Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1304596

[RFC PATCH v2 1/4] ARM: initialize cpu_scale to its default

From Juri Lelli <juri.lelli@arm.com>
Newsgroups linux.kernel
Subject [RFC PATCH v2 1/4] ARM: initialize cpu_scale to its default
Date 2016-01-08 15:20 +0100
Message-ID <qOG3w-7SE-19@gated-at.bofh.it> (permalink)
References <qOFTS-7OQ-53@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


Instead of looping through all cpus calling set_capacity_scale, we can
initialise cpu_scale per-cpu variables to SCHED_CAPACITY_SCALE with their
definition.

Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
---
 arch/arm/kernel/topology.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 08b7847..ec279d1 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -40,7 +40,7 @@
  * to run the rebalance_domains for all idle cores and the cpu_capacity can be
  * updated during this sequence.
  */
-static DEFINE_PER_CPU(unsigned long, cpu_scale);
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
 
 unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 {
@@ -306,8 +306,6 @@ void __init init_cpu_topology(void)
 		cpu_topo->socket_id = -1;
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
-
-		set_capacity_scale(cpu, SCHED_CAPACITY_SCALE);
 	}
 	smp_wmb();
 
-- 
2.2.2

Back to linux.kernel | Previous | Next | Find similar | Unroll thread


Thread

[RFC PATCH v2 1/4] ARM: initialize cpu_scale to its default Juri Lelli <juri.lelli@arm.com> - 2016-01-08 15:20 +0100

csiph-web