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

Pull user namespace changes from Eric Biederman:
 "While small this set of changes is very significant with respect to
  containers in general and user namespaces in particular.  The user
  space interface is now complete.

  This set of changes adds support for unprivileged users to create user
  namespaces and as a user namespace root to create other namespaces.
  The tyranny of supporting suid root preventing unprivileged users from
  using cool new kernel features is broken.

  This set of changes completes the work on setns, adding support for
  the pid, user, mount namespaces.

  This set of changes includes a bunch of basic pid namespace
  cleanups/simplifications.  Of particular significance is the rework of
  the pid namespace cleanup so it no longer requires sending out
  tendrils into all kinds of unexpected cleanup paths for operation.  At
  least one case of broken error handling is fixed by this cleanup.

  The files under /proc/<pid>/ns/ have been converted from regular files
  to magic symlinks which prevents incorrect caching by the VFS,
  ensuring the files always refer to the namespace the process is
  currently using and ensuring that the ptrace_mayaccess permission
  checks are always applied.

  The files under /proc/<pid>/ns/ have been given stable inode numbers
  so it is now possible to see if different processes share the same
  namespaces.

  Through the David Miller's net tree are changes to relax many of the
  permission checks in the networking stack to allowing the user
  namespace root to usefully use the networking stack.  Similar changes
  for the mount namespace and the pid namespace are coming through my
  tree.

  Two small changes to add user namespace support were commited here adn
  in David Miller's -net tree so that I could complete the work on the
  /proc/<pid>/ns/ files in this tree.

  Work remains to make it safe to build user namespaces and 9p, afs,
  ceph, cifs, coda, gfs2, ncpfs, nfs, nfsd, ocfs2, and xfs so the
  Kconfig guard remains in place preventing that user namespaces from
  being built when any of those filesystems are enabled.

  Future design work remains to allow root users outside of the initial
  user namespace to mount more than just /proc and /sys."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (38 commits)
  proc: Usable inode numbers for the namespace file descriptors.
  proc: Fix the namespace inode permission checks.
  proc: Generalize proc inode allocation
  userns: Allow unprivilged mounts of proc and sysfs
  userns: For /proc/self/{uid,gid}_map derive the lower userns from the struct file
  procfs: Print task uids and gids in the userns that opened the proc file
  userns: Implement unshare of the user namespace
  userns: Implent proc namespace operations
  userns: Kill task_user_ns
  userns: Make create_new_namespaces take a user_ns parameter
  userns: Allow unprivileged use of setns.
  userns: Allow unprivileged users to create new namespaces
  userns: Allow setting a userns mapping to your current uid.
  userns: Allow chown and setgid preservation
  userns: Allow unprivileged users to create user namespaces.
  userns: Ignore suid and sgid on binaries if the uid or gid can not be mapped
  userns: fix return value on mntns_install() failure
  vfs: Allow unprivileged manipulation of the mount namespace.
  vfs: Only support slave subtrees across different user namespaces
  vfs: Add a user namespace reference from struct mnt_namespace
  ...

14 files changed, 371 insertions, 115 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f34c41b..9915ffe 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3409,7 +3409,7 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
 {
 	struct cgroup_pidlist *l;
 	/* don't need task_nsproxy() if we're looking at ourself */
-	struct pid_namespace *ns = current->nsproxy->pid_ns;
+	struct pid_namespace *ns = task_active_pid_ns(current);
 
 	/*
 	 * We can't drop the pidlist_mutex before taking the l->mutex in case
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9ff549..301079d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6155,7 +6155,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	event->parent		= parent_event;
 
-	event->ns		= get_pid_ns(current->nsproxy->pid_ns);
+	event->ns		= get_pid_ns(task_active_pid_ns(current));
 	event->id		= atomic64_inc_return(&perf_event_id);
 
 	event->state		= PERF_EVENT_STATE_INACTIVE;
diff --git a/kernel/exit.c b/kernel/exit.c
index 50d2e93..b4df219 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,18 +72,6 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		list_del_rcu(&p->tasks);
 		list_del_init(&p->sibling);
 		__this_cpu_dec(process_counts);
-		/*
-		 * If we are the last child process in a pid namespace to be
-		 * reaped, notify the reaper sleeping zap_pid_ns_processes().
-		 */
-		if (IS_ENABLED(CONFIG_PID_NS)) {
-			struct task_struct *parent = p->real_parent;
-
-			if ((task_active_pid_ns(parent)->child_reaper == parent) &&
-			    list_empty(&parent->children) &&
-			    (parent->flags & PF_EXITING))
-				wake_up_process(parent);
-		}
 	}
 	list_del_rcu(&p->thread_group);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 115d6c2..c36c4e3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1044,8 +1044,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
-	if (clone_flags & CLONE_NEWPID)
-		sig->flags |= SIGNAL_UNKILLABLE;
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
@@ -1438,8 +1436,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
 
