2 Copyright(c) 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.
32 ======================
34 The I40E PMD (librte_pmd_i40e) provides poll mode driver support
35 for the Intel X710/XL710/X722 10/40 Gbps family of adapters.
41 Features of the I40E PMD are:
43 - Multiple queues for TX and RX
44 - Receiver Side Scaling (RSS)
46 - Packet type information
50 - VLAN/QinQ stripping and inserting
54 - Port hardware statistics
56 - Link state information
58 - Mirror on port, VLAN and VSI
59 - Interrupt mode for RX
60 - Scattered and gather for TX and RX
61 - Vector Poll mode driver
66 - IEEE1588/802.1AS timestamping
67 - VF Daemon (VFD) - EXPERIMENTAL
73 - Identifying your adapter using `Intel Support
74 <http://www.intel.com/support>`_ and get the latest NVM/FW images.
76 - Follow the DPDK :ref:`Getting Started Guide for Linux <linux_gsg>` to setup the basic DPDK environment.
78 - To get better performance on Intel platforms, please follow the "How to get best performance with NICs on Intel platforms"
79 section of the :ref:`Getting Started Guide for Linux <linux_gsg>`.
82 Pre-Installation Configuration
83 ------------------------------
88 The following options can be modified in the ``config`` file.
89 Please note that enabling debugging options may affect system performance.
91 - ``CONFIG_RTE_LIBRTE_I40E_PMD`` (default ``y``)
93 Toggle compilation of the ``librte_pmd_i40e`` driver.
95 - ``CONFIG_RTE_LIBRTE_I40E_DEBUG_*`` (default ``n``)
97 Toggle display of generic debugging messages.
99 - ``CONFIG_RTE_LIBRTE_I40E_RX_ALLOW_BULK_ALLOC`` (default ``y``)
101 Toggle bulk allocation for RX.
103 - ``CONFIG_RTE_LIBRTE_I40E_INC_VECTOR`` (default ``n``)
105 Toggle the use of Vector PMD instead of normal RX/TX path.
106 To enable vPMD for RX, bulk allocation for Rx must be allowed.
108 - ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC`` (default ``n``)
110 Toggle to use a 16-byte RX descriptor, by default the RX descriptor is 32 byte.
112 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_PF`` (default ``64``)
114 Number of queues reserved for PF.
116 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VF`` (default ``4``)
118 Number of queues reserved for each SR-IOV VF.
120 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM`` (default ``4``)
122 Number of queues reserved for each VMDQ Pool.
124 - ``CONFIG_RTE_LIBRTE_I40E_ITR_INTERVAL`` (default ``-1``)
126 Interrupt Throttling interval.
132 To compile the I40E PMD see :ref:`Getting Started Guide for Linux <linux_gsg>` or
133 :ref:`Getting Started Guide for FreeBSD <freebsd_gsg>` depending on your platform.
143 This section demonstrates how to launch ``testpmd`` with Intel XL710/X710
144 devices managed by ``librte_pmd_i40e`` in the Linux operating system.
146 #. Load ``igb_uio`` or ``vfio-pci`` driver:
148 .. code-block:: console
151 insmod ./x86_64-native-linuxapp-gcc/kmod/igb_uio.ko
155 .. code-block:: console
159 #. Bind the XL710/X710 adapters to ``igb_uio`` or ``vfio-pci`` loaded in the previous step:
161 .. code-block:: console
163 ./usertools/dpdk-devbind.py --bind igb_uio 0000:83:00.0
165 Or setup VFIO permissions for regular users and then bind to ``vfio-pci``:
167 .. code-block:: console
169 ./usertools/dpdk-devbind.py --bind vfio-pci 0000:83:00.0
171 #. Start ``testpmd`` with basic parameters:
173 .. code-block:: console
175 ./x86_64-native-linuxapp-gcc/app/testpmd -l 0-3 -n 4 -w 83:00.0 -- -i
179 .. code-block:: console
182 EAL: PCI device 0000:83:00.0 on NUMA socket 1
183 EAL: probe driver: 8086:1572 rte_i40e_pmd
184 EAL: PCI memory mapped at 0x7f7f80000000
185 EAL: PCI memory mapped at 0x7f7f80800000
186 PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.02 eetrack 8000208a
187 Interactive-mode selected
188 Configuring Port 0 (socket 0)
191 PMD: i40e_dev_rx_queue_setup(): Rx Burst Bulk Alloc Preconditions are
192 satisfied.Rx Burst Bulk Alloc function will be used on port=0, queue=0.
