rte_ip.h

Go to the documentation of this file.

/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 1982, 1986, 1990, 1993
 *      The Regents of the University of California.
 * Copyright(c) 2010-2014 Intel Corporation.
 * Copyright(c) 2014 6WIND S.A.
 * All rights reserved.
 */

#ifndef _RTE_IP_H_
#define _RTE_IP_H_

#include <stdint.h>

#ifdef RTE_EXEC_ENV_WINDOWS
#include <ws2tcpip.h>
#else
#include <sys/socket.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <netinet/ip.h>
#include <netinet/ip6.h>
#endif

#include <rte_byteorder.h>
#include <rte_mbuf.h>

#ifdef __cplusplus
extern "C" {
#endif

struct rte_ipv4_hdr {
    __extension__
    union {
        uint8_t version_ihl;    
        struct {
#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
            uint8_t ihl:4;     
            uint8_t version:4; 
#elif RTE_BYTE_ORDER == RTE_BIG_ENDIAN
            uint8_t version:4; 
            uint8_t ihl:4;     
#endif
        };
    };
    uint8_t  type_of_service;   
    rte_be16_t total_length;    
    rte_be16_t packet_id;       
    rte_be16_t fragment_offset; 
    uint8_t  time_to_live;      
    uint8_t  next_proto_id;     
    rte_be16_t hdr_checksum;    
    rte_be32_t src_addr;        
    rte_be32_t dst_addr;        
} __rte_packed;

#define RTE_IPV4(a, b, c, d) ((uint32_t)(((a) & 0xff) << 24) | \
                       (((b) & 0xff) << 16) | \
                       (((c) & 0xff) << 8)  | \
                       ((d) & 0xff))

#define RTE_IPV4_MAX_PKT_LEN        65535

#define RTE_IPV4_HDR_IHL_MASK   (0x0f)

#define RTE_IPV4_IHL_MULTIPLIER (4)

/* Type of Service fields */
#define RTE_IPV4_HDR_DSCP_MASK  (0xfc)
#define RTE_IPV4_HDR_ECN_MASK   (0x03)
#define RTE_IPV4_HDR_ECN_CE RTE_IPV4_HDR_ECN_MASK

/* Fragment Offset * Flags. */
#define RTE_IPV4_HDR_DF_SHIFT   14
#define RTE_IPV4_HDR_MF_SHIFT   13
#define RTE_IPV4_HDR_FO_SHIFT   3

#define RTE_IPV4_HDR_DF_FLAG    (1 << RTE_IPV4_HDR_DF_SHIFT)
#define RTE_IPV4_HDR_MF_FLAG    (1 << RTE_IPV4_HDR_MF_SHIFT)

#define RTE_IPV4_HDR_OFFSET_MASK    ((1 << RTE_IPV4_HDR_MF_SHIFT) - 1)

#define RTE_IPV4_HDR_OFFSET_UNITS   8

/*
 * IPv4 address types
 */
#define RTE_IPV4_ANY              ((uint32_t)0x00000000) 
#define RTE_IPV4_LOOPBACK         ((uint32_t)0x7f000001) 
#define RTE_IPV4_BROADCAST        ((uint32_t)0xe0000000) 
#define RTE_IPV4_ALLHOSTS_GROUP   ((uint32_t)0xe0000001) 
#define RTE_IPV4_ALLRTRS_GROUP    ((uint32_t)0xe0000002) 
#define RTE_IPV4_MAX_LOCAL_GROUP  ((uint32_t)0xe00000ff) 
/*
 * IPv4 Multicast-related macros
 */
#define RTE_IPV4_MIN_MCAST \
    RTE_IPV4(224, 0, 0, 0)          
#define RTE_IPV4_MAX_MCAST \
    RTE_IPV4(239, 255, 255, 255)    
#define RTE_IS_IPV4_MCAST(x) \
    ((x) >= RTE_IPV4_MIN_MCAST && (x) <= RTE_IPV4_MAX_MCAST)

/* IPv4 default fields values */
#define RTE_IPV4_MIN_IHL    (0x5)
#define RTE_IPV4_VHL_DEF    ((IPVERSION << 4) | RTE_IPV4_MIN_IHL)

static inline uint8_t
rte_ipv4_hdr_len(const struct rte_ipv4_hdr *ipv4_hdr)
{
    return (uint8_t)((ipv4_hdr->version_ihl & RTE_IPV4_HDR_IHL_MASK) *
        RTE_IPV4_IHL_MULTIPLIER);
}

static inline uint32_t
__rte_raw_cksum(const void *buf, size_t len, uint32_t sum)
{
    /* extend strict-aliasing rules */
    typedef uint16_t __attribute__((__may_alias__)) u16_p;
    const u16_p *u16_buf = (const u16_p *)buf;
    const u16_p *end = u16_buf + len / sizeof(*u16_buf);

    for (; u16_buf != end; ++u16_buf)
        sum += *u16_buf;