 		if (thread_group_leader(p)) {
-			if (is_child_reaper(pid))
-				p->nsproxy->pid_ns->child_reaper = p;
+			if (is_child_reaper(pid)) {
+				ns_of_pid(pid)->child_reaper = p;
+				p->signal->flags |= SIGNAL_UNKILLABLE;
+			}
 
 			p->signal->leader_pid = pid;
 			p->signal->tty = tty_kref_get(current->signal->tty);
@@ -1473,8 +1473,6 @@ bad_fork_cleanup_io:
 	if (p->io_context)
 		exit_io_context(p);
 bad_fork_cleanup_namespaces:
-	if (unlikely(clone_flags & CLONE_NEWPID))
-		pid_ns_release_proc(p->nsproxy->pid_ns);
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm)
@@ -1554,15 +1552,9 @@ long do_fork(unsigned long clone_flags,
 	 * Do some preliminary argument and permissions checking before we
 	 * actually start allocating stuff
 	 */
-	if (clone_flags & CLONE_NEWUSER) {
-		if (clone_flags & CLONE_THREAD)
+	if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) {
+		if (clone_flags & (CLONE_THREAD|CLONE_PARENT))
 			return -EINVAL;
-		/* hopefully this check will go away when userns support is
-		 * complete
-		 */
-		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
-				!capable(CAP_SETGID))
-			return -EPERM;
 	}
 
 	/*
@@ -1724,7 +1716,8 @@ static int check_unshare_flags(unsigned long unshare_flags)
 {
 	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
 				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
-				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
+				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
+				CLONE_NEWUSER|CLONE_NEWPID))
 		return -EINVAL;
 	/*
 	 * Not implemented, but pretend it works if there is nothing to
@@ -1791,19 +1784,40 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
 	struct fs_struct *fs, *new_fs = NULL;
 	struct files_struct *fd, *new_fd = NULL;
+	struct cred *new_cred = NULL;
 	struct nsproxy *new_nsproxy = NULL;
 	int do_sysvsem = 0;
 	int err;
 
-	err = check_unshare_flags(unshare_flags);
-	if (err)
-		goto bad_unshare_out;
-
+	/*
+	 * If unsharing a user namespace must also unshare the thread.
+	 */
+	if (unshare_flags & CLONE_NEWUSER)
+		unshare_flags |= CLONE_THREAD;
+	/*
+	 * If unsharing a pid namespace must also unshare the thread.
+	 */
+	if (unshare_flags & CLONE_NEWPID)
+		unshare_flags |= CLONE_THREAD;
+	/*
+	 * If unsharing a thread from a thread group, must also unshare vm.
+	 */
+	if (unshare_flags & CLONE_THREAD)
+		unshare_flags |= CLONE_VM;
+	/*
+	 * If unsharing vm, must also unshare signal handlers.
+	 */
+	if (unshare_flags & CLONE_VM)
+		unshare_flags |= CLONE_SIGHAND;
 	/*
 	 * If unsharing namespace, must also unshare filesystem information.
 	 */
 	if (unshare_flags & CLONE_NEWNS)
 		unshare_flags |= CLONE_FS;
+
+	err = check_unshare_flags(unshare_flags);
+	if (err)
+		goto bad_unshare_out;
 	/*
 	 * CLONE_NEWIPC must also detach from the undolist: after switching
 	 * to a new ipc namespace, the semaphore arrays from the old
@@ -1817,11 +1831,15 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	err = unshare_fd(unshare_flags, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
-	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs);
+	err = unshare_userns(unshare_flags, &new_cred);
 	if (err)
 		goto bad_unshare_cleanup_fd;
+	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
+					 new_cred, new_fs);
+	if (err)
+		goto bad_unshare_cleanup_cred;
 
-	if (new_fs || new_fd || do_sysvsem || new_nsproxy) {
+	if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
 		if (do_sysvsem) {
 			/*
 			 * CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1854,11 +1872,20 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 		}
 
 		task_unlock(current);
+
+		if (new_cred) {
+			/* Install the new user namespace */
+			commit_creds(new_cred);
+			new_cred = NULL;
+		}
 	}
 
 	if (new_nsproxy)
 		put_nsproxy(new_nsproxy);
 
