commit 82440737eef236077e5781061b4c8de2c0b013fb
author Steve Muckle <smuckle@codeaurora.org> Tue Feb 28 17:39:31 2012 -0800
committer Steve Muckle <smuckle@codeaurora.org> Mon Mar 19 17:32:55 2012 -0700
tree 760a8e04a93974e5a4199133bc2d4569e5879ac2
parent 099aa69b9cfb6f4c5b56dd1d1d06ce9ef92cf2d5

init: apply SCHED_FIFO to kthreadd

Hotplug (cpu_up) latency currently suffers because the system
must wait for kthreadd to spawn certain kthreads (such as the
migration and workqueue kthreads) and for them to run for
the first time. Setting SCHED_FIFO will cause kthreadd to run
immediately. The newly created kthreads will inherit the scheduler
policy and run immediately also.

The scheduling policy of newly created kthreads is already set
back to SCHED_NORMAL in kthread_create_on_node, so nothing needs
to be done to restore normal scheduling behavior for the kthreads
once spawned.

Change-Id: I236ceb29845cf58ea1ea886fc3210ccaab2dd792
Signed-off-by: Steve Muckle <smuckle@codeaurora.org>

init/main.c

diff --git a/init/main.c b/init/main.c
index d7211fa..d0f330b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -347,6 +347,7 @@
 static noinline void __init_refok rest_init(void)
 {
 	int pid;
+	const struct sched_param param = { .sched_priority = 1 };
 
 	rcu_scheduler_starting();
 	/*
@@ -360,6 +361,7 @@
 	rcu_read_lock();
 	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
 	rcu_read_unlock();
+	sched_setscheduler_nocheck(kthreadd_task, SCHED_FIFO, &param);
 	complete(&kthreadd_done);
 
 	/*