2 Copyright 2015 6WIND S.A.
4 Redistribution and use in source and binary forms, with or without
5 modification, are permitted provided that the following conditions
8 * Redistributions of source code must retain the above copyright
9 notice, this list of conditions and the following disclaimer.
10 * Redistributions in binary form must reproduce the above copyright
11 notice, this list of conditions and the following disclaimer in
12 the documentation and/or other materials provided with the
14 * Neither the name of 6WIND S.A. nor the names of its
15 contributors may be used to endorse or promote products derived
16 from this software without specific prior written permission.
18 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
33 The MLX5 poll mode driver library (**librte_pmd_mlx5**) provides support for
34 **Mellanox ConnectX-4** and **Mellanox ConnectX-4 Lx** families of
35 10/25/40/50/100 Gb/s adapters as well as their virtual functions (VF) in
38 Information and documentation about these adapters can be found on the
39 `Mellanox website <http://www.mellanox.com>`__. Help is also provided by the
40 `Mellanox community <http://community.mellanox.com/welcome>`__.
42 There is also a `section dedicated to this poll mode driver
43 <http://www.mellanox.com/page/products_dyn?product_family=209&mtag=pmd_for_dpdk>`__.
47 Due to external dependencies, this driver is disabled by default. It must
48 be enabled manually by setting ``CONFIG_RTE_LIBRTE_MLX5_PMD=y`` and
51 Implementation details
52 ----------------------
54 Besides its dependency on libibverbs (that implies libmlx5 and associated
55 kernel support), librte_pmd_mlx5 relies heavily on system calls for control
56 operations such as querying/updating the MTU and flow control parameters.
58 For security reasons and robustness, this driver only deals with virtual
59 memory addresses. The way resources allocations are handled by the kernel
60 combined with hardware specifications that allow it to handle virtual memory
61 addresses directly ensure that DPDK applications cannot access random
62 physical memory (or memory that does not belong to the current process).
64 This capability allows the PMD to coexist with kernel network interfaces
65 which remain functional, although they stop receiving unicast packets as
66 long as they share the same MAC address.
68 Enabling librte_pmd_mlx5 causes DPDK applications to be linked against
74 - Multiple TX and RX queues.
75 - Support for scattered TX and RX frames.
76 - IPv4, IPv6, TCPv4, TCPv6, UDPv4 and UDPv6 RSS on any number of queues.
77 - Several RSS hash keys, one for each flow type.
78 - Configurable RETA table.
79 - Support for multiple MAC addresses.
83 - RX CRC stripping configuration.
85 - Multicast promiscuous mode.
86 - Hardware checksum offloads.
87 - Flow director (RTE_FDIR_MODE_PERFECT and RTE_FDIR_MODE_PERFECT_MAC_VLAN).
88 - Secondary process TX is supported.
89 - KVM and VMware ESX SR-IOV modes are supported.
94 - Inner RSS for VXLAN frames is not supported yet.
95 - Port statistics through software counters only.
96 - Hardware checksum offloads for VXLAN inner header are not supported yet.
97 - Secondary process RX is not supported.
105 These options can be modified in the ``.config`` file.
107 - ``CONFIG_RTE_LIBRTE_MLX5_PMD`` (default **n**)
109 Toggle compilation of librte_pmd_mlx5 itself.
111 - ``CONFIG_RTE_LIBRTE_MLX5_DEBUG`` (default **n**)
113 Toggle debugging code and stricter compilation flags. Enabling this option
114 adds additional run-time checks and debugging messages at the cost of
117 - ``CONFIG_RTE_LIBRTE_MLX5_MAX_INLINE`` (default **0**)
119 Amount of data to be inlined during TX operations. Improves latency.
120 Can improve PPS performance when PCI backpressure is detected and may be
121 useful for scenarios involving heavy traffic on many queues.
123 Since the additional software logic necessary to handle this mode can
124 lower performance when there is no backpressure, it is not enabled by
127 - ``CONFIG_RTE_LIBRTE_MLX5_TX_MP_CACHE`` (default **8**)
129 Maximum number of cached memory pools (MPs) per TX queue. Each MP from
130 which buffers are to be transmitted must be associated to memory regions
131 (MRs). This is a slow operation that must be cached.
