2 Copyright 2016 6WIND S.A.
3 Copyright 2016 Mellanox.
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11 * Redistributions in binary form must reproduce the above copyright
12 notice, this list of conditions and the following disclaimer in
13 the documentation and/or other materials provided with the
15 * Neither the name of 6WIND S.A. nor the names of its
16 contributors may be used to endorse or promote products derived
17 from this software without specific prior written permission.
19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
33 Generic flow API (rte_flow)
34 ===========================
39 This API provides a generic means to configure hardware to match specific
40 ingress or egress traffic, alter its fate and query related counters
41 according to any number of user-defined rules.
43 It is named *rte_flow* after the prefix used for all its symbols, and is
44 defined in ``rte_flow.h``.
46 - Matching can be performed on packet data (protocol headers, payload) and
47 properties (e.g. associated physical port, virtual device function ID).
49 - Possible operations include dropping traffic, diverting it to specific
50 queues, to virtual/physical device functions or ports, performing tunnel
51 offloads, adding marks and so on.
53 It is slightly higher-level than the legacy filtering framework which it
54 encompasses and supersedes (including all functions and filter types) in
55 order to expose a single interface with an unambiguous behavior that is
56 common to all poll-mode drivers (PMDs).
64 A flow rule is the combination of attributes with a matching pattern and a
65 list of actions. Flow rules form the basis of this API.
67 Flow rules can have several distinct actions (such as counting,
68 encapsulating, decapsulating before redirecting packets to a particular
69 queue, etc.), instead of relying on several rules to achieve this and having
70 applications deal with hardware implementation details regarding their
73 Support for different priority levels on a rule basis is provided, for
74 example in order to force a more specific rule to come before a more generic
75 one for packets matched by both. However hardware support for more than a
76 single priority level cannot be guaranteed. When supported, the number of
77 available priority levels is usually low, which is why they can also be
78 implemented in software by PMDs (e.g. missing priority levels may be
79 emulated by reordering rules).
81 In order to remain as hardware-agnostic as possible, by default all rules
82 are considered to have the same priority, which means that the order between
83 overlapping rules (when a packet is matched by several filters) is
86 PMDs may refuse to create overlapping rules at a given priority level when
87 they can be detected (e.g. if a pattern matches an existing filter).
89 Thus predictable results for a given priority level can only be achieved
90 with non-overlapping rules, using perfect matching on all protocol layers.
92 Flow rules can also be grouped, the flow rule priority is specific to the
93 group they belong to. All flow rules in a given group are thus processed
94 either before or after another group.
96 Support for multiple actions per rule may be implemented internally on top
97 of non-default hardware priorities, as a result both features may not be
98 simultaneously available to applications.
100 Considering that allowed pattern/actions combinations cannot be known in
101 advance and would result in an impractically large number of capabilities to
102 expose, a method is provided to validate a given rule from the current
103 device configuration state.
105 This enables applications to check if the rule types they need is supported
106 at initialization time, before starting their data path. This method can be
107 used anytime, its only requirement being that the resources needed by a rule
108 should exist (e.g. a target RX queue should be configured first).
110 Each defined rule is associated with an opaque handle managed by the PMD,
111 applications are responsible for keeping it. These can be used for queries
112 and rules management, such as retrieving counters or other data and
115 To avoid resource leaks on the PMD side, handles must be explicitly
116 destroyed by the application before releasing associated resources such as
119 The following sections cover:
121 - **Attributes** (represented by ``struct rte_flow_attr``): properties of a
122 flow rule such as its direction (ingress or egress) and priority.
124 - **Pattern item** (represented by ``struct rte_flow_item``): part of a
125 matching pattern that either matches specific packet data or traffic
126 properties. It can also describe properties of the pattern itself, such as
129 - **Matching pattern**: traffic properties to look for, a combination of any
132 - **Actions** (represented by ``struct rte_flow_action``): operations to
133 perform whenever a packet is matched by a pattern.
141 Flow rules can be grouped by assigning them a common group number. Lower
142 values have higher priority. Group 0 has the highest priority.
144 Although optional, applications are encouraged to group similar rules as
145 much as possible to fully take advantage of hardware capabilities
146 (e.g. optimized matching) and work around limitations (e.g. a single pattern
147 type possibly allowed in a given group).
149 Note that support for more than a single group is not guaranteed.
154 A priority level can be assigned to a flow rule. Like groups, lower values
155 denote higher priority, with 0 as the maximum.
157 A rule with priority 0 in group 8 is always matched after a rule with
158 priority 8 in group 0.
160 Group and priority levels are arbitrary and up to the application, they do
161 not need to be contiguous nor start from 0, however the maximum number
162 varies between devices and may be affected by existing flow rules.
164 If a packet is matched by several rules of a given group for a given
165 priority level, the outcome is undefined. It can take any path, may be
166 duplicated or even cause unrecoverable errors.
168 Note that support for more than a single priority level is not guaranteed.
170 Attribute: Traffic direction
171 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
173 Flow rules can apply to inbound and/or outbound traffic (ingress/egress).
175 Several pattern items and actions are valid and can be used in both
176 directions. At least one direction must be specified.
178 Specifying both directions at once for a given rule is not recommended but
179 may be valid in a few cases (e.g. shared counters).
184 Pattern items fall in two categories:
186 - Matching protocol headers and packet data, usually associated with a
187 specification structure. These must be stacked in the same order as the
188 protocol layers to match inside packets, starting from the lowest.
190 - Matching meta-data or affecting pattern processing, often without a
191 specification structure. Since they do not match packet contents, their
192 position in the list is usually not relevant.
194 Item specification structures are used to match specific values among
195 protocol fields (or item properties). Documentation describes for each item
196 whether they are associated with one and their type name if so.
198 Up to three structures of the same type can be set for a given item:
200 - ``spec``: values to match (e.g. a given IPv4 address).
202 - ``last``: upper bound for an inclusive range with corresponding fields in
205 - ``mask``: bit-mask applied to both ``spec`` and ``last`` whose purpose is
206 to distinguish the values to take into account and/or partially mask them
207 out (e.g. in order to match an IPv4 address prefix).
209 Usage restrictions and expected behavior:
211 - Setting either ``mask`` or ``last`` without ``spec`` is an error.
213 - Field values in ``last`` which are either 0 or equal to the corresponding
214 values in ``spec`` are ignored; they do not generate a range. Nonzero
215 values lower than those in ``spec`` are not supported.
217 - Setting ``spec`` and optionally ``last`` without ``mask`` causes the PMD
218 to use the default mask defined for that item (defined as
219 ``rte_flow_item_{name}_mask`` constants).
221 - Not setting any of them (assuming item type allows it) is equivalent to
222 providing an empty (zeroed) ``mask`` for broad (nonspecific) matching.
224 - ``mask`` is a simple bit-mask applied before interpreting the contents of
225 ``spec`` and ``last``, which may yield unexpected results if not used
226 carefully. For example, if for an IPv4 address field, ``spec`` provides
227 *10.1.2.3*, ``last`` provides *10.3.4.5* and ``mask`` provides
228 *255.255.0.0*, the effective range becomes *10.1.0.0* to *10.3.255.255*.
