af_unix.c 48.1 KB
Newer Older
L
Linus Torvalds 已提交
1 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 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106
/*
 * NET4:	Implementation of BSD Unix domain sockets.
 *
 * Authors:	Alan Cox, <alan.cox@linux.org>
 *
 *		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.
 *
 * Version:	$Id: af_unix.c,v 1.133 2002/02/08 03:57:19 davem Exp $
 *
 * Fixes:
 *		Linus Torvalds	:	Assorted bug cures.
 *		Niibe Yutaka	:	async I/O support.
 *		Carsten Paeth	:	PF_UNIX check, address fixes.
 *		Alan Cox	:	Limit size of allocated blocks.
 *		Alan Cox	:	Fixed the stupid socketpair bug.
 *		Alan Cox	:	BSD compatibility fine tuning.
 *		Alan Cox	:	Fixed a bug in connect when interrupted.
 *		Alan Cox	:	Sorted out a proper draft version of
 *					file descriptor passing hacked up from
 *					Mike Shaver's work.
 *		Marty Leisner	:	Fixes to fd passing
 *		Nick Nevin	:	recvmsg bugfix.
 *		Alan Cox	:	Started proper garbage collector
 *		Heiko EiBfeldt	:	Missing verify_area check
 *		Alan Cox	:	Started POSIXisms
 *		Andreas Schwab	:	Replace inode by dentry for proper
 *					reference counting
 *		Kirk Petersen	:	Made this a module
 *	    Christoph Rohland	:	Elegant non-blocking accept/connect algorithm.
 *					Lots of bug fixes.
 *	     Alexey Kuznetosv	:	Repaired (I hope) bugs introduces
 *					by above two patches.
 *	     Andrea Arcangeli	:	If possible we block in connect(2)
 *					if the max backlog of the listen socket
 *					is been reached. This won't break
 *					old apps and it will avoid huge amount
 *					of socks hashed (this for unix_gc()
 *					performances reasons).
 *					Security fix that limits the max
 *					number of socks to 2*max_files and
 *					the number of skb queueable in the
 *					dgram receiver.
 *		Artur Skawina   :	Hash function optimizations
 *	     Alexey Kuznetsov   :	Full scale SMP. Lot of bugs are introduced 8)
 *	      Malcolm Beattie   :	Set peercred for socketpair
 *	     Michal Ostrowski   :       Module initialization cleanup.
 *	     Arnaldo C. Melo	:	Remove MOD_{INC,DEC}_USE_COUNT,
 *	     				the core infrastructure is doing that
 *	     				for all net proto families now (2.5.69+)
 *
 *
 * Known differences from reference BSD that was tested:
 *
 *	[TO FIX]
 *	ECONNREFUSED is not returned from one end of a connected() socket to the
 *		other the moment one end closes.
 *	fstat() doesn't return st_dev=0, and give the blksize as high water mark
 *		and a fake inode identifier (nor the BSD first socket fstat twice bug).
 *	[NOT TO FIX]
 *	accept() returns a path name even if the connecting socket has closed
 *		in the meantime (BSD loses the path and gives up).
 *	accept() returns 0 length path for an unbound connector. BSD returns 16
 *		and a null first byte in the path (but not for gethost/peername - BSD bug ??)
 *	socketpair(...SOCK_RAW..) doesn't panic the kernel.
 *	BSD af_unix apparently has connect forgetting to block properly.
 *		(need to check this with the POSIX spec in detail)
 *
 * Differences from 2.0.0-11-... (ANK)
 *	Bug fixes and improvements.
 *		- client shutdown killed server socket.
 *		- removed all useless cli/sti pairs.
 *
 *	Semantic changes/extensions.
 *		- generic control message passing.
 *		- SCM_CREDENTIALS control message.
 *		- "Abstract" (not FS based) socket bindings.
 *		  Abstract names are sequences of bytes (not zero terminated)
 *		  started by 0, so that this name space does not intersect
 *		  with BSD names.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/dcache.h>
#include <linux/namei.h>
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <net/sock.h>
107
#include <net/tcp_states.h>
L
Linus Torvalds 已提交
108 109 110 111 112 113 114 115 116 117 118
#include <net/af_unix.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/scm.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/rtnetlink.h>
#include <linux/mount.h>
#include <net/checksum.h>
#include <linux/security.h>

119
int sysctl_unix_max_dgram_qlen __read_mostly = 10;
L
Linus Torvalds 已提交
120 121

struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
122
DEFINE_SPINLOCK(unix_table_lock);
L
Linus Torvalds 已提交
123 124 125 126 127 128
static atomic_t unix_nr_socks = ATOMIC_INIT(0);

#define unix_sockets_unbound	(&unix_socket_table[UNIX_HASH_SIZE])

#define UNIX_ABSTRACT(sk)	(unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)

C
Catherine Zhang 已提交
129
#ifdef CONFIG_SECURITY_NETWORK
130
static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
C
Catherine Zhang 已提交
131
{
132
	memcpy(UNIXSID(skb), &scm->secid, sizeof(u32));
C
Catherine Zhang 已提交
133 134 135 136
}

static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{
137
	scm->secid = *UNIXSID(skb);
C
Catherine Zhang 已提交
138 139
}
#else
140
static inline void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
C
Catherine Zhang 已提交
141 142 143 144 145 146
{ }

static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{ }
#endif /* CONFIG_SECURITY_NETWORK */

L
Linus Torvalds 已提交
147 148
/*
 *  SMP locking strategy:
149
 *    hash table is protected with spinlock unix_table_lock
L
Linus Torvalds 已提交
150 151 152
 *    each socket state is protected by separate rwlock.
 */

153
static inline unsigned unix_hash_fold(__wsum n)
L
Linus Torvalds 已提交
154
{
155
	unsigned hash = (__force unsigned)n;
L
Linus Torvalds 已提交
156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176
	hash ^= hash>>16;
	hash ^= hash>>8;
	return hash&(UNIX_HASH_SIZE-1);
}

#define unix_peer(sk) (unix_sk(sk)->peer)

static inline int unix_our_peer(struct sock *sk, struct sock *osk)
{
	return unix_peer(osk) == sk;
}

static inline int unix_may_send(struct sock *sk, struct sock *osk)
{
	return (unix_peer(osk) == NULL || unix_our_peer(sk, osk));
}

static struct sock *unix_peer_get(struct sock *s)
{
	struct sock *peer;

177
	unix_state_lock(s);
L
Linus Torvalds 已提交
178 179 180
	peer = unix_peer(s);
	if (peer)
		sock_hold(peer);
181
	unix_state_unlock(s);
L
Linus Torvalds 已提交
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
	return peer;
}

static inline void unix_release_addr(struct unix_address *addr)
{
	if (atomic_dec_and_test(&addr->refcnt))
		kfree(addr);
}

/*
 *	Check unix socket name:
 *		- should be not zero length.
 *	        - if started by not zero, should be NULL terminated (FS object)
 *		- if started by zero, it is abstract name.
 */
197

L
Linus Torvalds 已提交
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
static int unix_mkname(struct sockaddr_un * sunaddr, int len, unsigned *hashp)
{
	if (len <= sizeof(short) || len > sizeof(*sunaddr))
		return -EINVAL;
	if (!sunaddr || sunaddr->sun_family != AF_UNIX)
		return -EINVAL;
	if (sunaddr->sun_path[0]) {
		/*
		 * This may look like an off by one error but it is a bit more
		 * subtle. 108 is the longest valid AF_UNIX path for a binding.
		 * sun_path[108] doesnt as such exist.  However in kernel space
		 * we are guaranteed that it is a valid memory location in our
		 * kernel address buffer.
		 */
		((char *)sunaddr)[len]=0;
		len = strlen(sunaddr->sun_path)+1+sizeof(short);
		return len;
	}

	*hashp = unix_hash_fold(csum_partial((char*)sunaddr, len, 0));
	return len;
}

static void __unix_remove_socket(struct sock *sk)
{
	sk_del_node_init(sk);
}

static void __unix_insert_socket(struct hlist_head *list, struct sock *sk)
{
	BUG_TRAP(sk_unhashed(sk));
	sk_add_node(sk, list);
}

static inline void unix_remove_socket(struct sock *sk)
{
234
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
235
	__unix_remove_socket(sk);
236
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
237 238 239 240
}

static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
{
241
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
242
	__unix_insert_socket(list, sk);
243
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
}

static struct sock *__unix_find_socket_byname(struct sockaddr_un *sunname,
					      int len, int type, unsigned hash)
{
	struct sock *s;
	struct hlist_node *node;

	sk_for_each(s, node, &unix_socket_table[hash ^ type]) {
		struct unix_sock *u = unix_sk(s);

		if (u->addr->len == len &&
		    !memcmp(u->addr->name, sunname, len))
			goto found;
	}
	s = NULL;
found:
	return s;
}

static inline struct sock *unix_find_socket_byname(struct sockaddr_un *sunname,
						   int len, int type,
						   unsigned hash)
{
	struct sock *s;

270
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
271 272 273
	s = __unix_find_socket_byname(sunname, len, type, hash);
	if (s)
		sock_hold(s);
274
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
275 276 277 278 279 280 281 282
	return s;
}

static struct sock *unix_find_socket_byinode(struct inode *i)
{
	struct sock *s;
	struct hlist_node *node;

283
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
284 285 286 287 288 289 290 291 292 293 294 295
	sk_for_each(s, node,
		    &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
		struct dentry *dentry = unix_sk(s)->dentry;

		if(dentry && dentry->d_inode == i)
		{
			sock_hold(s);
			goto found;
		}
	}
	s = NULL;
found:
296
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
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
	return s;
}

static inline int unix_writable(struct sock *sk)
{
	return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
}

static void unix_write_space(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);
	if (unix_writable(sk)) {
		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
			wake_up_interruptible(sk->sk_sleep);
		sk_wake_async(sk, 2, POLL_OUT);
	}
	read_unlock(&sk->sk_callback_lock);
}

/* When dgram socket disconnects (or changes its peer), we clear its receive
 * queue of packets arrived from previous peer. First, it allows to do
 * flow control based only on wmem_alloc; second, sk connected to peer
 * may receive messages only from that peer. */
static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
{
322
	if (!skb_queue_empty(&sk->sk_receive_queue)) {
L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
		skb_queue_purge(&sk->sk_receive_queue);
		wake_up_interruptible_all(&unix_sk(sk)->peer_wait);

		/* If one link of bidirectional dgram pipe is disconnected,
		 * we signal error. Messages are lost. Do not make this,
		 * when peer was not connected to us.
		 */
		if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) {
			other->sk_err = ECONNRESET;
			other->sk_error_report(other);
		}
	}
}

static void unix_sock_destructor(struct sock *sk)
{
	struct unix_sock *u = unix_sk(sk);

	skb_queue_purge(&sk->sk_receive_queue);

	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
	BUG_TRAP(sk_unhashed(sk));
	BUG_TRAP(!sk->sk_socket);
	if (!sock_flag(sk, SOCK_DEAD)) {
		printk("Attempt to release alive unix socket: %p\n", sk);
		return;
	}

	if (u->addr)
		unix_release_addr(u->addr);

	atomic_dec(&unix_nr_socks);
#ifdef UNIX_REFCNT_DEBUG
	printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk, atomic_read(&unix_nr_socks));
#endif
}

static int unix_release_sock (struct sock *sk, int embrion)
{
	struct unix_sock *u = unix_sk(sk);
	struct dentry *dentry;
	struct vfsmount *mnt;
	struct sock *skpair;
	struct sk_buff *skb;
	int state;

	unix_remove_socket(sk);

	/* Clear state */
372
	unix_state_lock(sk);
L
Linus Torvalds 已提交
373 374 375 376 377 378 379 380
	sock_orphan(sk);
	sk->sk_shutdown = SHUTDOWN_MASK;
	dentry	     = u->dentry;
	u->dentry    = NULL;
	mnt	     = u->mnt;
	u->mnt	     = NULL;
	state = sk->sk_state;
	sk->sk_state = TCP_CLOSE;
381
	unix_state_unlock(sk);
L
Linus Torvalds 已提交
382 383 384 385 386 387 388

	wake_up_interruptible_all(&u->peer_wait);

	skpair=unix_peer(sk);

	if (skpair!=NULL) {
		if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
389
			unix_state_lock(skpair);
L
Linus Torvalds 已提交
390 391 392 393
			/* No more writes */
			skpair->sk_shutdown = SHUTDOWN_MASK;
			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
				skpair->sk_err = ECONNRESET;
394
			unix_state_unlock(skpair);
L
Linus Torvalds 已提交
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
			skpair->sk_state_change(skpair);
			read_lock(&skpair->sk_callback_lock);
			sk_wake_async(skpair,1,POLL_HUP);
			read_unlock(&skpair->sk_callback_lock);
		}
		sock_put(skpair); /* It may now die */
		unix_peer(sk) = NULL;
	}

	/* Try to flush out this socket. Throw out buffers at least */

	while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		if (state==TCP_LISTEN)
			unix_release_sock(skb->sk, 1);
		/* passed fds are erased in the kfree_skb hook	      */
		kfree_skb(skb);
	}

	if (dentry) {
		dput(dentry);
		mntput(mnt);
	}

	sock_put(sk);

	/* ---- Socket is dead now and most probably destroyed ---- */

	/*
	 * Fixme: BSD difference: In BSD all sockets connected to use get
	 *	  ECONNRESET and we die on the spot. In Linux we behave
	 *	  like files and pipes do and wait for the last
	 *	  dereference.
	 *
	 * Can't we simply set sock->err?
	 *
	 *	  What the above comment does talk about? --ANK(980817)
	 */

	if (atomic_read(&unix_tot_inflight))
434
		unix_gc();		/* Garbage collect fds */
L
Linus Torvalds 已提交
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450

	return 0;
}

static int unix_listen(struct socket *sock, int backlog)
{
	int err;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);

	err = -EOPNOTSUPP;
	if (sock->type!=SOCK_STREAM && sock->type!=SOCK_SEQPACKET)
		goto out;			/* Only stream/seqpacket sockets accept */
	err = -EINVAL;
	if (!u->addr)
		goto out;			/* No listens on an unbound socket */
451
	unix_state_lock(sk);
L
Linus Torvalds 已提交
452 453 454 455 456 457 458 459 460 461 462 463 464
	if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN)
		goto out_unlock;
	if (backlog > sk->sk_max_ack_backlog)
		wake_up_interruptible_all(&u->peer_wait);
	sk->sk_max_ack_backlog	= backlog;
	sk->sk_state		= TCP_LISTEN;
	/* set credentials so connect can copy them */
	sk->sk_peercred.pid	= current->tgid;
	sk->sk_peercred.uid	= current->euid;
	sk->sk_peercred.gid	= current->egid;
	err = 0;

out_unlock:
465
	unix_state_unlock(sk);
L
Linus Torvalds 已提交
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
out:
	return err;
}

static int unix_release(struct socket *);
static int unix_bind(struct socket *, struct sockaddr *, int);
static int unix_stream_connect(struct socket *, struct sockaddr *,
			       int addr_len, int flags);
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int);
static int unix_getname(struct socket *, struct sockaddr *, int *, int);
static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct kiocb *, struct socket *,
			       struct msghdr *, size_t);
static int unix_stream_recvmsg(struct kiocb *, struct socket *,
			       struct msghdr *, size_t, int);
static int unix_dgram_sendmsg(struct kiocb *, struct socket *,
			      struct msghdr *, size_t);
static int unix_dgram_recvmsg(struct kiocb *, struct socket *,
			      struct msghdr *, size_t, int);
static int unix_dgram_connect(struct socket *, struct sockaddr *,
			      int, int);
static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
				  struct msghdr *, size_t);

493
static const struct proto_ops unix_stream_ops = {
L
Linus Torvalds 已提交
494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513
	.family =	PF_UNIX,
	.owner =	THIS_MODULE,
	.release =	unix_release,
	.bind =		unix_bind,
	.connect =	unix_stream_connect,
	.socketpair =	unix_socketpair,
	.accept =	unix_accept,
	.getname =	unix_getname,
	.poll =		unix_poll,
	.ioctl =	unix_ioctl,
	.listen =	unix_listen,
	.shutdown =	unix_shutdown,
	.setsockopt =	sock_no_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	unix_stream_sendmsg,
	.recvmsg =	unix_stream_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

514
static const struct proto_ops unix_dgram_ops = {
L
Linus Torvalds 已提交
515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
	.family =	PF_UNIX,
	.owner =	THIS_MODULE,
	.release =	unix_release,
	.bind =		unix_bind,
	.connect =	unix_dgram_connect,
	.socketpair =	unix_socketpair,
	.accept =	sock_no_accept,
	.getname =	unix_getname,
	.poll =		datagram_poll,
	.ioctl =	unix_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	unix_shutdown,
	.setsockopt =	sock_no_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	unix_dgram_sendmsg,
	.recvmsg =	unix_dgram_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

535
static const struct proto_ops unix_seqpacket_ops = {
L
Linus Torvalds 已提交
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
	.family =	PF_UNIX,
	.owner =	THIS_MODULE,
	.release =	unix_release,
	.bind =		unix_bind,
	.connect =	unix_stream_connect,
	.socketpair =	unix_socketpair,
	.accept =	unix_accept,
	.getname =	unix_getname,
	.poll =		datagram_poll,
	.ioctl =	unix_ioctl,
	.listen =	unix_listen,
	.shutdown =	unix_shutdown,
	.setsockopt =	sock_no_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	unix_seqpacket_sendmsg,
	.recvmsg =	unix_dgram_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

static struct proto unix_proto = {
	.name	  = "UNIX",
	.owner	  = THIS_MODULE,
	.obj_size = sizeof(struct unix_sock),
};

562 563 564 565 566 567 568 569
/*
 * AF_UNIX sockets do not interact with hardware, hence they
 * dont trigger interrupts - so it's safe for them to have
 * bh-unsafe locking for their sk_receive_queue.lock. Split off
 * this special lock-class by reinitializing the spinlock key:
 */
static struct lock_class_key af_unix_sk_receive_queue_lock_key;

L
Linus Torvalds 已提交
570 571 572 573 574
static struct sock * unix_create1(struct socket *sock)
{
	struct sock *sk = NULL;
	struct unix_sock *u;

D
Dipankar Sarma 已提交
575
	if (atomic_read(&unix_nr_socks) >= 2*get_max_files())
L
Linus Torvalds 已提交
576 577 578 579 580 581 582 583 584
		goto out;

	sk = sk_alloc(PF_UNIX, GFP_KERNEL, &unix_proto, 1);
	if (!sk)
		goto out;

	atomic_inc(&unix_nr_socks);

	sock_init_data(sock,sk);
585 586
	lockdep_set_class(&sk->sk_receive_queue.lock,
				&af_unix_sk_receive_queue_lock_key);
L
Linus Torvalds 已提交
587 588 589 590 591 592 593

	sk->sk_write_space	= unix_write_space;
	sk->sk_max_ack_backlog	= sysctl_unix_max_dgram_qlen;
	sk->sk_destruct		= unix_sock_destructor;
	u	  = unix_sk(sk);
	u->dentry = NULL;
	u->mnt	  = NULL;
594
	spin_lock_init(&u->lock);
595 596
	atomic_set(&u->inflight, 0);
	INIT_LIST_HEAD(&u->link);
I
Ingo Molnar 已提交
597
	mutex_init(&u->readlock); /* single task reading lock */
L
Linus Torvalds 已提交
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
	init_waitqueue_head(&u->peer_wait);
	unix_insert_socket(unix_sockets_unbound, sk);
out:
	return sk;
}

static int unix_create(struct socket *sock, int protocol)
{
	if (protocol && protocol != PF_UNIX)
		return -EPROTONOSUPPORT;

	sock->state = SS_UNCONNECTED;

	switch (sock->type) {
	case SOCK_STREAM:
		sock->ops = &unix_stream_ops;
		break;
		/*
		 *	Believe it or not BSD has AF_UNIX, SOCK_RAW though
		 *	nothing uses it.
		 */
	case SOCK_RAW:
		sock->type=SOCK_DGRAM;
	case SOCK_DGRAM:
		sock->ops = &unix_dgram_ops;
		break;
	case SOCK_SEQPACKET:
		sock->ops = &unix_seqpacket_ops;
		break;
	default:
		return -ESOCKTNOSUPPORT;
	}

	return unix_create1(sock) ? 0 : -ENOMEM;
}

static int unix_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (!sk)
		return 0;

	sock->sk = NULL;

	return unix_release_sock (sk, 0);
}

static int unix_autobind(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	static u32 ordernum = 1;
	struct unix_address * addr;
	int err;

I
Ingo Molnar 已提交
654
	mutex_lock(&u->readlock);
L
Linus Torvalds 已提交
655 656 657 658 659 660

	err = 0;
	if (u->addr)
		goto out;

	err = -ENOMEM;
661
	addr = kzalloc(sizeof(*addr) + sizeof(short) + 16, GFP_KERNEL);
L
Linus Torvalds 已提交
662 663 664 665 666 667 668 669 670 671
	if (!addr)
		goto out;

	addr->name->sun_family = AF_UNIX;
	atomic_set(&addr->refcnt, 1);

retry:
	addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short);
	addr->hash = unix_hash_fold(csum_partial((void*)addr->name, addr->len, 0));

672
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
673 674 675 676
	ordernum = (ordernum+1)&0xFFFFF;

	if (__unix_find_socket_byname(addr->name, addr->len, sock->type,
				      addr->hash)) {
677
		spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
678 679 680 681 682 683 684 685 686 687
		/* Sanity yield. It is unusual case, but yet... */
		if (!(ordernum&0xFF))
			yield();
		goto retry;
	}
	addr->hash ^= sk->sk_type;

	__unix_remove_socket(sk);
	u->addr = addr;
	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
688
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
689 690
	err = 0;

I
Ingo Molnar 已提交
691
out:	mutex_unlock(&u->readlock);
L
Linus Torvalds 已提交
692 693 694 695 696 697 698 699 700
	return err;
}

static struct sock *unix_find_other(struct sockaddr_un *sunname, int len,
				    int type, unsigned hash, int *error)
{
	struct sock *u;
	struct nameidata nd;
	int err = 0;
701

L
Linus Torvalds 已提交
702 703 704 705
	if (sunname->sun_path[0]) {
		err = path_lookup(sunname->sun_path, LOOKUP_FOLLOW, &nd);
		if (err)
			goto fail;
706
		err = vfs_permission(&nd, MAY_WRITE);
L
Linus Torvalds 已提交
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773
		if (err)
			goto put_fail;

		err = -ECONNREFUSED;
		if (!S_ISSOCK(nd.dentry->d_inode->i_mode))
			goto put_fail;
		u=unix_find_socket_byinode(nd.dentry->d_inode);
		if (!u)
			goto put_fail;

		if (u->sk_type == type)
			touch_atime(nd.mnt, nd.dentry);

		path_release(&nd);

		err=-EPROTOTYPE;
		if (u->sk_type != type) {
			sock_put(u);
			goto fail;
		}
	} else {
		err = -ECONNREFUSED;
		u=unix_find_socket_byname(sunname, len, type, hash);
		if (u) {
			struct dentry *dentry;
			dentry = unix_sk(u)->dentry;
			if (dentry)
				touch_atime(unix_sk(u)->mnt, dentry);
		} else
			goto fail;
	}
	return u;

put_fail:
	path_release(&nd);
fail:
	*error=err;
	return NULL;
}


static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
	struct dentry * dentry = NULL;
	struct nameidata nd;
	int err;
	unsigned hash;
	struct unix_address *addr;
	struct hlist_head *list;

	err = -EINVAL;
	if (sunaddr->sun_family != AF_UNIX)
		goto out;

	if (addr_len==sizeof(short)) {
		err = unix_autobind(sock);
		goto out;
	}

	err = unix_mkname(sunaddr, addr_len, &hash);
	if (err < 0)
		goto out;
	addr_len = err;

I
Ingo Molnar 已提交
774
	mutex_lock(&u->readlock);
L
Linus Torvalds 已提交
775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799

	err = -EINVAL;
	if (u->addr)
		goto out_up;

	err = -ENOMEM;
	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
	if (!addr)
		goto out_up;

	memcpy(addr->name, sunaddr, addr_len);
	addr->len = addr_len;
	addr->hash = hash ^ sk->sk_type;
	atomic_set(&addr->refcnt, 1);

	if (sunaddr->sun_path[0]) {
		unsigned int mode;
		err = 0;
		/*
		 * Get the parent directory, calculate the hash for last
		 * component.
		 */
		err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
		if (err)
			goto out_mknod_parent;
800 801

		dentry = lookup_create(&nd, 0);
L
Linus Torvalds 已提交
802 803 804
		err = PTR_ERR(dentry);
		if (IS_ERR(dentry))
			goto out_mknod_unlock;
805

L
Linus Torvalds 已提交
806 807 808 809 810 811 812 813
		/*
		 * All right, let's create it.
		 */
		mode = S_IFSOCK |
		       (SOCK_INODE(sock)->i_mode & ~current->fs->umask);
		err = vfs_mknod(nd.dentry->d_inode, dentry, mode, 0);
		if (err)
			goto out_mknod_dput;
814
		mutex_unlock(&nd.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
815 816 817 818 819 820
		dput(nd.dentry);
		nd.dentry = dentry;

		addr->hash = UNIX_HASH_SIZE;
	}

821
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843

	if (!sunaddr->sun_path[0]) {
		err = -EADDRINUSE;
		if (__unix_find_socket_byname(sunaddr, addr_len,
					      sk->sk_type, hash)) {
			unix_release_addr(addr);
			goto out_unlock;
		}

		list = &unix_socket_table[addr->hash];
	} else {
		list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
		u->dentry = nd.dentry;
		u->mnt    = nd.mnt;
	}

	err = 0;
	__unix_remove_socket(sk);
	u->addr = addr;
	__unix_insert_socket(list, sk);

out_unlock:
844
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
845
out_up:
I
Ingo Molnar 已提交
846
	mutex_unlock(&u->readlock);
L
Linus Torvalds 已提交
847 848 849 850 851 852
out:
	return err;

out_mknod_dput:
	dput(dentry);
out_mknod_unlock:
853
	mutex_unlock(&nd.dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
854 855 856 857 858 859 860 861
	path_release(&nd);
out_mknod_parent:
	if (err==-EEXIST)
		err=-EADDRINUSE;
	unix_release_addr(addr);
	goto out_up;
}

862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
{
	if (unlikely(sk1 == sk2) || !sk2) {
		unix_state_lock(sk1);
		return;
	}
	if (sk1 < sk2) {
		unix_state_lock(sk1);
		unix_state_lock_nested(sk2);
	} else {
		unix_state_lock(sk2);
		unix_state_lock_nested(sk1);
	}
}

static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
{
	if (unlikely(sk1 == sk2) || !sk2) {
		unix_state_unlock(sk1);
		return;
	}
	unix_state_unlock(sk1);
	unix_state_unlock(sk2);
}

L
Linus Torvalds 已提交
887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905
static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
			      int alen, int flags)
{
	struct sock *sk = sock->sk;
	struct sockaddr_un *sunaddr=(struct sockaddr_un*)addr;
	struct sock *other;
	unsigned hash;
	int err;

	if (addr->sa_family != AF_UNSPEC) {
		err = unix_mkname(sunaddr, alen, &hash);
		if (err < 0)
			goto out;
		alen = err;

		if (test_bit(SOCK_PASSCRED, &sock->flags) &&
		    !unix_sk(sk)->addr && (err = unix_autobind(sock)) != 0)
			goto out;

906
restart:
L
Linus Torvalds 已提交
907 908 909 910
		other=unix_find_other(sunaddr, alen, sock->type, hash, &err);
		if (!other)
			goto out;

911 912 913 914 915 916 917 918
		unix_state_double_lock(sk, other);

		/* Apparently VFS overslept socket death. Retry. */
		if (sock_flag(other, SOCK_DEAD)) {
			unix_state_double_unlock(sk, other);
			sock_put(other);
			goto restart;
		}
L
Linus Torvalds 已提交
919 920 921 922 923 924 925 926 927 928 929 930 931 932

		err = -EPERM;
		if (!unix_may_send(sk, other))
			goto out_unlock;

		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
		if (err)
			goto out_unlock;

	} else {
		/*
		 *	1003.1g breaking connected state with AF_UNSPEC
		 */
		other = NULL;
933
		unix_state_double_lock(sk, other);
L
Linus Torvalds 已提交
934 935 936 937 938 939 940 941
	}

	/*
	 * If it was connected, reconnect.
	 */
	if (unix_peer(sk)) {
		struct sock *old_peer = unix_peer(sk);
		unix_peer(sk)=other;
942
		unix_state_double_unlock(sk, other);
L
Linus Torvalds 已提交
943 944 945 946 947 948

		if (other != old_peer)
			unix_dgram_disconnected(sk, old_peer);
		sock_put(old_peer);
	} else {
		unix_peer(sk)=other;
949
		unix_state_double_unlock(sk, other);
L
Linus Torvalds 已提交
950
	}
951
	return 0;
L
Linus Torvalds 已提交
952 953

out_unlock:
954
	unix_state_double_unlock(sk, other);
L
Linus Torvalds 已提交
955 956 957 958 959 960 961 962 963 964 965 966 967 968 969
	sock_put(other);
out:
	return err;
}

static long unix_wait_for_peer(struct sock *other, long timeo)
{
	struct unix_sock *u = unix_sk(other);
	int sched;
	DEFINE_WAIT(wait);

	prepare_to_wait_exclusive(&u->peer_wait, &wait, TASK_INTERRUPTIBLE);

	sched = !sock_flag(other, SOCK_DEAD) &&
		!(other->sk_shutdown & RCV_SHUTDOWN) &&
970
		(skb_queue_len(&other->sk_receive_queue) >
L
Linus Torvalds 已提交
971 972
		 other->sk_max_ack_backlog);

973
	unix_state_unlock(other);
L
Linus Torvalds 已提交
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

	if (sched)
		timeo = schedule_timeout(timeo);

	finish_wait(&u->peer_wait, &wait);
	return timeo;
}

static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			       int addr_len, int flags)
{
	struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk), *newu, *otheru;
	struct sock *newsk = NULL;
	struct sock *other = NULL;
	struct sk_buff *skb = NULL;
	unsigned hash;
	int st;
	int err;
	long timeo;

	err = unix_mkname(sunaddr, addr_len, &hash);
	if (err < 0)
		goto out;
	addr_len = err;

	if (test_bit(SOCK_PASSCRED, &sock->flags)
		&& !u->addr && (err = unix_autobind(sock)) != 0)
		goto out;

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);

	/* First of all allocate resources.
	   If we will make it after state is locked,
	   we will have to recheck all again in any case.
	 */

	err = -ENOMEM;

	/* create new sock for complete connection */
	newsk = unix_create1(NULL);
	if (newsk == NULL)
		goto out;

	/* Allocate skb for sending to listening sock */
	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
	if (skb == NULL)
		goto out;

restart:
	/*  Find listening sock. */
	other = unix_find_other(sunaddr, addr_len, sk->sk_type, hash, &err);
	if (!other)
		goto out;

	/* Latch state of peer */
1031
	unix_state_lock(other);
L
Linus Torvalds 已提交
1032 1033 1034

	/* Apparently VFS overslept socket death. Retry. */
	if (sock_flag(other, SOCK_DEAD)) {
1035
		unix_state_unlock(other);
L
Linus Torvalds 已提交
1036 1037 1038 1039 1040 1041 1042 1043
		sock_put(other);
		goto restart;
	}

	err = -ECONNREFUSED;
	if (other->sk_state != TCP_LISTEN)
		goto out_unlock;

1044
	if (skb_queue_len(&other->sk_receive_queue) >
L
Linus Torvalds 已提交
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056
	    other->sk_max_ack_backlog) {
		err = -EAGAIN;
		if (!timeo)
			goto out_unlock;

		timeo = unix_wait_for_peer(other, timeo);

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
		sock_put(other);
		goto restart;
1057
	}
L
Linus Torvalds 已提交
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

	/* Latch our state.

