summaryrefslogtreecommitdiffstats
path: root/fs/ext4/file.c
blob: 2c5baa5e8291165e07d5609b650c38c13eda587f (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  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/iomap.h>
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/mman.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"

#ifdef CONFIG_FS_DAX
static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	if (!inode_trylock_shared(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock_shared(inode);
	}
	/*
	 * Recheck under inode lock - at this point we are sure it cannot
	 * change anymore
	 */
	if (!IS_DAX(inode)) {
		inode_unlock_shared(inode);
		/* Fallback to buffered IO in case we cannot support DAX */
		return generic_file_read_iter(iocb, to);
	}
	ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops);
	inode_unlock_shared(inode);

	file_accessed(iocb->ki_filp);
	return ret;
}
#endif

static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
		return -EIO;

	if (!iov_iter_count(to))
		return 0; /* skip atime */

#ifdef CONFIG_FS_DAX
	if (IS_DAX(file_inode(iocb->ki_filp)))
		return ext4_dax_read_iter(iocb, to);
#endif
	return generic_file_read_iter(iocb, to);
}

/*
 * 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;
}

static 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, struct iov_iter *from, loff_t pos)
{
	struct super_block *sb = inode->i_sb;
	int blockmask = sb->s_blocksize - 1;

	if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
		return 0;

	if ((pos | iov_iter_alignment(from)) & blockmask)
		return 1;

	return 0;
}

/* Is IO overwriting allocated and initialized blocks? */
static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
	struct ext4_map_blocks map;
	unsigned int blkbits = inode->i_blkbits;
	int err, blklen;

	if (pos + len > i_size_read(inode))
		return false;

	map.m_lblk = pos >> blkbits;
	map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits);
	blklen = map.m_len;

	err = ext4_map_blocks(NULL, inode, &map, 0);
	/*
	 * 'err==len' means that all of the blocks have been preallocated,
	 * regardless of whether they have been initialized or not. To exclude
	 * unwritten extents, we need to check m_flags.
	 */
	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
}

static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	ret = generic_write_checks(iocb, from);
	if (ret <= 0)
		return 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);

		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes)
			return -EFBIG;
		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
	}
	return iov_iter_count(from);
}

#ifdef CONFIG_FS_DAX
static ssize_t
ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	ssize_t ret;

	if (!inode_trylock(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock(inode);
	}
	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;
	ret = file_remove_privs(iocb->ki_filp);
	if (ret)
		goto out;
	ret = file_update_time(iocb->ki_filp);
	if (ret)
		goto out;

	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
out:
	inode_unlock(inode);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	return ret;
}
#endif

static ssize_t
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	int o_direct = iocb->ki_flags & IOCB_DIRECT;
	int unaligned_aio = 0;
	int overwrite = 0;
	ssize_t ret;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

#ifdef CONFIG_FS_DAX
	if (IS_DAX(inode))
		return ext4_dax_write_iter(iocb, from);
#endif
	if (!o_direct && (iocb->ki_flags & IOCB_NOWAIT))
		return -EOPNOTSUPP;

	if (!inode_trylock(inode)) {
		if (iocb->ki_flags & IOCB_NOWAIT)
			return -EAGAIN;
		inode_lock(inode);
	}

	ret = ext4_write_checks(iocb, from);
	if (ret <= 0)
		goto out;

	/*
	 * Unaligned direct AIO must be serialized among each other as zeroing
	 * of partial blocks of two competing unaligned AIOs can result in data
	 * corruption.
	 */
	if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
	    !is_sync_kiocb(iocb) &&
	    ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
		unaligned_aio = 1;
		ext4_unwritten_wait(inode);
	}

	iocb->private = &overwrite;
	/* Check whether we do a DIO overwrite or not */
	if (o_direct && !unaligned_aio) {
		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
			if (ext4_should_dioread_nolock(inode))
				overwrite = 1;
		} else if (iocb->ki_flags & IOCB_NOWAIT) {
			ret = -EAGAIN;
			goto out;
		}
	}

	ret = __generic_file_write_iter(iocb, from);
	/*
	 * Unaligned direct AIO must be the only IO in flight. Otherwise
	 * overlapping aligned IO after unaligned might result in data
	 * corruption.
	 */
	if (ret == -EIOCBQUEUED && unaligned_aio)
		ext4_unwritten_wait(inode);
	inode_unlock(inode);

	if (ret > 0)
		ret = generic_write_sync(iocb, ret);

	return ret;

out:
	inode_unlock(inode);
	return ret;
}

#ifdef CONFIG_FS_DAX
static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
		enum page_entry_size pe_size)
{
	int error = 0;
	vm_fault_t result;
	int retries = 0;
	handle_t *handle = NULL;
	struct inode *inode = file_inode(vmf->vma->vm_file);
	struct super_block *sb = inode->i_sb;

