aboutsummaryrefslogtreecommitdiff
path: root/kernel/rcutree_plugin.h
blob: a82566696b0b55ab2433507e824374a124139a30 (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
/*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * Internal non-public definitions that provide either classic
 * or preemptable semantics.
 *
 * 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 Red Hat, 2009
 * Copyright IBM Corporation, 2009
 *
 * Author: Ingo Molnar <mingo@elte.hu>
 *	   Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 */

#include <linux/delay.h>

#ifdef CONFIG_TREE_PREEMPT_RCU

struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);

static int rcu_preempted_readers_exp(struct rcu_node *rnp);

/*
 * Tell them what RCU they are running.
 */
static void __init rcu_bootup_announce(void)
{
	printk(KERN_INFO
	       "Experimental preemptable hierarchical RCU implementation.\n");
}

/*
 * Return the number of RCU-preempt batches processed thus far
 * for debug and statistics.
 */
long rcu_batches_completed_preempt(void)
{
	return rcu_preempt_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);

/*
 * Return the number of RCU batches processed thus far for debug & stats.
 */
long rcu_batches_completed(void)
{
	return rcu_batches_completed_preempt();
}
EXPORT_SYMBOL_GPL(rcu_batches_completed);

/*
 * Force a quiescent state for preemptible RCU.
 */
void rcu_force_quiescent_state(void)
{
	force_quiescent_state(&rcu_preempt_state, 0);
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);

/*
 * Record a preemptable-RCU quiescent state for the specified CPU.  Note
 * that this just means that the task currently running on the CPU is
 * not in a quiescent state.  There might be any number of tasks blocked
 * while in an RCU read-side critical section.
 */
static void rcu_preempt_qs(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
	rdp->passed_quiesc_completed = rdp->gpnum - 1;
	barrier();
	rdp->passed_quiesc = 1;
}

/*
 * We have entered the scheduler, and the current task might soon be
 * context-switched away from.  If this task is in an RCU read-side
 * critical section, we will no longer be able to rely on the CPU to
 * record that fact, so we enqueue the task on the appropriate entry
 * of the blocked_tasks[] array.  The task will dequeue itself when
 * it exits the outermost enclosing RCU read-side critical section.
 * Therefore, the current grace period cannot be permitted to complete
 * until the blocked_tasks[] entry indexed by the low-order bit of
 * rnp->gpnum empties.
 *
 * Caller must disable preemption.
 */
static void rcu_preempt_note_context_switch(int cpu)
{
	struct task_struct *t = current;
	unsigned long flags;
	int phase;
	struct rcu_data *rdp;
	struct rcu_node *rnp;

	if (t->rcu_read_lock_nesting &&
	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {

		/* Possibly blocking in an RCU read-side critical section. */
		rdp = rcu_preempt_state.rda[cpu];
		rnp = rdp->mynode;
		spin_lock_irqsave(&rnp->lock, flags);
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
		t->rcu_blocked_node = rnp;

		/*
		 * If this CPU has already checked in, then this task
		 * will hold up the next grace period rather than the
		 * current grace period.  Queue the task accordingly.
		 * If the task is queued for the current grace period
		 * (i.e., this CPU has not yet passed through a quiescent
		 * state for the current grace period), then as long
		 * as that task remains queued, the current grace period
		 * cannot end.
		 *
		 * But first, note that the current CPU must still be
		 * on line!
		 */
		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
		phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
		spin_unlock_irqrestore(&rnp->lock, flags);
	}

	/*
	 * Either we were not in an RCU read-side critical section to
	 * begin with, or we have now recorded that critical section
	 * globally.  Either way, we can now note a quiescent state
	 * for this CPU.  Again, if we were in an RCU read-side critical
	 * section, and if that critical section was blocking the current
	 * grace period, then the fact that the task has been enqueued
	 * means that we continue to block the current grace period.
	 */
	rcu_preempt_qs(cpu);
	local_irq_save(flags);
	t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
	local_irq_restore(flags);
}

