From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37160) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1f6TLz-0006fi-OH for qemu-devel@nongnu.org; Wed, 11 Apr 2018 23:56:56 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1f6TLw-0001aj-MS for qemu-devel@nongnu.org; Wed, 11 Apr 2018 23:56:55 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:56672 helo=mx1.redhat.com) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1f6TLw-0001Zj-HG for qemu-devel@nongnu.org; Wed, 11 Apr 2018 23:56:52 -0400 References: <20180411072027.5656-1-tiwei.bie@intel.com> <20180411083853.qa6y6zevjpvamrdx@debian> <20180411195957-mutt-send-email-mst@kernel.org> <8babe3ef-b401-58ec-b6d4-2b4a7e528560@redhat.com> <20180412063708-mutt-send-email-mst@kernel.org> From: Jason Wang Message-ID: Date: Thu, 12 Apr 2018 11:56:37 +0800 MIME-Version: 1.0 In-Reply-To: <20180412063708-mutt-send-email-mst@kernel.org> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [RFC] vhost-user: introduce F_NEED_ALL_IOTLB protocol feature List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Michael S. Tsirkin" Cc: Tiwei Bie , dan.daly@intel.com, qemu-devel@nongnu.org, peterx@redhat.com, zhihong.wang@intel.com, cunming.liang@intel.com On 2018=E5=B9=B404=E6=9C=8812=E6=97=A5 11:37, Michael S. Tsirkin wrote: >>>>> Yeah, we are still using the existing IOTLB update messages >>>>> to send the IOTLB messages to backend. The only difference >>>>> is that, QEMU won't wait for the queries before sending the >>>>> IOTLB update messages. >>>> Yes, my question is not very clear. I mean why must need a new featu= re bit? >>>> It looks to me qemu code can work without this. >>>> >>>> Thanks >>> Generally we avoid adding new messages without a protocol feature bit= . >>> While careful analysis might sometimes prove it's not a strict >>> requirement, it's just overall a clean and robust approach. >>> >> Right but the looks like the patch does not introduce any new type of >> messages. >> >> Thanks > In this case remote needs to know that it will send these messages. > > -- MST Ok, if some backend does not expect qemu will send without any query=20 from itself, I agree we need a new bit. But it looks more like a workaround for buggy backend, at least vhost=20 kernel does not need to know about this. Thanks