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 "OpenCL/types_ocl.c"
18 #include "OpenCL/common.c"
19 #include "include/rp_kernel.h"
20 #include "OpenCL/rp.c"
22 #define COMPARE_S "OpenCL/check_single_comp4.c"
23 #define COMPARE_M "OpenCL/check_multi_comp4.c"
25 #define PERM_OP(a,b,tt,n,m) \
35 #define HPERM_OP(a,tt,n,m) \
41 tt = tt >> (16 + n); \
45 __constant u32 c_SPtrans[8][64] =
48 0x02080800, 0x00080000, 0x02000002, 0x02080802,
49 0x02000000, 0x00080802, 0x00080002, 0x02000002,
50 0x00080802, 0x02080800, 0x02080000, 0x00000802,
51 0x02000802, 0x02000000, 0x00000000, 0x00080002,
52 0x00080000, 0x00000002, 0x02000800, 0x00080800,
53 0x02080802, 0x02080000, 0x00000802, 0x02000800,
54 0x00000002, 0x00000800, 0x00080800, 0x02080002,
55 0x00000800, 0x02000802, 0x02080002, 0x00000000,
56 0x00000000, 0x02080802, 0x02000800, 0x00080002,
57 0x02080800, 0x00080000, 0x00000802, 0x02000800,
58 0x02080002, 0x00000800, 0x00080800, 0x02000002,
59 0x00080802, 0x00000002, 0x02000002, 0x02080000,
60 0x02080802, 0x00080800, 0x02080000, 0x02000802,
61 0x02000000, 0x00000802, 0x00080002, 0x00000000,
62 0x00080000, 0x02000000, 0x02000802, 0x02080800,
63 0x00000002, 0x02080002, 0x00000800, 0x00080802,
66 0x40108010, 0x00000000, 0x00108000, 0x40100000,
67 0x40000010, 0x00008010, 0x40008000, 0x00108000,
68 0x00008000, 0x40100010, 0x00000010, 0x40008000,
69 0x00100010, 0x40108000, 0x40100000, 0x00000010,
70 0x00100000, 0x40008010, 0x40100010, 0x00008000,
71 0x00108010, 0x40000000, 0x00000000, 0x00100010,
72 0x40008010, 0x00108010, 0x40108000, 0x40000010,
73 0x40000000, 0x00100000, 0x00008010, 0x40108010,
74 0x00100010, 0x40108000, 0x40008000, 0x00108010,
75 0x40108010, 0x00100010, 0x40000010, 0x00000000,
76 0x40000000, 0x00008010, 0x00100000, 0x40100010,
77 0x00008000, 0x40000000, 0x00108010, 0x40008010,
78 0x40108000, 0x00008000, 0x00000000, 0x40000010,
79 0x00000010, 0x40108010, 0x00108000, 0x40100000,
80 0x40100010, 0x00100000, 0x00008010, 0x40008000,
81 0x40008010, 0x00000010, 0x40100000, 0x00108000,
84 0x04000001, 0x04040100, 0x00000100, 0x04000101,
85 0x00040001, 0x04000000, 0x04000101, 0x00040100,
86 0x04000100, 0x00040000, 0x04040000, 0x00000001,
87 0x04040101, 0x00000101, 0x00000001, 0x04040001,
88 0x00000000, 0x00040001, 0x04040100, 0x00000100,
89 0x00000101, 0x04040101, 0x00040000, 0x04000001,
90 0x04040001, 0x04000100, 0x00040101, 0x04040000,
91 0x00040100, 0x00000000, 0x04000000, 0x00040101,
92 0x04040100, 0x00000100, 0x00000001, 0x00040000,
93 0x00000101, 0x00040001, 0x04040000, 0x04000101,
94 0x00000000, 0x04040100, 0x00040100, 0x04040001,
95 0x00040001, 0x04000000, 0x04040101, 0x00000001,
96 0x00040101, 0x04000001, 0x04000000, 0x04040101,
97 0x00040000, 0x04000100, 0x04000101, 0x00040100,
98 0x04000100, 0x00000000, 0x04040001, 0x00000101,
99 0x04000001, 0x00040101, 0x00000100, 0x04040000,
102 0x00401008, 0x10001000, 0x00000008, 0x10401008,
103 0x00000000, 0x10400000, 0x10001008, 0x00400008,
104 0x10401000, 0x10000008, 0x10000000, 0x00001008,
105 0x10000008, 0x00401008, 0x00400000, 0x10000000,
106 0x10400008, 0x00401000, 0x00001000, 0x00000008,
107 0x00401000, 0x10001008, 0x10400000, 0x00001000,
108 0x00001008, 0x00000000, 0x00400008, 0x10401000,
109 0x10001000, 0x10400008, 0x10401008, 0x00400000,
110 0x10400008, 0x00001008, 0x00400000, 0x10000008,
111 0x00401000, 0x10001000, 0x00000008, 0x10400000,
112 0x10001008, 0x00000000, 0x00001000, 0x00400008,
113 0x00000000, 0x10400008, 0x10401000, 0x00001000,
114 0x10000000, 0x10401008, 0x00401008, 0x00400000,
115 0x10401008, 0x00000008, 0x10001000, 0x00401008,
116 0x00400008, 0x00401000, 0x10400000, 0x10001008,
117 0x00001008, 0x10000000, 0x10000008, 0x10401000,
120 0x08000000, 0x00010000, 0x00000400, 0x08010420,
121 0x08010020, 0x08000400, 0x00010420, 0x08010000,
122 0x00010000, 0x00000020, 0x08000020, 0x00010400,
123 0x08000420, 0x08010020, 0x08010400, 0x00000000,
124 0x00010400, 0x08000000, 0x00010020, 0x00000420,
125 0x08000400, 0x00010420, 0x00000000, 0x08000020,
126 0x00000020, 0x08000420, 0x08010420, 0x00010020,
127 0x08010000, 0x00000400, 0x00000420, 0x08010400,
128 0x08010400, 0x08000420, 0x00010020, 0x08010000,
129 0x00010000, 0x00000020, 0x08000020, 0x08000400,
130 0x08000000, 0x00010400, 0x08010420, 0x00000000,
131 0x00010420, 0x08000000, 0x00000400, 0x00010020,
132 0x08000420, 0x00000400, 0x00000000, 0x08010420,
133 0x08010020, 0x08010400, 0x00000420, 0x00010000,
134 0x00010400, 0x08010020, 0x08000400, 0x00000420,
135 0x00000020, 0x00010420, 0x08010000, 0x08000020,
138 0x80000040, 0x00200040, 0x00000000, 0x80202000,
139 0x00200040, 0x00002000, 0x80002040, 0x00200000,
140 0x00002040, 0x80202040, 0x00202000, 0x80000000,
141 0x80002000, 0x80000040, 0x80200000, 0x00202040,
142 0x00200000, 0x80002040, 0x80200040, 0x00000000,
143 0x00002000, 0x00000040, 0x80202000, 0x80200040,
144 0x80202040, 0x80200000, 0x80000000, 0x00002040,
145 0x00000040, 0x00202000, 0x00202040, 0x80002000,
146 0x00002040, 0x80000000, 0x80002000, 0x00202040,
147 0x80202000, 0x00200040, 0x00000000, 0x80002000,
148 0x80000000, 0x00002000, 0x80200040, 0x00200000,
149 0x00200040, 0x80202040, 0x00202000, 0x00000040,
150 0x80202040, 0x00202000, 0x00200000, 0x80002040,
151 0x80000040, 0x80200000, 0x00202040, 0x00000000,
152 0x00002000, 0x80000040, 0x80002040, 0x80202000,
153 0x80200000, 0x00002040, 0x00000040, 0x80200040,
156 0x00004000, 0x00000200, 0x01000200, 0x01000004,
157 0x01004204, 0x00004004, 0x00004200, 0x00000000,
158 0x01000000, 0x01000204, 0x00000204, 0x01004000,
159 0x00000004, 0x01004200, 0x01004000, 0x00000204,
160 0x01000204, 0x00004000, 0x00004004, 0x01004204,
161 0x00000000, 0x01000200, 0x01000004, 0x00004200,
162 0x01004004, 0x00004204, 0x01004200, 0x00000004,
163 0x00004204, 0x01004004, 0x00000200, 0x01000000,
164 0x00004204, 0x01004000, 0x01004004, 0x00000204,
165 0x00004000, 0x00000200, 0x01000000, 0x01004004,
166 0x01000204, 0x00004204, 0x00004200, 0x00000000,
167 0x00000200, 0x01000004, 0x00000004, 0x01000200,
168 0x00000000, 0x01000204, 0x01000200, 0x00004200,
169 0x00000204, 0x00004000, 0x01004204, 0x01000000,
170 0x01004200, 0x00000004, 0x00004004, 0x01004204,
171 0x01000004, 0x01004200, 0x01004000, 0x00004004,
174 0x20800080, 0x20820000, 0x00020080, 0x00000000,
175 0x20020000, 0x00800080, 0x20800000, 0x20820080,
176 0x00000080, 0x20000000, 0x00820000, 0x00020080,
177 0x00820080, 0x20020080, 0x20000080, 0x20800000,
178 0x00020000, 0x00820080, 0x00800080, 0x20020000,
179 0x20820080, 0x20000080, 0x00000000, 0x00820000,
180 0x20000000, 0x00800000, 0x20020080, 0x20800080,
181 0x00800000, 0x00020000, 0x20820000, 0x00000080,
182 0x00800000, 0x00020000, 0x20000080, 0x20820080,
183 0x00020080, 0x20000000, 0x00000000, 0x00820000,
184 0x20800080, 0x20020080, 0x20020000, 0x00800080,
185 0x20820000, 0x00000080, 0x00800080, 0x20020000,
186 0x20820080, 0x00800000, 0x20800000, 0x20000080,
187 0x00820000, 0x00020080, 0x20020080, 0x20800000,
188 0x00000080, 0x20820000, 0x00820080, 0x00000000,
