From: Wanpeng Li <wanpengli@xxxxxxxxxxx>
The target vCPUs are in runnable state after vcpu_kick and suitable
as a yield target. This patch implements the sched yield hypercall.
17% performance increase of ebizzy benchmark can be observed in an
over-subscribe environment. (w/ kvm-pv-tlb disabled, testing TLB flush
call-function IPI-many since call-function is not easy to be trigged
by userspace workload).
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpengli@xxxxxxxxxxx>
---
arch/x86/kvm/x86.c | 26 ++++++++++++++++++++++++++
1 file changed, 26 insertions(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e7e57de..f73af3b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7172,6 +7172,28 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
}
+static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
+{
+ struct kvm_vcpu *target;
+ struct kvm_apic_map *map;
+
+ rcu_read_lock();
+ map = rcu_dereference(kvm->arch.apic_map);
+
+ if (unlikely(!map))
+ goto out;
+
+ if (map->phys_map[dest_id]->vcpu) {
+ target = map->phys_map[dest_id]->vcpu;
+ rcu_read_unlock();
+ kvm_vcpu_yield_to(target);
+ }
+
+out:
+ if (!target)
+ rcu_read_unlock();
+}
+
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
@@ -7218,6 +7240,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
case KVM_HC_SEND_IPI:
ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
break;
+ case KVM_HC_SCHED_YIELD:
+ kvm_sched_yield(vcpu->kvm, a0);
+ ret = 0;
+ break;
default:
ret = -KVM_ENOSYS;
break;
--
2.7.4
