arm64: topology: Handle AMU FIE setup on CPU hotplug

Currently, when a cpufreq policy is created, the AMU FIE setup process
checks all CPUs in the policy -- including those that are offline. If any
of these CPUs are offline at that time, their AMU capability flag hasn't
been verified yet, leading the check fail. As a result, AMU FIE is not
enabled, even if the CPUs that are online do support it.

Later, when the previously offline CPUs come online and report AMU support,
there's no mechanism in place to re-enable AMU FIE for the policy. This
leaves the entire frequency domain without AMU FIE, despite being eligible.

Restrict the initial AMU FIE check to only those CPUs that are online at
the time the policy is created, and allow CPUs that come online later to
join the policy with AMU FIE enabled.

Signed-off-by: Lifeng Zheng <zhenglifeng1@huawei.com>
Acked-by: Beata Michalska <beata.michalska@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>

Author: Lifeng Zheng

arch/arm64/kernel/topology.c

@@ -284,7 +284,7 @@ static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
 	struct cpufreq_policy *policy = data;
 
 	if (val == CPUFREQ_CREATE_POLICY)
-		amu_fie_setup(policy->related_cpus);
+		amu_fie_setup(policy->cpus);
 
 	/*
 	 * We don't need to handle CPUFREQ_REMOVE_POLICY event as the AMU
@@ -303,10 +303,71 @@ static struct notifier_block init_amu_fie_notifier = {
 	.notifier_call = init_amu_fie_callback,
 };
 
+static int cpuhp_topology_online(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_policy(cpu);
+
+	/* Those are cheap checks */
+
+	/*
+	 * Skip this CPU if:
+	 *  - it has no cpufreq policy assigned yet,
+	 *  - no policy exists that spans CPUs with AMU counters, or
+	 *  - it was already handled.
+	 */
+	if (unlikely(!policy) || !cpumask_available(amu_fie_cpus) ||
+	    cpumask_test_cpu(cpu, amu_fie_cpus))
+		return 0;
+
+	/*
+	 * Only proceed if all already-online CPUs in this policy
+	 * support AMU counters.
+	 */
+	if (unlikely(!cpumask_subset(policy->cpus, amu_fie_cpus)))
+		return 0;
+
+	/*
+	 * If the new online CPU cannot pass this check, all the CPUs related to
+	 * the same policy should be clear from amu_fie_cpus mask, otherwise they
+	 * may use different source of the freq scale.
+	 */
+	if (!freq_counters_valid(cpu)) {
+		pr_warn("CPU[%u] doesn't support AMU counters\n", cpu);
+		topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_ARCH,
+						 policy->related_cpus);
+		cpumask_andnot(amu_fie_cpus, amu_fie_cpus, policy->related_cpus);
+		return 0;
+	}
+
+	cpumask_set_cpu(cpu, amu_fie_cpus);
+
+	topology_set_scale_freq_source(&amu_sfd, cpumask_of(cpu));
+
+	pr_debug("CPU[%u]: counter will be used for FIE.", cpu);
+
+	return 0;
+}
+
 static int __init init_amu_fie(void)
 {
-	return cpufreq_register_notifier(&init_amu_fie_notifier,
+	int ret;
+
+	ret = cpufreq_register_notifier(&init_amu_fie_notifier,
 					CPUFREQ_POLICY_NOTIFIER);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"arm64/topology:online",
+					cpuhp_topology_online,
+					NULL);
+	if (ret < 0) {
+		cpufreq_unregister_notifier(&init_amu_fie_notifier,
+					    CPUFREQ_POLICY_NOTIFIER);
+		return ret;
+	}
+
+	return 0;
 }
 core_initcall(init_amu_fie);
 

drivers/base/arch_topology.c

@@ -34,7 +34,14 @@ EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
 
 static bool supports_scale_freq_counters(const struct cpumask *cpus)
 {
-	return cpumask_subset(cpus, &scale_freq_counters_mask);
+	int i;
+
+	for_each_cpu(i, cpus) {
+		if (cpumask_test_cpu(i, &scale_freq_counters_mask))
+			return true;
+	}
+
+	return false;
 }
 
 bool topology_scale_freq_invariant(void)