summaryrefslogtreecommitdiff
path: root/sys/kern/kern_resource.c
blob: 05aca1807ff26d918ef4476401dbbb97e023cfb6 (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
/*	$NetBSD: kern_resource.c,v 1.191 2023/07/08 20:02:10 riastradh Exp $	*/

/*-
 * 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. 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	8.8 (Berkeley) 2/14/95
 */

#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: kern_resource.c,v 1.191 2023/07/08 20:02:10 riastradh Exp $");

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/file.h>
#include <sys/resourcevar.h>
#include <sys/kmem.h>
#include <sys/namei.h>
#include <sys/pool.h>
#include <sys/proc.h>
#include <sys/sysctl.h>
#include <sys/timevar.h>
#include <sys/kauth.h>
#include <sys/atomic.h>
#include <sys/mount.h>
#include <sys/syscallargs.h>
#include <sys/atomic.h>

#include <uvm/uvm_extern.h>

/*
 * Maximum process data and stack limits.
 * They are variables so they are patchable.
 */
rlim_t			maxdmap = MAXDSIZ;
rlim_t			maxsmap = MAXSSIZ;

static pool_cache_t	plimit_cache	__read_mostly;
static pool_cache_t	pstats_cache	__read_mostly;

static kauth_listener_t	resource_listener;
static struct sysctllog	*proc_sysctllog;

static int	donice(struct lwp *, struct proc *, int);
static void	sysctl_proc_setup(void);

static int
resource_listener_cb(kauth_cred_t cred, kauth_action_t action, void *cookie,
    void *arg0, void *arg1, void *arg2, void *arg3)
{
	struct proc *p;
	int result;

	result = KAUTH_RESULT_DEFER;
	p = arg0;

	switch (action) {
	case KAUTH_PROCESS_NICE:
		if (kauth_cred_geteuid(cred) != kauth_cred_geteuid(p->p_cred) &&
		    kauth_cred_getuid(cred) != kauth_cred_geteuid(p->p_cred)) {
			break;
		}

		if ((u_long)arg1 >= p->p_nice)
			result = KAUTH_RESULT_ALLOW;

		break;

	case KAUTH_PROCESS_RLIMIT: {
		enum kauth_process_req req;

		req = (enum kauth_process_req)(uintptr_t)arg1;

		switch (req) {
		case KAUTH_REQ_PROCESS_RLIMIT_GET:
			result = KAUTH_RESULT_ALLOW;
			break;

		case KAUTH_REQ_PROCESS_RLIMIT_SET: {
			struct rlimit *new_rlimit;
			u_long which;

			if ((p != curlwp->l_proc) &&
			    (proc_uidmatch(cred, p->p_cred) != 0))
				break;

			new_rlimit = arg2;
			which = (u_long)arg3;

			if (new_rlimit->rlim_max <= p->p_rlimit[which].rlim_max)
				result = KAUTH_RESULT_ALLOW;

			break;
			}

		default:
			break;
		}

		break;
	}

	default:
		break;
	}

	return result;
}

void
resource_init(void)
{

	plimit_cache = pool_cache_init(sizeof(struct plimit), 0, 0, 0,
	    "plimitpl", NULL, IPL_NONE, NULL, NULL, NULL);
	pstats_cache = pool_cache_init(sizeof(struct pstats), 0, 0, 0,
	    "pstatspl", NULL, IPL_NONE, NULL, NULL, NULL);

	resource_listener = kauth_listen_scope(KAUTH_SCOPE_PROCESS,
	    resource_listener_cb, NULL);

	sysctl_proc_setup();
}

/*
 * Resource controls and accounting.
 */

int
sys_getpriority(struct lwp *l, const struct sys_getpriority_args *uap,
    register_t *retval)
{
	/* {
		syscallarg(int) which;
		syscallarg(id_t) who;
	} */
	struct proc *curp = l->l_proc, *p;
	id_t who = SCARG(uap, who);
	int low = NZERO + PRIO_MAX + 1;

	mutex_enter(&proc_lock);
	switch (SCARG(uap, which)) {
	case PRIO_PROCESS:
		p = who ? proc_find(who) : curp;
		if (p != NULL)
			low = p->p_nice;
		break;

	case PRIO_PGRP: {
		struct pgrp *pg;

		if (who == 0)
			pg = curp->p_pgrp;
		else if ((pg = pgrp_find(who)) == NULL)
			break;
		LIST_FOREACH(p, &pg->pg_members, p_pglist) {
			if (p->p_nice < low)
				low = p->p_nice;
		}
		break;
	}

