2 Copyright 2012 6WIND S.A.
3 Copyright 2015 Mellanox
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 6WIND S.A. 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 MLX4 poll mode driver library
32 =============================
34 The MLX4 poll mode driver library (**librte_pmd_mlx4**) implements support
35 for **Mellanox ConnectX-3** and **Mellanox ConnectX-3 Pro** 10/40 Gbps adapters
36 as well as their virtual functions (VF) in SR-IOV context.
38 Information and documentation about this family of adapters can be found on
39 the `Mellanox website <http://www.mellanox.com>`_. Help is also provided by
40 the `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_MLX4_PMD=y`` and
51 Implementation details
52 ----------------------
54 Most Mellanox ConnectX-3 devices provide two ports but expose a single PCI
55 bus address, thus unlike most drivers, librte_pmd_mlx4 registers itself as a
56 PCI driver that allocates one Ethernet device per detected port.
58 For this reason, one cannot white/blacklist a single port without also
59 white/blacklisting the others on the same device.
61 Besides its dependency on libibverbs (that implies libmlx4 and associated
62 kernel support), librte_pmd_mlx4 relies heavily on system calls for control
63 operations such as querying/updating the MTU and flow control parameters.
65 For security reasons and robustness, this driver only deals with virtual
66 memory addresses. The way resources allocations are handled by the kernel
67 combined with hardware specifications that allow it to handle virtual memory
68 addresses directly ensure that DPDK applications cannot access random
69 physical memory (or memory that does not belong to the current process).
71 This capability allows the PMD to coexist with kernel network interfaces
72 which remain functional, although they stop receiving unicast packets as
73 long as they share the same MAC address.
75 Compiling librte_pmd_mlx4 causes DPDK to be linked against libibverbs.
83 These options can be modified in the ``.config`` file.
85 - ``CONFIG_RTE_LIBRTE_MLX4_PMD`` (default **n**)
87 Toggle compilation of librte_pmd_mlx4 itself.
89 - ``CONFIG_RTE_LIBRTE_MLX4_DLOPEN_DEPS`` (default **n**)
91 Build PMD with additional code to make it loadable without hard
92 dependencies on **libibverbs** nor **libmlx4**, which may not be installed
95 In this mode, their presence is still required for it to run properly,
96 however their absence won't prevent a DPDK application from starting (with
97 ``CONFIG_RTE_BUILD_SHARED_LIB`` disabled) and they won't show up as
98 missing with ``ldd(1)``.
100 It works by moving these dependencies to a purpose-built rdma-core "glue"
101 plug-in which must either be installed in a directory whose name is based
102 on ``CONFIG_RTE_EAL_PMD_PATH`` suffixed with ``-glue`` if set, or in a
103 standard location for the dynamic linker (e.g. ``/lib``) if left to the
104 default empty string (``""``).
106 This option has no performance impact.
108 - ``CONFIG_RTE_LIBRTE_MLX4_DEBUG`` (default **n**)
110 Toggle debugging code and stricter compilation flags. Enabling this option
111 adds additional run-time checks and debugging messages at the cost of
114 - ``CONFIG_RTE_LIBRTE_MLX4_TX_MP_CACHE`` (default **8**)
116 Maximum number of cached memory pools (MPs) per TX queue. Each MP from
117 which buffers are to be transmitted must be associated to memory regions
118 (MRs). This is a slow operation that must be cached.
120 This value is always 1 for RX queues since they use a single MP.
122 Environment variables
123 ~~~~~~~~~~~~~~~~~~~~~
127 A list of directories in which to search for the rdma-core "glue" plug-in,
128 separated by colons or semi-colons.
130 Only matters when compiled with ``CONFIG_RTE_LIBRTE_MLX4_DLOPEN_DEPS``
131 enabled and most useful when ``CONFIG_RTE_EAL_PMD_PATH`` is also set,
132 since ``LD_LIBRARY_PATH`` has no effect in this case.