230 Example of an item specification matching an Ethernet header:
232 .. _table_rte_flow_pattern_item_example:
234 .. table:: Ethernet item
236 +----------+----------+--------------------+
237 | Field | Subfield | Value |
238 +==========+==========+====================+
239 | ``spec`` | ``src`` | ``00:01:02:03:04`` |
240 | +----------+--------------------+
241 | | ``dst`` | ``00:2a:66:00:01`` |
242 | +----------+--------------------+
243 | | ``type`` | ``0x22aa`` |
244 +----------+----------+--------------------+
245 | ``last`` | unspecified |
246 +----------+----------+--------------------+
247 | ``mask`` | ``src`` | ``00:ff:ff:ff:00`` |
248 | +----------+--------------------+
249 | | ``dst`` | ``00:00:00:00:ff`` |
250 | +----------+--------------------+
251 | | ``type`` | ``0x0000`` |
252 +----------+----------+--------------------+
254 Non-masked bits stand for any value (shown as ``?`` below), Ethernet headers
255 with the following properties are thus matched:
257 - ``src``: ``??:01:02:03:??``
258 - ``dst``: ``??:??:??:??:01``
259 - ``type``: ``0x????``
264 A pattern is formed by stacking items starting from the lowest protocol
265 layer to match. This stacking restriction does not apply to meta items which
266 can be placed anywhere in the stack without affecting the meaning of the
269 Patterns are terminated by END items.
273 .. _table_rte_flow_tcpv4_as_l4:
275 .. table:: TCPv4 as L4
291 .. _table_rte_flow_tcpv6_in_vxlan:
293 .. table:: TCPv6 in VXLAN
295 +-------+------------+
297 +=======+============+
299 +-------+------------+
301 +-------+------------+
303 +-------+------------+
305 +-------+------------+
307 +-------+------------+
309 +-------+------------+
311 +-------+------------+
313 +-------+------------+
317 .. _table_rte_flow_tcpv4_as_l4_meta:
319 .. table:: TCPv4 as L4 with meta items
341 The above example shows how meta items do not affect packet data matching
342 items, as long as those remain stacked properly. The resulting matching
343 pattern is identical to "TCPv4 as L4".
345 .. _table_rte_flow_udpv6_anywhere:
347 .. table:: UDPv6 anywhere
359 If supported by the PMD, omitting one or several protocol layers at the
360 bottom of the stack as in the above example (missing an Ethernet
361 specification) enables looking up anywhere in packets.
363 It is unspecified whether the payload of supported encapsulations
364 (e.g. VXLAN payload) is matched by such a pattern, which may apply to inner,
365 outer or both packets.
367 .. _table_rte_flow_invalid_l3:
369 .. table:: Invalid, missing L3
381 The above pattern is invalid due to a missing L3 specification between L2
382 (Ethernet) and L4 (UDP). Doing so is only allowed at the bottom and at the
388 They match meta-data or affect pattern processing instead of matching packet
389 data directly, most of them do not need a specification structure. This
390 particularity allows them to be specified anywhere in the stack without
391 causing any side effect.
396 End marker for item lists. Prevents further processing of items, thereby
399 - Its numeric value is 0 for convenience.
400 - PMD support is mandatory.
401 - ``spec``, ``last`` and ``mask`` are ignored.
403 .. _table_rte_flow_item_end:
407 +----------+---------+
409 +==========+=========+
410 | ``spec`` | ignored |
411 +----------+---------+
412 | ``last`` | ignored |
413 +----------+---------+
414 | ``mask`` | ignored |
415 +----------+---------+
420 Used as a placeholder for convenience. It is ignored and simply discarded by
423 - PMD support is mandatory.
424 - ``spec``, ``last`` and ``mask`` are ignored.
426 .. _table_rte_flow_item_void:
430 +----------+---------+
432 +==========+=========+
433 | ``spec`` | ignored |
434 +----------+---------+
435 | ``last`` | ignored |
436 +----------+---------+
437 | ``mask`` | ignored |
438 +----------+---------+
440 One usage example for this type is generating rules that share a common
441 prefix quickly without reallocating memory, only by updating item types:
443 .. _table_rte_flow_item_void_example:
445 .. table:: TCP, UDP or ICMP as L4
447 +-------+--------------------+
449 +=======+====================+
451 +-------+--------------------+
453 +-------+------+------+------+
454 | 2 | UDP | VOID | VOID |
455 +-------+------+------+------+
456 | 3 | VOID | TCP | VOID |
457 +-------+------+------+------+
458 | 4 | VOID | VOID | ICMP |
459 +-------+------+------+------+
461 +-------+--------------------+
466 Inverted matching, i.e. process packets that do not match the pattern.
468 - ``spec``, ``last`` and ``mask`` are ignored.
470 .. _table_rte_flow_item_invert:
474 +----------+---------+
476 +==========+=========+
477 | ``spec`` | ignored |
478 +----------+---------+
479 | ``last`` | ignored |
480 +----------+---------+
481 | ``mask`` | ignored |
482 +----------+---------+
484 Usage example, matching non-TCPv4 packets only:
486 .. _table_rte_flow_item_invert_example:
488 .. table:: Anything but TCPv4
507 Matches packets addressed to the physical function of the device.
509 If the underlying device function differs from the one that would normally
510 receive the matched traffic, specifying this item prevents it from reaching
511 that device unless the flow rule contains a `Action: PF`_. Packets are not
512 duplicated between device instances by default.
514 - Likely to return an error or never match any traffic if applied to a VF
516 - Can be combined with any number of `Item: VF`_ to match both PF and VF
518 - ``spec``, ``last`` and ``mask`` must not be set.
520 .. _table_rte_flow_item_pf:
537 Matches packets addressed to a virtual function ID of the device.
539 If the underlying device function differs from the one that would normally
540 receive the matched traffic, specifying this item prevents it from reaching
541 that device unless the flow rule contains a `Action: VF`_. Packets are not
542 duplicated between device instances by default.
544 - Likely to return an error or never match any traffic if this causes a VF
545 device to match traffic addressed to a different VF.
546 - Can be specified multiple times to match traffic addressed to several VF
548 - Can be combined with a PF item to match both PF and VF traffic.
549 - Default ``mask`` matches any VF ID.
551 .. _table_rte_flow_item_vf:
555 +----------+----------+---------------------------+
556 | Field | Subfield | Value |
557 +==========+==========+===========================+
558 | ``spec`` | ``id`` | destination VF ID |
559 +----------+----------+---------------------------+
560 | ``last`` | ``id`` | upper range value |
561 +----------+----------+---------------------------+
562 | ``mask`` | ``id`` | zeroed to match any VF ID |
563 +----------+----------+---------------------------+
568 Matches packets coming from the specified physical port of the underlying
571 The first PORT item overrides the physical port normally associated with the
572 specified DPDK input port (port_id). This item can be provided several times
573 to match additional physical ports.
575 Note that physical ports are not necessarily tied to DPDK input ports
576 (port_id) when those are not under DPDK control. Possible values are
577 specific to each device, they are not necessarily indexed from zero and may
580 As a device property, the list of allowed values as well as the value
581 associated with a port_id should be retrieved by other means.
583 - Default ``mask`` matches any port index.
