sched/uclamp: Add system default clamps

Tasks without a user-defined clamp value are considered not clamped
and by default their utilization can have any value in the
[0..SCHED_CAPACITY_SCALE] range.

Tasks with a user-defined clamp value are allowed to request any value
in that range, and the required clamp is unconditionally enforced.
However, a "System Management Software" could be interested in limiting
the range of clamp values allowed for all tasks.

Add a privileged interface to define a system default configuration via:

  /proc/sys/kernel/sched_uclamp_util_{min,max}

which works as an unconditional clamp range restriction for all tasks.

With the default configuration, the full SCHED_CAPACITY_SCALE range of
values is allowed for each clamp index. Otherwise, the task-specific
clamp is capped by the corresponding system default value.

Do that by tracking, for each task, the "effective" clamp value and
bucket the task has been refcounted in at enqueue time. This
allows to lazy aggregate "requested" and "system default" values at
enqueue time and simplifies refcounting updates at dequeue time.

The cached bucket ids are used to avoid (relatively) more expensive
integer divisions every time a task is enqueued.

An active flag is used to report when the "effective" value is valid and
thus the task is actually refcounted in the corresponding rq's bucket.

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/20190621084217.8167-5-patrick.bellasi@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 98 insertions, 1 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2dde735635ec..b74de86b68c7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -773,6 +773,14 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 }
 
 #ifdef CONFIG_UCLAMP_TASK
+/* Max allowed minimum utilization */
+unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
+
+/* Max allowed maximum utilization */
+unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
+
+/* All clamps are required to be less or equal than these values */
+static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
 /* Integer rounded range for each bucket */
 #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
@@ -852,6 +860,25 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
 }
 
 /*
+ * The effective clamp bucket index of a task depends on, by increasing
+ * priority:
+ * - the task specific clamp value, when explicitly requested from userspace
+ * - the system default clamp value, defined by the sysadmin
+ */
+static inline struct uclamp_se
+uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
+{
+	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+	struct uclamp_se uc_max = uclamp_default[clamp_id];
+
+	/* System default restrictions always apply */
+	if (unlikely(uc_req.value > uc_max.value))
+		return uc_max;
+
+	return uc_req;
+}
+
+/*
  * When a task is enqueued on a rq, the clamp bucket currently defined by the
  * task's uclamp::bucket_id is refcounted on that rq. This also immediately
  * updates the rq's clamp value if required.
@@ -870,8 +897,12 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
 
 	lockdep_assert_held(&rq->lock);
 
+	/* Update task effective clamp */
+	p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id);
+
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
 	bucket->tasks++;
+	uc_se->active = true;
 
 	uclamp_idle_reset(rq, clamp_id, uc_se->value);
 
@@ -910,6 +941,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	SCHED_WARN_ON(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
+	uc_se->active = false;
 
 	/*
 	 * Keep "local max aggregation" simple and accept to (possibly)
@@ -958,8 +990,65 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
 
+int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	int old_min, old_max;
+	static DEFINE_MUTEX(mutex);
+	int result;
+
+	mutex_lock(&mutex);
+	old_min = sysctl_sched_uclamp_util_min;
+	old_max = sysctl_sched_uclamp_util_max;
+
+	result = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (result)
+		goto undo;
+	if (!write)
+		goto done;
+
+	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+		result = -EINVAL;
+		goto undo;
+	}
+
+	if (old_min != sysctl_sched_uclamp_util_min) {
+		uclamp_se_set(&uclamp_default[UCLAMP_MIN],
+			      sysctl_sched_uclamp_util_min);
+	}
+	if (old_max != sysctl_sched_uclamp_util_max) {
+		uclamp_se_set(&uclamp_default[UCLAMP_MAX],
+			      sysctl_sched_uclamp_util_max);
+	}
+
+	/*
+	 * Updating all the RUNNABLE task is expensive, keep it simple and do
+	 * just a lazy update at each next enqueue time.
+	 */
+	goto done;
+
+undo:
+	sysctl_sched_uclamp_util_min = old_min;
+	sysctl_sched_uclamp_util_max = old_max;
+done:
+	mutex_unlock(&mutex);
+
+	return result;
+}
+
+static void uclamp_fork(struct task_struct *p)
+{
+	unsigned int clamp_id;
+
+	for_each_clamp_id(clamp_id)
+		p->uclamp[clamp_id].active = false;
+}
+
 static void __init init_uclamp(void)
 {
+	struct uclamp_se uc_max = {};
 	unsigned int clamp_id;
 	int cpu;
 
@@ -969,14 +1058,20 @@ static void __init init_uclamp(void)
 	}
 
 	for_each_clamp_id(clamp_id) {
-		uclamp_se_set(&init_task.uclamp[clamp_id],
+		uclamp_se_set(&init_task.uclamp_req[clamp_id],
 			      uclamp_none(clamp_id));
 	}
+
+	/* System defaults allow max clamp values for both indexes */
+	uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX));
+	for_each_clamp_id(clamp_id)
+		uclamp_default[clamp_id] = uc_max;
 }
 
 #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 void uclamp_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
 
@@ -2545,6 +2640,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 */
 	p->prio = current->normal_prio;
 
+	uclamp_fork(p);
+
 	/*
 	 * Revert to default priority/policy on fork if requested.
 	 */