[ovs-dev] [branch2.12] ovn: Add a new logical switch port type - 'virtual'

Numan Siddique nusiddiq at redhat.com
Fri Aug 2 13:46:56 UTC 2019


On Fri, Aug 2, 2019 at 6:20 AM Guru Shetty <guru at ovn.org> wrote:

>
>
> On Thu, 1 Aug 2019 at 10:52, <nusiddiq at redhat.com> wrote:
>
>> From: Numan Siddique <nusiddiq at redhat.com>
>>
>> This new type is added for the following reasons:
>>
>>   - When a load balancer is created in an OpenStack deployment with
>> Octavia
>>     service, it creates a logical port 'VIP' for the virtual ip.
>>
>>   - This logical port is not bound to any VIF.
>>
>>   - Octavia service creates a service VM (with another logical port 'P'
>> which
>>     belongs to the same logical switch)
>>
>>   - The virtual ip 'VIP' is configured on this service VM.
>>
>>   - This service VM provides the load balancing for the VIP with the
>> configured
>>     backend IPs.
>>
>>   - Octavia service can be configured to create few service VMs with
>> active-standby mode
>>     with the active VM configured with the VIP.  The VIP can move between
>>     these service nodes.
>>
>> Presently there are few problems:
>>
>>   - When a floating ip (externally reachable IP) is associated to the VIP
>> and if
>>     the compute nodes have external connectivity then the external
>> traffic cannot
>>     reach the VIP using the floating ip as the VIP logical port would be
>> down.
>>     dnat_and_snat entry in NAT table for this vip will have
>> 'external_mac' and
>>     'logical_port' configured.
>>
>>   - The only way to make it work is to clear the 'external_mac' entry so
>> that
>>     the gateway chassis does the DNAT for the VIP.
>>
>> To solve these problems, this patch proposes a new logical port type -
>> virtual.
>> CMS when creating the logical port for the VIP, should
>>
>>  - set the type as 'virtual'
>>
>>  - configure the VIP in the options -
>> Logical_Switch_Port.options:virtual-ip
>>
>>  - And set the virtual parents in the options
>>    Logical_Switch_Port.options:virtual-parents.
>>    These virtual parents are the one which can be configured with the VIP.
>>
>> If suppose the virtual_ip is configured to 10.0.0.10 on a virtual logical
>> port 'sw0-vip'
>> and the virtual_parents are set to - [sw0-p1, sw0-p2] then below logical
>> flows are added in the
>> lsp_in_arp_rsp logical switch pipeline
>>
>>  - table=11(ls_in_arp_rsp), priority=100,
>>    match=(inport == "sw0-p1" && !is_chassis_resident("sw0-vip") &&
>>           ((arp.op == 1 && arp.spa == 10.0.0.10 && arp.tpa == 10.0.0.10)
>> ||
>>            (arp.op == 2 && arp.spa == 10.0.0.10))),
>>    action=(bind_vport("sw0-vip", inport); next;)
>> - table=11(ls_in_arp_rsp), priority=100,
>>    match=(inport == "sw0-p2" && !is_chassis_resident("sw0-vip") &&
>>           ((arp.op == 1 && arp.spa == 10.0.0.10 && arp.tpa == 10.0.0.10)
>> ||
>>            (arp.op == 2 && arp.spa == 10.0.0.10))),
>>    action=(bind_vport("sw0-vip", inport); next;)
>>
>> The action bind_vport will claim the logical port - sw0-vip on the
>> chassis where this action
>> is executed. Since the port - sw0-vip is claimed by a chassis, the
>> dnat_and_snat rule for
>> the VIP will be handled by the compute node.
>>
>> Co-authored-by: Ben Pfaff <blp at ovn.org>
>> Signed-off-by: Ben Pfaff <blp at ovn.org>
>> Acked-by: Gurucharan Shetty <guru at ovn.org>
>> Acked-by: Mark Michelson <mmichels at redhat.com>
>> Signed-off-by: Numan Siddique <nusiddiq at redhat.com>
>>
>
> Ben is on vacation. So I took the liberty to commit it.
>

Thanks for the review and committing the patch.

Numan


>
>
>>
>> (cherry picked from ovn commit 054f4c85c413e20d893e10ba053ec52ac15db49c)
>> ---
>>  NEWS                        |   1 +
>>  include/ovn/actions.h       |  18 ++-
>>  ovn/controller/binding.c    |  30 +++-
>>  ovn/controller/pinctrl.c    | 174 ++++++++++++++++++++
>>  ovn/lib/actions.c           |  59 +++++++
>>  ovn/lib/ovn-util.c          |   1 +
>>  ovn/northd/ovn-northd.8.xml |  61 ++++++-
>>  ovn/northd/ovn-northd.c     | 306 +++++++++++++++++++++++++++---------
>>  ovn/ovn-nb.xml              |  45 ++++++
>>  ovn/ovn-sb.ovsschema        |   6 +-
>>  ovn/ovn-sb.xml              |  46 ++++++
>>  ovn/utilities/ovn-trace.c   |   3 +
>>  tests/ovn.at                | 290 ++++++++++++++++++++++++++++++++++
>>  tests/test-ovn.c            |   1 +
>>  14 files changed, 954 insertions(+), 87 deletions(-)
>>
>> diff --git a/NEWS b/NEWS
>> index 8cf850823..be3ea42b4 100644
>> --- a/NEWS
>> +++ b/NEWS
>> @@ -60,6 +60,7 @@ v2.12.0 - xx xxx xxxx
>>         logical groups which results in tunnels only been formed between
>>         members of the same transport zone(s).
>>       * Support for IGMP Snooping and IGMP Querier.
>> +     * Support for new logical switch port type - 'virtual'.
>>     - New QoS type "linux-netem" on Linux.
>>     - Added support for TLS Server Name Indication (SNI).
>>     - Linux datapath:
>> diff --git a/include/ovn/actions.h b/include/ovn/actions.h
>> index 63d3907d8..0ca06537c 100644
>> --- a/include/ovn/actions.h
>> +++ b/include/ovn/actions.h
>> @@ -85,7 +85,8 @@ struct ovn_extend_table;
>>      OVNACT(SET_METER,         ovnact_set_meter)       \
>>      OVNACT(OVNFIELD_LOAD,     ovnact_load)            \
>>      OVNACT(CHECK_PKT_LARGER,  ovnact_check_pkt_larger) \
>> -    OVNACT(TRIGGER_EVENT,     ovnact_controller_event)
>> +    OVNACT(TRIGGER_EVENT,     ovnact_controller_event) \
>> +    OVNACT(BIND_VPORT,        ovnact_bind_vport)
>>
>>  /* enum ovnact_type, with a member OVNACT_<ENUM> for each action. */
>>  enum OVS_PACKED_ENUM ovnact_type {
>> @@ -328,6 +329,13 @@ struct ovnact_controller_event {
>>      size_t n_options;
>>  };
>>
>> +/* OVNACT_BIND_VPORT. */
>> +struct ovnact_bind_vport {
>> +    struct ovnact ovnact;
>> +    char *vport;
>> +    struct expr_field vport_parent;     /* Logical virtual port's port
>> name. */
>> +};
>> +
>>  /* Internal use by the helpers below. */
>>  void ovnact_init(struct ovnact *, enum ovnact_type, size_t len);
>>  void *ovnact_put(struct ofpbuf *, enum ovnact_type, size_t len);
>> @@ -505,6 +513,14 @@ enum action_opcode {
>>       * Snoop IGMP, learn the multicast participants
>>       */
>>      ACTION_OPCODE_IGMP,
>> +
>> +    /* "bind_vport(vport, vport_parent)".
>> +     *
>> +     *   'vport' follows the action_header, in the format - 32-bit field.
>> +     *   'vport_parent' is passed through the packet metadata as
>> +     *    MFF_LOG_INPORT.
>> +     */
>> +    ACTION_OPCODE_BIND_VPORT,
>>  };
>>
>>  /* Header. */
>> diff --git a/ovn/controller/binding.c b/ovn/controller/binding.c
>> index ace0f811b..dfe002b60 100644
>> --- a/ovn/controller/binding.c
>> +++ b/ovn/controller/binding.c
>> @@ -571,11 +571,31 @@ consider_local_datapath(struct ovsdb_idl_txn
>> *ovnsb_idl_txn,
>>                  sbrec_port_binding_set_encap(binding_rec, encap_rec);
>>              }
>>          } else if (binding_rec->chassis == chassis_rec) {
>> -            VLOG_INFO("Releasing lport %s from this chassis.",
>> -                      binding_rec->logical_port);
>> -            if (binding_rec->encap)
>> -                sbrec_port_binding_set_encap(binding_rec, NULL);
>> -            sbrec_port_binding_set_chassis(binding_rec, NULL);
>> +            if (!strcmp(binding_rec->type, "virtual")) {
>> +                /* pinctrl module takes care of binding the ports
>> +                 * of type 'virtual'.
