From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 24 Nov 2008 11:26:19 +0000 (+0100)
Subject: KVM: VMX: Fix pending NMI-vs.-IRQ race for user space irqchip
X-Git-Tag: v2.6.29-rc1~539^2~6
X-Git-Url: https://openfabrics.org/gitweb/?a=commitdiff_plain;h=264ff01d55b456932cef03082448b41d2edeb6a1;p=~shefty%2Frdma-dev.git

KVM: VMX: Fix pending NMI-vs.-IRQ race for user space irqchip

As with the kernel irqchip, don't allow an NMI to stomp over an already
injected IRQ; instead wait for the IRQ injection to be completed.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e446f232588..487e1dcdce3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2486,7 +2486,9 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
 	vmx_update_window_states(vcpu);
 
 	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
-		if (vcpu->arch.nmi_window_open) {
+		if (vcpu->arch.interrupt.pending) {
+			enable_nmi_window(vcpu);
+		} else if (vcpu->arch.nmi_window_open) {
 			vcpu->arch.nmi_pending = false;
 			vcpu->arch.nmi_injected = true;
 		} else {