Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull namespace updates from Eric Biederman:
 "This set of changes is a number of smaller things that have been
  overlooked in other development cycles focused on more fundamental
  change. The devpts changes are small things that were a distraction
  until we managed to kill off DEVPTS_MULTPLE_INSTANCES. There is an
  trivial regression fix to autofs for the unprivileged mount changes
  that went in last cycle. A pair of ioctls has been added by Andrey
  Vagin making it is possible to discover the relationships between
  namespaces when referring to them through file descriptors.

  The big user visible change is starting to add simple resource limits
  to catch programs that misbehave. With namespaces in general and user
  namespaces in particular allowing users to use more kinds of
  resources, it has become important to have something to limit errant
  programs. Because the purpose of these limits is to catch errant
  programs the code needs to be inexpensive to use as it always on, and
  the default limits need to be high enough that well behaved programs
  on well behaved systems don't encounter them.

  To this end, after some review I have implemented per user per user
  namespace limits, and use them to limit the number of namespaces. The
  limits being per user mean that one user can not exhause the limits of
  another user. The limits being per user namespace allow contexts where
  the limit is 0 and security conscious folks can remove from their
  threat anlysis the code used to manage namespaces (as they have
  historically done as it root only). At the same time the limits being
  per user namespace allow other parts of the system to use namespaces.

  Namespaces are increasingly being used in application sand boxing
  scenarios so an all or nothing disable for the entire system for the
  security conscious folks makes increasing use of these sandboxes
  impossible.

  There is also added a limit on the maximum number of mounts present in
  a single mount namespace. It is nontrivial to guess what a reasonable
  system wide limit on the number of mount structure in the kernel would
  be, especially as it various based on how a system is using
  containers. A limit on the number of mounts in a mount namespace
  however is much easier to understand and set. In most cases in
  practice only about 1000 mounts are used. Given that some autofs
  scenarious have the potential to be 30,000 to 50,000 mounts I have set
  the default limit for the number of mounts at 100,000 which is well
  above every known set of users but low enough that the mount hash
  tables don't degrade unreaonsably.

  These limits are a start. I expect this estabilishes a pattern that
  other limits for resources that namespaces use will follow. There has
  been interest in making inotify event limits per user per user
  namespace as well as interest expressed in making details about what
  is going on in the kernel more visible"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (28 commits)
  autofs:  Fix automounts by using current_real_cred()->uid
  mnt: Add a per mount namespace limit on the number of mounts
  netns: move {inc,dec}_net_namespaces into #ifdef
  nsfs: Simplify __ns_get_path
  tools/testing: add a test to check nsfs ioctl-s
  nsfs: add ioctl to get a parent namespace
  nsfs: add ioctl to get an owning user namespace for ns file descriptor
  kernel: add a helper to get an owning user namespace for a namespace
  devpts: Change the owner of /dev/pts/ptmx to the mounter of /dev/pts
  devpts: Remove sync_filesystems
  devpts: Make devpts_kill_sb safe if fsi is NULL
  devpts: Simplify devpts_mount by using mount_nodev
  devpts: Move the creation of /dev/pts/ptmx into fill_super
  devpts: Move parse_mount_options into fill_super
  userns: When the per user per user namespace limit is reached return ENOSPC
  userns; Document per user per user namespace limits.
  mntns: Add a limit on the number of mount namespaces.
  netns: Add a limit on the number of net namespaces
  cgroupns: Add a limit on the number of cgroup namespaces
  ipcns: Add a  limit on the number of ipc namespaces
  ...

7 files changed, 177 insertions, 29 deletions

diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 431fd7ee3488..e44271dfceb6 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -431,8 +431,8 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 		memcpy(&wq->name, &qstr, sizeof(struct qstr));
 		wq->dev = autofs4_get_dev(sbi);
 		wq->ino = autofs4_get_ino(sbi);
-		wq->uid = current_uid();
-		wq->gid = current_gid();
+		wq->uid = current_real_cred()->uid;
+		wq->gid = current_real_cred()->gid;
 		wq->pid = pid;
 		wq->tgid = tgid;
 		wq->status = -EINTR; /* Status return if interrupted */
diff --git a/fs/mount.h b/fs/mount.h
index 14db05d424f7..d2e25d7b64b3 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -10,9 +10,12 @@ struct mnt_namespace {
 	struct mount *	root;
 	struct list_head	list;
 	struct user_namespace	*user_ns;
+	struct ucounts		*ucounts;
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	u64 event;
+	unsigned int		mounts; /* # of mounts in the namespace */
+	unsigned int		pending_mounts;
 };
 
 struct mnt_pcp {
diff --git a/fs/namespace.c b/fs/namespace.c
index 7bb2cda3bfef..db1b5a38864e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -27,6 +27,9 @@
 #include "pnode.h"
 #include "internal.h"
 
