硬件时间戳中没有所需类型的消息

Question

我在多平台硬件时间戳应用程序下工作。 我对linux时间戳行为有点困惑。 我从recvmsg中收到错误“没有所需类型的消息”，并尝试像错误一样处理它。 我的调试代码如下。 我看到预期的行为：

1. 发送时间戳传出的数据包将在附加发送时间戳的情况下循环回到套接字的错误队列。

2. 可以使用带有标志| = MSG_ERRQUEUE的recvmsg接收克隆的已发送数据包。

3. recvmsg返回带有sock_extended_err的传出数据包（ee_errno == ENOMSG）。 ENOMSG是“没有所需类型的消息”。

因此，看起来linux应该将传出数据包的克隆保留在错误队列中以进行功能时间计算。 我应该在错误处理程序代码中跳过ENOMSG吗？

if (errno == EAGAIN || errno == EINTR || errno == ENOMSG)
    break;

为什么它通过错误消息报告？ 也许不清楚为什么ENOMSG会期望吗？

我得到了：错误描述=来自recvmsg的'没有所需类型的消息'。

recvmsg(sock, &msg, recvmsg_flags|MSG_ERRQUEUE);

for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg))
{
    ...
    switch (cmsg->cmsg_level) {
    case SOL_IP:
        ...
        pkt.cmsg = (const struct cmsghdr*)cmsg;
        pkt.msg  = (const struct msghdr*)msg;
        print_sol_ip(&pkt);
    break;
    }
}
/* Network level L3.
 * Note that there is no TCP error queue;
 * MSG_ERRQUEUE flag can not be used for socket type SOCK_STREAM.
 * Thus, any errors can only be obtained as the value returned by the socket,
 * or through option SO_ERROR.
 */
static void print_sol_ip(struct cmh_packet *pkt)
{
    const int type = pkt->cmsg->cmsg_type;
    const struct cmsghdr *cmsg = pkt->cmsg;
    if (pkt->cmsg->cmsg_level != SOL_IP) {
        printf("Wrong handler.\n");
        return;
    }
    printf("SOL::IP::");
    switch (type) {
    case IP_RECVERR:
        printf("RECVERR::\n");
        struct sock_extended_err *err;
        struct sockaddr *sk_addr;
        struct sockaddr_in *sk_addrin;
        socklen_t sk_addrlen;
        err = (struct sock_extended_err *)CMSG_DATA(pkt->cmsg);
        if ((sk_addr = malloc(sizeof(struct sockaddr))) == NULL) return;

        /*
         * The original destination address of the datagram that caused the error is supplied via msg_name
         * For local errors, no address is passed (this can be checked with the cmsg_len member of the cmsghdr).
         */
        printf("pointer to the data: %p\n", pkt->cmsg->__cmsg_data);
        printf("data byte count, including header: %zd\n", pkt->cmsg->cmsg_len); /* CMSG_LEN */
        printf("originating protocol: %d\n", pkt->cmsg->cmsg_level);             /* SOL_SOCKET */
        printf("protocol-specific type: %d\n", pkt->cmsg->cmsg_type);            /* SCM_RIGHTS */

        printf("%s = %d  \n", "error number", err->ee_errno);
        printf("%s = %d  \n", "error origin", err->ee_origin); /* origin: SO_EE_ORIGIN_ICMP..LOCAL..NONE */
        printf("%s = %d  \n", "error type", err->ee_type);     /* type: ICMP_NET_UNREACH..ICMP_HOST_UNREACH */
        printf("%s = %d  \n", "error code", err->ee_code);
        printf("%s = %d  \n", "error pad", err->ee_pad);
        printf("%s = %d  \n", "error info", err->ee_info);
        printf("%s = %d  \n", "error data", err->ee_data);
        printf("error description = '%s'\n", strerror(err->ee_errno));

