2 Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11 * Redistributions in binary form must reproduce the above copyright
12 notice, this list of conditions and the following disclaimer in
13 the documentation and/or other materials provided with the
15 * Neither the name of Intel Corporation nor the names of its
16 contributors may be used to endorse or promote products derived
17 from this software without specific prior written permission.
19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 Testpmd Runtime Functions
32 =========================
34 Where the testpmd application is started in interactive mode, (-i|--interactive),
35 it displays a prompt that can be used to start and stop forwarding,
36 configure the application, display statistics, set the Flow Director and other tasks.
38 .. code-block:: console
42 The testpmd prompt has some, limited, readline support.
43 Common bash command- line functions such as Ctrl+a and Ctrl+e to go to the start and end of the prompt line are supported
44 as well as access to the command history via the up-arrow.
46 There is also support for tab completion.
47 If you type a partial command and hit <TAB> you get a list of the available completions:
49 .. code-block:: console
51 testpmd> show port <TAB>
53 info [Mul-choice STRING]: show|clear port info|stats|fdir|stat_qmap X
54 info [Mul-choice STRING]: show|clear port info|stats|fdir|stat_qmap all
55 stats [Mul-choice STRING]: show|clear port info|stats|fdir|stat_qmap X
56 stats [Mul-choice STRING]: show|clear port info|stats|fdir|stat_qmap all
62 The testpmd has on-line help for the functions that are available at runtime.
63 These are divided into sections and can be accessed using help, help section or help all:
65 .. code-block:: console
69 Help is available for the following sections:
70 help control : Start and stop forwarding.
71 help display : Displaying port, stats and config information.
72 help config : Configuration information.
73 help ports : Configuring ports.
74 help flowdir : Flow Director filter help.
75 help registers : Reading and setting port registers.
76 help filters : Filters configuration help.
77 help all : All of the above sections.
85 Start packet forwarding with current configuration:
92 Start packet forwarding with current configuration after sending one burst of packets:
99 Stop packet forwarding, and display accumulated statistics:
113 The functions in the following sections are used to display information about the
114 testpmd configuration or the NIC status.
119 Display information for a given port or all ports:
121 show port (info|stats|fdir|stat_qmap) (port_id|all)
123 The available information categories are:
125 info : General port information such as MAC address.
127 stats : RX/TX statistics.
129 fdir : Flow Director information and statistics.
131 stat_qmap : Queue statistics mapping.
135 .. code-block:: console
137 testpmd> show port info 0
139 ********************* Infos for port 0 *********************
141 MAC address: XX:XX:XX:XX:XX:XX
143 Link speed: 10000 Mbps
144 Link duplex: full-duplex
145 Promiscuous mode: enabled
146 Allmulticast mode: disabled
147 Maximum number of MAC addresses: 127
156 Display the rss redirection table entry indicated by masks on port X:
158 show port (port_id) rss reta (size) (mask0, mask1...)
160 size is used to indicate the hardware supported reta size
165 Display the RSS hash functions and RSS hash key of a port:
167 show port (port_id) rss-hash [key]
172 Clear the port statistics for a given port or for all ports:
174 clear port (info|stats|fdir|stat_qmap) (port_id|all)
178 .. code-block:: console
180 testpmd> clear port stats all
185 Displays the configuration of the application.
186 The configuration comes from the command-line, the runtime or the application defaults:
188 show config (rxtx|cores|fwd)
190 The available information categories are:
192 rxtx : RX/TX configuration items.
194 cores : List of forwarding cores.
196 fwd : Packet forwarding configuration.
200 .. code-block:: console
202 testpmd> show config rxtx
204 io packet forwarding - CRC stripping disabled - packets/burst=16
205 nb forwarding cores=2 - nb forwarding ports=1
206 RX queues=1 - RX desc=128 - RX free threshold=0
207 RX threshold registers: pthresh=8 hthresh=8 wthresh=4
208 TX queues=1 - TX desc=512 - TX free threshold=0
209 TX threshold registers: pthresh=36 hthresh=0 wthresh=0
210 TX RS bit threshold=0 - TXQ flags=0x0
215 Display an RX descriptor for a port RX queue:
217 read rxd (port_id) (queue_id) (rxd_id)
221 .. code-block:: console
223 testpmd> read rxd 0 0 4
224 0x0000000B - 0x001D0180 / 0x0000000B - 0x001D0180
229 Display a TX descriptor for a port TX queue:
231 read txd (port_id) (queue_id) (txd_id)
