2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
28 #include "include/kernel_functions.c"
29 #include "types_amd.c"
30 #include "common_amd.c"
33 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
34 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
38 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
39 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
43 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
44 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
47 #define PERM_OP(a,b,tt,n,m) \
57 #define HPERM_OP(a,tt,n,m) \
63 tt = tt >> (16 + n); \
69 PERM_OP (r, l, tt, 4, 0x0f0f0f0f); \
70 PERM_OP (l, r, tt, 16, 0x0000ffff); \
71 PERM_OP (r, l, tt, 2, 0x33333333); \
72 PERM_OP (l, r, tt, 8, 0x00ff00ff); \
73 PERM_OP (r, l, tt, 1, 0x55555555); \
78 PERM_OP (l, r, tt, 1, 0x55555555); \
79 PERM_OP (r, l, tt, 8, 0x00ff00ff); \
80 PERM_OP (l, r, tt, 2, 0x33333333); \
81 PERM_OP (r, l, tt, 16, 0x0000ffff); \
82 PERM_OP (l, r, tt, 4, 0x0f0f0f0f); \
85 __constant u32 c_SPtrans[8][64] =
88 0x00820200, 0x00020000, 0x80800000, 0x80820200,
89 0x00800000, 0x80020200, 0x80020000, 0x80800000,
90 0x80020200, 0x00820200, 0x00820000, 0x80000200,
91 0x80800200, 0x00800000, 0x00000000, 0x80020000,
92 0x00020000, 0x80000000, 0x00800200, 0x00020200,
93 0x80820200, 0x00820000, 0x80000200, 0x00800200,
94 0x80000000, 0x00000200, 0x00020200, 0x80820000,
95 0x00000200, 0x80800200, 0x80820000, 0x00000000,
96 0x00000000, 0x80820200, 0x00800200, 0x80020000,
97 0x00820200, 0x00020000, 0x80000200, 0x00800200,
98 0x80820000, 0x00000200, 0x00020200, 0x80800000,
99 0x80020200, 0x80000000, 0x80800000, 0x00820000,
100 0x80820200, 0x00020200, 0x00820000, 0x80800200,
101 0x00800000, 0x80000200, 0x80020000, 0x00000000,
102 0x00020000, 0x00800000, 0x80800200, 0x00820200,
103 0x80000000, 0x80820000, 0x00000200, 0x80020200,
105 0x10042004, 0x00000000, 0x00042000, 0x10040000,
106 0x10000004, 0x00002004, 0x10002000, 0x00042000,
107 0x00002000, 0x10040004, 0x00000004, 0x10002000,
108 0x00040004, 0x10042000, 0x10040000, 0x00000004,
109 0x00040000, 0x10002004, 0x10040004, 0x00002000,
110 0x00042004, 0x10000000, 0x00000000, 0x00040004,
111 0x10002004, 0x00042004, 0x10042000, 0x10000004,
112 0x10000000, 0x00040000, 0x00002004, 0x10042004,
113 0x00040004, 0x10042000, 0x10002000, 0x00042004,
114 0x10042004, 0x00040004, 0x10000004, 0x00000000,
115 0x10000000, 0x00002004, 0x00040000, 0x10040004,
116 0x00002000, 0x10000000, 0x00042004, 0x10002004,
117 0x10042000, 0x00002000, 0x00000000, 0x10000004,
118 0x00000004, 0x10042004, 0x00042000, 0x10040000,
119 0x10040004, 0x00040000, 0x00002004, 0x10002000,
120 0x10002004, 0x00000004, 0x10040000, 0x00042000,
122 0x41000000, 0x01010040, 0x00000040, 0x41000040,
123 0x40010000, 0x01000000, 0x41000040, 0x00010040,
124 0x01000040, 0x00010000, 0x01010000, 0x40000000,
125 0x41010040, 0x40000040, 0x40000000, 0x41010000,
126 0x00000000, 0x40010000, 0x01010040, 0x00000040,
127 0x40000040, 0x41010040, 0x00010000, 0x41000000,
128 0x41010000, 0x01000040, 0x40010040, 0x01010000,
