aboutsummaryrefslogtreecommitdiff
path: root/mm/truncate.c
blob: 9dbf0b75da5defbada187e9b7fe5215a69031ff4 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/truncate.c - code for taking down pages from address_spaces
 *
 * Copyright (C) 2002, Linus Torvalds
 *
 * 10Sep2002	Andrew Morton
 *		Initial version.
 */

#include <linux/kernel.h>
#include <linux/backing-dev.h>
#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/buffer_head.h>	/* grr. try_to_release_page,
				   do_invalidatepage */
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
#include "internal.h"

/*
 * Regular page slots are stabilized by the page lock even without the tree
 * itself locked.  These unlocked entries need verification under the tree
 * lock.
 */
static inline void __clear_shadow_entry(struct address_space *mapping,
				pgoff_t index, void *entry)
{
	XA_STATE(xas, &mapping->i_pages, index);

	xas_set_update(&xas, workingset_update_node);
	if (xas_load(&xas) != entry)
		return;
	xas_store(&xas, NULL);
}

static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
			       void *entry)
{
	spin_lock(&mapping->host->i_lock);
	xa_lock_irq(&mapping->i_pages);
	__clear_shadow_entry(mapping, index, entry);
	xa_unlock_irq(&mapping->i_pages);
	if (mapping_shrinkable(mapping))
		inode_add_lru(mapping->host);
	spin_unlock(&mapping->host->i_lock);
}

/*
 * Unconditionally remove exceptional entries. Usually called from truncate
 * path. Note that the folio_batch may be altered by this function by removing
 * exceptional entries similar to what folio_batch_remove_exceptionals() does.
 */
static void truncate_folio_batch_exceptionals(struct address_space *mapping,
				struct folio_batch *fbatch, pgoff_t *indices)
{
	int i, j;
	bool dax;

	/* Handled by shmem itself */
	if (shmem_mapping(mapping))
		return;

	for (j = 0; j < folio_batch_count(fbatch); j++)
		if (xa_is_value(fbatch->folios[j]))
			break;

	if (j == folio_batch_count(fbatch))
		return;

	dax = dax_mapping(mapping);
	if (!dax) {
		spin_lock(&mapping->host->i_lock);
		xa_lock_irq(&mapping->i_pages);
	}

	for (i = j; i < folio_batch_count(fbatch); i++) {
		struct folio *folio = fbatch->folios[i];
		pgoff_t index = indices[i];

		if (!xa_is_value(folio)) {
			fbatch->folios[j++] = folio;
			continue;
		}

		if (unlikely(dax)) {
			dax_delete_mapping_entry(mapping, index);
			continue;
		}

		__clear_shadow_entry(mapping, index, folio);
	}

	if (!dax) {
		xa_unlock_irq(&mapping->i_pages);
		if (mapping_shrinkable(mapping))
			inode_add_lru(mapping->host);
		spin_unlock(&mapping->host->i_lock);
	}
	fbatch->nr = j;
}

/*
 * Invalidate exceptional entry if easily possible. This handles exceptional
 * entries for invalidate_inode_pages().
 */
static int invalidate_exceptional_entry(struct address_space *mapping,
					pgoff_t index, void *entry)
{
	/* Handled by shmem itself, or for DAX we do nothing. */
	if (shmem_mapping(mapping) || dax_mapping(mapping))
		return 1;
	clear_shadow_entry(mapping, index, entry);
	return 1;
}

/*
 * Invalidate exceptional entry if clean. This handles exceptional entries for
 * invalidate_inode_pages2() so for DAX it evicts only clean entries.
 */
static int invalidate_exceptional_entry2(struct address_space *mapping,
					 pgoff_t index, void *entry)
{
	/* Handled by shmem itself */
	if (shmem_mapping(mapping))
		return 1;
	if (dax_mapping(mapping))
		return dax_invalidate_mapping_entry_sync(mapping, index);
	clear_shadow_entry(mapping, index, entry);
	return 1;
}

