Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Message-ID: <1582822024.7365.139.camel@lca.pw>
Subject: Re: suspicious RCU due to "Prefer using an idle CPU as a migration
 target instead of comparing tasks"
From:   Qian Cai <cai@lca.pw>
To:     Valentin Schneider <valentin.schneider@arm.com>
Cc:     Mel Gorman <mgorman@techsingularity.net>,
        Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <a.p.zijlstra@chello.nl>,
        Juri Lelli <juri.lelli@redhat.com>,
        Steven Rostedt <rostedt@goodmis.org>, paulmck@kernel.org,
        linux-kernel@vger.kernel.org
Date:   Thu, 27 Feb 2020 11:47:04 -0500
In-Reply-To: <1582821327.7365.137.camel@lca.pw>
References: <1582812549.7365.134.camel@lca.pw>
         <1582814862.7365.135.camel@lca.pw> <jhjimjsvyoe.mognet@arm.com>
         <1582821327.7365.137.camel@lca.pw>
Content-Type: text/plain; charset="UTF-8"
Mime-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, 2020-02-27 at 11:35 -0500, Qian Cai wrote:
> On Thu, 2020-02-27 at 15:26 +0000, Valentin Schneider wrote:
> > On Thu, Feb 27 2020, Qian Cai wrote:
> > 
> > > On Thu, 2020-02-27 at 09:09 -0500, Qian Cai wrote:
> > > > The linux-next commit ff7db0bf24db ("sched/numa: Prefer using an idle CPU as a
> > > > migration target instead of comparing tasks") introduced a boot warning,
> > > 
> > > This?
> > > 
> > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > > index a61d83ea2930..ca780cd1eae2 100644
> > > --- a/kernel/sched/fair.c
> > > +++ b/kernel/sched/fair.c
> > > @@ -1607,7 +1607,9 @@ static void update_numa_stats(struct task_numa_env *env,
> > > if (ns->idle_cpu == -1)
> > > ns->idle_cpu = cpu;
> > > 
> > > +rcu_read_lock();
> > > idle_core = numa_idle_core(idle_core, cpu);
> > > +rcu_read_unlock();
> > > }
> > > }
> > > 
> > 
> > 
> > Hmph right, we have
> > numa_idle_core()->test_idle_cores()->rcu_dereference().
> > 
> > Dunno if it's preferable to wrap the entirety of update_numa_stats() or
> > if that fine-grained read-side section is ok.
> 
> I could not come up with a better fine-grained one than this.

Correction -- this one,

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a61d83ea2930..580d56f9c10b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1561,10 +1561,18 @@ numa_type numa_classify(unsigned int imbalance_pct,
 static inline int numa_idle_core(int idle_core, int cpu)
 {
 #ifdef CONFIG_SCHED_SMT
+	bool idle;
+
 	if (!static_branch_likely(&sched_smt_present) ||
-	    idle_core >= 0 || !test_idle_cores(cpu, false))
+	    idle_core >= 0)
 		return idle_core;
 
+	rcu_read_lock();
+	idle = test_idle_cores(cpu, false);
+	rcu_read_unlock();
+
+	if (!idle)
+		return idle_core;
 	/*
 	 * Prefer cores instead of packing HT siblings
 	 * and triggering future load balancing.