@@ -21,6 +21,7 @@
#include "lflow.h"
#include "lport.h"
#include "chassis.h"
+#include "pinctrl.h"
#include "lib/bundle.h"
#include "openvswitch/poll-loop.h"
#include "lib/uuid.h"
@@ -235,9 +236,12 @@ get_zone_ids(const struct sbrec_port_binding *binding,
}
static void
-put_replace_router_port_mac_flows(const struct
+put_replace_router_port_mac_flows(struct ovsdb_idl_index
+ *sbrec_port_binding_by_name,
+ const struct
sbrec_port_binding *localnet_port,
const struct sbrec_chassis *chassis,
+ const struct sset *active_tunnels,
const struct hmap *local_datapaths,
struct ofpbuf *ofpacts_p,
ofp_port_t ofport,
@@ -278,8 +282,21 @@ put_replace_router_port_mac_flows(const struct
char *err_str = NULL;
struct match match;
struct ofpact_mac *replace_mac;
+ char *cr_peer_name = xasprintf("cr-%s", rport_binding->logical_port);
- /* Table 65, priority 150.
+
+ if (pinctrl_is_chassis_resident(sbrec_port_binding_by_name,
+ chassis, active_tunnels,
+ cr_peer_name)) {
+ /* If a router port's chassisredirect port is
+ * resident on this chassis, then we need not do mac replace. */
+ free(cr_peer_name);
+ continue;
+ }
+
+ free(cr_peer_name);
+
+ /* Table 65, priority 150.
* =======================
*
* Implements output to localnet port.
@@ -792,7 +809,8 @@ consider_port_binding(struct ovsdb_idl_index *sbrec_port_binding_by_name,
&match, ofpacts_p);
if (!strcmp(binding->type, "localnet")) {
- put_replace_router_port_mac_flows(binding, chassis,
+ put_replace_router_port_mac_flows(sbrec_port_binding_by_name,
+ binding, chassis, active_tunnels,
local_datapaths, ofpacts_p,
ofport, flow_table);
}
@@ -221,6 +221,8 @@ static bool may_inject_pkts(void);
COVERAGE_DEFINE(pinctrl_drop_put_mac_binding);
COVERAGE_DEFINE(pinctrl_drop_buffered_packets_map);
+#define GARP_DEF_REPEAT_INTERVAL_MS (3 * 60 * 1000) /* 3 minutes */
+
void
pinctrl_init(void)
{
@@ -237,6 +239,25 @@ pinctrl_init(void)
&pinctrl);
}
+bool
+pinctrl_is_chassis_resident(struct ovsdb_idl_index *sbrec_port_binding_by_name,
+ const struct sbrec_chassis *chassis,
+ const struct sset *active_tunnels,
+ const char *port_name)
+{
+ const struct sbrec_port_binding *pb
+ = lport_lookup_by_name(sbrec_port_binding_by_name, port_name);
+ if (!pb || !pb->chassis) {
+ return false;
+ }
+ if (strcmp(pb->type, "chassisredirect")) {
+ return pb->chassis == chassis;
+ } else {
+ return ha_chassis_group_is_active(pb->ha_chassis_group,
+ active_tunnels, chassis);
+ }
+}
+
static ovs_be32
queue_msg(struct rconn *swconn, struct ofpbuf *msg)
{
@@ -2525,6 +2546,8 @@ struct garp_data {
int backoff; /* Backoff for the next announcement. */
uint32_t dp_key; /* Datapath used to output this GARP. */
uint32_t port_key; /* Port to inject the GARP into. */
+ bool is_repeat; /* Send GARPs continously */
+ long long int repeat_interval; /* Interval between GARP bursts in ms */
};
/* Contains GARPs to be sent. Protected by pinctrl_mutex*/
@@ -2545,7 +2568,8 @@ destroy_send_garps(void)
/* Runs with in the main ovn-controller thread context. */
static void
add_garp(const char *name, const struct eth_addr ea, ovs_be32 ip,
- uint32_t dp_key, uint32_t port_key)
+ uint32_t dp_key, uint32_t port_key, bool is_repeat,
+ long long int repeat_interval)
{
struct garp_data *garp = xmalloc(sizeof *garp);
garp->ea = ea;
@@ -2554,6 +2578,8 @@ add_garp(const char *name, const struct eth_addr ea, ovs_be32 ip,
garp->backoff = 1;
garp->dp_key = dp_key;
garp->port_key = port_key;
+ garp->is_repeat = is_repeat;
+ garp->repeat_interval = repeat_interval;
shash_add(&send_garp_data, name, garp);
/* Notify pinctrl_handler so that it can wakeup and process
@@ -2563,7 +2589,8 @@ add_garp(const char *name, const struct eth_addr ea, ovs_be32 ip,
/* Add or update a vif for which GARPs need to be announced. */
static void
-send_garp_update(const struct sbrec_port_binding *binding_rec,
+send_garp_update(struct ovsdb_idl_index *sbrec_port_binding_by_name,
+ const struct sbrec_port_binding *binding_rec,
struct shash *nat_addresses)
{
volatile struct garp_data *garp = NULL;
@@ -2588,7 +2615,7 @@ send_garp_update(const struct sbrec_port_binding *binding_rec,
add_garp(name, laddrs->ea,
laddrs->ipv4_addrs[i].addr,
binding_rec->datapath->tunnel_key,
- binding_rec->tunnel_key);
+ binding_rec->tunnel_key, false, 0);
}
free(name);
}
@@ -2598,6 +2625,64 @@ send_garp_update(const struct sbrec_port_binding *binding_rec,
return;
}
+ /* Update GARPs for local chassisredirect port, if the peer
+ * layer 2 switch is of type vlan.
