summaryrefslogtreecommitdiffstats
path: root/fs/ext4/file.c
blob: b64a60bf105a0c884c104b251ba59a6e0ef93d1b (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
660
661
662
663
664
665
666
/*
 *  linux/fs/ext4/file.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/file.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  ext4 fs regular file handling primitives
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *	(jj@sunsite.ms.mff.cuni.cz)
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"

/*
 * Called when an inode is released. Note that this is different
 * from ext4_file_open: open gets called at every open, but release
 * gets called only when /all/ the files are closed.
 */
static int ext4_release_file(struct inode *inode, struct file *filp)
{
	if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
		ext4_alloc_da_blocks(inode);
		ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
	}
	/* if we are the last writer on the inode, drop the block reservation */
	if ((filp->f_mode & FMODE_WRITE) &&
			(atomic_read(&inode->i_writecount) == 1) &&
		        !EXT4_I(inode)->i_reserved_data_blocks)
	{
		down_write(&EXT4_I(inode)->i_data_sem);
		ext4_discard_preallocations(inode);
		up_write(&EXT4_I(inode)->i_data_sem);
	}
	if (is_dx(inode) && filp->private_data)
		ext4_htree_free_dir_info(filp->private_data);

	return 0;
}

void ext4_unwritten_wait(struct inode *inode)
{
	wait_queue_head_t *wq = ext4_ioend_wq(inode);

	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
}

/*
 * This tests whether the IO in question is block-aligned or not.
 * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
 * are converted to written only after the IO is complete.  Until they are
 * mapped, these blocks appear as holes, so dio_zero_block() will assume that
 * it needs to zero out portions of the start and/or end block.  If 2 AIO
 * threads are at work on the same unwritten block, they must be synchronized
 * or one thread will zero the other's data, causing corruption.
 */
static int
ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
		   unsigned long nr_segs, loff_t pos)
{
	struct super_block *sb = inode->i_sb;
	int blockmask = sb->s_blocksize - 1;
	size_t count = iov_length(iov, nr_segs);
	loff_t final_size = pos + count;

	if (pos >= inode->i_size)
		return 0;

	if ((pos & blockmask) || (final_size & blockmask))
		return 1;

	return 0;
}

static ssize_t
ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
		    unsigned long nr_segs, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	struct blk_plug plug;
	int unaligned_aio = 0;
	ssize_t ret;
	int overwrite = 0;
	size_t length = iov_length(iov, nr_segs);

	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
	    !is_sync_kiocb(iocb))
		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);

	/* Unaligned direct AIO must be serialized; see comment above */
	if (unaligned_aio) {
		static unsigned long unaligned_warn_time;

		/* Warn about this once per day */
		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
			ext4_msg(inode->i_sb, KERN_WARNING,
				 "Unaligned AIO/DIO on inode %ld by %s; "
				 "performance will be poor.",
				 inode->i_ino, current->comm);
		mutex_lock(ext4_aio_mutex(inode));
		ext4_unwritten_wait(inode);
	}

	BUG_ON(iocb->ki_pos != pos);

	mutex_lock(&inode->i_mutex);
	blk_start_plug(&plug);

	iocb->private = &overwrite;

	/* check whether we do a DIO overwrite or not */
	if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
	    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
		struct ext4_map_blocks map;
		unsigned int blkbits = inode->i_blkbits;
		int err, len;

		map.m_lblk = pos >> blkbits;
		map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
			- map.m_lblk;
		len = map.m_len;

		err = ext4_map_blocks(NULL, inode, &map, 0);
		/*
		 * 'err==len' means that all of blocks has been preallocated no
		 * matter they are initialized or not.  For excluding
		 * uninitialized extents, we need to check m_flags.  There are
		 * two conditions that indicate for initialized extents.
		 * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
		 * 2) If we do a real lookup, non-flags are returned.
		 * So we should check these two conditions.
		 */
		if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
			overwrite = 1;
	}

