linux-kernel - Re: [RFC][PATCH] sched: Start stopper early

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, 8 Oct 2015 20:47:43 +0200
From:	Oleg Nesterov <oleg@...hat.com>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	heiko.carstens@...ibm.com, linux-kernel@...r.kernel.org,
	Tejun Heo <tj@...nel.org>, Ingo Molnar <mingo@...nel.org>,
	Rik van Riel <riel@...hat.com>
Subject: Re: [RFC][PATCH] sched: Start stopper early

On 10/08, Oleg Nesterov wrote:
>
> To avoid the confusion, let me repeat that I am not arguing with
> this change, perhaps it makes sense too.
>
> But unless I missed something it is not really correct and can't
> fix the problem. So I still think the series I sent should be
> applied first.

...

> But note that kthread_unpark() will only wake the stopper thread up.
>
> cpu_stopper->enabled is still false, and it will be false until
> smpboot_unpark_thread() calls ->pre_unpark() later. And this means
> that stop_two_cpus()->cpu_stop_queue_work() can silently fail until
> then. So I don't this patch can fix the problem.

So I'd suggest something like the patch below (uncompiled/untested)
on top of the series I sent.

Note also that (at least imo) it looks like a cleanup, and even
->selfparking becomes more consistent.

What do you think?

Oleg.


--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -40,7 +40,6 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	void				(*pre_unpark)(unsigned int cpu);
 	bool				selfparking;
 	const char			*thread_comm;
 };
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 7b76362..0adedca 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -34,6 +34,7 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 void stop_machine_park(int cpu);
+void stop_machine_unpark(int cpu);
 
 #else	/* CONFIG_SMP */
 
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -221,9 +221,8 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp
 {
 	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
 
-	if (ht->pre_unpark)
-		ht->pre_unpark(cpu);
-	kthread_unpark(tsk);
+	if (!ht->selfparking)
+		kthread_unpark(tsk);
 }
 
 void smpboot_unpark_threads(unsigned int cpu)
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -513,6 +513,14 @@ static void cpu_stop_unpark(unsigned int cpu)
 	spin_unlock_irq(&stopper->lock);
 }
 
+void stop_machine_unpark(int cpu)
+{
+	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+
+	cpu_stop_unpark(cpu);
+	kthread_unpark(stopper->thread);
+}
+
 static struct smp_hotplug_thread cpu_stop_threads = {
 	.store			= &cpu_stopper.thread,
 	.thread_should_run	= cpu_stop_should_run,
@@ -521,7 +529,6 @@ static struct smp_hotplug_thread cpu_stop_threads = {
 	.create			= cpu_stop_create,
 	.setup			= cpu_stop_unpark,
 	.park			= cpu_stop_park,
-	.pre_unpark		= cpu_stop_unpark,
 	.selfparking		= true,
 };
 
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5515,11 +5515,14 @@ static void set_cpu_rq_start_time(void)
 static int sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
+	int cpu = (long)hcpu;
+
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_STARTING:
 		set_cpu_rq_start_time();
 		return NOTIFY_OK;
 	case CPU_ONLINE:
+		stop_machine_unpark(cpu);
 		/*
 		 * At this point a starting CPU has marked itself as online via
 		 * set_cpu_online(). But it might not yet have marked itself
@@ -5528,7 +5531,7 @@ static int sched_cpu_active(struct notif
 		 * Thus, fall-through and help the starting CPU along.
 		 */
 	case CPU_DOWN_FAILED:
-		set_cpu_active((long)hcpu, true);
+		set_cpu_active(cpu, true);
 		return NOTIFY_OK;
 	default:
 		return NOTIFY_DONE;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/