/*
 * Tree-preemptable RCU implementation for rcu_read_lock().
 * Just increment ->rcu_read_lock_nesting, shared state will be updated
 * if we block.
 */
void __rcu_read_lock(void)
{
	ACCESS_ONCE(current->rcu_read_lock_nesting)++;
	barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);

/*
 * Check for preempted RCU readers blocking the current grace period
 * for the specified rcu_node structure.  If the caller needs a reliable
 * answer, it must hold the rcu_node's ->lock.
 */
static int rcu_preempted_readers(struct rcu_node *rnp)
{
	int phase = rnp->gpnum & 0x1;

	return !list_empty(&rnp->blocked_tasks[phase]) ||
	       !list_empty(&rnp->blocked_tasks[phase + 2]);
}

/*
 * Record a quiescent state for all tasks that were previously queued
 * on the specified rcu_node structure and that were blocking the current
 * RCU grace period.  The caller must hold the specified rnp->lock with
 * irqs disabled, and this lock is released upon return, but irqs remain
 * disabled.
 */
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
	__releases(rnp->lock)
{
	unsigned long mask;
	struct rcu_node *rnp_p;

	if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
		spin_unlock_irqrestore(&rnp->lock, flags);
		return;  /* Still need more quiescent states! */
	}

	rnp_p = rnp->parent;
	if (rnp_p == NULL) {
		/*
		 * Either there is only one rcu_node in the tree,
		 * or tasks were kicked up to root rcu_node due to
		 * CPUs going offline.
		 */
		rcu_report_qs_rsp(&rcu_preempt_state, flags);
		return;
	}

	/* Report up the rest of the hierarchy. */
	mask = rnp->grpmask;
	spin_unlock(&rnp->lock);	/* irqs remain disabled. */
	spin_lock(&rnp_p->lock);	/* irqs already disabled. */
	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
}

/*
 * Handle special cases during rcu_read_unlock(), such as needing to
 * notify RCU core processing or task having blocked during the RCU
 * read-side critical section.
 */
static void rcu_read_unlock_special(struct task_struct *t)
{
	int empty;
	int empty_exp;
	unsigned long flags;
	struct rcu_node *rnp;
	int special;

	/* NMI handlers cannot block and cannot safely manipulate state. */
	if (in_nmi())
		return;

	local_irq_save(flags);

	/*
	 * If RCU core is waiting for this CPU to exit critical section,
	 * let it know that we have done so.
	 */
	special = t->rcu_read_unlock_special;
	if (special & RCU_READ_UNLOCK_NEED_QS) {
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
		rcu_preempt_qs(smp_processor_id());
	}

	/* Hardware IRQ handlers cannot block. */
	if (in_irq()) {
		local_irq_restore(flags);
		return;
	}

	/* Clean up if blocked during RCU read-side critical section. */
	if (special & RCU_READ_UNLOCK_BLOCKED) {
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;

		/*
		 * Remove this task from the list it blocked on.  The
		 * task can migrate while we acquire the lock, but at
		 * most one time.  So at most two passes through loop.
		 */
		for (;;) {
			rnp = t->rcu_blocked_node;
			spin_lock(&rnp->lock);  /* irqs already disabled. */
			if (rnp == t->rcu_blocked_node)
				break;
			spin_unlock(&rnp->lock);  /* irqs remain disabled. */
		}
		empty = !rcu_preempted_readers(rnp);
		empty_exp = !rcu_preempted_readers_exp(rnp);
		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
		list_del_init(&t->rcu_node_entry);
		t->rcu_blocked_node = NULL;

		/*
		 * If this was the last task on the current list, and if
		 * we aren't waiting on any CPUs, report the quiescent state.
		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
		 */
		if (empty)
			spin_unlock_irqrestore(&rnp->lock, flags);
		else
			rcu_report_unblock_qs_rnp(rnp, flags);

