ipv6: Fix route replacement with dev-only route

[ Upstream commit e404b8c7cfb31654c9024d497cec58a501501692 ]

After commit 27596472473a ("ipv6: fix ECMP route replacement") it is no
longer possible to replace an ECMP-able route by a non ECMP-able route.
For example,
	ip route add 2001:db8::1/128 via fe80::1 dev dummy0
	ip route replace 2001:db8::1/128 dev dummy0
does not work as expected.

Tweak the replacement logic so that point 3 in the log of the above commit
becomes:
3. If the new route is not ECMP-able, and no matching non-ECMP-able route
exists, replace matching ECMP-able route (if any) or add the new route.

We can now summarize the entire replace semantics to:
When doing a replace, prefer replacing a matching route of the same
"ECMP-able-ness" as the replace argument. If there is no such candidate,
fallback to the first route found.

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7091568..5e8979c 100644 (file)
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -981,8 +981,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
                                        found++;
                                        break;
                                }
-                               if (rt_can_ecmp)
-                                       fallback_ins = fallback_ins ?: ins;
+                               fallback_ins = fallback_ins ?: ins;
                                goto next_iter;
                        }
 
@@ -1025,7 +1024,9 @@ next_iter:
        }
 
        if (fallback_ins && !found) {
-               /* No ECMP-able route found, replace first non-ECMP one */
+               /* No matching route with same ecmp-able-ness found, replace
+                * first matching route
+                */
                ins = fallback_ins;
                iter = rcu_dereference_protected(*ins,
                                    lockdep_is_held(&rt->fib6_table->tb6_lock));

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index c0885fb..7d1a7c0 100755 (executable)
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -848,6 +848,12 @@ ipv6_rt_replace_mpath()
        check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
        log_test $? 0 "Multipath with single path via multipath attribute"
 
+       # multipath with dev-only
+       add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+       run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+       check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+       log_test $? 0 "Multipath with dev-only"
+
        # route replace fails - invalid nexthop 1
        add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
        run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"