summaryrefslogtreecommitdiff
path: root/drivers/cpuidle/coupled.c
blob: 9acde71558d5101a1d98daeb8e16c185ff8ca98b (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * coupled.c - helper functions to enter the same idle state on multiple cpus
 *
 * Copyright (c) 2011 Google, Inc.
 *
 * Author: Colin Cross <ccross@android.com>
 */

#include <linux/kernel.h>
#include <linux/cpu.h>
#include <linux/cpuidle.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>

#include "cpuidle.h"

/**
 * DOC: Coupled cpuidle states
 *
 * On some ARM SMP SoCs (OMAP4460, Tegra 2, and probably more), the
 * cpus cannot be independently powered down, either due to
 * sequencing restrictions (on Tegra 2, cpu 0 must be the last to
 * power down), or due to HW bugs (on OMAP4460, a cpu powering up
 * will corrupt the gic state unless the other cpu runs a work
 * around).  Each cpu has a power state that it can enter without
 * coordinating with the other cpu (usually Wait For Interrupt, or
 * WFI), and one or more "coupled" power states that affect blocks
 * shared between the cpus (L2 cache, interrupt controller, and
 * sometimes the whole SoC).  Entering a coupled power state must
 * be tightly controlled on both cpus.
 *
 * This file implements a solution, where each cpu will wait in the
 * WFI state until all cpus are ready to enter a coupled state, at
 * which point the coupled state function will be called on all
 * cpus at approximately the same time.
 *
 * Once all cpus are ready to enter idle, they are woken by an smp
 * cross call.  At this point, there is a chance that one of the
 * cpus will find work to do, and choose not to enter idle.  A
 * final pass is needed to guarantee that all cpus will call the
 * power state enter function at the same time.  During this pass,
 * each cpu will increment the ready counter, and continue once the
 * ready counter matches the number of online coupled cpus.  If any
 * cpu exits idle, the other cpus will decrement their counter and
 * retry.
 *
 * requested_state stores the deepest coupled idle state each cpu
 * is ready for.  It is assumed that the states are indexed from
 * shallowest (highest power, lowest exit latency) to deepest
 * (lowest power, highest exit latency).  The requested_state
 * variable is not locked.  It is only written from the cpu that
 * it stores (or by the on/offlining cpu if that cpu is offline),
 * and only read after all the cpus are ready for the coupled idle
 * state are no longer updating it.
 *
 * Three atomic counters are used.  alive_count tracks the number
 * of cpus in the coupled set that are currently or soon will be
 * online.  waiting_count tracks the number of cpus that are in
 * the waiting loop, in the ready loop, or in the coupled idle state.
 * ready_count tracks the number of cpus that are in the ready loop
 * or in the coupled idle state.
 *
 * To use coupled cpuidle states, a cpuidle driver must:
 *
 *    Set struct cpuidle_device.coupled_cpus to the mask of all
 *    coupled cpus, usually the same as cpu_possible_mask if all cpus
 *    are part of the same cluster.  The coupled_cpus mask must be
 *    set in the struct cpuidle_device for each cpu.
 *
 *    Set struct cpuidle_device.safe_state to a state that is not a
 *    coupled state.  This is usually WFI.
 *
 *    Set CPUIDLE_FLAG_COUPLED in struct cpuidle_state.flags for each
 *    state that affects multiple cpus.
 *
 *    Provide a struct cpuidle_state.enter function for each state
 *    that affects multiple cpus.  This function is guaranteed to be
 *    called on all cpus at approximately the same time.  The driver
 *    should ensure that the cpus all abort together if any cpu tries
 *    to abort once the function is called.  The function should return
 *    with interrupts still disabled.
 */

/**
 * struct cpuidle_coupled - data for set of cpus that share a coupled idle state
 * @coupled_cpus: mask of cpus that are part of the coupled set
 * @requested_state: array of requested states for cpus in the coupled set
 * @ready_waiting_counts: combined count of cpus  in ready or waiting loops
 * @abort_barrier: synchronisation point for abort cases
 * @online_count: count of cpus that are online
 * @refcnt: reference count of cpuidle devices that are using this struct
 * @prevent: flag to prevent coupled idle while a cpu is hotplugging
 */
struct cpuidle_coupled {
	cpumask_t coupled_cpus;
	int requested_state[NR_CPUS];
	atomic_t ready_waiting_counts;
	atomic_t abort_barrier;
	int online_count;
	int refcnt;
	int prevent;
};

#define WAITING_BITS 16
#define MAX_WAITING_CPUS (1 << WAITING_BITS)
#define WAITING_MASK (MAX_WAITING_CPUS - 1)
#define READY_MASK (~WAITING_MASK)

#define CPUIDLE_COUPLED_NOT_IDLE	(-1)

static DEFINE_PER_CPU(call_single_data_t, cpuidle_coupled_poke_cb);

/*
 * The cpuidle_coupled_poke_pending mask is used to avoid calling
 * __smp_call_function_single with the per cpu call_single_data_t struct already
 * in use.  This prevents a deadlock where two cpus are waiting for each others
 * call_single_data_t struct to be available
 */
static cpumask_t cpuidle_coupled_poke_pending;

/*
 * The cpuidle_coupled_poked mask is used to ensure that each cpu has been poked
 * once to minimize entering the ready loop with a poke pending, which would
 * require aborting and retrying.
 */
static cpumask_t cpuidle_coupled_poked;

/**
 * cpuidle_coupled_parallel_barrier - synchronize all online coupled cpus
 * @dev: cpuidle_device of the calling cpu
 * @a:   atomic variable to hold the barrier
 *
 * No caller to this function will return from this function until all online
 * cpus in the same coupled group have called this function.  Once any caller
 * has returned from this function, the barrier is immediately available for
 * reuse.
 *
 * The atomic variable must be initialized to 0 before any cpu calls
 * this function, will be reset to 0 before any cpu returns from this function.
 *
 * Must only be called from within a coupled idle state handler
 * (state.enter when state.flags has CPUIDLE_FLAG_COUPLED set).
 *
 * Provides full smp barrier semantics before and after calling.
 */
void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a)
{
	int n = dev->coupled->online_count;

	smp_mb__before_atomic();
	atomic_inc(a);

	while (atomic_read(a) < n)
		cpu_relax();

	if (atomic_inc_return(a) == n * 2) {
		atomic_set(a, 0);
		return;
	}

	while (atomic_read(a) > n)
		cpu_relax();
}

/**
 * cpuidle_state_is_coupled - check if a state is part of a coupled set
 * @drv: struct cpuidle_driver for the platform
 * @state: index of the target state in drv->states
 *
 * Returns true if the target state is coupled with cpus besides this one
 */
bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state)
{
	return drv->states[state].flags & CPUIDLE_FLAG_COUPLED;
}

/**
 * cpuidle_coupled_state_verify - check if the coupled states are correctly set.
 * @drv: struct cpuidle_driver for the platform
 *
 * Returns 0 for valid state values, a negative error code otherwise:
 *  * -EINVAL if any coupled state(safe_state_index) is wrongly set.
 */
int cpuidle_coupled_state_verify(struct cpuidle_driver *drv)
{
	int i;

	for (i = drv->state_count - 1; i >= 0; i--) {
		if (cpuidle_state_is_coupled(drv, i) &&
		    (drv->safe_state_index == i ||
		     drv->safe_state_index < 0 ||
		     drv->safe_state_index >= drv->state_count))
			return -EINVAL;
	}

	return 0;
}

/**
 * cpuidle_coupled_set_ready - mark a cpu as ready
 * @coupled: the struct coupled that contains the current cpu
 */
static inline void cpuidle_coupled_set_ready(struct cpuidle_coupled *coupled)
{
	atomic_add(MAX_WAITING_CPUS, &coupled->ready_waiting_counts);
}

/**
 * cpuidle_coupled_set_not_ready - mark a cpu as not ready
 * @coupled: the struct coupled that contains the current cpu
 *
 * Decrements the ready counter, unless the ready (and thus the waiting) counter
 * is equal to the number of online cpus.  Prevents a race where one cpu
 * decrements the waiting counter and then re-increments it just before another
 * cpu has decremented its ready counter, leading to the ready counter going
 * down from the number of online cpus without going through the coupled idle
 * state.
 *
 * Returns 0 if the counter was decremented successfully, -EINVAL if the ready
 * counter was equal to the number of online cpus.
 */
static
inline int cpuidle_coupled_set_not_ready(struct cpuidle_coupled *coupled)
{
	int all;
	int ret;

	all = coupled->online_count | (coupled->online_count << WAITING_BITS);
	ret = atomic_add_unless(&coupled->ready_waiting_counts,
		-MAX_WAITING_CPUS, all);

	return ret ? 0 : -EINVAL;
}

/**
 * cpuidle_coupled_no_cpus_ready - check if no cpus in a coupled set are ready
 * @coupled: the struct coupled that contains the current cpu
 *
 * Returns true if all of the cpus in a coupled set are out of the ready loop.
 */
static inline int cpuidle_coupled_no_cpus_ready(struct cpuidle_coupled *coupled)
{
	int r = atomic_read(&coupled->ready_waiting_counts) >> WAITING_BITS;
	return r == 0;
}

/**
 * cpuidle_coupled_cpus_ready - check if all cpus in a coupled set are ready
 * @coupled: the struct coupled that contains the current cpu
 *
 * Returns true if all cpus coupled to this target state are in the ready loop
 */
static inline bool cpuidle_coupled_cpus_ready(struct cpuidle_coupled *coupled)
{
	int r = atomic_read(&coupled->ready_waiting_counts) >> WAITING_BITS;
	return r == coupled->online_count;
}

/**
 * cpuidle_coupled_cpus_waiting - check if all cpus in a coupled set are waiting
 * @coupled: the struct coupled that contains the current cpu
 *
 * Returns true if all cpus coupled to this target state are in the wait loop
 */
static inline bool cpuidle_coupled_cpus_waiting(struct cpuidle_coupled *coupled)
{
	int w = atomic_read(&coupled->ready_waiting_counts) & WAITING_MASK;
	return w == coupled->online_count;
}

/**
 * cpuidle_coupled_no_cpus_waiting - check if no cpus in coupled set are waiting
 * @coupled: the struct coupled that contains the current cpu
 *
 * Returns true if all of the cpus in a coupled set are out of the waiting loop.
 */
static inline int cpuidle_coupled_no_cpus_waiting(struct cpuidle_coupled *coupled)
{
	int w = atomic_read(&coupled->ready_waiting_counts) & WAITING_MASK;
	return w == 0;
}

/**
 * cpuidle_coupled_get_state - determine the deepest idle state
 * @dev: struct cpuidle_device for this cpu
 * @coupled: the struct coupled that contains the current cpu
 *
 * Returns the deepest idle state that all coupled cpus can enter
 */
static inline int cpuidle_coupled_get_state(struct cpuidle_device *dev,
		struct cpuidle_coupled *coupled)
{
	int i;
	int state = INT_MAX;

	/*
	 * Read barrier ensures that read of requested_state is ordered after
	 * reads of ready_count.  Matches the write barriers
	 * cpuidle_set_state_waiting.
	 */
	smp_rmb();

	for_each_cpu(i, &coupled->coupled_cpus)
		if (cpu_online(i) && coupled->requested_state[i] < state)
			state = coupled->requested_state[i];

	return state;
}

static void cpuidle_coupled_handle_poke(void *info)
{
	int cpu = (unsigned long)info;
	cpumask_set_cpu(cpu, &cpuidle_coupled_poked);
	cpumask_clear_cpu(cpu, &cpuidle_coupled_poke_pending);
}

/**
 * cpuidle_coupled_poke - wake up a cpu that may be waiting
 * @cpu: target cpu
 *
 * Ensures that the target cpu exits it's waiting idle state (if it is in it)
 * and will see updates to waiting_count before it re-enters it's waiting idle
 * state.
 *
 * If cpuidle_coupled_poked_mask is already set for the target cpu, that cpu
 * either has or will soon have a pending IPI that will wake it out of idle,
 * or it is currently processing the IPI and is not in idle.
 */
static void cpuidle_coupled_poke(int cpu)
{
	call_single_data_t *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);

	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
		smp_call_function_single_async(cpu, csd);
}

/**
 * cpuidle_coupled_poke_others - wake up all other cpus that may be waiting
 * @this_cpu: target cpu
 * @coupled: the struct coupled that contains the current cpu
 *
 * Calls cpuidle_coupled_poke on all other online cpus.
 */
static void cpuidle_coupled_poke_others(int this_cpu,
		struct cpuidle_coupled *coupled)
{
	int cpu;

	for_each_cpu(cpu, &coupled->coupled_cpus)
		if (cpu != this_cpu && cpu_online(cpu))
			cpuidle_coupled_poke(cpu);
}

/**
 * cpuidle_coupled_set_waiting - mark this cpu as in the wait loop
 * @cpu: target cpu
 * @coupled: the struct coupled that contains the current cpu
 * @next_state: the index in drv->states of the requested state for this cpu
 *
 * Updates the requested idle state for the specified cpuidle device.
 * Returns the number of waiting cpus.
 */
static int cpuidle_coupled_set_waiting(int cpu,
		struct cpuidle_coupled *coupled, int next_state)
{
	coupled->requested_state[cpu] = next_state;

	/*
	 * The atomic_inc_return provides a write barrier to order the write
	 * to requested_state with the later write that increments ready_count.
	 */
	return atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK;
}

/**
 * cpuidle_coupled_set_not_waiting - mark this cpu as leaving the wait loop
 * @cpu: target cpu
 * @coupled: the struct coupled that contains the current cpu
 *
 * Removes the requested idle state for the specified cpuidle device.
 */
static void cpuidle_coupled_set_not_waiting(int cpu,
		struct cpuidle_coupled *coupled)
{
	/*
	 * Decrementing waiting count can race with incrementing it in
	 * cpuidle_coupled_set_waiting, but that's OK.  Worst case, some
	 * cpus will increment ready_count and then spin until they
	 * notice that this cpu has cleared it's requested_state.
	 */
	atomic_dec(&coupled->ready_waiting_counts);

	coupled->requested_state[cpu] = CPUIDLE_COUPLED_NOT_IDLE;
}

/**
 * cpuidle_coupled_set_done - mark this cpu as leaving the ready loop
 * @cpu: the current cpu
 * @coupled: the struct coupled that contains the current cpu
 *
 * Marks this cpu as no longer in the ready and waiting loops.  Decrements
 * the waiting count first to prevent another cpu looping back in and seeing
 * this cpu as waiting just before it exits idle.
 */
static void cpuidle_coupled_set_done(int cpu, struct cpuidle_coupled *coupled)
{
	cpuidle_coupled_set_not_waiting(cpu, coupled);
	atomic_sub(MAX_WAITING_CPUS, &coupled->ready_waiting_counts);
}

/**
 * cpuidle_coupled_clear_pokes - spin until the poke interrupt is processed
 * @cpu: this cpu
 *
 * Turns on interrupts and spins until any outstanding poke interrupts have
 * been processed and the poke bit has been cleared.
 *
 * Other interrupts may also be processed while interrupts are enabled, so
 * need_resched() must be tested after this function returns to make sure
 * the interrupt didn't schedule work that should take the cpu out of idle.
 *
 * Returns 0 if no poke was pending, 1 if a poke was cleared.
 */
static int cpuidle_coupled_clear_pokes(int cpu)
{
	if (!cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending))
		return 0;

	local_irq_enable();
	while (cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending))
		cpu_relax();
	local_irq_disable();

	return 1;
}

static bool cpuidle_coupled_any_pokes_pending(struct cpuidle_coupled *coupled)
{
	cpumask_t cpus;
	int ret;

	cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus);
	ret = cpumask_and(&cpus, &cpuidle_coupled_poke_pending, &cpus);

	return ret;
}

/**
 * cpuidle_enter_state_coupled - attempt to enter a state with coupled cpus
 * @dev: struct cpuidle_device for the current cpu
 * @drv: struct cpuidle_driver for the platform
 * @next_state: index of the requested state in drv->states
 *
 * Coordinate with coupled cpus to enter the target state.  This is a two
 * stage process.  In the first stage, the cpus are operating independently,
 * and may call into cpuidle_enter_state_coupled at completely different times.
 * To save as much power as possible, the first cpus to call this function will
 * go to an intermediate state (the cpuidle_device's safe state), and wait for
 * all the other cpus to call this function.  Once all coupled cpus are idle,
 * the second stage will start.  Each coupled cpu will spin until all cpus have
 * guaranteed that they will call the target_state.
 *
 * This function must be called with interrupts disabled.  It may enable
 * interrupts while preparing for idle, and it will always return with
 * interrupts enabled.
 */
int cpuidle_enter_state_coupled(struct cpuidle_device *dev,
		struct cpuidle_driver *drv, int next_state)
{
	int entered_state = -1;
	struct cpuidle_coupled *coupled = dev->coupled;
	int w;

	if (!coupled)
		return -EINVAL;

	while (coupled->prevent) {
		cpuidle_coupled_clear_pokes(dev->cpu);
		if (need_resched()) {
			local_irq_enable();
			return entered_state;
		}
		entered_state = cpuidle_enter_state(dev, drv,
			drv->safe_state_index);
		local_irq_disable();
	}

	/* Read barrier ensures online_count is read after prevent is cleared */
	smp_rmb();

reset:
	cpumask_clear_cpu(dev->cpu, &cpuidle_coupled_poked);

	w = cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state);
	/*
	 * If this is the last cpu to enter the waiting state, poke
	 * all the other cpus out of their waiting state so they can
	 * enter a deeper state.  This can race with one of the cpus
	 * exiting the waiting state due to an interrupt and
	 * decrementing waiting_count, see comment below.
	 */
	if (w == coupled->online_count) {
		cpumask_set_cpu(dev->cpu, &cpuidle_coupled_poked);
		cpuidle_coupled_poke_others(dev->cpu, coupled);
	}

retry:
	/*
	 * Wait for all coupled cpus to be idle, using the deepest state
	 * allowed for a single cpu.  If this was not the poking cpu, wait
	 * for at least one poke before leaving to avoid a race where
	 * two cpus could arrive at the waiting loop at the same time,
	 * but the first of the two to arrive could skip the loop without
	 * processing the pokes from the last to arrive.
	 */
	while (!cpuidle_coupled_cpus_waiting(coupled) ||
			!cpumask_test_cpu(dev->cpu, &cpuidle_coupled_poked)) {
		if (cpuidle_coupled_clear_pokes(dev->cpu))
			continue;

		if (need_resched()) {
			cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
			goto out;
		}

		if (coupled->prevent) {
			cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
			goto out;
		}

		entered_state = cpuidle_enter_state(dev, drv,
			drv->safe_state_index);
		local_irq_disable();
	}

	cpuidle_coupled_clear_pokes(dev->cpu);
	if (need_resched()) {
		cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
		goto out;
	}

	/*
	 * Make sure final poke status for this cpu is visible before setting
	 * cpu as ready.
	 */
	smp_wmb();