/**
 * do_invalidatepage - invalidate part or all of a page
 * @page: the page which is affected
 * @offset: start of the range to invalidate
 * @length: length of the range to invalidate
 *
 * do_invalidatepage() is called when all or part of the page has become
 * invalidated by a truncate operation.
 *
 * do_invalidatepage() does not have to release all buffers, but it must
 * ensure that no dirty buffer is left outside @offset and that no I/O
 * is underway against any of the blocks which are outside the truncation
 * point.  Because the caller is about to free (and possibly reuse) those
 * blocks on-disk.
 */
void do_invalidatepage(struct page *page, unsigned int offset,
		       unsigned int length)
{
	void (*invalidatepage)(struct page *, unsigned int, unsigned int);

	invalidatepage = page->mapping->a_ops->invalidatepage;
#ifdef CONFIG_BLOCK
	if (!invalidatepage)
		invalidatepage = block_invalidatepage;
#endif
	if (invalidatepage)
		(*invalidatepage)(page, offset, length);
}

/*
 * If truncate cannot remove the fs-private metadata from the page, the page
 * becomes orphaned.  It will be left on the LRU and may even be mapped into
 * user pagetables if we're racing with filemap_fault().
 *
 * We need to bail out if page->mapping is no longer equal to the original
 * mapping.  This happens a) when the VM reclaimed the page while we waited on
 * its lock, b) when a concurrent invalidate_mapping_pages got there first and
 * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
 */
static void truncate_cleanup_folio(struct folio *folio)
{
	if (folio_mapped(folio))
		unmap_mapping_folio(folio);

	if (folio_has_private(folio))
		do_invalidatepage(&folio->page, 0, folio_size(folio));

	/*
	 * Some filesystems seem to re-dirty the page even after
	 * the VM has canceled the dirty bit (eg ext3 journaling).
	 * Hence dirty accounting check is placed after invalidation.
	 */
	folio_cancel_dirty(folio);
	folio_clear_mappedtodisk(folio);
}

/*
 * This is for invalidate_mapping_pages().  That function can be called at
 * any time, and is not supposed to throw away dirty pages.  But pages can
 * be marked dirty at any time too, so use remove_mapping which safely
 * discards clean, unused pages.
 *
 * Returns non-zero if the page was successfully invalidated.
 */
static int
invalidate_complete_page(struct address_space *mapping, struct page *page)
{

	if (page->mapping != mapping)
		return 0;

	if (page_has_private(page) && !try_to_release_page(page, 0))
		return 0;

	return remove_mapping(mapping, page);
}

int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
{
	if (folio->mapping != mapping)
		return -EIO;

	truncate_cleanup_folio(folio);
	filemap_remove_folio(folio);
	return 0;
}

/*
 * Handle partial folios.  The folio may be entirely within the
 * range if a split has raced with us.  If not, we zero the part of the
 * folio that's within the [start, end] range, and then split the folio if
 * it's large.  split_page_range() will discard pages which now lie beyond
 * i_size, and we rely on the caller to discard pages which lie within a
 * newly created hole.
 *
 * Returns false if splitting failed so the caller can avoid
 * discarding the entire folio which is stubbornly unsplit.
 */
bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
{
	loff_t pos = folio_pos(folio);
	unsigned int offset, length;

	if (pos < start)
		offset = start - pos;
	else
		offset = 0;
	length = folio_size(folio);
	if (pos + length <= (u64)end)
		length = length - offset;
	else
		length = end + 1 - pos - offset;

	folio_wait_writeback(folio);
	if (length == folio_size(folio)) {
		truncate_inode_folio(folio->mapping, folio);
		return true;
	}

	/*
	 * We may be zeroing pages we're about to discard, but it avoids
	 * doing a complex calculation here, and then doing the zeroing
	 * anyway if the page split fails.
	 */
	folio_zero_range(folio, offset, length);

	if (folio_has_private(folio))
		do_invalidatepage(&folio->page, offset, length);
	if (!folio_test_large(folio))
		return true;
	if (split_huge_page(&folio->page) == 0)
		return true;
	if (folio_test_dirty(folio))
		return false;
	truncate_inode_folio(folio->mapping, folio);
	return true;
}

