3.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dimitri Sivanich <redacted>

commit a841f8cef4bb124f0f5563314d0beaf2e1249d72 upstream.

It does not get processed because sched_domain_level_max is 0 at the
time that setup_relax_domain_level() is run.

Simply accept the value as it is, as we don't know the value of
sched_domain_level_max until sched domain construction is completed.

Fix sched_relax_domain_level in cpuset.  The build_sched_domain() routine calls
the set_domain_attribute() routine prior to setting the sd->level, however,
the set_domain_attribute() routine relies on the sd->level to decide whether
idle load balancing will be off/on.

Signed-off-by: Dimitri Sivanich <redacted>
Signed-off-by: Peter Zijlstra <redacted>
Link: http://lkml.kernel.org/r/20120605184436.GA15668@sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 kernel/sched/core.c |    9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c

@@ -6230,11 +6230,8 @@ int sched_domain_level_max;
 
 static int __init setup_relax_domain_level(char *str)
 {
-	unsigned long val;
-
-	val = simple_strtoul(str, NULL, 0);
-	if (val < sched_domain_level_max)
-		default_relax_domain_level = val;
+	if (kstrtoint(str, 0, &default_relax_domain_level))
+		pr_warn("Unable to set relax_domain_level\n");
 
 	return 1;
 }

@@ -6439,7 +6436,6 @@ struct sched_domain *build_sched_domain(
 	if (!sd)
 		return child;
 
-	set_domain_attribute(sd, attr);
 	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
 	if (child) {
 		sd->level = child->level + 1;

@@ -6447,6 +6443,7 @@ struct sched_domain *build_sched_domain(
 		child->parent = sd;
 	}
 	sd->child = child;
+	set_domain_attribute(sd, attr);
 
 	return sd;
 }