	/*
	 * All coupled cpus are probably idle.  There is a small chance that
	 * one of the other cpus just became active.  Increment the ready count,
	 * and spin until all coupled cpus have incremented the counter. Once a
	 * cpu has incremented the ready counter, it cannot abort idle and must
	 * spin until either all cpus have incremented the ready counter, or
	 * another cpu leaves idle and decrements the waiting counter.
	 */

	cpuidle_coupled_set_ready(coupled);
	while (!cpuidle_coupled_cpus_ready(coupled)) {
		/* Check if any other cpus bailed out of idle. */
		if (!cpuidle_coupled_cpus_waiting(coupled))
			if (!cpuidle_coupled_set_not_ready(coupled))
				goto retry;

		cpu_relax();
	}

	/*
	 * Make sure read of all cpus ready is done before reading pending pokes
	 */
	smp_rmb();

	/*
	 * There is a small chance that a cpu left and reentered idle after this
	 * cpu saw that all cpus were waiting.  The cpu that reentered idle will
	 * have sent this cpu a poke, which will still be pending after the
	 * ready loop.  The pending interrupt may be lost by the interrupt
	 * controller when entering the deep idle state.  It's not possible to
	 * clear a pending interrupt without turning interrupts on and handling
	 * it, and it's too late to turn on interrupts here, so reset the
	 * coupled idle state of all cpus and retry.
	 */
	if (cpuidle_coupled_any_pokes_pending(coupled)) {
		cpuidle_coupled_set_done(dev->cpu, coupled);
		/* Wait for all cpus to see the pending pokes */
		cpuidle_coupled_parallel_barrier(dev, &coupled->abort_barrier);
		goto reset;
	}

	/* all cpus have acked the coupled state */
	next_state = cpuidle_coupled_get_state(dev, coupled);

	entered_state = cpuidle_enter_state(dev, drv, next_state);

	cpuidle_coupled_set_done(dev->cpu, coupled);

out:
	/*
	 * Normal cpuidle states are expected to return with irqs enabled.
	 * That leads to an inefficiency where a cpu receiving an interrupt
	 * that brings it out of idle will process that interrupt before
	 * exiting the idle enter function and decrementing ready_count.  All
	 * other cpus will need to spin waiting for the cpu that is processing
	 * the interrupt.  If the driver returns with interrupts disabled,
	 * all other cpus will loop back into the safe idle state instead of
	 * spinning, saving power.
	 *
	 * Calling local_irq_enable here allows coupled states to return with
	 * interrupts disabled, but won't cause problems for drivers that
	 * exit with interrupts enabled.
	 */
	local_irq_enable();

	/*
	 * Wait until all coupled cpus have exited idle.  There is no risk that
	 * a cpu exits and re-enters the ready state because this cpu has
	 * already decremented its waiting_count.
	 */
	while (!cpuidle_coupled_no_cpus_ready(coupled))
		cpu_relax();

	return entered_state;
}

static void cpuidle_coupled_update_online_cpus(struct cpuidle_coupled *coupled)
{
	cpumask_t cpus;
	cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus);
	coupled->online_count = cpumask_weight(&cpus);
}

/**
 * cpuidle_coupled_register_device - register a coupled cpuidle device
 * @dev: struct cpuidle_device for the current cpu
 *
 * Called from cpuidle_register_device to handle coupled idle init.  Finds the
 * cpuidle_coupled struct for this set of coupled cpus, or creates one if none
 * exists yet.
 */
int cpuidle_coupled_register_device(struct cpuidle_device *dev)
{
	int cpu;
	struct cpuidle_device *other_dev;
	call_single_data_t *csd;
	struct cpuidle_coupled *coupled;

	if (cpumask_empty(&dev->coupled_cpus))
		return 0;

	for_each_cpu(cpu, &dev->coupled_cpus) {
		other_dev = per_cpu(cpuidle_devices, cpu);
		if (other_dev && other_dev->coupled) {
			coupled = other_dev->coupled;
			goto have_coupled;
		}
	}

