1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright 2016 6WIND S.A.
3 Copyright 2016 Mellanox Technologies, Ltd
5 Generic flow API (rte_flow)
6 ===========================
11 This API provides a generic means to configure hardware to match specific
12 ingress or egress traffic, alter its fate and query related counters
13 according to any number of user-defined rules.
15 It is named *rte_flow* after the prefix used for all its symbols, and is
16 defined in ``rte_flow.h``.
18 - Matching can be performed on packet data (protocol headers, payload) and
19 properties (e.g. associated physical port, virtual device function ID).
21 - Possible operations include dropping traffic, diverting it to specific
22 queues, to virtual/physical device functions or ports, performing tunnel
23 offloads, adding marks and so on.
25 It is slightly higher-level than the legacy filtering framework which it
26 encompasses and supersedes (including all functions and filter types) in
27 order to expose a single interface with an unambiguous behavior that is
28 common to all poll-mode drivers (PMDs).
36 A flow rule is the combination of attributes with a matching pattern and a
37 list of actions. Flow rules form the basis of this API.
39 Flow rules can have several distinct actions (such as counting,
40 encapsulating, decapsulating before redirecting packets to a particular
41 queue, etc.), instead of relying on several rules to achieve this and having
42 applications deal with hardware implementation details regarding their
45 Support for different priority levels on a rule basis is provided, for
46 example in order to force a more specific rule to come before a more generic
47 one for packets matched by both. However hardware support for more than a
48 single priority level cannot be guaranteed. When supported, the number of
49 available priority levels is usually low, which is why they can also be
50 implemented in software by PMDs (e.g. missing priority levels may be
51 emulated by reordering rules).
53 In order to remain as hardware-agnostic as possible, by default all rules
54 are considered to have the same priority, which means that the order between
55 overlapping rules (when a packet is matched by several filters) is
58 PMDs may refuse to create overlapping rules at a given priority level when
59 they can be detected (e.g. if a pattern matches an existing filter).
61 Thus predictable results for a given priority level can only be achieved
62 with non-overlapping rules, using perfect matching on all protocol layers.
64 Flow rules can also be grouped, the flow rule priority is specific to the
65 group they belong to. All flow rules in a given group are thus processed within
66 the context of that group. Groups are not linked by default, so the logical
67 hierarchy of groups must be explicitly defined by flow rules themselves in each
68 group using the JUMP action to define the next group to redirect too. Only flow
69 rules defined in the default group 0 are guarantee to be matched against, this
70 makes group 0 the origin of any group hierarchy defined by an application.
72 Support for multiple actions per rule may be implemented internally on top
73 of non-default hardware priorities, as a result both features may not be
74 simultaneously available to applications.
76 Considering that allowed pattern/actions combinations cannot be known in
77 advance and would result in an impractically large number of capabilities to
78 expose, a method is provided to validate a given rule from the current
79 device configuration state.
81 This enables applications to check if the rule types they need is supported
82 at initialization time, before starting their data path. This method can be
83 used anytime, its only requirement being that the resources needed by a rule
84 should exist (e.g. a target RX queue should be configured first).
86 Each defined rule is associated with an opaque handle managed by the PMD,
87 applications are responsible for keeping it. These can be used for queries
88 and rules management, such as retrieving counters or other data and
91 To avoid resource leaks on the PMD side, handles must be explicitly
92 destroyed by the application before releasing associated resources such as
95 The following sections cover:
97 - **Attributes** (represented by ``struct rte_flow_attr``): properties of a
98 flow rule such as its direction (ingress or egress) and priority.
100 - **Pattern item** (represented by ``struct rte_flow_item``): part of a
101 matching pattern that either matches specific packet data or traffic
102 properties. It can also describe properties of the pattern itself, such as
105 - **Matching pattern**: traffic properties to look for, a combination of any
108 - **Actions** (represented by ``struct rte_flow_action``): operations to
109 perform whenever a packet is matched by a pattern.
117 Flow rules can be grouped by assigning them a common group number. Groups
118 allow a logical hierarchy of flow rule groups (tables) to be defined. These
119 groups can be supported virtually in the PMD or in the physical device.
120 Group 0 is the default group and this is the only group which flows are
121 guarantee to matched against, all subsequent groups can only be reached by
122 way of the JUMP action from a matched flow rule.
124 Although optional, applications are encouraged to group similar rules as
125 much as possible to fully take advantage of hardware capabilities
126 (e.g. optimized matching) and work around limitations (e.g. a single pattern
127 type possibly allowed in a given group), while being aware that the groups
128 hierarchies must be programmed explicitly.
130 Note that support for more than a single group is not guaranteed.
135 A priority level can be assigned to a flow rule, lower values
136 denote higher priority, with 0 as the maximum.
138 Priority levels are arbitrary and up to the application, they do
139 not need to be contiguous nor start from 0, however the maximum number
140 varies between devices and may be affected by existing flow rules.
142 A flow which matches multiple rules in the same group will always matched by
143 the rule with the highest priority in that group.
145 If a packet is matched by several rules of a given group for a given
146 priority level, the outcome is undefined. It can take any path, may be
147 duplicated or even cause unrecoverable errors.
149 Note that support for more than a single priority level is not guaranteed.
151 Attribute: Traffic direction
152 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
154 Flow rule patterns apply to inbound and/or outbound traffic.
156 In the context of this API, **ingress** and **egress** respectively stand
157 for **inbound** and **outbound** based on the standpoint of the application
158 creating a flow rule.
160 There are no exceptions to this definition.
162 Several pattern items and actions are valid and can be used in both
163 directions. At least one direction must be specified.
165 Specifying both directions at once for a given rule is not recommended but
166 may be valid in a few cases (e.g. shared counters).
171 Instead of simply matching the properties of traffic as it would appear on a
172 given DPDK port ID, enabling this attribute transfers a flow rule to the
173 lowest possible level of any device endpoints found in the pattern.
175 When supported, this effectively enables an application to reroute traffic
176 not necessarily intended for it (e.g. coming from or addressed to different
177 physical ports, VFs or applications) at the device level.
179 It complements the behavior of some pattern items such as `Item: PHY_PORT`_
180 and is meaningless without them.
182 When transferring flow rules, **ingress** and **egress** attributes
183 (`Attribute: Traffic direction`_) keep their original meaning, as if
184 processing traffic emitted or received by the application.
189 Pattern items fall in two categories:
191 - Matching protocol headers and packet data, usually associated with a
192 specification structure. These must be stacked in the same order as the
193 protocol layers to match inside packets, starting from the lowest.
195 - Matching meta-data or affecting pattern processing, often without a
196 specification structure. Since they do not match packet contents, their
197 position in the list is usually not relevant.
199 Item specification structures are used to match specific values among
200 protocol fields (or item properties). Documentation describes for each item
201 whether they are associated with one and their type name if so.
203 Up to three structures of the same type can be set for a given item:
205 - ``spec``: values to match (e.g. a given IPv4 address).
207 - ``last``: upper bound for an inclusive range with corresponding fields in
210 - ``mask``: bit-mask applied to both ``spec`` and ``last`` whose purpose is
211 to distinguish the values to take into account and/or partially mask them
212 out (e.g. in order to match an IPv4 address prefix).
214 Usage restrictions and expected behavior:
216 - Setting either ``mask`` or ``last`` without ``spec`` is an error.
218 - Field values in ``last`` which are either 0 or equal to the corresponding
219 values in ``spec`` are ignored; they do not generate a range. Nonzero
220 values lower than those in ``spec`` are not supported.
222 - Setting ``spec`` and optionally ``last`` without ``mask`` causes the PMD
223 to use the default mask defined for that item (defined as
224 ``rte_flow_item_{name}_mask`` constants).
226 - Not setting any of them (assuming item type allows it) is equivalent to
227 providing an empty (zeroed) ``mask`` for broad (nonspecific) matching.
229 - ``mask`` is a simple bit-mask applied before interpreting the contents of
230 ``spec`` and ``last``, which may yield unexpected results if not used
231 carefully. For example, if for an IPv4 address field, ``spec`` provides
232 *10.1.2.3*, ``last`` provides *10.3.4.5* and ``mask`` provides
233 *255.255.0.0*, the effective range becomes *10.1.0.0* to *10.3.255.255*.
235 Example of an item specification matching an Ethernet header:
237 .. _table_rte_flow_pattern_item_example:
239 .. table:: Ethernet item
241 +----------+----------+-----------------------+
242 | Field | Subfield | Value |
243 +==========+==========+=======================+
244 | ``spec`` | ``src`` | ``00:00:01:02:03:04`` |
245 | +----------+-----------------------+
246 | | ``dst`` | ``00:00:2a:66:00:01`` |
247 | +----------+-----------------------+
248 | | ``type`` | ``0x22aa`` |
249 +----------+----------+-----------------------+
250 | ``last`` | unspecified |
251 +----------+----------+-----------------------+
252 | ``mask`` | ``src`` | ``00:00:ff:ff:ff:00`` |
253 | +----------+-----------------------+
254 | | ``dst`` | ``00:00:00:00:00:ff`` |
255 | +----------+-----------------------+
256 | | ``type`` | ``0x0000`` |
257 +----------+----------+-----------------------+
259 Non-masked bits stand for any value (shown as ``?`` below), Ethernet headers
260 with the following properties are thus matched:
262 - ``src``: ``??:??:01:02:03:??``
263 - ``dst``: ``??:??:??:??:??:01``
264 - ``type``: ``0x????``
269 A pattern is formed by stacking items starting from the lowest protocol
270 layer to match. This stacking restriction does not apply to meta items which
271 can be placed anywhere in the stack without affecting the meaning of the
274 Patterns are terminated by END items.
278 .. _table_rte_flow_tcpv4_as_l4:
280 .. table:: TCPv4 as L4
296 .. _table_rte_flow_tcpv6_in_vxlan:
298 .. table:: TCPv6 in VXLAN
300 +-------+------------+
302 +=======+============+
304 +-------+------------+
306 +-------+------------+
308 +-------+------------+
310 +-------+------------+
312 +-------+------------+
314 +-------+------------+
316 +-------+------------+
318 +-------+------------+
322 .. _table_rte_flow_tcpv4_as_l4_meta:
324 .. table:: TCPv4 as L4 with meta items
346 The above example shows how meta items do not affect packet data matching
347 items, as long as those remain stacked properly. The resulting matching
348 pattern is identical to "TCPv4 as L4".
350 .. _table_rte_flow_udpv6_anywhere:
352 .. table:: UDPv6 anywhere
364 If supported by the PMD, omitting one or several protocol layers at the
365 bottom of the stack as in the above example (missing an Ethernet
366 specification) enables looking up anywhere in packets.
368 It is unspecified whether the payload of supported encapsulations
369 (e.g. VXLAN payload) is matched by such a pattern, which may apply to inner,
370 outer or both packets.
372 .. _table_rte_flow_invalid_l3:
374 .. table:: Invalid, missing L3
386 The above pattern is invalid due to a missing L3 specification between L2
387 (Ethernet) and L4 (UDP). Doing so is only allowed at the bottom and at the
393 They match meta-data or affect pattern processing instead of matching packet
394 data directly, most of them do not need a specification structure. This
395 particularity allows them to be specified anywhere in the stack without
396 causing any side effect.
401 End marker for item lists. Prevents further processing of items, thereby
404 - Its numeric value is 0 for convenience.
405 - PMD support is mandatory.
406 - ``spec``, ``last`` and ``mask`` are ignored.
408 .. _table_rte_flow_item_end:
412 +----------+---------+
414 +==========+=========+
415 | ``spec`` | ignored |
416 +----------+---------+
417 | ``last`` | ignored |
418 +----------+---------+
419 | ``mask`` | ignored |
420 +----------+---------+
425 Used as a placeholder for convenience. It is ignored and simply discarded by
428 - PMD support is mandatory.
429 - ``spec``, ``last`` and ``mask`` are ignored.
431 .. _table_rte_flow_item_void:
435 +----------+---------+
437 +==========+=========+
438 | ``spec`` | ignored |
439 +----------+---------+
440 | ``last`` | ignored |
441 +----------+---------+
442 | ``mask`` | ignored |
443 +----------+---------+
445 One usage example for this type is generating rules that share a common
446 prefix quickly without reallocating memory, only by updating item types:
448 .. _table_rte_flow_item_void_example:
450 .. table:: TCP, UDP or ICMP as L4
452 +-------+--------------------+
454 +=======+====================+
456 +-------+--------------------+
458 +-------+------+------+------+
459 | 2 | UDP | VOID | VOID |
460 +-------+------+------+------+
461 | 3 | VOID | TCP | VOID |
462 +-------+------+------+------+
463 | 4 | VOID | VOID | ICMP |
464 +-------+------+------+------+
466 +-------+--------------------+
471 Inverted matching, i.e. process packets that do not match the pattern.
473 - ``spec``, ``last`` and ``mask`` are ignored.
475 .. _table_rte_flow_item_invert:
479 +----------+---------+
481 +==========+=========+
482 | ``spec`` | ignored |
483 +----------+---------+
484 | ``last`` | ignored |
485 +----------+---------+
486 | ``mask`` | ignored |
487 +----------+---------+
489 Usage example, matching non-TCPv4 packets only:
491 .. _table_rte_flow_item_invert_example:
493 .. table:: Anything but TCPv4
512 Matches traffic originating from (ingress) or going to (egress) the physical
513 function of the current device.
515 If supported, should work even if the physical function is not managed by
516 the application and thus not associated with a DPDK port ID.
518 - Can be combined with any number of `Item: VF`_ to match both PF and VF
520 - ``spec``, ``last`` and ``mask`` must not be set.
522 .. _table_rte_flow_item_pf:
539 Matches traffic originating from (ingress) or going to (egress) a given
540 virtual function of the current device.
542 If supported, should work even if the virtual function is not managed by the
543 application and thus not associated with a DPDK port ID.
545 Note this pattern item does not match VF representors traffic which, as
546 separate entities, should be addressed through their own DPDK port IDs.
548 - Can be specified multiple times to match traffic addressed to several VF
550 - Can be combined with a PF item to match both PF and VF traffic.
551 - Default ``mask`` matches any VF ID.
553 .. _table_rte_flow_item_vf:
557 +----------+----------+---------------------------+
558 | Field | Subfield | Value |
559 +==========+==========+===========================+
560 | ``spec`` | ``id`` | destination VF ID |
561 +----------+----------+---------------------------+
562 | ``last`` | ``id`` | upper range value |
563 +----------+----------+---------------------------+
564 | ``mask`` | ``id`` | zeroed to match any VF ID |
565 +----------+----------+---------------------------+
570 Matches traffic originating from (ingress) or going to (egress) a physical
571 port of the underlying device.
573 The first PHY_PORT item overrides the physical port normally associated with
574 the specified DPDK input port (port_id). This item can be provided several
575 times to match additional physical ports.
577 Note that physical ports are not necessarily tied to DPDK input ports
578 (port_id) when those are not under DPDK control. Possible values are
579 specific to each device, they are not necessarily indexed from zero and may
582 As a device property, the list of allowed values as well as the value
583 associated with a port_id should be retrieved by other means.
585 - Default ``mask`` matches any port index.
587 .. _table_rte_flow_item_phy_port:
591 +----------+-----------+--------------------------------+
592 | Field | Subfield | Value |
593 +==========+===========+================================+
594 | ``spec`` | ``index`` | physical port index |
595 +----------+-----------+--------------------------------+
596 | ``last`` | ``index`` | upper range value |
597 +----------+-----------+--------------------------------+
598 | ``mask`` | ``index`` | zeroed to match any port index |
599 +----------+-----------+--------------------------------+
604 Matches traffic originating from (ingress) or going to (egress) a given DPDK
607 Normally only supported if the port ID in question is known by the
608 underlying PMD and related to the device the flow rule is created against.
610 This must not be confused with `Item: PHY_PORT`_ which refers to the
611 physical port of a device, whereas `Item: PORT_ID`_ refers to a ``struct
612 rte_eth_dev`` object on the application side (also known as "port
613 representor" depending on the kind of underlying device).
615 - Default ``mask`` matches the specified DPDK port ID.
617 .. _table_rte_flow_item_port_id:
621 +----------+----------+-----------------------------+
622 | Field | Subfield | Value |
623 +==========+==========+=============================+
624 | ``spec`` | ``id`` | DPDK port ID |
625 +----------+----------+-----------------------------+
626 | ``last`` | ``id`` | upper range value |
627 +----------+----------+-----------------------------+
628 | ``mask`` | ``id`` | zeroed to match any port ID |
629 +----------+----------+-----------------------------+
634 Matches an arbitrary integer value which was set using the ``MARK`` action in
635 a previously matched rule.
637 This item can only specified once as a match criteria as the ``MARK`` action can
638 only be specified once in a flow action.
640 Note the value of MARK field is arbitrary and application defined.
642 Depending on the underlying implementation the MARK item may be supported on
643 the physical device, with virtual groups in the PMD or not at all.
645 - Default ``mask`` matches any integer value.
647 .. _table_rte_flow_item_mark:
651 +----------+----------+---------------------------+
652 | Field | Subfield | Value |
653 +==========+==========+===========================+
654 | ``spec`` | ``id`` | integer value |
655 +----------+--------------------------------------+
656 | ``last`` | ``id`` | upper range value |
657 +----------+----------+---------------------------+
658 | ``mask`` | ``id`` | zeroed to match any value |
659 +----------+----------+---------------------------+
664 Matches tag item set by other flows. Multiple tags are supported by specifying
667 - Default ``mask`` matches the specified tag value and index.
669 .. _table_rte_flow_item_tag:
673 +----------+----------+----------------------------------------+
674 | Field | Subfield | Value |
675 +==========+===========+=======================================+
676 | ``spec`` | ``data`` | 32 bit flow tag value |
677 | +-----------+---------------------------------------+
678 | | ``index`` | index of flow tag |
679 +----------+-----------+---------------------------------------+
680 | ``last`` | ``data`` | upper range value |
681 | +-----------+---------------------------------------+
682 | | ``index`` | field is ignored |
683 +----------+-----------+---------------------------------------+
684 | ``mask`` | ``data`` | bit-mask applies to "spec" and "last" |
685 | +-----------+---------------------------------------+
686 | | ``index`` | field is ignored |
687 +----------+-----------+---------------------------------------+
692 Matches 32 bit metadata item set.
694 On egress, metadata can be set either by mbuf metadata field with
695 PKT_TX_DYNF_METADATA flag or ``SET_META`` action. On ingress, ``SET_META``
696 action sets metadata for a packet and the metadata will be reported via
697 ``metadata`` dynamic field of ``rte_mbuf`` with PKT_RX_DYNF_METADATA flag.
699 - Default ``mask`` matches the specified Rx metadata value.
701 .. _table_rte_flow_item_meta:
705 +----------+----------+---------------------------------------+
706 | Field | Subfield | Value |
707 +==========+==========+=======================================+
708 | ``spec`` | ``data`` | 32 bit metadata value |
709 +----------+----------+---------------------------------------+
710 | ``last`` | ``data`` | upper range value |
711 +----------+----------+---------------------------------------+
712 | ``mask`` | ``data`` | bit-mask applies to "spec" and "last" |
713 +----------+----------+---------------------------------------+
715 Data matching item types
716 ~~~~~~~~~~~~~~~~~~~~~~~~
718 Most of these are basically protocol header definitions with associated
719 bit-masks. They must be specified (stacked) from lowest to highest protocol
720 layer to form a matching pattern.
722 The following list is not exhaustive, new protocols will be added in the
728 Matches any protocol in place of the current layer, a single ANY may also
729 stand for several protocol layers.
731 This is usually specified as the first pattern item when looking for a
732 protocol anywhere in a packet.
734 - Default ``mask`` stands for any number of layers.
736 .. _table_rte_flow_item_any:
740 +----------+----------+--------------------------------------+
741 | Field | Subfield | Value |
742 +==========+==========+======================================+
743 | ``spec`` | ``num`` | number of layers covered |
744 +----------+----------+--------------------------------------+
745 | ``last`` | ``num`` | upper range value |
746 +----------+----------+--------------------------------------+
747 | ``mask`` | ``num`` | zeroed to cover any number of layers |
748 +----------+----------+--------------------------------------+
750 Example for VXLAN TCP payload matching regardless of outer L3 (IPv4 or IPv6)
751 and L4 (UDP) both matched by the first ANY specification, and inner L3 (IPv4
752 or IPv6) matched by the second ANY specification:
754 .. _table_rte_flow_item_any_example:
756 .. table:: TCP in VXLAN with wildcards
758 +-------+------+----------+----------+-------+
759 | Index | Item | Field | Subfield | Value |
760 +=======+======+==========+==========+=======+
762 +-------+------+----------+----------+-------+
763 | 1 | ANY | ``spec`` | ``num`` | 2 |
764 +-------+------+----------+----------+-------+
766 +-------+------------------------------------+
768 +-------+------+----------+----------+-------+
769 | 4 | ANY | ``spec`` | ``num`` | 1 |
770 +-------+------+----------+----------+-------+
772 +-------+------------------------------------+
774 +-------+------------------------------------+
779 Matches a byte string of a given length at a given offset.
781 Offset is either absolute (using the start of the packet) or relative to the
782 end of the previous matched item in the stack, in which case negative values
785 If search is enabled, offset is used as the starting point. The search area
786 can be delimited by setting limit to a nonzero value, which is the maximum
787 number of bytes after offset where the pattern may start.
789 Matching a zero-length pattern is allowed, doing so resets the relative
790 offset for subsequent items.
792 - This type does not support ranges (``last`` field).
793 - Default ``mask`` matches all fields exactly.
795 .. _table_rte_flow_item_raw:
799 +----------+--------------+-------------------------------------------------+
800 | Field | Subfield | Value |
801 +==========+==============+=================================================+
802 | ``spec`` | ``relative`` | look for pattern after the previous item |
803 | +--------------+-------------------------------------------------+
804 | | ``search`` | search pattern from offset (see also ``limit``) |
805 | +--------------+-------------------------------------------------+
806 | | ``reserved`` | reserved, must be set to zero |
807 | +--------------+-------------------------------------------------+
808 | | ``offset`` | absolute or relative offset for ``pattern`` |
809 | +--------------+-------------------------------------------------+
810 | | ``limit`` | search area limit for start of ``pattern`` |
811 | +--------------+-------------------------------------------------+
812 | | ``length`` | ``pattern`` length |
813 | +--------------+-------------------------------------------------+
814 | | ``pattern`` | byte string to look for |
815 +----------+--------------+-------------------------------------------------+
816 | ``last`` | if specified, either all 0 or with the same values as ``spec`` |
817 +----------+----------------------------------------------------------------+
818 | ``mask`` | bit-mask applied to ``spec`` values with usual behavior |
819 +----------+----------------------------------------------------------------+
821 Example pattern looking for several strings at various offsets of a UDP
822 payload, using combined RAW items:
824 .. _table_rte_flow_item_raw_example:
826 .. table:: UDP payload matching
828 +-------+------+----------+--------------+-------+
829 | Index | Item | Field | Subfield | Value |
830 +=======+======+==========+==============+=======+
832 +-------+----------------------------------------+
834 +-------+----------------------------------------+
836 +-------+------+----------+--------------+-------+
837 | 3 | RAW | ``spec`` | ``relative`` | 1 |
838 | | | +--------------+-------+
839 | | | | ``search`` | 1 |
840 | | | +--------------+-------+
841 | | | | ``offset`` | 10 |
842 | | | +--------------+-------+
843 | | | | ``limit`` | 0 |
844 | | | +--------------+-------+
845 | | | | ``length`` | 3 |
846 | | | +--------------+-------+
847 | | | | ``pattern`` | "foo" |
848 +-------+------+----------+--------------+-------+
849 | 4 | RAW | ``spec`` | ``relative`` | 1 |
850 | | | +--------------+-------+
851 | | | | ``search`` | 0 |
852 | | | +--------------+-------+
853 | | | | ``offset`` | 20 |
854 | | | +--------------+-------+
855 | | | | ``limit`` | 0 |
856 | | | +--------------+-------+
857 | | | | ``length`` | 3 |
858 | | | +--------------+-------+
859 | | | | ``pattern`` | "bar" |
860 +-------+------+----------+--------------+-------+
861 | 5 | RAW | ``spec`` | ``relative`` | 1 |
862 | | | +--------------+-------+
863 | | | | ``search`` | 0 |
864 | | | +--------------+-------+
865 | | | | ``offset`` | -29 |
866 | | | +--------------+-------+
867 | | | | ``limit`` | 0 |
868 | | | +--------------+-------+
869 | | | | ``length`` | 3 |
870 | | | +--------------+-------+
871 | | | | ``pattern`` | "baz" |
872 +-------+------+----------+--------------+-------+
874 +-------+----------------------------------------+
878 - Locate "foo" at least 10 bytes deep inside UDP payload.