134 Run-time configuration
135 ~~~~~~~~~~~~~~~~~~~~~~
137 - librte_pmd_mlx4 brings kernel network interfaces up during initialization
138 because it is affected by their state. Forcing them down prevents packets
141 - **ethtool** operations on related kernel interfaces also affect the PMD.
143 - ``port`` parameter [int]
145 This parameter provides a physical port to probe and can be specified multiple
146 times for additional ports. All ports are probed by default if left
149 Kernel module parameters
150 ~~~~~~~~~~~~~~~~~~~~~~~~
152 The **mlx4_core** kernel module has several parameters that affect the
153 behavior and/or the performance of librte_pmd_mlx4. Some of them are described
156 - **num_vfs** (integer or triplet, optionally prefixed by device address
159 Create the given number of VFs on the specified devices.
161 - **log_num_mgm_entry_size** (integer)
163 Device-managed flow steering (DMFS) is required by DPDK applications. It is
164 enabled by using a negative value, the last four bits of which have a
167 - **-1**: force device-managed flow steering (DMFS).
168 - **-7**: configure optimized steering mode to improve performance with the
169 following limitation: VLAN filtering is not supported with this mode.
170 This is the recommended mode in case VLAN filter is not needed.
175 This driver relies on external libraries and kernel drivers for resources
176 allocations and initialization. The following dependencies are not part of
177 DPDK and must be installed separately:
179 - **libibverbs** (provided by rdma-core package)
181 User space verbs framework used by librte_pmd_mlx4. This library provides
182 a generic interface between the kernel and low-level user space drivers
185 It allows slow and privileged operations (context initialization, hardware
186 resources allocations) to be managed by the kernel and fast operations to
187 never leave user space.
189 - **libmlx4** (provided by rdma-core package)
191 Low-level user space driver library for Mellanox ConnectX-3 devices,
192 it is automatically loaded by libibverbs.
194 This library basically implements send/receive calls to the hardware
199 They provide the kernel-side verbs API and low level device drivers that
200 manage actual hardware initialization and resources sharing with user
203 Unlike most other PMDs, these modules must remain loaded and bound to
206 - mlx4_core: hardware driver managing Mellanox ConnectX-3 devices.
207 - mlx4_en: Ethernet device driver that provides kernel network interfaces.
208 - mlx4_ib: InifiniBand device driver.
209 - ib_uverbs: user space driver for verbs (entry point for libibverbs).
211 - **Firmware update**
213 Mellanox OFED releases include firmware updates for ConnectX-3 adapters.
215 Because each release provides new features, these updates must be applied to
216 match the kernel modules and libraries they come with.
220 Both libraries are BSD and GPL licensed. Linux kernel modules are GPL
223 Depending on system constraints and user preferences either RDMA core library
224 with a recent enough Linux kernel release (recommended) or Mellanox OFED,
225 which provides compatibility with older releases.
227 Current RDMA core package and Linux kernel (recommended)
228 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
230 - Minimal Linux kernel version: 4.14.
231 - Minimal RDMA core version: v15 (see `RDMA core installation documentation`_).
233 .. _`RDMA core installation documentation`: https://raw.githubusercontent.com/linux-rdma/rdma-core/master/README.md
235 .. _Mellanox_OFED_as_a_fallback:
237 Mellanox OFED as a fallback
238 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
240 - `Mellanox OFED`_ version: **4.2, 4.3**.
241 - firmware version: **2.42.5000** and above.
243 .. _`Mellanox OFED`: http://www.mellanox.com/page/products_dyn?product_family=26&mtag=linux_sw_drivers
247 Several versions of Mellanox OFED are available. Installing the version
248 this DPDK release was developed and tested against is strongly
249 recommended. Please check the `prerequisites`_.
251 Installing Mellanox OFED
252 ^^^^^^^^^^^^^^^^^^^^^^^^
254 1. Download latest Mellanox OFED.
