From patchwork Mon Jun 30 15:34:54 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Mihai Caraman X-Patchwork-Id: 4451171 Return-Path: X-Original-To: patchwork-kvm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 424A39F358 for ; Mon, 30 Jun 2014 15:50:56 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 189B720375 for ; Mon, 30 Jun 2014 15:50:55 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id ED3822021F for ; Mon, 30 Jun 2014 15:50:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754561AbaF3Puu (ORCPT ); Mon, 30 Jun 2014 11:50:50 -0400 Received: from mail-bn1blp0187.outbound.protection.outlook.com ([207.46.163.187]:46793 "EHLO na01-bn1-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754524AbaF3Pus (ORCPT ); Mon, 30 Jun 2014 11:50:48 -0400 Received: from BY2PR03CA036.namprd03.prod.outlook.com (10.242.234.157) by DM2PR03MB512.namprd03.prod.outlook.com (10.141.87.22) with Microsoft SMTP Server (TLS) id 15.0.974.11; Mon, 30 Jun 2014 15:35:08 +0000 Received: from BN1AFFO11FD030.protection.gbl (2a01:111:f400:7c10::160) by BY2PR03CA036.outlook.office365.com (2a01:111:e400:2c2c::29) with Microsoft SMTP Server (TLS) id 15.0.974.11 via Frontend Transport; Mon, 30 Jun 2014 15:35:08 +0000 Received: from az84smr01.freescale.net (192.88.158.2) by BN1AFFO11FD030.mail.protection.outlook.com (10.58.52.168) with Microsoft SMTP Server (TLS) id 15.0.969.12 via Frontend Transport; Mon, 30 Jun 2014 15:35:07 +0000 Received: from fsr-fed1764-012.ea.freescale.net (fsr-fed1764-012-010171073213.ea.freescale.net [10.171.73.213]) by az84smr01.freescale.net (8.14.3/8.14.0) with ESMTP id s5UFZ0Ng029673; Mon, 30 Jun 2014 08:35:05 -0700 From: Mihai Caraman To: CC: , , Mihai Caraman Subject: [PATCH 3/6 v2] KVM: PPC: Book3E: Increase FPU laziness Date: Mon, 30 Jun 2014 18:34:54 +0300 Message-ID: <1404142497-6430-4-git-send-email-mihai.caraman@freescale.com> X-Mailer: git-send-email 1.7.11.7 In-Reply-To: <1404142497-6430-1-git-send-email-mihai.caraman@freescale.com> References: <1404142497-6430-1-git-send-email-mihai.caraman@freescale.com> X-EOPAttributedMessage: 0 X-Forefront-Antispam-Report: CIP:192.88.158.2; CTRY:US; IPV:CAL; IPV:NLI; EFV:NLI; SFV:NSPM; SFS:(6009001)(199002)(189002)(19580395003)(44976005)(104166001)(6806004)(19580405001)(83322001)(68736004)(69596002)(102836001)(4396001)(26826002)(50226001)(77156001)(36756003)(62966002)(50466002)(77982001)(97736001)(99396002)(79102001)(48376002)(76482001)(21056001)(80022001)(81542001)(46102001)(81342001)(50986999)(47776003)(20776003)(64706001)(104016002)(95666004)(74502001)(105606002)(85306003)(92726001)(88136002)(89996001)(87936001)(92566001)(85852003)(76176999)(87286001)(93916002)(31966008)(74662001)(33646001)(2351001)(107046002)(84676001)(83072002)(86362001)(106466001)(229853001)(81156004)(32563001); DIR:OUT; SFP:; SCL:1; SRVR:DM2PR03MB512; H:az84smr01.freescale.net; FPR:; MLV:ovrnspm; PTR:InfoDomainNonexistent; MX:1; LANG:en; MIME-Version: 1.0 X-Microsoft-Antispam: BCL:0;PCL:0;RULEID: X-Forefront-PRVS: 0258E7CCD4 Received-SPF: Fail (: domain of freescale.com does not designate 192.88.158.2 as permitted sender) receiver=; client-ip=192.88.158.2; helo=az84smr01.freescale.net; Authentication-Results: spf=fail (sender IP is 192.88.158.2) smtp.mailfrom=mihai.caraman@freescale.com; X-OriginatorOrg: freescale.com Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Increase FPU laziness by calling kvmppc_load_guest_fp() just before returning to guest instead of each sched in. Without this improvement an interrupt may also claim floting point corrupting guest state. Signed-off-by: Mihai Caraman --- v2: - remove fpu_active - add descriptive comments arch/powerpc/kvm/booke.c | 43 ++++++++++++++++++++++++++++++++++++------- arch/powerpc/kvm/booke.h | 34 ---------------------------------- arch/powerpc/kvm/e500mc.c | 2 -- 3 files changed, 36 insertions(+), 43 deletions(-) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 80cd8df..4cc9b26 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -134,6 +134,40 @@ static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu) } #endif +/* + * Load up guest vcpu FP state if it's needed. + * It also set the MSR_FP in thread so that host know + * we're holding FPU, and then host can help to save + * guest vcpu FP state if other threads require to use FPU. + * This simulates an FP unavailable fault. + * + * It requires to be called with preemption disabled. + */ +static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PPC_FPU + if (!(current->thread.regs->msr & MSR_FP)) { + enable_kernel_fp(); + load_fp_state(&vcpu->arch.fp); + current->thread.fp_save_area = &vcpu->arch.fp; + current->thread.regs->msr |= MSR_FP; + } +#endif +} + +/* + * Save guest vcpu FP state into thread. + * It requires to be called with preemption disabled. + */ +static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PPC_FPU + if (current->thread.regs->msr & MSR_FP) + giveup_fpu(current); + current->thread.fp_save_area = NULL; +#endif +} + static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu) { #if defined(CONFIG_PPC_FPU) && !defined(CONFIG_KVM_BOOKE_HV) @@ -710,12 +744,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* * Since we can't trap on MSR_FP in GS-mode, we consider the guest - * as always using the FPU. Kernel usage of FP (via - * enable_kernel_fp()) in this thread must not occur while - * vcpu->fpu_active is set. + * as always using the FPU. */ - vcpu->fpu_active = 1; - kvmppc_load_guest_fp(vcpu); #endif @@ -739,8 +769,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) #ifdef CONFIG_PPC_FPU kvmppc_save_guest_fp(vcpu); - - vcpu->fpu_active = 0; #endif out: @@ -1220,6 +1248,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, else { /* interrupts now hard-disabled */ kvmppc_fix_ee_before_entry(); + kvmppc_load_guest_fp(vcpu); } } diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index f182b32..faad8af 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -123,40 +123,6 @@ extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val); -/* - * Load up guest vcpu FP state if it's needed. - * It also set the MSR_FP in thread so that host know - * we're holding FPU, and then host can help to save - * guest vcpu FP state if other threads require to use FPU. - * This simulates an FP unavailable fault. - * - * It requires to be called with preemption disabled. - */ -static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_PPC_FPU - if (vcpu->fpu_active && !(current->thread.regs->msr & MSR_FP)) { - enable_kernel_fp(); - load_fp_state(&vcpu->arch.fp); - current->thread.fp_save_area = &vcpu->arch.fp; - current->thread.regs->msr |= MSR_FP; - } -#endif -} - -/* - * Save guest vcpu FP state into thread. - * It requires to be called with preemption disabled. - */ -static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_PPC_FPU - if (vcpu->fpu_active && (current->thread.regs->msr & MSR_FP)) - giveup_fpu(current); - current->thread.fp_save_area = NULL; -#endif -} - static inline void kvmppc_clear_dbsr(void) { mtspr(SPRN_DBSR, mfspr(SPRN_DBSR)); diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 690499d..c60b653 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -145,8 +145,6 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) kvmppc_e500_tlbil_all(vcpu_e500); __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] = vcpu; } - - kvmppc_load_guest_fp(vcpu); } static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu)