From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:36798) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZKTEQ-0000Ba-0Z for qemu-devel@nongnu.org; Wed, 29 Jul 2015 11:25:25 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZKTEM-0001ZG-PP for qemu-devel@nongnu.org; Wed, 29 Jul 2015 11:25:21 -0400 Received: from mail-ob0-x234.google.com ([2607:f8b0:4003:c01::234]:36300) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZKTEM-0001XV-Kv for qemu-devel@nongnu.org; Wed, 29 Jul 2015 11:25:18 -0400 Received: by obnw1 with SMTP id w1so9655374obn.3 for ; Wed, 29 Jul 2015 08:25:17 -0700 (PDT) From: Don Slutz References: <1435102773-3498-1-git-send-email-Don.Slutz@Gmail.com> <1435102773-3498-9-git-send-email-Don.Slutz@Gmail.com> <20150701082204-mutt-send-email-mst@redhat.com> <5596893C.7020700@Gmail.com> <5596931B.90306@redhat.com> <20150705083719-mutt-send-email-mst@redhat.com> Message-ID: <55B8F058.6060408@Gmail.com> Date: Wed, 29 Jul 2015 11:25:12 -0400 MIME-Version: 1.0 In-Reply-To: <20150705083719-mutt-send-email-mst@redhat.com> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH v8 8/8] vmport: Add VMware all ring hack List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Michael S. Tsirkin" , Paolo Bonzini Cc: qemu-devel@nongnu.org, Markus Armbruster , Don Slutz , Luiz Capitulino , Anthony Liguori , =?UTF-8?Q?Andreas_F=c3=a4rber?= , Richard Henderson On 7/5/2015 2:40 AM, Michael S. Tsirkin wrote: > On Fri, Jul 03, 2015 at 03:50:19PM +0200, Paolo Bonzini wrote: >> >> On 03/07/2015 15:08, Don Slutz wrote: >>>> Creating it at the pc level and propagating makes code >>>> messy but I'd go along with it if it made sense from >>>> user's point of view, but it does not seem to make sense: >>>> to me this looks more like a CPU feature than a machine property. >>>> Or the property of the vmport rpc device that you created. >>> Well this is not a clear area. It does look more like a CPU feature. I >>> went with a machine feature because that is where "vmport" currently is. >> I think it should be a vmport property. >> >> It would be cleaner to implement it using the MemTxAttrs mechanism, but >> for KVM I'm afraid it would be too slow (and the slowness would affect >> all I/O accesses, not just vmport ones, unless really ugly hacks are done). >> >> Paolo > Can it ever be implemented for kvm? I couldn't think of a clean way to do it. > I do not know of a clean way. For Xen I need to enable #GP fault reporting and add code to check in/out to the magic VMware port. I would assume that some thing similar would be needed in kvm. Hope this helps. -Don Slutz