	   It is tricky place. We need to grab write lock and cannot
	   drop lock on peer. It is dangerous because deadlock is
	   possible. Connect to self case and simultaneous
	   attempt to connect are eliminated by checking socket
	   state. other is TCP_LISTEN, if sk is TCP_LISTEN we
	   check this before attempt to grab lock.

	   Well, and we have to recheck the state after socket locked.
	 */
	st = sk->sk_state;

	switch (st) {
	case TCP_CLOSE:
		/* This is ok... continue with connect */
		break;
	case TCP_ESTABLISHED:
		/* Socket is already connected */
		err = -EISCONN;
		goto out_unlock;
	default:
		err = -EINVAL;
		goto out_unlock;
	}

1085
	unix_state_lock_nested(sk);
L
Linus Torvalds 已提交
1086 1087

	if (sk->sk_state != st) {
1088 1089
		unix_state_unlock(sk);
		unix_state_unlock(other);
L
Linus Torvalds 已提交
1090 1091 1092 1093 1094 1095
		sock_put(other);
		goto restart;
	}

	err = security_unix_stream_connect(sock, other->sk_socket, newsk);
	if (err) {
1096
		unix_state_unlock(sk);
L
Linus Torvalds 已提交
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
		goto out_unlock;
	}

	/* The way is open! Fastly set all the necessary fields... */

	sock_hold(sk);
	unix_peer(newsk)	= sk;
	newsk->sk_state		= TCP_ESTABLISHED;
	newsk->sk_type		= sk->sk_type;
	newsk->sk_peercred.pid	= current->tgid;
	newsk->sk_peercred.uid	= current->euid;
	newsk->sk_peercred.gid	= current->egid;
	newu = unix_sk(newsk);
	newsk->sk_sleep		= &newu->peer_wait;
	otheru = unix_sk(other);

	/* copy address information from listening to new sock*/
	if (otheru->addr) {
		atomic_inc(&otheru->addr->refcnt);
		newu->addr = otheru->addr;
	}
	if (otheru->dentry) {
		newu->dentry	= dget(otheru->dentry);
		newu->mnt	= mntget(otheru->mnt);
	}

	/* Set credentials */
	sk->sk_peercred = other->sk_peercred;

	sock->state	= SS_CONNECTED;
	sk->sk_state	= TCP_ESTABLISHED;
1128 1129 1130 1131
	sock_hold(newsk);

	smp_mb__after_atomic_inc();	/* sock_hold() does an atomic_inc() */
	unix_peer(sk)	= newsk;
L
Linus Torvalds 已提交
1132

1133
	unix_state_unlock(sk);
L
Linus Torvalds 已提交
1134 1135 1136 1137 1138

	/* take ten and and send info to listening sock */
	spin_lock(&other->sk_receive_queue.lock);
	__skb_queue_tail(&other->sk_receive_queue, skb);
	spin_unlock(&other->sk_receive_queue.lock);
1139
	unix_state_unlock(other);
L
Linus Torvalds 已提交
1140 1141 1142 1143 1144 1145
	other->sk_data_ready(other, 0);
	sock_put(other);
	return 0;

out_unlock:
	if (other)
1146
		unix_state_unlock(other);
L
Linus Torvalds 已提交
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 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211

out:
	if (skb)
		kfree_skb(skb);
	if (newsk)
		unix_release_sock(newsk, 0);
	if (other)
		sock_put(other);
	return err;
}

static int unix_socketpair(struct socket *socka, struct socket *sockb)
{
	struct sock *ska=socka->sk, *skb = sockb->sk;

	/* Join our sockets back to back */
	sock_hold(ska);
	sock_hold(skb);
	unix_peer(ska)=skb;
	unix_peer(skb)=ska;
	ska->sk_peercred.pid = skb->sk_peercred.pid = current->tgid;
	ska->sk_peercred.uid = skb->sk_peercred.uid = current->euid;
	ska->sk_peercred.gid = skb->sk_peercred.gid = current->egid;

	if (ska->sk_type != SOCK_DGRAM) {
		ska->sk_state = TCP_ESTABLISHED;
		skb->sk_state = TCP_ESTABLISHED;
		socka->state  = SS_CONNECTED;
		sockb->state  = SS_CONNECTED;
	}
	return 0;
}

static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk = sock->sk;
	struct sock *tsk;
	struct sk_buff *skb;
	int err;

	err = -EOPNOTSUPP;
	if (sock->type!=SOCK_STREAM && sock->type!=SOCK_SEQPACKET)
		goto out;

	err = -EINVAL;
	if (sk->sk_state != TCP_LISTEN)
		goto out;

	/* If socket state is TCP_LISTEN it cannot change (for now...),
	 * so that no locks are necessary.
	 */

	skb = skb_recv_datagram(sk, 0, flags&O_NONBLOCK, &err);
	if (!skb) {
		/* This means receive shutdown. */
		if (err == 0)
			err = -EINVAL;
		goto out;
	}

	tsk = skb->sk;
	skb_free_datagram(sk, skb);
	wake_up_interruptible(&unix_sk(sk)->peer_wait);

	/* attach accepted sock to socket */
1212
	unix_state_lock(tsk);
L
Linus Torvalds 已提交
1213 1214
	newsock->state = SS_CONNECTED;
	sock_graft(tsk, newsock);
1215
	unix_state_unlock(tsk);
L
Linus Torvalds 已提交
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
	return 0;

out:
	return err;
}


static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer)
{
	struct sock *sk = sock->sk;
	struct unix_sock *u;
	struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr;
	int err = 0;

	if (peer) {
		sk = unix_peer_get(sk);

		err = -ENOTCONN;
		if (!sk)
			goto out;
		err = 0;
	} else {
		sock_hold(sk);
	}

	u = unix_sk(sk);
1242
	unix_state_lock(sk);
L
Linus Torvalds 已提交
1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
	if (!u->addr) {
		sunaddr->sun_family = AF_UNIX;
		sunaddr->sun_path[0] = 0;
		*uaddr_len = sizeof(short);
	} else {
		struct unix_address *addr = u->addr;

		*uaddr_len = addr->len;
		memcpy(sunaddr, addr->name, *uaddr_len);
	}
1253
	unix_state_unlock(sk);
L
Linus Torvalds 已提交
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 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
	sock_put(sk);
out:
	return err;
}

static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
	int i;

	scm->fp = UNIXCB(skb).fp;
	skb->destructor = sock_wfree;
	UNIXCB(skb).fp = NULL;

	for (i=scm->fp->count-1; i>=0; i--)
		unix_notinflight(scm->fp->fp[i]);
}

static void unix_destruct_fds(struct sk_buff *skb)
{
	struct scm_cookie scm;
	memset(&scm, 0, sizeof(scm));
	unix_detach_fds(&scm, skb);

	/* Alas, it calls VFS */
	/* So fscking what? fput() had been SMP-safe since the last Summer */
	scm_destroy(&scm);
	sock_wfree(skb);
}

static void unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
	int i;
	for (i=scm->fp->count-1; i>=0; i--)
		unix_inflight(scm->fp->fp[i]);
	UNIXCB(skb).fp = scm->fp;
	skb->destructor = unix_destruct_fds;
	scm->fp = NULL;
}

