udp.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.
 *
 *		The User Datagram Protocol (UDP).
 *
 * Version:	$Id: udp.c,v 1.102 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Alan Cox, <Alan.Cox@linux.org>
 *		Hirokazu Takahashi, <taka@valinux.co.jp>
 *
 * Fixes:
 *		Alan Cox	:	verify_area() calls
 *		Alan Cox	: 	stopped close while in use off icmp
 *					messages. Not a fix but a botch that
 *					for udp at least is 'valid'.
 *		Alan Cox	:	Fixed icmp handling properly
 *		Alan Cox	: 	Correct error for oversized datagrams
 *		Alan Cox	:	Tidied select() semantics.
 *		Alan Cox	:	udp_err() fixed properly, also now
 *					select and read wake correctly on errors
 *		Alan Cox	:	udp_send verify_area moved to avoid mem leak
 *		Alan Cox	:	UDP can count its memory
 *		Alan Cox	:	send to an unknown connection causes
 *					an ECONNREFUSED off the icmp, but
 *					does NOT close.
 *		Alan Cox	:	Switched to new sk_buff handlers. No more backlog!
 *		Alan Cox	:	Using generic datagram code. Even smaller and the PEEK
 *					bug no longer crashes it.
 *		Fred Van Kempen	: 	Net2e support for sk->broadcast.
 *		Alan Cox	:	Uses skb_free_datagram
 *		Alan Cox	:	Added get/set sockopt support.
 *		Alan Cox	:	Broadcasting without option set returns EACCES.
 *		Alan Cox	:	No wakeup calls. Instead we now use the callbacks.
 *		Alan Cox	:	Use ip_tos and ip_ttl
 *		Alan Cox	:	SNMP Mibs
 *		Alan Cox	:	MSG_DONTROUTE, and 0.0.0.0 support.
 *		Matt Dillon	:	UDP length checks.
 *		Alan Cox	:	Smarter af_inet used properly.
 *		Alan Cox	:	Use new kernel side addressing.
 *		Alan Cox	:	Incorrect return on truncated datagram receive.
 *	Arnt Gulbrandsen 	:	New udp_send and stuff
 *		Alan Cox	:	Cache last socket
 *		Alan Cox	:	Route cache
 *		Jon Peatfield	:	Minor efficiency fix to sendto().
 *		Mike Shaver	:	RFC1122 checks.
 *		Alan Cox	:	Nonblocking error fix.
 *	Willy Konynenberg	:	Transparent proxying support.
 *		Mike McLagan	:	Routing by source
 *		David S. Miller	:	New socket lookup architecture.
 *					Last socket cache retained as it
 *					does have a high hit rate.
 *		Olaf Kirch	:	Don't linearise iovec on sendmsg.
 *		Andi Kleen	:	Some cleanups, cache destination entry
 *					for connect.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *		Melvin Smith	:	Check msg_name not msg_namelen in sendto(),
 *					return ENOTCONN for unconnected sockets (POSIX)
 *		Janos Farkas	:	don't deliver multi/broadcasts to a different
 *					bound-to-device socket
 *	Hirokazu Takahashi	:	HW checksumming for outgoing UDP
 *					datagrams.
 *	Hirokazu Takahashi	:	sendfile() on UDP works now.
 *		Arnaldo C. Melo :	convert /proc/net/udp to seq_file
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov:		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 *	Derek Atkins <derek@ihtfp.com>: Add Encapulation Support
 *	James Chapman		:	Add L2TP encapsulation type.
 *
 *
 *		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 <asm/system.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <linux/bootmem.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/tcp_states.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include "udp_impl.h"

/*
 *	Snmp MIB for the UDP layer
 */

DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly;
EXPORT_SYMBOL(udp_statistics);

DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;
EXPORT_SYMBOL(udp_stats_in6);

struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);

int sysctl_udp_mem[3] __read_mostly;
int sysctl_udp_rmem_min __read_mostly;
int sysctl_udp_wmem_min __read_mostly;

EXPORT_SYMBOL(sysctl_udp_mem);
EXPORT_SYMBOL(sysctl_udp_rmem_min);
EXPORT_SYMBOL(sysctl_udp_wmem_min);

atomic_t udp_memory_allocated;
EXPORT_SYMBOL(udp_memory_allocated);

static inline int __udp_lib_lport_inuse(struct net *net, __u16 num,
					const struct hlist_head udptable[])
{
	struct sock *sk;
	struct hlist_node *node;

	sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
		if (sk->sk_net == net && sk->sk_hash == num)
			return 1;
	return 0;
}

