From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id 99F9E530A for ; Tue, 25 Nov 2014 15:35:23 +0100 (CET) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga102.jf.intel.com with ESMTP; 25 Nov 2014 06:43:50 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.07,455,1413270000"; d="scan'208";a="613773523" Received: from pgsmsx108.gar.corp.intel.com ([10.221.44.103]) by orsmga001.jf.intel.com with ESMTP; 25 Nov 2014 06:46:13 -0800 Received: from shsmsx151.ccr.corp.intel.com (10.239.6.50) by PGSMSX108.gar.corp.intel.com (10.221.44.103) with Microsoft SMTP Server (TLS) id 14.3.195.1; Tue, 25 Nov 2014 22:46:11 +0800 Received: from shsmsx104.ccr.corp.intel.com ([169.254.5.182]) by SHSMSX151.ccr.corp.intel.com ([169.254.3.86]) with mapi id 14.03.0195.001; Tue, 25 Nov 2014 22:46:10 +0800 From: "Zhou, Danny" To: "Liang, Cunming" , "Richardson, Bruce" , Neil Horman Thread-Topic: [dpdk-dev] [RFC PATCH 0/6] DPDK support to bifurcated driver Thread-Index: AQHQCLnU5FCMVbS0qkK44I+J1nYJ1Zxw3yQAgAAB3oCAAALnAIAAhrog Date: Tue, 25 Nov 2014 14:46:10 +0000 Message-ID: References: <1416924682-24170-1-git-send-email-cunming.liang@intel.com> <20141125142316.GD23352@hmsreliant.think-freely.org> <20141125142956.GA6672@bricha3-MOBL3> In-Reply-To: Accept-Language: zh-CN, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "dev@dpdk.org" Subject: Re: [dpdk-dev] [RFC PATCH 0/6] DPDK support to bifurcated driver 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: Tue, 25 Nov 2014 14:35:25 -0000 > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Liang, Cunming > Sent: Tuesday, November 25, 2014 10:40 PM > To: Richardson, Bruce; Neil Horman > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [RFC PATCH 0/6] DPDK support to bifurcated driver >=20 >=20 >=20 > > -----Original Message----- > > From: Richardson, Bruce > > Sent: Tuesday, November 25, 2014 10:30 PM > > To: Neil Horman > > Cc: Liang, Cunming; dev@dpdk.org > > Subject: Re: [dpdk-dev] [RFC PATCH 0/6] DPDK support to bifurcated driv= er > > > > On Tue, Nov 25, 2014 at 09:23:16AM -0500, Neil Horman wrote: > > > On Tue, Nov 25, 2014 at 10:11:16PM +0800, Cunming Liang wrote: > > > > > > > > This is a RFC patch set to support "bifurcated driver" in DPDK. > > > > > > > > > > > > What is "bifurcated driver"? > > > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D > > > > > > > > The "bifurcated driver" stands for the kernel NIC driver that suppo= rts: > > > > > > > > 1. on-demand rx/tx queue pairs split-off and assignment to user spa= ce > > > > > > > > 2. direct NIC resource(e.g. rx/tx queue registers) access from user= space > > > > > > > > 3. distributing packets to kernel or user space rx queues by > > > > NIC's flow director according to the filter rules > > > > > > > > Here's the kernel patch set to support. > > > > http://comments.gmane.org/gmane.linux.network/333615 > > > > > > > > > > > > Usage scenario > > > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > > > > > > > > It's well accepted by industry to use DPDK to process fast path pac= kets in > > > > user space in a high performance fashion, meanwhile processing slow= path > > > > control packets in kernel space is still needed as those packets us= ually > > > > rely on in_kernel TCP/IP stacks and/or socket programming interface= . > > > > > > > > KNI(Kernel NIC Interface) mechanism in DPDK is designed to meet thi= s > > > > requirement, with below limitation: > > > > > > > > 1) Software classifies packets and distributes them to kernel via= DPDK > > > > software rings, at the cost of significant CPU cycles and memo= ry > > bandwidth. > > > > > > > > 2) Memory copy packets between kernel' socket buffer and mbuf bri= ngs > > > > significant negative performance impact to KNI performance. > > > > > > > > The bifurcated driver provides a alternative approach that not only= offloads > > > > flow classification and distribution to NIC but also support packet= s zero_copy. > > > > > > > > User can use standard ethtool to add filter rules to the NIC in ord= er to > > > > distribute specific flows to the queues only accessed by kernel dri= ver and > > > > stack, and add other rules to distribute packets to the queues assi= gned to > > > > user-space. > > > > > > > > For those rx/tx queue pairs that directly accessed from user space, > > > > DPDK takes over the packets rx/tx as well as corresponding DMA oper= ation > > > > for high