl approach is faster on some processors and the same speed on others.
*/
.macro _speck_round_128bytes n
// x = ror(x, 8)
vtbl.8 X0_L, {X0_L}, ROTATE_TABLE
vtbl.8 X0_H, {X0_H}, ROTATE_TABLE
vtbl.8 X1_L, {X1_L}, ROTATE_TABLE
vtbl.8 X1_H, {X1_H}, ROTATE_TABLE
vtbl.8 X2_L, {X2_L}, ROTATE_TABLE
vtbl.8 X2_H, {X2_H}, ROTATE_TABLE
vtbl.8 X3_L, {X3_L}, ROTATE_TABLE
vtbl.8 X3_H, {X3_H}, ROTATE_TABLE
// x += y
vadd.u\n X0, Y0
vadd.u\n X1, Y1
vadd.u\n X2, Y2
vadd.u\n X3, Y3
// x ^= k
veor X0, ROUND_KEY
veor X1, ROUND_KEY
veor X2, ROUND_KEY
veor X3, ROUND_KEY
// y = rol(y, 3)
vshl.u\n TMP0, Y0, #3
vshl.u\n TMP1, Y1, #3
vshl.u\n TMP2, Y2, #3
vshl.u\n TMP3, Y3, #3
vsri.u\n TMP0, Y0, #(\n - 3)
vsri.u\n TMP1, Y1, #(\n - 3)
vsri.u\n TMP2, Y2, #(\n - 3)
vsri.u\n TMP3, Y3, #(\n - 3)
// y ^= x
veor Y0, TMP0, X0
veor Y1, TMP1, X1
veor Y2, TMP2, X2
veor Y3, TMP3, X3
.endm
/*
* _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
*
* This is the inverse of _speck_round_128bytes().
*/
.macro _speck_unround_128bytes n
// y ^= x
veor TMP0, Y0, X0
veor TMP1, Y1, X1
veor TMP2, Y2, X2
veor TMP3, Y3, X3
// y = ror(y, 3)
vshr.u\n Y0, TMP0, #3
vshr.u\n Y1, TMP1, #3
vshr.u\n Y2, TMP2, #3
vshr.u\n Y3, TMP3, #3
vsli.u\n Y0, TMP0, #(\n - 3)
vsli.u\n Y1, TMP1, #(\n - 3)
vsli.u\n Y2, TMP2, #(\n - 3)
vsli.u\n Y3, TMP3, #(\n - 3)
// x ^= k
veor X0, ROUND_KEY
veor X1, ROUND_KEY
veor X2, ROUND_KEY
veor X3, ROUND_KEY
// x -= y
vsub.u\n X0, Y0
vsub.u\n X1, Y1
vsub.u\n X2, Y2
vsub.u\n X3, Y3
// x = rol(x, 8);
vtbl.8 X0_L, {X0_L}, ROTATE_TABLE
vtbl.8 X0_H, {X0_H}, ROTATE_TABLE
vtbl.8 X1_L, {X1_L}, ROTATE_TABLE
vtbl.8 X1_H, {X1_H}, ROTATE_TABLE
vtbl.8 X2_L, {X2_L}, ROTATE_TABLE
vtbl.8 X2_H, {X2_H}, ROTATE_TABLE
vtbl.8 X3_L, {X3_L}, ROTATE_TABLE
vtbl.8 X3_H, {X3_H}, ROTATE_TABLE
.endm
.macro _xts128_precrypt_one dst_reg, tweak_buf, tmp
// Load the next source block
vld1.8 {\dst_reg}, [SRC]!
// Save the current tweak in the tweak buffer
vst1.8 {TWEAKV}, [\tweak_buf:128]!
// XOR the next source block with the current tweak
veor \dst_reg, TWEAKV
/*
* Calculate the next tweak by multiplying the current one by x,
* modulo p(x) = x^128 + x^7 + x^2 + x + 1.
*/
vshr.u64 \tmp, TWEAKV, #63
vshl.u64 TWEAKV, #1
veor TWEAKV_H, \tmp\()_L
vtbl.8 \tmp\()_H, {GF128MUL_TABLE}, \tmp\()_H
veor TWEAKV_L, \tmp\()_H
.endm
.macro _xts64_precrypt_two dst_reg, tweak_buf, tmp
// Load the next two source blocks
vld1.8 {\dst_reg}, [SRC]!
// Save the current two tweaks in the tweak buffer
vst1.8 {TWEAKV}, [\tweak_buf:128]!
// XOR the next two source blocks with the current two tweaks
veor \dst_reg, TWEAKV
/*
* Calculate the next two tweaks by multiplying the current ones by x^2,
* modulo p(x) = x^64 + x^4 + x^3 + x + 1.
*/
vshr.u64 \tmp, TWEAKV, #62
vshl.u64 TWEAKV, #2
vtbl.8 \tmp\()_L, {GF64MUL_TABLE}, \tmp\()_L
vtbl.8 \tmp\()_H, {GF64MUL_TABLE}, \tmp\()_H
veor TWEAKV, \tmp
.endm
/*
* _speck_xts_crypt() - Speck-XTS encryption/decryption
*
* Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
* using Speck-XTS, specifically the variant with a block size of '2n' and round
* count given by NROUNDS. The expanded round keys are given in ROUND_KEYS, and
* the current XTS tweak value is given in TWEAK. It's assumed that NBYTES is a
* nonzero multiple of 128.
*/
.macro _speck_xts_crypt n, decrypting
push {r4-r7}
mov r7, sp
/*
* The first four parameters were passed in registers r0-r3. Load the
* additional parameters, which were passed on the stack.
*/
ldr NBYTES, [sp, #16]
ldr TWEAK, [sp, #20]
/*
* If decrypting, modify the ROUND_KEYS parameter to point to the last
* round key rather than the first, since for decryption the round keys
* are used in reverse order.
*/
.if \decrypting
.if \n == 64
add ROUND_KEYS, ROUND_KEYS, NROUNDS, lsl #3
sub ROUND_KEYS, #8
.else
add ROUND_KEYS, ROUND_KEYS, NROUNDS, lsl #2
sub ROUND_KEYS, #4
.endif
.endif
// Load the index vector for vtbl-based 8-bit rotates
.if \decrypting
ldr r12, =.Lrol\n\()_8_table
.else
ldr r12, =.Lror\n\()_8_table
.endif
vld1.8 {ROTATE_TABLE}, [r12:64]
// One-time XTS preparation
/*
* Allocate stack space to store 128 bytes worth of tweaks. For
* performance, this space is aligned to a 16-byte boundary so that we
* can use the load/store instructions that declare 16-byte alignment.
*/
sub sp, #128
bic sp, #0xf
.if \n == 64
// Load first tweak
vld1.8 {TWEAKV}, [TWEAK]
// Load GF(2^128) multiplication table
ldr r12, =.Lgf128mul_table
vld1.8 {GF128MUL_TABLE}, [r12:64]
.else
// Load first tweak
vld1.8 {TWEAKV_L}, [TWEAK]
// Load GF(2^64) multiplication table
ldr r12, =.Lgf64mul_table
vld1.8 {GF64MUL_TABLE}, [r12:64]
// Calculate second tweak, packing it together with the first
vshr.u64 TMP0_L, TWEAKV_L, #63
vtbl.u8 TMP0_L, {GF64MUL_TABLE}, TMP0_L
vshl.u64 TWEAKV_H, TWEAKV_L, #1
veor TWEAKV_H, TMP0_L
.endif
.Lnext_128bytes_\@:
/*
* Load the source blocks into {X,Y}[0-3], XOR them with their XTS tweak
* values, and save the tweaks on the stack for later. Then
* de-interleave the 'x' and 'y' elements of each block, i.e. make it so
* that the X[0-3] registers contain only the second halves of blocks,
* and the Y[0-3] registers contain only the first halves of blocks.
* (Speck uses the order (y, x) rather than the more intuitive (x, y).)
