forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
rcutree.c
1903 lines (1665 loc) · 54.9 KB
/
rcutree.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
/*
* Read-Copy Update mechanism for mutual exclusion
*
* 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <[email protected]>
* Manfred Spraul <[email protected]>
* Paul E. McKenney <[email protected]> Hierarchical version
*
* Based on the original work by Paul McKenney <[email protected]>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/nmi.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
#include <linux/kernel_stat.h>
#include "rcutree.h"
/* Data structures. */
static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
#define RCU_STATE_INITIALIZER(name) { \
.level = { &name.node[0] }, \
.levelcnt = { \
NUM_RCU_LVL_0, /* root of hierarchy. */ \
NUM_RCU_LVL_1, \
NUM_RCU_LVL_2, \
NUM_RCU_LVL_3, \
NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \
}, \
.signaled = RCU_GP_IDLE, \
.gpnum = -300, \
.completed = -300, \
.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
.orphan_cbs_list = NULL, \
.orphan_cbs_tail = &name.orphan_cbs_list, \
.orphan_qlen = 0, \
.fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
}
struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
static int rcu_scheduler_active __read_mostly;
/*
* Return true if an RCU grace period is in progress. The ACCESS_ONCE()s
* permit this function to be invoked without holding the root rcu_node
* structure's ->lock, but of course results can be subject to change.
*/
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
}
/*
* Note a quiescent state. Because we do not need to know
* how many quiescent states passed, just if there was at least
* one since the start of the grace period, this just sets a flag.
*/
void rcu_sched_qs(int cpu)
{
struct rcu_data *rdp;
rdp = &per_cpu(rcu_sched_data, cpu);
rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
rcu_preempt_note_context_switch(cpu);
}
void rcu_bh_qs(int cpu)
{
struct rcu_data *rdp;
rdp = &per_cpu(rcu_bh_data, cpu);
rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
}
#ifdef CONFIG_NO_HZ
DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = 1,
.dynticks = 1,
};
#endif /* #ifdef CONFIG_NO_HZ */
static int blimit = 10; /* Maximum callbacks per softirq. */
static int qhimark = 10000; /* If this many pending, ignore blimit. */
static int qlowmark = 100; /* Once only this many pending, use blimit. */
module_param(blimit, int, 0);
module_param(qhimark, int, 0);
module_param(qlowmark, int, 0);
static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
static int rcu_pending(int cpu);
/*
* Return the number of RCU-sched batches processed thus far for debug & stats.
*/
long rcu_batches_completed_sched(void)
{
return rcu_sched_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
/*
* Return the number of RCU BH batches processed thus far for debug & stats.
*/
long rcu_batches_completed_bh(void)
{
return rcu_bh_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
/*
* Does the CPU have callbacks ready to be invoked?
*/
static int
cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
{
return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL];
}
/*
* Does the current CPU require a yet-as-unscheduled grace period?
*/
static int
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp);
}
/*
* Return the root node of the specified rcu_state structure.
*/
static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
{
return &rsp->node[0];
}
#ifdef CONFIG_SMP
/*
* If the specified CPU is offline, tell the caller that it is in
* a quiescent state. Otherwise, whack it with a reschedule IPI.
* Grace periods can end up waiting on an offline CPU when that
* CPU is in the process of coming online -- it will be added to the
* rcu_node bitmasks before it actually makes it online. The same thing
* can happen while a CPU is in the process of coming online. Because this
* race is quite rare, we check for it after detecting that the grace
* period has been delayed rather than checking each and every CPU
* each and every time we start a new grace period.
*/
static int rcu_implicit_offline_qs(struct rcu_data *rdp)
{
/*
* If the CPU is offline, it is in a quiescent state. We can
* trust its state not to change because interrupts are disabled.
