aboutsummaryrefslogtreecommitdiff
path: root/mm/workingset.c
blob: ae7e984b23c6b08e99c25adaf1b8533e623e4c49 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Workingset detection
 *
 * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
 */

#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/shmem_fs.h>
#include <linux/pagemap.h>
#include <linux/atomic.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>

/*
 *		Double CLOCK lists
 *
 * Per node, two clock lists are maintained for file pages: the
 * inactive and the active list.  Freshly faulted pages start out at
 * the head of the inactive list and page reclaim scans pages from the
 * tail.  Pages that are accessed multiple times on the inactive list
 * are promoted to the active list, to protect them from reclaim,
 * whereas active pages are demoted to the inactive list when the
 * active list grows too big.
 *
 *   fault ------------------------+
 *                                 |
 *              +--------------+   |            +-------------+
 *   reclaim <- |   inactive   | <-+-- demotion |    active   | <--+
 *              +--------------+                +-------------+    |
 *                     |                                           |
 *                     +-------------- promotion ------------------+
 *
 *
 *		Access frequency and refault distance
 *
 * A workload is thrashing when its pages are frequently used but they
 * are evicted from the inactive list every time before another access
 * would have promoted them to the active list.
 *
 * In cases where the average access distance between thrashing pages
 * is bigger than the size of memory there is nothing that can be
 * done - the thrashing set could never fit into memory under any
 * circumstance.
 *
 * However, the average access distance could be bigger than the
 * inactive list, yet smaller than the size of memory.  In this case,
 * the set could fit into memory if it weren't for the currently
 * active pages - which may be used more, hopefully less frequently:
 *
 *      +-memory available to cache-+
 *      |                           |
 *      +-inactive------+-active----+
 *  a b | c d e f g h i | J K L M N |
 *      +---------------+-----------+
 *
 * It is prohibitively expensive to accurately track access frequency
 * of pages.  But a reasonable approximation can be made to measure
 * thrashing on the inactive list, after which refaulting pages can be
 * activated optimistically to compete with the existing active pages.
 *
 * Approximating inactive page access frequency - Observations:
 *
 * 1. When a page is accessed for the first time, it is added to the
 *    head of the inactive list, slides every existing inactive page
 *    towards the tail by one slot, and pushes the current tail page
 *    out of memory.
 *
 * 2. When a page is accessed for the second time, it is promoted to
 *    the active list, shrinking the inactive list by one slot.  This
 *    also slides all inactive pages that were faulted into the cache
 *    more recently than the activated page towards the tail of the
 *    inactive list.
 *
 * Thus:
 *
 * 1. The sum of evictions and activations between any two points in
 *    time indicate the minimum number of inactive pages accessed in
 *    between.
 *
 * 2. Moving one inactive page N page slots towards the tail of the
 *    list requires at least N inactive page accesses.
 *
 * Combining these:
 *
 * 1. When a page is finally evicted from memory, the number of
 *    inactive pages accessed while the page was in cache is at least
 *    the number of page slots on the inactive list.
 *
 * 2. In addition, measuring the sum of evictions and activations (E)
 *    at the time of a page's eviction, and comparing it to another
 *    reading (R) at the time the page faults back into memory tells
 *    the minimum number of accesses while the page was not cached.
 *    This is called the refault distance.
 *
 * Because the first access of the page was the fault and the second
 * access the refault, we combine the in-cache distance with the
 * out-of-cache distance to get the complete minimum access distance
 * of this page:
 *
 *      NR_inactive + (R - E)
 *
 * And knowing the minimum access distance of a page, we can easily
 * tell if the page would be able to stay in cache assuming all page
 * slots in the cache were available:
 *
 *   NR_inactive + (R - E) <= NR_inactive + NR_active
 *
 * which can be further simplified to
 *
 *   (R - E) <= NR_active
 *
 * Put into words, the refault distance (out-of-cache) can be seen as
 * a deficit in inactive list space (in-cache).  If the inactive list
 * had (R - E) more page slots, the page would not have been evicted
 * in between accesses, but activated instead.  And on a full system,
 * the only thing eating into inactive list space is active pages.
 *
 *
 *		Refaulting inactive pages
 *
 * All that is known about the active list is that the pages have been
 * accessed more than once in the past.  This means that at any given
 * time there is actually a good chance that pages on the active list
 * are no longer in active use.
 *
 * So when a refault distance of (R - E) is observed and there are at
 * least (R - E) active pages, the refaulting page is activated
 * optimistically in the hope that (R - E) active pages are actually
 * used less frequently than the refaulting page - or even not used at
 * all anymore.
 *
 * That means if inactive cache is refaulting with a suitable refault
 * distance, we assume the cache workingset is transitioning and put
 * pressure on the current active list.
 *
 * If this is wrong and demotion kicks in, the pages which are truly
 * used more frequently will be reactivated while the less frequently
 * used once will be evicted from memory.
 *
 * But if this is right, the stale pages will be pushed out of memory
 * and the used pages get to stay in cache.
 *
 *		Refaulting active pages
 *
 * If on the other hand the refaulting pages have recently been
 * deactivated, it means that the active list is no longer protecting
 * actively used cache from reclaim. The cache is NOT transitioning to
 * a different workingset; the existing workingset is thrashing in the
 * space allocated to the page cache.
 *
 *
 *		Implementation
 *
 * For each node's LRU lists, a counter for inactive evictions and
 * activations is maintained (node->nonresident_age).
 *
 * On eviction, a snapshot of this counter (along with some bits to
 * identify the node) is stored in the now empty page cache
 * slot of the evicted page.  This is called a shadow entry.
 *
 * On cache misses for which there are shadow entries, an eligible
 * refault distance will immediately activate the refaulting page.
 */

