summaryrefslogtreecommitdiffstats
path: root/kernel/rcu/tree_exp.h
blob: 24343eb87b582e4f1dd5d436e6d7ef830e935c19 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
/*
 * RCU expedited grace periods
 *
 * 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 IBM Corporation, 2016
 *
 * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 */

/* Wrapper functions for expedited grace periods.  */
static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
{
	rcu_seq_start(&rsp->expedited_sequence);
}
static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
{
	rcu_seq_end(&rsp->expedited_sequence);
	smp_mb(); /* Ensure that consecutive grace periods serialize. */
}
static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
{
	unsigned long s;

	smp_mb(); /* Caller's modifications seen first by other CPUs. */
	s = rcu_seq_snap(&rsp->expedited_sequence);
	trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
	return s;
}
static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
{
	return rcu_seq_done(&rsp->expedited_sequence, s);
}

/*
 * Reset the ->expmaskinit values in the rcu_node tree to reflect any
 * recent CPU-online activity.  Note that these masks are not cleared
 * when CPUs go offline, so they reflect the union of all CPUs that have
 * ever been online.  This means that this function normally takes its
 * no-work-to-do fastpath.
 */
static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
{
	bool done;
	unsigned long flags;
	unsigned long mask;
	unsigned long oldmask;
	int ncpus = READ_ONCE(rsp->ncpus);
	struct rcu_node *rnp;
	struct rcu_node *rnp_up;

	/* If no new CPUs onlined since last time, nothing to do. */
	if (likely(ncpus == rsp->ncpus_snap))
		return;
	rsp->ncpus_snap = ncpus;

	/*
	 * Each pass through the following loop propagates newly onlined
	 * CPUs for the current rcu_node structure up the rcu_node tree.
	 */
	rcu_for_each_leaf_node(rsp, rnp) {
		raw_spin_lock_irqsave_rcu_node(rnp, flags);
		if (rnp->expmaskinit == rnp->expmaskinitnext) {
			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
			continue;  /* No new CPUs, nothing to do. */
		}

		/* Update this node's mask, track old value for propagation. */
		oldmask = rnp->expmaskinit;
		rnp->expmaskinit = rnp->expmaskinitnext;
		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);

		/* If was already nonzero, nothing to propagate. */
		if (oldmask)
			continue;

		/* Propagate the new CPU up the tree. */
		mask = rnp->grpmask;
		rnp_up = rnp->parent;
		done = false;
		while (rnp_up) {
			raw_spin_lock_irqsave_rcu_node(rnp_up, flags);
			if (rnp_up->expmaskinit)
				done = true;
			rnp_up->expmaskinit |= mask;
			raw_spin_unlock_irqrestore_rcu_node(rnp_up, flags);
			if (done)
				break;
			mask = rnp_up->grpmask;
			rnp_up = rnp_up->parent;
		}
	}
}

/*
 * Reset the ->expmask values in the rcu_node tree in preparation for
 * a new expedited grace period.
 */
static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
{
	unsigned long flags;
	struct rcu_node *rnp;

	sync_exp_reset_tree_hotplug(rsp);
	rcu_for_each_node_breadth_first(rsp, rnp) {
		raw_spin_lock_irqsave_rcu_node(rnp, flags);
		WARN_ON_ONCE(rnp->expmask);
		rnp->expmask = rnp->expmaskinit;
		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
	}
}

/*
 * 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 the rcu_state's exp_mutex.
 */
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
	return rnp->exp_tasks == NULL &&
	       READ_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 the rcu_state's exp_mutex and the specified rcu_node
 * structure's ->lock.
 */
static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
				 bool wake, unsigned long flags)
	__releases(rnp->lock)
{
	unsigned long mask;

	for (;;) {
		if (!sync_rcu_preempt_exp_done(rnp)) {
			if (!rnp->expmask)
				rcu_initiate_boost(rnp, flags);
			else
				raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
			break;
		}
		if (rnp->parent == NULL) {
			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
			if (wake) {
				smp_mb(); /* EGP done before wake_up(). */
				swake_up(&rsp->expedited_wq);
			}
			break;
		}
		mask = rnp->grpmask;
		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled */
		rnp = rnp->parent;
		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
		WARN_ON_ONCE(!(rnp->expmask & mask));
		rnp->expmask &= ~mask;
	}
}

