ipv6: make ECMP route replacement less greedy

[firefly-linux-kernel-4.4.55.git] / net / ipv6 / route.c

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c8bc9b4ac32835e7328025a8912f3627b365e38a..36bf4c3fe4f5deb1bb43c9c8f9c8797c27971b2e 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -404,6 +404,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
        }
 }
 
+static bool __rt6_check_expired(const struct rt6_info *rt)
+{
+       if (rt->rt6i_flags & RTF_EXPIRES)
+               return time_after(jiffies, rt->dst.expires);
+       else
+               return false;
+}
+
 static bool rt6_check_expired(const struct rt6_info *rt)
 {
        if (rt->rt6i_flags & RTF_EXPIRES) {
@@ -515,7 +523,7 @@ static void rt6_probe_deferred(struct work_struct *w)
                container_of(w, struct __rt6_probe_work, work);
 
        addrconf_addr_solict_mult(&work->target, &mcaddr);
-       ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL);
+       ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL);
        dev_put(work->dev);
        kfree(work);
 }
@@ -1166,11 +1174,10 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
        return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
-                                   struct flowi6 *fl6)
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+                                        struct flowi6 *fl6, int flags)
 {
        struct dst_entry *dst;
-       int flags = 0;
        bool any_src;
 
        dst = l3mdev_rt6_dst_by_oif(net, fl6);
@@ -1191,7 +1198,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 
        return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
 }
-EXPORT_SYMBOL(ip6_route_output);
+EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
@@ -1252,7 +1259,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 
 static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
 {
-       if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+       if (!__rt6_check_expired(rt) &&
+           rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
            rt6_check((struct rt6_info *)(rt->dst.from), cookie))
                return &rt->dst;
        else
@@ -1272,7 +1280,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
        rt6_dst_from_metrics_check(rt);
 
-       if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+       if (rt->rt6i_flags & RTF_PCPU ||
+           (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from))
                return rt6_dst_from_check(rt, cookie);
        else
                return rt6_check(rt, cookie);
@@ -1322,6 +1331,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
        rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
 }
 
+static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
+{
+       return !(rt->rt6i_flags & RTF_CACHE) &&
+               (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+}
+
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
                                 const struct ipv6hdr *iph, u32 mtu)
 {
@@ -1335,7 +1350,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
        if (mtu >= dst_mtu(dst))
                return;
 
-       if (rt6->rt6i_flags & RTF_CACHE) {
+       if (!rt6_cache_allowed_for_pmtu(rt6)) {
                rt6_do_update_pmtu(rt6, mtu);
        } else {
                const struct in6_addr *daddr, *saddr;
@@ -1712,6 +1727,8 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
                } else {
                        val = nla_get_u32(nla);
                }
+               if (type == RTAX_HOPLIMIT && val > 255)
+                       val = 255;
                if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
                        goto err;
 
@@ -3123,7 +3140,9 @@ static int rt6_fill_node(struct net *net,
        if (iif) {
 #ifdef CONFIG_IPV6_MROUTE
                if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
-                       int err = ip6mr_get_route(net, skb, rtm, nowait);
+                       int err = ip6mr_get_route(net, skb, rtm, nowait,
+                                                 portid);
+
                        if (err <= 0) {
                                if (!nowait) {
                                        if (err == 0)
@@ -3177,7 +3196,8 @@ static int rt6_fill_node(struct net *net,
        if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
                goto nla_put_failure;
 
-       lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+       if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+               goto nla_put_failure;
 
        nlmsg_end(skb, nlh);
        return 0;