[tip:sched/core] sched/fair: Optimize !CONFIG_NO_HZ_COMMON CPU load updates

[tip-bot for Frederic Weisbecker <tipbot@zytor.com>]

Commit-ID:  9fd81dd5ce0b12341c9f83346f8d32ac68bd3841
Gitweb:     http://git.kernel.org/tip/9fd81dd5ce0b12341c9f83346f8d32ac68bd3841
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Tue, 19 Apr 2016 17:36:51 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Sat, 23 Apr 2016 14:20:42 +0200

sched/fair: Optimize !CONFIG_NO_HZ_COMMON CPU load updates

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.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1461080211-16271-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 5 ++---
 kernel/sched/fair.c  | 9 +++++++--
 kernel/sched/sched.h | 6 ++++--
 3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c98a268..71dffbb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7381,8 +7381,6 @@ void __init sched_init(void)
 		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
 			rq->cpu_load[j] = 0;
 
-		rq->last_load_update_tick = jiffies;
-
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
@@ -7401,12 +7399,13 @@ void __init sched_init(void)
 
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ_COMMON
+		rq->last_load_update_tick = jiffies;
 		rq->nohz_flags = 0;
 #endif
 #ifdef CONFIG_NO_HZ_FULL
 		rq->last_sched_tick = 0;
 #endif
-#endif
+#endif /* CONFIG_SMP */
 		init_rq_hrtick(rq);
 		atomic_set(&rq->nr_iowait, 0);
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b70367a..b8a33ab 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4491,7 +4491,7 @@ 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.
  */
@@ -4557,6 +4557,7 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
 	}
 	return load;
 }
+#endif /* CONFIG_NO_HZ_COMMON */
 
 /**
  * __cpu_load_update - update the rq->cpu_load[] statistics
@@ -4596,7 +4597,7 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
 static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
 			    unsigned long pending_updates)
 {
-	unsigned long tickless_load = this_rq->cpu_load[0];
+	unsigned long __maybe_unused tickless_load = this_rq->cpu_load[0];
 	int i, scale;
 
 	this_rq->nr_load_updates++;
@@ -4609,6 +4610,7 @@ 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];
+#ifdef CONFIG_NO_HZ_COMMON
 		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);
@@ -4619,6 +4621,7 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
 			 */
 			old_load += tickless_load;
 		}
+#endif
 		new_load = this_load;
 		/*
 		 * Round up the averaging division if load is increasing. This
@@ -4731,8 +4734,10 @@ 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 32d9e22..69da6fc 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];
-	unsigned long last_load_update_tick;
 #ifdef CONFIG_NO_HZ_COMMON
+#ifdef CONFIG_SMP
+	unsigned long last_load_update_tick;
+#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