This patch introduces a new type of OVN ports called "localport". These ports will be present in every hypervisor and may have the same IP/MAC addresses. They are not bound to any chassis and traffic to these ports will never go through a tunnel.
Its main use case is the OpenStack metadata API support which relies on a local agent running on every hypervisor and serving metadata to VM's locally. This service is described in detail at [0]. An example to illustrate the purpose of this patch: - One logical switch sw0 with 2 ports (p1, p2) and 1 localport (lp) - Two hypervisors: HV1 and HV2 - p1 in HV1 (OVS port with external-id:iface-id="p1") - p2 in HV2 (OVS port with external-id:iface-id="p2") - lp in both hypevisors (OVS port with external-id:iface-id="lp") - p1 should be able to reach p2 and viceversa - lp on HV1 should be able to reach p1 but not p2 - lp on HV2 should be able to reach p2 but not p1 Explicit drop rules are inserted in table 32 with priority 150 in order to prevent traffic originated at a localport to go over a tunnel. [0] https://docs.openstack.org/developer/networking-ovn/design/metadata_api.html Signed-off-by: Daniel Alvarez <[email protected]> Signed-off-by: Ben Pfaff <[email protected]> --- ovn/controller/binding.c | 4 +- ovn/controller/ovn-controller.c | 2 +- ovn/controller/physical.c | 30 +++++++++- ovn/controller/physical.h | 4 +- ovn/northd/ovn-northd.8.xml | 8 +-- ovn/northd/ovn-northd.c | 6 +- ovn/ovn-architecture.7.xml | 45 ++++++++++++--- ovn/ovn-nb.xml | 9 +++ ovn/ovn-sb.xml | 14 +++++ tests/ovn.at | 122 ++++++++++++++++++++++++++++++++++++++++ 10 files changed, 226 insertions(+), 18 deletions(-) diff --git a/ovn/controller/binding.c b/ovn/controller/binding.c index 95e9deb..d033df0 100644 --- a/ovn/controller/binding.c +++ b/ovn/controller/binding.c @@ -380,7 +380,9 @@ consider_local_datapath(struct controller_ctx *ctx, if (iface_rec && qos_map && ctx->ovs_idl_txn) { get_qos_params(binding_rec, qos_map); } - our_chassis = true; + /* This port is in our chassis unless it is a localport */ + if(strcmp(binding_rec->type, "localport")) + our_chassis = true; } else if (!strcmp(binding_rec->type, "l2gateway")) { const char *chassis_id = smap_get(&binding_rec->options, "l2gateway-chassis"); diff --git a/ovn/controller/ovn-controller.c b/ovn/controller/ovn-controller.c index f22551d..0f4dd35 100644 --- a/ovn/controller/ovn-controller.c +++ b/ovn/controller/ovn-controller.c @@ -655,7 +655,7 @@ main(int argc, char *argv[]) physical_run(&ctx, mff_ovn_geneve, br_int, chassis, &ct_zones, &lports, - &flow_table, &local_datapaths); + &flow_table, &local_datapaths, &local_lports); ofctrl_put(&flow_table, &pending_ct_zones, get_nb_cfg(ctx.ovnsb_idl)); diff --git a/ovn/controller/physical.c b/ovn/controller/physical.c index 457fc45..2172dd8 100644 --- a/ovn/controller/physical.c +++ b/ovn/controller/physical.c @@ -769,7 +769,8 @@ physical_run(struct controller_ctx *ctx, enum mf_field_id mff_ovn_geneve, const struct ovsrec_bridge *br_int, const struct sbrec_chassis *chassis, const struct simap *ct_zones, struct lport_index *lports, - struct hmap *flow_table, struct hmap *local_datapaths) + struct hmap *flow_table, struct hmap *local_datapaths, + const struct sset *local_lports) { /* This bool tracks physical mapping changes. */ @@ -988,15 +989,40 @@ physical_run(struct controller_ctx *ctx, enum mf_field_id mff_ovn_geneve, */ struct match match; match_init_catchall(&match); - ofpbuf_clear(&ofpacts); match_set_reg_masked(&match, MFF_LOG_FLAGS - MFF_REG0, MLF_RCV_FROM_VXLAN, MLF_RCV_FROM_VXLAN); /* Resubmit to table 33. */ + ofpbuf_clear(&ofpacts); put_resubmit(OFTABLE_LOCAL_OUTPUT, &ofpacts); ofctrl_add_flow(flow_table, OFTABLE_REMOTE_OUTPUT, 150, 0, &match, &ofpacts); + /* Table 32, priority 150. + * ======================= + * + * Handles packets received from ports of type "localport". These ports + * are present on every hypervisor. Traffic that originates at one should + * never go over a tunnel to a remote hypervisor, so resubmit them to table + * 33 for local delivery. */ + match_init_catchall(&match); + ofpbuf_clear(&ofpacts); + put_resubmit(OFTABLE_LOCAL_OUTPUT, &ofpacts); + const char *localport; + SSET_FOR_EACH (localport, local_lports) { + /* Iterate over all local logical ports and insert a drop + * rule with higher priority for every localport in this + * datapath. */ + const struct sbrec_port_binding *pb = lport_lookup_by_name( + lports, localport); + if (pb && !strcmp(pb->type, "localport")) { + match_set_reg(&match, MFF_LOG_INPORT - MFF_REG0, pb->tunnel_key); + match_set_metadata(&match, htonll(pb->datapath->tunnel_key)); + ofctrl_add_flow(flow_table, OFTABLE_REMOTE_OUTPUT, 150, 0, + &match, &ofpacts); + } + } + /* Table 32, Priority 0. * ======================= * diff --git a/ovn/controller/physical.h b/ovn/controller/physical.h index e2debed..66aa80e 100644 --- a/ovn/controller/physical.h +++ b/ovn/controller/physical.h @@ -32,6 +32,7 @@ struct hmap; struct ovsdb_idl; struct ovsrec_bridge; struct simap; +struct sset; /* OVN Geneve option information. * @@ -45,6 +46,7 @@ void physical_run(struct controller_ctx *, enum mf_field_id mff_ovn_geneve, const struct ovsrec_bridge *br_int, const struct sbrec_chassis *chassis, const struct simap *ct_zones, struct lport_index *, - struct hmap *flow_table, struct hmap *local_datapaths); + struct hmap *flow_table, struct hmap *local_datapaths, + const struct sset *local_lports); #endif /* ovn/physical.h */ diff --git a/ovn/northd/ovn-northd.8.xml b/ovn/northd/ovn-northd.8.xml index c0b4c5e..7ff5245 100644 --- a/ovn/northd/ovn-northd.8.xml +++ b/ovn/northd/ovn-northd.8.xml @@ -492,8 +492,8 @@ output; </pre> <p> - These flows are omitted for logical ports (other than router ports) - that are down. + These flows are omitted for logical ports (other than router ports or + <code>localport</code> ports) that are down. </p> </li> @@ -519,8 +519,8 @@ nd_na { </pre> <p> - These flows are omitted for logical ports (other than router ports) - that are down. + These flows are omitted for logical ports (other than router ports or + <code>localport</code> ports) that are down. </p> </li> diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c index 83db753..a3bd859 100644 --- a/ovn/northd/ovn-northd.c +++ b/ovn/northd/ovn-northd.c @@ -3305,9 +3305,11 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap *ports, /* * Add ARP/ND reply flows if either the * - port is up or - * - port type is router + * - port type is router or + * - port type is localport */ - if (!lsp_is_up(op->nbsp) && strcmp(op->nbsp->type, "router")) { + if (!lsp_is_up(op->nbsp) && strcmp(op->nbsp->type, "router") && + strcmp(op->nbsp->type, "localport")) { continue; } diff --git a/ovn/ovn-architecture.7.xml b/ovn/ovn-architecture.7.xml index d8114f1..085a6ae 100644 --- a/ovn/ovn-architecture.7.xml +++ b/ovn/ovn-architecture.7.xml @@ -409,6 +409,21 @@ logical patch ports at each such point of connectivity, one on each side. </li> + <li> + <dfn>Localport ports</dfn> represent the points of local + connectivity between logical switches and VIFs. These ports are + present in every chassis (not bound to any particular one) and + traffic from them will never go through a tunnel. A + <code>localport</code> is expected to only generate traffic destined + for a local destination, typically in response to a request it + received. + One use case is how OpenStack Neutron uses a <code>localport</code> + port for serving metadata to VM's residing on every hypervisor. A + metadata proxy process is attached to this port on every host and all + VM's within the same network will reach it at the same IP/MAC address + without any traffic being sent over a tunnel. Further