Hi Numan, The feature looks very good overall. I have some more comments inlined.
On Thu, Jan 10, 2019 at 12:37 PM <[email protected]> wrote: > > From: Numan Siddique <[email protected]> > > In the case of OpenStack + OVN, when the VMs are booted on > hypervisors supporting SR-IOV nics, there are no OVS ports > for these VMs. When these VMs sends DHCPv4, DHPCv6 or IPv6 > Router Solicitation requests, the local ovn-controller > cannot reply to these packets. OpenStack Neutron dhcp agent > service needs to be run to serve these requests. > > With the new logical port type - 'external', OVN itself can > handle these requests avoiding the need to deploy any > external services like neutron dhcp agent. > > To make use of this feature, CMS has to > - create a logical port for such VMs > - set the type to 'external' > - set requested-chassis="<chassis-name>" in the options > column. > - create a localnet port for the logical switch > - configure the ovn-bridge-mappings option in the OVS db. > > When the ovn-controller running in that 'chassis', detects > the Port_Binding row, it adds the necessary DHCPv4/v6 OF > flows. Since the packet enters the logical switch pipeline > via the localnet port, the inport register (reg14) is set > to the tunnel key of localnet port in the match conditions. > > In case the chassis goes down for some reason, it is the > responsibility of CMS to change the 'requested-chassis' > option to some other active chassis, so that it can serve > these requests. > > When the VM with the external port, sends an ARP request for > the router ips, only the chassis which has claimed the port, > will reply to the ARP requests. Rest of the chassis on > receiving these packets drop them in the ingress switch > datapath stage - S_SWITCH_IN_EXTERNAL_PORT which is just > before S_SWITCH_IN_L2_LKUP. > > This would guarantee that only the chassis which has claimed > the external ports will run the router datapath pipeline. > > Signed-off-by: Numan Siddique <[email protected]> > --- > > v3 -> v4 > ------ > * Updated the documention as per Han Zhou's suggestion. > > v2 -> v3 > ------- > * Rebased > > ovn/controller/binding.c | 15 +- > ovn/controller/lflow.c | 41 ++- > ovn/controller/lflow.h | 2 + > ovn/controller/lport.c | 26 ++ > ovn/controller/lport.h | 5 + > ovn/controller/ovn-controller.c | 6 + > ovn/lib/ovn-util.c | 1 + > ovn/northd/ovn-northd.8.xml | 52 +++- > ovn/northd/ovn-northd.c | 123 ++++++-- > ovn/ovn-architecture.7.xml | 76 +++++ > ovn/ovn-nb.xml | 44 +++ > tests/ovn.at | 530 +++++++++++++++++++++++++++++++- > 12 files changed, 889 insertions(+), 32 deletions(-) > > diff --git a/ovn/controller/binding.c b/ovn/controller/binding.c > index 021ecddcf..ee396c93d 100644 > --- a/ovn/controller/binding.c > +++ b/ovn/controller/binding.c > @@ -471,13 +471,26 @@ consider_local_datapath(struct ovsdb_idl_txn > *ovnsb_idl_txn, > * for them. */ > sset_add(local_lports, binding_rec->logical_port); > our_chassis = false; > + } else if (!strcmp(binding_rec->type, "external")) { > + const char *chassis_id = smap_get(&binding_rec->options, > + "requested-chassis"); > + our_chassis = chassis_id && ( > + !strcmp(chassis_id, chassis_rec->name) || > + !strcmp(chassis_id, chassis_rec->hostname)); > + if (our_chassis) { > + add_local_datapath(sbrec_datapath_binding_by_key, > + sbrec_port_binding_by_datapath, > + sbrec_port_binding_by_name, > + binding_rec->datapath, true, local_datapaths); > + } > } > > if (our_chassis > || !strcmp(binding_rec->type, "patch") > || !strcmp(binding_rec->type, "localport") > || !strcmp(binding_rec->type, "vtep") > - || !strcmp(binding_rec->type, "localnet")) { > + || !strcmp(binding_rec->type, "localnet") > + || !strcmp(binding_rec->type, "external")) { Why calling update_local_lport_ids() when the type is external? I think "our_chassis" is enough as the condition for "external" port to be considered. > update_local_lport_ids(local_lport_ids, binding_rec); > } > > diff --git a/ovn/controller/lflow.c b/ovn/controller/lflow.c > index 8db81927e..98e8ed3b9 100644 > --- a/ovn/controller/lflow.c > +++ b/ovn/controller/lflow.c > @@ -52,7 +52,10 @@ lflow_init(void) > struct lookup_port_aux { > struct ovsdb_idl_index *sbrec_multicast_group_by_name_datapath; > struct ovsdb_idl_index *sbrec_port_binding_by_name; > + struct ovsdb_idl_index *sbrec_port_binding_by_type; > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key; > const struct sbrec_datapath_binding *dp; > + const struct sbrec_chassis *chassis; > }; > > struct condition_aux { > @@ -66,6 +69,8 @@ static void consider_logical_flow( > struct ovsdb_idl_index *sbrec_chassis_by_name, > struct ovsdb_idl_index *sbrec_multicast_group_by_name_datapath, > struct ovsdb_idl_index *sbrec_port_binding_by_name, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > const struct sbrec_logical_flow *, > const struct hmap *local_datapaths, > const struct sbrec_chassis *, > @@ -89,8 +94,24 @@ lookup_port_cb(const void *aux_, const char *port_name, > unsigned int *portp) > const struct sbrec_port_binding *pb > = lport_lookup_by_name(aux->sbrec_port_binding_by_name, port_name); > if (pb && pb->datapath == aux->dp) { > - *portp = pb->tunnel_key; > - return true; > + if (strcmp(pb->type, "external")) { > + *portp = pb->tunnel_key; > + return true; > + } > + const char *chassis_id = smap_get(&pb->options, > + "requested-chassis"); > + if (chassis_id && (!strcmp(chassis_id, aux->chassis->name) || > + !strcmp(chassis_id, aux->chassis->hostname))) { > + const struct sbrec_port_binding *localnet_pb > + = lport_lookup_by_type(aux->sbrec_datapath_binding_by_key, > + aux->sbrec_port_binding_by_type, > + aux->dp->tunnel_key, "localnet"); > + if (localnet_pb) { > + *portp = localnet_pb->tunnel_key; > + return true; > + } > + } > + return false; > } > > const struct sbrec_multicast_group *mg = mcgroup_lookup_by_dp_name( > @@ -144,6 +165,8 @@ add_logical_flows( > struct ovsdb_idl_index *sbrec_chassis_by_name, > struct ovsdb_idl_index *sbrec_multicast_group_by_name_datapath, > struct ovsdb_idl_index *sbrec_port_binding_by_name, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > const struct sbrec_dhcp_options_table *dhcp_options_table, > const struct sbrec_dhcpv6_options_table *dhcpv6_options_table, > const struct sbrec_logical_flow_table *logical_flow_table, > @@ -183,6 +206,8 @@ add_logical_flows( > consider_logical_flow(sbrec_chassis_by_name, > sbrec_multicast_group_by_name_datapath, > sbrec_port_binding_by_name, > + sbrec_port_binding_by_type, > + sbrec_datapath_binding_by_key, > lflow, local_datapaths, > chassis, &dhcp_opts, &dhcpv6_opts, &nd_ra_opts, > addr_sets, port_groups, active_tunnels, > @@ -200,6 +225,8 @@ consider_logical_flow( > struct ovsdb_idl_index *sbrec_chassis_by_name, > struct ovsdb_idl_index *sbrec_multicast_group_by_name_datapath, > struct ovsdb_idl_index *sbrec_port_binding_by_name, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > const struct sbrec_logical_flow *lflow, > const struct hmap *local_datapaths, > const struct sbrec_chassis *chassis, > @@ -292,7 +319,10 @@ consider_logical_flow( > .sbrec_multicast_group_by_name_datapath > = sbrec_multicast_group_by_name_datapath, > .sbrec_port_binding_by_name = sbrec_port_binding_by_name, > - .dp = lflow->logical_datapath > + .sbrec_port_binding_by_type = sbrec_port_binding_by_type, > + .sbrec_datapath_binding_by_key = sbrec_datapath_binding_by_key, > + .dp = lflow->logical_datapath, > + .chassis = chassis > }; > struct condition_aux cond_aux = { > .sbrec_chassis_by_name = sbrec_chassis_by_name, > @@ -463,6 +493,8 @@ void > lflow_run(struct ovsdb_idl_index *sbrec_chassis_by_name, > struct ovsdb_idl_index *sbrec_multicast_group_by_name_datapath, > struct ovsdb_idl_index *sbrec_port_binding_by_name, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > const struct sbrec_dhcp_options_table *dhcp_options_table, > const struct sbrec_dhcpv6_options_table *dhcpv6_options_table, > const struct sbrec_logical_flow_table *logical_flow_table, > @@ -481,7 +513,8 @@ lflow_run(struct ovsdb_idl_index *sbrec_chassis_by_name, > > add_logical_flows(sbrec_chassis_by_name, > sbrec_multicast_group_by_name_datapath, > - sbrec_port_binding_by_name, dhcp_options_table, > + sbrec_port_binding_by_name, sbrec_port_binding_by_type, > + sbrec_datapath_binding_by_key, dhcp_options_table, > dhcpv6_options_table, logical_flow_table, > local_datapaths, chassis, addr_sets, port_groups, > active_tunnels, local_lport_ids, flow_table, > group_table, > diff --git a/ovn/controller/lflow.h b/ovn/controller/lflow.h > index d19338140..b2911e0eb 100644 > --- a/ovn/controller/lflow.h > +++ b/ovn/controller/lflow.h > @@ -68,6 +68,8 @@ void lflow_init(void); > void lflow_run(struct ovsdb_idl_index *sbrec_chassis_by_name, > struct ovsdb_idl_index > *sbrec_multicast_group_by_name_datapath, > struct ovsdb_idl_index *sbrec_port_binding_by_name, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > const struct sbrec_dhcp_options_table *, > const struct sbrec_dhcpv6_options_table *, > const struct sbrec_logical_flow_table *, > diff --git a/ovn/controller/lport.c b/ovn/controller/lport.c > index cc5c5fbb2..9c827d9b0 100644 > --- a/ovn/controller/lport.c > +++ b/ovn/controller/lport.c > @@ -64,6 +64,32 @@ lport_lookup_by_key(struct ovsdb_idl_index > *sbrec_datapath_binding_by_key, > return retval; > } > > +const struct sbrec_port_binding * > +lport_lookup_by_type(struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + uint64_t dp_key, const char *port_type) > +{ > + /* Lookup datapath corresponding to dp_key. */ > + const struct sbrec_datapath_binding *db = datapath_lookup_by_key( > + sbrec_datapath_binding_by_key, dp_key); > + if (!db) { > + return NULL; > + } > + > + /* Build key for an indexed lookup. */ > + struct sbrec_port_binding *pb = sbrec_port_binding_index_init_row( > + sbrec_port_binding_by_type); > + sbrec_port_binding_index_set_datapath(pb, db); > + sbrec_port_binding_index_set_type(pb, port_type); The index sbrec_port_binding_by_type was defined with only one column (type), but here it is set with 2 columns. Would it get wrong result? > + > + const struct sbrec_port_binding *retval = sbrec_port_binding_index_find( > + sbrec_port_binding_by_type, pb); > + > + sbrec_port_binding_index_destroy_row(pb); > + > + return retval; > +} > + > const struct sbrec_datapath_binding * > datapath_lookup_by_key(struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > uint64_t dp_key) > diff --git a/ovn/controller/lport.h b/ovn/controller/lport.h > index 7dcd5bee0..2d49792f6 100644 > --- a/ovn/controller/lport.h > +++ b/ovn/controller/lport.h > @@ -42,6 +42,11 @@ const struct sbrec_port_binding *lport_lookup_by_key( > struct ovsdb_idl_index *sbrec_port_binding_by_key, > uint64_t dp_key, uint64_t port_key); > > +const struct sbrec_port_binding *lport_lookup_by_type( > + struct ovsdb_idl_index *sbrec_datapath_binding_by_key, > + struct ovsdb_idl_index *sbrec_port_binding_by_type, > + uint64_t dp_key, const char *port_type); > + > const struct sbrec_datapath_binding *datapath_lookup_by_key( > struct ovsdb_idl_index *sbrec_datapath_binding_by_key, uint64_t dp_key); > > diff --git a/ovn/controller/ovn-controller.c b/ovn/controller/ovn-controller.c > index 4e9a5865f..5aab9142f 100644 > --- a/ovn/controller/ovn-controller.c > +++ b/ovn/controller/ovn-controller.c > @@ -145,6 +145,7 @@ update_sb_monitors(struct ovsdb_idl *ovnsb_idl, > * ports that have a Gateway_Chassis that point's to our own > * chassis */ > sbrec_port_binding_add_clause_type(&pb, OVSDB_F_EQ, "chassisredirect"); > + sbrec_port_binding_add_clause_type(&pb, OVSDB_F_EQ, "external"); > if (chassis) { > /* This should be mostly redundant with the other clauses for port > * bindings, but it allows us to catch any ports that are assigned to > @@ -616,6 +617,9 @@ main(int argc, char *argv[]) > struct ovsdb_idl_index *sbrec_port_binding_by_datapath > = ovsdb_idl_index_create1(ovnsb_idl_loop.idl, > &sbrec_port_binding_col_datapath); > + struct ovsdb_idl_index *sbrec_port_binding_by_type > + = ovsdb_idl_index_create1(ovnsb_idl_loop.idl, > + &sbrec_port_binding_col_type); > struct ovsdb_idl_index *sbrec_datapath_binding_by_key > = ovsdb_idl_index_create1(ovnsb_idl_loop.idl, > &sbrec_datapath_binding_col_tunnel_key); > @@ -743,6 +747,8 @@ main(int argc, char *argv[]) > sbrec_chassis_by_name, > sbrec_multicast_group_by_name_datapath, > sbrec_port_binding_by_name, > + sbrec_port_binding_by_type, > + sbrec_datapath_binding_by_key, > sbrec_dhcp_options_table_get(ovnsb_idl_loop.idl), > > sbrec_dhcpv6_options_table_get(ovnsb_idl_loop.idl), > sbrec_logical_flow_table_get(ovnsb_idl_loop.idl), > diff --git a/ovn/lib/ovn-util.c b/ovn/lib/ovn-util.c > index