-/*-
- * BSD LICENSE
- *
- * Copyright 2016 6WIND S.A.
- * Copyright 2016 Mellanox.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of 6WIND S.A. nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2016 6WIND S.A.
+ * Copyright 2016 Mellanox Technologies, Ltd
*/
#ifndef RTE_FLOW_H_
* associated actions in hardware through flow rules.
*/
+#include <stddef.h>
+#include <stdint.h>
+
#include <rte_arp.h>
#include <rte_ether.h>
+#include <rte_eth_ctrl.h>
#include <rte_icmp.h>
#include <rte_ip.h>
#include <rte_sctp.h>
#include <rte_tcp.h>
#include <rte_udp.h>
+#include <rte_byteorder.h>
+#include <rte_esp.h>
#ifdef __cplusplus
extern "C" {
uint32_t priority; /**< Priority level within group. */
uint32_t ingress:1; /**< Rule applies to ingress traffic. */
uint32_t egress:1; /**< Rule applies to egress traffic. */
- uint32_t reserved:30; /**< Reserved, must be zero. */
+ /**
+ * Instead of simply matching the properties of traffic as it would
+ * appear on a given DPDK port ID, enabling this attribute transfers
+ * a flow rule to the lowest possible level of any device endpoints
+ * found in the pattern.
+ *
+ * When supported, this effectively enables an application to
+ * re-route traffic not necessarily intended for it (e.g. coming
+ * from or addressed to different physical ports, VFs or
+ * applications) at the device level.
+ *
+ * It complements the behavior of some pattern items such as
+ * RTE_FLOW_ITEM_TYPE_PHY_PORT and is meaningless without them.
+ *
+ * When transferring flow rules, ingress and egress attributes keep
+ * their original meaning, as if processing traffic emitted or
+ * received by the application.
+ */
+ uint32_t transfer:1;
+ uint32_t reserved:29; /**< Reserved, must be zero. */
};
/**
*
* Pattern items fall in two categories:
*
- * - Matching protocol headers and packet data (ANY, RAW, ETH, VLAN, IPV4,
- * IPV6, ICMP, UDP, TCP, SCTP, VXLAN and so on), usually associated with a
+ * - Matching protocol headers and packet data, usually associated with a
* specification structure. These must be stacked in the same order as the
- * protocol layers to match, starting from the lowest.
+ * protocol layers to match inside packets, starting from the lowest.
*
- * - Matching meta-data or affecting pattern processing (END, VOID, INVERT,
- * PF, VF, PORT and so on), often without a specification structure. Since
- * they do not match packet contents, these can be specified anywhere
- * within item lists without affecting others.
+ * - Matching meta-data or affecting pattern processing, often without a
+ * specification structure. Since they do not match packet contents, their
+ * position in the list is usually not relevant.
*
* See the description of individual types for more information. Those
* marked with [META] fall into the second category.
/**
* [META]
*
- * Matches packets addressed to the physical function of the device.
- *
- * If the underlying device function differs from the one that would
- * normally receive the matched traffic, specifying this item
- * prevents it from reaching that device unless the flow rule
- * contains a PF action. Packets are not duplicated between device
- * instances by default.
+ * Matches traffic originating from (ingress) or going to (egress)
+ * the physical function of the current device.
*
* No associated specification structure.
*/
/**
* [META]
*
- * Matches packets addressed to a virtual function ID of the device.
- *
- * If the underlying device function differs from the one that would
- * normally receive the matched traffic, specifying this item
- * prevents it from reaching that device unless the flow rule
- * contains a VF action. Packets are not duplicated between device
- * instances by default.
+ * Matches traffic originating from (ingress) or going to (egress) a
+ * given virtual function of the current device.
*
* See struct rte_flow_item_vf.
*/
/**
* [META]
*
- * Matches packets coming from the specified physical port of the
- * underlying device.
+ * Matches traffic originating from (ingress) or going to (egress) a
+ * physical port of the underlying device.
*
- * The first PORT item overrides the physical port normally
- * associated with the specified DPDK input port (port_id). This
- * item can be provided several times to match additional physical
- * ports.
+ * See struct rte_flow_item_phy_port.
+ */
+ RTE_FLOW_ITEM_TYPE_PHY_PORT,
+
+ /**
+ * [META]
+ *
+ * Matches traffic originating from (ingress) or going to (egress) a
+ * given DPDK port ID.
*
- * See struct rte_flow_item_port.
+ * See struct rte_flow_item_port_id.
*/
- RTE_FLOW_ITEM_TYPE_PORT,
+ RTE_FLOW_ITEM_TYPE_PORT_ID,
/**
* Matches a byte string of a given length at a given offset.
* See struct rte_flow_item_gre.
*/
RTE_FLOW_ITEM_TYPE_GRE,
+
+ /**
+ * [META]
+ *
+ * Fuzzy pattern match, expect faster than default.
+ *
+ * This is for device that support fuzzy matching option.
+ * Usually a fuzzy matching is fast but the cost is accuracy.
+ *
+ * See struct rte_flow_item_fuzzy.
+ */
+ RTE_FLOW_ITEM_TYPE_FUZZY,
+
+ /**
+ * Matches a GTP header.
