| Subject | Re: [PATCH v2 31/32] KVM: nVMX: Don't flush TLB on nested VM transition with EPT enabled | From | Paolo Bonzini <> | Date | Tue, 17 Mar 2020 18:18:37 +0100 |
| |
On 17/03/20 05:52, Sean Christopherson wrote: > diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c > index d816f1366943..a77eab5b0e8a 100644 > --- a/arch/x86/kvm/vmx/nested.c > +++ b/arch/x86/kvm/vmx/nested.c > @@ -1123,7 +1123,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne > } > > if (!nested_ept) > - kvm_mmu_new_cr3(vcpu, cr3, false); > + kvm_mmu_new_cr3(vcpu, cr3, enable_ept);
Even if enable_ept == false, we could have already scheduled or flushed the TLB soon due to one of 1) nested_vmx_transition_tlb_flush 2) vpid_sync_context in prepare_vmcs02 3) the processor doing it for !enable_vpid.
So for !enable_ept only KVM_REQ_MMU_SYNC is needed, not KVM_REQ_TLB_FLUSH_CURRENT I think. Worth adding a TODO?
Paolo
> vcpu->arch.cr3 = cr3; > kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); > -- 2.24.1
|