>> +                 * Release such ports if their virtual parents are no
>> +                 * longer claimed by this chassis. */
>> +                const struct sbrec_port_binding *parent
>> +                    = lport_lookup_by_name(sbrec_port_binding_by_name,
>> +                                        binding_rec->virtual_parent);
>> +                if (!parent || parent->chassis != chassis_rec) {
>> +                    VLOG_INFO("Releasing lport %s from this chassis.",
>> +                            binding_rec->logical_port);
>> +                    if (binding_rec->encap) {
>> +                        sbrec_port_binding_set_encap(binding_rec, NULL);
>> +                    }
>> +                    sbrec_port_binding_set_chassis(binding_rec, NULL);
>> +                    sbrec_port_binding_set_virtual_parent(binding_rec,
>> NULL);
>> +                }
>> +            } else {
>> +                VLOG_INFO("Releasing lport %s from this chassis.",
>> +                          binding_rec->logical_port);
>> +                if (binding_rec->encap) {
>> +                    sbrec_port_binding_set_encap(binding_rec, NULL);
>> +                }
>> +                sbrec_port_binding_set_chassis(binding_rec, NULL);
>> +            }
>>          } else if (our_chassis) {
>>              static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5,
>> 1);
>>              VLOG_INFO_RL(&rl,
>> diff --git a/ovn/controller/pinctrl.c b/ovn/controller/pinctrl.c
>> index d857067a5..357050eb5 100644
>> --- a/ovn/controller/pinctrl.c
>> +++ b/ovn/controller/pinctrl.c
>> @@ -273,9 +273,22 @@ static void pinctrl_ip_mcast_handle_igmp(
>>
>>  static bool may_inject_pkts(void);
>>
>> +static void init_put_vport_bindings(void);
>> +static void destroy_put_vport_bindings(void);
>> +static void run_put_vport_bindings(
>> +    struct ovsdb_idl_txn *ovnsb_idl_txn,
>> +    struct ovsdb_idl_index *sbrec_datapath_binding_by_key,
>> +    struct ovsdb_idl_index *sbrec_port_binding_by_key,
>> +    const struct sbrec_chassis *chassis)
>> +    OVS_REQUIRES(pinctrl_mutex);
>> +static void wait_put_vport_bindings(struct ovsdb_idl_txn *ovnsb_idl_txn);
>> +static void pinctrl_handle_bind_vport(const struct flow *md,
>> +                                      struct ofpbuf *userdata);
>> +
>>  COVERAGE_DEFINE(pinctrl_drop_put_mac_binding);
>>  COVERAGE_DEFINE(pinctrl_drop_buffered_packets_map);
>>  COVERAGE_DEFINE(pinctrl_drop_controller_event);
>> +COVERAGE_DEFINE(pinctrl_drop_put_vport_binding);
>>
>>  struct empty_lb_backends_event {
>>      struct hmap_node hmap_node;
>> @@ -432,6 +445,7 @@ pinctrl_init(void)
>>      init_buffered_packets_map();
>>      init_event_table();
>>      ip_mcast_snoop_init();
>> +    init_put_vport_bindings();
>>      pinctrl.br_int_name = NULL;
>>      pinctrl_handler_seq = seq_create();
>>      pinctrl_main_seq = seq_create();
>> @@ -1957,6 +1971,12 @@ process_packet_in(struct rconn *swconn, const
>> struct ofp_header *msg)
>>          ovs_mutex_unlock(&pinctrl_mutex);
>>          break;
>>
>> +    case ACTION_OPCODE_BIND_VPORT:
>> +        ovs_mutex_lock(&pinctrl_mutex);
>> +        pinctrl_handle_bind_vport(&pin.flow_metadata.flow, &userdata);
>> +        ovs_mutex_unlock(&pinctrl_mutex);
>> +        break;
>> +
>>      default:
>>          VLOG_WARN_RL(&rl, "unrecognized packet-in opcode %"PRIu32,
>>                       ntohl(ah->opcode));
>> @@ -2135,6 +2155,8 @@ pinctrl_run(struct ovsdb_idl_txn *ovnsb_idl_txn,
>>      run_put_mac_bindings(ovnsb_idl_txn, sbrec_datapath_binding_by_key,
>>                           sbrec_port_binding_by_key,
>>                           sbrec_mac_binding_by_lport_ip);
>> +    run_put_vport_bindings(ovnsb_idl_txn, sbrec_datapath_binding_by_key,
>> +                           sbrec_port_binding_by_key, chassis);
>>      send_garp_prepare(sbrec_port_binding_by_datapath,
>>                        sbrec_port_binding_by_name, br_int, chassis,
>>                        local_datapaths, active_tunnels);
>> @@ -2481,6 +2503,7 @@ pinctrl_wait(struct ovsdb_idl_txn *ovnsb_idl_txn)
>>  {
>>      wait_put_mac_bindings(ovnsb_idl_txn);
>>      wait_controller_event(ovnsb_idl_txn);
>> +    wait_put_vport_bindings(ovnsb_idl_txn);
>>      int64_t new_seq = seq_read(pinctrl_main_seq);
>>      seq_wait(pinctrl_main_seq, new_seq);
>>  }
>> @@ -2498,6 +2521,7 @@ pinctrl_destroy(void)
>>      destroy_buffered_packets_map();
>>      event_table_destroy();
>>      destroy_put_mac_bindings();
>> +    destroy_put_vport_bindings();
>>      destroy_dns_cache();
>>      ip_mcast_snoop_destroy();
>>      seq_destroy(pinctrl_main_seq);
>> @@ -4341,3 +4365,153 @@ pinctrl_handle_event(struct ofpbuf *userdata)
>>          return;
>>      }
>>  }
>> +
>> +struct put_vport_binding {
>> +    struct hmap_node hmap_node;
>> +
>> +    /* Key and value. */
>> +    uint32_t dp_key;
>> +    uint32_t vport_key;
>> +
>> +    uint32_t vport_parent_key;
>> +};
>> +
>> +/* Contains "struct put_vport_binding"s. */
>> +static struct hmap put_vport_bindings;
>> +
>> +static void
>> +init_put_vport_bindings(void)
>> +{
>> +    hmap_init(&put_vport_bindings);
>> +}
>> +
>> +static void
>> +flush_put_vport_bindings(void)
>> +{
>> +    struct put_vport_binding *vport_b;
>> +    HMAP_FOR_EACH_POP (vport_b, hmap_node, &put_vport_bindings) {
>> +        free(vport_b);
>> +    }
>> +}
>> +
>> +static void
>> +destroy_put_vport_bindings(void)
>> +{
>> +    flush_put_vport_bindings();
>> +    hmap_destroy(&put_vport_bindings);
>> +}
>> +
>> +static void
>> +wait_put_vport_bindings(struct ovsdb_idl_txn *ovnsb_idl_txn)
>> +{
>> +    if (ovnsb_idl_txn && !hmap_is_empty(&put_vport_bindings)) {
>> +        poll_immediate_wake();
>> +    }
>> +}
>> +
>> +static struct put_vport_binding *
>> +pinctrl_find_put_vport_binding(uint32_t dp_key, uint32_t vport_key,
>> +                               uint32_t hash)
>> +{
>> +    struct put_vport_binding *vpb;
>> +    HMAP_FOR_EACH_WITH_HASH (vpb, hmap_node, hash, &put_vport_bindings) {
>> +        if (vpb->dp_key == dp_key && vpb->vport_key == vport_key) {
>> +            return vpb;
>> +        }
>> +    }
>> +    return NULL;
>> +}
>> +
>> +static void
>> +run_put_vport_binding(struct ovsdb_idl_txn *ovnsb_idl_txn OVS_UNUSED,
>> +                      struct ovsdb_idl_index
>> *sbrec_datapath_binding_by_key,
>> +                      struct ovsdb_idl_index *sbrec_port_binding_by_key,
>> +                      const struct sbrec_chassis *chassis,
>> +                      const struct put_vport_binding *vpb)
>> +{
>> +    /* Convert logical datapath and logical port key into lport. */
>> +    const struct sbrec_port_binding *pb = lport_lookup_by_key(
>> +        sbrec_datapath_binding_by_key, sbrec_port_binding_by_key,
>> +        vpb->dp_key, vpb->vport_key);
>> +    if (!pb) {
>> +        static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5);
>> +
>> +        VLOG_WARN_RL(&rl, "unknown logical port with datapath %"PRIu32" "
>> +                     "and port %"PRIu32, vpb->dp_key, vpb->vport_key);
>> +        return;
>> +    }
>> +
>> +    /* pinctrl module updates the port binding only for type 'virtual'.
