summaryrefslogtreecommitdiffstats
path: root/include/linux/pagemap.h
blob: 01e84436cddfec1da8b871b6343d72a2420ba070 (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
#ifndef _LINUX_PAGEMAP_H
#define _LINUX_PAGEMAP_H

/*
 * Copyright 1995 Linus Torvalds
 */
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/compiler.h>
#include <asm/uaccess.h>
#include <linux/gfp.h>
#include <linux/bitops.h>
#include <linux/hardirq.h> /* for in_interrupt() */
#include <linux/hugetlb_inline.h>

/*
 * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
 * allocation mode flags.
 */
enum mapping_flags {
	AS_EIO		= __GFP_BITS_SHIFT + 0,	/* IO error on async write */
	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
	AS_EXITING	= __GFP_BITS_SHIFT + 4, /* final truncate in progress */
};

static inline void mapping_set_error(struct address_space *mapping, int error)
{
	if (unlikely(error)) {
		if (error == -ENOSPC)
			set_bit(AS_ENOSPC, &mapping->flags);
		else
			set_bit(AS_EIO, &mapping->flags);
	}
}

static inline void mapping_set_unevictable(struct address_space *mapping)
{
	set_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline void mapping_clear_unevictable(struct address_space *mapping)
{
	clear_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline int mapping_unevictable(struct address_space *mapping)
{
	if (mapping)
		return test_bit(AS_UNEVICTABLE, &mapping->flags);
	return !!mapping;
}

static inline void mapping_set_exiting(struct address_space *mapping)
{
	set_bit(AS_EXITING, &mapping->flags);
}

static inline int mapping_exiting(struct address_space *mapping)
{
	return test_bit(AS_EXITING, &mapping->flags);
}

static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
}

/* Restricts the given gfp_mask to what the mapping allows. */
static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
		gfp_t gfp_mask)
{
	return mapping_gfp_mask(mapping) & gfp_mask;
}

/*
 * This is non-atomic.  Only to be used before the mapping is activated.
 * Probably needs a barrier...
 */
static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
{
	m->flags = (m->flags & ~(__force unsigned long)__GFP_BITS_MASK) |
				(__force unsigned long)mask;
}

void release_pages(struct page **pages, int nr, bool cold);

/*
 * speculatively take a reference to a page.
 * If the page is free (_refcount == 0), then _refcount is untouched, and 0
 * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned.
 *
 * This function must be called inside the same rcu_read_lock() section as has
 * been used to lookup the page in the pagecache radix-tree (or page table):
 * this allows allocators to use a synchronize_rcu() to stabilize _refcount.
 *
 * Unless an RCU grace period has passed, the count of all pages coming out
 * of the allocator must be considered unstable. page_count may return higher
 * than expected, and put_page must be able to do the right thing when the
 * page has been finished with, no matter what it is subsequently allocated
 * for (because put_page is what is used here to drop an invalid speculative
 * reference).
 *
 * This is the interesting part of the lockless pagecache (and lockless
 * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
 * has the following pattern:
 * 1. find page in radix tree
 * 2. conditionally increment refcount
 * 3. check the page is still in pagecache (if no, goto 1)
 *
 * Remove-side that cares about stability of _refcount (eg. reclaim) has the
 * following (with tree_lock held for write):
 * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
 * B. remove page from pagecache
 * C. free the page
 *
 * There are 2 critical interleavings that matter:
 * - 2 runs before A: in this case, A sees elevated refcount and bails out
 * - A runs before 2: in this case, 2 sees zero refcount and retries;
 *   subsequently, B will complete and 1 will find no page, causing the
 *   lookup to return NULL.
 *
 * It is possible that between 1 and 2, the page is removed then the exact same
 * page is inserted into the same position in pagecache. That's OK: the
 * old find_get_page using tree_lock could equally have run before or after
 * such a re-insertion, depending on order that locks are granted.
 *
 * Lookups racing against pagecache insertion isn't a big problem: either 1
 * will find the page or it will not. Likewise, the old find_get_page could run
 * either before the insertion or afterwards, depending on timing.
 */
static inline int page_cache_get_speculative(struct page *page)
{
	VM_BUG_ON(in_interrupt());

#ifdef CONFIG_TINY_RCU
# ifdef CONFIG_PREEMPT_COUNT
	VM_BUG_ON(!in_atomic());
# endif
	/*
	 * Preempt must be disabled here - we rely on rcu_read_lock doing
	 * this for us.
	 *
	 * Pagecache won't be truncated from interrupt context, so if we have
	 * found a page in the radix tree here, we have pinned its refcount by
	 * disabling preempt, and hence no need for the "speculative get" that
	 * SMP requires.
	 */
	VM_BUG_ON_PAGE(page_count(page) == 0, page);
	page_ref_inc(page);

