diff --git a/northd/northd.c b/northd/northd.c index 0c73e70dff..11bc9ae19e 100644 --- a/northd/northd.c +++ b/northd/northd.c @@ -13935,6 +13935,221 @@ build_arp_resolve_flows_for_lrp(struct ovn_port *op, } } +static void +build_r_p_redirect_rule__( + const char *s_addr, const char *redirect_port_name, int protocol_port, + const char *proto, bool is_ipv6, struct ovn_port *ls_peer, + struct lflow_table *lflows, struct ds *match, struct ds *actions) +{ + int ip_ver = is_ipv6 ? 6 : 4; + ds_clear(actions); + ds_put_format(actions, "outport = \"%s\"; output;", redirect_port_name); + + /* Redirect packets in the input pipeline destined for LR's IP + * and the routing protocol's port to the LSP specified in + * 'routing-protocol-redirect' option.*/ + ds_clear(match); + ds_put_format(match, "ip%d.dst == %s && %s.dst == %d", ip_ver, s_addr, + proto, protocol_port); + ovn_lflow_add(lflows, ls_peer->od, S_SWITCH_IN_L2_LKUP, 100, + ds_cstr(match), + ds_cstr(actions), + ls_peer->lflow_ref); + + /* To accomodate "peer" nature of the routing daemons, redirect also + * replies to the daemons' client requests. */ + ds_clear(match); + ds_put_format(match, "ip%d.dst == %s && %s.src == %d", ip_ver, s_addr, + proto, protocol_port); + ovn_lflow_add(lflows, ls_peer->od, S_SWITCH_IN_L2_LKUP, 100, + ds_cstr(match), + ds_cstr(actions), + ls_peer->lflow_ref); +} + +static void +apply_r_p_redirect__( + const char *s_addr, const char *redirect_port_name, int protocol_flags, + bool is_ipv6, struct ovn_port *ls_peer, struct lflow_table *lflows, + struct ds *match, struct ds *actions) +{ + if (protocol_flags & REDIRECT_BGP) { + build_r_p_redirect_rule__(s_addr, redirect_port_name, 179, "tcp", + is_ipv6, ls_peer, lflows, match, actions); + } + + if (protocol_flags & REDIRECT_BFD) { + build_r_p_redirect_rule__(s_addr, redirect_port_name, 3784, "udp", + is_ipv6, ls_peer, lflows, match, actions); + } + + /* Because the redirected port shares IP and MAC addresses with the LRP, + * special consideration needs to be given to the signaling protocols. */ + if (is_ipv6) { + /* Ensure that redirect port receives copy of NA messages destined to + * its IP.*/ + ds_clear(match); + ds_clear(actions); + ds_put_format(actions, "clone { outport = \"%s\"; output; };", + redirect_port_name); + ds_put_format(match, "ip6.dst == %s && nd_na", s_addr); + ovn_lflow_add(lflows, ls_peer->od, S_SWITCH_IN_L2_LKUP, 100, + ds_cstr(match), + ds_cstr(actions), + ls_peer->lflow_ref); + } else { + /* Ensure that redirect port receives copy of ARP replies destined to + * its IP */ + ds_clear(match); + ds_clear(actions); + ds_put_format(actions, "clone { outport = \"%s\"; output; };", + redirect_port_name); + ds_put_format(match, "arp.op == 2 && arp.tpa == %s", s_addr); + ovn_lflow_add(lflows, ls_peer->od, S_SWITCH_IN_L2_LKUP, 100, + ds_cstr(match), + ds_cstr(actions), + ls_peer->lflow_ref); + + } +} + +static int +parse_redirected_routing_protocols(struct ovn_port *lrp) { + int redirected_protocol_flags = 0; + const char *redirect_protocols = smap_get(&lrp->nbrp->options, + "routing-protocols"); + if (redirect_protocols == NULL) { + return redirected_protocol_flags; + } + + char *proto; + char *save_ptr = NULL; + char *tokstr = xstrdup(redirect_protocols); + for (proto = strtok_r(tokstr, ",", &save_ptr); proto != NULL; + proto = strtok_r(NULL, ",", &save_ptr)) { + if (!strcmp(proto, "BGP")) { + redirected_protocol_flags |= REDIRECT_BGP; + continue; + } + + if (!strcmp(proto, "BFD")) { + redirected_protocol_flags |= REDIRECT_BFD; + continue; + } + static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5); + VLOG_WARN_RL(&rl, "Option 'routing-protocols' encountered unknown " + "value %s", + proto); + } + free(tokstr); + return redirected_protocol_flags; +} + +static void +build_lrouter_routing_protocol_redirect( + struct ovn_port *op, struct lflow_table *lflows, + struct ds *match, struct ds *actions) +{ + /* LRP has to have a peer.*/ + if (op->peer == NULL) { + return; + } + /* LRP has to have NB record.*/ + if (op->nbrp == NULL) { + return; + } + + /* Proceed only for LRPs that have 'routing-protocol-redirect' option set. + * Value of this option is the name of LSP to which the routing protocol + * traffic will be redirected. */ + const char *redirect_port = smap_get(&op->nbrp->options, + "routing-protocol-redirect"); + if (redirect_port == NULL) { + return; + } + + if (op->cr_port != NULL) { + static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5); + VLOG_WARN_RL(&rl, "Option 'routing-protocol-redirect' is not " + "supported on Distributed Gateway Port '%s'", + op->key); + return; + } + + /* Ensure that LSP, to which the routing protocol traffic is redirected, + * exists.*/ + struct ovn_port *peer_lsp; + bool redirect_port_exists = false; + HMAP_FOR_EACH (peer_lsp, dp_node, &op->peer->od->ports) { + size_t peer_lsp_s = strlen(peer_lsp->key); + if (peer_lsp_s == strlen(redirect_port) + && !strncmp(peer_lsp->key, redirect_port, peer_lsp_s)){ + redirect_port_exists = true; + break; + } + } + + if (!redirect_port_exists) { + static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5); + VLOG_WARN_RL(&rl, "Option 'routing-protocol-redirect' set on Logical " + "Router Port '%s' refers to non-existent Logical " + "Switch Port. Routing protocol redirecting won't be " + "configured.", + op->key); + return; + } + + + int redirected_protocols = parse_redirected_routing_protocols(op); + if (!redirected_protocols) { + static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5); + VLOG_WARN_RL(&rl, "Option 'routing-protocol-redirect' is set on " + "Logical Router Port '%s' but no known protocols " + "were set via 'routing-protocols' options. This " + "configuration has no effect.", + op->key); + return; + } + + /* Redirecte traffic destined for LRP's IPs and the specified routing + * protocol ports to the port defined in 'routing-protocol-redirect' + * option.*/ + for (size_t i = 0; i < op->lrp_networks.n_ipv4_addrs; i++) { + const char *ip_s = op->lrp_networks.ipv4_addrs[i].addr_s; + apply_r_p_redirect__(ip_s, redirect_port, redirected_protocols, false, + op->peer, lflows,match, actions); + } + for (size_t i = 0; i < op->lrp_networks.n_ipv6_addrs; i++) { + const char *ip_s = op->lrp_networks.ipv6_addrs[i].addr_s; + apply_r_p_redirect__(ip_s, redirect_port, redirected_protocols, true, + op->peer, lflows,match, actions); + } + + /* Drop ARP replies and IPv6 RA/NA packets originating from + * 'routing-protocol-redirect' LSP. As this port shares IP and MAC + * addresses with LRP, we don't want to create duplicates.*/ + ds_clear(match); + ds_put_format(match, "inport == \"%s\" && arp.op == 2", redirect_port); + ovn_lflow_add(lflows, op->peer->od, S_SWITCH_IN_CHECK_PORT_SEC, 80, + ds_cstr(match), + REGBIT_PORT_SEC_DROP " = 1; next;", + op->peer->lflow_ref); + + ds_clear(match); + ds_put_format(match, "inport == \"%s\" && nd_na", redirect_port); + ovn_lflow_add(lflows, op->peer->od, S_SWITCH_IN_CHECK_PORT_SEC, 80, + ds_cstr(match), + REGBIT_PORT_SEC_DROP " = 1; next;", + op->peer->lflow_ref); + + ds_clear(match); + ds_put_format(match, "inport == \"%s\" && nd_ra", redirect_port); + ovn_lflow_add(lflows, op->peer->od, S_SWITCH_IN_CHECK_PORT_SEC, 80, + ds_cstr(match), + REGBIT_PORT_SEC_DROP " = 1; next;", + op->peer->lflow_ref); +} + /* This function adds ARP resolve flows related to a LSP. */ static void build_arp_resolve_flows_for_lsp( @@ -16900,6 +17115,8 @@ build_lswitch_and_lrouter_iterate_by_lrp(struct ovn_port *op, op->lflow_ref); build_lrouter_icmp_packet_toobig_admin_flows(op, lsi->lflows, &lsi->match, &lsi->actions, op->lflow_ref); + build_lrouter_routing_protocol_redirect(op, lsi->lflows, + &lsi->match, &lsi->actions); } static void * diff --git a/northd/northd.h b/northd/northd.h index e04ec58567..9e326b7460 100644 --- a/northd/northd.h +++ b/northd/northd.h @@ -93,6 +93,13 @@ ovn_datapath_find_by_key(struct hmap *datapaths, uint32_t dp_key); bool od_has_lb_vip(const struct ovn_datapath *od); +/* List of routing and routing-related protocols which + * OVN is capable of redirecting from LRP to specific LSP. */ +enum redirected_routing_protcol_flag_type { + REDIRECT_BGP = (1 << 0), + REDIRECT_BFD = (1 << 1), +}; + struct tracked_ovn_ports { /* tracked created ports. * hmapx node data is 'struct ovn_port *' */ diff --git a/northd/ovn-northd.8.xml b/northd/ovn-northd.8.xml index 3abd5f75bb..185db0d514 100644 --- a/northd/ovn-northd.8.xml +++ b/northd/ovn-northd.8.xml @@ -284,6 +284,32 @@ dropped in the next stage. +
+ For each logical port that's defined as a target of routing protocol
+ redirecting (via routing-protocol-redirect
option set on
+ Logical Router Port), a filter is set in place that disallows
+ following traffic exiting this port:
+
+ Since this port shares IP and MAC addresses with the Logical Router
+ Port, we wan't to prevent duplicate replies and advertisements. This
+ is achieved by a rule with priority 80 that sets
+ REGBIT_PORT_SEC_DROP" = 1; next;"
.
+
+ For any logical port that's defined as a target of routing protocol
+ redirecting (via routing-protocol-redirect
option set on
+ Logical Router Port), we redirect the traffic related to protocols
+ specified in routing-protocols
option. It's acoomplished
+ with following priority-100 flows:
+
+
+ In addition to this, we add priority-100 rules that
+ clone
ARP replies and IPv6 Neighbor Advertisements to
+ this port as well. These allow to build proper ARP/IPv6 neighbor
+ list on this port.
+
+ NOTE: this feature is experimental and may be subject to + removal/change in the future. +
+
+ This option expects a name of a Logical Switch Port that's present
+ in the peer's Logical Switch. If set, it causes any traffic
+ that's destined for Logical Router Port's IP addresses (including
+ its IPv6 LLA) and the ports associated with routing protocols defined
+ ip routing-protocols
option, to be redirected
+ to the specified Logical Switch Port.
+
+ This allows external routing daemons to be bound to a port in OVN's
+ Logical Switch and act as if they were listening on Logical Router
+ Port's IP addresses.
