From patchwork Tue Dec 8 12:47:37 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shannon Zhao X-Patchwork-Id: 7796981 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 [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 5BF0B9F39B for ; Tue, 8 Dec 2015 12:49:32 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 62EC520462 for ; Tue, 8 Dec 2015 12:49:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 41DFA2045A for ; Tue, 8 Dec 2015 12:49:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964972AbbLHMtO (ORCPT ); Tue, 8 Dec 2015 07:49:14 -0500 Received: from szxga01-in.huawei.com ([58.251.152.64]:10936 "EHLO szxga01-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964943AbbLHMtM (ORCPT ); Tue, 8 Dec 2015 07:49:12 -0500 Received: from 172.24.1.50 (EHLO SZXEML429-HUB.china.huawei.com) ([172.24.1.50]) by szxrg01-dlp.huawei.com (MOS 4.3.7-GA FastPath queued) with ESMTP id DAM76589; Tue, 08 Dec 2015 20:48:27 +0800 (CST) Received: from HGHY1Z002260041.china.huawei.com (10.177.16.142) by SZXEML429-HUB.china.huawei.com (10.82.67.184) with Microsoft SMTP Server id 14.3.235.1; Tue, 8 Dec 2015 20:48:20 +0800 From: Shannon Zhao To: , , CC: , , , , , , , , , Subject: [PATCH v6 18/21] KVM: ARM64: Add PMU overflow interrupt routing Date: Tue, 8 Dec 2015 20:47:37 +0800 Message-ID: <1449578860-15808-19-git-send-email-zhaoshenglong@huawei.com> X-Mailer: git-send-email 1.9.0.msysgit.0 In-Reply-To: <1449578860-15808-1-git-send-email-zhaoshenglong@huawei.com> References: <1449578860-15808-1-git-send-email-zhaoshenglong@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.177.16.142] X-CFilter-Loop: Reflected X-Mirapoint-Virus-RAPID-Raw: score=unknown(0), refid=str=0001.0A090205.5666D19C.0120, ss=1, re=0.000, recu=0.000, reip=0.000, cl=1, cld=1, fgs=0, ip=0.0.0.0, so=2013-06-18 04:22:30, dmn=2013-03-21 17:37:32 X-Mirapoint-Loop-Id: 684573df254db5c23ff95462ea3ec84b 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=unavailable 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 From: Shannon Zhao When calling perf_event_create_kernel_counter to create perf_event, assign a overflow handler. Then when perf event overflows, call kvm_vcpu_kick() to sync the interrupt. Signed-off-by: Shannon Zhao --- arch/arm/kvm/arm.c | 2 ++ include/kvm/arm_pmu.h | 2 ++ virt/kvm/arm/pmu.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 55 insertions(+), 1 deletion(-) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index e06fd29..cd696ef 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -28,6 +28,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include "trace.h" @@ -569,6 +570,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * non-preemptible context. */ preempt_disable(); + kvm_pmu_flush_hwstate(vcpu); kvm_timer_flush_hwstate(vcpu); kvm_vgic_flush_hwstate(vcpu); diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index a131f76..c4041008 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -38,6 +38,7 @@ struct kvm_pmu { }; #ifdef CONFIG_KVM_ARM_PMU +void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu); u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u32 select_idx); void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u32 val); void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u32 val, bool all_enable); @@ -48,6 +49,7 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u32 data, u32 select_idx); void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u32 val); #else +void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {} u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u32 select_idx) { return 0; diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c index 9b9c706..ff182d6 100644 --- a/virt/kvm/arm/pmu.c +++ b/virt/kvm/arm/pmu.c @@ -21,6 +21,7 @@ #include #include #include +#include /** * kvm_pmu_get_counter_value - get PMU counter value @@ -90,6 +91,54 @@ static void kvm_pmu_stop_counter(struct kvm_pmc *pmc) } /** + * kvm_pmu_flush_hwstate - flush pmu state to cpu + * @vcpu: The vcpu pointer + * + * Inject virtual PMU IRQ if IRQ is pending for this cpu. + */ +void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + u32 overflow; + + if (pmu->irq_num == -1) + return; + + if (!vcpu_mode_is_32bit(vcpu)) { + if (!(vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMCR_E)) + return; + + overflow = vcpu_sys_reg(vcpu, PMCNTENSET_EL0) + & vcpu_sys_reg(vcpu, PMINTENSET_EL1) + & vcpu_sys_reg(vcpu, PMOVSSET_EL0); + } else { + if (!(vcpu_cp15(vcpu, c9_PMCR) & ARMV8_PMCR_E)) + return; + + overflow = vcpu_cp15(vcpu, c9_PMCNTENSET) + & vcpu_cp15(vcpu, c9_PMINTENSET) + & vcpu_cp15(vcpu, c9_PMOVSSET); + } + + kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, pmu->irq_num, + overflow ? 1 : 0); +} + +/** + * When perf event overflows, call kvm_pmu_overflow_set to set overflow status. + */ +static void kvm_pmu_perf_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + int idx = pmc->idx; + + kvm_pmu_overflow_set(vcpu, BIT(idx)); +} + +/** * kvm_pmu_enable_counter - enable selected PMU counter * @vcpu: The vcpu pointer * @val: the value guest writes to PMCNTENSET register @@ -341,7 +390,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u32 data, /* The initial sample period (overflow count) of an event. */ attr.sample_period = (-counter) & pmc->bitmask; - event = perf_event_create_kernel_counter(&attr, -1, current, NULL, pmc); + event = perf_event_create_kernel_counter(&attr, -1, current, + kvm_pmu_perf_overflow, pmc); if (IS_ERR(event)) { printk_once("kvm: pmu event creation failed %ld\n", PTR_ERR(event));