socket.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

/*
 * NET		An implementation of the SOCKET network access protocol.
 *
 * Version:	@(#)socket.c	1.1.93	18/02/95
 *
 * Authors:	Orest Zborowski, <[e-mail]>
 *		Ross Biro, <[e-mail]>
 *		Fred N. van Kempen, <[e-mail]>
 *
 * Fixes:
 *		Anonymous	:	NOTSOCK/BADF cleanup. Error fix in
 *					shutdown()
 *		Alan Cox	:	verify_area() fixes
 *		Alan Cox	:	Removed DDI
 *		Jonathan Kamens	:	SOCK_DGRAM reconnect bug
 *		Alan Cox	:	Moved a load of checks to the very
 *					top level.
 *		Alan Cox	:	Move address structures to/from user
 *					mode above the protocol layers.
 *		Rob Janssen	:	Allow 0 length sends.
 *		Alan Cox	:	Asynchronous I/O support (cribbed from the
 *					tty drivers).
 *		Niibe Yutaka	:	Asynchronous I/O for writes (4.4BSD style)
 *		Jeff Uphoff	:	Made max number of sockets command-line
 *					configurable.
 *		Matti Aarnio	:	Made the number of sockets dynamic,
 *					to be allocated when needed, and mr.
 *					Uphoff's max is used as max to be
 *					allowed to allocate.
 *		Linus		:	Argh. removed all the socket allocation
 *					altogether: it's in the inode now.
 *		Alan Cox	:	Made sock_alloc()/sock_release() public
 *					for NetROM and future kernel nfsd type
 *					stuff.
 *		Alan Cox	:	sendmsg/recvmsg basics.
 *		Tom Dyas	:	Export net symbols.
 *		Marcin Dalecki	:	Fixed problems with CONFIG_NET="n".
 *		Alan Cox	:	Added thread locking to sys_* calls
 *					for sockets. May have errors at the
 *					moment.
 *		Kevin Buhr	:	Fixed the dumb errors in the above.
 *		Andi Kleen	:	Some small cleanups, optimizations,
 *					and fixed a copy_from_user() bug.
 *		Tigran Aivazian	:	sys_send(args) calls sys_sendto(args, NULL, 0)
 *		Tigran Aivazian	:	Made listen(2) backlog sanity checks 
 *					protocol-independent
 *
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 *
 *	This module is effectively the top level interface to the BSD socket
 *	paradigm. 
 *
 */

#include <linux/config.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/net.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/wanrouter.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/highmem.h>

#if defined(CONFIG_KMOD) && defined(CONFIG_NET)
#include <linux/kmod.h>
#endif

#include <asm/uaccess.h>

#include <net/sock.h>
#include <net/scm.h>
#include <linux/netfilter.h>

static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
static loff_t sock_lseek(struct file *file, loff_t offset, int whence);
static ssize_t sock_read(struct file *file, char *buf,
			 size_t size, loff_t *ppos);
static ssize_t sock_write(struct file *file, const char *buf,
			  size_t size, loff_t *ppos);
static int sock_mmap(struct file *file, struct vm_area_struct * vma);

static int sock_close(struct inode *inode, struct file *file);
static unsigned int sock_poll(struct file *file,
			      struct poll_table_struct *wait);
static int sock_ioctl(struct inode *inode, struct file *file,
		      unsigned int cmd, unsigned long arg);
static int sock_fasync(int fd, struct file *filp, int on);
static ssize_t sock_readv(struct file *file, const struct iovec *vector,
			  unsigned long count, loff_t *ppos);
static ssize_t sock_writev(struct file *file, const struct iovec *vector,
			  unsigned long count, loff_t *ppos);
static ssize_t sock_sendpage(struct file *file, struct page *page,
			     int offset, size_t size, loff_t *ppos, int more);


/*
 *	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 struct file_operations socket_file_ops = {
	llseek:		sock_lseek,
	read:		sock_read,
	write:		sock_write,
	poll:		sock_poll,
	ioctl:		sock_ioctl,
	mmap:		sock_mmap,
	open:		sock_no_open,	/* special open code to disallow open via /proc */
	release:	sock_close,
	fasync:		sock_fasync,
	readv:		sock_readv,
	writev:		sock_writev,
	sendpage:	sock_sendpage
};

