sched: remove precise CPU load

CPU load calculations are statistical anyway, and there's little benefit
from having it calculated on every scheduling event. So remove this code,
it gets rid of a divide from the scheduler wakeup and context-switch
fastpath.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 9 insertions, 41 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index d4dabfcc776c..25cc9b2a8c15 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1972,42 +1972,11 @@ unsigned long nr_active(void)
  */
 static void update_cpu_load(struct rq *this_rq)
 {
-	u64 fair_delta64, exec_delta64, idle_delta64, sample_interval64, tmp64;
 	unsigned long total_load = this_rq->ls.load.weight;
 	unsigned long this_load =  total_load;
-	struct load_stat *ls = &this_rq->ls;
 	int i, scale;
 
 	this_rq->nr_load_updates++;
-	if (unlikely(!(sysctl_sched_features & SCHED_FEAT_PRECISE_CPU_LOAD)))
-		goto do_avg;
-
-	/* Update delta_fair/delta_exec fields first */
-	update_curr_load(this_rq);
-
-	fair_delta64 = ls->delta_fair + 1;
-	ls->delta_fair = 0;
-
-	exec_delta64 = ls->delta_exec + 1;
-	ls->delta_exec = 0;
-
-	sample_interval64 = this_rq->clock - ls->load_update_last;
-	ls->load_update_last = this_rq->clock;
-
-	if ((s64)sample_interval64 < (s64)TICK_NSEC)
-		sample_interval64 = TICK_NSEC;
-
-	if (exec_delta64 > sample_interval64)
-		exec_delta64 = sample_interval64;
-
-	idle_delta64 = sample_interval64 - exec_delta64;
-
-	tmp64 = div64_64(SCHED_LOAD_SCALE * exec_delta64, fair_delta64);
-	tmp64 = div64_64(tmp64 * exec_delta64, sample_interval64);
-
-	this_load = (unsigned long)tmp64;
-
-do_avg:
 
 	/* Update our load: */
 	for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
@@ -2017,7 +1986,13 @@ do_avg:
 
 		old_load = this_rq->cpu_load[i];
 		new_load = this_load;
-
+		/*
+		 * Round up the averaging division if load is increasing. This
+		 * prevents us from getting stuck on 9 if the load is 10, for
+		 * example.
+		 */
+		if (new_load > old_load)
+			new_load += scale-1;
 		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
 	}
 }
@@ -6484,7 +6459,6 @@ static inline void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 
 void __init sched_init(void)
 {
-	u64 now = sched_clock();
 	int highest_cpu = 0;
 	int i, j;
 
@@ -6509,8 +6483,6 @@ void __init sched_init(void)
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
 		list_add(&rq->cfs.leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
 #endif
-		rq->ls.load_update_last = now;
-		rq->ls.load_update_start = now;
 
 		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
 			rq->cpu_load[j] = 0;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index fd080f686f18..6b789dae7fdf 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -145,8 +145,6 @@ static void print_cpu(struct seq_file *m, int cpu)
 	P(nr_running);
 	SEQ_printf(m, "  .%-30s: %lu\n", "load",
 		   rq->ls.load.weight);
-	P(ls.delta_fair);
-	P(ls.delta_exec);
 	P(nr_switches);
 	P(nr_load_updates);
 	P(nr_uninterruptible);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 2138c40f4836..105d57b41aa2 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -94,16 +94,14 @@ enum {
 	SCHED_FEAT_FAIR_SLEEPERS	= 1,
 	SCHED_FEAT_SLEEPER_AVG		= 2,
 	SCHED_FEAT_SLEEPER_LOAD_AVG	= 4,
-	SCHED_FEAT_PRECISE_CPU_LOAD	= 8,
-	SCHED_FEAT_START_DEBIT		= 16,
-	SCHED_FEAT_SKIP_INITIAL		= 32,
+	SCHED_FEAT_START_DEBIT		= 8,
+	SCHED_FEAT_SKIP_INITIAL		= 16,
 };
 
 const_debug unsigned int sysctl_sched_features =
 		SCHED_FEAT_FAIR_SLEEPERS	*1 |
 		SCHED_FEAT_SLEEPER_AVG		*0 |
 		SCHED_FEAT_SLEEPER_LOAD_AVG	*1 |
-		SCHED_FEAT_PRECISE_CPU_LOAD	*1 |
 		SCHED_FEAT_START_DEBIT		*1 |
 		SCHED_FEAT_SKIP_INITIAL		*0;