*/
if (cpu_is_offline(rdp->cpu)) {
rdp->offline_fqs++;
return 1;
}
/* If preemptable RCU, no point in sending reschedule IPI. */
if (rdp->preemptable)
return 0;
/* The CPU is online, so send it a reschedule IPI. */
if (rdp->cpu != smp_processor_id())
smp_send_reschedule(rdp->cpu);
else
set_need_resched();
rdp->resched_ipi++;
return 0;
}
#endif /* #ifdef CONFIG_SMP */
#ifdef CONFIG_NO_HZ
/**
* rcu_enter_nohz - inform RCU that current CPU is entering nohz
*
* Enter nohz mode, in other words, -leave- the mode in which RCU
* read-side critical sections can occur. (Though RCU read-side
* critical sections can occur in irq handlers in nohz mode, a possibility
* handled by rcu_irq_enter() and rcu_irq_exit()).
*/
void rcu_enter_nohz(void)
{
unsigned long flags;
struct rcu_dynticks *rdtp;
smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
local_irq_save(flags);
rdtp = &__get_cpu_var(rcu_dynticks);
rdtp->dynticks++;
rdtp->dynticks_nesting--;
WARN_ON_ONCE(rdtp->dynticks & 0x1);
local_irq_restore(flags);
}
/*
* rcu_exit_nohz - inform RCU that current CPU is leaving nohz
*
* Exit nohz mode, in other words, -enter- the mode in which RCU
* read-side critical sections normally occur.
*/
void rcu_exit_nohz(void)
{
unsigned long flags;
struct rcu_dynticks *rdtp;
local_irq_save(flags);
rdtp = &__get_cpu_var(rcu_dynticks);
rdtp->dynticks++;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
local_irq_restore(flags);
smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
}
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
*
* If the CPU was idle with dynamic ticks active, and there is no
* irq handler running, this updates rdtp->dynticks_nmi to let the
* RCU grace-period handling know that the CPU is active.
*/
void rcu_nmi_enter(void)
{
struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
if (rdtp->dynticks & 0x1)
return;
rdtp->dynticks_nmi++;
WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
}
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
*
* If the CPU was idle with dynamic ticks active, and there is no
* irq handler running, this updates rdtp->dynticks_nmi to let the
* RCU grace-period handling know that the CPU is no longer active.
*/
void rcu_nmi_exit(void)
{
struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
if (rdtp->dynticks & 0x1)
return;
smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
rdtp->dynticks_nmi++;
WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
}
/**
* rcu_irq_enter - inform RCU of entry to hard irq context
*
* If the CPU was idle with dynamic ticks active, this updates the
* rdtp->dynticks to let the RCU handling know that the CPU is active.
*/
void rcu_irq_enter(void)
{
struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
if (rdtp->dynticks_nesting++)
return;
rdtp->dynticks++;
WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
}
/**
* rcu_irq_exit - inform RCU of exit from hard irq context
*
* If the CPU was idle with dynamic ticks active, update the rdp->dynticks
* to put let the RCU handling be aware that the CPU is going back to idle
* with no ticks.
*/
void rcu_irq_exit(void)
{
struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
if (--rdtp->dynticks_nesting)
return;
smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
rdtp->dynticks++;
WARN_ON_ONCE(rdtp->dynticks & 0x1);
/* If the interrupt queued a callback, get out of dyntick mode. */
if (__get_cpu_var(rcu_sched_data).nxtlist ||
__get_cpu_var(rcu_bh_data).nxtlist)
set_need_resched();
}
#ifdef CONFIG_SMP
/*
* Snapshot the specified CPU's dynticks counter so that we can later
* credit them with an implicit quiescent state. Return 1 if this CPU
* is in dynticks idle mode, which is an extended quiescent state.
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
int ret;
int snap;
int snap_nmi;
snap = rdp->dynticks->dynticks;
snap_nmi = rdp->dynticks->dynticks_nmi;
smp_mb(); /* Order sampling of snap with end of grace period. */
rdp->dynticks_snap = snap;
rdp->dynticks_nmi_snap = snap_nmi;
ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
if (ret)
rdp->dynticks_fqs++;
return ret;
}
/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
* for this same CPU.
