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 218show port (module_eeprom|eeprom) 219~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 220 221Display the EEPROM information of a port:: 222 223 testpmd> show port (port_id) (module_eeprom|eeprom) 224 225show port rss reta 226~~~~~~~~~~~~~~~~~~ 227 228Display the rss redirection table entry indicated by masks on port X:: 229 230 testpmd> show port (port_id) rss reta (size) (mask0, mask1...) 231 232size is used to indicate the hardware supported reta size 233 234show port rss-hash 235~~~~~~~~~~~~~~~~~~ 236 237Display the RSS hash functions and RSS hash key or RSS hash algorithm of a port:: 238 239 testpmd> show port (port_id) rss-hash [key | algorithm] 240 241clear port 242~~~~~~~~~~ 243 244Clear the port statistics and forward engine statistics for a given port or for all ports:: 245 246 testpmd> clear port (info|stats|xstats|fdir) (port_id|all) 247 248For example:: 249 250 testpmd> clear port stats all 251 252show (rxq|txq) 253~~~~~~~~~~~~~~ 254 255Display information for a given port's RX/TX queue:: 256 257 testpmd> show (rxq|txq) info (port_id) (queue_id) 258 259show desc status(rxq|txq) 260~~~~~~~~~~~~~~~~~~~~~~~~~ 261 262Display information for a given port's RX/TX descriptor status:: 263 264 testpmd> show port (port_id) (rxq|txq) (queue_id) desc (desc_id) status 265 266show desc used count(rxq|txq) 267~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 268 269Display the number of packet descriptors currently used by hardware for a queue:: 270 271 testpmd> show port (port_id) (rxq|txq) (queue_id) desc used count 272 273show config 274~~~~~~~~~~~ 275 276Displays the configuration of the application. 277The configuration comes from the command-line, the runtime or the application defaults:: 278 279 testpmd> show config (rxtx|cores|fwd|rxoffs|rxpkts|rxhdrs|txpkts|txtimes) 280 281The available information categories are: 282 283* ``rxtx``: RX/TX configuration items. 284 285* ``cores``: List of forwarding cores. 286 287* ``fwd``: Packet forwarding configuration. 288 289* ``rxoffs``: Packet offsets for RX split. 290 291* ``rxpkts``: Packets to RX length-based split configuration. 292 293* ``rxhdrs``: Packets to RX proto-based split configuration. 294 295* ``txpkts``: Packets to TX configuration. 296 297* ``txtimes``: Burst time pattern for Tx only mode. 298 299For example: 300 301.. code-block:: console 302 303 testpmd> show config rxtx 304 305 io packet forwarding - CRC stripping disabled - packets/burst=16 306 nb forwarding cores=2 - nb forwarding ports=1 307 RX queues=1 - RX desc=128 - RX free threshold=0 308 RX threshold registers: pthresh=8 hthresh=8 wthresh=4 309 TX queues=1 - TX desc=512 - TX free threshold=0 310 TX threshold registers: pthresh=36 hthresh=0 wthresh=0 311 TX RS bit threshold=0 - TXQ flags=0x0 312 313set fwd 314~~~~~~~ 315 316Set the packet forwarding mode:: 317 318 testpmd> set fwd (io|mac|macswap|flowgen| \ 319 rxonly|txonly|csum|icmpecho|noisy|5tswap|shared-rxq|recycle_mbufs) (""|retry) 320 321``retry`` can be specified for forwarding engines except ``rx_only``. 322 323The available information categories are: 324 325* ``io``: Forwards packets "as-is" in I/O mode. 326 This is the fastest possible forwarding operation as it does not access packets data. 327 This is the default mode. 328 329* ``mac``: Changes the source and the destination Ethernet addresses of packets before forwarding them. 330 Default application behavior is to set source Ethernet address to that of the transmitting interface, and destination 331 address to a dummy value (set during init). The user may specify a target destination Ethernet address via the 'eth-peer' or 332 'eth-peers-configfile' command-line options. It is not currently possible to specify a specific source Ethernet address. 333 334* ``macswap``: MAC swap forwarding mode. 335 Swaps the source and the destination Ethernet addresses of packets before forwarding them. 336 337* ``flowgen``: Multi-flow generation mode. 338 Originates a number of flows (with varying destination IP addresses), and terminate receive traffic. 339 340* ``rxonly``: Receives packets but doesn't transmit them. 341 342* ``txonly``: Generates and transmits packets without receiving any. 343 344* ``csum``: Changes the checksum field with hardware or software methods depending on the offload flags on the packet. 345 346* ``icmpecho``: Receives a burst of packets, lookup for ICMP echo requests and, if any, send back ICMP echo replies. 347 348* ``ieee1588``: Demonstrate L2 IEEE1588 V2 PTP timestamping for RX and TX. 349 350* ``noisy``: Noisy neighbor simulation. 351 Simulate more realistic behavior of a guest machine engaged in receiving 352 and sending packets performing Virtual Network Function (VNF). 353 354* ``5tswap``: Swap the source and destination of L2,L3,L4 if they exist. 355 356 L2 swaps the source address and destination address of Ethernet, as same as ``macswap``. 357 358 L3 swaps the source address and destination address of IP (v4 and v6). 359 360 L4 swaps the source port and destination port of transport layer (TCP and UDP). 361 362* ``shared-rxq``: Receive only for shared Rx queue. 363 Resolve packet source port from mbuf and update stream statistics accordingly. 364 365* ``recycle_mbufs``: Recycle Tx queue used mbufs for Rx queue mbuf ring. 366 This mode uses fast path mbuf recycle feature and forwards packets in I/O mode. 367 368Example:: 369 370 testpmd> set fwd rxonly 371 372 Set rxonly packet forwarding mode 373 374 375show fwd 376~~~~~~~~ 377 378When running, forwarding engines maintain statistics from the time they have been started. 379Example for the io forwarding engine, with some packet drops on the tx side:: 380 381 testpmd> show fwd stats all 382 383 ------- Forward Stats for RX Port= 0/Queue= 0 -> TX Port= 1/Queue= 0 ------- 384 RX-packets: 274293770 TX-packets: 274293642 TX-dropped: 128 385 386 ------- Forward Stats for RX Port= 1/Queue= 0 -> TX Port= 0/Queue= 0 ------- 387 RX-packets: 274301850 TX-packets: 274301850 TX-dropped: 0 388 389 ---------------------- Forward statistics for port 0 ---------------------- 390 RX-packets: 274293802 RX-dropped: 0 RX-total: 274293802 391 TX-packets: 274301862 TX-dropped: 0 TX-total: 274301862 392 ---------------------------------------------------------------------------- 393 394 ---------------------- Forward statistics for port 1 ---------------------- 395 RX-packets: 274301894 RX-dropped: 0 RX-total: 274301894 396 TX-packets: 274293706 TX-dropped: 128 TX-total: 274293834 397 ---------------------------------------------------------------------------- 398 399 +++++++++++++++ Accumulated forward statistics for all ports+++++++++++++++ 400 RX-packets: 548595696 RX-dropped: 0 RX-total: 548595696 401 TX-packets: 548595568 TX-dropped: 128 TX-total: 548595696 402 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 403 404 405clear fwd 406~~~~~~~~~ 407 408Clear the forwarding engines statistics:: 409 410 testpmd> clear fwd stats all 411 412read rxd 413~~~~~~~~ 414 415Display an RX descriptor for a port RX queue:: 416 417 testpmd> read rxd (port_id) (queue_id) (rxd_id) 418 419For example:: 420 421 testpmd> read rxd 0 0 4 422 0x0000000B - 0x001D0180 / 0x0000000B - 0x001D0180 423 424read txd 425~~~~~~~~ 426 427Display a TX descriptor for a port TX queue:: 428 429 testpmd> read txd (port_id) (queue_id) (txd_id) 430 431For example:: 432 433 testpmd> read txd 0 0 4 434 0x00000001 - 0x24C3C440 / 0x000F0000 - 0x2330003C 435 436show vf stats 437~~~~~~~~~~~~~ 438 439Display VF statistics:: 440 441 testpmd> show vf stats (port_id) (vf_id) 442 443clear vf stats 444~~~~~~~~~~~~~~ 445 446Reset VF statistics:: 447 448 testpmd> clear vf stats (port_id) (vf_id) 449 450show rx offloading capabilities 451~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 452 453List all per queue and per port Rx offloading capabilities of a port:: 454 455 testpmd> show port (port_id) rx_offload capabilities 456 457show rx offloading configuration 458~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 459 460List port level and all queue level Rx offloading configuration:: 461 462 testpmd> show port (port_id) rx_offload configuration 463 464show tx offloading capabilities 465~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 466 467List all per queue and per port Tx offloading capabilities of a port:: 468 469 testpmd> show port (port_id) tx_offload capabilities 470 471show tx offloading configuration 472~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 473 474List port level and all queue level Tx offloading configuration:: 475 476 testpmd> show port (port_id) tx_offload configuration 477 478show tx metadata setting 479~~~~~~~~~~~~~~~~~~~~~~~~ 480 481Show Tx metadata value set for a specific port:: 482 483 testpmd> show port (port_id) tx_metadata 484 485show port supported ptypes 486~~~~~~~~~~~~~~~~~~~~~~~~~~ 487 488Show ptypes supported for a specific port:: 489 490 testpmd> show port (port_id) ptypes 491 492set port supported ptypes 493~~~~~~~~~~~~~~~~~~~~~~~~~ 494 495set packet types classification for a specific port:: 496 497 testpmd> set port (port_id) ptypes_mask (mask) 498 499show port mac addresses info 500~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 501 502Show mac addresses added for a specific port:: 503 504 testpmd> show port (port_id) macs 505 506 507show port multicast mac addresses info 508~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 509 510Show multicast mac addresses added for a specific port:: 511 512 testpmd> show port (port_id) mcast_macs 513 514show flow transfer proxy port ID for the given port 515~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 516 517Show proxy port ID to use as the 1st argument in commands to 518manage ``transfer`` flows and their indirect components. 519:: 520 521 testpmd> show port (port_id) flow transfer proxy 522 523show device info 524~~~~~~~~~~~~~~~~ 525 526Show general information about devices probed:: 527 528 testpmd> show device info (<identifier>|all) 529 530For example: 531 532.. code-block:: console 533 534 testpmd> show device info net_pcap0 535 536 ********************* Infos for device net_pcap0 ********************* 537 Bus name: vdev 538 Driver name: net_pcap 539 Devargs: iface=enP2p6s0,phy_mac=1 540 Connect to socket: -1 541 542 Port id: 2 543 MAC address: 1E:37:93:28:04:B8 544 Device name: net_pcap0 545 546dump physmem 547~~~~~~~~~~~~ 548 549Dumps all physical memory segment layouts:: 550 551 testpmd> dump_physmem 552 553dump memzone 554~~~~~~~~~~~~ 555 556Dumps the layout of all memory zones:: 557 558 testpmd> dump_memzone 559 560dump socket memory 561~~~~~~~~~~~~~~~~~~ 562 563Dumps the memory usage of all sockets:: 564 565 testpmd> dump_socket_mem 566 567dump struct size 568~~~~~~~~~~~~~~~~ 569 570Dumps the size of all memory structures:: 571 572 testpmd> dump_struct_sizes 573 574dump ring 575~~~~~~~~~ 576 577Dumps the status of all or specific element in DPDK rings:: 578 579 testpmd> dump_ring [ring_name] 580 581dump mempool 582~~~~~~~~~~~~ 583 584Dumps the statistics of all or specific memory pool:: 585 586 testpmd> dump_mempool [mempool_name] 587 588dump devargs 589~~~~~~~~~~~~ 590 591Dumps the user device list:: 592 593 testpmd> dump_devargs 594 595dump lcores 596~~~~~~~~~~~ 597 598Dumps the logical cores list:: 599 600 testpmd> dump_lcores 601 602dump trace 603~~~~~~~~~~ 604 605Dumps the tracing data to the folder according to the current EAL settings:: 606 607 testpmd> dump_trace 608 609dump log types 610~~~~~~~~~~~~~~ 611 612Dumps the log level for all the dpdk modules:: 613 614 testpmd> dump_log_types 615 616show (raw_encap|raw_decap) 617~~~~~~~~~~~~~~~~~~~~~~~~~~ 618 619Display content of raw_encap/raw_decap buffers in hex:: 620 621 testpmd> show <raw_encap|raw_decap> <index> 622 testpmd> show <raw_encap|raw_decap> all 623 624For example:: 625 626 testpmd> show raw_encap 6 627 628 index: 6 at [0x1c565b0], len=50 629 00000000: 00 00 00 00 00 00 16 26 36 46 56 66 08 00 45 00 | .......&6FVf..E. 630 00000010: 00 00 00 00 00 00 00 11 00 00 C0 A8 01 06 C0 A8 | ................ 631 00000020: 03 06 00 00 00 FA 00 00 00 00 08 00 00 00 00 00 | ................ 632 00000030: 06 00 | .. 633 634show fec capabilities 635~~~~~~~~~~~~~~~~~~~~~ 636 637Show fec capabilities of a port:: 638 639 testpmd> show port (port_id) fec capabilities 640 641show fec mode 642~~~~~~~~~~~~~ 643 644Show fec mode of a port:: 645 646 testpmd> show port (port_id) fec_mode 647 648 649Configuration Functions 650----------------------- 651 652The testpmd application can be configured from the runtime as well as from the command-line. 653 654This section details the available configuration functions that are available. 655 656.. note:: 657 658 Configuration changes only become active when forwarding is started/restarted. 659 660set default 661~~~~~~~~~~~ 662 663Reset forwarding to the default configuration:: 664 665 testpmd> set default 666 667set verbose 668~~~~~~~~~~~ 669 670Set the debug verbosity level:: 671 672 testpmd> set verbose (level) 673 674Available levels are as following: 675 676* ``0`` silent except for error. 677* ``1`` fully verbose except for Tx packets. 678* ``2`` fully verbose except for Rx packets. 679* ``> 2`` fully verbose. 680 681set log 682~~~~~~~ 683 684Set the log level for a log type:: 685 686 testpmd> set log global|(type) (level) 687 688Where: 689 690* ``type`` is the log name. 691 692* ``level`` is the log level. 693 694For example, to change the global log level:: 695 696 testpmd> set log global (level) 697 698Regexes can also be used for type. To change log level of user1, user2 and user3:: 699 700 testpmd> set log user[1-3] (level) 701 702set nbport 703~~~~~~~~~~ 704 705Set the number of ports used by the application: 706 707set nbport (num) 708 709This is equivalent to the ``--nb-ports`` command-line option. 710 711set nbcore 712~~~~~~~~~~ 713 714Set the number of cores used by the application:: 715 716 testpmd> set nbcore (num) 717 718This is equivalent to the ``--nb-cores`` command-line option. 719 720.. note:: 721 722 The number of cores used must not be greater than number of ports used multiplied by the number of queues per port. 723 724set coremask 725~~~~~~~~~~~~ 726 727Set the forwarding cores hexadecimal mask:: 728 729 testpmd> set coremask (mask) 730 731This is equivalent to the ``--coremask`` command-line option. 732 733.. note:: 734 735 The main lcore is reserved for command line parsing only and cannot be masked on for packet forwarding. 736 737set portmask 738~~~~~~~~~~~~ 739 740Set the forwarding ports hexadecimal mask:: 741 742 testpmd> set portmask (mask) 743 744This is equivalent to the ``--portmask`` command-line option. 745 746set record-core-cycles 747~~~~~~~~~~~~~~~~~~~~~~ 748 749Set the recording of CPU cycles:: 750 751 testpmd> set record-core-cycles (on|off) 752 753Where: 754 755* ``on`` enables measurement of CPU cycles per packet. 756 757* ``off`` disables measurement of CPU cycles per packet. 758 759This is equivalent to the ``--record-core-cycles command-line`` option. 760 761set record-burst-stats 762~~~~~~~~~~~~~~~~~~~~~~ 763 764Set the displaying of RX and TX bursts:: 765 766 testpmd> set record-burst-stats (on|off) 767 768Where: 769 770* ``on`` enables display of RX and TX bursts. 771 772* ``off`` disables display of RX and TX bursts. 773 774This is equivalent to the ``--record-burst-stats command-line`` option. 775 776set burst 777~~~~~~~~~ 778 779Set number of packets per burst:: 780 781 testpmd> set burst (num) 782 783This is equivalent to the ``--burst command-line`` option. 784 785When retry is enabled, the transmit delay time and number of retries can also be set:: 786 787 testpmd> set burst tx delay (microseconds) retry (num) 788 789set rxoffs 790~~~~~~~~~~ 791 792Set the offsets of segments relating to the data buffer beginning on receiving 793if split feature is engaged. Affects only the queues configured with split 794offloads (currently BUFFER_SPLIT is supported only). 795 796 testpmd> set rxoffs (x[,y]*) 797 798Where x[,y]* represents a CSV list of values, without white space. If the list 799of offsets is shorter than the list of segments the zero offsets will be used 800for the remaining segments. 801 802set rxpkts 803~~~~~~~~~~ 804 805Set the length of segments to scatter packets on receiving if split 806feature is engaged. Affects only the queues configured with split offloads 807(currently BUFFER_SPLIT is supported only). Optionally the multiple memory 808pools can be specified with --mbuf-size command line parameter and the mbufs 809to receive will be allocated sequentially from these extra memory pools (the 810mbuf for the first segment is allocated from the first pool, the second one 811from the second pool, and so on, if segment number is greater then pool's the 812mbuf for remaining segments will be allocated from the last valid pool). 813 814 testpmd> set rxpkts (x[,y]*) 815 816Where x[,y]* represents a CSV list of values, without white space. Zero value 817means to use the corresponding memory pool data buffer size. 818 819set rxhdrs 820~~~~~~~~~~ 821 822Set the protocol headers of segments to scatter packets on receiving 823if split feature is engaged. 824Affects only the queues configured with split offloads 825(currently BUFFER_SPLIT is supported only). 826 827 testpmd> set rxhdrs (eth[,ipv4]*) 828 829Where eth[,ipv4]* represents a CSV list of values, without white space. 830If the list of offsets is shorter than the list of segments, 831zero offsets will be used for the remaining segments. 832 833set txpkts 834~~~~~~~~~~ 835 836Set the length of each segment of the TX-ONLY packets or length of packet for FLOWGEN mode:: 837 838 testpmd> set txpkts (x[,y]*) 839 840Where x[,y]* represents a CSV list of values, without white space. 841 842set txtimes 843~~~~~~~~~~~ 844 845Configure the timing burst pattern for Tx only mode. This command enables 846the packet send scheduling on dynamic timestamp mbuf field and configures 847timing pattern in Tx only mode. In this mode, if scheduling is enabled 848application provides timestamps in the packets being sent. It is possible 849to configure delay (in unspecified device clock units) between bursts 850and between the packets within the burst:: 851 852 testpmd> set txtimes (inter),(intra) 853 854where: 855 856* ``inter`` is the delay between the bursts in the device clock units. 857 If ``intra`` is zero, this is the time between the beginnings of the 858 first packets in the neighbour bursts, if ``intra`` is not zero, 859 ``inter`` specifies the time between the beginning of the first packet 860 of the current burst and the beginning of the last packet of the 861 previous burst. If ``inter`` parameter is zero the send scheduling 862 on timestamps is disabled (default). 863 864* ``intra`` is the delay between the packets within the burst specified 865 in the device clock units. The number of packets in the burst is defined 866 by regular burst setting. If ``intra`` parameter is zero no timestamps 867 provided in the packets excepting the first one in the burst. 868 869As the result the bursts of packet will be transmitted with specific 870delays between the packets within the burst and specific delay between 871the bursts. The rte_eth_read_clock() must be supported by the device(s) 872and is supposed to be engaged to get the current device clock value 873and provide the reference for the timestamps. If there is no supported 874rte_eth_read_clock() there will be no send scheduling provided on the port. 875 876set txsplit 877~~~~~~~~~~~ 878 879Set the split policy for the TX packets, applicable for TX-ONLY and CSUM forwarding modes:: 880 881 testpmd> set txsplit (off|on|rand) 882 883Where: 884 885* ``off`` disable packet copy & split for CSUM mode. 886 887* ``on`` split outgoing packet into multiple segments. Size of each segment 888 and number of segments per packet is determined by ``set txpkts`` command 889 (see above). 890 891* ``rand`` same as 'on', but number of segments per each packet is a random value between 1 and total number of segments. 892 893set corelist 894~~~~~~~~~~~~ 895 896Set the list of forwarding cores:: 897 898 testpmd> set corelist (x[,y]*) 899 900For example, to change the forwarding cores: 901 902.. code-block:: console 903 904 testpmd> set corelist 3,1 905 testpmd> show config fwd 906 907 io packet forwarding - ports=2 - cores=2 - streams=2 - NUMA support disabled 908 Logical Core 3 (socket 0) forwards packets on 1 streams: 909 RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01 910 Logical Core 1 (socket 0) forwards packets on 1 streams: 911 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00 912 913.. note:: 914 915 The cores are used in the same order as specified on the command line. 916 917set portlist 918~~~~~~~~~~~~ 919 920Set the list of forwarding ports:: 921 922 testpmd> set portlist (x[,y]*) 923 924For example, to change the port forwarding: 925 926.. code-block:: console 927 928 testpmd> set portlist 0,2,1,3 929 testpmd> show config fwd 930 931 io packet forwarding - ports=4 - cores=1 - streams=4 932 Logical Core 3 (socket 0) forwards packets on 4 streams: 933 RX P=0/Q=0 (socket 0) -> TX P=2/Q=0 (socket 0) peer=02:00:00:00:00:01 934 RX P=2/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00 935 RX P=1/Q=0 (socket 0) -> TX P=3/Q=0 (socket 0) peer=02:00:00:00:00:03 936 RX P=3/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:02 937 938set port setup on 939~~~~~~~~~~~~~~~~~ 940 941Select how to retrieve new ports created after "port attach" command:: 942 943 testpmd> set port setup on (iterator|event) 944 945For each new port, a setup is done. 946It will find the probed ports via RTE_ETH_FOREACH_MATCHING_DEV loop 947in iterator mode, or via RTE_ETH_EVENT_NEW in event mode. 948 949set tx loopback 950~~~~~~~~~~~~~~~ 951 952Enable/disable tx loopback:: 953 954 testpmd> set tx loopback (port_id) (on|off) 955 956set drop enable 957~~~~~~~~~~~~~~~ 958 959set drop enable bit for all queues:: 960 961 testpmd> set all queues drop (port_id) (on|off) 962 963set mac antispoof (for VF) 964~~~~~~~~~~~~~~~~~~~~~~~~~~ 965 966Set mac antispoof for a VF from the PF:: 967 968 testpmd> set vf mac antispoof (port_id) (vf_id) (on|off) 969 970vlan set stripq 971~~~~~~~~~~~~~~~ 972 973Set the VLAN strip for a queue on a port:: 974 975 testpmd> vlan set stripq (on|off) (port_id,queue_id) 976 977vlan set stripq (for VF) 978~~~~~~~~~~~~~~~~~~~~~~~~ 979 980Set VLAN strip for all queues in a pool for a VF from the PF:: 981 982 testpmd> set vf vlan stripq (port_id) (vf_id) (on|off) 983 984vlan set insert (for VF) 985~~~~~~~~~~~~~~~~~~~~~~~~ 986 987Set VLAN insert for a VF from the PF:: 988 989 testpmd> set vf vlan insert (port_id) (vf_id) (vlan_id) 990 991vlan set antispoof (for VF) 992~~~~~~~~~~~~~~~~~~~~~~~~~~~ 993 994Set VLAN antispoof for a VF from the PF:: 995 996 testpmd> set vf vlan antispoof (port_id) (vf_id) (on|off) 997 998vlan set (strip|filter|qinq_strip|extend) 999~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1000Set the VLAN strip/filter/QinQ strip/extend on for a port:: 1001 1002 testpmd> vlan set (strip|filter|qinq_strip|extend) (on|off) (port_id) 1003 1004vlan set tpid 1005~~~~~~~~~~~~~ 1006 1007Set the inner or outer VLAN TPID for packet filtering on a port:: 1008 1009 testpmd> vlan set (inner|outer) tpid (value) (port_id) 1010 1011.. note:: 1012 1013 TPID value must be a 16-bit number (value <= 65536). 