Offloading tunnel ports
-----------------------
Tunnel ports introduce a new stateless field that can be matched on.
Currently the rte_flow library provides an API to encap, decap and match
on tunnel headers. However, there is no rte_flow primitive to set and
match tunnel virtual ports.
There are several possible hardware models for offloading virtual tunnel port
flows including, but not limited to, the following:
1. Setting the virtual port on a hw register using the rte_flow_action_mark/
rte_flow_action_tag/rte_flow_set_meta objects.
2. Mapping a virtual port to an rte_flow group
3. Avoiding the need to match on transient objects by merging multi-table
flows to a single rte_flow rule.
Every approach has its pros and cons.
The preferred approach should take into account the entire system architecture
and is very often vendor specific.
The proposed rte_flow_tunnel_port_set helper function (drafted below) is
designed
to provide a common, vendor agnostic, API for setting the virtual port value.
The helper API enables PMD implementations to return vendor specific
combination of
rte_flow actions realizing the vendor's hardware model for setting a tunnel
port.
Applications may append the list of actions returned from the helper function
when
creating an rte_flow rule in hardware.
Similarly, the rte_flow_tunnel_port_match helper (drafted below) allows for
multiple hardware implementations to return a list of fte_flow items.
Miss handling
-------------
Packets going through multiple rte_flow groups are exposed to hw misses due to
partial packet processing. In such cases, the software should continue the
packet's processing from the point where the hardware missed.
We propose a generic rte_flow_restore structure providing the state that was
stored in hardware when the packet missed.
Currently, the structure will provide the tunnel state of the packet that
missed, namely:
1. The group id that missed
2. The tunnel port that missed
3. Tunnel information that was stored in memory (due to decap action).
In the future, we may add additional fields as more state may be stored in
the device memory (e.g. ct_state).
Applications may query the state via a new rte_flow_get_restore_info(mbuf) API,
thus allowing a vendor specific implementation.
API draft is provided below
---
diff --git a/lib/librte_ethdev/rte_flow.h b/lib/librte_ethdev/rte_flow.h
index b0e4199192..49c871fc46 100644
--- a/lib/librte_ethdev/rte_flow.h
+++ b/lib/librte_ethdev/rte_flow.h
@@ -3324,6 +3324,193 @@ int
rte_flow_get_aged_flows(uint16_t port_id, void **contexts,
uint32_t nb_contexts, struct rte_flow_error *error);
+/* Tunnel information. */
+__rte_experimental
+struct rte_flow_ip_tunnel_key {
+ rte_be64_t tun_id; /**< Tunnel identification. */
+ union {
+ struct {
+ rte_be32_t src; /**< IPv4 source address. */
+ rte_be32_t dst; /**< IPv4 destination address. */
+ } ipv4;
+ struct {
+ uint8_t src[16]; /**< IPv6 source address. */
+ uint8_t dst[16]; /**< IPv6 destination address. */
+ } ipv6;
+ } u;
+ bool is_ipv6; /**< True for valid IPv6 fields. Otherwise IPv4. */
+ rte_be16_t tun_flags; /**< Tunnel flags. */
+ uint8_t tos; /**< TOS for IPv4, TC for IPv6. */
+ uint8_t ttl; /**< TTL for IPv4, HL for IPv6. */
+ rte_be32_t label; /**< Flow Label for IPv6. */
+ rte_be16_t tp_src; /**< Tunnel port source. */
+ rte_be16_t tp_dst; /**< Tunnel port destination. */
+};
+
+
+/* Tunnel has a type and the key information. */
+__rte_experimental
+struct rte_flow_tunnel {
+ /** Tunnel type, for example RTE_FLOW_ITEM_TYPE_VXLAN,
+ * RTE_FLOW_ITEM_TYPE_NVGRE etc. */
+ enum rte_flow_item_type type;
+ struct rte_flow_ip_tunnel_key tun_info; /**< Tunnel key info. */
+};
+
+/**
+ * Indicate that the packet has a tunnel.
+ */
+#define RTE_FLOW_RESTORE_INFO_TUNNEL (1ULL << 0)
+
+/**
+ * Indicate that the packet has a non decapsulated tunnel header.
+ */
+#define RTE_FLOW_RESTORE_INFO_ENCAPSULATED (1ULL << 1)
+
+/**
+ * Indicate that the packet has a group_id.
+ */
+#define RTE_FLOW_RESTORE_INFO_GROUP_ID (1ULL << 2)
+
+/**
+ * Restore information structure to communicate the current packet processing
+ * state when some of the processing pipeline is done in hardware and should
+ * continue in software.
+ */
+__rte_experimental
+struct rte_flow_restore_info {
+ /** Bitwise flags (RTE_FLOW_RESTORE_INFO_*) to indicate validation of
+ * other fields in struct rte_flow_restore_info.
+ */
+ uint64_t flags;
+ uint32_t group_id; /**< Group ID. */
+ struct rte_flow_tunnel tunnel; /**< Tunnel information. */
+};
+
+/**
+ * Allocate an array of actions to be used in rte_flow_create, to implement
+ * tunnel-set for the given tunnel.
+ * Sample usage:
+ * actions vxlan_decap / tunnel_set(tunnel properties) / jump group 0 / end
+ *
+ * @param port_id
+ * Port identifier of Ethernet device.
+ * @param[in] tunnel
+ * Tunnel properties.
+ * @param[out] actions
+ * Array of actions to be allocated by the PMD. This array should be
+ * concatenated with the actions array provided to rte_flow_create.
+ * @param[out] num_of_actions
+ * Number of actions allocated.
+ * @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.
+ */
+__rte_experimental
+int
+rte_flow_tunnel_set(uint16_t port_id,
+ struct rte_flow_tunnel *tunnel,
+ struct rte_flow_action **actions,
+ uint32_t *num_of_actions,
+ struct rte_flow_error *error);
+
+/**
+ * Allocate an array of items to be used in rte_flow_create, to implement
+ * tunnel-match for the given tunnel.
+ * Sample usage:
+ * pattern tunnel-match(tunnel properties) / outer-header-matches /
+ * inner-header-matches / end
+ *
+ * @param port_id
+ * Port identifier of Ethernet device.
+ * @param[in] tunnel
+ * Tunnel properties.
+ * @param[out] items
+ * Array of items to be allocated by the PMD. This array should be
+ * concatenated with the items array provided to rte_flow_create.
+ * @param[out] num_of_items
+ * Number of items allocated.
+ * @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.
+ */
+__rte_experimental
+int
+rte_flow_tunnel_match(uint16_t port_id,
+ struct rte_flow_tunnel *tunnel,
+ struct rte_flow_item **items,
+ uint32_t *num_of_items,
+ struct rte_flow_error *error);
+
+/**
+ * Populate the current packet processing state, if exists, for the given mbuf.
+ *
+ * @param port_id
+ * Port identifier of Ethernet device.
+ * @param[in] m
+ * Mbuf struct.
+ * @param[out] info
+ * Restore information. Upon success contains the HW state.
+ * @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.
+ */
+__rte_experimental
+int
+rte_flow_get_restore_info(uint16_t port_id,
+ struct rte_mbuf *m,
+ struct rte_flow_restore_info *info,
+ struct rte_flow_error *error);
+
+/**
+ * Release the action array as allocated by rte_flow_tunnel_set.
+ *
+ * @param port_id
+ * Port identifier of Ethernet device.
+ * @param[in] actions
+ * Array of actions to be released.
+ * @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.
+ */
+__rte_experimental
+int
+rte_flow_action_release(uint16_t port_id,
+ struct rte_flow_action *actions,
+ struct rte_flow_error *error);
+
+/**
+ * Release the item array as allocated by rte_flow_tunnel_match.
+ *
+ * @param port_id
+ * Port identifier of Ethernet device.
+ * @param[in] items
+ * Array of items to be released.
+ * @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.
+ */
+__rte_experimental
+int
+rte_flow_item_release(uint16_t port_id,
+ struct rte_flow_item *items,
+ struct rte_flow_error *error);
+
#ifdef __cplusplus
}
#endif
