net: add bool confirm_neigh parameter for dst_ops.update_pmtu

[ Upstream commit bd085ef678b2cc8c38c105673dfe8ff8f5ec0c57 ]

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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index d178d5bad7e48aa0f8744a213d7660813290f978..9e3963f46458cddd80f037a8792df755085f8960 100644 (file)
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -545,7 +545,7 @@ 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, true);
 
        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 851cf11242401f187d211936d7bf88086551aa38..aac3f5b4c7b5b7db32c2a185d2e3e2c7253ef62c 100644 (file)
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -527,7 +527,7 @@ 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);
 }
 
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 5ec645f27ee3841f9a4074c94e5dca37bb86fc2e..443863c7b8da362476c15fd290ac2a32a8aa86e3 100644 (file)
--- 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 8e2d7cfa4e166a32dac08b6abb968870588294a8..d88e724d5755e3a679f160217f8a78f006e4bd8c 100644 (file)
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -26,7 +26,8 @@
 #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 1c002c0fb712a45e20b4e3daa72da4b6d19e935a..658191fba94ece0ef994dd624ff35a85e0da37ea 100644 (file)
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -118,7 +118,8 @@ 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,
@@ -259,7 +260,8 @@ 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 15e7f7915a21e0fbce09d5d2c17d877eae499e03..636a11c56cf5aa9a0ae5bbd2f73b791d8ca6ce55 100644 (file)
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1089,7 +1089,7 @@ 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 69127f6039b2b3308932d9a742f19c18482947c9..4590af50624467bb7eb4669c707917394d80a312 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -142,7 +142,8 @@ 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);
@@ -1035,7 +1036,8 @@ 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;
@@ -2559,7 +2561,8 @@ 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 2b144b92ae46a430d184fca120616166e8010f53..1e5e2e4be0b27142ad02716e9988a00c8840dbce 100644 (file)
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -222,12 +222,13 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 }
 
 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 9a31d13bf180d1e58a4a4b0a65750f377f963c52..890adadcda16aee20400d7dc394931fde8797c66 100644 (file)
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -150,7 +150,7 @@ 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 8fd28edd6ac570c0a54305484dfedf46a0bb9267..9853fa47641ee39310cfa540f17f4cc42931cc58 100644 (file)
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1060,7 +1060,7 @@ 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 076c21f6a645452cf55715de7dbc345299463a1a..f8fe4c9ead4dacda74c3c3ea88ed032ad1758338 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -99,7 +99,8 @@ 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(struct fib6_info *rt, int oif, int strict);
@@ -266,7 +267,8 @@ 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)
 {
 }
 
@@ -2352,7 +2354,8 @@ 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;
@@ -2370,7 +2373,10 @@ 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;
@@ -2401,9 +2407,11 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 }
 
 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,
@@ -2423,7 +2431,7 @@ 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 d35bcf92969c826b9d331bdd86ad8476dcad66ed..30232591cf2bfebd170c8cdb028408cf61f280b1 100644 (file)
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -221,12 +221,13 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 }
 
 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 473cce2a5231c8f3757e82c8f94eaf81326d9f4b..3f75cd947045e82709f25227cef876e8f103791b 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -209,7 +209,7 @@ 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 ad158d311ffaea073f0c13d76d20f4756ceec879..c0d55ed62d2e30f256ec59b7c83286e19a438d02 100644 (file)
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -278,7 +278,7 @@ 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);