|
1 /* |
|
2 * ==================================================================== |
|
3 * Copyright (c) 1998-2011 The OpenSSL Project. All rights reserved. |
|
4 * |
|
5 * Redistribution and use in source and binary forms, with or without |
|
6 * modification, are permitted provided that the following conditions |
|
7 * are met: |
|
8 * |
|
9 * 1. Redistributions of source code must retain the above copyright |
|
10 * notice, this list of conditions and the following disclaimer. |
|
11 * |
|
12 * 2. Redistributions in binary form must reproduce the above copyright |
|
13 * notice, this list of conditions and the following disclaimer in |
|
14 * the documentation and/or other materials provided with the |
|
15 * distribution. |
|
16 * |
|
17 * 3. All advertising materials mentioning features or use of this |
|
18 * software must display the following acknowledgment: |
|
19 * "This product includes software developed by the OpenSSL Project |
|
20 * for use in the OpenSSL Toolkit. (http://www.openssl.org/)" |
|
21 * |
|
22 * 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to |
|
23 * endorse or promote products derived from this software without |
|
24 * prior written permission. For written permission, please contact |
|
25 * [email protected]. |
|
26 * |
|
27 * 5. Products derived from this software may not be called "OpenSSL" |
|
28 * nor may "OpenSSL" appear in their names without prior written |
|
29 * permission of the OpenSSL Project. |
|
30 * |
|
31 * 6. Redistributions of any form whatsoever must retain the following |
|
32 * acknowledgment: |
|
33 * "This product includes software developed by the OpenSSL Project |
|
34 * for use in the OpenSSL Toolkit (http://www.openssl.org/)" |
|
35 * |
|
36 * THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY |
|
37 * EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
|
38 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR |
|
39 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OpenSSL PROJECT OR |
|
40 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
|
41 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT |
|
42 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
|
43 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
|
44 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, |
|
45 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) |
|
46 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED |
|
47 * OF THE POSSIBILITY OF SUCH DAMAGE. |
|
48 * ==================================================================== |
|
49 */ |
|
50 |
|
51 /* |
|
52 * Copyright (c) 2011, Oracle and/or its affiliates. All rights reserved. |
|
53 */ |
|
54 |
|
55 /*LINTLIBRARY*/ |
|
56 |
|
57 #if defined(lint) || defined(__lint) |
|
58 |
|
59 |
|
60 #include <sys/types.h> |
|
61 |
|
62 /*ARGSUSED*/ |
|
63 void t4_aes_expand128(uint64_t *rk, const uint32_t *key) |
|
64 { return; } |
|
65 |
|
66 /*ARGSUSED*/ |
|
67 void t4_aes_expand192(uint64_t *rk, const uint32_t *key) |
|
68 { return; } |
|
69 |
|
70 /*ARGSUSED*/ |
|
71 void t4_aes_expand256(uint64_t *rk, const uint32_t *key) |
|
72 { return; } |
|
73 |
|
74 void t4_aes128_load_keys_for_encrypt(uint64_t *ks) |
|
75 { return; } |
|
76 |
|
77 /*ARGSUSED*/ |
|
78 void t4_aes192_load_keys_for_encrypt(uint64_t *ks) |
|
79 { return; } |
|
80 |
|
81 /*ARGSUSED*/ |
|
82 void t4_aes256_load_keys_for_encrypt(uint64_t *ks) |
|
83 { return; } |
|
84 |
|
85 /*ARGSUSED*/ |
|
86 void t4_aes128_ecb_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
87 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
88 { return; } |
|
89 |
|
90 /*ARGSUSED*/ |
|
91 void t4_aes192_ecb_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
92 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
93 { return; } |
|
94 |
|
95 /*ARGSUSED*/ |
|
96 void t4_aes256_ecb_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
97 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
98 { return; } |
|
99 |
|
100 /*ARGSUSED*/ |
|
101 void t4_aes128_cbc_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
102 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
103 { return; } |
|
104 |
|
105 /*ARGSUSED*/ |
|
106 void t4_aes192_cbc_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
107 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
108 { return; } |
|
109 |
|
110 /*ARGSUSED*/ |
|
111 void t4_aes256_cbc_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
112 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
113 { return; } |
|
114 |
|
115 /*ARGSUSED*/ |
|
116 void t4_aes128_ctr_crypt(uint64_t *ks, uint64_t *asm_in, |
|
117 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
118 { return; } |
|
119 |
|
120 /*ARGSUSED*/ |
|
121 void t4_aes192_ctr_crypt(uint64_t *ks, uint64_t *asm_in, |
|
122 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
123 { return; } |
|
124 |
|
125 /*ARGSUSED*/ |
|
126 void t4_aes256_ctr_crypt(uint64_t *ks, uint64_t *asm_in, |
|
127 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
128 { return; } |
|
129 |
|
130 /*ARGSUSED*/ |
|
131 void t4_aes128_cfb128_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
132 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
133 { return; } |
|
134 |
|
135 /*ARGSUSED*/ |
|
136 void t4_aes192_cfb128_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
137 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
138 { return; } |
|
139 |
|
140 /*ARGSUSED*/ |
|
141 void t4_aes256_cfb128_encrypt(uint64_t *ks, uint64_t *asm_in, |
|
142 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
143 { return; } |
|
144 |
|
145 void t4_aes128_load_keys_for_decrypt(uint64_t *ks) |
|
146 { return; } |
|
147 |
|
148 /*ARGSUSED*/ |
|
149 void t4_aes192_load_keys_for_decrypt(uint64_t *ks) |
|
150 { return; } |
|
151 |
|
152 /*ARGSUSED*/ |
|
153 void t4_aes256_load_keys_for_decrypt(uint64_t *ks) |
|
154 { return; } |
|
155 |
|
156 /*ARGSUSED*/ |
|
157 void t4_aes128_ecb_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
158 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
159 { return; } |
|
160 |
|
161 /*ARGSUSED*/ |
|
162 void t4_aes192_ecb_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
163 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
164 { return; } |
|
165 |
|
166 /*ARGSUSED*/ |
|
167 void t4_aes256_ecb_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
168 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
169 { return; } |
|
170 |
|
171 /*ARGSUSED*/ |
|
172 void t4_aes128_cbc_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
173 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
174 { return; } |
|
175 |
|
176 /*ARGSUSED*/ |
|
177 void t4_aes192_cbc_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
178 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
179 { return; } |
|
180 |
|
181 /*ARGSUSED*/ |
|
182 void t4_aes256_cbc_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
183 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
184 { return; } |
|
185 |
|
186 /*ARGSUSED*/ |
|
187 void t4_aes128_cfb128_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
188 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
189 { return; } |
|
190 |
|
191 /*ARGSUSED*/ |
|
192 void t4_aes192_cfb128_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
193 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
194 { return; } |
|
195 |
|
196 /*ARGSUSED*/ |
|
197 void t4_aes256_cfb128_decrypt(uint64_t *ks, uint64_t *asm_in, |
|
198 uint64_t * asm_out, size_t amount_to_encrypt, uint64_t *iv) |
|
199 { return; } |
|
200 |
|
201 #else /* lint || __lint */ |
|
202 |
|
203 #include<sys/asm_linkage.h> |
|
204 |
|
205 |
|
206 ENTRY(t4_aes_expand128) |
|
207 |
|
208 !load key |
|
209 ld [%o1], %f0 |
|
210 ld [%o1 + 0x4], %f1 |
|
211 ld [%o1 + 0x8], %f2 |
|
212 ld [%o1 + 0xc], %f3 |
|
213 |
|
214 !expand the key |
|
215 !aes_kexpand1 %f0, %f2, 0x0, %f4 |
|
216 !aes_kexpand2 %f2, %f4, %f6 |
|
217 !aes_kexpand1 %f4, %f6, 0x1, %f8 |
|
218 !aes_kexpand2 %f6, %f8, %f10 |
|
219 !aes_kexpand1 %f8, %f10, 0x2, %f12 |
|
220 !aes_kexpand2 %f10, %f12, %f14 |
|
221 !aes_kexpand1 %f12, %f14, 0x3, %f16 |
|
222 !aes_kexpand2 %f14, %f16, %f18 |
|
223 !aes_kexpand1 %f16, %f18, 0x4, %f20 |
|
224 !aes_kexpand2 %f18, %f20, %f22 |
|
225 !aes_kexpand1 %f20, %f22, 0x5, %f24 |
|
226 !aes_kexpand2 %f22, %f24, %f26 |
|
227 !aes_kexpand1 %f24, %f26, 0x6, %f28 |
|
228 !aes_kexpand2 %f26, %f28, %f30 |
|
229 !aes_kexpand1 %f28, %f30, 0x7, %f32 |
|
230 !aes_kexpand2 %f30, %f32, %f34 |
|
231 !aes_kexpand1 %f32, %f34, 0x8, %f36 |
|
232 !aes_kexpand2 %f34, %f36, %f38 |
|
233 !aes_kexpand1 %f36, %f38, 0x9, %f40 |
|
234 !aes_kexpand2 %f38, %f40, %f42 |
|
235 .byte 0x88, 0xc8, 0x01, 0x02 |
|
236 .byte 0x8d, 0xb0, 0xa6, 0x24 |
|
237 .byte 0x90, 0xc9, 0x03, 0x06 |
|
238 .byte 0x95, 0xb1, 0xa6, 0x28 |
|
239 .byte 0x98, 0xca, 0x05, 0x0a |
|
240 .byte 0x9d, 0xb2, 0xa6, 0x2c |
|
241 .byte 0xa0, 0xcb, 0x07, 0x0e |
|
242 .byte 0xa5, 0xb3, 0xa6, 0x30 |
|
243 .byte 0xa8, 0xcc, 0x09, 0x12 |
|
244 .byte 0xad, 0xb4, 0xa6, 0x34 |
|
245 .byte 0xb0, 0xcd, 0x0b, 0x16 |
|
246 .byte 0xb5, 0xb5, 0xa6, 0x38 |
|
247 .byte 0xb8, 0xce, 0x0d, 0x1a |
|
248 .byte 0xbd, 0xb6, 0xa6, 0x3c |
|
249 .byte 0x82, 0xcf, 0x0f, 0x1e |
|
250 .byte 0x87, 0xb7, 0xa6, 0x21 |
|
251 .byte 0x8a, 0xc8, 0x51, 0x03 |
|
252 .byte 0x8f, 0xb0, 0xe6, 0x25 |
|
253 .byte 0x92, 0xc9, 0x53, 0x07 |
|
254 .byte 0x97, 0xb1, 0xe6, 0x29 |
|
255 |
|
256 !copy expanded key back into array |
|
257 std %f4, [%o0] |
|
258 std %f6, [%o0 + 0x8] |
|
259 std %f8, [%o0 + 0x10] |
|
260 std %f10, [%o0 + 0x18] |
|
261 std %f12, [%o0 + 0x20] |
|
262 std %f14, [%o0 + 0x28] |
|
263 std %f16, [%o0 + 0x30] |
|
264 std %f18, [%o0 + 0x38] |
|
265 std %f20, [%o0 + 0x40] |
|
266 std %f22, [%o0 + 0x48] |
|
267 std %f24, [%o0 + 0x50] |
|
268 std %f26, [%o0 + 0x58] |
|
269 std %f28, [%o0 + 0x60] |
|
270 std %f30, [%o0 + 0x68] |
|
271 std %f32, [%o0 + 0x70] |
|
272 std %f34, [%o0 + 0x78] |
|
273 std %f36, [%o0 + 0x80] |
|
274 std %f38, [%o0 + 0x88] |
|
275 std %f40, [%o0 + 0x90] |
|
276 retl |
|
277 std %f42, [%o0 + 0x98] |
|
278 |
|
279 SET_SIZE(t4_aes_expand128) |
|
280 |
|
281 |
|
282 ENTRY(t4_aes_expand192) |
|
283 |
|
284 !load key |
|
285 ld [%o1], %f0 |
|
286 ld [%o1 + 0x4], %f1 |
|
287 ld [%o1 + 0x8], %f2 |
|
288 ld [%o1 + 0xc], %f3 |
|
289 ld [%o1 + 0x10], %f4 |
|
290 ld [%o1 + 0x14], %f5 |
|
291 |
|
292 !expand the key |
|
293 !aes_kexpand1 %f0, %f4, 0x0, %f6 |
|
294 !aes_kexpand2 %f2, %f6, %f8 |
|
295 !aes_kexpand2 %f4, %f8, %f10 |
|
296 |
|
297 !aes_kexpand1 %f6, %f10, 0x1, %f12 |
|
298 !aes_kexpand2 %f8, %f12, %f14 |
|
299 !aes_kexpand2 %f10, %f14, %f16 |
|
300 |
|
301 !aes_kexpand1 %f12, %f16, 0x2, %f18 |
|
302 !aes_kexpand2 %f14, %f18, %f20 |
|
303 !aes_kexpand2 %f16, %f20, %f22 |
|
304 |
|
305 !aes_kexpand1 %f18, %f22, 0x3, %f24 |
|
306 !aes_kexpand2 %f20, %f24, %f26 |
|
307 !aes_kexpand2 %f22, %f26, %f28 |
|
308 |
|
309 !aes_kexpand1 %f24, %f28, 0x4, %f30 |
|
310 !aes_kexpand2 %f26, %f30, %f32 |
|
311 !aes_kexpand2 %f28, %f32, %f34 |
|
312 |
|
313 !aes_kexpand1 %f30, %f34, 0x5, %f36 |
|
314 !aes_kexpand2 %f32, %f36, %f38 |
|
315 !aes_kexpand2 %f34, %f38, %f40 |
|
316 |
|
317 !aes_kexpand1 %f36, %f40, 0x6, %f42 |
|
318 !aes_kexpand2 %f38, %f42, %f44 |
|
319 !aes_kexpand2 %f40, %f44, %f46 |
|
320 |
|
321 !aes_kexpand1 %f42, %f46, 0x7, %f48 |
|
322 !aes_kexpand2 %f44, %f48, %f50 |
|
323 .byte 0x8c, 0xc8, 0x01, 0x04 |
|
324 .byte 0x91, 0xb0, 0xa6, 0x26 |
|
325 .byte 0x95, 0xb1, 0x26, 0x28 |
|
326 .byte 0x98, 0xc9, 0x83, 0x0a |
