1.. SPDX-License-Identifier: BSD-3-Clause 2 Copyright(c) 2016 Intel Corporation. 3 4I40E Poll Mode Driver 5====================== 6 7The i40e PMD (**librte_net_i40e**) provides poll mode driver support for 810/25/40 Gbps Intel® Ethernet 700 Series Network Adapters based on 9the Intel Ethernet Controller X710/XL710/XXV710 and Intel Ethernet 10Connection X722 (only support part of features). 11 12 13Features 14-------- 15 16Features of the i40e PMD are: 17 18- Multiple queues for TX and RX 19- Receiver Side Scaling (RSS) 20- MAC/VLAN filtering 21- Packet type information 22- Flow director 23- Cloud filter 24- Checksum offload 25- VLAN/QinQ stripping and inserting 26- TSO offload 27- Promiscuous mode 28- Multicast mode 29- Port hardware statistics 30- Jumbo frames 31- Link state information 32- Link flow control 33- Mirror on port, VLAN and VSI 34- Interrupt mode for RX 35- Scattered and gather for TX and RX 36- Vector Poll mode driver 37- DCB 38- VMDQ 39- SR-IOV VF 40- Hot plug 41- IEEE1588/802.1AS timestamping 42- VF Daemon (VFD) - EXPERIMENTAL 43- Dynamic Device Personalization (DDP) 44- Queue region configuration 45- Virtual Function Port Representors 46- Malicious Device Drive event catch and notify 47- Generic flow API 48 49Prerequisites 50------------- 51 52- Identifying your adapter using `Intel Support 53 <http://www.intel.com/support>`_ and get the latest NVM/FW images. 54 55- Follow the DPDK :ref:`Getting Started Guide for Linux <linux_gsg>` to setup the basic DPDK environment. 56 57- To get better performance on Intel platforms, please follow the "How to get best performance with NICs on Intel platforms" 58 section of the :ref:`Getting Started Guide for Linux <linux_gsg>`. 59 60- Upgrade the NVM/FW version following the `Intel® Ethernet NVM Update Tool Quick Usage Guide for Linux 61 <https://www-ssl.intel.com/content/www/us/en/embedded/products/networking/nvm-update-tool-quick-linux-usage-guide.html>`_ and `Intel® Ethernet NVM Update Tool: Quick Usage Guide for EFI <https://www.intel.com/content/www/us/en/embedded/products/networking/nvm-update-tool-quick-efi-usage-guide.html>`_ if needed. 62 63- For information about supported media, please refer to this document: `Intel® Ethernet Controller X710/XXV710/XL710 Feature Support Matrix 64 <http://www.intel.com/content/dam/www/public/us/en/documents/release-notes/xl710-ethernet-controller-feature-matrix.pdf>`_. 65 66 .. Note:: 67 68 * Some adapters based on the Intel(R) Ethernet Controller 700 Series only 69 support Intel Ethernet Optics modules. On these adapters, other modules are not 70 supported and will not function. 71 72 * For connections based on Intel(R) Ethernet Controller 700 Series, 73 support is dependent on your system board. Please see your vendor for details. 74 75 * In all cases Intel recommends using Intel Ethernet Optics; other modules 76 may function but are not validated by Intel. Contact Intel for supported media types. 77 78Recommended Matching List 79------------------------- 80 81It is highly recommended to upgrade the i40e kernel driver and firmware to 82avoid the compatibility issues with i40e PMD. Here is the suggested matching 83list which has been tested and verified. The detailed information can refer 84to chapter Tested Platforms/Tested NICs in release notes. 85 86For X710/XL710/XXV710, 87 88 +--------------+-----------------------+------------------+ 89 | DPDK version | Kernel driver version | Firmware version | 90 +==============+=======================+==================+ 91 | 20.11 | 2.13.10 | 8.00 | 92 +--------------+-----------------------+------------------+ 93 | 20.08 | 2.12.6 | 7.30 | 94 +--------------+-----------------------+------------------+ 95 | 20.05 | 2.11.27 | 7.30 | 96 +--------------+-----------------------+------------------+ 97 | 20.02 | 2.10.19 | 7.20 | 98 +--------------+-----------------------+------------------+ 99 | 19.11 | 2.9.21 | 7.00 | 100 +--------------+-----------------------+------------------+ 101 | 19.08 | 2.8.43 | 7.00 | 102 +--------------+-----------------------+------------------+ 103 | 19.05 | 2.7.29 | 6.80 | 104 +--------------+-----------------------+------------------+ 105 | 19.02 | 2.7.26 | 6.80 | 106 +--------------+-----------------------+------------------+ 107 | 18.11 | 2.4.6 | 6.01 | 108 +--------------+-----------------------+------------------+ 109 | 18.08 | 2.4.6 | 6.01 | 110 +--------------+-----------------------+------------------+ 111 | 18.05 | 2.4.6 | 6.01 | 112 +--------------+-----------------------+------------------+ 113 | 18.02 | 2.4.3 | 6.01 | 114 +--------------+-----------------------+------------------+ 115 | 17.11 | 2.1.26 | 6.01 | 116 +--------------+-----------------------+------------------+ 117 | 17.08 | 2.0.19 | 6.01 | 118 +--------------+-----------------------+------------------+ 119 | 17.05 | 1.5.23 | 5.05 | 120 +--------------+-----------------------+------------------+ 121 | 17.02 | 1.5.23 | 5.05 | 122 +--------------+-----------------------+------------------+ 123 | 16.11 | 1.5.23 | 5.05 | 124 +--------------+-----------------------+------------------+ 125 | 16.07 | 1.4.25 | 5.04 | 126 +--------------+-----------------------+------------------+ 127 | 16.04 | 1.4.25 | 5.02 | 128 +--------------+-----------------------+------------------+ 129 130 131For X722, 132 133 +--------------+-----------------------+------------------+ 134 | DPDK version | Kernel driver version | Firmware version | 135 +==============+=======================+==================+ 136 | 20.11 | 2.13.10 | 5.00 | 137 +--------------+-----------------------+------------------+ 138 | 20.08 | 2.12.6 | 4.11 | 139 +--------------+-----------------------+------------------+ 140 | 20.05 | 2.11.27 | 4.11 | 141 +--------------+-----------------------+------------------+ 142 | 20.02 | 2.10.19 | 4.11 | 143 +--------------+-----------------------+------------------+ 144 | 19.11 | 2.9.21 | 4.10 | 145 +--------------+-----------------------+------------------+ 146 | 19.08 | 2.9.21 | 4.10 | 147 +--------------+-----------------------+------------------+ 148 | 19.05 | 2.7.29 | 3.33 | 149 +--------------+-----------------------+------------------+ 150 | 19.02 | 2.7.26 | 3.33 | 151 +--------------+-----------------------+------------------+ 152 | 18.11 | 2.4.6 | 3.33 | 153 +--------------+-----------------------+------------------+ 154 155 156Pre-Installation Configuration 157------------------------------ 158 159Config File Options 160~~~~~~~~~~~~~~~~~~~ 161 162The following options can be modified in the ``config/rte_config.h`` file. 163 164- ``RTE_LIBRTE_I40E_QUEUE_NUM_PER_PF`` (default ``64``) 165 166 Number of queues reserved for PF. 167 168- ``RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM`` (default ``4``) 169 170 Number of queues reserved for each VMDQ Pool. 171 172Runtime Config Options 173~~~~~~~~~~~~~~~~~~~~~~ 174 175- ``Reserved number of Queues per VF`` (default ``4``) 176 177 The number of reserved queue per VF is determined by its host PF. If the 178 PCI address of an i40e PF is aaaa:bb.cc, the number of reserved queues per 179 VF can be configured with EAL parameter like -a aaaa:bb.cc,queue-num-per-vf=n. 180 The value n can be 1, 2, 4, 8 or 16. If no such parameter is configured, the 181 number of reserved queues per VF is 4 by default. If VF request more than 182 reserved queues per VF, PF will able to allocate max to 16 queues after a VF 183 reset. 184 185 186- ``Support multiple driver`` (default ``disable``) 187 188 There was a multiple driver support issue during use of 700 series Ethernet 189 Adapter with both Linux kernel and DPDK PMD. To fix this issue, ``devargs`` 190 parameter ``support-multi-driver`` is introduced, for example:: 191 192 -a 84:00.0,support-multi-driver=1 193 194 With the above configuration, DPDK PMD will not change global registers, and 195 will switch PF interrupt from IntN to Int0 to avoid interrupt conflict between 196 DPDK and Linux Kernel. 