3 files changed, 54 insertions, 1 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1e215e8b9377..a26f13bd34e0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2784,11 +2784,46 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
         return r;
 }
 
+static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
+{
+        struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
+
+        g_context->get_cr3           = get_cr3;
+        g_context->inject_page_fault = kvm_inject_page_fault;
+
+        /*
+         * Note that arch.mmu.gva_to_gpa translates l2_gva to l1_gpa. The
+         * translation of l2_gpa to l1_gpa addresses is done using the
+         * arch.nested_mmu.gva_to_gpa function. Basically the gva_to_gpa
+         * functions between mmu and nested_mmu are swapped.
+         */
+        if (!is_paging(vcpu)) {
+                g_context->root_level = 0;
+                g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested;
+        } else if (is_long_mode(vcpu)) {
+                reset_rsvds_bits_mask(vcpu, g_context, PT64_ROOT_LEVEL);
+                g_context->root_level = PT64_ROOT_LEVEL;
+                g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
+        } else if (is_pae(vcpu)) {
+                reset_rsvds_bits_mask(vcpu, g_context, PT32E_ROOT_LEVEL);
+                g_context->root_level = PT32E_ROOT_LEVEL;
+                g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
+        } else {
+                reset_rsvds_bits_mask(vcpu, g_context, PT32_ROOT_LEVEL);
+                g_context->root_level = PT32_ROOT_LEVEL;
+                g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
+        }
+
+        return 0;
+}
+
 static int init_kvm_mmu(struct kvm_vcpu *vcpu)
 {
         vcpu->arch.update_pte.pfn = bad_pfn;
 
-        if (tdp_enabled)
+        if (mmu_is_nested(vcpu))
+                return init_kvm_nested_mmu(vcpu);
+        else if (tdp_enabled)
                 return init_kvm_tdp_mmu(vcpu);
         else
                 return init_kvm_softmmu(vcpu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 7086ca85d3e7..513abbb5ff46 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -47,6 +47,7 @@
 #define PFERR_USER_MASK (1U << 2)
 #define PFERR_RSVD_MASK (1U << 3)
 #define PFERR_FETCH_MASK (1U << 4)
+#define PFERR_NESTED_MASK (1U << 31)
 
 int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 46843ed36dc1..e4c76bf86081 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3489,6 +3489,22 @@ static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
         return gpa;
 }
 
+static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+{
+        gpa_t t_gpa;
+        u32 error;
+
+        BUG_ON(!mmu_is_nested(vcpu));
+
+        /* NPT walks are always user-walks */
+        access |= PFERR_USER_MASK;
+        t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &error);
+        if (t_gpa == UNMAPPED_GVA)
+                vcpu->arch.fault.error_code |= PFERR_NESTED_MASK;
+
+        return t_gpa;
+}
+
 gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
 {
         u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
@@ -5704,6 +5720,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
         vcpu->arch.walk_mmu = &vcpu->arch.mmu;
         vcpu->arch.mmu.root_hpa = INVALID_PAGE;
         vcpu->arch.mmu.translate_gpa = translate_gpa;
+        vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
         if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
                 vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
         else