/*
 * Report expedited quiescent state for specified node.  This is a
 * lock-acquisition wrapper function for __rcu_report_exp_rnp().
 *
 * Caller must hold the rcu_state's exp_mutex.
 */
static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
					      struct rcu_node *rnp, bool wake)
{
	unsigned long flags;

	raw_spin_lock_irqsave_rcu_node(rnp, flags);
	__rcu_report_exp_rnp(rsp, rnp, wake, flags);
}

/*
 * Report expedited quiescent state for multiple CPUs, all covered by the
 * specified leaf rcu_node structure.  Caller must hold the rcu_state's
 * exp_mutex.
 */
static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
				    unsigned long mask, bool wake)
{
	unsigned long flags;

	raw_spin_lock_irqsave_rcu_node(rnp, flags);
	if (!(rnp->expmask & mask)) {
		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
		return;
	}
	rnp->expmask &= ~mask;
	__rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */
}

/*
 * Report expedited quiescent state for specified rcu_data (CPU).
 */
static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
			       bool wake)
{
	rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake);
}

/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat,
			       unsigned long s)
{
	if (rcu_exp_gp_seq_done(rsp, s)) {
		trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
		/* Ensure test happens before caller kfree(). */
		smp_mb__before_atomic(); /* ^^^ */
		atomic_long_inc(stat);
		return true;
	}
	return false;
}

/*
 * Funnel-lock acquisition for expedited grace periods.  Returns true
 * if some other task completed an expedited grace period that this task
 * can piggy-back on, and with no mutex held.  Otherwise, returns false
 * with the mutex held, indicating that the caller must actually do the
 * expedited grace period.
 */
static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
{
	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
	struct rcu_node *rnp = rdp->mynode;
	struct rcu_node *rnp_root = rcu_get_root(rsp);

	/* Low-contention fastpath. */
	if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) &&
	    (rnp == rnp_root ||
	     ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) &&
	    mutex_trylock(&rsp->exp_mutex))
		goto fastpath;

	/*
	 * Each pass through the following loop works its way up
	 * the rcu_node tree, returning if others have done the work or
	 * otherwise falls through to acquire rsp->exp_mutex.  The mapping
	 * from CPU to rcu_node structure can be inexact, as it is just
	 * promoting locality and is not strictly needed for correctness.
	 */
	for (; rnp != NULL; rnp = rnp->parent) {
		if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s))
			return true;

		/* Work not done, either wait here or go up. */
		spin_lock(&rnp->exp_lock);
		if (ULONG_CMP_GE(rnp->exp_seq_rq, s)) {

			/* Someone else doing GP, so wait for them. */
			spin_unlock(&rnp->exp_lock);
			trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
						  rnp->grplo, rnp->grphi,
						  TPS("wait"));
			wait_event(rnp->exp_wq[(s >> 1) & 0x3],
				   sync_exp_work_done(rsp,
						      &rdp->exp_workdone2, s));
			return true;
		}
		rnp->exp_seq_rq = s; /* Followers can wait on us. */
		spin_unlock(&rnp->exp_lock);
		trace_rcu_exp_funnel_lock(rsp->name, rnp->level, rnp->grplo,
					  rnp->grphi, TPS("nxtlvl"));
	}
	mutex_lock(&rsp->exp_mutex);
fastpath:
	if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) {
		mutex_unlock(&rsp->exp_mutex);
		return true;
	}
	rcu_exp_gp_seq_start(rsp);
	trace_rcu_exp_grace_period(rsp->name, s, TPS("start"));
	return false;
}

/* Invoked on each online non-idle CPU for expedited quiescent state. */
static void sync_sched_exp_handler(void *data)
{
	struct rcu_data *rdp;
	struct rcu_node *rnp;
	struct rcu_state *rsp = data;

	rdp = this_cpu_ptr(rsp->rda);
	rnp = rdp->mynode;
	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
	    __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
		return;
	if (rcu_is_cpu_rrupt_from_idle()) {
		rcu_report_exp_rdp(&rcu_sched_state,
				   this_cpu_ptr(&rcu_sched_data), true);
		return;
	}
	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
	resched_cpu(smp_processor_id());
}