235 .. code-block:: console
237 testpmd> read txd 0 0 4
238 0x00000001 - 0x24C3C440 / 0x000F0000 - 0x2330003C
240 Configuration Functions
241 -----------------------
243 The testpmd application can be configured from the runtime as well as from the command-line.
245 This section details the available configuration functions that are available.
249 Configuration changes only become active when forwarding is started/restarted.
254 Reset forwarding to the default configuration:
261 Set the debug verbosity level:
265 Currently the only available levels are 0 (silent except for error) and 1 (fully verbose).
270 Set the number of ports used by the application:
274 This is equivalent to the --nb-ports command-line option.
279 Set the number of cores used by the application:
283 This is equivalent to the --nb-cores command-line option.
287 The number of cores used must not be greater than number of ports used multiplied by the number of queues per port.
292 Set the forwarding cores hexadecimal mask:
296 This is equivalent to the --coremask command-line option.
300 The master lcore is reserved for command line parsing only and cannot be masked on for packet forwarding.
305 Set the forwarding ports hexadecimal mask:
309 This is equivalent to the --portmask command-line option.
314 Set number of packets per burst:
318 This is equivalent to the --burst command-line option.
320 In mac_retry forwarding mode, the transmit delay time and number of retries can also be set.
322 set burst tx delay (micrseconds) retry (num)
327 Set the length of each segment of the TX-ONLY packets:
331 Where x[,y]* represents a CSV list of values, without white space.
336 Set the list of forwarding cores:
338 set corelist (x[,y]*)
340 For example, to change the forwarding cores:
342 .. code-block:: console
344 testpmd> set corelist 3,1
345 testpmd> show config fwd
347 io packet forwarding - ports=2 - cores=2 - streams=2 - NUMA support disabled
348 Logical Core 3 (socket 0) forwards packets on 1 streams:
349 RX P=0/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:01
350 Logical Core 1 (socket 0) forwards packets on 1 streams:
351 RX P=1/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
355 The cores are used in the same order as specified on the command line.
360 Set the list of forwarding ports:
362 set portlist (x[,y]*)
364 For example, to change the port forwarding:
366 .. code-block:: console
368 testpmd> set portlist 0,2,1,3
369 testpmd> show config fwd
371 io packet forwarding - ports=4 - cores=1 - streams=4
372 Logical Core 3 (socket 0) forwards packets on 4 streams:
373 RX P=0/Q=0 (socket 0) -> TX P=2/Q=0 (socket 0) peer=02:00:00:00:00:01
374 RX P=2/Q=0 (socket 0) -> TX P=0/Q=0 (socket 0) peer=02:00:00:00:00:00
375 RX P=1/Q=0 (socket 0) -> TX P=3/Q=0 (socket 0) peer=02:00:00:00:00:03
376 RX P=3/Q=0 (socket 0) -> TX P=1/Q=0 (socket 0) peer=02:00:00:00:00:02
381 Set the VLAN strip on a port:
383 vlan set strip (on|off) (port_id)
388 Set the VLAN strip for a queue on a port:
390 vlan set stripq (on|off) (port_id,queue_id)
395 Set the VLAN filter on a port:
397 vlan set filter (on|off) (port_id)
402 Set the VLAN QinQ (extended queue in queue) on for a port:
404 vlan set qinq (on|off) (port_id)
409 Set the outer VLAN TPID for packet filtering on a port:
411 vlan set tpid (value) (port_id)
415 TPID value must be a 16-bit number (value <= 65536).
420 Add a VLAN ID, or all identifiers, to the set of VLAN identifiers filtered by port ID:
422 rx_vlan add (vlan_id|all) (port_id)
426 VLAN filter must be set on that port. VLAN ID < 4096.
431 Remove a VLAN ID, or all identifiers, from the set of VLAN identifiers filtered by port ID:
433 rx_vlan rm (vlan_id|all) (port_id)
438 Add a VLAN ID, to the set of VLAN identifiers filtered for VF(s) for port ID:
440 rx_vlan add (vlan_id) port (port_id) vf (vf_mask)
445 Remove a VLAN ID, from the set of VLAN identifiers filtered for VF(s) for port ID:
447 rx_vlan rm (vlan_id) port (port_id) vf (vf_mask)
452 Set the outer VLAN TPID for packet filtering on a port:
454 rx_vlan set tpid (value) (port_id)
459 Add a tunnel filter on a port:
461 tunnel_filter add (port_id) (outer_mac) (inner_mac) (ip_addr) (inner_vlan)
462 (tunnel_type) (filter_type) (tenant_id) (queue_id)
467 Remove a tunnel filter on a port:
469 tunnel_filter rm (port_id) (outer_mac) (inner_mac) (ip_addr) (inner_vlan)
470 (tunnel_type) (filter_type) (tenant_id) (queue_id)
475 Add an UDP port for VXLAN packet filter on a port:
477 rx_vxlan_port add (udp_port) (port_id)
482 Remove an UDP port for VXLAN packet filter on a port:
484 rx_vxlan_port rm (udp_port) (port_id)
489 Set hardware insertion of VLAN ID in packets sent on a port:
491 tx_vlan set (vlan_id) (port_id)
496 Set port based hardware insertion of VLAN ID in pacekts sent on a port:
498 tx_vlan set pvid (port_id) (vlan_id) (on|off)
503 Disable hardware insertion of a VLAN header in packets sent on a port:
505 tx_vlan reset (port_id)
510 Select hardware or software calculation of the checksum when
511 transmitting a packet using the csum forward engine:
513 tx_cksum set (ip|udp|tcp|sctp|vxlan)
515 ip|udp|tcp|sctp always concern the inner layer.