+ */
+ if (!strcmp(binding_rec->type, "chassisredirect")) {
+ struct eth_addr mac;
+ ovs_be32 ip, mask;
+ uint32_t dp_key = 0;
+ uint32_t port_key = 0;
+ const struct sbrec_port_binding *peer_port = NULL;
+ const struct sbrec_port_binding *distributed_port = NULL;
+
+ if (!ovn_sbrec_get_port_binding_ip_mac(binding_rec, &mac,
+ &ip, &mask)) {
+ /* Router Port binding without ip and mac configured. */
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 1);
+ VLOG_WARN_RL(&rl, "cannot send garp, router port binding: %s, "
+ "does not have proper ip,mac values: %s",
+ binding_rec->logical_port, *binding_rec->mac);
+ return;
+ }
+
+ const char *lrp_name = smap_get(&binding_rec->options,
+ "distributed-port");
+ ovs_assert(lrp_name);
+
+ distributed_port = lport_lookup_by_name(sbrec_port_binding_by_name,
+ lrp_name);
+ ovs_assert(distributed_port);
+
+ const char *peer_name = smap_get(&distributed_port->options, "peer");
+ ovs_assert(peer_name);
+
+ peer_port = lport_lookup_by_name(sbrec_port_binding_by_name,
+ peer_name);
+ ovs_assert(peer_port);
+
+ const char *network_type = smap_get(&peer_port->datapath->external_ids,
+ "network-type");
+
+ /* Advertise GARP only of logical switch is of type bridged. */
+ if (!network_type || strcmp(network_type, "bridged")) {
+ return;
+ }
+
+ dp_key = peer_port->datapath->tunnel_key;
+ port_key = peer_port->tunnel_key;
+
+ garp = shash_find_data(&send_garp_data, binding_rec->logical_port);
+ if (garp) {
+ garp->dp_key = dp_key;
+ garp->port_key = port_key;
+ } else {
+ add_garp(binding_rec->logical_port, mac, ip,
+ dp_key, port_key, true, GARP_DEF_REPEAT_INTERVAL_MS);
+ }
+ return;
+ }
+
/* Update GARP for vif if it exists. */
garp = shash_find_data(&send_garp_data, binding_rec->logical_port);
if (garp) {
@@ -2617,7 +2702,8 @@ send_garp_update(const struct sbrec_port_binding *binding_rec,
add_garp(binding_rec->logical_port,
laddrs.ea, laddrs.ipv4_addrs[0].addr,
- binding_rec->datapath->tunnel_key, binding_rec->tunnel_key);
+ binding_rec->datapath->tunnel_key, binding_rec->tunnel_key,
+ false, 0);
destroy_lport_addresses(&laddrs);
break;
@@ -2679,7 +2765,12 @@ send_garp(struct rconn *swconn, struct garp_data *garp,
garp->backoff *= 2;
garp->announce_time = current_time + garp->backoff * 1000;
} else {
- garp->announce_time = LLONG_MAX;
+ if (garp->is_repeat) {
+ garp->backoff = 1;
+ garp->announce_time = current_time + garp->repeat_interval;
+ } else {
+ garp->announce_time = LLONG_MAX;
+ }
}
return garp->announce_time;
}
@@ -2763,25 +2854,6 @@ get_localnet_vifs_l3gwports(
sbrec_port_binding_index_destroy_row(target);
}
-static bool
-pinctrl_is_chassis_resident(struct ovsdb_idl_index *sbrec_port_binding_by_name,
- const struct sbrec_chassis *chassis,
- const struct sset *active_tunnels,
- const char *port_name)
-{
- const struct sbrec_port_binding *pb
- = lport_lookup_by_name(sbrec_port_binding_by_name, port_name);
- if (!pb || !pb->chassis) {
- return false;
- }
- if (strcmp(pb->type, "chassisredirect")) {
- return pb->chassis == chassis;
- } else {
- return ha_chassis_group_is_active(pb->ha_chassis_group,
- active_tunnels, chassis);
- }
-}
-
/* Extracts the mac, IPv4 and IPv6 addresses, and logical port from
* 'addresses' which should be of the format 'MAC [IP1 IP2 ..]