/*
 * Used to get rid of pages on hardware memory corruption.
 */
int generic_error_remove_page(struct address_space *mapping, struct page *page)
{
	VM_BUG_ON_PAGE(PageTail(page), page);

	if (!mapping)
		return -EINVAL;
	/*
	 * Only punch for normal data pages for now.
	 * Handling other types like directories would need more auditing.
	 */
	if (!S_ISREG(mapping->host->i_mode))
		return -EIO;
	return truncate_inode_folio(mapping, page_folio(page));
}
EXPORT_SYMBOL(generic_error_remove_page);

/*
 * Safely invalidate one page from its pagecache mapping.
 * It only drops clean, unused pages. The page must be locked.
 *
 * Returns 1 if the page is successfully invalidated, otherwise 0.
 */
int invalidate_inode_page(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	if (!mapping)
		return 0;
	if (PageDirty(page) || PageWriteback(page))
		return 0;
	if (page_mapped(page))
		return 0;
	return invalidate_complete_page(mapping, page);
}

/**
 * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
 * @mapping: mapping to truncate
 * @lstart: offset from which to truncate
 * @lend: offset to which to truncate (inclusive)
 *
 * Truncate the page cache, removing the pages that are between
 * specified offsets (and zeroing out partial pages
 * if lstart or lend + 1 is not page aligned).
 *
 * Truncate takes two passes - the first pass is nonblocking.  It will not
 * block on page locks and it will not block on writeback.  The second pass
 * will wait.  This is to prevent as much IO as possible in the affected region.
 * The first pass will remove most pages, so the search cost of the second pass
 * is low.
 *
 * We pass down the cache-hot hint to the page freeing code.  Even if the
 * mapping is large, it is probably the case that the final pages are the most
 * recently touched, and freeing happens in ascending file offset order.
 *
 * Note that since ->invalidatepage() accepts range to invalidate
 * truncate_inode_pages_range is able to handle cases where lend + 1 is not
 * page aligned properly.
 */
void truncate_inode_pages_range(struct address_space *mapping,
				loff_t lstart, loff_t lend)
{
	pgoff_t		start;		/* inclusive */
	pgoff_t		end;		/* exclusive */
	struct folio_batch fbatch;
	pgoff_t		indices[PAGEVEC_SIZE];
	pgoff_t		index;
	int		i;
	struct folio	*folio;
	bool		same_folio;

	if (mapping_empty(mapping))
		return;

	/*
	 * 'start' and 'end' always covers the range of pages to be fully
	 * truncated. Partial pages are covered with 'partial_start' at the
	 * start of the range and 'partial_end' at the end of the range.
	 * Note that 'end' is exclusive while 'lend' is inclusive.
	 */
	start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (lend == -1)
		/*
		 * lend == -1 indicates end-of-file so we have to set 'end'
		 * to the highest possible pgoff_t and since the type is
		 * unsigned we're using -1.
		 */
		end = -1;
	else
		end = (lend + 1) >> PAGE_SHIFT;

	folio_batch_init(&fbatch);
	index = start;
	while (index < end && find_lock_entries(mapping, index, end - 1,
			&fbatch, indices)) {
		index = indices[folio_batch_count(&fbatch) - 1] + 1;
		truncate_folio_batch_exceptionals(mapping, &fbatch, indices);
		for (i = 0; i < folio_batch_count(&fbatch); i++)
			truncate_cleanup_folio(fbatch.folios[i]);
		delete_from_page_cache_batch(mapping, &fbatch);
		for (i = 0; i < folio_batch_count(&fbatch); i++)
			folio_unlock(fbatch.folios[i]);
		folio_batch_release(&fbatch);
		cond_resched();
	}