189 0x20000000, 0x20800080, 0x00020000, 0x00820080,
193 __constant u32 c_skb[8][64] =
196 0x00000000, 0x00000010, 0x20000000, 0x20000010,
197 0x00010000, 0x00010010, 0x20010000, 0x20010010,
198 0x00000800, 0x00000810, 0x20000800, 0x20000810,
199 0x00010800, 0x00010810, 0x20010800, 0x20010810,
200 0x00000020, 0x00000030, 0x20000020, 0x20000030,
201 0x00010020, 0x00010030, 0x20010020, 0x20010030,
202 0x00000820, 0x00000830, 0x20000820, 0x20000830,
203 0x00010820, 0x00010830, 0x20010820, 0x20010830,
204 0x00080000, 0x00080010, 0x20080000, 0x20080010,
205 0x00090000, 0x00090010, 0x20090000, 0x20090010,
206 0x00080800, 0x00080810, 0x20080800, 0x20080810,
207 0x00090800, 0x00090810, 0x20090800, 0x20090810,
208 0x00080020, 0x00080030, 0x20080020, 0x20080030,
209 0x00090020, 0x00090030, 0x20090020, 0x20090030,
210 0x00080820, 0x00080830, 0x20080820, 0x20080830,
211 0x00090820, 0x00090830, 0x20090820, 0x20090830,
214 0x00000000, 0x02000000, 0x00002000, 0x02002000,
215 0x00200000, 0x02200000, 0x00202000, 0x02202000,
216 0x00000004, 0x02000004, 0x00002004, 0x02002004,
217 0x00200004, 0x02200004, 0x00202004, 0x02202004,
218 0x00000400, 0x02000400, 0x00002400, 0x02002400,
219 0x00200400, 0x02200400, 0x00202400, 0x02202400,
220 0x00000404, 0x02000404, 0x00002404, 0x02002404,
221 0x00200404, 0x02200404, 0x00202404, 0x02202404,
222 0x10000000, 0x12000000, 0x10002000, 0x12002000,
223 0x10200000, 0x12200000, 0x10202000, 0x12202000,
224 0x10000004, 0x12000004, 0x10002004, 0x12002004,
225 0x10200004, 0x12200004, 0x10202004, 0x12202004,
226 0x10000400, 0x12000400, 0x10002400, 0x12002400,
227 0x10200400, 0x12200400, 0x10202400, 0x12202400,
228 0x10000404, 0x12000404, 0x10002404, 0x12002404,
229 0x10200404, 0x12200404, 0x10202404, 0x12202404,
232 0x00000000, 0x00000001, 0x00040000, 0x00040001,
233 0x01000000, 0x01000001, 0x01040000, 0x01040001,
234 0x00000002, 0x00000003, 0x00040002, 0x00040003,
235 0x01000002, 0x01000003, 0x01040002, 0x01040003,
236 0x00000200, 0x00000201, 0x00040200, 0x00040201,
237 0x01000200, 0x01000201, 0x01040200, 0x01040201,
238 0x00000202, 0x00000203, 0x00040202, 0x00040203,
239 0x01000202, 0x01000203, 0x01040202, 0x01040203,
240 0x08000000, 0x08000001, 0x08040000, 0x08040001,
241 0x09000000, 0x09000001, 0x09040000, 0x09040001,
242 0x08000002, 0x08000003, 0x08040002, 0x08040003,
243 0x09000002, 0x09000003, 0x09040002, 0x09040003,
244 0x08000200, 0x08000201, 0x08040200, 0x08040201,
245 0x09000200, 0x09000201, 0x09040200, 0x09040201,
246 0x08000202, 0x08000203, 0x08040202, 0x08040203,
247 0x09000202, 0x09000203, 0x09040202, 0x09040203,
250 0x00000000, 0x00100000, 0x00000100, 0x00100100,
251 0x00000008, 0x00100008, 0x00000108, 0x00100108,
252 0x00001000, 0x00101000, 0x00001100, 0x00101100,
253 0x00001008, 0x00101008, 0x00001108, 0x00101108,
254 0x04000000, 0x04100000, 0x04000100, 0x04100100,
255 0x04000008, 0x04100008, 0x04000108, 0x04100108,
256 0x04001000, 0x04101000, 0x04001100, 0x04101100,
257 0x04001008, 0x04101008, 0x04001108, 0x04101108,
258 0x00020000, 0x00120000, 0x00020100, 0x00120100,
259 0x00020008, 0x00120008, 0x00020108, 0x00120108,
260 0x00021000, 0x00121000, 0x00021100, 0x00121100,
261 0x00021008, 0x00121008, 0x00021108, 0x00121108,
262 0x04020000, 0x04120000, 0x04020100, 0x04120100,
263 0x04020008, 0x04120008, 0x04020108, 0x04120108,
264 0x04021000, 0x04121000, 0x04021100, 0x04121100,
265 0x04021008, 0x04121008, 0x04021108, 0x04121108,
268 0x00000000, 0x10000000, 0x00010000, 0x10010000,
