vfs: Add setns support for the mount namespace

setns support for the mount namespace is a little tricky as an
arbitrary decision must be made about what to set fs->root and
fs->pwd to, as there is no expectation of a relationship between
the two mount namespaces.  Therefore I arbitrarily find the root
mount point, and follow every mount on top of it to find the top
of the mount stack.  Then I set fs->root and fs->pwd to that
location.  The topmost root of the mount stack seems like a
reasonable place to be.

Bind mount support for the mount namespace inodes has the
possibility of creating circular dependencies between mount
namespaces.  Circular dependencies can result in loops that
prevent mount namespaces from every being freed.  I avoid
creating those circular dependencies by adding a sequence number
to the mount namespace and require all bind mounts be of a
younger mount namespace into an older mount namespace.

Add a helper function proc_ns_inode so it is possible to
detect when we are attempting to bind mound a namespace inode.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

fs/mount.h

@@ -6,6 +6,7 @@ struct mnt_namespace {
 	atomic_t		count;
 	struct mount *	root;
 	struct list_head	list;
+	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	int event;
 };

fs/namespace.c

@@ -20,6 +20,7 @@
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
 #include <linux/fsnotify.h>	/* fsnotify_vfsmount_delete */
 #include <linux/uaccess.h>
+#include <linux/proc_fs.h>
 #include "pnode.h"
 #include "internal.h"
 
@@ -1308,6 +1309,26 @@ static int mount_is_safe(struct path *path)
 #endif
 }
 
+static bool mnt_ns_loop(struct path *path)
+{
+	/* Could bind mounting the mount namespace inode cause a
+	 * mount namespace loop?
+	 */
+	struct inode *inode = path->dentry->d_inode;
+	struct proc_inode *ei;
+	struct mnt_namespace *mnt_ns;
+
+	if (!proc_ns_inode(inode))
+		return false;
+
+	ei = PROC_I(inode);
+	if (ei->ns_ops != &mntns_operations)
+		return false;
+
+	mnt_ns = ei->ns;
+	return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
+}
+
 struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 					int flag)
 {
@@ -1655,6 +1676,10 @@ static int do_loopback(struct path *path, const char *old_name,
 	if (err)
 		return err;
 
+	err = -EINVAL;
+	if (mnt_ns_loop(&old_path))
+		goto out; 
+
 	err = lock_mount(path);
 	if (err)
 		goto out;
@@ -2261,6 +2286,15 @@ long do_mount(const char *dev_name, const char *dir_name,
 	return retval;
 }
 
+/*
+ * Assign a sequence number so we can detect when we attempt to bind
+ * mount a reference to an older mount namespace into the current
+ * mount namespace, preventing reference counting loops.  A 64bit
+ * number incrementing at 10Ghz will take 12,427 years to wrap which
+ * is effectively never, so we can ignore the possibility.
+ */
+static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
+
 static struct mnt_namespace *alloc_mnt_ns(void)
 {
 	struct mnt_namespace *new_ns;
@@ -2268,6 +2302,7 @@ static struct mnt_namespace *alloc_mnt_ns(void)
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
+	new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	atomic_set(&new_ns->count, 1);
 	new_ns->root = NULL;
 	INIT_LIST_HEAD(&new_ns->list);
@@ -2681,3 +2716,63 @@ bool our_mnt(struct vfsmount *mnt)
 {
 	return check_mnt(real_mount(mnt));
 }
+
+static void *mntns_get(struct task_struct *task)
+{
+	struct mnt_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	rcu_read_lock();
+	nsproxy = task_nsproxy(task);
+	if (nsproxy) {
+		ns = nsproxy->mnt_ns;
+		get_mnt_ns(ns);
+	}
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void mntns_put(void *ns)
+{
+	put_mnt_ns(ns);
+}
+
+static int mntns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct fs_struct *fs = current->fs;
+	struct mnt_namespace *mnt_ns = ns;
+	struct path root;
+
+	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_CHROOT))
+		return -EINVAL;
+
+	if (fs->users != 1)
+		return -EINVAL;
+
+	get_mnt_ns(mnt_ns);
+	put_mnt_ns(nsproxy->mnt_ns);
+	nsproxy->mnt_ns = mnt_ns;
+
+	/* Find the root */
+	root.mnt    = &mnt_ns->root->mnt;
+	root.dentry = mnt_ns->root->mnt.mnt_root;
+	path_get(&root);
+	while(d_mountpoint(root.dentry) && follow_down_one(&root))
+		;
+
+	/* Update the pwd and root */
+	set_fs_pwd(fs, &root);
+	set_fs_root(fs, &root);
+
+	path_put(&root);
+	return 0;
+}
+
+const struct proc_ns_operations mntns_operations = {
+	.name		= "mnt",
+	.type		= CLONE_NEWNS,
+	.get		= mntns_get,
+	.put		= mntns_put,
+	.install	= mntns_install,
+};

fs/proc/namespaces.c

@@ -27,6 +27,7 @@ static const struct proc_ns_operations *ns_entries[] = {
 #ifdef CONFIG_PID_NS
 	&pidns_operations,
 #endif
+	&mntns_operations,
 };
 
 static const struct file_operations ns_file_operations = {
@@ -201,3 +202,7 @@ struct file *proc_ns_fget(int fd)
 	return ERR_PTR(-EINVAL);
 }
 
+bool proc_ns_inode(struct inode *inode)
+{
+	return inode->i_fop == &ns_file_operations;
+}

include/linux/proc_fs.h

@@ -174,6 +174,7 @@ extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 	struct proc_dir_entry *parent);
 
 extern struct file *proc_ns_fget(int fd);
+extern bool proc_ns_inode(struct inode *inode);
 
 #else
 
@@ -229,6 +230,11 @@ static inline struct file *proc_ns_fget(int fd)
 	return ERR_PTR(-EINVAL);
 }
 
+static inline bool proc_ns_inode(struct inode *inode)
+{
+	return false;
+}
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)
@@ -252,6 +258,7 @@ extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
 extern const struct proc_ns_operations ipcns_operations;
 extern const struct proc_ns_operations pidns_operations;
+extern const struct proc_ns_operations mntns_operations;
 
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);