#define WORKINGSET_SHIFT 1
#define EVICTION_SHIFT	((BITS_PER_LONG - BITS_PER_XA_VALUE) +	\
			 WORKINGSET_SHIFT + NODES_SHIFT + \
			 MEM_CGROUP_ID_SHIFT)
#define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)

/*
 * Eviction timestamps need to be able to cover the full range of
 * actionable refaults. However, bits are tight in the xarray
 * entry, and after storing the identifier for the lruvec there might
 * not be enough left to represent every single actionable refault. In
 * that case, we have to sacrifice granularity for distance, and group
 * evictions into coarser buckets by shaving off lower timestamp bits.
 */
static unsigned int bucket_order __read_mostly;

static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
			 bool workingset)
{
	eviction &= EVICTION_MASK;
	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
	eviction = (eviction << WORKINGSET_SHIFT) | workingset;

	return xa_mk_value(eviction);
}

static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
			  unsigned long *evictionp, bool *workingsetp)
{
	unsigned long entry = xa_to_value(shadow);
	int memcgid, nid;
	bool workingset;

	workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1);
	entry >>= WORKINGSET_SHIFT;
	nid = entry & ((1UL << NODES_SHIFT) - 1);
	entry >>= NODES_SHIFT;
	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
	entry >>= MEM_CGROUP_ID_SHIFT;

	*memcgidp = memcgid;
	*pgdat = NODE_DATA(nid);
	*evictionp = entry;
	*workingsetp = workingset;
}

#ifdef CONFIG_LRU_GEN

static void *lru_gen_eviction(struct folio *folio)
{
	int hist;
	unsigned long token;
	unsigned long min_seq;
	struct lruvec *lruvec;
	struct lru_gen_struct *lrugen;
	int type = folio_is_file_lru(folio);
	int delta = folio_nr_pages(folio);
	int refs = folio_lru_refs(folio);
	int tier = lru_tier_from_refs(refs);
	struct mem_cgroup *memcg = folio_memcg(folio);
	struct pglist_data *pgdat = folio_pgdat(folio);

	BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT);

