2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
16 #include "include/kernel_functions.c"
17 #include "types_ocl.c"
20 #define COMPARE_S "check_single_comp4.c"
21 #define COMPARE_M "check_multi_comp4.c"
23 #define PERM_OP(a,b,tt,n,m) \
33 #define HPERM_OP(a,tt,n,m) \
39 tt = tt >> (16 + n); \
45 PERM_OP (r, l, tt, 4, 0x0f0f0f0f); \
46 PERM_OP (l, r, tt, 16, 0x0000ffff); \
47 PERM_OP (r, l, tt, 2, 0x33333333); \
48 PERM_OP (l, r, tt, 8, 0x00ff00ff); \
49 PERM_OP (r, l, tt, 1, 0x55555555); \
54 PERM_OP (l, r, tt, 1, 0x55555555); \
55 PERM_OP (r, l, tt, 8, 0x00ff00ff); \
56 PERM_OP (l, r, tt, 2, 0x33333333); \
57 PERM_OP (r, l, tt, 16, 0x0000ffff); \
58 PERM_OP (l, r, tt, 4, 0x0f0f0f0f); \
61 __constant u32 c_SPtrans[8][64] =
64 0x00820200, 0x00020000, 0x80800000, 0x80820200,
65 0x00800000, 0x80020200, 0x80020000, 0x80800000,
66 0x80020200, 0x00820200, 0x00820000, 0x80000200,
67 0x80800200, 0x00800000, 0x00000000, 0x80020000,
68 0x00020000, 0x80000000, 0x00800200, 0x00020200,
69 0x80820200, 0x00820000, 0x80000200, 0x00800200,
70 0x80000000, 0x00000200, 0x00020200, 0x80820000,
71 0x00000200, 0x80800200, 0x80820000, 0x00000000,
72 0x00000000, 0x80820200, 0x00800200, 0x80020000,
73 0x00820200, 0x00020000, 0x80000200, 0x00800200,
74 0x80820000, 0x00000200, 0x00020200, 0x80800000,
75 0x80020200, 0x80000000, 0x80800000, 0x00820000,
76 0x80820200, 0x00020200, 0x00820000, 0x80800200,
77 0x00800000, 0x80000200, 0x80020000, 0x00000000,
78 0x00020000, 0x00800000, 0x80800200, 0x00820200,
79 0x80000000, 0x80820000, 0x00000200, 0x80020200,
81 0x10042004, 0x00000000, 0x00042000, 0x10040000,
82 0x10000004, 0x00002004, 0x10002000, 0x00042000,
83 0x00002000, 0x10040004, 0x00000004, 0x10002000,
84 0x00040004, 0x10042000, 0x10040000, 0x00000004,
85 0x00040000, 0x10002004, 0x10040004, 0x00002000,
86 0x00042004, 0x10000000, 0x00000000, 0x00040004,
87 0x10002004, 0x00042004, 0x10042000, 0x10000004,
88 0x10000000, 0x00040000, 0x00002004, 0x10042004,
89 0x00040004, 0x10042000, 0x10002000, 0x00042004,
90 0x10042004, 0x00040004, 0x10000004, 0x00000000,
91 0x10000000, 0x00002004, 0x00040000, 0x10040004,
92 0x00002000, 0x10000000, 0x00042004, 0x10002004,
93 0x10042000, 0x00002000, 0x00000000, 0x10000004,
94 0x00000004, 0x10042004, 0x00042000, 0x10040000,
95 0x10040004, 0x00040000, 0x00002004, 0x10002000,
96 0x10002004, 0x00000004, 0x10040000, 0x00042000,
98 0x41000000, 0x01010040, 0x00000040, 0x41000040,
99 0x40010000, 0x01000000, 0x41000040, 0x00010040,
100 0x01000040, 0x00010000, 0x01010000, 0x40000000,
101 0x41010040, 0x40000040, 0x40000000, 0x41010000,
102 0x00000000, 0x40010000, 0x01010040, 0x00000040,
103 0x40000040, 0x41010040, 0x00010000, 0x41000000,
104 0x41010000, 0x01000040, 0x40010040, 0x01010000,
105 0x00010040, 0x00000000, 0x01000000, 0x40010040,
106 0x01010040, 0x00000040, 0x40000000, 0x00010000,
107 0x40000040, 0x40010000, 0x01010000, 0x41000040,
108 0x00000000, 0x01010040, 0x00010040, 0x41010000,
109 0x40010000, 0x01000000, 0x41010040, 0x40000000,
110 0x40010040, 0x41000000, 0x01000000, 0x41010040,
111 0x00010000, 0x01000040, 0x41000040, 0x00010040,
112 0x01000040, 0x00000000, 0x41010000, 0x40000040,
113 0x41000000, 0x40010040, 0x00000040, 0x01010000,
115 0x00100402, 0x04000400, 0x00000002, 0x04100402,
116 0x00000000, 0x04100000, 0x04000402, 0x00100002,
117 0x04100400, 0x04000002, 0x04000000, 0x00000402,
118 0x04000002, 0x00100402, 0x00100000, 0x04000000,
119 0x04100002, 0x00100400, 0x00000400, 0x00000002,
120 0x00100400, 0x04000402, 0x04100000, 0x00000400,
121 0x00000402, 0x00000000, 0x00100002, 0x04100400,
122 0x04000400, 0x04100002, 0x04100402, 0x00100000,
123 0x04100002, 0x00000402, 0x00100000, 0x04000002,
124 0x00100400, 0x04000400, 0x00000002, 0x04100000,
125 0x04000402, 0x00000000, 0x00000400, 0x00100002,
126 0x00000000, 0x04100002, 0x04100400, 0x00000400,
127 0x04000000, 0x04100402, 0x00100402, 0x00100000,
128 0x04100402, 0x00000002, 0x04000400, 0x00100402,
129 0x00100002, 0x00100400, 0x04100000, 0x04000402,
130 0x00000402, 0x04000000, 0x04000002, 0x04100400,
132 0x02000000, 0x00004000, 0x00000100, 0x02004108,
133 0x02004008, 0x02000100, 0x00004108, 0x02004000,
134 0x00004000, 0x00000008, 0x02000008, 0x00004100,
135 0x02000108, 0x02004008, 0x02004100, 0x00000000,
136 0x00004100, 0x02000000, 0x00004008, 0x00000108,
137 0x02000100, 0x00004108, 0x00000000, 0x02000008,
138 0x00000008, 0x02000108, 0x02004108, 0x00004008,
139 0x02004000, 0x00000100, 0x00000108, 0x02004100,
140 0x02004100, 0x02000108, 0x00004008, 0x02004000,
141 0x00004000, 0x00000008, 0x02000008, 0x02000100,
142 0x02000000, 0x00004100, 0x02004108, 0x00000000,
143 0x00004108, 0x02000000, 0x00000100, 0x00004008,
144 0x02000108, 0x00000100, 0x00000000, 0x02004108,
145 0x02004008, 0x02004100, 0x00000108, 0x00004000,
146 0x00004100, 0x02004008, 0x02000100, 0x00000108,
147 0x00000008, 0x00004108, 0x02004000, 0x02000008,
149 0x20000010, 0x00080010, 0x00000000, 0x20080800,
150 0x00080010, 0x00000800, 0x20000810, 0x00080000,
151 0x00000810, 0x20080810, 0x00080800, 0x20000000,
152 0x20000800, 0x20000010, 0x20080000, 0x00080810,
153 0x00080000, 0x20000810, 0x20080010, 0x00000000,
154 0x00000800, 0x00000010, 0x20080800, 0x20080010,
155 0x20080810, 0x20080000, 0x20000000, 0x00000810,
156 0x00000010, 0x00080800, 0x00080810, 0x20000800,
157 0x00000810, 0x20000000, 0x20000800, 0x00080810,
158 0x20080800, 0x00080010, 0x00000000, 0x20000800,
159 0x20000000, 0x00000800, 0x20080010, 0x00080000,
160 0x00080010, 0x20080810, 0x00080800, 0x00000010,
161 0x20080810, 0x00080800, 0x00080000, 0x20000810,
162 0x20000010, 0x20080000, 0x00080810, 0x00000000,
163 0x00000800, 0x20000010, 0x20000810, 0x20080800,
164 0x20080000, 0x00000810, 0x00000010, 0x20080010,
166 0x00001000, 0x00000080, 0x00400080, 0x00400001,
167 0x00401081, 0x00001001, 0x00001080, 0x00000000,
168 0x00400000, 0x00400081, 0x00000081, 0x00401000,
