-
Notifications
You must be signed in to change notification settings - Fork 2.9k
/
Copy pathkern_time.c
1835 lines (1657 loc) · 42.8 KB
/
kern_time.c
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
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* 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_time.c 8.1 (Berkeley) 6/10/93
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ktrace.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/limits.h>
#include <sys/clock.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/sysproto.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/kernel.h>
#include <sys/sleepqueue.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/posix4.h>
#include <sys/time.h>
#include <sys/timers.h>
#include <sys/timetc.h>
#include <sys/vnode.h>
#ifdef KTRACE
#include <sys/ktrace.h>
#endif
#include <vm/vm.h>
#include <vm/vm_extern.h>
#define MAX_CLOCKS (CLOCK_MONOTONIC+1)
#define CPUCLOCK_BIT 0x80000000
#define CPUCLOCK_PROCESS_BIT 0x40000000
#define CPUCLOCK_ID_MASK (~(CPUCLOCK_BIT|CPUCLOCK_PROCESS_BIT))
#define MAKE_THREAD_CPUCLOCK(tid) (CPUCLOCK_BIT|(tid))
#define MAKE_PROCESS_CPUCLOCK(pid) \
(CPUCLOCK_BIT|CPUCLOCK_PROCESS_BIT|(pid))
#define NS_PER_SEC 1000000000
static struct kclock posix_clocks[MAX_CLOCKS];
static uma_zone_t itimer_zone = NULL;
/*
* Time of day and interval timer support.
*
* These routines provide the kernel entry points to get and set
* the time-of-day and per-process interval timers. Subroutines
* here provide support for adding and subtracting timeval structures
* and decrementing interval timers, optionally reloading the interval
* timers when they expire.
*/
static int settime(struct thread *, struct timeval *);
static void timevalfix(struct timeval *);
static int user_clock_nanosleep(struct thread *td, clockid_t clock_id,
int flags, const struct timespec *ua_rqtp,
struct timespec *ua_rmtp);
static void itimer_start(void);
static int itimer_init(void *, int, int);
static void itimer_fini(void *, int);
static void itimer_enter(struct itimer *);
static void itimer_leave(struct itimer *);
static struct itimer *itimer_find(struct proc *, int);
static void itimers_alloc(struct proc *);
static int realtimer_create(struct itimer *);
static int realtimer_gettime(struct itimer *, struct itimerspec *);
static int realtimer_settime(struct itimer *, int,
struct itimerspec *, struct itimerspec *);
static int realtimer_delete(struct itimer *);
static void realtimer_clocktime(clockid_t, struct timespec *);
static void realtimer_expire(void *);
static void realtimer_expire_l(struct itimer *it, bool proc_locked);
static void realitexpire(void *arg);
static int register_posix_clock(int, const struct kclock *);
static void itimer_fire(struct itimer *it);
static int itimespecfix(struct timespec *ts);
#define CLOCK_CALL(clock, call, arglist) \
((*posix_clocks[clock].call) arglist)
SYSINIT(posix_timer, SI_SUB_P1003_1B, SI_ORDER_FIRST+4, itimer_start, NULL);
static int
settime(struct thread *td, struct timeval *tv)
{
struct timeval delta, tv1, tv2;
static struct timeval maxtime, laststep;
struct timespec ts;
microtime(&tv1);
delta = *tv;
timevalsub(&delta, &tv1);
/*
* If the system is secure, we do not allow the time to be
* set to a value earlier than 1 second less than the highest
* time we have yet seen. The worst a miscreant can do in
* this circumstance is "freeze" time. He couldn't go
* back to the past.
*
* We similarly do not allow the clock to be stepped more
* than one second, nor more than once per second. This allows
* a miscreant to make the clock march double-time, but no worse.
*/
if (securelevel_gt(td->td_ucred, 1) != 0) {
if (delta.tv_sec < 0 || delta.tv_usec < 0) {
/*
* Update maxtime to latest time we've seen.
