From: Roman Kagan Subject: Re: [PATCH] x86/kvm/hyper-v: avoid spurious pending stimer on vCPU init Date: Mon, 18 Mar 2019 09:35:27 +0000 Message-ID: <20190318093523.GA11912@rkaganb.sw.ru> References: <20190313171342.12814-1-vkuznets@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-2" Content-Transfer-Encoding: quoted-printable Cc: "kvm@vger.kernel.org" , Paolo Bonzini , =?iso-8859-2?Q?Radim_Kr=E8m=E1=F8?= , "linux-kernel@vger.kernel.org" To: Vitaly Kuznetsov Return-path: In-Reply-To: <20190313171342.12814-1-vkuznets@redhat.com> Content-Language: en-US Content-ID: Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Wed, Mar 13, 2019 at 06:13:42PM +0100, Vitaly Kuznetsov wrote: > When userspace initializes guest vCPUs it may want to zero all supported > MSRs including Hyper-V related ones including HV_X64_MSR_STIMERn_CONFIG/ > HV_X64_MSR_STIMERn_COUNT. With commit f3b138c5d89a ("kvm/x86: Update SynI= C > timers on guest entry only") we began doing stimer_mark_pending() > unconditionally on every config change. >=20 > The issue I'm observing manifests itself as following: > - Qemu writes 0 to STIMERn_{CONFIG,COUNT} MSRs and marks all stimers as > pending in stimer_pending_bitmap, arms KVM_REQ_HV_STIMER; > - kvm_hv_has_stimer_pending() starts returning true; > - kvm_vcpu_has_events() starts returning true; > - kvm_arch_vcpu_runnable() starts returning true; > - when kvm_arch_vcpu_ioctl_run() gets into > (vcpu->arch.mp_state =3D=3D KVM_MP_STATE_UNINITIALIZED) case: > - kvm_vcpu_block() gets in 'kvm_vcpu_check_block(vcpu) < 0' and returns > immediately, avoiding normal wait path; > - -EAGAIN is returned from kvm_arch_vcpu_ioctl_run() immediately forcin= g > userspace to retry. >=20 > So instead of normal wait path we get a busy loop on all secondary vCPUs > before they get INIT signal. This seems to be undesirable, especially giv= en > that this happens even when Hyper-V extensions are not used. >=20 > Generally, it seems to be pointless to mark an stimer as pending in > stimer_pending_bitmap and arm KVM_REQ_HV_STIMER as the only thing > kvm_hv_process_stimers() will do is clear the corresponding bit. We may > just not mark disabled timers as pending instead. >=20 > Fixes: f3b138c5d89a ("kvm/x86: Update SynIC timers on guest entry only") > Signed-off-by: Vitaly Kuznetsov > --- > arch/x86/kvm/hyperv.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) Reviewed-by: Roman Kagan