linux/fs/ext4/fsync.c
Theodore Ts'o 8fdd60f2ae Revert "ext4: use ext4_write_inode() when fsyncing w/o a journal"
This reverts commit ad211f3e94.

As Jan Kara pointed out, this change was unsafe since it means we lose
the call to sync_mapping_buffers() in the nojournal case.  The
original point of the commit was avoid taking the inode mutex (since
it causes a lockdep warning in generic/113); but we need the mutex in
order to call sync_mapping_buffers().

The real fix to this problem was discussed here:

https://lore.kernel.org/lkml/20181025150540.259281-4-bvanassche@acm.org

The proposed patch was to fix a syzbot complaint, but the problem can
also demonstrated via "kvm-xfstests -c nojournal generic/113".
Multiple solutions were discused in the e-mail thread, but none have
landed in the kernel as of this writing.  Anyway, commit
ad211f3e94 is absolutely the wrong way to suppress the lockdep, so
revert it.

Fixes: ad211f3e94 ("ext4: use ext4_write_inode() when fsyncing w/o a journal")
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reported: Jan Kara <jack@suse.cz>
2019-01-31 23:41:11 -05:00

168 lines
4.7 KiB
C

// 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 "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 = NULL;
struct inode *next;
int ret = 0;
if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
return 0;
inode = igrab(inode);
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(d_inode(dentry->d_parent));
dput(dentry);
if (!next)
break;
iput(inode);
inode = next;
/*
* 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 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;
}
iput(inode);
return ret;
}
/*
* 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)
{
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 = 0, err;
tid_t commit_tid;
bool needs_barrier = false;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
J_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_mount_flags value */
smp_rmb();
if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
ret = -EROFS;
goto out;
}
if (!journal) {
ret = __generic_file_fsync(file, start, end, datasync);
if (!ret)
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
goto issue_flush;
goto out;
}
ret = file_write_and_wait_range(file, start, end);
if (ret)
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)) {
ret = ext4_force_commit(inode->i_sb);
goto out;
}
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
issue_flush:
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
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;
}