aboutsummaryrefslogtreecommitdiff
path: root/mm/truncate.c
blob: c924764e2ce51bd7d38bcba70594224e749de660 (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
/*
 * 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/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/module.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/cleancache.h>
#include "internal.h"


/**
 * do_invalidatepage - invalidate part or all of a page
 * @page: the page which is affected
 * @offset: the index of the truncation point
 *
 * 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 long offset)
{
	void (*invalidatepage)(struct page *, unsigned long);
	invalidatepage = page->mapping->a_ops->invalidatepage;
#ifdef CONFIG_BLOCK
	if (!invalidatepage)
		invalidatepage = block_invalidatepage;
#endif
	if (invalidatepage)
		(*invalidatepage)(page, offset);
}

static inline void truncate_partial_page(struct page *page, unsigned partial)
{
	zero_user_segment(page, partial, PAGE_CACHE_SIZE);
	cleancache_flush_page(page->mapping, page);
	if (page_has_private(page))
		do_invalidatepage(page, partial);
}

/*
 * This cancels just the dirty bit on the kernel page itself, it
 * does NOT actually remove dirty bits on any mmap's that may be
 * around. It also leaves the page tagged dirty, so any sync
 * activity will still find it on the dirty lists, and in particular,
 * clear_page_dirty_for_io() will still look at the dirty bits in
 * the VM.
 *
 * Doing this should *normally* only ever be done when a page
 * is truncated, and is not actually mapped anywhere at all. However,
 * fs/buffer.c does this when it notices that somebody has cleaned
 * out all the buffers on a page without actually doing it through
 * the VM. Can you say "ext3 is horribly ugly"? Tought you could.
 */
void cancel_dirty_page(struct page *page, unsigned int account_size)
{
	if (TestClearPageDirty(page)) {
		struct address_space *mapping = page->mapping;
		if (mapping && mapping_cap_account_dirty(mapping)) {
			dec_zone_page_state(page, NR_FILE_DIRTY);
			dec_bdi_stat(mapping->backing_dev_info,
					BDI_RECLAIMABLE);
			if (account_size)
				task_io_account_cancelled_write(account_size);
		}
	}
}
EXPORT_SYMBOL(cancel_dirty_page);

/*
 * 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 bale 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 int
truncate_complete_page(struct address_space *mapping, struct page *page)
{
	if (page->mapping != mapping)
		return -EIO;

	if (page_has_private(page))
		do_invalidatepage(page, 0);

	cancel_dirty_page(page, PAGE_CACHE_SIZE);

	clear_page_mlock(page);
	ClearPageMappedToDisk(page);
	delete_from_page_cache(page);
	return 0;
}

/*
 * 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)
{
	int ret;

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

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

	clear_page_mlock(page);
	ret = remove_mapping(mapping, page);

	return ret;
}

int truncate_inode_page(struct address_space *mapping, struct page *page)
{
	if (page_mapped(page)) {
		unmap_mapping_range(mapping,
				   (loff_t)page->index << PAGE_CACHE_SHIFT,
				   PAGE_CACHE_SIZE, 0);
	}
	return truncate_complete_page(mapping, page);
}

/*
 * Used to get rid of pages on hardware memory corruption.
 */
int generic_error_remove_page(struct address_space *mapping, struct 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_page(mapping, 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 - 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
 *
 * Truncate the page cache, removing the pages that are between
 * specified offsets (and zeroing out partial page
 * (if lstart 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.
 *
 * When looking at page->index outside the page lock we need to be careful to
 * copy it into a local to avoid races (it could change at any time).
 *
 * 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.
 */
void truncate_inode_pages_range(struct address_space *mapping,
				loff_t lstart, loff_t lend)
{
	const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
	pgoff_t end;
	const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
	struct pagevec pvec;
	pgoff_t next;
	int i;

	cleancache_flush_inode(mapping);
	if (mapping->nrpages == 0)
		return;

	BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
	end = (lend >> PAGE_CACHE_SHIFT);

	pagevec_init(&pvec, 0);
	next = start;
	while (next <= end &&
	       pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
		mem_cgroup_uncharge_start();
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			pgoff_t page_index = page->index;

			if (page_index > end) {
				next = page_index;
				break;
			}

			if (page_index > next)
				next = page_index;
			next++;
			if (!trylock_page(page))
				continue;
			if (PageWriteback(page)) {
				unlock_page(page);
				continue;
			}
			truncate_inode_page(mapping, page);
			unlock_page(page);
		}
		pagevec_release(&pvec);
		mem_cgroup_uncharge_end();
		cond_resched();
	}

	if (partial) {
		struct page *page = find_lock_page(mapping, start - 1);
		if (page) {
			wait_on_page_writeback(page);
			truncate_partial_page(page, partial);
			unlock_page(page);
			page_cache_release(page);
		}
	}

	next = start;
	for ( ; ; ) {
		cond_resched();
		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
			if (next == start)
				break;
			next = start;
			continue;
		}
		if (pvec.pages[0]->index > end) {
			pagevec_release(&pvec);
			break;
		}
		mem_cgroup_uncharge_start();
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];

			if (page->index > end)
				break;
			lock_page(page);
			wait_on_page_writeback(page);
			truncate_inode_page(mapping, page);
			if (page->index > next)
				next = page->index;
			next++;
			unlock_page(page);
		}
		pagevec_release(&pvec);
		mem_cgroup_uncharge_end();
	}
	cleancache_flush_inode(mapping);
}
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_mutex.
 *
 * 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);

/**
 * invalidate_mapping_pages - 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)
 *
 * This function only removes the unlocked pages, if you want to
 * remove all the pages of one inode, you must call truncate_inode_pages.
 *
 * invalidate_mapping_pages() will not block on IO activity. It will not
 * invalidate pages which are dirty, locked, under writeback or mapped into
 * pagetables.
 */
unsigned long invalidate_mapping_pages(struct address_space *mapping,
		pgoff_t start, pgoff_t end)
{
	struct pagevec pvec;
	pgoff_t next = start;
	unsigned long ret;
	unsigned long count = 0;
	int i;

	pagevec_init(&pvec, 0);
	while (next <= end &&
			pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
		mem_cgroup_uncharge_start();
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			pgoff_t index;
			int lock_failed;

			lock_failed = !trylock_page(page);

			/*
			 * We really shouldn't be looking at the ->index of an
			 * unlocked page.  But we're not allowed to lock these
			 * pages.  So we rely upon nobody altering the ->index
			 * of this (pinned-by-us) page.
			 */
			index = page->index;
			if (index > next)
				next = index;
			next++;
			if (lock_failed)
				continue;

			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_page(page);
			count += ret;
			if (next > end)
				break;
		}
		pagevec_release(&pvec);
		mem_cgroup_uncharge_end();
		cond_resched();
	}
	return count;
}
EXPORT_SYMBOL(invalidate_mapping_pages);

/*
 * 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_page2(struct address_space *mapping, struct page *page)
{
	if (page->mapping != mapping)
		return 0;

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

	spin_lock_irq(&mapping->tree_lock);
	if (PageDirty(page))
		goto failed;

	clear_page_mlock(page);
	BUG_ON(page_has_private(page));
	__delete_from_page_cache(page);
	spin_unlock_irq(&mapping->tree_lock);
	mem_cgroup_uncharge_cache_page(page);

	if (mapping->a_ops->freepage)
		mapping->a_ops->freepage(page);

	page_cache_release(page);	/* pagecache ref */
	return 1;
failed:
	spin_unlock_irq(&mapping->tree_lock);
	return 0;
}