|
327 .byte 0x9d, 0xb2, 0x26, 0x2c |
|
328 .byte 0xa1, 0xb2, 0xa6, 0x2e |
|
329 .byte 0xa4, 0xcb, 0x05, 0x10 |
|
330 .byte 0xa9, 0xb3, 0xa6, 0x32 |
|
331 .byte 0xad, 0xb4, 0x26, 0x34 |
|
332 .byte 0xb0, 0xcc, 0x87, 0x16 |
|
333 .byte 0xb5, 0xb5, 0x26, 0x38 |
|
334 .byte 0xb9, 0xb5, 0xa6, 0x3a |
|
335 .byte 0xbc, 0xce, 0x09, 0x1c |
|
336 .byte 0x83, 0xb6, 0xa6, 0x3e |
|
337 .byte 0x87, 0xb7, 0x26, 0x21 |
|
338 .byte 0x8a, 0xcf, 0x8b, 0x03 |
|
339 .byte 0x8f, 0xb0, 0x66, 0x25 |
|
340 .byte 0x93, 0xb0, 0xe6, 0x27 |
|
341 .byte 0x96, 0xc9, 0x4d, 0x09 |
|
342 .byte 0x9b, 0xb1, 0xe6, 0x2b |
|
343 .byte 0x9f, 0xb2, 0x66, 0x2d |
|
344 .byte 0xa2, 0xca, 0xcf, 0x0f |
|
345 .byte 0xa7, 0xb3, 0x66, 0x31 |
|
346 |
|
347 !copy expanded key back into array |
|
348 std %f6, [%o0] |
|
349 std %f8, [%o0 + 0x8] |
|
350 std %f10, [%o0 + 0x10] |
|
351 std %f12, [%o0 + 0x18] |
|
352 std %f14, [%o0 + 0x20] |
|
353 std %f16, [%o0 + 0x28] |
|
354 std %f18, [%o0 + 0x30] |
|
355 std %f20, [%o0 + 0x38] |
|
356 std %f22, [%o0 + 0x40] |
|
357 std %f24, [%o0 + 0x48] |
|
358 std %f26, [%o0 + 0x50] |
|
359 std %f28, [%o0 + 0x58] |
|
360 std %f30, [%o0 + 0x60] |
|
361 std %f32, [%o0 + 0x68] |
|
362 std %f34, [%o0 + 0x70] |
|
363 std %f36, [%o0 + 0x78] |
|
364 std %f38, [%o0 + 0x80] |
|
365 std %f40, [%o0 + 0x88] |
|
366 std %f42, [%o0 + 0x90] |
|
367 std %f44, [%o0 + 0x98] |
|
368 std %f46, [%o0 + 0xa0] |
|
369 std %f48, [%o0 + 0xa8] |
|
370 retl |
|
371 std %f50, [%o0 + 0xb0] |
|
372 |
|
373 SET_SIZE(t4_aes_expand192) |
|
374 |
|
375 |
|
376 ENTRY(t4_aes_expand256) |
|
377 |
|
378 !load key |
|
379 ld [%o1], %f0 |
|
380 ld [%o1 + 0x4], %f1 |
|
381 ld [%o1 + 0x8], %f2 |
|
382 ld [%o1 + 0xc], %f3 |
|
383 ld [%o1 + 0x10], %f4 |
|
384 ld [%o1 + 0x14], %f5 |
|
385 ld [%o1 + 0x18], %f6 |
|
386 ld [%o1 + 0x1c], %f7 |
|
387 |
|
388 !expand the key |
|
389 !aes_kexpand1 %f0, %f6, 0x0, %f8 |
|
390 !aes_kexpand2 %f2, %f8, %f10 |
|
391 !aes_kexpand0 %f4, %f10, %f12 |
|
392 !aes_kexpand2 %f6, %f12, %f14 |
|
393 |
|
394 !aes_kexpand1 %f8, %f14, 0x1, %f16 |
|
395 !aes_kexpand2 %f10, %f16, %f18 |
|
396 !aes_kexpand0 %f12, %f18, %f20 |
|
397 !aes_kexpand2 %f14, %f20, %f22 |
|
398 |
|
399 !aes_kexpand1 %f16, %f22, 0x2, %f24 |
|
400 !aes_kexpand2 %f18, %f24, %f26 |
|
401 !aes_kexpand0 %f20, %f26, %f28 |
|
402 !aes_kexpand2 %f22, %f28, %f30 |
|
403 |
|
404 !aes_kexpand1 %f24, %f30, 0x3, %f32 |
|
405 !aes_kexpand2 %f26, %f32, %f34 |
|
406 !aes_kexpand0 %f28, %f34, %f36 |
|
407 !aes_kexpand2 %f30, %f36, %f38 |
|
408 |
|
409 !aes_kexpand1 %f32, %f38, 0x4, %f40 |
|
410 !aes_kexpand2 %f34, %f40, %f42 |
|
411 !aes_kexpand0 %f36, %f42, %f44 |
|
412 !aes_kexpand2 %f38, %f44, %f46 |
|
413 |
|
414 !aes_kexpand1 %f40, %f46, 0x5, %f48 |
|
415 !aes_kexpand2 %f42, %f48, %f50 |
|
416 !aes_kexpand0 %f44, %f50, %f52 |
|
417 !aes_kexpand2 %f46, %f52, %f54 |
|
418 |
|
419 !aes_kexpand1 %f48, %f54, 0x6, %f56 |
|
420 !aes_kexpand2 %f50, %f56, %f58 |
|
421 .byte 0x90, 0xc8, 0x01, 0x06 |
|
422 .byte 0x95, 0xb0, 0xa6, 0x28 |
|
423 .byte 0x99, 0xb1, 0x26, 0x0a |
|
424 .byte 0x9d, 0xb1, 0xa6, 0x2c |
|
425 .byte 0xa0, 0xca, 0x03, 0x0e |
|
426 .byte 0xa5, 0xb2, 0xa6, 0x30 |
|
427 .byte 0xa9, 0xb3, 0x26, 0x12 |
|
428 .byte 0xad, 0xb3, 0xa6, 0x34 |
|
429 .byte 0xb0, 0xcc, 0x05, 0x16 |
|
430 .byte 0xb5, 0xb4, 0xa6, 0x38 |
|
431 .byte 0xb9, 0xb5, 0x26, 0x1a |
|
432 .byte 0xbd, 0xb5, 0xa6, 0x3c |
|
433 .byte 0x82, 0xce, 0x07, 0x1e |
|
434 .byte 0x87, 0xb6, 0xa6, 0x21 |
|
435 .byte 0x8b, 0xb7, 0x26, 0x03 |
|
436 .byte 0x8f, 0xb7, 0xa6, 0x25 |
|
437 .byte 0x92, 0xc8, 0x49, 0x07 |
|
438 .byte 0x97, 0xb0, 0xe6, 0x29 |
|
439 .byte 0x9b, 0xb1, 0x66, 0x0b |
|
440 .byte 0x9f, 0xb1, 0xe6, 0x2d |
|
441 .byte 0xa2, 0xca, 0x4b, 0x0f |
|
442 .byte 0xa7, 0xb2, 0xe6, 0x31 |
|
443 .byte 0xab, 0xb3, 0x66, 0x13 |
|
444 .byte 0xaf, 0xb3, 0xe6, 0x35 |
|
445 .byte 0xb2, 0xcc, 0x4d, 0x17 |
|
446 .byte 0xb7, 0xb4, 0xe6, 0x39 |
|
447 |
|
448 !copy expanded key back into array |
|
449 std %f8, [%o0] |
|
450 std %f10, [%o0 + 0x8] |
|
451 std %f12, [%o0 + 0x10] |
|
452 std %f14, [%o0 + 0x18] |
|
453 std %f16, [%o0 + 0x20] |
|
454 std %f18, [%o0 + 0x28] |
|
455 std %f20, [%o0 + 0x30] |
|
456 std %f22, [%o0 + 0x38] |
|
457 std %f24, [%o0 + 0x40] |
|
458 std %f26, [%o0 + 0x48] |
|
459 std %f28, [%o0 + 0x50] |
|
460 std %f30, [%o0 + 0x58] |
|
461 std %f32, [%o0 + 0x60] |
|
462 std %f34, [%o0 + 0x68] |
|
463 std %f36, [%o0 + 0x70] |
|
464 std %f38, [%o0 + 0x78] |
|
465 std %f40, [%o0 + 0x80] |
|
466 std %f42, [%o0 + 0x88] |
|
467 std %f44, [%o0 + 0x90] |
|
468 std %f46, [%o0 + 0x98] |
|
469 std %f48, [%o0 + 0xa0] |
|
470 std %f50, [%o0 + 0xa8] |
|
471 std %f52, [%o0 + 0xb0] |
|
472 std %f54, [%o0 + 0xb8] |
|
473 std %f56, [%o0 + 0xc0] |
|
474 retl |
|
475 std %f58, [%o0 + 0xc8] |
|
476 |
|
477 SET_SIZE(t4_aes_expand256) |
|
478 |
|
479 |
|
480 #define FIRST_TWO_EROUNDS \ |
|
481 .byte 0xb2, 0xc8, 0x3e, 0x1d ; \ |
|
482 .byte 0xb6, 0xc8, 0xbe, 0x3d ; \ |
|
483 .byte 0xba, 0xc9, 0x36, 0x19 ; \ |
|
484 .byte 0xbe, 0xc9, 0xb6, 0x39 |
|
485 !aes_eround01 %f0, %f60, %f62, %f56 ; \ |
|
486 !aes_eround23 %f2, %f60, %f62, %f58 ; \ |
|
487 !aes_eround01 %f4, %f56, %f58, %f60 ; \ |
|
488 !aes_eround23 %f6, %f56, %f58, %f62 |
|
489 |
|
490 #define MID_TWO_EROUNDS \ |
|
491 .byte 0xb2, 0xca, 0x3e, 0x1d ; \ |
|
492 .byte 0xb6, 0xca, 0xbe, 0x3d ; \ |
|
493 .byte 0xba, 0xcb, 0x36, 0x19 ; \ |
|
494 .byte 0xbe, 0xcb, 0xb6, 0x39 |
|
495 !aes_eround01 %f8, %f60, %f62, %f56 ; \ |
|
496 !aes_eround23 %f10, %f60, %f62, %f58 ; \ |
|
497 !aes_eround01 %f12, %f56, %f58, %f60 ; \ |
|
498 !aes_eround23 %f14, %f56, %f58, %f62 |
|
499 |
|
500 #define MID_TWO_EROUNDS_2 \ |
|
501 .byte 0x8c, 0xca, 0x04, 0x00 ; \ |
|
502 .byte 0x88, 0xca, 0x84, 0x20 ; \ |
|
503 .byte 0xb2, 0xca, 0x3e, 0x1d ; \ |
|
504 .byte 0xb6, 0xca, 0xbe, 0x3d ; \ |
|
505 .byte 0x80, 0xcb, 0x08, 0x06 ; \ |
|
506 .byte 0x84, 0xcb, 0x88, 0x26 ; \ |
|
507 .byte 0xba, 0xcb, 0x36, 0x19 ; \ |
|
508 .byte 0xbe, 0xcb, 0xb6, 0x39 |
|
509 !aes_eround01 %f8, %f0, %f2, %f6 ; \ |
|
510 !aes_eround23 %f10, %f0, %f2, %f4 ; \ |
|
511 !aes_eround01 %f8, %f60, %f62, %f56 ; \ |
|
512 !aes_eround23 %f10, %f60, %f62, %f58 ; \ |
|
513 !aes_eround01 %f12, %f6, %f4, %f0 ; \ |
|
514 !aes_eround23 %f14, %f6, %f4, %f2 ; \ |
|
515 !aes_eround01 %f12, %f56, %f58, %f60 ; \ |
|
516 !aes_eround23 %f14, %f56, %f58, %f62 |
|
517 |
|
518 #define TEN_EROUNDS \ |
|
519 .byte 0xb2, 0xcc, 0x3e, 0x1d ; \ |
|
520 .byte 0xb6, 0xcc, 0xbe, 0x3d ; \ |
|
521 .byte 0xba, 0xcd, 0x36, 0x19 ; \ |
|
522 .byte 0xbe, 0xcd, 0xb6, 0x39 ; \ |
|
523 .byte 0xb2, 0xce, 0x3e, 0x1d ; \ |
|
524 .byte 0xb6, 0xce, 0xbe, 0x3d ; \ |
|
525 .byte 0xba, 0xcf, 0x36, 0x19 ; \ |
|
526 .byte 0xbe, 0xcf, 0xb6, 0x39 ; \ |
|
527 .byte 0xb2, 0xc8, 0x7e, 0x1d ; \ |
|
528 .byte 0xb6, 0xc8, 0xfe, 0x3d ; \ |
|
529 .byte 0xba, 0xc9, 0x76, 0x19 ; \ |
|
530 .byte 0xbe, 0xc9, 0xf6, 0x39 ; \ |
|
531 .byte 0xb2, 0xca, 0x7e, 0x1d ; \ |
|
532 .byte 0xb6, 0xca, 0xfe, 0x3d ; \ |
|
533 .byte 0xba, 0xcb, 0x76, 0x19 ; \ |
|
534 .byte 0xbe, 0xcb, 0xf6, 0x39 ; \ |
|
535 .byte 0xb2, 0xcc, 0x7e, 0x1d ; \ |
|
536 .byte 0xb6, 0xcc, 0xfe, 0x3d ; \ |
|
537 .byte 0xba, 0xcd, 0x76, 0x99 ; \ |
|
538 .byte 0xbe, 0xcd, 0xf6, 0xb9 |
|
539 !aes_eround01 %f16, %f60, %f62, %f56 ; \ |
|
540 !aes_eround23 %f18, %f60, %f62, %f58 ; \ |
|
541 !aes_eround01 %f20, %f56, %f58, %f60 ; \ |
|
542 !aes_eround23 %f22, %f56, %f58, %f62 ; \ |
|
543 !aes_eround01 %f24, %f60, %f62, %f56 ; \ |
|
544 !aes_eround23 %f26, %f60, %f62, %f58 ; \ |
|
545 !aes_eround01 %f28, %f56, %f58, %f60 ; \ |
|
546 !aes_eround23 %f30, %f56, %f58, %f62 ; \ |
|
547 !aes_eround01 %f32, %f60, %f62, %f56 ; \ |
|
548 !aes_eround23 %f34, %f60, %f62, %f58 ; \ |
|
549 !aes_eround01 %f36, %f56, %f58, %f60 ; \ |
|
550 !aes_eround23 %f38, %f56, %f58, %f62 ; \ |
|
551 !aes_eround01 %f40, %f60, %f62, %f56 ; \ |
|
552 !aes_eround23 %f42, %f60, %f62, %f58 ; \ |
|
553 !aes_eround01 %f44, %f56, %f58, %f60 ; \ |
|
554 !aes_eround23 %f46, %f56, %f58, %f62 ; \ |
|
555 !aes_eround01 %f48, %f60, %f62, %f56 ; \ |
|
556 !aes_eround23 %f50, %f60, %f62, %f58 ; \ |
|
557 !aes_eround01_l %f52, %f56, %f58, %f60 ; \ |
|
558 !aes_eround23_l %f54, %f56, %f58, %f62 |
|
559 |
|
560 #define TEN_EROUNDS_2 \ |
|
561 .byte 0x8c, 0xcc, 0x04, 0x00 ; \ |
|
562 .byte 0x88, 0xcc, 0x84, 0x20 ; \ |
|
563 .byte 0xb2, 0xcc, 0x3e, 0x1d ; \ |
|
564 .byte 0xb6, 0xcc, 0xbe, 0x3d ; \ |
|
565 .byte 0x80, 0xcd, 0x08, 0x06 ; \ |
|
566 .byte 0x84, 0xcd, 0x88, 0x26 ; \ |
|
567 .byte 0xba, 0xcd, 0x36, 0x19 ; \ |
|
568 .byte 0xbe, 0xcd, 0xb6, 0x39 ; \ |
|
569 .byte 0x8c, 0xce, 0x04, 0x00 ; \ |
|
570 .byte 0x88, 0xce, 0x84, 0x20 ; \ |
|
571 .byte 0xb2, 0xce, 0x3e, 0x1d ; \ |
|
572 .byte 0xb6, 0xce, 0xbe, 0x3d ; \ |
|
573 .byte 0x80, 0xcf, 0x08, 0x06 ; \ |
|
574 .byte 0x84, 0xcf, 0x88, 0x26 ; \ |
|
575 .byte 0xba, 0xcf, 0x36, 0x19 ; \ |
|
576 .byte 0xbe, 0xcf, 0xb6, 0x39 ; \ |
|
577 .byte 0x8c, 0xc8, 0x44, 0x00 ; \ |
|
578 .byte 0x88, 0xc8, 0xc4, 0x20 ; \ |
|
579 .byte 0xb2, 0xc8, 0x7e, 0x1d ; \ |
|
580 .byte 0xb6, 0xc8, 0xfe, 0x3d ; \ |
|
581 .byte 0x80, 0xc9, 0x48, 0x06 ; \ |
|
582 .byte 0x84, 0xc9, 0xc8, 0x26 ; \ |
|
583 .byte 0xba, 0xc9, 0x76, 0x19 ; \ |
|
584 .byte 0xbe, 0xc9, 0xf6, 0x39 ; \ |
|
585 .byte 0x8c, 0xca, 0x44, 0x00 ; \ |
|
586 .byte 0x88, 0xca, 0xc4, 0x20 ; \ |
|
587 .byte 0xb2, 0xca, 0x7e, 0x1d ; \ |
|
588 .byte 0xb6, 0xca, 0xfe, 0x3d ; \ |
|
589 .byte 0x80, 0xcb, 0x48, 0x06 ; \ |
|
590 .byte 0x84, 0xcb, 0xc8, 0x26 ; \ |
|
591 .byte 0xba, 0xcb, 0x76, 0x19 ; \ |
|
592 .byte 0xbe, 0xcb, 0xf6, 0x39 ; \ |
|
593 .byte 0x8c, 0xcc, 0x44, 0x00 ; \ |
|
594 .byte 0x88, 0xcc, 0xc4, 0x20 ; \ |
|
595 .byte 0xb2, 0xcc, 0x7e, 0x1d ; \ |
|
596 .byte 0xb6, 0xcc, 0xfe, 0x3d ; \ |
|
597 .byte 0x80, 0xcd, 0x48, 0x86 ; \ |
|
598 .byte 0x84, 0xcd, 0xc8, 0xa6 ; \ |
|
599 .byte 0xba, 0xcd, 0x76, 0x99 ; \ |
|
600 .byte 0xbe, 0xcd, 0xf6, 0xb9 |
|
601 !aes_eround01 %f16, %f0, %f2, %f6 ; \ |
|
602 !aes_eround23 %f18, %f0, %f2, %f4 ; \ |
|
603 !aes_eround01 %f16, %f60, %f62, %f56 ; \ |
|
604 !aes_eround23 %f18, %f60, %f62, %f58 ; \ |
|
605 !aes_eround01 %f20, %f6, %f4, %f0 ; \ |
|
606 !aes_eround23 %f22, %f6, %f4, %f2 ; \ |
|
607 !aes_eround01 %f20, %f56, %f58, %f60 ; \ |
|
608 !aes_eround23 %f22, %f56, %f58, %f62 ; \ |
|
609 !aes_eround01 %f24, %f0, %f2, %f6 ; \ |
|
610 !aes_eround23 %f26, %f0, %f2, %f4 ; \ |
|
611 !aes_eround01 %f24, %f60, %f62, %f56 ; \ |
|
612 !aes_eround23 %f26, %f60, %f62, %f58 ; \ |
|
613 !aes_eround01 %f28, %f6, %f4, %f0 ; \ |
|
614 !aes_eround23 %f30, %f6, %f4, %f2 ; \ |
|
615 !aes_eround01 %f28, %f56, %f58, %f60 ; \ |
|
616 !aes_eround23 %f30, %f56, %f58, %f62 ; \ |
|
617 !aes_eround01 %f32, %f0, %f2, %f6 ; \ |
|
618 !aes_eround23 %f34, %f0, %f2, %f4 ; \ |
|
619 !aes_eround01 %f32, %f60, %f62, %f56 ; \ |
|
620 !aes_eround23 %f34, %f60, %f62, %f58 ; \ |
|
621 !aes_eround01 %f36, %f6, %f4, %f0 ; \ |
|
622 !aes_eround23 %f38, %f6, %f4, %f2 ; \ |
|
623 !aes_eround01 %f36, %f56, %f58, %f60 ; \ |
|
624 !aes_eround23 %f38, %f56, %f58, %f62 ; \ |
|
625 !aes_eround01 %f40, %f0, %f2, %f6 ; \ |
|
626 !aes_eround23 %f42, %f0, %f2, %f4 ; \ |
|
627 !aes_eround01 %f40, %f60, %f62, %f56 ; \ |
|
628 !aes_eround23 %f42, %f60, %f62, %f58 ; \ |
|
629 !aes_eround01 %f44, %f6, %f4, %f0 ; \ |
|
630 !aes_eround23 %f46, %f6, %f4, %f2 ; \ |
|
631 !aes_eround01 %f44, %f56, %f58, %f60 ; \ |
|
632 !aes_eround23 %f46, %f56, %f58, %f62 ; \ |
|
633 !aes_eround01 %f48, %f0, %f2, %f6 ; \ |
|
634 !aes_eround23 %f50, %f0, %f2, %f4 ; \ |
|
635 !aes_eround01 %f48, %f60, %f62, %f56 ; \ |
|