+bad_unshare_cleanup_cred:
+	if (new_cred)
+		put_cred(new_cred);
 bad_unshare_cleanup_fd:
 	if (new_fd)
 		put_files_struct(new_fd);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 7e1c3de..78e2ecb 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -57,7 +57,8 @@ static inline struct nsproxy *create_nsproxy(void)
  * leave it to the caller to do proper locking and attach it to task.
  */
 static struct nsproxy *create_new_namespaces(unsigned long flags,
-			struct task_struct *tsk, struct fs_struct *new_fs)
+	struct task_struct *tsk, struct user_namespace *user_ns,
+	struct fs_struct *new_fs)
 {
 	struct nsproxy *new_nsp;
 	int err;
@@ -66,31 +67,31 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	if (!new_nsp)
 		return ERR_PTR(-ENOMEM);
 
-	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, new_fs);
+	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
 	if (IS_ERR(new_nsp->mnt_ns)) {
 		err = PTR_ERR(new_nsp->mnt_ns);
 		goto out_ns;
 	}
 
-	new_nsp->uts_ns = copy_utsname(flags, tsk);
+	new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
 	if (IS_ERR(new_nsp->uts_ns)) {
 		err = PTR_ERR(new_nsp->uts_ns);
 		goto out_uts;
 	}
 
-	new_nsp->ipc_ns = copy_ipcs(flags, tsk);
+	new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
 	if (IS_ERR(new_nsp->ipc_ns)) {
 		err = PTR_ERR(new_nsp->ipc_ns);
 		goto out_ipc;
 	}
 
-	new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
+	new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns);
 	if (IS_ERR(new_nsp->pid_ns)) {
 		err = PTR_ERR(new_nsp->pid_ns);
 		goto out_pid;
 	}
 
-	new_nsp->net_ns = copy_net_ns(flags, task_cred_xxx(tsk, user_ns), tsk->nsproxy->net_ns);
+	new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
 	if (IS_ERR(new_nsp->net_ns)) {
 		err = PTR_ERR(new_nsp->net_ns);
 		goto out_net;
@@ -122,6 +123,7 @@ out_ns:
 int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 {
 	struct nsproxy *old_ns = tsk->nsproxy;
+	struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
 	struct nsproxy *new_ns;
 	int err = 0;
 
@@ -134,7 +136,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 				CLONE_NEWPID | CLONE_NEWNET)))
 		return 0;
 
-	if (!capable(CAP_SYS_ADMIN)) {
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN)) {
 		err = -EPERM;
 		goto out;
 	}
@@ -151,7 +153,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 		goto out;
 	}
 
-	new_ns = create_new_namespaces(flags, tsk, tsk->fs);
+	new_ns = create_new_namespaces(flags, tsk,
+				       task_cred_xxx(tsk, user_ns), tsk->fs);
 	if (IS_ERR(new_ns)) {
 		err = PTR_ERR(new_ns);
 		goto out;
@@ -183,19 +186,21 @@ void free_nsproxy(struct nsproxy *ns)
  * On success, returns the new nsproxy.
  */
 int unshare_nsproxy_namespaces(unsigned long unshare_flags,
-		struct nsproxy **new_nsp, struct fs_struct *new_fs)
+	struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
 {
+	struct user_namespace *user_ns;
 	int err = 0;
 
 	if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-			       CLONE_NEWNET)))
+			       CLONE_NEWNET | CLONE_NEWPID)))
 		return 0;
 
-	if (!capable(CAP_SYS_ADMIN))
+	user_ns = new_cred ? new_cred->user_ns : current_user_ns();
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	*new_nsp = create_new_namespaces(unshare_flags, current,
-				new_fs ? new_fs : current->fs);
+	*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
+					 new_fs ? new_fs : current->fs);
 	if (IS_ERR(*new_nsp)) {
 		err = PTR_ERR(*new_nsp);
 		goto out;
@@ -241,9 +246,6 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 	struct file *file;
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	file = proc_ns_fget(fd);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
@@ -254,7 +256,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 	if (nstype && (ops->type != nstype))
 		goto out;
 
