1 files changed, 509 insertions, 127 deletions

diff --git a/fs/nsfs.c b/fs/nsfs.c
index 3506f6074288..bf27d5da91f1 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -8,117 +8,72 @@
 #include <linux/magic.h>
 #include <linux/ktime.h>
 #include <linux/seq_file.h>
+#include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/nsfs.h>
 #include <linux/uaccess.h>
-
+#include <linux/mnt_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/time_namespace.h>
+#include <linux/utsname.h>
+#include <linux/exportfs.h>
+#include <linux/nstree.h>
+#include <net/net_namespace.h>
+
+#include "mount.h"
 #include "internal.h"
 
 static struct vfsmount *nsfs_mnt;
 
+static struct path nsfs_root_path = {};
+
+void nsfs_get_root(struct path *path)
+{
+	*path = nsfs_root_path;
+	path_get(path);
+}
+
 static long ns_ioctl(struct file *filp, unsigned int ioctl,
 			unsigned long arg);
 static const struct file_operations ns_file_operations = {
-	.llseek		= no_llseek,
 	.unlocked_ioctl = ns_ioctl,
+	.compat_ioctl   = compat_ptr_ioctl,
 };
 
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	struct inode *inode = d_inode(dentry);
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+	struct ns_common *ns = inode->i_private;
+	const struct proc_ns_operations *ns_ops = ns->ops;
 
 	return dynamic_dname(buffer, buflen, "%s:[%lu]",
 		ns_ops->name, inode->i_ino);
 }
 
-static void ns_prune_dentry(struct dentry *dentry)
-{
-	struct inode *inode = d_inode(dentry);
-	if (inode) {
-		struct ns_common *ns = inode->i_private;
-		atomic_long_set(&ns->stashed, 0);
-	}
-}
-
-const struct dentry_operations ns_dentry_operations =
-{
-	.d_prune	= ns_prune_dentry,
-	.d_delete	= always_delete_dentry,
+const struct dentry_operations ns_dentry_operations = {
 	.d_dname	= ns_dname,
+	.d_prune	= stashed_dentry_prune,
 };
 
 static void nsfs_evict(struct inode *inode)
 {
 	struct ns_common *ns = inode->i_private;
-	clear_inode(inode);
-	ns->ops->put(ns);
-}
 
-static int __ns_get_path(struct path *path, struct ns_common *ns)
-{
-	struct vfsmount *mnt = nsfs_mnt;
-	struct dentry *dentry;
-	struct inode *inode;
-	unsigned long d;
-
-	rcu_read_lock();
-	d = atomic_long_read(&ns->stashed);
-	if (!d)
-		goto slow;
-	dentry = (struct dentry *)d;
-	if (!lockref_get_not_dead(&dentry->d_lockref))
-		goto slow;
-	rcu_read_unlock();
+	__ns_ref_active_put(ns);
+	clear_inode(inode);
 	ns->ops->put(ns);
-got_it:
-	path->mnt = mntget(mnt);
-	path->dentry = dentry;
-	return 0;
-slow:
-	rcu_read_unlock();
-	inode = new_inode_pseudo(mnt->mnt_sb);
-	if (!inode) {
-		ns->ops->put(ns);
-		return -ENOMEM;
-	}
-	inode->i_ino = ns->inum;
-	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-	inode->i_flags |= S_IMMUTABLE;
-	inode->i_mode = S_IFREG | S_IRUGO;
-	inode->i_fop = &ns_file_operations;
-	inode->i_private = ns;
-
-	dentry = d_alloc_anon(mnt->mnt_sb);
-	if (!dentry) {
-		iput(inode);
-		return -ENOMEM;
-	}
-	d_instantiate(dentry, inode);
-	dentry->d_fsdata = (void *)ns->ops;
-	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
-	if (d) {
-		d_delete(dentry);	/* make sure ->d_prune() does nothing */
-		dput(dentry);
-		cpu_relax();
-		return -EAGAIN;
-	}
-	goto got_it;
 }
 
 int ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb,
 		     void *private_data)
 {
-	int ret;
+	struct ns_common *ns;
 
-	do {
-		struct ns_common *ns = ns_get_cb(private_data);
-		if (!ns)
-			return -ENOENT;
-		ret = __ns_get_path(path, ns);
-	} while (ret == -EAGAIN);
+	ns = ns_get_cb(private_data);
+	if (!ns)
+		return -ENOENT;
 