details can be + seen at https://docs.openstack.org/developer/networking-ovn/design/metadata_api.html. + </li> </ul> </li> </ul> @@ -993,15 +1008,31 @@ hypervisor, in the same way as for unicast destinations. If a multicast group includes a logical port or ports on the local hypervisor, then its actions also resubmit to table 33. Table 32 also - includes a fallback flow that resubmits to table 33 if there is no - other match. Table 32 also contains a higher priority rule to match - packets received from VXLAN tunnels, based on flag MLF_RCV_FROM_VXLAN - and resubmit these packets to table 33 for local delivery. Packets - received from VXLAN tunnels reach here because of a lack of logical - output port field in the tunnel key and thus these packets needed to - be submitted to table 16 to determine the output port. + includes: </p> + <ul> + <li> + A higher-priority rule to match packets received from VXLAN tunnels, + based on flag MLF_RCV_FROM_VXLAN, and resubmit these packets to table + 33 for local delivery. Packets received from VXLAN tunnels reach + here because of a lack of logical output port field in the tunnel key + and thus these packets needed to be submitted to table 16 to + determine the output port. + </li> + <li> + A higher-priority rule to match packets received from ports of type + <code>localport</code>, based on the logical input port, and resubmit + these packets to table 33 for local delivery. Ports of type + <code>localport</code> exist on every hypervisor and by definition + their traffic should never go out through a tunnel. + </li> + <li> + A fallback flow that resubmits to table 33 if there is no other + match. + </li> + </ul> + <p> Flows in table 33 resemble those in table 32 but for logical ports that reside locally rather than remotely. For unicast logical output ports diff --git a/ovn/ovn-nb.xml b/ovn/ovn-nb.xml index f5be9e2..eb348fe 100644 --- a/ovn/ovn-nb.xml +++ b/ovn/ovn-nb.xml @@ -283,6 +283,15 @@ to model direct connectivity to an existing network. </dd> + <dt><code>localport</code></dt> + <dd> + A connection to a local VIF. Traffic that arrives on a + <code>localport</code> is never forwarded over a tunnel to another + chassis. These ports are present on every chassis and have the same + address in all of them. This is used to model connectivity to local + services that run on every hypervisor. + </dd> + <dt><code>l2gateway</code></dt> <dd> A connection to a physical network. diff --git a/ovn/ovn-sb.xml b/ovn/ovn-sb.xml index 387adb8..f3c3212 100644 --- a/ovn/ovn-sb.xml +++ b/ovn/ovn-sb.xml @@ -1802,6 +1802,11 @@ tcp.flags = RST; connectivity to the corresponding physical network. </dd> + <dt>localport</dt> + <dd> + Always empty. A localport port is present on every chassis. + </dd> + <dt>l3gateway</dt> <dd> The physical location of the L3 gateway. To successfully identify a @@ -1882,6 +1887,15 @@ tcp.flags = RST; to model direct connectivity to an existing network. </dd> + <dt><code>localport</code></dt> + <dd> + A connection to a local VIF. Traffic that arrives on a + <code>localport</code> is never forwarded over a tunnel to another + chassis. These ports are present on every chassis and have the same + address in all of them. This is used to model connectivity to local + services that run on every hypervisor. + </dd> + <dt><code>l2gateway</code></dt> <dd> An L2 connection to a physical network. The chassis this diff --git a/tests/ovn.at b/tests/ovn.at index b30315e..8abf45a 100644 --- a/tests/ovn.at +++ b/tests/ovn.at @@ -7374,3 +7374,125 @@ OVN_CHECK_PACKETS([hv2/vif1-tx.pcap], [expected]) OVN_CLEANUP([hv1],[hv2]) AT_CLEANUP + +AT_SETUP([ovn -- 2 HVs, 1 lport/HV, localport ports]) +AT_SKIP_IF([test $HAVE_PYTHON = no]) +ovn_start + +ovn-nbctl ls-add ls1 + +# Add localport to the switch +ovn-nbctl lsp-add ls1 lp01 +ovn-nbctl lsp-set-addresses lp01 f0:00:00:00:00:01 +ovn-nbctl lsp-set-type lp01 localport + +net_add n1 + +for i in 1 2; do + sim_add hv$i + as hv$i + ovs-vsctl add-br br-phys + ovn_attach n1 br-phys 192.168.0.