* [is_chassis_resident("LPORT_NAME")]', where IPn should be a valid IPv4
@@ -2923,6 +2995,67 @@ get_nat_addresses_and_keys(struct ovsdb_idl_index *sbrec_port_binding_by_name,
}
static void
+get_local_cr_ports(struct ovsdb_idl_index *sbrec_port_binding_by_name,
+ struct sset *local_cr_ports,
+ struct sset *local_l3gw_ports,
+ const struct sbrec_chassis *chassis,
+ const struct sset *active_tunnels)
+{
+ const char *gw_port;
+ SSET_FOR_EACH (gw_port, local_l3gw_ports) {
+ const struct sbrec_port_binding *binding_rec;
+
+ binding_rec = lport_lookup_by_name(sbrec_port_binding_by_name,
+ gw_port);
+ if (!binding_rec) {
+ continue;
+ }
+
+ /* For the patch port we will add send garp for peer's ip and mac. */
+ if (!strcmp(binding_rec->type, "patch")) {
+ const struct sbrec_port_binding *cr_port = NULL;
+
+ bool is_cr_resident;
+ struct eth_addr mac;
+ ovs_be32 ip, mask;
+
+ const char *peer_name = smap_get(&binding_rec->options, "peer");
+ ovs_assert(peer_name);
+
+ char *cr_peer_name = xasprintf("cr-%s", peer_name);
+ cr_port = lport_lookup_by_name(sbrec_port_binding_by_name,
+ cr_peer_name);
+ free(cr_peer_name);
+
+ if (!cr_port) {
+ continue;
+ }
+
+ is_cr_resident = pinctrl_is_chassis_resident
+ (sbrec_port_binding_by_name,
+ chassis,
+ active_tunnels,
+ cr_port->logical_port);
+ if (!is_cr_resident) {
+ continue;
+ }
+
+ if (!ovn_sbrec_get_port_binding_ip_mac(cr_port, &mac, &ip,
+ &mask)) {
+ /* Router Port binding without ip and mac configured. */
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 1);
+ VLOG_WARN_RL(&rl, "cannot send garp, router port binding: %s, "
+ "does not have proper ip,mac values: %s",
+ cr_port->logical_port, *cr_port->mac);
+ return;
+ }
+
+ sset_add(local_cr_ports, cr_port->logical_port);
+ }
+ }
+}
+
+static void
send_garp_wait(long long int send_garp_time)
{
/* Set the poll timer for next garp only if there is garp data to
@@ -2967,6 +3100,8 @@ send_garp_prepare(struct ovsdb_idl_index *sbrec_port_binding_by_datapath,
{
struct sset localnet_vifs = SSET_INITIALIZER(&localnet_vifs);
struct sset local_l3gw_ports = SSET_INITIALIZER(&local_l3gw_ports);
+ struct sset local_cr_ports = SSET_INITIALIZER(&local_cr_ports);
+
struct sset nat_ip_keys = SSET_INITIALIZER(&nat_ip_keys);
struct shash nat_addresses;
@@ -2981,11 +3116,17 @@ send_garp_prepare(struct ovsdb_idl_index *sbrec_port_binding_by_datapath,
&nat_ip_keys, &local_l3gw_ports,
chassis, active_tunnels,
&nat_addresses);
+
+ get_local_cr_ports(sbrec_port_binding_by_name,
+ &local_cr_ports, &local_l3gw_ports,
+ chassis, active_tunnels);
+
/* For deleted ports and deleted nat ips, remove from send_garp_data. */
struct shash_node *iter, *next;
SHASH_FOR_EACH_SAFE (iter, next, &send_garp_data) {
if (!sset_contains(&localnet_vifs, iter->name) &&
- !sset_contains(&nat_ip_keys, iter->name)) {
+ !sset_contains(&nat_ip_keys, iter->name) &&
+ !sset_contains(&local_cr_ports, iter->name)) {
send_garp_delete(iter->name);
}
}
@@ -2996,7 +3137,7 @@ send_garp_prepare(struct ovsdb_idl_index *sbrec_port_binding_by_datapath,
const struct sbrec_port_binding *pb = lport_lookup_by_name(
sbrec_port_binding_by_name, iface_id);
if (pb) {