1014 1015rx_vlan add 1016~~~~~~~~~~~ 1017 1018Add a VLAN ID, or all identifiers, to the set of VLAN identifiers filtered by port ID:: 1019 1020 testpmd> rx_vlan add (vlan_id|all) (port_id) 1021 1022.. note:: 1023 1024 VLAN filter must be set on that port. VLAN ID < 4096. 1025 Depending on the NIC used, number of vlan_ids may be limited to the maximum entries 1026 in VFTA table. This is important if enabling all vlan_ids. 1027 1028rx_vlan rm 1029~~~~~~~~~~ 1030 1031Remove a VLAN ID, or all identifiers, from the set of VLAN identifiers filtered by port ID:: 1032 1033 testpmd> rx_vlan rm (vlan_id|all) (port_id) 1034 1035rx_vlan add (for VF) 1036~~~~~~~~~~~~~~~~~~~~ 1037 1038Add a VLAN ID, to the set of VLAN identifiers filtered for VF(s) for port ID:: 1039 1040 testpmd> rx_vlan add (vlan_id) port (port_id) vf (vf_mask) 1041 1042rx_vlan rm (for VF) 1043~~~~~~~~~~~~~~~~~~~ 1044 1045Remove a VLAN ID, from the set of VLAN identifiers filtered for VF(s) for port ID:: 1046 1047 testpmd> rx_vlan rm (vlan_id) port (port_id) vf (vf_mask) 1048 1049rx_vxlan_port add 1050~~~~~~~~~~~~~~~~~ 1051 1052Add an UDP port for VXLAN packet filter on a port:: 1053 1054 testpmd> rx_vxlan_port add (udp_port) (port_id) 1055 1056rx_vxlan_port remove 1057~~~~~~~~~~~~~~~~~~~~ 1058 1059Remove an UDP port for VXLAN packet filter on a port:: 1060 1061 testpmd> rx_vxlan_port rm (udp_port) (port_id) 1062 1063tx_vlan set 1064~~~~~~~~~~~ 1065 1066Set hardware insertion of VLAN IDs in packets sent on a port:: 1067 1068 testpmd> tx_vlan set (port_id) vlan_id[, vlan_id_outer] 1069 1070For example, set a single VLAN ID (5) insertion on port 0:: 1071 1072 tx_vlan set 0 5 1073 1074Or, set double VLAN ID (inner: 2, outer: 3) insertion on port 1:: 1075 1076 tx_vlan set 1 2 3 1077 1078 1079tx_vlan set pvid 1080~~~~~~~~~~~~~~~~ 1081 1082Set port based hardware insertion of VLAN ID in packets sent on a port:: 1083 1084 testpmd> tx_vlan set pvid (port_id) (vlan_id) (on|off) 1085 1086tx_vlan reset 1087~~~~~~~~~~~~~ 1088 1089Disable hardware insertion of a VLAN header in packets sent on a port:: 1090 1091 testpmd> tx_vlan reset (port_id) 1092 1093csum set 1094~~~~~~~~ 1095 1096Select hardware or software calculation of the checksum when 1097transmitting a packet using the ``csum`` forwarding engine:: 1098 1099 testpmd> csum set (ip|udp|tcp|sctp|outer-ip|outer-udp) (hw|sw) (port_id) 1100 1101Where: 1102 1103* ``ip|udp|tcp|sctp`` always relate to the inner layer. 1104 1105* ``outer-ip`` relates to the outer IP layer (only for IPv4) in the case where the packet is recognized 1106 as a tunnel packet by the forwarding engine (geneve, gre, gtp, ipip and vxlan are supported). 1107 See also the ``csum parse-tunnel`` command. 1108 1109* ``outer-udp`` relates to the outer UDP layer in the case where the packet is recognized 1110 as a tunnel packet by the forwarding engine (geneve, gtp and vxlan are supported). 1111 See also the ``csum parse-tunnel`` command. 1112 1113.. note:: 1114 1115 Check the NIC Datasheet for hardware limits. 1116 1117csum parse-tunnel 1118~~~~~~~~~~~~~~~~~ 1119 1120Define how tunneled packets should be handled by the csum forward 1121engine:: 1122 1123 testpmd> csum parse-tunnel (on|off) (tx_port_id) 1124 1125If enabled, the csum forward engine will try to recognize supported 1126tunnel headers (geneve, gtp, gre, ipip, vxlan). 1127 1128If disabled, treat tunnel packets as non-tunneled packets (a inner 1129header is handled as a packet payload). 1130 1131.. note:: 1132 1133 The port argument is the TX port like in the ``csum set`` command. 1134 1135Example: 1136 1137Consider a packet in packet like the following:: 1138 1139 eth_out/ipv4_out/udp_out/vxlan/eth_in/ipv4_in/tcp_in 1140 1141* If parse-tunnel is enabled, the ``ip|udp|tcp|sctp`` parameters of ``csum set`` 1142 command relate to the inner headers (here ``ipv4_in`` and ``tcp_in``), and the 1143 ``outer-ip|outer-udp`` parameter relates to the outer headers (here ``ipv4_out`` and ``udp_out``). 1144 1145* If parse-tunnel is disabled, the ``ip|udp|tcp|sctp`` parameters of ``csum set`` 1146 command relate to the outer headers, here ``ipv4_out`` and ``udp_out``. 1147 1148csum show 1149~~~~~~~~~ 1150 1151Display tx checksum offload configuration:: 1152 1153 testpmd> csum show (port_id) 1154 1155tso set 1156~~~~~~~ 1157 1158Enable TCP Segmentation Offload (TSO) in the ``csum`` forwarding engine:: 1159 1160 testpmd> tso set (segsize) (port_id) 1161 1162.. note:: 1163 1164 Check the NIC datasheet for hardware limits. 1165 1166tso show 1167~~~~~~~~ 1168 1169Display the status of TCP Segmentation Offload:: 1170 1171 testpmd> tso show (port_id) 1172 1173tunnel tso set 1174~~~~~~~~~~~~~~ 1175 1176Set tso segment size of tunneled packets for a port in csum engine:: 1177 1178 testpmd> tunnel_tso set (tso_segsz) (port_id) 1179 1180tunnel tso show 1181~~~~~~~~~~~~~~~ 1182 1183Display the status of tunneled TCP Segmentation Offload for a port:: 1184 1185 testpmd> tunnel_tso show (port_id) 1186 1187set port - gro 1188~~~~~~~~~~~~~~ 1189 1190Enable or disable GRO in ``csum`` forwarding engine:: 1191 1192 testpmd> set port <port_id> gro on|off 1193 1194If enabled, the csum forwarding engine will perform GRO on the TCP/IPv4 1195packets received from the given port. 1196 1197If disabled, packets received from the given port won't be performed 1198GRO. By default, GRO is disabled for all ports. 1199 1200.. note:: 1201 1202 When enable GRO for a port, TCP/IPv4 packets received from the port 1203 will be performed GRO. After GRO, all merged packets have bad 1204 checksums, since the GRO library doesn't re-calculate checksums for 1205 the merged packets. Therefore, if users want the merged packets to 1206 have correct checksums, please select HW IP checksum calculation and 1207 HW TCP checksum calculation for the port which the merged packets are 1208 transmitted to. 1209 1210show port - gro 1211~~~~~~~~~~~~~~~ 1212 1213Display GRO configuration for a given port:: 1214 1215 testpmd> show port <port_id> gro 1216 1217set gro flush 1218~~~~~~~~~~~~~ 1219 1220Set the cycle to flush the GROed packets from reassembly tables:: 1221 1222 testpmd> set gro flush <cycles> 1223 1224When enable GRO, the csum forwarding engine performs GRO on received 1225packets, and the GROed packets are stored in reassembly tables. Users 1226can use this command to determine when the GROed packets are flushed 1227from the reassembly tables. 1228 1229The ``cycles`` is measured in GRO operation times. The csum forwarding 1230engine flushes the GROed packets from the tables every ``cycles`` GRO 1231operations. 1232 1233By default, the value of ``cycles`` is 1, which means flush GROed packets 1234from the reassembly tables as soon as one GRO operation finishes. The value 1235of ``cycles`` should be in the range of 1 to ``GRO_MAX_FLUSH_CYCLES``. 1236 1237Please note that the large value of ``cycles`` may cause the poor TCP/IP 1238stack performance. Because the GROed packets are delayed to arrive the 1239stack, thus causing more duplicated ACKs and TCP retransmissions. 1240 1241set port - gso 1242~~~~~~~~~~~~~~ 1243 1244Toggle per-port GSO support in ``csum`` forwarding engine:: 1245 1246 testpmd> set port <port_id> gso on|off 1247 1248If enabled, the csum forwarding engine will perform GSO on supported IPv4 1249packets, transmitted on the given port. 1250 1251If disabled, packets transmitted on the given port will not undergo GSO. 1252By default, GSO is disabled for all ports. 1253 1254.. note:: 1255 1256 When GSO is enabled on a port, supported IPv4 packets transmitted on that 1257 port undergo GSO. Afterwards, the segmented packets are represented by 1258 multi-segment mbufs; however, the csum forwarding engine doesn't calculation 1259 of checksums for GSO'd segments in SW. As a result, if users want correct 1260 checksums in GSO segments, they should enable HW checksum calculation for 1261 GSO-enabled ports. 1262 1263 For example, HW checksum calculation for VxLAN GSO'd packets may be enabled 1264 by setting the following options in the csum forwarding engine: 1265 1266 testpmd> csum set outer_ip hw <port_id> 1267 1268 testpmd> csum set ip hw <port_id> 1269 1270 testpmd> csum set tcp hw <port_id> 1271 1272 UDP GSO is the same as IP fragmentation, which treats the UDP header 1273 as the payload and does not modify it during segmentation. That is, 1274 after UDP GSO, only the first output fragment has the original UDP 1275 header. Therefore, users need to enable HW IP checksum calculation 1276 and SW UDP checksum calculation for GSO-enabled ports, if they want 1277 correct checksums for UDP/IPv4 packets. 1278 1279set gso segsz 1280~~~~~~~~~~~~~ 1281 1282Set the maximum GSO segment size (measured in bytes), which includes the 1283packet header and the packet payload for GSO-enabled ports (global):: 1284 1285 testpmd> set gso segsz <length> 1286 1287show port - gso 1288~~~~~~~~~~~~~~~ 1289 1290Display the status of Generic Segmentation Offload for a given port:: 1291 1292 testpmd> show port <port_id> gso 1293 1294mac_addr add 1295~~~~~~~~~~~~ 1296 1297Add an alternative MAC address to a port:: 1298 1299 testpmd> mac_addr add (port_id) (XX:XX:XX:XX:XX:XX) 1300 1301mac_addr remove 1302~~~~~~~~~~~~~~~ 1303 1304Remove a MAC address from a port:: 1305 1306 testpmd> mac_addr remove (port_id) (XX:XX:XX:XX:XX:XX) 1307 1308mcast_addr add 1309~~~~~~~~~~~~~~ 1310 1311To add the multicast MAC address to/from the set of multicast addresses 1312filtered by port:: 1313 1314 testpmd> mcast_addr add (port_id) (mcast_addr) 1315 1316mcast_addr remove 1317~~~~~~~~~~~~~~~~~ 1318 1319To remove the multicast MAC address to/from the set of multicast addresses 1320filtered by port:: 1321 1322 testpmd> mcast_addr remove (port_id) (mcast_addr) 1323 1324mcast_addr flush 1325~~~~~~~~~~~~~~~~ 1326 1327Flush all multicast MAC addresses on port_id:: 1328 1329 testpmd> mcast_addr flush (port_id) 1330 1331mac_addr add (for VF) 1332~~~~~~~~~~~~~~~~~~~~~ 1333 1334Add an alternative MAC address for a VF to a port:: 1335 1336 testpmd> mac_add add port (port_id) vf (vf_id) (XX:XX:XX:XX:XX:XX) 1337 1338mac_addr set 1339~~~~~~~~~~~~ 1340 1341Set the default MAC address for a port:: 1342 1343 testpmd> mac_addr set (port_id) (XX:XX:XX:XX:XX:XX) 1344 1345mac_addr set (for VF) 1346~~~~~~~~~~~~~~~~~~~~~ 1347 1348Set the MAC address for a VF from the PF:: 1349 1350 testpmd> set vf mac addr (port_id) (vf_id) (XX:XX:XX:XX:XX:XX) 1351 1352set eth-peer 1353~~~~~~~~~~~~ 1354 1355Set the forwarding peer address for certain port:: 1356 1357 testpmd> set eth-peer (port_id) (peer_addr) 1358 1359This is equivalent to the ``--eth-peer`` command-line option. 1360 1361set port-uta 1362~~~~~~~~~~~~ 1363 1364Set the unicast hash filter(s) on/off for a port:: 1365 1366 testpmd> set port (port_id) uta (XX:XX:XX:XX:XX:XX|all) (on|off) 1367 1368set promisc 1369~~~~~~~~~~~ 1370 1371Set the promiscuous mode on for a port or for all ports. 1372In promiscuous mode packets are not dropped if they aren't for the specified MAC address:: 1373 1374 testpmd> set promisc (port_id|all) (on|off) 1375 1376set allmulti 1377~~~~~~~~~~~~ 1378 1379Set the allmulti mode for a port or for all ports:: 1380 1381 testpmd> set allmulti (port_id|all) (on|off) 1382 1383Same as the ifconfig (8) option. Controls how multicast packets are handled. 1384 1385set flow_ctrl rx 1386~~~~~~~~~~~~~~~~ 1387 1388Set the link flow control parameter on a port:: 1389 1390 testpmd> set flow_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \ 1391 (pause_time) (send_xon) mac_ctrl_frame_fwd (on|off) \ 1392 autoneg (on|off) (port_id) 1393 1394Where: 1395 1396* ``high_water`` (integer): High threshold value to trigger XOFF. 1397 1398* ``low_water`` (integer): Low threshold value to trigger XON. 1399 1400* ``pause_time`` (integer): Pause quota in the Pause frame. 1401 1402* ``send_xon`` (0/1): Send XON frame. 1403 1404* ``mac_ctrl_frame_fwd``: Enable receiving MAC control frames. 1405 1406* ``autoneg``: Change the auto-negotiation parameter. 1407 1408show flow control 1409~~~~~~~~~~~~~~~~~ 1410 1411show the link flow control parameter on a port:: 1412 1413 testpmd> show port <port_id> flow_ctrl 1414 1415set pfc_ctrl rx 1416~~~~~~~~~~~~~~~ 1417 1418Set the priority flow control parameter on a port:: 1419 1420 testpmd> set pfc_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \ 1421 (pause_time) (priority) (port_id) 1422 1423Where: 1424 1425* ``high_water`` (integer): High threshold value. 1426 1427* ``low_water`` (integer): Low threshold value. 1428 1429* ``pause_time`` (integer): Pause quota in the Pause frame. 1430 1431* ``priority`` (0-7): VLAN User Priority. 1432 1433set pfc_queue_ctrl 1434~~~~~~~~~~~~~~~~~~ 1435 1436Set the priority flow control parameter on a given Rx and Tx queue of a port:: 1437 1438 testpmd> set pfc_queue_ctrl <port_id> rx (on|off) <tx_qid> <tx_tc> \ 1439 tx (on|off) <rx_qid> <rx_tc> <pause_time> 1440 1441Where: 1442 1443* ``tx_qid`` (integer): Tx qid for which ``tx_tc`` will be applied and traffic 1444 will be paused when PFC frame is received with ``tx_tc`` enabled. 1445 1446* ``tx_tc`` (0-15): TC for which traffic is to be paused for xmit. 1447 1448* ``rx_qid`` (integer): Rx qid for which threshold will be applied and PFC 1449 frame will be generated with ``tx_tc`` when exceeds the threshold. 1450 1451* ``rx_tc`` (0-15): TC filled in PFC frame for which remote Tx is to be paused. 1452 1453* ``pause_time`` (integer): Pause quanta filled in the PFC frame for which 1454 interval, remote Tx will be paused. Valid only if Tx pause is on. 1455 1456Set Rx queue available descriptors threshold 1457~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1458 1459Set available descriptors threshold for a specific Rx queue of port:: 1460 1461 testpmd> set port (port_id) rxq (queue_id) avail_thresh (0..99) 1462 1463Use 0 value to disable the threshold and corresponding event. 1464 1465set stat_qmap 1466~~~~~~~~~~~~~ 1467 1468Set statistics mapping (qmapping 0..15) for RX/TX queue on port:: 1469 1470 testpmd> set stat_qmap (tx|rx) (port_id) (queue_id) (qmapping) 1471 1472For example, to set rx queue 2 on port 0 to mapping 5:: 1473 1474 testpmd>set stat_qmap rx 0 2 5 1475 1476set xstats-hide-zero 1477~~~~~~~~~~~~~~~~~~~~ 1478 1479Set the option to hide zero values for xstats display:: 1480 1481 testpmd> set xstats-hide-zero on|off 1482 1483.. note:: 1484 1485 By default, the zero values are displayed for xstats. 1486 1487set port - rx/tx (for VF) 1488~~~~~~~~~~~~~~~~~~~~~~~~~ 1489 1490Set VF receive/transmit from a port:: 1491 1492 testpmd> set port (port_id) vf (vf_id) (rx|tx) (on|off) 1493 1494set port - rx mode(for VF) 1495~~~~~~~~~~~~~~~~~~~~~~~~~~ 1496 1497Set the VF receive mode of a port:: 1498 1499 testpmd> set port (port_id) vf (vf_id) \ 1500 rxmode (AUPE|ROPE|BAM|MPE) (on|off) 1501 1502The available receive modes are: 1503 1504* ``AUPE``: Accepts untagged VLAN. 1505 1506* ``ROPE``: Accepts unicast hash. 1507 1508* ``BAM``: Accepts broadcast packets. 1509 1510* ``MPE``: Accepts all multicast packets. 1511 1512set port - tx_rate (for Queue) 1513~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1514 1515Set TX rate limitation for a queue on a port:: 1516 1517 testpmd> set port (port_id) queue (queue_id) rate (rate_value) 1518 1519set port - tx_rate (for VF) 1520~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1521 1522Set TX rate limitation for queues in VF on a port:: 1523 1524 testpmd> set port (port_id) vf (vf_id) rate (rate_value) queue_mask (queue_mask) 1525 1526set flush_rx 1527~~~~~~~~~~~~ 1528 1529Set the flush on RX streams before forwarding. 1530The default is flush ``on``. 1531Mainly used with PCAP drivers to turn off the default behavior of flushing the first 512 packets on RX streams:: 1532 1533 testpmd> set flush_rx off 1534 1535set link up 1536~~~~~~~~~~~ 1537 1538Set link up for a port:: 1539 1540 testpmd> set link-up port (port id) 1541 1542set link down 1543~~~~~~~~~~~~~ 1544 1545Set link down for a port:: 1546 1547 testpmd> set link-down port (port id) 1548 1549E-tag set 1550~~~~~~~~~ 1551 1552Enable E-tag insertion for a VF on a port:: 1553 1554 testpmd> E-tag set insertion on port-tag-id (value) port (port_id) vf (vf_id) 1555 1556Disable E-tag insertion for a VF on a port:: 1557 1558 testpmd> E-tag set insertion off port (port_id) vf (vf_id) 1559 1560Enable/disable E-tag stripping on a port:: 1561 1562 testpmd> E-tag set stripping (on|off) port (port_id) 1563 1564Enable/disable E-tag based forwarding on a port:: 1565 1566 testpmd> E-tag set forwarding (on|off) port (port_id) 1567 1568config per port Rx offloading 1569~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1570 1571Enable or disable port Rx offloading on all Rx queues of a port:: 1572 1573 testpmd> port config (port_id|all) rx_offload (offloading) on|off 1574 1575* ``offloading``: can be any of these offloading capability: 1576 all, 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, rss_hash 1580 1581This command should be run when the port is stopped, or else it will fail. 1582 1583config per queue Rx offloading 1584~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1585 1586Enable or disable a per queue Rx offloading only on a specific Rx queue:: 1587 1588 testpmd> port (port_id) rxq (queue_id) rx_offload (offloading) on|off 1589 1590* ``offloading``: can be any of these offloading capability: 1591 all, vlan_strip, ipv4_cksum, udp_cksum, tcp_cksum, tcp_lro, 1592 qinq_strip, outer_ipv4_cksum, macsec_strip, 1593 vlan_filter, vlan_extend, scatter, timestamp, security, 1594 keep_crc 1595 1596This command should be run when the port is stopped, or else it will fail. 1597 1598config per port Tx offloading 1599~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1600 1601Enable or disable port Tx offloading on all Tx queues of a port:: 1602 1603 testpmd> port config (port_id|all) tx_offload (offloading) on|off 1604 1605* ``offloading``: can be any of these offloading capability: 1606 all, vlan_insert, ipv4_cksum, udp_cksum, tcp_cksum, 1607 sctp_cksum, tcp_tso, udp_tso, outer_ipv4_cksum, 1608 qinq_insert, vxlan_tnl_tso, gre_tnl_tso, 1609 ipip_tnl_tso, geneve_tnl_tso, macsec_insert, 1610 mt_lockfree, multi_segs, mbuf_fast_free, security 1611 1612This command should be run when the port is stopped, or else it will fail. 1613 1614config per queue Tx offloading 1615~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1616 1617Enable or disable a per queue Tx offloading only on a specific Tx queue:: 1618 1619 testpmd> port (port_id) txq (queue_id) tx_offload (offloading) on|off 1620 1621* ``offloading``: can be any of these offloading capability: 1622 all, vlan_insert, ipv4_cksum, udp_cksum, tcp_cksum, 1623 sctp_cksum, tcp_tso, udp_tso, outer_ipv4_cksum, 1624 qinq_insert, vxlan_tnl_tso, gre_tnl_tso, 1625 ipip_tnl_tso, geneve_tnl_tso, macsec_insert, 1626 mt_lockfree, multi_segs, mbuf_fast_free, security 1627 1628This command should be run when the port is stopped, or else it will fail. 1629 1630config per queue Tx affinity mapping 1631~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1632 1633Map a Tx queue with an aggregated port of the DPDK port (specified with port_id):: 1634 1635 testpmd> port (port_id) txq (queue_id) affinity (value) 1636 1637* ``affinity``: the number of the aggregated port. 1638 When multiple ports are aggregated into a single one, 1639 it allows to choose which port to use for Tx via a queue. 1640 1641This command should be run when the port is stopped, otherwise it fails. 1642 1643 1644Config VXLAN Encap outer layers 1645~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1646 1647Configure the outer layer to encapsulate a packet inside a VXLAN tunnel:: 1648 1649 set vxlan ip-version (ipv4|ipv6) vni (vni) udp-src (udp-src) \ 1650 udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) eth-src (eth-src) \ 1651 eth-dst (eth-dst) 1652 1653 set vxlan-with-vlan ip-version (ipv4|ipv6) vni (vni) udp-src (udp-src) \ 1654 udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) vlan-tci (vlan-tci) \ 1655 eth-src (eth-src) eth-dst (eth-dst) 1656 1657 set vxlan-tos-ttl ip-version (ipv4|ipv6) vni (vni) udp-src (udp-src) \ 1658 udp-dst (udp-dst) ip-tos (ip-tos) ip-ttl (ip-ttl) ip-src (ip-src) \ 1659 ip-dst (ip-dst) eth-src (eth-src) eth-dst (eth-dst) 1660 1661These commands will set an internal configuration inside testpmd, any following 1662flow rule using the action vxlan_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 NVGRE Encap outer layers 1667~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1668 1669Configure the outer layer to encapsulate a packet inside a NVGRE tunnel:: 1670 1671 set nvgre ip-version (ipv4|ipv6) tni (tni) ip-src (ip-src) ip-dst (ip-dst) \ 1672 eth-src (eth-src) eth-dst (eth-dst) 1673 set nvgre-with-vlan ip-version (ipv4|ipv6) tni (tni) ip-src (ip-src) \ 1674 ip-dst (ip-dst) vlan-tci (vlan-tci) eth-src (eth-src) eth-dst (eth-dst) 1675 1676These commands will set an internal configuration inside testpmd, any following 1677flow rule using the action nvgre_encap will use the last configuration set. 1678To have a different encapsulation header, one of those commands must be called 1679before the flow rule creation. 1680 1681Config L2 Encap 1682~~~~~~~~~~~~~~~ 1683 1684Configure the l2 to be used when encapsulating a packet with L2:: 1685 1686 set l2_encap ip-version (ipv4|ipv6) eth-src (eth-src) eth-dst (eth-dst) 1687 set l2_encap-with-vlan ip-version (ipv4|ipv6) vlan-tci (vlan-tci) \ 1688 eth-src (eth-src) eth-dst (eth-dst) 1689 1690Those commands will set an internal configuration inside testpmd, any following 1691flow rule using the action l2_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 L2 Decap 1696~~~~~~~~~~~~~~~ 1697 1698Configure the l2 to be removed when decapsulating a packet with L2:: 1699 1700 set l2_decap ip-version (ipv4|ipv6) 1701 set l2_decap-with-vlan ip-version (ipv4|ipv6) 1702 1703Those commands will set an internal configuration inside testpmd, any following 1704flow rule using the action l2_decap will use the last configuration set. 1705To have a different encapsulation header, one of those commands must be called 1706before the flow rule creation. 