129 0x00010040, 0x00000000, 0x01000000, 0x40010040,
130 0x01010040, 0x00000040, 0x40000000, 0x00010000,
131 0x40000040, 0x40010000, 0x01010000, 0x41000040,
132 0x00000000, 0x01010040, 0x00010040, 0x41010000,
133 0x40010000, 0x01000000, 0x41010040, 0x40000000,
134 0x40010040, 0x41000000, 0x01000000, 0x41010040,
135 0x00010000, 0x01000040, 0x41000040, 0x00010040,
136 0x01000040, 0x00000000, 0x41010000, 0x40000040,
137 0x41000000, 0x40010040, 0x00000040, 0x01010000,
139 0x00100402, 0x04000400, 0x00000002, 0x04100402,
140 0x00000000, 0x04100000, 0x04000402, 0x00100002,
141 0x04100400, 0x04000002, 0x04000000, 0x00000402,
142 0x04000002, 0x00100402, 0x00100000, 0x04000000,
143 0x04100002, 0x00100400, 0x00000400, 0x00000002,
144 0x00100400, 0x04000402, 0x04100000, 0x00000400,
145 0x00000402, 0x00000000, 0x00100002, 0x04100400,
146 0x04000400, 0x04100002, 0x04100402, 0x00100000,
147 0x04100002, 0x00000402, 0x00100000, 0x04000002,
148 0x00100400, 0x04000400, 0x00000002, 0x04100000,
149 0x04000402, 0x00000000, 0x00000400, 0x00100002,
150 0x00000000, 0x04100002, 0x04100400, 0x00000400,
151 0x04000000, 0x04100402, 0x00100402, 0x00100000,
152 0x04100402, 0x00000002, 0x04000400, 0x00100402,
153 0x00100002, 0x00100400, 0x04100000, 0x04000402,
154 0x00000402, 0x04000000, 0x04000002, 0x04100400,
156 0x02000000, 0x00004000, 0x00000100, 0x02004108,
157 0x02004008, 0x02000100, 0x00004108, 0x02004000,
158 0x00004000, 0x00000008, 0x02000008, 0x00004100,
159 0x02000108, 0x02004008, 0x02004100, 0x00000000,
160 0x00004100, 0x02000000, 0x00004008, 0x00000108,
161 0x02000100, 0x00004108, 0x00000000, 0x02000008,
162 0x00000008, 0x02000108, 0x02004108, 0x00004008,
163 0x02004000, 0x00000100, 0x00000108, 0x02004100,
164 0x02004100, 0x02000108, 0x00004008, 0x02004000,
165 0x00004000, 0x00000008, 0x02000008, 0x02000100,
166 0x02000000, 0x00004100, 0x02004108, 0x00000000,
167 0x00004108, 0x02000000, 0x00000100, 0x00004008,
168 0x02000108, 0x00000100, 0x00000000, 0x02004108,
169 0x02004008, 0x02004100, 0x00000108, 0x00004000,
170 0x00004100, 0x02004008, 0x02000100, 0x00000108,
171 0x00000008, 0x00004108, 0x02004000, 0x02000008,
173 0x20000010, 0x00080010, 0x00000000, 0x20080800,
174 0x00080010, 0x00000800, 0x20000810, 0x00080000,
175 0x00000810, 0x20080810, 0x00080800, 0x20000000,
176 0x20000800, 0x20000010, 0x20080000, 0x00080810,
177 0x00080000, 0x20000810, 0x20080010, 0x00000000,
178 0x00000800, 0x00000010, 0x20080800, 0x20080010,
179 0x20080810, 0x20080000, 0x20000000, 0x00000810,
180 0x00000010, 0x00080800, 0x00080810, 0x20000800,
181 0x00000810, 0x20000000, 0x20000800, 0x00080810,
182 0x20080800, 0x00080010, 0x00000000, 0x20000800,
183 0x20000000, 0x00000800, 0x20080010, 0x00080000,
184 0x00080010, 0x20080810, 0x00080800, 0x00000010,
185 0x20080810, 0x00080800, 0x00080000, 0x20000810,
186 0x20000010, 0x20080000, 0x00080810, 0x00000000,
187 0x00000800, 0x20000010, 0x20000810, 0x20080800,
188 0x20080000, 0x00000810, 0x00000010, 0x20080010,
190 0x00001000, 0x00000080, 0x00400080, 0x00400001,
