sched/idle: Optimize the loop time algorithm to reduce multicore disturb

hulk inclusion
category: bugfix
bugzilla: 180841 https://gitee.com/openeuler/kernel/issues/I4DDEL



The idle cpu will call ktime_get frequently. The smp_rmb() will influence the
share cache, especially arm a15 share L2 cache. The performance drop will enlarge
when the loop time is millisecond level.

Signed-off-by: Li Hua <hucool.lihua@huawei.com>
Reviewed-by: Chen Hui <judy.chenhui@huawei.com>
Signed-off-by: Chen Jun <chenjun102@huawei.com>
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>