256 2. Install the required libraries and kernel modules either by installing
257 only the required set, or by installing the entire Mellanox OFED:
261 .. code-block:: console
263 ./mlnxofedinstall --dpdk --upstream-libs
265 For SR-IOV hypervisors use:
267 .. code-block:: console
269 ./mlnxofedinstall --dpdk --upstream-libs --enable-sriov --hypervisor
271 For SR-IOV virtual machine use:
273 .. code-block:: console
275 ./mlnxofedinstall --dpdk --upstream-libs --guest
277 3. Verify the firmware is the correct one:
279 .. code-block:: console
283 4. Set all ports links to Ethernet, follow instructions on the screen:
285 .. code-block:: console
289 5. Continue with :ref:`section 2 of the Quick Start Guide <QSG_2>`.
294 * Mellanox(R) ConnectX(R)-3 Pro 40G MCX354A-FCC_Ax (2*40G)
301 1. Set all ports links to Ethernet
303 .. code-block:: console
305 PCI=<NIC PCI address>
306 echo eth > "/sys/bus/pci/devices/$PCI/mlx4_port0"
307 echo eth > "/sys/bus/pci/devices/$PCI/mlx4_port1"
311 If using Mellanox OFED one can permanently set the port link
312 to Ethernet using connectx_port_config tool provided by it.
313 :ref:`Mellanox_OFED_as_a_fallback`:
317 2. In case of bare metal or hypervisor, configure optimized steering mode
318 by adding the following line to ``/etc/modprobe.d/mlx4_core.conf``:
320 .. code-block:: console
322 options mlx4_core log_num_mgm_entry_size=-7
326 If VLAN filtering is used, set log_num_mgm_entry_size=-1.
327 Performance degradation can occur on this case.
329 3. Restart the driver:
331 .. code-block:: console
333 /etc/init.d/openibd restart
337 .. code-block:: console
339 service openibd restart
341 4. Compile DPDK and you are ready to go. See instructions on
342 :ref:`Development Kit Build System <Development_Kit_Build_System>`
347 1. Verify the optimized steering mode is configured:
349 .. code-block:: console
351 cat /sys/module/mlx4_core/parameters/log_num_mgm_entry_size
353 2. Use the CPU near local NUMA node to which the PCIe adapter is connected,
354 for better performance. For VMs, verify that the right CPU
355 and NUMA node are pinned according to the above. Run:
357 .. code-block:: console
361 to identify the NUMA node to which the PCIe adapter is connected.
363 3. If more than one adapter is used, and root complex capabilities allow
364 to put both adapters on the same NUMA node without PCI bandwidth degradation,
365 it is recommended to locate both adapters on the same NUMA node.
366 This in order to forward packets from one to the other without
367 NUMA performance penalty.
369 4. Disable pause frames:
371 .. code-block:: console
373 ethtool -A <netdev> rx off tx off
375 5. Verify IO non-posted prefetch is disabled by default. This can be checked
376 via the BIOS configuration. Please contact you server provider for more
377 information about the settings.
381 On some machines, depends on the machine integrator, it is beneficial
382 to set the PCI max read request parameter to 1K. This can be
383 done in the following way:
385 To query the read request size use:
387 .. code-block:: console
389 setpci -s <NIC PCI address> 68.w
391 If the output is different than 3XXX, set it by:
393 .. code-block:: console
395 setpci -s <NIC PCI address> 68.w=3XXX
397 The XXX can be different on different systems. Make sure to configure
398 according to the setpci output.
403 This section demonstrates how to launch **testpmd** with Mellanox ConnectX-3
404 devices managed by librte_pmd_mlx4.
406 #. Load the kernel modules:
408 .. code-block:: console
410 modprobe -a ib_uverbs mlx4_en mlx4_core mlx4_ib
412 Alternatively if MLNX_OFED is fully installed, the following script can
415 .. code-block:: console
417 /etc/init.d/openibd restart
421 User space I/O kernel modules (uio and igb_uio) are not used and do
422 not have to be loaded.