	/*
	 * We have to distinguish real writes from writes which will result in a
	 * COW page; COW writes should *not* poke the journal (the file will not
	 * be changed). Doing so would cause unintended failures when mounted
	 * read-only.
	 *
	 * We check for VM_SHARED rather than vmf->cow_page since the latter is
	 * unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for
	 * other sizes, dax_iomap_fault will handle splitting / fallback so that
	 * we eventually come back with a COW page.
	 */
	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
		(vmf->vma->vm_flags & VM_SHARED);
	pfn_t pfn;

	if (write) {
		sb_start_pagefault(sb);
		file_update_time(vmf->vma->vm_file);
		down_read(&EXT4_I(inode)->i_mmap_sem);
retry:
		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
					       EXT4_DATA_TRANS_BLOCKS(sb));
		if (IS_ERR(handle)) {
			up_read(&EXT4_I(inode)->i_mmap_sem);
			sb_end_pagefault(sb);
			return VM_FAULT_SIGBUS;
		}
	} else {
		down_read(&EXT4_I(inode)->i_mmap_sem);
	}
	result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
	if (write) {
		ext4_journal_stop(handle);

		if ((result & VM_FAULT_ERROR) && error == -ENOSPC &&
		    ext4_should_retry_alloc(sb, &retries))
			goto retry;
		/* Handling synchronous page fault? */
		if (result & VM_FAULT_NEEDDSYNC)
			result = dax_finish_sync_fault(vmf, pe_size, pfn);
		up_read(&EXT4_I(inode)->i_mmap_sem);
		sb_end_pagefault(sb);
	} else {
		up_read(&EXT4_I(inode)->i_mmap_sem);
	}

	return result;
}

static vm_fault_t ext4_dax_fault(struct vm_fault *vmf)
{
	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}

static const struct vm_operations_struct ext4_dax_vm_ops = {
	.fault		= ext4_dax_fault,
	.huge_fault	= ext4_dax_huge_fault,
	.page_mkwrite	= ext4_dax_fault,
	.pfn_mkwrite	= ext4_dax_fault,
};
#else
#define ext4_dax_vm_ops	ext4_file_vm_ops
#endif

static const struct vm_operations_struct ext4_file_vm_ops = {
	.fault		= ext4_filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite   = ext4_page_mkwrite,
};

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

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	/*
	 * We don't support synchronous mappings for non-DAX files. At least
	 * until someone comes with a sensible use case.
	 */
	if (!IS_DAX(file_inode(file)) && (vma->vm_flags & VM_SYNC))
		return -EOPNOTSUPP;

	file_accessed(file);
	if (IS_DAX(file_inode(file))) {
		vma->vm_ops = &ext4_dax_vm_ops;
		vma->vm_flags |= VM_HUGEPAGE;
	} else {
		vma->vm_ops = &ext4_file_vm_ops;
	}
	return 0;
}

static int ext4_sample_last_mounted(struct super_block *sb,
				    struct vfsmount *mnt)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct path path;
	char buf[64], *cp;
	handle_t *handle;
	int err;

	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
		return 0;

	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
		return 0;

	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));
	err = 0;
	if (IS_ERR(cp))
		goto out;

	handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
	err = PTR_ERR(handle);
	if (IS_ERR(handle))
		goto out;
	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
	if (err)
		goto out_journal;
	strlcpy(sbi->s_es->s_last_mounted, cp,
		sizeof(sbi->s_es->s_last_mounted));
	ext4_handle_dirty_super(handle, sb);
out_journal:
	ext4_journal_stop(handle);
out:
	sb_end_intwrite(sb);
	return err;
}

static int ext4_file_open(struct inode * inode, struct file * filp)
{
	int ret;

	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
		return -EIO;

	ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt);
	if (ret)
		return ret;

	ret = fscrypt_file_open(inode, filp);
	if (ret)
		return ret;

	/*
	 * Set up the jbd2_inode if we are opening the inode for
	 * writing and the journal is present
	 */
	if (filp->f_mode & FMODE_WRITE) {
		ret = ext4_inode_attach_jinode(inode);
		if (ret < 0)
			return ret;
	}

	filp->f_mode |= FMODE_NOWAIT;
	return dquot_file_open(inode, filp);
}

/*
 * 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 whence)
{
	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 (whence) {
	default:
		return generic_file_llseek_size(file, offset, whence,
						maxbytes, i_size_read(inode));
	case SEEK_HOLE:
		inode_lock_shared(inode);
		offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops);
		inode_unlock_shared(inode);
		break;
	case SEEK_DATA:
		inode_lock_shared(inode);
		offset = iomap_seek_data(inode, offset, &ext4_iomap_ops);
		inode_unlock_shared(inode);
		break;
	}

	if (offset < 0)
		return offset;
	return vfs_setpos(file, offset, maxbytes);
}

const struct file_operations ext4_file_operations = {
	.llseek		= ext4_llseek,
	.read_iter	= ext4_file_read_iter,
	.write_iter	= ext4_file_write_iter,
	.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext4_compat_ioctl,
#endif
	.mmap		= ext4_file_mmap,
	.mmap_supported_flags = MAP_SYNC,
	.open		= ext4_file_open,
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
	.get_unmapped_area = thp_get_unmapped_area,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= ext4_fallocate,
};

const struct inode_operations ext4_file_inode_operations = {
	.setattr	= ext4_setattr,
	.getattr	= ext4_file_getattr,
	.listxattr	= ext4_listxattr,
	.get_acl	= ext4_get_acl,
	.set_acl	= ext4_set_acl,
	.fiemap		= ext4_fiemap,
};