Commit 9c8fd1ba authored Feb 06, 2015 by Paolo Bonzini

KVM: x86: optimize delivery of TSC deadline timer interrupt

The newly-added tracepoint shows the following results on
the tscdeadline_latency test:

qemu-kvm-8387 [002] 6425.558974: kvm_vcpu_wakeup: poll time 10407 ns
qemu-kvm-8387 [002] 6425.558984: kvm_vcpu_wakeup: poll time 0 ns
qemu-kvm-8387 [002] 6425.561242: kvm_vcpu_wakeup: poll time 10477 ns
qemu-kvm-8387 [002] 6425.561251: kvm_vcpu_wakeup: poll time 0 ns

and so on. This is because we need to go through kvm_vcpu_block again
after the timer IRQ is injected. Avoid it by polling once before
entering kvm_vcpu_block.

On my machine (Xeon E5 Sandy Bridge) this removes about 500 cycles (7%)
from the latency of the TSC deadline timer.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

parent 362c698f

arch/x86/kvm/x86.c

+7 −6

Original line number	Original line	Diff line number	Diff line
	@@ -6406,12 +6406,13 @@ out:

	static inline int vcpu_block(struct kvm kvm, struct kvm_vcpu vcpu)		static inline int vcpu_block(struct kvm kvm, struct kvm_vcpu vcpu)
	{		{
			if (!kvm_arch_vcpu_runnable(vcpu)) {
	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
	kvm_vcpu_block(vcpu);		kvm_vcpu_block(vcpu);
	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);

	if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))		if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
	return 1;		return 1;
			}

	kvm_apic_accept_events(vcpu);		kvm_apic_accept_events(vcpu);
	switch(vcpu->arch.mp_state) {		switch(vcpu->arch.mp_state) {

Admin message