socket.c 92.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-or-later
2 3 4 5 6 7 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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
/*
 * 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 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/if_bridge.h>
#include <linux/if_frad.h>
#include <linux/if_vlan.h>
#include <linux/ptp_classify.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>
86
#include <linux/nospec.h>
87
#include <linux/indirect_call_wrapper.h>
88

89
#include <linux/uaccess.h>
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105
#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 <net/busy_poll.h>
#include <linux/errqueue.h>

106 107 108 109 110 111 112
/* proto_ops for ipv4 and ipv6 use the same {recv,send}msg function */
#if IS_ENABLED(CONFIG_INET)
#define INDIRECT_CALL_INET4(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
#else
#define INDIRECT_CALL_INET4(f, f1, ...) f(__VA_ARGS__)
#endif

113 114 115 116 117 118 119 120 121 122
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
unsigned int sysctl_net_busy_poll __read_mostly;
#endif

static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to);
static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
static int sock_mmap(struct file *file, struct vm_area_struct *vma);

static int sock_close(struct inode *inode, struct file *file);
123
static __poll_t sock_poll(struct file *file,
124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
			      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,
	.read_iter =	sock_read_iter,
	.write_iter =	sock_write_iter,
	.poll =		sock_poll,
	.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl = compat_sock_ioctl,
#endif
	.mmap =		sock_mmap,
	.release =	sock_close,
	.fasync =	sock_fasync,
	.sendpage =	sock_sendpage,
	.splice_write = generic_splice_sendpage,
	.splice_read =	sock_splice_read,
};

/*
 *	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;

/*
 * 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);
}

239
static struct kmem_cache *sock_inode_cachep __ro_after_init;
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256

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

	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	wq = kmalloc(sizeof(*wq), GFP_KERNEL);
	if (!wq) {
		kmem_cache_free(sock_inode_cachep, ei);
		return NULL;
	}
	init_waitqueue_head(&wq->wait);
	wq->fasync_list = NULL;
	wq->flags = 0;
257
	ei->socket.wq = wq;
258 259 260 261 262 263 264 265 266 267 268 269 270 271 272

	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;

	ei = container_of(inode, struct socket_alloc, vfs_inode);
273
	kfree_rcu(ei->socket.wq, rcu);
274 275 276 277 278 279 280 281 282 283
	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);
}

284
static void init_inodecache(void)
285 286 287 288 289 290 291 292
{
	sock_inode_cachep = kmem_cache_create("sock_inode_cache",
					      sizeof(struct socket_alloc),
					      0,
					      (SLAB_HWCACHE_ALIGN |
					       SLAB_RECLAIM_ACCOUNT |
					       SLAB_MEM_SPREAD | SLAB_ACCOUNT),
					      init_once);
293
	BUG_ON(sock_inode_cachep == NULL);
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314
}

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]",
				d_inode(dentry)->i_ino);
}

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

315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
static int sockfs_xattr_get(const struct xattr_handler *handler,
			    struct dentry *dentry, struct inode *inode,
			    const char *suffix, void *value, size_t size)
{
	if (value) {
		if (dentry->d_name.len + 1 > size)
			return -ERANGE;
		memcpy(value, dentry->d_name.name, dentry->d_name.len + 1);
	}
	return dentry->d_name.len + 1;
}

#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 const struct xattr_handler sockfs_xattr_handler = {
	.name = XATTR_NAME_SOCKPROTONAME,
	.get = sockfs_xattr_get,
};

static int sockfs_security_xattr_set(const struct xattr_handler *handler,
				     struct dentry *dentry, struct inode *inode,
				     const char *suffix, const void *value,
				     size_t size, int flags)
{
	/* Handled by LSM. */
	return -EAGAIN;
}

static const struct xattr_handler sockfs_security_xattr_handler = {
	.prefix = XATTR_SECURITY_PREFIX,
	.set = sockfs_security_xattr_set,
};

static const struct xattr_handler *sockfs_xattr_handlers[] = {
	&sockfs_xattr_handler,
	&sockfs_security_xattr_handler,
	NULL
};

356 357 358
static struct dentry *sockfs_mount(struct file_system_type *fs_type,
			 int flags, const char *dev_name, void *data)
{
359 360 361
	return mount_pseudo_xattr(fs_type, "socket:", &sockfs_ops,
				  sockfs_xattr_handlers,
				  &sockfs_dentry_operations, SOCKFS_MAGIC);
362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
}