-	return ret;
+	return path_from_stashed(&ns->stashed, nsfs_mnt, ns, path);
 }
 
 struct ns_get_path_task_args {
@@ -144,55 +99,110 @@ int ns_get_path(struct path *path, struct task_struct *task,
 	return ns_get_path_cb(path, ns_get_path_task, &args);
 }
 
+/**
+ * open_namespace - open a namespace
+ * @ns: the namespace to open
+ *
+ * This will consume a reference to @ns indendent of success or failure.
+ *
+ * Return: A file descriptor on success or a negative error code on failure.
+ */
+int open_namespace(struct ns_common *ns)
+{
+	struct path path __free(path_put) = {};
+	int err;
+
+	/* call first to consume reference */
+	err = path_from_stashed(&ns->stashed, nsfs_mnt, ns, &path);
+	if (err < 0)
+		return err;
+
+	return FD_ADD(O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred()));
+}
+
 int open_related_ns(struct ns_common *ns,
 		   struct ns_common *(*get_ns)(struct ns_common *ns))
 {
-	struct path path = {};
-	struct file *f;
-	int err;
-	int fd;
+	struct ns_common *relative;
 
-	fd = get_unused_fd_flags(O_CLOEXEC);
-	if (fd < 0)
-		return fd;
+	relative = get_ns(ns);
+	if (IS_ERR(relative))
+		return PTR_ERR(relative);
 
-	do {
-		struct ns_common *relative;
+	return open_namespace(relative);
+}
+EXPORT_SYMBOL_GPL(open_related_ns);
 
-		relative = get_ns(ns);
-		if (IS_ERR(relative)) {
-			put_unused_fd(fd);
-			return PTR_ERR(relative);
-		}
+static int copy_ns_info_to_user(const struct mnt_namespace *mnt_ns,
+				struct mnt_ns_info __user *uinfo, size_t usize,
+				struct mnt_ns_info *kinfo)
+{
+	/*
+	 * If userspace and the kernel have the same struct size it can just
+	 * be copied. If userspace provides an older struct, only the bits that
+	 * userspace knows about will be copied. If userspace provides a new
+	 * struct, only the bits that the kernel knows aobut will be copied and
+	 * the size value will be set to the size the kernel knows about.
+	 */
+	kinfo->size		= min(usize, sizeof(*kinfo));
+	kinfo->mnt_ns_id	= mnt_ns->ns.ns_id;
+	kinfo->nr_mounts	= READ_ONCE(mnt_ns->nr_mounts);
+	/* Subtract the root mount of the mount namespace. */
+	if (kinfo->nr_mounts)
+		kinfo->nr_mounts--;
+
+	if (copy_to_user(uinfo, kinfo, kinfo->size))
+		return -EFAULT;
 
-		err = __ns_get_path(&path, relative);
-	} while (err == -EAGAIN);
+	return 0;
+}
 
-	if (err) {
-		put_unused_fd(fd);
-		return err;
+static bool nsfs_ioctl_valid(unsigned int cmd)
+{
+	switch (cmd) {
+	case NS_GET_USERNS:
+	case NS_GET_PARENT:
+	case NS_GET_NSTYPE:
+	case NS_GET_OWNER_UID:
+	case NS_GET_MNTNS_ID:
+	case NS_GET_PID_FROM_PIDNS:
+	case NS_GET_TGID_FROM_PIDNS:
+	case NS_GET_PID_IN_PIDNS:
+	case NS_GET_TGID_IN_PIDNS:
+	case NS_GET_ID:
+		return true;
 	}
 
-	f = dentry_open(&path, O_RDONLY, current_cred());
-	path_put(&path);
-	if (IS_ERR(f)) {
-		put_unused_fd(fd);
-		fd = PTR_ERR(f);
-	} else
-		fd_install(fd, f);
+	/* Extensible ioctls require some extra handling. */
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(NS_MNT_GET_INFO):
+		return extensible_ioctl_valid(cmd, NS_MNT_GET_INFO, MNT_NS_INFO_SIZE_VER0);
+	case _IOC_NR(NS_MNT_GET_NEXT):
+		return extensible_ioctl_valid(cmd, NS_MNT_GET_NEXT, MNT_NS_INFO_SIZE_VER0);
+	case _IOC_NR(NS_MNT_GET_PREV):
+		return extensible_ioctl_valid(cmd, NS_MNT_GET_PREV, MNT_NS_INFO_SIZE_VER0);
+	}
 
-	return fd;
+	return false;
 }
-EXPORT_SYMBOL_GPL(open_related_ns);
 
 static long ns_ioctl(struct file *filp, unsigned int ioctl,
 			unsigned long arg)
 {
 	struct user_namespace *user_ns;
-	struct ns_common *ns = get_proc_ns(file_inode(filp));
+	struct pid_namespace *pid_ns;
+	struct task_struct *tsk;
+	struct ns_common *ns;
+	struct mnt_namespace *mnt_ns;
+	bool previous = false;
 	uid_t __user *argp;
 	uid_t uid;
+	int ret;
+
+	if (!nsfs_ioctl_valid(ioctl))
+		return -ENOIOCTLCMD;
 
+	ns = get_proc_ns(file_inode(filp));
 	switch (ioctl) {
 	case NS_GET_USERNS:
 		return open_related_ns(ns, ns_get_owner);
@@ -201,17 +211,134 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 			return -EINVAL;
 		return open_related_ns(ns, ns->ops->get_parent);
 	case NS_GET_NSTYPE:
-		return ns->ops->type;
+		return ns->ns_type;
 	case NS_GET_OWNER_UID:
-		if (ns->ops->type != CLONE_NEWUSER)
+		if (ns->ns_type != CLONE_NEWUSER)
 			return -EINVAL;
 		user_ns = container_of(ns, struct user_namespace, ns);
 		argp = (uid_t __user *) arg;
 		uid = from_kuid_munged(current_user_ns(), user_ns->owner);
 		return put_user(uid, argp);
+	case NS_GET_PID_FROM_PIDNS:
+		fallthrough;
+	case NS_GET_TGID_FROM_PIDNS:
+		fallthrough;
+	case NS_GET_PID_IN_PIDNS:
+		fallthrough;
+	case NS_GET_TGID_IN_PIDNS: {
+		if (ns->ns_type != CLONE_NEWPID)
+			return -EINVAL;
+
+		ret = -ESRCH;
+		pid_ns = container_of(ns, struct pid_namespace, ns);
+
+		guard(rcu)();
+
+		if (ioctl == NS_GET_PID_IN_PIDNS ||
+		    ioctl == NS_GET_TGID_IN_PIDNS)
+			tsk = find_task_by_vpid(arg);
+		else
+			tsk = find_task_by_pid_ns(arg, pid_ns);
+		if (!tsk)
+			break;
+
+		switch (ioctl) {
+		case NS_GET_PID_FROM_PIDNS:
+			ret = task_pid_vnr(tsk);
+			break;
+		case NS_GET_TGID_FROM_PIDNS:
+			ret = task_tgid_vnr(tsk);
+			break;
+		case NS_GET_PID_IN_PIDNS:
+			ret = task_pid_nr_ns(tsk, pid_ns);
+			break;
+		case NS_GET_TGID_IN_PIDNS:
+			ret = task_tgid_nr_ns(tsk, pid_ns);
+			break;
+		default:
+			ret = 0;
+			break;
+		}
+
+		if (!ret)
+			ret = -ESRCH;
+		return ret;
+	}
+	case NS_GET_MNTNS_ID:
+		if (ns->ns_type != CLONE_NEWNS)
+			return -EINVAL;
+		fallthrough;
+	case NS_GET_ID: {
+		__u64 __user *idp;
+		__u64 id;
+
+		idp = (__u64 __user *)arg;
+		id = ns->ns_id;
+		return put_user(id, idp);
+	}
+	}
+
+	/* extensible ioctls */
+	switch (_IOC_NR(ioctl)) {
+	case _IOC_NR(NS_MNT_GET_INFO): {
+		struct mnt_ns_info kinfo = {};
+		struct mnt_ns_info __user *uinfo = (struct mnt_ns_info __user *)arg;
+		size_t usize = _IOC_SIZE(ioctl);
+
+		if (ns->ns_type != CLONE_NEWNS)
+			return -EINVAL;
+
+		if (!uinfo)
+			return -EINVAL;
+
+		if (usize < MNT_NS_INFO_SIZE_VER0)
+			return -EINVAL;
+
+		return copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo);
+	}
+	case _IOC_NR(NS_MNT_GET_PREV):
+		previous = true;
+		fallthrough;
+	case _IOC_NR(NS_MNT_GET_NEXT): {
+		struct mnt_ns_info kinfo = {};
+		struct mnt_ns_info __user *uinfo = (struct mnt_ns_info __user *)arg;
+		struct path path __free(path_put) = {};
+		size_t usize = _IOC_SIZE(ioctl);
+
+		if (ns->ns_type != CLONE_NEWNS)
+			return -EINVAL;
+
+		if (usize < MNT_NS_INFO_SIZE_VER0)
+			return -EINVAL;
+
+		mnt_ns = get_sequential_mnt_ns(to_mnt_ns(ns), previous);
+		if (IS_ERR(mnt_ns))
+			return PTR_ERR(mnt_ns);
+
+		ns = to_ns_common(mnt_ns);
+		/* Transfer ownership of @mnt_ns reference to @path. */
+		ret = path_from_stashed(&ns->stashed, nsfs_mnt, ns, &path);
+		if (ret)
+			return ret;
+
+		FD_PREPARE(fdf, O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred()));
+		if (fdf.err)
+			return fdf.err;
+		/*
+		 * If @uinfo is passed return all information about the
+		 * mount namespace as well.
+		 */
+		ret = copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo);
+		if (ret)
+			return ret;
+		ret = fd_publish(fdf);
+		break;
+	}
 	default:
-		return -ENOTTY;
+		ret = -ENOTTY;
 	}
+
+	return ret;
 }
 