$i + ovs-vsctl add-port br-int vif01 -- \ + set Interface vif01 external-ids:iface-id=lp01 \ + options:tx_pcap=hv${i}/vif01-tx.pcap \ + options:rxq_pcap=hv${i}/vif01-rx.pcap \ + ofport-request=${i}0 + + ovs-vsctl add-port br-int vif${i}1 -- \ + set Interface vif${i}1 external-ids:iface-id=lp${i}1 \ + options:tx_pcap=hv${i}/vif${i}1-tx.pcap \ + options:rxq_pcap=hv${i}/vif${i}1-rx.pcap \ + ofport-request=${i}1 + + ovn-nbctl lsp-add ls1 lp${i}1 + ovn-nbctl lsp-set-addresses lp${i}1 f0:00:00:00:00:${i}1 + ovn-nbctl lsp-set-port-security lp${i}1 f0:00:00:00:00:${i}1 + + OVS_WAIT_UNTIL([test x`ovn-nbctl lsp-get-up lp${i}1` = xup]) +done + +ovn-nbctl --wait=sb sync +ovn-sbctl dump-flows + +ovn_populate_arp + +# Given the name of a logical port, prints the name of the hypervisor +# on which it is located. +vif_to_hv() { + echo hv${1%?} +} +# +# test_packet INPORT DST SRC ETHTYPE EOUT LOUT DEFHV +# +# This shell function causes a packet to be received on INPORT. The packet's +# content has Ethernet destination DST and source SRC (each exactly 12 hex +# digits) and Ethernet type ETHTYPE (4 hex digits). INPORT is specified as +# logical switch port numbers, e.g. 11 for vif11. +# +# EOUT is the end-to-end output port, that is, where the packet will end up +# after possibly bouncing through one or more localnet ports. LOUT is the +# logical output port, which might be a localnet port, as seen by ovn-trace +# (which doesn't know what localnet ports are connected to and therefore can't +# figure out the end-to-end answer). +# +# DEFHV is the default hypervisor from where the packet is going to be sent +# if the source port is a localport. +for i in 1 2; do + for j in 0 1; do + : > $i$j.expected + done +done +test_packet() { + local inport=$1 dst=$2 src=$3 eth=$4 eout=$5 lout=$6 defhv=$7 + echo "$@" + + # First try tracing the packet. + uflow="inport==\"lp$inport\" && eth.dst==$dst && eth.src==$src && eth.type==0x$eth" + if test $lout != drop; then + echo "output(\"$lout\");" + fi > expout + AT_CAPTURE_FILE([trace]) + AT_CHECK([ovn-trace --all ls1 "$uflow" | tee trace | sed '1,/Minimal trace/d'], [0], [expout]) + + # Then actually send a packet, for an end-to-end test. + local packet=$(echo $dst$src | sed 's/://g')${eth} + hv=`vif_to_hv $inport` + # If hypervisor 0 (localport) use the defhv parameter + if test $hv == hv0; then + hv=$defhv + fi + vif=vif$inport + as $hv ovs-appctl netdev-dummy/receive $vif $packet + if test $eout != drop; then + echo $packet >> ${eout#lp}.expected + fi +} + + +# lp11 and lp21 are on different hypervisors +test_packet 11 f0:00:00:00:00:21 f0:00:00:00:00:11 1121 lp21 lp21 +test_packet 21 f0:00:00:00:00:11 f0:00:00:00:00:21 2111 lp11 lp11 + +# Both VIFs should be able to reach the localport on their own HV +test_packet 11 f0:00:00:00:00:01 f0:00:00:00:00:11 1101 lp01 lp01 +test_packet 21 f0:00:00:00:00:01 f0:00:00:00:00:21 2101 lp01 lp01 + +# Packet sent from localport on same hv should reach the vif +test_packet 01 f0:00:00:00:00:11 f0:00:00:00:00:01 0111 lp11 lp11 hv1 +test_packet 01 f0:00:00:00:00:21 f0:00:00:00:00:01 0121 lp21 lp21 hv2 + +# Packet sent from localport on different hv should be dropped +test_packet 01 f0:00:00:00:00:21 f0:00:00:00:00:01 0121 drop lp21 hv1 +test_packet 01 f0:00:00:00:00:11 f0:00:00:00:00:01 0111 drop lp11 hv2 + +# Now check the packets actually received against the ones expected. +for i in 1 2; do + for j in 0 1; do + OVN_CHECK_PACKETS([hv$i/vif$i$j-tx.pcap], [$i$j.expected]) + done +done + +OVN_CLEANUP([hv1],[hv2]) + +AT_CLEANUP -- 1.8.3.1 _______________________________________________ dev mailing list [email protected] https://mail.openvswitch.org/mailman/listinfo/ovs-dev
