summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/lib/qspinlock.c
blob: 5de4dd549f6ec84cae2ce9b12ceaba66970b6e4b (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
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/bug.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/processor.h>
#include <linux/smp.h>
#include <linux/topology.h>
#include <linux/sched/clock.h>
#include <asm/qspinlock.h>
#include <asm/paravirt.h>

#define MAX_NODES	4

struct qnode {
	struct qnode	*next;
	struct qspinlock *lock;
	int		cpu;
	u8		sleepy; /* 1 if the previous vCPU was preempted or
				 * if the previous node was sleepy */
	u8		locked; /* 1 if lock acquired */
};

struct qnodes {
	int		count;
	struct qnode nodes[MAX_NODES];
};

/* Tuning parameters */
static int steal_spins __read_mostly = (1 << 5);
static int remote_steal_spins __read_mostly = (1 << 2);
#if _Q_SPIN_TRY_LOCK_STEAL == 1
static const bool maybe_stealers = true;
#else
static bool maybe_stealers __read_mostly = true;
#endif
static int head_spins __read_mostly = (1 << 8);

static bool pv_yield_owner __read_mostly = true;
static bool pv_yield_allow_steal __read_mostly = false;
static bool pv_spin_on_preempted_owner __read_mostly = false;
static bool pv_sleepy_lock __read_mostly = true;
static bool pv_sleepy_lock_sticky __read_mostly = false;
static u64 pv_sleepy_lock_interval_ns __read_mostly = 0;
static int pv_sleepy_lock_factor __read_mostly = 256;
static bool pv_yield_prev __read_mostly = true;
static bool pv_yield_sleepy_owner __read_mostly = true;
static bool pv_prod_head __read_mostly = false;

static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
static DEFINE_PER_CPU_ALIGNED(u64, sleepy_lock_seen_clock);

#if _Q_SPIN_SPEC_BARRIER == 1
#define spec_barrier() do { asm volatile("ori 31,31,0" ::: "memory"); } while (0)
#else
#define spec_barrier() do { } while (0)
#endif

static __always_inline bool recently_sleepy(void)
{
	/* pv_sleepy_lock is true when this is called */
	if (pv_sleepy_lock_interval_ns) {
		u64 seen = this_cpu_read(sleepy_lock_seen_clock);

		if (seen) {
			u64 delta = sched_clock() - seen;
			if (delta < pv_sleepy_lock_interval_ns)
				return true;
			this_cpu_write(sleepy_lock_seen_clock, 0);
		}
	}

	return false;
}

static __always_inline int get_steal_spins(bool paravirt, bool sleepy)
{
	if (paravirt && sleepy)
		return steal_spins * pv_sleepy_lock_factor;
	else
		return steal_spins;
}

static __always_inline int get_remote_steal_spins(bool paravirt, bool sleepy)
{
	if (paravirt && sleepy)
		return remote_steal_spins * pv_sleepy_lock_factor;
	else
		return remote_steal_spins;
}

static __always_inline int get_head_spins(bool paravirt, bool sleepy)
{
	if (paravirt && sleepy)
		return head_spins * pv_sleepy_lock_factor;
	else
		return head_spins;
}

static inline u32 encode_tail_cpu(int cpu)
{
	return (cpu + 1) << _Q_TAIL_CPU_OFFSET;
}

static inline int decode_tail_cpu(u32 val)
{
	return (val >> _Q_TAIL_CPU_OFFSET) - 1;
}

static inline int get_owner_cpu(u32 val)
{
	return (val & _Q_OWNER_CPU_MASK) >> _Q_OWNER_CPU_OFFSET;
}