/*
 *	The protocol list. Each protocol is registered in here.
 */

static struct net_proto_family *net_families[NPROTO];

#ifdef CONFIG_SMP
static atomic_t net_family_lockct = ATOMIC_INIT(0);
static spinlock_t net_family_lock = SPIN_LOCK_UNLOCKED;

/* The strategy is: modifications net_family vector are short, do not
   sleep and veeery rare, but read access should be free of any exclusive
   locks.
 */

static void net_family_write_lock(void)
{
	spin_lock(&net_family_lock);
	while (atomic_read(&net_family_lockct) != 0) {
		spin_unlock(&net_family_lock);

		current->policy |= SCHED_YIELD;
		schedule();

		spin_lock(&net_family_lock);
	}
}

static __inline__ void net_family_write_unlock(void)
{
	spin_unlock(&net_family_lock);
}

static __inline__ void net_family_read_lock(void)
{
	atomic_inc(&net_family_lockct);
	spin_unlock_wait(&net_family_lock);
}

static __inline__ void net_family_read_unlock(void)
{
	atomic_dec(&net_family_lockct);
}

#else
#define net_family_write_lock() do { } while(0)
#define net_family_write_unlock() do { } while(0)
#define net_family_read_lock() do { } while(0)
#define net_family_read_unlock() do { } while(0)
#endif


/*
 *	Statistics counters of the socket lists
 */

static union {
	int	counter;
	char	__pad[SMP_CACHE_BYTES];
} sockets_in_use[NR_CPUS] __cacheline_aligned = {{0}};

/*
 *	Support routines. Move socket addresses back and forth across the kernel/user
 *	divide and look after the messy bits.
 */

#define MAX_SOCK_ADDR	128		/* 108 for Unix domain - 
					   16 for IP, 16 for IPX,
					   24 for IPv6,
					   about 80 for AX.25 
					   must be at least one bigger than
					   the AF_UNIX size (see net/unix/af_unix.c
					   :unix_mkname()).  
					 */
					 
/**
 *	move_addr_to_kernel	-	copy a socket address into kernel space
 *	@uaddr: Address in user space
 *	@kaddr: Address in kernel space
 *	@ulen: Length in user space
 *
 *	The address is copied into kernel space. If the provided address is
 *	too long an error code of -EINVAL is returned. If the copy gives
 *	invalid addresses -EFAULT is returned. On a success 0 is returned.
 */

int move_addr_to_kernel(void *uaddr, int ulen, void *kaddr)
{
	if(ulen<0||ulen>MAX_SOCK_ADDR)
		return -EINVAL;
	if(ulen==0)
		return 0;
	if(copy_from_user(kaddr,uaddr,ulen))
		return -EFAULT;
	return 0;
}

/**
 *	move_addr_to_user	-	copy an address to user space
 *	@kaddr: kernel space address
 *	@klen: length of address in kernel
 *	@uaddr: user space address
 *	@ulen: pointer to user length field
 *
 *	The value pointed to by ulen on entry is the buffer length available.
 *	This is overwritten with the buffer space used. -EINVAL is returned
 *	if an overlong buffer is specified or a negative buffer size. -EFAULT
 *	is returned if either the buffer or the length field are not
 *	accessible.
 *	After copying the data up to the limit the user specifies, the true
 *	length of the data is written over the length limit the user
 *	specified. Zero is returned for a success.
 */
 
int move_addr_to_user(void *kaddr, int klen, void *uaddr, int *ulen)
{
	int err;
	int len;

	if((err=get_user(len, ulen)))
		return err;
	if(len>klen)
		len=klen;
	if(len<0 || len> MAX_SOCK_ADDR)
		return -EINVAL;
	if(len)
	{
		if(copy_to_user(uaddr,kaddr,len))
			return -EFAULT;
	}
	/*
	 *	"fromlen shall refer to the value before truncation.."
	 *			1003.1g
	 */
	return __put_user(klen, ulen);
}

