同一个socket是否可以bind多个端口？

版权所有，转载请注明出处。
Author: Tony

今天一个可爱的同事问我同一个socket能否bind多个port？说实话，真没这么玩过。本着严谨的态度，决定研究一下这样是否可以。
说明本内容针对的内核版本是SLES 11 SP2 3.0.13-0.27

首先分析系统调用函数bind，内核层实现在net/socket.c中：

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
    struct socket *sock;
    struct sockaddr_storage address;
    int err, fput_needed;

    sock = sockfd_lookup_light(fd, &err, &fput_needed);
    if (sock) {
        err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
        if (err >= 0) {
            err = security_socket_bind(sock,
                         (struct sockaddr *)&address,
                           addrlen);
            if (!err)
            /*这里调用对应proto_ops的bind，这里以tcp为例说明
              proto_ops实现了从协议无关的套接口层到协议相关的传输层的转接
            */
                err = sock->ops->bind(sock,
                         (struct sockaddr *)
                         &address, addrlen);
        }
        fput_light(sock->file, fput_needed);
    }
    return err;
}

在net/ipv4/af_inet.c中，inet_protosw定义了tcp传输层的proto_ops

static struct inet_protosw inetsw_array[] =
{
    {
        .type = SOCK_STREAM,
        .protocol = IPPROTO_TCP,
        .prot = &tcp_prot,
        /*这里指定了tcp传输层协议的proto_ops*/
        .ops = &inet_stream_ops,
        .no_check = 0,
        .flags = INET_PROTOSW_PERMANENT |
                  INET_PROTOSW_ICSK,
    },

    {
        .type = SOCK_DGRAM,
        .protocol = IPPROTO_UDP,
        .prot = &udp_prot,
        .ops = &inet_dgram_ops,
        .no_check = UDP_CSUM_DEFAULT,
        .flags = INET_PROTOSW_PERMANENT,
       },

       {
        .type = SOCK_DGRAM,
        .protocol = IPPROTO_ICMP,
        .prot = &ping_prot,
        .ops = &inet_dgram_ops,
        .no_check = UDP_CSUM_DEFAULT,
        .flags = INET_PROTOSW_REUSE,
       },

       {
     .type = SOCK_RAW,
     .protocol = IPPROTO_IP,    /* wild card */
     .prot = &raw_prot,
     .ops = &inet_sockraw_ops,
     .no_check = UDP_CSUM_DEFAULT,
     .flags = INET_PROTOSW_REUSE,
       }
};

inet_stream_ops的定义也在net/ipv4/af_inet.c中

const struct proto_ops inet_stream_ops = {
    .family         = PF_INET,
    .owner         = THIS_MODULE,
    .release     = inet_release,
    /*这里指定了tcp协议proto_ops的bind函数为inet_bind*/
    .bind         = inet_bind,
    .connect     = inet_stream_connect,
    .socketpair     = sock_no_socketpair,
    .accept         = inet_accept,
    .getname     = inet_getname,
    .poll         = tcp_poll,
    .ioctl         = inet_ioctl,
    .listen         = inet_listen,
    .shutdown     = inet_shutdown,
    .setsockopt     = sock_common_setsockopt,
    .getsockopt     = sock_common_getsockopt,
    .sendmsg     = inet_sendmsg,
    .recvmsg     = inet_recvmsg,
    .mmap         = sock_no_mmap,
    .sendpage     = inet_sendpage,
    .splice_read     = tcp_splice_read,
#ifdef CONFIG_COMPAT
    .compat_setsockopt = compat_sock_common_setsockopt,
    .compat_getsockopt = compat_sock_common_getsockopt,
    .compat_ioctl     = inet_compat_ioctl,
#endif
};

inet_bind的实现也在文件net/ipv4/af_inet.c中

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
    struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
    struct sock *sk = sock->sk;
    struct inet_sock *inet = inet_sk(sk);
    unsigned short snum;
    int chk_addr_ret;
    int err;

    /* If the socket has its own bind function then use it. (RAW) */
    if (sk->sk_prot->bind) {
        err = sk->sk_prot->bind(sk, uaddr, addr_len);
        goto out;
    }
    err = -EINVAL;
    if (addr_len < sizeof(struct sockaddr_in))
        goto out;

    if (addr->sin_family != AF_INET) {
        /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
         * only if s_addr is INADDR_ANY.
         */
        err = -EAFNOSUPPORT;
        if (addr->sin_family != AF_UNSPEC ||
            addr->sin_addr.s_addr != htonl(INADDR_ANY))
            goto out;
    }

    chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);

    /* Not specified by any standard per-se, however it breaks too
     * many applications when removed. It is unfortunate since
     * allowing applications to make a non-local bind solves
     * several problems with systems using dynamic addressing.
     * (ie. your servers still start up even if your ISDN link
     * is temporarily down)
     */
    err = -EADDRNOTAVAIL;
    if (!sysctl_ip_nonlocal_bind &&
     !(inet->freebind || inet->transparent) &&
        addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
        chk_addr_ret != RTN_LOCAL &&
        chk_addr_ret != RTN_MULTICAST &&
        chk_addr_ret != RTN_BROADCAST)
        goto out;

    snum = ntohs(addr->sin_port);
    err = -EACCES;
    if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
        goto out;

    /* We keep a pair of addresses. rcv_saddr is the one
     * used by hash lookups, and saddr is used for transmit.
     *
     * In the BSD API these are the same except where it
     * would be illegal to use them (multicast/broadcast) in
     * which case the sending device address is used.
     */
    lock_sock(sk);

    /* Check these errors (active socket, double bind). */
    err = -EINVAL;
    /*这里会校验要bind的sock是不是在TCP_CLOSE状态（未使用），以及当前
      sock是否已经bind相应的端口。
      当该sock第一次bind的时候，inet->inet_num肯定是0，当bind一次后，
      这个inet_num就变为了非零，从而一个socket最多bind一个端口，如果
      尝试bind多个端口将会返回错误22（EINVAL)
      下面我们看一下，inet_num是在什么时候被复制的？
    */
    if (sk->sk_state != TCP_CLOSE || inet->inet_num)
        goto out_release_sock;

    inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
    if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
        inet->inet_saddr = 0; /* Use device */

    /* Make sure we are allowed to bind here. */
    /* 这个函数会根据传入的参数，选择一个可用的端口进行bind,
       sk->sk_prot就是网络控制块sock的操作函数，struct proto
       实现了传输层到网络层的转换。
       tcp sock的get_port函数是inet_csk_get_port函数
       tcp_prot(struct proto)在net/ipv4/tcp_ipv4.c中定义
    */
    if (sk->sk_prot->get_port(sk, snum)) {
        inet->inet_saddr = inet->inet_rcv_saddr = 0;
        err = -EADDRINUSE;
        goto out_release_sock;
    }

    if (inet->inet_rcv_saddr)
        sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
    if (snum)
        sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
    inet->inet_sport = htons(inet->inet_num);
    inet->inet_daddr = 0;
    inet->inet_dport = 0;
    sk_dst_reset(sk);
    err = 0;
out_release_sock:
    release_sock(sk);
out:
    return err;
}

inet_csk_get_port的实现在net/ipv4/inet_connection_sock.c中

/* Obtain a reference to a local port for the given sock,
 * if snum is zero it means select any available local port.
 */
int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
    struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
    struct inet_bind_hashbucket *head;
    struct hlist_node *node;
    struct inet_bind_bucket *tb;
    int ret, attempts = 5;
    struct net *net = sock_net(sk);
    int smallest_size = -1, smallest_rover;

    local_bh_disable();
    /*从这里可用看的，如果传入的端口为0，那么内核会自动选择一个可用的端口*/
    if (!snum) {
        int remaining, rover, low, high;

