From mboxrd@z Thu Jan  1 00:00:00 1970
From: tglx@linutronix.de (Thomas Gleixner)
Date: Fri, 22 Feb 2013 19:45:32 +0100 (CET)
Subject: [PATCH 2/2][RFC] time : set broadcast irq affinity
In-Reply-To: <20130222095530.377fd218@chromoly>
References: <5123C299.3080005@linaro.org>
 <1361484083-5906-1-git-send-email-daniel.lezcano@linaro.org>
 <1361484083-5906-2-git-send-email-daniel.lezcano@linaro.org>
 <20130222095530.377fd218@chromoly>
Message-ID: <alpine.LFD.2.02.1302221945170.22263@ionos>
To: linux-arm-kernel@lists.infradead.org
List-Id: linux-arm-kernel.lists.infradead.org

On Fri, 22 Feb 2013, Jacob Pan wrote:
> On Thu, 21 Feb 2013 23:01:23 +0100
> Daniel Lezcano <daniel.lezcano@linaro.org> wrote:
> 
> > +/*
> > + * Set broadcast interrupt affinity
> > + */
> > +static void tick_broadcast_set_affinity(struct clock_event_device
> > *bc, int cpu) +{
> > +	struct cpumask cpumask;
> > +
> > +	if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ))
> > +		return;
> > +
> > +	cpumask_clear(&cpumask);
> > +	cpumask_set_cpu(cpu, &cpumask);
> > +	irq_set_affinity(bc->irq, &cpumask);
> would it be more efficient to keep track of the current bc->irq affinity
> via cpumask then set it only if it is different?

You beat me :)