197 198- ``Support VF Port Representor`` (default ``not enabled``) 199 200 The i40e PF PMD supports the creation of VF port representors for the control 201 and monitoring of i40e virtual function devices. Each port representor 202 corresponds to a single virtual function of that device. Using the ``devargs`` 203 option ``representor`` the user can specify which virtual functions to create 204 port representors for on initialization of the PF PMD by passing the VF IDs of 205 the VFs which are required.:: 206 207 -a DBDF,representor=[0,1,4] 208 209 Currently hot-plugging of representor ports is not supported so all required 210 representors must be specified on the creation of the PF. 211 212- ``Use latest supported vector`` (default ``disable``) 213 214 Latest supported vector path may not always get the best perf so vector path was 215 recommended to use only on later platform. But users may want the latest vector path 216 since it can get better perf in some real work loading cases. So ``devargs`` param 217 ``use-latest-supported-vec`` is introduced, for example:: 218 219 -a 84:00.0,use-latest-supported-vec=1 220 221- ``Enable validation for VF message`` (default ``not enabled``) 222 223 The PF counts messages from each VF. If in any period of seconds the message 224 statistic from a VF exceeds maximal limitation, the PF will ignore any new message 225 from that VF for some seconds. 226 Format -- "maximal-message@period-seconds:ignore-seconds" 227 For example:: 228 229 -a 84:00.0,vf_msg_cfg=80@120:180 230 231Vector RX Pre-conditions 232~~~~~~~~~~~~~~~~~~~~~~~~ 233For Vector RX it is assumed that the number of descriptor rings will be a power 234of 2. With this pre-condition, the ring pointer can easily scroll back to the 235head after hitting the tail without a conditional check. In addition Vector RX 236can use this assumption to do a bit mask using ``ring_size - 1``. 237 238Driver compilation and testing 239------------------------------ 240 241Refer to the document :ref:`compiling and testing a PMD for a NIC <pmd_build_and_test>` 242for details. 243 244 245SR-IOV: Prerequisites and sample Application Notes 246-------------------------------------------------- 247 248#. Load the kernel module: 249 250 .. code-block:: console 251 252 modprobe i40e 253 254 Check the output in dmesg: 255 256 .. code-block:: console 257 258 i40e 0000:83:00.1 ens802f0: renamed from eth0 259 260#. Bring up the PF ports: 261 262 .. code-block:: console 263 264 ifconfig ens802f0 up 265 266#. Create VF device(s): 267 268 Echo the number of VFs to be created into the ``sriov_numvfs`` sysfs entry 269 of the parent PF. 270 271 Example: 272 273 .. code-block:: console 274 275 echo 2 > /sys/devices/pci0000:00/0000:00:03.0/0000:81:00.0/sriov_numvfs 276 277 278#. Assign VF MAC address: 279 280 Assign MAC address to the VF using iproute2 utility. The syntax is: 281 282 .. code-block:: console 283 284 ip link set <PF netdev id> vf <VF id> mac <macaddr> 285 286 Example: 287 288 .. code-block:: console 289 290 ip link set ens802f0 vf 0 mac a0:b0:c0:d0:e0:f0 291 292#. Assign VF to VM, and bring up the VM. 293 Please see the documentation for the *I40E/IXGBE/IGB Virtual Function Driver*. 294 295#. Running testpmd: 296 297 Follow instructions available in the document 298 :ref:`compiling and testing a PMD for a NIC <pmd_build_and_test>` 299 to run testpmd. 300 301 Example output: 302 303 .. code-block:: console 304 305 ... 306 EAL: PCI device 0000:83:00.0 on NUMA socket 1 307 EAL: probe driver: 8086:1572 rte_i40e_pmd 308 EAL: PCI memory mapped at 0x7f7f80000000 309 EAL: PCI memory mapped at 0x7f7f80800000 310 PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.02 eetrack 8000208a 311 Interactive-mode selected 312 Configuring Port 0 (socket 0) 313 ... 314 315 PMD: i40e_dev_rx_queue_setup(): Rx Burst Bulk Alloc Preconditions are 316 satisfied.Rx Burst Bulk Alloc function will be used on port=0, queue=0. 317 318 ... 319 Port 0: 68:05:CA:26:85:84 320 Checking link statuses... 321 Port 0 Link Up - speed 10000 Mbps - full-duplex 322 Done 323 324 testpmd> 325 326 327Sample Application Notes 328------------------------ 329 330Vlan filter 331~~~~~~~~~~~ 332 333Vlan filter only works when Promiscuous mode is off. 334 335To start ``testpmd``, and add vlan 10 to port 0: 336 337.. code-block:: console 338 339 ./<build_dir>/app/dpdk-testpmd -l 0-15 -n 4 -- -i --forward-mode=mac 340 ... 