sched/core: Store maximum per-CPU capacity in root domain

To be able to compare the capacity of the target CPU with the highest
available CPU capacity, store the maximum per-CPU capacity in the root
domain.

The max per-CPU capacity should be 1024 for all systems except SMT,
where the capacity is currently based on smt_gain and the number of
hardware threads and is <1024. If SMT can be brought to work with a
per-thread capacity of 1024, this patch can be dropped and replaced by a
hard-coded max capacity of 1024 (=SCHED_CAPACITY_SCALE).

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: freedom.tan@mediatek.com
Cc: keita.kobayashi.ym@renesas.com
Cc: mgalbraith@suse.de
Cc: sgurrappadi@nvidia.com
Cc: vincent.guittot@linaro.org
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/26c69258-9947-f830-a53e-0c54e7750646@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -6903,6 +6903,7 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 	enum s_alloc alloc_state;
 	struct sched_domain *sd;
 	struct s_data d;
+	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
 
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
@@ -6953,11 +6954,22 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
+		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, 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);
+
 		cpu_attach_domain(sd, d.rd, i);
 	}
 	rcu_read_unlock();
 
+	if (rq) {
+		pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
+	}
+
 	ret = 0;
 error:
 	__free_domain_allocs(&d, alloc_state, cpu_map);

kernel/sched/sched.h

@@ -565,6 +565,8 @@ struct root_domain {
 	 */
 	cpumask_var_t rto_mask;
 	struct cpupri cpupri;
+
+	unsigned long max_cpu_capacity;
 };
 
 extern struct root_domain def_root_domain;