summaryrefslogtreecommitdiff
path: root/mm/mmu_notifier.c
blob: ec3b068cbbe6b1730c4205237c798834ad8d1ebe (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/mm/mmu_notifier.c
 *
 *  Copyright (C) 2008  Qumranet, Inc.
 *  Copyright (C) 2008  SGI
 *             Christoph Lameter <cl@linux.com>
 */

#include <linux/rculist.h>
#include <linux/mmu_notifier.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/interval_tree.h>
#include <linux/srcu.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>

/* global SRCU for all MMs */
DEFINE_STATIC_SRCU(srcu);

#ifdef CONFIG_LOCKDEP
struct lockdep_map __mmu_notifier_invalidate_range_start_map = {
	.name = "mmu_notifier_invalidate_range_start"
};
#endif

/*
 * The mmu_notifier_subscriptions structure is allocated and installed in
 * mm->notifier_subscriptions inside the mm_take_all_locks() protected
 * critical section and it's released only when mm_count reaches zero
 * in mmdrop().
 */
struct mmu_notifier_subscriptions {
	/* all mmu notifiers registered in this mm are queued in this list */
	struct hlist_head list;
	bool has_itree;
	/* to serialize the list modifications and hlist_unhashed */
	spinlock_t lock;
	unsigned long invalidate_seq;
	unsigned long active_invalidate_ranges;
	struct rb_root_cached itree;
	wait_queue_head_t wq;
	struct hlist_head deferred_list;
};

/*
 * This is a collision-retry read-side/write-side 'lock', a lot like a
 * seqcount, however this allows multiple write-sides to hold it at
 * once. Conceptually the write side is protecting the values of the PTEs in
 * this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any
 * writer exists.
 *
 * Note that the core mm creates nested invalidate_range_start()/end() regions
 * within the same thread, and runs invalidate_range_start()/end() in parallel
 * on multiple CPUs. This is designed to not reduce concurrency or block
 * progress on the mm side.
 *
 * As a secondary function, holding the full write side also serves to prevent
 * writers for the itree, this is an optimization to avoid extra locking
 * during invalidate_range_start/end notifiers.
 *
 * The write side has two states, fully excluded:
 *  - mm->active_invalidate_ranges != 0
 *  - subscriptions->invalidate_seq & 1 == True (odd)
 *  - some range on the mm_struct is being invalidated
 *  - the itree is not allowed to change
 *
 * And partially excluded:
 *  - mm->active_invalidate_ranges != 0
 *  - subscriptions->invalidate_seq & 1 == False (even)
 *  - some range on the mm_struct is being invalidated
 *  - the itree is allowed to change
 *
 * Operations on notifier_subscriptions->invalidate_seq (under spinlock):
 *    seq |= 1  # Begin writing
 *    seq++     # Release the writing state
 *    seq & 1   # True if a writer exists
 *
 * The later state avoids some expensive work on inv_end in the common case of
 * no mmu_interval_notifier monitoring the VA.
 */
static bool
mn_itree_is_invalidating(struct mmu_notifier_subscriptions *subscriptions)
{
	lockdep_assert_held(&subscriptions->lock);
	return subscriptions->invalidate_seq & 1;
}

static struct mmu_interval_notifier *
mn_itree_inv_start_range(struct mmu_notifier_subscriptions *subscriptions,
			 const struct mmu_notifier_range *range,
			 unsigned long *seq)
{
	struct interval_tree_node *node;
	struct mmu_interval_notifier *res = NULL;

	spin_lock(&subscriptions->lock);
	subscriptions->active_invalidate_ranges++;
	node = interval_tree_iter_first(&subscriptions->itree, range->start,
					range->end - 1);
	if (node) {
		subscriptions->invalidate_seq |= 1;
		res = container_of(node, struct mmu_interval_notifier,
				   interval_tree);
	}

	*seq = subscriptions->invalidate_seq;
	spin_unlock(&subscriptions->lock);
	return res;
}

static struct mmu_interval_notifier *
mn_itree_inv_next(struct mmu_interval_notifier *interval_sub,
		  const struct mmu_notifier_range *range)
{
	struct interval_tree_node *node;

	node = interval_tree_iter_next(&interval_sub->interval_tree,
				       range->start, range->end - 1);
	if (!node)
		return NULL;
	return container_of(node, struct mmu_interval_notifier, interval_tree);
}

static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions)
{
	struct mmu_interval_notifier *interval_sub;
	struct hlist_node *next;

	spin_lock(&subscriptions->lock);
	if (--subscriptions->active_invalidate_ranges ||
	    !mn_itree_is_invalidating(subscriptions)) {
		spin_unlock(&subscriptions->lock);
		return;
	}