- send_garp_update(pb, &nat_addresses);
+ send_garp_update(sbrec_port_binding_by_name, pb, &nat_addresses);
}
}
@@ -3006,7 +3147,17 @@ send_garp_prepare(struct ovsdb_idl_index *sbrec_port_binding_by_datapath,
const struct sbrec_port_binding *pb
= lport_lookup_by_name(sbrec_port_binding_by_name, gw_port);
if (pb) {
- send_garp_update(pb, &nat_addresses);
+ send_garp_update(sbrec_port_binding_by_name, pb, &nat_addresses);
+ }
+ }
+
+ /* Update send_garp_data for chassisredirect router ports. */
+ const char *cr_port;
+ SSET_FOR_EACH (cr_port, &local_cr_ports) {
+ const struct sbrec_port_binding *pb
+ = lport_lookup_by_name(sbrec_port_binding_by_name, cr_port);
+ if (pb) {
+ send_garp_update(sbrec_port_binding_by_name, pb, &nat_addresses);
}
}
@@ -44,4 +44,10 @@ void pinctrl_run(struct ovsdb_idl_txn *ovnsb_idl_txn,
void pinctrl_wait(struct ovsdb_idl_txn *ovnsb_idl_txn);
void pinctrl_destroy(void);
+bool
+pinctrl_is_chassis_resident(struct ovsdb_idl_index *sbrec_port_binding_by_name,
+ const struct sbrec_chassis *chassis,
+ const struct sset *active_tunnels,
+ const char *port_name);
+
#endif /* ovn/pinctrl.h */
@@ -16,6 +16,7 @@
#include "ovn-util.h"
#include "dirs.h"
#include "openvswitch/vlog.h"
+#include "openvswitch/ofp-parse.h"
#include "ovn/lib/ovn-nb-idl.h"
#include "ovn/lib/ovn-sb-idl.h"
@@ -371,3 +372,33 @@ ovn_logical_flow_hash(const struct uuid *logical_datapath,
hash = hash_string(match, hash);
return hash_string(actions, hash);
}
+
+/* Extracts the mac, ip and mask for a sbrec_port_binding.
+ *
+ * Expects following format:
+ * "MAC_ADDRESS IP/MASK"
+ *
+ * Return true if MAC, IP and MASK are found, false otherwise.
+ */
+bool
+ovn_sbrec_get_port_binding_ip_mac(const struct sbrec_port_binding *binding,
+ struct eth_addr *mac,
+ ovs_be32 *ip, ovs_be32 *mask)
+{
+ char *err_str = NULL;
+
+ err_str = str_to_mac(binding->mac[0], mac);
+ if (err_str) {
+ free(err_str);
+ return false;
+ }
+
+ err_str = ip_parse_masked(binding->mac[0] + ETH_ADDR_STRLEN + 1,
+ ip, mask);
+ if (err_str) {
+ free(err_str);
+ return false;
+ }
+
+ return true;
+}
@@ -19,6 +19,7 @@
#include "lib/packets.h"
struct nbrec_logical_router_port;
+struct sbrec_port_binding;
struct sbrec_logical_flow;
struct uuid;
@@ -81,4 +82,9 @@ uint32_t ovn_logical_flow_hash(const struct uuid *logical_datapath,
uint16_t priority,
const char *match, const char *actions);
+bool
+ovn_sbrec_get_port_binding_ip_mac(const struct sbrec_port_binding *binding,
+ struct eth_addr *mac, ovs_be32 *ip,
+ ovs_be32 *mask);
+
#endif
@@ -6264,6 +6264,20 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* from different chassis. */
ds_put_format(&match, " && is_chassis_resident(%s)",
op->od->l3redirect_port->json_key);
+ } else if (op->peer &&
+ op->peer->od->network_type == DP_NETWORK_BRIDGED) {
+
+ /* For a vlan backed router port, we will always have the
+ * is_chassis_resident check. This is because there could be
+ * vm/server on vlan network, but not on OVN chassis and could
+ * end up arping for router port ip.
+ *
+ * This check works on the assumption that for OVN chassis VMs,
+ * logical switch ARP responder will respond to ARP requests
+ * for router port IP.
