summaryrefslogtreecommitdiffstats
path: root/kernel/auditsc.c
blob: d7382c2aaa9efb21582d276472b5c3c261d4ccf1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
/* auditsc.c -- System-call auditing support
 * Handles all system-call specific auditing features.
 *
 * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
 * Copyright 2005 Hewlett-Packard Development Company, L.P.
 * Copyright (C) 2005, 2006 IBM Corporation
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * Written by Rickard E. (Rik) Faith <faith@redhat.com>
 *
 * Many of the ideas implemented here are from Stephen C. Tweedie,
 * especially the idea of avoiding a copy by using getname.
 *
 * The method for actual interception of syscall entry and exit (not in
 * this file -- see entry.S) is based on a GPL'd patch written by
 * okir@suse.de and Copyright 2003 SuSE Linux AG.
 *
 * POSIX message queue support added by George Wilson <ltcgcw@us.ibm.com>,
 * 2006.
 *
 * The support of additional filter rules compares (>, <, >=, <=) was
 * added by Dustin Kirkland <dustin.kirkland@us.ibm.com>, 2005.
 *
 * Modified by Amy Griffis <amy.griffis@hp.com> to collect additional
 * filesystem information.
 *
 * Subject and object context labeling support added by <danjones@us.ibm.com>
 * and <dustin.kirkland@us.ibm.com> for LSPP certification compliance.
 */

#include <linux/init.h>
#include <asm/types.h>
#include <linux/atomic.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/socket.h>
#include <linux/mqueue.h>
#include <linux/audit.h>
#include <linux/personality.h>
#include <linux/time.h>
#include <linux/netlink.h>
#include <linux/compiler.h>
#include <asm/unistd.h>
#include <linux/security.h>
#include <linux/list.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/fs_struct.h>

#include "audit.h"

/* flags stating the success for a syscall */
#define AUDITSC_INVALID 0
#define AUDITSC_SUCCESS 1
#define AUDITSC_FAILURE 2

/* AUDIT_NAMES is the number of slots we reserve in the audit_context
 * for saving names from getname().  If we get more names we will allocate
 * a name dynamically and also add those to the list anchored by names_list. */
#define AUDIT_NAMES	5

/* Indicates that audit should log the full pathname. */
#define AUDIT_NAME_FULL -1

/* no execve audit message should be longer than this (userspace limits) */
#define MAX_EXECVE_AUDIT_LEN 7500

/* number of audit rules */
int audit_n_rules;

/* determines whether we collect data for signals sent */
int audit_signals;

struct audit_cap_data {
	kernel_cap_t		permitted;
	kernel_cap_t		inheritable;
	union {
		unsigned int	fE;		/* effective bit of a file capability */
		kernel_cap_t	effective;	/* effective set of a process */
	};
};

/* When fs/namei.c:getname() is called, we store the pointer in name and
 * we don't let putname() free it (instead we free all of the saved
 * pointers at syscall exit time).
 *
 * Further, in fs/namei.c:path_lookup() we store the inode and device. */
struct audit_names {
	struct list_head list;		/* audit_context->names_list */
	const char	*name;
	unsigned long	ino;
	dev_t		dev;
	umode_t		mode;
	uid_t		uid;
	gid_t		gid;
	dev_t		rdev;
	u32		osid;
	struct audit_cap_data fcap;
	unsigned int	fcap_ver;
	int		name_len;	/* number of name's characters to log */
	bool		name_put;	/* call __putname() for this name */
	/*
	 * This was an allocated audit_names and not from the array of
	 * names allocated in the task audit context.  Thus this name
	 * should be freed on syscall exit
	 */
	bool		should_free;
};

struct audit_aux_data {
	struct audit_aux_data	*next;
	int			type;
};

#define AUDIT_AUX_IPCPERM	0

/* Number of target pids per aux struct. */
#define AUDIT_AUX_PIDS	16

struct audit_aux_data_execve {
	struct audit_aux_data	d;
	int argc;
	int envc;
	struct mm_struct *mm;
};

struct audit_aux_data_pids {
	struct audit_aux_data	d;
	pid_t			target_pid[AUDIT_AUX_PIDS];
	uid_t			target_auid[AUDIT_AUX_PIDS];
	uid_t			target_uid[AUDIT_AUX_PIDS];
	unsigned int		target_sessionid[AUDIT_AUX_PIDS];
	u32			target_sid[AUDIT_AUX_PIDS];
	char 			target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN];
	int			pid_count;
};

struct audit_aux_data_bprm_fcaps {
	struct audit_aux_data	d;
	struct audit_cap_data	fcap;
	unsigned int		fcap_ver;
	struct audit_cap_data	old_pcap;
	struct audit_cap_data	new_pcap;
};

struct audit_aux_data_capset {
	struct audit_aux_data	d;
	pid_t			pid;
	struct audit_cap_data	cap;
};

struct audit_tree_refs {
	struct audit_tree_refs *next;
	struct audit_chunk *c[31];
};

/* The per-task audit context. */
struct audit_context {
	int		    dummy;	/* must be the first element */
	int		    in_syscall;	/* 1 if task is in a syscall */
	enum audit_state    state, current_state;
	unsigned int	    serial;     /* serial number for record */
	int		    major;      /* syscall number */
	struct timespec	    ctime;      /* time of syscall entry */
	unsigned long	    argv[4];    /* syscall arguments */
	long		    return_code;/* syscall return code */
	u64		    prio;
	int		    return_valid; /* return code is valid */
	/*
	 * The names_list is the list of all audit_names collected during this
	 * syscall.  The first AUDIT_NAMES entries in the names_list will
	 * actually be from the preallocated_names array for performance
	 * reasons.  Except during allocation they should never be referenced
	 * through the preallocated_names array and should only be found/used
	 * by running the names_list.
	 */
	struct audit_names  preallocated_names[AUDIT_NAMES];
	int		    name_count; /* total records in names_list */
	struct list_head    names_list;	/* anchor for struct audit_names->list */
	char *		    filterkey;	/* key for rule that triggered record */
	struct path	    pwd;
	struct audit_context *previous; /* For nested syscalls */
	struct audit_aux_data *aux;
	struct audit_aux_data *aux_pids;
	struct sockaddr_storage *sockaddr;
	size_t sockaddr_len;
				/* Save things to print about task_struct */
	pid_t		    pid, ppid;
	uid_t		    uid, euid, suid, fsuid;
	gid_t		    gid, egid, sgid, fsgid;
	unsigned long	    personality;
	int		    arch;

	pid_t		    target_pid;
	uid_t		    target_auid;
	uid_t		    target_uid;
	unsigned int	    target_sessionid;
	u32		    target_sid;
	char		    target_comm[TASK_COMM_LEN];

	struct audit_tree_refs *trees, *first_trees;
	struct list_head killed_trees;
	int tree_count;

	int type;
	union {
		struct {
			int nargs;
			long args[6];
		} socketcall;
		struct {
			uid_t			uid;
			gid_t			gid;
			umode_t			mode;
			u32			osid;
			int			has_perm;
			uid_t			perm_uid;
			gid_t			perm_gid;
			umode_t			perm_mode;
			unsigned long		qbytes;
		} ipc;
		struct {
			mqd_t			mqdes;
			struct mq_attr 		mqstat;
		} mq_getsetattr;
		struct {
			mqd_t			mqdes;
			int			sigev_signo;
		} mq_notify;
		struct {
			mqd_t			mqdes;
			size_t			msg_len;
			unsigned int		msg_prio;
			struct timespec		abs_timeout;
		} mq_sendrecv;
		struct {
			int			oflag;
			umode_t			mode;
			struct mq_attr		attr;
		} mq_open;
		struct {
			pid_t			pid;
			struct audit_cap_data	cap;
		} capset;
		struct {
			int			fd;
			int			flags;
		} mmap;
	};
	int fds[2];

#if AUDIT_DEBUG
	int		    put_count;
	int		    ino_count;
#endif
};

static inline int open_arg(int flags, int mask)
{
	int n = ACC_MODE(flags);
	if (flags & (O_TRUNC | O_CREAT))
		n |= AUDIT_PERM_WRITE;
	return n & mask;
}

static int audit_match_perm(struct audit_context *ctx, int mask)
{
	unsigned n;
	if (unlikely(!ctx))
		return 0;
	n = ctx->major;

	switch (audit_classify_syscall(ctx->arch, n)) {
	case 0:	/* native */
		if ((mask & AUDIT_PERM_WRITE) &&
		     audit_match_class(AUDIT_CLASS_WRITE, n))
			return 1;
		if ((mask & AUDIT_PERM_READ) &&
		     audit_match_class(AUDIT_CLASS_READ, n))
			return 1;
		if ((mask & AUDIT_PERM_ATTR) &&
		     audit_match_class(AUDIT_CLASS_CHATTR, n))
			return 1;
		return 0;
	case 1: /* 32bit on biarch */
		if ((mask & AUDIT_PERM_WRITE) &&
		     audit_match_class(AUDIT_CLASS_WRITE_32, n))
			return 1;
		if ((mask & AUDIT_PERM_READ) &&
		     audit_match_class(AUDIT_CLASS_READ_32, n))
			return 1;
		if ((mask & AUDIT_PERM_ATTR) &&
		     audit_match_class(AUDIT_CLASS_CHATTR_32, n))
			return 1;
		return 0;
	case 2: /* open */
		return mask & ACC_MODE(ctx->argv[1]);
	case 3: /* openat */
		return mask & ACC_MODE(ctx->argv[2]);
	case 4: /* socketcall */
		return ((mask & AUDIT_PERM_WRITE) && ctx->argv[0] == SYS_BIND);
	case 5: /* execve */
		return mask & AUDIT_PERM_EXEC;
	default:
		return 0;
	}
}

