Re: [PATCH 5/7] perf: Optimise topology iteration

[Lin Ming <ming.m.lin@intel.com>]

On Mon, 2011-01-03 at 19:02 +0800, Peter Zijlstra wrote:
> On Mon, 2010-12-27 at 23:38 +0800, Lin Ming wrote:
> > Currently we iterate the full machine looking for a matching core_id/nb
> > for the percore and the amd northbridge stuff , using a smaller topology
> > mask makes sense. 
> 
> Does topology_thread_cpumask() include offline cpus? I tried looking at
> it, but I cannot find any code clearing bits in that mask on offline.

No, it does not include offline cpus.
For x86 code, remove_siblinginfo() clears the bits.

take_cpu_down ->
  __cpu_disable ->
    native_cpu_disable ->
      cpu_disable_common ->
        remove_siblinginfo

static void remove_siblinginfo(int cpu)
{
        int sibling;
        struct cpuinfo_x86 *c = &cpu_data(cpu);

        for_each_cpu(sibling, cpu_core_mask(cpu)) {
                cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
                /*/
                 * last thread sibling in this cpu core going down
                 */
                if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
                        cpu_data(sibling).booted_cores--;
        }

        for_each_cpu(sibling, cpu_sibling_mask(cpu))
                cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
        cpumask_clear(cpu_sibling_mask(cpu));
        cpumask_clear(cpu_core_mask(cpu));
        c->phys_proc_id = 0;
        c->cpu_core_id = 0;
        cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
}

Lin Ming

> 
> > Signed-off-by: Lin Ming <ming.m.lin@intel.com>
> > ---
> >  arch/x86/kernel/cpu/perf_event_amd.c   |    2 +-
> >  arch/x86/kernel/cpu/perf_event_intel.c |    2 +-
> >  2 files changed, 2 insertions(+), 2 deletions(-)
> > 
> > diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
> > index 67e2202..5a3b7b8 100644
> > --- a/arch/x86/kernel/cpu/perf_event_amd.c
> > +++ b/arch/x86/kernel/cpu/perf_event_amd.c
> > @@ -323,7 +323,7 @@ static void amd_pmu_cpu_starting(int cpu)
> >  	nb_id = amd_get_nb_id(cpu);
> >  	WARN_ON_ONCE(nb_id == BAD_APICID);
> >  
> > -	for_each_online_cpu(i) {
> > +	for_each_cpu(i, topology_core_cpumask(cpu)) {
> >  		nb = per_cpu(cpu_hw_events, i).amd_nb;
> >  		if (WARN_ON_ONCE(!nb))
> >  			continue;
> > diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
> > index 354d1de..ad70c2c 100644
> > --- a/arch/x86/kernel/cpu/perf_event_intel.c
> > +++ b/arch/x86/kernel/cpu/perf_event_intel.c
> > @@ -1111,7 +1111,7 @@ static void intel_pmu_cpu_starting(int cpu)
> >  	if (!ht_enabled(cpu))
> >  		return;
> >  
> > -	for_each_online_cpu(i) {
> > +	for_each_cpu(i, topology_thread_cpumask(cpu)) {
> >  		struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core;
> >  
> >  		if (pc && pc->core_id == core_id) {
> 
>