1707 1708Config MPLSoGRE Encap outer layers 1709~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1710 1711Configure the outer layer to encapsulate a packet inside a MPLSoGRE tunnel:: 1712 1713 set mplsogre_encap ip-version (ipv4|ipv6) label (label) \ 1714 ip-src (ip-src) ip-dst (ip-dst) eth-src (eth-src) eth-dst (eth-dst) 1715 set mplsogre_encap-with-vlan ip-version (ipv4|ipv6) label (label) \ 1716 ip-src (ip-src) ip-dst (ip-dst) vlan-tci (vlan-tci) \ 1717 eth-src (eth-src) eth-dst (eth-dst) 1718 1719These commands will set an internal configuration inside testpmd, any following 1720flow rule using the action mplsogre_encap will use the last configuration set. 1721To have a different encapsulation header, one of those commands must be called 1722before the flow rule creation. 1723 1724Config MPLSoGRE Decap outer layers 1725~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1726 1727Configure the outer layer to decapsulate MPLSoGRE packet:: 1728 1729 set mplsogre_decap ip-version (ipv4|ipv6) 1730 set mplsogre_decap-with-vlan ip-version (ipv4|ipv6) 1731 1732These commands will set an internal configuration inside testpmd, any following 1733flow rule using the action mplsogre_decap will use the last configuration set. 1734To have a different decapsulation header, one of those commands must be called 1735before the flow rule creation. 1736 1737Config MPLSoUDP Encap outer layers 1738~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1739 1740Configure the outer layer to encapsulate a packet inside a MPLSoUDP tunnel:: 1741 1742 set mplsoudp_encap ip-version (ipv4|ipv6) label (label) udp-src (udp-src) \ 1743 udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) \ 1744 eth-src (eth-src) eth-dst (eth-dst) 1745 set mplsoudp_encap-with-vlan ip-version (ipv4|ipv6) label (label) \ 1746 udp-src (udp-src) udp-dst (udp-dst) ip-src (ip-src) ip-dst (ip-dst) \ 1747 vlan-tci (vlan-tci) eth-src (eth-src) eth-dst (eth-dst) 1748 1749These commands will set an internal configuration inside testpmd, any following 1750flow rule using the action mplsoudp_encap will use the last configuration set. 1751To have a different encapsulation header, one of those commands must be called 1752before the flow rule creation. 1753 1754Config MPLSoUDP Decap outer layers 1755~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1756 1757Configure the outer layer to decapsulate MPLSoUDP packet:: 1758 1759 set mplsoudp_decap ip-version (ipv4|ipv6) 1760 set mplsoudp_decap-with-vlan ip-version (ipv4|ipv6) 1761 1762These commands will set an internal configuration inside testpmd, any following 1763flow rule using the action mplsoudp_decap will use the last configuration set. 1764To have a different decapsulation header, one of those commands must be called 1765before the flow rule creation. 1766 1767Config Raw Encapsulation 1768~~~~~~~~~~~~~~~~~~~~~~~~~ 1769 1770Configure the raw data to be used when encapsulating a packet by 1771rte_flow_action_raw_encap:: 1772 1773 set raw_encap {index} {item} [/ {item} [...]] / end_set 1774 1775There are multiple global buffers for ``raw_encap``, this command will set one 1776internal buffer index by ``{index}``. 1777If there is no ``{index}`` specified:: 1778 1779 set raw_encap {item} [/ {item} [...]] / end_set 1780 1781the default index ``0`` is used. 1782In order to use different encapsulating header, ``index`` must be specified 1783during the flow rule creation:: 1784 1785 testpmd> flow create 0 egress pattern eth / ipv4 / end actions 1786 raw_encap index 2 / end 1787 1788Otherwise the default index ``0`` is used. 1789 1790Config Raw Decapsulation 1791~~~~~~~~~~~~~~~~~~~~~~~~ 1792 1793Configure the raw data to be used when decapsulating a packet by 1794rte_flow_action_raw_decap:: 1795 1796 set raw_decap {index} {item} [/ {item} [...]] / end_set 1797 1798There are multiple global buffers for ``raw_decap``, this command will set 1799one internal buffer index by ``{index}``. 1800If there is no ``{index}`` specified:: 1801 1802 set raw_decap {item} [/ {item} [...]] / end_set 1803 1804the default index ``0`` is used. 1805In order to use different decapsulating header, ``index`` must be specified 1806during the flow rule creation:: 1807 1808 testpmd> flow create 0 egress pattern eth / ipv4 / end actions 1809 raw_encap index 3 / end 1810 1811Otherwise the default index ``0`` is used. 1812 1813Set fec mode 1814~~~~~~~~~~~~ 1815 1816Set fec mode for a specific port:: 1817 1818 testpmd> set port (port_id) fec_mode auto|off|rs|baser|llrs 1819 1820Config Sample actions list 1821~~~~~~~~~~~~~~~~~~~~~~~~~~ 1822 1823Configure the sample actions list to be used when sampling a packet by 1824rte_flow_action_sample:: 1825 1826 set sample_actions {index} {action} [/ {action} [...]] / end 1827 1828There are multiple global buffers for ``sample_actions``, this command will set 1829one internal buffer index by ``{index}``. 1830 1831In order to use different sample actions list, ``index`` must be specified 1832during the flow rule creation:: 1833 1834 testpmd> flow create 0 ingress pattern eth / ipv4 / end actions 1835 sample ratio 2 index 2 / end 1836 1837Otherwise the default index ``0`` is used. 1838 1839Port Functions 1840-------------- 1841 1842The following sections show functions for configuring ports. 1843 1844.. note:: 1845 1846 Port configuration changes only become active when forwarding is started/restarted. 1847 1848.. _port_attach: 1849 1850port attach 1851~~~~~~~~~~~ 1852 1853Attach a port specified by pci address or virtual device args:: 1854 1855 testpmd> port attach (identifier) 1856 1857To attach a new pci device, the device should be recognized by kernel first. 1858Then it should be moved under DPDK management. 1859Finally the port can be attached to testpmd. 1860 1861For example, to move a pci device using ixgbe under DPDK management: 1862 1863.. code-block:: console 1864 1865 # Check the status of the available devices. 1866 ./usertools/dpdk-devbind.py --status 1867 1868 Network devices using DPDK-compatible driver 1869 ============================================ 1870 <none> 1871 1872 Network devices using kernel driver 1873 =================================== 1874 0000:0a:00.0 '82599ES 10-Gigabit' if=eth2 drv=ixgbe unused= 1875 1876 1877 # Bind the device to igb_uio. 1878 sudo ./usertools/dpdk-devbind.py -b igb_uio 0000:0a:00.0 1879 1880 1881 # Recheck the status of the devices. 1882 ./usertools/dpdk-devbind.py --status 1883 Network devices using DPDK-compatible driver 1884 ============================================ 1885 0000:0a:00.0 '82599ES 10-Gigabit' drv=igb_uio unused= 1886 1887To attach a port created by virtual device, above steps are not needed. 1888 1889For example, to attach a port whose pci address is 0000:0a:00.0. 1890 1891.. code-block:: console 1892 1893 testpmd> port attach 0000:0a:00.0 1894 Attaching a new port... 1895 EAL: PCI device 0000:0a:00.0 on NUMA socket -1 1896 EAL: probe driver: 8086:10fb rte_ixgbe_pmd 1897 EAL: PCI memory mapped at 0x7f83bfa00000 1898 EAL: PCI memory mapped at 0x7f83bfa80000 1899 PMD: eth_ixgbe_dev_init(): MAC: 2, PHY: 18, SFP+: 5 1900 PMD: eth_ixgbe_dev_init(): port 0 vendorID=0x8086 deviceID=0x10fb 1901 Port 0 is attached. Now total ports is 1 1902 Done 1903 1904For example, to attach a port created by pcap PMD. 1905 1906.. code-block:: console 1907 1908 testpmd> port attach net_pcap0 1909 Attaching a new port... 1910 PMD: Initializing pmd_pcap for net_pcap0 1911 PMD: Creating pcap-backed ethdev on numa socket 0 1912 Port 0 is attached. Now total ports is 1 1913 Done 1914 1915In this case, identifier is ``net_pcap0``. 1916This identifier format is the same as ``--vdev`` format of DPDK applications. 1917 1918For example, to re-attach a bonding port which has been previously detached, 1919the mode and slave parameters must be given. 1920 1921.. code-block:: console 1922 1923 testpmd> port attach net_bond_0,mode=0,slave=1 1924 Attaching a new port... 1925 EAL: Initializing pmd_bond for net_bond_0 1926 EAL: Create bonding device net_bond_0 on port 0 in mode 0 on socket 0. 1927 Port 0 is attached. Now total ports is 1 1928 Done 1929 1930 1931port detach 1932~~~~~~~~~~~ 1933 1934Detach a specific port:: 1935 1936 testpmd> port detach (port_id) 1937 1938Before detaching a port, the port should be stopped and closed. 1939 1940For example, to detach a pci device port 0. 1941 1942.. code-block:: console 1943 1944 testpmd> port stop 0 1945 Stopping ports... 1946 Done 1947 testpmd> port close 0 1948 Closing ports... 1949 Done 1950 1951 testpmd> port detach 0 1952 Detaching a port... 1953 EAL: PCI device 0000:0a:00.0 on NUMA socket -1 1954 EAL: remove driver: 8086:10fb rte_ixgbe_pmd 1955 EAL: PCI memory unmapped at 0x7f83bfa00000 1956 EAL: PCI memory unmapped at 0x7f83bfa80000 1957 Done 1958 1959 1960For example, to detach a virtual device port 0. 1961 1962.. code-block:: console 1963 1964 testpmd> port stop 0 1965 Stopping ports... 1966 Done 1967 testpmd> port close 0 1968 Closing ports... 1969 Done 1970 1971 testpmd> port detach 0 1972 Detaching a port... 1973 PMD: Closing pcap ethdev on numa socket 0 1974 Port 'net_pcap0' is detached. Now total ports is 0 1975 Done 1976 1977To remove a pci device completely from the system, first detach the port from testpmd. 1978Then the device should be moved under kernel management. 1979Finally the device can be removed using kernel pci hotplug functionality. 1980 1981For example, to move a pci device under kernel management: 1982 1983.. code-block:: console 1984 1985 sudo ./usertools/dpdk-devbind.py -b ixgbe 0000:0a:00.0 1986 1987 ./usertools/dpdk-devbind.py --status 1988 1989 Network devices using DPDK-compatible driver 1990 ============================================ 1991 <none> 1992 1993 Network devices using kernel driver 1994 =================================== 1995 0000:0a:00.0 '82599ES 10-Gigabit' if=eth2 drv=ixgbe unused=igb_uio 1996 1997To remove a port created by a virtual device, above steps are not needed. 1998 1999port start 2000~~~~~~~~~~ 2001 2002Start all ports or a specific port:: 2003 2004 testpmd> port start (port_id|all) 2005 2006port stop 2007~~~~~~~~~ 2008 2009Stop all ports or a specific port:: 2010 2011 testpmd> port stop (port_id|all) 2012 2013port close 2014~~~~~~~~~~ 2015 2016Close all ports or a specific port:: 2017 2018 testpmd> port close (port_id|all) 2019 2020port reset 2021~~~~~~~~~~ 2022 2023Reset all ports or a specific port:: 2024 2025 testpmd> port reset (port_id|all) 2026 2027User should stop port(s) before resetting and (re-)start after reset. 2028 2029port config - queue ring size 2030~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2031 2032Configure a rx/tx queue ring size:: 2033 2034 testpmd> port config (port_id) (rxq|txq) (queue_id) ring_size (value) 2035 2036Only take effect after command that (re-)start the port or command that setup specific queue. 2037 2038port start/stop queue 2039~~~~~~~~~~~~~~~~~~~~~ 2040 2041Start/stop a rx/tx queue on a specific port:: 2042 2043 testpmd> port (port_id) (rxq|txq) (queue_id) (start|stop) 2044 2045port config - queue deferred start 2046~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2047 2048Switch on/off deferred start of a specific port queue:: 2049 2050 testpmd> port (port_id) (rxq|txq) (queue_id) deferred_start (on|off) 2051 2052port setup queue 2053~~~~~~~~~~~~~~~~~~~~~ 2054 2055Setup a rx/tx queue on a specific port:: 2056 2057 testpmd> port (port_id) (rxq|txq) (queue_id) setup 2058 2059Only take effect when port is started. 2060 2061port config - speed 2062~~~~~~~~~~~~~~~~~~~ 2063 2064Set the speed and duplex mode for all ports or a specific port:: 2065 2066 testpmd> port config (port_id|all) speed (10|100|1000|2500|5000|10000|25000|40000|50000|100000|200000|400000|auto) \ 2067 duplex (half|full|auto) 2068 2069port config - queues/descriptors 2070~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2071 2072Set number of queues/descriptors for rxq, txq, rxd and txd:: 2073 2074 testpmd> port config all (rxq|txq|rxd|txd) (value) 2075 2076This is equivalent to the ``--rxq``, ``--txq``, ``--rxd`` and ``--txd`` command-line options. 2077 2078port config - max-pkt-len 2079~~~~~~~~~~~~~~~~~~~~~~~~~ 2080 2081Set the maximum packet length:: 2082 2083 testpmd> port config all max-pkt-len (value) 2084 2085This is equivalent to the ``--max-pkt-len`` command-line option. 2086 2087port config - max-lro-pkt-size 2088~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2089 2090Set the maximum LRO aggregated packet size:: 2091 2092 testpmd> port config all max-lro-pkt-size (value) 2093 2094This is equivalent to the ``--max-lro-pkt-size`` command-line option. 2095 2096port config - Drop Packets 2097~~~~~~~~~~~~~~~~~~~~~~~~~~ 2098 2099Enable or disable packet drop on all RX queues of all ports when no receive buffers available:: 2100 2101 testpmd> port config all drop-en (on|off) 2102 2103Packet dropping when no receive buffers available is off by default. 2104 2105The ``on`` option is equivalent to the ``--enable-drop-en`` command-line option. 2106 2107port config - RSS 2108~~~~~~~~~~~~~~~~~ 2109 2110Set the RSS (Receive Side Scaling) mode on or off:: 2111 testpmd> port config all rss (all|default|level-default|level-outer|level-inner| \ 2112 ip|tcp|udp|sctp|tunnel|vlan|none| \ 2113 ipv4|ipv4-frag|ipv4-tcp|ipv4-udp|ipv4-sctp|ipv4-other| \ 2114 ipv6|ipv6-frag|ipv6-tcp|ipv6-udp|ipv6-sctp| \ 2115 ipv6-other|ipv6-ex|ipv6-tcp-ex|ipv6-udp-ex|ipv6-flow-label| \ 2116 l2-payload|port|vxlan|geneve|nvgre|gtpu|eth|s-vlan|c-vlan| \ 2117 esp|ah|l2tpv3|pfcp|pppoe|ecpri|mpls|ipv4-chksum|l4-chksum| \ 2118 l2tpv2|l3-pre96|l3-pre64|l3-pre56|l3-pre48|l3-pre40|l3-pre32| \ 2119 l2-dst-only|l2-src-only|l4-dst-only|l4-src-only|l3-dst-only|l3-src-only|<rsstype_id>) 2120 2121RSS is on by default. 2122 2123The ``all`` option is equivalent to eth|vlan|ip|tcp|udp|sctp|ether|l2tpv3|esp|ah|pfcp|l2tpv2. 2124 2125The ``default`` option enables all supported RSS types reported by device info. 2126 2127The ``none`` option is equivalent to the ``--disable-rss`` command-line option. 2128 2129port config - RSS Reta 2130~~~~~~~~~~~~~~~~~~~~~~ 2131 2132Set the RSS (Receive Side Scaling) redirection table:: 2133 2134 testpmd> port config all rss reta (hash,queue)[,(hash,queue)] 2135 2136port config - DCB 2137~~~~~~~~~~~~~~~~~ 2138 2139Set the DCB mode for an individual port:: 2140 2141 testpmd> port config (port_id) dcb vt (on|off) (traffic_class) pfc (on|off) 2142 2143The traffic class should be 4 or 8. 2144 2145port config - Burst 2146~~~~~~~~~~~~~~~~~~~ 2147 2148Set the number of packets per burst:: 2149 2150 testpmd> port config all burst (value) 2151 2152This is equivalent to the ``--burst`` command-line option. 2153 2154port config - Threshold 2155~~~~~~~~~~~~~~~~~~~~~~~ 2156 2157Set thresholds for TX/RX queues:: 2158 2159 testpmd> port config all (threshold) (value) 2160 2161Where the threshold type can be: 2162 2163* ``txpt:`` Set the prefetch threshold register of the TX rings, 0 <= value <= 255. 2164 2165* ``txht:`` Set the host threshold register of the TX rings, 0 <= value <= 255. 2166 2167* ``txwt:`` Set the write-back threshold register of the TX rings, 0 <= value <= 255. 2168 2169* ``rxpt:`` Set the prefetch threshold register of the RX rings, 0 <= value <= 255. 2170 2171* ``rxht:`` Set the host threshold register of the RX rings, 0 <= value <= 255. 2172 2173* ``rxwt:`` Set the write-back threshold register of the RX rings, 0 <= value <= 255. 2174 2175* ``txfreet:`` Set the transmit free threshold of the TX rings, 0 <= value <= txd. 2176 2177* ``rxfreet:`` Set the transmit free threshold of the RX rings, 0 <= value <= rxd. 2178 2179* ``txrst:`` Set the transmit RS bit threshold of TX rings, 0 <= value <= txd. 2180 2181These threshold options are also available from the command-line. 2182 2183port config pctype mapping 2184~~~~~~~~~~~~~~~~~~~~~~~~~~ 2185 2186Reset pctype mapping table:: 2187 2188 testpmd> port config (port_id) pctype mapping reset 2189 2190Update hardware defined pctype to software defined flow type mapping table:: 2191 2192 testpmd> port config (port_id) pctype mapping update (pctype_id_0[,pctype_id_1]*) (flow_type_id) 2193 2194where: 2195 2196* ``pctype_id_x``: hardware pctype id as index of bit in bitmask value of the pctype mapping table. 2197 2198* ``flow_type_id``: software flow type id as the index of the pctype mapping table. 2199 2200port config input set 2201~~~~~~~~~~~~~~~~~~~~~ 2202 2203Config RSS/FDIR/FDIR flexible payload input set for some pctype:: 2204 2205 testpmd> port config (port_id) pctype (pctype_id) \ 2206 (hash_inset|fdir_inset|fdir_flx_inset) \ 2207 (get|set|clear) field (field_idx) 2208 2209Clear RSS/FDIR/FDIR flexible payload input set for some pctype:: 2210 2211 testpmd> port config (port_id) pctype (pctype_id) \ 2212 (hash_inset|fdir_inset|fdir_flx_inset) clear all 2213 2214where: 2215 2216* ``pctype_id``: hardware packet classification types. 2217* ``field_idx``: hardware field index. 2218 2219port config udp_tunnel_port 2220~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2221 2222Add/remove UDP tunnel port for VXLAN/GENEVE tunneling protocols:: 2223 2224 testpmd> port config (port_id) udp_tunnel_port add|rm vxlan|geneve|ecpri (udp_port) 2225 2226port config tx_metadata 2227~~~~~~~~~~~~~~~~~~~~~~~ 2228 2229Set Tx metadata value per port. 2230testpmd will add this value to any Tx packet sent from this port:: 2231 2232 testpmd> port config (port_id) tx_metadata (value) 2233 2234port config dynf 2235~~~~~~~~~~~~~~~~ 2236 2237Set/clear dynamic flag per port. 2238testpmd will register this flag in the mbuf (same registration 2239for both Tx and Rx). Then set/clear this flag for each Tx 2240packet sent from this port. The set bit only works for Tx packet:: 2241 2242 testpmd> port config (port_id) dynf (name) (set|clear) 2243 2244port config mtu 2245~~~~~~~~~~~~~~~ 2246 2247To configure MTU(Maximum Transmission Unit) on devices using testpmd:: 2248 2249 testpmd> port config mtu (port_id) (value) 2250 2251port config rss hash key 2252~~~~~~~~~~~~~~~~~~~~~~~~ 2253 2254To configure the RSS hash key used to compute the RSS 2255hash of input [IP] packets received on port:: 2256 2257 testpmd> port config <port_id> rss-hash-key (ipv4|ipv4-frag|\ 2258 ipv4-tcp|ipv4-udp|ipv4-sctp|ipv4-other|\ 2259 ipv6|ipv6-frag|ipv6-tcp|ipv6-udp|ipv6-sctp|\ 2260 ipv6-other|l2-payload|ipv6-ex|ipv6-tcp-ex|\ 2261 ipv6-udp-ex <string of hex digits \ 2262 (variable length, NIC dependent)>) 2263 2264port config rss hash algorithm 2265~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2266 2267To configure the RSS hash algorithm used to compute the RSS 2268hash of input packets received on port:: 2269 2270 testpmd> port config <port_id> rss-hash-algo (default|\ 2271 simple_xor|toeplitz|symmetric_toeplitz|\ 2272 symmetric_toeplitz_sort) 2273 2274port cleanup txq mbufs 2275~~~~~~~~~~~~~~~~~~~~~~ 2276 2277To cleanup txq mbufs currently cached by driver:: 2278 2279 testpmd> port cleanup (port_id) txq (queue_id) (free_cnt) 2280 2281If the value of ``free_cnt`` is 0, driver should free all cached mbufs. 2282 2283Device Functions 2284---------------- 2285 2286The following sections show functions for device operations. 2287 2288device detach 2289~~~~~~~~~~~~~ 2290 2291Detach a device specified by pci address or virtual device args:: 2292 2293 testpmd> device detach (identifier) 2294 2295Before detaching a device associated with ports, the ports should be stopped and closed. 2296 2297For example, to detach a pci device whose address is 0002:03:00.0. 2298 2299.. code-block:: console 2300 2301 testpmd> device detach 0002:03:00.0 2302 Removing a device... 2303 Port 1 is now closed 2304 EAL: Releasing pci mapped resource for 0002:03:00.0 2305 EAL: Calling pci_unmap_resource for 0002:03:00.0 at 0x218a050000 2306 EAL: Calling pci_unmap_resource for 0002:03:00.0 at 0x218c050000 2307 Device 0002:03:00.0 is detached 2308 Now total ports is 1 2309 2310For example, to detach a port created by pcap PMD. 2311 2312.. code-block:: console 2313 2314 testpmd> device detach net_pcap0 2315 Removing a device... 2316 Port 0 is now closed 2317 Device net_pcap0 is detached 2318 Now total ports is 0 2319 Done 2320 2321In this case, identifier is ``net_pcap0``. 2322This identifier format is the same as ``--vdev`` format of DPDK applications. 2323 2324Link Bonding Functions 2325---------------------- 2326 2327The Link Bonding functions make it possible to dynamically create and 2328manage link bonding devices from within testpmd interactive prompt. 2329 2330See :doc:`../prog_guide/link_bonding_poll_mode_drv_lib` for more information. 2331 2332Traffic Metering and Policing 2333----------------------------- 2334 2335The following section shows functions for configuring traffic metering and 2336policing on the ethernet device through the use of generic ethdev API. 2337 2338show port traffic management capability 2339~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2340 2341Show traffic metering and policing capability of the port:: 2342 2343 testpmd> show port meter cap (port_id) 2344 2345add port meter profile (srTCM rfc2967) 2346~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2347 2348Add meter profile (srTCM rfc2697) to the ethernet device:: 2349 2350 testpmd> add port meter profile srtcm_rfc2697 (port_id) (profile_id) \ 2351 (cir) (cbs) (ebs) (packet_mode) 2352 2353where: 2354 2355* ``profile_id``: ID for the meter profile. 2356* ``cir``: Committed Information Rate (CIR) (bytes per second or packets per second). 2357* ``cbs``: Committed Burst Size (CBS) (bytes or packets). 2358* ``ebs``: Excess Burst Size (EBS) (bytes or packets). 2359* ``packet_mode``: Packets mode for meter profile. 2360 2361add port meter profile (trTCM rfc2968) 2362~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2363 2364Add meter profile (srTCM rfc2698) to the ethernet device:: 2365 2366 testpmd> add port meter profile trtcm_rfc2698 (port_id) (profile_id) \ 2367 (cir) (pir) (cbs) (pbs) (packet_mode) 2368 2369where: 2370 2371* ``profile_id``: ID for the meter profile. 2372* ``cir``: Committed information rate (bytes per second or packets per second). 2373* ``pir``: Peak information rate (bytes per second or packets per second). 2374* ``cbs``: Committed burst size (bytes or packets). 2375* ``pbs``: Peak burst size (bytes or packets). 2376* ``packet_mode``: Packets mode for meter profile. 2377 2378add port meter profile (trTCM rfc4115) 2379~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2380 2381Add meter profile (trTCM rfc4115) to the ethernet device:: 2382 2383 testpmd> add port meter profile trtcm_rfc4115 (port_id) (profile_id) \ 2384 (cir) (eir) (cbs) (ebs) (packet_mode) 2385 2386where: 2387 2388* ``profile_id``: ID for the meter profile. 