/*
 * Try to acquire the lock if it was not already locked. If the tail matches
 * mytail then clear it, otherwise leave it unchnaged. Return previous value.
 *
 * This is used by the head of the queue to acquire the lock and clean up
 * its tail if it was the last one queued.
 */
static __always_inline u32 trylock_clean_tail(struct qspinlock *lock, u32 tail)
{
	u32 newval = queued_spin_encode_locked_val();
	u32 prev, tmp;

	asm volatile(
"1:	lwarx	%0,0,%2,%7	# trylock_clean_tail			\n"
	/* This test is necessary if there could be stealers */
"	andi.	%1,%0,%5						\n"
"	bne	3f							\n"
	/* Test whether the lock tail == mytail */
"	and	%1,%0,%6						\n"
"	cmpw	0,%1,%3							\n"
	/* Merge the new locked value */
"	or	%1,%1,%4						\n"
"	bne	2f							\n"
	/* If the lock tail matched, then clear it, otherwise leave it. */
"	andc	%1,%1,%6						\n"
"2:	stwcx.	%1,0,%2							\n"
"	bne-	1b							\n"
"\t"	PPC_ACQUIRE_BARRIER "						\n"
"3:									\n"
	: "=&r" (prev), "=&r" (tmp)
	: "r" (&lock->val), "r"(tail), "r" (newval),
	  "i" (_Q_LOCKED_VAL),
	  "r" (_Q_TAIL_CPU_MASK),
	  "i" (_Q_SPIN_EH_HINT)
	: "cr0", "memory");

	return prev;
}

/*
 * Publish our tail, replacing previous tail. Return previous value.
 *
 * This provides a release barrier for publishing node, this pairs with the
 * acquire barrier in get_tail_qnode() when the next CPU finds this tail
 * value.
 */
static __always_inline u32 publish_tail_cpu(struct qspinlock *lock, u32 tail)
{
	u32 prev, tmp;

	kcsan_release();

	asm volatile(
"\t"	PPC_RELEASE_BARRIER "						\n"
"1:	lwarx	%0,0,%2		# publish_tail_cpu			\n"
"	andc	%1,%0,%4						\n"
"	or	%1,%1,%3						\n"
"	stwcx.	%1,0,%2							\n"
"	bne-	1b							\n"
	: "=&r" (prev), "=&r"(tmp)
	: "r" (&lock->val), "r" (tail), "r"(_Q_TAIL_CPU_MASK)
	: "cr0", "memory");

	return prev;
}

static __always_inline u32 set_mustq(struct qspinlock *lock)
{
	u32 prev;

	asm volatile(
"1:	lwarx	%0,0,%1		# set_mustq				\n"
"	or	%0,%0,%2						\n"
"	stwcx.	%0,0,%1							\n"
"	bne-	1b							\n"
	: "=&r" (prev)
	: "r" (&lock->val), "r" (_Q_MUST_Q_VAL)
	: "cr0", "memory");

	return prev;
}

static __always_inline u32 clear_mustq(struct qspinlock *lock)
{
	u32 prev;

	asm volatile(
"1:	lwarx	%0,0,%1		# clear_mustq				\n"
"	andc	%0,%0,%2						\n"
"	stwcx.	%0,0,%1							\n"
"	bne-	1b							\n"
	: "=&r" (prev)
	: "r" (&lock->val), "r" (_Q_MUST_Q_VAL)
	: "cr0", "memory");

	return prev;
}

static __always_inline bool try_set_sleepy(struct qspinlock *lock, u32 old)
{
	u32 prev;
	u32 new = old | _Q_SLEEPY_VAL;

	BUG_ON(!(old & _Q_LOCKED_VAL));
	BUG_ON(old & _Q_SLEEPY_VAL);

	asm volatile(
"1:	lwarx	%0,0,%1		# try_set_sleepy			\n"
"	cmpw	0,%0,%2							\n"
"	bne-	2f							\n"
"	stwcx.	%3,0,%1							\n"
"	bne-	1b							\n"
"2:									\n"
	: "=&r" (prev)
	: "r" (&lock->val), "r"(old), "r" (new)
	: "cr0", "memory");

	return likely(prev == old);
}

static __always_inline void seen_sleepy_owner(struct qspinlock *lock, u32 val)
{
	if (pv_sleepy_lock) {
		if (pv_sleepy_lock_interval_ns)
			this_cpu_write(sleepy_lock_seen_clock, sched_clock());
		if (!(val & _Q_SLEEPY_VAL))
			try_set_sleepy(lock, val);
	}
}