	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
	mutex_unlock(&inode->i_mutex);

	if (ret > 0 || ret == -EIOCBQUEUED) {
		ssize_t err;

		err = generic_write_sync(file, pos, ret);
		if (err < 0 && ret > 0)
			ret = err;
	}
	blk_finish_plug(&plug);

	if (unaligned_aio)
		mutex_unlock(ext4_aio_mutex(inode));

	return ret;
}

static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
		unsigned long nr_segs, loff_t pos)
{
	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
	ssize_t ret;

	/*
	 * If we have encountered a bitmap-format file, the size limit
	 * is smaller than s_maxbytes, which is for extent-mapped files.
	 */

	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
		size_t length = iov_length(iov, nr_segs);

		if ((pos > sbi->s_bitmap_maxbytes ||
		    (pos == sbi->s_bitmap_maxbytes && length > 0)))
			return -EFBIG;

		if (pos + length > sbi->s_bitmap_maxbytes) {
			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
					      sbi->s_bitmap_maxbytes - pos);
		}
	}

	if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
		ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
	else
		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);

	return ret;
}

static const struct vm_operations_struct ext4_file_vm_ops = {
	.fault		= filemap_fault,
	.page_mkwrite   = ext4_page_mkwrite,
	.remap_pages	= generic_file_remap_pages,
};

static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct address_space *mapping = file->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;
	file_accessed(file);
	vma->vm_ops = &ext4_file_vm_ops;
	return 0;
}

static int ext4_file_open(struct inode * inode, struct file * filp)
{
	struct super_block *sb = inode->i_sb;
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	struct ext4_inode_info *ei = EXT4_I(inode);
	struct vfsmount *mnt = filp->f_path.mnt;
	struct path path;
	char buf[64], *cp;

	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
		     !(sb->s_flags & MS_RDONLY))) {
		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
		/*
		 * Sample where the filesystem has been mounted and
		 * store it in the superblock for sysadmin convenience
		 * when trying to sort through large numbers of block
		 * devices or filesystem images.
		 */
		memset(buf, 0, sizeof(buf));
		path.mnt = mnt;
		path.dentry = mnt->mnt_root;
		cp = d_path(&path, buf, sizeof(buf));
		if (!IS_ERR(cp)) {
			handle_t *handle;
			int err;

			handle = ext4_journal_start_sb(sb, 1);
			if (IS_ERR(handle))
				return PTR_ERR(handle);
			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
			if (err) {
				ext4_journal_stop(handle);
				return err;
			}
			strlcpy(sbi->s_es->s_last_mounted, cp,
				sizeof(sbi->s_es->s_last_mounted));
			ext4_handle_dirty_super(handle, sb);
			ext4_journal_stop(handle);
		}
	}
	/*
	 * Set up the jbd2_inode if we are opening the inode for
	 * writing and the journal is present
	 */
	if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
		struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);

		spin_lock(&inode->i_lock);
		if (!ei->jinode) {
			if (!jinode) {
				spin_unlock(&inode->i_lock);
				return -ENOMEM;
			}
			ei->jinode = jinode;
			jbd2_journal_init_jbd_inode(ei->jinode, inode);
			jinode = NULL;
		}
		spin_unlock(&inode->i_lock);
		if (unlikely(jinode != NULL))
			jbd2_free_inode(jinode);
	}
	return dquot_file_open(inode, filp);
}

/*
 * Here we use ext4_map_blocks() to get a block mapping for a extent-based
 * file rather than ext4_ext_walk_space() because we can introduce
 * SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same
 * function.  When extent status tree has been fully implemented, it will
 * track all extent status for a file and we can directly use it to
 * retrieve the offset for SEEK_DATA/SEEK_HOLE.
 */

/*
 * When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to
 * lookup page cache to check whether or not there has some data between
 * [startoff, endoff] because, if this range contains an unwritten extent,
 * we determine this extent as a data or a hole according to whether the
 * page cache has data or not.
 */
static int ext4_find_unwritten_pgoff(struct inode *inode,
				     int origin,
				     struct ext4_map_blocks *map,
				     loff_t *offset)
{
	struct pagevec pvec;
	unsigned int blkbits;
	pgoff_t index;
	pgoff_t end;
	loff_t endoff;
	loff_t startoff;
	loff_t lastoff;
	int found = 0;

	blkbits = inode->i_sb->s_blocksize_bits;
	startoff = *offset;
	lastoff = startoff;
	endoff = (map->m_lblk + map->m_len) << blkbits;

	index = startoff >> PAGE_CACHE_SHIFT;
	end = endoff >> PAGE_CACHE_SHIFT;

	pagevec_init(&pvec, 0);
	do {
		int i, num;
		unsigned long nr_pages;

		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
					  (pgoff_t)num);
		if (nr_pages == 0) {
			if (origin == SEEK_DATA)
				break;

			BUG_ON(origin != SEEK_HOLE);
			/*
			 * If this is the first time to go into the loop and
			 * offset is not beyond the end offset, it will be a
			 * hole at this offset
			 */
			if (lastoff == startoff || lastoff < endoff)
				found = 1;
			break;
		}

		/*
		 * If this is the first time to go into the loop and
		 * offset is smaller than the first page offset, it will be a
		 * hole at this offset.
		 */
		if (lastoff == startoff && origin == SEEK_HOLE &&
		    lastoff < page_offset(pvec.pages[0])) {
			found = 1;
			break;
		}

		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];
			struct buffer_head *bh, *head;

			/*
			 * If the current offset is not beyond the end of given
			 * range, it will be a hole.
			 */
			if (lastoff < endoff && origin == SEEK_HOLE &&
			    page->index > end) {
				found = 1;
				*offset = lastoff;
				goto out;
			}

			lock_page(page);

			if (unlikely(page->mapping != inode->i_mapping)) {
				unlock_page(page);
				continue;
			}

			if (!page_has_buffers(page)) {
				unlock_page(page);
				continue;
			}

			if (page_has_buffers(page)) {
				lastoff = page_offset(page);
				bh = head = page_buffers(page);
				do {
					if (buffer_uptodate(bh) ||
					    buffer_unwritten(bh)) {
						if (origin == SEEK_DATA)
							found = 1;
					} else {
						if (origin == SEEK_HOLE)
							found = 1;
					}
					if (found) {
						*offset = max_t(loff_t,
							startoff, lastoff);
						unlock_page(page);
						goto out;
					}
					lastoff += bh->b_size;
					bh = bh->b_this_page;
				} while (bh != head);
			}

			lastoff = page_offset(page) + PAGE_SIZE;
			unlock_page(page);
		}

		/*
		 * The no. of pages is less than our desired, that would be a
		 * hole in there.
		 */
		if (nr_pages < num && origin == SEEK_HOLE) {
			found = 1;
			*offset = lastoff;
			break;
		}

		index = pvec.pages[i - 1]->index + 1;
		pagevec_release(&pvec);
	} while (index <= end);

out:
	pagevec_release(&pvec);
	return found;
}

/*
 * ext4_seek_data() retrieves the offset for SEEK_DATA.
 */
static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
{
	struct inode *inode = file->f_mapping->host;
	struct ext4_map_blocks map;
	struct extent_status es;
	ext4_lblk_t start, last, end;
	loff_t dataoff, isize;
	int blkbits;
	int ret = 0;

	mutex_lock(&inode->i_mutex);

	isize = i_size_read(inode);
	if (offset >= isize) {
		mutex_unlock(&inode->i_mutex);
		return -ENXIO;
	}

	blkbits = inode->i_sb->s_blocksize_bits;
	start = offset >> blkbits;
	last = start;
	end = isize >> blkbits;
	dataoff = offset;

	do {
		map.m_lblk = last;
		map.m_len = end - last + 1;
		ret = ext4_map_blocks(NULL, inode, &map, 0);
		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
			if (last != start)
				dataoff = last << blkbits;
			break;
		}

		/*
		 * If there is a delay extent at this offset,
		 * it will be as a data.
		 */
		es.start = last;
		(void)ext4_es_find_extent(inode, &es);
		if (last >= es.start &&
		    last < es.start + es.len) {
			if (last != start)
				dataoff = last << blkbits;
			break;
		}

