On 13/12/2017 14:35, Peter Zijlstra wrote:
>> + if (xchg(&vcpu->arch.st.steal.preempted, KVM_VCPU_NOT_PREEMPTED) ==
>> + (KVM_VCPU_SHOULD_FLUSH | KVM_VCPU_PREEMPTED)) {
>> + /*
>> + * Do TLB_FLUSH before entering the guest, its passed
>> + * the stage of request checking
>> + */
>> + kvm_vcpu_flush_tlb(vcpu, false);
>> + }
> And not a single word, _anywhere_ on why this doesn't need
> invalidate_gpa or wtf that actually is.
FWIW I've fixed the changelogs in kvm/queue.
Paolo
