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
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Cast6 Cipher 8-way parallel algorithm (AVX/x86_64)
*
* Copyright (C) 2012 Johannes Goetzfried
* <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
*
* Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*/
#include <linux/linkage.h>
#include <asm/frame.h>
#include "glue_helper-asm-avx.S"
.file "cast6-avx-x86_64-asm_64.S"
.extern cast_s1
.extern cast_s2
.extern cast_s3
.extern cast_s4
/* structure of crypto context */
#define km 0
#define kr (12*4*4)
/* s-boxes */
#define s1 cast_s1
#define s2 cast_s2
#define s3 cast_s3
#define s4 cast_s4
/**********************************************************************
8-way AVX cast6
**********************************************************************/
#define CTX %r15
#define RA1 %xmm0
#define RB1 %xmm1
#define RC1 %xmm2
#define RD1 %xmm3
#define RA2 %xmm4
#define RB2 %xmm5
#define RC2 %xmm6
#define RD2 %xmm7
#define RX %xmm8
#define RKM %xmm9
#define RKR %xmm10
#define RKRF %xmm11
#define RKRR %xmm12
#define R32 %xmm13
#define R1ST %xmm14
#define RTMP %xmm15
#define RID1 %rdi
#define RID1d %edi
#define RID2 %rsi
#define RID2d %esi
#define RGI1 %rdx
#define RGI1bl %dl
#define RGI1bh %dh
#define RGI2 %rcx
#define RGI2bl %cl
#define RGI2bh %ch
#define RGI3 %rax
#define RGI3bl %al
#define RGI3bh %ah
#define RGI4 %rbx
#define RGI4bl %bl
#define RGI4bh %bh
#define RFS1 %r8
#define RFS1d %r8d
#define RFS2 %r9
#define RFS2d %r9d
#define RFS3 %r10
#define RFS3d %r10d
#define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
movzbl src ## bh, RID1d; \
movzbl src ## bl, RID2d; \
shrq $16, src; \
movl s1(, RID1, 4), dst ## d; \
op1 s2(, RID2, 4), dst ## d; \
movzbl src ## bh, RID1d; \
movzbl src ## bl, RID2d; \
interleave_op(il_reg); \
op2 s3(, RID1, 4), dst ## d; \
op3 s4(, RID2, 4), dst ## d;
#define dummy(d) /* do nothing */
#define shr_next(reg) \
shrq $16, reg;
#define F_head(a, x, gi1, gi2, op0) \
op0 a, RKM, x; \
vpslld RKRF, x, RTMP; \
vpsrld RKRR, x, x; \
vpor RTMP, x, x; \
\
vmovq x, gi1; \
vpextrq $1, x, gi2;
#define F_tail(a, x, gi1, gi2, op1, op2, op3) \
lookup_32bit(##gi1, RFS1, op1, op2, op3, shr_next, ##gi1); \
lookup_32bit(##gi2, RFS3, op1, op2, op3, shr_next, ##gi2); \
\
lookup_32bit(##gi1, RFS2, op1, op2, op3, dummy, none); \
shlq $32, RFS2; \
orq RFS1, RFS2; \
lookup_32bit(##gi2, RFS1, op1, op2, op3, dummy, none); \
shlq $32, RFS1; \
orq RFS1, RFS3; \
\
vmovq RFS2, x; \
vpinsrq $1, RFS3, x, x;
#define F_2(a1, b1, a2, b2, op0, op1, op2, op3) \
F_head(b1, RX, RGI1, RGI2, op0); \
F_head(b2, RX, RGI3, RGI4, op0); \
\
F_tail(b1, RX, RGI1, RGI2, op1, op2, op3); \
F_tail(b2, RTMP, RGI3, RGI4, op1, op2, op3); \
\
vpxor a1, RX, a1; \
vpxor a2, RTMP, a2;
#define F1_2(a1, b1, a2, b2) \
F_2(a1, b1, a2, b2, vpaddd, xorl, subl, addl)
#define F2_2(a1, b1, a2, b2) \
F_2(a1, b1, a2, b2, vpxor, subl, addl, xorl)
#define F3_2(a1, b1, a2, b2) \
F_2(a1, b1, a2, b2, vpsubd, addl, xorl, subl)
#define qop(in, out, f) \
F ## f ## _2(out ## 1, in ## 1, out ## 2, in ## 2);
#define get_round_keys(nn) \
