【Linux 协议栈】（一）socket函数

由UDP 创建socket开始。

int socket(int domain,int type, int protocol)

family：指明了协议族/域，通常AF_INET、AF_INET6、AF_LOCAL等；

type：套接口类型，主要SOCK_STREAM（TCP）、SOCK_DGRAM（UDP）、SOCK_RAW（原始socket）；

protocol：一般取为0。成功时，返回一个小的非负整数值，与文件描述符类似。

AF_INET，AF是一组协议族，在这协议族中细分为V4的INET、V6的INET6、netlink的NETLINK等，区分出各自的专有用途，易于维护

一、sock_create

1、domain域的注册

inet_init()->sock_register()注册PF_INET域

int __sock_create(struct net *net, int family, int type, int protocol,
			 struct socket **res, int kern)
{
	int err;
	struct socket *sock;
	const struct net_proto_family *pf;

	/*
	 *      Check protocol is in range
	 */
	if (family < 0 || family >= NPROTO)
		return -EAFNOSUPPORT;
	if (type < 0 || type >= SOCK_MAX)
		return -EINVAL;

	/*
	 *	Allocate the socket and allow the family to set things up. if
	 *	the protocol is 0, the family is instructed to select an appropriate
	 *	default.
	 */
    /* 申请socket内存 */
	sock = sock_alloc();
	if (!sock) {
		net_warn_ratelimited("socket: no more sockets\n");
		return -ENFILE;	/* Not exactly a match, but its the
				   closest posix thing */
	}

	sock->type = type;

#ifdef CONFIG_MODULES
	/* Attempt to load a protocol module if the find failed.
	 *
	 * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user
	 * requested real, full-featured networking support upon configuration.
	 * Otherwise module support will break!
	 */
	if (rcu_access_pointer(net_families[family]) == NULL)
		request_module("net-pf-%d", family);
#endif
    /* 查找AFINET域 */
	rcu_read_lock();
	pf = rcu_dereference(net_families[family]);
	err = -EAFNOSUPPORT;
	if (!pf)
		goto out_release;
	/* Now protected by module ref count */
	rcu_read_unlock();
    /* 调用AFINET域创建函数 */
	err = pf->create(net, sock, protocol, kern);
	if (err < 0)
		goto out_module_put;


	return 0;

out_module_busy:
	err = -EAFNOSUPPORT;
out_module_put:
	sock->ops = NULL;
	module_put(pf->owner);
out_sock_release:
	sock_release(sock);
	return err;

out_release:
	rcu_read_unlock();
	goto out_sock_release;
}

2、socket内存申请

static struct socket *sock_alloc(void)
{
	struct inode *inode;
	struct socket *sock;

	inode = new_inode_pseudo(sock_mnt->mnt_sb);
	if (!inode)
		return NULL;

	sock = SOCKET_I(inode);

	kmemcheck_annotate_bitfield(sock, type);
	inode->i_ino = get_next_ino();
	inode->i_mode = S_IFSOCK | S_IRWXUGO;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_op = &sockfs_inode_ops;

	this_cpu_add(sockets_in_use, 1);
	return sock;
}

内存创建并不是直接创建struct socket结构大小，而是以socket_alloc结构创建，通过container_of找到socket内存地址

 由于linux套接字是与文件描述符绑定，所以inode要与socket关联申请，这样我们在调用文件系统的系统调用可以找到对应的套接字操作函数

以上是创建承接用户操作的结构struct socket，下面创建核态struct sock。可能是早起只有struct socket 处理用户态和核态的报文数据发送接收，后期发展中区分处理不同的域，造成接口内部复杂，为了兼容多个域处理函数，所以发展出了核态处理对象struct sock

3、inet_create()

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

	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;
	}


	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_flags = answer->flags;
	rcu_read_unlock();

	WARN_ON(!answer_prot->slab);

	err = -ENOBUFS;
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern);
	if (!sk)
		goto out;

	err = 0;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = SK_CAN_REUSE;

