Merge branch 'master'

11 files changed, 100 insertions, 46 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eaa150c..d368cf2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,13 +228,14 @@ static int inet_create(struct socket *sock, int protocol)
 	unsigned char answer_flags;
 	char answer_no_check;
 	int try_loading_module = 0;
-	int err = -ESOCKTNOSUPPORT;
+	int err;
 
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
 	answer = NULL;
 lookup_protocol:
+	err = -ESOCKTNOSUPPORT;
 	rcu_read_lock();
 	list_for_each_rcu(p, &inetsw[sock->type]) {
 		answer = list_entry(p, struct inet_protosw, list);
@@ -252,6 +253,7 @@ lookup_protocol:
 			if (IPPROTO_IP == answer->protocol)
 				break;
 		}
+		err = -EPROTONOSUPPORT;
 		answer = NULL;
 	}
 
@@ -280,9 +282,6 @@ lookup_protocol:
 	err = -EPERM;
 	if (answer->capability > 0 && !capable(answer->capability))
 		goto out_rcu_unlock;
-	err = -EPROTONOSUPPORT;
-	if (!protocol)
-		goto out_rcu_unlock;
 
 	sock->ops = answer->ops;
 	answer_prot = answer->prot;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 882f88f..19b1b98 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -544,12 +544,16 @@ static void nl_fib_input(struct sock *sk, int len)
 	struct sk_buff *skb = NULL;
         struct nlmsghdr *nlh = NULL;
 	struct fib_result_nl *frn;
-	int err;
 	u32 pid;     
 	struct fib_table *tb;
 	
-	skb = skb_recv_datagram(sk, 0, 0, &err);
+	skb = skb_dequeue(&sk->sk_receive_queue);
 	nlh = (struct nlmsghdr *)skb->data;
+	if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len ||
+	    nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn))) {
+		kfree_skb(skb);
+		return;
+	}
 	
 	frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
 	tb = fib_get_table(frn->tb_id_in);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c04607b..4a195c7 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -897,7 +897,10 @@ int igmp_rcv(struct sk_buff *skb)
 		/* Is it our report looped back? */
 		if (((struct rtable*)skb->dst)->fl.iif == 0)
 			break;
-		igmp_heard_report(in_dev, ih->group);
+		/* don't rely on MC router hearing unicast reports */
+		if (skb->pkt_type == PACKET_MULTICAST ||
+		    skb->pkt_type == PACKET_BROADCAST)
+			igmp_heard_report(in_dev, ih->group);
 		break;
 	case IGMP_PIM:
 #ifdef CONFIG_IP_PIMSM_V1
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
index 6259816..aeb7353 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
@@ -272,9 +272,9 @@ static const enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sCL -> sCL
  */
 /* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*ack*/	   { sIV, sIV, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
+/*ack*/	   { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
 /*
- *	sSS -> sIV	Might be a half-open connection.
+ *	sSS -> sIG	Might be a half-open connection.
  *	sSR -> sSR	Might answer late resent SYN.
  *	sES -> sES	:-)
  *	sFW -> sCW	Normal close request answered by ACK.
@@ -917,8 +917,12 @@ static int tcp_packet(struct ip_conntrack *conntrack,
 
 	switch (new_state) {
 	case TCP_CONNTRACK_IGNORE:
-		/* Either SYN in ORIGINAL
-		 * or SYN/ACK in REPLY. */
+		/* Ignored packets:
+		 * 
+		 * a) SYN in ORIGINAL
+		 * b) SYN/ACK in REPLY
+		 * c) ACK in reply direction after initial SYN in original.
+		 */
 		if (index == TCP_SYNACK_SET
 		    && conntrack->proto.tcp.last_index == TCP_SYN_SET
 		    && conntrack->proto.tcp.last_dir != dir
@@ -985,13 +989,20 @@ static int tcp_packet(struct ip_conntrack *conntrack,
 		}
 	case TCP_CONNTRACK_CLOSE:
 		if (index == TCP_RST_SET
-		    && test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)
-		    && conntrack->proto.tcp.last_index == TCP_SYN_SET
+		    && ((test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)
+		         && conntrack->proto.tcp.last_index == TCP_SYN_SET)
+		        || (!test_bit(IPS_ASSURED_BIT, &conntrack->status)
+		            && conntrack->proto.tcp.last_index == TCP_ACK_SET))
 		    && ntohl(th->ack_seq) == conntrack->proto.tcp.last_end) {
-			/* RST sent to invalid SYN we had let trough
-			 * SYN was in window then, tear down connection.
+			/* RST sent to invalid SYN or ACK we had let trough
+			 * at a) and c) above:
+			 *
+			 * a) SYN was in window then
+			 * c) we hold a half-open connection.
+			 *
+			 * Delete our connection entry.
 			 * We skip window checking, because packet might ACK
-			 * segments we ignored in the SYN. */
+			 * segments we ignored. */
 			goto in_window;
 		}
 		/* Just fall trough */
diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c
index 2d44b07..261cbb4 100644
--- a/net/ipv4/netfilter/ipt_recent.c
+++ b/net/ipv4/netfilter/ipt_recent.c
@@ -532,6 +532,7 @@ match(const struct sk_buff *skb,
 			}
 			if(info->seconds && info->hit_count) {
 				for(pkt_count = 0, hits_found = 0; pkt_count < ip_pkt_list_tot; pkt_count++) {
+					if(r_list[location].last_pkts[pkt_count] == 0) break;
 					if(time_before_eq(now,r_list[location].last_pkts[pkt_count]+info->seconds*HZ)) hits_found++;
 				}
 				if(hits_found >= info->hit_count) ans = !info->invert; else ans = info->invert;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c63b8ce..d954638 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -92,10 +92,13 @@ static int inet6_create(struct socket *sock, int protocol)
 	struct proto *answer_prot;
 	unsigned char answer_flags;
 	char answer_no_check;
-	int rc;
+	int try_loading_module = 0;
+	int err;
 
