linux-kernel - Re: [PATCH 3/3] sched: Use cpu_dying() to fix balance

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 15 Apr 2021 10:59:13 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Valentin Schneider <valentin.schneider@....com>
Cc:     tglx@...utronix.de, mingo@...nel.org, bigeasy@...utronix.de,
        swood@...hat.com, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        bristot@...hat.com, vincent.donnefort@....com, qais.yousef@....com,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH 3/3] sched: Use cpu_dying() to fix balance_push vs
 hotplug-rollback

On Tue, Apr 13, 2021 at 08:51:23AM +0200, Peter Zijlstra wrote:

> > I'm afraid I don't follow; we're replacing a read of rq->balance_push with
> > cpu_dying(), and those are still written on the same side of the
> > synchronize_rcu(). What am I missing?
> 
> Yeah, I'm not sure anymnore either; I tried to work out why I'd done
> that but upon closer examination everything fell flat.
> 
> Let me try again today :-)

Can't make sense of what I did.. I've removed that hunk. Patch now looks
like this.

---
Subject: sched: Use cpu_dying() to fix balance_push vs hotplug-rollback
From: Peter Zijlstra <peterz@...radead.org>
Date: Thu Jan 21 16:09:32 CET 2021

Use the new cpu_dying() state to simplify and fix the balance_push()
vs CPU hotplug rollback state.

Specifically, we currently rely on notifiers sched_cpu_dying() /
sched_cpu_activate() to terminate balance_push, however if the
cpu_down() fails when we're past sched_cpu_deactivate(), it should
terminate balance_push at that point and not wait until we hit
sched_cpu_activate().

Similarly, when cpu_up() fails and we're going back down, balance_push
should be active, where it currently is not.

So instead, make sure balance_push is enabled between
sched_cpu_deactivate() and sched_cpu_activate() (eg. when
!cpu_active()), and gate it's utility with cpu_dying().

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 kernel/sched/core.c  |   26 +++++++++++++++-----------
 kernel/sched/sched.h |    1 -
 2 files changed, 15 insertions(+), 12 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1811,7 +1811,7 @@ static inline bool is_cpu_allowed(struct
 		return cpu_online(cpu);
 
 	/* Regular kernel threads don't get to stay during offline. */
-	if (cpu_rq(cpu)->balance_push)
+	if (cpu_dying(cpu))
 		return false;
 
 	/* But are allowed during online. */
@@ -7639,6 +7639,9 @@ static DEFINE_PER_CPU(struct cpu_stop_wo
 
 /*
  * Ensure we only run per-cpu kthreads once the CPU goes !active.
+ *
+ * This is active/set between sched_cpu_deactivate() / sched_cpu_activate().
+ * But only effective when the hotplug motion is down.
  */
 static void balance_push(struct rq *rq)
 {
@@ -7646,12 +7649,19 @@ static void balance_push(struct rq *rq)
 
 	lockdep_assert_held(&rq->lock);
 	SCHED_WARN_ON(rq->cpu != smp_processor_id());
+
 	/*
 	 * Ensure the thing is persistent until balance_push_set(.on = false);
 	 */
 	rq->balance_callback = &balance_push_callback;
 
 	/*
+	 * Only active while going offline.
+	 */
+	if (!cpu_dying(rq->cpu))
+		return;
+
+	/*
 	 * Both the cpu-hotplug and stop task are in this case and are
 	 * required to complete the hotplug process.
 	 *
@@ -7704,7 +7714,6 @@ static void balance_push_set(int cpu, bo
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
-	rq->balance_push = on;
 	if (on) {
 		WARN_ON_ONCE(rq->balance_callback);
 		rq->balance_callback = &balance_push_callback;
@@ -7829,8 +7838,8 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq_flags rf;
 
 	/*
-	 * Make sure that when the hotplug state machine does a roll-back
-	 * we clear balance_push. Ideally that would happen earlier...
+	 * Clear the balance_push callback and prepare to schedule
+	 * regular tasks.
 	 */
 	balance_push_set(cpu, false);
 
@@ -8015,12 +8024,6 @@ int sched_cpu_dying(unsigned int cpu)
 	}
 	rq_unlock_irqrestore(rq, &rf);
 
-	/*
-	 * Now that the CPU is offline, make sure we're welcome
-	 * to new tasks once we come back up.
-	 */
-	balance_push_set(cpu, false);
-
 	calc_load_migrate(rq);
 	update_max_interval();
 	hrtick_clear(rq);
@@ -8205,7 +8208,7 @@ void __init sched_init(void)
 		rq->sd = NULL;
 		rq->rd = NULL;
 		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
-		rq->balance_callback = NULL;
+		rq->balance_callback = &balance_push_callback;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
 		rq->push_cpu = 0;
@@ -8252,6 +8255,7 @@ void __init sched_init(void)
 
 #ifdef CONFIG_SMP
 	idle_thread_set_boot_cpu();
+	balance_push_set(smp_processor_id(), false);
 #endif
 	init_sched_fair_class();
 
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -983,7 +983,6 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
-	unsigned char		balance_push;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;