summaryrefslogtreecommitdiffstats
path: root/mm/swap_state.c
blob: 85d9e5806a6a2cc09dbd0d07e30a4bbd84bbc296 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/mm/swap_state.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 *
 *  Rewritten to use page cache, (C) 1998 Stephen Tweedie
 */
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/mempolicy.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/migrate.h>
#include <linux/vmalloc.h>
#include <linux/swap_slots.h>
#include <linux/huge_mm.h>
#include <linux/shmem_fs.h>
#include "internal.h"
#include "swap.h"

/*
 * swapper_space is a fiction, retained to simplify the path through
 * vmscan's shrink_page_list.
 */
static const struct address_space_operations swap_aops = {
	.writepage	= swap_writepage,
	.dirty_folio	= noop_dirty_folio,
#ifdef CONFIG_MIGRATION
	.migrate_folio	= migrate_folio,
#endif
};

struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly;
static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly;
static bool enable_vma_readahead __read_mostly = true;

#define SWAP_RA_WIN_SHIFT	(PAGE_SHIFT / 2)
#define SWAP_RA_HITS_MASK	((1UL << SWAP_RA_WIN_SHIFT) - 1)
#define SWAP_RA_HITS_MAX	SWAP_RA_HITS_MASK
#define SWAP_RA_WIN_MASK	(~PAGE_MASK & ~SWAP_RA_HITS_MASK)

#define SWAP_RA_HITS(v)		((v) & SWAP_RA_HITS_MASK)
#define SWAP_RA_WIN(v)		(((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT)
#define SWAP_RA_ADDR(v)		((v) & PAGE_MASK)

#define SWAP_RA_VAL(addr, win, hits)				\
	(((addr) & PAGE_MASK) |					\
	 (((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) |	\
	 ((hits) & SWAP_RA_HITS_MASK))

/* Initial readahead hits is 4 to start up with a small window */
#define GET_SWAP_RA_VAL(vma)					\
	(atomic_long_read(&(vma)->swap_readahead_info) ? : 4)

static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);

void show_swap_cache_info(void)
{
	printk("%lu pages in swap cache\n", total_swapcache_pages());
	printk("Free swap  = %ldkB\n", K(get_nr_swap_pages()));
	printk("Total swap = %lukB\n", K(total_swap_pages));
}

void *get_shadow_from_swap_cache(swp_entry_t entry)
{
	struct address_space *address_space = swap_address_space(entry);
	pgoff_t idx = swp_offset(entry);
	struct page *page;

	page = xa_load(&address_space->i_pages, idx);
	if (xa_is_value(page))
		return page;
	return NULL;
}

/*
 * add_to_swap_cache resembles filemap_add_folio on swapper_space,
 * but sets SwapCache flag and private instead of mapping and index.
 */
int add_to_swap_cache(struct folio *folio, swp_entry_t entry,
			gfp_t gfp, void **shadowp)
{
	struct address_space *address_space = swap_address_space(entry);
	pgoff_t idx = swp_offset(entry);
	XA_STATE_ORDER(xas, &address_space->i_pages, idx, folio_order(folio));
	unsigned long i, nr = folio_nr_pages(folio);
	void *old;

	xas_set_update(&xas, workingset_update_node);

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio);

	folio_ref_add(folio, nr);
	folio_set_swapcache(folio);
	folio->swap = entry;

	do {
		xas_lock_irq(&xas);
		xas_create_range(&xas);
		if (xas_error(&xas))
			goto unlock;
		for (i = 0; i < nr; i++) {
			VM_BUG_ON_FOLIO(xas.xa_index != idx + i, folio);
			if (shadowp) {
				old = xas_load(&xas);
				if (xa_is_value(old))
					*shadowp = old;
			}
			xas_store(&xas, folio);
			xas_next(&xas);
		}
		address_space->nrpages += nr;
		__node_stat_mod_folio(folio, NR_FILE_PAGES, nr);
		__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, nr);
unlock:
		xas_unlock_irq(&xas);
	} while (xas_nomem(&xas, gfp));

	if (!xas_error(&xas))
		return 0;

	folio_clear_swapcache(folio);
	folio_ref_sub(folio, nr);
	return xas_error(&xas);
}

