Linux内核协议栈-一个socket的调用过程，从用户态接口到底层硬件

用户创建socket

调用内核__sock_create

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;

	/* Compatibility.

	   This uglymoron is moved from INET layer to here to avoid
	   deadlock in module load.
	 */
	if (family == PF_INET && type == SOCK_PACKET) {
		pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n",
			     current->comm);
		family = PF_PACKET;
	}

	err = security_socket_create(family, type, protocol, kern);
	if (err)
		return err;

	/*
	 *	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.
	 */
	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

	rcu_read_lock();
	pf = rcu_dereference(net_families[family]);
	err = -EAFNOSUPPORT;
	if (!pf)
		goto out_release;

	/*
	 * We will call the ->create function, that possibly is in a loadable
	 * module, so we have to bump that loadable module refcnt first.
	 */
	if (!try_module_get(pf->owner))
		goto out_release;

	/* Now protected by module ref count */
	rcu_read_unlock();

	err = pf->create(net, sock, protocol, kern);
	if (err < 0)
		goto out_module_put;

	/*
	 * Now to bump the refcnt of the [loadable] module that owns this
	 * socket at sock_release time we decrement its refcnt.
	 */
	if (!try_module_get(sock->ops->owner))
		goto out_module_busy;

	/*
	 * Now that we're done with the ->create function, the [loadable]
	 * module can have its refcnt decremented
	 */
	module_put(pf->owner);
	err = security_socket_post_create(sock, family, type, protocol, kern);
	if (err)
		goto out_sock_release;
	*res = sock;

	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;
}
EXPORT_SYMBOL(__sock_create);

/**
 *	sock_create - creates a socket
 *	@family: protocol family (AF_INET, ...)
 *	@type: communication type (SOCK_STREAM, ...)
 *	@protocol: protocol (0, ...)
 *	@res: new socket
 *
 *	A wrapper around __sock_create().
 *	Returns 0 or an error. This function internally uses GFP_KERNEL.
 */

int sock_create(int family, int type, int protocol, struct socket **res)
{
	return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
}
EXPORT_SYMBOL(sock_create);

利用sock_ioctl控制socket

static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
	struct socket *sock;
	struct sock *sk;
	void __user *argp = (void __user *)arg;
	int pid, err;
	struct net *net;

	sock = file->private_data;
	sk = sock->sk;
	net = sock_net(sk);
	if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) {
		struct ifreq ifr;
		bool need_copyout;
		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
			return -EFAULT;
		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
		if (!err && need_copyout)
			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
				return -EFAULT;
	} else
#ifdef CONFIG_WEXT_CORE
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
		err = wext_handle_ioctl(net, cmd, argp);
	} else
#endif
		switch (cmd) {
		case FIOSETOWN:
		case SIOCSPGRP:
			err = -EFAULT;
			if (get_user(pid, (int __user *)argp))
				break;
			err = f_setown(sock->file, pid, 1);
			break;
		case FIOGETOWN:
		case SIOCGPGRP:
			err = put_user(f_getown(sock->file),
				       (int __user *)argp);
			break;
		case SIOCGIFBR:
		case SIOCSIFBR:
		case SIOCBRADDBR:
		case SIOCBRDELBR:
			err = -ENOPKG;
			if (!br_ioctl_hook)
				request_module("bridge");

			mutex_lock(&br_ioctl_mutex);
			if (br_ioctl_hook)
				err = br_ioctl_hook(net, cmd, argp);
			mutex_unlock(&br_ioctl_mutex);
			break;
		case SIOCGIFVLAN:
		case SIOCSIFVLAN:
			err = -ENOPKG;
			if (!vlan_ioctl_hook)
				request_module("8021q");

			mutex_lock(&vlan_ioctl_mutex);
			if (vlan_ioctl_hook)
				err = vlan_ioctl_hook(net, argp);
			mutex_unlock(&vlan_ioctl_mutex);
			break;
		case SIOCADDDLCI:
		case SIOCDELDLCI:
			err = -ENOPKG;
			if (!dlci_ioctl_hook)
				request_module("dlci");

