aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/posix-timers.c
blob: 6edbb2c55c22fd56a61eb6665e32087592a81fc3 (plain) (blame)
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
/*
 * linux/kernel/posix-timers.c
 *
 *
 * 2002-10-15  Posix Clocks & timers
 *                           by George Anzinger george@mvista.com
 *
 *			     Copyright (C) 2002 2003 by MontaVista Software.
 *
 * 2004-06-01  Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug.
 *			     Copyright (C) 2004 Boris Hu
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or (at
 * your option) any later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.

 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA
 */

/* These are all the functions necessary to implement
 * POSIX clocks & timers
 */
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/mutex.h>

#include <asm/uaccess.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/idr.h>
#include <linux/posix-clock.h>
#include <linux/posix-timers.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <linux/export.h>

/*
 * Management arrays for POSIX timers.	 Timers are kept in slab memory
 * Timer ids are allocated by an external routine that keeps track of the
 * id and the timer.  The external interface is:
 *
 * void *idr_find(struct idr *idp, int id);           to find timer_id <id>
 * int idr_get_new(struct idr *idp, void *ptr);       to get a new id and
 *                                                    related it to <ptr>
 * void idr_remove(struct idr *idp, int id);          to release <id>
 * void idr_init(struct idr *idp);                    to initialize <idp>
 *                                                    which we supply.
 * The idr_get_new *may* call slab for more memory so it must not be
 * called under a spin lock.  Likewise idr_remore may release memory
 * (but it may be ok to do this under a lock...).
 * idr_find is just a memory look up and is quite fast.  A -1 return
 * indicates that the requested id does not exist.
 */

/*
 * Lets keep our timers in a slab cache :-)
 */
static struct kmem_cache *posix_timers_cache;
static struct idr posix_timers_id;
static DEFINE_SPINLOCK(idr_lock);

/*
 * we assume that the new SIGEV_THREAD_ID shares no bits with the other
 * SIGEV values.  Here we put out an error if this assumption fails.
 */
#if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \
                       ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD))
#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
#endif

/*
 * parisc wants ENOTSUP instead of EOPNOTSUPP
 */
#ifndef ENOTSUP
# define ENANOSLEEP_NOTSUP EOPNOTSUPP
#else
# define ENANOSLEEP_NOTSUP ENOTSUP
#endif

/*
 * The timer ID is turned into a timer address by idr_find().
 * Verifying a valid ID consists of:
 *
 * a) checking that idr_find() returns other than -1.
 * b) checking that the timer id matches the one in the timer itself.
 * c) that the timer owner is in the callers thread group.
 */

/*
 * CLOCKs: The POSIX standard calls for a couple of clocks and allows us
 *	    to implement others.  This structure defines the various
 *	    clocks.
 *
 * RESOLUTION: Clock resolution is used to round up timer and interval
 *	    times, NOT to report clock times, which are reported with as
 *	    much resolution as the system can muster.  In some cases this
 *	    resolution may depend on the underlying clock hardware and
 *	    may not be quantifiable until run time, and only then is the
 *	    necessary code is written.	The standard says we should say
 *	    something about this issue in the documentation...
 *
 * FUNCTIONS: The CLOCKs structure defines possible functions to
 *	    handle various clock functions.
 *
 *	    The standard POSIX timer management code assumes the
 *	    following: 1.) The k_itimer struct (sched.h) is used for
 *	    the timer.  2.) The list, it_lock, it_clock, it_id and
 *	    it_pid fields are not modified by timer code.
 *
 * Permissions: It is assumed that the clock_settime() function defined
 *	    for each clock will take care of permission checks.	 Some
 *	    clocks may be set able by any user (i.e. local process
 *	    clocks) others not.	 Currently the only set able clock we
 *	    have is CLOCK_REALTIME and its high res counter part, both of
 *	    which we beg off on and pass to do_sys_settimeofday().
 */

static struct k_clock posix_clocks[MAX_CLOCKS];

/*
 * These ones are defined below.
 */
static int common_nsleep(const clockid_t, int flags, struct timespec *t,
			 struct timespec __user *rmtp);
static int common_timer_create(struct k_itimer *new_timer);
static void common_timer_get(struct k_itimer *, struct itimerspec *);
static int common_timer_set(struct k_itimer *, int,
			    struct itimerspec *, struct itimerspec *);
static int common_timer_del(struct k_itimer *timer);

static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);

static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);

