sched: Update max cpu capacity in case of max frequency constraints

Wakeup balancing uses cpu capacity awareness and needs to know the
system-wide maximum cpu capacity.

Patch "sched: Store system-wide maximum cpu capacity in root domain"
finds the system-wide maximum cpu capacity during scheduler domain
hierarchy setup. This is sufficient as long as maximum frequency
invariance is not enabled.

If it is enabled, the system-wide maximum cpu capacity can change
between scheduler domain hierarchy setups due to frequency capping.

The cpu capacity is changed in update_cpu_capacity() which is called in
load balance on the lowest scheduler domain hierarchy level. To be able
to know if a change in cpu capacity for a certain cpu also has an effect
on the system-wide maximum cpu capacity it is normally necessary to
iterate over all cpus. This would be way too costly. That's why this
patch follows a different approach.

The unsigned long max_cpu_capacity value in struct root_domain is
replaced with a struct max_cpu_capacity, containing value (the
max_cpu_capacity) and cpu (the cpu index of the cpu providing the
maximum cpu_capacity).

Changes to the system-wide maximum cpu capacity and the cpu index are
made if:

 1 System-wide maximum cpu capacity < cpu capacity
 2 System-wide maximum cpu capacity > cpu capacity and cpu index == cpu

There are no changes to the system-wide maximum cpu capacity in all
other cases.

Atomic read and write access to the pair (max_cpu_capacity.val,
max_cpu_capacity.cpu) is enforced by max_cpu_capacity.lock.

The access to max_cpu_capacity.val in task_fits_max() is still performed
without taking the max_cpu_capacity.lock.

The code to set max cpu capacity in build_sched_domains() has been
removed because the whole functionality is now provided by
update_cpu_capacity() instead.

This approach can introduce errors temporarily, e.g. in case the cpu
currently providing the max cpu capacity has its cpu capacity lowered
due to frequency capping and calls update_cpu_capacity() before any cpu
which might provide the max cpu now.

There is also an outstanding question:

Should the cpu capacity of a cpu going idle be set to a very small
value?

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>

kernel/sched/core.c

@@ -5892,6 +5892,8 @@ static int init_rootdomain(struct root_domain *rd)
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;
+
+	init_max_cpu_capacity(&rd->max_cpu_capacity);
 	return 0;
 
 free_rto_mask:
@@ -7109,15 +7111,9 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, i);
 		cpu_attach_domain(sd, d.rd, i);
-
-		if (rq->cpu_capacity_orig > rq->rd->max_cpu_capacity)
-			rq->rd->max_cpu_capacity = rq->cpu_capacity_orig;
 	}
 	rcu_read_unlock();
 
-	if (rq)
-		pr_info("max cpu_capacity %lu\n", rq->rd->max_cpu_capacity);
-
 	ret = 0;
 error:
 	__free_domain_allocs(&d, alloc_state, cpu_map);

kernel/sched/fair.c

@@ -5099,7 +5099,7 @@ static inline bool __task_fits(struct task_struct *p, int cpu, int util)
 static inline bool task_fits_max(struct task_struct *p, int cpu)
 {
 	unsigned long capacity = capacity_of(cpu);
-	unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity;
+	unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity.val;
 
 	if (capacity == max_capacity)
 		return true;
@@ -6585,13 +6585,43 @@ static unsigned long scale_rt_capacity(int cpu)
 	return 1;
 }
 
+void init_max_cpu_capacity(struct max_cpu_capacity *mcc)
+{
+	raw_spin_lock_init(&mcc->lock);
+	mcc->val = 0;
+	mcc->cpu = -1;
+}
+
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
 	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
 	struct sched_group *sdg = sd->groups;
+	struct max_cpu_capacity *mcc;
+	unsigned long max_capacity;
+	int max_cap_cpu;
+	unsigned long flags;
 
 	cpu_rq(cpu)->cpu_capacity_orig = capacity;
 
+	mcc = &cpu_rq(cpu)->rd->max_cpu_capacity;
+
+	raw_spin_lock_irqsave(&mcc->lock, flags);
+	max_capacity = mcc->val;
+	max_cap_cpu = mcc->cpu;
+
+	if ((max_capacity > capacity && max_cap_cpu == cpu) ||
+	    (max_capacity < capacity)) {
+		mcc->val = capacity;
+		mcc->cpu = cpu;
+#ifdef CONFIG_SCHED_DEBUG
+		raw_spin_unlock_irqrestore(&mcc->lock, flags);
+		pr_info("CPU%d: update max cpu_capacity %lu\n", cpu, capacity);
+		goto skip_unlock;
+#endif
+	}
+	raw_spin_unlock_irqrestore(&mcc->lock, flags);
+
+skip_unlock: __attribute__ ((unused));
 	capacity *= scale_rt_capacity(cpu);
 	capacity >>= SCHED_CAPACITY_SHIFT;
 

kernel/sched/sched.h

@@ -510,6 +510,12 @@ struct dl_rq {
 
 #ifdef CONFIG_SMP
 
+struct max_cpu_capacity {
+	raw_spinlock_t lock;
+	unsigned long val;
+	int cpu;
+};
+
 /*
  * We add the notion of a root-domain which will be used to define per-domain
  * variables. Each exclusive cpuset essentially defines an island domain by
@@ -548,7 +554,7 @@ struct root_domain {
 	struct cpupri cpupri;
 
 	/* Maximum cpu capacity in the system. */
-	unsigned long max_cpu_capacity;
+	struct max_cpu_capacity max_cpu_capacity;
 };
 
 extern struct root_domain def_root_domain;
@@ -1340,6 +1346,8 @@ unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
 
+extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc);
+
 static inline void add_nr_running(struct rq *rq, unsigned count)
 {
 	unsigned prev_nr = rq->nr_running;