/*
 *	Send AF_UNIX data.
 */

static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
			      struct msghdr *msg, size_t len)
{
	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr=msg->msg_name;
	struct sock *other = NULL;
	int namelen = 0; /* fake GCC */
	int err;
	unsigned hash;
	struct sk_buff *skb;
	long timeo;
	struct scm_cookie tmp_scm;

	if (NULL == siocb->scm)
		siocb->scm = &tmp_scm;
	err = scm_send(sock, msg, siocb->scm);
	if (err < 0)
		return err;

	err = -EOPNOTSUPP;
	if (msg->msg_flags&MSG_OOB)
		goto out;

	if (msg->msg_namelen) {
		err = unix_mkname(sunaddr, msg->msg_namelen, &hash);
		if (err < 0)
			goto out;
		namelen = err;
	} else {
		sunaddr = NULL;
		err = -ENOTCONN;
		other = unix_peer_get(sk);
		if (!other)
			goto out;
	}

	if (test_bit(SOCK_PASSCRED, &sock->flags)
		&& !u->addr && (err = unix_autobind(sock)) != 0)
		goto out;

	err = -EMSGSIZE;
	if (len > sk->sk_sndbuf - 32)
		goto out;

	skb = sock_alloc_send_skb(sk, len, msg->msg_flags&MSG_DONTWAIT, &err);
	if (skb==NULL)
		goto out;

	memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
	if (siocb->scm->fp)
		unix_attach_fds(siocb->scm, skb);
1350
	unix_get_secdata(siocb->scm, skb);
C
Catherine Zhang 已提交
1351

1352
	skb_reset_transport_header(skb);
L
Linus Torvalds 已提交
1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370
	err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
	if (err)
		goto out_free;

	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);

restart:
	if (!other) {
		err = -ECONNRESET;
		if (sunaddr == NULL)
			goto out_free;

		other = unix_find_other(sunaddr, namelen, sk->sk_type,
					hash, &err);
		if (other==NULL)
			goto out_free;
	}

1371
	unix_state_lock(other);
L
Linus Torvalds 已提交
1372 1373 1374 1375 1376 1377 1378 1379 1380
	err = -EPERM;
	if (!unix_may_send(sk, other))
		goto out_unlock;

	if (sock_flag(other, SOCK_DEAD)) {
		/*
		 *	Check with 1003.1g - what should
		 *	datagram error
		 */
1381
		unix_state_unlock(other);
L
Linus Torvalds 已提交
1382 1383 1384
		sock_put(other);

		err = 0;
1385
		unix_state_lock(sk);
L
Linus Torvalds 已提交
1386 1387
		if (unix_peer(sk) == other) {
			unix_peer(sk)=NULL;
1388
			unix_state_unlock(sk);
L
Linus Torvalds 已提交
1389 1390 1391 1392 1393

			unix_dgram_disconnected(sk, other);
			sock_put(other);
			err = -ECONNREFUSED;
		} else {
1394
			unix_state_unlock(sk);
L
Linus Torvalds 已提交
1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413
		}

		other = NULL;
		if (err)
			goto out_free;
		goto restart;
	}

	err = -EPIPE;
	if (other->sk_shutdown & RCV_SHUTDOWN)
		goto out_unlock;

	if (sk->sk_type != SOCK_SEQPACKET) {
		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
		if (err)
			goto out_unlock;
	}

	if (unix_peer(other) != sk &&
1414
	    (skb_queue_len(&other->sk_receive_queue) >
L
Linus Torvalds 已提交
1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430
	     other->sk_max_ack_backlog)) {
		if (!timeo) {
			err = -EAGAIN;
			goto out_unlock;
		}

		timeo = unix_wait_for_peer(other, timeo);

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out_free;

		goto restart;
	}

	skb_queue_tail(&other->sk_receive_queue, skb);
1431
	unix_state_unlock(other);
L
Linus Torvalds 已提交
1432 1433 1434 1435 1436 1437
	other->sk_data_ready(other, len);
	sock_put(other);
	scm_destroy(siocb->scm);
	return len;

out_unlock:
1438
	unix_state_unlock(other);
L
Linus Torvalds 已提交
1439 1440 1441 1442 1443 1444 1445 1446 1447
out_free:
	kfree_skb(skb);
out:
	if (other)
		sock_put(other);
	scm_destroy(siocb->scm);
	return err;
}

1448

L
Linus Torvalds 已提交
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476
static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
			       struct msghdr *msg, size_t len)
{
	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
	struct sock *sk = sock->sk;
	struct sock *other = NULL;
	struct sockaddr_un *sunaddr=msg->msg_name;
	int err,size;
	struct sk_buff *skb;
	int sent=0;
	struct scm_cookie tmp_scm;

	if (NULL == siocb->scm)
		siocb->scm = &tmp_scm;
	err = scm_send(sock, msg, siocb->scm);
	if (err < 0)
		return err;

	err = -EOPNOTSUPP;
	if (msg->msg_flags&MSG_OOB)
		goto out_err;

	if (msg->msg_namelen) {
		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
		goto out_err;
	} else {
		sunaddr = NULL;
		err = -ENOTCONN;
1477
		other = unix_peer(sk);
L
Linus Torvalds 已提交
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487
		if (!other)
			goto out_err;
	}

	if (sk->sk_shutdown & SEND_SHUTDOWN)
		goto pipe_err;

	while(sent < len)
	{
		/*
1488 1489
		 *	Optimisation for the fact that under 0.01% of X
		 *	messages typically need breaking up.
L
Linus Torvalds 已提交
1490 1491
		 */

1492
		size = len-sent;
L
Linus Torvalds 已提交
1493 1494

		/* Keep two messages in the pipe so it schedules better */
1495 1496
		if (size > ((sk->sk_sndbuf >> 1) - 64))
			size = (sk->sk_sndbuf >> 1) - 64;
L
Linus Torvalds 已提交
1497 1498 1499

		if (size > SKB_MAX_ALLOC)
			size = SKB_MAX_ALLOC;
1500

L
Linus Torvalds 已提交
1501 1502 1503
		/*
		 *	Grab a buffer
		 */
1504

L
Linus Torvalds 已提交
1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527
		skb=sock_alloc_send_skb(sk,size,msg->msg_flags&MSG_DONTWAIT, &err);

		if (skb==NULL)
			goto out_err;

		/*
		 *	If you pass two values to the sock_alloc_send_skb
		 *	it tries to grab the large buffer with GFP_NOFS
		 *	(which can fail easily), and if it fails grab the
		 *	fallback size buffer which is under a page and will
		 *	succeed. [Alan]
		 */
		size = min_t(int, size, skb_tailroom(skb));

		memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
		if (siocb->scm->fp)
			unix_attach_fds(siocb->scm, skb);

		if ((err = memcpy_fromiovec(skb_put(skb,size), msg->msg_iov, size)) != 0) {
			kfree_skb(skb);
			goto out_err;
		}

1528
		unix_state_lock(other);
L
Linus Torvalds 已提交
1529 1530 1531 1532 1533 1534

		if (sock_flag(other, SOCK_DEAD) ||
		    (other->sk_shutdown & RCV_SHUTDOWN))
			goto pipe_err_free;

		skb_queue_tail(&other->sk_receive_queue, skb);
1535
		unix_state_unlock(other);
L
Linus Torvalds 已提交
1536 1537 1538 1539 1540 1541 1542 1543 1544 1545
		other->sk_data_ready(other, size);
		sent+=size;
	}

	scm_destroy(siocb->scm);
	siocb->scm = NULL;

	return sent;

pipe_err_free:
1546
	unix_state_unlock(other);
L
Linus Torvalds 已提交
1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562
	kfree_skb(skb);
pipe_err:
	if (sent==0 && !(msg->msg_flags&MSG_NOSIGNAL))
		send_sig(SIGPIPE,current,0);
	err = -EPIPE;
out_err:
	scm_destroy(siocb->scm);
	siocb->scm = NULL;
	return sent ? : err;
}

static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock,
				  struct msghdr *msg, size_t len)
{
	int err;
	struct sock *sk = sock->sk;
1563

L
Linus Torvalds 已提交
1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575
	err = sock_error(sk);
	if (err)
		return err;

	if (sk->sk_state != TCP_ESTABLISHED)
		return -ENOTCONN;

	if (msg->msg_namelen)
		msg->msg_namelen = 0;

	return unix_dgram_sendmsg(kiocb, sock, msg, len);
}
1576

L
Linus Torvalds 已提交
1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605
static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
{
	struct unix_sock *u = unix_sk(sk);

	msg->msg_namelen = 0;
	if (u->addr) {
		msg->msg_namelen = u->addr->len;
		memcpy(msg->msg_name, u->addr->name, u->addr->len);
	}
}

static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
			      struct msghdr *msg, size_t size,
			      int flags)
{
	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
	struct scm_cookie tmp_scm;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	int noblock = flags & MSG_DONTWAIT;
	struct sk_buff *skb;
	int err;

	err = -EOPNOTSUPP;
	if (flags&MSG_OOB)
		goto out;

	msg->msg_namelen = 0;

I
Ingo Molnar 已提交
1606
	mutex_lock(&u->readlock);
L
Linus Torvalds 已提交
1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out_unlock;

	wake_up_interruptible(&u->peer_wait);

	if (msg->msg_name)
		unix_copy_addr(msg, skb->sk);

	if (size > skb->len)
		size = skb->len;
	else if (size < skb->len)
		msg->msg_flags |= MSG_TRUNC;

	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size);
	if (err)
		goto out_free;

	if (!siocb->scm) {
		siocb->scm = &tmp_scm;
		memset(&tmp_scm, 0, sizeof(tmp_scm));
	}
	siocb->scm->creds = *UNIXCREDS(skb);
C
Catherine Zhang 已提交
1631
	unix_set_secdata(siocb->scm, skb);
L
Linus Torvalds 已提交
1632 1633 1634 1635 1636 1637

	if (!(flags & MSG_PEEK))
	{
		if (UNIXCB(skb).fp)
			unix_detach_fds(siocb->scm, skb);
	}
1638
	else
L
Linus Torvalds 已提交
1639 1640 1641 1642 1643 1644 1645
	{
		/* It is questionable: on PEEK we could:
		   - do not return fds - good, but too simple 8)
		   - return fds, and do not return them on read (old strategy,
		     apparently wrong)
		   - clone fds (I chose it for now, it is the most universal
		     solution)
1646 1647 1648 1649 1650

		   POSIX 1003.1g does not actually define this clearly
		   at all. POSIX 1003.1g doesn't define a lot of things
		   clearly however!

L
Linus Torvalds 已提交
1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661
		*/
		if (UNIXCB(skb).fp)
			siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
	}
	err = size;

	scm_recv(sock, msg, siocb->scm, flags);

out_free:
	skb_free_datagram(sk,skb);
out_unlock:
I
Ingo Molnar 已提交
1662
	mutex_unlock(&u->readlock);
L
Linus Torvalds 已提交
1663 1664 1665 1666 1667 1668 1669
out:
	return err;
}

/*
 *	Sleep until data has arrive. But check for races..
 */
1670

L
Linus Torvalds 已提交
1671 1672 1673 1674
static long unix_stream_data_wait(struct sock * sk, long timeo)
{
	DEFINE_WAIT(wait);

1675
	unix_state_lock(sk);
L
Linus Torvalds 已提交
1676 1677 1678 1679

	for (;;) {
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

1680
		if (!skb_queue_empty(&sk->sk_receive_queue) ||
L
Linus Torvalds 已提交
1681 1682 1683 1684 1685 1686 1687
		    sk->sk_err ||
		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
		    signal_pending(current) ||
		    !timeo)
			break;

		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
1688
		unix_state_unlock(sk);
L
Linus Torvalds 已提交
1689
		timeo = schedule_timeout(timeo);
1690
		unix_state_lock(sk);
L
Linus Torvalds 已提交
1691 1692 1693 1694
		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	}

	finish_wait(sk->sk_sleep, &wait);
1695
	unix_state_unlock(sk);
L
Linus Torvalds 已提交
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 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
	return timeo;
}



static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size,
			       int flags)
{
	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
	struct scm_cookie tmp_scm;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr=msg->msg_name;
	int copied = 0;
	int check_creds = 0;
	int target;
	int err = 0;
	long timeo;

	err = -EINVAL;
	if (sk->sk_state != TCP_ESTABLISHED)
		goto out;

	err = -EOPNOTSUPP;
	if (flags&MSG_OOB)
		goto out;

	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);

	msg->msg_namelen = 0;

	/* Lock the socket to prevent queue disordering
	 * while sleeps in memcpy_tomsg
	 */

	if (!siocb->scm) {
		siocb->scm = &tmp_scm;
		memset(&tmp_scm, 0, sizeof(tmp_scm));
	}

I
Ingo Molnar 已提交
1738
	mutex_lock(&u->readlock);
L
Linus Torvalds 已提交
1739 1740 1741 1742 1743 1744

	do
	{
		int chunk;
		struct sk_buff *skb;

1745
		unix_state_lock(sk);
L
Linus Torvalds 已提交
1746 1747 1748 1749
		skb = skb_dequeue(&sk->sk_receive_queue);
		if (skb==NULL)
		{
			if (copied >= target)
1750
				goto unlock;
L
Linus Torvalds 已提交
1751 1752 1753 1754

			/*
			 *	POSIX 1003.1g mandates this order.
			 */
1755

L
Linus Torvalds 已提交
1756
			if ((err = sock_error(sk)) != 0)
1757
				goto unlock;
L
Linus Torvalds 已提交
1758
			if (sk->sk_shutdown & RCV_SHUTDOWN)
1759 1760 1761
				goto unlock;

			unix_state_unlock(sk);
L
Linus Torvalds 已提交
1762 1763 1764
			err = -EAGAIN;
			if (!timeo)
				break;
I
Ingo Molnar 已提交
1765
			mutex_unlock(&u->readlock);
L
Linus Torvalds 已提交
1766 1767 1768 1769 1770 1771 1772

			timeo = unix_stream_data_wait(sk, timeo);

			if (signal_pending(current)) {
				err = sock_intr_errno(timeo);
				goto out;
			}
I
Ingo Molnar 已提交
1773
			mutex_lock(&u->readlock);
L
Linus Torvalds 已提交
1774
			continue;
1775 1776 1777
 unlock:
			unix_state_unlock(sk);
			break;
L
Linus Torvalds 已提交
1778
		}
1779
		unix_state_unlock(sk);
L
Linus Torvalds 已提交
1780 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 1813 1814 1815 1816 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 1842

		if (check_creds) {
			/* Never glue messages from different writers */
			if (memcmp(UNIXCREDS(skb), &siocb->scm->creds, sizeof(siocb->scm->creds)) != 0) {
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}
		} else {
			/* Copy credentials */
			siocb->scm->creds = *UNIXCREDS(skb);
			check_creds = 1;
		}

		/* Copy address just once */
		if (sunaddr)
		{
			unix_copy_addr(msg, skb->sk);
			sunaddr = NULL;
		}

		chunk = min_t(unsigned int, skb->len, size);
		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
			skb_queue_head(&sk->sk_receive_queue, skb);
			if (copied == 0)
				copied = -EFAULT;
			break;
		}
		copied += chunk;
		size -= chunk;

		/* Mark read part of skb as used */
		if (!(flags & MSG_PEEK))
		{
			skb_pull(skb, chunk);

			if (UNIXCB(skb).fp)
				unix_detach_fds(siocb->scm, skb);

			/* put the skb back if we didn't use it up.. */
			if (skb->len)
			{
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}

			kfree_skb(skb);

			if (siocb->scm->fp)
				break;
		}
		else
		{
			/* It is questionable, see note in unix_dgram_recvmsg.
			 */
			if (UNIXCB(skb).fp)
				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);

			/* put message back and return */
			skb_queue_head(&sk->sk_receive_queue, skb);
			break;
		}
	} while (size);

