nEPT: Fix cr3 handling in nested exit and entry

The existing code for handling cr3 and related VMCS fields during nested
exit and entry wasn't correct in all cases:

If L2 is allowed to control cr3 (and this is indeed the case in nested EPT),
during nested exit we must copy the modified cr3 from vmcs02 to vmcs12, and
we forgot to do so. This patch adds this copy.

If L0 isn't controlling cr3 when running L2 (i.e., L0 is using EPT), and
whoever does control cr3 (L1 or L2) is using PAE, the processor might have
saved PDPTEs and we should also save them in vmcs12 (and restore later).

Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Jun Nakajima <jun.nakajima@intel.com>
Signed-off-by: Xinhao Xu <xinhao.xu@intel.com>
Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 25a65063830537c2212e4aab36aed5eb3905dca1..e3c8e28aeb35d0c45ec2391801b9cd12c80cebe3 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7595,6 +7595,16 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
        kvm_set_cr3(vcpu, vmcs12->guest_cr3);
        kvm_mmu_reset_context(vcpu);
 
+       /*
+        * L1 may access the L2's PDPTR, so save them to construct vmcs12
+        */
+       if (enable_ept) {
+               vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+               vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+               vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+               vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+       }
+
        kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
        kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
 }
@@ -7917,6 +7927,22 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
        vmcs12->guest_pending_dbg_exceptions =
                vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
 
+       /*
+        * In some cases (usually, nested EPT), L2 is allowed to change its
+        * own CR3 without exiting. If it has changed it, we must keep it.
+        * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
+        * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
+        *
+        * Additionally, restore L2's PDPTR to vmcs12.
+        */
+       if (enable_ept) {
+               vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3);
+               vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
+               vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
+               vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
+               vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
+       }
+
        vmcs12->vm_entry_controls =
                (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
                (vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE);