socket 源码阅读 - socket

[junnplus]

系统调用 socket(family, type, protocol) 创建一个新 socket，并返回其文件描述符。

// net/socket.c
int __sys_socket(int family, int type, int protocol)
{
	int retval;
	struct socket *sock;
	int flags;

	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)
		return retval;

	return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
}

__sys_socket 中主要有两个函数调用。

• sock_create 函数创建一个新的 socket 指针。
• sock_map_fd 函数为新建的 socket 指针打开一个文件描述符。

[junnplus]

sock_create

// net/socket.c 

/**
 *	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);
}

/**
 *	__sock_create - creates a socket
 *	@net: net namespace
 *	@family: protocol family (AF_INET, ...)
 *	@type: communication type (SOCK_STREAM, ...)
 *	@protocol: protocol (0, ...)
 *	@res: new socket
 *	@kern: boolean for kernel space sockets
 *
 *	Creates a new socket and assigns it to @res, passing through LSM.
 *	Returns 0 or an error. On failure @res is set to %NULL. @kern must
 *	be set to true if the socket resides in kernel space.
 *	This function internally uses GFP_KERNEL.
 */

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;

	...
        // 分配 socket 空间

        // 创建 socket.sock

分配 socket 空间

// net/socket.c - __sock_create
	/*
	 *	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;

sock_alloc() 申请分配 socket 结构空间。

// net/socket.c
/**
 *	sock_alloc - allocate a socket
 *
 *	Allocate a new inode and socket object. The two are bound together
 *	and initialised. The socket is then returned. If we are out of inodes
 *	NULL is returned. This functions uses GFP_KERNEL internally.
 */

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);

	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;

	return sock;
}

sock_mnt 是 socket 网络文件系统的根结点，new_inode_pseudo 函数创建一个新的 inode 节点。 new_inode_pseudo 会通过 sock_mnt->mnt_sb 指向 socket 网络文件系统的超级块来创建一个挂载到 socket 网络文件系统上的 inode。

// fs/inode.c

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

static struct inode *alloc_inode(struct super_block *sb)
{
	const struct super_operations *ops = sb->s_op;
	struct inode *inode;

	if (ops->alloc_inode)
		inode = ops->alloc_inode(sb);
	else
		inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
...
}

sock_mnt->mnt_sb->op->alloc_inode 指向 sock_alloc_inode 函数。

// net/socket.c
static struct inode *sock_alloc_inode(struct super_block *sb)
{
	struct socket_alloc *ei;

	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	init_waitqueue_head(&ei->socket.wq.wait);
	ei->socket.wq.fasync_list = NULL;
	ei->socket.wq.flags = 0;

	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;
}

sock_alloc_inode 函数在 slab 高速缓存的 inode 缓存区直接分配 socket_alloc 结构。

// include/net/sock.h
struct socket_alloc {
	struct socket socket;
	struct inode vfs_inode;
};

socket_alloc 结构体中包含了 socket 和 inode 结构，这两块内存都会被分配，sock_alloc_inode 函数还顺带初始化了 socket 结构，返回 socket_alloc 中的 vfs_inode 结构地址。

所以，后面可以通过内联函数 SOCKET_I 从 inode 指针取得 socket 结构地址。

// include/net/sock.h
static inline struct socket *SOCKET_I(struct inode *inode)
{
	return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
}

// include/linux/kernel.h
#define container_of(ptr, type, member) ({				\
	void *__mptr = (void *)(ptr);					\
	((type *)(__mptr - offsetof(type, member))); })

// tools/include/linux/kernel.h
#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)

创建 socket.sock

上一步创建并初始化 socket 结构，下面开始创建特定网络协议的 sock 结构。

// net/socket.c - __sock_create
...
	rcu_read_lock();
	pf = rcu_dereference(net_families[family]);
	err = -EAFNOSUPPORT;
	if (!pf)
		goto out_release;

	rcu_read_unlock();

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

pf 表示对应的 family 网络协议族结构，从 net_families 中获得。

对于 INET 协议族， pf->create 指向 inet_create 函数。

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

[junnplus]

sock_map_fd

sock_map_fd 将为 socket 打开一个文件，并返回文件描述符 fd。

// net/socket.c
static int sock_map_fd(struct socket *sock, int flags)
{
	struct file *newfile;
	int fd = get_unused_fd_flags(flags);
	if (unlikely(fd < 0)) {
		sock_release(sock);
		return fd;
	}

	newfile = sock_alloc_file(sock, flags, NULL);
	if (!IS_ERR(newfile)) {
		fd_install(fd, newfile);
		return fd;
	}

	put_unused_fd(fd);
	return PTR_ERR(newfile);
}

• get_unused_fd_flags 申请一个文件描述符。
• sock_alloc_file 为 socket 申请一个文件指针。
• fd_install 把 fd 和文件指针建立了关联。

