Messages in this thread | | | Subject | Re: [PATCH V6 07/13] perf: Generic pci uncore device support | From | Peter Zijlstra <> | Date | Mon, 18 Jun 2012 09:43:08 +0200 |
| |
On Mon, 2012-06-18 at 11:06 +0800, Yan, Zheng wrote: > On 06/16/2012 12:02 AM, Peter Zijlstra wrote: > > On Fri, 2012-06-15 at 14:31 +0800, Yan, Zheng wrote: > >> @@ -305,6 +310,22 @@ struct intel_uncore_box *uncore_alloc_box(int cpu) > >> static struct intel_uncore_box * > >> uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) > >> { > >> + static struct intel_uncore_box *box; > >> + > >> + box = *per_cpu_ptr(pmu->box, cpu); > >> + if (box) > >> + return box; > >> + > >> + raw_spin_lock(&uncore_box_lock); > >> + list_for_each_entry(box, &pmu->box_list, list) { > >> + if (box->phys_id == topology_physical_package_id(cpu)) { > >> + atomic_inc(&box->refcnt); > >> + *per_cpu_ptr(pmu->box, cpu) = box; > >> + break; > >> + } > >> + } > >> + raw_spin_unlock(&uncore_box_lock); > >> + > >> return *per_cpu_ptr(pmu->box, cpu); > >> } > > > > So why can't we do that lookup from a hotplug notifier? > > > We can. But I personally prefer not to mix pci uncore initialization > code with cpu hotplug notifier. Because pci hotplug and cpu hotplug > are separate process, I'm not completely sure which one happens first.
I suspect nobody does.. OK we'll leave it as it is. Thanks
| |