从linux源码看socket的阻塞和非阻塞 顶

// 创建socket
int sock_fd = socket(AF_INET, SOCK_STREAM, 0);
...
// 更改socket为nonblock
fcntl(sock_fd, F_SETFL, fdflags | O_NONBLOCK);
// connect
....
while(1)  {  
    int recvlen = recv(sock_fd, recvbuf, RECV_BUF_SIZE) ; 
    ......
} 
...

socket(AF_INET, SOCK_STREAM, 0)
	|->sys_socket 进入系统调用
		|->sock_create
			|->__sock_create

const struct net_proto_family *pf;
// RCU(Read-Copy Update)是linux的一种内核同步方法，在此不阐述
// family=INET
pf = rcu_dereference(net_families[family]);
err = pf->create(net, sock, protocol);

inet_create(struct net *net, struct socket *sock, int protocol){
	Sock* sock;
	......
	// 此处是寻找对应协议处理器的过程
lookup_protocol:
	// 迭代寻找protocol==answer->protocol的情况
	list_for_each_rcu(p, &inetsw[sock->type]) answer = list_entry(p, struct inet_protosw, list);

		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		}
	......
	// 这边answer指的是SOCK_STREAM
	sock->ops = answer->ops;
	answer_no_check = answer->no_check;
	// 这边sk->prot就是answer_prot=>tcp_prot
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
	sock_init_data(sock, sk);
	......
}

static struct inet_protosw inetsw_array[] =
{
	{
		.type =       SOCK_STREAM,
		.protocol =   IPPROTO_TCP,
		.prot =       &tcp_prot,
		.ops =        &inet_stream_ops,
		.capability = -1,
		.no_check =   0,
		.flags =      INET_PROTOSW_PERMANENT |
			      INET_PROTOSW_ICSK,
	},
	......
}

const struct proto_ops inet_stream_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	......
	.sendmsg	   = tcp_sendmsg,
	.recvmsg	   = sock_common_recvmsg,
	......
}	

struct proto tcp_prot = {
	.name			= "TCP",
	.close			= tcp_close,
	.connect		= tcp_v4_connect,
	.disconnect		= tcp_disconnect,
	.accept			= inet_csk_accept,
	......
	// 我们重点考察tcp的读
	.recvmsg		= tcp_recvmsg,
	......
}

fcntl(sock_fd, F_SETFL, fdflags | O_NONBLOCK);
	|->setfl

static int setfl(int fd, struct file * filp, unsigned long arg) {
	......
	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
	......
}

socket.recv
	|->sys_recv
		|->sys_recvfrom
			|->sock_recvmsg
				|->__sock_recvmsg
					|->sock->ops->recvmsg

	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;

int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
			struct msghdr *msg, size_t size, int flags) {
	......
	// 如果flags的MSG_DONTWAIT标识置位，则传给recvmsg的第5个参数为正,否则为0
	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
				   flags & ~MSG_DONTWAIT, &addr_len);
	.....				   
}

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len)

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len){
	......	
	// copied是指向用户空间拷贝了多少字节，即读了多少
	int copied;
	// target指的是期望多少字节
	int target;
	// 等效为timo = nonblock ? 0 : sk->sk_rcvtimeo;
	timeo = sock_rcvtimeo(sk, nonblock);
	......	
	// 如果设置了MSG_WAITALL标识target=需要读的长度
	// 如果未设置，则为最低低水位值
	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
	......

	do{
		// 表明读到数据
		if (copied) {
			// 注意，这边只要!timeo，即nonblock设置了就会跳出循环
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current) ||
			    (flags & MSG_PEEK))
			break;
		}else{
			// 到这里，表明没有读到任何数据
			// 且nonblock设置了导致timeo=0，则返回-EAGAIN,符合我们的预期
			if (!timeo) {
				copied = -EAGAIN;
				break;
		}
		// 这边如果堵到了期望的数据，继续，否则当前进程阻塞在sk_wait_data上
		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			release_sock(sk);
			lock_sock(sk);
		} else
			sk_wait_data(sk, &timeo);
	} while (len > 0);		
	......
	return copied
}

	// 将进程状态设置为可打断INTERRUPTIBLE
	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	// 通过调用schedule_timeout让出CPU，然后进行睡眠
	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
	// 到这里的时候，有网络事件或超时事件唤醒了此进程，继续运行
	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	finish_wait(sk->sk_sleep, &wait);

next_rx_action
	|-process_backlog
		......
			|->packet_type->func 在这里我们考虑ip_rcv
					|->ipprot->handler 在这里ipprot重载为tcp_protocol
						(handler 即为tcp_v4_rcv)					

tcp_input.c
tcp_v4_rcv
	|-tcp_v4_do_rcv
		|-tcp_rcv_state_process
			|-tcp_data_queue
				|-sk->sk_data_ready=sock_def_readable
					|-wake_up_interruptible
						|-__wake_up
							|-__wake_up_common

fastcall signed long __sched schedule_timeout(signed long timeout) {
	......
	// 设定超时的回掉函数为process_timeout
	setup_timer(&timer, process_timeout, (unsigned long)current);
	__mod_timer(&timer, expire);
	// 这边让出CPU
	schedule();
	del_singleshot_timer_sync(&timer);
	timeout = expire - jiffies;
 out:
 	// 返回经过了多长事件
	return timeout < 0 ? 0 : timeout;	
}

static void process_timeout(unsigned long __data)
{
	wake_up_process((struct task_struct *)__data);
}