>> */
>> +    if (!strcmp(pb->type, "virtual")) {
>> +        const struct sbrec_port_binding *parent = lport_lookup_by_key(
>> +        sbrec_datapath_binding_by_key, sbrec_port_binding_by_key,
>> +        vpb->dp_key, vpb->vport_parent_key);
>> +        if (parent) {
>> +            VLOG_INFO("Claiming virtual lport %s for this chassis "
>> +                       "with the virtual parent %s",
>> +                       pb->logical_port, parent->logical_port);
>> +            sbrec_port_binding_set_chassis(pb, chassis);
>> +            sbrec_port_binding_set_virtual_parent(pb,
>> parent->logical_port);
>> +        }
>> +    }
>> +}
>> +
>> +/* Called by pinctrl_run(). Runs with in the main ovn-controller
>> + * thread context. */
>> +static void
>> +run_put_vport_bindings(struct ovsdb_idl_txn *ovnsb_idl_txn,
>> +                      struct ovsdb_idl_index
>> *sbrec_datapath_binding_by_key,
>> +                      struct ovsdb_idl_index *sbrec_port_binding_by_key,
>> +                      const struct sbrec_chassis *chassis)
>> +    OVS_REQUIRES(pinctrl_mutex)
>> +{
>> +    if (!ovnsb_idl_txn) {
>> +        return;
>> +    }
>> +
>> +    const struct put_vport_binding *vpb;
>> +    HMAP_FOR_EACH (vpb, hmap_node, &put_vport_bindings) {
>> +        run_put_vport_binding(ovnsb_idl_txn,
>> sbrec_datapath_binding_by_key,
>> +                              sbrec_port_binding_by_key, chassis, vpb);
>> +    }
>> +
>> +    flush_put_vport_bindings();
>> +}
>> +
>> +/* Called with in the pinctrl_handler thread context. */
>> +static void
>> +pinctrl_handle_bind_vport(
>> +    const struct flow *md, struct ofpbuf *userdata)
>> +    OVS_REQUIRES(pinctrl_mutex)
>> +{
>> +    /* Get the datapath key from the packet metadata. */
>> +    uint32_t dp_key = ntohll(md->metadata);
>> +    uint32_t vport_parent_key = md->regs[MFF_LOG_INPORT - MFF_REG0];
>> +
>> +    /* Get the virtual port key from the userdata buffer. */
>> +    uint32_t *vport_key = ofpbuf_try_pull(userdata, sizeof *vport_key);
>> +
>> +    if (!vport_key) {
>> +        return;
>> +    }
>> +
>> +    uint32_t hash = hash_2words(dp_key, *vport_key);
>> +
>> +    struct put_vport_binding *vpb
>> +        = pinctrl_find_put_vport_binding(dp_key, *vport_key, hash);
>> +    if (!vpb) {
>> +        if (hmap_count(&put_vport_bindings) >= 1000) {
>> +            COVERAGE_INC(pinctrl_drop_put_vport_binding);
>> +            return;
>> +        }
>> +
>> +        vpb = xmalloc(sizeof *vpb);
>> +        hmap_insert(&put_vport_bindings, &vpb->hmap_node, hash);
>> +    }
>> +
>> +    vpb->dp_key = dp_key;
>> +    vpb->vport_key = *vport_key;
>> +    vpb->vport_parent_key = vport_parent_key;
>> +
>> +    notify_pinctrl_main();
>> +}
>> diff --git a/ovn/lib/actions.c b/ovn/lib/actions.c
>> index 4eacc44ed..66916a837 100644
>> --- a/ovn/lib/actions.c
>> +++ b/ovn/lib/actions.c
>> @@ -2599,6 +2599,63 @@ ovnact_check_pkt_larger_free(struct
>> ovnact_check_pkt_larger *cipl OVS_UNUSED)
>>  {
>>  }
>>
>> +static void
>> +parse_bind_vport(struct action_context *ctx)
>> +{
>> +    if (!lexer_force_match(ctx->lexer, LEX_T_LPAREN)) {
>> +        return;
>> +    }
>> +
>> +    if (ctx->lexer->token.type != LEX_T_STRING) {
>> +        lexer_syntax_error(ctx->lexer, "expecting port name string");
>> +        return;
>> +    }
>> +
>> +    struct ovnact_bind_vport *bind_vp =
>> ovnact_put_BIND_VPORT(ctx->ovnacts);
>> +    bind_vp->vport = xstrdup(ctx->lexer->token.s);
>> +    lexer_get(ctx->lexer);
>> +    (void) (lexer_force_match(ctx->lexer, LEX_T_COMMA)
>> +            && action_parse_field(ctx, 0, false, &bind_vp->vport_parent)
>> +            && lexer_force_match(ctx->lexer, LEX_T_RPAREN));
>> +}
>> +
>> +static void
>> +format_BIND_VPORT(const struct ovnact_bind_vport *bind_vp,
>> +                  struct ds *s )
>> +{
>> +    ds_put_format(s, "bind_vport(\"%s\", ", bind_vp->vport);
>> +    expr_field_format(&bind_vp->vport_parent, s);
>> +    ds_put_cstr(s, ");");
>> +}
>> +
>> +static void
>> +encode_BIND_VPORT(const struct ovnact_bind_vport *vp,
>> +                 const struct ovnact_encode_params *ep,
>> +                 struct ofpbuf *ofpacts)
>> +{
>> +    uint32_t vport_key;
>> +    if (!ep->lookup_port(ep->aux, vp->vport, &vport_key)) {
>> +        return;
>> +    }
>> +
>> +    const struct arg args[] = {
>> +        { expr_resolve_field(&vp->vport_parent), MFF_LOG_INPORT },
>> +    };
>> +    encode_setup_args(args, ARRAY_SIZE(args), ofpacts);
>> +    size_t oc_offset =
>> encode_start_controller_op(ACTION_OPCODE_BIND_VPORT,
>> +                                                  false,
>> NX_CTLR_NO_METER,
>> +                                                  ofpacts);
>> +    ofpbuf_put(ofpacts, &vport_key, sizeof(uint32_t));
>> +    encode_finish_controller_op(oc_offset, ofpacts);
>> +    encode_restore_args(args, ARRAY_SIZE(args), ofpacts);
>> +}
>> +
>> +static void
>> +ovnact_bind_vport_free(struct ovnact_bind_vport *bp)
>> +{
>> +    free(bp->vport);
>> +}
>> +
>>  /* Parses an assignment or exchange or put_dhcp_opts action. */
>>  static void
>>  parse_set_action(struct action_context *ctx)
>> @@ -2706,6 +2763,8 @@ parse_action(struct action_context *ctx)
>>          parse_set_meter_action(ctx);
>>      } else if (lexer_match_id(ctx->lexer, "trigger_event")) {
>>          parse_trigger_event(ctx, ovnact_put_TRIGGER_EVENT(ctx->ovnacts));
>> +    } else if (lexer_match_id(ctx->lexer, "bind_vport")) {
>> +        parse_bind_vport(ctx);
>>      } else {
>>          lexer_syntax_error(ctx->lexer, "expecting action");
>>      }
>> diff --git a/ovn/lib/ovn-util.c b/ovn/lib/ovn-util.c
>> index 0f07d80ac..de745d73f 100644
>> --- a/ovn/lib/ovn-util.c
>> +++ b/ovn/lib/ovn-util.c
>> @@ -326,6 +326,7 @@ static const char *OVN_NB_LSP_TYPES[] = {
>>      "router",
>>      "vtep",
>>      "external",
>> +    "virtual",
>>  };
>>
>>  bool
>> diff --git a/ovn/northd/ovn-northd.8.xml b/ovn/northd/ovn-northd.8.xml
>> index d2267de0e..6ff7aaff1 100644
>> --- a/ovn/northd/ovn-northd.8.xml
>> +++ b/ovn/northd/ovn-northd.8.xml
>> @@ -519,6 +519,34 @@
>>          some additional flow cost for this and the value appears limited.
>>        </li>
>>
>> +      <li>
>> +        <p>
>> +          If inport <code>V</code> is of type <code>virtual</code> adds a
>> +          priority-100 logical flow for each <var>P</var> configured in
>> the
>> +          <ref table="Logical_Switch_Port"
>> column="options:virtual-parents"/>
>> +          column with the match
>> +        </p>
>> +        <pre>
>> +<code>inport == <var>P</var> &amp;&amp;
>> !is_chassis_resident(<var>V</var>) &amp;&amp; ((arp.op == 1 &amp;&amp;
>> arp.spa == <var>VIP</var> &amp;&amp; arp.tpa == <var>VIP</var>) || (arp.op
>> == 2 &amp;&amp; arp.spa == <var>VIP</var>))</code>
>> +        </pre>
>> +
>> +        <p>
>> +          and applies the action
>> +        </p>
>> +        <pre>
>> +<code>bind_vport(<var>V</var>, inport);</code>
>> +        </pre>
>> +
>> +        <p>
>> +         and advances the packet to the next table.
