summaryrefslogtreecommitdiff
path: root/fs/ext4/fsync.c
blob: b40d3b29f7e5c5b88694794c28198afc2f951aa4 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/fsync.c
 *
 *  Copyright (C) 1993  Stephen Tweedie (sct@redhat.com)
 *  from
 *  Copyright (C) 1992  Remy Card (card@masi.ibp.fr)
 *                      Laboratoire MASI - Institut Blaise Pascal
 *                      Universite Pierre et Marie Curie (Paris VI)
 *  from
 *  linux/fs/minix/truncate.c   Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  ext4fs fsync primitive
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 *
 *  Removed unnecessary code duplication for little endian machines
 *  and excessive __inline__s.
 *        Andi Kleen, 1997
 *
 * Major simplications and cleanup - we only need to do the metadata, because
 * we can depend on generic_block_fdatasync() to sync the data blocks.
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>

#include "ext4.h"
#include "ext4_jbd2.h"

#include <trace/events/ext4.h>

/*
 * If we're not journaling and this is a just-created file, we have to
 * sync our parent directory (if it was freshly created) since
 * otherwise it will only be written by writeback, leaving a huge
 * window during which a crash may lose the file.  This may apply for
 * the parent directory's parent as well, and so on recursively, if
 * they are also freshly created.
 */
static int ext4_sync_parent(struct inode *inode)
{
	struct dentry *dentry, *next;
	int ret = 0;

	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
		return 0;
	dentry = d_find_any_alias(inode);
	if (!dentry)
		return 0;
	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);

		next = dget_parent(dentry);
		dput(dentry);
		dentry = next;
		inode = dentry->d_inode;

		/*
		 * The directory inode may have gone through rmdir by now. But
		 * the inode itself and its blocks are still allocated (we hold
		 * a reference to the inode via its dentry), so it didn't go
		 * through ext4_evict_inode()) and so we are safe to flush
		 * metadata blocks and the inode.
		 */
		ret = sync_mapping_buffers(inode->i_mapping);
		if (ret)
			break;
		ret = sync_inode_metadata(inode, 1);
		if (ret)
			break;
	}
	dput(dentry);
	return ret;
}

static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
				int datasync, bool *needs_barrier)
{
	struct inode *inode = file->f_inode;
	int ret;

	ret = generic_buffers_fsync_noflush(file, start, end, datasync);
	if (!ret)
		ret = ext4_sync_parent(inode);
	if (test_opt(inode->i_sb, BARRIER))
		*needs_barrier = true;

	return ret;
}

static int ext4_fsync_journal(struct inode *inode, bool datasync,
			     bool *needs_barrier)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
	tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;

	/*
	 * Fastcommit does not really support fsync on directories or other
	 * special files. Force a full commit.
	 */
	if (!S_ISREG(inode->i_mode))
		return ext4_force_commit(inode->i_sb);

	if (journal->j_flags & JBD2_BARRIER &&
	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
		*needs_barrier = true;

	return ext4_fc_commit(journal, commit_tid);
}

/*
 * akpm: A new design for ext4_sync_file().
 *
 * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
 * There cannot be a transaction open by this task.
 * Another task could have dirtied this inode.  Its data can be in any
 * state in the journalling system.
 *
 * What we do is just kick off a commit and wait on it.  This will snapshot the
 * inode to disk.
 */
int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	int ret = 0, err;
	bool needs_barrier = false;
	struct inode *inode = file->f_mapping->host;

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

	ASSERT(ext4_journal_current_handle() == NULL);

	trace_ext4_sync_file_enter(file, datasync);

	if (sb_rdonly(inode->i_sb)) {
		/* Make sure that we read updated s_ext4_flags value */
		smp_rmb();
		if (ext4_forced_shutdown(inode->i_sb))
			ret = -EROFS;
		goto out;
	}

	if (!EXT4_SB(inode->i_sb)->s_journal) {
		ret = ext4_fsync_nojournal(file, start, end, datasync,
					   &needs_barrier);
		if (needs_barrier)
			goto issue_flush;
		goto out;
	}

	ret = file_write_and_wait_range(file, start, end);
	if (ret)
		goto out;

	/*
	 *  The caller's filemap_fdatawrite()/wait will sync the data.
	 *  Metadata is in the journal, we wait for proper transaction to
	 *  commit here.
	 */
	ret = ext4_fsync_journal(inode, datasync, &needs_barrier);

issue_flush:
	if (needs_barrier) {
		err = blkdev_issue_flush(inode->i_sb->s_bdev);
		if (!ret)
			ret = err;
	}
out:
	err = file_check_and_advance_wb_err(file);
	if (ret == 0)
		ret = err;
	trace_ext4_sync_file_exit(inode, ret);
	return ret;
}