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

Pull networking fixes from David Miller:

 1) Fix RCU locking in xfrm_local_error(), from Taehee Yoo.

 2) Fix return value assignments and thus error checking in
    iwl_mvm_start_ap_ibss(), from Johannes Berg.

 3) Don't count header length twice in vti4, from Stefano Brivio.

 4) Fix deadlock in rt6_age_examine_exception, from Eric Dumazet.

 5) Fix out-of-bounds access in nf_sk_lookup_slow{v4,v6}() from Subash
    Abhinov.

 6) Check nladdr size in netlink_connect(), from Alexander Potapenko.

 7) VF representor SQ numbers are 32 not 16 bits, in mlx5 driver, from
    Or Gerlitz.

 8) Out of bounds read in skb_network_protocol(), from Eric Dumazet.

 9) r8169 driver sets driver data pointer after register_netdev() which
    is too late. Fix from Heiner Kallweit.

10) Fix memory leak in mlx4 driver, from Moshe Shemesh.

11) The multi-VLAN decap fix added a regression when dealing with device
    that lack a MAC header, such as tun. Fix from Toshiaki Makita.

12) Fix integer overflow in dynamic interrupt coalescing code. From Tal
    Gilboa.

13) Use after free in vrf code, from David Ahern.

14) IPV6 route leak between VRFs fix, also from David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (81 commits)
  net: mvneta: fix enable of all initialized RXQs
  net/ipv6: Fix route leaking between VRFs
  vrf: Fix use after free and double free in vrf_finish_output
  ipv6: sr: fix seg6 encap performances with TSO enabled
  net/dim: Fix int overflow
  vlan: Fix vlan insertion for packets without ethernet header
  net: Fix untag for vlan packets without ethernet header
  atm: iphase: fix spelling mistake: "Receiverd" -> "Received"
  vhost: validate log when IOTLB is enabled
  qede: Do not drop rx-checksum invalidated packets.
  hv_netvsc: enable multicast if necessary
  ip_tunnel: Resolve ipsec merge conflict properly.
  lan78xx: Crash in lan78xx_writ_reg (Workqueue: events lan78xx_deferred_multicast_write)
  qede: Fix barrier usage after tx doorbell write.
  vhost: correctly remove wait queue during poll failure
  net/mlx4_core: Fix memory leak while delete slave's resources
  net/mlx4_en: Fix mixed PFC and Global pause user control requests
  net/smc: use announced length in sock_recvmsg()
  llc: properly handle dev_queue_xmit() return value
  strparser: Fix sign of err codes
  ...

6 files changed, 48 insertions, 10 deletions

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6d21068f9b55..a7fd1c5a2a14 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -362,13 +362,18 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	struct ip_tunnel *nt;
 	struct net_device *dev;
 	int t_hlen;
+	int mtu;
+	int err;
 
 	BUG_ON(!itn->fb_tunnel_dev);
 	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
 		return ERR_CAST(dev);
 
-	dev->mtu = ip_tunnel_bind_dev(dev);
+	mtu = ip_tunnel_bind_dev(dev);
+	err = dev_set_mtu(dev, mtu);
+	if (err)
+		goto err_dev_set_mtu;
 
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
@@ -376,6 +381,10 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
+
+err_dev_set_mtu:
+	unregister_netdevice(dev);
+	return ERR_PTR(err);
 }
 
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
@@ -1102,17 +1111,29 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 	nt->fwmark = fwmark;
 	err = register_netdevice(dev);
 	if (err)
-		goto out;
+		goto err_register_netdevice;
 
 	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
 		eth_hw_addr_random(dev);
 
 	mtu = ip_tunnel_bind_dev(dev);
-	if (!tb[IFLA_MTU])
-		dev->mtu = mtu;
+	if (tb[IFLA_MTU]) {
+		unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen;
+
+		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
+			    (unsigned int)(max - sizeof(struct iphdr)));
+	}
+
+	err = dev_set_mtu(dev, mtu);
+	if (err)
+		goto err_dev_set_mtu;
 
 	ip_tunnel_add(itn, nt);
-out:
+	return 0;
+
+err_dev_set_mtu:
+	unregister_netdevice(dev);
+err_register_netdevice:
 	return err;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 51b1669334fe..3f091ccad9af 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -387,8 +387,6 @@ static int vti_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
-	dev->mtu		= ETH_DATA_LEN;
 	dev->flags		= IFF_NOARP;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index b50721d9d30e..9db988f9a4d7 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -154,8 +154,20 @@ static unsigned int ipv4_conntrack_local(void *priv,
 					 struct sk_buff *skb,
 					 const struct nf_hook_state *state)
 {
-	if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+	if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
+		enum ip_conntrack_info ctinfo;
+		struct nf_conn *tmpl;
+
+		tmpl = nf_ct_get(skb, &ctinfo);
+		if (tmpl && nf_ct_is_template(tmpl)) {
+			/* when skipping ct, clear templates to avoid fooling
+			 * later targets/matches
+			 */
+			skb->_nfct = 0;
+			nf_ct_put(tmpl);
+		}
 		return NF_ACCEPT;
+	}
 
 	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
 }
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index e9293bdebba0..4824b1e183a1 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -108,10 +108,12 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
 	int doff = 0;
 
 	if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
-		struct udphdr _hdr, *hp;
+		struct tcphdr _hdr;
+		struct udphdr *hp;
 
 		hp = skb_header_pointer(skb, ip_hdrlen(skb),
-					sizeof(_hdr), &_hdr);
+					iph->protocol == IPPROTO_UDP ?
+					sizeof(*hp) : sizeof(_hdr), &_hdr);
 		if (hp == NULL)
 			return NULL;
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index fda37f2862c9..c3387dfd725b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -349,6 +349,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 	treq->snt_synack	= 0;
 	treq->tfo_listener	= false;
+	if (IS_ENABLED(CONFIG_SMC))
+		ireq->smc_ok = 0;
 
 	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9a1b3c1c1c14..ff6cd98ce8d5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6256,6 +6256,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (want_cookie && !tmp_opt.saw_tstamp)
 		tcp_clear_options(&tmp_opt);
 
+	if (IS_ENABLED(CONFIG_SMC) && want_cookie)
+		tmp_opt.smc_ok = 0;
+
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
 	inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent;