4 files changed, 53 insertions, 5 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index b183e2b606c8..6c7f365b1515 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -63,6 +63,16 @@ fwmark_reflect - BOOLEAN
         fwmark of the packet they are replying to.
         Default: 0
 
+fib_multipath_use_neigh - BOOLEAN
+        Use status of existing neighbor entry when determining nexthop for
+        multipath routes. If disabled, neighbor information is not used and
+        packets could be directed to a failed nexthop. Only valid for kernels
+        built with CONFIG_IP_ROUTE_MULTIPATH enabled.
+        Default: 0 (disabled)
+        Possible values:
+        0 - disabled
+        1 - enabled
+
 route/max_size - INTEGER
         Maximum number of routes allowed in the kernel.  Increase
         this when using large numbers of interfaces and/or routes.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index a69cde3ce460..d061ffeb1e71 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -133,6 +133,9 @@ struct netns_ipv4 {
         struct fib_rules_ops    *mr_rules_ops;
 #endif
 #endif
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+        int sysctl_fib_multipath_use_neigh;
+#endif
         atomic_t        rt_genid;
 };
 #endif
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d97268e8ff10..ab64d9f2eef9 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1559,21 +1559,45 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
+static bool fib_good_nh(const struct fib_nh *nh)
+{
+        int state = NUD_REACHABLE;
+
+        if (nh->nh_scope == RT_SCOPE_LINK) {
+                struct neighbour *n;
+
+                rcu_read_lock_bh();
+
+                n = __ipv4_neigh_lookup_noref(nh->nh_dev, nh->nh_gw);
+                if (n)
+                        state = n->nud_state;
+
+                rcu_read_unlock_bh();
+        }
+
+        return !!(state & NUD_VALID);
+}
 
 void fib_select_multipath(struct fib_result *res, int hash)
 {
         struct fib_info *fi = res->fi;
+        struct net *net = fi->fib_net;
+        bool first = false;
 
         for_nexthops(fi) {
                 if (hash > atomic_read(&nh->nh_upper_bound))
                         continue;
 
-                res->nh_sel = nhsel;
-                return;
+                if (!net->ipv4.sysctl_fib_multipath_use_neigh ||
+                    fib_good_nh(nh)) {
+                        res->nh_sel = nhsel;
+                        return;
+                }
+                if (!first) {
+                        res->nh_sel = nhsel;
+                        first = true;
+                }
         } endfor_nexthops(fi);
-
-        /* Race condition: route has just become dead. */
-        res->nh_sel = 0;
 }
 #endif
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1e1fe6086dd9..bb0419582b8d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -960,6 +960,17 @@ static struct ctl_table ipv4_net_table[] = {
                 .mode           = 0644,
                 .proc_handler   = proc_dointvec,
         },
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+        {
+                .procname       = "fib_multipath_use_neigh",
+                .data           = &init_net.ipv4.sysctl_fib_multipath_use_neigh,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec_minmax,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+#endif
         { }
 };