vbroadcastss (km+(4*(nn)))(CTX), RKM; \
vpand R1ST, RKR, RKRF; \
vpsubq RKRF, R32, RKRR; \
vpsrldq $1, RKR, RKR;
#define Q(n) \
get_round_keys(4*n+0); \
qop(RD, RC, 1); \
\
get_round_keys(4*n+1); \
qop(RC, RB, 2); \
\
get_round_keys(4*n+2); \
qop(RB, RA, 3); \
\
get_round_keys(4*n+3); \
qop(RA, RD, 1);
#define QBAR(n) \
get_round_keys(4*n+3); \
qop(RA, RD, 1); \
\
get_round_keys(4*n+2); \
qop(RB, RA, 3); \
\
get_round_keys(4*n+1); \
qop(RC, RB, 2); \
\
get_round_keys(4*n+0); \
qop(RD, RC, 1);
#define shuffle(mask) \
vpshufb mask, RKR, RKR;
#define preload_rkr(n, do_mask, mask) \
vbroadcastss .L16_mask, RKR; \
/* add 16-bit rotation to key rotations (mod 32) */ \
vpxor (kr+n*16)(CTX), RKR, RKR; \
do_mask(mask);
#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
vpunpckldq x1, x0, t0; \
vpunpckhdq x1, x0, t2; \
vpunpckldq x3, x2, t1; \
vpunpckhdq x3, x2, x3; \
\
vpunpcklqdq t1, t0, x0; \
vpunpckhqdq t1, t0, x1; \
vpunpcklqdq x3, t2, x2; \
vpunpckhqdq x3, t2, x3;
#define inpack_blocks(x0, x1, x2, x3, t0, t1, t2, rmask) \
vpshufb rmask, x0, x0; \
vpshufb rmask, x1, x1; \
vpshufb rmask, x2, x2; \
vpshufb rmask, x3, x3; \
\
transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
#define outunpack_blocks(x0, x1, x2, x3, t0, t1, t2, rmask) \
transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
\
vpshufb rmask, x0, x0; \
vpshufb rmask, x1, x1; \
vpshufb rmask, x2, x2; \
vpshufb rmask, x3, x3;
.section .rodata.cst16, "aM", @progbits, 16
.align 16
.Lxts_gf128mul_and_shl1_mask:
.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
.Lbswap_mask:
.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
.Lbswap128_mask:
.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
.Lrkr_enc_Q_Q_QBAR_QBAR:
.byte 0, 1, 2, 3, 4, 5, 6, 7, 11, 10, 9, 8, 15, 14, 13, 12
.Lrkr_enc_QBAR_QBAR_QBAR_QBAR:
.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
.Lrkr_dec_Q_Q_Q_Q:
.byte 12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
.Lrkr_dec_Q_Q_QBAR_QBAR:
.byte 12, 13, 14, 15, 8, 9, 10, 11, 7, 6, 5, 4, 3, 2, 1, 0
.Lrkr_dec_QBAR_QBAR_QBAR_QBAR:
.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
.section .rodata.cst4.L16_mask, "aM", @progbits, 4
.align 4
.L16_mask:
.byte 16, 16, 16, 16
.section .rodata.cst4.L32_mask, "aM", @progbits, 4
.align 4
.L32_mask:
.byte 32, 0, 0, 0
.section .rodata.cst4.first_mask, "aM", @progbits, 4
.align 4
.Lfirst_mask:
.byte 0x1f, 0, 0, 0
.text
.align 8
SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
/* input:
* %rdi: ctx
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
* output:
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
*/
pushq %r15;
pushq %rbx;
movq %rdi, CTX;
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
preload_rkr(0, dummy, none);
Q(0);
Q(1);
Q(2);
Q(3);
preload_rkr(1, shuffle, .Lrkr_enc_Q_Q_QBAR_QBAR);
Q(4);
Q(5);
QBAR(6);
QBAR(7);
preload_rkr(2, shuffle, .Lrkr_enc_QBAR_QBAR_QBAR_QBAR);
QBAR(8);
QBAR(9);
QBAR(10);
QBAR(11);
popq %rbx;
popq %r15;
vmovdqa .Lbswap_mask, RKM;
outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
RET;
SYM_FUNC_END(__cast6_enc_blk8)
.align 8
SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
/* input:
* %rdi: ctx
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
* output:
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks
*/
pushq %r15;
pushq %rbx;
movq %rdi, CTX;
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
preload_rkr(2, shuffle, .Lrkr_dec_Q_Q_Q_Q);
Q(11);
Q(10);
Q(9);
Q(8);
preload_rkr(1, shuffle, .Lrkr_dec_Q_Q_QBAR_QBAR);
Q(7);
Q(6);
QBAR(5);
QBAR(4);
preload_rkr(0, shuffle, .Lrkr_dec_QBAR_QBAR_QBAR_QBAR);
QBAR(3);
QBAR(2);
QBAR(1);
QBAR(0);
popq %rbx;
popq %r15;
vmovdqa .Lbswap_mask, RKM;
outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
RET;
SYM_FUNC_END(__cast6_dec_blk8)
SYM_FUNC_START(cast6_ecb_enc_8way)
/* input:
* %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
pushq %r15;
movq %rdi, CTX;
movq %rsi, %r11;
load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
call __cast6_enc_blk8;
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
popq %r15;
FRAME_END
RET;
SYM_FUNC_END(cast6_ecb_enc_8way)
SYM_FUNC_START(cast6_ecb_dec_8way)
/* input:
* %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
pushq %r15;
movq %rdi, CTX;
movq %rsi, %r11;
load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
call __cast6_dec_blk8;
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
popq %r15;
FRAME_END
RET;
SYM_FUNC_END(cast6_ecb_dec_8way)
SYM_FUNC_START(cast6_cbc_dec_8way)
/* input:
* %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
pushq %r12;
pushq %r15;
movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
call __cast6_dec_blk8;
store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
popq %r15;
popq %r12;
FRAME_END
RET;
SYM_FUNC_END(cast6_cbc_dec_8way)
SYM_FUNC_START(cast6_ctr_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
* %rdx: src
* %rcx: iv (little endian, 128bit)
*/
FRAME_BEGIN
pushq %r12;
pushq %r15
movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
RD2, RX, RKR, RKM);
call __cast6_enc_blk8;
store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
popq %r15;
popq %r12;
FRAME_END
RET;
SYM_FUNC_END(cast6_ctr_8way)
SYM_FUNC_START(cast6_xts_enc_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
* %rdx: src
* %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
*/
FRAME_BEGIN
pushq %r15;
movq %rdi, CTX
movq %rsi, %r11;
/* regs <= src, dst <= IVs, regs <= regs xor IVs */
load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask);
call __cast6_enc_blk8;
/* dst <= regs xor IVs(in dst) */
store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
popq %r15;
FRAME_END
RET;
SYM_FUNC_END(cast6_xts_enc_8way)
SYM_FUNC_START(cast6_xts_dec_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
* %rdx: src
* %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
*/
FRAME_BEGIN
pushq %r15;
movq %rdi, CTX
movq %rsi, %r11;
/* regs <= src, dst <= IVs, regs <= regs xor IVs */
load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask);
call __cast6_dec_blk8;
/* dst <= regs xor IVs(in dst) */
store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
popq %r15;
FRAME_END
RET;
SYM_FUNC_END(cast6_xts_dec_8way)
|
