[PATCH] arch/x86: Fix kdump on x86 with physically hotadded CPUs

[Jiri Olsa]

On Tue, Oct 04, 2016 at 04:38:16PM +0200, Thomas Gleixner wrote:
> On Tue, 4 Oct 2016, Prarit Bhargava wrote:
> > On 10/04/2016 06:58 AM, Thomas Gleixner wrote:
> > > While it is the right thing to initialize the package map in that case, it
> > > still papers over a robustness issue in the uncore code, which needs to be
> > > fixed first.
> > 
> > I will include a separate patch with an error check for pkg == 0xffff in the
> > uncore code.
> 
> 0xffff? That won't help. The id returned is -1 if the entry is not
> initialized. And aside of that just patching that particular place is not
> helping as the uncore code and also rapl is relying on the package map
> being populated.
> 
> So we need a sanity check in the initialization code which prevents any of
> this being executed.

I still need to test this, but how about something like this?

thanks,
jirka


---
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 28865938aadf..61d087a2f25d 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -598,8 +598,13 @@ static int rapl_cpu_online(unsigned int cpu)
 
 static int rapl_cpu_prepare(unsigned int cpu)
 {
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
+	struct rapl_pmu *pmu;
+	int pkg = topology_logical_package_id(cpu);
+
+	if (WARN_ON(pkg == -1))
+		return -EINVAL;
 
+	pmu = cpu_to_rapl_pmu(cpu);
 	if (pmu)
 		return 0;
 
@@ -613,7 +618,7 @@ static int rapl_cpu_prepare(unsigned int cpu)
 	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
 	pmu->cpu = -1;
 	rapl_hrtimer_init(pmu);
-	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	rapl_pmus->pmus[pkg] = pmu;
 	return 0;
 }
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 463dc7a5a6c3..3f657fbbf787 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1352,7 +1352,7 @@ static int __init intel_uncore_init(void)
 {
 	const struct x86_cpu_id *id;
 	struct intel_uncore_init_fun *uncore_init;
-	int pret = 0, cret = 0, ret;
+	int pret = 0, cret = 0, ret, cpu;
 
 	id = x86_match_cpu(intel_uncore_match);
 	if (!id)
@@ -1363,6 +1363,13 @@ static int __init intel_uncore_init(void)
 
 	max_packages = topology_max_packages();
 
+	for_each_present_cpu(cpu) {
+		int pkg = topology_logical_package_id(cpu);
+
+		if (WARN_ON(pkg == -1))
+			return -EINVAL;
+	}
+
 	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
 	if (uncore_init->pci_init) {
 		pret = uncore_init->pci_init();