1.. SPDX-License-Identifier: BSD-3-Clause 2 Copyright(c) 2010-2016 Intel Corporation. 3 4.. _testpmd_runtime: 5 6Testpmd Runtime Functions 7========================= 8 9Where the testpmd application is started in interactive mode, (``-i|--interactive``), 10it displays a prompt that can be used to start and stop forwarding, 11configure the application, display statistics (including the extended NIC 12statistics aka xstats) , set the Flow Director and other tasks:: 13 14 testpmd> 15 16The testpmd prompt has some, limited, readline support. 17Common bash command-line functions such as ``Ctrl+a`` and ``Ctrl+e`` to go to the start and end of the prompt line are supported 18as well as access to the command history via the up-arrow. 19 20There is also support for tab completion. 21If you type a partial command and hit ``<TAB>`` you get a list of the available completions: 22 23.. code-block:: console 24 25 testpmd> show port <TAB> 26 27 info [Mul-choice STRING]: show|clear port info|stats|xstats|fdir|dcb_tc|cap X 28 info [Mul-choice STRING]: show|clear port info|stats|xstats|fdir|dcb_tc|cap all 29 stats [Mul-choice STRING]: show|clear port info|stats|xstats|fdir|dcb_tc|cap X 30 stats [Mul-choice STRING]: show|clear port info|stats|xstats|fdir|dcb_tc|cap all 31 ... 32 33 34.. note:: 35 36 Some examples in this document are too long to fit on one line are shown wrapped at `"\\"` for display purposes:: 37 38 testpmd> set flow_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \ 39 (pause_time) (send_xon) (port_id) 40 41In the real ``testpmd>`` prompt these commands should be on a single line. 42 43Help Functions 44-------------- 45 46The testpmd has on-line help for the functions that are available at runtime. 47These are divided into sections and can be accessed using help, help section or help all: 48 49.. code-block:: console 50 51 testpmd> help 52 Help is available for the following sections: 53 54 help control : Start and stop forwarding. 55 help display : Displaying port, stats and config information. 56 help config : Configuration information. 57 help ports : Configuring ports. 58 help filters : Filters configuration help. 59 help traffic_management : Traffic Management commands. 60 help devices : Device related commands. 61 help drivers : Driver specific commands. 62 help all : All of the above sections. 63 64Command File Functions 65---------------------- 66 67To facilitate loading large number of commands or to avoid cutting and pasting where not 68practical or possible testpmd supports alternative methods for executing commands. 69 70* If started with the ``--cmdline-file=FILENAME`` command line argument testpmd 71 will execute all CLI commands contained within the file immediately before 72 starting packet forwarding or entering interactive mode. 73 74.. code-block:: console 75 76 ./dpdk-testpmd -n4 -r2 ... -- -i --cmdline-file=/home/ubuntu/flow-create-commands.txt 77 Interactive-mode selected 78 CLI commands to be read from /home/ubuntu/flow-create-commands.txt 79 Configuring Port 0 (socket 0) 80 Port 0: 7C:FE:90:CB:74:CE 81 Configuring Port 1 (socket 0) 82 Port 1: 7C:FE:90:CB:74:CA 83 Checking link statuses... 84 Port 0 Link Up - speed 10000 Mbps - full-duplex 85 Port 1 Link Up - speed 10000 Mbps - full-duplex 86 Done 87 Flow rule #0 created 88 Flow rule #1 created 89 ... 90 ... 91 Flow rule #498 created 92 Flow rule #499 created 93 Read all CLI commands from /home/ubuntu/flow-create-commands.txt 94 testpmd> 95 96 97* At run-time additional commands can be loaded in bulk by invoking the ``load FILENAME`` 98 command. 99 100.. code-block:: console 101 102 testpmd> load /home/ubuntu/flow-create-commands.txt 103 Flow rule #0 created 104 Flow rule #1 created 105 ... 106 ... 107 Flow rule #498 created 108 Flow rule #499 created 109 Read all CLI commands from /home/ubuntu/flow-create-commands.txt 110 testpmd> 111 112 113In all cases output from any included command will be displayed as standard output. 114Execution will continue until the end of the file is reached regardless of 115whether any errors occur. The end user must examine the output to determine if 116any failures occurred. 117 118 119Control Functions 120----------------- 121 122start 123~~~~~ 124 125Start packet forwarding with current configuration:: 126 127 testpmd> start 128 129start tx_first 130~~~~~~~~~~~~~~ 131 132Start packet forwarding with current configuration after sending specified number of bursts of packets:: 133 134 testpmd> start tx_first (""|burst_num) 135 136The default burst number is 1 when ``burst_num`` not presented. 137 138stop 139~~~~ 140 141Stop packet forwarding, and display accumulated statistics:: 142 143 testpmd> stop 144 145quit 146~~~~ 147 148Quit to prompt:: 149 150 testpmd> quit 151 152 153Display Functions 154----------------- 155 156The functions in the following sections are used to display information about the 157testpmd configuration or the NIC status. 158 159show port 160~~~~~~~~~ 161 162Display information for a given port or all ports:: 163 164 testpmd> show port (info|summary|stats|xstats|fdir|dcb_tc|cap) (port_id|all) 165 166The available information categories are: 167 168* ``info``: General port information such as MAC address. 169 170* ``summary``: Brief port summary such as Device Name, Driver Name etc. 171 172* ``stats``: RX/TX statistics. 173 174* ``xstats``: RX/TX extended NIC statistics. 175 176* ``fdir``: Flow Director information and statistics. 177 178* ``dcb_tc``: DCB information such as TC mapping. 179 180For example: 181 182.. code-block:: console 183 184 testpmd> show port info 0 185 186 ********************* Infos for port 0 ********************* 187 188 MAC address: XX:XX:XX:XX:XX:XX 189 Connect to socket: 0 190 memory allocation on the socket: 0 191 Link status: up 192 Link speed: 40000 Mbps 193 Link duplex: full-duplex 194 Promiscuous mode: enabled 195 Allmulticast mode: disabled 196 Maximum number of MAC addresses: 64 197 Maximum number of MAC addresses of hash filtering: 0 198 VLAN offload: 199 strip on, filter on, extend off, qinq strip off 200 Redirection table size: 512 201 Supported flow types: 202 ipv4-frag 203 ipv4-tcp 204 ipv4-udp 205 ipv4-sctp 206 ipv4-other 207 ipv6-frag 208 ipv6-tcp 209 ipv6-udp 210 ipv6-sctp 211 ipv6-other 212 l2_payload 213 port 214 vxlan 215 geneve 216 nvgre 217 vxlan-gpe 218 219show port (module_eeprom|eeprom) 220~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 221 222Display the EEPROM information of a port:: 223 224 testpmd> show port (port_id) (module_eeprom|eeprom) 225 226show port rss reta 227~~~~~~~~~~~~~~~~~~ 228 229Display the rss redirection table entry indicated by masks on port X:: 230 231 testpmd> show port (port_id) rss reta (size) (mask0, mask1...) 232 233size is used to indicate the hardware supported reta size 234 235show port rss-hash 236~~~~~~~~~~~~~~~~~~ 237 238Display the RSS hash functions and RSS hash key of a port:: 239 240 testpmd> show port (port_id) rss-hash [key] 241 242clear port 243~~~~~~~~~~ 244 245Clear the port statistics and forward engine statistics for a given port or for all ports:: 246 247 testpmd> clear port (info|stats|xstats|fdir) (port_id|all) 248 249For example:: 250 251 testpmd> clear port stats all 252 253show (rxq|txq) 254~~~~~~~~~~~~~~ 255 256Display information for a given port's RX/TX queue:: 257 258 testpmd> show (rxq|txq) info (port_id) (queue_id) 259 260show desc status(rxq|txq) 261~~~~~~~~~~~~~~~~~~~~~~~~~ 262 263Display information for a given port's RX/TX descriptor status:: 264 265 testpmd> show port (port_id) (rxq|txq) (queue_id) desc (desc_id) status 266 267show rxq desc used count 268~~~~~~~~~~~~~~~~~~~~~~~~ 269 270Display the number of receive packet descriptors currently filled by hardware 271and ready to be processed by the driver on a given RX queue:: 272 273 testpmd> show port (port_id) rxq (queue_id) desc used count 274 275show config 276~~~~~~~~~~~ 277 278Displays the configuration of the application. 279The configuration comes from the command-line, the runtime or the application defaults:: 280 281 testpmd> show config (rxtx|cores|fwd|rxoffs|rxpkts|rxhdrs|txpkts|txtimes) 282 283The available information categories are: 284 285* ``rxtx``: RX/TX configuration items. 286 287* ``cores``: List of forwarding cores. 288 289* ``fwd``: Packet forwarding configuration. 290 291* ``rxoffs``: Packet offsets for RX split. 292 293* ``rxpkts``: Packets to RX length-based split configuration. 294 295* ``rxhdrs``: Packets to RX proto-based split configuration. 296 297* ``txpkts``: Packets to TX configuration. 298 299* ``txtimes``: Burst time pattern for Tx only mode. 300 301For example: 302 303.. code-block:: console 304 305 testpmd> show config rxtx 306 307 io packet forwarding - CRC stripping disabled - packets/burst=16 308 nb forwarding cores=2 - nb forwarding ports=1 309 RX queues=1 - RX desc=128 - RX free threshold=0 310 RX threshold registers: pthresh=8 hthresh=8 wthresh=4 311 TX queues=1 - TX desc=512 - TX free threshold=0 312 TX threshold registers: pthresh=36 hthresh=0 wthresh=0 313 TX RS bit threshold=0 - TXQ flags=0x0 314 315set fwd 316~~~~~~~ 317 318Set the packet forwarding mode:: 319 320 testpmd> set fwd (io|mac|macswap|flowgen| \ 321 rxonly|txonly|csum|icmpecho|noisy|5tswap|shared-rxq) (""|retry) 322 323``retry`` can be specified for forwarding engines except ``rx_only``. 324 325The available information categories are: 326 327* ``io``: Forwards packets "as-is" in I/O mode. 328 This is the fastest possible forwarding operation as it does not access packets data. 329 This is the default mode. 330 331* ``mac``: Changes the source and the destination Ethernet addresses of packets before forwarding them. 332 Default application behavior is to set source Ethernet address to that of the transmitting interface, and destination 333 address to a dummy value (set during init). The user may specify a target destination Ethernet address via the 'eth-peer' or 334 'eth-peers-configfile' command-line options. It is not currently possible to specify a specific source Ethernet address. 335 336* ``macswap``: MAC swap forwarding mode. 337 Swaps the source and the destination Ethernet addresses of packets before forwarding them. 338 339* ``flowgen``: Multi-flow generation mode. 340 Originates a number of flows (with varying destination IP addresses), and terminate receive traffic. 341 342* ``rxonly``: Receives packets but doesn't transmit them. 343 344* ``txonly``: Generates and transmits packets without receiving any. 345 346* ``csum``: Changes the checksum field with hardware or software methods depending on the offload flags on the packet. 347 348* ``icmpecho``: Receives a burst of packets, lookup for ICMP echo requests and, if any, send back ICMP echo replies. 349 350* ``ieee1588``: Demonstrate L2 IEEE1588 V2 PTP timestamping for RX and TX. 351 352* ``noisy``: Noisy neighbor simulation. 353 Simulate more realistic behavior of a guest machine engaged in receiving 354 and sending packets performing Virtual Network Function (VNF). 355 356* ``5tswap``: Swap the source and destination of L2,L3,L4 if they exist. 357 358 L2 swaps the source address and destination address of Ethernet, as same as ``macswap``. 359 360 L3 swaps the source address and destination address of IP (v4 and v6). 361 362 L4 swaps the source port and destination port of transport layer (TCP and UDP). 363 364* ``shared-rxq``: Receive only for shared Rx queue. 365 Resolve packet source port from mbuf and update stream statistics accordingly. 366 367Example:: 368 369 testpmd> set fwd rxonly 370 371 Set rxonly packet forwarding mode 372 373 374show fwd 375~~~~~~~~ 376 377When running, forwarding engines maintain statistics from the time they have been started. 378Example for the io forwarding engine, with some packet drops on the tx side:: 379 380 testpmd> show fwd stats all 381 382 ------- Forward Stats for RX Port= 0/Queue= 0 -> TX Port= 1/Queue= 0 ------- 383 RX-packets: 274293770 TX-packets: 274293642 TX-dropped: 128 384 385 ------- Forward Stats for RX Port= 1/Queue= 0 -> TX Port= 0/Queue= 0 ------- 386 RX-packets: 274301850 TX-packets: 274301850 TX-dropped: 0 387 388 ---------------------- Forward statistics for port 0 ---------------------- 389 RX-packets: 274293802 RX-dropped: 0 RX-total: 274293802 390 TX-packets: 274301862 TX-dropped: 0 TX-total: 274301862 391 ---------------------------------------------------------------------------- 392 393 ---------------------- Forward statistics for port 1 ---------------------- 394 RX-packets: 274301894 RX-dropped: 0 RX-total: 274301894 395 TX-packets: 274293706 TX-dropped: 128 TX-total: 274293834 396 ---------------------------------------------------------------------------- 397 398 +++++++++++++++ Accumulated forward statistics for all ports+++++++++++++++ 399 RX-packets: 548595696 RX-dropped: 0 RX-total: 548595696 400 TX-packets: 548595568 TX-dropped: 128 TX-total: 548595696 401 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 402 403 404clear fwd 405~~~~~~~~~ 406 407Clear the forwarding engines statistics:: 408 409 testpmd> clear fwd stats all 410 411read rxd 412~~~~~~~~ 413 414Display an RX descriptor for a port RX queue:: 415 416 testpmd> read rxd (port_id) (queue_id) (rxd_id) 417 418For example:: 419 420 testpmd> read rxd 0 0 4 421 0x0000000B - 0x001D0180 / 0x0000000B - 0x001D0180 422 423read txd 424~~~~~~~~ 425 426Display a TX descriptor for a port TX queue:: 427 428 testpmd> read txd (port_id) (queue_id) (txd_id) 429 430For example:: 431 432 testpmd> read txd 0 0 4 433 0x00000001 - 0x24C3C440 / 0x000F0000 - 0x2330003C 434 435show vf stats 436~~~~~~~~~~~~~ 437 438Display VF statistics:: 439 440 testpmd> show vf stats (port_id) (vf_id) 441 442clear vf stats 443~~~~~~~~~~~~~~ 444 445Reset VF statistics:: 446 447 testpmd> clear vf stats (port_id) (vf_id) 448 449show rx offloading capabilities 450~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 451 452List all per queue and per port Rx offloading capabilities of a port:: 453 454 testpmd> show port (port_id) rx_offload capabilities 455 456show rx offloading configuration 457~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 458 459List port level and all queue level Rx offloading configuration:: 460 461 testpmd> show port (port_id) rx_offload configuration 462 463show tx offloading capabilities 464~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 465 466List all per queue and per port Tx offloading capabilities of a port:: 467 468 testpmd> show port (port_id) tx_offload capabilities 469 470show tx offloading configuration 471~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 472 473List port level and all queue level Tx offloading configuration:: 474 475 testpmd> show port (port_id) tx_offload configuration 476 477show tx metadata setting 478~~~~~~~~~~~~~~~~~~~~~~~~ 479 480Show Tx metadata value set for a specific port:: 481 482 testpmd> show port (port_id) tx_metadata 483 484show port supported ptypes 485~~~~~~~~~~~~~~~~~~~~~~~~~~ 486 487Show ptypes supported for a specific port:: 488 489 testpmd> show port (port_id) ptypes 490 491set port supported ptypes 492~~~~~~~~~~~~~~~~~~~~~~~~~ 493 494set packet types classification for a specific port:: 495 496 testpmd> set port (port_id) ptypes_mask (mask) 497 498show port mac addresses info 499~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 500 501Show mac addresses added for a specific port:: 502 503 testpmd> show port (port_id) macs 504 505 506show port multicast mac addresses info 507~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 508 509Show multicast mac addresses added for a specific port:: 510 511 testpmd> show port (port_id) mcast_macs 512 513show flow transfer proxy port ID for the given port 514~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 515 516Show proxy port ID to use as the 1st argument in commands to 517manage ``transfer`` flows and their indirect components. 518:: 519 520 testpmd> show port (port_id) flow transfer proxy 521 522show device info 523~~~~~~~~~~~~~~~~ 524 525Show general information about devices probed:: 526 527 testpmd> show device info (<identifier>|all) 528 529For example: 530 531.. code-block:: console 532 533 testpmd> show device info net_pcap0 534 535 ********************* Infos for device net_pcap0 ********************* 536 Bus name: vdev 537 Driver name: net_pcap 538 Devargs: iface=enP2p6s0,phy_mac=1 539 Connect to socket: -1 540 541 Port id: 2 542 MAC address: 1E:37:93:28:04:B8 543 Device name: net_pcap0 544 545dump physmem 546~~~~~~~~~~~~ 547 548Dumps all physical memory segment layouts:: 549 550 testpmd> dump_physmem 551 552dump memzone 553~~~~~~~~~~~~ 554 555Dumps the layout of all memory zones:: 556 557 testpmd> dump_memzone 558 559dump socket memory 560~~~~~~~~~~~~~~~~~~ 561 562Dumps the memory usage of all sockets:: 563 564 testpmd> dump_socket_mem 565 566dump struct size 567~~~~~~~~~~~~~~~~ 568 569Dumps the size of all memory structures:: 570 571 testpmd> dump_struct_sizes 572 573dump ring 574~~~~~~~~~ 575 576Dumps the status of all or specific element in DPDK rings:: 577 578 testpmd> dump_ring [ring_name] 579 580dump mempool 581~~~~~~~~~~~~ 582 583Dumps the statistics of all or specific memory pool:: 584 585 testpmd> dump_mempool [mempool_name] 586 587dump devargs 588~~~~~~~~~~~~ 589 590Dumps the user device list:: 591 592 testpmd> dump_devargs 593 594dump lcores 595~~~~~~~~~~~ 596 597Dumps the logical cores list:: 598 599 testpmd> dump_lcores 600 601dump log types 602~~~~~~~~~~~~~~ 603 604Dumps the log level for all the dpdk modules:: 605 606 testpmd> dump_log_types 607 608show (raw_encap|raw_decap) 609~~~~~~~~~~~~~~~~~~~~~~~~~~ 610 611Display content of raw_encap/raw_decap buffers in hex:: 612 613 testpmd> show <raw_encap|raw_decap> <index> 614 testpmd> show <raw_encap|raw_decap> all 615 616For example:: 617 618 testpmd> show raw_encap 6 619 620 index: 6 at [0x1c565b0], len=50 621 00000000: 00 00 00 00 00 00 16 26 36 46 56 66 08 00 45 00 | .......&6FVf..E. 622 00000010: 00 00 00 00 00 00 00 11 00 00 C0 A8 01 06 C0 A8 | ................ 623 00000020: 03 06 00 00 00 FA 00 00 00 00 08 00 00 00 00 00 | ................ 624 00000030: 06 00 | .. 625 626show fec capabilities 627~~~~~~~~~~~~~~~~~~~~~ 628 629Show fec capabilities of a port:: 630 631 testpmd> show port (port_id) fec capabilities 632 633show fec mode 634~~~~~~~~~~~~~ 635 636Show fec mode of a port:: 637 638 testpmd> show port (port_id) fec_mode 639 640 641Configuration Functions 642----------------------- 643 644The testpmd application can be configured from the runtime as well as from the command-line. 645 646This section details the available configuration functions that are available. 647 648.. note:: 649 650 Configuration changes only become active when forwarding is started/restarted. 651 652set default 653~~~~~~~~~~~ 654 655Reset forwarding to the default configuration:: 656 657 testpmd> set default 658 659set verbose 660~~~~~~~~~~~ 661 662Set the debug verbosity level:: 663 664 testpmd> set verbose (level) 665 666Available levels are as following: 667 668* ``0`` silent except for error. 669* ``1`` fully verbose except for Tx packets. 670* ``2`` fully verbose except for Rx packets. 671* ``> 2`` fully verbose. 672 673set log 674~~~~~~~ 675 676Set the log level for a log type:: 677 678 testpmd> set log global|(type) (level) 679 680Where: 681 682* ``type`` is the log name. 683 684* ``level`` is the log level. 685 686For example, to change the global log level:: 687 688 testpmd> set log global (level) 689 690Regexes can also be used for type. To change log level of user1, user2 and user3:: 691 692 testpmd> set log user[1-3] (level) 693 694set nbport 695~~~~~~~~~~ 696 697Set the number of ports used by the application: 698 699set nbport (num) 700 701This is equivalent to the ``--nb-ports`` command-line option. 702 703set nbcore 704~~~~~~~~~~ 705 706Set the number of cores used by the application:: 707 708 testpmd> set nbcore (num) 709 710This is equivalent to the ``--nb-cores`` command-line option. 711 712.. note:: 713 714 The number of cores used must not be greater than number of ports used multiplied by the number of queues per port. 715 716set coremask 717~~~~~~~~~~~~ 718 719Set the forwarding cores hexadecimal mask:: 720 721 testpmd> set coremask (mask) 722 723This is equivalent to the ``--coremask`` command-line option. 724 725.. note:: 726 727 The main lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. 728 729set portmask 730~~~~~~~~~~~~ 731 732Set the forwarding ports hexadecimal mask:: 733 734 testpmd> set portmask (mask) 735 736This is equivalent to the ``--portmask`` command-line option. 737 738set record-core-cycles 739~~~~~~~~~~~~~~~~~~~~~~ 740 741Set the recording of CPU cycles:: 742 743 testpmd> set record-core-cycles (on|off) 744 745Where: 746 747* ``on`` enables measurement of CPU cycles per packet. 748 749* ``off`` disables measurement of CPU cycles per packet. 750 751This is equivalent to the ``--record-core-cycles command-line`` option. 752 753set record-burst-stats 754~~~~~~~~~~~~~~~~~~~~~~ 755 756Set the displaying of RX and TX bursts:: 757 758 testpmd> set record-burst-stats (on|off) 759 760Where: 761 762* ``on`` enables display of RX and TX bursts. 763 764* ``off`` disables display of RX and TX bursts. 765 766This is equivalent to the ``--record-burst-stats command-line`` option. 767 768set burst 769~~~~~~~~~ 770 771Set number of packets per burst:: 772 773 testpmd> set burst (num) 774 775This is equivalent to the ``--burst command-line`` option. 776 777When retry is enabled, the transmit delay time and number of retries can also be set:: 778 779 testpmd> set burst tx delay (microseconds) retry (num) 780 781set rxoffs 782~~~~~~~~~~ 783 784Set the offsets of segments relating to the data buffer beginning on receiving 785if split feature is engaged. Affects only the queues configured with split 786offloads (currently BUFFER_SPLIT is supported only). 787 788 testpmd> set rxoffs (x[,y]*) 789 790Where x[,y]* represents a CSV list of values, without white space. If the list 791of offsets is shorter than the list of segments the zero offsets will be used 792for the remaining segments. 793 794set rxpkts 795~~~~~~~~~~ 796 797Set the length of segments to scatter packets on receiving if split 798feature is engaged. Affects only the queues configured with split offloads 799(currently BUFFER_SPLIT is supported only). Optionally the multiple memory 800pools can be specified with --mbuf-size command line parameter and the mbufs 801to receive will be allocated sequentially from these extra memory pools (the 802mbuf for the first segment is allocated from the first pool, the second one 803from the second pool, and so on, if segment number is greater then pool's the 804mbuf for remaining segments will be allocated from the last valid pool). 805 806 testpmd> set rxpkts (x[,y]*) 807 808Where x[,y]* represents a CSV list of values, without white space. Zero value 809means to use the corresponding memory pool data buffer size. 810 811set rxhdrs 812~~~~~~~~~~ 813 814Set the protocol headers of segments to scatter packets on receiving 815if split feature is engaged. 816Affects only the queues configured with split offloads 817(currently BUFFER_SPLIT is supported only). 818 819 testpmd> set rxhdrs (eth[,ipv4]*) 820 821Where eth[,ipv4]* represents a CSV list of values, without white space. 822If the list of offsets is shorter than the list of segments, 823zero offsets will be used for the remaining segments. 824 825set txpkts 826~~~~~~~~~~ 827 828Set the length of each segment of the TX-ONLY packets or length of packet for FLOWGEN mode:: 829 830 testpmd> set txpkts (x[,y]*) 831 832Where x[,y]* represents a CSV list of values, without white space. 833 834set txtimes 835~~~~~~~~~~~ 836 837Configure the timing burst pattern for Tx only mode. This command enables 838the packet send scheduling on dynamic timestamp mbuf field and configures 839timing pattern in Tx only mode. In this mode, if scheduling is enabled 840application provides timestamps in the packets being sent. It is possible 841to configure delay (in unspecified device clock units) between bursts 842and between the packets within the burst:: 843 844 testpmd> set txtimes (inter),(intra) 845 846where: 847 848* ``inter`` is the delay between the bursts in the device clock units. 849 If ``intra`` is zero, this is the time between the beginnings of the 850 first packets in the neighbour bursts, if ``intra`` is not zero, 851 ``inter`` specifies the time between the beginning of the first packet 852 of the current burst and the beginning of the last packet of the 853 previous burst. If ``inter`` parameter is zero the send scheduling 854 on timestamps is disabled (default). 855 856* ``intra`` is the delay between the packets within the burst specified 857 in the device clock units. The number of packets in the burst is defined 858 by regular burst setting. If ``intra`` parameter is zero no timestamps 859 provided in the packets excepting the first one in the burst. 860 861As the result the bursts of packet will be transmitted with specific 862delays between the packets within the burst and specific delay between 863the bursts. The rte_eth_read_clock() must be supported by the device(s) 864and is supposed to be engaged to get the current device clock value 865and provide the reference for the timestamps. If there is no supported 866rte_eth_read_clock() there will be no send scheduling provided on the port. 867 868set txsplit 869~~~~~~~~~~~ 870 871Set the split policy for the TX packets, applicable for TX-ONLY and CSUM forwarding modes:: 872 873 testpmd> set txsplit (off|on|rand) 874 875Where: 876 877* ``off`` disable packet copy & split for CSUM mode. 878 879* ``on`` split outgoing packet into multiple segments. Size of each segment 880 and number of segments per packet is determined by ``set txpkts`` command 881 (see above). 882 883* ``rand`` same as 'on', but number of segments per each packet is a random value between 1 and total number of segments. 884 885set corelist 886~~~~~~~~~~~~ 887 888Set the list of forwarding cores:: 889 890 testpmd> set corelist (x[,y]*) 891 892For example, to change the forwarding cores: 893 894.. code-block:: console 895 896 testpmd> set corelist 3,1 897 testpmd> show config fwd 898 899 io packet forwarding - ports=2 - cores=2 - streams=2 - NUMA support disabled 900 Logical Core 3 (socket 0) forwards packets on 1 streams: 901 RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 902 Logical Core 1 (socket 0) forwards packets on 1 streams: 903 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00 904 905.. note:: 906 907 The cores are used in the same order as specified on the command line. 908 909set portlist 910~~~~~~~~~~~~ 911 912Set the list of forwarding ports:: 913 914 testpmd> set portlist (x[,y]*) 915 916For example, to change the port forwarding: 917 918.. code-block:: console 919 920 testpmd> set portlist 0,2,1,3 921 testpmd> show config fwd 922 923 io packet forwarding - ports=4 - cores=1 - streams=4 924 Logical Core 3 (socket 0) forwards packets on 4 streams: 925 RX P=0/Q=0 (socket 0) -> TX P=2/Q=0 (socket 0) peer=02:00:00:00:00:01 926 RX P=2/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00 927 RX P=1/Q=0 (socket 0) -> TX P=3/Q=0 (socket 0) peer=02:00:00:00:00:03 928 RX P=3/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:02 929 930set port setup on 931~~~~~~~~~~~~~~~~~ 932 933Select how to retrieve new ports created after "port attach" command:: 934 935 testpmd> set port setup on (iterator|event) 936 937For each new port, a setup is done. 938It will find the probed ports via RTE_ETH_FOREACH_MATCHING_DEV loop 939in iterator mode, or via RTE_ETH_EVENT_NEW in event mode. 940 941set tx loopback 942~~~~~~~~~~~~~~~ 943 944Enable/disable tx loopback:: 945 946 testpmd> set tx loopback (port_id) (on|off) 947 948set drop enable 949~~~~~~~~~~~~~~~ 950 951set drop enable bit for all queues:: 952 953 testpmd> set all queues drop (port_id) (on|off) 954 955set mac antispoof (for VF) 956~~~~~~~~~~~~~~~~~~~~~~~~~~ 957 958Set mac antispoof for a VF from the PF:: 959 960 testpmd> set vf mac antispoof (port_id) (vf_id) (on|off) 961 962vlan set stripq 963~~~~~~~~~~~~~~~ 964 965Set the VLAN strip for a queue on a port:: 966 967 testpmd> vlan set stripq (on|off) (port_id,queue_id) 968 969vlan set stripq (for VF) 970~~~~~~~~~~~~~~~~~~~~~~~~ 971 972Set VLAN strip for all queues in a pool for a VF from the PF:: 973 974 testpmd> set vf vlan stripq (port_id) (vf_id) (on|off) 975 976vlan set insert (for VF) 977~~~~~~~~~~~~~~~~~~~~~~~~ 978 979Set VLAN insert for a VF from the PF:: 980 981 testpmd> set vf vlan insert (port_id) (vf_id) (vlan_id) 982 983vlan set antispoof (for VF) 984~~~~~~~~~~~~~~~~~~~~~~~~~~~ 985 986Set VLAN antispoof for a VF from the PF:: 987 988 testpmd> set vf vlan antispoof (port_id) (vf_id) (on|off) 989 990vlan set (strip|filter|qinq_strip|extend) 991~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 992Set the VLAN strip/filter/QinQ strip/extend on for a port:: 993 994 testpmd> vlan set (strip|filter|qinq_strip|extend) (on|off) (port_id) 995 996vlan set tpid 997~~~~~~~~~~~~~ 998 999Set the inner or outer VLAN TPID for packet filtering on a port:: 1000 1001 testpmd> vlan set (inner|outer) tpid (value) (port_id) 1002 1003.. note:: 1004 1005 TPID value must be a 16-bit number (value <= 65536). 1006 1007rx_vlan add 1008~~~~~~~~~~~ 1009 1010Add a VLAN ID, or all identifiers, to the set of VLAN identifiers filtered by port ID:: 1011 1012 testpmd> rx_vlan add (vlan_id|all) (port_id) 1013 1014.. note:: 1015 1016 VLAN filter must be set on that port. VLAN ID < 4096. 1017 Depending on the NIC used, number of vlan_ids may be limited to the maximum entries 1018 in VFTA table. This is important if enabling all vlan_ids. 1019 1020rx_vlan rm 1021~~~~~~~~~~ 1022 1023Remove a VLAN ID, or all identifiers, from the set of VLAN identifiers filtered by port ID:: 1024 1025 testpmd> rx_vlan rm (vlan_id|all) (port_id) 1026 1027rx_vlan add (for VF) 1028~~~~~~~~~~~~~~~~~~~~ 1029 1030Add a VLAN ID, to the set of VLAN identifiers filtered for VF(s) for port ID:: 1031 1032 testpmd> rx_vlan add (vlan_id) port (port_id) vf (vf_mask) 1033 1034rx_vlan rm (for VF) 1035~~~~~~~~~~~~~~~~~~~ 1036 1037Remove a VLAN ID, from the set of VLAN identifiers filtered for VF(s) for port ID:: 1038 1039 testpmd> rx_vlan rm (vlan_id) port (port_id) vf (vf_mask) 1040 1041rx_vxlan_port add 1042~~~~~~~~~~~~~~~~~ 1043 1044Add an UDP port for VXLAN packet filter on a port:: 1045 1046 testpmd> rx_vxlan_port add (udp_port) (port_id) 1047 1048rx_vxlan_port remove 1049~~~~~~~~~~~~~~~~~~~~ 1050 1051Remove an UDP port for VXLAN packet filter on a port:: 1052 1053 testpmd> rx_vxlan_port rm (udp_port) (port_id) 1054 1055tx_vlan set 1056~~~~~~~~~~~ 1057 1058Set hardware insertion of VLAN IDs in packets sent on a port:: 1059 1060 testpmd> tx_vlan set (port_id) vlan_id[, vlan_id_outer] 1061 1062For example, set a single VLAN ID (5) insertion on port 0:: 1063 1064 tx_vlan set 0 5 1065 1066Or, set double VLAN ID (inner: 2, outer: 3) insertion on port 1:: 1067 1068 tx_vlan set 1 2 3 1069 1070 1071tx_vlan set pvid 1072~~~~~~~~~~~~~~~~ 1073 1074Set port based hardware insertion of VLAN ID in packets sent on a port:: 1075 1076 testpmd> tx_vlan set pvid (port_id) (vlan_id) (on|off) 1077 1078tx_vlan reset 1079~~~~~~~~~~~~~ 1080 1081Disable hardware insertion of a VLAN header in packets sent on a port:: 1082 1083 testpmd> tx_vlan reset (port_id) 1084 1085csum set 1086~~~~~~~~ 1087 1088Select hardware or software calculation of the checksum when 1089transmitting a packet using the ``csum`` forwarding engine:: 1090 1091 testpmd> csum set (ip|udp|tcp|sctp|outer-ip|outer-udp) (hw|sw) (port_id) 1092 1093Where: 1094 1095* ``ip|udp|tcp|sctp`` always relate to the inner layer. 1096 1097* ``outer-ip`` relates to the outer IP layer (only for IPv4) in the case where the packet is recognized 1098 as a tunnel packet by the forwarding engine (geneve, gre, gtp, ipip, vxlan and vxlan-gpe are 1099 supported). See also the ``csum parse-tunnel`` command. 1100 1101* ``outer-udp`` relates to the outer UDP layer in the case where the packet is recognized 1102 as a tunnel packet by the forwarding engine (geneve, gtp, vxlan and vxlan-gpe are 1103 supported). See also the ``csum parse-tunnel`` command. 1104 1105.. note:: 1106 1107 Check the NIC Datasheet for hardware limits. 1108 1109csum parse-tunnel 1110~~~~~~~~~~~~~~~~~ 1111 1112Define how tunneled packets should be handled by the csum forward 1113engine:: 1114 1115 testpmd> csum parse-tunnel (on|off) (tx_port_id) 1116 1117If enabled, the csum forward engine will try to recognize supported 1118tunnel headers (geneve, gtp, gre, ipip, vxlan, vxlan-gpe). 1119 1120If disabled, treat tunnel packets as non-tunneled packets (a inner 1121header is handled as a packet payload). 1122 1123.. note:: 1124 1125 The port argument is the TX port like in the ``csum set`` command. 1126 1127Example: 1128 1129Consider a packet in packet like the following:: 1130 1131 eth_out/ipv4_out/udp_out/vxlan/eth_in/ipv4_in/tcp_in 1132 1133* If parse-tunnel is enabled, the ``ip|udp|tcp|sctp`` parameters of ``csum set`` 1134 command relate to the inner headers (here ``ipv4_in`` and ``tcp_in``), and the 1135 ``outer-ip|outer-udp`` parameter relates to the outer headers (here ``ipv4_out`` and ``udp_out``). 1136 1137* If parse-tunnel is disabled, the ``ip|udp|tcp|sctp`` parameters of ``csum set`` 1138 command relate to the outer headers, here ``ipv4_out`` and ``udp_out``. 1139 1140csum show 1141~~~~~~~~~ 1142 1143Display tx checksum offload configuration:: 1144 1145 testpmd> csum show (port_id) 1146 1147tso set 1148~~~~~~~ 1149 1150Enable TCP Segmentation Offload (TSO) in the ``csum`` forwarding engine:: 1151 1152 testpmd> tso set (segsize) (port_id) 1153 1154.. note:: 1155 1156 Check the NIC datasheet for hardware limits. 1157 1158tso show 1159~~~~~~~~ 1160 1161Display the status of TCP Segmentation Offload:: 1162 1163 testpmd> tso show (port_id) 1164 1165tunnel tso set 1166~~~~~~~~~~~~~~ 1167 1168Set tso segment size of tunneled packets for a port in csum engine:: 1169 1170 testpmd> tunnel_tso set (tso_segsz) (port_id) 1171 1172tunnel tso show 1173~~~~~~~~~~~~~~~ 1174 1175Display the status of tunneled TCP Segmentation Offload for a port:: 1176 1177 testpmd> tunnel_tso show (port_id) 1178 1179set port - gro 1180~~~~~~~~~~~~~~ 1181 1182Enable or disable GRO in ``csum`` forwarding engine:: 1183 1184 testpmd> set port <port_id> gro on|off 1185 1186If enabled, the csum forwarding engine will perform GRO on the TCP/IPv4 1187packets received from the given port. 1188 1189If disabled, packets received from the given port won't be performed 1190GRO. By default, GRO is disabled for all ports. 1191 1192.. note:: 1193 1194 When enable GRO for a port, TCP/IPv4 packets received from the port 1195 will be performed GRO. After GRO, all merged packets have bad 1196 checksums, since the GRO library doesn't re-calculate checksums for 1197 the merged packets. Therefore, if users want the merged packets to 1198 have correct checksums, please select HW IP checksum calculation and 1199 HW TCP checksum calculation for the port which the merged packets are 1200 transmitted to. 1201 1202show port - gro 1203~~~~~~~~~~~~~~~ 1204 1205Display GRO configuration for a given port:: 1206 1207 testpmd> show port <port_id> gro 1208 1209set gro flush 1210~~~~~~~~~~~~~ 1211 1212Set the cycle to flush the GROed packets from reassembly tables:: 1213 1214 testpmd> set gro flush <cycles> 1215 1216When enable GRO, the csum forwarding engine performs GRO on received 1217packets, and the GROed packets are stored in reassembly tables. Users 1218can use this command to determine when the GROed packets are flushed 1219from the reassembly tables. 1220 1221The ``cycles`` is measured in GRO operation times. The csum forwarding 1222engine flushes the GROed packets from the tables every ``cycles`` GRO 1223operations. 1224 1225By default, the value of ``cycles`` is 1, which means flush GROed packets 1226from the reassembly tables as soon as one GRO operation finishes. The value 1227of ``cycles`` should be in the range of 1 to ``GRO_MAX_FLUSH_CYCLES``. 1228 1229Please note that the large value of ``cycles`` may cause the poor TCP/IP 1230stack performance. Because the GROed packets are delayed to arrive the 1231stack, thus causing more duplicated ACKs and TCP retransmissions. 1232 1233set port - gso 1234~~~~~~~~~~~~~~ 1235 1236Toggle per-port GSO support in ``csum`` forwarding engine:: 1237 1238 testpmd> set port <port_id> gso on|off 1239 1240If enabled, the csum forwarding engine will perform GSO on supported IPv4 1241packets, transmitted on the given port. 1242 1243If disabled, packets transmitted on the given port will not undergo GSO. 1244By default, GSO is disabled for all ports. 1245 1246.. note:: 1247 1248 When GSO is enabled on a port, supported IPv4 packets transmitted on that 1249 port undergo GSO. Afterwards, the segmented packets are represented by 1250 multi-segment mbufs; however, the csum forwarding engine doesn't calculation 1251 of checksums for GSO'd segments in SW. As a result, if users want correct 1252 checksums in GSO segments, they should enable HW checksum calculation for 1253 GSO-enabled ports. 1254 1255 For example, HW checksum calculation for VxLAN GSO'd packets may be enabled 1256 by setting the following options in the csum forwarding engine: 1257 1258 testpmd> csum set outer_ip hw <port_id> 1259 1260 testpmd> csum set ip hw <port_id> 1261 1262 testpmd> csum set tcp hw <port_id> 1263 1264 UDP GSO is the same as IP fragmentation, which treats the UDP header 1265 as the payload and does not modify it during segmentation. That is, 1266 after UDP GSO, only the first output fragment has the original UDP 1267 header. Therefore, users need to enable HW IP checksum calculation 1268 and SW UDP checksum calculation for GSO-enabled ports, if they want 1269 correct checksums for UDP/IPv4 packets. 1270 1271set gso segsz 1272~~~~~~~~~~~~~ 1273 1274Set the maximum GSO segment size (measured in bytes), which includes the 1275packet header and the packet payload for GSO-enabled ports (global):: 1276 1277 testpmd> set gso segsz <length> 1278 1279show port - gso 1280~~~~~~~~~~~~~~~ 1281 1282Display the status of Generic Segmentation Offload for a given port:: 1283 1284 testpmd> show port <port_id> gso 1285 1286mac_addr add 1287~~~~~~~~~~~~ 1288 1289Add an alternative MAC address to a port:: 1290 1291 testpmd> mac_addr add (port_id) (XX:XX:XX:XX:XX:XX) 1292 1293mac_addr remove 1294~~~~~~~~~~~~~~~ 1295 1296Remove a MAC address from a port:: 1297 1298 testpmd> mac_addr remove (port_id) (XX:XX:XX:XX:XX:XX) 1299 1300mcast_addr add 1301~~~~~~~~~~~~~~ 1302 1303To add the multicast MAC address to/from the set of multicast addresses 1304filtered by port:: 1305 1306 testpmd> mcast_addr add (port_id) (mcast_addr) 1307 1308mcast_addr remove 1309~~~~~~~~~~~~~~~~~ 1310 1311To remove the multicast MAC address to/from the set of multicast addresses 1312filtered by port:: 1313 1314 testpmd> mcast_addr remove (port_id) (mcast_addr) 1315 1316mac_addr add (for VF) 1317~~~~~~~~~~~~~~~~~~~~~ 1318 1319Add an alternative MAC address for a VF to a port:: 1320 1321 testpmd> mac_add add port (port_id) vf (vf_id) (XX:XX:XX:XX:XX:XX) 1322 1323mac_addr set 1324~~~~~~~~~~~~ 1325 1326Set the default MAC address for a port:: 1327 1328 testpmd> mac_addr set (port_id) (XX:XX:XX:XX:XX:XX) 1329 1330mac_addr set (for VF) 1331~~~~~~~~~~~~~~~~~~~~~ 1332 1333Set the MAC address for a VF from the PF:: 1334 1335 testpmd> set vf mac addr (port_id) (vf_id) (XX:XX:XX:XX:XX:XX) 1336 1337set eth-peer 1338~~~~~~~~~~~~ 1339 1340Set the forwarding peer address for certain port:: 1341 1342 testpmd> set eth-peer (port_id) (peer_addr) 1343 1344This is equivalent to the ``--eth-peer`` command-line option. 1345 1346set port-uta 1347~~~~~~~~~~~~ 1348 1349Set the unicast hash filter(s) on/off for a port:: 1350 1351 testpmd> set port (port_id) uta (XX:XX:XX:XX:XX:XX|all) (on|off) 1352 1353set promisc 1354~~~~~~~~~~~ 1355 1356Set the promiscuous mode on for a port or for all ports. 1357In promiscuous mode packets are not dropped if they aren't for the specified MAC address:: 1358 1359 testpmd> set promisc (port_id|all) (on|off) 1360 1361set allmulti 1362~~~~~~~~~~~~ 1363 1364Set the allmulti mode for a port or for all ports:: 1365 1366 testpmd> set allmulti (port_id|all) (on|off) 1367 1368Same as the ifconfig (8) option. Controls how multicast packets are handled. 1369 1370set flow_ctrl rx 1371~~~~~~~~~~~~~~~~ 1372 1373Set the link flow control parameter on a port:: 1374 1375 testpmd> set flow_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \ 1376 (pause_time) (send_xon) mac_ctrl_frame_fwd (on|off) \ 1377 autoneg (on|off) (port_id) 1378 1379Where: 1380 1381* ``high_water`` (integer): High threshold value to trigger XOFF. 1382 1383* ``low_water`` (integer): Low threshold value to trigger XON. 1384 1385* ``pause_time`` (integer): Pause quota in the Pause frame. 1386 1387* ``send_xon`` (0/1): Send XON frame. 1388 1389* ``mac_ctrl_frame_fwd``: Enable receiving MAC control frames. 1390 1391* ``autoneg``: Change the auto-negotiation parameter. 1392 1393show flow control 1394~~~~~~~~~~~~~~~~~ 1395 1396show the link flow control parameter on a port:: 1397 1398 testpmd> show port <port_id> flow_ctrl 1399 1400set pfc_ctrl rx 1401~~~~~~~~~~~~~~~ 1402 1403Set the priority flow control parameter on a port:: 1404 1405 testpmd> set pfc_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \ 1406 (pause_time) (priority) (port_id) 1407 1408Where: 1409 1410* ``high_water`` (integer): High threshold value. 1411 1412* ``low_water`` (integer): Low threshold value. 1413 1414* ``pause_time`` (integer): Pause quota in the Pause frame. 1415 1416* ``priority`` (0-7): VLAN User Priority. 1417 1418set pfc_queue_ctrl 1419~~~~~~~~~~~~~~~~~~ 1420 1421Set the priority flow control parameter on a given Rx and Tx queue of a port:: 1422 1423 testpmd> set pfc_queue_ctrl <port_id> rx (on|off) <tx_qid> <tx_tc> \ 1424 tx (on|off) <rx_qid> <rx_tc> <pause_time> 1425 1426Where: 1427 1428* ``tx_qid`` (integer): Tx qid for which ``tx_tc`` will be applied and traffic 1429 will be paused when PFC frame is received with ``tx_tc`` enabled. 1430 1431* ``tx_tc`` (0-15): TC for which traffic is to be paused for xmit. 1432 1433* ``rx_qid`` (integer): Rx qid for which threshold will be applied and PFC 1434 frame will be generated with ``tx_tc`` when exceeds the threshold. 1435 1436* ``rx_tc`` (0-15): TC filled in PFC frame for which remote Tx is to be paused. 1437 1438* ``pause_time`` (integer): Pause quanta filled in the PFC frame for which 1439 interval, remote Tx will be paused. Valid only if Tx pause is on. 1440 1441Set Rx queue available descriptors threshold 1442~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1443 1444Set available descriptors threshold for a specific Rx queue of port:: 1445 1446 testpmd> set port (port_id) rxq (queue_id) avail_thresh (0..99) 1447 1448Use 0 value to disable the threshold and corresponding event. 1449 1450set stat_qmap 1451~~~~~~~~~~~~~ 1452 1453Set statistics mapping (qmapping 0..15) for RX/TX queue on port:: 1454 1455 testpmd> set stat_qmap (tx|rx) (port_id) (queue_id) (qmapping) 1456 1457For example, to set rx queue 2 on port 0 to mapping 5:: 1458 1459 testpmd>set stat_qmap rx 0 2 5 1460 1461set xstats-hide-zero 1462~~~~~~~~~~~~~~~~~~~~ 1463 1464Set the option to hide zero values for xstats display:: 1465 1466 testpmd> set xstats-hide-zero on|off 1467 1468.. note:: 1469 1470 By default, the zero values are displayed for xstats. 1471 1472set port - rx/tx (for VF) 1473~~~~~~~~~~~~~~~~~~~~~~~~~ 1474 1475Set VF receive/transmit from a port:: 1476 1477 testpmd> set port (port_id) vf (vf_id) (rx|tx) (on|off) 1478 1479set port - rx mode(for VF) 1480~~~~~~~~~~~~~~~~~~~~~~~~~~ 1481 1482Set the VF receive mode of a port:: 1483 1484 testpmd> set port (port_id) vf (vf_id) \ 1485 rxmode (AUPE|ROPE|BAM|MPE) (on|off) 1486 1487The available receive modes are: 1488 1489* ``AUPE``: Accepts untagged VLAN. 1490 1491* ``ROPE``: Accepts unicast hash. 1492 1493* ``BAM``: Accepts broadcast packets. 1494 1495* ``MPE``: Accepts all multicast packets. 1496 1497set port - tx_rate (for Queue) 1498~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1499 1500Set TX rate limitation for a queue on a port:: 1501 1502 testpmd> set port (port_id) queue (queue_id) rate (rate_value) 1503 1504set port - tx_rate (for VF) 1505~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1506 1507Set TX rate limitation for queues in VF on a port:: 1508 1509 testpmd> set port (port_id) vf (vf_id) rate (rate_value) queue_mask (queue_mask) 1510 1511set flush_rx 1512~~~~~~~~~~~~ 1513 1514Set the flush on RX streams before forwarding. 1515The default is flush ``on``. 