Linux socket 摘要(一)

PS：要转载请注明出处，本人版权所有。

PS: 这个只是基于《我自己》的理解，

如果和你的原则及想法相冲突，请谅解，勿喷。

前置说明

  本文作为本人csdn blog的主站的备份。（BlogID=022）

  本文发布于 2016-07-04 16:31:31，现用MarkDown+图床做备份更新。blog原图已丢失，使用csdn所存的图进行更新。（BlogID=022）

环境说明

  无

前言

---

  注意：Linux 一切皆文件

Linux 网络分层

---

注：Linux 网络分层，图片来自于百度图片

Linux 一个socket程序的执行流（结果就是得到一个fd,让我们能够通过fd去操作socket所创建的一个文件对象）

在用户态下：

某程序执行socket(int af, int type, int protocol)

经过系统调用层的实现

在内核态下：

会跳转到内核态执行sys_socket(),下面看其源码

SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
	int retval;
	struct socket *sock;
	int flags;

	/* Check the SOCK_* constants for consistency.  */
	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
	BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK);
	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);

	flags = type & ~SOCK_TYPE_MASK;
	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;
	type &= SOCK_TYPE_MASK;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	retval = sock_create(family, type, protocol, &sock);
	if (retval < 0)
		goto out;

	retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
	if (retval < 0)
		goto out_release;

out:
	/* It may be already another descriptor 8) Not kernel problem. */
	return retval;

out_release:
	sock_release(sock);
	return retval;
}

这里我们注意:函数里面执行了两个函数来完成socket的功能

• sock_create()//创建一个socket
• sock_map_fd()//获得一个标号，并返回这个fd

sock_create()源代码:

static int inet_create(struct net *net, struct socket *sock, int protocol)
{
	struct sock *sk;
	struct inet_protosw *answer;
	struct inet_sock *inet;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
	int try_loading_module = 0;
	int err;

	if (unlikely(!inet_ehash_secret))
		if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
			build_ehash_secret();

	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
lookup_protocol:
	err = -ESOCKTNOSUPPORT;
	rcu_read_lock();

	list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {

		err = 0;
		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		} else {
			/* Check for the two wild cases. */
			if (IPPROTO_IP == protocol) {
				protocol = answer->protocol;
				break;
			}
			if (IPPROTO_IP == answer->protocol)
				break;
		}
		err = -EPROTONOSUPPORT;
	}

	if (unlikely(err)) {
		if (try_loading_module < 2) {
			rcu_read_unlock();
			/*
			 * Be more specific, e.g. net-pf-2-proto-132-type-1
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
			 */
			if (++try_loading_module == 1)
				request_module("net-pf-%d-proto-%d-type-%d",
					       PF_INET, protocol, sock->type);
			/*
			 * Fall back to generic, e.g. net-pf-2-proto-132
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP)
			 */
			else
				request_module("net-pf-%d-proto-%d",
					       PF_INET, protocol);
			goto lookup_protocol;
		} else
			goto out_rcu_unlock;
	}

	err = -EPERM;

	if (answer->capability > 0 && !capable(answer->capability))
		goto out_rcu_unlock;

	err = -EAFNOSUPPORT;

	if (!inet_netns_ok(net, protocol))
		goto out_rcu_unlock;

	sock->ops = answer->ops;

	answer_prot = answer->prot;
	answer_no_check = answer->no_check;
	answer_flags = answer->flags;
	rcu_read_unlock();

	WARN_ON(answer_prot->slab == NULL);

	err = -ENOBUFS;

	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
	if (sk == NULL)
		goto out;

	err = 0;

	sk->sk_no_check = answer_no_check;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = 1;

	inet = inet_sk(sk);

	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;

	if (SOCK_RAW == sock->type) {
		inet->num = protocol;
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

	inet->id = 0;

	sock_init_data(sock, sk);

	sk->sk_destruct	   = inet_sock_destruct;
	sk->sk_protocol	   = protocol;

	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;

	inet->uc_ttl	= -1;
	inet->mc_loop	= 1;
	inet->mc_ttl	= 1;
	inet->mc_all	= 1;
	inet->mc_index	= 0;
	inet->mc_list	= NULL;

	sk_refcnt_debug_inc(sk);

	if (inet->num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
		inet->sport = htons(inet->num);
		/* Add to protocol hash chains. */
		sk->sk_prot->hash(sk);
	}

	if (sk->sk_prot->init) {

		err = sk->sk_prot->init(sk);
		if (err)
			sk_common_release(sk);
	}
out:
	return err;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}

static const struct net_proto_family inet_family_ops = {
    .family = PF_INET,
    .create = inet_create,
    .owner  = THIS_MODULE,
};

这里我们只注意:

• sock_alloc()//创建一个inode(给文件系统管理)，创建一个socket()对象
• pf->create()//若是tcp，则是inet_family_ops中create的值

sock_map_fd()的执行：

• sock_alloc_fd()//获得一个可用的fd
• sock_attach_fd()//把fd,file结构体，socket实例连接起来
• fd_install()//fd添加到pcb

后记

---

对流程的整理：

socket()

• sys_socket()
• sock_create()//创建一个socket
• sock_alloc()//创建一个inode(给文件系统管理)，创建一个socket()对象
• pf->create()//若是tcp，则是inet_family_ops中create的值
• sock_map_fd()//获得一个标号，并返回这个fd

参考文献

• 无

---

打赏、订阅、收藏、丢香蕉、硬币，请关注公众号（攻城狮的搬砖之路）

PS: 请尊重原创，不喜勿喷。

PS: 要转载请注明出处，本人版权所有。

PS: 有问题请留言，看到后我会第一时间回复。