sched/uclamp: Extend sched_setattr() to support utilization clamping

The SCHED_DEADLINE scheduling class provides an advanced and formal
model to define tasks requirements that can translate into proper
decisions for both task placements and frequencies selections. Other
classes have a more simplified model based on the POSIX concept of
priorities.

Such a simple priority based model however does not allow to exploit
most advanced features of the Linux scheduler like, for example, driving
frequencies selection via the schedutil cpufreq governor. However, also
for non SCHED_DEADLINE tasks, it's still interesting to define tasks
properties to support scheduler decisions.

Utilization clamping exposes to user-space a new set of per-task
attributes the scheduler can use as hints about the expected/required
utilization for a task. This allows to implement a "proactive" per-task
frequency control policy, a more advanced policy than the current one
based just on "passive" measured task utilization. For example, it's
possible to boost interactive tasks (e.g. to get better performance) or
cap background tasks (e.g. to be more energy/thermal efficient).

Introduce a new API to set utilization clamping values for a specified
task by extending sched_setattr(), a syscall which already allows to
define task specific properties for different scheduling classes. A new
pair of attributes allows to specify a minimum and maximum utilization
the scheduler can consider for a task.

Do that by validating the required clamp values before and then applying
the required changes using _the_ same pattern already in use for
__setscheduler(). This ensures that the task is re-enqueued with the new
clamp values.

Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alessio Balsini <balsini@android.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Perret <quentin.perret@arm.com>
Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com>
Cc: Steve Muckle <smuckle@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Todd Kjos <tkjos@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lkml.kernel.org/r/20190621084217.8167-7-patrick.bellasi@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 84 insertions, 7 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6d519f3f9789..e9a669266fa9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -805,10 +805,12 @@ static inline unsigned int uclamp_none(int clamp_id)
 	return SCHED_CAPACITY_SCALE;
 }
 
-static inline void uclamp_se_set(struct uclamp_se *uc_se, unsigned int value)
+static inline void uclamp_se_set(struct uclamp_se *uc_se,
+				 unsigned int value, bool user_defined)
 {
 	uc_se->value = value;
 	uc_se->bucket_id = uclamp_bucket_id(value);
+	uc_se->user_defined = user_defined;
 }
 
 static inline unsigned int
@@ -1016,11 +1018,11 @@ 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);
+			      sysctl_sched_uclamp_util_min, false);
 	}
 	if (old_max != sysctl_sched_uclamp_util_max) {
 		uclamp_se_set(&uclamp_default[UCLAMP_MAX],
-			      sysctl_sched_uclamp_util_max);
+			      sysctl_sched_uclamp_util_max, false);
 	}
 
 	/*
@@ -1038,6 +1040,42 @@ done:
 	return result;
 }
 
+static int uclamp_validate(struct task_struct *p,
+			   const struct sched_attr *attr)
+{
+	unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value;
+	unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value;
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN)
+		lower_bound = attr->sched_util_min;
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX)
+		upper_bound = attr->sched_util_max;
+
+	if (lower_bound > upper_bound)
+		return -EINVAL;
+	if (upper_bound > SCHED_CAPACITY_SCALE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void __setscheduler_uclamp(struct task_struct *p,
+				  const struct sched_attr *attr)
+{
+	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
+		return;
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
+			      attr->sched_util_min, true);
+	}
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
+			      attr->sched_util_max, true);
+	}
+}
+
 static void uclamp_fork(struct task_struct *p)
 {
 	unsigned int clamp_id;
@@ -1059,11 +1097,11 @@ static void __init init_uclamp(void)
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp_req[clamp_id],
-			      uclamp_none(clamp_id));
+			      uclamp_none(clamp_id), false);
 	}
 
 	/* System defaults allow max clamp values for both indexes */
-	uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX));
+	uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false);
 	for_each_clamp_id(clamp_id)
 		uclamp_default[clamp_id] = uc_max;
 }
@@ -1071,6 +1109,13 @@ static void __init init_uclamp(void)
 #else /* CONFIG_UCLAMP_TASK */
 static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { }
 static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { }
+static inline int uclamp_validate(struct task_struct *p,
+				  const struct sched_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+static void __setscheduler_uclamp(struct task_struct *p,
+				  const struct sched_attr *attr) { }
 static inline void uclamp_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
@@ -4412,6 +4457,13 @@ static void __setscheduler_params(struct task_struct *p,
 static void __setscheduler(struct rq *rq, struct task_struct *p,
 			   const struct sched_attr *attr, bool keep_boost)
 {
+	/*
+	 * If params can't change scheduling class changes aren't allowed
+	 * either.
+	 */
+	if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
+		return;
+
 	__setscheduler_params(p, attr);
 
 	/*
@@ -4549,6 +4601,13 @@ recheck:
 			return retval;
 	}
 
+	/* Update task specific "requested" clamps */
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) {
+		retval = uclamp_validate(p, attr);
+		if (retval)
+			return retval;
+	}
+
 	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
@@ -4578,6 +4637,8 @@ recheck:
 			goto change;
 		if (dl_policy(policy) && dl_param_changed(p, attr))
 			goto change;
+		if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		task_rq_unlock(rq, p, &rf);
@@ -4658,7 +4719,9 @@ change:
 		put_prev_task(rq, p);
 
 	prev_class = p->sched_class;
+
 	__setscheduler(rq, p, attr, pi);
+	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
 		/*
@@ -4834,6 +4897,10 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	if (ret)
 		return -EFAULT;
 
+	if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
+	    size < SCHED_ATTR_SIZE_VER1)
+		return -EINVAL;
+
 	/*
 	 * XXX: Do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
@@ -4903,10 +4970,15 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	rcu_read_lock();
 	retval = -ESRCH;
 	p = find_process_by_pid(pid);
-	if (p != NULL)
-		retval = sched_setattr(p, &attr);
+	if (likely(p))
+		get_task_struct(p);
 	rcu_read_unlock();
 
+	if (likely(p)) {
+		retval = sched_setattr(p, &attr);
+		put_task_struct(p);
+	}
+
 	return retval;
 }
 
@@ -5057,6 +5129,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	else
 		attr.sched_nice = task_nice(p);
 
+#ifdef CONFIG_UCLAMP_TASK
+	attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+	attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+#endif
+
 	rcu_read_unlock();
 
 	retval = sched_read_attr(uattr, &attr, size);