Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 29 Sep 2021 13:54:17 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Thomas Gleixner <tglx@linutronix.de>
Cc:     LKML <linux-kernel@vger.kernel.org>,
        Ingo Molnar <mingo@kernel.org>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Andy Lutomirski <luto@amacapital.net>
Subject: Re: [patch 4/5] sched: Delay task stack freeing on RT
Message-ID: <YVRT6QbX5zwiIJkI@hirez.programming.kicks-ass.net>
References: <20210928122339.502270600@linutronix.de>
 <20210928122411.593486363@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210928122411.593486363@linutronix.de>
Precedence: bulk

On Tue, Sep 28, 2021 at 02:24:30PM +0200, Thomas Gleixner wrote:

> --- a/kernel/exit.c
> +++ b/kernel/exit.c
> @@ -172,6 +172,11 @@ static void delayed_put_task_struct(stru
>  	kprobe_flush_task(tsk);
>  	perf_event_delayed_put(tsk);
>  	trace_sched_process_free(tsk);
> +
> +	/* RT enabled kernels delay freeing the VMAP'ed task stack */
> +	if (IS_ENABLED(CONFIG_PREEMPT_RT))
> +		put_task_stack(tsk);
> +
>  	put_task_struct(tsk);
>  }

> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -4846,8 +4846,12 @@ static struct rq *finish_task_switch(str
>  		if (prev->sched_class->task_dead)
>  			prev->sched_class->task_dead(prev);
>  
> -		/* Task is done with its stack. */
> -		put_task_stack(prev);
> +		/*
> +		 * Release VMAP'ed task stack immediate for reuse. On RT
> +		 * enabled kernels this is delayed for latency reasons.
> +		 */
> +		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
> +			put_task_stack(prev);
>  
>  		put_task_struct_rcu_user(prev);
>  	}


Having this logic split across two files seems unfortunate and prone to
'accidents'. Is there a real down-side to unconditionally doing it in
delayed_put_task_struct() ?

/me goes out for lunch... meanwhile tglx points at: 68f24b08ee89.

Bah.. Andy?