>> +        </p>
>> +
>> +        <p>
>> +          Where <var>VIP</var> is the virtual ip configured in the column
>> +          <ref table="Logical_Switch_Port" column="options:virtual-ip"/>.
>> +        </p>
>> +      </li>
>> +
>>        <li>
>>          <p>
>>            Priority-50 flows that match ARP requests to each known IP
>> address
>> @@ -541,7 +569,8 @@ output;
>>
>>          <p>
>>            These flows are omitted for logical ports (other than router
>> ports or
>> -          <code>localport</code> ports) that are down.
>> +          <code>localport</code> ports) that are down and for logical
>> ports of
>> +          type <code>virtual</code>.
>>          </p>
>>        </li>
>>
>> @@ -588,7 +617,8 @@ nd_na_router {
>>
>>          <p>
>>            These flows are omitted for logical ports (other than router
>> ports or
>> -          <code>localport</code> ports) that are down.
>> +          <code>localport</code> ports) that are down and for logical
>> ports of
>> +          type <code>virtual</code>.
>>          </p>
>>        </li>
>>
>> @@ -2031,6 +2061,33 @@ next;
>>            <code>eth.dst = <var>E</var>; next;</code>.
>>          </p>
>>
>> +        <p>
>> +          For each virtual ip <var>A</var> configured on a logical port
>> +          of type <code>virtual</code> and its virtual parent set in
>> +          its corresponding <ref db="OVN_Southbound"
>> table="Port_Binding"/>
>> +          record and the virtual parent with the Ethernet address
>> <var>E</var>
>> +          and the virtual ip is reachable via the router port
>> <var>P</var>, a
>> +          priority-100 flow with match <code>outport === <var>P</var>
>> +          &amp;&amp; reg0 == <var>A</var></code> has actions
>> +          <code>eth.dst = <var>E</var>; next;</code>.
>> +        </p>
>> +
>> +        <p>
>> +          For each virtual ip <var>A</var> configured on a logical port
>> +          of type <code>virtual</code> and its virtual parent
>> <code>not</code>
>> +          set in its corresponding
>> +          <ref db="OVN_Southbound" table="Port_Binding"/>
>> +          record and the virtual ip <var>A</var> is reachable via the
>> +          router port <var>P</var>, a
>> +          priority-100 flow with match <code>outport === <var>P</var>
>> +          &amp;&amp; reg0 == <var>A</var></code> has actions
>> +          <code>eth.dst = <var>00:00:00:00:00:00</var>; next;</code>.
>> +          This flow is added so that the ARP is always resolved for the
>> +          virtual ip <var>A</var> by generating ARP request and
>> +          <code>not</code> consulting the MAC_Binding table as it can
>> have
>> +          incorrect value for the virtual ip <var>A</var>.
>> +        </p>
>> +
>>          <p>
>>            For each IPv6 address <var>A</var> whose host is known to have
>>            Ethernet address <var>E</var> on router port <var>P</var>, a
>> diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c
>> index eb6c47cad..ae09cf338 100644
>> --- a/ovn/northd/ovn-northd.c
>> +++ b/ovn/northd/ovn-northd.c
>> @@ -4878,96 +4878,146 @@ build_lswitch_flows(struct hmap *datapaths,
>> struct hmap *ports,
>>              continue;
>>          }
>>
>> -        /*
>> -         * Add ARP/ND reply flows if either the
>> -         *  - port is up or
>> -         *  - port type is router or
>> -         *  - port type is localport
>> -         */
>> -        if (!lsp_is_up(op->nbsp) && strcmp(op->nbsp->type, "router") &&
>> -            strcmp(op->nbsp->type, "localport")) {
>> -            continue;
>> -        }
>> +        if (!strcmp(op->nbsp->type, "virtual")) {
>> +            /* Handle
>> +             *  - GARPs for virtual ip which belongs to a logical port
>> +             *    of type 'virtual' and bind that port.
>> +             *
>> +             *  - ARP reply from the virtual ip which belongs to a
>> logical
>> +             *    port of type 'virtual' and bind that port.
>> +             * */
>> +            ovs_be32 ip;
>> +            const char *virtual_ip = smap_get(&op->nbsp->options,
>> +                                              "virtual-ip");
>> +            const char *virtual_parents = smap_get(&op->nbsp->options,
>> +                                                   "virtual-parents");
>> +            if (!virtual_ip || !virtual_parents ||
>> +                !ip_parse(virtual_ip, &ip)) {
>> +                continue;
>> +            }
>>
>> -        if (lsp_is_external(op->nbsp)) {
>> -            continue;
>> -        }
>> +            char *tokstr = xstrdup(virtual_parents);
>> +            char *save_ptr = NULL;
>> +            char *vparent;
>> +            for (vparent = strtok_r(tokstr, ",", &save_ptr); vparent !=
>> NULL;
>> +                 vparent = strtok_r(NULL, ",", &save_ptr)) {
>> +                struct ovn_port *vp = ovn_port_find(ports, vparent);
>> +                if (!vp || vp->od != op->od) {
>> +                    /* vparent name should be valid and it should belong
>> +                     * to the same logical switch. */
>> +                    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++) {
>>                  ds_clear(&match);
>> -                ds_put_format(&match, "arp.tpa == %s && arp.op == 1",
>> -                              op->lsp_addrs[i].ipv4_addrs[j].addr_s);
>> +                ds_put_format(&match, "inport == \"%s\" && "
>> +                              "!is_chassis_resident(%s) && "
>> +                              "((arp.op == 1 && arp.spa == %s && "
>> +                              "arp.tpa == %s) || (arp.op == 2 && "
>> +                              "arp.spa == %s))",
>> +                              vparent, op->json_key, virtual_ip,
>> virtual_ip,
>> +                              virtual_ip);
>>                  ds_clear(&actions);
>>                  ds_put_format(&actions,
>> -                    "eth.dst = eth.src; "
>> -                    "eth.src = %s; "
>> -                    "arp.op = 2; /* ARP reply */ "
>> -                    "arp.tha = arp.sha; "
>> -                    "arp.sha = %s; "
>> -                    "arp.tpa = arp.spa; "
>> -                    "arp.spa = %s; "
>> -                    "outport = inport; "
>> -                    "flags.loopback = 1; "
>> -                    "output;",
>> -                    op->lsp_addrs[i].ea_s, op->lsp_addrs[i].ea_s,
>> -                    op->lsp_addrs[i].ipv4_addrs[j].addr_s);
>> -                ovn_lflow_add(lflows, op->od, S_SWITCH_IN_ARP_ND_RSP, 50,
>> +                    "bind_vport(%s, inport); "
>> +                    "next;",
>> +                    op->json_key);
>> +                ovn_lflow_add(lflows, op->od, S_SWITCH_IN_ARP_ND_RSP,
>> 100,
>>                                ds_cstr(&match), ds_cstr(&actions));
>> +            }
>>
>> -                /* Do not reply to an ARP request from the port that
>> owns the
>> -                 * address (otherwise a DHCP client that ARPs to check
>> for a
>> -                 * duplicate address will fail).  Instead, forward it
>> the usual
>> -                 * way.
>> -                 *
>> -                 * (Another alternative would be to simply drop the
>> packet.  If
>> -                 * everything is working as it is configured, then this
>> would
>> -                 * produce equivalent results, since no one should reply
>> to the
>> -                 * request.  But ARPing for one's own IP address is
>> intended to
>> -                 * detect situations where the network is not working as
>> -                 * configured, so dropping the request would frustrate
>> that
>> -                 * intent.) */
>> -                ds_put_format(&match, " && inport == %s", op->json_key);
>> -                ovn_lflow_add(lflows, op->od, S_SWITCH_IN_ARP_ND_RSP,
>> 100,
>> -                              ds_cstr(&match), "next;");
>> +            free(tokstr);
>> +        } else {
>> +            /*
>> +             * Add ARP/ND reply flows if either the
>> +             *  - port is up or
>> +             *  - port type is router or
>> +             *  - port type is localport
>> +             */
>> +            if (!lsp_is_up(op->nbsp) && strcmp(op->nbsp->type, "router")
>> &&
>> +                strcmp(op->nbsp->type, "localport")) {
>> +                continue;
>>              }
>>
>> -            /* For ND solicitations, we need to listen for both the
>> -             * unicast IPv6 address and its all-nodes multicast address,
>> -             * but always respond with the unicast IPv6 address. */
>> -            for (size_t j = 0; j < op->lsp_addrs[i].n_ipv6_addrs; j++) {
>> -                ds_clear(&match);
>> -                ds_put_format(&match,
>> -                        "nd_ns && ip6.dst == {%s, %s} && nd.target ==
>> %s",
>> -                        op->lsp_addrs[i].ipv6_addrs[j].addr_s,
>> -                        op->lsp_addrs[i].ipv6_addrs[j].sn_addr_s,
>> -                        op->lsp_addrs[i].ipv6_addrs[j].addr_s);
>> +            if (lsp_is_external(op->nbsp)) {
>> +                continue;
>> +            }
>>
>> -                ds_clear(&actions);
>> -                ds_put_format(&actions,
>> -                        "%s { "
>> +            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++) {
>> +                    ds_clear(&match);
>> +                    ds_put_format(&match, "arp.tpa == %s && arp.op == 1",
>> +                                op->lsp_addrs[i].ipv4_addrs[j].addr_s);
>> +                    ds_clear(&actions);
>> +                    ds_put_format(&actions,
>> +                        "eth.dst = eth.src; "
>>                          "eth.src = %s; "
>> -                        "ip6.src = %s; "
>> -                        "nd.target = %s; "
>> -                        "nd.tll = %s; "
>> +                        "arp.op = 2; /* ARP reply */ "
>> +                        "arp.tha = arp.sha; "
>> +                        "arp.sha = %s; "
>> +                        "arp.tpa = arp.spa; "
>> +                        "arp.spa = %s; "
>>                          "outport = inport; "
>>                          "flags.loopback = 1; "
>> -                        "output; "
>> -                        "};",
>> -                        !strcmp(op->nbsp->type, "router") ?
