socket.c 51.3 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6
/*
 * NET		An implementation of the SOCKET network access protocol.
 *
 * Version:	@(#)socket.c	1.1.93	18/02/95
 *
 * Authors:	Orest Zborowski, <obz@Kodak.COM>
7
 *		Ross Biro
L
Linus Torvalds 已提交
8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69
 *		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/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/seq_file.h>
A
Arjan van de Ven 已提交
70
#include <linux/mutex.h>
L
Linus Torvalds 已提交
71 72
#include <linux/wanrouter.h>
#include <linux/if_bridge.h>
73 74
#include <linux/if_frad.h>
#include <linux/if_vlan.h>
L
Linus Torvalds 已提交
75 76 77 78 79 80 81 82 83 84 85
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/divert.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/kmod.h>
86
#include <linux/audit.h>
87
#include <linux/wireless.h>
L
Linus Torvalds 已提交
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108

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

#include <net/compat.h>

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

static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf,
			 size_t size, loff_t pos);
static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf,
			  size_t size, 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);
109 110 111 112
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
		      unsigned int cmd, unsigned long arg);
#endif
L
Linus Torvalds 已提交
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
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 = {
	.owner =	THIS_MODULE,
	.llseek =	no_llseek,
	.aio_read =	sock_aio_read,
	.aio_write =	sock_aio_write,
	.poll =		sock_poll,
	.unlocked_ioctl = sock_ioctl,
133 134 135
#ifdef CONFIG_COMPAT
	.compat_ioctl = compat_sock_ioctl,
#endif
L
Linus Torvalds 已提交
136 137 138 139 140 141
	.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,
142 143
	.sendpage =	sock_sendpage,
	.splice_write = generic_splice_sendpage,
L
Linus Torvalds 已提交
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235
};

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

static struct net_proto_family *net_families[NPROTO];

#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
static atomic_t net_family_lockct = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(net_family_lock);

/* 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);

		yield();

		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 DEFINE_PER_CPU(int, sockets_in_use) = 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 __user *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;
236
	return audit_sockaddr(ulen, kaddr);
L
Linus Torvalds 已提交
237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
}

/**
 *	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 __user *uaddr, int __user *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)
	{
S
Steve Grubb 已提交
269 270
		if (audit_sockaddr(klen, kaddr))
			return -ENOMEM;
L
Linus Torvalds 已提交
271 272 273 274 275 276 277 278 279 280 281 282
		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

283
static kmem_cache_t * sock_inode_cachep __read_mostly;
L
Linus Torvalds 已提交
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322

static struct inode *sock_alloc_inode(struct super_block *sb)
{
	struct socket_alloc *ei;
	ei = (struct socket_alloc *)kmem_cache_alloc(sock_inode_cachep, SLAB_KERNEL);
	if (!ei)
		return NULL;
	init_waitqueue_head(&ei->socket.wait);
	
	ei->socket.fasync_list = NULL;
	ei->socket.state = SS_UNCONNECTED;
	ei->socket.flags = 0;
	ei->socket.ops = NULL;
	ei->socket.sk = NULL;
	ei->socket.file = NULL;
	ei->socket.flags = 0;

	return &ei->vfs_inode;
}

static void sock_destroy_inode(struct inode *inode)
{
	kmem_cache_free(sock_inode_cachep,
			container_of(inode, struct socket_alloc, vfs_inode));
}

static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
{
	struct socket_alloc *ei = (struct socket_alloc *) foo;

	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
	    SLAB_CTOR_CONSTRUCTOR)
		inode_init_once(&ei->vfs_inode);
}
 
static int init_inodecache(void)
{
	sock_inode_cachep = kmem_cache_create("sock_inode_cache",
				sizeof(struct socket_alloc),
323 324
				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
					SLAB_MEM_SPREAD),
L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334 335 336
				init_once, NULL);
	if (sock_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

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

337 338
static int sockfs_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
L
Linus Torvalds 已提交
339
{
340 341
	return get_sb_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC,
			     mnt);
L
Linus Torvalds 已提交
342 343
}

344
static struct vfsmount *sock_mnt __read_mostly;
L
Linus Torvalds 已提交
345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361

static struct file_system_type sock_fs_type = {
	.name =		"sockfs",
	.get_sb =	sockfs_get_sb,
	.kill_sb =	kill_anon_super,
};
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.
 *
362 363
 *	These functions create file structures and maps them to fd space
 *	of the current process. On success it returns file descriptor
L
Linus Torvalds 已提交
364 365 366 367 368 369 370 371 372 373 374 375
 *	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.
 */

376
static int sock_alloc_fd(struct file **filep)
L
Linus Torvalds 已提交
377 378 379 380
{
	int fd;

	fd = get_unused_fd();
381
	if (likely(fd >= 0)) {
L
Linus Torvalds 已提交
382 383
		struct file *file = get_empty_filp();

384 385
		*filep = file;
		if (unlikely(!file)) {
L
Linus Torvalds 已提交
386
			put_unused_fd(fd);
387
			return -ENFILE;
L
Linus Torvalds 已提交
388
		}
389 390 391 392
	} else
		*filep = NULL;
	return fd;
}
L
Linus Torvalds 已提交
393

394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
static int sock_attach_fd(struct socket *sock, struct file *file)
{
	struct qstr this;
	char name[32];

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

	file->f_dentry = d_alloc(sock_mnt->mnt_sb->s_root, &this);
	if (unlikely(!file->f_dentry))
		return -ENOMEM;

	file->f_dentry->d_op = &sockfs_dentry_operations;
	d_add(file->f_dentry, SOCK_INODE(sock));
	file->f_vfsmnt = mntget(sock_mnt);
	file->f_mapping = file->f_dentry->d_inode->i_mapping;

	sock->file = file;
	file->f_op = SOCK_INODE(sock)->i_fop = &socket_file_ops;
	file->f_mode = FMODE_READ | FMODE_WRITE;
	file->f_flags = O_RDWR;
	file->f_pos = 0;
	file->private_data = sock;
L
Linus Torvalds 已提交
418

419 420 421 422 423 424 425 426 427 428 429 430 431
	return 0;
}

int sock_map_fd(struct socket *sock)
{
	struct file *newfile;
	int fd = sock_alloc_fd(&newfile);

	if (likely(fd >= 0)) {
		int err = sock_attach_fd(sock, newfile);

		if (unlikely(err < 0)) {
			put_filp(newfile);
L
Linus Torvalds 已提交
432
			put_unused_fd(fd);
433
			return err;
L
Linus Torvalds 已提交
434
		}
435
		fd_install(fd, newfile);
L
Linus Torvalds 已提交
436 437 438 439
	}
	return fd;
}

440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461
static struct socket *sock_from_file(struct file *file, int *err)
{
	struct inode *inode;
	struct socket *sock;

	if (file->f_op == &socket_file_ops)
		return file->private_data;	/* set in sock_map_fd */

	inode = file->f_dentry->d_inode;
	if (!S_ISSOCK(inode->i_mode)) {
		*err = -ENOTSOCK;
		return NULL;
	}

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

L
Linus Torvalds 已提交
462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
/**
 *	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;

480
	if (!(file = fget(fd))) {
L
Linus Torvalds 已提交
481 482 483
		*err = -EBADF;
		return NULL;
	}
484 485
	sock = sock_from_file(file, err);
	if (!sock)
L
Linus Torvalds 已提交
486
		fput(file);
487 488
	return sock;
}
L
Linus Torvalds 已提交
489

490 491 492 493 494
static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
{
	struct file *file;
	struct socket *sock;

495
	*err = -EBADF;
496 497 498 499 500 501
	file = fget_light(fd, fput_needed);
	if (file) {
		sock = sock_from_file(file, err);
		if (sock)
			return sock;
		fput_light(file, *fput_needed);
L
Linus Torvalds 已提交
502
	}
503
	return NULL;
L
Linus Torvalds 已提交
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544
}

/**
 *	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(sock_mnt->mnt_sb);
	if (!inode)
		return NULL;

	sock = SOCKET_I(inode);

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

	get_cpu_var(sockets_in_use)++;
	put_cpu_var(sockets_in_use);
	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;
}

545
const struct file_operations bad_sock_fops = {
L
Linus Torvalds 已提交
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
	.owner = THIS_MODULE,
	.open = sock_no_open,
};

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

	get_cpu_var(sockets_in_use)--;
	put_cpu_var(sockets_in_use);
	if (!sock->file) {
		iput(SOCK_INODE(sock));
		return;
	}
	sock->file=NULL;
}

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

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

	err = security_socket_sendmsg(sock, msg, size);
	if (err)
		return err;

	return sock->ops->sendmsg(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;
}

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;
}

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

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

	err = security_socket_recvmsg(sock, msg, size, flags);
	if (err)
		return err;

	return sock->ops->recvmsg(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;
}

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;
}

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

689 690
static ssize_t sock_sendpage(struct file *file, struct page *page,
			     int offset, size_t size, loff_t *ppos, int more)
L
Linus Torvalds 已提交
691 692 693 694
{
	struct socket *sock;
	int flags;

695 696 697 698 699 700 701 702
	sock = file->private_data;

	flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT;
	if (more)
		flags |= MSG_MORE;

	return sock->ops->sendpage(sock, page, offset, size, flags);
}
L
Linus Torvalds 已提交
703

704 705 706 707 708 709 710
static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
		char __user *ubuf, size_t size, struct sock_iocb *siocb)
{
	if (!is_sync_kiocb(iocb)) {
		siocb = kmalloc(sizeof(*siocb), GFP_KERNEL);
		if (!siocb)
			return NULL;
L
Linus Torvalds 已提交
711 712 713
		iocb->ki_dtor = sock_aio_dtor;
	}

714 715 716
	siocb->kiocb = iocb;
	siocb->async_iov.iov_base = ubuf;
	siocb->async_iov.iov_len = size;
L
Linus Torvalds 已提交
717

718 719
	iocb->private = siocb;
	return siocb;
L
Linus Torvalds 已提交
720 721
}

722 723 724 725 726 727
static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
		struct file *file, struct iovec *iov, unsigned long nr_segs)
{
	struct socket *sock = file->private_data;
	size_t size = 0;
	int i;
L
Linus Torvalds 已提交
728

729 730
        for (i = 0 ; i < nr_segs ; i++)
                size += iov[i].iov_len;
L
Linus Torvalds 已提交
731

732 733 734 735 736 737 738 739 740 741 742 743 744
	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_readv(struct file *file, const struct iovec *iov,
			  unsigned long nr_segs, loff_t *ppos)
L
Linus Torvalds 已提交
745
{
746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764
	struct kiocb iocb;
	struct sock_iocb siocb;
	struct msghdr msg;
	int ret;

        init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;

	ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}

static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf,
			 size_t count, loff_t pos)
{
	struct sock_iocb siocb, *x;

L
Linus Torvalds 已提交
765 766
	if (pos != 0)
		return -ESPIPE;
767
	if (count == 0)		/* Match SYS5 behaviour */
L
Linus Torvalds 已提交
768 769
		return 0;

770 771 772 773 774
	x = alloc_sock_iocb(iocb, ubuf, count, &siocb);
	if (!x)
		return -ENOMEM;
	return do_sock_read(&x->async_msg, iocb, iocb->ki_filp,
			&x->async_iov, 1);
L
Linus Torvalds 已提交
775 776
}

777 778
static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
		struct file *file, struct iovec *iov, unsigned long nr_segs)
L
Linus Torvalds 已提交
779
{
780 781 782
	struct socket *sock = file->private_data;
	size_t size = 0;
	int i;
L
Linus Torvalds 已提交
783