	case PRIO_USER:
		if (who == 0)
			who = (int)kauth_cred_geteuid(l->l_cred);
		PROCLIST_FOREACH(p, &allproc) {
			mutex_enter(p->p_lock);
			if (kauth_cred_geteuid(p->p_cred) ==
			    (uid_t)who && p->p_nice < low)
				low = p->p_nice;
			mutex_exit(p->p_lock);
		}
		break;

	default:
		mutex_exit(&proc_lock);
		return EINVAL;
	}
	mutex_exit(&proc_lock);

	if (low == NZERO + PRIO_MAX + 1) {
		return ESRCH;
	}
	*retval = low - NZERO;
	return 0;
}

int
sys_setpriority(struct lwp *l, const struct sys_setpriority_args *uap,
    register_t *retval)
{
	/* {
		syscallarg(int) which;
		syscallarg(id_t) who;
		syscallarg(int) prio;
	} */
	struct proc *curp = l->l_proc, *p;
	id_t who = SCARG(uap, who);
	int found = 0, error = 0;

	mutex_enter(&proc_lock);
	switch (SCARG(uap, which)) {
	case PRIO_PROCESS:
		p = who ? proc_find(who) : curp;
		if (p != NULL) {
			mutex_enter(p->p_lock);
			found++;
			error = donice(l, p, SCARG(uap, prio));
			mutex_exit(p->p_lock);
		}
		break;

	case PRIO_PGRP: {
		struct pgrp *pg;

		if (who == 0)
			pg = curp->p_pgrp;
		else if ((pg = pgrp_find(who)) == NULL)
			break;
		LIST_FOREACH(p, &pg->pg_members, p_pglist) {
			mutex_enter(p->p_lock);
			found++;
			error = donice(l, p, SCARG(uap, prio));
			mutex_exit(p->p_lock);
			if (error)
				break;
		}
		break;
	}

	case PRIO_USER:
		if (who == 0)
			who = (int)kauth_cred_geteuid(l->l_cred);
		PROCLIST_FOREACH(p, &allproc) {
			mutex_enter(p->p_lock);
			if (kauth_cred_geteuid(p->p_cred) ==
			    (uid_t)SCARG(uap, who)) {
				found++;
				error = donice(l, p, SCARG(uap, prio));
			}
			mutex_exit(p->p_lock);
			if (error)
				break;
		}
		break;

	default:
		mutex_exit(&proc_lock);
		return EINVAL;
	}
	mutex_exit(&proc_lock);

	return (found == 0) ? ESRCH : error;
}

/*
 * Renice a process.
 *
 * Call with the target process' credentials locked.
 */
static int
donice(struct lwp *l, struct proc *chgp, int n)
{
	kauth_cred_t cred = l->l_cred;

	KASSERT(mutex_owned(chgp->p_lock));

	if (kauth_cred_geteuid(cred) && kauth_cred_getuid(cred) &&
	    kauth_cred_geteuid(cred) != kauth_cred_geteuid(chgp->p_cred) &&
	    kauth_cred_getuid(cred) != kauth_cred_geteuid(chgp->p_cred))
		return EPERM;

	if (n > PRIO_MAX) {
		n = PRIO_MAX;
	}
	if (n < PRIO_MIN) {
		n = PRIO_MIN;
	}
	n += NZERO;

	if (kauth_authorize_process(cred, KAUTH_PROCESS_NICE, chgp,
	    KAUTH_ARG(n), NULL, NULL)) {
		return EACCES;
	}

	sched_nice(chgp, n);
	return 0;
}

int
sys_setrlimit(struct lwp *l, const struct sys_setrlimit_args *uap,
    register_t *retval)
{
	/* {
		syscallarg(int) which;
		syscallarg(const struct rlimit *) rlp;
	} */
	int error, which = SCARG(uap, which);
	struct rlimit alim;

	error = copyin(SCARG(uap, rlp), &alim, sizeof(struct rlimit));
	if (error) {
		return error;
	}
	return dosetrlimit(l, l->l_proc, which, &alim);
}

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

	if ((u_int)which >= RLIM_NLIMITS)
		return EINVAL;

	if (limp->rlim_cur > limp->rlim_max) {
		/*
		 * This is programming error. According to SUSv2, we should
		 * return error in this case.
		 */
		return EINVAL;
	}

	alimp = &p->p_rlimit[which];
	/* if we don't change the value, no need to limcopy() */
	if (limp->rlim_cur == alimp->rlim_cur &&
	    limp->rlim_max == alimp->rlim_max)
		return 0;

