summaryrefslogtreecommitdiffstats
path: root/kernel/rcu/srcutree.c
blob: 66a998f9c5a71bce4a288718b1e95c5e7852560d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
/*
 * Sleepable 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, you can access it online at
 * http://www.gnu.org/licenses/gpl-2.0.html.
 *
 * Copyright (C) IBM Corporation, 2006
 * Copyright (C) Fujitsu, 2012
 *
 * Author: Paul McKenney <paulmck@us.ibm.com>
 *	   Lai Jiangshan <laijs@cn.fujitsu.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 *		Documentation/RCU/ *.txt
 *
 */

#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/preempt.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/srcu.h>

#include "rcu.h"
#include "rcu_segcblist.h"

/* Holdoff in nanoseconds for auto-expediting. */
#define DEFAULT_SRCU_EXP_HOLDOFF (25 * 1000)
static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF;
module_param(exp_holdoff, ulong, 0444);

/* Overflow-check frequency.  N bits roughly says every 2**N grace periods. */
static ulong counter_wrap_check = (ULONG_MAX >> 2);
module_param(counter_wrap_check, ulong, 0444);

static void srcu_invoke_callbacks(struct work_struct *work);
static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);

/*
 * Initialize SRCU combining tree.  Note that statically allocated
 * srcu_struct structures might already have srcu_read_lock() and
 * srcu_read_unlock() running against them.  So if the is_static parameter
 * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
 */
static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
{
	int cpu;
	int i;
	int level = 0;
	int levelspread[RCU_NUM_LVLS];
	struct srcu_data *sdp;
	struct srcu_node *snp;
	struct srcu_node *snp_first;

	/* Work out the overall tree geometry. */
	sp->level[0] = &sp->node[0];
	for (i = 1; i < rcu_num_lvls; i++)
		sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
	rcu_init_levelspread(levelspread, num_rcu_lvl);

	/* Each pass through this loop initializes one srcu_node structure. */
	rcu_for_each_node_breadth_first(sp, snp) {
		spin_lock_init(&snp->lock);
		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
			     ARRAY_SIZE(snp->srcu_data_have_cbs));
		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
			snp->srcu_have_cbs[i] = 0;
			snp->srcu_data_have_cbs[i] = 0;
		}
		snp->srcu_gp_seq_needed_exp = 0;
		snp->grplo = -1;
		snp->grphi = -1;
		if (snp == &sp->node[0]) {
			/* Root node, special case. */
			snp->srcu_parent = NULL;
			continue;
		}

		/* Non-root node. */
		if (snp == sp->level[level + 1])
			level++;
		snp->srcu_parent = sp->level[level - 1] +
				   (snp - sp->level[level]) /
				   levelspread[level - 1];
	}

	/*
	 * Initialize the per-CPU srcu_data array, which feeds into the
	 * leaves of the srcu_node tree.
	 */
	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
		     ARRAY_SIZE(sdp->srcu_unlock_count));
	level = rcu_num_lvls - 1;
	snp_first = sp->level[level];
	for_each_possible_cpu(cpu) {
		sdp = per_cpu_ptr(sp->sda, cpu);
		spin_lock_init(&sdp->lock);
		rcu_segcblist_init(&sdp->srcu_cblist);
		sdp->srcu_cblist_invoking = false;
		sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
		sdp->srcu_gp_seq_needed_exp = sp->srcu_gp_seq;
		sdp->mynode = &snp_first[cpu / levelspread[level]];
		for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
			if (snp->grplo < 0)
				snp->grplo = cpu;
			snp->grphi = cpu;
		}
		sdp->cpu = cpu;
		INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
		sdp->sp = sp;
		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
		if (is_static)
			continue;

		/* Dynamically allocated, better be no srcu_read_locks()! */
		for (i = 0; i < ARRAY_SIZE(sdp->srcu_lock_count); i++) {
			sdp->srcu_lock_count[i] = 0;
			sdp->srcu_unlock_count[i] = 0;
		}
	}
}

/*
 * Initialize non-compile-time initialized fields, including the
 * associated srcu_node and srcu_data structures.  The is_static
 * parameter is passed through to init_srcu_struct_nodes(), and
 * also tells us that ->sda has already been wired up to srcu_data.
 */
static int init_srcu_struct_fields(struct srcu_struct *sp, bool is_static)
{
	mutex_init(&sp->srcu_cb_mutex);
	mutex_init(&sp->srcu_gp_mutex);
	sp->srcu_idx = 0;
	sp->srcu_gp_seq = 0;
	sp->srcu_barrier_seq = 0;
	mutex_init(&sp->srcu_barrier_mutex);
	atomic_set(&sp->srcu_barrier_cpu_cnt, 0);
	INIT_DELAYED_WORK(&sp->work, process_srcu);
	if (!is_static)
		sp->sda = alloc_percpu(struct srcu_data);
	init_srcu_struct_nodes(sp, is_static);
	sp->srcu_gp_seq_needed_exp = 0;
	sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
	smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
	return sp->sda ? 0 : -ENOMEM;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC

int __init_srcu_struct(struct srcu_struct *sp, const char *name,
		       struct lock_class_key *key)
{
	/* Don't re-initialize a lock while it is held. */
	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
	lockdep_init_map(&sp->dep_map, name, key, 0);
	spin_lock_init(&sp->gp_lock);
	return init_srcu_struct_fields(sp, false);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/**
 * init_srcu_struct - initialize a sleep-RCU structure
 * @sp: structure to initialize.
 *
 * Must invoke this on a given srcu_struct before passing that srcu_struct
 * to any other function.  Each srcu_struct represents a separate domain
 * of SRCU protection.
 */
int init_srcu_struct(struct srcu_struct *sp)
{
	spin_lock_init(&sp->gp_lock);
	return init_srcu_struct_fields(sp, false);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/*
 * First-use initialization of statically allocated srcu_struct
 * structure.  Wiring up the combining tree is more than can be
 * done with compile-time initialization, so this check is added
 * to each update-side SRCU primitive.  Use ->gp_lock, which -is-
 * compile-time initialized, to resolve races involving multiple
 * CPUs trying to garner first-use privileges.
 */
static void check_init_srcu_struct(struct srcu_struct *sp)
{
	unsigned long flags;

	WARN_ON_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INIT);
	/* The smp_load_acquire() pairs with the smp_store_release(). */
	if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
		return; /* Already initialized. */
	spin_lock_irqsave(&sp->gp_lock, flags);
	if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
		spin_unlock_irqrestore(&sp->gp_lock, flags);
		return;
	}
	init_srcu_struct_fields(sp, true);
	spin_unlock_irqrestore(&sp->gp_lock, flags);
}

/*
 * Returns approximate total of the readers' ->srcu_lock_count[] values
 * for the rank of per-CPU counters specified by idx.
 */
static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
{
	int cpu;
	unsigned long sum = 0;

	for_each_possible_cpu(cpu) {
		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);

		sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
	}
	return sum;
}

/*
 * Returns approximate total of the readers' ->srcu_unlock_count[] values
 * for the rank of per-CPU counters specified by idx.
 */
static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
{
	int cpu;
	unsigned long sum = 0;

	for_each_possible_cpu(cpu) {
		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);

		sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
	}
	return sum;
}

/*
 * Return true if the number of pre-existing readers is determined to
 * be zero.
 */
static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
{
	unsigned long unlocks;

	unlocks = srcu_readers_unlock_idx(sp, idx);

	/*
	 * Make sure that a lock is always counted if the corresponding
	 * unlock is counted. Needs to be a smp_mb() as the read side may
	 * contain a read from a variable that is written to before the
	 * synchronize_srcu() in the write side. In this case smp_mb()s
	 * A and B act like the store buffering pattern.
	 *
	 * This smp_mb() also pairs with smp_mb() C to prevent accesses
	 * after the synchronize_srcu() from being executed before the
	 * grace period ends.
	 */
	smp_mb(); /* A */

	/*
	 * If the locks are the same as the unlocks, then there must have
	 * been no readers on this index at some time in between. This does
	 * not mean that there are no more readers, as one could have read
	 * the current index but not have incremented the lock counter yet.
	 *
	 * So suppose that the updater is preempted here for so long
	 * that more than ULONG_MAX non-nested readers come and go in
	 * the meantime.  It turns out that this cannot result in overflow
	 * because if a reader modifies its unlock count after we read it
	 * above, then that reader's next load of ->srcu_idx is guaranteed
	 * to get the new value, which will cause it to operate on the
	 * other bank of counters, where it cannot contribute to the
	 * overflow of these counters.  This means that there is a maximum
	 * of 2*NR_CPUS increments, which cannot overflow given current
	 * systems, especially not on 64-bit systems.
	 *
	 * OK, how about nesting?  This does impose a limit on nesting
	 * of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient,
	 * especially on 64-bit systems.
	 */
	return srcu_readers_lock_idx(sp, idx) == unlocks;
}

/**
 * srcu_readers_active - returns true if there are readers. and false
 *                       otherwise
 * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
 *
 * Note that this is not an atomic primitive, and can therefore suffer
 * severe errors when invoked on an active srcu_struct.  That said, it
 * can be useful as an error check at cleanup time.
 */
static bool srcu_readers_active(struct srcu_struct *sp)
{
	int cpu;
	unsigned long sum = 0;

	for_each_possible_cpu(cpu) {
		struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);

		sum += READ_ONCE(cpuc->srcu_lock_count[0]);
		sum += READ_ONCE(cpuc->srcu_lock_count[1]);
		sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
		sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
	}
	return sum;
}

#define SRCU_INTERVAL		1

/*
 * Return grace-period delay, zero if there are expedited grace
 * periods pending, SRCU_INTERVAL otherwise.
 */
static unsigned long srcu_get_delay(struct srcu_struct *sp)
{
	if (ULONG_CMP_LT(READ_ONCE(sp->srcu_gp_seq),
			 READ_ONCE(sp->srcu_gp_seq_needed_exp)))
		return 0;
	return SRCU_INTERVAL;
}

