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
|
/*-
* Copyright (c) 1982, 1986, 1989, 1991, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, Inc.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)kern_exit.c 8.7 (Berkeley) 2/12/94
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_compat.h"
#include "opt_kdtrace.h"
#include "opt_ktrace.h"
#include "opt_procdesc.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/capsicum.h>
#include <sys/eventhandler.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/proc.h>
#include <sys/procdesc.h>
#include <sys/pioctl.h>
#include <sys/jail.h>
#include <sys/tty.h>
#include <sys/wait.h>
#include <sys/vmmeter.h>
#include <sys/vnode.h>
#include <sys/racct.h>
#include <sys/resourcevar.h>
#include <sys/sbuf.h>
#include <sys/signalvar.h>
#include <sys/sched.h>
#include <sys/sx.h>
#include <sys/syscallsubr.h>
#include <sys/syslog.h>
#include <sys/ptrace.h>
#include <sys/acct.h> /* for acct_process() function prototype */
#include <sys/filedesc.h>
#include <sys/sdt.h>
#include <sys/shm.h>
#include <sys/sem.h>
#include <sys/umtx.h>
#ifdef KTRACE
#include <sys/ktrace.h>
#endif
#include <security/audit/audit.h>
#include <security/mac/mac_framework.h>
#include <vm/vm.h>
#include <vm/vm_extern.h>
#include <vm/vm_param.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <vm/vm_page.h>
#include <vm/uma.h>
#ifdef KDTRACE_HOOKS
#include <sys/dtrace_bsd.h>
dtrace_execexit_func_t dtrace_fasttrap_exit;
#endif
SDT_PROVIDER_DECLARE(proc);
SDT_PROBE_DEFINE1(proc, , , exit, "int");
/* Hook for NFS teardown procedure. */
void (*nlminfo_release_p)(struct proc *p);
struct proc *
proc_realparent(struct proc *child)
{
struct proc *p, *parent;
sx_assert(&proctree_lock, SX_LOCKED);
if ((child->p_treeflag & P_TREE_ORPHANED) == 0) {
if (child->p_oppid == 0 ||
child->p_pptr->p_pid == child->p_oppid)
parent = child->p_pptr;
else
parent = initproc;
return (parent);
}
for (p = child; (p->p_treeflag & P_TREE_FIRST_ORPHAN) == 0;) {
/* Cannot use LIST_PREV(), since the list head is not known. */
p = __containerof(p->p_orphan.le_prev, struct proc,
p_orphan.le_next);
KASSERT((p->p_treeflag & P_TREE_ORPHANED) != 0,
("missing P_ORPHAN %p", p));
}
parent = __containerof(p->p_orphan.le_prev, struct proc,
p_orphans.lh_first);
return (parent);
}
void
reaper_abandon_children(struct proc *p, bool exiting)
{
struct proc *p1, *p2, *ptmp;
sx_assert(&proctree_lock, SX_LOCKED);
KASSERT(p != initproc, ("reaper_abandon_children for initproc"));
if ((p->p_treeflag & P_TREE_REAPER) == 0)
return;
p1 = p->p_reaper;
LIST_FOREACH_SAFE(p2, &p->p_reaplist, p_reapsibling, ptmp) {
LIST_REMOVE(p2, p_reapsibling);
p2->p_reaper = p1;
p2->p_reapsubtree = p->p_reapsubtree;
LIST_INSERT_HEAD(&p1->p_reaplist, p2, p_reapsibling);
if (exiting && p2->p_pptr == p) {
PROC_LOCK(p2);
proc_reparent(p2, p1);
PROC_UNLOCK(p2);
}
}
KASSERT(LIST_EMPTY(&p->p_reaplist), ("p_reaplist not empty"));
p->p_treeflag &= ~P_TREE_REAPER;
}
static void
clear_orphan(struct proc *p)
{
struct proc *p1;
sx_assert(&proctree_lock, SA_XLOCKED);
if ((p->p_treeflag & P_TREE_ORPHANED) == 0)
return;
if ((p->p_treeflag & P_TREE_FIRST_ORPHAN) != 0) {
p1 = LIST_NEXT(p, p_orphan);
if (p1 != NULL)
p1->p_treeflag |= P_TREE_FIRST_ORPHAN;
p->p_treeflag &= ~P_TREE_FIRST_ORPHAN;
}
LIST_REMOVE(p, p_orphan);
p->p_treeflag &= ~P_TREE_ORPHANED;
}
/*
* exit -- death of process.
*/
void
sys_sys_exit(struct thread *td, struct sys_exit_args *uap)
{
exit1(td, W_EXITCODE(uap->rval, 0));
/* NOTREACHED */
}
/*
* Exit: deallocate address space and other resources, change proc state to
* zombie, and unlink proc from allproc and parent's lists. Save exit status
* and rusage for wait(). Check for child processes and orphan them.
*/
void
exit1(struct thread *td, int rv)
{
struct proc *p, *nq, *q, *t;
struct thread *tdt;
struct vnode *ttyvp = NULL;
mtx_assert(&Giant, MA_NOTOWNED);
p = td->td_proc;
/*
* XXX in case we're rebooting we just let init die in order to
* work around an unsolved stack overflow seen very late during
* shutdown on sparc64 when the gmirror worker process exists.
*/
if (p == initproc && rebooting == 0) {
printf("init died (signal %d, exit %d)\n",
WTERMSIG(rv), WEXITSTATUS(rv));
panic("Going nowhere without my init!");
}
/*
* Deref SU mp, since the thread does not return to userspace.
*/
if (softdep_ast_cleanup != NULL)
softdep_ast_cleanup();
/*
* MUST abort all other threads before proceeding past here.
*/
PROC_LOCK(p);
/*
* First check if some other thread or external request got
* here before us. If so, act appropriately: exit or suspend.
* We must ensure that stop requests are handled before we set
* P_WEXIT.
*/
thread_suspend_check(0);
while (p->p_flag & P_HADTHREADS) {
/*
* Kill off the other threads. This requires
* some co-operation from other parts of the kernel
* so it may not be instantaneous. With this state set
* any thread entering the kernel from userspace will
* thread_exit() in trap(). Any thread attempting to
* sleep will return immediately with EINTR or EWOULDBLOCK
* which will hopefully force them to back out to userland
* freeing resources as they go. Any thread attempting
* to return to userland will thread_exit() from userret().
* thread_exit() will unsuspend us when the last of the
* other threads exits.
* If there is already a thread singler after resumption,
* calling thread_single will fail; in that case, we just
* re-check all suspension request, the thread should
* either be suspended there or exit.
*/
if (!thread_single(p, SINGLE_EXIT))
/*
* All other activity in this process is now
* stopped. Threading support has been turned
* off.
*/
break;
/*
* Recheck for new stop or suspend requests which
* might appear while process lock was dropped in
* thread_single().
*/
thread_suspend_check(0);
}
KASSERT(p->p_numthreads == 1,
("exit1: proc %p exiting with %d threads", p, p->p_numthreads));
racct_sub(p, RACCT_NTHR, 1);
/*
* Wakeup anyone in procfs' PIOCWAIT. They should have a hold
* on our vmspace, so we should block below until they have
* released their reference to us. Note that if they have
* requested S_EXIT stops we will block here until they ack
* via PIOCCONT.
*/
_STOPEVENT(p, S_EXIT, rv);
/*
* Ignore any pending request to stop due to a stop signal.
* Once P_WEXIT is set, future requests will be ignored as
* well.
*/
p->p_flag &= ~P_STOPPED_SIG;
KASSERT(!P_SHOULDSTOP(p), ("exiting process is stopped"));
/*
* Note that we are exiting and do another wakeup of anyone in
* PIOCWAIT in case they aren't listening for S_EXIT stops or
* decided to wait again after we told them we are exiting.
*/
p->p_flag |= P_WEXIT;
wakeup(&p->p_stype);
/*
* Wait for any processes that have a hold on our vmspace to
* release their reference.
*/
while (p->p_lock > 0)
msleep(&p->p_lock, &p->p_mtx, PWAIT, "exithold", 0);
p->p_xstat = rv; /* Let event handler change exit status */
PROC_UNLOCK(p);
/* Drain the limit callout while we don't have the proc locked */
callout_drain(&p->p_limco);
#ifdef AUDIT
/*
* The Sun BSM exit token contains two components: an exit status as
* passed to exit(), and a return value to indicate what sort of exit
* it was. The exit status is WEXITSTATUS(rv), but it's not clear
* what the return value is.
*/
AUDIT_ARG_EXIT(WEXITSTATUS(rv), 0);
AUDIT_SYSCALL_EXIT(0, td);
#endif
/* Are we a task leader? */
if (p == p->p_leader) {
mtx_lock(&ppeers_lock);
q = p->p_peers;
while (q != NULL) {
PROC_LOCK(q);
kern_psignal(q, SIGKILL);
PROC_UNLOCK(q);
q = q->p_peers;
}
while (p->p_peers != NULL)
msleep(p, &ppeers_lock, PWAIT, "exit1", 0);
mtx_unlock(&ppeers_lock);
}
/*
* Check if any loadable modules need anything done at process exit.
* E.g. SYSV IPC stuff
* XXX what if one of these generates an error?
*/
EVENTHANDLER_INVOKE(process_exit, p);
/*
* If parent is waiting for us to exit or exec,
* P_PPWAIT is set; we will wakeup the parent below.
*/
PROC_LOCK(p);
rv = p->p_xstat; /* Event handler could change exit status */
stopprofclock(p);
p->p_flag &= ~(P_TRACED | P_PPWAIT | P_PPTRACE);
/*
* Stop the real interval timer. If the handler is currently
* executing, prevent it from rearming itself and let it finish.
*/
if (timevalisset(&p->p_realtimer.it_value) &&
callout_stop(&p->p_itcallout) == 0) {
timevalclear(&p->p_realtimer.it_interval);
msleep(&p->p_itcallout, &p->p_mtx, PWAIT, "ritwait", 0);
KASSERT(!timevalisset(&p->p_realtimer.it_value),
("realtime timer is still armed"));
}
PROC_UNLOCK(p);
/*
* Reset any sigio structures pointing to us as a result of
* F_SETOWN with our pid.
*/
funsetownlst(&p->p_sigiolst);
/*
* If this process has an nlminfo data area (for lockd), release it
*/
if (nlminfo_release_p != NULL && p->p_nlminfo != NULL)
(*nlminfo_release_p)(p);
/*
* Close open files and release open-file table.
* This may block!
*/
fdescfree(td);
/*
* If this thread tickled GEOM, we need to wait for the giggling to
* stop before we return to userland
*/
if (td->td_pflags & TDP_GEOM)
g_waitidle();
/*
* Remove ourself from our leader's peer list and wake our leader.
*/
mtx_lock(&ppeers_lock);
if (p->p_leader->p_peers) {
q = p->p_leader;
while (q->p_peers != p)
q = q->p_peers;
q->p_peers = p->p_peers;
wakeup(p->p_leader);
}
mtx_unlock(&ppeers_lock);
vmspace_exit(td);
sx_xlock(&proctree_lock);
if (SESS_LEADER(p)) {
struct session *sp = p->p_session;
struct tty *tp;
/*
* s_ttyp is not zero'd; we use this to indicate that
* the session once had a controlling terminal. (for
* logging and informational purposes)
*/
SESS_LOCK(sp);
ttyvp = sp->s_ttyvp;
tp = sp->s_ttyp;
sp->s_ttyvp = NULL;
sp->s_ttydp = NULL;
sp->s_leader = NULL;
SESS_UNLOCK(sp);
/*
* Signal foreground pgrp and revoke access to
* controlling terminal if it has not been revoked
* already.
*
* Because the TTY may have been revoked in the mean
* time and could already have a new session associated
* with it, make sure we don't send a SIGHUP to a
* foreground process group that does not belong to this
* session.
*/
if (tp != NULL) {
tty_lock(tp);
if (tp->t_session == sp)
tty_signal_pgrp(tp, SIGHUP);
tty_unlock(tp);
}
if (ttyvp != NULL) {
sx_xunlock(&proctree_lock);
if (vn_lock(ttyvp, LK_EXCLUSIVE) == 0) {
VOP_REVOKE(ttyvp, REVOKEALL);
VOP_UNLOCK(ttyvp, 0);
}
sx_xlock(&proctree_lock);
}
}
fixjobc(p, p->p_pgrp, 0);
sx_xunlock(&proctree_lock);
(void)acct_process(td);
/* Release the TTY now we've unlocked everything. */
if (ttyvp != NULL)
vrele(ttyvp);
#ifdef KTRACE
ktrprocexit(td);
#endif
/*
* Release reference to text vnode
*/
if (p->p_textvp != NULL) {
vrele(p->p_textvp);
p->p_textvp = NULL;
}
/*
* Release our limits structure.
*/
lim_free(p->p_limit);
p->p_limit = NULL;
tidhash_remove(td);
/*
* Remove proc from allproc queue and pidhash chain.
* Place onto zombproc. Unlink from parent's child list.
*/
sx_xlock(&allproc_lock);
LIST_REMOVE(p, p_list);
LIST_INSERT_HEAD(&zombproc, p, p_list);
LIST_REMOVE(p, p_hash);
sx_xunlock(&allproc_lock);
/*
* Call machine-dependent code to release any
* machine-dependent resources other than the address space.
* The address space is released by "vmspace_exitfree(p)" in
* vm_waitproc().
*/
cpu_exit(td);
WITNESS_WARN(WARN_PANIC, NULL, "process (pid %d) exiting", p->p_pid);
/*
* Reparent all children processes:
* - traced ones to the original parent (or init if we are that parent)
* - the rest to init
*/
sx_xlock(&proctree_lock);
q = LIST_FIRST(&p->p_children);
if (q != NULL) /* only need this if any child is S_ZOMB */
wakeup(q->p_reaper);
for (; q != NULL; q = nq) {
nq = LIST_NEXT(q, p_sibling);
PROC_LOCK(q);
q->p_sigparent = SIGCHLD;
if (!(q->p_flag & P_TRACED)) {
proc_reparent(q, q->p_reaper);
} else {
/*
* Traced processes are killed since their existence
* means someone is screwing up.
*/
t = proc_realparent(q);
if (t == p) {
proc_reparent(q, q->p_reaper);
} else {
PROC_LOCK(t);
proc_reparent(q, t);
PROC_UNLOCK(t);
}
/*
* Since q was found on our children list, the
* proc_reparent() call moved q to the orphan
* list due to present P_TRACED flag. Clear
* orphan link for q now while q is locked.
*/
clear_orphan(q);
q->p_flag &= ~(P_TRACED | P_STOPPED_TRACE);
FOREACH_THREAD_IN_PROC(q, tdt)
tdt->td_dbgflags &= ~TDB_SUSPEND;
kern_psignal(q, SIGKILL);
}
PROC_UNLOCK(q);
}
/*
* Also get rid of our orphans.
*/
while ((q = LIST_FIRST(&p->p_orphans)) != NULL) {
PROC_LOCK(q);
CTR2(KTR_PTRACE, "exit: pid %d, clearing orphan %d", p->p_pid,
q->p_pid);
clear_orphan(q);
PROC_UNLOCK(q);
}
/* Save exit status. */
PROC_LOCK(p);
p->p_xthread = td;
/* Tell the prison that we are gone. */
prison_proc_free(p->p_ucred->cr_prison);
#ifdef KDTRACE_HOOKS
/*
* Tell the DTrace fasttrap provider about the exit if it
* has declared an interest.
*/
if (dtrace_fasttrap_exit)
dtrace_fasttrap_exit(p);
#endif
/*
* Notify interested parties of our demise.
*/
KNOTE_LOCKED(&p->p_klist, NOTE_EXIT);
#ifdef KDTRACE_HOOKS
int reason = CLD_EXITED;
if (WCOREDUMP(rv))
reason = CLD_DUMPED;
else if (WIFSIGNALED(rv))
reason = CLD_KILLED;
SDT_PROBE1(proc, , , exit, reason);
#endif
/*
* Just delete all entries in the p_klist. At this point we won't
* report any more events, and there are nasty race conditions that
* can beat us if we don't.
*/
knlist_clear(&p->p_klist, 1);
/*
* If this is a process with a descriptor, we may not need to deliver
* a signal to the parent. proctree_lock is held over
* procdesc_exit() to serialize concurrent calls to close() and
* exit().
*/
#ifdef PROCDESC
if (p->p_procdesc == NULL || procdesc_exit(p)) {
#endif
/*
* Notify parent that we're gone. If parent has the
* PS_NOCLDWAIT flag set, or if the handler is set to SIG_IGN,
* notify process 1 instead (and hope it will handle this
* situation).
*/
PROC_LOCK(p->p_pptr);
mtx_lock(&p->p_pptr->p_sigacts->ps_mtx);
if (p->p_pptr->p_sigacts->ps_flag &
(PS_NOCLDWAIT | PS_CLDSIGIGN)) {
struct proc *pp;
mtx_unlock(&p->p_pptr->p_sigacts->ps_mtx);
pp = p->p_pptr;
PROC_UNLOCK(pp);
proc_reparent(p, p->p_reaper);
p->p_sigparent = SIGCHLD;
PROC_LOCK(p->p_pptr);
/*
* Notify parent, so in case he was wait(2)ing or
* executing waitpid(2) with our pid, he will
* continue.
*/
wakeup(pp);
} else
mtx_unlock(&p->p_pptr->p_sigacts->ps_mtx);
if (p->p_pptr == p->p_reaper || p->p_pptr == initproc)
childproc_exited(p);
else if (p->p_sigparent != 0) {
if (p->p_sigparent == SIGCHLD)
childproc_exited(p);
else /* LINUX thread */
kern_psignal(p->p_pptr, p->p_sigparent);
}
#ifdef PROCDESC
} else
PROC_LOCK(p->p_pptr);
#endif
sx_xunlock(&proctree_lock);
/*
* The state PRS_ZOMBIE prevents other proesses from sending
* signal to the process, to avoid memory leak, we free memory
* for signal queue at the time when the state is set.
*/
sigqueue_flush(&p->p_sigqueue);
sigqueue_flush(&td->td_sigqueue);
/*
* We have to wait until after acquiring all locks before
* changing p_state. We need to avoid all possible context
* switches (including ones from blocking on a mutex) while
* marked as a zombie. We also have to set the zombie state
* before we release the parent process' proc lock to avoid
* a lost wakeup. So, we first call wakeup, then we grab the
* sched lock, update the state, and release the parent process'
* proc lock.
*/
wakeup(p->p_pptr);
cv_broadcast(&p->p_pwait);
sched_exit(p->p_pptr, td);
umtx_thread_exit(td);
PROC_SLOCK(p);
p->p_state = PRS_ZOMBIE;
PROC_UNLOCK(p->p_pptr);
/*
* Hopefully no one will try to deliver a signal to the process this
* late in the game.
*/
knlist_destroy(&p->p_klist);
/*
* Save our children's rusage information in our exit rusage.
*/
PROC_STATLOCK(p);
ruadd(&p->p_ru, &p->p_rux, &p->p_stats->p_cru, &p->p_crux);
PROC_STATUNLOCK(p);
/*
* Make sure the scheduler takes this thread out of its tables etc.
* This will also release this thread's reference to the ucred.
* Other thread parts to release include pcb bits and such.
*/
thread_exit();
}
#ifndef _SYS_SYSPROTO_H_
struct abort2_args {
char *why;
int nargs;
void **args;
};
#endif
int
sys_abort2(struct thread *td, struct abort2_args *uap)
{
struct proc *p = td->td_proc;
struct sbuf *sb;
void *uargs[16];
int error, i, sig;
/*
* Do it right now so we can log either proper call of abort2(), or
* note, that invalid argument was passed. 512 is big enough to
* handle 16 arguments' descriptions with additional comments.
*/
sb = sbuf_new(NULL, NULL, 512, SBUF_FIXEDLEN);
sbuf_clear(sb);
sbuf_printf(sb, "%s(pid %d uid %d) aborted: ",
p->p_comm, p->p_pid, td->td_ucred->cr_uid);
/*
* Since we can't return from abort2(), send SIGKILL in cases, where
* abort2() was called improperly
*/
sig = SIGKILL;
/* Prevent from DoSes from user-space. */
if (uap->nargs < 0 || uap->nargs > 16)
goto out;
if (uap->nargs > 0) {
if (uap->args == NULL)
goto out;
error = copyin(uap->args, uargs, uap->nargs * sizeof(void *));
if (error != 0)
goto out;
}
/*
* Limit size of 'reason' string to 128. Will fit even when
* maximal number of arguments was chosen to be logged.
*/
if (uap->why != NULL) {
error = sbuf_copyin(sb, uap->why, 128);
if (error < 0)
goto out;
} else {
sbuf_printf(sb, "(null)");
}
if (uap->nargs > 0) {
sbuf_printf(sb, "(");
for (i = 0;i < uap->nargs; i++)
sbuf_printf(sb, "%s%p", i == 0 ? "" : ", ", uargs[i]);
sbuf_printf(sb, ")");
}
/*
* Final stage: arguments were proper, string has been
* successfully copied from userspace, and copying pointers
* from user-space succeed.
*/
sig = SIGABRT;
out:
if (sig == SIGKILL) {
sbuf_trim(sb);
sbuf_printf(sb, " (Reason text inaccessible)");
}
sbuf_cat(sb, "\n");
sbuf_finish(sb);
log(LOG_INFO, "%s", sbuf_data(sb));
sbuf_delete(sb);
exit1(td, W_EXITCODE(0, sig));
return (0);
}
#ifdef COMPAT_43
/*
* The dirty work is handled by kern_wait().
*/
int
owait(struct thread *td, struct owait_args *uap __unused)
{
int error, status;
error = kern_wait(td, WAIT_ANY, &status, 0, NULL);
if (error == 0)
td->td_retval[1] = status;
return (error);
}
#endif /* COMPAT_43 */
/*
* The dirty work is handled by kern_wait().
*/
int
sys_wait4(struct thread *td, struct wait4_args *uap)
{
struct rusage ru, *rup;
int error, status;
if (uap->rusage != NULL)
rup = &ru;
else
rup = NULL;
error = kern_wait(td, uap->pid, &status, uap->options, rup);
if (uap->status != NULL && error == 0)
error = copyout(&status, uap->status, sizeof(status));
if (uap->rusage != NULL && error == 0)
error = copyout(&ru, uap->rusage, sizeof(struct rusage));
return (error);
}
int
sys_wait6(struct thread *td, struct wait6_args *uap)
{
struct __wrusage wru, *wrup;
siginfo_t si, *sip;
idtype_t idtype;
id_t id;
int error, status;
idtype = uap->idtype;
id = uap->id;
if (uap->wrusage != NULL)
wrup = &wru;
else
wrup = NULL;
if (uap->info != NULL) {
sip = &si;
bzero(sip, sizeof(*sip));
} else
sip = NULL;
/*
* We expect all callers of wait6() to know about WEXITED and
* WTRAPPED.
*/
error = kern_wait6(td, idtype, id, &status, uap->options, wrup, sip);
if (uap->status != NULL && error == 0)
error = copyout(&status, uap->status, sizeof(status));
if (uap->wrusage != NULL && error == 0)
error = copyout(&wru, uap->wrusage, sizeof(wru));
if (uap->info != NULL && error == 0)
error = copyout(&si, uap->info, sizeof(si));
return (error);
}
/*
* Reap the remains of a zombie process and optionally return status and
* rusage. Asserts and will release both the proctree_lock and the process
* lock as part of its work.
*/
void
proc_reap(struct thread *td, struct proc *p, int *status, int options)
{
struct proc *q, *t;
sx_assert(&proctree_lock, SA_XLOCKED);
PROC_LOCK_ASSERT(p, MA_OWNED);
PROC_SLOCK_ASSERT(p, MA_OWNED);
KASSERT(p->p_state == PRS_ZOMBIE, ("proc_reap: !PRS_ZOMBIE"));
q = td->td_proc;
PROC_SUNLOCK(p);
td->td_retval[0] = p->p_pid;
if (status)
*status = p->p_xstat; /* convert to int */
if (options & WNOWAIT) {
/*
* Only poll, returning the status. Caller does not wish to
* release the proc struct just yet.
*/
PROC_UNLOCK(p);
sx_xunlock(&proctree_lock);
return;
}
PROC_LOCK(q);
sigqueue_take(p->p_ksi);
PROC_UNLOCK(q);
/*
* If we got the child via a ptrace 'attach', we need to give it back
* to the old parent.
*/
if (p->p_oppid != 0 && p->p_oppid != p->p_pptr->p_pid) {
PROC_UNLOCK(p);
t = proc_realparent(p);
PROC_LOCK(t);
PROC_LOCK(p);
CTR2(KTR_PTRACE,
"wait: traced child %d moved back to parent %d", p->p_pid,
t->p_pid);
proc_reparent(p, t);
p->p_oppid = 0;
PROC_UNLOCK(p);
pksignal(t, SIGCHLD, p->p_ksi);
wakeup(t);
cv_broadcast(&p->p_pwait);
PROC_UNLOCK(t);
sx_xunlock(&proctree_lock);
return;
}
p->p_oppid = 0;
PROC_UNLOCK(p);
/*
* Remove other references to this process to ensure we have an
* exclusive reference.
*/
sx_xlock(&allproc_lock);
LIST_REMOVE(p, p_list); /* off zombproc */
sx_xunlock(&allproc_lock);
LIST_REMOVE(p, p_sibling);
reaper_abandon_children(p, true);
LIST_REMOVE(p, p_reapsibling);
PROC_LOCK(p);
clear_orphan(p);
PROC_UNLOCK(p);
leavepgrp(p);
#ifdef PROCDESC
if (p->p_procdesc != NULL)
procdesc_reap(p);
#endif
sx_xunlock(&proctree_lock);
/*
* As a side effect of this lock, we know that all other writes to
* this proc are visible now, so no more locking is needed for p.
*/
PROC_LOCK(p);
p->p_xstat = 0; /* XXX: why? */
PROC_UNLOCK(p);
PROC_LOCK(q);
ruadd(&q->p_stats->p_cru, &q->p_crux, &p->p_ru, &p->p_rux);
PROC_UNLOCK(q);
/*
* Decrement the count of procs running with this uid.
*/
(void)chgproccnt(p->p_ucred->cr_ruidinfo, -1, 0);
/*
* Destroy resource accounting information associated with the process.
*/
#ifdef RACCT
if (racct_enable) {
PROC_LOCK(p);
racct_sub(p, RACCT_NPROC, 1);
PROC_UNLOCK(p);
}
#endif
racct_proc_exit(p);
/*
* Free credentials, arguments, and sigacts.
*/
crfree(p->p_ucred);
proc_set_cred(p, NULL);
pargs_drop(p->p_args);
p->p_args = NULL;
sigacts_free(p->p_sigacts);
p->p_sigacts = NULL;
/*
* Do any thread-system specific cleanups.
*/
thread_wait(p);
/*
* Give vm and machine-dependent layer a chance to free anything that
* cpu_exit couldn't release while still running in process context.
*/
vm_waitproc(p);
#ifdef MAC
mac_proc_destroy(p);
#endif
KASSERT(FIRST_THREAD_IN_PROC(p),
("proc_reap: no residual thread!"));
uma_zfree(proc_zone, p);
atomic_add_int(&nprocs, -1);
}
static int
proc_to_reap(struct thread *td, struct proc *p, idtype_t idtype, id_t id,
int *status, int options, struct __wrusage *wrusage, siginfo_t *siginfo,
int check_only)
{
struct rusage *rup;
sx_assert(&proctree_lock, SA_XLOCKED);
PROC_LOCK(p);
switch (idtype) {
case P_ALL:
break;
case P_PID:
if (p->p_pid != (pid_t)id) {
PROC_UNLOCK(p);
return (0);
}
break;
case P_PGID:
if (p->p_pgid != (pid_t)id) {
PROC_UNLOCK(p);
return (0);
}
break;
case P_SID:
if (p->p_session->s_sid != (pid_t)id) {
PROC_UNLOCK(p);
return (0);
}
break;
case P_UID:
if (p->p_ucred->cr_uid != (uid_t)id) {
PROC_UNLOCK(p);
return (0);
}
break;
case P_GID:
if (p->p_ucred->cr_gid != (gid_t)id) {
PROC_UNLOCK(p);
return (0);
}
break;
case P_JAILID:
if (p->p_ucred->cr_prison->pr_id != (int)id) {
PROC_UNLOCK(p);
return (0);
}
break;
/*
* It seems that the thread structures get zeroed out
* at process exit. This makes it impossible to
* support P_SETID, P_CID or P_CPUID.
*/
default:
PROC_UNLOCK(p);
return (0);
}
if (p_canwait(td, p)) {
PROC_UNLOCK(p);
return (0);
}
if (((options & WEXITED) == 0) && (p->p_state == PRS_ZOMBIE)) {
PROC_UNLOCK(p);
return (0);
}
/*
* This special case handles a kthread spawned by linux_clone
* (see linux_misc.c). The linux_wait4 and linux_waitpid
* functions need to be able to distinguish between waiting
* on a process and waiting on a thread. It is a thread if
* p_sigparent is not SIGCHLD, and the WLINUXCLONE option
* signifies we want to wait for threads and not processes.
*/
if ((p->p_sigparent != SIGCHLD) ^
((options & WLINUXCLONE) != 0)) {
PROC_UNLOCK(p);
return (0);
}
if (siginfo != NULL) {
bzero(siginfo, sizeof(*siginfo));
siginfo->si_errno = 0;
/*
* SUSv4 requires that the si_signo value is always
* SIGCHLD. Obey it despite the rfork(2) interface
* allows to request other signal for child exit
* notification.
*/
siginfo->si_signo = SIGCHLD;
/*
* This is still a rough estimate. We will fix the
* cases TRAPPED, STOPPED, and CONTINUED later.
*/
if (WCOREDUMP(p->p_xstat)) {
siginfo->si_code = CLD_DUMPED;
siginfo->si_status = WTERMSIG(p->p_xstat);
} else if (WIFSIGNALED(p->p_xstat)) {
siginfo->si_code = CLD_KILLED;
siginfo->si_status = WTERMSIG(p->p_xstat);
} else {
siginfo->si_code = CLD_EXITED;
siginfo->si_status = WEXITSTATUS(p->p_xstat);
}
siginfo->si_pid = p->p_pid;
siginfo->si_uid = p->p_ucred->cr_uid;
/*
* The si_addr field would be useful additional
* detail, but apparently the PC value may be lost
* when we reach this point. bzero() above sets
* siginfo->si_addr to NULL.
*/
}
/*
* There should be no reason to limit resources usage info to
* exited processes only. A snapshot about any resources used
* by a stopped process may be exactly what is needed.
*/
if (wrusage != NULL) {
rup = &wrusage->wru_self;
*rup = p->p_ru;
PROC_STATLOCK(p);
calcru(p, &rup->ru_utime, &rup->ru_stime);
PROC_STATUNLOCK(p);
rup = &wrusage->wru_children;
*rup = p->p_stats->p_cru;
calccru(p, &rup->ru_utime, &rup->ru_stime);
}
if (p->p_state == PRS_ZOMBIE && !check_only) {
PROC_SLOCK(p);
proc_reap(td, p, status, options);
return (-1);
}
PROC_UNLOCK(p);
return (1);
}
int
kern_wait(struct thread *td, pid_t pid, int *status, int options,
struct rusage *rusage)
{
struct __wrusage wru, *wrup;
idtype_t idtype;
id_t id;
int ret;
/*
* Translate the special pid values into the (idtype, pid)
* pair for kern_wait6. The WAIT_MYPGRP case is handled by
* kern_wait6() on its own.
*/
if (pid == WAIT_ANY) {
idtype = P_ALL;
id = 0;
} else if (pid < 0) {
idtype = P_PGID;
id = (id_t)-pid;
} else {
idtype = P_PID;
id = (id_t)pid;
}
if (rusage != NULL)
wrup = &wru;
else
wrup = NULL;
/*
* For backward compatibility we implicitly add flags WEXITED
* and WTRAPPED here.
*/
options |= WEXITED | WTRAPPED;
ret = kern_wait6(td, idtype, id, status, options, wrup, NULL);
if (rusage != NULL)
*rusage = wru.wru_self;
return (ret);
}
int
kern_wait6(struct thread *td, idtype_t idtype, id_t id, int *status,
int options, struct __wrusage *wrusage, siginfo_t *siginfo)
{
struct proc *p, *q;
int error, nfound, ret;
AUDIT_ARG_VALUE((int)idtype); /* XXX - This is likely wrong! */
AUDIT_ARG_PID((pid_t)id); /* XXX - This may be wrong! */
AUDIT_ARG_VALUE(options);
q = td->td_proc;
if ((pid_t)id == WAIT_MYPGRP && (idtype == P_PID || idtype == P_PGID)) {
PROC_LOCK(q);
id = (id_t)q->p_pgid;
PROC_UNLOCK(q);
idtype = P_PGID;
}
/* If we don't know the option, just return. */
if ((options & ~(WUNTRACED | WNOHANG | WCONTINUED | WNOWAIT |
WEXITED | WTRAPPED | WLINUXCLONE)) != 0)
return (EINVAL);
if ((options & (WEXITED | WUNTRACED | WCONTINUED | WTRAPPED)) == 0) {
/*
* We will be unable to find any matching processes,
* because there are no known events to look for.
* Prefer to return error instead of blocking
* indefinitely.
*/
return (EINVAL);
}
loop:
if (q->p_flag & P_STATCHILD) {
PROC_LOCK(q);
q->p_flag &= ~P_STATCHILD;
PROC_UNLOCK(q);
}
nfound = 0;
sx_xlock(&proctree_lock);
LIST_FOREACH(p, &q->p_children, p_sibling) {
ret = proc_to_reap(td, p, idtype, id, status, options,
wrusage, siginfo, 0);
if (ret == 0)
continue;
else if (ret == 1)
nfound++;
else
return (0);
PROC_LOCK(p);
PROC_SLOCK(p);
if ((options & WTRAPPED) != 0 &&
(p->p_flag & P_TRACED) != 0 &&
(p->p_flag & (P_STOPPED_TRACE | P_STOPPED_SIG)) != 0 &&
(p->p_suspcount == p->p_numthreads) &&
((p->p_flag & P_WAITED) == 0)) {
PROC_SUNLOCK(p);
if ((options & WNOWAIT) == 0)
p->p_flag |= P_WAITED;
sx_xunlock(&proctree_lock);
td->td_retval[0] = p->p_pid;
if (status != NULL)
*status = W_STOPCODE(p->p_xstat);
if (siginfo != NULL) {
siginfo->si_status = p->p_xstat;
siginfo->si_code = CLD_TRAPPED;
}
if ((options & WNOWAIT) == 0) {
PROC_LOCK(q);
sigqueue_take(p->p_ksi);
PROC_UNLOCK(q);
}
CTR4(KTR_PTRACE,
"wait: returning trapped pid %d status %#x (xstat %d) xthread %d",
p->p_pid, W_STOPCODE(p->p_xstat), p->p_xstat,
p->p_xthread != NULL ? p->p_xthread->td_tid : -1);
PROC_UNLOCK(p);
return (0);
}
if ((options & WUNTRACED) != 0 &&
(p->p_flag & P_STOPPED_SIG) != 0 &&
(p->p_suspcount == p->p_numthreads) &&
((p->p_flag & P_WAITED) == 0)) {
PROC_SUNLOCK(p);
if ((options & WNOWAIT) == 0)
p->p_flag |= P_WAITED;
sx_xunlock(&proctree_lock);
td->td_retval[0] = p->p_pid;
if (status != NULL)
*status = W_STOPCODE(p->p_xstat);
if (siginfo != NULL) {
siginfo->si_status = p->p_xstat;
siginfo->si_code = CLD_STOPPED;
}
if ((options & WNOWAIT) == 0) {
PROC_LOCK(q);
sigqueue_take(p->p_ksi);
PROC_UNLOCK(q);
}
PROC_UNLOCK(p);
return (0);
}
PROC_SUNLOCK(p);
if ((options & WCONTINUED) != 0 &&
(p->p_flag & P_CONTINUED) != 0) {
sx_xunlock(&proctree_lock);
td->td_retval[0] = p->p_pid;
if ((options & WNOWAIT) == 0) {
p->p_flag &= ~P_CONTINUED;
PROC_LOCK(q);
sigqueue_take(p->p_ksi);
PROC_UNLOCK(q);
}
PROC_UNLOCK(p);
if (status != NULL)
*status = SIGCONT;
if (siginfo != NULL) {
siginfo->si_status = SIGCONT;
siginfo->si_code = CLD_CONTINUED;
}
return (0);
}
PROC_UNLOCK(p);
}
/*
* Look in the orphans list too, to allow the parent to
* collect it's child exit status even if child is being
* debugged.
*
* Debugger detaches from the parent upon successful
* switch-over from parent to child. At this point due to
* re-parenting the parent loses the child to debugger and a
* wait4(2) call would report that it has no children to wait
* for. By maintaining a list of orphans we allow the parent
* to successfully wait until the child becomes a zombie.
*/
if (nfound == 0) {
LIST_FOREACH(p, &q->p_orphans, p_orphan) {
ret = proc_to_reap(td, p, idtype, id, NULL, options,
NULL, NULL, 1);
if (ret != 0) {
KASSERT(ret != -1, ("reaped an orphan (pid %d)",
(int)td->td_retval[0]));
nfound++;
break;
}
}
}
if (nfound == 0) {
sx_xunlock(&proctree_lock);
return (ECHILD);
}
if (options & WNOHANG) {
sx_xunlock(&proctree_lock);
td->td_retval[0] = 0;
return (0);
}
PROC_LOCK(q);
sx_xunlock(&proctree_lock);
if (q->p_flag & P_STATCHILD) {
q->p_flag &= ~P_STATCHILD;
error = 0;
} else
error = msleep(q, &q->p_mtx, PWAIT | PCATCH, "wait", 0);
PROC_UNLOCK(q);
if (error)
return (error);
goto loop;
}
/*
* Make process 'parent' the new parent of process 'child'.
* Must be called with an exclusive hold of proctree lock.
*/
void
proc_reparent(struct proc *child, struct proc *parent)
{
sx_assert(&proctree_lock, SX_XLOCKED);
PROC_LOCK_ASSERT(child, MA_OWNED);
if (child->p_pptr == parent)
return;
PROC_LOCK(child->p_pptr);
sigqueue_take(child->p_ksi);
PROC_UNLOCK(child->p_pptr);
LIST_REMOVE(child, p_sibling);
LIST_INSERT_HEAD(&parent->p_children, child, p_sibling);
clear_orphan(child);
if (child->p_flag & P_TRACED) {
if (LIST_EMPTY(&child->p_pptr->p_orphans)) {
child->p_treeflag |= P_TREE_FIRST_ORPHAN;
LIST_INSERT_HEAD(&child->p_pptr->p_orphans, child,
p_orphan);
} else {
LIST_INSERT_AFTER(LIST_FIRST(&child->p_pptr->p_orphans),
child, p_orphan);
}
child->p_treeflag |= P_TREE_ORPHANED;
}
child->p_pptr = parent;
}
|