summaryrefslogtreecommitdiff
path: root/sys/kern/kern_exit.c
blob: 1c47e088818b8473aa403bd859d2a8e2b45decc0 (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
/*	$OpenBSD: kern_exit.c,v 1.34 2001/08/25 12:11:40 art 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. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 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/param.h>
#include <sys/systm.h>
#include <sys/map.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/proc.h>
#include <sys/buf.h>
#include <sys/wait.h>
#include <sys/file.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>
#ifdef SYSVSHM
#include <sys/shm.h>
#endif
#ifdef SYSVSEM
#include <sys/sem.h>
#endif

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

#include <machine/cpu.h>

#include <vm/vm.h>
#include <vm/vm_kern.h>

#include <uvm/uvm_extern.h>

void proc_zap __P((struct proc *));

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

	exit1(p, W_EXITCODE(SCARG(uap, rval), 0));
	/* NOTREACHED */
	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(p, rv)
	struct proc *p;
	int rv;
{
	struct proc *q, *nq;
	struct vmspace *vm;

	if (p->p_pid == 1)
		panic("init died (signal %d, exit %d)",
		    WTERMSIG(rv), WEXITSTATUS(rv));

	if (p->p_flag & P_PROFIL)
		stopprofclock(p);
	MALLOC(p->p_ru, struct rusage *, sizeof(struct rusage),
		M_ZOMBIE, M_WAITOK);
	/*
	 * If parent is waiting for us to exit or exec, P_PPWAIT is set; we
	 * wake up the parent early to avoid deadlock.
	 */
	p->p_flag |= P_WEXIT;
	p->p_flag &= ~P_TRACED;
	if (p->p_flag & P_PPWAIT) {
		p->p_flag &= ~P_PPWAIT;
		wakeup((caddr_t)p->p_pptr);
	}
	p->p_sigignore = ~0;
	p->p_siglist = 0;
	timeout_del(&p->p_realit_to);

	/*
	 * Close open files and release open-file table.
	 * This may block!
	 */
	fdfree(p);

	/* The next three chunks should probably be moved to vmspace_exit. */
	vm = p->p_vmspace;
#ifdef SYSVSHM
	if (vm->vm_shm && vm->vm_refcnt == 1)
		shmexit(vm);
#endif
#ifdef SYSVSEM
	semexit(p);
#endif
	/*
	 * Release user portion of address space.
	 * This releases references to vnodes,
	 * which could cause I/O if the file has been unlinked.
	 * Need to do this early enough that we can still sleep.
	 * Can't free the entire vmspace as the kernel stack
	 * may be mapped within that space also.
	 */
	if (vm->vm_refcnt == 1)
		(void) uvm_deallocate(&vm->vm_map, VM_MIN_ADDRESS,
		    VM_MAXUSER_ADDRESS - VM_MIN_ADDRESS);

	if (SESS_LEADER(p)) {
		register struct session *sp = p->p_session;

		if (sp->s_ttyvp) {
			/*
			 * Controlling process.
			 * Signal foreground pgrp,
			 * drain controlling terminal
			 * and revoke access to controlling terminal.
			 */
			if (sp->s_ttyp->t_session == sp) {
				if (sp->s_ttyp->t_pgrp)
					pgsignal(sp->s_ttyp->t_pgrp, SIGHUP, 1);
				(void) ttywait(sp->s_ttyp);
				/*
				 * The tty could have been revoked
				 * if we blocked.
				 */
				if (sp->s_ttyvp)
					VOP_REVOKE(sp->s_ttyvp, REVOKEALL);
			}
			if (sp->s_ttyvp)
				vrele(sp->s_ttyvp);
			sp->s_ttyvp = NULL;
			/*
			 * s_ttyp is not zero'd; we use this to indicate
			 * that the session once had a controlling terminal.
			 * (for logging and informational purposes)
			 */
		}
		sp->s_leader = NULL;
	}
	fixjobc(p, p->p_pgrp, 0);
	(void)acct_process(p);
#ifdef KTRACE
	/* 
	 * release trace file
	 */
	p->p_traceflag = 0;	/* don't trace the vrele() */
	if (p->p_tracep)
		ktrsettracevnode(p, NULL);
#endif
	/*
	 * NOTE: WE ARE NO LONGER ALLOWED TO SLEEP!
	 */
	p->p_stat = SDEAD;

