/net/socket.c

Large files files are truncated, but you can click here to view the full file

/*
 * NET		An implementation of the SOCKET network access protocol.
 *
 * Version:	@(#)socket.c	1.1.93	18/02/95
 *
 * Authors:	Orest Zborowski, <obz@Kodak.COM>
 *		Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * 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.
 *
 *	Based upon Swansea University Computer Society NET3.039
 */

#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/net.h>
#include <linux/interrupt.h>
#include <linux/thread_info.h>
#include <linux/rcupdate.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/wanrouter.h>
#include <linux/if_bridge.h>
#include <linux/if_frad.h>
#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/kmod.h>
#include <linux/audit.h>
#include <linux/wireless.h>
#include <linux/nsproxy.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/xattr.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>

#include <net/compat.h>
#include <net/wext.h>
#include <net/cls_cgroup.h>

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

#include <linux/if_tun.h>
#include <linux/ipv6_route.h>
#include <linux/route.h>
#include <linux/sockios.h>
#include <linux/atalk.h>

static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
			 unsigned long nr_segs, loff_t pos);
static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
			  unsigned long nr_segs, loff_t pos);
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 long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
			      unsigned int cmd, unsigned long arg);
#endif
static int sock_fasync(int fd, struct file *filp, int on);
static ssize_t sock_sendpage(struct file *file, struct page *page,
			     int offset, size_t size, loff_t *ppos, int more);
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
				struct pipe_inode_info *pipe, size_t len,
				unsigned int flags);

/*
 *	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,
	.aio_read =	sock_aio_read,
	.aio_write =	sock_aio_write,
	.poll =		sock_poll,
	.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl = compat_sock_ioctl,
#endif
	.mmap =		sock_mmap,
	.open =		sock_no_open,	/* special open code to disallow open via /proc */
	.release =	sock_close,
	.fasync =	sock_fasync,
	.sendpage =	sock_sendpage,
	.splice_write = generic_splice_sendpage,
	.splice_read =	sock_splice_read,
};

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

static DEFINE_SPINLOCK(net_family_lock);
static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly;

/*
 *	Statistics counters of the socket lists
 */

static DEFINE_PER_CPU(int, sockets_in_use);

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

/**
 *	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 __user *uaddr, int ulen, struct sockaddr_storage *kaddr)
{
	if (ulen < 0 || ulen > sizeof(struct sockaddr_storage))
		return -EINVAL;
	if (ulen == 0)
		return 0;
	if (copy_from_user(kaddr, uaddr, ulen))
		return -EFAULT;
	return audit_sockaddr(ulen, kaddr);
}

/**
 *	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.
 */

static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen,
			     void __user *uaddr, int __user *ulen)
{
	int err;
	int len;

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

static struct kmem_cache *sock_inode_cachep __read_mostly;

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;
	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;
}

static void sock_destroy_inode(struct inode *inode)
{
	struct socket_alloc *ei;
	struct socket_wq *wq;

	ei = container_of(inode, struct socket_alloc, vfs_inode);
	wq = rcu_dereference_protected(ei->socket.wq, 1);
	kfree_rcu(wq, rcu);
	kmem_cache_free(sock_inode_cachep, ei);
}

static void init_once(void *foo)
{
	struct socket_alloc *ei = (struct socket_alloc *)foo;

	inode_init_once(&ei->vfs_inode);
}

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;
}

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

/*
 * sockfs_dname() is called from d_path().
 */
static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen)
{
	return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]",
				dentry->d_inode->i_ino);
}

static const struct dentry_operations sockfs_dentry_operations = {
	.d_dname  = sockfs_dname,
};

static struct dentry *sockfs_mount(struct file_system_type *fs_type,
			 int flags, const char *dev_name, void *data)
{
	return mount_pseudo(fs_type, "socket:", &sockfs_ops,
		&sockfs_dentry_operations, SOCKFS_MAGIC);
}

static struct vfsmount *sock_mnt __read_mostly;

static struct file_system_type sock_fs_type = {
	.name =		"sockfs",
	.mount =	sockfs_mount,
	.kill_sb =	kill_anon_super,
};