191 0x00401081, 0x00001001, 0x00001080, 0x00000000,
192 0x00400000, 0x00400081, 0x00000081, 0x00401000,
193 0x00000001, 0x00401080, 0x00401000, 0x00000081,
194 0x00400081, 0x00001000, 0x00001001, 0x00401081,
195 0x00000000, 0x00400080, 0x00400001, 0x00001080,
196 0x00401001, 0x00001081, 0x00401080, 0x00000001,
197 0x00001081, 0x00401001, 0x00000080, 0x00400000,
198 0x00001081, 0x00401000, 0x00401001, 0x00000081,
199 0x00001000, 0x00000080, 0x00400000, 0x00401001,
200 0x00400081, 0x00001081, 0x00001080, 0x00000000,
201 0x00000080, 0x00400001, 0x00000001, 0x00400080,
202 0x00000000, 0x00400081, 0x00400080, 0x00001080,
203 0x00000081, 0x00001000, 0x00401081, 0x00400000,
204 0x00401080, 0x00000001, 0x00001001, 0x00401081,
205 0x00400001, 0x00401080, 0x00401000, 0x00001001,
207 0x08200020, 0x08208000, 0x00008020, 0x00000000,
208 0x08008000, 0x00200020, 0x08200000, 0x08208020,
209 0x00000020, 0x08000000, 0x00208000, 0x00008020,
210 0x00208020, 0x08008020, 0x08000020, 0x08200000,
211 0x00008000, 0x00208020, 0x00200020, 0x08008000,
212 0x08208020, 0x08000020, 0x00000000, 0x00208000,
213 0x08000000, 0x00200000, 0x08008020, 0x08200020,
214 0x00200000, 0x00008000, 0x08208000, 0x00000020,
215 0x00200000, 0x00008000, 0x08000020, 0x08208020,
216 0x00008020, 0x08000000, 0x00000000, 0x00208000,
217 0x08200020, 0x08008020, 0x08008000, 0x00200020,
218 0x08208000, 0x00000020, 0x00200020, 0x08008000,
219 0x08208020, 0x00200000, 0x08200000, 0x08000020,
220 0x00208000, 0x00008020, 0x08008020, 0x08200000,
221 0x00000020, 0x08208000, 0x00208020, 0x00000000,
222 0x08000000, 0x08200020, 0x00008000, 0x00208020
225 __constant u32 c_skb[8][64] =
227 /* for C bits (numbered as per FIPS 46) 1 2 3 4 5 6 */
228 0x00000000, 0x00000010, 0x20000000, 0x20000010,
229 0x00010000, 0x00010010, 0x20010000, 0x20010010,
230 0x00000800, 0x00000810, 0x20000800, 0x20000810,
231 0x00010800, 0x00010810, 0x20010800, 0x20010810,
232 0x00000020, 0x00000030, 0x20000020, 0x20000030,
233 0x00010020, 0x00010030, 0x20010020, 0x20010030,
234 0x00000820, 0x00000830, 0x20000820, 0x20000830,
235 0x00010820, 0x00010830, 0x20010820, 0x20010830,
236 0x00080000, 0x00080010, 0x20080000, 0x20080010,
237 0x00090000, 0x00090010, 0x20090000, 0x20090010,
238 0x00080800, 0x00080810, 0x20080800, 0x20080810,
239 0x00090800, 0x00090810, 0x20090800, 0x20090810,
240 0x00080020, 0x00080030, 0x20080020, 0x20080030,
241 0x00090020, 0x00090030, 0x20090020, 0x20090030,
242 0x00080820, 0x00080830, 0x20080820, 0x20080830,
243 0x00090820, 0x00090830, 0x20090820, 0x20090830,
244 /* for C bits (numbered as per FIPS 46) 7 8 10 11 12 13 */
245 0x00000000, 0x02000000, 0x00002000, 0x02002000,
246 0x00200000, 0x02200000, 0x00202000, 0x02202000,
247 0x00000004, 0x02000004, 0x00002004, 0x02002004,
248 0x00200004, 0x02200004, 0x00202004, 0x02202004,
249 0x00000400, 0x02000400, 0x00002400, 0x02002400,
250 0x00200400, 0x02200400, 0x00202400, 0x02202400,
251 0x00000404, 0x02000404, 0x00002404, 0x02002404,
252 0x00200404, 0x02200404, 0x00202404, 0x02202404,