static __always_inline void seen_sleepy_lock(void)
{
	if (pv_sleepy_lock && pv_sleepy_lock_interval_ns)
		this_cpu_write(sleepy_lock_seen_clock, sched_clock());
}

static __always_inline void seen_sleepy_node(void)
{
	if (pv_sleepy_lock) {
		if (pv_sleepy_lock_interval_ns)
			this_cpu_write(sleepy_lock_seen_clock, sched_clock());
		/* Don't set sleepy because we likely have a stale val */
	}
}

static struct qnode *get_tail_qnode(struct qspinlock *lock, int prev_cpu)
{
	struct qnodes *qnodesp = per_cpu_ptr(&qnodes, prev_cpu);
	int idx;

	/*
	 * After publishing the new tail and finding a previous tail in the
	 * previous val (which is the control dependency), this barrier
	 * orders the release barrier in publish_tail_cpu performed by the
	 * last CPU, with subsequently looking at its qnode structures
	 * after the barrier.
	 */
	smp_acquire__after_ctrl_dep();

	for (idx = 0; idx < MAX_NODES; idx++) {
		struct qnode *qnode = &qnodesp->nodes[idx];
		if (qnode->lock == lock)
			return qnode;
	}

	BUG();
}

/* Called inside spin_begin(). Returns whether or not the vCPU was preempted. */
static __always_inline bool __yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt, bool mustq)
{
	int owner;
	u32 yield_count;
	bool preempted = false;

	BUG_ON(!(val & _Q_LOCKED_VAL));

	if (!paravirt)
		goto relax;

	if (!pv_yield_owner)
		goto relax;

	owner = get_owner_cpu(val);
	yield_count = yield_count_of(owner);

	if ((yield_count & 1) == 0)
		goto relax; /* owner vcpu is running */

	spin_end();

	seen_sleepy_owner(lock, val);
	preempted = true;

	/*
	 * Read the lock word after sampling the yield count. On the other side
	 * there may a wmb because the yield count update is done by the
	 * hypervisor preemption and the value update by the OS, however this
	 * ordering might reduce the chance of out of order accesses and
	 * improve the heuristic.
	 */
	smp_rmb();

	if (READ_ONCE(lock->val) == val) {
		if (mustq)
			clear_mustq(lock);
		yield_to_preempted(owner, yield_count);
		if (mustq)
			set_mustq(lock);
		spin_begin();

		/* Don't relax if we yielded. Maybe we should? */
		return preempted;
	}
	spin_begin();
relax:
	spin_cpu_relax();

	return preempted;
}

/* Called inside spin_begin(). Returns whether or not the vCPU was preempted. */
static __always_inline bool yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
{
	return __yield_to_locked_owner(lock, val, paravirt, false);
}

/* Called inside spin_begin(). Returns whether or not the vCPU was preempted. */
static __always_inline bool yield_head_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
{
	bool mustq = false;

	if ((val & _Q_MUST_Q_VAL) && pv_yield_allow_steal)
		mustq = true;

	return __yield_to_locked_owner(lock, val, paravirt, mustq);
}

static __always_inline void propagate_sleepy(struct qnode *node, u32 val, bool paravirt)
{
	struct qnode *next;
	int owner;

	if (!paravirt)
		return;
	if (!pv_yield_sleepy_owner)
		return;

	next = READ_ONCE(node->next);
	if (!next)
		return;

	if (next->sleepy)
		return;

	owner = get_owner_cpu(val);
	if (vcpu_is_preempted(owner))
		next->sleepy = 1;
}

/* Called inside spin_begin() */
static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *node, int prev_cpu, bool paravirt)
{
	u32 yield_count;
	bool preempted = false;

	if (!paravirt)
		goto relax;

	if (!pv_yield_sleepy_owner)
		goto yield_prev;