-	new_nsproxy = create_new_namespaces(0, tsk, tsk->fs);
+	new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
 	if (IS_ERR(new_nsproxy)) {
 		err = PTR_ERR(new_nsproxy);
 		goto out;
diff --git a/kernel/pid.c b/kernel/pid.c
index fd996c1..3e2cf81 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -36,6 +36,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/init_task.h>
 #include <linux/syscalls.h>
+#include <linux/proc_fs.h>
 
 #define pid_hashfn(nr, ns)	\
 	hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
@@ -78,6 +79,8 @@ struct pid_namespace init_pid_ns = {
 	.last_pid = 0,
 	.level = 0,
 	.child_reaper = &init_task,
+	.user_ns = &init_user_ns,
+	.proc_inum = PROC_PID_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
@@ -269,8 +272,24 @@ void free_pid(struct pid *pid)
 	unsigned long flags;
 
 	spin_lock_irqsave(&pidmap_lock, flags);
-	for (i = 0; i <= pid->level; i++)
-		hlist_del_rcu(&pid->numbers[i].pid_chain);
+	for (i = 0; i <= pid->level; i++) {
+		struct upid *upid = pid->numbers + i;
+		struct pid_namespace *ns = upid->ns;
+		hlist_del_rcu(&upid->pid_chain);
+		switch(--ns->nr_hashed) {
+		case 1:
+			/* When all that is left in the pid namespace
+			 * is the reaper wake up the reaper.  The reaper
+			 * may be sleeping in zap_pid_ns_processes().
+			 */
+			wake_up_process(ns->child_reaper);
+			break;
+		case 0:
+			ns->nr_hashed = -1;
+			schedule_work(&ns->proc_work);
+			break;
+		}
+	}
 	spin_unlock_irqrestore(&pidmap_lock, flags);
 
 	for (i = 0; i <= pid->level; i++)
@@ -292,6 +311,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		goto out;
 
 	tmp = ns;
+	pid->level = ns->level;
 	for (i = ns->level; i >= 0; i--) {
 		nr = alloc_pidmap(tmp);
 		if (nr < 0)
@@ -302,22 +322,32 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		tmp = tmp->parent;
 	}
 
+	if (unlikely(is_child_reaper(pid))) {
+		if (pid_ns_prepare_proc(ns))
+			goto out_free;
+	}
+
 	get_pid_ns(ns);
-	pid->level = ns->level;
 	atomic_set(&pid->count, 1);
 	for (type = 0; type < PIDTYPE_MAX; ++type)
 		INIT_HLIST_HEAD(&pid->tasks[type]);
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
-	for ( ; upid >= pid->numbers; --upid)
+	if (ns->nr_hashed < 0)
+		goto out_unlock;
+	for ( ; upid >= pid->numbers; --upid) {
 		hlist_add_head_rcu(&upid->pid_chain,
 				&pid_hash[pid_hashfn(upid->nr, upid->ns)]);
+		upid->ns->nr_hashed++;
+	}
 	spin_unlock_irq(&pidmap_lock);
 
 out:
 	return pid;
 
+out_unlock:
+	spin_unlock(&pidmap_lock);
 out_free:
 	while (++i <= ns->level)
 		free_pidmap(pid->numbers + i);
@@ -344,7 +374,7 @@ EXPORT_SYMBOL_GPL(find_pid_ns);
 
 struct pid *find_vpid(int nr)
 {
-	return find_pid_ns(nr, current->nsproxy->pid_ns);
+	return find_pid_ns(nr, task_active_pid_ns(current));
 }
 EXPORT_SYMBOL_GPL(find_vpid);
 
@@ -428,7 +458,7 @@ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 
 struct task_struct *find_task_by_vpid(pid_t vnr)
 {
-	return find_task_by_pid_ns(vnr, current->nsproxy->pid_ns);
+	return find_task_by_pid_ns(vnr, task_active_pid_ns(current));
 }
 
 struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
@@ -483,7 +513,7 @@ EXPORT_SYMBOL_GPL(pid_nr_ns);
 
 pid_t pid_vnr(struct pid *pid)
 {
-	return pid_nr_ns(pid, current->nsproxy->pid_ns);
+	return pid_nr_ns(pid, task_active_pid_ns(current));
 }
 EXPORT_SYMBOL_GPL(pid_vnr);
 
@@ -494,7 +524,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 
 	rcu_read_lock();
 	if (!ns)
-		ns = current->nsproxy->pid_ns;
+		ns = task_active_pid_ns(current);
 	if (likely(pid_alive(task))) {
 		if (type != PIDTYPE_PID)
 			task = task->group_leader;
@@ -569,6 +599,7 @@ void __init pidmap_init(void)
 	/* Reserve PID 0. We never call free_pidmap(0) */
 	set_bit(0, init_pid_ns.pidmap[0].page);
 	atomic_dec(&init_pid_ns.pidmap[0].nr_free);
+	init_pid_ns.nr_hashed = 1;
 