	/* Make invalidate_seq even */
	subscriptions->invalidate_seq++;

	/*
	 * The inv_end incorporates a deferred mechanism like rtnl_unlock().
	 * Adds and removes are queued until the final inv_end happens then
	 * they are progressed. This arrangement for tree updates is used to
	 * avoid using a blocking lock during invalidate_range_start.
	 */
	hlist_for_each_entry_safe(interval_sub, next,
				  &subscriptions->deferred_list,
				  deferred_item) {
		if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb))
			interval_tree_insert(&interval_sub->interval_tree,
					     &subscriptions->itree);
		else
			interval_tree_remove(&interval_sub->interval_tree,
					     &subscriptions->itree);
		hlist_del(&interval_sub->deferred_item);
	}
	spin_unlock(&subscriptions->lock);

	wake_up_all(&subscriptions->wq);
}

/**
 * mmu_interval_read_begin - Begin a read side critical section against a VA
 *                           range
 * @interval_sub: The interval subscription
 *
 * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a
 * collision-retry scheme similar to seqcount for the VA range under
 * subscription. If the mm invokes invalidation during the critical section
 * then mmu_interval_read_retry() will return true.
 *
 * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs
 * require a blocking context.  The critical region formed by this can sleep,
 * and the required 'user_lock' can also be a sleeping lock.
 *
 * The caller is required to provide a 'user_lock' to serialize both teardown
 * and setup.
 *
 * The return value should be passed to mmu_interval_read_retry().
 */
unsigned long
mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub)
{
	struct mmu_notifier_subscriptions *subscriptions =
		interval_sub->mm->notifier_subscriptions;
	unsigned long seq;
	bool is_invalidating;

	/*
	 * If the subscription has a different seq value under the user_lock
	 * than we started with then it has collided.
	 *
	 * If the subscription currently has the same seq value as the
	 * subscriptions seq, then it is currently between
	 * invalidate_start/end and is colliding.
	 *
	 * The locking looks broadly like this:
	 *   mn_itree_inv_start():                 mmu_interval_read_begin():
	 *                                         spin_lock
	 *                                          seq = READ_ONCE(interval_sub->invalidate_seq);
	 *                                          seq == subs->invalidate_seq
	 *                                         spin_unlock
	 *    spin_lock
	 *     seq = ++subscriptions->invalidate_seq
	 *    spin_unlock
	 *     op->invalidate():
	 *       user_lock
	 *        mmu_interval_set_seq()
	 *         interval_sub->invalidate_seq = seq
	 *       user_unlock
	 *
	 *                          [Required: mmu_interval_read_retry() == true]
	 *
	 *   mn_itree_inv_end():
	 *    spin_lock
	 *     seq = ++subscriptions->invalidate_seq
	 *    spin_unlock
	 *
	 *                                        user_lock
	 *                                         mmu_interval_read_retry():
	 *                                          interval_sub->invalidate_seq != seq
	 *                                        user_unlock
	 *
	 * Barriers are not needed here as any races here are closed by an
	 * eventual mmu_interval_read_retry(), which provides a barrier via the
	 * user_lock.
	 */
	spin_lock(&subscriptions->lock);
	/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
	seq = READ_ONCE(interval_sub->invalidate_seq);
	is_invalidating = seq == subscriptions->invalidate_seq;
	spin_unlock(&subscriptions->lock);

	/*
	 * interval_sub->invalidate_seq must always be set to an odd value via
	 * mmu_interval_set_seq() using the provided cur_seq from
	 * mn_itree_inv_start_range(). This ensures that if seq does wrap we
	 * will always clear the below sleep in some reasonable time as
	 * subscriptions->invalidate_seq is even in the idle state.
	 */
	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
	if (is_invalidating)
		wait_event(subscriptions->wq,
			   READ_ONCE(subscriptions->invalidate_seq) != seq);

