From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jan Kiszka Subject: Re: [Qemu-devel] KVM: Windows 64-bit troubles with user space irqchip Date: Thu, 03 Feb 2011 11:11:23 +0100 Message-ID: <4D4A7F4B.6050406@siemens.com> References: <4D496A8D.90000@siemens.com> <4D496BC5.10807@redhat.com> <4D496D77.2010405@siemens.com> <4D496FA6.8070301@siemens.com> <4D49738D.7080404@redhat.com> <4D4979BD.6080900@siemens.com> <20110202154611.GR14984@redhat.com> <4D497DAB.7010901@siemens.com> <4D4A64F2.8010309@redhat.com> <4D4A7629.1010506@siemens.com> <20110203100407.GA2449@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Avi Kivity , Gleb Natapov , kvm , qemu-devel To: Marcelo Tosatti Return-path: Received: from david.siemens.de ([192.35.17.14]:33777 "EHLO david.siemens.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756048Ab1BCKLj (ORCPT ); Thu, 3 Feb 2011 05:11:39 -0500 In-Reply-To: <20110203100407.GA2449@amt.cnet> Sender: kvm-owner@vger.kernel.org List-ID: On 2011-02-03 11:04, Marcelo Tosatti wrote: > On Thu, Feb 03, 2011 at 10:32:25AM +0100, Jan Kiszka wrote: >> On 2011-02-03 09:18, Avi Kivity wrote: >>> On 02/02/2011 05:52 PM, Jan Kiszka wrote: >>>>>> >>>>> If there is no problem in the logic of this commit (and I do not see >>>>> one yet) then we somewhere miss kicking vcpu when interrupt, that should be >>>>> handled, arrives? >>>> >>>> I'm not yet confident about the logic of the kernel patch: mov to cr8 is >>>> serializing. If the guest raises the tpr and then signals this with a >>>> succeeding, non vm-exiting instruction to the other vcpus, one of those >>>> could inject an interrupt with a higher priority than the previous tpr, >>>> but a lower one than current tpr. QEMU user space would accept this >>>> interrupt - and would likely surprise the guest. Do I miss something? >>> >>> apic_get_interrupt() is only called from the vcpu thread, so it should >>> see a correct tpr. >>> >>> The only difference I can see with the patch is that we may issue a >>> spurious cpu_interrupt(). But that shouldn't do anything bad, should it? >> >> I tested this yesterday, and it doesn't confuse Windows. It actually >> receives quite a few spurious IRQs in normal operation, w/ or w/o the >> kernel's tpr optimization. > > http://www.mail-archive.com/kvm@vger.kernel.org/msg41681.html Don't get the scenario yet: We do not inject (or set isr) over the context of apic_set_irq caller. > > tpr of a vcpu should always be inspected in vcpu context, instead of > iothread context? Maybe this is true for the in-kernel model, but I don't see the issue (anymore) for the way user space works. Jan -- Siemens AG, Corporate Technology, CT T DE IT 1 Corporate Competence Center Embedded Linux From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from [140.186.70.92] (port=36878 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Pkw9x-0006bh-BC for qemu-devel@nongnu.org; Thu, 03 Feb 2011 05:11:30 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Pkw9v-0001s3-VB for qemu-devel@nongnu.org; Thu, 03 Feb 2011 05:11:29 -0500 Received: from david.siemens.de ([192.35.17.14]:31207) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Pkw9v-0001rk-LV for qemu-devel@nongnu.org; Thu, 03 Feb 2011 05:11:27 -0500 Message-ID: <4D4A7F4B.6050406@siemens.com> Date: Thu, 03 Feb 2011 11:11:23 +0100 From: Jan Kiszka MIME-Version: 1.0 Subject: Re: [Qemu-devel] KVM: Windows 64-bit troubles with user space irqchip References: <4D496A8D.90000@siemens.com> <4D496BC5.10807@redhat.com> <4D496D77.2010405@siemens.com> <4D496FA6.8070301@siemens.com> <4D49738D.7080404@redhat.com> <4D4979BD.6080900@siemens.com> <20110202154611.GR14984@redhat.com> <4D497DAB.7010901@siemens.com> <4D4A64F2.8010309@redhat.com> <4D4A7629.1010506@siemens.com> <20110203100407.GA2449@amt.cnet> In-Reply-To: <20110203100407.GA2449@amt.cnet> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Marcelo Tosatti Cc: qemu-devel , Avi Kivity , Gleb Natapov , kvm On 2011-02-03 11:04, Marcelo Tosatti wrote: > On Thu, Feb 03, 2011 at 10:32:25AM +0100, Jan Kiszka wrote: >> On 2011-02-03 09:18, Avi Kivity wrote: >>> On 02/02/2011 05:52 PM, Jan Kiszka wrote: >>>>>> >>>>> If there is no problem in the logic of this commit (and I do not see >>>>> one yet) then we somewhere miss kicking vcpu when interrupt, that should be >>>>> handled, arrives? >>>> >>>> I'm not yet confident about the logic of the kernel patch: mov to cr8 is >>>> serializing. If the guest raises the tpr and then signals this with a >>>> succeeding, non vm-exiting instruction to the other vcpus, one of those >>>> could inject an interrupt with a higher priority than the previous tpr, >>>> but a lower one than current tpr. QEMU user space would accept this >>>> interrupt - and would likely surprise the guest. Do I miss something? >>> >>> apic_get_interrupt() is only called from the vcpu thread, so it should >>> see a correct tpr. >>> >>> The only difference I can see with the patch is that we may issue a >>> spurious cpu_interrupt(). But that shouldn't do anything bad, should it? >> >> I tested this yesterday, and it doesn't confuse Windows. It actually >> receives quite a few spurious IRQs in normal operation, w/ or w/o the >> kernel's tpr optimization. > > http://www.mail-archive.com/kvm@vger.kernel.org/msg41681.html Don't get the scenario yet: We do not inject (or set isr) over the context of apic_set_irq caller. > > tpr of a vcpu should always be inspected in vcpu context, instead of > iothread context? Maybe this is true for the in-kernel model, but I don't see the issue (anymore) for the way user space works. Jan -- Siemens AG, Corporate Technology, CT T DE IT 1 Corporate Competence Center Embedded Linux