[PATCHv3 2/2] kvm: set affinity hint for assigned device msi

[Michael S. Tsirkin]

To forward an interrupt to a vcpu that runs on
a host cpu different from the current one,
we need an ipi which likely will cost us as much
as delivering the interrupt directly to that cpu would.

Set irq affinity hint to point there, irq balancer
can then take this into accound and balance
interrupts accordingly.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
 virt/kvm/assigned-dev.c |    6 +++++-
 virt/kvm/irq_comm.c     |   25 +++++++++++++++++++++++--
 2 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 950a25f..cc4bb7a 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -146,9 +146,12 @@ static void deassign_host_irq(struct kvm *kvm,
 		for (i = 0; i < assigned_dev->entries_nr; i++)
 			disable_irq(assigned_dev->host_msix_entries[i].vector);
 
-		for (i = 0; i < assigned_dev->entries_nr; i++)
+		for (i = 0; i < assigned_dev->entries_nr; i++) {
+			u32 vector = assigned_dev->host_msix_entries[i].vector;
+			irq_set_affinity_hint(vector, NULL);
 			free_irq(assigned_dev->host_msix_entries[i].vector,
 				 assigned_dev);
+		}
 
 		assigned_dev->entries_nr = 0;
 		kfree(assigned_dev->host_msix_entries);
@@ -158,6 +161,7 @@ static void deassign_host_irq(struct kvm *kvm,
 		/* Deal with MSI and INTx */
 		disable_irq(assigned_dev->host_irq);
 
+		irq_set_affinity_hint(assigned_dev->host_irq, NULL);
 		free_irq(assigned_dev->host_irq, assigned_dev);
 
 		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index ac8b629..ba892df 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -22,6 +22,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
+#include <linux/interrupt.h>
 #include <trace/events/kvm.h>
 
 #include <asm/msidef.h>
@@ -80,11 +81,23 @@ inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
 #endif
 }
 
+static void kvm_vcpu_host_irq_hint(struct kvm_vcpu *vcpu, int host_irq)
+{
+	const struct cpumask *mask;
+	/* raw_smp_processor_id() is ok here: if we get preempted we can get a
+	 * wrong value but we don't mind much. */
+	if (host_irq >= 0 && unlikely(vcpu->cpu != raw_smp_processor_id())) {
+		mask = get_cpu_mask(vcpu->cpu);
+		irq_set_affinity_hint(host_irq, mask);
+	}
+}
+
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, int host_irq)
 {
 	int i, r = -1;
-	struct kvm_vcpu *vcpu, *lowest = NULL;
+	int matches = 0;
+	struct kvm_vcpu *vcpu, *lowest = NULL, *uninitialized_var(match);
 
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_is_dm_lowest_prio(irq))
@@ -98,10 +111,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 					irq->dest_id, irq->dest_mode))
 			continue;
 
+		++matches;
+
 		if (!kvm_is_dm_lowest_prio(irq)) {
 			if (r < 0)
 				r = 0;
 			r += kvm_apic_set_irq(vcpu, irq);
+			match = vcpu;
 		} else if (kvm_lapic_enabled(vcpu)) {
 			if (!lowest)
 				lowest = vcpu;
@@ -110,8 +126,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		}
 	}
 
-	if (lowest)
+	if (lowest) {
 		r = kvm_apic_set_irq(lowest, irq);
+		match = lowest;
+	}
+
+	if (matches == 1)
+		kvm_vcpu_host_irq_hint(match, host_irq);
 
 	return r;
 }
-- 
1.7.8.2.325.g247f9
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/