网络数据的发送

static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	//...
	res = sock_sendmsg(sock, &msg);
	//...
}

SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags)
{
	return __sys_sendto(fd, buff, len, flags, NULL, 0);
}

SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags, struct sockaddr __user *, addr,
		int, addr_len)
{
	return __sys_sendto(fd, buff, len, flags, addr, addr_len);
}

SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags)
{
	return __sys_sendmsg(fd, msg, flags, true);
}

static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
{
	int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg,
				     inet_sendmsg, sock, msg,
				     msg_data_left(msg));
	//...
}

int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
	//...
	return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg,
			       sk, msg, size);
}

int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
	//...
	return INDIRECT_CALL_2(prot->sendmsg, tcp_sendmsg, udpv6_sendmsg,
			       sk, msg, size);
}

int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct iphdr *iph = ip_hdr(skb);

	iph_set_totlen(iph, skb->len);
	ip_send_check(iph);

	/* if egress device is enslaved to an L3 master device pass the
	 * skb to its handler for processing
	 */
	skb = l3mdev_ip_out(sk, skb);
	if (unlikely(!skb))
		return 0;

	skb->protocol = htons(ETH_P_IP);

	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
		       net, sk, skb, NULL, skb_dst(skb)->dev,
		       dst_output);
}

int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	int err;

	err = __ip_local_out(net, sk, skb);
	if (likely(err == 1))
		err = dst_output(net, sk, skb);

	return err;
}

/* Output packet to network from transport.  */
static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	return INDIRECT_CALL_INET(skb_dst(skb)->output,
				  ip6_output, ip_output,
				  net, sk, skb);
}

int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;

	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);

	skb->dev = dev;
	skb->protocol = htons(ETH_P_IP);

	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
			    net, sk, skb, indev, dev,
			    ip_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
}

static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	unsigned int mtu;

#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
	/* Policy lookup after SNAT yielded a new policy */
	if (skb_dst(skb)->xfrm) {
		IPCB(skb)->flags |= IPSKB_REROUTED;
		return dst_output(net, sk, skb);
	}
#endif
	mtu = ip_skb_dst_mtu(sk, skb);
	if (skb_is_gso(skb))
		return ip_finish_output_gso(net, sk, skb, mtu);

	if (skb->len > mtu || IPCB(skb)->frag_max_size)
		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);

	return ip_finish_output2(net, sk, skb);
}

static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	//...
	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
	if (!IS_ERR(neigh)) {
		//...
		res = neigh_output(neigh, skb, is_v6gw);
		//...
	}
	//...
}

static inline int neigh_output(struct neighbour *n, struct sk_buff *skb,
			       bool skip_cache)
{
	const struct hh_cache *hh = &n->hh;

	/* n->nud_state and hh->hh_len could be changed under us.
	 * () is taking care of the race later.
	 */
	if (!skip_cache &&
	    (READ_ONCE(n->nud_state) & NUD_CONNECTED) &&
	    READ_ONCE(hh->hh_len))
		return neigh_hh_output(hh, skb);

	return n->output(n, skb);
}

static int arp_constructor(struct neighbour *neigh)
{
	//...
	if (!dev->header_ops) {
		neigh->nud_state = NUD_NOARP;
		neigh->ops = &arp_direct_ops;
		neigh->output = neigh_direct_output;
	} else {
	//...
		if (dev->header_ops->cache)
			neigh->ops = &arp_hh_ops;
		else
			neigh->ops = &arp_generic_ops;

		if (neigh->nud_state & NUD_VALID)
			neigh->output = neigh->ops->connected_output;
		else
			neigh->output = neigh->ops->output;
	}
	return 0;
}

static inline int dev_queue_xmit(struct sk_buff *skb)
{
	return __dev_queue_xmit(skb, NULL);
}

