[RFC,v1,3/8] sched/cpufreq_schedutil: make worker kthread be SCHED_DEADLINE

Message ID	20170705085905.6558-4-juri.lelli@arm.com (mailing list archive)
State	RFC, archived
Headers	show Return-Path: <linux-pm-owner@kernel.org> From: Juri Lelli <juri.lelli@arm.com> To: peterz@infradead.org, mingo@redhat.com, rjw@rjwysocki.net, viresh.kumar@linaro.org Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, tglx@linutronix.de, vincent.guittot@linaro.org, rostedt@goodmis.org, luca.abeni@santannapisa.it, claudio@evidence.eu.com, tommaso.cucinotta@santannapisa.it, bristot@redhat.com, mathieu.poirier@linaro.org, tkjos@android.com, joelaf@google.com, andresoportus@google.com, morten.rasmussen@arm.com, dietmar.eggemann@arm.com, patrick.bellasi@arm.com, juri.lelli@arm.com, Ingo Molnar <mingo@kernel.org>, "Rafael J . Wysocki" <rafael.j.wysocki@intel.com> Subject: [RFC PATCH v1 3/8] sched/cpufreq_schedutil: make worker kthread be SCHED_DEADLINE Date: Wed, 5 Jul 2017 09:59:00 +0100 Message-Id: <20170705085905.6558-4-juri.lelli@arm.com> In-Reply-To: <20170705085905.6558-1-juri.lelli@arm.com> References: <20170705085905.6558-1-juri.lelli@arm.com> Sender: linux-pm-owner@vger.kernel.org Precedence: bulk

diff --git a/include/linux/sched.h b/include/linux/sched.h index 1f0f427e0292..0ba767fdedae 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1359,6 +1359,7 @@ extern int idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern int sched_setattr(struct task_struct *, const struct sched_attr *); +extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5186797908dc..0e40c7ff2bf4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3998,7 +3998,9 @@ static int __sched_setscheduler(struct task_struct *p, } if (attr->sched_flags & - ~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM)) + ~(SCHED_FLAG_RESET_ON_FORK | + SCHED_FLAG_RECLAIM | + SCHED_FLAG_SPECIAL)) return -EINVAL; /* @@ -4065,6 +4067,9 @@ static int __sched_setscheduler(struct task_struct *p, } if (user) { + if (attr->sched_flags & SCHED_FLAG_SPECIAL) + return -EPERM; + retval = security_task_setscheduler(p); if (retval) return retval; @@ -4120,7 +4125,8 @@ static int __sched_setscheduler(struct task_struct *p, } #endif #ifdef CONFIG_SMP - if (dl_bandwidth_enabled() && dl_policy(policy)) { + if (dl_bandwidth_enabled() && dl_policy(policy) && + !(attr->sched_flags & SCHED_FLAG_SPECIAL)) { cpumask_t *span = rq->rd->span; /* @@ -4250,6 +4256,11 @@ int sched_setattr(struct task_struct *p, const struct sched_attr *attr) } EXPORT_SYMBOL_GPL(sched_setattr); +int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, false, true); +} + /** * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. * @p: the task in question. diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index f2494d1fc8ef..ba6227625f24 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -424,7 +424,16 @@ static void sugov_policy_free(struct sugov_policy *sg_policy) static int sugov_kthread_create(struct sugov_policy *sg_policy) { struct task_struct *thread; - struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 }; + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + .sched_policy = SCHED_DEADLINE, + .sched_flags = SCHED_FLAG_SPECIAL, + .sched_nice = 0, + .sched_priority = 0, + .sched_runtime = 0, + .sched_deadline = 0, + .sched_period = 0, + }; struct cpufreq_policy *policy = sg_policy->policy; int ret; @@ -442,10 +451,10 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy) return PTR_ERR(thread); } - ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, &param); + ret = sched_setattr_nocheck(thread, &attr); if (ret) { kthread_stop(thread); - pr_warn("%s: failed to set SCHED_FIFO\n", __func__); + pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__); return ret; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6912f7f35f9b..4ec82fa56b04 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -220,6 +220,9 @@ static void task_non_contending(struct task_struct *p) if (dl_se->dl_runtime == 0) return; + if (unlikely(dl_entity_is_special(dl_se))) + return; + WARN_ON(hrtimer_active(&dl_se->inactive_timer)); WARN_ON(dl_se->dl_non_contending); @@ -1150,6 +1153,9 @@ static void update_curr_dl(struct rq *rq) sched_rt_avg_update(rq, delta_exec); + if (unlikely(dl_entity_is_special(dl_se))) + return; + if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) delta_exec = grub_reclaim(delta_exec, rq, &curr->dl); dl_se->runtime -= delta_exec; @@ -2447,6 +2453,9 @@ int sched_dl_overflow(struct task_struct *p, int policy, u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; int cpus, err = -1; + if (attr->sched_flags & SCHED_FLAG_SPECIAL) + return 0; + /* !deadline task may carry old deadline bandwidth */ if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) return 0; @@ -2533,6 +2542,10 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr) */ bool __checkparam_dl(const struct sched_attr *attr) { + /* special dl tasks don't actually use any parameter */ + if (attr->sched_flags & SCHED_FLAG_SPECIAL) + return true; + /* deadline != 0 */ if (attr->sched_deadline == 0) return false; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d8798bb54ace..1be5dac728a4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -156,12 +156,30 @@ static inline int task_has_dl_policy(struct task_struct *p) } /* + * !! For sched_setattr_nocheck() (kernel) only !! + * + * This is actually gross. :( + * + * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE + * tasks, but still be able to sleep. We need this on platforms that cannot + * atomically change clock frequency. Remove once fast switching will be + * available on such platforms. + */ +#define SCHED_FLAG_SPECIAL 0x10000000 + +static inline int dl_entity_is_special(struct sched_dl_entity *dl_se) +{ + return dl_se->flags & SCHED_FLAG_SPECIAL; +} + +/* * Tells if entity @a should preempt entity @b. */ static inline bool dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) { - return dl_time_before(a->deadline, b->deadline); + return dl_entity_is_special(a) || + dl_time_before(a->deadline, b->deadline); } /*

[RFC,v1,3/8] sched/cpufreq_schedutil: make worker kthread be SCHED_DEADLINE

Commit Message

Comments

Patch