fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers

Btrfs needs to be able to control how filemap_write_and_wait_range() is called
in fsync to make it less of a painful operation, so push down taking i_mutex and
the calling of filemap_write_and_wait() down into the ->fsync() handlers.  Some
file systems can drop taking the i_mutex altogether it seems, like ext3 and
ocfs2.  For correctness sake I just pushed everything down in all cases to make
sure that we keep the current behavior the same for everybody, and then each
individual fs maintainer can make up their mind about what to do from there.
Thanks,

Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 15 insertions, 4 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index f605753c8fe9..8d74ad7ba556 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1811,7 +1811,7 @@ out:
         spin_unlock(&ci->i_unsafe_lock);
 }
 
-int ceph_fsync(struct file *file, int datasync)
+int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
         struct inode *inode = file->f_mapping->host;
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1822,9 +1822,10 @@ int ceph_fsync(struct file *file, int datasync)
         dout("fsync %p%s\n", inode, datasync ? " datasync" : "");
         sync_write_wait(inode);
 
-        ret = filemap_write_and_wait(inode->i_mapping);
+        ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
         if (ret < 0)
                 return ret;
+        mutex_lock(&inode->i_mutex);
 
         dirty = try_flush_caps(inode, NULL, &flush_tid);
         dout("fsync dirty caps are %s\n", ceph_cap_string(dirty));
@@ -1841,6 +1842,7 @@ int ceph_fsync(struct file *file, int datasync)
         }
 
         dout("fsync %p%s done\n", inode, datasync ? " datasync" : "");
+        mutex_unlock(&inode->i_mutex);
         return ret;
 }
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 0972b457a03f..1065ac779840 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1118,7 +1118,8 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
  * an fsync() on a dir will wait for any uncommitted directory
  * operations to commit.
  */
-static int ceph_dir_fsync(struct file *file, int datasync)
+static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
+                          int datasync)
 {
         struct inode *inode = file->f_path.dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1128,6 +1129,11 @@ static int ceph_dir_fsync(struct file *file, int datasync)
         int ret = 0;
 
         dout("dir_fsync %p\n", inode);
+        ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+        if (ret)
+                return ret;
+        mutex_lock(&inode->i_mutex);
+
         spin_lock(&ci->i_unsafe_lock);
         if (list_empty(head))
                 goto out;
@@ -1161,6 +1167,8 @@ static int ceph_dir_fsync(struct file *file, int datasync)
         } while (req->r_tid < last_tid);
 out:
         spin_unlock(&ci->i_unsafe_lock);
+        mutex_unlock(&inode->i_mutex);
+
         return ret;
 }
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 56c41ef47cad..30446b144e3d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -728,7 +728,8 @@ extern void ceph_put_cap(struct ceph_mds_client *mdsc,
 
 extern void ceph_queue_caps_release(struct inode *inode);
 extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
-extern int ceph_fsync(struct file *file, int datasync);
+extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
+                      int datasync);
 extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
                                     struct ceph_mds_session *session);
 extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,