		/*
		 * If this was the last task on the expedited lists,
		 * then we need to report up the rcu_node hierarchy.
		 */
		if (!empty_exp && !rcu_preempted_readers_exp(rnp))
			rcu_report_exp_rnp(&rcu_preempt_state, rnp);
	} else {
		local_irq_restore(flags);
	}
}

/*
 * Tree-preemptable RCU implementation for rcu_read_unlock().
 * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
 * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
 * invoke rcu_read_unlock_special() to clean up after a context switch
 * in an RCU read-side critical section and other special cases.
 */
void __rcu_read_unlock(void)
{
	struct task_struct *t = current;

	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
		rcu_read_unlock_special(t);
#ifdef CONFIG_PROVE_LOCKING
	WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);

#ifdef CONFIG_RCU_CPU_STALL_DETECTOR

/*
 * Scan the current list of tasks blocked within RCU read-side critical
 * sections, printing out the tid of each.
 */
static void rcu_print_task_stall(struct rcu_node *rnp)
{
	unsigned long flags;
	struct list_head *lp;
	int phase;
	struct task_struct *t;

	if (rcu_preempted_readers(rnp)) {
		spin_lock_irqsave(&rnp->lock, flags);
		phase = rnp->gpnum & 0x1;
		lp = &rnp->blocked_tasks[phase];
		list_for_each_entry(t, lp, rcu_node_entry)
			printk(" P%d", t->pid);
		spin_unlock_irqrestore(&rnp->lock, flags);
	}
}

#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */

/*
 * Check that the list of blocked tasks for the newly completed grace
 * period is in fact empty.  It is a serious bug to complete a grace
 * period that still has RCU readers blocked!  This function must be
 * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
 * must be held by the caller.
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
	WARN_ON_ONCE(rcu_preempted_readers(rnp));
	WARN_ON_ONCE(rnp->qsmask);
}

#ifdef CONFIG_HOTPLUG_CPU

/*
 * Handle tasklist migration for case in which all CPUs covered by the
 * specified rcu_node have gone offline.  Move them up to the root
 * rcu_node.  The reason for not just moving them to the immediate
 * parent is to remove the need for rcu_read_unlock_special() to
 * make more than two attempts to acquire the target rcu_node's lock.
 * Returns true if there were tasks blocking the current RCU grace
 * period.
 *
 * Returns 1 if there was previously a task blocking the current grace
 * period on the specified rcu_node structure.
 *
 * The caller must hold rnp->lock with irqs disabled.
 */
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
				     struct rcu_node *rnp,
				     struct rcu_data *rdp)
{
	int i;
	struct list_head *lp;
	struct list_head *lp_root;
	int retval = 0;
	struct rcu_node *rnp_root = rcu_get_root(rsp);
	struct task_struct *tp;

	if (rnp == rnp_root) {
		WARN_ONCE(1, "Last CPU thought to be offlined?");
		return 0;  /* Shouldn't happen: at least one CPU online. */
	}
	WARN_ON_ONCE(rnp != rdp->mynode &&
		     (!list_empty(&rnp->blocked_tasks[0]) ||
		      !list_empty(&rnp->blocked_tasks[1]) ||
		      !list_empty(&rnp->blocked_tasks[2]) ||
		      !list_empty(&rnp->blocked_tasks[3])));

	/*
	 * Move tasks up to root rcu_node.  Rely on the fact that the
	 * root rcu_node can be at most one ahead of the rest of the
	 * rcu_nodes in terms of gp_num value.  This fact allows us to
	 * move the blocked_tasks[] array directly, element by element.
	 */
	if (rcu_preempted_readers(rnp))
		retval |= RCU_OFL_TASKS_NORM_GP;
	if (rcu_preempted_readers_exp(rnp))
		retval |= RCU_OFL_TASKS_EXP_GP;
	for (i = 0; i < 4; i++) {
		lp = &rnp->blocked_tasks[i];
		lp_root = &rnp_root->blocked_tasks[i];
		while (!list_empty(lp)) {
			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
			spin_lock(&rnp_root->lock); /* irqs already disabled */
			list_del(&tp->rcu_node_entry);
			tp->rcu_blocked_node = rnp_root;
			list_add(&tp->rcu_node_entry, lp_root);
			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
		}
	}
	return retval;
}

