ip_conntrack_proto_tcp.c

linux-2.6.15.6

	if (tcph->rst) return TCP_RST_SET;
	else if (tcph->syn) return (tcph->ack ? TCP_SYNACK_SET : TCP_SYN_SET);
	else if (tcph->fin) return TCP_FIN_SET;
	else if (tcph->ack) return TCP_ACK_SET;
	else return TCP_NONE_SET;
}

/* TCP connection tracking based on 'Real Stateful TCP Packet Filtering
   in IP Filter' by Guido van Rooij.
   
   http://www.nluug.nl/events/sane2000/papers.html
   http://www.iae.nl/users/guido/papers/tcp_filtering.ps.gz
   
   The boundaries and the conditions are changed according to RFC793:
   the packet must intersect the window (i.e. segments may be
   after the right or before the left edge) and thus receivers may ACK
   segments after the right edge of the window.

   	td_maxend = max(sack + max(win,1)) seen in reply packets
	td_maxwin = max(max(win, 1)) + (sack - ack) seen in sent packets
	td_maxwin += seq + len - sender.td_maxend
			if seq + len > sender.td_maxend
	td_end    = max(seq + len) seen in sent packets
   
   I.   Upper bound for valid data:	seq <= sender.td_maxend
   II.  Lower bound for valid data:	seq + len >= sender.td_end - receiver.td_maxwin
   III.	Upper bound for valid ack:      sack <= receiver.td_end
   IV.	Lower bound for valid ack:	ack >= receiver.td_end - MAXACKWINDOW
   	
   where sack is the highest right edge of sack block found in the packet.
   	
   The upper bound limit for a valid ack is not ignored - 
   we doesn't have to deal with fragments. 
*/

static inline __u32 segment_seq_plus_len(__u32 seq,
					 size_t len,
					 struct iphdr *iph,
					 struct tcphdr *tcph)
{
	return (seq + len - (iph->ihl + tcph->doff)*4
		+ (tcph->syn ? 1 : 0) + (tcph->fin ? 1 : 0));
}
  
/* Fixme: what about big packets? */
#define MAXACKWINCONST			66000
#define MAXACKWINDOW(sender)						\
	((sender)->td_maxwin > MAXACKWINCONST ? (sender)->td_maxwin	\
					      : MAXACKWINCONST)
  
/*
 * Simplified tcp_parse_options routine from tcp_input.c
 */
static void tcp_options(const struct sk_buff *skb,
			struct iphdr *iph,
			struct tcphdr *tcph, 
			struct ip_ct_tcp_state *state)
{
	unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
	unsigned char *ptr;
	int length = (tcph->doff*4) - sizeof(struct tcphdr);
	
	if (!length)
		return;

	ptr = skb_header_pointer(skb,
				 (iph->ihl * 4) + sizeof(struct tcphdr),
				 length, buff);
	BUG_ON(ptr == NULL);

	state->td_scale = 
	state->flags = 0;
	
	while (length > 0) {
		int opcode=*ptr++;
		int opsize;
		
		switch (opcode) {
		case TCPOPT_EOL:
			return;
		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
			length--;
			continue;
		default:
			opsize=*ptr++;
			if (opsize < 2) /* "silly options" */
				return;
			if (opsize > length)
				break;	/* don't parse partial options */

			if (opcode == TCPOPT_SACK_PERM 
			    && opsize == TCPOLEN_SACK_PERM)
				state->flags |= IP_CT_TCP_FLAG_SACK_PERM;
			else if (opcode == TCPOPT_WINDOW
				 && opsize == TCPOLEN_WINDOW) {
				state->td_scale = *(u_int8_t *)ptr;
				
				if (state->td_scale > 14) {
					/* See RFC1323 */
					state->td_scale = 14;
				}
				state->flags |=
					IP_CT_TCP_FLAG_WINDOW_SCALE;
			}
			ptr += opsize - 2;
			length -= opsize;
		}
	}
}

static void tcp_sack(const struct sk_buff *skb,
		     struct iphdr *iph,
		     struct tcphdr *tcph,
		     __u32 *sack)
{
	unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
	unsigned char *ptr;
	int length = (tcph->doff*4) - sizeof(struct tcphdr);
	__u32 tmp;

	if (!length)
		return;

	ptr = skb_header_pointer(skb,
				 (iph->ihl * 4) + sizeof(struct tcphdr),
				 length, buff);
	BUG_ON(ptr == NULL);