	/*
	 * Notice that mmu_interval_read_retry() can already be true at this
	 * point, avoiding loops here allows the caller to provide a global
	 * time bound.
	 */

	return seq;
}
EXPORT_SYMBOL_GPL(mmu_interval_read_begin);

static void mn_itree_release(struct mmu_notifier_subscriptions *subscriptions,
			     struct mm_struct *mm)
{
	struct mmu_notifier_range range = {
		.flags = MMU_NOTIFIER_RANGE_BLOCKABLE,
		.event = MMU_NOTIFY_RELEASE,
		.mm = mm,
		.start = 0,
		.end = ULONG_MAX,
	};
	struct mmu_interval_notifier *interval_sub;
	unsigned long cur_seq;
	bool ret;

	for (interval_sub =
		     mn_itree_inv_start_range(subscriptions, &range, &cur_seq);
	     interval_sub;
	     interval_sub = mn_itree_inv_next(interval_sub, &range)) {
		ret = interval_sub->ops->invalidate(interval_sub, &range,
						    cur_seq);
		WARN_ON(!ret);
	}

	mn_itree_inv_end(subscriptions);
}

/*
 * This function can't run concurrently against mmu_notifier_register
 * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
 * runs with mm_users == 0. Other tasks may still invoke mmu notifiers
 * in parallel despite there being no task using this mm any more,
 * through the vmas outside of the exit_mmap context, such as with
 * vmtruncate. This serializes against mmu_notifier_unregister with
 * the notifier_subscriptions->lock in addition to SRCU and it serializes
 * against the other mmu notifiers with SRCU. struct mmu_notifier_subscriptions
 * can't go away from under us as exit_mmap holds an mm_count pin
 * itself.
 */
static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions,
			     struct mm_struct *mm)
{
	struct mmu_notifier *subscription;
	int id;

	/*
	 * SRCU here will block mmu_notifier_unregister until
	 * ->release returns.
	 */
	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu))
		/*
		 * If ->release runs before mmu_notifier_unregister it must be
		 * handled, as it's the only way for the driver to flush all
		 * existing sptes and stop the driver from establishing any more
		 * sptes before all the pages in the mm are freed.
		 */
		if (subscription->ops->release)
			subscription->ops->release(subscription, mm);

	spin_lock(&subscriptions->lock);
	while (unlikely(!hlist_empty(&subscriptions->list))) {
		subscription = hlist_entry(subscriptions->list.first,
					   struct mmu_notifier, hlist);
		/*
		 * We arrived before mmu_notifier_unregister so
		 * mmu_notifier_unregister will do nothing other than to wait
		 * for ->release to finish and for mmu_notifier_unregister to
		 * return.
		 */
		hlist_del_init_rcu(&subscription->hlist);
	}
	spin_unlock(&subscriptions->lock);
	srcu_read_unlock(&srcu, id);

	/*
	 * synchronize_srcu here prevents mmu_notifier_release from returning to
	 * exit_mmap (which would proceed with freeing all pages in the mm)
	 * until the ->release method returns, if it was invoked by
	 * mmu_notifier_unregister.
	 *
	 * The notifier_subscriptions can't go away from under us because
	 * one mm_count is held by exit_mmap.
	 */
	synchronize_srcu(&srcu);
}

void __mmu_notifier_release(struct mm_struct *mm)
{
	struct mmu_notifier_subscriptions *subscriptions =
		mm->notifier_subscriptions;

	if (subscriptions->has_itree)
		mn_itree_release(subscriptions, mm);

	if (!hlist_empty(&subscriptions->list))
		mn_hlist_release(subscriptions, mm);
}

/*
 * If no young bitflag is supported by the hardware, ->clear_flush_young can
 * unmap the address and return 1 or 0 depending if the mapping previously
 * existed or not.
 */
int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
					unsigned long start,
					unsigned long end)
{
	struct mmu_notifier *subscription;
	int young = 0, id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription,
				 &mm->notifier_subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		if (subscription->ops->clear_flush_young)
			young |= subscription->ops->clear_flush_young(
				subscription, mm, start, end);
	}
	srcu_read_unlock(&srcu, id);

	return young;
}

int __mmu_notifier_clear_young(struct mm_struct *mm,
			       unsigned long start,
			       unsigned long end)
{
	struct mmu_notifier *subscription;
	int young = 0, id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription,
				 &mm->notifier_subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		if (subscription->ops->clear_young)
			young |= subscription->ops->clear_young(subscription,
								mm, start, end);
	}
	srcu_read_unlock(&srcu, id);

	return young;
}

int __mmu_notifier_test_young(struct mm_struct *mm,
			      unsigned long address)
{
	struct mmu_notifier *subscription;
	int young = 0, id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription,
				 &mm->notifier_subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		if (subscription->ops->test_young) {
			young = subscription->ops->test_young(subscription, mm,
							      address);
			if (young)
				break;
		}
	}
	srcu_read_unlock(&srcu, id);

