forked from tmatsuya/linux-2.6
-
Notifications
You must be signed in to change notification settings - Fork 2
/
hrtimer.c
1882 lines (1596 loc) · 47 KB
/
hrtimer.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
/*
* linux/kernel/hrtimer.c
*
* Copyright(C) 2005-2006, Thomas Gleixner <[email protected]>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
* High-resolution kernel timers
*
* In contrast to the low-resolution timeout API implemented in
* kernel/timer.c, hrtimers provide finer resolution and accuracy
* depending on system configuration and capabilities.
*
* These timers are currently used for:
* - itimers
* - POSIX timers
* - nanosleep
* - precise in-kernel timing
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* Credits:
* based on kernel/timer.c
*
* Help, testing, suggestions, bugfixes, improvements were
* provided by:
*
* George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
* et. al.
*
* For licencing details see kernel-base/COPYING
*/
#include <linux/cpu.h>
#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
#include <linux/tick.h>
#include <linux/seq_file.h>
#include <linux/err.h>
#include <linux/debugobjects.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <asm/uaccess.h>
#include <trace/events/timer.h>
/*
* The timer bases:
*
* There are more clockids then hrtimer bases. Thus, we index
* into the timer bases by the hrtimer_base_type enum. When trying
* to reach a base using a clockid, hrtimer_clockid_to_base()
* is used to convert from clockid to the proper hrtimer_base_type.
*/
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
.clock_base =
{
{
.index = HRTIMER_BASE_MONOTONIC,
.clockid = CLOCK_MONOTONIC,
.get_time = &ktime_get,
.resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_REALTIME,
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
.resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_BOOTTIME,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
.resolution = KTIME_LOW_RES,
},
}
};
static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
};
static inline int hrtimer_clockid_to_base(clockid_t clock_id)
{
return hrtimer_clock_to_base_table[clock_id];
}
/*
* Get the coarse grained time at the softirq based on xtime and
* wall_to_monotonic.
*/
static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
{
ktime_t xtim, mono, boot;
struct timespec xts, tom, slp;
get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
xtim = timespec_to_ktime(xts);
mono = ktime_add(xtim, timespec_to_ktime(tom));
boot = ktime_add(mono, timespec_to_ktime(slp));
base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
}
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
*/
#ifdef CONFIG_SMP
/*
* We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
* means that all timers which are tied to this base via timer->base are
* locked, and the base itself is locked too.
*
* So __run_timers/migrate_timers can safely modify all timers which could
* be found on the lists/queues.
*
* When the timer's base is locked, and the timer removed from list, it is
* possible to set timer->base = NULL and drop the lock: the timer remains
* locked.
*/
static
struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
unsigned long *flags)
{
struct hrtimer_clock_base *base;
for (;;) {
base = timer->base;
if (likely(base != NULL)) {
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
return base;
/* The timer has migrated to another CPU: */
raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
}
cpu_relax();
}
}
/*
* Get the preferred target CPU for NOHZ
*/
static int hrtimer_get_target(int this_cpu, int pinned)
{
#ifdef CONFIG_NO_HZ
if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
return get_nohz_timer_target();
#endif
return this_cpu;
}
/*
* With HIGHRES=y we do not migrate the timer when it is expiring
* before the next event on the target cpu because we cannot reprogram
* the target cpu hardware and we would cause it to fire late.
*
* Called with cpu_base->lock of target cpu held.
*/
static int
hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
{
#ifdef CONFIG_HIGH_RES_TIMERS
ktime_t expires;
if (!new_base->cpu_base->hres_active)
return 0;
expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
#else
return 0;
#endif
}
/*
* Switch the timer base to the current CPU when possible.
*/
static inline struct hrtimer_clock_base *
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
int pinned)
{
struct hrtimer_clock_base *new_base;
struct hrtimer_cpu_base *new_cpu_base;
int this_cpu = smp_processor_id();
int cpu = hrtimer_get_target(this_cpu, pinned);
int basenum = base->index;
again:
new_cpu_base = &per_cpu(hrtimer_bases, cpu);
new_base = &new_cpu_base->clock_base[basenum];
if (base != new_base) {
/*
* We are trying to move timer to new_base.
* However we can't change timer's base while it is running,
* so we keep it on the same CPU. No hassle vs. reprogramming
* the event source in the high resolution case. The softirq
* code will take care of this when the timer function has
* completed. There is no conflict as we hold the lock until
* the timer is enqueued.
*/
if (unlikely(hrtimer_callback_running(timer)))
return base;
/* See the comment in lock_timer_base() */
timer->base = NULL;
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
cpu = this_cpu;
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
timer->base = base;
goto again;
}
timer->base = new_base;
}
return new_base;
}
#else /* CONFIG_SMP */
static inline struct hrtimer_clock_base *
lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
struct hrtimer_clock_base *base = timer->base;
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
return base;
}
# define switch_hrtimer_base(t, b, p) (b)
#endif /* !CONFIG_SMP */
/*
* Functions for the union type storage format of ktime_t which are
* too large for inlining:
*/
#if BITS_PER_LONG < 64
# ifndef CONFIG_KTIME_SCALAR
/**
* ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable
* @kt: addend
* @nsec: the scalar nsec value to add
*
* Returns the sum of kt and nsec in ktime_t format
*/
ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
{
ktime_t tmp;
if (likely(nsec < NSEC_PER_SEC)) {
tmp.tv64 = nsec;
} else {
unsigned long rem = do_div(nsec, NSEC_PER_SEC);
tmp = ktime_set((long)nsec, rem);
}
return ktime_add(kt, tmp);
}
EXPORT_SYMBOL_GPL(ktime_add_ns);
/**
* ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable
* @kt: minuend
* @nsec: the scalar nsec value to subtract
*
* Returns the subtraction of @nsec from @kt in ktime_t format
*/
ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec)
{
ktime_t tmp;
if (likely(nsec < NSEC_PER_SEC)) {
tmp.tv64 = nsec;
} else {
unsigned long rem = do_div(nsec, NSEC_PER_SEC);
tmp = ktime_set((long)nsec, rem);
}
return ktime_sub(kt, tmp);
}
EXPORT_SYMBOL_GPL(ktime_sub_ns);
# endif /* !CONFIG_KTIME_SCALAR */
/*
* Divide a ktime value by a nanosecond value
*/
u64 ktime_divns(const ktime_t kt, s64 div)
{
u64 dclc;
int sft = 0;
dclc = ktime_to_ns(kt);
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
div >>= 1;
}
dclc >>= sft;
do_div(dclc, (unsigned long) div);
return dclc;
}
#endif /* BITS_PER_LONG >= 64 */
/*
* Add two ktime values and do a safety check for overflow:
*/
ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
{
ktime_t res = ktime_add(lhs, rhs);
/*
* We use KTIME_SEC_MAX here, the maximum timeout which we can
* return to user space in a timespec:
*/
if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64)
res = ktime_set(KTIME_SEC_MAX, 0);
return res;
}
EXPORT_SYMBOL_GPL(ktime_add_safe);
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
static struct debug_obj_descr hrtimer_debug_descr;
static void *hrtimer_debug_hint(void *addr)
{
return ((struct hrtimer *) addr)->function;
}
/*
* fixup_init is called when:
* - an active object is initialized
*/
static int hrtimer_fixup_init(void *addr, enum debug_obj_state state)
{
struct hrtimer *timer = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
hrtimer_cancel(timer);
debug_object_init(timer, &hrtimer_debug_descr);
return 1;
default:
return 0;
}
}
/*
* fixup_activate is called when:
* - an active object is activated
* - an unknown object is activated (might be a statically initialized object)
*/
static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
{
switch (state) {
case ODEBUG_STATE_NOTAVAILABLE:
WARN_ON_ONCE(1);
return 0;
case ODEBUG_STATE_ACTIVE:
WARN_ON(1);
default:
return 0;
}
}
/*
* fixup_free is called when:
* - an active object is freed
*/
static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
{
struct hrtimer *timer = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
hrtimer_cancel(timer);
debug_object_free(timer, &hrtimer_debug_descr);
return 1;
default:
return 0;
}
}
static struct debug_obj_descr hrtimer_debug_descr = {
.name = "hrtimer",
.debug_hint = hrtimer_debug_hint,
.fixup_init = hrtimer_fixup_init,
.fixup_activate = hrtimer_fixup_activate,
.fixup_free = hrtimer_fixup_free,
};
static inline void debug_hrtimer_init(struct hrtimer *timer)
{
debug_object_init(timer, &hrtimer_debug_descr);
}
static inline void debug_hrtimer_activate(struct hrtimer *timer)
{
debug_object_activate(timer, &hrtimer_debug_descr);
}