+/* Maximum number of mounts in a mount namespace */
+unsigned int sysctl_mount_max __read_mostly = 100000;
+
 static unsigned int m_hash_mask __read_mostly;
 static unsigned int m_hash_shift __read_mostly;
 static unsigned int mp_hash_mask __read_mostly;
@@ -899,6 +902,9 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 
 	list_splice(&head, n->list.prev);
 
+	n->mounts += n->pending_mounts;
+	n->pending_mounts = 0;
+
 	attach_shadowed(mnt, parent, shadows);
 	touch_mnt_namespace(n);
 }
@@ -1419,11 +1425,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		propagate_umount(&tmp_list);
 
 	while (!list_empty(&tmp_list)) {
+		struct mnt_namespace *ns;
 		bool disconnect;
 		p = list_first_entry(&tmp_list, struct mount, mnt_list);
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
-		__touch_mnt_namespace(p->mnt_ns);
+		ns = p->mnt_ns;
+		if (ns) {
+			ns->mounts--;
+			__touch_mnt_namespace(ns);
+		}
 		p->mnt_ns = NULL;
 		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
@@ -1840,6 +1851,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse)
 	return 0;
 }
 
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
+{
+	unsigned int max = READ_ONCE(sysctl_mount_max);
+	unsigned int mounts = 0, old, pending, sum;
+	struct mount *p;
+
+	for (p = mnt; p; p = next_mnt(p, mnt))
+		mounts++;
+
+	old = ns->mounts;
+	pending = ns->pending_mounts;
+	sum = old + pending;
+	if ((old > sum) ||
+	    (pending > sum) ||
+	    (max < sum) ||
+	    (mounts > (max - sum)))
+		return -ENOSPC;
+
+	ns->pending_mounts = pending + mounts;
+	return 0;
+}
+
 /*
  *  @source_mnt : mount tree to be attached
  *  @nd         : place the mount tree @source_mnt is attached
@@ -1909,10 +1942,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			struct path *parent_path)
 {
 	HLIST_HEAD(tree_list);
+	struct mnt_namespace *ns = dest_mnt->mnt_ns;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Is there space to add these mounts to the mount namespace? */
+	if (!parent_path) {
+		err = count_mounts(ns, source_mnt);
+		if (err)
+			goto out;
+	}
+
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
@@ -1949,11 +1990,13 @@ static int attach_recursive_mnt(struct mount *source_mnt,
  out_cleanup_ids:
 	while (!hlist_empty(&tree_list)) {
 		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		child->mnt_parent->mnt_ns->pending_mounts = 0;
 		umount_tree(child, UMOUNT_SYNC);
 	}
 	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
+	ns->pending_mounts = 0;
 	return err;
 }
 
@@ -2719,9 +2762,20 @@ dput_out:
 	return retval;
 }
 
+static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns)
+{
+	return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES);
+}
+
+static void dec_mnt_namespaces(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES);
+}
+
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
 	ns_free_inum(&ns->ns);
+	dec_mnt_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	kfree(ns);
 }
@@ -2738,14 +2792,22 @@ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 {
 	struct mnt_namespace *new_ns;
+	struct ucounts *ucounts;
 	int ret;
 
+	ucounts = inc_mnt_namespaces(user_ns);
+	if (!ucounts)
+		return ERR_PTR(-ENOSPC);
+
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
-	if (!new_ns)
+	if (!new_ns) {
+		dec_mnt_namespaces(ucounts);
 		return ERR_PTR(-ENOMEM);
+	}
 	ret = ns_alloc_inum(&new_ns->ns);
 	if (ret) {
 		kfree(new_ns);
+		dec_mnt_namespaces(ucounts);
 		return ERR_PTR(ret);
 	}
 	new_ns->ns.ops = &mntns_operations;
@@ -2756,6 +2818,9 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 	init_waitqueue_head(&new_ns->poll);
 	new_ns->event = 0;
 	new_ns->user_ns = get_user_ns(user_ns);
+	new_ns->ucounts = ucounts;
+	new_ns->mounts = 0;
+	new_ns->pending_mounts = 0;
 	return new_ns;
 }
 
@@ -2805,6 +2870,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	q = new;
 	while (p) {
 		q->mnt_ns = new_ns;
+		new_ns->mounts++;
 		if (new_fs) {
 			if (&p->mnt == new_fs->root.mnt) {
 				new_fs->root.mnt = mntget(&q->mnt);
@@ -2843,6 +2909,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
 		struct mount *mnt = real_mount(m);
 		mnt->mnt_ns = new_ns;
 		new_ns->root = mnt;
+		new_ns->mounts++;
 		list_add(&mnt->mnt_list, &new_ns->list);
 	} else {
 		mntput(m);
@@ -3348,10 +3415,16 @@ static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 	return 0;
 }
 
+static struct user_namespace *mntns_owner(struct ns_common *ns)
+{
+	return to_mnt_ns(ns)->user_ns;
+}
+
 const struct proc_ns_operations mntns_operations = {
 	.name		= "mnt",
 	.type		= CLONE_NEWNS,
 	.get		= mntns_get,
 	.put		= mntns_put,
 	.install	= mntns_install,
+	.owner		= mntns_owner,
 };
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 8f20d6016e20..30bb10034120 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -5,11 +5,16 @@
 #include <linux/magic.h>
 #include <linux/ktime.h>
 #include <linux/seq_file.h>
+#include <linux/user_namespace.h>
+#include <linux/nsfs.h>
 
 static struct vfsmount *nsfs_mnt;
 
+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,
 };
 
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
@@ -44,22 +49,14 @@ static void nsfs_evict(struct inode *inode)
 	ns->ops->put(ns);
 }
 
-void *ns_get_path(struct path *path, struct task_struct *task,
-			const struct proc_ns_operations *ns_ops)
+static void *__ns_get_path(struct path *path, struct ns_common *ns)
 {
-	struct vfsmount *mnt = mntget(nsfs_mnt);
+	struct vfsmount *mnt = nsfs_mnt;
 	struct qstr qname = { .name = "", };
 	struct dentry *dentry;
 	struct inode *inode;
-	struct ns_common *ns;
 	unsigned long d;
 
-again:
-	ns = ns_ops->get(task);
-	if (!ns) {
-		mntput(mnt);
-		return ERR_PTR(-ENOENT);
-	}
 	rcu_read_lock();
 	d = atomic_long_read(&ns->stashed);
 	if (!d)
@@ -68,17 +65,16 @@ again:
 	if (!lockref_get_not_dead(&dentry->d_lockref))
 		goto slow;
 	rcu_read_unlock();
-	ns_ops->put(ns);
+	ns->ops->put(ns);
 got_it:
-	path->mnt = mnt;
+	path->mnt = mntget(mnt);
 	path->dentry = dentry;
 	return NULL;
 slow:
 	rcu_read_unlock();
 	inode = new_inode_pseudo(mnt->mnt_sb);
 	if (!inode) {
-		ns_ops->put(ns);
-		mntput(mnt);
+		ns->ops->put(ns);
 		return ERR_PTR(-ENOMEM);
 	}
 	inode->i_ino = ns->inum;
@@ -91,21 +87,96 @@ slow:
 	dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
 	if (!dentry) {
 		iput(inode);
-		mntput(mnt);
 		return ERR_PTR(-ENOMEM);
 	}
 	d_instantiate(dentry, inode);
-	dentry->d_fsdata = (void *)ns_ops;
+	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();
-		goto again;
+		return ERR_PTR(-EAGAIN);
 	}
 	goto got_it;
 }
 