#else
	if (unlikely(!get_page_unless_zero(page))) {
		/*
		 * Either the page has been freed, or will be freed.
		 * In either case, retry here and the caller should
		 * do the right thing (see comments above).
		 */
		return 0;
	}
#endif
	VM_BUG_ON_PAGE(PageTail(page), page);

	return 1;
}

/*
 * Same as above, but add instead of inc (could just be merged)
 */
static inline int page_cache_add_speculative(struct page *page, int count)
{
	VM_BUG_ON(in_interrupt());

#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
# ifdef CONFIG_PREEMPT_COUNT
	VM_BUG_ON(!in_atomic());
# endif
	VM_BUG_ON_PAGE(page_count(page) == 0, page);
	page_ref_add(page, count);

#else
	if (unlikely(!page_ref_add_unless(page, count, 0)))
		return 0;
#endif
	VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);

	return 1;
}

#ifdef CONFIG_NUMA
extern struct page *__page_cache_alloc(gfp_t gfp);
#else
static inline struct page *__page_cache_alloc(gfp_t gfp)
{
	return alloc_pages(gfp, 0);
}
#endif

static inline struct page *page_cache_alloc(struct address_space *x)
{
	return __page_cache_alloc(mapping_gfp_mask(x));
}

static inline struct page *page_cache_alloc_cold(struct address_space *x)
{
	return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
}

static inline gfp_t readahead_gfp_mask(struct address_space *x)
{
	return mapping_gfp_mask(x) |
				  __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN;
}

typedef int filler_t(void *, struct page *);

pgoff_t page_cache_next_hole(struct address_space *mapping,
			     pgoff_t index, unsigned long max_scan);
pgoff_t page_cache_prev_hole(struct address_space *mapping,
			     pgoff_t index, unsigned long max_scan);

#define FGP_ACCESSED		0x00000001
#define FGP_LOCK		0x00000002
#define FGP_CREAT		0x00000004
#define FGP_WRITE		0x00000008
#define FGP_NOFS		0x00000010
#define FGP_NOWAIT		0x00000020

struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
		int fgp_flags, gfp_t cache_gfp_mask);

/**
 * find_get_page - find and get a page reference
 * @mapping: the address_space to search
 * @offset: the page index
 *
 * Looks up the page cache slot at @mapping & @offset.  If there is a
 * page cache page, it is returned with an increased refcount.
 *
 * Otherwise, %NULL is returned.
 */
static inline struct page *find_get_page(struct address_space *mapping,
					pgoff_t offset)
{
	return pagecache_get_page(mapping, offset, 0, 0);
}

static inline struct page *find_get_page_flags(struct address_space *mapping,
					pgoff_t offset, int fgp_flags)
{
	return pagecache_get_page(mapping, offset, fgp_flags, 0);
}

/**
 * find_lock_page - locate, pin and lock a pagecache page
 * pagecache_get_page - find and get a page reference
 * @mapping: the address_space to search
 * @offset: the page index
 *
 * Looks up the page cache slot at @mapping & @offset.  If there is a
 * page cache page, it is returned locked and with an increased
 * refcount.
 *
 * Otherwise, %NULL is returned.
 *
 * find_lock_page() may sleep.
 */
static inline struct page *find_lock_page(struct address_space *mapping,
					pgoff_t offset)
{
	return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
}

/**
 * find_or_create_page - locate or add a pagecache page
 * @mapping: the page's address_space
 * @index: the page's index into the mapping
 * @gfp_mask: page allocation mode
 *
 * Looks up the page cache slot at @mapping & @offset.  If there is a
 * page cache page, it is returned locked and with an increased
 * refcount.
 *
 * If the page is not present, a new page is allocated using @gfp_mask
 * and added to the page cache and the VM's LRU list.  The page is
 * returned locked and with an increased refcount.
 *
 * On memory exhaustion, %NULL is returned.
 *
 * find_or_create_page() may sleep, even if @gfp_flags specifies an
 * atomic allocation!
 */
static inline struct page *find_or_create_page(struct address_space *mapping,
					pgoff_t offset, gfp_t gfp_mask)
{
	return pagecache_get_page(mapping, offset,
					FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
					gfp_mask);
}