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 7b07cc0d..560da0d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -10,6 +10,7 @@
 
 #include <linux/pid.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/err.h>
 #include <linux/acct.h>
@@ -71,10 +72,17 @@ err_alloc:
 	return NULL;
 }
 
+static void proc_cleanup_work(struct work_struct *work)
+{
+	struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
+	pid_ns_release_proc(ns);
+}
+
 /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
 #define MAX_PID_NS_LEVEL 32
 
-static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
+static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns,
+	struct pid_namespace *parent_pid_ns)
 {
 	struct pid_namespace *ns;
 	unsigned int level = parent_pid_ns->level + 1;
@@ -99,9 +107,15 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p
 	if (ns->pid_cachep == NULL)
 		goto out_free_map;
 
+	err = proc_alloc_inum(&ns->proc_inum);
+	if (err)
+		goto out_free_map;
+
 	kref_init(&ns->kref);
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
+	ns->user_ns = get_user_ns(user_ns);
+	INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
 	set_bit(0, ns->pidmap[0].page);
 	atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
@@ -109,14 +123,8 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p
 	for (i = 1; i < PIDMAP_ENTRIES; i++)
 		atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
 
-	err = pid_ns_prepare_proc(ns);
-	if (err)
-		goto out_put_parent_pid_ns;
-
 	return ns;
 
-out_put_parent_pid_ns:
-	put_pid_ns(parent_pid_ns);
 out_free_map:
 	kfree(ns->pidmap[0].page);
 out_free:
@@ -129,18 +137,21 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 {
 	int i;
 
+	proc_free_inum(ns->proc_inum);
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
+	put_user_ns(ns->user_ns);
 	kmem_cache_free(pid_ns_cachep, ns);
 }
 
-struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
+struct pid_namespace *copy_pid_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct pid_namespace *old_ns)
 {
 	if (!(flags & CLONE_NEWPID))
 		return get_pid_ns(old_ns);
-	if (flags & (CLONE_THREAD|CLONE_PARENT))
+	if (task_active_pid_ns(current) != old_ns)
 		return ERR_PTR(-EINVAL);
-	return create_pid_namespace(old_ns);
+	return create_pid_namespace(user_ns, old_ns);
 }
 
 static void free_pid_ns(struct kref *kref)
@@ -211,22 +222,15 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 
 	/*
 	 * sys_wait4() above can't reap the TASK_DEAD children.
-	 * Make sure they all go away, see __unhash_process().
+	 * Make sure they all go away, see free_pid().
 	 */
 	for (;;) {
-		bool need_wait = false;
-
-		read_lock(&tasklist_lock);
-		if (!list_empty(&current->children)) {
-			__set_current_state(TASK_UNINTERRUPTIBLE);
-			need_wait = true;
-		}
-		read_unlock(&tasklist_lock);
-
-		if (!need_wait)
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (pid_ns->nr_hashed == 1)
 			break;
 		schedule();
 	}
+	__set_current_state(TASK_RUNNING);
 
 	if (pid_ns->reboot)
 		current->signal->group_exit_code = pid_ns->reboot;
@@ -239,9 +243,10 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 static int pid_ns_ctl_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct pid_namespace *pid_ns = task_active_pid_ns(current);
 	struct ctl_table tmp = *table;
 
-	if (write && !capable(CAP_SYS_ADMIN))
+	if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
@@ -250,7 +255,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
 	 * it should synchronize its usage with external means.
 	 */
 
-	tmp.data = &current->nsproxy->pid_ns->last_pid;
+	tmp.data = &pid_ns->last_pid;
 	return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 }
 
@@ -299,6 +304,67 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
 	return 0;
 }
 