784 785
        for (i = 0 ; i < nr_segs ; i++)
                size += iov[i].iov_len;
L
Linus Torvalds 已提交
786

787 788 789 790 791 792 793 794 795
	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;
L
Linus Torvalds 已提交
796

797
	return __sock_sendmsg(iocb, sock, msg, size);
L
Linus Torvalds 已提交
798 799
}

800 801
static ssize_t sock_writev(struct file *file, const struct iovec *iov,
			   unsigned long nr_segs, loff_t *ppos)
L
Linus Torvalds 已提交
802 803
{
	struct msghdr msg;
804 805 806
	struct kiocb iocb;
	struct sock_iocb siocb;
	int ret;
L
Linus Torvalds 已提交
807

808 809
	init_sync_kiocb(&iocb, NULL);
	iocb.private = &siocb;
L
Linus Torvalds 已提交
810

811 812 813 814 815
	ret = do_sock_write(&msg, &iocb, file, (struct iovec *)iov, nr_segs);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&iocb);
	return ret;
}
L
Linus Torvalds 已提交
816

817 818 819 820
static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf,
			  size_t count, loff_t pos)
{
	struct sock_iocb siocb, *x;
L
Linus Torvalds 已提交
821

822 823 824 825
	if (pos != 0)
		return -ESPIPE;
	if (count == 0)		/* Match SYS5 behaviour */
		return 0;
L
Linus Torvalds 已提交
826

827 828 829
	x = alloc_sock_iocb(iocb, (void __user *)ubuf, count, &siocb);
	if (!x)
		return -ENOMEM;
L
Linus Torvalds 已提交
830

831 832
	return do_sock_write(&x->async_msg, iocb, iocb->ki_filp,
			&x->async_iov, 1);
L
Linus Torvalds 已提交
833 834 835 836 837 838 839 840
}


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

A
Arjan van de Ven 已提交
841
static DEFINE_MUTEX(br_ioctl_mutex);
L
Linus Torvalds 已提交
842 843 844 845
static int (*br_ioctl_hook)(unsigned int cmd, void __user *arg) = NULL;

void brioctl_set(int (*hook)(unsigned int, void __user *))
{
A
Arjan van de Ven 已提交
846
	mutex_lock(&br_ioctl_mutex);
L
Linus Torvalds 已提交
847
	br_ioctl_hook = hook;
A
Arjan van de Ven 已提交
848
	mutex_unlock(&br_ioctl_mutex);
L
Linus Torvalds 已提交
849 850 851
}
EXPORT_SYMBOL(brioctl_set);

A
Arjan van de Ven 已提交
852
static DEFINE_MUTEX(vlan_ioctl_mutex);
L
Linus Torvalds 已提交
853 854 855 856
static int (*vlan_ioctl_hook)(void __user *arg);

void vlan_ioctl_set(int (*hook)(void __user *))
{
A
Arjan van de Ven 已提交
857
	mutex_lock(&vlan_ioctl_mutex);
L
Linus Torvalds 已提交
858
	vlan_ioctl_hook = hook;
A
Arjan van de Ven 已提交
859
	mutex_unlock(&vlan_ioctl_mutex);
L
Linus Torvalds 已提交
860 861 862
}
EXPORT_SYMBOL(vlan_ioctl_set);

A
Arjan van de Ven 已提交
863
static DEFINE_MUTEX(dlci_ioctl_mutex);
L
Linus Torvalds 已提交
864 865 866 867
static int (*dlci_ioctl_hook)(unsigned int, void __user *);

void dlci_ioctl_set(int (*hook)(unsigned int, void __user *))
{
A
Arjan van de Ven 已提交
868
	mutex_lock(&dlci_ioctl_mutex);
L
Linus Torvalds 已提交
869
	dlci_ioctl_hook = hook;
A
Arjan van de Ven 已提交
870
	mutex_unlock(&dlci_ioctl_mutex);
L
Linus Torvalds 已提交
871 872 873 874 875 876 877 878 879 880 881 882 883 884
}
EXPORT_SYMBOL(dlci_ioctl_set);

/*
 *	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;
	void __user *argp = (void __user *)arg;
	int pid, err;

885
	sock = file->private_data;
L
Linus Torvalds 已提交
886 887 888
	if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
		err = dev_ioctl(cmd, argp);
	} else
889
#ifdef CONFIG_WIRELESS_EXT
L
Linus Torvalds 已提交
890 891 892
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
		err = dev_ioctl(cmd, argp);
	} else
893
#endif	/* CONFIG_WIRELESS_EXT */
L
Linus Torvalds 已提交
894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913
	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(sock->file->f_owner.pid, (int __user *)argp);
			break;
		case SIOCGIFBR:
		case SIOCSIFBR:
		case SIOCBRADDBR:
		case SIOCBRDELBR:
			err = -ENOPKG;
			if (!br_ioctl_hook)
				request_module("bridge");

A
Arjan van de Ven 已提交
914
			mutex_lock(&br_ioctl_mutex);
L
Linus Torvalds 已提交
915 916
			if (br_ioctl_hook) 
				err = br_ioctl_hook(cmd, argp);
A
Arjan van de Ven 已提交
917
			mutex_unlock(&br_ioctl_mutex);
L
Linus Torvalds 已提交
918 919 920 921 922 923 924
			break;
		case SIOCGIFVLAN:
		case SIOCSIFVLAN:
			err = -ENOPKG;
			if (!vlan_ioctl_hook)
				request_module("8021q");