341 342 testpmd> set promisc 0 off 343 testpmd> rx_vlan add 10 0 344 345 346Flow Director 347~~~~~~~~~~~~~ 348 349The Flow Director works in receive mode to identify specific flows or sets of flows and route them to specific queues. 350The 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. 351 352The default input set of each flow type is:: 353 354 ipv4-other : src_ip_address, dst_ip_address 355 ipv4-frag : src_ip_address, dst_ip_address 356 ipv4-tcp : src_ip_address, dst_ip_address, src_port, dst_port 357 ipv4-udp : src_ip_address, dst_ip_address, src_port, dst_port 358 ipv4-sctp : src_ip_address, dst_ip_address, src_port, dst_port, 359 verification_tag 360 ipv6-other : src_ip_address, dst_ip_address 361 ipv6-frag : src_ip_address, dst_ip_address 362 ipv6-tcp : src_ip_address, dst_ip_address, src_port, dst_port 363 ipv6-udp : src_ip_address, dst_ip_address, src_port, dst_port 364 ipv6-sctp : src_ip_address, dst_ip_address, src_port, dst_port, 365 verification_tag 366 l2_payload : ether_type 367 368The flex payload is selected from offset 0 to 15 of packet's payload by default, while it is masked out from matching. 369 370Start ``testpmd`` with ``--disable-rss`` and ``--pkt-filter-mode=perfect``: 371 372.. code-block:: console 373 374 ./<build_dir>/app/dpdk-testpmd -l 0-15 -n 4 -- -i --disable-rss \ 375 --pkt-filter-mode=perfect --rxq=8 --txq=8 --nb-cores=8 \ 376 --nb-ports=1 377 378Add 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: 379 380.. code-block:: console 381 382 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.3 \ 383 dst is 2.2.2.5 / udp src is 32 dst is 32 / end \ 384 actions mark id 1 / queue index 1 / end 385 386Check the flow director status: 387 388.. code-block:: console 389 390 testpmd> show port fdir 0 391 392 ######################## FDIR infos for port 0 #################### 393 MODE: PERFECT 394 SUPPORTED FLOW TYPE: ipv4-frag ipv4-tcp ipv4-udp ipv4-sctp ipv4-other 395 ipv6-frag ipv6-tcp ipv6-udp ipv6-sctp ipv6-other 396 l2_payload 397 FLEX PAYLOAD INFO: 398 max_len: 16 payload_limit: 480 399 payload_unit: 2 payload_seg: 3 400 bitmask_unit: 2 bitmask_num: 2 401 MASK: 402 vlan_tci: 0x0000, 403 src_ipv4: 0x00000000, 404 dst_ipv4: 0x00000000, 405 src_port: 0x0000, 406 dst_port: 0x0000 407 src_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000, 408 dst_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000 409 FLEX PAYLOAD SRC OFFSET: 410 L2_PAYLOAD: 0 1 2 3 4 5 6 ... 411 L3_PAYLOAD: 0 1 2 3 4 5 6 ... 412 L4_PAYLOAD: 0 1 2 3 4 5 6 ... 413 FLEX MASK CFG: 414 ipv4-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 415 ipv4-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 416 ipv4-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 417 ipv4-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 418 ipv4-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 419 ipv6-udp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 420 ipv6-tcp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 421 ipv6-sctp: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 422 ipv6-other: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 423 ipv6-frag: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 424 l2_payload: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 425 guarant_count: 1 best_count: 0 426 guarant_space: 512 best_space: 7168 427 collision: 0 free: 0 428 maxhash: 0 maxlen: 0 429 add: 0 remove: 0 430 f_add: 0 f_remove: 0 431 432 433Floating VEB 434~~~~~~~~~~~~~ 435 436The Intel® Ethernet 700 Series support a feature called 437"Floating VEB". 438 439A Virtual Ethernet Bridge (VEB) is an IEEE Edge Virtual Bridging (EVB) term 440for functionality that allows local switching between virtual endpoints within 441a physical endpoint and also with an external bridge/network. 442 443A "Floating" VEB doesn't have an uplink connection to the outside world so all 444switching is done internally and remains within the host. As such, this 445feature provides security benefits. 