链路层收包

Posted 2021-11-29 codestack

 

 

 

//当底层设备驱动程序接收一个报文时，就会通过调用netif_receive_skb将报文的SKB上传至网络层。
/*
在netif_rx函数中会调用netif_rx_schedule, 然后该函数又会去调用__netif_rx_schedule
在函数__netif_rx_schedule中会去触发软中断NET_RX_SOFTIRQ, 也即是去调用net_rx_action.
然后在net_rx_action函数中会去调用设备的poll函数, 它是设备自己注册的.
在设备的poll函数中, 会去调用netif_receive_skb函数,  在该函数中有下面一条语句 pt_prev->func, 此处的func为一个函数指针,
因此, 就完成了从链路层上传到网络层的这一个过程了.
*/

/*非NAPI方式，从驱动硬件中断中调用这个netif_rx函数，

而NAPI方式从硬件中断中调用____napi_schedule激活软中断,
*/
/*
            非NAPI方式                                              NAPI方式NAPI方式(NAPI的napi_struct是自己构造的，该结构上的poll钩子函数也是自己定义的。

                                        IRQ
                                         |
                  _______________________|_____________________________
                  |                                                     |
             netif_rx(netif_rx_internal)                napi_schedule
 上半部           |                                                     |
             enqueue_to_backlog                                  __napi_schedule
                  |                                                     |           
            skb加入input_pkt_queuem中                           napi_struct加入poll_list中
       　　__napi_schedule    

　　 　softnet_data->backlog加入poll_list中                                      |
                   |____________________________________________________|
                                             |
                                        net_rx_action
下半部                                       |
                      _______________________|_____________________________
                      |                                                     |
            process_backlog->__netif_receive_skb                驱动poll方法->napi_gro_receive->netif_receive_skb->__netif_receive_skb

*/

 

static int netif_rx_internal(struct sk_buff *skb)
{
	int ret;

	net_timestamp_check(netdev_tstamp_prequeue, skb);

	trace_netif_rx(skb);
#ifdef CONFIG_RPS
	if (static_key_false(&rps_needed)) {
		struct rps_dev_flow voidflow, *rflow = &voidflow;
		int cpu;

		preempt_disable();
		rcu_read_lock();

		cpu = get_rps_cpu(skb->dev, skb, &rflow);
		if (cpu < 0)
			cpu = smp_processor_id();

		ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);//这里面的数据在process_backlog

		rcu_read_unlock();
		preempt_enable();
	} else
#endif
	{
		unsigned int qtail;
		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
		put_cpu();
	}
	return ret;
}

 /* 队列中.在中断轮询的时候,软中断总函数do_softirq()直接到达网卡的接收软中断函数net_rx_action()，
   在此函数中调用queue->backlog_dev.poll=process_backlog;即process_backlog()函数，它将queue->input_pkt_queue
   队列中的数据向上层协议传输，比如网络层的ip协议等。
*/
/*
            非NAPI方式                                              NAPI方式NAPI方式(NAPI的napi_struct是自己构造的，该结构上的poll钩子函数也是自己定义的

                                        IRQ
                                         |
                  _______________________|_____________________________
                  |                                                     　　|
             netif_rx                                            napi_schedule
 上半部      |                                                       　  |
             enqueue_to_backlog

　　　　　____napi_schedule                                 __napi_schedule
                  |                                                    　　 |           
            skb加入input_pkt_queuem中                           napi_struct加入poll_list中
            softnet_data->backlog加入poll_list中                                      |
                   |____________________________________________________|
                                             |
                                        net_rx_action
下半部                                       |
                      _______________________|_____________________________
                      |                                                     |
            porcess_backlog->__netif_receive_skb                驱动poll方法->napi_gro_receive->netif_receive_skb->__netif_receive_skb

*/

static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
			      unsigned int *qtail)
{
	struct softnet_data *sd;
	unsigned long flags;
	unsigned int qlen;

	sd = &per_cpu(softnet_data, cpu);//获取cpu接口缓存队列（每cpu变量下次写内核同步介绍）

	local_irq_save(flags);//关中断，当该SKB添加到输入队列input_pkt_queue后打开中断，继续从硬件中断中接收输入然后放入该接收队列中

	rps_lock(sd);
	if (!netif_running(skb->dev))
		goto drop;
	qlen = skb_queue_len(&sd->input_pkt_queue);
	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {如果链路层缓存队列还没有满，则加入队列，否者上层处理严重阻塞，丢失，drop++
		if (qlen) { 队列不为空，说明已经有数据，只需加入队列，等待下次软中断处理
enqueue:
			__skb_queue_tail(&sd->input_pkt_queue, skb);/* 挂softnet_data输入队列 */ //net_rx_action中会对包的个数，以及软中断处理时间进行限制
			input_queue_tail_incr_save(sd, qtail);
			rps_unlock(sd); 
			local_irq_restore(flags);//打开中断，当该SKB添加到输入队列input_pkt_queue后打开中断，继续从硬件中断中接收输入然后放入该接收队列中
			return NET_RX_SUCCESS;
		}

		/* Schedule NAPI for backlog device
		 * We can use non atomic operation since we own the queue lock
		 */ /* &sd->backlog加入napi->poll_list，backlog即函数process_backlog */
		if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
			if (!rps_ipi_queued(sd))//这里就会调用net_dev_init中的->backlog_dev.poll=process_backlog从而到process_backlog中执行　　　　　　　　　　　　　　　　　　

for_each_possible_cpu(i) {
        struct softnet_data *sd = &per_cpu(softnet_data, i);

        skb_queue_head_init(&sd->input_pkt_queue);
        skb_queue_head_init(&sd->process_queue);
        INIT_LIST_HEAD(&sd->poll_list);
        sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
        sd->csd.func = rps_trigger_softirq;
        sd->csd.info = sd;
        sd->cpu = i;
#endif

        sd->backlog.poll = process_backlog;
        sd->backlog.weight = weight_p;
    }

    dev_boot_phase = 0;

    /* The loopback device is special if any other network devices
     * is present in a network namespace the loopback device must
     * be present. Since we now dynamically allocate and free the
     * loopback device ensure this invariant is maintained by
     * keeping the loopback device as the first device on the
     * list of network devices.  Ensuring the loopback devices
     * is the first device that appears and the last network device
     * that disappears.
     */
    if (register_pernet_device(&loopback_net_ops))
        goto out;

    if (register_pernet_device(&default_device_ops))
        goto out;

    open_softirq(NET_TX_SOFTIRQ, net_tx_action);
    open_softirq(NET_RX_SOFTIRQ, net_rx_action);

View Code

 　　　　　　　　　　　　　　____napi_schedule(sd, &sd->backlog);//加入list 并激活软中断

/*NAPI方式，把dev设备添加到了poll_list链表中。
每个网络设备（MAC层）都有自己的net_device数据结构，这个结构上有napi_struct。每当收到数据包时，网络设备驱动会把自己的napi_struct挂到CPU私有变量上。
这样在软中断时，net_rx_action会遍历cpu私有变量的poll_list，执行上面所挂的napi_struct结构的poll钩子函数,将数据包从驱动传到网络协议栈。

NAPI的napi_struct是自己构造的，该结构上的poll钩子函数也是自己定义的。
非NAPI的napi_struct结构是默认的，也就是per cpu的softnet_data>backlog，起poll钩子函数为process_backlog
*/

/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
                     struct napi_struct *napi)
{
    list_add_tail(&napi->poll_list, &sd->poll_list);
    __raise_softirq_irqoff(NET_RX_SOFTIRQ);
}

View Code

 

		}
		goto enqueue;
	}

drop:
	sd->dropped++;
	rps_unlock(sd);

	local_irq_restore(flags);

	atomic_long_inc(&skb->dev->rx_dropped);
	kfree_skb(skb);
	return NET_RX_DROP;
}