	/* No existing coupled info found, create a new one */
	coupled = kzalloc(sizeof(struct cpuidle_coupled), GFP_KERNEL);
	if (!coupled)
		return -ENOMEM;

	coupled->coupled_cpus = dev->coupled_cpus;

have_coupled:
	dev->coupled = coupled;
	if (WARN_ON(!cpumask_equal(&dev->coupled_cpus, &coupled->coupled_cpus)))
		coupled->prevent++;

	cpuidle_coupled_update_online_cpus(coupled);

	coupled->refcnt++;

	csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu);
	INIT_CSD(csd, cpuidle_coupled_handle_poke, (void *)(unsigned long)dev->cpu);

	return 0;
}

/**
 * cpuidle_coupled_unregister_device - unregister a coupled cpuidle device
 * @dev: struct cpuidle_device for the current cpu
 *
 * Called from cpuidle_unregister_device to tear down coupled idle.  Removes the
 * cpu from the coupled idle set, and frees the cpuidle_coupled_info struct if
 * this was the last cpu in the set.
 */
void cpuidle_coupled_unregister_device(struct cpuidle_device *dev)
{
	struct cpuidle_coupled *coupled = dev->coupled;

	if (cpumask_empty(&dev->coupled_cpus))
		return;

	if (--coupled->refcnt)
		kfree(coupled);
	dev->coupled = NULL;
}

/**
 * cpuidle_coupled_prevent_idle - prevent cpus from entering a coupled state
 * @coupled: the struct coupled that contains the cpu that is changing state
 *
 * Disables coupled cpuidle on a coupled set of cpus.  Used to ensure that
 * cpu_online_mask doesn't change while cpus are coordinating coupled idle.
 */
static void cpuidle_coupled_prevent_idle(struct cpuidle_coupled *coupled)
{
	int cpu = get_cpu();

	/* Force all cpus out of the waiting loop. */
	coupled->prevent++;
	cpuidle_coupled_poke_others(cpu, coupled);
	put_cpu();
	while (!cpuidle_coupled_no_cpus_waiting(coupled))
		cpu_relax();
}

/**
 * cpuidle_coupled_allow_idle - allows cpus to enter a coupled state
 * @coupled: the struct coupled that contains the cpu that is changing state
 *
 * Enables coupled cpuidle on a coupled set of cpus.  Used to ensure that
 * cpu_online_mask doesn't change while cpus are coordinating coupled idle.
 */
static void cpuidle_coupled_allow_idle(struct cpuidle_coupled *coupled)
{
	int cpu = get_cpu();

	/*
	 * Write barrier ensures readers see the new online_count when they
	 * see prevent == 0.
	 */
	smp_wmb();
	coupled->prevent--;
	/* Force cpus out of the prevent loop. */
	cpuidle_coupled_poke_others(cpu, coupled);
	put_cpu();
}

static int coupled_cpu_online(unsigned int cpu)
{
	struct cpuidle_device *dev;

	mutex_lock(&cpuidle_lock);

	dev = per_cpu(cpuidle_devices, cpu);
	if (dev && dev->coupled) {
		cpuidle_coupled_update_online_cpus(dev->coupled);
		cpuidle_coupled_allow_idle(dev->coupled);
	}

	mutex_unlock(&cpuidle_lock);
	return 0;
}

static int coupled_cpu_up_prepare(unsigned int cpu)
{
	struct cpuidle_device *dev;

	mutex_lock(&cpuidle_lock);

	dev = per_cpu(cpuidle_devices, cpu);
	if (dev && dev->coupled)
		cpuidle_coupled_prevent_idle(dev->coupled);

	mutex_unlock(&cpuidle_lock);
	return 0;
}

static int __init cpuidle_coupled_init(void)
{
	int ret;

	ret = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_COUPLED_PREPARE,
					"cpuidle/coupled:prepare",
					coupled_cpu_up_prepare,
					coupled_cpu_online);
	if (ret)
		return ret;
	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
					"cpuidle/coupled:online",
					coupled_cpu_online,
					coupled_cpu_up_prepare);
	if (ret < 0)
		cpuhp_remove_state_nocalls(CPUHP_CPUIDLE_COUPLED_PREPARE);
	return ret;
}
core_initcall(cpuidle_coupled_init);