*/
if (tv1.tv_sec > maxtime.tv_sec)
maxtime = tv1;
tv2 = *tv;
timevalsub(&tv2, &maxtime);
if (tv2.tv_sec < -1) {
tv->tv_sec = maxtime.tv_sec - 1;
printf("Time adjustment clamped to -1 second\n");
}
} else {
if (tv1.tv_sec == laststep.tv_sec)
return (EPERM);
if (delta.tv_sec > 1) {
tv->tv_sec = tv1.tv_sec + 1;
printf("Time adjustment clamped to +1 second\n");
}
laststep = *tv;
}
}
ts.tv_sec = tv->tv_sec;
ts.tv_nsec = tv->tv_usec * 1000;
tc_setclock(&ts);
resettodr();
return (0);
}
#ifndef _SYS_SYSPROTO_H_
struct clock_getcpuclockid2_args {
id_t id;
int which,
clockid_t *clock_id;
};
#endif
/* ARGSUSED */
int
sys_clock_getcpuclockid2(struct thread *td, struct clock_getcpuclockid2_args *uap)
{
clockid_t clk_id;
int error;
error = kern_clock_getcpuclockid2(td, uap->id, uap->which, &clk_id);
if (error == 0)
error = copyout(&clk_id, uap->clock_id, sizeof(clockid_t));
return (error);
}
int
kern_clock_getcpuclockid2(struct thread *td, id_t id, int which,
clockid_t *clk_id)
{
struct proc *p;
pid_t pid;
lwpid_t tid;
int error;
switch (which) {
case CPUCLOCK_WHICH_PID:
if (id != 0) {
error = pget(id, PGET_CANSEE | PGET_NOTID, &p);
if (error != 0)
return (error);
PROC_UNLOCK(p);
pid = id;
} else {
pid = td->td_proc->p_pid;
}
*clk_id = MAKE_PROCESS_CPUCLOCK(pid);
return (0);
case CPUCLOCK_WHICH_TID:
tid = id == 0 ? td->td_tid : id;
*clk_id = MAKE_THREAD_CPUCLOCK(tid);
return (0);
default:
return (EINVAL);
}
}
#ifndef _SYS_SYSPROTO_H_
struct clock_gettime_args {
clockid_t clock_id;
struct timespec *tp;
};
#endif
/* ARGSUSED */
int
sys_clock_gettime(struct thread *td, struct clock_gettime_args *uap)
{
struct timespec ats;
int error;
error = kern_clock_gettime(td, uap->clock_id, &ats);
if (error == 0)
error = copyout(&ats, uap->tp, sizeof(ats));
return (error);
}
static inline void
cputick2timespec(uint64_t runtime, struct timespec *ats)
{
uint64_t tr;
tr = cpu_tickrate();
ats->tv_sec = runtime / tr;
ats->tv_nsec = ((runtime % tr) * 1000000000ULL) / tr;
}
void
kern_thread_cputime(struct thread *targettd, struct timespec *ats)
{
uint64_t runtime, curtime, switchtime;
if (targettd == NULL) { /* current thread */
spinlock_enter();
switchtime = PCPU_GET(switchtime);
curtime = cpu_ticks();
runtime = curthread->td_runtime;
spinlock_exit();
runtime += curtime - switchtime;
} else {
PROC_LOCK_ASSERT(targettd->td_proc, MA_OWNED);
thread_lock(targettd);
runtime = targettd->td_runtime;
thread_unlock(targettd);
}
cputick2timespec(runtime, ats);
}
void
kern_process_cputime(struct proc *targetp, struct timespec *ats)
{
uint64_t runtime;
struct rusage ru;
PROC_LOCK_ASSERT(targetp, MA_OWNED);
PROC_STATLOCK(targetp);
rufetch(targetp, &ru);
runtime = targetp->p_rux.rux_runtime;
if (curthread->td_proc == targetp)
runtime += cpu_ticks() - PCPU_GET(switchtime);
PROC_STATUNLOCK(targetp);
cputick2timespec(runtime, ats);
}
static int
get_cputime(struct thread *td, clockid_t clock_id, struct timespec *ats)
{
struct proc *p, *p2;
struct thread *td2;
lwpid_t tid;
pid_t pid;
int error;
p = td->td_proc;
if ((clock_id & CPUCLOCK_PROCESS_BIT) == 0) {
tid = clock_id & CPUCLOCK_ID_MASK;
td2 = tdfind(tid, p->p_pid);
if (td2 == NULL)
return (EINVAL);
kern_thread_cputime(td2, ats);
PROC_UNLOCK(td2->td_proc);
} else {
pid = clock_id & CPUCLOCK_ID_MASK;
error = pget(pid, PGET_CANSEE, &p2);
if (error != 0)
return (EINVAL);
kern_process_cputime(p2, ats);
PROC_UNLOCK(p2);
}
return (0);
}
int
kern_clock_gettime(struct thread *td, clockid_t clock_id, struct timespec *ats)
{
struct timeval sys, user;
struct proc *p;
p = td->td_proc;
switch (clock_id) {
case CLOCK_REALTIME: /* Default to precise. */
case CLOCK_REALTIME_PRECISE:
nanotime(ats);
break;
case CLOCK_REALTIME_FAST:
getnanotime(ats);
break;
case CLOCK_VIRTUAL:
PROC_LOCK(p);
PROC_STATLOCK(p);
calcru(p, &user, &sys);
PROC_STATUNLOCK(p);
PROC_UNLOCK(p);
TIMEVAL_TO_TIMESPEC(&user, ats);
break;
case CLOCK_PROF:
PROC_LOCK(p);
PROC_STATLOCK(p);
calcru(p, &user, &sys);
PROC_STATUNLOCK(p);
PROC_UNLOCK(p);
timevaladd(&user, &sys);
TIMEVAL_TO_TIMESPEC(&user, ats);
break;
case CLOCK_MONOTONIC: /* Default to precise. */
case CLOCK_MONOTONIC_PRECISE:
case CLOCK_UPTIME:
case CLOCK_UPTIME_PRECISE:
nanouptime(ats);
break;
case CLOCK_UPTIME_FAST:
case CLOCK_MONOTONIC_FAST:
getnanouptime(ats);
break;
case CLOCK_SECOND:
ats->tv_sec = time_second;
ats->tv_nsec = 0;
break;
case CLOCK_THREAD_CPUTIME_ID:
kern_thread_cputime(NULL, ats);
break;
case CLOCK_PROCESS_CPUTIME_ID:
PROC_LOCK(p);
kern_process_cputime(p, ats);
PROC_UNLOCK(p);
break;
default:
if ((int)clock_id >= 0)
return (EINVAL);
return (get_cputime(td, clock_id, ats));
}
return (0);
}
#ifndef _SYS_SYSPROTO_H_
struct clock_settime_args {
clockid_t clock_id;
const struct timespec *tp;
};
#endif
/* ARGSUSED */
int
sys_clock_settime(struct thread *td, struct clock_settime_args *uap)
{
struct timespec ats;
int error;
if ((error = copyin(uap->tp, &ats, sizeof(ats))) != 0)
return (error);
return (kern_clock_settime(td, uap->clock_id, &ats));
}
static int allow_insane_settime = 0;
SYSCTL_INT(_debug, OID_AUTO, allow_insane_settime, CTLFLAG_RWTUN,
&allow_insane_settime, 0,
"do not perform possibly restrictive checks on settime(2) args");
int
kern_clock_settime(struct thread *td, clockid_t clock_id, struct timespec *ats)
{
struct timeval atv;
int error;
if ((error = priv_check(td, PRIV_CLOCK_SETTIME)) != 0)
return (error);
if (clock_id != CLOCK_REALTIME)
return (EINVAL);
if (!timespecvalid_interval(ats))
return (EINVAL);
if (!allow_insane_settime &&
(ats->tv_sec > 8000ULL * 365 * 24 * 60 * 60 ||
ats->tv_sec < utc_offset()))
return (EINVAL);
/* XXX Don't convert nsec->usec and back */
TIMESPEC_TO_TIMEVAL(&atv, ats);
error = settime(td, &atv);
return (error);
}
#ifndef _SYS_SYSPROTO_H_
struct clock_getres_args {
clockid_t clock_id;
struct timespec *tp;
};
#endif
int
sys_clock_getres(struct thread *td, struct clock_getres_args *uap)
{
struct timespec ts;
int error;
if (uap->tp == NULL)
return (0);
error = kern_clock_getres(td, uap->clock_id, &ts);
if (error == 0)
error = copyout(&ts, uap->tp, sizeof(ts));
return (error);
}
int
kern_clock_getres(struct thread *td, clockid_t clock_id, struct timespec *ts)
{
ts->tv_sec = 0;
switch (clock_id) {
case CLOCK_REALTIME:
case CLOCK_REALTIME_FAST:
case CLOCK_REALTIME_PRECISE:
case CLOCK_MONOTONIC:
case CLOCK_MONOTONIC_FAST:
case CLOCK_MONOTONIC_PRECISE:
case CLOCK_UPTIME:
case CLOCK_UPTIME_FAST:
case CLOCK_UPTIME_PRECISE:
/*
* Round up the result of the division cheaply by adding 1.
* Rounding up is especially important if rounding down
* would give 0. Perfect rounding is unimportant.
*/
ts->tv_nsec = NS_PER_SEC / tc_getfrequency() + 1;
break;
case CLOCK_VIRTUAL:
case CLOCK_PROF:
/* Accurately round up here because we can do so cheaply. */
ts->tv_nsec = howmany(NS_PER_SEC, hz);
break;
case CLOCK_SECOND:
ts->tv_sec = 1;
ts->tv_nsec = 0;
break;
case CLOCK_THREAD_CPUTIME_ID:
case CLOCK_PROCESS_CPUTIME_ID:
cputime:
ts->tv_nsec = 1000000000 / cpu_tickrate() + 1;
break;
default:
if ((int)clock_id < 0)
goto cputime;
return (EINVAL);
}
return (0);
}
int
kern_nanosleep(struct thread *td, struct timespec *rqt, struct timespec *rmt)
{
return (kern_clock_nanosleep(td, CLOCK_REALTIME, TIMER_RELTIME, rqt,
rmt));
}
static uint8_t nanowait[MAXCPU];
int
kern_clock_nanosleep(struct thread *td, clockid_t clock_id, int flags,
const struct timespec *rqt, struct timespec *rmt)
{
struct timespec ts, now;
sbintime_t sbt, sbtt, prec, tmp;
time_t over;
int error;
bool is_abs_real;
if (rqt->tv_nsec < 0 || rqt->tv_nsec >= NS_PER_SEC)
return (EINVAL);
if ((flags & ~TIMER_ABSTIME) != 0)
return (EINVAL);
switch (clock_id) {
case CLOCK_REALTIME:
case CLOCK_REALTIME_PRECISE:
case CLOCK_REALTIME_FAST:
case CLOCK_SECOND:
is_abs_real = (flags & TIMER_ABSTIME) != 0;
break;
case CLOCK_MONOTONIC:
case CLOCK_MONOTONIC_PRECISE:
case CLOCK_MONOTONIC_FAST:
case CLOCK_UPTIME:
case CLOCK_UPTIME_PRECISE:
case CLOCK_UPTIME_FAST:
is_abs_real = false;
break;
case CLOCK_VIRTUAL:
case CLOCK_PROF:
case CLOCK_PROCESS_CPUTIME_ID:
return (ENOTSUP);
case CLOCK_THREAD_CPUTIME_ID:
default:
return (EINVAL);
}
do {
ts = *rqt;
if ((flags & TIMER_ABSTIME) != 0) {
if (is_abs_real)
td->td_rtcgen =
atomic_load_acq_int(&rtc_generation);
error = kern_clock_gettime(td, clock_id, &now);
KASSERT(error == 0, ("kern_clock_gettime: %d", error));
timespecsub(&ts, &now, &ts);
}
if (ts.tv_sec < 0 || (ts.tv_sec == 0 && ts.tv_nsec == 0)) {
error = EWOULDBLOCK;
break;
}
if (ts.tv_sec > INT32_MAX / 2) {
over = ts.tv_sec - INT32_MAX / 2;
ts.tv_sec -= over;
} else
over = 0;
tmp = tstosbt(ts);
prec = tmp;
prec >>= tc_precexp;
if (TIMESEL(&sbt, tmp))
sbt += tc_tick_sbt;
sbt += tmp;
error = tsleep_sbt(&nanowait[curcpu], PWAIT | PCATCH, "nanslp",
sbt, prec, C_ABSOLUTE);
} while (error == 0 && is_abs_real && td->td_rtcgen == 0);
td->td_rtcgen = 0;
if (error != EWOULDBLOCK) {
if (TIMESEL(&sbtt, tmp))
sbtt += tc_tick_sbt;
if (sbtt >= sbt)
return (0);
if (error == ERESTART)
error = EINTR;
if ((flags & TIMER_ABSTIME) == 0 && rmt != NULL) {
ts = sbttots(sbt - sbtt);
ts.tv_sec += over;
if (ts.tv_sec < 0)
timespecclear(&ts);
*rmt = ts;
}
return (error);
}
return (0);
}
#ifndef _SYS_SYSPROTO_H_
struct nanosleep_args {
struct timespec *rqtp;
struct timespec *rmtp;
};
#endif
/* ARGSUSED */
int
sys_nanosleep(struct thread *td, struct nanosleep_args *uap)
{
return (user_clock_nanosleep(td, CLOCK_REALTIME, TIMER_RELTIME,
uap->rqtp, uap->rmtp));
}
#ifndef _SYS_SYSPROTO_H_
struct clock_nanosleep_args {
clockid_t clock_id;
int flags;
struct timespec *rqtp;
struct timespec *rmtp;
};
#endif
/* ARGSUSED */
int
sys_clock_nanosleep(struct thread *td, struct clock_nanosleep_args *uap)
{
int error;
error = user_clock_nanosleep(td, uap->clock_id, uap->flags, uap->rqtp,
uap->rmtp);
return (kern_posix_error(td, error));
}
static int
user_clock_nanosleep(struct thread *td, clockid_t clock_id, int flags,
const struct timespec *ua_rqtp, struct timespec *ua_rmtp)
{
struct timespec rmt, rqt;
int error, error2;
error = copyin(ua_rqtp, &rqt, sizeof(rqt));
if (error)
return (error);
error = kern_clock_nanosleep(td, clock_id, flags, &rqt, &rmt);
if (error == EINTR && ua_rmtp != NULL && (flags & TIMER_ABSTIME) == 0) {
error2 = copyout(&rmt, ua_rmtp, sizeof(rmt));
if (error2 != 0)
error = error2;
}
return (error);
}
#ifndef _SYS_SYSPROTO_H_
struct gettimeofday_args {
struct timeval *tp;
struct timezone *tzp;
};
#endif
/* ARGSUSED */
int
sys_gettimeofday(struct thread *td, struct gettimeofday_args *uap)
{
struct timeval atv;
struct timezone rtz;
int error = 0;
if (uap->tp) {
microtime(&atv);
error = copyout(&atv, uap->tp, sizeof (atv));
}
if (error == 0 && uap->tzp != NULL) {
rtz.tz_minuteswest = 0;
rtz.tz_dsttime = 0;
error = copyout(&rtz, uap->tzp, sizeof (rtz));
}
return (error);
}
#ifndef _SYS_SYSPROTO_H_
struct settimeofday_args {
struct timeval *tv;
struct timezone *tzp;
};
#endif
/* ARGSUSED */
int
sys_settimeofday(struct thread *td, struct settimeofday_args *uap)
{
struct timeval atv, *tvp;
struct timezone atz, *tzp;
int error;
if (uap->tv) {
error = copyin(uap->tv, &atv, sizeof(atv));
if (error)
return (error);
tvp = &atv;
} else
tvp = NULL;
if (uap->tzp) {
error = copyin(uap->tzp, &atz, sizeof(atz));
if (error)
return (error);
tzp = &atz;
} else
tzp = NULL;
return (kern_settimeofday(td, tvp, tzp));
}
int
kern_settimeofday(struct thread *td, struct timeval *tv, struct timezone *tzp)
{
int error;
error = priv_check(td, PRIV_SETTIMEOFDAY);
if (error)
return (error);
/* Verify all parameters before changing time. */
if (tv) {
if (tv->tv_usec < 0 || tv->tv_usec >= 1000000 ||
tv->tv_sec < 0)
return (EINVAL);
error = settime(td, tv);
}
return (error);
}
/*
* Get value of an interval timer. The process virtual and profiling virtual
* time timers are kept in the p_stats area, since they can be swapped out.
* These are kept internally in the way they are specified externally: in
* time until they expire.
*
* The real time interval timer is kept in the process table slot for the
* process, and its value (it_value) is kept as an absolute time rather than
* as a delta, so that it is easy to keep periodic real-time signals from
* drifting.
*
* Virtual time timers are processed in the hardclock() routine of
* kern_clock.c. The real time timer is processed by a timeout routine,
* called from the softclock() routine. Since a callout may be delayed in
* real time due to interrupt processing in the system, it is possible for
* the real time timeout routine (realitexpire, given below), to be delayed
* in real time past when it is supposed to occur. It does not suffice,
* therefore, to reload the real timer .it_value from the real time timers
* .it_interval. Rather, we compute the next time in absolute time the timer
* should go off.
*/
#ifndef _SYS_SYSPROTO_H_
struct getitimer_args {
u_int which;
struct itimerval *itv;
};
#endif
int
sys_getitimer(struct thread *td, struct getitimer_args *uap)
{
struct itimerval aitv;
int error;
error = kern_getitimer(td, uap->which, &aitv);
if (error != 0)
return (error);
return (copyout(&aitv, uap->itv, sizeof (struct itimerval)));
}
int
kern_getitimer(struct thread *td, u_int which, struct itimerval *aitv)
{
struct proc *p = td->td_proc;
struct timeval ctv;
if (which > ITIMER_PROF)
return (EINVAL);
if (which == ITIMER_REAL) {
/*
* Convert from absolute to relative time in .it_value
* part of real time timer. If time for real time timer
* has passed return 0, else return difference between
* current time and time for the timer to go off.
*/
PROC_LOCK(p);
*aitv = p->p_realtimer;
PROC_UNLOCK(p);
if (timevalisset(&aitv->it_value)) {
microuptime(&ctv);
if (timevalcmp(&aitv->it_value, &ctv, <))
timevalclear(&aitv->it_value);
else
timevalsub(&aitv->it_value, &ctv);
}
} else {
PROC_ITIMLOCK(p);
*aitv = p->p_stats->p_timer[which];
PROC_ITIMUNLOCK(p);
}
#ifdef KTRACE
if (KTRPOINT(td, KTR_STRUCT))
ktritimerval(aitv);
#endif
return (0);
}
#ifndef _SYS_SYSPROTO_H_
struct setitimer_args {
u_int which;
struct itimerval *itv, *oitv;
};
#endif
int
sys_setitimer(struct thread *td, struct setitimer_args *uap)
{
struct itimerval aitv, oitv;
int error;
if (uap->itv == NULL) {
uap->itv = uap->oitv;
return (sys_getitimer(td, (struct getitimer_args *)uap));
}
if ((error = copyin(uap->itv, &aitv, sizeof(struct itimerval))))
return (error);
error = kern_setitimer(td, uap->which, &aitv, &oitv);
if (error != 0 || uap->oitv == NULL)
return (error);
return (copyout(&oitv, uap->oitv, sizeof(struct itimerval)));
}
int
kern_setitimer(struct thread *td, u_int which, struct itimerval *aitv,
struct itimerval *oitv)
{
struct proc *p = td->td_proc;
struct timeval ctv;
sbintime_t sbt, pr;
if (aitv == NULL)
return (kern_getitimer(td, which, oitv));
if (which > ITIMER_PROF)
return (EINVAL);
#ifdef KTRACE
if (KTRPOINT(td, KTR_STRUCT))
ktritimerval(aitv);
#endif
if (itimerfix(&aitv->it_value) ||
aitv->it_value.tv_sec > INT32_MAX / 2)
return (EINVAL);
if (!timevalisset(&aitv->it_value))
timevalclear(&aitv->it_interval);
else if (itimerfix(&aitv->it_interval) ||
aitv->it_interval.tv_sec > INT32_MAX / 2)
return (EINVAL);
if (which == ITIMER_REAL) {
PROC_LOCK(p);
if (timevalisset(&p->p_realtimer.it_value))
callout_stop(&p->p_itcallout);
microuptime(&ctv);
if (timevalisset(&aitv->it_value)) {
pr = tvtosbt(aitv->it_value) >> tc_precexp;
timevaladd(&aitv->it_value, &ctv);
sbt = tvtosbt(aitv->it_value);
callout_reset_sbt(&p->p_itcallout, sbt, pr,
realitexpire, p, C_ABSOLUTE);
}
*oitv = p->p_realtimer;
p->p_realtimer = *aitv;
PROC_UNLOCK(p);
if (timevalisset(&oitv->it_value)) {
if (timevalcmp(&oitv->it_value, &ctv, <))
timevalclear(&oitv->it_value);
else
timevalsub(&oitv->it_value, &ctv);
}
} else {
if (aitv->it_interval.tv_sec == 0 &&
aitv->it_interval.tv_usec != 0 &&
aitv->it_interval.tv_usec < tick)
aitv->it_interval.tv_usec = tick;
if (aitv->it_value.tv_sec == 0 &&
aitv->it_value.tv_usec != 0 &&
aitv->it_value.tv_usec < tick)