e9464e926..0e4439c5d 100644 > --- a/ovn/lib/ovn-util.c > +++ b/ovn/lib/ovn-util.c > @@ -311,6 +311,7 @@ static const char *OVN_NB_LSP_TYPES[] = { > "localport", > "router", > "vtep", > + "external", > }; > > bool > diff --git a/ovn/northd/ovn-northd.8.xml b/ovn/northd/ovn-northd.8.xml > index f52699bd3..c133969ed 100644 > --- a/ovn/northd/ovn-northd.8.xml > +++ b/ovn/northd/ovn-northd.8.xml > @@ -113,6 +113,26 @@ > logical ports on which port security is not enabled, these advance > all > packets that match the <code>inport</code>. > </li> > + > + <li> > + <p> > + For each logical port of type <code>external</code> with port > + security enabled and the logical switch to which it belongs, has a > + localnet port, a priority 90 flow is added which matches on the > + <code>inport</code> of localnet port and the valid > + <code>eth.src</code> address(es) of the <code>external</code> > + logical port and sets the <code>REGBIT_EXT_PORT_NOT_RESIDENT</code> > + flag if the logical port doesn't reside on a chassis and advances > the > + packet to the next flow table. > + </p> > + > + <p> > + On the chassis where the <code>external</code> port resides doesn't > + add the above flow. The priority 50 flow with the match on the > + <code>inport</code> of the localnet port takes care of forwarding > + the packet to the next flow table. > + </p> > + </li> > </ul> > > <p> > @@ -626,7 +646,8 @@ nd_na_router { > <p> > This table adds the DHCPv4 options to a DHCPv4 packet from the > logical ports configured with IPv4 address(es) and DHCPv4 options, > - and similarly for DHCPv6 options. > + and similarly for DHCPv6 options. This table also adds flows for the > + logical ports of type <code>external</code>. > </p> > > <ul> > @@ -827,7 +848,34 @@ output; > </li> > </ul> > > - <h3>Ingress Table 16 Destination Lookup</h3> > + <h3>Ingress table 16 External ports</h3> > + > + <p> > + Traffic from the <code>external</code> logical ports enter the ingress > + datapath pipeline via the <code>localnet</code> port. This table adds > the > + below logical flows to handle the traffic from these ports. > + </p> > + > + <ul> > + <li> > + <p> > + For each router port IP address <code>A</code> which belongs to the > + logical switch, A priority-100 flow is added which matches > + <code>REGBIT_EXT_PORT_NOT_RESIDENT && arp.tpa == > <var>A</var> > + && arp.op == 1</code> (ARP request to the router > + IP) with the action to <code>drop</code> the packet. > + </p> > + > + <p> > + These flows guarantees that the ARP/NS request to the router IP > + address from the external ports is responded by only the chassis > + which has claimed these external ports. All the other chassis, > + drops these packets. > + </p> > + </li> > + </ul> > + > + <h3>Ingress Table 17 Destination Lookup</h3> > > <p> > This table implements switching behavior. It contains these logical > diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c > index 2de9fb38d..24203b50d 100644 > --- a/ovn/northd/ovn-northd.c > +++ b/ovn/northd/ovn-northd.c > @@ -119,7 +119,8 @@ enum ovn_stage { > PIPELINE_STAGE(SWITCH, IN, DHCP_RESPONSE, 13, "ls_in_dhcp_response") \ > PIPELINE_STAGE(SWITCH, IN, DNS_LOOKUP, 14, "ls_in_dns_lookup") \ > PIPELINE_STAGE(SWITCH, IN, DNS_RESPONSE, 15, "ls_in_dns_response") \ > - PIPELINE_STAGE(SWITCH, IN, L2_LKUP, 16, "ls_in_l2_lkup") \ > + PIPELINE_STAGE(SWITCH, IN, EXTERNAL_PORT, 16, "ls_in_external_port") \ > + PIPELINE_STAGE(SWITCH, IN, L2_LKUP, 17, "ls_in_l2_lkup") \ > \ > /* Logical switch egress stages. */ \ > PIPELINE_STAGE(SWITCH, OUT, PRE_LB, 0, "ls_out_pre_lb") \ > @@ -166,12 +167,13 @@ enum ovn_stage { > #define OVN_ACL_PRI_OFFSET 1000 > > /* Register definitions specific to switches. */ > -#define REGBIT_CONNTRACK_DEFRAG "reg0[0]" > -#define REGBIT_CONNTRACK_COMMIT "reg0[1]" > -#define REGBIT_CONNTRACK_NAT "reg0[2]" > -#define REGBIT_DHCP_OPTS_RESULT "reg0[3]" > -#define REGBIT_DNS_LOOKUP_RESULT "reg0[4]" > -#define REGBIT_ND_RA_OPTS_RESULT "reg0[5]" > +#define REGBIT_CONNTRACK_DEFRAG "reg0[0]" > +#define REGBIT_CONNTRACK_COMMIT "reg0[1]" > +#define REGBIT_CONNTRACK_NAT "reg0[2]" > +#define REGBIT_DHCP_OPTS_RESULT "reg0[3]" > +#define REGBIT_DNS_LOOKUP_RESULT "reg0[4]" > +#define REGBIT_ND_RA_OPTS_RESULT "reg0[5]" > +#define REGBIT_EXT_PORT_NOT_RESIDENT "reg0[6]" > > /* Register definitions for switches and routers. */ > #define REGBIT_NAT_REDIRECT "reg9[0]" > @@ -452,6 +454,8 @@ struct ovn_datapath { > > /* Port groups related to the datapath, used only when nbs is NOT NULL. > */ > struct hmap nb_pgs; > + > + bool has_external_ports; > }; > > struct macam_node { > @@ -1610,6 +1614,10 @@ join_logical_ports(struct northd_context *ctx, > od->localnet_port = op; > } > > + if (!strcmp(nbsp->type, "external")) { > + od->has_external_ports = true; > + } > + > op->lsp_addrs > = xmalloc(sizeof *op->lsp_addrs * nbsp->n_addresses); > for (size_t j = 0; j < nbsp->n_addresses; j++) { > @@ -2905,6 +2913,12 @@ lsp_is_up(const struct nbrec_logical_switch_port *lsp) > return !lsp->up || *lsp->up; > } > > +static bool > +lsp_is_external(const struct nbrec_logical_switch_port *nbsp) > +{ > + return !strcmp(nbsp->type, "external"); > +} > + > static bool > build_dhcpv4_action(struct ovn_port *op, ovs_be32 offer_ip, > struct ds *options_action, struct ds *response_action, > @@ -4086,9 +4100,24 @@ build_lswitch_flows(struct hmap *datapaths, struct > hmap *ports, > continue; > } > > + bool is_external = lsp_is_external(op->nbsp); > + if (is_external && (!op->od->localnet_port || !op->n_ps_addrs)) { > + /* If the lsp is external with no port securty addresses then, > + * we don't need to add any port security rules. > + * The packets from external ports is received on localnet port > + * and we allow the traffic from localnet ports. > + * > + * We also need to ignore these ports if the logical switch > + * doesn't have a localnet port. > + */ > + continue; > + } > + > ds_clear(&match); > ds_clear(&actions); > - ds_put_format(&match, "inport == %s", op->json_key); > + ds_put_format( > + &match, "inport == %s", > + is_external ? op->od->localnet_port->json_key : op->json_key); > build_port_security_l2("eth.src", op->ps_addrs, op->n_ps_addrs, > &match); It seems matching eth.src depends on setting port-security on the external port. If port-security is not enabled on the port, eth.src won't be in match condition, and the following code would generate a logical flow that sets REGBIT_EXT_PORT_NOT_RESIDENT = 1 for all packets coming in from localnet port. Did I misunderstand something here? Maybe port-security stage is not the right place to set the flag? > > @@ -4096,11 +4125,21 @@ build_lswitch_flows(struct hmap *datapaths, struct > hmap *ports, > if (queue_id) { > ds_put_format(&actions, "set_queue(%s); ", queue_id); > } > + > + if (is_external) { > + /* Set REGBIT_EXT_PORT_NOT_RESIDENT bit if the external port > + * doesn't reside on a chassis. */ > + ds_put_format(&match, " && !is_chassis_resident(%s)", > + op->json_key); > + ds_put_cstr(&actions, REGBIT_EXT_PORT_NOT_RESIDENT" = 1; "); > + } > + > ds_put_cstr(&actions, "next;"); > - ovn_lflow_add(lflows, op->od, S_SWITCH_IN_PORT_SEC_L2, 50, > + ovn_lflow_add(lflows, op->od, S_SWITCH_IN_PORT_SEC_L2, > + is_external ? 