A
Arjan van de Ven 已提交
925
			mutex_lock(&vlan_ioctl_mutex);
L
Linus Torvalds 已提交
926 927
			if (vlan_ioctl_hook)
				err = vlan_ioctl_hook(argp);
A
Arjan van de Ven 已提交
928
			mutex_unlock(&vlan_ioctl_mutex);
L
Linus Torvalds 已提交
929 930 931 932 933 934 935 936 937 938 939 940 941
			break;
		case SIOCGIFDIVERT:
		case SIOCSIFDIVERT:
		/* Convert this to call through a hook */
			err = divert_ioctl(cmd, argp);
			break;
		case SIOCADDDLCI:
		case SIOCDELDLCI:
			err = -ENOPKG;
			if (!dlci_ioctl_hook)
				request_module("dlci");

			if (dlci_ioctl_hook) {
A
Arjan van de Ven 已提交
942
				mutex_lock(&dlci_ioctl_mutex);
L
Linus Torvalds 已提交
943
				err = dlci_ioctl_hook(cmd, argp);
A
Arjan van de Ven 已提交
944
				mutex_unlock(&dlci_ioctl_mutex);
L
Linus Torvalds 已提交
945 946 947 948
			}
			break;
		default:
			err = sock->ops->ioctl(sock, cmd, arg);
949 950 951 952 953 954 955

			/*
			 * If this ioctl is unknown try to hand it down
			 * to the NIC driver.
			 */
			if (err == -ENOIOCTLCMD)
				err = dev_ioctl(cmd, argp);
L
Linus Torvalds 已提交
956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
			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;
	}

	security_socket_post_create(sock, family, type, protocol, 1);
	sock->type = type;
out:
	*res = sock;
	return err;
}

/* 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. 
	 */
991
	sock = file->private_data;
L
Linus Torvalds 已提交
992 993 994 995 996
	return sock->ops->poll(file, sock, wait);
}

static int sock_mmap(struct file * file, struct vm_area_struct * vma)
{
997
	struct socket *sock = file->private_data;
L
Linus Torvalds 已提交
998 999 1000 1001

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

1002
static int sock_close(struct inode *inode, struct file *filp)
L
Linus Torvalds 已提交
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
{
	/*
	 *	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_fasync(-1, filp, 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.
 *	3. fasync_list can be used from softirq context, so that
 *	   modification under socket lock have to be enhanced with
 *	   write_lock_bh(&sk->sk_callback_lock).
 *							--ANK (990710)
 */

static int sock_fasync(int fd, struct file *filp, int on)
{
	struct fasync_struct *fa, *fna=NULL, **prev;
	struct socket *sock;
	struct sock *sk;

	if (on)
	{
1042
		fna = kmalloc(sizeof(struct fasync_struct), GFP_KERNEL);
L
Linus Torvalds 已提交
1043 1044 1045 1046
		if(fna==NULL)
			return -ENOMEM;
	}

1047
	sock = filp->private_data;
L
Linus Torvalds 已提交
1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180

	if ((sk=sock->sk) == NULL) {
		kfree(fna);
		return -EINVAL;
	}

	lock_sock(sk);

	prev=&(sock->fasync_list);

	for (fa=*prev; fa!=NULL; prev=&fa->fa_next,fa=*prev)
		if (fa->fa_file==filp)
			break;

	if(on)
	{
		if(fa!=NULL)
		{
			write_lock_bh(&sk->sk_callback_lock);
			fa->fa_fd=fd;
			write_unlock_bh(&sk->sk_callback_lock);

			kfree(fna);
			goto out;
		}
		fna->fa_file=filp;
		fna->fa_fd=fd;
		fna->magic=FASYNC_MAGIC;
		fna->fa_next=sock->fasync_list;
		write_lock_bh(&sk->sk_callback_lock);
		sock->fasync_list=fna;
		write_unlock_bh(&sk->sk_callback_lock);
	}
	else
	{
		if (fa!=NULL)
		{
			write_lock_bh(&sk->sk_callback_lock);
			*prev=fa->fa_next;
			write_unlock_bh(&sk->sk_callback_lock);
			kfree(fa);
		}
	}

out:
	release_sock(sock->sk);
	return 0;
}

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

int sock_wake_async(struct socket *sock, int how, int band)
{
	if (!sock || !sock->fasync_list)
		return -1;
	switch (how)
	{
	case 1:
		
		if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
			break;
		goto call_kill;
	case 2:
		if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
			break;
		/* fall through */
	case 0:
	call_kill:
		__kill_fasync(sock->fasync_list, SIGIO, band);
		break;
	case 3:
		__kill_fasync(sock->fasync_list, SIGURG, band);
	}
	return 0;
}

static int __sock_create(int family, int type, int protocol, struct socket **res, int kern)
{
	int err;
	struct socket *sock;

	/*
	 *	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;
		
#if defined(CONFIG_KMOD)
	/* 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 (net_families[family]==NULL)
	{
		request_module("net-pf-%d",family);
	}
#endif

	net_family_read_lock();
	if (net_families[family] == NULL) {
		err = -EAFNOSUPPORT;
		goto out;
	}

/*
 *	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.
 */

	if (!(sock = sock_alloc())) {
1181 1182
		if (net_ratelimit())
			printk(KERN_WARNING "socket: no more sockets\n");
L
Linus Torvalds 已提交
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197
		err = -ENFILE;		/* Not exactly a match, but its the
					   closest posix thing */
		goto out;
	}

	sock->type  = type;

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

1198 1199
	if ((err = net_families[family]->create(sock, protocol)) < 0) {
		sock->ops = NULL;
L
Linus Torvalds 已提交
1200
		goto out_module_put;
1201 1202
	}

L
Linus Torvalds 已提交
1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
	/*
	 * 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)) {
		sock->ops = NULL;
		goto out_module_put;
	}
	/*
	 * Now that we're done with the ->create function, the [loadable]
	 * module can have its refcnt decremented
	 */
	module_put(net_families[family]->owner);
	*res = sock;
	security_socket_post_create(sock, family, type, protocol, kern);

out:
	net_family_read_unlock();
	return err;
out_module_put:
	module_put(net_families[family]->owner);
out_release:
	sock_release(sock);
	goto out;
}

int sock_create(int family, int type, int protocol, struct socket **res)
{
	return __sock_create(family, type, protocol, res, 0);
}