>> -                            "nd_na_router" : "nd_na",
>> -                        op->lsp_addrs[i].ea_s,
>> -                        op->lsp_addrs[i].ipv6_addrs[j].addr_s,
>> -                        op->lsp_addrs[i].ipv6_addrs[j].addr_s,
>> -                        op->lsp_addrs[i].ea_s);
>> -                ovn_lflow_add(lflows, op->od, S_SWITCH_IN_ARP_ND_RSP, 50,
>> -                              ds_cstr(&match), ds_cstr(&actions));
>> +                        "output;",
>> +                        op->lsp_addrs[i].ea_s, op->lsp_addrs[i].ea_s,
>> +                        op->lsp_addrs[i].ipv4_addrs[j].addr_s);
>> +                    ovn_lflow_add(lflows, op->od,
>> S_SWITCH_IN_ARP_ND_RSP, 50,
>> +                                ds_cstr(&match), ds_cstr(&actions));
>> +
>> +                    /* Do not reply to an ARP request from the port that
>> owns
>> +                     * the address (otherwise a DHCP client that ARPs to
>> check
>> +                     * for a duplicate address will fail).  Instead,
>> forward
>> +                     * it the usual way.
>> +                     *
>> +                     * (Another alternative would be to simply drop the
>> packet.
>> +                     * If everything is working as it is configured,
>> then this
>> +                     * would produce equivalent results, since no one
>> should
>> +                     * reply to the request.  But ARPing for one's own IP
>> +                     * address is intended to detect situations where the
>> +                     * network is not working as configured, so dropping
>> the
>> +                     * request would frustrate that intent.) */
>> +                    ds_put_format(&match, " && inport == %s",
>> op->json_key);
>> +                    ovn_lflow_add(lflows, op->od,
>> S_SWITCH_IN_ARP_ND_RSP, 100,
>> +                                ds_cstr(&match), "next;");
>> +                }
>>
>> -                /* Do not reply to a solicitation from the port that
>> owns the
>> -                 * address (otherwise DAD detection will fail). */
>> -                ds_put_format(&match, " && inport == %s", op->json_key);
>> -                ovn_lflow_add(lflows, op->od, S_SWITCH_IN_ARP_ND_RSP,
>> 100,
>> -                              ds_cstr(&match), "next;");
>> +                /* For ND solicitations, we need to listen for both the
>> +                 * unicast IPv6 address and its all-nodes multicast
>> address,
>> +                 * but always respond with the unicast IPv6 address. */
>> +                for (size_t j = 0; j < op->lsp_addrs[i].n_ipv6_addrs;
>> j++) {
>> +                    ds_clear(&match);
>> +                    ds_put_format(&match,
>> +                            "nd_ns && ip6.dst == {%s, %s} && nd.target
>> == %s",
>> +                            op->lsp_addrs[i].ipv6_addrs[j].addr_s,
>> +                            op->lsp_addrs[i].ipv6_addrs[j].sn_addr_s,
>> +                            op->lsp_addrs[i].ipv6_addrs[j].addr_s);
>> +
>> +                    ds_clear(&actions);
>> +                    ds_put_format(&actions,
>> +                            "%s { "
>> +                            "eth.src = %s; "
>> +                            "ip6.src = %s; "
>> +                            "nd.target = %s; "
>> +                            "nd.tll = %s; "
>> +                            "outport = inport; "
>> +                            "flags.loopback = 1; "
>> +                            "output; "
>> +                            "};",
>> +                            !strcmp(op->nbsp->type, "router") ?
>> +                                "nd_na_router" : "nd_na",
>> +                            op->lsp_addrs[i].ea_s,
>> +                            op->lsp_addrs[i].ipv6_addrs[j].addr_s,
>> +                            op->lsp_addrs[i].ipv6_addrs[j].addr_s,
>> +                            op->lsp_addrs[i].ea_s);
>> +                    ovn_lflow_add(lflows, op->od,
>> S_SWITCH_IN_ARP_ND_RSP, 50,
>> +                                ds_cstr(&match), ds_cstr(&actions));
>> +
>> +                    /* Do not reply to a solicitation from the port that
>> owns
>> +                     * the address (otherwise DAD detection will fail).
>> */
>> +                    ds_put_format(&match, " && inport == %s",
>> op->json_key);
>> +                    ovn_lflow_add(lflows, op->od,
>> S_SWITCH_IN_ARP_ND_RSP, 100,
>> +                                ds_cstr(&match), "next;");
>> +                }
>>              }
>>          }
>>      }
>> @@ -7504,7 +7554,8 @@ build_lrouter_flows(struct hmap *datapaths, struct
>> hmap *ports,
>>                                    100, ds_cstr(&match),
>> ds_cstr(&actions));
>>                  }
>>              }
>> -        } else if (op->od->n_router_ports && strcmp(op->nbsp->type,
>> "router")) {
>> +        } else if (op->od->n_router_ports && strcmp(op->nbsp->type,
>> "router")
>> +                   && strcmp(op->nbsp->type, "virtual")) {
>>              /* This is a logical switch port that backs a VM or a
>> container.
>>               * Extract its addresses. For each of the address, go
>> through all
>>               * the router ports attached to the switch (to which this
>> port
>> @@ -7581,6 +7632,105 @@ build_lrouter_flows(struct hmap *datapaths,
>> struct hmap *ports,
>>                      }
>>                  }
>>              }
>> +        } else if (op->od->n_router_ports && strcmp(op->nbsp->type,
>> "router")
>> +                   && !strcmp(op->nbsp->type, "virtual")) {
>> +            /* This is a virtual port. Add ARP replies for the virtual
>> ip with
>> +             * the mac of the present active virtual parent.
>> +             * If the logical port doesn't have virtual parent set in
>> +             * Port_Binding table, then add the flow to set eth.dst to
>> +             * 00:00:00:00:00:00 and advance to next table so that ARP is
>> +             * resolved by router pipeline using the arp{} action.