	/*
	 * If the previous waiter was preempted it might not be able to
	 * propagate sleepy to us, so check the lock in that case too.
	 */
	if (node->sleepy || vcpu_is_preempted(prev_cpu)) {
		u32 val = READ_ONCE(lock->val);

		if (val & _Q_LOCKED_VAL) {
			if (node->next && !node->next->sleepy) {
				/*
				 * Propagate sleepy to next waiter. Only if
				 * owner is preempted, which allows the queue
				 * to become "non-sleepy" if vCPU preemption
				 * ceases to occur, even if the lock remains
				 * highly contended.
				 */
				if (vcpu_is_preempted(get_owner_cpu(val)))
					node->next->sleepy = 1;
			}

			preempted = yield_to_locked_owner(lock, val, paravirt);
			if (preempted)
				return preempted;
		}
		node->sleepy = false;
	}

yield_prev:
	if (!pv_yield_prev)
		goto relax;

	yield_count = yield_count_of(prev_cpu);
	if ((yield_count & 1) == 0)
		goto relax; /* owner vcpu is running */

	spin_end();

	preempted = true;
	seen_sleepy_node();

	smp_rmb(); /* See __yield_to_locked_owner comment */

	if (!READ_ONCE(node->locked)) {
		yield_to_preempted(prev_cpu, yield_count);
		spin_begin();
		return preempted;
	}
	spin_begin();

relax:
	spin_cpu_relax();

	return preempted;
}

static __always_inline bool steal_break(u32 val, int iters, bool paravirt, bool sleepy)
{
	if (iters >= get_steal_spins(paravirt, sleepy))
		return true;

	if (IS_ENABLED(CONFIG_NUMA) &&
	    (iters >= get_remote_steal_spins(paravirt, sleepy))) {
		int cpu = get_owner_cpu(val);
		if (numa_node_id() != cpu_to_node(cpu))
			return true;
	}
	return false;
}

static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool paravirt)
{
	bool seen_preempted = false;
	bool sleepy = false;
	int iters = 0;
	u32 val;

	if (!steal_spins) {
		/* XXX: should spin_on_preempted_owner do anything here? */
		return false;
	}

	/* Attempt to steal the lock */
	spin_begin();
	do {
		bool preempted = false;

		val = READ_ONCE(lock->val);
		if (val & _Q_MUST_Q_VAL)
			break;
		spec_barrier();

		if (unlikely(!(val & _Q_LOCKED_VAL))) {
			spin_end();
			if (__queued_spin_trylock_steal(lock))
				return true;
			spin_begin();
		} else {
			preempted = yield_to_locked_owner(lock, val, paravirt);
		}

		if (paravirt && pv_sleepy_lock) {
			if (!sleepy) {
				if (val & _Q_SLEEPY_VAL) {
					seen_sleepy_lock();
					sleepy = true;
				} else if (recently_sleepy()) {
					sleepy = true;
				}
			}
			if (pv_sleepy_lock_sticky && seen_preempted &&
			    !(val & _Q_SLEEPY_VAL)) {
				if (try_set_sleepy(lock, val))
					val |= _Q_SLEEPY_VAL;
			}
		}

		if (preempted) {
			seen_preempted = true;
			sleepy = true;
			if (!pv_spin_on_preempted_owner)
				iters++;
			/*
			 * pv_spin_on_preempted_owner don't increase iters
			 * while the owner is preempted -- we won't interfere
			 * with it by definition. This could introduce some
			 * latency issue if we continually observe preempted
			 * owners, but hopefully that's a rare corner case of
			 * a badly oversubscribed system.
			 */
		} else {
			iters++;
		}
	} while (!steal_break(val, iters, paravirt, sleepy));

	spin_end();

	return false;
}

static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, bool paravirt)
{
	struct qnodes *qnodesp;
	struct qnode *next, *node;
	u32 val, old, tail;
	bool seen_preempted = false;
	bool sleepy = false;
	bool mustq = false;
	int idx;
	int iters = 0;