585 .. _table_rte_flow_item_port:
589 +----------+-----------+--------------------------------+
590 | Field | Subfield | Value |
591 +==========+===========+================================+
592 | ``spec`` | ``index`` | physical port index |
593 +----------+-----------+--------------------------------+
594 | ``last`` | ``index`` | upper range value |
595 +----------+-----------+--------------------------------+
596 | ``mask`` | ``index`` | zeroed to match any port index |
597 +----------+-----------+--------------------------------+
599 Data matching item types
600 ~~~~~~~~~~~~~~~~~~~~~~~~
602 Most of these are basically protocol header definitions with associated
603 bit-masks. They must be specified (stacked) from lowest to highest protocol
604 layer to form a matching pattern.
606 The following list is not exhaustive, new protocols will be added in the
612 Matches any protocol in place of the current layer, a single ANY may also
613 stand for several protocol layers.
615 This is usually specified as the first pattern item when looking for a
616 protocol anywhere in a packet.
618 - Default ``mask`` stands for any number of layers.
620 .. _table_rte_flow_item_any:
624 +----------+----------+--------------------------------------+
625 | Field | Subfield | Value |
626 +==========+==========+======================================+
627 | ``spec`` | ``num`` | number of layers covered |
628 +----------+----------+--------------------------------------+
629 | ``last`` | ``num`` | upper range value |
630 +----------+----------+--------------------------------------+
631 | ``mask`` | ``num`` | zeroed to cover any number of layers |
632 +----------+----------+--------------------------------------+
634 Example for VXLAN TCP payload matching regardless of outer L3 (IPv4 or IPv6)
635 and L4 (UDP) both matched by the first ANY specification, and inner L3 (IPv4
636 or IPv6) matched by the second ANY specification:
638 .. _table_rte_flow_item_any_example:
640 .. table:: TCP in VXLAN with wildcards
642 +-------+------+----------+----------+-------+
643 | Index | Item | Field | Subfield | Value |
644 +=======+======+==========+==========+=======+
646 +-------+------+----------+----------+-------+
647 | 1 | ANY | ``spec`` | ``num`` | 2 |
648 +-------+------+----------+----------+-------+
650 +-------+------------------------------------+
652 +-------+------+----------+----------+-------+
653 | 4 | ANY | ``spec`` | ``num`` | 1 |
654 +-------+------+----------+----------+-------+
656 +-------+------------------------------------+
658 +-------+------------------------------------+
663 Matches a byte string of a given length at a given offset.
665 Offset is either absolute (using the start of the packet) or relative to the
666 end of the previous matched item in the stack, in which case negative values
669 If search is enabled, offset is used as the starting point. The search area
670 can be delimited by setting limit to a nonzero value, which is the maximum
671 number of bytes after offset where the pattern may start.
673 Matching a zero-length pattern is allowed, doing so resets the relative
674 offset for subsequent items.
676 - This type does not support ranges (``last`` field).
677 - Default ``mask`` matches all fields exactly.
679 .. _table_rte_flow_item_raw:
683 +----------+--------------+-------------------------------------------------+
684 | Field | Subfield | Value |
685 +==========+==============+=================================================+
686 | ``spec`` | ``relative`` | look for pattern after the previous item |
687 | +--------------+-------------------------------------------------+
688 | | ``search`` | search pattern from offset (see also ``limit``) |
689 | +--------------+-------------------------------------------------+
690 | | ``reserved`` | reserved, must be set to zero |
691 | +--------------+-------------------------------------------------+
692 | | ``offset`` | absolute or relative offset for ``pattern`` |
693 | +--------------+-------------------------------------------------+
694 | | ``limit`` | search area limit for start of ``pattern`` |
695 | +--------------+-------------------------------------------------+
696 | | ``length`` | ``pattern`` length |
697 | +--------------+-------------------------------------------------+
698 | | ``pattern`` | byte string to look for |
699 +----------+--------------+-------------------------------------------------+
700 | ``last`` | if specified, either all 0 or with the same values as ``spec`` |
701 +----------+----------------------------------------------------------------+
702 | ``mask`` | bit-mask applied to ``spec`` values with usual behavior |
703 +----------+----------------------------------------------------------------+
705 Example pattern looking for several strings at various offsets of a UDP
706 payload, using combined RAW items:
708 .. _table_rte_flow_item_raw_example:
710 .. table:: UDP payload matching
712 +-------+------+----------+--------------+-------+
713 | Index | Item | Field | Subfield | Value |
714 +=======+======+==========+==============+=======+
716 +-------+----------------------------------------+
718 +-------+----------------------------------------+
720 +-------+------+----------+--------------+-------+
721 | 3 | RAW | ``spec`` | ``relative`` | 1 |
722 | | | +--------------+-------+
723 | | | | ``search`` | 1 |
724 | | | +--------------+-------+
725 | | | | ``offset`` | 10 |
726 | | | +--------------+-------+
727 | | | | ``limit`` | 0 |
728 | | | +--------------+-------+
729 | | | | ``length`` | 3 |
730 | | | +--------------+-------+
731 | | | | ``pattern`` | "foo" |
732 +-------+------+----------+--------------+-------+
733 | 4 | RAW | ``spec`` | ``relative`` | 1 |
734 | | | +--------------+-------+
735 | | | | ``search`` | 0 |
736 | | | +--------------+-------+
737 | | | | ``offset`` | 20 |
738 | | | +--------------+-------+
739 | | | | ``limit`` | 0 |
740 | | | +--------------+-------+
741 | | | | ``length`` | 3 |
742 | | | +--------------+-------+
743 | | | | ``pattern`` | "bar" |
744 +-------+------+----------+--------------+-------+
745 | 5 | RAW | ``spec`` | ``relative`` | 1 |
746 | | | +--------------+-------+
747 | | | | ``search`` | 0 |
748 | | | +--------------+-------+
749 | | | | ``offset`` | -29 |
750 | | | +--------------+-------+
751 | | | | ``limit`` | 0 |
752 | | | +--------------+-------+
753 | | | | ``length`` | 3 |
754 | | | +--------------+-------+
755 | | | | ``pattern`` | "baz" |
756 +-------+------+----------+--------------+-------+
758 +-------+----------------------------------------+
762 - Locate "foo" at least 10 bytes deep inside UDP payload.
763 - Locate "bar" after "foo" plus 20 bytes.
764 - Locate "baz" after "bar" minus 29 bytes.
766 Such a packet may be represented as follows (not to scale)::
769 | |<--------->| |<--------->|
771 |-----|------|-----|-----|-----|-----|-----------|-----|------|
772 | ETH | IPv4 | UDP | ... | baz | foo | ......... | bar | .... |
773 |-----|------|-----|-----|-----|-----|-----------|-----|------|
775 |<--------------------------->|
778 Note that matching subsequent pattern items would resume after "baz", not
779 "bar" since matching is always performed after the previous item of the
785 Matches an Ethernet header.
787 The ``type`` field either stands for "EtherType" or "TPID" when followed by
788 so-called layer 2.5 pattern items such as ``RTE_FLOW_ITEM_TYPE_VLAN``. In
789 the latter case, ``type`` refers to that of the outer header, with the inner
790 EtherType/TPID provided by the subsequent pattern item. This is the same
791 order as on the wire.
