码迷,mamicode.com
首页 > 其他好文 > 详细

深入理解TCP协议及其源代码-send和recv背后数据的收发过程

时间:2019-12-26 19:34:06      阅读:75      评论:0      收藏:0      [点我收藏+]

标签:RoCE   ndt   数据段   字节   就是   target   linux   协议栈   imp   

send和recv背后数据的收发过程

send和recv是TCP常用的发送数据和接受数据函数,这两个函数具体在linux内核的代码实现上是如何实现的呢?
ssize_t recv(int sockfd, void buf, size_t len, int flags)
ssize_t send(int sockfd, const void
buf, size_t len, int flags)

理论分析

对于send函数,比较容易理解,捋一下计算机网络的知识,可以大概的到实现的方法,首先TCP是面向连接的,会有三次握手,建立连接成功,即代表两个进程可以用send和recv通信,作为发送信息的一方,肯定是接收到了从用户程序发送数据的请求,即send函数的参数之一,接收到数据后,若数据的大小超过一定长度,肯定不可能直接发送除去,因此,首先要对数据分段,将数据分成一个个的代码段,其次,TCP协议位于传输层,有响应的头部字段,在传输时肯定要加在数据前,数据也就被准备好了。当然,TCP是没有能力直接通过物理链路发送出去的,要想数据正确传输,还需要一层一层的进行。所以,最后一步是将数据传递给网络层,网络层再封装,然后链路层、物理层,最后被发送除去。总结一下就是:
1.数据分段
2.封装头部
3.传递给下一层。

对于secv函数,有一个不太能理解的就是,作为接收方,我是否是一直在等待其他进程给我发送数据,如果是,那么就应该是不停的判断是否有数到了,如果有,就把数据保存起来,然后执行send的逆过程即可。若没有一直等,那就可能是进程被挂起了,如果有数据到达,内核通过中断唤醒进程,然后接收数据。至于具体是哪种,可以通过代码和调试得到结果。

源码分析

首先,当调用send()函数时,内核封装send()为sendto(),然后发起系统调用。其实也很好理解,send()就是sendto()的一种特殊情况,而sendto()在内核的系统调用服务程序为sys_sendto

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;
}

这里定义了一个struct msghdr msg,他是用来表示要发送的数据的一些属性。

struct msghdr {
    void        *msg_name;  /* 接收方的struct sockaddr结构体地址 (用于udp)*/
    int     msg_namelen;    /*  接收方的struct sockaddr结构体地址(用于udp)*/
    struct iov_iter msg_iter;   /* io缓冲区的地址 */
    void        *msg_control;   /* 辅助数据的地址 */
    __kernel_size_t msg_controllen; /* 辅助数据的长度 */
    unsigned int    msg_flags;  /*接受消息的表示 */
    struct kiocb    *msg_iocb;  /* ptr to iocb for async requests */
};

还有一个struct iovec,他被称为io向量,故名思意,用来表示io数据的一些信息。

struct iovec
{
    void __user *iov_base;  /* 要传输数据的用户态下的地址*) */
    __kernel_size_t iov_len; /*要传输数据的长度 */
};

所以,__sys_sendto函数其实做了3件事:1.通过fd获取了对应的struct socket2.创建了用来描述要发送的数据的结构体struct msghdr。3.调用了sock_sendmsg来执行实际的发送。继续追踪这个函数,会看到最终调用的是sock->ops->sendmsg(sock, msg, msg_data_left(msg));,即socet在初始化时赋值给结构体struct proto tcp_prot的函数tcp_sendmsg

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,
    ......

tcp_sendmsg实际上调用的是int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)

int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
{
    struct tcp_sock *tp = tcp_sk(sk);/*进行了强制类型转换*/
    struct sk_buff *skb;
    flags = msg->msg_flags;
    ......
        if (copied)
            tcp_push(sk, flags & ~MSG_MORE, mss_now,
                 TCP_NAGLE_PUSH, size_goal);
}

tcp_sendmsg_locked中,完成的是将所有的数据组织成发送队列,这个发送队列是struct sock结构中的一个域sk_write_queue,这个队列的每一个元素是一个skb,里面存放的就是待发送的数据。然后调用了tcp_push()函数。

struct sock{
    ...
    struct sk_buff_head sk_write_queue;/*指向skb队列的第一个元素*/
    ...
    struct sk_buff  *sk_send_head;/*指向队列第一个还没有发送的元素*/
}