+static void *pidns_get(struct task_struct *task)
+{
+	struct pid_namespace *ns;
+
+	rcu_read_lock();
+	ns = get_pid_ns(task_active_pid_ns(task));
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void pidns_put(void *ns)
+{
+	put_pid_ns(ns);
+}
+
+static int pidns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct pid_namespace *active = task_active_pid_ns(current);
+	struct pid_namespace *ancestor, *new = ns;
+
+	if (!ns_capable(new->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/*
+	 * Only allow entering the current active pid namespace
+	 * or a child of the current active pid namespace.
+	 *
+	 * This is required for fork to return a usable pid value and
+	 * this maintains the property that processes and their
+	 * children can not escape their current pid namespace.
+	 */
+	if (new->level < active->level)
+		return -EINVAL;
+
+	ancestor = new;
+	while (ancestor->level > active->level)
+		ancestor = ancestor->parent;
+	if (ancestor != active)
+		return -EINVAL;
+
+	put_pid_ns(nsproxy->pid_ns);
+	nsproxy->pid_ns = get_pid_ns(new);
+	return 0;
+}
+
+static unsigned int pidns_inum(void *ns)
+{
+	struct pid_namespace *pid_ns = ns;
+	return pid_ns->proc_inum;
+}
+
+const struct proc_ns_operations pidns_operations = {
+	.name		= "pid",
+	.type		= CLONE_NEWPID,
+	.get		= pidns_get,
+	.put		= pidns_put,
+	.install	= pidns_install,
+	.inum		= pidns_inum,
+};
+
 static __init int pid_namespaces_init(void)
 {
 	pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1f5e55d..7b09b88 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -215,8 +215,12 @@ ok:
 	smp_rmb();
 	if (task->mm)
 		dumpable = get_dumpable(task->mm);
-	if (!dumpable  && !ptrace_has_cap(task_user_ns(task), mode))
+	rcu_read_lock();
+	if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+		rcu_read_unlock();
 		return -EPERM;
+	}
+	rcu_read_unlock();
 
 	return security_ptrace_access_check(task, mode);
 }
@@ -280,8 +284,10 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	if (seize)
 		flags |= PT_SEIZED;
-	if (ns_capable(task_user_ns(task), CAP_SYS_PTRACE))
+	rcu_read_lock();
+	if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
 		flags |= PT_PTRACE_CAP;
+	rcu_read_unlock();
 	task->ptrace = flags;
 
 	__ptrace_link(task, current);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c1fb821..257002c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4097,8 +4097,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		goto out_free_cpus_allowed;
 	}
 	retval = -EPERM;
-	if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE))
-		goto out_unlock;
+	if (!check_same_owner(p)) {
+		rcu_read_lock();
+		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
+			rcu_read_unlock();
+			goto out_unlock;
+		}
+		rcu_read_unlock();
+	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
diff --git a/kernel/signal.c b/kernel/signal.c
index a49c7f3..580a91e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1753,7 +1753,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	 * see comment in do_notify_parent() about the following 4 lines
 	 */
 	rcu_read_lock();
-	info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns);
+	info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent));
 	info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk));
 	rcu_read_unlock();
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 65bdcf1..5a63844 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1344,7 +1344,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 		goto out_putname;
 	}
 
-	mnt = current->nsproxy->pid_ns->proc_mnt;
+	mnt = task_active_pid_ns(current)->proc_mnt;
 	file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
 	result = PTR_ERR(file);
 	if (IS_ERR(file))
diff --git a/kernel/user.c b/kernel/user.c
index 750acff..33acb5e 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
 
 /*
  * userns count is 1 for root user, 1 for init_uts_ns,
@@ -51,6 +52,7 @@ struct user_namespace init_user_ns = {
 	},
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
+	.proc_inum = PROC_USER_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 456a6b9..f5975cc 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,6 +9,7 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
 #include <linux/highuid.h>
 #include <linux/cred.h>
 #include <linux/securebits.h>
@@ -26,6 +27,24 @@ static struct kmem_cache *user_ns_cachep __read_mostly;
 static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *map);
 
+static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
+{
+	/* Start with the same capabilities as init but useless for doing
+	 * anything as the capabilities are bound to the new user namespace.
+	 */
+	cred->securebits = SECUREBITS_DEFAULT;
+	cred->cap_inheritable = CAP_EMPTY_SET;
+	cred->cap_permitted = CAP_FULL_SET;
+	cred->cap_effective = CAP_FULL_SET;
+	cred->cap_bset = CAP_FULL_SET;
+#ifdef CONFIG_KEYS
+	key_put(cred->request_key_auth);
+	cred->request_key_auth = NULL;
+#endif
+	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
+	cred->user_ns = user_ns;
+}
+
 /*
  * Create a new user namespace, deriving the creator from the user in the
  * passed credentials, and replacing that user with the new root user for the
@@ -39,6 +58,7 @@ 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;
 
