aboutsummaryrefslogtreecommitdiffstats
path: root/mm/readahead.c
blob: e4ed04149785f069b201cd2ffaa9caa90c4b0d22 (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
/*
 * mm/readahead.c - address_space-level file readahead.
 *
 * Copyright (C) 2002, Linus Torvalds
 *
 * 09Apr2002	Andrew Morton
 *		Initial version.
 */

#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/pagevec.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/file.h>

/*
 * Initialise a struct file's readahead state.  Assumes that the caller has
 * memset *ra to zero.
 */
void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
{
	ra->ra_pages = mapping->backing_dev_info->ra_pages;
	ra->prev_pos = -1;
}
EXPORT_SYMBOL_GPL(file_ra_state_init);

#define list_to_page(head) (list_entry((head)->prev, struct page, lru))

/*
 * see if a page needs releasing upon read_cache_pages() failure
 * - the caller of read_cache_pages() may have set PG_private or PG_fscache
 *   before calling, such as the NFS fs marking pages that are cached locally
 *   on disk, thus we need to give the fs a chance to clean up in the event of
 *   an error
 */
static void read_cache_pages_invalidate_page(struct address_space *mapping,
					     struct page *page)
{
	if (page_has_private(page)) {
		if (!trylock_page(page))
			BUG();
		page->mapping = mapping;
		do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
		page->mapping = NULL;
		unlock_page(page);
	}
	page_cache_release(page);
}

/*
 * release a list of pages, invalidating them first if need be
 */
static void read_cache_pages_invalidate_pages(struct address_space *mapping,
					      struct list_head *pages)
{
	struct page *victim;

	while (!list_empty(pages)) {
		victim = list_to_page(pages);
		list_del(&victim->lru);
		read_cache_pages_invalidate_page(mapping, victim);
	}
}

/**
 * read_cache_pages - populate an address space with some pages & start reads against them
 * @mapping: the address_space
 * @pages: The address of a list_head which contains the target pages.  These
 *   pages have their ->index populated and are otherwise uninitialised.
 * @filler: callback routine for filling a single page.
 * @data: private data for the callback routine.
 *
 * Hides the details of the LRU cache etc from the filesystems.
 */
int read_cache_pages(struct address_space *mapping, struct list_head *pages,
			int (*filler)(void *, struct page *), void *data)
{
	struct page *page;
	int ret = 0;

	while (!list_empty(pages)) {
		page = list_to_page(pages);
		list_del(&page->lru);
		if (add_to_page_cache_lru(page, mapping,
					page->index, GFP_KERNEL)) {
			read_cache_pages_invalidate_page(mapping, page);
			continue;
		}
		page_cache_release(page);

		ret = filler(data, page);
		if (unlikely(ret)) {
			read_cache_pages_invalidate_pages(mapping, pages);
			break;
		}
		task_io_account_read(PAGE_CACHE_SIZE);
	}
	return ret;
}

EXPORT_SYMBOL(read_cache_pages);

static int read_pages(struct address_space *mapping, struct file *filp,
		struct list_head *pages, unsigned nr_pages)
{
	struct blk_plug plug;
	unsigned page_idx;
	int ret;

	blk_start_plug(&plug);

	if (mapping->a_ops->readpages) {
		ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
		/* Clean up the remaining pages */
		put_pages_list(pages);
		goto out;
	}

	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
		struct page *page = list_to_page(pages);
		list_del(&page->lru);
		if (!add_to_page_cache_lru(page, mapping,
					page->index, GFP_KERNEL)) {
			mapping->a_ops->readpage(filp, page);
		}
		page_cache_release(page);
	}
	ret = 0;

out:
	blk_finish_plug(&plug);

	return ret;
}

/*
 * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
 * the pages first, then submits them all for I/O. This avoids the very bad
 * behaviour which would occur if page allocations are causing VM writeback.
 * We really don't want to intermingle reads and writes like that.
 *
 * Returns the number of pages requested, or the maximum amount of I/O allowed.
 */
static int
__do_page_cache_readahead(struct address_space *mapping, struct file *filp,
			pgoff_t offset, unsigned long nr_to_read,
			unsigned long lookahead_size)
{
	struct inode *inode = mapping->host;
	struct page *page;
	unsigned long end_index;	/* The last page we want to read */
	LIST_HEAD(page_pool);
	int page_idx;
	int ret = 0;
	loff_t isize = i_size_read(inode);

	if (isize == 0)
		goto out;