#define lock_timer(tid, flags)						   \
({	struct k_itimer *__timr;					   \
	__cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags));  \
	__timr;								   \
})

static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
{
	spin_unlock_irqrestore(&timr->it_lock, flags);
}

/* Get clock_realtime */
static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
{
	ktime_get_real_ts(tp);
	return 0;
}

/* Set clock_realtime */
static int posix_clock_realtime_set(const clockid_t which_clock,
				    const struct timespec *tp)
{
	return do_sys_settimeofday(tp, NULL);
}

static int posix_clock_realtime_adj(const clockid_t which_clock,
				    struct timex *t)
{
	return do_adjtimex(t);
}

/*
 * Get monotonic time for posix timers
 */
static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
{
	ktime_get_ts(tp);
	return 0;
}

/*
 * Get monotonic-raw time for posix timers
 */
static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
{
	getrawmonotonic(tp);
	return 0;
}


static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp)
{
	*tp = current_kernel_time();
	return 0;
}

static int posix_get_monotonic_coarse(clockid_t which_clock,
						struct timespec *tp)
{
	*tp = get_monotonic_coarse();
	return 0;
}

static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
{
	*tp = ktime_to_timespec(KTIME_LOW_RES);
	return 0;
}

static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
{
	get_monotonic_boottime(tp);
	return 0;
}


/*
 * Initialize everything, well, just everything in Posix clocks/timers ;)
 */
static __init int init_posix_timers(void)
{
	struct k_clock clock_realtime = {
		.clock_getres	= hrtimer_get_res,
		.clock_get	= posix_clock_realtime_get,
		.clock_set	= posix_clock_realtime_set,
		.clock_adj	= posix_clock_realtime_adj,
		.nsleep		= common_nsleep,
		.nsleep_restart	= hrtimer_nanosleep_restart,
		.timer_create	= common_timer_create,
		.timer_set	= common_timer_set,
		.timer_get	= common_timer_get,
		.timer_del	= common_timer_del,
	};
	struct k_clock clock_monotonic = {
		.clock_getres	= hrtimer_get_res,
		.clock_get	= posix_ktime_get_ts,
		.nsleep		= common_nsleep,
		.nsleep_restart	= hrtimer_nanosleep_restart,
		.timer_create	= common_timer_create,
		.timer_set	= common_timer_set,
		.timer_get	= common_timer_get,
		.timer_del	= common_timer_del,
	};
	struct k_clock clock_monotonic_raw = {
		.clock_getres	= hrtimer_get_res,
		.clock_get	= posix_get_monotonic_raw,
	};
	struct k_clock clock_realtime_coarse = {
		.clock_getres	= posix_get_coarse_res,
		.clock_get	= posix_get_realtime_coarse,
	};
	struct k_clock clock_monotonic_coarse = {
		.clock_getres	= posix_get_coarse_res,
		.clock_get	= posix_get_monotonic_coarse,
	};
	struct k_clock clock_boottime = {
		.clock_getres	= hrtimer_get_res,
		.clock_get	= posix_get_boottime,
		.nsleep		= common_nsleep,
		.nsleep_restart	= hrtimer_nanosleep_restart,
		.timer_create	= common_timer_create,
		.timer_set	= common_timer_set,
		.timer_get	= common_timer_get,
		.timer_del	= common_timer_del,
	};

	posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
	posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
	posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);

	posix_timers_cache = kmem_cache_create("posix_timers_cache",
					sizeof (struct k_itimer), 0, SLAB_PANIC,
					NULL);
	idr_init(&posix_timers_id);
	return 0;
}

__initcall(init_posix_timers);

static void schedule_next_timer(struct k_itimer *timr)
{
	struct hrtimer *timer = &timr->it.real.timer;

	if (timr->it.real.interval.tv64 == 0)
		return;

	timr->it_overrun += (unsigned int) hrtimer_forward(timer,
						timer->base->get_time(),
						timr->it.real.interval);

	timr->it_overrun_last = timr->it_overrun;
	timr->it_overrun = -1;
	++timr->it_requeue_pending;
	hrtimer_restart(timer);
}

