[PATCH 3/3] sched: Optimize !CONFIG_NO_HZ_COMMON cpu load updates

[Frederic Weisbecker]

Some code in cpu load update only concern NO_HZ configs but it is
built on all configurations. When NO_HZ isn't built, that code is harmless
but just happens to take some useless ressources in CPU and memory:

1) one useless field in struct rq
2) jiffies record on every tick that is never used (cpu_load_update_periodic)
3) decay_load_missed is called two times on every tick to eventually
   return immediately with no action taken. And that function is dead
   code.

For pure optimization purposes, lets conditionally build the NO_HZ
related code.

Cc: Byungchul Park <byungchul.park@xxxxxxx>
Cc: Chris Metcalf <cmetcalf@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Luiz Capitulino <lcapitulino@xxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
---
 kernel/sched/core.c  |  3 ++-
 kernel/sched/fair.c  | 43 ++++++++++++++++++++++++++++++++-----------
 kernel/sched/sched.h |  6 ++++--
 3 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4c522a7..59a2821 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7327,8 +7327,9 @@ void __init sched_init(void)
 
 		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
 			rq->cpu_load[j] = 0;
-
+#ifdef CONFIG_NO_HZ_COMMON
 		rq->last_load_update_tick = jiffies;
+#endif
 
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1dd864d..4618e5b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4423,6 +4423,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 }
 
 #ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ_COMMON
 
 /*
  * per rq 'load' arrray crap; XXX kill this.
@@ -4490,6 +4491,33 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
 	return load;
 }
 
+static unsigned long
+cpu_load_update_missed(unsigned long old_load, unsigned long tickless_load,
+		       unsigned long pending_updates, int idx)
+{
+	old_load = decay_load_missed(old_load, pending_updates - 1, idx);
+	if (tickless_load) {
+		old_load -= decay_load_missed(tickless_load, pending_updates - 1, idx);
+		/*
+		 * old_load can never be a negative value because a
+		 * decayed tickless_load cannot be greater than the
+		 * original tickless_load.
+		 */
+		old_load += tickless_load;
+	}
+	return old_load;
+}
+#else /* !CONFIG_NO_HZ_COMMON */
+
+static inline unsigned long
+cpu_load_update_missed(unsigned long old_load, unsigned long tickless_load,
+		       unsigned long pending_updates, int idx)
+{
+	return old_load;
+}
+
+#endif /* CONFIG_NO_HZ_COMMON */
+
 /**
  * __cpu_load_update - update the rq->cpu_load[] statistics
  * @this_rq: The rq to update statistics for
@@ -4540,17 +4568,8 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
 
 		/* scale is effectively 1 << i now, and >> i divides by scale */
 
-		old_load = this_rq->cpu_load[i];
-		old_load = decay_load_missed(old_load, pending_updates - 1, i);
-		if (tickless_load) {
-			old_load -= decay_load_missed(tickless_load, pending_updates - 1, i);
-			/*
-			 * old_load can never be a negative value because a
-			 * decayed tickless_load cannot be greater than the
-			 * original tickless_load.
-			 */
-			old_load += tickless_load;
-		}
+		old_load = cpu_load_update_missed(this_rq->cpu_load[i],
+						  tickless_load, pending_updates, i);
 		new_load = this_load;
 		/*
 		 * Round up the averaging division if load is increasing. This
@@ -4661,8 +4680,10 @@ static inline void cpu_load_update_nohz(struct rq *this_rq,
 
 static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load)
 {
+#ifdef CONFIG_NO_HZ_COMMON
 	/* See the mess around cpu_load_update_nohz(). */
 	this_rq->last_load_update_tick = READ_ONCE(jiffies);
+#endif
 	cpu_load_update(this_rq, load, 1);
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1802013..2302bb6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -585,11 +585,13 @@ struct rq {
 #endif
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
+#ifdef CONFIG_NO_HZ_COMMON
+#ifdef CONFIG_SMP
 	unsigned long last_load_update_tick;
-#ifdef CONFIG_NO_HZ_COMMON
+#endif /* CONFIG_SMP */
 	u64 nohz_stamp;
 	unsigned long nohz_flags;
-#endif
+#endif /* CONFIG_NO_HZ_COMMON */
 #ifdef CONFIG_NO_HZ_FULL
 	unsigned long last_sched_tick;
 #endif
-- 
2.7.0