static int do_launder_page(struct address_space *mapping, struct page *page)
{
	if (!PageDirty(page))
		return 0;
	if (page->mapping != mapping || mapping->a_ops->launder_page == NULL)
		return 0;
	return mapping->a_ops->launder_page(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.
 *
 * Returns -EBUSY if any pages could not be invalidated.
 */
int invalidate_inode_pages2_range(struct address_space *mapping,
				  pgoff_t start, pgoff_t end)
{
	struct pagevec pvec;
	pgoff_t next;
	int i;
	int ret = 0;
	int ret2 = 0;
	int did_range_unmap = 0;
	int wrapped = 0;

	cleancache_flush_inode(mapping);
	pagevec_init(&pvec, 0);
	next = start;
	while (next <= end && !wrapped &&
		pagevec_lookup(&pvec, mapping, next,
			min(end - next, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
		mem_cgroup_uncharge_start();
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			pgoff_t page_index;

			lock_page(page);
			if (page->mapping != mapping) {
				unlock_page(page);
				continue;
			}
			page_index = page->index;
			next = page_index + 1;
			if (next == 0)
				wrapped = 1;
			if (page_index > end) {
				unlock_page(page);
				break;
			}
			wait_on_page_writeback(page);
			if (page_mapped(page)) {
				if (!did_range_unmap) {
					/*
					 * Zap the rest of the file in one hit.
					 */
					unmap_mapping_range(mapping,
					   (loff_t)page_index<<PAGE_CACHE_SHIFT,
					   (loff_t)(end - page_index + 1)
							<< PAGE_CACHE_SHIFT,
					    0);
					did_range_unmap = 1;
				} else {
					/*
					 * Just zap this page
					 */
					unmap_mapping_range(mapping,
					  (loff_t)page_index<<PAGE_CACHE_SHIFT,
					  PAGE_CACHE_SIZE, 0);
				}
			}
			BUG_ON(page_mapped(page));
			ret2 = do_launder_page(mapping, page);
			if (ret2 == 0) {
				if (!invalidate_complete_page2(mapping, page))
					ret2 = -EBUSY;
			}
			if (ret2 < 0)
				ret = ret2;
			unlock_page(page);
		}
		pagevec_release(&pvec);
		mem_cgroup_uncharge_end();
		cond_resched();
	}
	cleancache_flush_inode(mapping);
	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.
 *
 * Returns -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
 * @oldsize: old file size
 * @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 oldsize, 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 inode_mutex held and before all filesystem specific
 * block truncation has been performed.
 */
void truncate_setsize(struct inode *inode, loff_t newsize)
{
	loff_t oldsize;

	oldsize = inode->i_size;
	i_size_write(inode, newsize);

	truncate_pagecache(inode, oldsize, newsize);
}
EXPORT_SYMBOL(truncate_setsize);

/**
 * vmtruncate - unmap mappings "freed" by truncate() syscall
 * @inode: inode of the file used
 * @newsize: file offset to start truncating
 *
 * This function is deprecated and truncate_setsize or truncate_pagecache
 * should be used instead, together with filesystem specific block truncation.
 */
int vmtruncate(struct inode *inode, loff_t newsize)
{
	int error;

	error = inode_newsize_ok(inode, newsize);
	if (error)
		return error;

	truncate_setsize(inode, newsize);
	if (inode->i_op->truncate)
		inode->i_op->truncate(inode);
	return 0;
}
EXPORT_SYMBOL(vmtruncate);

int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
	struct address_space *mapping = inode->i_mapping;
	loff_t holebegin = round_up(lstart, PAGE_SIZE);
	loff_t holelen = 1 + lend - holebegin;

	/*
	 * If the underlying filesystem is not going to provide
	 * a way to truncate a range of blocks (punch a hole) -
	 * we should return failure right now.
	 */
	if (!inode->i_op->truncate_range)
		return -ENOSYS;

	mutex_lock(&inode->i_mutex);
	inode_dio_wait(inode);
	unmap_mapping_range(mapping, holebegin, holelen, 1);
	inode->i_op->truncate_range(inode, lstart, lend);
	/* unmap again to remove racily COWed private pages */
	unmap_mapping_range(mapping, holebegin, holelen, 1);
	mutex_unlock(&inode->i_mutex);

	return 0;
}