diff mbox

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

Message ID 20170523085351.18586-4-juri.lelli@arm.com (mailing list archive)
State RFC, archived
Headers show

Commit Message

Juri Lelli May 23, 2017, 8:53 a.m. UTC 
Worker kthread needs to be able to change frequency for all other
threads.

Make it special, just under STOP class.

Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Claudio Scordino <claudio@evidence.eu.com>
---
 include/linux/sched.h            |  1 +
 include/uapi/linux/sched.h       |  1 +
 kernel/sched/core.c              | 19 +++++++++++++++++--
 kernel/sched/cpufreq_schedutil.c | 15 ++++++++++++---
 kernel/sched/deadline.c          |  6 ++++++
 kernel/sched/sched.h             |  8 +++++++-
 6 files changed, 44 insertions(+), 6 deletions(-)

Comments

Peter Zijlstra May 23, 2017, 6:52 p.m. UTC | #1 
On Tue, May 23, 2017 at 09:53:46AM +0100, Juri Lelli wrote:
> diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
> index e2a6c7b3510b..72723859ef74 100644
> --- a/include/uapi/linux/sched.h
> +++ b/include/uapi/linux/sched.h
> @@ -48,5 +48,6 @@
>   */
>  #define SCHED_FLAG_RESET_ON_FORK	0x01
>  #define SCHED_FLAG_RECLAIM		0x02
> +#define SCHED_FLAG_SPECIAL		0x04
>  
>  #endif /* _UAPI_LINUX_SCHED_H */
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 7fc2011c3ce7..ba57e2ef9aef 100644

> @@ -4205,7 +4212,9 @@ 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;
>  
>  	/*

Could we pretty please not expose this gruesome hack to userspace?

So if you stick it in attr->sched_flags, use a high bit and don't put it
in a uapi header. Also make the flags check explicitly fail on it when
@user. Such that only _nocheck() (and thus kernel) callers have access
to it.

Also, there's not nearly enough warnings and other derisory comments
near it.
Juri Lelli May 24, 2017, 9:31 a.m. UTC | #2 
Hi,

On 23/05/17 20:52, Peter Zijlstra wrote:
> On Tue, May 23, 2017 at 09:53:46AM +0100, Juri Lelli wrote:
> > diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
> > index e2a6c7b3510b..72723859ef74 100644
> > --- a/include/uapi/linux/sched.h
> > +++ b/include/uapi/linux/sched.h
> > @@ -48,5 +48,6 @@
> >   */
> >  #define SCHED_FLAG_RESET_ON_FORK	0x01
> >  #define SCHED_FLAG_RECLAIM		0x02
> > +#define SCHED_FLAG_SPECIAL		0x04
> >  
> >  #endif /* _UAPI_LINUX_SCHED_H */
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index 7fc2011c3ce7..ba57e2ef9aef 100644
> 
> > @@ -4205,7 +4212,9 @@ 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;
> >  
> >  	/*
> 
> Could we pretty please not expose this gruesome hack to userspace?
> 
> So if you stick it in attr->sched_flags, use a high bit and don't put it
> in a uapi header. Also make the flags check explicitly fail on it when
> @user. Such that only _nocheck() (and thus kernel) callers have access
> to it.
>

Sure, I should have done it in the first place.

> Also, there's not nearly enough warnings and other derisory comments
> near it.

Eheh, I'll add all the derisory remarks I'm capable of. :/

Thanks,

- Juri
diff mbox

Patch

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8127f8bbef56..fd30bec5e199 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1360,6 +1360,7 @@  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/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index e2a6c7b3510b..72723859ef74 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -48,5 +48,6 @@ 
  */
 #define SCHED_FLAG_RESET_ON_FORK	0x01
 #define SCHED_FLAG_RECLAIM		0x02
+#define SCHED_FLAG_SPECIAL		0x04
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7fc2011c3ce7..ba57e2ef9aef 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2495,6 +2495,9 @@  static int 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;
@@ -4119,6 +4122,10 @@  __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 static 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;
@@ -4205,7 +4212,9 @@  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;
 
 	/*
@@ -4327,7 +4336,8 @@  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;
 
 			/*
@@ -4457,6 +4467,11 @@  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 7f1913e265d1..1508109c7f19 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -421,7 +421,16 @@  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;
 
@@ -439,10 +448,10 @@  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 fed54b078240..5ee4fd9b1c7f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -187,6 +187,9 @@  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);
 
@@ -1036,6 +1039,9 @@  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;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f1e400c6403c..e48cc8762e04 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -155,13 +155,19 @@  static inline int task_has_dl_policy(struct task_struct *p)
 	return dl_policy(p->policy);
 }
 
+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);
 }
 
 /*