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_RX_OLFLAGS_ENABLE`` (default ``y``)
110 Toggle to enable RX ``olflags``.
111 This is only meaningful when Vector PMD is used.
113 - ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC`` (default ``n``)
115 Toggle to use a 16-byte RX descriptor, by default the RX descriptor is 32 byte.
117 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_PF`` (default ``64``)
119 Number of queues reserved for PF.
121 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VF`` (default ``4``)
123 Number of queues reserved for each SR-IOV VF.
125 - ``CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM`` (default ``4``)
127 Number of queues reserved for each VMDQ Pool.
129 - ``CONFIG_RTE_LIBRTE_I40E_ITR_INTERVAL`` (default ``-1``)
131 Interrupt Throttling interval.
137 To compile the I40E PMD see :ref:`Getting Started Guide for Linux <linux_gsg>` or
138 :ref:`Getting Started Guide for FreeBSD <freebsd_gsg>` depending on your platform.
148 This section demonstrates how to launch ``testpmd`` with Intel XL710/X710
149 devices managed by ``librte_pmd_i40e`` in the Linux operating system.
151 #. Load ``igb_uio`` or ``vfio-pci`` driver:
153 .. code-block:: console
156 insmod ./x86_64-native-linuxapp-gcc/kmod/igb_uio.ko
160 .. code-block:: console
164 #. Bind the XL710/X710 adapters to ``igb_uio`` or ``vfio-pci`` loaded in the previous step:
166 .. code-block:: console
168 ./usertools/dpdk-devbind.py --bind igb_uio 0000:83:00.0
170 Or setup VFIO permissions for regular users and then bind to ``vfio-pci``:
172 .. code-block:: console
174 ./usertools/dpdk-devbind.py --bind vfio-pci 0000:83:00.0
176 #. Start ``testpmd`` with basic parameters:
178 .. code-block:: console
180 ./x86_64-native-linuxapp-gcc/app/testpmd -l 0-3 -n 4 -w 83:00.0 -- -i
184 .. code-block:: console
187 EAL: PCI device 0000:83:00.0 on NUMA socket 1
188 EAL: probe driver: 8086:1572 rte_i40e_pmd
189 EAL: PCI memory mapped at 0x7f7f80000000
190 EAL: PCI memory mapped at 0x7f7f80800000
191 PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.02 eetrack 8000208a
192 Interactive-mode selected
193 Configuring Port 0 (socket 0)
196 PMD: i40e_dev_rx_queue_setup(): Rx Burst Bulk Alloc Preconditions are
197 satisfied.Rx Burst Bulk Alloc function will be used on port=0, queue=0.
200 Port 0: 68:05:CA:26:85:84
201 Checking link statuses...
202 Port 0 Link Up - speed 10000 Mbps - full-duplex
208 SR-IOV: Prerequisites and sample Application Notes
209 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
211 #. Load the kernel module:
213 .. code-block:: console
217 Check the output in dmesg:
219 .. code-block:: console
221 i40e 0000:83:00.1 ens802f0: renamed from eth0
223 #. Bring up the PF ports:
225 .. code-block:: console
229 #. Create VF device(s):
231 Echo the number of VFs to be created into the ``sriov_numvfs`` sysfs entry
236 .. code-block:: console
238 echo 2 > /sys/devices/pci0000:00/0000:00:03.0/0000:81:00.0/sriov_numvfs
241 #. Assign VF MAC address:
243 Assign MAC address to the VF using iproute2 utility. The syntax is:
245 .. code-block:: console
247 ip link set <PF netdev id> vf <VF id> mac <macaddr>
251 .. code-block:: console
253 ip link set ens802f0 vf 0 mac a0:b0:c0:d0:e0:f0
255 #. Assign VF to VM, and bring up the VM.
256 Please see the documentation for the *I40E/IXGBE/IGB Virtual Function Driver*.
259 Sample Application Notes
260 ------------------------
265 Vlan filter only works when Promiscuous mode is off.
267 To start ``testpmd``, and add vlan 10 to port 0:
269 .. code-block:: console
271 ./app/testpmd -l 0-15 -n 4 -- -i --forward-mode=mac
274 testpmd> set promisc 0 off
275 testpmd> rx_vlan add 10 0
281 The Flow Director works in receive mode to identify specific flows or sets of flows and route them to specific queues.
282 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.
284 The default input set of each flow type is::
286 ipv4-other : src_ip_address, dst_ip_address
287 ipv4-frag : src_ip_address, dst_ip_address
288 ipv4-tcp : src_ip_address, dst_ip_address, src_port, dst_port
289 ipv4-udp : src_ip_address, dst_ip_address, src_port, dst_port
290 ipv4-sctp : src_ip_address, dst_ip_address, src_port, dst_port,
292 ipv6-other : src_ip_address, dst_ip_address
293 ipv6-frag : src_ip_address, dst_ip_address
294 ipv6-tcp : src_ip_address, dst_ip_address, src_port, dst_port
295 ipv6-udp : src_ip_address, dst_ip_address, src_port, dst_port
296 ipv6-sctp : src_ip_address, dst_ip_address, src_port, dst_port,
298 l2_payload : ether_type
300 The flex payload is selected from offset 0 to 15 of packet's payload by default, while it is masked out from matching.