879 - Locate "bar" after "foo" plus 20 bytes.
880 - Locate "baz" after "bar" minus 29 bytes.
882 Such a packet may be represented as follows (not to scale)::
885 | |<--------->| |<--------->|
887 |-----|------|-----|-----|-----|-----|-----------|-----|------|
888 | ETH | IPv4 | UDP | ... | baz | foo | ......... | bar | .... |
889 |-----|------|-----|-----|-----|-----|-----------|-----|------|
891 |<--------------------------->|
894 Note that matching subsequent pattern items would resume after "baz", not
895 "bar" since matching is always performed after the previous item of the
901 Matches an Ethernet header.
903 The ``type`` field either stands for "EtherType" or "TPID" when followed by
904 so-called layer 2.5 pattern items such as ``RTE_FLOW_ITEM_TYPE_VLAN``. In
905 the latter case, ``type`` refers to that of the outer header, with the inner
906 EtherType/TPID provided by the subsequent pattern item. This is the same
907 order as on the wire.
908 If the ``type`` field contains a TPID value, then only tagged packets with the
909 specified TPID will match the pattern.
910 Otherwise, only untagged packets will match the pattern.
911 If the ``ETH`` item is the only item in the pattern, and the ``type`` field is
912 not specified, then both tagged and untagged packets will match the pattern.
914 - ``dst``: destination MAC.
915 - ``src``: source MAC.
916 - ``type``: EtherType or TPID.
917 - Default ``mask`` matches destination and source addresses only.
922 Matches an 802.1Q/ad VLAN tag.
924 The corresponding standard outer EtherType (TPID) values are
925 ``RTE_ETHER_TYPE_VLAN`` or ``RTE_ETHER_TYPE_QINQ``. It can be overridden by the
926 preceding pattern item.
927 If a ``VLAN`` item is present in the pattern, then only tagged packets will
930 - ``tci``: tag control information.
931 - ``inner_type``: inner EtherType or TPID.
932 - Default ``mask`` matches the VID part of TCI only (lower 12 bits).
937 Matches an IPv4 header.
939 Note: IPv4 options are handled by dedicated pattern items.
941 - ``hdr``: IPv4 header definition (``rte_ip.h``).
942 - Default ``mask`` matches source and destination addresses only.
947 Matches an IPv6 header.
949 Note: IPv6 options are handled by dedicated pattern items, see `Item:
952 - ``hdr``: IPv6 header definition (``rte_ip.h``).
953 - Default ``mask`` matches source and destination addresses only.
958 Matches an ICMP header.
960 - ``hdr``: ICMP header definition (``rte_icmp.h``).
961 - Default ``mask`` matches ICMP type and code only.
966 Matches a UDP header.
968 - ``hdr``: UDP header definition (``rte_udp.h``).
969 - Default ``mask`` matches source and destination ports only.
974 Matches a TCP header.
976 - ``hdr``: TCP header definition (``rte_tcp.h``).
977 - Default ``mask`` matches source and destination ports only.
982 Matches a SCTP header.
984 - ``hdr``: SCTP header definition (``rte_sctp.h``).
985 - Default ``mask`` matches source and destination ports only.
990 Matches a VXLAN header (RFC 7348).
992 - ``flags``: normally 0x08 (I flag).
993 - ``rsvd0``: reserved, normally 0x000000.
994 - ``vni``: VXLAN network identifier.
995 - ``rsvd1``: reserved, normally 0x00.
996 - Default ``mask`` matches VNI only.
1001 Matches an IEEE 802.1BR E-Tag header.
1003 The corresponding standard outer EtherType (TPID) value is
1004 ``RTE_ETHER_TYPE_ETAG``. It can be overridden by the preceding pattern item.
1006 - ``epcp_edei_in_ecid_b``: E-Tag control information (E-TCI), E-PCP (3b),
1007 E-DEI (1b), ingress E-CID base (12b).
1008 - ``rsvd_grp_ecid_b``: reserved (2b), GRP (2b), E-CID base (12b).
1009 - ``in_ecid_e``: ingress E-CID ext.
1010 - ``ecid_e``: E-CID ext.
1011 - ``inner_type``: inner EtherType or TPID.
1012 - Default ``mask`` simultaneously matches GRP and E-CID base.
1017 Matches a NVGRE header (RFC 7637).
1019 - ``c_k_s_rsvd0_ver``: checksum (1b), undefined (1b), key bit (1b),
1020 sequence number (1b), reserved 0 (9b), version (3b). This field must have
1021 value 0x2000 according to RFC 7637.
1022 - ``protocol``: protocol type (0x6558).
1023 - ``tni``: virtual subnet ID.
1024 - ``flow_id``: flow ID.
1025 - Default ``mask`` matches TNI only.
1030 Matches a MPLS header.
1032 - ``label_tc_s_ttl``: label, TC, Bottom of Stack and TTL.
1033 - Default ``mask`` matches label only.
1038 Matches a GRE header.
1040 - ``c_rsvd0_ver``: checksum, reserved 0 and version.
1041 - ``protocol``: protocol type.
1042 - Default ``mask`` matches protocol only.
1047 Matches a GRE key field.
1048 This should be preceded by item ``GRE``.
1050 - Value to be matched is a big-endian 32 bit integer.
1051 - When this item present it implicitly match K bit in default mask as "1"
1056 Fuzzy pattern match, expect faster than default.
1058 This is for device that support fuzzy match option. Usually a fuzzy match is
1059 fast but the cost is accuracy. i.e. Signature Match only match pattern's hash
1060 value, but it is possible two different patterns have the same hash value.
1062 Matching accuracy level can be configured by threshold. Driver can divide the
1063 range of threshold and map to different accuracy levels that device support.
1065 Threshold 0 means perfect match (no fuzziness), while threshold 0xffffffff
1066 means fuzziest match.
1068 .. _table_rte_flow_item_fuzzy:
1072 +----------+---------------+--------------------------------------------------+
1073 | Field | Subfield | Value |
1074 +==========+===============+==================================================+
1075 | ``spec`` | ``threshold`` | 0 as perfect match, 0xffffffff as fuzziest match |
1076 +----------+---------------+--------------------------------------------------+
1077 | ``last`` | ``threshold`` | upper range value |
1078 +----------+---------------+--------------------------------------------------+
1079 | ``mask`` | ``threshold`` | bit-mask apply to "spec" and "last" |
1080 +----------+---------------+--------------------------------------------------+
1082 Usage example, fuzzy match a TCPv4 packets:
1084 .. _table_rte_flow_item_fuzzy_example:
1086 .. table:: Fuzzy matching
1088 +-------+----------+
1090 +=======+==========+
1092 +-------+----------+
1094 +-------+----------+
1096 +-------+----------+
1098 +-------+----------+
1100 +-------+----------+
1102 Item: ``GTP``, ``GTPC``, ``GTPU``
1103 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1105 Matches a GTPv1 header.
1107 Note: GTP, GTPC and GTPU use the same structure. GTPC and GTPU item
1108 are defined for a user-friendly API when creating GTP-C and GTP-U
1111 - ``v_pt_rsv_flags``: version (3b), protocol type (1b), reserved (1b),
1112 extension header flag (1b), sequence number flag (1b), N-PDU number
1114 - ``msg_type``: message type.
1115 - ``msg_len``: message length.
1116 - ``teid``: tunnel endpoint identifier.
1117 - Default ``mask`` matches teid only.
1122 Matches an ESP header.
1124 - ``hdr``: ESP header definition (``rte_esp.h``).
1125 - Default ``mask`` matches SPI only.
1130 Matches a GENEVE header.
1132 - ``ver_opt_len_o_c_rsvd0``: version (2b), length of the options fields (6b),
1133 OAM packet (1b), critical options present (1b), reserved 0 (6b).
1134 - ``protocol``: protocol type.
1135 - ``vni``: virtual network identifier.
1136 - ``rsvd1``: reserved, normally 0x00.
1137 - Default ``mask`` matches VNI only.
1142 Matches a VXLAN-GPE header (draft-ietf-nvo3-vxlan-gpe-05).
1144 - ``flags``: normally 0x0C (I and P flags).
1145 - ``rsvd0``: reserved, normally 0x0000.
1146 - ``protocol``: protocol type.
1147 - ``vni``: VXLAN network identifier.
1148 - ``rsvd1``: reserved, normally 0x00.
1149 - Default ``mask`` matches VNI only.
1151 Item: ``ARP_ETH_IPV4``
1152 ^^^^^^^^^^^^^^^^^^^^^^
1154 Matches an ARP header for Ethernet/IPv4.
1156 - ``hdr``: hardware type, normally 1.
1157 - ``pro``: protocol type, normally 0x0800.
1158 - ``hln``: hardware address length, normally 6.
1159 - ``pln``: protocol address length, normally 4.
1160 - ``op``: opcode (1 for request, 2 for reply).
1161 - ``sha``: sender hardware address.
1162 - ``spa``: sender IPv4 address.
1163 - ``tha``: target hardware address.
1164 - ``tpa``: target IPv4 address.
1165 - Default ``mask`` matches SHA, SPA, THA and TPA.
1170 Matches the presence of any IPv6 extension header.
1172 - ``next_hdr``: next header.
1173 - Default ``mask`` matches ``next_hdr``.
1175 Normally preceded by any of:
1183 Matches any ICMPv6 header.
1185 - ``type``: ICMPv6 type.
1186 - ``code``: ICMPv6 code.
1187 - ``checksum``: ICMPv6 checksum.
1188 - Default ``mask`` matches ``type`` and ``code``.
1190 Item: ``ICMP6_ND_NS``
1191 ^^^^^^^^^^^^^^^^^^^^^
1193 Matches an ICMPv6 neighbor discovery solicitation.
1195 - ``type``: ICMPv6 type, normally 135.
1196 - ``code``: ICMPv6 code, normally 0.
1197 - ``checksum``: ICMPv6 checksum.
1198 - ``reserved``: reserved, normally 0.
1199 - ``target_addr``: target address.
1200 - Default ``mask`` matches target address only.
1202 Item: ``ICMP6_ND_NA``
1203 ^^^^^^^^^^^^^^^^^^^^^
1205 Matches an ICMPv6 neighbor discovery advertisement.
1207 - ``type``: ICMPv6 type, normally 136.
1208 - ``code``: ICMPv6 code, normally 0.
1209 - ``checksum``: ICMPv6 checksum.
1210 - ``rso_reserved``: route flag (1b), solicited flag (1b), override flag
1211 (1b), reserved (29b).
1212 - ``target_addr``: target address.
1213 - Default ``mask`` matches target address only.
1215 Item: ``ICMP6_ND_OPT``
1216 ^^^^^^^^^^^^^^^^^^^^^^
1218 Matches the presence of any ICMPv6 neighbor discovery option.
1220 - ``type``: ND option type.