269 0x00000004, 0x10000004, 0x00010004, 0x10010004,
270 0x20000000, 0x30000000, 0x20010000, 0x30010000,
271 0x20000004, 0x30000004, 0x20010004, 0x30010004,
272 0x00100000, 0x10100000, 0x00110000, 0x10110000,
273 0x00100004, 0x10100004, 0x00110004, 0x10110004,
274 0x20100000, 0x30100000, 0x20110000, 0x30110000,
275 0x20100004, 0x30100004, 0x20110004, 0x30110004,
276 0x00001000, 0x10001000, 0x00011000, 0x10011000,
277 0x00001004, 0x10001004, 0x00011004, 0x10011004,
278 0x20001000, 0x30001000, 0x20011000, 0x30011000,
279 0x20001004, 0x30001004, 0x20011004, 0x30011004,
280 0x00101000, 0x10101000, 0x00111000, 0x10111000,
281 0x00101004, 0x10101004, 0x00111004, 0x10111004,
282 0x20101000, 0x30101000, 0x20111000, 0x30111000,
283 0x20101004, 0x30101004, 0x20111004, 0x30111004,
286 0x00000000, 0x08000000, 0x00000008, 0x08000008,
287 0x00000400, 0x08000400, 0x00000408, 0x08000408,
288 0x00020000, 0x08020000, 0x00020008, 0x08020008,
289 0x00020400, 0x08020400, 0x00020408, 0x08020408,
290 0x00000001, 0x08000001, 0x00000009, 0x08000009,
291 0x00000401, 0x08000401, 0x00000409, 0x08000409,
292 0x00020001, 0x08020001, 0x00020009, 0x08020009,
293 0x00020401, 0x08020401, 0x00020409, 0x08020409,
294 0x02000000, 0x0A000000, 0x02000008, 0x0A000008,
295 0x02000400, 0x0A000400, 0x02000408, 0x0A000408,
296 0x02020000, 0x0A020000, 0x02020008, 0x0A020008,
297 0x02020400, 0x0A020400, 0x02020408, 0x0A020408,
298 0x02000001, 0x0A000001, 0x02000009, 0x0A000009,
299 0x02000401, 0x0A000401, 0x02000409, 0x0A000409,
300 0x02020001, 0x0A020001, 0x02020009, 0x0A020009,
301 0x02020401, 0x0A020401, 0x02020409, 0x0A020409,
304 0x00000000, 0x00000100, 0x00080000, 0x00080100,
305 0x01000000, 0x01000100, 0x01080000, 0x01080100,
306 0x00000010, 0x00000110, 0x00080010, 0x00080110,
307 0x01000010, 0x01000110, 0x01080010, 0x01080110,
308 0x00200000, 0x00200100, 0x00280000, 0x00280100,
309 0x01200000, 0x01200100, 0x01280000, 0x01280100,
310 0x00200010, 0x00200110, 0x00280010, 0x00280110,
311 0x01200010, 0x01200110, 0x01280010, 0x01280110,
312 0x00000200, 0x00000300, 0x00080200, 0x00080300,
313 0x01000200, 0x01000300, 0x01080200, 0x01080300,
314 0x00000210, 0x00000310, 0x00080210, 0x00080310,
315 0x01000210, 0x01000310, 0x01080210, 0x01080310,
316 0x00200200, 0x00200300, 0x00280200, 0x00280300,
317 0x01200200, 0x01200300, 0x01280200, 0x01280300,
318 0x00200210, 0x00200310, 0x00280210, 0x00280310,
319 0x01200210, 0x01200310, 0x01280210, 0x01280310,
322 0x00000000, 0x04000000, 0x00040000, 0x04040000,
323 0x00000002, 0x04000002, 0x00040002, 0x04040002,
324 0x00002000, 0x04002000, 0x00042000, 0x04042000,
325 0x00002002, 0x04002002, 0x00042002, 0x04042002,
326 0x00000020, 0x04000020, 0x00040020, 0x04040020,
327 0x00000022, 0x04000022, 0x00040022, 0x04040022,
328 0x00002020, 0x04002020, 0x00042020, 0x04042020,
329 0x00002022, 0x04002022, 0x00042022, 0x04042022,
330 0x00000800, 0x04000800, 0x00040800, 0x04040800,
331 0x00000802, 0x04000802, 0x00040802, 0x04040802,
332 0x00002800, 0x04002800, 0x00042800, 0x04042800,
333 0x00002802, 0x04002802, 0x00042802, 0x04042802,
334 0x00000820, 0x04000820, 0x00040820, 0x04040820,
335 0x00000822, 0x04000822, 0x00040822, 0x04040822,
336 0x00002820, 0x04002820, 0x00042820, 0x04042820,
337 0x00002822, 0x04002822, 0x00042822, 0x04042822
341 #define BOX(i,n,S) (S)[(n)][(i)]
343 static void _des_crypt_encrypt (u32 iv[2], u32 data[2], u32 Kc[16], u32 Kd[16], __local u32 s_SPtrans[8][64])
349 for (u32 i = 0; i < 16; i += 2)