446 447In addition, a Floating VEB overcomes a limitation of normal VEBs where they 448cannot forward packets when the physical link is down. Floating VEBs don't need 449to connect to the NIC port so they can still forward traffic from VF to VF 450even when the physical link is down. 451 452Therefore, with this feature enabled VFs can be limited to communicating with 453each other but not an outside network, and they can do so even when there is 454no physical uplink on the associated NIC port. 455 456To enable this feature, the user should pass a ``devargs`` parameter to the 457EAL, for example:: 458 459 -a 84:00.0,enable_floating_veb=1 460 461In this configuration the PMD will use the floating VEB feature for all the 462VFs created by this PF device. 463 464Alternatively, the user can specify which VFs need to connect to this floating 465VEB using the ``floating_veb_list`` argument:: 466 467 -a 84:00.0,enable_floating_veb=1,floating_veb_list=1;3-4 468 469In this example ``VF1``, ``VF3`` and ``VF4`` connect to the floating VEB, 470while other VFs connect to the normal VEB. 471 472The current implementation only supports one floating VEB and one regular 473VEB. VFs can connect to a floating VEB or a regular VEB according to the 474configuration passed on the EAL command line. 475 476The floating VEB functionality requires a NIC firmware version of 5.0 477or greater. 478 479Dynamic Device Personalization (DDP) 480~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 481 482The Intel® Ethernet 700 Series except for the Intel Ethernet Connection 483X722 support a feature called "Dynamic Device Personalization (DDP)", 484which is used to configure hardware by downloading a profile to support 485protocols/filters which are not supported by default. The DDP 486functionality requires a NIC firmware version of 6.0 or greater. 487 488Current implementation supports GTP-C/GTP-U/PPPoE/PPPoL2TP/ESP, 489steering can be used with rte_flow API. 490 491GTPv1 package is released, and it can be downloaded from 492https://downloadcenter.intel.com/download/27587. 493 494PPPoE package is released, and it can be downloaded from 495https://downloadcenter.intel.com/download/28040. 496 497ESP-AH package is released, and it can be downloaded from 498https://downloadcenter.intel.com/download/29446. 499 500Load a profile which supports GTP and store backup profile: 501 502.. code-block:: console 503 504 testpmd> ddp add 0 ./gtp.pkgo,./backup.pkgo 505 506Delete a GTP profile and restore backup profile: 507 508.. code-block:: console 509 510 testpmd> ddp del 0 ./backup.pkgo 511 512Get loaded DDP package info list: 513 514.. code-block:: console 515 516 testpmd> ddp get list 0 517 518Display information about a GTP profile: 519 520.. code-block:: console 521 522 testpmd> ddp get info ./gtp.pkgo 523 524Input set configuration 525~~~~~~~~~~~~~~~~~~~~~~~ 526Input set for any PCTYPE can be configured with user defined configuration, 527For example, to use only 48bit prefix for IPv6 src address for IPv6 TCP RSS: 528 529.. code-block:: console 530 531 testpmd> port config 0 pctype 43 hash_inset clear all 532 testpmd> port config 0 pctype 43 hash_inset set field 13 533 testpmd> port config 0 pctype 43 hash_inset set field 14 534 testpmd> port config 0 pctype 43 hash_inset set field 15 535 536Queue region configuration 537~~~~~~~~~~~~~~~~~~~~~~~~~~~ 538The Intel® Ethernet 700 Series supports a feature of queue regions 539configuration for RSS in the PF, so that different traffic classes or 540different packet classification types can be separated to different 541queues in different queue regions. There is an API for configuration 542of queue regions in RSS with a command line. It can parse the parameters 543of the region index, queue number, queue start index, user priority, traffic 544classes and so on. Depending on commands from the command line, it will call 545i40e private APIs and start the process of setting or flushing the queue 546region configuration. As this feature is specific for i40e only private 547APIs are used. These new ``test_pmd`` commands are as shown below. For 548details please refer to :doc:`../testpmd_app_ug/index`. 