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
|
/*
***********************************************************************
*
* Implementation of the Skein hash function.
*
* Source code author: Doug Whiting, 2008.
*
* This algorithm and source code is released to the public domain.
*
***********************************************************************
*/
#ifndef _SKEIN_BLOCK_H_
#define _SKEIN_BLOCK_H_
#include "skein_base.h" /* get the Skein API definitions */
#ifndef SKEIN_USE_ASM
#define SKEIN_USE_ASM (0) /* default is all C code (no ASM) */
#endif
#ifndef SKEIN_LOOP
#define SKEIN_LOOP 001 /* default: unroll 256 and 512, but not 1024 */
#endif
#define BLK_BITS (WCNT * 64) /* some useful definitions for code here */
#define KW_TWK_BASE (0)
#define KW_KEY_BASE (3)
#define ks (kw + KW_KEY_BASE)
#define ts (kw + KW_TWK_BASE)
#ifdef SKEIN_DEBUG
#define debug_save_tweak(ctx) \
{ \
ctx->h.tweak[0] = ts[0]; \
ctx->h.tweak[1] = ts[1]; \
}
#else
#define debug_save_tweak(ctx)
#endif
#if !(SKEIN_USE_ASM & 256)
#undef RCNT
#define RCNT (SKEIN_256_ROUNDS_TOTAL / 8)
#ifdef SKEIN_LOOP /* configure how much to unroll the loop */
#define SKEIN_UNROLL_256 (((SKEIN_LOOP) / 100) % 10)
#else
#define SKEIN_UNROLL_256 (0)
#endif
#if SKEIN_UNROLL_256
#if (RCNT % SKEIN_UNROLL_256)
#error "Invalid SKEIN_UNROLL_256" /* sanity check on unroll count */
#endif
#endif
#define ROUND256(p0, p1, p2, p3, ROT, r_num) \
do { \
X##p0 += X##p1; \
X##p1 = rol64(X##p1, ROT##_0); \
X##p1 ^= X##p0; \
X##p2 += X##p3; \
X##p3 = rol64(X##p3, ROT##_1); \
X##p3 ^= X##p2; \
} while (0)
#if SKEIN_UNROLL_256 == 0
#define R256(p0, p1, p2, p3, ROT, r_num) /* fully unrolled */ \
ROUND256(p0, p1, p2, p3, ROT, r_num)
#define I256(R) \
do { \
/* inject the key schedule value */ \
X0 += ks[((R) + 1) % 5]; \
X1 += ks[((R) + 2) % 5] + ts[((R) + 1) % 3]; \
X2 += ks[((R) + 3) % 5] + ts[((R) + 2) % 3]; \
X3 += ks[((R) + 4) % 5] + (R) + 1; \
} while (0)
#else
/* looping version */
#define R256(p0, p1, p2, p3, ROT, r_num) ROUND256(p0, p1, p2, p3, ROT, r_num)
#define I256(R) \
do { \
/* inject the key schedule value */ \
X0 += ks[r + (R) + 0]; \
X1 += ks[r + (R) + 1] + ts[r + (R) + 0];\
X2 += ks[r + (R) + 2] + ts[r + (R) + 1];\
X3 += ks[r + (R) + 3] + r + (R); \
/* rotate key schedule */ \
ks[r + (R) + 4] = ks[r + (R) - 1]; \
ts[r + (R) + 2] = ts[r + (R) - 1]; \
} while (0)
#endif
#define R256_8_ROUNDS(R) \
do { \
R256(0, 1, 2, 3, R_256_0, 8 * (R) + 1); \
