zebra: Allow kernel routes to stick around better on interface state changes

Currently kernel routes on system bring up would be `auto-accepted`,
then if an interface went down all kernel and system routes would
be re-evaluated.  There exists situations where a kernel route can
exist but the interface itself is not exactly in a state that is
ready to create a connected route yet.  As such when any interface
goes down in the system all kernel/system routes would be re-evaluated
and then since that interfaces connected route is not in the table yet
the route is matching against a default route( or not at all ) and
is being dropped.

Modify the code such that kernel or system routes just look for interface
being in a good state (up or operative) and accept it.

Broken code:
eva# show ip route
Codes: K - kernel route, C - connected, S - static, R - RIP,
       O - OSPF, I - IS-IS, B - BGP, E - EIGRP, N - NHRP,
       T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP,
       F - PBR, f - OpenFabric,
       > - selected route, * - FIB route, q - queued, r - rejected, b - backup
       t - trapped, o - offload failure

K>* 0.0.0.0/0 [0/100] via 192.168.119.1, enp39s0, 00:05:08
K>* 1.2.3.5/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.6/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.7/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.8/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.9/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.10/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.11/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.12/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.13/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.14/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.16/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 1.2.3.17/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
C>* 4.5.6.99/32 is directly connected, dummy9, 00:05:08
K>* 4.9.10.11/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:05:08
K>* 10.11.12.13/32 [0/0] via 192.168.119.1, enp39s0, 00:05:08
C>* 192.168.10.0/24 is directly connected, dummy99, 00:05:08
C>* 192.168.119.0/24 is directly connected, enp39s0, 00:05:08
<shutdown a non-related interface>
eva# show ip route
Codes: K - kernel route, C - connected, S - static, R - RIP,
       O - OSPF, I - IS-IS, B - BGP, E - EIGRP, N - NHRP,
       T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP,
       F - PBR, f - OpenFabric,
       > - selected route, * - FIB route, q - queued, r - rejected, b - backup
       t - trapped, o - offload failure

K>* 0.0.0.0/0 [0/100] via 192.168.119.1, enp39s0, 00:05:28
C>* 4.5.6.99/32 is directly connected, dummy9, 00:05:28
K>* 10.11.12.13/32 [0/0] via 192.168.119.1, enp39s0, 00:05:28
C>* 192.168.10.0/24 is directly connected, dummy99, 00:05:28
C>* 192.168.119.0/24 is directly connected, enp39s0, 00:05:28

Working code:
eva# show ip route
Codes: K - kernel route, C - connected, S - static, R - RIP,
       O - OSPF, I - IS-IS, B - BGP, E - EIGRP, N - NHRP,
       T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP,
       F - PBR, f - OpenFabric,
       > - selected route, * - FIB route, q - queued, r - rejected, b - backup
       t - trapped, o - offload failure

K>* 0.0.0.0/0 [0/100] via 192.168.119.1, enp39s0, 00:00:04
K>* 1.2.3.5/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.6/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.7/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.8/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.9/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.10/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.11/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.12/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.13/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.14/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.16/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 1.2.3.17/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
C>* 4.5.6.99/32 is directly connected, dummy9, 00:00:04
K>* 4.9.10.11/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:04
K>* 10.11.12.13/32 [0/0] via 192.168.119.1, enp39s0, 00:00:04
C>* 192.168.10.0/24 is directly connected, dummy99, 00:00:04
C>* 192.168.119.0/24 is directly connected, enp39s0, 00:00:04
<shutdown a non-related interface>
eva# show ip route
Codes: K - kernel route, C - connected, S - static, R - RIP,
       O - OSPF, I - IS-IS, B - BGP, E - EIGRP, N - NHRP,
       T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP,
       F - PBR, f - OpenFabric,
       > - selected route, * - FIB route, q - queued, r - rejected, b - backup
       t - trapped, o - offload failure

K>* 0.0.0.0/0 [0/100] via 192.168.119.1, enp39s0, 00:00:15
K>* 1.2.3.5/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.6/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.7/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.8/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.9/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.10/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.11/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.12/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.13/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.14/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.16/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 1.2.3.17/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
C>* 4.5.6.99/32 is directly connected, dummy9, 00:00:15
K>* 4.9.10.11/32 [0/0] via 172.22.0.44, br-23e378ed7fd2 linkdown, 00:00:15
K>* 10.11.12.13/32 [0/0] via 192.168.119.1, enp39s0, 00:00:15
C>* 192.168.10.0/24 is directly connected, dummy99, 00:00:15
C>* 192.168.119.0/24 is directly connected, enp39s0, 00:00:15
eva#

Signed-off-by: Donald Sharp <sharpd@nvidia.com>

1 files changed, 11 insertions, 16 deletions

diff --git a/zebra/zebra_nhg.c b/zebra/zebra_nhg.c
index f025507f7d..9a0f48158f 100644
--- a/zebra/zebra_nhg.c
+++ b/zebra/zebra_nhg.c
@@ -2084,11 +2084,7 @@ static int nexthop_active(struct nexthop *nexthop, struct nhg_hash_entry *nhe,
 		 * route and interface is up, its active. We trust kernel routes
 		 * to be good.
 		 */
-		if (ifp
-		    && (if_is_operative(ifp)
-			|| (if_is_up(ifp)
-			    && (type == ZEBRA_ROUTE_KERNEL
-				|| type == ZEBRA_ROUTE_SYSTEM))))
+		if (ifp && (if_is_operative(ifp)))
 			return 1;
 		else
 			return 0;
@@ -2457,20 +2453,19 @@ static unsigned nexthop_active_check(struct route_node *rn,
 		zlog_debug("%s: re %p, nexthop %pNHv", __func__, re, nexthop);
 
 	/*
-	 * If the kernel has sent us a NEW route, then
+	 * If this is a kernel route, then if the interface is *up* then
 	 * by golly gee whiz it's a good route.
-	 *
-	 * If its an already INSTALLED route we have already handled, then the
-	 * kernel route's nexthop might have became unreachable
-	 * and we have to handle that.
 	 */
-	if (!CHECK_FLAG(re->status, ROUTE_ENTRY_INSTALLED) &&
-	    (re->type == ZEBRA_ROUTE_KERNEL ||
-	     re->type == ZEBRA_ROUTE_SYSTEM)) {
-		SET_FLAG(nexthop->flags, NEXTHOP_FLAG_ACTIVE);
-		goto skip_check;
-	}
+	if (re->type == ZEBRA_ROUTE_KERNEL || re->type == ZEBRA_ROUTE_SYSTEM) {
+		struct interface *ifp;
+
+		ifp = if_lookup_by_index(nexthop->ifindex, nexthop->vrf_id);
 
+		if (ifp && (if_is_operative(ifp) || if_is_up(ifp))) {
+			SET_FLAG(nexthop->flags, NEXTHOP_FLAG_ACTIVE);
+			goto skip_check;
+		}
+	}
 
 	vrf_id = zvrf_id(rib_dest_vrf(rib_dest_from_rnode(rn)));
 	switch (nexthop->type) {