195 Port 0: 68:05:CA:26:85:84
196 Checking link statuses...
197 Port 0 Link Up - speed 10000 Mbps - full-duplex
203 SR-IOV: Prerequisites and sample Application Notes
204 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
206 #. Load the kernel module:
208 .. code-block:: console
212 Check the output in dmesg:
214 .. code-block:: console
216 i40e 0000:83:00.1 ens802f0: renamed from eth0
218 #. Bring up the PF ports:
220 .. code-block:: console
224 #. Create VF device(s):
226 Echo the number of VFs to be created into the ``sriov_numvfs`` sysfs entry
231 .. code-block:: console
233 echo 2 > /sys/devices/pci0000:00/0000:00:03.0/0000:81:00.0/sriov_numvfs
236 #. Assign VF MAC address:
238 Assign MAC address to the VF using iproute2 utility. The syntax is:
240 .. code-block:: console
242 ip link set <PF netdev id> vf <VF id> mac <macaddr>
246 .. code-block:: console
248 ip link set ens802f0 vf 0 mac a0:b0:c0:d0:e0:f0
250 #. Assign VF to VM, and bring up the VM.
251 Please see the documentation for the *I40E/IXGBE/IGB Virtual Function Driver*.
254 Sample Application Notes
255 ------------------------
260 Vlan filter only works when Promiscuous mode is off.
262 To start ``testpmd``, and add vlan 10 to port 0:
264 .. code-block:: console
266 ./app/testpmd -l 0-15 -n 4 -- -i --forward-mode=mac
269 testpmd> set promisc 0 off
270 testpmd> rx_vlan add 10 0
276 The Flow Director works in receive mode to identify specific flows or sets of flows and route them to specific queues.
277 The Flow Director filters can match the different fields for different type of packet: flow type, specific input set per flow type and the flexible payload.
279 The default input set of each flow type is::
281 ipv4-other : src_ip_address, dst_ip_address
282 ipv4-frag : src_ip_address, dst_ip_address
283 ipv4-tcp : src_ip_address, dst_ip_address, src_port, dst_port
284 ipv4-udp : src_ip_address, dst_ip_address, src_port, dst_port
285 ipv4-sctp : src_ip_address, dst_ip_address, src_port, dst_port,
287 ipv6-other : src_ip_address, dst_ip_address
288 ipv6-frag : src_ip_address, dst_ip_address
289 ipv6-tcp : src_ip_address, dst_ip_address, src_port, dst_port
290 ipv6-udp : src_ip_address, dst_ip_address, src_port, dst_port
291 ipv6-sctp : src_ip_address, dst_ip_address, src_port, dst_port,
293 l2_payload : ether_type
295 The flex payload is selected from offset 0 to 15 of packet's payload by default, while it is masked out from matching.
297 Start ``testpmd`` with ``--disable-rss`` and ``--pkt-filter-mode=perfect``:
299 .. code-block:: console
301 ./app/testpmd -l 0-15 -n 4 -- -i --disable-rss --pkt-filter-mode=perfect \
302 --rxq=8 --txq=8 --nb-cores=8 --nb-ports=1
304 Add a rule to direct ``ipv4-udp`` packet whose ``dst_ip=2.2.2.5, src_ip=2.2.2.3, src_port=32, dst_port=32`` to queue 1:
306 .. code-block:: console
308 testpmd> flow_director_filter 0 mode IP add flow ipv4-udp \
309 src 2.2.2.3 32 dst 2.2.2.5 32 vlan 0 flexbytes () \
310 fwd pf queue 1 fd_id 1
312 Check the flow director status:
314 .. code-block:: console
316 testpmd> show port fdir 0
318 ######################## FDIR infos for port 0 ####################
320 SUPPORTED FLOW TYPE: ipv4-frag ipv4-tcp ipv4-udp ipv4-sctp ipv4-other
321 ipv6-frag ipv6-tcp ipv6-udp ipv6-sctp ipv6-other
324 max_len: 16 payload_limit: 480
325 payload_unit: 2 payload_seg: 3
326 bitmask_unit: 2 bitmask_num: 2
329 src_ipv4: 0x00000000,
330 dst_ipv4: 0x00000000,
333 src_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000,
334 dst_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000
335 FLEX PAYLOAD SRC OFFSET:
336 L2_PAYLOAD: 0 1 2 3 4 5 6 ...
337 L3_PAYLOAD: 0 1 2 3 4 5 6 ...
338 L4_PAYLOAD: 0 1 2 3 4 5 6 ...
340 ipv4-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
341 ipv4-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
342 ipv4-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
343 ipv4-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
344 ipv4-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
345 ipv6-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
346 ipv6-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
347 ipv6-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
348 ipv6-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
349 ipv6-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
350 l2_payload: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
351 guarant_count: 1 best_count: 0
352 guarant_space: 512 best_space: 7168
359 Delete all flow director rules on a port:
361 .. code-block:: console
363 testpmd> flush_flow_director 0
368 The IntelĀ® Ethernet Controller X710 and XL710 Family support a feature called
371 A Virtual Ethernet Bridge (VEB) is an IEEE Edge Virtual Bridging (EVB) term
372 for functionality that allows local switching between virtual endpoints within
373 a physical endpoint and also with an external bridge/network.