636 !aes_eround23 %f50, %f60, %f62, %f58 ; \ |
|
637 !aes_eround01_l %f52, %f6, %f4, %f0 ; \ |
|
638 !aes_eround23_l %f54, %f6, %f4, %f2 ; \ |
|
639 !aes_eround01_l %f52, %f56, %f58, %f60 ; \ |
|
640 !aes_eround23_l %f54, %f56, %f58, %f62 |
|
641 |
|
642 #define TWELVE_EROUNDS \ |
|
643 MID_TWO_EROUNDS ; \ |
|
644 TEN_EROUNDS |
|
645 |
|
646 #define TWELVE_EROUNDS_2 \ |
|
647 MID_TWO_EROUNDS_2 ; \ |
|
648 TEN_EROUNDS_2 |
|
649 |
|
650 #define FOURTEEN_EROUNDS \ |
|
651 FIRST_TWO_EROUNDS ; \ |
|
652 TWELVE_EROUNDS |
|
653 |
|
654 #define FOURTEEN_EROUNDS_2 \ |
|
655 .byte 0xb0, 0xc8, 0x2c, 0x14 ; \ |
|
656 .byte 0xac, 0xc8, 0xac, 0x34 ; \ |
|
657 ldd [%o0 + 0x60], %f20 ; \ |
|
658 .byte 0xb2, 0xc8, 0x3e, 0x1d ; \ |
|
659 .byte 0xb6, 0xc8, 0xbe, 0x3d ; \ |
|
660 .byte 0x80, 0xc9, 0x2c, 0x18 ; \ |
|
661 .byte 0x84, 0xc9, 0xac, 0x38 ;\ |
|
662 ldd [%o0 + 0x68], %f22 ; \ |
|
663 .byte 0xba, 0xc9, 0x36, 0x19 ; \ |
|
664 ldd [%o0 + 0x70], %f24 ; \ |
|
665 .byte 0xbe, 0xc9, 0xb6, 0x39 ; \ |
|
666 .byte 0x8c, 0xca, 0x04, 0x00 ; \ |
|
667 .byte 0x88, 0xca, 0x84, 0x20 ; \ |
|
668 .byte 0xb2, 0xca, 0x3e, 0x1d ; \ |
|
669 .byte 0xb6, 0xca, 0xbe, 0x3d ; \ |
|
670 .byte 0x80, 0xcb, 0x08, 0x06 ; \ |
|
671 .byte 0x84, 0xcb, 0x88, 0x26 ; \ |
|
672 .byte 0xba, 0xcb, 0x36, 0x19 ; \ |
|
673 .byte 0xbe, 0xcb, 0xb6, 0x39 ; \ |
|
674 .byte 0x8c, 0xcc, 0x04, 0x00 ; \ |
|
675 .byte 0x88, 0xcc, 0x84, 0x20 ; \ |
|
676 .byte 0xb2, 0xcc, 0x3e, 0x1d ; \ |
|
677 .byte 0xb6, 0xcc, 0xbe, 0x3d ; \ |
|
678 .byte 0x80, 0xcd, 0x08, 0x06 ; \ |
|
679 .byte 0x84, 0xcd, 0x88, 0x26 ; \ |
|
680 .byte 0xba, 0xcd, 0x36, 0x19 ; \ |
|
681 .byte 0xbe, 0xcd, 0xb6, 0x39 ; \ |
|
682 .byte 0x8c, 0xce, 0x04, 0x00 ; \ |
|
683 .byte 0x88, 0xce, 0x84, 0x20 ; \ |
|
684 .byte 0xb2, 0xce, 0x3e, 0x1d ; \ |
|
685 .byte 0xb6, 0xce, 0xbe, 0x3d ; \ |
|
686 .byte 0x80, 0xcf, 0x08, 0x06 ; \ |
|
687 .byte 0x84, 0xcf, 0x88, 0x26 ; \ |
|
688 .byte 0xba, 0xcf, 0x36, 0x19 ; \ |
|
689 .byte 0xbe, 0xcf, 0xb6, 0x39 ; \ |
|
690 .byte 0x8c, 0xc8, 0x44, 0x00 ; \ |
|
691 .byte 0x88, 0xc8, 0xc4, 0x20 ; \ |
|
692 .byte 0xb2, 0xc8, 0x7e, 0x1d ; \ |
|
693 .byte 0xb6, 0xc8, 0xfe, 0x3d ; \ |
|
694 .byte 0x80, 0xc9, 0x48, 0x06 ; \ |
|
695 .byte 0x84, 0xc9, 0xc8, 0x26 ; \ |
|
696 .byte 0xba, 0xc9, 0x76, 0x19 ; \ |
|
697 .byte 0xbe, 0xc9, 0xf6, 0x39 ; \ |
|
698 .byte 0x8c, 0xca, 0x44, 0x00 ; \ |
|
699 .byte 0x88, 0xca, 0xc4, 0x20 ; \ |
|
700 .byte 0xb2, 0xca, 0x7e, 0x1d ; \ |
|
701 .byte 0xb6, 0xca, 0xfe, 0x3d ; \ |
|
702 .byte 0x80, 0xcb, 0x48, 0x06 ; \ |
|
703 .byte 0x84, 0xcb, 0xc8, 0x26 ; \ |
|
704 .byte 0xba, 0xcb, 0x76, 0x19 ; \ |
|
705 .byte 0xbe, 0xcb, 0xf6, 0x39 ; \ |
|
706 .byte 0x8c, 0xcc, 0x44, 0x00 ; \ |
|
707 .byte 0x88, 0xcc, 0xc4, 0x20 ; \ |
|
708 ldd [%o0 + 0x10], %f0 ; \ |
|
709 .byte 0xb2, 0xcc, 0x7e, 0x1d ; \ |
|
710 ldd [%o0 + 0x18], %f2 ; \ |
|
711 .byte 0xb6, 0xcc, 0xfe, 0x3d ; \ |
|
712 .byte 0xa8, 0xcd, 0x48, 0x86 ; \ |
|
713 .byte 0xac, 0xcd, 0xc8, 0xa6 ; \ |
|
714 ldd [%o0 + 0x20], %f4 ; \ |
|
715 .byte 0xba, 0xcd, 0x76, 0x99 ; \ |
|
716 ldd [%o0 + 0x28], %f6 ; \ |
|
717 .byte 0xbe, 0xcd, 0xf6, 0xb9 |
|
718 !aes_eround01 %f0, %f20, %f22, %f24 ; \ |
|
719 !aes_eround23 %f2, %f20, %f22, %f22 ; \ |
|
720 !ldd [%o0 + 0x60], %f20 ; \ |
|
721 !aes_eround01 %f0, %f60, %f62, %f56 ; \ |
|
722 !aes_eround23 %f2, %f60, %f62, %f58 ; \ |
|
723 !aes_eround01 %f4, %f24, %f22, %f0 ; \ |
|
724 !aes_eround23 %f6, %f24, %f22, %f2 ; \ |
|
725 !ldd [%o0 + 0x68], %f22 ; \ |
|
726 !aes_eround01 %f4, %f56, %f58, %f60 ; \ |
|
727 !ldd [%o0 + 0x70], %f24 ; \ |
|
728 !aes_eround23 %f6, %f56, %f58, %f62 ; \ |
|
729 !aes_eround01 %f8, %f0, %f2, %f6 ; \ |
|
730 !aes_eround23 %f10, %f0, %f2, %f4 ; \ |
|
731 !aes_eround01 %f8, %f60, %f62, %f56 ; \ |
|
732 !aes_eround23 %f10, %f60, %f62, %f58 ; \ |
|
733 !aes_eround01 %f12, %f6, %f4, %f0 ; \ |
|
734 !aes_eround23 %f14, %f6, %f4, %f2 ; \ |
|
735 !aes_eround01 %f12, %f56, %f58, %f60 ; \ |
|
736 !aes_eround23 %f14, %f56, %f58, %f62 ; \ |
|
737 !aes_eround01 %f16, %f0, %f2, %f6 ; \ |
|
738 !aes_eround23 %f18, %f0, %f2, %f4 ; \ |
|
739 !aes_eround01 %f16, %f60, %f62, %f56 ; \ |
|
740 !aes_eround23 %f18, %f60, %f62, %f58 ; \ |
|
741 !aes_eround01 %f20, %f6, %f4, %f0 ; \ |
|
742 !aes_eround23 %f22, %f6, %f4, %f2 ; \ |
|
743 !aes_eround01 %f20, %f56, %f58, %f60 ; \ |
|
744 !aes_eround23 %f22, %f56, %f58, %f62 ; \ |
|
745 !aes_eround01 %f24, %f0, %f2, %f6 ; \ |
|
746 !aes_eround23 %f26, %f0, %f2, %f4 ; \ |
|
747 !aes_eround01 %f24, %f60, %f62, %f56 ; \ |
|
748 !aes_eround23 %f26, %f60, %f62, %f58 ; \ |
|
749 !aes_eround01 %f28, %f6, %f4, %f0 ; \ |
|
750 !aes_eround23 %f30, %f6, %f4, %f2 ; \ |
|
751 !aes_eround01 %f28, %f56, %f58, %f60 ; \ |
|
752 !aes_eround23 %f30, %f56, %f58, %f62 ; \ |
|
753 !aes_eround01 %f32, %f0, %f2, %f6 ; \ |
|
754 !aes_eround23 %f34, %f0, %f2, %f4 ; \ |
|
755 !aes_eround01 %f32, %f60, %f62, %f56 ; \ |
|
756 !aes_eround23 %f34, %f60, %f62, %f58 ; \ |
|
757 !aes_eround01 %f36, %f6, %f4, %f0 ; \ |
|
758 !aes_eround23 %f38, %f6, %f4, %f2 ; \ |
|
759 !aes_eround01 %f36, %f56, %f58, %f60 ; \ |
|
760 !aes_eround23 %f38, %f56, %f58, %f62 ; \ |
|
761 !aes_eround01 %f40, %f0, %f2, %f6 ; \ |
|
762 !aes_eround23 %f42, %f0, %f2, %f4 ; \ |
|
763 !aes_eround01 %f40, %f60, %f62, %f56 ; \ |
|
764 !aes_eround23 %f42, %f60, %f62, %f58 ; \ |
|
765 !aes_eround01 %f44, %f6, %f4, %f0 ; \ |
|
766 !aes_eround23 %f46, %f6, %f4, %f2 ; \ |
|
767 !aes_eround01 %f44, %f56, %f58, %f60 ; \ |
|
768 !aes_eround23 %f46, %f56, %f58, %f62 ; \ |
|
769 !aes_eround01 %f48, %f0, %f2, %f6 ; \ |
|
770 !aes_eround23 %f50, %f0, %f2, %f4 ; \ |
|
771 !ldd [%o0 + 0x10], %f0 ; \ |
|
772 !aes_eround01 %f48, %f60, %f62, %f56 ; \ |
|
773 !ldd [%o0 + 0x18], %f2 ; \ |
|
774 !aes_eround23 %f50, %f60, %f62, %f58 ; \ |
|
775 !aes_eround01_l %f52, %f6, %f4, %f20 ; \ |
|
776 !aes_eround23_l %f54, %f6, %f4, %f22 ; \ |
|
777 !ldd [%o0 + 0x20], %f4 ; \ |
|
778 !aes_eround01_l %f52, %f56, %f58, %f60 ; \ |
|
779 !ldd [%o0 + 0x28], %f6 ; \ |
|
780 !aes_eround23_l %f54, %f56, %f58, %f62 |
|
781 |
|
782 #define FIRST_TWO_DROUNDS \ |
|
783 .byte 0xb2, 0xc8, 0x3e, 0x5d ; \ |
|
784 .byte 0xb6, 0xc8, 0xbe, 0x7d ; \ |
|
785 .byte 0xba, 0xc9, 0x36, 0x59 ; \ |
|
786 .byte 0xbe, 0xc9, 0xb6, 0x79 |
|
787 !aes_dround01 %f0, %f60, %f62, %f56 ; \ |
|
788 !aes_dround23 %f2, %f60, %f62, %f58 ; \ |
|
789 !aes_dround01 %f4, %f56, %f58, %f60 ; \ |
|
790 !aes_dround23 %f6, %f56, %f58, %f62 |
|
791 |
|
792 #define MID_TWO_DROUNDS \ |
|
793 .byte 0xb2, 0xca, 0x3e, 0x5d ; \ |
|
794 .byte 0xb6, 0xca, 0xbe, 0x7d ; \ |
|
795 .byte 0xba, 0xcb, 0x36, 0x59 ; \ |
|
796 .byte 0xbe, 0xcb, 0xb6, 0x79 |
|
797 !aes_dround01 %f8, %f60, %f62, %f56 ; \ |
|
798 !aes_dround23 %f10, %f60, %f62, %f58 ; \ |
|
799 !aes_dround01 %f12, %f56, %f58, %f60 ; \ |
|
800 !aes_dround23 %f14, %f56, %f58, %f62 |
|
801 |
|
802 #define MID_TWO_DROUNDS_2 \ |
|
803 .byte 0x8c, 0xca, 0x04, 0x40 ; \ |
|
804 .byte 0x88, 0xca, 0x84, 0x60 ; \ |
|
805 .byte 0xb2, 0xca, 0x3e, 0x5d ; \ |
|
806 .byte 0xb6, 0xca, 0xbe, 0x7d ; \ |
|
807 .byte 0x80, 0xcb, 0x08, 0x46 ; \ |
|
808 .byte 0x84, 0xcb, 0x88, 0x66 ; \ |
|
809 .byte 0xba, 0xcb, 0x36, 0x59 ; \ |
|
810 .byte 0xbe, 0xcb, 0xb6, 0x79 |
|
811 !aes_dround01 %f8, %f0, %f2, %f6 ; \ |
|
812 !aes_dround23 %f10, %f0, %f2, %f4 ; \ |
|
813 !aes_dround01 %f8, %f60, %f62, %f56 ; \ |
|
814 !aes_dround23 %f10, %f60, %f62, %f58 ; \ |
|
815 !aes_dround01 %f12, %f6, %f4, %f0 ; \ |
|
816 !aes_dround23 %f14, %f6, %f4, %f2 ; \ |
|
817 !aes_dround01 %f12, %f56, %f58, %f60 ; \ |
|
818 !aes_dround23 %f14, %f56, %f58, %f62 |
|
819 |
|
820 #define TEN_DROUNDS \ |
|
821 .byte 0xb2, 0xcc, 0x3e, 0x5d ; \ |
|
822 .byte 0xb6, 0xcc, 0xbe, 0x7d ; \ |
|
823 .byte 0xba, 0xcd, 0x36, 0x59 ; \ |
|
824 .byte 0xbe, 0xcd, 0xb6, 0x79 ; \ |
|
825 .byte 0xb2, 0xce, 0x3e, 0x5d ; \ |
|
826 .byte 0xb6, 0xce, 0xbe, 0x7d ; \ |
|
827 .byte 0xba, 0xcf, 0x36, 0x59 ; \ |
|
828 .byte 0xbe, 0xcf, 0xb6, 0x79 ; \ |
|
829 .byte 0xb2, 0xc8, 0x7e, 0x5d ; \ |
|
830 .byte 0xb6, 0xc8, 0xfe, 0x7d ; \ |
|
831 .byte 0xba, 0xc9, 0x76, 0x59 ; \ |
|
832 .byte 0xbe, 0xc9, 0xf6, 0x79 ; \ |
|
833 .byte 0xb2, 0xca, 0x7e, 0x5d ; \ |
|
834 .byte 0xb6, 0xca, 0xfe, 0x7d ; \ |
|
835 .byte 0xba, 0xcb, 0x76, 0x59 ; \ |
|
836 .byte 0xbe, 0xcb, 0xf6, 0x79 ; \ |
|
837 .byte 0xb2, 0xcc, 0x7e, 0x5d ; \ |
|
838 .byte 0xb6, 0xcc, 0xfe, 0x7d ; \ |
|
839 .byte 0xba, 0xcd, 0x76, 0xd9 ; \ |
|
840 .byte 0xbe, 0xcd, 0xf6, 0xf9 |
|
841 !aes_dround01 %f16, %f60, %f62, %f56 ; \ |
|
842 !aes_dround23 %f18, %f60, %f62, %f58 ; \ |
|
843 !aes_dround01 %f20, %f56, %f58, %f60 ; \ |
|
844 !aes_dround23 %f22, %f56, %f58, %f62 ; \ |
|
845 !aes_dround01 %f24, %f60, %f62, %f56 ; \ |
|
846 !aes_dround23 %f26, %f60, %f62, %f58 ; \ |
|
847 !aes_dround01 %f28, %f56, %f58, %f60 ; \ |
|
848 !aes_dround23 %f30, %f56, %f58, %f62 ; \ |
|
849 !aes_dround01 %f32, %f60, %f62, %f56 ; \ |
|
850 !aes_dround23 %f34, %f60, %f62, %f58 ; \ |
|
851 !aes_dround01 %f36, %f56, %f58, %f60 ; \ |
|
852 !aes_dround23 %f38, %f56, %f58, %f62 ; \ |
|
853 !aes_dround01 %f40, %f60, %f62, %f56 ; \ |
|
854 !aes_dround23 %f42, %f60, %f62, %f58 ; \ |
|
855 !aes_dround01 %f44, %f56, %f58, %f60 ; \ |
|
856 !aes_dround23 %f46, %f56, %f58, %f62 ; \ |
|
857 !aes_dround01 %f48, %f60, %f62, %f56 ; \ |
|
858 !aes_dround23 %f50, %f60, %f62, %f58 ; \ |
|
859 !aes_dround01_l %f52, %f56, %f58, %f60 ; \ |
|
860 !aes_dround23_l %f54, %f56, %f58, %f62 |
|
861 |
|
862 #define TEN_DROUNDS_2 \ |
|
863 .byte 0x8c, 0xcc, 0x04, 0x40 ; \ |
|
864 .byte 0x88, 0xcc, 0x84, 0x60 ; \ |
|
865 .byte 0xb2, 0xcc, 0x3e, 0x5d ; \ |
|
866 .byte 0xb6, 0xcc, 0xbe, 0x7d ; \ |
|
867 .byte 0x80, 0xcd, 0x08, 0x46 ; \ |
|
868 .byte 0x84, 0xcd, 0x88, 0x66 ; \ |
|
869 .byte 0xba, 0xcd, 0x36, 0x59 ; \ |
|
870 .byte 0xbe, 0xcd, 0xb6, 0x79 ; \ |
|
871 .byte 0x8c, 0xce, 0x04, 0x40 ; \ |
|
872 .byte 0x88, 0xce, 0x84, 0x60 ; \ |
|
873 .byte 0xb2, 0xce, 0x3e, 0x5d ; \ |
|
874 .byte 0xb6, 0xce, 0xbe, 0x7d ; \ |
|
875 .byte 0x80, 0xcf, 0x08, 0x46 ; \ |
|
876 .byte 0x84, 0xcf, 0x88, 0x66 ; \ |
|
877 .byte 0xba, 0xcf, 0x36, 0x59 ; \ |
|
878 .byte 0xbe, 0xcf, 0xb6, 0x79 ; \ |
|
879 .byte 0x8c, 0xc8, 0x44, 0x40 ; \ |
|
880 .byte 0x88, 0xc8, 0xc4, 0x60 ; \ |
|
881 .byte 0xb2, 0xc8, 0x7e, 0x5d ; \ |
|
882 .byte 0xb6, 0xc8, 0xfe, 0x7d ; \ |
|
883 .byte 0x80, 0xc9, 0x48, 0x46 ; \ |
|
884 .byte 0x84, 0xc9, 0xc8, 0x66 ; \ |
|
885 .byte 0xba, 0xc9, 0x76, 0x59 ; \ |
|
886 .byte 0xbe, 0xc9, 0xf6, 0x79 ; \ |
|
887 .byte 0x8c, 0xca, 0x44, 0x40 ; \ |
|
888 .byte 0x88, 0xca, 0xc4, 0x60 ; \ |
|
889 .byte 0xb2, 0xca, 0x7e, 0x5d ; \ |
|
890 .byte 0xb6, 0xca, 0xfe, 0x7d ; \ |
|
891 .byte 0x80, 0xcb, 0x48, 0x46 ; \ |
|
892 .byte 0x84, 0xcb, 0xc8, 0x66 ; \ |
|
893 .byte 0xba, 0xcb, 0x76, 0x59 ; \ |
|
894 .byte 0xbe, 0xcb, 0xf6, 0x79 ; \ |
|
895 .byte 0x8c, 0xcc, 0x44, 0x40 ; \ |
|
896 .byte 0x88, 0xcc, 0xc4, 0x60 ; \ |
|
897 .byte 0xb2, 0xcc, 0x7e, 0x5d ; \ |
|
898 .byte 0xb6, 0xcc, 0xfe, 0x7d ; \ |
|
899 .byte 0x80, 0xcd, 0x48, 0xc6 ; \ |
|
900 .byte 0x84, 0xcd, 0xc8, 0xe6 ; \ |
|
901 .byte 0xba, 0xcd, 0x76, 0xd9 ; \ |
|
902 .byte 0xbe, 0xcd, 0xf6, 0xf9 |
|
903 !aes_dround01 %f16, %f0, %f2, %f6 ; \ |
|
904 !aes_dround23 %f18, %f0, %f2, %f4 ; \ |
|
905 !aes_dround01 %f16, %f60, %f62, %f56 ; \ |
|
906 !aes_dround23 %f18, %f60, %f62, %f58 ; \ |
|
907 !aes_dround01 %f20, %f6, %f4, %f0 ; \ |
|
908 !aes_dround23 %f22, %f6, %f4, %f2 ; \ |
|
909 !aes_dround01 %f20, %f56, %f58, %f60 ; \ |
|
910 !aes_dround23 %f22, %f56, %f58, %f62 ; \ |
|
911 !aes_dround01 %f24, %f0, %f2, %f6 ; \ |
|
912 !aes_dround23 %f26, %f0, %f2, %f4 ; \ |
