From: Patrick Bellasi <patrick.bellasi@arm.com> To: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org Cc: Ingo Molnar <mingo@redhat.com>, Peter Zijlstra <peterz@infradead.org>, Tejun Heo <tj@kernel.org>, "Rafael J . Wysocki" <rafael.j.wysocki@intel.com>, Viresh Kumar <viresh.kumar@linaro.org>, Vincent Guittot <vincent.guittot@linaro.org>, Paul Turner <pjt@google.com>, Dietmar Eggemann <dietmar.eggemann@arm.com>, Morten Rasmussen <morten.rasmussen@arm.com>, Juri Lelli <juri.lelli@redhat.com>, Todd Kjos <tkjos@google.com>, Joel Fernandes <joelaf@google.com>, Steve Muckle <smuckle@google.com>, Suren Baghdasaryan <surenb@google.com> Subject: [PATCH v2 09/12] sched/core: uclamp: map TG's clamp values into CPU's clamp groups Date: Mon, 16 Jul 2018 09:29:03 +0100 Message-ID: <20180716082906.6061-10-patrick.bellasi@arm.com> (raw) In-Reply-To: <20180716082906.6061-1-patrick.bellasi@arm.com> Utilization clamping requires to map each different clamp value into one of the available clamp groups used by the scheduler's fast-path to account for RUNNABLE tasks. Thus, each time a TG's clamp value is updated we need to get a reference to the new value's clamp group and release a reference to the previous one. Let's ensure that, whenever a task group is assigned a specific clamp_value, this is properly translated into a unique clamp group to be used in the fast-path (i.e. at enqueue/dequeue time). We do that by slightly refactoring uclamp_group_get() to make the *task_struct parameter optional. This allows to re-use the code already available to support the per-task API. Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Todd Kjos <tkjos@google.com> Cc: Joel Fernandes <joelaf@google.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org --- include/linux/sched.h | 2 ++ kernel/sched/core.c | 46 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 46 insertions(+), 2 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 0635e8073cd3..260aa8d3fca9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -583,6 +583,8 @@ struct sched_dl_entity { * * A utilization clamp group maps a "clamp value" (value), i.e. * util_{min,max}, to a "clamp group index" (group_id). + * The same "group_id" can be used by multiple TG's to enforce the same + * clamp "value" for a given clamp index. */ struct uclamp_se { /* Utilization constraint for tasks in this group */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 30b1d894f978..04e758224e22 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1219,7 +1219,8 @@ static inline int uclamp_group_get(struct task_struct *p, raw_spin_unlock_irqrestore(&uc_map[next_group_id].se_lock, flags); /* Update CPU's clamp group refcounts of RUNNABLE task */ - uclamp_task_update_active(p, clamp_id, next_group_id); + if (p) + uclamp_task_update_active(p, clamp_id, next_group_id); /* Release the previous clamp group */ uclamp_group_put(clamp_id, prev_group_id); @@ -1276,18 +1277,47 @@ static inline int alloc_uclamp_sched_group(struct task_group *tg, { struct uclamp_se *uc_se; int clamp_id; + int ret = 1; for (clamp_id = 0; clamp_id < UCLAMP_CNT; ++clamp_id) { uc_se = &tg->uclamp[clamp_id]; uc_se->value = parent->uclamp[clamp_id].value; uc_se->group_id = UCLAMP_NONE; + + if (uclamp_group_get(NULL, clamp_id, uc_se, + parent->uclamp[clamp_id].value)) { + ret = 0; + goto out; + } } - return 1; +out: + return ret; +} + +/** + * release_uclamp_sched_group: release utilization clamp references of a TG + * @tg: the task group being removed + * + * An empty task group can be removed only when it has no more tasks or child + * groups. This means that we can also safely release all the reference + * counting to clamp groups. + */ +static inline void free_uclamp_sched_group(struct task_group *tg) +{ + struct uclamp_se *uc_se; + int clamp_id; + + for (clamp_id = 0; clamp_id < UCLAMP_CNT; ++clamp_id) { + uc_se = &tg->uclamp[clamp_id]; + uclamp_group_put(clamp_id, uc_se->group_id); + } } + #else /* CONFIG_UCLAMP_TASK_GROUP */ static inline void init_uclamp_sched_group(void) { } +static inline void free_uclamp_sched_group(struct task_group *tg) { } static inline int alloc_uclamp_sched_group(struct task_group *tg, struct task_group *parent) { @@ -1364,6 +1394,7 @@ static void __init init_uclamp(void) #else /* CONFIG_UCLAMP_TASK */ static inline void uclamp_cpu_get(struct rq *rq, struct task_struct *p) { } static inline void uclamp_cpu_put(struct rq *rq, struct task_struct *p) { } +static inline void free_uclamp_sched_group(struct task_group *tg) { } static inline int alloc_uclamp_sched_group(struct task_group *tg, struct task_group *parent) { @@ -6944,6 +6975,7 @@ static DEFINE_SPINLOCK(task_group_lock); static void sched_free_group(struct task_group *tg) { + free_uclamp_sched_group(tg); free_fair_sched_group(tg); free_rt_sched_group(tg); autogroup_free(tg); @@ -7192,6 +7224,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) static int cpu_util_min_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 min_value) { + struct uclamp_se *uc_se; struct task_group *tg; int ret = -EINVAL; @@ -7209,6 +7242,10 @@ static int cpu_util_min_write_u64(struct cgroup_subsys_state *css, if (tg->uclamp[UCLAMP_MAX].value < min_value) goto out; + /* Update TG's reference count */ + uc_se = &tg->uclamp[UCLAMP_MIN]; + ret = uclamp_group_get(NULL, UCLAMP_MIN, uc_se, min_value); + out: rcu_read_unlock(); mutex_unlock(&uclamp_mutex); @@ -7219,6 +7256,7 @@ static int cpu_util_min_write_u64(struct cgroup_subsys_state *css, static int cpu_util_max_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 max_value) { + struct uclamp_se *uc_se; struct task_group *tg; int ret = -EINVAL; @@ -7236,6 +7274,10 @@ static int cpu_util_max_write_u64(struct cgroup_subsys_state *css, if (tg->uclamp[UCLAMP_MIN].value > max_value) goto out; + /* Update TG's reference count */ + uc_se = &tg->uclamp[UCLAMP_MAX]; + ret = uclamp_group_get(NULL, UCLAMP_MAX, uc_se, max_value); + out: rcu_read_unlock(); mutex_unlock(&uclamp_mutex); -- 2.17.1
next prev parent reply index Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-07-16 8:28 [PATCH v2 00/12] Add utilization clamping support Patrick Bellasi 2018-07-16 8:28 ` [PATCH v2 01/12] sched/core: uclamp: extend sched_setattr to support utilization clamping Patrick Bellasi 2018-07-17 17:50 ` Joel Fernandes 2018-07-18 8:42 ` Patrick Bellasi 2018-07-18 17:02 ` Joel Fernandes 2018-07-17 18:04 ` Joel Fernandes 2018-07-16 8:28 ` [PATCH v2 02/12] sched/core: uclamp: map TASK's clamp values into CPU's clamp groups Patrick Bellasi 2018-07-19 23:51 ` Suren Baghdasaryan 2018-07-20 15:11 ` Patrick Bellasi 2018-07-21 0:25 ` Suren Baghdasaryan 2018-07-23 13:36 ` Patrick Bellasi 2018-07-16 8:28 ` [PATCH v2 03/12] sched/core: uclamp: add CPU's clamp groups accounting Patrick Bellasi 2018-07-20 20:25 ` Suren Baghdasaryan 2018-07-16 8:28 ` [PATCH v2 04/12] sched/core: uclamp: update CPU's refcount on clamp changes Patrick Bellasi 2018-07-16 8:28 ` [PATCH v2 05/12] sched/cpufreq: uclamp: add utilization clamping for FAIR tasks Patrick Bellasi 2018-07-16 8:29 ` [PATCH v2 06/12] sched/cpufreq: uclamp: add utilization clamping for RT tasks Patrick Bellasi 2018-07-16 8:29 ` [PATCH v2 07/12] sched/core: uclamp: enforce last task UCLAMP_MAX Patrick Bellasi 2018-07-21 1:23 ` Suren Baghdasaryan 2018-07-23 15:02 ` Patrick Bellasi 2018-07-23 16:40 ` Suren Baghdasaryan 2018-07-16 8:29 ` [PATCH v2 08/12] sched/core: uclamp: extend cpu's cgroup controller Patrick Bellasi 2018-07-21 2:37 ` Suren Baghdasaryan 2018-07-21 3:16 ` Suren Baghdasaryan 2018-07-23 15:17 ` Patrick Bellasi 2018-07-23 15:30 ` Tejun Heo 2018-07-23 17:22 ` Patrick Bellasi 2018-07-24 13:29 ` Tejun Heo 2018-07-24 15:39 ` Patrick Bellasi 2018-07-27 0:39 ` Joel Fernandes 2018-07-27 8:09 ` Quentin Perret 2018-07-16 8:29 ` Patrick Bellasi [this message] 2018-07-16 8:29 ` [PATCH v2 10/12] sched/core: uclamp: use TG's clamps to restrict Task's clamps Patrick Bellasi 2018-07-22 3:05 ` Suren Baghdasaryan 2018-07-23 15:40 ` Patrick Bellasi 2018-07-23 17:11 ` Suren Baghdasaryan 2018-07-24 9:56 ` Patrick Bellasi 2018-07-24 15:28 ` Suren Baghdasaryan 2018-07-24 15:49 ` Patrick Bellasi 2018-07-16 8:29 ` [PATCH v2 11/12] sched/core: uclamp: update CPU's refcount on TG's clamp changes Patrick Bellasi 2018-07-22 3:17 ` Suren Baghdasaryan 2018-07-16 8:29 ` [PATCH v2 12/12] sched/core: uclamp: use percentage clamp values Patrick Bellasi 2018-07-22 4:04 ` Suren Baghdasaryan 2018-07-24 16:43 ` Patrick Bellasi 2018-07-24 17:11 ` Suren Baghdasaryan 2018-07-24 17:17 ` Patrick Bellasi 2018-07-17 13:03 ` [PATCH v2 00/12] Add utilization clamping support Joel Fernandes 2018-07-17 13:41 ` Patrick Bellasi
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20180716082906.6061-10-patrick.bellasi@arm.com \ --to=patrick.bellasi@arm.com \ --cc=dietmar.eggemann@arm.com \ --cc=joelaf@google.com \ --cc=juri.lelli@redhat.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-pm@vger.kernel.org \ --cc=mingo@redhat.com \ --cc=morten.rasmussen@arm.com \ --cc=peterz@infradead.org \ --cc=pjt@google.com \ --cc=rafael.j.wysocki@intel.com \ --cc=smuckle@google.com \ --cc=surenb@google.com \ --cc=tj@kernel.org \ --cc=tkjos@google.com \ --cc=vincent.guittot@linaro.org \ --cc=viresh.kumar@linaro.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
LKML Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \ linux-kernel@vger.kernel.org public-inbox-index lkml Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel AGPL code for this site: git clone https://public-inbox.org/public-inbox.git