vfs: Add a function to lazily unmount all mounts from any dentry.
The new function detach_mounts comes in two pieces. The first piece
is a static inline test of d_mounpoint that returns immediately
without taking any locks if d_mounpoint is not set. In the common
case when mountpoints are absent this allows the vfs to continue
running with it's same cacheline foot print.
The second piece of detach_mounts __detach_mounts actually does the
work and it assumes that a mountpoint is present so it is slow and
takes namespace_sem for write, and then locks the mount hash (aka
mount_lock) after a struct mountpoint has been found.
With those two locks held each entry on the list of mounts on a
mountpoint is selected and lazily unmounted until all of the mount
have been lazily unmounted.
v7: Wrote a proper change description and removed the changelog
documenting deleted wrong turns.
Signed-off-by: Eric W. Biederman <ebiederman@twitter.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/mount.h b/fs/mount.h
index 68bb03e..f82c628 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -87,6 +87,15 @@
extern bool legitimize_mnt(struct vfsmount *, unsigned);
+extern void __detach_mounts(struct dentry *dentry);
+
+static inline void detach_mounts(struct dentry *dentry)
+{
+ if (!d_mountpoint(dentry))
+ return;
+ __detach_mounts(dentry);
+}
+
static inline void get_mnt_ns(struct mnt_namespace *ns)
{
atomic_inc(&ns->count);
diff --git a/fs/namespace.c b/fs/namespace.c
index 88fc3f4..00e5b1e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1468,6 +1468,37 @@
return retval;
}
+/*
+ * __detach_mounts - lazily unmount all mounts on the specified dentry
+ *
+ * During unlink, rmdir, and d_drop it is possible to loose the path
+ * to an existing mountpoint, and wind up leaking the mount.
+ * detach_mounts allows lazily unmounting those mounts instead of
+ * leaking them.
+ *
+ * The caller may hold dentry->d_inode->i_mutex.
+ */
+void __detach_mounts(struct dentry *dentry)
+{
+ struct mountpoint *mp;
+ struct mount *mnt;
+
+ namespace_lock();
+ mp = lookup_mountpoint(dentry);
+ if (!mp)
+ goto out_unlock;
+
+ lock_mount_hash();
+ while (!hlist_empty(&mp->m_list)) {
+ mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
+ umount_tree(mnt, 2);
+ }
+ unlock_mount_hash();
+ put_mountpoint(mp);
+out_unlock:
+ namespace_unlock();
+}
+
/*
* Is the caller allowed to modify his namespace?
*/