|
913 !aes_dround01 %f24, %f60, %f62, %f56 ; \ |
|
914 !aes_dround23 %f26, %f60, %f62, %f58 ; \ |
|
915 !aes_dround01 %f28, %f6, %f4, %f0 ; \ |
|
916 !aes_dround23 %f30, %f6, %f4, %f2 ; \ |
|
917 !aes_dround01 %f28, %f56, %f58, %f60 ; \ |
|
918 !aes_dround23 %f30, %f56, %f58, %f62 ; \ |
|
919 !aes_dround01 %f32, %f0, %f2, %f6 ; \ |
|
920 !aes_dround23 %f34, %f0, %f2, %f4 ; \ |
|
921 !aes_dround01 %f32, %f60, %f62, %f56 ; \ |
|
922 !aes_dround23 %f34, %f60, %f62, %f58 ; \ |
|
923 !aes_dround01 %f36, %f6, %f4, %f0 ; \ |
|
924 !aes_dround23 %f38, %f6, %f4, %f2 ; \ |
|
925 !aes_dround01 %f36, %f56, %f58, %f60 ; \ |
|
926 !aes_dround23 %f38, %f56, %f58, %f62 ; \ |
|
927 !aes_dround01 %f40, %f0, %f2, %f6 ; \ |
|
928 !aes_dround23 %f42, %f0, %f2, %f4 ; \ |
|
929 !aes_dround01 %f40, %f60, %f62, %f56 ; \ |
|
930 !aes_dround23 %f42, %f60, %f62, %f58 ; \ |
|
931 !aes_dround01 %f44, %f6, %f4, %f0 ; \ |
|
932 !aes_dround23 %f46, %f6, %f4, %f2 ; \ |
|
933 !aes_dround01 %f44, %f56, %f58, %f60 ; \ |
|
934 !aes_dround23 %f46, %f56, %f58, %f62 ; \ |
|
935 !aes_dround01 %f48, %f0, %f2, %f6 ; \ |
|
936 !aes_dround23 %f50, %f0, %f2, %f4 ; \ |
|
937 !aes_dround01 %f48, %f60, %f62, %f56 ; \ |
|
938 !aes_dround23 %f50, %f60, %f62, %f58 ; \ |
|
939 !aes_dround01_l %f52, %f6, %f4, %f0 ; \ |
|
940 !aes_dround23_l %f54, %f6, %f4, %f2 ; \ |
|
941 !aes_dround01_l %f52, %f56, %f58, %f60 ; \ |
|
942 !aes_dround23_l %f54, %f56, %f58, %f62 |
|
943 |
|
944 #define TWELVE_DROUNDS \ |
|
945 MID_TWO_DROUNDS ; \ |
|
946 TEN_DROUNDS |
|
947 |
|
948 #define TWELVE_DROUNDS_2 \ |
|
949 MID_TWO_DROUNDS_2 ; \ |
|
950 TEN_DROUNDS_2 |
|
951 |
|
952 #define FOURTEEN_DROUNDS \ |
|
953 FIRST_TWO_DROUNDS ; \ |
|
954 TWELVE_DROUNDS |
|
955 |
|
956 #define FOURTEEN_DROUNDS_2 \ |
|
957 .byte 0xb0, 0xc8, 0x2c, 0x54 ; \ |
|
958 .byte 0xac, 0xc8, 0xac, 0x74 ; \ |
|
959 ldd [%o0 + 0x80], %f20 ; \ |
|
960 .byte 0xb2, 0xc8, 0x3e, 0x5d ; \ |
|
961 .byte 0xb6, 0xc8, 0xbe, 0x7d ; \ |
|
962 .byte 0x80, 0xc9, 0x2c, 0x58 ; \ |
|
963 .byte 0x84, 0xc9, 0xac, 0x78 ; \ |
|
964 ldd [%o0 + 0x88], %f22 ; \ |
|
965 .byte 0xba, 0xc9, 0x36, 0x59 ; \ |
|
966 ldd [%o0 + 0x70], %f24 ; \ |
|
967 .byte 0xbe, 0xc9, 0xb6, 0x79 ; \ |
|
968 .byte 0x8c, 0xca, 0x04, 0x40 ; \ |
|
969 .byte 0x88, 0xca, 0x84, 0x60 ; \ |
|
970 .byte 0xb2, 0xca, 0x3e, 0x5d ; \ |
|
971 .byte 0xb6, 0xca, 0xbe, 0x7d ; \ |
|
972 .byte 0x80, 0xcb, 0x08, 0x46 ; \ |
|
973 .byte 0x84, 0xcb, 0x88, 0x66 ; \ |
|
974 .byte 0xba, 0xcb, 0x36, 0x59 ; \ |
|
975 .byte 0xbe, 0xcb, 0xb6, 0x79 ; \ |
|
976 .byte 0x8c, 0xcc, 0x04, 0x40 ; \ |
|
977 .byte 0x88, 0xcc, 0x84, 0x60 ; \ |
|
978 .byte 0xb2, 0xcc, 0x3e, 0x5d ; \ |
|
979 .byte 0xb6, 0xcc, 0xbe, 0x7d ; \ |
|
980 .byte 0x80, 0xcd, 0x08, 0x46 ; \ |
|
981 .byte 0x84, 0xcd, 0x88, 0x66 ; \ |
|
982 .byte 0xba, 0xcd, 0x36, 0x59 ; \ |
|
983 .byte 0xbe, 0xcd, 0xb6, 0x79 ; \ |
|
984 .byte 0x8c, 0xce, 0x04, 0x40 ; \ |
|
985 .byte 0x88, 0xce, 0x84, 0x60 ; \ |
|
986 .byte 0xb2, 0xce, 0x3e, 0x5d ; \ |
|
987 .byte 0xb6, 0xce, 0xbe, 0x7d ; \ |
|
988 .byte 0x80, 0xcf, 0x08, 0x46 ; \ |
|
989 .byte 0x84, 0xcf, 0x88, 0x66 ; \ |
|
990 .byte 0xba, 0xcf, 0x36, 0x59 ; \ |
|
991 .byte 0xbe, 0xcf, 0xb6, 0x79 ; \ |
|
992 .byte 0x8c, 0xc8, 0x44, 0x40 ; \ |
|
993 .byte 0x88, 0xc8, 0xc4, 0x60 ; \ |
|
994 .byte 0xb2, 0xc8, 0x7e, 0x5d ; \ |
|
995 .byte 0xb6, 0xc8, 0xfe, 0x7d ; \ |
|
996 .byte 0x80, 0xc9, 0x48, 0x46 ; \ |
|
997 .byte 0x84, 0xc9, 0xc8, 0x66 ; \ |
|
998 .byte 0xba, 0xc9, 0x76, 0x59 ; \ |
|
999 .byte 0xbe, 0xc9, 0xf6, 0x79 ; \ |
|
1000 .byte 0x8c, 0xca, 0x44, 0x40 ; \ |
|
1001 .byte 0x88, 0xca, 0xc4, 0x60 ; \ |
|
1002 .byte 0xb2, 0xca, 0x7e, 0x5d ; \ |
|
1003 .byte 0xb6, 0xca, 0xfe, 0x7d ; \ |
|
1004 .byte 0x80, 0xcb, 0x48, 0x46 ; \ |
|
1005 .byte 0x84, 0xcb, 0xc8, 0x66 ; \ |
|
1006 .byte 0xba, 0xcb, 0x76, 0x59 ; \ |
|
1007 .byte 0xbe, 0xcb, 0xf6, 0x79 ; \ |
|
1008 .byte 0x8c, 0xcc, 0x44, 0x40 ; \ |
|
1009 .byte 0x88, 0xcc, 0xc4, 0x60 ; \ |
|
1010 ldd [%o0 + 0xd0], %f0 ; \ |
|
1011 .byte 0xb2, 0xcc, 0x7e, 0x5d ; \ |
|
1012 ldd [%o0 + 0xd8], %f2 ; \ |
|
1013 .byte 0xb6, 0xcc, 0xfe, 0x7d ; \ |
|
1014 .byte 0xa8, 0xcd, 0x48, 0xc6 ; \ |
|
1015 .byte 0xac, 0xcd, 0xc8, 0xe6 ; \ |
|
1016 ldd [%o0 + 0xc0], %f4 ; \ |
|
1017 .byte 0xba, 0xcd, 0x76, 0xd9 ; \ |
|
1018 ldd [%o0 + 0xc8], %f6 ; \ |
|
1019 .byte 0xbe, 0xcd, 0xf6, 0xf9 |
|
1020 !aes_dround01 %f0, %f20, %f22, %f24 ; \ |
|
1021 !aes_dround23 %f2, %f20, %f22, %f22 ; \ |
|
1022 !ldd [%o0 + 0x80], %f20 ; \ |
|
1023 !aes_dround01 %f0, %f60, %f62, %f56 ; \ |
|
1024 !aes_dround23 %f2, %f60, %f62, %f58 ; \ |
|
1025 !aes_dround01 %f4, %f24, %f22, %f0 ; \ |
|
1026 !aes_dround23 %f6, %f24, %f22, %f2 ; \ |
|
1027 !ldd [%o0 + 0x88], %f22 ; \ |
|
1028 !aes_dround01 %f4, %f56, %f58, %f60 ; \ |
|
1029 !ldd [%o0 + 0x70], %f24 ; \ |
|
1030 !aes_dround23 %f6, %f56, %f58, %f62 ; \ |
|
1031 !aes_dround01 %f8, %f0, %f2, %f6 ; \ |
|
1032 !aes_dround23 %f10, %f0, %f2, %f4 ; \ |
|
1033 !aes_dround01 %f8, %f60, %f62, %f56 ; \ |
|
1034 !aes_dround23 %f10, %f60, %f62, %f58 ; \ |
|
1035 !aes_dround01 %f12, %f6, %f4, %f0 ; \ |
|
1036 !aes_dround23 %f14, %f6, %f4, %f2 ; \ |
|
1037 !aes_dround01 %f12, %f56, %f58, %f60 ; \ |
|
1038 !aes_dround23 %f14, %f56, %f58, %f62 ; \ |
|
1039 !aes_dround01 %f16, %f0, %f2, %f6 ; \ |
|
1040 !aes_dround23 %f18, %f0, %f2, %f4 ; \ |
|
1041 !aes_dround01 %f16, %f60, %f62, %f56 ; \ |
|
1042 !aes_dround23 %f18, %f60, %f62, %f58 ; \ |
|
1043 !aes_dround01 %f20, %f6, %f4, %f0 ; \ |
|
1044 !aes_dround23 %f22, %f6, %f4, %f2 ; \ |
|
1045 !aes_dround01 %f20, %f56, %f58, %f60 ; \ |
|
1046 !aes_dround23 %f22, %f56, %f58, %f62 ; \ |
|
1047 !aes_dround01 %f24, %f0, %f2, %f6 ; \ |
|
1048 !aes_dround23 %f26, %f0, %f2, %f4 ; \ |
|
1049 !aes_dround01 %f24, %f60, %f62, %f56 ; \ |
|
1050 !aes_dround23 %f26, %f60, %f62, %f58 ; \ |
|
1051 !aes_dround01 %f28, %f6, %f4, %f0 ; \ |
|
1052 !aes_dround23 %f30, %f6, %f4, %f2 ; \ |
|
1053 !aes_dround01 %f28, %f56, %f58, %f60 ; \ |
|
1054 !aes_dround23 %f30, %f56, %f58, %f62 ; \ |
|
1055 !aes_dround01 %f32, %f0, %f2, %f6 ; \ |
|
1056 !aes_dround23 %f34, %f0, %f2, %f4 ; \ |
|
1057 !aes_dround01 %f32, %f60, %f62, %f56 ; \ |
|
1058 !aes_dround23 %f34, %f60, %f62, %f58 ; \ |
|
1059 !aes_dround01 %f36, %f6, %f4, %f0 ; \ |
|
1060 !aes_dround23 %f38, %f6, %f4, %f2 ; \ |
|
1061 !aes_dround01 %f36, %f56, %f58, %f60 ; \ |
|
1062 !aes_dround23 %f38, %f56, %f58, %f62 ; \ |
|
1063 !aes_dround01 %f40, %f0, %f2, %f6 ; \ |
|
1064 !aes_dround23 %f42, %f0, %f2, %f4 ; \ |
|
1065 !aes_dround01 %f40, %f60, %f62, %f56 ; \ |
|
1066 !aes_dround23 %f42, %f60, %f62, %f58 ; \ |
|
1067 !aes_dround01 %f44, %f6, %f4, %f0 ; \ |
|
1068 !aes_dround23 %f46, %f6, %f4, %f2 ; \ |
|
1069 !aes_dround01 %f44, %f56, %f58, %f60 ; \ |
|
1070 !aes_dround23 %f46, %f56, %f58, %f62 ; \ |
|
1071 !aes_dround01 %f48, %f0, %f2, %f6 ; \ |
|
1072 !aes_dround23 %f50, %f0, %f2, %f4 ; \ |
|
1073 !ldd [%o0 + 0xd0], %f0 ; \ |
|
1074 !aes_dround01 %f48, %f60, %f62, %f56 ; \ |
|
1075 !ldd [%o0 + 0xd8], %f2 ; \ |
|
1076 !aes_dround23 %f50, %f60, %f62, %f58 ; \ |
|
1077 !aes_dround01_l %f52, %f6, %f4, %f20 ; \ |
|
1078 !aes_dround23_l %f54, %f6, %f4, %f22 ; \ |
|
1079 !ldd [%o0 + 0xc0], %f4 ; \ |
|
1080 !aes_dround01_l %f52, %f56, %f58, %f60 ; \ |
|
1081 !ldd [%o0 + 0xc8], %f6 ; \ |
|
1082 !aes_dround23_l %f54, %f56, %f58, %f62 |
|
1083 |
|
1084 |
|
1085 ENTRY(t4_aes128_load_keys_for_encrypt) |
|
1086 |
|
1087 ldd [%o0 + 0x10], %f16 |
|
1088 ldd [%o0 + 0x18], %f18 |
|
1089 ldd [%o0 + 0x20], %f20 |
|
1090 ldd [%o0 + 0x28], %f22 |
|
1091 ldd [%o0 + 0x30], %f24 |
|
1092 ldd [%o0 + 0x38], %f26 |
|
1093 ldd [%o0 + 0x40], %f28 |
|
1094 ldd [%o0 + 0x48], %f30 |
|
1095 ldd [%o0 + 0x50], %f32 |
|
1096 ldd [%o0 + 0x58], %f34 |
|
1097 ldd [%o0 + 0x60], %f36 |
|
1098 ldd [%o0 + 0x68], %f38 |
|
1099 ldd [%o0 + 0x70], %f40 |
|
1100 ldd [%o0 + 0x78], %f42 |
|
1101 ldd [%o0 + 0x80], %f44 |
|
1102 ldd [%o0 + 0x88], %f46 |
|
1103 ldd [%o0 + 0x90], %f48 |
|
1104 ldd [%o0 + 0x98], %f50 |
|
1105 ldd [%o0 + 0xa0], %f52 |
|
1106 retl |
|
1107 ldd [%o0 + 0xa8], %f54 |
|
1108 |
|
1109 SET_SIZE(t4_aes128_load_keys_for_encrypt) |
|
1110 |
|
1111 |
|
1112 ENTRY(t4_aes192_load_keys_for_encrypt) |
|
1113 |
|
1114 ldd [%o0 + 0x10], %f8 |
|
1115 ldd [%o0 + 0x18], %f10 |
|
1116 ldd [%o0 + 0x20], %f12 |
|
1117 ldd [%o0 + 0x28], %f14 |
|
1118 ldd [%o0 + 0x30], %f16 |
|
1119 ldd [%o0 + 0x38], %f18 |
|
1120 ldd [%o0 + 0x40], %f20 |
|
1121 ldd [%o0 + 0x48], %f22 |
|
1122 ldd [%o0 + 0x50], %f24 |
|
1123 ldd [%o0 + 0x58], %f26 |
|
1124 ldd [%o0 + 0x60], %f28 |
|
1125 ldd [%o0 + 0x68], %f30 |
|
1126 ldd [%o0 + 0x70], %f32 |
|
1127 ldd [%o0 + 0x78], %f34 |
|
1128 ldd [%o0 + 0x80], %f36 |
|
1129 ldd [%o0 + 0x88], %f38 |
|
1130 ldd [%o0 + 0x90], %f40 |
|
1131 ldd [%o0 + 0x98], %f42 |
|
1132 ldd [%o0 + 0xa0], %f44 |
|
1133 ldd [%o0 + 0xa8], %f46 |
|
1134 ldd [%o0 + 0xb0], %f48 |
|
1135 ldd [%o0 + 0xb8], %f50 |
|
1136 ldd [%o0 + 0xc0], %f52 |
|
1137 retl |
|
1138 ldd [%o0 + 0xc8], %f54 |
|
1139 |
|
1140 SET_SIZE(t4_aes192_load_keys_for_encrypt) |
|
1141 |
|
1142 |
|
1143 ENTRY(t4_aes256_load_keys_for_encrypt) |
|
1144 |
|
1145 ldd [%o0 + 0x10], %f0 |
|
1146 ldd [%o0 + 0x18], %f2 |
|
1147 ldd [%o0 + 0x20], %f4 |
|
1148 ldd [%o0 + 0x28], %f6 |
|
1149 ldd [%o0 + 0x30], %f8 |
|
1150 ldd [%o0 + 0x38], %f10 |
|
1151 ldd [%o0 + 0x40], %f12 |
|
1152 ldd [%o0 + 0x48], %f14 |
|
1153 ldd [%o0 + 0x50], %f16 |
|
1154 ldd [%o0 + 0x58], %f18 |
|
1155 ldd [%o0 + 0x60], %f20 |
|
1156 ldd [%o0 + 0x68], %f22 |
|
1157 ldd [%o0 + 0x70], %f24 |
|
1158 ldd [%o0 + 0x78], %f26 |
|
1159 ldd [%o0 + 0x80], %f28 |
|
1160 ldd [%o0 + 0x88], %f30 |
|
1161 ldd [%o0 + 0x90], %f32 |
|
1162 ldd [%o0 + 0x98], %f34 |
|
1163 ldd [%o0 + 0xa0], %f36 |
|
1164 ldd [%o0 + 0xa8], %f38 |
|
1165 ldd [%o0 + 0xb0], %f40 |
|
1166 ldd [%o0 + 0xb8], %f42 |
|
1167 ldd [%o0 + 0xc0], %f44 |
|
1168 ldd [%o0 + 0xc8], %f46 |
|
1169 ldd [%o0 + 0xd0], %f48 |
|
1170 ldd [%o0 + 0xd8], %f50 |
|
1171 ldd [%o0 + 0xe0], %f52 |
|
1172 retl |
|
1173 ldd [%o0 + 0xe8], %f54 |
|
1174 |
|
1175 SET_SIZE(t4_aes256_load_keys_for_encrypt) |
|
1176 |
|
1177 |
|
1178 #define TEST_PARALLEL_ECB_ENCRYPT |
|
1179 #ifdef TEST_PARALLEL_ECB_ENCRYPT |
|
1180 ENTRY(t4_aes128_ecb_encrypt) |
|
1181 |
|
1182 ldx [%o0], %g1 ! ks[0] |
|
1183 ldx [%o0 + 8], %g2 ! ks[1] |
|
1184 and %o3, 16, %o4 |
|
1185 brz %o4, ecbenc128_loop |
|
1186 nop |
|
1187 |
|
1188 ldx [%o1], %g3 !input |
|
1189 ldx [%o1 + 8], %g4 !input |
|
1190 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1191 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1192 movxtod %g3, %f60 |
|
1193 movxtod %g4, %f62 |
|
1194 |
|
1195 TEN_EROUNDS |
|
1196 |
|
1197 std %f60, [%o2] |
|
1198 std %f62, [%o2 + 8] |
|
1199 |
|
1200 add %o1, 16, %o1 |
|
1201 subcc %o3, 16, %o3 |
|
1202 be ecbenc128_loop_end |
|
1203 add %o2, 16, %o2 |
|
1204 |
|
1205 ecbenc128_loop: |
|
1206 ldx [%o1], %g3 !input |
|
1207 ldx [%o1 + 8], %g4 !input |
|
1208 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1209 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1210 movxtod %g3, %f0 |
|
1211 movxtod %g4, %f2 |
|
1212 ldx [%o1 + 16], %g3 !input |
|
1213 ldx [%o1 + 24], %g4 !input |
|
1214 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1215 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1216 movxtod %g3, %f60 |
|
1217 movxtod %g4, %f62 |
|
1218 |
|
1219 TEN_EROUNDS_2 |
|
1220 |
|
1221 std %f0, [%o2] |
|
1222 std %f2, [%o2 + 8] |
|
1223 |
|
1224 std %f60, [%o2 + 16] |
|
1225 std %f62, [%o2 + 24] |
|
1226 |
|
1227 add %o1, 32, %o1 |
|