>> +             * The MAC_Binding entry for the virtual ip might be
>> invalid. */
>> +            ovs_be32 ip;
>> +
>> +            const char *vip = smap_get(&op->nbsp->options,
>> +                                       "virtual-ip");
>> +            const char *virtual_parents = smap_get(&op->nbsp->options,
>> +                                                   "virtual-parents");
>> +            if (!vip || !virtual_parents ||
>> +                !ip_parse(vip, &ip) || !op->sb) {
>> +                continue;
>> +            }
>> +
>> +            if (!op->sb->virtual_parent || !op->sb->virtual_parent[0] ||
>> +                !op->sb->chassis) {
>> +                /* The virtual port is not claimed yet. */
>> +                for (size_t i = 0; i < op->od->n_router_ports; i++) {
>> +                    const char *peer_name = smap_get(
>> +                        &op->od->router_ports[i]->nbsp->options,
>> +                        "router-port");
>> +                    if (!peer_name) {
>> +                        continue;
>> +                    }
>> +
>> +                    struct ovn_port *peer = ovn_port_find(ports,
>> peer_name);
>> +                    if (!peer || !peer->nbrp) {
>> +                        continue;
>> +                    }
>> +
>> +                    if (find_lrp_member_ip(peer, vip)) {
>> +                        ds_clear(&match);
>> +                        ds_put_format(&match, "outport == %s && reg0 ==
>> %s",
>> +                                        peer->json_key, vip);
>> +
>> +                        ds_clear(&actions);
>> +                        ds_put_format(&actions,
>> +                                      "eth.dst = 00:00:00:00:00:00;
>> next;");
>> +                        ovn_lflow_add(lflows, peer->od,
>> +                                        S_ROUTER_IN_ARP_RESOLVE, 100,
>> +                                        ds_cstr(&match),
>> ds_cstr(&actions));
>> +                        break;
>> +                    }
>> +                }
>> +            } else {
>> +                struct ovn_port *vp =
>> +                    ovn_port_find(ports, op->sb->virtual_parent);
>> +                if (!vp || !vp->nbsp) {
>> +                    continue;
>> +                }
>> +
>> +                for (size_t i = 0; i < vp->n_lsp_addrs; i++) {
>> +                    bool found_vip_network = false;
>> +                    const char *ea_s = vp->lsp_addrs[i].ea_s;
>> +                    for (size_t j = 0; j < vp->od->n_router_ports; j++) {
>> +                        /* Get the Logical_Router_Port that the
>> +                        * Logical_Switch_Port is connected to, as
>> +                        * 'peer'. */
>> +                        const char *peer_name = smap_get(
>> +                            &vp->od->router_ports[j]->nbsp->options,
>> +                            "router-port");
>> +                        if (!peer_name) {
>> +                            continue;
>> +                        }
>> +
>> +                        struct ovn_port *peer =
>> +                            ovn_port_find(ports, peer_name);
>> +                        if (!peer || !peer->nbrp) {
>> +                            continue;
>> +                        }
>> +
>> +                        if (!find_lrp_member_ip(peer, vip)) {
>> +                            continue;
>> +                        }
>> +
>> +                        ds_clear(&match);
>> +                        ds_put_format(&match, "outport == %s && reg0 ==
>> %s",
>> +                                        peer->json_key, vip);
>> +
>> +                        ds_clear(&actions);
>> +                        ds_put_format(&actions, "eth.dst = %s; next;",
>> ea_s);
>> +                        ovn_lflow_add(lflows, peer->od,
>> +                                        S_ROUTER_IN_ARP_RESOLVE, 100,
>> +                                        ds_cstr(&match),
>> ds_cstr(&actions));
>> +                        found_vip_network = true;
>> +                        break;
>> +                    }
>> +
>> +                    if (found_vip_network) {
>> +                        break;
>> +                    }
>> +                }
>> +            }
>>          } else if (!strcmp(op->nbsp->type, "router")) {
>>              /* This is a logical switch port that connects to a router.
>> */
>>
>> @@ -9256,6 +9406,8 @@ main(int argc, char *argv[])
>>                           &sbrec_port_binding_col_gateway_chassis);
>>      ovsdb_idl_add_column(ovnsb_idl_loop.idl,
>>                           &sbrec_port_binding_col_ha_chassis_group);
>> +    ovsdb_idl_add_column(ovnsb_idl_loop.idl,
>> +                         &sbrec_port_binding_col_virtual_parent);
>>      ovsdb_idl_add_column(ovnsb_idl_loop.idl,
>>                           &sbrec_gateway_chassis_col_chassis);
>>      ovsdb_idl_add_column(ovnsb_idl_loop.idl,
>> &sbrec_gateway_chassis_col_name);
>> diff --git a/ovn/ovn-nb.xml b/ovn/ovn-nb.xml
>> index 57b6edbf8..f5f10a5c1 100644
>> --- a/ovn/ovn-nb.xml
>> +++ b/ovn/ovn-nb.xml
>> @@ -465,6 +465,31 @@
>>                </li>
>>              </ul>
>>            </dd>
>> +
>> +          <dt><code>virtual</code></dt>
>> +          <dd>
>> +            <p>
>> +              Represents a logical port which does not have an OVS
>> +              port in the integration bridge and has a virtual ip
>> configured
>> +              in the <ref column="options:virtual-ip"/> column. This
>> virtual ip
>> +              can move around between the logical ports configured in
>> +              the <ref column="options:virtual-parents"/> column.
>> +            </p>
>> +
>> +            <p>
>> +              One of the use case where <code>virtual</code>
>> +              ports can be used is.
>> +            </p>
>> +
>> +            <ul>
>> +              <li>
>> +                The <code>virtual ip</code> represents a load balancer
>> vip
>> +                and the <code>virtual parents</code> provide load
>> balancer
>> +                service in an active-standby setup with the active
>> virtual
>> +                parent owning the <code>virtual ip</code>.
>> +              </li>
>> +            </ul>
>> +           </dd>
>>          </dl>
>>        </column>
>>      </group>
>> @@ -618,6 +643,26 @@
>>            interface, in bits.
>>          </column>
>>        </group>
>> +
>> +      <group title="Virtual port Options">
>> +        <p>
>> +          These options apply when <ref column="type"/> is
>> +          <code>virtual</code>.
>> +        </p>
>> +
>> +        <column name="options" key="virtual-ip">
>> +          This option represents the virtual IPv4 address.
>> +        </column>
>> +
>> +        <column name="options" key="virtual-parents">
>> +          This options represents a set of logical port names (with in
>> the same
>> +          logical switch) which can own the <code>virtual ip</code>
>> configured
>> +          in the <ref column="options:virtual-ip"/>. All these virtual
>> parents
>> +          should add the <code>virtual ip</code> in the
>> +          <ref column="port_security"/> if port security addressed are
>> enabled.
>> +        </column>
>> +      </group>
>> +
>>      </group>
>>
>>      <group title="Containers">
>> diff --git a/ovn/ovn-sb.ovsschema b/ovn/ovn-sb.ovsschema
>> index 2b7bc57a7..5c013b17e 100644
>> --- a/ovn/ovn-sb.ovsschema
>> +++ b/ovn/ovn-sb.ovsschema
>> @@ -1,7 +1,7 @@
>>  {
>>      "name": "OVN_Southbound",
>> -    "version": "2.4.0",
>> -    "cksum": "3059284885 20260",
>> +    "version": "2.5.0",
>> +    "cksum": "1257419092 20387",
>>      "tables": {
>>          "SB_Global": {
>>              "columns": {
>> @@ -173,6 +173,8 @@
>>                                        "minInteger": 1,
>>                                        "maxInteger": 4095},
>>                                "min": 0, "max": 1}},
>> +                "virtual_parent": {"type": {"key": "string", "min": 0,
>> +                                            "max": 1}},
>>                  "chassis": {"type": {"key": {"type": "uuid",
>>                                               "refTable": "Chassis",
>>                                               "refType": "weak"},
>> diff --git a/ovn/ovn-sb.xml b/ovn/ovn-sb.xml
>> index 544a071fa..17c45bbac 100644
>> --- a/ovn/ovn-sb.xml
>> +++ b/ovn/ovn-sb.xml
>> @@ -2017,6 +2017,24 @@ tcp.flags = RST;
>>            </p>
>>            <p><b>Prerequisite:</b> <code>igmp</code></p>
>>          </dd>
>> +
>> +        <dt><code>bind_vport(<var>V</var>, <var>P</var>);</code></dt>
>> +        <dd>
>> +          <p>
>> +            <b>Parameters</b>: logical port string field <var>V</var>
>> +            of type <code>virtual</code>, logical port string field
>> +            <var>P</var>.
>> +          </p>
>> +
>> +          <p>
>> +            Binds the virtual logical port <var>V</var> and sets the
>> +            <ref table="Port_Binding" column="chassis"/> column and
>> +            <ref table="Port_Binding" column="virtual_parent"/> of
>> +            the table <ref table="Port_Binding"/>.
>> +            <ref table="Port_Binding" column="virtual_parent"/> is
>> +            set to <var>P</var>.
>> +          </p>
>> +        </dd>
>>        </dl>
>>      </column>
>>
>> @@ -2480,6 +2498,13 @@ tcp.flags = RST;
>>              the <code>outport</code> will be reset to the value of the
>>              distributed port.
>>            </dd>
>> +
>> +          <dt><code>virtual</code></dt>
>> +          <dd>
>> +            Represents a logical port with an <code>virtual ip</code>.
>> +            This <code>virtual ip</code> can be configured on a
>> +            logical port (which is refered as virtual parent).
>> +          </dd>
>>          </dl>
>>        </column>
>>      </group>
>> @@ -2720,6 +2745,27 @@ tcp.flags = RST;
>>        </column>
>>      </group>
>>
>> +    <group title="Virtual ports">
>> +      <column name="virtual_parent">
>> +        <p>
>> +          This column is set by <code>ovn-controller</code> with one of
>> the
>> +          value from the
>> +          <ref table="Logical_Switch_Port"
>> column="options:virtual-parents"
>> +          db="OVN_Northbound"/> in the OVN_Northbound database's
>> +          <ref table="Logical_Switch_Port" db="OVN_Northbound"/> table
>> +          when the OVN action <code>bind_vport</code> is executed.
>> +          <code>ovn-controller</code> also sets the
>> +          <ref column="chassis"/> column when it executes this action
>> +          with its chassis id.
>> +        </p>
>> +
>> +        <p>
>> +          <code>ovn-controller</code> sets this column only if the
>> +          <ref column="type"/> is "virtual".
>> +        </p>
>> +      </column>
>> +    </group>
>> +
>>      <group title="Naming">
>>        <column name="external_ids" key="name">
>>          <p>
>> diff --git a/ovn/utilities/ovn-trace.c b/ovn/utilities/ovn-trace.c
>> index 044eb1cc2..b532b8eaf 100644
>> --- a/ovn/utilities/ovn-trace.c
>> +++ b/ovn/utilities/ovn-trace.c
>> @@ -2144,6 +2144,9 @@ trace_actions(const struct ovnact *ovnacts, size_t
>> ovnacts_len,
>>
>>          case OVNACT_CHECK_PKT_LARGER:
>>              break;
>> +
>> +        case OVNACT_BIND_VPORT:
>> +            break;
>>          }
>>      }
>>      ds_destroy(&s);
>> diff --git a/tests/ovn.at b/tests/ovn.at
>> index cb380d275..5d6c90c5f 100644
>> --- a/tests/ovn.at
>> +++ b/tests/ovn.at
>> @@ -1368,6 +1368,24 @@ reg0 = check_pkt_larger(foo);
>>  reg0[0] = check_pkt_larger(foo);
>>      Syntax error at `foo' expecting `;'.
>>
>> +# bind_vport
>> +# lsp1's port key is 0x11.
>> +bind_vport("lsp1", inport);
>> +    encodes as controller(userdata=00.00.00.11.00.00.00.00.11.00.00.00)
>> +# lsp2 doesn't exist. So it should be encoded as drop.
>> +bind_vport("lsp2", inport);
>> +    encodes as drop
>> +bind_vport;
>> +    Syntax error at `;' expecting `('.
>> +bind_vport(;
>> +    Syntax error at `;' expecting port name string.
>> +bind_vport("xyzzy";
>> +    Syntax error at `;' expecting `,'.
>> +bind_vport("xyzzy",;
>> +    Syntax error at `;' expecting field name.
>> +bind_vport("xyzzy", inport;
>> +    Syntax error at `;' expecting `)'.
>> +
>>  # Miscellaneous negative tests.
>>  ;
>>      Syntax error at `;'.
>> @@ -14345,6 +14363,278 @@ OVN_CLEANUP([hv1],[hv2])
>>
>>  AT_CLEANUP
>>
>> +AT_SETUP([ovn -- virtual ports])
>> +AT_KEYWORDS([virtual ports])
>> +AT_SKIP_IF([test $HAVE_PYTHON = no])
>> +ovn_start
>> +
>> +send_garp() {
>> +    local hv=$1 inport=$2 eth_src=$3 eth_dst=$4 spa=$5 tpa=$6
>> +    local
>> request=${eth_dst}${eth_src}08060001080006040001${eth_src}${spa}${eth_dst}${tpa}
>> +    as hv$hv ovs-appctl netdev-dummy/receive hv${hv}-vif$inport $request
>> +}
>> +
>> +send_arp_reply() {
>> +    local hv=$1 inport=$2 eth_src=$3 eth_dst=$4 spa=$5 tpa=$6
>> +    local
>> request=${eth_dst}${eth_src}08060001080006040002${eth_src}${spa}${eth_dst}${tpa}
>> +    as hv$hv ovs-appctl netdev-dummy/receive hv${hv}-vif$inport $request
>> +}
>> +
>> +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=sw0-p1 \
>> +    options:tx_pcap=hv1/vif1-tx.pcap \
>> +    options:rxq_pcap=hv1/vif1-rx.pcap \
>> +    ofport-request=1
>> +ovs-vsctl -- add-port br-int hv1-vif2 -- \
>> +    set interface hv1-vif2 external-ids:iface-id=sw0-p3 \
>> +    options:tx_pcap=hv1/vif2-tx.pcap \
>> +    options:rxq_pcap=hv1/vif2-rx.pcap \
>> +    ofport-request=2
>> +
>> +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=sw0-p2 \
>> +    options:tx_pcap=hv2/vif1-tx.pcap \
>> +    options:rxq_pcap=hv2/vif1-rx.pcap \
>> +    ofport-request=1
>> +ovs-vsctl -- add-port br-int hv2-vif2 -- \
>> +    set interface hv2-vif2 external-ids:iface-id=sw1-p1 \
>> +    options:tx_pcap=hv2/vif2-tx.pcap \
>> +    options:rxq_pcap=hv2/vif2-rx.pcap \
>> +    ofport-request=2
>> +
>> +ovn-nbctl ls-add sw0
>> +
>> +ovn-nbctl lsp-add sw0 sw0-vir
>> +ovn-nbctl lsp-set-addresses sw0-vir "50:54:00:00:00:10 10.0.0.10"
>> +ovn-nbctl lsp-set-port-security sw0-vir "50:54:00:00:00:10 10.0.0.10"
>> +ovn-nbctl lsp-set-type sw0-vir virtual
>> +ovn-nbctl set logical_switch_port sw0-vir options:virtual-ip=10.0.0.10
>> +ovn-nbctl set logical_switch_port sw0-vir
>> options:virtual-parents=sw0-p1,sw0-p2
>> +
>> +ovn-nbctl lsp-add sw0 sw0-p1
>> +ovn-nbctl lsp-set-addresses sw0-p1 "50:54:00:00:00:03 10.0.0.3"
>> +ovn-nbctl lsp-set-port-security sw0-p1 "50:54:00:00:00:03 10.0.0.3
>> 10.0.0.10"
>> +
>> +ovn-nbctl lsp-add sw0 sw0-p2
>> +ovn-nbctl lsp-set-addresses sw0-p2 "50:54:00:00:00:04 10.0.0.4"
>> +ovn-nbctl lsp-set-port-security sw0-p2 "50:54:00:00:00:04 10.0.0.4
>> 10.0.0.10"
>> +
>> +ovn-nbctl lsp-add sw0 sw0-p3
>> +ovn-nbctl lsp-set-addresses sw0-p3 "50:54:00:00:00:05 10.0.0.5"
>> +ovn-nbctl lsp-set-port-security sw0-p3 "50:54:00:00:00:05 10.0.0.5"
>> +
>> +# Create the second logical switch with one port
>> +ovn-nbctl ls-add sw1
>> +ovn-nbctl lsp-add sw1 sw1-p1
>> +ovn-nbctl lsp-set-addresses sw1-p1 "40:54:00:00:00:03 20.0.0.3"
>> +ovn-nbctl lsp-set-port-security sw1-p1 "40:54:00:00:00:03 20.0.0.3"
>> +
>> +# Create a logical router and attach both logical switches
>> +ovn-nbctl lr-add lr0
>> +ovn-nbctl lrp-add lr0 lr0-sw0 00:00:00:00:ff:01 10.0.0.1/24
>> +ovn-nbctl lsp-add sw0 sw0-lr0
>> +ovn-nbctl lsp-set-type sw0-lr0 router
>> +ovn-nbctl lsp-set-addresses sw0-lr0 00:00:00:00:ff:01
>> +ovn-nbctl lsp-set-options sw0-lr0 router-port=lr0-sw0
>> +
>> +ovn-nbctl lrp-add lr0 lr0-sw1 00:00:00:00:ff:02 20.0.0.1/24
>> +ovn-nbctl lsp-add sw1 sw1-lr0
>> +ovn-nbctl lsp-set-type sw1-lr0 router
>> +ovn-nbctl lsp-set-addresses sw1-lr0 00:00:00:00:ff:02
>> +ovn-nbctl lsp-set-options sw1-lr0 router-port=lr0-sw1
>> +
>> +OVN_POPULATE_ARP
>> +ovn-nbctl --wait=hv sync
>> +
>> +# Check that logical flows are added for sw0-vir in lsp_in_arp_rsp
>> pipeline
>> +# with bind_vport action.
>> +
>> +ovn-sbctl dump-flows sw0 | grep ls_in_arp_rsp | grep bind_vport >
>> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=11(ls_in_arp_rsp      ), priority=100  , match=(inport ==
>> "sw0-p1" && !is_chassis_resident("sw0-vir") && ((arp.op == 1 && arp.spa ==
>> 10.0.0.10 && arp.tpa == 10.0.0.10) || (arp.op == 2 && arp.spa ==
>> 10.0.0.10))), action=(bind_vport("sw0-vir", inport); next;)
>> +  table=11(ls_in_arp_rsp      ), priority=100  , match=(inport ==
>> "sw0-p2" && !is_chassis_resident("sw0-vir") && ((arp.op == 1 && arp.spa ==
>> 10.0.0.10 && arp.tpa == 10.0.0.10) || (arp.op == 2 && arp.spa ==
>> 10.0.0.10))), action=(bind_vport("sw0-vir", inport); next;)
>> +])
>> +
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +# Since the sw0-vir is not claimed by any chassis, eth.dst should be set
>> to
>> +# zero if the ip4.dst is the virtual ip in the router pipeline.