/*
 *	Obtains the first available file descriptor and sets it up for use.
 *
 *	These functions create file structures and maps them to fd space
 *	of the 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 increment ref. count on file by 1.
 *
 *	In any case returned fd MAY BE not valid!
 *	This race condition is unavoidable
 *	with shared fd spaces, we cannot solve it inside kernel,
 *	but we take care of internal coherence yet.
 */

struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
{
	struct qstr name = { .name = "" };
	struct path path;
	struct file *file;

	if (dname) {
		name.name = dname;
		name.len = strlen(name.name);
	} else if (sock->sk) {
		name.name = sock->sk->sk_prot_creator->name;
		name.len = strlen(name.name);
	}
	path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
	if (unlikely(!path.dentry))
		return ERR_PTR(-ENOMEM);
	path.mnt = mntget(sock_mnt);

	d_instantiate(path.dentry, SOCK_INODE(sock));
	SOCK_INODE(sock)->i_fop = &socket_file_ops;

	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
		  &socket_file_ops);
	if (unlikely(!file)) {
		/* drop dentry, keep inode */
		ihold(path.dentry->d_inode);
		path_put(&path);
		return ERR_PTR(-ENFILE);
	}

	sock->file = file;
	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
	file->f_pos = 0;
	file->private_data = sock;
	return file;
}
EXPORT_SYMBOL(sock_alloc_file);

static int sock_map_fd(struct socket *sock, int flags)
{
	struct file *newfile;
	int fd = get_unused_fd_flags(flags);
	if (unlikely(fd < 0))
		return fd;

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

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

struct socket *sock_from_file(struct file *file, int *err)
{
	if (file->f_op == &socket_file_ops)
		return file->private_data;	/* set in sock_map_fd */

	*err = -ENOTSOCK;
	return NULL;
}
EXPORT_SYMBOL(sock_from_file);

/**
 *	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 socket *sock;

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

	sock = sock_from_file(file, err);
	if (!sock)
		fput(file);
	return sock;
}
EXPORT_SYMBOL(sockfd_lookup);

static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
{
	struct file *file;
	struct socket *sock;

	*err = -EBADF;
	file = fget_light(fd, fput_needed);
	if (file) {
		sock = sock_from_file(file, err);
		if (sock)
			return sock;
		fput_light(file, *fput_needed);
	}
	return NULL;
}

#define XATTR_SOCKPROTONAME_SUFFIX "sockprotoname"
#define XATTR_NAME_SOCKPROTONAME (XATTR_SYSTEM_PREFIX XATTR_SOCKPROTONAME_SUFFIX)
#define XATTR_NAME_SOCKPROTONAME_LEN (sizeof(XATTR_NAME_SOCKPROTONAME)-1)
static ssize_t sockfs_getxattr(struct dentry *dentry,
			       const char *name, void *value, size_t size)
{
	const char *proto_name;
	size_t proto_size;
	int error;

	error = -ENODATA;
	if (!strncmp(name, XATTR_NAME_SOCKPROTONAME, XATTR_NAME_SOCKPROTONAME_LEN)) {
		proto_name = dentry->d_name.name;
		proto_size = strlen(proto_name);

		if (value) {
			error = -ERANGE;
			if (proto_size + 1 > size)
				goto out;

			strncpy(value, proto_name, proto_size + 1);
		}
		error = proto_size + 1;
	}

out:
	return error;
}

static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
				size_t size)
{
	ssize_t len;
	ssize_t used = 0;

	len = security_inode_listsecurity(dentry->d_inode, buffer, size);
	if (len < 0)
		return len;
	used += len;
	if (buffer) {
		if (size < used)
			return -ERANGE;
		buffer += len;
	}

	len = (XATTR_NAME_SOCKPROTONAME_LEN + 1);
	used += len;
	if (buffer) {
		if (size < used)
			return -ERANGE;
		memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len);
		buffer += len;
	}

	return used;
}

static const struct inode_operations sockfs_inode_ops = {
	.getxattr = sockfs_getxattr,
	.listxattr = sockfs_listxattr,
};

/**
 *	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.
 */

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;
}

/*
 *	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;
}

const struct file_operations bad_sock_fops = {
	.owner = THIS_MODULE,
	.open = sock_no_open,
	.llseek = noop_llseek,
};

