深入理解TCP协议及其源代码——send和recv背后数据的收发过程

TCP数据发送和接收的原理

TCP连接的建立过程

深入理解TCP协议及其源代码——send和recv背后数据的收发过程_第1张图片

TCP Socket的连接的过程是服务端先通过socket()函数创建一个socket对象,生成一个socket文件描述符,然后通过bind()函数将生成的socket绑定到要监听的地址和端口上面。绑定好了之后,使用listen()函数来监听相应的端口。而客户端是在通过socket()函数创建一个socket对象之后,通过connect()函数向被服务端监听的socket发起一个连接请求,即发起一次TCP连接的三次握手。接下来就可以就可以通过TCP连接收发数据了。

Socket中send()recv()

为了实现数据的收发,每个TCP socket在内核中都维护了一个发送缓冲区和一个接收缓冲区,send()函数把应用缓冲区中的数据拷贝到TCP发送缓冲区中,接下来的发送过程由TCP负责;recv()函数是将TCP接收缓冲区中的数据拷贝到应用缓冲区中。在socket中,send()recv()只管拷贝,真正的发送和接收是由TCP连接负责的。接下来我们看看TCP连接是如何实现数据收发的。

TCP连接中的数据收发

追踪socket中的__sys_sendto__sys_recvfrom函数

实验环境的准备参考构建调试Linux内核网络代码的环境MenuOS系统

$ cd ~/linuxnet/lab3
$ make rootfs
#保持当前终端和Qemu运行,重新打开一个终端,运行gdb
$ gdb
(gdb)file ~/linux-5.0.1/vmlinux
(gdb)target remote:1234
(gdb)b __sys_sendto
(gdb)b __sys_recvfrom
(gdb)c
MenuOS>>replyhi#在MenuOS中执行
MenuOS>>hello#在MenuOS中执行
(gdb)info b# 设置好的断点信息如下
(gdb) info b
Num     Type           Disp Enb Address            What
1       breakpoint     keep y   0xffffffff817ba370 in __sys_sendto at net/socket.c:1758
2       breakpoint     keep y   0xffffffff817ba540 in __sys_recvfrom at net/socket.c:1819

我们先给socket中的__sys_sendto__sys_recvfrom打上断点,执行一次replyhi/hello命令观察一下断点的情况:
深入理解TCP协议及其源代码——send和recv背后数据的收发过程_第2张图片

此处客户端给服务端发送了字符串"hello",而服务端回复了"hi",__sys_sendto()__sys_recvfrom()函数的参数值如下:

Breakpoint 2, __sys_recvfrom (fd=5, ubuf=0xffb668ec, size=1024, flags=2147483648, addr=0x0 , 
    addr_len=0x0 ) at net/socket.c:1819
1819    {
(gdb) x/5c ubuf////第一次截到__sys_recvfrom函数时,从缓冲区中看到已经收到了字符串"hello"
0xffb668ec: 104 'h' 101 'e' 108 'l' 108 'l' 111 'o'
(gdb) c
Continuing.

Breakpoint 1, __sys_sendto (fd=4, buff=0xffb66d0c, len=5, flags=0, addr=0x0 , addr_len=0)
    at net/socket.c:1758
1758    {
(gdb) x/5c buff//这时,截到了发送hello的__sys_sendto函数
0xffb66d0c: 104 'h' 101 'e' 108 'l' 108 'l' 111 'o'
(gdb) c
Continuing.

Breakpoint 2, __sys_recvfrom (fd=4, ubuf=0xffb6690c, size=1024, flags=2147483648, addr=0x0 , 
    addr_len=0x0 ) at net/socket.c:1819
1819    {
(gdb) x/5c ubuf//此时该函数尚未接收到字符串
0xffb6690c: 0 '\000'    0 '\000'    0 '\000'    0 '\000'    0 '\000'
(gdb) c
Continuing.