在tcp协议的头部有几个标志字段:URG、ACK、RSH、RST、SYN、FIN,tcp_push中会判断这个skb的元素是否需要push,如果需要就将tcp头部字段的push置一,置一的过程如下:

static void tcp_push(struct sock *sk, int flags, int mss_now,
             int nonagle, int size_goal)
{
    struct tcp_sock *tp = tcp_sk(sk);
    struct sk_buff *skb;

    skb = tcp_write_queue_tail(sk);
    if (!skb)
        return;
    if (!(flags & MSG_MORE) || forced_push(tp))
        tcp_mark_push(tp, skb);

    tcp_mark_urg(tp, flags);

    if (tcp_should_autocork(sk, skb, size_goal)) {

        /* avoid atomic op if TSQ_THROTTLED bit is already set */
        if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
            NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
            set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
        }
        /* It is possible TX completion already happened
         * before we set TSQ_THROTTLED.
         */
        if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize)
            return;
    }

    if (flags & MSG_MORE)
        nonagle = TCP_NAGLE_CORK;

    __tcp_push_pending_frames(sk, mss_now, nonagle);
}

整个过程会有点绕,首先struct tcp_skb_cb结构体存放的就是tcp的头部,头部的控制位为tcp_flags,通过tcp_mark_push会将skb中的cb,也就是48个字节的数组,类型转换为struct tcp_skb_cb,这样位于skb的cb就成了tcp的头部。

static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
    TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
    tp->pushed_seq = tp->write_seq;
}

...
#define TCP_SKB_CB(__skb)   ((struct tcp_skb_cb *)&((__skb)->cb[0]))
...

struct sk_buff {
    ... 
    char            cb[48] __aligned(8);
    ...
struct tcp_skb_cb {
    __u32       seq;        /* Starting sequence number */
    __u32       end_seq;    /* SEQ + FIN + SYN + datalen    */
    __u8        tcp_flags;  /* tcp头部标志,位于第13个字节tcp[13]) */
    ......
};

然后,tcp_push调用了__tcp_push_pending_frames(sk, mss_now, nonagle);函数发送数据:

void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
                   int nonagle)
{

    if (tcp_write_xmit(sk, cur_mss, nonagle, 0,
               sk_gfp_mask(sk, GFP_ATOMIC)))
        tcp_check_probe_timer(sk);
}

随后又调用了tcp_write_xmit来发送数据:

static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
               int push_one, gfp_t gfp)
{
    struct tcp_sock *tp = tcp_sk(sk);
    struct sk_buff *skb;
    unsigned int tso_segs, sent_pkts;
    int cwnd_quota;
    int result;
    bool is_cwnd_limited = false, is_rwnd_limited = false;
    u32 max_segs;
    /*统计已发送的报文总数*/
    sent_pkts = 0;
    ......

    /*若发送队列未满,则准备发送报文*/
    while ((skb = tcp_send_head(sk))) {
        unsigned int limit;

        if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
            /* "skb_mstamp_ns" is used as a start point for the retransmit timer */
            skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
            list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
            tcp_init_tso_segs(skb, mss_now);
            goto repair; /* Skip network transmission */
        }

        if (tcp_pacing_check(sk))
            break;

        tso_segs = tcp_init_tso_segs(skb, mss_now);
        BUG_ON(!tso_segs);
        /*检查发送窗口的大小*/
        cwnd_quota = tcp_cwnd_test(tp, skb);
        if (!cwnd_quota) {
            if (push_one == 2)
                /* Force out a loss probe pkt. */
                cwnd_quota = 1;
            else
                break;
        }

        if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) {
            is_rwnd_limited = true;
            break;
        ......
        limit = mss_now;
        if (tso_segs > 1 && !tcp_urg_mode(tp))
            limit = tcp_mss_split_point(sk, skb, mss_now,
                            min_t(unsigned int,
                              cwnd_quota,
                              max_segs),
                            nonagle);

        if (skb->len > limit &&
            unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
                      skb, limit, mss_now, gfp)))
            break;

        if (tcp_small_queue_check(sk, skb, 0))
            break;

        if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
            break;
    ......