+ *
+ * Configure flow for GTP packets.
+ *
+ * See struct rte_flow_item_gtp.
+ */
+ RTE_FLOW_ITEM_TYPE_GTP,
+
+ /**
+ * Matches a GTP header.
+ *
+ * Configure flow for GTP-C packets.
+ *
+ * See struct rte_flow_item_gtp.
+ */
+ RTE_FLOW_ITEM_TYPE_GTPC,
+
+ /**
+ * Matches a GTP header.
+ *
+ * Configure flow for GTP-U packets.
+ *
+ * See struct rte_flow_item_gtp.
+ */
+ RTE_FLOW_ITEM_TYPE_GTPU,
+
+ /**
+ * Matches a ESP header.
+ *
+ * See struct rte_flow_item_esp.
+ */
+ RTE_FLOW_ITEM_TYPE_ESP,
+
+ /**
+ * Matches a GENEVE header.
+ *
+ * See struct rte_flow_item_geneve.
+ */
+ RTE_FLOW_ITEM_TYPE_GENEVE,
+
+ /**
+ * Matches a VXLAN-GPE header.
+ *
+ * See struct rte_flow_item_vxlan_gpe.
+ */
+ RTE_FLOW_ITEM_TYPE_VXLAN_GPE,
};
/**
};
/** Default mask for RTE_FLOW_ITEM_TYPE_ANY. */
+#ifndef __cplusplus
static const struct rte_flow_item_any rte_flow_item_any_mask = {
.num = 0x00000000,
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_VF
*
- * Matches packets addressed to a virtual function ID of the device.
+ * Matches traffic originating from (ingress) or going to (egress) a given
+ * virtual function of the current device.
+ *
+ * If supported, should work even if the virtual function is not managed by
+ * the application and thus not associated with a DPDK port ID.
*
- * If the underlying device function differs from the one that would
- * normally receive the matched traffic, specifying this item prevents it
- * from reaching that device unless the flow rule contains a VF
- * action. Packets are not duplicated between device instances by default.
+ * Note this pattern item does not match VF representors traffic which, as
+ * separate entities, should be addressed through their own DPDK port IDs.
*
- * - Likely to return an error or never match any traffic if this causes a
- * VF device to match traffic addressed to a different VF.
* - Can be specified multiple times to match traffic addressed to several
* VF IDs.
* - Can be combined with a PF item to match both PF and VF traffic.
* A zeroed mask can be used to match any VF ID.
*/
struct rte_flow_item_vf {
- uint32_t id; /**< Destination VF ID. */
+ uint32_t id; /**< VF ID. */
};
/** Default mask for RTE_FLOW_ITEM_TYPE_VF. */
+#ifndef __cplusplus
static const struct rte_flow_item_vf rte_flow_item_vf_mask = {
.id = 0x00000000,
};
+#endif
/**
- * RTE_FLOW_ITEM_TYPE_PORT
+ * RTE_FLOW_ITEM_TYPE_PHY_PORT
*
- * Matches packets coming from the specified physical port of the underlying
- * device.
+ * Matches traffic originating from (ingress) or going to (egress) a
+ * physical port of the underlying device.
*
- * The first PORT item overrides the physical port normally associated with
- * the specified DPDK input port (port_id). This item can be provided
+ * The first PHY_PORT item overrides the physical port normally associated
+ * with the specified DPDK input port (port_id). This item can be provided
* several times to match additional physical ports.
*
* Note that physical ports are not necessarily tied to DPDK input ports
*
* A zeroed mask can be used to match any port index.
*/
-struct rte_flow_item_port {
+struct rte_flow_item_phy_port {
uint32_t index; /**< Physical port index. */
};
-/** Default mask for RTE_FLOW_ITEM_TYPE_PORT. */
-static const struct rte_flow_item_port rte_flow_item_port_mask = {
+/** Default mask for RTE_FLOW_ITEM_TYPE_PHY_PORT. */
+#ifndef __cplusplus
+static const struct rte_flow_item_phy_port rte_flow_item_phy_port_mask = {
.index = 0x00000000,
};
+#endif
+
+/**
+ * RTE_FLOW_ITEM_TYPE_PORT_ID
+ *
+ * Matches traffic originating from (ingress) or going to (egress) a given
+ * DPDK port ID.
+ *
+ * Normally only supported if the port ID in question is known by the
+ * underlying PMD and related to the device the flow rule is created
+ * against.
+ *
+ * This must not be confused with @p PHY_PORT which refers to the physical
+ * port of a device, whereas @p PORT_ID refers to a struct rte_eth_dev
+ * object on the application side (also known as "port representor"
+ * depending on the kind of underlying device).
+ */
+struct rte_flow_item_port_id {
+ uint32_t id; /**< DPDK port ID. */
+};
+
+/** Default mask for RTE_FLOW_ITEM_TYPE_PORT_ID. */
+#ifndef __cplusplus
+static const struct rte_flow_item_port_id rte_flow_item_port_id_mask = {
+ .id = 0xffffffff,
+};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_RAW
int32_t offset; /**< Absolute or relative offset for pattern. */
uint16_t limit; /**< Search area limit for start of pattern. */
uint16_t length; /**< Pattern length. */
- uint8_t pattern[]; /**< Byte string to look for. */
+ const uint8_t *pattern; /**< Byte string to look for. */
};
/** Default mask for RTE_FLOW_ITEM_TYPE_RAW. */
+#ifndef __cplusplus
static const struct rte_flow_item_raw rte_flow_item_raw_mask = {
.relative = 1,
.search = 1,
.offset = 0xffffffff,
.limit = 0xffff,
.length = 0xffff,
+ .pattern = NULL,
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_ETH
*
* Matches an Ethernet header.