		/*
		 * If there is a unwritten extent at this offset,
		 * it will be as a data or a hole according to page
		 * cache that has data or not.
		 */
		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
			int unwritten;
			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
							      &map, &dataoff);
			if (unwritten)
				break;
		}

		last++;
		dataoff = last << blkbits;
	} while (last <= end);

	mutex_unlock(&inode->i_mutex);

	if (dataoff > isize)
		return -ENXIO;

	if (dataoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
		return -EINVAL;
	if (dataoff > maxsize)
		return -EINVAL;

	if (dataoff != file->f_pos) {
		file->f_pos = dataoff;
		file->f_version = 0;
	}

	return dataoff;
}

/*
 * ext4_seek_hole() retrieves the offset for SEEK_HOLE.
 */
static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
{
	struct inode *inode = file->f_mapping->host;
	struct ext4_map_blocks map;
	struct extent_status es;
	ext4_lblk_t start, last, end;
	loff_t holeoff, isize;
	int blkbits;
	int ret = 0;

	mutex_lock(&inode->i_mutex);

	isize = i_size_read(inode);
	if (offset >= isize) {
		mutex_unlock(&inode->i_mutex);
		return -ENXIO;
	}

	blkbits = inode->i_sb->s_blocksize_bits;
	start = offset >> blkbits;
	last = start;
	end = isize >> blkbits;
	holeoff = offset;

	do {
		map.m_lblk = last;
		map.m_len = end - last + 1;
		ret = ext4_map_blocks(NULL, inode, &map, 0);
		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
			last += ret;
			holeoff = last << blkbits;
			continue;
		}

		/*
		 * If there is a delay extent at this offset,
		 * we will skip this extent.
		 */
		es.start = last;
		(void)ext4_es_find_extent(inode, &es);
		if (last >= es.start &&
		    last < es.start + es.len) {
			last = es.start + es.len;
			holeoff = last << blkbits;
			continue;
		}

		/*
		 * If there is a unwritten extent at this offset,
		 * it will be as a data or a hole according to page
		 * cache that has data or not.
		 */
		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
			int unwritten;
			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
							      &map, &holeoff);
			if (!unwritten) {
				last += ret;
				holeoff = last << blkbits;
				continue;
			}
		}

		/* find a hole */
		break;
	} while (last <= end);

	mutex_unlock(&inode->i_mutex);

	if (holeoff > isize)
		holeoff = isize;

	if (holeoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
		return -EINVAL;
	if (holeoff > maxsize)
		return -EINVAL;

	if (holeoff != file->f_pos) {
		file->f_pos = holeoff;
		file->f_version = 0;
	}

	return holeoff;
}

/*
 * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
 * by calling generic_file_llseek_size() with the appropriate maxbytes
 * value for each.
 */
loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes;

	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
	else
		maxbytes = inode->i_sb->s_maxbytes;

	switch (origin) {
	case SEEK_SET:
	case SEEK_CUR:
	case SEEK_END:
		return generic_file_llseek_size(file, offset, origin,
						maxbytes, i_size_read(inode));
	case SEEK_DATA:
		return ext4_seek_data(file, offset, maxbytes);
	case SEEK_HOLE:
		return ext4_seek_hole(file, offset, maxbytes);
	}

	return -EINVAL;
}

const struct file_operations ext4_file_operations = {
	.llseek		= ext4_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= generic_file_aio_read,
	.aio_write	= ext4_file_write,
	.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext4_compat_ioctl,
#endif
	.mmap		= ext4_file_mmap,
	.open		= ext4_file_open,
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
	.fallocate	= ext4_fallocate,
};

const struct inode_operations ext4_file_inode_operations = {
	.setattr	= ext4_setattr,
	.getattr	= ext4_getattr,
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= ext4_listxattr,
	.removexattr	= generic_removexattr,
	.get_acl	= ext4_get_acl,
	.fiemap		= ext4_fiemap,
};