[PATCH v13 5/6] sched/core: uclamp: Update CPU's refcount on TG's clamp changes

[Patrick Bellasi]

On updates of task group (TG) clamp values, ensure that these new values
are enforced on all RUNNABLE tasks of the task group, i.e. all RUNNABLE
tasks are immediately boosted and/or capped as requested.

Do that each time we update effective clamps from cpu_util_update_eff().
Use the *cgroup_subsys_state (css) to walk the list of tasks in each
affected TG and update their RUNNABLE tasks.
Update each task by using the same mechanism used for cpu affinity masks
updates, i.e. by taking the rq lock.

Signed-off-by: Patrick Bellasi <patrick.bellasi@xxxxxxx>
Acked-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
---
 kernel/sched/core.c | 58 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 106cf69d70cc..8cc1198e7199 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1043,6 +1043,57 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
 
+static inline void
+uclamp_update_active(struct task_struct *p, unsigned int clamp_id)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	/*
+	 * Lock the task and the rq where the task is (or was) queued.
+	 *
+	 * We might lock the (previous) rq of a !RUNNABLE task, but that's the
+	 * price to pay to safely serialize util_{min,max} updates with
+	 * enqueues, dequeues and migration operations.
+	 * This is the same locking schema used by __set_cpus_allowed_ptr().
+	 */
+	rq = task_rq_lock(p, &rf);
+
+	/*
+	 * Setting the clamp bucket is serialized by task_rq_lock().
+	 * If the task is not yet RUNNABLE and its task_struct is not
+	 * affecting a valid clamp bucket, the next time it's enqueued,
+	 * it will already see the updated clamp bucket value.
+	 */
+	if (!p->uclamp[clamp_id].active)
+		goto done;
+
+	uclamp_rq_dec_id(rq, p, clamp_id);
+	uclamp_rq_inc_id(rq, p, clamp_id);
+
+done:
+
+	task_rq_unlock(rq, p, &rf);
+}
+
+static inline void
+uclamp_update_active_tasks(struct cgroup_subsys_state *css,
+			   unsigned int clamps)
+{
+	struct css_task_iter it;
+	struct task_struct *p;
+	unsigned int clamp_id;
+
+	css_task_iter_start(css, 0, &it);
+	while ((p = css_task_iter_next(&it))) {
+		for_each_clamp_id(clamp_id) {
+			if ((0x1 << clamp_id) & clamps)
+				uclamp_update_active(p, clamp_id);
+		}
+	}
+	css_task_iter_end(&it);
+}
+
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 static void cpu_util_update_eff(struct cgroup_subsys_state *css);
 static void uclamp_update_root_tg(void)
@@ -7148,8 +7199,13 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css)
 			uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
 			clamps |= (0x1 << clamp_id);
 		}
-		if (!clamps)
+		if (!clamps) {
 			css = css_rightmost_descendant(css);
+			continue;
+		}
+
+		/* Immediately update descendants RUNNABLE tasks */
+		uclamp_update_active_tasks(css, clamps);
 	}
 }
 
-- 
2.22.0