/**
 *	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) {
		struct module *owner = sock->ops->owner;

		sock->ops->release(sock);
		sock->ops = NULL;
		module_put(owner);
	}

	if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
		printk(KERN_ERR "sock_release: fasync list not empty!\n");

	if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags))
		return;

	this_cpu_sub(sockets_in_use, 1);
	if (!sock->file) {
		iput(SOCK_INODE(sock));
		return;
	}
	sock->file = NULL;
}
EXPORT_SYMBOL(sock_release);

int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
{
	*tx_flags = 0;
	if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE))
		*tx_flags |= SKBTX_HW_TSTAMP;
	if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE))
		*tx_flags |= SKBTX_SW_TSTAMP;
	if (sock_flag(sk, SOCK_WIFI_STATUS))
		*tx_flags |= SKBTX_WIFI_STATUS;
	return 0;
}
EXPORT_SYMBOL(sock_tx_timestamp);

static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
				       struct msghdr *msg, size_t size)
{
	struct sock_iocb *si = kiocb_to_siocb(iocb);

	si->sock = sock;
	si->scm = NULL;
	si->msg = msg;
	si->size = size;

	return sock->ops->sendmsg(iocb, sock, msg, size);
}

static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
				 struct msghdr *msg, size_t size)
{
	int err = security_socket_sendmsg(sock, msg, size);

	return err ?: __sock_sendmsg_nosec(iocb, sock, msg, size);
}

int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_sendmsg(&iocb, sock, msg, size);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}
EXPORT_SYMBOL(sock_sendmsg);

static int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_sendmsg_nosec(&iocb, sock, msg, size);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}

int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
		   struct kvec *vec, size_t num, size_t size)
{
	mm_segment_t oldfs = get_fs();
	int result;

	set_fs(KERNEL_DS);
	/*
	 * the following is safe, since for compiler definitions of kvec and
	 * iovec are identical, yielding the same in-core layout and alignment
	 */
	msg->msg_iov = (struct iovec *)vec;
	msg->msg_iovlen = num;
	result = sock_sendmsg(sock, msg, size);
	set_fs(oldfs);
	return result;
}
EXPORT_SYMBOL(kernel_sendmsg);

static int ktime2ts(ktime_t kt, struct timespec *ts)
{
	if (kt.tv64) {
		*ts = ktime_to_timespec(kt);
		return 1;
	} else {
		return 0;
	}
}

/*
 * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
 */
void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb)
{
	int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP);
	struct timespec ts[3];
	int empty = 1;
	struct skb_shared_hwtstamps *shhwtstamps =
		skb_hwtstamps(skb);

	/* Race occurred between timestamp enabling and packet
	   receiving.  Fill in the current time for now. */
	if (need_software_tstamp && skb->tstamp.tv64 == 0)
		__net_timestamp(skb);

	if (need_software_tstamp) {
		if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) {
			struct timeval tv;
			skb_get_timestamp(skb, &tv);
			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP,
				 sizeof(tv), &tv);
		} else {
			skb_get_timestampns(skb, &ts[0]);
			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS,
				 sizeof(ts[0]), &ts[0]);
		}
	}


	memset(ts, 0, sizeof(ts));
	if (skb->tstamp.tv64 &&
	    sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) {
		skb_get_timestampns(skb, ts + 0);
		empty = 0;
	}
	if (shhwtstamps) {
		if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) &&
		    ktime2ts(shhwtstamps->syststamp, ts + 1))
			empty = 0;
		if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) &&
		    ktime2ts(shhwtstamps->hwtstamp, ts + 2))
			empty = 0;
	}
	if (!empty)
		put_cmsg(msg, SOL_SOCKET,
			 SCM_TIMESTAMPING, sizeof(ts), &ts);
}
EXPORT_SYMBOL_GPL(__sock_recv_timestamp);

void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb)
{
	int ack;

	if (!sock_flag(sk, SOCK_WIFI_STATUS))
		return;
	if (!skb->wifi_acked_valid)
		return;

	ack = skb->wifi_acked;

	put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack);
}
EXPORT_SYMBOL_GPL(__sock_recv_wifi_status);

static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
				   struct sk_buff *skb)
{
	if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
		put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
			sizeof(__u32), &skb->dropcount);
}

void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb)
{
	sock_recv_timestamp(msg, sk, skb);
	sock_recv_drops(msg, sk, skb);
}
EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);

static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
				       struct msghdr *msg, size_t size, int flags)
{
	struct sock_iocb *si = kiocb_to_siocb(iocb);

	si->sock = sock;
	si->scm = NULL;
	si->msg = msg;
	si->size = size;
	si->flags = flags;

	return sock->ops->recvmsg(iocb, sock, msg, size, flags);
}

static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock,
				 struct msghdr *msg, size_t size, int flags)
{
	int err = security_socket_recvmsg(sock, msg, size, flags);

	return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags);
}

int sock_recvmsg(struct socket *sock, struct msghdr *msg,
		 size_t size, int flags)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}
EXPORT_SYMBOL(sock_recvmsg);

static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
			      size_t size, int flags)
{
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;