169 0x00000001, 0x00401080, 0x00401000, 0x00000081,
170 0x00400081, 0x00001000, 0x00001001, 0x00401081,
171 0x00000000, 0x00400080, 0x00400001, 0x00001080,
172 0x00401001, 0x00001081, 0x00401080, 0x00000001,
173 0x00001081, 0x00401001, 0x00000080, 0x00400000,
174 0x00001081, 0x00401000, 0x00401001, 0x00000081,
175 0x00001000, 0x00000080, 0x00400000, 0x00401001,
176 0x00400081, 0x00001081, 0x00001080, 0x00000000,
177 0x00000080, 0x00400001, 0x00000001, 0x00400080,
178 0x00000000, 0x00400081, 0x00400080, 0x00001080,
179 0x00000081, 0x00001000, 0x00401081, 0x00400000,
180 0x00401080, 0x00000001, 0x00001001, 0x00401081,
181 0x00400001, 0x00401080, 0x00401000, 0x00001001,
183 0x08200020, 0x08208000, 0x00008020, 0x00000000,
184 0x08008000, 0x00200020, 0x08200000, 0x08208020,
185 0x00000020, 0x08000000, 0x00208000, 0x00008020,
186 0x00208020, 0x08008020, 0x08000020, 0x08200000,
187 0x00008000, 0x00208020, 0x00200020, 0x08008000,
188 0x08208020, 0x08000020, 0x00000000, 0x00208000,
189 0x08000000, 0x00200000, 0x08008020, 0x08200020,
190 0x00200000, 0x00008000, 0x08208000, 0x00000020,
191 0x00200000, 0x00008000, 0x08000020, 0x08208020,
192 0x00008020, 0x08000000, 0x00000000, 0x00208000,
193 0x08200020, 0x08008020, 0x08008000, 0x00200020,
194 0x08208000, 0x00000020, 0x00200020, 0x08008000,
195 0x08208020, 0x00200000, 0x08200000, 0x08000020,
196 0x00208000, 0x00008020, 0x08008020, 0x08200000,
197 0x00000020, 0x08208000, 0x00208020, 0x00000000,
198 0x08000000, 0x08200020, 0x00008000, 0x00208020
201 __constant u32 c_skb[8][64] =
203 /* for C bits (numbered as per FIPS 46) 1 2 3 4 5 6 */
204 0x00000000, 0x00000010, 0x20000000, 0x20000010,
205 0x00010000, 0x00010010, 0x20010000, 0x20010010,
206 0x00000800, 0x00000810, 0x20000800, 0x20000810,
207 0x00010800, 0x00010810, 0x20010800, 0x20010810,
208 0x00000020, 0x00000030, 0x20000020, 0x20000030,
209 0x00010020, 0x00010030, 0x20010020, 0x20010030,
210 0x00000820, 0x00000830, 0x20000820, 0x20000830,
211 0x00010820, 0x00010830, 0x20010820, 0x20010830,
212 0x00080000, 0x00080010, 0x20080000, 0x20080010,
213 0x00090000, 0x00090010, 0x20090000, 0x20090010,
214 0x00080800, 0x00080810, 0x20080800, 0x20080810,
215 0x00090800, 0x00090810, 0x20090800, 0x20090810,
216 0x00080020, 0x00080030, 0x20080020, 0x20080030,
217 0x00090020, 0x00090030, 0x20090020, 0x20090030,
218 0x00080820, 0x00080830, 0x20080820, 0x20080830,
219 0x00090820, 0x00090830, 0x20090820, 0x20090830,
220 /* for C bits (numbered as per FIPS 46) 7 8 10 11 12 13 */
221 0x00000000, 0x02000000, 0x00002000, 0x02002000,
222 0x00200000, 0x02200000, 0x00202000, 0x02202000,
223 0x00000004, 0x02000004, 0x00002004, 0x02002004,
224 0x00200004, 0x02200004, 0x00202004, 0x02202004,
225 0x00000400, 0x02000400, 0x00002400, 0x02002400,
226 0x00200400, 0x02200400, 0x00202400, 0x02202400,
227 0x00000404, 0x02000404, 0x00002404, 0x02002404,
228 0x00200404, 0x02200404, 0x00202404, 0x02202404,
229 0x10000000, 0x12000000, 0x10002000, 0x12002000,