static int audit_match_filetype(struct audit_context *ctx, int val)
{
	struct audit_names *n;
	umode_t mode = (umode_t)val;

	if (unlikely(!ctx))
		return 0;

	list_for_each_entry(n, &ctx->names_list, list) {
		if ((n->ino != -1) &&
		    ((n->mode & S_IFMT) == mode))
			return 1;
	}

	return 0;
}

/*
 * We keep a linked list of fixed-sized (31 pointer) arrays of audit_chunk *;
 * ->first_trees points to its beginning, ->trees - to the current end of data.
 * ->tree_count is the number of free entries in array pointed to by ->trees.
 * Original condition is (NULL, NULL, 0); as soon as it grows we never revert to NULL,
 * "empty" becomes (p, p, 31) afterwards.  We don't shrink the list (and seriously,
 * it's going to remain 1-element for almost any setup) until we free context itself.
 * References in it _are_ dropped - at the same time we free/drop aux stuff.
 */

#ifdef CONFIG_AUDIT_TREE
static void audit_set_auditable(struct audit_context *ctx)
{
	if (!ctx->prio) {
		ctx->prio = 1;
		ctx->current_state = AUDIT_RECORD_CONTEXT;
	}
}

static int put_tree_ref(struct audit_context *ctx, struct audit_chunk *chunk)
{
	struct audit_tree_refs *p = ctx->trees;
	int left = ctx->tree_count;
	if (likely(left)) {
		p->c[--left] = chunk;
		ctx->tree_count = left;
		return 1;
	}
	if (!p)
		return 0;
	p = p->next;
	if (p) {
		p->c[30] = chunk;
		ctx->trees = p;
		ctx->tree_count = 30;
		return 1;
	}
	return 0;
}

static int grow_tree_refs(struct audit_context *ctx)
{
	struct audit_tree_refs *p = ctx->trees;
	ctx->trees = kzalloc(sizeof(struct audit_tree_refs), GFP_KERNEL);
	if (!ctx->trees) {
		ctx->trees = p;
		return 0;
	}
	if (p)
		p->next = ctx->trees;
	else
		ctx->first_trees = ctx->trees;
	ctx->tree_count = 31;
	return 1;
}
#endif

static void unroll_tree_refs(struct audit_context *ctx,
		      struct audit_tree_refs *p, int count)
{
#ifdef CONFIG_AUDIT_TREE
	struct audit_tree_refs *q;
	int n;
	if (!p) {
		/* we started with empty chain */
		p = ctx->first_trees;
		count = 31;
		/* if the very first allocation has failed, nothing to do */
		if (!p)
			return;
	}
	n = count;
	for (q = p; q != ctx->trees; q = q->next, n = 31) {
		while (n--) {
			audit_put_chunk(q->c[n]);
			q->c[n] = NULL;
		}
	}
	while (n-- > ctx->tree_count) {
		audit_put_chunk(q->c[n]);
		q->c[n] = NULL;
	}
	ctx->trees = p;
	ctx->tree_count = count;
#endif
}

static void free_tree_refs(struct audit_context *ctx)
{
	struct audit_tree_refs *p, *q;
	for (p = ctx->first_trees; p; p = q) {
		q = p->next;
		kfree(p);
	}
}

static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree)
{
#ifdef CONFIG_AUDIT_TREE
	struct audit_tree_refs *p;
	int n;
	if (!tree)
		return 0;
	/* full ones */
	for (p = ctx->first_trees; p != ctx->trees; p = p->next) {
		for (n = 0; n < 31; n++)
			if (audit_tree_match(p->c[n], tree))
				return 1;
	}
	/* partial */
	if (p) {
		for (n = ctx->tree_count; n < 31; n++)
			if (audit_tree_match(p->c[n], tree))
				return 1;
	}
#endif
	return 0;
}

/* Determine if any context name data matches a rule's watch data */
/* Compare a task_struct with an audit_rule.  Return 1 on match, 0
 * otherwise.
 *
 * If task_creation is true, this is an explicit indication that we are
 * filtering a task rule at task creation time.  This and tsk == current are
 * the only situations where tsk->cred may be accessed without an rcu read lock.
 */
static int audit_filter_rules(struct task_struct *tsk,
			      struct audit_krule *rule,
			      struct audit_context *ctx,
			      struct audit_names *name,
			      enum audit_state *state,
			      bool task_creation)
{
	const struct cred *cred;
	int i, need_sid = 1;
	u32 sid;

	cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation);

	for (i = 0; i < rule->field_count; i++) {
		struct audit_field *f = &rule->fields[i];
		struct audit_names *n;
		int result = 0;

		switch (f->type) {
		case AUDIT_PID:
			result = audit_comparator(tsk->pid, f->op, f->val);
			break;
		case AUDIT_PPID:
			if (ctx) {
				if (!ctx->ppid)
					ctx->ppid = sys_getppid();
				result = audit_comparator(ctx->ppid, f->op, f->val);
			}
			break;
		case AUDIT_UID:
			result = audit_comparator(cred->uid, f->op, f->val);
			break;
		case AUDIT_EUID:
			result = audit_comparator(cred->euid, f->op, f->val);
			break;
		case AUDIT_SUID:
			result = audit_comparator(cred->suid, f->op, f->val);
			break;
		case AUDIT_FSUID:
			result = audit_comparator(cred->fsuid, f->op, f->val);
			break;
		case AUDIT_GID:
			result = audit_comparator(cred->gid, f->op, f->val);
			break;
		case AUDIT_EGID:
			result = audit_comparator(cred->egid, f->op, f->val);
			break;
		case AUDIT_SGID:
			result = audit_comparator(cred->sgid, f->op, f->val);
			break;
		case AUDIT_FSGID:
			result = audit_comparator(cred->fsgid, f->op, f->val);
			break;
		case AUDIT_PERS:
			result = audit_comparator(tsk->personality, f->op, f->val);
			break;
		case AUDIT_ARCH:
			if (ctx)
				result = audit_comparator(ctx->arch, f->op, f->val);
			break;

		case AUDIT_EXIT:
			if (ctx && ctx->return_valid)
				result = audit_comparator(ctx->return_code, f->op, f->val);
			break;
		case AUDIT_SUCCESS:
			if (ctx && ctx->return_valid) {
				if (f->val)
					result = audit_comparator(ctx->return_valid, f->op, AUDITSC_SUCCESS);
				else
					result = audit_comparator(ctx->return_valid, f->op, AUDITSC_FAILURE);
			}
			break;
		case AUDIT_DEVMAJOR:
			if (name) {
				if (audit_comparator(MAJOR(name->dev), f->op, f->val) ||
				    audit_comparator(MAJOR(name->rdev), f->op, f->val))
					++result;
			} else if (ctx) {
				list_for_each_entry(n, &ctx->names_list, list) {
					if (audit_comparator(MAJOR(n->dev), f->op, f->val) ||
					    audit_comparator(MAJOR(n->rdev), f->op, f->val)) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_DEVMINOR:
			if (name) {
				if (audit_comparator(MINOR(name->dev), f->op, f->val) ||
				    audit_comparator(MINOR(name->rdev), f->op, f->val))
					++result;
			} else if (ctx) {
				list_for_each_entry(n, &ctx->names_list, list) {
					if (audit_comparator(MINOR(n->dev), f->op, f->val) ||
					    audit_comparator(MINOR(n->rdev), f->op, f->val)) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_INODE:
			if (name)
				result = (name->ino == f->val);
			else if (ctx) {
				list_for_each_entry(n, &ctx->names_list, list) {
					if (audit_comparator(n->ino, f->op, f->val)) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_WATCH:
			if (name)
				result = audit_watch_compare(rule->watch, name->ino, name->dev);
			break;
		case AUDIT_DIR:
			if (ctx)
				result = match_tree_refs(ctx, rule->tree);
			break;
		case AUDIT_LOGINUID:
			result = 0;
			if (ctx)
				result = audit_comparator(tsk->loginuid, f->op, f->val);
			break;
		case AUDIT_SUBJ_USER:
		case AUDIT_SUBJ_ROLE:
		case AUDIT_SUBJ_TYPE:
		case AUDIT_SUBJ_SEN:
		case AUDIT_SUBJ_CLR:
			/* NOTE: this may return negative values indicating
			   a temporary error.  We simply treat this as a
			   match for now to avoid losing information that
			   may be wanted.   An error message will also be
			   logged upon error */
			if (f->lsm_rule) {
				if (need_sid) {
					security_task_getsecid(tsk, &sid);
					need_sid = 0;
				}
				result = security_audit_rule_match(sid, f->type,
				                                  f->op,
				                                  f->lsm_rule,
				                                  ctx);
			}
			break;
		case AUDIT_OBJ_USER:
		case AUDIT_OBJ_ROLE:
		case AUDIT_OBJ_TYPE:
		case AUDIT_OBJ_LEV_LOW:
		case AUDIT_OBJ_LEV_HIGH:
			/* The above note for AUDIT_SUBJ_USER...AUDIT_SUBJ_CLR
			   also applies here */
			if (f->lsm_rule) {
				/* Find files that match */
				if (name) {
					result = security_audit_rule_match(
					           name->osid, f->type, f->op,
					           f->lsm_rule, ctx);
				} else if (ctx) {
					list_for_each_entry(n, &ctx->names_list, list) {
						if (security_audit_rule_match(n->osid, f->type,
									      f->op, f->lsm_rule,
									      ctx)) {
							++result;
							break;
						}
					}
				}
				/* Find ipc objects that match */
				if (!ctx || ctx->type != AUDIT_IPC)
					break;
				if (security_audit_rule_match(ctx->ipc.osid,
							      f->type, f->op,
							      f->lsm_rule, ctx))
					++result;
			}
			break;
		case AUDIT_ARG0:
		case AUDIT_ARG1:
		case AUDIT_ARG2:
		case AUDIT_ARG3:
			if (ctx)
				result = audit_comparator(ctx->argv[f->type-AUDIT_ARG0], f->op, f->val);
			break;
		case AUDIT_FILTERKEY:
			/* ignore this field for filtering */
			result = 1;
			break;
		case AUDIT_PERM:
			result = audit_match_perm(ctx, f->val);
			break;
		case AUDIT_FILETYPE:
			result = audit_match_filetype(ctx, f->val);
			break;
		}