	same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
	folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0);
	if (folio) {
		same_folio = lend < folio_pos(folio) + folio_size(folio);
		if (!truncate_inode_partial_folio(folio, lstart, lend)) {
			start = folio->index + folio_nr_pages(folio);
			if (same_folio)
				end = folio->index;
		}
		folio_unlock(folio);
		folio_put(folio);
		folio = NULL;
	}

	if (!same_folio)
		folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT,
						FGP_LOCK, 0);
	if (folio) {
		if (!truncate_inode_partial_folio(folio, lstart, lend))
			end = folio->index;
		folio_unlock(folio);
		folio_put(folio);
	}

	index = start;
	while (index < end) {
		cond_resched();
		if (!find_get_entries(mapping, index, end - 1, &fbatch,
				indices)) {
			/* If all gone from start onwards, we're done */
			if (index == start)
				break;
			/* Otherwise restart to make sure all gone */
			index = start;
			continue;
		}

		for (i = 0; i < folio_batch_count(&fbatch); i++) {
			struct folio *folio = fbatch.folios[i];

			/* We rely upon deletion not changing page->index */
			index = indices[i];

			if (xa_is_value(folio))
				continue;

			folio_lock(folio);
			VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
			folio_wait_writeback(folio);
			truncate_inode_folio(mapping, folio);
			folio_unlock(folio);
			index = folio_index(folio) + folio_nr_pages(folio) - 1;
		}
		truncate_folio_batch_exceptionals(mapping, &fbatch, indices);
		folio_batch_release(&fbatch);
		index++;
	}
}
EXPORT_SYMBOL(truncate_inode_pages_range);

/**
 * truncate_inode_pages - truncate *all* the pages from an offset
 * @mapping: mapping to truncate
 * @lstart: offset from which to truncate
 *
 * Called under (and serialised by) inode->i_rwsem and
 * mapping->invalidate_lock.
 *
 * Note: When this function returns, there can be a page in the process of
 * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
 * mapping->nrpages can be non-zero when this function returns even after
 * truncation of the whole mapping.
 */
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
{
	truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
}
EXPORT_SYMBOL(truncate_inode_pages);

/**
 * truncate_inode_pages_final - truncate *all* pages before inode dies
 * @mapping: mapping to truncate
 *
 * Called under (and serialized by) inode->i_rwsem.
 *
 * Filesystems have to use this in the .evict_inode path to inform the
 * VM that this is the final truncate and the inode is going away.
 */
void truncate_inode_pages_final(struct address_space *mapping)
{
	/*
	 * Page reclaim can not participate in regular inode lifetime
	 * management (can't call iput()) and thus can race with the
	 * inode teardown.  Tell it when the address space is exiting,
	 * so that it does not install eviction information after the
	 * final truncate has begun.
	 */
	mapping_set_exiting(mapping);

	if (!mapping_empty(mapping)) {
		/*
		 * As truncation uses a lockless tree lookup, cycle
		 * the tree lock to make sure any ongoing tree
		 * modification that does not see AS_EXITING is
		 * completed before starting the final truncate.
		 */
		xa_lock_irq(&mapping->i_pages);
		xa_unlock_irq(&mapping->i_pages);
	}

	truncate_inode_pages(mapping, 0);
}
EXPORT_SYMBOL(truncate_inode_pages_final);

static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
{
	pgoff_t indices[PAGEVEC_SIZE];
	struct folio_batch fbatch;
	pgoff_t index = start;
	unsigned long ret;
	unsigned long count = 0;
	int i;

	folio_batch_init(&fbatch);
	while (find_lock_entries(mapping, index, end, &fbatch, indices)) {
		for (i = 0; i < folio_batch_count(&fbatch); i++) {
			struct page *page = &fbatch.folios[i]->page;