Breakpoint 1, __sys_sendto (fd=5, buff=0xffb66cec, len=2, flags=0, addr=0x0 , addr_len=0)
    at net/socket.c:1758
1758    {
(gdb) x/5c buff//从缓冲区看出已经发送了hello
0xffb66cec: 104 'h' 105 'i' 0 '\000'    0 '\000'    0 '\000'
 

追踪缓冲区

可以看到,socket中的__sys_sendto__sys_recvfrom函数的缓冲区分别是buff和ubuf指向的内存空间,我们从源码中看一看这两个缓冲区中的数据是如何被处理的。

在~/linux-5.0.1/net/socket.c中找到对应的源码:

int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
         struct sockaddr __user *addr,  int addr_len)
{
    struct socket *sock;
    struct sockaddr_storage address;
    int err;
    struct msghdr msg;
    struct iovec iov;
    int fput_needed;

    err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter);
    if (unlikely(err))
        return err;
    sock = sockfd_lookup_light(fd, &err, &fput_needed);
    if (!sock)
        goto out;

    msg.msg_name = NULL;
    msg.msg_control = NULL;
    msg.msg_controllen = 0;
    msg.msg_namelen = 0;
    if (addr) {
        err = move_addr_to_kernel(addr, addr_len, &address);
        if (err < 0)
            goto out_put;
        msg.msg_name = (struct sockaddr *)&address;
        msg.msg_namelen = addr_len;
    }
    if (sock->file->f_flags & O_NONBLOCK)
        flags |= MSG_DONTWAIT;
    msg.msg_flags = flags;
    err = sock_sendmsg(sock, &msg);

out_put:
    fput_light(sock->file, fput_needed);
out:
    return err;
}


int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
           struct sockaddr __user *addr, int __user *addr_len)
{
    struct socket *sock;
    struct iovec iov;
    struct msghdr msg;
    struct sockaddr_storage address;
    int err, err2;
    int fput_needed;

    err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter);
    if (unlikely(err))
        return err;
    sock = sockfd_lookup_light(fd, &err, &fput_needed);
    if (!sock)
        goto out;

    msg.msg_control = NULL;
    msg.msg_controllen = 0;
    /* Save some cycles and don't copy the address if not needed */
    msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
    /* We assume all kernel code knows the size of sockaddr_storage */
    msg.msg_namelen = 0;
    msg.msg_iocb = NULL;
    msg.msg_flags = 0;
    if (sock->file->f_flags & O_NONBLOCK)
        flags |= MSG_DONTWAIT;
    err = sock_recvmsg(sock, &msg, flags);

    if (err >= 0 && addr != NULL) {
        err2 = move_addr_to_user(&address,
                     msg.msg_namelen, addr, addr_len);
        if (err2 < 0)
            err = err2;
    }

    fput_light(sock->file, fput_needed);
out:
    return err;
}

可以看到,buff和ubuf分别被传入err后传给了sock_recvmsgsock_sendmsg函数,接下来看查看这两个函数的源码:

int sock_sendmsg(struct socket *sock, struct msghdr *msg)
{
    int err = security_socket_sendmsg(sock, msg,
                      msg_data_left(msg));

    return err ?: sock_sendmsg_nosec(sock, msg);
}
EXPORT_SYMBOL(sock_sendmsg);


int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags)
{
    int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags);

    return err ?: sock_recvmsg_nosec(sock, msg, flags);
}
EXPORT_SYMBOL(sock_recvmsg);

在源码中已经难以分析出函数的调用关系了,不妨运行时一路追踪下去,看看什么时候能调用到tcp协议相关的函数:
深入理解TCP协议及其源代码——send和recv背后数据的收发过程_第3张图片

终于找到了send()对应的tcp中的函数,发现该源码在net/ipv4/tcp.c:1439:

int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
    int ret;

    lock_sock(sk);
    ret = tcp_sendmsg_locked(sk, msg, size);
    release_sock(sk);

    return ret;
}
EXPORT_SYMBOL(tcp_sendmsg);

继续追查tcp_sendmsg_locked函数:

int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
{
    struct tcp_sock *tp = tcp_sk(sk);
    struct ubuf_info *uarg = NULL;
    struct sk_buff *skb;
    struct sockcm_cookie sockc;
    int flags, err, copied = 0;
    int mss_now = 0, size_goal, copied_syn = 0;
    bool process_backlog = false;
    bool zc = false;
    long timeo;

    flags = msg->msg_flags;

    if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
        if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
            err = -EINVAL;
            goto out_err;
        }

        skb = tcp_write_queue_tail(sk);
        uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb));
        if (!uarg) {
            err = -ENOBUFS;
            goto out_err;
        }

        zc = sk->sk_route_caps & NETIF_F_SG;
        if (!zc)
            uarg->zerocopy = 0;
    }

    if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
        !tp->repair) {
        err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
        if (err == -EINPROGRESS && copied_syn > 0)
            goto out;
        else if (err)
            goto out_err;
    }

    timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

    tcp_rate_check_app_limited(sk);  /* is sending application-limited? */

    /* Wait for a connection to finish. One exception is TCP Fast Open
     * (passive side) where data is allowed to be sent before a connection
     * is fully established.
     */
    if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
        !tcp_passive_fastopen(sk)) {
        err = sk_stream_wait_connect(sk, &timeo);
        if (err != 0)
            goto do_error;
    }

    if (unlikely(tp->repair)) {
        if (tp->repair_queue == TCP_RECV_QUEUE) {
            copied = tcp_send_rcvq(sk, msg, size);
            goto out_nopush;
        }

        err = -EINVAL;
        if (tp->repair_queue == TCP_NO_QUEUE)
            goto out_err;

        /* 'common' sending to sendq */
    }

    sockcm_init(&sockc, sk);
    if (msg->msg_controllen) {
        err = sock_cmsg_send(sk, msg, &sockc);
        if (unlikely(err)) {
            err = -EINVAL;
            goto out_err;
        }
    }

    /* This should be in poll */
    sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);

    /* Ok commence sending. */
    copied = 0;

restart:
    mss_now = tcp_send_mss(sk, &size_goal, flags);

    err = -EPIPE;
    if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
        goto do_error;

    while (msg_data_left(msg)) {
        int copy = 0;

        skb = tcp_write_queue_tail(sk);
        if (skb)
            copy = size_goal - skb->len;

        if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
            bool first_skb;
            int linear;

new_segment:
            if (!sk_stream_memory_free(sk))
                goto wait_for_sndbuf;

            if (process_backlog && sk_flush_backlog(sk)) {
                process_backlog = false;
                goto restart;
            }
            first_skb = tcp_rtx_and_write_queues_empty(sk);
            linear = select_size(first_skb, zc);
            skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation,
                          first_skb);
            if (!skb)
                goto wait_for_memory;

            process_backlog = true;
            skb->ip_summed = CHECKSUM_PARTIAL;

            skb_entail(sk, skb);
            copy = size_goal;

            /* All packets are restored as if they have
             * already been sent. skb_mstamp_ns isn't set to
             * avoid wrong rtt estimation.
             */
            if (tp->repair)
                TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
        }

        /* Try to append data to the end of skb. */
        if (copy > msg_data_left(msg))
            copy = msg_data_left(msg);

        /* Where to copy to? */
        if (skb_availroom(skb) > 0 && !zc) {
            /* We have some space in skb head. Superb! */
            copy = min_t(int, copy, skb_availroom(skb));
            err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
            if (err)
                goto do_fault;
        } else if (!zc) {
            bool merge = true;
            int i = skb_shinfo(skb)->nr_frags;
            struct page_frag *pfrag = sk_page_frag(sk);

            if (!sk_page_frag_refill(sk, pfrag))
                goto wait_for_memory;

            if (!skb_can_coalesce(skb, i, pfrag->page,
                          pfrag->offset)) {
                if (i >= sysctl_max_skb_frags) {
                    tcp_mark_push(tp, skb);
                    goto new_segment;
                }
                merge = false;
            }

            copy = min_t(int, copy, pfrag->size - pfrag->offset);

            if (!sk_wmem_schedule(sk, copy))
                goto wait_for_memory;

            err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
                               pfrag->page,
                               pfrag->offset,
                               copy);
            if (err)
                goto do_error;