#define SOCKFS_MAGIC 0x534F434B
static int sockfs_statfs(struct super_block *sb, struct statfs *buf)
{
	buf->f_type = SOCKFS_MAGIC;
	buf->f_bsize = 1024;
	buf->f_namelen = 255;
	return 0;
}

static struct super_operations sockfs_ops = {
	statfs:		sockfs_statfs,
};

static struct super_block * sockfs_read_super(struct super_block *sb, void *data, int silent)
{
	struct inode *root = new_inode(sb);
	if (!root)
		return NULL;
	root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR;
	root->i_uid = root->i_gid = 0;
	root->i_atime = root->i_mtime = root->i_ctime = CURRENT_TIME;
	sb->s_blocksize = 1024;
	sb->s_blocksize_bits = 10;
	sb->s_magic = SOCKFS_MAGIC;
	sb->s_op	= &sockfs_ops;
	sb->s_root = d_alloc(NULL, &(const struct qstr) { "socket:", 7, 0 });
	if (!sb->s_root) {
		iput(root);
		return NULL;
	}
	sb->s_root->d_sb = sb;
	sb->s_root->d_parent = sb->s_root;
	d_instantiate(sb->s_root, root);
	return sb;
}

static struct vfsmount *sock_mnt;
static DECLARE_FSTYPE(sock_fs_type, "sockfs", sockfs_read_super, FS_NOMOUNT);
static int sockfs_delete_dentry(struct dentry *dentry)
{
	return 1;
}
static struct dentry_operations sockfs_dentry_operations = {
	d_delete:	sockfs_delete_dentry,
};

/*
 *	Obtains the first available file descriptor and sets it up for use.
 *
 *	This functions creates file structure and maps it to fd space
 *	of current process. On success it returns file descriptor
 *	and file struct implicitly stored in sock->file.
 *	Note that another thread may close file descriptor before we return
 *	from this function. We use the fact that now we do not refer
 *	to socket after mapping. If one day we will need it, this
 *	function will inincrement ref. count on file by 1.
 *
 *	In any case returned fd MAY BE not valid!
 *	This race condition is inavoidable
 *	with shared fd spaces, we cannot solve is inside kernel,
 *	but we take care of internal coherence yet.
 */

static int sock_map_fd(struct socket *sock)
{
	int fd;
	struct qstr this;
	char name[32];

	/*
	 *	Find a file descriptor suitable for return to the user. 
	 */

	fd = get_unused_fd();
	if (fd >= 0) {
		struct file *file = get_empty_filp();

		if (!file) {
			put_unused_fd(fd);
			fd = -ENFILE;
			goto out;
		}

		sprintf(name, "[%lu]", sock->inode->i_ino);
		this.name = name;
		this.len = strlen(name);
		this.hash = sock->inode->i_ino;

		file->f_dentry = d_alloc(sock_mnt->mnt_sb->s_root, &this);
		if (!file->f_dentry) {
			put_filp(file);
			put_unused_fd(fd);
			fd = -ENOMEM;
			goto out;
		}
		file->f_dentry->d_op = &sockfs_dentry_operations;
		d_add(file->f_dentry, sock->inode);
		file->f_vfsmnt = mntget(sock_mnt);

		sock->file = file;
		file->f_op = sock->inode->i_fop = &socket_file_ops;
		file->f_mode = 3;
		file->f_flags = O_RDWR;
		file->f_pos = 0;
		fd_install(fd, file);
	}

out:
	return fd;
}

extern __inline__ struct socket *socki_lookup(struct inode *inode)
{
	return &inode->u.socket_i;
}

/**
 *	sockfd_lookup	- 	Go from a file number to its socket slot
 *	@fd: file handle
 *	@err: pointer to an error code return
 *
 *	The file handle passed in is locked and the socket it is bound
 *	too is returned. If an error occurs the err pointer is overwritten
 *	with a negative errno code and NULL is returned. The function checks
 *	for both invalid handles and passing a handle which is not a socket.
 *
 *	On a success the socket object pointer is returned.
 */

struct socket *sockfd_lookup(int fd, int *err)
{
	struct file *file;
	struct inode *inode;
	struct socket *sock;

	if (!(file = fget(fd)))
	{
		*err = -EBADF;
		return NULL;
	}

	inode = file->f_dentry->d_inode;
	if (!inode->i_sock || !(sock = socki_lookup(inode)))
	{
		*err = -ENOTSOCK;
		fput(file);
		return NULL;
	}

