KVM: X86: Bail out of direct yield in case of under-committed scenarios

In case of under-committed scenarios, vCPUs can be scheduled easily;
kvm_vcpu_yield_to adds extra overhead, and it is also common to see
when vcpu->ready is true but yield later failing due to p->state is
TASK_RUNNING.

Let's bail out in such scenarios by checking the length of current cpu
runqueue, which can be treated as a hint of under-committed instead of
guarantee of accuracy. 30%+ of directed-yield attempts can now avoid
the expensive lookups in kvm_sched_yield() in an under-committed scenario.

Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1621339235-11131-2-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b6bca61692912099fcc7eaa9ab8d49d512be67d..dfb7c320581fcbed892fd45e45a82ed5a416a6d0 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8360,6 +8360,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 
        vcpu->stat.directed_yield_attempted++;
 
+       if (single_task_running())
+               goto no_yield;
+
        rcu_read_lock();
        map = rcu_dereference(vcpu->kvm->arch.apic_map);