1228 subcc %o3, 32, %o3 |
|
1229 bne ecbenc128_loop |
|
1230 add %o2, 32, %o2 |
|
1231 ecbenc128_loop_end: |
|
1232 retl |
|
1233 nop |
|
1234 |
|
1235 SET_SIZE(t4_aes128_ecb_encrypt) |
|
1236 |
|
1237 |
|
1238 ENTRY(t4_aes192_ecb_encrypt) |
|
1239 |
|
1240 ldx [%o0], %g1 ! ks[0] |
|
1241 ldx [%o0 + 8], %g2 ! ks[1] |
|
1242 and %o3, 16, %o4 |
|
1243 brz %o4, ecbenc192_loop |
|
1244 nop |
|
1245 |
|
1246 ldx [%o1], %g3 !input |
|
1247 ldx [%o1 + 8], %g4 !input |
|
1248 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1249 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1250 movxtod %g3, %f60 |
|
1251 movxtod %g4, %f62 |
|
1252 |
|
1253 TWELVE_EROUNDS |
|
1254 |
|
1255 std %f60, [%o2] |
|
1256 std %f62, [%o2 + 8] |
|
1257 |
|
1258 add %o1, 16, %o1 |
|
1259 subcc %o3, 16, %o3 |
|
1260 be ecbenc192_loop_end |
|
1261 add %o2, 16, %o2 |
|
1262 |
|
1263 ecbenc192_loop: |
|
1264 ldx [%o1], %g3 !input |
|
1265 ldx [%o1 + 8], %g4 !input |
|
1266 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1267 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1268 movxtod %g3, %f0 |
|
1269 movxtod %g4, %f2 |
|
1270 ldx [%o1 + 16], %g3 !input |
|
1271 ldx [%o1 + 24], %g4 !input |
|
1272 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1273 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1274 movxtod %g3, %f60 |
|
1275 movxtod %g4, %f62 |
|
1276 |
|
1277 TWELVE_EROUNDS_2 |
|
1278 |
|
1279 std %f0, [%o2] |
|
1280 std %f2, [%o2 + 8] |
|
1281 |
|
1282 std %f60, [%o2 + 16] |
|
1283 std %f62, [%o2 + 24] |
|
1284 |
|
1285 add %o1, 32, %o1 |
|
1286 subcc %o3, 32, %o3 |
|
1287 bne ecbenc192_loop |
|
1288 add %o2, 32, %o2 |
|
1289 ecbenc192_loop_end: |
|
1290 retl |
|
1291 nop |
|
1292 |
|
1293 SET_SIZE(t4_aes192_ecb_encrypt) |
|
1294 |
|
1295 |
|
1296 ENTRY(t4_aes256_ecb_encrypt) |
|
1297 |
|
1298 ldx [%o0], %g1 ! ks[0] |
|
1299 ldx [%o0 + 8], %g2 ! ks[1] |
|
1300 and %o3, 16, %o4 |
|
1301 brz %o4, ecbenc256_loop |
|
1302 nop |
|
1303 |
|
1304 ldx [%o1], %g3 !input |
|
1305 ldx [%o1 + 8], %g4 !input |
|
1306 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1307 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1308 movxtod %g3, %f60 |
|
1309 movxtod %g4, %f62 |
|
1310 |
|
1311 FOURTEEN_EROUNDS |
|
1312 |
|
1313 std %f60, [%o2] |
|
1314 std %f62, [%o2 + 8] |
|
1315 |
|
1316 add %o1, 16, %o1 |
|
1317 subcc %o3, 16, %o3 |
|
1318 be ecbenc256_loop_end |
|
1319 add %o2, 16, %o2 |
|
1320 |
|
1321 ecbenc256_loop: |
|
1322 ldx [%o1], %g3 !input |
|
1323 ldx [%o1 + 8], %g4 !input |
|
1324 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1325 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1326 movxtod %g3, %f20 |
|
1327 movxtod %g4, %f22 |
|
1328 ldx [%o1 + 16], %g3 !input |
|
1329 ldx [%o1 + 24], %g4 !input |
|
1330 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1331 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1332 movxtod %g3, %f60 |
|
1333 movxtod %g4, %f62 |
|
1334 |
|
1335 FOURTEEN_EROUNDS_2 |
|
1336 |
|
1337 std %f20, [%o2] |
|
1338 std %f22, [%o2 + 8] |
|
1339 |
|
1340 std %f60, [%o2 + 16] |
|
1341 std %f62, [%o2 + 24] |
|
1342 |
|
1343 add %o1, 32, %o1 |
|
1344 subcc %o3, 32, %o3 |
|
1345 bne ecbenc256_loop |
|
1346 add %o2, 32, %o2 |
|
1347 |
|
1348 ldd [%o0 + 0x60], %f20 |
|
1349 ldd [%o0 + 0x68], %f22 |
|
1350 |
|
1351 ecbenc256_loop_end: |
|
1352 retl |
|
1353 nop |
|
1354 |
|
1355 SET_SIZE(t4_aes256_ecb_encrypt) |
|
1356 |
|
1357 #else |
|
1358 |
|
1359 ENTRY(t4_aes128_ecb_encrypt) |
|
1360 |
|
1361 ldx [%o0], %g1 ! ks[0] |
|
1362 ldx [%o0 + 8], %g2 ! ks[1] |
|
1363 |
|
1364 ecbenc128_loop: |
|
1365 ldx [%o1], %g3 !input |
|
1366 ldx [%o1 + 8], %g4 !input |
|
1367 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1368 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1369 movxtod %g3, %f60 |
|
1370 movxtod %g4, %f62 |
|
1371 |
|
1372 TEN_EROUNDS |
|
1373 |
|
1374 std %f60, [%o2] |
|
1375 std %f62, [%o2 + 8] |
|
1376 |
|
1377 add %o1, 16, %o1 |
|
1378 subcc %o3, 16, %o3 |
|
1379 bne ecbenc128_loop |
|
1380 add %o2, 16, %o2 |
|
1381 |
|
1382 retl |
|
1383 nop |
|
1384 |
|
1385 SET_SIZE(t4_aes128_ecb_encrypt) |
|
1386 |
|
1387 |
|
1388 ENTRY(t4_aes192_ecb_encrypt) |
|
1389 |
|
1390 ldx [%o0], %g1 ! ks[0] |
|
1391 ldx [%o0 + 8], %g2 ! ks[1] |
|
1392 |
|
1393 ecbenc192_loop: |
|
1394 ldx [%o1], %g3 !input |
|
1395 ldx [%o1 + 8], %g4 !input |
|
1396 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1397 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1398 movxtod %g3, %f60 |
|
1399 movxtod %g4, %f62 |
|
1400 |
|
1401 TWELVE_EROUNDS |
|
1402 |
|
1403 std %f60, [%o2] |
|
1404 std %f62, [%o2 + 8] |
|
1405 |
|
1406 add %o1, 16, %o1 |
|
1407 subcc %o3, 16, %o3 |
|
1408 bne ecbenc192_loop |
|
1409 add %o2, 16, %o2 |
|
1410 |
|
1411 retl |
|
1412 nop |
|
1413 |
|
1414 SET_SIZE(t4_aes192_ecb_encrypt) |
|
1415 |
|
1416 |
|
1417 ENTRY(t4_aes256_ecb_encrypt) |
|
1418 |
|
1419 ldx [%o0], %g1 ! ks[0] |
|
1420 ldx [%o0 + 8], %g2 ! ks[1] |
|
1421 |
|
1422 ecbenc256_loop: |
|
1423 ldx [%o1], %g3 !input |
|
1424 ldx [%o1 + 8], %g4 !input |
|
1425 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1426 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1427 movxtod %g3, %f60 |
|
1428 movxtod %g4, %f62 |
|
1429 |
|
1430 FOURTEEN_EROUNDS |
|
1431 |
|
1432 std %f60, [%o2] |
|
1433 std %f62, [%o2 + 8] |
|
1434 |
|
1435 add %o1, 16, %o1 |
|
1436 subcc %o3, 16, %o3 |
|
1437 bne ecbenc256_loop |
|
1438 add %o2, 16, %o2 |
|
1439 |
|
1440 retl |
|
1441 nop |
|
1442 |
|
1443 SET_SIZE(t4_aes256_ecb_encrypt) |
|
1444 #endif |
|
1445 |
|
1446 |
|
1447 ENTRY(t4_aes128_cbc_encrypt) |
|
1448 |
|
1449 ldd [%o4], %f60 ! IV |
|
1450 ldd [%o4 +8], %f62 ! IV |
|
1451 ldx [%o0], %g1 ! ks[0] |
|
1452 ldx [%o0 + 8], %g2 ! ks[1] |
|
1453 |
|
1454 cbcenc128_loop: |
|
1455 ldx [%o1], %g3 !input |
|
1456 ldx [%o1 + 8], %g4 !input |
|
1457 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1458 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1459 movxtod %g3, %f56 |
|
1460 movxtod %g4, %f58 |
|
1461 fxor %f60, %f56, %f60 |
|
1462 fxor %f62, %f58, %f62 |
|
1463 |
|
1464 TEN_EROUNDS |
|
1465 |
|
1466 std %f60, [%o2] |
|
1467 std %f62, [%o2 + 8] |
|
1468 |
|
1469 add %o1, 16, %o1 |
|
1470 subcc %o3, 16, %o3 |
|
1471 bne cbcenc128_loop |
|
1472 add %o2, 16, %o2 |
|
1473 |
|
1474 std %f60, [%o4] |
|
1475 retl |
|
1476 std %f62, [%o4 + 8] |
|
1477 |
|
1478 SET_SIZE(t4_aes128_cbc_encrypt) |
|
1479 |
|
1480 |
|
1481 ENTRY(t4_aes192_cbc_encrypt) |
|
1482 |
|
1483 ldd [%o4], %f60 ! IV |
|
1484 ldd [%o4 + 8], %f62 ! IV |
|
1485 ldx [%o0], %g1 ! ks[0] |
|
1486 ldx [%o0 + 8], %g2 ! ks[1] |
|
1487 |
|
1488 cbcenc192_loop: |
|
1489 ldx [%o1], %g3 !input |
|
1490 ldx [%o1 + 8], %g4 !input |
|
1491 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1492 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1493 movxtod %g3, %f56 |
|
1494 movxtod %g4, %f58 |
|
1495 fxor %f60, %f56, %f60 |
|
1496 fxor %f62, %f58, %f62 |
|
1497 |
|
1498 TWELVE_EROUNDS |
|
1499 |
|
1500 std %f60, [%o2] |
|
1501 std %f62, [%o2 + 8] |
|
1502 |
|
1503 add %o1, 16, %o1 |
|
1504 subcc %o3, 16, %o3 |
|
1505 bne cbcenc192_loop |
|
1506 add %o2, 16, %o2 |
|
1507 |
|
1508 std %f60, [%o4] |
|
1509 retl |
|
1510 std %f62, [%o4 + 8] |
|
1511 |
|
1512 SET_SIZE(t4_aes192_cbc_encrypt) |
|
1513 |
|
1514 |
|
1515 ENTRY(t4_aes256_cbc_encrypt) |
|
1516 |
|
1517 ldd [%o4], %f60 ! IV |
|
1518 ldd [%o4 + 8], %f62 ! IV |
|
1519 ldx [%o0], %g1 ! ks[0] |
|
1520 ldx [%o0 + 8], %g2 ! ks[1] |
|
1521 |
|
1522 cbcenc256_loop: |
|
1523 ldx [%o1], %g3 !input |
|
1524 ldx [%o1 + 8], %g4 !input |
|
1525 xor %g1, %g3, %g3 !input ^ ks[0-1] |
|
1526 xor %g2, %g4, %g4 !input ^ ks[0-1] |
|
1527 movxtod %g3, %f56 |
|
1528 movxtod %g4, %f58 |
|
1529 fxor %f60, %f56, %f60 |
|
1530 fxor %f62, %f58, %f62 |
|
1531 |
|
1532 FOURTEEN_EROUNDS |
|
1533 |
|
1534 std %f60, [%o2] |
|
1535 std %f62, [%o2 + 8] |
|
1536 |
|
1537 add %o1, 16, %o1 |
|
1538 subcc %o3, 16, %o3 |
|
1539 bne cbcenc256_loop |
|
1540 add %o2, 16, %o2 |
|
1541 |
|
1542 std %f60, [%o4] |
|
1543 retl |
|
1544 std %f62, [%o4 + 8] |
|
1545 |
|
1546 SET_SIZE(t4_aes256_cbc_encrypt) |
|
1547 |
|
1548 |
|
1549 #define TEST_PARALLEL_CTR_CRYPT |
|
1550 #ifdef TEST_PARALLEL_CTR_CRYPT |
|
1551 ENTRY(t4_aes128_ctr_crypt) |
|
1552 |
|
1553 ldx [%o4], %g3 ! IV |
|
1554 ldx [%o4 +8], %g4 ! IV |
|
1555 ldx [%o0], %g1 ! ks[0] |
|
1556 ldx [%o0 + 8], %g2 ! ks[1] |
|
1557 and %o3, 16, %g5 |
|
1558 brz, %g5, ctr128_loop |
|
1559 |
|
1560 xor %g1, %g3, %g5 |
|
1561 movxtod %g5, %f60 |
|
1562 xor %g2, %g4, %g5 |
|
1563 movxtod %g5, %f62 |
|
1564 inc %g4 |
|
1565 |
|
1566 TEN_EROUNDS |
|
1567 |
|
1568 ldd [%o1], %f56 !input |
|
1569 ldd [%o1 + 8], %f58 !input |
|
1570 fxor %f60, %f56, %f60 |
|
1571 fxor %f62, %f58, %f62 |
|
1572 std %f60, [%o2] |
|
1573 std %f62, [%o2 + 8] |
|
1574 |
|
1575 add %o1, 16, %o1 |
|
1576 subcc %o3, 16, %o3 |
|
1577 be ctr128_loop_end |
|
1578 add %o2, 16, %o2 |
|
1579 |
|
1580 ctr128_loop: |
|
1581 xor %g1, %g3, %g5 |
|
1582 movxtod %g5, %f0 |
|
1583 xor %g2, %g4, %g5 |
|
1584 movxtod %g5, %f2 |
|
1585 inc %g4 |
|
1586 |
|
1587 xor %g1, %g3, %g5 |
|
1588 movxtod %g5, %f60 |
|
1589 xor %g2, %g4, %g5 |
|
1590 movxtod %g5, %f62 |
|
1591 inc %g4 |
|
1592 |
|
1593 TEN_EROUNDS_2 |
|
1594 |
|
1595 ldd [%o1], %f6 !input |
|
1596 ldd [%o1 + 8], %f4 !input |
|
1597 ldd [%o1 + 16], %f56 !input |
|
1598 ldd [%o1 + 24], %f58 !input |
|
1599 fxor %f0, %f6, %f0 |
|
1600 fxor %f2, %f4, %f2 |
|
1601 fxor %f60, %f56, %f60 |
|
1602 fxor %f62, %f58, %f62 |
|
1603 std %f0, [%o2] |
|
1604 std %f2, [%o2 + 8] |
|
1605 std %f60, [%o2 + 16] |
|
1606 std %f62, [%o2 + 24] |
|
1607 |
|
1608 add %o1, 32, %o1 |
|
1609 subcc %o3, 32, %o3 |
|
1610 bne ctr128_loop |
|
1611 add %o2, 32, %o2 |
|
1612 |
|
1613 ctr128_loop_end: |
|
1614 stx %g3, [%o4] |
|
1615 retl |
|
1616 stx %g4, [%o4 + 8] |
|
1617 |
|
1618 SET_SIZE(t4_aes128_ctr_crypt) |
|
1619 |
|
1620 |
|
1621 ENTRY(t4_aes192_ctr_crypt) |
|
1622 |
|
1623 ldx [%o4], %g3 ! IV |
|
1624 ldx [%o4 +8], %g4 ! IV |
|
1625 ldx [%o0], %g1 ! ks[0] |
|
1626 ldx [%o0 + 8], %g2 ! ks[1] |
|
1627 and %o3, 16, %g5 |
|
1628 brz, %g5, ctr192_loop |
|
1629 |
|
1630 xor %g1, %g3, %g5 |
|
1631 movxtod %g5, %f60 |
|
1632 xor %g2, %g4, %g5 |
|
1633 movxtod %g5, %f62 |
|
1634 inc %g4 |
|
1635 |
|
1636 TWELVE_EROUNDS |
|
1637 |
|
1638 ldd [%o1], %f56 !input |
|
1639 ldd [%o1 + 8], %f58 !input |
|
1640 fxor %f60, %f56, %f60 |
|
1641 fxor %f62, %f58, %f62 |
|
1642 std %f60, [%o2] |
|
1643 std %f62, [%o2 + 8] |
|
1644 |
|
1645 add %o1, 16, %o1 |
|
1646 subcc %o3, 16, %o3 |
|
1647 be ctr192_loop_end |
|
1648 add %o2, 16, %o2 |
|
1649 |
|
1650 ctr192_loop: |
|
1651 xor %g1, %g3, %g5 |
|
1652 movxtod %g5, %f0 |
|
1653 xor %g2, %g4, %g5 |
|
1654 movxtod %g5, %f2 |
|
1655 inc %g4 |
|
1656 |
|
1657 xor %g1, %g3, %g5 |
|
1658 movxtod %g5, %f60 |
|
1659 xor %g2, %g4, %g5 |
|
1660 movxtod %g5, %f62 |
|
1661 inc %g4 |
|
1662 |
|
1663 TWELVE_EROUNDS_2 |
|
1664 |
|
1665 ldd [%o1], %f6 !input |
|
1666 ldd [%o1 + 8], %f4 !input |
|
1667 ldd [%o1 + 16], %f56 !input |
|
1668 ldd [%o1 + 24], %f58 !input |
|
1669 fxor %f0, %f6, %f0 |
|
1670 fxor %f2, %f4, %f2 |
|
1671 fxor %f60, %f56, %f60 |
|
1672 fxor %f62, %f58, %f62 |
|
1673 std %f0, [%o2] |
|
1674 std %f2, [%o2 + 8] |
|
1675 std %f60, [%o2 + 16] |
|
1676 std %f62, [%o2 + 24] |
|
1677 |
|
1678 add %o1, 32, %o1 |
|
1679 subcc %o3, 32, %o3 |
|
1680 bne ctr192_loop |
|
1681 add %o2, 32, %o2 |
|
1682 |
|
1683 ctr192_loop_end: |
|
1684 stx %g3, [%o4] |
|
1685 retl |
|
1686 stx %g4, [%o4 + 8] |
|
1687 |
|
1688 SET_SIZE(t4_aes192_ctr_crypt) |
|
1689 |
|
1690 |
|
1691 ENTRY(t4_aes256_ctr_crypt) |
|
1692 |
|
1693 ldx [%o4], %g3 ! IV |
|
1694 ldx [%o4 +8], %g4 ! IV |
|
1695 ldx [%o0], %g1 ! ks[0] |
|
1696 ldx [%o0 + 8], %g2 ! ks[1] |
|
1697 and %o3, 16, %g5 |
|
1698 brz, %g5, ctr256_loop |
|
1699 |
|
1700 xor %g1, %g3, %g5 |
|
1701 movxtod %g5, %f60 |
|
1702 xor %g2, %g4, %g5 |
|
1703 movxtod %g5, %f62 |
|
1704 inc %g4 |
|
1705 |
|
1706 FOURTEEN_EROUNDS |
|
1707 |
|
1708 ldd [%o1], %f56 !input |
|
1709 ldd [%o1 + 8], %f58 !input |
|
1710 fxor %f60, %f56, %f60 |
|
1711 fxor %f62, %f58, %f62 |
|
1712 std %f60, [%o2] |
|
1713 std %f62, [%o2 + 8] |
|
1714 |
|
1715 add %o1, 16, %o1 |
|
1716 subcc %o3, 16, %o3 |
|
1717 be ctr256_loop_end |
|
1718 add %o2, 16, %o2 |
|
1719 |
|
1720 ctr256_loop: |
|
1721 xor %g1, %g3, %g5 |
|
1722 movxtod %g5, %f20 |
|
1723 xor %g2, %g4, %g5 |
|
1724 movxtod %g5, %f22 |
|
1725 inc %g4 |
|
1726 |
|
1727 xor %g1, %g3, %g5 |
|
1728 movxtod %g5, %f60 |
|
1729 xor %g2, %g4, %g5 |
|
1730 movxtod %g5, %f62 |
|
1731 inc %g4 |
|
1732 |
|
1733 FOURTEEN_EROUNDS_2 |
|
1734 |
|
1735 ldd [%o1], %f56 !input |
|
1736 ldd [%o1 + 8], %f58 !input |
|
1737 fxor %f20, %f56, %f20 |
|
1738 fxor %f22, %f58, %f22 |
|
1739 ldd [%o1 + 16], %f56 !input |
|
1740 ldd [%o1 + 24], %f58 !input |
|
1741 fxor %f60, %f56, %f60 |
|
1742 fxor %f62, %f58, %f62 |
|
1743 std %f20, [%o2] |
|
1744 std %f22, [%o2 + 8] |
|
1745 std %f60, [%o2 + 16] |
|
1746 std %f62, [%o2 + 24] |
|
1747 |
|
1748 add %o1, 32, %o1 |
|
1749 subcc %o3, 32, %o3 |
|
1750 bne ctr256_loop |
|
1751 add %o2, 32, %o2 |
|
1752 |
|
1753 ldd [%o0 + 0x60], %f20 |
|
1754 ldd [%o0 + 0x68], %f22 |
|
1755 |
|
1756 ctr256_loop_end: |
|
1757 stx %g3, [%o4] |
|
1758 retl |
|
1759 stx %g4, [%o4 + 8] |
|
1760 |
|
1761 SET_SIZE(t4_aes256_ctr_crypt) |
|
1762 |
|
1763 #else |
|
1764 |
|
1765 ENTRY(t4_aes128_ctr_crypt) |
|
1766 |
|
1767 ldx [%o4], %g3 ! IV |
|
1768 ldx [%o4 +8], %g4 ! IV |
|
1769 ldx [%o0], %g1 ! ks[0] |
|
1770 ldx [%o0 + 8], %g2 ! ks[1] |
|
1771 |
|
1772 ctr128_loop: |
|
1773 xor %g1, %g3, %g5 |
|
1774 movxtod %g5, %f60 |
|
1775 xor %g2, %g4, %g5 |
|
1776 movxtod %g5, %f62 |
|
1777 inc %g4 |
|
1778 |
|
1779 TEN_EROUNDS |
|
1780 |
|
1781 ldd [%o1], %f56 !input |
|
1782 ldd [%o1 + 8], %f58 !input |
|
1783 fxor %f60, %f56, %f60 |
|
1784 fxor %f62, %f58, %f62 |
|
1785 std %f60, [%o2] |
|
1786 std %f62, [%o2 + 8] |
|
1787 |
|
1788 add %o1, 16, %o1 |
|
1789 subcc %o3, 16, %o3 |
|
1790 bne ctr128_loop |
|
1791 add %o2, 16, %o2 |
|
1792 |
|
1793 stx %g3, [%o4] |
|
1794 retl |
|
1795 stx %g4, [%o4 + 8] |
|
1796 |
|
1797 SET_SIZE(t4_aes128_ctr_crypt) |
|
1798 |
|
1799 ENTRY(t4_aes192_ctr_crypt) |
|
1800 |
|
1801 ldx [%o4], %g3 ! IV |
|
1802 ldx [%o4 +8], %g4 ! IV |
|
1803 ldx [%o0], %g1 ! ks[0] |
|
1804 ldx [%o0 + 8], %g2 ! ks[1] |
|
1805 |
|
1806 ctr192_loop: |
|
1807 xor %g1, %g3, %g5 |
|
1808 movxtod %g5, %f60 |
|
1809 xor %g2, %g4, %g5 |
|
1810 movxtod %g5, %f62 |
|
1811 inc %g4 |
|
1812 |
|
1813 TWELVE_EROUNDS |
|
1814 |
|
1815 ldd [%o1], %f56 !input |
|
1816 ldd [%o1 + 8], %f58 !input |
|
1817 fxor %f60, %f56, %f60 |
|
1818 fxor %f62, %f58, %f62 |
|
1819 std %f60, [%o2] |
|
1820 std %f62, [%o2 + 8] |
|
1821 |
|
1822 add %o1, 16, %o1 |
|
1823 subcc %o3, 16, %o3 |
|
1824 bne ctr192_loop |
|
1825 add %o2, 16, %o2 |
|
1826 |
|
1827 stx %g3, [%o4] |
|
1828 retl |
|
1829 stx %g4, [%o4 + 8] |
|
1830 |
|
1831 SET_SIZE(t4_aes192_ctr_crypt) |
|
1832 |
|
1833 |
|
1834 ENTRY(t4_aes256_ctr_crypt) |
|
1835 |
|
1836 ldx [%o4], %g3 ! IV |
|
1837 ldx [%o4 +8], %g4 ! IV |
|
1838 ldx [%o0], %g1 ! ks[0] |
|
1839 ldx [%o0 + 8], %g2 ! ks[1] |
|
1840 |
|
1841 ctr256_loop: |
|
1842 xor %g1, %g3, %g5 |
|
1843 movxtod %g5, %f60 |
|
1844 xor %g2, %g4, %g5 |
|
1845 movxtod %g5, %f62 |
|
1846 inc %g4 |
|
1847 |
|
1848 FOURTEEN_EROUNDS |
|
1849 |
|
1850 ldd [%o1], %f56 !input |
|
1851 ldd [%o1 + 8], %f58 !input |
|
1852 fxor %f60, %f56, %f60 |
|
1853 fxor %f62, %f58, %f62 |
|
1854 std %f60, [%o2] |
|
1855 std %f62, [%o2 + 8] |
|
1856 |
|
1857 add %o1, 16, %o1 |
|
1858 subcc %o3, 16, %o3 |
|
1859 bne ctr256_loop |
|
1860 add %o2, 16, %o2 |
|
1861 |
|
1862 stx %g3, [%o4] |
|
1863 retl |
|
1864 stx %g4, [%o4 + 8] |
|
1865 |
|
1866 SET_SIZE(t4_aes256_ctr_crypt) |
|
1867 |
|
1868 #endif |
|
1869 |
|
1870 ENTRY(t4_aes128_cfb128_encrypt) |
|
1871 |
|
1872 ldd [%o4], %f60 ! IV |
|
1873 ldd [%o4 +8], %f62 ! IV |
|
1874 ldx [%o0], %g1 ! ks[0] |
|
1875 ldx [%o0 + 8], %g2 ! ks[1] |
|
1876 |
|
1877 cfb128_128_loop: |
|
1878 movxtod %g1, %f56 |
|
1879 movxtod %g2, %f58 |
|
1880 fxor %f60, %f56, %f60 |
|
1881 fxor %f62, %f58, %f62 |
|
1882 |
|
1883 TEN_EROUNDS |
|
1884 |
|
1885 ldd [%o1], %f56 !input |
|
1886 ldd [%o1 + 8], %f58 !input |
|
1887 fxor %f60, %f56, %f60 |
|
1888 fxor %f62, %f58, %f62 |
|
1889 |
|
1890 std %f60, [%o2] |
|
1891 std %f62, [%o2 + 8] |
|
1892 |
|
1893 add %o1, 16, %o1 |
|
1894 subcc %o3, 16, %o3 |
|
1895 bne cfb128_128_loop |
|
1896 add %o2, 16, %o2 |
|
1897 |
|
1898 std %f60, [%o4] |
|
1899 retl |
|
1900 std %f62, [%o4 + 8] |
|
1901 |
|
1902 SET_SIZE(t4_aes128_cfb128_encrypt) |
|
1903 |
|
1904 |
|
1905 ENTRY(t4_aes192_cfb128_encrypt) |
|
1906 |
|
1907 ldd [%o4], %f60 ! IV |
|
1908 ldd [%o4 +8], %f62 ! IV |
|
1909 ldx [%o0], %g1 ! ks[0] |
|
1910 ldx [%o0 + 8], %g2 ! ks[1] |
|
1911 |
|
1912 cfb128_192_loop: |
|
1913 movxtod %g1, %f56 |
|
1914 movxtod %g2, %f58 |
|
1915 fxor %f60, %f56, %f60 |
|
1916 fxor %f62, %f58, %f62 |
|
1917 |
|
1918 TWELVE_EROUNDS |
|
1919 |
|
1920 ldd [%o1], %f56 !input |
|
1921 ldd [%o1 + 8], %f58 !input |
|
1922 fxor %f60, %f56, %f60 |
|
1923 fxor %f62, %f58, %f62 |
|
1924 |
|
1925 std %f60, [%o2] |
|
1926 std %f62, [%o2 + 8] |
|
1927 |
|
1928 add %o1, 16, %o1 |
|
1929 subcc %o3, 16, %o3 |
|
1930 bne cfb128_192_loop |
|
1931 add %o2, 16, %o2 |
|
1932 |
|
1933 std %f60, [%o4] |
|
1934 retl |
|
1935 std %f62, [%o4 + 8] |
|
1936 |
|
1937 SET_SIZE(t4_aes192_cfb128_encrypt) |
|
1938 |
|
1939 |
|
1940 ENTRY(t4_aes256_cfb128_encrypt) |
|
1941 |
|
1942 ldd [%o4], %f60 ! IV |
|
1943 ldd [%o4 +8], %f62 ! IV |
|
1944 ldx [%o0], %g1 ! ks[0] |
|
1945 ldx [%o0 + 8], %g2 ! ks[1] |
|
1946 |
|
1947 cfb128_256_loop: |
|
1948 movxtod %g1, %f56 |
|
1949 movxtod %g2, %f58 |
|
1950 fxor %f60, %f56, %f60 |
|
1951 fxor %f62, %f58, %f62 |
|
1952 |
|
1953 FOURTEEN_EROUNDS |
|
1954 |
|
1955 ldd [%o1], %f56 !input |
|
1956 ldd [%o1 + 8], %f58 !input |
|
1957 fxor %f60, %f56, %f60 |
|
1958 fxor %f62, %f58, %f62 |
|
1959 |
|
1960 std %f60, [%o2] |
|
1961 std %f62, [%o2 + 8] |
|
1962 |
|
1963 add %o1, 16, %o1 |
|
1964 subcc %o3, 16, %o3 |
|
1965 bne cfb128_256_loop |
|
1966 add %o2, 16, %o2 |
|
1967 |
|
1968 std %f60, [%o4] |
|
1969 retl |
|
1970 std %f62, [%o4 + 8] |
|
1971 |
|
1972 SET_SIZE(t4_aes256_cfb128_encrypt) |
|
1973 |
|
1974 |
|
1975 ENTRY(t4_aes128_load_keys_for_decrypt) |
|
1976 |
|
1977 ldd [%o0], %f52 |
|
1978 ldd [%o0 + 0x8], %f54 |
|
1979 ldd [%o0 + 0x10], %f48 |
|
1980 ldd [%o0 + 0x18], %f50 |
|
1981 ldd [%o0 + 0x20], %f44 |
|
1982 ldd [%o0 + 0x28], %f46 |
|
1983 ldd [%o0 + 0x30], %f40 |
|
1984 ldd [%o0 + 0x38], %f42 |
|
1985 ldd [%o0 + 0x40], %f36 |
|
1986 ldd [%o0 + 0x48], %f38 |
|
1987 ldd [%o0 + 0x50], %f32 |
|
1988 ldd [%o0 + 0x58], %f34 |
|
1989 ldd [%o0 + 0x60], %f28 |
|
1990 ldd [%o0 + 0x68], %f30 |
|
1991 ldd [%o0 + 0x70], %f24 |
|
1992 ldd [%o0 + 0x78], %f26 |
|
1993 ldd [%o0 + 0x80], %f20 |
|
1994 ldd [%o0 + 0x88], %f22 |
|
1995 ldd [%o0 + 0x90], %f16 |
|
1996 retl |
|
1997 ldd [%o0 + 0x98], %f18 |
|
1998 |
|
1999 SET_SIZE(t4_aes128_load_keys_for_decrypt) |
|
2000 |
|
2001 |
|
2002 ENTRY(t4_aes192_load_keys_for_decrypt) |
|
2003 |
|
2004 ldd [%o0], %f52 |
|
2005 ldd [%o0 + 0x8], %f54 |
|
2006 ldd [%o0 + 0x10], %f48 |
|
2007 ldd [%o0 + 0x18], %f50 |
|
2008 ldd [%o0 + 0x20], %f44 |
|
2009 ldd [%o0 + 0x28], %f46 |
|
2010 ldd [%o0 + 0x30], %f40 |
|
2011 ldd [%o0 + 0x38], %f42 |
|
2012 ldd [%o0 + 0x40], %f36 |
|
2013 ldd [%o0 + 0x48], %f38 |
|
2014 ldd [%o0 + 0x50], %f32 |
|
2015 ldd [%o0 + 0x58], %f34 |
|
2016 ldd [%o0 + 0x60], %f28 |
|
2017 ldd [%o0 + 0x68], %f30 |
|
2018 ldd [%o0 + 0x70], %f24 |
|
2019 ldd [%o0 + 0x78], %f26 |
|
2020 ldd [%o0 + 0x80], %f20 |
|
2021 ldd [%o0 + 0x88], %f22 |
|
2022 ldd [%o0 + 0x90], %f16 |
|
2023 ldd [%o0 + 0x98], %f18 |
|
2024 ldd [%o0 + 0xa0], %f12 |
|
2025 ldd [%o0 + 0xa8], %f14 |
|
2026 ldd [%o0 + 0xb0], %f8 |
|
2027 retl |
|
2028 ldd [%o0 + 0xb8], %f10 |
|
2029 |
|
2030 SET_SIZE(t4_aes192_load_keys_for_decrypt) |
|
2031 |
|
2032 |
|
2033 ENTRY(t4_aes256_load_keys_for_decrypt) |
|
2034 |
|
2035 |
|
2036 ldd [%o0], %f52 |
|
2037 ldd [%o0 + 0x8], %f54 |
|
2038 ldd [%o0 + 0x10], %f48 |
|
2039 ldd [%o0 + 0x18], %f50 |
|
2040 ldd [%o0 + 0x20], %f44 |
|
2041 ldd [%o0 + 0x28], %f46 |
|
2042 ldd [%o0 + 0x30], %f40 |
|
2043 ldd [%o0 + 0x38], %f42 |
|
2044 ldd [%o0 + 0x40], %f36 |
|
2045 ldd [%o0 + 0x48], %f38 |
|
2046 ldd [%o0 + 0x50], %f32 |
|
2047 ldd [%o0 + 0x58], %f34 |
|
2048 ldd [%o0 + 0x60], %f28 |
|
2049 ldd [%o0 + 0x68], %f30 |
|
2050 ldd [%o0 + 0x70], %f24 |
|
2051 ldd [%o0 + 0x78], %f26 |
|
2052 ldd [%o0 + 0x80], %f20 |
|
2053 ldd [%o0 + 0x88], %f22 |
|
2054 ldd [%o0 + 0x90], %f16 |
|
2055 ldd [%o0 + 0x98], %f18 |
|
2056 ldd [%o0 + 0xa0], %f12 |
|
2057 ldd [%o0 + 0xa8], %f14 |
|
2058 ldd [%o0 + 0xb0], %f8 |
|
2059 ldd [%o0 + 0xb8], %f10 |
|
2060 ldd [%o0 + 0xc0], %f4 |
|
2061 ldd [%o0 + 0xc8], %f6 |
|
2062 ldd [%o0 + 0xd0], %f0 |
|
2063 retl |
|
2064 ldd [%o0 + 0xd8], %f2 |
|
2065 |
|
2066 SET_SIZE(t4_aes256_load_keys_for_decrypt) |
|
2067 |
|
2068 |
|
2069 #define TEST_PARALLEL_ECB_DECRYPT |
|
2070 #ifdef TEST_PARALLEL_ECB_DECRYPT |
|
2071 ENTRY(t4_aes128_ecb_decrypt) |
|
2072 |
|
2073 ldx [%o0 + 0xa0], %g1 !ks[last-1] |
|
2074 ldx [%o0 + 0xa8], %g2 !ks[last] |
|
2075 and %o3, 16, %o4 |
|
2076 brz %o4, ecbdec128_loop |
|
2077 nop |
|
2078 |
|
2079 ldx [%o1], %o4 |
|
2080 ldx [%o1 + 8], %o5 |
|
2081 xor %g1, %o4, %g3 !initial ARK |
|
2082 movxtod %g3, %f60 |
|
2083 xor %g2, %o5, %g3 !initial ARK |
|
2084 movxtod %g3, %f62 |
|
2085 |
|
2086 TEN_DROUNDS |
|
2087 |
|
2088 std %f60, [%o2] |
|
2089 std %f62, [%o2 + 0x8] |
|
2090 |
|
2091 add %o1, 16, %o1 |
|
2092 subcc %o3, 16, %o3 |
|
2093 be ecbdec128_loop_end |
|
2094 add %o2, 16, %o2 |
|
2095 |
|
2096 ecbdec128_loop: |
|
2097 ldx [%o1], %o4 |
|
2098 ldx [%o1 + 8], %o5 |
|
2099 xor %g1, %o4, %g3 !initial ARK |
|
2100 movxtod %g3, %f0 |
|
2101 xor %g2, %o5, %g3 !initial ARK |
|
2102 movxtod %g3, %f2 |
|
2103 ldx [%o1 + 16], %o4 |
|
2104 ldx [%o1 + 24], %o5 |
|
2105 xor %g1, %o4, %g3 !initial ARK |
|
2106 movxtod %g3, %f60 |
|
2107 xor %g2, %o5, %g3 !initial ARK |
|
2108 movxtod %g3, %f62 |
|
2109 |
|
2110 TEN_DROUNDS_2 |
|
2111 |
|
2112 std %f0, [%o2] |
|
2113 std %f2, [%o2 + 8] |
|
2114 std %f60, [%o2 + 16] |
|
2115 std %f62, [%o2 + 24] |
|
2116 |
|
2117 add %o1, 32, %o1 |
|
2118 subcc %o3, 32, %o3 |
|
2119 bne ecbdec128_loop |
|
2120 add %o2, 32, %o2 |
|
2121 ecbdec128_loop_end: |
|
2122 |
|
2123 retl |
|
2124 nop |
|
2125 |
|
2126 SET_SIZE(t4_aes128_ecb_decrypt) |
|
2127 |
|
2128 ENTRY(t4_aes192_ecb_decrypt) |
|
2129 |
|
2130 ldx [%o0 + 0xc0], %g1 !ks[last-1] |
|
2131 ldx [%o0 + 0xc8], %g2 !ks[last] |
|
2132 and %o3, 16, %o4 |
|
2133 brz %o4, ecbdec192_loop |
|
2134 nop |
|
2135 |
|
2136 ldx [%o1], %o4 |
|
2137 ldx [%o1 + 8], %o5 |
|
2138 xor %g1, %o4, %g3 !initial ARK |
|
2139 movxtod %g3, %f60 |
|
2140 xor %g2, %o5, %g3 !initial ARK |
|
2141 movxtod %g3, %f62 |
|
2142 |
|
2143 TWELVE_DROUNDS |
|
2144 |
|
2145 std %f60, [%o2] |
|
