Re: idle issues running sembench on 128 cpus II

[Dave Kleikamp <dave.kleikamp@oracle.com>]

On 05/04/2011 06:48 PM, Andi Kleen wrote:
>> Here's a new patch without the raw. Boots on my Westmere.
>
> Sorry appended the old patch. Here's really the new version.
>
> From: Andi Kleen<ak@linux.intel.com>
> Date: Wed, 4 May 2011 15:09:27 -0700
> Subject: [PATCH] Move C3 stop test outside lock
>
> Avoid taking locks in the idle path for systems where the timer
> doesn't stop in C3.
>
> Signed-off-by: Andi Kleen<ak@linux.intel.com>
>
> diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
> index da800ff..7f565b7 100644
> --- a/kernel/time/tick-broadcast.c
> +++ b/kernel/time/tick-broadcast.c
> @@ -456,23 +456,22 @@ void tick_broadcast_oneshot_control(unsigned long reason)
>   	unsigned long flags;
>   	int cpu;
>
> -	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
> -
>   	/*
>   	 * Periodic mode does not care about the enter/exit of power
>   	 * states
>   	 */
>   	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
> -		goto out;
> +		return;
>
> -	bc = tick_broadcast_device.evtdev;
>   	cpu = smp_processor_id();
> +	bc = tick_broadcast_device.evtdev;
>   	td =&per_cpu(tick_cpu_device, cpu);
>   	dev = td->evtdev;
>
>   	if (!(dev->features&  CLOCK_EVT_FEAT_C3STOP))
> -		goto out;
> +		return;

out: is now defined but not used in this function.

>
> +	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
>   	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
>   		if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
>   			cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask());
>