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
long curr;
long curr_nmi;
long snap;
long snap_nmi;
curr = rdp->dynticks->dynticks;
snap = rdp->dynticks_snap;
curr_nmi = rdp->dynticks->dynticks_nmi;
snap_nmi = rdp->dynticks_nmi_snap;
smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
/*
* If the CPU passed through or entered a dynticks idle phase with
* no active irq/NMI handlers, then we can safely pretend that the CPU
* already acknowledged the request to pass through a quiescent
* state. Either way, that CPU cannot possibly be in an RCU
* read-side critical section that started before the beginning
* of the current RCU grace period.
*/
if ((curr != snap || (curr & 0x1) == 0) &&
(curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
rdp->dynticks_fqs++;
return 1;
}
/* Go check for the CPU being offline. */
return rcu_implicit_offline_qs(rdp);
}
#endif /* #ifdef CONFIG_SMP */
#else /* #ifdef CONFIG_NO_HZ */
#ifdef CONFIG_SMP
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
return 0;
}
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
return rcu_implicit_offline_qs(rdp);
}
#endif /* #ifdef CONFIG_SMP */
#endif /* #else #ifdef CONFIG_NO_HZ */
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
rsp->gp_start = jiffies;
rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
}
static void print_other_cpu_stall(struct rcu_state *rsp)
{
int cpu;
long delta;
unsigned long flags;
struct rcu_node *rnp = rcu_get_root(rsp);
/* Only let one CPU complain about others per time interval. */
spin_lock_irqsave(&rnp->lock, flags);
delta = jiffies - rsp->jiffies_stall;
if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
/*
* Now rat on any tasks that got kicked up to the root rcu_node
* due to CPU offlining.
*/
rcu_print_task_stall(rnp);
spin_unlock_irqrestore(&rnp->lock, flags);
/* OK, time to rat on our buddy... */
printk(KERN_ERR "INFO: RCU detected CPU stalls:");
rcu_for_each_leaf_node(rsp, rnp) {
rcu_print_task_stall(rnp);
if (rnp->qsmask == 0)
continue;
for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
if (rnp->qsmask & (1UL << cpu))
printk(" %d", rnp->grplo + cpu);
}
printk(" (detected by %d, t=%ld jiffies)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start));
trigger_all_cpu_backtrace();
force_quiescent_state(rsp, 0); /* Kick them all. */
}
static void print_cpu_stall(struct rcu_state *rsp)
{
unsigned long flags;
struct rcu_node *rnp = rcu_get_root(rsp);
printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
smp_processor_id(), jiffies - rsp->gp_start);
trigger_all_cpu_backtrace();
spin_lock_irqsave(&rnp->lock, flags);
if ((long)(jiffies - rsp->jiffies_stall) >= 0)
rsp->jiffies_stall =
jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
spin_unlock_irqrestore(&rnp->lock, flags);
set_need_resched(); /* kick ourselves to get things going. */
}
static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
long delta;
struct rcu_node *rnp;
delta = jiffies - rsp->jiffies_stall;
rnp = rdp->mynode;
if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
} else if (rcu_gp_in_progress(rsp) && delta >= RCU_STALL_RAT_DELAY) {
/* They had two time units to dump stack, so complain. */
print_other_cpu_stall(rsp);
}
}
#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
}
static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
}
#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
/*
* Update CPU-local rcu_data state to record the newly noticed grace period.
* This is used both when we started the grace period and when we notice
* that someone else started the grace period. The caller must hold the
* ->lock of the leaf rcu_node structure corresponding to the current CPU,
* and must have irqs disabled.