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.
 */

389 390 391 392 393 394 395 396 397 398 399 400
/**
 *	sock_alloc_file - Bind a &socket to a &file
 *	@sock: socket
 *	@flags: file status flags
 *	@dname: protocol name
 *
 *	Returns the &file bound with @sock, implicitly storing it
 *	in sock->file. If dname is %NULL, sets to "".
 *	On failure the return is a ERR pointer (see linux/err.h).
 *	This function uses GFP_KERNEL internally.
 */

401 402 403 404
struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
{
	struct file *file;

405 406
	if (!dname)
		dname = sock->sk ? sock->sk->sk_prot_creator->name : "";
407

408 409 410
	file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
				O_RDWR | (flags & O_NONBLOCK),
				&socket_file_ops);
411
	if (IS_ERR(file)) {
412
		sock_release(sock);
413 414 415 416 417 418 419 420 421 422 423 424 425
		return file;
	}

	sock->file = file;
	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);
426 427
	if (unlikely(fd < 0)) {
		sock_release(sock);
428
		return fd;
429
	}
430 431 432 433 434 435 436 437 438 439 440

	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);
}

441 442 443 444 445 446 447 448
/**
 *	sock_from_file - Return the &socket bounded to @file.
 *	@file: file
 *	@err: pointer to an error code return
 *
 *	On failure returns %NULL and assigns -ENOTSOCK to @err.
 */

449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
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
465
 *	to is returned. If an error occurs the err pointer is overwritten
466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
 *	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 fd f = fdget(fd);
	struct socket *sock;

	*err = -EBADF;
	if (f.file) {
		sock = sock_from_file(f.file, err);
		if (likely(sock)) {
			*fput_needed = f.flags;
			return sock;
		}
		fdput(f);
	}
	return NULL;
}

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

	len = security_inode_listsecurity(d_inode(dentry), 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;
}

535 536 537 538 539 540 541
static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
	int err = simple_setattr(dentry, iattr);

	if (!err && (iattr->ia_valid & ATTR_UID)) {
		struct socket *sock = SOCKET_I(d_inode(dentry));

542 543 544 545
		if (sock->sk)
			sock->sk->sk_uid = iattr->ia_uid;
		else
			err = -ENOENT;
546 547 548 549 550
	}

	return err;
}

551 552
static const struct inode_operations sockfs_inode_ops = {
	.listxattr = sockfs_listxattr,
553
	.setattr = sockfs_setattr,
554 555 556
};

/**
557
 *	sock_alloc - allocate a socket
558 559 560
 *
 *	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
561
 *	NULL is returned. This functions uses GFP_KERNEL internally.
562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585
 */

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

	inode = new_inode_pseudo(sock_mnt->mnt_sb);
	if (!inode)
		return NULL;

	sock = SOCKET_I(inode);

	inode->i_ino = get_next_ino();
	inode->i_mode = S_IFSOCK | S_IRWXUGO;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_op = &sockfs_inode_ops;

	return sock;
}
EXPORT_SYMBOL(sock_alloc);

/**
586
 *	sock_release - close a socket
587 588 589 590 591 592 593
 *	@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.
 */

594
static void __sock_release(struct socket *sock, struct inode *inode)
595 596 597 598
{
	if (sock->ops) {
		struct module *owner = sock->ops->owner;

599 600
		if (inode)
			inode_lock(inode);
601
		sock->ops->release(sock);
602
		sock->sk = NULL;
603 604
		if (inode)
			inode_unlock(inode);
605 606 607 608
		sock->ops = NULL;
		module_put(owner);
	}

609
	if (sock->wq->fasync_list)
610 611 612 613 614 615 616 617
		pr_err("%s: fasync list not empty!\n", __func__);

	if (!sock->file) {
		iput(SOCK_INODE(sock));
		return;
	}
	sock->file = NULL;
}
618 619 620 621 622

void sock_release(struct socket *sock)
{
	__sock_release(sock, NULL);
}
623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641
EXPORT_SYMBOL(sock_release);

void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
{
	u8 flags = *tx_flags;

	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
		flags |= SKBTX_HW_TSTAMP;

	if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
		flags |= SKBTX_SW_TSTAMP;

	if (tsflags & SOF_TIMESTAMPING_TX_SCHED)
		flags |= SKBTX_SCHED_TSTAMP;

	*tx_flags = flags;
}
EXPORT_SYMBOL(__sock_tx_timestamp);

642 643 644 645 646 647 648 649 650 651
INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *,
					   size_t));
static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
{
	int ret = INDIRECT_CALL_INET4(sock->ops->sendmsg, inet_sendmsg, sock,
				      msg, msg_data_left(msg));
	BUG_ON(ret == -EIOCBQUEUED);
	return ret;
}

652 653 654 655 656 657 658 659
/**
 *	sock_sendmsg - send a message through @sock
 *	@sock: socket
 *	@msg: message to send
 *
 *	Sends @msg through @sock, passing through LSM.
 *	Returns the number of bytes sent, or an error code.
 */
660 661 662 663 664 665 666 667 668
int sock_sendmsg(struct socket *sock, struct msghdr *msg)
{
	int err = security_socket_sendmsg(sock, msg,
					  msg_data_left(msg));

	return err ?: sock_sendmsg_nosec(sock, msg);
}
EXPORT_SYMBOL(sock_sendmsg);

669 670 671 672 673 674 675 676 677 678 679 680
/**
 *	kernel_sendmsg - send a message through @sock (kernel-space)
 *	@sock: socket
 *	@msg: message header
 *	@vec: kernel vec
 *	@num: vec array length
 *	@size: total message data size
 *
 *	Builds the message data with @vec and sends it through @sock.
 *	Returns the number of bytes sent, or an error code.
 */

681 682 683
int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
		   struct kvec *vec, size_t num, size_t size)
{
684
	iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
685 686 687 688
	return sock_sendmsg(sock, msg);
}
EXPORT_SYMBOL(kernel_sendmsg);

689 690 691 692 693 694 695 696 697 698 699 700 701
/**
 *	kernel_sendmsg_locked - send a message through @sock (kernel-space)
 *	@sk: sock
 *	@msg: message header
 *	@vec: output s/g array
 *	@num: output s/g array length
 *	@size: total message data size
 *
 *	Builds the message data with @vec and sends it through @sock.
 *	Returns the number of bytes sent, or an error code.
 *	Caller must hold @sk.
 */

702 703 704 705 706 707 708 709
int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
			  struct kvec *vec, size_t num, size_t size)
{
	struct socket *sock = sk->sk_socket;

	if (!sock->ops->sendmsg_locked)
		return sock_no_sendmsg_locked(sk, msg, size);

710
	iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
711 712 713 714 715

	return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg));
}
EXPORT_SYMBOL(kernel_sendmsg_locked);

716 717 718 719 720 721 722 723 724 725
static bool skb_is_err_queue(const struct sk_buff *skb)
{
	/* pkt_type of skbs enqueued on the error queue are set to
	 * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
	 * in recvmsg, since skbs received on a local socket will never
	 * have a pkt_type of PACKET_OUTGOING.
	 */
	return skb->pkt_type == PACKET_OUTGOING;
}

726 727 728 729 730
/* On transmit, software and hardware timestamps are returned independently.
 * As the two skb clones share the hardware timestamp, which may be updated
 * before the software timestamp is received, a hardware TX timestamp may be
 * returned only if there is no software TX timestamp. Ignore false software
 * timestamps, which may be made in the __sock_recv_timestamp() call when the
731
 * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a
732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759
 * hardware timestamp.
 */
static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp)
{
	return skb->tstamp && !false_tstamp && skb_is_err_queue(skb);
}

static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
	struct scm_ts_pktinfo ts_pktinfo;
	struct net_device *orig_dev;

	if (!skb_mac_header_was_set(skb))
		return;

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

	rcu_read_lock();
	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
	if (orig_dev)
		ts_pktinfo.if_index = orig_dev->ifindex;
	rcu_read_unlock();

	ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb);
	put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO,
		 sizeof(ts_pktinfo), &ts_pktinfo);
}

760 761 762 763 764 765 766
/*
 * 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);
767 768 769
	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
	struct scm_timestamping_internal tss;

770
	int empty = 1, false_tstamp = 0;
771 772 773 774 775
	struct skb_shared_hwtstamps *shhwtstamps =
		skb_hwtstamps(skb);

	/* Race occurred between timestamp enabling and packet
	   receiving.  Fill in the current time for now. */
776
	if (need_software_tstamp && skb->tstamp == 0) {
777
		__net_timestamp(skb);
778 779
		false_tstamp = 1;
	}
780 781 782

	if (need_software_tstamp) {
		if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) {
783 784 785 786 787 788 789 790 791 792 793 794 795
			if (new_tstamp) {
				struct __kernel_sock_timeval tv;

				skb_get_new_timestamp(skb, &tv);
				put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW,
					 sizeof(tv), &tv);
			} else {
				struct __kernel_old_timeval tv;