			mutex_lock(&dlci_ioctl_mutex);
			if (dlci_ioctl_hook)
				err = dlci_ioctl_hook(cmd, argp);
			mutex_unlock(&dlci_ioctl_mutex);
			break;
		case SIOCGSKNS:
			err = -EPERM;
			if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
				break;

			err = open_related_ns(&net->ns, get_net_ns);
			break;
		case SIOCGSTAMP_OLD:
		case SIOCGSTAMPNS_OLD:
			if (!sock->ops->gettstamp) {
				err = -ENOIOCTLCMD;
				break;
			}
			err = sock->ops->gettstamp(sock, argp,
						   cmd == SIOCGSTAMP_OLD,
						   !IS_ENABLED(CONFIG_64BIT));
			break;
		case SIOCGSTAMP_NEW:
		case SIOCGSTAMPNS_NEW:
			if (!sock->ops->gettstamp) {
				err = -ENOIOCTLCMD;
				break;
			}
			err = sock->ops->gettstamp(sock, argp,
						   cmd == SIOCGSTAMP_NEW,
						   false);
			break;
		default:
			err = sock_do_ioctl(net, sock, cmd, arg);
			break;
		}
	return err;
}

虚拟层inet协议族的创建inet_create

static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
	struct socket *sock;
	struct sock *sk;
	void __user *argp = (void __user *)arg;
	int pid, err;
	struct net *net;

	sock = file->private_data;
	sk = sock->sk;
	net = sock_net(sk);
	if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) {
		struct ifreq ifr;
		bool need_copyout;
		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
			return -EFAULT;
		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
		if (!err && need_copyout)
			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
				return -EFAULT;
	} else
#ifdef CONFIG_WEXT_CORE
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
		err = wext_handle_ioctl(net, cmd, argp);
	} else
#endif
		switch (cmd) {
		case FIOSETOWN:
		case SIOCSPGRP:
			err = -EFAULT;
			if (get_user(pid, (int __user *)argp))
				break;
			err = f_setown(sock->file, pid, 1);
			break;
		case FIOGETOWN:
		case SIOCGPGRP:
			err = put_user(f_getown(sock->file),
				       (int __user *)argp);
			break;
		case SIOCGIFBR:
		case SIOCSIFBR:
		case SIOCBRADDBR:
		case SIOCBRDELBR:
			err = -ENOPKG;
			if (!br_ioctl_hook)
				request_module("bridge");

			mutex_lock(&br_ioctl_mutex);
			if (br_ioctl_hook)
				err = br_ioctl_hook(net, cmd, argp);
			mutex_unlock(&br_ioctl_mutex);
			break;
		case SIOCGIFVLAN:
		case SIOCSIFVLAN:
			err = -ENOPKG;
			if (!vlan_ioctl_hook)
				request_module("8021q");

			mutex_lock(&vlan_ioctl_mutex);
			if (vlan_ioctl_hook)
				err = vlan_ioctl_hook(net, argp);
			mutex_unlock(&vlan_ioctl_mutex);
			break;
		case SIOCADDDLCI:
		case SIOCDELDLCI:
			err = -ENOPKG;
			if (!dlci_ioctl_hook)
				request_module("dlci");

			mutex_lock(&dlci_ioctl_mutex);
			if (dlci_ioctl_hook)
				err = dlci_ioctl_hook(cmd, argp);
			mutex_unlock(&dlci_ioctl_mutex);
			break;
		case SIOCGSKNS:
			err = -EPERM;
			if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
				break;

			err = open_related_ns(&net->ns, get_net_ns);
			break;
		case SIOCGSTAMP_OLD:
		case SIOCGSTAMPNS_OLD:
			if (!sock->ops->gettstamp) {
				err = -ENOIOCTLCMD;
				break;
			}
			err = sock->ops->gettstamp(sock, argp,
						   cmd == SIOCGSTAMP_OLD,
						   !IS_ENABLED(CONFIG_64BIT));
			break;
		case SIOCGSTAMP_NEW:
		case SIOCGSTAMPNS_NEW:
			if (!sock->ops->gettstamp) {
				err = -ENOIOCTLCMD;
				break;
			}
			err = sock->ops->gettstamp(sock, argp,
						   cmd == SIOCGSTAMP_NEW,
						   false);
			break;
		default:
			err = sock_do_ioctl(net, sock, cmd, arg);
			break;
		}
	return err;
}