*/
static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
if (rdp->gpnum != rnp->gpnum) {
rdp->qs_pending = 1;
rdp->passed_quiesc = 0;
rdp->gpnum = rnp->gpnum;
}
}
static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_node *rnp;
local_irq_save(flags);
rnp = rdp->mynode;
if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
!spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
local_irq_restore(flags);
return;
}
__note_new_gpnum(rsp, rnp, rdp);
spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* Did someone else start a new RCU grace period start since we last
* checked? Update local state appropriately if so. Must be called
* on the CPU corresponding to rdp.
*/
static int
check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
int ret = 0;
local_irq_save(flags);
if (rdp->gpnum != rsp->gpnum) {
note_new_gpnum(rsp, rdp);
ret = 1;
}
local_irq_restore(flags);
return ret;
}
/*
* Advance this CPU's callbacks, but only if the current grace period
* has ended. This may be called only from the CPU to whom the rdp
* belongs. In addition, the corresponding leaf rcu_node structure's
* ->lock must be held by the caller, with irqs disabled.
*/
static void
__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
/* Did another grace period end? */
if (rdp->completed != rnp->completed) {
/* Advance callbacks. No harm if list empty. */
rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
/* Remember that we saw this grace-period completion. */
rdp->completed = rnp->completed;
}
}
/*
* Advance this CPU's callbacks, but only if the current grace period
* has ended. This may be called only from the CPU to whom the rdp
* belongs.
*/
static void
rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_node *rnp;
local_irq_save(flags);
rnp = rdp->mynode;
if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
!spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
local_irq_restore(flags);
return;
}
__rcu_process_gp_end(rsp, rnp, rdp);
spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* Do per-CPU grace-period initialization for running CPU. The caller
* must hold the lock of the leaf rcu_node structure corresponding to
* this CPU.
*/
static void
rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
/* Prior grace period ended, so advance callbacks for current CPU. */
__rcu_process_gp_end(rsp, rnp, rdp);
/*
* Because this CPU just now started the new grace period, we know
* that all of its callbacks will be covered by this upcoming grace
* period, even the ones that were registered arbitrarily recently.
* Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
*
* Other CPUs cannot be sure exactly when the grace period started.
* Therefore, their recently registered callbacks must pass through
* an additional RCU_NEXT_READY stage, so that they will be handled
* by the next RCU grace period.
*/
rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
/* Set state so that this CPU will detect the next quiescent state. */
__note_new_gpnum(rsp, rnp, rdp);
}
/*
* Start a new RCU grace period if warranted, re-initializing the hierarchy
* in preparation for detecting the next grace period. The caller must hold
* the root node's ->lock, which is released before return. Hard irqs must
* be disabled.
*/
static void
rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
__releases(rcu_get_root(rsp)->lock)
{
struct rcu_data *rdp = rsp->rda[smp_processor_id()];
struct rcu_node *rnp = rcu_get_root(rsp);
if (!cpu_needs_another_gp(rsp, rdp)) {
if (rnp->completed == rsp->completed) {
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
spin_unlock(&rnp->lock); /* irqs remain disabled. */
/*
* Propagate new ->completed value to rcu_node structures
* so that other CPUs don't have to wait until the start
* of the next grace period to process their callbacks.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->completed = rsp->completed;
spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
local_irq_restore(flags);
return;
}
/* Advance to a new grace period and initialize state. */
rsp->gpnum++;
WARN_ON_ONCE(rsp->signaled == RCU_GP_INIT);
rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
record_gp_stall_check_time(rsp);
/* Special-case the common single-level case. */
if (NUM_RCU_NODES == 1) {
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
rnp->completed = rsp->completed;
rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
rcu_start_gp_per_cpu(rsp, rnp, rdp);
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
spin_unlock(&rnp->lock); /* leave irqs disabled. */
/* Exclude any concurrent CPU-hotplug operations. */
spin_lock(&rsp->onofflock); /* irqs already disabled. */
/*
* Set the quiescent-state-needed bits in all the rcu_node
* structures for all currently online CPUs in breadth-first
* order, starting from the root rcu_node structure. This
* operation relies on the layout of the hierarchy within the
* rsp->node[] array. Note that other CPUs will access only
* the leaves of the hierarchy, which still indicate that no
* grace period is in progress, at least until the corresponding
* leaf node has been initialized. In addition, we have excluded
* CPU-hotplug operations.