	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));

	qnodesp = this_cpu_ptr(&qnodes);
	if (unlikely(qnodesp->count >= MAX_NODES)) {
		spec_barrier();
		while (!queued_spin_trylock(lock))
			cpu_relax();
		return;
	}

	idx = qnodesp->count++;
	/*
	 * Ensure that we increment the head node->count before initialising
	 * the actual node. If the compiler is kind enough to reorder these
	 * stores, then an IRQ could overwrite our assignments.
	 */
	barrier();
	node = &qnodesp->nodes[idx];
	node->next = NULL;
	node->lock = lock;
	node->cpu = smp_processor_id();
	node->sleepy = 0;
	node->locked = 0;

	tail = encode_tail_cpu(node->cpu);

	/*
	 * Assign all attributes of a node before it can be published.
	 * Issues an lwsync, serving as a release barrier, as well as a
	 * compiler barrier.
	 */
	old = publish_tail_cpu(lock, tail);

	/*
	 * If there was a previous node; link it and wait until reaching the
	 * head of the waitqueue.
	 */
	if (old & _Q_TAIL_CPU_MASK) {
		int prev_cpu = decode_tail_cpu(old);
		struct qnode *prev = get_tail_qnode(lock, prev_cpu);

		/* Link @node into the waitqueue. */
		WRITE_ONCE(prev->next, node);

		/* Wait for mcs node lock to be released */
		spin_begin();
		while (!READ_ONCE(node->locked)) {
			spec_barrier();

			if (yield_to_prev(lock, node, prev_cpu, paravirt))
				seen_preempted = true;
		}
		spec_barrier();
		spin_end();

		smp_rmb(); /* acquire barrier for the mcs lock */

		/*
		 * Generic qspinlocks have this prefetch here, but it seems
		 * like it could cause additional line transitions because
		 * the waiter will keep loading from it.
		 */
		if (_Q_SPIN_PREFETCH_NEXT) {
			next = READ_ONCE(node->next);
			if (next)
				prefetchw(next);
		}
	}

	/* We're at the head of the waitqueue, wait for the lock. */
again:
	spin_begin();
	for (;;) {
		bool preempted;

		val = READ_ONCE(lock->val);
		if (!(val & _Q_LOCKED_VAL))
			break;
		spec_barrier();

		if (paravirt && pv_sleepy_lock && maybe_stealers) {
			if (!sleepy) {
				if (val & _Q_SLEEPY_VAL) {
					seen_sleepy_lock();
					sleepy = true;
				} else if (recently_sleepy()) {
					sleepy = true;
				}
			}
			if (pv_sleepy_lock_sticky && seen_preempted &&
			    !(val & _Q_SLEEPY_VAL)) {
				if (try_set_sleepy(lock, val))
					val |= _Q_SLEEPY_VAL;
			}
		}

		propagate_sleepy(node, val, paravirt);
		preempted = yield_head_to_locked_owner(lock, val, paravirt);
		if (!maybe_stealers)
			continue;

		if (preempted)
			seen_preempted = true;

		if (paravirt && preempted) {
			sleepy = true;

			if (!pv_spin_on_preempted_owner)
				iters++;
		} else {
			iters++;
		}

		if (!mustq && iters >= get_head_spins(paravirt, sleepy)) {
			mustq = true;
			set_mustq(lock);
			val |= _Q_MUST_Q_VAL;
		}
	}
	spec_barrier();
	spin_end();

	/* If we're the last queued, must clean up the tail. */
	old = trylock_clean_tail(lock, tail);
	if (unlikely(old & _Q_LOCKED_VAL)) {
		BUG_ON(!maybe_stealers);
		goto again; /* Can only be true if maybe_stealers. */
	}

	if ((old & _Q_TAIL_CPU_MASK) == tail)
		goto release; /* We were the tail, no next. */

	/* There is a next, must wait for node->next != NULL (MCS protocol) */
	next = READ_ONCE(node->next);
	if (!next) {
		spin_begin();
		while (!(next = READ_ONCE(node->next)))
			cpu_relax();
		spin_end();
	}
	spec_barrier();