I
Ingo Molnar 已提交
1843
	mutex_unlock(&u->readlock);
L
Linus Torvalds 已提交
1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856
	scm_recv(sock, msg, siocb->scm, flags);
out:
	return copied ? : err;
}

static int unix_shutdown(struct socket *sock, int mode)
{
	struct sock *sk = sock->sk;
	struct sock *other;

	mode = (mode+1)&(RCV_SHUTDOWN|SEND_SHUTDOWN);

	if (mode) {
1857
		unix_state_lock(sk);
L
Linus Torvalds 已提交
1858 1859 1860 1861
		sk->sk_shutdown |= mode;
		other=unix_peer(sk);
		if (other)
			sock_hold(other);
1862
		unix_state_unlock(sk);
L
Linus Torvalds 已提交
1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873
		sk->sk_state_change(sk);

		if (other &&
			(sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {

			int peer_mode = 0;

			if (mode&RCV_SHUTDOWN)
				peer_mode |= SEND_SHUTDOWN;
			if (mode&SEND_SHUTDOWN)
				peer_mode |= RCV_SHUTDOWN;
1874
			unix_state_lock(other);
L
Linus Torvalds 已提交
1875
			other->sk_shutdown |= peer_mode;
1876
			unix_state_unlock(other);
L
Linus Torvalds 已提交
1877 1878 1879 1880 1881 1882 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
			other->sk_state_change(other);
			read_lock(&other->sk_callback_lock);
			if (peer_mode == SHUTDOWN_MASK)
				sk_wake_async(other,1,POLL_HUP);
			else if (peer_mode & RCV_SHUTDOWN)
				sk_wake_async(other,1,POLL_IN);
			read_unlock(&other->sk_callback_lock);
		}
		if (other)
			sock_put(other);
	}
	return 0;
}

static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	long amount=0;
	int err;

	switch(cmd)
	{
		case SIOCOUTQ:
			amount = atomic_read(&sk->sk_wmem_alloc);
			err = put_user(amount, (int __user *)arg);
			break;
		case SIOCINQ:
		{
			struct sk_buff *skb;

			if (sk->sk_state == TCP_LISTEN) {
				err = -EINVAL;
				break;
			}

			spin_lock(&sk->sk_receive_queue.lock);
			if (sk->sk_type == SOCK_STREAM ||
			    sk->sk_type == SOCK_SEQPACKET) {
				skb_queue_walk(&sk->sk_receive_queue, skb)
					amount += skb->len;
			} else {
				skb = skb_peek(&sk->sk_receive_queue);
				if (skb)
					amount=skb->len;
			}
			spin_unlock(&sk->sk_receive_queue.lock);
			err = put_user(amount, (int __user *)arg);
			break;
		}

		default:
1928
			err = -ENOIOCTLCMD;
L
Linus Torvalds 已提交
1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946
			break;
	}
	return err;
}

static unsigned int unix_poll(struct file * file, struct socket *sock, poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask;

	poll_wait(file, sk->sk_sleep, wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err)
		mask |= POLLERR;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;
1947 1948
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLRDHUP;
L
Linus Torvalds 已提交
1949 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

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sk->sk_shutdown & RCV_SHUTDOWN))
		mask |= POLLIN | POLLRDNORM;

	/* Connection-based need to check for termination and startup */
	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && sk->sk_state == TCP_CLOSE)
		mask |= POLLHUP;

	/*
	 * we set writable also when the other side has shut down the
	 * connection. This prevents stuck sockets.
	 */
	if (unix_writable(sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;

	return mask;
}


#ifdef CONFIG_PROC_FS
static struct sock *unix_seq_idx(int *iter, loff_t pos)
{
	loff_t off = 0;
	struct sock *s;

	for (s = first_unix_socket(iter); s; s = next_unix_socket(iter, s)) {
1977
		if (off == pos)
L
Linus Torvalds 已提交
1978 1979 1980 1981 1982 1983 1984 1985 1986
			return s;
		++off;
	}
	return NULL;
}


static void *unix_seq_start(struct seq_file *seq, loff_t *pos)
{
1987
	spin_lock(&unix_table_lock);
L
Linus Torvalds 已提交
1988 1989 1990 1991 1992 1993 1994
	return *pos ? unix_seq_idx(seq->private, *pos - 1) : ((void *) 1);
}

static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;

1995
	if (v == (void *)1)
L
Linus Torvalds 已提交
1996 1997 1998 1999 2000 2001
		return first_unix_socket(seq->private);
	return next_unix_socket(seq->private, v);
}

static void unix_seq_stop(struct seq_file *seq, void *v)
{
2002
	spin_unlock(&unix_table_lock);
L
Linus Torvalds 已提交
2003 2004 2005 2006
}

static int unix_seq_show(struct seq_file *seq, void *v)
{
2007

L
Linus Torvalds 已提交
2008 2009 2010 2011 2012 2013
	if (v == (void *)1)
		seq_puts(seq, "Num       RefCount Protocol Flags    Type St "
			 "Inode Path\n");
	else {
		struct sock *s = v;
		struct unix_sock *u = unix_sk(s);
2014
		unix_state_lock(s);
L
Linus Torvalds 已提交
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

		seq_printf(seq, "%p: %08X %08X %08X %04X %02X %5lu",
			s,
			atomic_read(&s->sk_refcnt),
			0,
			s->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0,
			s->sk_type,
			s->sk_socket ?
			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTED : SS_UNCONNECTED) :
			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
			sock_i_ino(s));

		if (u->addr) {
			int i, len;
			seq_putc(seq, ' ');

			i = 0;
			len = u->addr->len - sizeof(short);
			if (!UNIX_ABSTRACT(s))
				len--;
			else {
				seq_putc(seq, '@');
				i++;
			}
			for ( ; i < len; i++)
				seq_putc(seq, u->addr->name->sun_path[i]);
		}
2042
		unix_state_unlock(s);
L
Linus Torvalds 已提交
2043 2044 2045 2046 2047 2048
		seq_putc(seq, '\n');
	}

	return 0;
}

2049
static const struct seq_operations unix_seq_ops = {
L
Linus Torvalds 已提交
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
	.start  = unix_seq_start,
	.next   = unix_seq_next,
	.stop   = unix_seq_stop,
	.show   = unix_seq_show,
};


static int unix_seq_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	int rc = -ENOMEM;
	int *iter = kmalloc(sizeof(int), GFP_KERNEL);

	if (!iter)
		goto out;

	rc = seq_open(file, &unix_seq_ops);
	if (rc)
		goto out_kfree;

	seq	     = file->private_data;
	seq->private = iter;
	*iter = 0;
out:
	return rc;
out_kfree:
	kfree(iter);
	goto out;
}

2080
static const struct file_operations unix_seq_fops = {
L
Linus Torvalds 已提交
2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100
	.owner		= THIS_MODULE,
	.open		= unix_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

#endif

static struct net_proto_family unix_family_ops = {
	.family = PF_UNIX,
	.create = unix_create,
	.owner	= THIS_MODULE,
};

static int __init af_unix_init(void)
{
	int rc = -1;
	struct sk_buff *dummy_skb;

2101
	BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb));
L
Linus Torvalds 已提交
2102 2103

	rc = proto_register(&unix_proto, 1);
2104 2105
	if (rc != 0) {
		printk(KERN_CRIT "%s: Cannot create unix_sock SLAB cache!\n",
L
Linus Torvalds 已提交
2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131
		       __FUNCTION__);
		goto out;
	}

	sock_register(&unix_family_ops);
#ifdef CONFIG_PROC_FS
	proc_net_fops_create("unix", 0, &unix_seq_fops);
#endif
	unix_sysctl_register();
out:
	return rc;
}

static void __exit af_unix_exit(void)
{
	sock_unregister(PF_UNIX);
	unix_sysctl_unregister();
	proc_net_remove("unix");
	proto_unregister(&unix_proto);
}

module_init(af_unix_init);
module_exit(af_unix_exit);

MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_UNIX);