Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

4 files changed, 2478 insertions, 0 deletions

diff --git a/net/unix/Makefile b/net/unix/Makefile
new file mode 100644
index 00000000000..b852a2bde9a
--- /dev/null
+++ b/net/unix/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for the Linux unix domain socket layer.
+#
+
+obj-$(CONFIG_UNIX)	+= unix.o
+
+unix-y			:= af_unix.o garbage.o
+unix-$(CONFIG_SYSCTL)	+= sysctl_net_unix.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
new file mode 100644
index 00000000000..acc73fe6869
--- /dev/null
+++ b/net/unix/af_unix.c
@@ -0,0 +1,2098 @@
+/*
+ * 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/config.h>
+#include <linux/kernel.h>
+#include <linux/major.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>
+#include <linux/tcp.h>
+#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/smp_lock.h>
+#include <linux/rtnetlink.h>
+#include <linux/mount.h>
+#include <net/checksum.h>
+#include <linux/security.h>
+
+int sysctl_unix_max_dgram_qlen = 10;
+
+struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
+DEFINE_RWLOCK(unix_table_lock);
+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)
+
+/*
+ *  SMP locking strategy:
+ *    hash table is protected with rwlock unix_table_lock
+ *    each socket state is protected by separate rwlock.
+ */
+
+static inline unsigned unix_hash_fold(unsigned hash)
+{
+	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;
+
+	unix_state_rlock(s);
+	peer = unix_peer(s);
+	if (peer)
+		sock_hold(peer);
+	unix_state_runlock(s);
+	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.
+ */
+ 
+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)
+{
+	write_lock(&unix_table_lock);
+	__unix_remove_socket(sk);
+	write_unlock(&unix_table_lock);
+}
+
+static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
+{
+	write_lock(&unix_table_lock);
+	__unix_insert_socket(list, sk);
+	write_unlock(&unix_table_lock);
+}
+
+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;
+
+	read_lock(&unix_table_lock);
+	s = __unix_find_socket_byname(sunname, len, type, hash);
+	if (s)
+		sock_hold(s);
+	read_unlock(&unix_table_lock);
+	return s;
+}
+
+static struct sock *unix_find_socket_byinode(struct inode *i)
+{
+	struct sock *s;
+	struct hlist_node *node;
+
+	read_lock(&unix_table_lock);
+	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:
+	read_unlock(&unix_table_lock);
+	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)
+{
+	if (skb_queue_len(&sk->sk_receive_queue)) {
+		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 */
+	unix_state_wlock(sk);
+	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;
+	unix_state_wunlock(sk);
+
+	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) {
+			unix_state_wlock(skpair);
+			/* No more writes */
+			skpair->sk_shutdown = SHUTDOWN_MASK;
+			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
+				skpair->sk_err = ECONNRESET;
+			unix_state_wunlock(skpair);
+			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))
+		unix_gc();		/* Garbage collect fds */	
+
+	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 */
+	unix_state_wlock(sk);
+	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:
+	unix_state_wunlock(sk);
+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);
+
+static struct proto_ops unix_stream_ops = {
+	.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,
+};
+
+static struct proto_ops unix_dgram_ops = {
+	.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,
+};
+
+static struct proto_ops unix_seqpacket_ops = {
+	.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),
+};
+
+static struct sock * unix_create1(struct socket *sock)
+{
+	struct sock *sk = NULL;
+	struct unix_sock *u;
+
+	if (atomic_read(&unix_nr_socks) >= 2*files_stat.max_files)
+		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);
+
+	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;
+	rwlock_init(&u->lock);
+	atomic_set(&u->inflight, sock ? 0 : -1);
+	init_MUTEX(&u->readsem); /* single task reading lock */
+	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;
+
+	down(&u->readsem);
+
+	err = 0;
+	if (u->addr)
+		goto out;
+
+	err = -ENOMEM;
+	addr = kmalloc(sizeof(*addr) + sizeof(short) + 16, GFP_KERNEL);
+	if (!addr)
+		goto out;
+
+	memset(addr, 0, sizeof(*addr) + sizeof(short) + 16);
+	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));
+
+	write_lock(&unix_table_lock);
+	ordernum = (ordernum+1)&0xFFFFF;
+
+	if (__unix_find_socket_byname(addr->name, addr->len, sock->type,
+				      addr->hash)) {
+		write_unlock(&unix_table_lock);
+		/* 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);
+	write_unlock(&unix_table_lock);
+	err = 0;
+
+out:	up(&u->readsem);
+	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;
+	
+	if (sunname->sun_path[0]) {
+		err = path_lookup(sunname->sun_path, LOOKUP_FOLLOW, &nd);
+		if (err)
+			goto fail;
+		err = permission(nd.dentry->d_inode,MAY_WRITE, &nd);
+		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;
+
+	down(&u->readsem);
+
+	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;
+		/*
+		 * Yucky last component or no last component at all?
