网卡 超时处理watchdog

超时处理dev_watchdog

当watchdog发现网卡处于up状态并且发送队列处于停止时间大于5秒时将触发看门狗机制，

dev_watchdog先找到停止的队列，然后调用igb_tx_timeout整个网卡队列做超时处理，igb_tx_timeout中对网卡做了DOWN、UP的操作。

static void dev_watchdog(unsigned long arg)
{
    struct net_device *dev = (struct net_device *)arg;

    netif_tx_lock(dev);
    if (!qdisc_tx_is_noop(dev)) {        //txq->qdisc不是noop_qdisc
        if (netif_device_present(dev) && //网卡设备还存在
            netif_running(dev) &&        // 网卡设备还在运行
            netif_carrier_ok(dev)) {     //网卡设备在线
            int some_queue_timedout = 0;
            unsigned int i;
            unsigned long trans_start;

            for (i = 0; i < dev->num_tx_queues; i++) {
                struct netdev_queue *txq;

                txq = netdev_get_tx_queue(dev, i); 
                /*
                 * old device drivers set dev->trans_start
                 */
                trans_start = txq->trans_start ? : dev->trans_start;
                if (netif_xmit_stopped(txq) && //发送队列是停止状态
                    time_after(jiffies, (trans_start +
                             dev->watchdog_timeo))) { //发送队列停止超过5秒
                    some_queue_timedout = 1;
                    txq->trans_timeout++;
                    break;
                }
            }

            if (some_queue_timedout) {
                WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
                       dev->name, netdev_drivername(dev), i); 
                dev->netdev_ops->ndo_tx_timeout(dev); //超时处理函数
            }
            if (!mod_timer(&dev->watchdog_timer,
                       round_jiffies(jiffies +
                             dev->watchdog_timeo)))
                dev_hold(dev);
        }
    }   
    netif_tx_unlock(dev);

    dev_put(dev);
}

static const struct net_device_ops igb_netdev_ops = {
    .ndo_open       = igb_open,
    .ndo_stop       = igb_close,
    .ndo_start_xmit     = igb_xmit_frame,
... ...
    .ndo_tx_timeout     = igb_tx_timeout,
... ... 
}

igb_tx_timeout:
    schedule_work(&adapter->reset_task);

igb_reset_task:
    netdev_err(adapter->netdev, "Reset adapter\n");
    igb_reinit_locked:
        igb_down
        igb_up

 

linux 网络设备 watchdog 分析