ext4: update ext4_sync_file() to not use __generic_file_fsync()

When the filesystem is created without a journal, we eventually call
into __generic_file_fsync() in order to write out all the modified
in-core data to the permanent storage device. This function happens to
try and obtain an inode_lock() while synchronizing the files buffer
and it's associated metadata.

Generally, this is fine, however it becomes a problem when there is
higher level code that has already obtained an inode_lock() as this
leads to a recursive lock situation. This case is especially true when
porting across direct I/O to iomap infrastructure as we obtain an
inode_lock() early on in the I/O within ext4_dio_write_iter() and hold
it until the I/O has been completed. Consequently, to not run into
this specific issue, we move away from calling into
__generic_file_fsync() and perform the necessary synchronization tasks
within ext4_sync_file().

Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/3495f35ef67f2021b567e28e6f59222e583689b8.1572949325.git.mbobrowski@mbobrowski.org
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
This commit is contained in:
Matthew Bobrowski 2019-11-05 23:02:23 +11:00 committed by Theodore Ts'o
parent 0b9f230b94
commit 3eaf9cc62f
1 changed files with 47 additions and 25 deletions

View File

@ -80,6 +80,43 @@ static int ext4_sync_parent(struct inode *inode)
return ret;
}
static int ext4_fsync_nojournal(struct inode *inode, bool datasync,
bool *needs_barrier)
{
int ret, err;
ret = sync_mapping_buffers(inode->i_mapping);
if (!(inode->i_state & I_DIRTY_ALL))
return ret;
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
return ret;
err = sync_inode_metadata(inode, 1);
if (!ret)
ret = err;
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;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
*needs_barrier = true;
return jbd2_complete_transaction(journal, commit_tid);
}
/*
* akpm: A new design for ext4_sync_file().
*
@ -91,17 +128,14 @@ static int ext4_sync_parent(struct inode *inode)
* 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;
struct inode *inode = file->f_mapping->host;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
if (unlikely(ext4_forced_shutdown(sbi)))
return -EIO;
J_ASSERT(ext4_journal_current_handle() == NULL);
@ -111,23 +145,15 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int 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)
if (sbi->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.
@ -142,18 +168,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* (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)) {
if (!sbi->s_journal)
ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
else if (ext4_should_journal_data(inode))
ret = ext4_force_commit(inode->i_sb);
goto out;
}
else
ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
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;