+ *
+ * The @p type field either stands for "EtherType" or "TPID" when followed
+ * by so-called layer 2.5 pattern items such as RTE_FLOW_ITEM_TYPE_VLAN. In
+ * the latter case, @p type refers to that of the outer header, with the
+ * inner EtherType/TPID provided by the subsequent pattern item. This is the
+ * same order as on the wire.
*/
struct rte_flow_item_eth {
struct ether_addr dst; /**< Destination MAC. */
struct ether_addr src; /**< Source MAC. */
- uint16_t type; /**< EtherType. */
+ rte_be16_t type; /**< EtherType or TPID. */
};
/** Default mask for RTE_FLOW_ITEM_TYPE_ETH. */
+#ifndef __cplusplus
static const struct rte_flow_item_eth rte_flow_item_eth_mask = {
.dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
.src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .type = 0x0000,
+ .type = RTE_BE16(0x0000),
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_VLAN
*
* Matches an 802.1Q/ad VLAN tag.
*
- * This type normally follows either RTE_FLOW_ITEM_TYPE_ETH or
- * RTE_FLOW_ITEM_TYPE_VLAN.
+ * The corresponding standard outer EtherType (TPID) values are
+ * ETHER_TYPE_VLAN or ETHER_TYPE_QINQ. It can be overridden by the preceding
+ * pattern item.
*/
struct rte_flow_item_vlan {
- uint16_t tpid; /**< Tag protocol identifier. */
- uint16_t tci; /**< Tag control information. */
+ rte_be16_t tci; /**< Tag control information. */
+ rte_be16_t inner_type; /**< Inner EtherType or TPID. */
};
/** Default mask for RTE_FLOW_ITEM_TYPE_VLAN. */
+#ifndef __cplusplus
static const struct rte_flow_item_vlan rte_flow_item_vlan_mask = {
- .tpid = 0x0000,
- .tci = 0xffff,
+ .tci = RTE_BE16(0x0fff),
+ .inner_type = RTE_BE16(0x0000),
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_IPV4
};
/** Default mask for RTE_FLOW_ITEM_TYPE_IPV4. */
+#ifndef __cplusplus
static const struct rte_flow_item_ipv4 rte_flow_item_ipv4_mask = {
.hdr = {
- .src_addr = 0xffffffff,
- .dst_addr = 0xffffffff,
+ .src_addr = RTE_BE32(0xffffffff),
+ .dst_addr = RTE_BE32(0xffffffff),
},
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_IPV6.
};
/** Default mask for RTE_FLOW_ITEM_TYPE_IPV6. */
+#ifndef __cplusplus
static const struct rte_flow_item_ipv6 rte_flow_item_ipv6_mask = {
.hdr = {
.src_addr =
"\xff\xff\xff\xff\xff\xff\xff\xff",
},
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_ICMP.
};
/** Default mask for RTE_FLOW_ITEM_TYPE_ICMP. */
+#ifndef __cplusplus
static const struct rte_flow_item_icmp rte_flow_item_icmp_mask = {
.hdr = {
.icmp_type = 0xff,
.icmp_code = 0xff,
},
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_UDP.
};
/** Default mask for RTE_FLOW_ITEM_TYPE_UDP. */
+#ifndef __cplusplus
static const struct rte_flow_item_udp rte_flow_item_udp_mask = {
.hdr = {
- .src_port = 0xffff,
- .dst_port = 0xffff,
+ .src_port = RTE_BE16(0xffff),
+ .dst_port = RTE_BE16(0xffff),
},
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_TCP.
};
/** Default mask for RTE_FLOW_ITEM_TYPE_TCP. */
+#ifndef __cplusplus
static const struct rte_flow_item_tcp rte_flow_item_tcp_mask = {
.hdr = {
- .src_port = 0xffff,
- .dst_port = 0xffff,
+ .src_port = RTE_BE16(0xffff),
+ .dst_port = RTE_BE16(0xffff),
},
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_SCTP.
};
/** Default mask for RTE_FLOW_ITEM_TYPE_SCTP. */
+#ifndef __cplusplus
static const struct rte_flow_item_sctp rte_flow_item_sctp_mask = {
.hdr = {
- .src_port = 0xffff,
- .dst_port = 0xffff,
+ .src_port = RTE_BE16(0xffff),
+ .dst_port = RTE_BE16(0xffff),
},
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_VXLAN.
};
/** Default mask for RTE_FLOW_ITEM_TYPE_VXLAN. */
+#ifndef __cplusplus
static const struct rte_flow_item_vxlan rte_flow_item_vxlan_mask = {
.vni = "\xff\xff\xff",
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_E_TAG.