1516Mainly used with PCAP drivers to turn off the default behavior of flushing the first 512 packets on RX streams:: 1517 1518 testpmd> set flush_rx off 1519 1520set link up 1521~~~~~~~~~~~ 1522 1523Set link up for a port:: 1524 1525 testpmd> set link-up port (port id) 1526 1527set link down 1528~~~~~~~~~~~~~ 1529 1530Set link down for a port:: 1531 1532 testpmd> set link-down port (port id) 1533 1534E-tag set 1535~~~~~~~~~ 1536 1537Enable E-tag insertion for a VF on a port:: 1538 1539 testpmd> E-tag set insertion on port-tag-id (value) port (port_id) vf (vf_id) 1540 1541Disable E-tag insertion for a VF on a port:: 1542 1543 testpmd> E-tag set insertion off port (port_id) vf (vf_id) 1544 1545Enable/disable E-tag stripping on a port:: 1546 1547 testpmd> E-tag set stripping (on|off) port (port_id) 1548 1549Enable/disable E-tag based forwarding on a port:: 1550 1551 testpmd> E-tag set forwarding (on|off) port (port_id) 1552 1553config per port Rx offloading 1554~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1555 1556Enable or disable a per port Rx offloading on all Rx queues of a port:: 1557 1558 testpmd> port config (port_id) rx_offload (offloading) on|off 1559 1560* ``offloading``: can be any of these offloading capability: 1561 vlan_strip, ipv4_cksum, udp_cksum, tcp_cksum, tcp_lro, 1562 qinq_strip, outer_ipv4_cksum, macsec_strip, 1563 vlan_filter, vlan_extend, scatter, timestamp, security, 1564 keep_crc, rss_hash 1565 1566This command should be run when the port is stopped, or else it will fail. 1567 1568config per queue Rx offloading 1569~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1570 1571Enable or disable a per queue Rx offloading only on a specific Rx queue:: 1572 1573 testpmd> port (port_id) rxq (queue_id) rx_offload (offloading) on|off 1574 1575* ``offloading``: can be any of these offloading capability: 1576 vlan_strip, ipv4_cksum, udp_cksum, tcp_cksum, tcp_lro, 1577 qinq_strip, outer_ipv4_cksum, macsec_strip, 1578 vlan_filter, vlan_extend, scatter, timestamp, security, 1579 keep_crc 1580 1581This command should be run when the port is stopped, or else it will fail. 1582 1583config per port Tx offloading 1584~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1585 1586Enable or disable a per port Tx offloading on all Tx queues of a port:: 1587 1588 testpmd> port config (port_id) tx_offload (offloading) on|off 1589 1590* ``offloading``: can be any of these offloading capability: 1591 vlan_insert, ipv4_cksum, udp_cksum, tcp_cksum, 1592 sctp_cksum, tcp_tso, udp_tso, outer_ipv4_cksum, 1593 qinq_insert, vxlan_tnl_tso, gre_tnl_tso, 1594 ipip_tnl_tso, geneve_tnl_tso, macsec_insert, 1595 mt_lockfree, multi_segs, mbuf_fast_free, security 1596 1597This command should be run when the port is stopped, or else it will fail. 1598 1599config per queue Tx offloading 1600~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1601 1602Enable or disable a per queue Tx offloading only on a specific Tx queue:: 1603 1604 testpmd> port (port_id) txq (queue_id) tx_offload (offloading) on|off 1605 1606* ``offloading``: can be any of these offloading capability: 1607 vlan_insert, ipv4_cksum, udp_cksum, tcp_cksum, 1608 sctp_cksum, tcp_tso, udp_tso, outer_ipv4_cksum, 1609 qinq_insert, vxlan_tnl_tso, gre_tnl_tso, 1610 ipip_tnl_tso, geneve_tnl_tso, macsec_insert, 1611 mt_lockfree, multi_segs, mbuf_fast_free, security 1612 1613This command should be run when the port is stopped, or else it will fail. 1614 1615Config VXLAN Encap outer layers 1616~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1617 1618Configure the outer layer to encapsulate a packet inside a VXLAN tunnel:: 1619 1620 set vxlan ip-version (ipv4|ipv6) vni (vni) udp-src (udp-src) \ 1621 udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) eth-src (eth-src) \ 1622 eth-dst (eth-dst) 1623 1624 set vxlan-with-vlan ip-version (ipv4|ipv6) vni (vni) udp-src (udp-src) \ 1625 udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) vlan-tci (vlan-tci) \ 1626 eth-src (eth-src) eth-dst (eth-dst) 1627 1628 set vxlan-tos-ttl ip-version (ipv4|ipv6) vni (vni) udp-src (udp-src) \ 1629 udp-dst (udp-dst) ip-tos (ip-tos) ip-ttl (ip-ttl) ip-src (ip-src) \ 1630 ip-dst (ip-dst) eth-src (eth-src) eth-dst (eth-dst) 1631 1632These commands will set an internal configuration inside testpmd, any following 1633flow rule using the action vxlan_encap will use the last configuration set. 1634To have a different encapsulation header, one of those commands must be called 1635before the flow rule creation. 1636 1637Config NVGRE Encap outer layers 1638~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1639 1640Configure the outer layer to encapsulate a packet inside a NVGRE tunnel:: 1641 1642 set nvgre ip-version (ipv4|ipv6) tni (tni) ip-src (ip-src) ip-dst (ip-dst) \ 1643 eth-src (eth-src) eth-dst (eth-dst) 1644 set nvgre-with-vlan ip-version (ipv4|ipv6) tni (tni) ip-src (ip-src) \ 1645 ip-dst (ip-dst) vlan-tci (vlan-tci) eth-src (eth-src) eth-dst (eth-dst) 1646 1647These commands will set an internal configuration inside testpmd, any following 1648flow rule using the action nvgre_encap will use the last configuration set. 1649To have a different encapsulation header, one of those commands must be called 1650before the flow rule creation. 1651 1652Config L2 Encap 1653~~~~~~~~~~~~~~~ 1654 1655Configure the l2 to be used when encapsulating a packet with L2:: 1656 1657 set l2_encap ip-version (ipv4|ipv6) eth-src (eth-src) eth-dst (eth-dst) 1658 set l2_encap-with-vlan ip-version (ipv4|ipv6) vlan-tci (vlan-tci) \ 1659 eth-src (eth-src) eth-dst (eth-dst) 1660 1661Those commands will set an internal configuration inside testpmd, any following 1662flow rule using the action l2_encap will use the last configuration set. 1663To have a different encapsulation header, one of those commands must be called 1664before the flow rule creation. 1665 1666Config L2 Decap 1667~~~~~~~~~~~~~~~ 1668 1669Configure the l2 to be removed when decapsulating a packet with L2:: 1670 1671 set l2_decap ip-version (ipv4|ipv6) 1672 set l2_decap-with-vlan ip-version (ipv4|ipv6) 1673 1674Those commands will set an internal configuration inside testpmd, any following 1675flow rule using the action l2_decap will use the last configuration set. 1676To have a different encapsulation header, one of those commands must be called 1677before the flow rule creation. 1678 1679Config MPLSoGRE Encap outer layers 1680~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1681 1682Configure the outer layer to encapsulate a packet inside a MPLSoGRE tunnel:: 1683 1684 set mplsogre_encap ip-version (ipv4|ipv6) label (label) \ 1685 ip-src (ip-src) ip-dst (ip-dst) eth-src (eth-src) eth-dst (eth-dst) 1686 set mplsogre_encap-with-vlan ip-version (ipv4|ipv6) label (label) \ 1687 ip-src (ip-src) ip-dst (ip-dst) vlan-tci (vlan-tci) \ 1688 eth-src (eth-src) eth-dst (eth-dst) 1689 1690These commands will set an internal configuration inside testpmd, any following 1691flow rule using the action mplsogre_encap will use the last configuration set. 1692To have a different encapsulation header, one of those commands must be called 1693before the flow rule creation. 1694 1695Config MPLSoGRE Decap outer layers 1696~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1697 1698Configure the outer layer to decapsulate MPLSoGRE packet:: 1699 1700 set mplsogre_decap ip-version (ipv4|ipv6) 1701 set mplsogre_decap-with-vlan ip-version (ipv4|ipv6) 1702 1703These commands will set an internal configuration inside testpmd, any following 1704flow rule using the action mplsogre_decap will use the last configuration set. 1705To have a different decapsulation header, one of those commands must be called 1706before the flow rule creation. 1707 1708Config MPLSoUDP Encap outer layers 1709~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1710 1711Configure the outer layer to encapsulate a packet inside a MPLSoUDP tunnel:: 1712 1713 set mplsoudp_encap ip-version (ipv4|ipv6) label (label) udp-src (udp-src) \ 1714 udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) \ 1715 eth-src (eth-src) eth-dst (eth-dst) 1716 set mplsoudp_encap-with-vlan ip-version (ipv4|ipv6) label (label) \ 1717 udp-src (udp-src) udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) \ 1718 vlan-tci (vlan-tci) eth-src (eth-src) eth-dst (eth-dst) 1719 1720These commands will set an internal configuration inside testpmd, any following 1721flow rule using the action mplsoudp_encap will use the last configuration set. 1722To have a different encapsulation header, one of those commands must be called 1723before the flow rule creation. 1724 1725Config MPLSoUDP Decap outer layers 1726~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1727 1728Configure the outer layer to decapsulate MPLSoUDP packet:: 1729 1730 set mplsoudp_decap ip-version (ipv4|ipv6) 1731 set mplsoudp_decap-with-vlan ip-version (ipv4|ipv6) 1732 1733These commands will set an internal configuration inside testpmd, any following 1734flow rule using the action mplsoudp_decap will use the last configuration set. 1735To have a different decapsulation header, one of those commands must be called 1736before the flow rule creation. 1737 1738Config Raw Encapsulation 1739~~~~~~~~~~~~~~~~~~~~~~~~~ 1740 1741Configure the raw data to be used when encapsulating a packet by 1742rte_flow_action_raw_encap:: 1743 1744 set raw_encap {index} {item} [/ {item} [...]] / end_set 1745 1746There are multiple global buffers for ``raw_encap``, this command will set one 1747internal buffer index by ``{index}``. 1748If there is no ``{index}`` specified:: 1749 1750 set raw_encap {item} [/ {item} [...]] / end_set 1751 1752the default index ``0`` is used. 1753In order to use different encapsulating header, ``index`` must be specified 1754during the flow rule creation:: 1755 1756 testpmd> flow create 0 egress pattern eth / ipv4 / end actions 1757 raw_encap index 2 / end 1758 1759Otherwise the default index ``0`` is used. 1760 1761Config Raw Decapsulation 1762~~~~~~~~~~~~~~~~~~~~~~~~ 1763 1764Configure the raw data to be used when decapsulating a packet by 1765rte_flow_action_raw_decap:: 1766 1767 set raw_decap {index} {item} [/ {item} [...]] / end_set 1768 1769There are multiple global buffers for ``raw_decap``, this command will set 1770one internal buffer index by ``{index}``. 1771If there is no ``{index}`` specified:: 1772 1773 set raw_decap {item} [/ {item} [...]] / end_set 1774 1775the default index ``0`` is used. 1776In order to use different decapsulating header, ``index`` must be specified 1777during the flow rule creation:: 1778 1779 testpmd> flow create 0 egress pattern eth / ipv4 / end actions 1780 raw_encap index 3 / end 1781 1782Otherwise the default index ``0`` is used. 1783 1784Set fec mode 1785~~~~~~~~~~~~ 1786 1787Set fec mode for a specific port:: 1788 1789 testpmd> set port (port_id) fec_mode auto|off|rs|baser 1790 1791Config Sample actions list 1792~~~~~~~~~~~~~~~~~~~~~~~~~~ 1793 1794Configure the sample actions list to be used when sampling a packet by 1795rte_flow_action_sample:: 1796 1797 set sample_actions {index} {action} [/ {action} [...]] / end 1798 1799There are multiple global buffers for ``sample_actions``, this command will set 1800one internal buffer index by ``{index}``. 1801 1802In order to use different sample actions list, ``index`` must be specified 1803during the flow rule creation:: 1804 1805 testpmd> flow create 0 ingress pattern eth / ipv4 / end actions 1806 sample ratio 2 index 2 / end 1807 1808Otherwise the default index ``0`` is used. 1809 1810Port Functions 1811-------------- 1812 1813The following sections show functions for configuring ports. 1814 1815.. note:: 1816 1817 Port configuration changes only become active when forwarding is started/restarted. 1818 1819.. _port_attach: 1820 1821port attach 1822~~~~~~~~~~~ 1823 1824Attach a port specified by pci address or virtual device args:: 1825 1826 testpmd> port attach (identifier) 1827 1828To attach a new pci device, the device should be recognized by kernel first. 1829Then it should be moved under DPDK management. 1830Finally the port can be attached to testpmd. 1831 1832For example, to move a pci device using ixgbe under DPDK management: 1833 1834.. code-block:: console 1835 1836 # Check the status of the available devices. 1837 ./usertools/dpdk-devbind.py --status 1838 1839 Network devices using DPDK-compatible driver 1840 ============================================ 1841 <none> 1842 1843 Network devices using kernel driver 1844 =================================== 1845 0000:0a:00.0 '82599ES 10-Gigabit' if=eth2 drv=ixgbe unused= 1846 1847 1848 # Bind the device to igb_uio. 1849 sudo ./usertools/dpdk-devbind.py -b igb_uio 0000:0a:00.0 1850 1851 1852 # Recheck the status of the devices. 1853 ./usertools/dpdk-devbind.py --status 1854 Network devices using DPDK-compatible driver 1855 ============================================ 1856 0000:0a:00.0 '82599ES 10-Gigabit' drv=igb_uio unused= 1857 1858To attach a port created by virtual device, above steps are not needed. 1859 1860For example, to attach a port whose pci address is 0000:0a:00.0. 1861 1862.. code-block:: console 1863 1864 testpmd> port attach 0000:0a:00.0 1865 Attaching a new port... 1866 EAL: PCI device 0000:0a:00.0 on NUMA socket -1 1867 EAL: probe driver: 8086:10fb rte_ixgbe_pmd 1868 EAL: PCI memory mapped at 0x7f83bfa00000 1869 EAL: PCI memory mapped at 0x7f83bfa80000 1870 PMD: eth_ixgbe_dev_init(): MAC: 2, PHY: 18, SFP+: 5 1871 PMD: eth_ixgbe_dev_init(): port 0 vendorID=0x8086 deviceID=0x10fb 1872 Port 0 is attached. Now total ports is 1 1873 Done 1874 1875For example, to attach a port created by pcap PMD. 1876 1877.. code-block:: console 1878 1879 testpmd> port attach net_pcap0 1880 Attaching a new port... 1881 PMD: Initializing pmd_pcap for net_pcap0 1882 PMD: Creating pcap-backed ethdev on numa socket 0 1883 Port 0 is attached. Now total ports is 1 1884 Done 1885 1886In this case, identifier is ``net_pcap0``. 1887This identifier format is the same as ``--vdev`` format of DPDK applications. 1888 1889For example, to re-attach a bonded port which has been previously detached, 1890the mode and slave parameters must be given. 1891 1892.. code-block:: console 1893 1894 testpmd> port attach net_bond_0,mode=0,slave=1 1895 Attaching a new port... 1896 EAL: Initializing pmd_bond for net_bond_0 1897 EAL: Create bonded device net_bond_0 on port 0 in mode 0 on socket 0. 1898 Port 0 is attached. Now total ports is 1 1899 Done 1900 1901 1902port detach 1903~~~~~~~~~~~ 1904 1905Detach a specific port:: 1906 1907 testpmd> port detach (port_id) 1908 1909Before detaching a port, the port should be stopped and closed. 1910 1911For example, to detach a pci device port 0. 1912 1913.. code-block:: console 1914 1915 testpmd> port stop 0 1916 Stopping ports... 1917 Done 1918 testpmd> port close 0 1919 Closing ports... 1920 Done 1921 1922 testpmd> port detach 0 1923 Detaching a port... 1924 EAL: PCI device 0000:0a:00.0 on NUMA socket -1 1925 EAL: remove driver: 8086:10fb rte_ixgbe_pmd 1926 EAL: PCI memory unmapped at 0x7f83bfa00000 1927 EAL: PCI memory unmapped at 0x7f83bfa80000 1928 Done 1929 1930 1931For example, to detach a virtual device port 0. 1932 1933.. code-block:: console 1934 1935 testpmd> port stop 0 1936 Stopping ports... 1937 Done 1938 testpmd> port close 0 1939 Closing ports... 1940 Done 1941 1942 testpmd> port detach 0 1943 Detaching a port... 1944 PMD: Closing pcap ethdev on numa socket 0 1945 Port 'net_pcap0' is detached. Now total ports is 0 1946 Done 1947 1948To remove a pci device completely from the system, first detach the port from testpmd. 1949Then the device should be moved under kernel management. 1950Finally the device can be removed using kernel pci hotplug functionality. 1951 1952For example, to move a pci device under kernel management: 1953 1954.. code-block:: console 1955 1956 sudo ./usertools/dpdk-devbind.py -b ixgbe 0000:0a:00.0 1957 1958 ./usertools/dpdk-devbind.py --status 1959 1960 Network devices using DPDK-compatible driver 1961 ============================================ 1962 <none> 1963 1964 Network devices using kernel driver 1965 =================================== 1966 0000:0a:00.0 '82599ES 10-Gigabit' if=eth2 drv=ixgbe unused=igb_uio 1967 1968To remove a port created by a virtual device, above steps are not needed. 1969 1970port start 1971~~~~~~~~~~ 1972 1973Start all ports or a specific port:: 1974 1975 testpmd> port start (port_id|all) 1976 1977port stop 1978~~~~~~~~~ 1979 1980Stop all ports or a specific port:: 1981 1982 testpmd> port stop (port_id|all) 1983 1984port close 1985~~~~~~~~~~ 1986 1987Close all ports or a specific port:: 1988 1989 testpmd> port close (port_id|all) 1990 1991port reset 1992~~~~~~~~~~ 1993 1994Reset all ports or a specific port:: 1995 1996 testpmd> port reset (port_id|all) 1997 1998User should stop port(s) before resetting and (re-)start after reset. 1999 2000port config - queue ring size 2001~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2002 2003Configure a rx/tx queue ring size:: 2004 2005 testpmd> port (port_id) (rxq|txq) (queue_id) ring_size (value) 2006 2007Only take effect after command that (re-)start the port or command that setup specific queue. 2008 2009port start/stop queue 2010~~~~~~~~~~~~~~~~~~~~~ 2011 2012Start/stop a rx/tx queue on a specific port:: 2013 2014 testpmd> port (port_id) (rxq|txq) (queue_id) (start|stop) 2015 2016port config - queue deferred start 2017~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2018 2019Switch on/off deferred start of a specific port queue:: 2020 2021 testpmd> port (port_id) (rxq|txq) (queue_id) deferred_start (on|off) 2022 2023port setup queue 2024~~~~~~~~~~~~~~~~~~~~~ 2025 2026Setup a rx/tx queue on a specific port:: 2027 2028 testpmd> port (port_id) (rxq|txq) (queue_id) setup 2029 2030Only take effect when port is started. 2031 2032port config - speed 2033~~~~~~~~~~~~~~~~~~~ 2034 2035Set the speed and duplex mode for all ports or a specific port:: 2036 2037 testpmd> port config (port_id|all) speed (10|100|1000|10000|25000|40000|50000|100000|200000|auto) \ 2038 duplex (half|full|auto) 2039 2040port config - queues/descriptors 2041~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2042 2043Set number of queues/descriptors for rxq, txq, rxd and txd:: 2044 2045 testpmd> port config all (rxq|txq|rxd|txd) (value) 2046 2047This is equivalent to the ``--rxq``, ``--txq``, ``--rxd`` and ``--txd`` command-line options. 2048 2049port config - max-pkt-len 2050~~~~~~~~~~~~~~~~~~~~~~~~~ 2051 2052Set the maximum packet length:: 2053 2054 testpmd> port config all max-pkt-len (value) 2055 2056This is equivalent to the ``--max-pkt-len`` command-line option. 2057 2058port config - max-lro-pkt-size 2059~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2060 2061Set the maximum LRO aggregated packet size:: 2062 2063 testpmd> port config all max-lro-pkt-size (value) 2064 2065This is equivalent to the ``--max-lro-pkt-size`` command-line option. 2066 2067port config - Drop Packets 2068~~~~~~~~~~~~~~~~~~~~~~~~~~ 2069 2070Enable or disable packet drop on all RX queues of all ports when no receive buffers available:: 2071 2072 testpmd> port config all drop-en (on|off) 2073 2074Packet dropping when no receive buffers available is off by default. 2075 2076The ``on`` option is equivalent to the ``--enable-drop-en`` command-line option. 2077 2078port config - RSS 2079~~~~~~~~~~~~~~~~~ 2080 2081Set the RSS (Receive Side Scaling) mode on or off:: 2082 testpmd> port config all rss (all|default|level-default|level-outer|level-inner| \ 2083 ip|tcp|udp|sctp|tunnel|vlan|none| \ 2084 ipv4|ipv4-frag|ipv4-tcp|ipv4-udp|ipv4-sctp|ipv4-other| \ 2085 ipv6|ipv6-frag|ipv6-tcp|ipv6-udp|ipv6-sctp| \ 2086 ipv6-other|ipv6-ex|ipv6-tcp-ex|ipv6-udp-ex| \ 2087 l2-payload|port|vxlan|geneve|nvgre|gtpu|eth|s-vlan|c-vlan| \ 2088 esp|ah|l2tpv3|pfcp|pppoe|ecpri|mpls|ipv4-chksum|l4-chksum| \ 2089 l2tpv2|l3-pre96|l3-pre64|l3-pre56|l3-pre48|l3-pre40|l3-pre32| \ 2090 l2-dst-only|l2-src-only|l4-dst-only|l4-src-only|l3-dst-only|l3-src-only|<rsstype_id>) 2091 2092RSS is on by default. 2093 2094The ``all`` option is equivalent to eth|vlan|ip|tcp|udp|sctp|ether|l2tpv3|esp|ah|pfcp|l2tpv2. 2095 2096The ``default`` option enables all supported RSS types reported by device info. 2097 2098The ``none`` option is equivalent to the ``--disable-rss`` command-line option. 2099 2100port config - RSS Reta 2101~~~~~~~~~~~~~~~~~~~~~~ 2102 2103Set the RSS (Receive Side Scaling) redirection table:: 2104 2105 testpmd> port config all rss reta (hash,queue)[,(hash,queue)] 2106 2107port config - DCB 2108~~~~~~~~~~~~~~~~~ 2109 2110Set the DCB mode for an individual port:: 2111 2112 testpmd> port config (port_id) dcb vt (on|off) (traffic_class) pfc (on|off) 2113 2114The traffic class should be 4 or 8. 2115 2116port config - Burst 2117~~~~~~~~~~~~~~~~~~~ 2118 2119Set the number of packets per burst:: 2120 2121 testpmd> port config all burst (value) 2122 2123This is equivalent to the ``--burst`` command-line option. 2124 2125port config - Threshold 2126~~~~~~~~~~~~~~~~~~~~~~~ 2127 2128Set thresholds for TX/RX queues:: 2129 2130 testpmd> port config all (threshold) (value) 2131 2132Where the threshold type can be: 2133 2134* ``txpt:`` Set the prefetch threshold register of the TX rings, 0 <= value <= 255. 2135 2136* ``txht:`` Set the host threshold register of the TX rings, 0 <= value <= 255. 2137 2138* ``txwt:`` Set the write-back threshold register of the TX rings, 0 <= value <= 255. 2139 2140* ``rxpt:`` Set the prefetch threshold register of the RX rings, 0 <= value <= 255. 2141 2142* ``rxht:`` Set the host threshold register of the RX rings, 0 <= value <= 255. 2143 2144* ``rxwt:`` Set the write-back threshold register of the RX rings, 0 <= value <= 255. 2145 2146* ``txfreet:`` Set the transmit free threshold of the TX rings, 0 <= value <= txd. 2147 2148* ``rxfreet:`` Set the transmit free threshold of the RX rings, 0 <= value <= rxd. 2149 2150* ``txrst:`` Set the transmit RS bit threshold of TX rings, 0 <= value <= txd. 2151 2152These threshold options are also available from the command-line. 2153 2154port config pctype mapping 2155~~~~~~~~~~~~~~~~~~~~~~~~~~ 2156 2157Reset pctype mapping table:: 2158 2159 testpmd> port config (port_id) pctype mapping reset 2160 2161Update hardware defined pctype to software defined flow type mapping table:: 2162 2163 testpmd> port config (port_id) pctype mapping update (pctype_id_0[,pctype_id_1]*) (flow_type_id) 2164 2165where: 2166 2167* ``pctype_id_x``: hardware pctype id as index of bit in bitmask value of the pctype mapping table. 2168 2169* ``flow_type_id``: software flow type id as the index of the pctype mapping table. 2170 2171port config input set 2172~~~~~~~~~~~~~~~~~~~~~ 2173 2174Config RSS/FDIR/FDIR flexible payload input set for some pctype:: 2175 2176 testpmd> port config (port_id) pctype (pctype_id) \ 2177 (hash_inset|fdir_inset|fdir_flx_inset) \ 2178 (get|set|clear) field (field_idx) 2179 2180Clear RSS/FDIR/FDIR flexible payload input set for some pctype:: 2181 2182 testpmd> port config (port_id) pctype (pctype_id) \ 2183 (hash_inset|fdir_inset|fdir_flx_inset) clear all 2184 2185where: 2186 2187* ``pctype_id``: hardware packet classification types. 2188* ``field_idx``: hardware field index. 2189 2190port config udp_tunnel_port 2191~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2192 2193Add/remove UDP tunnel port for VXLAN/GENEVE tunneling protocols:: 2194 2195 testpmd> port config (port_id) udp_tunnel_port add|rm vxlan|geneve|vxlan-gpe|ecpri (udp_port) 2196 2197port config tx_metadata 2198~~~~~~~~~~~~~~~~~~~~~~~ 2199 2200Set Tx metadata value per port. 2201testpmd will add this value to any Tx packet sent from this port:: 2202 2203 testpmd> port config (port_id) tx_metadata (value) 2204 2205port config dynf 2206~~~~~~~~~~~~~~~~ 2207 2208Set/clear dynamic flag per port. 2209testpmd will register this flag in the mbuf (same registration 2210for both Tx and Rx). Then set/clear this flag for each Tx 2211packet sent from this port. The set bit only works for Tx packet:: 2212 2213 testpmd> port config (port_id) dynf (name) (set|clear) 2214 2215port config mtu 2216~~~~~~~~~~~~~~~ 2217 2218To configure MTU(Maximum Transmission Unit) on devices using testpmd:: 2219 2220 testpmd> port config mtu (port_id) (value) 2221 2222port config rss hash key 2223~~~~~~~~~~~~~~~~~~~~~~~~ 2224 2225To configure the RSS hash key used to compute the RSS 2226hash of input [IP] packets received on port:: 2227 2228 testpmd> port config <port_id> rss-hash-key (ipv4|ipv4-frag|\ 2229 ipv4-tcp|ipv4-udp|ipv4-sctp|ipv4-other|\ 2230 ipv6|ipv6-frag|ipv6-tcp|ipv6-udp|ipv6-sctp|\ 2231 ipv6-other|l2-payload|ipv6-ex|ipv6-tcp-ex|\ 2232 ipv6-udp-ex <string of hex digits \ 2233 (variable length, NIC dependent)>) 2234 2235port cleanup txq mbufs 2236~~~~~~~~~~~~~~~~~~~~~~ 2237 2238To cleanup txq mbufs currently cached by driver:: 2239 2240 testpmd> port cleanup (port_id) txq (queue_id) (free_cnt) 2241 2242If the value of ``free_cnt`` is 0, driver should free all cached mbufs. 2243 2244Device Functions 2245---------------- 2246 2247The following sections show functions for device operations. 2248 2249device detach 2250~~~~~~~~~~~~~ 2251 2252Detach a device specified by pci address or virtual device args:: 2253 2254 testpmd> device detach (identifier) 2255 2256Before detaching a device associated with ports, the ports should be stopped and closed. 2257 2258For example, to detach a pci device whose address is 0002:03:00.0. 2259 2260.. code-block:: console 2261 2262 testpmd> device detach 0002:03:00.0 2263 Removing a device... 2264 Port 1 is now closed 2265 EAL: Releasing pci mapped resource for 0002:03:00.0 2266 EAL: Calling pci_unmap_resource for 0002:03:00.0 at 0x218a050000 2267 EAL: Calling pci_unmap_resource for 0002:03:00.0 at 0x218c050000 2268 Device 0002:03:00.0 is detached 2269 Now total ports is 1 2270 2271For example, to detach a port created by pcap PMD. 2272 2273.. code-block:: console 2274 2275 testpmd> device detach net_pcap0 2276 Removing a device... 2277 Port 0 is now closed 2278 Device net_pcap0 is detached 2279 Now total ports is 0 2280 Done 2281 2282In this case, identifier is ``net_pcap0``. 2283This identifier format is the same as ``--vdev`` format of DPDK applications. 2284 2285Link Bonding Functions 2286---------------------- 2287 2288The Link Bonding functions make it possible to dynamically create and 2289manage link bonding devices from within testpmd interactive prompt. 2290 2291See :doc:`../prog_guide/link_bonding_poll_mode_drv_lib` for more information. 2292 2293Traffic Metering and Policing 2294----------------------------- 2295 2296The following section shows functions for configuring traffic metering and 2297policing on the ethernet device through the use of generic ethdev API. 2298 2299show port traffic management capability 2300~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2301 2302Show traffic metering and policing capability of the port:: 2303 2304 testpmd> show port meter cap (port_id) 2305 2306add port meter profile (srTCM rfc2967) 2307~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2308 2309Add meter profile (srTCM rfc2697) to the ethernet device:: 2310 2311 testpmd> add port meter profile srtcm_rfc2697 (port_id) (profile_id) \ 2312 (cir) (cbs) (ebs) (packet_mode) 2313 2314where: 2315 2316* ``profile_id``: ID for the meter profile. 2317* ``cir``: Committed Information Rate (CIR) (bytes per second or packets per second). 2318* ``cbs``: Committed Burst Size (CBS) (bytes or packets). 2319* ``ebs``: Excess Burst Size (EBS) (bytes or packets). 2320* ``packet_mode``: Packets mode for meter profile. 2321 2322add port meter profile (trTCM rfc2968) 2323~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2324 2325Add meter profile (srTCM rfc2698) to the ethernet device:: 2326 2327 testpmd> add port meter profile trtcm_rfc2698 (port_id) (profile_id) \ 2328 (cir) (pir) (cbs) (pbs) (packet_mode) 2329 2330where: 2331 2332* ``profile_id``: ID for the meter profile. 2333* ``cir``: Committed information rate (bytes per second or packets per second). 2334* ``pir``: Peak information rate (bytes per second or packets per second). 2335* ``cbs``: Committed burst size (bytes or packets). 2336* ``pbs``: Peak burst size (bytes or packets). 2337* ``packet_mode``: Packets mode for meter profile. 2338 2339add port meter profile (trTCM rfc4115) 2340~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2341 2342Add meter profile (trTCM rfc4115) to the ethernet device:: 2343 2344 testpmd> add port meter profile trtcm_rfc4115 (port_id) (profile_id) \ 2345 (cir) (eir) (cbs) (ebs) (packet_mode) 2346 2347where: 2348 2349* ``profile_id``: ID for the meter profile. 2350* ``cir``: Committed information rate (bytes per second or packets per second). 2351* ``eir``: Excess information rate (bytes per second or packets per second). 2352* ``cbs``: Committed burst size (bytes or packets). 2353* ``ebs``: Excess burst size (bytes or packets). 2354* ``packet_mode``: Packets mode for meter profile. 2355 2356delete port meter profile 2357~~~~~~~~~~~~~~~~~~~~~~~~~ 2358 2359Delete meter profile from the ethernet device:: 2360 2361 testpmd> del port meter profile (port_id) (profile_id) 2362 2363create port policy 2364~~~~~~~~~~~~~~~~~~ 2365 2366Create new policy object for the ethernet device:: 2367 2368 testpmd> add port meter policy (port_id) (policy_id) g_actions \ 2369 {action} y_actions {action} r_actions {action} 2370 2371where: 2372 2373* ``policy_id``: policy ID. 2374* ``action``: action lists for green/yellow/red colors. 2375 2376delete port policy 2377~~~~~~~~~~~~~~~~~~ 2378 2379Delete policy object for the ethernet device:: 2380 2381 testpmd> del port meter policy (port_id) (policy_id) 2382 2383where: 2384 2385* ``policy_id``: policy ID. 2386 2387create port meter 2388~~~~~~~~~~~~~~~~~ 2389 2390Create new meter object for the ethernet device:: 2391 2392 testpmd> create port meter (port_id) (mtr_id) (profile_id) \ 2393 (policy_id) (meter_enable) (stats_mask) (shared) (default_input_color) \ 2394 (use_pre_meter_color) [(dscp_tbl_entry0) (dscp_tbl_entry1)...\ 2395 (dscp_tbl_entry63)] [(vlan_tbl_entry0) (vlan_tbl_entry1) ... \ 2396 (vlan_tbl_entry15)] 2397 2398where: 2399 2400* ``mtr_id``: meter object ID. 2401* ``profile_id``: ID for the meter profile. 2402* ``policy_id``: ID for the policy. 2403* ``meter_enable``: When this parameter has a non-zero value, the meter object 2404 gets enabled at the time of creation, otherwise remains disabled. 2405* ``stats_mask``: Mask of statistics counter types to be enabled for the 2406 meter object. 2407* ``shared``: When this parameter has a non-zero value, the meter object is 2408 shared by multiple flows. Otherwise, meter object is used by single flow. 2409* ``default_input_color``: Default input color for incoming packets. 2410 If incoming packet misses DSCP or VLAN input color table then it will be used 2411 as input color. 2412* ``use_pre_meter_color``: When this parameter has a non-zero value, the 2413 input color for the current meter object is determined by the latest meter 2414 object in the same flow. Otherwise, the current meter object uses the 2415 *dscp_table* to determine the input color. 2416* ``dscp_tbl_entryx``: DSCP table entry x providing meter providing input 2417 color, 0 <= x <= 63. 2418* ``vlan_tbl_entryx``: VLAN table entry x providing meter input color, 2419 0 <= x <= 15. 2420 2421enable port meter 2422~~~~~~~~~~~~~~~~~ 2423 2424Enable meter for the ethernet device:: 2425 2426 testpmd> enable port meter (port_id) (mtr_id) 2427 2428disable port meter 2429~~~~~~~~~~~~~~~~~~ 2430 2431Disable meter for the ethernet device:: 2432 2433 testpmd> disable port meter (port_id) (mtr_id) 2434 2435delete port meter 2436~~~~~~~~~~~~~~~~~ 2437 2438Delete meter for the ethernet device:: 2439 2440 testpmd> del port meter (port_id) (mtr_id) 2441 2442Set port meter profile 2443~~~~~~~~~~~~~~~~~~~~~~ 2444 2445Set meter profile for the ethernet device:: 2446 2447 testpmd> set port meter profile (port_id) (mtr_id) (profile_id) 2448 2449set port meter dscp table 2450~~~~~~~~~~~~~~~~~~~~~~~~~ 2451 2452Set meter dscp table for the ethernet device:: 2453 2454 testpmd> set port meter dscp table (port_id) (mtr_id) (proto) \ 2455 [(dscp_tbl_entry0) (dscp_tbl_entry1)...(dscp_tbl_entry63)] 2456 2457set port meter vlan table 2458~~~~~~~~~~~~~~~~~~~~~~~~~ 2459Set meter VLAN table for the Ethernet device:: 2460 2461 testpmd> set port meter vlan table (port_id) (mtr_id) (proto) \ 2462 [(vlan_tbl_entry0) (vlan_tbl_entry1)...(vlan_tbl_entry15)] 2463 2464set port meter protocol 2465~~~~~~~~~~~~~~~~~~~~~~~ 2466Set meter protocol and corresponding priority:: 2467 2468 testpmd> set port meter proto (port_id) (mtr_id) (proto) (prio) 2469 2470get port meter protocol 2471~~~~~~~~~~~~~~~~~~~~~~~ 2472Get meter protocol:: 2473 2474 testpmd> get port meter proto (port_id) (mtr_id) 2475 2476get port meter protocol priority 2477~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2478Get priority associated to meter protocol:: 2479 2480 testpmd> get port meter proto_prio (port_id) (mtr_id) (proto) 2481 2482set port meter stats mask 2483~~~~~~~~~~~~~~~~~~~~~~~~~ 2484 2485Set meter stats mask for the ethernet device:: 2486 2487 testpmd> set port meter stats mask (port_id) (mtr_id) (stats_mask) 2488 2489where: 2490 2491* ``stats_mask``: Bit mask indicating statistics counter types to be enabled. 2492 2493show port meter stats 2494~~~~~~~~~~~~~~~~~~~~~ 2495 2496Show meter stats of the ethernet device:: 2497 2498 testpmd> show port meter stats (port_id) (mtr_id) (clear) 2499 2500where: 2501 2502* ``clear``: Flag that indicates whether the statistics counters should 2503 be cleared (i.e. set to zero) immediately after they have been read or not. 2504 2505Traffic Management 2506------------------ 2507 2508The following section shows functions for configuring traffic management on 2509the ethernet device through the use of generic TM API. 2510 2511show port traffic management capability 2512~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2513 2514Show traffic management capability of the port:: 2515 2516 testpmd> show port tm cap (port_id) 2517 2518show port traffic management capability (hierarchy level) 2519~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2520 2521Show traffic management hierarchy level capability of the port:: 2522 2523 testpmd> show port tm level cap (port_id) (level_id) 2524 2525show port traffic management capability (hierarchy node level) 2526~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2527 2528Show the traffic management hierarchy node capability of the port:: 2529 2530 testpmd> show port tm node cap (port_id) (node_id) 2531 2532show port traffic management hierarchy node type 2533~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2534 2535Show the port traffic management hierarchy node type:: 2536 2537 testpmd> show port tm node type (port_id) (node_id) 2538 2539show port traffic management hierarchy node stats 2540~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2541 2542Show the port traffic management hierarchy node statistics:: 2543 2544 testpmd> show port tm node stats (port_id) (node_id) (clear) 2545 2546where: 2547 2548* ``clear``: When this parameter has a non-zero value, the statistics counters 2549 are cleared (i.e. set to zero) immediately after they have been read, 2550 otherwise the statistics counters are left untouched. 2551 2552Add port traffic management private shaper profile 2553~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2554 2555Add the port traffic management private shaper profile:: 2556 2557 testpmd> add port tm node shaper profile (port_id) (shaper_profile_id) \ 2558 (cmit_tb_rate) (cmit_tb_size) (peak_tb_rate) (peak_tb_size) \ 2559 (packet_length_adjust) (packet_mode) 2560 2561where: 2562 2563* ``shaper_profile id``: Shaper profile ID for the new profile. 2564* ``cmit_tb_rate``: Committed token bucket rate (bytes per second or packets per second). 2565* ``cmit_tb_size``: Committed token bucket size (bytes or packets). 2566* ``peak_tb_rate``: Peak token bucket rate (bytes per second or packets per second). 2567* ``peak_tb_size``: Peak token bucket size (bytes or packets). 2568* ``packet_length_adjust``: The value (bytes) to be added to the length of 2569 each packet for the purpose of shaping. This parameter value can be used to 2570 correct the packet length with the framing overhead bytes that are consumed 2571 on the wire. 2572* ``packet_mode``: Shaper configured in packet mode. This parameter value if 2573 zero, configures shaper in byte mode and if non-zero configures it in packet 2574 mode. 2575 2576Delete port traffic management private shaper profile 2577~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2578 2579Delete the port traffic management private shaper:: 2580 2581 testpmd> del port tm node shaper profile (port_id) (shaper_profile_id) 2582 2583where: 2584 2585* ``shaper_profile id``: Shaper profile ID that needs to be deleted. 2586 2587Add port traffic management shared shaper 2588~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2589 2590Create the port traffic management shared shaper:: 2591 2592 testpmd> add port tm node shared shaper (port_id) (shared_shaper_id) \ 2593 (shaper_profile_id) 2594 2595where: 2596 2597* ``shared_shaper_id``: Shared shaper ID to be created. 2598* ``shaper_profile id``: Shaper profile ID for shared shaper. 2599 2600Set port traffic management shared shaper 2601~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2602 2603Update the port traffic management shared shaper:: 2604 2605 testpmd> set port tm node shared shaper (port_id) (shared_shaper_id) \ 2606 (shaper_profile_id) 2607 2608where: 2609 2610* ``shared_shaper_id``: Shared shaper ID to be update. 2611* ``shaper_profile id``: Shaper profile ID for shared shaper. 2612 2613Delete port traffic management shared shaper 2614~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2615 2616Delete the port traffic management shared shaper:: 2617 2618 testpmd> del port tm node shared shaper (port_id) (shared_shaper_id) 2619 2620where: 2621 2622* ``shared_shaper_id``: Shared shaper ID to be deleted. 2623 2624Set port traffic management hierarchy node private shaper 2625~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2626 2627set the port traffic management hierarchy node private shaper:: 2628 2629 testpmd> set port tm node shaper profile (port_id) (node_id) \ 2630 (shaper_profile_id) 2631 2632where: 2633 2634* ``shaper_profile id``: Private shaper profile ID to be enabled on the 2635 hierarchy node. 2636 2637Add port traffic management WRED profile 2638~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2639 2640Create a new WRED profile:: 2641 2642 testpmd> add port tm node wred profile (port_id) (wred_profile_id) \ 2643 (color_g) (min_th_g) (max_th_g) (maxp_inv_g) (wq_log2_g) \ 2644 (color_y) (min_th_y) (max_th_y) (maxp_inv_y) (wq_log2_y) \ 2645 (color_r) (min_th_r) (max_th_r) (maxp_inv_r) (wq_log2_r) 2646 2647where: 2648 2649* ``wred_profile id``: Identifier for the newly create WRED profile 2650* ``color_g``: Packet color (green) 2651* ``min_th_g``: Minimum queue threshold for packet with green color 2652* ``max_th_g``: Minimum queue threshold for packet with green color 2653* ``maxp_inv_g``: Inverse of packet marking probability maximum value (maxp) 2654* ``wq_log2_g``: Negated log2 of queue weight (wq) 2655* ``color_y``: Packet color (yellow) 2656* ``min_th_y``: Minimum queue threshold for packet with yellow color 2657* ``max_th_y``: Minimum queue threshold for packet with yellow color 2658* ``maxp_inv_y``: Inverse of packet marking probability maximum value (maxp) 2659* ``wq_log2_y``: Negated log2 of queue weight (wq) 2660* ``color_r``: Packet color (red) 2661* ``min_th_r``: Minimum queue threshold for packet with yellow color 2662* ``max_th_r``: Minimum queue threshold for packet with yellow color 2663* ``maxp_inv_r``: Inverse of packet marking probability maximum value (maxp) 2664* ``wq_log2_r``: Negated log2 of queue weight (wq) 2665 2666Delete port traffic management WRED profile 2667~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2668 2669Delete the WRED profile:: 2670 2671 testpmd> del port tm node wred profile (port_id) (wred_profile_id) 2672 2673Add port traffic management hierarchy nonleaf node 2674~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2675 2676Add nonleaf node to port traffic management hierarchy:: 2677 2678 testpmd> add port tm nonleaf node (port_id) (node_id) (parent_node_id) \ 2679 (priority) (weight) (level_id) (shaper_profile_id) \ 2680 (n_sp_priorities) (stats_mask) (n_shared_shapers) \ 2681 [(shared_shaper_0) (shared_shaper_1) ...] \ 2682 2683where: 2684 2685* ``parent_node_id``: Node ID of the parent. 2686* ``priority``: Node priority (highest node priority is zero). This is used by 2687 the SP algorithm running on the parent node for scheduling this node. 2688* ``weight``: Node weight (lowest weight is one). The node weight is relative 2689 to the weight sum of all siblings that have the same priority. It is used by 2690 the WFQ algorithm running on the parent node for scheduling this node. 2691* ``level_id``: Hierarchy level of the node. 2692* ``shaper_profile_id``: Shaper profile ID of the private shaper to be used by 2693 the node. 2694* ``n_sp_priorities``: Number of strict priorities. 2695* ``stats_mask``: Mask of statistics counter types to be enabled for this node. 2696* ``n_shared_shapers``: Number of shared shapers. 2697* ``shared_shaper_id``: Shared shaper id. 2698 2699Add port traffic management hierarchy nonleaf node with packet mode 2700~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2701 2702Add nonleaf node with packet mode to port traffic management hierarchy:: 2703 2704 testpmd> add port tm nonleaf node pktmode (port_id) (node_id) (parent_node_id) \ 2705 (priority) (weight) (level_id) (shaper_profile_id) \ 2706 (n_sp_priorities) (stats_mask) (n_shared_shapers) \ 2707 [(shared_shaper_0) (shared_shaper_1) ...] \ 2708 2709where: 2710 2711* ``parent_node_id``: Node ID of the parent. 2712* ``priority``: Node priority (highest node priority is zero). This is used by 2713 the SP algorithm running on the parent node for scheduling this node. 2714* ``weight``: Node weight (lowest weight is one). The node weight is relative 2715 to the weight sum of all siblings that have the same priority. It is used by 2716 the WFQ algorithm running on the parent node for scheduling this node. 2717* ``level_id``: Hierarchy level of the node. 2718* ``shaper_profile_id``: Shaper profile ID of the private shaper to be used by 2719 the node. 2720* ``n_sp_priorities``: Number of strict priorities. Packet mode is enabled on 2721 all of them. 2722* ``stats_mask``: Mask of statistics counter types to be enabled for this node. 2723* ``n_shared_shapers``: Number of shared shapers. 2724* ``shared_shaper_id``: Shared shaper id. 2725 2726Add port traffic management hierarchy leaf node 2727~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2728 2729Add leaf node to port traffic management hierarchy:: 2730 2731 testpmd> add port tm leaf node (port_id) (node_id) (parent_node_id) \ 2732 (priority) (weight) (level_id) (shaper_profile_id) \ 2733 (cman_mode) (wred_profile_id) (stats_mask) (n_shared_shapers) \ 2734 [(shared_shaper_id) (shared_shaper_id) ...] \ 2735 2736where: 2737 2738* ``parent_node_id``: Node ID of the parent. 2739* ``priority``: Node priority (highest node priority is zero). This is used by 2740 the SP algorithm running on the parent node for scheduling this node. 2741* ``weight``: Node weight (lowest weight is one). The node weight is relative 2742 to the weight sum of all siblings that have the same priority. It is used by 2743 the WFQ algorithm running on the parent node for scheduling this node. 2744* ``level_id``: Hierarchy level of the node. 2745* ``shaper_profile_id``: Shaper profile ID of the private shaper to be used by 2746 the node. 2747* ``cman_mode``: Congestion management mode to be enabled for this node. 2748* ``wred_profile_id``: WRED profile id to be enabled for this node. 2749* ``stats_mask``: Mask of statistics counter types to be enabled for this node. 2750* ``n_shared_shapers``: Number of shared shapers. 2751* ``shared_shaper_id``: Shared shaper id. 2752 2753Delete port traffic management hierarchy node 2754~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2755 2756Delete node from port traffic management hierarchy:: 2757 2758 testpmd> del port tm node (port_id) (node_id) 2759 2760Update port traffic management hierarchy parent node 2761~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2762 2763Update port traffic management hierarchy parent node:: 2764 2765 testpmd> set port tm node parent (port_id) (node_id) (parent_node_id) \ 2766 (priority) (weight) 2767 2768This function can only be called after the hierarchy commit invocation. Its 2769success depends on the port support for this operation, as advertised through 2770the port capability set. This function is valid for all nodes of the traffic 2771management hierarchy except root node. 2772 2773Suspend port traffic management hierarchy node 2774~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2775 2776 testpmd> suspend port tm node (port_id) (node_id) 2777 2778Resume port traffic management hierarchy node 2779~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2780 2781 testpmd> resume port tm node (port_id) (node_id) 2782 2783Commit port traffic management hierarchy 2784~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2785 2786Commit the traffic management hierarchy on the port:: 2787 2788 testpmd> port tm hierarchy commit (port_id) (clean_on_fail) 2789 2790where: 2791 2792* ``clean_on_fail``: When set to non-zero, hierarchy is cleared on function 2793 call failure. On the other hand, hierarchy is preserved when this parameter 2794 is equal to zero. 2795 2796Set port traffic management mark VLAN dei 2797~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2798 2799Enables/Disables the traffic management marking on the port for VLAN packets:: 2800 2801 testpmd> set port tm mark vlan_dei <port_id> <green> <yellow> <red> 2802 2803where: 2804 2805* ``port_id``: The port which on which VLAN packets marked as ``green`` or 2806 ``yellow`` or ``red`` will have dei bit enabled 2807 2808* ``green`` enable 1, disable 0 marking for dei bit of VLAN packets marked as green 2809 2810* ``yellow`` enable 1, disable 0 marking for dei bit of VLAN packets marked as yellow 2811 2812* ``red`` enable 1, disable 0 marking for dei bit of VLAN packets marked as red 2813 2814Set port traffic management mark IP dscp 2815~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2816 2817Enables/Disables the traffic management marking on the port for IP dscp packets:: 2818 2819 testpmd> set port tm mark ip_dscp <port_id> <green> <yellow> <red> 2820 2821where: 2822 2823* ``port_id``: The port which on which IP packets marked as ``green`` or 2824 ``yellow`` or ``red`` will have IP dscp bits updated 2825 2826* ``green`` enable 1, disable 0 marking IP dscp to low drop precedence for green packets 2827 2828* ``yellow`` enable 1, disable 0 marking IP dscp to medium drop precedence for yellow packets 2829 2830* ``red`` enable 1, disable 0 marking IP dscp to high drop precedence for red packets 2831 2832Set port traffic management mark IP ecn 2833~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2834 2835Enables/Disables the traffic management marking on the port for IP ecn packets:: 2836 2837 testpmd> set port tm mark ip_ecn <port_id> <green> <yellow> <red> 2838 2839where: 2840 2841* ``port_id``: The port which on which IP packets marked as ``green`` or 2842 ``yellow`` or ``red`` will have IP ecn bits updated 2843 2844* ``green`` enable 1, disable 0 marking IP ecn for green marked packets with ecn of 2'b01 or 2'b10 2845 to ecn of 2'b11 when IP is caring TCP or SCTP 2846 2847* ``yellow`` enable 1, disable 0 marking IP ecn for yellow marked packets with ecn of 2'b01 or 2'b10 2848 to ecn of 2'b11 when IP is caring TCP or SCTP 2849 2850* ``red`` enable 1, disable 0 marking IP ecn for yellow marked packets with ecn of 2'b01 or 2'b10 2851 to ecn of 2'b11 when IP is caring TCP or SCTP 2852 2853Congestion Management 2854--------------------- 2855 2856Get capabilities 2857~~~~~~~~~~~~~~~~ 2858 2859Retrieve congestion management capabilities supported by driver for given port. 2860Below example command retrieves capabilities for port 0:: 2861 2862 testpmd> show port cman capa 0 2863 2864Get configuration 2865~~~~~~~~~~~~~~~~~ 2866 2867Retrieve congestion management configuration for given port. 2868Below example command retrieves configuration for port 0:: 2869 2870 testpmd> show port cman config 0 2871 2872Set configuration 2873~~~~~~~~~~~~~~~~~ 2874 2875Configures congestion management settings on given queue 2876or mempool associated with queue. 2877Below example command configures RED as congestion management algorithm 2878for port 0 and queue 0:: 2879 2880 testpmd> set port cman config 0 0 obj queue mode red 10 100 1 2881 2882Filter Functions 2883---------------- 2884 2885This section details the available filter functions that are available. 2886 2887Note these functions interface the deprecated legacy filtering framework, 2888superseded by *rte_flow*. See `Flow rules management`_. 2889 2890.. _testpmd_rte_flow: 2891 2892Flow rules management 2893--------------------- 2894 2895Control of the generic flow API (*rte_flow*) is fully exposed through the 2896``flow`` command (configuration, validation, creation, destruction, queries 2897and operation modes). 2898 2899Considering *rte_flow* overlaps with all `Filter Functions`_, using both 2900features simultaneously may cause undefined side-effects and is therefore 2901not recommended. 2902 2903``flow`` syntax 2904~~~~~~~~~~~~~~~ 2905 2906Because the ``flow`` command uses dynamic tokens to handle the large number 2907of possible flow rules combinations, its behavior differs slightly from 2908other commands, in particular: 2909 2910- Pressing *?* or the *<tab>* key displays contextual help for the current 2911 token, not that of the entire command. 2912 2913- Optional and repeated parameters are supported (provided they are listed 2914 in the contextual help). 2915 2916The first parameter stands for the operation mode. Possible operations and 2917their general syntax are described below. They are covered in detail in the 2918following sections. 2919 2920- Get info about flow engine:: 2921 2922 flow info {port_id} 2923 2924- Configure flow engine:: 2925 2926 flow configure {port_id} 2927 [queues_number {number}] [queues_size {size}] 2928 [counters_number {number}] 2929 [aging_counters_number {number}] 2930 [meters_number {number}] [flags {number}] 2931 2932- Create a pattern template:: 2933 2934 flow pattern_template {port_id} create [pattern_template_id {id}] 2935 [relaxed {boolean}] [ingress] [egress] [transfer] 2936 template {item} [/ {item} [...]] / end 2937 2938- Destroy a pattern template:: 2939 2940 flow pattern_template {port_id} destroy pattern_template {id} [...] 2941 2942- Create an actions template:: 2943 2944 flow actions_template {port_id} create [actions_template_id {id}] 2945 [ingress] [egress] [transfer] 2946 template {action} [/ {action} [...]] / end 2947 mask {action} [/ {action} [...]] / end 2948 2949- Destroy an actions template:: 2950 2951 flow actions_template {port_id} destroy actions_template {id} [...] 2952 2953- Create a table:: 2954 2955 flow table {port_id} create 2956 [table_id {id}] 2957 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 2958 rules_number {number} 2959 pattern_template {pattern_template_id} 2960 actions_template {actions_template_id} 2961 2962- Destroy a table:: 2963 2964 flow table {port_id} destroy table {id} [...] 2965 2966- Check whether a flow rule can be created:: 2967 2968 flow validate {port_id} 2969 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 2970 pattern {item} [/ {item} [...]] / end 2971 actions {action} [/ {action} [...]] / end 2972 2973- Enqueue creation of a flow rule:: 2974 2975 flow queue {port_id} create {queue_id} 2976 [postpone {boolean}] template_table {table_id} 2977 pattern_template {pattern_template_index} 2978 actions_template {actions_template_index} 2979 pattern {item} [/ {item} [...]] / end 2980 actions {action} [/ {action} [...]] / end 2981 2982- Enqueue destruction of specific flow rules:: 2983 2984 flow queue {port_id} destroy {queue_id} 2985 [postpone {boolean}] rule {rule_id} [...] 2986 2987- Push enqueued operations:: 2988 2989 flow push {port_id} queue {queue_id} 2990 2991- Pull all operations results from a queue:: 2992 2993 flow pull {port_id} queue {queue_id} 2994 2995- Create a flow rule:: 2996 2997 flow create {port_id} 2998 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 2999 pattern {item} [/ {item} [...]] / end 3000 actions {action} [/ {action} [...]] / end 3001 3002- Destroy specific flow rules:: 3003 3004 flow destroy {port_id} rule {rule_id} [...] 3005 3006- Destroy all flow rules:: 3007 3008 flow flush {port_id} 3009 3010- Query an existing flow rule:: 3011 3012 flow query {port_id} {rule_id} {action} 3013 3014- List existing flow rules sorted by priority, filtered by group 3015 identifiers:: 3016 3017 flow list {port_id} [group {group_id}] [...] 3018 3019- Restrict ingress traffic to the defined flow rules:: 3020 3021 flow isolate {port_id} {boolean} 3022 3023- Dump internal representation information of all flows in hardware:: 3024 3025 flow dump {port_id} all {output_file} 3026 3027 for one flow:: 3028 3029 flow dump {port_id} rule {rule_id} {output_file} 3030 3031- List and destroy aged flow rules:: 3032 3033 flow aged {port_id} [destroy] 3034 3035- Enqueue list and destroy aged flow rules:: 3036 3037 flow queue {port_id} aged {queue_id} [destroy] 3038 3039- Tunnel offload - create a tunnel stub:: 3040 3041 flow tunnel create {port_id} type {tunnel_type} 3042 3043- Tunnel offload - destroy a tunnel stub:: 3044 3045 flow tunnel destroy {port_id} id {tunnel_id} 3046 3047- Tunnel offload - list port tunnel stubs:: 3048 3049 flow tunnel list {port_id} 3050 3051Retrieving info about flow management engine 3052~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3053 3054``flow info`` retrieves info on pre-configurable resources in the underlying 3055device to give a hint of possible values for flow engine configuration. 3056 3057``rte_flow_info_get()``:: 3058 3059 flow info {port_id} 3060 3061If successful, it will show:: 3062 3063 Flow engine resources on port #[...]: 3064 Number of queues: #[...] 3065 Size of queues: #[...] 3066 Number of counters: #[...] 3067 Number of aging objects: #[...] 3068 Number of meters: #[...] 3069 3070Otherwise it will show an error message of the form:: 3071 3072 Caught error type [...] ([...]): [...] 3073 3074Configuring flow management engine 3075~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3076 3077``flow configure`` pre-allocates all the needed resources in the underlying 3078device to be used later at the flow creation. Flow queues are allocated as well 3079for asynchronous flow creation/destruction operations. It is bound to 3080``rte_flow_configure()``:: 3081 3082 flow configure {port_id} 3083 [queues_number {number}] [queues_size {size}] 3084 [counters_number {number}] 3085 [aging_counters_number {number}] 3086 [host_port {number}] 3087 [meters_number {number}] 3088 [flags {number}] 3089 3090If successful, it will show:: 3091 3092 Configure flows on port #[...]: number of queues #[...] with #[...] elements 3093 3094Otherwise it will show an error message of the form:: 3095 3096 Caught error type [...] ([...]): [...] 3097 3098Creating pattern templates 3099~~~~~~~~~~~~~~~~~~~~~~~~~~ 3100 3101``flow pattern_template create`` creates the specified pattern template. 3102It is bound to ``rte_flow_pattern_template_create()``:: 3103 3104 flow pattern_template {port_id} create [pattern_template_id {id}] 3105 [relaxed {boolean}] [ingress] [egress] [transfer] 3106 template {item} [/ {item} [...]] / end 3107 3108If successful, it will show:: 3109 3110 Pattern template #[...] created 3111 3112Otherwise it will show an error message of the form:: 3113 3114 Caught error type [...] ([...]): [...] 3115 3116This command uses the same pattern items as ``flow create``, 3117their format is described in `Creating flow rules`_. 3118 3119Destroying pattern templates 3120~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3121 3122``flow pattern_template destroy`` destroys one or more pattern templates 3123from their template ID (as returned by ``flow pattern_template create``), 3124this command calls ``rte_flow_pattern_template_destroy()`` as many 3125times as necessary:: 3126 3127 flow pattern_template {port_id} destroy pattern_template {id} [...] 3128 3129If successful, it will show:: 3130 3131 Pattern template #[...] destroyed 3132 3133It does not report anything for pattern template IDs that do not exist. 3134The usual error message is shown when a pattern template cannot be destroyed:: 3135 3136 Caught error type [...] ([...]): [...] 3137 3138Creating actions templates 3139~~~~~~~~~~~~~~~~~~~~~~~~~~ 3140 3141``flow actions_template create`` creates the specified actions template. 3142It is bound to ``rte_flow_actions_template_create()``:: 3143 3144 flow actions_template {port_id} create [actions_template_id {id}] 3145 [ingress] [egress] [transfer] 3146 template {action} [/ {action} [...]] / end 3147 mask {action} [/ {action} [...]] / end 3148 3149If successful, it will show:: 3150 3151 Actions template #[...] created 3152 3153Otherwise it will show an error message of the form:: 3154 3155 Caught error type [...] ([...]): [...] 3156 3157This command uses the same actions as ``flow create``, 3158their format is described in `Creating flow rules`_. 3159 3160Destroying actions templates 3161~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3162 3163``flow actions_template destroy`` destroys one or more actions templates 3164from their template ID (as returned by ``flow actions_template create``), 3165this command calls ``rte_flow_actions_template_destroy()`` as many 3166times as necessary:: 3167 3168 flow actions_template {port_id} destroy actions_template {id} [...] 3169 3170If successful, it will show:: 3171 3172 Actions template #[...] destroyed 3173 3174It does not report anything for actions template IDs that do not exist. 3175The usual error message is shown when an actions template cannot be destroyed:: 3176 3177 Caught error type [...] ([...]): [...] 3178 3179Creating template table 3180~~~~~~~~~~~~~~~~~~~~~~~ 3181 3182``flow template_table create`` creates the specified template table. 3183It is bound to ``rte_flow_template_table_create()``:: 3184 3185 flow template_table {port_id} create 3186 [table_id {id}] [group {group_id}] 3187 [priority {level}] [ingress] [egress] 3188 [transfer [vport_orig] [wire_orig]] 3189 rules_number {number} 3190 pattern_template {pattern_template_id} 3191 actions_template {actions_template_id} 3192 3193If successful, it will show:: 3194 3195 Template table #[...] created 3196 3197Otherwise it will show an error message of the form:: 3198 3199 Caught error type [...] ([...]): [...] 3200 3201Destroying flow table 3202~~~~~~~~~~~~~~~~~~~~~ 3203 3204``flow template_table destroy`` destroys one or more template tables 3205from their table ID (as returned by ``flow template_table create``), 3206this command calls ``rte_flow_template_table_destroy()`` as many 3207times as necessary:: 3208 3209 flow template_table {port_id} destroy table {id} [...] 3210 3211If successful, it will show:: 3212 3213 Template table #[...] destroyed 3214 3215It does not report anything for table IDs that do not exist. 3216The usual error message is shown when a table cannot be destroyed:: 3217 3218 Caught error type [...] ([...]): [...] 3219 3220Pushing enqueued operations 3221~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3222 3223``flow push`` pushes all the outstanding enqueued operations 3224to the underlying device immediately. 3225It is bound to ``rte_flow_push()``:: 3226 3227 flow push {port_id} queue {queue_id} 3228 3229If successful, it will show:: 3230 3231 Queue #[...] operations pushed 3232 3233The usual error message is shown when operations cannot be pushed:: 3234 3235 Caught error type [...] ([...]): [...] 3236 3237Pulling flow operations results 3238~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3239 3240``flow pull`` asks the underlying device about flow queue operations 3241results and return all the processed (successfully or not) operations. 3242It is bound to ``rte_flow_pull()``:: 3243 3244 flow pull {port_id} queue {queue_id} 3245 3246If successful, it will show:: 3247 3248 Queue #[...] pulled #[...] operations (#[...] failed, #[...] succeeded) 3249 3250The usual error message is shown when operations results cannot be pulled:: 3251 3252 Caught error type [...] ([...]): [...] 3253 3254Creating a tunnel stub for offload 3255~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3256 3257``flow tunnel create`` setup a tunnel stub for tunnel offload flow rules:: 3258 3259 flow tunnel create {port_id} type {tunnel_type} 3260 3261If successful, it will return a tunnel stub ID usable with other commands:: 3262 3263 port [...]: flow tunnel #[...] type [...] 3264 3265Tunnel stub ID is relative to a port. 3266 3267Destroying tunnel offload stub 3268~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3269 3270``flow tunnel destroy`` destroy port tunnel stub:: 3271 3272 flow tunnel destroy {port_id} id {tunnel_id} 3273 3274Listing tunnel offload stubs 3275~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3276 3277``flow tunnel list`` list port tunnel offload stubs:: 3278 3279 flow tunnel list {port_id} 3280 3281Validating flow rules 3282~~~~~~~~~~~~~~~~~~~~~ 3283 3284``flow validate`` reports whether a flow rule would be accepted by the 3285underlying device in its current state but stops short of creating it. It is 3286bound to ``rte_flow_validate()``:: 3287 3288 flow validate {port_id} 3289 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 3290 pattern {item} [/ {item} [...]] / end 3291 actions {action} [/ {action} [...]] / end 3292 3293If successful, it will show:: 3294 3295 Flow rule validated 3296 3297Otherwise it will show an error message of the form:: 3298 3299 Caught error type [...] ([...]): [...] 3300 3301This command uses the same parameters as ``flow create``, their format is 3302described in `Creating flow rules`_. 3303 3304Check whether redirecting any Ethernet packet received on port 0 to RX queue 3305index 6 is supported:: 3306 3307 testpmd> flow validate 0 ingress pattern eth / end 3308 actions queue index 6 / end 3309 Flow rule validated 3310 testpmd> 3311 3312Port 0 does not support TCPv6 rules:: 3313 3314 testpmd> flow validate 0 ingress pattern eth / ipv6 / tcp / end 3315 actions drop / end 3316 Caught error type 9 (specific pattern item): Invalid argument 3317 testpmd> 3318 3319Creating flow rules 3320~~~~~~~~~~~~~~~~~~~ 3321 3322``flow create`` validates and creates the specified flow rule. It is bound 3323to ``rte_flow_create()``:: 3324 3325 flow create {port_id} 3326 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 3327 [tunnel_set {tunnel_id}] [tunnel_match {tunnel_id}] 3328 pattern {item} [/ {item} [...]] / end 3329 actions {action} [/ {action} [...]] / end 3330 3331If successful, it will return a flow rule ID usable with other commands:: 3332 3333 Flow rule #[...] created 3334 3335Otherwise it will show an error message of the form:: 3336 3337 Caught error type [...] ([...]): [...] 3338 3339Parameters describe in the following order: 3340 3341- Attributes (*group*, *priority*, *ingress*, *egress*, *transfer* tokens). 3342- Tunnel offload specification (tunnel_set, tunnel_match) 3343- A matching pattern, starting with the *pattern* token and terminated by an 3344 *end* pattern item. 3345- Actions, starting with the *actions* token and terminated by an *end* 3346 action. 3347 3348These translate directly to *rte_flow* objects provided as-is to the 3349underlying functions. 3350 3351The shortest valid definition only comprises mandatory tokens:: 3352 3353 testpmd> flow create 0 pattern end actions end 3354 3355Note that PMDs may refuse rules that essentially do nothing such as this 3356one. 3357 3358**All unspecified object values are automatically initialized to 0.** 3359 3360Enqueueing creation of flow rules 3361~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3362 3363``flow queue create`` adds creation operation of a flow rule to a queue. 3364It is bound to ``rte_flow_async_create()``:: 3365 3366 flow queue {port_id} create {queue_id} 3367 [postpone {boolean}] template_table {table_id} 3368 pattern_template {pattern_template_index} 3369 actions_template {actions_template_index} 3370 pattern {item} [/ {item} [...]] / end 3371 actions {action} [/ {action} [...]] / end 3372 3373If successful, it will return a flow rule ID usable with other commands:: 3374 3375 Flow rule #[...] creaion enqueued 3376 3377Otherwise it will show an error message of the form:: 3378 3379 Caught error type [...] ([...]): [...] 3380 3381This command uses the same pattern items and actions as ``flow create``, 3382their format is described in `Creating flow rules`_. 3383 3384``flow queue pull`` must be called to retrieve the operation status. 3385 3386Attributes 3387^^^^^^^^^^ 3388 3389These tokens affect flow rule attributes (``struct rte_flow_attr``) and are 3390specified before the ``pattern`` token. 3391 3392- ``group {group id}``: priority group. 3393- ``priority {level}``: priority level within group. 3394- ``ingress``: rule applies to ingress traffic. 3395- ``egress``: rule applies to egress traffic. 3396- ``transfer``: apply rule directly to endpoints found in pattern. 3397 3398Please note that use of ``transfer`` attribute requires that the flow and 3399its indirect components be managed via so-called ``transfer`` proxy port. 3400See `show flow transfer proxy port ID for the given port`_ for details. 3401 3402Each instance of an attribute specified several times overrides the previous 3403value as shown below (group 4 is used):: 3404 3405 testpmd> flow create 0 group 42 group 24 group 4 [...] 3406 3407Note that once enabled, ``ingress`` and ``egress`` cannot be disabled. 3408 3409While not specifying a direction is an error, some rules may allow both 3410simultaneously. 3411 3412Most rules affect RX therefore contain the ``ingress`` token:: 3413 3414 testpmd> flow create 0 ingress pattern [...] 3415 3416Tunnel offload 3417^^^^^^^^^^^^^^ 3418 3419Indicate tunnel offload rule type 3420 3421- ``tunnel_set {tunnel_id}``: mark rule as tunnel offload decap_set type. 3422- ``tunnel_match {tunnel_id}``: mark rule as tunnel offload match type. 3423 3424Matching pattern 3425^^^^^^^^^^^^^^^^ 3426 3427A matching pattern starts after the ``pattern`` token. It is made of pattern 3428items and is terminated by a mandatory ``end`` item. 3429 3430Items are named after their type (*RTE_FLOW_ITEM_TYPE_* from ``enum 3431rte_flow_item_type``). 3432 3433The ``/`` token is used as a separator between pattern items as shown 3434below:: 3435 3436 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end [...] 3437 3438Note that protocol items like these must be stacked from lowest to highest 3439layer to make sense. For instance, the following rule is either invalid or 3440unlikely to match any packet:: 3441 3442 testpmd> flow create 0 ingress pattern eth / udp / ipv4 / end [...] 3443 3444More information on these restrictions can be found in the *rte_flow* 3445documentation. 3446 3447Several items support additional specification structures, for example 3448``ipv4`` allows specifying source and destination addresses as follows:: 3449 3450 testpmd> flow create 0 ingress pattern eth / ipv4 src is 10.1.1.1 3451 dst is 10.2.0.0 / end [...] 3452 3453This rule matches all IPv4 traffic with the specified properties. 3454 3455In this example, ``src`` and ``dst`` are field names of the underlying 3456``struct rte_flow_item_ipv4`` object. All item properties can be specified 3457in a similar fashion. 3458 3459The ``is`` token means that the subsequent value must be matched exactly, 3460and assigns ``spec`` and ``mask`` fields in ``struct rte_flow_item`` 3461accordingly. Possible assignment tokens are: 3462 3463- ``is``: match value perfectly (with full bit-mask). 3464- ``spec``: match value according to configured bit-mask. 3465- ``last``: specify upper bound to establish a range. 3466- ``mask``: specify bit-mask with relevant bits set to one. 3467- ``prefix``: generate bit-mask with <prefix-length> most-significant bits set to one. 3468 3469These yield identical results:: 3470 3471 ipv4 src is 10.1.1.1 3472 3473:: 3474 3475 ipv4 src spec 10.1.1.1 src mask 255.255.255.255 3476 3477:: 3478 3479 ipv4 src spec 10.1.1.1 src prefix 32 3480 3481:: 3482 3483 ipv4 src is 10.1.1.1 src last 10.1.1.1 # range with a single value 3484 3485:: 3486 3487 ipv4 src is 10.1.1.1 src last 0 # 0 disables range 3488 3489Inclusive ranges can be defined with ``last``:: 3490 3491 ipv4 src is 10.1.1.1 src last 10.2.3.4 # 10.1.1.1 to 10.2.3.4 3492 3493Note that ``mask`` affects both ``spec`` and ``last``:: 3494 3495 ipv4 src is 10.1.1.1 src last 10.2.3.4 src mask 255.255.0.0 3496 # matches 10.1.0.0 to 10.2.255.255 3497 3498Properties can be modified multiple times:: 3499 3500 ipv4 src is 10.1.1.1 src is 10.1.2.3 src is 10.2.3.4 # matches 10.2.3.4 3501 3502:: 3503 3504 ipv4 src is 10.1.1.1 src prefix 24 src prefix 16 # matches 10.1.0.0/16 3505 3506Pattern items 3507^^^^^^^^^^^^^ 3508 3509This section lists supported pattern items and their attributes, if any. 3510 3511- ``end``: end list of pattern items. 3512 3513- ``void``: no-op pattern item. 3514 3515- ``invert``: perform actions when pattern does not match. 3516 3517- ``any``: match any protocol for the current layer. 3518 3519 - ``num {unsigned}``: number of layers covered. 3520 3521- ``port_id``: match traffic from/to a given DPDK port ID. 3522 3523 - ``id {unsigned}``: DPDK port ID. 3524 3525- ``mark``: match value set in previously matched flow rule using the mark action. 3526 3527 - ``id {unsigned}``: arbitrary integer value. 3528 3529- ``raw``: match an arbitrary byte string. 3530 3531 - ``relative {boolean}``: look for pattern after the previous item. 3532 - ``search {boolean}``: search pattern from offset (see also limit). 3533 - ``offset {integer}``: absolute or relative offset for pattern. 3534 - ``limit {unsigned}``: search area limit for start of pattern. 3535 - ``pattern {string}``: byte string to look for. 3536 - ``pattern_hex {string}``: byte string (provided in hexadecimal) to look for. 3537 3538- ``eth``: match Ethernet header. 3539 3540 - ``dst {MAC-48}``: destination MAC. 3541 - ``src {MAC-48}``: source MAC. 3542 - ``type {unsigned}``: EtherType or TPID. 3543 3544- ``vlan``: match 802.1Q/ad VLAN tag. 3545 3546 - ``tci {unsigned}``: tag control information. 3547 - ``pcp {unsigned}``: priority code point. 3548 - ``dei {unsigned}``: drop eligible indicator. 3549 - ``vid {unsigned}``: VLAN identifier. 3550 - ``inner_type {unsigned}``: inner EtherType or TPID. 3551 3552- ``ipv4``: match IPv4 header. 3553 3554 - ``version_ihl {unsigned}``: IPv4 version and IP header length. 3555 - ``tos {unsigned}``: type of service. 3556 - ``ttl {unsigned}``: time to live. 3557 - ``proto {unsigned}``: next protocol ID. 3558 - ``src {ipv4 address}``: source address. 3559 - ``dst {ipv4 address}``: destination address. 3560 3561- ``ipv6``: match IPv6 header. 3562 3563 - ``tc {unsigned}``: traffic class. 3564 - ``flow {unsigned}``: flow label. 3565 - ``proto {unsigned}``: protocol (next header). 3566 - ``hop {unsigned}``: hop limit. 3567 - ``src {ipv6 address}``: source address. 3568 - ``dst {ipv6 address}``: destination address. 3569 3570- ``icmp``: match ICMP header. 3571 3572 - ``type {unsigned}``: ICMP packet type. 3573 - ``code {unsigned}``: ICMP packet code. 3574 3575- ``udp``: match UDP header. 3576 3577 - ``src {unsigned}``: UDP source port. 3578 - ``dst {unsigned}``: UDP destination port. 3579 3580- ``tcp``: match TCP header. 3581 3582 - ``src {unsigned}``: TCP source port. 3583 - ``dst {unsigned}``: TCP destination port. 3584 3585- ``sctp``: match SCTP header. 3586 3587 - ``src {unsigned}``: SCTP source port. 3588 - ``dst {unsigned}``: SCTP destination port. 3589 - ``tag {unsigned}``: validation tag. 3590 - ``cksum {unsigned}``: checksum. 3591 3592- ``vxlan``: match VXLAN header. 3593 3594 - ``vni {unsigned}``: VXLAN identifier. 3595 - ``last_rsvd {unsigned}``: VXLAN last reserved 8-bits. 3596 3597- ``e_tag``: match IEEE 802.1BR E-Tag header. 3598 3599 - ``grp_ecid_b {unsigned}``: GRP and E-CID base. 3600 3601- ``nvgre``: match NVGRE header. 3602 3603 - ``tni {unsigned}``: virtual subnet ID. 3604 3605- ``mpls``: match MPLS header. 3606 3607 - ``label {unsigned}``: MPLS label. 3608 3609- ``gre``: match GRE header. 3610 3611 - ``protocol {unsigned}``: protocol type. 3612 3613- ``gre_key``: match GRE optional key field. 3614 3615 - ``value {unsigned}``: key value. 3616 3617- ``gre_option``: match GRE optional fields(checksum/key/sequence). 3618 3619 - ``checksum {unsigned}``: checksum value. 3620 - ``key {unsigned}``: key value. 3621 - ``sequence {unsigned}``: sequence number value. 3622 3623- ``fuzzy``: fuzzy pattern match, expect faster than default. 3624 3625 - ``thresh {unsigned}``: accuracy threshold. 3626 3627- ``gtp``, ``gtpc``, ``gtpu``: match GTPv1 header. 3628 3629 - ``teid {unsigned}``: tunnel endpoint identifier. 3630 3631- ``geneve``: match GENEVE header. 3632 3633 - ``vni {unsigned}``: virtual network identifier. 3634 - ``protocol {unsigned}``: protocol type. 3635 3636- ``geneve-opt``: match GENEVE header option. 3637 3638 - ``class {unsigned}``: GENEVE option class. 3639 - ``type {unsigned}``: GENEVE option type. 3640 - ``length {unsigned}``: GENEVE option length in 32-bit words. 3641 - ``data {hex string}``: GENEVE option data, the length is defined by 3642 ``length`` field. 3643 3644- ``vxlan-gpe``: match VXLAN-GPE header. 3645 3646 - ``vni {unsigned}``: VXLAN-GPE identifier. 3647 3648- ``arp_eth_ipv4``: match ARP header for Ethernet/IPv4. 3649 3650 - ``sha {MAC-48}``: sender hardware address. 3651 - ``spa {ipv4 address}``: sender IPv4 address. 3652 - ``tha {MAC-48}``: target hardware address. 3653 - ``tpa {ipv4 address}``: target IPv4 address. 3654 3655- ``ipv6_ext``: match presence of any IPv6 extension header. 3656 3657 - ``next_hdr {unsigned}``: next header. 3658 3659- ``icmp6``: match any ICMPv6 header. 3660 3661 - ``type {unsigned}``: ICMPv6 type. 3662 - ``code {unsigned}``: ICMPv6 code. 3663 3664- ``icmp6_echo_request``: match ICMPv6 echo request. 3665 3666 - ``ident {unsigned}``: ICMPv6 echo request identifier. 3667 - ``seq {unsigned}``: ICMPv6 echo request sequence number. 3668 3669- ``icmp6_echo_reply``: match ICMPv6 echo reply. 3670 3671 - ``ident {unsigned}``: ICMPv6 echo reply identifier. 3672 - ``seq {unsigned}``: ICMPv6 echo reply sequence number. 3673 3674- ``icmp6_nd_ns``: match ICMPv6 neighbor discovery solicitation. 3675 3676 - ``target_addr {ipv6 address}``: target address. 3677 3678- ``icmp6_nd_na``: match ICMPv6 neighbor discovery advertisement. 3679 3680 - ``target_addr {ipv6 address}``: target address. 3681 3682- ``icmp6_nd_opt``: match presence of any ICMPv6 neighbor discovery option. 3683 3684 - ``type {unsigned}``: ND option type. 3685 3686- ``icmp6_nd_opt_sla_eth``: match ICMPv6 neighbor discovery source Ethernet 3687 link-layer address option. 3688 3689 - ``sla {MAC-48}``: source Ethernet LLA. 3690 3691- ``icmp6_nd_opt_tla_eth``: match ICMPv6 neighbor discovery target Ethernet 3692 link-layer address option. 3693 3694 - ``tla {MAC-48}``: target Ethernet LLA. 3695 3696- ``meta``: match application specific metadata. 3697 3698 - ``data {unsigned}``: metadata value. 3699 3700- ``gtp_psc``: match GTP PDU extension header with type 0x85. 3701 3702 - ``pdu_type {unsigned}``: PDU type. 3703 3704 - ``qfi {unsigned}``: QoS flow identifier. 3705 3706- ``pppoes``, ``pppoed``: match PPPoE header. 3707 3708 - ``session_id {unsigned}``: session identifier. 3709 3710- ``pppoe_proto_id``: match PPPoE session protocol identifier. 3711 3712 - ``proto_id {unsigned}``: PPP protocol identifier. 3713 3714- ``l2tpv3oip``: match L2TPv3 over IP header. 3715 3716 - ``session_id {unsigned}``: L2TPv3 over IP session identifier. 3717 3718- ``ah``: match AH header. 3719 3720 - ``spi {unsigned}``: security parameters index. 3721 3722- ``pfcp``: match PFCP header. 3723 3724 - ``s_field {unsigned}``: S field. 3725 - ``seid {unsigned}``: session endpoint identifier. 3726 3727- ``integrity``: match packet integrity. 3728 3729 - ``level {unsigned}``: Packet encapsulation level the item should 3730 apply to. See rte_flow_action_rss for details. 3731 - ``value {unsigned}``: A bitmask that specify what packet elements 3732 must be matched for integrity. 3733 3734- ``conntrack``: match conntrack state. 3735 3736- ``port_representor``: match traffic entering the embedded switch from the given ethdev 3737 3738 - ``port_id {unsigned}``: ethdev port ID 3739 3740- ``represented_port``: match traffic entering the embedded switch from 3741 the entity represented by the given ethdev 3742 3743 - ``ethdev_port_id {unsigned}``: ethdev port ID 3744 3745- ``l2tpv2``: match L2TPv2 header. 3746 3747 - ``length {unsigned}``: L2TPv2 option length. 3748 - ``tunnel_id {unsigned}``: L2TPv2 tunnel identifier. 3749 - ``session_id {unsigned}``: L2TPv2 session identifier. 3750 - ``ns {unsigned}``: L2TPv2 option ns. 3751 - ``nr {unsigned}``: L2TPv2 option nr. 3752 - ``offset_size {unsigned}``: L2TPv2 option offset. 3753 3754- ``ppp``: match PPP header. 3755 3756 - ``addr {unsigned}``: PPP address. 3757 - ``ctrl {unsigned}``: PPP control. 3758 - ``proto_id {unsigned}``: PPP protocol identifier. 3759 3760- ``meter``: match meter color. 3761 3762 - ``color {value}``: meter color value (green/yellow/red). 3763 3764- ``send_to_kernel``: send packets to kernel. 3765 3766 3767Actions list 3768^^^^^^^^^^^^ 3769 3770A list of actions starts after the ``actions`` token in the same fashion as 3771`Matching pattern`_; actions are separated by ``/`` tokens and the list is 3772terminated by a mandatory ``end`` action. 3773 3774Actions are named after their type (*RTE_FLOW_ACTION_TYPE_* from ``enum 3775rte_flow_action_type``). 3776 3777Dropping all incoming UDPv4 packets can be expressed as follows:: 3778 3779 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end 3780 actions drop / end 3781 3782Several actions have configurable properties which must be specified when 3783there is no valid default value. For example, ``queue`` requires a target 3784queue index. 3785 3786This rule redirects incoming UDPv4 traffic to queue index 6:: 3787 3788 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end 3789 actions queue index 6 / end 3790 3791While this one could be rejected by PMDs (unspecified queue index):: 3792 3793 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end 3794 actions queue / end 3795 3796As defined by *rte_flow*, the list is not ordered, all actions of a given 3797rule are performed simultaneously. These are equivalent:: 3798 3799 queue index 6 / void / mark id 42 / end 3800 3801:: 3802 3803 void / mark id 42 / queue index 6 / end 3804 3805All actions in a list should have different types, otherwise only the last 3806action of a given type is taken into account:: 3807 3808 queue index 4 / queue index 5 / queue index 6 / end # will use queue 6 3809 3810:: 3811 3812 drop / drop / drop / end # drop is performed only once 3813 3814:: 3815 3816 mark id 42 / queue index 3 / mark id 24 / end # mark will be 24 3817 3818Considering they are performed simultaneously, opposite and overlapping 3819actions can sometimes be combined when the end result is unambiguous:: 3820 3821 drop / queue index 6 / end # drop has no effect 3822 3823:: 3824 3825 queue index 6 / rss queues 6 7 8 / end # queue has no effect 3826 3827:: 3828 3829 drop / passthru / end # drop has no effect 3830 3831Note that PMDs may still refuse such combinations. 3832 3833Actions 3834^^^^^^^ 3835 3836This section lists supported actions and their attributes, if any. 3837 3838- ``end``: end list of actions. 3839 3840- ``void``: no-op action. 3841 3842- ``passthru``: let subsequent rule process matched packets. 3843 3844- ``jump``: redirect traffic to group on device. 3845 3846 - ``group {unsigned}``: group to redirect to. 3847 3848- ``mark``: attach 32 bit value to packets. 3849 3850 - ``id {unsigned}``: 32 bit value to return with packets. 3851 3852- ``flag``: flag packets. 3853 3854- ``queue``: assign packets to a given queue index. 3855 3856 - ``index {unsigned}``: queue index to use. 3857 3858- ``drop``: drop packets (note: passthru has priority). 3859 3860- ``count``: enable counters for this rule. 3861 3862- ``rss``: spread packets among several queues. 3863 3864 - ``func {hash function}``: RSS hash function to apply, allowed tokens are 3865 ``toeplitz``, ``simple_xor``, ``symmetric_toeplitz`` and ``default``. 3866 3867 - ``level {unsigned}``: encapsulation level for ``types``. 3868 3869 - ``types [{RSS hash type} [...]] end``: specific RSS hash types. 3870 Note that an empty list does not disable RSS but instead requests 3871 unspecified "best-effort" settings. 3872 3873 - ``key {string}``: RSS hash key, overrides ``key_len``. 3874 3875 - ``key_len {unsigned}``: RSS hash key length in bytes, can be used in 3876 conjunction with ``key`` to pad or truncate it. 3877 3878 - ``queues [{unsigned} [...]] end``: queue indices to use. 3879 3880- ``pf``: direct traffic to physical function. 3881 3882- ``vf``: direct traffic to a virtual function ID. 3883 3884 - ``original {boolean}``: use original VF ID if possible. 3885 - ``id {unsigned}``: VF ID. 3886 3887- ``port_id``: direct matching traffic to a given DPDK port ID. 3888 3889 - ``original {boolean}``: use original DPDK port ID if possible. 3890 - ``id {unsigned}``: DPDK port ID. 3891 3892- ``of_set_mpls_ttl``: OpenFlow's ``OFPAT_SET_MPLS_TTL``. 3893 3894 - ``mpls_ttl``: MPLS TTL. 3895 3896- ``of_dec_mpls_ttl``: OpenFlow's ``OFPAT_DEC_MPLS_TTL``. 3897 3898- ``of_set_nw_ttl``: OpenFlow's ``OFPAT_SET_NW_TTL``. 3899 3900 - ``nw_ttl``: IP TTL. 3901 3902- ``of_dec_nw_ttl``: OpenFlow's ``OFPAT_DEC_NW_TTL``. 3903 3904- ``of_copy_ttl_out``: OpenFlow's ``OFPAT_COPY_TTL_OUT``. 3905 3906- ``of_copy_ttl_in``: OpenFlow's ``OFPAT_COPY_TTL_IN``. 3907 3908- ``of_pop_vlan``: OpenFlow's ``OFPAT_POP_VLAN``. 3909 3910- ``of_push_vlan``: OpenFlow's ``OFPAT_PUSH_VLAN``. 3911 3912 - ``ethertype``: Ethertype. 3913 3914- ``of_set_vlan_vid``: OpenFlow's ``OFPAT_SET_VLAN_VID``. 3915 3916 - ``vlan_vid``: VLAN id. 3917 3918- ``of_set_vlan_pcp``: OpenFlow's ``OFPAT_SET_VLAN_PCP``. 3919 3920 - ``vlan_pcp``: VLAN priority. 3921 3922- ``of_pop_mpls``: OpenFlow's ``OFPAT_POP_MPLS``. 3923 3924 - ``ethertype``: Ethertype. 3925 3926- ``of_push_mpls``: OpenFlow's ``OFPAT_PUSH_MPLS``. 3927 3928 - ``ethertype``: Ethertype. 3929 3930- ``vxlan_encap``: Performs a VXLAN encapsulation, outer layer configuration 3931 is done through `Config VXLAN Encap outer layers`_. 3932 3933- ``vxlan_decap``: Performs a decapsulation action by stripping all headers of 3934 the VXLAN tunnel network overlay from the matched flow. 3935 3936- ``nvgre_encap``: Performs a NVGRE encapsulation, outer layer configuration 3937 is done through `Config NVGRE Encap outer layers`_. 3938 3939- ``nvgre_decap``: Performs a decapsulation action by stripping all headers of 3940 the NVGRE tunnel network overlay from the matched flow. 3941 3942- ``l2_encap``: Performs a L2 encapsulation, L2 configuration 3943 is done through `Config L2 Encap`_. 3944 3945- ``l2_decap``: Performs a L2 decapsulation, L2 configuration 3946 is done through `Config L2 Decap`_. 3947 3948- ``mplsogre_encap``: Performs a MPLSoGRE encapsulation, outer layer 3949 configuration is done through `Config MPLSoGRE Encap outer layers`_. 3950 3951- ``mplsogre_decap``: Performs a MPLSoGRE decapsulation, outer layer 3952 configuration is done through `Config MPLSoGRE Decap outer layers`_. 3953 3954- ``mplsoudp_encap``: Performs a MPLSoUDP encapsulation, outer layer 3955 configuration is done through `Config MPLSoUDP Encap outer layers`_. 3956 3957- ``mplsoudp_decap``: Performs a MPLSoUDP decapsulation, outer layer 3958 configuration is done through `Config MPLSoUDP Decap outer layers`_. 3959 3960- ``set_ipv4_src``: Set a new IPv4 source address in the outermost IPv4 header. 3961 3962 - ``ipv4_addr``: New IPv4 source address. 3963 3964- ``set_ipv4_dst``: Set a new IPv4 destination address in the outermost IPv4 3965 header. 3966 3967 - ``ipv4_addr``: New IPv4 destination address. 3968 3969- ``set_ipv6_src``: Set a new IPv6 source address in the outermost IPv6 header. 3970 3971 - ``ipv6_addr``: New IPv6 source address. 3972 3973- ``set_ipv6_dst``: Set a new IPv6 destination address in the outermost IPv6 3974 header. 3975 3976 - ``ipv6_addr``: New IPv6 destination address. 3977 3978- ``set_tp_src``: Set a new source port number in the outermost TCP/UDP 3979 header. 3980 3981 - ``port``: New TCP/UDP source port number. 3982 3983- ``set_tp_dst``: Set a new destination port number in the outermost TCP/UDP 3984 header. 3985 3986 - ``port``: New TCP/UDP destination port number. 3987 3988- ``mac_swap``: Swap the source and destination MAC addresses in the outermost 3989 Ethernet header. 3990 3991- ``dec_ttl``: Performs a decrease TTL value action 3992 3993- ``set_ttl``: Set TTL value with specified value 3994 - ``ttl_value {unsigned}``: The new TTL value to be set 3995 3996- ``set_mac_src``: set source MAC address 3997 3998 - ``mac_addr {MAC-48}``: new source MAC address 3999 4000- ``set_mac_dst``: set destination MAC address 4001 4002 - ``mac_addr {MAC-48}``: new destination MAC address 4003 4004- ``inc_tcp_seq``: Increase sequence number in the outermost TCP header. 4005 4006 - ``value {unsigned}``: Value to increase TCP sequence number by. 4007 4008- ``dec_tcp_seq``: Decrease sequence number in the outermost TCP header. 4009 4010 - ``value {unsigned}``: Value to decrease TCP sequence number by. 4011 4012- ``inc_tcp_ack``: Increase acknowledgment number in the outermost TCP header. 4013 4014 - ``value {unsigned}``: Value to increase TCP acknowledgment number by. 4015 4016- ``dec_tcp_ack``: Decrease acknowledgment number in the outermost TCP header. 4017 4018 - ``value {unsigned}``: Value to decrease TCP acknowledgment number by. 4019 4020- ``set_ipv4_dscp``: Set IPv4 DSCP value with specified value 4021 4022 - ``dscp_value {unsigned}``: The new DSCP value to be set 4023 4024- ``set_ipv6_dscp``: Set IPv6 DSCP value with specified value 4025 4026 - ``dscp_value {unsigned}``: The new DSCP value to be set 4027 4028- ``indirect``: Use indirect action created via 4029 ``flow indirect_action {port_id} create`` 4030 4031 - ``indirect_action_id {unsigned}``: Indirect action ID to use 4032 4033- ``color``: Color the packet to reflect the meter color result 4034 4035 - ``type {value}``: Set color type with specified value(green/yellow/red) 4036 4037- ``port_representor``: at embedded switch level, send matching traffic to 4038 the given ethdev 4039 4040 - ``port_id {unsigned}``: ethdev port ID 4041 4042- ``represented_port``: at embedded switch level, send matching traffic to 4043 the entity represented by the given ethdev 4044 4045 - ``ethdev_port_id {unsigned}``: ethdev port ID 4046 4047- ``meter_mark``: meter the directed packets using profile and policy 4048 4049 - ``mtr_profile {unsigned}``: meter profile ID to use 4050 - ``mtr_policy {unsigned}``: meter policy ID to use 4051 - ``mtr_color_mode {unsigned}``: meter color-awareness mode (blind/aware) 4052 - ``mtr_init_color {value}``: initial color value (green/yellow/red) 4053 - ``mtr_state {unsigned}``: meter state (disabled/enabled) 4054 4055Destroying flow rules 4056~~~~~~~~~~~~~~~~~~~~~ 4057 4058``flow destroy`` destroys one or more rules from their rule ID (as returned 4059by ``flow create``), this command calls ``rte_flow_destroy()`` as many 4060times as necessary:: 4061 4062 flow destroy {port_id} rule {rule_id} [...] 4063 4064If successful, it will show:: 4065 4066 Flow rule #[...] destroyed 4067 4068It does not report anything for rule IDs that do not exist. The usual error 4069message is shown when a rule cannot be destroyed:: 4070 4071 Caught error type [...] ([...]): [...] 4072 4073``flow flush`` destroys all rules on a device and does not take extra 4074arguments. It is bound to ``rte_flow_flush()``:: 4075 4076 flow flush {port_id} 4077 4078Any errors are reported as above. 4079 4080Creating several rules and destroying them:: 4081 4082 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4083 actions queue index 2 / end 4084 Flow rule #0 created 4085 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4086 actions queue index 3 / end 4087 Flow rule #1 created 4088 testpmd> flow destroy 0 rule 0 rule 1 4089 Flow rule #1 destroyed 4090 Flow rule #0 destroyed 4091 testpmd> 4092 4093The same result can be achieved using ``flow flush``:: 4094 4095 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4096 actions queue index 2 / end 4097 Flow rule #0 created 4098 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4099 actions queue index 3 / end 4100 Flow rule #1 created 4101 testpmd> flow flush 0 4102 testpmd> 4103 4104Non-existent rule IDs are ignored:: 4105 4106 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4107 actions queue index 2 / end 4108 Flow rule #0 created 4109 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4110 actions queue index 3 / end 4111 Flow rule #1 created 4112 testpmd> flow destroy 0 rule 42 rule 10 rule 2 4113 testpmd> 4114 testpmd> flow destroy 0 rule 0 4115 Flow rule #0 destroyed 4116 testpmd> 4117 4118Enqueueing destruction of flow rules 4119~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4120 4121``flow queue destroy`` adds destruction operations to destroy one or more rules 4122from their rule ID (as returned by ``flow queue create``) to a queue, 4123this command calls ``rte_flow_async_destroy()`` as many times as necessary:: 4124 4125 flow queue {port_id} destroy {queue_id} 4126 [postpone {boolean}] rule {rule_id} [...] 4127 4128If successful, it will show:: 4129 4130 Flow rule #[...] destruction enqueued 4131 4132It does not report anything for rule IDs that do not exist. The usual error 4133message is shown when a rule cannot be destroyed:: 4134 4135 Caught error type [...] ([...]): [...] 4136 4137``flow queue pull`` must be called to retrieve the operation status. 4138 4139Querying flow rules 4140~~~~~~~~~~~~~~~~~~~ 4141 4142``flow query`` queries a specific action of a flow rule having that 4143ability. Such actions collect information that can be reported using this 4144command. It is bound to ``rte_flow_query()``:: 4145 4146 flow query {port_id} {rule_id} {action} 4147 4148If successful, it will display either the retrieved data for known actions 4149or the following message:: 4150 4151 Cannot display result for action type [...] ([...]) 4152 4153Otherwise, it will complain either that the rule does not exist or that some 4154error occurred:: 4155 4156 Flow rule #[...] not found 4157 4158:: 4159 4160 Caught error type [...] ([...]): [...] 4161 4162Currently only the ``count`` action is supported. This action reports the 4163number of packets that hit the flow rule and the total number of bytes. Its 4164output has the following format:: 4165 4166 count: 4167 hits_set: [...] # whether "hits" contains a valid value 4168 bytes_set: [...] # whether "bytes" contains a valid value 4169 hits: [...] # number of packets 4170 bytes: [...] # number of bytes 4171 4172Querying counters for TCPv6 packets redirected to queue 6:: 4173 4174 testpmd> flow create 0 ingress pattern eth / ipv6 / tcp / end 4175 actions queue index 6 / count / end 4176 Flow rule #4 created 4177 testpmd> flow query 0 4 count 4178 count: 4179 hits_set: 1 4180 bytes_set: 0 4181 hits: 386446 4182 bytes: 0 4183 testpmd> 4184 4185Listing flow rules 4186~~~~~~~~~~~~~~~~~~ 4187 4188``flow list`` lists existing flow rules sorted by priority and optionally 4189filtered by group identifiers:: 4190 4191 flow list {port_id} [group {group_id}] [...] 4192 4193This command only fails with the following message if the device does not 4194exist:: 4195 4196 Invalid port [...] 4197 4198Output consists of a header line followed by a short description of each 4199flow rule, one per line. There is no output at all when no flow rules are 4200configured on the device:: 4201 4202 ID Group Prio Attr Rule 4203 [...] [...] [...] [...] [...] 4204 4205``Attr`` column flags: 4206 4207- ``i`` for ``ingress``. 4208- ``e`` for ``egress``. 4209 4210Creating several flow rules and listing them:: 4211 4212 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4213 actions queue index 6 / end 4214 Flow rule #0 created 4215 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4216 actions queue index 2 / end 4217 Flow rule #1 created 4218 testpmd> flow create 0 priority 5 ingress pattern eth / ipv4 / udp / end 4219 actions rss queues 6 7 8 end / end 4220 Flow rule #2 created 4221 testpmd> flow list 0 4222 ID Group Prio Attr Rule 4223 0 0 0 i- ETH IPV4 => QUEUE 4224 1 0 0 i- ETH IPV6 => QUEUE 4225 2 0 5 i- ETH IPV4 UDP => RSS 4226 testpmd> 4227 4228Rules are sorted by priority (i.e. group ID first, then priority level):: 4229 4230 testpmd> flow list 1 4231 ID Group Prio Attr Rule 4232 0 0 0 i- ETH => COUNT 4233 6 0 500 i- ETH IPV6 TCP => DROP COUNT 4234 5 0 1000 i- ETH IPV6 ICMP => QUEUE 4235 1 24 0 i- ETH IPV4 UDP => QUEUE 4236 4 24 10 i- ETH IPV4 TCP => DROP 4237 3 24 20 i- ETH IPV4 => DROP 4238 2 24 42 i- ETH IPV4 UDP => QUEUE 4239 7 63 0 i- ETH IPV6 UDP VXLAN => MARK QUEUE 4240 testpmd> 4241 4242Output can be limited to specific groups:: 4243 4244 testpmd> flow list 1 group 0 group 63 4245 ID Group Prio Attr Rule 4246 0 0 0 i- ETH => COUNT 4247 6 0 500 i- ETH IPV6 TCP => DROP COUNT 4248 5 0 1000 i- ETH IPV6 ICMP => QUEUE 4249 7 63 0 i- ETH IPV6 UDP VXLAN => MARK QUEUE 4250 testpmd> 4251 4252Toggling isolated mode 4253~~~~~~~~~~~~~~~~~~~~~~ 4254 4255``flow isolate`` can be used to tell the underlying PMD that ingress traffic 4256must only be injected from the defined flow rules; that no default traffic 4257is expected outside those rules and the driver is free to assign more 4258resources to handle them. It is bound to ``rte_flow_isolate()``:: 4259 4260 flow isolate {port_id} {boolean} 4261 4262If successful, enabling or disabling isolated mode shows either:: 4263 4264 Ingress traffic on port [...] 4265 is now restricted to the defined flow rules 4266 4267Or:: 4268 4269 Ingress traffic on port [...] 4270 is not restricted anymore to the defined flow rules 4271 4272Otherwise, in case of error:: 4273 4274 Caught error type [...] ([...]): [...] 4275 4276Mainly due to its side effects, PMDs supporting this mode may not have the 4277ability to toggle it more than once without reinitializing affected ports 4278first (e.g. by exiting testpmd). 4279 4280Enabling isolated mode:: 4281 4282 testpmd> flow isolate 0 true 4283 Ingress traffic on port 0 is now restricted to the defined flow rules 4284 testpmd> 4285 4286Disabling isolated mode:: 4287 4288 testpmd> flow isolate 0 false 4289 Ingress traffic on port 0 is not restricted anymore to the defined flow rules 4290 testpmd> 4291 4292Dumping HW internal information 4293~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4294 4295``flow dump`` dumps the hardware's internal representation information of 4296all flows. It is bound to ``rte_flow_dev_dump()``:: 4297 4298 flow dump {port_id} {output_file} 4299 4300If successful, it will show:: 4301 4302 Flow dump finished 4303 4304Otherwise, it will complain error occurred:: 4305 4306 Caught error type [...] ([...]): [...] 4307 4308Listing and destroying aged flow rules 4309~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4310 4311``flow aged`` simply lists aged flow rules be get from api ``rte_flow_get_aged_flows``, 4312and ``destroy`` parameter can be used to destroy those flow rules in PMD:: 4313 4314 flow aged {port_id} [destroy] 4315 4316Listing current aged flow rules:: 4317 4318 testpmd> flow aged 0 4319 Port 0 total aged flows: 0 4320 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.14 / end 4321 actions age timeout 5 / queue index 0 / end 4322 Flow rule #0 created 4323 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.15 / end 4324 actions age timeout 4 / queue index 0 / end 4325 Flow rule #1 created 4326 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.16 / end 4327 actions age timeout 2 / queue index 0 / end 4328 Flow rule #2 created 4329 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.17 / end 4330 actions age timeout 3 / queue index 0 / end 4331 Flow rule #3 created 4332 4333 4334Aged Rules are simply list as command ``flow list {port_id}``, but strip the detail rule 4335information, all the aged flows are sorted by the longest timeout time. For example, if 4336those rules be configured in the same time, ID 2 will be the first aged out rule, the next 4337will be ID 3, ID 1, ID 0:: 4338 4339 testpmd> flow aged 0 4340 Port 0 total aged flows: 4 4341 ID Group Prio Attr 4342 2 0 0 i-- 4343 3 0 0 i-- 4344 1 0 0 i-- 4345 0 0 0 i-- 4346 4347If attach ``destroy`` parameter, the command will destroy all the list aged flow rules:: 4348 4349 testpmd> flow aged 0 destroy 4350 Port 0 total aged flows: 4 4351 ID Group Prio Attr 4352 2 0 0 i-- 4353 3 0 0 i-- 4354 1 0 0 i-- 4355 0 0 0 i-- 4356 4357 Flow rule #2 destroyed 4358 Flow rule #3 destroyed 4359 Flow rule #1 destroyed 4360 Flow rule #0 destroyed 4361 4 flows be destroyed 4362 testpmd> flow aged 0 4363 Port 0 total aged flows: 0 4364 4365 4366Enqueueing listing and destroying aged flow rules 4367~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4368 4369``flow queue aged`` simply lists aged flow rules be get from 4370``rte_flow_get_q_aged_flows`` API, and ``destroy`` parameter can be used to 4371destroy those flow rules in PMD:: 4372 4373 flow queue {port_id} aged {queue_id} [destroy] 4374 4375Listing current aged flow rules:: 4376 4377 testpmd> flow queue 0 aged 0 4378 Port 0 queue 0 total aged flows: 0 4379 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4380 pattern eth / ipv4 src is 2.2.2.14 / end 4381 actions age timeout 5 / queue index 0 / end 4382 Flow rule #0 creation enqueued 4383 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4384 pattern eth / ipv4 src is 2.2.2.15 / end 4385 actions age timeout 4 / queue index 0 / end 4386 Flow rule #1 creation enqueued 4387 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4388 pattern eth / ipv4 src is 2.2.2.16 / end 4389 actions age timeout 4 / queue index 0 / end 4390 Flow rule #2 creation enqueued 4391 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4392 pattern eth / ipv4 src is 2.2.2.17 / end 4393 actions age timeout 4 / queue index 0 / end 4394 Flow rule #3 creation enqueued 4395 testpmd> flow pull 0 queue 0 4396 Queue #0 pulled 4 operations (0 failed, 4 succeeded) 4397 4398Aged Rules are simply list as command ``flow queue {port_id} list {queue_id}``, 4399but strip the detail rule information, all the aged flows are sorted by the 4400longest timeout time. For example, if those rules is configured in the same time, 4401ID 2 will be the first aged out rule, the next will be ID 3, ID 1, ID 0:: 4402 4403 testpmd> flow queue 0 aged 0 4404 Port 0 queue 0 total aged flows: 4 4405 ID Group Prio Attr 4406 2 0 0 --- 4407 3 0 0 --- 4408 1 0 0 --- 4409 0 0 0 --- 4410 4411 0 flows destroyed 4412 4413If attach ``destroy`` parameter, the command will destroy all the list aged flow rules:: 4414 4415 testpmd> flow queue 0 aged 0 destroy 4416 Port 0 queue 0 total aged flows: 4 4417 ID Group Prio Attr 4418 2 0 0 --- 4419 3 0 0 --- 4420 1 0 0 --- 4421 0 0 0 --- 4422 Flow rule #2 destruction enqueued 4423 Flow rule #3 destruction enqueued 4424 Flow rule #1 destruction enqueued 4425 Flow rule #0 destruction enqueued 4426 4427 4 flows destroyed 4428 testpmd> flow queue 0 aged 0 4429 Port 0 total aged flows: 0 4430 4431.. note:: 4432 4433 The queue must be empty before attaching ``destroy`` parameter. 4434 4435 4436Creating indirect actions 4437~~~~~~~~~~~~~~~~~~~~~~~~~ 4438 4439``flow indirect_action {port_id} create`` creates indirect action with optional 4440indirect action ID. It is bound to ``rte_flow_action_handle_create()``:: 4441 4442 flow indirect_action {port_id} create [action_id {indirect_action_id}] 4443 [ingress] [egress] [transfer] action {action} / end 4444 4445If successful, it will show:: 4446 4447 Indirect action #[...] created 4448 4449Otherwise, it will complain either that indirect action already exists or that 4450some error occurred:: 4451 4452 Indirect action #[...] is already assigned, delete it first 4453 4454:: 4455 4456 Caught error type [...] ([...]): [...] 4457 4458Create indirect rss action with id 100 to queues 1 and 2 on port 0:: 4459 4460 testpmd> flow indirect_action 0 create action_id 100 \ 4461 ingress action rss queues 1 2 end / end 4462 4463Create indirect rss action with id assigned by testpmd to queues 1 and 2 on 4464port 0:: 4465 4466 testpmd> flow indirect_action 0 create action_id \ 4467 ingress action rss queues 0 1 end / end 4468 4469Enqueueing creation of indirect actions 4470~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4471 4472``flow queue indirect_action create`` adds creation operation of an indirect 4473action to a queue. It is bound to ``rte_flow_async_action_handle_create()``:: 4474 4475 flow queue {port_id} create {queue_id} [postpone {boolean}] 4476 table {table_id} item_template {item_template_id} 4477 action_template {action_template_id} 4478 pattern {item} [/ {item} [...]] / end 4479 actions {action} [/ {action} [...]] / end 4480 4481If successful, it will show:: 4482 4483 Indirect action #[...] creation queued 4484 4485Otherwise it will show an error message of the form:: 4486 4487 Caught error type [...] ([...]): [...] 4488 4489This command uses the same parameters as ``flow indirect_action create``, 4490described in `Creating indirect actions`_. 4491 4492``flow queue pull`` must be called to retrieve the operation status. 4493 4494Updating indirect actions 4495~~~~~~~~~~~~~~~~~~~~~~~~~ 4496 4497``flow indirect_action {port_id} update`` updates configuration of the indirect 4498action from its indirect action ID (as returned by 4499``flow indirect_action {port_id} create``). It is bound to 4500``rte_flow_action_handle_update()``:: 4501 4502 flow indirect_action {port_id} update {indirect_action_id} 4503 action {action} / end 4504 4505If successful, it will show:: 4506 4507 Indirect action #[...] updated 4508 4509Otherwise, it will complain either that indirect action not found or that some 4510error occurred:: 4511 4512 Failed to find indirect action #[...] on port [...] 4513 4514:: 4515 4516 Caught error type [...] ([...]): [...] 4517 4518Update indirect rss action having id 100 on port 0 with rss to queues 0 and 3 4519(in create example above rss queues were 1 and 2):: 4520 4521 testpmd> flow indirect_action 0 update 100 action rss queues 0 3 end / end 4522 4523Enqueueing update of indirect actions 4524~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4525 4526``flow queue indirect_action update`` adds update operation for an indirect 4527action to a queue. It is bound to ``rte_flow_async_action_handle_update()``:: 4528 4529 flow queue {port_id} indirect_action {queue_id} update 4530 {indirect_action_id} [postpone {boolean}] action {action} / end 4531 4532If successful, it will show:: 4533 4534 Indirect action #[...] update queued 4535 4536Otherwise it will show an error message of the form:: 4537 4538 Caught error type [...] ([...]): [...] 4539 4540``flow queue pull`` must be called to retrieve the operation status. 4541 4542Destroying indirect actions 4543~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4544 4545``flow indirect_action {port_id} destroy`` destroys one or more indirect actions 4546from their indirect action IDs (as returned by 4547``flow indirect_action {port_id} create``). It is bound to 4548``rte_flow_action_handle_destroy()``:: 4549 4550 flow indirect_action {port_id} destroy action_id {indirect_action_id} [...] 4551 4552If successful, it will show:: 4553 4554 Indirect action #[...] destroyed 4555 4556It does not report anything for indirect action IDs that do not exist. 4557The usual error message is shown when a indirect action cannot be destroyed:: 4558 4559 Caught error type [...] ([...]): [...] 4560 4561Destroy indirect actions having id 100 & 101:: 4562 4563 testpmd> flow indirect_action 0 destroy action_id 100 action_id 101 4564 4565Enqueueing destruction of indirect actions 4566~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4567 4568``flow queue indirect_action destroy`` adds destruction operation to destroy 4569one or more indirect actions from their indirect action IDs (as returned by 4570``flow queue {port_id} indirect_action {queue_id} create``) to a queue. 4571It is bound to ``rte_flow_async_action_handle_destroy()``:: 4572 4573 flow queue {port_id} indirect_action {queue_id} destroy 4574 [postpone {boolean}] action_id {indirect_action_id} [...] 4575 4576If successful, it will show:: 4577 4578 Indirect action #[...] destruction queued 4579 4580Otherwise it will show an error message of the form:: 4581 4582 Caught error type [...] ([...]): [...] 4583 4584``flow queue pull`` must be called to retrieve the operation status. 4585 4586Query indirect actions 4587~~~~~~~~~~~~~~~~~~~~~~ 4588 4589``flow indirect_action {port_id} query`` queries the indirect action from its 4590indirect action ID (as returned by ``flow indirect_action {port_id} create``). 4591It is bound to ``rte_flow_action_handle_query()``:: 4592 4593 flow indirect_action {port_id} query {indirect_action_id} 4594 4595Currently only rss indirect action supported. If successful, it will show:: 4596 4597 Indirect RSS action: 4598 refs:[...] 4599 4600Otherwise, it will complain either that indirect action not found or that some 4601error occurred:: 4602 4603 Failed to find indirect action #[...] on port [...] 4604 4605:: 4606 4607 Caught error type [...] ([...]): [...] 4608 4609Query indirect action having id 100:: 4610 4611 testpmd> flow indirect_action 0 query 100 4612 4613Enqueueing query of indirect actions 4614~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4615 4616``flow queue indirect_action query`` adds query operation for an indirect 4617action to a queue. It is bound to ``rte_flow_async_action_handle_query()``:: 4618 4619 flow queue {port_id} indirect_action {queue_id} query 4620 {indirect_action_id} [postpone {boolean}] 4621 4622If successful, it will show:: 4623 4624 Indirect action #[...] query queued 4625 4626Otherwise it will show an error message of the form:: 4627 4628 Caught error type [...] ([...]): [...] 4629 4630``flow queue pull`` must be called to retrieve the operation status. 4631 4632Sample QinQ flow rules 4633~~~~~~~~~~~~~~~~~~~~~~ 4634 4635Before creating QinQ rule(s) the following commands should be issued to enable QinQ:: 4636 4637 testpmd> port stop 0 4638 testpmd> vlan set extend on 0 4639 4640The above command sets the inner and outer TPID's to 0x8100. 4641 4642To change the TPID's the following commands should be used:: 4643 4644 testpmd> vlan set outer tpid 0x88A8 0 4645 testpmd> vlan set inner tpid 0x8100 0 4646 testpmd> port start 0 4647 4648Validate and create a QinQ rule on port 0 to steer traffic to a VF queue in a VM. 4649 4650:: 4651 4652 testpmd> flow validate 0 ingress pattern eth / vlan tci is 123 / 4653 vlan tci is 456 / end actions vf id 1 / queue index 0 / end 4654 Flow rule #0 validated 4655 4656 testpmd> flow create 0 ingress pattern eth / vlan tci is 4 / 4657 vlan tci is 456 / end actions vf id 123 / queue index 0 / end 4658 Flow rule #0 created 4659 4660 testpmd> flow list 0 4661 ID Group Prio Attr Rule 4662 0 0 0 i- ETH VLAN VLAN=>VF QUEUE 4663 4664Validate and create a QinQ rule on port 0 to steer traffic to a queue on the host. 4665 4666:: 4667 4668 testpmd> flow validate 0 ingress pattern eth / vlan tci is 321 / 4669 vlan tci is 654 / end actions pf / queue index 0 / end 4670 Flow rule #1 validated 4671 4672 testpmd> flow create 0 ingress pattern eth / vlan tci is 321 / 4673 vlan tci is 654 / end actions pf / queue index 1 / end 4674 Flow rule #1 created 4675 4676 testpmd> flow list 0 4677 ID Group Prio Attr Rule 4678 0 0 0 i- ETH VLAN VLAN=>VF QUEUE 4679 1 0 0 i- ETH VLAN VLAN=>PF QUEUE 4680 4681Sample VXLAN flow rules 4682~~~~~~~~~~~~~~~~~~~~~~~ 4683 4684Before creating VXLAN rule(s), the UDP port should be added for VXLAN packet 4685filter on a port:: 4686 4687 testpmd> rx_vxlan_port add 4789 0 4688 4689Create VXLAN rules on port 0 to steer traffic to PF queues. 4690 4691:: 4692 4693 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan / 4694 eth dst is 00:11:22:33:44:55 / end actions pf / queue index 1 / end 4695 Flow rule #0 created 4696 4697 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan vni is 3 / 4698 eth dst is 00:11:22:33:44:55 / end actions pf / queue index 2 / end 4699 Flow rule #1 created 4700 4701 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan / 4702 eth dst is 00:11:22:33:44:55 / vlan tci is 10 / end actions pf / 4703 queue index 3 / end 4704 Flow rule #2 created 4705 4706 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan vni is 5 / 4707 eth dst is 00:11:22:33:44:55 / vlan tci is 20 / end actions pf / 4708 queue index 4 / end 4709 Flow rule #3 created 4710 4711 testpmd> flow create 0 ingress pattern eth dst is 00:00:00:00:01:00 / ipv4 / 4712 udp / vxlan vni is 6 / eth dst is 00:11:22:33:44:55 / end actions pf / 4713 queue index 5 / end 4714 Flow rule #4 created 4715 4716 testpmd> flow list 0 4717 ID Group Prio Attr Rule 4718 0 0 0 i- ETH IPV4 UDP VXLAN ETH => QUEUE 4719 1 0 0 i- ETH IPV4 UDP VXLAN ETH => QUEUE 4720 2 0 0 i- ETH IPV4 UDP VXLAN ETH VLAN => QUEUE 4721 3 0 0 i- ETH IPV4 UDP VXLAN ETH VLAN => QUEUE 4722 4 0 0 i- ETH IPV4 UDP VXLAN ETH => QUEUE 4723 4724Sample VXLAN encapsulation rule 4725~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4726 4727VXLAN encapsulation outer layer has default value pre-configured in testpmd 4728source code, those can be changed by using the following commands 4729 4730IPv4 VXLAN outer header:: 4731 4732 testpmd> set vxlan ip-version ipv4 vni 4 udp-src 4 udp-dst 4 ip-src 127.0.0.1 4733 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4734 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4735 queue index 0 / end 4736 4737 testpmd> set vxlan-with-vlan ip-version ipv4 vni 4 udp-src 4 udp-dst 4 ip-src 4738 127.0.0.1 ip-dst 128.0.0.1 vlan-tci 34 eth-src 11:11:11:11:11:11 4739 eth-dst 22:22:22:22:22:22 4740 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4741 queue index 0 / end 4742 4743 testpmd> set vxlan-tos-ttl ip-version ipv4 vni 4 udp-src 4 udp-dst 4 ip-tos 0 4744 ip-ttl 255 ip-src 127.0.0.1 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 4745 eth-dst 22:22:22:22:22:22 4746 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4747 queue index 0 / end 4748 4749IPv6 VXLAN outer header:: 4750 4751 testpmd> set vxlan ip-version ipv6 vni 4 udp-src 4 udp-dst 4 ip-src ::1 4752 ip-dst ::2222 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4753 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4754 queue index 0 / end 4755 4756 testpmd> set vxlan-with-vlan ip-version ipv6 vni 4 udp-src 4 udp-dst 4 4757 ip-src ::1 ip-dst ::2222 vlan-tci 34 eth-src 11:11:11:11:11:11 4758 eth-dst 22:22:22:22:22:22 4759 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4760 queue index 0 / end 4761 4762 testpmd> set vxlan-tos-ttl ip-version ipv6 vni 4 udp-src 4 udp-dst 4 4763 ip-tos 0 ip-ttl 255 ::1 ip-dst ::2222 eth-src 11:11:11:11:11:11 4764 eth-dst 22:22:22:22:22:22 4765 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4766 queue index 0 / end 4767 4768Sample NVGRE encapsulation rule 4769~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4770 4771NVGRE encapsulation outer layer has default value pre-configured in testpmd 4772source code, those can be changed by using the following commands 4773 4774IPv4 NVGRE outer header:: 4775 4776 testpmd> set nvgre ip-version ipv4 tni 4 ip-src 127.0.0.1 ip-dst 128.0.0.1 4777 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4778 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4779 queue index 0 / end 4780 4781 testpmd> set nvgre-with-vlan ip-version ipv4 tni 4 ip-src 127.0.0.1 4782 ip-dst 128.0.0.1 vlan-tci 34 eth-src 11:11:11:11:11:11 4783 eth-dst 22:22:22:22:22:22 4784 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4785 queue index 0 / end 4786 4787IPv6 NVGRE outer header:: 4788 4789 testpmd> set nvgre ip-version ipv6 tni 4 ip-src ::1 ip-dst ::2222 4790 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4791 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4792 queue index 0 / end 4793 4794 testpmd> set nvgre-with-vlan ip-version ipv6 tni 4 ip-src ::1 ip-dst ::2222 4795 vlan-tci 34 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4796 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4797 queue index 0 / end 4798 4799Sample L2 encapsulation rule 4800~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4801 4802L2 encapsulation has default value pre-configured in testpmd 4803source code, those can be changed by using the following commands 4804 4805L2 header:: 4806 4807 testpmd> set l2_encap ip-version ipv4 4808 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4809 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / mpls / end actions 4810 mplsoudp_decap / l2_encap / end 4811 4812L2 with VXLAN header:: 4813 4814 testpmd> set l2_encap-with-vlan ip-version ipv4 vlan-tci 34 4815 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4816 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / mpls / end actions 4817 mplsoudp_decap / l2_encap / end 4818 4819Sample L2 decapsulation rule 4820~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4821 4822L2 decapsulation has default value pre-configured in testpmd 4823source code, those can be changed by using the following commands 4824 4825L2 header:: 4826 4827 testpmd> set l2_decap 4828 testpmd> flow create 0 egress pattern eth / end actions l2_decap / mplsoudp_encap / 4829 queue index 0 / end 4830 4831L2 with VXLAN header:: 4832 4833 testpmd> set l2_encap-with-vlan 4834 testpmd> flow create 0 egress pattern eth / end actions l2_encap / mplsoudp_encap / 4835 queue index 0 / end 4836 4837Sample MPLSoGRE encapsulation rule 4838~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4839 4840MPLSoGRE encapsulation outer layer has default value pre-configured in testpmd 4841source code, those can be changed by using the following commands 4842 4843IPv4 MPLSoGRE outer header:: 4844 4845 testpmd> set mplsogre_encap ip-version ipv4 label 4 4846 ip-src 127.0.0.1 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 4847 eth-dst 22:22:22:22:22:22 4848 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4849 mplsogre_encap / end 4850 4851IPv4 MPLSoGRE with VLAN outer header:: 4852 4853 testpmd> set mplsogre_encap-with-vlan ip-version ipv4 label 4 4854 ip-src 127.0.0.1 ip-dst 128.0.0.1 vlan-tci 34 4855 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4856 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4857 mplsogre_encap / end 4858 4859IPv6 MPLSoGRE outer header:: 4860 4861 testpmd> set mplsogre_encap ip-version ipv6 mask 4 4862 ip-src ::1 ip-dst ::2222 eth-src 11:11:11:11:11:11 4863 eth-dst 22:22:22:22:22:22 4864 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4865 mplsogre_encap / end 4866 4867IPv6 MPLSoGRE with VLAN outer header:: 4868 4869 testpmd> set mplsogre_encap-with-vlan ip-version ipv6 mask 4 4870 ip-src ::1 ip-dst ::2222 vlan-tci 34 4871 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4872 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4873 mplsogre_encap / end 4874 4875Sample MPLSoGRE decapsulation rule 4876~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4877 4878MPLSoGRE decapsulation outer layer has default value pre-configured in testpmd 4879source code, those can be changed by using the following commands 4880 4881IPv4 MPLSoGRE outer header:: 4882 4883 testpmd> set mplsogre_decap ip-version ipv4 4884 testpmd> flow create 0 ingress pattern eth / ipv4 / gre / mpls / end actions 4885 mplsogre_decap / l2_encap / end 4886 4887IPv4 MPLSoGRE with VLAN outer header:: 4888 4889 testpmd> set mplsogre_decap-with-vlan ip-version ipv4 4890 testpmd> flow create 0 ingress pattern eth / vlan / ipv4 / gre / mpls / end 4891 actions mplsogre_decap / l2_encap / end 4892 4893IPv6 MPLSoGRE outer header:: 4894 4895 testpmd> set mplsogre_decap ip-version ipv6 4896 testpmd> flow create 0 ingress pattern eth / ipv6 / gre / mpls / end 4897 actions mplsogre_decap / l2_encap / end 4898 4899IPv6 MPLSoGRE with VLAN outer header:: 4900 4901 testpmd> set mplsogre_decap-with-vlan ip-version ipv6 4902 testpmd> flow create 0 ingress pattern eth / vlan / ipv6 / gre / mpls / end 4903 actions mplsogre_decap / l2_encap / end 4904 4905Sample MPLSoUDP encapsulation rule 4906~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4907 4908MPLSoUDP encapsulation outer layer has default value pre-configured in testpmd 4909source code, those can be changed by using the following commands 4910 4911IPv4 MPLSoUDP outer header:: 4912 4913 testpmd> set mplsoudp_encap ip-version ipv4 label 4 udp-src 5 udp-dst 10 4914 ip-src 127.0.0.1 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 4915 eth-dst 22:22:22:22:22:22 4916 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4917 mplsoudp_encap / end 4918 4919IPv4 MPLSoUDP with VLAN outer header:: 4920 4921 testpmd> set mplsoudp_encap-with-vlan ip-version ipv4 label 4 udp-src 5 4922 udp-dst 10 ip-src 127.0.0.1 ip-dst 128.0.0.1 vlan-tci 34 4923 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4924 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4925 mplsoudp_encap / end 4926 4927IPv6 MPLSoUDP outer header:: 4928 4929 testpmd> set mplsoudp_encap ip-version ipv6 mask 4 udp-src 5 udp-dst 10 4930 ip-src ::1 ip-dst ::2222 eth-src 11:11:11:11:11:11 4931 eth-dst 22:22:22:22:22:22 4932 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4933 mplsoudp_encap / end 4934 4935IPv6 MPLSoUDP with VLAN outer header:: 4936 4937 testpmd> set mplsoudp_encap-with-vlan ip-version ipv6 mask 4 udp-src 5 4938 udp-dst 10 ip-src ::1 ip-dst ::2222 vlan-tci 34 4939 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4940 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 4941 mplsoudp_encap / end 4942 4943Sample MPLSoUDP decapsulation rule 4944~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4945 4946MPLSoUDP decapsulation outer layer has default value pre-configured in testpmd 4947source code, those can be changed by using the following commands 4948 4949IPv4 MPLSoUDP outer header:: 4950 4951 testpmd> set mplsoudp_decap ip-version ipv4 4952 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / mpls / end actions 4953 mplsoudp_decap / l2_encap / end 4954 4955IPv4 MPLSoUDP with VLAN outer header:: 4956 4957 testpmd> set mplsoudp_decap-with-vlan ip-version ipv4 4958 testpmd> flow create 0 ingress pattern eth / vlan / ipv4 / udp / mpls / end 4959 actions mplsoudp_decap / l2_encap / end 4960 4961IPv6 MPLSoUDP outer header:: 4962 4963 testpmd> set mplsoudp_decap ip-version ipv6 4964 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / mpls / end 4965 actions mplsoudp_decap / l2_encap / end 4966 4967IPv6 MPLSoUDP with VLAN outer header:: 4968 4969 testpmd> set mplsoudp_decap-with-vlan ip-version ipv6 4970 testpmd> flow create 0 ingress pattern eth / vlan / ipv6 / udp / mpls / end 4971 actions mplsoudp_decap / l2_encap / end 4972 4973Sample Raw encapsulation rule 4974~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4975 4976Raw encapsulation configuration can be set by the following commands 4977 4978Encapsulating VxLAN:: 4979 4980 testpmd> set raw_encap 4 eth src is 10:11:22:33:44:55 / vlan tci is 1 4981 inner_type is 0x0800 / ipv4 / udp dst is 4789 / vxlan vni 4982 is 2 / end_set 4983 testpmd> flow create 0 egress pattern eth / ipv4 / end actions 4984 raw_encap index 4 / end 4985 4986Sample Raw decapsulation rule 4987~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4988 4989Raw decapsulation configuration can be set by the following commands 4990 4991Decapsulating VxLAN:: 4992 4993 testpmd> set raw_decap eth / ipv4 / udp / vxlan / end_set 4994 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan / eth / ipv4 / 4995 end actions raw_decap / queue index 0 / end 4996 4997Sample ESP rules 4998~~~~~~~~~~~~~~~~ 4999 5000ESP rules can be created by the following commands:: 5001 5002 testpmd> flow create 0 ingress pattern eth / ipv4 / esp spi is 1 / end actions 5003 queue index 3 / end 5004 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / esp spi is 1 / end 5005 actions queue index 3 / end 5006 testpmd> flow create 0 ingress pattern eth / ipv6 / esp spi is 1 / end actions 5007 queue index 3 / end 5008 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / esp spi is 1 / end 5009 actions queue index 3 / end 5010 5011Sample AH rules 5012~~~~~~~~~~~~~~~~ 5013 5014AH rules can be created by the following commands:: 5015 5016 testpmd> flow create 0 ingress pattern eth / ipv4 / ah spi is 1 / end actions 5017 queue index 3 / end 5018 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / ah spi is 1 / end 5019 actions queue index 3 / end 5020 testpmd> flow create 0 ingress pattern eth / ipv6 / ah spi is 1 / end actions 5021 queue index 3 / end 5022 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / ah spi is 1 / end 5023 actions queue index 3 / end 5024 5025Sample PFCP rules 5026~~~~~~~~~~~~~~~~~ 5027 5028PFCP rules can be created by the following commands(s_field need to be 1 5029if seid is set):: 5030 5031 testpmd> flow create 0 ingress pattern eth / ipv4 / pfcp s_field is 0 / end 5032 actions queue index 3 / end 5033 testpmd> flow create 0 ingress pattern eth / ipv4 / pfcp s_field is 1 5034 seid is 1 / end actions queue index 3 / end 5035 testpmd> flow create 0 ingress pattern eth / ipv6 / pfcp s_field is 0 / end 5036 actions queue index 3 / end 5037 testpmd> flow create 0 ingress pattern eth / ipv6 / pfcp s_field is 1 5038 seid is 1 / end actions queue index 3 / end 5039 5040Sample Sampling/Mirroring rules 5041~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5042 5043Sample/Mirroring rules can be set by the following commands 5044 5045NIC-RX Sampling rule, the matched ingress packets and sent to the queue 1, 5046and 50% packets are duplicated and marked with 0x1234 and sent to queue 0. 5047 5048:: 5049 5050 testpmd> set sample_actions 0 mark id 0x1234 / queue index 0 / end 5051 testpmd> flow create 0 ingress group 1 pattern eth / end actions 5052 sample ratio 2 index 0 / queue index 1 / end 5053 5054Match packets coming from a VM which is referred to by means of 5055its representor ethdev (port 1), mirror 50% of them to the 5056said representor (for bookkeeping) as well as encapsulate 5057all the packets and steer them to the physical port: 5058 5059:: 5060 5061 testpmd> set sample_actions 0 port_representor ethdev_port_id 1 / end 5062 5063 testpmd> set vxlan ip-version ipv4 vni 4 udp-src 32 udp-dst 4789 ip-src 127.0.0.1 5064 ip-dst 127.0.0.2 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5065 5066 testpmd> flow create 0 transfer pattern represented_port ethdev_port_id is 1 / end 5067 actions sample ratio 2 index 0 / vxlan_encap / 5068 represented_port ethdev_port_id 0 / end 5069 5070The rule is inserted via port 0 (assumed to have "transfer" privilege). 5071 5072Sample integrity rules 5073~~~~~~~~~~~~~~~~~~~~~~ 5074 5075Integrity rules can be created by the following commands: 5076 5077Integrity rule that forwards valid TCP packets to group 1. 5078TCP packet integrity is matched with the ``l4_ok`` bit 3. 5079 5080:: 5081 5082 testpmd> flow create 0 ingress 5083 pattern eth / ipv4 / tcp / integrity value mask 8 value spec 8 / end 5084 actions jump group 1 / end 5085 5086Integrity rule that forwards invalid packets to application. 5087General packet integrity is matched with the ``packet_ok`` bit 0. 5088 5089:: 5090 5091 testpmd> flow create 0 ingress pattern integrity value mask 1 value spec 0 / end actions queue index 0 / end 5092 5093Sample conntrack rules 5094~~~~~~~~~~~~~~~~~~~~~~ 5095 5096Conntrack rules can be set by the following commands 5097 5098Need to construct the connection context with provided information. 5099In the first table, create a flow rule by using conntrack action and jump to 5100the next table. In the next table, create a rule to check the state. 5101 5102:: 5103 5104 testpmd> set conntrack com peer 1 is_orig 1 enable 1 live 1 sack 1 cack 0 5105 last_dir 0 liberal 0 state 1 max_ack_win 7 r_lim 5 last_win 510 5106 last_seq 2632987379 last_ack 2532480967 last_end 2632987379 5107 last_index 0x8 5108 testpmd> set conntrack orig scale 7 fin 0 acked 1 unack_data 0 5109 sent_end 2632987379 reply_end 2633016339 max_win 28960 5110 max_ack 2632987379 5111 testpmd> set conntrack rply scale 7 fin 0 acked 1 unack_data 0 5112 sent_end 2532480967 reply_end 2532546247 max_win 65280 5113 max_ack 2532480967 5114 testpmd> flow indirect_action 0 create ingress action conntrack / end 5115 testpmd> flow create 0 group 3 ingress pattern eth / ipv4 / tcp / end actions indirect 0 / jump group 5 / end 5116 testpmd> flow create 0 group 5 ingress pattern eth / ipv4 / tcp / conntrack is 1 / end actions queue index 5 / end 5117 5118Construct the conntrack again with only "is_orig" set to 0 (other fields are 5119ignored), then use "update" interface to update the direction. Create flow 5120rules like above for the peer port. 5121 5122:: 5123 5124 testpmd> flow indirect_action 0 update 0 action conntrack_update dir / end 5125 5126Sample meter with policy rules 5127~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5128 5129Meter with policy rules can be created by the following commands: 5130 5131Need to create policy first and actions are set for green/yellow/red colors. 5132Create meter with policy id. Create flow with meter id. 5133 5134Example for policy with meter color action. The purpose is to color the packet 5135to reflect the meter color result. 5136The meter policy action list: ``green -> green, yellow -> yellow, red -> red``. 5137 5138:: 5139 5140 testpmd> add port meter profile srtcm_rfc2697 0 13 21504 2688 0 0 5141 testpmd> add port meter policy 0 1 g_actions color type green / end y_actions color type yellow / end 5142 r_actions color type red / end 5143 testpmd> create port meter 0 1 13 1 yes 0xffff 0 0 5144 testpmd> flow create 0 priority 0 ingress group 1 pattern eth / end actions meter mtr_id 1 / end 5145 5146Sample L2TPv2 RSS rules 5147~~~~~~~~~~~~~~~~~~~~~~~ 5148 5149L2TPv2 RSS rules can be created by the following commands:: 5150 5151 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 type control 5152 / end actions rss types l2tpv2 end queues end / end 5153 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / end 5154 actions rss types eth l2-src-only end queues end / end 5155 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / end 5156 actions rss types l2tpv2 end queues end / end 5157 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5158 / end actions rss types ipv4 end queues end / end 5159 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv6 5160 / udp / end actions rss types ipv6-udp end queues end / end 5161 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / l2tpv2 / ppp / ipv4 5162 / tcp / end actions rss types ipv4-tcp end queues end / end 5163 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / l2tpv2 / ppp / ipv6 5164 / end actions rss types ipv6 end queues end / end 5165 5166Sample L2TPv2 FDIR rules 5167~~~~~~~~~~~~~~~~~~~~~~~~ 5168 5169L2TPv2 FDIR rules can be created by the following commands:: 5170 5171 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 type control 5172 session_id is 0x1111 / end actions queue index 3 / end 5173 testpmd> flow create 0 ingress pattern eth src is 00:00:00:00:00:01 / ipv4 5174 / udp / l2tpv2 type data / end actions queue index 3 / end 5175 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 type data 5176 session_id is 0x1111 / ppp / end actions queue index 3 / end 5177 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5178 src is 10.0.0.1 / end actions queue index 3 / end 5179 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / l2tpv2 / ppp / ipv6 5180 dst is ABAB:910B:6666:3457:8295:3333:1800:2929 / end actions queue index 3 / end 5181 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5182 / udp src is 22 / end actions queue index 3 / end 5183 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5184 / tcp dst is 23 / end actions queue index 3 / end 5185 5186Sample RAW rule 5187~~~~~~~~~~~~~~~ 5188 5189A RAW rule can be created as following using ``pattern_hex`` key and mask. 5190 5191:: 5192 5193 testpmd> flow create 0 group 0 priority 1 ingress pattern raw relative is 0 search is 0 offset 5194 is 0 limit is 0 pattern_hex spec 00000000000000000000000000000000000000000000000000000a0a0a0a 5195 pattern_hex mask 0000000000000000000000000000000000000000000000000000ffffffff / end actions 5196 queue index 4 / end 5197 5198BPF Functions 5199-------------- 5200 5201The following sections show functions to load/unload eBPF based filters. 5202 5203bpf-load 5204~~~~~~~~ 5205 5206Load an eBPF program as a callback for particular RX/TX queue:: 5207 5208 testpmd> bpf-load rx|tx (portid) (queueid) (load-flags) (bpf-prog-filename) 5209 5210The available load-flags are: 5211 5212* ``J``: use JIT generated native code, otherwise BPF interpreter will be used. 5213 5214* ``M``: assume input parameter is a pointer to rte_mbuf, otherwise assume it is a pointer to first segment's data. 5215 5216* ``-``: none. 5217 5218.. note:: 5219 5220 You'll need clang v3.7 or above to build bpf program you'd like to load 5221 5222For example: 5223 5224.. code-block:: console 5225 5226 cd examples/bpf 5227 clang -O2 -target bpf -c t1.c 5228 5229Then to load (and JIT compile) t1.o at RX queue 0, port 1: 5230 5231.. code-block:: console 5232 5233 testpmd> bpf-load rx 1 0 J ./dpdk.org/examples/bpf/t1.o 5234 5235To load (not JITed) t1.o at TX queue 0, port 0: 5236 5237.. code-block:: console 5238 5239 testpmd> bpf-load tx 0 0 - ./dpdk.org/examples/bpf/t1.o 5240 5241bpf-unload 5242~~~~~~~~~~ 5243 5244Unload previously loaded eBPF program for particular RX/TX queue:: 5245 5246 testpmd> bpf-unload rx|tx (portid) (queueid) 5247 5248For example to unload BPF filter from TX queue 0, port 0: 5249 5250.. code-block:: console 5251 5252 testpmd> bpf-unload tx 0 0 5253 5254Flex Item Functions 5255------------------- 5256 5257The following sections show functions that configure and create flex item object, 5258create flex pattern and use it in a flow rule. 5259The commands will use 20 bytes IPv4 header for examples: 5260 5261:: 5262 5263 0 1 2 3 5264 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 5265 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5266 | ver | IHL | TOS | length | +0 5267 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5268 | identification | flg | frag. offset | +4 5269 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5270 | TTL | protocol | checksum | +8 5271 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5272 | source IP address | +12 5273 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5274 | destination IP address | +16 5275 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5276 5277 5278Create flex item 5279~~~~~~~~~~~~~~~~ 5280 5281Flex item object is created by PMD according to a new header configuration. The 5282header configuration is compiled by the testpmd and stored in 5283``rte_flow_item_flex_conf`` type variable. 5284 5285:: 5286 5287 # flow flex_item create <port> <flex id> <configuration file> 5288 testpmd> flow flex_item init 0 3 ipv4_flex_config.json 5289 port-0: created flex item #3 5290 5291Flex item configuration is kept in external JSON file. 5292It describes the following header elements: 5293 5294**New header length.** 5295 5296Specify whether the new header has fixed or variable length and the basic/minimal 5297header length value. 5298 5299If header length is not fixed, header location with a value that completes header 5300length calculation and scale/offset function must be added. 5301 5302Scale function depends on port hardware. 5303 5304**Next protocol.** 5305 5306Describes location in the new header that specify following network header type. 5307 5308**Flow match samples.** 5309 5310Describes locations in the new header that will be used in flow rules. 5311 5312Number of flow samples and sample maximal length depend of port hardware. 5313 5314**Input trigger.** 5315 5316Describes preceding network header configuration. 5317 5318**Output trigger.** 5319 5320Describes conditions that trigger transfer to following network header 5321 5322.. code-block:: json 5323 5324 { 5325 "next_header": { "field_mode": "FIELD_MODE_FIXED", "field_size": 20}, 5326 "next_protocol": {"field_size": 8, "field_base": 72}, 5327 "sample_data": [ 5328 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 0}, 5329 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 32}, 5330 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 64}, 5331 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 96} 5332 ], 5333 "input_link": [ 5334 {"item": "eth type is 0x0800"}, 5335 {"item": "vlan inner_type is 0x0800"} 5336 ], 5337 "output_link": [ 5338 {"item": "udp", "next": 17}, 5339 {"item": "tcp", "next": 6}, 5340 {"item": "icmp", "next": 1} 5341 ] 5342 } 5343 5344 5345Flex pattern and flow rules 5346~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5347 5348Flex pattern describe parts of network header that will trigger flex flow item hit in a flow rule. 5349Flex pattern directly related to flex item samples configuration. 5350Flex pattern can be shared between ports. 5351 5352**Flex pattern and flow rule to match IPv4 version and 20 bytes length** 5353 5354:: 5355 5356 # set flex_pattern <pattern_id> is <hex bytes sequence> 5357 testpmd> flow flex_item pattern 5 is 45FF 5358 created pattern #5 5359 5360 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / flex item is 3 pattern is 5 / end actions mark id 1 / queue index 0 / end 5361 Flow rule #0 created 5362 5363**Flex pattern and flow rule to match packets with source address 1.2.3.4** 5364 5365:: 5366 5367 testpmd> flow flex_item pattern 2 spec 45000000000000000000000001020304 mask FF0000000000000000000000FFFFFFFF 5368 created pattern #2 5369 5370 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / flex item is 3 pattern is 2 / end actions mark id 1 / queue index 0 / end 5371 Flow rule #0 created 5372 5373Driver specific commands 5374------------------------ 5375 5376Some drivers provide specific features. 5377See: 5378 5379- :ref:`net/bonding testpmd driver specific commands <bonding_testpmd_commands>` 5380- :ref:`net/i40e testpmd driver specific commands <net_i40e_testpmd_commands>` 5381- :ref:`net/ixgbe testpmd driver specific commands <net_ixgbe_testpmd_commands>` 5382