[tip:sched/core] irq_work: Remove BUG_ON in irq_work_run()

[tip:sched/core] irq_work: Remove BUG_ON in irq_work_run()

[tip-bot for Peter Zijlstra]

Commit-ID:  a77353e5eb56b6c6098bfce59aff1f449451b0b7
Gitweb:     http://git.kernel.org/tip/a77353e5eb56b6c6098bfce59aff1f449451b0b7
Author:     Peter Zijlstra <peterz@infradead.org>
AuthorDate: Wed, 25 Jun 2014 07:13:07 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Sat, 5 Jul 2014 11:17:26 +0200

irq_work: Remove BUG_ON in irq_work_run()

Because of a collision with 8d056c48e486 ("CPU hotplug, smp: flush any
pending IPI callbacks before CPU offline"), which ends up calling
hotplug_cfd()->flush_smp_call_function_queue()->irq_work_run(), which
is not from IRQ context.

And since that already calls irq_work_run() from the hotplug path,
remove our entire hotplug handling.

Reported-by: Stephen Warren <swarren@wwwdotorg.org>
Tested-by: Stephen Warren <swarren@wwwdotorg.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-busatzs2gvz4v62258agipuf@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/irq_work.c | 46 ++++------------------------------------------
 1 file changed, 4 insertions(+), 42 deletions(-)

diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 4b0a890..e6bcbe7 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -160,20 +160,14 @@ static void irq_work_run_list(struct llist_head *list)
 	}
 }
 
-static void __irq_work_run(void)
-{
-	irq_work_run_list(&__get_cpu_var(raised_list));
-	irq_work_run_list(&__get_cpu_var(lazy_list));
-}
-
 /*
- * Run the irq_work entries on this cpu. Requires to be ran from hardirq
- * context with local IRQs disabled.
+ * hotplug calls this through:
+ *  hotplug_cfd() -> flush_smp_call_function_queue()
  */
 void irq_work_run(void)
 {
-	BUG_ON(!in_irq());
-	__irq_work_run();
+	irq_work_run_list(&__get_cpu_var(raised_list));
+	irq_work_run_list(&__get_cpu_var(lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -189,35 +183,3 @@ void irq_work_sync(struct irq_work *work)
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
-
-#ifdef CONFIG_HOTPLUG_CPU
-static int irq_work_cpu_notify(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_DYING:
-		/* Called from stop_machine */
-		if (WARN_ON_ONCE(cpu != smp_processor_id()))
-			break;
-		__irq_work_run();
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpu_notify;
-
-static __init int irq_work_init_cpu_notifier(void)
-{
-	cpu_notify.notifier_call = irq_work_cpu_notify;
-	cpu_notify.priority = 0;
-	register_cpu_notifier(&cpu_notify);
-	return 0;
-}
-device_initcall(irq_work_init_cpu_notifier);
-
-#endif /* CONFIG_HOTPLUG_CPU */

Re: [tip:sched/core] irq_work: Remove BUG_ON in irq_work_run()

[Srivatsa S. Bhat]

Hi Ingo,

On 07/05/2014 04:13 PM, tip-bot for Peter Zijlstra wrote:
> Commit-ID:  a77353e5eb56b6c6098bfce59aff1f449451b0b7
> Gitweb:     http://git.kernel.org/tip/a77353e5eb56b6c6098bfce59aff1f449451b0b7
> Author:     Peter Zijlstra <peterz@infradead.org>
> AuthorDate: Wed, 25 Jun 2014 07:13:07 +0200
> Committer:  Ingo Molnar <mingo@kernel.org>
> CommitDate: Sat, 5 Jul 2014 11:17:26 +0200
> 
> irq_work: Remove BUG_ON in irq_work_run()
>

I believe this fix has to go into 3.16 itself, since this fixes a CPU hotplug
regression on many systems, as reported here:

https://lkml.org/lkml/2014/6/24/765
https://lkml.org/lkml/2014/7/1/473
https://lkml.org/lkml/2014/7/4/16

I didn't find this fix in mainline yet, so I thought of sending a note.

Thank you!

Regards,
Srivatsa S. Bhat
 
> Because of a collision with 8d056c48e486 ("CPU hotplug, smp: flush any
> pending IPI callbacks before CPU offline"), which ends up calling
> hotplug_cfd()->flush_smp_call_function_queue()->irq_work_run(), which
> is not from IRQ context.
> 
> And since that already calls irq_work_run() from the hotplug path,
> remove our entire hotplug handling.
> 
> Reported-by: Stephen Warren <swarren@wwwdotorg.org>
> Tested-by: Stephen Warren <swarren@wwwdotorg.org>
> Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
> Cc: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
> Signed-off-by: Peter Zijlstra <peterz@infradead.org>
> Link: http://lkml.kernel.org/n/tip-busatzs2gvz4v62258agipuf@git.kernel.org
> Signed-off-by: Ingo Molnar <mingo@kernel.org>
> ---
>  kernel/irq_work.c | 46 ++++------------------------------------------
>  1 file changed, 4 insertions(+), 42 deletions(-)
> 
> diff --git a/kernel/irq_work.c b/kernel/irq_work.c
> index 4b0a890..e6bcbe7 100644
> --- a/kernel/irq_work.c
> +++ b/kernel/irq_work.c
> @@ -160,20 +160,14 @@ static void irq_work_run_list(struct llist_head *list)
>  	}
>  }
> 
> -static void __irq_work_run(void)
> -{
> -	irq_work_run_list(&__get_cpu_var(raised_list));
> -	irq_work_run_list(&__get_cpu_var(lazy_list));
> -}
> -
>  /*
> - * Run the irq_work entries on this cpu. Requires to be ran from hardirq
> - * context with local IRQs disabled.
> + * hotplug calls this through:
> + *  hotplug_cfd() -> flush_smp_call_function_queue()
>   */
>  void irq_work_run(void)
>  {
> -	BUG_ON(!in_irq());
> -	__irq_work_run();
> +	irq_work_run_list(&__get_cpu_var(raised_list));
> +	irq_work_run_list(&__get_cpu_var(lazy_list));
>  }
>  EXPORT_SYMBOL_GPL(irq_work_run);
> 
> @@ -189,35 +183,3 @@ void irq_work_sync(struct irq_work *work)
>  		cpu_relax();
>  }
>  EXPORT_SYMBOL_GPL(irq_work_sync);
> -
> -#ifdef CONFIG_HOTPLUG_CPU
> -static int irq_work_cpu_notify(struct notifier_block *self,
> -			       unsigned long action, void *hcpu)
> -{
> -	long cpu = (long)hcpu;
> -
> -	switch (action) {
> -	case CPU_DYING:
> -		/* Called from stop_machine */
> -		if (WARN_ON_ONCE(cpu != smp_processor_id()))
> -			break;
> -		__irq_work_run();
> -		break;
> -	default:
> -		break;
> -	}
> -	return NOTIFY_OK;
> -}
> -
> -static struct notifier_block cpu_notify;
> -
> -static __init int irq_work_init_cpu_notifier(void)
> -{
> -	cpu_notify.notifier_call = irq_work_cpu_notify;
> -	cpu_notify.priority = 0;
> -	register_cpu_notifier(&cpu_notify);
> -	return 0;
> -}
> -device_initcall(irq_work_init_cpu_notifier);
> -
> -#endif /* CONFIG_HOTPLUG_CPU */
>