/*
 * This must be called only on folios that have
 * been verified to be in the swap cache.
 */
void __delete_from_swap_cache(struct folio *folio,
			swp_entry_t entry, void *shadow)
{
	struct address_space *address_space = swap_address_space(entry);
	int i;
	long nr = folio_nr_pages(folio);
	pgoff_t idx = swp_offset(entry);
	XA_STATE(xas, &address_space->i_pages, idx);

	xas_set_update(&xas, workingset_update_node);

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
	VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);

	for (i = 0; i < nr; i++) {
		void *entry = xas_store(&xas, shadow);
		VM_BUG_ON_PAGE(entry != folio, entry);
		xas_next(&xas);
	}
	folio->swap.val = 0;
	folio_clear_swapcache(folio);
	address_space->nrpages -= nr;
	__node_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
	__lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr);
}

/**
 * add_to_swap - allocate swap space for a folio
 * @folio: folio we want to move to swap
 *
 * Allocate swap space for the folio and add the folio to the
 * swap cache.
 *
 * Context: Caller needs to hold the folio lock.
 * Return: Whether the folio was added to the swap cache.
 */
bool add_to_swap(struct folio *folio)
{
	swp_entry_t entry;
	int err;

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);

	entry = folio_alloc_swap(folio);
	if (!entry.val)
		return false;

	/*
	 * XArray node allocations from PF_MEMALLOC contexts could
	 * completely exhaust the page allocator. __GFP_NOMEMALLOC
	 * stops emergency reserves from being allocated.
	 *
	 * TODO: this could cause a theoretical memory reclaim
	 * deadlock in the swap out path.
	 */
	/*
	 * Add it to the swap cache.
	 */
	err = add_to_swap_cache(folio, entry,
			__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL);
	if (err)
		/*
		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
		 * clear SWAP_HAS_CACHE flag.
		 */
		goto fail;
	/*
	 * Normally the folio will be dirtied in unmap because its
	 * pte should be dirty. A special case is MADV_FREE page. The
	 * page's pte could have dirty bit cleared but the folio's
	 * SwapBacked flag is still set because clearing the dirty bit
	 * and SwapBacked flag has no lock protected. For such folio,
	 * unmap will not set dirty bit for it, so folio reclaim will
	 * not write the folio out. This can cause data corruption when
	 * the folio is swapped in later. Always setting the dirty flag
	 * for the folio solves the problem.
	 */
	folio_mark_dirty(folio);

	return true;

fail:
	put_swap_folio(folio, entry);
	return false;
}

/*
 * This must be called only on folios that have
 * been verified to be in the swap cache and locked.
 * It will never put the folio into the free list,
 * the caller has a reference on the folio.
 */
void delete_from_swap_cache(struct folio *folio)
{
	swp_entry_t entry = folio->swap;
	struct address_space *address_space = swap_address_space(entry);

	xa_lock_irq(&address_space->i_pages);
	__delete_from_swap_cache(folio, entry, NULL);
	xa_unlock_irq(&address_space->i_pages);

	put_swap_folio(folio, entry);
	folio_ref_sub(folio, folio_nr_pages(folio));
}

void clear_shadow_from_swap_cache(int type, unsigned long begin,
				unsigned long end)
{
	unsigned long curr = begin;
	void *old;

	for (;;) {
		swp_entry_t entry = swp_entry(type, curr);
		struct address_space *address_space = swap_address_space(entry);
		XA_STATE(xas, &address_space->i_pages, curr);

		xas_set_update(&xas, workingset_update_node);

		xa_lock_irq(&address_space->i_pages);
		xas_for_each(&xas, old, end) {
			if (!xa_is_value(old))
				continue;
			xas_store(&xas, NULL);
		}
		xa_unlock_irq(&address_space->i_pages);