/*
 * This function is exported for use by the signal deliver code.  It is
 * called just prior to the info block being released and passes that
 * block to us.  It's function is to update the overrun entry AND to
 * restart the timer.  It should only be called if the timer is to be
 * restarted (i.e. we have flagged this in the sys_private entry of the
 * info block).
 *
 * To protect against the timer going away while the interrupt is queued,
 * we require that the it_requeue_pending flag be set.
 */
void do_schedule_next_timer(struct siginfo *info)
{
	struct k_itimer *timr;
	unsigned long flags;

	timr = lock_timer(info->si_tid, &flags);

	if (timr && timr->it_requeue_pending == info->si_sys_private) {
		if (timr->it_clock < 0)
			posix_cpu_timer_schedule(timr);
		else
			schedule_next_timer(timr);

		info->si_overrun += timr->it_overrun_last;
	}

	if (timr)
		unlock_timer(timr, flags);
}

int posix_timer_event(struct k_itimer *timr, int si_private)
{
	struct task_struct *task;
	int shared, ret = -1;
	/*
	 * FIXME: if ->sigq is queued we can race with
	 * dequeue_signal()->do_schedule_next_timer().
	 *
	 * If dequeue_signal() sees the "right" value of
	 * si_sys_private it calls do_schedule_next_timer().
	 * We re-queue ->sigq and drop ->it_lock().
	 * do_schedule_next_timer() locks the timer
	 * and re-schedules it while ->sigq is pending.
	 * Not really bad, but not that we want.
	 */
	timr->sigq->info.si_sys_private = si_private;

	rcu_read_lock();
	task = pid_task(timr->it_pid, PIDTYPE_PID);
	if (task) {
		shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
		ret = send_sigqueue(timr->sigq, task, shared);
	}
	rcu_read_unlock();
	/* If we failed to send the signal the timer stops. */
	return ret > 0;
}
EXPORT_SYMBOL_GPL(posix_timer_event);

/*
 * This function gets called when a POSIX.1b interval timer expires.  It
 * is used as a callback from the kernel internal timer.  The
 * run_timer_list code ALWAYS calls with interrupts on.

 * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers.
 */
static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
{
	struct k_itimer *timr;
	unsigned long flags;
	int si_private = 0;
	enum hrtimer_restart ret = HRTIMER_NORESTART;

	timr = container_of(timer, struct k_itimer, it.real.timer);
	spin_lock_irqsave(&timr->it_lock, flags);

	if (timr->it.real.interval.tv64 != 0)
		si_private = ++timr->it_requeue_pending;

	if (posix_timer_event(timr, si_private)) {
		/*
		 * signal was not sent because of sig_ignor
		 * we will not get a call back to restart it AND
		 * it should be restarted.
		 */
		if (timr->it.real.interval.tv64 != 0) {
			ktime_t now = hrtimer_cb_get_time(timer);

			/*
			 * FIXME: What we really want, is to stop this
			 * timer completely and restart it in case the
			 * SIG_IGN is removed. This is a non trivial
			 * change which involves sighand locking
			 * (sigh !), which we don't want to do late in
			 * the release cycle.
			 *
			 * For now we just let timers with an interval
			 * less than a jiffie expire every jiffie to
			 * avoid softirq starvation in case of SIG_IGN
			 * and a very small interval, which would put
			 * the timer right back on the softirq pending
			 * list. By moving now ahead of time we trick
			 * hrtimer_forward() to expire the timer
			 * later, while we still maintain the overrun
			 * accuracy, but have some inconsistency in
			 * the timer_gettime() case. This is at least
			 * better than a starved softirq. A more
			 * complex fix which solves also another related
			 * inconsistency is already in the pipeline.
			 */
#ifdef CONFIG_HIGH_RES_TIMERS
			{
				ktime_t kj = ktime_set(0, NSEC_PER_SEC / HZ);

				if (timr->it.real.interval.tv64 < kj.tv64)
					now = ktime_add(now, kj);
			}
#endif
			timr->it_overrun += (unsigned int)
				hrtimer_forward(timer, now,
						timr->it.real.interval);
			ret = HRTIMER_RESTART;
			++timr->it_requeue_pending;
		}
	}

	unlock_timer(timr, flags);
	return ret;
}

static struct pid *good_sigevent(sigevent_t * event)
{
	struct task_struct *rtn = current->group_leader;

	if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
		(!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
		 !same_thread_group(rtn, current) ||
		 (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
		return NULL;

	if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
	    ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
		return NULL;

	return task_pid(rtn);
}

void posix_timers_register_clock(const clockid_t clock_id,
				 struct k_clock *new_clock)
{
	if ((unsigned) clock_id >= MAX_CLOCKS) {
		printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
		       clock_id);
		return;
	}

	if (!new_clock->clock_get) {
		printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
		       clock_id);
		return;
	}
	if (!new_clock->clock_getres) {
		printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
		       clock_id);
		return;
	}

	posix_clocks[clock_id] = *new_clock;
}
EXPORT_SYMBOL_GPL(posix_timers_register_clock);

static struct k_itimer * alloc_posix_timer(void)
{
	struct k_itimer *tmr;
	tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);
	if (!tmr)
		return tmr;
	if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
		kmem_cache_free(posix_timers_cache, tmr);
		return NULL;
	}
	memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
	return tmr;
}

static void k_itimer_rcu_free(struct rcu_head *head)
{
	struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);

	kmem_cache_free(posix_timers_cache, tmr);
}

#define IT_ID_SET	1
#define IT_ID_NOT_SET	0
static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
{
	if (it_id_set) {
		unsigned long flags;
		spin_lock_irqsave(&idr_lock, flags);
		idr_remove(&posix_timers_id, tmr->it_id);
		spin_unlock_irqrestore(&idr_lock, flags);
	}
	put_pid(tmr->it_pid);
	sigqueue_free(tmr->sigq);
	call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
}

static struct k_clock *clockid_to_kclock(const clockid_t id)
{
	if (id < 0)
		return (id & CLOCKFD_MASK) == CLOCKFD ?
			&clock_posix_dynamic : &clock_posix_cpu;

	if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
		return NULL;
	return &posix_clocks[id];
}

static int common_timer_create(struct k_itimer *new_timer)
{
	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
	return 0;
}

/* Create a POSIX.1b interval timer. */

SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
		struct sigevent __user *, timer_event_spec,
		timer_t __user *, created_timer_id)
{
	struct k_clock *kc = clockid_to_kclock(which_clock);
	struct k_itimer *new_timer;
	int error, new_timer_id;
	sigevent_t event;
	int it_id_set = IT_ID_NOT_SET;

	if (!kc)
		return -EINVAL;
	if (!kc->timer_create)
		return -EOPNOTSUPP;

	new_timer = alloc_posix_timer();
	if (unlikely(!new_timer))
		return -EAGAIN;

	spin_lock_init(&new_timer->it_lock);

	idr_preload(GFP_KERNEL);
	spin_lock_irq(&idr_lock);
	error = idr_alloc(&posix_timers_id, new_timer, 0, 0, GFP_NOWAIT);
	spin_unlock_irq(&idr_lock);
	idr_preload_end();
	if (error < 0) {
		/*
		 * Weird looking, but we return EAGAIN if the IDR is
		 * full (proper POSIX return value for this)
		 */
		if (error == -ENOSPC)
			error = -EAGAIN;
		goto out;
	}
	new_timer_id = error;

	it_id_set = IT_ID_SET;
	new_timer->it_id = (timer_t) new_timer_id;
	new_timer->it_clock = which_clock;
	new_timer->it_overrun = -1;

	if (timer_event_spec) {
		if (copy_from_user(&event, timer_event_spec, sizeof (event))) {
			error = -EFAULT;
			goto out;
		}
		rcu_read_lock();
		new_timer->it_pid = get_pid(good_sigevent(&event));
		rcu_read_unlock();
		if (!new_timer->it_pid) {
			error = -EINVAL;
			goto out;
		}
	} else {
		event.sigev_notify = SIGEV_SIGNAL;
		event.sigev_signo = SIGALRM;
		event.sigev_value.sival_int = new_timer->it_id;
		new_timer->it_pid = get_pid(task_tgid(current));
	}