/**
 * __dev_queue_xmit() - transmit a buffer
 * @skb:	buffer to transmit
 * @sb_dev:	suboordinate device used for L2 forwarding offload
 *
 * Queue a buffer for transmission to a network device. The caller must
 * have set the device and priority and built the buffer before calling
 * this function. The function can be called from an interrupt.
 *
 * When calling this method, interrupts MUST be enabled. This is because
 * the BH enable code must have IRQs enabled so that it will not deadlock.
 *
 * Regardless of the return value, the skb is consumed, so it is currently
 * difficult to retry a send to this method. (You can bump the ref count
 * before sending to hold a reference for retry if you are careful.)
 *
 * Return:
 * * 0				- buffer successfully transmitted
 * * positive qdisc return code	- NET_XMIT_DROP etc.
 * * negative errno		- other errors
 */
int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
{
	struct net_device *dev = skb->dev;
	struct netdev_queue *txq = NULL;
	struct Qdisc *q;
	int rc = -ENOMEM;
	bool again = false;

	//...

	if (!txq)
		txq = netdev_core_pick_tx(dev, skb, sb_dev);

	q = rcu_dereference_bh(txq->qdisc);

	trace_net_dev_queue(skb);
	if (q->enqueue) {
		rc = __dev_xmit_skb(skb, q, dev, txq);
		goto out;
	}

	/* 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)
	 */
	if (dev->flags & IFF_UP) {
		int cpu = smp_processor_id(); /* ok because BHs are off */

		/* Other cpus might concurrently change txq->xmit_lock_owner
		 * to -1 or to their cpu id, but not to our id.
		 */
		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
			if (dev_xmit_recursion())
				goto recursion_alert;

			skb = validate_xmit_skb(skb, dev, &again);
			if (!skb)
				goto out;

			HARD_TX_LOCK(dev, txq, cpu);

			if (!netif_xmit_stopped(txq)) {
				dev_xmit_recursion_inc();
				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
				dev_xmit_recursion_dec();
				if (dev_xmit_complete(rc)) {
					HARD_TX_UNLOCK(dev, txq);
					goto out;
				}
			}
			//...
		} else {
			//...
		}
	}

	//...
}

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);
	struct sk_buff *to_free = NULL;
	bool contended;
	int rc;

	qdisc_calculate_pkt_len(skb, q);

	if (q->flags & TCQ_F_NOLOCK) {
		if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) &&
		    qdisc_run_begin(q)) {
			/* Retest nolock_qdisc_is_empty() within the protection
			 * of q->seqlock to protect from racing with requeuing.
			 */
			if (unlikely(!nolock_qdisc_is_empty(q))) {
				rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
				__qdisc_run(q);
				qdisc_run_end(q);

				goto no_lock_out;
			}

			qdisc_bstats_cpu_update(q, skb);
			if (sch_direct_xmit(skb, q, dev, txq, NULL, true) &&
			    !nolock_qdisc_is_empty(q))
				__qdisc_run(q);

			qdisc_run_end(q);
			return NET_XMIT_SUCCESS;
		}

		rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
		qdisc_run(q);

no_lock_out:
		if (unlikely(to_free))
			kfree_skb_list_reason(to_free,
					      SKB_DROP_REASON_QDISC_DROP);
		return rc;
	}

	/*
	 * Heuristic to force contended enqueues to serialize on a
	 * separate lock before trying to get qdisc main lock.
	 * This permits qdisc->running owner to get the lock more
	 * often and dequeue packets faster.
	 * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit
	 * and then other tasks will only enqueue packets. The packets will be
	 * sent after the qdisc owner is scheduled again. To prevent this
	 * scenario the task always serialize on the lock.
	 */
	contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT);
	if (unlikely(contended))
		spin_lock(&q->busylock);

	spin_lock(root_lock);
	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
		__qdisc_drop(skb, &to_free);
		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.
		 */

		qdisc_bstats_update(q, skb);

		if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) {
			if (unlikely(contended)) {
				spin_unlock(&q->busylock);
				contended = false;
			}
			__qdisc_run(q);
		}

		qdisc_run_end(q);
		rc = NET_XMIT_SUCCESS;
	} else {
		rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
		if (qdisc_run_begin(q)) {
			if (unlikely(contended)) {
				spin_unlock(&q->busylock);
				contended = false;
			}
			__qdisc_run(q);
			qdisc_run_end(q);
		}
	}
	spin_unlock(root_lock);
	if (unlikely(to_free))
		kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP);
	if (unlikely(contended))
		spin_unlock(&q->busylock);
	return rc;
}

void __qdisc_run(struct Qdisc *q)
{
	int quota = READ_ONCE(dev_tx_weight);
	int packets;

	while (qdisc_restart(q, &packets)) {
		quota -= packets;
		if (quota <= 0) {
			if (q->flags & TCQ_F_NOLOCK)
				set_bit(__QDISC_STATE_MISSED, &q->state);
			else
				__netif_schedule(q);

			break;
		}
	}
}

static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
					      struct sk_buff *skb, struct net_device *dev,
					      bool more)
{
	__this_cpu_write(softnet_data.xmit.more, more);
	return ops->ndo_start_xmit(skb, dev);
}

static const struct net_device_ops igb_netdev_ops = {
	//...
	.ndo_start_xmit		= igb_xmit_frame,
	//...
};

netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
				struct igb_ring *tx_ring)
{
	//...
	tso = igb_tso(tx_ring, first, &hdr_len);
	if (tso < 0)
		goto out_drop;
	else if (!tso)
		igb_tx_csum(tx_ring, first);

	if (igb_tx_map(tx_ring, first, hdr_len))
	//...
}

static int igb_tx_map(struct igb_ring *tx_ring,
		      struct igb_tx_buffer *first,
		      const u8 hdr_len)
{
	struct sk_buff *skb = first->skb;
	struct igb_tx_buffer *tx_buffer;
	union e1000_adv_tx_desc *tx_desc;
	skb_frag_t *frag;
	dma_addr_t dma;
	unsigned int data_len, size;
	u32 tx_flags = first->tx_flags;
	u32 cmd_type = igb_tx_cmd_type(skb, tx_flags);
	u16 i = tx_ring->next_to_use;

	tx_desc = IGB_TX_DESC(tx_ring, i);

	igb_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len);

	size = skb_headlen(skb);
	data_len = skb->data_len;

	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);

	tx_buffer = first;

	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
		if (dma_mapping_error(tx_ring->dev, dma))
			goto dma_error;

		/* record length, and DMA address */
		dma_unmap_len_set(tx_buffer, len, size);
		dma_unmap_addr_set(tx_buffer, dma, dma);

		tx_desc->read.buffer_addr = cpu_to_le64(dma);

		while (unlikely(size > IGB_MAX_DATA_PER_TXD)) {
			tx_desc->read.cmd_type_len =
				cpu_to_le32(cmd_type ^ IGB_MAX_DATA_PER_TXD);

			i++;
			tx_desc++;
			if (i == tx_ring->count) {
				tx_desc = IGB_TX_DESC(tx_ring, 0);
				i = 0;
			}
			tx_desc->read.olinfo_status = 0;

			dma += IGB_MAX_DATA_PER_TXD;
			size -= IGB_MAX_DATA_PER_TXD;

			tx_desc->read.buffer_addr = cpu_to_le64(dma);
		}

		if (likely(!data_len))
			break;

		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size);

		i++;
		tx_desc++;
		if (i == tx_ring->count) {
			tx_desc = IGB_TX_DESC(tx_ring, 0);
			i = 0;
		}
		tx_desc->read.olinfo_status = 0;

		size = skb_frag_size(frag);
		data_len -= size;

		dma = skb_frag_dma_map(tx_ring->dev, frag, 0,
				       size, DMA_TO_DEVICE);

		tx_buffer = &tx_ring->tx_buffer_info[i];
	}

	/* write last descriptor with RS and EOP bits */
	cmd_type |= size | IGB_TXD_DCMD;
	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);

	netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);

	/* set the timestamp */
	first->time_stamp = jiffies;

	skb_tx_timestamp(skb);

	/* Force memory writes to complete before letting h/w know there
	 * are new descriptors to fetch.  (Only applicable for weak-ordered
	 * memory model archs, such as IA-64).
	 *
	 * We also need this memory barrier to make certain all of the
	 * status bits have been updated before next_to_watch is written.
	 */
	dma_wmb();

	/* set next_to_watch value indicating a packet is present */
	first->next_to_watch = tx_desc;

	i++;
	if (i == tx_ring->count)
		i = 0;

	tx_ring->next_to_use = i;

	/* Make sure there is space in the ring for the next send. */
	igb_maybe_stop_tx(tx_ring, DESC_NEEDED);

	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
		writel(i, tx_ring->tail);
	}
	return 0;
	//...
}