/*
 * Do CPU-offline processing for preemptable RCU.
 */
static void rcu_preempt_offline_cpu(int cpu)
{
	__rcu_offline_cpu(cpu, &rcu_preempt_state);
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

/*
 * Check for a quiescent state from the current CPU.  When a task blocks,
 * the task is recorded in the corresponding CPU's rcu_node structure,
 * which is checked elsewhere.
 *
 * Caller must disable hard irqs.
 */
static void rcu_preempt_check_callbacks(int cpu)
{
	struct task_struct *t = current;

	if (t->rcu_read_lock_nesting == 0) {
		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
		rcu_preempt_qs(cpu);
		return;
	}
	if (per_cpu(rcu_preempt_data, cpu).qs_pending)
		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
}

/*
 * Process callbacks for preemptable RCU.
 */
static void rcu_preempt_process_callbacks(void)
{
	__rcu_process_callbacks(&rcu_preempt_state,
				&__get_cpu_var(rcu_preempt_data));
}

/*
 * Queue a preemptable-RCU callback for invocation after a grace period.
 */
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_preempt_state);
}
EXPORT_SYMBOL_GPL(call_rcu);

/**
 * synchronize_rcu - wait until a grace period has elapsed.
 *
 * Control will return to the caller some time after a full grace
 * period has elapsed, in other words after all currently executing RCU
 * read-side critical sections have completed.  RCU read-side critical
 * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
 * and may be nested.
 */
void synchronize_rcu(void)
{
	struct rcu_synchronize rcu;

	if (!rcu_scheduler_active)
		return;

	init_completion(&rcu.completion);
	/* Will wake me after RCU finished. */
	call_rcu(&rcu.head, wakeme_after_rcu);
	/* Wait for it. */
	wait_for_completion(&rcu.completion);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);

static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
static long sync_rcu_preempt_exp_count;
static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);

/*
 * Return non-zero if there are any tasks in RCU read-side critical
 * sections blocking the current preemptible-RCU expedited grace period.
 * If there is no preemptible-RCU expedited grace period currently in
 * progress, returns zero unconditionally.
 */
static int rcu_preempted_readers_exp(struct rcu_node *rnp)
{
	return !list_empty(&rnp->blocked_tasks[2]) ||
	       !list_empty(&rnp->blocked_tasks[3]);
}

/*
 * return non-zero if there is no RCU expedited grace period in progress
 * for the specified rcu_node structure, in other words, if all CPUs and
 * tasks covered by the specified rcu_node structure have done their bit
 * for the current expedited grace period.  Works only for preemptible
 * RCU -- other RCU implementation use other means.
 *
 * Caller must hold sync_rcu_preempt_exp_mutex.
 */
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
	return !rcu_preempted_readers_exp(rnp) &&
	       ACCESS_ONCE(rnp->expmask) == 0;
}

/*
 * Report the exit from RCU read-side critical section for the last task
 * that queued itself during or before the current expedited preemptible-RCU
 * grace period.  This event is reported either to the rcu_node structure on
 * which the task was queued or to one of that rcu_node structure's ancestors,
 * recursively up the tree.  (Calm down, calm down, we do the recursion
 * iteratively!)
 *
 * Caller must hold sync_rcu_preempt_exp_mutex.
 */
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
{
	unsigned long flags;
	unsigned long mask;

	spin_lock_irqsave(&rnp->lock, flags);
	for (;;) {
		if (!sync_rcu_preempt_exp_done(rnp))
			break;
		if (rnp->parent == NULL) {
			wake_up(&sync_rcu_preempt_exp_wq);
			break;
		}
		mask = rnp->grpmask;
		spin_unlock(&rnp->lock); /* irqs remain disabled */
		rnp = rnp->parent;
		spin_lock(&rnp->lock); /* irqs already disabled */
		rnp->expmask &= ~mask;
	}
	spin_unlock_irqrestore(&rnp->lock, flags);
}