	new_timer->it_sigev_notify     = event.sigev_notify;
	new_timer->sigq->info.si_signo = event.sigev_signo;
	new_timer->sigq->info.si_value = event.sigev_value;
	new_timer->sigq->info.si_tid   = new_timer->it_id;
	new_timer->sigq->info.si_code  = SI_TIMER;

	if (copy_to_user(created_timer_id,
			 &new_timer_id, sizeof (new_timer_id))) {
		error = -EFAULT;
		goto out;
	}

	error = kc->timer_create(new_timer);
	if (error)
		goto out;

	spin_lock_irq(&current->sighand->siglock);
	new_timer->it_signal = current->signal;
	list_add(&new_timer->list, &current->signal->posix_timers);
	spin_unlock_irq(&current->sighand->siglock);

	return 0;
	/*
	 * In the case of the timer belonging to another task, after
	 * the task is unlocked, the timer is owned by the other task
	 * and may cease to exist at any time.  Don't use or modify
	 * new_timer after the unlock call.
	 */
out:
	release_posix_timer(new_timer, it_id_set);
	return error;
}

/*
 * Locking issues: We need to protect the result of the id look up until
 * we get the timer locked down so it is not deleted under us.  The
 * removal is done under the idr spinlock so we use that here to bridge
 * the find to the timer lock.  To avoid a dead lock, the timer id MUST
 * be release with out holding the timer lock.
 */
static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
{
	struct k_itimer *timr;

	/*
	 * timer_t could be any type >= int and we want to make sure any
	 * @timer_id outside positive int range fails lookup.
	 */
	if ((unsigned long long)timer_id > INT_MAX)
		return NULL;

	rcu_read_lock();
	timr = idr_find(&posix_timers_id, (int)timer_id);
	if (timr) {
		spin_lock_irqsave(&timr->it_lock, *flags);
		if (timr->it_signal == current->signal) {
			rcu_read_unlock();
			return timr;
		}
		spin_unlock_irqrestore(&timr->it_lock, *flags);
	}
	rcu_read_unlock();

	return NULL;
}

/*
 * Get the time remaining on a POSIX.1b interval timer.  This function
 * is ALWAYS called with spin_lock_irq on the timer, thus it must not
 * mess with irq.
 *
 * We have a couple of messes to clean up here.  First there is the case
 * of a timer that has a requeue pending.  These timers should appear to
 * be in the timer list with an expiry as if we were to requeue them
 * now.
 *
 * The second issue is the SIGEV_NONE timer which may be active but is
 * not really ever put in the timer list (to save system resources).
 * This timer may be expired, and if so, we will do it here.  Otherwise
 * it is the same as a requeue pending timer WRT to what we should
 * report.
 */
static void
common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
{
	ktime_t now, remaining, iv;
	struct hrtimer *timer = &timr->it.real.timer;

	memset(cur_setting, 0, sizeof(struct itimerspec));

	iv = timr->it.real.interval;

	/* interval timer ? */
	if (iv.tv64)
		cur_setting->it_interval = ktime_to_timespec(iv);
	else if (!hrtimer_active(timer) &&
		 (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
		return;

	now = timer->base->get_time();

	/*
	 * When a requeue is pending or this is a SIGEV_NONE
	 * timer move the expiry time forward by intervals, so
	 * expiry is > now.
	 */
	if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
	    (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
		timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);

	remaining = ktime_sub(hrtimer_get_expires(timer), now);
	/* Return 0 only, when the timer is expired and not pending */
	if (remaining.tv64 <= 0) {
		/*
		 * A single shot SIGEV_NONE timer must return 0, when
		 * it is expired !
		 */
		if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
			cur_setting->it_value.tv_nsec = 1;
	} else
		cur_setting->it_value = ktime_to_timespec(remaining);
}

/* Get the time remaining on a POSIX.1b interval timer. */
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
		struct itimerspec __user *, setting)
{
	struct itimerspec cur_setting;
	struct k_itimer *timr;
	struct k_clock *kc;
	unsigned long flags;
	int ret = 0;

	timr = lock_timer(timer_id, &flags);
	if (!timr)
		return -EINVAL;

	kc = clockid_to_kclock(timr->it_clock);
	if (WARN_ON_ONCE(!kc || !kc->timer_get))
		ret = -EINVAL;
	else
		kc->timer_get(timr, &cur_setting);

	unlock_timer(timr, flags);

	if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
		return -EFAULT;

	return ret;
}

/*
 * Get the number of overruns of a POSIX.1b interval timer.  This is to
 * be the overrun of the timer last delivered.  At the same time we are
 * accumulating overruns on the next timer.  The overrun is frozen when
 * the signal is delivered, either at the notify time (if the info block
 * is not queued) or at the actual delivery time (as we are informed by
 * the call back to do_schedule_next_timer().  So all we need to do is
 * to pick up the frozen overrun.
 */
SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
{
	struct k_itimer *timr;
	int overrun;
	unsigned long flags;

	timr = lock_timer(timer_id, &flags);
	if (!timr)
		return -EINVAL;

	overrun = timr->it_overrun_last;
	unlock_timer(timr, flags);

	return overrun;
}

/* Set a POSIX.1b interval timer. */
/* timr->it_lock is taken. */
static int
common_timer_set(struct k_itimer *timr, int flags,
		 struct itimerspec *new_setting, struct itimerspec *old_setting)
{
	struct hrtimer *timer = &timr->it.real.timer;
	enum hrtimer_mode mode;

	if (old_setting)
		common_timer_get(timr, old_setting);

	/* disable the timer */
	timr->it.real.interval.tv64 = 0;
	/*
	 * careful here.  If smp we could be in the "fire" routine which will
	 * be spinning as we hold the lock.  But this is ONLY an SMP issue.
	 */
	if (hrtimer_try_to_cancel(timer) < 0)
		return TIMER_RETRY;

	timr->it_requeue_pending = (timr->it_requeue_pending + 2) & 
		~REQUEUE_PENDING;
	timr->it_overrun_last = 0;

	/* switch off the timer when it_value is zero */
	if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
		return 0;

	mode = flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL;
	hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
	timr->it.real.timer.function = posix_timer_fn;

	hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value));

	/* Convert interval */
	timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);

	/* SIGEV_NONE timers are not queued ! See common_timer_get */
	if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
		/* Setup correct expiry time for relative timers */
		if (mode == HRTIMER_MODE_REL) {
			hrtimer_add_expires(timer, timer->base->get_time());
		}
		return 0;
	}

	hrtimer_start_expires(timer, mode);
	return 0;
}

/* Set a POSIX.1b interval timer */
SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
		const struct itimerspec __user *, new_setting,
		struct itimerspec __user *, old_setting)
{
	struct k_itimer *timr;
	struct itimerspec new_spec, old_spec;
	int error = 0;
	unsigned long flag;
	struct itimerspec *rtn = old_setting ? &old_spec : NULL;
	struct k_clock *kc;

	if (!new_setting)
		return -EINVAL;

	if (copy_from_user(&new_spec, new_setting, sizeof (new_spec)))
		return -EFAULT;

	if (!timespec_valid(&new_spec.it_interval) ||
	    !timespec_valid(&new_spec.it_value))
		return -EINVAL;
retry:
	timr = lock_timer(timer_id, &flag);
	if (!timr)
		return -EINVAL;

	kc = clockid_to_kclock(timr->it_clock);
	if (WARN_ON_ONCE(!kc || !kc->timer_set))
		error = -EINVAL;
	else
		error = kc->timer_set(timr, flags, &new_spec, rtn);

	unlock_timer(timr, flag);
	if (error == TIMER_RETRY) {
		rtn = NULL;	// We already got the old time...
		goto retry;
	}

	if (old_setting && !error &&
	    copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
		error = -EFAULT;

	return error;
}

static int common_timer_del(struct k_itimer *timer)
{
	timer->it.real.interval.tv64 = 0;

	if (hrtimer_try_to_cancel(&timer->it.real.timer) < 0)
		return TIMER_RETRY;
	return 0;
}

static inline int timer_delete_hook(struct k_itimer *timer)
{
	struct k_clock *kc = clockid_to_kclock(timer->it_clock);

	if (WARN_ON_ONCE(!kc || !kc->timer_del))
		return -EINVAL;
	return kc->timer_del(timer);
}