+void *ns_get_path(struct path *path, struct task_struct *task,
+			const struct proc_ns_operations *ns_ops)
+{
+	struct ns_common *ns;
+	void *ret;
+
+again:
+	ns = ns_ops->get(task);
+	if (!ns)
+		return ERR_PTR(-ENOENT);
+
+	ret = __ns_get_path(path, ns);
+	if (IS_ERR(ret) && PTR_ERR(ret) == -EAGAIN)
+		goto again;
+	return ret;
+}
+
+static int open_related_ns(struct ns_common *ns,
+		   struct ns_common *(*get_ns)(struct ns_common *ns))
+{
+	struct path path = {};
+	struct file *f;
+	void *err;
+	int fd;
+
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	while (1) {
+		struct ns_common *relative;
+
+		relative = get_ns(ns);
+		if (IS_ERR(relative)) {
+			put_unused_fd(fd);
+			return PTR_ERR(relative);
+		}
+
+		err = __ns_get_path(&path, relative);
+		if (IS_ERR(err) && PTR_ERR(err) == -EAGAIN)
+			continue;
+		break;
+	}
+	if (IS_ERR(err)) {
+		put_unused_fd(fd);
+		return PTR_ERR(err);
+	}
+
+	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);
+
+	return fd;
+}
+
+static long ns_ioctl(struct file *filp, unsigned int ioctl,
+			unsigned long arg)
+{
+	struct ns_common *ns = get_proc_ns(file_inode(filp));
+
+	switch (ioctl) {
+	case NS_GET_USERNS:
+		return open_related_ns(ns, ns_get_owner);
+	case NS_GET_PARENT:
+		if (!ns->ops->get_parent)
+			return -EINVAL;
+		return open_related_ns(ns, ns->ops->get_parent);
+	default:
+		return -ENOTTY;
+	}
+}
+
 int ns_get_name(char *buf, size_t size, struct task_struct *task,
 			const struct proc_ns_operations *ns_ops)
 {
diff --git a/fs/pnode.c b/fs/pnode.c
index 99899705b105..234a9ac49958 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -259,7 +259,7 @@ static int propagate_one(struct mount *m)
 		read_sequnlock_excl(&mount_lock);
 	}
 	hlist_add_head(&child->mnt_hash, list);
-	return 0;
+	return count_mounts(m->mnt_ns, child);
 }
 
 /*
diff --git a/fs/pnode.h b/fs/pnode.h
index 0fcdbe7ca648..550f5a8b4fcf 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -52,4 +52,5 @@ void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 struct mount *copy_tree(struct mount *, struct dentry *, int);
 bool is_path_reachable(struct mount *, struct dentry *,
 			 const struct path *root);
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
 #endif /* _LINUX_PNODE_H */
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 2ed3d71d4767..71025b9e2a4e 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -72,7 +72,7 @@ static DEFINE_SPINLOCK(sysctl_lock);
 
 static void drop_sysctl_table(struct ctl_table_header *header);
 static int sysctl_follow_link(struct ctl_table_header **phead,
-	struct ctl_table **pentry, struct nsproxy *namespaces);
+	struct ctl_table **pentry);
 static int insert_links(struct ctl_table_header *head);
 static void put_links(struct ctl_table_header *header);
 
@@ -319,11 +319,11 @@ static void sysctl_head_finish(struct ctl_table_header *head)
 }
 
 static struct ctl_table_set *
-lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+lookup_header_set(struct ctl_table_root *root)
 {
 	struct ctl_table_set *set = &root->default_set;
 	if (root->lookup)
-		set = root->lookup(root, namespaces);
+		set = root->lookup(root);
 	return set;
 }
 
@@ -496,7 +496,7 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 
 	if (S_ISLNK(p->mode)) {
-		ret = sysctl_follow_link(&h, &p, current->nsproxy);
+		ret = sysctl_follow_link(&h, &p);
 		err = ERR_PTR(ret);
 		if (ret)
 			goto out;
@@ -664,7 +664,7 @@ static bool proc_sys_link_fill_cache(struct file *file,
 
 	if (S_ISLNK(table->mode)) {
 		/* It is not an error if we can not follow the link ignore it */
-		int err = sysctl_follow_link(&head, &table, current->nsproxy);
+		int err = sysctl_follow_link(&head, &table);
 		if (err)
 			goto out;
 	}
@@ -981,7 +981,7 @@ static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
 }
 
 static int sysctl_follow_link(struct ctl_table_header **phead,
-	struct ctl_table **pentry, struct nsproxy *namespaces)
+	struct ctl_table **pentry)
 {
 	struct ctl_table_header *head;
 	struct ctl_table_root *root;
@@ -993,7 +993,7 @@ static int sysctl_follow_link(struct ctl_table_header **phead,
 	ret = 0;
 	spin_lock(&sysctl_lock);
 	root = (*pentry)->data;
-	set = lookup_header_set(root, namespaces);
+	set = lookup_header_set(root);
 	dir = xlate_dir(set, (*phead)->parent);
 	if (IS_ERR(dir))
 		ret = PTR_ERR(dir);