From 815403a6ea8828402a64fea9df8ca62be1f1c0ad Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Sep 2019 14:45:16 -0700 Subject: [PATCH] KVM: nVMX: Always write vmcs02.GUEST_CR3 during nested VM-Enter commit 04f11ef45810da5ae2542dd78cc353f3761bd2cb upstream. Write the desired L2 CR3 into vmcs02.GUEST_CR3 during nested VM-Enter instead of deferring the VMWRITE until vmx_set_cr3(). If the VMWRITE is deferred, then KVM can consume a stale vmcs02.GUEST_CR3 when it refreshes vmcs12->guest_cr3 during nested_vmx_vmexit() if the emulated VM-Exit occurs without actually entering L2, e.g. if the nested run is squashed because nested VM-Enter (from L1) is putting L2 into HLT. Note, the above scenario can occur regardless of whether L1 is intercepting HLT, e.g. L1 can intercept HLT and then re-enter L2 with vmcs.GUEST_ACTIVITY_STATE=HALTED. But practically speaking, a VMM will likely put a guest into HALTED if and only if it's not intercepting HLT. In an ideal world where EPT *requires* unrestricted guest (and vice versa), VMX could handle CR3 similar to how it handles RSP and RIP, e.g. mark CR3 dirty and conditionally load it at vmx_vcpu_run(). But the unrestricted guest silliness complicates the dirty tracking logic to the point that explicitly handling vmcs02.GUEST_CR3 during nested VM-Enter is a simpler overall implementation. Cc: stable@vger.kernel.org Reported-and-tested-by: Reto Buerki Tested-by: Vitaly Kuznetsov Reviewed-by: Liran Alon Signed-off-by: Sean Christopherson Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/nested.c | 10 ++++++++++ arch/x86/kvm/vmx/vmx.c | 10 +++++++--- 2 files changed, 17 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0e7c930..d052374 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2418,6 +2418,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 04a8212..f09a213 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2995,6 +2995,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -3011,15 +3012,18 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) + /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (enable_unrestricted_guest || is_paging(vcpu)) guest_cr3 = kvm_read_cr3(vcpu); else guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -- 2.7.4