516 vxlan concerns the outer IP and UDP layer (in case the packet
517 is recognized as a vxlan packet by the forward engine)
521 Check the NIC Datasheet for hardware limits.
526 Display tx checksum offload configuration:
528 tx_checksum show (port_id)
533 Enable TCP Segmentation Offload in csum forward engine:
535 tso set (segsize) (port_id)
538 Please check the NIC datasheet for HW limits
543 Display the status of TCP Segmentation Offload:
550 Set the packet forwarding mode:
552 set fwd (io|mac|mac_retry|macswap|flowgen|rxonly|txonly|csum|icmpecho)
554 The available information categories are:
556 * io: forwards packets "as-is" in I/O mode.
557 This is the fastest possible forwarding operation as it does not access packets data.
558 This is the default mode.
560 * mac: changes the source and the destination Ethernet addresses of packets before forwarding them.
562 * mac_retry: same as "mac" forwarding mode, but includes retries if the destination queue is full.
564 * macswap: MAC swap forwarding mode.
565 Swaps the source and the destination Ethernet addresses of packets before forwarding them.
567 * flowgen: multi-flow generation mode.
568 Originates a bunch of flows (varying destination IP addresses), and terminate receive traffic.
570 * rxonly: receives packets but doesn't transmit them.
572 * txonly: generates and transmits packets without receiving any.
574 * csum: changes the checksum field with HW or SW methods depending on the offload flags on the packet.
576 * icmpecho: receives a burst of packets, lookup for IMCP echo requests and, if any, send back ICMP echo replies.
581 .. code-block:: console
583 testpmd> set fwd rxonly
585 Set rxonly packet forwarding mode
590 Add an alternative MAC address to a port:
592 mac_addr add (port_id) (XX:XX:XX:XX:XX:XX)
597 Remove a MAC address from a port:
599 mac_addr remove (port_id) (XX:XX:XX:XX:XX:XX)
604 Add an alternative MAC address for a VF to a port:
606 mac_add add port (port_id) vf (vf_id) (XX:XX:XX:XX:XX:XX)
611 Set the unicast hash filter(s) on/off for a port X:
613 set port (port_id) uta (XX:XX:XX:XX:XX:XX|all) (on|off)
618 Set the promiscuous mode on for a port or for all ports.
619 In promiscuous mode packets are not dropped if they aren't for the specified MAC address:
621 set promisc (port_id|all) (on|off)
626 Set the allmulti mode for a port or for all ports:
628 set allmulti (port_id|all) (on|off)
630 Same as the ifconfig (8) option. Controls how multicast packets are handled.
635 Set the link flow control parameter on a port:
637 set flow_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \
638 (pause_time) (send_xon) (port_id)
642 high_water (integer): High threshold value to trigger XOFF.
644 low_water (integer) : Low threshold value to trigger XON.
646 pause_time (integer): Pause quota in the Pause frame.
648 send_xon (0/1) : Send XON frame.
650 mac_ctrl_frame_fwd : Enable receiving MAC control frames
655 Set the priority flow control parameter on a port:
657 set pfc_ctrl rx (on|off) tx (on|off) (high_water) (low_water) \ (pause_time) (priority) (port_id)
661 priority (0-7): VLAN User Priority.
666 Set statistics mapping (qmapping 0..15) for RX/TX queue on port:
668 set stat_qmap (tx|rx) (port_id) (queue_id) (qmapping)
670 For example, to set rx queue 2 on port 0 to mapping 5:
672 .. code-block:: console
674 testpmd>set stat_qmap rx 0 2 5
676 set port - rx/tx(for VF)
677 ~~~~~~~~~~~~~~~~~~~~~~~~
679 Set VF receive/transmit from a port:
681 set port (port_id) vf (vf_id) (rx|tx) (on|off)
683 set port - mac address filter (for VF)
684 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
686 Add/Remove unicast or multicast MAC addr filter for a VF:
688 set port (port_id) vf (vf_id) (mac_addr)
689 (exact-mac|exact-mac-vlan|hashmac|hashmac-vlan) (on|off)
691 set port - rx mode(for VF)
692 ~~~~~~~~~~~~~~~~~~~~~~~~~~
694 Set the VF receive mode of a port:
696 set port (port_id) vf (vf_id) rxmode (AUPE|ROPE|BAM|MPE) (on|off)
698 The available receive modes are:
700 * AUPE: accepts untagged VLAN.
702 * ROPE: accepts unicast hash.
704 * BAM: accepts broadcast packets
706 * MPE: accepts all multicast packets
708 set port - tx_rate (for Queue)
709 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
711 Set TX rate limitation for queue of a port ID:
713 set port (port_id) queue (queue_id) rate (rate_value)
715 set port - tx_rate (for VF)
716 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
718 Set TX rate limitation for queues in VF of a port ID:
720 set port (port_id) vf (vf_id) rate (rate_value) queue_mask (queue_mask)
722 set port - mirror rule
723 ~~~~~~~~~~~~~~~~~~~~~~
725 Set port or vlan type mirror rule for a port.
727 set port (port_id) mirror-rule (rule_id) (pool-mirror|vlan-mirror) (poolmask|vlanid[,vlanid]*) dst-pool (pool_id) (on|off)
729 For example to enable mirror traffic with vlan 0,1 to pool 0:
731 .. code-block:: console
733 set port 0 mirror-rule 0 vlan-mirror 0,1 dst-pool 0 on
735 reset port - mirror rule
736 ~~~~~~~~~~~~~~~~~~~~~~~~
738 Reset a mirror rule for a port.
740 reset port (port_id) mirror-rule (rule_id)
745 Flush (default) or don't flush RX streams before forwarding.
746 Mainly used with PCAP drivers to avoid the default behavior of flushing the first 512 packets on RX streams.
753 Set the bypass mode for the lowest port on bypass enabled NIC.
755 set bypass mode (normal|bypass|isolate) (port_id)
760 Set the event required to initiate specified bypass mode for the lowest port on a bypass enabled NIC where:
762 * timeout: enable bypass after watchdog timeout.
764 * os_on: enable bypass when OS/board is powered on.
766 * os_off: enable bypass when OS/board is powered off.
768 * power_on: enable bypass when power supply is turned on.
770 * power_off: enable bypass when power supply is turned off.
772 set bypass event (timeout|os_on|os_off|power_on|power_off) mode (normal|bypass|isolate) (port_id)
777 Set the bypass watchdog timeout to 'n' seconds where 0 = instant.
779 set bypass timeout (0|1.5|2|3|4|8|16|32)
784 Show the bypass configuration for a bypass enabled NIC using the lowest port on the NIC.
786 show bypass config (port_id)
791 Set link up for a port.
793 set link-up port (port id)
798 Set link down for a port.
800 set link-down port (port id)
805 The following sections show functions for configuring ports.
809 Port configuration changes only become active when forwarding is started/restarted.
814 Start all ports or a specific port:
816 port start (port_id|all)
821 Stop all ports or a specific port:
823 port stop (port_id|all)
828 Close all ports or a specific port:
830 port close (port_id|all)
832 port start/stop queue
833 ~~~~~~~~~~~~~~~~~~~~~
835 Start/stop a rx/tx queue on a specific port:
837 port (port_id) (rxq|txq) (queue_id) (start|stop)
839 Only take effect when port is started.
844 Set the speed and duplex mode for all ports or a specific port:
846 port config (port_id|all) speed (10|100|1000|10000|auto) duplex (half|full|auto)
848 port config - queues/descriptors
849 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
851 Set number of queues/descriptors for rxq, txq, rxd and txd:
853 port config all (rxq|txq|rxd|txd) (value)
855 This is equivalent to the --rxq, --txq, --rxd and --txd command-line options.
857 port config - max-pkt-len
858 ~~~~~~~~~~~~~~~~~~~~~~~~~
860 Set the maximum packet length:
862 port config all max-pkt-len (value)
864 This is equivalent to the --max-pkt-len command-line option.
866 port config - CRC Strip
867 ~~~~~~~~~~~~~~~~~~~~~~~
869 Set hardware CRC stripping on or off for all ports:
871 port config all crc-strip (on|off)
873 CRC stripping is off by default.
875 The on option is equivalent to the --crc-strip command-line option.
877 port config - RX Checksum
878 ~~~~~~~~~~~~~~~~~~~~~~~~~
880 Set hardware RX checksum offload to on or off for all ports:
882 port config all rx-cksum (on|off)
884 Checksum offload is off by default.
886 The on option is equivalent to the --enable-rx-cksum command-line option.
891 Set hardware VLAN on or off for all ports:
893 port config all hw-vlan (on|off)
895 Hardware VLAN is on by default.
897 The off option is equivalent to the --disable-hw-vlan command-line option.
899 port config - Drop Packets
900 ~~~~~~~~~~~~~~~~~~~~~~~~~~
902 Set packet drop for packets with no descriptors on or off for all ports:
904 port config all drop-en (on|off)
906 Packet dropping for packets with no descriptors is off by default.
908 The on option is equivalent to the --enable-drop-en command-line option.
913 Set the RSS (Receive Side Scaling) mode on or off:
915 port config all rss (ip|udp|none)
917 RSS is on by default.
919 The off option is equivalent to the --disable-rss command-line option.
921 port config - RSS Reta
922 ~~~~~~~~~~~~~~~~~~~~~~
924 Set the RSS (Receive Side Scaling) redirection table:
926 port config all rss reta (hash,queue)[,(hash,queue)]
931 Set the DCB mode for an individual port:
933 port config (port_id) dcb vt (on|off) (traffic_class) pfc (on|off)
935 The traffic class should be 4 or 8.
940 Set the number of packets per burst:
942 port config all burst (value)
944 This is equivalent to the --burst command-line option.
946 port config - Threshold
947 ~~~~~~~~~~~~~~~~~~~~~~~
949 Set thresholds for TX/RX queues:
951 port config all (threshold) (value)
953 Where the threshold type can be:
955 * txpt: Set the prefetch threshold register of the TX rings, 0 <= value <= 255.