/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
static void sync_sched_exp_online_cleanup(int cpu)
{
	struct rcu_data *rdp;
	int ret;
	struct rcu_node *rnp;
	struct rcu_state *rsp = &rcu_sched_state;

	rdp = per_cpu_ptr(rsp->rda, cpu);
	rnp = rdp->mynode;
	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
		return;
	ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0);
	WARN_ON_ONCE(ret);
}

/*
 * Select the nodes that the upcoming expedited grace period needs
 * to wait for.
 */
static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
				     smp_call_func_t func)
{
	int cpu;
	unsigned long flags;
	unsigned long mask_ofl_test;
	unsigned long mask_ofl_ipi;
	int ret;
	struct rcu_node *rnp;

	sync_exp_reset_tree(rsp);
	rcu_for_each_leaf_node(rsp, rnp) {
		raw_spin_lock_irqsave_rcu_node(rnp, flags);

		/* Each pass checks a CPU for identity, offline, and idle. */
		mask_ofl_test = 0;
		for_each_leaf_node_possible_cpu(rnp, cpu) {
			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);

			if (raw_smp_processor_id() == cpu ||
			    !(atomic_add_return(0, &rdtp->dynticks) & 0x1) ||
			    !(rnp->qsmaskinitnext & rdp->grpmask))
				mask_ofl_test |= rdp->grpmask;
		}
		mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;

		/*
		 * Need to wait for any blocked tasks as well.  Note that
		 * additional blocking tasks will also block the expedited
		 * GP until such time as the ->expmask bits are cleared.
		 */
		if (rcu_preempt_has_tasks(rnp))
			rnp->exp_tasks = rnp->blkd_tasks.next;
		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);

		/* IPI the remaining CPUs for expedited quiescent state. */
		for_each_leaf_node_possible_cpu(rnp, cpu) {
			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
			if (!(mask_ofl_ipi & mask))
				continue;
retry_ipi:
			ret = smp_call_function_single(cpu, func, rsp, 0);
			if (!ret) {
				mask_ofl_ipi &= ~mask;
				continue;
			}
			/* Failed, raced with CPU hotplug operation. */
			raw_spin_lock_irqsave_rcu_node(rnp, flags);
			if ((rnp->qsmaskinitnext & mask) &&
			    (rnp->expmask & mask)) {
				/* Online, so delay for a bit and try again. */
				raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
				schedule_timeout_uninterruptible(1);
				goto retry_ipi;
			}
			/* CPU really is offline, so we can ignore it. */
			if (!(rnp->expmask & mask))
				mask_ofl_ipi &= ~mask;
			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
		}
		/* Report quiescent states for those that went offline. */
		mask_ofl_test |= mask_ofl_ipi;
		if (mask_ofl_test)
			rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
	}
}

static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
{
	int cpu;
	unsigned long jiffies_stall;
	unsigned long jiffies_start;
	unsigned long mask;
	int ndetected;
	struct rcu_node *rnp;
	struct rcu_node *rnp_root = rcu_get_root(rsp);
	int ret;

	jiffies_stall = rcu_jiffies_till_stall_check();
	jiffies_start = jiffies;

	for (;;) {
		ret = swait_event_timeout(
				rsp->expedited_wq,
				sync_rcu_preempt_exp_done(rnp_root),
				jiffies_stall);
		if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root))
			return;
		WARN_ON(ret < 0);  /* workqueues should not be signaled. */
		if (rcu_cpu_stall_suppress)
			continue;
		panic_on_rcu_stall();
		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
		       rsp->name);
		ndetected = 0;
		rcu_for_each_leaf_node(rsp, rnp) {
			ndetected += rcu_print_task_exp_stall(rnp);
			for_each_leaf_node_possible_cpu(rnp, cpu) {
				struct rcu_data *rdp;

