On 6/8/21 11:06 PM, Peter Zijlstra wrote:

On Tue, Jun 08, 2021 at 05:26:58PM +0530, Kajol Jain wrote:

quoted

+static int nvdimm_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
+{
+	struct nvdimm_pmu *nd_pmu;
+	u32 target;
+	int nodeid;
+	const struct cpumask *cpumask;
+
+	nd_pmu = hlist_entry_safe(node, struct nvdimm_pmu, node);
+
+	/* Clear it, incase given cpu is set in nd_pmu->arch_cpumask */
+	cpumask_test_and_clear_cpu(cpu, &nd_pmu->arch_cpumask);
+
+	/*
+	 * If given cpu is not same as current designated cpu for
+	 * counter access, just return.
+	 */
+	if (cpu != nd_pmu->cpu)
+		return 0;
+
+	/* Check for any active cpu in nd_pmu->arch_cpumask */
+	target = cpumask_any(&nd_pmu->arch_cpumask);
+	nd_pmu->cpu = target;
+
+	/*
+	 * Incase we don't have any active cpu in nd_pmu->arch_cpumask,
+	 * check in given cpu's numa node list.
+	 */
+	if (target >= nr_cpu_ids) {
+		nodeid = cpu_to_node(cpu);
+		cpumask = cpumask_of_node(nodeid);
+		target = cpumask_any_but(cpumask, cpu);
+		nd_pmu->cpu = target;
+
+		if (target >= nr_cpu_ids)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int nvdimm_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
+{
+	struct nvdimm_pmu *nd_pmu;
+
+	nd_pmu = hlist_entry_safe(node, struct nvdimm_pmu, node);
+
+	if (nd_pmu->cpu >= nr_cpu_ids)
+		nd_pmu->cpu = cpu;
+
+	return 0;
+}

quoted

+static int nvdimm_pmu_cpu_hotplug_init(struct nvdimm_pmu *nd_pmu)
+{
+	int nodeid, rc;
+	const struct cpumask *cpumask;
+
+	/*
+	 * Incase cpu hotplug is not handled by arch specific code
+	 * they can still provide required cpumask which can be used
+	 * to get designatd cpu for counter access.
+	 * Check for any active cpu in nd_pmu->arch_cpumask.
+	 */
+	if (!cpumask_empty(&nd_pmu->arch_cpumask)) {
+		nd_pmu->cpu = cpumask_any(&nd_pmu->arch_cpumask);
+	} else {
+		/* pick active cpu from the cpumask of device numa node. */
+		nodeid = dev_to_node(nd_pmu->dev);
+		cpumask = cpumask_of_node(nodeid);
+		nd_pmu->cpu = cpumask_any(cpumask);
+	}
+
+	rc = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "perf/nvdimm:online",
+				     nvdimm_pmu_cpu_online, nvdimm_pmu_cpu_offline);
+

Did you actually test this hotplug stuff?

That is, create a counter, unplug the CPU the counter was on, and
continue counting? "perf stat -I" is a good option for this, concurrent
with a hotplug.

Because I don't think it's actually correct. The thing is perf core is
strictly per-cpu, and it will place the event on a specific CPU context.
If you then unplug that CPU, nothing will touch the events on that CPU
anymore.

What drivers that span CPUs need to do is call
perf_pmu_migrate_context() whenever the CPU they were assigned to goes
away. Please have a look at arch/x86/events/rapl.c or
arch/x86/events/amd/power.c for relatively simple drivers that have this
property.

Hi Peter,
    Primarily I tested off-lining multiple cpus and checking if cpumask file is updating as expected,
followed with perf stat commands.
But I missed the scenario where we are off-lining CPU while running perf stat. My bad, thanks
for pointing it out.
I will fix this issue and send new version of the patchset.

Thanks,
Kajol Jain