		/* search the next swapcache until we meet end */
		curr >>= SWAP_ADDRESS_SPACE_SHIFT;
		curr++;
		curr <<= SWAP_ADDRESS_SPACE_SHIFT;
		if (curr > end)
			break;
	}
}

/*
 * If we are the only user, then try to free up the swap cache.
 *
 * Its ok to check the swapcache flag without the folio lock
 * here because we are going to recheck again inside
 * folio_free_swap() _with_ the lock.
 * 					- Marcelo
 */
void free_swap_cache(struct page *page)
{
	struct folio *folio = page_folio(page);

	if (folio_test_swapcache(folio) && !folio_mapped(folio) &&
	    folio_trylock(folio)) {
		folio_free_swap(folio);
		folio_unlock(folio);
	}
}

/*
 * Perform a free_page(), also freeing any swap cache associated with
 * this page if it is the last user of the page.
 */
void free_page_and_swap_cache(struct page *page)
{
	free_swap_cache(page);
	if (!is_huge_zero_page(page))
		put_page(page);
}

/*
 * Passed an array of pages, drop them all from swapcache and then release
 * them.  They are removed from the LRU and freed if this is their last use.
 */
void free_pages_and_swap_cache(struct encoded_page **pages, int nr)
{
	lru_add_drain();
	for (int i = 0; i < nr; i++)
		free_swap_cache(encoded_page_ptr(pages[i]));
	release_pages(pages, nr);
}

static inline bool swap_use_vma_readahead(void)
{
	return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
}

/*
 * Lookup a swap entry in the swap cache. A found folio will be returned
 * unlocked and with its refcount incremented - we rely on the kernel
 * lock getting page table operations atomic even if we drop the folio
 * lock before returning.
 *
 * Caller must lock the swap device or hold a reference to keep it valid.
 */
struct folio *swap_cache_get_folio(swp_entry_t entry,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct folio *folio;

	folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry));
	if (!IS_ERR(folio)) {
		bool vma_ra = swap_use_vma_readahead();
		bool readahead;

		/*
		 * At the moment, we don't support PG_readahead for anon THP
		 * so let's bail out rather than confusing the readahead stat.
		 */
		if (unlikely(folio_test_large(folio)))
			return folio;

		readahead = folio_test_clear_readahead(folio);
		if (vma && vma_ra) {
			unsigned long ra_val;
			int win, hits;

			ra_val = GET_SWAP_RA_VAL(vma);
			win = SWAP_RA_WIN(ra_val);
			hits = SWAP_RA_HITS(ra_val);
			if (readahead)
				hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
			atomic_long_set(&vma->swap_readahead_info,
					SWAP_RA_VAL(addr, win, hits));
		}

		if (readahead) {
			count_vm_event(SWAP_RA_HIT);
			if (!vma || !vma_ra)
				atomic_inc(&swapin_readahead_hits);
		}
	} else {
		folio = NULL;
	}

	return folio;
}

/**
 * filemap_get_incore_folio - Find and get a folio from the page or swap caches.
 * @mapping: The address_space to search.
 * @index: The page cache index.
 *
 * This differs from filemap_get_folio() in that it will also look for the
 * folio in the swap cache.
 *
 * Return: The found folio or %NULL.
 */
struct folio *filemap_get_incore_folio(struct address_space *mapping,
		pgoff_t index)
{
	swp_entry_t swp;
	struct swap_info_struct *si;
	struct folio *folio = filemap_get_entry(mapping, index);

	if (!folio)
		return ERR_PTR(-ENOENT);
	if (!xa_is_value(folio))
		return folio;
	if (!shmem_mapping(mapping))
		return ERR_PTR(-ENOENT);

	swp = radix_to_swp_entry(folio);
	/* There might be swapin error entries in shmem mapping. */
	if (non_swap_entry(swp))
		return ERR_PTR(-ENOENT);
	/* Prevent swapoff from happening to us */
	si = get_swap_device(swp);
	if (!si)
		return ERR_PTR(-ENOENT);
	index = swp_offset(swp);
	folio = filemap_get_folio(swap_address_space(swp), index);
	put_swap_device(si);
	return folio;
}

struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
				     struct mempolicy *mpol, pgoff_t ilx,
				     bool *new_page_allocated)
{
	struct swap_info_struct *si;
	struct folio *folio;
	struct page *page;
	void *shadow = NULL;

