基于82599网卡的二层网络数据包发送

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

  /*
   * 循环发送qdisc队列中的报文，直到达到了发送阈值，或者队列中的报文发送完毕，
   * 或者时间片到了，其他进程需要使用cpu
   */
  while (qdisc_restart(q, &packets)) {
      /*
       * Ordered by possible occurrence: Postpone processing if
       * 1. we've exceeded packet quota
       * 2. another process needs the CPU;
       */
      quota -= packets;

      /*
       * 如果quota <= 0，说明qdisc队列中仍然有报文没有发送完，这个时候需要触发
       * 软中断，在软中断处理函数中发送剩余报文
       */
      if (quota <= 0 || need_resched()) {
          __netif_schedule(q);
          break;
      }
  }

  qdisc_run_end(q);
}

static __latent_entropy void net_tx_action(struct softirq_action *h)
{
	struct softnet_data *sd = this_cpu_ptr(&softnet_data);

	……
	/*
	 * softnet_data->output_queue链表不为空，说明其中存有数据没有发送完毕的qdisc
	 * 队列，那么这个时候需要调用qdisc_run()尝试将队列中的报文发送出去
	 */
	if (sd->output_queue) {
		struct Qdisc *head;

		local_irq_disable();
		head = sd->output_queue;
		sd->output_queue = NULL;
		sd->output_queue_tailp = &sd->output_queue;
		local_irq_enable();

		while (head) {
			struct Qdisc *q = head;
			spinlock_t *root_lock;

			head = head->next_sched;

			root_lock = qdisc_lock(q);
			spin_lock(root_lock);
			/* We need to make sure head->next_sched is read
			 * before clearing __QDISC_STATE_SCHED
			 */
			smp_mb__before_atomic();
			clear_bit(__QDISC_STATE_SCHED, &q->state);
			qdisc_run(q);
			spin_unlock(root_lock);
		}
	}
}

static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
			       struct ixgbe_ring *tx_ring, int napi_budget)
{
	struct ixgbe_adapter *adapter = q_vector->adapter;
	struct ixgbe_tx_buffer *tx_buffer;
	union ixgbe_adv_tx_desc *tx_desc;
	unsigned int total_bytes = 0, total_packets = 0;
	unsigned int budget = q_vector->tx.work_limit;
   
	/* 获取第一个可以被网卡驱动处理的描述符索引 */
	unsigned int i = tx_ring->next_to_clean;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return true;

	tx_buffer = &tx_ring->tx_buffer_info[i];
	tx_desc = IXGBE_TX_DESC(tx_ring, i);
	i -= tx_ring->count;

	do {

		/*
		 * tx_buffer->next_to_watch保存的是环形队列中第一个没有存放某个报文数据
		 * 的报文发送描述符
		 */
		union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;

		/* if next_to_watch is not set then there is no work pending */
		/*
		 * 如果某个报文发送描述符对应的报文缓冲区的next_to_watch成员没有设置，
		 * 说明这个缓冲区对象并不是某个报文对应的第一个缓冲区(当报文以共享方式
		 * 存放的时候，一个报文可能会对应多个缓冲区)。
		 */
		if (!eop_desc)
			break;

		read_barrier_depends();

		/*
		 * 如果eop_desc描述符对应的dd为没有被设置，说明网卡还没有处理完属于该报文
		 * 对应的所有缓冲区，所以就暂时不处理对应的描述符了，而是要等到属于该报文
		 * 的所有描述符都被网卡处理完了之后才去处理属于该报文的所有描述符
		 */
		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
			break;

		tx_buffer->next_to_watch = NULL;

		total_bytes += tx_buffer->bytecount;
		total_packets += tx_buffer->gso_segs;

		napi_consume_skb(tx_buffer->skb, napi_budget);

		/* 取消skb->data指向内存的dma映射，以让cpu可以使用该块内存 */
		dma_unmap_single(tx_ring->dev,
				 dma_unmap_addr(tx_buffer, dma),
				 dma_unmap_len(tx_buffer, len),
				 DMA_TO_DEVICE);

		tx_buffer->skb = NULL;
		dma_unmap_len_set(tx_buffer, len, 0);

		/* 取消skb中分片数据对应内存的dma映射，以让cpu可以使用该块内存 */
		while (tx_desc != eop_desc) {
			tx_buffer++;
			tx_desc++;
			i++;
			if (unlikely(!i)) {
				i -= tx_ring->count;
				tx_buffer = tx_ring->tx_buffer_info;
				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
			}

			/* unmap any remaining paged data */
			if (dma_unmap_len(tx_buffer, len)) {
				dma_unmap_page(tx_ring->dev,
					       dma_unmap_addr(tx_buffer, dma),
					       dma_unmap_len(tx_buffer, len),
					       DMA_TO_DEVICE);
				dma_unmap_len_set(tx_buffer, len, 0);
			}
		}

		/* move us one more past the eop_desc for start of next pkt */
		tx_buffer++;
		tx_desc++;
		i++;
		if (unlikely(!i)) {
			i -= tx_ring->count;
			tx_buffer = tx_ring->tx_buffer_info;
			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
		}

		/* issue prefetch for next Tx descriptor */
		prefetch(tx_desc);

		/* update budget accounting */
		budget--;
	} while (likely(budget));

	/* 更新环形队列中的next_to_clean */
	i += tx_ring->count;
	tx_ring->next_to_clean = i;
	……

	return !!budget;
}