summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_resource.c
blob: 811ccf479b5f63382f23c33049e7952b0033961d (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
/*-
 * Copyright (c) 1982, 1986, 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_resource.c	8.5 (Berkeley) 1/21/94
 * $Id: kern_resource.c,v 1.47 1999/04/27 12:21:07 phk Exp $
 */

#include "opt_compat.h"
#include "opt_rlimit.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/kernel.h>
#include <sys/file.h>
#include <sys/resourcevar.h>
#include <sys/malloc.h>
#include <sys/proc.h>

#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_prot.h>
#include <sys/lock.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>

static int donice __P((struct proc *curp, struct proc *chgp, int n));
/* dosetrlimit non-static:  Needed by SysVR4 emulator */
int dosetrlimit __P((struct proc *p, u_int which, struct rlimit *limp));

/*
 * Resource controls and accounting.
 */

#ifndef _SYS_SYSPROTO_H_
struct getpriority_args {
	int	which;
	int	who;
};
#endif
int
getpriority(curp, uap)
	struct proc *curp;
	register struct getpriority_args *uap;
{
	register struct proc *p;
	register int low = PRIO_MAX + 1;

	switch (uap->which) {

	case PRIO_PROCESS:
		if (uap->who == 0)
			p = curp;
		else
			p = pfind(uap->who);
		if (p == 0)
			break;
		low = p->p_nice;
		break;

	case PRIO_PGRP: {
		register struct pgrp *pg;

		if (uap->who == 0)
			pg = curp->p_pgrp;
		else if ((pg = pgfind(uap->who)) == NULL)
			break;
		for (p = pg->pg_members.lh_first; p != 0;
		     p = p->p_pglist.le_next) {
			if (p->p_nice < low)
				low = p->p_nice;
		}
		break;
	}

	case PRIO_USER:
		if (uap->who == 0)
			uap->who = curp->p_ucred->cr_uid;
		for (p = allproc.lh_first; p != 0; p = p->p_list.le_next)
			if (p->p_ucred->cr_uid == uap->who &&
			    p->p_nice < low)
				low = p->p_nice;
		break;

	default:
		return (EINVAL);
	}
	if (low == PRIO_MAX + 1)
		return (ESRCH);
	curp->p_retval[0] = low;
	return (0);
}

#ifndef _SYS_SYSPROTO_H_
struct setpriority_args {
	int	which;
	int	who;
	int	prio;
};
#endif
/* ARGSUSED */
int
setpriority(curp, uap)
	struct proc *curp;
	register struct setpriority_args *uap;
{
	register struct proc *p;
	int found = 0, error = 0;

	switch (uap->which) {

	case PRIO_PROCESS:
		if (uap->who == 0)
			p = curp;
		else
			p = pfind(uap->who);
		if (p == 0)
			break;
		error = donice(curp, p, uap->prio);
		found++;
		break;

	case PRIO_PGRP: {
		register struct pgrp *pg;

		if (uap->who == 0)
			pg = curp->p_pgrp;
		else if ((pg = pgfind(uap->who)) == NULL)
			break;
		for (p = pg->pg_members.lh_first; p != 0;
		    p = p->p_pglist.le_next) {
			error = donice(curp, p, uap->prio);
			found++;
		}
		break;
	}

	case PRIO_USER:
		if (uap->who == 0)
			uap->who = curp->p_ucred->cr_uid;
		for (p = allproc.lh_first; p != 0; p = p->p_list.le_next)
			if (p->p_ucred->cr_uid == uap->who) {
				error = donice(curp, p, uap->prio);
				found++;
			}
		break;

	default:
		return (EINVAL);
	}
	if (found == 0)
		return (ESRCH);
	return (error);
}

static int
donice(curp, chgp, n)
	register struct proc *curp, *chgp;
	register int n;
{
	register struct pcred *pcred = curp->p_cred;

	if (pcred->pc_ucred->cr_uid && pcred->p_ruid &&
	    pcred->pc_ucred->cr_uid != chgp->p_ucred->cr_uid &&
	    pcred->p_ruid != chgp->p_ucred->cr_uid)
		return (EPERM);
	if (n > PRIO_MAX)
		n = PRIO_MAX;
	if (n < PRIO_MIN)
		n = PRIO_MIN;
	if (n < chgp->p_nice && suser(curp))
		return (EACCES);
	chgp->p_nice = n;
	(void)resetpriority(chgp);
	return (0);
}

/* rtprio system call */
#ifndef _SYS_SYSPROTO_H_
struct rtprio_args {
	int		function;
	pid_t		pid;
	struct rtprio	*rtp;
};
#endif