793 - ``dst``: destination MAC.
794 - ``src``: source MAC.
795 - ``type``: EtherType or TPID.
796 - Default ``mask`` matches destination and source addresses only.
801 Matches an 802.1Q/ad VLAN tag.
803 The corresponding standard outer EtherType (TPID) values are
804 ``ETHER_TYPE_VLAN`` or ``ETHER_TYPE_QINQ``. It can be overridden by the
805 preceding pattern item.
807 - ``tci``: tag control information.
808 - ``inner_type``: inner EtherType or TPID.
809 - Default ``mask`` matches the VID part of TCI only (lower 12 bits).
814 Matches an IPv4 header.
816 Note: IPv4 options are handled by dedicated pattern items.
818 - ``hdr``: IPv4 header definition (``rte_ip.h``).
819 - Default ``mask`` matches source and destination addresses only.
824 Matches an IPv6 header.
826 Note: IPv6 options are handled by dedicated pattern items.
828 - ``hdr``: IPv6 header definition (``rte_ip.h``).
829 - Default ``mask`` matches source and destination addresses only.
834 Matches an ICMP header.
836 - ``hdr``: ICMP header definition (``rte_icmp.h``).
837 - Default ``mask`` matches ICMP type and code only.
842 Matches a UDP header.
844 - ``hdr``: UDP header definition (``rte_udp.h``).
845 - Default ``mask`` matches source and destination ports only.
850 Matches a TCP header.
852 - ``hdr``: TCP header definition (``rte_tcp.h``).
853 - Default ``mask`` matches source and destination ports only.
858 Matches a SCTP header.
860 - ``hdr``: SCTP header definition (``rte_sctp.h``).
861 - Default ``mask`` matches source and destination ports only.
866 Matches a VXLAN header (RFC 7348).
868 - ``flags``: normally 0x08 (I flag).
869 - ``rsvd0``: reserved, normally 0x000000.
870 - ``vni``: VXLAN network identifier.
871 - ``rsvd1``: reserved, normally 0x00.
872 - Default ``mask`` matches VNI only.
877 Matches an IEEE 802.1BR E-Tag header.
879 The corresponding standard outer EtherType (TPID) value is
880 ``ETHER_TYPE_ETAG``. It can be overridden by the preceding pattern item.
882 - ``epcp_edei_in_ecid_b``: E-Tag control information (E-TCI), E-PCP (3b),
883 E-DEI (1b), ingress E-CID base (12b).
884 - ``rsvd_grp_ecid_b``: reserved (2b), GRP (2b), E-CID base (12b).
885 - ``in_ecid_e``: ingress E-CID ext.
886 - ``ecid_e``: E-CID ext.
887 - ``inner_type``: inner EtherType or TPID.
888 - Default ``mask`` simultaneously matches GRP and E-CID base.
893 Matches a NVGRE header (RFC 7637).
895 - ``c_k_s_rsvd0_ver``: checksum (1b), undefined (1b), key bit (1b),
896 sequence number (1b), reserved 0 (9b), version (3b). This field must have
897 value 0x2000 according to RFC 7637.
898 - ``protocol``: protocol type (0x6558).
899 - ``tni``: virtual subnet ID.
900 - ``flow_id``: flow ID.
901 - Default ``mask`` matches TNI only.
906 Matches a MPLS header.
908 - ``label_tc_s_ttl``: label, TC, Bottom of Stack and TTL.
909 - Default ``mask`` matches label only.
914 Matches a GRE header.
916 - ``c_rsvd0_ver``: checksum, reserved 0 and version.
917 - ``protocol``: protocol type.
918 - Default ``mask`` matches protocol only.
923 Fuzzy pattern match, expect faster than default.
925 This is for device that support fuzzy match option. Usually a fuzzy match is
926 fast but the cost is accuracy. i.e. Signature Match only match pattern's hash
927 value, but it is possible two different patterns have the same hash value.
929 Matching accuracy level can be configured by threshold. Driver can divide the
930 range of threshold and map to different accuracy levels that device support.
932 Threshold 0 means perfect match (no fuzziness), while threshold 0xffffffff
933 means fuzziest match.
935 .. _table_rte_flow_item_fuzzy:
939 +----------+---------------+--------------------------------------------------+
940 | Field | Subfield | Value |
941 +==========+===============+==================================================+
942 | ``spec`` | ``threshold`` | 0 as perfect match, 0xffffffff as fuzziest match |
943 +----------+---------------+--------------------------------------------------+
944 | ``last`` | ``threshold`` | upper range value |
945 +----------+---------------+--------------------------------------------------+
946 | ``mask`` | ``threshold`` | bit-mask apply to "spec" and "last" |
947 +----------+---------------+--------------------------------------------------+
949 Usage example, fuzzy match a TCPv4 packets:
951 .. _table_rte_flow_item_fuzzy_example:
953 .. table:: Fuzzy matching
969 Item: ``GTP``, ``GTPC``, ``GTPU``
970 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
972 Matches a GTPv1 header.
974 Note: GTP, GTPC and GTPU use the same structure. GTPC and GTPU item
975 are defined for a user-friendly API when creating GTP-C and GTP-U
978 - ``v_pt_rsv_flags``: version (3b), protocol type (1b), reserved (1b),
979 extension header flag (1b), sequence number flag (1b), N-PDU number
981 - ``msg_type``: message type.
982 - ``msg_len``: message length.
983 - ``teid``: tunnel endpoint identifier.
984 - Default ``mask`` matches teid only.
989 Matches an ESP header.
991 - ``hdr``: ESP header definition (``rte_esp.h``).
992 - Default ``mask`` matches SPI only.
997 Matches a GENEVE header.
999 - ``ver_opt_len_o_c_rsvd0``: version (2b), length of the options fields (6b),
1000 OAM packet (1b), critical options present (1b), reserved 0 (6b).
1001 - ``protocol``: protocol type.
1002 - ``vni``: virtual network identifier.
1003 - ``rsvd1``: reserved, normally 0x00.
1004 - Default ``mask`` matches VNI only.
1009 Each possible action is represented by a type. Some have associated
1010 configuration structures. Several actions combined in a list can be assigned
1011 to a flow rule and are performed in order.
1013 They fall in three categories:
1015 - Actions that modify the fate of matching traffic, for instance by dropping
1016 or assigning it a specific destination.
1018 - Actions that modify matching traffic contents or its properties. This
1019 includes adding/removing encapsulation, encryption, compression and marks.
1021 - Actions related to the flow rule itself, such as updating counters or
1022 making it non-terminating.
