Merge tag 'pm-5.5-rc3' of git://git.kernel.org/pub/scm/linux/kernel/g…

…it/rafael/linux-pm

Pull power management fix from Rafael Wysocki:
 "Fix a problem related to CPU offline/online and cpufreq governors that
  in some system configurations may lead to a system-wide deadlock
  during CPU online"

* tag 'pm-5.5-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: Avoid leaving stale IRQ work items during CPU offline

include/linux/cpufreq.h

@@ -595,17 +595,6 @@ struct governor_attr {
 			 size_t count);
 };
 
-static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
-{
-	/*
-	 * Allow remote callbacks if:
-	 * - dvfs_possible_from_any_cpu flag is set
-	 * - the local and remote CPUs share cpufreq policy
-	 */
-	return policy->dvfs_possible_from_any_cpu ||
-		cpumask_test_cpu(smp_processor_id(), policy->cpus);
-}
-
 /*********************************************************************
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/

include/linux/sched/cpufreq.h

@@ -12,6 +12,8 @@
 #define SCHED_CPUFREQ_MIGRATION	(1U << 1)
 
 #ifdef CONFIG_CPU_FREQ
+struct cpufreq_policy;
+
 struct update_util_data {
        void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
 };
@@ -20,6 +22,7 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
                        void (*func)(struct update_util_data *data, u64 time,
 				    unsigned int flags));
 void cpufreq_remove_update_util_hook(int cpu);
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy);
 
 static inline unsigned long map_util_freq(unsigned long util,
 					unsigned long freq, unsigned long cap)

kernel/sched/cpufreq.c

@@ -5,6 +5,8 @@
  * Copyright (C) 2016, Intel Corporation
  * Author: Rafael J. Wysocki <[email protected]>
  */
+#include <linux/cpufreq.h>
+
 #include "sched.h"
 
 DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
@@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu)
 	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook);
+
+/**
+ * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated.
+ * @policy: cpufreq policy to check.
+ *
+ * Return 'true' if:
+ * - the local and remote CPUs share @policy,
+ * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going
+ *   offline (in which case it is not expected to run cpufreq updates any more).
+ */
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
+{
+	return cpumask_test_cpu(smp_processor_id(), policy->cpus) ||
+		(policy->dvfs_possible_from_any_cpu &&
+		 rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)));
+}

kernel/sched/cpufreq_schedutil.c

@@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	 * by the hardware, as calculating the frequency is pointless if
 	 * we cannot in fact act on it.
 	 *
-	 * For the slow switching platforms, the kthread is always scheduled on
-	 * the right set of CPUs and any CPU can find the next frequency and
-	 * schedule the kthread.
+	 * This is needed on the slow switching platforms too to prevent CPUs
+	 * going offline from leaving stale IRQ work items behind.
 	 */
-	if (sg_policy->policy->fast_switch_enabled &&
-	    !cpufreq_this_cpu_can_update(sg_policy->policy))
+	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
 	if (unlikely(sg_policy->limits_changed)) {