549 550.. code-block:: console 551 552 testpmd> set port (port_id) queue-region region_id (value) \ 553 queue_start_index (value) queue_num (value) 554 testpmd> set port (port_id) queue-region region_id (value) flowtype (value) 555 testpmd> set port (port_id) queue-region UP (value) region_id (value) 556 testpmd> set port (port_id) queue-region flush (on|off) 557 testpmd> show port (port_id) queue-region 558 559Generic flow API 560~~~~~~~~~~~~~~~~~~~ 561 562- ``RSS Flow`` 563 564 RSS Flow supports to set hash input set, hash function, enable hash 565 and configure queue region. 566 For example: 567 Configure queue region as queue 0, 1, 2, 3. 568 569 .. code-block:: console 570 571 testpmd> flow create 0 ingress pattern end actions rss types end \ 572 queues 0 1 2 3 end / end 573 574 Enable hash and set input set for ipv4-tcp. 575 576 .. code-block:: console 577 578 testpmd> flow create 0 ingress pattern eth / ipv4 / tcp / end \ 579 actions rss types ipv4-tcp l3-src-only end queues end / end 580 581 Set symmetric hash enable for flow type ipv4-tcp. 582 583 .. code-block:: console 584 585 testpmd> flow create 0 ingress pattern eth / ipv4 / tcp / end \ 586 actions rss types ipv4-tcp end queues end func symmetric_toeplitz / end 587 588 Set hash function as simple xor. 589 590 .. code-block:: console 591 592 testpmd> flow create 0 ingress pattern end actions rss types end \ 593 queues end func simple_xor / end 594 595Limitations or Known issues 596--------------------------- 597 598MPLS packet classification 599~~~~~~~~~~~~~~~~~~~~~~~~~~ 600 601For firmware versions prior to 5.0, MPLS packets are not recognized by the NIC. 602The L2 Payload flow type in flow director can be used to classify MPLS packet 603by using a command in testpmd like: 604 605 testpmd> flow_director_filter 0 mode IP add flow l2_payload ether \ 606 0x8847 flexbytes () fwd pf queue <N> fd_id <M> 607 608With the NIC firmware version 5.0 or greater, some limited MPLS support 609is added: Native MPLS (MPLS in Ethernet) skip is implemented, while no 610new packet type, no classification or offload are possible. With this change, 611L2 Payload flow type in flow director cannot be used to classify MPLS packet 612as with previous firmware versions. Meanwhile, the Ethertype filter can be 613used to classify MPLS packet by using a command in testpmd like: 614 615 testpmd> flow create 0 ingress pattern eth type is 0x8847 / end \ 616 actions queue index <M> / end 617 61816 Byte RX Descriptor setting on DPDK VF 619~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 620 621Currently the VF's RX descriptor mode is decided by PF. There's no PF-VF 622interface for VF to request the RX descriptor mode, also no interface to notify 623VF its own RX descriptor mode. 624For all available versions of the i40e driver, these drivers don't support 16 625byte RX descriptor. If the Linux i40e kernel driver is used as host driver, 626while DPDK i40e PMD is used as the VF driver, DPDK cannot choose 16 byte receive 627descriptor. The reason is that the RX descriptor is already set to 32 byte by 628the i40e kernel driver. 629In the future, if the Linux i40e driver supports 16 byte RX descriptor, user 630should make sure the DPDK VF uses the same RX descriptor mode, 16 byte or 32 631byte, as the PF driver. 632 633The same rule for DPDK PF + DPDK VF. The PF and VF should use the same RX 634descriptor mode. Or the VF RX will not work. 635 636Receive packets with Ethertype 0x88A8 637~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 638 639Due to the FW limitation, PF can receive packets with Ethertype 0x88A8 640only when floating VEB is disabled. 641 642Incorrect Rx statistics when packet is oversize 643~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 644 645When a packet is over maximum frame size, the packet is dropped. 646However, the Rx statistics, when calling `rte_eth_stats_get` incorrectly 647shows it as received. 