TCP IP源码分析

proto结构体

proto定义了传输层的接口，是传输层对不同socket的抽象，比如conncet、close、传输层协议名称、disconnect、accept等接口，可以看下面的注释理解主要的接口。

struct proto {
	void			(*close)(struct sock *sk, 
					long timeout);
					关闭socket连接
	int			(*connect)(struct sock *sk,
				        struct sockaddr *uaddr, 
					int addr_len);
					连接
	int			(*disconnect)(struct sock *sk, int flags);
	关闭连接

	struct sock *		(*accept) (struct sock *sk, int flags, int *err);
	建立三次握手

	int			(*ioctl)(struct sock *sk, int cmd,
					 unsigned long arg);
					 
	int			(*init)(struct sock *sk);
	void			(*destroy)(struct sock *sk);
	void			(*shutdown)(struct sock *sk, int how);
	int			(*setsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval,
					unsigned int optlen);
	int			(*getsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval, 
					int __user *option);  	 
#ifdef CONFIG_COMPAT
	int			(*compat_setsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					unsigned int optlen);
	int			(*compat_getsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int __user *option);
	int			(*compat_ioctl)(struct sock *sk,
					unsigned int cmd, unsigned long arg);
#endif
	int			(*sendmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg, size_t len);
					   发送消息
	int			(*recvmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg,
					size_t len, int noblock, int flags, 
					int *addr_len);
					接受消息
	int			(*sendpage)(struct sock *sk, struct page *page,
					int offset, size_t size, int flags);
					发送一个page
	int			(*bind)(struct sock *sk, 
					struct sockaddr *uaddr, int addr_len);
					绑定ip和port
    
	int			(*backlog_rcv) (struct sock *sk, 
						struct sk_buff *skb);

	/* Keeping track of sk's, looking them up, and port selection methods. */
	void			(*hash)(struct sock *sk);
	void			(*unhash)(struct sock *sk);
	void			(*rehash)(struct sock *sk);
	int			(*get_port)(struct sock *sk, unsigned short snum);
	void			(*clear_sk)(struct sock *sk, int size);

	/* Keeping track of sockets in use */
#ifdef CONFIG_PROC_FS
	unsigned int		inuse_idx;
#endif

	/* Memory pressure */
	void			(*enter_memory_pressure)(struct sock *sk);
	atomic_long_t		*memory_allocated;	/* Current allocated memory. */
	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
	/*
	 * Pressure flag: try to collapse.
	 * Technical note: it is used by multiple contexts non atomically.
	 * All the __sk_mem_schedule() is of this nature: accounting
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	long			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;
	bool			no_autobind;

	struct kmem_cache	*slab;
	unsigned int		obj_size;
	int			slab_flags;

	struct percpu_counter	*orphan_count;

	struct request_sock_ops	*rsk_prot;
	struct timewait_sock_ops *twsk_prot;

	union {
		struct inet_hashinfo	*hashinfo;
		struct udp_table	*udp_table;
		struct raw_hashinfo	*raw_hash;
	} h;

	struct module		*owner;

	char			name[32];
	//协议名称

	struct list_head	node;
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
};

tcp_port

tcp_prot是一个proto类型的实例，记录了tcp连接的接口。

struct proto tcp_prot = {
	.name			= "TCP",
	.owner			= THIS_MODULE,
	.close			= tcp_close,
	.connect		= tcp_v4_connect,
	.disconnect		= tcp_disconnect,
	.accept			= inet_csk_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v4_init_sock,
	.destroy		= tcp_v4_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.recvmsg		= tcp_recvmsg,
	.sendmsg		= tcp_sendmsg,
	.sendpage		= tcp_sendpage,
	.backlog_rcv		= tcp_v4_do_rcv,
	.hash			= inet_hash,
	.unhash			= inet_unhash,
	.get_port		= inet_csk_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.sockets_allocated	= &tcp_sockets_allocated,
	.orphan_count		= &tcp_orphan_count,
	.memory_allocated	= &tcp_memory_allocated,
	.memory_pressure	= &tcp_memory_pressure,
	.sysctl_mem		= sysctl_tcp_mem,
	.sysctl_wmem		= sysctl_tcp_wmem,
	.sysctl_rmem		= sysctl_tcp_rmem,
	.max_header		= MAX_TCP_HEADER,
	.obj_size		= sizeof(struct tcp_sock),
	.slab_flags		= SLAB_DESTROY_BY_RCU,
	.twsk_prot		= &tcp_timewait_sock_ops,
	.rsk_prot		= &tcp_request_sock_ops,
	.h.hashinfo		= &tcp_hashinfo,
	.no_autobind		= true,
#ifdef CONFIG_COMPAT
	.compat_setsockopt	= compat_tcp_setsockopt,
	.compat_getsockopt	= compat_tcp_getsockopt,
#endif
};

RFC 1323: TCP 扩展

这个RFC主要是考虑如何在高带宽和高延迟网络下实现窗口缩放和时间戳。
影响TCP性能的三个方面：

• 窗口尺寸限制：窗口大小 为16bit，说明窗口最大为64KB，可以通过窗口缩放实现。
• 丢包之后恢复
• 往返时间度量（RTO）

窗口缩放

使用Options中的定义方式，把窗口大小从16bit变成32bit，增加了窗口的大小。

TMA（Time Wait Assassination）现象

Time_Wait 状态会被异常终止的状态，在Time_Wait 状态忽略RST段，TCP数据包中有一个RST标志位，表示重新建立连接，收到这个数据包会会导致TCP连接异常终止，因此，在Time_Wait 状态忽略RST段可以解决这个问题。