sock.c

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Generic socket support routines. Memory allocators, socket lock/release
 *		handler for protocols to use and generic option handler.
 *
 *
 * Version:	$Id: sock.c,v 1.117 2002/02/01 22:01:03 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Fixes:
 *		Alan Cox	: 	Numerous verify_area() problems
 *		Alan Cox	:	Connecting on a connecting socket
 *					now returns an error for tcp.
 *		Alan Cox	:	sock->protocol is set correctly.
 *					and is not sometimes left as 0.
 *		Alan Cox	:	connect handles icmp errors on a
 *					connect properly. Unfortunately there
 *					is a restart syscall nasty there. I
 *					can't match BSD without hacking the C
 *					library. Ideas urgently sought!
 *		Alan Cox	:	Disallow bind() to addresses that are
 *					not ours - especially broadcast ones!!
 *		Alan Cox	:	Socket 1024 _IS_ ok for users. (fencepost)
 *		Alan Cox	:	sock_wfree/sock_rfree don't destroy sockets,
 *					instead they leave that for the DESTROY timer.
 *		Alan Cox	:	Clean up error flag in accept
 *		Alan Cox	:	TCP ack handling is buggy, the DESTROY timer
 *					was buggy. Put a remove_sock() in the handler
 *					for memory when we hit 0. Also altered the timer
 *					code. The ACK stuff can wait and needs major 
 *					TCP layer surgery.
 *		Alan Cox	:	Fixed TCP ack bug, removed remove sock
 *					and fixed timer/inet_bh race.
 *		Alan Cox	:	Added zapped flag for TCP
 *		Alan Cox	:	Move kfree_skb into skbuff.c and tidied up surplus code
 *		Alan Cox	:	for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
 *		Alan Cox	:	kfree_s calls now are kfree_skbmem so we can track skb resources
 *		Alan Cox	:	Supports socket option broadcast now as does udp. Packet and raw need fixing.
 *		Alan Cox	:	Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
 *		Rick Sladkey	:	Relaxed UDP rules for matching packets.
 *		C.E.Hawkins	:	IFF_PROMISC/SIOCGHWADDR support
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Fixed connect() taking signals I think.
 *		Alan Cox	:	SO_LINGER supported
 *		Alan Cox	:	Error reporting fixes
 *		Anonymous	:	inet_create tidied up (sk->reuse setting)
 *		Alan Cox	:	inet sockets don't set sk->type!
 *		Alan Cox	:	Split socket option code
 *		Alan Cox	:	Callbacks
 *		Alan Cox	:	Nagle flag for Charles & Johannes stuff
 *		Alex		:	Removed restriction on inet fioctl
 *		Alan Cox	:	Splitting INET from NET core
 *		Alan Cox	:	Fixed bogus SO_TYPE handling in getsockopt()
 *		Adam Caldwell	:	Missing return in SO_DONTROUTE/SO_DEBUG code
 *		Alan Cox	:	Split IP from generic code
 *		Alan Cox	:	New kfree_skbmem()
 *		Alan Cox	:	Make SO_DEBUG superuser only.
 *		Alan Cox	:	Allow anyone to clear SO_DEBUG
 *					(compatibility fix)
 *		Alan Cox	:	Added optimistic memory grabbing for AF_UNIX throughput.
 *		Alan Cox	:	Allocator for a socket is settable.
 *		Alan Cox	:	SO_ERROR includes soft errors.
 *		Alan Cox	:	Allow NULL arguments on some SO_ opts
 *		Alan Cox	: 	Generic socket allocation to make hooks
 *					easier (suggested by Craig Metz).
 *		Michael Pall	:	SO_ERROR returns positive errno again
 *              Steve Whitehouse:       Added default destructor to free
 *                                      protocol private data.
 *              Steve Whitehouse:       Added various other default routines
 *                                      common to several socket families.
 *              Chris Evans     :       Call suser() check last on F_SETOWN
 *		Jay Schulist	:	Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
 *		Andi Kleen	:	Add sock_kmalloc()/sock_kfree_s()
 *		Andi Kleen	:	Fix write_space callback
 *		Chris Evans	:	Security fixes - signedness again
 *		Arnaldo C. Melo :       cleanups, use skb_queue_purge
 *
 * To Fix:
 *
 *
 *		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.
 */

#include <linux/capability.h>
#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>

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

#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>

#include <linux/filter.h>

#ifdef CONFIG_INET
#include <net/tcp.h>
#endif

/* Take into consideration the size of the struct sk_buff overhead in the
 * determination of these values, since that is non-constant across
 * platforms.  This makes socket queueing behavior and performance
 * not depend upon such differences.
 */
#define _SK_MEM_PACKETS		256
#define _SK_MEM_OVERHEAD	(sizeof(struct sk_buff) + 256)
#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

/* Run time adjustable parameters. */
__u32 sysctl_wmem_max = SK_WMEM_MAX;
__u32 sysctl_rmem_max = SK_RMEM_MAX;
__u32 sysctl_wmem_default = SK_WMEM_MAX;
__u32 sysctl_rmem_default = SK_RMEM_MAX;

/* Maximal space eaten by iovec or ancilliary data plus some space */
int sysctl_optmem_max = sizeof(unsigned long)*(2*UIO_MAXIOV + 512);

static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
	struct timeval tv;

	if (optlen < sizeof(tv))
		return -EINVAL;
	if (copy_from_user(&tv, optval, sizeof(tv)))
		return -EFAULT;

	*timeo_p = MAX_SCHEDULE_TIMEOUT;
	if (tv.tv_sec == 0 && tv.tv_usec == 0)
		return 0;
	if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
		*timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ);
	return 0;
}

static void sock_warn_obsolete_bsdism(const char *name)
{
	static int warned;
	static char warncomm[TASK_COMM_LEN];
	if (strcmp(warncomm, current->comm) && warned < 5) { 
		strcpy(warncomm,  current->comm); 
		printk(KERN_WARNING "process `%s' is using obsolete "
		       "%s SO_BSDCOMPAT\n", warncomm, name);
		warned++;
	}
}

static void sock_disable_timestamp(struct sock *sk)
{	
	if (sock_flag(sk, SOCK_TIMESTAMP)) { 
		sock_reset_flag(sk, SOCK_TIMESTAMP);
		net_disable_timestamp();
	}
}


/*
 *	This is meant for all protocols to use and covers goings on
 *	at the socket level. Everything here is generic.
 */

int sock_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int optlen)
{
	struct sock *sk=sock->sk;
	struct sk_filter *filter;
	int val;
	int valbool;
	struct linger ling;
	int ret = 0;
	
	/*
	 *	Options without arguments
	 */

#ifdef SO_DONTLINGER		/* Compatibility item... */
	if (optname == SO_DONTLINGER) {
		lock_sock(sk);
		sock_reset_flag(sk, SOCK_LINGER);
		release_sock(sk);
		return 0;
	}
#endif
	
  	if(optlen<sizeof(int))
  		return(-EINVAL);
  	
	if (get_user(val, (int __user *)optval))
		return -EFAULT;
	
  	valbool = val?1:0;

	lock_sock(sk);

  	switch(optname) 
  	{
		case SO_DEBUG:	
			if(val && !capable(CAP_NET_ADMIN))
			{
				ret = -EACCES;
			}
			else if (valbool)
				sock_set_flag(sk, SOCK_DBG);
			else
				sock_reset_flag(sk, SOCK_DBG);
			break;
		case SO_REUSEADDR:
			sk->sk_reuse = valbool;
			break;
		case SO_TYPE:
		case SO_ERROR:
			ret = -ENOPROTOOPT;
		  	break;
		case SO_DONTROUTE:
			if (valbool)
				sock_set_flag(sk, SOCK_LOCALROUTE);
			else
				sock_reset_flag(sk, SOCK_LOCALROUTE);
			break;
		case SO_BROADCAST:
			sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
			break;
		case SO_SNDBUF:
			/* Don't error on this BSD doesn't and if you think
			   about it this is right. Otherwise apps have to
			   play 'guess the biggest size' games. RCVBUF/SNDBUF
			   are treated in BSD as hints */
			   
			if (val > sysctl_wmem_max)
				val = sysctl_wmem_max;
set_sndbuf:
			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
			if ((val * 2) < SOCK_MIN_SNDBUF)
				sk->sk_sndbuf = SOCK_MIN_SNDBUF;
			else
				sk->sk_sndbuf = val * 2;