				mask = leaf_node_cpu_bit(rnp, cpu);
				if (!(rnp->expmask & mask))
					continue;
				ndetected++;
				rdp = per_cpu_ptr(rsp->rda, cpu);
				pr_cont(" %d-%c%c%c", cpu,
					"O."[!!cpu_online(cpu)],
					"o."[!!(rdp->grpmask & rnp->expmaskinit)],
					"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
			}
		}
		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
			jiffies - jiffies_start, rsp->expedited_sequence,
			rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
		if (ndetected) {
			pr_err("blocking rcu_node structures:");
			rcu_for_each_node_breadth_first(rsp, rnp) {
				if (rnp == rnp_root)
					continue; /* printed unconditionally */
				if (sync_rcu_preempt_exp_done(rnp))
					continue;
				pr_cont(" l=%u:%d-%d:%#lx/%c",
					rnp->level, rnp->grplo, rnp->grphi,
					rnp->expmask,
					".T"[!!rnp->exp_tasks]);
			}
			pr_cont("\n");
		}
		rcu_for_each_leaf_node(rsp, rnp) {
			for_each_leaf_node_possible_cpu(rnp, cpu) {
				mask = leaf_node_cpu_bit(rnp, cpu);
				if (!(rnp->expmask & mask))
					continue;
				dump_cpu_task(cpu);
			}
		}
		jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
	}
}

/*
 * Wait for the current expedited grace period to complete, and then
 * wake up everyone who piggybacked on the just-completed expedited
 * grace period.  Also update all the ->exp_seq_rq counters as needed
 * in order to avoid counter-wrap problems.
 */
static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
{
	struct rcu_node *rnp;

	synchronize_sched_expedited_wait(rsp);
	rcu_exp_gp_seq_end(rsp);
	trace_rcu_exp_grace_period(rsp->name, s, TPS("end"));

	/*
	 * Switch over to wakeup mode, allowing the next GP, but -only- the
	 * next GP, to proceed.
	 */
	mutex_lock(&rsp->exp_wake_mutex);

	rcu_for_each_node_breadth_first(rsp, rnp) {
		if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
			spin_lock(&rnp->exp_lock);
			/* Recheck, avoid hang in case someone just arrived. */
			if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
				rnp->exp_seq_rq = s;
			spin_unlock(&rnp->exp_lock);
		}
		wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]);
	}
	trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
	mutex_unlock(&rsp->exp_wake_mutex);
}

/* Let the workqueue handler know what it is supposed to do. */
struct rcu_exp_work {
	smp_call_func_t rew_func;
	struct rcu_state *rew_rsp;
	unsigned long rew_s;
	struct work_struct rew_work;
};

/*
 * Work-queue handler to drive an expedited grace period forward.
 */
static void wait_rcu_exp_gp(struct work_struct *wp)
{
	struct rcu_exp_work *rewp;

	/* Initialize the rcu_node tree in preparation for the wait. */
	rewp = container_of(wp, struct rcu_exp_work, rew_work);
	sync_rcu_exp_select_cpus(rewp->rew_rsp, rewp->rew_func);

	/* Wait and clean up, including waking everyone. */
	rcu_exp_wait_wake(rewp->rew_rsp, rewp->rew_s);
}

/*
 * Given an rcu_state pointer and a smp_call_function() handler, kick
 * off the specified flavor of expedited grace period.
 */
static void _synchronize_rcu_expedited(struct rcu_state *rsp,
				       smp_call_func_t func)
{
	struct rcu_data *rdp;
	struct rcu_exp_work rew;
	struct rcu_node *rnp;
	unsigned long s;

	/* If expedited grace periods are prohibited, fall back to normal. */
	if (rcu_gp_is_normal()) {
		wait_rcu_gp(rsp->call);
		return;
	}

	/* Take a snapshot of the sequence number.  */
	s = rcu_exp_gp_seq_snap(rsp);
	if (exp_funnel_lock(rsp, s))
		return;  /* Someone else did our work for us. */

	/* Marshall arguments and schedule the expedited grace period. */
	rew.rew_func = func;
	rew.rew_rsp = rsp;
	rew.rew_s = s;
	INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
	schedule_work(&rew.rew_work);

