KVM: x86: nVMX: close leak of L0's x2APIC MSRs (CVE-2019-3887)

The nested_vmx_prepare_msr_bitmap() function doesn't directly guard the
x2APIC MSR intercepts with the "virtualize x2APIC mode" MSR. As a
result, we discovered the potential for a buggy or malicious L1 to get
access to L0's x2APIC MSRs, via an L2, as follows.

1. L1 executes WRMSR(IA32_SPEC_CTRL, 1). This causes the spec_ctrl
variable, in nested_vmx_prepare_msr_bitmap() to become true.
2. L1 disables "virtualize x2APIC mode" in VMCS12.
3. L1 enables "APIC-register virtualization" in VMCS12.

Now, KVM will set VMCS02's x2APIC MSR intercepts from VMCS12, and then
set "virtualize x2APIC mode" to 0 in VMCS02. Oops.

This patch closes the leak by explicitly guarding VMCS02's x2APIC MSR
intercepts with VMCS12's "virtualize x2APIC mode" control.

The scenario outlined above and fix prescribed here, were verified with
a related patch in kvm-unit-tests titled "Add leak scenario to
virt_x2apic_mode_test".

Note, it looks like this issue may have been introduced inadvertently
during a merge---see 15303ba5.
Signed-off-by: Marc Orr <marcorr@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/vmx/nested.c

@@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
 	}
 }
 
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+	int msr;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned word = msr / BITS_PER_LONG;
+
+		msr_bitmap[word] = ~0;
+		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	}
+}
+
 /*
  * Merge L0's and L1's MSR bitmap, return false to indicate that
  * we do not use the hardware.
@@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 		return false;
 
 	msr_bitmap_l1 = (unsigned long *)kmap(page);
-	if (nested_cpu_has_apic_reg_virt(vmcs12)) {
-		/*
-		 * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
-		 * just lets the processor take the value from the virtual-APIC page;
-		 * take those 256 bits directly from the L1 bitmap.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-			unsigned word = msr / BITS_PER_LONG;
-			msr_bitmap_l0[word] = msr_bitmap_l1[word];
-			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
-		}
-	} else {
-		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-			unsigned word = msr / BITS_PER_LONG;
-			msr_bitmap_l0[word] = ~0;
-			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
-		}
-	}
 
-	nested_vmx_disable_intercept_for_msr(
-		msr_bitmap_l1, msr_bitmap_l0,
-		X2APIC_MSR(APIC_TASKPRI),
-		MSR_TYPE_W);
+	/*
+	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
+	 * 4-byte writes on 32-bit systems) up front to enable intercepts for
+	 * the x2APIC MSR range and selectively disable them below.
+	 */
+	enable_x2apic_msr_intercepts(msr_bitmap_l0);
+
+	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
+		if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+			/*
+			 * L0 need not intercept reads for MSRs between 0x800
+			 * and 0x8ff, it just lets the processor take the value
+			 * from the virtual-APIC page; take those 256 bits
+			 * directly from the L1 bitmap.
+			 */
+			for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+				unsigned word = msr / BITS_PER_LONG;
+
+				msr_bitmap_l0[word] = msr_bitmap_l1[word];
+			}
+		}
 
-	if (nested_cpu_has_vid(vmcs12)) {
-		nested_vmx_disable_intercept_for_msr(
-			msr_bitmap_l1, msr_bitmap_l0,
-			X2APIC_MSR(APIC_EOI),
-			MSR_TYPE_W);
 		nested_vmx_disable_intercept_for_msr(
 			msr_bitmap_l1, msr_bitmap_l0,
-			X2APIC_MSR(APIC_SELF_IPI),
+			X2APIC_MSR(APIC_TASKPRI),
 			MSR_TYPE_W);
+
+		if (nested_cpu_has_vid(vmcs12)) {
+			nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
+				X2APIC_MSR(APIC_EOI),
+				MSR_TYPE_W);
+			nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
+				X2APIC_MSR(APIC_SELF_IPI),
+				MSR_TYPE_W);
+		}
 	}
 
 	if (spec_ctrl)