	return young;
}

void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
			       pte_t pte)
{
	struct mmu_notifier *subscription;
	int id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription,
				 &mm->notifier_subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		if (subscription->ops->change_pte)
			subscription->ops->change_pte(subscription, mm, address,
						      pte);
	}
	srcu_read_unlock(&srcu, id);
}

static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions,
			       const struct mmu_notifier_range *range)
{
	struct mmu_interval_notifier *interval_sub;
	unsigned long cur_seq;

	for (interval_sub =
		     mn_itree_inv_start_range(subscriptions, range, &cur_seq);
	     interval_sub;
	     interval_sub = mn_itree_inv_next(interval_sub, range)) {
		bool ret;

		ret = interval_sub->ops->invalidate(interval_sub, range,
						    cur_seq);
		if (!ret) {
			if (WARN_ON(mmu_notifier_range_blockable(range)))
				continue;
			goto out_would_block;
		}
	}
	return 0;

out_would_block:
	/*
	 * On -EAGAIN the non-blocking caller is not allowed to call
	 * invalidate_range_end()
	 */
	mn_itree_inv_end(subscriptions);
	return -EAGAIN;
}

static int mn_hlist_invalidate_range_start(
	struct mmu_notifier_subscriptions *subscriptions,
	struct mmu_notifier_range *range)
{
	struct mmu_notifier *subscription;
	int ret = 0;
	int id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		const struct mmu_notifier_ops *ops = subscription->ops;

		if (ops->invalidate_range_start) {
			int _ret;

			if (!mmu_notifier_range_blockable(range))
				non_block_start();
			_ret = ops->invalidate_range_start(subscription, range);
			if (!mmu_notifier_range_blockable(range))
				non_block_end();
			if (_ret) {
				pr_info("%pS callback failed with %d in %sblockable context.\n",
					ops->invalidate_range_start, _ret,
					!mmu_notifier_range_blockable(range) ?
						"non-" :
						"");
				WARN_ON(mmu_notifier_range_blockable(range) ||
					_ret != -EAGAIN);
				/*
				 * We call all the notifiers on any EAGAIN,
				 * there is no way for a notifier to know if
				 * its start method failed, thus a start that
				 * does EAGAIN can't also do end.
				 */
				WARN_ON(ops->invalidate_range_end);
				ret = _ret;
			}
		}
	}

	if (ret) {
		/*
		 * Must be non-blocking to get here.  If there are multiple
		 * notifiers and one or more failed start, any that succeeded
		 * start are expecting their end to be called.  Do so now.
		 */
		hlist_for_each_entry_rcu(subscription, &subscriptions->list,
					 hlist, srcu_read_lock_held(&srcu)) {
			if (!subscription->ops->invalidate_range_end)
				continue;

			subscription->ops->invalidate_range_end(subscription,
								range);
		}
	}
	srcu_read_unlock(&srcu, id);

	return ret;
}

int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
{
	struct mmu_notifier_subscriptions *subscriptions =
		range->mm->notifier_subscriptions;
	int ret;

	if (subscriptions->has_itree) {
		ret = mn_itree_invalidate(subscriptions, range);
		if (ret)
			return ret;
	}
	if (!hlist_empty(&subscriptions->list))
		return mn_hlist_invalidate_range_start(subscriptions, range);
	return 0;
}

static void
mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions,
			struct mmu_notifier_range *range)
{
	struct mmu_notifier *subscription;
	int id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		if (subscription->ops->invalidate_range_end) {
			if (!mmu_notifier_range_blockable(range))
				non_block_start();
			subscription->ops->invalidate_range_end(subscription,
								range);
			if (!mmu_notifier_range_blockable(range))
				non_block_end();
		}
	}
	srcu_read_unlock(&srcu, id);
}

void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
{
	struct mmu_notifier_subscriptions *subscriptions =
		range->mm->notifier_subscriptions;

	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
	if (subscriptions->has_itree)
		mn_itree_inv_end(subscriptions);

	if (!hlist_empty(&subscriptions->list))
		mn_hlist_invalidate_end(subscriptions, range);
	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
}

void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
					unsigned long start, unsigned long end)
{
	struct mmu_notifier *subscription;
	int id;

	id = srcu_read_lock(&srcu);
	hlist_for_each_entry_rcu(subscription,
				 &mm->notifier_subscriptions->list, hlist,
				 srcu_read_lock_held(&srcu)) {
		if (subscription->ops->arch_invalidate_secondary_tlbs)
			subscription->ops->arch_invalidate_secondary_tlbs(
				subscription, mm,
				start, end);
	}
	srcu_read_unlock(&srcu, id);
}