375 A "Floating" VEB doesn't have an uplink connection to the outside world so all
376 switching is done internally and remains within the host. As such, this
377 feature provides security benefits.
379 In addition, a Floating VEB overcomes a limitation of normal VEBs where they
380 cannot forward packets when the physical link is down. Floating VEBs don't need
381 to connect to the NIC port so they can still forward traffic from VF to VF
382 even when the physical link is down.
384 Therefore, with this feature enabled VFs can be limited to communicating with
385 each other but not an outside network, and they can do so even when there is
386 no physical uplink on the associated NIC port.
388 To enable this feature, the user should pass a ``devargs`` parameter to the
391 -w 84:00.0,enable_floating_veb=1
393 In this configuration the PMD will use the floating VEB feature for all the
394 VFs created by this PF device.
396 Alternatively, the user can specify which VFs need to connect to this floating
397 VEB using the ``floating_veb_list`` argument::
399 -w 84:00.0,enable_floating_veb=1,floating_veb_list=1;3-4
401 In this example ``VF1``, ``VF3`` and ``VF4`` connect to the floating VEB,
402 while other VFs connect to the normal VEB.
404 The current implementation only supports one floating VEB and one regular
405 VEB. VFs can connect to a floating VEB or a regular VEB according to the
406 configuration passed on the EAL command line.
408 The floating VEB functionality requires a NIC firmware version of 5.0
412 Limitations or Known issues
413 ---------------------------
415 MPLS packet classification on X710/XL710
416 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
418 For firmware versions prior to 5.0, MPLS packets are not recognized by the NIC.
419 The L2 Payload flow type in flow director can be used to classify MPLS packet
420 by using a command in testpmd like:
422 testpmd> flow_director_filter 0 mode IP add flow l2_payload ether \
423 0x8847 flexbytes () fwd pf queue <N> fd_id <M>
425 With the NIC firmware version 5.0 or greater, some limited MPLS support
426 is added: Native MPLS (MPLS in Ethernet) skip is implemented, while no
427 new packet type, no classification or offload are possible. With this change,
428 L2 Payload flow type in flow director cannot be used to classify MPLS packet
429 as with previous firmware versions. Meanwhile, the Ethertype filter can be
430 used to classify MPLS packet by using a command in testpmd like:
432 testpmd> ethertype_filter 0 add mac_ignr 00:00:00:00:00:00 ethertype \
435 16 Byte Descriptor cannot be used on DPDK VF
436 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
438 If the Linux i40e kernel driver is used as host driver, while DPDK i40e PMD
439 is used as the VF driver, DPDK cannot choose 16 byte receive descriptor. That
440 is to say, user should keep ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC=n`` in
443 Link down with i40e kernel driver after DPDK application exit
444 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
446 After DPDK application quit, and the device is bound back to Linux i40e
447 kernel driver, the link cannot be up after ``ifconfig <dev> up``.
448 To work around this issue, ``ethtool -s <dev> autoneg on`` should be
449 set first and then the link can be brought up through ``ifconfig <dev> up``.
451 NOTE: requires Linux kernel i40e driver version >= 1.4.X
453 Receive packets with Ethertype 0x88A8
454 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
456 Due to the FW limitation, PF can receive packets with Ethertype 0x88A8
457 only when floating VEB is disabled.
459 Incorrect Rx statistics when packet is oversize
460 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
462 When a packet is over maximum frame size, the packet is dropped.
463 However the Rx statistics, when calling `rte_eth_stats_get` incorrectly
464 shows it as received.
466 VF & TC max bandwidth setting
467 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
469 The per VF max bandwidth and per TC max bandwidth cannot be enabled in parallel.
470 The dehavior is different when handling per VF and per TC max bandwidth setting.
471 When enabling per VF max bandwidth, SW will check if per TC max bandwidth is
472 enabled. If so, return failure.
473 When enabling per TC max bandwidth, SW will check if per VF max bandwidth
474 is enabled. If so, disable per VF max bandwidth and continue with per TC max
477 TC TX scheduling mode setting
478 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
480 There're 2 TX scheduling modes for TCs, round robin and strict priority mode.
481 If a TC is set to strict priority mode, it can consume unlimited bandwidth.
482 It means if APP has set the max bandwidth for that TC, it comes to no
484 It's suggested to set the strict priority mode for a TC that is latency
485 sensitive but no consuming much bandwidth.