/**
 * cleanup_srcu_struct - deconstruct a sleep-RCU structure
 * @sp: structure to clean up.
 *
 * Must invoke this after you are finished using a given srcu_struct that
 * was initialized via init_srcu_struct(), else you leak memory.
 */
void cleanup_srcu_struct(struct srcu_struct *sp)
{
	int cpu;

	if (WARN_ON(!srcu_get_delay(sp)))
		return; /* Leakage unless caller handles error. */
	if (WARN_ON(srcu_readers_active(sp)))
		return; /* Leakage unless caller handles error. */
	flush_delayed_work(&sp->work);
	for_each_possible_cpu(cpu)
		flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
	    WARN_ON(srcu_readers_active(sp))) {
		pr_info("cleanup_srcu_struct: Active srcu_struct %p state: %d\n", sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
		return; /* Caller forgot to stop doing call_srcu()? */
	}
	free_percpu(sp->sda);
	sp->sda = NULL;
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);

/*
 * Counts the new reader in the appropriate per-CPU element of the
 * srcu_struct.
 * Returns an index that must be passed to the matching srcu_read_unlock().
 */
int __srcu_read_lock(struct srcu_struct *sp)
{
	int idx;

	idx = READ_ONCE(sp->srcu_idx) & 0x1;
	this_cpu_inc(sp->sda->srcu_lock_count[idx]);
	smp_mb(); /* B */  /* Avoid leaking the critical section. */
	return idx;
}
EXPORT_SYMBOL_GPL(__srcu_read_lock);

/*
 * Removes the count for the old reader from the appropriate per-CPU
 * element of the srcu_struct.  Note that this may well be a different
 * CPU than that which was incremented by the corresponding srcu_read_lock().
 */
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
	smp_mb(); /* C */  /* Avoid leaking the critical section. */
	this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);

/*
 * We use an adaptive strategy for synchronize_srcu() and especially for
 * synchronize_srcu_expedited().  We spin for a fixed time period
 * (defined below) to allow SRCU readers to exit their read-side critical
 * sections.  If there are still some readers after a few microseconds,
 * we repeatedly block for 1-millisecond time periods.
 */
#define SRCU_RETRY_CHECK_DELAY		5

/*
 * Start an SRCU grace period.
 */
static void srcu_gp_start(struct srcu_struct *sp)
{
	struct srcu_data *sdp = this_cpu_ptr(sp->sda);
	int state;

	RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock),
			 "Invoked srcu_gp_start() without ->gp_lock!");
	WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
	rcu_segcblist_advance(&sdp->srcu_cblist,
			      rcu_seq_current(&sp->srcu_gp_seq));
	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
				       rcu_seq_snap(&sp->srcu_gp_seq));
	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
	rcu_seq_start(&sp->srcu_gp_seq);
	state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}

/*
 * Track online CPUs to guide callback workqueue placement.
 */
DEFINE_PER_CPU(bool, srcu_online);

void srcu_online_cpu(unsigned int cpu)
{
	WRITE_ONCE(per_cpu(srcu_online, cpu), true);
}

void srcu_offline_cpu(unsigned int cpu)
{
	WRITE_ONCE(per_cpu(srcu_online, cpu), false);
}

/*
 * Place the workqueue handler on the specified CPU if online, otherwise
 * just run it whereever.  This is useful for placing workqueue handlers
 * that are to invoke the specified CPU's callbacks.
 */
static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
				       struct delayed_work *dwork,
				       unsigned long delay)
{
	bool ret;

	preempt_disable();
	if (READ_ONCE(per_cpu(srcu_online, cpu)))
		ret = queue_delayed_work_on(cpu, wq, dwork, delay);
	else
		ret = queue_delayed_work(wq, dwork, delay);
	preempt_enable();
	return ret;
}

/*
 * Schedule callback invocation for the specified srcu_data structure,
 * if possible, on the corresponding CPU.
 */
static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
{
	srcu_queue_delayed_work_on(sdp->cpu, system_power_efficient_wq,
				   &sdp->work, delay);
}

/*
 * Schedule callback invocation for all srcu_data structures associated
 * with the specified srcu_node structure that have callbacks for the
 * just-completed grace period, the one corresponding to idx.  If possible,
 * schedule this invocation on the corresponding CPUs.
 */
static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
				  unsigned long mask, unsigned long delay)
{
	int cpu;

	for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
		if (!(mask & (1 << (cpu - snp->grplo))))
			continue;
		srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu), delay);
	}
}

/*
 * Note the end of an SRCU grace period.  Initiates callback invocation
 * and starts a new grace period if needed.
 *
 * The ->srcu_cb_mutex acquisition does not protect any data, but
 * instead prevents more than one grace period from starting while we
 * are initiating callback invocation.  This allows the ->srcu_have_cbs[]
 * array to have a finite number of elements.
 */
static void srcu_gp_end(struct srcu_struct *sp)
{
	unsigned long cbdelay;
	bool cbs;
	int cpu;
	unsigned long flags;
	unsigned long gpseq;
	int idx;
	int idxnext;
	unsigned long mask;
	struct srcu_data *sdp;
	struct srcu_node *snp;

