Revert "XANMOD: fair: Remove all energy efficiency functions"

This reverts commit a237421.

kernel/sched/fair.c

@@ -6983,6 +6983,199 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 	return min(max_util, eenv->cpu_cap);
 }
 
+/*
+ * compute_energy(): Use the Energy Model to estimate the energy that @pd would
+ * consume for a given utilization landscape @eenv. When @dst_cpu < 0, the task
+ * contribution is ignored.
+ */
+static inline unsigned long
+compute_energy(struct energy_env *eenv, struct perf_domain *pd,
+	       struct cpumask *pd_cpus, struct task_struct *p, int dst_cpu)
+{
+	unsigned long max_util = eenv_pd_max_util(eenv, pd_cpus, p, dst_cpu);
+	unsigned long busy_time = eenv->pd_busy_time;
+
+	if (dst_cpu >= 0)
+		busy_time = min(eenv->pd_cap, busy_time + eenv->task_busy_time);
+
+	return em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+}
+
+/*
+ * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the
+ * waking task. find_energy_efficient_cpu() looks for the CPU with maximum
+ * spare capacity in each performance domain and uses it as a potential
+ * candidate to execute the task. Then, it uses the Energy Model to figure
+ * out which of the CPU candidates is the most energy-efficient.
+ *
+ * The rationale for this heuristic is as follows. In a performance domain,
+ * all the most energy efficient CPU candidates (according to the Energy
+ * Model) are those for which we'll request a low frequency. When there are
+ * several CPUs for which the frequency request will be the same, we don't
+ * have enough data to break the tie between them, because the Energy Model
+ * only includes active power costs. With this model, if we assume that
+ * frequency requests follow utilization (e.g. using schedutil), the CPU with
+ * the maximum spare capacity in a performance domain is guaranteed to be among
+ * the best candidates of the performance domain.
+ *
+ * In practice, it could be preferable from an energy standpoint to pack
+ * small tasks on a CPU in order to let other CPUs go in deeper idle states,
+ * but that could also hurt our chances to go cluster idle, and we have no
+ * ways to tell with the current Energy Model if this is actually a good
+ * idea or not. So, find_energy_efficient_cpu() basically favors
+ * cluster-packing, and spreading inside a cluster. That should at least be
+ * a good thing for latency, and this is consistent with the idea that most
+ * of the energy savings of EAS come from the asymmetry of the system, and
+ * not so much from breaking the tie between identical CPUs. That's also the
+ * reason why EAS is enabled in the topology code only for systems where
+ * SD_ASYM_CPUCAPACITY is set.
+ *
+ * NOTE: Forkees are not accepted in the energy-aware wake-up path because
+ * they don't have any useful utilization data yet and it's not possible to
+ * forecast their impact on energy consumption. Consequently, they will be
+ * placed by find_idlest_cpu() on the least loaded CPU, which might turn out
+ * to be energy-inefficient in some use-cases. The alternative would be to
+ * bias new tasks towards specific types of CPUs first, or to try to infer
+ * their util_avg from the parent task, but those heuristics could hurt
+ * other use-cases too. So, until someone finds a better way to solve this,
+ * let's keep things simple by re-using the existing slow path.
+ */
+static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
+{
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
+	unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
+	struct root_domain *rd = this_rq()->rd;
+	int cpu, best_energy_cpu, target = -1;
+	struct sched_domain *sd;
+	struct perf_domain *pd;
+	struct energy_env eenv;
+
+	rcu_read_lock();
+	pd = rcu_dereference(rd->pd);
+	if (!pd || READ_ONCE(rd->overutilized))