其中协议族的结构proto_ops结构如下

struct proto_ops {
	int		family;
	struct module	*owner;
	int		(*release)   (struct socket *sock);
	int		(*bind)	     (struct socket *sock,
				      struct sockaddr *myaddr,
				      int sockaddr_len);
	int		(*connect)   (struct socket *sock,
				      struct sockaddr *vaddr,
				      int sockaddr_len, int flags);
	int		(*socketpair)(struct socket *sock1,
				      struct socket *sock2);
	int		(*accept)    (struct socket *sock,
				      struct socket *newsock, int flags, bool kern);
	int		(*getname)   (struct socket *sock,
				      struct sockaddr *addr,
				      int peer);
	__poll_t	(*poll)	     (struct file *file, struct socket *sock,
				      struct poll_table_struct *wait);
	int		(*ioctl)     (struct socket *sock, unsigned int cmd,
				      unsigned long arg);
#ifdef CONFIG_COMPAT
	int	 	(*compat_ioctl) (struct socket *sock, unsigned int cmd,
				      unsigned long arg);
#endif
	int		(*gettstamp) (struct socket *sock, void __user *userstamp,
				      bool timeval, bool time32);
	int		(*listen)    (struct socket *sock, int len);
	int		(*shutdown)  (struct socket *sock, int flags);
	int		(*setsockopt)(struct socket *sock, int level,
				      int optname, char __user *optval, unsigned int optlen);
	int		(*getsockopt)(struct socket *sock, int level,
				      int optname, char __user *optval, int __user *optlen);
#ifdef CONFIG_COMPAT
	int		(*compat_setsockopt)(struct socket *sock, int level,
				      int optname, char __user *optval, unsigned int optlen);
	int		(*compat_getsockopt)(struct socket *sock, int level,
				      int optname, char __user *optval, int __user *optlen);
#endif
	void		(*show_fdinfo)(struct seq_file *m, struct socket *sock);
	int		(*sendmsg)   (struct socket *sock, struct msghdr *m,
				      size_t total_len);
	/* Notes for implementing recvmsg:
	 * ===============================
	 * msg->msg_namelen should get updated by the recvmsg handlers
	 * iff msg_name != NULL. It is by default 0 to prevent
	 * returning uninitialized memory to user space.  The recvfrom
	 * handlers can assume that msg.msg_name is either NULL or has
	 * a minimum size of sizeof(struct sockaddr_storage).
	 */
	int		(*recvmsg)   (struct socket *sock, struct msghdr *m,
				      size_t total_len, int flags);
	int		(*mmap)	     (struct file *file, struct socket *sock,
				      struct vm_area_struct * vma);
	ssize_t		(*sendpage)  (struct socket *sock, struct page *page,
				      int offset, size_t size, int flags);
	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
	int		(*set_peek_off)(struct sock *sk, int val);
	int		(*peek_len)(struct socket *sock);

	/* The following functions are called internally by kernel with
	 * sock lock already held.
	 */
	int		(*read_sock)(struct sock *sk, read_descriptor_t *desc,
				     sk_read_actor_t recv_actor);
	int		(*sendpage_locked)(struct sock *sk, struct page *page,
					   int offset, size_t size, int flags);
	int		(*sendmsg_locked)(struct sock *sk, struct msghdr *msg,
					  size_t size);
	int		(*set_rcvlowat)(struct sock *sk, int val);
};

