summaryrefslogtreecommitdiff
path: root/fs/mpage.c
blob: 22b9de5ddd684d5606b421d497be85fa52144089 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * fs/mpage.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains functions related to preparing and submitting BIOs which contain
 * multiple pagecache pages.
 *
 * 15May2002	Andrew Morton
 *		Initial version
 * 27Jun2002	axboe@suse.de
 *		use bio_add_page() to build bio's just the right size
 */

#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/kdev_t.h>
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include "internal.h"

/*
 * I/O completion handler for multipage BIOs.
 *
 * The mpage code never puts partial pages into a BIO (except for end-of-file).
 * If a page does not map to a contiguous run of blocks then it simply falls
 * back to block_read_full_folio().
 *
 * Why is this?  If a page's completion depends on a number of different BIOs
 * which can complete in any order (or at the same time) then determining the
 * status of that page is hard.  See end_buffer_async_read() for the details.
 * There is no point in duplicating all that complexity.
 */
static void mpage_end_io(struct bio *bio)
{
	struct bio_vec *bv;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bv, bio, iter_all) {
		struct page *page = bv->bv_page;
		page_endio(page, bio_op(bio),
			   blk_status_to_errno(bio->bi_status));
	}

	bio_put(bio);
}

static struct bio *mpage_bio_submit(struct bio *bio)
{
	bio->bi_end_io = mpage_end_io;
	guard_bio_eod(bio);
	submit_bio(bio);
	return NULL;
}

/*
 * support function for mpage_readahead.  The fs supplied get_block might
 * return an up to date buffer.  This is used to map that buffer into
 * the page, which allows read_folio to avoid triggering a duplicate call
 * to get_block.
 *
 * The idea is to avoid adding buffers to pages that don't already have
 * them.  So when the buffer is up to date and the page size == block size,
 * this marks the page up to date instead of adding new buffers.
 */
static void map_buffer_to_folio(struct folio *folio, struct buffer_head *bh,
		int page_block)
{
	struct inode *inode = folio->mapping->host;
	struct buffer_head *page_bh, *head;
	int block = 0;

	head = folio_buffers(folio);
	if (!head) {
		/*
		 * don't make any buffers if there is only one buffer on
		 * the folio and the folio just needs to be set up to date
		 */
		if (inode->i_blkbits == PAGE_SHIFT &&
		    buffer_uptodate(bh)) {
			folio_mark_uptodate(folio);
			return;
		}
		create_empty_buffers(&folio->page, i_blocksize(inode), 0);
		head = folio_buffers(folio);
	}

	page_bh = head;
	do {
		if (block == page_block) {
			page_bh->b_state = bh->b_state;
			page_bh->b_bdev = bh->b_bdev;
			page_bh->b_blocknr = bh->b_blocknr;
			break;
		}
		page_bh = page_bh->b_this_page;
		block++;
	} while (page_bh != head);
}

struct mpage_readpage_args {
	struct bio *bio;
	struct folio *folio;
	unsigned int nr_pages;
	bool is_readahead;
	sector_t last_block_in_bio;
	struct buffer_head map_bh;
	unsigned long first_logical_block;
	get_block_t *get_block;
};

/*
 * This is the worker routine which does all the work of mapping the disk
 * blocks and constructs largest possible bios, submits them for IO if the
 * blocks are not contiguous on the disk.
 *
 * We pass a buffer_head back and forth and use its buffer_mapped() flag to
 * represent the validity of its disk mapping and to decide when to do the next
 * get_block() call.
 */
static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
{
	struct folio *folio = args->folio;
	struct inode *inode = folio->mapping->host;
	const unsigned blkbits = inode->i_blkbits;
	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
	const unsigned blocksize = 1 << blkbits;
	struct buffer_head *map_bh = &args->map_bh;
	sector_t block_in_file;
	sector_t last_block;
	sector_t last_block_in_file;
	sector_t blocks[MAX_BUF_PER_PAGE];
	unsigned page_block;
	unsigned first_hole = blocks_per_page;
	struct block_device *bdev = NULL;
	int length;
	int fully_mapped = 1;
	blk_opf_t opf = REQ_OP_READ;
	unsigned nblocks;
	unsigned relative_block;
	gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL);

	/* MAX_BUF_PER_PAGE, for example */
	VM_BUG_ON_FOLIO(folio_test_large(folio), folio);

	if (args->is_readahead) {
		opf |= REQ_RAHEAD;
		gfp |= __GFP_NORETRY | __GFP_NOWARN;
	}

	if (folio_buffers(folio))
		goto confused;

	block_in_file = (sector_t)folio->index << (PAGE_SHIFT - blkbits);
	last_block = block_in_file + args->nr_pages * blocks_per_page;
	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
	if (last_block > last_block_in_file)
		last_block = last_block_in_file;
	page_block = 0;

	/*
	 * Map blocks using the result from the previous get_blocks call first.
	 */
	nblocks = map_bh->b_size >> blkbits;
	if (buffer_mapped(map_bh) &&
			block_in_file > args->first_logical_block &&
			block_in_file < (args->first_logical_block + nblocks)) {
		unsigned map_offset = block_in_file - args->first_logical_block;
		unsigned last = nblocks - map_offset;

		for (relative_block = 0; ; relative_block++) {
			if (relative_block == last) {
				clear_buffer_mapped(map_bh);
				break;
			}
			if (page_block == blocks_per_page)
				break;
			blocks[page_block] = map_bh->b_blocknr + map_offset +
						relative_block;
			page_block++;
			block_in_file++;
		}
		bdev = map_bh->b_bdev;
	}

	/*
	 * Then do more get_blocks calls until we are done with this folio.
	 */
	map_bh->b_folio = folio;
	while (page_block < blocks_per_page) {
		map_bh->b_state = 0;
		map_bh->b_size = 0;

		if (block_in_file < last_block) {
			map_bh->b_size = (last_block-block_in_file) << blkbits;
			if (args->get_block(inode, block_in_file, map_bh, 0))
				goto confused;
			args->first_logical_block = block_in_file;
		}

		if (!buffer_mapped(map_bh)) {
			fully_mapped = 0;
			if (first_hole == blocks_per_page)
				first_hole = page_block;
			page_block++;
			block_in_file++;
			continue;
		}

		/* some filesystems will copy data into the page during
		 * the get_block call, in which case we don't want to
		 * read it again.  map_buffer_to_folio copies the data
		 * we just collected from get_block into the folio's buffers
		 * so read_folio doesn't have to repeat the get_block call
		 */
		if (buffer_uptodate(map_bh)) {
			map_buffer_to_folio(folio, map_bh, page_block);
			goto confused;
		}
	
		if (first_hole != blocks_per_page)
			goto confused;		/* hole -> non-hole */

		/* Contiguous blocks? */
		if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
			goto confused;
		nblocks = map_bh->b_size >> blkbits;
		for (relative_block = 0; ; relative_block++) {
			if (relative_block == nblocks) {
				clear_buffer_mapped(map_bh);
				break;
			} else if (page_block == blocks_per_page)
				break;
			blocks[page_block] = map_bh->b_blocknr+relative_block;
			page_block++;
			block_in_file++;
		}
		bdev = map_bh->b_bdev;
	}

	if (first_hole != blocks_per_page) {
		folio_zero_segment(folio, first_hole << blkbits, PAGE_SIZE);
		if (first_hole == 0) {
			folio_mark_uptodate(folio);
			folio_unlock(folio);
			goto out;
		}
	} else if (fully_mapped) {
		folio_set_mappedtodisk(folio);
	}

	/*
	 * This folio will go to BIO.  Do we need to send this BIO off first?
	 */
	if (args->bio && (args->last_block_in_bio != blocks[0] - 1))
		args->bio = mpage_bio_submit(args->bio);

alloc_new:
	if (args->bio == NULL) {
		args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), opf,
				      gfp);
		if (args->bio == NULL)
			goto confused;
		args->bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
	}

	length = first_hole << blkbits;
	if (!bio_add_folio(args->bio, folio, length, 0)) {
		args->bio = mpage_bio_submit(args->bio);
		goto alloc_new;
	}

	relative_block = block_in_file - args->first_logical_block;
	nblocks = map_bh->b_size >> blkbits;
	if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
	    (first_hole != blocks_per_page))
		args->bio = mpage_bio_submit(args->bio);
	else
		args->last_block_in_bio = blocks[blocks_per_page - 1];
out:
	return args->bio;

confused:
	if (args->bio)
		args->bio = mpage_bio_submit(args->bio);
	if (!folio_test_uptodate(folio))
		block_read_full_folio(folio, args->get_block);
	else
		folio_unlock(folio);
	goto out;
}

/**
 * mpage_readahead - start reads against pages
 * @rac: Describes which pages to read.
 * @get_block: The filesystem's block mapper function.
 *
 * This function walks the pages and the blocks within each page, building and
 * emitting large BIOs.
 *
 * If anything unusual happens, such as:
 *
 * - encountering a page which has buffers
 * - encountering a page which has a non-hole after a hole
 * - encountering a page with non-contiguous blocks
 *
 * then this code just gives up and calls the buffer_head-based read function.
 * It does handle a page which has holes at the end - that is a common case:
 * the end-of-file on blocksize < PAGE_SIZE setups.
 *
 * BH_Boundary explanation:
 *
 * There is a problem.  The mpage read code assembles several pages, gets all
 * their disk mappings, and then submits them all.  That's fine, but obtaining
 * the disk mappings may require I/O.  Reads of indirect blocks, for example.
 *
 * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
 * submitted in the following order:
 *
 * 	12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
 *
 * because the indirect block has to be read to get the mappings of blocks
 * 13,14,15,16.  Obviously, this impacts performance.
 *
 * So what we do it to allow the filesystem's get_block() function to set
 * BH_Boundary when it maps block 11.  BH_Boundary says: mapping of the block
 * after this one will require I/O against a block which is probably close to
 * this one.  So you should push what I/O you have currently accumulated.
 *
 * This all causes the disk requests to be issued in the correct order.
 */
void mpage_readahead(struct readahead_control *rac, get_block_t get_block)
{
	struct folio *folio;
	struct mpage_readpage_args args = {
		.get_block = get_block,
		.is_readahead = true,
	};

	while ((folio = readahead_folio(rac))) {
		prefetchw(&folio->flags);
		args.folio = folio;
		args.nr_pages = readahead_count(rac);
		args.bio = do_mpage_readpage(&args);
	}
	if (args.bio)
		mpage_bio_submit(args.bio);
}
EXPORT_SYMBOL(mpage_readahead);

/*
 * This isn't called much at all
 */
int mpage_read_folio(struct folio *folio, get_block_t get_block)
{
	struct mpage_readpage_args args = {
		.folio = folio,
		.nr_pages = 1,
		.get_block = get_block,
	};

	args.bio = do_mpage_readpage(&args);
	if (args.bio)
		mpage_bio_submit(args.bio);
	return 0;
}
EXPORT_SYMBOL(mpage_read_folio);

/*
 * Writing is not so simple.
 *
 * If the page has buffers then they will be used for obtaining the disk
 * mapping.  We only support pages which are fully mapped-and-dirty, with a
 * special case for pages which are unmapped at the end: end-of-file.
 *
 * If the page has no buffers (preferred) then the page is mapped here.
 *
 * If all blocks are found to be contiguous then the page can go into the
 * BIO.  Otherwise fall back to the mapping's writepage().
 * 
 * FIXME: This code wants an estimate of how many pages are still to be
 * written, so it can intelligently allocate a suitably-sized BIO.  For now,
 * just allocate full-size (16-page) BIOs.
 */

struct mpage_data {
	struct bio *bio;
	sector_t last_block_in_bio;
	get_block_t *get_block;
};

/*
 * We have our BIO, so we can now mark the buffers clean.  Make
 * sure to only clean buffers which we know we'll be writing.
 */
static void clean_buffers(struct page *page, unsigned first_unmapped)
{
	unsigned buffer_counter = 0;
	struct buffer_head *bh, *head;
	if (!page_has_buffers(page))
		return;
	head = page_buffers(page);
	bh = head;

	do {
		if (buffer_counter++ == first_unmapped)
			break;
		clear_buffer_dirty(bh);
		bh = bh->b_this_page;
	} while (bh != head);

	/*
	 * we cannot drop the bh if the page is not uptodate or a concurrent
	 * read_folio would fail to serialize with the bh and it would read from
	 * disk before we reach the platter.
	 */
	if (buffer_heads_over_limit && PageUptodate(page))
		try_to_free_buffers(page_folio(page));
}

/*
 * For situations where we want to clean all buffers attached to a page.
 * We don't need to calculate how many buffers are attached to the page,
 * we just need to specify a number larger than the maximum number of buffers.
 */
void clean_page_buffers(struct page *page)
{
	clean_buffers(page, ~0U);
}

static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
		      void *data)
{
	struct mpage_data *mpd = data;
	struct bio *bio = mpd->bio;
	struct address_space *mapping = folio->mapping;
	struct inode *inode = mapping->host;
	const unsigned blkbits = inode->i_blkbits;
	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
	sector_t last_block;
	sector_t block_in_file;
	sector_t blocks[MAX_BUF_PER_PAGE];
	unsigned page_block;
	unsigned first_unmapped = blocks_per_page;
	struct block_device *bdev = NULL;
	int boundary = 0;
	sector_t boundary_block = 0;
	struct block_device *boundary_bdev = NULL;
	size_t length;
	struct buffer_head map_bh;
	loff_t i_size = i_size_read(inode);
	int ret = 0;
	struct buffer_head *head = folio_buffers(folio);

	if (head) {
		struct buffer_head *bh = head;

		/* If they're all mapped and dirty, do it */
		page_block = 0;
		do {
			BUG_ON(buffer_locked(bh));
			if (!buffer_mapped(bh)) {
				/*
				 * unmapped dirty buffers are created by
				 * block_dirty_folio -> mmapped data
				 */
				if (buffer_dirty(bh))
					goto confused;
				if (first_unmapped == blocks_per_page)
					first_unmapped = page_block;
				continue;
			}

			if (first_unmapped != blocks_per_page)
				goto confused;	/* hole -> non-hole */

			if (!buffer_dirty(bh) || !buffer_uptodate(bh))
				goto confused;
			if (page_block) {
				if (bh->b_blocknr != blocks[page_block-1] + 1)
					goto confused;
			}
			blocks[page_block++] = bh->b_blocknr;
			boundary = buffer_boundary(bh);
			if (boundary) {
				boundary_block = bh->b_blocknr;
				boundary_bdev = bh->b_bdev;
			}
			bdev = bh->b_bdev;
		} while ((bh = bh->b_this_page) != head);

		if (first_unmapped)
			goto page_is_mapped;

		/*
		 * Page has buffers, but they are all unmapped. The page was
		 * created by pagein or read over a hole which was handled by
		 * block_read_full_folio().  If this address_space is also
		 * using mpage_readahead then this can rarely happen.
		 */
		goto confused;
	}