302 Start ``testpmd`` with ``--disable-rss`` and ``--pkt-filter-mode=perfect``:
304 .. code-block:: console
306 ./app/testpmd -l 0-15 -n 4 -- -i --disable-rss --pkt-filter-mode=perfect \
307 --rxq=8 --txq=8 --nb-cores=8 --nb-ports=1
309 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:
311 .. code-block:: console
313 testpmd> flow_director_filter 0 mode IP add flow ipv4-udp \
314 src 2.2.2.3 32 dst 2.2.2.5 32 vlan 0 flexbytes () \
315 fwd pf queue 1 fd_id 1
317 Check the flow director status:
319 .. code-block:: console
321 testpmd> show port fdir 0
323 ######################## FDIR infos for port 0 ####################
325 SUPPORTED FLOW TYPE: ipv4-frag ipv4-tcp ipv4-udp ipv4-sctp ipv4-other
326 ipv6-frag ipv6-tcp ipv6-udp ipv6-sctp ipv6-other
329 max_len: 16 payload_limit: 480
330 payload_unit: 2 payload_seg: 3
331 bitmask_unit: 2 bitmask_num: 2
334 src_ipv4: 0x00000000,
335 dst_ipv4: 0x00000000,
338 src_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000,
339 dst_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000
340 FLEX PAYLOAD SRC OFFSET:
341 L2_PAYLOAD: 0 1 2 3 4 5 6 ...
342 L3_PAYLOAD: 0 1 2 3 4 5 6 ...
343 L4_PAYLOAD: 0 1 2 3 4 5 6 ...
345 ipv4-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
346 ipv4-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
347 ipv4-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
348 ipv4-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
349 ipv4-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
350 ipv6-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
351 ipv6-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
352 ipv6-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
353 ipv6-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
354 ipv6-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
355 l2_payload: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
356 guarant_count: 1 best_count: 0
357 guarant_space: 512 best_space: 7168
364 Delete all flow director rules on a port:
366 .. code-block:: console
368 testpmd> flush_flow_director 0
373 The IntelĀ® Ethernet Controller X710 and XL710 Family support a feature called
376 A Virtual Ethernet Bridge (VEB) is an IEEE Edge Virtual Bridging (EVB) term
377 for functionality that allows local switching between virtual endpoints within
378 a physical endpoint and also with an external bridge/network.
380 A "Floating" VEB doesn't have an uplink connection to the outside world so all
381 switching is done internally and remains within the host. As such, this
382 feature provides security benefits.
384 In addition, a Floating VEB overcomes a limitation of normal VEBs where they
385 cannot forward packets when the physical link is down. Floating VEBs don't need
386 to connect to the NIC port so they can still forward traffic from VF to VF
387 even when the physical link is down.
389 Therefore, with this feature enabled VFs can be limited to communicating with
390 each other but not an outside network, and they can do so even when there is
391 no physical uplink on the associated NIC port.
393 To enable this feature, the user should pass a ``devargs`` parameter to the
396 -w 84:00.0,enable_floating_veb=1
398 In this configuration the PMD will use the floating VEB feature for all the
399 VFs created by this PF device.
401 Alternatively, the user can specify which VFs need to connect to this floating
402 VEB using the ``floating_veb_list`` argument::
404 -w 84:00.0,enable_floating_veb=1,floating_veb_list=1;3-4
406 In this example ``VF1``, ``VF3`` and ``VF4`` connect to the floating VEB,
407 while other VFs connect to the normal VEB.
409 The current implementation only supports one floating VEB and one regular
410 VEB. VFs can connect to a floating VEB or a regular VEB according to the
411 configuration passed on the EAL command line.
413 The floating VEB functionality requires a NIC firmware version of 5.0
417 Limitations or Known issues
418 ---------------------------
420 MPLS packet classification on X710/XL710
421 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
423 For firmware versions prior to 5.0, MPLS packets are not recognized by the NIC.
424 The L2 Payload flow type in flow director can be used to classify MPLS packet
425 by using a command in testpmd like:
427 testpmd> flow_director_filter 0 mode IP add flow l2_payload ether \
428 0x8847 flexbytes () fwd pf queue <N> fd_id <M>
430 With the NIC firmware version 5.0 or greater, some limited MPLS support
431 is added: Native MPLS (MPLS in Ethernet) skip is implemented, while no
432 new packet type, no classification or offload are possible. With this change,
433 L2 Payload flow type in flow director cannot be used to classify MPLS packet
434 as with previous firmware versions. Meanwhile, the Ethertype filter can be
435 used to classify MPLS packet by using a command in testpmd like:
437 testpmd> ethertype_filter 0 add mac_ignr 00:00:00:00:00:00 ethertype \
440 16 Byte Descriptor cannot be used on DPDK VF
441 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
443 If the Linux i40e kernel driver is used as host driver, while DPDK i40e PMD
444 is used as the VF driver, DPDK cannot choose 16 byte receive descriptor. That
445 is to say, user should keep ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC=n`` in
448 Link down with i40e kernel driver after DPDK application exist
449 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
451 After DPDK application quit, and the device is bound back to Linux i40e
452 kernel driver, the link cannot be up after ``ifconfig <dev> up``.
453 To work around this issue, ``ethtool -s <dev> autoneg on`` should be
454 set first and then the link can be brought up through ``ifconfig <dev> up``.
456 NOTE: requires Linux kernel i40e driver version >= 1.4.X
458 Receive packets with Ethertype 0x88A8
459 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
461 Due to the FW limitation, PF can receive packets with Ethertype 0x88A8
462 only when floating VEB is disabled.
464 Incorrect Rx statistics when packet is oversize
465 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
467 When a packet is over maximum frame size, the packet is dropped.
468 However the Rx statistics, when calling `rte_eth_stats_get` incorrectly
469 shows it as received.