[PATCH v5 07/14] sched/topology: Introduce sched_energy_present static key

[Quentin Perret]

In order to ensure a minimal performance impact on non-energy-aware
systems, introduce a static_key guarding the access to Energy-Aware
Scheduling (EAS) code.

The static key is set iff all the following conditions are met for at
least one root domain:
  1. all online CPUs of the root domain are covered by the Energy
     Model (EM);
  2. the complexity of the root domain's EM is low enough to keep
     scheduling overheads low;
  3. the root domain has an asymmetric CPU capacity topology (detected
     by looking for the SD_ASYM_CPUCAPACITY flag in the sched_domain
     hierarchy).

The static key is checked in the rd_freq_domain() function which returns
the frequency domains of a root domain when they are available. As EAS
cannot be enabled with CONFIG_ENERGY_MODEL=n, rd_freq_domain() is
stubbed to 'NULL' to let the compiler remove the unused EAS code by
constant propagation.

cc: Ingo Molnar <mingo@xxxxxxxxxx>
cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Quentin Perret <quentin.perret@xxxxxxx>
---
 kernel/sched/sched.h    | 17 ++++++++++
 kernel/sched/topology.c | 73 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 25d64a0b6fe0..a317457804dd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2222,8 +2222,25 @@ static inline unsigned long cpu_util_irq(struct rq *rq)
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_ENERGY_MODEL
+extern struct static_key_false sched_energy_present;
+/**
+ * rd_freq_domain - Get the frequency domains of a root domain.
+ *
+ * Must be called from a RCU read-side critical section.
+ */
+static inline struct freq_domain *rd_freq_domain(struct root_domain *rd)
+{
+	if (!static_branch_unlikely(&sched_energy_present))
+		return NULL;
+
+	return rcu_dereference(rd->fd);
+}
 #define freq_domain_span(fd) (to_cpumask(((fd)->obj->cpus)))
 #else
+static inline struct freq_domain *rd_freq_domain(struct root_domain *rd)
+{
+	return NULL;
+}
 #define freq_domain_span(fd) NULL
 #endif
 #endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8f3f746b0d5e..483bb7bf7af6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -275,12 +275,32 @@ static void destroy_freq_domain_rcu(struct rcu_head *rp)
 	free_fd(fd);
 }
 
+/*
+ * The complexity of the Energy Model is defined as: nr_fd * (nr_cpus + nr_cs)
+ * with: 'nr_fd' the number of frequency domains; 'nr_cpus' the number of CPUs;
+ * and 'nr_cs' the sum of the capacity states numbers of all frequency domains.
+ *
+ * It is generally not a good idea to use such a model in the wake-up path on
+ * very complex platforms because of the associated scheduling overheads. The
+ * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
+ * with per-CPU DVFS and less than 8 capacity states each, for example.
+ */
+#define EM_MAX_COMPLEXITY 2048
+
+
 static void build_freq_domains(const struct cpumask *cpu_map)
 {
+	int i, nr_fd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct freq_domain *fd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
-	int i;
+
+	/* EAS is enabled for asymmetric CPU capacity topologies. */
+	if (!per_cpu(sd_ea, cpu)) {
+		if (sched_debug())
+			pr_info("rd %*pbl: !sd_ea\n", cpumask_pr_args(cpu_map));
+		goto free;
+	}
 
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
@@ -293,6 +313,18 @@ static void build_freq_domains(const struct cpumask *cpu_map)
 			goto free;
 		tmp->next = fd;
 		fd = tmp;
+
+		/* Count freq. doms and perf states for the complexity check. */
+		nr_fd++;
+		nr_cs += em_fd_nr_cap_states(fd->obj);
+	}
+
+	/* Bail out if the Energy Model complexity is too high. */
+	if (nr_fd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+		if (sched_debug())
+			pr_info("rd %*pbl: EM complexity is too high\n ",
+						cpumask_pr_args(cpu_map));
+		goto free;
 	}
 
 	freq_domain_debug(cpu_map, fd);
@@ -312,6 +344,44 @@ static void build_freq_domains(const struct cpumask *cpu_map)
 	if (tmp)
 		call_rcu(&tmp->rcu, destroy_freq_domain_rcu);
 }
+
+/*
+ * This static_key is set if at least one root domain meets all the following
+ * conditions:
+ *    1. all CPUs of the root domain are covered by the EM;
+ *    2. the EM complexity is low enough to keep scheduling overheads low;
+ *    3. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
+ */
+DEFINE_STATIC_KEY_FALSE(sched_energy_present);
+
+static void sched_energy_start(int ndoms_new, cpumask_var_t doms_new[])
+{
+	/*
+	 * The conditions for EAS to start are checked during the creation of
+	 * root domains. If one of them meets all conditions, it will have a
+	 * non-null list of frequency domains.
+	 */
+	while (ndoms_new) {
+		if (cpu_rq(cpumask_first(doms_new[ndoms_new - 1]))->rd->fd)
+			goto enable;
+		ndoms_new--;
+	}
+
+	if (static_branch_unlikely(&sched_energy_present)) {
+		if (sched_debug())
+			pr_info("%s: stopping EAS\n", __func__);
+		static_branch_disable_cpuslocked(&sched_energy_present);
+	}
+
+	return;
+
+enable:
+	if (!static_branch_unlikely(&sched_energy_present)) {
+		if (sched_debug())
+			pr_info("%s: starting EAS\n", __func__);
+		static_branch_enable_cpuslocked(&sched_energy_present);
+	}
+}
 #else
 static void free_rd_fd(struct root_domain *rd) { }
 #endif
@@ -2046,6 +2116,7 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 match3:
 		;
 	}
+	sched_energy_start(ndoms_new, doms_new);
 #endif
 
 	/* Remember the new sched domains: */
-- 
2.18.0