	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_RLIMIT,
	    p, KAUTH_ARG(KAUTH_REQ_PROCESS_RLIMIT_SET), limp, KAUTH_ARG(which));
	if (error)
		return error;

	lim_privatise(p);
	/* p->p_limit is now unchangeable */
	alimp = &p->p_rlimit[which];

	switch (which) {

	case RLIMIT_DATA:
		if (limp->rlim_cur > maxdmap)
			limp->rlim_cur = maxdmap;
		if (limp->rlim_max > maxdmap)
			limp->rlim_max = maxdmap;
		break;

	case RLIMIT_STACK:
		if (limp->rlim_cur > maxsmap)
			limp->rlim_cur = maxsmap;
		if (limp->rlim_max > maxsmap)
			limp->rlim_max = maxsmap;

		/*
		 * Return EINVAL if the new stack size limit is lower than
		 * current usage. Otherwise, the process would get SIGSEGV the
		 * moment it would try to access anything on its current stack.
		 * This conforms to SUSv2.
		 */
		if (btoc(limp->rlim_cur) < p->p_vmspace->vm_ssize ||
		    btoc(limp->rlim_max) < p->p_vmspace->vm_ssize) {
			return EINVAL;
		}

		/*
		 * Stack is allocated to the max at exec time with
		 * only "rlim_cur" bytes accessible (In other words,
		 * allocates stack dividing two contiguous regions at
		 * "rlim_cur" bytes boundary).
		 *
		 * Since allocation is done in terms of page, roundup
		 * "rlim_cur" (otherwise, contiguous regions
		 * overlap).  If stack limit is going up make more
		 * accessible, if going down make inaccessible.
		 */
		limp->rlim_max = round_page(limp->rlim_max);
		limp->rlim_cur = round_page(limp->rlim_cur);
		if (limp->rlim_cur != alimp->rlim_cur) {
			vaddr_t addr;
			vsize_t size;
			vm_prot_t prot;
			char *base, *tmp;

			base = p->p_vmspace->vm_minsaddr;
			if (limp->rlim_cur > alimp->rlim_cur) {
				prot = VM_PROT_READ | VM_PROT_WRITE;
				size = limp->rlim_cur - alimp->rlim_cur;
				tmp = STACK_GROW(base, alimp->rlim_cur);
			} else {
				prot = VM_PROT_NONE;
				size = alimp->rlim_cur - limp->rlim_cur;
				tmp = STACK_GROW(base, limp->rlim_cur);
			}
			addr = (vaddr_t)STACK_ALLOC(tmp, size);
			(void) uvm_map_protect(&p->p_vmspace->vm_map,
			    addr, addr + size, prot, false);
		}
		break;

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

	case RLIMIT_NPROC:
		if (limp->rlim_cur > maxproc)
			limp->rlim_cur = maxproc;
		if (limp->rlim_max > maxproc)
			limp->rlim_max = maxproc;
		break;

	case RLIMIT_NTHR:
		if (limp->rlim_cur > maxlwp)
			limp->rlim_cur = maxlwp;
		if (limp->rlim_max > maxlwp)
			limp->rlim_max = maxlwp;
		break;
	}

	mutex_enter(&p->p_limit->pl_lock);
	*alimp = *limp;
	mutex_exit(&p->p_limit->pl_lock);
	return 0;
}

int
sys_getrlimit(struct lwp *l, const struct sys_getrlimit_args *uap,
    register_t *retval)
{
	/* {
		syscallarg(int) which;
		syscallarg(struct rlimit *) rlp;
	} */
	struct proc *p = l->l_proc;
	int which = SCARG(uap, which);
	struct rlimit rl;

	if ((u_int)which >= RLIM_NLIMITS)
		return EINVAL;

	mutex_enter(p->p_lock);
	memcpy(&rl, &p->p_rlimit[which], sizeof(rl));
	mutex_exit(p->p_lock);

	return copyout(&rl, SCARG(uap, rlp), sizeof(rl));
}

void
addrulwp(struct lwp *l, struct bintime *tm)
{

	lwp_lock(l);
	bintime_add(tm, &l->l_rtime);
	if ((l->l_pflag & LP_RUNNING) != 0 &&
	    (l->l_pflag & (LP_INTR | LP_TIMEINTR)) != LP_INTR) {
		struct bintime diff;
		/*
		 * 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.
		 */
		binuptime(&diff);
		membar_consumer(); /* for softint_dispatch() */
		bintime_sub(&diff, &l->l_stime);
		bintime_add(tm, &diff);
	}
	lwp_unlock(l);
}

/*
 * Transform the running time and tick information in proc p into user,
 * system, and interrupt time usage.
 *
 * Should be called with p->p_lock held unless called from exit1().
 */
void
calcru(struct proc *p, struct timeval *up, struct timeval *sp,
    struct timeval *ip, struct timeval *rp)
{
	uint64_t u, st, ut, it, tot, dt;
	struct lwp *l;
	struct bintime tm;
	struct timeval tv;

	KASSERT(p->p_stat == SDEAD || mutex_owned(p->p_lock));

	mutex_spin_enter(&p->p_stmutex);
	st = p->p_sticks;
	ut = p->p_uticks;
	it = p->p_iticks;
	mutex_spin_exit(&p->p_stmutex);

	tm = p->p_rtime;

	LIST_FOREACH(l, &p->p_lwps, l_sibling) {
		addrulwp(l, &tm);
	}

	tot = st + ut + it;
	bintime2timeval(&tm, &tv);
	u = (uint64_t)tv.tv_sec * 1000000ul + tv.tv_usec;

	if (tot == 0) {
		/* No ticks, so can't use to share time out, split 50-50 */
		st = ut = u / 2;
	} else {
		st = (u * st) / tot;
		ut = (u * ut) / tot;
	}

	/*
	 * Try to avoid lying to the users (too much)
	 *
	 * Of course, user/sys time are based on sampling (ie: statistics)
	 * so that would be impossible, but convincing the mark
	 * that we have used less ?time this call than we had
	 * last time, is beyond reasonable...  (the con fails!)
	 *
	 * Note that since actual used time cannot decrease, either
	 * utime or stime (or both) must be greater now than last time
	 * (or both the same) - if one seems to have decreased, hold
	 * it constant and steal the necessary bump from the other
	 * which must have increased.
	 */
	if (p->p_xutime > ut) {
		dt = p->p_xutime - ut;
		st -= uimin(dt, st);
		ut = p->p_xutime;
	} else if (p->p_xstime > st) {
		dt = p->p_xstime - st;
		ut -= uimin(dt, ut);
		st = p->p_xstime;
	}

	if (sp != NULL) {
		p->p_xstime = st;
		sp->tv_sec = st / 1000000;
		sp->tv_usec = st % 1000000;
	}
	if (up != NULL) {
		p->p_xutime = ut;
		up->tv_sec = ut / 1000000;
		up->tv_usec = ut % 1000000;
	}
	if (ip != NULL) {
		if (it != 0)		/* it != 0 --> tot != 0 */
			it = (u * it) / tot;
		ip->tv_sec = it / 1000000;
		ip->tv_usec = it % 1000000;
	}
	if (rp != NULL) {
		*rp = tv;
	}
}

int
sys___getrusage50(struct lwp *l, const struct sys___getrusage50_args *uap,
    register_t *retval)
{
	/* {
		syscallarg(int) who;
		syscallarg(struct rusage *) rusage;
	} */
	int error;
	struct rusage ru;
	struct proc *p = l->l_proc;

	error = getrusage1(p, SCARG(uap, who), &ru);
	if (error != 0)
		return error;

	return copyout(&ru, SCARG(uap, rusage), sizeof(ru));
}

int
getrusage1(struct proc *p, int who, struct rusage *ru)
{

	switch (who) {
	case RUSAGE_SELF:
		mutex_enter(p->p_lock);
		ruspace(p);
		memcpy(ru, &p->p_stats->p_ru, sizeof(*ru));
		calcru(p, &ru->ru_utime, &ru->ru_stime, NULL, NULL);
		rulwps(p, ru);
		mutex_exit(p->p_lock);
		break;
	case RUSAGE_CHILDREN:
		mutex_enter(p->p_lock);
		memcpy(ru, &p->p_stats->p_cru, sizeof(*ru));
		mutex_exit(p->p_lock);
		break;
	default:
		return EINVAL;
	}

	return 0;
}

void
ruspace(struct proc *p)
{
	struct vmspace *vm = p->p_vmspace;
	struct rusage *ru = &p->p_stats->p_ru;

	ru->ru_ixrss = vm->vm_tsize << (PAGE_SHIFT - 10);
	ru->ru_idrss = vm->vm_dsize << (PAGE_SHIFT - 10);
	ru->ru_isrss = vm->vm_ssize << (PAGE_SHIFT - 10);
#ifdef __HAVE_NO_PMAP_STATS
	/* We don't keep track of the max so we get the current */
	ru->ru_maxrss = vm_resident_count(vm) << (PAGE_SHIFT - 10);
#else
	ru->ru_maxrss = vm->vm_rssmax << (PAGE_SHIFT - 10);
#endif
}

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

	timeradd(&ru->ru_utime, &ru2->ru_utime, &ru->ru_utime);
	timeradd(&ru->ru_stime, &ru2->ru_stime, &ru->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++;
}

void
rulwps(proc_t *p, struct rusage *ru)
{
	lwp_t *l;

