KVM: VMX: Reject KVM_RUN if userspace forces emulation during nested VM-Enter

Extend KVM's restrictions on userspace forcing "emulation required" at odd
times to cover stuffing invalid guest state while a nested run is pending.
Clobbering guest state while KVM is in the middle of emulating VM-Enter is
nonsensical, as it puts the vCPU into an architecturally impossible state,
and will trip KVM's sanity check that guards against KVM bugs, e.g. helps
detect missed VMX consistency checks.

  WARNING: CPU: 3 PID: 6336 at arch/x86/kvm/vmx/vmx.c:6480 __vmx_handle_exit arch/x86/kvm/vmx/vmx.c:6480 [inline]
  WARNING: CPU: 3 PID: 6336 at arch/x86/kvm/vmx/vmx.c:6480 vmx_handle_exit+0x40f/0x1f70 arch/x86/kvm/vmx/vmx.c:6637
  Modules linked in:
  CPU: 3 UID: 0 PID: 6336 Comm: syz.0.73 Not tainted 6.13.0-rc1-syzkaller-00316-gb5f217084ab3 #0
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
  RIP: 0010:__vmx_handle_exit arch/x86/kvm/vmx/vmx.c:6480 [inline]
  RIP: 0010:vmx_handle_exit+0x40f/0x1f70 arch/x86/kvm/vmx/vmx.c:6637
   <TASK>
   vcpu_enter_guest arch/x86/kvm/x86.c:11081 [inline]
   vcpu_run+0x3047/0x4f50 arch/x86/kvm/x86.c:11242
   kvm_arch_vcpu_ioctl_run+0x44a/0x1740 arch/x86/kvm/x86.c:11560
   kvm_vcpu_ioctl+0x6ce/0x1520 virt/kvm/kvm_main.c:4340
   vfs_ioctl fs/ioctl.c:51 [inline]
   __do_sys_ioctl fs/ioctl.c:906 [inline]
   __se_sys_ioctl fs/ioctl.c:892 [inline]
   __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>

Reported-by: syzbot+ac0bc3a70282b4d586cc@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/67598fb9.050a0220.17f54a.003b.GAE@google.com
Debugged-by: James Houghton <jthoughton@google.com>
Tested-by: James Houghton <jthoughton@google.com>
Link: https://lore.kernel.org/r/20250224171409.2348647-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

arch/x86/kvm/vmx/vmx.c

@@ -5876,11 +5876,35 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu)
+/*
+ * Returns true if emulation is required (due to the vCPU having invalid state
+ * with unsrestricted guest mode disabled) and KVM can't faithfully emulate the
+ * current vCPU state.
+ */
+static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	return vmx->emulation_required && !vmx->rmode.vm86_active &&
+	if (!vmx->emulation_required)
+		return false;
+
+	/*
+	 * It is architecturally impossible for emulation to be required when a
+	 * nested VM-Enter is pending completion, as VM-Enter will VM-Fail if
+	 * guest state is invalid and unrestricted guest is disabled, i.e. KVM
+	 * should synthesize VM-Fail instead emulation L2 code.  This path is
+	 * only reachable if userspace modifies L2 guest state after KVM has
+	 * performed the nested VM-Enter consistency checks.
+	 */
+	if (vmx->nested.nested_run_pending)
+		return true;
+
+	/*
+	 * KVM only supports emulating exceptions if the vCPU is in Real Mode.
+	 * If emulation is required, KVM can't perform a successful VM-Enter to
+	 * inject the exception.
+	 */
+	return !vmx->rmode.vm86_active &&
 	       (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected);
 }
 
@@ -5903,7 +5927,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (!kvm_emulate_instruction(vcpu, 0))
 			return 0;
 
-		if (vmx_emulation_required_with_pending_exception(vcpu)) {
+		if (vmx_unhandleable_emulation_required(vcpu)) {
 			kvm_prepare_emulation_failure_exit(vcpu);
 			return 0;
 		}
@@ -5927,7 +5951,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
 {
-	if (vmx_emulation_required_with_pending_exception(vcpu)) {
+	if (vmx_unhandleable_emulation_required(vcpu)) {
 		kvm_prepare_emulation_failure_exit(vcpu);
 		return 0;
 	}