	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}

/**
 * kernel_recvmsg - Receive a message from a socket (kernel space)
 * @sock:       The socket to receive the message from
 * @msg:        Received message
 * @vec:        Input s/g array for message data
 * @num:        Size of input s/g array
 * @size:       Number of bytes to read
 * @flags:      Message flags (MSG_DONTWAIT, etc...)
 *
 * On return the msg structure contains the scatter/gather array passed in the
 * vec argument. The array is modified so that it consists of the unfilled
 * portion of the original array.
 *
 * The returned value is the total number of bytes received, or an error.
 */
int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
		   struct kvec *vec, size_t num, size_t size, int flags)
{
	mm_segment_t oldfs = get_fs();
	int result;

	set_fs(KERNEL_DS);
	/*
	 * the following is safe, since for compiler definitions of kvec and
	 * iovec are identical, yielding the same in-core layout and alignment
	 */
	msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num;
	result = sock_recvmsg(sock, msg, size, flags);
	set_fs(oldfs);
	return result;
}
EXPORT_SYMBOL(kernel_recvmsg);

static void sock_aio_dtor(struct kiocb *iocb)
{
	kfree(iocb->private);
}

static ssize_t sock_sendpage(struct file *file, struct page *page,
			     int offset, size_t size, loff_t *ppos, int more)
{
	struct socket *sock;
	int flags;

	sock = file->private_data;

	flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
	/* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */
	flags |= more;

	return kernel_sendpage(sock, page, offset, size, flags);
}

static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
				struct pipe_inode_info *pipe, size_t len,
				unsigned int flags)
{
	struct socket *sock = file->private_data;

	if (unlikely(!sock->ops->splice_read))
		return -EINVAL;

	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
}

static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
					 struct sock_iocb *siocb)
{
	if (!is_sync_kiocb(iocb)) {
		siocb = kmalloc(sizeof(*siocb), GFP_KERNEL);
		if (!siocb)
			return NULL;
		iocb->ki_dtor = sock_aio_dtor;
	}

	siocb->kiocb = iocb;
	iocb->private = siocb;
	return siocb;
}

static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
		struct file *file, const struct iovec *iov,
		unsigned long nr_segs)
{
	struct socket *sock = file->private_data;
	size_t size = 0;
	int i;

	for (i = 0; i < nr_segs; i++)
		size += iov[i].iov_len;

	msg->msg_name = NULL;
	msg->msg_namelen = 0;
	msg->msg_control = NULL;
	msg->msg_controllen = 0;
	msg->msg_iov = (struct iovec *)iov;
	msg->msg_iovlen = nr_segs;
	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;

	return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags);
}

static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos)
{
	struct sock_iocb siocb, *x;

	if (pos != 0)
		return -ESPIPE;

	if (iocb->ki_left == 0)	/* Match SYS5 behaviour */
		return 0;


	x = alloc_sock_iocb(iocb, &siocb);
	if (!x)
		return -ENOMEM;
	return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
}

static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
			struct file *file, const struct iovec *iov,
			unsigned long nr_segs)
{
	struct socket *sock = file->private_data;
	size_t size = 0;
	int i;

	for (i = 0; i < nr_segs; i++)
		size += iov[i].iov_len;

	msg->msg_name = NULL;
	msg->msg_namelen = 0;
	msg->msg_control = NULL;
	msg->msg_controllen = 0;
	msg->msg_iov = (struct iovec *)iov;
	msg->msg_iovlen = nr_segs;
	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
	if (sock->type == SOCK_SEQPACKET)
		msg->msg_flags |= MSG_EOR;

	return __sock_sendmsg(iocb, sock, msg, size);
}

static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
			  unsigned long nr_segs, loff_t pos)
{
	struct sock_iocb siocb, *x;