		if (!result)
			return 0;
	}

	if (ctx) {
		if (rule->prio <= ctx->prio)
			return 0;
		if (rule->filterkey) {
			kfree(ctx->filterkey);
			ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
		}
		ctx->prio = rule->prio;
	}
	switch (rule->action) {
	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
	}
	return 1;
}

/* At process creation time, we can determine if system-call auditing is
 * completely disabled for this task.  Since we only have the task
 * structure at this point, we can only check uid and gid.
 */
static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
{
	struct audit_entry *e;
	enum audit_state   state;

	rcu_read_lock();
	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
		if (audit_filter_rules(tsk, &e->rule, NULL, NULL,
				       &state, true)) {
			if (state == AUDIT_RECORD_CONTEXT)
				*key = kstrdup(e->rule.filterkey, GFP_ATOMIC);
			rcu_read_unlock();
			return state;
		}
	}
	rcu_read_unlock();
	return AUDIT_BUILD_CONTEXT;
}

/* At syscall entry and exit time, this filter is called if the
 * audit_state is not low enough that auditing cannot take place, but is
 * also not high enough that we already know we have to write an audit
 * record (i.e., the state is AUDIT_SETUP_CONTEXT or AUDIT_BUILD_CONTEXT).
 */
static enum audit_state audit_filter_syscall(struct task_struct *tsk,
					     struct audit_context *ctx,
					     struct list_head *list)
{
	struct audit_entry *e;
	enum audit_state state;

	if (audit_pid && tsk->tgid == audit_pid)
		return AUDIT_DISABLED;

	rcu_read_lock();
	if (!list_empty(list)) {
		int word = AUDIT_WORD(ctx->major);
		int bit  = AUDIT_BIT(ctx->major);

		list_for_each_entry_rcu(e, list, list) {
			if ((e->rule.mask[word] & bit) == bit &&
			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
					       &state, false)) {
				rcu_read_unlock();
				ctx->current_state = state;
				return state;
			}
		}
	}
	rcu_read_unlock();
	return AUDIT_BUILD_CONTEXT;
}

/*
 * Given an audit_name check the inode hash table to see if they match.
 * Called holding the rcu read lock to protect the use of audit_inode_hash
 */
static int audit_filter_inode_name(struct task_struct *tsk,
				   struct audit_names *n,
				   struct audit_context *ctx) {
	int word, bit;
	int h = audit_hash_ino((u32)n->ino);
	struct list_head *list = &audit_inode_hash[h];
	struct audit_entry *e;
	enum audit_state state;

	word = AUDIT_WORD(ctx->major);
	bit  = AUDIT_BIT(ctx->major);

	if (list_empty(list))
		return 0;

	list_for_each_entry_rcu(e, list, list) {
		if ((e->rule.mask[word] & bit) == bit &&
		    audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
			ctx->current_state = state;
			return 1;
		}
	}

	return 0;
}

/* At syscall exit time, this filter is called if any audit_names have been
 * collected during syscall processing.  We only check rules in sublists at hash
 * buckets applicable to the inode numbers in audit_names.
 * Regarding audit_state, same rules apply as for audit_filter_syscall().
 */
void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
{
	struct audit_names *n;

	if (audit_pid && tsk->tgid == audit_pid)
		return;

	rcu_read_lock();

	list_for_each_entry(n, &ctx->names_list, list) {
		if (audit_filter_inode_name(tsk, n, ctx))
			break;
	}
	rcu_read_unlock();
}

static inline struct audit_context *audit_get_context(struct task_struct *tsk,
						      int return_valid,
						      long return_code)
{
	struct audit_context *context = tsk->audit_context;

	if (!context)
		return NULL;
	context->return_valid = return_valid;

	/*
	 * we need to fix up the return code in the audit logs if the actual
	 * return codes are later going to be fixed up by the arch specific
	 * signal handlers
	 *
	 * This is actually a test for:
	 * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
	 * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
	 *
	 * but is faster than a bunch of ||
	 */
	if (unlikely(return_code <= -ERESTARTSYS) &&
	    (return_code >= -ERESTART_RESTARTBLOCK) &&
	    (return_code != -ENOIOCTLCMD))
		context->return_code = -EINTR;
	else
		context->return_code  = return_code;

	if (context->in_syscall && !context->dummy) {
		audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
		audit_filter_inodes(tsk, context);
	}

	tsk->audit_context = NULL;
	return context;
}

static inline void audit_free_names(struct audit_context *context)
{
	struct audit_names *n, *next;

#if AUDIT_DEBUG == 2
	if (context->put_count + context->ino_count != context->name_count) {
		printk(KERN_ERR "%s:%d(:%d): major=%d in_syscall=%d"
		       " name_count=%d put_count=%d"
		       " ino_count=%d [NOT freeing]\n",
		       __FILE__, __LINE__,
		       context->serial, context->major, context->in_syscall,
		       context->name_count, context->put_count,
		       context->ino_count);
		list_for_each_entry(n, &context->names_list, list) {
			printk(KERN_ERR "names[%d] = %p = %s\n", i,
			       n->name, n->name ?: "(null)");
		}
		dump_stack();
		return;
	}
#endif
#if AUDIT_DEBUG
	context->put_count  = 0;
	context->ino_count  = 0;
#endif

	list_for_each_entry_safe(n, next, &context->names_list, list) {
		list_del(&n->list);
		if (n->name && n->name_put)
			__putname(n->name);
		if (n->should_free)
			kfree(n);
	}
	context->name_count = 0;
	path_put(&context->pwd);
	context->pwd.dentry = NULL;
	context->pwd.mnt = NULL;
}

static inline void audit_free_aux(struct audit_context *context)
{
	struct audit_aux_data *aux;

	while ((aux = context->aux)) {
		context->aux = aux->next;
		kfree(aux);
	}
	while ((aux = context->aux_pids)) {
		context->aux_pids = aux->next;
		kfree(aux);
	}
}

static inline void audit_zero_context(struct audit_context *context,
				      enum audit_state state)
{
	memset(context, 0, sizeof(*context));
	context->state      = state;
	context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
}

static inline struct audit_context *audit_alloc_context(enum audit_state state)
{
	struct audit_context *context;

	if (!(context = kmalloc(sizeof(*context), GFP_KERNEL)))
		return NULL;
	audit_zero_context(context, state);
	INIT_LIST_HEAD(&context->killed_trees);
	INIT_LIST_HEAD(&context->names_list);
	return context;
}

/**
 * audit_alloc - allocate an audit context block for a task
 * @tsk: task
 *
 * Filter on the task information and allocate a per-task audit context
 * if necessary.  Doing so turns on system call auditing for the
 * specified task.  This is called from copy_process, so no lock is
 * needed.
 */
int audit_alloc(struct task_struct *tsk)
{
	struct audit_context *context;
	enum audit_state     state;
	char *key = NULL;

	if (likely(!audit_ever_enabled))
		return 0; /* Return if not auditing. */

	state = audit_filter_task(tsk, &key);
	if (state == AUDIT_DISABLED)
		return 0;

	if (!(context = audit_alloc_context(state))) {
		kfree(key);
		audit_log_lost("out of memory in audit_alloc");
		return -ENOMEM;
	}
	context->filterkey = key;

	tsk->audit_context  = context;
	set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
	return 0;
}

static inline void audit_free_context(struct audit_context *context)
{
	struct audit_context *previous;
	int		     count = 0;

	do {
		previous = context->previous;
		if (previous || (count &&  count < 10)) {
			++count;
			printk(KERN_ERR "audit(:%d): major=%d name_count=%d:"
			       " freeing multiple contexts (%d)\n",
			       context->serial, context->major,
			       context->name_count, count);
		}
		audit_free_names(context);
		unroll_tree_refs(context, NULL, 0);
		free_tree_refs(context);
		audit_free_aux(context);
		kfree(context->filterkey);
		kfree(context->sockaddr);
		kfree(context);
		context  = previous;
	} while (context);
	if (count >= 10)
		printk(KERN_ERR "audit: freed %d contexts\n", count);
}

void audit_log_task_context(struct audit_buffer *ab)
{
	char *ctx = NULL;
	unsigned len;
	int error;
	u32 sid;

	security_task_getsecid(current, &sid);
	if (!sid)
		return;

	error = security_secid_to_secctx(sid, &ctx, &len);
	if (error) {
		if (error != -EINVAL)
			goto error_path;
		return;
	}

	audit_log_format(ab, " subj=%s", ctx);
	security_release_secctx(ctx, len);
	return;

error_path:
	audit_panic("error in audit_log_task_context");
	return;
}

EXPORT_SYMBOL(audit_log_task_context);

static void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
	char name[sizeof(tsk->comm)];
	struct mm_struct *mm = tsk->mm;
	struct vm_area_struct *vma;

	/* tsk == current */

	get_task_comm(name, tsk);
	audit_log_format(ab, " comm=");
	audit_log_untrustedstring(ab, name);

	if (mm) {
		down_read(&mm->mmap_sem);
		vma = mm->mmap;
		while (vma) {
			if ((vma->vm_flags & VM_EXECUTABLE) &&
			    vma->vm_file) {
				audit_log_d_path(ab, "exe=",
						 &vma->vm_file->f_path);
				break;
			}
			vma = vma->vm_next;
		}
		up_read(&mm->mmap_sem);
	}
	audit_log_task_context(ab);
}

static int audit_log_pid_context(struct audit_context *context, pid_t pid,
				 uid_t auid, uid_t uid, unsigned int sessionid,
				 u32 sid, char *comm)
{
	struct audit_buffer *ab;
	char *ctx = NULL;
	u32 len;
	int rc = 0;

	ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID);
	if (!ab)
		return rc;

	audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, auid,
			 uid, sessionid);
	if (security_secid_to_secctx(sid, &ctx, &len)) {
		audit_log_format(ab, " obj=(none)");
		rc = 1;
	} else {
		audit_log_format(ab, " obj=%s", ctx);
		security_release_secctx(ctx, len);
	}
	audit_log_format(ab, " ocomm=");
	audit_log_untrustedstring(ab, comm);
	audit_log_end(ab);

	return rc;
}

/*
 * to_send and len_sent accounting are very loose estimates.  We aren't
 * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being
 * within about 500 bytes (next page boundary)
 *
 * why snprintf?  an int is up to 12 digits long.  if we just assumed when
 * logging that a[%d]= was going to be 16 characters long we would be wasting
 * space in every audit message.  In one 7500 byte message we can log up to
 * about 1000 min size arguments.  That comes down to about 50% waste of space
 * if we didn't do the snprintf to find out how long arg_num_len was.
 */
static int audit_log_single_execve_arg(struct audit_context *context,
					struct audit_buffer **ab,
					int arg_num,
					size_t *len_sent,
					const char __user *p,
					char *buf)
{
	char arg_num_len_buf[12];
	const char __user *tmp_p = p;
	/* how many digits are in arg_num? 5 is the length of ' a=""' */
	size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
	size_t len, len_left, to_send;
	size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
	unsigned int i, has_cntl = 0, too_long = 0;
	int ret;

	/* strnlen_user includes the null we don't want to send */
	len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1;

	/*
	 * We just created this mm, if we can't find the strings
	 * we just copied into it something is _very_ wrong. Similar
	 * for strings that are too long, we should not have created
	 * any.
	 */
	if (unlikely((len == -1) || len > MAX_ARG_STRLEN - 1)) {
		WARN_ON(1);
		send_sig(SIGKILL, current, 0);
		return -1;
	}

	/* walk the whole argument looking for non-ascii chars */
	do {
		if (len_left > MAX_EXECVE_AUDIT_LEN)
			to_send = MAX_EXECVE_AUDIT_LEN;
		else
			to_send = len_left;
		ret = copy_from_user(buf, tmp_p, to_send);
		/*
		 * There is no reason for this copy to be short. We just
		 * copied them here, and the mm hasn't been exposed to user-
		 * space yet.
		 */
		if (ret) {
			WARN_ON(1);
			send_sig(SIGKILL, current, 0);
			return -1;
		}
		buf[to_send] = '\0';
		has_cntl = audit_string_contains_control(buf, to_send);
		if (has_cntl) {
			/*
			 * hex messages get logged as 2 bytes, so we can only
			 * send half as much in each message
			 */
			max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2;
			break;
		}
		len_left -= to_send;
		tmp_p += to_send;
	} while (len_left > 0);

	len_left = len;

	if (len > max_execve_audit_len)
		too_long = 1;

	/* rewalk the argument actually logging the message */
	for (i = 0; len_left > 0; i++) {
		int room_left;

		if (len_left > max_execve_audit_len)
			to_send = max_execve_audit_len;
		else
			to_send = len_left;

		/* do we have space left to send this argument in this ab? */
		room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent;
		if (has_cntl)
			room_left -= (to_send * 2);
		else
			room_left -= to_send;
		if (room_left < 0) {
			*len_sent = 0;
			audit_log_end(*ab);
			*ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE);
			if (!*ab)
				return 0;
		}

		/*
		 * first record needs to say how long the original string was
		 * so we can be sure nothing was lost.
		 */
		if ((i == 0) && (too_long))
			audit_log_format(*ab, " a%d_len=%zu", arg_num,
					 has_cntl ? 2*len : len);

		/*
		 * normally arguments are small enough to fit and we already
		 * filled buf above when we checked for control characters
		 * so don't bother with another copy_from_user
		 */
		if (len >= max_execve_audit_len)
			ret = copy_from_user(buf, p, to_send);
		else
			ret = 0;
		if (ret) {
			WARN_ON(1);
			send_sig(SIGKILL, current, 0);
			return -1;
		}
		buf[to_send] = '\0';

		/* actually log it */
		audit_log_format(*ab, " a%d", arg_num);
		if (too_long)
			audit_log_format(*ab, "[%d]", i);
		audit_log_format(*ab, "=");
		if (has_cntl)
			audit_log_n_hex(*ab, buf, to_send);
		else
			audit_log_string(*ab, buf);

		p += to_send;
		len_left -= to_send;
		*len_sent += arg_num_len;
		if (has_cntl)
			*len_sent += to_send * 2;
		else
			*len_sent += to_send;
	}
	/* include the null we didn't log */
	return len + 1;
}

static void audit_log_execve_info(struct audit_context *context,
				  struct audit_buffer **ab,
				  struct audit_aux_data_execve *axi)
{
	int i;
	size_t len, len_sent = 0;
	const char __user *p;
	char *buf;

	if (axi->mm != current->mm)
		return; /* execve failed, no additional info */

	p = (const char __user *)axi->mm->arg_start;

	audit_log_format(*ab, "argc=%d", axi->argc);

	/*
	 * we need some kernel buffer to hold the userspace args.  Just
	 * allocate one big one rather than allocating one of the right size
	 * for every single argument inside audit_log_single_execve_arg()
	 * should be <8k allocation so should be pretty safe.
	 */
	buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
	if (!buf) {
		audit_panic("out of memory for argv string\n");
		return;
	}

	for (i = 0; i < axi->argc; i++) {
		len = audit_log_single_execve_arg(context, ab, i,
						  &len_sent, p, buf);
		if (len <= 0)
			break;
		p += len;
	}
	kfree(buf);
}

static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
{
	int i;

	audit_log_format(ab, " %s=", prefix);
	CAP_FOR_EACH_U32(i) {
		audit_log_format(ab, "%08x", cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
	}
}

static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
{
	kernel_cap_t *perm = &name->fcap.permitted;
	kernel_cap_t *inh = &name->fcap.inheritable;
	int log = 0;

	if (!cap_isclear(*perm)) {
		audit_log_cap(ab, "cap_fp", perm);
		log = 1;
	}
	if (!cap_isclear(*inh)) {
		audit_log_cap(ab, "cap_fi", inh);
		log = 1;
	}

	if (log)
		audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver);
}

static void show_special(struct audit_context *context, int *call_panic)
{
	struct audit_buffer *ab;
	int i;

	ab = audit_log_start(context, GFP_KERNEL, context->type);
	if (!ab)
		return;

	switch (context->type) {
	case AUDIT_SOCKETCALL: {
		int nargs = context->socketcall.nargs;
		audit_log_format(ab, "nargs=%d", nargs);
		for (i = 0; i < nargs; i++)
			audit_log_format(ab, " a%d=%lx", i,
				context->socketcall.args[i]);
		break; }
	case AUDIT_IPC: {
		u32 osid = context->ipc.osid;

