int dev_queue_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
struct Qdisc *q;
int rc = -ENOMEM;
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
//关闭软中断 - __rcu_read_lock_bh()--->local_bh_disable();
rcu_read_lock_bh();
// 选择一个发送队列，如果设备提供了select_queue回调函数就使用它，否则由内核选择一个队列,这里只是Linux内核多队列的实现，但是要真正的使用都队列，需要网卡支持多队列才可以，一般的网卡都只有一个队列。在调用alloc_etherdev分配net_device是，设置队列的个数
txq = dev_pick_tx(dev, skb);
//从netdev_queue结构上获取设备的qdisc
q = rcu_dereference_bh(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
#endif
//如果硬件设备有队列可以使用，该函数由dev_queue_xmit函数直接调用或由dev_queue_xmit通过qdisc_run函数调用
trace_net_dev_queue(skb);
if (q->enqueue) {
rc = __dev_xmit_skb(skb, q, dev, txq); //使用流控对象发送数据包(包含入队和出队)
//更详细的内容参考说明3
goto out;
}
//下面的处理是在没有发送队列的情况下
/* The device has no queue. Common case for software devices:
loopback, all the sorts of tunnels...
Really, it is unlikely that netif_tx_lock protection is necessary
here. (f.e. loopback and IP tunnels are clean ignoring statistics
counters.)
However, it is possible, that they rely on protection
made by us here.
Check this and shot the lock. It is not prone from deadlocks.
Either shot noqueue qdisc, it is even simpler 8)
*/
//首先，确定设备是开启的，并且还要确定队列是运行的，启动和停止队列有驱动程序决定
//设备没有输出队列典型的是回环设备。这里需要做的就是直接调用dev_start_queue_xmit、、函数，经过驱动发送出去，如果发送失败，就直接丢弃，没有队列可以保存。
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
if (txq->xmit_lock_owner != cpu) {
if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
goto recursion_alert;
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_tx_queue_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
rc = dev_hard_start_xmit(skb, dev, txq);//见说明4
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
}
}
HARD_TX_UNLOCK(dev, txq);
if (net_ratelimit())
printk(KERN_CRIT "Virtual device %s asks to "
"queue packet!\n", dev->name);
} else {
/* Recursion is It is possible,
* unfortunately
*/
recursion_alert:
if (net_ratelimit())
printk(KERN_CRIT "Dead loop on virtual device "
"%s, fix it urgently!\n", dev->name);
}
}
rc = -ENETDOWN;
rcu_read_unlock_bh();
kfree_skb(skb);
return rc;
out:
rcu_read_unlock_bh();
return rc;
}
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev,
struct netdev_queue *txq)
{
spinlock_t *root_lock = qdisc_lock(q);
bool contended = qdisc_is_running(q);
int rc;
/*
* Heuristic to force contended enqueues to serialize on a
* separate lock before trying to get qdisc main lock.
* This permits __QDISC_STATE_RUNNING owner to get the lock more often
* and dequeue packets faster.
*/
if (unlikely(contended))
spin_lock(&q->busylock);
spin_lock(root_lock);
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
kfree_skb(skb);
rc = NET_XMIT_DROP;
} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
qdisc_run_begin(q)) {
/*
* This is a work-conserving queue; there are no old skbs
* waiting to be sent out; and the qdisc is not running -
* xmit the skb directly.
*/
if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
skb_dst_force(skb);
__qdisc_update_bstats(q, skb->len);
if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
}
__qdisc_run(q);
} else
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
skb_dst_force(skb);
rc = qdisc_enqueue_root(skb, q);
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
}
__qdisc_run(q);
}
}
spin_unlock(root_lock);
if (unlikely(contended))
spin_unlock(&q->busylock);
return rc;
}
void __qdisc_run(struct Qdisc *q)
{
unsigned long start_time = jiffies;
while (qdisc_restart(q)) { //返回值大于0，说明流控对象非空。
/*
* Postpone processing if
* 1. another process needs the CPU;
* 2. we've been doing it for too long.
*/
if (need_resched() || jiffies != start_time) { //已经不允许继续运行本流控对象。
__netif_schedule(q); //将本队列加入软中断的output_queue链表中。
break;
}
}
qdisc_run_end(q);
}
struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;//驱动程序的函数集
int rc = NETDEV_TX_OK;
if (likely(!skb->next)) {
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);//如果dev_add_pack加入的是ETH_P_ALL，那么就会复制一份给你的回调函数。
/*
* If device doesnt need skb->dst, release it right now while
* its hot in this cpu cache
*/
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(skb);
skb_orphan_try(skb);
if (vlan_tx_tag_present(skb) &&
!(dev->features & NETIF_F_HW_VLAN_TX)) {
skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
if (unlikely(!skb))
goto out;
skb->vlan_tci = 0;
}
if (netif_needs_gso(dev, skb)) {
if (unlikely(dev_gso_segment(skb)))
goto out_kfree_skb;
if (skb->next)
goto gso;
} else {
if (skb_needs_linearize(skb, dev) &&
__skb_linearize(skb))
goto out_kfree_skb;
/* If packet is not checksummed and device does not
* support checksumming for this protocol, complete
* checksumming here.
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_set_transport_header(skb, skb->csum_start -
skb_headroom(skb));
if (!dev_can_checksum(dev, skb) &&
skb_checksum_help(skb))
goto out_kfree_skb;
}
}
rc = ops->ndo_start_xmit(skb, dev);//调用网卡的驱动程序发送数据。不同的网络设备有不同的发送函数
trace_net_dev_xmit(skb, rc);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}
gso:
do {
struct sk_buff *nskb = skb->next;
skb->next = nskb->next;
nskb->next = NULL;
/*
* If device doesnt need nskb->dst, release it right now while
* its hot in this cpu cache
*/
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(nskb);
rc = ops->ndo_start_xmit(nskb, dev); //调用网卡的驱动程序发送数据。不同的网络设备有不同的发送函数
trace_net_dev_xmit(nskb, rc);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
goto out_kfree_gso_skb;
nskb->next = skb->next;
skb->next = nskb;
return rc;
}
txq_trans_update(txq);
if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
out_kfree_gso_skb:
if (likely(skb->next == NULL))
skb->destructor = DEV_GSO_CB(skb)->destructor;
out_kfree_skb:
kfree_skb(skb);
out:
return rc;
}
