| Message ID | d172212019f0f43160f110a500867c8451cd021f.1711462992.git.felix.huettner@mail.schwarz |
|---|---|
| State | Superseded |
| Headers | show |
| Series | [ovs-dev] northd: Support routing over other address families. | expand |
| Context | Check | Description |
|---|---|---|
| ovsrobot/apply-robot | success | apply and check: success |
| ovsrobot/github-robot-_Build_and_Test | success | github build: passed |
| ovsrobot/github-robot-_ovn-kubernetes | success | github build: passed |
On 3/27/24 09:43, Felix Huettner via dev wrote: > In most cases IPv4 packets are routed only over other IPv4 networks and > IPv6 packets are routed only over IPv6 networks. However there is no > interent reason for this limitation. Routing IPv4 packets over IPv6 > networks just requires the router to contain a route for an IPv4 network > with an IPv6 nexthop. > > This was previously prevented in OVN in ovn-nbctl and northd. By > removing these filters the forwarding will work if the mac addresses are > prepopulated. > > If the mac addresses are not prepopulated we will attempt to resolve them using > the original address family of the packet and not the address family of the > nexthop. This will fail and we will not forward the packet. > > This feature can for example be used by service providers to > interconnect multiple IPv4 networks of a customer without needing to > negotiate free IPv4 addresses by just using any IPv6 address. > > Signed-off-by: Felix Huettner <felix.huettner@mail.schwarz> > --- Hi Felix, Thanks for the patch! It's a very useful addition to the OVN feature set. The code looks mostly OK to me, I only had some minor comments, please see below. > NEWS | 4 + > northd/northd.c | 45 ++-- > tests/ovn-nbctl.at | 8 +- > tests/ovn.at | 615 ++++++++++++++++++++++++++++++++++++++++++ > utilities/ovn-nbctl.c | 12 +- > 5 files changed, 650 insertions(+), 34 deletions(-) > > diff --git a/NEWS b/NEWS > index 4d6ebea89..b419b2628 100644 > --- a/NEWS > +++ b/NEWS > @@ -12,6 +12,10 @@ Post v24.03.0 > flow table id. > "lflow-stage-to-oftable STAGE_NAME" that converts stage name into OpenFlow > table id. > + - Allow Static Routes where the address families of ip_prefix and nexthop > + diverge (e.g. IPv4 packets over IPv6 links). This is currently limited to > + nexthops that have their mac addresses prepopulated (so > + dynamic_neigh_routers must be false). > > OVN v24.03.0 - 01 Mar 2024 > -------------------------- > diff --git a/northd/northd.c b/northd/northd.c > index 1839b7d8b..0359cde89 100644 > --- a/northd/northd.c > +++ b/northd/northd.c > @@ -10238,18 +10238,6 @@ parsed_routes_add(struct ovn_datapath *od, const struct hmap *lr_ports, > return NULL; > } > > - /* Verify that ip_prefix and nexthop have same address familiy. */ > - if (valid_nexthop) { > - if (IN6_IS_ADDR_V4MAPPED(&prefix) != IN6_IS_ADDR_V4MAPPED(&nexthop)) { > - static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1); > - VLOG_WARN_RL(&rl, "Address family doesn't match between 'ip_prefix'" > - " %s and 'nexthop' %s in static route "UUID_FMT, > - route->ip_prefix, route->nexthop, > - UUID_ARGS(&route->header_.uuid)); > - return NULL; > - } > - } > - > /* Verify that ip_prefix and nexthop are on the same network. */ > if (!is_discard_route && > !find_static_route_outport(od, lr_ports, route, > @@ -10666,7 +10654,7 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, > struct lflow_ref *lflow_ref) > > { > - bool is_ipv4 = IN6_IS_ADDR_V4MAPPED(&eg->prefix); > + bool is_ipv4_network = IN6_IS_ADDR_V4MAPPED(&eg->prefix); > uint16_t priority; > struct ecmp_route_list_node *er; > struct ds route_match = DS_EMPTY_INITIALIZER; > @@ -10675,7 +10663,8 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, > int ofs = !strcmp(eg->origin, ROUTE_ORIGIN_CONNECTED) ? > ROUTE_PRIO_OFFSET_CONNECTED: ROUTE_PRIO_OFFSET_STATIC; > build_route_match(NULL, eg->route_table_id, prefix_s, eg->plen, > - eg->is_src_route, is_ipv4, &route_match, &priority, ofs); > + eg->is_src_route, is_ipv4_network, &route_match, > + &priority, ofs); > free(prefix_s); > > struct ds actions = DS_EMPTY_INITIALIZER; > @@ -10708,7 +10697,11 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, > /* Find the outgoing port. */ > const char *lrp_addr_s = NULL; > struct ovn_port *out_port = NULL; > - if (!find_static_route_outport(od, lr_ports, route, is_ipv4, > + bool is_ipv4_gateway = is_ipv4_network; > + if (route->nexthop && route->nexthop[0]) { > + is_ipv4_gateway = strchr(route->nexthop, '.') ? true : false; > + } It might be a bit cleaner to just store the next-hop family in the parsed_route structure at parse time, in parsed_routes_add(). > + if (!find_static_route_outport(od, lr_ports, route, is_ipv4_gateway, > &lrp_addr_s, &out_port)) { > continue; > } > @@ -10733,9 +10726,9 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, > "eth.src = %s; " > "outport = %s; " > "next;", > - is_ipv4 ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6, > + is_ipv4_gateway ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6, > route->nexthop, > - is_ipv4 ? REG_SRC_IPV4 : REG_SRC_IPV6, > + is_ipv4_gateway ? REG_SRC_IPV4 : REG_SRC_IPV6, > lrp_addr_s, > out_port->lrp_networks.ea_s, > out_port->json_key); > @@ -10757,13 +10750,18 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, > const struct ovsdb_idl_row *stage_hint, bool is_discard_route, > int ofs, struct lflow_ref *lflow_ref) > { > - bool is_ipv4 = strchr(network_s, '.') ? true : false; > + bool is_ipv4_network = strchr(network_s, '.') ? true : false; > + bool is_ipv4_gateway = is_ipv4_network; > struct ds match = DS_EMPTY_INITIALIZER; > uint16_t priority; > const struct ovn_port *op_inport = NULL; > > + if (gateway && gateway[0]) { > + is_ipv4_gateway = strchr(gateway, '.') ? true : false; > + } > + Same comment about storing the next hop family in the parsed_route and passing it as argument to add_route(). > /* IPv6 link-local addresses must be scoped to the local router port. */ > - if (!is_ipv4) { > + if (!is_ipv4_network) { > struct in6_addr network; > ovs_assert(ipv6_parse(network_s, &network)); > if (in6_is_lla(&network)) { > @@ -10771,7 +10769,7 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, > } > } > build_route_match(op_inport, rtb_id, network_s, plen, is_src_route, > - is_ipv4, &match, &priority, ofs); > + is_ipv4_network, &match, &priority, ofs); > > struct ds common_actions = DS_EMPTY_INITIALIZER; > struct ds actions = DS_EMPTY_INITIALIZER; > @@ -10779,11 +10777,12 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, > ds_put_cstr(&actions, debug_drop_action()); > } else { > ds_put_format(&common_actions, REG_ECMP_GROUP_ID" = 0; %s = ", > - is_ipv4 ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6); > + is_ipv4_gateway ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6); > if (gateway && gateway[0]) { > ds_put_cstr(&common_actions, gateway); > } else { > - ds_put_format(&common_actions, "ip%s.dst", is_ipv4 ? "4" : "6"); > + ds_put_format(&common_actions, "ip%s.dst", > + is_ipv4_network ? "4" : "6"); > } > ds_put_format(&common_actions, "; " > "%s = %s; " > @@ -10791,7 +10790,7 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, > "outport = %s; " > "flags.loopback = 1; " > "next;", > - is_ipv4 ? REG_SRC_IPV4 : REG_SRC_IPV6, > + is_ipv4_gateway ? REG_SRC_IPV4 : REG_SRC_IPV6, > lrp_addr_s, > op->lrp_networks.ea_s, > op->json_key); > diff --git a/tests/ovn-nbctl.at b/tests/ovn-nbctl.at > index 5248e6c76..60dcdc9be 100644 > --- a/tests/ovn-nbctl.at > +++ b/tests/ovn-nbctl.at > @@ -1757,7 +1757,7 @@ AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.1/24 11.0.0.2]) > AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.10.0/24 lp0]) > AT_CHECK([ovn-nbctl --bfd lr-route-add lr0 10.0.20.0/24 11.0.2.1 lp0]) > AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.10.0/24 lp1], [1], [], > - [ovn-nbctl: bad IPv4 nexthop argument: lp1 > + [ovn-nbctl: bad nexthop argument: lp1 > ]) > > dnl Add overlapping route with 10.0.0.1/24 > @@ -1771,13 +1771,13 @@ AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.111/24a 11.0.0.1], [1], [], > [ovn-nbctl: bad prefix argument: 10.0.0.111/24a > ]) > AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.111/24 11.0.0.1a], [1], [], > - [ovn-nbctl: bad IPv4 nexthop argument: 11.0.0.1a > + [ovn-nbctl: bad nexthop argument: 11.0.0.1a > ]) > AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.111/24 11.0.0.1/24], [1], [], > - [ovn-nbctl: bad IPv4 nexthop argument: 11.0.0.1/24 > + [ovn-nbctl: bad nexthop argument: 11.0.0.1/24 > ]) > AT_CHECK([ovn-nbctl lr-route-add lr0 2001:0db8:1::/64 2001:0db8:0:f103::1/64], [1], [], > - [ovn-nbctl: bad IPv6 nexthop argument: 2001:0db8:0:f103::1/64 > + [ovn-nbctl: bad nexthop argument: 2001:0db8:0:f103::1/64 > ]) > AT_CHECK([ovn-nbctl --ecmp lr-route-add lr0 20.0.0.0/24 discard], [1], [], > [ovn-nbctl: ecmp is not valid for discard routes. Shall we add some positive tests too, i.e., route with IPv4 prefix and v6 next hop and the other way around? > diff --git a/tests/ovn.at b/tests/ovn.at > index 4d0c7ad53..8818d0db9 100644 > --- a/tests/ovn.at > +++ b/tests/ovn.at > @@ -38475,3 +38475,618 @@ OVS_WAIT_FOR_OUTPUT([as hv1 ovs-ofctl dump-flows br-int table=0 |grep priority=1 > OVN_CLEANUP([hv1]) > AT_CLEANUP > ]) > + > +OVN_FOR_EACH_NORTHD([ > +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, 2 peer LRs, IPv4 over IPv6]) If you decide to use fmt-pkt (see my comment below) please also add: AT_SKIP_IF([test $HAVE_SCAPY = no]) > +ovn_start > + > +# Logical network: > +# Two LRs - R1 and R2 that are connected to each other as peers in 2001:db8::/64 > +# network. R1 has a switchs ls1 (192.168.1.0/24) connected to it. > +# R2 has ls2 (172.16.1.0/24) connected to it. > + > +ls1_lp1_mac="f0:00:00:01:02:03" > +rp_ls1_mac="00:00:00:01:02:03" > +rp_ls2_mac="00:00:00:01:02:04" > +ls2_lp1_mac="f0:00:00:01:02:04" > + > +ls1_lp1_ip="192.168.1.2" > +ls2_lp1_ip="172.16.1.2" > + > +ovn-nbctl lr-add R1 > +ovn-nbctl lr-add R2 Please prefix all relevant commands with "check " to ensure they don't fail. This applies to the all test cases being added by this patch. > + > +ovn-nbctl ls-add ls1 > +ovn-nbctl ls-add ls2 > + > +# Connect ls1 to R1 > +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 192.168.1.1/24 > + > +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ > + options:router-port=ls1 addresses=\"$rp_ls1_mac\" > + > +# Connect ls2 to R2 > +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 172.16.1.1/24 > + > +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ > + options:router-port=ls2 addresses=\"$rp_ls2_mac\" > + > +# Connect R1 to R2 > +ovn-nbctl lrp-add R1 R1_R2 00:00:00:02:03:04 2001:db8::1/64 peer=R2_R1 > +ovn-nbctl lrp-add R2 R2_R1 00:00:00:02:03:05 2001:db8::2/64 peer=R1_R2 > + > +AT_CHECK([ovn-nbctl lr-route-add R1 "0.0.0.0/0" 2001:db8::2]) > +AT_CHECK([ovn-nbctl lr-route-add R2 "0.0.0.0/0" 2001:db8::1]) > + > +# Create logical port ls1-lp1 in ls1 > +ovn-nbctl lsp-add ls1 ls1-lp1 \ > +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" > + > +# Create logical port ls2-lp1 in ls2 > +ovn-nbctl lsp-add ls2 ls2-lp1 \ > +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" > + > +# Create two hypervisor and create OVS ports corresponding to logical ports. > +net_add n1 > + > +sim_add hv1 > +as hv1 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.1 > +ovs-vsctl -- add-port br-int hv1-vif1 -- \ > + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ > + options:tx_pcap=hv1/vif1-tx.pcap \ > + options:rxq_pcap=hv1/vif1-rx.pcap \ > + ofport-request=1 > + > +sim_add hv2 > +as hv2 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.2 > +ovs-vsctl -- add-port br-int hv2-vif1 -- \ > + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ > + options:tx_pcap=hv2/vif1-tx.pcap \ > + options:rxq_pcap=hv2/vif1-rx.pcap \ > + ofport-request=1 > + > + > +# Pre-populate the hypervisors' ARP tables so that we don't lose any > +# packets for ARP resolution (native tunneling doesn't queue packets > +# for ARP resolution). > +OVN_POPULATE_ARP > + > +# Allow some time for ovn-northd and ovn-controller to catch up. > +wait_for_ports_up > +check ovn-nbctl --wait=hv sync > + > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > + We're trying to use fmt-pkt() in all new test cases. It's cleaner than other options. > + > +echo "---------NB dump-----" > +ovn-nbctl show > +echo "---------------------" > +ovn-nbctl list logical_router > +echo "---------------------" > +ovn-nbctl list logical_router_port > +echo "---------------------" > + > +echo "---------SB dump-----" > +ovn-sbctl list datapath_binding > +echo "---------------------" > +ovn-sbctl list port_binding > +echo "---------------------" > + > +echo "------ hv1 dump ----------" > +as hv1 ovs-ofctl show br-int > +as hv1 ovs-ofctl dump-flows br-int > +echo "------ hv2 dump ----------" > +as hv2 ovs-ofctl show br-int > +as hv2 ovs-ofctl dump-flows br-int > + I know we do this kind of flow/DB dump for other tests too but it just clutters the log in case of succesful execution in my opinion. If it's really useful, can we dump these to files and use AT_CAPTURE_FILE() to > +# Packet to Expect > +# The TTL should be decremented by 2. > +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && > + ip4 && ip.ttl==62 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +echo $packet | ovstest test-ovn expr-to-packets > expected > + > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "reg0 == 172.16.1.2" | wc -l], [0], [1 > +]) > + > +# Disable the ls2-lp1 port. > +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "reg0 == 172.16.1.2" | wc -l], [0], [0 > +]) > + > +# Generate the packet destined for ls2-lp1 and it should not be delivered. > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > + > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > +# The 2nd packet sent shound not be received. > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +OVN_CLEANUP([hv1],[hv2]) > + > +AT_CLEANUP > +]) > + > +OVN_FOR_EACH_NORTHD([ > +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, LRs connected via LS, IPv4 over IPv6]) > +ovn_start > + > +# Logical network: > +# Two LRs - R1 and R2 that are connected to ls-transfer in 2001:db8::/64 > +# network. R1 has a switchs ls1 (192.168.1.0/24) connected to it. > +# R2 has ls2 (172.16.1.0/24) connected to it. > + > +ls1_lp1_mac="f0:00:00:01:02:03" > +rp_ls1_mac="00:00:00:01:02:03" > +rp_ls2_mac="00:00:00:01:02:04" > +ls2_lp1_mac="f0:00:00:01:02:04" > + > +ls1_lp1_ip="192.168.1.2" > +ls2_lp1_ip="172.16.1.2" > + > +ovn-nbctl