summaryrefslogtreecommitdiffstats
path: root/fs/ext4/fsync.c
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2009-12-08 23:51:10 -0500
committerTheodore Ts'o <tytso@mit.edu>2009-12-08 23:51:10 -0500
commitb436b9bef84de6893e86346d8fbf7104bc520645 (patch)
tree50fb9ae167bcd622e9adf47646bcf3b4c7dd111d /fs/ext4/fsync.c
parent194074acacebc169ded90a4657193f5180015051 (diff)
downloadlinux-b436b9bef84de6893e86346d8fbf7104bc520645.tar.gz
linux-b436b9bef84de6893e86346d8fbf7104bc520645.tar.bz2
linux-b436b9bef84de6893e86346d8fbf7104bc520645.zip
ext4: Wait for proper transaction commit on fsync
We cannot rely on buffer dirty bits during fsync because pdflush can come before fsync is called and clear dirty bits without forcing a transaction commit. What we do is that we track which transaction has last changed the inode and which transaction last changed allocation and force it to disk on fsync. Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/fsync.c')
-rw-r--r--fs/ext4/fsync.c46
1 files changed, 17 insertions, 29 deletions
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a3c25076aef1..0b22497d92e1 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -51,25 +51,30 @@
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
- int err, ret = 0;
+ int ret;
+ tid_t commit_tid;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
+ if (inode->i_sb->s_flags & MS_RDONLY)
+ return 0;
+
ret = flush_aio_dio_completed_IO(inode);
if (ret < 0)
return ret;
+
+ if (!journal)
+ return simple_fsync(file, dentry, datasync);
+
/*
- * data=writeback:
+ * data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
- * sync_inode() will sync the metadata
- *
- * data=ordered:
- * The caller's filemap_fdatawrite() will write the data and
- * sync_inode() will write the inode if it is dirty. Then the caller's
- * filemap_fdatawait() will wait on the pages.
+ * 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).
@@ -82,27 +87,10 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
- if (!journal)
- ret = sync_mapping_buffers(inode->i_mapping);
-
- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
- goto out;
-
- /*
- * The VFS has written the file data. If the inode is unaltered
- * then we need not start a commit.
- */
- if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = 0, /* sys_fsync did this */
- };
- err = sync_inode(inode, &wbc);
- if (ret == 0)
- ret = err;
- }
-out:
- if (journal && (journal->j_flags & JBD2_BARRIER))
+ commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+ if (jbd2_log_start_commit(journal, commit_tid))
+ jbd2_log_wait_commit(journal, commit_tid);
+ else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}