648 649RX/TX statistics may be incorrect when register overflowed 650~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 651 652The rx_bytes/tx_bytes statistics register is 48 bit length. 653Although this limitation is enlarged to 64 bit length on the software side, 654but there is no way to detect if the overflow occurred more than once. 655So rx_bytes/tx_bytes statistics data is correct when statistics are 656updated at least once between two overflows. 657 658VF & TC max bandwidth setting 659~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 660 661The per VF max bandwidth and per TC max bandwidth cannot be enabled in parallel. 662The behavior is different when handling per VF and per TC max bandwidth setting. 663When enabling per VF max bandwidth, SW will check if per TC max bandwidth is 664enabled. If so, return failure. 665When enabling per TC max bandwidth, SW will check if per VF max bandwidth 666is enabled. If so, disable per VF max bandwidth and continue with per TC max 667bandwidth setting. 668 669TC TX scheduling mode setting 670~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 671 672There are 2 TX scheduling modes for TCs, round robin and strict priority mode. 673If a TC is set to strict priority mode, it can consume unlimited bandwidth. 674It means if APP has set the max bandwidth for that TC, it comes to no 675effect. 676It's suggested to set the strict priority mode for a TC that is latency 677sensitive but no consuming much bandwidth. 678 679VF performance is impacted by PCI extended tag setting 680~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 681 682To reach maximum NIC performance in the VF the PCI extended tag must be 683enabled. The DPDK i40e PF driver will set this feature during initialization, 684but the kernel PF driver does not. So when running traffic on a VF which is 685managed by the kernel PF driver, a significant NIC performance downgrade has 686been observed (for 64 byte packets, there is about 25% line-rate downgrade for 687a 25GbE device and about 35% for a 40GbE device). 688 689For kernel version >= 4.11, the kernel's PCI driver will enable the extended 690tag if it detects that the device supports it. So by default, this is not an 691issue. For kernels <= 4.11 or when the PCI extended tag is disabled it can be 692enabled using the steps below. 693 694#. Get the current value of the PCI configure register:: 695 696 setpci -s <XX:XX.X> a8.w 697 698#. Set bit 8:: 699 700 value = value | 0x100 701 702#. Set the PCI configure register with new value:: 703 704 setpci -s <XX:XX.X> a8.w=<value> 705 706Vlan strip of VF 707~~~~~~~~~~~~~~~~ 708 709The VF vlan strip function is only supported in the i40e kernel driver >= 2.1.26. 710 711DCB function 712~~~~~~~~~~~~ 713 714DCB works only when RSS is enabled. 715 716Global configuration warning 717~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 718 719I40E PMD will set some global registers to enable some function or set some 720configure. Then when using different ports of the same NIC with Linux kernel 721and DPDK, the port with Linux kernel will be impacted by the port with DPDK. 722For example, register I40E_GL_SWT_L2TAGCTRL is used to control L2 tag, i40e 723PMD uses I40E_GL_SWT_L2TAGCTRL to set vlan TPID. If setting TPID in port A 724with DPDK, then the configuration will also impact port B in the NIC with 725kernel driver, which don't want to use the TPID. 726So PMD reports warning to clarify what is changed by writing global register. 727 728Cloud Filter 729~~~~~~~~~~~~ 730 731When programming cloud filters for IPv4/6_UDP/TCP/SCTP with SRC port only or DST port only, 732it will make any cloud filter using inner_vlan or tunnel key invalid. Default configuration will be 733recovered only by NIC core reset. 734 735High Performance of Small Packets on 40GbE NIC 736---------------------------------------------- 737 738As there might be firmware fixes for performance enhancement in latest version 739of firmware image, the firmware update might be needed for getting high performance. 740Check the Intel support website for the latest firmware updates. 