diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 042dee5561258f166f289276be3376d6130c4a0c..995eb50543601f70f8162ef1dfc2a79f6d21d032 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+ * Pending status in irr may be outdated: the IRQ line may have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;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9f508c8e66e12b1fc15c78489eea9cd10b7c7f22..a9adf75344bee024bf8fb02b13036046f9aabae5 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1987,6 +1987,9 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
+bool kvm_notify_irqfd_resampler(struct kvm *kvm,
+ unsigned int irqchip,
+ unsigned int pin);
void kvm_irq_routing_update(struct kvm *);
#else
static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
@@ -1995,6 +1998,13 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
}
static inline void kvm_irqfd_release(struct kvm *kvm) {}
+
+static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
+ unsigned int irqchip,
+ unsigned int pin)
+{
+ return false;
+}
#endif
#else
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 61aea70dd888d4553e9c39978979c3cd82222dc6..b0af834ffa95092540d0aee1e39602c3907d84bb 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -55,6 +55,15 @@ irqfd_inject(struct work_struct *work)
irqfd->gsi, 1, false);
}
+static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler)
+{
+ struct kvm_kernel_irqfd *irqfd;
+
+ list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
+ srcu_read_lock_held(&resampler->kvm->irq_srcu))
+ eventfd_signal(irqfd->resamplefd, 1);
+}
+
/*
* Since resampler irqfds share an IRQ source ID, we de-assert once
* then notify all of the resampler irqfds using this GSI. We can't
@@ -65,7 +74,6 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
{
struct kvm_kernel_irqfd_resampler *resampler;
struct kvm *kvm;
- struct kvm_kernel_irqfd *irqfd;
int idx;
resampler = container_of(kian,
@@ -76,11 +84,7 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
resampler->notifier.gsi, 0, false);
idx = srcu_read_lock(&kvm->irq_srcu);
-
- list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
- srcu_read_lock_held(&kvm->irq_srcu))
- eventfd_signal(irqfd->resamplefd, 1);
-
+ irqfd_resampler_notify(resampler);
srcu_read_unlock(&kvm->irq_srcu, idx);
}
@@ -648,6 +652,31 @@ void kvm_irq_routing_update(struct kvm *kvm)
spin_unlock_irq(&kvm->irqfds.lock);
}
+bool kvm_notify_irqfd_resampler(struct kvm *kvm,
+ unsigned int irqchip,
+ unsigned int pin)
+{
+ struct kvm_kernel_irqfd_resampler *resampler;
+ int gsi, idx;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1) {
+ list_for_each_entry_srcu(resampler,
+ &kvm->irqfds.resampler_list, link,
+ srcu_read_lock_held(&kvm->irq_srcu)) {
+ if (resampler->notifier.gsi == gsi) {
+ irqfd_resampler_notify(resampler);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return true;
+ }
+ }
+ }
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ return false;
+}
+
/*
* create a host-wide workqueue for issuing deferred shutdown requests
* aggregated from all vm* instances. We need our own isolated