sched: backport cpufreq hooks from 4.9-rc4

The scheduler cpufreq hooks are required by the schedutil cpufreq
governor.

Change-Id: Ied6c46262bb33b7e81bbb3d3d2761124e0c676b7
Signed-off-by: Steve Muckle <smuckle@linaro.org>
[trivial cherry-picking fixes]
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>

include/linux/sched.h

@@ -3291,4 +3291,21 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#define SCHED_CPUFREQ_RT        (1U << 0)
+#define SCHED_CPUFREQ_DL        (1U << 1)
+#define SCHED_CPUFREQ_IOWAIT    (1U << 2)
+
+#define SCHED_CPUFREQ_RT_DL     (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
+
+#ifdef CONFIG_CPU_FREQ
+struct update_util_data {
+	void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
+};
+
+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);
+#endif /* CONFIG_CPU_FREQ */
+
 #endif

kernel/sched/Makefile

@@ -21,4 +21,5 @@ obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_SCHED_TUNE) += tune.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+obj-$(CONFIG_CPU_FREQ) += cpufreq.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHED) += cpufreq_sched.o

kernel/sched/cpufreq.c

@@ -0,0 +1,63 @@
+/*
+ * Scheduler code and data structures related to cpufreq.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "sched.h"
+
+DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.
+ * @cpu: The CPU to set the pointer for.
+ * @data: New pointer value.
+ * @func: Callback function to set for the CPU.
+ *
+ * Set and publish the update_util_data pointer for the given CPU.
+ *
+ * The update_util_data pointer of @cpu is set to @data and the callback
+ * function pointer in the target struct update_util_data is set to @func.
+ * That function will be called by cpufreq_update_util() from RCU-sched
+ * read-side critical sections, so it must not sleep.  @data will always be
+ * passed to it as the first argument which allows the function to get to the
+ * target update_util_data structure and its container.
+ *
+ * The update_util_data pointer of @cpu must be NULL when this function is
+ * called or it will WARN() and return with no effect.
+ */
+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))
+{
+	if (WARN_ON(!data || !func))
+		return;
+
+	if (WARN_ON(per_cpu(cpufreq_update_util_data, cpu)))
+		return;
+
+	data->func = func;
+	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
+}
+EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook);
+
+/**
+ * cpufreq_remove_update_util_hook - Clear the CPU's update_util_data pointer.
+ * @cpu: The CPU to clear the pointer for.
+ *
+ * Clear the update_util_data pointer for the given CPU.
+ *
+ * Callers must use RCU-sched callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * right after this function to avoid use-after-free.
+ */
+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);

kernel/sched/deadline.c

@@ -753,6 +753,9 @@ static void update_curr_dl(struct rq *rq)
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
+	/* kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
+
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
 

kernel/sched/fair.c

@@ -2711,6 +2711,29 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
+static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
+{
+        if (&this_rq()->cfs == cfs_rq) {
+                /*
+                 * There are a few boundary cases this might miss but it should
+                 * get called often enough that that should (hopefully) not be
+                 * a real problem -- added to that it only calls on the local
+                 * CPU, so if we enqueue remotely we'll miss an update, but
+                 * the next tick/schedule should update.
+                 *
+                 * It will not get called when we go idle, because the idle
+                 * thread is a different class (!fair), nor will the utilization
+                 * number include things like RT tasks.
+                 *
+                 * As is, the util number is not freq-invariant (we'd have to
+                 * implement arch_scale_freq_capacity() for that).
+                 *
+                 * See cpu_util().
+                 */
+                cpufreq_update_util(rq_of(cfs_rq), 0);
+        }
+}
+
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 
 /*
@@ -2731,10 +2754,11 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 } while (0)
 
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
-static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq,
+					 bool update_freq)
 {
 	struct sched_avg *sa = &cfs_rq->avg;
-	int decayed, removed = 0;
+	int decayed, removed = 0, removed_util = 0;
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
@@ -2747,6 +2771,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
 		sub_positive(&sa->util_avg, r);
 		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
+		removed_util = 1;
 	}
 
 	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2761,6 +2786,9 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	if (cfs_rq == &rq_of(cfs_rq)->cfs)
 		trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
 
+	if (update_freq && (decayed || removed_util))
+		cfs_rq_util_change(cfs_rq);
+
 	return decayed || removed;
 }
 
@@ -2779,7 +2807,7 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 			  se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
+	if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
 
 	if (entity_is_task(se))
@@ -2811,6 +2839,8 @@ skip_aging:
 	cfs_rq->avg.load_sum += se->avg.load_sum;
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
+
+	cfs_rq_util_change(cfs_rq);
 }
 
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -2823,6 +2853,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+
+	cfs_rq_util_change(cfs_rq);
 }
 
 /* Add the load generated by se into cfs_rq's load average */
@@ -2840,7 +2872,7 @@ enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 			cfs_rq->curr == se, NULL);
 	}
 
-	decayed = update_cfs_rq_load_avg(now, cfs_rq);
+	decayed = update_cfs_rq_load_avg(now, cfs_rq, !migrated);
 
 	cfs_rq->runnable_load_avg += sa->load_avg;
 	cfs_rq->runnable_load_sum += sa->load_sum;
@@ -2940,7 +2972,11 @@ static int idle_balance(struct rq *this_rq);
 
 #else /* CONFIG_SMP */
 
-static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline void update_load_avg(struct sched_entity *se, int update_tg)
+{
+	cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
+}
+
 static inline void
 enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
@@ -4257,6 +4293,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	int task_wakeup = flags & ENQUEUE_WAKEUP;
 #endif
 
+	/*
+	 * If in_iowait is set, the code below may not trigger any cpufreq
+	 * utilization updates, so do it here explicitly with the IOWAIT flag
+	 * passed.
+	 */
+	if (p->in_iowait)
+		cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+
 	for_each_sched_entity(se) {
 		if (se->on_rq)
 			break;
@@ -6923,7 +6967,8 @@ static void update_blocked_averages(int cpu)
 		if (throttled_hierarchy(cfs_rq))
 			continue;
 
-		if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
+		if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq,
+					   true))
 			update_tg_load_avg(cfs_rq, 0);
 	}
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -6984,7 +7029,7 @@ static inline void update_blocked_averages(int cpu)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 	update_rq_clock(rq);
-	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 

kernel/sched/rt.c

@@ -1002,6 +1002,9 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
+	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
 

kernel/sched/sched.h

@@ -2038,3 +2038,55 @@ static inline void account_reset_rq(struct rq *rq)
 	rq->prev_steal_time_rq = 0;
 #endif
 }
+
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @rq: Runqueue to carry out the update for.
+ * @flags: Update reason flags.
+ *
+ * This function is called by the scheduler on the CPU whose utilization is
+ * being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid.  Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
+{
+        struct update_util_data *data;
+
+        data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+        if (data)
+                data->func(data, rq_clock(rq), flags);
+}
+
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
+{
+        if (cpu_of(rq) == smp_processor_id())
+                cpufreq_update_util(rq, flags);
+}
+#else
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
+#endif /* CONFIG_CPU_FREQ */
+
+#ifdef arch_scale_freq_capacity
+#ifndef arch_scale_freq_invariant
+#define arch_scale_freq_invariant()     (true)
+#endif
+#else /* arch_scale_freq_capacity */
+#define arch_scale_freq_invariant()     (false)
+#endif