2389* ``cir``: Committed information rate (bytes per second or packets per second). 2390* ``eir``: Excess information rate (bytes per second or packets per second). 2391* ``cbs``: Committed burst size (bytes or packets). 2392* ``ebs``: Excess burst size (bytes or packets). 2393* ``packet_mode``: Packets mode for meter profile. 2394 2395delete port meter profile 2396~~~~~~~~~~~~~~~~~~~~~~~~~ 2397 2398Delete meter profile from the ethernet device:: 2399 2400 testpmd> del port meter profile (port_id) (profile_id) 2401 2402create port policy 2403~~~~~~~~~~~~~~~~~~ 2404 2405Create new policy object for the ethernet device:: 2406 2407 testpmd> add port meter policy (port_id) (policy_id) g_actions \ 2408 {action} y_actions {action} r_actions {action} 2409 2410where: 2411 2412* ``policy_id``: policy ID. 2413* ``action``: action lists for green/yellow/red colors. 2414 2415delete port policy 2416~~~~~~~~~~~~~~~~~~ 2417 2418Delete policy object for the ethernet device:: 2419 2420 testpmd> del port meter policy (port_id) (policy_id) 2421 2422where: 2423 2424* ``policy_id``: policy ID. 2425 2426create port meter 2427~~~~~~~~~~~~~~~~~ 2428 2429Create new meter object for the ethernet device:: 2430 2431 testpmd> create port meter (port_id) (mtr_id) (profile_id) \ 2432 (policy_id) (meter_enable) (stats_mask) (shared) (default_input_color) \ 2433 (use_pre_meter_color) [(dscp_tbl_entry0) (dscp_tbl_entry1)...\ 2434 (dscp_tbl_entry63)] [(vlan_tbl_entry0) (vlan_tbl_entry1) ... \ 2435 (vlan_tbl_entry15)] 2436 2437where: 2438 2439* ``mtr_id``: meter object ID. 2440* ``profile_id``: ID for the meter profile. 2441* ``policy_id``: ID for the policy. 2442* ``meter_enable``: When this parameter has a non-zero value, the meter object 2443 gets enabled at the time of creation, otherwise remains disabled. 2444* ``stats_mask``: Mask of statistics counter types to be enabled for the 2445 meter object. 2446* ``shared``: When this parameter has a non-zero value, the meter object is 2447 shared by multiple flows. Otherwise, meter object is used by single flow. 2448* ``default_input_color``: Default input color for incoming packets. 2449 If incoming packet misses DSCP or VLAN input color table then it will be used 2450 as input color. 2451* ``use_pre_meter_color``: When this parameter has a non-zero value, the 2452 input color for the current meter object is determined by the latest meter 2453 object in the same flow. Otherwise, the current meter object uses the 2454 *dscp_table* to determine the input color. 2455* ``dscp_tbl_entryx``: DSCP table entry x providing meter providing input 2456 color, 0 <= x <= 63. 2457* ``vlan_tbl_entryx``: VLAN table entry x providing meter input color, 2458 0 <= x <= 15. 2459 2460enable port meter 2461~~~~~~~~~~~~~~~~~ 2462 2463Enable meter for the ethernet device:: 2464 2465 testpmd> enable port meter (port_id) (mtr_id) 2466 2467disable port meter 2468~~~~~~~~~~~~~~~~~~ 2469 2470Disable meter for the ethernet device:: 2471 2472 testpmd> disable port meter (port_id) (mtr_id) 2473 2474delete port meter 2475~~~~~~~~~~~~~~~~~ 2476 2477Delete meter for the ethernet device:: 2478 2479 testpmd> del port meter (port_id) (mtr_id) 2480 2481Set port meter profile 2482~~~~~~~~~~~~~~~~~~~~~~ 2483 2484Set meter profile for the ethernet device:: 2485 2486 testpmd> set port meter profile (port_id) (mtr_id) (profile_id) 2487 2488set port meter dscp table 2489~~~~~~~~~~~~~~~~~~~~~~~~~ 2490 2491Set meter dscp table for the ethernet device:: 2492 2493 testpmd> set port meter dscp table (port_id) (mtr_id) (proto) \ 2494 [(dscp_tbl_entry0) (dscp_tbl_entry1)...(dscp_tbl_entry63)] 2495 2496set port meter vlan table 2497~~~~~~~~~~~~~~~~~~~~~~~~~ 2498Set meter VLAN table for the Ethernet device:: 2499 2500 testpmd> set port meter vlan table (port_id) (mtr_id) (proto) \ 2501 [(vlan_tbl_entry0) (vlan_tbl_entry1)...(vlan_tbl_entry15)] 2502 2503set port meter protocol 2504~~~~~~~~~~~~~~~~~~~~~~~ 2505Set meter protocol and corresponding priority:: 2506 2507 testpmd> set port meter proto (port_id) (mtr_id) (proto) (prio) 2508 2509get port meter protocol 2510~~~~~~~~~~~~~~~~~~~~~~~ 2511Get meter protocol:: 2512 2513 testpmd> get port meter proto (port_id) (mtr_id) 2514 2515get port meter protocol priority 2516~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2517Get priority associated to meter protocol:: 2518 2519 testpmd> get port meter proto_prio (port_id) (mtr_id) (proto) 2520 2521set port meter stats mask 2522~~~~~~~~~~~~~~~~~~~~~~~~~ 2523 2524Set meter stats mask for the ethernet device:: 2525 2526 testpmd> set port meter stats mask (port_id) (mtr_id) (stats_mask) 2527 2528where: 2529 2530* ``stats_mask``: Bit mask indicating statistics counter types to be enabled. 2531 2532show port meter stats 2533~~~~~~~~~~~~~~~~~~~~~ 2534 2535Show meter stats of the ethernet device:: 2536 2537 testpmd> show port meter stats (port_id) (mtr_id) (clear) 2538 2539where: 2540 2541* ``clear``: Flag that indicates whether the statistics counters should 2542 be cleared (i.e. set to zero) immediately after they have been read or not. 2543 2544Traffic Management 2545------------------ 2546 2547The following section shows functions for configuring traffic management on 2548the ethernet device through the use of generic TM API. 2549 2550show port traffic management capability 2551~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2552 2553Show traffic management capability of the port:: 2554 2555 testpmd> show port tm cap (port_id) 2556 2557show port traffic management capability (hierarchy level) 2558~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2559 2560Show traffic management hierarchy level capability of the port:: 2561 2562 testpmd> show port tm level cap (port_id) (level_id) 2563 2564show port traffic management capability (hierarchy node level) 2565~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2566 2567Show the traffic management hierarchy node capability of the port:: 2568 2569 testpmd> show port tm node cap (port_id) (node_id) 2570 2571show port traffic management hierarchy node type 2572~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2573 2574Show the port traffic management hierarchy node type:: 2575 2576 testpmd> show port tm node type (port_id) (node_id) 2577 2578show port traffic management hierarchy node stats 2579~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2580 2581Show the port traffic management hierarchy node statistics:: 2582 2583 testpmd> show port tm node stats (port_id) (node_id) (clear) 2584 2585where: 2586 2587* ``clear``: When this parameter has a non-zero value, the statistics counters 2588 are cleared (i.e. set to zero) immediately after they have been read, 2589 otherwise the statistics counters are left untouched. 2590 2591Add port traffic management private shaper profile 2592~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2593 2594Add the port traffic management private shaper profile:: 2595 2596 testpmd> add port tm node shaper profile (port_id) (shaper_profile_id) \ 2597 (cmit_tb_rate) (cmit_tb_size) (peak_tb_rate) (peak_tb_size) \ 2598 (packet_length_adjust) (packet_mode) 2599 2600where: 2601 2602* ``shaper_profile id``: Shaper profile ID for the new profile. 2603* ``cmit_tb_rate``: Committed token bucket rate (bytes per second or packets per second). 2604* ``cmit_tb_size``: Committed token bucket size (bytes or packets). 2605* ``peak_tb_rate``: Peak token bucket rate (bytes per second or packets per second). 2606* ``peak_tb_size``: Peak token bucket size (bytes or packets). 2607* ``packet_length_adjust``: The value (bytes) to be added to the length of 2608 each packet for the purpose of shaping. This parameter value can be used to 2609 correct the packet length with the framing overhead bytes that are consumed 2610 on the wire. 2611* ``packet_mode``: Shaper configured in packet mode. This parameter value if 2612 zero, configures shaper in byte mode and if non-zero configures it in packet 2613 mode. 2614 2615Delete port traffic management private shaper profile 2616~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2617 2618Delete the port traffic management private shaper:: 2619 2620 testpmd> del port tm node shaper profile (port_id) (shaper_profile_id) 2621 2622where: 2623 2624* ``shaper_profile id``: Shaper profile ID that needs to be deleted. 2625 2626Add port traffic management shared shaper 2627~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2628 2629Create the port traffic management shared shaper:: 2630 2631 testpmd> add port tm node shared shaper (port_id) (shared_shaper_id) \ 2632 (shaper_profile_id) 2633 2634where: 2635 2636* ``shared_shaper_id``: Shared shaper ID to be created. 2637* ``shaper_profile id``: Shaper profile ID for shared shaper. 2638 2639Set port traffic management shared shaper 2640~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2641 2642Update the port traffic management shared shaper:: 2643 2644 testpmd> set port tm node shared shaper (port_id) (shared_shaper_id) \ 2645 (shaper_profile_id) 2646 2647where: 2648 2649* ``shared_shaper_id``: Shared shaper ID to be update. 2650* ``shaper_profile id``: Shaper profile ID for shared shaper. 2651 2652Delete port traffic management shared shaper 2653~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2654 2655Delete the port traffic management shared shaper:: 2656 2657 testpmd> del port tm node shared shaper (port_id) (shared_shaper_id) 2658 2659where: 2660 2661* ``shared_shaper_id``: Shared shaper ID to be deleted. 2662 2663Set port traffic management hierarchy node private shaper 2664~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2665 2666set the port traffic management hierarchy node private shaper:: 2667 2668 testpmd> set port tm node shaper profile (port_id) (node_id) \ 2669 (shaper_profile_id) 2670 2671where: 2672 2673* ``shaper_profile id``: Private shaper profile ID to be enabled on the 2674 hierarchy node. 2675 2676Add port traffic management WRED profile 2677~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2678 2679Create a new WRED profile:: 2680 2681 testpmd> add port tm node wred profile (port_id) (wred_profile_id) \ 2682 (color_g) (min_th_g) (max_th_g) (maxp_inv_g) (wq_log2_g) \ 2683 (color_y) (min_th_y) (max_th_y) (maxp_inv_y) (wq_log2_y) \ 2684 (color_r) (min_th_r) (max_th_r) (maxp_inv_r) (wq_log2_r) 2685 2686where: 2687 2688* ``wred_profile id``: Identifier for the newly create WRED profile 2689* ``color_g``: Packet color (green) 2690* ``min_th_g``: Minimum queue threshold for packet with green color 2691* ``max_th_g``: Minimum queue threshold for packet with green color 2692* ``maxp_inv_g``: Inverse of packet marking probability maximum value (maxp) 2693* ``wq_log2_g``: Negated log2 of queue weight (wq) 2694* ``color_y``: Packet color (yellow) 2695* ``min_th_y``: Minimum queue threshold for packet with yellow color 2696* ``max_th_y``: Minimum queue threshold for packet with yellow color 2697* ``maxp_inv_y``: Inverse of packet marking probability maximum value (maxp) 2698* ``wq_log2_y``: Negated log2 of queue weight (wq) 2699* ``color_r``: Packet color (red) 2700* ``min_th_r``: Minimum queue threshold for packet with yellow color 2701* ``max_th_r``: Minimum queue threshold for packet with yellow color 2702* ``maxp_inv_r``: Inverse of packet marking probability maximum value (maxp) 2703* ``wq_log2_r``: Negated log2 of queue weight (wq) 2704 2705Delete port traffic management WRED profile 2706~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2707 2708Delete the WRED profile:: 2709 2710 testpmd> del port tm node wred profile (port_id) (wred_profile_id) 2711 2712Add port traffic management hierarchy nonleaf node 2713~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2714 2715Add nonleaf node to port traffic management hierarchy:: 2716 2717 testpmd> add port tm nonleaf node (port_id) (node_id) (parent_node_id) \ 2718 (priority) (weight) (level_id) (shaper_profile_id) \ 2719 (n_sp_priorities) (stats_mask) (n_shared_shapers) \ 2720 [(shared_shaper_0) (shared_shaper_1) ...] \ 2721 2722where: 2723 2724* ``parent_node_id``: Node ID of the parent. 2725* ``priority``: Node priority (highest node priority is zero). This is used by 2726 the SP algorithm running on the parent node for scheduling this node. 2727* ``weight``: Node weight (lowest weight is one). The node weight is relative 2728 to the weight sum of all siblings that have the same priority. It is used by 2729 the WFQ algorithm running on the parent node for scheduling this node. 2730* ``level_id``: Hierarchy level of the node. 2731* ``shaper_profile_id``: Shaper profile ID of the private shaper to be used by 2732 the node. 2733* ``n_sp_priorities``: Number of strict priorities. 2734* ``stats_mask``: Mask of statistics counter types to be enabled for this node. 2735* ``n_shared_shapers``: Number of shared shapers. 2736* ``shared_shaper_id``: Shared shaper id. 2737 2738Add port traffic management hierarchy nonleaf node with packet mode 2739~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2740 2741Add nonleaf node with packet mode to port traffic management hierarchy:: 2742 2743 testpmd> add port tm nonleaf node pktmode (port_id) (node_id) (parent_node_id) \ 2744 (priority) (weight) (level_id) (shaper_profile_id) \ 2745 (n_sp_priorities) (stats_mask) (n_shared_shapers) \ 2746 [(shared_shaper_0) (shared_shaper_1) ...] \ 2747 2748where: 2749 2750* ``parent_node_id``: Node ID of the parent. 2751* ``priority``: Node priority (highest node priority is zero). This is used by 2752 the SP algorithm running on the parent node for scheduling this node. 2753* ``weight``: Node weight (lowest weight is one). The node weight is relative 2754 to the weight sum of all siblings that have the same priority. It is used by 2755 the WFQ algorithm running on the parent node for scheduling this node. 2756* ``level_id``: Hierarchy level of the node. 2757* ``shaper_profile_id``: Shaper profile ID of the private shaper to be used by 2758 the node. 2759* ``n_sp_priorities``: Number of strict priorities. Packet mode is enabled on 2760 all of them. 2761* ``stats_mask``: Mask of statistics counter types to be enabled for this node. 2762* ``n_shared_shapers``: Number of shared shapers. 2763* ``shared_shaper_id``: Shared shaper id. 2764 2765Add port traffic management hierarchy leaf node 2766~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2767 2768Add leaf node to port traffic management hierarchy:: 2769 2770 testpmd> add port tm leaf node (port_id) (node_id) (parent_node_id) \ 2771 (priority) (weight) (level_id) (shaper_profile_id) \ 2772 (cman_mode) (wred_profile_id) (stats_mask) (n_shared_shapers) \ 2773 [(shared_shaper_id) (shared_shaper_id) ...] \ 2774 2775where: 2776 2777* ``parent_node_id``: Node ID of the parent. 2778* ``priority``: Node priority (highest node priority is zero). This is used by 2779 the SP algorithm running on the parent node for scheduling this node. 2780* ``weight``: Node weight (lowest weight is one). The node weight is relative 2781 to the weight sum of all siblings that have the same priority. It is used by 2782 the WFQ algorithm running on the parent node for scheduling this node. 2783* ``level_id``: Hierarchy level of the node. 2784* ``shaper_profile_id``: Shaper profile ID of the private shaper to be used by 2785 the node. 2786* ``cman_mode``: Congestion management mode to be enabled for this node. 2787* ``wred_profile_id``: WRED profile id to be enabled for this node. 2788* ``stats_mask``: Mask of statistics counter types to be enabled for this node. 2789* ``n_shared_shapers``: Number of shared shapers. 2790* ``shared_shaper_id``: Shared shaper id. 2791 2792Delete port traffic management hierarchy node 2793~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2794 2795Delete node from port traffic management hierarchy:: 2796 2797 testpmd> del port tm node (port_id) (node_id) 2798 2799Update port traffic management hierarchy parent node 2800~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2801 2802Update port traffic management hierarchy parent node:: 2803 2804 testpmd> set port tm node parent (port_id) (node_id) (parent_node_id) \ 2805 (priority) (weight) 2806 2807This function can only be called after the hierarchy commit invocation. Its 2808success depends on the port support for this operation, as advertised through 2809the port capability set. This function is valid for all nodes of the traffic 2810management hierarchy except root node. 2811 2812Suspend port traffic management hierarchy node 2813~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2814 2815 testpmd> suspend port tm node (port_id) (node_id) 2816 2817Resume port traffic management hierarchy node 2818~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2819 2820 testpmd> resume port tm node (port_id) (node_id) 2821 2822Commit port traffic management hierarchy 2823~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2824 2825Commit the traffic management hierarchy on the port:: 2826 2827 testpmd> port tm hierarchy commit (port_id) (clean_on_fail) 2828 2829where: 2830 2831* ``clean_on_fail``: When set to non-zero, hierarchy is cleared on function 2832 call failure. On the other hand, hierarchy is preserved when this parameter 2833 is equal to zero. 2834 2835Set port traffic management mark VLAN dei 2836~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2837 2838Enables/Disables the traffic management marking on the port for VLAN packets:: 2839 2840 testpmd> set port tm mark vlan_dei <port_id> <green> <yellow> <red> 2841 2842where: 2843 2844* ``port_id``: The port which on which VLAN packets marked as ``green`` or 2845 ``yellow`` or ``red`` will have dei bit enabled 2846 2847* ``green`` enable 1, disable 0 marking for dei bit of VLAN packets marked as green 2848 2849* ``yellow`` enable 1, disable 0 marking for dei bit of VLAN packets marked as yellow 2850 2851* ``red`` enable 1, disable 0 marking for dei bit of VLAN packets marked as red 2852 2853Set port traffic management mark IP dscp 2854~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2855 2856Enables/Disables the traffic management marking on the port for IP dscp packets:: 2857 2858 testpmd> set port tm mark ip_dscp <port_id> <green> <yellow> <red> 2859 2860where: 2861 2862* ``port_id``: The port which on which IP packets marked as ``green`` or 2863 ``yellow`` or ``red`` will have IP dscp bits updated 2864 2865* ``green`` enable 1, disable 0 marking IP dscp to low drop precedence for green packets 2866 2867* ``yellow`` enable 1, disable 0 marking IP dscp to medium drop precedence for yellow packets 2868 2869* ``red`` enable 1, disable 0 marking IP dscp to high drop precedence for red packets 2870 2871Set port traffic management mark IP ecn 2872~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2873 2874Enables/Disables the traffic management marking on the port for IP ecn packets:: 2875 2876 testpmd> set port tm mark ip_ecn <port_id> <green> <yellow> <red> 2877 2878where: 2879 2880* ``port_id``: The port which on which IP packets marked as ``green`` or 2881 ``yellow`` or ``red`` will have IP ecn bits updated 2882 2883* ``green`` enable 1, disable 0 marking IP ecn for green marked packets with ecn of 2'b01 or 2'b10 2884 to ecn of 2'b11 when IP is caring TCP or SCTP 2885 2886* ``yellow`` enable 1, disable 0 marking IP ecn for yellow marked packets with ecn of 2'b01 or 2'b10 2887 to ecn of 2'b11 when IP is caring TCP or SCTP 2888 2889* ``red`` enable 1, disable 0 marking IP ecn for yellow marked packets with ecn of 2'b01 or 2'b10 2890 to ecn of 2'b11 when IP is caring TCP or SCTP 2891 2892Congestion Management 2893--------------------- 2894 2895Get capabilities 2896~~~~~~~~~~~~~~~~ 2897 2898Retrieve congestion management capabilities supported by driver for given port. 2899Below example command retrieves capabilities for port 0:: 2900 2901 testpmd> show port cman capa 0 2902 2903Get configuration 2904~~~~~~~~~~~~~~~~~ 2905 2906Retrieve congestion management configuration for given port. 2907Below example command retrieves configuration for port 0:: 2908 2909 testpmd> show port cman config 0 2910 2911Set configuration 2912~~~~~~~~~~~~~~~~~ 2913 2914Configures congestion management settings on given queue 2915or mempool associated with queue. 2916Below example command configures RED as congestion management algorithm 2917for port 0 and queue 0:: 2918 2919 testpmd> set port cman config 0 0 obj queue mode red 10 100 1 2920 2921.. _testpmd_rte_flow: 2922 2923Flow rules management 2924--------------------- 2925 2926Control of the generic flow API (*rte_flow*) is fully exposed through the 2927``flow`` command (configuration, validation, creation, destruction, queries 2928and operation modes). 2929 2930``flow`` syntax 2931~~~~~~~~~~~~~~~ 2932 2933Because the ``flow`` command uses dynamic tokens to handle the large number 2934of possible flow rules combinations, its behavior differs slightly from 2935other commands, in particular: 2936 2937- Pressing *?* or the *<tab>* key displays contextual help for the current 2938 token, not that of the entire command. 2939 2940- Optional and repeated parameters are supported (provided they are listed 2941 in the contextual help). 2942 2943The first parameter stands for the operation mode. Possible operations and 2944their general syntax are described below. They are covered in detail in the 2945following sections. 2946 2947- Get info about flow engine:: 2948 2949 flow info {port_id} 2950 2951- Configure flow engine:: 2952 2953 flow configure {port_id} 2954 [queues_number {number}] [queues_size {size}] 2955 [counters_number {number}] 2956 [aging_counters_number {number}] 2957 [meters_number {number}] [flags {number}] 2958 2959- Create a pattern template:: 2960 2961 flow pattern_template {port_id} create [pattern_template_id {id}] 2962 [relaxed {boolean}] [ingress] [egress] [transfer] 2963 template {item} [/ {item} [...]] / end 2964 2965- Destroy a pattern template:: 2966 2967 flow pattern_template {port_id} destroy pattern_template {id} [...] 2968 2969- Create an actions template:: 2970 2971 flow actions_template {port_id} create [actions_template_id {id}] 2972 [ingress] [egress] [transfer] 2973 template {action} [/ {action} [...]] / end 2974 mask {action} [/ {action} [...]] / end 2975 2976- Destroy an actions template:: 2977 2978 flow actions_template {port_id} destroy actions_template {id} [...] 2979 2980- Create a table:: 2981 2982 flow table {port_id} create 2983 [table_id {id}] [resizable] 2984 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 2985 rules_number {number} 2986 pattern_template {pattern_template_id} 2987 actions_template {actions_template_id} 2988 2989- Resize a table:: 2990 2991 flow template_table {port_id} resize 2992 table_resize_id {id} table_resize_rules_num {number} 2993 2994- Complete table resize:: 2995 2996 flow template_table {port_id} resize_complete table {table_id} 2997 2998- Destroy a table:: 2999 3000 flow table {port_id} destroy table {id} [...] 