When KVM_CAP_HYPERV_SYNIC{,2} is activated, KVM already checks for
irqchip_in_kernel() so normally SynIC irqs should never be set. It is,
however,  possible for a misbehaving VMM to write to SYNIC/STIMER MSRs
causing erroneous behavior.

The immediate issue being fixed is that kvm_irq_delivery_to_apic()
(kvm_irq_delivery_to_apic_fast()) crashes when called with
'irq.shorthand = APIC_DEST_SELF' and 'src == NULL'.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/kvm/hyperv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 7480e3562d30..a79a094c1266 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -453,6 +453,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
 	struct kvm_lapic_irq irq;
 	int ret, vector;
 
+	if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm))
+		return -EINVAL;
+
 	if (sint >= ARRAY_SIZE(synic->sint))
 		return -EINVAL;
 
-- 
2.35.1