+ */
+ ds_put_format(&match, " && is_chassis_resident(\"cr-%s\")",
+ op->key);
}
ds_clear(&actions);
@@ -7365,18 +7379,23 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
ovn_lflow_add(lflows, od, S_ROUTER_IN_GW_REDIRECT, 300,
REGBIT_DISTRIBUTED_NAT" == 1", "next;");
- /* For traffic with outport == l3dgw_port, if the
- * packet did not match any higher priority redirect
- * rule, then the traffic is redirected to the central
- * instance of the l3dgw_port. */
- ds_clear(&match);
- ds_put_format(&match, "outport == %s",
- od->l3dgw_port->json_key);
- ds_clear(&actions);
- ds_put_format(&actions, "outport = %s; next;",
- od->l3redirect_port->json_key);
- ovn_lflow_add(lflows, od, S_ROUTER_IN_GW_REDIRECT, 50,
- ds_cstr(&match), ds_cstr(&actions));
+ /* For VLAN backed networks, default match will not redirect to
+ * chassis redirect port. */
+ if (od->l3dgw_port->peer &&
+ od->l3dgw_port->peer->od->network_type == DP_NETWORK_OVERLAY) {
+ /* For traffic with outport == l3dgw_port, if the
+ * packet did not match any higher priority redirect
+ * rule, then the traffic is redirected to the central
+ * instance of the l3dgw_port. */
+ ds_clear(&match);
+ ds_put_format(&match, "outport == %s",
+ od->l3dgw_port->json_key);
+ ds_clear(&actions);
+ ds_put_format(&actions, "outport = %s; next;",
+ od->l3redirect_port->json_key);
+ ovn_lflow_add(lflows, od, S_ROUTER_IN_GW_REDIRECT, 50,
+ ds_cstr(&match), ds_cstr(&actions));
+ }
/* If the Ethernet destination has not been resolved,
* redirect to the central instance of the l3dgw_port.
@@ -14021,7 +14021,7 @@ ovn-hv4-0
OVN_CLEANUP([hv1], [hv2], [hv3])
AT_CLEANUP
-AT_SETUP([ovn -- 2 HVs, 2 lports/HV, localnet ports, DVR chassis mac])
+AT_SETUP([ovn -- 2 HVs, 2 lports/HV, localnet ports, DVR E-W chassis mac])
ovn_start
@@ -14031,6 +14031,8 @@ ovn_start
# of VIF port name indicates the hypervisor it is bound to, e.g.
# lp23 means VIF 3 on hv2.
#
+# Both the switches are connected to a logical router "router".
+#
# Each switch's VLAN tag and their logical switch ports are:
# - ls1:
# - tagged with VLAN 101
@@ -14188,6 +14190,7 @@ test_ip() {
echo "------ OVN dump ------"
ovn-nbctl show
ovn-sbctl show
+ovn-sbctl list port_binding
echo "------ hv1 dump ------"
as hv1 ovs-vsctl show
@@ -14214,6 +14217,308 @@ as hv2 ovs-appctl fdb/show br-phys
OVN_CHECK_PACKETS([hv2/vif22-tx.pcap], [vif22.expected])
+
+# Associate a chassis as gateway chassis and validate garp.
+
+OVN_CLEANUP([hv1],[hv2])
+
+AT_CLEANUP
+
+
+AT_SETUP([ovn -- 2 HVs, 2 lports/HV, localnet ports, DVR N-S GARP])
+ovn_start
+
+
+# In this test cases we create 2 switches, all connected to same
+# physical network (through br-phys on each HV). Each switch has
+# 1 VIF. Each HV has 1 VIF port. The first digit
+# of VIF port name indicates the hypervisor it is bound to, e.g.
+# lp23 means VIF 3 on hv2.
+#
+# Both the switches are connected to a logical router "router".
+#
+# Additionally, we create a logical switch (ls-underlay) for N-S traffic.
+#
+# Each switch's VLAN tag and their logical switch ports are:
+# - ls1:
+# - tagged with VLAN 101
+# - ports: lp11
+# - ls2:
+# - tagged with VLAN 201
+# - ports: lp22
+# - ls-underlay:
+# - tagged with VLAN 1000
+#
+# Note: a localnet port is created for each switch to connect to
+# physical network.
+# lsp_to_ls LSP
+#
+# Prints the name of the logical switch that contains LSP.