 int ns_get_name(char *buf, size_t size, struct task_struct *task,
@@ -234,27 +361,9 @@ bool proc_ns_file(const struct file *file)
 	return file->f_op == &ns_file_operations;
 }
 
-struct file *proc_ns_fget(int fd)
-{
-	struct file *file;
-
-	file = fget(fd);
-	if (!file)
-		return ERR_PTR(-EBADF);
-
-	if (file->f_op != &ns_file_operations)
-		goto out_invalid;
-
-	return file;
-
-out_invalid:
-	fput(file);
-	return ERR_PTR(-EINVAL);
-}
-
 /**
  * ns_match() - Returns true if current namespace matches dev/ino provided.
- * @ns_common: current ns
+ * @ns: current namespace
  * @dev: dev_t from nsfs that will be matched against current nsfs
  * @ino: ino_t from nsfs that will be matched against current nsfs
  *
@@ -269,7 +378,8 @@ bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino)
 static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+	const struct ns_common *ns = inode->i_private;
+	const struct proc_ns_operations *ns_ops = ns->ops;
 
 	seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino);
 	return 0;
@@ -279,6 +389,248 @@ static const struct super_operations nsfs_ops = {
 	.statfs = simple_statfs,
 	.evict_inode = nsfs_evict,
 	.show_path = nsfs_show_path,
+	.drop_inode = inode_just_drop,
+};
+
+static int nsfs_init_inode(struct inode *inode, void *data)
+{
+	struct ns_common *ns = data;
+
+	inode->i_private = data;
+	inode->i_mode |= S_IRUGO;
+	inode->i_fop = &ns_file_operations;
+	inode->i_ino = ns->inum;
+
+	/*
+	 * Bring the namespace subtree back to life if we have to. This
+	 * can happen when e.g., all processes using a network namespace
+	 * and all namespace files or namespace file bind-mounts have
+	 * died but there are still sockets pinning it. The SIOCGSKNS
+	 * ioctl on such a socket will resurrect the relevant namespace
+	 * subtree.
+	 */
+	__ns_ref_active_get(ns);
+	return 0;
+}
+
+static void nsfs_put_data(void *data)
+{
+	struct ns_common *ns = data;
+	ns->ops->put(ns);
+}
+
+static const struct stashed_operations nsfs_stashed_ops = {
+	.init_inode = nsfs_init_inode,
+	.put_data = nsfs_put_data,
+};
+
+#define NSFS_FID_SIZE_U32_VER0 (NSFS_FILE_HANDLE_SIZE_VER0 / sizeof(u32))
+#define NSFS_FID_SIZE_U32_LATEST (NSFS_FILE_HANDLE_SIZE_LATEST / sizeof(u32))
+
+static int nsfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
+			  struct inode *parent)
+{
+	struct nsfs_file_handle *fid = (struct nsfs_file_handle *)fh;
+	struct ns_common *ns = inode->i_private;
+	int len = *max_len;
+
+	if (parent)
+		return FILEID_INVALID;
+
+	if (len < NSFS_FID_SIZE_U32_VER0) {
+		*max_len = NSFS_FID_SIZE_U32_LATEST;
+		return FILEID_INVALID;
+	} else if (len > NSFS_FID_SIZE_U32_LATEST) {
+		*max_len = NSFS_FID_SIZE_U32_LATEST;
+	}
+
+	fid->ns_id	= ns->ns_id;
+	fid->ns_type	= ns->ns_type;
+	fid->ns_inum	= inode->i_ino;
+	return FILEID_NSFS;
+}
+
+bool is_current_namespace(struct ns_common *ns)
+{
+	switch (ns->ns_type) {
+#ifdef CONFIG_CGROUPS
+	case CLONE_NEWCGROUP:
+		return current_in_namespace(to_cg_ns(ns));
+#endif
+#ifdef CONFIG_IPC_NS
+	case CLONE_NEWIPC:
+		return current_in_namespace(to_ipc_ns(ns));
+#endif
+	case CLONE_NEWNS:
+		return current_in_namespace(to_mnt_ns(ns));
+#ifdef CONFIG_NET_NS
+	case CLONE_NEWNET:
+		return current_in_namespace(to_net_ns(ns));
+#endif
+#ifdef CONFIG_PID_NS
+	case CLONE_NEWPID:
+		return current_in_namespace(to_pid_ns(ns));
+#endif
+#ifdef CONFIG_TIME_NS
+	case CLONE_NEWTIME:
+		return current_in_namespace(to_time_ns(ns));
+#endif
+#ifdef CONFIG_USER_NS
+	case CLONE_NEWUSER:
+		return current_in_namespace(to_user_ns(ns));
+#endif
+#ifdef CONFIG_UTS_NS
+	case CLONE_NEWUTS:
+		return current_in_namespace(to_uts_ns(ns));
+#endif
+	default:
+		VFS_WARN_ON_ONCE(true);
+		return false;
+	}
+}
+
+static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
+					int fh_len, int fh_type)
+{
+	struct path path __free(path_put) = {};
+	struct nsfs_file_handle *fid = (struct nsfs_file_handle *)fh;
+	struct user_namespace *owning_ns = NULL;
+	struct ns_common *ns;
+	int ret;
+
+	if (fh_len < NSFS_FID_SIZE_U32_VER0)
+		return NULL;
+
+	/* Check that any trailing bytes are zero. */
+	if ((fh_len > NSFS_FID_SIZE_U32_LATEST) &&
+	    memchr_inv((void *)fid + NSFS_FID_SIZE_U32_LATEST, 0,
+		       fh_len - NSFS_FID_SIZE_U32_LATEST))
+		return NULL;
+
+	switch (fh_type) {
+	case FILEID_NSFS:
+		break;
+	default:
+		return NULL;
+	}
+
+	if (!fid->ns_id)
+		return NULL;
+	/* Either both are set or both are unset. */
+	if (!fid->ns_inum != !fid->ns_type)
+		return NULL;
+
+	scoped_guard(rcu) {
+		ns = ns_tree_lookup_rcu(fid->ns_id, fid->ns_type);
+		if (!ns)
+			return NULL;
+
+		VFS_WARN_ON_ONCE(ns->ns_id != fid->ns_id);
+
+		if (fid->ns_inum && (fid->ns_inum != ns->inum))
+			return NULL;
+		if (fid->ns_type && (fid->ns_type != ns->ns_type))
+			return NULL;
+
+		/*
+		 * This is racy because we're not actually taking an
+		 * active reference. IOW, it could happen that the
+		 * namespace becomes inactive after this check.
+		 * We don't care because nsfs_init_inode() will just
+		 * resurrect the relevant namespace tree for us. If it
+		 * has been active here we just allow it's resurrection.
+		 * We could try to take an active reference here and
+		 * then drop it again. But really, why bother.
+		 */
+		if (!ns_get_unless_inactive(ns))
+			return NULL;
+	}
+
+	switch (ns->ns_type) {
+#ifdef CONFIG_CGROUPS
+	case CLONE_NEWCGROUP:
+		if (!current_in_namespace(to_cg_ns(ns)))
+			owning_ns = to_cg_ns(ns)->user_ns;
+		break;
+#endif
+#ifdef CONFIG_IPC_NS
+	case CLONE_NEWIPC:
+		if (!current_in_namespace(to_ipc_ns(ns)))
+			owning_ns = to_ipc_ns(ns)->user_ns;
+		break;
+#endif
+	case CLONE_NEWNS:
+		if (!current_in_namespace(to_mnt_ns(ns)))
+			owning_ns = to_mnt_ns(ns)->user_ns;
+		break;
+#ifdef CONFIG_NET_NS
+	case CLONE_NEWNET:
+		if (!current_in_namespace(to_net_ns(ns)))
+			owning_ns = to_net_ns(ns)->user_ns;
+		break;
+#endif
+#ifdef CONFIG_PID_NS
+	case CLONE_NEWPID:
+		if (!current_in_namespace(to_pid_ns(ns))) {
+			owning_ns = to_pid_ns(ns)->user_ns;
+		} else if (!READ_ONCE(to_pid_ns(ns)->child_reaper)) {
+			ns->ops->put(ns);
+			return ERR_PTR(-EPERM);
+		}
+		break;
+#endif
+#ifdef CONFIG_TIME_NS
+	case CLONE_NEWTIME:
+		if (!current_in_namespace(to_time_ns(ns)))
+			owning_ns = to_time_ns(ns)->user_ns;
+		break;
+#endif
+#ifdef CONFIG_USER_NS
+	case CLONE_NEWUSER:
+		if (!current_in_namespace(to_user_ns(ns)))
+			owning_ns = to_user_ns(ns);
+		break;
+#endif
+#ifdef CONFIG_UTS_NS
+	case CLONE_NEWUTS:
+		if (!current_in_namespace(to_uts_ns(ns)))
+			owning_ns = to_uts_ns(ns)->user_ns;
+		break;
+#endif
+	default:
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (owning_ns && !ns_capable(owning_ns, CAP_SYS_ADMIN)) {
+		ns->ops->put(ns);
+		return ERR_PTR(-EPERM);
+	}
+
+	/* path_from_stashed() unconditionally consumes the reference. */
+	ret = path_from_stashed(&ns->stashed, nsfs_mnt, ns, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return no_free_ptr(path.dentry);
+}
+
+static int nsfs_export_permission(struct handle_to_path_ctx *ctx,
+				   unsigned int oflags)
+{
+	/* nsfs_fh_to_dentry() performs all permission checks. */
+	return 0;
+}
+
+static struct file *nsfs_export_open(const struct path *path, unsigned int oflags)
+{
+	return file_open_root(path, "", oflags, 0);
+}
+
+static const struct export_operations nsfs_export_operations = {
+	.encode_fh	= nsfs_encode_fh,
+	.fh_to_dentry	= nsfs_fh_to_dentry,
+	.open		= nsfs_export_open,
+	.permission	= nsfs_export_permission,
 };
 