	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);

	/*
	 * Preallocate as many pages as we will need.
	 */
	for (page_idx = 0; page_idx < nr_to_read; page_idx++) {
		pgoff_t page_offset = offset + page_idx;

		if (page_offset > end_index)
			break;

		rcu_read_lock();
		page = radix_tree_lookup(&mapping->page_tree, page_offset);
		rcu_read_unlock();
		if (page)
			continue;

		page = page_cache_alloc_readahead(mapping);
		if (!page)
			break;
		page->index = page_offset;
		list_add(&page->lru, &page_pool);
		if (page_idx == nr_to_read - lookahead_size)
			SetPageReadahead(page);
		ret++;
	}

	/*
	 * Now start the IO.  We ignore I/O errors - if the page is not
	 * uptodate then the caller will launch readpage again, and
	 * will then handle the error.
	 */
	if (ret)
		read_pages(mapping, filp, &page_pool, ret);
	BUG_ON(!list_empty(&page_pool));
out:
	return ret;
}

/*
 * Chunk the readahead into 2 megabyte units, so that we don't pin too much
 * memory at once.
 */
int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
		pgoff_t offset, unsigned long nr_to_read)
{
	int ret = 0;

	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
		return -EINVAL;

	nr_to_read = max_sane_readahead(nr_to_read);
	while (nr_to_read) {
		int err;

		unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_CACHE_SIZE;

		if (this_chunk > nr_to_read)
			this_chunk = nr_to_read;
		err = __do_page_cache_readahead(mapping, filp,
						offset, this_chunk, 0);
		if (err < 0) {
			ret = err;
			break;
		}
		ret += err;
		offset += this_chunk;
		nr_to_read -= this_chunk;
	}
	return ret;
}

/*
 * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
 * sensible upper limit.
 */
unsigned long max_sane_readahead(unsigned long nr)
{
	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
}

/*
 * Submit IO for the read-ahead request in file_ra_state.
 */
unsigned long ra_submit(struct file_ra_state *ra,
		       struct address_space *mapping, struct file *filp)
{
	int actual;

	actual = __do_page_cache_readahead(mapping, filp,
					ra->start, ra->size, ra->async_size);

	return actual;
}

/*
 * Set the initial window size, round to next power of 2 and square
 * for small size, x 4 for medium, and x 2 for large
 * for 128k (32 page) max ra
 * 1-8 page = 32k initial, > 8 page = 128k initial
 */
static unsigned long get_init_ra_size(unsigned long size, unsigned long max)
{
	unsigned long newsize = roundup_pow_of_two(size);

	if (newsize <= max / 32)
		newsize = newsize * 4;
	else if (newsize <= max / 4)
		newsize = newsize * 2;
	else
		newsize = max;

	return newsize;
}

/*
 *  Get the previous window size, ramp it up, and
 *  return it as the new window size.
 */
static unsigned long get_next_ra_size(struct file_ra_state *ra,
						unsigned long max)
{
	unsigned long cur = ra->size;
	unsigned long newsize;

	if (cur < max / 16)
		newsize = 4 * cur;
	else
		newsize = 2 * cur;