	*new_page_allocated = false;
	si = get_swap_device(entry);
	if (!si)
		return NULL;

	for (;;) {
		int err;
		/*
		 * First check the swap cache.  Since this is normally
		 * called after swap_cache_get_folio() failed, re-calling
		 * that would confuse statistics.
		 */
		folio = filemap_get_folio(swap_address_space(entry),
						swp_offset(entry));
		if (!IS_ERR(folio)) {
			page = folio_file_page(folio, swp_offset(entry));
			goto got_page;
		}

		/*
		 * Just skip read ahead for unused swap slot.
		 * During swap_off when swap_slot_cache is disabled,
		 * we have to handle the race between putting
		 * swap entry in swap cache and marking swap slot
		 * as SWAP_HAS_CACHE.  That's done in later part of code or
		 * else swap_off will be aborted if we return NULL.
		 */
		if (!swap_swapcount(si, entry) && swap_slot_cache_enabled)
			goto fail_put_swap;

		/*
		 * Get a new page to read into from swap.  Allocate it now,
		 * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will
		 * cause any racers to loop around until we add it to cache.
		 */
		folio = (struct folio *)alloc_pages_mpol(gfp_mask, 0,
						mpol, ilx, numa_node_id());
		if (!folio)
                        goto fail_put_swap;

		/*
		 * Swap entry may have been freed since our caller observed it.
		 */
		err = swapcache_prepare(entry);
		if (!err)
			break;

		folio_put(folio);
		if (err != -EEXIST)
			goto fail_put_swap;

		/*
		 * We might race against __delete_from_swap_cache(), and
		 * stumble across a swap_map entry whose SWAP_HAS_CACHE
		 * has not yet been cleared.  Or race against another
		 * __read_swap_cache_async(), which has set SWAP_HAS_CACHE
		 * in swap_map, but not yet added its page to swap cache.
		 */
		schedule_timeout_uninterruptible(1);
	}

	/*
	 * The swap entry is ours to swap in. Prepare the new page.
	 */

	__folio_set_locked(folio);
	__folio_set_swapbacked(folio);

	if (mem_cgroup_swapin_charge_folio(folio, NULL, gfp_mask, entry))
		goto fail_unlock;

	/* May fail (-ENOMEM) if XArray node allocation failed. */
	if (add_to_swap_cache(folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow))
		goto fail_unlock;

	mem_cgroup_swapin_uncharge_swap(entry);

	if (shadow)
		workingset_refault(folio, shadow);

	/* Caller will initiate read into locked folio */
	folio_add_lru(folio);
	*new_page_allocated = true;
	page = &folio->page;
got_page:
	put_swap_device(si);
	return page;

fail_unlock:
	put_swap_folio(folio, entry);
	folio_unlock(folio);
	folio_put(folio);
fail_put_swap:
	put_swap_device(si);
	return NULL;
}

/*
 * Locate a page of swap in physical memory, reserving swap cache space
 * and reading the disk if it is not already cached.
 * A failure return means that either the page allocation failed or that
 * the swap entry is no longer in use.
 *
 * get/put_swap_device() aren't needed to call this function, because
 * __read_swap_cache_async() call them and swap_readpage() holds the
 * swap cache folio lock.
 */
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
				   struct vm_area_struct *vma,
				   unsigned long addr, struct swap_iocb **plug)
{
	bool page_allocated;
	struct mempolicy *mpol;
	pgoff_t ilx;
	struct page *page;

	mpol = get_vma_policy(vma, addr, 0, &ilx);
	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
					&page_allocated);
	mpol_cond_put(mpol);

	if (page_allocated)
		swap_readpage(page, false, plug);
	return page;
}

static unsigned int __swapin_nr_pages(unsigned long prev_offset,
				      unsigned long offset,
				      int hits,
				      int max_pages,
				      int prev_win)
{
	unsigned int pages, last_ra;