/*
 * Same as mmu_notifier_register but here the caller must hold the mmap_lock in
 * write mode. A NULL mn signals the notifier is being registered for itree
 * mode.
 */
int __mmu_notifier_register(struct mmu_notifier *subscription,
			    struct mm_struct *mm)
{
	struct mmu_notifier_subscriptions *subscriptions = NULL;
	int ret;

	mmap_assert_write_locked(mm);
	BUG_ON(atomic_read(&mm->mm_users) <= 0);

	/*
	 * Subsystems should only register for invalidate_secondary_tlbs() or
	 * invalidate_range_start()/end() callbacks, not both.
	 */
	if (WARN_ON_ONCE(subscription &&
			 (subscription->ops->arch_invalidate_secondary_tlbs &&
			 (subscription->ops->invalidate_range_start ||
			  subscription->ops->invalidate_range_end))))
		return -EINVAL;

	if (!mm->notifier_subscriptions) {
		/*
		 * kmalloc cannot be called under mm_take_all_locks(), but we
		 * know that mm->notifier_subscriptions can't change while we
		 * hold the write side of the mmap_lock.
		 */
		subscriptions = kzalloc(
			sizeof(struct mmu_notifier_subscriptions), GFP_KERNEL);
		if (!subscriptions)
			return -ENOMEM;

		INIT_HLIST_HEAD(&subscriptions->list);
		spin_lock_init(&subscriptions->lock);
		subscriptions->invalidate_seq = 2;
		subscriptions->itree = RB_ROOT_CACHED;
		init_waitqueue_head(&subscriptions->wq);
		INIT_HLIST_HEAD(&subscriptions->deferred_list);
	}

	ret = mm_take_all_locks(mm);
	if (unlikely(ret))
		goto out_clean;

	/*
	 * Serialize the update against mmu_notifier_unregister. A
	 * side note: mmu_notifier_release can't run concurrently with
	 * us because we hold the mm_users pin (either implicitly as
	 * current->mm or explicitly with get_task_mm() or similar).
	 * We can't race against any other mmu notifier method either
	 * thanks to mm_take_all_locks().
	 *
	 * release semantics on the initialization of the
	 * mmu_notifier_subscriptions's contents are provided for unlocked
	 * readers.  acquire can only be used while holding the mmgrab or
	 * mmget, and is safe because once created the
	 * mmu_notifier_subscriptions is not freed until the mm is destroyed.
	 * As above, users holding the mmap_lock or one of the
	 * mm_take_all_locks() do not need to use acquire semantics.
	 */
	if (subscriptions)
		smp_store_release(&mm->notifier_subscriptions, subscriptions);

	if (subscription) {
		/* Pairs with the mmdrop in mmu_notifier_unregister_* */
		mmgrab(mm);
		subscription->mm = mm;
		subscription->users = 1;

		spin_lock(&mm->notifier_subscriptions->lock);
		hlist_add_head_rcu(&subscription->hlist,
				   &mm->notifier_subscriptions->list);
		spin_unlock(&mm->notifier_subscriptions->lock);
	} else
		mm->notifier_subscriptions->has_itree = true;

	mm_drop_all_locks(mm);
	BUG_ON(atomic_read(&mm->mm_users) <= 0);
	return 0;

out_clean:
	kfree(subscriptions);
	return ret;
}
EXPORT_SYMBOL_GPL(__mmu_notifier_register);

/**
 * mmu_notifier_register - Register a notifier on a mm
 * @subscription: The notifier to attach
 * @mm: The mm to attach the notifier to
 *
 * Must not hold mmap_lock nor any other VM related lock when calling
 * this registration function. Must also ensure mm_users can't go down
 * to zero while this runs to avoid races with mmu_notifier_release,
 * so mm has to be current->mm or the mm should be pinned safely such
 * as with get_task_mm(). If the mm is not current->mm, the mm_users
 * pin should be released by calling mmput after mmu_notifier_register
 * returns.
 *
 * mmu_notifier_unregister() or mmu_notifier_put() must be always called to
 * unregister the notifier.
 *
 * While the caller has a mmu_notifier get the subscription->mm pointer will remain
 * valid, and can be converted to an active mm pointer via mmget_not_zero().
 */
int mmu_notifier_register(struct mmu_notifier *subscription,
			  struct mm_struct *mm)
{
	int ret;

	mmap_write_lock(mm);
	ret = __mmu_notifier_register(subscription, mm);
	mmap_write_unlock(mm);
	return ret;
}
EXPORT_SYMBOL_GPL(mmu_notifier_register);

static struct mmu_notifier *
find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops)
{
	struct mmu_notifier *subscription;

	spin_lock(&mm->notifier_subscriptions->lock);
	hlist_for_each_entry_rcu(subscription,
				 &mm->notifier_subscriptions->list, hlist,
				 lockdep_is_held(&mm->notifier_subscriptions->lock)) {
		if (subscription->ops != ops)
			continue;

		if (likely(subscription->users != UINT_MAX))
			subscription->users++;
		else
			subscription = ERR_PTR(-EOVERFLOW);
		spin_unlock(&mm->notifier_subscriptions->lock);
		return subscription;
	}
	spin_unlock(&mm->notifier_subscriptions->lock);
	return NULL;
}

/**
 * mmu_notifier_get_locked - Return the single struct mmu_notifier for
 *                           the mm & ops
 * @ops: The operations struct being subscribe with
 * @mm : The mm to attach notifiers too
 *
 * This function either allocates a new mmu_notifier via
 * ops->alloc_notifier(), or returns an already existing notifier on the
 * list. The value of the ops pointer is used to determine when two notifiers
 * are the same.
 *
 * Each call to mmu_notifier_get() must be paired with a call to
 * mmu_notifier_put(). The caller must hold the write side of mm->mmap_lock.
 *
 * While the caller has a mmu_notifier get the mm pointer will remain valid,
 * and can be converted to an active mm pointer via mmget_not_zero().
 */
struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops,
					     struct mm_struct *mm)
{
	struct mmu_notifier *subscription;
	int ret;

	mmap_assert_write_locked(mm);

	if (mm->notifier_subscriptions) {
		subscription = find_get_mmu_notifier(mm, ops);
		if (subscription)
			return subscription;
	}

	subscription = ops->alloc_notifier(mm);
	if (IS_ERR(subscription))
		return subscription;
	subscription->ops = ops;
	ret = __mmu_notifier_register(subscription, mm);
	if (ret)
		goto out_free;
	return subscription;
out_free:
	subscription->ops->free_notifier(subscription);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(mmu_notifier_get_locked);

/* this is called after the last mmu_notifier_unregister() returned */
void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
{
	BUG_ON(!hlist_empty(&mm->notifier_subscriptions->list));
	kfree(mm->notifier_subscriptions);
	mm->notifier_subscriptions = LIST_POISON1; /* debug */
}

/*
 * This releases the mm_count pin automatically and frees the mm
 * structure if it was the last user of it. It serializes against
 * running mmu notifiers with SRCU and against mmu_notifier_unregister
 * with the unregister lock + SRCU. All sptes must be dropped before
 * calling mmu_notifier_unregister. ->release or any other notifier
 * method may be invoked concurrently with mmu_notifier_unregister,
 * and only after mmu_notifier_unregister returned we're guaranteed
 * that ->release or any other method can't run anymore.
 */
void mmu_notifier_unregister(struct mmu_notifier *subscription,
			     struct mm_struct *mm)
{
	BUG_ON(atomic_read(&mm->mm_count) <= 0);

	if (!hlist_unhashed(&subscription->hlist)) {
		/*
		 * SRCU here will force exit_mmap to wait for ->release to
		 * finish before freeing the pages.
		 */
		int id;

		id = srcu_read_lock(&srcu);
		/*
		 * exit_mmap will block in mmu_notifier_release to guarantee
		 * that ->release is called before freeing the pages.
		 */
		if (subscription->ops->release)
			subscription->ops->release(subscription, mm);
		srcu_read_unlock(&srcu, id);

		spin_lock(&mm->notifier_subscriptions->lock);
		/*
		 * Can not use list_del_rcu() since __mmu_notifier_release
		 * can delete it before we hold the lock.
		 */
		hlist_del_init_rcu(&subscription->hlist);
		spin_unlock(&mm->notifier_subscriptions->lock);
	}

	/*
	 * Wait for any running method to finish, of course including
	 * ->release if it was run by mmu_notifier_release instead of us.
	 */
	synchronize_srcu(&srcu);