*/
mov r12, sp
.if \n == 64
_xts128_precrypt_one X0, r12, TMP0
_xts128_precrypt_one Y0, r12, TMP0
_xts128_precrypt_one X1, r12, TMP0
_xts128_precrypt_one Y1, r12, TMP0
_xts128_precrypt_one X2, r12, TMP0
_xts128_precrypt_one Y2, r12, TMP0
_xts128_precrypt_one X3, r12, TMP0
_xts128_precrypt_one Y3, r12, TMP0
vswp X0_L, Y0_H
vswp X1_L, Y1_H
vswp X2_L, Y2_H
vswp X3_L, Y3_H
.else
_xts64_precrypt_two X0, r12, TMP0
_xts64_precrypt_two Y0, r12, TMP0
_xts64_precrypt_two X1, r12, TMP0
_xts64_precrypt_two Y1, r12, TMP0
_xts64_precrypt_two X2, r12, TMP0
_xts64_precrypt_two Y2, r12, TMP0
_xts64_precrypt_two X3, r12, TMP0
_xts64_precrypt_two Y3, r12, TMP0
vuzp.32 Y0, X0
vuzp.32 Y1, X1
vuzp.32 Y2, X2
vuzp.32 Y3, X3
.endif
// Do the cipher rounds
mov r12, ROUND_KEYS
mov r6, NROUNDS
.Lnext_round_\@:
.if \decrypting
.if \n == 64
vld1.64 ROUND_KEY_L, [r12]
sub r12, #8
vmov ROUND_KEY_H, ROUND_KEY_L
.else
vld1.32 {ROUND_KEY_L[],ROUND_KEY_H[]}, [r12]
sub r12, #4
.endif
_speck_unround_128bytes \n
.else
.if \n == 64
vld1.64 ROUND_KEY_L, [r12]!
vmov ROUND_KEY_H, ROUND_KEY_L
.else
vld1.32 {ROUND_KEY_L[],ROUND_KEY_H[]}, [r12]!
.endif
_speck_round_128bytes \n
.endif
subs r6, r6, #1
bne .Lnext_round_\@
// Re-interleave the 'x' and 'y' elements of each block
.if \n == 64
vswp X0_L, Y0_H
vswp X1_L, Y1_H
vswp X2_L, Y2_H
vswp X3_L, Y3_H
.else
vzip.32 Y0, X0
vzip.32 Y1, X1
vzip.32 Y2, X2
vzip.32 Y3, X3
.endif
// XOR the encrypted/decrypted blocks with the tweaks we saved earlier
mov r12, sp
vld1.8 {TMP0, TMP1}, [r12:128]!
vld1.8 {TMP2, TMP3}, [r12:128]!
veor X0, TMP0
veor Y0, TMP1
veor X1, TMP2
veor Y1, TMP3
vld1.8 {TMP0, TMP1}, [r12:128]!
vld1.8 {TMP2, TMP3}, [r12:128]!
veor X2, TMP0
veor Y2, TMP1
veor X3, TMP2
veor Y3, TMP3
// Store the ciphertext in the destination buffer
vst1.8 {X0, Y0}, [DST]!
vst1.8 {X1, Y1}, [DST]!
vst1.8 {X2, Y2}, [DST]!
vst1.8 {X3, Y3}, [DST]!
// Continue if there are more 128-byte chunks remaining, else return
subs NBYTES, #128
bne .Lnext_128bytes_\@
// Store the next tweak
.if \n == 64
vst1.8 {TWEAKV}, [TWEAK]
.else
vst1.8 {TWEAKV_L}, [TWEAK]
.endif
mov sp, r7
pop {r4-r7}
bx lr
.endm
ENTRY(speck128_xts_encrypt_neon)
_speck_xts_crypt n=64, decrypting=0
ENDPROC(speck128_xts_encrypt_neon)
ENTRY(speck128_xts_decrypt_neon)
_speck_xts_crypt n=64, decrypting=1
ENDPROC(speck128_xts_decrypt_neon)
ENTRY(speck64_xts_encrypt_neon)
_speck_xts_crypt n=32, decrypting=0
ENDPROC(speck64_xts_encrypt_neon)
ENTRY(speck64_xts_decrypt_neon)
_speck_xts_crypt n=32, decrypting=1
ENDPROC(speck64_xts_decrypt_neon)
|