    /* if length is odd, keeping it byte order independent */
    if (unlikely(len % 2)) {
        uint16_t left = 0;
        *(unsigned char *)&left = *(const unsigned char *)end;
        sum += left;
    }

    return sum;
}

static inline uint16_t
__rte_raw_cksum_reduce(uint32_t sum)
{
    sum = ((sum & 0xffff0000) >> 16) + (sum & 0xffff);
    sum = ((sum & 0xffff0000) >> 16) + (sum & 0xffff);
    return (uint16_t)sum;
}

static inline uint16_t
rte_raw_cksum(const void *buf, size_t len)
{
    uint32_t sum;

    sum = __rte_raw_cksum(buf, len, 0);
    return __rte_raw_cksum_reduce(sum);
}

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;
    }
    RTE_ASSERT(seg != NULL);
    if (seg == NULL)
        return -1;
    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((uint16_t)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;
}

static inline uint16_t
rte_ipv4_cksum(const struct rte_ipv4_hdr *ipv4_hdr)
{
    uint16_t cksum;
    cksum = rte_raw_cksum(ipv4_hdr, rte_ipv4_hdr_len(ipv4_hdr));
    return (uint16_t)~cksum;
}

static inline uint16_t
rte_ipv4_phdr_cksum(const struct rte_ipv4_hdr *ipv4_hdr, uint64_t ol_flags)
{
    struct ipv4_psd_header {
        uint32_t src_addr; /* IP address of source host. */
        uint32_t dst_addr; /* IP address of destination host. */
        uint8_t  zero;     /* zero. */
        uint8_t  proto;    /* L4 protocol type. */
        uint16_t len;      /* L4 length. */
    } psd_hdr;

    uint32_t l3_len;

    psd_hdr.src_addr = ipv4_hdr->src_addr;
    psd_hdr.dst_addr = ipv4_hdr->dst_addr;
    psd_hdr.zero = 0;
    psd_hdr.proto = ipv4_hdr->next_proto_id;
    if (ol_flags & RTE_MBUF_F_TX_TCP_SEG) {
        psd_hdr.len = 0;
    } else {
        l3_len = rte_be_to_cpu_16(ipv4_hdr->total_length);
        psd_hdr.len = rte_cpu_to_be_16((uint16_t)(l3_len -
            rte_ipv4_hdr_len(ipv4_hdr)));
    }
    return rte_raw_cksum(&psd_hdr, sizeof(psd_hdr));
}

static inline uint16_t
__rte_ipv4_udptcp_cksum(const struct rte_ipv4_hdr *ipv4_hdr, const void *l4_hdr)
{
    uint32_t cksum;
    uint32_t l3_len, l4_len;
    uint8_t ip_hdr_len;

    ip_hdr_len = rte_ipv4_hdr_len(ipv4_hdr);
    l3_len = rte_be_to_cpu_16(ipv4_hdr->total_length);
    if (l3_len < ip_hdr_len)
        return 0;

    l4_len = l3_len - ip_hdr_len;

    cksum = rte_raw_cksum(l4_hdr, l4_len);
    cksum += rte_ipv4_phdr_cksum(ipv4_hdr, 0);

    cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);

    return (uint16_t)cksum;
}

static inline uint16_t
rte_ipv4_udptcp_cksum(const struct rte_ipv4_hdr *ipv4_hdr, const void *l4_hdr)
{
    uint16_t cksum = __rte_ipv4_udptcp_cksum(ipv4_hdr, l4_hdr);

    cksum = ~cksum;

    /*
     * Per RFC 768: If the computed checksum is zero for UDP,
     * it is transmitted as all ones
     * (the equivalent in one's complement arithmetic).
     */
    if (cksum == 0 && ipv4_hdr->next_proto_id == IPPROTO_UDP)
        cksum = 0xffff;

    return cksum;
}

static inline uint16_t
__rte_ipv4_udptcp_cksum_mbuf(const struct rte_mbuf *m,
                 const struct rte_ipv4_hdr *ipv4_hdr,
                 uint16_t l4_off)
{
    uint16_t raw_cksum;
    uint32_t cksum;

    if (l4_off > m->pkt_len)
        return 0;

    if (rte_raw_cksum_mbuf(m, l4_off, m->pkt_len - l4_off, &raw_cksum))
        return 0;

    cksum = raw_cksum + rte_ipv4_phdr_cksum(ipv4_hdr, 0);

    cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);

    return (uint16_t)cksum;
}

__rte_experimental
static inline uint16_t
rte_ipv4_udptcp_cksum_mbuf(const struct rte_mbuf *m,
               const struct rte_ipv4_hdr *ipv4_hdr, uint16_t l4_off)
{
    uint16_t cksum = __rte_ipv4_udptcp_cksum_mbuf(m, ipv4_hdr, l4_off);

    cksum = ~cksum;