R256(0, 3, 2, 1, R_256_1, 8 * (R) + 2); \
R256(0, 1, 2, 3, R_256_2, 8 * (R) + 3); \
R256(0, 3, 2, 1, R_256_3, 8 * (R) + 4); \
I256(2 * (R)); \
R256(0, 1, 2, 3, R_256_4, 8 * (R) + 5); \
R256(0, 3, 2, 1, R_256_5, 8 * (R) + 6); \
R256(0, 1, 2, 3, R_256_6, 8 * (R) + 7); \
R256(0, 3, 2, 1, R_256_7, 8 * (R) + 8); \
I256(2 * (R) + 1); \
} while (0)
#define R256_UNROLL_R(NN) \
((SKEIN_UNROLL_256 == 0 && \
SKEIN_256_ROUNDS_TOTAL / 8 > (NN)) || \
(SKEIN_UNROLL_256 > (NN)))
#if (SKEIN_UNROLL_256 > 14)
#error "need more unrolling in skein_256_process_block"
#endif
#endif
#if !(SKEIN_USE_ASM & 512)
#undef RCNT
#define RCNT (SKEIN_512_ROUNDS_TOTAL / 8)
#ifdef SKEIN_LOOP /* configure how much to unroll the loop */
#define SKEIN_UNROLL_512 (((SKEIN_LOOP) / 10) % 10)
#else
#define SKEIN_UNROLL_512 (0)
#endif
#if SKEIN_UNROLL_512
#if (RCNT % SKEIN_UNROLL_512)
#error "Invalid SKEIN_UNROLL_512" /* sanity check on unroll count */
#endif
#endif
#define ROUND512(p0, p1, p2, p3, p4, p5, p6, p7, ROT, r_num) \
do { \
X##p0 += X##p1; \
X##p1 = rol64(X##p1, ROT##_0); \
X##p1 ^= X##p0; \
X##p2 += X##p3; \
X##p3 = rol64(X##p3, ROT##_1); \
X##p3 ^= X##p2; \
X##p4 += X##p5; \
X##p5 = rol64(X##p5, ROT##_2); \
X##p5 ^= X##p4; \
X##p6 += X##p7; \
X##p7 = rol64(X##p7, ROT##_3); \
X##p7 ^= X##p6; \
} while (0)
#if SKEIN_UNROLL_512 == 0
#define R512(p0, p1, p2, p3, p4, p5, p6, p7, ROT, r_num) /* unrolled */ \
ROUND512(p0, p1, p2, p3, p4, p5, p6, p7, ROT, r_num)
#define I512(R) \
do { \
/* inject the key schedule value */ \
X0 += ks[((R) + 1) % 9]; \
X1 += ks[((R) + 2) % 9]; \
X2 += ks[((R) + 3) % 9]; \
X3 += ks[((R) + 4) % 9]; \
X4 += ks[((R) + 5) % 9]; \
X5 += ks[((R) + 6) % 9] + ts[((R) + 1) % 3]; \
X6 += ks[((R) + 7) % 9] + ts[((R) + 2) % 3]; \
X7 += ks[((R) + 8) % 9] + (R) + 1; \
} while (0)
#else /* looping version */
#define R512(p0, p1, p2, p3, p4, p5, p6, p7, ROT, r_num) \
ROUND512(p0, p1, p2, p3, p4, p5, p6, p7, ROT, r_num) \
#define I512(R) \
do { \
/* inject the key schedule value */ \
X0 += ks[r + (R) + 0]; \
X1 += ks[r + (R) + 1]; \
X2 += ks[r + (R) + 2]; \
X3 += ks[r + (R) + 3]; \
X4 += ks[r + (R) + 4]; \
X5 += ks[r + (R) + 5] + ts[r + (R) + 0]; \
X6 += ks[r + (R) + 6] + ts[r + (R) + 1]; \
X7 += ks[r + (R) + 7] + r + (R); \
/* rotate key schedule */ \
ks[r + (R) + 8] = ks[r + (R) - 1]; \
ts[r + (R) + 2] = ts[r + (R) - 1]; \
} while (0)
#endif /* end of looped code definitions */
#define R512_8_ROUNDS(R) /* do 8 full rounds */ \