			/* We rely upon deletion not changing page->index */
			index = indices[i];

			if (xa_is_value(page)) {
				count += invalidate_exceptional_entry(mapping,
								      index,
								      page);
				continue;
			}
			index += thp_nr_pages(page) - 1;

			ret = invalidate_inode_page(page);
			unlock_page(page);
			/*
			 * Invalidation is a hint that the page is no longer
			 * of interest and try to speed up its reclaim.
			 */
			if (!ret) {
				deactivate_file_page(page);
				/* It is likely on the pagevec of a remote CPU */
				if (nr_pagevec)
					(*nr_pagevec)++;
			}
			count += ret;
		}
		folio_batch_remove_exceptionals(&fbatch);
		folio_batch_release(&fbatch);
		cond_resched();
		index++;
	}
	return count;
}

/**
 * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode
 * @mapping: the address_space which holds the cache to invalidate
 * @start: the offset 'from' which to invalidate
 * @end: the offset 'to' which to invalidate (inclusive)
 *
 * This function removes pages that are clean, unmapped and unlocked,
 * as well as shadow entries. It will not block on IO activity.
 *
 * If you want to remove all the pages of one inode, regardless of
 * their use and writeback state, use truncate_inode_pages().
 *
 * Return: the number of the cache entries that were invalidated
 */
unsigned long invalidate_mapping_pages(struct address_space *mapping,
		pgoff_t start, pgoff_t end)
{
	return __invalidate_mapping_pages(mapping, start, end, NULL);
}
EXPORT_SYMBOL(invalidate_mapping_pages);

/**
 * invalidate_mapping_pagevec - Invalidate all the unlocked pages of one inode
 * @mapping: the address_space which holds the pages to invalidate
 * @start: the offset 'from' which to invalidate
 * @end: the offset 'to' which to invalidate (inclusive)
 * @nr_pagevec: invalidate failed page number for caller
 *
 * This helper is similar to invalidate_mapping_pages(), except that it accounts
 * for pages that are likely on a pagevec and counts them in @nr_pagevec, which
 * will be used by the caller.
 */
void invalidate_mapping_pagevec(struct address_space *mapping,
		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
{
	__invalidate_mapping_pages(mapping, start, end, nr_pagevec);
}

/*
 * This is like invalidate_complete_page(), except it ignores the page's
 * refcount.  We do this because invalidate_inode_pages2() needs stronger
 * invalidation guarantees, and cannot afford to leave pages behind because
 * shrink_page_list() has a temp ref on them, or because they're transiently
 * sitting in the lru_cache_add() pagevecs.
 */
static int invalidate_complete_folio2(struct address_space *mapping,
					struct folio *folio)
{
	if (folio->mapping != mapping)
		return 0;

	if (folio_has_private(folio) &&
	    !filemap_release_folio(folio, GFP_KERNEL))
		return 0;

	spin_lock(&mapping->host->i_lock);
	xa_lock_irq(&mapping->i_pages);
	if (folio_test_dirty(folio))
		goto failed;

	BUG_ON(folio_has_private(folio));
	__filemap_remove_folio(folio, NULL);
	xa_unlock_irq(&mapping->i_pages);
	if (mapping_shrinkable(mapping))
		inode_add_lru(mapping->host);
	spin_unlock(&mapping->host->i_lock);

	filemap_free_folio(mapping, folio);
	return 1;
failed:
	xa_unlock_irq(&mapping->i_pages);
	spin_unlock(&mapping->host->i_lock);
	return 0;
}

static int do_launder_folio(struct address_space *mapping, struct folio *folio)
{
	if (!folio_test_dirty(folio))
		return 0;
	if (folio->mapping != mapping || mapping->a_ops->launder_page == NULL)
		return 0;
	return mapping->a_ops->launder_page(&folio->page);
}

