sched: hmp: fix out-of-range CPU possible
authorChris Redpath <chris.redpath@arm.com>
Wed, 11 Jun 2014 13:08:40 +0000 (14:08 +0100)
committerJon Medhurst <tixy@linaro.org>
Wed, 11 Jun 2014 14:08:35 +0000 (15:08 +0100)
commit4378062f289e67259f017f6b176ee385dc974836
tree0797cd6fc66c81a5b55d71f660b8fd2c7a95c957
parentd1df056f9e6dd9707037ed74621e170dfa8f4c52
sched: hmp: fix out-of-range CPU possible

If someone hotplugs all the little CPUs while another CPU is handling
a wakeup, we can potentially return new_cpu == NR_CPUS from
hmp_select_slower_cpu (which is called internally by
hmp_best_little_cpu as well). We will use this to deref the
per_cpu rq array in hmp_next_down_delay which can go boom.

Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Signed-off-by: Jon Medhurst <tixy@linaro.org>
kernel/sched/fair.c