do { \
R512(0, 1, 2, 3, 4, 5, 6, 7, R_512_0, 8 * (R) + 1); \
R512(2, 1, 4, 7, 6, 5, 0, 3, R_512_1, 8 * (R) + 2); \
R512(4, 1, 6, 3, 0, 5, 2, 7, R_512_2, 8 * (R) + 3); \
R512(6, 1, 0, 7, 2, 5, 4, 3, R_512_3, 8 * (R) + 4); \
I512(2 * (R)); \
R512(0, 1, 2, 3, 4, 5, 6, 7, R_512_4, 8 * (R) + 5); \
R512(2, 1, 4, 7, 6, 5, 0, 3, R_512_5, 8 * (R) + 6); \
R512(4, 1, 6, 3, 0, 5, 2, 7, R_512_6, 8 * (R) + 7); \
R512(6, 1, 0, 7, 2, 5, 4, 3, R_512_7, 8 * (R) + 8); \
I512(2 * (R) + 1); /* and key injection */ \
} while (0)
#define R512_UNROLL_R(NN) \
((SKEIN_UNROLL_512 == 0 && \
SKEIN_512_ROUNDS_TOTAL / 8 > (NN)) || \
(SKEIN_UNROLL_512 > (NN)))
#if (SKEIN_UNROLL_512 > 14)
#error "need more unrolling in skein_512_process_block"
#endif
#endif
#if !(SKEIN_USE_ASM & 1024)
#undef RCNT
#define RCNT (SKEIN_1024_ROUNDS_TOTAL / 8)
#ifdef SKEIN_LOOP /* configure how much to unroll the loop */
#define SKEIN_UNROLL_1024 ((SKEIN_LOOP) % 10)
#else
#define SKEIN_UNROLL_1024 (0)
#endif
#if (SKEIN_UNROLL_1024 != 0)
#if (RCNT % SKEIN_UNROLL_1024)
#error "Invalid SKEIN_UNROLL_1024" /* sanity check on unroll count */
#endif
#endif
#define ROUND1024(p0, p1, p2, p3, p4, p5, p6, p7, p8, p9, pA, pB, pC, pD, pE, \
pF, ROT, r_num) \
do { \
X##p0 += X##p1; \
X##p1 = rol64(X##p1, ROT##_0); \
X##p1 ^= X##p0; \
X##p2 += X##p3; \
X##p3 = rol64(X##p3, ROT##_1); \
X##p3 ^= X##p2; \
X##p4 += X##p5; \
X##p5 = rol64(X##p5, ROT##_2); \
X##p5 ^= X##p4; \
X##p6 += X##p7; \
X##p7 = rol64(X##p7, ROT##_3); \
X##p7 ^= X##p6; \
X##p8 += X##p9; \
X##p9 = rol64(X##p9, ROT##_4); \
X##p9 ^= X##p8; \
X##pA += X##pB; \
X##pB = rol64(X##pB, ROT##_5); \
X##pB ^= X##pA; \
X##pC += X##pD; \
X##pD = rol64(X##pD, ROT##_6); \
X##pD ^= X##pC; \
X##pE += X##pF; \
X##pF = rol64(X##pF, ROT##_7); \
X##pF ^= X##pE; \
} while (0)
#if SKEIN_UNROLL_1024 == 0
#define R1024(p0, p1, p2, p3, p4, p5, p6, p7, p8, p9, pA, pB, pC, pD, pE, pF, \
ROT, rn) \
ROUND1024(p0, p1, p2, p3, p4, p5, p6, p7, p8, p9, pA, pB, pC, pD, pE, \
pF, ROT, rn) \
#define I1024(R) \
do { \
/* inject the key schedule value */ \
X00 += ks[((R) + 1) % 17]; \
X01 += ks[((R) + 2) % 17]; \
X02 += ks[((R) + 3) % 17]; \
X03 += ks[((R) + 4) % 17]; \
X04 += ks[((R) + 5) % 17]; \
X05 += ks[((R) + 6) % 17]; \
X06 += ks[((R) + 7) % 17]; \
X07 += ks[((R) + 8) % 17]; \
X08 += ks[((R) + 9) % 17]; \
X09 += ks[((R) + 10) % 17]; \
X10 += ks[((R) + 11) % 17]; \
X11 += ks[((R) + 12) % 17]; \
X12 += ks[((R) + 13) % 17]; \