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

asmlinkage long sys_socket(int family, int type, int protocol)
{
	int retval;
	struct socket *sock;

	retval = sock_create(family, type, protocol, &sock);
	if (retval < 0)
		goto out;

	retval = sock_map_fd(sock);
	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.
 */

asmlinkage long sys_socketpair(int family, int type, int protocol, int __user *usockvec)
{
	struct socket *sock1, *sock2;
	int fd1, fd2, err;

	/*
	 * 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 = fd2 = -1;

	err = sock_map_fd(sock1);
	if (err < 0)
		goto out_release_both;
	fd1 = err;

	err = sock_map_fd(sock2);
	if (err < 0)
		goto out_close_1;
	fd2 = err;

	/* 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_close_1:
        sock_release(sock2);
	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).
 */

asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen)
{
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
1339
	int err, fput_needed;
L
Linus Torvalds 已提交
1340

1341
	if((sock = sockfd_lookup_light(fd, &err, &fput_needed))!=NULL)
L
Linus Torvalds 已提交
1342 1343 1344
	{
		if((err=move_addr_to_kernel(umyaddr,addrlen,address))>=0) {
			err = security_socket_bind(sock, (struct sockaddr *)address, addrlen);
1345 1346 1347
			if (!err)
				err = sock->ops->bind(sock,
					(struct sockaddr *)address, addrlen);
L
Linus Torvalds 已提交
1348
		}
1349
		fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365
	}			
	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.
 */

int sysctl_somaxconn = SOMAXCONN;

asmlinkage long sys_listen(int fd, int backlog)
{
	struct socket *sock;
1366
	int err, fput_needed;
L
Linus Torvalds 已提交
1367
	
1368
	if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) {
L
Linus Torvalds 已提交
1369 1370 1371 1372
		if ((unsigned) backlog > sysctl_somaxconn)
			backlog = sysctl_somaxconn;

		err = security_socket_listen(sock, backlog);
1373 1374
		if (!err)
			err = sock->ops->listen(sock, backlog);
L
Linus Torvalds 已提交
1375

1376
		fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396
	}
	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.
 */

asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen)
{
	struct socket *sock, *newsock;
1397
	struct file *newfile;
1398
	int err, len, newfd, fput_needed;
L
Linus Torvalds 已提交
1399 1400
	char address[MAX_SOCK_ADDR];

1401
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
L
Linus Torvalds 已提交
1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417
	if (!sock)
		goto out;

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

1418 1419 1420
	newfd = sock_alloc_fd(&newfile);
	if (unlikely(newfd < 0)) {
		err = newfd;
1421 1422
		sock_release(newsock);
		goto out_put;
1423 1424 1425 1426 1427 1428
	}

	err = sock_attach_fd(newsock, newfile);
	if (err < 0)
		goto out_fd;

1429 1430
	err = security_socket_accept(sock, newsock);
	if (err)
1431
		goto out_fd;
1432

L
Linus Torvalds 已提交
1433 1434
	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
	if (err < 0)
1435
		goto out_fd;
L
Linus Torvalds 已提交
1436 1437 1438 1439

	if (upeer_sockaddr) {
		if(newsock->ops->getname(newsock, (struct sockaddr *)address, &len, 2)<0) {
			err = -ECONNABORTED;
1440
			goto out_fd;
L
Linus Torvalds 已提交
1441 1442 1443
		}
		err = move_addr_to_user(address, len, upeer_sockaddr, upeer_addrlen);
		if (err < 0)
1444
			goto out_fd;
L
Linus Torvalds 已提交
1445 1446 1447 1448
	}

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

1449 1450
	fd_install(newfd, newfile);
	err = newfd;
L
Linus Torvalds 已提交
1451 1452 1453 1454

	security_socket_post_accept(sock, newsock);

out_put:
1455
	fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1456 1457
out:
	return err;
1458
out_fd:
1459
	fput(newfile);
1460
	put_unused_fd(newfd);
L
Linus Torvalds 已提交
1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480
	goto out_put;
}


/*
 *	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.
 */

asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
{
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
1481
	int err, fput_needed;
L
Linus Torvalds 已提交
1482

1483
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
L
Linus Torvalds 已提交
1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496
	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:
1497
	fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510
out:
	return err;
}

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

asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len)
{
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
1511
	int len, err, fput_needed;
L
Linus Torvalds 已提交
1512
	
1513
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
L
Linus Torvalds 已提交
1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526
	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:
1527
	fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540
out:
	return err;
}

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

asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len)
{
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
1541
	int len, err, fput_needed;
L
Linus Torvalds 已提交
1542

1543
	if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) {
L
Linus Torvalds 已提交
1544 1545
		err = security_socket_getpeername(sock);
		if (err) {
1546
			fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1547 1548 1549 1550 1551 1552
			return err;
		}

		err = sock->ops->getname(sock, (struct sockaddr *)address, &len, 1);
		if (!err)
			err=move_addr_to_user(address,len, usockaddr, usockaddr_len);
1553
		fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
	}
	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.
 */

asmlinkage long sys_sendto(int fd, void __user * buff, size_t len, unsigned flags,
			   struct sockaddr __user *addr, int addr_len)
{
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
	int err;
	struct msghdr msg;
	struct iovec iov;
1572 1573 1574 1575 1576 1577 1578 1579
	int fput_needed;
	struct file *sock_file;

	sock_file = fget_light(fd, &fput_needed);
	if (!sock_file)
		return -EBADF;

	sock = sock_from_file(sock_file, &err);
L
Linus Torvalds 已提交
1580
	if (!sock)
1581
		goto out_put;
L
Linus Torvalds 已提交
1582 1583 1584 1585 1586 1587 1588 1589
	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;
1590
	if (addr) {
L
Linus Torvalds 已提交
1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602
		err = move_addr_to_kernel(addr, addr_len, address);
		if (err < 0)
			goto out_put;
		msg.msg_name=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:		
1603
	fput_light(sock_file, fput_needed);
L
Linus Torvalds 已提交
1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629
	return err;
}

