[CVE-2016-4440][xenial] kvm:vmx: more complete state update on APICv on/off

[Luis Henriques]

From: Roman Kagan <rkagan at virtuozzo.com>

The function to update APICv on/off state (in particular, to deactivate
it when enabling Hyper-V SynIC) is incomplete: it doesn't adjust
APICv-related fields among secondary processor-based VM-execution
controls.  As a result, Windows 2012 guests get stuck when SynIC-based
auto-EOI interrupt intersected with e.g. an IPI in the guest.

In addition, the MSR intercept bitmap isn't updated every time "virtualize
x2APIC mode" is toggled.  This path can only be triggered by a malicious
guest, because Windows didn't use x2APIC but rather their own synthetic
APIC access MSRs; however a guest running in a SynIC-enabled VM could
switch to x2APIC and thus obtain direct access to host APIC MSRs
(CVE-2016-4440).

The patch fixes those omissions.

Signed-off-by: Roman Kagan <rkagan at virtuozzo.com>
Reported-by: Steve Rutherford <srutherford at google.com>
Reported-by: Yang Zhang <yang.zhang.wz at gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini at redhat.com>
(cherry picked from commit 3ce424e45411cf5a13105e0386b6ecf6eeb4f66f)
CVE-2016-4440
BugLink: https://bugs.launchpad.net/bugs/1584192
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 arch/x86/kvm/vmx.c | 48 ++++++++++++++++++++++++++++++------------------
 1 file changed, 30 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index aaea1bd5558f..92d2564844ae 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2331,7 +2331,9 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 
 	if (is_guest_mode(vcpu))
 		msr_bitmap = vmx_msr_bitmap_nested;
-	else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
+	else if (cpu_has_secondary_exec_ctrls() &&
+		 (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
+		  SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -4692,6 +4694,19 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+	if (cpu_has_secondary_exec_ctrls()) {
+		if (kvm_vcpu_apicv_active(vcpu))
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+				      SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				      SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+		else
+			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+					SECONDARY_EXEC_APIC_REGISTER_VIRT |
+					SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+	}
+
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_set_msr_bitmap(vcpu);
 }
 
 static u32 vmx_exec_control(struct vcpu_vmx *vmx)
@@ -6247,23 +6262,20 @@ static __init int hardware_setup(void)
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
-	if (enable_apicv) {
-		for (msr = 0x800; msr <= 0x8ff; msr++)
-			vmx_disable_intercept_msr_read_x2apic(msr);
-
-		/* According SDM, in x2apic mode, the whole id reg is used.
-		 * But in KVM, it only use the highest eight bits. Need to
-		 * intercept it */
-		vmx_enable_intercept_msr_read_x2apic(0x802);
-		/* TMCCT */
-		vmx_enable_intercept_msr_read_x2apic(0x839);
-		/* TPR */
-		vmx_disable_intercept_msr_write_x2apic(0x808);
-		/* EOI */
-		vmx_disable_intercept_msr_write_x2apic(0x80b);
-		/* SELF-IPI */
-		vmx_disable_intercept_msr_write_x2apic(0x83f);
-	}
+	for (msr = 0x800; msr <= 0x8ff; msr++)
+		vmx_disable_intercept_msr_read_x2apic(msr);
+
+	/* According SDM, in x2apic mode, the whole id reg is used.  But in
+	 * KVM, it only use the highest eight bits. Need to intercept it */
+	vmx_enable_intercept_msr_read_x2apic(0x802);
+	/* TMCCT */
+	vmx_enable_intercept_msr_read_x2apic(0x839);
+	/* TPR */
+	vmx_disable_intercept_msr_write_x2apic(0x808);
+	/* EOI */
+	vmx_disable_intercept_msr_write_x2apic(0x80b);
+	/* SELF-IPI */
+	vmx_disable_intercept_msr_write_x2apic(0x83f);
 
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(0ull,