	if (pos != 0)
		return -ESPIPE;

	x = alloc_sock_iocb(iocb, &siocb);
	if (!x)
		return -ENOMEM;

	return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
}

/*
 * Atomic setting of ioctl hooks to avoid race
 * with module unload.
 */

static DEFINE_MUTEX(br_ioctl_mutex);
static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg);

void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *))
{
	mutex_lock(&br_ioctl_mutex);
	br_ioctl_hook = hook;
	mutex_unlock(&br_ioctl_mutex);
}
EXPORT_SYMBOL(brioctl_set);

static DEFINE_MUTEX(vlan_ioctl_mutex);
static int (*vlan_ioctl_hook) (struct net *, void __user *arg);

void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
{
	mutex_lock(&vlan_ioctl_mutex);
	vlan_ioctl_hook = hook;
	mutex_unlock(&vlan_ioctl_mutex);
}
EXPORT_SYMBOL(vlan_ioctl_set);

static DEFINE_MUTEX(dlci_ioctl_mutex);
static int (*dlci_ioctl_hook) (unsigned int, void __user *);

void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
{
	mutex_lock(&dlci_ioctl_mutex);
	dlci_ioctl_hook = hook;
	mutex_unlock(&dlci_ioctl_mutex);
}
EXPORT_SYMBOL(dlci_ioctl_set);

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

	err = sock->ops->ioctl(sock, cmd, arg);

	/*
	 * If this ioctl is unknown try to hand it down
	 * to the NIC driver.
	 */
	if (err == -ENOIOCTLCMD)
		err = dev_ioctl(net, cmd, argp);

	return err;
}

/*
 *	With an ioctl, arg may well be a user mode pointer, but we don't know
 *	what to do with it - that's up to the protocol still.
 */

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 (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
		err = dev_ioctl(net, cmd, argp);
	} else
#ifdef CONFIG_WEXT_CORE
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
		err = dev_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;
		default:
			err = sock_do_ioctl(net, sock, cmd, arg);
			break;
		}
	return err;
}

int sock_create_lite(int family, int type, int protocol, struct socket **res)
{
	int err;
	struct socket *sock = NULL;

	err = security_socket_create(family, type, protocol, 1);
	if (err)
		goto out;

	sock = sock_alloc();
	if (!sock) {
		err = -ENOMEM;
		goto out;
	}

	sock->type = type;
	err = security_socket_post_create(sock, family, type, protocol, 1);
	if (err)
		goto out_release;

out:
	*res = sock;
	return err;
out_release:
	sock_release(sock);
	sock = NULL;
	goto out;
}
EXPORT_SYMBOL(sock_create_lite);

/* No kernel lock held - perfect */
static unsigned int sock_poll(struct file *file, poll_table *wait)
{
	struct socket *sock;

	/*
	 *      We can't return errors to poll, so it's either yes or no.
	 */
	sock = file->private_data;
	return sock->ops->poll(file, sock, wait);
}

static int sock_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct socket *sock = file->private_data;

	return sock->ops->mmap(file, sock, vma);
}

static int sock_close(struct inode *inode, struct file *filp)
{
	/*
	 *      It was possible the inode is NULL we were
	 *      closing an unfinished socket.
	 */

	if (!inode) {
		printk(KERN_DEBUG "sock_close: NULL inode\n");
		return 0;
	}
	sock_release(SOCKET_I(inode));
	return 0;
}

/*
 *	Update the socket async list
 *
 *	Fasync_list locking strategy.
 *
 *	1. fasync_list is modified only under process context socket lock
 *	   i.e. under semaphore.
 *	2. fasync_list is used under read_lock(&sk->sk_callback_lock)
 *	   or under socket lock
 */

static int sock_fasync(int fd, struct file *filp, int on)
{
	struct socket *sock = filp->private_data;
	struct sock *sk = sock->sk;
	struct socket_wq *wq;

	if (sk == NULL)
		return -EINVAL;

	lock_sock(sk);
	wq = rcu_dereference_protected(sock->wq, sock_owned_by_user(sk));
	fasync_helper(fd, filp, on, &wq->fasync_list);

	if (!wq->fasync_list)
		sock_reset_flag(sk, SOCK_FASYNC);
	else
		sock_set_flag(sk, SOCK_FASYNC);