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

asmlinkage long sys_send(int fd, void __user * buff, size_t len, unsigned 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.
 */

asmlinkage long sys_recvfrom(int fd, void __user * ubuf, size_t size, unsigned flags,
			     struct sockaddr __user *addr, int __user *addr_len)
{
	struct socket *sock;
	struct iovec iov;
	struct msghdr msg;
	char address[MAX_SOCK_ADDR];
	int err,err2;
1630 1631 1632 1633 1634 1635
	struct file *sock_file;
	int fput_needed;

	sock_file = fget_light(fd, &fput_needed);
	if (!sock_file)
		return -EBADF;
L
Linus Torvalds 已提交
1636

1637
	sock = sock_from_file(sock_file, &err);
L
Linus Torvalds 已提交
1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659
	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;
	msg.msg_name=address;
	msg.msg_namelen=MAX_SOCK_ADDR;
	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;
	}
out:
1660
	fput_light(sock_file, fput_needed);
L
Linus Torvalds 已提交
1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
	return err;
}

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

asmlinkage long sys_recv(int fd, void __user * ubuf, size_t size, unsigned 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.
 */

asmlinkage long sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen)
{
1680
	int err, fput_needed;
L
Linus Torvalds 已提交
1681 1682 1683 1684 1685
	struct socket *sock;

	if (optlen < 0)
		return -EINVAL;
			
1686
	if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL)
L
Linus Torvalds 已提交
1687 1688
	{
		err = security_socket_setsockopt(sock,level,optname);
1689 1690
		if (err)
			goto out_put;
L
Linus Torvalds 已提交
1691 1692 1693 1694 1695

		if (level == SOL_SOCKET)
			err=sock_setsockopt(sock,level,optname,optval,optlen);
		else
			err=sock->ops->setsockopt(sock, level, optname, optval, optlen);
1696 1697
out_put:
		fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708
	}
	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.
 */

asmlinkage long sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen)
{
1709
	int err, fput_needed;
L
Linus Torvalds 已提交
1710 1711
	struct socket *sock;

1712 1713 1714 1715
	if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) {
		err = security_socket_getsockopt(sock, level, optname);
		if (err)
			goto out_put;
L
Linus Torvalds 已提交
1716 1717 1718 1719 1720

		if (level == SOL_SOCKET)
			err=sock_getsockopt(sock,level,optname,optval,optlen);
		else
			err=sock->ops->getsockopt(sock, level, optname, optval, optlen);
1721 1722
out_put:
		fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
	}
	return err;
}


/*
 *	Shutdown a socket.
 */

asmlinkage long sys_shutdown(int fd, int how)
{
1734
	int err, fput_needed;
L
Linus Torvalds 已提交
1735 1736
	struct socket *sock;

1737
	if ((sock = sockfd_lookup_light(fd, &err, &fput_needed))!=NULL)
L
Linus Torvalds 已提交
1738 1739
	{
		err = security_socket_shutdown(sock, how);
1740 1741 1742
		if (!err)
			err = sock->ops->shutdown(sock, how);
		fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764
	}
	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)


/*
 *	BSD sendmsg interface
 */

asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags)
{
	struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg;
	struct socket *sock;
	char address[MAX_SOCK_ADDR];
	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
1765 1766 1767
	unsigned char ctl[sizeof(struct cmsghdr) + 20]
			__attribute__ ((aligned (sizeof(__kernel_size_t))));
			/* 20 is size of ipv6_pktinfo */
L
Linus Torvalds 已提交
1768 1769 1770
	unsigned char *ctl_buf = ctl;
	struct msghdr msg_sys;
	int err, ctl_len, iov_size, total_len;
1771
	int fput_needed;
L
Linus Torvalds 已提交
1772 1773 1774 1775 1776 1777 1778 1779
	
	err = -EFAULT;
	if (MSG_CMSG_COMPAT & flags) {
		if (get_compat_msghdr(&msg_sys, msg_compat))
			return -EFAULT;
	} else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr)))
		return -EFAULT;

1780
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
L
Linus Torvalds 已提交
1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812
	if (!sock) 
		goto out;

	/* do not move before msg_sys is valid */
	err = -EMSGSIZE;
	if (msg_sys.msg_iovlen > UIO_MAXIOV)
		goto out_put;

	/* Check whether to allocate the iovec area*/
	err = -ENOMEM;
	iov_size = msg_sys.msg_iovlen * sizeof(struct iovec);
	if (msg_sys.msg_iovlen > UIO_FASTIOV) {
		iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL);
		if (!iov)
			goto out_put;
	}

