kvm_apic_update_apicv is called when AVIC is still active, thus IRR bits
can be set by the CPU after it was called, and won't cause the irr_pending
to be set to true.
Also the logic in avic_kick_target_vcpu doesn't expect a race with this
function.
To make it simple, just keep irr_pending set to true and
let the next interrupt injection to the guest clear it.
Signed-off-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
---
arch/x86/kvm/lapic.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index baca9fa37a91c..6e1fbbf4c508b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2312,7 +2312,10 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
apic->irr_pending = true;
apic->isr_count = 1;
} else {
- apic->irr_pending = (apic_search_irr(apic) != -1);
+ /*
+ * Don't touch irr_pending, let it be cleared when
+ * we process the interrupt
+ */
apic->isr_count = count_vectors(apic->regs + APIC_ISR);
}
}
--
2.26.3