957 * txht: Set the host threshold register of the TX rings, 0 <= value <= 255.
959 * txwt: Set the write-back threshold register of the TX rings, 0 <= value <= 255.
961 * rxpt: Set the prefetch threshold register of the RX rings, 0 <= value <= 255.
963 * rxht: Set the host threshold register of the RX rings, 0 <= value <= 255.
965 * rxwt: Set the write-back threshold register of the RX rings, 0 <= value <= 255.
967 * txfreet: Set the transmit free threshold of the TX rings, 0 <= value <= txd.
969 * rxfreet: Set the transmit free threshold of the RX rings, 0 <= value <= rxd.
971 * txrst: Set the transmit RS bit threshold of TX rings, 0 <= value <= txd.
972 These threshold options are also available from the command-line.
974 Flow Director Functions
975 -----------------------
977 The Flow Director works in receive mode to identify specific flows or sets of flows and route them to specific queues.
979 Two types of filtering are supported which are referred to as Perfect Match and Signature filters:
981 * Perfect match filters.
982 The hardware checks a match between the masked fields of the received packets and the programmed filters.
985 The hardware checks a match between a hash-based signature of the masked fields of the received packet.
987 The Flow Director filters can match the following fields in a packet:
989 * Source IP and destination IP addresses.
991 * Source port and destination port numbers (for UDP and TCP packets).
993 * IPv4/IPv6 and UDP/ TCP/SCTP protocol match.
997 * Flexible 2-byte tuple match anywhere in the first 64 bytes of the packet.
999 The Flow Director can also mask out parts of all of these fields so that filters are only applied to certain fields
1000 or parts of the fields.
1001 For example it is possible to mask out sub-nets of IP addresses or to ignore VLAN headers.
1003 In the following sections, several common parameters are used in the Flow Director filters.
1004 These are explained below:
1006 * src: A pair of source address values. The source IP, in IPv4 or IPv6 format, and the source port:
1008 src 192.168.0.1 1024
1010 src 2001:DB8:85A3:0:0:8A2E:370:7000 1024
1012 * dst: A pair of destination address values. The destination IP, in IPv4 or IPv6 format, and the destination port.
1014 * flexbytes: A 2-byte tuple to be matched within the first 64 bytes of a packet.
1016 The offset where the match occurs is set by the --pkt-filter-flexbytes-offset command-line parameter
1017 and is counted from the first byte of the destination Ethernet MAC address.
1018 The default offset is 0xC bytes, which is the "Type" word in the MAC header.
1019 Typically, the flexbyte value is set to 0x0800 to match the IPv4 MAC type or 0x86DD to match IPv6.
1020 These values change when a VLAN tag is added.
1022 * vlan: The VLAN header to match in the packet.
1024 * queue: The index of the RX queue to route matched packets to.
1026 * soft: The 16-bit value in the MBUF flow director ID field for RX packets matching the filter.
1028 add_signature_filter
1029 ~~~~~~~~~~~~~~~~~~~~
1031 Add a signature filter:
1033 # Command is displayed on several lines for clarity.
1035 add_signature_filter (port_id) (ip|udp|tcp|sctp)
1037 src (src_ip_address) (src_port)
1039 dst (dst_ip_address) (dst_port)
1041 flexbytes (flexbytes_values)
1043 vlan (vlan_id) queue (queue_id)
1045 upd_signature_filter
1046 ~~~~~~~~~~~~~~~~~~~~
1048 Update a signature filter:
1050 # Command is displayed on several lines for clarity.
1052 upd_signature_filter (port_id) (ip|udp|tcp|sctp)
1054 src (src_ip_address) (src_port)
1056 dst (dst_ip_address) (dst_port)
1058 flexbytes (flexbytes_values)
1060 vlan (vlan_id) queue (queue_id)
1065 Remove a signature filter:
1067 # Command is displayed on several lines for clarity.
1069 rm_signature_filter (port_id) (ip|udp|tcp|sctp)
1071 src (src_ip_address) (src_port)
1073 dst (dst_ip_address) (dst_port)
1075 flexbytes (flexbytes_values)
1082 Add a perfect filter:
1084 # Command is displayed on several lines for clarity.
1086 add_perfect_filter (port_id) (ip|udp|tcp|sctp)
1088 src (src_ip_address) (src_port)
1090 dst (dst_ip_address) (dst_port)
1092 flexbytes (flexbytes_values)
1094 vlan (vlan_id) queue (queue_id) soft (soft_id)
1099 Update a perfect filter:
1101 # Command is displayed on several lines for clarity.
