2 Copyright(c) 2015-2017 Netronome Systems, Inc. All rights reserved.
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11 * Redistributions in binary form must reproduce the above copyright
12 notice, this list of conditions and the following disclaimer in
13 the documentation and/or other materials provided with the
15 * Neither the name of Intel Corporation nor the names of its
16 contributors may be used to endorse or promote products derived
17 from this software without specific prior written permission.
19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 NFP poll mode driver library
32 ============================
34 Netronome's sixth generation of flow processors pack 216 programmable
35 cores and over 100 hardware accelerators that uniquely combine packet,
36 flow, security and content processing in a single device that scales
39 This document explains how to use DPDK with the Netronome Poll Mode
40 Driver (PMD) supporting Netronome's Network Flow Processor 6xxx
41 (NFP-6xxx) and Netronome's Flow Processor 4xxx (NFP-4xxx).
43 NFP is a SRIOV capable device and the PMD driver supports the physical
44 function (PF) and the virtual functions (VFs).
49 Before using the Netronome's DPDK PMD some NFP configuration,
50 which is not related to DPDK, is required. The system requires
51 installation of **Netronome's BSP (Board Support Package)** along
52 with a specific NFP firmware application. Netronome's NSP ABI
53 version should be 0.20 or higher.
55 If you have a NFP device you should already have the code and
56 documentation for this configuration. Contact
57 **support@netronome.com** to obtain the latest available firmware.
59 The NFP Linux netdev kernel driver for VFs has been a part of the
60 vanilla kernel since kernel version 4.5, and support for the PF
61 since kernel version 4.11. Support for older kernels can be obtained
63 **https://github.com/Netronome/nfp-drv-kmods** along with the build
66 NFP PMD needs to be used along with UIO ``igb_uio`` or VFIO (``vfio-pci``)
72 Netronome's PMD code is provided in the **drivers/net/nfp** directory.
73 Although NFP PMD has NetronomeĀ“s BSP dependencies, it is possible to
74 compile it along with other DPDK PMDs even if no BSP was installed previously.
75 Of course, a DPDK app will require such a BSP installed for using the
76 NFP PMD, along with a specific NFP firmware application.
78 Default PMD configuration is at the **common_linux configuration** file:
80 - **CONFIG_RTE_LIBRTE_NFP_PMD=y**
82 Once the DPDK is built all the DPDK apps and examples include support for
86 Driver compilation and testing
87 ------------------------------
89 Refer to the document :ref:`compiling and testing a PMD for a NIC <pmd_build_and_test>`
95 NFP PMD supports using the NFP PF as another DPDK port, but it does not
96 have any functionality for controlling VFs. In fact, it is not possible to use
97 the PMD with the VFs if the PF is being used by DPDK, that is, with the NFP PF
98 bound to ``igb_uio`` or ``vfio-pci`` kernel drivers. Future DPDK versions will
99 have a PMD able to work with the PF and VFs at the same time and with the PF
100 implementing VF management along with other PF-only functionalities/offloads.
102 The PMD PF has extra work to do which will delay the DPDK app initialization
103 like uploading the firmware and configure the Link state properly when starting or
104 stopping a PF port. Since DPDK 18.05 the firmware upload happens when
105 a PF is initialized, which was not always true with older DPDK versions.
107 Depending on the Netronome product installed in the system, firmware files
108 should be available under ``/lib/firmware/netronome``. DPDK PMD supporting the
109 PF looks for a firmware file in this order:
111 1) First try to find a firmware image specific for this device using the
114 serial-00-15-4d-12-20-65-10-ff.nffw
116 2) Then try the PCI name:
118 pci-0000:04:00.0.nffw
120 3) Finally try the card type and media:
122 nic_AMDA0099-0001_2x25.nffw
124 Netronome's software packages install firmware files under ``/lib/firmware/netronome``
125 to support all the Netronome's SmartNICs and different firmware applications.
126 This is usually done using file names based on SmartNIC type and media and with a
127 directory per firmware application. Options 1 and 2 for firmware filenames allow
128 more than one SmartNIC, same type of SmartNIC or different ones, and to upload a
129 different firmware to each SmartNIC.
135 Some NFP cards support several physical ports with just one single PCI device.
136 The DPDK core is designed with a 1:1 relationship between PCI devices and DPDK
137 ports, so NFP PMD PF support requires handling the multiport case specifically.
138 During NFP PF initialization, the PMD will extract the information about the
139 number of PF ports from the firmware and will create as many DPDK ports as
142 Because the unusual relationship between a single PCI device and several DPDK
143 ports, there are some limitations when using more than one PF DPDK port: there
144 is no support for RX interrupts and it is not possible either to use those PF
145 ports with the device hotplug functionality.
148 PF multiprocess support
149 -----------------------
151 Due to how the driver needs to access the NFP through a CPP interface, which implies
152 to use specific registers inside the chip, the number of secondary processes with PF
153 ports is limited to only one.
155 This limitation will be solved in future versions but having basic multiprocess support
156 is important for allowing development and debugging through the PF using a secondary
157 process which will create a CPP bridge for user space tools accessing the NFP.
163 #. **Enable SR-IOV on the NFP device:** The current NFP PMD supports the PF and
164 the VFs on a NFP device. However, it is not possible to work with both at the
165 same time because the VFs require the PF being bound to the NFP PF Linux
166 netdev driver. Make sure you are working with a kernel with NFP PF support or
167 get the drivers from the above Github repository and follow the instructions
168 for building and installing it.
170 VFs need to be enabled before they can be used with the PMD.
171 Before enabling the VFs it is useful to obtain information about the
172 current NFP PCI device detected by the system:
174 .. code-block:: console
178 Now, for example, configure two virtual functions on a NFP-6xxx device
179 whose PCI system identity is "0000:03:00.0":
181 .. code-block:: console
183 echo 2 > /sys/bus/pci/devices/0000:03:00.0/sriov_numvfs
185 The result of this command may be shown using lspci again:
187 .. code-block:: console
191 Two new PCI devices should appear in the output of the above command. The
192 -k option shows the device driver, if any, that devices are bound to.
193 Depending on the modules loaded at this point the new PCI devices may be
194 bound to nfp_netvf driver.