Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

6 files changed, 41 insertions, 31 deletions

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 51fdbb490437..eab2a7fb15d1 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -278,6 +278,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	bool ecn_ok = false;
+	struct flowi4 fl4;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
@@ -346,20 +347,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * hasn't changed since we received the original syn, but I see
 	 * no easy way to do this.
 	 */
-	{
-		struct flowi4 fl4;
-
-		flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
-				   RT_SCOPE_UNIVERSE, IPPROTO_TCP,
-				   inet_sk_flowi_flags(sk),
-				   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
-				   ireq->loc_addr, th->source, th->dest);
-		security_req_classify_flow(req, flowi4_to_flowi(&fl4));
-		rt = ip_route_output_key(sock_net(sk), &fl4);
-		if (IS_ERR(rt)) {
-			reqsk_free(req);
-			goto out;
-		}
+	flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
+			   RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+			   inet_sk_flowi_flags(sk),
+			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
+			   ireq->loc_addr, th->source, th->dest);
+	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+	rt = ip_route_output_key(sock_net(sk), &fl4);
+	if (IS_ERR(rt)) {
+		reqsk_free(req);
+		goto out;
 	}
 
 	/* Try to redo what tcp_v4_send_synack did. */
@@ -373,5 +370,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	ireq->rcv_wscale  = rcv_wscale;
 
 	ret = get_cookie_sock(sk, skb, req, &rt->dst);
+	/* ip_queue_xmit() depends on our flow being setup
+	 * Normal sockets get it right from inet_csk_route_child_sock()
+	 */
+	if (ret)
+		inet_sk(ret)->cork.fl.u.ip4 = fl4;
 out:	return ret;
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fe9f604ed1e2..3a25cf743f8b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1470,9 +1470,13 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = newtp->write_seq ^ jiffies;
 
-	if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
-		goto put_and_exit;
-
+	if (!dst) {
+		dst = inet_csk_route_child_sock(sk, newsk, req);
+		if (!dst)
+			goto put_and_exit;
+	} else {
+		/* syncookie case : see end of cookie_v4_check() */
+	}
 	sk_setup_caps(newsk, dst);
 
 	tcp_mtup_init(newsk);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index b853f06cc148..16c33e308121 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -257,7 +257,6 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
 
 		if (rt) {
 			dev = rt->dst.dev;
-			dev_hold(dev);
 			dst_release(&rt->dst);
 		}
 	} else
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 92be12bb8d23..24c456e8aa1d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1090,7 +1090,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	struct net *net = dev_net(dev);
 
 	if (unlikely(!idev))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
 	if (unlikely(!rt)) {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 2124977ac31d..ca7e8354e4f8 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -967,20 +967,21 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 		}
 	}
 
-	if (nf_conntrack_event_report(IPCT_DESTROY, ct,
-				      NETLINK_CB(skb).pid,
-				      nlmsg_report(nlh)) < 0) {
+	if (del_timer(&ct->timeout)) {
+		if (nf_conntrack_event_report(IPCT_DESTROY, ct,
+					      NETLINK_CB(skb).pid,
+					      nlmsg_report(nlh)) < 0) {
+			nf_ct_delete_from_lists(ct);
+			/* we failed to report the event, try later */
+			nf_ct_insert_dying_list(ct);
+			nf_ct_put(ct);
+			return 0;
+		}
+		/* death_by_timeout would report the event again */
+		set_bit(IPS_DYING_BIT, &ct->status);
 		nf_ct_delete_from_lists(ct);
-		/* we failed to report the event, try later */
-		nf_ct_insert_dying_list(ct);
 		nf_ct_put(ct);
-		return 0;
 	}
-
-	/* death_by_timeout would report the event again */
-	set_bit(IPS_DYING_BIT, &ct->status);
-
-	nf_ct_kill(ct);
 	nf_ct_put(ct);
 
 	return 0;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 60d47180f043..02a21abea65e 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -469,11 +469,15 @@ enqueue:
 	if (slot->qlen == 1) {		/* The flow is new */
 		if (q->tail == NULL) {	/* It is the first flow */
 			slot->next = x;
-			q->tail = slot;
 		} else {
 			slot->next = q->tail->next;
 			q->tail->next = x;
 		}
+		/* We put this flow at the end of our flow list.
+		 * This might sound unfair for a new flow to wait after old ones,
+		 * but we could endup servicing new flows only, and freeze old ones.
+		 */
+		q->tail = slot;
 		/* We could use a bigger initial quantum for new flows */
 		slot->allot = q->scaled_quantum;
 	}