Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Eric W. Biederman" <ebiederm@xmission.com>
To:     Luis Chamberlain <mcgrof@kernel.org>
Cc:     Shakeel Butt <shakeelb@google.com>,
        Colin Ian King <colin.king@canonical.com>,
        NeilBrown <neilb@suse.de>, Vasily Averin <vvs@virtuozzo.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Michal Hocko <mhocko@suse.com>,
        Roman Gushchin <roman.gushchin@linux.dev>,
        Linux MM <linux-mm@kvack.org>, netdev@vger.kernel.org,
        "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>, Tejun Heo <tj@kernel.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Eric Dumazet <edumazet@google.com>,
        Kees Cook <keescook@chromium.org>,
        Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>,
        David Ahern <dsahern@kernel.org>, linux-kernel@vger.kernel.org,
        kernel@openvz.org
References: <a5e09e93-106d-0527-5b1e-48dbf3b48b4e@virtuozzo.com>
        <YhzeCkXEvga7+o/A@bombadil.infradead.org>
        <20220301180917.tkibx7zpcz2faoxy@google.com>
        <Yh5lyr8dJXmEoFG6@bombadil.infradead.org>
        <87wnhdwg75.fsf@email.froward.int.ebiederm.org>
        <Yh6PPPqgPxJy+Jvx@bombadil.infradead.org>
Date:   Wed, 02 Mar 2022 08:43:54 -0600
In-Reply-To: <Yh6PPPqgPxJy+Jvx@bombadil.infradead.org> (Luis Chamberlain's
        message of "Tue, 1 Mar 2022 13:25:16 -0800")
Message-ID: <87ilswwh1x.fsf@email.froward.int.ebiederm.org>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.1 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain
Subject: Re: [PATCH RFC] net: memcg accounting for veth devices
Precedence: bulk

Luis Chamberlain <mcgrof@kernel.org> writes:

> On Tue, Mar 01, 2022 at 02:50:06PM -0600, Eric W. Biederman wrote:
>> I really have not looked at this pids controller.
>> 
>> So I am not certain I understand your example here but I hope I have
>> answered your question.
>
> During experimentation with the above stress-ng test case, I saw tons
> of thread just waiting to do exit:

You increment the count of concurrent threads after a no return function
in do_exit.  Since the increment is never reached the count always goes
down and eventually the warning prints.

> diff --git a/kernel/exit.c b/kernel/exit.c
> index 80c4a67d2770..653ca7ebfb58 100644
> --- a/kernel/exit.c
> +++ b/kernel/exit.c
> @@ -730,11 +730,24 @@ static void check_stack_usage(void)
>  static inline void check_stack_usage(void) {}
>  #endif
>  
> +/* Approx more than twice max_threads */
> +#define MAX_EXIT_CONCURRENT (1<<17)
> +static atomic_t exit_concurrent_max = ATOMIC_INIT(MAX_EXIT_CONCURRENT);
> +static DECLARE_WAIT_QUEUE_HEAD(exit_wq);
> +
>  void __noreturn do_exit(long code)
>  {
>  	struct task_struct *tsk = current;
>  	int group_dead;
>  
> +	if (atomic_dec_if_positive(&exit_concurrent_max) < 0) {
> +		pr_warn_ratelimited("exit: exit_concurrent_max (%u) close to 0 (max : %u), throttling...",
> +				    atomic_read(&exit_concurrent_max),
> +				    MAX_EXIT_CONCURRENT);
> +		wait_event(exit_wq,
> +			   atomic_dec_if_positive(&exit_concurrent_max) >= 0);
> +	}
> +
>  	/*
>  	 * We can get here from a kernel oops, sometimes with preemption off.
>  	 * Start by checking for critical errors.
> @@ -881,6 +894,9 @@ void __noreturn do_exit(long code)
>  
>  	lockdep_free_task(tsk);
>  	do_task_dead();

The function do_task_dead never returns.

> +
> +	atomic_inc(&exit_concurrent_max);
> +	wake_up(&exit_wq);
>  }
>  EXPORT_SYMBOL_GPL(do_exit);
>  
> diff --git a/kernel/ucount.c b/kernel/ucount.c
> index 4f5613dac227..980ffaba1ac5 100644
> --- a/kernel/ucount.c
> +++ b/kernel/ucount.c
> @@ -238,6 +238,8 @@ struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
>  		long max;
>  		tns = iter->ns;
>  		max = READ_ONCE(tns->ucount_max[type]);
> +		if (atomic_long_read(&iter->ucount[type]) > max/16)
> +			cond_resched();
>  		if (!atomic_long_inc_below(&iter->ucount[type], max))
>  			goto fail;
>  	}

Eric