+
+net_add n1
+for i in 1 2; do
+ sim_add hv$i
+ as hv$i
+ ovs-vsctl add-br br-phys
+ ovs-vsctl set open . external-ids:ovn-bridge-mappings=phys:br-phys
+ ovs-vsctl set open . external-ids:ovn-chassis-mac-mappings="phys:aa:bb:cc:dd:ee:$i$i"
+ ovs-vsctl set open . external-ids:system-id="HV$i"
+ ovn_attach n1 br-phys 192.168.0.$i
+ ovs-vsctl set-controller br-int ptcp:
+done
+
+ovn-nbctl ls-add ls-underlay bridged
+ovn-nbctl lsp-add ls-underlay ln3 "" 1000
+ovn-nbctl lsp-set-addresses ln3 unknown
+ovn-nbctl lsp-set-type ln3 localnet
+ovn-nbctl lsp-set-options ln3 network_name=phys
+
+ovn-nbctl lr-add router
+ovn-nbctl lrp-add router router-to-underlay 00:00:01:01:02:07 172.31.0.1/24
+
+ovn-nbctl lsp-add ls-underlay underlay-to-router -- set Logical_Switch_Port \
+ underlay-to-router type=router \
+ options:router-port=router-to-underlay \
+ -- lsp-set-addresses underlay-to-router router
+
+ovn-nbctl --wait=sb sync
+
+# Associate hv2 as gateway chassis
+ovn-nbctl lrp-set-gateway-chassis router-to-underlay hv2
+
+ovn-nbctl show
+ovn-sbctl show
+
+# Dump a bunch of info helpful for debugging if there's a failure.
+
+echo "------ OVN dump ------"
+ovn-nbctl show
+ovn-sbctl show
+
+echo "------ hv1 dump ------"
+as hv1 ovs-vsctl show
+as hv1 ovs-vsctl list Open_Vswitch
+
+echo "------ hv2 dump ------"
+as hv2 ovs-vsctl show
+as hv2 ovs-vsctl list Open_Vswitch
+
+sleep 1
+
+echo "----------- Post Traffic hv1 dump -----------"
+as hv1 ovs-ofctl -O OpenFlow13 dump-flows br-int
+as hv1 ovs-appctl fdb/show br-phys
+
+echo "----------- Post Traffic hv2 dump -----------"
+as hv2 ovs-ofctl -O OpenFlow13 dump-flows br-int
+as hv2 ovs-appctl fdb/show br-phys
+
+AT_CHECK([as hv2 ovs-appctl fdb/show br-phys | grep 00:00:01:01:02:07 | grep 1000 | wc -l], [0], [[1
+]])
+
OVN_CLEANUP([hv1],[hv2])
AT_CLEANUP
+
+
+AT_SETUP([ovn -- 2 HVs, 2 lports/HV, localnet ports, DVR N-S Ping])
+ovn_start
+
+# In this test cases we create 3 switches, all connected to same
+# physical network (through br-phys on each HV). LS1 and LS2 have
+# 1 VIF each. Each HV has 1 VIF port. The first digit
+# of VIF port name indicates the hypervisor it is bound to, e.g.
+# lp23 means VIF 3 on hv2.
+#
+# All the switches are connected to a logical router "router".
+#
+# Each switch's VLAN tag and their logical switch ports are:
+# - ls1:
+# - tagged with VLAN 101
+# - ports: lp11
+# - ls2:
+# - tagged with VLAN 201
+# - ports: lp22
+# - ls-underlay:
+# - tagged with VLAN 1000
+# Note: a localnet port is created for each switch to connect to
+# physical network.
+
+for i in 1 2; do
+ ls_name=ls$i
+ ovn-nbctl ls-add $ls_name bridged
+ ln_port_name=ln$i
+ if test $i -eq 1; then
+ ovn-nbctl lsp-add $ls_name $ln_port_name "" 101
+ elif test $i -eq 2; then
+ ovn-nbctl lsp-add $ls_name $ln_port_name "" 201
+ fi
+ ovn-nbctl lsp-set-addresses $ln_port_name unknown
+ ovn-nbctl lsp-set-type $ln_port_name localnet
+ ovn-nbctl lsp-set-options $ln_port_name network_name=phys
+done
+
+# lsp_to_ls LSP
+#
+# Prints the name of the logical switch that contains LSP.
+lsp_to_ls () {
+ case $1 in dnl (
+ lp?[[11]]) echo ls1 ;; dnl (
+ lp?[[12]]) echo ls2 ;; dnl (
+ *) AT_FAIL_IF([:]) ;;
+ esac
+}
+
+vif_to_hv () {
+ case $1 in dnl (
+ vif[[1]]?) echo hv1 ;; dnl (
+ vif[[2]]?) echo hv2 ;; dnl (
+ vif?[[north]]?) echo hv4 ;; dnl (
+ *) AT_FAIL_IF([:]) ;;
+ esac
+}
+
+ip_to_hex() {
+ printf "%02x%02x%02x%02x" "$@"
+}
+
+net_add n1
+for i in 1 2; do
+ sim_add hv$i
+ as hv$i
+ ovs-vsctl add-br br-phys
+ ovs-vsctl set open . external-ids:ovn-bridge-mappings=phys:br-phys
+ ovs-vsctl set open . external-ids:ovn-chassis-mac-mappings="phys:aa:bb:cc:dd:ee:$i$i"
+ ovn_attach n1 br-phys 192.168.0.$i
+
+ ovs-vsctl add-port br-int vif$i$i -- \
+ set Interface vif$i$i external-ids:iface-id=lp$i$i \
+ options:tx_pcap=hv$i/vif$i$i-tx.pcap \
+ options:rxq_pcap=hv$i/vif$i$i-rx.pcap \
+ ofport-request=$i$i
+
+ lsp_name=lp$i$i
+ ls_name=$(lsp_to_ls $lsp_name)
+
+ ovn-nbctl lsp-add $ls_name $lsp_name
+ ovn-nbctl lsp-set-addresses $lsp_name "f0:00:00:00:00:$i$i 192.168.$i.$i"
+ ovn-nbctl lsp-set-port-security $lsp_name f0:00:00:00:00:$i$i
+
+ OVS_WAIT_UNTIL([test x`ovn-nbctl lsp-get-up $lsp_name` = xup])
+
+done
+
+ovn-nbctl ls-add ls-underlay bridged
+ovn-nbctl lsp-add ls-underlay ln3 "" 1000
+ovn-nbctl lsp-set-addresses ln3 unknown
+ovn-nbctl lsp-set-type ln3 localnet
+ovn-nbctl lsp-set-options ln3 network_name=phys
+
+ovn-nbctl ls-add ls-north bridged
+ovn-nbctl lsp-add ls-north ln4 "" 1000
+ovn-nbctl lsp-set-addresses ln4 unknown
+ovn-nbctl lsp-set-type ln4 localnet
+ovn-nbctl lsp-set-options ln4 network_name=phys
+
+# Add a VM on ls-north
+ovn-nbctl lsp-add ls-north lp-north
+ovn-nbctl lsp-set-addresses lp-north "f0:f0:00:00:00:11 172.31.0.10"
+ovn-nbctl lsp-set-port-security lp-north f0:f0:00:00:00:11
+
+# Add 3rd hypervisor
+sim_add hv3
+as hv3 ovs-vsctl add-br br-phys
+as hv3 ovs-vsctl set open . external-ids:ovn-bridge-mappings=phys:br-phys
+as hv3 ovs-vsctl set open . external-ids:ovn-chassis-mac-mappings="phys:aa:bb:cc:dd:ee:33"
+as hv3 ovn_attach n1 br-phys 192.168.0.3
+
+# Add 4th hypervisor
+sim_add hv4
+as hv4 ovs-vsctl add-br br-phys
+as hv4 ovs-vsctl set open . external-ids:ovn-bridge-mappings=phys:br-phys
+as hv4 ovs-vsctl set open . external-ids:ovn-chassis-mac-mappings="phys:aa:bb:cc:dd:ee:44"
+as hv4 ovn_attach n1 br-phys 192.168.0.4
+
+as hv4 ovs-vsctl add-port br-int vif-north -- \
+ set Interface vif-north external-ids:iface-id=lp-north \
+ options:tx_pcap=hv4/vif-north-tx.pcap \
+ options:rxq_pcap=hv4/vif-north-rx.pcap \
+ ofport-request=44
+
+ovn-nbctl lr-add router
+ovn-nbctl lrp-add router router-to-ls1 00:00:01:01:02:03 192.168.1.3/24
+ovn-nbctl lrp-add router router-to-ls2 00:00:01:01:02:05 192.168.2.3/24
+ovn-nbctl lrp-add router router-to-underlay 00:00:01:01:02:07 172.31.0.1/24
+
+ovn-nbctl lsp-add ls1 ls1-to-router -- set Logical_Switch_Port ls1-to-router type=router \
+ options:router-port=router-to-ls1 -- lsp-set-addresses ls1-to-router router
+ovn-nbctl lsp-add ls2 ls2-to-router -- set Logical_Switch_Port ls2-to-router type=router \
+ options:router-port=router-to-ls2 -- lsp-set-addresses ls2-to-router router
+ovn-nbctl lsp-add ls-underlay underlay-to-router -- set Logical_Switch_Port \
+ underlay-to-router type=router \
+ options:router-port=router-to-underlay \
+ -- lsp-set-addresses underlay-to-router router
+
+ovn-nbctl lrp-set-gateway-chassis router-to-underlay hv3
+
+ovn-nbctl --wait=sb sync
+
+sleep 2
+
+OVN_POPULATE_ARP
+
+test_ip() {
+ # This packet has bad checksums but logical L3 routing doesn't check.
+ local inport=$1 src_mac=$2 dst_mac=$3 src_ip=$4 dst_ip=$5
+ local packet=${dst_mac}${src_mac}08004500001c0000000040110000${src_ip}${dst_ip}0035111100080000
+ shift; shift; shift; shift; shift
+ hv=`vif_to_hv $inport`
+ as $hv ovs-appctl netdev-dummy/receive $inport $packet
+}
+
+# Dump a bunch of info helpful for debugging if there's a failure.