/*
 * Set realtime priority
 */

/* ARGSUSED */
int
rtprio(curp, uap)
	struct proc *curp;
	register struct rtprio_args *uap;
{
	register struct proc *p;
	register struct pcred *pcred = curp->p_cred;
	struct rtprio rtp;
	int error;

	error = copyin(uap->rtp, &rtp, sizeof(struct rtprio));
	if (error)
		return (error);

	if (uap->pid == 0)
		p = curp;
	else
		p = pfind(uap->pid);

	if (p == 0)
		return (ESRCH);

	switch (uap->function) {
	case RTP_LOOKUP:
		return (copyout(&p->p_rtprio, uap->rtp, sizeof(struct rtprio)));
	case RTP_SET:
		if (pcred->pc_ucred->cr_uid && pcred->p_ruid &&
		    pcred->pc_ucred->cr_uid != p->p_ucred->cr_uid &&
		    pcred->p_ruid != p->p_ucred->cr_uid)
		        return (EPERM);
		/* disallow setting rtprio in most cases if not superuser */
		if (suser(curp)) {
			/* can't set someone else's */
			if (uap->pid)
				return (EPERM);
			/* can't set realtime priority */
/*
 * Realtime priority has to be restricted for reasons which should be
 * obvious. However, for idle priority, there is a potential for
 * system deadlock if an idleprio process gains a lock on a resource
 * that other processes need (and the idleprio process can't run
 * due to a CPU-bound normal process). Fix me! XXX
 */
#if 0
 			if (RTP_PRIO_IS_REALTIME(rtp.type))
#endif
			if (rtp.type != RTP_PRIO_NORMAL)
				return (EPERM);
		}
		switch (rtp.type) {
#ifdef RTP_PRIO_FIFO
		case RTP_PRIO_FIFO:
#endif
		case RTP_PRIO_REALTIME:
		case RTP_PRIO_NORMAL:
		case RTP_PRIO_IDLE:
			if (rtp.prio > RTP_PRIO_MAX)
				return (EINVAL);
			p->p_rtprio = rtp;
			return (0);
		default:
			return (EINVAL);
		}

	default:
		return (EINVAL);
	}
}

#if defined(COMPAT_43) || defined(COMPAT_SUNOS)
#ifndef _SYS_SYSPROTO_H_
struct osetrlimit_args {
	u_int	which;
	struct	orlimit *rlp;
};
#endif
/* ARGSUSED */
int
osetrlimit(p, uap)
	struct proc *p;
	register struct osetrlimit_args *uap;
{
	struct orlimit olim;
	struct rlimit lim;
	int error;

	if ((error =
	    copyin((caddr_t)uap->rlp, (caddr_t)&olim, sizeof(struct orlimit))))
		return (error);
	lim.rlim_cur = olim.rlim_cur;
	lim.rlim_max = olim.rlim_max;
	return (dosetrlimit(p, uap->which, &lim));
}

#ifndef _SYS_SYSPROTO_H_
struct ogetrlimit_args {
	u_int	which;
	struct	orlimit *rlp;
};
#endif
/* ARGSUSED */
int
ogetrlimit(p, uap)
	struct proc *p;
	register struct ogetrlimit_args *uap;
{
	struct orlimit olim;

	if (uap->which >= RLIM_NLIMITS)
		return (EINVAL);
	olim.rlim_cur = p->p_rlimit[uap->which].rlim_cur;
	if (olim.rlim_cur == -1)
		olim.rlim_cur = 0x7fffffff;
	olim.rlim_max = p->p_rlimit[uap->which].rlim_max;
	if (olim.rlim_max == -1)
		olim.rlim_max = 0x7fffffff;
	return (copyout((caddr_t)&olim, (caddr_t)uap->rlp, sizeof(olim)));
}
#endif /* COMPAT_43 || COMPAT_SUNOS */

#ifndef _SYS_SYSPROTO_H_
struct __setrlimit_args {
	u_int	which;
	struct	rlimit *rlp;
};
#endif
/* ARGSUSED */
int
setrlimit(p, uap)
	struct proc *p;
	register struct __setrlimit_args *uap;
{
	struct rlimit alim;
	int error;

	if ((error =
	    copyin((caddr_t)uap->rlp, (caddr_t)&alim, sizeof (struct rlimit))))
		return (error);
	return (dosetrlimit(p, uap->which, &alim));
}

int
dosetrlimit(p, which, limp)
	struct proc *p;
	u_int which;
	struct rlimit *limp;
{
	register struct rlimit *alimp;
	int error;

	if (which >= RLIM_NLIMITS)
		return (EINVAL);
	alimp = &p->p_rlimit[which];