1103 upd_perfect_filter (port_id) (ip|udp|tcp|sctp)
1105 src (src_ip_address) (src_port)
1107 dst (dst_ip_address) (dst_port)
1109 flexbytes (flexbytes_values)
1111 vlan (vlan_id) queue (queue_id)
1116 Remove a perfect filter:
1118 rm_perfect_filter (port_id) (ip|udp|tcp|sctp)
1120 src (src_ip_address) (src_port)
1122 dst (dst_ip_address) (dst_port)
1124 flexbytes (flexbytes_values)
1126 vlan (vlan_id) soft (soft_id)
1131 Set IPv4 filter masks:
1133 # Command is displayed on several lines for clarity.
1135 set_masks_filter (port_id) only_ip_flow (0|1)
1137 src_mask (ip_src_mask) (src_port_mask)
1139 dst_mask (ip_dst_mask) (dst_port_mask)
1141 flexbytes (0|1) vlan_id (0|1) vlan_prio (0|1)
1143 set_ipv6_masks_filter
1144 ~~~~~~~~~~~~~~~~~~~~~
1146 Set IPv6 filter masks:
1148 # Command is displayed on several lines for clarity.
1150 set_ipv6_masks_filter (port_id) only_ip_flow (0|1)
1152 src_mask (ip_src_mask) (src_port_mask)
1154 dst_mask (ip_dst_mask) (dst_port_mask)
1156 flexbytes (0|1) vlan_id (0|1) vlan_prio (0|1)
1160 Link Bonding Functions
1161 ----------------------
1163 The Link Bonding functions make it possible to dynamically create and
1164 manage link bonding devices from within testpmd interactive prompt.
1166 create bonded device
1167 ~~~~~~~~~~~~~~~~~~~~
1169 Create a new bonding device:
1171 create bonded device (mode) (socket)
1173 For example, to create a bonded device in mode 1 on socket 0.
1175 .. code-block:: console
1177 testpmd> create bonded 1 0
1178 created new bonded device (port X)
1183 Adds Ethernet device to a Link Bonding device:
1185 add bonding slave (slave id) (port id)
1187 For example, to add Ethernet device (port 6) to a Link Bonding device (port 10).
1189 .. code-block:: console
1191 testpmd> add bonding slave 6 10
1194 remove bonding slave
1195 ~~~~~~~~~~~~~~~~~~~~
1197 Removes an Ethernet slave device from a Link Bonding device:
1199 remove bonding slave (slave id) (port id)
1201 For example, to remove Ethernet slave device (port 6) to a Link Bonding device (port 10).
1203 .. code-block:: console
1205 testpmd> remove bonding slave 6 10
1210 Set the Link Bonding mode of a Link Bonding device:
1212 set bonding mode (value) (port id)
1214 For example, to set the bonding mode of a Link Bonding device (port 10) to broadcast (mode 3).
1216 .. code-block:: console
1218 testpmd> set bonding mode 3 10
1223 Set an Ethernet slave device as the primary device on a Link Bonding device:
1225 set bonding primary (slave id) (port id)
1227 For example, to set the Ethernet slave device (port 6) as the primary port of a Link Bonding device (port 10).
1229 .. code-block:: console
1231 testpmd> set bonding primary 6 10
1236 Set the MAC address of a Link Bonding device:
1238 set bonding mac (port id) (mac)
1240 For example, to set the MAC address of a Link Bonding device (port 10) to 00:00:00:00:00:01
1242 .. code-block:: console
1244 testpmd> set bonding mac 10 00:00:00:00:00:01
1246 set bonding xmit_balance_policy
1247 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1249 Set the transmission policy for a Link Bonding device when it is in Balance XOR mode:
1251 set bonding xmit_balance_policy (port_id) (l2|l23|l34)
1253 For example, set a Link Bonding device (port 10) to use a balance policy of layer 3+4 (IP addresses & UDP ports )
1255 .. code-block:: console
1257 testpmd> set bonding xmit_balance_policy 10 l34
1260 set bonding mon_period
1261 ~~~~~~~~~~~~~~~~~~~~~~
1263 Set the link status monitoring polling period in milliseconds for a bonding devicie.
1265 This adds support for PMD slave devices which do not support link status interrupts.
1266 When the mon_period is set to a value greater than 0 then all PMD's which do not support
1267 link status ISR will be queried every polling interval to check if their link status has changed.
1269 set bonding mon_period (port_id) (value)
1271 For example, to set the link status monitoring polling period of bonded device (port 5) to 150ms
1273 .. code-block:: console
1275 testpmd> set bonding mon_period 5 150
1281 Show the current configuration of a Link Bonding device:
1283 show bonding config (port id)
1286 to show the configuration a Link Bonding device (port 9) with 3 slave devices (1, 3, 4)
1287 in balance mode with a transmission policy of layer 2+3.