	/*
	 * Unlock the next mcs waiter node. Release barrier is not required
	 * here because the acquirer is only accessing the lock word, and
	 * the acquire barrier we took the lock with orders that update vs
	 * this store to locked. The corresponding barrier is the smp_rmb()
	 * acquire barrier for mcs lock, above.
	 */
	if (paravirt && pv_prod_head) {
		int next_cpu = next->cpu;
		WRITE_ONCE(next->locked, 1);
		if (_Q_SPIN_MISO)
			asm volatile("miso" ::: "memory");
		if (vcpu_is_preempted(next_cpu))
			prod_cpu(next_cpu);
	} else {
		WRITE_ONCE(next->locked, 1);
		if (_Q_SPIN_MISO)
			asm volatile("miso" ::: "memory");
	}

release:
	qnodesp->count--; /* release the node */
}

void queued_spin_lock_slowpath(struct qspinlock *lock)
{
	/*
	 * This looks funny, but it induces the compiler to inline both
	 * sides of the branch rather than share code as when the condition
	 * is passed as the paravirt argument to the functions.
	 */
	if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && is_shared_processor()) {
		if (try_to_steal_lock(lock, true)) {
			spec_barrier();
			return;
		}
		queued_spin_lock_mcs_queue(lock, true);
	} else {
		if (try_to_steal_lock(lock, false)) {
			spec_barrier();
			return;
		}
		queued_spin_lock_mcs_queue(lock, false);
	}
}
EXPORT_SYMBOL(queued_spin_lock_slowpath);

#ifdef CONFIG_PARAVIRT_SPINLOCKS
void pv_spinlocks_init(void)
{
}
#endif

#include <linux/debugfs.h>
static int steal_spins_set(void *data, u64 val)
{
#if _Q_SPIN_TRY_LOCK_STEAL == 1
	/* MAYBE_STEAL remains true */
	steal_spins = val;
#else
	static DEFINE_MUTEX(lock);

	/*
	 * The lock slow path has a !maybe_stealers case that can assume
	 * the head of queue will not see concurrent waiters. That waiter
	 * is unsafe in the presence of stealers, so must keep them away
	 * from one another.
	 */

	mutex_lock(&lock);
	if (val && !steal_spins) {
		maybe_stealers = true;
		/* wait for queue head waiter to go away */
		synchronize_rcu();
		steal_spins = val;
	} else if (!val && steal_spins) {
		steal_spins = val;
		/* wait for all possible stealers to go away */
		synchronize_rcu();
		maybe_stealers = false;
	} else {
		steal_spins = val;
	}
	mutex_unlock(&lock);
#endif

	return 0;
}

static int steal_spins_get(void *data, u64 *val)
{
	*val = steal_spins;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_steal_spins, steal_spins_get, steal_spins_set, "%llu\n");

static int remote_steal_spins_set(void *data, u64 val)
{
	remote_steal_spins = val;

	return 0;
}

static int remote_steal_spins_get(void *data, u64 *val)
{
	*val = remote_steal_spins;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_remote_steal_spins, remote_steal_spins_get, remote_steal_spins_set, "%llu\n");

static int head_spins_set(void *data, u64 val)
{
	head_spins = val;

	return 0;
}

static int head_spins_get(void *data, u64 *val)
{
	*val = head_spins;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_head_spins, head_spins_get, head_spins_set, "%llu\n");

static int pv_yield_owner_set(void *data, u64 val)
{
	pv_yield_owner = !!val;

	return 0;
}

static int pv_yield_owner_get(void *data, u64 *val)
{
	*val = pv_yield_owner;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_owner, pv_yield_owner_get, pv_yield_owner_set, "%llu\n");

static int pv_yield_allow_steal_set(void *data, u64 val)
{
	pv_yield_allow_steal = !!val;

	return 0;
}

static int pv_yield_allow_steal_get(void *data, u64 *val)
{
	*val = pv_yield_allow_steal;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_allow_steal, pv_yield_allow_steal_get, pv_yield_allow_steal_set, "%llu\n");

static int pv_spin_on_preempted_owner_set(void *data, u64 val)
{
	pv_spin_on_preempted_owner = !!val;

	return 0;
}

static int pv_spin_on_preempted_owner_get(void *data, u64 *val)
{
	*val = pv_spin_on_preempted_owner;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_spin_on_preempted_owner, pv_spin_on_preempted_owner_get, pv_spin_on_preempted_owner_set, "%llu\n");

