Re: [PATCH v3 1/3] sched: Stop nohz stats when decayed

[Peter Zijlstra <peterz@infradead.org>]

On Mon, Feb 12, 2018 at 09:07:52AM +0100, Vincent Guittot wrote:
> @@ -9222,6 +9259,20 @@ void nohz_balance_enter_idle(int cpu)
>  	atomic_inc(&nohz.nr_cpus);
>  
>  	set_cpu_sd_state_idle(cpu);
> +
> +	/*
> +         * Ensures that if nohz_idle_balance() fails to observe our
> +         * @idle_cpus_mask store, it must observe the @has_blocked
> +         * store.
> +         */
> +        smp_mb__after_atomic();
> +
> +out:
> +	/*
> +	 * Each time a cpu enter idle, we assume that it has blocked load and
> +	 * enable the periodic update of the load of idle cpus
> +	 */
> +	WRITE_ONCE(nohz.has_blocked, 1);
>  }
>  #else
>  static inline void nohz_balancer_kick(struct rq *rq) { }

I moved the barrier up one statement, such that its right after the
atomic_inc(). Otherwise people will get all itchy about __after_atomic()
semantics and we really only care about the cpumask_set_cpu() vs
WRITE_ONCE() ordering, so it doesn't really matter _where_ that barrier
lands in between.

> @@ -9374,6 +9425,22 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
>  
>  	SCHED_WARN_ON((flags & NOHZ_KICK_MASK) == NOHZ_BALANCE_KICK);
>  
> +	/*
> +	 * We assume there will be no idle load after this update and clear
> +	 * the has_blocked flag. If a cpu enters idle in the mean time, it will
> +	 * set the has_blocked flag and trig another update of idle load.
> +	 * Because a cpu that becomes idle, is added to idle_cpus_mask before
> +	 * setting the flag, we are sure to not clear the state and not
> +	 * check the load of an idle cpu.
> +	 */
> +	WRITE_ONCE(nohz.has_blocked, 0);
> +
> +	/*
> +         * Ensures that if we miss the CPU, we must see the has_blocked
> +         * store from nohz_balance_enter_idle().
> +         */
> +        smp_mb();
> +
>  	for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
>  		if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
>  			continue;

Fixed that white space damage for you ;-)