*
* Note that the grace period cannot complete until we finish
* the initialization process, as there will be at least one
* qsmask bit set in the root node until that time, namely the
* one corresponding to this CPU, due to the fact that we have
* irqs disabled.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
spin_lock(&rnp->lock); /* irqs already disabled. */
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
rnp->completed = rsp->completed;
if (rnp == rdp->mynode)
rcu_start_gp_per_cpu(rsp, rnp, rdp);
spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
rnp = rcu_get_root(rsp);
spin_lock(&rnp->lock); /* irqs already disabled. */
rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
spin_unlock(&rnp->lock); /* irqs remain disabled. */
spin_unlock_irqrestore(&rsp->onofflock, flags);
}
/*
* Report a full set of quiescent states to the specified rcu_state
* data structure. This involves cleaning up after the prior grace
* period and letting rcu_start_gp() start up the next grace period
* if one is needed. Note that the caller must hold rnp->lock, as
* required by rcu_start_gp(), which will release it.
*/
static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
__releases(rcu_get_root(rsp)->lock)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
rsp->completed = rsp->gpnum;
rsp->signaled = RCU_GP_IDLE;
rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */
}
/*
* Similar to rcu_report_qs_rdp(), for which it is a helper function.
* Allows quiescent states for a group of CPUs to be reported at one go
* to the specified rcu_node structure, though all the CPUs in the group
* must be represented by the same rcu_node structure (which need not be
* a leaf rcu_node structure, though it often will be). That structure's
* lock must be held upon entry, and it is released before return.
*/
static void
rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
struct rcu_node *rnp_c;
/* Walk up the rcu_node hierarchy. */
for (;;) {
if (!(rnp->qsmask & mask)) {
/* Our bit has already been cleared, so done. */
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
rnp->qsmask &= ~mask;
if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
/* Other bits still set at this level, so done. */
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
mask = rnp->grpmask;
if (rnp->parent == NULL) {
/* No more levels. Exit loop holding root lock. */
break;
}
spin_unlock_irqrestore(&rnp->lock, flags);
rnp_c = rnp;
rnp = rnp->parent;
spin_lock_irqsave(&rnp->lock, flags);
WARN_ON_ONCE(rnp_c->qsmask);
}
/*
* Get here if we are the last CPU to pass through a quiescent
* state for this grace period. Invoke rcu_report_qs_rsp()
* to clean up and start the next grace period if one is needed.
*/
rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
}
/*
* Record a quiescent state for the specified CPU to that CPU's rcu_data
* structure. This must be either called from the specified CPU, or
* called when the specified CPU is known to be offline (and when it is
* also known that no other CPU is concurrently trying to help the offline
* CPU). The lastcomp argument is used to make sure we are still in the
* grace period of interest. We don't want to end the current grace period
* based on quiescent states detected in an earlier grace period!
*/
static void
rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
{
unsigned long flags;
unsigned long mask;
struct rcu_node *rnp;
rnp = rdp->mynode;
spin_lock_irqsave(&rnp->lock, flags);
if (lastcomp != rnp->completed) {
/*
* Someone beat us to it for this grace period, so leave.
* The race with GP start is resolved by the fact that we
* hold the leaf rcu_node lock, so that the per-CPU bits
* cannot yet be initialized -- so we would simply find our
* CPU's bit already cleared in rcu_report_qs_rnp() if this
* race occurred.
*/
rdp->passed_quiesc = 0; /* try again later! */
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
mask = rdp->grpmask;
if ((rnp->qsmask & mask) == 0) {
spin_unlock_irqrestore(&rnp->lock, flags);
} else {
rdp->qs_pending = 0;
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
*/
rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
}
}
/*
* Check to see if there is a new grace period of which this CPU
* is not yet aware, and if so, set up local rcu_data state for it.
