[PATCH v2 11/12] sched/core: uclamp: update CPU's refcount on TG's clamp changes

[Patrick Bellasi]

When a task group refcounts a new clamp group, we need to ensure that
the new clamp values are immediately enforced to all its tasks which are
currently RUNNABLE. This is to ensure that all currently RUNNABLE task
are boosted and/or clamped as requested as soon as possible.

Let's ensure that, whenever a new clamp group is refcounted by a task
group, all its RUNNABLE tasks are correctly accounted in their
respective CPUs. We do that by slightly refactoring uclamp_group_get()
to get an additional parameter *cgroup_subsys_state which, when
provided, it's used to walk the list of tasks in the correspond TGs and
update the RUNNABLE ones.

This is a "brute force" solution which allows to reuse the same refcount
update code already used by the per-task API. That's also the only way
to ensure a prompt enforcement of new clamp constraints on RUNNABLE
tasks, as soon as a task group attribute is tweaked.

Signed-off-by: Patrick Bellasi <patrick.bellasi@xxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Todd Kjos <tkjos@xxxxxxxxxx>
Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Steve Muckle <smuckle@xxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Morten Rasmussen <morten.rasmussen@xxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-pm@xxxxxxxxxxxxxxx
---
 kernel/sched/core.c | 42 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 34 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 50613d3d5b83..42cff5ffddae 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1198,21 +1198,43 @@ static inline void uclamp_group_put(int clamp_id, int group_id)
 	raw_spin_unlock_irqrestore(&uc_map[group_id].se_lock, flags);
 }
 
+static inline void uclamp_group_get_tg(struct cgroup_subsys_state *css,
+				       int clamp_id, unsigned int group_id)
+{
+	struct css_task_iter it;
+	struct task_struct *p;
+
+	/* Update clamp groups for RUNNABLE tasks in this TG */
+	css_task_iter_start(css, 0, &it);
+	while ((p = css_task_iter_next(&it)))
+		uclamp_task_update_active(p, clamp_id, group_id);
+	css_task_iter_end(&it);
+}
+
 /**
  * uclamp_group_get: increase the reference count for a clamp group
  * @p: the task which clamp value must be tracked
- * @clamp_id: the clamp index affected by the task
- * @uc_se: the utilization clamp data for the task
- * @clamp_value: the new clamp value for the task
+ * @css: the task group which clamp value must be tracked
+ * @clamp_id: the clamp index affected by the task (group)
+ * @uc_se: the utilization clamp data for the task (group)
+ * @clamp_value: the new clamp value for the task (group)
  *
  * Each time a task changes its utilization clamp value, for a specified clamp
  * index, we need to find an available clamp group which can be used to track
  * this new clamp value. The corresponding clamp group index will be used by
  * the task to reference count the clamp value on CPUs while enqueued.
  *
+ * When the cgroup's cpu controller utilization clamping support is enabled,
+ * each task group has a set of clamp values which are used to restrict the
+ * corresponding task specific clamp values.
+ * When a clamp value for a task group is changed, all the (active) tasks
+ * belonging to that task group must be update to ensure they are refcounting
+ * the correct CPU's clamp value.
+ *
  * Return: -ENOSPC if there are no available clamp groups, 0 on success.
  */
 static inline int uclamp_group_get(struct task_struct *p,
+				   struct cgroup_subsys_state *css,
 				   int clamp_id, struct uclamp_se *uc_se,
 				   unsigned int clamp_value)
 {
@@ -1240,6 +1262,10 @@ static inline int uclamp_group_get(struct task_struct *p,
 	uc_map[next_group_id].se_count += 1;
 	raw_spin_unlock_irqrestore(&uc_map[next_group_id].se_lock, flags);
 
+	/* Newly created TG don't have tasks assigned */
+	if (css)
+		uclamp_group_get_tg(css, clamp_id, next_group_id);
+
 	/* Update CPU's clamp group refcounts of RUNNABLE task */
 	if (p)
 		uclamp_task_update_active(p, clamp_id, next_group_id);
@@ -1307,7 +1333,7 @@ static inline int alloc_uclamp_sched_group(struct task_group *tg,
 		uc_se->value = parent->uclamp[clamp_id].value;
 		uc_se->group_id = UCLAMP_NONE;
 
-		if (uclamp_group_get(NULL, clamp_id, uc_se,
+		if (uclamp_group_get(NULL, NULL, clamp_id, uc_se,
 				     parent->uclamp[clamp_id].value)) {
 			ret = 0;
 			goto out;
@@ -1362,12 +1388,12 @@ static inline int __setscheduler_uclamp(struct task_struct *p,
 
 	/* Update min utilization clamp */
 	uc_se = &p->uclamp[UCLAMP_MIN];
-	retval |= uclamp_group_get(p, UCLAMP_MIN, uc_se,
+	retval |= uclamp_group_get(p, NULL, UCLAMP_MIN, uc_se,
 				   attr->sched_util_min);
 
 	/* Update max utilization clamp */
 	uc_se = &p->uclamp[UCLAMP_MAX];
-	retval |= uclamp_group_get(p, UCLAMP_MAX, uc_se,
+	retval |= uclamp_group_get(p, NULL, UCLAMP_MAX, uc_se,
 				   attr->sched_util_max);
 
 	mutex_unlock(&uclamp_mutex);
@@ -7274,7 +7300,7 @@ static int cpu_util_min_write_u64(struct cgroup_subsys_state *css,
 
 	/* Update TG's reference count */
 	uc_se = &tg->uclamp[UCLAMP_MIN];
-	ret = uclamp_group_get(NULL, UCLAMP_MIN, uc_se, min_value);
+	ret = uclamp_group_get(NULL, css, UCLAMP_MIN, uc_se, min_value);
 
 out:
 	rcu_read_unlock();
@@ -7306,7 +7332,7 @@ static int cpu_util_max_write_u64(struct cgroup_subsys_state *css,
 
 	/* Update TG's reference count */
 	uc_se = &tg->uclamp[UCLAMP_MAX];
-	ret = uclamp_group_get(NULL, UCLAMP_MAX, uc_se, max_value);
+	ret = uclamp_group_get(NULL, css, UCLAMP_MAX, uc_se, max_value);
 
 out:
 	rcu_read_unlock();
-- 
2.17.1