/*
 * Snapshot the tasks blocking the newly started preemptible-RCU expedited
 * grace period for the specified rcu_node structure.  If there are no such
 * tasks, report it up the rcu_node hierarchy.
 *
 * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock.
 */
static void
sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
{
	int must_wait;

	spin_lock(&rnp->lock); /* irqs already disabled */
	list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
	list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
	must_wait = rcu_preempted_readers_exp(rnp);
	spin_unlock(&rnp->lock); /* irqs remain disabled */
	if (!must_wait)
		rcu_report_exp_rnp(rsp, rnp);
}

/*
 * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
 * is to invoke synchronize_sched_expedited() to push all the tasks to
 * the ->blocked_tasks[] lists, move all entries from the first set of
 * ->blocked_tasks[] lists to the second set, and finally wait for this
 * second set to drain.
 */
void synchronize_rcu_expedited(void)
{
	unsigned long flags;
	struct rcu_node *rnp;
	struct rcu_state *rsp = &rcu_preempt_state;
	long snap;
	int trycount = 0;

	smp_mb(); /* Caller's modifications seen first by other CPUs. */
	snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
	smp_mb(); /* Above access cannot bleed into critical section. */

	/*
	 * Acquire lock, falling back to synchronize_rcu() if too many
	 * lock-acquisition failures.  Of course, if someone does the
	 * expedited grace period for us, just leave.
	 */
	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
		if (trycount++ < 10)
			udelay(trycount * num_online_cpus());
		else {
			synchronize_rcu();
			return;
		}
		if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
			goto mb_ret; /* Others did our work for us. */
	}
	if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
		goto unlock_mb_ret; /* Others did our work for us. */

	/* force all RCU readers onto blocked_tasks[]. */
	synchronize_sched_expedited();

	spin_lock_irqsave(&rsp->onofflock, flags);

	/* Initialize ->expmask for all non-leaf rcu_node structures. */
	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
		spin_lock(&rnp->lock); /* irqs already disabled. */
		rnp->expmask = rnp->qsmaskinit;
		spin_unlock(&rnp->lock); /* irqs remain disabled. */
	}

	/* Snapshot current state of ->blocked_tasks[] lists. */
	rcu_for_each_leaf_node(rsp, rnp)
		sync_rcu_preempt_exp_init(rsp, rnp);
	if (NUM_RCU_NODES > 1)
		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));

	spin_unlock_irqrestore(&rsp->onofflock, flags);

	/* Wait for snapshotted ->blocked_tasks[] lists to drain. */
	rnp = rcu_get_root(rsp);
	wait_event(sync_rcu_preempt_exp_wq,
		   sync_rcu_preempt_exp_done(rnp));

	/* Clean up and exit. */
	smp_mb(); /* ensure expedited GP seen before counter increment. */
	ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
unlock_mb_ret:
	mutex_unlock(&sync_rcu_preempt_exp_mutex);
mb_ret:
	smp_mb(); /* ensure subsequent action seen after grace period. */
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

/*
 * Check to see if there is any immediate preemptable-RCU-related work
 * to be done.
 */
static int rcu_preempt_pending(int cpu)
{
	return __rcu_pending(&rcu_preempt_state,
			     &per_cpu(rcu_preempt_data, cpu));
}

/*
 * Does preemptable RCU need the CPU to stay out of dynticks mode?
 */
static int rcu_preempt_needs_cpu(int cpu)
{
	return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
}

/**
 * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
 */
void rcu_barrier(void)
{
	_rcu_barrier(&rcu_preempt_state, call_rcu);
}
EXPORT_SYMBOL_GPL(rcu_barrier);

