1 .. SPDX-License-Identifier: BSD-3-Clause
3 Copyright 2019 Netcope Technologies
5 NFB poll mode driver library
6 =================================
8 The NFB poll mode driver library implements support for the Netcope
9 FPGA Boards (**NFB-40G2, NFB-100G2, NFB-200G2QL**) and Silicom **FB2CGG3** card,
10 FPGA-based programmable NICs. The NFB PMD uses interface provided by the libnfb
11 library to communicate with these cards over the nfb layer.
13 More information about the
14 `NFB cards <http://www.netcope.com/en/products/fpga-boards>`_
16 (`Netcope Development Kit <http://www.netcope.com/en/products/fpga-development-kit>`_)
17 can be found on the `Netcope Technologies website <http://www.netcope.com/>`_.
21 This driver has external dependencies.
22 Therefore it is disabled in default configuration files.
23 It can be enabled by setting ``CONFIG_RTE_LIBRTE_NFB_PMD=y``
28 Currently the driver is supported only on x86_64 architectures.
29 Only x86_64 versions of the external libraries are provided.
34 This PMD requires kernel modules which are responsible for initialization and
35 allocation of resources needed for nfb layer function.
36 Communication between PMD and kernel modules is mediated by libnfb library.
37 These kernel modules and library are not part of DPDK and must be installed
42 The library provides API for initialization of nfb transfers, receiving and
43 transmitting data segments.
49 Kernel modules manage initialization of hardware, allocation and
50 sharing of resources for user space applications.
52 Dependencies can be found here:
53 `Netcope common <https://www.netcope.com/en/company/community-support/dpdk-libsze2#NFB>`_.
55 Versions of the packages
56 ~~~~~~~~~~~~~~~~~~~~~~~~
58 The minimum version of the provided packages:
65 These configuration options can be modified before compilation in the
68 * ``CONFIG_RTE_LIBRTE_NFB_PMD`` default value: **n**
70 Value **y** enables compilation of nfb PMD.
75 The PMD supports hardware timestamps of frame receipt on physical network interface. In order to use
76 the timestamps, the hardware timestamping unit must be enabled (follow the documentation of the NFB
77 products) and the device argument `timestamp=1` must be used.
79 .. code-block:: console
81 $RTE_TARGET/app/testpmd -w b3:00.0,timestamp=1 <other EAL params> -- <testpmd params>
83 When the timestamps are enabled with the *devarg*, a timestamp validity flag is set in the MBUFs
84 containing received frames and timestamp is inserted into the `rte_mbuf` struct.
86 The timestamp is an `uint64_t` field. Its lower 32 bits represent *seconds* portion of the timestamp
87 (number of seconds elapsed since 1.1.1970 00:00:00 UTC) and its higher 32 bits represent
88 *nanosecond* portion of the timestamp (number of nanoseconds elapsed since the beginning of the
89 second in the *seconds* portion.
93 ----------------------
95 Kernel modules have to be loaded before running the DPDK application.
100 The NFB cards are multi-port multi-queue cards, where (generally) data from any
101 Ethernet port may be sent to any queue.
102 They are represented in DPDK as a single port.
104 NFB-200G2QL card employs an add-on cable which allows to connect it to two
105 physical PCI-E slots at the same time (see the diagram below).
106 This is done to allow 200 Gbps of traffic to be transferred through the PCI-E
107 bus (note that a single PCI-E 3.0 x16 slot provides only 125 Gbps theoretical
110 Although each slot may be connected to a different CPU and therefore to a different
111 NUMA node, the card is represented as a single port in DPDK. To work with data
112 from the individual queues on the right NUMA node, connection of NUMA nodes on
113 first and last queue (each NUMA node has half of the queues) need to be checked.
115 .. figure:: img/szedata2_nfb200g_architecture.*
118 NFB-200G2QL high-level diagram
123 Driver is usable only on Linux architecture, namely on CentOS.
125 Since a card is always represented as a single port, but can be connected to two
126 NUMA nodes, there is need for manual check where master/slave is connected.
131 Read packets from 0. and 1. receive queue and write them to 0. and 1.
134 .. code-block:: console
136 $RTE_TARGET/app/testpmd -l 0-3 -n 2 \
137 -- --port-topology=chained --rxq=2 --txq=2 --nb-cores=2 -i -a
141 .. code-block:: console
144 EAL: PCI device 0000:06:00.0 on NUMA socket -1
145 EAL: probe driver: 1b26:c1c1 net_nfb
146 PMD: Initializing NFB device (0000:06:00.0)
147 PMD: Available DMA queues RX: 8 TX: 8
148 PMD: NFB device (0000:06:00.0) successfully initialized
149 Interactive-mode selected
151 Configuring Port 0 (socket 0)
152 Port 0: 00:11:17:00:00:00
153 Checking link statuses...
154 Port 0 Link Up - speed 10000 Mbps - full-duplex
156 Start automatic packet forwarding
157 io packet forwarding - CRC stripping disabled - packets/burst=32
158 nb forwarding cores=2 - nb forwarding ports=1
159 RX queues=2 - RX desc=128 - RX free threshold=0
160 RX threshold registers: pthresh=0 hthresh=0 wthresh=0
161 TX queues=2 - TX desc=512 - TX free threshold=0
162 TX threshold registers: pthresh=0 hthresh=0 wthresh=0
163 TX RS bit threshold=0 - TXQ flags=0x0