Re: [PATCH] proc: readdir race fix

[Oleg Nesterov <oleg@tv-sign.ru>]

On 09/04, Eric W. Biederman wrote:
> 
> -static struct task_struct *next_tgid(struct task_struct *start)
> -{
> -	struct task_struct *pos;
> +	task = NULL;
>  	rcu_read_lock();
> -	pos = start;
> -	if (pid_alive(start))
> -		pos = next_task(start);
> -	if (pid_alive(pos) && (pos != &init_task)) {
> -		get_task_struct(pos);
> -		goto done;
> +retry:
> +	pid = find_next_pid(tgid);
> +	if (pid) {
> +		tgid = pid->nr + 1;
> +		task = pid_task(pid, PIDTYPE_PID);
> +		if (!task || !thread_group_leader(task))
                              ^^^^^^^^^^^^^^^^^^^
There is a window while de_thread() switches leadership, so next_tgid()
may skip a task doing exec. What do you think about

                             // needs a comment
		if (!task || task->pid != task->tgid)
			goto retry;

instead? Currently first_tgid() has the same (very minor) problem.

> +			goto retry;
> +		get_task_struct(task);
>  	}
> -	pos = NULL;
> -done:
>  	rcu_read_unlock();
> -	put_task_struct(start);
> -	return pos;
> +	return task;
> +
>  }

Emply line before '}'

> +struct pid *find_next_pid(int nr)
> +{
> +	struct pid *next;
> +
> +	next = find_pid(nr);
> +	while (!next) {
> +		nr = next_pidmap(nr);
> +		if (nr <= 0)
> +			break;
> +		next = find_pid(nr);
> +	}
> +	return next;
> +}

This is strange that we are doing find_pid() before and at the end of loop,
I'd suggest this code:

	struct pid *find_next_pid(int nr)
	{
		struct pid *pid;

		do {
			pid = find_pid(nr);
			if (pid != NULL)
				break;
			nr = next_pidmap(nr);
		} while (nr > 0);

		return pid;
	}

Imho, a bit easier to read.

Oleg.