 	/* Look for the requested type/protocol pair. */
 	answer = NULL;
+lookup_protocol:
+	err = -ESOCKTNOSUPPORT;
 	rcu_read_lock();
 	list_for_each_rcu(p, &inetsw6[sock->type]) {
 		answer = list_entry(p, struct inet_protosw, list);
@@ -113,21 +116,37 @@ static int inet6_create(struct socket *sock, int protocol)
 			if (IPPROTO_IP == answer->protocol)
 				break;
 		}
+		err = -EPROTONOSUPPORT;
 		answer = NULL;
 	}
 
-	rc = -ESOCKTNOSUPPORT;
-	if (!answer)
-		goto out_rcu_unlock;
-	rc = -EPERM;
+	if (!answer) {
+		if (try_loading_module < 2) {
+			rcu_read_unlock();
+			/*
+			 * Be more specific, e.g. net-pf-10-proto-132-type-1
+			 * (net-pf-PF_INET6-proto-IPPROTO_SCTP-type-SOCK_STREAM)
+			 */
+			if (++try_loading_module == 1)
+				request_module("net-pf-%d-proto-%d-type-%d",
+						PF_INET6, protocol, sock->type);
+			/*
+			 * Fall back to generic, e.g. net-pf-10-proto-132
+			 * (net-pf-PF_INET6-proto-IPPROTO_SCTP)
+			 */
+			else
+				request_module("net-pf-%d-proto-%d",
+						PF_INET6, protocol);
+			goto lookup_protocol;
+		} else
+			goto out_rcu_unlock;
+	}
+
+	err = -EPERM;
 	if (answer->capability > 0 && !capable(answer->capability))
 		goto out_rcu_unlock;
-	rc = -EPROTONOSUPPORT;
-	if (!protocol)
-		goto out_rcu_unlock;
 
 	sock->ops = answer->ops;
-
 	answer_prot = answer->prot;
 	answer_no_check = answer->no_check;
 	answer_flags = answer->flags;
@@ -135,14 +154,14 @@ static int inet6_create(struct socket *sock, int protocol)
 
 	BUG_TRAP(answer_prot->slab != NULL);
 
-	rc = -ENOBUFS;
+	err = -ENOBUFS;
 	sk = sk_alloc(PF_INET6, GFP_KERNEL, answer_prot, 1);
 	if (sk == NULL)
 		goto out;
 
 	sock_init_data(sock, sk);
 
-	rc = 0;
+	err = 0;
 	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = 1;
@@ -202,14 +221,14 @@ static int inet6_create(struct socket *sock, int protocol)
 		sk->sk_prot->hash(sk);
 	}
 	if (sk->sk_prot->init) {
-		rc = sk->sk_prot->init(sk);
-		if (rc) {
+		err = sk->sk_prot->init(sk);
+		if (err) {
 			sk_common_release(sk);
 			goto out;
 		}
 	}
 out:
-	return rc;
+	return err;
 out_rcu_unlock:
 	rcu_read_unlock();
 	goto out;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index f15e04a..fd939da 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1231,6 +1231,11 @@ int igmp6_event_report(struct sk_buff *skb)
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		return 0;
 
