sched/topology: Consolidate and clean up access to a CPU's max compute capacity

Remove the rq::cpu_capacity_orig field and use arch_scale_cpu_capacity()
instead.

The scheduler uses 3 methods to get access to a CPU's max compute capacity:

- arch_scale_cpu_capacity(cpu) which is the default way to get a CPU's capacity.

- cpu_capacity_orig field which is periodically updated with
arch_scale_cpu_capacity().

- capacity_orig_of(cpu) which encapsulates rq->cpu_capacity_orig.

There is no real need to save the value returned by arch_scale_cpu_capacity()
in struct rq. arch_scale_cpu_capacity() returns:

- either a per_cpu variable.

- or a const value for systems which have only one capacity.

Remove rq::cpu_capacity_orig and use arch_scale_cpu_capacity() everywhere.

No functional changes.

Some performance tests on Arm64:

- small SMP device (hikey): no noticeable changes
- HMP device (RB5): hackbench shows minor improvement (1-2%)
- large smp (thx2): hackbench and tbench shows minor improvement (1%)

Signed-off-by: Vincent Guittot <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>
Reviewed-by: Dietmar Eggemann <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

Documentation/scheduler/sched-capacity.rst

···
 -------------------
 
 Two different capacity values are used within the scheduler. A CPU's
-``capacity_orig`` is its maximum attainable capacity, i.e. its maximum
-attainable performance level. A CPU's ``capacity`` is its ``capacity_orig`` to
-which some loss of available performance (e.g. time spent handling IRQs) is
-subtracted.
+``original capacity`` is its maximum attainable capacity, i.e. its maximum
+attainable performance level. This original capacity is returned by
+the function arch_scale_cpu_capacity(). A CPU's ``capacity`` is its ``original
+capacity`` to which some loss of available performance (e.g. time spent
+handling IRQs) is subtracted.
 
 Note that a CPU's ``capacity`` is solely intended to be used by the CFS class,
-while ``capacity_orig`` is class-agnostic. The rest of this document will use
-the term ``capacity`` interchangeably with ``capacity_orig`` for the sake of
+while ``original capacity`` is class-agnostic. The rest of this document will use
+the term ``capacity`` interchangeably with ``original capacity`` for the sake of
 brevity.
 
 1.3 Platform examples

kernel/sched/core.c

···
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
+		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
 		rq->balance_callback = &balance_push_callback;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;

kernel/sched/cpudeadline.c

···
 			if (!dl_task_fits_capacity(p, cpu)) {
 				cpumask_clear_cpu(cpu, later_mask);
 
-				cap = capacity_orig_of(cpu);
+				cap = arch_scale_cpu_capacity(cpu);
 
 				if (cap > max_cap ||
 				    (cpu == task_cpu(p) && cap == max_cap)) {

kernel/sched/deadline.c

···
 	int i;
 
 	for_each_cpu_and(i, mask, cpu_active_mask)
-		cap += capacity_orig_of(i);
+		cap += arch_scale_cpu_capacity(i);
 
 	return cap;
 }
···
 static inline unsigned long dl_bw_capacity(int i)
 {
 	if (!sched_asym_cpucap_active() &&
-	    capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
+	    arch_scale_cpu_capacity(i) == SCHED_CAPACITY_SCALE) {
 		return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
 	} else {
 		RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),

kernel/sched/fair.c

···
 	 * To avoid overestimation of actual task utilization, skip updates if
 	 * we cannot grant there is idle time in this CPU.
 	 */
-	if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq))))
+	if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
 		return;
 
 	/*
···
 		return fits;
 
 	/*
-	 * We must use capacity_orig_of() for comparing against uclamp_min and
+	 * We must use arch_scale_cpu_capacity() for comparing against uclamp_min and
 	 * uclamp_max. We only care about capacity pressure (by using
 	 * capacity_of()) for comparing against the real util.
 	 *
 	 * If a task is boosted to 1024 for example, we don't want a tiny
 	 * pressure to skew the check whether it fits a CPU or not.
 	 *
-	 * Similarly if a task is capped to capacity_orig_of(little_cpu), it
+	 * Similarly if a task is capped to arch_scale_cpu_capacity(little_cpu), it
 	 * should fit a little cpu even if there's some pressure.
 	 *
 	 * Only exception is for thermal pressure since it has a direct impact
···
 	 * For uclamp_max, we can tolerate a drop in performance level as the
 	 * goal is to cap the task. So it's okay if it's getting less.
 	 */
-	capacity_orig = capacity_orig_of(cpu);
+	capacity_orig = arch_scale_cpu_capacity(cpu);
 	capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);
 
 	/*
···
 		 * Look for the CPU with best capacity.
 		 */
 		else if (fits < 0)
-			cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu));
+			cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu));
 
 		/*
 		 * First, select CPU which fits better (-1 being better than 0).
···
 		util = max(util, util_est);
 	}
 
-	return min(util, capacity_orig_of(cpu));
+	return min(util, arch_scale_cpu_capacity(cpu));
 }
 
 unsigned long cpu_util_cfs(int cpu)
···
 	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
-
 	if (!capacity)
 		capacity = 1;
 
···
 check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 {
 	return ((rq->cpu_capacity * sd->imbalance_pct) <
-				(rq->cpu_capacity_orig * 100));
+				(arch_scale_cpu_capacity(cpu_of(rq)) * 100));
 }
 
 /*
···
 static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
 {
 	return rq->misfit_task_load &&
-		(rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+		(arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity ||
 		 check_cpu_capacity(rq, sd));
 }
 

kernel/sched/rt.c

···
 	min_cap = uclamp_eff_value(p, UCLAMP_MIN);
 	max_cap = uclamp_eff_value(p, UCLAMP_MAX);
 
-	cpu_cap = capacity_orig_of(cpu);
+	cpu_cap = arch_scale_cpu_capacity(cpu);
 
 	return cpu_cap >= min(min_cap, max_cap);
 }

kernel/sched/sched.h

···
 	struct sched_domain __rcu	*sd;
 
 	unsigned long		cpu_capacity;
-	unsigned long		cpu_capacity_orig;
 
 	struct balance_callback *balance_callback;
 
···
 #endif
 
 #ifdef CONFIG_SMP
-static inline unsigned long capacity_orig_of(int cpu)
-{
-	return cpu_rq(cpu)->cpu_capacity_orig;
-}
-
 /**
  * enum cpu_util_type - CPU utilization type
  * @FREQUENCY_UTIL:	Utilization used to select frequency

kernel/sched/topology.c

···
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
+		unsigned long capacity;
+
 		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, i);
 
+		capacity = arch_scale_cpu_capacity(i);
 		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
-		if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
-			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+		if (capacity > READ_ONCE(d.rd->max_cpu_capacity))
+			WRITE_ONCE(d.rd->max_cpu_capacity, capacity);
 
 		cpu_attach_domain(sd, d.rd, i);
 	}