![Theodore Ts'o](/assets/img/avatar_default.png)
This is a bit complicated because we are trying to optimize when we send barriers to the fs data disk. We could just throw in an extra barrier to the data disk whenever we send a barrier to the journal disk, but that's not always strictly necessary. We only need to send a barrier during a commit when there are data blocks which are must be written out due to an inode written in ordered mode, or if fsync() depends on the commit to force data blocks to disk. Finally, before we drop transactions from the beginning of the journal during a checkpoint operation, we need to guarantee that any blocks that were flushed out to the data disk are firmly on the rust platter before we drop the transaction from the journal. Thanks to Oleg Drokin for pointing out this flaw in ext3/ext4. Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
109 lines
3.3 KiB
C
109 lines
3.3 KiB
C
/*
|
|
* 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>
|
|
|
|
/*
|
|
* 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, 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 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,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, NULL);
|
|
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;
|
|
}
|