	/* Fast path for timestamp-only option */
	if (length == TCPOLEN_TSTAMP_ALIGNED*4
	    && *(__u32 *)ptr ==
	        __constant_ntohl((TCPOPT_NOP << 24) 
	        		 | (TCPOPT_NOP << 16)
	        		 | (TCPOPT_TIMESTAMP << 8)
	        		 | TCPOLEN_TIMESTAMP))
		return;
		
	while (length > 0) {
		int opcode=*ptr++;
		int opsize, i;
		
		switch (opcode) {
		case TCPOPT_EOL:
			return;
		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
			length--;
			continue;
		default:
			opsize=*ptr++;
			if (opsize < 2) /* "silly options" */
				return;
			if (opsize > length)
				break;	/* don't parse partial options */

			if (opcode == TCPOPT_SACK 
			    && opsize >= (TCPOLEN_SACK_BASE 
			    		  + TCPOLEN_SACK_PERBLOCK)
			    && !((opsize - TCPOLEN_SACK_BASE) 
			    	 % TCPOLEN_SACK_PERBLOCK)) {
			    	for (i = 0;
			    	     i < (opsize - TCPOLEN_SACK_BASE);
			    	     i += TCPOLEN_SACK_PERBLOCK) {
					tmp = ntohl(*((u_int32_t *)(ptr+i)+1));
					
					if (after(tmp, *sack))
						*sack = tmp;
				}
				return;
			}
			ptr += opsize - 2;
			length -= opsize;
		}
	}
}

static int tcp_in_window(struct ip_ct_tcp *state, 
                         enum ip_conntrack_dir dir,
                         unsigned int index,
                         const struct sk_buff *skb,
                         struct iphdr *iph,
                         struct tcphdr *tcph)
{
	struct ip_ct_tcp_state *sender = &state->seen[dir];
	struct ip_ct_tcp_state *receiver = &state->seen[!dir];
	__u32 seq, ack, sack, end, win, swin;
	int res;
	
	/*
	 * Get the required data from the packet.
	 */
	seq = ntohl(tcph->seq);
	ack = sack = ntohl(tcph->ack_seq);
	win = ntohs(tcph->window);
	end = segment_seq_plus_len(seq, skb->len, iph, tcph);
	
	if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
		tcp_sack(skb, iph, tcph, &sack);
		
	DEBUGP("tcp_in_window: START\n");
	DEBUGP("tcp_in_window: src=%u.%u.%u.%u:%hu dst=%u.%u.%u.%u:%hu "
	       "seq=%u ack=%u sack=%u win=%u end=%u\n",
		NIPQUAD(iph->saddr), ntohs(tcph->source), 
		NIPQUAD(iph->daddr), ntohs(tcph->dest),
		seq, ack, sack, win, end);
	DEBUGP("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
	       "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
		sender->td_end, sender->td_maxend, sender->td_maxwin,
		sender->td_scale, 
		receiver->td_end, receiver->td_maxend, receiver->td_maxwin, 
		receiver->td_scale);
		
	if (sender->td_end == 0) {
		/*
		 * Initialize sender data.
		 */
		if (tcph->syn && tcph->ack) {
			/*
			 * Outgoing SYN-ACK in reply to a SYN.
			 */
			sender->td_end = 
			sender->td_maxend = end;
			sender->td_maxwin = (win == 0 ? 1 : win);

			tcp_options(skb, iph, tcph, sender);
			/* 
			 * RFC 1323:
			 * Both sides must send the Window Scale option
			 * to enable window scaling in either direction.
			 */
			if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
			      && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
				sender->td_scale = 
				receiver->td_scale = 0;
		} else {
			/*
			 * We are in the middle of a connection,
			 * its history is lost for us.
			 * Let's try to use the data from the packet.
		 	 */
			sender->td_end = end;
			sender->td_maxwin = (win == 0 ? 1 : win);
			sender->td_maxend = end + sender->td_maxwin;
		}
	} else if (((state->state == TCP_CONNTRACK_SYN_SENT
		     && dir == IP_CT_DIR_ORIGINAL)
		    || (state->state == TCP_CONNTRACK_SYN_RECV
		        && dir == IP_CT_DIR_REPLY))
		    && after(end, sender->td_end)) {
		/*
		 * RFC 793: "if a TCP is reinitialized ... then it need
		 * not wait at all; it must only be sure to use sequence 
		 * numbers larger than those recently used."
		 */
		sender->td_end =
		sender->td_maxend = end;
		sender->td_maxwin = (win == 0 ? 1 : win);

		tcp_options(skb, iph, tcph, sender);
	}
	
	if (!(tcph->ack)) {
		/*
		 * If there is no ACK, just pretend it was set and OK.
		 */
		ack = sack = receiver->td_end;
	} else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) == 
		    (TCP_FLAG_ACK|TCP_FLAG_RST)) 
		   && (ack == 0)) {
		/*
		 * Broken TCP stacks, that set ACK in RST packets as well
		 * with zero ack value.
		 */
		ack = sack = receiver->td_end;
	}

	if (seq == end
	    && (!tcph->rst 
	        || (seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT)))
		/*
		 * Packets contains no data: we assume it is valid
		 * and check the ack value only.
		 * However RST segments are always validated by their
		 * SEQ number, except when seq == 0 (reset sent answering
		 * SYN.
		 */
		seq = end = sender->td_end;
		