741Users should consult the release notes specific to a DPDK release to identify 742the validated firmware version for a NIC using the i40e driver. 743 744Use 16 Bytes RX Descriptor Size 745~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 746 747As i40e PMD supports both 16 and 32 bytes RX descriptor sizes, and 16 bytes size can provide helps to high performance of small packets. 748In ``config/rte_config.h`` set the following to use 16 bytes size RX descriptors:: 749 750 #define RTE_LIBRTE_I40E_16BYTE_RX_DESC 1 751 752Input set requirement of each pctype for FDIR 753~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 754 755Each PCTYPE can only have one specific FDIR input set at one time. 756For example, if creating 2 rte_flow rules with different input set for one PCTYPE, 757it will fail and return the info "Conflict with the first rule's input set", 758which means the current rule's input set conflicts with the first rule's. 759Remove the first rule if want to change the input set of the PCTYPE. 760 761Example of getting best performance with l3fwd example 762------------------------------------------------------ 763 764The following is an example of running the DPDK ``l3fwd`` sample application to get high performance with a 765server with Intel Xeon processors and Intel Ethernet CNA XL710. 766 767The example scenario is to get best performance with two Intel Ethernet CNA XL710 40GbE ports. 768See :numref:`figure_intel_perf_test_setup` for the performance test setup. 769 770.. _figure_intel_perf_test_setup: 771 772.. figure:: img/intel_perf_test_setup.* 773 774 Performance Test Setup 775 776 7771. Add two Intel Ethernet CNA XL710 to the platform, and use one port per card to get best performance. 778 The reason for using two NICs is to overcome a PCIe v3.0 limitation since it cannot provide 80GbE bandwidth 779 for two 40GbE ports, but two different PCIe v3.0 x8 slot can. 780 Refer to the sample NICs output above, then we can select ``82:00.0`` and ``85:00.0`` as test ports:: 781 782 82:00.0 Ethernet [0200]: Intel XL710 for 40GbE QSFP+ [8086:1583] 783 85:00.0 Ethernet [0200]: Intel XL710 for 40GbE QSFP+ [8086:1583] 784 7852. Connect the ports to the traffic generator. For high speed testing, it's best to use a hardware traffic generator. 786 7873. Check the PCI devices numa node (socket id) and get the cores number on the exact socket id. 788 In this case, ``82:00.0`` and ``85:00.0`` are both in socket 1, and the cores on socket 1 in the referenced platform 789 are 18-35 and 54-71. 790 Note: Don't use 2 logical cores on the same core (e.g core18 has 2 logical cores, core18 and core54), instead, use 2 logical 791 cores from different cores (e.g core18 and core19). 792 7934. Bind these two ports to igb_uio. 794 7955. As to Intel Ethernet CNA XL710 40GbE port, we need at least two queue pairs to achieve best performance, then two queues per port 796 will be required, and each queue pair will need a dedicated CPU core for receiving/transmitting packets. 797 7986. The DPDK sample application ``l3fwd`` will be used for performance testing, with using two ports for bi-directional forwarding. 799 Compile the ``l3fwd sample`` with the default lpm mode. 800 8017. The command line of running l3fwd would be something like the following:: 802 803 ./dpdk-l3fwd -l 18-21 -n 4 -a 82:00.0 -a 85:00.0 \ 804 -- -p 0x3 --config '(0,0,18),(0,1,19),(1,0,20),(1,1,21)' 805 806 This means that the application uses core 18 for port 0, queue pair 0 forwarding, core 19 for port 0, queue pair 1 forwarding, 807 core 20 for port 1, queue pair 0 forwarding, and core 21 for port 1, queue pair 1 forwarding. 808 8098. Configure the traffic at a traffic generator. 810 811 * Start creating a stream on packet generator. 812 813 * Set the Ethernet II type to 0x0800. 814 815Tx bytes affected by the link status change 816~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 817 818For firmware versions prior to 6.01 for X710 series and 3.33 for X722 series, the tx_bytes statistics data is affected by 819the link down event. Each time the link status changes to down, the tx_bytes decreases 110 bytes. 820