[PATCH v3 9/9] x86/kvm/mmu: check if MMU reconfiguration is needed in init_kvm_nested_mmu()

From: Vitaly Kuznetsov
Date: Mon Oct 01 2018 - 10:21:01 EST


We don't use root page role for nested_mmu, however, optimizing out
re-initialization in case nothing changed is still valuable as this
is done for every nested vmentry.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Reviewed-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
---
arch/x86/kvm/mmu.c | 6 ++++++
1 file changed, 6 insertions(+)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 10b39ff83943..1c8e439e4373 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4920,8 +4920,14 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu)

static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
+ union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;

+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == g_context->mmu_role.as_u64)
+ return;
+
+ g_context->mmu_role.as_u64 = new_role.as_u64;
g_context->get_cr3 = get_cr3;
g_context->get_pdptr = kvm_pdptr_read;
g_context->inject_page_fault = kvm_inject_page_fault;
--
2.17.1