summaryrefslogtreecommitdiffstats
path: root/fs/ext4/fsync.c
blob: 40f345201737ec9a914dcaaf9e2dcd210a6a7314 (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
/*
 *  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/jbd2.h>
#include <linux/blkdev.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 void ext4_sync_parent(struct inode *inode)
{
	struct dentry *dentry = NULL;

	while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
		dentry = list_entry(inode->i_dentry.next,
				    struct dentry, d_alias);
		if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
			break;
		inode = dentry->d_parent->d_inode;
		sync_mapping_buffers(inode->i_mapping);
	}
}

/*
 * 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.
 *
 * i_mutex lock is held when entering and exiting this function
 */

int ext4_sync_file(struct file *file, int datasync)
{
	struct inode *inode = file->f_mapping->host;
	struct ext4_inode_info *ei = EXT4_I(inode);
	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
	int ret;
	tid_t commit_tid;

	J_ASSERT(ext4_journal_current_handle() == NULL);

	trace_ext4_sync_file(file, datasync);

	if (inode->i_sb->s_flags & MS_RDONLY)
		return 0;

	ret = flush_completed_IO(inode);
	if (ret < 0)
		return ret;

	if (!journal) {
		ret = simple_fsync(file, datasync);
		if (!ret && !list_empty(&inode->i_dentry))
			ext4_sync_parent(inode);
		return ret;
	}

	/*
	 * data=writeback,ordered:
	 *  The caller's filemap_fdatawrite()/wait will sync the data.
	 *  Metadata is in the journal, we wait for proper transaction to
	 *  commit here.
	 *
	 * data=journal:
	 *  filemap_fdatawrite won't do anything (the buffers are clean).
	 *  ext4_force_commit will write the file data into the journal and
	 *  will wait on that.
	 *  filemap_fdatawait() will encounter a ton of newly-dirtied pages
	 *  (they were dirtied by commit).  But that's OK - the blocks are
	 *  safe in-journal, which is all fsync() needs to ensure.
	 */
	if (ext4_should_journal_data(inode))
		return ext4_force_commit(inode->i_sb);

	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
	if (jbd2_log_start_commit(journal, commit_tid)) {
		/*
		 * When the journal is on a different device than the
		 * fs data disk, we need to issue the barrier in
		 * writeback mode.  (In ordered mode, the jbd2 layer
		 * will take care of issuing the barrier.  In
		 * data=journal, all of the data blocks are written to
		 * the journal device.)
		 */
		if (ext4_should_writeback_data(inode) &&
		    (journal->j_fs_dev != journal->j_dev) &&
		    (journal->j_flags & JBD2_BARRIER))
			blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
					NULL, BLKDEV_IFL_WAIT);
		ret = jbd2_log_wait_commit(journal, commit_tid);
	} else if (journal->j_flags & JBD2_BARRIER)
		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
			BLKDEV_IFL_WAIT);
	return ret;
}
OpenPOWER on IntegriCloud