	/* Prevent more than one additional grace period. */
	mutex_lock(&sp->srcu_cb_mutex);

	/* End the current grace period. */
	spin_lock_irq(&sp->gp_lock);
	idx = rcu_seq_state(sp->srcu_gp_seq);
	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
	cbdelay = srcu_get_delay(sp);
	sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
	rcu_seq_end(&sp->srcu_gp_seq);
	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
		sp->srcu_gp_seq_needed_exp = gpseq;
	spin_unlock_irq(&sp->gp_lock);
	mutex_unlock(&sp->srcu_gp_mutex);
	/* A new grace period can start at this point.  But only one. */

	/* Initiate callback invocation as needed. */
	idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
	idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
	rcu_for_each_node_breadth_first(sp, snp) {
		spin_lock_irq(&snp->lock);
		cbs = false;
		if (snp >= sp->level[rcu_num_lvls - 1])
			cbs = snp->srcu_have_cbs[idx] == gpseq;
		snp->srcu_have_cbs[idx] = gpseq;
		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
		if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
			snp->srcu_gp_seq_needed_exp = gpseq;
		mask = snp->srcu_data_have_cbs[idx];
		snp->srcu_data_have_cbs[idx] = 0;
		spin_unlock_irq(&snp->lock);
		if (cbs) {
			smp_mb(); /* GP end before CB invocation. */
			srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
		}

		/* Occasionally prevent srcu_data counter wrap. */
		if (!(gpseq & counter_wrap_check))
			for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
				sdp = per_cpu_ptr(sp->sda, cpu);
				spin_lock_irqsave(&sdp->lock, flags);
				if (ULONG_CMP_GE(gpseq,
						 sdp->srcu_gp_seq_needed + 100))
					sdp->srcu_gp_seq_needed = gpseq;
				spin_unlock_irqrestore(&sdp->lock, flags);
			}
	}

	/* Callback initiation done, allow grace periods after next. */
	mutex_unlock(&sp->srcu_cb_mutex);

	/* Start a new grace period if needed. */
	spin_lock_irq(&sp->gp_lock);
	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
	if (!rcu_seq_state(gpseq) &&
	    ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
		srcu_gp_start(sp);
		spin_unlock_irq(&sp->gp_lock);
		/* Throttle expedited grace periods: Should be rare! */
		srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff
				    ? 0 : SRCU_INTERVAL);
	} else {
		spin_unlock_irq(&sp->gp_lock);
	}
}

/*
 * Funnel-locking scheme to scalably mediate many concurrent expedited
 * grace-period requests.  This function is invoked for the first known
 * expedited request for a grace period that has already been requested,
 * but without expediting.  To start a completely new grace period,
 * whether expedited or not, use srcu_funnel_gp_start() instead.
 */
static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
				  unsigned long s)
{
	unsigned long flags;

	for (; snp != NULL; snp = snp->srcu_parent) {
		if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
		    ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
			return;
		spin_lock_irqsave(&snp->lock, flags);
		if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
			spin_unlock_irqrestore(&snp->lock, flags);
			return;
		}
		WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
		spin_unlock_irqrestore(&snp->lock, flags);
	}
	spin_lock_irqsave(&sp->gp_lock, flags);
	if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
		sp->srcu_gp_seq_needed_exp = s;
	spin_unlock_irqrestore(&sp->gp_lock, flags);
}

/*
 * Funnel-locking scheme to scalably mediate many concurrent grace-period
 * requests.  The winner has to do the work of actually starting grace
 * period s.  Losers must either ensure that their desired grace-period
 * number is recorded on at least their leaf srcu_node structure, or they
 * must take steps to invoke their own callbacks.
 */
static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
				 unsigned long s, bool do_norm)
{
	unsigned long flags;
	int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
	struct srcu_node *snp = sdp->mynode;
	unsigned long snp_seq;

	/* Each pass through the loop does one level of the srcu_node tree. */
	for (; snp != NULL; snp = snp->srcu_parent) {
		if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
			return; /* GP already done and CBs recorded. */
		spin_lock_irqsave(&snp->lock, flags);
		if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
			snp_seq = snp->srcu_have_cbs[idx];
			if (snp == sdp->mynode && snp_seq == s)
				snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
			spin_unlock_irqrestore(&snp->lock, flags);
			if (snp == sdp->mynode && snp_seq != s) {
				smp_mb(); /* CBs after GP! */
				srcu_schedule_cbs_sdp(sdp, do_norm
							   ? SRCU_INTERVAL
							   : 0);
				return;
			}
			if (!do_norm)
				srcu_funnel_exp_start(sp, snp, s);
			return;
		}
		snp->srcu_have_cbs[idx] = s;
		if (snp == sdp->mynode)
			snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
		if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
			snp->srcu_gp_seq_needed_exp = s;
		spin_unlock_irqrestore(&snp->lock, flags);
	}