	KASSERT(mutex_owned(p->p_lock));

	LIST_FOREACH(l, &p->p_lwps, l_sibling) {
		ruadd(ru, &l->l_ru);
		ru->ru_nvcsw += (l->l_ncsw - l->l_nivcsw);
		ru->ru_nivcsw += l->l_nivcsw;
	}
}

/*
 * lim_copy: make a copy of the plimit structure.
 *
 * We use copy-on-write after fork, and copy when a limit is changed.
 */
struct plimit *
lim_copy(struct plimit *lim)
{
	struct plimit *newlim;
	char *corename;
	size_t alen, len;

	newlim = pool_cache_get(plimit_cache, PR_WAITOK);
	mutex_init(&newlim->pl_lock, MUTEX_DEFAULT, IPL_NONE);
	newlim->pl_writeable = false;
	newlim->pl_refcnt = 1;
	newlim->pl_sv_limit = NULL;

	mutex_enter(&lim->pl_lock);
	memcpy(newlim->pl_rlimit, lim->pl_rlimit,
	    sizeof(struct rlimit) * RLIM_NLIMITS);

	/*
	 * Note: the common case is a use of default core name.
	 */
	alen = 0;
	corename = NULL;
	for (;;) {
		if (lim->pl_corename == defcorename) {
			newlim->pl_corename = defcorename;
			newlim->pl_cnlen = 0;
			break;
		}
		len = lim->pl_cnlen;
		if (len == alen) {
			newlim->pl_corename = corename;
			newlim->pl_cnlen = len;
			memcpy(corename, lim->pl_corename, len);
			corename = NULL;
			break;
		}
		mutex_exit(&lim->pl_lock);
		if (corename) {
			kmem_free(corename, alen);
		}
		alen = len;
		corename = kmem_alloc(alen, KM_SLEEP);
		mutex_enter(&lim->pl_lock);
	}
	mutex_exit(&lim->pl_lock);

	if (corename) {
		kmem_free(corename, alen);
	}
	return newlim;
}

void
lim_addref(struct plimit *lim)
{
	atomic_inc_uint(&lim->pl_refcnt);
}

/*
 * lim_privatise: give a process its own private plimit structure.
 */
void
lim_privatise(proc_t *p)
{
	struct plimit *lim = p->p_limit, *newlim;

	if (lim->pl_writeable) {
		return;
	}

	newlim = lim_copy(lim);

	mutex_enter(p->p_lock);
	if (p->p_limit->pl_writeable) {
		/* Other thread won the race. */
		mutex_exit(p->p_lock);
		lim_free(newlim);
		return;
	}

	/*
	 * Since p->p_limit can be accessed without locked held,
	 * old limit structure must not be deleted yet.
	 */
	newlim->pl_sv_limit = p->p_limit;
	newlim->pl_writeable = true;
	p->p_limit = newlim;
	mutex_exit(p->p_lock);
}

void
lim_setcorename(proc_t *p, char *name, size_t len)
{
	struct plimit *lim;
	char *oname;
	size_t olen;

	lim_privatise(p);
	lim = p->p_limit;

	mutex_enter(&lim->pl_lock);
	oname = lim->pl_corename;
	olen = lim->pl_cnlen;
	lim->pl_corename = name;
	lim->pl_cnlen = len;
	mutex_exit(&lim->pl_lock);

	if (oname != defcorename) {
		kmem_free(oname, olen);
	}
}

void
lim_free(struct plimit *lim)
{
	struct plimit *sv_lim;

	do {
		membar_release();
		if (atomic_dec_uint_nv(&lim->pl_refcnt) > 0) {
			return;
		}
		membar_acquire();
		if (lim->pl_corename != defcorename) {
			kmem_free(lim->pl_corename, lim->pl_cnlen);
		}
		sv_lim = lim->pl_sv_limit;
		mutex_destroy(&lim->pl_lock);
		pool_cache_put(plimit_cache, lim);
	} while ((lim = sv_lim) != NULL);
}

struct pstats *
pstatscopy(struct pstats *ps)
{
	struct pstats *nps;
	size_t len;

	nps = pool_cache_get(pstats_cache, PR_WAITOK);

	len = (char *)&nps->pstat_endzero - (char *)&nps->pstat_startzero;
	memset(&nps->pstat_startzero, 0, len);

	len = (char *)&nps->pstat_endcopy - (char *)&nps->pstat_startcopy;
	memcpy(&nps->pstat_startcopy, &ps->pstat_startcopy, len);