253 0x10000000, 0x12000000, 0x10002000, 0x12002000,
254 0x10200000, 0x12200000, 0x10202000, 0x12202000,
255 0x10000004, 0x12000004, 0x10002004, 0x12002004,
256 0x10200004, 0x12200004, 0x10202004, 0x12202004,
257 0x10000400, 0x12000400, 0x10002400, 0x12002400,
258 0x10200400, 0x12200400, 0x10202400, 0x12202400,
259 0x10000404, 0x12000404, 0x10002404, 0x12002404,
260 0x10200404, 0x12200404, 0x10202404, 0x12202404,
261 /* for C bits (numbered as per FIPS 46) 14 15 16 17 19 20 */
262 0x00000000, 0x00000001, 0x00040000, 0x00040001,
263 0x01000000, 0x01000001, 0x01040000, 0x01040001,
264 0x00000002, 0x00000003, 0x00040002, 0x00040003,
265 0x01000002, 0x01000003, 0x01040002, 0x01040003,
266 0x00000200, 0x00000201, 0x00040200, 0x00040201,
267 0x01000200, 0x01000201, 0x01040200, 0x01040201,
268 0x00000202, 0x00000203, 0x00040202, 0x00040203,
269 0x01000202, 0x01000203, 0x01040202, 0x01040203,
270 0x08000000, 0x08000001, 0x08040000, 0x08040001,
271 0x09000000, 0x09000001, 0x09040000, 0x09040001,
272 0x08000002, 0x08000003, 0x08040002, 0x08040003,
273 0x09000002, 0x09000003, 0x09040002, 0x09040003,
274 0x08000200, 0x08000201, 0x08040200, 0x08040201,
275 0x09000200, 0x09000201, 0x09040200, 0x09040201,
276 0x08000202, 0x08000203, 0x08040202, 0x08040203,
277 0x09000202, 0x09000203, 0x09040202, 0x09040203,
278 /* for C bits (numbered as per FIPS 46) 21 23 24 26 27 28 */
279 0x00000000, 0x00100000, 0x00000100, 0x00100100,
280 0x00000008, 0x00100008, 0x00000108, 0x00100108,
281 0x00001000, 0x00101000, 0x00001100, 0x00101100,
282 0x00001008, 0x00101008, 0x00001108, 0x00101108,
283 0x04000000, 0x04100000, 0x04000100, 0x04100100,
284 0x04000008, 0x04100008, 0x04000108, 0x04100108,
285 0x04001000, 0x04101000, 0x04001100, 0x04101100,
286 0x04001008, 0x04101008, 0x04001108, 0x04101108,
287 0x00020000, 0x00120000, 0x00020100, 0x00120100,
288 0x00020008, 0x00120008, 0x00020108, 0x00120108,
289 0x00021000, 0x00121000, 0x00021100, 0x00121100,
290 0x00021008, 0x00121008, 0x00021108, 0x00121108,
291 0x04020000, 0x04120000, 0x04020100, 0x04120100,
292 0x04020008, 0x04120008, 0x04020108, 0x04120108,
293 0x04021000, 0x04121000, 0x04021100, 0x04121100,
294 0x04021008, 0x04121008, 0x04021108, 0x04121108,
295 /* for D bits (numbered as per FIPS 46) 1 2 3 4 5 6 */
296 0x00000000, 0x10000000, 0x00010000, 0x10010000,
297 0x00000004, 0x10000004, 0x00010004, 0x10010004,
298 0x20000000, 0x30000000, 0x20010000, 0x30010000,
299 0x20000004, 0x30000004, 0x20010004, 0x30010004,
300 0x00100000, 0x10100000, 0x00110000, 0x10110000,
301 0x00100004, 0x10100004, 0x00110004, 0x10110004,
302 0x20100000, 0x30100000, 0x20110000, 0x30110000,
303 0x20100004, 0x30100004, 0x20110004, 0x30110004,
304 0x00001000, 0x10001000, 0x00011000, 0x10011000,
305 0x00001004, 0x10001004, 0x00011004, 0x10011004,
306 0x20001000, 0x30001000, 0x20011000, 0x30011000,
307 0x20001004, 0x30001004, 0x20011004, 0x30011004,
308 0x00101000, 0x10101000, 0x00111000, 0x10111000,
309 0x00101004, 0x10101004, 0x00111004, 0x10111004,
310 0x20101000, 0x30101000, 0x20111000, 0x30111000,
311 0x20101004, 0x30101004, 0x20111004, 0x30111004,
312 /* for D bits (numbered as per FIPS 46) 8 9 11 12 13 14 */
313 0x00000000, 0x08000000, 0x00000008, 0x08000008,
314 0x00000400, 0x08000400, 0x00000408, 0x08000408,
315 0x00020000, 0x08020000, 0x00020008, 0x08020008,
316 0x00020400, 0x08020400, 0x00020408, 0x08020408,
317 0x00000001, 0x08000001, 0x00000009, 0x08000009,
318 0x00000401, 0x08000401, 0x00000409, 0x08000409,
319 0x00020001, 0x08020001, 0x00020009, 0x08020009,
320 0x00020401, 0x08020401, 0x00020409, 0x08020409,
321 0x02000000, 0x0A000000, 0x02000008, 0x0A000008,
322 0x02000400, 0x0A000400, 0x02000408, 0x0A000408,
323 0x02020000, 0x0A020000, 0x02020008, 0x0A020008,
324 0x02020400, 0x0A020400, 0x02020408, 0x0A020408,
325 0x02000001, 0x0A000001, 0x02000009, 0x0A000009,
326 0x02000401, 0x0A000401, 0x02000409, 0x0A000409,
327 0x02020001, 0x0A020001, 0x02020009, 0x0A020009,
328 0x02020401, 0x0A020401, 0x02020409, 0x0A020409,
329 /* for D bits (numbered as per FIPS 46) 16 17 18 19 20 21 */
330 0x00000000, 0x00000100, 0x00080000, 0x00080100,
331 0x01000000, 0x01000100, 0x01080000, 0x01080100,
332 0x00000010, 0x00000110, 0x00080010, 0x00080110,
333 0x01000010, 0x01000110, 0x01080010, 0x01080110,
334 0x00200000, 0x00200100, 0x00280000, 0x00280100,
335 0x01200000, 0x01200100, 0x01280000, 0x01280100,
336 0x00200010, 0x00200110, 0x00280010, 0x00280110,
337 0x01200010, 0x01200110, 0x01280010, 0x01280110,
338 0x00000200, 0x00000300, 0x00080200, 0x00080300,
339 0x01000200, 0x01000300, 0x01080200, 0x01080300,
340 0x00000210, 0x00000310, 0x00080210, 0x00080310,
341 0x01000210, 0x01000310, 0x01080210, 0x01080310,
342 0x00200200, 0x00200300, 0x00280200, 0x00280300,
343 0x01200200, 0x01200300, 0x01280200, 0x01280300,
344 0x00200210, 0x00200310, 0x00280210, 0x00280310,
345 0x01200210, 0x01200310, 0x01280210, 0x01280310,
346 /* for D bits (numbered as per FIPS 46) 22 23 24 25 27 28 */
347 0x00000000, 0x04000000, 0x00040000, 0x04040000,
348 0x00000002, 0x04000002, 0x00040002, 0x04040002,
349 0x00002000, 0x04002000, 0x00042000, 0x04042000,
350 0x00002002, 0x04002002, 0x00042002, 0x04042002,
351 0x00000020, 0x04000020, 0x00040020, 0x04040020,
352 0x00000022, 0x04000022, 0x00040022, 0x04040022,
353 0x00002020, 0x04002020, 0x00042020, 0x04042020,
354 0x00002022, 0x04002022, 0x00042022, 0x04042022,
355 0x00000800, 0x04000800, 0x00040800, 0x04040800,
356 0x00000802, 0x04000802, 0x00040802, 0x04040802,
357 0x00002800, 0x04002800, 0x00042800, 0x04042800,
358 0x00002802, 0x04002802, 0x00042802, 0x04042802,
359 0x00000820, 0x04000820, 0x00040820, 0x04040820,
360 0x00000822, 0x04000822, 0x00040822, 0x04040822,
361 0x00002820, 0x04002820, 0x00042820, 0x04042820,
362 0x00002822, 0x04002822, 0x00042822, 0x04042822
366 #define BOX(i,n,S) (u32x) ((S)[(n)][(i)])
370 #define BOX(i,n,S) (u32x) ((S)[(n)][(i).s0], (S)[(n)][(i).s1])
374 #define BOX(i,n,S) (u32x) ((S)[(n)][(i).s0], (S)[(n)][(i).s1], (S)[(n)][(i).s2], (S)[(n)][(i).s3])
377 static void _des_crypt_keysetup (u32x c, u32x d, u32x Kc[16], u32x Kd[16], __local u32 s_skb[8][64])