1289 .. code-block:: console
1291 testpmd> show bonding config 9
1293 Balance Xmit Policy: BALANCE_XMIT_POLICY_LAYER23
1295 Active Slaves (3): [1 3 4]
1301 The Register functions can be used to read from and write to registers on the network card referenced by a port number.
1302 This is mainly useful for debugging purposes.
1303 Reference should be made to the appropriate datasheet for the network card for details on the register addresses
1304 and fields that can be accessed.
1309 Display the value of a port register:
1311 read reg (port_id) (address)
1313 For example, to examine the Flow Director control register (FDIRCTL, 0x0000EE000) on an Intel® 82599 10 GbE Controller:
1315 .. code-block:: console
1317 testpmd> read reg 0 0xEE00
1318 port 0 PCI register at offset 0xEE00: 0x4A060029 (1241907241)
1323 Display a port register bit field:
1325 read regfield (port_id) (address) (bit_x) (bit_y)
1327 For example, reading the lowest two bits from the register in the example above:
1329 .. code-block:: console
1331 testpmd> read regfield 0 0xEE00 0 1
1332 port 0 PCI register at offset 0xEE00: bits[0, 1]=0x1 (1)
1337 Display a single port register bit:
1339 read regbit (port_id) (address) (bit_x)
1341 For example, reading the lowest bit from the register in the example above:
1343 .. code-block:: console
1345 testpmd> read regbit 0 0xEE00 0
1346 port 0 PCI register at offset 0xEE00: bit 0=1
1351 Set the value of a port register:
1353 write reg (port_id) (address) (value)
1355 For example, to clear a register:
1357 .. code-block:: console
1359 testpmd> write reg 0 0xEE00 0x0
1360 port 0 PCI register at offset 0xEE00: 0x00000000 (0)
1365 Set bit field of a port register:
1367 write regfield (port_id) (address) (bit_x) (bit_y) (value)
1369 For example, writing to the register cleared in the example above:
1371 .. code-block:: console
1373 testpmd> write regfield 0 0xEE00 0 1 2
1374 port 0 PCI register at offset 0xEE00: 0x00000002 (2)
1379 Set single bit value of a port register:
1381 write regbit (port_id) (address) (bit_x) (value)
1383 For example, to set the high bit in the register from the example above:
1385 .. code-block:: console
1387 testpmd> write regbit 0 0xEE00 31 1
1388 port 0 PCI register at offset 0xEE00: 0x8000000A (2147483658)
1393 This section details the available filter functions that are available.
1396 ~~~~~~~~~~~~~~~~~~~~
1398 Add or delete a L2 Ethertype filter, which identify packets by their L2 Ethertype mainly assign them to a receive queue.
1400 ethertype_filter (port_id) (add|del) (mac_addr|mac_ignr) (mac_address) ethertype (ether_type) (drop|fwd) queue (queue_id)
1402 The available information parameters are:
1404 * port_id: the port which the Ethertype filter assigned on.
1406 * mac_addr: compare destination mac address.
1408 * mac_ignr: ignore destination mac address match.
1410 * mac_address: destination mac address to match.
1412 * ether_type: the EtherType value want to match,
1413 for example 0x0806 for ARP packet. 0x0800 (IPv4) and 0x86DD (IPv6) are invalid.
1415 * queue_id : The receive queue associated with this EtherType filter. It is meaningless when deleting or dropping.
1417 Example, to add/remove an ethertype filter rule:
1419 .. code-block:: console
1421 testpmd> ethertype_filter 0 add mac_ignr ethertype 0x0806 fwd queue 3
1422 testpmd> ethertype_filter 0 del mac_ignr ethertype 0x0806 fwd queue 3
1427 Add a 2-tuple filter,
1428 which identify packets by specific protocol and destination TCP/UDP port
1429 and forwards packets into one of the receive queues.
1431 add_2tuple_filter (port_id) protocol (pro_value) (pro_mask) dst_port (port_value) (port_mask)
1432 flags (flg_value) priority (prio_value) queue (queue_id) index (idx)
1434 The available information parameters are:
1436 * port_id: the port which the 2-tuple filter assigned on.
1438 * pro_value: IP L4 protocol
1440 * pro_mask: protocol participates in the match or not, 1 means participate
1442 * port_value: destination port in L4.
1444 * port_mask: destination port participates in the match or not, 1 means participate.
1446 * flg_value: TCP control bits. The non-zero value is invalid, when the pro_value is not set to 0x06 (TCP).
1448 * prio_value: the priority of this filter.
1450 * queue_id: The receive queue associated with this 2-tuple filter
1452 * index: the index of this 2-tuple filter
1456 .. code-block:: console
1458 testpmd> add_2tuple_filter 0 protocol 0x06 1 dst_port 32 1 flags 0x02 priority 3 queue 3 index 0
1460 remove_2tuple_filter
1461 ~~~~~~~~~~~~~~~~~~~~
1463 Remove a 2-tuple filter
1465 remove_2tuple_filter (port_id) index (idx)
1470 Get and display a 2-tuple filter
1472 get_2tuple_filter (port_id) index (idx)
1476 .. code-block:: console
1478 testpmd> get_2tuple_filter 0 index 0
1481 Destination Port: 0x0020 mask: 1
1482 protocol: 0x06 mask:1 tcp_flags: 0x02
1483 priority: 3 queue: 3
1488 Add a 5-tuple filter,
1489 which consists of a 5-tuple (protocol, source and destination IP addresses, source and destination TCP/UDP/SCTP port)
1490 and routes packets into one of the receive queues.
1492 add_5tuple_filter (port_id) dst_ip (dst_address) src_ip (src_address) dst_port (dst_port_value) src_port (src_port_value)
1493 protocol (protocol_value) mask (mask_value) flags (flags_value) priority (prio_value) queue (queue_id) index (idx)
1495 The available information parameters are:
1497 * port_id: the port which the 5-tuple filter assigned on.
1499 * dst_address: destination IP address.
1501 * src_address: source IP address.
1503 * dst_port_value: TCP/UDP destination port.
1505 * src_port_value: TCP/UDP source port.
1507 * protocol_value: L4 protocol.
1509 * mask_value: participates in the match or not by bit for field above, 1b means participate
1511 * flags_value: TCP control bits. The non-zero value is invalid, when the protocol_value is not set to 0x06 (TCP).
1513 * prio_value: the priority of this filter.
1515 * queue_id: The receive queue associated with this 5-tuple filter.
1517 * index: the index of this 5-tuple filter
1521 .. code-block:: console
1523 testpmd> add_5tuple_filter 1 dst_ip 2.2.2.5 src_ip 2.2.2.4 dst_port 64 src_port 32 protocol 0x06 mask 0x1F flags 0x0 priority 3 queue 3 index 0
1525 remove_5tuple_filter
1526 ~~~~~~~~~~~~~~~~~~~~
1528 Remove a 5-tuple filter
1530 remove_5tuple_filter (port_id) index (idx)
1535 Get and display a 5-tuple filter
1537 get_5tuple_filter (port_id) index (idx)
1541 .. code-block:: console
1543 testpmd> get_5tuple_filter 1 index 0
1546 Destination IP: 0x02020205 mask: 1
1547 Source IP: 0x02020204 mask: 1
1548 Destination Port: 0x0040 mask: 1
1549 Source Port: 0x0020 mask: 1
1550 protocol: 0x06 mask: 1
1551 priority: 3 flags: 0x00 queue: 3
1556 Add SYN filter, which can forward TCP packets whose *SYN* flag is set into a separate queue.
1558 add_syn_filter (port_id) priority (high|low) queue (queue_id)
1560 The available information parameters are:
1562 * port_id: the port which the SYN filter assigned on.
1564 * high: this SYN filter has higher priority than other filters.
1566 * low: this SYN filter has lower priority than other filters.
1568 * queue_id: The receive queue associated with this SYN filter
1572 .. code-block:: console
1574 testpmd> add_syn_filter 0 priority high queue 3,
1581 remove_syn_filter (port_id)
1586 Get and display SYN filter
1588 get_syn_filter (port_id)
1592 .. code-block:: console
1594 testpmd> get_syn_filter 0
1596 syn filter: on, priority: high, queue: 3
1602 which recognizes any arbitrary pattern within the first 128 bytes of the packet
1603 and routes packets into one of the receive queues.
1605 add_flex_filter (port_id) len (len_value) bytes (bytes_string) mask (mask_value)
1606 priority (prio_value) queue (queue_id) index (idx)
1608 The available information parameters are:
1610 * port_id: the port which the Flex filter assigned on.
1612 * len_value: filter length in byte, no greater than 128.
1614 * bytes_string: a sting in format of octal, means the value the flex filter need to match.
1616 * mask_value: a sting in format of octal, bit 1 means corresponding byte in DWORD participates in the match.
1618 * prio_value: the priority of this filter.
1620 * queue_id: The receive queue associated with this Flex filter.
1622 * index: the index of this Flex filter
1626 .. code-block:: console
1628 testpmd> add_flex_filter 0 len 16 bytes 0x00000000000000000000000008060000 mask 000C priority 3 queue 3 index 0
1630 Assign a packet whose 13th and 14th bytes are 0x0806 to queue 3.
1635 Remove a Flex filter
1637 remove_flex_filter (port_id) index (idx)
1642 Get and display a Flex filter
1644 get_flex_filter (port_id) index (idx)
1648 .. code-block:: console
1650 testpmd> get_flex_filter 0 index 0
1656 dword[]: 0x00000000 00000000 00000000 08060000 00000000 00000000 00000000
1657 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1658 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1659 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1662 0b0000000000001100000000000000000000000000000000000000000000000000000000
1663 0000000000000000000000000000000000000000000000000000000000
1665 priority: 3 queue: 3