/* Delete a POSIX.1b interval timer. */
SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
{
	struct k_itimer *timer;
	unsigned long flags;

retry_delete:
	timer = lock_timer(timer_id, &flags);
	if (!timer)
		return -EINVAL;

	if (timer_delete_hook(timer) == TIMER_RETRY) {
		unlock_timer(timer, flags);
		goto retry_delete;
	}

	spin_lock(&current->sighand->siglock);
	list_del(&timer->list);
	spin_unlock(&current->sighand->siglock);
	/*
	 * This keeps any tasks waiting on the spin lock from thinking
	 * they got something (see the lock code above).
	 */
	timer->it_signal = NULL;

	unlock_timer(timer, flags);
	release_posix_timer(timer, IT_ID_SET);
	return 0;
}

/*
 * return timer owned by the process, used by exit_itimers
 */
static void itimer_delete(struct k_itimer *timer)
{
	unsigned long flags;

retry_delete:
	spin_lock_irqsave(&timer->it_lock, flags);

	if (timer_delete_hook(timer) == TIMER_RETRY) {
		unlock_timer(timer, flags);
		goto retry_delete;
	}
	list_del(&timer->list);
	/*
	 * This keeps any tasks waiting on the spin lock from thinking
	 * they got something (see the lock code above).
	 */
	timer->it_signal = NULL;

	unlock_timer(timer, flags);
	release_posix_timer(timer, IT_ID_SET);
}

/*
 * This is called by do_exit or de_thread, only when there are no more
 * references to the shared signal_struct.
 */
void exit_itimers(struct signal_struct *sig)
{
	struct k_itimer *tmr;

	while (!list_empty(&sig->posix_timers)) {
		tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
		itimer_delete(tmr);
	}
}

SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
		const struct timespec __user *, tp)
{
	struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec new_tp;

	if (!kc || !kc->clock_set)
		return -EINVAL;

	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
		return -EFAULT;

	return kc->clock_set(which_clock, &new_tp);
}

SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
		struct timespec __user *,tp)
{
	struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec kernel_tp;
	int error;

	if (!kc)
		return -EINVAL;

	error = kc->clock_get(which_clock, &kernel_tp);

	if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
		error = -EFAULT;

	return error;
}

SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
		struct timex __user *, utx)
{
	struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timex ktx;
	int err;

	if (!kc)
		return -EINVAL;
	if (!kc->clock_adj)
		return -EOPNOTSUPP;

	if (copy_from_user(&ktx, utx, sizeof(ktx)))
		return -EFAULT;

	err = kc->clock_adj(which_clock, &ktx);

	if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx)))
		return -EFAULT;

	return err;
}

SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
		struct timespec __user *, tp)
{
	struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec rtn_tp;
	int error;

	if (!kc)
		return -EINVAL;

	error = kc->clock_getres(which_clock, &rtn_tp);

	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
		error = -EFAULT;

	return error;
}

/*
 * nanosleep for monotonic and realtime clocks
 */
static int common_nsleep(const clockid_t which_clock, int flags,
			 struct timespec *tsave, struct timespec __user *rmtp)
{
	return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ?
				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
				 which_clock);
}

SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
		const struct timespec __user *, rqtp,
		struct timespec __user *, rmtp)
{
	struct k_clock *kc = clockid_to_kclock(which_clock);
	struct timespec t;

	if (!kc)
		return -EINVAL;
	if (!kc->nsleep)
		return -ENANOSLEEP_NOTSUP;

	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
		return -EFAULT;

	if (!timespec_valid(&t))
		return -EINVAL;

	return kc->nsleep(which_clock, flags, &t, rmtp);
}

/*
 * This will restart clock_nanosleep. This is required only by
 * compat_clock_nanosleep_restart for now.
 */
long clock_nanosleep_restart(struct restart_block *restart_block)
{
	clockid_t which_clock = restart_block->nanosleep.clockid;
	struct k_clock *kc = clockid_to_kclock(which_clock);

	if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
		return -EINVAL;

	return kc->nsleep_restart(restart_block);
}