3001 3002- Check whether a flow rule can be created:: 3003 3004 flow validate {port_id} 3005 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 3006 pattern {item} [/ {item} [...]] / end 3007 actions {action} [/ {action} [...]] / end 3008 3009- Enqueue creation of a flow rule:: 3010 3011 flow queue {port_id} create {queue_id} 3012 [postpone {boolean}] template_table {table_id} 3013 pattern_template {pattern_template_index} 3014 actions_template {actions_template_index} 3015 pattern {item} [/ {item} [...]] / end 3016 actions {action} [/ {action} [...]] / end 3017 3018- Enqueue flow update following table resize:: 3019 3020 flow queue {port_id} update_resized {table_id} rule {rule_id} 3021 3022- Enqueue destruction of specific flow rules:: 3023 3024 flow queue {port_id} destroy {queue_id} 3025 [postpone {boolean}] rule {rule_id} [...] 3026 3027- Push enqueued operations:: 3028 3029 flow push {port_id} queue {queue_id} 3030 3031- Pull all operations results from a queue:: 3032 3033 flow pull {port_id} queue {queue_id} 3034 3035- Create a flow rule:: 3036 3037 flow create {port_id} 3038 [group {group_id}] [priority {level}] [ingress] [egress] 3039 [transfer] [tunnel_set {tunnel_id}] [tunnel_match {tunnel_id}] 3040 [user_id {user_id}] pattern {item} [/ {item} [...]] / end 3041 actions {action} [/ {action} [...]] / end 3042 3043- Destroy specific flow rules:: 3044 3045 flow destroy {port_id} rule {rule_id} [...] [user_id] 3046 3047- Update a flow rule with new actions:: 3048 3049 flow update {port_id} {rule_id} 3050 actions {action} [/ {action} [...]] / end [user_id] 3051 3052- Destroy all flow rules:: 3053 3054 flow flush {port_id} 3055 3056- Query an existing flow rule:: 3057 3058 flow query {port_id} {rule_id} {action} [user_id] 3059 3060- List existing flow rules sorted by priority, filtered by group 3061 identifiers:: 3062 3063 flow list {port_id} [group {group_id}] [...] 3064 3065- Restrict ingress traffic to the defined flow rules:: 3066 3067 flow isolate {port_id} {boolean} 3068 3069- Dump internal representation information of all flows in hardware:: 3070 3071 flow dump {port_id} all {output_file} [user_id] 3072 3073 for one flow:: 3074 3075 flow dump {port_id} rule {rule_id} {output_file} [user_id] 3076 3077- List and destroy aged flow rules:: 3078 3079 flow aged {port_id} [destroy] 3080 3081- Enqueue list and destroy aged flow rules:: 3082 3083 flow queue {port_id} aged {queue_id} [destroy] 3084 3085- Tunnel offload - create a tunnel stub:: 3086 3087 flow tunnel create {port_id} type {tunnel_type} 3088 3089- Tunnel offload - destroy a tunnel stub:: 3090 3091 flow tunnel destroy {port_id} id {tunnel_id} 3092 3093- Tunnel offload - list port tunnel stubs:: 3094 3095 flow tunnel list {port_id} 3096 3097Retrieving info about flow management engine 3098~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3099 3100``flow info`` retrieves info on pre-configurable resources in the underlying 3101device to give a hint of possible values for flow engine configuration. 3102 3103``rte_flow_info_get()``:: 3104 3105 flow info {port_id} 3106 3107If successful, it will show:: 3108 3109 Flow engine resources on port #[...]: 3110 Number of queues: #[...] 3111 Size of queues: #[...] 3112 Number of counters: #[...] 3113 Number of aging objects: #[...] 3114 Number of meters: #[...] 3115 3116Otherwise it will show an error message of the form:: 3117 3118 Caught error type [...] ([...]): [...] 3119 3120Configuring flow management engine 3121~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3122 3123``flow configure`` pre-allocates all the needed resources in the underlying 3124device to be used later at the flow creation. Flow queues are allocated as well 3125for asynchronous flow creation/destruction operations. It is bound to 3126``rte_flow_configure()``:: 3127 3128 flow configure {port_id} 3129 [queues_number {number}] [queues_size {size}] 3130 [counters_number {number}] 3131 [aging_counters_number {number}] 3132 [host_port {number}] 3133 [meters_number {number}] 3134 [flags {number}] 3135 3136If successful, it will show:: 3137 3138 Configure flows on port #[...]: number of queues #[...] with #[...] elements 3139 3140Otherwise it will show an error message of the form:: 3141 3142 Caught error type [...] ([...]): [...] 3143 3144Creating pattern templates 3145~~~~~~~~~~~~~~~~~~~~~~~~~~ 3146 3147``flow pattern_template create`` creates the specified pattern template. 3148It is bound to ``rte_flow_pattern_template_create()``:: 3149 3150 flow pattern_template {port_id} create [pattern_template_id {id}] 3151 [relaxed {boolean}] [ingress] [egress] [transfer] 3152 template {item} [/ {item} [...]] / end 3153 3154If successful, it will show:: 3155 3156 Pattern template #[...] created 3157 3158Otherwise it will show an error message of the form:: 3159 3160 Caught error type [...] ([...]): [...] 3161 3162This command uses the same pattern items as ``flow create``, 3163their format is described in `Creating flow rules`_. 3164 3165Destroying pattern templates 3166~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3167 3168``flow pattern_template destroy`` destroys one or more pattern templates 3169from their template ID (as returned by ``flow pattern_template create``), 3170this command calls ``rte_flow_pattern_template_destroy()`` as many 3171times as necessary:: 3172 3173 flow pattern_template {port_id} destroy pattern_template {id} [...] 3174 3175If successful, it will show:: 3176 3177 Pattern template #[...] destroyed 3178 3179It does not report anything for pattern template IDs that do not exist. 3180The usual error message is shown when a pattern template cannot be destroyed:: 3181 3182 Caught error type [...] ([...]): [...] 3183 3184Creating actions templates 3185~~~~~~~~~~~~~~~~~~~~~~~~~~ 3186 3187``flow actions_template create`` creates the specified actions template. 3188It is bound to ``rte_flow_actions_template_create()``:: 3189 3190 flow actions_template {port_id} create [actions_template_id {id}] 3191 [ingress] [egress] [transfer] 3192 template {action} [/ {action} [...]] / end 3193 mask {action} [/ {action} [...]] / end 3194 3195If successful, it will show:: 3196 3197 Actions template #[...] created 3198 3199Otherwise it will show an error message of the form:: 3200 3201 Caught error type [...] ([...]): [...] 3202 3203This command uses the same actions as ``flow create``, 3204their format is described in `Creating flow rules`_. 3205 3206Destroying actions templates 3207~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3208 3209``flow actions_template destroy`` destroys one or more actions templates 3210from their template ID (as returned by ``flow actions_template create``), 3211this command calls ``rte_flow_actions_template_destroy()`` as many 3212times as necessary:: 3213 3214 flow actions_template {port_id} destroy actions_template {id} [...] 3215 3216If successful, it will show:: 3217 3218 Actions template #[...] destroyed 3219 3220It does not report anything for actions template IDs that do not exist. 3221The usual error message is shown when an actions template cannot be destroyed:: 3222 3223 Caught error type [...] ([...]): [...] 3224 3225Creating template table 3226~~~~~~~~~~~~~~~~~~~~~~~ 3227 3228``flow template_table create`` creates the specified template table. 3229It is bound to ``rte_flow_template_table_create()``:: 3230 3231 flow template_table {port_id} create 3232 [table_id {id}] [group {group_id}] 3233 [priority {level}] [ingress] [egress] 3234 [transfer [vport_orig] [wire_orig]] 3235 rules_number {number} 3236 pattern_template {pattern_template_id} 3237 actions_template {actions_template_id} 3238 3239If successful, it will show:: 3240 3241 Template table #[...] created 3242 3243Otherwise it will show an error message of the form:: 3244 3245 Caught error type [...] ([...]): [...] 3246 3247Destroying flow table 3248~~~~~~~~~~~~~~~~~~~~~ 3249 3250``flow template_table destroy`` destroys one or more template tables 3251from their table ID (as returned by ``flow template_table create``), 3252this command calls ``rte_flow_template_table_destroy()`` as many 3253times as necessary:: 3254 3255 flow template_table {port_id} destroy table {id} [...] 3256 3257If successful, it will show:: 3258 3259 Template table #[...] destroyed 3260 3261It does not report anything for table IDs that do not exist. 3262The usual error message is shown when a table cannot be destroyed:: 3263 3264 Caught error type [...] ([...]): [...] 3265 3266Pushing enqueued operations 3267~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3268 3269``flow push`` pushes all the outstanding enqueued operations 3270to the underlying device immediately. 3271It is bound to ``rte_flow_push()``:: 3272 3273 flow push {port_id} queue {queue_id} 3274 3275If successful, it will show:: 3276 3277 Queue #[...] operations pushed 3278 3279The usual error message is shown when operations cannot be pushed:: 3280 3281 Caught error type [...] ([...]): [...] 3282 3283Pulling flow operations results 3284~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3285 3286``flow pull`` asks the underlying device about flow queue operations 3287results and return all the processed (successfully or not) operations. 3288It is bound to ``rte_flow_pull()``:: 3289 3290 flow pull {port_id} queue {queue_id} 3291 3292If successful, it will show:: 3293 3294 Queue #[...] pulled #[...] operations (#[...] failed, #[...] succeeded) 3295 3296The usual error message is shown when operations results cannot be pulled:: 3297 3298 Caught error type [...] ([...]): [...] 3299 3300Calculating hash 3301~~~~~~~~~~~~~~~~ 3302 3303``flow hash {port_id} template_table`` calculates the hash for a given pattern. 3304It is bound to ``rte_flow_calc_table_hash()``:: 3305 3306 flow hash {port_id} template_table {table_id} 3307 pattern_template {pattern_template_index} 3308 actions_template {actions_template_index} 3309 pattern {item} [/ {item} [...]] / end 3310 3311If successful, it will show the calculated hash result as seen below:: 3312 3313 Hash results 0x[...] 3314 3315Otherwise, it will show an error message of the form:: 3316 3317 Caught error type [...] ([...]): [...] 3318 3319This command uses the same pattern items as ``flow create``, 3320their format is described in `Creating flow rules`_. 3321 3322Simulate encap hash calculation 3323~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3324 3325``flow hash {port_id} encap`` adds hash query, that returns the hash value 3326that the HW will calculate when encapsulating a packet:: 3327 3328 flow hash {port_id} encap {target field} pattern {item} [/ {item} [...]] / end 3329 3330If successful, it will show:: 3331 3332 encap hash result #[...] 3333 3334The value will be shown as uint16_t without endian conversion. 3335 3336Otherwise it will show an error message of the form:: 3337 3338 Failed to calculate encap hash - [...] 3339 3340Creating a tunnel stub for offload 3341~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3342 3343``flow tunnel create`` setup a tunnel stub for tunnel offload flow rules:: 3344 3345 flow tunnel create {port_id} type {tunnel_type} 3346 3347If successful, it will return a tunnel stub ID usable with other commands:: 3348 3349 port [...]: flow tunnel #[...] type [...] 3350 3351Tunnel stub ID is relative to a port. 3352 3353Destroying tunnel offload stub 3354~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3355 3356``flow tunnel destroy`` destroy port tunnel stub:: 3357 3358 flow tunnel destroy {port_id} id {tunnel_id} 3359 3360Listing tunnel offload stubs 3361~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3362 3363``flow tunnel list`` list port tunnel offload stubs:: 3364 3365 flow tunnel list {port_id} 3366 3367Validating flow rules 3368~~~~~~~~~~~~~~~~~~~~~ 3369 3370``flow validate`` reports whether a flow rule would be accepted by the 3371underlying device in its current state but stops short of creating it. It is 3372bound to ``rte_flow_validate()``:: 3373 3374 flow validate {port_id} 3375 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 3376 pattern {item} [/ {item} [...]] / end 3377 actions {action} [/ {action} [...]] / end 3378 3379If successful, it will show:: 3380 3381 Flow rule validated 3382 3383Otherwise it will show an error message of the form:: 3384 3385 Caught error type [...] ([...]): [...] 3386 3387This command uses the same parameters as ``flow create``, their format is 3388described in `Creating flow rules`_. 3389 3390Check whether redirecting any Ethernet packet received on port 0 to RX queue 3391index 6 is supported:: 3392 3393 testpmd> flow validate 0 ingress pattern eth / end 3394 actions queue index 6 / end 3395 Flow rule validated 3396 testpmd> 3397 3398Port 0 does not support TCPv6 rules:: 3399 3400 testpmd> flow validate 0 ingress pattern eth / ipv6 / tcp / end 3401 actions drop / end 3402 Caught error type 9 (specific pattern item): Invalid argument 3403 testpmd> 3404 3405Creating flow rules 3406~~~~~~~~~~~~~~~~~~~ 3407 3408``flow create`` validates and creates the specified flow rule. It is bound 3409to ``rte_flow_create()``:: 3410 3411 flow create {port_id} 3412 [group {group_id}] [priority {level}] [ingress] [egress] [transfer] 3413 [tunnel_set {tunnel_id}] [tunnel_match {tunnel_id}] 3414 [user_id {user_id}] pattern {item} [/ {item} [...]] / end 3415 actions {action} [/ {action} [...]] / end 3416 3417If successful, it will return a flow rule ID usable with other commands:: 3418 3419 Flow rule #[...] created 3420 3421Or if ``user_id`` is provided:: 3422 3423 Flow rule #[...] created, user-id [...] 3424 3425Otherwise it will show an error message of the form:: 3426 3427 Caught error type [...] ([...]): [...] 3428 3429Parameters describe in the following order: 3430 3431- Attributes (*group*, *priority*, *ingress*, *egress*, *transfer* tokens). 3432- Tunnel offload specification (tunnel_set, tunnel_match) 3433- User identifier for the flow. 3434- A matching pattern, starting with the *pattern* token and terminated by an 3435 *end* pattern item. 3436- Actions, starting with the *actions* token and terminated by an *end* 3437 action. 3438 3439These translate directly to *rte_flow* objects provided as-is to the 3440underlying functions. 3441 3442The shortest valid definition only comprises mandatory tokens:: 3443 3444 testpmd> flow create 0 pattern end actions end 3445 3446Note that PMDs may refuse rules that essentially do nothing such as this 3447one. 3448 3449**All unspecified object values are automatically initialized to 0.** 3450 3451Enqueueing creation of flow rules 3452~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3453 3454``flow queue create`` adds creation operation of a flow rule to a queue. 3455It is bound to ``rte_flow_async_create()``:: 3456 3457 flow queue {port_id} create {queue_id} 3458 [postpone {boolean}] template_table {table_id} 3459 pattern_template {pattern_template_index} 3460 actions_template {actions_template_index} 3461 pattern {item} [/ {item} [...]] / end 3462 actions {action} [/ {action} [...]] / end 3463 3464If successful, it will return a flow rule ID usable with other commands:: 3465 3466 Flow rule #[...] creaion enqueued 3467 3468Otherwise it will show an error message of the form:: 3469 3470 Caught error type [...] ([...]): [...] 3471 3472This command uses the same pattern items and actions as ``flow create``, 3473their format is described in `Creating flow rules`_. 3474 3475``flow queue pull`` must be called to retrieve the operation status. 3476 3477Attributes 3478^^^^^^^^^^ 3479 3480These tokens affect flow rule attributes (``struct rte_flow_attr``) and are 3481specified before the ``pattern`` token. 3482 3483- ``group {group id}``: priority group. 3484- ``priority {level}``: priority level within group. 3485- ``ingress``: rule applies to ingress traffic. 3486- ``egress``: rule applies to egress traffic. 3487- ``transfer``: apply rule directly to endpoints found in pattern. 3488 3489Please note that use of ``transfer`` attribute requires that the flow and 3490its indirect components be managed via so-called ``transfer`` proxy port. 3491See `show flow transfer proxy port ID for the given port`_ for details. 3492 3493Each instance of an attribute specified several times overrides the previous 3494value as shown below (group 4 is used):: 3495 3496 testpmd> flow create 0 group 42 group 24 group 4 [...] 3497 3498Note that once enabled, ``ingress`` and ``egress`` cannot be disabled. 3499 3500While not specifying a direction is an error, some rules may allow both 3501simultaneously. 3502 3503Most rules affect RX therefore contain the ``ingress`` token:: 3504 3505 testpmd> flow create 0 ingress pattern [...] 3506 3507Tunnel offload 3508^^^^^^^^^^^^^^ 3509 3510Indicate tunnel offload rule type 3511 3512- ``tunnel_set {tunnel_id}``: mark rule as tunnel offload decap_set type. 3513- ``tunnel_match {tunnel_id}``: mark rule as tunnel offload match type. 3514 3515Matching pattern 3516^^^^^^^^^^^^^^^^ 3517 3518A matching pattern starts after the ``pattern`` token. It is made of pattern 3519items and is terminated by a mandatory ``end`` item. 3520 3521Items are named after their type (*RTE_FLOW_ITEM_TYPE_* from ``enum 3522rte_flow_item_type``). 3523 3524The ``/`` token is used as a separator between pattern items as shown 3525below:: 3526 3527 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end [...] 3528 3529Note that protocol items like these must be stacked from lowest to highest 3530layer to make sense. For instance, the following rule is either invalid or 3531unlikely to match any packet:: 3532 3533 testpmd> flow create 0 ingress pattern eth / udp / ipv4 / end [...] 3534 3535More information on these restrictions can be found in the *rte_flow* 3536documentation. 3537 3538Several items support additional specification structures, for example 3539``ipv4`` allows specifying source and destination addresses as follows:: 3540 3541 testpmd> flow create 0 ingress pattern eth / ipv4 src is 10.1.1.1 3542 dst is 10.2.0.0 / end [...] 3543 3544This rule matches all IPv4 traffic with the specified properties. 3545 3546In this example, ``src`` and ``dst`` are field names of the underlying 3547``struct rte_flow_item_ipv4`` object. All item properties can be specified 3548in a similar fashion. 3549 3550The ``is`` token means that the subsequent value must be matched exactly, 3551and assigns ``spec`` and ``mask`` fields in ``struct rte_flow_item`` 3552accordingly. Possible assignment tokens are: 3553 3554- ``is``: match value perfectly (with full bit-mask). 3555- ``spec``: match value according to configured bit-mask. 3556- ``last``: specify upper bound to establish a range. 3557- ``mask``: specify bit-mask with relevant bits set to one. 3558- ``prefix``: generate bit-mask with <prefix-length> most-significant bits set to one. 3559 3560These yield identical results:: 3561 3562 ipv4 src is 10.1.1.1 3563 3564:: 3565 3566 ipv4 src spec 10.1.1.1 src mask 255.255.255.255 3567 3568:: 3569 3570 ipv4 src spec 10.1.1.1 src prefix 32 3571 3572:: 3573 3574 ipv4 src is 10.1.1.1 src last 10.1.1.1 # range with a single value 3575 3576:: 3577 3578 ipv4 src is 10.1.1.1 src last 0 # 0 disables range 3579 3580Inclusive ranges can be defined with ``last``:: 3581 3582 ipv4 src is 10.1.1.1 src last 10.2.3.4 # 10.1.1.1 to 10.2.3.4 3583 3584Note that ``mask`` affects both ``spec`` and ``last``:: 3585 3586 ipv4 src is 10.1.1.1 src last 10.2.3.4 src mask 255.255.0.0 3587 # matches 10.1.0.0 to 10.2.255.255 3588 3589Properties can be modified multiple times:: 3590 3591 ipv4 src is 10.1.1.1 src is 10.1.2.3 src is 10.2.3.4 # matches 10.2.3.4 3592 3593:: 3594 3595 ipv4 src is 10.1.1.1 src prefix 24 src prefix 16 # matches 10.1.0.0/16 3596 3597Pattern items 3598^^^^^^^^^^^^^ 3599 3600This section lists supported pattern items and their attributes, if any. 3601 3602- ``end``: end list of pattern items. 3603 3604- ``void``: no-op pattern item. 3605 3606- ``invert``: perform actions when pattern does not match. 3607 3608- ``any``: match any protocol for the current layer. 3609 3610 - ``num {unsigned}``: number of layers covered. 3611 3612- ``port_id``: match traffic from/to a given DPDK port ID. 3613 3614 - ``id {unsigned}``: DPDK port ID. 3615 3616- ``mark``: match value set in previously matched flow rule using the mark action. 3617 3618 - ``id {unsigned}``: arbitrary integer value. 3619 3620- ``raw``: match an arbitrary byte string. 3621 3622 - ``relative {boolean}``: look for pattern after the previous item. 3623 - ``search {boolean}``: search pattern from offset (see also limit). 3624 - ``offset {integer}``: absolute or relative offset for pattern. 3625 - ``limit {unsigned}``: search area limit for start of pattern. 3626 - ``pattern {string}``: byte string to look for. 3627 - ``pattern_hex {string}``: byte string (provided in hexadecimal) to look for. 3628 3629- ``eth``: match Ethernet header. 3630 3631 - ``dst {MAC-48}``: destination MAC. 3632 - ``src {MAC-48}``: source MAC. 3633 - ``type {unsigned}``: EtherType or TPID. 3634 3635- ``vlan``: match 802.1Q/ad VLAN tag. 3636 3637 - ``tci {unsigned}``: tag control information. 3638 - ``pcp {unsigned}``: priority code point. 3639 - ``dei {unsigned}``: drop eligible indicator. 3640 - ``vid {unsigned}``: VLAN identifier. 3641 - ``inner_type {unsigned}``: inner EtherType or TPID. 3642 3643- ``ipv4``: match IPv4 header. 3644 3645 - ``version_ihl {unsigned}``: IPv4 version and IP header length. 3646 - ``tos {unsigned}``: type of service. 3647 - ``ttl {unsigned}``: time to live. 3648 - ``proto {unsigned}``: next protocol ID. 3649 - ``src {ipv4 address}``: source address. 3650 - ``dst {ipv4 address}``: destination address. 3651 3652- ``ipv6``: match IPv6 header. 3653 3654 - ``tc {unsigned}``: traffic class. 3655 - ``flow {unsigned}``: flow label. 3656 - ``proto {unsigned}``: protocol (next header). 3657 - ``hop {unsigned}``: hop limit. 3658 - ``src {ipv6 address}``: source address. 3659 - ``dst {ipv6 address}``: destination address. 3660 3661- ``icmp``: match ICMP header. 3662 3663 - ``type {unsigned}``: ICMP packet type. 3664 - ``code {unsigned}``: ICMP packet code. 3665 3666- ``udp``: match UDP header. 3667 3668 - ``src {unsigned}``: UDP source port. 3669 - ``dst {unsigned}``: UDP destination port. 3670 3671- ``tcp``: match TCP header. 3672 3673 - ``src {unsigned}``: TCP source port. 3674 - ``dst {unsigned}``: TCP destination port. 3675 3676- ``sctp``: match SCTP header. 3677 3678 - ``src {unsigned}``: SCTP source port. 3679 - ``dst {unsigned}``: SCTP destination port. 3680 - ``tag {unsigned}``: validation tag. 3681 - ``cksum {unsigned}``: checksum. 