From: Adrien Mazarguil Date: Wed, 21 Dec 2016 14:51:17 +0000 (+0100) Subject: ethdev: introduce generic flow API X-Git-Tag: spdx-start~5264 X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=b1a4b4cbc0a8;p=dpdk.git ethdev: introduce generic flow API This new API supersedes all the legacy filter types described in rte_eth_ctrl.h. It is slightly higher level and as a result relies more on PMDs to process and validate flow rules. Benefits: - A unified API is easier to program for, applications do not have to be written for a specific filter type which may or may not be supported by the underlying device. - The behavior of a flow rule is the same regardless of the underlying device, applications do not need to be aware of hardware quirks. - Extensible by design, API/ABI breakage should rarely occur if at all. - Documentation is self-standing, no need to look up elsewhere. Existing filter types will be deprecated and removed in the near future. Signed-off-by: Adrien Mazarguil Acked-by: Olga Shern --- diff --git a/MAINTAINERS b/MAINTAINERS index 3bb0b99566..ebc97b8d25 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -243,6 +243,10 @@ M: Thomas Monjalon F: lib/librte_ether/ F: scripts/test-null.sh +Flow API +M: Adrien Mazarguil +F: lib/librte_ether/rte_flow* + Crypto API M: Declan Doherty F: lib/librte_cryptodev/ diff --git a/doc/api/doxy-api-index.md b/doc/api/doxy-api-index.md index de65b4ca9a..4951552f64 100644 --- a/doc/api/doxy-api-index.md +++ b/doc/api/doxy-api-index.md @@ -39,6 +39,8 @@ There are many libraries, so their headers may be grouped by topics: [dev] (@ref rte_dev.h), [ethdev] (@ref rte_ethdev.h), [ethctrl] (@ref rte_eth_ctrl.h), + [rte_flow] (@ref rte_flow.h), + [rte_flow_driver] (@ref rte_flow_driver.h), [cryptodev] (@ref rte_cryptodev.h), [devargs] (@ref rte_devargs.h), [bond] (@ref rte_eth_bond.h), diff --git a/lib/librte_ether/Makefile b/lib/librte_ether/Makefile index efe1e5fea6..9335361706 100644 --- a/lib/librte_ether/Makefile +++ b/lib/librte_ether/Makefile @@ -44,6 +44,7 @@ EXPORT_MAP := rte_ether_version.map LIBABIVER := 5 SRCS-y += rte_ethdev.c +SRCS-y += rte_flow.c # # Export include files @@ -51,6 +52,8 @@ SRCS-y += rte_ethdev.c SYMLINK-y-include += rte_ethdev.h SYMLINK-y-include += rte_eth_ctrl.h SYMLINK-y-include += rte_dev_info.h +SYMLINK-y-include += rte_flow.h +SYMLINK-y-include += rte_flow_driver.h # this lib depends upon: DEPDIRS-y += lib/librte_net lib/librte_eal lib/librte_mempool lib/librte_ring lib/librte_mbuf diff --git a/lib/librte_ether/rte_eth_ctrl.h b/lib/librte_ether/rte_eth_ctrl.h index fe80eb0137..8386904243 100644 --- a/lib/librte_ether/rte_eth_ctrl.h +++ b/lib/librte_ether/rte_eth_ctrl.h @@ -99,6 +99,7 @@ enum rte_filter_type { RTE_ETH_FILTER_FDIR, RTE_ETH_FILTER_HASH, RTE_ETH_FILTER_L2_TUNNEL, + RTE_ETH_FILTER_GENERIC, RTE_ETH_FILTER_MAX }; diff --git a/lib/librte_ether/rte_ether_version.map b/lib/librte_ether/rte_ether_version.map index b7ee80c87d..a0217814bd 100644 --- a/lib/librte_ether/rte_ether_version.map +++ b/lib/librte_ether/rte_ether_version.map @@ -151,5 +151,10 @@ DPDK_17.02 { global: _rte_eth_dev_reset; + rte_flow_create; + rte_flow_destroy; + rte_flow_flush; + rte_flow_query; + rte_flow_validate; } DPDK_16.11; diff --git a/lib/librte_ether/rte_flow.c b/lib/librte_ether/rte_flow.c new file mode 100644 index 0000000000..d98fb1b333 --- /dev/null +++ b/lib/librte_ether/rte_flow.c @@ -0,0 +1,159 @@ +/*- + * 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. + */ + +#include + +#include +#include +#include "rte_ethdev.h" +#include "rte_flow_driver.h" +#include "rte_flow.h" + +/* Get generic flow operations structure from a port. */ +const struct rte_flow_ops * +rte_flow_ops_get(uint8_t port_id, struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops; + int code; + + if (unlikely(!rte_eth_dev_is_valid_port(port_id))) + code = ENODEV; + else if (unlikely(!dev->dev_ops->filter_ctrl || + dev->dev_ops->filter_ctrl(dev, + RTE_ETH_FILTER_GENERIC, + RTE_ETH_FILTER_GET, + &ops) || + !ops)) + code = ENOSYS; + else + return ops; + rte_flow_error_set(error, code, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(code)); + return NULL; +} + +/* Check whether a flow rule can be created on a given port. */ +int +rte_flow_validate(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error) +{ + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + + if (unlikely(!ops)) + return -rte_errno; + if (likely(!!ops->validate)) + return ops->validate(dev, attr, pattern, actions, error); + rte_flow_error_set(error, ENOSYS, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); + return -rte_errno; +} + +/* Create a flow rule on a given port. */ +struct rte_flow * +rte_flow_create(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (unlikely(!ops)) + return NULL; + if (likely(!!ops->create)) + return ops->create(dev, attr, pattern, actions, error); + rte_flow_error_set(error, ENOSYS, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); + return NULL; +} + +/* Destroy a flow rule on a given port. */ +int +rte_flow_destroy(uint8_t port_id, + struct rte_flow *flow, + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (unlikely(!ops)) + return -rte_errno; + if (likely(!!ops->destroy)) + return ops->destroy(dev, flow, error); + rte_flow_error_set(error, ENOSYS, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); + return -rte_errno; +} + +/* Destroy all flow rules associated with a port. */ +int +rte_flow_flush(uint8_t port_id, + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (unlikely(!ops)) + return -rte_errno; + if (likely(!!ops->flush)) + return ops->flush(dev, error); + rte_flow_error_set(error, ENOSYS, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); + return -rte_errno; +} + +/* Query an existing flow rule. */ +int +rte_flow_query(uint8_t port_id, + struct rte_flow *flow, + enum rte_flow_action_type action, + void *data, + struct rte_flow_error *error) +{ + struct rte_eth_dev *dev = &rte_eth_devices[port_id]; + const struct rte_flow_ops *ops = rte_flow_ops_get(port_id, error); + + if (!ops) + return -rte_errno; + if (likely(!!ops->query)) + return ops->query(dev, flow, action, data, error); + rte_flow_error_set(error, ENOSYS, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, rte_strerror(ENOSYS)); + return -rte_errno; +} diff --git a/lib/librte_ether/rte_flow.h b/lib/librte_ether/rte_flow.h new file mode 100644 index 0000000000..98084ac72d --- /dev/null +++ b/lib/librte_ether/rte_flow.h @@ -0,0 +1,947 @@ +/*- + * 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. + */ + +#ifndef RTE_FLOW_H_ +#define RTE_FLOW_H_ + +/** + * @file + * RTE generic flow API + * + * This interface provides the ability to program packet matching and + * associated actions in hardware through flow rules. + */ + +#include +#include +#include +#include +#include +#include +#include + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * Flow rule attributes. + * + * Priorities are set on two levels: per group and per rule within groups. + * + * Lower values denote higher priority, the highest priority for both levels + * is 0, so that a rule with priority 0 in group 8 is always matched after a + * rule with priority 8 in group 0. + * + * Although optional, applications are encouraged to group similar rules as + * much as possible to fully take advantage of hardware capabilities + * (e.g. optimized matching) and work around limitations (e.g. a single + * pattern type possibly allowed in a given group). + * + * Group and priority levels are arbitrary and up to the application, they + * do not need to be contiguous nor start from 0, however the maximum number + * varies between devices and may be affected by existing flow rules. + * + * If a packet is matched by several rules of a given group for a given + * priority level, the outcome is undefined. It can take any path, may be + * duplicated or even cause unrecoverable errors. + * + * Note that support for more than a single group and priority level is not + * guaranteed. + * + * Flow rules can apply to inbound and/or outbound traffic (ingress/egress). + * + * Several pattern items and actions are valid and can be used in both + * directions. Those valid for only one direction are described as such. + * + * At least one direction must be specified. + * + * Specifying both directions at once for a given rule is not recommended + * but may be valid in a few cases (e.g. shared counter). + */ +struct rte_flow_attr { + uint32_t group; /**< Priority group. */ + 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. */ +}; + +/** + * Matching pattern item types. + * + * 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 + * specification structure. These must be stacked in the same order as the + * protocol layers to match, 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. + * + * See the description of individual types for more information. Those + * marked with [META] fall into the second category. + */ +enum rte_flow_item_type { + /** + * [META] + * + * End marker for item lists. Prevents further processing of items, + * thereby ending the pattern. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_END, + + /** + * [META] + * + * Used as a placeholder for convenience. It is ignored and simply + * discarded by PMDs. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_VOID, + + /** + * [META] + * + * Inverted matching, i.e. process packets that do not match the + * pattern. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_INVERT, + + /** + * Matches any protocol in place of the current layer, a single ANY + * may also stand for several protocol layers. + * + * See struct rte_flow_item_any. + */ + RTE_FLOW_ITEM_TYPE_ANY, + + /** + * [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. + * + * No associated specification structure. + */ + RTE_FLOW_ITEM_TYPE_PF, + + /** + * [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. + * + * See struct rte_flow_item_vf. + */ + RTE_FLOW_ITEM_TYPE_VF, + + /** + * [META] + * + * Matches packets coming from the specified 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_port. + */ + RTE_FLOW_ITEM_TYPE_PORT, + + /** + * Matches a byte string of a given length at a given offset. + * + * See struct rte_flow_item_raw. + */ + RTE_FLOW_ITEM_TYPE_RAW, + + /** + * Matches an Ethernet header. + * + * See struct rte_flow_item_eth. + */ + RTE_FLOW_ITEM_TYPE_ETH, + + /** + * Matches an 802.1Q/ad VLAN tag. + * + * See struct rte_flow_item_vlan. + */ + RTE_FLOW_ITEM_TYPE_VLAN, + + /** + * Matches an IPv4 header. + * + * See struct rte_flow_item_ipv4. + */ + RTE_FLOW_ITEM_TYPE_IPV4, + + /** + * Matches an IPv6 header. + * + * See struct rte_flow_item_ipv6. + */ + RTE_FLOW_ITEM_TYPE_IPV6, + + /** + * Matches an ICMP header. + * + * See struct rte_flow_item_icmp. + */ + RTE_FLOW_ITEM_TYPE_ICMP, + + /** + * Matches a UDP header. + * + * See struct rte_flow_item_udp. + */ + RTE_FLOW_ITEM_TYPE_UDP, + + /** + * Matches a TCP header. + * + * See struct rte_flow_item_tcp. + */ + RTE_FLOW_ITEM_TYPE_TCP, + + /** + * Matches a SCTP header. + * + * See struct rte_flow_item_sctp. + */ + RTE_FLOW_ITEM_TYPE_SCTP, + + /** + * Matches a VXLAN header. + * + * See struct rte_flow_item_vxlan. + */ + RTE_FLOW_ITEM_TYPE_VXLAN, +}; + +/** + * RTE_FLOW_ITEM_TYPE_ANY + * + * Matches any protocol in place of the current layer, a single ANY may also + * stand for several protocol layers. + * + * This is usually specified as the first pattern item when looking for a + * protocol anywhere in a packet. + * + * A zeroed mask stands for any number of layers. + */ +struct rte_flow_item_any { + uint32_t num; /* Number of layers covered. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_VF + * + * 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. + * + * - 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. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_PORT + * + * Matches packets coming from the specified 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. + * + * Note that physical ports are not necessarily tied to DPDK input ports + * (port_id) when those are not under DPDK control. Possible values are + * specific to each device, they are not necessarily indexed from zero and + * may not be contiguous. + * + * As a device property, the list of allowed values as well as the value + * associated with a port_id should be retrieved by other means. + * + * A zeroed mask can be used to match any port index. + */ +struct rte_flow_item_port { + uint32_t index; /**< Physical port index. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_RAW + * + * Matches a byte string of a given length at a given offset. + * + * Offset is either absolute (using the start of the packet) or relative to + * the end of the previous matched item in the stack, in which case negative + * values are allowed. + * + * If search is enabled, offset is used as the starting point. The search + * area can be delimited by setting limit to a nonzero value, which is the + * maximum number of bytes after offset where the pattern may start. + * + * Matching a zero-length pattern is allowed, doing so resets the relative + * offset for subsequent items. + * + * This type does not support ranges (struct rte_flow_item.last). + */ +struct rte_flow_item_raw { + uint32_t relative:1; /**< Look for pattern after the previous item. */ + uint32_t search:1; /**< Search pattern from offset (see also limit). */ + uint32_t reserved:30; /**< Reserved, must be set to zero. */ + 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. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_ETH + * + * Matches an Ethernet header. + */ +struct rte_flow_item_eth { + struct ether_addr dst; /**< Destination MAC. */ + struct ether_addr src; /**< Source MAC. */ + uint16_t type; /**< EtherType. */ +}; + +/** + * 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. + */ +struct rte_flow_item_vlan { + uint16_t tpid; /**< Tag protocol identifier. */ + uint16_t tci; /**< Tag control information. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_IPV4 + * + * Matches an IPv4 header. + * + * Note: IPv4 options are handled by dedicated pattern items. + */ +struct rte_flow_item_ipv4 { + struct ipv4_hdr hdr; /**< IPv4 header definition. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_IPV6. + * + * Matches an IPv6 header. + * + * Note: IPv6 options are handled by dedicated pattern items. + */ +struct rte_flow_item_ipv6 { + struct ipv6_hdr hdr; /**< IPv6 header definition. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_ICMP. + * + * Matches an ICMP header. + */ +struct rte_flow_item_icmp { + struct icmp_hdr hdr; /**< ICMP header definition. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_UDP. + * + * Matches a UDP header. + */ +struct rte_flow_item_udp { + struct udp_hdr hdr; /**< UDP header definition. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_TCP. + * + * Matches a TCP header. + */ +struct rte_flow_item_tcp { + struct tcp_hdr hdr; /**< TCP header definition. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_SCTP. + * + * Matches a SCTP header. + */ +struct rte_flow_item_sctp { + struct sctp_hdr hdr; /**< SCTP header definition. */ +}; + +/** + * RTE_FLOW_ITEM_TYPE_VXLAN. + * + * Matches a VXLAN header (RFC 7348). + */ +struct rte_flow_item_vxlan { + uint8_t flags; /**< Normally 0x08 (I flag). */ + uint8_t rsvd0[3]; /**< Reserved, normally 0x000000. */ + uint8_t vni[3]; /**< VXLAN identifier. */ + uint8_t rsvd1; /**< Reserved, normally 0x00. */ +}; + +/** + * Matching pattern item definition. + * + * A pattern is formed by stacking items starting from the lowest protocol + * layer to match. This stacking restriction does not apply to meta items + * which can be placed anywhere in the stack without affecting the meaning + * of the resulting pattern. + * + * Patterns are terminated by END items. + * + * The spec field should be a valid pointer to a structure of the related + * item type. It may be set to NULL in many cases to use default values. + * + * Optionally, last can point to a structure of the same type to define an + * inclusive range. This is mostly supported by integer and address fields, + * may cause errors otherwise. Fields that do not support ranges must be set + * to 0 or to the same value as the corresponding fields in spec. + * + * By default all fields present in spec are considered relevant (see note + * below). This behavior can be altered by providing a mask structure of the + * same type with applicable bits set to one. It can also be used to + * partially filter out specific fields (e.g. as an alternate mean to match + * ranges of IP addresses). + * + * Mask is a simple bit-mask applied before interpreting the contents of + * spec and last, which may yield unexpected results if not used + * carefully. For example, if for an IPv4 address field, spec provides + * 10.1.2.3, last provides 10.3.4.5 and mask provides 255.255.0.0, the + * effective range becomes 10.1.0.0 to 10.3.255.255. + * + * Note: the defaults for data-matching items such as IPv4 when mask is not + * specified actually depend on the underlying implementation since only + * recognized fields can be taken into account. + */ +struct rte_flow_item { + enum rte_flow_item_type type; /**< Item type. */ + const void *spec; /**< Pointer to item specification structure. */ + const void *last; /**< Defines an inclusive range (spec to last). */ + const void *mask; /**< Bit-mask applied to spec and last. */ +}; + +/** + * Action types. + * + * 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. + * + * 