path: root/net/ipv4/tcp_minisocks.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.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Version:	$Id: tcp_minisocks.c,v 1.15 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *		Linus Torvalds, <torvalds@cs.helsinki.fi>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Matthew Dillon, <dillon@apollo.west.oic.com>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 */

#include <linux/config.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/workqueue.h>
#include <net/tcp.h>
#include <net/inet_common.h>
#include <net/xfrm.h>

#ifdef CONFIG_SYSCTL
#define SYNC_INIT 0 /* let the user enable it */
#else
#define SYNC_INIT 1
#endif

int sysctl_tcp_tw_recycle;
int sysctl_tcp_max_tw_buckets = NR_FILE*2;

int sysctl_tcp_syncookies = SYNC_INIT; 
int sysctl_tcp_abort_on_overflow;

static void tcp_tw_schedule(struct tcp_tw_bucket *tw, int timeo);

static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
{
	if (seq == s_win)
		return 1;
	if (after(end_seq, s_win) && before(seq, e_win))
		return 1;
	return (seq == e_win && seq == end_seq);
}

/* New-style handling of TIME_WAIT sockets. */

int tcp_tw_count;


/* Must be called with locally disabled BHs. */
static void tcp_timewait_kill(struct tcp_tw_bucket *tw)
{
	struct tcp_ehash_bucket *ehead;
	struct tcp_bind_hashbucket *bhead;
	struct tcp_bind_bucket *tb;

	/* Unlink from established hashes. */
	ehead = &tcp_ehash[tw->tw_hashent];
	write_lock(&ehead->lock);
	if (hlist_unhashed(&tw->tw_node)) {
		write_unlock(&ehead->lock);
		return;
	}
	__hlist_del(&tw->tw_node);
	sk_node_init(&tw->tw_node);
	write_unlock(&ehead->lock);

	/* Disassociate with bind bucket. */
	bhead = &tcp_bhash[tcp_bhashfn(tw->tw_num)];
	spin_lock(&bhead->lock);
	tb = tw->tw_tb;
	__hlist_del(&tw->tw_bind_node);
	tw->tw_tb = NULL;
	tcp_bucket_destroy(tb);
	spin_unlock(&bhead->lock);

#ifdef INET_REFCNT_DEBUG
	if (atomic_read(&tw->tw_refcnt) != 1) {
		printk(KERN_DEBUG "tw_bucket %p refcnt=%d\n", tw,
		       atomic_read(&tw->tw_refcnt));
	}
#endif
	tcp_tw_put(tw);
}

/* 
 * * Main purpose of TIME-WAIT state is to close connection gracefully,
 *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
 *   (and, probably, tail of data) and one or more our ACKs are lost.
 * * What is TIME-WAIT timeout? It is associated with maximal packet
 *   lifetime in the internet, which results in wrong conclusion, that
 *   it is set to catch "old duplicate segments" wandering out of their path.
 *   It is not quite correct. This timeout is calculated so that it exceeds
 *   maximal retransmission timeout enough to allow to lose one (or more)
 *   segments sent by peer and our ACKs. This time may be calculated from RTO.
 * * When TIME-WAIT socket receives RST, it means that another end
 *   finally closed and we are allowed to kill TIME-WAIT too.
 * * Second purpose of TIME-WAIT is catching old duplicate segments.
 *   Well, certainly it is pure paranoia, but if we load TIME-WAIT
 *   with this semantics, we MUST NOT kill TIME-WAIT state with RSTs.
 * * If we invented some more clever way to catch duplicates
 *   (f.e. based on PAWS), we could truncate TIME-WAIT to several RTOs.
 *
 * The algorithm below is based on FORMAL INTERPRETATION of RFCs.
 * When you compare it to RFCs, please, read section SEGMENT ARRIVES
 * from the very beginning.
 *
 * NOTE. With recycling (and later with fin-wait-2) TW bucket
 * is _not_ stateless. It means, that strictly speaking we must
 * spinlock it. I do not want! Well, probability of misbehaviour
 * is ridiculously low and, seems, we could use some mb() tricks
 * to avoid misread sequence numbers, states etc.  --ANK
 */
enum tcp_tw_status
tcp_timewait_state_process(struct tcp_tw_bucket *tw, struct sk_buff *skb,
			   struct tcphdr *th, unsigned len)
{
	struct tcp_options_received tmp_opt;
	int paws_reject = 0;

	tmp_opt.saw_tstamp = 0;
	if (th->doff > (sizeof(struct tcphdr) >> 2) && tw->tw_ts_recent_stamp) {
		tcp_parse_options(skb, &tmp_opt, 0);

		if (tmp_opt.saw_tstamp) {
			tmp_opt.ts_recent	   = tw->tw_ts_recent;
			tmp_opt.ts_recent_stamp = tw->tw_ts_recent_stamp;
			paws_reject = tcp_paws_check(&tmp_opt, th->rst);
		}
	}

	if (tw->tw_substate == TCP_FIN_WAIT2) {
		/* Just repeat all the checks of tcp_rcv_state_process() */

		/* Out of window, send ACK */
		if (paws_reject ||
		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
				   tw->tw_rcv_nxt,
				   tw->tw_rcv_nxt + tw->tw_rcv_wnd))