230 0x10200000, 0x12200000, 0x10202000, 0x12202000,
231 0x10000004, 0x12000004, 0x10002004, 0x12002004,
232 0x10200004, 0x12200004, 0x10202004, 0x12202004,
233 0x10000400, 0x12000400, 0x10002400, 0x12002400,
234 0x10200400, 0x12200400, 0x10202400, 0x12202400,
235 0x10000404, 0x12000404, 0x10002404, 0x12002404,
236 0x10200404, 0x12200404, 0x10202404, 0x12202404,
237 /* for C bits (numbered as per FIPS 46) 14 15 16 17 19 20 */
238 0x00000000, 0x00000001, 0x00040000, 0x00040001,
239 0x01000000, 0x01000001, 0x01040000, 0x01040001,
240 0x00000002, 0x00000003, 0x00040002, 0x00040003,
241 0x01000002, 0x01000003, 0x01040002, 0x01040003,
242 0x00000200, 0x00000201, 0x00040200, 0x00040201,
243 0x01000200, 0x01000201, 0x01040200, 0x01040201,
244 0x00000202, 0x00000203, 0x00040202, 0x00040203,
245 0x01000202, 0x01000203, 0x01040202, 0x01040203,
246 0x08000000, 0x08000001, 0x08040000, 0x08040001,
247 0x09000000, 0x09000001, 0x09040000, 0x09040001,
248 0x08000002, 0x08000003, 0x08040002, 0x08040003,
249 0x09000002, 0x09000003, 0x09040002, 0x09040003,
250 0x08000200, 0x08000201, 0x08040200, 0x08040201,
251 0x09000200, 0x09000201, 0x09040200, 0x09040201,
252 0x08000202, 0x08000203, 0x08040202, 0x08040203,
253 0x09000202, 0x09000203, 0x09040202, 0x09040203,
254 /* for C bits (numbered as per FIPS 46) 21 23 24 26 27 28 */
255 0x00000000, 0x00100000, 0x00000100, 0x00100100,
256 0x00000008, 0x00100008, 0x00000108, 0x00100108,
257 0x00001000, 0x00101000, 0x00001100, 0x00101100,
258 0x00001008, 0x00101008, 0x00001108, 0x00101108,
259 0x04000000, 0x04100000, 0x04000100, 0x04100100,
260 0x04000008, 0x04100008, 0x04000108, 0x04100108,
261 0x04001000, 0x04101000, 0x04001100, 0x04101100,
262 0x04001008, 0x04101008, 0x04001108, 0x04101108,
263 0x00020000, 0x00120000, 0x00020100, 0x00120100,
264 0x00020008, 0x00120008, 0x00020108, 0x00120108,
265 0x00021000, 0x00121000, 0x00021100, 0x00121100,
266 0x00021008, 0x00121008, 0x00021108, 0x00121108,
267 0x04020000, 0x04120000, 0x04020100, 0x04120100,
268 0x04020008, 0x04120008, 0x04020108, 0x04120108,
269 0x04021000, 0x04121000, 0x04021100, 0x04121100,
270 0x04021008, 0x04121008, 0x04021108, 0x04121108,
271 /* for D bits (numbered as per FIPS 46) 1 2 3 4 5 6 */
272 0x00000000, 0x10000000, 0x00010000, 0x10010000,
273 0x00000004, 0x10000004, 0x00010004, 0x10010004,
274 0x20000000, 0x30000000, 0x20010000, 0x30010000,
275 0x20000004, 0x30000004, 0x20010004, 0x30010004,
276 0x00100000, 0x10100000, 0x00110000, 0x10110000,
277 0x00100004, 0x10100004, 0x00110004, 0x10110004,
278 0x20100000, 0x30100000, 0x20110000, 0x30110000,
279 0x20100004, 0x30100004, 0x20110004, 0x30110004,
280 0x00001000, 0x10001000, 0x00011000, 0x10011000,
281 0x00001004, 0x10001004, 0x00011004, 0x10011004,
282 0x20001000, 0x30001000, 0x20011000, 0x30011000,
283 0x20001004, 0x30001004, 0x20011004, 0x30011004,
284 0x00101000, 0x10101000, 0x00111000, 0x10111000,
285 0x00101004, 0x10101004, 0x00111004, 0x10111004,