lr-add R1 > +ovn-nbctl lr-add R2 > + > +ovn-nbctl ls-add ls1 > +ovn-nbctl ls-add ls2 > +ovn-nbctl ls-add ls-transfer > + > +# Connect ls1 to R1 > +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 192.168.1.1/24 > + > +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ > + options:router-port=ls1 addresses=\"$rp_ls1_mac\" > + > +# Connect ls2 to R2 > +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 172.16.1.1/24 > + > +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ > + options:router-port=ls2 addresses=\"$rp_ls2_mac\" > + > +# Connect R1 to R2 > +ovn-nbctl lrp-add R1 R1_ls-transfer 00:00:00:02:03:04 2001:db8::1/64 > +ovn-nbctl lrp-add R2 R2_ls-transfer 00:00:00:02:03:05 2001:db8::2/64 > + > +ovn-nbctl lsp-add ls-transfer ls-transfer_r1 -- \ > + set Logical_Switch_Port ls-transfer_r1 type=router \ > + options:router-port=R1_ls-transfer addresses=\"router\" > +ovn-nbctl lsp-add ls-transfer ls-transfer_r2 -- \ > + set Logical_Switch_Port ls-transfer_r2 type=router \ > + options:router-port=R2_ls-transfer addresses=\"router\" > + > +AT_CHECK([ovn-nbctl lr-route-add R1 "0.0.0.0/0" 2001:db8::2]) > +AT_CHECK([ovn-nbctl lr-route-add R2 "0.0.0.0/0" 2001:db8::1]) > + > +# Create logical port ls1-lp1 in ls1 > +ovn-nbctl lsp-add ls1 ls1-lp1 \ > +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" > + > +# Create logical port ls2-lp1 in ls2 > +ovn-nbctl lsp-add ls2 ls2-lp1 \ > +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" > + > +# Create two hypervisor and create OVS ports corresponding to logical ports. > +net_add n1 > + > +sim_add hv1 > +as hv1 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.1 > +ovs-vsctl -- add-port br-int hv1-vif1 -- \ > + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ > + options:tx_pcap=hv1/vif1-tx.pcap \ > + options:rxq_pcap=hv1/vif1-rx.pcap \ > + ofport-request=1 > + > +sim_add hv2 > +as hv2 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.2 > +ovs-vsctl -- add-port br-int hv2-vif1 -- \ > + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ > + options:tx_pcap=hv2/vif1-tx.pcap \ > + options:rxq_pcap=hv2/vif1-rx.pcap \ > + ofport-request=1 > + > + > +# Pre-populate the hypervisors' ARP tables so that we don't lose any > +# packets for ARP resolution (native tunneling doesn't queue packets > +# for ARP resolution). > +OVN_POPULATE_ARP > + > +# Allow some time for ovn-northd and ovn-controller to catch up. > +wait_for_ports_up > +check ovn-nbctl --wait=hv sync > + > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > + fmt-pkt() is a better option IMO. > + > +echo "---------NB dump-----" > +ovn-nbctl show > +echo "---------------------" > +ovn-nbctl list logical_router > +echo "---------------------" > +ovn-nbctl list logical_router_port > +echo "---------------------" > + > +echo "---------SB dump-----" > +ovn-sbctl list datapath_binding > +echo "---------------------" > +ovn-sbctl list port_binding > +echo "---------------------" > + > +echo "------ hv1 dump ----------" > +as hv1 ovs-ofctl show br-int > +as hv1 ovs-ofctl dump-flows br-int > +echo "------ hv2 dump ----------" > +as hv2 ovs-ofctl show br-int > +as hv2 ovs-ofctl dump-flows br-int > + > +# Packet to Expect > +# The TTL should be decremented by 2. > +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && > + ip4 && ip.ttl==62 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +echo $packet | ovstest test-ovn expr-to-packets > expected > + > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "reg0 == 172.16.1.2" | wc -l], [0], [1 > +]) > + > +# Disable the ls2-lp1 port. > +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "reg0 == 172.16.1.2" | wc -l], [0], [0 > +]) > + > +# Generate the packet destined for ls2-lp1 and it should not be delivered. > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > + > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > +# The 2nd packet sent shound not be received. > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +OVN_CLEANUP([hv1],[hv2]) > + > +AT_CLEANUP > +]) > + > +OVN_FOR_EACH_NORTHD([ > +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, LRs connected via LS, IPv4 over IPv6, ECMP]) > +ovn_start > + > +# Logical network: > +# Two LRs - R1 and R2 that are connected to ls-transfer1 and lr-transfer2 in > +# 2001:db8:1::/64 and 2001:db8:2::/64 > +# network. R1 has a switchs ls1 (192.168.1.0/24) connected to it. > +# R2 has ls2 (172.16.1.0/24) connected to it. > + > +ls1_lp1_mac="f0:00:00:01:02:03" > +rp_ls1_mac="00:00:00:01:02:03" > +rp_ls2_mac="00:00:00:01:02:04" > +ls2_lp1_mac="f0:00:00:01:02:04" > + > +ls1_lp1_ip="192.168.1.2" > +ls2_lp1_ip="172.16.1.2" > + > +ovn-nbctl lr-add R1 > +ovn-nbctl lr-add R2 > + > +ovn-nbctl ls-add ls1 > +ovn-nbctl ls-add ls2 > +ovn-nbctl ls-add ls-transfer1 > +ovn-nbctl ls-add ls-transfer2 > + > +# Connect ls1 to R1 > +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 192.168.1.1/24 > + > +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ > + options:router-port=ls1 addresses=\"$rp_ls1_mac\" > + > +# Connect ls2 to R2 > +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 172.16.1.1/24 > + > +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ > + options:router-port=ls2 addresses=\"$rp_ls2_mac\" > + > +# Connect R1 to R2 (ls-transfer1) > +ovn-nbctl lrp-add R1 R1_ls-transfer1 00:00:00:02:03:04 2001:db8:1::1/64 > +ovn-nbctl lrp-add R2 R2_ls-transfer1 00:00:00:02:03:05 2001:db8:1::2/64 > + > +ovn-nbctl lsp-add ls-transfer1 ls-transfer1_r1 -- \ > + set Logical_Switch_Port ls-transfer1_r1 type=router \ > + options:router-port=R1_ls-transfer1 addresses=\"router\" > +ovn-nbctl lsp-add ls-transfer1 ls-transfer1_r2 -- \ > + set Logical_Switch_Port ls-transfer1_r2 type=router \ > + options:router-port=R2_ls-transfer1 addresses=\"router\" > + > +# Connect R1 to R2 (ls-transfer2) > +ovn-nbctl lrp-add R1 R1_ls-transfer2 00:00:00:02:03:14 2001:db8:2::1/64 > +ovn-nbctl lrp-add R2 R2_ls-transfer2 00:00:00:02:03:15 2001:db8:2::2/64 > + > +ovn-nbctl lsp-add ls-transfer2 ls-transfer2_r1 -- \ > + set Logical_Switch_Port ls-transfer2_r1 type=router \ > + options:router-port=R1_ls-transfer2 addresses=\"router\" > +ovn-nbctl lsp-add ls-transfer2 ls-transfer2_r2 -- \ > + set Logical_Switch_Port ls-transfer2_r2 type=router \ > + options:router-port=R2_ls-transfer2 addresses=\"router\" > + > +AT_CHECK([ovn-nbctl lr-route-add R1 "0.0.0.0/0" 2001:db8:1::2]) > +AT_CHECK([ovn-nbctl --ecmp lr-route-add R1 "0.0.0.0/0" 2001:db8:2::2]) > +AT_CHECK([ovn-nbctl lr-route-add R2 "0.0.0.0/0" 2001:db8:1::1]) > +AT_CHECK([ovn-nbctl --ecmp lr-route-add R2 "0.0.0.0/0" 2001:db8:2::1]) > + > +# Create logical port ls1-lp1 in ls1 > +ovn-nbctl lsp-add ls1 ls1-lp1 \ > +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" > + > +# Create logical port ls2-lp1 in ls2 > +ovn-nbctl lsp-add ls2 ls2-lp1 \ > +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" > + > +# Create two hypervisor and create OVS ports corresponding to logical ports. > +net_add n1 > + > +sim_add hv1 > +as hv1 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.1 > +ovs-vsctl -- add-port br-int hv1-vif1 -- \ > + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ > + options:tx_pcap=hv1/vif1-tx.pcap \ > + options:rxq_pcap=hv1/vif1-rx.pcap \ > + ofport-request=1 > + > +sim_add hv2 > +as hv2 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.2 > +ovs-vsctl -- add-port br-int hv2-vif1 -- \ > + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ > + options:tx_pcap=hv2/vif1-tx.pcap \ > + options:rxq_pcap=hv2/vif1-rx.pcap \ > + ofport-request=1 > + > + > +# Pre-populate the hypervisors' ARP tables so that we don't lose any > +# packets for ARP resolution (native tunneling doesn't queue packets > +# for ARP resolution). > +OVN_POPULATE_ARP > + > +# Allow some time for ovn-northd and ovn-controller to catch up. > +wait_for_ports_up > +check ovn-nbctl --wait=hv sync > + > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > + > + > +echo "---------NB dump-----" > +ovn-nbctl show > +echo "---------------------" > +ovn-nbctl list logical_router > +echo "---------------------" > +ovn-nbctl list logical_router_port > +echo "---------------------" > + > +echo "---------SB dump-----" > +ovn-sbctl list datapath_binding > +echo "---------------------" > +ovn-sbctl list port_binding > +echo "---------------------" > + > +echo "------ hv1 dump ----------" > +as hv1 ovs-ofctl show br-int > +as hv1 ovs-ofctl dump-flows br-int > +echo "------ hv2 dump ----------" > +as hv2 ovs-ofctl show br-int > +as hv2 ovs-ofctl dump-flows br-int > + > +# Packet to Expect > +# The TTL should be decremented by 2. > +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && > + ip4 && ip.ttl==62 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +echo $packet | ovstest test-ovn expr-to-packets > expected > + > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "reg0 == 172.16.1.2" | wc -l], [0], [1 > +]) > + > +# Disable the ls2-lp1 port. > +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "reg0 == 172.16.1.2" | wc -l], [0], [0 > +]) > + > +# Generate the packet destined for ls2-lp1 and it should not be delivered. > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > + > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > +# The 2nd packet sent shound not be received. > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +OVN_CLEANUP([hv1],[hv2]) > + > +AT_CLEANUP > +]) > + > +OVN_FOR_EACH_NORTHD([ > +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, 2 peer LRs, IPv6 over IPv4]) > +ovn_start > + > +# Logical network: > +# Two LRs - R1 and R2 that are connected to each other as peers in 10.0.0.0/24 > +# network. R1 has a switchs ls1 (2001:db8:1::/64) connected to it. > +# R2 has ls2 (2001:db8:2::/64) connected to it. > + > +ls1_lp1_mac="f0:00:00:01:02:03" > +rp_ls1_mac="00:00:00:01:02:03" > +rp_ls2_mac="00:00:00:01:02:04" > +ls2_lp1_mac="f0:00:00:01:02:04" > + > +ls1_lp1_ip="2001:db8:1::2" > +ls2_lp1_ip="2001:db8:2::2" > + > +ovn-nbctl lr-add R1 > +ovn-nbctl lr-add R2 > + > +ovn-nbctl ls-add ls1 > +ovn-nbctl ls-add ls2 > + > +# Connect ls1 to R1 > +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 2001:db8:1::1/64 > + > +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ > + options:router-port=ls1 addresses=\"$rp_ls1_mac\" > + > +# Connect ls2 to R2 > +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 2001:db8:2::1/64 > + > +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ > + options:router-port=ls2 addresses=\"$rp_ls2_mac\" > + > +# Connect R1 to R2 > +ovn-nbctl lrp-add R1 R1_R2 00:00:00:02:03:04 10.0.0.1/24 peer=R2_R1 > +ovn-nbctl lrp-add R2 R2_R1 00:00:00:02:03:05 10.0.0.2/24 peer=R1_R2 > + > +AT_CHECK([ovn-nbctl lr-route-add R1 "::/0" 10.0.0.2]) > +AT_CHECK([ovn-nbctl lr-route-add R2 "::/0" 10.0.0.1]) > + > +# Create logical port ls1-lp1 in ls1 > +ovn-nbctl lsp-add ls1 ls1-lp1 \ > +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" > + > +# Create logical port ls2-lp1 in ls2 > +ovn-nbctl lsp-add ls2 ls2-lp1 \ > +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" > + > +# Create two hypervisor and create OVS ports corresponding to logical ports. > +net_add n1 > + > +sim_add hv1 > +as hv1 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.1 > +ovs-vsctl -- add-port br-int hv1-vif1 -- \ > + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ > + options:tx_pcap=hv1/vif1-tx.pcap \ > + options:rxq_pcap=hv1/vif1-rx.pcap \ > + ofport-request=1 > + > +sim_add hv2 > +as hv2 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.2 > +ovs-vsctl -- add-port br-int hv2-vif1 -- \ > + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ > + options:tx_pcap=hv2/vif1-tx.pcap \ > + options:rxq_pcap=hv2/vif1-rx.pcap \ > + ofport-request=1 > + > + > +# Pre-populate the hypervisors' ARP tables so that we don't lose any > +# packets for ARP resolution (native tunneling doesn't queue packets > +# for ARP resolution). > +OVN_POPULATE_ARP > + > +# Allow some time for ovn-northd and ovn-controller to catch up. > +wait_for_ports_up > +check ovn-nbctl --wait=hv sync > + > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip6 && ip.ttl==64 && ip6.src==$ls1_lp1_ip && ip6.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > + > + > +echo "---------NB dump-----" > +ovn-nbctl show > +echo "---------------------" > +ovn-nbctl list logical_router > +echo "---------------------" > +ovn-nbctl list logical_router_port > +echo "---------------------" > + > +echo "---------SB dump-----" > +ovn-sbctl list datapath_binding > +echo "---------------------" > +ovn-sbctl list port_binding > +echo "---------------------" > + > +echo "------ hv1 dump ----------" > +as hv1 ovs-ofctl show br-int > +as hv1 ovs-ofctl dump-flows br-int > +echo "------ hv2 dump ----------" > +as hv2 ovs-ofctl show br-int > +as hv2 ovs-ofctl dump-flows br-int > + > +# Packet to Expect > +# The TTL should be decremented by 2. > +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && > + ip6 && ip.ttl==62 && ip6.src==$ls1_lp1_ip && ip6.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > +echo $packet | ovstest test-ovn expr-to-packets > expected > + > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "xxreg0 == 2001:db8:2::2" | wc -l], [0], [1 > +]) > + > +# Disable the ls2-lp1 port. > +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false > + > +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ > +grep "xxreg0 == 2001:db8:2::2" | wc -l], [0], [0 > +]) > + > +# Generate the packet destined for ls2-lp1 and it should not be delivered. > +# Packet to send. > +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && > + ip6 && ip.ttl==64 && ip6.src==$ls1_lp1_ip && ip6.dst==$ls2_lp1_ip && > + udp && udp.src==53 && udp.dst==4369" > + > +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) > +# The 2nd packet sent shound not be received. > +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) > + > +OVN_CLEANUP([hv1],[hv2]) > + > +AT_CLEANUP > +]) > diff --git a/utilities/ovn-nbctl.c b/utilities/ovn-nbctl.c > index 25eb86f7f..f827b2ad9 100644 > --- a/utilities/ovn-nbctl.c > +++ b/utilities/ovn-nbctl.c > @@ -4546,11 +4546,9 @@ nbctl_lr_route_add(struct ctl_context *ctx) > } > > char *route_table = shash_find_data(&ctx->options, "--route-table"); > - bool v6_prefix = false; > prefix = normalize_ipv4_prefix_str(ctx->argv[2]); > if (!prefix) { > prefix = normalize_ipv6_prefix_str(ctx->argv[2]); > - v6_prefix = true; > } > if (!prefix) { > ctl_error(ctx, "bad prefix argument: %s", ctx->argv[2]); > @@ -4561,15 +4559,15 @@ nbctl_lr_route_add(struct ctl_context *ctx) > if (is_discard_route) { > next_hop = xasprintf("discard"); > } else { > - next_hop = v6_prefix > - ? normalize_ipv6_addr_str(ctx->argv[3]) > - : normalize_ipv4_addr_str(ctx->argv[3]); > + next_hop = normalize_ipv4_addr_str(ctx->argv[3]); > + if (!next_hop) { > + next_hop = normalize_ipv6_addr_str(ctx->argv[3]); > + } > if (!next_hop) { > /* check if it is a output port. */ > error = lrp_by_name_or_uuid(ctx, ctx->argv[3], true, &out_lrp); > if (error) { > - ctl_error(ctx, "bad %s nexthop argument: %s", > - v6_prefix ? "IPv6" : "IPv4", ctx->argv[3]); > + ctl_error(ctx, "bad nexthop argument: %s", ctx->argv[3]); > free(error); > goto cleanup; > } > > base-commit: dc52bf70cb7e066fdb84d88622d7f380eda18e8c Regards, Dumitru