	/* Top of tree, must ensure the grace period will be started. */
	spin_lock_irqsave(&sp->gp_lock, flags);
	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
		/*
		 * Record need for grace period s.  Pair with load
		 * acquire setting up for initialization.
		 */
		smp_store_release(&sp->srcu_gp_seq_needed, s); /*^^^*/
	}
	if (!do_norm && ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
		sp->srcu_gp_seq_needed_exp = s;

	/* If grace period not already done and none in progress, start it. */
	if (!rcu_seq_done(&sp->srcu_gp_seq, s) &&
	    rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
		WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
		srcu_gp_start(sp);
		queue_delayed_work(system_power_efficient_wq, &sp->work,
				   srcu_get_delay(sp));
	}
	spin_unlock_irqrestore(&sp->gp_lock, flags);
}

/*
 * Wait until all readers counted by array index idx complete, but
 * loop an additional time if there is an expedited grace period pending.
 * The caller must ensure that ->srcu_idx is not changed while checking.
 */
static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
{
	for (;;) {
		if (srcu_readers_active_idx_check(sp, idx))
			return true;
		if (--trycount + !srcu_get_delay(sp) <= 0)
			return false;
		udelay(SRCU_RETRY_CHECK_DELAY);
	}
}

/*
 * Increment the ->srcu_idx counter so that future SRCU readers will
 * use the other rank of the ->srcu_(un)lock_count[] arrays.  This allows
 * us to wait for pre-existing readers in a starvation-free manner.
 */
static void srcu_flip(struct srcu_struct *sp)
{
	/*
	 * Ensure that if this updater saw a given reader's increment
	 * from __srcu_read_lock(), that reader was using an old value
	 * of ->srcu_idx.  Also ensure that if a given reader sees the
	 * new value of ->srcu_idx, this updater's earlier scans cannot
	 * have seen that reader's increments (which is OK, because this
	 * grace period need not wait on that reader).
	 */
	smp_mb(); /* E */  /* Pairs with B and C. */

	WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);

	/*
	 * Ensure that if the updater misses an __srcu_read_unlock()
	 * increment, that task's next __srcu_read_lock() will see the
	 * above counter update.  Note that both this memory barrier
	 * and the one in srcu_readers_active_idx_check() provide the
	 * guarantee for __srcu_read_lock().
	 */
	smp_mb(); /* D */  /* Pairs with C. */
}

/*
 * If SRCU is likely idle, return true, otherwise return false.
 *
 * Note that it is OK for several current from-idle requests for a new
 * grace period from idle to specify expediting because they will all end
 * up requesting the same grace period anyhow.  So no loss.
 *
 * Note also that if any CPU (including the current one) is still invoking
 * callbacks, this function will nevertheless say "idle".  This is not
 * ideal, but the overhead of checking all CPUs' callback lists is even
 * less ideal, especially on large systems.  Furthermore, the wakeup
 * can happen before the callback is fully removed, so we have no choice
 * but to accept this type of error.
 *
 * This function is also subject to counter-wrap errors, but let's face
 * it, if this function was preempted for enough time for the counters
 * to wrap, it really doesn't matter whether or not we expedite the grace
 * period.  The extra overhead of a needlessly expedited grace period is
 * negligible when amoritized over that time period, and the extra latency
 * of a needlessly non-expedited grace period is similarly negligible.
 */
static bool srcu_might_be_idle(struct srcu_struct *sp)
{
	unsigned long curseq;
	unsigned long flags;
	struct srcu_data *sdp;
	unsigned long t;

	/* If the local srcu_data structure has callbacks, not idle.  */
	local_irq_save(flags);
	sdp = this_cpu_ptr(sp->sda);
	if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
		local_irq_restore(flags);
		return false; /* Callbacks already present, so not idle. */
	}
	local_irq_restore(flags);

	/*
	 * No local callbacks, so probabalistically probe global state.
	 * Exact information would require acquiring locks, which would
	 * kill scalability, hence the probabalistic nature of the probe.
	 */

	/* First, see if enough time has passed since the last GP. */
	t = ktime_get_mono_fast_ns();
	if (exp_holdoff == 0 ||
	    time_in_range_open(t, sp->srcu_last_gp_end,
			       sp->srcu_last_gp_end + exp_holdoff))
		return false; /* Too soon after last GP. */

	/* Next, check for probable idleness. */
	curseq = rcu_seq_current(&sp->srcu_gp_seq);
	smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
	if (ULONG_CMP_LT(curseq, READ_ONCE(sp->srcu_gp_seq_needed)))
		return false; /* Grace period in progress, so not idle. */
	smp_mb(); /* Order ->srcu_gp_seq with prior access. */
	if (curseq != rcu_seq_current(&sp->srcu_gp_seq))
		return false; /* GP # changed, so not idle. */
	return true; /* With reasonable probability, idle! */
}

/*
 * SRCU callback function to leak a callback.
 */
static void srcu_leak_callback(struct rcu_head *rhp)
{
}