133 This value is always 1 for RX queues since they use a single MP.
135 Environment variables
136 ~~~~~~~~~~~~~~~~~~~~~
138 - ``MLX5_ENABLE_CQE_COMPRESSION``
140 A nonzero value lets ConnectX-4 return smaller completion entries to
141 improve performance when PCI backpressure is detected. It is most useful
142 for scenarios involving heavy traffic on many queues.
144 Since the additional software logic necessary to handle this mode can
145 lower performance when there is no backpressure, it is not enabled by
148 - ``MLX5_PMD_ENABLE_PADDING``
150 Enables HW packet padding in PCI bus transactions.
152 When packet size is cache aligned and CRC stripping is enabled, 4 fewer
153 bytes are written to the PCI bus. Enabling padding makes such packets
156 In cases where PCI bandwidth is the bottleneck, padding can improve
159 This is disabled by default since this can also decrease performance for
160 unaligned packet sizes.
162 Run-time configuration
163 ~~~~~~~~~~~~~~~~~~~~~~
165 - librte_pmd_mlx5 brings kernel network interfaces up during initialization
166 because it is affected by their state. Forcing them down prevents packets
169 - **ethtool** operations on related kernel interfaces also affect the PMD.
174 This driver relies on external libraries and kernel drivers for resources
175 allocations and initialization. The following dependencies are not part of
176 DPDK and must be installed separately:
180 User space Verbs framework used by librte_pmd_mlx5. This library provides
181 a generic interface between the kernel and low-level user space drivers
184 It allows slow and privileged operations (context initialization, hardware
185 resources allocations) to be managed by the kernel and fast operations to
186 never leave user space.
190 Low-level user space driver library for Mellanox ConnectX-4 devices,
191 it is automatically loaded by libibverbs.
193 This library basically implements send/receive calls to the hardware
196 - **Kernel modules** (mlnx-ofed-kernel)
198 They provide the kernel-side Verbs API and low level device drivers that
199 manage actual hardware initialization and resources sharing with user
202 Unlike most other PMDs, these modules must remain loaded and bound to
205 - mlx5_core: hardware driver managing Mellanox ConnectX-4 devices and
206 related Ethernet kernel network devices.
207 - mlx5_ib: InifiniBand device driver.
208 - ib_uverbs: user space driver for Verbs (entry point for libibverbs).
210 - **Firmware update**
212 Mellanox OFED releases include firmware updates for ConnectX-4 adapters.
214 Because each release provides new features, these updates must be applied to
215 match the kernel modules and libraries they come with.
219 Both libraries are BSD and GPL licensed. Linux kernel modules are GPL
222 Currently supported by DPDK:
224 - Mellanox OFED **3.1-1.0.3**, **3.1-1.5.7.1** or **3.2-2.0.0.0** depending
227 The following features are supported with version **3.1-1.5.7.1** and
230 - IPv6, UPDv6, TCPv6 RSS.
231 - RX checksum offloads.
234 The following features are supported with version **3.2-2.0.0.0** and
240 - RX CRC stripping configuration.
242 - Minimum firmware version:
244 With MLNX_OFED **3.1-1.0.3**:
246 - ConnectX-4: **12.12.1240**
247 - ConnectX-4 Lx: **14.12.1100**
249 With MLNX_OFED **3.1-1.5.7.1**:
251 - ConnectX-4: **12.13.0144**
252 - ConnectX-4 Lx: **14.13.0144**
254 With MLNX_OFED **3.2-2.0.0.0**:
256 - ConnectX-4: **12.14.2036**
257 - ConnectX-4 Lx: **14.14.2036**
259 Getting Mellanox OFED
260 ~~~~~~~~~~~~~~~~~~~~~
262 While these libraries and kernel modules are available on OpenFabrics
263 Alliance's `website <https://www.openfabrics.org/>`__ and provided by package
264 managers on most distributions, this PMD requires Ethernet extensions that
265 may not be supported at the moment (this is a work in progress).
268 <http://www.mellanox.com/page/products_dyn?product_family=26&mtag=linux>`__
269 includes the necessary support and should be used in the meantime. For DPDK,
270 only libibverbs, libmlx5, mlnx-ofed-kernel packages and firmware updates are
271 required from that distribution.
275 Several versions of Mellanox OFED are available. Installing the version
276 this DPDK release was developed and tested against is strongly
277 recommended. Please check the `prerequisites`_.
