Merge tag 'v5.5-rc3' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 37 insertions, 9 deletions

diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index b5dcd1d83c7f..7c2fe50fd76d 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2016, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
+#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)));
+}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 86800b4d5453..9b8916fd00a2 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/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)) {
@@ -915,7 +913,7 @@ static int __init sugov_register(void)
 {
 	return cpufreq_register_governor(&schedutil_gov);
 }
-fs_initcall(sugov_register);
+core_initcall(sugov_register);
 
 #ifdef CONFIG_ENERGY_MODEL
 extern bool sched_energy_update;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 280d54ccb4be..8da0222924cf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7329,7 +7329,14 @@ static int detach_tasks(struct lb_env *env)
 			    load < 16 && !env->sd->nr_balance_failed)
 				goto next;
 
-			if (load/2 > env->imbalance)
+			/*
+			 * Make sure that we don't migrate too much load.
+			 * Nevertheless, let relax the constraint if
+			 * scheduler fails to find a good waiting task to
+			 * migrate.
+			 */
+			if (load/2 > env->imbalance &&
+			    env->sd->nr_balance_failed <= env->sd->cache_nice_tries)
 				goto next;
 
 			env->imbalance -= load;
@@ -8418,6 +8425,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 	if (!idlest)
 		return NULL;
 
+	/* The local group has been skipped because of CPU affinity */
+	if (!local)
+		return idlest;
+
 	/*
 	 * If the local group is idler than the selected idlest group
 	 * don't try and push the task.
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e3719027e..ce8f6748678a 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -185,7 +185,8 @@ static void group_init(struct psi_group *group)
 
 	for_each_possible_cpu(cpu)
 		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
-	group->avg_next_update = sched_clock() + psi_period;
+	group->avg_last_update = sched_clock();
+	group->avg_next_update = group->avg_last_update + psi_period;
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
@@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
 		u32 remaining;
 
 		remaining = win->size - elapsed;
-		growth += div_u64(win->prev_growth * remaining, win->size);
+		growth += div64_u64(win->prev_growth * remaining, win->size);
 	}
 
 	return growth;