/*
 * Enqueue an SRCU callback on the srcu_data structure associated with
 * the current CPU and the specified srcu_struct structure, initiating
 * grace-period processing if it is not already running.
 *
 * Note that all CPUs must agree that the grace period extended beyond
 * all pre-existing SRCU read-side critical section.  On systems with
 * more than one CPU, this means that when "func()" is invoked, each CPU
 * is guaranteed to have executed a full memory barrier since the end of
 * its last corresponding SRCU read-side critical section whose beginning
 * preceded the call to call_rcu().  It also means that each CPU executing
 * an SRCU read-side critical section that continues beyond the start of
 * "func()" must have executed a memory barrier after the call_rcu()
 * but before the beginning of that SRCU read-side critical section.
 * Note that these guarantees include CPUs that are offline, idle, or
 * executing in user mode, as well as CPUs that are executing in the kernel.
 *
 * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
 * resulting SRCU callback function "func()", then both CPU A and CPU
 * B are guaranteed to execute a full memory barrier during the time
 * interval between the call to call_rcu() and the invocation of "func()".
 * This guarantee applies even if CPU A and CPU B are the same CPU (but
 * again only if the system has more than one CPU).
 *
 * Of course, these guarantees apply only for invocations of call_srcu(),
 * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
 * srcu_struct structure.
 */
void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
		 rcu_callback_t func, bool do_norm)
{
	unsigned long flags;
	bool needexp = false;
	bool needgp = false;
	unsigned long s;
	struct srcu_data *sdp;

	check_init_srcu_struct(sp);
	if (debug_rcu_head_queue(rhp)) {
		/* Probable double call_srcu(), so leak the callback. */
		WRITE_ONCE(rhp->func, srcu_leak_callback);
		WARN_ONCE(1, "call_srcu(): Leaked duplicate callback\n");
		return;
	}
	rhp->func = func;
	local_irq_save(flags);
	sdp = this_cpu_ptr(sp->sda);
	spin_lock(&sdp->lock);
	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
	rcu_segcblist_advance(&sdp->srcu_cblist,
			      rcu_seq_current(&sp->srcu_gp_seq));
	s = rcu_seq_snap(&sp->srcu_gp_seq);
	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
		sdp->srcu_gp_seq_needed = s;
		needgp = true;
	}
	if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
		sdp->srcu_gp_seq_needed_exp = s;
		needexp = true;
	}
	spin_unlock_irqrestore(&sdp->lock, flags);
	if (needgp)
		srcu_funnel_gp_start(sp, sdp, s, do_norm);
	else if (needexp)
		srcu_funnel_exp_start(sp, sdp->mynode, s);
}

/**
 * call_srcu() - Queue a callback for invocation after an SRCU grace period
 * @sp: srcu_struct in queue the callback
 * @head: structure to be used for queueing the SRCU callback.
 * @func: function to be invoked after the SRCU grace period
 *
 * The callback function will be invoked some time after a full SRCU
 * grace period elapses, in other words after all pre-existing SRCU
 * read-side critical sections have completed.  However, the callback
 * function might well execute concurrently with other SRCU read-side
 * critical sections that started after call_srcu() was invoked.  SRCU
 * read-side critical sections are delimited by srcu_read_lock() and
 * srcu_read_unlock(), and may be nested.
 *
 * The callback will be invoked from process context, but must nevertheless
 * be fast and must not block.
 */
void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
	       rcu_callback_t func)
{
	__call_srcu(sp, rhp, func, true);
}
EXPORT_SYMBOL_GPL(call_srcu);

/*
 * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
 */
static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
{
	struct rcu_synchronize rcu;

	RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
			 lock_is_held(&rcu_bh_lock_map) ||
			 lock_is_held(&rcu_lock_map) ||
			 lock_is_held(&rcu_sched_lock_map),
			 "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section");

	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
		return;
	might_sleep();
	check_init_srcu_struct(sp);
	init_completion(&rcu.completion);
	init_rcu_head_on_stack(&rcu.head);
	__call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
	wait_for_completion(&rcu.completion);
	destroy_rcu_head_on_stack(&rcu.head);
}

/**
 * synchronize_srcu_expedited - Brute-force SRCU grace period
 * @sp: srcu_struct with which to synchronize.
 *
 * Wait for an SRCU grace period to elapse, but be more aggressive about
 * spinning rather than blocking when waiting.
 *
 * Note that synchronize_srcu_expedited() has the same deadlock and
 * memory-ordering properties as does synchronize_srcu().
 */
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
	__synchronize_srcu(sp, rcu_gp_is_normal());
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);

/**
 * synchronize_srcu - wait for prior SRCU read-side critical-section completion
 * @sp: srcu_struct with which to synchronize.
 *
 * Wait for the count to drain to zero of both indexes. To avoid the
 * possible starvation of synchronize_srcu(), it waits for the count of
 * the index=((->srcu_idx & 1) ^ 1) to drain to zero at first,
 * and then flip the srcu_idx and wait for the count of the other index.
 *
 * Can block; must be called from process context.
 *
 * Note that it is illegal to call synchronize_srcu() from the corresponding
 * SRCU read-side critical section; doing so will result in deadlock.
 * However, it is perfectly legal to call synchronize_srcu() on one
 * srcu_struct from some other srcu_struct's read-side critical section,
 * as long as the resulting graph of srcu_structs is acyclic.
 *
 * There are memory-ordering constraints implied by synchronize_srcu().
 * On systems with more than one CPU, when synchronize_srcu() returns,
 * each CPU is guaranteed to have executed a full memory barrier since
 * the end of its last corresponding SRCU-sched read-side critical section
 * whose beginning preceded the call to synchronize_srcu().  In addition,
 * each CPU having an SRCU read-side critical section that extends beyond
 * the return from synchronize_srcu() is guaranteed to have executed a
 * full memory barrier after the beginning of synchronize_srcu() and before
 * the beginning of that SRCU read-side critical section.  Note that these
 * guarantees include CPUs that are offline, idle, or executing in user mode,
 * as well as CPUs that are executing in the kernel.
 *
 * Furthermore, if CPU A invoked synchronize_srcu(), which returned
 * to its caller on CPU B, then both CPU A and CPU B are guaranteed
 * to have executed a full memory barrier during the execution of
 * synchronize_srcu().  This guarantee applies even if CPU A and CPU B
 * are the same CPU, but again only if the system has more than one CPU.
 *
 * Of course, these memory-ordering guarantees apply only when
 * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
 * passed the same srcu_struct structure.
 *
 * If SRCU is likely idle, expedite the first request.  This semantic
 * was provided by Classic SRCU, and is relied upon by its users, so TREE
 * SRCU must also provide it.  Note that detecting idleness is heuristic
 * and subject to both false positives and negatives.
 */
void synchronize_srcu(struct srcu_struct *sp)
{
	if (srcu_might_be_idle(sp) || rcu_gp_is_expedited())
		synchronize_srcu_expedited(sp);
	else
		__synchronize_srcu(sp, true);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);

/*
 * Callback function for srcu_barrier() use.
 */
static void srcu_barrier_cb(struct rcu_head *rhp)
{
	struct srcu_data *sdp;
	struct srcu_struct *sp;

	sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
	sp = sdp->sp;
	if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
		complete(&sp->srcu_barrier_completion);
}

/**
 * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
 * @sp: srcu_struct on which to wait for in-flight callbacks.
 */
void srcu_barrier(struct srcu_struct *sp)
{
	int cpu;
	struct srcu_data *sdp;
	unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);

	check_init_srcu_struct(sp);
	mutex_lock(&sp->srcu_barrier_mutex);
	if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
		smp_mb(); /* Force ordering following return. */
		mutex_unlock(&sp->srcu_barrier_mutex);
		return; /* Someone else did our work for us. */
	}
	rcu_seq_start(&sp->srcu_barrier_seq);
	init_completion(&sp->srcu_barrier_completion);

	/* Initial count prevents reaching zero until all CBs are posted. */
	atomic_set(&sp->srcu_barrier_cpu_cnt, 1);

	/*
	 * Each pass through this loop enqueues a callback, but only
	 * on CPUs already having callbacks enqueued.  Note that if
	 * a CPU already has callbacks enqueue, it must have already
	 * registered the need for a future grace period, so all we
	 * need do is enqueue a callback that will use the same
	 * grace period as the last callback already in the queue.
	 */
	for_each_possible_cpu(cpu) {
		sdp = per_cpu_ptr(sp->sda, cpu);
		spin_lock_irq(&sdp->lock);
		atomic_inc(&sp->srcu_barrier_cpu_cnt);
		sdp->srcu_barrier_head.func = srcu_barrier_cb;
		debug_rcu_head_queue(&sdp->srcu_barrier_head);
		if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
					   &sdp->srcu_barrier_head, 0)) {
			debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
			atomic_dec(&sp->srcu_barrier_cpu_cnt);
		}
		spin_unlock_irq(&sdp->lock);
	}

	/* Remove the initial count, at which point reaching zero can happen. */
	if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
		complete(&sp->srcu_barrier_completion);
	wait_for_completion(&sp->srcu_barrier_completion);

	rcu_seq_end(&sp->srcu_barrier_seq);
	mutex_unlock(&sp->srcu_barrier_mutex);
}
EXPORT_SYMBOL_GPL(srcu_barrier);

/**
 * srcu_batches_completed - return batches completed.
 * @sp: srcu_struct on which to report batch completion.
 *
 * Report the number of batches, correlated with, but not necessarily
 * precisely the same as, the number of grace periods that have elapsed.
 */
unsigned long srcu_batches_completed(struct srcu_struct *sp)
{
	return sp->srcu_idx;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);

/*
 * Core SRCU state machine.  Push state bits of ->srcu_gp_seq
 * to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
 * completed in that state.
 */
static void srcu_advance_state(struct srcu_struct *sp)
{
	int idx;

	mutex_lock(&sp->srcu_gp_mutex);