        /*
         * Remove proc from pidhash chain so looking it up won't
         * work.  Move it from allproc to zombproc, but do not yet
         * wake up the reaper.  We will put the proc on the
         * deadproc list later (using the p_hash member), and
         * wake up the reaper when we do.
         */
	LIST_REMOVE(p, p_hash);
	LIST_REMOVE(p, p_list);
	LIST_INSERT_HEAD(&zombproc, p, p_list);

	/*
	 * Give orphaned children to init(8).
	 */
	q = p->p_children.lh_first;
	if (q)		/* only need this if any child is S_ZOMB */
		wakeup((caddr_t)initproc);
	for (; q != 0; q = nq) {
		nq = q->p_sibling.le_next;
		proc_reparent(q, initproc);
		/*
		 * Traced processes are killed
		 * since their existence means someone is screwing up.
		 */
		if (q->p_flag & P_TRACED) {
			q->p_flag &= ~P_TRACED;
			psignal(q, SIGKILL);
		}
	}

	/*
	 * Save exit status and final rusage info, adding in child rusage
	 * info and self times.
	 */
	p->p_xstat = rv;
	*p->p_ru = p->p_stats->p_ru;
	calcru(p, &p->p_ru->ru_utime, &p->p_ru->ru_stime, NULL);
	ruadd(p->p_ru, &p->p_stats->p_cru);

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

	/*
	 * notify interested parties of our demise.
	 */
	KNOTE(&p->p_klist, NOTE_EXIT);

	/*
	 * Notify parent that we're gone.  If we have P_NOZOMBIE or parent has
	 * the P_NOCLDWAIT flag set, notify process 1 instead (and hope it
	 * will handle this situation).
	 */
	if ((p->p_flag & P_NOZOMBIE) || (p->p_pptr->p_flag & P_NOCLDWAIT)) {
		struct proc *pp = p->p_pptr;
		proc_reparent(p, initproc);
		/*
		 * If this was the last child of our parent, notify
		 * parent, so in case he was wait(2)ing, he will
		 * continue.
		 */
		if (pp->p_children.lh_first == NULL)
			wakeup((caddr_t)pp);
	}

	if ((p->p_flag & P_FSTRACE) == 0 && p->p_exitsig != 0)
		psignal(p->p_pptr, P_EXITSIG(p));
	wakeup((caddr_t)p->p_pptr);

	/*
	 * Notify procfs debugger
	 */
	if (p->p_flag & P_FSTRACE)
		wakeup((caddr_t)p);

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

	/*
	 * Clear curproc after we've done all operations
	 * that could block, and before tearing down the rest
	 * of the process state that might be used from clock, etc.
	 * Also, can't clear curproc while we're still runnable,
	 * as we're not on a run queue (we are current, just not
	 * a proper proc any longer!).
	 *
	 * Other substructures are freed from wait().
	 */
	curproc = NULL;
	limfree(p->p_limit);
	p->p_limit = NULL;

	/*
	 * 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).
	 */
	cpu_exit(p);
}

/*
 * 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 (a spin lock), place the proc on that
 * list (using the p_hash member), and wake up the reaper.
 */
void
exit2(p)
	struct proc *p;
{

	simple_lock(&deadproc_slock);
	LIST_INSERT_HEAD(&deadproc, p, p_hash);
	simple_unlock(&deadproc_slock);

	wakeup(&deadproc);
}

/*
 * 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()
{
	struct proc *p;

	for (;;) {
		simple_lock(&deadproc_slock);
		p = LIST_FIRST(&deadproc);
		if (p == NULL) {
			/* No work for us; go to sleep until someone exits. */
			simple_unlock(&deadproc_slock);
			(void) tsleep(&deadproc, PVM, "reaper", 0);
			continue;
		}

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

		/*
		 * Give machine-dependent code a chance to free any
		 * resources it couldn't free while still running on
		 * that process's context.  This must be done before
		 * uvm_exit(), in case these resources are in the PCB.
		 */
		cpu_wait(p);

		/*
		 * Free the VM resources we're still holding on to.
		 * We must do this from a valid thread because doing
		 * so may block.
		 */
		uvm_exit(p);

		/* Process is now a true zombie. */
		if ((p->p_flag & P_NOZOMBIE) == 0) {
			p->p_stat = SZOMB;