 其包含的functions和struct proto很类似，但是其在socket层

上图来源：https://blog.csdn.net/feiwatson/article/details/82785697

接下来分为字节流（TCP）和数据报（UDP），二者结构分别为：

const struct proto_ops inet_stream_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,
	.poll		   = tcp_poll,
	.ioctl		   = inet_ioctl,
	.gettstamp	   = sock_gettstamp,
	.listen		   = inet_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = inet_recvmsg,
#ifdef CONFIG_MMU
	.mmap		   = tcp_mmap,
#endif
	.sendpage	   = inet_sendpage,
	.splice_read	   = tcp_splice_read,
	.read_sock	   = tcp_read_sock,
	.sendmsg_locked    = tcp_sendmsg_locked,
	.sendpage_locked   = tcp_sendpage_locked,
	.peek_len	   = tcp_peek_len,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
	.compat_ioctl	   = inet_compat_ioctl,
#endif
	.set_rcvlowat	   = tcp_set_rcvlowat,
};
EXPORT_SYMBOL(inet_stream_ops);

const struct proto_ops inet_dgram_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = udp_poll,
	.ioctl		   = inet_ioctl,
	.gettstamp	   = sock_gettstamp,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = inet_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
	.set_peek_off	   = sk_set_peek_off,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
	.compat_ioctl	   = inet_compat_ioctl,
#endif
};
EXPORT_SYMBOL(inet_dgram_ops);

以数据报（UDP）为例，结构udp_prot结构如下：

struct proto udp_prot = {
	.name			= "UDP",
	.owner			= THIS_MODULE,
	.close			= udp_lib_close,
	.pre_connect		= udp_pre_connect,
	.connect		= ip4_datagram_connect,
	.disconnect		= udp_disconnect,
	.ioctl			= udp_ioctl,
	.init			= udp_init_sock,
	.destroy		= udp_destroy_sock,
	.setsockopt		= udp_setsockopt,
	.getsockopt		= udp_getsockopt,
	.sendmsg		= udp_sendmsg,
	.recvmsg		= udp_recvmsg,
	.sendpage		= udp_sendpage,
	.release_cb		= ip4_datagram_release_cb,
	.hash			= udp_lib_hash,
	.unhash			= udp_lib_unhash,
	.rehash			= udp_v4_rehash,
	.get_port		= udp_v4_get_port,
	.memory_allocated	= &udp_memory_allocated,
	.sysctl_mem		= sysctl_udp_mem,
	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_udp_wmem_min),
	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_udp_rmem_min),
	.obj_size		= sizeof(struct udp_sock),
	.h.udp_table		= &udp_table,
#ifdef CONFIG_COMPAT
	.compat_setsockopt	= compat_udp_setsockopt,
	.compat_getsockopt	= compat_udp_getsockopt,
#endif
	.diag_destroy		= udp_abort,
};
EXPORT_SYMBOL(udp_prot);

tcp_prot结构如下：

struct proto tcp_prot = {
	.name			= "TCP",
	.owner			= THIS_MODULE,
	.close			= tcp_close,
	.pre_connect		= tcp_v4_pre_connect,
	.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,
	.keepalive		= tcp_set_keepalive,
	.recvmsg		= tcp_recvmsg,
	.sendmsg		= tcp_sendmsg,
	.sendpage		= tcp_sendpage,
	.backlog_rcv		= tcp_v4_do_rcv,
	.release_cb		= tcp_release_cb,
	.hash			= inet_hash,
	.unhash			= inet_unhash,
	.get_port		= inet_csk_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.leave_memory_pressure	= tcp_leave_memory_pressure,
	.stream_memory_free	= tcp_stream_memory_free,
	.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_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
	.max_header		= MAX_TCP_HEADER,
	.obj_size		= sizeof(struct tcp_sock),
	.slab_flags		= SLAB_TYPESAFE_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
	.diag_destroy		= tcp_abort,
};
EXPORT_SYMBOL(tcp_prot);

其具体对应的钩子函数（回调函数）结构如下图所示：

经过一系列关系，最终进入网络接口层，改成负责完成网络驱动的功能，然后就进入额具体的网络设备。