3682 3683- ``vxlan``: match VXLAN header. 3684 3685 - ``vni {unsigned}``: VXLAN identifier. 3686 - ``flag_g {unsigned}``: VXLAN flag GBP bit. 3687 - ``flag_ver {unsigned}``: VXLAN flag GPE version. 3688 - ``flag_i {unsigned}``: VXLAN flag Instance bit. 3689 - ``flag_p {unsigned}``: VXLAN flag GPE Next Protocol bit. 3690 - ``flag_b {unsigned}``: VXLAN flag GPE Ingress-Replicated BUM. 3691 - ``flag_o {unsigned}``: VXLAN flag GPE OAM Packet bit. 3692 - ``flag_d {unsigned}``: VXLAN flag GBP Don't Learn bit. 3693 - ``flag_a {unsigned}``: VXLAN flag GBP Applied bit. 3694 - ``group_policy_id {unsigned}``: VXLAN GBP Group Policy ID. 3695 - ``protocol {unsigned}`` : VXLAN GPE next protocol. 3696 - ``first_rsvd {unsigned}`` : VXLAN rsvd0 first byte. 3697 - ``secnd_rsvd {unsigned}`` : VXLAN rsvd0 second byte. 3698 - ``third_rsvd {unsigned}`` : VXLAN rsvd0 third byte. 3699 - ``last_rsvd {unsigned}``: VXLAN last reserved byte. 3700 3701- ``e_tag``: match IEEE 802.1BR E-Tag header. 3702 3703 - ``grp_ecid_b {unsigned}``: GRP and E-CID base. 3704 3705- ``nvgre``: match NVGRE header. 3706 3707 - ``tni {unsigned}``: virtual subnet ID. 3708 3709- ``mpls``: match MPLS header. 3710 3711 - ``label {unsigned}``: MPLS label. 3712 3713- ``gre``: match GRE header. 3714 3715 - ``protocol {unsigned}``: protocol type. 3716 3717- ``gre_key``: match GRE optional key field. 3718 3719 - ``value {unsigned}``: key value. 3720 3721- ``gre_option``: match GRE optional fields(checksum/key/sequence). 3722 3723 - ``checksum {unsigned}``: checksum value. 3724 - ``key {unsigned}``: key value. 3725 - ``sequence {unsigned}``: sequence number value. 3726 3727- ``fuzzy``: fuzzy pattern match, expect faster than default. 3728 3729 - ``thresh {unsigned}``: accuracy threshold. 3730 3731- ``gtp``, ``gtpc``, ``gtpu``: match GTPv1 header. 3732 3733 - ``teid {unsigned}``: tunnel endpoint identifier. 3734 3735- ``geneve``: match GENEVE header. 3736 3737 - ``vni {unsigned}``: virtual network identifier. 3738 - ``protocol {unsigned}``: protocol type. 3739 3740- ``geneve-opt``: match GENEVE header option. 3741 3742 - ``class {unsigned}``: GENEVE option class. 3743 - ``type {unsigned}``: GENEVE option type. 3744 - ``length {unsigned}``: GENEVE option length in 32-bit words. 3745 - ``data {hex string}``: GENEVE option data, the length is defined by 3746 ``length`` field. 3747 3748- ``arp_eth_ipv4``: match ARP header for Ethernet/IPv4. 3749 3750 - ``sha {MAC-48}``: sender hardware address. 3751 - ``spa {ipv4 address}``: sender IPv4 address. 3752 - ``tha {MAC-48}``: target hardware address. 3753 - ``tpa {ipv4 address}``: target IPv4 address. 3754 3755- ``ipv6_ext``: match presence of any IPv6 extension header. 3756 3757 - ``next_hdr {unsigned}``: next header. 3758 3759- ``icmp6``: match any ICMPv6 header. 3760 3761 - ``type {unsigned}``: ICMPv6 type. 3762 - ``code {unsigned}``: ICMPv6 code. 3763 3764- ``icmp6_echo_request``: match ICMPv6 echo request. 3765 3766 - ``ident {unsigned}``: ICMPv6 echo request identifier. 3767 - ``seq {unsigned}``: ICMPv6 echo request sequence number. 3768 3769- ``icmp6_echo_reply``: match ICMPv6 echo reply. 3770 3771 - ``ident {unsigned}``: ICMPv6 echo reply identifier. 3772 - ``seq {unsigned}``: ICMPv6 echo reply sequence number. 3773 3774- ``icmp6_nd_ns``: match ICMPv6 neighbor discovery solicitation. 3775 3776 - ``target_addr {ipv6 address}``: target address. 3777 3778- ``icmp6_nd_na``: match ICMPv6 neighbor discovery advertisement. 3779 3780 - ``target_addr {ipv6 address}``: target address. 3781 3782- ``icmp6_nd_opt``: match presence of any ICMPv6 neighbor discovery option. 3783 3784 - ``type {unsigned}``: ND option type. 3785 3786- ``icmp6_nd_opt_sla_eth``: match ICMPv6 neighbor discovery source Ethernet 3787 link-layer address option. 3788 3789 - ``sla {MAC-48}``: source Ethernet LLA. 3790 3791- ``icmp6_nd_opt_tla_eth``: match ICMPv6 neighbor discovery target Ethernet 3792 link-layer address option. 3793 3794 - ``tla {MAC-48}``: target Ethernet LLA. 3795 3796- ``meta``: match application specific metadata. 3797 3798 - ``data {unsigned}``: metadata value. 3799 3800- ``random``: match application specific random value. 3801 3802 - ``value {unsigned}``: random value. 3803 3804- ``gtp_psc``: match GTP PDU extension header with type 0x85. 3805 3806 - ``pdu_type {unsigned}``: PDU type. 3807 3808 - ``qfi {unsigned}``: QoS flow identifier. 3809 3810- ``pppoes``, ``pppoed``: match PPPoE header. 3811 3812 - ``session_id {unsigned}``: session identifier. 3813 3814- ``pppoe_proto_id``: match PPPoE session protocol identifier. 3815 3816 - ``proto_id {unsigned}``: PPP protocol identifier. 3817 3818- ``l2tpv3oip``: match L2TPv3 over IP header. 3819 3820 - ``session_id {unsigned}``: L2TPv3 over IP session identifier. 3821 3822- ``ah``: match AH header. 3823 3824 - ``spi {unsigned}``: security parameters index. 3825 3826- ``pfcp``: match PFCP header. 3827 3828 - ``s_field {unsigned}``: S field. 3829 - ``seid {unsigned}``: session endpoint identifier. 3830 3831- ``integrity``: match packet integrity. 3832 3833 - ``level {unsigned}``: Packet encapsulation level the item should 3834 apply to. See rte_flow_action_rss for details. 3835 - ``value {unsigned}``: A bitmask that specify what packet elements 3836 must be matched for integrity. 3837 3838- ``conntrack``: match conntrack state. 3839 3840- ``port_representor``: match traffic entering the embedded switch from the given ethdev 3841 3842 - ``port_id {unsigned}``: ethdev port ID 3843 3844- ``represented_port``: match traffic entering the embedded switch from 3845 the entity represented by the given ethdev 3846 3847 - ``ethdev_port_id {unsigned}``: ethdev port ID 3848 3849- ``l2tpv2``: match L2TPv2 header. 3850 3851 - ``length {unsigned}``: L2TPv2 option length. 3852 - ``tunnel_id {unsigned}``: L2TPv2 tunnel identifier. 3853 - ``session_id {unsigned}``: L2TPv2 session identifier. 3854 - ``ns {unsigned}``: L2TPv2 option ns. 3855 - ``nr {unsigned}``: L2TPv2 option nr. 3856 - ``offset_size {unsigned}``: L2TPv2 option offset. 3857 3858- ``ppp``: match PPP header. 3859 3860 - ``addr {unsigned}``: PPP address. 3861 - ``ctrl {unsigned}``: PPP control. 3862 - ``proto_id {unsigned}``: PPP protocol identifier. 3863 3864- ``ib_bth``: match InfiniBand BTH(base transport header). 3865 3866 - ``opcode {unsigned}``: Opcode. 3867 - ``pkey {unsigned}``: Partition key. 3868 - ``dst_qp {unsigned}``: Destination Queue Pair. 3869 - ``psn {unsigned}``: Packet Sequence Number. 3870 3871- ``meter``: match meter color. 3872 3873 - ``color {value}``: meter color value (green/yellow/red). 3874 3875- ``aggr_affinity``: match aggregated port. 3876 3877 - ``affinity {value}``: aggregated port (starts from 1). 3878 3879- ``tx_queue``: match Tx queue of sent packet. 3880 3881 - ``tx_queue {value}``: send queue value (starts from 0). 3882 3883- ``send_to_kernel``: send packets to kernel. 3884 3885- ``ptype``: match the packet type (L2/L3/L4 and tunnel information). 3886 3887 - ``packet_type {unsigned}``: packet type. 3888 3889- ``compare``: match the comparison result between packet fields or value. 3890 3891 - ``op {string}``: comparison operation type. 3892 - ``a_type {string}``: compared field. 3893 - ``b_type {string}``: comparator field. 3894 - ``width {unsigned}``: comparison width. 3895 3896 3897Actions list 3898^^^^^^^^^^^^ 3899 3900A list of actions starts after the ``actions`` token in the same fashion as 3901`Matching pattern`_; actions are separated by ``/`` tokens and the list is 3902terminated by a mandatory ``end`` action. 3903 3904Actions are named after their type (*RTE_FLOW_ACTION_TYPE_* from ``enum 3905rte_flow_action_type``). 3906 3907Dropping all incoming UDPv4 packets can be expressed as follows:: 3908 3909 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end 3910 actions drop / end 3911 3912Several actions have configurable properties which must be specified when 3913there is no valid default value. For example, ``queue`` requires a target 3914queue index. 3915 3916This rule redirects incoming UDPv4 traffic to queue index 6:: 3917 3918 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end 3919 actions queue index 6 / end 3920 3921While this one could be rejected by PMDs (unspecified queue index):: 3922 3923 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end 3924 actions queue / end 3925 3926As defined by *rte_flow*, the list is not ordered, all actions of a given 3927rule are performed simultaneously. These are equivalent:: 3928 3929 queue index 6 / void / mark id 42 / end 3930 3931:: 3932 3933 void / mark id 42 / queue index 6 / end 3934 3935All actions in a list should have different types, otherwise only the last 3936action of a given type is taken into account:: 3937 3938 queue index 4 / queue index 5 / queue index 6 / end # will use queue 6 3939 3940:: 3941 3942 drop / drop / drop / end # drop is performed only once 3943 3944:: 3945 3946 mark id 42 / queue index 3 / mark id 24 / end # mark will be 24 3947 3948Considering they are performed simultaneously, opposite and overlapping 3949actions can sometimes be combined when the end result is unambiguous:: 3950 3951 drop / queue index 6 / end # drop has no effect 3952 3953:: 3954 3955 queue index 6 / rss queues 6 7 8 / end # queue has no effect 3956 3957:: 3958 3959 drop / passthru / end # drop has no effect 3960 3961Note that PMDs may still refuse such combinations. 3962 3963Actions 3964^^^^^^^ 3965 3966This section lists supported actions and their attributes, if any. 3967 3968- ``end``: end list of actions. 3969 3970- ``void``: no-op action. 3971 3972- ``passthru``: let subsequent rule process matched packets. 3973 3974- ``jump``: redirect traffic to group on device. 3975 3976 - ``group {unsigned}``: group to redirect to. 3977 3978- ``mark``: attach 32 bit value to packets. 3979 3980 - ``id {unsigned}``: 32 bit value to return with packets. 3981 3982- ``flag``: flag packets. 3983 3984- ``queue``: assign packets to a given queue index. 3985 3986 - ``index {unsigned}``: queue index to use. 3987 3988- ``drop``: drop packets (note: passthru has priority). 3989 3990- ``count``: enable counters for this rule. 3991 3992- ``rss``: spread packets among several queues. 3993 3994 - ``func {hash function}``: RSS hash function to apply, allowed tokens are 3995 ``toeplitz``, ``simple_xor``, ``symmetric_toeplitz`` and ``default``. 3996 3997 - ``level {unsigned}``: encapsulation level for ``types``. 3998 3999 - ``types [{RSS hash type} [...]] end``: specific RSS hash types. 4000 Note that an empty list does not disable RSS but instead requests 4001 unspecified "best-effort" settings. 4002 4003 - ``key {string}``: RSS hash key, overrides ``key_len``. 4004 4005 - ``key_len {unsigned}``: RSS hash key length in bytes, can be used in 4006 conjunction with ``key`` to pad or truncate it. 4007 4008 - ``queues [{unsigned} [...]] end``: queue indices to use. 4009 4010- ``pf``: direct traffic to physical function. 4011 4012- ``vf``: direct traffic to a virtual function ID. 4013 4014 - ``original {boolean}``: use original VF ID if possible. 4015 - ``id {unsigned}``: VF ID. 4016 4017- ``port_id``: direct matching traffic to a given DPDK port ID. 4018 4019 - ``original {boolean}``: use original DPDK port ID if possible. 4020 - ``id {unsigned}``: DPDK port ID. 4021 4022- ``of_set_mpls_ttl``: OpenFlow's ``OFPAT_SET_MPLS_TTL``. 4023 4024 - ``mpls_ttl``: MPLS TTL. 4025 4026- ``of_dec_mpls_ttl``: OpenFlow's ``OFPAT_DEC_MPLS_TTL``. 4027 4028- ``of_set_nw_ttl``: OpenFlow's ``OFPAT_SET_NW_TTL``. 4029 4030 - ``nw_ttl``: IP TTL. 4031 4032- ``of_dec_nw_ttl``: OpenFlow's ``OFPAT_DEC_NW_TTL``. 4033 4034- ``of_copy_ttl_out``: OpenFlow's ``OFPAT_COPY_TTL_OUT``. 4035 4036- ``of_copy_ttl_in``: OpenFlow's ``OFPAT_COPY_TTL_IN``. 4037 4038- ``of_pop_vlan``: OpenFlow's ``OFPAT_POP_VLAN``. 4039 4040- ``of_push_vlan``: OpenFlow's ``OFPAT_PUSH_VLAN``. 4041 4042 - ``ethertype``: Ethertype. 4043 4044- ``of_set_vlan_vid``: OpenFlow's ``OFPAT_SET_VLAN_VID``. 4045 4046 - ``vlan_vid``: VLAN id. 4047 4048- ``of_set_vlan_pcp``: OpenFlow's ``OFPAT_SET_VLAN_PCP``. 4049 4050 - ``vlan_pcp``: VLAN priority. 4051 4052- ``of_pop_mpls``: OpenFlow's ``OFPAT_POP_MPLS``. 4053 4054 - ``ethertype``: Ethertype. 4055 4056- ``of_push_mpls``: OpenFlow's ``OFPAT_PUSH_MPLS``. 4057 4058 - ``ethertype``: Ethertype. 4059 4060- ``vxlan_encap``: Performs a VXLAN encapsulation, outer layer configuration 4061 is done through `Config VXLAN Encap outer layers`_. 4062 4063- ``vxlan_decap``: Performs a decapsulation action by stripping all headers of 4064 the VXLAN tunnel network overlay from the matched flow. 4065 4066- ``nvgre_encap``: Performs a NVGRE encapsulation, outer layer configuration 4067 is done through `Config NVGRE Encap outer layers`_. 4068 4069- ``nvgre_decap``: Performs a decapsulation action by stripping all headers of 4070 the NVGRE tunnel network overlay from the matched flow. 4071 4072- ``l2_encap``: Performs a L2 encapsulation, L2 configuration 4073 is done through `Config L2 Encap`_. 4074 4075- ``l2_decap``: Performs a L2 decapsulation, L2 configuration 4076 is done through `Config L2 Decap`_. 4077 4078- ``mplsogre_encap``: Performs a MPLSoGRE encapsulation, outer layer 4079 configuration is done through `Config MPLSoGRE Encap outer layers`_. 4080 4081- ``mplsogre_decap``: Performs a MPLSoGRE decapsulation, outer layer 4082 configuration is done through `Config MPLSoGRE Decap outer layers`_. 4083 4084- ``mplsoudp_encap``: Performs a MPLSoUDP encapsulation, outer layer 4085 configuration is done through `Config MPLSoUDP Encap outer layers`_. 4086 4087- ``mplsoudp_decap``: Performs a MPLSoUDP decapsulation, outer layer 4088 configuration is done through `Config MPLSoUDP Decap outer layers`_. 4089 4090- ``set_ipv4_src``: Set a new IPv4 source address in the outermost IPv4 header. 4091 4092 - ``ipv4_addr``: New IPv4 source address. 4093 4094- ``set_ipv4_dst``: Set a new IPv4 destination address in the outermost IPv4 4095 header. 4096 4097 - ``ipv4_addr``: New IPv4 destination address. 4098 4099- ``set_ipv6_src``: Set a new IPv6 source address in the outermost IPv6 header. 4100 4101 - ``ipv6_addr``: New IPv6 source address. 4102 4103- ``set_ipv6_dst``: Set a new IPv6 destination address in the outermost IPv6 4104 header. 4105 4106 - ``ipv6_addr``: New IPv6 destination address. 4107 4108- ``set_tp_src``: Set a new source port number in the outermost TCP/UDP 4109 header. 4110 4111 - ``port``: New TCP/UDP source port number. 4112 4113- ``set_tp_dst``: Set a new destination port number in the outermost TCP/UDP 4114 header. 4115 4116 - ``port``: New TCP/UDP destination port number. 4117 4118- ``mac_swap``: Swap the source and destination MAC addresses in the outermost 4119 Ethernet header. 4120 4121- ``dec_ttl``: Performs a decrease TTL value action 4122 4123- ``set_ttl``: Set TTL value with specified value 4124 - ``ttl_value {unsigned}``: The new TTL value to be set 4125 4126- ``set_mac_src``: set source MAC address 4127 4128 - ``mac_addr {MAC-48}``: new source MAC address 4129 4130- ``set_mac_dst``: set destination MAC address 4131 4132 - ``mac_addr {MAC-48}``: new destination MAC address 4133 4134- ``inc_tcp_seq``: Increase sequence number in the outermost TCP header. 4135 4136 - ``value {unsigned}``: Value to increase TCP sequence number by. 4137 4138- ``dec_tcp_seq``: Decrease sequence number in the outermost TCP header. 4139 4140 - ``value {unsigned}``: Value to decrease TCP sequence number by. 4141 4142- ``inc_tcp_ack``: Increase acknowledgment number in the outermost TCP header. 4143 4144 - ``value {unsigned}``: Value to increase TCP acknowledgment number by. 4145 4146- ``dec_tcp_ack``: Decrease acknowledgment number in the outermost TCP header. 4147 4148 - ``value {unsigned}``: Value to decrease TCP acknowledgment number by. 4149 4150- ``set_ipv4_dscp``: Set IPv4 DSCP value with specified value 4151 4152 - ``dscp_value {unsigned}``: The new DSCP value to be set 4153 4154- ``set_ipv6_dscp``: Set IPv6 DSCP value with specified value 4155 4156 - ``dscp_value {unsigned}``: The new DSCP value to be set 4157 4158- ``indirect``: Use indirect action created via 4159 ``flow indirect_action {port_id} create`` 4160 4161 - ``indirect_action_id {unsigned}``: Indirect action ID to use 4162 4163- ``color``: Color the packet to reflect the meter color result 4164 4165 - ``type {value}``: Set color type with specified value(green/yellow/red) 4166 4167- ``port_representor``: at embedded switch level, send matching traffic to 4168 the given ethdev 4169 4170 - ``port_id {unsigned}``: ethdev port ID 4171 4172- ``represented_port``: at embedded switch level, send matching traffic to 4173 the entity represented by the given ethdev 4174 4175 - ``ethdev_port_id {unsigned}``: ethdev port ID 4176 4177- ``meter_mark``: meter the directed packets using profile and policy 4178 4179 - ``mtr_profile {unsigned}``: meter profile ID to use 4180 - ``mtr_policy {unsigned}``: meter policy ID to use 4181 - ``mtr_color_mode {unsigned}``: meter color-awareness mode (blind/aware) 4182 - ``mtr_init_color {value}``: initial color value (green/yellow/red) 4183 - ``mtr_state {unsigned}``: meter state (disabled/enabled) 4184 4185- ``modify_field``: Modify packet field 4186 4187 - ``op``: modify operation (set/add/sub) 4188 - ``dst_type``: the destination field to be modified, the supported fields as 4189 ``enum rte_flow_field_id`` listed. 4190 - ``dst_level``: destination field level. 4191 - ``dst_tag_index``: destination field tag array. 4192 - ``dst_type_id``: destination field type ID. 4193 - ``dst_class``: destination field class ID. 4194 - ``dst_offset``: destination field bit offset. 4195 - ``src_type``: the modify source field, the supported fields as 4196 ``enum rte_flow_field_id`` listed. 4197 - ``src_level``: source field level. 4198 - ``src_tag_index``: source field tag array. 4199 - ``src_type_id``: source field type ID. 4200 - ``src_class``: source field class ID. 4201 - ``src_offset``: source field bit offset. 4202 - ``src_value``: source immediate value. 4203 - ``src_ptr``: pointer to source immediate value. 4204 - ``width``: number of bits to copy. 4205 4206- ``nat64``: NAT64 IP headers translation 4207 4208 - ``type {unsigned}``: NAT64 translation type 4209 4210Destroying flow rules 4211~~~~~~~~~~~~~~~~~~~~~ 4212 4213``flow destroy`` destroys one or more rules from their rule ID (as returned 4214by ``flow create``), this command calls ``rte_flow_destroy()`` as many 4215times as necessary:: 4216 4217 flow destroy {port_id} rule {rule_id} [...] [user_id] 4218 4219If successful, it will show:: 4220 4221 Flow rule #[...] destroyed 4222 4223Or if ``user_id`` flag is provided:: 4224 4225 Flow rule #[...] destroyed, user-id [...] 4226 4227Optional ``user_id`` is a flag that signifies the rule ID 4228is the one provided by the user at creation. 4229It does not report anything for rule IDs that do not exist. The usual error 4230message is shown when a rule cannot be destroyed:: 4231 4232 Caught error type [...] ([...]): [...] 4233 4234``flow flush`` destroys all rules on a device and does not take extra 4235arguments. It is bound to ``rte_flow_flush()``:: 4236 4237 flow flush {port_id} 4238 4239Any errors are reported as above. 4240 4241Creating several rules and destroying them:: 4242 4243 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4244 actions queue index 2 / end 4245 Flow rule #0 created 4246 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4247 actions queue index 3 / end 4248 Flow rule #1 created 4249 testpmd> flow destroy 0 rule 0 rule 1 4250 Flow rule #1 destroyed 4251 Flow rule #0 destroyed 4252 testpmd> 4253 4254The same result can be achieved using ``flow flush``:: 4255 4256 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4257 actions queue index 2 / end 4258 Flow rule #0 created 4259 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4260 actions queue index 3 / end 4261 Flow rule #1 created 4262 testpmd> flow flush 0 4263 testpmd> 4264 4265Non-existent rule IDs are ignored:: 4266 4267 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4268 actions queue index 2 / end 4269 Flow rule #0 created 4270 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4271 actions queue index 3 / end 4272 Flow rule #1 created 4273 testpmd> flow destroy 0 rule 42 rule 10 rule 2 4274 testpmd> 4275 testpmd> flow destroy 0 rule 0 4276 Flow rule #0 destroyed 4277 testpmd> 4278 4279Updating flow rules with new actions 4280~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4281 4282``flow update`` updates a flow rule specified by a rule ID with a new action 4283list by making a call to ``rte_flow_actions_update()``:: 4284 4285 flow update {port_id} {rule_id} 4286 actions {action} [/ {action} [...]] / end [user_id] 4287 4288If successful, it will show:: 4289 4290 Flow rule #[...] updated with new actions 4291 4292Or if ``user_id`` flag is provided:: 4293 4294 Flow rule #[...] updated with new actions, user-id [...] 4295 4296If a flow rule can not be found:: 4297 4298 Failed to find flow [...] 4299 4300Otherwise it will show the usual error message of the form:: 4301 4302 Caught error type [...] ([...]): [...] 4303 4304Optional ``user_id`` is a flag that signifies the rule ID is the one provided 4305by the user at creation. 4306 4307Action list is identical to the one described for the ``flow create``. 4308 4309Creating, updating and destroying a flow rule:: 4310 4311 testpmd> flow create 0 group 1 pattern eth / end actions drop / end 4312 Flow rule #0 created 4313 testpmd> flow update 0 0 actions queue index 1 / end 4314 Flow rule #0 updated with new actions 4315 testpmd> flow destroy 0 rule 0 4316 Flow rule #0 destroyed 4317 4318Enqueueing destruction of flow rules 4319~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4320 4321``flow queue destroy`` adds destruction operations to destroy one or more rules 4322from their rule ID (as returned by ``flow queue create``) to a queue, 4323this command calls ``rte_flow_async_destroy()`` as many times as necessary:: 4324 4325 flow queue {port_id} destroy {queue_id} 4326 [postpone {boolean}] rule {rule_id} [...] 4327 4328If successful, it will show:: 4329 4330 Flow rule #[...] destruction enqueued 4331 4332It does not report anything for rule IDs that do not exist. The usual error 4333message is shown when a rule cannot be destroyed:: 4334 4335 Caught error type [...] ([...]): [...] 4336 4337``flow queue pull`` must be called to retrieve the operation status. 4338 4339Querying flow rules 4340~~~~~~~~~~~~~~~~~~~ 4341 4342``flow query`` queries a specific action of a flow rule having that 4343ability. Such actions collect information that can be reported using this 4344command. It is bound to ``rte_flow_query()``:: 4345 4346 flow query {port_id} {rule_id} {action} [user_id] 4347 4348Optional ``user_id`` is a flag that signifies the rule ID 4349is the one provided by the user at creation. 