signals: zap_pid_ns_process() should use force_sig()

send_signal() assumes that signals with SEND_SIG_PRIV are generated from
within the same namespace.  So any nested container-init processes become
immune to the SIGKILL generated by kill_proc_info() in
zap_pid_ns_processes().

Use force_sig() in zap_pid_ns_processes() instead - force_sig() clears the
SIGNAL_UNKILLABLE flag ensuring the signal is processed by
container-inits.
Signed-off-by: NSukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Roland McGrath <roland@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Daniel Lezcano <daniel.lezcano@free.fr>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

kernel/pid_namespace.c

@@ -152,6 +152,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 {
 	int nr;
 	int rc;
+	struct task_struct *task;
 
 	/*
 	 * The last thread in the cgroup-init thread group is terminating.
@@ -169,7 +170,19 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	read_lock(&tasklist_lock);
 	nr = next_pidmap(pid_ns, 1);
 	while (nr > 0) {
-		kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
+		rcu_read_lock();
+
+		/*
+		 * Use force_sig() since it clears SIGNAL_UNKILLABLE ensuring
+		 * any nested-container's init processes don't ignore the
+		 * signal
+		 */
+		task = pid_task(find_vpid(nr), PIDTYPE_PID);
+		if (task)
+			force_sig(SIGKILL, task);
+
+		rcu_read_unlock();
+
 		nr = next_pidmap(pid_ns, nr);
 	}
 	read_unlock(&tasklist_lock);