	/*
	 * This heuristic has been found to work well on both sequential and
	 * random loads, swapping to hard disk or to SSD: please don't ask
	 * what the "+ 2" means, it just happens to work well, that's all.
	 */
	pages = hits + 2;
	if (pages == 2) {
		/*
		 * We can have no readahead hits to judge by: but must not get
		 * stuck here forever, so check for an adjacent offset instead
		 * (and don't even bother to check whether swap type is same).
		 */
		if (offset != prev_offset + 1 && offset != prev_offset - 1)
			pages = 1;
	} else {
		unsigned int roundup = 4;
		while (roundup < pages)
			roundup <<= 1;
		pages = roundup;
	}

	if (pages > max_pages)
		pages = max_pages;

	/* Don't shrink readahead too fast */
	last_ra = prev_win / 2;
	if (pages < last_ra)
		pages = last_ra;

	return pages;
}

static unsigned long swapin_nr_pages(unsigned long offset)
{
	static unsigned long prev_offset;
	unsigned int hits, pages, max_pages;
	static atomic_t last_readahead_pages;

	max_pages = 1 << READ_ONCE(page_cluster);
	if (max_pages <= 1)
		return 1;

	hits = atomic_xchg(&swapin_readahead_hits, 0);
	pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
				  max_pages,
				  atomic_read(&last_readahead_pages));
	if (!hits)
		WRITE_ONCE(prev_offset, offset);
	atomic_set(&last_readahead_pages, pages);

	return pages;
}

/**
 * swap_cluster_readahead - swap in pages in hope we need them soon
 * @entry: swap entry of this memory
 * @gfp_mask: memory allocation flags
 * @mpol: NUMA memory allocation policy to be applied
 * @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
 *
 * Returns the struct page for entry and addr, after queueing swapin.
 *
 * Primitive swap readahead code. We simply read an aligned block of
 * (1 << page_cluster) entries in the swap area. This method is chosen
 * because it doesn't cost us any seek time.  We also make sure to queue
 * the 'original' request together with the readahead ones...
 *
 * Note: it is intentional that the same NUMA policy and interleave index
 * are used for every page of the readahead: neighbouring pages on swap
 * are fairly likely to have been swapped out from the same node.
 */
struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
				    struct mempolicy *mpol, pgoff_t ilx)
{
	struct page *page;
	unsigned long entry_offset = swp_offset(entry);
	unsigned long offset = entry_offset;
	unsigned long start_offset, end_offset;
	unsigned long mask;
	struct swap_info_struct *si = swp_swap_info(entry);
	struct blk_plug plug;
	struct swap_iocb *splug = NULL;
	bool page_allocated;

	mask = swapin_nr_pages(offset) - 1;
	if (!mask)
		goto skip;

	/* Read a page_cluster sized and aligned cluster around offset. */
	start_offset = offset & ~mask;
	end_offset = offset | mask;
	if (!start_offset)	/* First page is swap header. */
		start_offset++;
	if (end_offset >= si->max)
		end_offset = si->max - 1;

	blk_start_plug(&plug);
	for (offset = start_offset; offset <= end_offset ; offset++) {
		/* Ok, do the async read-ahead now */
		page = __read_swap_cache_async(
				swp_entry(swp_type(entry), offset),
				gfp_mask, mpol, ilx, &page_allocated);
		if (!page)
			continue;
		if (page_allocated) {
			swap_readpage(page, false, &splug);
			if (offset != entry_offset) {
				SetPageReadahead(page);
				count_vm_event(SWAP_RA);
			}
		}
		put_page(page);
	}
	blk_finish_plug(&plug);
	swap_read_unplug(splug);
	lru_add_drain();	/* Push any new pages onto the LRU now */
skip:
	/* The page was likely read above, so no need for plugging here */
	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
					&page_allocated);
	if (unlikely(page_allocated))
		swap_readpage(page, false, NULL);
	return page;
}