	if (sock->file != file) {
		printk(KERN_ERR "socki_lookup: socket file changed!\n");
		sock->file = file;
	}
	return sock;
}

extern __inline__ void sockfd_put(struct socket *sock)
{
	fput(sock->file);
}

/**
 *	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.
 */

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

	inode = get_empty_inode();
	if (!inode)
		return NULL;

	inode->i_sb = sock_mnt->mnt_sb;
	sock = socki_lookup(inode);

	inode->i_mode = S_IFSOCK|S_IRWXUGO;
	inode->i_sock = 1;
	inode->i_uid = current->fsuid;
	inode->i_gid = current->fsgid;

	sock->inode = inode;
	init_waitqueue_head(&sock->wait);
	sock->fasync_list = NULL;
	sock->state = SS_UNCONNECTED;
	sock->flags = 0;
	sock->ops = NULL;
	sock->sk = NULL;
	sock->file = NULL;

	sockets_in_use[smp_processor_id()].counter++;
	return sock;
}

/*
 *	In theory you can't get an open on this inode, but /proc provides
 *	a back door. Remember to keep it shut otherwise you'll let the
 *	creepy crawlies in.
 */
  
static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
{
	return -ENXIO;
}

/**
 *	sock_release	-	close a socket
 *	@sock: socket to close
 *
 *	The socket is released from the protocol stack if it has a release
 *	callback, and the inode is then released if the socket is bound to
 *	an inode not a file. 
 */
 
void sock_release(struct socket *sock)
{
	if (sock->ops) 
		sock->ops->release(sock);

	if (sock->fasync_list)
		printk(KERN_ERR "sock_release: fasync list not empty!\n");

	sockets_in_use[smp_processor_id()].counter--;
	if (!sock->file) {
		iput(sock->inode);
		return;
	}
	sock->file=NULL;
}

int sock_sendmsg(struct socket *sock, struct msghdr *msg, int size)
{
	int err;
	struct scm_cookie scm;

	err = scm_send(sock, msg, &scm);
	if (err >= 0) {
		err = sock->ops->sendmsg(sock, msg, size, &scm);
		scm_destroy(&scm);
	}
	return err;
}

int sock_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags)
{
	struct scm_cookie scm;

	memset(&scm, 0, sizeof(scm));

	size = sock->ops->recvmsg(sock, msg, size, flags, &scm);
	if (size >= 0)
		scm_recv(sock, msg, &scm, flags);

	return size;
}


/*
 *	Sockets are not seekable.
 */

static loff_t sock_lseek(struct file *file, loff_t offset, int whence)
{
	return -ESPIPE;
}

/*
 *	Read data from a socket. ubuf is a user mode pointer. We make sure the user
 *	area ubuf...ubuf+size-1 is writable before asking the protocol.
 */

static ssize_t sock_read(struct file *file, char *ubuf,
			 size_t size, loff_t *ppos)
{
	struct socket *sock;
	struct iovec iov;
	struct msghdr msg;
	int flags;

	if (ppos != &file->f_pos)
		return -ESPIPE;
	if (size==0)		/* Match SYS5 behaviour */
		return 0;

	sock = socki_lookup(file->f_dentry->d_inode); 

	msg.msg_name=NULL;
	msg.msg_namelen=0;
	msg.msg_iov=&iov;
	msg.msg_iovlen=1;
	msg.msg_control=NULL;
	msg.msg_controllen=0;
	iov.iov_base=ubuf;
	iov.iov_len=size;
	flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT;

	return sock_recvmsg(sock, &msg, size, flags);
}


/*
 *	Write data to a socket. We verify that the user area ubuf..ubuf+size-1
 *	is readable by the user process.
 */

static ssize_t sock_write(struct file *file, const char *ubuf,
			  size_t size, loff_t *ppos)
{
	struct socket *sock;
	struct msghdr msg;
	struct iovec iov;
	
	if (ppos != &file->f_pos)
		return -ESPIPE;
	if(size==0)		/* Match SYS5 behaviour */
		return 0;

	sock = socki_lookup(file->f_dentry->d_inode);