KVM: nVMX: mark vmcs12 pages dirty on L2 exit

commit c9f04407f2e0b3fc9ff7913c65fcfcb0a4b61570 upstream.

The host physical addresses of L1's Virtual APIC Page and Posted
Interrupt descriptor are loaded into the VMCS02. The CPU may write
to these pages via their host physical address while L2 is running,
bypassing address-translation-based dirty tracking (e.g. EPT write
protection). Mark them dirty on every exit from L2 to prevent them
from getting out of sync with dirty tracking.

Also mark the virtual APIC page and the posted interrupt descriptor
dirty when KVM is virtualizing posted interrupt processing.

Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3df636400ec8c31732a76f03988a2e8475c25cd3..b886a7c9ed4b9772bb9336e16804a9b30dc08ac9 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4527,6 +4527,28 @@ static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
        return enable_apicv && lapic_in_kernel(vcpu);
 }
 
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+       struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+       gfn_t gfn;
+
+       /*
+        * Don't need to mark the APIC access page dirty; it is never
+        * written to by the CPU during APIC virtualization.
+        */
+
+       if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+               gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+               kvm_vcpu_mark_page_dirty(vcpu, gfn);
+       }
+
+       if (nested_cpu_has_posted_intr(vmcs12)) {
+               gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+               kvm_vcpu_mark_page_dirty(vcpu, gfn);
+       }
+}
+
+
 static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
        struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4534,18 +4556,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
        void *vapic_page;
        u16 status;
 
-       if (vmx->nested.pi_desc &&
-           vmx->nested.pi_pending) {
-               vmx->nested.pi_pending = false;
-               if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-                       return;
-
-               max_irr = find_last_bit(
-                       (unsigned long *)vmx->nested.pi_desc->pir, 256);
+       if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+               return;
 
-               if (max_irr == 256)
-                       return;
+       vmx->nested.pi_pending = false;
+       if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+               return;
 
+       max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+       if (max_irr != 256) {
                vapic_page = kmap(vmx->nested.virtual_apic_page);
                __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
                kunmap(vmx->nested.virtual_apic_page);
@@ -4557,6 +4576,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
                        vmcs_write16(GUEST_INTR_STATUS, status);
                }
        }
+
+       nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -7761,6 +7782,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
                                vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
                                KVM_ISA_VMX);
 
+       /*
+        * The host physical addresses of some pages of guest memory
+        * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
+        * may write to these pages via their host physical address while
+        * L2 is running, bypassing any address-translation-based dirty
+        * tracking (e.g. EPT write protection).
+        *
+        * Mark them dirty on every exit from L2 to prevent them from
+        * getting out of sync with dirty tracking.
+        */
+       nested_mark_vmcs12_pages_dirty(vcpu);
+
        if (vmx->nested.nested_run_pending)
                return false;