summaryrefslogtreecommitdiff
path: root/sys/kern/kern_exit.c
blob: 3f851fd2a9a660574f2d3555049e89efcb5251a0 (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
/*	$OpenBSD: kern_exit.c,v 1.182 2019/12/19 17:40:10 mpi Exp $	*/
/*	$NetBSD: kern_exit.c,v 1.39 1996/04/22 01:38:25 christos Exp $	*/

/*
 * 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.
 * 3. 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/param.h>
#include <sys/systm.h>
#include <sys/ioctl.h>
#include <sys/proc.h>
#include <sys/tty.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/wait.h>
#include <sys/vnode.h>
#include <sys/syslog.h>
#include <sys/malloc.h>
#include <sys/resourcevar.h>
#include <sys/ptrace.h>
#include <sys/acct.h>
#include <sys/filedesc.h>
#include <sys/signalvar.h>
#include <sys/sched.h>
#include <sys/ktrace.h>
#include <sys/pool.h>
#include <sys/mutex.h>
#include <sys/pledge.h>
#ifdef SYSVSEM
#include <sys/sem.h>
#endif
#include <sys/witness.h>

#include <sys/mount.h>
#include <sys/syscallargs.h>

#include <uvm/uvm_extern.h>

#include "kcov.h"
#if NKCOV > 0
#include <sys/kcov.h>
#endif

void	proc_finish_wait(struct proc *, struct proc *);
void	process_zap(struct process *);
void	proc_free(struct proc *);
void	unveil_destroy(struct process *ps);

/*
 * exit --
 *	Death of process.
 */
int
sys_exit(struct proc *p, void *v, register_t *retval)
{
	struct sys_exit_args /* {
		syscallarg(int) rval;
	} */ *uap = v;

	exit1(p, SCARG(uap, rval), 0, EXIT_NORMAL);
	/* NOTREACHED */
	return (0);
}

int
sys___threxit(struct proc *p, void *v, register_t *retval)
{
	struct sys___threxit_args /* {
		syscallarg(pid_t *) notdead;
	} */ *uap = v;

	if (SCARG(uap, notdead) != NULL) {
		pid_t zero = 0;
		if (copyout(&zero, SCARG(uap, notdead), sizeof(zero)))
			psignal(p, SIGSEGV);
	}
	exit1(p, 0, 0, EXIT_THREAD);

	return (0);
}

/*
 * 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 proc *p, int xexit, int xsig, int flags)
{
	struct process *pr, *qr, *nqr;
	struct rusage *rup;

	atomic_setbits_int(&p->p_flag, P_WEXIT);

	pr = p->p_p;

	/* single-threaded? */
	if (!P_HASSIBLING(p)) {
		flags = EXIT_NORMAL;
	} else {
		/* nope, multi-threaded */
		if (flags == EXIT_NORMAL)
			single_thread_set(p, SINGLE_EXIT, 0);
		else if (flags == EXIT_THREAD)
			single_thread_check(p, 0);
	}

	if (flags == EXIT_NORMAL) {
		if (pr->ps_pid == 1)
			panic("init died (signal %d, exit %d)", xsig, xexit);

		atomic_setbits_int(&pr->ps_flags, PS_EXITING);
		pr->ps_xexit = xexit;
		pr->ps_xsig  = xsig;

		/*
		 * If parent is waiting for us to exit or exec, PS_PPWAIT
		 * is set; we wake up the parent early to avoid deadlock.
		 */
		if (pr->ps_flags & PS_PPWAIT) {
			atomic_clearbits_int(&pr->ps_flags, PS_PPWAIT);
			atomic_clearbits_int(&pr->ps_pptr->ps_flags,
			    PS_ISPWAIT);
			wakeup(pr->ps_pptr);
		}
	}

	/* unlink ourselves from the active threads */
	TAILQ_REMOVE(&pr->ps_threads, p, p_thr_link);
	if ((p->p_flag & P_THREAD) == 0) {
		/* main thread gotta wait because it has the pid, et al */
		while (pr->ps_refcnt > 1)
			tsleep_nsec(&pr->ps_threads, PWAIT, "thrdeath", INFSLP);
		if (pr->ps_flags & PS_PROFIL)
			stopprofclock(pr);
	}

	rup = pr->ps_ru;
	if (rup == NULL) {
		rup = pool_get(&rusage_pool, PR_WAITOK | PR_ZERO);
		if (pr->ps_ru == NULL) {
			pr->ps_ru = rup;
		} else {
			pool_put(&rusage_pool, rup);
			rup = pr->ps_ru;
		}
	}
	p->p_siglist = 0;
	if ((p->p_flag & P_THREAD) == 0)
		pr->ps_siglist = 0;

#if NKCOV > 0
	kcov_exit(p);
#endif

	if ((p->p_flag & P_THREAD) == 0) {
		sigio_freelist(&pr->ps_sigiolst);

		/* close open files and release open-file table */
		fdfree(p);

		timeout_del(&pr->ps_realit_to);
		timeout_del(&pr->ps_rucheck_to);
#ifdef SYSVSEM
		semexit(pr);
#endif
		killjobc(pr);
#ifdef ACCOUNTING
		acct_process(p);
#endif

#ifdef KTRACE
		/* release trace file */
		if (pr->ps_tracevp)
			ktrcleartrace(pr);
#endif

		unveil_destroy(pr);

		/*
		 * If parent has the SAS_NOCLDWAIT flag set, we're not
		 * going to become a zombie.
		 */
		if (pr->ps_pptr->ps_sigacts->ps_flags & SAS_NOCLDWAIT)
			atomic_setbits_int(&pr->ps_flags, PS_NOZOMBIE);
	}

	p->p_fd = NULL;		/* zap the thread's copy */

        /*
	 * Remove proc from pidhash chain and allproc so looking
	 * it up won't work.  We will put the proc on the
	 * deadproc list later (using the p_hash member), and
	 * wake up the reaper when we do.  If this is the last
	 * thread of a process that isn't PS_NOZOMBIE, we'll put
	 * the process on the zombprocess list below.
	 */
	/*
	 * NOTE: WE ARE NO LONGER ALLOWED TO SLEEP!
	 */
	p->p_stat = SDEAD;

	LIST_REMOVE(p, p_hash);
	LIST_REMOVE(p, p_list);

	if ((p->p_flag & P_THREAD) == 0) {
		LIST_REMOVE(pr, ps_hash);
		LIST_REMOVE(pr, ps_list);

		if ((pr->ps_flags & PS_NOZOMBIE) == 0)
			LIST_INSERT_HEAD(&zombprocess, pr, ps_list);
		else {
			/*
			 * Not going to be a zombie, so it's now off all
			 * the lists scanned by ispidtaken(), so block
			 * fast reuse of the pid now.
			 */
			freepid(pr->ps_pid);
		}

		/*
		 * Give orphaned children to init(8).
		 */
		qr = LIST_FIRST(&pr->ps_children);
		if (qr)		/* only need this if any child is S_ZOMB */
			wakeup(initprocess);
		for (; qr != 0; qr = nqr) {
			nqr = LIST_NEXT(qr, ps_sibling);
			proc_reparent(qr, initprocess);
			/*
			 * Traced processes are killed since their
			 * existence means someone is screwing up.
			 */
			if (qr->ps_flags & PS_TRACED &&
			    !(qr->ps_flags & PS_EXITING)) {
				atomic_clearbits_int(&qr->ps_flags, PS_TRACED);
				/*
				 * If single threading is active,
				 * direct the signal to the active
				 * thread to avoid deadlock.
				 */
				if (qr->ps_single)
					ptsignal(qr->ps_single, SIGKILL,
					    STHREAD);
				else
					prsignal(qr, SIGKILL);
			}
		}
	}

	/* add thread's accumulated rusage into the process's total */
	ruadd(rup, &p->p_ru);
	tuagg(pr, p);

	/*
	 * clear %cpu usage during swap
	 */
	p->p_pctcpu = 0;

	if ((p->p_flag & P_THREAD) == 0) {
		/*
		 * Final thread has died, so add on our children's rusage
		 * and calculate the total times
		 */
		calcru(&pr->ps_tu, &rup->ru_utime, &rup->ru_stime, NULL);
		ruadd(rup, &pr->ps_cru);

		/* notify interested parties of our demise and clean up */
		knote_processexit(p);

		/*
		 * Notify parent that we're gone.  If we're not going to
		 * become a zombie, reparent to process 1 (init) so that
		 * we can wake our original parent to possibly unblock
		 * wait4() to return ECHILD.
		 */
		if (pr->ps_flags & PS_NOZOMBIE) {
			struct process *ppr = pr->ps_pptr;
			proc_reparent(pr, initprocess);
			wakeup(ppr);
		}

		/*
		 * Release the process's signal state.
		 */
		sigactsfree(pr);
	}

	/* just a thread? detach it from its process */
	if (p->p_flag & P_THREAD) {
		/* scheduler_wait_hook(pr->ps_mainproc, p); XXX */
		if (--pr->ps_refcnt == 1)
			wakeup(&pr->ps_threads);
		KASSERT(pr->ps_refcnt > 0);
	}

	/* Release the thread's read reference of resource limit structure. */
	if (p->p_limit != NULL) {
		struct plimit *limit;

		limit = p->p_limit;
		p->p_limit = NULL;
		lim_free(limit);
	}

	/*
	 * Other substructures are freed from reaper and wait().
	 */

	/*
	 * Finally, call machine-dependent code to switch to a new
	 * context (possibly the idle context).  Once we are no longer
	 * using the dead process's vmspace and stack, exit2() will be
	 * called to schedule those resources to be released by the
	 * reaper thread.
	 *
	 * Note that cpu_exit() will end with a call equivalent to
	 * cpu_switch(), finishing our execution (pun intended).
	 */
	uvmexp.swtch++;
	cpu_exit(p);
	panic("cpu_exit returned");
}

/*
 * Locking of this proclist is special; it's accessed in a
 * critical section of process exit, and thus locking it can't
 * modify interrupt state.  We use a simple spin lock for this
 * proclist.  We use the p_hash member to linkup to deadproc.
 */
struct mutex deadproc_mutex =
    MUTEX_INITIALIZER_FLAGS(IPL_NONE, "deadproc", MTX_NOWITNESS);
struct proclist deadproc = LIST_HEAD_INITIALIZER(deadproc);

/*
 * We are called from cpu_exit() once it is safe to schedule the
 * dead process's resources to be freed.
 *
 * NOTE: One must be careful with locking in this routine.  It's
 * called from a critical section in machine-dependent code, so
 * we should refrain from changing any interrupt state.
 *
 * We lock the deadproc list, place the proc on that list (using
 * the p_hash member), and wake up the reaper.
 */
void
exit2(struct proc *p)
{
	mtx_enter(&deadproc_mutex);
	LIST_INSERT_HEAD(&deadproc, p, p_hash);
	mtx_leave(&deadproc_mutex);

	wakeup(&deadproc);
}

void
proc_free(struct proc *p)
{
	crfree(p->p_ucred);
	pool_put(&proc_pool, p);
	nthreads--;
}

/*
 * Process reaper.  This is run by a kernel thread to free the resources
 * of a dead process.  Once the resources are free, the process becomes
 * a zombie, and the parent is allowed to read the undead's status.
 */
void
reaper(void *arg)
{
	struct proc *p;

	KERNEL_UNLOCK();

	SCHED_ASSERT_UNLOCKED();

	for (;;) {
		mtx_enter(&deadproc_mutex);
		while ((p = LIST_FIRST(&deadproc)) == NULL)
			msleep_nsec(&deadproc, &deadproc_mutex, PVM, "reaper",
			    INFSLP);