+	/* send our report if the MC router may not have heard this report */
+	if (skb->pkt_type != PACKET_MULTICAST &&
+	    skb->pkt_type != PACKET_BROADCAST)
+		return 0;
+
 	if (!pskb_may_pull(skb, sizeof(struct in6_addr)))
 		return -EINVAL;
 
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 5a6fcf3..6035633 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -280,9 +280,9 @@ static enum tcp_conntrack tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sCL -> sCL
  */
 /* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*ack*/	   { sIV, sIV, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
+/*ack*/	   { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
 /*
- *	sSS -> sIV	Might be a half-open connection.
+ *	sSS -> sIG	Might be a half-open connection.
  *	sSR -> sSR	Might answer late resent SYN.
  *	sES -> sES	:-)
  *	sFW -> sCW	Normal close request answered by ACK.
@@ -912,8 +912,12 @@ static int tcp_packet(struct nf_conn *conntrack,
 
 	switch (new_state) {
 	case TCP_CONNTRACK_IGNORE:
-		/* Either SYN in ORIGINAL
-		 * or SYN/ACK in REPLY. */
+		/* Ignored packets:
+		 *
+		 * a) SYN in ORIGINAL
+		 * b) SYN/ACK in REPLY
+		 * c) ACK in reply direction after initial SYN in original. 
+		 */
 		if (index == TCP_SYNACK_SET
 		    && conntrack->proto.tcp.last_index == TCP_SYN_SET
 		    && conntrack->proto.tcp.last_dir != dir
@@ -979,13 +983,20 @@ static int tcp_packet(struct nf_conn *conntrack,
 		}
 	case TCP_CONNTRACK_CLOSE:
 		if (index == TCP_RST_SET
-		    && test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)
-		    && conntrack->proto.tcp.last_index == TCP_SYN_SET
+		    && ((test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)
+		         && conntrack->proto.tcp.last_index == TCP_SYN_SET)
+		        || (!test_bit(IPS_ASSURED_BIT, &conntrack->status)
+		            && conntrack->proto.tcp.last_index == TCP_ACK_SET))
 		    && ntohl(th->ack_seq) == conntrack->proto.tcp.last_end) {
-			/* RST sent to invalid SYN we had let trough
-			 * SYN was in window then, tear down connection.
+			/* RST sent to invalid SYN or ACK we had let trough
+			 * at a) and c) above:
+			 *
+			 * a) SYN was in window then
+			 * c) we hold a half-open connection.
+			 *
+			 * Delete our connection entry.
 			 * We skip window checking, because packet might ACK
-			 * segments we ignored in the SYN. */
+			 * segments we ignored. */
 			goto in_window;
 		}
 		/* Just fall trough */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index abab81f..d890dfa 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4743,11 +4743,6 @@ static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 	struct sk_buff *skb;
 	long timeo;
 
-	/* Caller is allowed not to check sk->sk_err before calling.  */
-	error = sock_error(sk);
-	if (error)
-		goto no_packet;
-
 	timeo = sock_rcvtimeo(sk, noblock);
 
 	SCTP_DEBUG_PRINTK("Timeout: timeo: %ld, MAX: %ld.\n",
@@ -4774,6 +4769,11 @@ static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (skb)
 			return skb;
 
+		/* Caller is allowed not to check sk->sk_err before calling. */
+		error = sock_error(sk);
+		if (error)
+			goto no_packet;
+
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			break;
 
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 6bc2720..268ddaf 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -261,7 +261,8 @@ void sctp_transport_route(struct sctp_transport *transport,
 		 * association's active path for getsockname().
 		 */ 
 		if (asoc && (transport == asoc->peer.active_path))
-			af->to_sk_saddr(&transport->saddr, asoc->base.sk);
+			opt->pf->af->to_sk_saddr(&transport->saddr,
+						 asoc->base.sk);
 	} else
 		transport->pmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index e3b242d..c76ea22 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -59,7 +59,6 @@ __rpc_purge_upcall(struct inode *inode, int err)
 	struct rpc_inode *rpci = RPC_I(inode);
 
 	__rpc_purge_list(rpci, &rpci->pipe, err);
-	__rpc_purge_list(rpci, &rpci->in_upcall, err);
 	rpci->pipelen = 0;
 	wake_up(&rpci->waitq);
 }
@@ -119,6 +118,7 @@ rpc_close_pipes(struct inode *inode)
 	down(&inode->i_sem);
 	if (rpci->ops != NULL) {
 		rpci->nreaders = 0;
+		__rpc_purge_list(rpci, &rpci->in_upcall, -EPIPE);
 		__rpc_purge_upcall(inode, -EPIPE);
 		rpci->nwriters = 0;
 		if (rpci->ops->release_pipe)