2 Copyright(c) 2015-2016 Intel Corporation. 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 FM10K Poll Mode Driver
32 ======================
34 The FM10K poll mode driver library provides support for the Intel FM10000
35 (FM10K) family of 40GbE/100GbE adapters.
37 FTAG Based Forwarding of FM10K
38 ------------------------------
40 FTAG Based Forwarding is a unique feature of FM10K. The FM10K family of NICs
41 support the addition of a Fabric Tag (FTAG) to carry special information.
42 The FTAG is placed at the beginning of the frame, it contains information
43 such as where the packet comes from and goes, and the vlan tag. In FTAG based
44 forwarding mode, the switch logic forwards packets according to glort (global
45 resource tag) information, rather than the mac and vlan table. Currently this
46 feature works only on PF.
48 To enable this feature, the user should pass a devargs parameter to the eal
49 like "-w 84:00.0,enable_ftag=1", and the application should make sure an
50 appropriate FTAG is inserted for every frame on TX side.
55 Vector PMD (vPMD) uses IntelĀ® SIMD instructions to optimize packet I/O.
56 It improves load/store bandwidth efficiency of L1 data cache by using a wider
57 SSE/AVX ''register (1)''.
58 The wider register gives space to hold multiple packet buffers so as to save
59 on the number of instructions when bulk processing packets.
61 There is no change to the PMD API. The RX/TX handlers are the only two entries for
62 vPMD packet I/O. They are transparently registered at runtime RX/TX execution
63 if all required conditions are met.
65 1. To date, only an SSE version of FM10K vPMD is available.
66 To ensure that vPMD is in the binary code, set
67 ``CONFIG_RTE_LIBRTE_FM10K_INC_VECTOR=y`` in the configure file.
69 Some constraints apply as pre-conditions for specific optimizations on bulk
70 packet transfers. The following sections explain RX and TX constraints in the
78 Prerequisites and Pre-conditions
79 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
81 For Vector RX it is assumed that the number of descriptor rings will be a power
82 of 2. With this pre-condition, the ring pointer can easily scroll back to the
83 head after hitting the tail without a conditional check. In addition Vector RX
84 can use this assumption to do a bit mask using ``ring_size - 1``.
87 Features not Supported by Vector RX PMD
88 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
90 Some features are not supported when trying to increase the throughput in
101 Other features are supported using optional MACRO configuration. They include:
107 To enable via ``RX_OLFLAGS`` use ``RTE_LIBRTE_FM10K_RX_OLFLAGS_ENABLE=y``.
109 To guarantee the constraint, the following configuration flags in ``dev_conf.rxmode``
118 * ``fdir_conf->mode``
124 As vPMD is focused on high throughput, it processes 4 packets at a time. So it assumes
125 that the RX burst should be greater than 4 packets per burst. It returns zero if using
126 ``nb_pkt`` < 4 in the receive handler. If ``nb_pkt`` is not a multiple of 4, a
127 floor alignment will be applied.
133 Features not Supported by TX Vector PMD
134 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
136 TX vPMD only works when ``txq_flags`` is set to ``FM10K_SIMPLE_TX_FLAG``.
137 This means that it does not support TX multi-segment, VLAN offload or TX csum
138 offload. The following MACROs are used for these three features:
140 * ``ETH_TXQ_FLAGS_NOMULTSEGS``
142 * ``ETH_TXQ_FLAGS_NOVLANOFFL``
144 * ``ETH_TXQ_FLAGS_NOXSUMSCTP``
146 * ``ETH_TXQ_FLAGS_NOXSUMUDP``
148 * ``ETH_TXQ_FLAGS_NOXSUMTCP``
157 The Intel FM10000 family of NICs integrate a hardware switch and multiple host
158 interfaces. The FM10000 PMD driver only manages host interfaces. For the
159 switch component another switch driver has to be loaded prior to to the
160 FM10000 PMD driver. The switch driver can be acquired from Intel support.
161 Only Testpoint is validated with DPDK, the latest version that has been
162 validated with DPDK is 4.1.6.
167 The FM10000 family of NICs strip the CRC for every packets coming into the
168 host interface. So, CRC will be stripped even when the
169 ``rxmode.hw_strip_crc`` member is set to 0 in ``struct rte_eth_conf``.
172 Maximum packet length
173 ~~~~~~~~~~~~~~~~~~~~~
175 The FM10000 family of NICS support a maximum of a 15K jumbo frame. The value
176 is fixed and cannot be changed. So, even when the ``rxmode.max_rx_pkt_len``
177 member of ``struct rte_eth_conf`` is set to a value lower than 15364, frames
178 up to 15364 bytes can still reach the host interface.
180 Statistic Polling Frequency
181 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
183 The FM10000 NICs expose a set of statistics via the PCI BARs. These statistics
184 are read from the hardware registers when ``rte_eth_stats_get()`` or
185 ``rte_eth_xstats_get()`` is called. The packet counting registers are 32 bits
186 while the byte counting registers are 48 bits. As a result, the statistics must
187 be polled regularly in order to ensure the consistency of the returned reads.
189 Given the PCIe Gen3 x8, about 50Gbps of traffic can occur. With 64 byte packets
190 this gives almost 100 million packets/second, causing 32 bit integer overflow
191 after approx 40 seconds. To ensure these overflows are detected and accounted
192 for in the statistics, it is necessary to read statistic regularly. It is
193 suggested to read stats every 20 seconds, which will ensure the statistics
200 The FM10000 family of NICS need one separate interrupt for mailbox. So only
201 drivers which support multiple interrupt vectors e.g. vfio-pci can work
202 for fm10k interrupt mode.