zebra: Fix to avoid two Vrfs with same table ids

During internal testing, when the following sequence is followed, two
non default vrfs end up pointing to the same table-id

 - Initially vrf201 has table id 1002
 - ip link add dev vrf202 type vrf table 1002
 - ip link set dev vrf202 up
 - ip link set dev <intrerface> master vrf202

This will ideally lead to zebra exit since this is a misconfiguration as
expected.

However if we perform a restart frr.service at this point, we end up
having two vrfs pointing to same table-id and bad things can happen.
This is because in the interface_vrf_change, we incorrectly check for
vrf_lookup_by_id() to evaluate if there is a misconfig. This works well
for a non restart case but not for the startup case.

root@mlx-3700-20:mgmt:/var/log/frr# sudo vtysh -c "sh vrf"
vrf mgmt id 37 table 1001
vrf vrf201 id 46 table 1002
vrf vrf202 id 59 table 1002 >>>>

Fix: in all cases of misconfiguration, exit zebra as expected.

Ticket :#3970414

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

Signed-off-by: Rajasekar Raja <rajasekarr@nvidia.com>

1 files changed, 20 insertions, 16 deletions

diff --git a/zebra/interface.c b/zebra/interface.c
index f1f24cc29f..b3adc4483e 100644
--- a/zebra/interface.c
+++ b/zebra/interface.c
@@ -1483,23 +1483,27 @@ static void interface_vrf_change(enum dplane_op_e op, ifindex_t ifindex,
 				"DPLANE_OP_INTF_UPDATE for VRF %s(%u) table %u",
 				name, ifindex, tableid);
 
-		if (!vrf_lookup_by_id((vrf_id_t)ifindex)) {
-			vrf_id_t exist_id;
-
-			exist_id = zebra_vrf_lookup_by_table(tableid, ns_id);
-			if (exist_id != VRF_DEFAULT) {
-				vrf = vrf_lookup_by_id(exist_id);
-
-				if (vrf)
-					flog_err(EC_ZEBRA_VRF_MISCONFIGURED,
-						 "VRF %s id %u table id overlaps existing vrf %s(%d), misconfiguration exiting",
-						 name, ifindex, vrf->name,
-						 vrf->vrf_id);
-				else
-					flog_err(EC_ZEBRA_VRF_NOT_FOUND,
-						 "VRF %s id %u does not exist",
-						 name, ifindex);
+		/*
+		 * For a given tableid, if there already exists a vrf and it
+		 * is different from the current vrf to be operated, then there
+		 * is a misconfiguration and zebra will exit.
+		 */
+		vrf_id_t exist_id = zebra_vrf_lookup_by_table(tableid, ns_id);
+
+		if (exist_id != VRF_DEFAULT) {
+			vrf = vrf_lookup_by_id(exist_id);
+
+			if (!vrf_lookup_by_id((vrf_id_t)ifindex) && !vrf) {
+				flog_err(EC_ZEBRA_VRF_NOT_FOUND,
+					 "VRF %s id %u does not exist", name,
+					 ifindex);
+				exit(-1);
+			}
 
+			if (vrf && strcmp(name, vrf->name)) {
+				flog_err(EC_ZEBRA_VRF_MISCONFIGURED,
+					 "VRF %s id %u table id overlaps existing vrf %s(%d), misconfiguration exiting",
+					 name, ifindex, vrf->name, vrf->vrf_id);
 				exit(-1);
 			}
 		}