/**
 * grab_cache_page_nowait - returns locked page at given index in given cache
 * @mapping: target address_space
 * @index: the page index
 *
 * Same as grab_cache_page(), but do not wait if the page is unavailable.
 * This is intended for speculative data generators, where the data can
 * be regenerated if the page couldn't be grabbed.  This routine should
 * be safe to call while holding the lock for another page.
 *
 * Clear __GFP_FS when allocating the page to avoid recursion into the fs
 * and deadlock against the caller's locked page.
 */
static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
				pgoff_t index)
{
	return pagecache_get_page(mapping, index,
			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
			mapping_gfp_mask(mapping));
}

struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
			  unsigned int nr_entries, struct page **entries,
			  pgoff_t *indices);
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
			unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
			       unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
			int tag, unsigned int nr_pages, struct page **pages);
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
			int tag, unsigned int nr_entries,
			struct page **entries, pgoff_t *indices);

struct page *grab_cache_page_write_begin(struct address_space *mapping,
			pgoff_t index, unsigned flags);

/*
 * Returns locked page at given index in given cache, creating it if needed.
 */
static inline struct page *grab_cache_page(struct address_space *mapping,
								pgoff_t index)
{
	return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
}

extern struct page * read_cache_page(struct address_space *mapping,
				pgoff_t index, filler_t *filler, void *data);
extern struct page * read_cache_page_gfp(struct address_space *mapping,
				pgoff_t index, gfp_t gfp_mask);
extern int read_cache_pages(struct address_space *mapping,
		struct list_head *pages, filler_t *filler, void *data);

static inline struct page *read_mapping_page(struct address_space *mapping,
				pgoff_t index, void *data)
{
	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
	return read_cache_page(mapping, index, filler, data);
}

/*
 * Get the offset in PAGE_SIZE.
 * (TODO: hugepage should have ->index in PAGE_SIZE)
 */
static inline pgoff_t page_to_pgoff(struct page *page)
{
	pgoff_t pgoff;

	if (unlikely(PageHeadHuge(page)))
		return page->index << compound_order(page);

	if (likely(!PageTransTail(page)))
		return page->index;

	/*
	 *  We don't initialize ->index for tail pages: calculate based on
	 *  head page
	 */
	pgoff = compound_head(page)->index;
	pgoff += page - compound_head(page);
	return pgoff;
}

/*
 * Return byte-offset into filesystem object for page.
 */
static inline loff_t page_offset(struct page *page)
{
	return ((loff_t)page->index) << PAGE_SHIFT;
}

static inline loff_t page_file_offset(struct page *page)
{
	return ((loff_t)page_file_index(page)) << PAGE_SHIFT;
}

extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
				     unsigned long address);

static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
					unsigned long address)
{
	pgoff_t pgoff;
	if (unlikely(is_vm_hugetlb_page(vma)))
		return linear_hugepage_index(vma, address);
	pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
	pgoff += vma->vm_pgoff;
	return pgoff;
}

extern void __lock_page(struct page *page);
extern int __lock_page_killable(struct page *page);
extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
				unsigned int flags);
extern void unlock_page(struct page *page);

static inline int trylock_page(struct page *page)
{
	page = compound_head(page);
	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
}

/*
 * lock_page may only be called if we have the page's inode pinned.
 */
static inline void lock_page(struct page *page)
{
	might_sleep();
	if (!trylock_page(page))
		__lock_page(page);
}

/*
 * lock_page_killable is like lock_page but can be interrupted by fatal
 * signals.  It returns 0 if it locked the page and -EINTR if it was
 * killed while waiting.
 */
static inline int lock_page_killable(struct page *page)
{
	might_sleep();
	if (!trylock_page(page))
		return __lock_page_killable(page);
	return 0;
}

/*
 * lock_page_or_retry - Lock the page, unless this would block and the
 * caller indicated that it can handle a retry.
 *
 * Return value and mmap_sem implications depend on flags; see
 * __lock_page_or_retry().
 */
static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
				     unsigned int flags)
{
	might_sleep();
	return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
}

/*
 * This is exported only for wait_on_page_locked/wait_on_page_writeback,
 * and for filesystems which need to wait on PG_private.
 */
extern void wait_on_page_bit(struct page *page, int bit_nr);

extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
extern int wait_on_page_bit_killable_timeout(struct page *page,
					     int bit_nr, unsigned long timeout);

static inline int wait_on_page_locked_killable(struct page *page)
{
	if (!PageLocked(page))
		return 0;
	return wait_on_page_bit_killable(compound_head(page), PG_locked);
}

extern wait_queue_head_t *page_waitqueue(struct page *page);
static inline void wake_up_page(struct page *page, int bit)
{
	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
}

/* 
 * Wait for a page to be unlocked.
 *
 * This must be called with the caller "holding" the page,
 * ie with increased "page->count" so that the page won't
 * go away during the wait..
 */
static inline void wait_on_page_locked(struct page *page)
{
	if (PageLocked(page))
		wait_on_page_bit(compound_head(page), PG_locked);
}

/* 
 * Wait for a page to complete writeback
 */
static inline void wait_on_page_writeback(struct page *page)
{
	if (PageWriteback(page))
		wait_on_page_bit(page, PG_writeback);
}

extern void end_page_writeback(struct page *page);
void wait_for_stable_page(struct page *page);

void page_endio(struct page *page, bool is_write, int err);

/*
 * Add an arbitrary waiter to a page's wait queue
 */
extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);

/*
 * Fault one or two userspace pages into pagetables.
 * Return -EINVAL if more than two pages would be needed.
 * Return non-zero on a fault.
 */
static inline int fault_in_pages_writeable(char __user *uaddr, int size)
{
	int span, ret;

	if (unlikely(size == 0))
		return 0;

	span = offset_in_page(uaddr) + size;
	if (span > 2 * PAGE_SIZE)
		return -EINVAL;
	/*
	 * Writing zeroes into userspace here is OK, because we know that if
	 * the zero gets there, we'll be overwriting it.
	 */
	ret = __put_user(0, uaddr);
	if (ret == 0 && span > PAGE_SIZE)
		ret = __put_user(0, uaddr + size - 1);
	return ret;
}

static inline int fault_in_pages_readable(const char __user *uaddr, int size)
{
	volatile char c;
	int ret;

	if (unlikely(size == 0))
		return 0;

	ret = __get_user(c, uaddr);
	if (ret == 0) {
		const char __user *end = uaddr + size - 1;

		if (((unsigned long)uaddr & PAGE_MASK) !=
				((unsigned long)end & PAGE_MASK)) {
			ret = __get_user(c, end);
			(void)c;
		}
	}
	return ret;
}

/*
 * Multipage variants of the above prefault helpers, useful if more than
 * PAGE_SIZE of data needs to be prefaulted. These are separate from the above
 * functions (which only handle up to PAGE_SIZE) to avoid clobbering the
 * filemap.c hotpaths.
 */
static inline int fault_in_multipages_writeable(char __user *uaddr, int size)
{
	char __user *end = uaddr + size - 1;

	if (unlikely(size == 0))
		return 0;

	if (unlikely(uaddr > end))
		return -EFAULT;
	/*
	 * Writing zeroes into userspace here is OK, because we know that if
	 * the zero gets there, we'll be overwriting it.
	 */
	do {
		if (unlikely(__put_user(0, uaddr) != 0))
			return -EFAULT;
		uaddr += PAGE_SIZE;
	} while (uaddr <= end);

	/* Check whether the range spilled into the next page. */
	if (((unsigned long)uaddr & PAGE_MASK) ==
			((unsigned long)end & PAGE_MASK))
		return __put_user(0, end);

	return 0;
}

static inline int fault_in_multipages_readable(const char __user *uaddr,
					       int size)
{
	volatile char c;
	const char __user *end = uaddr + size - 1;

	if (unlikely(size == 0))
		return 0;

	if (unlikely(uaddr > end))
		return -EFAULT;

	do {
		if (unlikely(__get_user(c, uaddr) != 0))
			return -EFAULT;
		uaddr += PAGE_SIZE;
	} while (uaddr <= end);

	/* Check whether the range spilled into the next page. */
	if (((unsigned long)uaddr & PAGE_MASK) ==
			((unsigned long)end & PAGE_MASK)) {
		return __get_user(c, end);
	}

	(void)c;
	return 0;
}

int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
				pgoff_t index, gfp_t gfp_mask);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
				pgoff_t index, gfp_t gfp_mask);
extern void delete_from_page_cache(struct page *page);
extern void __delete_from_page_cache(struct page *page, void *shadow);
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);

/*
 * Like add_to_page_cache_locked, but used to add newly allocated pages:
 * the page is new, so we can just run __SetPageLocked() against it.
 */
static inline int add_to_page_cache(struct page *page,
		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
{
	int error;

	__SetPageLocked(page);
	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
	if (unlikely(error))
		__ClearPageLocked(page);
	return error;
}

static inline unsigned long dir_pages(struct inode *inode)
{
	return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
			       PAGE_SHIFT;
}

#endif /* _LINUX_PAGEMAP_H */