KVM: Fix mmu_reload() clash with nested vmx event injection

Currently the inject_pending_event() call during guest entry happens after
kvm_mmu_reload().  This is for historical reasons - we used to
inject_pending_event() in atomic context, while kvm_mmu_reload() needs task
context.

A problem is that nested vmx can cause the mmu context to be reset, if event
injection is intercepted and causes a #VMEXIT instead (the #VMEXIT resets
CR0/CR3/CR4).  If this happens, we end up with invalid root_hpa, and since
kvm_mmu_reload() has already run, no one will fix it and we end up entering
the guest this way.

Fix by reordering event injection to be before kvm_mmu_reload().  Use
->cancel_injection() to undo if kvm_mmu_reload() fails.

https://bugzilla.kernel.org/show_bug.cgi?id=42980

Reported-by: Luke-Jr <luke-jr+linuxbugs@utopios.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

1 files changed, 6 insertions, 4 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4de705cdcafd..b78f89d34242 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5279,10 +5279,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_deliver_pmi(vcpu);
 	}
 
-	r = kvm_mmu_reload(vcpu);
-	if (unlikely(r))
-		goto out;
-
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
 		inject_pending_event(vcpu);
 
@@ -5298,6 +5294,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	r = kvm_mmu_reload(vcpu);
+	if (unlikely(r)) {
+		kvm_x86_ops->cancel_injection(vcpu);
+		goto out;
+	}
+
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);