Some of the higher layers like iomap takes inode_lock() when calling
generic_write_sync().
Also writeback already happens from other paths without inode lock,
so it's difficult to say that we really need sync_mapping_buffers() to
take any inode locking here. Having said that, let's add a _nolock
variant of this function in libfs for now so that filesystems like
ext2 and ext4's nojournal mode can use it.
Ext4 when got converted to iomap for direct-io already copied it's own
variant of __generic_file_fsync() without lock. Hence let's add a helper
API and use it both in ext2 and ext4.
Later we can review other filesystems as well to see if we can make
_nolock as the default path if inode_lock() is not necessary here.
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@xxxxxxxxx>
---
fs/libfs.c | 43 +++++++++++++++++++++++++++++++++++++++++++
include/linux/fs.h | 1 +
2 files changed, 44 insertions(+)
diff --git a/fs/libfs.c b/fs/libfs.c
index 4eda519c3002..d2dfb72e3cf8 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1110,6 +1110,49 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
}
EXPORT_SYMBOL_GPL(generic_fh_to_parent);
+/**
+ * __generic_file_fsync_nolock - generic fsync implementation for simple
+ * filesystems with no inode lock
+ *
+ * @file: file to synchronize
+ * @start: start offset in bytes
+ * @end: end offset in bytes (inclusive)
+ * @datasync: only synchronize essential metadata if true
+ *
+ * This is a generic implementation of the fsync method for simple
+ * filesystems which track all non-inode metadata in the buffers list
+ * hanging off the address_space structure.
+ */
+int __generic_file_fsync_nolock(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ struct inode *inode = file->f_mapping->host;
+ int err;
+ int ret;
+
+ err = file_write_and_wait_range(file, start, end);
+ if (err)
+ return err;
+
+ ret = sync_mapping_buffers(inode->i_mapping);
+ if (!(inode->i_state & I_DIRTY_ALL))
+ goto out;
+ if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+ goto out;
+
+ err = sync_inode_metadata(inode, 1);
+ if (ret == 0)
+ ret = err;
+
+out:
+ /* check and advance again to catch errors after syncing out buffers */
+ err = file_check_and_advance_wb_err(file);
+ if (ret == 0)
+ ret = err;
+ return ret;
+}
+EXPORT_SYMBOL(__generic_file_fsync_nolock);
+
/**
* __generic_file_fsync - generic fsync implementation for simple filesystems
*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c85916e9f7db..21d2b5670308 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2935,6 +2935,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count);
+extern int __generic_file_fsync_nolock(struct file *, loff_t, loff_t, int);
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
--
2.39.2
