From 7274a5c1bbec45f06f1fff4b8c8b5855b6cc189d Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Thu, 22 Aug 2019 14:28:08 +0100 Subject: [PATCH] sched/uclamp: Propagate system defaults to the root group The clamp values are not tunable at the level of the root task group. That's for two main reasons: - the root group represents "system resources" which are always entirely available from the cgroup standpoint. - when tuning/restricting "system resources" makes sense, tuning must be done using a system wide API which should also be available when control groups are not. When a system wide restriction is available, cgroups should be aware of its value in order to know exactly how much "system resources" are available for the subgroups. Utilization clamping supports already the concepts of: - system defaults: which define the maximum possible clamp values usable by tasks. - effective clamps: which allows a parent cgroup to constraint (maybe temporarily) its descendants without losing the information related to the values "requested" from them. Exploit these two concepts and bind them together in such a way that, whenever system default are tuned, the new values are propagated to (possibly) restrict or relax the "effective" value of nested cgroups. When cgroups are in use, force an update of all the RUNNABLE tasks. Otherwise, keep things simple and do just a lazy update next time each task will be enqueued. Do that since we assume a more strict resource control is required when cgroups are in use. This allows also to keep "effective" clamp values updated in case we need to expose them to user-space. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Michal Koutny Acked-by: Tejun Heo Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190822132811.31294-4-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8855481857b5..e6800fe040ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1017,10 +1017,30 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) uclamp_rq_dec_id(rq, p, clamp_id); } +#ifdef CONFIG_UCLAMP_TASK_GROUP +static void cpu_util_update_eff(struct cgroup_subsys_state *css); +static void uclamp_update_root_tg(void) +{ + struct task_group *tg = &root_task_group; + + uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN], + sysctl_sched_uclamp_util_min, false); + uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX], + sysctl_sched_uclamp_util_max, false); + + rcu_read_lock(); + cpu_util_update_eff(&root_task_group.css); + rcu_read_unlock(); +} +#else +static void uclamp_update_root_tg(void) { } +#endif + int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + bool update_root_tg = false; int old_min, old_max; int result; @@ -1043,16 +1063,23 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, if (old_min != sysctl_sched_uclamp_util_min) { uclamp_se_set(&uclamp_default[UCLAMP_MIN], sysctl_sched_uclamp_util_min, false); + update_root_tg = true; } if (old_max != sysctl_sched_uclamp_util_max) { uclamp_se_set(&uclamp_default[UCLAMP_MAX], sysctl_sched_uclamp_util_max, false); + update_root_tg = true; } + if (update_root_tg) + uclamp_update_root_tg(); + /* - * Updating all the RUNNABLE task is expensive, keep it simple and do - * just a lazy update at each next enqueue time. + * We update all RUNNABLE tasks only when task groups are in use. + * Otherwise, keep it simple and do just a lazy update at each next + * task enqueue time. */ + goto done; undo: -- 2.30.2