	return min(newsize, max);
}

/*
 * On-demand readahead design.
 *
 * The fields in struct file_ra_state represent the most-recently-executed
 * readahead attempt:
 *
 *                        |<----- async_size ---------|
 *     |------------------- size -------------------->|
 *     |==================#===========================|
 *     ^start             ^page marked with PG_readahead
 *
 * To overlap application thinking time and disk I/O time, we do
 * `readahead pipelining': Do not wait until the application consumed all
 * readahead pages and stalled on the missing page at readahead_index;
 * Instead, submit an asynchronous readahead I/O as soon as there are
 * only async_size pages left in the readahead window. Normally async_size
 * will be equal to size, for maximum pipelining.
 *
 * In interleaved sequential reads, concurrent streams on the same fd can
 * be invalidating each other's readahead state. So we flag the new readahead
 * page at (start+size-async_size) with PG_readahead, and use it as readahead
 * indicator. The flag won't be set on already cached pages, to avoid the
 * readahead-for-nothing fuss, saving pointless page cache lookups.
 *
 * prev_pos tracks the last visited byte in the _previous_ read request.
 * It should be maintained by the caller, and will be used for detecting
 * small random reads. Note that the readahead algorithm checks loosely
 * for sequential patterns. Hence interleaved reads might be served as
 * sequential ones.
 *
 * There is a special-case: if the first page which the application tries to
 * read happens to be the first page of the file, it is assumed that a linear
 * read is about to happen and the window is immediately set to the initial size
 * based on I/O request size and the max_readahead.
 *
 * The code ramps up the readahead size aggressively at first, but slow down as
 * it approaches max_readhead.
 */

/*
 * Count contiguously cached pages from @offset-1 to @offset-@max,
 * this count is a conservative estimation of
 * 	- length of the sequential read sequence, or
 * 	- thrashing threshold in memory tight systems
 */
static pgoff_t count_history_pages(struct address_space *mapping,
				   struct file_ra_state *ra,
				   pgoff_t offset, unsigned long max)
{
	pgoff_t head;

	rcu_read_lock();
	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
	rcu_read_unlock();

	return offset - 1 - head;
}

/*
 * page cache context based read-ahead
 */
static int try_context_readahead(struct address_space *mapping,
				 struct file_ra_state *ra,
				 pgoff_t offset,
				 unsigned long req_size,
				 unsigned long max)
{
	pgoff_t size;

	size = count_history_pages(mapping, ra, offset, max);

	/*
	 * not enough history pages:
	 * it could be a random read
	 */
	if (size <= req_size)
		return 0;

	/*
	 * starts from beginning of file:
	 * it is a strong indication of long-run stream (or whole-file-read)
	 */
	if (size >= offset)
		size *= 2;

	ra->start = offset;
	ra->size = min(size + req_size, max);
	ra->async_size = 1;

	return 1;
}

/*
 * A minimal readahead algorithm for trivial sequential/random reads.
 */
static unsigned long
ondemand_readahead(struct address_space *mapping,
		   struct file_ra_state *ra, struct file *filp,
		   bool hit_readahead_marker, pgoff_t offset,
		   unsigned long req_size)
{
	unsigned long max = max_sane_readahead(ra->ra_pages);

	/*
	 * start of file
	 */
	if (!offset)
		goto initial_readahead;

	/*
	 * It's the expected callback offset, assume sequential access.
	 * Ramp up sizes, and push forward the readahead window.
	 */
	if ((offset == (ra->start + ra->size - ra->async_size) ||
	     offset == (ra->start + ra->size))) {
		ra->start += ra->size;
		ra->size = get_next_ra_size(ra, max);
		ra->async_size = ra->size;
		goto readit;
	}

	/*
	 * Hit a marked page without valid readahead state.
	 * E.g. interleaved reads.
	 * Query the pagecache for async_size, which normally equals to
	 * readahead size. Ramp it up and use it as the new readahead size.
	 */
	if (hit_readahead_marker) {
		pgoff_t start;

		rcu_read_lock();
		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
		rcu_read_unlock();

		if (!start || start - offset > max)
			return 0;

		ra->start = start;
		ra->size = start - offset;	/* old async_size */
		ra->size += req_size;
		ra->size = get_next_ra_size(ra, max);
		ra->async_size = ra->size;
		goto readit;
	}

	/*
	 * oversize read
	 */
	if (req_size > max)
		goto initial_readahead;

	/*
	 * sequential cache miss
	 */
	if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
		goto initial_readahead;

