From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753916AbdFWL77 (ORCPT ); Fri, 23 Jun 2017 07:59:59 -0400 Received: from mail-pf0-f193.google.com ([209.85.192.193]:35313 "EHLO mail-pf0-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751189AbdFWL75 (ORCPT ); Fri, 23 Jun 2017 07:59:57 -0400 From: Wanpeng Li X-Google-Original-From: Wanpeng Li To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org Cc: Paolo Bonzini , =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= , Wanpeng Li Subject: [PATCH v2] KVM: LAPIC: Fix lapic timer injection delay Date: Fri, 23 Jun 2017 04:59:50 -0700 Message-Id: <1498219190-6457-1-git-send-email-wanpeng.li@hotmail.com> X-Mailer: git-send-email 2.7.4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Wanpeng Li Linux as a guest will prevent to program the next event to the clock event device when the event is in the past. However, it is not guaranteed by all the guests, the guest like kvm-unit-tests/apic.flat will write current tsc value visible in guest to MSR_IA32_TSCDEADLINE, lapic timer which is emulated by vmx preemption timer will program the absolute target tsc value to vmcs preemption timer field w/ delta == 0, then plays a vmentry and an upcoming vmx preemption timer fire vmexit dance, the lapic timer injection is delayed for this duration. Actually the lapic timer which is emulated by hrtimer can handle this correctly. This patch fixes it by firing the lapic timer and injecting a timer interrupt immediately during the next vmentry if guest programs an expired timer to the emulated timer device. This saves ~300 cycles on the tsc_deadline_timer test of apic.flat. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li --- arch/x86/kvm/lapic.c | 7 ++++++- arch/x86/kvm/vmx.c | 3 +++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d24c874..08cf73d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1504,12 +1504,17 @@ static void cancel_hv_timer(struct kvm_lapic *apic) static bool start_hv_timer(struct kvm_lapic *apic) { u64 tscdeadline = apic->lapic_timer.tscdeadline; + int ret = 0; if ((atomic_read(&apic->lapic_timer.pending) && !apic_lvtt_period(apic)) || - kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { + (ret = kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline))) { if (apic->lapic_timer.hv_timer_in_use) cancel_hv_timer(apic); + if (ret == 1) { + apic_timer_expired(apic); + return true; + } } else { apic->lapic_timer.hv_timer_in_use = true; hrtimer_cancel(&apic->lapic_timer.timer); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2e906cf..2008e9b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11149,6 +11149,9 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl); u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; + if (delta_tsc == 0) + return 1; + /* Convert to host delta tsc if tsc scaling is enabled */ if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && u64_shl_div_u64(delta_tsc, -- 2.7.4