	BUG_ON(atomic_read(&mm->mm_count) <= 0);

	mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_notifier_unregister);

static void mmu_notifier_free_rcu(struct rcu_head *rcu)
{
	struct mmu_notifier *subscription =
		container_of(rcu, struct mmu_notifier, rcu);
	struct mm_struct *mm = subscription->mm;

	subscription->ops->free_notifier(subscription);
	/* Pairs with the get in __mmu_notifier_register() */
	mmdrop(mm);
}

/**
 * mmu_notifier_put - Release the reference on the notifier
 * @subscription: The notifier to act on
 *
 * This function must be paired with each mmu_notifier_get(), it releases the
 * reference obtained by the get. If this is the last reference then process
 * to free the notifier will be run asynchronously.
 *
 * Unlike mmu_notifier_unregister() the get/put flow only calls ops->release
 * when the mm_struct is destroyed. Instead free_notifier is always called to
 * release any resources held by the user.
 *
 * As ops->release is not guaranteed to be called, the user must ensure that
 * all sptes are dropped, and no new sptes can be established before
 * mmu_notifier_put() is called.
 *
 * This function can be called from the ops->release callback, however the
 * caller must still ensure it is called pairwise with mmu_notifier_get().
 *
 * Modules calling this function must call mmu_notifier_synchronize() in
 * their __exit functions to ensure the async work is completed.
 */
void mmu_notifier_put(struct mmu_notifier *subscription)
{
	struct mm_struct *mm = subscription->mm;

	spin_lock(&mm->notifier_subscriptions->lock);
	if (WARN_ON(!subscription->users) || --subscription->users)
		goto out_unlock;
	hlist_del_init_rcu(&subscription->hlist);
	spin_unlock(&mm->notifier_subscriptions->lock);

	call_srcu(&srcu, &subscription->rcu, mmu_notifier_free_rcu);
	return;

out_unlock:
	spin_unlock(&mm->notifier_subscriptions->lock);
}
EXPORT_SYMBOL_GPL(mmu_notifier_put);

static int __mmu_interval_notifier_insert(
	struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
	struct mmu_notifier_subscriptions *subscriptions, unsigned long start,
	unsigned long length, const struct mmu_interval_notifier_ops *ops)
{
	interval_sub->mm = mm;
	interval_sub->ops = ops;
	RB_CLEAR_NODE(&interval_sub->interval_tree.rb);
	interval_sub->interval_tree.start = start;
	/*
	 * Note that the representation of the intervals in the interval tree
	 * considers the ending point as contained in the interval.
	 */
	if (length == 0 ||
	    check_add_overflow(start, length - 1,
			       &interval_sub->interval_tree.last))
		return -EOVERFLOW;

	/* Must call with a mmget() held */
	if (WARN_ON(atomic_read(&mm->mm_users) <= 0))
		return -EINVAL;

	/* pairs with mmdrop in mmu_interval_notifier_remove() */
	mmgrab(mm);

	/*
	 * If some invalidate_range_start/end region is going on in parallel
	 * we don't know what VA ranges are affected, so we must assume this
	 * new range is included.
	 *
	 * If the itree is invalidating then we are not allowed to change
	 * it. Retrying until invalidation is done is tricky due to the
	 * possibility for live lock, instead defer the add to
	 * mn_itree_inv_end() so this algorithm is deterministic.
	 *
	 * In all cases the value for the interval_sub->invalidate_seq should be
	 * odd, see mmu_interval_read_begin()
	 */
	spin_lock(&subscriptions->lock);
	if (subscriptions->active_invalidate_ranges) {
		if (mn_itree_is_invalidating(subscriptions))
			hlist_add_head(&interval_sub->deferred_item,
				       &subscriptions->deferred_list);
		else {
			subscriptions->invalidate_seq |= 1;
			interval_tree_insert(&interval_sub->interval_tree,
					     &subscriptions->itree);
		}
		interval_sub->invalidate_seq = subscriptions->invalidate_seq;
	} else {
		WARN_ON(mn_itree_is_invalidating(subscriptions));
		/*
		 * The starting seq for a subscription not under invalidation
		 * should be odd, not equal to the current invalidate_seq and
		 * invalidate_seq should not 'wrap' to the new seq any time
		 * soon.
		 */
		interval_sub->invalidate_seq =
			subscriptions->invalidate_seq - 1;
		interval_tree_insert(&interval_sub->interval_tree,
				     &subscriptions->itree);
	}
	spin_unlock(&subscriptions->lock);
	return 0;
}

