sched/uclamp: Enforce last task's UCLAMP_MAX

When a task sleeps it removes its max utilization clamp from its CPU.
However, the blocked utilization on that CPU can be higher than the max
clamp value enforced while the task was running. This allows undesired
CPU frequency increases while a CPU is idle, for example, when another
CPU on the same frequency domain triggers a frequency update, since
schedutil can now see the full not clamped blocked utilization of the
idle CPU.

Fix this by using:

  uclamp_rq_dec_id(p, rq, UCLAMP_MAX)
    uclamp_rq_max_value(rq, UCLAMP_MAX, clamp_value)

to detect when a CPU has no more RUNNABLE clamped tasks and to flag this
condition.

Don't track any minimum utilization clamps since an idle CPU never
requires a minimum frequency. The decay of the blocked utilization is
good enough to reduce the CPU frequency.

Signed-off-by: Patrick Bellasi <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Alessio Balsini <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Joel Fernandes <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Morten Rasmussen <[email protected]>
Cc: Paul Turner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Quentin Perret <[email protected]>
Cc: Rafael J . Wysocki <[email protected]>
Cc: Steve Muckle <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Todd Kjos <[email protected]>
Cc: Vincent Guittot <[email protected]>
Cc: Viresh Kumar <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

kernel/sched/core.c

@@ -803,8 +803,36 @@ static inline void uclamp_se_set(struct uclamp_se *uc_se, unsigned int value)
 	uc_se->bucket_id = uclamp_bucket_id(value);
 }
 
+static inline unsigned int
+uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
+		  unsigned int clamp_value)
+{
+	/*
+	 * Avoid blocked utilization pushing up the frequency when we go
+	 * idle (which drops the max-clamp) by retaining the last known
+	 * max-clamp.
+	 */
+	if (clamp_id == UCLAMP_MAX) {
+		rq->uclamp_flags |= UCLAMP_FLAG_IDLE;
+		return clamp_value;
+	}
+
+	return uclamp_none(UCLAMP_MIN);
+}
+
+static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
+				     unsigned int clamp_value)
+{
+	/* Reset max-clamp retention only on idle exit */
+	if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE))
+		return;
+
+	WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
+}
+
 static inline
-unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id)
+unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
+				 unsigned int clamp_value)
 {
 	struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
 	int bucket_id = UCLAMP_BUCKETS - 1;
@@ -820,7 +848,7 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id)
 	}
 
 	/* No tasks -- default clamp values */
-	return uclamp_none(clamp_id);
+	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
 /*
@@ -845,6 +873,8 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
 	bucket->tasks++;
 
+	uclamp_idle_reset(rq, clamp_id, uc_se->value);
+
 	/*
 	 * Local max aggregation: rq buckets always track the max
 	 * "requested" clamp value of its RUNNABLE tasks.
@@ -871,6 +901,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
 	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
 	struct uclamp_bucket *bucket;
+	unsigned int bkt_clamp;
 	unsigned int rq_clamp;
 
 	lockdep_assert_held(&rq->lock);
@@ -895,8 +926,10 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	 * e.g. due to future modification, warn and fixup the expected value.
 	 */
 	SCHED_WARN_ON(bucket->value > rq_clamp);
-	if (bucket->value >= rq_clamp)
-		WRITE_ONCE(uc_rq->value, uclamp_rq_max_value(rq, clamp_id));
+	if (bucket->value >= rq_clamp) {
+		bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
+		WRITE_ONCE(uc_rq->value, bkt_clamp);
+	}
 }
 
 static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
@@ -908,6 +941,10 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 
 	for_each_clamp_id(clamp_id)
 		uclamp_rq_inc_id(rq, p, clamp_id);
+
+	/* Reset clamp idle holding when there is one RUNNABLE task */
+	if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+		rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
 }
 
 static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
@@ -926,8 +963,10 @@ static void __init init_uclamp(void)
 	unsigned int clamp_id;
 	int cpu;
 
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
 		memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
+		cpu_rq(cpu)->uclamp_flags = 0;
+	}
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp[clamp_id],

kernel/sched/sched.h

@@ -870,6 +870,8 @@ struct rq {
 #ifdef CONFIG_UCLAMP_TASK
 	/* Utilization clamp values based on CPU's RUNNABLE tasks */
 	struct uclamp_rq	uclamp[UCLAMP_CNT] ____cacheline_aligned;
+	unsigned int		uclamp_flags;
+#define UCLAMP_FLAG_IDLE 0x01
 #endif
 
 	struct cfs_rq		cfs;