/*
 * Initialize preemptable RCU's per-CPU data.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
	rcu_init_percpu_data(cpu, &rcu_preempt_state, 1);
}

/*
 * Move preemptable RCU's callbacks to ->orphan_cbs_list.
 */
static void rcu_preempt_send_cbs_to_orphanage(void)
{
	rcu_send_cbs_to_orphanage(&rcu_preempt_state);
}

/*
 * Initialize preemptable RCU's state structures.
 */
static void __init __rcu_init_preempt(void)
{
	RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
}

/*
 * Check for a task exiting while in a preemptable-RCU read-side
 * critical section, clean up if so.  No need to issue warnings,
 * as debug_check_no_locks_held() already does this if lockdep
 * is enabled.
 */
void exit_rcu(void)
{
	struct task_struct *t = current;

	if (t->rcu_read_lock_nesting == 0)
		return;
	t->rcu_read_lock_nesting = 1;
	rcu_read_unlock();
}

#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */

/*
 * Tell them what RCU they are running.
 */
static void __init rcu_bootup_announce(void)
{
	printk(KERN_INFO "Hierarchical RCU implementation.\n");
}

/*
 * Return the number of RCU batches processed thus far for debug & stats.
 */
long rcu_batches_completed(void)
{
	return rcu_batches_completed_sched();
}
EXPORT_SYMBOL_GPL(rcu_batches_completed);

/*
 * Force a quiescent state for RCU, which, because there is no preemptible
 * RCU, becomes the same as rcu-sched.
 */
void rcu_force_quiescent_state(void)
{
	rcu_sched_force_quiescent_state();
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);

/*
 * Because preemptable RCU does not exist, we never have to check for
 * CPUs being in quiescent states.
 */
static void rcu_preempt_note_context_switch(int cpu)
{
}

/*
 * Because preemptable RCU does not exist, there are never any preempted
 * RCU readers.
 */
static int rcu_preempted_readers(struct rcu_node *rnp)
{
	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU

/* Because preemptible RCU does not exist, no quieting of tasks. */
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
{
	spin_unlock_irqrestore(&rnp->lock, flags);
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

#ifdef CONFIG_RCU_CPU_STALL_DETECTOR

/*
 * Because preemptable RCU does not exist, we never have to check for
 * tasks blocked within RCU read-side critical sections.
 */
static void rcu_print_task_stall(struct rcu_node *rnp)
{
}

#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */

/*
 * Because there is no preemptable RCU, there can be no readers blocked,
 * so there is no need to check for blocked tasks.  So check only for
 * bogus qsmask values.
 */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
	WARN_ON_ONCE(rnp->qsmask);
}

#ifdef CONFIG_HOTPLUG_CPU

/*
 * Because preemptable RCU does not exist, it never needs to migrate
 * tasks that were blocked within RCU read-side critical sections, and
 * such non-existent tasks cannot possibly have been blocking the current
 * grace period.
 */
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
				     struct rcu_node *rnp,
				     struct rcu_data *rdp)
{
	return 0;
}

/*
 * Because preemptable RCU does not exist, it never needs CPU-offline
 * processing.
 */
static void rcu_preempt_offline_cpu(int cpu)
{
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

/*
 * Because preemptable RCU does not exist, it never has any callbacks
 * to check.
 */
static void rcu_preempt_check_callbacks(int cpu)
{
}

/*
 * Because preemptable RCU does not exist, it never has any callbacks
 * to process.
 */
static void rcu_preempt_process_callbacks(void)
{
}

/*
 * In classic RCU, call_rcu() is just call_rcu_sched().
 */
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	call_rcu_sched(head, func);
}
EXPORT_SYMBOL_GPL(call_rcu);

/*
 * Wait for an rcu-preempt grace period, but make it happen quickly.
 * But because preemptable RCU does not exist, map to rcu-sched.
 */
void synchronize_rcu_expedited(void)
{
	synchronize_sched_expedited();
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

