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:   Tue, 30 Jun 2020 19:07:51 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Qais Yousef <qais.yousef@arm.com>
Cc:     Ingo Molnar <mingo@redhat.com>,
        Valentin Schneider <valentin.schneider@arm.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Patrick Bellasi <patrick.bellasi@matbug.net>,
        Chris Redpath <chris.redpath@arm.com>,
        Lukasz Luba <lukasz.luba@arm.com>, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v6 2/2] sched/uclamp: Protect uclamp fast path code with
 static key
Message-ID: <20200630170751.GA4817@hirez.programming.kicks-ass.net>
References: <20200630112123.12076-1-qais.yousef@arm.com>
 <20200630112123.12076-3-qais.yousef@arm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200630112123.12076-3-qais.yousef@arm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, Jun 30, 2020 at 12:21:23PM +0100, Qais Yousef wrote:
> @@ -993,10 +1013,38 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
>  
>  	lockdep_assert_held(&rq->lock);
>  
> +	/*
> +	 * If sched_uclamp_used was enabled after task @p was enqueued,
> +	 * we could end up with unbalanced call to uclamp_rq_dec_id().
> +	 *
> +	 * In this case the uc_se->active flag should be false since no uclamp
> +	 * accounting was performed at enqueue time and we can just return
> +	 * here.
> +	 *
> +	 * Need to be careful of the following enqeueue/dequeue ordering
> +	 * problem too
> +	 *
> +	 *	enqueue(taskA)
> +	 *	// sched_uclamp_used gets enabled
> +	 *	enqueue(taskB)
> +	 *	dequeue(taskA)
> +	 *	// Must not decrement bukcet->tasks here
> +	 *	dequeue(taskB)
> +	 *
> +	 * where we could end up with stale data in uc_se and
> +	 * bucket[uc_se->bucket_id].
> +	 *
> +	 * The following check here eliminates the possibility of such race.
> +	 */
> +	if (unlikely(!uc_se->active))
> +		return;
> +
>  	bucket = &uc_rq->bucket[uc_se->bucket_id];
> +
>  	SCHED_WARN_ON(!bucket->tasks);
>  	if (likely(bucket->tasks))
>  		bucket->tasks--;
> +
>  	uc_se->active = false;
>  
>  	/*

> @@ -1221,6 +1289,8 @@ static void __setscheduler_uclamp(struct task_struct *p,
>  	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
>  		return;
>  
> +	static_branch_enable(&sched_uclamp_used);
> +
>  	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
>  		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
>  			      attr->sched_util_min, true);
> @@ -7387,6 +7457,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
>  	if (req.ret)
>  		return req.ret;
>  
> +	static_branch_enable(&sched_uclamp_used);
> +
>  	mutex_lock(&uclamp_mutex);
>  	rcu_read_lock();
>  

There's a fun race described in 9107c89e269d ("perf: Fix race between
event install and jump_labels"), are we sure this isn't also susceptible
to something similar?

I suspect not, but I just wanted to make sure.