Merge branch 'master' of git://eden-feed.erg.abdn.ac.uk/net-2.6

net/dccp/dccp.h

@@ -226,7 +226,7 @@ static inline void dccp_csum_outgoing(struct sk_buff *skb)
 
 extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb);
 
-extern int  dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb);
+extern int  dccp_retransmit_skb(struct sock *sk);
 
 extern void dccp_send_ack(struct sock *sk);
 extern void dccp_reqsk_send_ack(struct sk_buff *sk, struct request_sock *rsk);

net/dccp/ipv4.c

@@ -196,8 +196,8 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk,
 static void dccp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data +
-							(iph->ihl << 2));
+	const u8 offset = iph->ihl << 2;
+	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
 	struct dccp_sock *dp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
@@ -207,7 +207,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < (iph->ihl << 2) + 8) {
+	if (skb->len < offset + sizeof(*dh) ||
+	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
 		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		return;
 	}
@@ -238,7 +239,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	dp = dccp_sk(sk);
 	seq = dccp_hdr_seq(dh);
 	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
-	    !between48(seq, dp->dccps_swl, dp->dccps_swh)) {
+	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}

net/dccp/ipv6.c

@@ -89,12 +89,19 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 {
 	struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data;
 	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
 	struct sock *sk;
 	int err;
 	__u64 seq;
 	struct net *net = dev_net(skb->dev);
 
+	if (skb->len < offset + sizeof(*dh) ||
+	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
+		ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+		return;
+	}
+
 	sk = inet6_lookup(net, &dccp_hashinfo,
 			&hdr->daddr, dh->dccph_dport,
 			&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
@@ -116,6 +123,14 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (sk->sk_state == DCCP_CLOSED)
 		goto out;
 
+	dp = dccp_sk(sk);
+	seq = dccp_hdr_seq(dh);
+	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
+	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
+		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
+		goto out;
+	}
+
 	np = inet6_sk(sk);
 
 	if (type == ICMPV6_PKT_TOOBIG) {
@@ -168,7 +183,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	icmpv6_err_convert(type, code, &err);
 
-	seq = dccp_hdr_seq(dh);
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
 		struct request_sock *req, **prev;

net/dccp/output.c

@@ -53,8 +53,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 					  dccp_packet_hdr_len(dcb->dccpd_type);
 		int err, set_ack = 1;
 		u64 ackno = dp->dccps_gsr;
-
-		dccp_inc_seqno(&dp->dccps_gss);
+		/*
+		 * Increment GSS here already in case the option code needs it.
+		 * Update GSS for real only if option processing below succeeds.
+		 */
+		dcb->dccpd_seq = ADD48(dp->dccps_gss, 1);
 
 		switch (dcb->dccpd_type) {
 		case DCCP_PKT_DATA:
@@ -66,6 +69,9 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		case DCCP_PKT_REQUEST:
 			set_ack = 0;
+			/* Use ISS on the first (non-retransmitted) Request. */
+			if (icsk->icsk_retransmits == 0)
+				dcb->dccpd_seq = dp->dccps_iss;
 			/* fall through */
 
 		case DCCP_PKT_SYNC:
@@ -84,8 +90,6 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 			break;
 		}
 
-		dcb->dccpd_seq = dp->dccps_gss;
-
 		if (dccp_insert_options(sk, skb)) {
 			kfree_skb(skb);
 			return -EPROTO;
@@ -103,7 +107,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 		/* XXX For now we're using only 48 bits sequence numbers */
 		dh->dccph_x	= 1;
 
-		dp->dccps_awh = dp->dccps_gss;
+		dccp_update_gss(sk, dcb->dccpd_seq);
 		dccp_hdr_set_seq(dh, dp->dccps_gss);
 		if (set_ack)
 			dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
@@ -112,6 +116,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 		case DCCP_PKT_REQUEST:
 			dccp_hdr_request(skb)->dccph_req_service =
 							dp->dccps_service;
+			/*
+			 * Limit Ack window to ISS <= P.ackno <= GSS, so that
+			 * only Responses to Requests we sent are considered.
+			 */
+			dp->dccps_awl = dp->dccps_iss;
 			break;
 		case DCCP_PKT_RESET:
 			dccp_hdr_reset(skb)->dccph_reset_code =
@@ -284,14 +293,26 @@ void dccp_write_xmit(struct sock *sk, int block)
 	}
 }
 