#ifdef CONFIG_HOTPLUG_CPU

/*
 * Because preemptable RCU does not exist, there is never any need to
 * report on tasks preempted in RCU read-side critical sections during
 * expedited RCU grace periods.
 */
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
{
	return;
}

#endif /* #ifdef CONFIG_HOTPLUG_CPU */

/*
 * Because preemptable RCU does not exist, it never has any work to do.
 */
static int rcu_preempt_pending(int cpu)
{
	return 0;
}

/*
 * Because preemptable RCU does not exist, it never needs any CPU.
 */
static int rcu_preempt_needs_cpu(int cpu)
{
	return 0;
}

/*
 * Because preemptable RCU does not exist, rcu_barrier() is just
 * another name for rcu_barrier_sched().
 */
void rcu_barrier(void)
{
	rcu_barrier_sched();
}
EXPORT_SYMBOL_GPL(rcu_barrier);

/*
 * Because preemptable RCU does not exist, there is no per-CPU
 * data to initialize.
 */
static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
}

/*
 * Because there is no preemptable RCU, there are no callbacks to move.
 */
static void rcu_preempt_send_cbs_to_orphanage(void)
{
}

/*
 * Because preemptable RCU does not exist, it need not be initialized.
 */
static void __init __rcu_init_preempt(void)
{
}

#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */

#if !defined(CONFIG_RCU_FAST_NO_HZ)

/*
 * Check to see if any future RCU-related work will need to be done
 * by the current CPU, even if none need be done immediately, returning
 * 1 if so.  This function is part of the RCU implementation; it is -not-
 * an exported member of the RCU API.
 *
 * Because we have preemptible RCU, just check whether this CPU needs
 * any flavor of RCU.  Do not chew up lots of CPU cycles with preemption
 * disabled in a most-likely vain attempt to cause RCU not to need this CPU.
 */
int rcu_needs_cpu(int cpu)
{
	return rcu_needs_cpu_quick_check(cpu);
}

#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */

#define RCU_NEEDS_CPU_FLUSHES 5

/*
 * Check to see if any future RCU-related work will need to be done
 * by the current CPU, even if none need be done immediately, returning
 * 1 if so.  This function is part of the RCU implementation; it is -not-
 * an exported member of the RCU API.
 *
 * Because we are not supporting preemptible RCU, attempt to accelerate
 * any current grace periods so that RCU no longer needs this CPU, but
 * only if all other CPUs are already in dynticks-idle mode.  This will
 * allow the CPU cores to be powered down immediately, as opposed to after
 * waiting many milliseconds for grace periods to elapse.
 */
int rcu_needs_cpu(int cpu)
{
	int c = 1;
	int i;
	int thatcpu;

	/* Don't bother unless we are the last non-dyntick-idle CPU. */
	for_each_cpu_not(thatcpu, nohz_cpu_mask)
		if (thatcpu != cpu)
			return rcu_needs_cpu_quick_check(cpu);

	/* Try to push remaining RCU-sched and RCU-bh callbacks through. */
	for (i = 0; i < RCU_NEEDS_CPU_FLUSHES && c; i++) {
		c = 0;
		if (per_cpu(rcu_sched_data, cpu).nxtlist) {
			rcu_sched_qs(cpu);
			force_quiescent_state(&rcu_sched_state, 0);
			__rcu_process_callbacks(&rcu_sched_state,
						&per_cpu(rcu_sched_data, cpu));
			c = !!per_cpu(rcu_sched_data, cpu).nxtlist;
		}
		if (per_cpu(rcu_bh_data, cpu).nxtlist) {
			rcu_bh_qs(cpu);
			force_quiescent_state(&rcu_bh_state, 0);
			__rcu_process_callbacks(&rcu_bh_state,
						&per_cpu(rcu_bh_data, cpu));
			c = !!per_cpu(rcu_bh_data, cpu).nxtlist;
		}
	}

	/* If RCU callbacks are still pending, RCU still needs this CPU. */
	return c;
}

#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */