1 files changed, 33 insertions, 3 deletions

diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 042dee556125..995eb5054360 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -368,9 +368,39 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
-		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
-		    && ioapic->irr & (1 << index))
-			ioapic_service(ioapic, index, false);
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+		    ioapic->irr & (1 << index) && !e->fields.mask && !e->fields.remote_irr) {
+			/*
+			 * Pending status in irr may be outdated: the IRQ line may have
+			 * already been deasserted by a device while the IRQ was masked.
+			 * This occurs, for instance, if the interrupt is handled in a
+			 * Linux guest as a oneshot interrupt (IRQF_ONESHOT). In this
+			 * case the guest acknowledges the interrupt to the device in
+			 * its threaded irq handler, i.e. after the EOI but before
+			 * unmasking, so at the time of unmasking the IRQ line is
+			 * already down but our pending irr bit is still set. In such
+			 * cases, injecting this pending interrupt to the guest is
+			 * buggy: the guest will receive an extra unwanted interrupt.
+			 *
+			 * So we need to check here if the IRQ is actually still pending.
+			 * As we are generally not able to probe the IRQ line status
+			 * directly, we do it through irqfd resampler. Namely, we clear
+			 * the pending status and notify the resampler that this interrupt
+			 * is done, without actually injecting it into the guest. If the
+			 * IRQ line is actually already deasserted, we are done. If it is
+			 * still asserted, a new interrupt will be shortly triggered
+			 * through irqfd and injected into the guest.
+			 *
+			 * If, however, it's not possible to resample (no irqfd resampler
+			 * registered for this irq), then unconditionally inject this
+			 * pending interrupt into the guest, so the guest will not miss
+			 * an interrupt, although may get an extra unwanted interrupt.
+			 */
+			if (kvm_notify_irqfd_resampler(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index))
+				ioapic->irr &= ~(1 << index);
+			else
+				ioapic_service(ioapic, index, false);
+		}
 		if (e->fields.delivery_mode == APIC_DM_FIXED) {
 			struct kvm_lapic_irq irq;