深入理解TCP协议及其源代码

struct proto tcp_prot = {
    .name            = "TCP",
    .owner            = THIS_MODULE,
    .close            = tcp_close,
    .pre_connect        = tcp_v4_pre_connect,
    .connect        = tcp_v4_connect,
    .disconnect        = tcp_disconnect,
    .accept            = inet_csk_accept,
    .ioctl            = tcp_ioctl,
    .init            = tcp_v4_init_sock,
    .destroy        = tcp_v4_destroy_sock,
    .shutdown        = tcp_shutdown,
    .setsockopt        = tcp_setsockopt,
    .getsockopt        = tcp_getsockopt,
    .keepalive        = tcp_set_keepalive,
    .recvmsg        = tcp_recvmsg,
    .sendmsg        = tcp_sendmsg,
    .sendpage        = tcp_sendpage,
    .backlog_rcv        = tcp_v4_do_rcv,
    .release_cb        = tcp_release_cb,
    .hash            = inet_hash,
    .unhash            = inet_unhash,
    .get_port        = inet_csk_get_port,
    .enter_memory_pressure    = tcp_enter_memory_pressure,
    .leave_memory_pressure    = tcp_leave_memory_pressure,
    .stream_memory_free    = tcp_stream_memory_free,
    .sockets_allocated    = &tcp_sockets_allocated,
    .orphan_count        = &tcp_orphan_count,
    .memory_allocated    = &tcp_memory_allocated,
    .memory_pressure    = &tcp_memory_pressure,
    .sysctl_mem        = sysctl_tcp_mem,
    .sysctl_wmem_offset    = offsetof(struct net, ipv4.sysctl_tcp_wmem),
    .sysctl_rmem_offset    = offsetof(struct net, ipv4.sysctl_tcp_rmem),
    .max_header        = MAX_TCP_HEADER,
    .obj_size        = sizeof(struct tcp_sock),
    .slab_flags        = SLAB_TYPESAFE_BY_RCU,
    .twsk_prot        = &tcp_timewait_sock_ops,
    .rsk_prot        = &tcp_request_sock_ops,
    .h.hashinfo        = &tcp_hashinfo,
    .no_autobind        = true,
#ifdef CONFIG_COMPAT
    .compat_setsockopt    = compat_tcp_setsockopt,
    .compat_getsockopt    = compat_tcp_getsockopt,
#endif
    .diag_destroy        = tcp_abort,
};
EXPORT_SYMBOL(tcp_prot);

b tcp_v4_connect
b inet_csk_accept
c

/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
    struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
    struct inet_sock *inet = inet_sk(sk);
    struct tcp_sock *tp = tcp_sk(sk);
    __be16 orig_sport, orig_dport;
    __be32 daddr, nexthop;
    struct flowi4 *fl4;
    struct rtable *rt;
    int err;
    struct ip_options_rcu *inet_opt;
    struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;

    if (addr_len < sizeof(struct sockaddr_in))
        return -EINVAL;

    if (usin->sin_family != AF_INET)
        return -EAFNOSUPPORT;

    nexthop = daddr = usin->sin_addr.s_addr;
    inet_opt = rcu_dereference_protected(inet->inet_opt,
                         lockdep_sock_is_held(sk));
    if (inet_opt && inet_opt->opt.srr) {
        if (!daddr)
            return -EINVAL;
        nexthop = inet_opt->opt.faddr;
    }

    orig_sport = inet->inet_sport;
    orig_dport = usin->sin_port;
    fl4 = &inet->cork.fl.u.ip4;
    rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
                  RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
                  IPPROTO_TCP,
                  orig_sport, orig_dport, sk);
    if (IS_ERR(rt)) {
        err = PTR_ERR(rt);
        if (err == -ENETUNREACH)
            IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
        return err;
    }

    if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
        ip_rt_put(rt);
        return -ENETUNREACH;
    }

    if (!inet_opt || !inet_opt->opt.srr)
        daddr = fl4->daddr;

    if (!inet->inet_saddr)
        inet->inet_saddr = fl4->saddr;
    sk_rcv_saddr_set(sk, inet->inet_saddr);

    if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
        /* Reset inherited state */
        tp->rx_opt.ts_recent       = 0;
        tp->rx_opt.ts_recent_stamp = 0;
        if (likely(!tp->repair))
            tp->write_seq       = 0;
    }

    inet->inet_dport = usin->sin_port;
    sk_daddr_set(sk, daddr);

    inet_csk(sk)->icsk_ext_hdr_len = 0;
    if (inet_opt)
        inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;

    tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;

    /* Socket identity is still unknown (sport may be zero).
     * However we set state to SYN-SENT and not releasing socket
     * lock select source port, enter ourselves into the hash tables and
     * complete initialization after this.
     */
    tcp_set_state(sk, TCP_SYN_SENT);
    err = inet_hash_connect(tcp_death_row, sk);
    if (err)
        goto failure;

    sk_set_txhash(sk);

    rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
                   inet->inet_sport, inet->inet_dport, sk);
    if (IS_ERR(rt)) {
        err = PTR_ERR(rt);
        rt = NULL;
        goto failure;
    }
    /* OK, now commit destination to socket.  */
    sk->sk_gso_type = SKB_GSO_TCPV4;
    sk_setup_caps(sk, &rt->dst);
    rt = NULL;

    if (likely(!tp->repair)) {
        if (!tp->write_seq)
            tp->write_seq = secure_tcp_seq(inet->inet_saddr,
                               inet->inet_daddr,
                               inet->inet_sport,
                               usin->sin_port);
        tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
                         inet->inet_saddr,
                         inet->inet_daddr);
    }