2146 std %f62, [%o2 + 0x8] |
|
2147 |
|
2148 add %o1, 16, %o1 |
|
2149 subcc %o3, 16, %o3 |
|
2150 be ecbdec192_loop_end |
|
2151 add %o2, 16, %o2 |
|
2152 |
|
2153 ecbdec192_loop: |
|
2154 ldx [%o1], %o4 |
|
2155 ldx [%o1 + 8], %o5 |
|
2156 xor %g1, %o4, %g3 !initial ARK |
|
2157 movxtod %g3, %f0 |
|
2158 xor %g2, %o5, %g3 !initial ARK |
|
2159 movxtod %g3, %f2 |
|
2160 ldx [%o1 + 16], %o4 |
|
2161 ldx [%o1 + 24], %o5 |
|
2162 xor %g1, %o4, %g3 !initial ARK |
|
2163 movxtod %g3, %f60 |
|
2164 xor %g2, %o5, %g3 !initial ARK |
|
2165 movxtod %g3, %f62 |
|
2166 |
|
2167 TWELVE_DROUNDS_2 |
|
2168 |
|
2169 std %f0, [%o2] |
|
2170 std %f2, [%o2 + 8] |
|
2171 std %f60, [%o2 + 16] |
|
2172 std %f62, [%o2 + 24] |
|
2173 |
|
2174 add %o1, 32, %o1 |
|
2175 subcc %o3, 32, %o3 |
|
2176 bne ecbdec192_loop |
|
2177 add %o2, 32, %o2 |
|
2178 ecbdec192_loop_end: |
|
2179 |
|
2180 retl |
|
2181 nop |
|
2182 |
|
2183 SET_SIZE(t4_aes192_ecb_decrypt) |
|
2184 |
|
2185 |
|
2186 ENTRY(t4_aes256_ecb_decrypt) |
|
2187 |
|
2188 ldx [%o0 + 0xe0], %g1 !ks[last-1] |
|
2189 ldx [%o0 + 0xe8], %g2 !ks[last] |
|
2190 and %o3, 16, %o4 |
|
2191 brz %o4, ecbdec256_loop |
|
2192 nop |
|
2193 |
|
2194 ldx [%o1], %o4 |
|
2195 ldx [%o1 + 8], %o5 |
|
2196 xor %g1, %o4, %g3 !initial ARK |
|
2197 movxtod %g3, %f60 |
|
2198 xor %g2, %o5, %g3 !initial ARK |
|
2199 movxtod %g3, %f62 |
|
2200 |
|
2201 FOURTEEN_DROUNDS |
|
2202 |
|
2203 std %f60, [%o2] |
|
2204 std %f62, [%o2 + 0x8] |
|
2205 |
|
2206 add %o1, 16, %o1 |
|
2207 subcc %o3, 16, %o3 |
|
2208 be ecbdec256_loop_end |
|
2209 add %o2, 16, %o2 |
|
2210 |
|
2211 ecbdec256_loop: |
|
2212 ldx [%o1], %o4 |
|
2213 ldx [%o1 + 8], %o5 |
|
2214 xor %g1, %o4, %g3 !initial ARK |
|
2215 movxtod %g3, %f20 |
|
2216 xor %g2, %o5, %g3 !initial ARK |
|
2217 movxtod %g3, %f22 |
|
2218 ldx [%o1 + 16], %o4 |
|
2219 ldx [%o1 + 24], %o5 |
|
2220 xor %g1, %o4, %g3 !initial ARK |
|
2221 movxtod %g3, %f60 |
|
2222 xor %g2, %o5, %g3 !initial ARK |
|
2223 movxtod %g3, %f62 |
|
2224 |
|
2225 FOURTEEN_DROUNDS_2 |
|
2226 |
|
2227 std %f20, [%o2] |
|
2228 std %f22, [%o2 + 8] |
|
2229 std %f60, [%o2 + 16] |
|
2230 std %f62, [%o2 + 24] |
|
2231 |
|
2232 add %o1, 32, %o1 |
|
2233 subcc %o3, 32, %o3 |
|
2234 bne ecbdec256_loop |
|
2235 add %o2, 32, %o2 |
|
2236 |
|
2237 ldd [%o0 + 0x80], %f20 |
|
2238 ldd [%o0 + 0x88], %f22 |
|
2239 |
|
2240 ecbdec256_loop_end: |
|
2241 |
|
2242 retl |
|
2243 nop |
|
2244 |
|
2245 SET_SIZE(t4_aes256_ecb_decrypt) |
|
2246 |
|
2247 #else |
|
2248 |
|
2249 ENTRY(t4_aes128_ecb_decrypt) |
|
2250 |
|
2251 ldx [%o0 + 0xa0], %g1 !ks[last-1] |
|
2252 ldx [%o0 + 0xa8], %g2 !ks[last] |
|
2253 |
|
2254 ecbdec128_loop: |
|
2255 ldx [%o1], %o4 |
|
2256 ldx [%o1 + 8], %o5 |
|
2257 xor %g1, %o4, %g3 !initial ARK |
|
2258 movxtod %g3, %f60 |
|
2259 xor %g2, %o5, %g3 !initial ARK |
|
2260 movxtod %g3, %f62 |
|
2261 |
|
2262 TEN_DROUNDS |
|
2263 |
|
2264 std %f60, [%o2] |
|
2265 std %f62, [%o2 + 0x8] |
|
2266 |
|
2267 add %o1, 16, %o1 |
|
2268 subcc %o3, 16, %o3 |
|
2269 bne ecbdec128_loop |
|
2270 add %o2, 16, %o2 |
|
2271 |
|
2272 retl |
|
2273 nop |
|
2274 |
|
2275 SET_SIZE(t4_aes128_ecb_decrypt) |
|
2276 |
|
2277 |
|
2278 ENTRY(t4_aes192_ecb_decrypt) |
|
2279 |
|
2280 ldx [%o0 + 0xc0], %g1 !ks[last-1] |
|
2281 ldx [%o0 + 0xc8], %g2 !ks[last] |
|
2282 |
|
2283 ecbdec192_loop: |
|
2284 ldx [%o1], %o4 |
|
2285 ldx [%o1 + 8], %o5 |
|
2286 xor %g1, %o4, %g3 !initial ARK |
|
2287 movxtod %g3, %f60 |
|
2288 xor %g2, %o5, %g3 !initial ARK |
|
2289 movxtod %g3, %f62 |
|
2290 |
|
2291 TWELVE_DROUNDS |
|
2292 |
|
2293 std %f60, [%o2] |
|
2294 std %f62, [%o2 + 0x8] |
|
2295 |
|
2296 add %o1, 16, %o1 |
|
2297 subcc %o3, 16, %o3 |
|
2298 bne ecbdec192_loop |
|
2299 add %o2, 16, %o2 |
|
2300 |
|
2301 retl |
|
2302 nop |
|
2303 |
|
2304 SET_SIZE(t4_aes192_ecb_decrypt) |
|
2305 |
|
2306 |
|
2307 ENTRY(t4_aes256_ecb_decrypt) |
|
2308 |
|
2309 ldx [%o0 + 0xe0], %g1 !ks[last-1] |
|
2310 ldx [%o0 + 0xe8], %g2 !ks[last] |
|
2311 |
|
2312 ecbdec256_loop: |
|
2313 ldx [%o1], %o4 |
|
2314 ldx [%o1 + 8], %o5 |
|
2315 xor %g1, %o4, %g3 !initial ARK |
|
2316 movxtod %g3, %f60 |
|
2317 xor %g2, %o5, %g3 !initial ARK |
|
2318 movxtod %g3, %f62 |
|
2319 |
|
2320 FOURTEEN_DROUNDS |
|
2321 |
|
2322 std %f60, [%o2] |
|
2323 std %f62, [%o2 + 0x8] |
|
2324 |
|
2325 add %o1, 16, %o1 |
|
2326 subcc %o3, 16, %o3 |
|
2327 bne ecbdec256_loop |
|
2328 add %o2, 16, %o2 |
|
2329 |
|
2330 retl |
|
2331 nop |
|
2332 |
|
2333 SET_SIZE(t4_aes256_ecb_decrypt) |
|
2334 |
|
2335 #endif |
|
2336 |
|
2337 #define TEST_PARALLEL_CBC_DECRYPT |
|
2338 #ifdef EST_PARALLEL_CBC_DECRYPT |
|
2339 ENTRY(t4_aes128_cbc_decrypt) |
|
2340 |
|
2341 save %sp, -SA(MINFRAME), %sp |
|
2342 ldx [%i4], %o0 !IV |
|
2343 ldx [%i4 + 8], %o1 !IV |
|
2344 ldx [%i0 + 0xa0], %o2 !ks[last-1] |
|
2345 ldx [%i0 + 0xa8], %o3 !ks[last] |
|
2346 and %i3, 16, %o4 |
|
2347 brz %o4, cbcdec128_loop |
|
2348 nop |
|
2349 |
|
2350 ldx [%i1], %o4 |
|
2351 ldx [%i1 + 8], %o5 |
|
2352 xor %o2, %o4, %g1 !initial ARK |
|
2353 movxtod %g1, %f60 |
|
2354 xor %o3, %o5, %g1 !initial ARK |
|
2355 movxtod %g1, %f62 |
|
2356 |
|
2357 TEN_DROUNDS |
|
2358 |
|
2359 movxtod %o0, %f56 |
|
2360 movxtod %o1, %f58 |
|
2361 mov %o4, %o0 !save last block as next IV |
|
2362 mov %o5, %o1 |
|
2363 fxor %f56, %f60, %f60 !add in previous IV |
|
2364 fxor %f58, %f62, %f62 |
|
2365 |
|
2366 std %f60, [%i2] |
|
2367 std %f62, [%i2 + 0x8] |
|
2368 |
|
2369 add %i1, 16, %i1 |
|
2370 subcc %i3, 16, %i3 |
|
2371 be cbcdec128_loop_end |
|
2372 add %i2, 16, %i2 |
|
2373 |
|
2374 |
|
2375 cbcdec128_loop: |
|
2376 ldx [%i1], %g4 |
|
2377 ldx [%i1 + 8], %g5 |
|
2378 xor %o2, %g4, %g1 !initial ARK |
|
2379 movxtod %g1, %f0 |
|
2380 xor %o3, %g5, %g1 !initial ARK |
|
2381 movxtod %g1, %f2 |
|
2382 |
|
2383 ldx [%i1 + 16], %o4 |
|
2384 ldx [%i1 + 24], %o5 |
|
2385 xor %o2, %o4, %g1 !initial ARK |
|
2386 movxtod %g1, %f60 |
|
2387 xor %o3, %o5, %g1 !initial ARK |
|
2388 movxtod %g1, %f62 |
|
2389 |
|
2390 TEN_DROUNDS_2 |
|
2391 |
|
2392 movxtod %o0, %f6 |
|
2393 movxtod %o1, %f4 |
|
2394 fxor %f6, %f0, %f0 !add in previous IV |
|
2395 fxor %f4, %f2, %f2 |
|
2396 |
|
2397 std %f0, [%i2] |
|
2398 std %f2, [%i2 + 8] |
|
2399 |
|
2400 movxtod %g4, %f56 |
|
2401 movxtod %g5, %f58 |
|
2402 mov %o4, %o0 !save last block as next IV |
|
2403 mov %o5, %o1 |
|
2404 fxor %f56, %f60, %f60 !add in previous IV |
|
2405 fxor %f58, %f62, %f62 |
|
2406 |
|
2407 std %f60, [%i2 + 16] |
|
2408 std %f62, [%i2 + 24] |
|
2409 |
|
2410 add %i1, 32, %i1 |
|
2411 subcc %i3, 32, %i3 |
|
2412 bne cbcdec128_loop |
|
2413 add %i2, 32, %i2 |
|
2414 |
|
2415 cbcdec128_loop_end: |
|
2416 stx %o0, [%i4] |
|
2417 stx %o1, [%i4 + 8] |
|
2418 ret |
|
2419 restore |
|
2420 |
|
2421 SET_SIZE(t4_aes128_cbc_decrypt) |
|
2422 |
|
2423 |
|
2424 ENTRY(t4_aes192_cbc_decrypt) |
|
2425 |
|
2426 save %sp, -SA(MINFRAME), %sp |
|
2427 ldx [%i4], %o0 !IV |
|
2428 ldx [%i4 + 8], %o1 !IV |
|
2429 ldx [%i0 + 0xc0], %o2 !ks[last-1] |
|
2430 ldx [%i0 + 0xc8], %o3 !ks[last] |
|
2431 and %i3, 16, %o4 |
|
2432 brz %o4, cbcdec192_loop |
|
2433 nop |
|
2434 |
|
2435 ldx [%i1], %o4 |
|
2436 ldx [%i1 + 8], %o5 |
|
2437 xor %o2, %o4, %g1 !initial ARK |
|
2438 movxtod %g1, %f60 |
|
2439 xor %o3, %o5, %g1 !initial ARK |
|
2440 movxtod %g1, %f62 |
|
2441 |
|
2442 TWELVE_DROUNDS |
|
2443 |
|
2444 movxtod %o0, %f56 |
|
2445 movxtod %o1, %f58 |
|
2446 mov %o4, %o0 !save last block as next IV |
|
2447 mov %o5, %o1 |
|
2448 fxor %f56, %f60, %f60 !add in previous IV |
|
2449 fxor %f58, %f62, %f62 |
|
2450 |
|
2451 std %f60, [%i2] |
|
2452 std %f62, [%i2 + 0x8] |
|
2453 |
|
2454 add %i1, 16, %i1 |
|
2455 subcc %i3, 16, %i3 |
|
2456 be cbcdec192_loop_end |
|
2457 add %i2, 16, %i2 |
|
2458 |
|
2459 |
|
2460 cbcdec192_loop: |
|
2461 ldx [%i1], %g4 |
|
2462 ldx [%i1 + 8], %g5 |
|
2463 xor %o2, %g4, %g1 !initial ARK |
|
2464 movxtod %g1, %f0 |
|
2465 xor %o3, %g5, %g1 !initial ARK |
|
2466 movxtod %g1, %f2 |
|
2467 |
|
2468 ldx [%i1 + 16], %o4 |
|
2469 ldx [%i1 + 24], %o5 |
|
2470 xor %o2, %o4, %g1 !initial ARK |
|
2471 movxtod %g1, %f60 |
|
2472 xor %o3, %o5, %g1 !initial ARK |
|
2473 movxtod %g1, %f62 |
|
2474 |
|
2475 TWELVE_DROUNDS_2 |
|
2476 |
|
2477 movxtod %o0, %f6 |
|
2478 movxtod %o1, %f4 |
|
2479 fxor %f6, %f0, %f0 !add in previous IV |
|
2480 fxor %f4, %f2, %f2 |
|
2481 |
|
2482 std %f0, [%i2] |
|
2483 std %f2, [%i2 + 8] |
|
2484 |
|
2485 movxtod %g4, %f56 |
|
2486 movxtod %g5, %f58 |
|
2487 mov %o4, %o0 !save last block as next IV |
|
2488 mov %o5, %o1 |
|
2489 fxor %f56, %f60, %f60 !add in previous IV |
|
2490 fxor %f58, %f62, %f62 |
|
2491 |
|
2492 std %f60, [%i2 + 16] |
|
2493 std %f62, [%i2 + 24] |
|
2494 |
|
2495 add %i1, 32, %i1 |
|
2496 subcc %i3, 32, %i3 |
|
2497 bne cbcdec192_loop |
|
2498 add %i2, 32, %i2 |
|
2499 |
|
2500 cbcdec192_loop_end: |
|
2501 stx %o0, [%i4] |
|
2502 stx %o1, [%i4 + 8] |
|
2503 ret |
|
2504 restore |
|
2505 |
|
2506 SET_SIZE(t4_aes192_cbc_decrypt) |
|
2507 |
|
2508 |
|
2509 ENTRY(t4_aes256_cbc_decrypt) |
|
2510 |
|
2511 save %sp, -SA(MINFRAME), %sp |
|
2512 mov %i0, %o0 !FOURTEEN_DROUNDS uses %o0 |
|
2513 ldx [%i4], %g2 !IV |
|
2514 ldx [%i4 + 8], %o1 !IV |
|
2515 ldx [%o0 + 0xe0], %o2 !ks[last-1] |
|
2516 ldx [%o0 + 0xe8], %o3 !ks[last] |
|
2517 and %i3, 16, %o4 |
|
2518 brz %o4, cbcdec256_loop |
|
2519 nop |
|
2520 |
|
2521 ldx [%i1], %o4 |
|
2522 ldx [%i1 + 8], %o5 |
|
2523 xor %o2, %o4, %g1 !initial ARK |
|
2524 movxtod %g1, %f60 |
|
2525 xor %o3, %o5, %g1 !initial ARK |
|
2526 movxtod %g1, %f62 |
|
2527 |
|
2528 FOURTEEN_DROUNDS |
|
2529 |
|
2530 movxtod %g2, %f56 |
|
2531 movxtod %o1, %f58 |
|
2532 mov %o4, %g2 !save last block as next IV |
|
2533 mov %o5, %o1 |
|
2534 fxor %f56, %f60, %f60 !add in previous IV |
|
2535 fxor %f58, %f62, %f62 |
|
2536 |
|
2537 std %f60, [%i2] |
|
2538 std %f62, [%i2 + 0x8] |
|
2539 |
|
2540 add %i1, 16, %i1 |
|
2541 subcc %i3, 16, %i3 |
|
2542 be cbcdec256_loop_end |
|
2543 add %i2, 16, %i2 |
|
2544 |
|
2545 |
|
2546 cbcdec256_loop: |
|
2547 ldx [%i1], %g4 |
|
2548 ldx [%i1 + 8], %g5 |
|
2549 xor %o2, %g4, %g1 !initial ARK |
|
2550 movxtod %g1, %f20 |
|
2551 xor %o3, %g5, %g1 !initial ARK |
|
2552 movxtod %g1, %f22 |
|
2553 |
|
2554 ldx [%i1 + 16], %o4 |
|
2555 ldx [%i1 + 24], %o5 |
|
2556 xor %o2, %o4, %g1 !initial ARK |
|
2557 movxtod %g1, %f60 |
|
2558 xor %o3, %o5, %g1 !initial ARK |
|
2559 movxtod %g1, %f62 |
|
2560 |
|
2561 FOURTEEN_DROUNDS_2 |
|
2562 |
|
2563 movxtod %g2, %f56 |
|
2564 movxtod %o1, %f58 |
|
2565 fxor %f56, %f20, %f20 !add in previous IV |
|
2566 fxor %f58, %f22, %f22 |
|
2567 |
|
2568 std %f20, [%i2] |
|
2569 std %f22, [%i2 + 8] |
|
2570 |
|
2571 movxtod %g4, %f56 |
|
2572 movxtod %g5, %f58 |
|
2573 mov %o4, %g2 !save last block as next IV |
|
2574 mov %o5, %o1 |
|
2575 fxor %f56, %f60, %f60 !add in previous IV |
|
2576 fxor %f58, %f62, %f62 |
|
2577 |
|
2578 std %f60, [%i2 + 16] |
|
2579 std %f62, [%i2 + 24] |
|
2580 |
|
2581 add %i1, 32, %i1 |
|
2582 subcc %i3, 32, %i3 |
|
2583 bne cbcdec256_loop |
|
2584 add %i2, 32, %i2 |
|
2585 |
|
2586 ldd [%o0 + 0x80], %f20 |
|
2587 ldd [%o0 + 0x88], %f22 |
|
2588 |
|
2589 cbcdec256_loop_end: |
|
2590 stx %g2, [%i4] |
|
2591 stx %o1, [%i4 + 8] |
|
2592 ret |
|
2593 restore |
|
2594 |
|
2595 SET_SIZE(t4_aes256_cbc_decrypt) |
|
2596 |
|
2597 #else |
|
2598 |
|
2599 ENTRY(t4_aes128_cbc_decrypt) |
|
2600 |
|
2601 save %sp, -SA(MINFRAME), %sp |
|
2602 ldx [%i4], %o0 !IV |
|
2603 ldx [%i4 + 8], %o1 !IV |
|
2604 ldx [%i0 + 0xa0], %o2 !ks[last-1] |
|