	release_sock(sk);
	return 0;
}

/* This function may be called only under socket lock or callback_lock or rcu_lock */

int sock_wake_async(struct socket *sock, int how, int band)
{
	struct socket_wq *wq;

	if (!sock)
		return -1;
	rcu_read_lock();
	wq = rcu_dereference(sock->wq);
	if (!wq || !wq->fasync_list) {
		rcu_read_unlock();
		return -1;
	}
	switch (how) {
	case SOCK_WAKE_WAITD:
		if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
			break;
		goto call_kill;
	case SOCK_WAKE_SPACE:
		if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
			break;
		/* fall through */
	case SOCK_WAKE_IO:
call_kill:
		kill_fasync(&wq->fasync_list, SIGIO, band);
		break;
	case SOCK_WAKE_URG:
		kill_fasync(&wq->fasync_list, SIGURG, band);
	}
	rcu_read_unlock();
	return 0;
}
EXPORT_SYMBOL(sock_wake_async);

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;
			printk(KERN_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;
}
EXPORT_SYMBOL(__sock_create);

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);

int sock_create_kern(int family, int type, int protocol, struct socket **res)
{
	return __sock_create(&init_net, family, type, protocol, res, 1);
}
EXPORT_SYMBOL(sock_create_kern);

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;
}

/*
 *	Create a pair of connected sockets.
 */

SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
		int __user *, usockvec)
{
	struct socket *sock1, *sock2;
	int fd1, fd2, err;
	struct file *newfile1, *newfile2;
	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;

	/*
	 * Obtain the first socket and check if the underlying protocol
	 * supports the socketpair call.
	 */

	err = sock_create(family, type, protocol, &sock1);
	if (err < 0)
		goto out;

	err = sock_create(family, type, protocol, &sock2);
	if (err < 0)
		goto out_release_1;

	err = sock1->ops->socketpair(sock1, sock2);
	if (err < 0)
		goto out_release_both;

	fd1 = get_unused_fd_flags(flags);
	if (unlikely(fd1 < 0)) {
		err = fd1;
		goto out_release_both;
	}
	fd2 = get_unused_fd_flags(flags);
	if (unlikely(fd2 < 0)) {
		err = fd2;
		put_unused_fd(fd1);
		goto out_release_both;
	}

	newfile1 = sock_alloc_file(sock1, flags, NULL);
	if (unlikely(IS_ERR(newfile1))) {
		err = PTR_ERR(newfile1);
		put_unused_fd(fd1);
		put_unused_fd(fd2);
		goto out_release_both;
	}

	newfile2 = sock_alloc_file(sock2, flags, NULL);
	if (IS_ERR(newfile2)) {
		err = PTR_ERR(newfile2);
		fput(newfile1);
		put_unused_fd(fd1);
		put_unused_fd(fd2);
		sock_release(sock2);
		goto out;
	}

	audit_fd_pair(fd1, fd2);
	fd_install(fd1, newfile1);
	fd_install(fd2, newfile2);
	/* fd1 and fd2 may be already another descriptors.
	 * Not kernel problem.
	 */

	err = put_user(fd1, &usockvec[0]);
	if (!err)
		err = put_user(fd2, &usockvec[1]);
	if (!err)
		return 0;

	sys_close(fd2);
	sys_close(fd1);
	return err;

out_release_both:
	sock_release(sock2);
out_release_1:
	sock_release(sock1);
out:
	return err;
}

/*
 *	Bind a name to a socket. Nothing much to do here since it's
 *	the protocol's responsibility to handle the local address.
 *
 *	We move the socket address to kernel space before we call
 *	the protocol layer (having also checked the address is ok).
 */

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		err = move_addr_to_kernel(umyaddr, addrlen, &address);
		if (err >= 0) {
			err = security_socket_bind(sock,
						   (struct sockaddr *)&address,
						   addrlen);
			if (!err)
				err = sock->ops->bind(sock,
						      (struct sockaddr *)
						      &address, addrlen);
		}
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Perform a listen. Basically, we allow the protocol to do anything
 *	necessary for a listen, and if that works, we mark the socket as
 *	ready for listening.
 */

SYSCALL_DEFINE2(listen, int, fd, int, backlog)
{
	struct socket *sock;
	int err, fput_needed;
	int somaxconn;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
		if ((unsigned int)backlog > somaxconn)
			backlog = somaxconn;

		err = security_socket_listen(sock, backlog);
		if (!err)
			err = sock->ops->listen(sock, backlog);