	DEBUGP("tcp_in_window: src=%u.%u.%u.%u:%hu dst=%u.%u.%u.%u:%hu "
	       "seq=%u ack=%u sack =%u win=%u end=%u\n",
		NIPQUAD(iph->saddr), ntohs(tcph->source),
		NIPQUAD(iph->daddr), ntohs(tcph->dest),
		seq, ack, sack, win, end);
	DEBUGP("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
	       "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
		sender->td_end, sender->td_maxend, sender->td_maxwin,
		sender->td_scale, 
		receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
		receiver->td_scale);
	
	DEBUGP("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
		before(seq, sender->td_maxend + 1),
	    	after(end, sender->td_end - receiver->td_maxwin - 1),
	    	before(sack, receiver->td_end + 1),
	    	after(ack, receiver->td_end - MAXACKWINDOW(sender)));
	
	if (sender->loose || receiver->loose ||
	    (before(seq, sender->td_maxend + 1) &&
	     after(end, sender->td_end - receiver->td_maxwin - 1) &&
	     before(sack, receiver->td_end + 1) &&
	     after(ack, receiver->td_end - MAXACKWINDOW(sender)))) {
	    	/*
		 * Take into account window scaling (RFC 1323).
		 */
		if (!tcph->syn)
			win <<= sender->td_scale;
		
		/*
		 * Update sender data.
		 */
		swin = win + (sack - ack);
		if (sender->td_maxwin < swin)
			sender->td_maxwin = swin;
		if (after(end, sender->td_end))
			sender->td_end = end;
		/*
		 * Update receiver data.
		 */
		if (after(end, sender->td_maxend))
			receiver->td_maxwin += end - sender->td_maxend;
		if (after(sack + win, receiver->td_maxend - 1)) {
			receiver->td_maxend = sack + win;
			if (win == 0)
				receiver->td_maxend++;
		}

		/* 
		 * Check retransmissions.
		 */
		if (index == TCP_ACK_SET) {
			if (state->last_dir == dir
			    && state->last_seq == seq
			    && state->last_ack == ack
			    && state->last_end == end)
				state->retrans++;
			else {
				state->last_dir = dir;
				state->last_seq = seq;
				state->last_ack = ack;
				state->last_end = end;
				state->retrans = 0;
			}
		}
		/*
		 * Close the window of disabled window tracking :-)
		 */
		if (sender->loose)
			sender->loose--;
		
		res = 1;
	} else {
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
			"ip_ct_tcp: %s ",
			before(seq, sender->td_maxend + 1) ?
			after(end, sender->td_end - receiver->td_maxwin - 1) ?
			before(sack, receiver->td_end + 1) ?
			after(ack, receiver->td_end - MAXACKWINDOW(sender)) ? "BUG"
			: "ACK is under the lower bound (possible overly delayed ACK)"
			: "ACK is over the upper bound (ACKed data not seen yet)"
			: "SEQ is under the lower bound (already ACKed data retransmitted)"
			: "SEQ is over the upper bound (over the window of the receiver)");

		res = ip_ct_tcp_be_liberal;
  	}
  
	DEBUGP("tcp_in_window: res=%i sender end=%u maxend=%u maxwin=%u "
	       "receiver end=%u maxend=%u maxwin=%u\n",
		res, sender->td_end, sender->td_maxend, sender->td_maxwin, 
		receiver->td_end, receiver->td_maxend, receiver->td_maxwin);

	return res;
}

#ifdef CONFIG_IP_NF_NAT_NEEDED
/* Update sender->td_end after NAT successfully mangled the packet */
void ip_conntrack_tcp_update(struct sk_buff *skb,
			     struct ip_conntrack *conntrack, 
			     enum ip_conntrack_dir dir)
{
	struct iphdr *iph = skb->nh.iph;
	struct tcphdr *tcph = (void *)skb->nh.iph + skb->nh.iph->ihl*4;
	__u32 end;
#ifdef DEBUGP_VARS