Commit 9805cf03 authored by Wanpeng Li's avatar Wanpeng Li Committed by Paolo Bonzini
Browse files

KVM: LAPIC: Narrow the timer latency between wait_lapic_expire and world switch 



Let's treat lapic_timer_advance_ns automatic tuning logic as hypervisor
overhead, move it before wait_lapic_expire instead of between wait_lapic_expire
and the world switch, the wait duration should be calculated by the
up-to-date guest_tsc after the overhead of automatic tuning logic. This
patch reduces ~30+ cycles for kvm-unit-tests/tscdeadline-latency when testing
busy waits.

Signed-off-by: default avatarWanpeng Li <wanpengli@tencent.com>
Message-Id: <1621339235-11131-5-git-send-email-wanpengli@tencent.com>
Reviewed-by: default avatarSean Christopherson <seanjc@google.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent fb0f9479

arch/x86/kvm/lapic.c

+11 −3
Original line number Diff line number Diff line
@@ -1598,11 +1598,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) 
	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());

	apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline;



	if (lapic_timer_advance_dynamic) {

		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);

		/*

		 * If the timer fired early, reread the TSC to account for the

		 * overhead of the above adjustment to avoid waiting longer

		 * than is necessary.

		 */

		if (guest_tsc < tsc_deadline)

		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);

			guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());

	}



	if (lapic_timer_advance_dynamic)

		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);

	if (guest_tsc < tsc_deadline)

		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);

}



void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)