		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	For accept, we attempt to create a new socket, set up the link
 *	with the client, wake up the client, then return the new
 *	connected fd. We collect the address of the connector in kernel
 *	space and move it to user at the very end. This is unclean because
 *	we open the socket then return an error.
 *
 *	1003.1g adds the ability to recvmsg() to query connection pending
 *	status to recvmsg. We need to add that support in a way thats
 *	clean when we restucture accept also.
 */

SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen, int, flags)
{
	struct socket *sock, *newsock;
	struct file *newfile;
	int err, len, newfd, fput_needed;
	struct sockaddr_storage address;

	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = -ENFILE;
	newsock = sock_alloc();
	if (!newsock)
		goto out_put;

	newsock->type = sock->type;
	newsock->ops = sock->ops;

	/*
	 * We don't need try_module_get here, as the listening socket (sock)
	 * has the protocol module (sock->ops->owner) held.
	 */
	__module_get(newsock->ops->owner);

	newfd = get_unused_fd_flags(flags);
	if (unlikely(newfd < 0)) {
		err = newfd;
		sock_release(newsock);
		goto out_put;
	}
	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
	if (unlikely(IS_ERR(newfile))) {
		err = PTR_ERR(newfile);
		put_unused_fd(newfd);
		sock_release(newsock);
		goto out_put;
	}

	err = security_socket_accept(sock, newsock);
	if (err)
		goto out_fd;

	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
	if (err < 0)
		goto out_fd;

	if (upeer_sockaddr) {
		if (newsock->ops->getname(newsock, (struct sockaddr *)&address,
					  &len, 2) < 0) {
			err = -ECONNABORTED;
			goto out_fd;
		}
		err = move_addr_to_user(&address,
					len, upeer_sockaddr, upeer_addrlen);
		if (err < 0)
			goto out_fd;
	}

	/* File flags are not inherited via accept() unlike another OSes. */

	fd_install(newfd, newfile);
	err = newfd;

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
out_fd:
	fput(newfile);
	put_unused_fd(newfd);
	goto out_put;
}

SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen)
{
	return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
}

/*
 *	Attempt to connect to a socket with the server address.  The address
 *	is in user space so we verify it is OK and move it to kernel space.
 *
 *	For 1003.1g we need to add clean support for a bind to AF_UNSPEC to
 *	break bindings
 *
 *	NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and
 *	other SEQPACKET protocols that take time to connect() as it doesn't
 *	include the -EINPROGRESS status for such sockets.
 */

SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
		int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;
	err = move_addr_to_kernel(uservaddr, addrlen, &address);
	if (err < 0)
		goto out_put;

	err =
	    security_socket_connect(sock, (struct sockaddr *)&address, addrlen);
	if (err)
		goto out_put;

	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
				 sock->file->f_flags);
out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Get the local address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int len, err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = security_socket_getsockname(sock);
	if (err)
		goto out_put;

	err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0);
	if (err)
		goto out_put;
	err = move_addr_to_user(&address, len, usockaddr, usockaddr_len);

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Get the remote address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int len, err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_getpeername(sock);
		if (err) {
			fput_light(sock->file, fput_needed);
			return err;
		}

		err =
		    sock->ops->getname(sock, (struct sockaddr *)&address, &len,
				       1);
		if (!err)
			err = move_addr_to_user(&address, len, usockaddr,
						usockaddr_len);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Send a datagram to a given address. We move the address into kernel
 *	space and check the user space data area is readable before invoking
 *	the protocol.
 */

SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags, struct sockaddr __user *, addr,
		int, addr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err;
	struct msghdr msg;
	struct iovec iov;
	int fput_needed;

	if (len > INT_MAX)
		len = INT_MAX;
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	iov.iov_base = buff;
	iov.iov_len = len;
	msg.msg_name = NULL;
	msg.msg_iov = &iov;
	msg.msg_iovlen = 1;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;
	if (addr) {
		err = move_addr_to_kernel(addr, addr_len, &address);
		if (err < 0)
			goto out_put;
		msg.msg_name = (struct sockaddr *)&address;
		msg.msg_namelen = addr_len;
	}
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	msg.msg_flags = flags;
	err = sock_sendmsg(sock, &msg, len);

