Re: Preemption Broken: centrino_target busted under SMP on 2.6.20.4

[Dave Jones <davej@redhat.com>]

On Mon, Apr 09, 2007 at 05:26:51PM -0700, Andrew Morton wrote:
 > On Thu, 5 Apr 2007 16:50:34 -0400
 > Dave Jones <davej@redhat.com> wrote:
 > 
 > > diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c
 > > index f43b987..824d0a2 100644
 > > --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c
 > > +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c
 > > @@ -708,6 +708,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 > >  	saved_mask = current->cpus_allowed;
 > >  	first_cpu = 1;
 > >  	cpus_clear(covered_cpus);
 > > +	preempt_disable();
 > >  	for_each_cpu_mask(j, online_policy_cpus) {
 > >  		/*
 > >  		 * Support for SMP systems.
 > > @@ -798,6 +799,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 > >  	}
 > >  
 > >  migrate_end:
 > > +	preempt_enable();
 > >  	set_cpus_allowed(current, saved_mask);
 > >  	return 0;
 > >  }
 > 
 > This means we'll call set_cpus_allowed() while in atomic state, but
 > set_cpus_allowed() does sleepy stuff.

Puzzled. This diff shouldn't change anything about the context we're in
when we call set_cpus_allowed, and as we're not seeing warnings now,
I'm not sure what I'm missing?

[which may be 'the obvious', you wouldn't believe the evening I've had
 involving gas leaks and noxious fumes. Wheee, floaty head.]

	Dave

-- 
http://www.codemonkey.org.uk