Messages in this thread | | | Subject | Re: [PATCH v5 4/5] KVM: VMX: Allow direct access to MSR_IA32_SPEC_CTRL | From | David Woodhouse <> | Date | Wed, 31 Jan 2018 22:05:29 +0000 |
| |
On Wed, 2018-01-31 at 13:18 -0800, Jim Mattson wrote: > On Wed, Jan 31, 2018 at 12:21 PM, David Woodhouse wrote: > > > > > Reading and writing this MSR is expensive. And if it's yielded to the > > guest in the MSR bitmap, that means we have to save its value on vmexit > > and set it back to zero. > > Agreed. But my point is that if it's not yielded to the guest in the > MSR bitmap, then we don't have to save its value on VM-exit and set it > back to zero. The vmcs02 MSR bitmap is reconstructed on every L1->L2 > transition. Sometimes, it will yield the MSR and sometimes it won't.
Strictly: if SPEC_CTRL is not already set to 1 *and* hasn't been yielded to the guest in the MSR bitmap, then we don't have to set it back to zero.
If L1 decides it's *always* going to trap and never pass through, but the value is already set to non-zero, we need to get that case right. [unhandled content-type:application/x-pkcs7-signature]
| |