 	/* The creator needs a mapping in the parent user namespace
 	 * or else we won't be able to reasonably tell userspace who
@@ -52,38 +72,45 @@ int create_user_ns(struct cred *new)
 	if (!ns)
 		return -ENOMEM;
 
+	ret = proc_alloc_inum(&ns->proc_inum);
+	if (ret) {
+		kmem_cache_free(user_ns_cachep, ns);
+		return ret;
+	}
+
 	kref_init(&ns->kref);
+	/* Leave the new->user_ns reference with the new user namespace. */
 	ns->parent = parent_ns;
 	ns->owner = owner;
 	ns->group = group;
 
-	/* Start with the same capabilities as init but useless for doing
-	 * anything as the capabilities are bound to the new user namespace.
-	 */
-	new->securebits = SECUREBITS_DEFAULT;
-	new->cap_inheritable = CAP_EMPTY_SET;
-	new->cap_permitted = CAP_FULL_SET;
-	new->cap_effective = CAP_FULL_SET;
-	new->cap_bset = CAP_FULL_SET;
-#ifdef CONFIG_KEYS
-	key_put(new->request_key_auth);
-	new->request_key_auth = NULL;
-#endif
-	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
-
-	/* Leave the new->user_ns reference with the new user namespace. */
-	/* Leave the reference to our user_ns with the new cred. */
-	new->user_ns = ns;
+	set_cred_user_ns(new, ns);
 
 	return 0;
 }
 
+int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
+{
+	struct cred *cred;
+
+	if (!(unshare_flags & CLONE_NEWUSER))
+		return 0;
+
+	cred = prepare_creds();
+	if (!cred)
+		return -ENOMEM;
+
+	*new_cred = cred;
+	return create_user_ns(cred);
+}
+
 void free_user_ns(struct kref *kref)
 {
 	struct user_namespace *parent, *ns =
 		container_of(kref, struct user_namespace, kref);
 
 	parent = ns->parent;
+	proc_free_inum(ns->proc_inum);
 	kmem_cache_free(user_ns_cachep, ns);
 	put_user_ns(parent);
 }
@@ -372,7 +399,7 @@ static int uid_m_show(struct seq_file *seq, void *v)
 	struct user_namespace *lower_ns;
 	uid_t lower;
 
-	lower_ns = current_user_ns();
+	lower_ns = seq_user_ns(seq);
 	if ((lower_ns == ns) && lower_ns->parent)
 		lower_ns = lower_ns->parent;
 
@@ -393,7 +420,7 @@ static int gid_m_show(struct seq_file *seq, void *v)
 	struct user_namespace *lower_ns;
 	gid_t lower;
 
-	lower_ns = current_user_ns();
+	lower_ns = seq_user_ns(seq);
 	if ((lower_ns == ns) && lower_ns->parent)
 		lower_ns = lower_ns->parent;
 
@@ -669,10 +696,14 @@ ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t siz
 {
 	struct seq_file *seq = file->private_data;
 	struct user_namespace *ns = seq->private;
+	struct user_namespace *seq_ns = seq_user_ns(seq);
 
 	if (!ns->parent)
 		return -EPERM;
 
+	if ((seq_ns != ns) && (seq_ns != ns->parent))
+		return -EPERM;
+
 	return map_write(file, buf, size, ppos, CAP_SETUID,
 			 &ns->uid_map, &ns->parent->uid_map);
 }
@@ -681,10 +712,14 @@ ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t siz
 {
 	struct seq_file *seq = file->private_data;
 	struct user_namespace *ns = seq->private;
+	struct user_namespace *seq_ns = seq_user_ns(seq);
 
 	if (!ns->parent)
 		return -EPERM;
 
+	if ((seq_ns != ns) && (seq_ns != ns->parent))
+		return -EPERM;
+
 	return map_write(file, buf, size, ppos, CAP_SETGID,
 			 &ns->gid_map, &ns->parent->gid_map);
 }
@@ -709,6 +744,21 @@ ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t
 static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *new_map)
 {
+	/* Allow mapping to your own filesystem ids */
+	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) {
+		u32 id = new_map->extent[0].lower_first;
+		if (cap_setid == CAP_SETUID) {
+			kuid_t uid = make_kuid(ns->parent, id);
+			if (uid_eq(uid, current_fsuid()))
+				return true;
+		}
+		else if (cap_setid == CAP_SETGID) {
+			kgid_t gid = make_kgid(ns->parent, id);
+			if (gid_eq(gid, current_fsgid()))
+				return true;
+		}
+	}
+
 	/* Allow anyone to set a mapping that doesn't require privilege */
 	if (!cap_valid(cap_setid))
 		return true;
@@ -722,6 +772,65 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 	return false;
 }
 
