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

Pull networking fixes from David Miller:

 1) Use an appropriate TSQ pacing shift in mac80211, from Toke
    Høiland-Jørgensen.

 2) Just like ipv4's ip_route_me_harder(), we have to use skb_to_full_sk
    in ip6_route_me_harder, from Eric Dumazet.

 3) Fix several shutdown races and similar other problems in l2tp, from
    James Chapman.

 4) Handle missing XDP flush properly in tuntap, for real this time.
    From Jason Wang.

 5) Out-of-bounds access in powerpc ebpf tailcalls, from Daniel
    Borkmann.

 6) Fix phy_resume() locking, from Andrew Lunn.

 7) IFLA_MTU values are ignored on newlink for some tunnel types, fix
    from Xin Long.

 8) Revert F-RTO middle box workarounds, they only handle one dimension
    of the problem. From Yuchung Cheng.

 9) Fix socket refcounting in RDS, from Ka-Cheong Poon.

10) Don't allow ppp unit registration to an unregistered channel, from
    Guillaume Nault.

11) Various hv_netvsc fixes from Stephen Hemminger.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (98 commits)
  hv_netvsc: propagate rx filters to VF
  hv_netvsc: filter multicast/broadcast
  hv_netvsc: defer queue selection to VF
  hv_netvsc: use napi_schedule_irqoff
  hv_netvsc: fix race in napi poll when rescheduling
  hv_netvsc: cancel subchannel setup before halting device
  hv_netvsc: fix error unwind handling if vmbus_open fails
  hv_netvsc: only wake transmit queue if link is up
  hv_netvsc: avoid retry on send during shutdown
  virtio-net: re enable XDP_REDIRECT for mergeable buffer
  ppp: prevent unregistered channels from connecting to PPP units
  tc-testing: skbmod: fix match value of ethertype
  mlxsw: spectrum_switchdev: Check success of FDB add operation
  net: make skb_gso_*_seglen functions private
  net: xfrm: use skb_gso_validate_network_len() to check gso sizes
  net: sched: tbf: handle GSO_BY_FRAGS case in enqueue
  net: rename skb_gso_validate_mtu -> skb_gso_validate_network_len
  rds: Incorrect reference counting in TCP socket creation
  net: ethtool: don't ignore return from driver get_fecparam method
  vrf: check forwarding on the original netdevice when generating ICMP dest unreachable
  ...

9 files changed, 29 insertions, 25 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 997c7f19ad62..a8a919520090 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->ignore_df)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
 		return false;
 
 	return true;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4b15fe928278..6e0f21eed88a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1982,14 +1982,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct net *net = dev_net(dev);
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
-	struct ip6_tnl *nt, *t;
 	struct ip_tunnel_encap ipencap;
+	struct ip6_tnl *nt, *t;
+	int err;
 
 	nt = netdev_priv(dev);
 
 	if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
-		int err = ip6_tnl_encap_setup(nt, &ipencap);
-
+		err = ip6_tnl_encap_setup(nt, &ipencap);
 		if (err < 0)
 			return err;
 	}
@@ -2005,7 +2005,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 			return -EEXIST;
 	}
 
-	return ip6_tnl_create2(dev);
+	err = ip6_tnl_create2(dev);
+	if (!err && tb[IFLA_MTU])
+		ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
+
+	return err;
 }
 
 static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d95ceca7ff8f..531d6957af36 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -21,18 +21,19 @@
 int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct sock *sk = sk_to_full_sk(skb->sk);
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	struct flowi6 fl6 = {
-		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
+		.flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
 		.flowi6_mark = skb->mark,
-		.flowi6_uid = sock_net_uid(net, skb->sk),
+		.flowi6_uid = sock_net_uid(net, sk),
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
 	int err;
 
-	dst = ip6_route_output(net, skb->sk, &fl6);
+	dst = ip6_route_output(net, sk, &fl6);
 	err = dst->error;
 	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
@@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 	if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
 	    xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
 		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 		skb_dst_set(skb, dst);
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 94deb69bbbda..91ed25a24b79 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 	}
 
 	fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
-	if ((flags & XT_RPFILTER_LOOSE) == 0) {
-		fl6.flowi6_oif = dev->ifindex;
-		lookup_flags |= RT6_LOOKUP_F_IFACE;
-	}
 
 	rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags);
 	if (rt->dst.error)
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index d346705d6ee6..207cb35569b1 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->len <= mtu)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
 		return false;
 
 	return true;
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index bed57ee65f7b..6b7f075f811f 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
 	    !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
 				target, maniptype))
 		return false;
+
+	/* must reload, offset might have changed */
+	ipv6h = (void *)skb->data + iphdroff;
+
 manip_addr:
 	if (maniptype == NF_NAT_MANIP_SRC)
 		ipv6h->saddr = target->src.u3.in6;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index cc5174c7254c..62fc84d7bdff 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	}
 
 	*dest = 0;
- again:
 	rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags);
 	if (rt->dst.error)
 		goto put_rt_err;
@@ -189,15 +188,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
 		goto put_rt_err;
 
-	if (oif && oif != rt->rt6i_idev->dev) {
-		/* multipath route? Try again with F_IFACE */
-		if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) {
-			lookup_flags |= RT6_LOOKUP_F_IFACE;
-			fl6.flowi6_oif = oif->ifindex;
-			ip6_rt_put(rt);
-			goto again;
-		}
-	}
+	if (oif && oif != rt->rt6i_idev->dev)
+		goto put_rt_err;
 
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3a1775a62973..0195598f7bb5 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
+	if (tb[IFLA_MTU]) {
+		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+
+		if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len)
+			dev->mtu = mtu;
+	}
+
 #ifdef CONFIG_IPV6_SIT_6RD
 	if (ipip6_netlink_6rd_parms(data, &ip6rd))
 		err = ipip6_tunnel_update_6rd(nt, &ip6rd);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 8ae87d4ec5ff..5959ce9620eb 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 
 	if ((!skb_is_gso(skb) && skb->len > mtu) ||
 	    (skb_is_gso(skb) &&
-	     skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) {
+	     !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) {
 		skb->dev = dst->dev;
 		skb->protocol = htons(ETH_P_IPV6);