tcp_write_xmit位于tcpoutput.c中,它实现了tcp的拥塞控制,然后调用了tcp_transmit_skb(sk, skb, 1, gfp)传输数据,实际上调用的是__tcp_transmit_skb

static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
                  int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
    
    skb_push(skb, tcp_header_size);
    skb_reset_transport_header(skb);
    ......
    /* 构建TCP头部和校验和 */
    th = (struct tcphdr *)skb->data;
    th->source      = inet->inet_sport;
    th->dest        = inet->inet_dport;
    th->seq         = htonl(tcb->seq);
    th->ack_seq     = htonl(rcv_nxt);

    tcp_options_write((__be32 *)(th + 1), tp, &opts);
    skb_shinfo(skb)->gso_type = sk->sk_gso_type;
    if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) {
        th->window      = htons(tcp_select_window(sk));
        tcp_ecn_send(sk, skb, th, tcp_header_size);
    } else {
        /* RFC1323: The window in SYN & SYN/ACK segments
         * is never scaled.
         */
        th->window  = htons(min(tp->rcv_wnd, 65535U));
    }
    ......
    icsk->icsk_af_ops->send_check(sk, skb);

    if (likely(tcb->tcp_flags & TCPHDR_ACK))
        tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);

    if (skb->len != tcp_header_size) {
        tcp_event_data_sent(tp, sk);
        tp->data_segs_out += tcp_skb_pcount(skb);
        tp->bytes_sent += skb->len - tcp_header_size;
    }

    if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
        TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
                  tcp_skb_pcount(skb));

    tp->segs_out += tcp_skb_pcount(skb);
    /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */
    skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
    skb_shinfo(skb)->gso_size = tcp_skb_mss(skb);

    /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */

    /* Cleanup our debris for IP stacks */
    memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
                   sizeof(struct inet6_skb_parm)));

    err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
    ......
}

tcp_transmit_skb是tcp发送数据位于传输层的最后一步,这里首先对TCP数据段的头部进行了处理,然后调用了网络层提供的发送接口icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);实现了数据的发送,自此,数据离开了传输层,传输层的任务也就结束了。

对于recv函数,与send类似,自然也是recvfrom的特殊情况,调用的也就是__sys_recvfrom,整个函数的调用路径与send非常类似:

int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
           struct sockaddr __user *addr, int __user *addr_len)
{
    ......
    err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter);
    if (unlikely(err))
        return err;
    sock = sockfd_lookup_light(fd, &err, &fput_needed);
    .....
    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);
    .....
}

__sys_recvfrom调用了sock_recvmsg来接收数据,整个函数实际调用的是sock->ops->recvmsg(sock, msg, msg_data_left(msg), flags);,同样,根据tcp_prot结构的初始化,调用的其实是tcp_rcvmsg
.接受函数比发送函数要复杂得多,因为数据接收不仅仅只是接收,tcp的三次握手也是在接收函数实现的,所以收到数据后要判断当前的状态,是否正在建立连接等,根据发来的信息考虑状态是否要改变,在这里,我们仅仅考虑在连接建立后数据的接收。

int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
        int flags, int *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);
    .....
        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;
    ......
        last = skb_peek_tail(&sk->sk_receive_queue);
        skb_queue_walk(&sk->sk_receive_queue, skb) {
            last = skb;
    ......
            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);
    

这里共维护了三个队列:prequeuebacklogreceive_queue,分别为预处理队列,后备队列和接收队列,在连接建立后,若没有数据到来,接收队列为空,进程会在sk_busy_loop函数内循环等待,知道接收队列不为空,并调用函数数skb_copy_datagram_msg将接收到的数据拷贝到用户态,实际调用的是__skb_datagram_iter,这里同样用了struct msghdr *msg来实现。

int __skb_datagram_iter(const struct sk_buff *skb, int offset,
            struct iov_iter *to, int len, bool fault_short,
            size_t (*cb)(const void *, size_t, void *, struct iov_iter *),
            void *data)
{
    int start = skb_headlen(skb);
    int i, copy = start - offset, start_off = offset, n;
    struct sk_buff *frag_iter;

    /* 拷贝tcp头部 */
    if (copy > 0) {
        if (copy > len)
            copy = len;
        n = cb(skb->data + offset, copy, data, to);
        offset += n;
        if (n != copy)
            goto short_copy;
        if ((len -= copy) == 0)
            return 0;
    }

    /* 拷贝数据部分 */
    for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
        int end;
        const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

        WARN_ON(start > offset + len);

        end = start + skb_frag_size(frag);
        if ((copy = end - offset) > 0) {
            struct page *page = skb_frag_page(frag);
            u8 *vaddr = kmap(page);

            if (copy > len)
                copy = len;
            n = cb(vaddr + frag->page_offset +
                offset - start, copy, data, to);
            kunmap(page);
            offset += n;
            if (n != copy)
                goto short_copy;
            if (!(len -= copy))
                return 0;
        }
        start = end;
    }

