From: Yang Zhang <yang.z.zhang@xxxxxxxxx>
Current interrupt coalescing logci which only used by RTC has conflict
with Posted Interrupt.
This patch introduces a new mechinism to use eoi to track interrupt:
When delivering an interrupt to vcpu, the need_eoi set to number of
vcpu that received the interrupt. And decrease it when each vcpu writing
eoi. No subsequent RTC interrupt can deliver to vcpu until all vcpus
write eoi.
Signed-off-by: Yang Zhang <yang.z.zhang@xxxxxxxxx>
---
virt/kvm/ioapic.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 74 insertions(+), 2 deletions(-)
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 4ddaa07..35b3d8c 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -103,7 +103,8 @@ static void rtc_irq_restore(struct kvm_ioapic *ioapic)
kvm_for_each_vcpu(i, vcpu, ioapic->kvm) {
if (kvm_apic_pending_eoi(vcpu, vector)) {
need_eoi++;
- set_bit(vcpu->vcpu_id, ioapic->rtc_status.vcpu_map);
+ set_bit(vcpu->vcpu_id,
+ ioapic->rtc_status.expected_eoi_bitmap);
}
}
ioapic->rtc_status.need_eoi = need_eoi;
@@ -132,6 +133,50 @@ static void rtc_irq_get_dest_vcpu(struct kvm_ioapic *ioapic, int irq)
spin_unlock(&ioapic->lock);
}
+static void rtc_irq_set_eoi(struct kvm_ioapic *ioapic, int irq)
+{
+ union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
+
+ if (irq != 8)
+ return;
+
+ if (likely(!bitmap_empty(ioapic->rtc_status.vcpu_map, KVM_MAX_VCPUS))) {
+ if (entry->fields.delivery_mode == APIC_DM_LOWEST)
+ ioapic->rtc_status.need_eoi = 1;
+ else {
+ int weight;
+ weight = bitmap_weight(ioapic->rtc_status.vcpu_map,
+ sizeof(ioapic->rtc_status.vcpu_map));
+ ioapic->rtc_status.need_eoi = weight;
+ }
+ bitmap_copy(ioapic->rtc_status.expected_eoi_bitmap,
+ ioapic->rtc_status.vcpu_map, KVM_MAX_VCPUS);
+ }
+}
+
+static void rtc_irq_ack_eoi(struct kvm_vcpu *vcpu,
+ struct rtc_status *rtc_status, int irq)
+{
+ if (irq != 8)
+ return;
+
+ if (test_and_clear_bit(vcpu->vcpu_id, rtc_status->expected_eoi_bitmap))
+ --rtc_status->need_eoi;
+
+ WARN_ON(rtc_status->need_eoi < 0);
+}
+
+static bool rtc_irq_check(struct kvm_ioapic *ioapic, int irq)
+{
+ if (irq != 8)
+ return false;
+
+ if (ioapic->rtc_status.need_eoi > 0)
+ return true; /* coalesced */
+
+ return false;
+}
+
#else
static void rtc_irq_reset(struct kvm_ioapic *ioapic)
@@ -148,6 +193,22 @@ static void rtc_irq_get_dest_vcpu(struct kvm_ioapic *ioapic, int irq)
{
return;
}
+
+static void rtc_irq_set_eoi(struct kvm_ioapic *ioapic, int irq)
+{
+ return;
+}
+
+static void rtc_irq_ack_eoi(struct kvm_vcpu *vcpu,
+ struct rtc_status *rtc_status, int irq)
+{
+ return;
+}
+
+static bool rtc_irq_check(struct kvm_ioapic *ioapic, int irq)
+{
+ return false;
+}
#endif
static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
@@ -260,7 +321,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
&& ioapic->irr & (1 << index))
ioapic_service(ioapic, index);
+ spin_unlock(&ioapic->lock);
kvm_scan_ioapic_entry(ioapic->kvm);
+ spin_lock(&ioapic->lock);
break;
}
}
@@ -284,6 +347,8 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
irqe.level = 1;
irqe.shorthand = 0;
+ rtc_irq_set_eoi(ioapic, irq);
+
return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
}
@@ -308,6 +373,11 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
ret = 1;
} else {
int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+
+ if (rtc_irq_check(ioapic, irq)) {
+ ret = 0; /* coalesced */
+ goto out;
+ }
ioapic->irr |= mask;
if ((edge && old_irr != ioapic->irr) ||
(!edge && !entry.fields.remote_irr))
@@ -315,6 +385,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
else
ret = 0; /* report coalesced interrupt */
}
+out:
trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
spin_unlock(&ioapic->lock);
@@ -342,6 +413,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
if (ent->fields.vector != vector)
continue;
+ rtc_irq_ack_eoi(vcpu, &ioapic->rtc_status, i);
/*
* We are dropping lock while calling ack notifiers because ack
* notifier callbacks for assigned devices call into IOAPIC
@@ -562,7 +634,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
update_handled_vectors(ioapic);
rtc_irq_restore(ioapic);
- kvm_scan_ioapic_entry(kvm);
spin_unlock(&ioapic->lock);
+ kvm_scan_ioapic_entry(kvm);
return 0;
}
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