		audit_log_format(ab, "ouid=%u ogid=%u mode=%#ho",
			 context->ipc.uid, context->ipc.gid, context->ipc.mode);
		if (osid) {
			char *ctx = NULL;
			u32 len;
			if (security_secid_to_secctx(osid, &ctx, &len)) {
				audit_log_format(ab, " osid=%u", osid);
				*call_panic = 1;
			} else {
				audit_log_format(ab, " obj=%s", ctx);
				security_release_secctx(ctx, len);
			}
		}
		if (context->ipc.has_perm) {
			audit_log_end(ab);
			ab = audit_log_start(context, GFP_KERNEL,
					     AUDIT_IPC_SET_PERM);
			audit_log_format(ab,
				"qbytes=%lx ouid=%u ogid=%u mode=%#ho",
				context->ipc.qbytes,
				context->ipc.perm_uid,
				context->ipc.perm_gid,
				context->ipc.perm_mode);
			if (!ab)
				return;
		}
		break; }
	case AUDIT_MQ_OPEN: {
		audit_log_format(ab,
			"oflag=0x%x mode=%#ho mq_flags=0x%lx mq_maxmsg=%ld "
			"mq_msgsize=%ld mq_curmsgs=%ld",
			context->mq_open.oflag, context->mq_open.mode,
			context->mq_open.attr.mq_flags,
			context->mq_open.attr.mq_maxmsg,
			context->mq_open.attr.mq_msgsize,
			context->mq_open.attr.mq_curmsgs);
		break; }
	case AUDIT_MQ_SENDRECV: {
		audit_log_format(ab,
			"mqdes=%d msg_len=%zd msg_prio=%u "
			"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
			context->mq_sendrecv.mqdes,
			context->mq_sendrecv.msg_len,
			context->mq_sendrecv.msg_prio,
			context->mq_sendrecv.abs_timeout.tv_sec,
			context->mq_sendrecv.abs_timeout.tv_nsec);
		break; }
	case AUDIT_MQ_NOTIFY: {
		audit_log_format(ab, "mqdes=%d sigev_signo=%d",
				context->mq_notify.mqdes,
				context->mq_notify.sigev_signo);
		break; }
	case AUDIT_MQ_GETSETATTR: {
		struct mq_attr *attr = &context->mq_getsetattr.mqstat;
		audit_log_format(ab,
			"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
			"mq_curmsgs=%ld ",
			context->mq_getsetattr.mqdes,
			attr->mq_flags, attr->mq_maxmsg,
			attr->mq_msgsize, attr->mq_curmsgs);
		break; }
	case AUDIT_CAPSET: {
		audit_log_format(ab, "pid=%d", context->capset.pid);
		audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable);
		audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted);
		audit_log_cap(ab, "cap_pe", &context->capset.cap.effective);
		break; }
	case AUDIT_MMAP: {
		audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
				 context->mmap.flags);
		break; }
	}
	audit_log_end(ab);
}

static void audit_log_name(struct audit_context *context, struct audit_names *n,
			   int record_num, int *call_panic)
{
	struct audit_buffer *ab;
	ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH);
	if (!ab)
		return; /* audit_panic has been called */

	audit_log_format(ab, "item=%d", record_num);

	if (n->name) {
		switch (n->name_len) {
		case AUDIT_NAME_FULL:
			/* log the full path */
			audit_log_format(ab, " name=");
			audit_log_untrustedstring(ab, n->name);
			break;
		case 0:
			/* name was specified as a relative path and the
			 * directory component is the cwd */
			audit_log_d_path(ab, "name=", &context->pwd);
			break;
		default:
			/* log the name's directory component */
			audit_log_format(ab, " name=");
			audit_log_n_untrustedstring(ab, n->name,
						    n->name_len);
		}
	} else
		audit_log_format(ab, " name=(null)");

	if (n->ino != (unsigned long)-1) {
		audit_log_format(ab, " inode=%lu"
				 " dev=%02x:%02x mode=%#ho"
				 " ouid=%u ogid=%u rdev=%02x:%02x",
				 n->ino,
				 MAJOR(n->dev),
				 MINOR(n->dev),
				 n->mode,
				 n->uid,
				 n->gid,
				 MAJOR(n->rdev),
				 MINOR(n->rdev));
	}
	if (n->osid != 0) {
		char *ctx = NULL;
		u32 len;
		if (security_secid_to_secctx(
			n->osid, &ctx, &len)) {
			audit_log_format(ab, " osid=%u", n->osid);
			*call_panic = 2;
		} else {
			audit_log_format(ab, " obj=%s", ctx);
			security_release_secctx(ctx, len);
		}
	}

	audit_log_fcaps(ab, n);

	audit_log_end(ab);
}

static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
{
	const struct cred *cred;
	int i, call_panic = 0;
	struct audit_buffer *ab;
	struct audit_aux_data *aux;
	const char *tty;
	struct audit_names *n;

	/* tsk == current */
	context->pid = tsk->pid;
	if (!context->ppid)
		context->ppid = sys_getppid();
	cred = current_cred();
	context->uid   = cred->uid;
	context->gid   = cred->gid;
	context->euid  = cred->euid;
	context->suid  = cred->suid;
	context->fsuid = cred->fsuid;
	context->egid  = cred->egid;
	context->sgid  = cred->sgid;
	context->fsgid = cred->fsgid;
	context->personality = tsk->personality;

	ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
	if (!ab)
		return;		/* audit_panic has been called */
	audit_log_format(ab, "arch=%x syscall=%d",
			 context->arch, context->major);
	if (context->personality != PER_LINUX)
		audit_log_format(ab, " per=%lx", context->personality);
	if (context->return_valid)
		audit_log_format(ab, " success=%s exit=%ld",
				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
				 context->return_code);

	spin_lock_irq(&tsk->sighand->siglock);
	if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
		tty = tsk->signal->tty->name;
	else
		tty = "(none)";
	spin_unlock_irq(&tsk->sighand->siglock);

	audit_log_format(ab,
		  " a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
		  " ppid=%d pid=%d auid=%u uid=%u gid=%u"
		  " euid=%u suid=%u fsuid=%u"
		  " egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
		  context->argv[0],
		  context->argv[1],
		  context->argv[2],
		  context->argv[3],
		  context->name_count,
		  context->ppid,
		  context->pid,
		  tsk->loginuid,
		  context->uid,
		  context->gid,
		  context->euid, context->suid, context->fsuid,
		  context->egid, context->sgid, context->fsgid, tty,
		  tsk->sessionid);


	audit_log_task_info(ab, tsk);
	audit_log_key(ab, context->filterkey);
	audit_log_end(ab);

	for (aux = context->aux; aux; aux = aux->next) {

		ab = audit_log_start(context, GFP_KERNEL, aux->type);
		if (!ab)
			continue; /* audit_panic has been called */

		switch (aux->type) {

		case AUDIT_EXECVE: {
			struct audit_aux_data_execve *axi = (void *)aux;
			audit_log_execve_info(context, &ab, axi);
			break; }

		case AUDIT_BPRM_FCAPS: {
			struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
			audit_log_format(ab, "fver=%x", axs->fcap_ver);
			audit_log_cap(ab, "fp", &axs->fcap.permitted);
			audit_log_cap(ab, "fi", &axs->fcap.inheritable);
			audit_log_format(ab, " fe=%d", axs->fcap.fE);
			audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted);
			audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable);
			audit_log_cap(ab, "old_pe", &axs->old_pcap.effective);
			audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted);
			audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable);
			audit_log_cap(ab, "new_pe", &axs->new_pcap.effective);
			break; }

		}
		audit_log_end(ab);
	}

	if (context->type)
		show_special(context, &call_panic);

	if (context->fds[0] >= 0) {
		ab = audit_log_start(context, GFP_KERNEL, AUDIT_FD_PAIR);
		if (ab) {
			audit_log_format(ab, "fd0=%d fd1=%d",
					context->fds[0], context->fds[1]);
			audit_log_end(ab);
		}
	}

	if (context->sockaddr_len) {
		ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR);
		if (ab) {
			audit_log_format(ab, "saddr=");
			audit_log_n_hex(ab, (void *)context->sockaddr,
					context->sockaddr_len);
			audit_log_end(ab);
		}
	}

	for (aux = context->aux_pids; aux; aux = aux->next) {
		struct audit_aux_data_pids *axs = (void *)aux;

		for (i = 0; i < axs->pid_count; i++)
			if (audit_log_pid_context(context, axs->target_pid[i],
						  axs->target_auid[i],
						  axs->target_uid[i],
						  axs->target_sessionid[i],
						  axs->target_sid[i],
						  axs->target_comm[i]))
				call_panic = 1;
	}

	if (context->target_pid &&
	    audit_log_pid_context(context, context->target_pid,
				  context->target_auid, context->target_uid,
				  context->target_sessionid,
				  context->target_sid, context->target_comm))
			call_panic = 1;

	if (context->pwd.dentry && context->pwd.mnt) {
		ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD);
		if (ab) {
			audit_log_d_path(ab, "cwd=", &context->pwd);
			audit_log_end(ab);
		}
	}

	i = 0;
	list_for_each_entry(n, &context->names_list, list)
		audit_log_name(context, n, i++, &call_panic);

	/* Send end of event record to help user space know we are finished */
	ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
	if (ab)
		audit_log_end(ab);
	if (call_panic)
		audit_panic("error converting sid to string");
}

/**
 * audit_free - free a per-task audit context
 * @tsk: task whose audit context block to free
 *
 * Called from copy_process and do_exit
 */
void audit_free(struct task_struct *tsk)
{
	struct audit_context *context;

	context = audit_get_context(tsk, 0, 0);
	if (!context)
		return;

	/* Check for system calls that do not go through the exit
	 * function (e.g., exit_group), then free context block.
	 * We use GFP_ATOMIC here because we might be doing this
	 * in the context of the idle thread */
	/* that can happen only if we are called from do_exit() */
	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
		audit_log_exit(context, tsk);
	if (!list_empty(&context->killed_trees))
		audit_kill_trees(&context->killed_trees);

	audit_free_context(context);
}

/**
 * audit_syscall_entry - fill in an audit record at syscall entry
 * @arch: architecture type
 * @major: major syscall type (function)
 * @a1: additional syscall register 1
 * @a2: additional syscall register 2
 * @a3: additional syscall register 3
 * @a4: additional syscall register 4
 *
 * Fill in audit context at syscall entry.  This only happens if the
 * audit context was created when the task was created and the state or
 * filters demand the audit context be built.  If the state from the
 * per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT,
 * then the record will be written at syscall exit time (otherwise, it
 * will only be written if another part of the kernel requests that it
 * be written).
 */
void __audit_syscall_entry(int arch, int major,
			 unsigned long a1, unsigned long a2,
			 unsigned long a3, unsigned long a4)
{
	struct task_struct *tsk = current;
	struct audit_context *context = tsk->audit_context;
	enum audit_state     state;

	if (!context)
		return;

	/*
	 * This happens only on certain architectures that make system
	 * calls in kernel_thread via the entry.S interface, instead of
	 * with direct calls.  (If you are porting to a new
	 * architecture, hitting this condition can indicate that you
	 * got the _exit/_leave calls backward in entry.S.)
	 *
	 * i386     no
	 * x86_64   no
	 * ppc64    yes (see arch/powerpc/platforms/iseries/misc.S)
	 *
	 * This also happens with vm86 emulation in a non-nested manner
	 * (entries without exits), so this case must be caught.
	 */
	if (context->in_syscall) {
		struct audit_context *newctx;

#if AUDIT_DEBUG
		printk(KERN_ERR
		       "audit(:%d) pid=%d in syscall=%d;"
		       " entering syscall=%d\n",
		       context->serial, tsk->pid, context->major, major);
#endif
		newctx = audit_alloc_context(context->state);
		if (newctx) {
			newctx->previous   = context;
			context		   = newctx;
			tsk->audit_context = newctx;
		} else	{
			/* If we can't alloc a new context, the best we
			 * can do is to leak memory (any pending putname
			 * will be lost).  The only other alternative is
			 * to abandon auditing. */
			audit_zero_context(context, context->state);
		}
	}
	BUG_ON(context->in_syscall || context->name_count);

	if (!audit_enabled)
		return;

	context->arch	    = arch;
	context->major      = major;
	context->argv[0]    = a1;
	context->argv[1]    = a2;
	context->argv[2]    = a3;
	context->argv[3]    = a4;

	state = context->state;
	context->dummy = !audit_n_rules;
	if (!context->dummy && state == AUDIT_BUILD_CONTEXT) {
		context->prio = 0;
		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
	}
	if (state == AUDIT_DISABLED)
		return;

	context->serial     = 0;
	context->ctime      = CURRENT_TIME;
	context->in_syscall = 1;
	context->current_state  = state;
	context->ppid       = 0;
}

void audit_finish_fork(struct task_struct *child)
{
	struct audit_context *ctx = current->audit_context;
	struct audit_context *p = child->audit_context;
	if (!p || !ctx)
		return;
	if (!ctx->in_syscall || ctx->current_state != AUDIT_RECORD_CONTEXT)
		return;
	p->arch = ctx->arch;
	p->major = ctx->major;
	memcpy(p->argv, ctx->argv, sizeof(ctx->argv));
	p->ctime = ctx->ctime;
	p->dummy = ctx->dummy;
	p->in_syscall = ctx->in_syscall;
	p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL);
	p->ppid = current->pid;
	p->prio = ctx->prio;
	p->current_state = ctx->current_state;
}

/**
 * audit_syscall_exit - deallocate audit context after a system call
 * @pt_regs: syscall registers
 *
 * Tear down after system call.  If the audit context has been marked as
 * auditable (either because of the AUDIT_RECORD_CONTEXT state from
 * filtering, or because some other part of the kernel write an audit
 * message), then write out the syscall information.  In call cases,
 * free the names stored from getname().
 */
void __audit_syscall_exit(int success, long return_code)
{
	struct task_struct *tsk = current;
	struct audit_context *context;

	if (success)
		success = AUDITSC_SUCCESS;
	else
		success = AUDITSC_FAILURE;

	context = audit_get_context(tsk, success, return_code);
	if (!context)
		return;

	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
		audit_log_exit(context, tsk);

	context->in_syscall = 0;
	context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;

	if (!list_empty(&context->killed_trees))
		audit_kill_trees(&context->killed_trees);

	if (context->previous) {
		struct audit_context *new_context = context->previous;
		context->previous  = NULL;
		audit_free_context(context);
		tsk->audit_context = new_context;
	} else {
		audit_free_names(context);
		unroll_tree_refs(context, NULL, 0);
		audit_free_aux(context);
		context->aux = NULL;
		context->aux_pids = NULL;
		context->target_pid = 0;
		context->target_sid = 0;
		context->sockaddr_len = 0;
		context->type = 0;
		context->fds[0] = -1;
		if (context->state != AUDIT_RECORD_CONTEXT) {
			kfree(context->filterkey);
			context->filterkey = NULL;
		}
		tsk->audit_context = context;
	}
}

static inline void handle_one(const struct inode *inode)
{
#ifdef CONFIG_AUDIT_TREE
	struct audit_context *context;
	struct audit_tree_refs *p;
	struct audit_chunk *chunk;
	int count;
	if (likely(hlist_empty(&inode->i_fsnotify_marks)))
		return;
	context = current->audit_context;
	p = context->trees;
	count = context->tree_count;
	rcu_read_lock();
	chunk = audit_tree_lookup(inode);
	rcu_read_unlock();
	if (!chunk)
		return;
	if (likely(put_tree_ref(context, chunk)))
		return;
	if (unlikely(!grow_tree_refs(context))) {
		printk(KERN_WARNING "out of memory, audit has lost a tree reference\n");
		audit_set_auditable(context);
		audit_put_chunk(chunk);
		unroll_tree_refs(context, p, count);
		return;
	}
	put_tree_ref(context, chunk);
#endif
}

static void handle_path(const struct dentry *dentry)
{
#ifdef CONFIG_AUDIT_TREE
	struct audit_context *context;
	struct audit_tree_refs *p;
	const struct dentry *d, *parent;
	struct audit_chunk *drop;
	unsigned long seq;
	int count;

	context = current->audit_context;
	p = context->trees;
	count = context->tree_count;
retry:
	drop = NULL;
	d = dentry;
	rcu_read_lock();
	seq = read_seqbegin(&rename_lock);
	for(;;) {
		struct inode *inode = d->d_inode;
		if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) {
			struct audit_chunk *chunk;
			chunk = audit_tree_lookup(inode);
			if (chunk) {
				if (unlikely(!put_tree_ref(context, chunk))) {
					drop = chunk;
					break;
				}
			}
		}
		parent = d->d_parent;
		if (parent == d)
			break;
		d = parent;
	}
	if (unlikely(read_seqretry(&rename_lock, seq) || drop)) {  /* in this order */
		rcu_read_unlock();
		if (!drop) {
			/* just a race with rename */
			unroll_tree_refs(context, p, count);
			goto retry;
		}
		audit_put_chunk(drop);
		if (grow_tree_refs(context)) {
			/* OK, got more space */
			unroll_tree_refs(context, p, count);
			goto retry;
		}
		/* too bad */
		printk(KERN_WARNING
			"out of memory, audit has lost a tree reference\n");
		unroll_tree_refs(context, p, count);
		audit_set_auditable(context);
		return;
	}
	rcu_read_unlock();
#endif
}

static struct audit_names *audit_alloc_name(struct audit_context *context)
{
	struct audit_names *aname;

	if (context->name_count < AUDIT_NAMES) {
		aname = &context->preallocated_names[context->name_count];
		memset(aname, 0, sizeof(*aname));
	} else {
		aname = kzalloc(sizeof(*aname), GFP_NOFS);
		if (!aname)
			return NULL;
		aname->should_free = true;
	}

	aname->ino = (unsigned long)-1;
	list_add_tail(&aname->list, &context->names_list);

	context->name_count++;
#if AUDIT_DEBUG
	context->ino_count++;
#endif
	return aname;
}

/**
 * audit_getname - add a name to the list
 * @name: name to add
 *
 * Add a name to the list of audit names for this context.
 * Called from fs/namei.c:getname().
 */
void __audit_getname(const char *name)
{
	struct audit_context *context = current->audit_context;
	struct audit_names *n;

	if (IS_ERR(name) || !name)
		return;