90 : 50, > ds_cstr(&match), ds_cstr(&actions)); > > - if (op->nbsp->n_port_security) { > + if (op->nbsp->n_port_security && !is_external) { > build_port_security_ip(P_IN, op, lflows); > build_port_security_nd(op, lflows); > } > @@ -4148,7 +4187,7 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap > *ports, > * - port type is localport > */ > if (!lsp_is_up(op->nbsp) && strcmp(op->nbsp->type, "router") && > - strcmp(op->nbsp->type, "localport")) { > + strcmp(op->nbsp->type, "localport") && > lsp_is_external(op->nbsp)) { > continue; > } > > @@ -4260,6 +4299,13 @@ build_lswitch_flows(struct hmap *datapaths, struct > hmap *ports, > continue; > } > > + bool is_external = lsp_is_external(op->nbsp); > + if (is_external && !op->od->localnet_port) { > + /* If it's an external port and there is no localnet port > + * ignore it. */ > + continue; > + } > + > for (size_t i = 0; i < op->n_lsp_addrs; i++) { > for (size_t j = 0; j < op->lsp_addrs[i].n_ipv4_addrs; j++) { > struct ds options_action = DS_EMPTY_INITIALIZER; > @@ -4272,8 +4318,8 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap > *ports, > ds_put_format( > &match, "inport == %s && eth.src == %s && " > "ip4.src == 0.0.0.0 && ip4.dst == 255.255.255.255 && > " > - "udp.src == 68 && udp.dst == 67", op->json_key, > - op->lsp_addrs[i].ea_s); > + "udp.src == 68 && udp.dst == 67", > + op->json_key, op->lsp_addrs[i].ea_s); > > ovn_lflow_add(lflows, op->od, S_SWITCH_IN_DHCP_OPTIONS, > 100, ds_cstr(&match), > @@ -4378,7 +4424,8 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap > *ports, > /* Ingress table 12 and 13: DHCP options and response, by default goto > * next. (priority 0). > * Ingress table 14 and 15: DNS lookup and response, by default goto > next. > - * (priority 0).*/ > + * (priority 0). > + * Ingress table 16 - External port handling */ > > HMAP_FOR_EACH (od, key_node, datapaths) { > if (!od->nbs) { > @@ -4389,9 +4436,47 @@ build_lswitch_flows(struct hmap *datapaths, struct > hmap *ports, > ovn_lflow_add(lflows, od, S_SWITCH_IN_DHCP_RESPONSE, 0, "1", > "next;"); > ovn_lflow_add(lflows, od, S_SWITCH_IN_DNS_LOOKUP, 0, "1", "next;"); > ovn_lflow_add(lflows, od, S_SWITCH_IN_DNS_RESPONSE, 0, "1", "next;"); > + ovn_lflow_add(lflows, od, S_SWITCH_IN_EXTERNAL_PORT, 0, "1", > "next;"); > + > + if (od->has_external_ports) { > + /* Table 16: External port. Drop ARP request for router ips from > + * external ports if REGBIT_EXT_PORT_NOT_RESIDENT is set. > + * This makes the router pipeline to be run only the chassis s/only the chassis/only on the chassis/ > + * binding the external ports. */ > + for (size_t i = 0; i < od->n_router_ports; i++) { > + struct ovn_port *rp = od->router_ports[i]; > + for (size_t j = 0; j < rp->n_lsp_addrs; j++) { > + for (size_t k = 0; k < rp->lsp_addrs[j].n_ipv4_addrs; > + k++) { > + ds_clear(&match); > + ds_put_format( > + &match, REGBIT_EXT_PORT_NOT_RESIDENT"" > + " && arp.tpa == %s && arp.op == 1", > + rp->lsp_addrs[j].ipv4_addrs[k].addr_s); > + ds_clear(&actions); > + ovn_lflow_add(lflows, od, S_SWITCH_IN_EXTERNAL_PORT, > + 100, ds_cstr(&match), "drop;"); > + } > + for (size_t k = 0; k < rp->lsp_addrs[j].n_ipv6_addrs; > + k++) { > + ds_clear(&match); > + ds_put_format( > + &match, REGBIT_EXT_PORT_NOT_RESIDENT"" > + " && nd_ns && ip6.dst == {%s, %s} && " > + "nd.target == %s", > + rp->lsp_addrs[j].ipv6_addrs[k].addr_s, > + rp->lsp_addrs[j].ipv6_addrs[k].sn_addr_s, > + rp->lsp_addrs[j].ipv6_addrs[k].addr_s); > + ds_clear(&actions); > + ovn_lflow_add(lflows, od, S_SWITCH_IN_EXTERNAL_PORT, > + 100, ds_cstr(&match), "drop;"); > + } > + } > + } > + } > } > > - /* Ingress table 16: Destination lookup, broadcast and multicast handling > + /* Ingress table 17: Destination lookup, broadcast and multicast handling > * (priority 100). */ > HMAP_FOR_EACH (op, key_node, ports) { > if (!op->nbsp) { > @@ -4411,9 +4496,9 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap > *ports, > "outport = \""MC_FLOOD"\"; output;"); > } > > - /* Ingress table 16: Destination lookup, unicast handling (priority 50), > */ > + /* Ingress table 17: Destination lookup, unicast handling (priority 50), > */ > HMAP_FOR_EACH (op, key_node, ports) { > - if (!op->nbsp) { > + if (!op->nbsp || lsp_is_external(op->nbsp)) { > continue; > } > > @@ -4530,7 +4615,7 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap > *ports, > } > } > > - /* Ingress table 16: Destination lookup for unknown MACs (priority 0). */ > + /* Ingress table 17: Destination lookup for unknown MACs (priority 0). */ > HMAP_FOR_EACH (od, key_node, datapaths) { > if (!od->nbs) { > continue; > @@ -4565,7 +4650,7 @@ build_lswitch_flows(struct hmap *datapaths, struct hmap > *ports, > * Priority 150 rules drop packets to disabled logical ports, so that > they > * don't even receive multicast or broadcast packets. */ > HMAP_FOR_EACH (op, key_node, ports) { > - if (!op->nbsp) { > + if (!op->nbsp || lsp_is_external(op->nbsp)) { > continue; > } > > diff --git a/ovn/ovn-architecture.7.xml b/ovn/ovn-architecture.7.xml > index 3936e6016..71bdb64df 100644 > --- a/ovn/ovn-architecture.7.xml > +++ b/ovn/ovn-architecture.7.xml > @@ -1678,6 +1678,82 @@ > </li> > </ol> > > + <h2>Native OVN services for external logical ports</h2> > + > + <p> > + To support OVN native services (like DHCP/IPv6 RA/DNS lookup) to the > + cloud resources which are external, OVN supports <code>external</code> > + logical ports. > + </p> > + > + <p> > + Below are some of the use cases where <code>external</code> ports can be > + used. > + </p> > + > + <ul> > + <li> > + VMs connected to SR-IOV nics - Traffic from these VMs by passes the > + kernel stack and local <code>ovn-controller</code> do not bind these > + ports and cannot serve the native services. > + </li> > + <li> > + When CMS supports provisioning baremetal servers. > + </li> > + </ul> > + > + <p> > + OVN will provide the native services if CMS has done the below > + configuration in the <dfn>OVN Northbound Database</dfn>. > + </p> > + > + <ul> > + <li> > + A row is created in <code>Logical_Switch_Port</code>, configuring the > + <ref column="addresses" table="Logical_Switch_Port" db="OVN_NB"/> > column > + and setting the <ref column="type" table="Logical_Switch_Port" > + db="OVN_NB"/> to <code>external</code>. > + </li> > + > + <li> > + <ref column="options:requested-chassis" table="Logical_Switch_Port" > + db="OVN_NB"/> column is configured to a desired chassis. > + </li> > + > + <li> > + The chassis on which this logical port is requested has the > + <code>ovn-bridge-mappings</code> configured and has proper L2 > + connectivity so that it can receive the DHCP and other related request > + packets from these external resources. > + </li> > + > + <li> > + The Logical_Switch of this port has a <code>localnet</code> port. > + </li> > + > + <li> > + Native OVN services are enabled by configuring the DHCP and other > + options like the way it is done for the normal logical ports. > + </li> > + </ul> > + > + <p> > + OVN doesn't support HA for these <code>external</code> ports. In case > + the <code>ovn-controller</code> running on the requested chassis goes > down, > + it is the responsiblity of CMS, to reschedule these <code>external</code> > + ports to other active chassis. > + </p> > + > + <p> > + It is recommended to request the same chassis for all the external ports. > + Otherwise, the physical switch might see MAC flap issue when different > + chassis provide the native services. For example when supporting native > + DHCPv4 service, DHCPv4 server mac (configured in > + <ref column="options:server_mac" table="DHCP_Options" db="OVN_NB"/> > column > + in table <ref table="DHCP_Options"/>) > + originating from different ports can cause MAC flap issue. > + </p> > + > <h1>Security</h1> > > <h2>Role-Based Access Controls for the Soutbound DB</h2> > diff --git a/ovn/ovn-nb.xml b/ovn/ovn-nb.xml > index 4141751f8..e45d07f1d 100644 > --- a/ovn/ovn-nb.xml > +++ b/ovn/ovn-nb.xml > @@ -348,6 +348,50 @@ > <dd> > A port to a logical switch on a VTEP gateway. > </dd> > + > + <dt><code>external</code></dt> > + <dd> > + <p> > + Represents a logical port which is external and not having > + an OVS port in the integration bridge. > + <code>OVN</code> will never receive any traffic from this port > or > + send any traffic to this port. <code>OVN</code> can support > + native services like DHCPv4/DHCPv6/DNS for this port. > + If <ref column="options:requested-chassis"/> is defined, > + <code>ovn-controller</code> running in that chassis will bind > + this port to provide these native services. It is expected that > + this port belong to a bridged logical switch > + (with a <code>localnet</code> port). > + </p> > + > + <p> > + It is recommended to request the same chassis for all the > + external ports. Otherwise, the physical switch might see > + MAC flap issue when different chassis provide the native > + services. For example when supporting native DHCPv4 > + service, DHCPv4 server mac (configured in > + <ref column="options:server_mac" table="DHCP_Options" > + db="OVN_NB"/> column in table <ref table="DHCP_Options"/>) > + originating from different ports can cause MAC flap issue. > + </p> > + > + <p> > + Below are some of the use cases where <code>external</code> > + ports can be used. > + </p> > + > + <ul> > + <li> > + VMs connected to SR-IOV nics - Traffic from these VMs by > passes > + the kernel stack and local <code>ovn-controller</code> do not > + bind these ports and cannot serve the native services. > + </li> > + > + <li> > + When CMS supports provisioning baremetal servers. > + </li> > + </ul> > + </dd> > </dl> > </column> > </group> > diff --git a/tests/ovn.at b/tests/ovn.at > index 2db3f675a..9598a81ae 100644 > --- a/tests/ovn.at > +++ b/tests/ovn.at > @@ -9456,9 +9456,9 @@ AT_CHECK([as hv2 ovs-ofctl dump-flows br-int table=32 | > grep active_backup | gre > sleep 3 # let BFD sessions settle so we get the right flows on the right > chassis > > # make sure that flows for handling the outside router port reside on gw1 > -AT_CHECK([as gw1 ovs-ofctl dump-flows br-int table=24 | grep > 00:00:02:01:02:04 | wc -l], [0], [[1 > +AT_CHECK([as gw1 ovs-ofctl dump-flows br-int table=25 | grep > 00:00:02:01:02:04 | wc -l], [0], [[1 > ]]) > -AT_CHECK([as gw2 ovs-ofctl dump-flows br-int table=24 | grep > 00:00:02:01:02:04 | wc -l], [0], [[0 > +AT_CHECK([as gw2 ovs-ofctl dump-flows br-int table=25 | grep > 00:00:02:01:02:04 | wc -l], [0], [[0 > ]]) > > # make sure ARP responder flows for outside router port reside on gw1 too > @@ -9548,9 +9548,9 @@ AT_CHECK([ovs-vsctl --bare --columns bfd find Interface > name=ovn-hv1-0],[0], > sleep 3 # let BFD sessions settle so we get the right flows on the right > chassis > > # make sure that flows for handling the outside router port reside on gw2 now > -AT_CHECK([as gw2 ovs-ofctl dump-flows br-int table=24 | grep > 00:00:02:01:02:04 | wc -l], [0], [[1 > +AT_CHECK([as gw2 ovs-ofctl dump-flows br-int table=25 | grep > 00:00:02:01:02:04 | wc -l], [0], [[1 > ]]) > -AT_CHECK([as gw1 ovs-ofctl dump-flows br-int table=24 | grep > 00:00:02:01:02:04 | wc -l], [0], [[0 > +AT_CHECK([as gw1 ovs-ofctl dump-flows br-int table=25 | grep > 00:00:02:01:02:04 | wc -l], [0], [[0 > ]]) > > # disconnect GW2 from the network, GW1 should take over > @@ -9562,9 +9562,9 @@ sleep 4 > bfd_dump > > # make sure that flows for handling the outside router port reside on gw2 now > -AT_CHECK([as gw1 ovs-ofctl dump-flows br-int table=24 | grep > 00:00:02:01:02:04 | wc -l], [0], [[1 > +AT_CHECK([as gw1 ovs-ofctl dump-flows br-int table=25 | grep > 00:00:02:01:02:04 | wc -l], [0], [[1 > ]]) > -AT_CHECK([as gw2 ovs-ofctl dump-flows br-int table=24 | grep > 00:00:02:01:02:04 | wc -l], [0], [[0 > +AT_CHECK([as gw2 ovs-ofctl dump-flows br-int table=25 | grep > 00:00:02:01:02:04 | wc -l], [0], [[0 > ]]) > > # check that the chassis redirect port has been reclaimed by the gw1 chassis > @@ -11431,6 +11431,524 @@ as hv2 start_daemon ovn-controller > OVN_CLEANUP([hv1],[hv2]) > AT_CLEANUP > > +AT_SETUP([ovn -- external logical port]) > +AT_SKIP_IF([test $HAVE_PYTHON = no]) > +ovn_start > + > +net_add n1 > +sim_add hv1 > +sim_add hv2 > + > +ovn-nbctl ls-add ls1 > +ovn-nbctl lsp-add ls1 ls1-lp1 \ > +-- lsp-set-addresses ls1-lp1 "f0:00:00:00:00:01 10.0.0.4 ae70::4" > + > +# Add a couple of external logical port > +ovn-nbctl lsp-add ls1 ls1-lp_ext1 \ > +-- lsp-set-addresses ls1-lp_ext1 "f0:00:00:00:00:03 10.0.0.6 ae70::6" > +ovn-nbctl lsp-set-port-security ls1-lp_ext1 \ > +"f0:00:00:00:00:03 10.0.0.6 ae70::6" > +ovn-nbctl lsp-set-type ls1-lp_ext1 external > + > +ovn-nbctl lsp-add ls1 ls1-lp_ext2 \ > +-- lsp-set-addresses ls1-lp_ext2 "f0:00:00:00:00:04 10.0.0.7 ae70::7" > +ovn-nbctl lsp-set-port-security ls1-lp_ext2 \ > +"f0:00:00:00:00:04 10.0.0.7 ae70::8" > +ovn-nbctl lsp-set-type ls1-lp_ext2 external > + > +d1="$(ovn-nbctl create DHCP_Options cidr=10.0.0.0/24 \ > +options="\"server_id\"=\"10.0.0.1\" \"server_mac\"=\"ff:10:00:00:00:01\" \ > +\"lease_time\"=\"3600\" \"router\"=\"10.0.0.1\"")" > + > +d2="$(ovn-nbctl create DHCP_Options cidr="ae70\:\:/64" \ > +options="\"server_id\"=\"00:00:00:10:00:01\"")" > + > +ovn-nbctl lsp-set-dhcpv4-options ls1-lp1 ${d1} > +ovn-nbctl lsp-set-dhcpv4-options ls1-lp_ext1 ${d1} > +ovn-nbctl lsp-set-dhcpv4-options ls1-lp_ext2 ${d1} > + > +ovn-nbctl lsp-set-dhcpv6-options ls1-lp1 ${d2} > +ovn-nbctl lsp-set-dhcpv6-options ls1-lp_ext1 ${d2} > +ovn-nbctl lsp-set-dhcpv6-options ls1-lp_ext2 ${d2} > + > +# Create a logical router and connect it to ls1 > +ovn-nbctl lr-add lr0 > +ovn-nbctl lrp-add lr0 lr0-ls1 a0:10:00:00:00:01 10.0.0.1/24 > +ovn-nbctl lsp-add ls1 ls1-lr0 > +ovn-nbctl set Logical_Switch_Port ls1-lr0 type=router \ > + options:router-port=lr0-ls1 addresses=router > + > +as hv1 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.1 > +ovs-vsctl -- add-port br-phys hv1-ext1 -- \ > + set interface hv1-ext1 options:tx_pcap=hv1/ext1-tx.pcap \ > + options:rxq_pcap=hv1/ext1-rx.pcap \ > + ofport-request=2 > +ovs-vsctl set open . external-ids:ovn-bridge-mappings=phys:br-phys > + > +as hv2 > +ovs-vsctl add-br br-phys > +ovn_attach n1 br-phys 192.168.0.2 > +ovs-vsctl -- add-port br-phys hv2-ext2 -- \ > + set interface hv2-ext2 options:tx_pcap=hv2/ext2-tx.pcap \ > + options:rxq_pcap=hv2/ext2-rx.pcap \ > + ofport-request=2 > +ovs-vsctl set open . external-ids:ovn-bridge-mappings=phys:br-phys > + > +ovn-sbctl dump-flows > lflows_n.txt > + > +# No DHCPv4/v6 flows for the external port - ls1-lp_ext1 - 10.0.0.6 in hv1 > and > +# hv2 as requested-chassis option is not set and no localnet port added to > ls1. > +AT_CHECK([ovn-sbctl dump-flows ls1 | grep "offerip = 10.0.0.6" | \ > +wc -l], [0], [0 > +]) > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | wc -l], [0], [0 > +]) > + > +hv1_uuid=$(ovn-sbctl list chassis hv1 | grep uuid | awk '{print $3}') > + > +# The port_binding row for ls1-lp_ext1 should have empty chassis > +chassis=$(ovn-sbctl list port_binding ls1-lp_ext1 | grep -v gateway | \ > +grep -v requested | grep chassis | awk '{print $3}') > + > +AT_CHECK([test $chassis == "[[]]"], [0], []) > + > +# Set the requested-chassis option for ls1-lp_ext1 > +ovn-nbctl --wait=hv lsp-set-options ls1-lp_ext1 requested-chassis=hv1 > + > +# No DHCPv4/v6 flows for the external port - ls1-lp_ext1 - 10.0.0.6 in hv1 > and hv2 > +# as no localnet port added to ls1 yet. > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | wc -l], [0], [0 > +]) > + > +# Add the localnet port to the logical switch ls1 > +ovn-nbctl lsp-add ls1 ln-public > +ovn-nbctl lsp-set-addresses ln-public unknown > +ovn-nbctl lsp-set-type ln-public localnet > +ovn-nbctl --wait=hv lsp-set-options ln-public network_name=phys > + > +ln_public_key=$(ovn-sbctl list port_binding ln-public | grep tunnel_key | \ > +awk '{print $3}') > + > +# The ls1-lp_ext1 should be bound to hv1 > +chassis=$(ovn-sbctl list port_binding ls1-lp_ext1 | grep -v gateway | \ > +grep -v requested | grep chassis | awk '{print $3}') > +AT_CHECK([test $chassis == "$hv1_uuid"], [0], []) > + > +# There should be DHCPv4/v6 OF flows for the ls1-lp_ext1 port in hv1 > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | grep reg14=0x$ln_public_key | \ > +wc -l], [0], [3 > +]) > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | \ > +grep reg14=0x$ln_public_key | wc -l], [0], [1 > +]) > + > +# There should ne no DHCPv4/v6 flows for ls1-lp_ext1 on hv2 > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | wc -l], [0], [0 > +]) > + > +# No DHCPv4/v6 flows for the external port - ls1-lp_ext2 - 10.0.0.7 in hv1 > and > +# hv2 as requested-chassis option is not set. > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.07" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.07" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.07" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.07" | wc -l], [0], [0 > +]) > + > +as hv1 > +ovs-vsctl show > + > +# This shell function sends a DHCP request packet > +# test_dhcp INPORT SRC_MAC DHCP_TYPE OFFER_IP ... > +test_dhcp() { > + local inport=$1 src_mac=$2 dhcp_type=$3 offer_ip=$4 use_ip=$5 > + shift; shift; shift; shift; shift; > + if test $use_ip != 0; then > + src_ip=$1 > + dst_ip=$2 > + shift; shift; > + else > + src_ip=`ip_to_hex 0 0 0 0` > + dst_ip=`ip_to_hex 255 255 255 255` > + fi > + local > request=ffffffffffff${src_mac}0800451001100000000080110000${src_ip}${dst_ip} > + # udp header and dhcp header > + request=${request}0044004300fc0000 > + > request=${request}010106006359aa760000000000000000000000000000000000000000${src_mac} > + # client hardware padding > + request=${request}00000000000000000000 > + # server hostname > + > request=${request}0000000000000000000000000000000000000000000000000000000000000000 > + > request=${request}0000000000000000000000000000000000000000000000000000000000000000 > + # boot file name > + > request=${request}0000000000000000000000000000000000000000000000000000000000000000 > + > request=${request}0000000000000000000000000000000000000000000000000000000000000000 > + > request=${request}0000000000000000000000000000000000000000000000000000000000000000 > + > request=${request}0000000000000000000000000000000000000000000000000000000000000000 > + # dhcp magic cookie > + request=${request}63825363 > + # dhcp message type > + request=${request}3501${dhcp_type}ff > + > + local srv_mac=$1 srv_ip=$2 expected_dhcp_opts=$3 > + # total IP length will be the IP length of the request packet > + # (which is 272 in our case) + 8 (padding bytes) + (expected_dhcp_opts / > 2) > + ip_len=`expr 280 + ${#expected_dhcp_opts} / 2` > + udp_len=`expr $ip_len - 20` > + ip_len=$(printf "%x" $ip_len) > + udp_len=$(printf "%x" $udp_len) > + # $ip_len var will be in 3 digits i.e 134. So adding a '0' before $ip_len > + local > reply=${src_mac}${srv_mac}080045100${ip_len}000000008011XXXX${srv_ip}${offer_ip} > + # udp header and dhcp header. > + # $udp_len var will be in 3 digits. So adding a '0' before $udp_len > + reply=${reply}004300440${udp_len}0000020106006359aa760000000000000000 > + # your ip address > + reply=${reply}${offer_ip} > + # next server ip address, relay agent ip address, client mac address > + reply=${reply}0000000000000000${src_mac} > + # client hardware padding > + reply=${reply}00000000000000000000 > + # server hostname > + > reply=${reply}0000000000000000000000000000000000000000000000000000000000000000 > + > reply=${reply}0000000000000000000000000000000000000000000000000000000000000000 > + # boot file name > + > reply=${reply}0000000000000000000000000000000000000000000000000000000000000000 > + > reply=${reply}0000000000000000000000000000000000000000000000000000000000000000 > + > reply=${reply}0000000000000000000000000000000000000000000000000000000000000000 > + > reply=${reply}0000000000000000000000000000000000000000000000000000000000000000 > + # dhcp magic cookie > + reply=${reply}63825363 > + # dhcp message type > + local dhcp_reply_type=02 > + if test $dhcp_type = 03; then > + dhcp_reply_type=05 > + fi > + > reply=${reply}3501${dhcp_reply_type}${expected_dhcp_opts}00000000ff00000000 > + echo $reply >> ext1_v4.expected > + > + as hv1 ovs-appctl netdev-dummy/receive hv${inport}-ext${inport} $request > +} > + > + > +trim_zeros() { > + sed 's/\(00\)\{1,\}$//' > +} > + > +# This shell function sends a DHCPv6 request packet > +# test_dhcpv6 INPORT SRC_MAC SRC_LLA DHCPv6_MSG_TYPE OFFER_IP OUTPORT... > +# The OUTPORTs (zero or more) list the VIFs on which the original DHCPv6 > +# packet should be received twice (one from ovn-controller and the other > +# from the "ovs-ofctl monitor br-int resume" > +test_dhcpv6() { > + local inport=$1 src_mac=$2 src_lla=$3 msg_code=$4 offer_ip=$5 > + local req_pkt_in_expected=$6 > + local request=ffffffffffff${src_mac}86dd00000000002a1101${src_lla} > + # dst ip ff02::1:2 > + request=${request}ff020000000000000000000000010002 > + # udp header and dhcpv6 header > + request=${request}02220223002affff${msg_code}010203 > + # Client identifier > + request=${request}0001000a00030001${src_mac} > + # IA-NA (Identity Association for Non Temporary Address) > + request=${request}0003000c0102030400000e1000001518 > + shift; shift; shift; shift; shift; > + > + local server_mac=000000100001 > + local server_lla=fe80000000000000020000fffe100001 > + local reply_code=07 > + if test $msg_code = 01; then > + reply_code=02 > + fi > + local msg_len=54 > + if test $offer_ip = 1; then > + msg_len=28 > + fi > + local reply=${src_mac}${server_mac}86dd0000000000${msg_len}1101 > + reply=${reply}${server_lla}${src_lla} > + > + # udp header and dhcpv6 header > + reply=${reply}0223022200${msg_len}ffff${reply_code}010203 > + # Client identifier > + reply=${reply}0001000a00030001${src_mac} > + # IA-NA > + if test $offer_ip != 1; then > + reply=${reply}0003002801020304ffffffffffffffff00050018${offer_ip} > + reply=${reply}ffffffffffffffff > + fi > + # Server identifier > + reply=${reply}0002000a00030001${server_mac} > + > + echo $reply | trim_zeros >> ext${inport}_v6.expected > + # The inport also receives the request packet since it is connected > + # to the br-phys. > + #echo $request >> ext${inport}_v6.expected > + > + as hv1 ovs-appctl netdev-dummy/receive hv${inport}-ext${inport} $request > +} > + > +reset_pcap_file() { > + local iface=$1 > + local pcap_file=$2 > + ovs-vsctl -- set Interface $iface options:tx_pcap=dummy-tx.pcap \ > +options:rxq_pcap=dummy-rx.pcap > + rm -f ${pcap_file}*.pcap > + ovs-vsctl -- set Interface $iface options:tx_pcap=${pcap_file}-tx.pcap \ > +options:rxq_pcap=${pcap_file}-rx.pcap > +} > + > +ip_to_hex() { > + printf "%02x%02x%02x%02x" "$@" > +} > + > +AT_CAPTURE_FILE([ofctl_monitor0_hv1.log]) > +as hv1 ovs-ofctl monitor br-int resume --detach --no-chdir \ > +--pidfile=ovs-ofctl0.pid 2> ofctl_monitor0_hv1.log > + > +AT_CAPTURE_FILE([ofctl_monitor0_hv2.log]) > +as hv2 ovs-ofctl monitor br-int resume --detach --no-chdir \ > +--pidfile=ovs-ofctl0.pid 2> ofctl_monitor0_hv2.log > + > +# Send DHCPDISCOVER. > +offer_ip=`ip_to_hex 10 0 0 6` > +server_ip=`ip_to_hex 10 0 0 1` > +server_mac=ff1000000001 > +expected_dhcp_opts=330400000e100104ffffff0003040a00000136040a000001 > +test_dhcp 1 f00000000003 01 $offer_ip 0 $server_mac $server_ip \ > +$expected_dhcp_opts > + > +# NXT_RESUMEs should be 1 in hv1. > +OVS_WAIT_UNTIL([test 1 = `cat ofctl_monitor0_hv1.log | grep -c NXT_RESUME`]) > + > +# NXT_RESUMEs should be 0 in hv2. > +OVS_WAIT_UNTIL([test 0 = `cat ofctl_monitor0_hv2.log | grep -c NXT_RESUME`]) > + > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/ext1-tx.pcap > > ext1_v4.packets > +cat ext1_v4.expected | cut -c -48 > expout > +AT_CHECK([cat ext1_v4.packets | cut -c -48], [0], [expout]) > +# Skipping the IPv4 checksum. > +cat ext1_v4.expected | cut -c 53- > expout > +AT_CHECK([cat ext1_v4.packets | cut -c 53-], [0], [expout]) > + > +# ovs-ofctl also resumes the packets and this causes other ports to receive > +# the DHCP request packet. So reset the pcap files so that its easier to > test. > +reset_pcap_file hv1-ext1 hv1/ext1 > +rm -f ext1_v4.expected > +rm -f ext1_v4.packets > + > +# Send DHCPv6 request > +src_mac=f00000000003 > +src_lla=fe80000000000000f20000fffe000003 > +offer_ip=ae700000000000000000000000000006 > +test_dhcpv6 1 $src_mac $src_lla 01 $offer_ip > + > +# NXT_RESUMEs should be 2 in hv1. > +OVS_WAIT_UNTIL([test 2 = `cat ofctl_monitor0_hv1.log | grep -c NXT_RESUME`]) > + > +# NXT_RESUMEs should be 0 in hv2. > +OVS_WAIT_UNTIL([test 0 = `cat ofctl_monitor0_hv2.log | grep -c NXT_RESUME`]) > + > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/ext1-tx.pcap | \ > +sort > ext1_v6.packets > +cat ext1_v6.expected | cut -c -120 > expout > +AT_CHECK([cat ext1_v6.packets | cut -c -120], [0], [expout]) > +# Skipping the UDP checksum > +cat ext1_v6.expected | cut -c 125- > expout > +AT_CHECK([cat ext1_v6.packets | cut -c 125-], [0], [expout]) > + > +rm -f ext1_v6.expected > +rm -f ext1_v6.packets > +reset_pcap_file hv1-ext1 hv1/ext1 > + > +# Change the requested-chassis option for ls1-lp_ext1 from hv1 to hv2 > +ovn-nbctl --wait=hv lsp-set-options ls1-lp_ext1 requested-chassis=hv2 > + > +hv2_uuid=$(ovn-sbctl list chassis hv2 | grep uuid | awk '{print $3}') > + > +# The ls1-lp_ext1 should be bound to hv2 > +chassis=$(ovn-sbctl list port_binding ls1-lp_ext1 | grep -v gateway | \ > +grep -v requested | grep chassis | awk '{print $3}') > +AT_CHECK([test $chassis == "$hv2_uuid"], [0], []) > + > +# There should be OF flows for DHCP4/v6 for the ls1-lp_ext1 port in hv2 > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | grep reg14=0x$ln_public_key | \ > +wc -l], [0], [3 > +]) > +AT_CHECK([as hv2 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | \ > +grep reg14=0x$ln_public_key | wc -l], [0], [1 > +]) > + > +# There should ne no DHCPv4/v6 flows for ls1-lp_ext1 on hv1 > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep "0a.00.00.06" | wc -l], [0], [0 > +]) > +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int | grep table=20 | \ > +grep controller | grep tp_src=546 | grep \ > +"ae.70.00.00.00.00.00.00.00.00.00.00.00.00.00.06" | \ > +grep reg14=0x$ln_public_key | wc -l], [0], [0 > +]) > + > +# Send DHCPDISCOVER again for hv1/ext1. The DHCP response should come from > +# hv2 ovn-controller. Due to the test setup, the port hv1/ext1 is also > +# receiving the expected packet. > +offer_ip=`ip_to_hex 10 0 0 6` > +server_ip=`ip_to_hex 10 0 0 1` > +server_mac=ff1000000001 > +expected_dhcp_opts=330400000e100104ffffff0003040a00000136040a000001 > +test_dhcp 1 f00000000003 01 $offer_ip 0 $server_mac $server_ip \ > +$expected_dhcp_opts > + > +# NXT_RESUMEs should be 2 in hv1. > +OVS_WAIT_UNTIL([test 2 = `cat ofctl_monitor0_hv1.log | grep -c NXT_RESUME`]) > + > +# NXT_RESUMEs should be 1 in hv2. > +OVS_WAIT_UNTIL([test 1 = `cat ofctl_monitor0_hv2.log | grep -c NXT_RESUME`]) > + > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/ext1-tx.pcap > > ext1_v4.packets > +cat ext1_v4.expected | cut -c -48 > expout > +AT_CHECK([cat ext1_v4.packets | cut -c -48], [0], [expout]) > +# Skipping the IPv4 checksum. > +cat ext1_v4.expected | cut -c 53- > expout > +AT_CHECK([cat ext1_v4.packets | cut -c 53-], [0], [expout]) > + > +# ovs-ofctl also resumes the packets and this causes other ports to receive > +# the DHCP request packet. So reset the pcap files so that its easier to > test. > +reset_pcap_file hv1-ext1 hv1/ext1 > +rm -f ext1_v4.expected > + > +# Send DHCPv6 request again > +src_mac=f00000000003 > +src_lla=fe80000000000000f20000fffe000003 > +offer_ip=ae700000000000000000000000000006 > +test_dhcpv6 1 $src_mac $src_lla 01 $offer_ip 1 > + > +# NXT_RESUMEs should be 2 in hv1. > +OVS_WAIT_UNTIL([test 2 = `cat ofctl_monitor0_hv1.log | grep -c NXT_RESUME`]) > + > +# NXT_RESUMEs should be 2 in hv2. > +OVS_WAIT_UNTIL([test 2 = `cat ofctl_monitor0_hv2.log | grep -c NXT_RESUME`]) > + > +as hv1 > +ovs-vsctl show > +ovs-ofctl dump-flows br-int > + > +as hv2 > +ovs-vsctl show > +ovs-ofctl dump-flows br-int > + > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/ext1-tx.pcap | \ > +sort > ext1_v6.packets > +cat ext1_v6.expected | cut -c -120 > expout > +AT_CHECK([cat ext1_v6.packets | cut -c -120], [0], [expout]) > +# Skipping the UDP checksum > +cat ext1_v6.expected | cut -c 125- > expout > +AT_CHECK([cat ext1_v6.packets | cut -c 125-], [0], [expout]) > + > +rm -f ext1_v6.expected > +rm -f ext1_v6.packets > + > +as hv1 > +ovs-vsctl show > +reset_pcap_file hv1-ext1 hv1/ext1 > +reset_pcap_file br-phys_n1 hv1/br-phys_n1 > +reset_pcap_file br-phys hv1/br-phys > + > +as hv2 > +ovs-vsctl show > +reset_pcap_file hv2-ext2 hv2/ext2 > +reset_pcap_file br-phys_n1 hv2/br-phys_n1 > +reset_pcap_file br-phys hv2/br-phys > + > +# From ls1-lp_ext1, send ARP request for the router ip. The ARP > +# response should come from the router pipeline of hv2. > +ext1_mac=f00000000003 > +router_mac=a01000000001 > +ext1_ip=`ip_to_hex 10 0 0 6` > +router_ip=`ip_to_hex 10 0 0 1` > +arp_request=ffffffffffff${ext1_mac}08060001080006040001${ext1_mac}${ext1_ip}000000000000${router_ip} > + > +as hv1 ovs-appctl netdev-dummy/receive hv1-ext1 $arp_request > +expected_response=${src_mac}${router_mac}08060001080006040002${router_mac}${router_ip}${ext1_mac}${ext1_ip} > +echo $expected_response > expout > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/ext1-tx.pcap > ext1_arp_resp > +AT_CHECK([cat ext1_arp_resp], [0], [expout]) > + > +# Verify that the response came from hv2 > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv2/br-phys_n1-tx.pcap > > ext1_arp_resp > +AT_CHECK([cat ext1_arp_resp], [0], [expout]) > + > + > +# # Change the requested-chassis option for ls1-lp_ext1 from hv2 to hv1 > +ovn-nbctl --wait=hv lsp-set-options ls1-lp_ext1 requested-chassis=hv1 > + > +as hv1 > +ovs-vsctl show > +reset_pcap_file hv1-ext1 hv1/ext1 > +reset_pcap_file br-phys_n1 hv1/br-phys_n1 > +reset_pcap_file br-phys hv1/br-phys > + > +as hv2 > +ovs-vsctl show > +reset_pcap_file hv2-ext2 hv2/ext2 > +reset_pcap_file br-phys_n1 hv2/br-phys_n1 > +reset_pcap_file br-phys hv2/br-phys > + > +as hv1 ovs-appctl netdev-dummy/receive hv1-ext1 $arp_request > + > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv1/ext1-tx.pcap > ext1_arp_resp > +AT_CHECK([cat ext1_arp_resp], [0], [expout]) > + > +# Verify that the response didn't come from hv2 > +$PYTHON "$top_srcdir/utilities/ovs-pcap.in" hv2/br-phys_n1-tx.pcap > > ext1_arp_resp > +AT_CHECK([cat ext1_arp_resp], [0], []) > + > +OVN_CLEANUP([hv1],[hv2]) > +AT_CLEANUP > + > AT_SETUP([ovn -- ovn-controller restart]) > AT_SKIP_IF([test $HAVE_PYTHON = no]) > ovn_start > -- > 2.20.1 > > _______________________________________________ > dev mailing list > [email protected] > https://mail.openvswitch.org/mailman/listinfo/ovs-dev _______________________________________________ dev mailing list [email protected] https://mail.openvswitch.org/mailman/listinfo/ovs-dev