381 PERM_OP (d, c, tt, 4, 0x0f0f0f0f);
382 HPERM_OP (c, tt, 2, 0xcccc0000);
383 HPERM_OP (d, tt, 2, 0xcccc0000);
384 PERM_OP (d, c, tt, 1, 0x55555555);
385 PERM_OP (c, d, tt, 8, 0x00ff00ff);
386 PERM_OP (d, c, tt, 1, 0x55555555);
388 d = ((d & 0x000000ff) << 16)
389 | ((d & 0x0000ff00) << 0)
390 | ((d & 0x00ff0000) >> 16)
391 | ((c & 0xf0000000) >> 4);
396 for (u32 i = 0; i < 16; i++)
398 const u32 shifts3s0[16] = { 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1 };
399 const u32 shifts3s1[16] = { 27, 27, 26, 26, 26, 26, 26, 26, 27, 26, 26, 26, 26, 26, 26, 27 };
401 c = c >> shifts3s0[i] | c << shifts3s1[i];
402 d = d >> shifts3s0[i] | d << shifts3s1[i];
407 const u32x c00 = (c >> 0) & 0x0000003f;
408 const u32x c06 = (c >> 6) & 0x00383003;
409 const u32x c07 = (c >> 7) & 0x0000003c;
410 const u32x c13 = (c >> 13) & 0x0000060f;
411 const u32x c20 = (c >> 20) & 0x00000001;
413 u32x s = BOX (((c00 >> 0) & 0xff), 0, s_skb)
414 | BOX (((c06 >> 0) & 0xff)
415 |((c07 >> 0) & 0xff), 1, s_skb)
416 | BOX (((c13 >> 0) & 0xff)
417 |((c06 >> 8) & 0xff), 2, s_skb)
418 | BOX (((c20 >> 0) & 0xff)
420 |((c06 >> 16) & 0xff), 3, s_skb);
422 const u32x d00 = (d >> 0) & 0x00003c3f;
423 const u32x d07 = (d >> 7) & 0x00003f03;
424 const u32x d21 = (d >> 21) & 0x0000000f;
425 const u32x d22 = (d >> 22) & 0x00000030;
427 u32x t = BOX (((d00 >> 0) & 0xff), 4, s_skb)
428 | BOX (((d07 >> 0) & 0xff)
429 |((d00 >> 8) & 0xff), 5, s_skb)
430 | BOX (((d07 >> 8) & 0xff), 6, s_skb)
431 | BOX (((d21 >> 0) & 0xff)
432 |((d22 >> 0) & 0xff), 7, s_skb);
434 Kc[i] = ((t << 16) | (s & 0x0000ffff));
435 Kd[i] = ((s >> 16) | (t & 0xffff0000));
439 static void _des_crypt_encrypt (u32x iv[2], u32 mask, u32 rounds, u32x Kc[16], u32x Kd[16], __local u32 s_SPtrans[8][64])
443 const u32 E0 = ((mask >> 0) & 0x003f)
444 | ((mask >> 4) & 0x3f00);
445 const u32 E1 = ((mask >> 2) & 0x03f0)
446 | ((mask >> 6) & 0xf000)
447 | ((mask >> 22) & 0x0003);
452 for (u32 i = 0; i < rounds; i++)
455 for (u32 j = 0; j < 16; j++)
458 u32x t = r ^ (r >> 16);
482 const u32x um = u & 0x3f3f3f3f;
483 const u32x tm = t & 0x3f3f3f3f;
485 l ^= BOX (((um >> 0) & 0xff), 0, s_SPtrans)
486 | BOX (((um >> 8) & 0xff), 2, s_SPtrans)
487 | BOX (((um >> 16) & 0xff), 4, s_SPtrans)
488 | BOX (((um >> 24) & 0xff), 6, s_SPtrans)
489 | BOX (((tm >> 0) & 0xff), 1, s_SPtrans)
490 | BOX (((tm >> 8) & 0xff), 3, s_SPtrans)
491 | BOX (((tm >> 16) & 0xff), 5, s_SPtrans)
492 | BOX (((tm >> 24) & 0xff), 7, s_SPtrans);
508 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12400_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bsdicrypt_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
514 const u32 gid = get_global_id (0);
515 const u32 lid = get_local_id (0);
521 __local u32 s_SPtrans[8][64];
523 s_SPtrans[0][lid] = c_SPtrans[0][lid];
524 s_SPtrans[1][lid] = c_SPtrans[1][lid];
525 s_SPtrans[2][lid] = c_SPtrans[2][lid];
526 s_SPtrans[3][lid] = c_SPtrans[3][lid];
527 s_SPtrans[4][lid] = c_SPtrans[4][lid];
