[Devel] Re: [PATCH 14/15] Destroy pid namespace on init's death

[Oleg Nesterov]

On 07/30, sukadev at us.ibm.com wrote:
>
> --- lx26-23-rc1-mm1.orig/kernel/exit.c	2007-07-26 20:08:16.000000000 -0700
> +++ lx26-23-rc1-mm1/kernel/exit.c	2007-07-30 23:10:30.000000000 -0700
> @@ -915,6 +915,7 @@ fastcall NORET_TYPE void do_exit(long co
>  {
>  	struct task_struct *tsk = current;
>  	int group_dead;
> +	struct pid_namespace *pid_ns = tsk->nsproxy->pid_ns;
>  
>  	profile_task_exit(tsk);
>  
> @@ -925,9 +926,10 @@ fastcall NORET_TYPE void do_exit(long co
>  	if (unlikely(!tsk->pid))
>  		panic("Attempted to kill the idle task!");
>  	if (unlikely(tsk == task_child_reaper(tsk))) {
> -		if (task_active_pid_ns(tsk) != &init_pid_ns)
> -			task_active_pid_ns(tsk)->child_reaper =
> -					init_pid_ns.child_reaper;
> +		if (pid_ns != &init_pid_ns) {
> +			zap_pid_ns_processes(pid_ns);
> +			pid_ns->child_reaper = init_pid_ns.child_reaper;
> +		}
>  		else
>  			panic("Attempted to kill init!");
>  	}

Just to remind you, this is not right when init is multi-threaded,
we should do this only when the last thread exits.

> -static long do_wait(pid_t pid, int options, struct siginfo __user *infop,
> +long do_wait(pid_t pid, int options, struct siginfo __user *infop,
>  		    int __user *stat_addr, struct rusage __user *ru)

Small nit, other in-kernel reapers use sys_wait4(), perhaps we can use
it too, in that case we don't need to export do_wait().

> +void zap_pid_ns_processes(struct pid_namespace *pid_ns)
> +{
> +	int nr;
> +	int rc;
> +	int options = WEXITED|__WALL;
> +
> +	/*
> +	 * We know pid == 1 is terminating. Find remaining pid_ts
> +	 * in the namespace, signal them and then wait for them
> +	 * exit.
> +	 */
> +	nr = next_pidmap(pid_ns, 1);
> +	while (nr > 0) {
> +		kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
> +		nr = next_pidmap(pid_ns, nr);
> +	}

Without tasklist_lock held this is not reliable.

Oleg.