Messages in this thread Patch in this message | | | From | Morten Rasmussen <> | Subject | [RFC PATCH 03/16] sched: Introduce sd energy data structures | Date | Fri, 23 May 2014 19:16:30 +0100 |
| |
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
The struct sched_energy represents the per scheduler group related data which is needed for the energy aware scheduler.
It contains a pointer to a struct capacity_state array which contains (compute capacity, power consumption @ this compute capacity) tuples.
The struct sched_group_energy wraps struct sched_energy and an atomic reference counter, latter is used for scheduler internal bookkeeping of data allocation and freeing.
Allocation and freeing of struct sched_group_energy uses the existing infrastructure of the scheduler which is currently used for the other sd hierarchy data structures (e.g. struct sched_domain). That's why struct sd_data is provisioned with a per cpu struct sched_group_energy double pointer.
The struct sched_group gets a pointer to a struct sched_group_energy.
The function ptr sched_domain_energy_f is introduced into struct sched_domain_topology_level which will allow the arch to set a pass a particular struct sd_energy from the topology shim layer into the scheduler core.
The function ptr 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. E.g. it is not possible to use this feature to provide per-cpu sd energy in sd level DIE (former CPU) 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 set-up 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 scheduler building block (e.g a sched domain or a group) are provisioned with the same energy data.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com> --- include/linux/sched.h | 24 ++++++++++++++++++++++++ kernel/sched/sched.h | 10 ++++++++++ 2 files changed, 34 insertions(+)
diff --git a/include/linux/sched.h b/include/linux/sched.h index 261a419..4eb149b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -909,6 +909,21 @@ struct sched_domain_attr { extern int sched_domain_level_max; +#ifdef CONFIG_SCHED_ENERGY +struct capacity_state { + int cap; /* compute capacity */ + int power; /* power consumption at this compute capacity */ +}; + +struct sched_energy { + long max_capacity; /* maximal compute capacity */ + int idle_power; /* power consumption in idle state */ + int wakeup_energy; /* energy for wakeup->sleep cycle (x1024) */ + int nr_cap_states; /* number of capacity states */ + struct capacity_state *cap_states; /* ptr to capacity state array */ +}; +#endif + struct sched_group; struct sched_domain { @@ -1007,6 +1022,9 @@ bool cpus_share_cache(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef const int (*sched_domain_flags_f)(void); +#ifdef CONFIG_SCHED_ENERGY +typedef const struct sched_energy *(*sched_domain_energy_f)(int cpu); +#endif #define SDTL_OVERLAP 0x01 @@ -1014,11 +1032,17 @@ struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; struct sched_group_power **__percpu sgp; +#ifdef CONFIG_SCHED_ENERGY + struct sched_group_energy **__percpu sge; +#endif }; struct sched_domain_topology_level { sched_domain_mask_f mask; sched_domain_flags_f sd_flags; +#ifdef CONFIG_SCHED_ENERGY + sched_domain_energy_f energy; +#endif int flags; int numa_level; struct sd_data data; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 456e492..c566f5e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -755,12 +755,22 @@ struct sched_group_power { unsigned long cpumask[0]; /* iteration mask */ }; +#ifdef CONFIG_SCHED_ENERGY +struct sched_group_energy { + atomic_t ref; + struct sched_energy data; +}; +#endif + struct sched_group { struct sched_group *next; /* Must be a circular list */ atomic_t ref; unsigned int group_weight; struct sched_group_power *sgp; +#ifdef CONFIG_SCHED_ENERGY + struct sched_group_energy *sge; +#endif /* * The CPUs this group covers. -- 1.7.9.5
| |