	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	lrugen = &lruvec->lrugen;
	min_seq = READ_ONCE(lrugen->min_seq[type]);
	token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0);

	hist = lru_hist_from_seq(min_seq);
	atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);

	return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
}

static void lru_gen_refault(struct folio *folio, void *shadow)
{
	int hist, tier, refs;
	int memcg_id;
	bool workingset;
	unsigned long token;
	unsigned long min_seq;
	struct lruvec *lruvec;
	struct lru_gen_struct *lrugen;
	struct mem_cgroup *memcg;
	struct pglist_data *pgdat;
	int type = folio_is_file_lru(folio);
	int delta = folio_nr_pages(folio);

	unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset);

	if (pgdat != folio_pgdat(folio))
		return;

	rcu_read_lock();

	memcg = folio_memcg_rcu(folio);
	if (memcg_id != mem_cgroup_id(memcg))
		goto unlock;

	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	lrugen = &lruvec->lrugen;

	min_seq = READ_ONCE(lrugen->min_seq[type]);
	if ((token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)))
		goto unlock;

	hist = lru_hist_from_seq(min_seq);
	/* see the comment in folio_lru_refs() */
	refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset;
	tier = lru_tier_from_refs(refs);

	atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
	mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta);

	/*
	 * Count the following two cases as stalls:
	 * 1. For pages accessed through page tables, hotter pages pushed out
	 *    hot pages which refaulted immediately.
	 * 2. For pages accessed multiple times through file descriptors,
	 *    numbers of accesses might have been out of the range.
	 */
	if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
		folio_set_workingset(folio);
		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
	}
unlock:
	rcu_read_unlock();
}

#else /* !CONFIG_LRU_GEN */

static void *lru_gen_eviction(struct folio *folio)
{
	return NULL;
}

static void lru_gen_refault(struct folio *folio, void *shadow)
{
}

#endif /* CONFIG_LRU_GEN */

/**
 * workingset_age_nonresident - age non-resident entries as LRU ages
 * @lruvec: the lruvec that was aged
 * @nr_pages: the number of pages to count
 *
 * As in-memory pages are aged, non-resident pages need to be aged as
 * well, in order for the refault distances later on to be comparable
 * to the in-memory dimensions. This function allows reclaim and LRU
 * operations to drive the non-resident aging along in parallel.
 */
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
{
	/*
	 * Reclaiming a cgroup means reclaiming all its children in a
	 * round-robin fashion. That means that each cgroup has an LRU
	 * order that is composed of the LRU orders of its child
	 * cgroups; and every page has an LRU position not just in the
	 * cgroup that owns it, but in all of that group's ancestors.
	 *
	 * So when the physical inactive list of a leaf cgroup ages,
	 * the virtual inactive lists of all its parents, including
	 * the root cgroup's, age as well.
	 */
	do {
		atomic_long_add(nr_pages, &lruvec->nonresident_age);
	} while ((lruvec = parent_lruvec(lruvec)));
}

/**
 * workingset_eviction - note the eviction of a folio from memory
 * @target_memcg: the cgroup that is causing the reclaim
 * @folio: the folio being evicted
 *
 * Return: a shadow entry to be stored in @folio->mapping->i_pages in place
 * of the evicted @folio so that a later refault can be detected.
 */
void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
{
	struct pglist_data *pgdat = folio_pgdat(folio);
	unsigned long eviction;
	struct lruvec *lruvec;
	int memcgid;

	/* Folio is fully exclusive and pins folio's memory cgroup pointer */
	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
	VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);

	if (lru_gen_enabled())
		return lru_gen_eviction(folio);

	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
	/* XXX: target_memcg can be NULL, go through lruvec */
	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
	eviction = atomic_long_read(&lruvec->nonresident_age);
	eviction >>= bucket_order;
	workingset_age_nonresident(lruvec, folio_nr_pages(folio));
	return pack_shadow(memcgid, pgdat, eviction,
				folio_test_workingset(folio));
}