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=9 (lr_in_arp_resolve  ), priority=100  , match=(outport ==
>> "lr0-sw0" && reg0 == 10.0.0.10), action=(eth.dst = 00:00:00:00:00:00; next;)
>> +])
>> +
>> +ip_to_hex() {
>> +    printf "%02x%02x%02x%02x" "$@"
>> +}
>> +
>> +hv1_ch_uuid=`ovn-sbctl --bare --columns _uuid find chassis name="hv1"`
>> +hv2_ch_uuid=`ovn-sbctl --bare --columns _uuid find chassis name="hv2"`
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns chassis find port_binding \
>> +logical_port=sw0-vir) = x], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = x])
>> +
>> +# From sw0-p0 send GARP for 10.0.0.10. hv1 should claim sw0-vir
>> +# and sw0-p1 should be its virtual_parent.
>> +eth_src=505400000003
>> +eth_dst=ffffffffffff
>> +spa=$(ip_to_hex 10 0 0 10)
>> +tpa=$(ip_to_hex 10 0 0 10)
>> +send_garp 1 1 $eth_src $eth_dst $spa $tpa
>> +
>> +OVS_WAIT_UNTIL([test x$(ovn-sbctl --bare --columns chassis find
>> port_binding \
>> +logical_port=sw0-vir) = x$hv1_ch_uuid], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = xsw0-p1])
>> +
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +# There should be an arp resolve flow to resolve the virtual_ip with the
>> +# sw0-p1's MAC.
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=9 (lr_in_arp_resolve  ), priority=100  , match=(outport ==
>> "lr0-sw0" && reg0 == 10.0.0.10), action=(eth.dst = 50:54:00:00:00:03; next;)
>> +])
>> +
>> +# send the garp from sw0-p2 (in hv2). hv2 should claim sw0-vir
>> +# and sw0-p2 shpuld be its virtual_parent.
>> +eth_src=505400000004
>> +eth_dst=ffffffffffff
>> +spa=$(ip_to_hex 10 0 0 10)
>> +tpa=$(ip_to_hex 10 0 0 10)
>> +send_garp 2 1 $eth_src $eth_dst $spa $tpa
>> +
>> +OVS_WAIT_UNTIL([test x$(ovn-sbctl --bare --columns chassis find
>> port_binding \
>> +logical_port=sw0-vir) = x$hv2_ch_uuid], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = xsw0-p2])
>> +
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +# There should be an arp resolve flow to resolve the virtual_ip with the
>> +# sw0-p2's MAC.
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=9 (lr_in_arp_resolve  ), priority=100  , match=(outport ==
>> "lr0-sw0" && reg0 == 10.0.0.10), action=(eth.dst = 50:54:00:00:00:04; next;)
>> +])
>> +
>> +# Now send arp reply from sw0-p1. hv1 should claim sw0-vir
>> +# and sw0-p1 shpuld be its virtual_parent.
>> +eth_src=505400000003
>> +eth_dst=ffffffffffff
>> +spa=$(ip_to_hex 10 0 0 10)
>> +tpa=$(ip_to_hex 10 0 0 4)
>> +send_arp_reply 1 1 $eth_src $eth_dst $spa $tpa
>> +
>> +OVS_WAIT_UNTIL([test x$(ovn-sbctl --bare --columns chassis find
>> port_binding \
>> +logical_port=sw0-vir) = x$hv1_ch_uuid], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = xsw0-p1])
>> +
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=9 (lr_in_arp_resolve  ), priority=100  , match=(outport ==
>> "lr0-sw0" && reg0 == 10.0.0.10), action=(eth.dst = 50:54:00:00:00:03; next;)
>> +])
>> +
>> +# Delete hv1-vif1 port. hv1 should release sw0-vir
>> +as hv1 ovs-vsctl del-port hv1-vif1
>> +
>> +OVS_WAIT_UNTIL([test x$(ovn-sbctl --bare --columns chassis find
>> port_binding \
>> +logical_port=sw0-vir) = x], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = x])
>> +
>> +# Since the sw0-vir is not claimed by any chassis, eth.dst should be set
>> to
>> +# zero if the ip4.dst is the virtual ip.
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=9 (lr_in_arp_resolve  ), priority=100  , match=(outport ==
>> "lr0-sw0" && reg0 == 10.0.0.10), action=(eth.dst = 00:00:00:00:00:00; next;)
>> +])
>> +
>> +# Now send arp reply from sw0-p2. hv2 should claim sw0-vir
>> +# and sw0-p2 shpuld be its virtual_parent.
>> +eth_src=505400000004
>> +eth_dst=ffffffffffff
>> +spa=$(ip_to_hex 10 0 0 10)
>> +tpa=$(ip_to_hex 10 0 0 3)
>> +send_arp_reply 2 1 $eth_src $eth_dst $spa $tpa
>> +
>> +OVS_WAIT_UNTIL([test x$(ovn-sbctl --bare --columns chassis find
>> port_binding \
>> +logical_port=sw0-vir) = x$hv2_ch_uuid], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = xsw0-p2])
>> +
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=9 (lr_in_arp_resolve  ), priority=100  , match=(outport ==
>> "lr0-sw0" && reg0 == 10.0.0.10), action=(eth.dst = 50:54:00:00:00:04; next;)
>> +])
>> +
>> +# Delete sw0-p2 logical port
>> +ovn-nbctl lsp-del sw0-p2
>> +
>> +OVS_WAIT_UNTIL([test x$(ovn-sbctl --bare --columns chassis find
>> port_binding \
>> +logical_port=sw0-vir) = x], [0], [])
>> +
>> +AT_CHECK([test x$(ovn-sbctl --bare --columns virtual_parent find
>> port_binding \
>> +logical_port=sw0-vir) = x])
>> +
>> +# Clear virtual_ip column of sw0-vir. There should be no bind_vport
>> flows.
>> +ovn-nbctl --wait=hv remove logical_switch_port sw0-vir options virtual-ip
>> +
>> +ovn-sbctl dump-flows sw0 | grep ls_in_arp_rsp | grep bind_vport >
>> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +])
>> +
>> +# Add back virtual_ip and clear virtual_parents.
>> +ovn-nbctl --wait=hv set logical_switch_port sw0-vir
>> options:virtual-ip=10.0.0.10
>> +
>> +ovn-sbctl dump-flows sw0 | grep ls_in_arp_rsp | grep bind_vport >
>> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +  table=11(ls_in_arp_rsp      ), priority=100  , match=(inport ==
>> "sw0-p1" && !is_chassis_resident("sw0-vir") && ((arp.op == 1 && arp.spa ==
>> 10.0.0.10 && arp.tpa == 10.0.0.10) || (arp.op == 2 && arp.spa ==
>> 10.0.0.10))), action=(bind_vport("sw0-vir", inport); next;)
>> +])
>> +
>> +ovn-nbctl --wait=hv remove logical_switch_port sw0-vir options
>> virtual-parents
>> +ovn-sbctl dump-flows sw0 | grep ls_in_arp_rsp | grep bind_vport >
>> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +])
>> +
>> +ovn-sbctl dump-flows lr0 | grep lr_in_arp_resolve | grep "reg0 ==
>> 10.0.0.10" \
>> +> lflows.txt
>> +
>> +AT_CHECK([cat lflows.txt], [0], [dnl
>> +])
>> +
>> +OVN_CLEANUP([hv1], [hv2])
>> +AT_CLEANUP
>> +
>>  # Run ovn-nbctl in daemon mode, change to a backup database and verify
>> that
>>  # an insert operation is not allowed.
>>  AT_SETUP([ovn -- can't write to a backup database server instance])
>> diff --git a/tests/test-ovn.c b/tests/test-ovn.c
>> index 0b9e8246e..cf1bc5432 100644
>> --- a/tests/test-ovn.c
>> +++ b/tests/test-ovn.c
>> @@ -1253,6 +1253,7 @@ test_parse_actions(struct ovs_cmdl_context *ctx
>> OVS_UNUSED)
>>      simap_put(&ports, "eth0", 5);
>>      simap_put(&ports, "eth1", 6);
>>      simap_put(&ports, "LOCAL", ofp_to_u16(OFPP_LOCAL));
>> +    simap_put(&ports, "lsp1", 0x11);
>>
>>      ds_init(&input);
>>      while (!ds_get_test_line(&input, stdin)) {
>> --
>> 2.21.0
>>
>> _______________________________________________
>> dev mailing list
>> dev at openvswitch.org
>> https://mail.openvswitch.org/mailman/listinfo/ovs-dev
>>
>


More information about the dev mailing list