			/*
			 *	Wake up sending tasks if we
			 *	upped the value.
			 */
			sk->sk_write_space(sk);
			break;

		case SO_SNDBUFFORCE:
			if (!capable(CAP_NET_ADMIN)) {
				ret = -EPERM;
				break;
			}
			goto set_sndbuf;

		case SO_RCVBUF:
			/* Don't error on this BSD doesn't and if you think
			   about it this is right. Otherwise apps have to
			   play 'guess the biggest size' games. RCVBUF/SNDBUF
			   are treated in BSD as hints */
			  
			if (val > sysctl_rmem_max)
				val = sysctl_rmem_max;
set_rcvbuf:
			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
			/* FIXME: is this lower bound the right one? */
			if ((val * 2) < SOCK_MIN_RCVBUF)
				sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
			else
				sk->sk_rcvbuf = val * 2;
			break;

		case SO_RCVBUFFORCE:
			if (!capable(CAP_NET_ADMIN)) {
				ret = -EPERM;
				break;
			}
			goto set_rcvbuf;

		case SO_KEEPALIVE:
#ifdef CONFIG_INET
			if (sk->sk_protocol == IPPROTO_TCP)
				tcp_set_keepalive(sk, valbool);
#endif
			sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
			break;

	 	case SO_OOBINLINE:
			sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
			break;

	 	case SO_NO_CHECK:
			sk->sk_no_check = valbool;
			break;

		case SO_PRIORITY:
			if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) 
				sk->sk_priority = val;
			else
				ret = -EPERM;
			break;

		case SO_LINGER:
			if(optlen<sizeof(ling)) {
				ret = -EINVAL;	/* 1003.1g */
				break;
			}
			if (copy_from_user(&ling,optval,sizeof(ling))) {
				ret = -EFAULT;
				break;
			}
			if (!ling.l_onoff)
				sock_reset_flag(sk, SOCK_LINGER);
			else {
#if (BITS_PER_LONG == 32)
				if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
					sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
				else
#endif
					sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
				sock_set_flag(sk, SOCK_LINGER);
			}
			break;

		case SO_BSDCOMPAT:
			sock_warn_obsolete_bsdism("setsockopt");
			break;

		case SO_PASSCRED:
			if (valbool)
				set_bit(SOCK_PASSCRED, &sock->flags);
			else
				clear_bit(SOCK_PASSCRED, &sock->flags);
			break;

		case SO_TIMESTAMP:
			if (valbool)  {
				sock_set_flag(sk, SOCK_RCVTSTAMP);
				sock_enable_timestamp(sk);
			} else
				sock_reset_flag(sk, SOCK_RCVTSTAMP);
			break;

		case SO_RCVLOWAT:
			if (val < 0)
				val = INT_MAX;
			sk->sk_rcvlowat = val ? : 1;
			break;

		case SO_RCVTIMEO:
			ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
			break;

		case SO_SNDTIMEO:
			ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
			break;

#ifdef CONFIG_NETDEVICES
		case SO_BINDTODEVICE:
		{
			char devname[IFNAMSIZ]; 

			/* Sorry... */ 
			if (!capable(CAP_NET_RAW)) {
				ret = -EPERM;
				break;
			}

			/* Bind this socket to a particular device like "eth0",
			 * as specified in the passed interface name. If the
			 * name is "" or the option length is zero the socket 
			 * is not bound. 
			 */ 

			if (!valbool) {
				sk->sk_bound_dev_if = 0;
			} else {
				if (optlen > IFNAMSIZ - 1)
					optlen = IFNAMSIZ - 1;
				memset(devname, 0, sizeof(devname));
				if (copy_from_user(devname, optval, optlen)) {
					ret = -EFAULT;
					break;
				}

				/* Remove any cached route for this socket. */
				sk_dst_reset(sk);

				if (devname[0] == '\0') {
					sk->sk_bound_dev_if = 0;
				} else {
					struct net_device *dev = dev_get_by_name(devname);
					if (!dev) {
						ret = -ENODEV;
						break;
					}
					sk->sk_bound_dev_if = dev->ifindex;
					dev_put(dev);
				}
			}
			break;
		}
#endif


		case SO_ATTACH_FILTER:
			ret = -EINVAL;
			if (optlen == sizeof(struct sock_fprog)) {
				struct sock_fprog fprog;

				ret = -EFAULT;
				if (copy_from_user(&fprog, optval, sizeof(fprog)))
					break;

				ret = sk_attach_filter(&fprog, sk);
			}
			break;

		case SO_DETACH_FILTER:
			spin_lock_bh(&sk->sk_lock.slock);
			filter = sk->sk_filter;
                        if (filter) {
				sk->sk_filter = NULL;
				spin_unlock_bh(&sk->sk_lock.slock);
				sk_filter_release(sk, filter);
				break;
			}
			spin_unlock_bh(&sk->sk_lock.slock);
			ret = -ENONET;
			break;