+static void *userns_get(struct task_struct *task)
+{
+	struct user_namespace *user_ns;
+
+	rcu_read_lock();
+	user_ns = get_user_ns(__task_cred(task)->user_ns);
+	rcu_read_unlock();
+
+	return user_ns;
+}
+
+static void userns_put(void *ns)
+{
+	put_user_ns(ns);
+}
+
+static int userns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct user_namespace *user_ns = ns;
+	struct cred *cred;
+
+	/* Don't allow gaining capabilities by reentering
+	 * the same user namespace.
+	 */
+	if (user_ns == current_user_ns())
+		return -EINVAL;
+
+	/* Threaded many not enter a different user namespace */
+	if (atomic_read(&current->mm->mm_users) > 1)
+		return -EINVAL;
+
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	cred = prepare_creds();
+	if (!cred)
+		return -ENOMEM;
+
+	put_user_ns(cred->user_ns);
+	set_cred_user_ns(cred, get_user_ns(user_ns));
+
+	return commit_creds(cred);
+}
+
+static unsigned int userns_inum(void *ns)
+{
+	struct user_namespace *user_ns = ns;
+	return user_ns->proc_inum;
+}
+
+const struct proc_ns_operations userns_operations = {
+	.name		= "user",
+	.type		= CLONE_NEWUSER,
+	.get		= userns_get,
+	.put		= userns_put,
+	.install	= userns_install,
+	.inum		= userns_inum,
+};
+
 static __init int user_namespaces_init(void)
 {
 	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 679d97a..f6336d5 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -32,18 +32,25 @@ static struct uts_namespace *create_uts_ns(void)
  * @old_ns: namespace to clone
  * Return NULL on error (failure to kmalloc), new ns otherwise
  */
-static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
+static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 					  struct uts_namespace *old_ns)
 {
 	struct uts_namespace *ns;
+	int err;
 
 	ns = create_uts_ns();
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
 
+	err = proc_alloc_inum(&ns->proc_inum);
+	if (err) {
+		kfree(ns);
+		return ERR_PTR(err);
+	}
+
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
-	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns));
+	ns->user_ns = get_user_ns(user_ns);
 	up_read(&uts_sem);
 	return ns;
 }
@@ -55,9 +62,8 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
  * versa.
  */
 struct uts_namespace *copy_utsname(unsigned long flags,
-				   struct task_struct *tsk)
+	struct user_namespace *user_ns, struct uts_namespace *old_ns)
 {
-	struct uts_namespace *old_ns = tsk->nsproxy->uts_ns;
 	struct uts_namespace *new_ns;
 
 	BUG_ON(!old_ns);
@@ -66,7 +72,7 @@ struct uts_namespace *copy_utsname(unsigned long flags,
 	if (!(flags & CLONE_NEWUTS))
 		return old_ns;
 
-	new_ns = clone_uts_ns(tsk, old_ns);
+	new_ns = clone_uts_ns(user_ns, old_ns);
 
 	put_uts_ns(old_ns);
 	return new_ns;
@@ -78,6 +84,7 @@ void free_uts_ns(struct kref *kref)
 
 	ns = container_of(kref, struct uts_namespace, kref);
 	put_user_ns(ns->user_ns);
+	proc_free_inum(ns->proc_inum);
 	kfree(ns);
 }
 
@@ -102,19 +109,31 @@ static void utsns_put(void *ns)
 	put_uts_ns(ns);
 }
 
-static int utsns_install(struct nsproxy *nsproxy, void *ns)
+static int utsns_install(struct nsproxy *nsproxy, void *new)
 {
+	struct uts_namespace *ns = new;
+
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
 	get_uts_ns(ns);
 	put_uts_ns(nsproxy->uts_ns);
 	nsproxy->uts_ns = ns;
 	return 0;
 }
 
+static unsigned int utsns_inum(void *vp)
+{
+	struct uts_namespace *ns = vp;
+
+	return ns->proc_inum;
+}
+
 const struct proc_ns_operations utsns_operations = {
 	.name		= "uts",
 	.type		= CLONE_NEWUTS,
 	.get		= utsns_get,
 	.put		= utsns_put,
 	.install	= utsns_install,
+	.inum		= utsns_inum,
 };
-