/**
 * invalidate_inode_pages2_range - remove range of pages from an address_space
 * @mapping: the address_space
 * @start: the page offset 'from' which to invalidate
 * @end: the page offset 'to' which to invalidate (inclusive)
 *
 * Any pages which are found to be mapped into pagetables are unmapped prior to
 * invalidation.
 *
 * Return: -EBUSY if any pages could not be invalidated.
 */
int invalidate_inode_pages2_range(struct address_space *mapping,
				  pgoff_t start, pgoff_t end)
{
	pgoff_t indices[PAGEVEC_SIZE];
	struct folio_batch fbatch;
	pgoff_t index;
	int i;
	int ret = 0;
	int ret2 = 0;
	int did_range_unmap = 0;

	if (mapping_empty(mapping))
		return 0;

	folio_batch_init(&fbatch);
	index = start;
	while (find_get_entries(mapping, index, end, &fbatch, indices)) {
		for (i = 0; i < folio_batch_count(&fbatch); i++) {
			struct folio *folio = fbatch.folios[i];

			/* We rely upon deletion not changing folio->index */
			index = indices[i];

			if (xa_is_value(folio)) {
				if (!invalidate_exceptional_entry2(mapping,
						index, folio))
					ret = -EBUSY;
				continue;
			}

			if (!did_range_unmap && folio_mapped(folio)) {
				/*
				 * If folio is mapped, before taking its lock,
				 * zap the rest of the file in one hit.
				 */
				unmap_mapping_pages(mapping, index,
						(1 + end - index), false);
				did_range_unmap = 1;
			}

			folio_lock(folio);
			VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
			if (folio->mapping != mapping) {
				folio_unlock(folio);
				continue;
			}
			folio_wait_writeback(folio);

			if (folio_mapped(folio))
				unmap_mapping_folio(folio);
			BUG_ON(folio_mapped(folio));

			ret2 = do_launder_folio(mapping, folio);
			if (ret2 == 0) {
				if (!invalidate_complete_folio2(mapping, folio))
					ret2 = -EBUSY;
			}
			if (ret2 < 0)
				ret = ret2;
			folio_unlock(folio);
		}
		folio_batch_remove_exceptionals(&fbatch);
		folio_batch_release(&fbatch);
		cond_resched();
		index++;
	}
	/*
	 * For DAX we invalidate page tables after invalidating page cache.  We
	 * could invalidate page tables while invalidating each entry however
	 * that would be expensive. And doing range unmapping before doesn't
	 * work as we have no cheap way to find whether page cache entry didn't
	 * get remapped later.
	 */
	if (dax_mapping(mapping)) {
		unmap_mapping_pages(mapping, start, end - start + 1, false);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);

/**
 * invalidate_inode_pages2 - remove all pages from an address_space
 * @mapping: the address_space
 *
 * Any pages which are found to be mapped into pagetables are unmapped prior to
 * invalidation.
 *
 * Return: -EBUSY if any pages could not be invalidated.
 */
int invalidate_inode_pages2(struct address_space *mapping)
{
	return invalidate_inode_pages2_range(mapping, 0, -1);
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2);

/**
 * truncate_pagecache - unmap and remove pagecache that has been truncated
 * @inode: inode
 * @newsize: new file size
 *
 * inode's new i_size must already be written before truncate_pagecache
 * is called.
 *
 * This function should typically be called before the filesystem
 * releases resources associated with the freed range (eg. deallocates
 * blocks). This way, pagecache will always stay logically coherent
 * with on-disk format, and the filesystem would not have to deal with
 * situations such as writepage being called for a page that has already
 * had its underlying blocks deallocated.
 */
void truncate_pagecache(struct inode *inode, loff_t newsize)
{
	struct address_space *mapping = inode->i_mapping;
	loff_t holebegin = round_up(newsize, PAGE_SIZE);

	/*
	 * unmap_mapping_range is called twice, first simply for
	 * efficiency so that truncate_inode_pages does fewer
	 * single-page unmaps.  However after this first call, and
	 * before truncate_inode_pages finishes, it is possible for
	 * private pages to be COWed, which remain after
	 * truncate_inode_pages finishes, hence the second
	 * unmap_mapping_range call must be made for correctness.
	 */
	unmap_mapping_range(mapping, holebegin, 0, 1);
	truncate_inode_pages(mapping, newsize);
	unmap_mapping_range(mapping, holebegin, 0, 1);
}
EXPORT_SYMBOL(truncate_pagecache);