				skb_get_timestamp(skb, &tv);
				put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD,
					 sizeof(tv), &tv);
			}
796
		} else {
797 798 799 800 801 802 803 804 805 806 807 808 809
			if (new_tstamp) {
				struct __kernel_timespec ts;

				skb_get_new_timestampns(skb, &ts);
				put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
					 sizeof(ts), &ts);
			} else {
				struct timespec ts;

				skb_get_timestampns(skb, &ts);
				put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD,
					 sizeof(ts), &ts);
			}
810 811 812 813 814
		}
	}

	memset(&tss, 0, sizeof(tss));
	if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
815
	    ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0))
816 817 818
		empty = 0;
	if (shhwtstamps &&
	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
819
	    !skb_is_swtx_tstamp(skb, false_tstamp) &&
820
	    ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) {
821
		empty = 0;
822 823 824 825
		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
		    !skb_is_err_queue(skb))
			put_ts_pktinfo(msg, skb);
	}
826
	if (!empty) {
827 828 829 830
		if (sock_flag(sk, SOCK_TSTAMP_NEW))
			put_cmsg_scm_timestamping64(msg, &tss);
		else
			put_cmsg_scm_timestamping(msg, &tss);
831 832 833 834 835 836

		if (skb_is_err_queue(skb) && skb->len &&
		    SKB_EXT_ERR(skb)->opt_stats)
			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
				 skb->len, skb->data);
	}
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871
}
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 && SOCK_SKB_CB(skb)->dropcount)
		put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
			sizeof(__u32), &SOCK_SKB_CB(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);

872 873 874 875 876 877 878 879 880
INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *,
					   size_t , int ));
static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
				     int flags)
{
	return INDIRECT_CALL_INET4(sock->ops->recvmsg, inet_recvmsg, sock, msg,
				   msg_data_left(msg), flags);
}

881 882 883 884 885 886 887 888 889
/**
 *	sock_recvmsg - receive a message from @sock
 *	@sock: socket
 *	@msg: message to receive
 *	@flags: message flags
 *
 *	Receives @msg from @sock, passing through LSM. Returns the total number
 *	of bytes received, or an error.
 */
890 891 892 893 894 895 896 897 898
int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags)
{
	int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags);

	return err ?: sock_recvmsg_nosec(sock, msg, flags);
}
EXPORT_SYMBOL(sock_recvmsg);

/**
899 900 901 902 903 904 905
 *	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...)
906
 *
907 908 909
 *	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.
910
 *
911
 *	The returned value is the total number of bytes received, or an error.
912
 */
913

914 915 916 917 918 919
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;

920
	iov_iter_kvec(&msg->msg_iter, READ, vec, num, size);
921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949
	set_fs(KERNEL_DS);
	result = sock_recvmsg(sock, msg, flags);
	set_fs(oldfs);
	return result;
}
EXPORT_SYMBOL(kernel_recvmsg);

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))
950
		return generic_file_splice_read(file, ppos, pipe, len, flags);
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 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

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

static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *file = iocb->ki_filp;
	struct socket *sock = file->private_data;
	struct msghdr msg = {.msg_iter = *to,
			     .msg_iocb = iocb};
	ssize_t res;

	if (file->f_flags & O_NONBLOCK)
		msg.msg_flags = MSG_DONTWAIT;

	if (iocb->ki_pos != 0)
		return -ESPIPE;

	if (!iov_iter_count(to))	/* Match SYS5 behaviour */
		return 0;

	res = sock_recvmsg(sock, &msg, msg.msg_flags);
	*to = msg.msg_iter;
	return res;
}

static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct socket *sock = file->private_data;
	struct msghdr msg = {.msg_iter = *from,
			     .msg_iocb = iocb};
	ssize_t res;

	if (iocb->ki_pos != 0)
		return -ESPIPE;

	if (file->f_flags & O_NONBLOCK)
		msg.msg_flags = MSG_DONTWAIT;

	if (sock->type == SOCK_SEQPACKET)
		msg.msg_flags |= MSG_EOR;

	res = sock_sendmsg(sock, &msg);
	*from = msg.msg_iter;
	return res;
}

/*
 * 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,
1038
			  unsigned int cmd, unsigned long arg)
1039 1040 1041 1042 1043 1044 1045 1046 1047 1048
{
	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.
	 */
1049 1050
	if (err != -ENOIOCTLCMD)
		return err;
1051