282 Compared to librte_pmd_mlx4 that implements a single RSS configuration per
283 port, librte_pmd_mlx5 supports per-protocol RSS configuration.
285 Since ``testpmd`` defaults to IP RSS mode and there is currently no
286 command-line parameter to enable additional protocols (UDP and TCP as well
287 as IP), the following commands must be entered from its CLI to get the same
288 behavior as librte_pmd_mlx4:
290 .. code-block:: console
293 > port config all rss all
299 This section demonstrates how to launch **testpmd** with Mellanox ConnectX-4
300 devices managed by librte_pmd_mlx5.
302 #. Load the kernel modules:
304 .. code-block:: console
306 modprobe -a ib_uverbs mlx5_core mlx5_ib
308 Alternatively if MLNX_OFED is fully installed, the following script can
311 .. code-block:: console
313 /etc/init.d/openibd restart
317 User space I/O kernel modules (uio and igb_uio) are not used and do
318 not have to be loaded.
320 #. Make sure Ethernet interfaces are in working order and linked to kernel
321 verbs. Related sysfs entries should be present:
323 .. code-block:: console
325 ls -d /sys/class/net/*/device/infiniband_verbs/uverbs* | cut -d / -f 5
329 .. code-block:: console
336 #. Optionally, retrieve their PCI bus addresses for whitelisting:
338 .. code-block:: console
341 for intf in eth2 eth3 eth4 eth5;
343 (cd "/sys/class/net/${intf}/device/" && pwd -P);
346 sed -n 's,.*/\(.*\),-w \1,p'
350 .. code-block:: console
357 #. Request huge pages:
359 .. code-block:: console
361 echo 1024 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages/nr_hugepages
363 #. Start testpmd with basic parameters:
365 .. code-block:: console
367 testpmd -c 0xff00 -n 4 -w 05:00.0 -w 05:00.1 -w 06:00.0 -w 06:00.1 -- --rxq=2 --txq=2 -i
371 .. code-block:: console
374 EAL: PCI device 0000:05:00.0 on NUMA socket 0
375 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
376 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_0" (VF: false)
377 PMD: librte_pmd_mlx5: 1 port(s) detected
378 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:fe
379 EAL: PCI device 0000:05:00.1 on NUMA socket 0
380 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
381 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_1" (VF: false)
382 PMD: librte_pmd_mlx5: 1 port(s) detected
383 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:ff
384 EAL: PCI device 0000:06:00.0 on NUMA socket 0
385 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
386 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_2" (VF: false)
387 PMD: librte_pmd_mlx5: 1 port(s) detected
388 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:fa
389 EAL: PCI device 0000:06:00.1 on NUMA socket 0
390 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
391 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_3" (VF: false)
392 PMD: librte_pmd_mlx5: 1 port(s) detected
393 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:fb
394 Interactive-mode selected
395 Configuring Port 0 (socket 0)
396 PMD: librte_pmd_mlx5: 0x8cba80: TX queues number update: 0 -> 2
397 PMD: librte_pmd_mlx5: 0x8cba80: RX queues number update: 0 -> 2
398 Port 0: E4:1D:2D:E7:0C:FE
399 Configuring Port 1 (socket 0)
400 PMD: librte_pmd_mlx5: 0x8ccac8: TX queues number update: 0 -> 2
401 PMD: librte_pmd_mlx5: 0x8ccac8: RX queues number update: 0 -> 2
402 Port 1: E4:1D:2D:E7:0C:FF
403 Configuring Port 2 (socket 0)
404 PMD: librte_pmd_mlx5: 0x8cdb10: TX queues number update: 0 -> 2
405 PMD: librte_pmd_mlx5: 0x8cdb10: RX queues number update: 0 -> 2
406 Port 2: E4:1D:2D:E7:0C:FA
407 Configuring Port 3 (socket 0)
408 PMD: librte_pmd_mlx5: 0x8ceb58: TX queues number update: 0 -> 2
409 PMD: librte_pmd_mlx5: 0x8ceb58: RX queues number update: 0 -> 2
410 Port 3: E4:1D:2D:E7:0C:FB
411 Checking link statuses...
412 Port 0 Link Up - speed 40000 Mbps - full-duplex
413 Port 1 Link Up - speed 40000 Mbps - full-duplex
414 Port 2 Link Up - speed 10000 Mbps - full-duplex
415 Port 3 Link Up - speed 10000 Mbps - full-duplex