354 u = Kc[i + 0] ^ rotl32 (r, 30u);
355 t = Kd[i + 0] ^ rotl32 (r, 26u);
357 l ^= BOX (((u >> 0) & 0x3f), 0, s_SPtrans)
358 | BOX (((u >> 8) & 0x3f), 2, s_SPtrans)
359 | BOX (((u >> 16) & 0x3f), 4, s_SPtrans)
360 | BOX (((u >> 24) & 0x3f), 6, s_SPtrans)
361 | BOX (((t >> 0) & 0x3f), 1, s_SPtrans)
362 | BOX (((t >> 8) & 0x3f), 3, s_SPtrans)
363 | BOX (((t >> 16) & 0x3f), 5, s_SPtrans)
364 | BOX (((t >> 24) & 0x3f), 7, s_SPtrans);
366 u = Kc[i + 1] ^ rotl32 (l, 30u);
367 t = Kd[i + 1] ^ rotl32 (l, 26u);
369 r ^= BOX (((u >> 0) & 0x3f), 0, s_SPtrans)
370 | BOX (((u >> 8) & 0x3f), 2, s_SPtrans)
371 | BOX (((u >> 16) & 0x3f), 4, s_SPtrans)
372 | BOX (((u >> 24) & 0x3f), 6, s_SPtrans)
373 | BOX (((t >> 0) & 0x3f), 1, s_SPtrans)
374 | BOX (((t >> 8) & 0x3f), 3, s_SPtrans)
375 | BOX (((t >> 16) & 0x3f), 5, s_SPtrans)
376 | BOX (((t >> 24) & 0x3f), 7, s_SPtrans);
383 static void _des_crypt_keysetup (u32 c, u32 d, u32 Kc[16], u32 Kd[16], __local u32 s_skb[8][64])
387 PERM_OP (d, c, tt, 4, 0x0f0f0f0f);
388 HPERM_OP (c, tt, 2, 0xcccc0000);
389 HPERM_OP (d, tt, 2, 0xcccc0000);
390 PERM_OP (d, c, tt, 1, 0x55555555);
391 PERM_OP (c, d, tt, 8, 0x00ff00ff);
392 PERM_OP (d, c, tt, 1, 0x55555555);
394 d = ((d & 0x000000ff) << 16)
395 | ((d & 0x0000ff00) << 0)
396 | ((d & 0x00ff0000) >> 16)
397 | ((c & 0xf0000000) >> 4);
402 for (u32 i = 0; i < 16; i++)
404 if ((i < 2) || (i == 8) || (i == 15))
406 c = ((c >> 1) | (c << 27));
407 d = ((d >> 1) | (d << 27));
411 c = ((c >> 2) | (c << 26));
412 d = ((d >> 2) | (d << 26));
418 const u32 c00 = (c >> 0) & 0x0000003f;
419 const u32 c06 = (c >> 6) & 0x00383003;
420 const u32 c07 = (c >> 7) & 0x0000003c;
421 const u32 c13 = (c >> 13) & 0x0000060f;
422 const u32 c20 = (c >> 20) & 0x00000001;
424 u32 s = BOX (((c00 >> 0) & 0xff), 0, s_skb)
425 | BOX (((c06 >> 0) & 0xff)
426 |((c07 >> 0) & 0xff), 1, s_skb)
427 | BOX (((c13 >> 0) & 0xff)
428 |((c06 >> 8) & 0xff), 2, s_skb)
429 | BOX (((c20 >> 0) & 0xff)
431 |((c06 >> 16) & 0xff), 3, s_skb);
433 const u32 d00 = (d >> 0) & 0x00003c3f;
434 const u32 d07 = (d >> 7) & 0x00003f03;
435 const u32 d21 = (d >> 21) & 0x0000000f;
436 const u32 d22 = (d >> 22) & 0x00000030;
438 u32 t = BOX (((d00 >> 0) & 0xff), 4, s_skb)
439 | BOX (((d07 >> 0) & 0xff)
440 |((d00 >> 8) & 0xff), 5, s_skb)
441 | BOX (((d07 >> 8) & 0xff), 6, s_skb)
442 | BOX (((d21 >> 0) & 0xff)
443 |((d22 >> 0) & 0xff), 7, s_skb);
445 Kc[i] = ((t << 16) | (s & 0x0000ffff));
446 Kd[i] = ((s >> 16) | (t & 0xffff0000));
450 static void transform_netntlmv1_key (const u32 w0, const u32 w1, u32 out[2])
452 const uchar4 t0 = as_uchar4 (w0);
453 const uchar4 t1 = as_uchar4 (w1);
458 k0.s0 = (t0.s0 >> 0);
459 k0.s1 = (t0.s0 << 7) | (t0.s1 >> 1);
460 k0.s2 = (t0.s1 << 6) | (t0.s2 >> 2);
461 k0.s3 = (t0.s2 << 5) | (t0.s3 >> 3);
462 k1.s0 = (t0.s3 << 4) | (t1.s0 >> 4);
463 k1.s1 = (t1.s0 << 3) | (t1.s1 >> 5);
464 k1.s2 = (t1.s1 << 2) | (t1.s2 >> 6);
465 k1.s3 = (t1.s2 << 1);
467 out[0] = as_uint (k0);
468 out[1] = as_uint (k1);
471 __kernel void m05500_m04 (__global pw_t *pws, __global kernel_rule_t * rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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)
477 const u32 gid = get_global_id (0);
478 const u32 lid = get_local_id (0);
479 const u32 lsz = get_local_size (0);
485 __local u32 s_SPtrans[8][64];
486 __local u32 s_skb[8][64];
488 for (u32 i = lid; i < 64; i += lsz)
490 s_SPtrans[0][i] = c_SPtrans[0][i];
491 s_SPtrans[1][i] = c_SPtrans[1][i];
492 s_SPtrans[2][i] = c_SPtrans[2][i];
493 s_SPtrans[3][i] = c_SPtrans[3][i];
494 s_SPtrans[4][i] = c_SPtrans[4][i];
495 s_SPtrans[5][i] = c_SPtrans[5][i];
496 s_SPtrans[6][i] = c_SPtrans[6][i];
497 s_SPtrans[7][i] = c_SPtrans[7][i];
499 s_skb[0][i] = c_skb[0][i];
500 s_skb[1][i] = c_skb[1][i];
501 s_skb[2][i] = c_skb[2][i];
502 s_skb[3][i] = c_skb[3][i];
503 s_skb[4][i] = c_skb[4][i];
504 s_skb[5][i] = c_skb[5][i];
505 s_skb[6][i] = c_skb[6][i];
506 s_skb[7][i] = c_skb[7][i];
509 barrier (CLK_LOCAL_MEM_FENCE);
511 if (gid >= gid_max) return;
519 pw_buf0[0] = pws[gid].i[ 0];
520 pw_buf0[1] = pws[gid].i[ 1];
521 pw_buf0[2] = pws[gid].i[ 2];
522 pw_buf0[3] = pws[gid].i[ 3];
526 pw_buf1[0] = pws[gid].i[ 4];
527 pw_buf1[1] = pws[gid].i[ 5];
528 pw_buf1[2] = pws[gid].i[ 6];
529 pw_buf1[3] = pws[gid].i[ 7];
531 const u32 pw_len = pws[gid].pw_len;
537 const u32 s0 = salt_bufs[salt_pos].salt_buf[0];
538 const u32 s1 = salt_bufs[salt_pos].salt_buf[1];
539 const u32 s2 = salt_bufs[salt_pos].salt_buf[2];
550 for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
580 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
582 append_0x80_2x4 (w0, w1, out_len);
589 make_unicode (w0, w0_t, w1_t);
590 make_unicode (w1, w2_t, w3_t);
592 w3_t[2] = out_len * 8 * 2;
599 MD4_STEP (MD4_Fo, a, b, c, d, w0_t[0], MD4C00, MD4S00);
600 MD4_STEP (MD4_Fo, d, a, b, c, w0_t[1], MD4C00, MD4S01);
601 MD4_STEP (MD4_Fo, c, d, a, b, w0_t[2], MD4C00, MD4S02);
602 MD4_STEP (MD4_Fo, b, c, d, a, w0_t[3], MD4C00, MD4S03);
603 MD4_STEP (MD4_Fo, a, b, c, d, w1_t[0], MD4C00, MD4S00);
604 MD4_STEP (MD4_Fo, d, a, b, c, w1_t[1], MD4C00, MD4S01);
605 MD4_STEP (MD4_Fo, c, d, a, b, w1_t[2], MD4C00, MD4S02);
606 MD4_STEP (MD4_Fo, b, c, d, a, w1_t[3], MD4C00, MD4S03);
607 MD4_STEP (MD4_Fo, a, b, c, d, w2_t[0], MD4C00, MD4S00);
608 MD4_STEP (MD4_Fo, d, a, b, c, w2_t[1], MD4C00, MD4S01);
609 MD4_STEP (MD4_Fo, c, d, a, b, w2_t[2], MD4C00, MD4S02);
610 MD4_STEP (MD4_Fo, b, c, d, a, w2_t[3], MD4C00, MD4S03);
611 MD4_STEP (MD4_Fo, a, b, c, d, w3_t[0], MD4C00, MD4S00);
612 MD4_STEP (MD4_Fo, d, a, b, c, w3_t[1], MD4C00, MD4S01);
613 MD4_STEP (MD4_Fo, c, d, a, b, w3_t[2], MD4C00, MD4S02);
614 MD4_STEP (MD4_Fo, b, c, d, a, w3_t[3], MD4C00, MD4S03);
616 MD4_STEP (MD4_Go, a, b, c, d, w0_t[0], MD4C01, MD4S10);
617 MD4_STEP (MD4_Go, d, a, b, c, w1_t[0], MD4C01, MD4S11);
618 MD4_STEP (MD4_Go, c, d, a, b, w2_t[0], MD4C01, MD4S12);
619 MD4_STEP (MD4_Go, b, c, d, a, w3_t[0], MD4C01, MD4S13);
620 MD4_STEP (MD4_Go, a, b, c, d, w0_t[1], MD4C01, MD4S10);
621 MD4_STEP (MD4_Go, d, a, b, c, w1_t[1], MD4C01, MD4S11);
622 MD4_STEP (MD4_Go, c, d, a, b, w2_t[1], MD4C01, MD4S12);
623 MD4_STEP (MD4_Go, b, c, d, a, w3_t[1], MD4C01, MD4S13);
624 MD4_STEP (MD4_Go, a, b, c, d, w0_t[2], MD4C01, MD4S10);
625 MD4_STEP (MD4_Go, d, a, b, c, w1_t[2], MD4C01, MD4S11);
626 MD4_STEP (MD4_Go, c, d, a, b, w2_t[2], MD4C01, MD4S12);
627 MD4_STEP (MD4_Go, b, c, d, a, w3_t[2], MD4C01, MD4S13);
628 MD4_STEP (MD4_Go, a, b, c, d, w0_t[3], MD4C01, MD4S10);
629 MD4_STEP (MD4_Go, d, a, b, c, w1_t[3], MD4C01, MD4S11);
630 MD4_STEP (MD4_Go, c, d, a, b, w2_t[3], MD4C01, MD4S12);
631 MD4_STEP (MD4_Go, b, c, d, a, w3_t[3], MD4C01, MD4S13);
633 MD4_STEP (MD4_H , a, b, c, d, w0_t[0], MD4C02, MD4S20);
634 MD4_STEP (MD4_H , d, a, b, c, w2_t[0], MD4C02, MD4S21);
635 MD4_STEP (MD4_H , c, d, a, b, w1_t[0], MD4C02, MD4S22);
636 MD4_STEP (MD4_H , b, c, d, a, w3_t[0], MD4C02, MD4S23);
637 MD4_STEP (MD4_H , a, b, c, d, w0_t[2], MD4C02, MD4S20);
