1 files changed, 218 insertions, 21 deletions

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a5aff94e1f0..db95d8eb761 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -10,12 +10,14 @@
 
 #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>
 #include <linux/slab.h>
-
-#define BITS_PER_PAGE		(PAGE_SIZE*8)
+#include <linux/proc_ns.h>
+#include <linux/reboot.h>
+#include <linux/export.h>
 
 struct pid_cache {
 	int nr_ids;
@@ -68,12 +70,29 @@ err_alloc:
 	return NULL;
 }
 
-static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
+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 user_namespace *user_ns,
+	struct pid_namespace *parent_pid_ns)
 {
 	struct pid_namespace *ns;
 	unsigned int level = parent_pid_ns->level + 1;
 	int i;
+	int err;
 
+	if (level > MAX_PID_NS_LEVEL) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = -ENOMEM;
 	ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
 	if (ns == NULL)
 		goto out;
@@ -86,9 +105,16 @@ 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);
+	ns->nr_hashed = PIDNS_HASH_ADDING;
+	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);
@@ -103,45 +129,71 @@ out_free_map:
 out_free:
 	kmem_cache_free(pid_ns_cachep, ns);
 out:
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(err);
+}
+
+static void delayed_free_pidns(struct rcu_head *p)
+{
+	kmem_cache_free(pid_ns_cachep,
+			container_of(p, struct pid_namespace, rcu));
 }
 
 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);
-	kmem_cache_free(pid_ns_cachep, ns);
+	put_user_ns(ns->user_ns);
+	call_rcu(&ns->rcu, delayed_free_pidns);
 }
 
-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);
 }
 
-void free_pid_ns(struct kref *kref)
+static void free_pid_ns(struct kref *kref)
 {
-	struct pid_namespace *ns, *parent;
+	struct pid_namespace *ns;
 
 	ns = container_of(kref, struct pid_namespace, kref);
-
-	parent = ns->parent;
 	destroy_pid_namespace(ns);
+}
+
+void put_pid_ns(struct pid_namespace *ns)
+{
+	struct pid_namespace *parent;
 
-	if (parent != NULL)
-		put_pid_ns(parent);
+	while (ns != &init_pid_ns) {
+		parent = ns->parent;
+		if (!kref_put(&ns->kref, free_pid_ns))
+			break;
+		ns = parent;
+	}
 }
+EXPORT_SYMBOL_GPL(put_pid_ns);
 
 void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 {
 	int nr;
 	int rc;
-	struct task_struct *task;
+	struct task_struct *task, *me = current;
+	int init_pids = thread_group_leader(me) ? 1 : 2;
+
+	/* Don't allow any more processes into the pid namespace */
+	disable_pid_allocation(pid_ns);
+
+	/* Ignore SIGCHLD causing any terminated children to autoreap */
+	spin_lock_irq(&me->sighand->siglock);
+	me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
+	spin_unlock_irq(&me->sighand->siglock);
 
 	/*
 	 * The last thread in the cgroup-init thread group is terminating.
@@ -161,13 +213,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	while (nr > 0) {
 		rcu_read_lock();
 
-		/*
-		 * Any nested-container's init processes won't ignore the
-		 * SEND_SIG_NOINFO signal, see send_signal()->si_fromuser().
-		 */
 		task = pid_task(find_vpid(nr), PIDTYPE_PID);
-		if (task)
-			send_sig_info(SIGKILL, SEND_SIG_NOINFO, task);
+		if (task && !__fatal_signal_pending(task))
+			send_sig_info(SIGKILL, SEND_SIG_FORCED, task);
 
 		rcu_read_unlock();
 
@@ -175,18 +223,167 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	}
 	read_unlock(&tasklist_lock);
 
+	/* Firstly reap the EXIT_ZOMBIE children we may have. */
 	do {
 		clear_thread_flag(TIF_SIGPENDING);
 		rc = sys_wait4(-1, NULL, __WALL, NULL);
 	} while (rc != -ECHILD);
 
+	/*
+	 * sys_wait4() above can't reap the TASK_DEAD children.
+	 * Make sure they all go away, see free_pid().
+	 */
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (pid_ns->nr_hashed == init_pids)
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (pid_ns->reboot)
+		current->signal->group_exit_code = pid_ns->reboot;
+
 	acct_exit_ns(pid_ns);
 	return;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+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 && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/*
+	 * Writing directly to ns' last_pid field is OK, since this field
+	 * is volatile in a living namespace anyway and a code writing to
+	 * it should synchronize its usage with external means.
+	 */
+
+	tmp.data = &pid_ns->last_pid;
+	return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+}
+
+extern int pid_max;
+static int zero = 0;
+static struct ctl_table pid_ns_ctl_table[] = {
+	{
+		.procname = "ns_last_pid",
+		.maxlen = sizeof(int),
+		.mode = 0666, /* permissions are checked in the handler */
+		.proc_handler = pid_ns_ctl_handler,
+		.extra1 = &zero,
+		.extra2 = &pid_max,
+	},
+	{ }
+};
+static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
+#endif	/* CONFIG_CHECKPOINT_RESTORE */
+
+int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
+{
+	if (pid_ns == &init_pid_ns)
+		return 0;
+
+	switch (cmd) {
+	case LINUX_REBOOT_CMD_RESTART2:
+	case LINUX_REBOOT_CMD_RESTART:
+		pid_ns->reboot = SIGHUP;
+		break;
+
+	case LINUX_REBOOT_CMD_POWER_OFF:
+	case LINUX_REBOOT_CMD_HALT:
+		pid_ns->reboot = SIGINT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	read_lock(&tasklist_lock);
+	force_sig(SIGKILL, pid_ns->child_reaper);
+	read_unlock(&tasklist_lock);
+
+	do_exit(0);
+
+	/* Not reached */
+	return 0;
+}
+
+static void *pidns_get(struct task_struct *task)
+{
+	struct pid_namespace *ns;
+
+	rcu_read_lock();
+	ns = task_active_pid_ns(task);
+	if (ns)
+		get_pid_ns(ns);
+	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) ||
+	    !ns_capable(current_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_for_children);
+	nsproxy->pid_ns_for_children = 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);
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	register_sysctl_paths(kern_path, pid_ns_ctl_table);
+#endif
 	return 0;
 }