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>

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 5508baa11bb669545724b998af92d9a0375af054..e10206e7f4bbe7f470fd83687ddd3c48322bc892 100644 (file)
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -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;