On Fri, Apr 19, 2024 at 09:53:13AM +0200, Dumitru Ceara wrote: > On 3/27/24 09:43, Felix Huettner via dev wrote: > > In most cases IPv4 packets are routed only over other IPv4 networks and > > IPv6 packets are routed only over IPv6 networks. However there is no > > interent reason for this limitation. Routing IPv4 packets over IPv6 > > networks just requires the router to contain a route for an IPv4 network > > with an IPv6 nexthop. > > > > This was previously prevented in OVN in ovn-nbctl and northd. By > > removing these filters the forwarding will work if the mac addresses are > > prepopulated. > > > > If the mac addresses are not prepopulated we will attempt to resolve them using > > the original address family of the packet and not the address family of the > > nexthop. This will fail and we will not forward the packet. > > > > This feature can for example be used by service providers to > > interconnect multiple IPv4 networks of a customer without needing to > > negotiate free IPv4 addresses by just using any IPv6 address. > > > > Signed-off-by: Felix Huettner <felix.huettner@mail.schwarz> > > --- > > Hi Felix, > > Thanks for the patch! It's a very useful addition to the OVN feature > set. The code looks mostly OK to me, I only had some minor comments, > please see below. > Hi Dumitru, thanks for the review. They will be addressed in v2 Thanks
diff --git a/NEWS b/NEWS index 4d6ebea89..b419b2628 100644 --- a/NEWS +++ b/NEWS @@ -12,6 +12,10 @@ Post v24.03.0 flow table id. "lflow-stage-to-oftable STAGE_NAME" that converts stage name into OpenFlow table id. + - Allow Static Routes where the address families of ip_prefix and nexthop + diverge (e.g. IPv4 packets over IPv6 links). This is currently limited to + nexthops that have their mac addresses prepopulated (so + dynamic_neigh_routers must be false). OVN v24.03.0 - 01 Mar 2024 -------------------------- diff --git a/northd/northd.c b/northd/northd.c index 1839b7d8b..0359cde89 100644 --- a/northd/northd.c +++ b/northd/northd.c @@ -10238,18 +10238,6 @@ parsed_routes_add(struct ovn_datapath *od, const struct hmap *lr_ports, return NULL; } - /* Verify that ip_prefix and nexthop have same address familiy. */ - if (valid_nexthop) { - if (IN6_IS_ADDR_V4MAPPED(&prefix) != IN6_IS_ADDR_V4MAPPED(&nexthop)) { - static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1); - VLOG_WARN_RL(&rl, "Address family doesn't match between 'ip_prefix'" - " %s and 'nexthop' %s in static route "UUID_FMT, - route->ip_prefix, route->nexthop, - UUID_ARGS(&route->header_.uuid)); - return NULL; - } - } - /* Verify that ip_prefix and nexthop are on the same network. */ if (!is_discard_route && !find_static_route_outport(od, lr_ports, route, @@ -10666,7 +10654,7 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, struct lflow_ref *lflow_ref) { - bool is_ipv4 = IN6_IS_ADDR_V4MAPPED(&eg->prefix); + bool is_ipv4_network = IN6_IS_ADDR_V4MAPPED(&eg->prefix); uint16_t priority; struct ecmp_route_list_node *er; struct ds route_match = DS_EMPTY_INITIALIZER; @@ -10675,7 +10663,8 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, int ofs = !strcmp(eg->origin, ROUTE_ORIGIN_CONNECTED) ? ROUTE_PRIO_OFFSET_CONNECTED: ROUTE_PRIO_OFFSET_STATIC; build_route_match(NULL, eg->route_table_id, prefix_s, eg->plen, - eg->is_src_route, is_ipv4, &route_match, &priority, ofs); + eg->is_src_route, is_ipv4_network, &route_match, + &priority, ofs); free(prefix_s); struct ds actions = DS_EMPTY_INITIALIZER; @@ -10708,7 +10697,11 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, /* Find the outgoing port. */ const char *lrp_addr_s = NULL; struct ovn_port *out_port = NULL; - if (!find_static_route_outport(od, lr_ports, route, is_ipv4, + bool is_ipv4_gateway = is_ipv4_network; + if (route->nexthop && route->nexthop[0]) { + is_ipv4_gateway = strchr(route->nexthop, '.') ? true : false; + } + if (!find_static_route_outport(od, lr_ports, route, is_ipv4_gateway, &lrp_addr_s, &out_port)) { continue; } @@ -10733,9 +10726,9 @@ build_ecmp_route_flow(struct lflow_table *lflows, struct ovn_datapath *od, "eth.src = %s; " "outport = %s; " "next;", - is_ipv4 ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6, + is_ipv4_gateway ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6, route->nexthop, - is_ipv4 ? REG_SRC_IPV4 : REG_SRC_IPV6, + is_ipv4_gateway ? REG_SRC_IPV4 : REG_SRC_IPV6, lrp_addr_s, out_port->lrp_networks.ea_s, out_port->json_key); @@ -10757,13 +10750,18 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, const struct ovsdb_idl_row *stage_hint, bool is_discard_route, int ofs, struct lflow_ref *lflow_ref) { - bool is_ipv4 = strchr(network_s, '.') ? true : false; + bool is_ipv4_network = strchr(network_s, '.') ? true : false; + bool is_ipv4_gateway = is_ipv4_network; struct ds match = DS_EMPTY_INITIALIZER; uint16_t priority; const struct ovn_port *op_inport = NULL; + if (gateway && gateway[0]) { + is_ipv4_gateway = strchr(gateway, '.') ? true : false; + } + /* IPv6 link-local addresses must be scoped to the local router port. */ - if (!is_ipv4) { + if (!is_ipv4_network) { struct in6_addr network; ovs_assert(ipv6_parse(network_s, &network)); if (in6_is_lla(&network)) { @@ -10771,7 +10769,7 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, } } build_route_match(op_inport, rtb_id, network_s, plen, is_src_route, - is_ipv4, &match, &priority, ofs); + is_ipv4_network, &match, &priority, ofs); struct ds common_actions = DS_EMPTY_INITIALIZER; struct ds actions = DS_EMPTY_INITIALIZER; @@ -10779,11 +10777,12 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, ds_put_cstr(&actions, debug_drop_action()); } else { ds_put_format(&common_actions, REG_ECMP_GROUP_ID" = 0; %s = ", - is_ipv4 ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6); + is_ipv4_gateway ? REG_NEXT_HOP_IPV4 : REG_NEXT_HOP_IPV6); if (gateway && gateway[0]) { ds_put_cstr(&common_actions, gateway); } else { - ds_put_format(&common_actions, "ip%s.dst", is_ipv4 ? "4" : "6"); + ds_put_format(&common_actions, "ip%s.dst", + is_ipv4_network ? "4" : "6"); } ds_put_format(&common_actions, "; " "%s = %s; " @@ -10791,7 +10790,7 @@ add_route(struct lflow_table *lflows, struct ovn_datapath *od, "outport = %s; " "flags.loopback = 1; " "next;", - is_ipv4 ? REG_SRC_IPV4 : REG_SRC_IPV6, + is_ipv4_gateway ? REG_SRC_IPV4 : REG_SRC_IPV6, lrp_addr_s, op->lrp_networks.ea_s, op->json_key); diff --git a/tests/ovn-nbctl.at b/tests/ovn-nbctl.at index 5248e6c76..60dcdc9be 100644 --- a/tests/ovn-nbctl.at +++ b/tests/ovn-nbctl.at @@ -1757,7 +1757,7 @@ AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.1/24 11.0.0.2]) AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.10.0/24 lp0]) AT_CHECK([ovn-nbctl --bfd lr-route-add lr0 10.0.20.0/24 11.0.2.1 lp0]) AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.10.0/24 lp1], [1], [], - [ovn-nbctl: bad IPv4 nexthop argument: lp1 + [ovn-nbctl: bad nexthop argument: lp1 ]) dnl Add overlapping route with 10.0.0.1/24 @@ -1771,13 +1771,13 @@ AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.111/24a 11.0.0.1], [1], [], [ovn-nbctl: bad prefix argument: 10.0.0.111/24a ]) AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.111/24 11.0.0.1a], [1], [], - [ovn-nbctl: bad IPv4 nexthop argument: 11.0.0.1a + [ovn-nbctl: bad nexthop argument: 11.0.0.1a ]) AT_CHECK([ovn-nbctl lr-route-add lr0 10.0.0.111/24 11.0.0.1/24], [1], [], - [ovn-nbctl: bad IPv4 nexthop argument: 11.0.0.1/24 + [ovn-nbctl: bad nexthop argument: 11.0.0.1/24 ]) AT_CHECK([ovn-nbctl lr-route-add lr0 2001:0db8:1::/64 2001:0db8:0:f103::1/64], [1], [], - [ovn-nbctl: bad IPv6 nexthop argument: 2001:0db8:0:f103::1/64 + [ovn-nbctl: bad nexthop argument: 2001:0db8:0:f103::1/64 ]) AT_CHECK([ovn-nbctl --ecmp lr-route-add lr0 20.0.0.0/24 discard], [1], [], [ovn-nbctl: ecmp is not valid for discard routes. diff --git a/tests/ovn.at b/tests/ovn.at index 4d0c7ad53..8818d0db9 100644 --- a/tests/ovn.at +++ b/tests/ovn.at @@ -38475,3 +38475,618 @@ OVS_WAIT_FOR_OUTPUT([as hv1 ovs-ofctl dump-flows br-int table=0 |grep priority=1 OVN_CLEANUP([hv1]) AT_CLEANUP ]) + +OVN_FOR_EACH_NORTHD([ +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, 2 peer LRs, IPv4 over IPv6]) +ovn_start + +# Logical network: +# Two LRs - R1 and R2 that are connected to each other as peers in 2001:db8::/64 +# network. R1 has a switchs ls1 (192.168.1.0/24) connected to it. +# R2 has ls2 (172.16.1.0/24) connected to it. + +ls1_lp1_mac="f0:00:00:01:02:03" +rp_ls1_mac="00:00:00:01:02:03" +rp_ls2_mac="00:00:00:01:02:04" +ls2_lp1_mac="f0:00:00:01:02:04" + +ls1_lp1_ip="192.168.1.2" +ls2_lp1_ip="172.16.1.2" + +ovn-nbctl lr-add R1 +ovn-nbctl lr-add R2 + +ovn-nbctl ls-add ls1 +ovn-nbctl ls-add ls2 + +# Connect ls1 to R1 +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 192.168.1.1/24 + +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ + options:router-port=ls1 addresses=\"$rp_ls1_mac\" + +# Connect ls2 to R2 +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 172.16.1.1/24 + +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ + options:router-port=ls2 addresses=\"$rp_ls2_mac\" + +# Connect R1 to R2 +ovn-nbctl lrp-add R1 R1_R2 00:00:00:02:03:04 2001:db8::1/64 peer=R2_R1 +ovn-nbctl lrp-add R2 R2_R1 00:00:00:02:03:05 2001:db8::2/64 peer=R1_R2 + +AT_CHECK([ovn-nbctl lr-route-add R1 "0.0.0.0/0" 2001:db8::2]) +AT_CHECK([ovn-nbctl lr-route-add R2 "0.0.0.0/0" 2001:db8::1]) + +# Create logical port ls1-lp1 in ls1 +ovn-nbctl lsp-add ls1 ls1-lp1 \ +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" + +# Create logical port ls2-lp1 in ls2 +ovn-nbctl lsp-add ls2 ls2-lp1 \ +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" + +# Create two hypervisor and create OVS ports corresponding to logical ports. +net_add n1 + +sim_add hv1 +as hv1 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.1 +ovs-vsctl -- add-port br-int hv1-vif1 -- \ + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ + options:tx_pcap=hv1/vif1-tx.pcap \ + options:rxq_pcap=hv1/vif1-rx.pcap \ + ofport-request=1 + +sim_add hv2 +as hv2 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.2 +ovs-vsctl -- add-port br-int hv2-vif1 -- \ + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ + options:tx_pcap=hv2/vif1-tx.pcap \ + options:rxq_pcap=hv2/vif1-rx.pcap \ + ofport-request=1 + + +# Pre-populate the hypervisors' ARP tables so that we don't lose any +# packets for ARP resolution (native tunneling doesn't queue packets +# for ARP resolution). +OVN_POPULATE_ARP + +# Allow some time for ovn-northd and ovn-controller to catch up. +wait_for_ports_up +check ovn-nbctl --wait=hv sync + +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) + + +echo "---------NB dump-----" +ovn-nbctl show +echo "---------------------" +ovn-nbctl list logical_router +echo "---------------------" +ovn-nbctl list logical_router_port +echo "---------------------" + +echo "---------SB dump-----" +ovn-sbctl list datapath_binding +echo "---------------------" +ovn-sbctl list port_binding +echo "---------------------" + +echo "------ hv1 dump ----------" +as hv1 ovs-ofctl show br-int +as hv1 ovs-ofctl dump-flows br-int +echo "------ hv2 dump ----------" +as hv2 ovs-ofctl show br-int +as hv2 ovs-ofctl dump-flows br-int + +# Packet to Expect +# The TTL should be decremented by 2. +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && + ip4 && ip.ttl==62 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +echo $packet | ovstest test-ovn expr-to-packets > expected + +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "reg0 == 172.16.1.2" | wc -l], [0], [1 +]) + +# Disable the ls2-lp1 port. +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "reg0 == 172.16.1.2" | wc -l], [0], [0 +]) + +# Generate the packet destined for ls2-lp1 and it should not be delivered. +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" + +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) +# The 2nd packet sent shound not be received. +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +OVN_CLEANUP([hv1],[hv2]) + +AT_CLEANUP +]) + +OVN_FOR_EACH_NORTHD([ +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, LRs connected via LS, IPv4 over IPv6]) +ovn_start + +# Logical network: +# Two LRs - R1 and R2 that are connected to ls-transfer in 2001:db8::/64 +# network. R1 has a switchs ls1 (192.168.1.0/24) connected to it. +# R2 has ls2 (172.16.1.0/24) connected to it. + +ls1_lp1_mac="f0:00:00:01:02:03" +rp_ls1_mac="00:00:00:01:02:03" +rp_ls2_mac="00:00:00:01:02:04" +ls2_lp1_mac="f0:00:00:01:02:04" + +ls1_lp1_ip="192.168.1.2" +ls2_lp1_ip="172.16.1.2" + +ovn-nbctl lr-add R1 +ovn-nbctl lr-add R2 + +ovn-nbctl ls-add ls1 +ovn-nbctl ls-add ls2 +ovn-nbctl ls-add ls-transfer + +# Connect ls1 to R1 +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 192.168.1.1/24 + +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ + options:router-port=ls1 addresses=\"$rp_ls1_mac\" + +# Connect ls2 to R2 +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 172.16.1.1/24 + +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ + options:router-port=ls2 addresses=\"$rp_ls2_mac\" + +# Connect R1 to R2 +ovn-nbctl lrp-add R1 R1_ls-transfer 00:00:00:02:03:04 2001:db8::1/64 +ovn-nbctl lrp-add R2 R2_ls-transfer 00:00:00:02:03:05 2001:db8::2/64 + +ovn-nbctl lsp-add ls-transfer ls-transfer_r1 -- \ + set Logical_Switch_Port ls-transfer_r1 type=router \ + options:router-port=R1_ls-transfer addresses=\"router\" +ovn-nbctl lsp-add ls-transfer ls-transfer_r2 -- \ + set Logical_Switch_Port ls-transfer_r2 type=router \ + options:router-port=R2_ls-transfer addresses=\"router\" + +AT_CHECK([ovn-nbctl lr-route-add R1 "0.0.0.0/0" 2001:db8::2]) +AT_CHECK([ovn-nbctl lr-route-add R2 "0.0.0.0/0" 2001:db8::1]) + +# Create logical port ls1-lp1 in ls1 +ovn-nbctl lsp-add ls1 ls1-lp1 \ +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" + +# Create logical port ls2-lp1 in ls2 +ovn-nbctl lsp-add ls2 ls2-lp1 \ +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" + +# Create two hypervisor and create OVS ports corresponding to logical ports. +net_add n1 + +sim_add hv1 +as hv1 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.1 +ovs-vsctl -- add-port br-int hv1-vif1 -- \ + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ + options:tx_pcap=hv1/vif1-tx.pcap \ + options:rxq_pcap=hv1/vif1-rx.pcap \ + ofport-request=1 + +sim_add hv2 +as hv2 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.2 +ovs-vsctl -- add-port br-int hv2-vif1 -- \ + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ + options:tx_pcap=hv2/vif1-tx.pcap \ + options:rxq_pcap=hv2/vif1-rx.pcap \ + ofport-request=1 + + +# Pre-populate the hypervisors' ARP tables so that we don't lose any +# packets for ARP resolution (native tunneling doesn't queue packets +# for ARP resolution). +OVN_POPULATE_ARP + +# Allow some time for ovn-northd and ovn-controller to catch up. +wait_for_ports_up +check ovn-nbctl --wait=hv sync + +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) + + +echo "---------NB dump-----" +ovn-nbctl show +echo "---------------------" +ovn-nbctl list logical_router +echo "---------------------" +ovn-nbctl list logical_router_port +echo "---------------------" + +echo "---------SB dump-----" +ovn-sbctl list datapath_binding +echo "---------------------" +ovn-sbctl list port_binding +echo "---------------------" + +echo "------ hv1 dump ----------" +as hv1 ovs-ofctl show br-int +as hv1 ovs-ofctl dump-flows br-int +echo "------ hv2 dump ----------" +as hv2 ovs-ofctl show br-int +as hv2 ovs-ofctl dump-flows br-int + +# Packet to Expect +# The TTL should be decremented by 2. +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && + ip4 && ip.ttl==62 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +echo $packet | ovstest test-ovn expr-to-packets > expected + +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "reg0 == 172.16.1.2" | wc -l], [0], [1 +]) + +# Disable the ls2-lp1 port. +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "reg0 == 172.16.1.2" | wc -l], [0], [0 +]) + +# Generate the packet destined for ls2-lp1 and it should not be delivered. +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" + +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) +# The 2nd packet sent shound not be received. +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +OVN_CLEANUP([hv1],[hv2]) + +AT_CLEANUP +]) + +OVN_FOR_EACH_NORTHD([ +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, LRs connected via LS, IPv4 over IPv6, ECMP]) +ovn_start + +# Logical network: +# Two LRs - R1 and R2 that are connected to ls-transfer1 and lr-transfer2 in +# 2001:db8:1::/64 and 2001:db8:2::/64 +# network. R1 has a switchs ls1 (192.168.1.0/24) connected to it. +# R2 has ls2 (172.16.1.0/24) connected to it. + +ls1_lp1_mac="f0:00:00:01:02:03" +rp_ls1_mac="00:00:00:01:02:03" +rp_ls2_mac="00:00:00:01:02:04" +ls2_lp1_mac="f0:00:00:01:02:04" + +ls1_lp1_ip="192.168.1.2" +ls2_lp1_ip="172.16.1.2" + +ovn-nbctl lr-add R1 +ovn-nbctl lr-add R2 + +ovn-nbctl ls-add ls1 +ovn-nbctl ls-add ls2 +ovn-nbctl ls-add ls-transfer1 +ovn-nbctl ls-add ls-transfer2 + +# Connect ls1 to R1 +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 192.168.1.1/24 + +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ + options:router-port=ls1 addresses=\"$rp_ls1_mac\" + +# Connect ls2 to R2 +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 172.16.1.1/24 + +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ + options:router-port=ls2 addresses=\"$rp_ls2_mac\" + +# Connect R1 to R2 (ls-transfer1) +ovn-nbctl lrp-add R1 R1_ls-transfer1 00:00:00:02:03:04 2001:db8:1::1/64 +ovn-nbctl lrp-add R2 R2_ls-transfer1 00:00:00:02:03:05 2001:db8:1::2/64 + +ovn-nbctl lsp-add ls-transfer1 ls-transfer1_r1 -- \ + set Logical_Switch_Port ls-transfer1_r1 type=router \ + options:router-port=R1_ls-transfer1 addresses=\"router\" +ovn-nbctl lsp-add ls-transfer1 ls-transfer1_r2 -- \ + set Logical_Switch_Port ls-transfer1_r2 type=router \ + options:router-port=R2_ls-transfer1 addresses=\"router\" + +# Connect R1 to R2 (ls-transfer2) +ovn-nbctl lrp-add R1 R1_ls-transfer2 00:00:00:02:03:14 2001:db8:2::1/64 +ovn-nbctl lrp-add R2 R2_ls-transfer2 00:00:00:02:03:15 2001:db8:2::2/64 + +ovn-nbctl lsp-add ls-transfer2 ls-transfer2_r1 -- \ + set Logical_Switch_Port ls-transfer2_r1 type=router \ + options:router-port=R1_ls-transfer2 addresses=\"router\" +ovn-nbctl lsp-add ls-transfer2 ls-transfer2_r2 -- \ + set Logical_Switch_Port ls-transfer2_r2 type=router \ + options:router-port=R2_ls-transfer2 addresses=\"router\" + +AT_CHECK([ovn-nbctl lr-route-add R1 "0.0.0.0/0" 2001:db8:1::2]) +AT_CHECK([ovn-nbctl --ecmp lr-route-add R1 "0.0.0.0/0" 2001:db8:2::2]) +AT_CHECK([ovn-nbctl lr-route-add R2 "0.0.0.0/0" 2001:db8:1::1]) +AT_CHECK([ovn-nbctl --ecmp lr-route-add R2 "0.0.0.0/0" 2001:db8:2::1]) + +# Create logical port ls1-lp1 in ls1 +ovn-nbctl lsp-add ls1 ls1-lp1 \ +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" + +# Create logical port ls2-lp1 in ls2 +ovn-nbctl lsp-add ls2 ls2-lp1 \ +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" + +# Create two hypervisor and create OVS ports corresponding to logical ports. +net_add n1 + +sim_add hv1 +as hv1 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.1 +ovs-vsctl -- add-port br-int hv1-vif1 -- \ + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ + options:tx_pcap=hv1/vif1-tx.pcap \ + options:rxq_pcap=hv1/vif1-rx.pcap \ + ofport-request=1 + +sim_add hv2 +as hv2 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.2 +ovs-vsctl -- add-port br-int hv2-vif1 -- \ + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ + options:tx_pcap=hv2/vif1-tx.pcap \ + options:rxq_pcap=hv2/vif1-rx.pcap \ + ofport-request=1 + + +# Pre-populate the hypervisors' ARP tables so that we don't lose any +# packets for ARP resolution (native tunneling doesn't queue packets +# for ARP resolution). +OVN_POPULATE_ARP + +# Allow some time for ovn-northd and ovn-controller to catch up. +wait_for_ports_up +check ovn-nbctl --wait=hv sync + +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) + + +echo "---------NB dump-----" +ovn-nbctl show +echo "---------------------" +ovn-nbctl list logical_router +echo "---------------------" +ovn-nbctl list logical_router_port +echo "---------------------" + +echo "---------SB dump-----" +ovn-sbctl list datapath_binding +echo "---------------------" +ovn-sbctl list port_binding +echo "---------------------" + +echo "------ hv1 dump ----------" +as hv1 ovs-ofctl show br-int +as hv1 ovs-ofctl dump-flows br-int +echo "------ hv2 dump ----------" +as hv2 ovs-ofctl show br-int +as hv2 ovs-ofctl dump-flows br-int + +# Packet to Expect +# The TTL should be decremented by 2. +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && + ip4 && ip.ttl==62 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +echo $packet | ovstest test-ovn expr-to-packets > expected + +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "reg0 == 172.16.1.2" | wc -l], [0], [1 +]) + +# Disable the ls2-lp1 port. +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "reg0 == 172.16.1.2" | wc -l], [0], [0 +]) + +# Generate the packet destined for ls2-lp1 and it should not be delivered. +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip4 && ip.ttl==64 && ip4.src==$ls1_lp1_ip && ip4.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" + +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) +# The 2nd packet sent shound not be received. +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +OVN_CLEANUP([hv1],[hv2]) + +AT_CLEANUP +]) + +OVN_FOR_EACH_NORTHD([ +AT_SETUP([2 HVs, 2 LS, 1 lport/LS, 2 peer LRs, IPv6 over IPv4]) +ovn_start + +# Logical network: +# Two LRs - R1 and R2 that are connected to each other as peers in 10.0.0.0/24 +# network. R1 has a switchs ls1 (2001:db8:1::/64) connected to it. +# R2 has ls2 (2001:db8:2::/64) connected to it. + +ls1_lp1_mac="f0:00:00:01:02:03" +rp_ls1_mac="00:00:00:01:02:03" +rp_ls2_mac="00:00:00:01:02:04" +ls2_lp1_mac="f0:00:00:01:02:04" + +ls1_lp1_ip="2001:db8:1::2" +ls2_lp1_ip="2001:db8:2::2" + +ovn-nbctl lr-add R1 +ovn-nbctl lr-add R2 + +ovn-nbctl ls-add ls1 +ovn-nbctl ls-add ls2 + +# Connect ls1 to R1 +ovn-nbctl lrp-add R1 ls1 $rp_ls1_mac 2001:db8:1::1/64 + +ovn-nbctl lsp-add ls1 rp-ls1 -- set Logical_Switch_Port rp-ls1 type=router \ + options:router-port=ls1 addresses=\"$rp_ls1_mac\" + +# Connect ls2 to R2 +ovn-nbctl lrp-add R2 ls2 $rp_ls2_mac 2001:db8:2::1/64 + +ovn-nbctl lsp-add ls2 rp-ls2 -- set Logical_Switch_Port rp-ls2 type=router \ + options:router-port=ls2 addresses=\"$rp_ls2_mac\" + +# Connect R1 to R2 +ovn-nbctl lrp-add R1 R1_R2 00:00:00:02:03:04 10.0.0.1/24 peer=R2_R1 +ovn-nbctl lrp-add R2 R2_R1 00:00:00:02:03:05 10.0.0.2/24 peer=R1_R2 + +AT_CHECK([ovn-nbctl lr-route-add R1 "::/0" 10.0.0.2]) +AT_CHECK([ovn-nbctl lr-route-add R2 "::/0" 10.0.0.1]) + +# Create logical port ls1-lp1 in ls1 +ovn-nbctl lsp-add ls1 ls1-lp1 \ +-- lsp-set-addresses ls1-lp1 "$ls1_lp1_mac $ls1_lp1_ip" + +# Create logical port ls2-lp1 in ls2 +ovn-nbctl lsp-add ls2 ls2-lp1 \ +-- lsp-set-addresses ls2-lp1 "$ls2_lp1_mac $ls2_lp1_ip" + +# Create two hypervisor and create OVS ports corresponding to logical ports. +net_add n1 + +sim_add hv1 +as hv1 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.1 +ovs-vsctl -- add-port br-int hv1-vif1 -- \ + set interface hv1-vif1 external-ids:iface-id=ls1-lp1 \ + options:tx_pcap=hv1/vif1-tx.pcap \ + options:rxq_pcap=hv1/vif1-rx.pcap \ + ofport-request=1 + +sim_add hv2 +as hv2 +ovs-vsctl add-br br-phys +ovn_attach n1 br-phys 192.168.0.2 +ovs-vsctl -- add-port br-int hv2-vif1 -- \ + set interface hv2-vif1 external-ids:iface-id=ls2-lp1 \ + options:tx_pcap=hv2/vif1-tx.pcap \ + options:rxq_pcap=hv2/vif1-rx.pcap \ + ofport-request=1 + + +# Pre-populate the hypervisors' ARP tables so that we don't lose any +# packets for ARP resolution (native tunneling doesn't queue packets +# for ARP resolution). +OVN_POPULATE_ARP + +# Allow some time for ovn-northd and ovn-controller to catch up. +wait_for_ports_up +check ovn-nbctl --wait=hv sync + +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip6 && ip.ttl==64 && ip6.src==$ls1_lp1_ip && ip6.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) + + +echo "---------NB dump-----" +ovn-nbctl show +echo "---------------------" +ovn-nbctl list logical_router +echo "---------------------" +ovn-nbctl list logical_router_port +echo "---------------------" + +echo "---------SB dump-----" +ovn-sbctl list datapath_binding +echo "---------------------" +ovn-sbctl list port_binding +echo "---------------------" + +echo "------ hv1 dump ----------" +as hv1 ovs-ofctl show br-int +as hv1 ovs-ofctl dump-flows br-int +echo "------ hv2 dump ----------" +as hv2 ovs-ofctl show br-int +as hv2 ovs-ofctl dump-flows br-int + +# Packet to Expect +# The TTL should be decremented by 2. +packet="eth.src==$rp_ls2_mac && eth.dst==$ls2_lp1_mac && + ip6 && ip.ttl==62 && ip6.src==$ls1_lp1_ip && ip6.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" +echo $packet | ovstest test-ovn expr-to-packets > expected + +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "xxreg0 == 2001:db8:2::2" | wc -l], [0], [1 +]) + +# Disable the ls2-lp1 port. +ovn-nbctl --wait=hv set logical_switch_port ls2-lp1 enabled=false + +AT_CHECK([ovn-sbctl dump-flows | grep lr_in_arp_resolve | \ +grep "xxreg0 == 2001:db8:2::2" | wc -l], [0], [0 +]) + +# Generate the packet destined for ls2-lp1 and it should not be delivered. +# Packet to send. +packet="inport==\"ls1-lp1\" && eth.src==$ls1_lp1_mac && eth.dst==$rp_ls1_mac && + ip6 && ip.ttl==64 && ip6.src==$ls1_lp1_ip && ip6.dst==$ls2_lp1_ip && + udp && udp.src==53 && udp.dst==4369" + +OVS_WAIT_UNTIL([as hv1 ovs-appctl -t ovn-controller inject-pkt "$packet"]) +# The 2nd packet sent shound not be received. +OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) + +OVN_CLEANUP([hv1],[hv2]) + +AT_CLEANUP +]) diff --git a/utilities/ovn-nbctl.c b/utilities/ovn-nbctl.c index 25eb86f7f..f827b2ad9 100644 --- a/utilities/ovn-nbctl.c +++ b/utilities/ovn-nbctl.c @@ -4546,11 +4546,9 @@ nbctl_lr_route_add(struct ctl_context *ctx) } char *route_table = shash_find_data(&ctx->options, "--route-table"); - bool v6_prefix = false; prefix = normalize_ipv4_prefix_str(ctx->argv[2]); if (!prefix) { prefix = normalize_ipv6_prefix_str(ctx->argv[2]); - v6_prefix = true; } if (!prefix) { ctl_error(ctx, "bad prefix argument: %s", ctx->argv[2]); @@ -4561,15 +4559,15 @@ nbctl_lr_route_add(struct ctl_context *ctx) if (is_discard_route) { next_hop = xasprintf("discard"); } else { - next_hop = v6_prefix - ? normalize_ipv6_addr_str(ctx->argv[3]) - : normalize_ipv4_addr_str(ctx->argv[3]); + next_hop = normalize_ipv4_addr_str(ctx->argv[3]); + if (!next_hop) { + next_hop = normalize_ipv6_addr_str(ctx->argv[3]); + } if (!next_hop) { /* check if it is a output port. */ error = lrp_by_name_or_uuid(ctx, ctx->argv[3], true, &out_lrp); if (error) { - ctl_error(ctx, "bad %s nexthop argument: %s", - v6_prefix ? "IPv6" : "IPv4", ctx->argv[3]); + ctl_error(ctx, "bad nexthop argument: %s", ctx->argv[3]); free(error); goto cleanup; }
In most cases IPv4 packets are routed only over other IPv4 networks and IPv6 packets are routed only over IPv6 networks. However there is no interent reason for this limitation. Routing IPv4 packets over IPv6 networks just requires the router to contain a route for an IPv4 network with an IPv6 nexthop. This was previously prevented in OVN in ovn-nbctl and northd. By removing these filters the forwarding will work if the mac addresses are prepopulated. If the mac addresses are not prepopulated we will attempt to resolve them using the original address family of the packet and not the address family of the nexthop. This will fail and we will not forward the packet. This feature can for example be used by service providers to interconnect multiple IPv4 networks of a customer without needing to negotiate free IPv4 addresses by just using any IPv6 address. Signed-off-by: Felix Huettner <felix.huettner@mail.schwarz> --- NEWS | 4 + northd/northd.c | 45 ++-- tests/ovn-nbctl.at | 8 +- tests/ovn.at | 615 ++++++++++++++++++++++++++++++++++++++++++ utilities/ovn-nbctl.c | 12 +- 5 files changed, 650 insertions(+), 34 deletions(-) base-commit: dc52bf70cb7e066fdb84d88622d7f380eda18e8c