	/* Wait for expedited grace period to complete. */
	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
	rnp = rcu_get_root(rsp);
	wait_event(rnp->exp_wq[(s >> 1) & 0x3],
		   sync_exp_work_done(rsp,
				      &rdp->exp_workdone0, s));

	/* Let the next expedited grace period start. */
	mutex_unlock(&rsp->exp_mutex);
}

/**
 * synchronize_sched_expedited - Brute-force RCU-sched grace period
 *
 * Wait for an RCU-sched grace period to elapse, but use a "big hammer"
 * approach to force the grace period to end quickly.  This consumes
 * significant time on all CPUs and is unfriendly to real-time workloads,
 * so is thus not recommended for any sort of common-case code.  In fact,
 * if you are using synchronize_sched_expedited() in a loop, please
 * restructure your code to batch your updates, and then use a single
 * synchronize_sched() instead.
 *
 * This implementation can be thought of as an application of sequence
 * locking to expedited grace periods, but using the sequence counter to
 * determine when someone else has already done the work instead of for
 * retrying readers.
 */
void synchronize_sched_expedited(void)
{
	struct rcu_state *rsp = &rcu_sched_state;

	/* If only one CPU, this is automatically a grace period. */
	if (rcu_blocking_is_gp())
		return;

	_synchronize_rcu_expedited(rsp, sync_sched_exp_handler);
}
EXPORT_SYMBOL_GPL(synchronize_sched_expedited);

#ifdef CONFIG_PREEMPT_RCU

/*
 * Remote handler for smp_call_function_single().  If there is an
 * RCU read-side critical section in effect, request that the
 * next rcu_read_unlock() record the quiescent state up the
 * ->expmask fields in the rcu_node tree.  Otherwise, immediately
 * report the quiescent state.
 */
static void sync_rcu_exp_handler(void *info)
{
	struct rcu_data *rdp;
	struct rcu_state *rsp = info;
	struct task_struct *t = current;

	/*
	 * Within an RCU read-side critical section, request that the next
	 * rcu_read_unlock() report.  Unless this RCU read-side critical
	 * section has already blocked, in which case it is already set
	 * up for the expedited grace period to wait on it.
	 */
	if (t->rcu_read_lock_nesting > 0 &&
	    !t->rcu_read_unlock_special.b.blocked) {
		t->rcu_read_unlock_special.b.exp_need_qs = true;
		return;
	}

	/*
	 * We are either exiting an RCU read-side critical section (negative
	 * values of t->rcu_read_lock_nesting) or are not in one at all
	 * (zero value of t->rcu_read_lock_nesting).  Or we are in an RCU
	 * read-side critical section that blocked before this expedited
	 * grace period started.  Either way, we can immediately report
	 * the quiescent state.
	 */
	rdp = this_cpu_ptr(rsp->rda);
	rcu_report_exp_rdp(rsp, rdp, true);
}

/**
 * synchronize_rcu_expedited - Brute-force RCU grace period
 *
 * Wait for an RCU-preempt grace period, but expedite it.  The basic
 * idea is to IPI all non-idle non-nohz online CPUs.  The IPI handler
 * checks whether the CPU is in an RCU-preempt critical section, and
 * if so, it sets a flag that causes the outermost rcu_read_unlock()
 * to report the quiescent state.  On the other hand, if the CPU is
 * not in an RCU read-side critical section, the IPI handler reports
 * the quiescent state immediately.
 *
 * Although this is a greate improvement over previous expedited
 * implementations, it is still unfriendly to real-time workloads, so is
 * thus not recommended for any sort of common-case code.  In fact, if
 * you are using synchronize_rcu_expedited() in a loop, please restructure
 * your code to batch your updates, and then Use a single synchronize_rcu()
 * instead.
 */
void synchronize_rcu_expedited(void)
{
	struct rcu_state *rsp = rcu_state_p;

	_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);

#else /* #ifdef CONFIG_PREEMPT_RCU */

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

#endif /* #else #ifdef CONFIG_PREEMPT_RCU */