		/* Remove us from the deadproc list. */
		LIST_REMOVE(p, p_hash);
		mtx_leave(&deadproc_mutex);

		WITNESS_THREAD_EXIT(p);

		KERNEL_LOCK();

		/*
		 * Free the VM resources we're still holding on to.
		 * We must do this from a valid thread because doing
		 * so may block.
		 */
		uvm_uarea_free(p);
		p->p_vmspace = NULL;		/* zap the thread's copy */

		if (p->p_flag & P_THREAD) {
			/* Just a thread */
			proc_free(p);
		} else {
			struct process *pr = p->p_p;

			/* Release the rest of the process's vmspace */
			uvm_exit(pr);

			if ((pr->ps_flags & PS_NOZOMBIE) == 0) {
				/* Process is now a true zombie. */
				atomic_setbits_int(&pr->ps_flags, PS_ZOMBIE);
				prsignal(pr->ps_pptr, SIGCHLD);

				/* Wake up the parent so it can get exit status. */
				wakeup(pr->ps_pptr);
			} else {
				/* No one will wait for us. Just zap the process now */
				process_zap(pr);
			}
		}

		KERNEL_UNLOCK();
	}
}

int
sys_wait4(struct proc *q, void *v, register_t *retval)
{
	struct sys_wait4_args /* {
		syscallarg(pid_t) pid;
		syscallarg(int *) status;
		syscallarg(int) options;
		syscallarg(struct rusage *) rusage;
	} */ *uap = v;
	struct rusage ru;
	int status, error;

	error = dowait4(q, SCARG(uap, pid),
	    SCARG(uap, status) ? &status : NULL,
	    SCARG(uap, options), SCARG(uap, rusage) ? &ru : NULL, retval);
	if (error == 0 && retval[0] > 0 && SCARG(uap, status)) {
		error = copyout(&status, SCARG(uap, status), sizeof(status));
	}
	if (error == 0 && retval[0] > 0 && SCARG(uap, rusage)) {
		error = copyout(&ru, SCARG(uap, rusage), sizeof(ru));
#ifdef KTRACE
		if (error == 0 && KTRPOINT(q, KTR_STRUCT))
			ktrrusage(q, &ru);
#endif
	}
	return (error);
}

int
dowait4(struct proc *q, pid_t pid, int *statusp, int options,
    struct rusage *rusage, register_t *retval)
{
	int nfound;
	struct process *pr;
	struct proc *p;
	int error;

	if (pid == 0)
		pid = -q->p_p->ps_pgid;
	if (options &~ (WUNTRACED|WNOHANG|WCONTINUED))
		return (EINVAL);

loop:
	nfound = 0;
	LIST_FOREACH(pr, &q->p_p->ps_children, ps_sibling) {
		if ((pr->ps_flags & PS_NOZOMBIE) ||
		    (pid != WAIT_ANY &&
		    pr->ps_pid != pid &&
		    pr->ps_pgid != -pid))
			continue;

		p = pr->ps_mainproc;

		nfound++;
		if (pr->ps_flags & PS_ZOMBIE) {
			retval[0] = pr->ps_pid;

			if (statusp != NULL)
				*statusp = W_EXITCODE(pr->ps_xexit,
				    pr->ps_xsig);
			if (rusage != NULL)
				memcpy(rusage, pr->ps_ru, sizeof(*rusage));
			proc_finish_wait(q, p);
			return (0);
		}
		if (pr->ps_flags & PS_TRACED &&
		    (pr->ps_flags & PS_WAITED) == 0 && pr->ps_single &&
		    pr->ps_single->p_stat == SSTOP &&
		    (pr->ps_single->p_flag & P_SUSPSINGLE) == 0) {
			single_thread_wait(pr);

			atomic_setbits_int(&pr->ps_flags, PS_WAITED);
			retval[0] = pr->ps_pid;