static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
{
debug_object_deactivate(timer, &hrtimer_debug_descr);
}
static inline void debug_hrtimer_free(struct hrtimer *timer)
{
debug_object_free(timer, &hrtimer_debug_descr);
}
static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode);
void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode)
{
debug_object_init_on_stack(timer, &hrtimer_debug_descr);
__hrtimer_init(timer, clock_id, mode);
}
EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);
void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
debug_object_free(timer, &hrtimer_debug_descr);
}
#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
#endif
static inline void
debug_init(struct hrtimer *timer, clockid_t clockid,
enum hrtimer_mode mode)
{
debug_hrtimer_init(timer);
trace_hrtimer_init(timer, clockid, mode);
}
static inline void debug_activate(struct hrtimer *timer)
{
debug_hrtimer_activate(timer);
trace_hrtimer_start(timer);
}
static inline void debug_deactivate(struct hrtimer *timer)
{
debug_hrtimer_deactivate(timer);
trace_hrtimer_cancel(timer);
}
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
/*
* High resolution timer enabled ?
*/
static int hrtimer_hres_enabled __read_mostly = 1;
/*
* Enable / Disable high resolution mode
*/
static int __init setup_hrtimer_hres(char *str)
{
if (!strcmp(str, "off"))
hrtimer_hres_enabled = 0;
else if (!strcmp(str, "on"))
hrtimer_hres_enabled = 1;
else
return 0;
return 1;
}
__setup("highres=", setup_hrtimer_hres);
/*
* hrtimer_high_res_enabled - query, if the highres mode is enabled
*/
static inline int hrtimer_is_hres_enabled(void)
{
return hrtimer_hres_enabled;
}
/*
* Is the high resolution mode active ?
*/
static inline int hrtimer_hres_active(void)
{
return __this_cpu_read(hrtimer_bases.hres_active);
}
/*
* Reprogram the event source with checking both queues for the
* next event
* Called with interrupts disabled and base->lock held
*/
static void
hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
int i;
struct hrtimer_clock_base *base = cpu_base->clock_base;
ktime_t expires, expires_next;
expires_next.tv64 = KTIME_MAX;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
struct hrtimer *timer;
struct timerqueue_node *next;
next = timerqueue_getnext(&base->active);
if (!next)
continue;
timer = container_of(next, struct hrtimer, node);
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
/*
* clock_was_set() has changed base->offset so the
* result might be negative. Fix it up to prevent a
* false positive in clockevents_program_event()
*/
if (expires.tv64 < 0)
expires.tv64 = 0;
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
}
if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
return;
cpu_base->expires_next.tv64 = expires_next.tv64;
if (cpu_base->expires_next.tv64 != KTIME_MAX)
tick_program_event(cpu_base->expires_next, 1);
}
/*
* Shared reprogramming for clock_realtime and clock_monotonic
*
* When a timer is enqueued and expires earlier than the already enqueued
* timers, we have to check, whether it expires earlier than the timer for
* which the clock event device was armed.
*
* Called with interrupts disabled and base->cpu_base.lock held
*/
static int hrtimer_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base)
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
int res;
WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
/*
* When the callback is running, we do not reprogram the clock event
* device. The timer callback is either running on a different CPU or
* the callback is executed in the hrtimer_interrupt context. The
* reprogramming is handled either by the softirq, which called the
* callback or at the end of the hrtimer_interrupt.
*/
if (hrtimer_callback_running(timer))
return 0;
/*
* CLOCK_REALTIME timer might be requested with an absolute
* expiry time which is less than base->offset. Nothing wrong
* about that, just avoid to call into the tick code, which
* has now objections against negative expiry values.
*/
if (expires.tv64 < 0)
return -ETIME;
if (expires.tv64 >= cpu_base->expires_next.tv64)
return 0;
/*
* If a hang was detected in the last timer interrupt then we
* do not schedule a timer which is earlier than the expiry
* which we enforced in the hang detection. We want the system
* to make progress.
*/
if (cpu_base->hang_detected)
return 0;
/*
* Clockevents returns -ETIME, when the event was in the past.
*/
res = tick_program_event(expires, 0);
if (!IS_ERR_VALUE(res))
cpu_base->expires_next = expires;
return res;
}
/*
* Initialize the high resolution related parts of cpu_base
*/
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
base->expires_next.tv64 = KTIME_MAX;
base->hres_active = 0;
}
/*
* When High resolution timers are active, try to reprogram. Note, that in case
* the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
* check happens. The timer gets enqueued into the rbtree. The reprogramming
* and expiry check is done in the hrtimer_interrupt or in the softirq.
*/
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base,
int wakeup)
{
if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
if (wakeup) {
raw_spin_unlock(&base->cpu_base->lock);
raise_softirq_irqoff(HRTIMER_SOFTIRQ);
raw_spin_lock(&base->cpu_base->lock);
} else
__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
return 1;
}
return 0;
}
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
return ktime_get_update_offsets(offs_real, offs_boot);
}
/*
* Retrigger next event is called after clock was set
*
* Called with interrupts disabled via on_each_cpu()
*/
static void retrigger_next_event(void *arg)
{
struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
if (!hrtimer_hres_active())
return;
raw_spin_lock(&base->lock);
hrtimer_update_base(base);
hrtimer_force_reprogram(base, 0);
raw_spin_unlock(&base->lock);
}
/*
* Switch to high resolution mode
*/
static int hrtimer_switch_to_hres(void)
{
int i, cpu = smp_processor_id();
struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
unsigned long flags;
if (base->hres_active)
return 1;
local_irq_save(flags);
if (tick_init_highres()) {
local_irq_restore(flags);
printk(KERN_WARNING "Could not switch to high resolution "
"mode on CPU %d\n", cpu);
return 0;
}
base->hres_active = 1;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
base->clock_base[i].resolution = KTIME_HIGH_RES;
tick_setup_sched_timer();
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
local_irq_restore(flags);
return 1;
}
/*
* Called from timekeeping code to reprogramm the hrtimer interrupt
* device. If called from the timer interrupt context we defer it to
* softirq context.
*/
void clock_was_set_delayed(void)
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
cpu_base->clock_was_set = 1;
__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}
#else
static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
static inline void
hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base,
int wakeup)
{
return 0;
}
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void retrigger_next_event(void *arg) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
/*
* Clock realtime was set
*
* Change the offset of the realtime clock vs. the monotonic
* clock.
*
* We might have to reprogram the high resolution timer interrupt. On
* SMP we call the architecture specific code to retrigger _all_ high
* resolution timer interrupts. On UP we just disable interrupts and
* call the high resolution interrupt code.
*/
void clock_was_set(void)
{
#ifdef CONFIG_HIGH_RES_TIMERS
/* Retrigger the CPU local events everywhere */
on_each_cpu(retrigger_next_event, NULL, 1);
#endif
timerfd_clock_was_set();
}
/*
* During resume we might have to reprogram the high resolution timer
* interrupt (on the local CPU):
*/
void hrtimers_resume(void)
{
WARN_ONCE(!irqs_disabled(),
KERN_INFO "hrtimers_resume() called with IRQs enabled!");
retrigger_next_event(NULL);
timerfd_clock_was_set();
}
static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
if (timer->start_site)
return;
timer->start_site = __builtin_return_address(0);
memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
timer->start_pid = current->pid;
#endif
}
static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
timer->start_site = NULL;
#endif
}
static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
{
#ifdef CONFIG_TIMER_STATS
if (likely(!timer_stats_active))
return;
timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
timer->function, timer->start_comm, 0);
#endif
}
/*
* Counterpart to lock_hrtimer_base above:
*/
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}
/**
* hrtimer_forward - forward the timer expiry
* @timer: hrtimer to forward
* @now: forward past this time
* @interval: the interval to forward
*
* Forward the timer expiry so it will expire in the future.
* Returns the number of overruns.