	/*
	 * The page has no buffers: map it to disk
	 */
	BUG_ON(!folio_test_uptodate(folio));
	block_in_file = (sector_t)folio->index << (PAGE_SHIFT - blkbits);
	/*
	 * Whole page beyond EOF? Skip allocating blocks to avoid leaking
	 * space.
	 */
	if (block_in_file >= (i_size + (1 << blkbits) - 1) >> blkbits)
		goto page_is_mapped;
	last_block = (i_size - 1) >> blkbits;
	map_bh.b_folio = folio;
	for (page_block = 0; page_block < blocks_per_page; ) {

		map_bh.b_state = 0;
		map_bh.b_size = 1 << blkbits;
		if (mpd->get_block(inode, block_in_file, &map_bh, 1))
			goto confused;
		if (!buffer_mapped(&map_bh))
			goto confused;
		if (buffer_new(&map_bh))
			clean_bdev_bh_alias(&map_bh);
		if (buffer_boundary(&map_bh)) {
			boundary_block = map_bh.b_blocknr;
			boundary_bdev = map_bh.b_bdev;
		}
		if (page_block) {
			if (map_bh.b_blocknr != blocks[page_block-1] + 1)
				goto confused;
		}
		blocks[page_block++] = map_bh.b_blocknr;
		boundary = buffer_boundary(&map_bh);
		bdev = map_bh.b_bdev;
		if (block_in_file == last_block)
			break;
		block_in_file++;
	}
	BUG_ON(page_block == 0);

	first_unmapped = page_block;

page_is_mapped:
	/* Don't bother writing beyond EOF, truncate will discard the folio */
	if (folio_pos(folio) >= i_size)
		goto confused;
	length = folio_size(folio);
	if (folio_pos(folio) + length > i_size) {
		/*
		 * The page straddles i_size.  It must be zeroed out on each
		 * and every writepage invocation because it may be mmapped.
		 * "A file is mapped in multiples of the page size.  For a file
		 * that is not a multiple of the page size, the remaining memory
		 * is zeroed when mapped, and writes to that region are not
		 * written out to the file."
		 */
		length = i_size - folio_pos(folio);
		folio_zero_segment(folio, length, folio_size(folio));
	}

	/*
	 * This page will go to BIO.  Do we need to send this BIO off first?
	 */
	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
		bio = mpage_bio_submit(bio);

alloc_new:
	if (bio == NULL) {
		bio = bio_alloc(bdev, BIO_MAX_VECS,
				REQ_OP_WRITE | wbc_to_write_flags(wbc),
				GFP_NOFS);
		bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
		wbc_init_bio(wbc, bio);
	}

	/*
	 * Must try to add the page before marking the buffer clean or
	 * the confused fail path above (OOM) will be very confused when
	 * it finds all bh marked clean (i.e. it will not write anything)
	 */
	wbc_account_cgroup_owner(wbc, &folio->page, folio_size(folio));
	length = first_unmapped << blkbits;
	if (!bio_add_folio(bio, folio, length, 0)) {
		bio = mpage_bio_submit(bio);
		goto alloc_new;
	}

	clean_buffers(&folio->page, first_unmapped);

	BUG_ON(folio_test_writeback(folio));
	folio_start_writeback(folio);
	folio_unlock(folio);
	if (boundary || (first_unmapped != blocks_per_page)) {
		bio = mpage_bio_submit(bio);
		if (boundary_block) {
			write_boundary_block(boundary_bdev,
					boundary_block, 1 << blkbits);
		}
	} else {
		mpd->last_block_in_bio = blocks[blocks_per_page - 1];
	}
	goto out;

confused:
	if (bio)
		bio = mpage_bio_submit(bio);

	/*
	 * The caller has a ref on the inode, so *mapping is stable
	 */
	ret = block_write_full_page(&folio->page, mpd->get_block, wbc);
	mapping_set_error(mapping, ret);
out:
	mpd->bio = bio;
	return ret;
}

/**
 * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 * @get_block: the filesystem's block mapper function.
 *
 * This is a library function, which implements the writepages()
 * address_space_operation.
 */
int
mpage_writepages(struct address_space *mapping,
		struct writeback_control *wbc, get_block_t get_block)
{
	struct mpage_data mpd = {
		.get_block	= get_block,
	};
	struct blk_plug plug;
	int ret;

	blk_start_plug(&plug);
	ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
	if (mpd.bio)
		mpage_bio_submit(mpd.bio);
	blk_finish_plug(&plug);
	return ret;
}
EXPORT_SYMBOL(mpage_writepages);