4350If successful, it will display either the retrieved data for known actions 4351or the following message:: 4352 4353 Cannot display result for action type [...] ([...]) 4354 4355Otherwise, it will complain either that the rule does not exist or that some 4356error occurred:: 4357 4358 Flow rule #[...] not found 4359 4360:: 4361 4362 Caught error type [...] ([...]): [...] 4363 4364Currently only the ``count`` action is supported. This action reports the 4365number of packets that hit the flow rule and the total number of bytes. Its 4366output has the following format:: 4367 4368 count: 4369 hits_set: [...] # whether "hits" contains a valid value 4370 bytes_set: [...] # whether "bytes" contains a valid value 4371 hits: [...] # number of packets 4372 bytes: [...] # number of bytes 4373 4374Querying counters for TCPv6 packets redirected to queue 6:: 4375 4376 testpmd> flow create 0 ingress pattern eth / ipv6 / tcp / end 4377 actions queue index 6 / count / end 4378 Flow rule #4 created 4379 testpmd> flow query 0 4 count 4380 count: 4381 hits_set: 1 4382 bytes_set: 0 4383 hits: 386446 4384 bytes: 0 4385 testpmd> 4386 4387Listing flow rules 4388~~~~~~~~~~~~~~~~~~ 4389 4390``flow list`` lists existing flow rules sorted by priority and optionally 4391filtered by group identifiers:: 4392 4393 flow list {port_id} [group {group_id}] [...] 4394 4395This command only fails with the following message if the device does not 4396exist:: 4397 4398 Invalid port [...] 4399 4400Output consists of a header line followed by a short description of each 4401flow rule, one per line. There is no output at all when no flow rules are 4402configured on the device:: 4403 4404 ID Group Prio Attr Rule 4405 [...] [...] [...] [...] [...] 4406 4407``Attr`` column flags: 4408 4409- ``i`` for ``ingress``. 4410- ``e`` for ``egress``. 4411 4412Creating several flow rules and listing them:: 4413 4414 testpmd> flow create 0 ingress pattern eth / ipv4 / end 4415 actions queue index 6 / end 4416 Flow rule #0 created 4417 testpmd> flow create 0 ingress pattern eth / ipv6 / end 4418 actions queue index 2 / end 4419 Flow rule #1 created 4420 testpmd> flow create 0 priority 5 ingress pattern eth / ipv4 / udp / end 4421 actions rss queues 6 7 8 end / end 4422 Flow rule #2 created 4423 testpmd> flow list 0 4424 ID Group Prio Attr Rule 4425 0 0 0 i- ETH IPV4 => QUEUE 4426 1 0 0 i- ETH IPV6 => QUEUE 4427 2 0 5 i- ETH IPV4 UDP => RSS 4428 testpmd> 4429 4430Rules are sorted by priority (i.e. group ID first, then priority level):: 4431 4432 testpmd> flow list 1 4433 ID Group Prio Attr Rule 4434 0 0 0 i- ETH => COUNT 4435 6 0 500 i- ETH IPV6 TCP => DROP COUNT 4436 5 0 1000 i- ETH IPV6 ICMP => QUEUE 4437 1 24 0 i- ETH IPV4 UDP => QUEUE 4438 4 24 10 i- ETH IPV4 TCP => DROP 4439 3 24 20 i- ETH IPV4 => DROP 4440 2 24 42 i- ETH IPV4 UDP => QUEUE 4441 7 63 0 i- ETH IPV6 UDP VXLAN => MARK QUEUE 4442 testpmd> 4443 4444Output can be limited to specific groups:: 4445 4446 testpmd> flow list 1 group 0 group 63 4447 ID Group Prio Attr Rule 4448 0 0 0 i- ETH => COUNT 4449 6 0 500 i- ETH IPV6 TCP => DROP COUNT 4450 5 0 1000 i- ETH IPV6 ICMP => QUEUE 4451 7 63 0 i- ETH IPV6 UDP VXLAN => MARK QUEUE 4452 testpmd> 4453 4454Toggling isolated mode 4455~~~~~~~~~~~~~~~~~~~~~~ 4456 4457``flow isolate`` can be used to tell the underlying PMD that ingress traffic 4458must only be injected from the defined flow rules; that no default traffic 4459is expected outside those rules and the driver is free to assign more 4460resources to handle them. It is bound to ``rte_flow_isolate()``:: 4461 4462 flow isolate {port_id} {boolean} 4463 4464If successful, enabling or disabling isolated mode shows either:: 4465 4466 Ingress traffic on port [...] 4467 is now restricted to the defined flow rules 4468 4469Or:: 4470 4471 Ingress traffic on port [...] 4472 is not restricted anymore to the defined flow rules 4473 4474Otherwise, in case of error:: 4475 4476 Caught error type [...] ([...]): [...] 4477 4478Mainly due to its side effects, PMDs supporting this mode may not have the 4479ability to toggle it more than once without reinitializing affected ports 4480first (e.g. by exiting testpmd). 4481 4482Enabling isolated mode:: 4483 4484 testpmd> flow isolate 0 true 4485 Ingress traffic on port 0 is now restricted to the defined flow rules 4486 testpmd> 4487 4488Disabling isolated mode:: 4489 4490 testpmd> flow isolate 0 false 4491 Ingress traffic on port 0 is not restricted anymore to the defined flow rules 4492 testpmd> 4493 4494Dumping HW internal information 4495~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4496 4497``flow dump`` dumps the hardware's internal representation information of 4498all flows. It is bound to ``rte_flow_dev_dump()``:: 4499 4500 flow dump {port_id} {output_file} [user_id] 4501 4502If successful, it will show:: 4503 4504 Flow dump finished 4505 4506Otherwise, it will complain error occurred:: 4507 4508 Caught error type [...] ([...]): [...] 4509 4510Optional ``user_id`` is a flag that signifies the rule ID 4511is the one provided by the user at creation. 4512 4513Listing and destroying aged flow rules 4514~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4515 4516``flow aged`` simply lists aged flow rules be get from api ``rte_flow_get_aged_flows``, 4517and ``destroy`` parameter can be used to destroy those flow rules in PMD:: 4518 4519 flow aged {port_id} [destroy] 4520 4521Listing current aged flow rules:: 4522 4523 testpmd> flow aged 0 4524 Port 0 total aged flows: 0 4525 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.14 / end 4526 actions age timeout 5 / queue index 0 / end 4527 Flow rule #0 created 4528 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.15 / end 4529 actions age timeout 4 / queue index 0 / end 4530 Flow rule #1 created 4531 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.16 / end 4532 actions age timeout 2 / queue index 0 / end 4533 Flow rule #2 created 4534 testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.17 / end 4535 actions age timeout 3 / queue index 0 / end 4536 Flow rule #3 created 4537 4538 4539Aged Rules are simply list as command ``flow list {port_id}``, but strip the detail rule 4540information, all the aged flows are sorted by the longest timeout time. For example, if 4541those rules be configured in the same time, ID 2 will be the first aged out rule, the next 4542will be ID 3, ID 1, ID 0:: 4543 4544 testpmd> flow aged 0 4545 Port 0 total aged flows: 4 4546 ID Group Prio Attr 4547 2 0 0 i-- 4548 3 0 0 i-- 4549 1 0 0 i-- 4550 0 0 0 i-- 4551 4552If attach ``destroy`` parameter, the command will destroy all the list aged flow rules:: 4553 4554 testpmd> flow aged 0 destroy 4555 Port 0 total aged flows: 4 4556 ID Group Prio Attr 4557 2 0 0 i-- 4558 3 0 0 i-- 4559 1 0 0 i-- 4560 0 0 0 i-- 4561 4562 Flow rule #2 destroyed 4563 Flow rule #3 destroyed 4564 Flow rule #1 destroyed 4565 Flow rule #0 destroyed 4566 4 flows be destroyed 4567 testpmd> flow aged 0 4568 Port 0 total aged flows: 0 4569 4570 4571Enqueueing listing and destroying aged flow rules 4572~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4573 4574``flow queue aged`` simply lists aged flow rules be get from 4575``rte_flow_get_q_aged_flows`` API, and ``destroy`` parameter can be used to 4576destroy those flow rules in PMD:: 4577 4578 flow queue {port_id} aged {queue_id} [destroy] 4579 4580Listing current aged flow rules:: 4581 4582 testpmd> flow queue 0 aged 0 4583 Port 0 queue 0 total aged flows: 0 4584 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4585 pattern eth / ipv4 src is 2.2.2.14 / end 4586 actions age timeout 5 / queue index 0 / end 4587 Flow rule #0 creation enqueued 4588 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4589 pattern eth / ipv4 src is 2.2.2.15 / end 4590 actions age timeout 4 / queue index 0 / end 4591 Flow rule #1 creation enqueued 4592 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4593 pattern eth / ipv4 src is 2.2.2.16 / end 4594 actions age timeout 4 / queue index 0 / end 4595 Flow rule #2 creation enqueued 4596 testpmd> flow queue 0 create 0 ingress tanle 0 item_template 0 action_template 0 4597 pattern eth / ipv4 src is 2.2.2.17 / end 4598 actions age timeout 4 / queue index 0 / end 4599 Flow rule #3 creation enqueued 4600 testpmd> flow pull 0 queue 0 4601 Queue #0 pulled 4 operations (0 failed, 4 succeeded) 4602 4603Aged Rules are simply list as command ``flow queue {port_id} list {queue_id}``, 4604but strip the detail rule information, all the aged flows are sorted by the 4605longest timeout time. For example, if those rules is configured in the same time, 4606ID 2 will be the first aged out rule, the next will be ID 3, ID 1, ID 0:: 4607 4608 testpmd> flow queue 0 aged 0 4609 Port 0 queue 0 total aged flows: 4 4610 ID Group Prio Attr 4611 2 0 0 --- 4612 3 0 0 --- 4613 1 0 0 --- 4614 0 0 0 --- 4615 4616 0 flows destroyed 4617 4618If attach ``destroy`` parameter, the command will destroy all the list aged flow rules:: 4619 4620 testpmd> flow queue 0 aged 0 destroy 4621 Port 0 queue 0 total aged flows: 4 4622 ID Group Prio Attr 4623 2 0 0 --- 4624 3 0 0 --- 4625 1 0 0 --- 4626 0 0 0 --- 4627 Flow rule #2 destruction enqueued 4628 Flow rule #3 destruction enqueued 4629 Flow rule #1 destruction enqueued 4630 Flow rule #0 destruction enqueued 4631 4632 4 flows destroyed 4633 testpmd> flow queue 0 aged 0 4634 Port 0 total aged flows: 0 4635 4636.. note:: 4637 4638 The queue must be empty before attaching ``destroy`` parameter. 4639 4640 4641Creating indirect actions 4642~~~~~~~~~~~~~~~~~~~~~~~~~ 4643 4644``flow indirect_action {port_id} create`` creates indirect action with optional 4645indirect action ID. It is bound to ``rte_flow_action_handle_create()``:: 4646 4647 flow indirect_action {port_id} create [action_id {indirect_action_id}] 4648 [ingress] [egress] [transfer] action {action} / end 4649 4650If successful, it will show:: 4651 4652 Indirect action #[...] created 4653 4654Otherwise, it will complain either that indirect action already exists or that 4655some error occurred:: 4656 4657 Indirect action #[...] is already assigned, delete it first 4658 4659:: 4660 4661 Caught error type [...] ([...]): [...] 4662 4663Create indirect rss action with id 100 to queues 1 and 2 on port 0:: 4664 4665 testpmd> flow indirect_action 0 create action_id 100 \ 4666 ingress action rss queues 1 2 end / end 4667 4668Create indirect rss action with id assigned by testpmd to queues 1 and 2 on 4669port 0:: 4670 4671 testpmd> flow indirect_action 0 create action_id \ 4672 ingress action rss queues 0 1 end / end 4673 4674Enqueueing creation of indirect actions 4675~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4676 4677``flow queue indirect_action create`` adds creation operation of an indirect 4678action to a queue. It is bound to ``rte_flow_async_action_handle_create()``:: 4679 4680 flow queue {port_id} create {queue_id} [postpone {boolean}] 4681 table {table_id} item_template {item_template_id} 4682 action_template {action_template_id} 4683 pattern {item} [/ {item} [...]] / end 4684 actions {action} [/ {action} [...]] / end 4685 4686If successful, it will show:: 4687 4688 Indirect action #[...] creation queued 4689 4690Otherwise it will show an error message of the form:: 4691 4692 Caught error type [...] ([...]): [...] 4693 4694This command uses the same parameters as ``flow indirect_action create``, 4695described in `Creating indirect actions`_. 4696 4697``flow queue pull`` must be called to retrieve the operation status. 4698 4699Updating indirect actions 4700~~~~~~~~~~~~~~~~~~~~~~~~~ 4701 4702``flow indirect_action {port_id} update`` updates configuration of the indirect 4703action from its indirect action ID (as returned by 4704``flow indirect_action {port_id} create``). It is bound to 4705``rte_flow_action_handle_update()``:: 4706 4707 flow indirect_action {port_id} update {indirect_action_id} 4708 action {action} / end 4709 4710If successful, it will show:: 4711 4712 Indirect action #[...] updated 4713 4714Otherwise, it will complain either that indirect action not found or that some 4715error occurred:: 4716 4717 Failed to find indirect action #[...] on port [...] 4718 4719:: 4720 4721 Caught error type [...] ([...]): [...] 4722 4723Update indirect rss action having id 100 on port 0 with rss to queues 0 and 3 4724(in create example above rss queues were 1 and 2):: 4725 4726 testpmd> flow indirect_action 0 update 100 action rss queues 0 3 end / end 4727 4728Enqueueing update of indirect actions 4729~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4730 4731``flow queue indirect_action update`` adds update operation for an indirect 4732action to a queue. It is bound to ``rte_flow_async_action_handle_update()``:: 4733 4734 flow queue {port_id} indirect_action {queue_id} update 4735 {indirect_action_id} [postpone {boolean}] action {action} / end 4736 4737If successful, it will show:: 4738 4739 Indirect action #[...] update queued 4740 4741Otherwise it will show an error message of the form:: 4742 4743 Caught error type [...] ([...]): [...] 4744 4745``flow queue pull`` must be called to retrieve the operation status. 4746 4747Destroying indirect actions 4748~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4749 4750``flow indirect_action {port_id} destroy`` destroys one or more indirect actions 4751from their indirect action IDs (as returned by 4752``flow indirect_action {port_id} create``). It is bound to 4753``rte_flow_action_handle_destroy()``:: 4754 4755 flow indirect_action {port_id} destroy action_id {indirect_action_id} [...] 4756 4757If successful, it will show:: 4758 4759 Indirect action #[...] destroyed 4760 4761It does not report anything for indirect action IDs that do not exist. 4762The usual error message is shown when a indirect action cannot be destroyed:: 4763 4764 Caught error type [...] ([...]): [...] 4765 4766Destroy indirect actions having id 100 & 101:: 4767 4768 testpmd> flow indirect_action 0 destroy action_id 100 action_id 101 4769 4770Enqueueing destruction of indirect actions 4771~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4772 4773``flow queue indirect_action destroy`` adds destruction operation to destroy 4774one or more indirect actions from their indirect action IDs (as returned by 4775``flow queue {port_id} indirect_action {queue_id} create``) to a queue. 4776It is bound to ``rte_flow_async_action_handle_destroy()``:: 4777 4778 flow queue {port_id} indirect_action {queue_id} destroy 4779 [postpone {boolean}] action_id {indirect_action_id} [...] 4780 4781If successful, it will show:: 4782 4783 Indirect action #[...] destruction queued 4784 4785Otherwise it will show an error message of the form:: 4786 4787 Caught error type [...] ([...]): [...] 4788 4789``flow queue pull`` must be called to retrieve the operation status. 4790 4791Query indirect actions 4792~~~~~~~~~~~~~~~~~~~~~~ 4793 4794``flow indirect_action {port_id} query`` queries the indirect action from its 4795indirect action ID (as returned by ``flow indirect_action {port_id} create``). 4796It is bound to ``rte_flow_action_handle_query()``:: 4797 4798 flow indirect_action {port_id} query {indirect_action_id} 4799 4800Currently only rss indirect action supported. If successful, it will show:: 4801 4802 Indirect RSS action: 4803 refs:[...] 4804 4805Otherwise, it will complain either that indirect action not found or that some 4806error occurred:: 4807 4808 Failed to find indirect action #[...] on port [...] 4809 4810:: 4811 4812 Caught error type [...] ([...]): [...] 4813 4814Query indirect action having id 100:: 4815 4816 testpmd> flow indirect_action 0 query 100 4817 4818Enqueueing query of indirect actions 4819~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4820 4821``flow queue indirect_action query`` adds query operation for an indirect 4822action to a queue. It is bound to ``rte_flow_async_action_handle_query()``:: 4823 4824 flow queue {port_id} indirect_action {queue_id} query 4825 {indirect_action_id} [postpone {boolean}] 4826 4827If successful, it will show:: 4828 4829 Indirect action #[...] query queued 4830 4831Otherwise it will show an error message of the form:: 4832 4833 Caught error type [...] ([...]): [...] 4834 4835``flow queue pull`` must be called to retrieve the operation status. 4836 4837Sample QinQ flow rules 4838~~~~~~~~~~~~~~~~~~~~~~ 4839 4840Before creating QinQ rule(s) the following commands should be issued to enable QinQ:: 4841 4842 testpmd> port stop 0 4843 testpmd> vlan set extend on 0 4844 4845The above command sets the inner and outer TPID's to 0x8100. 4846 4847To change the TPID's the following commands should be used:: 4848 4849 testpmd> vlan set outer tpid 0x88A8 0 4850 testpmd> vlan set inner tpid 0x8100 0 4851 testpmd> port start 0 4852 4853Validate and create a QinQ rule on port 0 to steer traffic to a VF queue in a VM. 4854 4855:: 4856 4857 testpmd> flow validate 0 ingress pattern eth / vlan tci is 123 / 4858 vlan tci is 456 / end actions vf id 1 / queue index 0 / end 4859 Flow rule #0 validated 4860 4861 testpmd> flow create 0 ingress pattern eth / vlan tci is 4 / 4862 vlan tci is 456 / end actions vf id 123 / queue index 0 / end 4863 Flow rule #0 created 4864 4865 testpmd> flow list 0 4866 ID Group Prio Attr Rule 4867 0 0 0 i- ETH VLAN VLAN=>VF QUEUE 4868 4869Validate and create a QinQ rule on port 0 to steer traffic to a queue on the host. 4870 4871:: 4872 4873 testpmd> flow validate 0 ingress pattern eth / vlan tci is 321 / 4874 vlan tci is 654 / end actions pf / queue index 0 / end 4875 Flow rule #1 validated 4876 4877 testpmd> flow create 0 ingress pattern eth / vlan tci is 321 / 4878 vlan tci is 654 / end actions pf / queue index 1 / end 4879 Flow rule #1 created 4880 4881 testpmd> flow list 0 4882 ID Group Prio Attr Rule 4883 0 0 0 i- ETH VLAN VLAN=>VF QUEUE 4884 1 0 0 i- ETH VLAN VLAN=>PF QUEUE 4885 4886Sample VXLAN flow rules 4887~~~~~~~~~~~~~~~~~~~~~~~ 4888 4889Before creating VXLAN rule(s), the UDP port should be added for VXLAN packet 4890filter on a port:: 4891 4892 testpmd> rx_vxlan_port add 4789 0 4893 4894Create VXLAN rules on port 0 to steer traffic to PF queues. 4895 4896:: 4897 4898 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan / 4899 eth dst is 00:11:22:33:44:55 / end actions pf / queue index 1 / end 4900 Flow rule #0 created 4901 4902 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan vni is 3 / 4903 eth dst is 00:11:22:33:44:55 / end actions pf / queue index 2 / end 4904 Flow rule #1 created 4905 4906 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan / 4907 eth dst is 00:11:22:33:44:55 / vlan tci is 10 / end actions pf / 4908 queue index 3 / end 4909 Flow rule #2 created 4910 4911 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan vni is 5 / 4912 eth dst is 00:11:22:33:44:55 / vlan tci is 20 / end actions pf / 4913 queue index 4 / end 4914 Flow rule #3 created 4915 4916 testpmd> flow create 0 ingress pattern eth dst is 00:00:00:00:01:00 / ipv4 / 4917 udp / vxlan vni is 6 / eth dst is 00:11:22:33:44:55 / end actions pf / 4918 queue index 5 / end 4919 Flow rule #4 created 4920 4921 testpmd> flow list 0 4922 ID Group Prio Attr Rule 4923 0 0 0 i- ETH IPV4 UDP VXLAN ETH => QUEUE 4924 1 0 0 i- ETH IPV4 UDP VXLAN ETH => QUEUE 4925 2 0 0 i- ETH IPV4 UDP VXLAN ETH VLAN => QUEUE 4926 3 0 0 i- ETH IPV4 UDP VXLAN ETH VLAN => QUEUE 4927 4 0 0 i- ETH IPV4 UDP VXLAN ETH => QUEUE 4928 4929Sample VXLAN encapsulation rule 4930~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4931 4932VXLAN encapsulation outer layer has default value pre-configured in testpmd 4933source code, those can be changed by using the following commands 4934 4935IPv4 VXLAN outer header:: 4936 4937 testpmd> set vxlan ip-version ipv4 vni 4 udp-src 4 udp-dst 4 ip-src 127.0.0.1 4938 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4939 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4940 queue index 0 / end 4941 4942 testpmd> set vxlan-with-vlan ip-version ipv4 vni 4 udp-src 4 udp-dst 4 ip-src 4943 127.0.0.1 ip-dst 128.0.0.1 vlan-tci 34 eth-src 11:11:11:11:11:11 4944 eth-dst 22:22:22:22:22:22 4945 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4946 queue index 0 / end 4947 4948 testpmd> set vxlan-tos-ttl ip-version ipv4 vni 4 udp-src 4 udp-dst 4 ip-tos 0 4949 ip-ttl 255 ip-src 127.0.0.1 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 4950 eth-dst 22:22:22:22:22:22 4951 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4952 queue index 0 / end 4953 4954IPv6 VXLAN outer header:: 4955 4956 testpmd> set vxlan ip-version ipv6 vni 4 udp-src 4 udp-dst 4 ip-src ::1 4957 ip-dst ::2222 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4958 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4959 queue index 0 / end 4960 4961 testpmd> set vxlan-with-vlan ip-version ipv6 vni 4 udp-src 4 udp-dst 4 4962 ip-src ::1 ip-dst ::2222 vlan-tci 34 eth-src 11:11:11:11:11:11 4963 eth-dst 22:22:22:22:22:22 4964 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4965 queue index 0 / end 4966 4967 testpmd> set vxlan-tos-ttl ip-version ipv6 vni 4 udp-src 4 udp-dst 4 4968 ip-tos 0 ip-ttl 255 ::1 ip-dst ::2222 eth-src 11:11:11:11:11:11 4969 eth-dst 22:22:22:22:22:22 4970 testpmd> flow create 0 ingress pattern end actions vxlan_encap / 4971 queue index 0 / end 4972 4973Sample NVGRE encapsulation rule 4974~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4975 4976NVGRE encapsulation outer layer has default value pre-configured in testpmd 4977source code, those can be changed by using the following commands 4978 4979IPv4 NVGRE outer header:: 4980 4981 testpmd> set nvgre ip-version ipv4 tni 4 ip-src 127.0.0.1 ip-dst 128.0.0.1 4982 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4983 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4984 queue index 0 / end 4985 4986 testpmd> set nvgre-with-vlan ip-version ipv4 tni 4 ip-src 127.0.0.1 4987 ip-dst 128.0.0.1 vlan-tci 34 eth-src 11:11:11:11:11:11 4988 eth-dst 22:22:22:22:22:22 4989 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4990 queue index 0 / end 4991 4992IPv6 NVGRE outer header:: 4993 4994 testpmd> set nvgre ip-version ipv6 tni 4 ip-src ::1 ip-dst ::2222 4995 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 4996 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 4997 queue index 0 / end 4998 4999 testpmd> set nvgre-with-vlan ip-version ipv6 tni 4 ip-src ::1 ip-dst ::2222 5000 vlan-tci 34 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5001 testpmd> flow create 0 ingress pattern end actions nvgre_encap / 5002 queue index 0 / end 5003 5004Sample L2 encapsulation rule 5005~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5006 5007L2 encapsulation has