From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40036) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZkeMx-0005Uz-IC for qemu-devel@nongnu.org; Fri, 09 Oct 2015 16:34:24 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZkeMu-0006Ks-4y for qemu-devel@nongnu.org; Fri, 09 Oct 2015 16:34:23 -0400 Received: from mx1.redhat.com ([209.132.183.28]:40009) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Zka4E-0003Ae-Nb for qemu-devel@nongnu.org; Fri, 09 Oct 2015 11:58:46 -0400 References: <1444397988-20167-1-git-send-email-den@openvz.org> <1444397988-20167-2-git-send-email-den@openvz.org> <5617D259.8070101@redhat.com> <20151009155307.GU27239@rkaganb.sw.ru> From: Paolo Bonzini Message-ID: <5617E431.3070809@redhat.com> Date: Fri, 9 Oct 2015 17:58:41 +0200 MIME-Version: 1.0 In-Reply-To: <20151009155307.GU27239@rkaganb.sw.ru> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 1/2] kvm/x86: Hyper-V synthetic interrupt controller List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Roman Kagan , "Denis V. Lunev" , virtualization@lists.linux-foundation.org, qemu-devel@nongnu.org, Andrey Smetanin , Vitaly Kuznetsov , "K. Y. Srinivasan" , Gleb Natapov , Christian Borntraeger On 09/10/2015 17:53, Roman Kagan wrote: > > I really don't like this auto-EOI extension, but I guess that's the > > spec. :( If it wasn't for it, you could do everything very easily in > > userspace using Google's proposed MSR exit. > I guess you're right. We'd probably have to (ab)use MSI for SINT > delivery, though. Not really an issue, as MSI on x86 is really just the external entry point into the LAPIC, it makes sense that it be the external interface into KVM's virtualized LAPIC. Userspace split irqchip is (ab)using MSI routes the same way. > Anyway the need to implement auto-EOI rules that out. Yup. I look forward to reviewing v2! Paolo From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: [PATCH 1/2] kvm/x86: Hyper-V synthetic interrupt controller Date: Fri, 9 Oct 2015 17:58:41 +0200 Message-ID: <5617E431.3070809@redhat.com> References: <1444397988-20167-1-git-send-email-den@openvz.org> <1444397988-20167-2-git-send-email-den@openvz.org> <5617D259.8070101@redhat.com> <20151009155307.GU27239@rkaganb.sw.ru> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20151009155307.GU27239@rkaganb.sw.ru> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: Roman Kagan , "Denis V. Lunev" , virtualization@lists.linux-foundation.org, qemu-devel@nongnu.org, Andrey Smetanin , Vitaly Kuznetsov , "K. Y. Srinivasan" , Gleb Natapov , Christian Borntraeger List-Id: virtualization@lists.linuxfoundation.org On 09/10/2015 17:53, Roman Kagan wrote: > > I really don't like this auto-EOI extension, but I guess that's the > > spec. :( If it wasn't for it, you could do everything very easily in > > userspace using Google's proposed MSR exit. > I guess you're right. We'd probably have to (ab)use MSI for SINT > delivery, though. Not really an issue, as MSI on x86 is really just the external entry point into the LAPIC, it makes sense that it be the external interface into KVM's virtualized LAPIC. Userspace split irqchip is (ab)using MSI routes the same way. > Anyway the need to implement auto-EOI rules that out. Yup. I look forward to reviewing v2! Paolo