*
* Matches a E-tag header.
+ *
+ * The corresponding standard outer EtherType (TPID) value is
+ * ETHER_TYPE_ETAG. It can be overridden by the preceding pattern item.
*/
struct rte_flow_item_e_tag {
- uint16_t tpid; /**< Tag protocol identifier (0x893F). */
/**
* E-Tag control information (E-TCI).
* E-PCP (3b), E-DEI (1b), ingress E-CID base (12b).
*/
- uint16_t epcp_edei_in_ecid_b;
+ rte_be16_t epcp_edei_in_ecid_b;
/** Reserved (2b), GRP (2b), E-CID base (12b). */
- uint16_t rsvd_grp_ecid_b;
+ rte_be16_t rsvd_grp_ecid_b;
uint8_t in_ecid_e; /**< Ingress E-CID ext. */
uint8_t ecid_e; /**< E-CID ext. */
+ rte_be16_t inner_type; /**< Inner EtherType or TPID. */
};
+/** Default mask for RTE_FLOW_ITEM_TYPE_E_TAG. */
+#ifndef __cplusplus
+static const struct rte_flow_item_e_tag rte_flow_item_e_tag_mask = {
+ .rsvd_grp_ecid_b = RTE_BE16(0x3fff),
+};
+#endif
+
/**
* RTE_FLOW_ITEM_TYPE_NVGRE.
*
*
* c_k_s_rsvd0_ver must have value 0x2000 according to RFC 7637.
*/
- uint16_t c_k_s_rsvd0_ver;
- uint16_t protocol; /**< Protocol type (0x6558). */
+ rte_be16_t c_k_s_rsvd0_ver;
+ rte_be16_t protocol; /**< Protocol type (0x6558). */
uint8_t tni[3]; /**< Virtual subnet ID. */
uint8_t flow_id; /**< Flow ID. */
};
+/** Default mask for RTE_FLOW_ITEM_TYPE_NVGRE. */
+#ifndef __cplusplus
+static const struct rte_flow_item_nvgre rte_flow_item_nvgre_mask = {
+ .tni = "\xff\xff\xff",
+};
+#endif
+
/**
* RTE_FLOW_ITEM_TYPE_MPLS.
*
};
/** Default mask for RTE_FLOW_ITEM_TYPE_MPLS. */
+#ifndef __cplusplus
static const struct rte_flow_item_mpls rte_flow_item_mpls_mask = {
.label_tc_s = "\xff\xff\xf0",
};
+#endif
/**
* RTE_FLOW_ITEM_TYPE_GRE.
* Checksum (1b), reserved 0 (12b), version (3b).
* Refer to RFC 2784.
*/
- uint16_t c_rsvd0_ver;
- uint16_t protocol; /**< Protocol type. */
+ rte_be16_t c_rsvd0_ver;
+ rte_be16_t protocol; /**< Protocol type. */
};
/** Default mask for RTE_FLOW_ITEM_TYPE_GRE. */
+#ifndef __cplusplus
static const struct rte_flow_item_gre rte_flow_item_gre_mask = {
- .protocol = 0xffff,
+ .protocol = RTE_BE16(0xffff),
+};
+#endif
+
+/**
+ * RTE_FLOW_ITEM_TYPE_FUZZY
+ *
+ * Fuzzy pattern match, expect faster than default.
+ *
+ * This is for device that support fuzzy match option.
+ * Usually a fuzzy match is fast but the cost is accuracy.
+ * i.e. Signature Match only match pattern's hash value, but it is
+ * possible two different patterns have the same hash value.
+ *
+ * Matching accuracy level can be configure by threshold.
+ * Driver can divide the range of threshold and map to different
+ * accuracy levels that device support.
+ *
+ * Threshold 0 means perfect match (no fuzziness), while threshold
+ * 0xffffffff means fuzziest match.
+ */
+struct rte_flow_item_fuzzy {
+ uint32_t thresh; /**< Accuracy threshold. */
+};
+
+/** Default mask for RTE_FLOW_ITEM_TYPE_FUZZY. */
+#ifndef __cplusplus
+static const struct rte_flow_item_fuzzy rte_flow_item_fuzzy_mask = {
+ .thresh = 0xffffffff,
+};
+#endif
+
+/**
+ * RTE_FLOW_ITEM_TYPE_GTP.
+ *
+ * Matches a GTPv1 header.
+ */
+struct rte_flow_item_gtp {
+ /**
+ * Version (3b), protocol type (1b), reserved (1b),
+ * Extension header flag (1b),
+ * Sequence number flag (1b),
+ * N-PDU number flag (1b).
+ */
+ uint8_t v_pt_rsv_flags;
+ uint8_t msg_type; /**< Message type. */
+ rte_be16_t msg_len; /**< Message length. */
+ rte_be32_t teid; /**< Tunnel endpoint identifier. */
};
+/** Default mask for RTE_FLOW_ITEM_TYPE_GTP. */
+#ifndef __cplusplus
+static const struct rte_flow_item_gtp rte_flow_item_gtp_mask = {
+ .teid = RTE_BE32(0xffffffff),
+};
+#endif
+
+/**
+ * RTE_FLOW_ITEM_TYPE_ESP
+ *
+ * Matches an ESP header.
+ */
+struct rte_flow_item_esp {
+ struct esp_hdr hdr; /**< ESP header definition. */
+};
+
+/** Default mask for RTE_FLOW_ITEM_TYPE_ESP. */
+#ifndef __cplusplus
+static const struct rte_flow_item_esp rte_flow_item_esp_mask = {
+ .hdr = {
+ .spi = 0xffffffff,
+ },
+};
+#endif
+
+/**
+ * RTE_FLOW_ITEM_TYPE_GENEVE.
+ *
+ * Matches a GENEVE header.
+ */
+struct rte_flow_item_geneve {
+ /**
+ * Version (2b), length of the options fields (6b), OAM packet (1b),
+ * critical options present (1b), reserved 0 (6b).
+ */
+ rte_be16_t ver_opt_len_o_c_rsvd0;
+ rte_be16_t protocol; /**< Protocol type. */
+ uint8_t vni[3]; /**< Virtual Network Identifier. */
+ uint8_t rsvd1; /**< Reserved, normally 0x00. */
+};
+
+/** Default mask for RTE_FLOW_ITEM_TYPE_GENEVE. */
+#ifndef __cplusplus
+static const struct rte_flow_item_geneve rte_flow_item_geneve_mask = {
+ .vni = "\xff\xff\xff",
+};
+#endif
+
+/**
+ * RTE_FLOW_ITEM_TYPE_VXLAN_GPE (draft-ietf-nvo3-vxlan-gpe-05).
+ *
+ * Matches a VXLAN-GPE header.
+ */
+struct rte_flow_item_vxlan_gpe {
+ uint8_t flags; /**< Normally 0x0c (I and P flags). */
+ uint8_t rsvd0[2]; /**< Reserved, normally 0x0000. */
+ uint8_t protocol; /**< Protocol type. */
+ uint8_t vni[3]; /**< VXLAN identifier. */
+ uint8_t rsvd1; /**< Reserved, normally 0x00. */
+};
+
+/** Default mask for RTE_FLOW_ITEM_TYPE_VXLAN_GPE. */
+#ifndef __cplusplus
+static const struct rte_flow_item_vxlan_gpe rte_flow_item_vxlan_gpe_mask = {
+ .vni = "\xff\xff\xff",
+};
+#endif
+
/**
* Matching pattern item definition.
*
*
* Each possible action is represented by a type. Some have associated
* configuration structures. Several actions combined in a list can be
- * affected to a flow rule. That list is not ordered.
+ * assigned to a flow rule and are performed in order.
*
* They fall in three categories:
*
- * - Terminating actions (such as QUEUE, DROP, RSS, PF, VF) that prevent
- * processing matched packets by subsequent flow rules, unless overridden
- * with PASSTHRU.
+ * - Actions that modify the fate of matching traffic, for instance by
+ * dropping or assigning it a specific destination.
*
- * - Non terminating actions (PASSTHRU, DUP) that leave matched packets up
- * for additional processing by subsequent flow rules.
+ * - Actions that modify matching traffic contents or its properties. This
+ * includes adding/removing encapsulation, encryption, compression and
+ * marks.
*
- * - Other non terminating meta actions that do not affect the fate of
- * packets (END, VOID, MARK, FLAG, COUNT).
+ * - Actions related to the flow rule itself, such as updating counters or
+ * making it non-terminating.
*
- * When several actions are combined in a flow rule, they should all have
- * different types (e.g. dropping a packet twice is not possible).
+ * Flow rules being terminating by default, not specifying any action of the
+ * fate kind results in undefined behavior. This applies to both ingress and
+ * egress.
*
- * Only the last action of a given type is taken into account. PMDs still
- * perform error checking on the entire list.
- *
- * Note that PASSTHRU is the only action able to override a terminating
- * rule.
+ * PASSTHRU, when supported, makes a flow rule non-terminating.
*/
enum rte_flow_action_type {
/**
- * [META]
- *
* End marker for action lists. Prevents further processing of
* actions, thereby ending the list.
*
RTE_FLOW_ACTION_TYPE_END,
/**
- * [META]
- *
* Used as a placeholder for convenience. It is ignored and simply
* discarded by PMDs.
*
RTE_FLOW_ACTION_TYPE_VOID,
/**
- * Leaves packets up for additional processing by subsequent flow
- * rules. This is the default when a rule does not contain a
- * terminating action, but can be specified to force a rule to
- * become non-terminating.
+ * Leaves traffic up for additional processing by subsequent flow
+ * rules; makes a flow rule non-terminating.
*
* No associated configuration structure.
*/
RTE_FLOW_ACTION_TYPE_PASSTHRU,
/**
- * [META]
- *
* Attaches an integer value to packets and sets PKT_RX_FDIR and
* PKT_RX_FDIR_ID mbuf flags.
*
RTE_FLOW_ACTION_TYPE_MARK,
/**
- * [META]
- *
* Flags packets. Similar to MARK without a specific value; only
* sets the PKT_RX_FDIR mbuf flag.
*
RTE_FLOW_ACTION_TYPE_DROP,
/**
- * [META]
- *
- * Enables counters for this rule.
+ * Enables counters for this flow rule.
*
* These counters can be retrieved and reset through rte_flow_query(),
* see struct rte_flow_query_count.
*/
RTE_FLOW_ACTION_TYPE_COUNT,
- /**
- * Duplicates packets to a given queue index.
- *
- * This is normally combined with QUEUE, however when used alone, it
- * is actually similar to QUEUE + PASSTHRU.
- *
- * See struct rte_flow_action_dup.
- */
- RTE_FLOW_ACTION_TYPE_DUP,
-
/**
* Similar to QUEUE, except RSS is additionally performed on packets
* to spread them among several queues according to the provided
RTE_FLOW_ACTION_TYPE_RSS,
/**
- * Redirects packets to the physical function (PF) of the current
- * device.
+ * Directs matching traffic to the physical function (PF) of the
+ * current device.
*
* No associated configuration structure.
*/
RTE_FLOW_ACTION_TYPE_PF,
/**
- * Redirects packets to the virtual function (VF) of the current
- * device with the specified ID.
+ * Directs matching traffic to a given virtual function of the
+ * current device.
*
* See struct rte_flow_action_vf.
*/
RTE_FLOW_ACTION_TYPE_VF,
+
+ /**
+ * Directs packets to a given physical port index of the underlying
+ * device.
+ *
+ * See struct rte_flow_action_phy_port.
+ */
+ RTE_FLOW_ACTION_TYPE_PHY_PORT,
+
+ /**
+ * Directs matching traffic to a given DPDK port ID.
+ *
+ * See struct rte_flow_action_port_id.
+ */
+ RTE_FLOW_ACTION_TYPE_PORT_ID,
+
+ /**
+ * Traffic metering and policing (MTR).
+ *
+ * See struct rte_flow_action_meter.
+ * See file rte_mtr.h for MTR object configuration.
+ */
+ RTE_FLOW_ACTION_TYPE_METER,
+
+ /**
+ * Redirects packets to security engine of current device for security
+ * processing as specified by security session.
+ *
+ * See struct rte_flow_action_security.
+ */
+ RTE_FLOW_ACTION_TYPE_SECURITY
};
/**
* RTE_FLOW_ACTION_TYPE_QUEUE
*
* Assign packets to a given queue index.
- *
- * Terminating by default.
*/
struct rte_flow_action_queue {
uint16_t index; /**< Queue index to use. */
uint64_t bytes; /**< Number of bytes through this rule [out]. */
};
-/**
- * RTE_FLOW_ACTION_TYPE_DUP
- *
- * Duplicates packets to a given queue index.
- *
- * This is normally combined with QUEUE, however when used alone, it is
- * actually similar to QUEUE + PASSTHRU.
- *
- * Non-terminating by default.
- */
-struct rte_flow_action_dup {
- uint16_t index; /**< Queue index to duplicate packets to. */
-};
-
/**
* RTE_FLOW_ACTION_TYPE_RSS
*
* Similar to QUEUE, except RSS is additionally performed on packets to
* spread them among several queues according to the provided parameters.
*
+ * Unlike global RSS settings used by other DPDK APIs, unsetting the
+ * @p types field does not disable RSS in a flow rule. Doing so instead
+ * requests safe unspecified "best-effort" settings from the underlying PMD,
+ * which depending on the flow rule, may result in anything ranging from
+ * empty (single queue) to all-inclusive RSS.
+ *
* Note: RSS hash result is stored in the hash.rss mbuf field which overlaps
* hash.fdir.lo. Since the MARK action sets the hash.fdir.hi field only,
* both can be requested simultaneously.
- *
- * Terminating by default.
*/
struct rte_flow_action_rss {
- const struct rte_eth_rss_conf *rss_conf; /**< RSS parameters. */
- uint16_t num; /**< Number of entries in queue[]. */
- uint16_t queue[]; /**< Queues indices to use. */
+ enum rte_eth_hash_function func; /**< RSS hash function to apply. */
+ /**
+ * Packet encapsulation level RSS hash @p types apply to.
+ *
+ * - @p 0 requests the default behavior. Depending on the packet
+ * type, it can mean outermost, innermost, anything in between or
+ * even no RSS.
+ *
+ * It basically stands for the innermost encapsulation level RSS
+ * can be performed on according to PMD and device capabilities.
+ *
+ * - @p 1 requests RSS to be performed on the outermost packet
+ * encapsulation level.
+ *
+ * - @p 2 and subsequent values request RSS to be performed on the
+ * specified inner packet encapsulation level, from outermost to
+ * innermost (lower to higher values).
+ *
+ * Values other than @p 0 are not necessarily supported.
+ *
+ * Requesting a specific RSS level on unrecognized traffic results
+ * in undefined behavior. For predictable results, it is recommended
+ * to make the flow rule pattern match packet headers up to the
+ * requested encapsulation level so that only matching traffic goes
+ * through.
+ */
+ uint32_t level;
+ uint64_t types; /**< Specific RSS hash types (see ETH_RSS_*). */
+ uint32_t key_len; /**< Hash key length in bytes. */
+ uint32_t queue_num; /**< Number of entries in @p queue. */
+ const uint8_t *key; /**< Hash key. */
+ const uint16_t *queue; /**< Queue indices to use. */
};
/**
* RTE_FLOW_ACTION_TYPE_VF
*
- * Redirects packets to a virtual function (VF) of the current device.
+ * Directs matching traffic to a given virtual function of the current
+ * device.
*
* Packets matched by a VF pattern item can be redirected to their original
* VF ID instead of the specified one. This parameter may not be available
* and is not guaranteed to work properly if the VF part is matched by a
* prior flow rule or if packets are not addressed to a VF in the first
* place.
- *
- * Terminating by default.
*/
struct rte_flow_action_vf {
uint32_t original:1; /**< Use original VF ID if possible. */
uint32_t reserved:31; /**< Reserved, must be zero. */
- uint32_t id; /**< VF ID to redirect packets to. */
+ uint32_t id; /**< VF ID. */
+};
+
+/**
+ * RTE_FLOW_ACTION_TYPE_PHY_PORT
+ *
+ * Directs packets to a given physical port index of the underlying
+ * device.
+ *
+ * @see RTE_FLOW_ITEM_TYPE_PHY_PORT
+ */
+struct rte_flow_action_phy_port {
+ uint32_t original:1; /**< Use original port index if possible. */
+ uint32_t reserved:31; /**< Reserved, must be zero. */
+ uint32_t index; /**< Physical port index. */
+};
+
+/**
+ * RTE_FLOW_ACTION_TYPE_PORT_ID
+ *
+ * Directs matching traffic to a given DPDK port ID.
+ *
+ * @see RTE_FLOW_ITEM_TYPE_PORT_ID
+ */
+struct rte_flow_action_port_id {
+ uint32_t original:1; /**< Use original DPDK port ID if possible. */
+ uint32_t reserved:31; /**< Reserved, must be zero. */
+ uint32_t id; /**< DPDK port ID. */
+};
+
+/**
+ * RTE_FLOW_ACTION_TYPE_METER
+ *
+ * Traffic metering and policing (MTR).
+ *
+ * Packets matched by items of this type can be either dropped or passed to the
+ * next item with their color set by the MTR object.
+ */
+struct rte_flow_action_meter {
+ uint32_t mtr_id; /**< MTR object ID created with rte_mtr_create(). */
+};
+
+/**
+ * RTE_FLOW_ACTION_TYPE_SECURITY
+ *
+ * Perform the security action on flows matched by the pattern items
+ * according to the configuration of the security session.
+ *
+ * This action modifies the payload of matched flows. For INLINE_CRYPTO, the
+ * security protocol headers and IV are fully provided by the application as
+ * specified in the flow pattern. The payload of matching packets is
+ * encrypted on egress, and decrypted and authenticated on ingress.
+ * For INLINE_PROTOCOL, the security protocol is fully offloaded to HW,
+ * providing full encapsulation and decapsulation of packets in security
+ * protocols. The flow pattern specifies both the outer security header fields
+ * and the inner packet fields. The security session specified in the action
+ * must match the pattern parameters.
+ *
+ * The security session specified in the action must be created on the same
+ * port as the flow action that is being specified.
+ *
+ * The ingress/egress flow attribute should match that specified in the
+ * security session if the security session supports the definition of the
+ * direction.
+ *
+ * Multiple flows can be configured to use the same security session.
+ */
+struct rte_flow_action_security {
+ void *security_session; /**< Pointer to security session structure. */
};
/**
RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, /**< Priority field. */
RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, /**< Ingress field. */
RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, /**< Egress field. */
+ RTE_FLOW_ERROR_TYPE_ATTR_TRANSFER, /**< Transfer field. */
RTE_FLOW_ERROR_TYPE_ATTR, /**< Attributes structure. */
RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */
+ RTE_FLOW_ERROR_TYPE_ITEM_SPEC, /**< Item specification. */
+ RTE_FLOW_ERROR_TYPE_ITEM_LAST, /**< Item specification range. */
+ RTE_FLOW_ERROR_TYPE_ITEM_MASK, /**< Item specification mask. */
RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */
RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */
+ RTE_FLOW_ERROR_TYPE_ACTION_CONF, /**< Action configuration. */
RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */
};
/**
* Check whether a flow rule can be created on a given port.
*
- * While this function has no effect on the target device, the flow rule is
- * validated against its current configuration state and the returned value
- * should be considered valid by the caller for that state only.
+ * The flow rule is validated for correctness and whether it could be accepted
+ * by the device given sufficient resources. The rule is checked against the
+ * current device mode and queue configuration. The flow rule may also
+ * optionally be validated against existing flow rules and device resources.
+ * This function has no effect on the target device.
*
* The returned value is guaranteed to remain valid only as long as no
* successful calls to rte_flow_create() or rte_flow_destroy() are made in
*
* -ENOSYS: underlying device does not support this functionality.
*
+ * -EIO: underlying device is removed.
+ *
* -EINVAL: unknown or invalid rule specification.
*
* -ENOTSUP: valid but unsupported rule specification (e.g. partial
* bit-masks are unsupported).
*
- * -EEXIST: collision with an existing rule.
+ * -EEXIST: collision with an existing rule. Only returned if device
+ * supports flow rule collision checking and there was a flow rule
+ * collision. Not receiving this return code is no guarantee that creating
+ * the rule will not fail due to a collision.
