arm64/watchdog_hld: Add a cpufreq notifier for update watchdog thresh

arm64 depends on the cpufreq driver to gain the maximum cpu frequency
to convert the watchdog_thresh to perf event period. cpufreq drivers
like cppc_cpufreq will be initialized lately after the initializing of
the hard lockup detector so just use a safe cpufreq which will be
inaccurency. Use a cpufreq notifier to adjust the event's period to
a more accurate one.

Reviewed-by: Jie Zhan <[email protected]>
Reviewed-by: Douglas Anderson <[email protected]>
Signed-off-by: Yicong Yang <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: Yicong Yang

arch/arm64/kernel/watchdog_hld.c

@@ -34,3 +34,61 @@ bool __init arch_perf_nmi_is_available(void)
 	 */
 	return arm_pmu_irq_is_nmi();
 }
+
+static int watchdog_perf_update_period(void *data)
+{
+	int cpu = smp_processor_id();
+	u64 max_cpu_freq, new_period;
+
+	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
+	if (!max_cpu_freq)
+		return 0;
+
+	new_period = watchdog_thresh * max_cpu_freq;
+	hardlockup_detector_perf_adjust_period(new_period);
+
+	return 0;
+}
+
+static int watchdog_freq_notifier_callback(struct notifier_block *nb,
+					   unsigned long val, void *data)
+{
+	struct cpufreq_policy *policy = data;
+	int cpu;
+
+	if (val != CPUFREQ_CREATE_POLICY)
+		return NOTIFY_DONE;
+
+	/*
+	 * Let each online CPU related to the policy update the period by their
+	 * own. This will serialize with the framework on start/stop the lockup
+	 * detector (softlockup_{start,stop}_all) and avoid potential race
+	 * condition. Otherwise we may have below theoretical race condition:
+	 * (core 0/1 share the same policy)
+	 * [core 0]                      [core 1]
+	 *                               hardlockup_detector_event_create()
+	 *                                 hw_nmi_get_sample_period()
+	 * (cpufreq registered, notifier callback invoked)
+	 * watchdog_freq_notifier_callback()
+	 *   watchdog_perf_update_period()
+	 *   (since core 1's event's not yet created,
+	 *    the period is not set)
+	 *                                 perf_event_create_kernel_counter()
+	 *                                 (event's period is SAFE_MAX_CPU_FREQ)
+	 */
+	for_each_cpu(cpu, policy->cpus)
+		smp_call_on_cpu(cpu, watchdog_perf_update_period, NULL, false);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block watchdog_freq_notifier = {
+	.notifier_call = watchdog_freq_notifier_callback,
+};
+
+static int __init init_watchdog_freq_notifier(void)
+{
+	return cpufreq_register_notifier(&watchdog_freq_notifier,
+					 CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(init_watchdog_freq_notifier);