    inet->inet_id = tp->write_seq ^ jiffies;

    if (tcp_fastopen_defer_connect(sk, &err))
        return err;
    if (err)
        goto failure;

    err = tcp_connect(sk);

    if (err)
        goto failure;

    return 0;

failure:
    /*
     * This unhashes the socket and releases the local port,
     * if necessary.
     */
    tcp_set_state(sk, TCP_CLOSE);
    ip_rt_put(rt);
    sk->sk_route_caps = 0;
    inet->inet_dport = 0;
    return err;
}
EXPORT_SYMBOL(tcp_v4_connect);

int tcp_connect(struct sock *sk)
{
    struct tcp_sock *tp = tcp_sk(sk);
    struct sk_buff *buff;
    int err;

    tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);

    if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
        return -EHOSTUNREACH; /* Routing failure or similar. */

    tcp_connect_init(sk);

    if (unlikely(tp->repair)) {
        tcp_finish_connect(sk, NULL);
        return 0;
    }

    buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true);
    if (unlikely(!buff))
        return -ENOBUFS;

    tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
    tcp_mstamp_refresh(tp);
    tp->retrans_stamp = tcp_time_stamp(tp);
    tcp_connect_queue_skb(sk, buff);
    tcp_ecn_send_syn(sk, buff);
    tcp_rbtree_insert(&sk->tcp_rtx_queue, buff);

    /* Send off SYN; include data in Fast Open. */
    err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
          tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
    if (err == -ECONNREFUSED)
        return err;

    /* We change tp->snd_nxt after the tcp_transmit_skb() call
     * in order to make this packet get counted in tcpOutSegs.
     */
    tp->snd_nxt = tp->write_seq;
    tp->pushed_seq = tp->write_seq;
    buff = tcp_send_head(sk);
    if (unlikely(buff)) {
        tp->snd_nxt    = TCP_SKB_CB(buff)->seq;
        tp->pushed_seq    = TCP_SKB_CB(buff)->seq;
    }
    TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);

    /* Timer for repeating the SYN until an answer. */
    inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
                  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
    return 0;
}
EXPORT_SYMBOL(tcp_connect);

static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
                gfp_t gfp_mask)
{
    return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
                  tcp_sk(sk)->rcv_nxt);
}

struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
{
    struct inet_connection_sock *icsk = inet_csk(sk);
    struct request_sock_queue *queue = &icsk->icsk_accept_queue;
    struct request_sock *req;
    struct sock *newsk;
    int error;

    lock_sock(sk);

    /* We need to make sure that this socket is listening,
     * and that it has something pending.
     */
    error = -EINVAL;
    if (sk->sk_state != TCP_LISTEN)
        goto out_err;

    /* Find already established connection */
    if (reqsk_queue_empty(queue)) {
        long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);

        /* If this is a non blocking socket don‘t sleep */
        error = -EAGAIN;
        if (!timeo)
            goto out_err;

        error = inet_csk_wait_for_connect(sk, timeo);
        if (error)
            goto out_err;
    }
    req = reqsk_queue_remove(queue, sk);
    newsk = req->sk;

    if (sk->sk_protocol == IPPROTO_TCP &&
        tcp_rsk(req)->tfo_listener) {
        spin_lock_bh(&queue->fastopenq.lock);
        if (tcp_rsk(req)->tfo_listener) {
            /* We are still waiting for the final ACK from 3WHS
             * so can‘t free req now. Instead, we set req->sk to
             * NULL to signify that the child socket is taken
             * so reqsk_fastopen_remove() will free the req
             * when 3WHS finishes (or is aborted).
             */
            req->sk = NULL;
            req = NULL;
        }
        spin_unlock_bh(&queue->fastopenq.lock);
    }
out:
    release_sock(sk);
    if (req)
        reqsk_put(req);
    return newsk;
out_err:
    newsk = NULL;
    req = NULL;
    *err = error;
    goto out;
}
EXPORT_SYMBOL(inet_csk_accept);

/*
 * Wait for an incoming connection, avoid race conditions. This must be called
 * with the socket locked.
 */
static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
{
    struct inet_connection_sock *icsk = inet_csk(sk);
    DEFINE_WAIT(wait);
    int err;

    /*
     * True wake-one mechanism for incoming connections: only
     * one process gets woken up, not the ‘whole herd‘.
     * Since we do not ‘race & poll‘ for established sockets
     * anymore, the common case will execute the loop only once.
     *
     * Subtle issue: "add_wait_queue_exclusive()" will be added
     * after any current non-exclusive waiters, and we know that
     * it will always _stay_ after any new non-exclusive waiters
     * because all non-exclusive waiters are added at the
     * beginning of the wait-queue. As such, it‘s ok to "drop"
     * our exclusiveness temporarily when we get woken up without
     * having to remove and re-insert us on the wait queue.
     */
    for (;;) {
        prepare_to_wait_exclusive(sk_sleep(sk), &wait,
                      TASK_INTERRUPTIBLE);
        release_sock(sk);
        if (reqsk_queue_empty(&icsk->icsk_accept_queue))
            timeo = schedule_timeout(timeo);
        sched_annotate_sleep();
        lock_sock(sk);
        err = 0;
        if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
            break;
        err = -EINVAL;
        if (sk->sk_state != TCP_LISTEN)
            break;
        err = sock_intr_errno(timeo);
        if (signal_pending(current))
            break;
        err = -EAGAIN;
        if (!timeo)
            break;
    }
    finish_wait(sk_sleep(sk), &wait);
    return err;
}