	/*
	 * Query the page cache and look for the traces(cached history pages)
	 * that a sequential stream would leave behind.
	 */
	if (try_context_readahead(mapping, ra, offset, req_size, max))
		goto readit;

	/*
	 * standalone, small random read
	 * Read as is, and do not pollute the readahead state.
	 */
	return __do_page_cache_readahead(mapping, filp, offset, req_size, 0);

initial_readahead:
	ra->start = offset;
	ra->size = get_init_ra_size(req_size, max);
	ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;

readit:
	/*
	 * Will this read hit the readahead marker made by itself?
	 * If so, trigger the readahead marker hit now, and merge
	 * the resulted next readahead window into the current one.
	 */
	if (offset == ra->start && ra->size == ra->async_size) {
		ra->async_size = get_next_ra_size(ra, max);
		ra->size += ra->async_size;
	}

	return ra_submit(ra, mapping, filp);
}

/**
 * page_cache_sync_readahead - generic file readahead
 * @mapping: address_space which holds the pagecache and I/O vectors
 * @ra: file_ra_state which holds the readahead state
 * @filp: passed on to ->readpage() and ->readpages()
 * @offset: start offset into @mapping, in pagecache page-sized units
 * @req_size: hint: total size of the read which the caller is performing in
 *            pagecache pages
 *
 * page_cache_sync_readahead() should be called when a cache miss happened:
 * it will submit the read.  The readahead logic may decide to piggyback more
 * pages onto the read request if access patterns suggest it will improve
 * performance.
 */
void page_cache_sync_readahead(struct address_space *mapping,
			       struct file_ra_state *ra, struct file *filp,
			       pgoff_t offset, unsigned long req_size)
{
	/* no read-ahead */
	if (!ra->ra_pages)
		return;

	/* be dumb */
	if (filp && (filp->f_mode & FMODE_RANDOM)) {
		force_page_cache_readahead(mapping, filp, offset, req_size);
		return;
	}

	/* do read-ahead */
	ondemand_readahead(mapping, ra, filp, false, offset, req_size);
}
EXPORT_SYMBOL_GPL(page_cache_sync_readahead);

/**
 * page_cache_async_readahead - file readahead for marked pages
 * @mapping: address_space which holds the pagecache and I/O vectors
 * @ra: file_ra_state which holds the readahead state
 * @filp: passed on to ->readpage() and ->readpages()
 * @page: the page at @offset which has the PG_readahead flag set
 * @offset: start offset into @mapping, in pagecache page-sized units
 * @req_size: hint: total size of the read which the caller is performing in
 *            pagecache pages
 *
 * page_cache_async_readahead() should be called when a page is used which
 * has the PG_readahead flag; this is a marker to suggest that the application
 * has used up enough of the readahead window that we should start pulling in
 * more pages.
 */
void
page_cache_async_readahead(struct address_space *mapping,
			   struct file_ra_state *ra, struct file *filp,
			   struct page *page, pgoff_t offset,
			   unsigned long req_size)
{
	/* no read-ahead */
	if (!ra->ra_pages)
		return;

	/*
	 * Same bit is used for PG_readahead and PG_reclaim.
	 */
	if (PageWriteback(page))
		return;

	ClearPageReadahead(page);

	/*
	 * Defer asynchronous read-ahead on IO congestion.
	 */
	if (bdi_read_congested(mapping->backing_dev_info))
		return;

	/* do read-ahead */
	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
}
EXPORT_SYMBOL_GPL(page_cache_async_readahead);

static ssize_t
do_readahead(struct address_space *mapping, struct file *filp,
	     pgoff_t index, unsigned long nr)
{
	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
		return -EINVAL;

	force_page_cache_readahead(mapping, filp, index, nr);
	return 0;
}

SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
{
	ssize_t ret;
	struct fd f;

	ret = -EBADF;
	f = fdget(fd);
	if (f.file) {
		if (f.file->f_mode & FMODE_READ) {
			struct address_space *mapping = f.file->f_mapping;
			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
			unsigned long len = end - start + 1;
			ret = do_readahead(mapping, f.file, start, len);
		}
		fdput(f);
	}
	return ret;
}