diff options
Diffstat (limited to 'lib/librte_net')
| -rw-r--r-- | lib/librte_net/Makefile | 14 | ||||
| -rw-r--r-- | lib/librte_net/rte_ether.h | 417 | ||||
| -rw-r--r-- | lib/librte_net/rte_gre.h | 71 | ||||
| -rw-r--r-- | lib/librte_net/rte_ip.h | 71 | ||||
| -rw-r--r-- | lib/librte_net/rte_net.c | 517 | ||||
| -rw-r--r-- | lib/librte_net/rte_net.h | 94 | ||||
| -rw-r--r-- | lib/librte_net/rte_net_version.map | 6 |
7 files changed, 1188 insertions, 2 deletions
diff --git a/lib/librte_net/Makefile b/lib/librte_net/Makefile index ad2e482d..20cf6644 100644 --- a/lib/librte_net/Makefile +++ b/lib/librte_net/Makefile @@ -31,10 +31,20 @@ include $(RTE_SDK)/mk/rte.vars.mk +LIB = librte_net.a + CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -O3 +EXPORT_MAP := rte_net_version.map +LIBABIVER := 1 + +SRCS-$(CONFIG_RTE_LIBRTE_NET) := rte_net.c + # install includes -SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include := rte_ip.h rte_tcp.h rte_udp.h rte_sctp.h rte_icmp.h rte_arp.h +SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include := rte_ip.h rte_tcp.h rte_udp.h +SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_sctp.h rte_icmp.h rte_arp.h +SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_ether.h rte_gre.h rte_net.h +DEPDIRS-$(CONFIG_RTE_LIBRTE_NET) += lib/librte_eal lib/librte_mbuf -include $(RTE_SDK)/mk/rte.install.mk +include $(RTE_SDK)/mk/rte.lib.mk diff --git a/lib/librte_net/rte_ether.h b/lib/librte_net/rte_ether.h new file mode 100644 index 00000000..ff3d0654 --- /dev/null +++ b/lib/librte_net/rte_ether.h @@ -0,0 +1,417 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. + * All rights reserved. + * + * 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 Intel Corporation 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_ETHER_H_ +#define _RTE_ETHER_H_ + +/** + * @file + * + * Ethernet Helpers in RTE + */ + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stdint.h> +#include <stdio.h> + +#include <rte_memcpy.h> +#include <rte_random.h> +#include <rte_mbuf.h> +#include <rte_byteorder.h> + +#define ETHER_ADDR_LEN 6 /**< Length of Ethernet address. */ +#define ETHER_TYPE_LEN 2 /**< Length of Ethernet type field. */ +#define ETHER_CRC_LEN 4 /**< Length of Ethernet CRC. */ +#define ETHER_HDR_LEN \ + (ETHER_ADDR_LEN * 2 + ETHER_TYPE_LEN) /**< Length of Ethernet header. */ +#define ETHER_MIN_LEN 64 /**< Minimum frame len, including CRC. */ +#define ETHER_MAX_LEN 1518 /**< Maximum frame len, including CRC. */ +#define ETHER_MTU \ + (ETHER_MAX_LEN - ETHER_HDR_LEN - ETHER_CRC_LEN) /**< Ethernet MTU. */ + +#define ETHER_MAX_VLAN_FRAME_LEN \ + (ETHER_MAX_LEN + 4) /**< Maximum VLAN frame length, including CRC. */ + +#define ETHER_MAX_JUMBO_FRAME_LEN \ + 0x3F00 /**< Maximum Jumbo frame length, including CRC. */ + +#define ETHER_MAX_VLAN_ID 4095 /**< Maximum VLAN ID. */ + +#define ETHER_MIN_MTU 68 /**< Minimum MTU for IPv4 packets, see RFC 791. */ + +/** + * Ethernet address: + * A universally administered address is uniquely assigned to a device by its + * manufacturer. The first three octets (in transmission order) contain the + * Organizationally Unique Identifier (OUI). The following three (MAC-48 and + * EUI-48) octets are assigned by that organization with the only constraint + * of uniqueness. + * A locally administered address is assigned to a device by a network + * administrator and does not contain OUIs. + * See http://standards.ieee.org/regauth/groupmac/tutorial.html + */ +struct ether_addr { + uint8_t addr_bytes[ETHER_ADDR_LEN]; /**< Addr bytes in tx order */ +} __attribute__((__packed__)); + +#define ETHER_LOCAL_ADMIN_ADDR 0x02 /**< Locally assigned Eth. address. */ +#define ETHER_GROUP_ADDR 0x01 /**< Multicast or broadcast Eth. address. */ + +/** + * Check if two Ethernet addresses are the same. + * + * @param ea1 + * A pointer to the first ether_addr structure containing + * the ethernet address. + * @param ea2 + * A pointer to the second ether_addr structure containing + * the ethernet address. + * + * @return + * True (1) if the given two ethernet address are the same; + * False (0) otherwise. + */ +static inline int is_same_ether_addr(const struct ether_addr *ea1, + const struct ether_addr *ea2) +{ + int i; + for (i = 0; i < ETHER_ADDR_LEN; i++) + if (ea1->addr_bytes[i] != ea2->addr_bytes[i]) + return 0; + return 1; +} + +/** + * Check if an Ethernet address is filled with zeros. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is filled with zeros; + * false (0) otherwise. + */ +static inline int is_zero_ether_addr(const struct ether_addr *ea) +{ + int i; + for (i = 0; i < ETHER_ADDR_LEN; i++) + if (ea->addr_bytes[i] != 0x00) + return 0; + return 1; +} + +/** + * Check if an Ethernet address is a unicast address. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is a unicast address; + * false (0) otherwise. + */ +static inline int is_unicast_ether_addr(const struct ether_addr *ea) +{ + return (ea->addr_bytes[0] & ETHER_GROUP_ADDR) == 0; +} + +/** + * Check if an Ethernet address is a multicast address. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is a multicast address; + * false (0) otherwise. + */ +static inline int is_multicast_ether_addr(const struct ether_addr *ea) +{ + return ea->addr_bytes[0] & ETHER_GROUP_ADDR; +} + +/** + * Check if an Ethernet address is a broadcast address. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is a broadcast address; + * false (0) otherwise. + */ +static inline int is_broadcast_ether_addr(const struct ether_addr *ea) +{ + const unaligned_uint16_t *ea_words = (const unaligned_uint16_t *)ea; + + return (ea_words[0] == 0xFFFF && ea_words[1] == 0xFFFF && + ea_words[2] == 0xFFFF); +} + +/** + * Check if an Ethernet address is a universally assigned address. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is a universally assigned address; + * false (0) otherwise. + */ +static inline int is_universal_ether_addr(const struct ether_addr *ea) +{ + return (ea->addr_bytes[0] & ETHER_LOCAL_ADMIN_ADDR) == 0; +} + +/** + * Check if an Ethernet address is a locally assigned address. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is a locally assigned address; + * false (0) otherwise. + */ +static inline int is_local_admin_ether_addr(const struct ether_addr *ea) +{ + return (ea->addr_bytes[0] & ETHER_LOCAL_ADMIN_ADDR) != 0; +} + +/** + * Check if an Ethernet address is a valid address. Checks that the address is a + * unicast address and is not filled with zeros. + * + * @param ea + * A pointer to a ether_addr structure containing the ethernet address + * to check. + * @return + * True (1) if the given ethernet address is valid; + * false (0) otherwise. + */ +static inline int is_valid_assigned_ether_addr(const struct ether_addr *ea) +{ + return is_unicast_ether_addr(ea) && (!is_zero_ether_addr(ea)); +} + +/** + * Generate a random Ethernet address that is locally administered + * and not multicast. + * @param addr + * A pointer to Ethernet address. + */ +static inline void eth_random_addr(uint8_t *addr) +{ + uint64_t rand = rte_rand(); + uint8_t *p = (uint8_t *)&rand; + + rte_memcpy(addr, p, ETHER_ADDR_LEN); + addr[0] &= ~ETHER_GROUP_ADDR; /* clear multicast bit */ + addr[0] |= ETHER_LOCAL_ADMIN_ADDR; /* set local assignment bit */ +} + +/** + * Fast copy an Ethernet address. + * + * @param ea_from + * A pointer to a ether_addr structure holding the Ethernet address to copy. + * @param ea_to + * A pointer to a ether_addr structure where to copy the Ethernet address. + */ +static inline void ether_addr_copy(const struct ether_addr *ea_from, + struct ether_addr *ea_to) +{ +#ifdef __INTEL_COMPILER + uint16_t *from_words = (uint16_t *)(ea_from->addr_bytes); + uint16_t *to_words = (uint16_t *)(ea_to->addr_bytes); + + to_words[0] = from_words[0]; + to_words[1] = from_words[1]; + to_words[2] = from_words[2]; +#else + /* + * Use the common way, because of a strange gcc warning. + */ + *ea_to = *ea_from; +#endif +} + +#define ETHER_ADDR_FMT_SIZE 18 +/** + * Format 48bits Ethernet address in pattern xx:xx:xx:xx:xx:xx. + * + * @param buf + * A pointer to buffer contains the formatted MAC address. + * @param size + * The format buffer size. + * @param eth_addr + * A pointer to a ether_addr structure. + */ +static inline void +ether_format_addr(char *buf, uint16_t size, + const struct ether_addr *eth_addr) +{ + snprintf(buf, size, "%02X:%02X:%02X:%02X:%02X:%02X", + eth_addr->addr_bytes[0], + eth_addr->addr_bytes[1], + eth_addr->addr_bytes[2], + eth_addr->addr_bytes[3], + eth_addr->addr_bytes[4], + eth_addr->addr_bytes[5]); +} + +/** + * Ethernet header: Contains the destination address, source address + * and frame type. + */ +struct ether_hdr { + struct ether_addr d_addr; /**< Destination address. */ + struct ether_addr s_addr; /**< Source address. */ + uint16_t ether_type; /**< Frame type. */ +} __attribute__((__packed__)); + +/** + * Ethernet VLAN Header. + * Contains the 16-bit VLAN Tag Control Identifier and the Ethernet type + * of the encapsulated frame. + */ +struct vlan_hdr { + uint16_t vlan_tci; /**< Priority (3) + CFI (1) + Identifier Code (12) */ + uint16_t eth_proto;/**< Ethernet type of encapsulated frame. */ +} __attribute__((__packed__)); + +/** + * VXLAN protocol header. + * Contains the 8-bit flag, 24-bit VXLAN Network Identifier and + * Reserved fields (24 bits and 8 bits) + */ +struct vxlan_hdr { + uint32_t vx_flags; /**< flag (8) + Reserved (24). */ + uint32_t vx_vni; /**< VNI (24) + Reserved (8). */ +} __attribute__((__packed__)); + +/* Ethernet frame types */ +#define ETHER_TYPE_IPv4 0x0800 /**< IPv4 Protocol. */ +#define ETHER_TYPE_IPv6 0x86DD /**< IPv6 Protocol. */ +#define ETHER_TYPE_ARP 0x0806 /**< Arp Protocol. */ +#define ETHER_TYPE_RARP 0x8035 /**< Reverse Arp Protocol. */ +#define ETHER_TYPE_VLAN 0x8100 /**< IEEE 802.1Q VLAN tagging. */ +#define ETHER_TYPE_QINQ 0x88A8 /**< IEEE 802.1ad QinQ tagging. */ +#define ETHER_TYPE_1588 0x88F7 /**< IEEE 802.1AS 1588 Precise Time Protocol. */ +#define ETHER_TYPE_SLOW 0x8809 /**< Slow protocols (LACP and Marker). */ +#define ETHER_TYPE_TEB 0x6558 /**< Transparent Ethernet Bridging. */ + +#define ETHER_VXLAN_HLEN (sizeof(struct udp_hdr) + sizeof(struct vxlan_hdr)) +/**< VXLAN tunnel header length. */ + +/** + * Extract VLAN tag information into mbuf + * + * Software version of VLAN stripping + * + * @param m + * The packet mbuf. + * @return + * - 0: Success + * - 1: not a vlan packet + */ +static inline int rte_vlan_strip(struct rte_mbuf *m) +{ + struct ether_hdr *eh + = rte_pktmbuf_mtod(m, struct ether_hdr *); + + if (eh->ether_type != rte_cpu_to_be_16(ETHER_TYPE_VLAN)) + return -1; + + struct vlan_hdr *vh = (struct vlan_hdr *)(eh + 1); + m->ol_flags |= PKT_RX_VLAN_PKT; + m->vlan_tci = rte_be_to_cpu_16(vh->vlan_tci); + + /* Copy ether header over rather than moving whole packet */ + memmove(rte_pktmbuf_adj(m, sizeof(struct vlan_hdr)), + eh, 2 * ETHER_ADDR_LEN); + + return 0; +} + +/** + * Insert VLAN tag into mbuf. + * + * Software version of VLAN unstripping + * + * @param m + * The packet mbuf. + * @return + * - 0: On success + * -EPERM: mbuf is is shared overwriting would be unsafe + * -ENOSPC: not enough headroom in mbuf + */ +static inline int rte_vlan_insert(struct rte_mbuf **m) +{ + struct ether_hdr *oh, *nh; + struct vlan_hdr *vh; + + /* Can't insert header if mbuf is shared */ + if (rte_mbuf_refcnt_read(*m) > 1) { + struct rte_mbuf *copy; + + copy = rte_pktmbuf_clone(*m, (*m)->pool); + if (unlikely(copy == NULL)) + return -ENOMEM; + rte_pktmbuf_free(*m); + *m = copy; + } + + oh = rte_pktmbuf_mtod(*m, struct ether_hdr *); + nh = (struct ether_hdr *) + rte_pktmbuf_prepend(*m, sizeof(struct