528 s_SPtrans[5][lid] = c_SPtrans[5][lid];
529 s_SPtrans[6][lid] = c_SPtrans[6][lid];
530 s_SPtrans[7][lid] = c_SPtrans[7][lid];
532 __local u32 s_skb[8][64];
534 s_skb[0][lid] = c_skb[0][lid];
535 s_skb[1][lid] = c_skb[1][lid];
536 s_skb[2][lid] = c_skb[2][lid];
537 s_skb[3][lid] = c_skb[3][lid];
538 s_skb[4][lid] = c_skb[4][lid];
539 s_skb[5][lid] = c_skb[5][lid];
540 s_skb[6][lid] = c_skb[6][lid];
541 s_skb[7][lid] = c_skb[7][lid];
543 barrier (CLK_LOCAL_MEM_FENCE);
545 if (gid >= gid_max) return;
553 w[ 0] = pws[gid].i[ 0];
554 w[ 1] = pws[gid].i[ 1];
555 w[ 2] = pws[gid].i[ 2];
556 w[ 3] = pws[gid].i[ 3];
557 w[ 4] = pws[gid].i[ 4];
558 w[ 5] = pws[gid].i[ 5];
559 w[ 6] = pws[gid].i[ 6];
560 w[ 7] = pws[gid].i[ 7];
561 w[ 8] = pws[gid].i[ 8];
562 w[ 9] = pws[gid].i[ 9];
563 w[10] = pws[gid].i[10];
564 w[11] = pws[gid].i[11];
565 w[12] = pws[gid].i[12];
566 w[13] = pws[gid].i[13];
567 w[14] = pws[gid].i[14];
568 w[15] = pws[gid].i[15];
570 u32 pw_len = pws[gid].pw_len;
580 out[0] = (w[0] << 1) & 0xfefefefe;
581 out[1] = (w[1] << 1) & 0xfefefefe;
583 for (u32 i = 8, j = 2; i < pw_len; i += 8, j += 2)
585 _des_crypt_keysetup (out[0], out[1], Kc, Kd, s_skb);
587 IP (out[0], out[1], tt);
589 out[0] = rotr32 (out[0], 31);
590 out[1] = rotr32 (out[1], 31);
592 _des_crypt_encrypt (out, 0, 1, Kc, Kd, s_SPtrans);
594 out[0] = rotl32 (out[0], 31);
595 out[1] = rotl32 (out[1], 31);
597 FP (out[1], out[0], tt);
599 const u32 R = (w[j + 0] << 1) & 0xfefefefe;
600 const u32 L = (w[j + 1] << 1) & 0xfefefefe;
607 out[0] = (out[0] & 0xfefefefe) >> 1;
608 out[1] = (out[1] & 0xfefefefe) >> 1;
610 out[0] = (out[0] << 1) & 0xfefefefe;
611 out[1] = (out[1] << 1) & 0xfefefefe;
614 _des_crypt_keysetup (out[0], out[1], Kc, Kd, s_skb);
616 tmps[gid].Kc[ 0] = Kc[ 0];
617 tmps[gid].Kc[ 1] = Kc[ 1];
618 tmps[gid].Kc[ 2] = Kc[ 2];
619 tmps[gid].Kc[ 3] = Kc[ 3];
620 tmps[gid].Kc[ 4] = Kc[ 4];
621 tmps[gid].Kc[ 5] = Kc[ 5];
622 tmps[gid].Kc[ 6] = Kc[ 6];
623 tmps[gid].Kc[ 7] = Kc[ 7];
624 tmps[gid].Kc[ 8] = Kc[ 8];
625 tmps[gid].Kc[ 9] = Kc[ 9];
626 tmps[gid].Kc[10] = Kc[10];
627 tmps[gid].Kc[11] = Kc[11];
628 tmps[gid].Kc[12] = Kc[12];
629 tmps[gid].Kc[13] = Kc[13];
630 tmps[gid].Kc[14] = Kc[14];
631 tmps[gid].Kc[15] = Kc[15];
633 tmps[gid].Kd[ 0] = Kd[ 0];
634 tmps[gid].Kd[ 1] = Kd[ 1];
635 tmps[gid].Kd[ 2] = Kd[ 2];
636 tmps[gid].Kd[ 3] = Kd[ 3];
637 tmps[gid].Kd[ 4] = Kd[ 4];
638 tmps[gid].Kd[ 5] = Kd[ 5];
639 tmps[gid].Kd[ 6] = Kd[ 6];
640 tmps[gid].Kd[ 7] = Kd[ 7];
641 tmps[gid].Kd[ 8] = Kd[ 8];
642 tmps[gid].Kd[ 9] = Kd[ 9];
643 tmps[gid].Kd[10] = Kd[10];
644 tmps[gid].Kd[11] = Kd[11];
645 tmps[gid].Kd[12] = Kd[12];
646 tmps[gid].Kd[13] = Kd[13];
647 tmps[gid].Kd[14] = Kd[14];
648 tmps[gid].Kd[15] = Kd[15];
654 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12400_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bsdicrypt_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
660 const u32 gid = get_global_id (0);
661 const u32 lid = get_local_id (0);
667 __local u32 s_SPtrans[8][64];
