On Mon, Feb 27, 2017 at 09:48:35PM +0800, Wanpeng Li wrote: > 2017-02-27 20:43 GMT+08:00 Peter Zijlstra <pet...@infradead.org>: > > I have no clue what that tries to do. > > The patch tries to mark sched clock stable if > KVM_FEATURE_CLOCKSOURCE_STABLE_BIT / PVCLOCK_TSC_STABLE_BIT is set in > kvm guest even if there is no invariant tsc cpuid bit.
I just ripped out the interface to 'set stable' for good reasons. Also, the branch you add it to doesn't in fact do clear_stable -- so who does? Also, the sched/clock.c code shouldn't know about hypervisor anything. So whatever it is you're doing, you're doing it wrong.