From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 09/10] KVM: Enable MSI for device assignment Date: Tue, 04 Nov 2008 16:35:19 +0200 Message-ID: <49105DA7.3020204@redhat.com> References: <1225428647-27614-1-git-send-email-sheng@linux.intel.com> <1225428647-27614-10-git-send-email-sheng@linux.intel.com> <49103098.7020109@redhat.com> <20081104132543.GB18696@yukikaze> <49104F01.30604@redhat.com> <20081104135853.GC18696@yukikaze> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit To: Avi Kivity , Sheng Yang , kvm@vger.kernel.org Return-path: Received: from mx2.redhat.com ([66.187.237.31]:49422 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752238AbYKDOfY (ORCPT ); Tue, 4 Nov 2008 09:35:24 -0500 In-Reply-To: <20081104135853.GC18696@yukikaze> Sender: kvm-owner@vger.kernel.org List-ID: Sheng Yang wrote: >> In fact, it's not just for pci. We could msi-enable e1000 and get >> improved performance there as well. >> > > E1000? Don't understand... Sounds like INTx->MSI... > There are msi-capable e1000 cards. If we upgrade qemu's e1000 to support msi, and if the guest supports msi, it will be msi all the way. >>> But I guess what you means is only set >>> gsi can result in kvm_set_irq() deliver the MSI correctly. I think this can >>> be done. Associating gsi with guest_msi_addr and guest_msi_data in a linked >>> list, for gsi >= IOAPIC_PINS, >>> >> Let's say, (gsi >> 24) == 1. That gives us 16M potential MSIs. >> > > Confused... GSI become a bitmap? > A structure... struct gsi { u32 n : 24; u32 type : 8; // 0 -> classic gsi, 1 -> msi }; -- error compiling committee.c: too many arguments to function