/**
 *  __udp_lib_get_port  -  UDP/-Lite port lookup for IPv4 and IPv6
 *
 *  @sk:          socket struct in question
 *  @snum:        port number to look up
 *  @udptable:    hash list table, must be of UDP_HTABLE_SIZE
 *  @saddr_comp:  AF-dependent comparison of bound local IP addresses
 */
int __udp_lib_get_port(struct sock *sk, unsigned short snum,
		       struct hlist_head udptable[],
		       int (*saddr_comp)(const struct sock *sk1,
					 const struct sock *sk2 )    )
{
	struct hlist_node *node;
	struct hlist_head *head;
	struct sock *sk2;
	int    error = 1;
	struct net *net = sk->sk_net;

	write_lock_bh(&udp_hash_lock);

	if (!snum) {
		int i, low, high, remaining;
		unsigned rover, best, best_size_so_far;

		inet_get_local_port_range(&low, &high);
		remaining = (high - low) + 1;

		best_size_so_far = UINT_MAX;
		best = rover = net_random() % remaining + low;

		/* 1st pass: look for empty (or shortest) hash chain */
		for (i = 0; i < UDP_HTABLE_SIZE; i++) {
			int size = 0;

			head = &udptable[rover & (UDP_HTABLE_SIZE - 1)];
			if (hlist_empty(head))
				goto gotit;

			sk_for_each(sk2, node, head) {
				if (++size >= best_size_so_far)
					goto next;
			}
			best_size_so_far = size;
			best = rover;
		next:
			/* fold back if end of range */
			if (++rover > high)
				rover = low + ((rover - low)
					       & (UDP_HTABLE_SIZE - 1));


		}

		/* 2nd pass: find hole in shortest hash chain */
		rover = best;
		for (i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++) {
			if (! __udp_lib_lport_inuse(net, rover, udptable))
				goto gotit;
			rover += UDP_HTABLE_SIZE;
			if (rover > high)
				rover = low + ((rover - low)
					       & (UDP_HTABLE_SIZE - 1));
		}


		/* All ports in use! */
		goto fail;

gotit:
		snum = rover;
	} else {
		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];

		sk_for_each(sk2, node, head)
			if (sk2->sk_hash == snum                             &&
			    sk2 != sk                                        &&
			    sk2->sk_net == net				     &&
			    (!sk2->sk_reuse        || !sk->sk_reuse)         &&
			    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
			     || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
			    (*saddr_comp)(sk, sk2)                             )
				goto fail;
	}

	inet_sk(sk)->num = snum;
	sk->sk_hash = snum;
	if (sk_unhashed(sk)) {
		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
		sk_add_node(sk, head);
		sock_prot_inuse_add(sk->sk_prot, 1);
	}
	error = 0;
fail:
	write_unlock_bh(&udp_hash_lock);
	return error;
}

int udp_get_port(struct sock *sk, unsigned short snum,
			int (*scmp)(const struct sock *, const struct sock *))
{
	return  __udp_lib_get_port(sk, snum, udp_hash, scmp);
}

/*
 *	IOCTL requests applicable to the UDP protocol
 */

int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch (cmd) {
	case SIOCOUTQ:
	{
		int amount = atomic_read(&sk->sk_wmem_alloc);
		return put_user(amount, (int __user *)arg);
	}

	case SIOCINQ:
	{
		struct sk_buff *skb;
		unsigned long amount;

		amount = 0;
		spin_lock_bh(&sk->sk_receive_queue.lock);
		skb = skb_peek(&sk->sk_receive_queue);
		if (skb != NULL) {
			/*
			 * We will only return the amount
			 * of this packet since that is all
			 * that will be read.
			 */
			amount = skb->len - sizeof(struct udphdr);
		}
		spin_unlock_bh(&sk->sk_receive_queue.lock);
		return put_user(amount, (int __user *)arg);
	}

	default:
		return -ENOIOCTLCMD;
	}

	return 0;
}

int udp_disconnect(struct sock *sk, int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	/*
	 *	1003.1g - break association.
	 */

	sk->sk_state = TCP_CLOSE;
	inet->daddr = 0;
	inet->dport = 0;
	sk->sk_bound_dev_if = 0;
	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
		sk->sk_prot->unhash(sk);
		inet->sport = 0;
	}
	sk_dst_reset(sk);
	return 0;
}

/*
 *	Socket option code for UDP
 */
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
		       char __user *optval, int optlen,
		       int (*push_pending_frames)(struct sock *))
{
	struct udp_sock *up = udp_sk(sk);
	int val;
	int err = 0;
#ifdef CONFIG_IP_UDPLITE
	int is_udplite = IS_UDPLITE(sk);
#endif

	if (optlen<sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	switch (optname) {
	case UDP_CORK:
		if (val != 0) {
			up->corkflag = 1;
		} else {
			up->corkflag = 0;
			lock_sock(sk);
			(*push_pending_frames)(sk);
			release_sock(sk);
		}
		break;

	case UDP_ENCAP:
		switch (val) {
		case 0:
		case UDP_ENCAP_ESPINUDP:
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			up->encap_rcv = xfrm4_udp_encap_rcv;
			/* FALLTHROUGH */
		case UDP_ENCAP_L2TPINUDP:
			up->encap_type = val;
			break;
		default:
			err = -ENOPROTOOPT;
			break;
		}
		break;

#ifdef CONFIG_IP_UDPLITE
	/*
	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
	 */
	/* The sender sets actual checksum coverage length via this option.
	 * The case coverage > packet length is handled by send module. */
	case UDPLITE_SEND_CSCOV:
		if (!is_udplite)         /* Disable the option on UDP sockets */
			return -ENOPROTOOPT;
		if (val != 0 && val < 8) /* Illegal coverage: use default (8) */
			val = 8;
		up->pcslen = val;
		up->pcflag |= UDPLITE_SEND_CC;
		break;

	/* The receiver specifies a minimum checksum coverage value. To make
	 * sense, this should be set to at least 8 (as done below). If zero is
	 * used, this again means full checksum coverage.                     */
	case UDPLITE_RECV_CSCOV:
		if (!is_udplite)         /* Disable the option on UDP sockets */
			return -ENOPROTOOPT;
		if (val != 0 && val < 8) /* Avoid silly minimal values.       */
			val = 8;
		up->pcrlen = val;
		up->pcflag |= UDPLITE_RECV_CC;
		break;
#endif

	default:
		err = -ENOPROTOOPT;
		break;
	}

	return err;
}

int udp_lib_getsockopt(struct sock *sk, int level, int optname,
		       char __user *optval, int __user *optlen)
{
	struct udp_sock *up = udp_sk(sk);
	int val, len;

	if (get_user(len,optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(int));

	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case UDP_CORK:
		val = up->corkflag;
		break;

	case UDP_ENCAP:
		val = up->encap_type;
		break;

	/* The following two cannot be changed on UDP sockets, the return is
	 * always 0 (which corresponds to the full checksum coverage of UDP). */
	case UDPLITE_SEND_CSCOV:
		val = up->pcslen;
		break;

	case UDPLITE_RECV_CSCOV:
		val = up->pcrlen;
		break;

	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val,len))
		return -EFAULT;
	return 0;
}

/**
 * 	udp_poll - wait for a UDP event.
 *	@file - file struct
 *	@sock - socket
 *	@wait - poll table
 *
 *	This is same as datagram poll, except for the special case of
 *	blocking sockets. If application is using a blocking fd
 *	and a packet with checksum error is in the queue;
 *	then it could get return from select indicating data available
 *	but then block when reading it. Add special case code
 *	to work around these arguably broken applications.
 */
unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	unsigned int mask = datagram_poll(file, sock, wait);
	struct sock *sk = sock->sk;
	int 	is_lite = IS_UDPLITE(sk);

	/* Check for false positives due to checksum errors */
	if ( (mask & POLLRDNORM) &&
	     !(file->f_flags & O_NONBLOCK) &&
	     !(sk->sk_shutdown & RCV_SHUTDOWN)){
		struct sk_buff_head *rcvq = &sk->sk_receive_queue;
		struct sk_buff *skb;

		spin_lock_bh(&rcvq->lock);
		while ((skb = skb_peek(rcvq)) != NULL &&
		       udp_lib_checksum_complete(skb)) {
			UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
			__skb_unlink(skb, rcvq);
			kfree_skb(skb);
		}
		spin_unlock_bh(&rcvq->lock);

		/* nothing to see, move along */
		if (skb == NULL)
			mask &= ~(POLLIN | POLLRDNORM);
	}

	return mask;

}


/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS

static struct sock *udp_get_first(struct seq_file *seq)
{
	struct sock *sk;
	struct udp_iter_state *state = seq->private;

	for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
		struct hlist_node *node;
		sk_for_each(sk, node, state->hashtable + state->bucket) {
			if (sk->sk_family == state->family)
				goto found;
		}
	}
	sk = NULL;
found:
	return sk;
}

static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
	struct udp_iter_state *state = seq->private;

	do {
		sk = sk_next(sk);
try_again:
		;
	} while (sk && sk->sk_family != state->family);

	if (!sk && ++state->bucket < UDP_HTABLE_SIZE) {
		sk = sk_head(state->hashtable + state->bucket);
		goto try_again;
	}
	return sk;
}

static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
{
	struct sock *sk = udp_get_first(seq);

	if (sk)
		while (pos && (sk = udp_get_next(seq, sk)) != NULL)
			--pos;
	return pos ? NULL : sk;
}

static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
	__acquires(udp_hash_lock)
{
	read_lock(&udp_hash_lock);
	return *pos ? udp_get_idx(seq, *pos-1) : (void *)1;
}

static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *sk;

	if (v == (void *)1)
		sk = udp_get_idx(seq, 0);
	else
		sk = udp_get_next(seq, v);

	++*pos;
	return sk;
}

static void udp_seq_stop(struct seq_file *seq, void *v)
	__releases(udp_hash_lock)
{
	read_unlock(&udp_hash_lock);
}

static int udp_seq_open(struct inode *inode, struct file *file)
{
	struct udp_seq_afinfo *afinfo = PDE(inode)->data;
	struct seq_file *seq;
	int rc = -ENOMEM;
	struct udp_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL);

	if (!s)
		goto out;
	s->family		= afinfo->family;
	s->hashtable		= afinfo->hashtable;
	s->seq_ops.start	= udp_seq_start;
	s->seq_ops.next		= udp_seq_next;
	s->seq_ops.show		= afinfo->seq_show;
	s->seq_ops.stop		= udp_seq_stop;

	rc = seq_open(file, &s->seq_ops);
	if (rc)
		goto out_kfree;

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

/* ------------------------------------------------------------------------ */
int udp_proc_register(struct udp_seq_afinfo *afinfo)
{
	struct proc_dir_entry *p;
	int rc = 0;

	if (!afinfo)
		return -EINVAL;
	afinfo->seq_fops->owner		= afinfo->owner;
	afinfo->seq_fops->open		= udp_seq_open;
	afinfo->seq_fops->read		= seq_read;
	afinfo->seq_fops->llseek	= seq_lseek;
	afinfo->seq_fops->release	= seq_release_private;

	p = proc_net_fops_create(&init_net, afinfo->name, S_IRUGO, afinfo->seq_fops);
	if (p)
		p->data = afinfo;
	else
		rc = -ENOMEM;
	return rc;
}

void udp_proc_unregister(struct udp_seq_afinfo *afinfo)
{
	if (!afinfo)
		return;
	proc_net_remove(&init_net, afinfo->name);
	memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
}
#endif /* CONFIG_PROC_FS */

void __init udp_init(void)
{
	unsigned long limit;

	/* Set the pressure threshold up by the same strategy of TCP. It is a
	 * fraction of global memory that is up to 1/2 at 256 MB, decreasing
	 * toward zero with the amount of memory, with a floor of 128 pages.
	 */
	limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
	limit = (limit * (nr_all_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
	limit = max(limit, 128UL);
	sysctl_udp_mem[0] = limit / 4 * 3;
	sysctl_udp_mem[1] = limit;
	sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2;

	sysctl_udp_rmem_min = SK_MEM_QUANTUM;
	sysctl_udp_wmem_min = SK_MEM_QUANTUM;
}

EXPORT_SYMBOL(udp_disconnect);
EXPORT_SYMBOL(udp_hash);
EXPORT_SYMBOL(udp_hash_lock);
EXPORT_SYMBOL(udp_ioctl);
EXPORT_SYMBOL(udp_get_port);
EXPORT_SYMBOL(udp_lib_getsockopt);
EXPORT_SYMBOL(udp_lib_setsockopt);
EXPORT_SYMBOL(udp_poll);

#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(udp_proc_register);
EXPORT_SYMBOL(udp_proc_unregister);
#endif