int init_swap_address_space(unsigned int type, unsigned long nr_pages)
{
	struct address_space *spaces, *space;
	unsigned int i, nr;

	nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
	spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL);
	if (!spaces)
		return -ENOMEM;
	for (i = 0; i < nr; i++) {
		space = spaces + i;
		xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ);
		atomic_set(&space->i_mmap_writable, 0);
		space->a_ops = &swap_aops;
		/* swap cache doesn't use writeback related tags */
		mapping_set_no_writeback_tags(space);
	}
	nr_swapper_spaces[type] = nr;
	swapper_spaces[type] = spaces;

	return 0;
}

void exit_swap_address_space(unsigned int type)
{
	int i;
	struct address_space *spaces = swapper_spaces[type];

	for (i = 0; i < nr_swapper_spaces[type]; i++)
		VM_WARN_ON_ONCE(!mapping_empty(&spaces[i]));
	kvfree(spaces);
	nr_swapper_spaces[type] = 0;
	swapper_spaces[type] = NULL;
}

#define SWAP_RA_ORDER_CEILING	5

struct vma_swap_readahead {
	unsigned short win;
	unsigned short offset;
	unsigned short nr_pte;
};

static void swap_ra_info(struct vm_fault *vmf,
			 struct vma_swap_readahead *ra_info)
{
	struct vm_area_struct *vma = vmf->vma;
	unsigned long ra_val;
	unsigned long faddr, pfn, fpfn, lpfn, rpfn;
	unsigned long start, end;
	unsigned int max_win, hits, prev_win, win;

	max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
			     SWAP_RA_ORDER_CEILING);
	if (max_win == 1) {
		ra_info->win = 1;
		return;
	}

	faddr = vmf->address;
	fpfn = PFN_DOWN(faddr);
	ra_val = GET_SWAP_RA_VAL(vma);
	pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val));
	prev_win = SWAP_RA_WIN(ra_val);
	hits = SWAP_RA_HITS(ra_val);
	ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits,
					       max_win, prev_win);
	atomic_long_set(&vma->swap_readahead_info,
			SWAP_RA_VAL(faddr, win, 0));
	if (win == 1)
		return;

	if (fpfn == pfn + 1) {
		lpfn = fpfn;
		rpfn = fpfn + win;
	} else if (pfn == fpfn + 1) {
		lpfn = fpfn - win + 1;
		rpfn = fpfn + 1;
	} else {
		unsigned int left = (win - 1) / 2;

		lpfn = fpfn - left;
		rpfn = fpfn + win - left;
	}
	start = max3(lpfn, PFN_DOWN(vma->vm_start),
		     PFN_DOWN(faddr & PMD_MASK));
	end = min3(rpfn, PFN_DOWN(vma->vm_end),
		   PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE));

	ra_info->nr_pte = end - start;
	ra_info->offset = fpfn - start;
}

/**
 * swap_vma_readahead - swap in pages in hope we need them soon
 * @targ_entry: swap entry of the targeted memory
 * @gfp_mask: memory allocation flags
 * @mpol: NUMA memory allocation policy to be applied
 * @targ_ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
 * @vmf: fault information
 *
 * Returns the struct page for entry and addr, after queueing swapin.
 *
 * Primitive swap readahead code. We simply read in a few pages whose
 * virtual addresses are around the fault address in the same vma.
 *
 * Caller must hold read mmap_lock if vmf->vma is not NULL.
 *
 */
static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
				       struct mempolicy *mpol, pgoff_t targ_ilx,
				       struct vm_fault *vmf)
{
	struct blk_plug plug;
	struct swap_iocb *splug = NULL;
	struct page *page;
	pte_t *pte = NULL, pentry;
	unsigned long addr;
	swp_entry_t entry;
	pgoff_t ilx;
	unsigned int i;
	bool page_allocated;
	struct vma_swap_readahead ra_info = {
		.win = 1,
	};