669 s_SPtrans[0][lid] = c_SPtrans[0][lid];
670 s_SPtrans[1][lid] = c_SPtrans[1][lid];
671 s_SPtrans[2][lid] = c_SPtrans[2][lid];
672 s_SPtrans[3][lid] = c_SPtrans[3][lid];
673 s_SPtrans[4][lid] = c_SPtrans[4][lid];
674 s_SPtrans[5][lid] = c_SPtrans[5][lid];
675 s_SPtrans[6][lid] = c_SPtrans[6][lid];
676 s_SPtrans[7][lid] = c_SPtrans[7][lid];
678 barrier (CLK_LOCAL_MEM_FENCE);
680 if (gid >= gid_max) return;
684 Kc[ 0] = tmps[gid].Kc[ 0];
685 Kc[ 1] = tmps[gid].Kc[ 1];
686 Kc[ 2] = tmps[gid].Kc[ 2];
687 Kc[ 3] = tmps[gid].Kc[ 3];
688 Kc[ 4] = tmps[gid].Kc[ 4];
689 Kc[ 5] = tmps[gid].Kc[ 5];
690 Kc[ 6] = tmps[gid].Kc[ 6];
691 Kc[ 7] = tmps[gid].Kc[ 7];
692 Kc[ 8] = tmps[gid].Kc[ 8];
693 Kc[ 9] = tmps[gid].Kc[ 9];
694 Kc[10] = tmps[gid].Kc[10];
695 Kc[11] = tmps[gid].Kc[11];
696 Kc[12] = tmps[gid].Kc[12];
697 Kc[13] = tmps[gid].Kc[13];
698 Kc[14] = tmps[gid].Kc[14];
699 Kc[15] = tmps[gid].Kc[15];
703 Kd[ 0] = tmps[gid].Kd[ 0];
704 Kd[ 1] = tmps[gid].Kd[ 1];
705 Kd[ 2] = tmps[gid].Kd[ 2];
706 Kd[ 3] = tmps[gid].Kd[ 3];
707 Kd[ 4] = tmps[gid].Kd[ 4];
708 Kd[ 5] = tmps[gid].Kd[ 5];
709 Kd[ 6] = tmps[gid].Kd[ 6];
710 Kd[ 7] = tmps[gid].Kd[ 7];
711 Kd[ 8] = tmps[gid].Kd[ 8];
712 Kd[ 9] = tmps[gid].Kd[ 9];
713 Kd[10] = tmps[gid].Kd[10];
714 Kd[11] = tmps[gid].Kd[11];
715 Kd[12] = tmps[gid].Kd[12];
716 Kd[13] = tmps[gid].Kd[13];
717 Kd[14] = tmps[gid].Kd[14];
718 Kd[15] = tmps[gid].Kd[15];
722 iv[0] = tmps[gid].iv[0];
723 iv[1] = tmps[gid].iv[1];
725 const u32 mask = salt_bufs[salt_pos].salt_buf[0];
727 _des_crypt_encrypt (iv, mask, loop_cnt, Kc, Kd, s_SPtrans);
729 tmps[gid].Kc[ 0] = Kc[ 0];
730 tmps[gid].Kc[ 1] = Kc[ 1];
731 tmps[gid].Kc[ 2] = Kc[ 2];
732 tmps[gid].Kc[ 3] = Kc[ 3];
733 tmps[gid].Kc[ 4] = Kc[ 4];
734 tmps[gid].Kc[ 5] = Kc[ 5];
735 tmps[gid].Kc[ 6] = Kc[ 6];
736 tmps[gid].Kc[ 7] = Kc[ 7];
737 tmps[gid].Kc[ 8] = Kc[ 8];
738 tmps[gid].Kc[ 9] = Kc[ 9];
739 tmps[gid].Kc[10] = Kc[10];
740 tmps[gid].Kc[11] = Kc[11];
741 tmps[gid].Kc[12] = Kc[12];
742 tmps[gid].Kc[13] = Kc[13];
743 tmps[gid].Kc[14] = Kc[14];
744 tmps[gid].Kc[15] = Kc[15];
746 tmps[gid].Kd[ 0] = Kd[ 0];
747 tmps[gid].Kd[ 1] = Kd[ 1];
748 tmps[gid].Kd[ 2] = Kd[ 2];
749 tmps[gid].Kd[ 3] = Kd[ 3];
750 tmps[gid].Kd[ 4] = Kd[ 4];
751 tmps[gid].Kd[ 5] = Kd[ 5];
752 tmps[gid].Kd[ 6] = Kd[ 6];
753 tmps[gid].Kd[ 7] = Kd[ 7];
754 tmps[gid].Kd[ 8] = Kd[ 8];
755 tmps[gid].Kd[ 9] = Kd[ 9];
756 tmps[gid].Kd[10] = Kd[10];
757 tmps[gid].Kd[11] = Kd[11];
758 tmps[gid].Kd[12] = Kd[12];
759 tmps[gid].Kd[13] = Kd[13];
760 tmps[gid].Kd[14] = Kd[14];
761 tmps[gid].Kd[15] = Kd[15];
763 tmps[gid].iv[0] = iv[0];
764 tmps[gid].iv[1] = iv[1];
767 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m12400_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global bsdicrypt_tmp_t *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
773 const u32 gid = get_global_id (0);
775 if (gid >= gid_max) return;
777 const u32 lid = get_local_id (0);
779 const u32x r0 = tmps[gid].iv[0];
780 const u32x r1 = tmps[gid].iv[1];
786 #include VECT_COMPARE_M