1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
	if (cmd == SIOCGIFCONF) {
		struct ifconf ifc;
		if (copy_from_user(&ifc, argp, sizeof(struct ifconf)))
			return -EFAULT;
		rtnl_lock();
		err = dev_ifconf(net, &ifc, sizeof(struct ifreq));
		rtnl_unlock();
		if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf)))
			err = -EFAULT;
	} else {
		struct ifreq ifr;
		bool need_copyout;
1064
		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
1065 1066 1067
			return -EFAULT;
		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
		if (!err && need_copyout)
1068
			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
1069 1070
				return -EFAULT;
	}
1071 1072 1073 1074 1075 1076 1077 1078
	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.
 */

1079 1080 1081 1082 1083 1084 1085
/**
 *	get_net_ns - increment the refcount of the network namespace
 *	@ns: common namespace (net)
 *
 *	Returns the net's common namespace.
 */

1086
struct ns_common *get_net_ns(struct ns_common *ns)
1087 1088 1089
{
	return &get_net(container_of(ns, struct net, ns))->ns;
}
1090
EXPORT_SYMBOL_GPL(get_net_ns);
1091

1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102
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);
1103 1104 1105 1106 1107 1108 1109 1110 1111
	if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) {
		struct ifreq ifr;
		bool need_copyout;
		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
			return -EFAULT;
		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
		if (!err && need_copyout)
			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
				return -EFAULT;
1112 1113 1114
	} else
#ifdef CONFIG_WEXT_CORE
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
1115
		err = wext_handle_ioctl(net, cmd, argp);
1116 1117 1118 1119 1120 1121 1122 1123
	} else
#endif
		switch (cmd) {
		case FIOSETOWN:
		case SIOCSPGRP:
			err = -EFAULT;
			if (get_user(pid, (int __user *)argp))
				break;
1124
			err = f_setown(sock->file, pid, 1);
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
			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;
1166 1167 1168 1169 1170 1171 1172
		case SIOCGSKNS:
			err = -EPERM;
			if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
				break;

			err = open_related_ns(&net->ns, get_net_ns);
			break;
1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
		case SIOCGSTAMP_OLD:
		case SIOCGSTAMPNS_OLD:
			if (!sock->ops->gettstamp) {
				err = -ENOIOCTLCMD;
				break;
			}
			err = sock->ops->gettstamp(sock, argp,
						   cmd == SIOCGSTAMP_OLD,
						   !IS_ENABLED(CONFIG_64BIT));
			break;
		case SIOCGSTAMP_NEW:
		case SIOCGSTAMPNS_NEW:
			if (!sock->ops->gettstamp) {
				err = -ENOIOCTLCMD;
				break;
			}
			err = sock->ops->gettstamp(sock, argp,
						   cmd == SIOCGSTAMP_NEW,
						   false);
			break;
1193
		default:
1194
			err = sock_do_ioctl(net, sock, cmd, arg);
1195 1196 1197 1198 1199
			break;
		}
	return err;
}

1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
/**
 *	sock_create_lite - creates a socket
 *	@family: protocol family (AF_INET, ...)
 *	@type: communication type (SOCK_STREAM, ...)
 *	@protocol: protocol (0, ...)
 *	@res: new socket
 *
 *	Creates a new socket and assigns it to @res, passing through LSM.
 *	The new socket initialization is not complete, see kernel_accept().
 *	Returns 0 or an error. On failure @res is set to %NULL.
 *	This function internally uses GFP_KERNEL.
 */

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
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 */
1244
static __poll_t sock_poll(struct file *file, poll_table *wait)
1245
{
1246
	struct socket *sock = file->private_data;
1247
	__poll_t events = poll_requested_events(wait), flag = 0;
1248

1249 1250
	if (!sock->ops->poll)
		return 0;
1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261

	if (sk_can_busy_loop(sock->sk)) {
		/* poll once if requested by the syscall */
		if (events & POLL_BUSY_LOOP)
			sk_busy_loop(sock->sk, 1);

		/* if this socket can poll_ll, tell the system call */
		flag = POLL_BUSY_LOOP;
	}

	return sock->ops->poll(file, sock, wait) | flag;
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272
}

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)
{
1273
	__sock_release(SOCKET_I(inode), inode);
1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
	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);
1298
	wq = sock->wq;
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
	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 rcu_lock */

int sock_wake_async(struct socket_wq *wq, int how, int band)
{
	if (!wq || !wq->fasync_list)
		return -1;

	switch (how) {
	case SOCK_WAKE_WAITD:
		if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags))
			break;
		goto call_kill;
	case SOCK_WAKE_SPACE:
		if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->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);
	}

	return 0;
}
EXPORT_SYMBOL(sock_wake_async);

