Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753010AbcLLOcC (ORCPT ); Mon, 12 Dec 2016 09:32:02 -0500 Received: from mailhub.sw.ru ([195.214.232.25]:26741 "EHLO relay.sw.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752810AbcLLOcA (ORCPT ); Mon, 12 Dec 2016 09:32:00 -0500 X-Greylist: delayed 1772 seconds by postgrey-1.27 at vger.kernel.org; Mon, 12 Dec 2016 09:31:59 EST From: Denis Plotnikov To: rkagan@virtuozzo.com, den@virtuozzo.com, pbonzini@redhat.com, rkrcmar@redhat.com Cc: svt-core@lists.sw.ru, kvm@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH v1] KVM: x86: avoid redundant REQ_EVENT Date: Mon, 12 Dec 2016 17:02:23 +0300 Message-Id: <20161212140223.277077-1-dplotnikov@virtuozzo.com> X-Mailer: git-send-email 2.10.1.352.g0cf3611 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4142 Lines: 120 When processing KVM_REQ_EVENT, apic_update_ppr is called which may set KVM_REQ_EVENT again if the recalculated value of PPR becomes smaller than the previous one. This results in cancelling the guest entry and reiterating in vcpu_enter_guest. However this is unnecessary because at this point KVM_REQ_EVENT is already being processed and there are no other changes in the lapic that may require full-fledged state recalculation. This situation is often hit on systems with TPR shadow, where the TPR can be updated by the guest without a vmexit, so that the first apic_update_ppr to notice it is exactly the one called while processing KVM_REQ_EVENT. To avoid it, introduce a parameter in apic_update_ppr allowing to suppress setting of KVM_REQ_EVENT, and use it on the paths called from KVM_REQ_EVENT processing. This microoptimization gives 10% performance increase on a synthetic test doing a lot of IPC in Windows using window messages. Reviewed-by: Roman Kagan Signed-off-by: Denis Plotnikov --- arch/x86/kvm/lapic.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 6f69340..b3025d8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -544,7 +544,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void apic_update_ppr(struct kvm_lapic *apic) +static void apic_update_ppr(struct kvm_lapic *apic, bool make_req) { u32 tpr, isrv, ppr, old_ppr; int isr; @@ -564,7 +564,7 @@ static void apic_update_ppr(struct kvm_lapic *apic) if (old_ppr != ppr) { kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr); - if (ppr < old_ppr) + if (make_req && ppr < old_ppr) kvm_make_request(KVM_REQ_EVENT, apic->vcpu); } } @@ -572,7 +572,7 @@ static void apic_update_ppr(struct kvm_lapic *apic) static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) { kvm_lapic_set_reg(apic, APIC_TASKPRI, tpr); - apic_update_ppr(apic); + apic_update_ppr(apic, true); } static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) @@ -1032,7 +1032,7 @@ static int apic_set_eoi(struct kvm_lapic *apic) return vector; apic_clear_isr(vector, apic); - apic_update_ppr(apic); + apic_update_ppr(apic, true); if (test_bit(vector, vcpu_to_synic(apic->vcpu)->vec_bitmap)) kvm_hv_synic_send_eoi(apic->vcpu, vector); @@ -1147,7 +1147,7 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) val = apic_get_tmcct(apic); break; case APIC_PROCPRI: - apic_update_ppr(apic); + apic_update_ppr(apic, true); val = kvm_lapic_get_reg(apic, offset); break; case APIC_TASKPRI: @@ -1841,7 +1841,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_lapic_set_base(vcpu, vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP); vcpu->arch.pv_eoi.msr_val = 0; - apic_update_ppr(apic); + apic_update_ppr(apic, true); vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; @@ -1964,7 +1964,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) if (!apic_enabled(apic)) return -1; - apic_update_ppr(apic); + apic_update_ppr(apic, false); highest_irr = apic_find_highest_irr(apic); if ((highest_irr == -1) || ((highest_irr & 0xF0) <= kvm_lapic_get_reg(apic, APIC_PROCPRI))) @@ -2013,12 +2013,12 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) */ apic_set_isr(vector, apic); - apic_update_ppr(apic); + apic_update_ppr(apic, true); apic_clear_irr(vector, apic); if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { apic_clear_isr(vector, apic); - apic_update_ppr(apic); + apic_update_ppr(apic, true); } return vector; @@ -2068,7 +2068,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); - apic_update_ppr(apic); + apic_update_ppr(apic, true); hrtimer_cancel(&apic->lapic_timer.timer); apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); -- 2.10.1.352.g0cf3611