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
  ...

1 files changed, 89 insertions, 23 deletions

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);