 static int nsfs_init_fs_context(struct fs_context *fc)
@@ -286,8 +638,12 @@ static int nsfs_init_fs_context(struct fs_context *fc)
 	struct pseudo_fs_context *ctx = init_pseudo(fc, NSFS_MAGIC);
 	if (!ctx)
 		return -ENOMEM;
+	fc->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
+	ctx->s_d_flags |= DCACHE_DONTCACHE;
 	ctx->ops = &nsfs_ops;
+	ctx->eops = &nsfs_export_operations;
 	ctx->dops = &ns_dentry_operations;
+	fc->s_fs_info = (void *)&nsfs_stashed_ops;
 	return 0;
 }
 
@@ -303,4 +659,30 @@ void __init nsfs_init(void)
 	if (IS_ERR(nsfs_mnt))
 		panic("can't set nsfs up\n");
 	nsfs_mnt->mnt_sb->s_flags &= ~SB_NOUSER;
+	nsfs_root_path.mnt = nsfs_mnt;
+	nsfs_root_path.dentry = nsfs_mnt->mnt_root;
+}
+
+void nsproxy_ns_active_get(struct nsproxy *ns)
+{
+	ns_ref_active_get(ns->mnt_ns);
+	ns_ref_active_get(ns->uts_ns);
+	ns_ref_active_get(ns->ipc_ns);
+	ns_ref_active_get(ns->pid_ns_for_children);
+	ns_ref_active_get(ns->cgroup_ns);
+	ns_ref_active_get(ns->net_ns);
+	ns_ref_active_get(ns->time_ns);
+	ns_ref_active_get(ns->time_ns_for_children);
+}
+
+void nsproxy_ns_active_put(struct nsproxy *ns)
+{
+	ns_ref_active_put(ns->mnt_ns);
+	ns_ref_active_put(ns->uts_ns);
+	ns_ref_active_put(ns->ipc_ns);
+	ns_ref_active_put(ns->pid_ns_for_children);
+	ns_ref_active_put(ns->cgroup_ns);
+	ns_ref_active_put(ns->net_ns);
+	ns_ref_active_put(ns->time_ns);
+	ns_ref_active_put(ns->time_ns_for_children);
 }