638 MD4_STEP (MD4_H , d, a, b, c, w2_t[2], MD4C02, MD4S21);
639 MD4_STEP (MD4_H , c, d, a, b, w1_t[2], MD4C02, MD4S22);
640 MD4_STEP (MD4_H , b, c, d, a, w3_t[2], MD4C02, MD4S23);
641 MD4_STEP (MD4_H , a, b, c, d, w0_t[1], MD4C02, MD4S20);
642 MD4_STEP (MD4_H , d, a, b, c, w2_t[1], MD4C02, MD4S21);
643 MD4_STEP (MD4_H , c, d, a, b, w1_t[1], MD4C02, MD4S22);
644 MD4_STEP (MD4_H , b, c, d, a, w3_t[1], MD4C02, MD4S23);
645 MD4_STEP (MD4_H , a, b, c, d, w0_t[3], MD4C02, MD4S20);
646 MD4_STEP (MD4_H , d, a, b, c, w2_t[3], MD4C02, MD4S21);
648 if (allx (s2 != ((d + MD4M_D) >> 16))) continue;
650 MD4_STEP (MD4_H , c, d, a, b, w1_t[3], MD4C02, MD4S22);
651 MD4_STEP (MD4_H , b, c, d, a, w3_t[3], MD4C02, MD4S23);
664 transform_netntlmv1_key (a, b, key);
669 _des_crypt_keysetup (key[0], key[1], Kc, Kd, s_skb);
673 _des_crypt_encrypt (iv1, data, Kc, Kd, s_SPtrans);
679 const u32 bc = (b >> 24) | (c << 8);
680 const u32 cd = (c >> 24) | (d << 8);
682 transform_netntlmv1_key (bc, cd, key);
684 _des_crypt_keysetup (key[0], key[1], Kc, Kd, s_skb);
688 _des_crypt_encrypt (iv2, data, Kc, Kd, s_SPtrans);
694 const u32 r0 = iv1[0];
695 const u32 r1 = iv1[1];
696 const u32 r2 = iv2[0];
697 const u32 r3 = iv2[1];
703 __kernel void m05500_m08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
707 __kernel void m05500_m16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
711 __kernel void m05500_s04 (__global pw_t *pws, __global kernel_rule_t * rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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)
717 const u32 gid = get_global_id (0);
718 const u32 lid = get_local_id (0);
719 const u32 lsz = get_local_size (0);
725 __local u32 s_SPtrans[8][64];
726 __local u32 s_skb[8][64];
728 for (u32 i = lid; i < 64; i += lsz)
730 s_SPtrans[0][i] = c_SPtrans[0][i];
731 s_SPtrans[1][i] = c_SPtrans[1][i];
732 s_SPtrans[2][i] = c_SPtrans[2][i];
733 s_SPtrans[3][i] = c_SPtrans[3][i];
734 s_SPtrans[4][i] = c_SPtrans[4][i];
735 s_SPtrans[5][i] = c_SPtrans[5][i];
736 s_SPtrans[6][i] = c_SPtrans[6][i];
737 s_SPtrans[7][i] = c_SPtrans[7][i];
739 s_skb[0][i] = c_skb[0][i];
740 s_skb[1][i] = c_skb[1][i];
741 s_skb[2][i] = c_skb[2][i];
742 s_skb[3][i] = c_skb[3][i];
743 s_skb[4][i] = c_skb[4][i];
744 s_skb[5][i] = c_skb[5][i];
745 s_skb[6][i] = c_skb[6][i];
746 s_skb[7][i] = c_skb[7][i];
749 barrier (CLK_LOCAL_MEM_FENCE);
751 if (gid >= gid_max) return;
759 pw_buf0[0] = pws[gid].i[ 0];
760 pw_buf0[1] = pws[gid].i[ 1];
761 pw_buf0[2] = pws[gid].i[ 2];
762 pw_buf0[3] = pws[gid].i[ 3];
766 pw_buf1[0] = pws[gid].i[ 4];
767 pw_buf1[1] = pws[gid].i[ 5];
768 pw_buf1[2] = pws[gid].i[ 6];
769 pw_buf1[3] = pws[gid].i[ 7];
771 const u32 pw_len = pws[gid].pw_len;
777 const u32 s0 = salt_bufs[salt_pos].salt_buf[0];
778 const u32 s1 = salt_bufs[salt_pos].salt_buf[1];
779 const u32 s2 = salt_bufs[salt_pos].salt_buf[2];
790 const u32 search[4] =
792 digests_buf[digests_offset].digest_buf[DGST_R0],
793 digests_buf[digests_offset].digest_buf[DGST_R1],
794 digests_buf[digests_offset].digest_buf[DGST_R2],
795 digests_buf[digests_offset].digest_buf[DGST_R3]
802 for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
832 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
834 append_0x80_2x4 (w0, w1, out_len);
841 make_unicode (w0, w0_t, w1_t);
842 make_unicode (w1, w2_t, w3_t);
844 w3_t[2] = out_len * 8 * 2;
851 MD4_STEP (MD4_Fo, a, b, c, d, w0_t[0], MD4C00, MD4S00);
