From patchwork Mon Jul 2 16:46:21 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marc Zyngier X-Patchwork-Id: 10502081 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id BE3F460284 for ; Mon, 2 Jul 2018 16:46:52 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id A9AFF28D4C for ; Mon, 2 Jul 2018 16:46:52 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 9BD5228D4E; Mon, 2 Jul 2018 16:46:52 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.9 required=2.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,MAILING_LIST_MULTI autolearn=unavailable version=3.3.1 Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 4531328D4C for ; Mon, 2 Jul 2018 16:46:52 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20170209; h=Sender: Content-Transfer-Encoding:Content-Type:MIME-Version:Cc:List-Subscribe: List-Help:List-Post:List-Archive:List-Unsubscribe:List-Id:Message-Id:Date: Subject:To:From:Reply-To:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:In-Reply-To: References:List-Owner; bh=0h9Q9Tqhdg2VbqVOqb3N2MRLe9yPz+mEwc55evGw0NY=; b=FPn bckLR64aVSEVSaEyrTEV0vKrKFCAwy02nQhNNZAudf1lotKGfLKFkNihPftA/cC/CCMzG6Z/Dyqt0 2RJRGjddrxZprdPcs6+dxpBE5KTNXH1RTBsGYIDLZWbcVNPpjG3dSC22l3BtwwOBqaZTMKZudxoB4 JRHLvGUgzZNfkbPhBGeYvnMW1drS/kSJJcnZCtNW4O5Hs7Ta112l1VJ07CSV+0tmU65RivFg4GBCN qH54iycE4Aw+wABaq8GG9pc5JFwXZMzVjva+NILsXbIPI6SehLRrs0Y1EBEmsiyPAdEmyzDhQX/d4 rijCSiXbLvmt9xzWVrklrKhBQ39WjLA==; Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.90_1 #2 (Red Hat Linux)) id 1fa1yS-0001tF-Hv; Mon, 02 Jul 2018 16:46:48 +0000 Received: from foss.arm.com ([217.140.101.70]) by bombadil.infradead.org with esmtp (Exim 4.90_1 #2 (Red Hat Linux)) id 1fa1yO-0001sf-WF for linux-arm-kernel@lists.infradead.org; Mon, 02 Jul 2018 16:46:46 +0000 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 6CE6C80D; Mon, 2 Jul 2018 09:46:34 -0700 (PDT) Received: from approximate.cambridge.arm.com (approximate.cambridge.arm.com [10.1.206.75]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 7FEBC3F5BA; Mon, 2 Jul 2018 09:46:33 -0700 (PDT) From: Marc Zyngier To: kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu, linux-arm-kernel@lists.infradead.org Subject: [RFC PATCH] KVM: arm/arm64: Enable adaptative WFE trapping Date: Mon, 2 Jul 2018 17:46:21 +0100 Message-Id: <20180702164621.9899-1-marc.zyngier@arm.com> X-Mailer: git-send-email 2.17.1 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20180702_094645_114391_44B72640 X-CRM114-Status: GOOD ( 13.20 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Christoffer Dall MIME-Version: 1.0 Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org X-Virus-Scanned: ClamAV using ClamSMTP Trapping blocking WFE is extremely beneficial in situations where the system is oversubscribed, as it allows another thread to run while being blocked. In a non-oversubscribed environment, this is the complete opposite, and trapping WFE is just unnecessary overhead. Let's only enable WFE trapping if the CPU has more than a single task to run (that is, more than just the vcpu thread). Signed-off-by: Marc Zyngier Reviewed-by: Christoffer Dall --- This small patchlet seem to have some interesting effects in my limited testing. Installing 100 concurrent Debian VMs results results in about 90 million WFE exits without this patch, and only 7.6 millions with it (TX1, 96 cores, 2 vcpu guests). I haven't measured any significant performance variation in that process. I'd welcome any benchmarking result from people with more interesting workloads than mine so that I could make my mind about it. arch/arm/include/asm/kvm_emulate.h | 10 ++++++++++ arch/arm64/include/asm/kvm_emulate.h | 10 ++++++++++ virt/kvm/arm/arm.c | 6 ++++++ 3 files changed, 26 insertions(+) diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 6493bd479ddc..b50fe8380868 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -107,6 +107,16 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr; } +static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr &= ~HCR_TWE; +} + +static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr |= HCR_TWE; +} + static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) { return 1; diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 1dab3a984608..a71e5af816a9 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -81,6 +81,16 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr_el2; } +static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr_el2 &= ~HCR_TWE; +} + +static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr_el2 |= HCR_TWE; +} + static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr) { vcpu->arch.vsesr_el2 = vsesr; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 04e554cae3a2..8e66b89a3db2 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -380,6 +381,11 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_timer_vcpu_load(vcpu); kvm_vcpu_load_sysregs(vcpu); kvm_arch_vcpu_load_fp(vcpu); + + if (single_task_running()) + vcpu_clear_wfe_traps(vcpu); + else + vcpu_set_wfe_traps(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)