vlan_hdr)); + if (nh == NULL) + return -ENOSPC; + + memmove(nh, oh, 2 * ETHER_ADDR_LEN); + nh->ether_type = rte_cpu_to_be_16(ETHER_TYPE_VLAN); + + vh = (struct vlan_hdr *) (nh + 1); + vh->vlan_tci = rte_cpu_to_be_16((*m)->vlan_tci); + + return 0; +} + +#ifdef __cplusplus +} +#endif + +#endif /* _RTE_ETHER_H_ */ diff --git a/lib/librte_net/rte_gre.h b/lib/librte_net/rte_gre.h new file mode 100644 index 00000000..46568ff5 --- /dev/null +++ b/lib/librte_net/rte_gre.h @@ -0,0 +1,71 @@ +/*- + * BSD LICENSE + * + * Copyright 2016 6WIND S.A. + * + * 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 Intel Corporation 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_GRE_H_ +#define _RTE_GRE_H_ + +#include <stdint.h> +#include <rte_byteorder.h> + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * GRE Header + */ +struct gre_hdr { +#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN + uint16_t res2:4; /**< Reserved */ + uint16_t s:1; /**< Sequence Number Present bit */ + uint16_t k:1; /**< Key Present bit */ + uint16_t res1:1; /**< Reserved */ + uint16_t c:1; /**< Checksum Present bit */ + uint16_t ver:3; /**< Version Number */ + uint16_t res3:5; /**< Reserved */ +#elif RTE_BYTE_ORDER == RTE_BIG_ENDIAN + uint16_t c:1; /**< Checksum Present bit */ + uint16_t res1:1; /**< Reserved */ + uint16_t k:1; /**< Key Present bit */ + uint16_t s:1; /**< Sequence Number Present bit */ + uint16_t res2:4; /**< Reserved */ + uint16_t res3:5; /**< Reserved */ + uint16_t ver:3; /**< Version Number */ +#endif + uint16_t proto; /**< Protocol Type */ +} __attribute__((__packed__)); + +#ifdef __cplusplus +} +#endif + +#endif /* RTE_GRE_H_ */ diff --git a/lib/librte_net/rte_ip.h b/lib/librte_net/rte_ip.h index 5b7554ab..4491b86e 100644 --- a/lib/librte_net/rte_ip.h +++ b/lib/librte_net/rte_ip.h @@ -230,6 +230,77 @@ rte_raw_cksum(const void *buf, size_t len) } /** + * Compute the raw (non complemented) checksum of a packet. + * + * @param m + * The pointer to the mbuf. + * @param off + * The offset in bytes to start the checksum. + * @param len + * The length in bytes of the data to ckecksum. + * @param cksum + * A pointer to the checksum, filled on success. + * @return + * 0 on success, -1 on error (bad length or offset). + */ +static inline int +rte_raw_cksum_mbuf(const struct rte_mbuf *m, uint32_t off, uint32_t len, + uint16_t *cksum) +{ + const struct rte_mbuf *seg; + const char *buf; + uint32_t sum, tmp; + uint32_t seglen, done; + + /* easy case: all data in the first segment */ + if (off + len <= rte_pktmbuf_data_len(m)) { + *cksum = rte_raw_cksum(rte_pktmbuf_mtod_offset(m, + const char *, off), len); + return 0; + } + + if (unlikely(off + len > rte_pktmbuf_pkt_len(m))) + return -1; /* invalid params, return a dummy value */ + + /* else browse the segment to find offset */ + seglen = 0; + for (seg = m; seg != NULL; seg = seg->next) { + seglen = rte_pktmbuf_data_len(seg); + if (off < seglen) + break; + off -= seglen; + } + seglen -= off; + buf = rte_pktmbuf_mtod_offset(seg, const char *, off); + if (seglen >= len) { + /* all in one segment */ + *cksum = rte_raw_cksum(buf, len); + return 0; + } + + /* hard case: process checksum of several segments */ + sum = 0; + done = 0; + for (;;) { + tmp = __rte_raw_cksum(buf, seglen, 0); + if (done & 1) + tmp = rte_bswap16(tmp); + sum += tmp; + done += seglen; + if (done == len) + break; + seg = seg->next; + buf = rte_pktmbuf_mtod(seg, const char *); + seglen = rte_pktmbuf_data_len(seg); + if (seglen > len - done) + seglen = len - done; + } + + *cksum = __rte_raw_cksum_reduce(sum); + return 0; +} + +/** * Process the IPv4 checksum of an IPv4 header. * * The checksum field must be set to 0 by the caller. diff --git a/lib/librte_net/rte_net.c b/lib/librte_net/rte_net.c new file mode 100644 index 00000000..a8c7aff9 --- /dev/null +++ b/lib/librte_net/rte_net.c @@ -0,0 +1,517 @@ +/*- + * BSD LICENSE + * + * Copyright 2016 6WIND S.A. + * All rights reserved. + * + * 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 <stdint.h> + +#include <rte_mbuf.h> +#include <rte_mbuf_ptype.h> +#include <rte_byteorder.h> +#include <rte_ether.h> +#include <rte_ip.h> +#include <rte_tcp.h> +#include <rte_udp.h> +#include <rte_sctp.h> +#include <rte_gre.h> +#include <rte_net.h> + +/* get l3 packet type from ip6 next protocol */ +static uint32_t +ptype_l3_ip6(uint8_t ip6_proto) +{ + static const uint32_t ip6_ext_proto_map[256] = { + [IPPROTO_HOPOPTS] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6, + [IPPROTO_ROUTING] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6, + [IPPROTO_FRAGMENT] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6, + [IPPROTO_ESP] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6, + [IPPROTO_AH] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6, + [IPPROTO_DSTOPTS] = RTE_PTYPE_L3_IPV6_EXT - RTE_PTYPE_L3_IPV6, + }; + + return RTE_PTYPE_L3_IPV6 + ip6_ext_proto_map[ip6_proto]; +} + +/* get l3 packet type from ip version and header length */ +static uint32_t +ptype_l3_ip(uint8_t ipv_ihl) +{ + static const uint32_t ptype_l3_ip_proto_map[256] = { + [0x45] = RTE_PTYPE_L3_IPV4, + [0x46] = RTE_PTYPE_L3_IPV4_EXT, + [0x47] = RTE_PTYPE_L3_IPV4_EXT, + [0x48] = RTE_PTYPE_L3_IPV4_EXT, + [0x49] = RTE_PTYPE_L3_IPV4_EXT, + [0x4A] = RTE_PTYPE_L3_IPV4_EXT, + [0x4B] = RTE_PTYPE_L3_IPV4_EXT, + [0x4C] = RTE_PTYPE_L3_IPV4_EXT, + [0x4D] = RTE_PTYPE_L3_IPV4_EXT, + [0x4E] = RTE_PTYPE_L3_IPV4_EXT, + [0x4F] = RTE_PTYPE_L3_IPV4_EXT, + }; + + return ptype_l3_ip_proto_map[ipv_ihl]; +} + +/* get l4 packet type from proto */ +static uint32_t +ptype_l4(uint8_t proto) +{ + static const uint32_t ptype_l4_proto[256] = { + [IPPROTO_UDP] = RTE_PTYPE_L4_UDP, + [IPPROTO_TCP] = RTE_PTYPE_L4_TCP, + [IPPROTO_SCTP] = RTE_PTYPE_L4_SCTP, + }; + + return ptype_l4_proto[proto]; +} + +/* get inner l3 packet type from ip6 next protocol */ +static uint32_t +ptype_inner_l3_ip6(uint8_t ip6_proto) +{ + static const uint32_t ptype_inner_ip6_ext_proto_map[256] = { + [IPPROTO_HOPOPTS] = RTE_PTYPE_INNER_L3_IPV6_EXT - + RTE_PTYPE_INNER_L3_IPV6, + [IPPROTO_ROUTING] = RTE_PTYPE_INNER_L3_IPV6_EXT - + RTE_PTYPE_INNER_L3_IPV6, + [IPPROTO_FRAGMENT] = RTE_PTYPE_INNER_L3_IPV6_EXT - + RTE_PTYPE_INNER_L3_IPV6, + [IPPROTO_ESP] = RTE_PTYPE_INNER_L3_IPV6_EXT - + RTE_PTYPE_INNER_L3_IPV6, + [IPPROTO_AH] = RTE_PTYPE_INNER_L3_IPV6_EXT - + RTE_PTYPE_INNER_L3_IPV6, + [IPPROTO_DSTOPTS] = RTE_PTYPE_INNER_L3_IPV6_EXT - + RTE_PTYPE_INNER_L3_IPV6, + }; + + return RTE_PTYPE_INNER_L3_IPV6 + + ptype_inner_ip6_ext_proto_map[ip6_proto]; +} + +/* get inner l3 packet type from ip version and header length */ +static uint32_t +ptype_inner_l3_ip(uint8_t ipv_ihl) +{ + static const uint32_t ptype_inner_l3_ip_proto_map[256] = { + [0x45] = RTE_PTYPE_INNER_L3_IPV4, + [0x46] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x47] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x48] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x49] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x4A] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x4B] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x4C] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x4D] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x4E] = RTE_PTYPE_INNER_L3_IPV4_EXT, + [0x4F] = RTE_PTYPE_INNER_L3_IPV4_EXT, + }; + + return ptype_inner_l3_ip_proto_map[ipv_ihl]; +} + +/* get inner l4 packet type from proto */ +static uint32_t +ptype_inner_l4(uint8_t proto) +{ + static const uint32_t ptype_inner_l4_proto[256] = { + [IPPROTO_UDP] = RTE_PTYPE_INNER_L4_UDP, + [IPPROTO_TCP] = RTE_PTYPE_INNER_L4_TCP, + [IPPROTO_SCTP] = RTE_PTYPE_INNER_L4_SCTP, + }; + + return ptype_inner_l4_proto[proto]; +} + +/* get the tunnel packet type if any, update proto and off. */ +static uint32_t +ptype_tunnel(uint16_t *proto, const struct rte_mbuf *m, + uint32_t *off) +{ + switch (*proto) { + case IPPROTO_GRE: { + static const uint8_t opt_len[16] = { + [0x0] = 4, + [0x1] = 8, + [0x2] = 8, + [0x8] = 8, + [0x3] = 12, + [0x9] = 12, + [0xa] = 12, + [0xb] = 16, + }; + const struct gre_hdr *gh; + struct gre_hdr gh_copy; + uint16_t flags; + + gh = rte_pktmbuf_read(m, *off, sizeof(*gh), &gh_copy); + if (unlikely(gh == NULL)) + return 0; + + flags = rte_be_to_cpu_16(*(const uint16_t *)gh); + flags >>= 12; + if (opt_len[flags] == 0) + return 0; + + *off += opt_len[flags]; + *proto = gh->proto; + if (*proto == rte_cpu_to_be_16(ETHER_TYPE_TEB)) + return RTE_PTYPE_TUNNEL_NVGRE; + else + return RTE_PTYPE_TUNNEL_GRE; + } + case IPPROTO_IPIP: + *proto = rte_cpu_to_be_16(ETHER_TYPE_IPv4); + return RTE_PTYPE_TUNNEL_IP; + case IPPROTO_IPV6: + *proto = rte_cpu_to_be_16(ETHER_TYPE_IPv6); + return RTE_PTYPE_TUNNEL_IP; /* IP is also valid for IPv6 */ + default: + return 0; + } +} + +/* get the ipv4 header length */ +static uint8_t +ip4_hlen(const struct ipv4_hdr *hdr) +{ + return (hdr->version_ihl & 0xf) * 4; +} + +/* parse ipv6 extended headers, update offset and return next proto */ +static uint16_t +skip_ip6_ext(uint16_t proto, const struct rte_mbuf *m, uint32_t *off, + int *frag) +{ + struct ext_hdr { + uint8_t next_hdr; + uint8_t len; + }; + const struct ext_hdr *xh; + struct ext_hdr xh_copy; + unsigned int i; + + *frag = 0; + +#define MAX_EXT_HDRS 5 + for (i = 0; i < MAX_EXT_HDRS; i++) { + switch (proto) { + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: + xh = rte_pktmbuf_read(m, *off, sizeof(*xh), + &xh_copy); + if (xh == NULL) + return 0; + *off += (xh->len + 1) * 8; + proto = xh->next_hdr; + break; + case IPPROTO_FRAGMENT: + xh = rte_pktmbuf_read(m, *off, sizeof(*xh), + &xh_copy); + if (xh == NULL) + return 0; + *off += 8; + proto = xh->next_hdr; + *frag = 1; + return proto; /* this is always the last ext hdr */ + case IPPROTO_NONE: + return 0; + default: + return proto; + } + } + return 0; +} + +/* parse mbuf data to get packet type */ +uint32_t rte_net_get_ptype(const struct rte_mbuf *m, + struct rte_net_hdr_lens *hdr_lens, uint32_t layers) +{ + struct rte_net_hdr_lens local_hdr_lens; + const struct ether_hdr *eh; + struct ether_hdr eh_copy; + uint32_t pkt_type = RTE_PTYPE_L2_ETHER; + uint32_t off = 0; + uint16_t proto; + + if (hdr_lens == NULL) + hdr_lens = &local_hdr_lens; + + eh = rte_pktmbuf_read(m, off, sizeof(*eh), &eh_copy); + if (unlikely(eh == NULL)) + return 0; + proto = eh->ether_type; + off = sizeof(*eh); + hdr_lens->l2_len = off; + + if ((layers & RTE_PTYPE_L2_MASK) == 0) + return 0; + + if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) + goto l3; /* fast path if packet is IPv4 */ + + if (proto == rte_cpu_to_be_16(ETHER_TYPE_VLAN)) { + const struct vlan_hdr *vh; + struct vlan_hdr vh_copy; + + pkt_type = RTE_PTYPE_L2_ETHER_VLAN; + vh = rte_pktmbuf_read(m, off, sizeof(*vh), &vh_copy); + if (unlikely(vh == NULL)) + return pkt_type; + off += sizeof(*vh); + hdr_lens->l2_len += sizeof(*vh); + proto = vh->eth_proto; + } else if (proto == rte_cpu_to_be_16(ETHER_TYPE_QINQ)) { + const struct vlan_hdr *vh; + struct vlan_hdr vh_copy; + + pkt_type = RTE_PTYPE_L2_ETHER_QINQ; + vh = rte_pktmbuf_read(m, off + sizeof(*vh), sizeof(*vh), + &vh_copy); + if (unlikely(vh == NULL)) + return pkt_type; + off += 2 * sizeof(*vh); + hdr_lens->l2_len += 2 * sizeof(*vh); + proto = vh->eth_proto; + } + + l3: + if ((layers & RTE_PTYPE_L3_MASK) == 0) + return pkt_type; + + if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) { + const struct ipv4_hdr *ip4h; + struct ipv4_hdr ip4h_copy; + + ip4h = rte_pktmbuf_read(m, off, sizeof(*ip4h), &ip4h_copy); + if (unlikely(ip4h == NULL)) + return pkt_type; + + pkt_type |= ptype_l3_ip(ip4h->version_ihl); + hdr_lens->l3_len = ip4_hlen(ip4h); + off += hdr_lens->l3_len; + + if ((layers & RTE_PTYPE_L4_MASK) == 0) + return pkt_type; + + if (ip4h->fragment_offset & rte_cpu_to_be_16( + IPV4_HDR_OFFSET_MASK | IPV4_HDR_MF_FLAG)) { + pkt_type |= RTE_PTYPE_L4_FRAG; + hdr_lens->l4_len = 0; + return pkt_type; + } + proto = ip4h->next_proto_id; + pkt_type |= ptype_l4(proto); + } else if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) { + const struct ipv6_hdr *ip6h; + struct ipv6_hdr ip6h_copy; + int frag = 0; + + ip6h = rte_pktmbuf_read(m, off, sizeof(*ip6h), &ip6h_copy); + if (unlikely(ip6h == NULL)) + return pkt_type; + + proto = ip6h->proto; + hdr_lens->l3_len = sizeof(*ip6h); + off += hdr_lens->l3_len; + pkt_type |= ptype_l3_ip6(proto); + if ((pkt_type & RTE_PTYPE_L3_MASK) == RTE_PTYPE_L3_IPV6_EXT) { + proto = skip_ip6_ext(proto, m, &off, &frag); + hdr_lens->l3_len = off - hdr_lens->l2_len; + } + if (proto == 0) + return pkt_type; + + if ((layers & RTE_PTYPE_L4_MASK) == 0) + return pkt_type; + + if (frag) { + pkt_type |= RTE_PTYPE_L4_FRAG; + hdr_lens->l4_len = 0; + return pkt_type; + } + pkt_type |= ptype_l4(proto); + } + + if ((pkt_type & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP) { + hdr_lens->l4_len = sizeof(struct udp_hdr); + return pkt_type; + } else if ((pkt_type & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_TCP) { + const struct tcp_hdr *th; + struct tcp_hdr th_copy; + + th = rte_pktmbuf_read(m, off, sizeof(*th), &th_copy); + if (unlikely(th == NULL)) + return pkt_type & (RTE_PTYPE_L2_MASK | + RTE_PTYPE_L3_MASK); + hdr_lens->l4_len = (th->data_off & 0xf0) >> 2; + return pkt_type; + } else if ((pkt_type & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_SCTP) { + hdr_lens->l4_len = sizeof(struct sctp_hdr); + return pkt_type; + } else { + uint32_t prev_off = off; + + hdr_lens->l4_len = 0; + + if ((layers & RTE_PTYPE_TUNNEL_MASK) == 0) + return pkt_type; + + pkt_type |= ptype_tunnel(&proto, m, &off); + hdr_lens->tunnel_len = off - prev_off; + } + + /* same job for inner header: we need to duplicate the code + * because the packet types do not have the same value. + */ + if ((layers & RTE_PTYPE_INNER_L2_MASK) == 0) + return pkt_type; + + if (proto == rte_cpu_to_be_16(ETHER_TYPE_TEB)) { + eh = rte_pktmbuf_read(m, off, sizeof(*eh), &eh_copy); + if (unlikely(eh == NULL)) + return pkt_type; + pkt_type |= RTE_PTYPE_INNER_L2_ETHER; + proto = eh->ether_type; + off += sizeof(*eh); + hdr_lens->inner_l2_len = sizeof(*eh); + } + + if (proto == rte_cpu_to_be_16(ETHER_TYPE_VLAN)) { + const struct vlan_hdr *vh; + struct vlan_hdr vh_copy; + + pkt_type &= ~RTE_PTYPE_INNER_L2_MASK; + pkt_type |= RTE_PTYPE_INNER_L2_ETHER_VLAN; + vh = rte_pktmbuf_read(m, off, sizeof(*vh), &vh_copy); + if (unlikely(vh == NULL)) + return pkt_type; + off += sizeof(*vh); + hdr_lens->inner_l2_len += sizeof(*vh); + proto = vh->eth_proto; + } else if (proto == rte_cpu_to_be_16(ETHER_TYPE_QINQ)) { + const struct vlan_hdr *vh; + struct vlan_hdr vh_copy; + + pkt_type &= ~RTE_PTYPE_INNER_L2_MASK; + pkt_type |= RTE_PTYPE_INNER_L2_ETHER_QINQ; + vh = rte_pktmbuf_read(m, off + sizeof(*vh), sizeof(*vh), + &vh_copy); + if (unlikely(vh == NULL)) + return pkt_type; + off += 2 * sizeof(*vh); + hdr_lens->inner_l2_len += 2 * sizeof(*vh); + proto = vh->eth_proto; + } + + if ((layers & RTE_PTYPE_INNER_L3_MASK) == 0) + return pkt_type; + + if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) { + const struct ipv4_hdr *ip4h; + struct ipv4_hdr ip4h_copy; + + ip4h = rte_pktmbuf_read(m, off, sizeof(*ip4h), &ip4h_copy); + if (unlikely(ip4h == NULL)) + return pkt_type; + + pkt_type |= ptype_inner_l3_ip(ip4h->version_ihl); + hdr_lens->inner_l3_len = ip4_hlen(ip4h); + off += hdr_lens->inner_l3_len; + + if ((layers & RTE_PTYPE_INNER_L4_MASK) == 0) + return pkt_type; + if (ip4h->fragment_offset & + rte_cpu_to_be_16(IPV4_HDR_OFFSET_MASK | + IPV4_HDR_MF_FLAG)) { + pkt_type |= RTE_PTYPE_INNER_L4_FRAG; + hdr_lens->inner_l4_len = 0; + return