+		 * (foo/., foo/.., /////)
+		 */
+		err = -EEXIST;
+		if (nd.last_type != LAST_NORM)
+			goto out_mknod;
+		/*
+		 * Lock the directory.
+		 */
+		down(&nd.dentry->d_inode->i_sem);
+		/*
+		 * Do the final lookup.
+		 */
+		dentry = lookup_hash(&nd.last, nd.dentry);
+		err = PTR_ERR(dentry);
+		if (IS_ERR(dentry))
+			goto out_mknod_unlock;
+		err = -ENOENT;
+		/*
+		 * Special case - lookup gave negative, but... we had foo/bar/
+		 * From the vfs_mknod() POV we just have a negative dentry -
+		 * all is fine. Let's be bastards - you had / on the end, you've
+		 * been asking for (non-existent) directory. -ENOENT for you.
+		 */
+		if (nd.last.name[nd.last.len] && !dentry->d_inode)
+			goto out_mknod_dput;
+		/*
+		 * 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;
+		up(&nd.dentry->d_inode->i_sem);
+		dput(nd.dentry);
+		nd.dentry = dentry;
+
+		addr->hash = UNIX_HASH_SIZE;
+	}
+
+	write_lock(&unix_table_lock);
+
+	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:
+	write_unlock(&unix_table_lock);
+out_up:
+	up(&u->readsem);
+out:
+	return err;
+
+out_mknod_dput:
+	dput(dentry);
+out_mknod_unlock:
+	up(&nd.dentry->d_inode->i_sem);
+out_mknod:
+	path_release(&nd);
+out_mknod_parent:
+	if (err==-EEXIST)
+		err=-EADDRINUSE;
+	unix_release_addr(addr);
+	goto out_up;
+}
+
+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;
+
+		other=unix_find_other(sunaddr, alen, sock->type, hash, &err);
+		if (!other)
+			goto out;
+
+		unix_state_wlock(sk);
+
+		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;
+		unix_state_wlock(sk);
+	}
+
+	/*
+	 * If it was connected, reconnect.
+	 */
+	if (unix_peer(sk)) {
+		struct sock *old_peer = unix_peer(sk);
+		unix_peer(sk)=other;
+		unix_state_wunlock(sk);
+
+		if (other != old_peer)
+			unix_dgram_disconnected(sk, old_peer);
+		sock_put(old_peer);
+	} else {
+		unix_peer(sk)=other;
+		unix_state_wunlock(sk);
+	}
+ 	return 0;
+
+out_unlock:
+	unix_state_wunlock(sk);
+	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) &&
+		(skb_queue_len(&other->sk_receive_queue) >
+		 other->sk_max_ack_backlog);
+
+	unix_state_runlock(other);
+
+	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 */
+	unix_state_rlock(other);
+
+	/* Apparently VFS overslept socket death. Retry. */
+	if (sock_flag(other, SOCK_DEAD)) {
+		unix_state_runlock(other);
+		sock_put(other);
+		goto restart;
+	}
+
+	err = -ECONNREFUSED;
+	if (other->sk_state != TCP_LISTEN)
+		goto out_unlock;
+
+	if (skb_queue_len(&other->sk_receive_queue) >
+	    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;
+        }
+
+	/* 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;
+	}
+
+	unix_state_wlock(sk);
+
+	if (sk->sk_state != st) {
+		unix_state_wunlock(sk);
+		unix_state_runlock(other);
+		sock_put(other);
+		goto restart;
+	}
+
+	err = security_unix_stream_connect(sock, other->sk_socket, newsk);
+	if (err) {
+		unix_state_wunlock(sk);
+		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_hold(newsk);
+	unix_peer(sk)	= newsk;
+	sock->state	= SS_CONNECTED;
+	sk->sk_state	= TCP_ESTABLISHED;
+
+	unix_state_wunlock(sk);
+
+	/* take ten and and send info to listening sock */
+	spin_lock(&other->sk_receive_queue.lock);
+	__skb_queue_tail(&other->sk_receive_queue, skb);
+	/* Undo artificially decreased inflight after embrion
+	 * is installed to listening socket. */
+	atomic_inc(&newu->inflight);
+	spin_unlock(&other->sk_receive_queue.lock);
+	unix_state_runlock(other);
+	other->sk_data_ready(other, 0);
+	sock_put(other);
+	return 0;
+
+out_unlock:
+	if (other)
+		unix_state_runlock(other);
+
+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)