/**
 * workingset_refault - Evaluate the refault of a previously evicted folio.
 * @folio: The freshly allocated replacement folio.
 * @shadow: Shadow entry of the evicted folio.
 *
 * Calculates and evaluates the refault distance of the previously
 * evicted folio in the context of the node and the memcg whose memory
 * pressure caused the eviction.
 */
void workingset_refault(struct folio *folio, void *shadow)
{
	bool file = folio_is_file_lru(folio);
	struct mem_cgroup *eviction_memcg;
	struct lruvec *eviction_lruvec;
	unsigned long refault_distance;
	unsigned long workingset_size;
	struct pglist_data *pgdat;
	struct mem_cgroup *memcg;
	unsigned long eviction;
	struct lruvec *lruvec;
	unsigned long refault;
	bool workingset;
	int memcgid;
	long nr;

	if (lru_gen_enabled()) {
		lru_gen_refault(folio, shadow);
		return;
	}

	unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
	eviction <<= bucket_order;

	rcu_read_lock();
	/*
	 * Look up the memcg associated with the stored ID. It might
	 * have been deleted since the folio's eviction.
	 *
	 * Note that in rare events the ID could have been recycled
	 * for a new cgroup that refaults a shared folio. This is
	 * impossible to tell from the available data. However, this
	 * should be a rare and limited disturbance, and activations
	 * are always speculative anyway. Ultimately, it's the aging
	 * algorithm's job to shake out the minimum access frequency
	 * for the active cache.
	 *
	 * XXX: On !CONFIG_MEMCG, this will always return NULL; it
	 * would be better if the root_mem_cgroup existed in all
	 * configurations instead.
	 */
	eviction_memcg = mem_cgroup_from_id(memcgid);
	if (!mem_cgroup_disabled() && !eviction_memcg)
		goto out;
	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
	refault = atomic_long_read(&eviction_lruvec->nonresident_age);

	/*
	 * Calculate the refault distance
	 *
	 * The unsigned subtraction here gives an accurate distance
	 * across nonresident_age overflows in most cases. There is a
	 * special case: usually, shadow entries have a short lifetime
	 * and are either refaulted or reclaimed along with the inode
	 * before they get too old.  But it is not impossible for the
	 * nonresident_age to lap a shadow entry in the field, which
	 * can then result in a false small refault distance, leading
	 * to a false activation should this old entry actually
	 * refault again.  However, earlier kernels used to deactivate
	 * unconditionally with *every* reclaim invocation for the
	 * longest time, so the occasional inappropriate activation
	 * leading to pressure on the active list is not a problem.
	 */
	refault_distance = (refault - eviction) & EVICTION_MASK;

	/*
	 * The activation decision for this folio is made at the level
	 * where the eviction occurred, as that is where the LRU order
	 * during folio reclaim is being determined.
	 *
	 * However, the cgroup that will own the folio is the one that
	 * is actually experiencing the refault event.
	 */
	nr = folio_nr_pages(folio);
	memcg = folio_memcg(folio);
	lruvec = mem_cgroup_lruvec(memcg, pgdat);

	mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);

	mem_cgroup_flush_stats_delayed();
	/*
	 * Compare the distance to the existing workingset size. We
	 * don't activate pages that couldn't stay resident even if
	 * all the memory was available to the workingset. Whether
	 * workingset competition needs to consider anon or not depends
	 * on having swap.
	 */
	workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
	if (!file) {
		workingset_size += lruvec_page_state(eviction_lruvec,
						     NR_INACTIVE_FILE);
	}
	if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
		workingset_size += lruvec_page_state(eviction_lruvec,
						     NR_ACTIVE_ANON);
		if (file) {
			workingset_size += lruvec_page_state(eviction_lruvec,
						     NR_INACTIVE_ANON);
		}
	}
	if (refault_distance > workingset_size)
		goto out;

	folio_set_active(folio);
	workingset_age_nonresident(lruvec, nr);
	mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr);