X13 += ks[((R) + 14) % 17] + ts[((R) + 1) % 3]; \
X14 += ks[((R) + 15) % 17] + ts[((R) + 2) % 3]; \
X15 += ks[((R) + 16) % 17] + (R) + 1; \
} while (0)
#else /* looping version */
#define R1024(p0, p1, p2, p3, p4, p5, p6, p7, p8, p9, pA, pB, pC, pD, pE, pF, \
ROT, rn) \
ROUND1024(p0, p1, p2, p3, p4, p5, p6, p7, p8, p9, pA, pB, pC, pD, pE, \
pF, ROT, rn) \
#define I1024(R) \
do { \
/* inject the key schedule value */ \
X00 += ks[r + (R) + 0]; \
X01 += ks[r + (R) + 1]; \
X02 += ks[r + (R) + 2]; \
X03 += ks[r + (R) + 3]; \
X04 += ks[r + (R) + 4]; \
X05 += ks[r + (R) + 5]; \
X06 += ks[r + (R) + 6]; \
X07 += ks[r + (R) + 7]; \
X08 += ks[r + (R) + 8]; \
X09 += ks[r + (R) + 9]; \
X10 += ks[r + (R) + 10]; \
X11 += ks[r + (R) + 11]; \
X12 += ks[r + (R) + 12]; \
X13 += ks[r + (R) + 13] + ts[r + (R) + 0]; \
X14 += ks[r + (R) + 14] + ts[r + (R) + 1]; \
X15 += ks[r + (R) + 15] + r + (R); \
/* rotate key schedule */ \
ks[r + (R) + 16] = ks[r + (R) - 1]; \
ts[r + (R) + 2] = ts[r + (R) - 1]; \
} while (0)
#endif
#define R1024_8_ROUNDS(R) \
do { \
R1024(00, 01, 02, 03, 04, 05, 06, 07, 08, 09, 10, 11, 12, \
13, 14, 15, R1024_0, 8 * (R) + 1); \
R1024(00, 09, 02, 13, 06, 11, 04, 15, 10, 07, 12, 03, 14, \
05, 08, 01, R1024_1, 8 * (R) + 2); \
R1024(00, 07, 02, 05, 04, 03, 06, 01, 12, 15, 14, 13, 08, \
11, 10, 09, R1024_2, 8 * (R) + 3); \
R1024(00, 15, 02, 11, 06, 13, 04, 09, 14, 01, 08, 05, 10, \
03, 12, 07, R1024_3, 8 * (R) + 4); \
I1024(2 * (R)); \
R1024(00, 01, 02, 03, 04, 05, 06, 07, 08, 09, 10, 11, 12, \
13, 14, 15, R1024_4, 8 * (R) + 5); \
R1024(00, 09, 02, 13, 06, 11, 04, 15, 10, 07, 12, 03, 14, \
05, 08, 01, R1024_5, 8 * (R) + 6); \
R1024(00, 07, 02, 05, 04, 03, 06, 01, 12, 15, 14, 13, 08, \
11, 10, 09, R1024_6, 8 * (R) + 7); \
R1024(00, 15, 02, 11, 06, 13, 04, 09, 14, 01, 08, 05, 10, \
03, 12, 07, R1024_7, 8 * (R) + 8); \
I1024(2 * (R) + 1); \
} while (0)
#define R1024_UNROLL_R(NN) \
((SKEIN_UNROLL_1024 == 0 && \
SKEIN_1024_ROUNDS_TOTAL / 8 > (NN)) || \
(SKEIN_UNROLL_1024 > (NN)))
#if (SKEIN_UNROLL_1024 > 14)
#error "need more unrolling in Skein_1024_Process_Block"
#endif
#endif
void skein_256_process_block(struct skein_256_ctx *ctx, const u8 *blk_ptr,
size_t blk_cnt, size_t byte_cnt_add);
void skein_512_process_block(struct skein_512_ctx *ctx, const u8 *blk_ptr,
size_t blk_cnt, size_t byte_cnt_add);
void skein_1024_process_block(struct skein_1024_ctx *ctx, const u8 *blk_ptr,
size_t blk_cnt, size_t byte_cnt_add);
#endif
|