	return nps;
}

void
pstatsfree(struct pstats *ps)
{

	pool_cache_put(pstats_cache, ps);
}

/*
 * sysctl_proc_findproc: a routine for sysctl proc subtree helpers that
 * need to pick a valid process by PID.
 *
 * => Hold a reference on the process, on success.
 */
static int
sysctl_proc_findproc(lwp_t *l, pid_t pid, proc_t **p2)
{
	proc_t *p;
	int error;

	if (pid == PROC_CURPROC) {
		p = l->l_proc;
	} else {
		mutex_enter(&proc_lock);
		p = proc_find(pid);
		if (p == NULL) {
			mutex_exit(&proc_lock);
			return ESRCH;
		}
	}
	error = rw_tryenter(&p->p_reflock, RW_READER) ? 0 : EBUSY;
	if (pid != PROC_CURPROC) {
		mutex_exit(&proc_lock);
	}
	*p2 = p;
	return error;
}

/*
 * sysctl_proc_paxflags: helper routine to get process's paxctl flags
 */
static int
sysctl_proc_paxflags(SYSCTLFN_ARGS)
{
	struct proc *p;
	struct sysctlnode node;
	int paxflags;
	int error;

	/* First, validate the request. */
	if (namelen != 0 || name[-1] != PROC_PID_PAXFLAGS)
		return EINVAL;

	/* Find the process.  Hold a reference (p_reflock), if found. */
	error = sysctl_proc_findproc(l, (pid_t)name[-2], &p);
	if (error)
		return error;

	/* XXX-elad */
	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_CANSEE, p,
	    KAUTH_ARG(KAUTH_REQ_PROCESS_CANSEE_ENTRY), NULL, NULL);
	if (error) {
		rw_exit(&p->p_reflock);
		return error;
	}

	/* Retrieve the limits. */
	node = *rnode;
	paxflags = p->p_pax;
	node.sysctl_data = &paxflags;

	error = sysctl_lookup(SYSCTLFN_CALL(&node));

	/* If attempting to write new value, it's an error */
	if (error == 0 && newp != NULL)
		error = EACCES;

	rw_exit(&p->p_reflock);
	return error;
}

/*
 * sysctl_proc_corename: helper routine to get or set the core file name
 * for a process specified by PID.
 */
static int
sysctl_proc_corename(SYSCTLFN_ARGS)
{
	struct proc *p;
	struct plimit *lim;
	char *cnbuf, *cname;
	struct sysctlnode node;
	size_t len;
	int error;

	/* First, validate the request. */
	if (namelen != 0 || name[-1] != PROC_PID_CORENAME)
		return EINVAL;

	/* Find the process.  Hold a reference (p_reflock), if found. */
	error = sysctl_proc_findproc(l, (pid_t)name[-2], &p);
	if (error)
		return error;

	/* XXX-elad */
	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_CANSEE, p,
	    KAUTH_ARG(KAUTH_REQ_PROCESS_CANSEE_ENTRY), NULL, NULL);
	if (error) {
		rw_exit(&p->p_reflock);
		return error;
	}

	cnbuf = PNBUF_GET();

	if (oldp) {
		/* Get case: copy the core name into the buffer. */
		error = kauth_authorize_process(l->l_cred,
		    KAUTH_PROCESS_CORENAME, p,
		    KAUTH_ARG(KAUTH_REQ_PROCESS_CORENAME_GET), NULL, NULL);
		if (error) {
			goto done;
		}
		lim = p->p_limit;
		mutex_enter(&lim->pl_lock);
		strlcpy(cnbuf, lim->pl_corename, MAXPATHLEN);
		mutex_exit(&lim->pl_lock);
	}

	node = *rnode;
	node.sysctl_data = cnbuf;
	error = sysctl_lookup(SYSCTLFN_CALL(&node));

	/* Return if error, or if caller is only getting the core name. */
	if (error || newp == NULL) {
		goto done;
	}

	/*
	 * Set case.  Check permission and then validate new core name.
	 * It must be either "core", "/core", or end in ".core".
	 */
	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_CORENAME,
	    p, KAUTH_ARG(KAUTH_REQ_PROCESS_CORENAME_SET), cnbuf, NULL);
	if (error) {
		goto done;
	}
	len = strlen(cnbuf);
	if ((len < 4 || strcmp(cnbuf + len - 4, "core") != 0) ||
	    (len > 4 && cnbuf[len - 5] != '/' && cnbuf[len - 5] != '.')) {
		error = EINVAL;
		goto done;
	}

	/* Allocate, copy and set the new core name for plimit structure. */
	cname = kmem_alloc(++len, KM_NOSLEEP);
	if (cname == NULL) {
		error = ENOMEM;
		goto done;
	}
	memcpy(cname, cnbuf, len);
	lim_setcorename(p, cname, len);
done:
	rw_exit(&p->p_reflock);
	PNBUF_PUT(cnbuf);
	return error;
}

/*
 * sysctl_proc_stop: helper routine for checking/setting the stop flags.
 */
static int
sysctl_proc_stop(SYSCTLFN_ARGS)
{
	struct proc *p;
	int isset, flag, error = 0;
	struct sysctlnode node;

	if (namelen != 0)
		return EINVAL;

	/* Find the process.  Hold a reference (p_reflock), if found. */
	error = sysctl_proc_findproc(l, (pid_t)name[-2], &p);
	if (error)
		return error;

	/* XXX-elad */
	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_CANSEE, p,
	    KAUTH_ARG(KAUTH_REQ_PROCESS_CANSEE_ENTRY), NULL, NULL);
	if (error) {
		goto out;
	}

	/* Determine the flag. */
	switch (rnode->sysctl_num) {
	case PROC_PID_STOPFORK:
		flag = PS_STOPFORK;
		break;
	case PROC_PID_STOPEXEC:
		flag = PS_STOPEXEC;
		break;
	case PROC_PID_STOPEXIT:
		flag = PS_STOPEXIT;
		break;
	default:
		error = EINVAL;
		goto out;
	}
	isset = (p->p_flag & flag) ? 1 : 0;
	node = *rnode;
	node.sysctl_data = &isset;
	error = sysctl_lookup(SYSCTLFN_CALL(&node));

	/* Return if error, or if callers is only getting the flag. */
	if (error || newp == NULL) {
		goto out;
	}

	/* Check if caller can set the flags. */
	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_STOPFLAG,
	    p, KAUTH_ARG(flag), NULL, NULL);
	if (error) {
		goto out;
	}
	mutex_enter(p->p_lock);
	if (isset) {
		p->p_sflag |= flag;
	} else {
		p->p_sflag &= ~flag;
	}
	mutex_exit(p->p_lock);
out:
	rw_exit(&p->p_reflock);
	return error;
}

/*
 * sysctl_proc_plimit: helper routine to get/set rlimits of a process.
 */
static int
sysctl_proc_plimit(SYSCTLFN_ARGS)
{
	struct proc *p;
	u_int limitno;
	int which, error = 0;
        struct rlimit alim;
	struct sysctlnode node;

	if (namelen != 0)
		return EINVAL;

	which = name[-1];
	if (which != PROC_PID_LIMIT_TYPE_SOFT &&
	    which != PROC_PID_LIMIT_TYPE_HARD)
		return EINVAL;

	limitno = name[-2] - 1;
	if (limitno >= RLIM_NLIMITS)
		return EINVAL;

	if (name[-3] != PROC_PID_LIMIT)
		return EINVAL;

	/* Find the process.  Hold a reference (p_reflock), if found. */
	error = sysctl_proc_findproc(l, (pid_t)name[-4], &p);
	if (error)
		return error;

	/* XXX-elad */
	error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_CANSEE, p,
	    KAUTH_ARG(KAUTH_REQ_PROCESS_CANSEE_ENTRY), NULL, NULL);
	if (error)
		goto out;

	/* Check if caller can retrieve the limits. */
	if (newp == NULL) {
		error = kauth_authorize_process(l->l_cred, KAUTH_PROCESS_RLIMIT,
		    p, KAUTH_ARG(KAUTH_REQ_PROCESS_RLIMIT_GET), &alim,
		    KAUTH_ARG(which));
		if (error)
			goto out;
	}

	/* Retrieve the limits. */
	node = *rnode;
	memcpy(&alim, &p->p_rlimit[limitno], sizeof(alim));
	if (which == PROC_PID_LIMIT_TYPE_HARD) {
		node.sysctl_data = &alim.rlim_max;
	} else {
		node.sysctl_data = &alim.rlim_cur;
	}
	error = sysctl_lookup(SYSCTLFN_CALL(&node));

	/* Return if error, or if we are only retrieving the limits. */
	if (error || newp == NULL) {
		goto out;
	}
	error = dosetrlimit(l, p, limitno, &alim);
out:
	rw_exit(&p->p_reflock);
	return error;
}

/*
 * Setup sysctl nodes.
 */
static void
sysctl_proc_setup(void)
{

	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT|CTLFLAG_ANYNUMBER,
		       CTLTYPE_NODE, "curproc",
		       SYSCTL_DESCR("Per-process settings"),
		       NULL, 0, NULL, 0,
		       CTL_PROC, PROC_CURPROC, CTL_EOL);

