Linux内核学习（3)——socket的创建

通过前面的系统调用，我们就进入socket的内核处理过程。

本节来看socket的创建

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;
}

我们跳过这些不相关的，直接到关键代码

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) {
		static int warned;
		if (!warned) {
			warned = 1;
			pr_info("%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;
}

针对sock = sock_alloc();我们来看具体是怎么回事

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;
}

struct inode *new_inode_pseudo(struct super_block *sb)
{
	struct inode *inode = alloc_inode(sb);

	if (inode) {
		spin_lock(&inode->i_lock);
		inode->i_state = 0;
		spin_unlock(&inode->i_lock);
		INIT_LIST_HEAD(&inode->i_sb_list);
	}
	return inode;
}

可以看到，这里是文件节点的创建，那么它是怎么创建的呢？我们继续看

static int __init sock_init(void)
{
	int err;
	/*
	 *      Initialize the network sysctl infrastructure.
	 */
	err = net_sysctl_init();
	if (err)
		goto out;

	/*
	 *      Initialize skbuff SLAB cache
	 */
	skb_init();

	/*
	 *      Initialize the protocols module.
	 */

	init_inodecache();

	err = register_filesystem(&sock_fs_type);
	if (err)
		goto out_fs;
	sock_mnt = kern_mount(&sock_fs_type);
	if (IS_ERR(sock_mnt)) {
		err = PTR_ERR(sock_mnt);
		goto out_mount;
	}

	/* The real protocol initialization is performed in later initcalls.
	 */

#ifdef CONFIG_NETFILTER
	err = netfilter_init();
	if (err)
		goto out;
#endif

	ptp_classifier_init();

out:
	return err;

out_mount:
	unregister_filesystem(&sock_fs_type);
out_fs:
	goto out;
}

可以i看到，文件系统是这里设置的，每次创建节点就是下面的cache分配的，每次分配的大小是sizeof(struct socket_alloc)

static int init_inodecache(void)
{
    sock_inode_cachep = kmem_cache_create("sock_inode_cache",
                          sizeof(struct socket_alloc),
                          0,
                          (SLAB_HWCACHE_ALIGN |
                           SLAB_RECLAIM_ACCOUNT |
                           SLAB_MEM_SPREAD),
                          init_once);
    if (sock_inode_cachep == NULL)
        return -ENOMEM;
    return 0;
}

 

分配的内容为：

struct socket_alloc {
    struct socket socket;
    struct inode vfs_inode;
};

static const struct super_operations sockfs_ops = {
    .alloc_inode    = sock_alloc_inode,
    .destroy_inode    = sock_destroy_inode,
    .statfs        = simple_statfs,
};

 

static struct inode *sock_alloc_inode(struct super_block *sb)
{
	struct socket_alloc *ei;
	struct socket_wq *wq;

	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	wq = kmalloc(sizeof(*wq), GFP_KERNEL);
	if (!wq) {
		kmem_cache_free(sock_inode_cachep, ei);
		return NULL;
	}
	init_waitqueue_head(&wq->wait);
	wq->fasync_list = NULL;
	wq->flags = 0;
	RCU_INIT_POINTER(ei->socket.wq, wq);

	ei->socket.state = SS_UNCONNECTED;
	ei->socket.flags = 0;
	ei->socket.ops = NULL;
	ei->socket.sk = NULL;
	ei->socket.file = NULL;

	return &ei->vfs_inode;
}

总结一下，这里实际就是创建了文件节点 inode，以及关联的 socket 数据结构，分配的时候是这两者之和，在文件系统那边返回的是inode，处理完了，再用SOCKET_I 这个宏拿到socket的数据结构。

接下来就进入

err = pf->create(net, sock, protocol, kern);

这里我们以 ipv4为例子

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

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;

	if (protocol < 0 || protocol >= IPPROTO_MAX)
		return -EINVAL;

	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 (sock->type == SOCK_RAW && !kern &&
	    !ns_capable(net->user_ns, CAP_NET_RAW))
		goto out_rcu_unlock;

	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;
	}

	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_refcnt_debug_inc(sk);

	if (inet->inet_num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
		inet->inet_sport = htons(inet->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;
}