2605 ldx [%i0 + 0xa8], %o3 !ks[last] |
|
2606 |
|
2607 cbcdec128_loop: |
|
2608 ldx [%i1], %o4 |
|
2609 ldx [%i1 + 8], %o5 |
|
2610 xor %o2, %o4, %g1 !initial ARK |
|
2611 movxtod %g1, %f60 |
|
2612 xor %o3, %o5, %g1 !initial ARK |
|
2613 movxtod %g1, %f62 |
|
2614 |
|
2615 TEN_DROUNDS |
|
2616 |
|
2617 movxtod %o0, %f56 |
|
2618 movxtod %o1, %f58 |
|
2619 mov %o4, %o0 !save last block as next IV |
|
2620 mov %o5, %o1 |
|
2621 fxor %f56, %f60, %f60 !add in previous IV |
|
2622 fxor %f58, %f62, %f62 |
|
2623 |
|
2624 std %f60, [%i2] |
|
2625 std %f62, [%i2 + 0x8] |
|
2626 |
|
2627 add %i1, 16, %i1 |
|
2628 subcc %i3, 16, %i3 |
|
2629 bne cbcdec128_loop |
|
2630 add %i2, 16, %i2 |
|
2631 |
|
2632 stx %o0, [%i4] |
|
2633 stx %o1, [%i4 + 8] |
|
2634 ret |
|
2635 restore |
|
2636 |
|
2637 SET_SIZE(t4_aes128_cbc_decrypt) |
|
2638 |
|
2639 |
|
2640 ENTRY(t4_aes192_cbc_decrypt) |
|
2641 |
|
2642 save %sp, -SA(MINFRAME), %sp |
|
2643 ldx [%i4], %o0 !IV |
|
2644 ldx [%i4 + 8], %o1 !IV |
|
2645 ldx [%i0 + 0xc0], %o2 !ks[last-1] |
|
2646 ldx [%i0 + 0xc8], %o3 !ks[last] |
|
2647 |
|
2648 cbcdec192_loop: |
|
2649 ldx [%i1], %o4 |
|
2650 ldx [%i1 + 8], %o5 |
|
2651 xor %o2, %o4, %g1 !initial ARK |
|
2652 movxtod %g1, %f60 |
|
2653 xor %o3, %o5, %g1 !initial ARK |
|
2654 movxtod %g1, %f62 |
|
2655 |
|
2656 TWELVE_DROUNDS |
|
2657 |
|
2658 movxtod %o0, %f56 |
|
2659 movxtod %o1, %f58 |
|
2660 mov %o4, %o0 !save last block as next IV |
|
2661 mov %o5, %o1 |
|
2662 fxor %f56, %f60, %f60 !add in previous IV |
|
2663 fxor %f58, %f62, %f62 |
|
2664 |
|
2665 std %f60, [%i2] |
|
2666 std %f62, [%i2 + 0x8] |
|
2667 |
|
2668 add %i1, 16, %i1 |
|
2669 subcc %i3, 16, %i3 |
|
2670 bne cbcdec192_loop |
|
2671 add %i2, 16, %i2 |
|
2672 |
|
2673 stx %o0, [%i4] |
|
2674 stx %o1, [%i4 + 8] |
|
2675 ret |
|
2676 restore |
|
2677 |
|
2678 SET_SIZE(t4_aes192_cbc_decrypt) |
|
2679 |
|
2680 |
|
2681 ENTRY(t4_aes256_cbc_decrypt) |
|
2682 |
|
2683 save %sp, -SA(MINFRAME), %sp |
|
2684 ldx [%i4], %o0 !IV |
|
2685 ldx [%i4 + 8], %o1 !IV |
|
2686 ldx [%i0 + 0xe0], %o2 !ks[last-1] |
|
2687 ldx [%i0 + 0xe8], %o3 !ks[last] |
|
2688 |
|
2689 cbcdec256_loop: |
|
2690 ldx [%i1], %o4 |
|
2691 ldx [%i1 + 8], %o5 |
|
2692 xor %o2, %o4, %g1 !initial ARK |
|
2693 movxtod %g1, %f60 |
|
2694 xor %o3, %o5, %g1 !initial ARK |
|
2695 movxtod %g1, %f62 |
|
2696 |
|
2697 FOURTEEN_DROUNDS |
|
2698 |
|
2699 movxtod %o0, %f56 |
|
2700 movxtod %o1, %f58 |
|
2701 mov %o4, %o0 !save last block as next IV |
|
2702 mov %o5, %o1 |
|
2703 fxor %f56, %f60, %f60 !add in previous IV |
|
2704 fxor %f58, %f62, %f62 |
|
2705 |
|
2706 std %f60, [%i2] |
|
2707 std %f62, [%i2 + 0x8] |
|
2708 |
|
2709 add %i1, 16, %i1 |
|
2710 subcc %i3, 16, %i3 |
|
2711 bne cbcdec256_loop |
|
2712 add %i2, 16, %i2 |
|
2713 |
|
2714 stx %o0, [%i4] |
|
2715 stx %o1, [%i4 + 8] |
|
2716 ret |
|
2717 restore |
|
2718 |
|
2719 SET_SIZE(t4_aes256_cbc_decrypt) |
|
2720 |
|
2721 #endif |
|
2722 |
|
2723 #define TEST_PARALLEL_CFB128_DECRYPT |
|
2724 #ifdef TEST_PARALLEL_CFB128_DECRYPT |
|
2725 |
|
2726 ENTRY(t4_aes128_cfb128_decrypt) |
|
2727 |
|
2728 ldd [%o4], %f56 !IV |
|
2729 ldd [%o4 + 8], %f58 !IV |
|
2730 ldx [%o0], %g1 ! ks[0] |
|
2731 ldx [%o0 + 8], %g2 ! ks[1] |
|
2732 and %o3, 16, %o5 |
|
2733 brz %o5, cfb128dec_128_loop |
|
2734 |
|
2735 movxtod %g1, %f60 |
|
2736 movxtod %g2, %f62 |
|
2737 fxor %f60, %f56, %f60 |
|
2738 fxor %f62, %f58, %f62 |
|
2739 |
|
2740 /* CFB mode uses encryption for the decrypt operation */ |
|
2741 TEN_EROUNDS |
|
2742 |
|
2743 ldd [%o1], %f56 !input |
|
2744 ldd [%o1 + 8], %f58 !input |
|
2745 fxor %f60, %f56, %f60 |
|
2746 fxor %f62, %f58, %f62 |
|
2747 |
|
2748 std %f60, [%o2] |
|
2749 std %f62, [%o2 + 8] |
|
2750 |
|
2751 add %o1, 16, %o1 |
|
2752 subcc %o3, 16, %o3 |
|
2753 be cfb128dec_128_loop_end |
|
2754 add %o2, 16, %o2 |
|
2755 |
|
2756 cfb128dec_128_loop: |
|
2757 ldd [%o1], %f6 !input |
|
2758 ldd [%o1 + 8], %f4 !input |
|
2759 movxtod %g1, %f60 |
|
2760 movxtod %g2, %f62 |
|
2761 fxor %f60, %f6, %f0 |
|
2762 fxor %f62, %f4, %f2 |
|
2763 fxor %f60, %f56, %f60 |
|
2764 fxor %f62, %f58, %f62 |
|
2765 |
|
2766 /* CFB mode uses encryption for the decrypt operation */ |
|
2767 TEN_EROUNDS_2 |
|
2768 |
|
2769 ldd [%o1], %f6 !input |
|
2770 ldd [%o1 + 8], %f4 !input |
|
2771 ldd [%o1 + 16], %f56 !input |
|
2772 ldd [%o1 + 24], %f58 !input |
|
2773 |
|
2774 fxor %f60, %f6, %f6 |
|
2775 fxor %f62, %f4, %f4 |
|
2776 fxor %f0, %f56, %f60 |
|
2777 fxor %f2, %f58, %f62 |
|
2778 |
|
2779 std %f6, [%o2] |
|
2780 std %f4, [%o2 + 8] |
|
2781 std %f60, [%o2 + 16] |
|
2782 std %f62, [%o2 + 24] |
|
2783 |
|
2784 add %o1, 32, %o1 |
|
2785 subcc %o3, 32, %o3 |
|
2786 bne cfb128dec_128_loop |
|
2787 add %o2, 32, %o2 |
|
2788 |
|
2789 cfb128dec_128_loop_end: |
|
2790 std %f56, [%o4] |
|
2791 retl |
|
2792 std %f58, [%o4 + 8] |
|
2793 |
|
2794 SET_SIZE(t4_aes128_cfb128_decrypt) |
|
2795 |
|
2796 |
|
2797 ENTRY(t4_aes192_cfb128_decrypt) |
|
2798 |
|
2799 ldd [%o4], %f56 !IV |
|
2800 ldd [%o4 + 8], %f58 !IV |
|
2801 ldx [%o0], %g1 ! ks[0] |
|
2802 ldx [%o0 + 8], %g2 ! ks[1] |
|
2803 and %o3, 16, %o5 |
|
2804 brz %o5, cfb128dec_192_loop |
|
2805 |
|
2806 movxtod %g1, %f60 |
|
2807 movxtod %g2, %f62 |
|
2808 fxor %f60, %f56, %f60 |
|
2809 fxor %f62, %f58, %f62 |
|
2810 |
|
2811 /* CFB mode uses encryption for the decrypt operation */ |
|
2812 TWELVE_EROUNDS |
|
2813 |
|
2814 ldd [%o1], %f56 !input |
|
2815 ldd [%o1 + 8], %f58 !input |
|
2816 fxor %f60, %f56, %f60 |
|
2817 fxor %f62, %f58, %f62 |
|
2818 |
|
2819 std %f60, [%o2] |
|
2820 std %f62, [%o2 + 8] |
|
2821 |
|
2822 add %o1, 16, %o1 |
|
2823 subcc %o3, 16, %o3 |
|
2824 be cfb128dec_192_loop_end |
|
2825 add %o2, 16, %o2 |
|
2826 |
|
2827 cfb128dec_192_loop: |
|
2828 ldd [%o1], %f6 !input |
|
2829 ldd [%o1 + 8], %f4 !input |
|
2830 movxtod %g1, %f60 |
|
2831 movxtod %g2, %f62 |
|
2832 fxor %f60, %f6, %f0 |
|
2833 fxor %f62, %f4, %f2 |
|
2834 fxor %f60, %f56, %f60 |
|
2835 fxor %f62, %f58, %f62 |
|
2836 |
|
2837 /* CFB mode uses encryption for the decrypt operation */ |
|
2838 TWELVE_EROUNDS_2 |
|
2839 |
|
2840 ldd [%o1], %f6 !input |
|
2841 ldd [%o1 + 8], %f4 !input |
|
2842 ldd [%o1 + 16], %f56 !input |
|
2843 ldd [%o1 + 24], %f58 !input |
|
2844 |
|
2845 fxor %f60, %f6, %f6 |
|
2846 fxor %f62, %f4, %f4 |
|
2847 fxor %f0, %f56, %f60 |
|
2848 fxor %f2, %f58, %f62 |
|
2849 |
|
2850 std %f6, [%o2] |
|
2851 std %f4, [%o2 + 8] |
|
2852 std %f60, [%o2 + 16] |
|
2853 std %f62, [%o2 + 24] |
|
2854 |
|
2855 add %o1, 32, %o1 |
|
2856 subcc %o3, 32, %o3 |
|
2857 bne cfb128dec_192_loop |
|
2858 add %o2, 32, %o2 |
|
2859 |
|
2860 cfb128dec_192_loop_end: |
|
2861 std %f56, [%o4] |
|
2862 retl |
|
2863 std %f58, [%o4 + 8] |
|
2864 |
|
2865 SET_SIZE(t4_aes192_cfb128_decrypt) |
|
2866 |
|
2867 |
|
2868 ENTRY(t4_aes256_cfb128_decrypt) |
|
2869 |
|
2870 ldd [%o4], %f56 !IV |
|
2871 ldd [%o4 + 8], %f58 !IV |
|
2872 ldx [%o0], %g1 ! ks[0] |
|
2873 ldx [%o0 + 8], %g2 ! ks[1] |
|
2874 and %o3, 16, %o5 |
|
2875 brz %o5, cfb128dec_256_loop |
|
2876 |
|
2877 movxtod %g1, %f60 |
|
2878 movxtod %g2, %f62 |
|
2879 fxor %f60, %f56, %f60 |
|
2880 fxor %f62, %f58, %f62 |
|
2881 |
|
2882 /* CFB mode uses encryption for the decrypt operation */ |
|
2883 FOURTEEN_EROUNDS |
|
2884 |
|
2885 ldd [%o1], %f56 !input |
|
2886 ldd [%o1 + 8], %f58 !input |
|
2887 fxor %f60, %f56, %f60 |
|
2888 fxor %f62, %f58, %f62 |
|
2889 |
|
2890 std %f60, [%o2] |
|
2891 std %f62, [%o2 + 8] |
|
2892 |
|
2893 add %o1, 16, %o1 |
|
2894 subcc %o3, 16, %o3 |
|
2895 be cfb128dec_256_loop_end |
|
2896 add %o2, 16, %o2 |
|
2897 |
|
2898 cfb128dec_256_loop: |
|
2899 ldd [%o1], %f20 !input |
|
2900 ldd [%o1 + 8], %f22 !input |
|
2901 movxtod %g1, %f60 |
|
2902 movxtod %g2, %f62 |
|
2903 fxor %f60, %f20, %f20 |
|
2904 fxor %f62, %f22, %f22 |
|
2905 fxor %f60, %f56, %f60 |
|
2906 fxor %f62, %f58, %f62 |
|
2907 |
|
2908 /* CFB mode uses encryption for the decrypt operation */ |
|
2909 FOURTEEN_EROUNDS_2 |
|
2910 |
|
2911 ldd [%o1 + 16], %f56 !input |
|
2912 ldd [%o1 + 24], %f58 !input |
|
2913 fxor %f20, %f56, %f20 |
|
2914 fxor %f22, %f58, %f22 |
|
2915 std %f20, [%o2 + 16] |
|
2916 std %f22, [%o2 + 24] |
|
2917 |
|
2918 ldd [%o1], %f20 !input |
|
2919 ldd [%o1 + 8], %f22 !input |
|
2920 |
|
2921 fxor %f60, %f20, %f20 |
|
2922 fxor %f62, %f22, %f22 |
|
2923 |
|
2924 std %f20, [%o2] |
|
2925 std %f22, [%o2 + 8] |
|
2926 |
|
2927 add %o1, 32, %o1 |
|
2928 subcc %o3, 32, %o3 |
|
2929 bne cfb128dec_256_loop |
|
2930 add %o2, 32, %o2 |
|
2931 |
|
2932 ldd [%o0 + 0x60], %f20 |
|
2933 ldd [%o0 + 0x68], %f22 |
|
2934 |
|
2935 cfb128dec_256_loop_end: |
|
2936 std %f56, [%o4] |
|
2937 retl |
|
2938 std %f58, [%o4 + 8] |
|
2939 |
|
2940 SET_SIZE(t4_aes256_cfb128_decrypt) |
|
2941 |
|
2942 #else |
|
2943 ENTRY(t4_aes128_cfb128_decrypt) |
|
2944 |
|
2945 ldd [%o4], %f56 !IV |
|
2946 ldd [%o4 + 8], %f58 !IV |
|
2947 ldx [%o0], %g1 ! ks[0] |
|
2948 ldx [%o0 + 8], %g2 ! ks[1] |
|
2949 |
|
2950 cfb128dec_128_loop: |
|
2951 movxtod %g1, %f60 |
|
2952 movxtod %g2, %f62 |
|
2953 fxor %f60, %f56, %f60 |
|
2954 fxor %f62, %f58, %f62 |
|
2955 |
|
2956 /* CFB mode uses encryption for the decrypt operation */ |
|
2957 TEN_EROUNDS |
|
2958 |
|
2959 ldd [%o1], %f56 !input |
|
2960 ldd [%o1 + 8], %f58 !input |
|
2961 fxor %f60, %f56, %f60 |
|
2962 fxor %f62, %f58, %f62 |
|
2963 |
|
2964 std %f60, [%o2] |
|
2965 std %f62, [%o2 + 8] |
|
2966 |
|
2967 add %o1, 16, %o1 |
|
2968 subcc %o3, 16, %o3 |
|
2969 bne cfb128dec_128_loop |
|
2970 add %o2, 16, %o2 |
|
2971 |
|
2972 std %f56, [%o4] |
|
2973 retl |
|
2974 std %f58, [%o4 + 8] |
|
2975 |
|
2976 SET_SIZE(t4_aes128_cfb128_decrypt) |
|
2977 |
|
2978 |
|
2979 ENTRY(t4_aes192_cfb128_decrypt) |
|
2980 |
|
2981 ldd [%o4], %f56 !IV |
|
2982 ldd [%o4 + 8], %f58 !IV |
|
2983 ldx [%o0], %g1 ! ks[0] |
|
2984 ldx [%o0 + 8], %g2 ! ks[1] |
|
2985 |
|
2986 cfb128dec_192_loop: |
|
2987 movxtod %g1, %f60 |
|
2988 movxtod %g2, %f62 |
|
2989 fxor %f60, %f56, %f60 |
|
2990 fxor %f62, %f58, %f62 |
|
2991 |
|
2992 /* CFB mode uses encryption for the decrypt operation */ |
|
2993 TWELVE_EROUNDS |
|
2994 |
|
2995 ldd [%o1], %f56 !input |
|
2996 ldd [%o1 + 8], %f58 !input |
|
2997 fxor %f60, %f56, %f60 |
|
2998 fxor %f62, %f58, %f62 |
|
2999 |
|
3000 std %f60, [%o2] |
|
3001 std %f62, [%o2 + 8] |
|
3002 |
|
3003 add %o1, 16, %o1 |
|
3004 subcc %o3, 16, %o3 |
|
3005 bne cfb128dec_192_loop |
|
3006 add %o2, 16, %o2 |
|
3007 |
|
3008 std %f56, [%o4] |
|
3009 retl |
|
3010 std %f58, [%o4 + 8] |
|
3011 |
|
3012 SET_SIZE(t4_aes192_cfb128_decrypt) |
|
3013 |
|
3014 |
|
3015 ENTRY(t4_aes256_cfb128_decrypt) |
|
3016 |
|
3017 ldd [%o4], %f56 !IV |
|
3018 ldd [%o4 + 8], %f58 !IV |
|
3019 ldx [%o0], %g1 ! ks[0] |
|
3020 ldx [%o0 + 8], %g2 ! ks[1] |
|
3021 |
|
3022 cfb128dec_256_loop: |
|
3023 movxtod %g1, %f60 |
|
3024 movxtod %g2, %f62 |
|
3025 fxor %f60, %f56, %f60 |
|
3026 fxor %f62, %f58, %f62 |
|
3027 |
|
3028 /* CFB mode uses encryption for the decrypt operation */ |
|
3029 FOURTEEN_EROUNDS |
|
3030 |
|
3031 ldd [%o1], %f56 !input |
|
3032 ldd [%o1 + 8], %f58 !input |
|
3033 fxor %f60, %f56, %f60 |
|
3034 fxor %f62, %f58, %f62 |
|
3035 |
|
3036 std %f60, [%o2] |
|
3037 std %f62, [%o2 + 8] |
|
3038 |
|
3039 add %o1, 16, %o1 |
|
3040 subcc %o3, 16, %o3 |
|
3041 bne cfb128dec_256_loop |
|
3042 add %o2, 16, %o2 |
|
3043 |
|
3044 std %f56, [%o4] |
|
3045 retl |
|
3046 std %f58, [%o4 + 8] |
|
3047 |
|
3048 SET_SIZE(t4_aes256_cfb128_decrypt) |
|
3049 |
|
3050 #endif |
|
3051 |
|
3052 #endif /* lint || __lint */ |