again:
        inet_get_local_port_range(&low, &high);
        remaining = (high - low) + 1;
        smallest_rover = rover = net_random() % remaining + low;

        smallest_size = -1;
        do {
            if (inet_is_reserved_local_port(rover))
                goto next_nolock;
            head = &hashinfo->bhash[inet_bhashfn(net, rover,
                    hashinfo->bhash_size)];
            spin_lock(&head->lock);
            inet_bind_bucket_for_each(tb, node, &head->chain)
                if (net_eq(ib_net(tb), net) && tb->port == rover) {
                    if (tb->fastreuse > 0 &&
                        sk->sk_reuse &&
                        sk->sk_state != TCP_LISTEN &&
                     (tb->num_owners < smallest_size || smallest_size == -1)) {
                        smallest_size = tb->num_owners;
                        smallest_rover = rover;
                        if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
                            spin_unlock(&head->lock);
                            snum = smallest_rover;
                            goto have_snum;
                        }
                    }
                    goto next;
                }
            break;
        next:
            spin_unlock(&head->lock);
        next_nolock:
            if (++rover > high)
                rover = low;
        } while (--remaining > 0);

        /* Exhausted local port range during search? It is not
         * possible for us to be holding one of the bind hash
         * locks if this test triggers, because if 'remaining'
         * drops to zero, we broke out of the do/while loop at
         * the top level, not from the 'break;' statement.
         */
        ret = 1;
        if (remaining <= 0) {
            if (smallest_size != -1) {
                snum = smallest_rover;
                goto have_snum;
            }
            goto fail;
        }
        /* OK, here is the one we will use. HEAD is
         * non-NULL and we hold it's mutex.
         */
        snum = rover;
    } else {
have_snum:
        head = &hashinfo->bhash[inet_bhashfn(net, snum,
                hashinfo->bhash_size)];
        spin_lock(&head->lock);
        inet_bind_bucket_for_each(tb, node, &head->chain)
            if (net_eq(ib_net(tb), net) && tb->port == snum)
                goto tb_found;
    }
    tb = NULL;
    goto tb_not_found;
tb_found:
    if (!hlist_empty(&tb->owners)) {
        if (tb->fastreuse > 0 &&
            sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
            smallest_size == -1) {
            goto success;
        } else {
            ret = 1;
            if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
                if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
                    smallest_size != -1 && --attempts >= 0) {
                    spin_unlock(&head->lock);
                    goto again;
                }
                goto fail_unlock;
            }
        }
    }
tb_not_found:
    ret = 1;
    if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep,
                    net, head, snum)) == NULL)
        goto fail_unlock;
    if (hlist_empty(&tb->owners)) {
        if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
            tb->fastreuse = 1;
        else
            tb->fastreuse = 0;
    } else if (tb->fastreuse &&
         (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
        tb->fastreuse = 0;
success:
    if (!inet_csk(sk)->icsk_bind_hash)
        /*到这里说明端口是可用的了,需要将该sk挂接到该端口的owners链表中
          我们看一下这个函数的实现。
        */
        inet_bind_hash(sk, tb, snum);
    WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
    ret = 0;

fail_unlock:
    spin_unlock(&head->lock);
fail:
    local_bh_enable();
    return ret;
}

inet_bind_hash函数在net/ipv4/inet_hashtables.c中实现

void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
         const unsigned short snum)
{
    struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;

    atomic_inc(&hashinfo->bsockets);
    /*
        在这里将sock的inet_num置为选中的端口。
    */
    inet_sk(sk)->inet_num = snum;
    sk_add_bind_node(sk, &tb->owners);
    tb->num_owners++;
    inet_csk(sk)->icsk_bind_hash = tb;
}

综上的分析，可用看出同一个socket只可以bind最多一个端口，如果bind超过1个端口，会返回错误22（EINVAL）。