Summary:

Allows rbinds across any two namespaces.  NOTE: currenly bind from foriegn
namespace to current namespace is allowed. This patch now allows:

binds/rbinds from any namespace to any other namespace, under the assumption
that if a process has access to a namespace, it ought to have permission to
manipulate that namespace. The only case disallowed is a recursive bind to a
detached mount.

The patch incorporates ideas from Miklos and Jamie, and is dependent on
Miklos's "fix race in mark_mounts_for_expiry" patch to function correctly. Also
it depends on Miklos's "fix bind mount from foreign namespace" patch, because
without that patch umounts would fail.


Signed off by Ram Pai <linuxram@us.ibm.com>

--- /home/linux/views/linux-2.6.12-rc4/fs/namespace.c	2005-05-06 23:22:29.000000000 -0700
+++ linux-2.6.12-rc4/fs/namespace.c	2005-05-21 02:58:48.000000000 -0700
@@ -616,11 +616,14 @@ out_unlock:
 }
 
 /*
- * do loopback mount.
+ * do loopback mount.  The loopback mount can be done from any namespace
+ * to any other namespace including the current namespace, as long as
+ * the task acquired rights to manipulate them.
  */
 static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
 {
 	struct nameidata old_nd;
+	struct namespace *mntpt_ns, *old_ns;
 	struct vfsmount *mnt = NULL;
 	int err = mount_is_safe(nd);
 	if (err)
@@ -631,15 +634,41 @@ static int do_loopback(struct nameidata 
 	if (err)
 		return err;
 
-	down_write(&current->namespace->sem);
 	err = -EINVAL;
-	if (check_mnt(nd->mnt) && (!recurse || check_mnt(old_nd.mnt))) {
-		err = -ENOMEM;
-		if (recurse)
-			mnt = copy_tree(old_nd.mnt, old_nd.dentry);
-		else
-			mnt = clone_mnt(old_nd.mnt, old_nd.dentry);
+	spin_lock(&vfsmount_lock);
+
+	/* 
+	 * Allow all kinds of binds and rbinds except
+	 * recursive bind to a detached mount
+	 */
+	mntpt_ns = nd->mnt->mnt_namespace;
+	old_ns = old_nd.mnt->mnt_namespace;
+	if (!mntpt_ns || !mntpt_ns->root || 
+		(recurse && (!old_ns || !old_ns->root))) {
+		spin_unlock(&vfsmount_lock);
+		goto out;
 	}
+	get_namespace(mntpt_ns);
+	if (recurse && old_ns != mntpt_ns)
+		get_namespace(old_ns);
+
+	spin_unlock(&vfsmount_lock);
+
+	/* 
+	 * make sure we don't race with some other thread manipulating the
+	 * namespaces.
+	 */
+	if (recurse && (old_ns < mntpt_ns))
+		down_write(&old_ns->sem);
+	down_write(&mntpt_ns->sem);
+	if (recurse && (old_ns > mntpt_ns))
+		down_write(&old_ns->sem);
+
+	err = -ENOMEM;
+	if (recurse)
+		mnt = copy_tree(old_nd.mnt, old_nd.dentry);
+	else
+		mnt = clone_mnt(old_nd.mnt, old_nd.dentry);
 
 	if (mnt) {
 		/* stop bind mounts from expiring */
@@ -656,7 +685,14 @@ static int do_loopback(struct nameidata 
 			mntput(mnt);
 	}
 
-	up_write(&current->namespace->sem);
+	up_write(&mntpt_ns->sem);
+	if (recurse && (old_ns != mntpt_ns)) {
+		up_write(&old_ns->sem);
+		put_namespace(old_ns);
+	}
+	put_namespace(mntpt_ns);
+
+out:
 	path_release(&old_nd);
 	return err;
 }