linux内核数据包转发流程（三）网卡帧接收分析

【版权声明：转载请保留出处：blog.csdn.net/gentleliu。邮箱：shallnew*163.com】

每个cpu都有队列来处理接收到的帧，都有其数据结构来处理入口和出口流量，因此，不同cpu之间没有必要使用上锁机制，。此队列数据结构为softnet_data(定义在include/linux/netdevice.h中):

/*
 * Incoming packets are placed on per-cpu queues so that
 * no locking is needed.
 */
struct softnet_data
{
struct Qdisc *output_queue; 
struct sk_buff_headinput_pkt_queue;//有数据要传输的设备列表
struct list_headpoll_list; //双向链表，其中的设备有输入帧等着被处理。
struct sk_buff*completion_queue;//缓冲区列表，其中缓冲区已成功传输，可以释放掉


struct napi_structbacklog;
};

此结构字段可用于传输和接收。换而言之，NET_RX_SOFTIRQ和NET_TX_SOFTIRQ软IRQ都引用此结构。入口帧会排入input_pkt_queue(NAPI有所不同)。

softnet_data是在net_dev_init函数中初始化的：

/*
 *       This is called single threaded during boot, so no need
 *       to take the rtnl semaphore.
 */
static int __init net_dev_init(void)
{
int i, rc = -ENOMEM;

......

/*
* Initialise the packet receive queues.
*/

for_each_possible_cpu(i) {
struct softnet_data *queue;

queue = &per_cpu(softnet_data, i);
skb_queue_head_init(&queue->input_pkt_queue);
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);

queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
queue->backlog.gro_list = NULL;
queue->backlog.gro_count = 0;
}

......

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

......
}

非NAPI设备驱动会为其所接收的每一个帧产生一个中断事件，在高流量负载下，会花掉大量时间处理中断事件，造成资源浪费。而NAPI驱动混合了中断事件和轮询，在高流量负载下其性能会比旧方法要好。
NAPI主要思想是混合使用中断事件和轮询，而不是仅仅使用中断事件驱动模型。当收到新的帧时，关中断，再一次处理完所有入口队列。从内核观点来看，NAPI方法因为中断事件少了，减少了cpu负载。
使用非NAPI的驱动程序的xx_rx()函数一般如下：

void xx_rx()
{
struct sk_buff *skb;

skb = dev_alloc_skb(pkt_len + 5);
if (skb != NULL) {
skb_reserve(skb, 2);/* Align IP on 16 byte boundaries */

/*memcpy(skb_put(skb, 2), pkt, pkt_len);*/ //copy data to skb

skb->protocol = eth_type_trans(skb, dev);
netif_rx(skb);
}
}

第一步是分配一个缓存区来保存报文。 注意缓存分配函数 (dev_alloc_skb) 需要知道数据长度。

第二步将报文数据被拷贝到缓存区; skb_put  函数更新缓存中的数据末尾指针并返回指向新建空间的指针。

第三步提取协议标识及获取其他信息。

最后调用netif_rx(skb)做进一步处理，该函数一般定义在net/core/dev.c中。

int netif_rx(struct sk_buff *skb)
{
struct softnet_data *queue;
unsigned long flags;

/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
return NET_RX_DROP;

if (!skb->tstamp.tv64)
net_timestamp(skb);

/*
* The code is rearranged so that the path is the most
* short when CPU is congested, but is still operating.
*/
local_irq_save(flags);
queue = &__get_cpu_var(softnet_data);

__get_cpu_var(netdev_rx_stat).total++;
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {//是否还有空间,netdev_max_backlog一般为300
//只有当新缓冲区为空时，才会触发软中断（napi_schedule()）,如果缓冲区不为空，软中断已被触发，没有必要再去触发一次。
if (queue->input_pkt_queue.qlen) {
enqueue:
__skb_queue_tail(&queue->input_pkt_queue, skb);//这里是关键之处，将skb加入input_pkt_queue之中。
local_irq_restore(flags);
return NET_RX_SUCCESS;
}

napi_schedule(&queue->backlog);//触发软中断
goto enqueue;
}

__get_cpu_var(netdev_rx_stat).dropped++;
local_irq_restore(flags);

kfree_skb(skb);
return NET_RX_DROP;
}
EXPORT_SYMBOL(netif_rx);

static inline void napi_schedule(struct napi_struct *n)
{
	if (napi_schedule_prep(n))
		__napi_schedule(n);
}

void __napi_schedule(struct napi_struct *n)
{
	unsigned long flags;

	local_irq_save(flags);
	list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);//将该设备加入轮询链表，等待该设备的帧被处理
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);//最终触发软中断
	local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);

至此中断的上半部完成，其他的工作交由下半部来实现。napi_schedule(&queue->backlog)函数将有等待的接收数据包的NIC链入softnet_data的poll_list队列，然后触发软中断，让下半部去完成数据的处理工作。
而是用ＮＡＰＩ设备的接受数据时直接触发软中断，不需要通过netif_rx()函数设置好接收队列再触发软中断。比如e100硬中断处理函数为：

static irqreturn_t e100_intr(int irq, void *dev_id)
{
	struct net_device *netdev = dev_id;
	struct nic *nic = netdev_priv(netdev);
	u8 stat_ack = ioread8(&nic->csr->scb.stat_ack);

	DPRINTK(INTR, DEBUG, "stat_ack = 0x%02X\n", stat_ack);

	if (stat_ack == stat_ack_not_ours ||	/* Not our interrupt */
	   stat_ack == stat_ack_not_present)	/* Hardware is ejected */
		return IRQ_NONE;

	/* Ack interrupt(s) */
	iowrite8(stat_ack, &nic->csr->scb.stat_ack);

	/* We hit Receive No Resource (RNR); restart RU after cleaning */
	if (stat_ack & stat_ack_rnr)
		nic->ru_running = RU_SUSPENDED;

	if (likely(napi_schedule_prep(&nic->napi))) {
		e100_disable_irq(nic);
		__napi_schedule(&nic->napi);//此处触发软中断
	}

	return IRQ_HANDLED;
}

在前面我们已经知道在net_dev_init()函数中注册了收报软中断函数net_rx_action(),当软中断被触发之后，该函数将被调用。
net_rx_action()函数为：

static void net_rx_action(struct softirq_action *h)
{
	struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
	unsigned long time_limit = jiffies + 2;
	int budget = netdev_budget;
	void *have;

	local_irq_disable();

	while (!list_empty(list)) {
		struct napi_struct *n;
		int work, weight;

		/* If softirq window is exhuasted then punt.
		 * Allow this to run for 2 jiffies since which will allow
		 * an average latency of 1.5/HZ.
		 */
		if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))//入口队列仍然有缓冲区，软IRQ再度被调度执行。
			goto softnet_break;

		local_irq_enable();

		/* Even though interrupts have been re-enabled, this
		 * access is safe because interrupts can only add new
		 * entries to the tail of this list, and only ->poll()
		 * calls can remove this head entry from the list.
		 */
		n = list_entry(list->next, struct napi_struct, poll_list);

		have = netpoll_poll_lock(n);

		weight = n->weight;

		/* This NAPI_STATE_SCHED test is for avoiding a race
		 * with netpoll‘s poll_napi().  Only the entity which
		 * obtains the lock and sees NAPI_STATE_SCHED set will
		 * actually make the ->poll() call.  Therefore we avoid
		 * accidently calling ->poll() when NAPI is not scheduled.
		 */
		work = 0;
		if (test_bit(NAPI_STATE_SCHED, &n->state)) {
			work = n->poll(n, weight);//执行poll函数，返回已处理的帧
			trace_napi_poll(n);
		}

		WARN_ON_ONCE(work > weight);

		budget -= work;

		local_irq_disable();

		/* Drivers must not modify the NAPI state if they
		 * consume the entire weight.  In such cases this code
		 * still "owns" the NAPI instance and therefore can
		 * move the instance around on the list at-will.
		 */
		if (unlikely(work == weight)) {//队列被清空。调用napi_complete()负责此事。
			if (unlikely(napi_disable_pending(n))) {
				local_irq_enable();
				napi_complete(n);
				local_irq_disable();
			} else
				list_move_tail(&n->poll_list, list);
		}

		netpoll_poll_unlock(have);
	}
out:
	local_irq_enable();

#ifdef CONFIG_NET_DMA
	/*
	 * There may not be any more sk_buffs coming right now, so push
	 * any pending DMA copies to hardware
	 */
	dma_issue_pending_all();
#endif

	return;

softnet_break:
	__get_cpu_var(netdev_rx_stat).time_squeeze++;
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	goto out;
}

由上可见，下半部的主要工作是遍历有数据帧等待接收的设备链表，对于每个设备，执行它相应的poll函数。
对非NAPI设备来说，poll函数在net_dev_init()函数中初始化为process_backlog()。
process_backlog()函数定义为：

static int process_backlog(struct napi_struct *napi, int quota)
{
	int work = 0;
	struct softnet_data *queue = &__get_cpu_var(softnet_data);
	unsigned long start_time = jiffies;

	napi->weight = weight_p;
	do {
		struct sk_buff *skb;

		local_irq_disable();
		skb = __skb_dequeue(&queue->input_pkt_queue);
		if (!skb) {
			__napi_complete(napi);
			local_irq_enable();
			break;
		}
		local_irq_enable();

		netif_receive_skb(skb);
	} while (++work < quota && jiffies == start_time);

	return work;
}

对NAPI设备来的说，驱动程序必须提供一个poll方法,poll 方法有下面原型:
int (*poll)(struct napi_struct *dev, int *budget); 
在初始化时需要添加该方法：
netif_napi_add(netdev, &nic->napi, xx_poll, XX_NAPI_WEIGHT);

NAPI驱动 的 poll 方法实现一般如下（借用《Linux设备驱动程序》中代码，内核有点没对上，懒得去写了）:

static int xx_poll(struct net_device *dev, int *budget)
{
    int npackets = 0, quota = min(dev->quota, *budget);
    struct sk_buff *skb;
    struct xx_priv *priv = netdev_priv(dev);
    struct xx_packet *pkt;

    while (npackets < quota && priv->rx_queue) {
        pkt = xx_dequeue_buf(dev);
        skb = dev_alloc_skb(pkt->datalen + 2);
        if (! skb) {

            if (printk_ratelimit())
                printk(KERN_NOTICE "xx: packet dropped\n"); priv->stats.rx_dropped++; xx_release_buffer(pkt); continue;
        }
        memcpy(skb_put(skb, pkt->datalen), pkt->data, pkt->datalen);
        skb->dev = dev;
        skb->protocol = eth_type_trans(skb, dev);
        skb->ip_summed = CHECKSUM_UNNECESSARY; /* don‘t check it */
        netif_receive_skb(skb);

        /* Maintain stats */
        npackets++;
        priv->stats.rx_packets++;
        priv->stats.rx_bytes += pkt->datalen;
        xx_release_buffer(pkt);

    }
    /* If we processed all packets, we‘re done; tell the kernel and reenable ints */
    *budget -= npackets;
    dev->quota -= npackets;
    if (! priv->rx_queue) {

        netif_rx_complete(dev);
        xx_rx_ints(dev, 1);
        return 0;

    }
    /* We couldn‘t process everything. */
    return 1;

}

NAPI驱动提供自己的poll函数和私有队列。
不管是非NAPI或NAPI，他们的poll函数最后都会调用netif_receive_skb(skb)来处理接收到的帧。该函数会想各个已注册的协议例程发送一个skb，之后数据进入Linux内核协议栈处理。

linux内核数据包转发流程（三）网卡帧接收分析,古老的榕树,5-wow.com