From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id 6B5DB5922 for ; Fri, 23 Sep 2016 12:34:16 +0200 (CEST) Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga103.fm.intel.com with ESMTP; 23 Sep 2016 03:34:15 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.30,381,1470726000"; d="scan'208";a="12541221" Received: from bricha3-mobl3.ger.corp.intel.com ([10.237.221.45]) by orsmga005.jf.intel.com with SMTP; 23 Sep 2016 03:34:12 -0700 Received: by (sSMTP sendmail emulation); Fri, 23 Sep 2016 11:34:12 +0025 Date: Fri, 23 Sep 2016 11:34:12 +0100 From: Bruce Richardson To: Thomas Monjalon Cc: "Iremonger, Bernard" , dev@dpdk.org, Jerin Jacob , "Shah, Rahul R" , "Lu, Wenzhuo" , azelezniak Message-ID: <20160923103411.GA59204@bricha3-MOBL3> References: <1471528125-26357-1-git-send-email-bernard.iremonger@intel.com> <3664576.rt1sgYQyhm@xps13> <20160923092048.GA58328@bricha3-MOBL3> <3936536.tPp6g5Daih@xps13> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3936536.tPp6g5Daih@xps13> Organization: Intel Research and =?iso-8859-1?Q?De=ACvel?= =?iso-8859-1?Q?opment?= Ireland Ltd. User-Agent: Mutt/1.5.23 (2014-03-12) Subject: Re: [dpdk-dev] [RFC PATCH v2 3/5] librte_ether: add API's for VF management X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Sep 2016 10:34:17 -0000 On Fri, Sep 23, 2016 at 11:36:21AM +0200, Thomas Monjalon wrote: > 2016-09-23 10:20, Bruce Richardson: > > On Thu, Sep 22, 2016 at 07:04:37PM +0200, Thomas Monjalon wrote: > > > 2016-09-15 16:46, Iremonger, Bernard: > > > > > > > Do we really need to expose VF specific functions here? > > > > > > > It can be generic(PF/VF) function indexed only through port_id. > > > > > > > (example: as rte_eth_dev_set_vlan_anti_spoof(uint8_t port_id, > > > > > > > uint8_t on)) For instance, In Thunderx PMD, We are not exposing a > > > > > > > separate port_id for PF. We only enumerate 0..N VFs as 0..N ethdev > > > > > > > port_id > > > > > > > > > > > > Our intention with this patch is to control the VF from the PF. > > > > > > > > > > > > The following librte_ether functions already work in a similar way: > > > > > > > > > > > > rte_eth_dev_set_vf_rxmode(uint8_t port_id, uint16_t vf, uint16_t > > > > > > rx_mode, uint8_t on) > > > > > > > > > > > > rte_eth_dev_set_vf_rx(uint8_t port_id, uint16_t vf, uint8_t on) > > > > > > > > > > > > rte_eth_dev_set_vf_tx(uint8_t port_id, uint16_t vf, uint8_t on) > > > > > > > > > > > > int rte_eth_set_vf_rate_limit(uint8_t port_id, uint16_t vf, uint16_t > > > > > > tx_rate, uint64_t q_msk) > > > > > > > > > > I have a bad feeling with these functions dedicated to VF from PF. > > > > > Are we sure there is no other way? > > > > > I mean we just need to know the VF with a port ID. > > > > > > > > When the VF is used in a VM the port ID of the VF is not visible to the PF. > > > > I don't think there is another way to do this. > > > > > > I don't understand why we could not assign a port id to the VF from the > > > host instead of having the couple PF port id / VF id. > > > Can we enumerate all the VFs associated to a PF? > > > Then can we allocate them a port id in the array rte_eth_devices? > > > > Hi Thomas, > > > > The VF is not a port visible to DPDK, though, so it shouldn't have a port id > > IMHO. DPDK can't actually do anything with it. > > You say the contrary below. > > > The PCI device for the VF is likely passed through to a different VM and being > > used there. Unfortunately, the VF still needs certain things done for it by the > > PF, so if the PF is under DPDK control, it needs to provide the functionality > > to assist the VF. > > Why not have a VF_from_PF driver which does the mailbox things? > So you can manage the VF from the PF with a simple port id. > It really seems to be the cleanest design to me. Just to confirm I am understanding your suggestion correctly: * for a normal app, eg. testpmd or l2fwd, things stay exactly as they are * for an app that wants to control VFs from PFs, then we provide a new ethdev driver, and a call in the PF to create an new instance of it e.g. rte_eth_vf_from_pf(pf_port_id, vf_number) * then to control the VF, you make regular rte_ethdev calls using the new ethdev port id you got from the vf_from_pf call. * it's up to that app to know what ports are regular ports that can do IO, and what ports are VF control ports, though we may add in an ethdev flag value somewhere to assist in this. Is that basically it? /Bruce