286 0x20101000, 0x30101000, 0x20111000, 0x30111000,
287 0x20101004, 0x30101004, 0x20111004, 0x30111004,
288 /* for D bits (numbered as per FIPS 46) 8 9 11 12 13 14 */
289 0x00000000, 0x08000000, 0x00000008, 0x08000008,
290 0x00000400, 0x08000400, 0x00000408, 0x08000408,
291 0x00020000, 0x08020000, 0x00020008, 0x08020008,
292 0x00020400, 0x08020400, 0x00020408, 0x08020408,
293 0x00000001, 0x08000001, 0x00000009, 0x08000009,
294 0x00000401, 0x08000401, 0x00000409, 0x08000409,
295 0x00020001, 0x08020001, 0x00020009, 0x08020009,
296 0x00020401, 0x08020401, 0x00020409, 0x08020409,
297 0x02000000, 0x0A000000, 0x02000008, 0x0A000008,
298 0x02000400, 0x0A000400, 0x02000408, 0x0A000408,
299 0x02020000, 0x0A020000, 0x02020008, 0x0A020008,
300 0x02020400, 0x0A020400, 0x02020408, 0x0A020408,
301 0x02000001, 0x0A000001, 0x02000009, 0x0A000009,
302 0x02000401, 0x0A000401, 0x02000409, 0x0A000409,
303 0x02020001, 0x0A020001, 0x02020009, 0x0A020009,
304 0x02020401, 0x0A020401, 0x02020409, 0x0A020409,
305 /* for D bits (numbered as per FIPS 46) 16 17 18 19 20 21 */
306 0x00000000, 0x00000100, 0x00080000, 0x00080100,
307 0x01000000, 0x01000100, 0x01080000, 0x01080100,
308 0x00000010, 0x00000110, 0x00080010, 0x00080110,
309 0x01000010, 0x01000110, 0x01080010, 0x01080110,
310 0x00200000, 0x00200100, 0x00280000, 0x00280100,
311 0x01200000, 0x01200100, 0x01280000, 0x01280100,
312 0x00200010, 0x00200110, 0x00280010, 0x00280110,
313 0x01200010, 0x01200110, 0x01280010, 0x01280110,
314 0x00000200, 0x00000300, 0x00080200, 0x00080300,
315 0x01000200, 0x01000300, 0x01080200, 0x01080300,
316 0x00000210, 0x00000310, 0x00080210, 0x00080310,
317 0x01000210, 0x01000310, 0x01080210, 0x01080310,
318 0x00200200, 0x00200300, 0x00280200, 0x00280300,
319 0x01200200, 0x01200300, 0x01280200, 0x01280300,
320 0x00200210, 0x00200310, 0x00280210, 0x00280310,
321 0x01200210, 0x01200310, 0x01280210, 0x01280310,
322 /* for D bits (numbered as per FIPS 46) 22 23 24 25 27 28 */
323 0x00000000, 0x04000000, 0x00040000, 0x04040000,
324 0x00000002, 0x04000002, 0x00040002, 0x04040002,
325 0x00002000, 0x04002000, 0x00042000, 0x04042000,
326 0x00002002, 0x04002002, 0x00042002, 0x04042002,
327 0x00000020, 0x04000020, 0x00040020, 0x04040020,
328 0x00000022, 0x04000022, 0x00040022, 0x04040022,
329 0x00002020, 0x04002020, 0x00042020, 0x04042020,
330 0x00002022, 0x04002022, 0x00042022, 0x04042022,
331 0x00000800, 0x04000800, 0x00040800, 0x04040800,
332 0x00000802, 0x04000802, 0x00040802, 0x04040802,
333 0x00002800, 0x04002800, 0x00042800, 0x04042800,
334 0x00002802, 0x04002802, 0x00042802, 0x04042802,
335 0x00000820, 0x04000820, 0x00040820, 0x04040820,
336 0x00000822, 0x04000822, 0x00040822, 0x04040822,
337 0x00002820, 0x04002820, 0x00042820, 0x04042820,
338 0x00002822, 0x04002822, 0x00042822, 0x04042822
342 #define BOX(i,n,S) (u32x) ((S)[(n)][(i)])
346 #define BOX(i,n,S) (u32x) ((S)[(n)][(i).s0], (S)[(n)][(i).s1])
350 #define BOX(i,n,S) (u32x) ((S)[(n)][(i).s0], (S)[(n)][(i).s1], (S)[(n)][(i).s2], (S)[(n)][(i).s3])
353 static void _des_crypt_keysetup (u32 c, u32 d, u32 Kc[16], u32 Kd[16], __local u32 s_skb[8][64])
357 PERM_OP (d, c, tt, 4, 0x0f0f0f0f);
358 HPERM_OP (c, tt, 2, 0xcccc0000);
359 HPERM_OP (d, tt, 2, 0xcccc0000);
360 PERM_OP (d, c, tt, 1, 0x55555555);
361 PERM_OP (c, d, tt, 8, 0x00ff00ff);
362 PERM_OP (d, c, tt, 1, 0x55555555);
364 d = ((d & 0x000000ff) << 16)
365 | ((d & 0x0000ff00) << 0)
366 | ((d & 0x00ff0000) >> 16)
367 | ((c & 0xf0000000) >> 4);
372 for (u32 i = 0; i < 16; i++)
374 const u32 shifts3s0[16] = { 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1 };
375 const u32 shifts3s1[16] = { 27, 27, 26, 26, 26, 26, 26, 26, 27, 26, 26, 26, 26, 26, 26, 27 };
377 c = c >> shifts3s0[i] | c << shifts3s1[i];
378 d = d >> shifts3s0[i] | d << shifts3s1[i];
383 const u32 c00 = (c >> 0) & 0x0000003f;
384 const u32 c06 = (c >> 6) & 0x00383003;
385 const u32 c07 = (c >> 7) & 0x0000003c;
386 const u32 c13 = (c >> 13) & 0x0000060f;
387 const u32 c20 = (c >> 20) & 0x00000001;
389 u32 s = BOX (((c00 >> 0) & 0xff), 0, s_skb)
390 | BOX (((c06 >> 0) & 0xff)
391 |((c07 >> 0) & 0xff), 1, s_skb)
392 | BOX (((c13 >> 0) & 0xff)
393 |((c06 >> 8) & 0xff), 2, s_skb)
394 | BOX (((c20 >> 0) & 0xff)
396 |((c06 >> 16) & 0xff), 3, s_skb);
398 const u32 d00 = (d >> 0) & 0x00003c3f;
399 const u32 d07 = (d >> 7) & 0x00003f03;
400 const u32 d21 = (d >> 21) & 0x0000000f;
401 const u32 d22 = (d >> 22) & 0x00000030;
403 u32 t = BOX (((d00 >> 0) & 0xff), 4, s_skb)
404 | BOX (((d07 >> 0) & 0xff)
405 |((d00 >> 8) & 0xff), 5, s_skb)
406 | BOX (((d07 >> 8) & 0xff), 6, s_skb)
407 | BOX (((d21 >> 0) & 0xff)
408 |((d22 >> 0) & 0xff), 7, s_skb);
410 Kc[i] = ((t << 16) | (s & 0x0000ffff));
411 Kd[i] = ((s >> 16) | (t & 0xffff0000));
415 static void _des_crypt_encrypt (u32 iv[2], u32 mask, u32 rounds, u32 Kc[16], u32 Kd[16], __local u32 s_SPtrans[8][64])
419 const u32 E0 = ((mask >> 0) & 0x003f)
420 | ((mask >> 4) & 0x3f00);
421 const u32 E1 = ((mask >> 2) & 0x03f0)
422 | ((mask >> 6) & 0xf000)
423 | ((mask >> 22) & 0x0003);
428 for (u32 i = 0; i < rounds; i++)
431 for (u32 j = 0; j < 16; j++)
434 u32 t = r ^ (r >> 16);
458 const u32 um = u & 0x3f3f3f3f;
459 const u32 tm = t & 0x3f3f3f3f;
461 l ^= BOX (((um >> 0) & 0xff), 0, s_SPtrans)
462 | BOX (((um >> 8) & 0xff), 2, s_SPtrans)
463 | BOX (((um >> 16) & 0xff), 4, s_SPtrans)
464 | BOX (((um >> 24) & 0xff), 6, s_SPtrans)
465 | BOX (((tm >> 0) & 0xff), 1, s_SPtrans)
466 | BOX (((tm >> 8) & 0xff), 3, s_SPtrans)
467 | BOX (((tm >> 16) & 0xff), 5, s_SPtrans)
468 | BOX (((tm >> 24) & 0xff), 7, s_SPtrans);
484 __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)
490 const u32 gid = get_global_id (0);
491 const u32 lid = get_local_id (0);
497 __local u32 s_SPtrans[8][64];
499 s_SPtrans[0][lid] = c_SPtrans[0][lid];
500 s_SPtrans[1][lid] = c_SPtrans[1][lid];
501 s_SPtrans[2][lid] = c_SPtrans[2][lid];
502 s_SPtrans[3][lid] = c_SPtrans[3][lid];
503 s_SPtrans[4][lid] = c_SPtrans[4][lid];
504 s_SPtrans[5][lid] = c_SPtrans[5][lid];
505 s_SPtrans[6][lid] = c_SPtrans[6][lid];
506 s_SPtrans[7][lid] = c_SPtrans[7][lid];
508 __local u32 s_skb[8][64];
510 s_skb[0][lid] = c_skb[0][lid];
511 s_skb[1][lid] = c_skb[1][lid];
512 s_skb[2][lid] = c_skb[2][lid];
513 s_skb[3][lid] = c_skb[3][lid];
514 s_skb[4][lid] = c_skb[4][lid];
515 s_skb[5][lid] = c_skb[5][lid];
516 s_skb[6][lid] = c_skb[6][lid];
517 s_skb[7][lid] = c_skb[7][lid];
519 barrier (CLK_LOCAL_MEM_FENCE);
521 if (gid >= gid_max) return;
529 w[ 0] = pws[gid].i[ 0];
530 w[ 1] = pws[gid].i[ 1];
531 w[ 2] = pws[gid].i[ 2];
532 w[ 3] = pws[gid].i[ 3];
533 w[ 4] = pws[gid].i[ 4];
534 w[ 5] = pws[gid].i[ 5];
535 w[ 6] = pws[gid].i[ 6];
536 w[ 7] = pws[gid].i[ 7];
537 w[ 8] = pws[gid].i[ 8];
538 w[ 9] = pws[gid].i[ 9];
539 w[10] = pws[gid].i[10];
540 w[11] = pws[gid].i[11];
541 w[12] = pws[gid].i[12];
542 w[13] = pws[gid].i[13];
543 w[14] = pws[gid].i[14];
544 w[15] = pws[gid].i[15];
546 u32 pw_len = pws[gid].pw_len;
556 out[0] = (w[0] << 1) & 0xfefefefe;
557 out[1] = (w[1] << 1) & 0xfefefefe;
559 for (u32 i = 8, j = 2; i < pw_len; i += 8, j += 2)
561 _des_crypt_keysetup (out[0], out[1], Kc, Kd, s_skb);
563 IP (out[0], out[1], tt);
565 out[0] = rotr32 (out[0], 31);
566 out[1] = rotr32 (out[1], 31);
568 _des_crypt_encrypt (out, 0, 1, Kc, Kd, s_SPtrans);
570 out[0] = rotl32 (out[0], 31);
571 out[1] = rotl32 (out[1], 31);
573 FP (out[1], out[0], tt);
575 const u32 R = (w[j + 0] << 1) & 0xfefefefe;
576 const u32 L = (w[j + 1] << 1) & 0xfefefefe;
583 out[0] = (out[0] & 0xfefefefe) >> 1;
584 out[1] = (out[1] & 0xfefefefe) >> 1;
586 out[0] = (out[0] << 1) & 0xfefefefe;
587 out[1] = (out[1] << 1) & 0xfefefefe;
590 _des_crypt_keysetup (out[0], out[1], Kc, Kd, s_skb);
592 tmps[gid].Kc[ 0] = Kc[ 0];
593 tmps[gid].Kc[ 1] = Kc[ 1];
594 tmps[gid].Kc[ 2] = Kc[ 2];
595 tmps[gid].Kc[ 3] = Kc[ 3];
596 tmps[gid].Kc[ 4] = Kc[ 4];
597 tmps[gid].Kc[ 5] = Kc[ 5];
598 tmps[gid].Kc[ 6] = Kc[ 6];
599 tmps[gid].Kc[ 7] = Kc[ 7];
600 tmps[gid].Kc[ 8] = Kc[ 8];
601 tmps[gid].Kc[ 9] = Kc[ 9];
602 tmps[gid].Kc[10] = Kc[10];
603 tmps[gid].Kc[11] = Kc[11];
604 tmps[gid].Kc[12] = Kc[12];
605 tmps[gid].Kc[13] = Kc[13];
606 tmps[gid].Kc[14] = Kc[14];
607 tmps[gid].Kc[15] = Kc[15];
609 tmps[gid].Kd[ 0] = Kd[ 0];
610 tmps[gid].Kd[ 1] = Kd[ 1];
611 tmps[gid].Kd[ 2] = Kd[ 2];
612 tmps[gid].Kd[ 3] = Kd[ 3];
613 tmps[gid].Kd[ 4] = Kd[ 4];
614 tmps[gid].Kd[ 5] = Kd[ 5];
615 tmps[gid].Kd[ 6] = Kd[ 6];
616 tmps[gid].Kd[ 7] = Kd[ 7];
617 tmps[gid].Kd[ 8] = Kd[ 8];
618 tmps[gid].Kd[ 9] = Kd[ 9];
619 tmps[gid].Kd[10] = Kd[10];
620 tmps[gid].Kd[11] = Kd[11];
621 tmps[gid].Kd[12] = Kd[12];
622 tmps[gid].Kd[13] = Kd[13];
623 tmps[gid].Kd[14] = Kd[14];
624 tmps[gid].Kd[15] = Kd[15];
630 __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)
636 const u32 gid = get_global_id (0);
