[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180522235028.80564-1-joel@joelfernandes.org>
Date: Tue, 22 May 2018 16:50:28 -0700
From: "Joel Fernandes (Google)" <joelaf@...gle.com>
To: linux-kernel@...r.kernel.org
Cc: "Joel Fernandes (Google)" <joel@...lfernandes.org>,
"Rafael J . Wysocki" <rafael.j.wysocki@...el.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Patrick Bellasi <patrick.bellasi@....com>,
Juri Lelli <juri.lelli@...hat.com>,
Luca Abeni <luca.abeni@...tannapisa.it>,
Todd Kjos <tkjos@...gle.com>, claudio@...dence.eu.com,
kernel-team@...roid.com, linux-pm@...r.kernel.org
Subject: [PATCH RFC] schedutil: Address the r/w ordering race in kthread
Currently there is a race in schedutil code for slow-switch single-CPU
systems. Fix it by enforcing ordering the write to work_in_progress to
happen before the read of next_freq.
Kthread Sched update
sugov_work() sugov_update_single()
lock();
// The CPU is free to rearrange below
// two in any order, so it may clear
// the flag first and then read next
// freq. Lets assume it does.
work_in_progress = false
if (work_in_progress)
return;
sg_policy->next_freq = 0;
freq = sg_policy->next_freq;
sg_policy->next_freq = real-freq;
unlock();
Reported-by: Viresh Kumar <viresh.kumar@...aro.org>
CC: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
CC: Peter Zijlstra <peterz@...radead.org>
CC: Ingo Molnar <mingo@...hat.com>
CC: Patrick Bellasi <patrick.bellasi@....com>
CC: Juri Lelli <juri.lelli@...hat.com>
Cc: Luca Abeni <luca.abeni@...tannapisa.it>
CC: Todd Kjos <tkjos@...gle.com>
CC: claudio@...dence.eu.com
CC: kernel-team@...roid.com
CC: linux-pm@...r.kernel.org
Signed-off-by: Joel Fernandes (Google) <joel@...lfernandes.org>
---
I split this into separate patch, because this race can also happen in
mainline.
kernel/sched/cpufreq_schedutil.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5c482ec38610..ce7749da7a44 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -401,6 +401,13 @@ static void sugov_work(struct kthread_work *work)
*/
raw_spin_lock_irqsave(&sg_policy->update_lock, flags);
freq = sg_policy->next_freq;
+
+ /*
+ * sugov_update_single can access work_in_progress without update_lock,
+ * make sure next_freq is read before work_in_progress is set.
+ */
+ smp_mb();
+
sg_policy->work_in_progress = false;
raw_spin_unlock_irqrestore(&sg_policy->update_lock, flags);
--
2.17.0.441.gb46fe60e1d-goog
Powered by blists - more mailing lists