1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352
/**
 *	__sock_create - creates a socket
 *	@net: net namespace
 *	@family: protocol family (AF_INET, ...)
 *	@type: communication type (SOCK_STREAM, ...)
 *	@protocol: protocol (0, ...)
 *	@res: new socket
 *	@kern: boolean for kernel space sockets
 *
 *	Creates a new socket and assigns it to @res, passing through LSM.
 *	Returns 0 or an error. On failure @res is set to %NULL. @kern must
 *	be set to true if the socket resides in kernel space.
 *	This function internally uses GFP_KERNEL.
 */

1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461
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) {
		pr_info_once("%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);

1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472
/**
 *	sock_create - creates a socket
 *	@family: protocol family (AF_INET, ...)
 *	@type: communication type (SOCK_STREAM, ...)
 *	@protocol: protocol (0, ...)
 *	@res: new socket
 *
 *	A wrapper around __sock_create().
 *	Returns 0 or an error. This function internally uses GFP_KERNEL.
 */

1473 1474 1475 1476 1477 1478
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);

1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490
/**
 *	sock_create_kern - creates a socket (kernel space)
 *	@net: net namespace
 *	@family: protocol family (AF_INET, ...)
 *	@type: communication type (SOCK_STREAM, ...)
 *	@protocol: protocol (0, ...)
 *	@res: new socket
 *
 *	A wrapper around __sock_create().
 *	Returns 0 or an error. This function internally uses GFP_KERNEL.
 */

1491 1492 1493 1494 1495 1496
int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res)
{
	return __sock_create(net, family, type, protocol, res, 1);
}
EXPORT_SYMBOL(sock_create_kern);

1497
int __sys_socket(int family, int type, int protocol)
1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518
{
	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)
1519
		return retval;
1520

1521
	return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
1522 1523
}

1524 1525 1526 1527 1528
SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
{
	return __sys_socket(family, type, protocol);
}

1529 1530 1531 1532
/*
 *	Create a pair of connected sockets.
 */

1533
int __sys_socketpair(int family, int type, int protocol, int __user *usockvec)
1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547
{
	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;

1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569
	/*
	 * reserve descriptors and make sure we won't fail
	 * to return them to userland.
	 */
	fd1 = get_unused_fd_flags(flags);
	if (unlikely(fd1 < 0))
		return fd1;

	fd2 = get_unused_fd_flags(flags);
	if (unlikely(fd2 < 0)) {
		put_unused_fd(fd1);
		return fd2;
	}

	err = put_user(fd1, &usockvec[0]);
	if (err)
		goto out;

	err = put_user(fd2, &usockvec[1]);
	if (err)
		goto out;

1570 1571 1572 1573 1574 1575
	/*
	 * Obtain the first socket and check if the underlying protocol
	 * supports the socketpair call.
	 */

	err = sock_create(family, type, protocol, &sock1);
1576
	if (unlikely(err < 0))
1577 1578 1579
		goto out;

	err = sock_create(family, type, protocol, &sock2);
1580 1581 1582
	if (unlikely(err < 0)) {
		sock_release(sock1);
		goto out;
1583 1584
	}

1585 1586 1587 1588 1589 1590 1591
	err = security_socket_socketpair(sock1, sock2);
	if (unlikely(err)) {
		sock_release(sock2);
		sock_release(sock1);
		goto out;
	}

1592 1593 1594 1595 1596
	err = sock1->ops->socketpair(sock1, sock2);
	if (unlikely(err < 0)) {
		sock_release(sock2);
		sock_release(sock1);
		goto out;
1597 1598 1599 1600 1601
	}

	newfile1 = sock_alloc_file(sock1, flags, NULL);
	if (IS_ERR(newfile1)) {
		err = PTR_ERR(newfile1);
1602 1603
		sock_release(sock2);
		goto out;
1604 1605 1606 1607 1608
	}

	newfile2 = sock_alloc_file(sock2, flags, NULL);
	if (IS_ERR(newfile2)) {
		err = PTR_ERR(newfile2);
1609 1610
		fput(newfile1);
		goto out;
1611 1612 1613 1614 1615 1616 1617 1618
	}

	audit_fd_pair(fd1, fd2);

	fd_install(fd1, newfile1);
	fd_install(fd2, newfile2);
	return 0;

1619
out:
1620 1621 1622 1623 1624
	put_unused_fd(fd2);
	put_unused_fd(fd1);
	return err;
}

1625 1626 1627 1628 1629 1630
SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
		int __user *, usockvec)
{
	return __sys_socketpair(family, type, protocol, usockvec);
}

1631 1632 1633 1634 1635 1636 1637 1638
/*
 *	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).
 */

1639
int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen)
1640 1641 1642 1643 1644 1645 1646 1647
{
	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);
1648
		if (!err) {
1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661
			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;
}

1662 1663 1664 1665 1666
SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
	return __sys_bind(fd, umyaddr, addrlen);
}

1667 1668 1669 1670 1671 1672
/*
 *	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.
 */

1673
int __sys_listen(int fd, int backlog)
1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693
{
	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;
}

1694 1695 1696 1697 1698
SYSCALL_DEFINE2(listen, int, fd, int, backlog)
{
	return __sys_listen(fd, backlog);
}

1699 1700 1701 1702 1703 1704 1705 1706 1707
/*
 *	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
1708
 *	clean when we restructure accept also.
1709 1710
 */

1711 1712
int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
		  int __user *upeer_addrlen, int flags)
1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759
{
	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 (IS_ERR(newfile)) {
		err = PTR_ERR(newfile);
		put_unused_fd(newfd);
		goto out_put;
	}

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

1760
	err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
1761 1762 1763 1764
	if (err < 0)
		goto out_fd;

	if (upeer_sockaddr) {
1765 1766 1767
		len = newsock->ops->getname(newsock,
					(struct sockaddr *)&address, 2);
		if (len < 0) {
1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791
			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;
}

1792 1793 1794 1795 1796 1797
SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen, int, flags)
{
	return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags);
}

1798 1799 1800
SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen)
{
1801
	return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815
}

/*
 *	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.
 */

1816
int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841
{
	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;
}

1842 1843 1844 1845 1846 1847
SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
		int, addrlen)
{
	return __sys_connect(fd, uservaddr, addrlen);
}

1848 1849 1850 1851 1852
/*
 *	Get the local address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

1853 1854
int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
		      int __user *usockaddr_len)
1855 1856 1857
{
	struct socket *sock;
	struct sockaddr_storage address;
1858
	int err, fput_needed;
1859 1860 1861 1862 1863 1864 1865 1866 1867

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

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

1868 1869
	err = sock->ops->getname(sock, (struct sockaddr *)&address, 0);
	if (err < 0)
1870
		goto out_put;
1871 1872
        /* "err" is actually length in this case */
	err = move_addr_to_user(&address, err, usockaddr, usockaddr_len);
1873 1874 1875 1876 1877 1878 1879

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

1880 1881 1882 1883 1884 1885
SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	return __sys_getsockname(fd, usockaddr, usockaddr_len);
}

1886 1887 1888 1889 1890
/*
 *	Get the remote address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

1891 1892
int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
		      int __user *usockaddr_len)
1893 1894 1895
{
	struct socket *sock;
	struct sockaddr_storage address;
1896
	int err, fput_needed;
1897 1898 1899 1900 1901 1902 1903 1904 1905

	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;
		}

1906 1907 1908 1909
		err = sock->ops->getname(sock, (struct sockaddr *)&address, 1);
		if (err >= 0)
			/* "err" is actually length in this case */
			err = move_addr_to_user(&address, err, usockaddr,
1910 1911 1912 1913 1914 1915
						usockaddr_len);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

1916 1917 1918 1919 1920 1921
SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	return __sys_getpeername(fd, usockaddr, usockaddr_len);
}

1922 1923 1924 1925 1926
/*
 *	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.
 */
1927 1928
int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
		 struct sockaddr __user *addr,  int addr_len)
1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err;
	struct msghdr msg;
	struct iovec iov;
	int fput_needed;

	err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter);
	if (unlikely(err))
		return err;
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	msg.msg_name = NULL;
	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);

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

1966 1967 1968 1969 1970 1971 1972
SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags, struct sockaddr __user *, addr,
		int, addr_len)
{
	return __sys_sendto(fd, buff, len, flags, addr, addr_len);
}

1973 1974 1975 1976 1977 1978 1979
/*
 *	Send a datagram down a socket.
 */

SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags)
{
1980
	return __sys_sendto(fd, buff, len, flags, NULL, 0);
1981 1982 1983 1984 1985 1986 1987
}

/*
 *	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.
 */
1988 1989
int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
		   struct sockaddr __user *addr, int __user *addr_len)
1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011
{
	struct socket *sock;
	struct iovec iov;
	struct msghdr msg;
	struct sockaddr_storage address;
	int err, err2;
	int fput_needed;

	err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter);
	if (unlikely(err))
		return err;
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	/* 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;
	msg.msg_iocb = NULL;
2012
	msg.msg_flags = 0;
2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	err = sock_recvmsg(sock, &msg, 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;
}

2029 2030 2031 2032 2033 2034 2035
SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
		unsigned int, flags, struct sockaddr __user *, addr,
		int __user *, addr_len)
{
	return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len);
}

2036 2037 2038 2039 2040 2041 2042
/*
 *	Receive a datagram from a socket.
 */

SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
		unsigned int, flags)
{
2043
	return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
2044 2045 2046 2047 2048 2049 2050
}

/*
 *	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.
 */

2051 2052
static int __sys_setsockopt(int fd, int level, int optname,
			    char __user *optval, int optlen)
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
{
	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;
}

2080 2081 2082 2083 2084 2085
SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int, optlen)
{
	return __sys_setsockopt(fd, level, optname, optval, optlen);
}

2086 2087 2088 2089 2090
/*
 *	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.
 */

2091 2092
static int __sys_getsockopt(int fd, int level, int optname,
			    char __user *optval, int __user *optlen)
2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116
{
	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;
}

2117 2118 2119 2120 2121 2122
SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int __user *, optlen)
{
	return __sys_getsockopt(fd, level, optname, optval, optlen);
}

2123 2124 2125 2126
/*
 *	Shutdown a socket.
 */

2127
int __sys_shutdown(int fd, int how)
2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141
{
	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;
}

2142 2143 2144 2145 2146
SYSCALL_DEFINE2(shutdown, int, fd, int, how)
{
	return __sys_shutdown(fd, how);
}

2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163
/* 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 user_msghdr __user *umsg,
				 struct sockaddr __user **save_addr,
				 struct iovec **iov)
{
2164
	struct user_msghdr msg;
2165 2166
	ssize_t err;

2167
	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
2168 2169
		return -EFAULT;

2170 2171 2172 2173 2174 2175
	kmsg->msg_control = (void __force *)msg.msg_control;
	kmsg->msg_controllen = msg.msg_controllen;
	kmsg->msg_flags = msg.msg_flags;

	kmsg->msg_namelen = msg.msg_namelen;
	if (!msg.msg_name)
2176 2177 2178 2179 2180 2181 2182 2183 2184
		kmsg->msg_namelen = 0;

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

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

	if (save_addr)
2185
		*save_addr = msg.msg_name;
2186

2187
	if (msg.msg_name && kmsg->msg_namelen) {
2188
		if (!save_addr) {
2189 2190
			err = move_addr_to_kernel(msg.msg_name,
						  kmsg->msg_namelen,
2191 2192 2193 2194 2195 2196 2197 2198 2199
						  kmsg->msg_name);
			if (err < 0)
				return err;
		}
	} else {
		kmsg->msg_name = NULL;
		kmsg->msg_namelen = 0;
	}

2200
	if (msg.msg_iovlen > UIO_MAXIOV)
2201 2202 2203 2204
		return -EMSGSIZE;

	kmsg->msg_iocb = NULL;

2205 2206
	return import_iovec(save_addr ? READ : WRITE,
			    msg.msg_iov, msg.msg_iovlen,
2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219
			    UIO_FASTIOV, iov, &kmsg->msg_iter);
}

static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
			 struct msghdr *msg_sys, unsigned int flags,
			 struct used_address *used_address,
			 unsigned int allowed_msghdr_flags)
{
	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]
2220
				__aligned(sizeof(__kernel_size_t));
2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249
	/* 20 is size of ipv6_pktinfo */
	unsigned char *ctl_buf = ctl;
	int ctl_len;
	ssize_t err;

	msg_sys->msg_name = &address;

	if (MSG_CMSG_COMPAT & flags)
		err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov);
	else
		err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov);
	if (err < 0)
		return err;

	err = -ENOBUFS;

	if (msg_sys->msg_controllen > INT_MAX)
		goto out_freeiov;
	flags |= (msg_sys->msg_flags & allowed_msghdr_flags);
	ctl_len = msg_sys->msg_controllen;
	if ((MSG_CMSG_COMPAT & flags) && ctl_len) {
		err =
		    cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl,
						     sizeof(ctl));
		if (err)
			goto out_freeiov;
		ctl_buf = msg_sys->msg_control;
		ctl_len = msg_sys->msg_controllen;
	} else if (ctl_len) {
2250 2251
		BUILD_BUG_ON(sizeof(struct cmsghdr) !=
			     CMSG_ALIGN(sizeof(struct cmsghdr)));
2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299