	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		dump_stack();
#endif
		return;
	}

	n = audit_alloc_name(context);
	if (!n)
		return;

	n->name = name;
	n->name_len = AUDIT_NAME_FULL;
	n->name_put = true;

	if (!context->pwd.dentry)
		get_fs_pwd(current->fs, &context->pwd);
}

/* audit_putname - intercept a putname request
 * @name: name to intercept and delay for putname
 *
 * If we have stored the name from getname in the audit context,
 * then we delay the putname until syscall exit.
 * Called from include/linux/fs.h:putname().
 */
void audit_putname(const char *name)
{
	struct audit_context *context = current->audit_context;

	BUG_ON(!context);
	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		if (context->name_count) {
			struct audit_names *n;
			int i;

			list_for_each_entry(n, &context->names_list, list)
				printk(KERN_ERR "name[%d] = %p = %s\n", i,
				       n->name, n->name ?: "(null)");
			}
#endif
		__putname(name);
	}
#if AUDIT_DEBUG
	else {
		++context->put_count;
		if (context->put_count > context->name_count) {
			printk(KERN_ERR "%s:%d(:%d): major=%d"
			       " in_syscall=%d putname(%p) name_count=%d"
			       " put_count=%d\n",
			       __FILE__, __LINE__,
			       context->serial, context->major,
			       context->in_syscall, name, context->name_count,
			       context->put_count);
			dump_stack();
		}
	}
#endif
}

static inline int audit_copy_fcaps(struct audit_names *name, const struct dentry *dentry)
{
	struct cpu_vfs_cap_data caps;
	int rc;

	if (!dentry)
		return 0;

	rc = get_vfs_caps_from_disk(dentry, &caps);
	if (rc)
		return rc;

	name->fcap.permitted = caps.permitted;
	name->fcap.inheritable = caps.inheritable;
	name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
	name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;

	return 0;
}


/* Copy inode data into an audit_names. */
static void audit_copy_inode(struct audit_names *name, const struct dentry *dentry,
			     const struct inode *inode)
{
	name->ino   = inode->i_ino;
	name->dev   = inode->i_sb->s_dev;
	name->mode  = inode->i_mode;
	name->uid   = inode->i_uid;
	name->gid   = inode->i_gid;
	name->rdev  = inode->i_rdev;
	security_inode_getsecid(inode, &name->osid);
	audit_copy_fcaps(name, dentry);
}

/**
 * audit_inode - store the inode and device from a lookup
 * @name: name being audited
 * @dentry: dentry being audited
 *
 * Called from fs/namei.c:path_lookup().
 */
void __audit_inode(const char *name, const struct dentry *dentry)
{
	struct audit_context *context = current->audit_context;
	const struct inode *inode = dentry->d_inode;
	struct audit_names *n;

	if (!context->in_syscall)
		return;

	list_for_each_entry_reverse(n, &context->names_list, list) {
		if (n->name && (n->name == name))
			goto out;
	}

	/* unable to find the name from a previous getname() */
	n = audit_alloc_name(context);
	if (!n)
		return;
out:
	handle_path(dentry);
	audit_copy_inode(n, dentry, inode);
}

/**
 * audit_inode_child - collect inode info for created/removed objects
 * @dentry: dentry being audited
 * @parent: inode of dentry parent
 *
 * For syscalls that create or remove filesystem objects, audit_inode
 * can only collect information for the filesystem object's parent.
 * This call updates the audit context with the child's information.
 * Syscalls that create a new filesystem object must be hooked after
 * the object is created.  Syscalls that remove a filesystem object
 * must be hooked prior, in order to capture the target inode during
 * unsuccessful attempts.
 */
void __audit_inode_child(const struct dentry *dentry,
			 const struct inode *parent)
{
	struct audit_context *context = current->audit_context;
	const char *found_parent = NULL, *found_child = NULL;
	const struct inode *inode = dentry->d_inode;
	const char *dname = dentry->d_name.name;
	struct audit_names *n;
	int dirlen = 0;

	if (!context->in_syscall)
		return;

	if (inode)
		handle_one(inode);

	/* parent is more likely, look for it first */
	list_for_each_entry(n, &context->names_list, list) {
		if (!n->name)
			continue;

		if (n->ino == parent->i_ino &&
		    !audit_compare_dname_path(dname, n->name, &dirlen)) {
			n->name_len = dirlen; /* update parent data in place */
			found_parent = n->name;
			goto add_names;
		}
	}

	/* no matching parent, look for matching child */
	list_for_each_entry(n, &context->names_list, list) {
		if (!n->name)
			continue;

		/* strcmp() is the more likely scenario */
		if (!strcmp(dname, n->name) ||
		     !audit_compare_dname_path(dname, n->name, &dirlen)) {
			if (inode)
				audit_copy_inode(n, NULL, inode);
			else
				n->ino = (unsigned long)-1;
			found_child = n->name;
			goto add_names;
		}
	}

add_names:
	if (!found_parent) {
		n = audit_alloc_name(context);
		if (!n)
			return;
		audit_copy_inode(n, NULL, parent);
	}

	if (!found_child) {
		n = audit_alloc_name(context);
		if (!n)
			return;

		/* Re-use the name belonging to the slot for a matching parent
		 * directory. All names for this context are relinquished in
		 * audit_free_names() */
		if (found_parent) {
			n->name = found_parent;
			n->name_len = AUDIT_NAME_FULL;
			/* don't call __putname() */
			n->name_put = false;
		}

		if (inode)
			audit_copy_inode(n, NULL, inode);
	}
}
EXPORT_SYMBOL_GPL(__audit_inode_child);

/**
 * auditsc_get_stamp - get local copies of audit_context values
 * @ctx: audit_context for the task
 * @t: timespec to store time recorded in the audit_context
 * @serial: serial value that is recorded in the audit_context
 *
 * Also sets the context as auditable.
 */
int auditsc_get_stamp(struct audit_context *ctx,
		       struct timespec *t, unsigned int *serial)
{
	if (!ctx->in_syscall)
		return 0;
	if (!ctx->serial)
		ctx->serial = audit_serial();
	t->tv_sec  = ctx->ctime.tv_sec;
	t->tv_nsec = ctx->ctime.tv_nsec;
	*serial    = ctx->serial;
	if (!ctx->prio) {
		ctx->prio = 1;
		ctx->current_state = AUDIT_RECORD_CONTEXT;
	}
	return 1;
}

/* global counter which is incremented every time something logs in */
static atomic_t session_id = ATOMIC_INIT(0);

/**
 * audit_set_loginuid - set a task's audit_context loginuid
 * @task: task whose audit context is being modified
 * @loginuid: loginuid value
 *
 * Returns 0.
 *
 * Called (set) from fs/proc/base.c::proc_loginuid_write().
 */
int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
{
	unsigned int sessionid = atomic_inc_return(&session_id);
	struct audit_context *context = task->audit_context;

	if (context && context->in_syscall) {
		struct audit_buffer *ab;

		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
		if (ab) {
			audit_log_format(ab, "login pid=%d uid=%u "
				"old auid=%u new auid=%u"
				" old ses=%u new ses=%u",
				task->pid, task_uid(task),
				task->loginuid, loginuid,
				task->sessionid, sessionid);
			audit_log_end(ab);
		}
	}
	task->sessionid = sessionid;
	task->loginuid = loginuid;
	return 0;
}

/**
 * __audit_mq_open - record audit data for a POSIX MQ open
 * @oflag: open flag
 * @mode: mode bits
 * @attr: queue attributes
 *
 */
void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr)
{
	struct audit_context *context = current->audit_context;

	if (attr)
		memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr));
	else
		memset(&context->mq_open.attr, 0, sizeof(struct mq_attr));

	context->mq_open.oflag = oflag;
	context->mq_open.mode = mode;

	context->type = AUDIT_MQ_OPEN;
}

/**
 * __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive
 * @mqdes: MQ descriptor
 * @msg_len: Message length
 * @msg_prio: Message priority
 * @abs_timeout: Message timeout in absolute time
 *
 */
void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
			const struct timespec *abs_timeout)
{
	struct audit_context *context = current->audit_context;
	struct timespec *p = &context->mq_sendrecv.abs_timeout;

	if (abs_timeout)
		memcpy(p, abs_timeout, sizeof(struct timespec));
	else
		memset(p, 0, sizeof(struct timespec));

	context->mq_sendrecv.mqdes = mqdes;
	context->mq_sendrecv.msg_len = msg_len;
	context->mq_sendrecv.msg_prio = msg_prio;

	context->type = AUDIT_MQ_SENDRECV;
}

/**
 * __audit_mq_notify - record audit data for a POSIX MQ notify
 * @mqdes: MQ descriptor
 * @notification: Notification event
 *
 */

void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
{
	struct audit_context *context = current->audit_context;

	if (notification)
		context->mq_notify.sigev_signo = notification->sigev_signo;
	else
		context->mq_notify.sigev_signo = 0;

	context->mq_notify.mqdes = mqdes;
	context->type = AUDIT_MQ_NOTIFY;
}

/**
 * __audit_mq_getsetattr - record audit data for a POSIX MQ get/set attribute
 * @mqdes: MQ descriptor
 * @mqstat: MQ flags
 *
 */
void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
{
	struct audit_context *context = current->audit_context;
	context->mq_getsetattr.mqdes = mqdes;
	context->mq_getsetattr.mqstat = *mqstat;
	context->type = AUDIT_MQ_GETSETATTR;
}