-int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
+/**
+ * dccp_retransmit_skb  -  Retransmit Request, Close, or CloseReq packets
+ * There are only four retransmittable packet types in DCCP:
+ * - Request  in client-REQUEST  state (sec. 8.1.1),
+ * - CloseReq in server-CLOSEREQ state (sec. 8.3),
+ * - Close    in   node-CLOSING  state (sec. 8.3),
+ * - Acks in client-PARTOPEN state (sec. 8.1.5, handled by dccp_delack_timer()).
+ * This function expects sk->sk_send_head to contain the original skb.
+ */
+int dccp_retransmit_skb(struct sock *sk)
 {
+	WARN_ON(sk->sk_send_head == NULL);
+
 	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0)
 		return -EHOSTUNREACH; /* Routing failure or similar. */
 
-	return dccp_transmit_skb(sk, (skb_cloned(skb) ?
-				      pskb_copy(skb, GFP_ATOMIC):
-				      skb_clone(skb, GFP_ATOMIC)));
+	/* this count is used to distinguish original and retransmitted skb */
+	inet_csk(sk)->icsk_retransmits++;
+
+	return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC));
 }
 
 struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
@@ -437,19 +458,7 @@ static inline void dccp_connect_init(struct sock *sk)
 
 	dccp_sync_mss(sk, dst_mtu(dst));
 
-	/*
-	 * SWL and AWL are initially adjusted so that they are not less than
-	 * the initial Sequence Numbers received and sent, respectively:
-	 *	SWL := max(GSR + 1 - floor(W/4), ISR),
-	 *	AWL := max(GSS - W' + 1, ISS).
-	 * These adjustments MUST be applied only at the beginning of the
-	 * connection.
-	 */
-	dccp_update_gss(sk, dp->dccps_iss);
-	dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss));
-
-	/* S.GAR - greatest valid acknowledgement number received on a non-Sync;
-	 *         initialized to S.ISS (sec. 8.5)                            */
+	/* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */
 	dp->dccps_gar = dp->dccps_iss;
 
 	icsk->icsk_retransmits = 0;

net/dccp/timer.c

@@ -98,22 +98,12 @@ static void dccp_retransmit_timer(struct sock *sk)
 		goto backoff;
 	}
 
-	/*
-	 * sk->sk_send_head has to have one skb with
-	 * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP
-	 * packet types. The only packets eligible for retransmission are:
-	 *	-- Requests in client-REQUEST  state (sec. 8.1.1)
-	 *	-- Acks     in client-PARTOPEN state (sec. 8.1.5)
-	 *	-- CloseReq in server-CLOSEREQ state (sec. 8.3)
-	 *	-- Close    in   node-CLOSING  state (sec. 8.3)                */
-	WARN_ON(sk->sk_send_head == NULL);
-
 	/*
 	 * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was
 	 * sent, no need to retransmit, this sock is dead.
 	 */
 	if (dccp_write_timeout(sk))
-		goto out;
+		return;
 
 	/*
 	 * We want to know the number of packets retransmitted, not the
@@ -122,30 +112,28 @@ static void dccp_retransmit_timer(struct sock *sk)
 	if (icsk->icsk_retransmits == 0)
 		DCCP_INC_STATS_BH(DCCP_MIB_TIMEOUTS);
 
-	if (dccp_retransmit_skb(sk, sk->sk_send_head) < 0) {
+	if (dccp_retransmit_skb(sk) != 0) {
 		/*
 		 * Retransmission failed because of local congestion,
 		 * do not backoff.
 		 */
-		if (icsk->icsk_retransmits == 0)
+		if (--icsk->icsk_retransmits == 0)
 			icsk->icsk_retransmits = 1;
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 					  min(icsk->icsk_rto,
 					      TCP_RESOURCE_PROBE_INTERVAL),
 					  DCCP_RTO_MAX);
-		goto out;
+		return;
 	}
 
 backoff:
 	icsk->icsk_backoff++;
-	icsk->icsk_retransmits++;
 
 	icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX);
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto,
 				  DCCP_RTO_MAX);
 	if (icsk->icsk_retransmits > sysctl_dccp_retries1)
 		__sk_dst_reset(sk);
-out:;
 }
 
 static void dccp_write_timer(unsigned long data)