	/*
	 * Preserve historical bugs by treating negative limits as unsigned.
	 */
	if (limp->rlim_cur < 0)
		limp->rlim_cur = RLIM_INFINITY;
	if (limp->rlim_max < 0)
		limp->rlim_max = RLIM_INFINITY;

	if (limp->rlim_cur > alimp->rlim_max ||
	    limp->rlim_max > alimp->rlim_max)
		if ((error = suser_xxx(0, p, PRISON_ROOT)))
			return (error);
	if (limp->rlim_cur > limp->rlim_max)
		limp->rlim_cur = limp->rlim_max;
	if (p->p_limit->p_refcnt > 1 &&
	    (p->p_limit->p_lflags & PL_SHAREMOD) == 0) {
		p->p_limit->p_refcnt--;
		p->p_limit = limcopy(p->p_limit);
		alimp = &p->p_rlimit[which];
	}

	switch (which) {

	case RLIMIT_CPU:
		if (limp->rlim_cur > RLIM_INFINITY / (rlim_t)1000000)
			p->p_limit->p_cpulimit = RLIM_INFINITY;
		else
			p->p_limit->p_cpulimit = 
			    (rlim_t)1000000 * limp->rlim_cur;
		break;
	case RLIMIT_DATA:
		if (limp->rlim_cur > MAXDSIZ)
			limp->rlim_cur = MAXDSIZ;
		if (limp->rlim_max > MAXDSIZ)
			limp->rlim_max = MAXDSIZ;
		break;

	case RLIMIT_STACK:
		if (limp->rlim_cur > MAXSSIZ)
			limp->rlim_cur = MAXSSIZ;
		if (limp->rlim_max > MAXSSIZ)
			limp->rlim_max = MAXSSIZ;
		/*
		 * Stack is allocated to the max at exec time with only
		 * "rlim_cur" bytes accessible.  If stack limit is going
		 * up make more accessible, if going down make inaccessible.
		 */
		if (limp->rlim_cur != alimp->rlim_cur) {
			vm_offset_t addr;
			vm_size_t size;
			vm_prot_t prot;

			if (limp->rlim_cur > alimp->rlim_cur) {
				prot = VM_PROT_ALL;
				size = limp->rlim_cur - alimp->rlim_cur;
				addr = USRSTACK - limp->rlim_cur;
			} else {
				prot = VM_PROT_NONE;
				size = alimp->rlim_cur - limp->rlim_cur;
				addr = USRSTACK - alimp->rlim_cur;
			}
			addr = trunc_page(addr);
			size = round_page(size);
			(void) vm_map_protect(&p->p_vmspace->vm_map,
					      addr, addr+size, prot, FALSE);
		}
		break;

	case RLIMIT_NOFILE:
		if (limp->rlim_cur > maxfilesperproc)
			limp->rlim_cur = maxfilesperproc;
		if (limp->rlim_max > maxfilesperproc)
			limp->rlim_max = maxfilesperproc;
		break;

	case RLIMIT_NPROC:
		if (limp->rlim_cur > maxprocperuid)
			limp->rlim_cur = maxprocperuid;
		if (limp->rlim_max > maxprocperuid)
			limp->rlim_max = maxprocperuid;
		break;
	}
	*alimp = *limp;
	return (0);
}

#ifndef _SYS_SYSPROTO_H_
struct __getrlimit_args {
	u_int	which;
	struct	rlimit *rlp;
};
#endif
/* ARGSUSED */
int
getrlimit(p, uap)
	struct proc *p;
	register struct __getrlimit_args *uap;
{

	if (uap->which >= RLIM_NLIMITS)
		return (EINVAL);
	return (copyout((caddr_t)&p->p_rlimit[uap->which], (caddr_t)uap->rlp,
	    sizeof (struct rlimit)));
}

/*
 * Transform the running time and tick information in proc p into user,
 * system, and interrupt time usage.
 */
void
calcru(p, up, sp, ip)
	struct proc *p;
	struct timeval *up;
	struct timeval *sp;
	struct timeval *ip;
{
	/* {user, system, interrupt, total} {ticks, usec}; previous tu: */
	u_int64_t ut, uu, st, su, it, iu, tt, tu, ptu;
	int s;
	struct timeval tv;