static int pv_sleepy_lock_set(void *data, u64 val)
{
	pv_sleepy_lock = !!val;

	return 0;
}

static int pv_sleepy_lock_get(void *data, u64 *val)
{
	*val = pv_sleepy_lock;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_sleepy_lock, pv_sleepy_lock_get, pv_sleepy_lock_set, "%llu\n");

static int pv_sleepy_lock_sticky_set(void *data, u64 val)
{
	pv_sleepy_lock_sticky = !!val;

	return 0;
}

static int pv_sleepy_lock_sticky_get(void *data, u64 *val)
{
	*val = pv_sleepy_lock_sticky;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_sleepy_lock_sticky, pv_sleepy_lock_sticky_get, pv_sleepy_lock_sticky_set, "%llu\n");

static int pv_sleepy_lock_interval_ns_set(void *data, u64 val)
{
	pv_sleepy_lock_interval_ns = val;

	return 0;
}

static int pv_sleepy_lock_interval_ns_get(void *data, u64 *val)
{
	*val = pv_sleepy_lock_interval_ns;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_sleepy_lock_interval_ns, pv_sleepy_lock_interval_ns_get, pv_sleepy_lock_interval_ns_set, "%llu\n");

static int pv_sleepy_lock_factor_set(void *data, u64 val)
{
	pv_sleepy_lock_factor = val;

	return 0;
}

static int pv_sleepy_lock_factor_get(void *data, u64 *val)
{
	*val = pv_sleepy_lock_factor;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_sleepy_lock_factor, pv_sleepy_lock_factor_get, pv_sleepy_lock_factor_set, "%llu\n");

static int pv_yield_prev_set(void *data, u64 val)
{
	pv_yield_prev = !!val;

	return 0;
}

static int pv_yield_prev_get(void *data, u64 *val)
{
	*val = pv_yield_prev;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_prev, pv_yield_prev_get, pv_yield_prev_set, "%llu\n");

static int pv_yield_sleepy_owner_set(void *data, u64 val)
{
	pv_yield_sleepy_owner = !!val;

	return 0;
}

static int pv_yield_sleepy_owner_get(void *data, u64 *val)
{
	*val = pv_yield_sleepy_owner;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_sleepy_owner, pv_yield_sleepy_owner_get, pv_yield_sleepy_owner_set, "%llu\n");

static int pv_prod_head_set(void *data, u64 val)
{
	pv_prod_head = !!val;

	return 0;
}

static int pv_prod_head_get(void *data, u64 *val)
{
	*val = pv_prod_head;

	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fops_pv_prod_head, pv_prod_head_get, pv_prod_head_set, "%llu\n");

static __init int spinlock_debugfs_init(void)
{
	debugfs_create_file("qspl_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_steal_spins);
	debugfs_create_file("qspl_remote_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_remote_steal_spins);
	debugfs_create_file("qspl_head_spins", 0600, arch_debugfs_dir, NULL, &fops_head_spins);
	if (is_shared_processor()) {
		debugfs_create_file("qspl_pv_yield_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_owner);
		debugfs_create_file("qspl_pv_yield_allow_steal", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_allow_steal);
		debugfs_create_file("qspl_pv_spin_on_preempted_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_spin_on_preempted_owner);
		debugfs_create_file("qspl_pv_sleepy_lock", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock);
		debugfs_create_file("qspl_pv_sleepy_lock_sticky", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_sticky);
		debugfs_create_file("qspl_pv_sleepy_lock_interval_ns", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_interval_ns);
		debugfs_create_file("qspl_pv_sleepy_lock_factor", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_factor);
		debugfs_create_file("qspl_pv_yield_prev", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_prev);
		debugfs_create_file("qspl_pv_yield_sleepy_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_sleepy_owner);
		debugfs_create_file("qspl_pv_prod_head", 0600, arch_debugfs_dir, NULL, &fops_pv_prod_head);
	}

	return 0;
}
device_initcall(spinlock_debugfs_init);