            /* Update the skb. */
            if (merge) {
                skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
            } else {
                skb_fill_page_desc(skb, i, pfrag->page,
                           pfrag->offset, copy);
                page_ref_inc(pfrag->page);
            }
            pfrag->offset += copy;
        } else {
            err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
            if (err == -EMSGSIZE || err == -EEXIST) {
                tcp_mark_push(tp, skb);
                goto new_segment;
            }
            if (err < 0)
                goto do_error;
            copy = err;
        }

        if (!copied)
            TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;

        tp->write_seq += copy;
        TCP_SKB_CB(skb)->end_seq += copy;
        tcp_skb_pcount_set(skb, 0);

        copied += copy;
        if (!msg_data_left(msg)) {
            if (unlikely(flags & MSG_EOR))
                TCP_SKB_CB(skb)->eor = 1;
            goto out;
        }

        if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair))
            continue;

        if (forced_push(tp)) {
            tcp_mark_push(tp, skb);
            __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
        } else if (skb == tcp_send_head(sk))
            tcp_push_one(sk, mss_now);
        continue;

wait_for_sndbuf:
        set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
        if (copied)
            tcp_push(sk, flags & ~MSG_MORE, mss_now,
                 TCP_NAGLE_PUSH, size_goal);

        err = sk_stream_wait_memory(sk, &timeo);
        if (err != 0)
            goto do_error;

        mss_now = tcp_send_mss(sk, &size_goal, flags);
    }

out:
    if (copied) {
        tcp_tx_timestamp(sk, sockc.tsflags);
        tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
    }
out_nopush:
    sock_zerocopy_put(uarg);
    return copied + copied_syn;

do_fault:
    if (!skb->len) {
        tcp_unlink_write_queue(skb, sk);
        /* It is the one place in all of TCP, except connection
         * reset, where we can be unlinking the send_head.
         */
        tcp_check_send_head(sk, skb);
        sk_wmem_free_skb(sk, skb);
    }

do_error:
    if (copied + copied_syn)
        goto out;
out_err:
    sock_zerocopy_put_abort(uarg, true);
    err = sk_stream_error(sk, flags, err);
    /* make sure we wake any epoll edge trigger waiter */
    if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
             err == -EAGAIN)) {
        sk->sk_write_space(sk);
        tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
    }
    return err;
}
EXPORT_SYMBOL_GPL(tcp_sendmsg_locked);

在同一个文件中,还能找到tcp_recvmsg函数:

int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
        int flags, int *addr_len)
{
    struct tcp_sock *tp = tcp_sk(sk);
    int copied = 0;
    u32 peek_seq;
    u32 *seq;
    unsigned long used;
    int err, inq;
    int target;     /* Read at least this many bytes */
    long timeo;
    struct sk_buff *skb, *last;
    u32 urg_hole = 0;
    struct scm_timestamping tss;
    bool has_tss = false;
    bool has_cmsg;

    if (unlikely(flags & MSG_ERRQUEUE))
        return inet_recv_error(sk, msg, len, addr_len);

    if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
        (sk->sk_state == TCP_ESTABLISHED))
        sk_busy_loop(sk, nonblock);

    lock_sock(sk);

    err = -ENOTCONN;
    if (sk->sk_state == TCP_LISTEN)
        goto out;

    has_cmsg = tp->recvmsg_inq;
    timeo = sock_rcvtimeo(sk, nonblock);

    /* Urgent data needs to be handled specially. */
    if (flags & MSG_OOB)
        goto recv_urg;

    if (unlikely(tp->repair)) {
        err = -EPERM;
        if (!(flags & MSG_PEEK))
            goto out;

        if (tp->repair_queue == TCP_SEND_QUEUE)
            goto recv_sndq;

        err = -EINVAL;
        if (tp->repair_queue == TCP_NO_QUEUE)
            goto out;

        /* 'common' recv queue MSG_PEEK-ing */
    }

    seq = &tp->copied_seq;
    if (flags & MSG_PEEK) {
        peek_seq = tp->copied_seq;
        seq = &peek_seq;
    }

    target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

    do {
        u32 offset;