// net/socket.c
/**
 *	sock_alloc_file - Bind a &socket to a &file
 *	@sock: socket
 *	@flags: file status flags
 *	@dname: protocol name
 *
 *	Returns the &file bound with @sock, implicitly storing it
 *	in sock->file. If dname is %NULL, sets to "".
 *	On failure the return is a ERR pointer (see linux/err.h).
 *	This function uses GFP_KERNEL internally.
 */

struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
{
	struct file *file;

	if (!dname)
		dname = sock->sk ? sock->sk->sk_prot_creator->name : "";

	file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
				O_RDWR | (flags & O_NONBLOCK),
				&socket_file_ops);
	if (IS_ERR(file)) {
		sock_release(sock);
		return file;
	}

	sock->file = file;
	file->private_data = sock;
	stream_open(SOCK_INODE(sock), file);
	return file;
}

SOCK_INODE(sock) 是 SOCKET_I 的逆向操作，返回 socket 指针的 inode 结构指针。

alloc_file_pseudo 函数为 inode 申请一个文件指针，并指定该 socket 文件的操作函数。

// net/socket.c
/*
 *	Socket files have a set of 'special' operations as well as the generic file ones. These don't appear
 *	in the operation structures but are done directly via the socketcall() multiplexor.
 */

static const struct file_operations socket_file_ops = {
	.owner =	THIS_MODULE,
	.llseek =	no_llseek,
	.read_iter =	sock_read_iter,
	.write_iter =	sock_write_iter,
	.poll =		sock_poll,
	.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl = compat_sock_ioctl,
#endif
	.mmap =		sock_mmap,
	.release =	sock_close,
	.fasync =	sock_fasync,
	.sendpage =	sock_sendpage,
	.splice_write = generic_splice_sendpage,
	.splice_read =	sock_splice_read,
	.show_fdinfo =	sock_show_fdinfo,
};

之后互相关联 socket 指针和文件指针，并为这个文件指针打开一个流。

[junnplus]

inet_create

// net/ipv4/af_inet.c
/*
 *	Create an inet socket.
 */

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;

        // socket 的状态置为未连接。
	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
lookup_protocol:
	err = -ESOCKTNOSUPPORT;
	rcu_read_lock();
        // 在 inetsw 对应类型的链表中查找符合的 inet_protosw 结构体
	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;
	}
...
        // 设置 socket 的套接口层处理函数集
	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_flags = answer->flags;
	rcu_read_unlock();

	WARN_ON(!answer_prot->slab);

	err = -ENOBUFS;
        // 分配 inet_sock 结构
	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;

        // 初始化 sock
...
}

inet sock 实际上由 sk_alloc 来分配。

// net/core/sock.c
/**
 *	sk_alloc - All socket objects are allocated here
 *	@net: the applicable net namespace
 *	@family: protocol family
 *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *	@prot: struct proto associated with this new sock instance
 *	@kern: is this to be a kernel socket?
 */
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
		      struct proto *prot, int kern)
{
	struct sock *sk;

	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
		 */
		sk->sk_prot = sk->sk_prot_creator = prot;
		sk->sk_kern_sock = kern;
		sock_lock_init(sk);
		sk->sk_net_refcnt = kern ? 0 : 1;
		if (likely(sk->sk_net_refcnt)) {
			get_net(net);
			sock_inuse_add(net, 1);
		}

		sock_net_set(sk, net);
		refcount_set(&sk->sk_wmem_alloc, 1);

		mem_cgroup_sk_alloc(sk);
		cgroup_sk_alloc(&sk->sk_cgrp_data);
		sock_update_classid(&sk->sk_cgrp_data);
		sock_update_netprioidx(&sk->sk_cgrp_data);
	}

	return sk;
}

static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
		int family)
{
	struct sock *sk;
	struct kmem_cache *slab;

	slab = prot->slab;
	if (slab != NULL) {
		sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
		if (!sk)
			return sk;
		if (want_init_on_alloc(priority))
			sk_prot_clear_nulls(sk, prot->obj_size);
	} else
		sk = kmalloc(prot->obj_size, priority);

	if (sk != NULL) {
		if (security_sk_alloc(sk, family, priority))
			goto out_free;

		if (!try_module_get(prot->owner))
			goto out_free_sec;
		sk_tx_queue_clear(sk);
	}

	return sk;

out_free_sec:
	security_sk_free(sk);
out_free:
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	return NULL;
}