* Otherwise, see if this CPU has just passed through its first
* quiescent state for this grace period, and record that fact if so.
*/
static void
rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
{
/* If there is now a new grace period, record and return. */
if (check_for_new_grace_period(rsp, rdp))
return;
/*
* Does this CPU still need to do its part for current grace period?
* If no, return and let the other CPUs do their part as well.
*/
if (!rdp->qs_pending)
return;
/*
* Was there a quiescent state since the beginning of the grace
* period? If no, then exit and wait for the next call.
*/
if (!rdp->passed_quiesc)
return;
/*
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* Move a dying CPU's RCU callbacks to the ->orphan_cbs_list for the
* specified flavor of RCU. The callbacks will be adopted by the next
* _rcu_barrier() invocation or by the CPU_DEAD notifier, whichever
* comes first. Because this is invoked from the CPU_DYING notifier,
* irqs are already disabled.
*/
static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
{
int i;
struct rcu_data *rdp = rsp->rda[smp_processor_id()];
if (rdp->nxtlist == NULL)
return; /* irqs disabled, so comparison is stable. */
spin_lock(&rsp->onofflock); /* irqs already disabled. */
*rsp->orphan_cbs_tail = rdp->nxtlist;
rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
rsp->orphan_qlen += rdp->qlen;
rdp->qlen = 0;
spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
}
/*
* Adopt previously orphaned RCU callbacks.
*/
static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
{
unsigned long flags;
struct rcu_data *rdp;
spin_lock_irqsave(&rsp->onofflock, flags);
rdp = rsp->rda[smp_processor_id()];
if (rsp->orphan_cbs_list == NULL) {
spin_unlock_irqrestore(&rsp->onofflock, flags);
return;
}
*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
rdp->qlen += rsp->orphan_qlen;
rsp->orphan_cbs_list = NULL;
rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
rsp->orphan_qlen = 0;
spin_unlock_irqrestore(&rsp->onofflock, flags);
}
/*
* Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy
* and move all callbacks from the outgoing CPU to the current one.
*/
static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
unsigned long mask;
int need_report = 0;
struct rcu_data *rdp = rsp->rda[cpu];
struct rcu_node *rnp;
/* Exclude any attempts to start a new grace period. */
spin_lock_irqsave(&rsp->onofflock, flags);
/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
rnp = rdp->mynode; /* this is the outgoing CPU's rnp. */
mask = rdp->grpmask; /* rnp->grplo is constant. */
do {
spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
if (rnp->qsmaskinit != 0) {
if (rnp != rdp->mynode)
spin_unlock(&rnp->lock); /* irqs remain disabled. */
break;
}
if (rnp == rdp->mynode)
need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
else
spin_unlock(&rnp->lock); /* irqs remain disabled. */
mask = rnp->grpmask;
rnp = rnp->parent;
} while (rnp != NULL);
/*
* We still hold the leaf rcu_node structure lock here, and
* irqs are still disabled. The reason for this subterfuge is
* because invoking rcu_report_unblock_qs_rnp() with ->onofflock
* held leads to deadlock.
*/
spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
rnp = rdp->mynode;
if (need_report & RCU_OFL_TASKS_NORM_GP)
rcu_report_unblock_qs_rnp(rnp, flags);
else
spin_unlock_irqrestore(&rnp->lock, flags);
if (need_report & RCU_OFL_TASKS_EXP_GP)
rcu_report_exp_rnp(rsp, rnp);
rcu_adopt_orphan_cbs(rsp);
}
/*
* Remove the specified CPU from the RCU hierarchy and move any pending
* callbacks that it might have to the current CPU. This code assumes
* that at least one CPU in the system will remain running at all times.
* Any attempt to offline -all- CPUs is likely to strand RCU callbacks.
*/