	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT|CTLFLAG_READONLY,
		       CTLTYPE_INT, "paxflags",
		       SYSCTL_DESCR("Process PAX control flags"),
		       sysctl_proc_paxflags, 0, NULL, 0,
		       CTL_PROC, PROC_CURPROC, PROC_PID_PAXFLAGS, CTL_EOL);

	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT|CTLFLAG_READWRITE|CTLFLAG_ANYWRITE,
		       CTLTYPE_STRING, "corename",
		       SYSCTL_DESCR("Core file name"),
		       sysctl_proc_corename, 0, NULL, MAXPATHLEN,
		       CTL_PROC, PROC_CURPROC, PROC_PID_CORENAME, CTL_EOL);
	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT,
		       CTLTYPE_NODE, "rlimit",
		       SYSCTL_DESCR("Process limits"),
		       NULL, 0, NULL, 0,
		       CTL_PROC, PROC_CURPROC, PROC_PID_LIMIT, CTL_EOL);

#define create_proc_plimit(s, n) do {					\
	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,			\
		       CTLFLAG_PERMANENT,				\
		       CTLTYPE_NODE, s,					\
		       SYSCTL_DESCR("Process " s " limits"),		\
		       NULL, 0, NULL, 0,				\
		       CTL_PROC, PROC_CURPROC, PROC_PID_LIMIT, n,	\
		       CTL_EOL);					\
	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,			\
		       CTLFLAG_PERMANENT|CTLFLAG_READWRITE|CTLFLAG_ANYWRITE, \
		       CTLTYPE_QUAD, "soft",				\
		       SYSCTL_DESCR("Process soft " s " limit"),	\
		       sysctl_proc_plimit, 0, NULL, 0,			\
		       CTL_PROC, PROC_CURPROC, PROC_PID_LIMIT, n,	\
		       PROC_PID_LIMIT_TYPE_SOFT, CTL_EOL);		\
	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,			\
		       CTLFLAG_PERMANENT|CTLFLAG_READWRITE|CTLFLAG_ANYWRITE, \
		       CTLTYPE_QUAD, "hard",				\
		       SYSCTL_DESCR("Process hard " s " limit"),	\
		       sysctl_proc_plimit, 0, NULL, 0,			\
		       CTL_PROC, PROC_CURPROC, PROC_PID_LIMIT, n,	\
		       PROC_PID_LIMIT_TYPE_HARD, CTL_EOL);		\
	} while (0/*CONSTCOND*/)

	create_proc_plimit("cputime",		PROC_PID_LIMIT_CPU);
	create_proc_plimit("filesize",		PROC_PID_LIMIT_FSIZE);
	create_proc_plimit("datasize",		PROC_PID_LIMIT_DATA);
	create_proc_plimit("stacksize",		PROC_PID_LIMIT_STACK);
	create_proc_plimit("coredumpsize",	PROC_PID_LIMIT_CORE);
	create_proc_plimit("memoryuse",		PROC_PID_LIMIT_RSS);
	create_proc_plimit("memorylocked",	PROC_PID_LIMIT_MEMLOCK);
	create_proc_plimit("maxproc",		PROC_PID_LIMIT_NPROC);
	create_proc_plimit("descriptors",	PROC_PID_LIMIT_NOFILE);
	create_proc_plimit("sbsize",		PROC_PID_LIMIT_SBSIZE);
	create_proc_plimit("vmemoryuse",	PROC_PID_LIMIT_AS);
	create_proc_plimit("maxlwp",		PROC_PID_LIMIT_NTHR);

#undef create_proc_plimit

	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT|CTLFLAG_READWRITE|CTLFLAG_ANYWRITE,
		       CTLTYPE_INT, "stopfork",
		       SYSCTL_DESCR("Stop process at fork(2)"),
		       sysctl_proc_stop, 0, NULL, 0,
		       CTL_PROC, PROC_CURPROC, PROC_PID_STOPFORK, CTL_EOL);
	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT|CTLFLAG_READWRITE|CTLFLAG_ANYWRITE,
		       CTLTYPE_INT, "stopexec",
		       SYSCTL_DESCR("Stop process at execve(2)"),
		       sysctl_proc_stop, 0, NULL, 0,
		       CTL_PROC, PROC_CURPROC, PROC_PID_STOPEXEC, CTL_EOL);
	sysctl_createv(&proc_sysctllog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT|CTLFLAG_READWRITE|CTLFLAG_ANYWRITE,
		       CTLTYPE_INT, "stopexit",
		       SYSCTL_DESCR("Stop process before completing exit"),
		       sysctl_proc_stop, 0, NULL, 0,
		       CTL_PROC, PROC_CURPROC, PROC_PID_STOPEXIT, CTL_EOL);
}