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:   Fri, 22 May 2020 16:57:07 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     "Ahmed S. Darwish" <a.darwish@linutronix.de>
Cc:     Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        "Paul E. McKenney" <paulmck@kernel.org>,
        "Sebastian A. Siewior" <bigeasy@linutronix.de>,
        Steven Rostedt <rostedt@goodmis.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Konstantin Khlebnikov <khlebnikov@yandex-team.ru>,
        linux-mm@kvack.org
Subject: Re: [PATCH v1 02/25] mm/swap: Don't abuse the seqcount latching API
Message-ID: <20200522145707.GO325280@hirez.programming.kicks-ass.net>
References: <20200519214547.352050-1-a.darwish@linutronix.de>
 <20200519214547.352050-3-a.darwish@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200519214547.352050-3-a.darwish@linutronix.de>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, May 19, 2020 at 11:45:24PM +0200, Ahmed S. Darwish wrote:
> @@ -713,10 +713,20 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
>   */
>  void lru_add_drain_all(void)
>  {

> +	static unsigned int lru_drain_gen;
>  	static struct cpumask has_work;
> +	static DEFINE_MUTEX(lock);
> +	int cpu, this_gen;
>  
>  	/*
>  	 * Make sure nobody triggers this path before mm_percpu_wq is fully
> @@ -725,21 +735,48 @@ void lru_add_drain_all(void)
>  	if (WARN_ON(!mm_percpu_wq))
>  		return;
>  

> +	this_gen = READ_ONCE(lru_drain_gen);
> +	smp_rmb();

	this_gen = smp_load_acquire(&lru_drain_gen);
>  
>  	mutex_lock(&lock);
>  
>  	/*
> +	 * (C) Exit the draining operation if a newer generation, from another
> +	 * lru_add_drain_all(), was already scheduled for draining. Check (A).
>  	 */
> +	if (unlikely(this_gen != lru_drain_gen))
>  		goto done;
>  

> +	WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1);
> +	smp_wmb();

You can leave this smp_wmb() out and rely on the smp_mb() implied by
queue_work_on()'s test_and_set_bit().

>  	cpumask_clear(&has_work);
> -
>  	for_each_online_cpu(cpu) {
>  		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
>  

While you're here, do:

	s/cpumask_set_cpu/__&/

> @@ -766,7 +803,7 @@ void lru_add_drain_all(void)
>  {
>  	lru_add_drain();
>  }
> -#endif
> +#endif /* CONFIG_SMP */
>  
>  /**
>   * release_pages - batched put_page()