/**
 * audit_ipc_obj - record audit data for ipc object
 * @ipcp: ipc permissions
 *
 */
void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
{
	struct audit_context *context = current->audit_context;
	context->ipc.uid = ipcp->uid;
	context->ipc.gid = ipcp->gid;
	context->ipc.mode = ipcp->mode;
	context->ipc.has_perm = 0;
	security_ipc_getsecid(ipcp, &context->ipc.osid);
	context->type = AUDIT_IPC;
}

/**
 * audit_ipc_set_perm - record audit data for new ipc permissions
 * @qbytes: msgq bytes
 * @uid: msgq user id
 * @gid: msgq group id
 * @mode: msgq mode (permissions)
 *
 * Called only after audit_ipc_obj().
 */
void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode)
{
	struct audit_context *context = current->audit_context;

	context->ipc.qbytes = qbytes;
	context->ipc.perm_uid = uid;
	context->ipc.perm_gid = gid;
	context->ipc.perm_mode = mode;
	context->ipc.has_perm = 1;
}

int audit_bprm(struct linux_binprm *bprm)
{
	struct audit_aux_data_execve *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!audit_enabled || !context || context->dummy))
		return 0;

	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->argc = bprm->argc;
	ax->envc = bprm->envc;
	ax->mm = bprm->mm;
	ax->d.type = AUDIT_EXECVE;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}


/**
 * audit_socketcall - record audit data for sys_socketcall
 * @nargs: number of args
 * @args: args array
 *
 */
void audit_socketcall(int nargs, unsigned long *args)
{
	struct audit_context *context = current->audit_context;

	if (likely(!context || context->dummy))
		return;

	context->type = AUDIT_SOCKETCALL;
	context->socketcall.nargs = nargs;
	memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long));
}

/**
 * __audit_fd_pair - record audit data for pipe and socketpair
 * @fd1: the first file descriptor
 * @fd2: the second file descriptor
 *
 */
void __audit_fd_pair(int fd1, int fd2)
{
	struct audit_context *context = current->audit_context;
	context->fds[0] = fd1;
	context->fds[1] = fd2;
}

/**
 * audit_sockaddr - record audit data for sys_bind, sys_connect, sys_sendto
 * @len: data length in user space
 * @a: data address in kernel space
 *
 * Returns 0 for success or NULL context or < 0 on error.
 */
int audit_sockaddr(int len, void *a)
{
	struct audit_context *context = current->audit_context;

	if (likely(!context || context->dummy))
		return 0;

	if (!context->sockaddr) {
		void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL);
		if (!p)
			return -ENOMEM;
		context->sockaddr = p;
	}

	context->sockaddr_len = len;
	memcpy(context->sockaddr, a, len);
	return 0;
}

void __audit_ptrace(struct task_struct *t)
{
	struct audit_context *context = current->audit_context;

	context->target_pid = t->pid;
	context->target_auid = audit_get_loginuid(t);
	context->target_uid = task_uid(t);
	context->target_sessionid = audit_get_sessionid(t);
	security_task_getsecid(t, &context->target_sid);
	memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
}

/**
 * audit_signal_info - record signal info for shutting down audit subsystem
 * @sig: signal value
 * @t: task being signaled
 *
 * If the audit subsystem is being terminated, record the task (pid)
 * and uid that is doing that.
 */
int __audit_signal_info(int sig, struct task_struct *t)
{
	struct audit_aux_data_pids *axp;
	struct task_struct *tsk = current;
	struct audit_context *ctx = tsk->audit_context;
	uid_t uid = current_uid(), t_uid = task_uid(t);

	if (audit_pid && t->tgid == audit_pid) {
		if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
			audit_sig_pid = tsk->pid;
			if (tsk->loginuid != -1)
				audit_sig_uid = tsk->loginuid;
			else
				audit_sig_uid = uid;
			security_task_getsecid(tsk, &audit_sig_sid);
		}
		if (!audit_signals || audit_dummy_context())
			return 0;
	}

	/* optimize the common case by putting first signal recipient directly
	 * in audit_context */
	if (!ctx->target_pid) {
		ctx->target_pid = t->tgid;
		ctx->target_auid = audit_get_loginuid(t);
		ctx->target_uid = t_uid;
		ctx->target_sessionid = audit_get_sessionid(t);
		security_task_getsecid(t, &ctx->target_sid);
		memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
		return 0;
	}

	axp = (void *)ctx->aux_pids;
	if (!axp || axp->pid_count == AUDIT_AUX_PIDS) {
		axp = kzalloc(sizeof(*axp), GFP_ATOMIC);
		if (!axp)
			return -ENOMEM;

		axp->d.type = AUDIT_OBJ_PID;
		axp->d.next = ctx->aux_pids;
		ctx->aux_pids = (void *)axp;
	}
	BUG_ON(axp->pid_count >= AUDIT_AUX_PIDS);

	axp->target_pid[axp->pid_count] = t->tgid;
	axp->target_auid[axp->pid_count] = audit_get_loginuid(t);
	axp->target_uid[axp->pid_count] = t_uid;
	axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
	security_task_getsecid(t, &axp->target_sid[axp->pid_count]);
	memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
	axp->pid_count++;

	return 0;
}

/**
 * __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps
 * @bprm: pointer to the bprm being processed
 * @new: the proposed new credentials
 * @old: the old credentials
 *
 * Simply check if the proc already has the caps given by the file and if not
 * store the priv escalation info for later auditing at the end of the syscall
 *
 * -Eric
 */
int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
			   const struct cred *new, const struct cred *old)
{
	struct audit_aux_data_bprm_fcaps *ax;
	struct audit_context *context = current->audit_context;
	struct cpu_vfs_cap_data vcaps;
	struct dentry *dentry;

	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->d.type = AUDIT_BPRM_FCAPS;
	ax->d.next = context->aux;
	context->aux = (void *)ax;

	dentry = dget(bprm->file->f_dentry);
	get_vfs_caps_from_disk(dentry, &vcaps);
	dput(dentry);

	ax->fcap.permitted = vcaps.permitted;
	ax->fcap.inheritable = vcaps.inheritable;
	ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
	ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;

	ax->old_pcap.permitted   = old->cap_permitted;
	ax->old_pcap.inheritable = old->cap_inheritable;
	ax->old_pcap.effective   = old->cap_effective;

	ax->new_pcap.permitted   = new->cap_permitted;
	ax->new_pcap.inheritable = new->cap_inheritable;
	ax->new_pcap.effective   = new->cap_effective;
	return 0;
}

/**
 * __audit_log_capset - store information about the arguments to the capset syscall
 * @pid: target pid of the capset call
 * @new: the new credentials
 * @old: the old (current) credentials
 *
 * Record the aguments userspace sent to sys_capset for later printing by the
 * audit system if applicable
 */
void __audit_log_capset(pid_t pid,
		       const struct cred *new, const struct cred *old)
{
	struct audit_context *context = current->audit_context;
	context->capset.pid = pid;
	context->capset.cap.effective   = new->cap_effective;
	context->capset.cap.inheritable = new->cap_effective;
	context->capset.cap.permitted   = new->cap_permitted;
	context->type = AUDIT_CAPSET;
}

void __audit_mmap_fd(int fd, int flags)
{
	struct audit_context *context = current->audit_context;
	context->mmap.fd = fd;
	context->mmap.flags = flags;
	context->type = AUDIT_MMAP;
}

static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
{
	uid_t auid, uid;
	gid_t gid;
	unsigned int sessionid;

	auid = audit_get_loginuid(current);
	sessionid = audit_get_sessionid(current);
	current_uid_gid(&uid, &gid);

	audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u",
			 auid, uid, gid, sessionid);
	audit_log_task_context(ab);
	audit_log_format(ab, " pid=%d comm=", current->pid);
	audit_log_untrustedstring(ab, current->comm);
	audit_log_format(ab, " reason=");
	audit_log_string(ab, reason);
	audit_log_format(ab, " sig=%ld", signr);
}
/**
 * audit_core_dumps - record information about processes that end abnormally
 * @signr: signal value
 *
 * If a process ends with a core dump, something fishy is going on and we
 * should record the event for investigation.
 */
void audit_core_dumps(long signr)
{
	struct audit_buffer *ab;

	if (!audit_enabled)
		return;

	if (signr == SIGQUIT)	/* don't care for those */
		return;

	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
	audit_log_abend(ab, "memory violation", signr);
	audit_log_end(ab);
}

void __audit_seccomp(unsigned long syscall)
{
	struct audit_buffer *ab;

	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
	audit_log_abend(ab, "seccomp", SIGKILL);
	audit_log_format(ab, " syscall=%ld", syscall);
	audit_log_end(ab);
}

struct list_head *audit_killed_trees(void)
{
	struct audit_context *ctx = current->audit_context;
	if (likely(!ctx || !ctx->in_syscall))
		return NULL;
	return &ctx->killed_trees;
}
OpenPOWER on IntegriCloud