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Send a datagram down a socket.
 */

SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags)
{
	return sys_sendto(fd, buff, len, flags, NULL, 0);
}

/*
 *	Receive a frame from the socket and optionally record the address of the
 *	sender. We verify the buffers are writable and if needed move the
 *	sender address from kernel to user space.
 */

SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
		unsigned int, flags, struct sockaddr __user *, addr,
		int __user *, addr_len)
{
	struct socket *sock;
	struct iovec iov;
	struct msghdr msg;
	struct sockaddr_storage address;
	int err, err2;
	int fput_needed;

	if (size > INT_MAX)
		size = INT_MAX;
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_iovlen = 1;
	msg.msg_iov = &iov;
	iov.iov_len = size;
	iov.iov_base = ubuf;
	/* Save some cycles and don't copy the address if not needed */
	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
	/* We assume all kernel code knows the size of sockaddr_storage */
	msg.msg_namelen = 0;
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	err = sock_recvmsg(sock, &msg, size, flags);

	if (err >= 0 && addr != NULL) {
		err2 = move_addr_to_user(&address,
					 msg.msg_namelen, addr, addr_len);
		if (err2 < 0)
			err = err2;
	}

	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Receive a datagram from a socket.
 */

asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size,
			 unsigned int flags)
{
	return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
}

/*
 *	Set a socket option. Because we don't know the option lengths we have
 *	to pass the user mode parameter for the protocols to sort out.
 */

SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int, optlen)
{
	int err, fput_needed;
	struct socket *sock;

	if (optlen < 0)
		return -EINVAL;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_setsockopt(sock, level, optname);
		if (err)
			goto out_put;

		if (level == SOL_SOCKET)
			err =
			    sock_setsockopt(sock, level, optname, optval,
					    optlen);
		else
			err =
			    sock->ops->setsockopt(sock, level, optname, optval,
						  optlen);
out_put:
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Get a socket option. Because we don't know the option lengths we have
 *	to pass a user mode parameter for the protocols to sort out.
 */

SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int __user *, optlen)
{
	int err, fput_needed;
	struct socket *sock;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_getsockopt(sock, level, optname);
		if (err)
			goto out_put;

		if (level == SOL_SOCKET)
			err =
			    sock_getsockopt(sock, level, optname, optval,
					    optlen);
		else
			err =
			    sock->ops->getsockopt(sock, level, optname, optval,
						  optlen);
out_put:
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Shutdown a socket.
 */

SYSCALL_DEFINE2(shutdown, int, fd, int, how)
{
	int err, fput_needed;
	struct socket *sock;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_shutdown(sock, how);
		if (!err)
			err = sock->ops->shutdown(sock, how);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/* A couple of helpful macros for getting the address of the 32/64 bit
 * fields which are the same type (int / unsigned) on our platforms.
 */
#define COMPAT_MSG(msg, member)	((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member)
#define COMPAT_NAMELEN(msg)	COMPAT_MSG(msg, msg_namelen)
#define COMPAT_FLAGS(msg)	COMPAT_MSG(msg, msg_flags)

struct used_address {
	struct sockaddr_storage name;
	unsigned int name_len;
};

static int copy_msghdr_from_user(struct msghdr *kmsg,
				 struct msghdr __user *umsg)
{
	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
		return -EFAULT;

	if (kmsg->msg_namelen < 0)
		return -EINVAL;

	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
	return 0;
}

static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
			 struct msghdr *msg_sys, unsigned int flags,
			 struct used_address *used_address)
{
	struct compat_msghdr __user *msg_compat =
	    (struct compat_msghdr __user *)msg;
	struct sockaddr_storage address;
	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
	unsigned char ctl[sizeof(struct cmsghdr) + 20]
	    __attribute__ ((aligned(sizeof(__kernel_size_t))));
	/* 20 is size of ipv6_pktinfo */
	unsigned char *ctl_buf = ctl;
	int err, ctl_len, total_len;

	err = -EFAULT;
	if (MSG_CMSG_COMPAT & flags) {
		if (get_compat_msghdr(msg_sys, msg_compat))
			return -EFAULT;
	} else {
		err = copy_msghdr_from_user(msg_sys, msg);
		if (err)
			return err;
	}

	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
		err = -EMSGSIZ…