	/* Folio was active prior to eviction */
	if (workingset) {
		folio_set_workingset(folio);
		/* XXX: Move to lru_cache_add() when it supports new vs putback */
		lru_note_cost_folio(folio);
		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
	}
out:
	rcu_read_unlock();
}

/**
 * workingset_activation - note a page activation
 * @folio: Folio that is being activated.
 */
void workingset_activation(struct folio *folio)
{
	struct mem_cgroup *memcg;

	rcu_read_lock();
	/*
	 * Filter non-memcg pages here, e.g. unmap can call
	 * mark_page_accessed() on VDSO pages.
	 *
	 * XXX: See workingset_refault() - this should return
	 * root_mem_cgroup even for !CONFIG_MEMCG.
	 */
	memcg = folio_memcg_rcu(folio);
	if (!mem_cgroup_disabled() && !memcg)
		goto out;
	workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio));
out:
	rcu_read_unlock();
}

/*
 * Shadow entries reflect the share of the working set that does not
 * fit into memory, so their number depends on the access pattern of
 * the workload.  In most cases, they will refault or get reclaimed
 * along with the inode, but a (malicious) workload that streams
 * through files with a total size several times that of available
 * memory, while preventing the inodes from being reclaimed, can
 * create excessive amounts of shadow nodes.  To keep a lid on this,
 * track shadow nodes and reclaim them when they grow way past the
 * point where they would still be useful.
 */

struct list_lru shadow_nodes;

void workingset_update_node(struct xa_node *node)
{
	struct address_space *mapping;

	/*
	 * Track non-empty nodes that contain only shadow entries;
	 * unlink those that contain pages or are being freed.
	 *
	 * Avoid acquiring the list_lru lock when the nodes are
	 * already where they should be. The list_empty() test is safe
	 * as node->private_list is protected by the i_pages lock.
	 */
	mapping = container_of(node->array, struct address_space, i_pages);
	lockdep_assert_held(&mapping->i_pages.xa_lock);

	if (node->count && node->count == node->nr_values) {
		if (list_empty(&node->private_list)) {
			list_lru_add(&shadow_nodes, &node->private_list);
			__inc_lruvec_kmem_state(node, WORKINGSET_NODES);
		}
	} else {
		if (!list_empty(&node->private_list)) {
			list_lru_del(&shadow_nodes, &node->private_list);
			__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
		}
	}
}

static unsigned long count_shadow_nodes(struct shrinker *shrinker,
					struct shrink_control *sc)
{
	unsigned long max_nodes;
	unsigned long nodes;
	unsigned long pages;

	nodes = list_lru_shrink_count(&shadow_nodes, sc);
	if (!nodes)
		return SHRINK_EMPTY;

	/*
	 * Approximate a reasonable limit for the nodes
	 * containing shadow entries. We don't need to keep more
	 * shadow entries than possible pages on the active list,
	 * since refault distances bigger than that are dismissed.
	 *
	 * The size of the active list converges toward 100% of
	 * overall page cache as memory grows, with only a tiny
	 * inactive list. Assume the total cache size for that.
	 *
	 * Nodes might be sparsely populated, with only one shadow
	 * entry in the extreme case. Obviously, we cannot keep one
	 * node for every eligible shadow entry, so compromise on a
	 * worst-case density of 1/8th. Below that, not all eligible
	 * refaults can be detected anymore.
	 *
	 * On 64-bit with 7 xa_nodes per page and 64 slots
	 * each, this will reclaim shadow entries when they consume
	 * ~1.8% of available memory:
	 *
	 * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
	 */
#ifdef CONFIG_MEMCG
	if (sc->memcg) {
		struct lruvec *lruvec;
		int i;