	/* This will also move the address data into kernel space */
	if (MSG_CMSG_COMPAT & flags) {
		err = verify_compat_iovec(&msg_sys, iov, address, VERIFY_READ);
	} else
		err = verify_iovec(&msg_sys, iov, address, VERIFY_READ);
	if (err < 0) 
		goto out_freeiov;
	total_len = err;

	err = -ENOBUFS;

	if (msg_sys.msg_controllen > INT_MAX)
		goto out_freeiov;
	ctl_len = msg_sys.msg_controllen; 
	if ((MSG_CMSG_COMPAT & flags) && ctl_len) {
A
Al Viro 已提交
1813
		err = cmsghdr_from_user_compat_to_kern(&msg_sys, sock->sk, ctl, sizeof(ctl));
L
Linus Torvalds 已提交
1814 1815 1816
		if (err)
			goto out_freeiov;
		ctl_buf = msg_sys.msg_control;
A
Al Viro 已提交
1817
		ctl_len = msg_sys.msg_controllen;
L
Linus Torvalds 已提交
1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847
	} else if (ctl_len) {
		if (ctl_len > sizeof(ctl))
		{
			ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL);
			if (ctl_buf == NULL) 
				goto out_freeiov;
		}
		err = -EFAULT;
		/*
		 * Careful! Before this, msg_sys.msg_control contains a user pointer.
		 * Afterwards, it will be a kernel pointer. Thus the compiler-assisted
		 * checking falls down on this.
		 */
		if (copy_from_user(ctl_buf, (void __user *) msg_sys.msg_control, ctl_len))
			goto out_freectl;
		msg_sys.msg_control = ctl_buf;
	}
	msg_sys.msg_flags = flags;

	if (sock->file->f_flags & O_NONBLOCK)
		msg_sys.msg_flags |= MSG_DONTWAIT;
	err = sock_sendmsg(sock, &msg_sys, total_len);

out_freectl:
	if (ctl_buf != ctl)    
		sock_kfree_s(sock->sk, ctl_buf, ctl_len);
out_freeiov:
	if (iov != iovstack)
		sock_kfree_s(sock->sk, iov, iov_size);
out_put:
1848
	fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865
out:       
	return err;
}

/*
 *	BSD recvmsg interface
 */

asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flags)
{
	struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg;
	struct socket *sock;
	struct iovec iovstack[UIO_FASTIOV];
	struct iovec *iov=iovstack;
	struct msghdr msg_sys;
	unsigned long cmsg_ptr;
	int err, iov_size, total_len, len;
1866
	int fput_needed;
L
Linus Torvalds 已提交
1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881

	/* kernel mode address */
	char addr[MAX_SOCK_ADDR];

	/* user mode address pointers */
	struct sockaddr __user *uaddr;
	int __user *uaddr_len;
	
	if (MSG_CMSG_COMPAT & flags) {
		if (get_compat_msghdr(&msg_sys, msg_compat))
			return -EFAULT;
	} else
		if (copy_from_user(&msg_sys,msg,sizeof(struct msghdr)))
			return -EFAULT;

1882
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
L
Linus Torvalds 已提交
1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930
	if (!sock)
		goto out;

	err = -EMSGSIZE;
	if (msg_sys.msg_iovlen > UIO_MAXIOV)
		goto out_put;
	
	/* Check whether to allocate the iovec area*/
	err = -ENOMEM;
	iov_size = msg_sys.msg_iovlen * sizeof(struct iovec);
	if (msg_sys.msg_iovlen > UIO_FASTIOV) {
		iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL);
		if (!iov)
			goto out_put;
	}

	/*
	 *	Save the user-mode address (verify_iovec will change the
	 *	kernel msghdr to use the kernel address space)
	 */
	 
	uaddr = (void __user *) msg_sys.msg_name;
	uaddr_len = COMPAT_NAMELEN(msg);
	if (MSG_CMSG_COMPAT & flags) {
		err = verify_compat_iovec(&msg_sys, iov, addr, VERIFY_WRITE);
	} else
		err = verify_iovec(&msg_sys, iov, addr, VERIFY_WRITE);
	if (err < 0)
		goto out_freeiov;
	total_len=err;

	cmsg_ptr = (unsigned long)msg_sys.msg_control;
	msg_sys.msg_flags = 0;
	if (MSG_CMSG_COMPAT & flags)
		msg_sys.msg_flags = MSG_CMSG_COMPAT;
	
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	err = sock_recvmsg(sock, &msg_sys, total_len, flags);
	if (err < 0)
		goto out_freeiov;
	len = err;

	if (uaddr != NULL) {
		err = move_addr_to_user(addr, msg_sys.msg_namelen, uaddr, uaddr_len);
		if (err < 0)
			goto out_freeiov;
	}
1931 1932
	err = __put_user((msg_sys.msg_flags & ~MSG_CMSG_COMPAT),
			 COMPAT_FLAGS(msg));
L
Linus Torvalds 已提交
1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948
	if (err)
		goto out_freeiov;
	if (MSG_CMSG_COMPAT & flags)
		err = __put_user((unsigned long)msg_sys.msg_control-cmsg_ptr, 
				 &msg_compat->msg_controllen);
	else
		err = __put_user((unsigned long)msg_sys.msg_control-cmsg_ptr, 
				 &msg->msg_controllen);
	if (err)
		goto out_freeiov;
	err = len;

out_freeiov:
	if (iov != iovstack)
		sock_kfree_s(sock->sk, iov, iov_size);
out_put:
1949
	fput_light(sock->file, fput_needed);
L
Linus Torvalds 已提交
1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982
out:
	return err;
}

#ifdef __ARCH_WANT_SYS_SOCKETCALL

/* Argument list sizes for sys_socketcall */
#define AL(x) ((x) * sizeof(unsigned long))
static unsigned char nargs[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
				AL(3),AL(3),AL(4),AL(4),AL(4),AL(6),
				AL(6),AL(2),AL(5),AL(5),AL(3),AL(3)};
#undef AL

/*
 *	System call vectors. 
 *
 *	Argument checking cleaned up. Saved 20% in size.
 *  This function doesn't need to set the kernel lock because
 *  it is set by the callees. 
 */

asmlinkage long sys_socketcall(int call, unsigned long __user *args)
{
	unsigned long a[6];
	unsigned long a0,a1;
	int err;

	if(call<1||call>SYS_RECVMSG)
		return -EINVAL;

	/* copy_from_user should be SMP safe. */
	if (copy_from_user(a, args, nargs[call]))
		return -EFAULT;
1983

1984
	err = audit_socketcall(nargs[call]/sizeof(unsigned long), a);
1985 1986 1987
	if (err)
		return err;

L
Linus Torvalds 已提交
1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099
	a0=a[0];
	a1=a[1];
	
	switch(call) 
	{
		case SYS_SOCKET:
			err = sys_socket(a0,a1,a[2]);
			break;
		case SYS_BIND:
			err = sys_bind(a0,(struct sockaddr __user *)a1, a[2]);
			break;
		case SYS_CONNECT:
			err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
			break;
		case SYS_LISTEN:
			err = sys_listen(a0,a1);
			break;
		case SYS_ACCEPT:
			err = sys_accept(a0,(struct sockaddr __user *)a1, (int __user *)a[2]);
			break;
		case SYS_GETSOCKNAME:
			err = sys_getsockname(a0,(struct sockaddr __user *)a1, (int __user *)a[2]);
			break;
		case SYS_GETPEERNAME:
			err = sys_getpeername(a0, (struct sockaddr __user *)a1, (int __user *)a[2]);
			break;
		case SYS_SOCKETPAIR:
			err = sys_socketpair(a0,a1, a[2], (int __user *)a[3]);
			break;
		case SYS_SEND:
			err = sys_send(a0, (void __user *)a1, a[2], a[3]);
			break;
		case SYS_SENDTO:
			err = sys_sendto(a0,(void __user *)a1, a[2], a[3],
					 (struct sockaddr __user *)a[4], a[5]);
			break;
		case SYS_RECV:
			err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
			break;
		case SYS_RECVFROM:
			err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
					   (struct sockaddr __user *)a[4], (int __user *)a[5]);
			break;
		case SYS_SHUTDOWN:
			err = sys_shutdown(a0,a1);
			break;
		case SYS_SETSOCKOPT:
			err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
			break;
		case SYS_GETSOCKOPT:
			err = sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]);
			break;
		case SYS_SENDMSG:
			err = sys_sendmsg(a0, (struct msghdr __user *) a1, a[2]);
			break;
		case SYS_RECVMSG:
			err = sys_recvmsg(a0, (struct msghdr __user *) a1, a[2]);
			break;
		default:
			err = -EINVAL;
			break;
	}
	return err;
}

#endif /* __ARCH_WANT_SYS_SOCKETCALL */

/*
 *	This function is called by a protocol handler that wants to
 *	advertise its address family, and have it linked into the
 *	SOCKET module.
 */

int sock_register(struct net_proto_family *ops)
{
	int err;

	if (ops->family >= NPROTO) {
		printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family, NPROTO);
		return -ENOBUFS;
	}
	net_family_write_lock();
	err = -EEXIST;
	if (net_families[ops->family] == NULL) {
		net_families[ops->family]=ops;
		err = 0;
	}
	net_family_write_unlock();
	printk(KERN_INFO "NET: Registered protocol family %d\n",
	       ops->family);
	return err;
}

/*
 *	This function is called by a protocol handler that wants to
 *	remove its address family, and have it unlinked from the
 *	SOCKET module.
 */

int sock_unregister(int family)
{
	if (family < 0 || family >= NPROTO)
		return -1;

	net_family_write_lock();
	net_families[family]=NULL;
	net_family_write_unlock();
	printk(KERN_INFO "NET: Unregistered protocol family %d\n",
	       family);
	return 0;
}

2100
static int __init sock_init(void)
L
Linus Torvalds 已提交
2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119
{
	/*
	 *	Initialize sock SLAB cache.
	 */
	 
	sk_init();

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

	/*
	 *	Initialize the protocols module. 
	 */

	init_inodecache();
	register_filesystem(&sock_fs_type);
	sock_mnt = kern_mount(&sock_fs_type);
2120 2121

	/* The real protocol initialization is performed in later initcalls.
L
Linus Torvalds 已提交
2122 2123 2124 2125 2126
	 */

#ifdef CONFIG_NETFILTER
	netfilter_init();
#endif
2127 2128

	return 0;
L
Linus Torvalds 已提交
2129 2130
}

2131 2132
core_initcall(sock_init);	/* early initcall */

L
Linus Torvalds 已提交
2133 2134 2135 2136 2137 2138
#ifdef CONFIG_PROC_FS
void socket_seq_show(struct seq_file *seq)
{
	int cpu;
	int counter = 0;

2139
	for_each_possible_cpu(cpu)
L
Linus Torvalds 已提交
2140 2141 2142 2143 2144 2145 2146 2147 2148 2149
		counter += per_cpu(sockets_in_use, cpu);

	/* It can be negative, by the way. 8) */
	if (counter < 0)
		counter = 0;

	seq_printf(seq, "sockets: used %d\n", counter);
}
#endif /* CONFIG_PROC_FS */

2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file, unsigned cmd,
				unsigned long arg)
{
	struct socket *sock = file->private_data;
	int ret = -ENOIOCTLCMD;

	if (sock->ops->compat_ioctl)
		ret = sock->ops->compat_ioctl(sock, cmd, arg);

	return ret;
}
#endif

L
Linus Torvalds 已提交
2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179
/* ABI emulation layers need these two */
EXPORT_SYMBOL(move_addr_to_kernel);
EXPORT_SYMBOL(move_addr_to_user);
EXPORT_SYMBOL(sock_create);
EXPORT_SYMBOL(sock_create_kern);
EXPORT_SYMBOL(sock_create_lite);
EXPORT_SYMBOL(sock_map_fd);
EXPORT_SYMBOL(sock_recvmsg);
EXPORT_SYMBOL(sock_register);
EXPORT_SYMBOL(sock_release);
EXPORT_SYMBOL(sock_sendmsg);
EXPORT_SYMBOL(sock_unregister);
EXPORT_SYMBOL(sock_wake_async);
EXPORT_SYMBOL(sockfd_lookup);
EXPORT_SYMBOL(kernel_sendmsg);
EXPORT_SYMBOL(kernel_recvmsg);