/**
 * mmu_interval_notifier_insert - Insert an interval notifier
 * @interval_sub: Interval subscription to register
 * @start: Starting virtual address to monitor
 * @length: Length of the range to monitor
 * @mm: mm_struct to attach to
 * @ops: Interval notifier operations to be called on matching events
 *
 * This function subscribes the interval notifier for notifications from the
 * mm.  Upon return the ops related to mmu_interval_notifier will be called
 * whenever an event that intersects with the given range occurs.
 *
 * Upon return the range_notifier may not be present in the interval tree yet.
 * The caller must use the normal interval notifier read flow via
 * mmu_interval_read_begin() to establish SPTEs for this range.
 */
int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub,
				 struct mm_struct *mm, unsigned long start,
				 unsigned long length,
				 const struct mmu_interval_notifier_ops *ops)
{
	struct mmu_notifier_subscriptions *subscriptions;
	int ret;

	might_lock(&mm->mmap_lock);

	subscriptions = smp_load_acquire(&mm->notifier_subscriptions);
	if (!subscriptions || !subscriptions->has_itree) {
		ret = mmu_notifier_register(NULL, mm);
		if (ret)
			return ret;
		subscriptions = mm->notifier_subscriptions;
	}
	return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions,
					      start, length, ops);
}
EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert);

int mmu_interval_notifier_insert_locked(
	struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
	unsigned long start, unsigned long length,
	const struct mmu_interval_notifier_ops *ops)
{
	struct mmu_notifier_subscriptions *subscriptions =
		mm->notifier_subscriptions;
	int ret;

	mmap_assert_write_locked(mm);

	if (!subscriptions || !subscriptions->has_itree) {
		ret = __mmu_notifier_register(NULL, mm);
		if (ret)
			return ret;
		subscriptions = mm->notifier_subscriptions;
	}
	return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions,
					      start, length, ops);
}
EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked);

static bool
mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions,
			  unsigned long seq)
{
	bool ret;

	spin_lock(&subscriptions->lock);
	ret = subscriptions->invalidate_seq != seq;
	spin_unlock(&subscriptions->lock);
	return ret;
}

/**
 * mmu_interval_notifier_remove - Remove a interval notifier
 * @interval_sub: Interval subscription to unregister
 *
 * This function must be paired with mmu_interval_notifier_insert(). It cannot
 * be called from any ops callback.
 *
 * Once this returns ops callbacks are no longer running on other CPUs and
 * will not be called in future.
 */
void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub)
{
	struct mm_struct *mm = interval_sub->mm;
	struct mmu_notifier_subscriptions *subscriptions =
		mm->notifier_subscriptions;
	unsigned long seq = 0;

	might_sleep();

	spin_lock(&subscriptions->lock);
	if (mn_itree_is_invalidating(subscriptions)) {
		/*
		 * remove is being called after insert put this on the
		 * deferred list, but before the deferred list was processed.
		 */
		if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) {
			hlist_del(&interval_sub->deferred_item);
		} else {
			hlist_add_head(&interval_sub->deferred_item,
				       &subscriptions->deferred_list);
			seq = subscriptions->invalidate_seq;
		}
	} else {
		WARN_ON(RB_EMPTY_NODE(&interval_sub->interval_tree.rb));
		interval_tree_remove(&interval_sub->interval_tree,
				     &subscriptions->itree);
	}
	spin_unlock(&subscriptions->lock);

	/*
	 * The possible sleep on progress in the invalidation requires the
	 * caller not hold any locks held by invalidation callbacks.
	 */
	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
	if (seq)
		wait_event(subscriptions->wq,
			   mmu_interval_seq_released(subscriptions, seq));

	/* pairs with mmgrab in mmu_interval_notifier_insert() */
	mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove);

/**
 * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed
 *
 * This function ensures that all outstanding async SRU work from
 * mmu_notifier_put() is completed. After it returns any mmu_notifier_ops
 * associated with an unused mmu_notifier will no longer be called.
 *
 * Before using the caller must ensure that all of its mmu_notifiers have been
 * fully released via mmu_notifier_put().
 *
 * Modules using the mmu_notifier_put() API should call this in their __exit
 * function to avoid module unloading races.
 */
void mmu_notifier_synchronize(void)
{
	synchronize_srcu(&srcu);
}
EXPORT_SYMBOL_GPL(mmu_notifier_synchronize);