        sk_addr = (struct sockaddr*)pkt->msg->msg_name;
        sk_addrlen = pkt->msg->msg_namelen;
        sk_addrin = (struct sockaddr_in*)sk_addr;
        printf("%s:%d addrlen: %d\n", inet_ntoa(sk_addrin->sin_addr), ntohs(sk_addrin->sin_port), sk_addrlen);

        print_af(sk_addr->sa_family);
        break;

    case IP_PKTINFO:
        printf("PKTINFO::\n");
        struct in_pktinfo *pki;
        pki = (struct in_pktinfo *)CMSG_DATA(pkt->cmsg);
        printf("Source interface index %u local address %s destination address %s",
                pki->ipi_ifindex,
                inet_ntoa(pki->ipi_spec_dst),
                inet_ntoa(pki->ipi_addr));
        break;
    case IP_RECVOPTS:       /* Routing header and other options are already installed on the local host. */
        printf("IP_RECVOPTS::\n");
        break;

    case IP_RETOPTS:
        printf("IP_RETOPTS::\n");
        break;

    case IP_TOS:            /* the field is used to create network packet priorities.
                           There are several default values flag TOS: IPTOS_LOWDELAY,
                           in order to minimize delays for the traffic, IPTOS_THROUGHPUT,
                           to improve throughput, IPTOS_RELIABILITY, to increase
                           reliability, IPTOS_MINCOST, should be used for "optional data"
                           that can be sent at the minimum speed. */
        printf("IP_TOS::\n");
        break;

    case IP_TTL:            /* ip_default_ttl */
        printf("IP_TTL::\n");
        int ttl;
        int *pttl;
        pttl = (int *) CMSG_DATA(pkt->cmsg);
        ttl = *pttl;
        printf("ttl value = %d\n", ttl);
        break;
    case IP_HDRINCL:        /* Enabling this flag means that the user has already added the IP header to the top of their data. */
        printf("IP_HDRINCL::\n");
        break;
    case IP_MTU:
        printf("IP_MTU::\n");
        //TODO: getsockopt(sock, level, IP_MTU, IP_MTU_value_get, size);
        break;

    case IP_ROUTER_ALERT:       /* It transmits this socket all packets that are sent with the option
                                 * of IP Router Alert. This option is used only in the
                                 * type of sockets RAW.
                                 * */
        printf("IP_ROUTER_ALERT::\n");
        break;
    case IP_MULTICAST_TTL:
        printf("IP_MULTICAST_TTL::\n");
        break;
    default:
        printf("TYPE %d\n", cmsg->cmsg_type);
        break;

    }
}

Answer 1

很明显，我从环回时间戳skb中获得了ENOMSG。 如linux / Documentation / networking / timestamping.txt中所述。 最后，我发现ip_recv_error（）从sk-> sk_error_queue（errqueue）提取了skb并重置了错误sk-> sk_err =0。但是它还检查了sk_error_queue中是否存在其他skb。 我的erqueue在sk_error_queue中有几个skb，这就是为什么最终检查errqueue中的ip_recv_error发现它具有skb的原因。

skb2 = skb_peek(&sk->sk_error_queue);

它具有skb2，并且sk-> sk_err被重置回ENOMSG。

sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;

skb2以前来自

void skb_tstamp_tx(struct sk_buff *orig_skb,
        struct skb_shared_hwtstamps *hwtstamps)

serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = ENOMSG;

无论错误从哪个队列中读取，如果errqueue包含skb（skb cb控制缓冲区应在ee_errno中包含错误），recvmsg都会报告错误。 因为udp_recvmsg调用__skb_recv_datagram，它检查struct sk是否包含错误。

int error = sock_error(sk); 

如果是这样，它将报告-1，并在skb中发现错误。 因此，对于udp来说，从sk_error_queue中读取所有消息至关重要。 因为在最后一次读取期间，sk-> sk_err将重置（或getsockopt（SO_ERROR））。 或者只是略过而已，下次读取时会有些延迟。