637 const u32 lid = get_local_id (0);
643 __local u32 s_SPtrans[8][64];
645 s_SPtrans[0][lid] = c_SPtrans[0][lid];
646 s_SPtrans[1][lid] = c_SPtrans[1][lid];
647 s_SPtrans[2][lid] = c_SPtrans[2][lid];
648 s_SPtrans[3][lid] = c_SPtrans[3][lid];
649 s_SPtrans[4][lid] = c_SPtrans[4][lid];
650 s_SPtrans[5][lid] = c_SPtrans[5][lid];
651 s_SPtrans[6][lid] = c_SPtrans[6][lid];
652 s_SPtrans[7][lid] = c_SPtrans[7][lid];
654 barrier (CLK_LOCAL_MEM_FENCE);
656 if (gid >= gid_max) return;
660 Kc[ 0] = tmps[gid].Kc[ 0];
661 Kc[ 1] = tmps[gid].Kc[ 1];
662 Kc[ 2] = tmps[gid].Kc[ 2];
663 Kc[ 3] = tmps[gid].Kc[ 3];
664 Kc[ 4] = tmps[gid].Kc[ 4];
665 Kc[ 5] = tmps[gid].Kc[ 5];
666 Kc[ 6] = tmps[gid].Kc[ 6];
667 Kc[ 7] = tmps[gid].Kc[ 7];
668 Kc[ 8] = tmps[gid].Kc[ 8];
669 Kc[ 9] = tmps[gid].Kc[ 9];
670 Kc[10] = tmps[gid].Kc[10];
671 Kc[11] = tmps[gid].Kc[11];
672 Kc[12] = tmps[gid].Kc[12];
673 Kc[13] = tmps[gid].Kc[13];
674 Kc[14] = tmps[gid].Kc[14];
675 Kc[15] = tmps[gid].Kc[15];
679 Kd[ 0] = tmps[gid].Kd[ 0];
680 Kd[ 1] = tmps[gid].Kd[ 1];
681 Kd[ 2] = tmps[gid].Kd[ 2];
682 Kd[ 3] = tmps[gid].Kd[ 3];
683 Kd[ 4] = tmps[gid].Kd[ 4];
684 Kd[ 5] = tmps[gid].Kd[ 5];
685 Kd[ 6] = tmps[gid].Kd[ 6];
686 Kd[ 7] = tmps[gid].Kd[ 7];
687 Kd[ 8] = tmps[gid].Kd[ 8];
688 Kd[ 9] = tmps[gid].Kd[ 9];
689 Kd[10] = tmps[gid].Kd[10];
690 Kd[11] = tmps[gid].Kd[11];
691 Kd[12] = tmps[gid].Kd[12];
692 Kd[13] = tmps[gid].Kd[13];
693 Kd[14] = tmps[gid].Kd[14];
694 Kd[15] = tmps[gid].Kd[15];
698 iv[0] = tmps[gid].iv[0];
699 iv[1] = tmps[gid].iv[1];
701 const u32 mask = salt_bufs[salt_pos].salt_buf[0];
703 _des_crypt_encrypt (iv, mask, loop_cnt, Kc, Kd, s_SPtrans);
705 tmps[gid].Kc[ 0] = Kc[ 0];
706 tmps[gid].Kc[ 1] = Kc[ 1];
707 tmps[gid].Kc[ 2] = Kc[ 2];
708 tmps[gid].Kc[ 3] = Kc[ 3];
709 tmps[gid].Kc[ 4] = Kc[ 4];
710 tmps[gid].Kc[ 5] = Kc[ 5];
711 tmps[gid].Kc[ 6] = Kc[ 6];
712 tmps[gid].Kc[ 7] = Kc[ 7];
713 tmps[gid].Kc[ 8] = Kc[ 8];
714 tmps[gid].Kc[ 9] = Kc[ 9];
715 tmps[gid].Kc[10] = Kc[10];
716 tmps[gid].Kc[11] = Kc[11];
717 tmps[gid].Kc[12] = Kc[12];
718 tmps[gid].Kc[13] = Kc[13];
719 tmps[gid].Kc[14] = Kc[14];
720 tmps[gid].Kc[15] = Kc[15];
722 tmps[gid].Kd[ 0] = Kd[ 0];
723 tmps[gid].Kd[ 1] = Kd[ 1];
724 tmps[gid].Kd[ 2] = Kd[ 2];
725 tmps[gid].Kd[ 3] = Kd[ 3];
726 tmps[gid].Kd[ 4] = Kd[ 4];
727 tmps[gid].Kd[ 5] = Kd[ 5];
728 tmps[gid].Kd[ 6] = Kd[ 6];
729 tmps[gid].Kd[ 7] = Kd[ 7];
730 tmps[gid].Kd[ 8] = Kd[ 8];
731 tmps[gid].Kd[ 9] = Kd[ 9];
732 tmps[gid].Kd[10] = Kd[10];
733 tmps[gid].Kd[11] = Kd[11];
734 tmps[gid].Kd[12] = Kd[12];
735 tmps[gid].Kd[13] = Kd[13];
736 tmps[gid].Kd[14] = Kd[14];
737 tmps[gid].Kd[15] = Kd[15];
739 tmps[gid].iv[0] = iv[0];
740 tmps[gid].iv[1] = iv[1];
743 __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)
749 const u32 gid = get_global_id (0);
751 if (gid >= gid_max) return;
753 const u32 lid = get_local_id (0);
755 const u32 r0 = tmps[gid].iv[0];
756 const u32 r1 = tmps[gid].iv[1];