Messages in this thread | | | Date | Thu, 5 Oct 2023 20:48:45 -0700 | Subject | Re: [PATCH v2] KVM: x86: Refine calculation of guest wall clock to use a single TSC read | From | Sean Christopherson <> |
| |
On Thu, 05 Oct 2023 10:16:10 +0100, David Woodhouse wrote: > When populating the guest's PV wall clock information, KVM currently does > a simple 'kvm_get_real_ns() - get_kvmclock_ns(kvm)'. This is an antipattern > which should be avoided; when working with the relationship between two > clocks, it's never correct to obtain one of them "now" and then the other > at a slightly different "now" after an unspecified period of preemption > (which might not even be under the control of the kernel, if this is an > L1 hosting an L2 guest under nested virtualization). > > [...]
Applied to kvm-x86 misc, thanks! And double thanks for the function comment, it's awesome!
Note, I moved the declaration in x86.h just below get_kvmclock_ns() to bundle the two kvmclock helpers together.
[1/1] KVM: x86: Refine calculation of guest wall clock to use a single TSC read https://github.com/kvm-x86/linux/commit/5d6d6a7d7e66
-- https://github.com/kvm-x86/linux/tree/next
| |