Merge branch 'disable-neigh-update-for-tunnels-during-pmtu-update'

Hangbin Liu says:

====================
disable neigh update for tunnels during pmtu update

When we setup a pair of gretap, ping each other and create neighbour cache.
Then delete and recreate one side. We will never be able to ping6 to the new
created gretap.

The reason is when we ping6 remote via gretap, we will call like

gre_tap_xmit()
 - ip_tunnel_xmit()
   - tnl_update_pmtu()
     - skb_dst_update_pmtu()
       - ip6_rt_update_pmtu()
         - __ip6_rt_update_pmtu()
           - dst_confirm_neigh()
             - ip6_confirm_neigh()
               - __ipv6_confirm_neigh()
                 - n->confirmed = now

As the confirmed time updated, in neigh_timer_handler() the check for
NUD_DELAY confirm time will pass and the neigh state will back to
NUD_REACHABLE. So the old/wrong mac address will be used again.

If we do not update the confirmed time, the neigh state will go to
neigh->nud_state = NUD_PROBE; then go to NUD_FAILED and re-create the
neigh later, which is what IPv4 does.

We couldn't remove the ip6_confirm_neigh() directly as we still need it
for TCP flows. To fix it, we have to pass a bool parameter to
dst_ops.update_pmtu() and only disable neighbor update for tunnels.

v5: No code change, upate some commits description
v4: No code change, upate some commits description
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

19 files changed, 58 insertions, 32 deletions

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index e5b7d6d2286e..fca471e27f39 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -540,7 +540,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {
diff --git a/include/net/dst.h b/include/net/dst.h
index 8224dad2ae94..3448cf865ede 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -516,7 +516,16 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
 	struct dst_entry *dst = skb_dst(skb);
 
 	if (dst && dst->ops->update_pmtu)
-		dst->ops->update_pmtu(dst, NULL, skb, mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
+}
+
+/* update dst pmtu but not do neighbor confirm */
+static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	if (dst && dst->ops->update_pmtu)
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
 }
 
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
@@ -526,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
 	u32 encap_mtu = dst_mtu(encap_dst);
 
 	if (skb->len > encap_mtu - headroom)
-		skb_dst_update_pmtu(skb, encap_mtu - headroom);
+		skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
 }
 
 #endif /* _NET_DST_H */
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 5ec645f27ee3..443863c7b8da 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -27,7 +27,8 @@ struct dst_ops {
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
-					       struct sk_buff *skb, u32 mtu);
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
 	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
 					    struct sk_buff *skb);
 	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
index 2cdfc5d6c25d..8c69f0c95a8e 100644
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -22,7 +22,8 @@
 #endif
 
 static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			     struct sk_buff *skb, u32 mtu)
+			     struct sk_buff *skb, u32 mtu,
+			     bool confirm_neigh)
 {
 }
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index aea918135ec3..08c3dc45f1a4 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb , u32 mtu);
+			       struct sk_buff *skb , u32 mtu,
+			       bool confirm_neigh);
 static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
 			    struct sk_buff *skb);
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,
@@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops)
  * advertise to the other end).
  */
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
 	struct dn_route *rt = (struct dn_route *) dst;
 	struct neighbour *n = rt->n;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e4c6e8b40490..18c0d5bffe12 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
 		if (!dst)
 			goto out;
 	}
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = __sk_dst_check(sk, 0);
 	if (!dst)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 38c02bb62e2c..0fe2a5d3e258 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
 	if (skb_valid_dst(skb))
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9b153c7fcbb4..e90b600c7a25 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f88c93c38f11..87e979f2b74a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -139,7 +139,8 @@ static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
 static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static void		ipv4_dst_destroy(struct dst_entry *dst);
@@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct rtable *rt = (struct rtable *) dst;
 	struct flowi4 fl4;
@@ -2687,7 +2689,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					  struct sk_buff *skb, u32 mtu)
+					  struct sk_buff *skb, u32 mtu,
+					  bool confirm_neigh)
 {
 }
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 35b84b52b702..9ebd54752e03 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 }
 
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index fe9cb8d1adca..e315526fa244 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
 
 	if (IS_ERR(dst))
 		return NULL;
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = inet6_csk_route_socket(sk, &fl6);
 	return IS_ERR(dst) ? NULL : dst;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 9d0965252ddf..ee968d980746 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 754a484d35df..2f376dbc37d5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst_update_pmtu(skb2, rel_info);
+		skb_dst_update_pmtu_no_confirm(skb2, rel_info);
 	}
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
@@ -1132,7 +1132,7 @@ route_lookup:
 	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
 		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
-	skb_dst_update_pmtu(skb, mtu);
+	skb_dst_update_pmtu_no_confirm(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 024db17386d2..6f08b760c2a7 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b59940416cb5..affb51c11a25 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -95,7 +95,8 @@ static int		ip6_pkt_prohibit(struct sk_buff *skb);
 static int		ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
@@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
 }
 
 static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					 struct sk_buff *skb, u32 mtu)
+					 struct sk_buff *skb, u32 mtu,
+					 bool confirm_neigh)
 {
 }
 
@@ -2692,7 +2694,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
-				 const struct ipv6hdr *iph, u32 mtu)
+				 const struct ipv6hdr *iph, u32 mtu,
+				 bool confirm_neigh)
 {
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
@@ -2710,7 +2713,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 		daddr = NULL;
 		saddr = NULL;
 	}
-	dst_confirm_neigh(dst, daddr);
+
+	if (confirm_neigh)
+		dst_confirm_neigh(dst, daddr);
+
 	mtu = max_t(u32, mtu, IPV6_MIN_MTU);
 	if (mtu >= dst_mtu(dst))
 		return;
@@ -2764,9 +2770,11 @@ out_unlock:
 }
 
 static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
-	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu,
+			     confirm_neigh);
 }
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
@@ -2785,7 +2793,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
+		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_update_pmtu);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b2ccbc473127..98954830c40b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		}
 
 		if (tunnel->parms.iph.daddr)
-			skb_dst_update_pmtu(skb, mtu);
+			skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 699e0730ce8e..af7a4b8b1e9c 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 }
 
 static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b1e300f8881b..b00866d777fe 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
 	struct rtable *ort = skb_rtable(skb);
 
 	if (!skb->dev && sk && sk_fullsock(sk))
-		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true);
 }
 
 static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 7235a6032671..3bbe1a58ec87 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 
 		pf->af->from_sk(&addr, sk);
 		pf->to_sk_daddr(&t->ipaddr, sk);
-		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu, true);
 		pf->to_sk_daddr(&addr, sk);
 
 		dst = sctp_transport_dst_check(t);