			/* Wake up the parent so it can get exit status. */
			psignal(p->p_pptr, SIGCHLD);
			wakeup((caddr_t)p->p_pptr);
		} else {
			/* Noone will wait for us. Just zap the process now */
			proc_zap(p);
		}
	}
}

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

	if (SCARG(uap, pid) == 0)
		SCARG(uap, pid) = -q->p_pgid;
	if (SCARG(uap, options) &~ (WUNTRACED|WNOHANG|WALTSIG))
		return (EINVAL);

loop:
	nfound = 0;
	for (p = q->p_children.lh_first; p != 0; p = p->p_sibling.le_next) {
		if ((p->p_flag & P_NOZOMBIE) ||
		    (SCARG(uap, pid) != WAIT_ANY &&
		    p->p_pid != SCARG(uap, pid) &&
		    p->p_pgid != -SCARG(uap, pid)))
			continue;

		/*
		 * Wait for processes with p_exitsig != SIGCHLD processes only
		 * if WALTSIG is set; wait for processes with pexitsig ==
		 * SIGCHLD only if WALTSIG is clear.
		 */
		if ((SCARG(uap, options) & WALTSIG) ?
		    (p->p_exitsig == SIGCHLD) : (P_EXITSIG(p) != SIGCHLD))
			continue;

		nfound++;
		if (p->p_stat == SZOMB) {
			retval[0] = p->p_pid;

			if (SCARG(uap, status)) {
				status = p->p_xstat;	/* convert to int */
				error = copyout((caddr_t)&status,
						(caddr_t)SCARG(uap, status),
						sizeof(status));
				if (error)
					return (error);
			}
			if (SCARG(uap, rusage) &&
			    (error = copyout((caddr_t)p->p_ru,
			    (caddr_t)SCARG(uap, rusage),
			    sizeof(struct rusage))))
				return (error);

			/*
			 * If we got the child via a ptrace 'attach',
			 * we need to give it back to the old parent.
			 */
			if (p->p_oppid && (t = pfind(p->p_oppid))) {
				p->p_oppid = 0;
				proc_reparent(p, t);
				if (p->p_exitsig != 0)
					psignal(t, P_EXITSIG(p));
				wakeup((caddr_t)t);
				return (0);
			}

			scheduler_wait_hook(q, p);
			p->p_xstat = 0;
			ruadd(&q->p_stats->p_cru, p->p_ru);

			proc_zap(p);

			return (0);
		}
		if (p->p_stat == SSTOP && (p->p_flag & P_WAITED) == 0 &&
		    (p->p_flag & P_TRACED || SCARG(uap, options) & WUNTRACED)) {
			p->p_flag |= P_WAITED;
			retval[0] = p->p_pid;

			if (SCARG(uap, status)) {
				status = W_STOPCODE(p->p_xstat);
				error = copyout((caddr_t)&status,
				    (caddr_t)SCARG(uap, status),
				    sizeof(status));
			} else
				error = 0;
			return (error);
		}
	}
	if (nfound == 0)
		return (ECHILD);
	if (SCARG(uap, options) & WNOHANG) {
		retval[0] = 0;
		return (0);
	}
	if ((error = tsleep((caddr_t)q, PWAIT | PCATCH, "wait", 0)) != 0)
		return (error);
	goto loop;
}

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

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

	if (parent == initproc)
		child->p_exitsig = SIGCHLD;

	LIST_REMOVE(child, p_sibling);
	LIST_INSERT_HEAD(&parent->p_children, child, p_sibling);
	child->p_pptr = parent;
}

void
proc_zap(p)
	struct proc *p;
{

	FREE(p->p_ru, M_ZOMBIE);

	/*
	 * Finally finished with old proc entry.
	 * Unlink it from its process group and free it.
	 */
	leavepgrp(p);
	LIST_REMOVE(p, p_list);	/* off zombproc */
	LIST_REMOVE(p, p_sibling);

	/*
	 * Decrement the count of procs running with this uid.
	 */
	(void)chgproccnt(p->p_cred->p_ruid, -1);

	/*
	 * Free up credentials.
	 */
	if (--p->p_cred->p_refcnt == 0) {
		crfree(p->p_cred->pc_ucred);
		FREE(p->p_cred, M_SUBPROC);
	}

	/*
	 * Release reference to text vnode
	 */
	if (p->p_textvp)
		vrele(p->p_textvp);

	pool_put(&proc_pool, p);
	nprocs--;
}