performance packet I/O. > > > > > > > > > > > > What's the impact and change to DPDK > > > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > > > > > > > > DPDK usually binds PCIe NIC devices by leveraging kernel' user spac= e driver > > > > mechanism UIO or VFIO to map entire NIC' PCIe I/O space of NIC to u= ser > > space. > > > > The bifurcated driver PMD talks to a NIC interface using raw socket= APIs and > > > > only mmap() limited I/O space (e.g. certain 4K pages) for accessing= involved > > > > rx/tx queue pairs. So the impact and changes mainly comes with belo= w: > > > > > > > > - netdev > > > > DPDK needs to create a af_packet socket and bind it to a bifurc= ated > > netdev. > > > > The socket fd will be used to request 'queue pairs info', > > > > 'split/return queue pairs' and etc. The PCIe device ID, netdev = MAC > > address, > > > > numa info are also from the netdev response. > > > > > > > > - PCIe device scan and driver probe > > > > netdev provides the PCIe device ID information. Refer to the de= vice ID, > > > > the correct driver should be used. And for such netdev device, = the > > creation > > > > of PCIe device is no longer from scan but the on-demand assignm= ent. > > > > > > > > - PCIe BAR mapping > > > > "bifurcated driver" maps several pages for the queue pairs. > > > > Others BAR register space maps to a fake page. The BAR mapping = go > > through > > > > mmap on sockfd. Which is a little different from what UIO/VFIO = does. > > > > > > > > - PMD > > > > The PMD will no longer really initialize and configure NIC. > > > > Instead, it only takes care the queue pair setup, rx_burst and = tx_burst. > > > > > > > > The patch uses eal '--vdev' parameter to assign netdev iface name a= nd > > number of > > > > queue pairs. Here's a example about how to configure the bifurcated= driver > > and > > > > run DPDK testpmd with bifurcated PMD. > > > > > > > > 1. Set promisc mode > > > > > ifconfig eth0 promisc > > > > > > > > 2. Turn on fdir > > > > > ethtool -K eth0 ntuple on > > > > > > > > 3. Setup a flow director rule to distribute packets with source i= p > > > > 0.0.0.0 to rxq No.0 > > > > > ethtool -N eth0 flow-type udp4 src-ip 0.0.0.0 action 0 > > > > > > > > 4. Run testpmd on netdev 'eth0' with 1 queue pair. > > > > > ./x86_64-native-linuxapp-gcc/app/testpmd -c 0x3 -n 4 \ > > > > > --vdev=3Drte_bifurc,iface=3Deth0,qpairs=3D1 -- \ > > > > > -i --rxfreet=3D32 --txfreet=3D32 --txrst=3D32 > > > > Note: > > > > iface and qpairs arguments above specify the netdev interface n= ame and > > > > number of qpairs that user space request from the "bifurcated d= river" > > > > respectively. > > > > > > > > 5. Setup a flow director rule to distribute packets with source i= p > > > > 1.1.1.1 to rxq No.32. This needs to be done after testpmd star= ts. > > > > > ethtool -N eth0 flow-type udp4 src-ip 1.1.1.1 action 32 > > > > > > > > Below illustrates the detailed changes in this patch set. > > > > > > > > eal > > > > -------- > > > > The first two patches are all about the eal API declaration and Lin= ux version > > > > definition to support af_packet socket and verbs of bifurcated netd= ev. > > > > Those APIs include the verbs like open, bind, (un)map, split/rettur= n, > > map_umem. > > > > And other APIs like set_pci, get_ifinfo and get/put_devargs which h= elp to > > > > generate pci device from bifurcated netdev and get basic netdev inf= o. > > > > > > > > The third patch is used to allow probing driver on the PCIe VDEV cr= eated from > > > > a NIC interface driven by "bifurcated driver". It defines a new fla= g > > > > 'RTE_PCI_DRV_BIFURC' used for direct ring access PMD. > > > > > > > > librte_bifurc > > > > --------------- > > > > The library is used as a VDEV bus driver to scan '--vdev=3Drte_bifu= rc' VDEV > > > > from eal command-line. It generates the PCIe VDEV device ready for = further > > > > driver probe. It maintains the bifurcated device information includ= e sockfd, > > > > hwaddr, mtu, qpairs, iface_name. It's used for other direct ring ac= cess PMD > > > > to apply for bifurcated device info. > > > > > > > > direct ring access PMD > > > > ------------------------- > > > > The patch provides direct ring access PMD for ixgbe. Comparing to t= he normal > > > > PMD ixgbe, it uses 'RTE_PCI_DRV_BIFURC' flag during self registrati= on. > > > > It mostly reuses the existing PMD ops to avoid re-implementing ever= ything > > > > from scratch. And it also modifies the rx/tx_queue_setup to allow q= ueue > > > > setup from any queue offset. > > > > > > > > Supported NIC driver > > > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D > > > > > > > > The "bifurcated driver" kernel patch only supports "ixgbe" driver a= t the > > moment, > > > > so this RFC patch also provides "ixgbe" PMD via direct-mapped rings= as > > sample. > > > > The support for 40GE(i40e) will be added in the future. > > > > > > > > In addition, for those multi-queues enabled NIC with flow director = capability > > > > to do perform packet classification and distribution, there's no sp= ecial > > > > technical gap to provide bifurcated driver approach support. > > > > > > > > Limitation > > > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > > > > > > > > By using "bifurcated driver", user space only takes over the DMA op= eration. > > > > For those NIC configure setting, it's out of control from user spac= e PMD. > > > > All the NIC setting including add/del filter rules need to be done = by > > > > standard Linux network tools(e.g. ethtool). > > > > So the feature support really depend on how much are supported by e= thtool. > > > > > > > > > > > > Any questions, comments and feedback are welcome. > > > > > > > > > > > > -END- > > > > > > > > Signed-off-by: Cunming Liang > > > > Signed-off-by: Danny Zhou > > > > > > > > *** BLURB HERE *** > > > > > > > > Cunming Liang (6): > > > > eal: common direct ring access API > > > > eal: direct ring access support by linux af_packet > > > > pci: allow VDEV as pci device during device driver probe > > > > bifurc: add driver to scan bifurcated netdev > > > > ixgbe: rx/tx queue stop bug fix > > > > ixgbe: PMD for bifurc ixgbe net device > > > > > > > > config/common_linuxapp | 5 + > > > > lib/Makefile | 1 + > > > > lib/librte_bifurc/Makefile | 58 +++++ > > > > lib/librte_bifurc/rte_bifurc.c | 284 > > +++++++++++++++++++++ > > > > lib/librte_bifurc/rte_bifurc.h | 90 +++++++ > > > > lib/librte_eal/common/Makefile | 5 + > > > > lib/librte_eal/common/include/rte_pci.h | 4 + > > > > lib/librte_eal/common/include/rte_pci_bifurc.h | 186 +++++++++++++= + > > > > lib/librte_eal/linuxapp/eal/Makefile | 1 + > > > > lib/librte_eal/linuxapp/eal/eal_pci.c | 42 ++-- > > > > lib/librte_eal/linuxapp/eal/eal_pci_bifurc.c | 336 > > +++++++++++++++++++++++++ > > > > lib/librte_ether/rte_ethdev.c | 3 +- > > > > lib/librte_pmd_ixgbe/Makefile | 13 +- > > > > lib/librte_pmd_ixgbe/ixgbe_bifurcate.c | 303 > > ++++++++++++++++++++++ > > > > lib/librte_pmd_ixgbe/ixgbe_bifurcate.h | 57 +++++ > > > > lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 44 +++- > > > > lib/librte_pmd_ixgbe/ixgbe_rxtx.h | 10 + > > > > mk/rte.app.mk | 6 + > > > > 18 files changed, 1421 insertions(+), 27 deletions(-) > > > > create mode 100644 lib/librte_bifurc/Makefile > > > > create mode 100644 lib/librte_bifurc/rte_bifurc.c > > > > create mode 100644 lib/librte_bifurc/rte_bifurc.h > > > > create mode 100644 lib/librte_eal/common/include/rte_pci_bifurc.h > > > > create mode 100644 lib/librte_eal/linuxapp/eal/eal_pci_bifurc.c > > > > create mode 100644 lib/librte_pmd_ixgbe/ixgbe_bifurcate.c > > > > create mode 100644 lib/librte_pmd_ixgbe/ixgbe_bifurcate.h > > > > > > > > -- > > > > 1.8.1.4 > > > > > > > > > > > AIUI, the bifurcated driver hasn't yet been accepted upstream, has it= ? Given > > > that, I don't think its wise to pull this in yet ahead of the kernel = work, as > > > there may still be kernel side changes that the user space pmd will h= ave to > > > adapt to. > > > Neil > > > > > Hence the RFC nature of the patch, I believe. :-) Before the kernel par= t hits the > > main kernel tree we can at least discuss the overall direction to be ta= ken for > > this driver because it's significantly different that any other HW driv= er. > [Liang, Cunming] Yes, as Bruce said, that's the major purpose. > Another one is having this patch, people can run it together with kernel = patch. > It helps to understand the benefit and raise comments per user experience= . > > > > /Bruce Echo Bruce. Also the V2 DPDK RFC patchset will be submitted to dpdk.org to = support=20 V2 netdev kernel patchset with memory protection accordingly. Then people c= an play=20 with bifurcated driver and have a global view on how it works and what kind= s of perf.=20 can be achieved, instead of keep asking basic questions.