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. + * + * - Non terminating actions (PASSTHRU, DUP) that leave matched packets up + * for additional processing by subsequent flow rules. + * + * - Other non terminating meta actions that do not affect the fate of + * packets (END, VOID, MARK, FLAG, COUNT). + * + * When several actions are combined in a flow rule, they should all have + * different types (e.g. dropping a packet twice is not possible). + * + * 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. + */ +enum rte_flow_action_type { + /** + * [META] + * + * End marker for action lists. Prevents further processing of + * actions, thereby ending the list. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_END, + + /** + * [META] + * + * Used as a placeholder for convenience. It is ignored and simply + * discarded by PMDs. + * + * No associated configuration structure. + */ + 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. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_PASSTHRU, + + /** + * [META] + * + * Attaches a 32 bit value to packets. + * + * See struct rte_flow_action_mark. + */ + RTE_FLOW_ACTION_TYPE_MARK, + + /** + * [META] + * + * Flag packets. Similar to MARK but only affects ol_flags. + * + * Note: a distinctive flag must be defined for it. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_FLAG, + + /** + * Assigns packets to a given queue index. + * + * See struct rte_flow_action_queue. + */ + RTE_FLOW_ACTION_TYPE_QUEUE, + + /** + * Drops packets. + * + * PASSTHRU overrides this action if both are specified. + * + * No associated configuration structure. + */ + RTE_FLOW_ACTION_TYPE_DROP, + + /** + * [META] + * + * Enables counters for this rule. + * + * These counters can be retrieved and reset through rte_flow_query(), + * see struct rte_flow_query_count. + * + * No associated configuration structure. + */ + 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 + * parameters. + * + * See struct rte_flow_action_rss. + */ + RTE_FLOW_ACTION_TYPE_RSS, + + /** + * Redirects packets 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. + * + * See struct rte_flow_action_vf. + */ + RTE_FLOW_ACTION_TYPE_VF, +}; + +/** + * RTE_FLOW_ACTION_TYPE_MARK + * + * Attaches a 32 bit value to packets. + * + * This value is arbitrary and application-defined. For compatibility with + * FDIR it is returned in the hash.fdir.hi mbuf field. PKT_RX_FDIR_ID is + * also set in ol_flags. + */ +struct rte_flow_action_mark { + uint32_t id; /**< 32 bit value to return with packets. */ +}; + +/** + * 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. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_COUNT (query) + * + * Query structure to retrieve and reset flow rule counters. + */ +struct rte_flow_query_count { + uint32_t reset:1; /**< Reset counters after query [in]. */ + uint32_t hits_set:1; /**< hits field is set [out]. */ + uint32_t bytes_set:1; /**< bytes field is set [out]. */ + uint32_t reserved:29; /**< Reserved, must be zero [in, out]. */ + uint64_t hits; /**< Number of hits for this rule [out]. */ + 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. + * + * Note: RSS hash result is normally stored in the hash.rss mbuf field, + * however it conflicts with the MARK action as they share the same + * space. When both actions are specified, the RSS hash is discarded and + * PKT_RX_RSS_HASH is not set in ol_flags. MARK has priority. The mbuf + * structure should eventually evolve to store both. + * + * 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. */ +}; + +/** + * RTE_FLOW_ACTION_TYPE_VF + * + * Redirects packets to a virtual function (VF) 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. */ +}; + +/** + * Definition of a single action. + * + * A list of actions is terminated by a END action. + * + * For simple actions without a configuration structure, conf remains NULL. + */ +struct rte_flow_action { + enum rte_flow_action_type type; /**< Action type. */ + const void *conf; /**< Pointer to action configuration structure. */ +}; + +/** + * Opaque type returned after successfully creating a flow. + * + * This handle can be used to manage and query the related flow (e.g. to + * destroy it or retrieve counters). + */ +struct rte_flow; + +/** + * Verbose error types. + * + * Most of them provide the type of the object referenced by struct + * rte_flow_error.cause. + */ +enum rte_flow_error_type { + RTE_FLOW_ERROR_TYPE_NONE, /**< No error. */ + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */ + RTE_FLOW_ERROR_TYPE_HANDLE, /**< Flow rule (handle). */ + RTE_FLOW_ERROR_TYPE_ATTR_GROUP, /**< Group field. */ + 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, /**< Attributes structure. */ + RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */ + RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */ + RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */ + RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */ +}; + +/** + * Verbose error structure definition. + * + * This object is normally allocated by applications and set by PMDs, the + * message points to a constant string which does not need to be freed by + * the application, however its pointer can be considered valid only as long + * as its associated DPDK port remains configured. Closing the underlying + * device or unloading the PMD invalidates it. + * + * Both cause and message may be NULL regardless of the error type. + */ +struct rte_flow_error { + enum rte_flow_error_type type; /**< Cause field and error types. */ + const void *cause; /**< Object responsible for the error. */ + const char *message; /**< Human-readable error message. */ +}; + +/** + * 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 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 + * the meantime and no device parameter affecting flow rules in any way are + * modified, due to possible collisions or resource limitations (although in + * such cases EINVAL should not be returned). + * + * @param port_id + * Port identifier of Ethernet device. + * @param[in] attr + * Flow rule attributes. + * @param[in] pattern + * Pattern specification (list terminated by the END pattern item). + * @param[in] actions + * Associated actions (list terminated by the END action). + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * 0 if flow rule is valid and can be created. A negative errno value + * otherwise (rte_errno is also set), the following errors are defined: + * + * -ENOSYS: underlying device does not support this functionality. + * + * -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. + * + * -ENOMEM: not enough resources. + * + * -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, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error); + +/** + * Create a flow rule on a given port. + * + * @param port_id + * Port identifier of Ethernet device. + * @param[in] attr + * Flow rule attributes. + * @param[in] pattern + * Pattern specification (list terminated by the END pattern item). + * @param[in] actions + * Associated actions (list terminated by the END action). + * @param[out] error + * Perform verbose error reporting if not NULL. PMDs initialize this + * structure in case of error only. + * + * @return + * A valid handle in case of success, NULL otherwise and rte_errno is set + * to the positive version of one of the error codes defined for + * rte_flow_validate(). + */ +struct rte_flow * +rte_flow_create(uint8_t port_id, + const struct rte_flow_attr *attr, + const struct rte_flow_item pattern[], + const struct rte_flow_action actions[], + struct rte_flow_error *error); + +/** + * Destroy a flow rule on a given port. + * + * Failure to destroy a flow rule handle may occur when other flow rules + * depend on it, and destroying it would result in an inconsistent state. + * + * This function is only guaranteed to succeed if handles are destroyed in + * reverse order of their creation. + * + * @param port_id + * Port identifier of Ethernet device. + * @param flow + * Flow rule handle to destroy. + * @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_destroy(uint8_t port_id, + struct rte_flow *flow, + struct rte_flow_error *error); + +/** + * Destroy all flow rules associated with a port. + * + * In the unlikely event of failure, handles are still considered destroyed + * and no longer valid but the port must be assumed to be in an inconsistent + * state. + * + * @param port_id + * Port identifier of Ethernet device. + * @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_flush(uint8_t port_id, + struct rte_flow_error *error); + +/** + * Query an existing flow rule. + * + * This function allows retrieving flow-specific data such as counters. + * Data is gathered by special actions which must be present in the flow + * rule definition. + * + * \see RTE_FLOW_ACTION_TYPE_COUNT + * + * @param port_id + * Port identifier of Ethernet device. + * @param flow + * Flow rule handle to query. + * @param action + * Action type to query. + * @param[in, out] data + * Pointer to storage for the associated query data type. + * @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_query(uint8_t port_id, + struct rte_flow *flow, + enum rte_flow_action_type action, + void *data, + struct rte_flow_error *error); + +#ifdef __cplusplus +} +#endif + +#endif /* RTE_FLOW_H_ */ diff --git a/lib/librte_ether/rte_flow_driver.h b/lib/librte_ether/rte_flow_driver.h new file mode 100644 index 0000000000..cc97785b50 --- /dev/null +++ b/lib/librte_ether/rte_flow_driver.h @@ -0,0 +1,182 @@ +/*- + * 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. + */ + +#ifndef RTE_FLOW_DRIVER_H_ +#define RTE_FLOW_DRIVER_H_ + +/** + * @file + * RTE generic flow API (driver side) + * + * This file provides implementation helpers for internal use by PMDs, they + * are not intended to be exposed to applications and are not subject to ABI + * versioning. + */ + +#include + +#include +#include "rte_ethdev.h" +#include "rte_flow.h" + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * Generic flow operations structure implemented and returned by PMDs. + * + * To implement this API, PMDs must handle the RTE_ETH_FILTER_GENERIC filter + * type in their .filter_ctrl callback function (struct eth_dev_ops) as well + * as the RTE_ETH_FILTER_GET filter operation. + * + * If successful, this operation must result in a pointer to a PMD-specific + * struct rte_flow_ops written to the argument address as described below: + * + * \code + * + * // PMD filter_ctrl callback + * + * static const struct rte_flow_ops pmd_flow_ops = { ... }; + * + * switch (filter_type) { + * case RTE_ETH_FILTER_GENERIC: + * if (filter_op != RTE_ETH_FILTER_GET) + * return -EINVAL; + * *(const void **)arg = &pmd_flow_ops; + * return 0; + * } + * + * \endcode + * + * See also rte_flow_ops_get(). + * + * These callback functions are not supposed to be used by applications + * directly, which must rely on the API defined in rte_flow.h. + * + * Public-facing wrapper functions perform a few consistency checks so that + * unimplemented (i.e. NULL) callbacks simply return -ENOTSUP. These + * callbacks otherwise only differ by their first argument (with port ID + * already resolved to a pointer to struct rte_eth_dev). + */ +struct rte_flow_ops { + /** See rte_flow_validate(). */ + int (*validate) + (struct rte_eth_dev *, + const struct rte_flow_attr *, + const struct rte_flow_item [], + const struct rte_flow_action [], + struct rte_flow_error *); + /** See rte_flow_create(). */ + struct rte_flow *(*create) + (struct rte_eth_dev *, + const struct rte_flow_attr *, + const struct rte_flow_item [], + const struct rte_flow_action [], + struct rte_flow_error *); + /** See rte_flow_destroy(). */ + int (*destroy) + (struct rte_eth_dev *, + struct rte_flow *, + struct rte_flow_error *); + /** See rte_flow_flush(). */ + int (*flush) + (struct rte_eth_dev *, + struct rte_flow_error *); + /** See rte_flow_query(). */ + int (*query) + (struct rte_eth_dev *, + struct rte_flow *, + enum rte_flow_action_type, + void *, + struct rte_flow_error *); +}; + +/** + * Initialize generic flow error structure. + * + * This function also sets rte_errno to a given value. + * + * @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 + * Pointer to flow error structure. + */ +static inline struct rte_flow_error * +rte_flow_error_set(struct rte_flow_error *error, + int code, + enum rte_flow_error_type type, + const void *cause, + const char *message) +{ + if (error) { + *error = (struct rte_flow_error){ + .type = type, + .cause = cause, + .message = message, + }; + } + rte_errno = code; + return error; +} + +/** + * Get generic flow operations structure from a port. + * + * @param port_id + * Port identifier to query. + * @param[out] error + * Pointer to flow error structure. + * + * @return + * The flow operations structure associated with port_id, NULL in case of + * error, in which case rte_errno is set and the error structure contains + * additional details. + */ +const struct rte_flow_ops * +rte_flow_ops_get(uint8_t port_id, struct rte_flow_error *error); + +#ifdef __cplusplus +} +#endif + +#endif /* RTE_FLOW_DRIVER_H_ */