KVM: nVMX: Do not generate #DF if #PF happens during exception delivery into L2

If #PF happens during delivery of an exception into L2 and L1 also do
not have the page mapped in its shadow page table then L0 needs to
generate vmexit to L2 with original event in IDT_VECTORING_INFO, but
current code combines both exception and generates #DF instead. Fix that
by providing nVMX specific function to handle page faults during page
table walk that handles this case correctly.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 20 insertions, 0 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ac9ded4d4257..be7fd0e1ad42 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7518,6 +7518,20 @@ static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
         vcpu->arch.walk_mmu = &vcpu->arch.mmu;
 }
 
+static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
+                struct x86_exception *fault)
+{
+        struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+        WARN_ON(!is_guest_mode(vcpu));
+
+        /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
+        if (vmcs12->exception_bitmap & (1u << PF_VECTOR))
+                nested_vmx_vmexit(vcpu);
+        else
+                kvm_inject_page_fault(vcpu, fault);
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7771,6 +7785,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
         kvm_set_cr3(vcpu, vmcs12->guest_cr3);
         kvm_mmu_reset_context(vcpu);
 
+        if (!enable_ept)
+                vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
+
         /*
          * L1 may access the L2's PDPTR, so save them to construct vmcs12
          */
@@ -8230,6 +8247,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
         kvm_set_cr3(vcpu, vmcs12->host_cr3);
         kvm_mmu_reset_context(vcpu);
 
+        if (!enable_ept)
+                vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+
         if (enable_vpid) {
                 /*
                  * Trivially support vpid by letting L2s share their parent