	/*
	 * Because readers might be delayed for an extended period after
	 * fetching ->srcu_idx for their index, at any point in time there
	 * might well be readers using both idx=0 and idx=1.  We therefore
	 * need to wait for readers to clear from both index values before
	 * invoking a callback.
	 *
	 * The load-acquire ensures that we see the accesses performed
	 * by the prior grace period.
	 */
	idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
	if (idx == SRCU_STATE_IDLE) {
		spin_lock_irq(&sp->gp_lock);
		if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
			WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
			spin_unlock_irq(&sp->gp_lock);
			mutex_unlock(&sp->srcu_gp_mutex);
			return;
		}
		idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
		if (idx == SRCU_STATE_IDLE)
			srcu_gp_start(sp);
		spin_unlock_irq(&sp->gp_lock);
		if (idx != SRCU_STATE_IDLE) {
			mutex_unlock(&sp->srcu_gp_mutex);
			return; /* Someone else started the grace period. */
		}
	}

	if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
		idx = 1 ^ (sp->srcu_idx & 1);
		if (!try_check_zero(sp, idx, 1)) {
			mutex_unlock(&sp->srcu_gp_mutex);
			return; /* readers present, retry later. */
		}
		srcu_flip(sp);
		rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
	}

	if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {

		/*
		 * SRCU read-side critical sections are normally short,
		 * so check at least twice in quick succession after a flip.
		 */
		idx = 1 ^ (sp->srcu_idx & 1);
		if (!try_check_zero(sp, idx, 2)) {
			mutex_unlock(&sp->srcu_gp_mutex);
			return; /* readers present, retry later. */
		}
		srcu_gp_end(sp);  /* Releases ->srcu_gp_mutex. */
	}
}

/*
 * Invoke a limited number of SRCU callbacks that have passed through
 * their grace period.  If there are more to do, SRCU will reschedule
 * the workqueue.  Note that needed memory barriers have been executed
 * in this task's context by srcu_readers_active_idx_check().
 */
static void srcu_invoke_callbacks(struct work_struct *work)
{
	bool more;
	struct rcu_cblist ready_cbs;
	struct rcu_head *rhp;
	struct srcu_data *sdp;
	struct srcu_struct *sp;

	sdp = container_of(work, struct srcu_data, work.work);
	sp = sdp->sp;
	rcu_cblist_init(&ready_cbs);
	spin_lock_irq(&sdp->lock);
	smp_mb(); /* Old grace periods before callback invocation! */
	rcu_segcblist_advance(&sdp->srcu_cblist,
			      rcu_seq_current(&sp->srcu_gp_seq));
	if (sdp->srcu_cblist_invoking ||
	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
		spin_unlock_irq(&sdp->lock);
		return;  /* Someone else on the job or nothing to do. */
	}

	/* We are on the job!  Extract and invoke ready callbacks. */
	sdp->srcu_cblist_invoking = true;
	rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
	spin_unlock_irq(&sdp->lock);
	rhp = rcu_cblist_dequeue(&ready_cbs);
	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
		debug_rcu_head_unqueue(rhp);
		local_bh_disable();
		rhp->func(rhp);
		local_bh_enable();
	}

	/*
	 * Update counts, accelerate new callbacks, and if needed,
	 * schedule another round of callback invocation.
	 */
	spin_lock_irq(&sdp->lock);
	rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
				       rcu_seq_snap(&sp->srcu_gp_seq));
	sdp->srcu_cblist_invoking = false;
	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
	spin_unlock_irq(&sdp->lock);
	if (more)
		srcu_schedule_cbs_sdp(sdp, 0);
}

/*
 * Finished one round of SRCU grace period.  Start another if there are
 * more SRCU callbacks queued, otherwise put SRCU into not-running state.
 */
static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
{
	bool pushgp = true;

	spin_lock_irq(&sp->gp_lock);
	if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
		if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
			/* All requests fulfilled, time to go idle. */
			pushgp = false;
		}
	} else if (!rcu_seq_state(sp->srcu_gp_seq)) {
		/* Outstanding request and no GP.  Start one. */
		srcu_gp_start(sp);
	}
	spin_unlock_irq(&sp->gp_lock);

	if (pushgp)
		queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
}

/*
 * This is the work-queue function that handles SRCU grace periods.
 */
void process_srcu(struct work_struct *work)
{
	struct srcu_struct *sp;

	sp = container_of(work, struct srcu_struct, work.work);

	srcu_advance_state(sp);
	srcu_reschedule(sp, srcu_get_delay(sp));
}
EXPORT_SYMBOL_GPL(process_srcu);

void srcutorture_get_gp_data(enum rcutorture_type test_type,
			     struct srcu_struct *sp, int *flags,
			     unsigned long *gpnum, unsigned long *completed)
{
	if (test_type != SRCU_FLAVOR)
		return;
	*flags = 0;
	*completed = rcu_seq_ctr(sp->srcu_gp_seq);
	*gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
}
EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);

static int __init srcu_bootup_announce(void)
{
	pr_info("Hierarchical SRCU implementation.\n");
	if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF)
		pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff);
	return 0;
}
early_initcall(srcu_bootup_announce);
OpenPOWER on IntegriCloud