+		goto unlock;
+
+	/*
+	 * Energy-aware wake-up happens on the lowest sched_domain starting
+	 * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu.
+	 */
+	sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity));
+	while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+		sd = sd->parent;
+	if (!sd)
+		goto unlock;
+
+	target = prev_cpu;
+
+	sync_entity_load_avg(&p->se);
+	if (!task_util_est(p))
+		goto unlock;
+
+	eenv_task_busy_time(&eenv, p, prev_cpu);
+
+	for (; pd; pd = pd->next) {
+		unsigned long cpu_cap, cpu_thermal_cap, util;
+		unsigned long cur_delta, max_spare_cap = 0;
+		bool compute_prev_delta = false;
+		int max_spare_cap_cpu = -1;
+		unsigned long base_energy;
+
+		cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask);
+
+		if (cpumask_empty(cpus))
+			continue;
+
+		/* Account thermal pressure for the energy estimation */
+		cpu = cpumask_first(cpus);
+		cpu_thermal_cap = arch_scale_cpu_capacity(cpu);
+		cpu_thermal_cap -= arch_scale_thermal_pressure(cpu);
+
+		eenv.cpu_cap = cpu_thermal_cap;
+		eenv.pd_cap = 0;
+
+		for_each_cpu(cpu, cpus) {
+			eenv.pd_cap += cpu_thermal_cap;
+
+			if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+				continue;
+
+			if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+				continue;
+
+			util = cpu_util_next(cpu, p, cpu);
+			cpu_cap = capacity_of(cpu);
+
+			/*
+			 * Skip CPUs that cannot satisfy the capacity request.
+			 * IOW, placing the task there would make the CPU
+			 * overutilized. Take uclamp into account to see how
+			 * much capacity we can get out of the CPU; this is
+			 * aligned with sched_cpu_util().
+			 */
+			util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
+			if (!fits_capacity(util, cpu_cap))
+				continue;
+
+			lsub_positive(&cpu_cap, util);
+
+			if (cpu == prev_cpu) {
+				/* Always use prev_cpu as a candidate. */
+				compute_prev_delta = true;
+			} else if (cpu_cap > max_spare_cap) {
+				/*
+				 * Find the CPU with the maximum spare capacity
+				 * in the performance domain.
+				 */
+				max_spare_cap = cpu_cap;
+				max_spare_cap_cpu = cpu;
+			}
+		}
+
+		if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+			continue;
+
+		eenv_pd_busy_time(&eenv, cpus, p);
+		/* Compute the 'base' energy of the pd, without @p */
+		base_energy = compute_energy(&eenv, pd, cpus, p, -1);
+
+		/* Evaluate the energy impact of using prev_cpu. */
+		if (compute_prev_delta) {
+			prev_delta = compute_energy(&eenv, pd, cpus, p,
+						    prev_cpu);
+			/* CPU utilization has changed */
+			if (prev_delta < base_energy)
+				goto unlock;
+			prev_delta -= base_energy;
+			best_delta = min(best_delta, prev_delta);
+		}
+
+		/* Evaluate the energy impact of using max_spare_cap_cpu. */
+		if (max_spare_cap_cpu >= 0) {
+			cur_delta = compute_energy(&eenv, pd, cpus, p,
+						   max_spare_cap_cpu);
+			/* CPU utilization has changed */
+			if (cur_delta < base_energy)
+				goto unlock;
+			cur_delta -= base_energy;
+			if (cur_delta < best_delta) {
+				best_delta = cur_delta;
+				best_energy_cpu = max_spare_cap_cpu;
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	if (best_delta < prev_delta)
+		target = best_energy_cpu;
+
+	return target;
+
+unlock:
+	rcu_read_unlock();
+
+	return target;
+}
+
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
  * that have the relevant SD flag set. In practice, this is SD_BALANCE_WAKE,
@@ -7010,6 +7203,14 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 	lockdep_assert_held(&p->pi_lock);
 	if (wake_flags & WF_TTWU) {
 		record_wakee(p);
+
+		if (sched_energy_enabled()) {
+			new_cpu = find_energy_efficient_cpu(p, prev_cpu);
+			if (new_cpu >= 0)
+				return new_cpu;
+			new_cpu = prev_cpu;
+		}
+
 		want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr);
 	}