		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
			pages += lruvec_page_state_local(lruvec,
							 NR_LRU_BASE + i);
		pages += lruvec_page_state_local(
			lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
		pages += lruvec_page_state_local(
			lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
	} else
#endif
		pages = node_present_pages(sc->nid);

	max_nodes = pages >> (XA_CHUNK_SHIFT - 3);

	if (nodes <= max_nodes)
		return 0;
	return nodes - max_nodes;
}

static enum lru_status shadow_lru_isolate(struct list_head *item,
					  struct list_lru_one *lru,
					  spinlock_t *lru_lock,
					  void *arg) __must_hold(lru_lock)
{
	struct xa_node *node = container_of(item, struct xa_node, private_list);
	struct address_space *mapping;
	int ret;

	/*
	 * Page cache insertions and deletions synchronously maintain
	 * the shadow node LRU under the i_pages lock and the
	 * lru_lock.  Because the page cache tree is emptied before
	 * the inode can be destroyed, holding the lru_lock pins any
	 * address_space that has nodes on the LRU.
	 *
	 * We can then safely transition to the i_pages lock to
	 * pin only the address_space of the particular node we want
	 * to reclaim, take the node off-LRU, and drop the lru_lock.
	 */

	mapping = container_of(node->array, struct address_space, i_pages);

	/* Coming from the list, invert the lock order */
	if (!xa_trylock(&mapping->i_pages)) {
		spin_unlock_irq(lru_lock);
		ret = LRU_RETRY;
		goto out;
	}

	if (!spin_trylock(&mapping->host->i_lock)) {
		xa_unlock(&mapping->i_pages);
		spin_unlock_irq(lru_lock);
		ret = LRU_RETRY;
		goto out;
	}

	list_lru_isolate(lru, item);
	__dec_lruvec_kmem_state(node, WORKINGSET_NODES);

	spin_unlock(lru_lock);

	/*
	 * The nodes should only contain one or more shadow entries,
	 * no pages, so we expect to be able to remove them all and
	 * delete and free the empty node afterwards.
	 */
	if (WARN_ON_ONCE(!node->nr_values))
		goto out_invalid;
	if (WARN_ON_ONCE(node->count != node->nr_values))
		goto out_invalid;
	xa_delete_node(node, workingset_update_node);
	__inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM);

out_invalid:
	xa_unlock_irq(&mapping->i_pages);
	if (mapping_shrinkable(mapping))
		inode_add_lru(mapping->host);
	spin_unlock(&mapping->host->i_lock);
	ret = LRU_REMOVED_RETRY;
out:
	cond_resched();
	spin_lock_irq(lru_lock);
	return ret;
}

static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
				       struct shrink_control *sc)
{
	/* list_lru lock nests inside the IRQ-safe i_pages lock */
	return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate,
					NULL);
}

static struct shrinker workingset_shadow_shrinker = {
	.count_objects = count_shadow_nodes,
	.scan_objects = scan_shadow_nodes,
	.seeks = 0, /* ->count reports only fully expendable nodes */
	.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
};

/*
 * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
 * i_pages lock.
 */
static struct lock_class_key shadow_nodes_key;

static int __init workingset_init(void)
{
	unsigned int timestamp_bits;
	unsigned int max_order;
	int ret;

	BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT);
	/*
	 * Calculate the eviction bucket size to cover the longest
	 * actionable refault distance, which is currently half of
	 * memory (totalram_pages/2). However, memory hotplug may add
	 * some more pages at runtime, so keep working with up to
	 * double the initial memory by using totalram_pages as-is.
	 */
	timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
	max_order = fls_long(totalram_pages() - 1);
	if (max_order > timestamp_bits)
		bucket_order = max_order - timestamp_bits;
	pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
	       timestamp_bits, max_order, bucket_order);

	ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow");
	if (ret)
		goto err;
	ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key,
			      &workingset_shadow_shrinker);
	if (ret)
		goto err_list_lru;
	register_shrinker_prepared(&workingset_shadow_shrinker);
	return 0;
err_list_lru:
	free_prealloced_shrinker(&workingset_shadow_shrinker);
err:
	return ret;
}
module_init(workingset_init);