	/* XXX: why spl-protect ?  worst case is an off-by-one report */
	s = splstatclock();
	ut = p->p_uticks;
	st = p->p_sticks;
	it = p->p_iticks;
	splx(s);

	tt = ut + st + it;
	if (tt == 0) {
		st = 1;
		tt = 1;
	}

	tu = p->p_runtime;
#ifdef SMP
	if (p->p_oncpu != 0xff) {
#else
	if (p == curproc) {
#endif
		/*
		 * Adjust for the current time slice.  This is actually fairly
		 * important since the error here is on the order of a time
		 * quantum, which is much greater than the sampling error.
		 */
		microuptime(&tv);
		tu += (tv.tv_usec - switchtime.tv_usec) +
		    (tv.tv_sec - switchtime.tv_sec) * (int64_t)1000000;
	}
	ptu = p->p_stats->p_uu + p->p_stats->p_su + p->p_stats->p_iu;
	if (tu < ptu || (int64_t)tu < 0) {
		/* XXX no %qd in kernel.  Truncate. */
		printf("calcru: negative time of %ld usec for pid %d (%s)\n",
		       (long)tu, p->p_pid, p->p_comm);
		tu = ptu;
	}

	/* Subdivide tu. */
	uu = (tu * ut) / tt;
	su = (tu * st) / tt;
	iu = tu - uu - su;

	/* Enforce monotonicity. */
	if (uu < p->p_stats->p_uu || su < p->p_stats->p_su ||
	    iu < p->p_stats->p_iu) {
		if (uu < p->p_stats->p_uu)
			uu = p->p_stats->p_uu;
		else if (uu + p->p_stats->p_su + p->p_stats->p_iu > tu)
			uu = tu - p->p_stats->p_su - p->p_stats->p_iu;
		if (st == 0)
			su = p->p_stats->p_su;
		else {
			su = ((tu - uu) * st) / (st + it);
			if (su < p->p_stats->p_su)
				su = p->p_stats->p_su;
			else if (uu + su + p->p_stats->p_iu > tu)
				su = tu - uu - p->p_stats->p_iu;
		}
		KASSERT(uu + su + p->p_stats->p_iu <= tu,
		    ("calcru: monotonisation botch 1"));
		iu = tu - uu - su;
		KASSERT(iu >= p->p_stats->p_iu,
		    ("calcru: monotonisation botch 2"));
	}
	p->p_stats->p_uu = uu;
	p->p_stats->p_su = su;
	p->p_stats->p_iu = iu;

	up->tv_sec = uu / 1000000;
	up->tv_usec = uu % 1000000;
	sp->tv_sec = su / 1000000;
	sp->tv_usec = su % 1000000;
	if (ip != NULL) {
		ip->tv_sec = iu / 1000000;
		ip->tv_usec = iu % 1000000;
	}
}

#ifndef _SYS_SYSPROTO_H_
struct getrusage_args {
	int	who;
	struct	rusage *rusage;
};
#endif
/* ARGSUSED */
int
getrusage(p, uap)
	register struct proc *p;
	register struct getrusage_args *uap;
{
	register struct rusage *rup;

	switch (uap->who) {

	case RUSAGE_SELF:
		rup = &p->p_stats->p_ru;
		calcru(p, &rup->ru_utime, &rup->ru_stime, NULL);
		break;

	case RUSAGE_CHILDREN:
		rup = &p->p_stats->p_cru;
		break;

	default:
		return (EINVAL);
	}
	return (copyout((caddr_t)rup, (caddr_t)uap->rusage,
	    sizeof (struct rusage)));
}

void
ruadd(ru, ru2)
	register struct rusage *ru, *ru2;
{
	register long *ip, *ip2;
	register int i;

	timevaladd(&ru->ru_utime, &ru2->ru_utime);
	timevaladd(&ru->ru_stime, &ru2->ru_stime);
	if (ru->ru_maxrss < ru2->ru_maxrss)
		ru->ru_maxrss = ru2->ru_maxrss;
	ip = &ru->ru_first; ip2 = &ru2->ru_first;
	for (i = &ru->ru_last - &ru->ru_first; i >= 0; i--)
		*ip++ += *ip2++;
}

/*
 * Make a copy of the plimit structure.
 * We share these structures copy-on-write after fork,
 * and copy when a limit is changed.
 */
struct plimit *
limcopy(lim)
	struct plimit *lim;
{
	register struct plimit *copy;

	MALLOC(copy, struct plimit *, sizeof(struct plimit),
	    M_SUBPROC, M_WAITOK);
	bcopy(lim->pl_rlimit, copy->pl_rlimit, sizeof(struct plimit));
	copy->p_lflags = 0;
	copy->p_refcnt = 1;
	return (copy);
}
OpenPOWER on IntegriCloud