+
+echo "------ OVN dump ------"
+ovn-nbctl show
+ovn-sbctl show
+ovn-sbctl list port_binding
+ovn-sbctl list mac_binding
+
+echo "------ hv1 dump ------"
+as hv1 ovs-vsctl show
+as hv1 ovs-vsctl list Open_Vswitch
+
+echo "------ hv2 dump ------"
+as hv2 ovs-vsctl show
+as hv2 ovs-vsctl list Open_Vswitch
+
+echo "Send traffic"
+sip=`ip_to_hex 192 168 1 1`
+dip=`ip_to_hex 172 31 0 10`
+test_ip vif11 f00000000011 000001010203 $sip $dip vif-north
+
+sleep 1
+
+echo "----------- Post Traffic hv1 dump -----------"
+as hv1 ovs-ofctl -O OpenFlow13 dump-flows br-int
+as hv1 ovs-appctl fdb/show br-phys
+
+echo "----------- Post Traffic hv2 dump -----------"
+as hv2 ovs-ofctl -O OpenFlow13 dump-flows br-int
+as hv2 ovs-appctl fdb/show br-phys
+
+echo "----------- Post Traffic hv3 dump -----------"
+as hv3 ovs-ofctl -O OpenFlow13 dump-flows br-int
+as hv3 ovs-appctl fdb/show br-phys
+
+echo "----------- Post Traffic hv4 dump -----------"
+as hv4 ovs-ofctl -O OpenFlow13 dump-flows br-int
+as hv4 ovs-appctl fdb/show br-phys
+
+# Confirm that HV1 chassis mac is never seen on Gateway chassis, i.e HV3
+AT_CHECK([as hv3 ovs-appctl fdb/show br-phys | grep aa:bb:cc:dd:ee:11 | wc -l], [0], [[0
+]])
+
+OVN_CLEANUP([hv1],[hv2],[hv3],[hv4])
+
+AT_CLEANUP
Background: [1] https://mail.openvswitch.org/pipermail/ovs-dev/2018-October/353066.html [2] https://docs.google.com/document/d/1uoQH478wM1OZ16HrxzbOUvk5LvFnfNEWbkPT6Zmm9OU/edit?usp=sharing This Series: Layer 2, Layer 3 E-W and Layer 3 N-S (NO NAT) changes for vlan backed distributed logical router. This patch: For North-South traffic, we need a chassis which will respond to ARP requests for router port coming from outside. For this purpose, we will reply upon gateway-chassis construct in OVN, on a logical router port, we will associate one or more chassis as gateway chassis. One of these chassis would be active at a point and will become entry point to traffic, bound for end points behind logical router coming from outside network (North to South). This patch make some enhancements to gateway chassis implementation to manage above used case. A. Do not replace router port mac with chassis mac on gateway chassis. This is done, because: i. Chassisredirect port is NOT a distributed port, hence we need not replace its mac address (which same as router port mac). ii. ARP cache will be consistent everywhere, i.e just like endpoints on OVN chassis will see configured router port mac as resolved mac for router port ip, outside endpoints will see that as well. iii. For implementing Network Address Translation. Although not a part of this series. But, follow up series would be having this feature and approach would rely upon sending packets to redirect chassis using chassis redirect router port mac as dest mac. B. Advertise router port GARP on gateway chassis. This is needed, especially if a failover happens and chassisredirect port moves to a new gateway chassis. Otherwise, there would be packet drops till outside router ARPs for router port ip again. Intention of this GARP is to update top of the rack (TOR) to direct router port mac to new hypervisor. Hence, we could have done the same using RARP as well, but because ovn-controller has implementation for GARP already, hence it did not look like worthy to add a RARP implementation just for this. C. For South to North traffic, we need not pass through gateway chassis, if there is no address transalation needed. For overlay networks, NATing is a must to talk to outside networks. However, for vlan backed networks, NATing is not a must, and hence in the absence of NATing configuration we need redirect the packet to gateway chassis. Signed-off-by: Ankur Sharma <ankur.sharma@nutanix.com> --- ovn/controller/physical.c | 24 +++- ovn/controller/pinctrl.c | 205 +++++++++++++++++++++++++++---- ovn/controller/pinctrl.h | 6 + ovn/lib/ovn-util.c | 31 +++++ ovn/lib/ovn-util.h | 6 + ovn/northd/ovn-northd.c | 43 +++++-- tests/ovn.at | 307 +++++++++++++++++++++++++++++++++++++++++++++- 7 files changed, 579 insertions(+), 43 deletions(-)