	swap_ra_info(vmf, &ra_info);
	if (ra_info.win == 1)
		goto skip;

	addr = vmf->address - (ra_info.offset * PAGE_SIZE);
	ilx = targ_ilx - ra_info.offset;

	blk_start_plug(&plug);
	for (i = 0; i < ra_info.nr_pte; i++, ilx++, addr += PAGE_SIZE) {
		if (!pte++) {
			pte = pte_offset_map(vmf->pmd, addr);
			if (!pte)
				break;
		}
		pentry = ptep_get_lockless(pte);
		if (!is_swap_pte(pentry))
			continue;
		entry = pte_to_swp_entry(pentry);
		if (unlikely(non_swap_entry(entry)))
			continue;
		pte_unmap(pte);
		pte = NULL;
		page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
						&page_allocated);
		if (!page)
			continue;
		if (page_allocated) {
			swap_readpage(page, false, &splug);
			if (i != ra_info.offset) {
				SetPageReadahead(page);
				count_vm_event(SWAP_RA);
			}
		}
		put_page(page);
	}
	if (pte)
		pte_unmap(pte);
	blk_finish_plug(&plug);
	swap_read_unplug(splug);
	lru_add_drain();
skip:
	/* The page was likely read above, so no need for plugging here */
	page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
					&page_allocated);
	if (unlikely(page_allocated))
		swap_readpage(page, false, NULL);
	return page;
}

/**
 * swapin_readahead - swap in pages in hope we need them soon
 * @entry: swap entry of this memory
 * @gfp_mask: memory allocation flags
 * @vmf: fault information
 *
 * Returns the struct page for entry and addr, after queueing swapin.
 *
 * It's a main entry function for swap readahead. By the configuration,
 * it will read ahead blocks by cluster-based(ie, physical disk based)
 * or vma-based(ie, virtual address based on faulty address) readahead.
 */
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
				struct vm_fault *vmf)
{
	struct mempolicy *mpol;
	pgoff_t ilx;
	struct page *page;

	mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx);
	page = swap_use_vma_readahead() ?
		swap_vma_readahead(entry, gfp_mask, mpol, ilx, vmf) :
		swap_cluster_readahead(entry, gfp_mask, mpol, ilx);
	mpol_cond_put(mpol);
	return page;
}

#ifdef CONFIG_SYSFS
static ssize_t vma_ra_enabled_show(struct kobject *kobj,
				     struct kobj_attribute *attr, char *buf)
{
	return sysfs_emit(buf, "%s\n",
			  enable_vma_readahead ? "true" : "false");
}
static ssize_t vma_ra_enabled_store(struct kobject *kobj,
				      struct kobj_attribute *attr,
				      const char *buf, size_t count)
{
	ssize_t ret;

	ret = kstrtobool(buf, &enable_vma_readahead);
	if (ret)
		return ret;

	return count;
}
static struct kobj_attribute vma_ra_enabled_attr = __ATTR_RW(vma_ra_enabled);

static struct attribute *swap_attrs[] = {
	&vma_ra_enabled_attr.attr,
	NULL,
};

static const struct attribute_group swap_attr_group = {
	.attrs = swap_attrs,
};

static int __init swap_init_sysfs(void)
{
	int err;
	struct kobject *swap_kobj;

	swap_kobj = kobject_create_and_add("swap", mm_kobj);
	if (!swap_kobj) {
		pr_err("failed to create swap kobject\n");
		return -ENOMEM;
	}
	err = sysfs_create_group(swap_kobj, &swap_attr_group);
	if (err) {
		pr_err("failed to register swap group\n");
		goto delete_obj;
	}
	return 0;

delete_obj:
	kobject_put(swap_kobj);
	return err;
}
subsys_initcall(swap_init_sysfs);
#endif