net: add bool confirm_neigh parameter for dst_ops.update_pmtu

The MTU update code is supposed to be invoked in response to real
networking events that update the PMTU. In IPv6 PMTU update function
__ip6_rt_update_pmtu() we called dst_confirm_neigh() to update neighbor
confirmed time.

But for tunnel code, it will call pmtu before xmit, like:
  - tnl_update_pmtu()
    - skb_dst_update_pmtu()
      - ip6_rt_update_pmtu()
        - __ip6_rt_update_pmtu()
          - dst_confirm_neigh()

If the tunnel remote dst mac address changed and we still do the neigh
confirm, we will not be able to update neigh cache and ping6 remote
will failed.

So for this ip_tunnel_xmit() case, _EVEN_ if the MTU is changed, we
should not be invoking dst_confirm_neigh() as we have no evidence
of successful two-way communication at this point.

On the other hand it is also important to keep the neigh reachability fresh
for TCP flows, so we cannot remove this dst_confirm_neigh() call.

To fix the issue, we have to add a new bool parameter for dst_ops.update_pmtu
to choose whether we should do neigh update or not. I will add the parameter
in this patch and set all the callers to true to comply with the previous
way, and fix the tunnel code one by one on later patches.

v5: No change.
v4: No change.
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.

Suggested-by: David Miller <davem@davemloft.net>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 38 insertions, 22 deletions

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/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..3ba69174ad6c 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, true);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);
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/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);