+
+ NOTE: this feature is experimental and may be subject to + removal/change in the future. +
+
+ This option expects a comma-separated list of routing, and
+ routing-related protocols, whose control plane traffic will be
+ redirected to a port specified in
+ routing-protocol-redirect
option. Currently supported
+ options are:
+
BGP
(forwards TCP port 179)
+ BFD
(forwards UDP port 3748)
+ When configured, represents a match expression, in the same diff --git a/tests/ovn-northd.at b/tests/ovn-northd.at index f2f42275aa..f1e206cfc6 100644 --- a/tests/ovn-northd.at +++ b/tests/ovn-northd.at @@ -13757,3 +13757,96 @@ AT_CHECK([grep -e "172.168.0.110" -e "172.168.0.120" -e "10.0.0.3" -e "20.0.0.3" AT_CLEANUP ]) + +OVN_FOR_EACH_NORTHD_NO_HV([ +AT_SETUP([Routing protocol control plane redirect]) +ovn_start + +check ovn-sbctl chassis-add hv1 geneve 127.0.0.1 + +check ovn-nbctl lr-add lr -- \ + lrp-add lr lr-ls 02:ac:10:01:00:01 172.16.1.1/24 +check ovn-nbctl --wait=sb set logical_router lr options:chassis=hv1 + +check ovn-nbctl ls-add ls -- \ + lsp-add ls ls-lr -- \ + lsp-set-type ls-lr router -- \ + lsp-set-addresses ls-lr router -- \ + lsp-set-options ls-lr router-port=lr-ls + +check ovn-nbctl lsp-add ls lsp-bgp -- \ + lsp-set-addresses lsp-bgp unknown + +# Function that ensures that no redirect rules are installed. +check_no_redirect() { + AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_l2_lkup | grep -E "tcp.dst == 179|tcp.src == 179" | wc -l], [0], [0 +]) + + AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_check_port_sec | grep -E "priority=80" | wc -l], [0], [0 +]) + check_no_bfd_redirect +} + +# Function that ensures that no BFD redirect rules are installed. +check_no_bfd_redirect() { + AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_l2_lkup | grep -E "udp.dst == 3784|udp.src == 3784" | wc -l], [0], [0 +]) +} + +# By default, no rules related to routing protocol redirect are present +check_no_redirect + +# Set "lsp-bgp" port as target of BGP control plane redirected traffic +check ovn-nbctl --wait=sb set logical_router_port lr-ls options:routing-protocol-redirect=lsp-bgp +check ovn-nbctl --wait=sb set logical_router_port lr-ls options:routing-protocols=BGP + +# Check that BGP control plane traffic is redirected "lsp-bgp" +AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_l2_lkup | grep -E "tcp.dst == 179|tcp.src == 179" | ovn_strip_lflows], [0], [dnl + table=??(ls_in_l2_lkup ), priority=100 , match=(ip4.dst == 172.16.1.1 && tcp.dst == 179), action=(outport = "lsp-bgp"; output;) + table=??(ls_in_l2_lkup ), priority=100 , match=(ip4.dst == 172.16.1.1 && tcp.src == 179), action=(outport = "lsp-bgp"; output;) + table=??(ls_in_l2_lkup ), priority=100 , match=(ip6.dst == fe80::ac:10ff:fe01:1 && tcp.dst == 179), action=(outport = "lsp-bgp"; output;) + table=??(ls_in_l2_lkup ), priority=100 , match=(ip6.dst == fe80::ac:10ff:fe01:1 && tcp.src == 179), action=(outport = "lsp-bgp"; output;) +]) + +# Check that ARP/ND traffic is cloned to the "lsp-bgp" +AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_l2_lkup | grep "arp.op == 2 && arp.tpa == 172.16.1.1" | ovn_strip_lflows], [0], [dnl + table=??(ls_in_l2_lkup ), priority=100 , match=(arp.op == 2 && arp.tpa == 172.16.1.1), action=(clone { outport = "lsp-bgp"; output; };) +]) +AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_l2_lkup | grep "&& nd_na" | ovn_strip_lflows], [0], [dnl + table=??(ls_in_l2_lkup ), priority=100 , match=(ip6.dst == fe80::ac:10ff:fe01:1 && nd_na), action=(clone { outport = "lsp-bgp"; output; };) +]) + +# Check that at this point no BFD redirecting is present +check_no_bfd_redirect + +# Add BFD traffic redirect +check ovn-nbctl --wait=sb set logical_router_port lr-ls options:routing-protocols=BGP,BFD + +# Check that BFD traffic is redirected to "lsp-bgp" +AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_l2_lkup | grep -E "udp.dst == 3784|udp.src == 3784" | ovn_strip_lflows], [0], [dnl + table=??(ls_in_l2_lkup ), priority=100 , match=(ip4.dst == 172.16.1.1 && udp.dst == 3784), action=(outport = "lsp-bgp"; output;) + table=??(ls_in_l2_lkup ), priority=100 , match=(ip4.dst == 172.16.1.1 && udp.src == 3784), action=(outport = "lsp-bgp"; output;) + table=??(ls_in_l2_lkup ), priority=100 , match=(ip6.dst == fe80::ac:10ff:fe01:1 && udp.dst == 3784), action=(outport = "lsp-bgp"; output;) + table=??(ls_in_l2_lkup ), priority=100 , match=(ip6.dst == fe80::ac:10ff:fe01:1 && udp.src == 3784), action=(outport = "lsp-bgp"; output;) +]) + + +# Check that ARP replies and ND advertisements are blocked from exiting "lsp-bgp" +AT_CHECK([ovn-sbctl dump-flows ls | grep ls_in_check_port_sec | grep "priority=80" | ovn_strip_lflows], [0], [dnl + table=??(ls_in_check_port_sec), priority=80 , match=(inport == "lsp-bgp" && arp.op == 2), action=(reg0[[15]] = 1; next;) + table=??(ls_in_check_port_sec), priority=80 , match=(inport == "lsp-bgp" && nd_na), action=(reg0[[15]] = 1; next;) + table=??(ls_in_check_port_sec), priority=80 , match=(inport == "lsp-bgp" && nd_ra), action=(reg0[[15]] = 1; next;) +]) + +# Remove 'bgp-redirect' option from LRP and check that rules are removed +check ovn-nbctl --wait=sb remove logical_router_port lr-ls options routing-protocol-redirect +check ovn-nbctl --wait=sb remove logical_router_port lr-ls options routing-protocols +check_no_redirect + +# Set non-existent LSP as target of 'bgp-redirect' and check that no rules are added +check ovn-nbctl --wait=sb set logical_router_port lr-ls options:routing-protocol-redirect=lsp-foo +check ovn-nbctl --wait=sb set logical_router_port lr-ls options:routing-protocols=BGP,BFD +check_no_redirect + +AT_CLEANUP +]) diff --git a/tests/system-ovn.at b/tests/system-ovn.at index 7ba2e150b4..93ed7d17bd 100644 --- a/tests/system-ovn.at +++ b/tests/system-ovn.at @@ -13504,3 +13504,103 @@ OVS_TRAFFIC_VSWITCHD_STOP(["/failed to query port patch-.*/d AT_CLEANUP ]) + +OVN_FOR_EACH_NORTHD([ +AT_SETUP([Routing protocol redirect]) +AT_SKIP_IF([test $HAVE_NC = no]) + +ovn_start +OVS_TRAFFIC_VSWITCHD_START() + +ADD_BR([br-int]) +ADD_BR([br-ext]) + +check ovs-ofctl add-flow br-ext action=normal +# Set external-ids in br-int needed for ovn-controller +check ovs-vsctl \ + -- set Open_vSwitch . external-ids:system-id=hv1 \ + -- set Open_vSwitch . external-ids:ovn-remote=unix:$ovs_base/ovn-sb/ovn-sb.sock \ + -- set Open_vSwitch . external-ids:ovn-encap-type=geneve \ + -- set Open_vSwitch . external-ids:ovn-encap-ip=169.0.0.1 \ + -- set bridge br-int fail-mode=secure other-config:disable-in-band=true + +# Start ovn-controller +start_daemon ovn-controller + +check ovn-nbctl lr-add R1 \ + -- set Logical_Router R1 options:chassis=hv1 + +check ovn-nbctl ls-add public + +check ovn-nbctl lrp-add R1 rp-public 00:00:02:01:02:03 172.16.1.1/24 + +check ovn-nbctl lsp-add public public-rp -- set Logical_Switch_Port public-rp \ + type=router options:router-port=rp-public \ + -- lsp-set-addresses public-rp router + +check ovn-nbctl lsp-add public bgp-daemon \ + -- lsp-set-addresses bgp-daemon unknown + +AT_CHECK([ovs-vsctl set Open_vSwitch . external-ids:ovn-bridge-mappings=phynet:br-ext]) +check ovn-nbctl lsp-add public public1 \ + -- lsp-set-addresses public1 unknown \ + -- lsp-set-type public1 localnet \ + -- lsp-set-options public1 network_name=phynet + +check ovn-nbctl --wait=hv sync + +# Set option that redirects BGP traffic to a LSP "bgp-daemon" +check ovn-nbctl --wait=sb set logical_router_port rp-public options:routing-protocol-redirect=bgp-daemon +check ovn-nbctl --wait=sb set logical_router_port rp-public options:routing-protocols=BGP + +# Create "bgp-daemon" interface in a namespace with IP and MAC matching LRP "rp-public" +ADD_NAMESPACES(bgp-daemon) +ADD_VETH(bgp-daemon, bgp-daemon, br-int, "172.16.1.1/24", "00:00:02:01:02:03") + +ADD_NAMESPACES(ext-foo) +ADD_VETH(ext-foo, ext-foo, br-ext, "172.16.1.100/24", "00:10:10:01:02:13", \ + "172.16.1.1") + +# Flip the interface down/up to get proper IPv6 LLA +NS_EXEC([bgp-daemon], [ip link set down bgp-daemon]) +NS_EXEC([bgp-daemon], [ip link set up bgp-daemon]) +NS_EXEC([ext-foo], [ip link set down ext-foo]) +NS_EXEC([ext-foo], [ip link set up ext-foo]) + +# Wait until IPv6 LLA loses the "tentative" flag otherwise it can't be bound to. +OVS_WAIT_UNTIL([NS_EXEC([bgp-daemon], [ip a show dev bgp-daemon | grep "fe80::" | grep -v tentative])]) +OVS_WAIT_UNTIL([NS_EXEC([ext-foo], [ip a show dev ext-foo | grep "fe80::" | grep -v tentative])]) + +# Verify that BGP control plane traffic is delivered to the "bgp-daemon" +# interface on both IPv4 and IPv6 LLA addresses +NETNS_DAEMONIZE([bgp-daemon], [nc -l -k 172.16.1.1 179], [bgp_v4.pid]) +NS_CHECK_EXEC([ext-foo], [echo "TCP test" | nc --send-only 172.16.1.1 179]) + +NETNS_DAEMONIZE([bgp-daemon], [nc -l -6 -k fe80::200:2ff:fe01:203%bgp-daemon 179], [bgp_v6.pid]) +NS_CHECK_EXEC([ext-foo], [echo "TCP test" | nc --send-only -6 fe80::200:2ff:fe01:203%ext-foo 179]) + +# Verify connection in other direction. i.e when daemon running on "bgp-daemon" port +# makes a client connection to its peer +NETNS_DAEMONIZE([ext-foo], [nc -l -k 172.16.1.100 179], [reply_bgp_v4.pid]) +NS_CHECK_EXEC([bgp-daemon], [echo "TCP test" | nc --send-only 172.16.1.100 179]) + +NETNS_DAEMONIZE([ext-foo], [nc -l -6 -k fe80::210:10ff:fe01:213%ext-foo 179], [reply_bgp_v6.pid]) +NS_CHECK_EXEC([bgp-daemon], [echo "TCP test" | nc --send-only -6 fe80::210:10ff:fe01:213%bgp-daemon 179]) + + +OVS_APP_EXIT_AND_WAIT([ovn-controller]) + +as ovn-sb +OVS_APP_EXIT_AND_WAIT([ovsdb-server]) + +as ovn-nb +OVS_APP_EXIT_AND_WAIT([ovsdb-server]) + +as northd +OVS_APP_EXIT_AND_WAIT([ovn-northd]) + +as +OVS_TRAFFIC_VSWITCHD_STOP(["/.*error receiving.*/d +/.*terminating with signal 15.*/d"]) +AT_CLEANUP +])