1221 - ``length``: ND option length.
1222 - Default ``mask`` matches type only.
1224 Normally preceded by any of:
1226 - `Item: ICMP6_ND_NA`_
1227 - `Item: ICMP6_ND_NS`_
1228 - `Item: ICMP6_ND_OPT`_
1230 Item: ``ICMP6_ND_OPT_SLA_ETH``
1231 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1233 Matches an ICMPv6 neighbor discovery source Ethernet link-layer address
1236 - ``type``: ND option type, normally 1.
1237 - ``length``: ND option length, normally 1.
1238 - ``sla``: source Ethernet LLA.
1239 - Default ``mask`` matches source link-layer address only.
1241 Normally preceded by any of:
1243 - `Item: ICMP6_ND_NA`_
1244 - `Item: ICMP6_ND_OPT`_
1246 Item: ``ICMP6_ND_OPT_TLA_ETH``
1247 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1249 Matches an ICMPv6 neighbor discovery target Ethernet link-layer address
1252 - ``type``: ND option type, normally 2.
1253 - ``length``: ND option length, normally 1.
1254 - ``tla``: target Ethernet LLA.
1255 - Default ``mask`` matches target link-layer address only.
1257 Normally preceded by any of:
1259 - `Item: ICMP6_ND_NS`_
1260 - `Item: ICMP6_ND_OPT`_
1265 Matches an application specific 32 bit metadata item.
1267 - Default ``mask`` matches the specified metadata value.
1272 Matches a GTP PDU extension header with type 0x85.
1274 - ``pdu_type``: PDU type.
1275 - ``qfi``: QoS flow identifier.
1276 - Default ``mask`` matches QFI only.
1278 Item: ``PPPOES``, ``PPPOED``
1279 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1281 Matches a PPPoE header.
1283 - ``version_type``: version (4b), type (4b).
1284 - ``code``: message type.
1285 - ``session_id``: session identifier.
1286 - ``length``: payload length.
1288 Item: ``PPPOE_PROTO_ID``
1289 ^^^^^^^^^^^^^^^^^^^^^^^^
1291 Matches a PPPoE session protocol identifier.
1293 - ``proto_id``: PPP protocol identifier.
1294 - Default ``mask`` matches proto_id only.
1299 Matches a network service header (RFC 8300).
1301 - ``version``: normally 0x0 (2 bits).
1302 - ``oam_pkt``: indicate oam packet (1 bit).
1303 - ``reserved``: reserved bit (1 bit).
1304 - ``ttl``: maximum SFF hopes (6 bits).
1305 - ``length``: total length in 4 bytes words (6 bits).
1306 - ``reserved1``: reserved1 bits (4 bits).
1307 - ``mdtype``: ndicates format of NSH header (4 bits).
1308 - ``next_proto``: indicates protocol type of encap data (8 bits).
1309 - ``spi``: service path identifier (3 bytes).
1310 - ``sindex``: service index (1 byte).
1311 - Default ``mask`` matches mdtype, next_proto, spi, sindex.
1317 Matches a Internet Group Management Protocol (RFC 2236).
1319 - ``type``: IGMP message type (Query/Report).
1320 - ``max_resp_time``: max time allowed before sending report.
1321 - ``checksum``: checksum, 1s complement of whole IGMP message.
1322 - ``group_addr``: group address, for Query value will be 0.
1323 - Default ``mask`` matches group_addr.
1329 Matches a IP Authentication Header (RFC 4302).
1331 - ``next_hdr``: next payload after AH.
1332 - ``payload_len``: total length of AH in 4B words.
1333 - ``reserved``: reserved bits.
1334 - ``spi``: security parameters index.
1335 - ``seq_num``: counter value increased by 1 on each packet sent.
1336 - Default ``mask`` matches spi.
1341 Matches a HIGIG2 header field. It is layer 2.5 protocol and used in
1344 - Default ``mask`` matches classification and vlan.
1349 Matches a L2TPv3 over IP header.
1351 - ``session_id``: L2TPv3 over IP session identifier.
1352 - Default ``mask`` matches session_id only.
1357 Matches a PFCP Header.
1359 - ``s_field``: S field.
1360 - ``msg_type``: message type.
1361 - ``msg_len``: message length.
1362 - ``seid``: session endpoint identifier.
1363 - Default ``mask`` matches s_field and seid.
1368 Matches a eCPRI header.
1370 - ``hdr``: eCPRI header definition (``rte_ecpri.h``).
1371 - Default ``mask`` matches nothing, for all eCPRI messages.
1376 Each possible action is represented by a type.
1377 An action can have an associated configuration object.
1378 Several actions combined in a list can be assigned
1379 to a flow rule and are performed in order.
1381 They fall in three categories:
1383 - Actions that modify the fate of matching traffic, for instance by dropping
1384 or assigning it a specific destination.
1386 - Actions that modify matching traffic contents or its properties. This
1387 includes adding/removing encapsulation, encryption, compression and marks.
1389 - Actions related to the flow rule itself, such as updating counters or
1390 making it non-terminating.
1392 Flow rules being terminating by default, not specifying any action of the
1393 fate kind results in undefined behavior. This applies to both ingress and
1396 PASSTHRU, when supported, makes a flow rule non-terminating.
1398 Like matching patterns, action lists are terminated by END items.
1400 Example of action that redirects packets to queue index 10:
1402 .. _table_rte_flow_action_example:
1404 .. table:: Queue action
1406 +-----------+-------+
1408 +===========+=======+
1410 +-----------+-------+
1412 Actions are performed in list order:
1414 .. _table_rte_flow_count_then_drop:
1416 .. table:: Count then drop
1430 .. _table_rte_flow_mark_count_redirect:
1432 .. table:: Mark, count then redirect
1434 +-------+--------+------------+-------+
1435 | Index | Action | Field | Value |
1436 +=======+========+============+=======+
1437 | 0 | MARK | ``mark`` | 0x2a |
1438 +-------+--------+------------+-------+
1439 | 1 | COUNT | ``shared`` | 0 |
1440 | | +------------+-------+
1442 +-------+--------+------------+-------+
1443 | 2 | QUEUE | ``queue`` | 10 |
1444 +-------+--------+------------+-------+
1446 +-------+-----------------------------+
1450 .. _table_rte_flow_redirect_queue_5:
1452 .. table:: Redirect to queue 5
1454 +-------+--------+-----------+-------+
1455 | Index | Action | Field | Value |
1456 +=======+========+===========+=======+
1458 +-------+--------+-----------+-------+
1459 | 1 | QUEUE | ``queue`` | 5 |
1460 +-------+--------+-----------+-------+
1462 +-------+----------------------------+
1464 In the above example, while DROP and QUEUE must be performed in order, both
1465 have to happen before reaching END. Only QUEUE has a visible effect.
1467 Note that such a list may be thought as ambiguous and rejected on that
1470 .. _table_rte_flow_redirect_queue_5_3:
1472 .. table:: Redirect to queues 5 and 3
1474 +-------+--------+-----------+-------+
1475 | Index | Action | Field | Value |
1476 +=======+========+===========+=======+
1477 | 0 | QUEUE | ``queue`` | 5 |
1478 +-------+--------+-----------+-------+
1480 +-------+--------+-----------+-------+
1481 | 2 | QUEUE | ``queue`` | 3 |
1482 +-------+--------+-----------+-------+
1484 +-------+----------------------------+
1486 As previously described, all actions must be taken into account. This
1487 effectively duplicates traffic to both queues. The above example also shows
1488 that VOID is ignored.
1493 Common action types are described in this section. Like pattern item types,
1494 this list is not exhaustive as new actions will be added in the future.
1499 End marker for action lists. Prevents further processing of actions, thereby
1502 - Its numeric value is 0 for convenience.
1503 - PMD support is mandatory.
1504 - No configurable properties.
1506 .. _table_rte_flow_action_end:
1519 Used as a placeholder for convenience. It is ignored and simply discarded by
1522 - PMD support is mandatory.
1523 - No configurable properties.
1525 .. _table_rte_flow_action_void:
1535 Action: ``PASSTHRU``
1536 ^^^^^^^^^^^^^^^^^^^^
1538 Leaves traffic up for additional processing by subsequent flow rules; makes
1539 a flow rule non-terminating.
1541 - No configurable properties.
1543 .. _table_rte_flow_action_passthru:
1553 Example to copy a packet to a queue and continue processing by subsequent
1556 .. _table_rte_flow_action_passthru_example:
1558 .. table:: Copy to queue 8
1560 +-------+--------+-----------+-------+
1561 | Index | Action | Field | Value |
1562 +=======+========+===========+=======+
1564 +-------+--------+-----------+-------+
1565 | 1 | QUEUE | ``queue`` | 8 |
1566 +-------+--------+-----------+-------+
1568 +-------+----------------------------+
1573 Redirects packets to a group on the current device.
1575 In a hierarchy of groups, which can be used to represent physical or logical
1576 flow group/tables on the device, this action redirects the matched flow to
1577 the specified group on that device.
1579 If a matched flow is redirected to a table which doesn't contain a matching
1580 rule for that flow then the behavior is undefined and the resulting behavior
1581 is up to the specific device. Best practice when using groups would be define
1582 a default flow rule for each group which a defines the default actions in that
1583 group so a consistent behavior is defined.
1585 Defining an action for matched flow in a group to jump to a group which is
1586 higher in the group hierarchy may not be supported by physical devices,
1587 depending on how groups are mapped to the physical devices. In the
1588 definitions of jump actions, applications should be aware that it may be
1589 possible to define flow rules which trigger an undefined behavior causing
1590 flows to loop between groups.
1592 .. _table_rte_flow_action_jump:
1596 +-----------+------------------------------+
1598 +===========+==============================+
1599 | ``group`` | Group to redirect packets to |
1600 +-----------+------------------------------+
1605 Attaches an integer value to packets and sets ``PKT_RX_FDIR`` and
1606 ``PKT_RX_FDIR_ID`` mbuf flags.
1608 This value is arbitrary and application-defined. Maximum allowed value
1609 depends on the underlying implementation. It is returned in the
1610 ``hash.fdir.hi`` mbuf field.
1612 .. _table_rte_flow_action_mark:
1616 +--------+--------------------------------------+
1618 +========+======================================+
1619 | ``id`` | integer value to return with packets |
1620 +--------+--------------------------------------+
1625 Flags packets. Similar to `Action: MARK`_ without a specific value; only
1626 sets the ``PKT_RX_FDIR`` mbuf flag.
1628 - No configurable properties.
1630 .. _table_rte_flow_action_flag:
1643 Assigns packets to a given queue index.
1645 .. _table_rte_flow_action_queue:
1649 +-----------+--------------------+
1651 +===========+====================+
1652 | ``index`` | queue index to use |
1653 +-----------+--------------------+
1660 - No configurable properties.
1662 .. _table_rte_flow_action_drop:
1675 Adds a counter action to a matched flow.
1677 If more than one count action is specified in a single flow rule, then each
1678 action must specify a unique id.
1680 Counters can be retrieved and reset through ``rte_flow_query()``, see
1681 ``struct rte_flow_query_count``.
1683 The shared flag indicates whether the counter is unique to the flow rule the
1684 action is specified with, or whether it is a shared counter.
1686 For a count action with the shared flag set, then a global device
1687 namespace is assumed for the counter id, so that any matched flow rules using
1688 a count action with the same counter id on the same port will contribute to
1691 For ports within the same switch domain then the counter id namespace extends
1692 to all ports within that switch domain.
1694 .. _table_rte_flow_action_count:
1698 +------------+---------------------+
1700 +============+=====================+
1701 | ``shared`` | shared counter flag |
1702 +------------+---------------------+
1703 | ``id`` | counter id |
1704 +------------+---------------------+
1706 Query structure to retrieve and reset flow rule counters:
1708 .. _table_rte_flow_query_count:
1710 .. table:: COUNT query
1712 +---------------+-----+-----------------------------------+
1713 | Field | I/O | Value |
1714 +===============+=====+===================================+
1715 | ``reset`` | in | reset counter after query |
1716 +---------------+-----+-----------------------------------+
1717 | ``hits_set`` | out | ``hits`` field is set |
1718 +---------------+-----+-----------------------------------+
1719 | ``bytes_set`` | out | ``bytes`` field is set |
1720 +---------------+-----+-----------------------------------+
1721 | ``hits`` | out | number of hits for this rule |
1722 +---------------+-----+-----------------------------------+
1723 | ``bytes`` | out | number of bytes through this rule |
1724 +---------------+-----+-----------------------------------+
1729 Similar to QUEUE, except RSS is additionally performed on packets to spread
1730 them among several queues according to the provided parameters.
1732 Unlike global RSS settings used by other DPDK APIs, unsetting the ``types``
1733 field does not disable RSS in a flow rule. Doing so instead requests safe
1734 unspecified "best-effort" settings from the underlying PMD, which depending
1735 on the flow rule, may result in anything ranging from empty (single queue)
1736 to all-inclusive RSS.
1738 If non-applicable for matching packets RSS types are requested,
1739 these RSS types are simply ignored. For example, it happens if:
1741 - Hashing of both TCP and UDP ports is requested
1742 (only one can be present in a packet).
1744 - Requested RSS types contradict to flow rule pattern
1745 (e.g. pattern has UDP item, but RSS types contain TCP).
1747 If requested RSS hash types are not supported by the Ethernet device at all
1748 (not reported in ``dev_info.flow_tpe_rss_offloads``),
1749 the flow creation will fail.
1751 Note: RSS hash result is stored in the ``hash.rss`` mbuf field which
1752 overlaps ``hash.fdir.lo``. Since `Action: MARK`_ sets the ``hash.fdir.hi``
1753 field only, both can be requested simultaneously.
1755 Also, regarding packet encapsulation ``level``:
1757 - ``0`` requests the default behavior. Depending on the packet type, it can
1758 mean outermost, innermost, anything in between or even no RSS.
1760 It basically stands for the innermost encapsulation level RSS can be
1761 performed on according to PMD and device capabilities.
1763 - ``1`` requests RSS to be performed on the outermost packet encapsulation
1766 - ``2`` and subsequent values request RSS to be performed on the specified
1767 inner packet encapsulation level, from outermost to innermost (lower to
1770 Values other than ``0`` are not necessarily supported.
1772 Requesting a specific RSS level on unrecognized traffic results in undefined
1773 behavior. For predictable results, it is recommended to make the flow rule
1774 pattern match packet headers up to the requested encapsulation level so that
1775 only matching traffic goes through.
1777 .. _table_rte_flow_action_rss:
1781 +---------------+---------------------------------------------+
1783 +===============+=============================================+
1784 | ``func`` | RSS hash function to apply |
1785 +---------------+---------------------------------------------+
1786 | ``level`` | encapsulation level for ``types`` |
1787 +---------------+---------------------------------------------+
1788 | ``types`` | specific RSS hash types (see ``ETH_RSS_*``) |
1789 +---------------+---------------------------------------------+
1790 | ``key_len`` | hash key length in bytes |
1791 +---------------+---------------------------------------------+
1792 | ``queue_num`` | number of entries in ``queue`` |
1793 +---------------+---------------------------------------------+
1794 | ``key`` | hash key |
1795 +---------------+---------------------------------------------+
1796 | ``queue`` | queue indices to use |
1797 +---------------+---------------------------------------------+
1802 Directs matching traffic to the physical function (PF) of the current
1807 - No configurable properties.
1809 .. _table_rte_flow_action_pf:
1822 Directs matching traffic to a given virtual function of the current device.
1824 Packets matched by a VF pattern item can be redirected to their original VF
1825 ID instead of the specified one. This parameter may not be available and is
1826 not guaranteed to work properly if the VF part is matched by a prior flow
1827 rule or if packets are not addressed to a VF in the first place.
1831 .. _table_rte_flow_action_vf:
1835 +--------------+--------------------------------+
1837 +==============+================================+
1838 | ``original`` | use original VF ID if possible |
1839 +--------------+--------------------------------+
1841 +--------------+--------------------------------+
1843 Action: ``PHY_PORT``
1844 ^^^^^^^^^^^^^^^^^^^^
1846 Directs matching traffic to a given physical port index of the underlying
1849 See `Item: PHY_PORT`_.
1851 .. _table_rte_flow_action_phy_port:
1855 +--------------+-------------------------------------+
1857 +==============+=====================================+
1858 | ``original`` | use original port index if possible |
1859 +--------------+-------------------------------------+
1860 | ``index`` | physical port index |
1861 +--------------+-------------------------------------+
1865 Directs matching traffic to a given DPDK port ID.
1867 See `Item: PORT_ID`_.
1869 .. _table_rte_flow_action_port_id:
1873 +--------------+---------------------------------------+
1875 +==============+=======================================+
1876 | ``original`` | use original DPDK port ID if possible |
1877 +--------------+---------------------------------------+
1878 | ``id`` | DPDK port ID |
1879 +--------------+---------------------------------------+
1884 Applies a stage of metering and policing.
1886 The metering and policing (MTR) object has to be first created using the
1887 rte_mtr_create() API function. The ID of the MTR object is specified as
1888 action parameter. More than one flow can use the same MTR object through
1889 the meter action. The MTR object can be further updated or queried using
1892 .. _table_rte_flow_action_meter:
1896 +--------------+---------------+
1898 +==============+===============+
1899 | ``mtr_id`` | MTR object ID |
1900 +--------------+---------------+
1902 Action: ``SECURITY``
1903 ^^^^^^^^^^^^^^^^^^^^
1905 Perform the security action on flows matched by the pattern items
1906 according to the configuration of the security session.
1908 This action modifies the payload of matched flows. For INLINE_CRYPTO, the
1909 security protocol headers and IV are fully provided by the application as
1910 specified in the flow pattern. The payload of matching packets is
1911 encrypted on egress, and decrypted and authenticated on ingress.
1912 For INLINE_PROTOCOL, the security protocol is fully offloaded to HW,
1913 providing full encapsulation and decapsulation of packets in security
1914 protocols. The flow pattern specifies both the outer security header fields
1915 and the inner packet fields. The security session specified in the action
1916 must match the pattern parameters.
1918 The security session specified in the action must be created on the same
1919 port as the flow action that is being specified.
1921 The ingress/egress flow attribute should match that specified in the
1922 security session if the security session supports the definition of the
1925 Multiple flows can be configured to use the same security session.
1927 .. _table_rte_flow_action_security:
1931 +----------------------+--------------------------------------+
1933 +======================+======================================+
1934 | ``security_session`` | security session to apply |
1935 +----------------------+--------------------------------------+
1937 The following is an example of configuring IPsec inline using the
1938 INLINE_CRYPTO security session:
1940 The encryption algorithm, keys and salt are part of the opaque
1941 ``rte_security_session``. The SA is identified according to the IP and ESP
1942 fields in the pattern items.
1944 .. _table_rte_flow_item_esp_inline_example:
1946 .. table:: IPsec inline crypto flow pattern items.
1948 +-------+----------+
1950 +=======+==========+
1952 +-------+----------+
1954 +-------+----------+
1956 +-------+----------+
1958 +-------+----------+
1960 .. _table_rte_flow_action_esp_inline_example:
1962 .. table:: IPsec inline flow actions.
1964 +-------+----------+
1966 +=======+==========+
1968 +-------+----------+
1970 +-------+----------+
1972 Action: ``OF_SET_MPLS_TTL``
1973 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
1975 Implements ``OFPAT_SET_MPLS_TTL`` ("MPLS TTL") as defined by the `OpenFlow
1976 Switch Specification`_.
1978 .. _table_rte_flow_action_of_set_mpls_ttl:
1980 .. table:: OF_SET_MPLS_TTL
1982 +--------------+----------+
1984 +==============+==========+
1985 | ``mpls_ttl`` | MPLS TTL |
1986 +--------------+----------+
1988 Action: ``OF_DEC_MPLS_TTL``
1989 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
1991 Implements ``OFPAT_DEC_MPLS_TTL`` ("decrement MPLS TTL") as defined by the
1992 `OpenFlow Switch Specification`_.
1994 .. _table_rte_flow_action_of_dec_mpls_ttl:
1996 .. table:: OF_DEC_MPLS_TTL
2004 Action: ``OF_SET_NW_TTL``
2005 ^^^^^^^^^^^^^^^^^^^^^^^^^
2007 Implements ``OFPAT_SET_NW_TTL`` ("IP TTL") as defined by the `OpenFlow
2008 Switch Specification`_.
2010 .. _table_rte_flow_action_of_set_nw_ttl:
2012 .. table:: OF_SET_NW_TTL
2014 +------------+--------+
2016 +============+========+
2017 | ``nw_ttl`` | IP TTL |
2018 +------------+--------+
2020 Action: ``OF_DEC_NW_TTL``
2021 ^^^^^^^^^^^^^^^^^^^^^^^^^
2023 Implements ``OFPAT_DEC_NW_TTL`` ("decrement IP TTL") as defined by the
2024 `OpenFlow Switch Specification`_.
2026 .. _table_rte_flow_action_of_dec_nw_ttl:
2028 .. table:: OF_DEC_NW_TTL
2036 Action: ``OF_COPY_TTL_OUT``
2037 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
2039 Implements ``OFPAT_COPY_TTL_OUT`` ("copy TTL "outwards" -- from
2040 next-to-outermost to outermost") as defined by the `OpenFlow Switch
2043 .. _table_rte_flow_action_of_copy_ttl_out:
2045 .. table:: OF_COPY_TTL_OUT
2053 Action: ``OF_COPY_TTL_IN``
2054 ^^^^^^^^^^^^^^^^^^^^^^^^^^
2056 Implements ``OFPAT_COPY_TTL_IN`` ("copy TTL "inwards" -- from outermost to
2057 next-to-outermost") as defined by the `OpenFlow Switch Specification`_.
2059 .. _table_rte_flow_action_of_copy_ttl_in:
2061 .. table:: OF_COPY_TTL_IN
2069 Action: ``OF_POP_VLAN``
2070 ^^^^^^^^^^^^^^^^^^^^^^^
2072 Implements ``OFPAT_POP_VLAN`` ("pop the outer VLAN tag") as defined
2073 by the `OpenFlow Switch Specification`_.
2075 .. _table_rte_flow_action_of_pop_vlan:
2077 .. table:: OF_POP_VLAN
2085 Action: ``OF_PUSH_VLAN``
2086 ^^^^^^^^^^^^^^^^^^^^^^^^
2088 Implements ``OFPAT_PUSH_VLAN`` ("push a new VLAN tag") as defined by the
2089 `OpenFlow Switch Specification`_.
2091 .. _table_rte_flow_action_of_push_vlan:
2093 .. table:: OF_PUSH_VLAN
2095 +---------------+-----------+
2097 +===============+===========+
2098 | ``ethertype`` | EtherType |
2099 +---------------+-----------+
2101 Action: ``OF_SET_VLAN_VID``
2102 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
2104 Implements ``OFPAT_SET_VLAN_VID`` ("set the 802.1q VLAN id") as defined by
2105 the `OpenFlow Switch Specification`_.
2107 .. _table_rte_flow_action_of_set_vlan_vid:
2109 .. table:: OF_SET_VLAN_VID
2111 +--------------+---------+
2113 +==============+=========+
2114 | ``vlan_vid`` | VLAN id |
2115 +--------------+---------+
2117 Action: ``OF_SET_VLAN_PCP``
2118 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
2120 Implements ``OFPAT_SET_LAN_PCP`` ("set the 802.1q priority") as defined by
2121 the `OpenFlow Switch Specification`_.
2123 .. _table_rte_flow_action_of_set_vlan_pcp:
2125 .. table:: OF_SET_VLAN_PCP
2127 +--------------+---------------+
2129 +==============+===============+
2130 | ``vlan_pcp`` | VLAN priority |
2131 +--------------+---------------+
2133 Action: ``OF_POP_MPLS``
2134 ^^^^^^^^^^^^^^^^^^^^^^^
2136 Implements ``OFPAT_POP_MPLS`` ("pop the outer MPLS tag") as defined by the
2137 `OpenFlow Switch Specification`_.
2139 .. _table_rte_flow_action_of_pop_mpls:
2141 .. table:: OF_POP_MPLS
2143 +---------------+-----------+
2145 +===============+===========+
2146 | ``ethertype`` | EtherType |
2147 +---------------+-----------+
2149 Action: ``OF_PUSH_MPLS``
2150 ^^^^^^^^^^^^^^^^^^^^^^^^
2152 Implements ``OFPAT_PUSH_MPLS`` ("push a new MPLS tag") as defined by the
2153 `OpenFlow Switch Specification`_.
2155 .. _table_rte_flow_action_of_push_mpls:
2157 .. table:: OF_PUSH_MPLS
2159 +---------------+-----------+
2161 +===============+===========+
2162 | ``ethertype`` | EtherType |
2163 +---------------+-----------+
2165 Action: ``VXLAN_ENCAP``
2166 ^^^^^^^^^^^^^^^^^^^^^^^
2168 Performs a VXLAN encapsulation action by encapsulating the matched flow in the
2169 VXLAN tunnel as defined in the``rte_flow_action_vxlan_encap`` flow items
2172 This action modifies the payload of matched flows. The flow definition specified
2173 in the ``rte_flow_action_tunnel_encap`` action structure must define a valid
2174 VLXAN network overlay which conforms with RFC 7348 (Virtual eXtensible Local
2175 Area Network (VXLAN): A Framework for Overlaying Virtualized Layer 2 Networks
2176 over Layer 3 Networks). The pattern must be terminated with the
2177 RTE_FLOW_ITEM_TYPE_END item type.
2179 .. _table_rte_flow_action_vxlan_encap:
2181 .. table:: VXLAN_ENCAP
2183 +----------------+-------------------------------------+
2185 +================+=====================================+
2186 | ``definition`` | Tunnel end-point overlay definition |
2187 +----------------+-------------------------------------+
2189 .. _table_rte_flow_action_vxlan_encap_example:
2191 .. table:: IPv4 VxLAN flow pattern example.
2193 +-------+----------+
2195 +=======+==========+
2197 +-------+----------+
2199 +-------+----------+
2201 +-------+----------+
2203 +-------+----------+
2205 +-------+----------+
2207 Action: ``VXLAN_DECAP``
2208 ^^^^^^^^^^^^^^^^^^^^^^^
2210 Performs a decapsulation action by stripping all headers of the VXLAN tunnel
2211 network overlay from the matched flow.
2213 The flow items pattern defined for the flow rule with which a ``VXLAN_DECAP``
2214 action is specified, must define a valid VXLAN tunnel as per RFC7348. If the
2215 flow pattern does not specify a valid VXLAN tunnel then a
2216 RTE_FLOW_ERROR_TYPE_ACTION error should be returned.
2218 This action modifies the payload of matched flows.
2220 Action: ``NVGRE_ENCAP``
2221 ^^^^^^^^^^^^^^^^^^^^^^^
2223 Performs a NVGRE encapsulation action by encapsulating the matched flow in the
2224 NVGRE tunnel as defined in the``rte_flow_action_tunnel_encap`` flow item
2227 This action modifies the payload of matched flows. The flow definition specified
2228 in the ``rte_flow_action_tunnel_encap`` action structure must defined a valid
2229 NVGRE network overlay which conforms with RFC 7637 (NVGRE: Network
2230 Virtualization Using Generic Routing Encapsulation). The pattern must be
2231 terminated with the RTE_FLOW_ITEM_TYPE_END item type.
2233 .. _table_rte_flow_action_nvgre_encap:
2235 .. table:: NVGRE_ENCAP
2237 +----------------+-------------------------------------+
2239 +================+=====================================+
2240 | ``definition`` | NVGRE end-point overlay definition |
2241 +----------------+-------------------------------------+
2243 .. _table_rte_flow_action_nvgre_encap_example:
2245 .. table:: IPv4 NVGRE flow pattern example.
2247 +-------+----------+
2249 +=======+==========+
2251 +-------+----------+
2253 +-------+----------+
2255 +-------+----------+
2257 +-------+----------+
2259 Action: ``NVGRE_DECAP``
2260 ^^^^^^^^^^^^^^^^^^^^^^^
2262 Performs a decapsulation action by stripping all headers of the NVGRE tunnel
2263 network overlay from the matched flow.
2265 The flow items pattern defined for the flow rule with which a ``NVGRE_DECAP``
2266 action is specified, must define a valid NVGRE tunnel as per RFC7637. If the
2267 flow pattern does not specify a valid NVGRE tunnel then a
2268 RTE_FLOW_ERROR_TYPE_ACTION error should be returned.
2270 This action modifies the payload of matched flows.
2272 Action: ``RAW_ENCAP``
2273 ^^^^^^^^^^^^^^^^^^^^^
2275 Adds outer header whose template is provided in its data buffer,
2276 as defined in the ``rte_flow_action_raw_encap`` definition.
2278 This action modifies the payload of matched flows. The data supplied must
2279 be a valid header, either holding layer 2 data in case of adding layer 2 after
2280 decap layer 3 tunnel (for example MPLSoGRE) or complete tunnel definition
2281 starting from layer 2 and moving to the tunnel item itself. When applied to
2282 the original packet the resulting packet must be a valid packet.
2284 .. _table_rte_flow_action_raw_encap:
2286 .. table:: RAW_ENCAP
2288 +----------------+----------------------------------------+
2290 +================+========================================+
2291 | ``data`` | Encapsulation data |
2292 +----------------+----------------------------------------+
2293 | ``preserve`` | Bit-mask of data to preserve on output |
2294 +----------------+----------------------------------------+
2295 | ``size`` | Size of data and preserve |
2296 +----------------+----------------------------------------+
2298 Action: ``RAW_DECAP``
2299 ^^^^^^^^^^^^^^^^^^^^^^^
2301 Remove outer header whose template is provided in its data buffer,
2302 as defined in the ``rte_flow_action_raw_decap``
2304 This action modifies the payload of matched flows. The data supplied must
2305 be a valid header, either holding layer 2 data in case of removing layer 2
2306 before encapsulation of layer 3 tunnel (for example MPLSoGRE) or complete
2307 tunnel definition starting from layer 2 and moving to the tunnel item itself.
2308 When applied to the original packet the resulting packet must be a
2311 .. _table_rte_flow_action_raw_decap:
2313 .. table:: RAW_DECAP
2315 +----------------+----------------------------------------+
2317 +================+========================================+
2318 | ``data`` | Decapsulation data |
2319 +----------------+----------------------------------------+
2320 | ``size`` | Size of data |
2321 +----------------+----------------------------------------+
2323 Action: ``SET_IPV4_SRC``
2324 ^^^^^^^^^^^^^^^^^^^^^^^^
2326 Set a new IPv4 source address in the outermost IPv4 header.
2328 It must be used with a valid RTE_FLOW_ITEM_TYPE_IPV4 flow pattern item.
2329 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2331 .. _table_rte_flow_action_set_ipv4_src:
2333 .. table:: SET_IPV4_SRC
2335 +-----------------------------------------+
2337 +===============+=========================+
2338 | ``ipv4_addr`` | new IPv4 source address |
2339 +---------------+-------------------------+
2341 Action: ``SET_IPV4_DST``
2342 ^^^^^^^^^^^^^^^^^^^^^^^^
2344 Set a new IPv4 destination address in the outermost IPv4 header.
2346 It must be used with a valid RTE_FLOW_ITEM_TYPE_IPV4 flow pattern item.
2347 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2349 .. _table_rte_flow_action_set_ipv4_dst:
2351 .. table:: SET_IPV4_DST
2353 +---------------+------------------------------+
2355 +===============+==============================+
2356 | ``ipv4_addr`` | new IPv4 destination address |
2357 +---------------+------------------------------+
2359 Action: ``SET_IPV6_SRC``
2360 ^^^^^^^^^^^^^^^^^^^^^^^^
2362 Set a new IPv6 source address in the outermost IPv6 header.
2364 It must be used with a valid RTE_FLOW_ITEM_TYPE_IPV6 flow pattern item.
2365 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2367 .. _table_rte_flow_action_set_ipv6_src:
2369 .. table:: SET_IPV6_SRC
2371 +---------------+-------------------------+
2373 +===============+=========================+
2374 | ``ipv6_addr`` | new IPv6 source address |
2375 +---------------+-------------------------+
2377 Action: ``SET_IPV6_DST``
2378 ^^^^^^^^^^^^^^^^^^^^^^^^
2380 Set a new IPv6 destination address in the outermost IPv6 header.
2382 It must be used with a valid RTE_FLOW_ITEM_TYPE_IPV6 flow pattern item.
2383 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2385 .. _table_rte_flow_action_set_ipv6_dst:
2387 .. table:: SET_IPV6_DST
2389 +---------------+------------------------------+
2391 +===============+==============================+
2392 | ``ipv6_addr`` | new IPv6 destination address |
2393 +---------------+------------------------------+
2395 Action: ``SET_TP_SRC``
2396 ^^^^^^^^^^^^^^^^^^^^^^^^^
2398 Set a new source port number in the outermost TCP/UDP header.
2400 It must be used with a valid RTE_FLOW_ITEM_TYPE_TCP or RTE_FLOW_ITEM_TYPE_UDP
2401 flow pattern item. Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2403 .. _table_rte_flow_action_set_tp_src:
2405 .. table:: SET_TP_SRC
2407 +----------+-------------------------+
2409 +==========+=========================+
2410 | ``port`` | new TCP/UDP source port |
2411 +---------------+--------------------+
2413 Action: ``SET_TP_DST``
2414 ^^^^^^^^^^^^^^^^^^^^^^^^^
2416 Set a new destination port number in the outermost TCP/UDP header.
2418 It must be used with a valid RTE_FLOW_ITEM_TYPE_TCP or RTE_FLOW_ITEM_TYPE_UDP
2419 flow pattern item. Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2421 .. _table_rte_flow_action_set_tp_dst:
2423 .. table:: SET_TP_DST
2425 +----------+------------------------------+
2427 +==========+==============================+
2428 | ``port`` | new TCP/UDP destination port |
2429 +---------------+-------------------------+
2431 Action: ``MAC_SWAP``
2432 ^^^^^^^^^^^^^^^^^^^^^^^^^
2434 Swap the source and destination MAC addresses in the outermost Ethernet
2437 It must be used with a valid RTE_FLOW_ITEM_TYPE_ETH flow pattern item.
2438 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2440 .. _table_rte_flow_action_mac_swap:
2455 If there is no valid RTE_FLOW_ITEM_TYPE_IPV4 or RTE_FLOW_ITEM_TYPE_IPV6
2456 in pattern, Some PMDs will reject rule because behavior will be undefined.
2458 .. _table_rte_flow_action_dec_ttl:
2471 Assigns a new TTL value.
2473 If there is no valid RTE_FLOW_ITEM_TYPE_IPV4 or RTE_FLOW_ITEM_TYPE_IPV6
2474 in pattern, Some PMDs will reject rule because behavior will be undefined.
2476 .. _table_rte_flow_action_set_ttl:
2480 +---------------+--------------------+
2482 +===============+====================+
2483 | ``ttl_value`` | new TTL value |
2484 +---------------+--------------------+
2486 Action: ``SET_MAC_SRC``
2487 ^^^^^^^^^^^^^^^^^^^^^^^
2489 Set source MAC address.
2491 It must be used with a valid RTE_FLOW_ITEM_TYPE_ETH flow pattern item.
2492 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2494 .. _table_rte_flow_action_set_mac_src:
2496 .. table:: SET_MAC_SRC
2498 +--------------+---------------+
2500 +==============+===============+
2501 | ``mac_addr`` | MAC address |
2502 +--------------+---------------+
2504 Action: ``SET_MAC_DST``
2505 ^^^^^^^^^^^^^^^^^^^^^^^
2507 Set destination MAC address.
2509 It must be used with a valid RTE_FLOW_ITEM_TYPE_ETH flow pattern item.
2510 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2512 .. _table_rte_flow_action_set_mac_dst:
2514 .. table:: SET_MAC_DST
2516 +--------------+---------------+
2518 +==============+===============+
2519 | ``mac_addr`` | MAC address |
2520 +--------------+---------------+
2522 Action: ``INC_TCP_SEQ``
2523 ^^^^^^^^^^^^^^^^^^^^^^^
2525 Increase sequence number in the outermost TCP header.
2526 Value to increase TCP sequence number by is a big-endian 32 bit integer.
2528 Using this action on non-matching traffic will result in undefined behavior.
2530 Action: ``DEC_TCP_SEQ``
2531 ^^^^^^^^^^^^^^^^^^^^^^^
2533 Decrease sequence number in the outermost TCP header.
2534 Value to decrease TCP sequence number by is a big-endian 32 bit integer.
2536 Using this action on non-matching traffic will result in undefined behavior.
2538 Action: ``INC_TCP_ACK``
2539 ^^^^^^^^^^^^^^^^^^^^^^^
2541 Increase acknowledgment number in the outermost TCP header.
2542 Value to increase TCP acknowledgment number by is a big-endian 32 bit integer.
2544 Using this action on non-matching traffic will result in undefined behavior.
2546 Action: ``DEC_TCP_ACK``
2547 ^^^^^^^^^^^^^^^^^^^^^^^
2549 Decrease acknowledgment number in the outermost TCP header.
2550 Value to decrease TCP acknowledgment number by is a big-endian 32 bit integer.
2552 Using this action on non-matching traffic will result in undefined behavior.
2559 Tag is a transient data used during flow matching. This is not delivered to
2560 application. Multiple tags are supported by specifying index.
2562 .. _table_rte_flow_action_set_tag:
2566 +-----------+----------------------------+
2568 +===========+============================+
2569 | ``data`` | 32 bit tag value |
2570 +-----------+----------------------------+
2571 | ``mask`` | bit-mask applies to "data" |
2572 +-----------+----------------------------+
2573 | ``index`` | index of tag to set |
2574 +-----------+----------------------------+
2576 Action: ``SET_META``
2577 ^^^^^^^^^^^^^^^^^^^^^^^
2579 Set metadata. Item ``META`` matches metadata.
2581 Metadata set by mbuf metadata field with PKT_TX_DYNF_METADATA flag on egress
2582 will be overridden by this action. On ingress, the metadata will be carried by
2583 ``metadata`` dynamic field of ``rte_mbuf`` which can be accessed by
2584 ``RTE_FLOW_DYNF_METADATA()``. PKT_RX_DYNF_METADATA flag will be set along
2587 The mbuf dynamic field must be registered by calling
2588 ``rte_flow_dynf_metadata_register()`` prior to use ``SET_META`` action.
2590 Altering partial bits is supported with ``mask``. For bits which have never been
2591 set, unpredictable value will be seen depending on driver implementation. For
2592 loopback/hairpin packet, metadata set on Rx/Tx may or may not be propagated to
2593 the other path depending on HW capability.
2595 .. _table_rte_flow_action_set_meta:
2599 +----------+----------------------------+
2601 +==========+============================+
2602 | ``data`` | 32 bit metadata value |
2603 +----------+----------------------------+
2604 | ``mask`` | bit-mask applies to "data" |
2605 +----------+----------------------------+
2607 Action: ``SET_IPV4_DSCP``
2608 ^^^^^^^^^^^^^^^^^^^^^^^^^
2612 Modify DSCP in IPv4 header.
2614 It must be used with RTE_FLOW_ITEM_TYPE_IPV4 in pattern.
2615 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2617 .. _table_rte_flow_action_set_ipv4_dscp:
2619 .. table:: SET_IPV4_DSCP
2621 +-----------+---------------------------------+
2623 +===========+=================================+
2624 | ``dscp`` | DSCP in low 6 bits, rest ignore |
2625 +-----------+---------------------------------+
2627 Action: ``SET_IPV6_DSCP``
2628 ^^^^^^^^^^^^^^^^^^^^^^^^^
2632 Modify DSCP in IPv6 header.
2634 It must be used with RTE_FLOW_ITEM_TYPE_IPV6 in pattern.
2635 Otherwise, RTE_FLOW_ERROR_TYPE_ACTION error will be returned.
2637 .. _table_rte_flow_action_set_ipv6_dscp:
2639 .. table:: SET_IPV6_DSCP
2641 +-----------+---------------------------------+
2643 +===========+=================================+
2644 | ``dscp`` | DSCP in low 6 bits, rest ignore |
2645 +-----------+---------------------------------+
2650 Set ageing timeout configuration to a flow.
2652 Event RTE_ETH_EVENT_FLOW_AGED will be reported if
2653 timeout passed without any matching on the flow.
2655 .. _table_rte_flow_action_age:
2659 +--------------+---------------------------------+
2661 +==============+=================================+
2662 | ``timeout`` | 24 bits timeout value |
2663 +--------------+---------------------------------+
2664 | ``reserved`` | 8 bits reserved, must be zero |
2665 +--------------+---------------------------------+
2666 | ``context`` | user input flow context |
2667 +--------------+---------------------------------+
2672 All specified pattern items (``enum rte_flow_item_type``) and actions
2673 (``enum rte_flow_action_type``) use positive identifiers.
2675 The negative space is reserved for dynamic types generated by PMDs during
2676 run-time. PMDs may encounter them as a result but must not accept negative
2677 identifiers they are not aware of.
2679 A method to generate them remains to be defined.
2684 Pattern item types will be added as new protocols are implemented.
2686 Variable headers support through dedicated pattern items, for example in
2687 order to match specific IPv4 options and IPv6 extension headers would be
2688 stacked after IPv4/IPv6 items.
2690 Other action types are planned but are not defined yet. These include the
2691 ability to alter packet data in several ways, such as performing
2692 encapsulation/decapsulation of tunnel headers.
2697 A rather simple API with few functions is provided to fully manage flow
2700 Each created flow rule is associated with an opaque, PMD-specific handle
2701 pointer. The application is responsible for keeping it until the rule is
2704 Flows rules are represented by ``struct rte_flow`` objects.
2709 Given that expressing a definite set of device capabilities is not
2710 practical, a dedicated function is provided to check if a flow rule is
2711 supported and can be created.
2716 rte_flow_validate(uint16_t port_id,
2717 const struct rte_flow_attr *attr,
2718 const struct rte_flow_item pattern[],
2719 const struct rte_flow_action actions[],
2720 struct rte_flow_error *error);
2722 The flow rule is validated for correctness and whether it could be accepted
2723 by the device given sufficient resources. The rule is checked against the
2724 current device mode and queue configuration. The flow rule may also
2725 optionally be validated against existing flow rules and device resources.
2726 This function has no effect on the target device.
2728 The returned value is guaranteed to remain valid only as long as no
2729 successful calls to ``rte_flow_create()`` or ``rte_flow_destroy()`` are made
2730 in the meantime and no device parameter affecting flow rules in any way are
2731 modified, due to possible collisions or resource limitations (although in
2732 such cases ``EINVAL`` should not be returned).
2736 - ``port_id``: port identifier of Ethernet device.
2737 - ``attr``: flow rule attributes.
2738 - ``pattern``: pattern specification (list terminated by the END pattern
2740 - ``actions``: associated actions (list terminated by the END action).
2741 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
2742 this structure in case of error only.
2746 - 0 if flow rule is valid and can be created. A negative errno value
2747 otherwise (``rte_errno`` is also set), the following errors are defined.
2748 - ``-ENOSYS``: underlying device does not support this functionality.
2749 - ``-EINVAL``: unknown or invalid rule specification.
2750 - ``-ENOTSUP``: valid but unsupported rule specification (e.g. partial
2751 bit-masks are unsupported).
2752 - ``EEXIST``: collision with an existing rule. Only returned if device
2753 supports flow rule collision checking and there was a flow rule
2754 collision. Not receiving this return code is no guarantee that creating
2755 the rule will not fail due to a collision.
2756 - ``ENOMEM``: not enough memory to execute the function, or if the device
2757 supports resource validation, resource limitation on the device.
2758 - ``-EBUSY``: action cannot be performed due to busy device resources, may
2759 succeed if the affected queues or even the entire port are in a stopped
2760 state (see ``rte_eth_dev_rx_queue_stop()`` and ``rte_eth_dev_stop()``).
2765 Creating a flow rule is similar to validating one, except the rule is
2766 actually created and a handle returned.
2771 rte_flow_create(uint16_t port_id,
2772 const struct rte_flow_attr *attr,
2773 const struct rte_flow_item pattern[],
2774 const struct rte_flow_action *actions[],
2775 struct rte_flow_error *error);
2779 - ``port_id``: port identifier of Ethernet device.
2780 - ``attr``: flow rule attributes.
2781 - ``pattern``: pattern specification (list terminated by the END pattern
2783 - ``actions``: associated actions (list terminated by the END action).
2784 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
2785 this structure in case of error only.
2789 A valid handle in case of success, NULL otherwise and ``rte_errno`` is set
2790 to the positive version of one of the error codes defined for
2791 ``rte_flow_validate()``.
2796 Flow rules destruction is not automatic, and a queue or a port should not be
2797 released if any are still attached to them. Applications must take care of
2798 performing this step before releasing resources.
2803 rte_flow_destroy(uint16_t port_id,
2804 struct rte_flow *flow,
2805 struct rte_flow_error *error);
2808 Failure to destroy a flow rule handle may occur when other flow rules depend
2809 on it, and destroying it would result in an inconsistent state.
2811 This function is only guaranteed to succeed if handles are destroyed in
2812 reverse order of their creation.
2816 - ``port_id``: port identifier of Ethernet device.
2817 - ``flow``: flow rule handle to destroy.
2818 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
2819 this structure in case of error only.
2823 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
2828 Convenience function to destroy all flow rule handles associated with a
2829 port. They are released as with successive calls to ``rte_flow_destroy()``.
2834 rte_flow_flush(uint16_t port_id,
2835 struct rte_flow_error *error);
2837 In the unlikely event of failure, handles are still considered destroyed and
2838 no longer valid but the port must be assumed to be in an inconsistent state.
2842 - ``port_id``: port identifier of Ethernet device.
2843 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
2844 this structure in case of error only.
2848 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
2853 Query an existing flow rule.
2855 This function allows retrieving flow-specific data such as counters. Data
2856 is gathered by special actions which must be present in the flow rule
2862 rte_flow_query(uint16_t port_id,
2863 struct rte_flow *flow,
2864 const struct rte_flow_action *action,
2866 struct rte_flow_error *error);
2870 - ``port_id``: port identifier of Ethernet device.
2871 - ``flow``: flow rule handle to query.
2872 - ``action``: action to query, this must match prototype from flow rule.
2873 - ``data``: pointer to storage for the associated query data type.
2874 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
2875 this structure in case of error only.
2879 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
2881 .. _flow_isolated_mode:
2886 The general expectation for ingress traffic is that flow rules process it
2887 first; the remaining unmatched or pass-through traffic usually ends up in a
2888 queue (with or without RSS, locally or in some sub-device instance)
2889 depending on the global configuration settings of a port.
2891 While fine from a compatibility standpoint, this approach makes drivers more
2892 complex as they have to check for possible side effects outside of this API
2893 when creating or destroying flow rules. It results in a more limited set of
2894 available rule types due to the way device resources are assigned (e.g. no
2895 support for the RSS action even on capable hardware).
