sched: Initialize energy data structures

The sched_group_energy (sge) pointer of the first sched_group (sg) in
the sched_domain (sd) is initialized to point to the appropriate (in
terms of sd level and cpu) sge data defined in the arch and so to the
correct part of the Energy Model (EM).

Energy-aware scheduling allows that a system has only EM data up to a
certain sd level (so called highest energy aware balancing sd level).
A check in init_sched_energy() enforces that all sd's below this sd
level contain EM data.

The 'int cpu' parameter of sched_domain_energy_f requires that
check_sched_energy_data() makes sure that all cpus spanned by a sg
are provisioned with the same EM data.

This patch has also been tested with feature FORCE_SD_OVERLAP enabled.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7c6e2b3263490f57d58ac30556c11630a9bc3744..f1b1c9eaeb107179219eb3dbe35d86df5778b5a3 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6304,6 +6304,66 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
        atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight);
 }
 
+/*
+ * Check that the per-cpu provided sd energy data is consistent for all cpus
+ * within the mask.
+ */
+static inline void check_sched_energy_data(int cpu, sched_domain_energy_f fn,
+                                          const struct cpumask *cpumask)
+{
+       const struct sched_group_energy * const sge = fn(cpu);
+       struct cpumask mask;
+       int i;
+
+       if (cpumask_weight(cpumask) <= 1)
+               return;
+
+       cpumask_xor(&mask, cpumask, get_cpu_mask(cpu));
+
+       for_each_cpu(i, &mask) {
+               const struct sched_group_energy * const e = fn(i);
+               int y;
+
+               BUG_ON(e->nr_idle_states != sge->nr_idle_states);
+
+               for (y = 0; y < (e->nr_idle_states); y++) {
+                       BUG_ON(e->idle_states[y].power !=
+                                       sge->idle_states[y].power);
+               }
+
+               BUG_ON(e->nr_cap_states != sge->nr_cap_states);
+
+               for (y = 0; y < (e->nr_cap_states); y++) {
+                       BUG_ON(e->cap_states[y].cap != sge->cap_states[y].cap);
+                       BUG_ON(e->cap_states[y].power !=
+                                       sge->cap_states[y].power);
+               }
+       }
+}
+
+static void init_sched_energy(int cpu, struct sched_domain *sd,
+                             sched_domain_energy_f fn)
+{
+       if (!(fn && fn(cpu)))
+               return;
+
+       if (cpu != group_balance_cpu(sd->groups))
+               return;
+
+       if (sd->child && !sd->child->groups->sge) {
+               pr_err("BUG: EAS setup broken for CPU%d\n", cpu);
+#ifdef CONFIG_SCHED_DEBUG
+               pr_err("     energy data on %s but not on %s domain\n",
+                       sd->name, sd->child->name);
+#endif
+               return;
+       }
+
+       check_sched_energy_data(cpu, fn, sched_group_cpus(sd->groups));
+
+       sd->groups->sge = fn(cpu);
+}
+
 /*
  * Initializers for schedule domains
  * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
@@ -7010,10 +7070,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 
        /* Calculate CPU capacity for physical packages and nodes */
        for (i = nr_cpumask_bits-1; i >= 0; i--) {
+               struct sched_domain_topology_level *tl = sched_domain_topology;
+
                if (!cpumask_test_cpu(i, cpu_map))
                        continue;
 
-               for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+               for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent, tl++) {
+                       init_sched_energy(i, sd, tl->energy);
                        claim_allocations(i, sd);
                        init_sched_groups_capacity(i, sd);
                }