aboutsummaryrefslogtreecommitdiffstats
path: root/pseudo_util.c
blob: 0c156cfc444dd68d5a5f908b92c8b0901032fbbe (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
/*
 * pseudo_util.c, miscellaneous utility functions
 *
 * Copyright (c) 2008-2013 Wind River Systems, Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the Lesser GNU General Public License version 2.1 as
 * published by the Free Software Foundation.
 *
 * 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 Lesser GNU General Public License for more details.
 *
 * You should have received a copy of the Lesser GNU General Public License
 * version 2.1 along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA 
 *
 */
/* we need access to RTLD_NEXT for a horrible workaround */
#define _GNU_SOURCE

#include <ctype.h>
#include <errno.h>
#include <stdarg.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <sys/stat.h>
#include <regex.h>
#include <time.h>
#include <sys/time.h>
#include <unistd.h>
#include <limits.h>

/* see the comments below about (*real_regcomp)() */
#include <dlfcn.h>

#include "pseudo.h"
#include "pseudo_ipc.h"
#include "pseudo_db.h"

struct pseudo_variables {
	char *key;
	size_t key_len;
	char *value;
};

/* The order below is not arbitrary, but based on an assumption
 * of how often things will be used.
 */
static struct pseudo_variables pseudo_env[] = {
	{ "PSEUDO_PREFIX", 13, NULL },
	{ "PSEUDO_BINDIR", 13, NULL },
	{ "PSEUDO_LIBDIR", 13, NULL },
	{ "PSEUDO_LOCALSTATEDIR", 20, NULL },
	{ "PSEUDO_PASSWD", 13, NULL },
	{ "PSEUDO_CHROOT", 13, NULL },
	{ "PSEUDO_UIDS", 11, NULL },
	{ "PSEUDO_GIDS", 11, NULL },
	{ "PSEUDO_OPTS", 11, NULL },
	{ "PSEUDO_DEBUG", 12, NULL },
	{ "PSEUDO_DEBUG_FILE", 17, NULL },
	{ "PSEUDO_TAG", 10, NULL },
	{ "PSEUDO_ENOSYS_ABORT", 19, NULL },
	{ "PSEUDO_NOSYMLINKEXP", 19, NULL },
	{ "PSEUDO_DISABLED", 15, NULL },
	{ "PSEUDO_UNLOAD", 13, NULL },
	{ "PSEUDO_ALLOW_FSYNC", 18, NULL },
#ifdef PSEUDO_PROFILING
	{ "PSEUDO_PROFILE_PATH", 19, NULL },
#endif
	{ "PSEUDO_EVLOG", 12, NULL },
	{ "PSEUDO_EVLOG_FILE", 17, NULL },
	{ NULL, 0, NULL } /* Magic terminator */
};

typedef struct {
	struct timeval stamp;
	int len;
	char *data;
} pseudo_evlog_entry;

/* so bash overrides getenv/unsetenv/etcetera, preventing them from
 * actually modifying environ, so we have pseudo_wrappers try to dlsym
 * the right values. This could fail, in which case we'd get null
 * pointers, and we'll just call whatever the linker gives us and
 * hope for the best.
 */
#define SETENV(x, y, z) (pseudo_real_setenv ? pseudo_real_setenv : setenv)(x, y, z)
#define GETENV(x) (pseudo_real_getenv ? pseudo_real_getenv : getenv)(x)
#define UNSETENV(x) (pseudo_real_unsetenv ? pseudo_real_unsetenv : unsetenv)(x)

#define PSEUDO_EVLOG_ENTRIES 250
#define PSEUDO_EVLOG_LENGTH 256
static pseudo_evlog_entry event_log[PSEUDO_EVLOG_ENTRIES];
static char *pseudo_evlog_buffer;
static int pseudo_evlog_next_entry = 0;
static void pseudo_evlog_set(char *);
static void pseudo_evlog_flags_finalize(void);
static unsigned long pseudo_debug_flags_in(char *);

/* -1 - init hasn't been run yet
 * 0 - init has been run
 * 1 - init is running
 *
 * There are cases where the constructor is run AFTER the
 * program starts playing with things, so we need to do our
 * best to handle that case.
 */
static int pseudo_util_initted = -1;  /* Not yet run */

/* bypass wrapper logic on path computations */
int (*pseudo_real_lstat)(const char *path, PSEUDO_STATBUF *buf) = NULL;
/* bash workaround */
int (*pseudo_real_unsetenv)(const char *) = unsetenv;
char * (*pseudo_real_getenv)(const char *) = getenv;
int (*pseudo_real_setenv)(const char *, const char *, int) = setenv;

#if 0
static void
dump_env(char **envp) {
	size_t i = 0;
	for (i = 0; envp[i]; i++) {
		pseudo_debug(PDBGF_ENV, "dump_envp: [%d]%s\n", (int) i, envp[i]);
	}

	for (i = 0; pseudo_env[i].key; i++) {
		pseudo_debug(PDBGF_ENV, "dump_envp: {%d}%s=%s\n", (int) i, pseudo_env[i].key, pseudo_env[i].value);
	}

	pseudo_debug(PDBGF_ENV, "dump_envp: _in_init %d\n", pseudo_util_initted);
}
#endif

int
pseudo_has_unload(char * const *envp) {
	static const char unload[] = "PSEUDO_UNLOAD";
	static size_t unload_len = sizeof(unload) - 1;
	size_t i = 0;

	/* Is it in the caller environment? */
	if (NULL != GETENV(unload))
		return 1;

	/* Is it in the environment cache? */
	if (pseudo_util_initted == -1)
		pseudo_init_util();
	while (pseudo_env[i].key && strcmp(pseudo_env[i].key, unload))
		++i;
	if (pseudo_env[i].key && pseudo_env[i].value)
		return 1;

	/* Is it in the operational environment? */
	while (envp && *envp) {
		if ((!strncmp(*envp, unload, unload_len)) && ('=' == (*envp)[unload_len]))
			return 1;
		++envp;
	}
	return 0;
}

/* Caller must free memory! */
char *
pseudo_get_value(const char *key) {
	size_t i = 0;
	char * value;

	if (pseudo_util_initted == -1)
		pseudo_init_util();

	for (i = 0; pseudo_env[i].key && memcmp(pseudo_env[i].key, key, pseudo_env[i].key_len + 1); i++)
		;

	/* Check if the environment has it and we don't ...
	 * if so, something went wrong... so we'll attempt to recover
	 */
	if (pseudo_env[i].key && !pseudo_env[i].value && GETENV(pseudo_env[i].key))
		pseudo_init_util();

	if (pseudo_env[i].value)
		value = strdup(pseudo_env[i].value);
	else
		value = NULL;

	if (!pseudo_env[i].key) 
		pseudo_diag("Unknown variable %s.\n", key);

	return value;
}

/* We make a copy, so the original values should be freed. */
int
pseudo_set_value(const char *key, const char *value) {
	int rc = 0;
	size_t i = 0;

	if (pseudo_util_initted == -1)
		pseudo_init_util();

	for (i = 0; pseudo_env[i].key && memcmp(pseudo_env[i].key, key, pseudo_env[i].key_len + 1); i++)
		;

	if (pseudo_env[i].key) {
		if (pseudo_env[i].value)
			free(pseudo_env[i].value);
		if (value) {
			char *new = strdup(value);
			if (new)
				pseudo_env[i].value = new;
			else
				pseudo_diag("warning: failed to save new value (%s) for key %s\n",
					value, key);
		} else
			pseudo_env[i].value = NULL;
	} else {
		if (!pseudo_util_initted) pseudo_diag("Unknown variable %s.\n", key);
		rc = -EINVAL;
	}

	return rc;
}

void
pseudo_init_util(void) {
	size_t i = 0;
	char * env;

	pseudo_util_initted = 1;

	for (i = 0; pseudo_env[i].key; i++) {
		if (GETENV(pseudo_env[i].key))
			pseudo_set_value(pseudo_env[i].key, GETENV(pseudo_env[i].key));
	}

	pseudo_util_initted = 0;

	/* Somewhere we have to set the debug level.. */
	env = pseudo_get_value("PSEUDO_DEBUG");
	if (env) {
		int i;
		int level = atoi(env);
		if (level > 0) {
			for (i = 0; i < level; ++i) {
				pseudo_debug_verbose();
			}
		} else {
			pseudo_debug_set(env);
		}
		pseudo_debug_flags_finalize();
	}
	free(env);
	env = pseudo_get_value("PSEUDO_EVLOG");
	if (env) {
		pseudo_evlog_set(env);
		pseudo_evlog_flags_finalize();
	}
	free(env);
}

unsigned long pseudo_util_debug_flags = 0;
unsigned long pseudo_util_evlog_flags = 0;
int pseudo_util_debug_fd = 2;
int pseudo_util_evlog_fd = 2;
static int debugged_newline = 1;
static char pid_text[32];
static size_t pid_len;
static int pseudo_append_element(char *newpath, char *root, size_t allocated, char **pcurrent, const char *element, size_t elen, int leave_this);
static int pseudo_append_elements(char *newpath, char *root, size_t allocated, char **current, const char *elements, size_t elen, int leave_last);
extern char **environ;
static ssize_t pseudo_max_pathlen = -1;
static ssize_t pseudo_sys_max_pathlen = -1;

/* in our installed system, we usually use a name of the form
 * libpseudoCHECKSUM.so, where CHECKSUM is an md5 checksum of the host
 * libc.so -- this forces rebuilds of the library when the C library
 * changes.  The problem is that the pseudo binary may be
 * a prebuilt, in which case it doesn't know about CHECKSUM, so it
 * has to determine whether a given PRELINK_LIBRARIES contains libpseudo.so
 * or libpseudoCHECKSUM.so, without prior knowledge... Fancy!
 * 
 * We search for anything matching libpseudo*.so, where * is any
 * sequence of non-spaces (including an empty string), with either
 * the beginning of the string or a space in front of it, and either
 * the end of the string or a space after it.
 */
static char *libpseudo_name = "libpseudo.so";
/* this used to look for a "libpseudo*.so", but it turns out you can
 * specify a path even on Linux.
 */
static char *libpseudo_pattern = "(^|=| )[^ ]*libpseudo[^ ]*\\.so($| )";
static regex_t libpseudo_regex;
static int libpseudo_regex_compiled = 0;

/* Okay, so, there's a funny story behind this.  On one of the systems
 * we need to run on, /usr/bin/find happens to provide its own
 * definitions of regcomp and regexec which are INCOMPATIBLE with the
 * ones in the C library, and not only that, but which have buggy and/or
 * incompatible semantics, such that they trash elements of the pmatch
 * array.  So we do our best to call the "real" regcomp/regexec in the
 * C library.  If we can't find them, we just do our best and hope that
 * no one called us from a program with incompatible variants.
 *
 */
#if PSEUDO_PORT_LINUX
static int (*real_regcomp)(regex_t *__restrict __preg, const char *__restrict __pattern, int __cflags);
static int (*real_regexec)(const regex_t *__restrict __preg, const char *__restrict __string, size_t __nmatch, regmatch_t __pmatch[__restrict_arr], int __eflags);
#else
#define real_regcomp regcomp
#define real_regexec regexec
#endif /* PSEUDO_PORT_LINUX */

static int
libpseudo_regex_init(void) {
	int rc;

	if (libpseudo_regex_compiled)
		return 0;
#if PSEUDO_PORT_LINUX
	real_regcomp = dlsym(RTLD_NEXT, "regcomp");
	if (!real_regcomp)
		real_regcomp = regcomp;
	real_regexec = dlsym(RTLD_NEXT, "regexec");
	if (!real_regexec)
		real_regexec = regexec;
#endif
	rc = (*real_regcomp)(&libpseudo_regex, libpseudo_pattern, REG_EXTENDED);
	if (rc == 0)
		libpseudo_regex_compiled = 1;
	return rc;
}

/* given a space-or-colon-separated list of files, ala PRELINK_LIBRARIES,
 # return that list without any variants of libpseudo*.so.
 */
static char *
without_libpseudo(char *list) {
	regmatch_t pmatch[1];
	int counter = 0;
	int skip_start = 0;

	if (libpseudo_regex_init())
		return NULL;

	if (list[0] == '=' || list[0] == PSEUDO_LINKPATH_SEPARATOR[0])
		skip_start = 1;

	if ((*real_regexec)(&libpseudo_regex, list, 1, pmatch, 0)) {
		return list;
	}
	list = strdup(list);
	while (!(*real_regexec)(&libpseudo_regex, list, 1, pmatch, 0)) {
		char *start = list + pmatch[0].rm_so;
		char *end = list + pmatch[0].rm_eo;
		/* don't copy over the space or = */
		start += skip_start;
		memmove(start, end, strlen(end) + 1);
		++counter;
		if (counter > 5) {
			pseudo_diag("Found way too many libpseudo.so in environment, giving up.\n");
			return list;
		}
	}
	return list;
}

static char *
with_libpseudo(char *list, char *libdir_path) {
	regmatch_t pmatch[1];

	if (libpseudo_regex_init())
		return NULL;
	if ((*real_regexec)(&libpseudo_regex, list, 1, pmatch, 0)) {
		size_t len;
#if PSEUDO_PORT_DARWIN
		/* <%s:%s/%s\0> */
		len = strlen(list) + 1 + strlen(libdir_path) + 1 + strlen(libpseudo_name) + 1;
#else
		/* suppress warning */
		(void) libdir_path;
		/* <%s %s\0> */
		len = strlen(list) + 1 + strlen(libpseudo_name) + 1;
#endif
		char *new = malloc(len);
		if (new) {
			/* insert space only if there were previous bits */
			/* on Darwin, we have to provide the full path to
			 * libpseudo
			 */
#if PSEUDO_PORT_DARWIN
			snprintf(new, len, "%s%s%s/%s", list,
				*list ? PSEUDO_LINKPATH_SEPARATOR : "",
				libdir_path ? libdir_path : "",
				libpseudo_name);
#else
			snprintf(new, len, "%s%s%s", list,
				*list ? PSEUDO_LINKPATH_SEPARATOR : "",
				libpseudo_name);
#endif
		}
		return new;
	} else {
		return strdup(list);
	}
}

char *pseudo_version = PSEUDO_VERSION;

/* going away soon */
static int max_debug_level = 0;

void
pseudo_debug_terse(void) {
	char s[2] = { pseudo_debug_type_symbolic(max_debug_level) };

	if (max_debug_level > 0) {
		--max_debug_level;
		pseudo_debug_clear(s);
	}
}

void
pseudo_debug_verbose(void) {
	char s[2] = { pseudo_debug_type_symbolic(max_debug_level + 1) };

	if (s[0]) {
		pseudo_debug_set(s);
		++max_debug_level;
	}
}

void
pseudo_debug_set(char *s) {
	pseudo_util_debug_flags = pseudo_debug_flags_in(s);
}

static void
pseudo_evlog_set(char *s) {
	pseudo_util_evlog_flags = pseudo_debug_flags_in(s);
}

/* This exists because we don't want to allocate a bunch of strings
 * and free them immediately if you have several flags set.
 */
static void
pseudo_flags_finalize(unsigned long flags, char *value) {
	char buf[PDBG_MAX + 1] = "", *s = buf;
	for (int i = 0; i < PDBG_MAX; ++i) {
		if (flags & (1 << i)) {
			*s++ = pseudo_debug_type_symbolic(i);
		}
	}
	pseudo_set_value(value, buf);
}

void
pseudo_debug_flags_finalize(void) {
	pseudo_flags_finalize(pseudo_util_debug_flags, "PSEUDO_DEBUG");
}

void
pseudo_evlog_flags_finalize(void) {
	pseudo_flags_finalize(pseudo_util_evlog_flags, "PSEUDO_EVLOG");
}

static unsigned long
pseudo_debug_flags_in(char *s) {
	unsigned long flags = 0;
	if (!s)
		return flags;
	for (; *s; ++s) {
		int id = pseudo_debug_type_symbolic_id(*s);
		if (id > 0) {
			flags |= (1 << id);
		}
	}
	return flags;
}

void
pseudo_debug_clear(char *s) {
	if (!s)
		return;
	for (; *s; ++s) {
		int id = pseudo_debug_type_symbolic_id(*s);
		if (id > 0) {
			pseudo_util_debug_flags &= ~(1 << id);
		}
	}
}

int
pseudo_diag(char *fmt, ...) {
	va_list ap;
	char debuff[8192];
	int len;
	/* gcc on Ubuntu 8.10 requires that you examine the return from
	 * write(), and won't let you cast it to void.  Of course, if you
	 * can't print error messages, there's nothing to do.
	 */
	int wrote = 0;

	va_start(ap, fmt);
	len = vsnprintf(debuff, 8192, fmt, ap);
	va_end(ap);

	if (len > 8192)
		len = 8192;

	if (debugged_newline && (pseudo_util_debug_flags & PDBGF_PID)) {
		wrote += write(pseudo_util_debug_fd, pid_text, pid_len);
	}
	debugged_newline = (debuff[len - 1] == '\n');

	wrote += write(pseudo_util_debug_fd, debuff, len);
	return wrote;
}

void
pseudo_evlog_dump(void) {
	char scratch[256], firstdate[64], lastdate[64];
	time_t first = 0, last = 0;
	int len;
	int entries = 0;
	struct tm first_tm, last_tm;
	int wrote; /* ignoring write errors because there's nothing we can do */

	for (int i = 0; i < PSEUDO_EVLOG_ENTRIES; ++i) {
		pseudo_evlog_entry *e = &event_log[i];
		if (!e->data || e->len < 0 || e->stamp.tv_sec == 0)
			continue;
		++entries;
		if (!first || e->stamp.tv_sec < first)
			first = e->stamp.tv_sec;
		if (!last || e->stamp.tv_sec > last)
			last = e->stamp.tv_sec;
	}
	localtime_r(&first, &first_tm);
	localtime_r(&last, &last_tm);
	strftime(firstdate, 64, "%Y-%M-%D %H:%M:%S", &first_tm);
	strftime(lastdate, 64, "%Y-%M-%D %H:%M:%S", &last_tm);

	len = snprintf(scratch, 256, "event log for pid %d [%d entries]\n",
		getpid(), entries);
	if (len > 256)
		len = 256;
	wrote = write(pseudo_util_evlog_fd, scratch, len);
	len = snprintf(scratch, 256, "  first entry %s\n", firstdate);
	wrote = write(pseudo_util_evlog_fd, scratch, len);
	len = snprintf(scratch, 256, "  last entry %s\n", lastdate);
	wrote = write(pseudo_util_evlog_fd, scratch, len);

	for (int i = 0; i < PSEUDO_EVLOG_ENTRIES; ++i) {
		int entry = (pseudo_evlog_next_entry + i) % PSEUDO_EVLOG_ENTRIES;
		pseudo_evlog_entry *ev = &event_log[entry];
		if (!ev->data || ev->len <= 0)
			continue;
		localtime_r(&ev->stamp.tv_sec, &first_tm);
		len = strftime(firstdate, 64, "%H:%M:%S", &first_tm);
		if (len) {
			len = snprintf(scratch, 256, "%s.%03d: ", firstdate,
				(int) (ev->stamp.tv_usec / 1000));
			wrote = write(pseudo_util_evlog_fd, scratch, len);
		} else {
			wrote = write(pseudo_util_evlog_fd, "no timestamp: ", 14);
		}
		wrote = write(pseudo_util_evlog_fd, ev->data, ev->len);
	}
	(void) wrote;
}

int
pseudo_evlog_internal(char *fmt, ...) {
	va_list ap;
	pseudo_evlog_entry *ev = &event_log[pseudo_evlog_next_entry++];

	pseudo_evlog_next_entry %= PSEUDO_EVLOG_ENTRIES;

	if (!ev->data) {
		pseudo_evlog_buffer = malloc(PSEUDO_EVLOG_ENTRIES * PSEUDO_EVLOG_LENGTH);
		if (pseudo_evlog_buffer) {
			for (int i = 0; i < PSEUDO_EVLOG_ENTRIES; ++i) {
				event_log[i].data = pseudo_evlog_buffer + (PSEUDO_EVLOG_LENGTH * i);
			}
		} else {
			pseudo_diag("fatal: can't allocate event log storage.\n");
		}
	}

	va_start(ap, fmt);
	ev->len = vsnprintf(ev->data, PSEUDO_EVLOG_LENGTH, fmt, ap);
	va_end(ap);
	if (ev->len > PSEUDO_EVLOG_LENGTH) {
		strcpy(ev->data + PSEUDO_EVLOG_LENGTH - 5, "...\n");
		ev->len = PSEUDO_EVLOG_LENGTH - 1;
	}
	gettimeofday(&ev->stamp, NULL);

	return ev->len;
}

/* store pid in text form for prepending to messages */
void
pseudo_new_pid() {
#if PSEUDO_PORT_LINUX
	extern char *program_invocation_short_name; /* glibcism */
#else
	char *program_invocation_short_name = "unknown";
#endif
	int pid = getpid();
	pid_len = snprintf(pid_text, 32, "%d: ", pid);
	pseudo_debug(PDBGF_PID, "new pid: %d [%s]\n", pid, program_invocation_short_name);
}

/* helper function for pseudo_fix_path
 * adds "element" to "newpath" at location current, if it can, then
 * checks whether this now points to a symlink.  If it does, expand
 * the symlink, appending each element in turn the same way.
 */
static int
pseudo_append_element(char *newpath, char *root, size_t allocated, char **pcurrent, const char *element, size_t elen, int leave_this) {
	static int link_recursion = 0;
	size_t curlen;
	char *current;
	PSEUDO_STATBUF buf;
	if (!newpath ||
	    !pcurrent || !*pcurrent ||
	    !root || !element) {
		pseudo_diag("pseudo_append_element: invalid args.\n");
		return -1;
	}
	current = *pcurrent;
	/* sanity-check:  ignore // or /./ */
	if (elen == 0 || (elen == 1 && *element == '.')) {
		return 1;
	}
	/* backtrack for .. */
	if (elen == 2 && element[0] == '.' && element[1] == '.') {
		/* if newpath's whole contents are '/', do nothing */
		if (current <= root + 1)
			return 1;
		/* backtrack to the character before the / */
		current -= 2;
		/* now find the previous slash */
		while (current > root && *current != '/') {
			--current;
		}
		/* and point to the nul just past it */
		*(++current) = '\0';
		*pcurrent = current;
		return 1;
	}
	curlen = current - newpath;
	/* current length, plus / <element> / \0 */
	/* => curlen + elen + 3 */
	if (curlen + elen + 3 > allocated) {
		pseudo_diag("pseudo_append_element: path too long (wanted %lu bytes).\n", (unsigned long) curlen + elen + 3);
		return -1;
	}
	memcpy(current, element, elen);
	current += elen;
	/* nul-terminate, and we now point to the nul after the slash */
	*current = '\0';
	/* now, the moment of truth... is that a symlink? */
	/* if lstat fails, that's fine -- nonexistent files aren't symlinks */
	if (!leave_this) {
		int is_link;
		is_link = (pseudo_real_lstat) && (pseudo_real_lstat(newpath, &buf) != -1) && S_ISLNK(buf.st_mode);
		if (link_recursion >= PSEUDO_MAX_LINK_RECURSION && is_link) {
			pseudo_diag("link recursion too deep, not expanding path '%s'.\n", newpath);
			is_link = 0;
		}
		if (is_link) {
			char linkbuf[pseudo_path_max() + 1];
			ssize_t linklen;
			int retval;

			linklen = readlink(newpath, linkbuf, pseudo_path_max());
			if (linklen == -1) {
				pseudo_diag("uh-oh!  '%s' seems to be a symlink, but I can't read it.  Ignoring.", newpath);
				return 0;
			}
			/* null-terminate buffer */
			linkbuf[linklen] = '\0';
			/* absolute symlink means start over! */
			if (*linkbuf == '/') {
				current = newpath + 1;
			} else {
				/* point back at the end of the previous path... */
				current -= elen;
			}
			/* null terminate at the new pointer */
			*current = '\0';
			/* append all the elements in series */
			*pcurrent = current;
			++link_recursion;
			retval = pseudo_append_elements(newpath, root, allocated, pcurrent, linkbuf, linklen, 0);
			--link_recursion;
			return retval;
		}
	}
	/* okay, not a symlink, go ahead and append a slash */
	*(current++) = '/';
	*current = '\0';
	*pcurrent = current;
	return 1;
}

static int
pseudo_append_elements(char *newpath, char *root, size_t allocated, char **current, const char *element, size_t elen, int leave_last) {
	int retval = 1;
	const char * start = element;
	if (!newpath || !root ||
	    !current || !*current ||
	    !element) {
		pseudo_diag("pseudo_append_elements: invalid arguments.");
		return -1;
	}
	while (element < (start + elen) && *element) {
		size_t this_elen;
		int leave_this = 0;
		char *next = strchr(element, '/');
		if (!next) {
			next = strchr(element, '\0');
			leave_this = leave_last;
		}
		this_elen = next - element;
		switch (this_elen) {
		case 0: /* path => '/' */
			break;
		case 1: /* path => '?/' */
			if (*element != '.') {
				if (pseudo_append_element(newpath, root, allocated, current, element, this_elen, leave_this) == -1) {
					retval = -1;
				}
			}
			break;
		default:
			if (pseudo_append_element(newpath, root, allocated, current, element, this_elen, leave_this) == -1) {
				retval = -1;
			}
			break;
		}
		/* and now move past the separator */
		element += this_elen + 1;
	}
	return retval;
}

/* don't do so many allocations */
#define PATHBUFS 16
static char *pathbufs[PATHBUFS] = { 0 };
static int pathbuf = 0;

/* Canonicalize path.  "base", if present, is an already-canonicalized
 * path of baselen characters, presumed not to end in a /.  path is
 * the new path to be canonicalized.  The tricky part is that path may
 * contain symlinks, which must be resolved.
 * if "path" starts with a /, then it is an absolute path, and
 * we ignore base.
 */
char *
pseudo_fix_path(const char *base, const char *path, size_t rootlen, size_t baselen, size_t *lenp, int leave_last) {
	size_t newpathlen, pathlen;
	char *newpath;
	char *current;
	char *effective_root;
	int trailing_slash = 0;
	
	if (!path) {
		pseudo_diag("can't fix empty path.\n");
		return 0;
	}
	newpathlen = pseudo_path_max();
	if (!pathbufs[pathbuf]) {
		pathbufs[pathbuf] = malloc(newpathlen);
	}
	newpath = pathbufs[pathbuf];
	pathbuf = (pathbuf + 1) % PATHBUFS;
	pathlen = strlen(path);
	/* a trailing slash has special meaning */
	if (pathlen > 0 && path[pathlen - 1] == '/') {
		trailing_slash = 1;
	}
	/* allow a bit of slush.  overallocating a bit won't
	 * hurt.  rounding to 256's in the hopes that it makes life
	 * easier for the library.
	 */
	if (!newpath) {
		pseudo_diag("allocation failed seeking memory for path (%s).\n", path);
		return 0;
	}
	newpath[0] = '\0';
	current = newpath;
	if (baselen && (path[0] != '/' || rootlen)) {
		memcpy(current, base, baselen);
		current += baselen;
	}
	/* "root" is a pointer to the beginning of the *modifiable*
	 * part of the string; you can't back up over it.
	 */
	effective_root = newpath + rootlen;
	*current++ = '/';
	*current = '\0';
	/* at any given point:
	 * current points to just after the last / of newpath
	 * path points to the next element of path
	 * newpathlen is the total allocated length of newpath
	 * (current - newpath) is the used length of newpath
	 */
	if (pseudo_append_elements(newpath, effective_root, newpathlen, &current, path, pathlen, leave_last) != -1) {
		--current;
		if (*current == '/' && current > effective_root && !trailing_slash) {
			*current = '\0';
		}
		pseudo_debug(PDBGF_PATH, "%s + %s => <%s>\n",
			base ? base : "<nil>",
			path ? path : "<nil>",
			newpath ? newpath : "<nil>");
		if (lenp) {
			*lenp = current - newpath;
		}
		return newpath;
	} else {
		return 0;
	}
}

/* remove the libpseudo stuff from the environment (leaving other preloads
 * alone).
 * There's an implicit memory leak here, but this is called only right
 * before an exec(), or at most once in a given run.
 *
 * we don't try to fix the library path.
 */
void pseudo_dropenv() {
	char *ld_preload = GETENV(PRELINK_LIBRARIES);

	if (ld_preload) {
		ld_preload = without_libpseudo(ld_preload);
		if (!ld_preload) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_LIBRARIES);
		}
		if (ld_preload && strlen(ld_preload)) {
			SETENV(PRELINK_LIBRARIES, ld_preload, 1);
		} else {
			UNSETENV(PRELINK_LIBRARIES);
		}
	}
}

char **
pseudo_dropenvp(char * const *envp) {
	char **new_envp;
	int i, j;

	for (i = 0; envp[i]; ++i) ;

	new_envp = malloc((i + 1) * sizeof(*new_envp));
	if (!new_envp) {
		pseudo_diag("fatal: can't allocate new environment.\n");
		return NULL;
	}

	j = 0;
	for (i = 0; envp[i]; ++i) {
		if (STARTSWITH(envp[i], PRELINK_LIBRARIES "=")) {
			char *new_val = without_libpseudo(envp[i]);
			if (!new_val) {
				pseudo_diag("fatal: can't allocate new environment variable.\n");
				return 0;
			} else {
				/* don't keep an empty value; if the whole string is
				 * PRELINK_LIRBARIES=, we just drop it. */
				if (strcmp(new_val, PRELINK_LIBRARIES "=")) {
					new_envp[j++] = new_val;
				}
			}
		} else {
			new_envp[j++] = envp[i];
		}
	}
	new_envp[j++] = NULL;
	return new_envp;
}

/* add pseudo stuff to the environment.
 */
void
pseudo_setupenv() {
	size_t i = 0;

	pseudo_debug(PDBGF_CLIENT, "setting up pseudo environment.\n");

	/* Make sure everything has been evaluated */
	free(pseudo_get_prefix(NULL));
	free(pseudo_get_bindir());
	free(pseudo_get_libdir());
	free(pseudo_get_localstatedir());

	while (pseudo_env[i].key) {
		if (pseudo_env[i].value) {
			SETENV(pseudo_env[i].key, pseudo_env[i].value, 0);
			pseudo_debug(PDBGF_ENV | PDBGF_VERBOSE, "pseudo_env: %s => %s\n",
				pseudo_env[i].key, pseudo_env[i].value);
		}
		i++;
	}

	const char *ld_library_path = GETENV(PRELINK_PATH);
	char *libdir_path = pseudo_libdir_path(NULL);
	if (!ld_library_path) {
		size_t len = strlen(libdir_path) + 1 + (strlen(libdir_path) + 2) + 1;
		char *newenv = malloc(len);
		if (!newenv) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_PATH);
		}
		snprintf(newenv, len, "%s:%s64", libdir_path, libdir_path);
		SETENV(PRELINK_PATH, newenv, 1);
	} else if (!strstr(ld_library_path, libdir_path)) {
		size_t len = strlen(ld_library_path) + 1 + strlen(libdir_path) + 1 + (strlen(libdir_path) + 2) + 1;
		char *newenv = malloc(len);
		if (!newenv) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_PATH);
		}
		snprintf(newenv, len, "%s:%s:%s64", ld_library_path, libdir_path, libdir_path);
		SETENV(PRELINK_PATH, newenv, 1);
	} else {
		/* nothing to do, ld_library_path exists and contains
		 * our preferred path */
	}

	char *ld_preload = GETENV(PRELINK_LIBRARIES);
	if (ld_preload) {
		ld_preload = with_libpseudo(ld_preload, libdir_path);
		if (!ld_preload) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_LIBRARIES);
		}
		SETENV(PRELINK_LIBRARIES, ld_preload, 1);
		free(ld_preload);
	} else {
		ld_preload = with_libpseudo("", libdir_path);
		if (!ld_preload) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_LIBRARIES);
		}
		SETENV(PRELINK_LIBRARIES, ld_preload, 1);
		free(ld_preload);
	}

	/* we kept libdir path until now because with_libpseudo might
	 * need it
	 */
	free(libdir_path);


#if PSEUDO_PORT_DARWIN
	char *force_flat = GETENV("DYLD_FORCE_FLAT_NAMESPACE");
	if (!force_flat) {
		SETENV("DYLD_FORCE_FLAT_NAMESPACE", "1", 1);
	}
#endif
}

/* add pseudo stuff to the environment.
 * We can't just use setenv(), because one use case is that we're trying
 * to modify the environment of a process about to be forked through
 * execve().
 */
char **
pseudo_setupenvp(char * const *envp) {
	char **new_envp;

	size_t i, j, k;
	size_t env_count = 0;

	size_t size_pseudoenv = 0;

	char *ld_preload = NULL, *ld_library_path = NULL;

	pseudo_debug(PDBGF_ENV, "setting up envp environment.\n");

	/* Make sure everything has been evaluated */
	free(pseudo_get_prefix(NULL));
	free(pseudo_get_bindir());
	free(pseudo_get_libdir());
	free(pseudo_get_localstatedir());

	for (i = 0; envp[i]; ++i) {
		if (STARTSWITH(envp[i], PRELINK_LIBRARIES "=")) {
			ld_preload = envp[i];
		}
		if (STARTSWITH(envp[i], PRELINK_PATH "=")) {
			ld_library_path = envp[i];
		}
		++env_count;
	}

	for (i = 0; pseudo_env[i].key; i++) {
		size_pseudoenv++;
	}

	env_count += size_pseudoenv; /* We're going to over allocate */

	j = 0;
	new_envp = malloc((env_count + 1) * sizeof(*new_envp));
	if (!new_envp) {
		pseudo_diag("fatal: can't allocate new environment.\n");
		return NULL;
	}	

	char *libdir_path = pseudo_libdir_path(NULL);
	if (!ld_library_path) {
		size_t len = strlen(PRELINK_PATH "=") + strlen(libdir_path) + 1 + (strlen(libdir_path) + 2) + 1;
		char *newenv = malloc(len);
		if (!newenv) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_PATH);
		}
		snprintf(newenv, len, PRELINK_PATH "=%s:%s64", libdir_path, libdir_path);
		new_envp[j++] = newenv;
	} else if (!strstr(ld_library_path, libdir_path)) {
		size_t len = strlen(ld_library_path) + 1 + strlen(libdir_path) + 1 + (strlen(libdir_path) + 2) + 1;
		char *newenv = malloc(len);
		if (!newenv) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_PATH);
		}
		snprintf(newenv, len, "%s:%s:%s64", ld_library_path, libdir_path, libdir_path);
		new_envp[j++] = newenv;
	} else {
		/* keep old value */
		new_envp[j++] = ld_library_path;
	}

	if (ld_preload) {
		ld_preload = with_libpseudo(ld_preload, libdir_path);
		if (!ld_preload) {
			pseudo_diag("fatal: can't allocate new %s variable.\n", PRELINK_LIBRARIES);
		}
		new_envp[j++] = ld_preload;
	} else {
		ld_preload = with_libpseudo("", libdir_path);
		size_t len = strlen(PRELINK_LIBRARIES "=") + strlen(ld_preload) + 1;
		char *newenv = malloc(len);
		snprintf(newenv, len, PRELINK_LIBRARIES "=%s", ld_preload);
		new_envp[j++] = newenv;
		free(ld_preload);
	}

	free(libdir_path);

	for (i = 0; envp[i]; ++i) {
		if (STARTSWITH(envp[i], PRELINK_LIBRARIES "=")) continue;
		if (STARTSWITH(envp[i], PRELINK_PATH "=")) continue;
		new_envp[j++] = envp[i];
	}

	for (i = 0; pseudo_env[i].key; i++) {
		int found = 0;
		for (k = 0; k < j; k++) {
			if (!strncmp(pseudo_env[i].key,new_envp[k],strlen(pseudo_env[i].key))) {
				found = 1;
				break;
			}
		}
		if (!found && pseudo_env[i].key && pseudo_env[i].value) {
			size_t len = strlen(pseudo_env[i].key) + 1 + strlen(pseudo_env[i].value) + 1;
			char *newenv = malloc(len);
			if (!newenv) {
				pseudo_diag("fatal: can't allocate new variable.\n");
			}
			snprintf(newenv, len, "%s=%s", pseudo_env[i].key, pseudo_env[i].value);
			new_envp[j++] = newenv;
		}
	}
	new_envp[j++] = NULL;
	return new_envp;
}

/* Append the file value to the prefix value. */
char *
pseudo_append_path(const char * prefix, size_t prefix_len, char *file) {
	char *path;

	if (!file) {
		return strdup(prefix);
	} else {
		size_t len = prefix_len + strlen(file) + 2;
		path = malloc(len);
		if (path) {
			char *endptr;
			int rc;

			rc = snprintf(path, len, "%s", prefix);
			/* this certainly SHOULD be impossible */
			if ((size_t) rc >= len)
				rc = len - 1;
			endptr = path + rc;
			/* strip extra slashes.
			 * This probably has no real effect, but I don't like
			 * seeing "//" in paths.
			 */
			while ((endptr > path) && (endptr[-1] == '/'))
				--endptr;
			snprintf(endptr, len - (endptr - path), "/%s", file);
		}
		return path;
	}
}


/* get the full path to a file under $PSEUDO_PREFIX.  Other ways of
 * setting the prefix all set it in the environment.
 */
char *
pseudo_prefix_path(char *file) {
	char * rc;
	char * prefix = pseudo_get_prefix(NULL);

	if (!prefix) {
		pseudo_diag("You must set the PSEUDO_PREFIX environment variable to run pseudo.\n");
		exit(1);
	}

	rc = pseudo_append_path(prefix, strlen(prefix), file);	
	free(prefix);

	return rc;
}

/* get the full path to a file under $PSEUDO_BINDIR. */
char *
pseudo_bindir_path(char *file) {
	char * rc;
	char * bindir = pseudo_get_bindir();

	if (!bindir) {
		pseudo_diag("You must set the PSEUDO_BINDIR environment variable to run pseudo.\n");
		exit(1);
	}

	rc = pseudo_append_path(bindir, strlen(bindir), file);	
	free(bindir);

	return rc;
}

/* get the full path to a file under $PSEUDO_LIBDIR. */
char *
pseudo_libdir_path(char *file) {
	char * rc;
	char * libdir = pseudo_get_libdir();

	if (!libdir) {
		pseudo_diag("You must set the PSEUDO_LIBDIR environment variable to run pseudo.\n");
		exit(1);
	}

	rc = pseudo_append_path(libdir, strlen(libdir), file);	
	free(libdir);

	return rc;
}

/* get the full path to a file under $PSEUDO_LOCALSTATEDIR. */
char *
pseudo_localstatedir_path(char *file) {
	char * rc;
	char * localstatedir = pseudo_get_localstatedir();

	if (!localstatedir) {
		pseudo_diag("You must set the PSEUDO_LOCALSTATEDIR environment variable to run pseudo.\n");
		exit(1);
	}

	rc = pseudo_append_path(localstatedir, strlen(localstatedir), file);	
	free(localstatedir);

	return rc;
}

char *
pseudo_get_prefix(char *pathname) {
	char *s = pseudo_get_value("PSEUDO_PREFIX");

	/* Generate the PSEUDO_PREFIX if necessary, and possible... */
	if (!s && pathname) {
		char mypath[pseudo_path_max()];
		char *dir;
		char *tmp_path;

		if (pathname[0] == '/') {
			snprintf(mypath, pseudo_path_max(), "%s", pathname);
			s = mypath + strlen(mypath);
		} else {
			if (!getcwd(mypath, pseudo_path_max())) {
				mypath[0] = '\0';
			}
			s = mypath + strlen(mypath);
			s += snprintf(s, pseudo_path_max() - (s - mypath), "/%s",
				pathname);
		}
		tmp_path = pseudo_fix_path(NULL, mypath, 0, 0, 0, AT_SYMLINK_NOFOLLOW);
		/* point s to the end of the fixed path */
		if ((int) strlen(tmp_path) >= pseudo_path_max()) {
			pseudo_diag("Can't expand path '%s' -- expansion exceeds %d.\n",
				mypath, (int) pseudo_path_max());
		} else {
			s = mypath + snprintf(mypath, pseudo_path_max(), "%s", tmp_path);
		}

		while (s > (mypath + 1) && *s != '/')
			--s;
		*s = '\0';
		dir = s - 1;
		while (dir > mypath && *dir != '/') {
			--dir;
		}
		/* strip bin directory, if any */
		if (!strncmp(dir, "/bin", 4)) {
			*dir = '\0';
		}
		/* degenerate case: /bin/pseudo should yield a pseudo_prefix "/" */
		if (*mypath == '\0') {
			strcpy(mypath, "/");
		}

		pseudo_diag("Warning: PSEUDO_PREFIX unset, defaulting to %s.\n",
			mypath);
		pseudo_set_value("PSEUDO_PREFIX", mypath);
		s = pseudo_get_value("PSEUDO_PREFIX");
	}
	return s;
}

char *
pseudo_get_bindir(void) {
	char *s = pseudo_get_value("PSEUDO_BINDIR");
	if (!s) {
		char *pseudo_bindir = pseudo_prefix_path(PSEUDO_BINDIR);
		if (pseudo_bindir) {
			pseudo_set_value("PSEUDO_BINDIR", pseudo_bindir);
			s = pseudo_bindir;
		}
	}
	return s;
}

char *
pseudo_get_libdir(void) {
	char *s = pseudo_get_value("PSEUDO_LIBDIR");
	if (!s) {
		char *pseudo_libdir;
		pseudo_libdir = pseudo_prefix_path(PSEUDO_LIBDIR);
		if (pseudo_libdir) {
			pseudo_set_value("PSEUDO_LIBDIR", pseudo_libdir);
			s = pseudo_libdir;
		}
	}
#if PSEUDO_PORT_DARWIN
	/* on Darwin, we need lib64, because dyld won't search */
#else
	/* If we somehow got lib64 in there, clean it down to just lib... */
	if (s) {
		size_t len = strlen(s);
		if (s[len-2] == '6' && s[len-1] == '4') {
			s[len-2] = '\0';
			pseudo_set_value("PSEUDO_LIBDIR", s);
		}
	}
#endif

	return s;
}

char *
pseudo_get_localstatedir() {
	char *s = pseudo_get_value("PSEUDO_LOCALSTATEDIR");
	if (!s) {
		char *pseudo_localstatedir = pseudo_prefix_path(PSEUDO_LOCALSTATEDIR);
		if (pseudo_localstatedir) {
			pseudo_set_value("PSEUDO_LOCALSTATEDIR", pseudo_localstatedir);
			s = pseudo_localstatedir;
		}
	}
	return s;
}

/* these functions define the sizes pseudo will try to use
 * when trying to allocate space, or guess how much space
 * other people will have allocated; see the GNU man page
 * for realpath(3) for an explanation of why the sys_path_max
 * functions exists, approximately -- it's there to be a size
 * that I'm pretty sure the user will have allocated if they
 * provided a buffer to that defective function.
 */
/* I'm pretty sure this will be larger than real PATH_MAX */
#define REALLY_BIG_PATH 16384
/* A likely common value for PATH_MAX */
#define SORTA_BIG_PATH 4096
ssize_t
pseudo_path_max(void) {
	if (pseudo_max_pathlen == -1) {
		long l = pathconf("/", _PC_PATH_MAX);
		if (l < 0) {
			if (_POSIX_PATH_MAX > 0) {
				pseudo_max_pathlen = _POSIX_PATH_MAX;
			} else {
				pseudo_max_pathlen = REALLY_BIG_PATH;
			}
		} else {
			if (l <= REALLY_BIG_PATH) {
				pseudo_max_pathlen = l;
			} else {
				pseudo_max_pathlen = REALLY_BIG_PATH;
			}
		}
	}
	return pseudo_max_pathlen;
}

ssize_t
pseudo_sys_path_max(void) {
	if (pseudo_sys_max_pathlen == -1) {
		long l = pathconf("/", _PC_PATH_MAX);
		if (l < 0) {
			if (_POSIX_PATH_MAX > 0) {
				pseudo_sys_max_pathlen = _POSIX_PATH_MAX;
			} else {
				pseudo_sys_max_pathlen = SORTA_BIG_PATH;
			}
		} else {
			if (l <= SORTA_BIG_PATH) {
				pseudo_sys_max_pathlen = l;
			} else {
				pseudo_sys_max_pathlen = SORTA_BIG_PATH;
			}
		}
	}
	return pseudo_sys_max_pathlen;
}

/* complicated because in theory you can have modes like * 'ab+'
 * which is the same as 'a+' in POSIX.  The first letter really does have
 * to be one of r, w, a, though.
 */
int
pseudo_access_fopen(const char *mode) {
	int access = 0;
	for (; *mode; ++mode) {
		switch (*mode) {
		case 'a':
			access |= (PSA_APPEND | PSA_WRITE);
			break;
		case 'r':
			access |= PSA_READ;
			break;
		case 'w':
			access |= PSA_WRITE;
			break;
		case 'x':
			/* special case -- note that this conflicts with a
			 * rarely-used glibc extension
			 */
			access |= PSA_EXEC;
			break;
		case 'b':			/* binary mode */
			break;
		case 'c': case 'e': case 'm':	/* glibc extensions */
			break;
		case '+':
			/* one of these will already be set, presumably */
			access |= (PSA_READ | PSA_WRITE);
			break;
		default:
			access = -1;
			break;
		}
	}
	return access;
}

/* find a passwd/group file to use
 * uses in order:
 * - PSEUDO_CHROOT/etc/<file> (only if CHROOT is set)
 * - PSEUDO_PASSWD/etc/<file>
 * - /etc/<file>
 */

#if PSEUDO_PORT_DARWIN
/* on Darwin, you can't just use /etc/passwd for system lookups,
 * you have to use the real library calls because they know about
 * Directory Services.  So...
 *
 * We make up fake fds and FILE * objects that can't possibly be
 * valid.
 */
int pseudo_host_etc_passwd_fd = -3;
int pseudo_host_etc_group_fd = -4;
static FILE pseudo_fake_passwd_file;
static FILE pseudo_fake_group_file;
FILE *pseudo_host_etc_passwd_file = &pseudo_fake_passwd_file;
FILE *pseudo_host_etc_group_file = &pseudo_fake_group_file;

#endif

int
pseudo_etc_file(const char *file, char *realname, int flags, const char **search_dirs, int dircount) {
	char filename[pseudo_path_max()];
	int rc = -1;

	if (!file) {
		pseudo_debug(PDBGF_CHROOT, "pseudo_etc_file: needs argument, usually passwd/group\n");
		errno = ENOENT;
		return -1;
	}
	int i;
	if (!search_dirs || dircount == 0) {
		pseudo_debug(PDBGF_CHROOT, "pseudo_etc_file: no search dirs.\n");
		errno = ENOENT;
		return -1;
	}
	for (i = 0; i < dircount; ++i) {
		const char *s = search_dirs[i];
		/* we used to pass in some paths as NULL when unset,
		 * so we skipped those. Now NULL entries don't get
		 * put in, so the only NULL should be the sentinel
		 * value, and this should never get hit.
		 *
		 * "should" is not comforting to me.
		 */
		if (!s)
			break;
#if PSEUDO_PORT_DARWIN
		/* special magic: empty string implies our emulation
		 * of the passwd/group files.
		 */
		if (!*s) {
			if (!strcmp("passwd", file)) {
				pseudo_debug(PDBGF_CHROOT, "Darwin hackery: pseudo_etc_passwd returning magic passwd fd\n");
				return pseudo_host_etc_passwd_fd;
			} else if (!strcmp("group", file)) {
				pseudo_debug(PDBGF_CHROOT, "Darwin hackery: pseudo_etc_passwd returning magic group fd\n");
				return pseudo_host_etc_group_fd;
			}
		}
#endif
		snprintf(filename, pseudo_path_max(), "%s/etc/%s",
			s, file);
		rc = open(filename, flags, 0600);
		if (rc >= 0) {
			if (realname)
				strcpy(realname, filename);
			pseudo_debug(PDBGF_CHROOT, "pseudo_etc_file: using '%s' for '%s'.\n",
				filename, file);
			return rc;
		} else {
			pseudo_debug(PDBGF_CHROOT | PDBGF_VERBOSE, "didn't find <%s>\n",
				filename);
		}
	}
	return rc;
}

/* set up a log file */
static int
pseudo_logfile(char *filename, char *defname, int prefer_fd) {
	char *pseudo_path;
	char *s;
#if PSEUDO_PORT_LINUX
	extern char *program_invocation_short_name; /* glibcism */
#else
	char *program_invocation_short_name = "unknown";
#endif
	int fd;

	if (!filename) {
		if (!defname) {
			pseudo_debug(PDBGF_INVOKE, "no special log file requested, using stderr.\n");
			return -1;
		}
		pseudo_path = pseudo_localstatedir_path(defname);
		if (!pseudo_path) {
			pseudo_diag("can't get path for prefix/%s\n", PSEUDO_LOGFILE);
			return -1;
		}
	} else {
		char *pid = NULL, *prog = NULL;
		size_t len;
		for (s = filename; *s; ++s) {
			if (s[0] == '%') {
				switch (s[1]) {
				case '%': /* skip the %% */
					++s;
					break;
				case 'd':
					if (pid) {
						pseudo_diag("found second %%d in PSEUDO_DEBUG_FILE, ignoring.\n");
						return -1;
					} else {
						pid = s;
					}
					break;
				case 's':
					if (prog) {
						pseudo_diag("found second %%s in PSEUDO_DEBUG_FILE, ignoring.\n");
						return -1;
					} else {
						prog = s;
					}
					break;
				default:
					if (isprint(s[1])) {
						pseudo_diag("found unknown format character '%c' in PSEUDO_DEBUG_FILE, ignoring.\n",
							s[1]);
					} else {
						pseudo_diag("found unknown format character '\\x%02x' in PSEUDO_DEBUG_FILE, ignoring.\n",
							(unsigned char) s[1]);
					}
					return -1;
					break;
				}
			}
		}
		len = strlen(filename) + 1;
		if (pid)
			len += 8;
		if (prog)
			len += strlen(program_invocation_short_name);
		pseudo_path = malloc(len);
		if (!pseudo_path) {
			pseudo_diag("can't allocate space for debug file name.\n");
			return -1;
		}
		if (pid && prog) {
			if (pid < prog) {
				snprintf(pseudo_path, len, filename, getpid(), program_invocation_short_name);
			} else {
				snprintf(pseudo_path, len, filename, program_invocation_short_name, getpid());
			}
		} else if (pid) {
			snprintf(pseudo_path, len, filename, getpid());
		} else if (prog) {
			snprintf(pseudo_path, len, filename, program_invocation_short_name);
		} else {
			strcpy(pseudo_path, filename);
		}
		free(filename);
	}	
	fd = open(pseudo_path, O_WRONLY | O_APPEND | O_CREAT, 0644);
	if (fd == -1) {
		pseudo_diag("help: can't open log file %s: %s\n", pseudo_path, strerror(errno));
	} else {
		/* try to force fd to prefer_fd.  We do this because glibc's malloc
		 * debug unconditionally writes to fd 2, and we don't want
		 * a client process ending op on fd 2, or server debugging
		 * becomes a nightmare. So, server sets prefer_fd to 2. Client
		 * leaves it at -1.
		 */
		if (prefer_fd >= 0 && fd != prefer_fd) {
			int newfd;
			close(prefer_fd);
			newfd = dup2(fd, prefer_fd);
			if (newfd != -1) {
				fd = newfd;
			}
		}
		pseudo_util_debug_fd = fd;
	}
	free(pseudo_path);
	if (fd == -1)
		return -1;
	else
		return 0;
}

int
pseudo_debug_logfile(char *defname, int prefer_fd) {
	char *filename = pseudo_get_value("PSEUDO_DEBUG_FILE");
	int fd;

	fd = pseudo_logfile(filename, defname, prefer_fd);
	if (fd > -1) {
		pseudo_util_debug_fd = fd;
		return 0;
	}
	return 1;
}

int
pseudo_evlog_logfile(char *defname, int prefer_fd) {
	char *filename = pseudo_get_value("PSEUDO_EVLOG_FILE");
	int fd;

	fd = pseudo_logfile(filename, defname, prefer_fd);
	if (fd > -1) {
		pseudo_util_evlog_fd = fd;
		return 0;
	}
	return 1;
}

void
pseudo_stat32_from64(struct stat *buf32, const struct stat64 *buf) {
	buf32->st_dev = buf->st_dev;
	buf32->st_ino = buf->st_ino;
	buf32->st_mode = buf->st_mode;
	buf32->st_nlink = buf->st_nlink;
	buf32->st_uid = buf->st_uid;
	buf32->st_gid = buf->st_gid;
	buf32->st_rdev = buf->st_rdev;
	buf32->st_size = buf->st_size;
	buf32->st_blksize = buf->st_blksize;
	buf32->st_blocks = buf->st_blocks;
	buf32->st_atime = buf->st_atime;
	buf32->st_mtime = buf->st_mtime;
	buf32->st_ctime = buf->st_ctime;
}

void
pseudo_stat64_from32(struct stat64 *buf64, const struct stat *buf) {
	buf64->st_dev = buf->st_dev;
	buf64->st_ino = buf->st_ino;
	buf64->st_mode = buf->st_mode;
	buf64->st_nlink = buf->st_nlink;
	buf64->st_uid = buf->st_uid;
	buf64->st_gid = buf->st_gid;
	buf64->st_rdev = buf->st_rdev;
	buf64->st_size = buf->st_size;
	buf64->st_blksize = buf->st_blksize;
	buf64->st_blocks = buf->st_blocks;
	buf64->st_atime = buf->st_atime;
	buf64->st_mtime = buf->st_mtime;
	buf64->st_ctime = buf->st_ctime;
}

/* pretty-dump some data.
 * expects to be called using pseudo_debug_call() so it doesn't have
 * to do debug checks.
 */
void
pseudo_dump_data(char *name, const void *v, size_t len) {
	char hexbuf[128];
	char asciibuf[32];
	const unsigned char *base = v;
	const unsigned char *data = base;
	int remaining = len;
	pseudo_diag("%s at %p [%d byte%s]:\n",
		name ? name : "data", v, (int) len, len == 1 ? "" : "s");
	while (remaining > 0) {
		char *hexptr = hexbuf;
		char *asciiptr = asciibuf;
		for (int i = 0; i < 16 && i < remaining; ++i) {
			hexptr += snprintf(hexptr, 4, "%02x ", data[i]);
			if (isprint(data[i])) {
				*asciiptr++ = data[i];
			} else {
				*asciiptr++ = '.';
			}
			if (i % 4 == 3) {
				*hexptr++ = ' ';
			}
		}
		*hexptr = '\0';
		*asciiptr = '\0';
		pseudo_diag("0x%06x %-50.50s '%.16s'\n",
			(int) (data - base),
			hexbuf, asciibuf);
		remaining = remaining - 16;
		data = data + 16;
	}
}
="p">(u64 ts, char *buf) { unsigned long rem_nsec; if (!printk_time) return 0; rem_nsec = do_div(ts, 1000000000); if (!buf) return snprintf(NULL, 0, "[%5lu.000000] ", (unsigned long)ts); return sprintf(buf, "[%5lu.%06lu] ", (unsigned long)ts, rem_nsec / 1000); } static size_t print_prefix(const struct printk_log *msg, bool syslog, char *buf) { size_t len = 0; unsigned int prefix = (msg->facility << 3) | msg->level; if (syslog) { if (buf) { len += sprintf(buf, "<%u>", prefix); } else { len += 3; if (prefix > 999) len += 3; else if (prefix > 99) len += 2; else if (prefix > 9) len++; } } len += print_time(msg->ts_nsec, buf ? buf + len : NULL); return len; } static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *buf, size_t size) { const char *text = log_text(msg); size_t text_size = msg->text_len; size_t len = 0; do { const char *next = memchr(text, '\n', text_size); size_t text_len; if (next) { text_len = next - text; next++; text_size -= next - text; } else { text_len = text_size; } if (buf) { if (print_prefix(msg, syslog, NULL) + text_len + 1 >= size - len) break; len += print_prefix(msg, syslog, buf + len); memcpy(buf + len, text, text_len); len += text_len; buf[len++] = '\n'; } else { /* SYSLOG_ACTION_* buffer size only calculation */ len += print_prefix(msg, syslog, NULL); len += text_len; len++; } text = next; } while (text); return len; } static int syslog_print(char __user *buf, int size) { char *text; struct printk_log *msg; int len = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; while (size > 0) { size_t n; size_t skip; logbuf_lock_irq(); if (syslog_seq < log_first_seq) { /* messages are gone, move to first one */ syslog_seq = log_first_seq; syslog_idx = log_first_idx; syslog_partial = 0; } if (syslog_seq == log_next_seq) { logbuf_unlock_irq(); break; } skip = syslog_partial; msg = log_from_idx(syslog_idx); n = msg_print_text(msg, true, text, LOG_LINE_MAX + PREFIX_MAX); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_idx = log_next(syslog_idx); syslog_seq++; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; logbuf_unlock_irq(); if (!n) break; if (copy_to_user(buf, text + skip, n)) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { char *text; int len = 0; u64 next_seq; u64 seq; u32 idx; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; logbuf_lock_irq(); /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ seq = clear_seq; idx = clear_idx; while (seq < log_next_seq) { struct printk_log *msg = log_from_idx(idx); len += msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; } /* move first record forward until length fits into the buffer */ seq = clear_seq; idx = clear_idx; while (len > size && seq < log_next_seq) { struct printk_log *msg = log_from_idx(idx); len -= msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; } /* last message fitting into this dump */ next_seq = log_next_seq; len = 0; while (len >= 0 && seq < next_seq) { struct printk_log *msg = log_from_idx(idx); int textlen; textlen = msg_print_text(msg, true, text, LOG_LINE_MAX + PREFIX_MAX); if (textlen < 0) { len = textlen; break; } idx = log_next(idx); seq++; logbuf_unlock_irq(); if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; logbuf_lock_irq(); if (seq < log_first_seq) { /* messages are gone, move to next one */ seq = log_first_seq; idx = log_first_idx; } } if (clear) { clear_seq = log_next_seq; clear_idx = log_next_idx; } logbuf_unlock_irq(); kfree(text); return len; } static void syslog_clear(void) { logbuf_lock_irq(); clear_seq = log_next_seq; clear_idx = log_next_idx; logbuf_unlock_irq(); } int do_syslog(int type, char __user *buf, int len, int source) { bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; error = wait_event_interruptible(log_wait, syslog_seq != log_next_seq); if (error) return error; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; /* FALL THRU */ /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: logbuf_lock_irq(); if (syslog_seq < log_first_seq) { /* messages are gone, move to first one */ syslog_seq = log_first_seq; syslog_idx = log_first_idx; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = log_next_seq - syslog_seq; } else { u64 seq = syslog_seq; u32 idx = syslog_idx; while (seq < log_next_seq) { struct printk_log *msg = log_from_idx(idx); error += msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; } error -= syslog_partial; } logbuf_unlock_irq(); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ static void console_lock_spinning_enable(void) { raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose the lock if there was a busy waiter. * They must not touch items synchronized by console_lock * in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ static int console_lock_spinning_disable_and_check(void) { int waiter; raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, 1, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, 1, _THIS_IP_); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, 1, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, 1, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); return 1; } /* * Call the console drivers, asking them to write out * log_buf[start] to log_buf[end - 1]. * The console_lock must be held. */ static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) { struct console *con; trace_console_rcuidle(text, len); if (!console_drivers) return; for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; if (!(con->flags & CON_ENABLED)) continue; if (!con->write) continue; if (!cpu_online(smp_processor_id()) && !(con->flags & CON_ANYTIME)) continue; if (con->flags & CON_EXTENDED) con->write(con, ext_text, ext_len); else con->write(con, text, len); } } int printk_delay_msec __read_mostly; static inline void printk_delay(void) { if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } /* * Continuation lines are buffered, and not committed to the record buffer * until the line is complete, or a race forces it. The line fragments * though, are printed immediately to the consoles to ensure everything has * reached the console in case of a kernel crash. */ static struct cont { char buf[LOG_LINE_MAX]; size_t len; /* length == 0 means unused buffer */ struct task_struct *owner; /* task of first print*/ u64 ts_nsec; /* time of first print */ u8 level; /* log level of first message */ u8 facility; /* log facility of first message */ enum log_flags flags; /* prefix, newline flags */ } cont; static void cont_flush(void) { if (cont.len == 0) return; log_store(cont.facility, cont.level, cont.flags, cont.ts_nsec, NULL, 0, cont.buf, cont.len); cont.len = 0; } static bool cont_add(int facility, int level, enum log_flags flags, const char *text, size_t len) { /* * If ext consoles are present, flush and skip in-kernel * continuation. See nr_ext_console_drivers definition. Also, if * the line gets too long, split it up in separate records. */ if (nr_ext_console_drivers || cont.len + len > sizeof(cont.buf)) { cont_flush(); return false; } if (!cont.len) { cont.facility = facility; cont.level = level; cont.owner = current; cont.ts_nsec = local_clock(); cont.flags = flags; } memcpy(cont.buf + cont.len, text, len); cont.len += len; // The original flags come from the first line, // but later continuations can add a newline. if (flags & LOG_NEWLINE) { cont.flags |= LOG_NEWLINE; cont_flush(); } if (cont.len > (sizeof(cont.buf) * 80) / 100) cont_flush(); return true; } static size_t log_output(int facility, int level, enum log_flags lflags, const char *dict, size_t dictlen, char *text, size_t text_len) { /* * If an earlier line was buffered, and we're a continuation * write from the same process, try to add it to the buffer. */ if (cont.len) { if (cont.owner == current && (lflags & LOG_CONT)) { if (cont_add(facility, level, lflags, text, text_len)) return text_len; } /* Otherwise, make sure it's flushed */ cont_flush(); } /* Skip empty continuation lines that couldn't be added - they just flush */ if (!text_len && (lflags & LOG_CONT)) return 0; /* If it doesn't end in a newline, try to buffer the current line */ if (!(lflags & LOG_NEWLINE)) { if (cont_add(facility, level, lflags, text, text_len)) return text_len; } /* Store it in the record log */ return log_store(facility, level, lflags, 0, dict, dictlen, text, text_len); } /* Must be called under logbuf_lock. */ int vprintk_store(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) { static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len; enum log_flags lflags = 0; /* * The printf needs to come first; we need the syslog * prefix which might be passed-in as a parameter. */ text_len = vscnprintf(text, sizeof(textbuf), fmt, args); /* mark and strip a trailing newline */ if (text_len && text[text_len-1] == '\n') { text_len--; lflags |= LOG_NEWLINE; } /* strip kernel syslog prefix and extract log level or control flags */ if (facility == 0) { int kern_level; while ((kern_level = printk_get_level(text)) != 0) { switch (kern_level) { case '0' ... '7': if (level == LOGLEVEL_DEFAULT) level = kern_level - '0'; /* fallthrough */ case 'd': /* KERN_DEFAULT */ lflags |= LOG_PREFIX; break; case 'c': /* KERN_CONT */ lflags |= LOG_CONT; } text_len -= 2; text += 2; } } if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dict) lflags |= LOG_PREFIX|LOG_NEWLINE; return log_output(facility, level, lflags, dict, dictlen, text, text_len); } asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) { int printed_len; bool in_sched = false; unsigned long flags; if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; in_sched = true; } boot_delay_msec(level); printk_delay(); /* This stops the holder of console_sem just where we want him */ logbuf_lock_irqsave(flags); printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args); logbuf_unlock_irqrestore(flags); /* If called from the scheduler, we can not call up(). */ if (!in_sched) { /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to * console */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); asmlinkage int vprintk(const char *fmt, va_list args) { return vprintk_func(fmt, args); } EXPORT_SYMBOL(vprintk); asmlinkage int printk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, dict, dictlen, fmt, args); va_end(args); return r; } EXPORT_SYMBOL(printk_emit); int vprintk_default(const char *fmt, va_list args) { int r; #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) { r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); return r; } #endif r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); return r; } EXPORT_SYMBOL_GPL(vprintk_default); /** * printk - print a kernel message * @fmt: format string * * This is printk(). It can be called from any context. We want it to work. * * We try to grab the console_lock. If we succeed, it's easy - we log the * output and call the console drivers. If we fail to get the semaphore, we * place the output into the log buffer and return. The current holder of * the console_sem will notice the new output in console_unlock(); and will * send it to the consoles before releasing the lock. * * One effect of this deferred printing is that code which calls printk() and * then changes console_loglevel may break. This is because console_loglevel * is inspected when the actual printing occurs. * * See also: * printf(3) * * See the vsnprintf() documentation for format string extensions over C99. */ asmlinkage __visible int printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_func(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(printk); #else /* CONFIG_PRINTK */ #define LOG_LINE_MAX 0 #define PREFIX_MAX 0 static u64 syslog_seq; static u32 syslog_idx; static u64 console_seq; static u32 console_idx; static u64 exclusive_console_stop_seq; static u64 log_first_seq; static u32 log_first_idx; static u64 log_next_seq; static char *log_text(const struct printk_log *msg) { return NULL; } static char *log_dict(const struct printk_log *msg) { return NULL; } static struct printk_log *log_from_idx(u32 idx) { return NULL; } static u32 log_next(u32 idx) { return 0; } static ssize_t msg_print_ext_header(char *buf, size_t size, struct printk_log *msg, u64 seq) { return 0; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *dict, size_t dict_len, char *text, size_t text_len) { return 0; } static void console_lock_spinning_enable(void) { } static int console_lock_spinning_disable_and_check(void) { return 0; } static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *buf, size_t size) { return 0; } static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static int __add_preferred_console(char *name, int idx, char *options, char *brl_options) { struct console_cmdline *c; int i; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { if (strcmp(c->name, name) == 0 && c->index == idx) { if (!brl_options) preferred_console = i; return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; strlcpy(c->name, name, sizeof(c->name)); c->options = options; braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */ char *s, *options, *brl_options = NULL; int idx; if (_braille_console_setup(&str, &brl_options)) return 1; /* * Decode str into name, index, options. */ if (str[0] >= '0' && str[0] <= '9') { strcpy(buf, "ttyS"); strncpy(buf + 4, str, sizeof(buf) - 5); } else { strncpy(buf, str, sizeof(buf) - 1); } buf[sizeof(buf) - 1] = 0; options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strcpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strcpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if (isdigit(*s) || *s == ',') break; idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(buf, idx, options, brl_options); console_set_on_cmdline = 1; return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(char *name, int idx, char *options) { return __add_preferred_console(name, idx, options, NULL); } bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); /** * suspend_console - suspend the console subsystem * * This disables printk() while we go into suspend states */ void suspend_console(void) { if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); console_lock(); console_suspended = 1; up_console_sem(); } void resume_console(void) { if (!console_suspend_enabled) return; down_console_sem(); console_suspended = 0; console_unlock(); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { if (!cpuhp_tasks_frozen) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); } return 0; } /** * console_lock - lock the console system for exclusive use. * * Acquires a lock which guarantees that the caller has * exclusive access to the console system and the console_drivers list. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); down_console_sem(); if (console_suspended) return; console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to lock the console system for exclusive use. * * Try to acquire a lock which guarantees that the caller has exclusive * access to the console system and the console_drivers list. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { if (down_trylock_console_sem()) return 0; if (console_suspended) { up_console_sem(); return 0; } console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); /* * Check if we have any console that is capable of printing while cpu is * booting or shutting down. Requires console_sem. */ static int have_callable_console(void) { struct console *con; for_each_console(con) if ((con->flags & CON_ENABLED) && (con->flags & CON_ANYTIME)) return 1; return 0; } /* * Can we actually use the console at this time on this cpu? * * Console drivers may assume that per-cpu resources have been allocated. So * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't * call them until this CPU is officially up. */ static inline int can_use_console(void) { return cpu_online(raw_smp_processor_id()) || have_callable_console(); } /** * console_unlock - unlock the console system * * Releases the console_lock which the caller holds on the console system * and the console driver list. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock(); emits * the output prior to releasing the lock. * * If there is output waiting, we wake /dev/kmsg and syslog() users. * * console_unlock(); may be called from any context. */ void console_unlock(void) { static char ext_text[CONSOLE_EXT_LOG_MAX]; static char text[LOG_LINE_MAX + PREFIX_MAX]; unsigned long flags; bool do_cond_resched, retry; if (console_suspended) { up_console_sem(); return; } /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. * * console_trylock() is not able to detect the preemptive * context reliably. Therefore the value must be stored before * and cleared after the the "again" goto label. */ do_cond_resched = console_may_schedule; again: console_may_schedule = 0; /* * We released the console_sem lock, so we need to recheck if * cpu is online and (if not) is there at least one CON_ANYTIME * console. */ if (!can_use_console()) { console_locked = 0; up_console_sem(); return; } for (;;) { struct printk_log *msg; size_t ext_len = 0; size_t len; printk_safe_enter_irqsave(flags); raw_spin_lock(&logbuf_lock); if (console_seq < log_first_seq) { len = sprintf(text, "** %llu printk messages dropped **\n", log_first_seq - console_seq); /* messages are gone, move to first one */ console_seq = log_first_seq; console_idx = log_first_idx; } else { len = 0; } skip: if (console_seq == log_next_seq) break; msg = log_from_idx(console_idx); if (suppress_message_printing(msg->level)) { /* * Skip record we have buffered and already printed * directly to the console when we received it, and * record that has level above the console loglevel. */ console_idx = log_next(console_idx); console_seq++; goto skip; } /* Output to all consoles once old messages replayed. */ if (unlikely(exclusive_console && console_seq >= exclusive_console_stop_seq)) { exclusive_console = NULL; } len += msg_print_text(msg, console_msg_format & MSG_FORMAT_SYSLOG, text + len, sizeof(text) - len); if (nr_ext_console_drivers) { ext_len = msg_print_ext_header(ext_text, sizeof(ext_text), msg, console_seq); ext_len += msg_print_ext_body(ext_text + ext_len, sizeof(ext_text) - ext_len, log_dict(msg), msg->dict_len, log_text(msg), msg->text_len); } console_idx = log_next(console_idx); console_seq++; raw_spin_unlock(&logbuf_lock); /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. */ console_lock_spinning_enable(); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(ext_text, ext_len, text, len); start_critical_timings(); if (console_lock_spinning_disable_and_check()) { printk_safe_exit_irqrestore(flags); return; } printk_safe_exit_irqrestore(flags); if (do_cond_resched) cond_resched(); } console_locked = 0; raw_spin_unlock(&logbuf_lock); up_console_sem(); /* * Someone could have filled up the buffer again, so re-check if there's * something to flush. In case we cannot trylock the console_sem again, * there's a new owner and the console_unlock() from them will do the * flush, no worries. */ raw_spin_lock(&logbuf_lock); retry = console_seq != log_next_seq; raw_spin_unlock(&logbuf_lock); printk_safe_exit_irqrestore(flags); if (retry && console_trylock()) goto again; } EXPORT_SYMBOL(console_unlock); /** * console_conditional_schedule - yield the CPU if required * * If the console code is currently allowed to sleep, and * if this CPU should yield the CPU to another task, do * so here. * * Must be called within console_lock();. */ void __sched console_conditional_schedule(void) { if (console_may_schedule) cond_resched(); } EXPORT_SYMBOL(console_conditional_schedule); void console_unblank(void) { struct console *c; /* * console_unblank can no longer be called in interrupt context unless * oops_in_progress is set to 1.. */ if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; for_each_console(c) if ((c->flags & CON_ENABLED) && c->unblank) c->unblank(); console_unlock(); } /** * console_flush_on_panic - flush console content on panic * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(void) { /* * If someone else is holding the console lock, trylock will fail * and may_schedule may be set. Ignore and proceed to unlock so * that messages are flushed out. As this can be called from any * context and we don't want to get preempted while flushing, * ensure may_schedule is cleared. */ console_trylock(); console_may_schedule = 0; console_unlock(); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; console_lock(); for_each_console(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can disable console output before suspending a port, and can * re-enable output afterwards. */ void console_stop(struct console *console) { console_lock(); console->flags &= ~CON_ENABLED; console_unlock(); } EXPORT_SYMBOL(console_stop); void console_start(struct console *console) { console_lock(); console->flags |= CON_ENABLED; console_unlock(); } EXPORT_SYMBOL(console_start); static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { int i; unsigned long flags; struct console *bcon = NULL; struct console_cmdline *c; static bool has_preferred; if (console_drivers) for_each_console(bcon) if (WARN(bcon == newcon, "console '%s%d' already registered\n", bcon->name, bcon->index)) return; /* * before we register a new CON_BOOT console, make sure we don't * already have a valid console */ if (console_drivers && newcon->flags & CON_BOOT) { /* find the last or real console */ for_each_console(bcon) { if (!(bcon->flags & CON_BOOT)) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); return; } } } if (console_drivers && console_drivers->flags & CON_BOOT) bcon = console_drivers; if (!has_preferred || bcon || !console_drivers) has_preferred = preferred_console >= 0; /* * See if we want to use this console driver. If we * didn't select a console we take the first one * that registers here. */ if (!has_preferred) { if (newcon->index < 0) newcon->index = 0; if (newcon->setup == NULL || newcon->setup(newcon, NULL) == 0) { newcon->flags |= CON_ENABLED; if (newcon->device) { newcon->flags |= CON_CONSDEV; has_preferred = true; } } } /* * See if this console matches one we selected on * the command line. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return; if (newcon->setup && newcon->setup(newcon, c->options) != 0) break; } newcon->flags |= CON_ENABLED; if (i == preferred_console) { newcon->flags |= CON_CONSDEV; has_preferred = true; } break; } if (!(newcon->flags & CON_ENABLED)) return; /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) newcon->flags &= ~CON_PRINTBUFFER; /* * Put this console in the list - keep the * preferred driver at the head of the list. */ console_lock(); if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) { newcon->next = console_drivers; console_drivers = newcon; if (newcon->next) newcon->next->flags &= ~CON_CONSDEV; } else { newcon->next = console_drivers->next; console_drivers->next = newcon; } if (newcon->flags & CON_EXTENDED) if (!nr_ext_console_drivers++) pr_info("printk: continuation disabled due to ext consoles, expect more fragments in /dev/kmsg\n"); if (newcon->flags & CON_PRINTBUFFER) { /* * console_unlock(); will print out the buffered messages * for us. */ logbuf_lock_irqsave(flags); console_seq = syslog_seq; console_idx = syslog_idx; /* * We're about to replay the log buffer. Only do this to the * just-registered console to avoid excessive message spam to * the already-registered consoles. * * Set exclusive_console with disabled interrupts to reduce * race window with eventual console_flush_on_panic() that * ignores console_lock. */ exclusive_console = newcon; exclusive_console_stop_seq = console_seq; logbuf_unlock_irqrestore(flags); } console_unlock(); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ pr_info("%sconsole [%s%d] enabled\n", (newcon->flags & CON_BOOT) ? "boot" : "" , newcon->name, newcon->index); if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { /* We need to iterate through all boot consoles, to make * sure we print everything out, before we unregister them. */ for_each_console(bcon) if (bcon->flags & CON_BOOT) unregister_console(bcon); } } EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { struct console *a, *b; int res; pr_info("%sconsole [%s%d] disabled\n", (console->flags & CON_BOOT) ? "boot" : "" , console->name, console->index); res = _braille_unregister_console(console); if (res) return res; res = 1; console_lock(); if (console_drivers == console) { console_drivers=console->next; res = 0; } else if (console_drivers) { for (a=console_drivers->next, b=console_drivers ; a; b=a, a=b->next) { if (a == console) { b->next = a->next; res = 0; break; } } } if (!res && (console->flags & CON_EXTENDED)) nr_ext_console_drivers--; /* * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. */ if (console_drivers != NULL && console->flags & CON_CONSDEV) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; console_unlock(); console_sysfs_notify(); return res; } EXPORT_SYMBOL(unregister_console); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistred when the real preferred console is registered. */ static int __init printk_late_init(void) { struct console *con; int ret; for_each_console(con) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console(con); } } ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = __this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { .func = wake_up_klogd_work_func, .flags = IRQ_WORK_LAZY, }; void wake_up_klogd(void) { preempt_disable(); if (waitqueue_active(&log_wait)) { this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } void defer_console_output(void) { preempt_disable(); __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); preempt_enable(); } int vprintk_deferred(const char *fmt, va_list args) { int r; r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args); defer_console_output(); return r; } int printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); /** * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump(enum kmsg_dump_reason reason) { struct kmsg_dumper *dumper; unsigned long flags; if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) return; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { if (dumper->max_reason && reason > dumper->max_reason) continue; /* initialize iterator with data about the stored records */ dumper->active = true; logbuf_lock_irqsave(flags); dumper->cur_seq = clear_seq; dumper->cur_idx = clear_idx; dumper->next_seq = log_next_seq; dumper->next_idx = log_next_idx; logbuf_unlock_irqrestore(flags); /* invoke dumper which will iterate over records */ dumper->dump(dumper, reason); /* reset iterator */ dumper->active = false; } rcu_read_unlock(); } /** * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. * * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { struct printk_log *msg; size_t l = 0; bool ret = false; if (!dumper->active) goto out; if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; dumper->cur_idx = log_first_idx; } /* last entry */ if (dumper->cur_seq >= log_next_seq) goto out; msg = log_from_idx(dumper->cur_idx); l = msg_print_text(msg, syslog, line, size); dumper->cur_idx = log_next(dumper->cur_idx); dumper->cur_seq++; ret = true; out: if (len) *len = l; return ret; } /** * kmsg_dump_get_line - retrieve one kmsg log line * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { unsigned long flags; bool ret; logbuf_lock_irqsave(flags); ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); logbuf_unlock_irqrestore(flags); return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, char *buf, size_t size, size_t *len) { unsigned long flags; u64 seq; u32 idx; u64 next_seq; u32 next_idx; size_t l = 0; bool ret = false; if (!dumper->active) goto out; logbuf_lock_irqsave(flags); if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; dumper->cur_idx = log_first_idx; } /* last entry */ if (dumper->cur_seq >= dumper->next_seq) { logbuf_unlock_irqrestore(flags); goto out; } /* calculate length of entire buffer */ seq = dumper->cur_seq; idx = dumper->cur_idx; while (seq < dumper->next_seq) { struct printk_log *msg = log_from_idx(idx); l += msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; } /* move first record forward until length fits into the buffer */ seq = dumper->cur_seq; idx = dumper->cur_idx; while (l >= size && seq < dumper->next_seq) { struct printk_log *msg = log_from_idx(idx); l -= msg_print_text(msg, true, NULL, 0); idx = log_next(idx); seq++; } /* last message in next interation */ next_seq = seq; next_idx = idx; l = 0; while (seq < dumper->next_seq) { struct printk_log *msg = log_from_idx(idx); l += msg_print_text(msg, syslog, buf + l, size - l); idx = log_next(idx); seq++; } dumper->next_seq = next_seq; dumper->next_idx = next_idx; ret = true; logbuf_unlock_irqrestore(flags); out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind_nolock - reset the interator (unlocked version) * @dumper: registered kmsg dumper * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. * * The function is similar to kmsg_dump_rewind(), but grabs no locks. */ void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) { dumper->cur_seq = clear_seq; dumper->cur_idx = clear_idx; dumper->next_seq = log_next_seq; dumper->next_idx = log_next_idx; } /** * kmsg_dump_rewind - reset the interator * @dumper: registered kmsg dumper * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dumper *dumper) { unsigned long flags; logbuf_lock_irqsave(flags); kmsg_dump_rewind_nolock(dumper); logbuf_unlock_irqrestore(flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif