FROMLIST: sched/pelt: Introduce PELT multiplier

The new sysctl sched_pelt_multiplier allows a user to set a clock
multiplier to x2 or x4 (x1 being the default). This clock multiplier
artificially speeds up PELT ramp up/down similarly to use a faster
half-life than the default 32ms.

  - x1: 32ms half-life
  - x2: 16ms half-life
  - x4: 8ms  half-life

Internally, a new clock is created: rq->clock_task_mult. It sits in the
clock hierarchy between rq->clock_task and rq->clock_pelt.

Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>

Bug: 263742061
Link: https://lore.kernel.org/lkml/20220829055450.1703092-2-dietmar.eggemann@arm.com
Change-Id: Id379ff3cf07733ae63a854bc1e5af64426576788
Signed-off-by: Jing-Ting Wu <Jing-Ting.Wu@mediatek.com>

kernel/sched/core.c

@@ -733,7 +733,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
-	update_rq_clock_pelt(rq, delta);
+	update_rq_clock_task_mult(rq, delta);
 }
 
 void update_rq_clock(struct rq *rq)

kernel/sched/pelt.c

@@ -468,3 +468,63 @@ int update_irq_load_avg(struct rq *rq, u64 running)
 	return ret;
 }
 #endif
+
+__read_mostly unsigned int sched_pelt_lshift;
+
+#ifdef CONFIG_SYSCTL
+static unsigned int sysctl_sched_pelt_multiplier = 1;
+
+int sched_pelt_multiplier(struct ctl_table *table, int write, void *buffer,
+			  size_t *lenp, loff_t *ppos)
+{
+	static DEFINE_MUTEX(mutex);
+	unsigned int old;
+	int ret;
+
+	mutex_lock(&mutex);
+	old = sysctl_sched_pelt_multiplier;
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret)
+		goto undo;
+	if (!write)
+		goto done;
+
+	switch (sysctl_sched_pelt_multiplier)  {
+	case 1:
+		fallthrough;
+	case 2:
+		fallthrough;
+	case 4:
+		WRITE_ONCE(sched_pelt_lshift,
+			   sysctl_sched_pelt_multiplier >> 1);
+		goto done;
+	default:
+		ret = -EINVAL;
+	}
+
+undo:
+	sysctl_sched_pelt_multiplier = old;
+done:
+	mutex_unlock(&mutex);
+
+	return ret;
+}
+
+static struct ctl_table sched_pelt_sysctls[] = {
+	{
+		.procname       = "sched_pelt_multiplier",
+		.data           = &sysctl_sched_pelt_multiplier,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sched_pelt_multiplier,
+	},
+	{}
+};
+
+static int __init sched_pelt_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_pelt_sysctls);
+	return 0;
+}
+late_initcall(sched_pelt_sysctl_init);
+#endif

kernel/sched/pelt.h

@@ -61,6 +61,14 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 	WRITE_ONCE(avg->util_est.enqueued, enqueued);
 }
 
+static inline u64 rq_clock_task_mult(struct rq *rq)
+{
+	lockdep_assert_rq_held(rq);
+	assert_clock_updated(rq);
+
+	return rq->clock_task_mult;
+}
+
 static inline u64 rq_clock_pelt(struct rq *rq)
 {
 	lockdep_assert_rq_held(rq);
@@ -72,7 +80,7 @@ static inline u64 rq_clock_pelt(struct rq *rq)
 /* The rq is idle, we can sync to clock_task */
 static inline void _update_idle_rq_clock_pelt(struct rq *rq)
 {
-	rq->clock_pelt  = rq_clock_task(rq);
+	rq->clock_pelt = rq_clock_task_mult(rq);
 
 	u64_u32_store(rq->clock_idle, rq_clock(rq));
 	/* Paired with smp_rmb in migrate_se_pelt_lag() */
@@ -121,6 +129,27 @@ static inline void update_rq_clock_pelt(struct rq *rq, s64 delta)
 	rq->clock_pelt += delta;
 }
 
+extern unsigned int sched_pelt_lshift;
+
+/*
+ * absolute time   |1      |2      |3      |4      |5      |6      |
+ * @ mult = 1      --------****************--------****************-
+ * @ mult = 2      --------********----------------********---------
+ * @ mult = 4      --------****--------------------****-------------
+ * clock task mult
+ * @ mult = 2      |   |   |2  |3  |   |   |   |   |5  |6  |   |   |
+ * @ mult = 4      | | | | |2|3| | | | | | | | | | |5|6| | | | | | |
+ *
+ */
+static inline void update_rq_clock_task_mult(struct rq *rq, s64 delta)
+{
+	delta <<= READ_ONCE(sched_pelt_lshift);
+
+	rq->clock_task_mult += delta;
+
+	update_rq_clock_pelt(rq, delta);
+}
+
 /*
  * When rq becomes idle, we have to check if it has lost idle time
  * because it was fully busy. A rq is fully used when the /Sum util_sum
@@ -147,7 +176,7 @@ static inline void update_idle_rq_clock_pelt(struct rq *rq)
 	 * rq's clock_task.
 	 */
 	if (util_sum >= divider)
-		rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt;
+		rq->lost_idle_time += rq_clock_task_mult(rq) - rq->clock_pelt;
 
 	_update_idle_rq_clock_pelt(rq);
 }
@@ -218,13 +247,18 @@ update_irq_load_avg(struct rq *rq, u64 running)
 	return 0;
 }
 
-static inline u64 rq_clock_pelt(struct rq *rq)
+static inline u64 rq_clock_task_mult(struct rq *rq)
 {
 	return rq_clock_task(rq);
 }
 
+static inline u64 rq_clock_pelt(struct rq *rq)
+{
+	return rq_clock_task_mult(rq);
+}
+
 static inline void
-update_rq_clock_pelt(struct rq *rq, s64 delta) { }
+update_rq_clock_task_mult(struct rq *rq, s64 delta) { }
 
 static inline void
 update_idle_rq_clock_pelt(struct rq *rq) { }

kernel/sched/sched.h

@@ -1022,6 +1022,7 @@ struct rq {
 	u64			clock;
 	/* Ensure that all clocks are in the same cache line */
 	u64			clock_task ____cacheline_aligned;
+	u64			clock_task_mult;
 	u64			clock_pelt;
 	unsigned long		lost_idle_time;
 	u64			clock_pelt_idle;