sched: allow select_prev_cpu_us to be set to values greater than 100us

At present sched_select_prev_cpu_us tunable is restricted to values
below 100us.  Fix this unintended restriction.

CRs-Fixed: 972237
Change-Id: I5eaf9f40468805c396328ca1022baef32acf8de0
Signed-off-by: Joonwoo Park <joonwoop@codeaurora.org>
This commit is contained in:
Joonwoo Park 2016-01-14 18:22:36 -08:00 committed by David Keitel
parent fbeb32ce8f
commit 615b6f6221

View file

@ -3996,8 +3996,11 @@ int sched_hmp_proc_update_handler(struct ctl_table *table, int write,
goto done;
}
update_min_nice = 1;
} else {
/* all tunables other than min_nice are in percentage */
} else if (data != &sysctl_sched_select_prev_cpu_us) {
/*
* all tunables other than min_nice and prev_cpu_us are
* in percentage.
*/
if (sysctl_sched_downmigrate_pct >
sysctl_sched_upmigrate_pct || *data > 100) {
*data = old_val;