424 #. Make sure Ethernet interfaces are in working order and linked to kernel
425 verbs. Related sysfs entries should be present:
427 .. code-block:: console
429 ls -d /sys/class/net/*/device/infiniband_verbs/uverbs* | cut -d / -f 5
433 .. code-block:: console
440 #. Optionally, retrieve their PCI bus addresses for whitelisting:
442 .. code-block:: console
445 for intf in eth2 eth3 eth4 eth5;
447 (cd "/sys/class/net/${intf}/device/" && pwd -P);
450 sed -n 's,.*/\(.*\),-w \1,p'
454 .. code-block:: console
463 There are only two distinct PCI bus addresses because the Mellanox
464 ConnectX-3 adapters installed on this system are dual port.
466 #. Request huge pages:
468 .. code-block:: console
470 echo 1024 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages/nr_hugepages
472 #. Start testpmd with basic parameters:
474 .. code-block:: console
476 testpmd -l 8-15 -n 4 -w 0000:83:00.0 -w 0000:84:00.0 -- --rxq=2 --txq=2 -i
480 .. code-block:: console
483 EAL: PCI device 0000:83:00.0 on NUMA socket 1
484 EAL: probe driver: 15b3:1007 librte_pmd_mlx4
485 PMD: librte_pmd_mlx4: PCI information matches, using device "mlx4_0" (VF: false)
486 PMD: librte_pmd_mlx4: 2 port(s) detected
487 PMD: librte_pmd_mlx4: port 1 MAC address is 00:02:c9:b5:b7:50
488 PMD: librte_pmd_mlx4: port 2 MAC address is 00:02:c9:b5:b7:51
489 EAL: PCI device 0000:84:00.0 on NUMA socket 1
490 EAL: probe driver: 15b3:1007 librte_pmd_mlx4
491 PMD: librte_pmd_mlx4: PCI information matches, using device "mlx4_1" (VF: false)
492 PMD: librte_pmd_mlx4: 2 port(s) detected
493 PMD: librte_pmd_mlx4: port 1 MAC address is 00:02:c9:b5:ba:b0
494 PMD: librte_pmd_mlx4: port 2 MAC address is 00:02:c9:b5:ba:b1
495 Interactive-mode selected
496 Configuring Port 0 (socket 0)
497 PMD: librte_pmd_mlx4: 0x867d60: TX queues number update: 0 -> 2
498 PMD: librte_pmd_mlx4: 0x867d60: RX queues number update: 0 -> 2
499 Port 0: 00:02:C9:B5:B7:50
500 Configuring Port 1 (socket 0)
501 PMD: librte_pmd_mlx4: 0x867da0: TX queues number update: 0 -> 2
502 PMD: librte_pmd_mlx4: 0x867da0: RX queues number update: 0 -> 2
503 Port 1: 00:02:C9:B5:B7:51
504 Configuring Port 2 (socket 0)
505 PMD: librte_pmd_mlx4: 0x867de0: TX queues number update: 0 -> 2
506 PMD: librte_pmd_mlx4: 0x867de0: RX queues number update: 0 -> 2
507 Port 2: 00:02:C9:B5:BA:B0
508 Configuring Port 3 (socket 0)
509 PMD: librte_pmd_mlx4: 0x867e20: TX queues number update: 0 -> 2
510 PMD: librte_pmd_mlx4: 0x867e20: RX queues number update: 0 -> 2
511 Port 3: 00:02:C9:B5:BA:B1
512 Checking link statuses...
513 Port 0 Link Up - speed 10000 Mbps - full-duplex
514 Port 1 Link Up - speed 40000 Mbps - full-duplex
515 Port 2 Link Up - speed 10000 Mbps - full-duplex
516 Port 3 Link Up - speed 40000 Mbps - full-duplex