    /*
     * Per RFC 768: If the computed checksum is zero for UDP,
     * it is transmitted as all ones
     * (the equivalent in one's complement arithmetic).
     */
    if (cksum == 0 && ipv4_hdr->next_proto_id == IPPROTO_UDP)
        cksum = 0xffff;

    return cksum;
}

__rte_experimental
static inline int
rte_ipv4_udptcp_cksum_verify(const struct rte_ipv4_hdr *ipv4_hdr,
                 const void *l4_hdr)
{
    uint16_t cksum = __rte_ipv4_udptcp_cksum(ipv4_hdr, l4_hdr);

    if (cksum != 0xffff)
        return -1;

    return 0;
}

__rte_experimental
static inline uint16_t
rte_ipv4_udptcp_cksum_mbuf_verify(const struct rte_mbuf *m,
                  const struct rte_ipv4_hdr *ipv4_hdr,
                  uint16_t l4_off)
{
    uint16_t cksum = __rte_ipv4_udptcp_cksum_mbuf(m, ipv4_hdr, l4_off);

    if (cksum != 0xffff)
        return -1;

    return 0;
}

struct rte_ipv6_hdr {
    rte_be32_t vtc_flow;    
    rte_be16_t payload_len; 
    uint8_t  proto;     
    uint8_t  hop_limits;    
    uint8_t  src_addr[16];  
    uint8_t  dst_addr[16];  
} __rte_packed;

/* IPv6 vtc_flow: IPv / TC / flow_label */
#define RTE_IPV6_HDR_FL_SHIFT 0
#define RTE_IPV6_HDR_TC_SHIFT 20
#define RTE_IPV6_HDR_FL_MASK    ((1u << RTE_IPV6_HDR_TC_SHIFT) - 1)
#define RTE_IPV6_HDR_TC_MASK    (0xff << RTE_IPV6_HDR_TC_SHIFT)
#define RTE_IPV6_HDR_DSCP_MASK  (0xfc << RTE_IPV6_HDR_TC_SHIFT)
#define RTE_IPV6_HDR_ECN_MASK   (0x03 << RTE_IPV6_HDR_TC_SHIFT)
#define RTE_IPV6_HDR_ECN_CE RTE_IPV6_HDR_ECN_MASK

#define RTE_IPV6_MIN_MTU 1280 
static inline uint16_t
rte_ipv6_phdr_cksum(const struct rte_ipv6_hdr *ipv6_hdr, uint64_t ol_flags)
{
    uint32_t sum;
    struct {
        rte_be32_t len;   /* L4 length. */
        rte_be32_t proto; /* L4 protocol - top 3 bytes must be zero */
    } psd_hdr;

    psd_hdr.proto = (uint32_t)(ipv6_hdr->proto << 24);
    if (ol_flags & RTE_MBUF_F_TX_TCP_SEG) {
        psd_hdr.len = 0;
    } else {
        psd_hdr.len = ipv6_hdr->payload_len;
    }

    sum = __rte_raw_cksum(ipv6_hdr->src_addr,
        sizeof(ipv6_hdr->src_addr) + sizeof(ipv6_hdr->dst_addr),
        0);
    sum = __rte_raw_cksum(&psd_hdr, sizeof(psd_hdr), sum);
    return __rte_raw_cksum_reduce(sum);
}

static inline uint16_t
__rte_ipv6_udptcp_cksum(const struct rte_ipv6_hdr *ipv6_hdr, const void *l4_hdr)
{
    uint32_t cksum;
    uint32_t l4_len;

    l4_len = rte_be_to_cpu_16(ipv6_hdr->payload_len);

    cksum = rte_raw_cksum(l4_hdr, l4_len);
    cksum += rte_ipv6_phdr_cksum(ipv6_hdr, 0);

    cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);

    return (uint16_t)cksum;
}

static inline uint16_t
rte_ipv6_udptcp_cksum(const struct rte_ipv6_hdr *ipv6_hdr, const void *l4_hdr)
{
    uint16_t cksum = __rte_ipv6_udptcp_cksum(ipv6_hdr, l4_hdr);

    cksum = ~cksum;

    /*
     * Per RFC 768: If the computed checksum is zero for UDP,
     * it is transmitted as all ones
     * (the equivalent in one's complement arithmetic).
     */
    if (cksum == 0 && ipv6_hdr->proto == IPPROTO_UDP)
        cksum = 0xffff;

    return cksum;
}

static inline uint16_t
__rte_ipv6_udptcp_cksum_mbuf(const struct rte_mbuf *m,
                 const struct rte_ipv6_hdr *ipv6_hdr,
                 uint16_t l4_off)
{
    uint16_t raw_cksum;
    uint32_t cksum;

    if (l4_off > m->pkt_len)
        return 0;

    if (rte_raw_cksum_mbuf(m, l4_off, m->pkt_len - l4_off, &raw_cksum))
        return 0;

    cksum = raw_cksum + rte_ipv6_phdr_cksum(ipv6_hdr, 0);

    cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);

    return (uint16_t)cksum;
}

__rte_experimental
static inline uint16_t
rte_ipv6_udptcp_cksum_mbuf(const struct rte_mbuf *m,
               const struct rte_ipv6_hdr *ipv6_hdr, uint16_t l4_off)
{
    uint16_t cksum = __rte_ipv6_udptcp_cksum_mbuf(m, ipv6_hdr, l4_off);

    cksum = ~cksum;

    /*
     * Per RFC 768: If the computed checksum is zero for UDP,
     * it is transmitted as all ones
     * (the equivalent in one's complement arithmetic).
     */
    if (cksum == 0 && ipv6_hdr->proto == IPPROTO_UDP)
        cksum = 0xffff;

    return cksum;
}

__rte_experimental
static inline int
rte_ipv6_udptcp_cksum_verify(const struct rte_ipv6_hdr *ipv6_hdr,
                 const void *l4_hdr)
{
    uint16_t cksum = __rte_ipv6_udptcp_cksum(ipv6_hdr, l4_hdr);

    if (cksum != 0xffff)
        return -1;

    return 0;
}

__rte_experimental
static inline int
rte_ipv6_udptcp_cksum_mbuf_verify(const struct rte_mbuf *m,
                  const struct rte_ipv6_hdr *ipv6_hdr,
                  uint16_t l4_off)
{
    uint16_t cksum = __rte_ipv6_udptcp_cksum_mbuf(m, ipv6_hdr, l4_off);

    if (cksum != 0xffff)
        return -1;

    return 0;
}

#define RTE_IPV6_EHDR_MF_SHIFT  0
#define RTE_IPV6_EHDR_MF_MASK   1
#define RTE_IPV6_EHDR_FO_SHIFT  3
#define RTE_IPV6_EHDR_FO_MASK   (~((1 << RTE_IPV6_EHDR_FO_SHIFT) - 1))
#define RTE_IPV6_EHDR_FO_ALIGN  (1 << RTE_IPV6_EHDR_FO_SHIFT)

#define RTE_IPV6_FRAG_USED_MASK (RTE_IPV6_EHDR_MF_MASK | RTE_IPV6_EHDR_FO_MASK)

#define RTE_IPV6_GET_MF(x)  ((x) & RTE_IPV6_EHDR_MF_MASK)
#define RTE_IPV6_GET_FO(x)  ((x) >> RTE_IPV6_EHDR_FO_SHIFT)

#define RTE_IPV6_SET_FRAG_DATA(fo, mf)  \
    (((fo) & RTE_IPV6_EHDR_FO_MASK) | ((mf) & RTE_IPV6_EHDR_MF_MASK))

struct rte_ipv6_fragment_ext {
    uint8_t next_header;    
    uint8_t reserved;   
    rte_be16_t frag_data;   
    rte_be32_t id;      
} __rte_packed;

/* IPv6 fragment extension header size */
#define RTE_IPV6_FRAG_HDR_SIZE  sizeof(struct rte_ipv6_fragment_ext)

__rte_experimental
static inline int
rte_ipv6_get_next_ext(const uint8_t *p, int proto, size_t *ext_len)
{
    int next_proto;

    switch (proto) {
    case IPPROTO_AH:
        next_proto = *p++;
        *ext_len = (*p + 2) * sizeof(uint32_t);
        break;

    case IPPROTO_HOPOPTS:
    case IPPROTO_ROUTING:
    case IPPROTO_DSTOPTS:
        next_proto = *p++;
        *ext_len = (*p + 1) * sizeof(uint64_t);
        break;

    case IPPROTO_FRAGMENT:
        next_proto = *p;
        *ext_len = RTE_IPV6_FRAG_HDR_SIZE;
        break;

    default:
        return -EINVAL;
    }

    return next_proto;
}

#ifdef __cplusplus
}
#endif

#endif /* _RTE_IP_H_ */