        /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
        if (tp->urg_data && tp->urg_seq == *seq) {
            if (copied)
                break;
            if (signal_pending(current)) {
                copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
                break;
            }
        }

        /* Next get a buffer. */

        last = skb_peek_tail(&sk->sk_receive_queue);
        skb_queue_walk(&sk->sk_receive_queue, skb) {
            last = skb;
            /* Now that we have two receive queues this
             * shouldn't happen.
             */
            if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
                 "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
                 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
                 flags))
                break;

            offset = *seq - TCP_SKB_CB(skb)->seq;
            if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
                pr_err_once("%s: found a SYN, please report !\n", __func__);
                offset--;
            }
            if (offset < skb->len)
                goto found_ok_skb;
            if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
                goto found_fin_ok;
            WARN(!(flags & MSG_PEEK),
                 "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
                 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
        }

        /* Well, if we have backlog, try to process it now yet. */

        if (copied >= target && !sk->sk_backlog.tail)
            break;

        if (copied) {
            if (sk->sk_err ||
                sk->sk_state == TCP_CLOSE ||
                (sk->sk_shutdown & RCV_SHUTDOWN) ||
                !timeo ||
                signal_pending(current))
                break;
        } else {
            if (sock_flag(sk, SOCK_DONE))
                break;

            if (sk->sk_err) {
                copied = sock_error(sk);
                break;
            }

            if (sk->sk_shutdown & RCV_SHUTDOWN)
                break;

            if (sk->sk_state == TCP_CLOSE) {
                /* This occurs when user tries to read
                 * from never connected socket.
                 */
                copied = -ENOTCONN;
                break;
            }

            if (!timeo) {
                copied = -EAGAIN;
                break;
            }

            if (signal_pending(current)) {
                copied = sock_intr_errno(timeo);
                break;
            }
        }

        tcp_cleanup_rbuf(sk, copied);

        if (copied >= target) {
            /* Do not sleep, just process backlog. */
            release_sock(sk);
            lock_sock(sk);
        } else {
            sk_wait_data(sk, &timeo, last);
        }

        if ((flags & MSG_PEEK) &&
            (peek_seq - copied - urg_hole != tp->copied_seq)) {
            net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
                        current->comm,
                        task_pid_nr(current));
            peek_seq = tp->copied_seq;
        }
        continue;

found_ok_skb:
        /* Ok so how much can we use? */
        used = skb->len - offset;
        if (len < used)
            used = len;

        /* Do we have urgent data here? */
        if (tp->urg_data) {
            u32 urg_offset = tp->urg_seq - *seq;
            if (urg_offset < used) {
                if (!urg_offset) {
                    if (!sock_flag(sk, SOCK_URGINLINE)) {
                        ++*seq;
                        urg_hole++;
                        offset++;
                        used--;
                        if (!used)
                            goto skip_copy;
                    }
                } else
                    used = urg_offset;
            }
        }

        if (!(flags & MSG_TRUNC)) {
            err = skb_copy_datagram_msg(skb, offset, msg, used);
            if (err) {
                /* Exception. Bailout! */
                if (!copied)
                    copied = -EFAULT;
                break;
            }
        }

        *seq += used;
        copied += used;
        len -= used;

        tcp_rcv_space_adjust(sk);

skip_copy:
        if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
            tp->urg_data = 0;
            tcp_fast_path_check(sk);
        }
        if (used + offset < skb->len)
            continue;

        if (TCP_SKB_CB(skb)->has_rxtstamp) {
            tcp_update_recv_tstamps(skb, &tss);
            has_tss = true;
            has_cmsg = true;
        }
        if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
            goto found_fin_ok;
        if (!(flags & MSG_PEEK))
            sk_eat_skb(sk, skb);
        continue;

found_fin_ok:
        /* Process the FIN. */
        ++*seq;
        if (!(flags & MSG_PEEK))
            sk_eat_skb(sk, skb);
        break;
    } while (len > 0);

    /* According to UNIX98, msg_name/msg_namelen are ignored
     * on connected socket. I was just happy when found this 8) --ANK
     */

    /* Clean up data we have read: This will do ACK frames. */
    tcp_cleanup_rbuf(sk, copied);

    release_sock(sk);

    if (has_cmsg) {
        if (has_tss)
            tcp_recv_timestamp(msg, sk, &tss);
        if (tp->recvmsg_inq) {
            inq = tcp_inq_hint(sk);
            put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
        }
    }

    return copied;

out:
    release_sock(sk);
    return err;

recv_urg:
    err = tcp_recv_urg(sk, msg, len, flags);
    goto out;

recv_sndq:
    err = tcp_peek_sndq(sk, msg, len);
    goto out;
}
EXPORT_SYMBOL(tcp_recvmsg);

可以看到,这两个函数相当复杂。在socket系统调用中调用了__sys_send()__sys_recv后,实际调用的tcp协议中的函数正是tcp_sendmsgtcp_recvmsg函数,下面给这两个函数打上断点,在Meno OS中验证一下:
深入理解TCP协议及其源代码——send和recv背后数据的收发过程_第4张图片
深入理解TCP协议及其源代码——send和recv背后数据的收发过程_第5张图片

Breakpoint 2, __sys_recvfrom (fd=5, ubuf=0xffb668ec, size=1024, flags=2147483648, addr=0x0 , 
    addr_len=0x0 ) at net/socket.c:1819
1819    {
(gdb) c
Continuing.

Breakpoint 6, tcp_recvmsg (sk=0xffff888006558880, msg=0xffffc900008b7dc0, len=1024, nonblock=0, flags=-2147483648, 
    addr_len=0xffffc900008b7d8c) at net/ipv4/tcp.c:1930
1930    {
(gdb) c
Continuing.

Breakpoint 1, __sys_sendto (fd=4, buff=0xffb66d0c, len=5, flags=0, addr=0x0 , addr_len=0)
    at net/socket.c:1758
1758    {
(gdb) c
Continuing.
fdget (fd=) at ./include/linux/file.h:60
60      return __to_fd(__fdget(fd));
(gdb) c
Continuing.

Breakpoint 7, tcp_sendmsg (sk=0xffff888006559100, msg=0xffffc90000043dc0, size=5) at net/ipv4/tcp.c:1439
1439    {
(gdb) c
Continuing.

Breakpoint 1, __sys_sendto (fd=5, buff=0xffb66cec, len=2, flags=0, addr=0x0 , addr_len=0)
    at net/socket.c:1758
1758    {
(gdb) c
Continuing.

Breakpoint 7, tcp_sendmsg (sk=0xffff888006558880, msg=0xffffc900008b7dc0, size=2) at net/ipv4/tcp.c:1439
1439    {
(gdb) c
Continuing.

Breakpoint 2, __sys_recvfrom (fd=4, ubuf=0xffb6690c, size=1024, flags=2147483648, addr=0x0 , 
    addr_len=0x0 ) at net/socket.c:1819
1819    {
(gdb) c
Continuing.
fdget (fd=) at ./include/linux/file.h:60
60      return __to_fd(__fdget(fd));
(gdb) c
Continuing.

Breakpoint 6, tcp_recvmsg (sk=0xffff888006559100, msg=0xffffc90000043dc0, len=1024, nonblock=0, flags=-2147483648, 
    addr_len=0xffffc90000043d8c) at net/ipv4/tcp.c:1930
1930    {
(gdb) c
Continuing.

Breakpoint 5, __sys_accept4 (fd=4, upeer_sockaddr=0xffb668dc, upeer_addrlen=0xffb668bc, flags=0) at net/socket.c:1542
1542    {
(gdb) c
Continuing.
(gdb) 

可以看到,__sys_send()__sys_recv每一次运行后,tcp_sendmsgtcp_recvmsg都被调用一次,验证了我们的结论。

参考资料

https://www.cnblogs.com/f-ck-need-u/p/7623252.html#2-5-send-recv-
https://github.com/mengning/net

你可能感兴趣的:(深入理解TCP协议及其源代码——send和recv背后数据的收发过程)