		/* We implement the SO_SNDLOWAT etc to
		   not be settable (1003.1g 5.3) */
		default:
		  	ret = -ENOPROTOOPT;
			break;
  	}
	release_sock(sk);
	return ret;
}


int sock_getsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;
	
	union
	{
  		int val;
  		struct linger ling;
		struct timeval tm;
	} v;
	
	unsigned int lv = sizeof(int);
	int len;
  	
  	if(get_user(len,optlen))
  		return -EFAULT;
	if(len < 0)
		return -EINVAL;
		
  	switch(optname) 
  	{
		case SO_DEBUG:		
			v.val = sock_flag(sk, SOCK_DBG);
			break;
		
		case SO_DONTROUTE:
			v.val = sock_flag(sk, SOCK_LOCALROUTE);
			break;
		
		case SO_BROADCAST:
			v.val = !!sock_flag(sk, SOCK_BROADCAST);
			break;

		case SO_SNDBUF:
			v.val = sk->sk_sndbuf;
			break;
		
		case SO_RCVBUF:
			v.val = sk->sk_rcvbuf;
			break;

		case SO_REUSEADDR:
			v.val = sk->sk_reuse;
			break;

		case SO_KEEPALIVE:
			v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
			break;

		case SO_TYPE:
			v.val = sk->sk_type;		  		
			break;

		case SO_ERROR:
			v.val = -sock_error(sk);
			if(v.val==0)
				v.val = xchg(&sk->sk_err_soft, 0);
			break;

		case SO_OOBINLINE:
			v.val = !!sock_flag(sk, SOCK_URGINLINE);
			break;
	
		case SO_NO_CHECK:
			v.val = sk->sk_no_check;
			break;

		case SO_PRIORITY:
			v.val = sk->sk_priority;
			break;
		
		case SO_LINGER:	
			lv		= sizeof(v.ling);
			v.ling.l_onoff	= !!sock_flag(sk, SOCK_LINGER);
 			v.ling.l_linger	= sk->sk_lingertime / HZ;
			break;
					
		case SO_BSDCOMPAT:
			sock_warn_obsolete_bsdism("getsockopt");
			break;

		case SO_TIMESTAMP:
			v.val = sock_flag(sk, SOCK_RCVTSTAMP);
			break;

		case SO_RCVTIMEO:
			lv=sizeof(struct timeval);
			if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
				v.tm.tv_sec = 0;
				v.tm.tv_usec = 0;
			} else {
				v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
				v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
			}
			break;

		case SO_SNDTIMEO:
			lv=sizeof(struct timeval);
			if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
				v.tm.tv_sec = 0;
				v.tm.tv_usec = 0;
			} else {
				v.tm.tv_sec = sk->sk_sndtimeo / HZ;
				v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
			}
			break;

		case SO_RCVLOWAT:
			v.val = sk->sk_rcvlowat;
			break;

		case SO_SNDLOWAT:
			v.val=1;
			break; 

		case SO_PASSCRED:
			v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
			break;

		case SO_PEERCRED:
			if (len > sizeof(sk->sk_peercred))
				len = sizeof(sk->sk_peercred);
			if (copy_to_user(optval, &sk->sk_peercred, len))
				return -EFAULT;
			goto lenout;

		case SO_PEERNAME:
		{
			char address[128];

			if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
				return -ENOTCONN;
			if (lv < len)
				return -EINVAL;
			if (copy_to_user(optval, address, len))
				return -EFAULT;
			goto lenout;
		}

		/* Dubious BSD thing... Probably nobody even uses it, but
		 * the UNIX standard wants it for whatever reason... -DaveM
		 */
		case SO_ACCEPTCONN:
			v.val = sk->sk_state == TCP_LISTEN;
			break;

		case SO_PEERSEC:
			return security_socket_getpeersec_stream(sock, optval, optlen, len);

		default:
			return(-ENOPROTOOPT);
	}
	if (len > lv)
		len = lv;
	if (copy_to_user(optval, &v, len))
		return -EFAULT;
lenout:
  	if (put_user(len, optlen))
  		return -EFAULT;
  	return 0;
}

