diff options
| author | Vitaly Kuznetsov | 2018-10-08 21:28:08 +0200 |
|---|---|---|
| committer | Paolo Bonzini | 2018-10-17 00:30:04 +0200 |
| commit | 14c07ad89f4d728a468caaea6a769c018c2b8dd6 (patch) | |
| tree | ccb089dc2bd41e92d0f0e7adf3891a34f57a325e /arch/x86/kvm/mmu.c | |
| parent | x86/kvm/mmu.c: add kvm_mmu parameter to kvm_mmu_free_roots() (diff) | |
| download | kernel-qcow2-linux-14c07ad89f4d728a468caaea6a769c018c2b8dd6.tar.gz kernel-qcow2-linux-14c07ad89f4d728a468caaea6a769c018c2b8dd6.tar.xz kernel-qcow2-linux-14c07ad89f4d728a468caaea6a769c018c2b8dd6.zip | |
x86/kvm/mmu: introduce guest_mmu
When EPT is used for nested guest we need to re-init MMU as shadow
EPT MMU (nested_ept_init_mmu_context() does that). When we return back
from L2 to L1 kvm_mmu_reset_context() in nested_vmx_load_cr3() resets
MMU back to normal TDP mode. Add a special 'guest_mmu' so we can use
separate root caches; the improved hit rate is not very important for
single vCPU performance, but it avoids contention on the mmu_lock for
many vCPUs.
On the nested CPUID benchmark, with 16 vCPUs, an L2->L1->L2 vmexit
goes from 42k to 26k cycles.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch/x86/kvm/mmu.c')
| -rw-r--r-- | arch/x86/kvm/mmu.c | 20 |
1 files changed, 15 insertions, 5 deletions
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 96c753746b3b..bf9e3145ff0b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4832,7 +4832,10 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); static union kvm_mmu_page_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty) { - union kvm_mmu_page_role role = vcpu->arch.mmu->base_role; + union kvm_mmu_page_role role; + + /* Role is inherited from root_mmu */ + role.word = vcpu->arch.root_mmu.base_role.word; role.level = PT64_ROOT_4LEVEL; role.direct = false; @@ -4982,8 +4985,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOTS_ALL); - WARN_ON(VALID_PAGE(vcpu->arch.mmu->root_hpa)); + kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL); + WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa)); + kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); + WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa)); } EXPORT_SYMBOL_GPL(kvm_mmu_unload); @@ -5422,13 +5427,18 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; + vcpu->arch.root_mmu.root_hpa = INVALID_PAGE; vcpu->arch.root_mmu.translate_gpa = translate_gpa; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE; + vcpu->arch.guest_mmu.translate_gpa = translate_gpa; + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + + vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; return alloc_mmu_pages(vcpu); } |