拷贝完成后,函数返回,整个接收的过程也就完成了。
整体来讲与我们的分析并不大,用一张函数间的相互调用图可以表示
技术图片

gdb调试分析

接下来用gdb调试验证上面的分析,调试环境为linux5.0.1+menuos(64位),测试程序为hello/hi网络聊天程序,将其植入到menuos,命令为client。
首先看send的调用关系,分别将断点打在__sys_sendtotcp_sendmsg_lockedtcp_push__tcp_push_pending_framestcp_write_xmit__tcp_transmit_skb。观察函数的调用顺序,与我们的分析是否一致。

(gdb) file vmlinux
Reading symbols from vmlinux...done.
warning: File "/home/netlab/netlab/linux-5.2.7/scripts/gdb/vmlinux-gdb.py" auto-loading has been declined by your `auto-load safe-path' set to "$debugdir:$datadir/auto-load".
To enable execution of this file add
    add-auto-load-safe-path /home/netlab/netlab/linux-5.2.7/scripts/gdb/vmlinux-gdb.py
line to your configuration file "/home/netlab/.gdbinit".
To completely disable this security protection add
    set auto-load safe-path /
line to your configuration file "/home/netlab/.gdbinit".
For more information about this security protection see the
"Auto-loading safe path" section in the GDB manual.  E.g., run from the shell:
    info "(gdb)Auto-loading safe path"
(gdb) target remote: 1234
Remote debugging using : 1234
0x0000000000000000 in fixed_percpu_data ()
(gdb) c
Continuing.
^C
Program received signal SIGINT, Interrupt.
default_idle () at arch/x86/kernel/process.c:581
581     trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
(gdb) b __sys_sendto
Breakpoint 1 at 0xffffffff817ef560: file net/socket.c, line 1929.
(gdb) b tcp_sendmsg_locked
Breakpoint 2 at 0xffffffff81895000: file net/ipv4/tcp.c, line 1158.
(gdb) b tcp_push
Breakpoint 3 at 0xffffffff818907c0: file ./include/linux/skbuff.h, line 1766.
(gdb) b __tcp_push_pending_frames
Breakpoint 4 at 0xffffffff818a44a0: file net/ipv4/tcp_output.c, line 2584.
(gdb) b tcp_wrtie_xmit
Function "tcp_wrtie_xmit" not defined.
Make breakpoint pending on future shared library load? (y or [n]) n
(gdb) b tcp_write_xmit
Breakpoint 5 at 0xffffffff818a32d0: file net/ipv4/tcp_output.c, line 2330.
(gdb) b __tcp_transmit_skb
Breakpoint 6 at 0xffffffff818a2830: file net/ipv4/tcp_output.c, line 1015.
(gdb) 

执行client命令,观察程序暂停的位置:

Breakpoint 6, __tcp_transmit_skb (sk=0xffff888006478880, 
    skb=0xffff888006871400, clone_it=1, gfp_mask=3264, rcv_nxt=0)
    at net/ipv4/tcp_output.c:1015
1015    {
(gdb) 

并非我们预想的那样,程序停在了__tcp_transmit_skb,但仔细分析,这应该是三次握手的过程,继续调试

Breakpoint 6, __tcp_transmit_skb (sk=0xffff888006478880, 
    skb=0xffff888006871400, clone_it=1, gfp_mask=3264, rcv_nxt=0)
    at net/ipv4/tcp_output.c:1015
1015    {
(gdb) c
Continuing.

Breakpoint 6, __tcp_transmit_skb (sk=0xffff888006478880, 
    skb=0xffff88800757a100, clone_it=0, gfp_mask=0, rcv_nxt=1155786088)
    at net/ipv4/tcp_output.c:1015
1015    {
(gdb) c
Continuing.

又有两次停在了这里,恰恰验证了猜想,因为这个程序的服务端和客户端都在同一台主机上,共用了同一个TCP协议栈,在TCP三次握手时,客户端发送两次,服务端发送一次,恰好三次。下面我们用客户端向服务器端发送,分析程序的调用过程:

Breakpoint 1, __sys_sendto (fd=5, buff=0x7ffc33c54bc0, len=2, flags=0, 
    addr=0x0 <fixed_percpu_data>, addr_len=0) at net/socket.c:1929
1929    {
(gdb) c
Continuing.

Breakpoint 2, tcp_sendmsg_locked (sk=0xffff888006479100, 
    msg=0xffffc900001f7e28, size=2) at net/ipv4/tcp.c:1158
1158    {
(gdb) c
Continuing.

Breakpoint 3, tcp_push (sk=0xffff888006479100, flags=0, mss_now=32752, 
    nonagle=0, size_goal=32752) at net/ipv4/tcp.c:699
699     skb = tcp_write_queue_tail(sk);
(gdb) c
Continuing.

Breakpoint 4, __tcp_push_pending_frames (sk=0xffff888006479100, cur_mss=32752, 
    nonagle=0) at net/ipv4/tcp_output.c:2584
2584        if (unlikely(sk->sk_state == TCP_CLOSE))
(gdb) c
Continuing.

Breakpoint 5, tcp_write_xmit (sk=0xffff888006479100, mss_now=32752, nonagle=0, 
    push_one=0, gfp=2592) at net/ipv4/tcp_output.c:2330
2330    {
(gdb) c
Continuing.

Breakpoint 6, __tcp_transmit_skb (sk=0xffff888006479100, 
    skb=0xffff888006871400, clone_it=1, gfp_mask=2592, rcv_nxt=405537035)
    at net/ipv4/tcp_output.c:1015
1015    {
(gdb) c
Continuing.

Breakpoint 6, __tcp_transmit_skb (sk=0xffff888006478880, 
    skb=0xffff88800757a100, clone_it=0, gfp_mask=0, rcv_nxt=1155786090)
    at net/ipv4/tcp_output.c:1015
1015    {
(gdb) c

可以看到,与我们分析的顺序是一致的,但是最后__tcp_transmit_skb调用了两次,经过仔细分析,终于找到原因——这是接收方接收到数据后发送ACK使用的。
验证完send,来验证一下recv
将断点分别设在:
__sys_recvfromsock_recvmsgtcp_rcvmsg__skb_datagram_iter处,以同样的方式观察:

Breakpoint 1, __sys_recvfrom (fd=5, ubuf=0x7ffd9428d960, size=1024, flags=0, 
    addr=0x0 <fixed_percpu_data>, addr_len=0x0 <fixed_percpu_data>)
    at net/socket.c:1990
1990    {
(gdb) c
Continuing.

Breakpoint 2, sock_recvmsg (sock=0xffff888006df1900, msg=0xffffc900001f7e28, 
    flags=0) at net/socket.c:891
891 {
(gdb) c
Continuing.

Breakpoint 3, tcp_recvmsg (sk=0xffff888006479100, msg=0xffffc900001f7e28, 
    len=1024, nonblock=0, flags=0, addr_len=0xffffc900001f7df4)
    at net/ipv4/tcp.c:1933
1933    {
(gdb) c

在未发送之前,程序也会暂停在断点处,根据之前的分析,这也是三次握手的过程,但是为什么没有__skb_datagram_iter呢?,因为三次握手时,并没有发送数据过来,所以并没有数据被拷贝到用户空间。
同样,尝试发送数据观察调用过程。

Breakpoint 1, __sys_recvfrom (fd=5, ubuf=0x7ffd9428d960, size=1024, flags=0, 
    addr=0x0 <fixed_percpu_data>, addr_len=0x0 <fixed_percpu_data>)
    at net/socket.c:1990
1990    {
(gdb) c
Continuing.

Breakpoint 2, sock_recvmsg (sock=0xffff888006df1900, msg=0xffffc900001f7e28, 
    flags=0) at net/socket.c:891
891 {
(gdb) c
Continuing.

Breakpoint 3, tcp_recvmsg (sk=0xffff888006479100, msg=0xffffc900001f7e28, 
    len=1024, nonblock=0, flags=0, addr_len=0xffffc900001f7df4)
    at net/ipv4/tcp.c:1933
1933    {
(gdb) c
Continuing.

Breakpoint 4, __skb_datagram_iter (skb=0xffff8880068714e0, offset=0, 
    to=0xffffc900001efe38, len=2, fault_short=false, 
    cb=0xffffffff817ff860 <simple_copy_to_iter>, data=0x0 <fixed_percpu_data>)
    at net/core/datagram.c:414
414 {

验证完毕。

深入理解TCP协议及其源代码-send和recv背后数据的收发过程

标签:RoCE   ndt   数据段   字节   就是   target   linux   协议栈   imp   

原文地址:https://www.cnblogs.com/myguaiguai/p/12069485.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!