default value pre-configured in testpmd 5008source code, those can be changed by using the following commands 5009 5010L2 header:: 5011 5012 testpmd> set l2_encap ip-version ipv4 5013 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5014 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / mpls / end actions 5015 mplsoudp_decap / l2_encap / end 5016 5017L2 with VXLAN header:: 5018 5019 testpmd> set l2_encap-with-vlan ip-version ipv4 vlan-tci 34 5020 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5021 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / mpls / end actions 5022 mplsoudp_decap / l2_encap / end 5023 5024Sample L2 decapsulation rule 5025~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5026 5027L2 decapsulation has default value pre-configured in testpmd 5028source code, those can be changed by using the following commands 5029 5030L2 header:: 5031 5032 testpmd> set l2_decap 5033 testpmd> flow create 0 egress pattern eth / end actions l2_decap / mplsoudp_encap / 5034 queue index 0 / end 5035 5036L2 with VXLAN header:: 5037 5038 testpmd> set l2_encap-with-vlan 5039 testpmd> flow create 0 egress pattern eth / end actions l2_encap / mplsoudp_encap / 5040 queue index 0 / end 5041 5042Sample MPLSoGRE encapsulation rule 5043~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5044 5045MPLSoGRE encapsulation outer layer has default value pre-configured in testpmd 5046source code, those can be changed by using the following commands 5047 5048IPv4 MPLSoGRE outer header:: 5049 5050 testpmd> set mplsogre_encap ip-version ipv4 label 4 5051 ip-src 127.0.0.1 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 5052 eth-dst 22:22:22:22:22:22 5053 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5054 mplsogre_encap / end 5055 5056IPv4 MPLSoGRE with VLAN outer header:: 5057 5058 testpmd> set mplsogre_encap-with-vlan ip-version ipv4 label 4 5059 ip-src 127.0.0.1 ip-dst 128.0.0.1 vlan-tci 34 5060 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5061 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5062 mplsogre_encap / end 5063 5064IPv6 MPLSoGRE outer header:: 5065 5066 testpmd> set mplsogre_encap ip-version ipv6 mask 4 5067 ip-src ::1 ip-dst ::2222 eth-src 11:11:11:11:11:11 5068 eth-dst 22:22:22:22:22:22 5069 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5070 mplsogre_encap / end 5071 5072IPv6 MPLSoGRE with VLAN outer header:: 5073 5074 testpmd> set mplsogre_encap-with-vlan ip-version ipv6 mask 4 5075 ip-src ::1 ip-dst ::2222 vlan-tci 34 5076 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5077 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5078 mplsogre_encap / end 5079 5080Sample MPLSoGRE decapsulation rule 5081~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5082 5083MPLSoGRE decapsulation outer layer has default value pre-configured in testpmd 5084source code, those can be changed by using the following commands 5085 5086IPv4 MPLSoGRE outer header:: 5087 5088 testpmd> set mplsogre_decap ip-version ipv4 5089 testpmd> flow create 0 ingress pattern eth / ipv4 / gre / mpls / end actions 5090 mplsogre_decap / l2_encap / end 5091 5092IPv4 MPLSoGRE with VLAN outer header:: 5093 5094 testpmd> set mplsogre_decap-with-vlan ip-version ipv4 5095 testpmd> flow create 0 ingress pattern eth / vlan / ipv4 / gre / mpls / end 5096 actions mplsogre_decap / l2_encap / end 5097 5098IPv6 MPLSoGRE outer header:: 5099 5100 testpmd> set mplsogre_decap ip-version ipv6 5101 testpmd> flow create 0 ingress pattern eth / ipv6 / gre / mpls / end 5102 actions mplsogre_decap / l2_encap / end 5103 5104IPv6 MPLSoGRE with VLAN outer header:: 5105 5106 testpmd> set mplsogre_decap-with-vlan ip-version ipv6 5107 testpmd> flow create 0 ingress pattern eth / vlan / ipv6 / gre / mpls / end 5108 actions mplsogre_decap / l2_encap / end 5109 5110Sample MPLSoUDP encapsulation rule 5111~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5112 5113MPLSoUDP encapsulation outer layer has default value pre-configured in testpmd 5114source code, those can be changed by using the following commands 5115 5116IPv4 MPLSoUDP outer header:: 5117 5118 testpmd> set mplsoudp_encap ip-version ipv4 label 4 udp-src 5 udp-dst 10 5119 ip-src 127.0.0.1 ip-dst 128.0.0.1 eth-src 11:11:11:11:11:11 5120 eth-dst 22:22:22:22:22:22 5121 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5122 mplsoudp_encap / end 5123 5124IPv4 MPLSoUDP with VLAN outer header:: 5125 5126 testpmd> set mplsoudp_encap-with-vlan ip-version ipv4 label 4 udp-src 5 5127 udp-dst 10 ip-src 127.0.0.1 ip-dst 128.0.0.1 vlan-tci 34 5128 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5129 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5130 mplsoudp_encap / end 5131 5132IPv6 MPLSoUDP outer header:: 5133 5134 testpmd> set mplsoudp_encap ip-version ipv6 mask 4 udp-src 5 udp-dst 10 5135 ip-src ::1 ip-dst ::2222 eth-src 11:11:11:11:11:11 5136 eth-dst 22:22:22:22:22:22 5137 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5138 mplsoudp_encap / end 5139 5140IPv6 MPLSoUDP with VLAN outer header:: 5141 5142 testpmd> set mplsoudp_encap-with-vlan ip-version ipv6 mask 4 udp-src 5 5143 udp-dst 10 ip-src ::1 ip-dst ::2222 vlan-tci 34 5144 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5145 testpmd> flow create 0 egress pattern eth / end actions l2_decap / 5146 mplsoudp_encap / end 5147 5148Sample MPLSoUDP decapsulation rule 5149~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5150 5151MPLSoUDP decapsulation outer layer has default value pre-configured in testpmd 5152source code, those can be changed by using the following commands 5153 5154IPv4 MPLSoUDP outer header:: 5155 5156 testpmd> set mplsoudp_decap ip-version ipv4 5157 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / mpls / end actions 5158 mplsoudp_decap / l2_encap / end 5159 5160IPv4 MPLSoUDP with VLAN outer header:: 5161 5162 testpmd> set mplsoudp_decap-with-vlan ip-version ipv4 5163 testpmd> flow create 0 ingress pattern eth / vlan / ipv4 / udp / mpls / end 5164 actions mplsoudp_decap / l2_encap / end 5165 5166IPv6 MPLSoUDP outer header:: 5167 5168 testpmd> set mplsoudp_decap ip-version ipv6 5169 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / mpls / end 5170 actions mplsoudp_decap / l2_encap / end 5171 5172IPv6 MPLSoUDP with VLAN outer header:: 5173 5174 testpmd> set mplsoudp_decap-with-vlan ip-version ipv6 5175 testpmd> flow create 0 ingress pattern eth / vlan / ipv6 / udp / mpls / end 5176 actions mplsoudp_decap / l2_encap / end 5177 5178Sample Raw encapsulation rule 5179~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5180 5181Raw encapsulation configuration can be set by the following commands 5182 5183Encapsulating VxLAN:: 5184 5185 testpmd> set raw_encap 4 eth src is 10:11:22:33:44:55 / vlan tci is 1 5186 inner_type is 0x0800 / ipv4 / udp dst is 4789 / vxlan vni 5187 is 2 / end_set 5188 testpmd> flow create 0 egress pattern eth / ipv4 / end actions 5189 raw_encap index 4 / end 5190 5191Sample Raw decapsulation rule 5192~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5193 5194Raw decapsulation configuration can be set by the following commands 5195 5196Decapsulating VxLAN:: 5197 5198 testpmd> set raw_decap eth / ipv4 / udp / vxlan / end_set 5199 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / vxlan / eth / ipv4 / 5200 end actions raw_decap / queue index 0 / end 5201 5202Sample ESP rules 5203~~~~~~~~~~~~~~~~ 5204 5205ESP rules can be created by the following commands:: 5206 5207 testpmd> flow create 0 ingress pattern eth / ipv4 / esp spi is 1 / end actions 5208 queue index 3 / end 5209 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / esp spi is 1 / end 5210 actions queue index 3 / end 5211 testpmd> flow create 0 ingress pattern eth / ipv6 / esp spi is 1 / end actions 5212 queue index 3 / end 5213 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / esp spi is 1 / end 5214 actions queue index 3 / end 5215 5216Sample AH rules 5217~~~~~~~~~~~~~~~~ 5218 5219AH rules can be created by the following commands:: 5220 5221 testpmd> flow create 0 ingress pattern eth / ipv4 / ah spi is 1 / end actions 5222 queue index 3 / end 5223 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / ah spi is 1 / end 5224 actions queue index 3 / end 5225 testpmd> flow create 0 ingress pattern eth / ipv6 / ah spi is 1 / end actions 5226 queue index 3 / end 5227 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / ah spi is 1 / end 5228 actions queue index 3 / end 5229 5230Sample PFCP rules 5231~~~~~~~~~~~~~~~~~ 5232 5233PFCP rules can be created by the following commands(s_field need to be 1 5234if seid is set):: 5235 5236 testpmd> flow create 0 ingress pattern eth / ipv4 / pfcp s_field is 0 / end 5237 actions queue index 3 / end 5238 testpmd> flow create 0 ingress pattern eth / ipv4 / pfcp s_field is 1 5239 seid is 1 / end actions queue index 3 / end 5240 testpmd> flow create 0 ingress pattern eth / ipv6 / pfcp s_field is 0 / end 5241 actions queue index 3 / end 5242 testpmd> flow create 0 ingress pattern eth / ipv6 / pfcp s_field is 1 5243 seid is 1 / end actions queue index 3 / end 5244 5245Sample Sampling/Mirroring rules 5246~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5247 5248Sample/Mirroring rules can be set by the following commands 5249 5250NIC-RX Sampling rule, the matched ingress packets and sent to the queue 1, 5251and 50% packets are duplicated and marked with 0x1234 and sent to queue 0. 5252 5253:: 5254 5255 testpmd> set sample_actions 0 mark id 0x1234 / queue index 0 / end 5256 testpmd> flow create 0 ingress group 1 pattern eth / end actions 5257 sample ratio 2 index 0 / queue index 1 / end 5258 5259Match packets coming from a VM which is referred to by means of 5260its representor ethdev (port 1), mirror 50% of them to the 5261said representor (for bookkeeping) as well as encapsulate 5262all the packets and steer them to the physical port: 5263 5264:: 5265 5266 testpmd> set sample_actions 0 port_representor ethdev_port_id 1 / end 5267 5268 testpmd> set vxlan ip-version ipv4 vni 4 udp-src 32 udp-dst 4789 ip-src 127.0.0.1 5269 ip-dst 127.0.0.2 eth-src 11:11:11:11:11:11 eth-dst 22:22:22:22:22:22 5270 5271 testpmd> flow create 0 transfer pattern represented_port ethdev_port_id is 1 / end 5272 actions sample ratio 2 index 0 / vxlan_encap / 5273 represented_port ethdev_port_id 0 / end 5274 5275The rule is inserted via port 0 (assumed to have "transfer" privilege). 5276 5277Sample integrity rules 5278~~~~~~~~~~~~~~~~~~~~~~ 5279 5280Integrity rules can be created by the following commands: 5281 5282Integrity rule that forwards valid TCP packets to group 1. 5283TCP packet integrity is matched with the ``l4_ok`` bit 3. 5284 5285:: 5286 5287 testpmd> flow create 0 ingress 5288 pattern eth / ipv4 / tcp / integrity value mask 8 value spec 8 / end 5289 actions jump group 1 / end 5290 5291Integrity rule that forwards invalid packets to application. 5292General packet integrity is matched with the ``packet_ok`` bit 0. 5293 5294:: 5295 5296 testpmd> flow create 0 ingress pattern integrity value mask 1 value spec 0 / end actions queue index 0 / end 5297 5298Sample conntrack rules 5299~~~~~~~~~~~~~~~~~~~~~~ 5300 5301Conntrack rules can be set by the following commands 5302 5303Need to construct the connection context with provided information. 5304In the first table, create a flow rule by using conntrack action and jump to 5305the next table. In the next table, create a rule to check the state. 5306 5307:: 5308 5309 testpmd> set conntrack com peer 1 is_orig 1 enable 1 live 1 sack 1 cack 0 5310 last_dir 0 liberal 0 state 1 max_ack_win 7 r_lim 5 last_win 510 5311 last_seq 2632987379 last_ack 2532480967 last_end 2632987379 5312 last_index 0x8 5313 testpmd> set conntrack orig scale 7 fin 0 acked 1 unack_data 0 5314 sent_end 2632987379 reply_end 2633016339 max_win 28960 5315 max_ack 2632987379 5316 testpmd> set conntrack rply scale 7 fin 0 acked 1 unack_data 0 5317 sent_end 2532480967 reply_end 2532546247 max_win 65280 5318 max_ack 2532480967 5319 testpmd> flow indirect_action 0 create ingress action conntrack / end 5320 testpmd> flow create 0 group 3 ingress pattern eth / ipv4 / tcp / end actions indirect 0 / jump group 5 / end 5321 testpmd> flow create 0 group 5 ingress pattern eth / ipv4 / tcp / conntrack is 1 / end actions queue index 5 / end 5322 5323Construct the conntrack again with only "is_orig" set to 0 (other fields are 5324ignored), then use "update" interface to update the direction. Create flow 5325rules like above for the peer port. 5326 5327:: 5328 5329 testpmd> flow indirect_action 0 update 0 action conntrack_update dir / end 5330 5331Sample meter with policy rules 5332~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5333 5334Meter with policy rules can be created by the following commands: 5335 5336Need to create policy first and actions are set for green/yellow/red colors. 5337Create meter with policy id. Create flow with meter id. 5338 5339Example for policy with meter color action. The purpose is to color the packet 5340to reflect the meter color result. 5341The meter policy action list: ``green -> green, yellow -> yellow, red -> red``. 5342 5343:: 5344 5345 testpmd> add port meter profile srtcm_rfc2697 0 13 21504 2688 0 0 5346 testpmd> add port meter policy 0 1 g_actions color type green / end y_actions color type yellow / end 5347 r_actions color type red / end 5348 testpmd> create port meter 0 1 13 1 yes 0xffff 0 0 5349 testpmd> flow create 0 priority 0 ingress group 1 pattern eth / end actions meter mtr_id 1 / end 5350 5351Sample L2TPv2 RSS rules 5352~~~~~~~~~~~~~~~~~~~~~~~ 5353 5354L2TPv2 RSS rules can be created by the following commands:: 5355 5356 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 type control 5357 / end actions rss types l2tpv2 end queues end / end 5358 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / end 5359 actions rss types eth l2-src-only end queues end / end 5360 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / end 5361 actions rss types l2tpv2 end queues end / end 5362 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5363 / end actions rss types ipv4 end queues end / end 5364 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv6 5365 / udp / end actions rss types ipv6-udp end queues end / end 5366 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / l2tpv2 / ppp / ipv4 5367 / tcp / end actions rss types ipv4-tcp end queues end / end 5368 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / l2tpv2 / ppp / ipv6 5369 / end actions rss types ipv6 end queues end / end 5370 5371Sample L2TPv2 FDIR rules 5372~~~~~~~~~~~~~~~~~~~~~~~~ 5373 5374L2TPv2 FDIR rules can be created by the following commands:: 5375 5376 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 type control 5377 session_id is 0x1111 / end actions queue index 3 / end 5378 testpmd> flow create 0 ingress pattern eth src is 00:00:00:00:00:01 / ipv4 5379 / udp / l2tpv2 type data / end actions queue index 3 / end 5380 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 type data 5381 session_id is 0x1111 / ppp / end actions queue index 3 / end 5382 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5383 src is 10.0.0.1 / end actions queue index 3 / end 5384 testpmd> flow create 0 ingress pattern eth / ipv6 / udp / l2tpv2 / ppp / ipv6 5385 dst is ABAB:910B:6666:3457:8295:3333:1800:2929 / end actions queue index 3 / end 5386 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5387 / udp src is 22 / end actions queue index 3 / end 5388 testpmd> flow create 0 ingress pattern eth / ipv4 / udp / l2tpv2 / ppp / ipv4 5389 / tcp dst is 23 / end actions queue index 3 / end 5390 5391Sample RAW rule 5392~~~~~~~~~~~~~~~ 5393 5394A RAW rule can be created as following using ``pattern_hex`` key and mask. 5395 5396:: 5397 5398 testpmd> flow create 0 group 0 priority 1 ingress pattern raw relative is 0 search is 0 offset 5399 is 0 limit is 0 pattern_hex spec 00000000000000000000000000000000000000000000000000000a0a0a0a 5400 pattern_hex mask 0000000000000000000000000000000000000000000000000000ffffffff / end actions 5401 queue index 4 / end 5402 5403Sample match with comparison rule 5404~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5405 5406Match with comparison rule can be created as following using ``compare``. 5407 5408:: 5409 5410 testpmd> flow pattern_template 0 create ingress pattern_template_id 1 template compare op mask le 5411 a_type mask tag a_tag_index mask 1 b_type mask tag b_tag_index mask 2 width mask 0xffffffff / end 5412 testpmd> flow actions_template 0 create ingress actions_template_id 1 template count / drop / end 5413 mask count / drop / end 5414 testpmd> flow template_table 0 create table_id 1 group 2 priority 1 ingress rules_number 1 5415 pattern_template 1 actions_template 1 5416 testpmd> flow queue 0 create 0 template_table 1 pattern_template 0 actions_template 0 postpone no 5417 pattern compare op is le a_type is tag a_tag_index is 1 b_type is tag b_tag_index is 2 width is 32 / end 5418 actions count / drop / end 5419 5420BPF Functions 5421-------------- 5422 5423The following sections show functions to load/unload eBPF based filters. 5424 5425bpf-load 5426~~~~~~~~ 5427 5428Load an eBPF program as a callback for particular RX/TX queue:: 5429 5430 testpmd> bpf-load rx|tx (portid) (queueid) (load-flags) (bpf-prog-filename) 5431 5432The available load-flags are: 5433 5434* ``J``: use JIT generated native code, otherwise BPF interpreter will be used. 5435 5436* ``M``: assume input parameter is a pointer to rte_mbuf, otherwise assume it is a pointer to first segment's data. 5437 5438* ``-``: none. 5439 5440.. note:: 5441 5442 You'll need clang v3.7 or above to build bpf program you'd like to load 5443 5444For example: 5445 5446.. code-block:: console 5447 5448 cd examples/bpf 5449 clang -O2 -target bpf -c t1.c 5450 5451Then to load (and JIT compile) t1.o at RX queue 0, port 1: 5452 5453.. code-block:: console 5454 5455 testpmd> bpf-load rx 1 0 J ./dpdk.org/examples/bpf/t1.o 5456 5457To load (not JITed) t1.o at TX queue 0, port 0: 5458 5459.. code-block:: console 5460 5461 testpmd> bpf-load tx 0 0 - ./dpdk.org/examples/bpf/t1.o 5462 5463bpf-unload 5464~~~~~~~~~~ 5465 5466Unload previously loaded eBPF program for particular RX/TX queue:: 5467 5468 testpmd> bpf-unload rx|tx (portid) (queueid) 5469 5470For example to unload BPF filter from TX queue 0, port 0: 5471 5472.. code-block:: console 5473 5474 testpmd> bpf-unload tx 0 0 5475 5476Flex Item Functions 5477------------------- 5478 5479The following sections show functions that configure and create flex item object, 5480create flex pattern and use it in a flow rule. 5481The commands will use 20 bytes IPv4 header for examples: 5482 5483:: 5484 5485 0 1 2 3 5486 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 5487 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5488 | ver | IHL | TOS | length | +0 5489 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5490 | identification | flg | frag. offset | +4 5491 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5492 | TTL | protocol | checksum | +8 5493 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5494 | source IP address | +12 5495 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5496 | destination IP address | +16 5497 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ 5498 5499 5500Create flex item 5501~~~~~~~~~~~~~~~~ 5502 5503Flex item object is created by PMD according to a new header configuration. The 5504header configuration is compiled by the testpmd and stored in 5505``rte_flow_item_flex_conf`` type variable. 5506 5507:: 5508 5509 # flow flex_item create <port> <flex id> <configuration file> 5510 testpmd> flow flex_item init 0 3 ipv4_flex_config.json 5511 port-0: created flex item #3 5512 5513Flex item configuration is kept in external JSON file. 5514It describes the following header elements: 5515 5516**New header length.** 5517 5518Specify whether the new header has fixed or variable length and the basic/minimal 5519header length value. 5520 5521If header length is not fixed, header location with a value that completes header 5522length calculation and scale/offset function must be added. 5523 5524Scale function depends on port hardware. 5525 5526**Next protocol.** 5527 5528Describes location in the new header that specify following network header type. 5529 5530**Flow match samples.** 5531 5532Describes locations in the new header that will be used in flow rules. 5533 5534Number of flow samples and sample maximal length depend of port hardware. 5535 5536**Input trigger.** 5537 5538Describes preceding network header configuration. 5539 5540**Output trigger.** 5541 5542Describes conditions that trigger transfer to following network header 5543 5544.. code-block:: json 5545 5546 { 5547 "next_header": { "field_mode": "FIELD_MODE_FIXED", "field_size": 20}, 5548 "next_protocol": {"field_size": 8, "field_base": 72}, 5549 "sample_data": [ 5550 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 0}, 5551 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 32}, 5552 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 64}, 5553 { "field_mode": "FIELD_MODE_FIXED", "field_size": 32, "field_base": 96} 5554 ], 5555 "input_link": [ 5556 {"item": "eth type is 0x0800"}, 5557 {"item": "vlan inner_type is 0x0800"} 5558 ], 5559 "output_link": [ 5560 {"item": "udp", "next": 17}, 5561 {"item": "tcp", "next": 6}, 5562 {"item": "icmp", "next": 1} 5563 ] 5564 } 5565 5566 5567Flex pattern and flow rules 5568~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5569 5570Flex pattern describe parts of network header that will trigger flex flow item hit in a flow rule. 5571Flex pattern directly related to flex item samples configuration. 5572Flex pattern can be shared between ports. 5573 5574**Flex pattern and flow rule to match IPv4 version and 20 bytes length** 5575 5576:: 5577 5578 # set flex_pattern <pattern_id> is <hex bytes sequence> 5579 testpmd> flow flex_item pattern 5 is 45FF 5580 created pattern #5 5581 5582 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 5583 Flow rule #0 created 5584 5585**Flex pattern and flow rule to match packets with source address 1.2.3.4** 5586 5587:: 5588 5589 testpmd> flow flex_item pattern 2 spec 45000000000000000000000001020304 mask FF0000000000000000000000FFFFFFFF 5590 created pattern #2 5591 5592 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 5593 Flow rule #0 created 5594 5595Driver specific commands 5596------------------------ 5597 5598Some drivers provide specific features. 5599See: 5600 5601- :ref:`net/bonding testpmd driver specific commands <bonding_testpmd_commands>` 5602- :ref:`net/i40e testpmd driver specific commands <net_i40e_testpmd_commands>` 5603- :ref:`net/ixgbe testpmd driver specific commands <net_ixgbe_testpmd_commands>` 5604