sched: Introduce energy data structures

The struct sched_group_energy represents the per sched_group related
data which is needed for energy aware scheduling. It contains:

  (1) number of elements of the idle state array
  (2) pointer to the idle state array which comprises 'power consumption'
      for each idle state
  (3) number of elements of the capacity state array
  (4) pointer to the capacity state array which comprises 'compute
      capacity and power consumption' tuples for each capacity state

The struct sched_group obtains a pointer to a struct sched_group_energy.

The function pointer sched_domain_energy_f is introduced into struct
sched_domain_topology_level which will allow the arch to pass a particular
struct sched_group_energy from the topology shim layer into the scheduler
core.

The function pointer sched_domain_energy_f has an 'int cpu' parameter
since the folding of two adjacent sd levels via sd degenerate doesn't work
for all sd levels. I.e. it is not possible for example to use this feature
to provide per-cpu energy in sd level DIE on ARM's TC2 platform.

It was discussed that the folding of sd levels approach is preferable
over the cpu parameter approach, simply because the user (the arch
specifying the sd topology table) can introduce less errors. But since
it is not working, the 'int cpu' parameter is the only way out. It's
possible to use the folding of sd levels approach for
sched_domain_flags_f and the cpu parameter approach for the
sched_domain_energy_f at the same time though. With the use of the
'int cpu' parameter, an extra check function has to be provided to make
sure that all cpus spanned by a sched group are provisioned with the same
energy data.

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

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fa39434e3fdd1c74eaf18dd4a31dae0b69a9db1c..5bee272a86d8e660321204db0625e6411ea34959 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1021,6 +1021,22 @@ struct sched_domain_attr {
 
 extern int sched_domain_level_max;
 
+struct capacity_state {
+       unsigned long cap;      /* compute capacity */
+       unsigned long power;    /* power consumption at this compute capacity */
+};
+
+struct idle_state {
+       unsigned long power;     /* power consumption in this idle state */
+};
+
+struct sched_group_energy {
+       unsigned int nr_idle_states;    /* number of idle states */
+       struct idle_state *idle_states; /* ptr to idle state array */
+       unsigned int nr_cap_states;     /* number of capacity states */
+       struct capacity_state *cap_states; /* ptr to capacity state array */
+};
+
 struct sched_group;
 
 struct sched_domain {
@@ -1119,6 +1135,8 @@ bool cpus_share_cache(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
+typedef
+const struct sched_group_energy * const(*sched_domain_energy_f)(int cpu);
 
 #define SDTL_OVERLAP   0x01
 
@@ -1131,6 +1149,7 @@ struct sd_data {
 struct sched_domain_topology_level {
        sched_domain_mask_f mask;
        sched_domain_flags_f sd_flags;
+       sched_domain_energy_f energy;
        int                 flags;
        int                 numa_level;
        struct sd_data      data;

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2b7ffa5a20ad4836efa2ecb812fb05f50f1355d3..1813cba2995d752a9ba423025baf0fda23bd9b84 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -863,6 +863,7 @@ struct sched_group {
 
        unsigned int group_weight;
        struct sched_group_capacity *sgc;
+       const struct sched_group_energy const *sge;
 
        /*
         * The CPUs this group covers.