/**
 *	sk_alloc - All socket objects are allocated here
 *	@family: protocol family
 *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *	@prot: struct proto associated with this new sock instance
 *	@zero_it: if we should zero the newly allocated sock
 */
struct sock *sk_alloc(int family, gfp_t priority,
		      struct proto *prot, int zero_it)
{
	struct sock *sk = NULL;
	kmem_cache_t *slab = prot->slab;

	if (slab != NULL)
		sk = kmem_cache_alloc(slab, priority);
	else
		sk = kmalloc(prot->obj_size, priority);

	if (sk) {
		if (zero_it) {
			memset(sk, 0, prot->obj_size);
			sk->sk_family = family;
			/*
			 * See comment in struct sock definition to understand
			 * why we need sk_prot_creator -acme
			 */
			sk->sk_prot = sk->sk_prot_creator = prot;
			sock_lock_init(sk);
		}
		
		if (security_sk_alloc(sk, family, priority))
			goto out_free;

		if (!try_module_get(prot->owner))
			goto out_free;
	}
	return sk;

out_free:
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	return NULL;
}

void sk_free(struct sock *sk)
{
	struct sk_filter *filter;
	struct module *owner = sk->sk_prot_creator->owner;

	if (sk->sk_destruct)
		sk->sk_destruct(sk);

	filter = sk->sk_filter;
	if (filter) {
		sk_filter_release(sk, filter);
		sk->sk_filter = NULL;
	}

	sock_disable_timestamp(sk);

	if (atomic_read(&sk->sk_omem_alloc))
		printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
		       __FUNCTION__, atomic_read(&sk->sk_omem_alloc));

	security_sk_free(sk);
	if (sk->sk_prot_creator->slab != NULL)
		kmem_cache_free(sk->sk_prot_creator->slab, sk);
	else
		kfree(sk);
	module_put(owner);
}

struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
{
	struct sock *newsk = sk_alloc(sk->sk_family, priority, sk->sk_prot, 0);

	if (newsk != NULL) {
		struct sk_filter *filter;

		memcpy(newsk, sk, sk->sk_prot->obj_size);

		/* SANITY */
		sk_node_init(&newsk->sk_node);
		sock_lock_init(newsk);
		bh_lock_sock(newsk);

		atomic_set(&newsk->sk_rmem_alloc, 0);
		atomic_set(&newsk->sk_wmem_alloc, 0);
		atomic_set(&newsk->sk_omem_alloc, 0);
		skb_queue_head_init(&newsk->sk_receive_queue);
		skb_queue_head_init(&newsk->sk_write_queue);

		rwlock_init(&newsk->sk_dst_lock);
		rwlock_init(&newsk->sk_callback_lock);

		newsk->sk_dst_cache	= NULL;
		newsk->sk_wmem_queued	= 0;
		newsk->sk_forward_alloc = 0;
		newsk->sk_send_head	= NULL;
		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;
		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;

		sock_reset_flag(newsk, SOCK_DONE);
		skb_queue_head_init(&newsk->sk_error_queue);

		filter = newsk->sk_filter;
		if (filter != NULL)
			sk_filter_charge(newsk, filter);

		if (unlikely(xfrm_sk_clone_policy(newsk))) {
			/* It is still raw copy of parent, so invalidate
			 * destructor and make plain sk_free() */
			newsk->sk_destruct = NULL;
			sk_free(newsk);
			newsk = NULL;
			goto out;
		}

		newsk->sk_err	   = 0;
		newsk->sk_priority = 0;
		atomic_set(&newsk->sk_refcnt, 2);

		/*
		 * Increment the counter in the same struct proto as the master
		 * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
		 * is the same as sk->sk_prot->socks, as this field was copied
		 * with memcpy).
		 *
		 * This _changes_ the previous behaviour, where
		 * tcp_create_openreq_child always was incrementing the
		 * equivalent to tcp_prot->socks (inet_sock_nr), so this have
		 * to be taken into account in all callers. -acme
		 */
		sk_refcnt_debug_inc(newsk);
		newsk->sk_socket = NULL;
		newsk->sk_sleep	 = NULL;

		if (newsk->sk_prot->sockets_allocated)
			atomic_inc(newsk->sk_prot->sockets_allocated);
	}
out:
	return newsk;
}

EXPORT_SYMBOL_GPL(sk_clone);

void __init sk_init(void)
{
	if (num_physpages <= 4096) {
		sysctl_wmem_max = 32767;
		sysctl_rmem_max = 32767;
		sysctl_wmem_default = 32767;
		sysctl_rmem_default = 32767;
	} else if (num_physpages >= 131072) {
		sysctl_wmem_max = 131071;
		sysctl_rmem_max = 131071;
	}
}

/*
 *	Simple resource managers for sockets.
 */


/* 
 * Write buffer destructor automatically called from kfree_skb. 
 */
void sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	/* In case it might be waiting for more memory. */
	atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE))
		sk->sk_write_space(sk);
	sock_put(sk);
}

/* 
 * Read buffer destructor automatically called from kfree_skb. 
 */
void sock_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
}


int sock_i_uid(struct sock *sk)
{
	int uid;

	read_lock(&sk->sk_callback_lock);
	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
	read_unlock(&sk->sk_callback_lock);
	return uid;
}

unsigned long sock_i_ino(struct sock *sk)
{
	unsigned long ino;

	read_lock(&sk->sk_callback_lock);
	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
	read_unlock(&sk->sk_callback_lock);
	return ino;
}

/*
 * Allocate a skb from the socket's send buffer.
 */
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
			     gfp_t priority)
{
	if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
		struct sk_buff * skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_w(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/*
 * Allocate a skb from the socket's receive buffer.
 */ 
struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
			     gfp_t priority)
{
	if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
		struct sk_buff *skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_r(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/* 
 * Allocate a memory block from the socket's option memory buffer.
 */ 
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
	if ((unsigned)size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
		void *mem;
		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.
		 */
		atomic_add(size, &sk->sk_omem_alloc);
		mem = kmalloc(size, priority);
		if (mem)
			return mem;
		atomic_sub(size, &sk->sk_omem_alloc);
	}
	return NULL;
}

/*
 * Free an option memory block.
 */
void sock_kfree_s(struct sock *sk, void *mem, int size)
{
	kfree(mem);
	atomic_sub(size, &sk->sk_omem_alloc);
}

/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
   I think, these locks should be removed for datagram sockets.
 */
static long sock_wait_for_wmem(struct sock * sk, long timeo)
{
	DEFINE_WAIT(wait);

	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
	for (;;) {
		if (!timeo)
			break;
		if (signal_pending(current))
			break;
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
			break;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			break;
		if (sk->sk_err)
			break;
		timeo = schedule_timeout(timeo);
	}
	finish_wait(sk->sk_sleep, &wait);
	return timeo;
}


/*
 *	Generic send/receive buffer handlers
 */

static struct sk_buff *sock_alloc_send_pskb(struct sock *sk,
					    unsigned long header_len,
					    unsigned long data_len,
					    int noblock, int *errcode)
{
	struct sk_buff *skb;
	gfp_t gfp_mask;
	long timeo;
	int err;

	gfp_mask = sk->sk_allocation;
	if (gfp_mask & __GFP_WAIT)
		gfp_mask |= __GFP_REPEAT;

	timeo = sock_sndtimeo(sk, noblock);
	while (1) {
		err = sock_error(sk);
		if (err != 0)
			goto failure;

		err = -EPIPE;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			goto failure;

		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
			skb = alloc_skb(header_len, sk->sk_allocation);
			if (skb) {
				int npages;
				int i;

				/* No pages, we're done... */
				if (!data_len)
					break;

				npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
				skb->truesize += data_len;
				skb_shinfo(skb)->nr_frags = npages;
				for (i = 0; i < npages; i++) {
					struct page *page;
					skb_frag_t *frag;

					page = alloc_pages(sk->sk_allocation, 0);
					if (!page) {
						err = -ENOBUFS;
						skb_shinfo(skb)->nr_frags = i;
						kfree_skb(skb);
						goto failure;
					}

					frag = &skb_shinfo(skb)->frags[i];
					frag->page = page;
					frag->page_offset = 0;
					frag->size = (data_len >= PAGE_SIZE ?
						      PAGE_SIZE :
						      data_len);
					data_len -= PAGE_SIZE;
				}

				/* Full success... */
				break;
			}
			err = -ENOBUFS;