From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:44776) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aMZw3-000485-3M for qemu-devel@nongnu.org; Fri, 22 Jan 2016 06:31:24 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1aMZvz-0006PU-Sj for qemu-devel@nongnu.org; Fri, 22 Jan 2016 06:31:23 -0500 Received: from mx2.parallels.com ([199.115.105.18]:53103) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aMZvz-0006PJ-NC for qemu-devel@nongnu.org; Fri, 22 Jan 2016 06:31:19 -0500 References: <1450949580-25759-1-git-send-email-asmetanin@virtuozzo.com> <56A1FF8F.3050701@redhat.com> <56A20131.8090102@virtuozzo.com> <56A20C30.4020608@redhat.com> From: Andrey Smetanin Message-ID: <56A212F9.4030800@virtuozzo.com> Date: Fri, 22 Jan 2016 14:31:05 +0300 MIME-Version: 1.0 In-Reply-To: <56A20C30.4020608@redhat.com> Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH v1] kvm/x86: Hyper-V tsc page setup Reply-To: asmetanin@virtuozzo.com List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini , kvm@vger.kernel.org Cc: Gleb Natapov , "Denis V. Lunev" , Roman Kagan , qemu-devel@nongnu.org On 01/22/2016 02:02 PM, Paolo Bonzini wrote: > > > On 22/01/2016 11:15, Andrey Smetanin wrote: >>> >>> - unless KVM can use a master clock, it is incorrect to set up the TSC >>> page this way; the sequence needs to be 0xFFFFFFFF in that case >> 0xFFFFFFFF is not an invalid value for tsc page, >> see https://lkml.org/lkml/2015/11/2/655 > > oh, I see now. > >>> - writing the TSC page must be done while all VCPUs are stopped, because >>> the TSC page doesn't provide the possibility for the guest to retry in >>> the middle of an update (like seqcount in Linux doess) >> I think Windows guest gives tsc page address at boot time and protects >> against other vcpu's tsc page access. > > Sometimes the TSC is detected to be unstable and Linux switches to > another clocksource. At least in that case you can get a write to the > TSC page while the guest is running. Sorry, now I got it, you mean host TSC is unstable and we should mark guest tsc page invalid. Now I understand please ignore my prev. message. > > In that case it would be enough to write a zero to tsc_sequence, which > _can_ be done atomically while the guest is running. However, KVM > already has a mechanism to stop all VCPUs (KVM_REQ_MASTERCLOCK_UPDATE) > so we might as well use it. > > Paolo >