1024 Flow rules being terminating by default, not specifying any action of the
1025 fate kind results in undefined behavior. This applies to both ingress and
1028 PASSTHRU, when supported, makes a flow rule non-terminating.
1030 Like matching patterns, action lists are terminated by END items.
1032 Example of action that redirects packets to queue index 10:
1034 .. _table_rte_flow_action_example:
1036 .. table:: Queue action
1038 +-----------+-------+
1040 +===========+=======+
1042 +-----------+-------+
1044 Actions are performed in list order:
1046 .. _table_rte_flow_count_then_drop:
1048 .. table:: Count then drop
1062 .. _table_rte_flow_mark_count_redirect:
1064 .. table:: Mark, count then redirect
1066 +-------+--------+-----------+-------+
1067 | Index | Action | Field | Value |
1068 +=======+========+===========+=======+
1069 | 0 | MARK | ``mark`` | 0x2a |
1070 +-------+--------+-----------+-------+
1072 +-------+--------+-----------+-------+
1073 | 2 | QUEUE | ``queue`` | 10 |
1074 +-------+--------+-----------+-------+
1076 +-------+----------------------------+
1080 .. _table_rte_flow_redirect_queue_5:
1082 .. table:: Redirect to queue 5
1084 +-------+--------+-----------+-------+
1085 | Index | Action | Field | Value |
1086 +=======+========+===========+=======+
1088 +-------+--------+-----------+-------+
1089 | 1 | QUEUE | ``queue`` | 5 |
1090 +-------+--------+-----------+-------+
1092 +-------+----------------------------+
1094 In the above example, while DROP and QUEUE must be performed in order, both
1095 have to happen before reaching END. Only QUEUE has a visible effect.
1097 Note that such a list may be thought as ambiguous and rejected on that
1100 .. _table_rte_flow_redirect_queue_5_3:
1102 .. table:: Redirect to queues 5 and 3
1104 +-------+--------+-----------+-------+
1105 | Index | Action | Field | Value |
1106 +=======+========+===========+=======+
1107 | 0 | QUEUE | ``queue`` | 5 |
1108 +-------+--------+-----------+-------+
1110 +-------+--------+-----------+-------+
1111 | 2 | QUEUE | ``queue`` | 3 |
1112 +-------+--------+-----------+-------+
1114 +-------+----------------------------+
1116 As previously described, all actions must be taken into account. This
1117 effectively duplicates traffic to both queues. The above example also shows
1118 that VOID is ignored.
1123 Common action types are described in this section. Like pattern item types,
1124 this list is not exhaustive as new actions will be added in the future.
1129 End marker for action lists. Prevents further processing of actions, thereby
1132 - Its numeric value is 0 for convenience.
1133 - PMD support is mandatory.
1134 - No configurable properties.
1136 .. _table_rte_flow_action_end:
1149 Used as a placeholder for convenience. It is ignored and simply discarded by
1152 - PMD support is mandatory.
1153 - No configurable properties.
1155 .. _table_rte_flow_action_void:
1165 Action: ``PASSTHRU``
1166 ^^^^^^^^^^^^^^^^^^^^
1168 Leaves traffic up for additional processing by subsequent flow rules; makes
1169 a flow rule non-terminating.
1171 - No configurable properties.
1173 .. _table_rte_flow_action_passthru:
1183 Example to copy a packet to a queue and continue processing by subsequent
1186 .. _table_rte_flow_action_passthru_example:
1188 .. table:: Copy to queue 8
1190 +-------+--------+-----------+-------+
1191 | Index | Action | Field | Value |
1192 +=======+========+===========+=======+
1194 +-------+--------+-----------+-------+
1195 | 1 | QUEUE | ``queue`` | 8 |
1196 +-------+--------+-----------+-------+
1198 +-------+----------------------------+
1203 Attaches an integer value to packets and sets ``PKT_RX_FDIR`` and
1204 ``PKT_RX_FDIR_ID`` mbuf flags.
1206 This value is arbitrary and application-defined. Maximum allowed value
1207 depends on the underlying implementation. It is returned in the
1208 ``hash.fdir.hi`` mbuf field.
1210 .. _table_rte_flow_action_mark:
1214 +--------+--------------------------------------+
1216 +========+======================================+
1217 | ``id`` | integer value to return with packets |
1218 +--------+--------------------------------------+
1223 Flags packets. Similar to `Action: MARK`_ without a specific value; only
1224 sets the ``PKT_RX_FDIR`` mbuf flag.
1226 - No configurable properties.
1228 .. _table_rte_flow_action_flag:
1241 Assigns packets to a given queue index.
1243 .. _table_rte_flow_action_queue:
1247 +-----------+--------------------+
1249 +===========+====================+
1250 | ``index`` | queue index to use |
1251 +-----------+--------------------+
1258 - No configurable properties.
1260 .. _table_rte_flow_action_drop:
1273 Enables counters for this rule.
1275 These counters can be retrieved and reset through ``rte_flow_query()``, see
1276 ``struct rte_flow_query_count``.
1278 - Counters can be retrieved with ``rte_flow_query()``.
1279 - No configurable properties.
1281 .. _table_rte_flow_action_count:
1291 Query structure to retrieve and reset flow rule counters:
1293 .. _table_rte_flow_query_count:
1295 .. table:: COUNT query
1297 +---------------+-----+-----------------------------------+
1298 | Field | I/O | Value |
1299 +===============+=====+===================================+
1300 | ``reset`` | in | reset counter after query |
1301 +---------------+-----+-----------------------------------+
1302 | ``hits_set`` | out | ``hits`` field is set |
1303 +---------------+-----+-----------------------------------+
1304 | ``bytes_set`` | out | ``bytes`` field is set |
1305 +---------------+-----+-----------------------------------+
1306 | ``hits`` | out | number of hits for this rule |
1307 +---------------+-----+-----------------------------------+
1308 | ``bytes`` | out | number of bytes through this rule |
1309 +---------------+-----+-----------------------------------+
1314 Similar to QUEUE, except RSS is additionally performed on packets to spread
1315 them among several queues according to the provided parameters.
1317 Unlike global RSS settings used by other DPDK APIs, unsetting the ``types``
1318 field does not disable RSS in a flow rule. Doing so instead requests safe
1319 unspecified "best-effort" settings from the underlying PMD, which depending
1320 on the flow rule, may result in anything ranging from empty (single queue)
1321 to all-inclusive RSS.
1323 Note: RSS hash result is stored in the ``hash.rss`` mbuf field which
1324 overlaps ``hash.fdir.lo``. Since `Action: MARK`_ sets the ``hash.fdir.hi``
1325 field only, both can be requested simultaneously.
1327 Also, regarding packet encapsulation ``level``:
1329 - ``0`` requests the default behavior. Depending on the packet type, it can
1330 mean outermost, innermost, anything in between or even no RSS.
1332 It basically stands for the innermost encapsulation level RSS can be
1333 performed on according to PMD and device capabilities.
1335 - ``1`` requests RSS to be performed on the outermost packet encapsulation
1338 - ``2`` and subsequent values request RSS to be performed on the specified
1339 inner packet encapsulation level, from outermost to innermost (lower to
1342 Values other than ``0`` are not necessarily supported.
1344 Requesting a specific RSS level on unrecognized traffic results in undefined
1345 behavior. For predictable results, it is recommended to make the flow rule
1346 pattern match packet headers up to the requested encapsulation level so that
1347 only matching traffic goes through.
1349 .. _table_rte_flow_action_rss:
1353 +---------------+---------------------------------------------+
1355 +===============+=============================================+
1356 | ``func`` | RSS hash function to apply |
1357 +---------------+---------------------------------------------+
1358 | ``level`` | encapsulation level for ``types`` |
1359 +---------------+---------------------------------------------+
1360 | ``types`` | specific RSS hash types (see ``ETH_RSS_*``) |
1361 +---------------+---------------------------------------------+
1362 | ``key_len`` | hash key length in bytes |
1363 +---------------+---------------------------------------------+
1364 | ``queue_num`` | number of entries in ``queue`` |
1365 +---------------+---------------------------------------------+
1366 | ``key`` | hash key |
1367 +---------------+---------------------------------------------+
1368 | ``queue`` | queue indices to use |
1369 +---------------+---------------------------------------------+
1374 Redirects packets to the physical function (PF) of the current device.
1376 - No configurable properties.
1378 .. _table_rte_flow_action_pf:
1391 Redirects packets to a virtual function (VF) of the current device.
1393 Packets matched by a VF pattern item can be redirected to their original VF
1394 ID instead of the specified one. This parameter may not be available and is
1395 not guaranteed to work properly if the VF part is matched by a prior flow
1396 rule or if packets are not addressed to a VF in the first place.
1398 .. _table_rte_flow_action_vf:
1402 +--------------+--------------------------------+
1404 +==============+================================+
1405 | ``original`` | use original VF ID if possible |
1406 +--------------+--------------------------------+
1407 | ``vf`` | VF ID to redirect packets to |
1408 +--------------+--------------------------------+
1413 Applies a stage of metering and policing.
1415 The metering and policing (MTR) object has to be first created using the
1416 rte_mtr_create() API function. The ID of the MTR object is specified as
1417 action parameter. More than one flow can use the same MTR object through
1418 the meter action. The MTR object can be further updated or queried using
1421 .. _table_rte_flow_action_meter:
1425 +--------------+---------------+
1427 +==============+===============+
1428 | ``mtr_id`` | MTR object ID |
1429 +--------------+---------------+
1431 Action: ``SECURITY``
1432 ^^^^^^^^^^^^^^^^^^^^
1434 Perform the security action on flows matched by the pattern items
1435 according to the configuration of the security session.
1437 This action modifies the payload of matched flows. For INLINE_CRYPTO, the
1438 security protocol headers and IV are fully provided by the application as
1439 specified in the flow pattern. The payload of matching packets is
1440 encrypted on egress, and decrypted and authenticated on ingress.
1441 For INLINE_PROTOCOL, the security protocol is fully offloaded to HW,
1442 providing full encapsulation and decapsulation of packets in security
1443 protocols. The flow pattern specifies both the outer security header fields
1444 and the inner packet fields. The security session specified in the action
1445 must match the pattern parameters.
1447 The security session specified in the action must be created on the same
1448 port as the flow action that is being specified.
1450 The ingress/egress flow attribute should match that specified in the
1451 security session if the security session supports the definition of the
1454 Multiple flows can be configured to use the same security session.
1456 .. _table_rte_flow_action_security:
1460 +----------------------+--------------------------------------+
1462 +======================+======================================+
1463 | ``security_session`` | security session to apply |
1464 +----------------------+--------------------------------------+
1466 The following is an example of configuring IPsec inline using the
1467 INLINE_CRYPTO security session:
1469 The encryption algorithm, keys and salt are part of the opaque
1470 ``rte_security_session``. The SA is identified according to the IP and ESP
1471 fields in the pattern items.
1473 .. _table_rte_flow_item_esp_inline_example:
1475 .. table:: IPsec inline crypto flow pattern items.
1477 +-------+----------+
1479 +=======+==========+
1481 +-------+----------+
1483 +-------+----------+
1485 +-------+----------+
1487 +-------+----------+
1489 .. _table_rte_flow_action_esp_inline_example:
1491 .. table:: IPsec inline flow actions.
1493 +-------+----------+
1495 +=======+==========+
1497 +-------+----------+
1499 +-------+----------+
1504 All specified pattern items (``enum rte_flow_item_type``) and actions
1505 (``enum rte_flow_action_type``) use positive identifiers.
1507 The negative space is reserved for dynamic types generated by PMDs during
1508 run-time. PMDs may encounter them as a result but must not accept negative
1509 identifiers they are not aware of.
1511 A method to generate them remains to be defined.
1516 Pattern item types will be added as new protocols are implemented.
1518 Variable headers support through dedicated pattern items, for example in
1519 order to match specific IPv4 options and IPv6 extension headers would be
1520 stacked after IPv4/IPv6 items.
1522 Other action types are planned but are not defined yet. These include the
1523 ability to alter packet data in several ways, such as performing
1524 encapsulation/decapsulation of tunnel headers.
1529 A rather simple API with few functions is provided to fully manage flow
1532 Each created flow rule is associated with an opaque, PMD-specific handle
1533 pointer. The application is responsible for keeping it until the rule is
1536 Flows rules are represented by ``struct rte_flow`` objects.
1541 Given that expressing a definite set of device capabilities is not
1542 practical, a dedicated function is provided to check if a flow rule is
1543 supported and can be created.
1548 rte_flow_validate(uint16_t port_id,
1549 const struct rte_flow_attr *attr,
1550 const struct rte_flow_item pattern[],
1551 const struct rte_flow_action actions[],
1552 struct rte_flow_error *error);
1554 The flow rule is validated for correctness and whether it could be accepted
1555 by the device given sufficient resources. The rule is checked against the
1556 current device mode and queue configuration. The flow rule may also
1557 optionally be validated against existing flow rules and device resources.
1558 This function has no effect on the target device.
1560 The returned value is guaranteed to remain valid only as long as no
1561 successful calls to ``rte_flow_create()`` or ``rte_flow_destroy()`` are made
1562 in the meantime and no device parameter affecting flow rules in any way are
1563 modified, due to possible collisions or resource limitations (although in
1564 such cases ``EINVAL`` should not be returned).
1568 - ``port_id``: port identifier of Ethernet device.
1569 - ``attr``: flow rule attributes.
1570 - ``pattern``: pattern specification (list terminated by the END pattern
1572 - ``actions``: associated actions (list terminated by the END action).
1573 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
1574 this structure in case of error only.
1578 - 0 if flow rule is valid and can be created. A negative errno value
1579 otherwise (``rte_errno`` is also set), the following errors are defined.
1580 - ``-ENOSYS``: underlying device does not support this functionality.
1581 - ``-EINVAL``: unknown or invalid rule specification.
1582 - ``-ENOTSUP``: valid but unsupported rule specification (e.g. partial
1583 bit-masks are unsupported).
1584 - ``EEXIST``: collision with an existing rule. Only returned if device
1585 supports flow rule collision checking and there was a flow rule
1586 collision. Not receiving this return code is no guarantee that creating
1587 the rule will not fail due to a collision.
1588 - ``ENOMEM``: not enough memory to execute the function, or if the device
1589 supports resource validation, resource limitation on the device.
1590 - ``-EBUSY``: action cannot be performed due to busy device resources, may
1591 succeed if the affected queues or even the entire port are in a stopped
1592 state (see ``rte_eth_dev_rx_queue_stop()`` and ``rte_eth_dev_stop()``).
1597 Creating a flow rule is similar to validating one, except the rule is
1598 actually created and a handle returned.
1603 rte_flow_create(uint16_t port_id,
1604 const struct rte_flow_attr *attr,
1605 const struct rte_flow_item pattern[],
1606 const struct rte_flow_action *actions[],
1607 struct rte_flow_error *error);
1611 - ``port_id``: port identifier of Ethernet device.
1612 - ``attr``: flow rule attributes.
1613 - ``pattern``: pattern specification (list terminated by the END pattern
1615 - ``actions``: associated actions (list terminated by the END action).
1616 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
1617 this structure in case of error only.
1621 A valid handle in case of success, NULL otherwise and ``rte_errno`` is set
1622 to the positive version of one of the error codes defined for
1623 ``rte_flow_validate()``.
1628 Flow rules destruction is not automatic, and a queue or a port should not be
1629 released if any are still attached to them. Applications must take care of
1630 performing this step before releasing resources.
1635 rte_flow_destroy(uint16_t port_id,
1636 struct rte_flow *flow,
1637 struct rte_flow_error *error);
1640 Failure to destroy a flow rule handle may occur when other flow rules depend
1641 on it, and destroying it would result in an inconsistent state.
1643 This function is only guaranteed to succeed if handles are destroyed in
1644 reverse order of their creation.
1648 - ``port_id``: port identifier of Ethernet device.
1649 - ``flow``: flow rule handle to destroy.
1650 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
1651 this structure in case of error only.
1655 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
1660 Convenience function to destroy all flow rule handles associated with a
1661 port. They are released as with successive calls to ``rte_flow_destroy()``.
1666 rte_flow_flush(uint16_t port_id,
1667 struct rte_flow_error *error);
1669 In the unlikely event of failure, handles are still considered destroyed and
1670 no longer valid but the port must be assumed to be in an inconsistent state.
1674 - ``port_id``: port identifier of Ethernet device.
1675 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
1676 this structure in case of error only.
1680 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
1685 Query an existing flow rule.
1687 This function allows retrieving flow-specific data such as counters. Data
1688 is gathered by special actions which must be present in the flow rule
1694 rte_flow_query(uint16_t port_id,
1695 struct rte_flow *flow,
1696 enum rte_flow_action_type action,
1698 struct rte_flow_error *error);
1702 - ``port_id``: port identifier of Ethernet device.
1703 - ``flow``: flow rule handle to query.
1704 - ``action``: action type to query.
1705 - ``data``: pointer to storage for the associated query data type.
1706 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
1707 this structure in case of error only.
1711 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
1716 The general expectation for ingress traffic is that flow rules process it
1717 first; the remaining unmatched or pass-through traffic usually ends up in a
1718 queue (with or without RSS, locally or in some sub-device instance)
1719 depending on the global configuration settings of a port.
1721 While fine from a compatibility standpoint, this approach makes drivers more
1722 complex as they have to check for possible side effects outside of this API
1723 when creating or destroying flow rules. It results in a more limited set of
1724 available rule types due to the way device resources are assigned (e.g. no
1725 support for the RSS action even on capable hardware).
1727 Given that nonspecific traffic can be handled by flow rules as well,
1728 isolated mode is a means for applications to tell a driver that ingress on
1729 the underlying port must be injected from the defined flow rules only; that
1730 no default traffic is expected outside those rules.
1732 This has the following benefits:
1734 - Applications get finer-grained control over the kind of traffic they want
1735 to receive (no traffic by default).
1737 - More importantly they control at what point nonspecific traffic is handled
1738 relative to other flow rules, by adjusting priority levels.
1740 - Drivers can assign more hardware resources to flow rules and expand the
1741 set of supported rule types.
1743 Because toggling isolated mode may cause profound changes to the ingress
1744 processing path of a driver, it may not be possible to leave it once
1745 entered. Likewise, existing flow rules or global configuration settings may
1746 prevent a driver from entering isolated mode.
1748 Applications relying on this mode are therefore encouraged to toggle it as
1749 soon as possible after device initialization, ideally before the first call
1750 to ``rte_eth_dev_configure()`` to avoid possible failures due to conflicting
1753 Once effective, the following functionality has no effect on the underlying
1754 port and may return errors such as ``ENOTSUP`` ("not supported"):
1756 - Toggling promiscuous mode.
1757 - Toggling allmulticast mode.
1758 - Configuring MAC addresses.
1759 - Configuring multicast addresses.
1760 - Configuring VLAN filters.
1761 - Configuring Rx filters through the legacy API (e.g. FDIR).
1762 - Configuring global RSS settings.
1767 rte_flow_isolate(uint16_t port_id, int set, struct rte_flow_error *error);
1771 - ``port_id``: port identifier of Ethernet device.
1772 - ``set``: nonzero to enter isolated mode, attempt to leave it otherwise.
1773 - ``error``: perform verbose error reporting if not NULL. PMDs initialize
1774 this structure in case of error only.
1778 - 0 on success, a negative errno value otherwise and ``rte_errno`` is set.
1780 Verbose error reporting
1781 -----------------------
1783 The defined *errno* values may not be accurate enough for users or
1784 application developers who want to investigate issues related to flow rules
1785 management. A dedicated error object is defined for this purpose:
1789 enum rte_flow_error_type {
1790 RTE_FLOW_ERROR_TYPE_NONE, /**< No error. */
1791 RTE_FLOW_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */
1792 RTE_FLOW_ERROR_TYPE_HANDLE, /**< Flow rule (handle). */
1793 RTE_FLOW_ERROR_TYPE_ATTR_GROUP, /**< Group field. */
1794 RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, /**< Priority field. */
1795 RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, /**< Ingress field. */
1796 RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, /**< Egress field. */
1797 RTE_FLOW_ERROR_TYPE_ATTR, /**< Attributes structure. */
1798 RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */
1799 RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */
1800 RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */
1801 RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */
1804 struct rte_flow_error {
1805 enum rte_flow_error_type type; /**< Cause field and error types. */
1806 const void *cause; /**< Object responsible for the error. */
1807 const char *message; /**< Human-readable error message. */
1810 Error type ``RTE_FLOW_ERROR_TYPE_NONE`` stands for no error, in which case
1811 remaining fields can be ignored. Other error types describe the type of the
1812 object pointed by ``cause``.
1814 If non-NULL, ``cause`` points to the object responsible for the error. For a
1815 flow rule, this may be a pattern item or an individual action.
1817 If non-NULL, ``message`` provides a human-readable error message.
1819 This object is normally allocated by applications and set by PMDs in case of
1820 error, the message points to a constant string which does not need to be
1821 freed by the application, however its pointer can be considered valid only
1822 as long as its associated DPDK port remains configured. Closing the
1823 underlying device or unloading the PMD invalidates it.
1834 rte_flow_error_set(struct rte_flow_error *error,
1836 enum rte_flow_error_type type,
1838 const char *message);
1840 This function initializes ``error`` (if non-NULL) with the provided
1841 parameters and sets ``rte_errno`` to ``code``. A negative error ``code`` is
1847 - DPDK does not keep track of flow rules definitions or flow rule objects
1848 automatically. Applications may keep track of the former and must keep
1849 track of the latter. PMDs may also do it for internal needs, however this
1850 must not be relied on by applications.
1852 - Flow rules are not maintained between successive port initializations. An
1853 application exiting without releasing them and restarting must re-create
1856 - API operations are synchronous and blocking (``EAGAIN`` cannot be
1859 - There is no provision for reentrancy/multi-thread safety, although nothing
1860 should prevent different devices from being configured at the same
1861 time. PMDs may protect their control path functions accordingly.
1863 - Stopping the data path (TX/RX) should not be necessary when managing flow
1864 rules. If this cannot be achieved naturally or with workarounds (such as
1865 temporarily replacing the burst function pointers), an appropriate error
1866 code must be returned (``EBUSY``).
1868 - PMDs, not applications, are responsible for maintaining flow rules
1869 configuration when stopping and restarting a port or performing other
1870 actions which may affect them. They can only be destroyed explicitly by
1873 For devices exposing multiple ports sharing global settings affected by flow
1876 - All ports under DPDK control must behave consistently, PMDs are
1877 responsible for making sure that existing flow rules on a port are not
1878 affected by other ports.
1880 - Ports not under DPDK control (unaffected or handled by other applications)
1881 are user's responsibility. They may affect existing flow rules and cause
1882 undefined behavior. PMDs aware of this may prevent flow rules creation
1883 altogether in such cases.
1888 The PMD interface is defined in ``rte_flow_driver.h``. It is not subject to
1889 API/ABI versioning constraints as it is not exposed to applications and may
1890 evolve independently.
1892 It is currently implemented on top of the legacy filtering framework through
1893 filter type *RTE_ETH_FILTER_GENERIC* that accepts the single operation
1894 *RTE_ETH_FILTER_GET* to return PMD-specific *rte_flow* callbacks wrapped
1895 inside ``struct rte_flow_ops``.
1897 This overhead is temporarily necessary in order to keep compatibility with
1898 the legacy filtering framework, which should eventually disappear.
1900 - PMD callbacks implement exactly the interface described in `Rules
1901 management`_, except for the port ID argument which has already been
1902 converted to a pointer to the underlying ``struct rte_eth_dev``.
1904 - Public API functions do not process flow rules definitions at all before
1905 calling PMD functions (no basic error checking, no validation
1906 whatsoever). They only make sure these callbacks are non-NULL or return
1907 the ``ENOSYS`` (function not supported) error.
1909 This interface additionally defines the following helper function:
1911 - ``rte_flow_ops_get()``: get generic flow operations structure from a
1914 More will be added over time.
1916 Device compatibility
1917 --------------------
1919 No known implementation supports all the described features.
1921 Unsupported features or combinations are not expected to be fully emulated
1922 in software by PMDs for performance reasons. Partially supported features
1923 may be completed in software as long as hardware performs most of the work
1924 (such as queue redirection and packet recognition).
1926 However PMDs are expected to do their best to satisfy application requests
1927 by working around hardware limitations as long as doing so does not affect
1928 the behavior of existing flow rules.
1930 The following sections provide a few examples of such cases and describe how
1931 PMDs should handle them, they are based on limitations built into the
1937 Each flow rule comes with its own, per-layer bit-masks, while hardware may
1938 support only a single, device-wide bit-mask for a given layer type, so that
1939 two IPv4 rules cannot use different bit-masks.
1941 The expected behavior in this case is that PMDs automatically configure
1942 global bit-masks according to the needs of the first flow rule created.
1944 Subsequent rules are allowed only if their bit-masks match those, the
1945 ``EEXIST`` error code should be returned otherwise.
1947 Unsupported layer types
1948 ~~~~~~~~~~~~~~~~~~~~~~~
1950 Many protocols can be simulated by crafting patterns with the `Item: RAW`_
1953 PMDs can rely on this capability to simulate support for protocols with
1954 headers not directly recognized by hardware.
1956 ``ANY`` pattern item
1957 ~~~~~~~~~~~~~~~~~~~~
1959 This pattern item stands for anything, which can be difficult to translate
1960 to something hardware would understand, particularly if followed by more
1963 Consider the following pattern:
1965 .. _table_rte_flow_unsupported_any:
1967 .. table:: Pattern with ANY as L3
1969 +-------+-----------------------+
1971 +=======+=======================+
1973 +-------+-----+---------+-------+
1974 | 1 | ANY | ``num`` | ``1`` |
1975 +-------+-----+---------+-------+
1977 +-------+-----------------------+
1979 +-------+-----------------------+
1981 Knowing that TCP does not make sense with something other than IPv4 and IPv6
1982 as L3, such a pattern may be translated to two flow rules instead:
1984 .. _table_rte_flow_unsupported_any_ipv4:
1986 .. table:: ANY replaced with IPV4
1988 +-------+--------------------+
1990 +=======+====================+
1992 +-------+--------------------+
1993 | 1 | IPV4 (zeroed mask) |
1994 +-------+--------------------+
1996 +-------+--------------------+
1998 +-------+--------------------+
2002 .. _table_rte_flow_unsupported_any_ipv6:
2004 .. table:: ANY replaced with IPV6
2006 +-------+--------------------+
2008 +=======+====================+
2010 +-------+--------------------+
2011 | 1 | IPV6 (zeroed mask) |
2012 +-------+--------------------+
2014 +-------+--------------------+
2016 +-------+--------------------+
2018 Note that as soon as a ANY rule covers several layers, this approach may
2019 yield a large number of hidden flow rules. It is thus suggested to only
2020 support the most common scenarios (anything as L2 and/or L3).
2025 - When combined with `Action: QUEUE`_, packet counting (`Action: COUNT`_)
2026 and tagging (`Action: MARK`_ or `Action: FLAG`_) may be implemented in
2027 software as long as the target queue is used by a single rule.
2029 - When a single target queue is provided, `Action: RSS`_ can also be
2030 implemented through `Action: QUEUE`_.
2035 While it would naturally make sense, flow rules cannot be assumed to be
2036 processed by hardware in the same order as their creation for several
2039 - They may be managed internally as a tree or a hash table instead of a
2041 - Removing a flow rule before adding another one can either put the new rule
2042 at the end of the list or reuse a freed entry.
2043 - Duplication may occur when packets are matched by several rules.
2045 For overlapping rules (particularly in order to use `Action: PASSTHRU`_)
2046 predictable behavior is only guaranteed by using different priority levels.
2048 Priority levels are not necessarily implemented in hardware, or may be
2049 severely limited (e.g. a single priority bit).
2051 For these reasons, priority levels may be implemented purely in software by
2054 - For devices expecting flow rules to be added in the correct order, PMDs
2055 may destroy and re-create existing rules after adding a new one with
2058 - A configurable number of dummy or empty rules can be created at
2059 initialization time to save high priority slots for later.
2061 - In order to save priority levels, PMDs may evaluate whether rules are
2062 likely to collide and adjust their priority accordingly.
2067 - A device profile selection function which could be used to force a
2068 permanent profile instead of relying on its automatic configuration based
2069 on existing flow rules.
2071 - A method to optimize *rte_flow* rules with specific pattern items and
2072 action types generated on the fly by PMDs. DPDK should assign negative
2073 numbers to these in order to not collide with the existing types. See
2076 - Adding specific egress pattern items and actions as described in
2077 `Attribute: Traffic direction`_.
2079 - Optional software fallback when PMDs are unable to handle requested flow
2080 rules so applications do not have to implement their own.