summaryrefslogtreecommitdiffstats
path: root/include/linux/pagemap.h
blob: 69ed3cb1197ac942b8d982e395fb48d5ecdbb29b (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
#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() */

/*
 * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
 * allocation mode flags.
 */
#define	AS_EIO		(__GFP_BITS_SHIFT + 0)	/* IO error on async write */
#define AS_ENOSPC	(__GFP_BITS_SHIFT + 1)	/* ENOSPC on async write */
#define AS_MM_ALL_LOCKS	(__GFP_BITS_SHIFT + 2)	/* under mm_take_all_locks() */

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

/*
 * The page cache can done in larger chunks than
 * one page, because it allows for more efficient
 * throughput (it can then be mapped into user
 * space in smaller chunks for same flexibility).
 *
 * Or rather, it _will_ be done in larger chunks.
 */
#define PAGE_CACHE_SHIFT	PAGE_SHIFT
#define PAGE_CACHE_SIZE		PAGE_SIZE
#define PAGE_CACHE_MASK		PAGE_MASK
#define PAGE_CACHE_ALIGN(addr)	(((addr)+PAGE_CACHE_SIZE-1)&PAGE_CACHE_MASK)

#define page_cache_get(page)		get_page(page)
#define page_cache_release(page)	put_page(page)
void release_pages(struct page **pages, int nr, int cold);

/*
 * speculatively take a reference to a page.
 * If the page is free (_count == 0), then _count is untouched, and 0
 * is returned. Otherwise, _count 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 _count.
 *
 * 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 _count (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());

#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
# ifdef CONFIG_PREEMPT
	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_count(page) == 0);
	atomic_inc(&page->_count);

#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(PageTail(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_CLASSIC_RCU)
# ifdef CONFIG_PREEMPT
	VM_BUG_ON(!in_atomic());
# endif
	VM_BUG_ON(page_count(page) == 0);
	atomic_add(count, &page->_count);

#else
	if (unlikely(!atomic_add_unless(&page->_count, count, 0)))
		return 0;
#endif
	VM_BUG_ON(PageCompound(page) && page != compound_head(page));

	return 1;
}

static inline int page_freeze_refs(struct page *page, int count)
{
	return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
}

static inline void page_unfreeze_refs(struct page *page, int count)
{
	VM_BUG_ON(page_count(page) != 0);
	VM_BUG_ON(count == 0);

	atomic_set(&page->_count, count);
}

#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);
}

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

extern struct page * find_get_page(struct address_space *mapping,
				pgoff_t index);
extern struct page * find_lock_page(struct address_space *mapping,
				pgoff_t index);
extern struct page * find_or_create_page(struct address_space *mapping,
				pgoff_t index, gfp_t gfp_mask);
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);

struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index);

/*
 * 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 * grab_cache_page_nowait(struct address_space *mapping,
				pgoff_t index);
extern struct page * read_cache_page_async(struct address_space *mapping,
				pgoff_t index, filler_t *filler,
				void *data);
extern struct page * read_cache_page(struct address_space *mapping,
				pgoff_t index, filler_t *filler,
				void *data);
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_async(
						struct address_space *mapping,
						     pgoff_t index, void *data)
{
	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
	return read_cache_page_async(mapping, index, filler, 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);
}

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 remove_from_page_cache(struct page *page);
extern void __remove_from_page_cache(struct page *page);

/*
 * 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;
}

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

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

extern void __lock_page(struct page *page);
extern int __lock_page_killable(struct page *page);
extern void __lock_page_nosync(struct page *page);
extern void unlock_page(struct page *page);

/*
 * 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 (TestSetPageLocked(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 (TestSetPageLocked(page))
		return __lock_page_killable(page);
	return 0;
}

/*
 * lock_page_nosync should only be used if we can't pin the page's inode.
 * Doesn't play quite so well with block device plugging.
 */
static inline void lock_page_nosync(struct page *page)
{
	might_sleep();
	if (TestSetPageLocked(page))
		__lock_page_nosync(page);
}
	
/*
 * This is exported only for wait_on_page_locked/wait_on_page_writeback.
 * Never use this directly!
 */
extern void wait_on_page_bit(struct page *page, int bit_nr);

/* 
 * 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(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);

/*
 * Fault a userspace page into pagetables.  Return non-zero on a fault.
 *
 * This assumes that two userspace pages are always sufficient.  That's
 * not true if PAGE_CACHE_SIZE > PAGE_SIZE.
 */
static inline int fault_in_pages_writeable(char __user *uaddr, int size)
{
	int ret;

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

	/*
	 * 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) {
		char __user *end = uaddr + size - 1;

		/*
		 * If the page was already mapped, this will get a cache miss
		 * for sure, so try to avoid doing it.
		 */
		if (((unsigned long)uaddr & PAGE_MASK) !=
				((unsigned long)end & PAGE_MASK))
		 	ret = __put_user(0, end);
	}
	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);
	}
	return ret;
}

#endif /* _LINUX_PAGEMAP_H */
OpenPOWER on IntegriCloud