			if (statusp != NULL)
				*statusp = W_STOPCODE(pr->ps_xsig);
			if (rusage != NULL)
				memset(rusage, 0, sizeof(*rusage));
			return (0);
		}
		if (p->p_stat == SSTOP &&
		    (pr->ps_flags & PS_WAITED) == 0 &&
		    (p->p_flag & P_SUSPSINGLE) == 0 &&
		    (pr->ps_flags & PS_TRACED ||
		    options & WUNTRACED)) {
			atomic_setbits_int(&pr->ps_flags, PS_WAITED);
			retval[0] = pr->ps_pid;

			if (statusp != NULL)
				*statusp = W_STOPCODE(pr->ps_xsig);
			if (rusage != NULL)
				memset(rusage, 0, sizeof(*rusage));
			return (0);
		}
		if ((options & WCONTINUED) && (p->p_flag & P_CONTINUED)) {
			atomic_clearbits_int(&p->p_flag, P_CONTINUED);
			retval[0] = pr->ps_pid;

			if (statusp != NULL)
				*statusp = _WCONTINUED;
			if (rusage != NULL)
				memset(rusage, 0, sizeof(*rusage));
			return (0);
		}
	}
	if (nfound == 0)
		return (ECHILD);
	if (options & WNOHANG) {
		retval[0] = 0;
		return (0);
	}
	if ((error = tsleep_nsec(q->p_p, PWAIT | PCATCH, "wait", INFSLP)) != 0)
		return (error);
	goto loop;
}

void
proc_finish_wait(struct proc *waiter, struct proc *p)
{
	struct process *pr, *tr;
	struct rusage *rup;

	/*
	 * If we got the child via a ptrace 'attach',
	 * we need to give it back to the old parent.
	 */
	pr = p->p_p;
	if (pr->ps_oppid && (tr = prfind(pr->ps_oppid))) {
		atomic_clearbits_int(&pr->ps_flags, PS_TRACED);
		pr->ps_oppid = 0;
		proc_reparent(pr, tr);
		prsignal(tr, SIGCHLD);
		wakeup(tr);
	} else {
		scheduler_wait_hook(waiter, p);
		rup = &waiter->p_p->ps_cru;
		ruadd(rup, pr->ps_ru);
		LIST_REMOVE(pr, ps_list);	/* off zombprocess */
		freepid(pr->ps_pid);
		process_zap(pr);
	}
}

/*
 * make process 'parent' the new parent of process 'child'.
 */
void
proc_reparent(struct process *child, struct process *parent)
{

	if (child->ps_pptr == parent)
		return;

	LIST_REMOVE(child, ps_sibling);
	LIST_INSERT_HEAD(&parent->ps_children, child, ps_sibling);
	child->ps_pptr = parent;
}

void
process_zap(struct process *pr)
{
	struct vnode *otvp;
	struct proc *p = pr->ps_mainproc;

	/*
	 * Finally finished with old proc entry.
	 * Unlink it from its process group and free it.
	 */
	leavepgrp(pr);
	LIST_REMOVE(pr, ps_sibling);

	/*
	 * Decrement the count of procs running with this uid.
	 */
	(void)chgproccnt(pr->ps_ucred->cr_ruid, -1);

	/*
	 * Release reference to text vnode
	 */
	otvp = pr->ps_textvp;
	pr->ps_textvp = NULL;
	if (otvp)
		vrele(otvp);

	KASSERT(pr->ps_refcnt == 1);
	if (pr->ps_ptstat != NULL)
		free(pr->ps_ptstat, M_SUBPROC, sizeof(*pr->ps_ptstat));
	pool_put(&rusage_pool, pr->ps_ru);
	KASSERT(TAILQ_EMPTY(&pr->ps_threads));
	lim_free(pr->ps_limit);
	crfree(pr->ps_ucred);
	pool_put(&process_pool, pr);
	nprocesses--;

	proc_free(p);
}