[tip:smp/hotplug] sched/migration: Move calc_load_migrate() into CPU_DYING

[tip-bot for Thomas Gleixner]

Commit-ID:  5dd44d07d3d373f0f3981b506152e3d7df5f5b75
Gitweb:     http://git.kernel.org/tip/5dd44d07d3d373f0f3981b506152e3d7df5f5b75
Author:     Thomas Gleixner <tglx@xxxxxxxxxxxxx>
AuthorDate: Thu, 10 Mar 2016 12:54:16 +0100
Committer:  Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Thu, 5 May 2016 13:17:54 +0200

sched/migration: Move calc_load_migrate() into CPU_DYING

It really does not matter when we fold the load for the outgoing cpu. It's
almost dead anyway, so there is no harm if we fail to fold the few
microseconds which are required for going fully away.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: rt@xxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/20160310120025.328739226@xxxxxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

---
 kernel/sched/core.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bafc308..688e8a8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5447,9 +5447,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		migrate_tasks(rq);
 		BUG_ON(rq->nr_running != 1); /* the migration thread */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
-		break;
-
-	case CPU_DEAD:
 		calc_load_migrate(rq);
 		break;
 #endif