pkt_type; + } + proto = ip4h->next_proto_id; + pkt_type |= ptype_inner_l4(proto); + } else if (proto == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) { + const struct ipv6_hdr *ip6h; + struct ipv6_hdr ip6h_copy; + int frag = 0; + + ip6h = rte_pktmbuf_read(m, off, sizeof(*ip6h), &ip6h_copy); + if (unlikely(ip6h == NULL)) + return pkt_type; + + proto = ip6h->proto; + hdr_lens->inner_l3_len = sizeof(*ip6h); + off += hdr_lens->inner_l3_len; + pkt_type |= ptype_inner_l3_ip6(proto); + if ((pkt_type & RTE_PTYPE_INNER_L3_MASK) == + RTE_PTYPE_INNER_L3_IPV6_EXT) { + uint32_t prev_off; + + prev_off = off; + proto = skip_ip6_ext(proto, m, &off, &frag); + hdr_lens->inner_l3_len += off - prev_off; + } + if (proto == 0) + return pkt_type; + + if ((layers & RTE_PTYPE_INNER_L4_MASK) == 0) + return pkt_type; + + if (frag) { + pkt_type |= RTE_PTYPE_INNER_L4_FRAG; + hdr_lens->inner_l4_len = 0; + return pkt_type; + } + pkt_type |= ptype_inner_l4(proto); + } + + if ((pkt_type & RTE_PTYPE_INNER_L4_MASK) == RTE_PTYPE_INNER_L4_UDP) { + hdr_lens->inner_l4_len = sizeof(struct udp_hdr); + } else if ((pkt_type & RTE_PTYPE_INNER_L4_MASK) == + RTE_PTYPE_INNER_L4_TCP) { + const struct tcp_hdr *th; + struct tcp_hdr th_copy; + + th = rte_pktmbuf_read(m, off, sizeof(*th), &th_copy); + if (unlikely(th == NULL)) + return pkt_type & (RTE_PTYPE_INNER_L2_MASK | + RTE_PTYPE_INNER_L3_MASK); + hdr_lens->inner_l4_len = (th->data_off & 0xf0) >> 2; + } else if ((pkt_type & RTE_PTYPE_INNER_L4_MASK) == + RTE_PTYPE_INNER_L4_SCTP) { + hdr_lens->inner_l4_len = sizeof(struct sctp_hdr); + } else { + hdr_lens->inner_l4_len = 0; + } + + return pkt_type; +} diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h new file mode 100644 index 00000000..d4156aea --- /dev/null +++ b/lib/librte_net/rte_net.h @@ -0,0 +1,94 @@ +/*- + * BSD LICENSE + * + * Copyright 2016 6WIND S.A. + * All rights reserved. + * + * 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 Intel Corporation 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_NET_PTYPE_H_ +#define _RTE_NET_PTYPE_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * Structure containing header lengths associated to a packet, filled + * by rte_net_get_ptype(). + */ +struct rte_net_hdr_lens { + uint8_t l2_len; + uint8_t l3_len; + uint8_t l4_len; + uint8_t tunnel_len; + uint8_t inner_l2_len; + uint8_t inner_l3_len; + uint8_t inner_l4_len; +}; + +/** + * Parse an Ethernet packet to get its packet type. + * + * This function parses the network headers in mbuf data and return its + * packet type. + * + * If it is provided by the user, it also fills a rte_net_hdr_lens + * structure that contains the lengths of the parsed network + * headers. Each length field is valid only if the associated packet + * type is set. For instance, hdr_lens->l2_len is valid only if + * (retval & RTE_PTYPE_L2_MASK) != RTE_PTYPE_UNKNOWN. + * + * Supported packet types are: + * L2: Ether, Vlan, QinQ + * L3: IPv4, IPv6 + * L4: TCP, UDP, SCTP + * Tunnels: IPv4, IPv6, Gre, Nvgre + * + * @param m + * The packet mbuf to be parsed. + * @param hdr_lens + * A pointer to a structure where the header lengths will be returned, + * or NULL. + * @param layers + * List of layers to parse. The function will stop at the first + * empty layer. Examples: + * - To parse all known layers, use RTE_PTYPE_ALL_MASK. + * - To parse only L2 and L3, use RTE_PTYPE_L2_MASK | RTE_PTYPE_L3_MASK + * @return + * The packet type of the packet. + */ +uint32_t rte_net_get_ptype(const struct rte_mbuf *m, + struct rte_net_hdr_lens *hdr_lens, uint32_t layers); + +#ifdef __cplusplus +} +#endif + + +#endif /* _RTE_NET_PTYPE_H_ */ diff --git a/lib/librte_net/rte_net_version.map b/lib/librte_net/rte_net_version.map new file mode 100644 index 00000000..3b15e651 --- /dev/null +++ b/lib/librte_net/rte_net_version.map @@ -0,0 +1,6 @@ +DPDK_16.11 { + global: + rte_net_get_ptype; + + local: *; +}; |