2897 Given that nonspecific traffic can be handled by flow rules as well,
2898 isolated mode is a means for applications to tell a driver that ingress on
2899 the underlying port must be injected from the defined flow rules only; that
2900 no default traffic is expected outside those rules.
2902 This has the following benefits:
2904 - Applications get finer-grained control over the kind of traffic they want
2905 to receive (no traffic by default).
2907 - More importantly they control at what point nonspecific traffic is handled
2908 relative to other flow rules, by adjusting priority levels.
2910 - Drivers can assign more hardware resources to flow rules and expand the
2911 set of supported rule types.
2913 Because toggling isolated mode may cause profound changes to the ingress
2914 processing path of a driver, it may not be possible to leave it once
2915 entered. Likewise, existing flow rules or global configuration settings may
2916 prevent a driver from entering isolated mode.
2918 Applications relying on this mode are therefore encouraged to toggle it as
2919 soon as possible after device initialization, ideally before the first call
2920 to ``rte_eth_dev_configure()`` to avoid possible failures due to conflicting
2923 Once effective, the following functionality has no effect on the underlying
2924 port and may return errors such as ``ENOTSUP`` ("not supported"):
2926 - Toggling promiscuous mode.
2927 - Toggling allmulticast mode.
2928 - Configuring MAC addresses.
2929 - Configuring multicast addresses.
2930 - Configuring VLAN filters.
2931 - Configuring Rx filters through the legacy API (e.g. FDIR).
2932 - Configuring global RSS settings.
2937 rte_flow_isolate(uint16_t port_id, int set, struct rte_flow_error *error);
2941 - ``port_id``: port identifier of Ethernet device.
2942 - ``set``: nonzero to enter isolated mode, attempt to leave it otherwise.
2943 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
2944 this structure in case of error only.
2948 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
2950 Verbose error reporting
2951 -----------------------
2953 The defined *errno* values may not be accurate enough for users or
2954 application developers who want to investigate issues related to flow rules
2955 management. A dedicated error object is defined for this purpose:
2959 enum rte_flow_error_type {
2960 RTE_FLOW_ERROR_TYPE_NONE, /**< No error. */
2961 RTE_FLOW_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */
2962 RTE_FLOW_ERROR_TYPE_HANDLE, /**< Flow rule (handle). */
2963 RTE_FLOW_ERROR_TYPE_ATTR_GROUP, /**< Group field. */
2964 RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, /**< Priority field. */
2965 RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, /**< Ingress field. */
2966 RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, /**< Egress field. */
2967 RTE_FLOW_ERROR_TYPE_ATTR, /**< Attributes structure. */
2968 RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */
2969 RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */
2970 RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */
2971 RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */
2974 struct rte_flow_error {
2975 enum rte_flow_error_type type; /**< Cause field and error types. */
2976 const void *cause; /**< Object responsible for the error. */
2977 const char *message; /**< Human-readable error message. */
2980 Error type ``RTE_FLOW_ERROR_TYPE_NONE`` stands for no error, in which case
2981 remaining fields can be ignored. Other error types describe the type of the
2982 object pointed by ``cause``.
2984 If non-NULL, ``cause`` points to the object responsible for the error. For a
2985 flow rule, this may be a pattern item or an individual action.
2987 If non-NULL, ``message`` provides a human-readable error message.
2989 This object is normally allocated by applications and set by PMDs in case of
2990 error, the message points to a constant string which does not need to be
2991 freed by the application, however its pointer can be considered valid only
2992 as long as its associated DPDK port remains configured. Closing the
2993 underlying device or unloading the PMD invalidates it.
3004 rte_flow_error_set(struct rte_flow_error *error,
3006 enum rte_flow_error_type type,
3008 const char *message);
3010 This function initializes ``error`` (if non-NULL) with the provided
3011 parameters and sets ``rte_errno`` to ``code``. A negative error ``code`` is
3020 rte_flow_conv(enum rte_flow_conv_op op,
3024 struct rte_flow_error *error);
3026 Convert ``src`` to ``dst`` according to operation ``op``. Possible
3029 - Attributes, pattern item or action duplication.
3030 - Duplication of an entire pattern or list of actions.
3031 - Duplication of a complete flow rule description.
3032 - Pattern item or action name retrieval.
3037 - DPDK does not keep track of flow rules definitions or flow rule objects
3038 automatically. Applications may keep track of the former and must keep
3039 track of the latter. PMDs may also do it for internal needs, however this
3040 must not be relied on by applications.
3042 - Flow rules are not maintained between successive port initializations. An
3043 application exiting without releasing them and restarting must re-create
3046 - API operations are synchronous and blocking (``EAGAIN`` cannot be
3049 - Stopping the data path (TX/RX) should not be necessary when managing flow
3050 rules. If this cannot be achieved naturally or with workarounds (such as
3051 temporarily replacing the burst function pointers), an appropriate error
3052 code must be returned (``EBUSY``).
3054 - PMDs, not applications, are responsible for maintaining flow rules
3055 configuration when stopping and restarting a port or performing other
3056 actions which may affect them. They can only be destroyed explicitly by
3059 For devices exposing multiple ports sharing global settings affected by flow
3062 - All ports under DPDK control must behave consistently, PMDs are
3063 responsible for making sure that existing flow rules on a port are not
3064 affected by other ports.
3066 - Ports not under DPDK control (unaffected or handled by other applications)
3067 are user's responsibility. They may affect existing flow rules and cause
3068 undefined behavior. PMDs aware of this may prevent flow rules creation
3069 altogether in such cases.
3074 The PMD interface is defined in ``rte_flow_driver.h``. It is not subject to
3075 API/ABI versioning constraints as it is not exposed to applications and may
3076 evolve independently.
3078 It is currently implemented on top of the legacy filtering framework through
3079 filter type *RTE_ETH_FILTER_GENERIC* that accepts the single operation
3080 *RTE_ETH_FILTER_GET* to return PMD-specific *rte_flow* callbacks wrapped
3081 inside ``struct rte_flow_ops``.
3083 This overhead is temporarily necessary in order to keep compatibility with
3084 the legacy filtering framework, which should eventually disappear.
3086 - PMD callbacks implement exactly the interface described in `Rules
3087 management`_, except for the port ID argument which has already been
3088 converted to a pointer to the underlying ``struct rte_eth_dev``.
3090 - Public API functions do not process flow rules definitions at all before
3091 calling PMD functions (no basic error checking, no validation
3092 whatsoever). They only make sure these callbacks are non-NULL or return
3093 the ``ENOSYS`` (function not supported) error.
3095 This interface additionally defines the following helper function:
3097 - ``rte_flow_ops_get()``: get generic flow operations structure from a
3100 If PMD interfaces don't support re-entrancy/multi-thread safety,
3101 the rte_flow API functions will protect threads by mutex per port.
3102 The application can check whether ``RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE``
3103 is set in ``dev_flags``, meaning the PMD is thread-safe regarding rte_flow,
3104 so the API level protection is disabled.
3105 Please note that this API-level mutex protects only rte_flow functions,
3106 other control path functions are not in scope.
3108 More will be added over time.
3110 Device compatibility
3111 --------------------
3113 No known implementation supports all the described features.
3115 Unsupported features or combinations are not expected to be fully emulated
3116 in software by PMDs for performance reasons. Partially supported features
3117 may be completed in software as long as hardware performs most of the work
3118 (such as queue redirection and packet recognition).
3120 However PMDs are expected to do their best to satisfy application requests
3121 by working around hardware limitations as long as doing so does not affect
3122 the behavior of existing flow rules.
3124 The following sections provide a few examples of such cases and describe how
3125 PMDs should handle them, they are based on limitations built into the
3131 Each flow rule comes with its own, per-layer bit-masks, while hardware may
3132 support only a single, device-wide bit-mask for a given layer type, so that
3133 two IPv4 rules cannot use different bit-masks.
3135 The expected behavior in this case is that PMDs automatically configure
3136 global bit-masks according to the needs of the first flow rule created.
3138 Subsequent rules are allowed only if their bit-masks match those, the
3139 ``EEXIST`` error code should be returned otherwise.
3141 Unsupported layer types
3142 ~~~~~~~~~~~~~~~~~~~~~~~
3144 Many protocols can be simulated by crafting patterns with the `Item: RAW`_
3147 PMDs can rely on this capability to simulate support for protocols with
3148 headers not directly recognized by hardware.
3150 ``ANY`` pattern item
3151 ~~~~~~~~~~~~~~~~~~~~
3153 This pattern item stands for anything, which can be difficult to translate
3154 to something hardware would understand, particularly if followed by more
3157 Consider the following pattern:
3159 .. _table_rte_flow_unsupported_any:
3161 .. table:: Pattern with ANY as L3
3163 +-------+-----------------------+
3165 +=======+=======================+
3167 +-------+-----+---------+-------+
3168 | 1 | ANY | ``num`` | ``1`` |
3169 +-------+-----+---------+-------+
3171 +-------+-----------------------+
3173 +-------+-----------------------+
3175 Knowing that TCP does not make sense with something other than IPv4 and IPv6
3176 as L3, such a pattern may be translated to two flow rules instead:
3178 .. _table_rte_flow_unsupported_any_ipv4:
3180 .. table:: ANY replaced with IPV4
3182 +-------+--------------------+
3184 +=======+====================+
3186 +-------+--------------------+
3187 | 1 | IPV4 (zeroed mask) |
3188 +-------+--------------------+
3190 +-------+--------------------+
3192 +-------+--------------------+
3196 .. _table_rte_flow_unsupported_any_ipv6:
3198 .. table:: ANY replaced with IPV6
3200 +-------+--------------------+
3202 +=======+====================+
3204 +-------+--------------------+
3205 | 1 | IPV6 (zeroed mask) |
3206 +-------+--------------------+
3208 +-------+--------------------+
3210 +-------+--------------------+
3212 Note that as soon as a ANY rule covers several layers, this approach may
3213 yield a large number of hidden flow rules. It is thus suggested to only
3214 support the most common scenarios (anything as L2 and/or L3).
3219 - When combined with `Action: QUEUE`_, packet counting (`Action: COUNT`_)
3220 and tagging (`Action: MARK`_ or `Action: FLAG`_) may be implemented in
3221 software as long as the target queue is used by a single rule.
3223 - When a single target queue is provided, `Action: RSS`_ can also be
3224 implemented through `Action: QUEUE`_.
3229 While it would naturally make sense, flow rules cannot be assumed to be
3230 processed by hardware in the same order as their creation for several
3233 - They may be managed internally as a tree or a hash table instead of a
3235 - Removing a flow rule before adding another one can either put the new rule
3236 at the end of the list or reuse a freed entry.
3237 - Duplication may occur when packets are matched by several rules.
3239 For overlapping rules (particularly in order to use `Action: PASSTHRU`_)
3240 predictable behavior is only guaranteed by using different priority levels.
3242 Priority levels are not necessarily implemented in hardware, or may be
3243 severely limited (e.g. a single priority bit).
3245 For these reasons, priority levels may be implemented purely in software by
3248 - For devices expecting flow rules to be added in the correct order, PMDs
3249 may destroy and re-create existing rules after adding a new one with
3252 - A configurable number of dummy or empty rules can be created at
3253 initialization time to save high priority slots for later.
3255 - In order to save priority levels, PMDs may evaluate whether rules are
3256 likely to collide and adjust their priority accordingly.
3261 - A device profile selection function which could be used to force a
3262 permanent profile instead of relying on its automatic configuration based
3263 on existing flow rules.
3265 - A method to optimize *rte_flow* rules with specific pattern items and
3266 action types generated on the fly by PMDs. DPDK should assign negative
3267 numbers to these in order to not collide with the existing types. See
3270 - Adding specific egress pattern items and actions as described in
3271 `Attribute: Traffic direction`_.
3273 - Optional software fallback when PMDs are unable to handle requested flow
3274 rules so applications do not have to implement their own.
3276 .. _OpenFlow Switch Specification: https://www.opennetworking.org/software-defined-standards/specifications/
git.droids-corp.org / dpdk.git / blob