852 MD4_STEP (MD4_Fo, d, a, b, c, w0_t[1], MD4C00, MD4S01);
853 MD4_STEP (MD4_Fo, c, d, a, b, w0_t[2], MD4C00, MD4S02);
854 MD4_STEP (MD4_Fo, b, c, d, a, w0_t[3], MD4C00, MD4S03);
855 MD4_STEP (MD4_Fo, a, b, c, d, w1_t[0], MD4C00, MD4S00);
856 MD4_STEP (MD4_Fo, d, a, b, c, w1_t[1], MD4C00, MD4S01);
857 MD4_STEP (MD4_Fo, c, d, a, b, w1_t[2], MD4C00, MD4S02);
858 MD4_STEP (MD4_Fo, b, c, d, a, w1_t[3], MD4C00, MD4S03);
859 MD4_STEP (MD4_Fo, a, b, c, d, w2_t[0], MD4C00, MD4S00);
860 MD4_STEP (MD4_Fo, d, a, b, c, w2_t[1], MD4C00, MD4S01);
861 MD4_STEP (MD4_Fo, c, d, a, b, w2_t[2], MD4C00, MD4S02);
862 MD4_STEP (MD4_Fo, b, c, d, a, w2_t[3], MD4C00, MD4S03);
863 MD4_STEP (MD4_Fo, a, b, c, d, w3_t[0], MD4C00, MD4S00);
864 MD4_STEP (MD4_Fo, d, a, b, c, w3_t[1], MD4C00, MD4S01);
865 MD4_STEP (MD4_Fo, c, d, a, b, w3_t[2], MD4C00, MD4S02);
866 MD4_STEP (MD4_Fo, b, c, d, a, w3_t[3], MD4C00, MD4S03);
868 MD4_STEP (MD4_Go, a, b, c, d, w0_t[0], MD4C01, MD4S10);
869 MD4_STEP (MD4_Go, d, a, b, c, w1_t[0], MD4C01, MD4S11);
870 MD4_STEP (MD4_Go, c, d, a, b, w2_t[0], MD4C01, MD4S12);
871 MD4_STEP (MD4_Go, b, c, d, a, w3_t[0], MD4C01, MD4S13);
872 MD4_STEP (MD4_Go, a, b, c, d, w0_t[1], MD4C01, MD4S10);
873 MD4_STEP (MD4_Go, d, a, b, c, w1_t[1], MD4C01, MD4S11);
874 MD4_STEP (MD4_Go, c, d, a, b, w2_t[1], MD4C01, MD4S12);
875 MD4_STEP (MD4_Go, b, c, d, a, w3_t[1], MD4C01, MD4S13);
876 MD4_STEP (MD4_Go, a, b, c, d, w0_t[2], MD4C01, MD4S10);
877 MD4_STEP (MD4_Go, d, a, b, c, w1_t[2], MD4C01, MD4S11);
878 MD4_STEP (MD4_Go, c, d, a, b, w2_t[2], MD4C01, MD4S12);
879 MD4_STEP (MD4_Go, b, c, d, a, w3_t[2], MD4C01, MD4S13);
880 MD4_STEP (MD4_Go, a, b, c, d, w0_t[3], MD4C01, MD4S10);
881 MD4_STEP (MD4_Go, d, a, b, c, w1_t[3], MD4C01, MD4S11);
882 MD4_STEP (MD4_Go, c, d, a, b, w2_t[3], MD4C01, MD4S12);
883 MD4_STEP (MD4_Go, b, c, d, a, w3_t[3], MD4C01, MD4S13);
885 MD4_STEP (MD4_H , a, b, c, d, w0_t[0], MD4C02, MD4S20);
886 MD4_STEP (MD4_H , d, a, b, c, w2_t[0], MD4C02, MD4S21);
887 MD4_STEP (MD4_H , c, d, a, b, w1_t[0], MD4C02, MD4S22);
888 MD4_STEP (MD4_H , b, c, d, a, w3_t[0], MD4C02, MD4S23);
889 MD4_STEP (MD4_H , a, b, c, d, w0_t[2], MD4C02, MD4S20);
890 MD4_STEP (MD4_H , d, a, b, c, w2_t[2], MD4C02, MD4S21);
891 MD4_STEP (MD4_H , c, d, a, b, w1_t[2], MD4C02, MD4S22);
892 MD4_STEP (MD4_H , b, c, d, a, w3_t[2], MD4C02, MD4S23);
893 MD4_STEP (MD4_H , a, b, c, d, w0_t[1], MD4C02, MD4S20);
894 MD4_STEP (MD4_H , d, a, b, c, w2_t[1], MD4C02, MD4S21);
895 MD4_STEP (MD4_H , c, d, a, b, w1_t[1], MD4C02, MD4S22);
896 MD4_STEP (MD4_H , b, c, d, a, w3_t[1], MD4C02, MD4S23);
897 MD4_STEP (MD4_H , a, b, c, d, w0_t[3], MD4C02, MD4S20);
898 MD4_STEP (MD4_H , d, a, b, c, w2_t[3], MD4C02, MD4S21);
900 if (allx (s2 != ((d + MD4M_D) >> 16))) continue;
902 MD4_STEP (MD4_H , c, d, a, b, w1_t[3], MD4C02, MD4S22);
903 MD4_STEP (MD4_H , b, c, d, a, w3_t[3], MD4C02, MD4S23);
916 transform_netntlmv1_key (a, b, key);
921 _des_crypt_keysetup (key[0], key[1], Kc, Kd, s_skb);
925 _des_crypt_encrypt (iv1, data, Kc, Kd, s_SPtrans);
932 transform_netntlmv1_key (((b >> 24) | (c << 8)), ((c >> 24) | (d << 8)), key);
934 _des_crypt_keysetup (key[0], key[1], Kc, Kd, s_skb);
938 _des_crypt_encrypt (iv2, data, Kc, Kd, s_SPtrans);
950 const u32 r0 = iv1[0];
951 const u32 r1 = iv1[1];
952 const u32 r2 = iv2[0];
953 const u32 r3 = iv2[1];
959 __kernel void m05500_s08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
963 __kernel void m05500_s16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)