*/
u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
u64 orun = 1;
ktime_t delta;
delta = ktime_sub(now, hrtimer_get_expires(timer));
if (delta.tv64 < 0)
return 0;
if (interval.tv64 < timer->base->resolution.tv64)
interval.tv64 = timer->base->resolution.tv64;
if (unlikely(delta.tv64 >= interval.tv64)) {
s64 incr = ktime_to_ns(interval);
orun = ktime_divns(delta, incr);
hrtimer_add_expires_ns(timer, incr * orun);
if (hrtimer_get_expires_tv64(timer) > now.tv64)
return orun;
/*
* This (and the ktime_add() below) is the
* correction for exact:
*/
orun++;
}
hrtimer_add_expires(timer, interval);
return orun;
}
EXPORT_SYMBOL_GPL(hrtimer_forward);
/*
* enqueue_hrtimer - internal function to (re)start a timer
*
* The timer is inserted in expiry order. Insertion into the
* red black tree is O(log(n)). Must hold the base lock.
*
* Returns 1 when the new timer is the leftmost timer in the tree.
*/
static int enqueue_hrtimer(struct hrtimer *timer,
struct hrtimer_clock_base *base)
{
debug_activate(timer);
timerqueue_add(&base->active, &timer->node);
base->cpu_base->active_bases |= 1 << base->index;
/*
* HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
* state of a possibly running callback.
*/
timer->state |= HRTIMER_STATE_ENQUEUED;
return (&timer->node == base->active.next);
}
/*
* __remove_hrtimer - internal function to remove a timer
*
* Caller must hold the base lock.
*
* High resolution timer mode reprograms the clock event device when the
* timer is the one which expires next. The caller can disable this by setting
* reprogram to zero. This is useful, when the context does a reprogramming
* anyway (e.g. timer interrupt)
*/
static void __remove_hrtimer(struct hrtimer *timer,
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
struct timerqueue_node *next_timer;
if (!(timer->state & HRTIMER_STATE_ENQUEUED))
goto out;
next_timer = timerqueue_getnext(&base->active);
timerqueue_del(&base->active, &timer->node);
if (&timer->node == next_timer) {
#ifdef CONFIG_HIGH_RES_TIMERS
/* Reprogram the clock event device. if enabled */
if (reprogram && hrtimer_hres_active()) {
ktime_t expires;
expires = ktime_sub(hrtimer_get_expires(timer),
base->offset);
if (base->cpu_base->expires_next.tv64 == expires.tv64)
hrtimer_force_reprogram(base->cpu_base, 1);
}
#endif
}
if (!timerqueue_getnext(&base->active))
base->cpu_base->active_bases &= ~(1 << base->index);
out:
timer->state = newstate;
}
/*
* remove hrtimer, called with base lock held
*/
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
if (hrtimer_is_queued(timer)) {
unsigned long state;
int reprogram;
/*
* Remove the timer and force reprogramming when high
* resolution mode is active and the timer is on the current
* CPU. If we remove a timer on another CPU, reprogramming is
* skipped. The interrupt event on this CPU is fired and
* reprogramming happens in the interrupt handler. This is a
* rare case and less expensive than a smp call.
*/
debug_deactivate(timer);
timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
/*
* We must preserve the CALLBACK state flag here,
* otherwise we could move the timer base in
* switch_hrtimer_base.
*/
state = timer->state & HRTIMER_STATE_CALLBACK;
__remove_hrtimer(timer, base, state, reprogram);
return 1;
}
return 0;
}
int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
unsigned long delta_ns, const enum hrtimer_mode mode,
int wakeup)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
int ret, leftmost;
base = lock_hrtimer_base(timer, &flags);
/* Remove an active timer from the queue: */
ret = remove_hrtimer(timer, base);
/* Switch the timer base, if necessary: */
new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
if (mode & HRTIMER_MODE_REL) {
tim = ktime_add_safe(tim, new_base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
* to signal that they simply return xtime in
* do_gettimeoffset(). In this case we want to round up by
* resolution when starting a relative timer, to avoid short
* timeouts. This will go away with the GTOD framework.
*/
#ifdef CONFIG_TIME_LOW_RES
tim = ktime_add_safe(tim, base->resolution);
#endif
}
hrtimer_set_expires_range_ns(timer, tim, delta_ns);
timer_stats_hrtimer_set_start_info(timer);
leftmost = enqueue_hrtimer(timer, new_base);
/*
* Only allow reprogramming if the new base is on this CPU.
* (it might still be on another CPU if the timer was pending)
*
* XXX send_remote_softirq() ?
*/
if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
hrtimer_enqueue_reprogram(timer, new_base, wakeup);