ipv6: introduce ip6_dst_mtu_forward and protect forwarding path with it

[~andy/linux] / net / ipv6 / ip6_output.c

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e6f931997996ef46efa1272b16e261bf8f6609a7..ef02b26ccf812e57e794e9b151746600bcb9a8f0 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -321,6 +321,27 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
        return dst_output(skb);
 }
 
+static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+       unsigned int mtu;
+       struct inet6_dev *idev;
+
+       if (dst_metric_locked(dst, RTAX_MTU)) {
+               mtu = dst_metric_raw(dst, RTAX_MTU);
+               if (mtu)
+                       return mtu;
+       }
+
+       mtu = IPV6_MIN_MTU;
+       rcu_read_lock();
+       idev = __in6_dev_get(dst->dev);
+       if (idev)
+               mtu = idev->cnf.mtu6;
+       rcu_read_unlock();
+
+       return mtu;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
        struct dst_entry *dst = skb_dst(skb);
@@ -336,7 +357,8 @@ int ip6_forward(struct sk_buff *skb)
                goto drop;
 
        if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
-               IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+               IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                IPSTATS_MIB_INDISCARDS);
                goto drop;
        }
 
@@ -370,8 +392,8 @@ int ip6_forward(struct sk_buff *skb)
                /* Force OUTPUT device used as source address */
                skb->dev = dst->dev;
                icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
-               IP6_INC_STATS_BH(net,
-                                ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
+               IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                IPSTATS_MIB_INHDRERRORS);
 
                kfree_skb(skb);
                return -ETIMEDOUT;
@@ -384,14 +406,15 @@ int ip6_forward(struct sk_buff *skb)
                if (proxied > 0)
                        return ip6_input(skb);
                else if (proxied < 0) {
-                       IP6_INC_STATS(net, ip6_dst_idev(dst),
-                                     IPSTATS_MIB_INDISCARDS);
+                       IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                        IPSTATS_MIB_INDISCARDS);
                        goto drop;
                }
        }
 
        if (!xfrm6_route_forward(skb)) {
-               IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
+               IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                IPSTATS_MIB_INDISCARDS);
                goto drop;
        }
        dst = skb_dst(skb);
@@ -439,7 +462,7 @@ int ip6_forward(struct sk_buff *skb)
                }
        }
 
-       mtu = dst_mtu(dst);
+       mtu = ip6_dst_mtu_forward(dst);
        if (mtu < IPV6_MIN_MTU)
                mtu = IPV6_MIN_MTU;
 
@@ -448,16 +471,17 @@ int ip6_forward(struct sk_buff *skb)
                /* Again, force OUTPUT device used as source address */
                skb->dev = dst->dev;
                icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-               IP6_INC_STATS_BH(net,
-                                ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
-               IP6_INC_STATS_BH(net,
-                                ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
+               IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                IPSTATS_MIB_INTOOBIGERRORS);
+               IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                IPSTATS_MIB_FRAGFAILS);
                kfree_skb(skb);
                return -EMSGSIZE;
        }
 
        if (skb_cow(skb, dst->dev->hard_header_len)) {
-               IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+               IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
+                                IPSTATS_MIB_OUTDISCARDS);
                goto drop;
        }
 
@@ -938,7 +962,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *     @sk: socket which provides route info
  *     @fl6: flow to lookup
  *     @final_dst: final destination address for ipsec lookup
- *     @can_sleep: we are in a sleepable context
  *
  *     This function performs a route lookup on the given flow.
  *
@@ -946,8 +969,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *     error code.
  */
 struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
-                                     const struct in6_addr *final_dst,
-                                     bool can_sleep)
+                                     const struct in6_addr *final_dst)
 {
        struct dst_entry *dst = NULL;
        int err;
@@ -957,8 +979,6 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
                return ERR_PTR(err);
        if (final_dst)
                fl6->daddr = *final_dst;
-       if (can_sleep)
-               fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
        return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
@@ -969,7 +989,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *     @sk: socket which provides the dst cache and route info
  *     @fl6: flow to lookup
  *     @final_dst: final destination address for ipsec lookup
- *     @can_sleep: we are in a sleepable context
  *
  *     This function performs a route lookup on the given flow with the
  *     possibility of using the cached route in the socket if it is valid.
@@ -980,8 +999,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *     error code.
  */
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
-                                        const struct in6_addr *final_dst,
-                                        bool can_sleep)
+                                        const struct in6_addr *final_dst)
 {
        struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
        int err;
@@ -993,8 +1011,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
                return ERR_PTR(err);
        if (final_dst)
                fl6->daddr = *final_dst;
-       if (can_sleep)
-               fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
        return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
@@ -1162,10 +1178,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                np->cork.hop_limit = hlimit;
                np->cork.tclass = tclass;
                if (rt->dst.flags & DST_XFRM_TUNNEL)
-                       mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+                       mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
                              rt->dst.dev->mtu : dst_mtu(&rt->dst);
                else
-                       mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+                       mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
                              rt->dst.dev->mtu : dst_mtu(rt->dst.path);
                if (np->frag_size < mtu) {
                        if (np->frag_size)
@@ -1285,7 +1301,7 @@ alloc_new_skb:
                        if (skb == NULL || skb_prev == NULL)
                                ip6_append_data_mtu(&mtu, &maxfraglen,
                                                    fragheaderlen, skb, rt,
-                                                   np->pmtudisc ==
+                                                   np->pmtudisc >=
                                                    IPV6_PMTUDISC_PROBE);
 
                        skb_prev = skb;