*
- * -ENOMEM: not enough resources.
+ * -ENOMEM: not enough memory to execute the function, or if the device
+ * supports resource validation, resource limitation on the device.
*
* -EBUSY: action cannot be performed due to busy device resources, may
* succeed if the affected queues or even the entire port are in a stopped
* state (see rte_eth_dev_rx_queue_stop() and rte_eth_dev_stop()).
*/
int
-rte_flow_validate(uint8_t port_id,
+rte_flow_validate(uint16_t port_id,
const struct rte_flow_attr *attr,
const struct rte_flow_item pattern[],
const struct rte_flow_action actions[],
* rte_flow_validate().
*/
struct rte_flow *
-rte_flow_create(uint8_t port_id,
+rte_flow_create(uint16_t port_id,
const struct rte_flow_attr *attr,
const struct rte_flow_item pattern[],
const struct rte_flow_action actions[],
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-rte_flow_destroy(uint8_t port_id,
+rte_flow_destroy(uint16_t port_id,
struct rte_flow *flow,
struct rte_flow_error *error);
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-rte_flow_flush(uint8_t port_id,
+rte_flow_flush(uint16_t port_id,
struct rte_flow_error *error);
/**
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-rte_flow_query(uint8_t port_id,
+rte_flow_query(uint16_t port_id,
struct rte_flow *flow,
enum rte_flow_action_type action,
void *data,
struct rte_flow_error *error);
+/**
+ * Restrict ingress traffic to the defined flow rules.
+ *
+ * Isolated mode guarantees that all ingress traffic comes from defined flow
+ * rules only (current and future).
+ *
+ * Besides making ingress more deterministic, it allows PMDs to safely reuse
+ * resources otherwise assigned to handle the remaining traffic, such as
+ * global RSS configuration settings, VLAN filters, MAC address entries,
+ * legacy filter API rules and so on in order to expand the set of possible
+ * flow rule types.
+ *
+ * Calling this function as soon as possible after device initialization,
+ * ideally before the first call to rte_eth_dev_configure(), is recommended
+ * to avoid possible failures due to conflicting settings.
+ *
+ * Once effective, leaving isolated mode may not be possible depending on
+ * PMD implementation.
+ *
+ * Additionally, the following functionality has no effect on the underlying
+ * port and may return errors such as ENOTSUP ("not supported"):
+ *
+ * - Toggling promiscuous mode.
+ * - Toggling allmulticast mode.
+ * - Configuring MAC addresses.
+ * - Configuring multicast addresses.
+ * - Configuring VLAN filters.
+ * - Configuring Rx filters through the legacy API (e.g. FDIR).
+ * - Configuring global RSS settings.
+ *
+ * @param port_id
+ * Port identifier of Ethernet device.
+ * @param set
+ * Nonzero to enter isolated mode, attempt to leave it otherwise.
+ * @param[out] error
+ * Perform verbose error reporting if not NULL. PMDs initialize this
+ * structure in case of error only.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+rte_flow_isolate(uint16_t port_id, int set, struct rte_flow_error *error);
+
+/**
+ * Initialize flow error structure.
+ *
+ * @param[out] error
+ * Pointer to flow error structure (may be NULL).
+ * @param code
+ * Related error code (rte_errno).
+ * @param type
+ * Cause field and error types.
+ * @param cause
+ * Object responsible for the error.
+ * @param message
+ * Human-readable error message.
+ *
+ * @return
+ * Negative error code (errno value) and rte_errno is set.
+ */
+int
+rte_flow_error_set(struct rte_flow_error *error,
+ int code,
+ enum rte_flow_error_type type,
+ const void *cause,
+ const char *message);
+
+/**
+ * Generic flow representation.
+ *
+ * This form is sufficient to describe an rte_flow independently from any
+ * PMD implementation and allows for replayability and identification.
+ */
+struct rte_flow_desc {
+ size_t size; /**< Allocated space including data[]. */
+ struct rte_flow_attr attr; /**< Attributes. */
+ struct rte_flow_item *items; /**< Items. */
+ struct rte_flow_action *actions; /**< Actions. */
+ uint8_t data[]; /**< Storage for items/actions. */
+};
+
+/**
+ * Copy an rte_flow rule description.
+ *
+ * @param[in] fd
+ * Flow rule description.
+ * @param[in] len
+ * Total size of allocated data for the flow description.
+ * @param[in] attr
+ * Flow rule attributes.
+ * @param[in] items
+ * Pattern specification (list terminated by the END pattern item).
+ * @param[in] actions
+ * Associated actions (list terminated by the END action).
+ *
+ * @return
+ * If len is greater or equal to the size of the flow, the total size of the
+ * flow description and its data.
+ * If len is lower than the size of the flow, the number of bytes that would
+ * have been written to desc had it been sufficient. Nothing is written.
+ */
+size_t
+rte_flow_copy(struct rte_flow_desc *fd, size_t len,
+ const struct rte_flow_attr *attr,
+ const struct rte_flow_item *items,
+ const struct rte_flow_action *actions);
+
#ifdef __cplusplus
}
#endif