万字图解 | 深入揭秘Linux 接收网络数据包

static int __igb_open(struct net_device *netdev, bool resuming) 
{
    /* 分配多 TX 队列的内存空间 */
    err = igb_setup_all_tx_resources(adapter);
    /* 分配多 RX 队列的内存空间 */
    err = igb_setup_all_rx_resources(adapter);
    /* 给网卡配置 RX/TX 队列，给 RX 申请 DMA 空间 */
    igb_configure(adapter);
    /* 注册中断处理函数 */
    err = igb_request_irq(adapter);
    /* 打开 NAPI */
    for (i = 0; i < adapter->num_q_vectors; i++)
        napi_enable(&(adapter->q_vector[i]->napi));
    /* 打开硬中断 */
    igb_irq_enable(adapter);
    /* 启动所有 TX 队列 */
    netif_tx_start_all_queues(netdev);
}

int igb_open(struct net_device *netdev) 
{
    return __igb_open(netdev, false); 
}

# 软中断，处理数据包，放进 socket buffer，数据包处理完后，开启硬中断。
__do_softirq
|-- net_rx_action
    |-- igb_poll # 遍历 softnet_data.poll_list
        |-- igb_clean_rx_irq #调用 igb_clean_rx_irq 循环处理数据包，直到处理完
            |-- napi_gro_receive #数据包合并
                |--napi_skb_finish
                   |-- netif_receive_skb
                      |-- ip_rcv #ip层处理数据包
                          |-- tcp_v4_rcv #tcp处理数据包
                              |-- ...

struct e1000_rx_ring {
 /* pointer to the descriptor ring memory */
 void *desc; /* 内存描述符（e1000_rx_desc）数组。 */
 /* physical address of the descriptor ring */
 dma_addr_t dma;
 /* length of descriptor ring in bytes */
 unsigned int size;
 /* number of descriptors in the ring */
 unsigned int count;
 /* next descriptor to associate a buffer with */
 unsigned int next_to_use;
 /* next descriptor to check for DD status bit */
 unsigned int next_to_clean;
 /* array of buffer information structs */
 struct e1000_rx_buffer *buffer_info;
 struct sk_buff *rx_skb_top;

 /* cpu for rx queue */
 int cpu;

 u16 rdh;
 u16 rdt;
};

/* 描述符指向的内存块。*/
struct e1000_rx_buffer {
 union {
  struct page *page; /* jumbo: alloc_page */
  u8 *data; /* else, netdev_alloc_frag */
 } rxbuf;
 dma_addr_t dma;
};

/* Receive Descriptor - 内存描述符。*/
struct e1000_rx_desc {
 __le64 buffer_addr; /* Address of the descriptor's data buffer */
 __le16 length;  /* Length of data DMAed into data buffer */
 __le16 csum;  /* Packet checksum */
 u8 status;  /* Descriptor status */
 u8 errors;  /* Descriptor Errors */
 __le16 special;
};

struct sk_buff_head {
 /* These two members must be first. */
 struct sk_buff *next;
 struct sk_buff *prev;

 __u32  qlen;   //表示链表中的节点数
 spinlock_t lock; //用作多线程同步
};

struct sk_buff {
 union {
  struct {
   /* These two members must be first to match sk_buff_head. */
   struct sk_buff  *next; //后续节点
   struct sk_buff  *prev; //前序节点

   union {
    struct net_device *dev; //记录接受或发送报文的网络设备
    /* Some protocols might use this space to store information,
     * while device pointer would be NULL.
     * UDP receive path is one user.
     */
    unsigned long  dev_scratch;
   };
  };

  struct list_head list; //指向头节点
 };

  union {
  struct sock  *sk; //报文所属的套接字
  int   ip_defrag_offset;
 };

 union {
  ktime_t  tstamp; //报文时间戳
  u64  skb_mstamp_ns; /* earliest departure time */
 };

  __u16   transport_header; //指向传输层协议首部的起始。
 __u16   network_header; //指向网络层协议首部的开始。
 __u16   mac_header; //指向 MAC 协议首部的开始。

  sk_buff_data_t  tail;
 sk_buff_data_t  end;
 unsigned char    *head,*data;

__u16   transport_header; //指向传输层协议首部的起始。
__u16   network_header; //指向网络层协议首部的开始。
__u16   mac_header; //指向 MAC 协议首部的开始。

__u16   transport_header; //指向传输层协议首部的起始。
__u16   network_header; //指向网络层协议首部的开始。
__u16   mac_header; //指向 MAC 协议首部的开始。