aitv->it_value.tv_usec = tick;
PROC_ITIMLOCK(p);
*oitv = p->p_stats->p_timer[which];
p->p_stats->p_timer[which] = *aitv;
PROC_ITIMUNLOCK(p);
}
#ifdef KTRACE
if (KTRPOINT(td, KTR_STRUCT))
ktritimerval(oitv);
#endif
return (0);
}
static void
realitexpire_reset_callout(struct proc *p, sbintime_t *isbtp)
{
sbintime_t prec;
prec = isbtp == NULL ? tvtosbt(p->p_realtimer.it_interval) : *isbtp;
callout_reset_sbt(&p->p_itcallout, tvtosbt(p->p_realtimer.it_value),
prec >> tc_precexp, realitexpire, p, C_ABSOLUTE);
}
void
itimer_proc_continue(struct proc *p)
{
struct timeval ctv;
struct itimer *it;
int id;
PROC_LOCK_ASSERT(p, MA_OWNED);
if ((p->p_flag2 & P2_ITSTOPPED) != 0) {
p->p_flag2 &= ~P2_ITSTOPPED;
microuptime(&ctv);
if (timevalcmp(&p->p_realtimer.it_value, &ctv, >=))
realitexpire(p);
else
realitexpire_reset_callout(p, NULL);
}
if (p->p_itimers != NULL) {
for (id = 3; id < TIMER_MAX; id++) {
it = p->p_itimers->its_timers[id];
if (it == NULL)
continue;
if ((it->it_flags & ITF_PSTOPPED) != 0) {
ITIMER_LOCK(it);
if ((it->it_flags & ITF_PSTOPPED) != 0) {
it->it_flags &= ~ITF_PSTOPPED;
if ((it->it_flags & ITF_DELETING) == 0)
realtimer_expire_l(it, true);
}
ITIMER_UNLOCK(it);
}
}
}
}
/*
* Real interval timer expired:
* send process whose timer expired an alarm signal.
* If time is not set up to reload, then just return.
* Else compute next time timer should go off which is > current time.
* This is where delay in processing this timeout causes multiple
* SIGALRM calls to be compressed into one.
* tvtohz() always adds 1 to allow for the time until the next clock
* interrupt being strictly less than 1 clock tick, but we don't want
* that here since we want to appear to be in sync with the clock
* interrupt even when we're delayed.
*/
static void
realitexpire(void *arg)
{
struct proc *p;
struct timeval ctv;
sbintime_t isbt;
p = (struct proc *)arg;
kern_psignal(p, SIGALRM);
if (!timevalisset(&p->p_realtimer.it_interval)) {
timevalclear(&p->p_realtimer.it_value);
return;
}
isbt = tvtosbt(p->p_realtimer.it_interval);
if (isbt >= sbt_timethreshold)
getmicrouptime(&ctv);
else
microuptime(&ctv);
do {
timevaladd(&p->p_realtimer.it_value,
&p->p_realtimer.it_interval);
} while (timevalcmp(&p->p_realtimer.it_value, &ctv, <=));
if (P_SHOULDSTOP(p) || P_KILLED(p)) {
p->p_flag2 |= P2_ITSTOPPED;
return;
}
p->p_flag2 &= ~P2_ITSTOPPED;
realitexpire_reset_callout(p, &isbt);
}
/*
* Check that a proposed value to load into the .it_value or
* .it_interval part of an interval timer is acceptable, and
* fix it to have at least minimal value (i.e. if it is less
* than the resolution of the clock, round it up.)
*/
int
itimerfix(struct timeval *tv)
{
if (tv->tv_sec < 0 || tv->tv_usec < 0 || tv->tv_usec >= 1000000)
return (EINVAL);
if (tv->tv_sec == 0 && tv->tv_usec != 0 &&
tv->tv_usec < (u_int)tick / 16)
tv->tv_usec = (u_int)tick / 16;
return (0);
}
/*
* Decrement an interval timer by a specified number
* of microseconds, which must be less than a second,
* i.e. < 1000000. If the timer expires, then reload
* it. In this case, carry over (usec - old value) to
* reduce the value reloaded into the timer so that
* the timer does not drift. This routine assumes