Rik noted a while back that a handful of sd->flags & SD_ASYM_CPUCAPACITY
& family in the CFS load-balancer code aren't guarded by the sched_asym_cpucapacity static branch. The load-balancer is already doing a humongous amount of work, but turning those checks into NOPs for those who don't need it is fairly straightforward, so do that. Suggested-by: Rik van Riel <[email protected]> Signed-off-by: Valentin Schneider <[email protected]> --- kernel/sched/fair.c | 11 ++++++----- kernel/sched/sched.h | 6 ++++++ 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0f6a4e58ce3c..7d01fa0bfc7e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8465,7 +8465,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, continue; /* Check for a misfit task on the cpu */ - if (env->sd->flags & SD_ASYM_CPUCAPACITY && + if (sd_has_asym_cpucapacity(env->sd) && sgs->group_misfit_task_load < rq->misfit_task_load) { sgs->group_misfit_task_load = rq->misfit_task_load; *sg_status |= SG_OVERLOAD; @@ -8522,7 +8522,8 @@ static bool update_sd_pick_busiest(struct lb_env *env, * CPUs in the group should either be possible to resolve * internally or be covered by avg_load imbalance (eventually). */ - if (sgs->group_type == group_misfit_task && + if (static_branch_unlikely(&sched_asym_cpucapacity) && + sgs->group_type == group_misfit_task && (!group_smaller_max_cpu_capacity(sg, sds->local) || sds->local_stat.group_type != group_has_spare)) return false; @@ -8605,7 +8606,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, * throughput. Maximize throughput, power/energy consequences are not * considered. */ - if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && + if (sd_has_asym_cpucapacity(env->sd) && (sgs->group_type <= group_fully_busy) && (group_smaller_min_cpu_capacity(sds->local, sg))) return false; @@ -8728,7 +8729,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, } /* Check if task fits in the group */ - if (sd->flags & SD_ASYM_CPUCAPACITY && + if (sd_has_asym_cpucapacity(sd) && !task_fits_capacity(p, group->sgc->max_capacity)) { sgs->group_misfit_task_load = 1; } @@ -9419,7 +9420,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, * Higher per-CPU capacity is considered better than balancing * average load. */ - if (env->sd->flags & SD_ASYM_CPUCAPACITY && + if (sd_has_asym_cpucapacity(env->sd) && capacity_of(env->dst_cpu) < capacity && nr_running == 1) continue; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 045b01064c1e..21bd71f58c06 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1482,6 +1482,12 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); extern struct static_key_false sched_asym_cpucapacity; +static inline bool sd_has_asym_cpucapacity(struct sched_domain *sd) +{ + return static_branch_unlikely(&sched_asym_cpucapacity) && + sd->flags & SD_ASYM_CPUCAPACITY; +} + struct sched_group_capacity { atomic_t ref; /* -- 2.27.0
