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
  ...

1 files changed, 85 insertions, 14 deletions

diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 68f594212759..86b7854fec8e 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -29,6 +29,17 @@ static DEFINE_MUTEX(userns_state_mutex);
 static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *map);
+static void free_user_ns(struct work_struct *work);
+
+static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid)
+{
+	return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES);
+}
+
+static void dec_user_namespaces(struct ucounts *ucounts)
+{
+	return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES);
+}
 
 static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
 {
@@ -62,10 +73,16 @@ int create_user_ns(struct cred *new)
 	struct user_namespace *ns, *parent_ns = new->user_ns;
 	kuid_t owner = new->euid;
 	kgid_t group = new->egid;
-	int ret;
+	struct ucounts *ucounts;
+	int ret, i;
 
+	ret = -ENOSPC;
 	if (parent_ns->level > 32)
-		return -EUSERS;
+		goto fail;
+
+	ucounts = inc_user_namespaces(parent_ns, owner);
+	if (!ucounts)
+		goto fail;
 
 	/*
 	 * Verify that we can not violate the policy of which files
@@ -73,26 +90,27 @@ int create_user_ns(struct cred *new)
 	 * by verifing that the root directory is at the root of the
 	 * mount namespace which allows all files to be accessed.
 	 */
+	ret = -EPERM;
 	if (current_chrooted())
-		return -EPERM;
+		goto fail_dec;
 
 	/* The creator needs a mapping in the parent user namespace
 	 * or else we won't be able to reasonably tell userspace who
 	 * created a user_namespace.
 	 */
+	ret = -EPERM;
 	if (!kuid_has_mapping(parent_ns, owner) ||
 	    !kgid_has_mapping(parent_ns, group))
-		return -EPERM;
+		goto fail_dec;
 
+	ret = -ENOMEM;
 	ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
 	if (!ns)
-		return -ENOMEM;
+		goto fail_dec;
 
 	ret = ns_alloc_inum(&ns->ns);
-	if (ret) {
-		kmem_cache_free(user_ns_cachep, ns);
-		return ret;
-	}
+	if (ret)
+		goto fail_free;
 	ns->ns.ops = &userns_operations;
 
 	atomic_set(&ns->count, 1);
@@ -101,18 +119,37 @@ int create_user_ns(struct cred *new)
 	ns->level = parent_ns->level + 1;
 	ns->owner = owner;
 	ns->group = group;
+	INIT_WORK(&ns->work, free_user_ns);
+	for (i = 0; i < UCOUNT_COUNTS; i++) {
+		ns->ucount_max[i] = INT_MAX;
+	}
+	ns->ucounts = ucounts;
 
 	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
 	mutex_lock(&userns_state_mutex);
 	ns->flags = parent_ns->flags;
 	mutex_unlock(&userns_state_mutex);
 
-	set_cred_user_ns(new, ns);
-
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	init_rwsem(&ns->persistent_keyring_register_sem);
 #endif
+	ret = -ENOMEM;
+	if (!setup_userns_sysctls(ns))
+		goto fail_keyring;
+
+	set_cred_user_ns(new, ns);
 	return 0;
+fail_keyring:
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	key_put(ns->persistent_keyring_register);
+#endif
+	ns_free_inum(&ns->ns);
+fail_free:
+	kmem_cache_free(user_ns_cachep, ns);
+fail_dec:
+	dec_user_namespaces(ucounts);
+fail:
+	return ret;
 }
 
 int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
@@ -135,21 +172,30 @@ int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
 	return err;
 }
 
-void free_user_ns(struct user_namespace *ns)
+static void free_user_ns(struct work_struct *work)
 {
-	struct user_namespace *parent;
+	struct user_namespace *parent, *ns =
+		container_of(work, struct user_namespace, work);
 
 	do {
+		struct ucounts *ucounts = ns->ucounts;
 		parent = ns->parent;
+		retire_userns_sysctls(ns);
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 		key_put(ns->persistent_keyring_register);
 #endif
 		ns_free_inum(&ns->ns);
 		kmem_cache_free(user_ns_cachep, ns);
+		dec_user_namespaces(ucounts);
 		ns = parent;
 	} while (atomic_dec_and_test(&parent->count));
 }
-EXPORT_SYMBOL(free_user_ns);
+
+void __put_user_ns(struct user_namespace *ns)
+{
+	schedule_work(&ns->work);
+}
+EXPORT_SYMBOL(__put_user_ns);
 
 static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
 {
@@ -1004,12 +1050,37 @@ static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 	return commit_creds(cred);
 }
 
+struct ns_common *ns_get_owner(struct ns_common *ns)
+{
+	struct user_namespace *my_user_ns = current_user_ns();
+	struct user_namespace *owner, *p;
+
+	/* See if the owner is in the current user namespace */
+	owner = p = ns->ops->owner(ns);
+	for (;;) {
+		if (!p)
+			return ERR_PTR(-EPERM);
+		if (p == my_user_ns)
+			break;
+		p = p->parent;
+	}
+
+	return &get_user_ns(owner)->ns;
+}
+
+static struct user_namespace *userns_owner(struct ns_common *ns)
+{
+	return to_user_ns(ns)->parent;
+}
+
 const struct proc_ns_operations userns_operations = {
 	.name		= "user",
 	.type		= CLONE_NEWUSER,
 	.get		= userns_get,
 	.put		= userns_put,
 	.install	= userns_install,
+	.owner		= userns_owner,
+	.get_parent	= ns_get_owner,
 };
 
 static __init int user_namespaces_init(void)