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

	inet->nodefrag = 0;

	if (SOCK_RAW == sock->type) {
		inet->inet_num = protocol;
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}
    /* pmtudisc path mtu discover，通过发送df置1的ip报文来探测链路支持的最大mtu */
	if (net->ipv4.sysctl_ip_no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

	inet->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;
	inet->rcv_tos	= 0;
	sk->sk_reuse	=1;

	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;
}

 （1）通过type 找到SOCK_DRAM类的UDP对应的用户对象和核态对象

SOCK_DRAM的注册： 

 

inet_dram_ops-》用户态、udp_prot-》核态

（2）sock 创建

struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
		      struct proto *prot, int kern)
{
	struct sock *sk;
    /* sock创建也不是只创建strcut sock结构，cache创建的是一个大结构，但是首元素是struct sock */
	sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
	if (sk) {
		sk->sk_family = family;
		/*
		 * See comment in struct sock definition to understand
		 * why we need sk_prot_creator -acme
		 */
        /* 记录sock 对应的类 */
		sk->sk_prot = sk->sk_prot_creator = prot;
		sock_lock_init(sk);
		sk->sk_net_refcnt = kern ? 0 : 1;
		if (likely(sk->sk_net_refcnt))
			get_net(net);
		sock_net_set(sk, net);
		sock_vrf_set(sk, net_to_vrf(net));
        /* 初始化litevrf */
        sock_litevrf_set(sk, 0);
		atomic_set(&sk->sk_wmem_alloc, 1);
		sk->sk_h2p_redir_flag = 0;
		 
		sock_update_classid(sk);
		sock_update_netprioidx(sk);
	}

	return sk;
}

sock也不是单独创建struct sock结构。struct sock、struct inet_sock、struct udp_sock三者之间可转换 

 

void sock_init_data(struct socket *sock, struct sock *sk)
{
	skb_queue_head_init(&sk->sk_receive_queue);
	skb_queue_head_init(&sk->sk_write_queue);
	skb_queue_head_init(&sk->sk_error_queue);

	sk->sk_send_head	=	NULL;

	init_timer(&sk->sk_timer);

	sk->sk_allocation	=	GFP_KERNEL;
	sk->sk_rcvbuf		=	sysctl_rmem_default;/* 收发包默认缓冲区64k */
	sk->sk_sndbuf		=	sysctl_wmem_default;
	sk->sk_state		=	TCP_CLOSE;
	sk_set_socket(sk, sock);

	sock_set_flag(sk, SOCK_ZAPPED);

	if (sock) {
		sk->sk_type	=	sock->type;
		sk->sk_wq	=	sock->wq;
		sock->sk	=	sk;
	} else
		sk->sk_wq	=	NULL;

	rwlock_init(&sk->sk_callback_lock);
	lockdep_set_class_and_name(&sk->sk_callback_lock,
			af_callback_keys + sk->sk_family,
			af_family_clock_key_strings[sk->sk_family]);

	sk->sk_state_change	=	sock_def_wakeup;
	sk->sk_data_ready	=	sock_def_readable;
	sk->sk_write_space	=	sock_def_write_space;
	sk->sk_error_report	=	sock_def_error_report;
	sk->sk_destruct		=	sock_def_destruct;

	sk->sk_frag.page	=	NULL;
	sk->sk_frag.offset	=	0;
	sk->sk_peek_off		=	-1;

	sk->sk_peer_pid 	=	NULL;
	sk->sk_peer_cred	=	NULL;
	sk->sk_write_pending	=	0;
	sk->sk_rcvlowat		=	1;
	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;/* 收发包默认超时0 */
	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;

	sk->sk_stamp = ktime_set(-1L, 0);

#ifdef CONFIG_NET_RX_BUSY_POLL
	sk->sk_napi_id		=	0;
	sk->sk_ll_usec		=	sysctl_net_busy_read;
#endif

	sk->sk_max_pacing_rate = ~0U;
	sk->sk_pacing_rate = ~0U;
	sk->sk_incoming_cpu = -1;
	/*
	 * Before updating sk_refcnt, we must commit prior changes to memory
	 * (Documentation/RCU/rculist_nulls.txt for details)
	 */
	smp_wmb();
	atomic_set(&sk->sk_refcnt, 1);
	atomic_set(&sk->sk_drops, 0);
}