Messages in this thread | | | From | David Matlack <> | Date | Mon, 7 Feb 2022 13:50:23 -0800 | Subject | Re: [PATCH 01/23] KVM: MMU: pass uses_nx directly to reset_shadow_zero_bits_mask |
| |
On Mon, Feb 7, 2022 at 8:10 AM Sean Christopherson <seanjc@google.com> wrote: > > On Sat, Feb 05, 2022, Paolo Bonzini wrote: > > On 2/4/22 18:59, David Matlack wrote: > > > > + reset_shadow_zero_bits_mask(vcpu, context, is_efer_nx(context)); > > > > > > Out of curiousity, how does KVM mitigate iTLB multi-hit when shadowing > > > NPT and the guest has not enabled EFER.NX? > > > > You got me worried for a second but iTLB multihit is Intel-only, isn't it? > > AFAIK, yes, big Core only. arch/x86/kernel/cpu/common.c sets NO_ITLB_MULTIHIT > for all AMD, Hygon, and Atom CPUs.
Ah that's right, it's Intel-only. Thanks!
| |