/**
 * truncate_setsize - update inode and pagecache for a new file size
 * @inode: inode
 * @newsize: new file size
 *
 * truncate_setsize updates i_size and performs pagecache truncation (if
 * necessary) to @newsize. It will be typically be called from the filesystem's
 * setattr function when ATTR_SIZE is passed in.
 *
 * Must be called with a lock serializing truncates and writes (generally
 * i_rwsem but e.g. xfs uses a different lock) and before all filesystem
 * specific block truncation has been performed.
 */
void truncate_setsize(struct inode *inode, loff_t newsize)
{
	loff_t oldsize = inode->i_size;

	i_size_write(inode, newsize);
	if (newsize > oldsize)
		pagecache_isize_extended(inode, oldsize, newsize);
	truncate_pagecache(inode, newsize);
}
EXPORT_SYMBOL(truncate_setsize);

/**
 * pagecache_isize_extended - update pagecache after extension of i_size
 * @inode:	inode for which i_size was extended
 * @from:	original inode size
 * @to:		new inode size
 *
 * Handle extension of inode size either caused by extending truncate or by
 * write starting after current i_size. We mark the page straddling current
 * i_size RO so that page_mkwrite() is called on the nearest write access to
 * the page.  This way filesystem can be sure that page_mkwrite() is called on
 * the page before user writes to the page via mmap after the i_size has been
 * changed.
 *
 * The function must be called after i_size is updated so that page fault
 * coming after we unlock the page will already see the new i_size.
 * The function must be called while we still hold i_rwsem - this not only
 * makes sure i_size is stable but also that userspace cannot observe new
 * i_size value before we are prepared to store mmap writes at new inode size.
 */
void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
{
	int bsize = i_blocksize(inode);
	loff_t rounded_from;
	struct page *page;
	pgoff_t index;

	WARN_ON(to > inode->i_size);

	if (from >= to || bsize == PAGE_SIZE)
		return;
	/* Page straddling @from will not have any hole block created? */
	rounded_from = round_up(from, bsize);
	if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1)))
		return;

	index = from >> PAGE_SHIFT;
	page = find_lock_page(inode->i_mapping, index);
	/* Page not cached? Nothing to do */
	if (!page)
		return;
	/*
	 * See clear_page_dirty_for_io() for details why set_page_dirty()
	 * is needed.
	 */
	if (page_mkclean(page))
		set_page_dirty(page);
	unlock_page(page);
	put_page(page);
}
EXPORT_SYMBOL(pagecache_isize_extended);

/**
 * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
 * @inode: inode
 * @lstart: offset of beginning of hole
 * @lend: offset of last byte of hole
 *
 * This function should typically be called before the filesystem
 * releases resources associated with the freed range (eg. deallocates
 * blocks). This way, pagecache will always stay logically coherent
 * with on-disk format, and the filesystem would not have to deal with
 * situations such as writepage being called for a page that has already
 * had its underlying blocks deallocated.
 */
void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
{
	struct address_space *mapping = inode->i_mapping;
	loff_t unmap_start = round_up(lstart, PAGE_SIZE);
	loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
	/*
	 * This rounding is currently just for example: unmap_mapping_range
	 * expands its hole outwards, whereas we want it to contract the hole
	 * inwards.  However, existing callers of truncate_pagecache_range are
	 * doing their own page rounding first.  Note that unmap_mapping_range
	 * allows holelen 0 for all, and we allow lend -1 for end of file.
	 */

	/*
	 * Unlike in truncate_pagecache, unmap_mapping_range is called only
	 * once (before truncating pagecache), and without "even_cows" flag:
	 * hole-punching should not remove private COWed pages from the hole.
	 */
	if ((u64)unmap_end > (u64)unmap_start)
		unmap_mapping_range(mapping, unmap_start,
				    1 + unmap_end - unmap_start, 0);
	truncate_inode_pages_range(mapping, lstart, lend);
}
EXPORT_SYMBOL(truncate_pagecache_range);