On 4/3/24 12:29, Lorenzo Bianconi wrote:
> Similar to what is already implemented for routed e/w traffic,
> introduce pmtud support for e/w traffic between two logical switch ports
> connected to the same logical switch, but running on two different
> hypervisors.
> 
> Acked-by: Mark Michelson <[email protected]>
> Reported-at: https://issues.redhat.com/browse/FDP-362
> Signed-off-by: Lorenzo Bianconi <[email protected]>
> ---
> Changes since v1:
> - move logic in consider_port_binding
> - add more self-test
> - fix typos
> ---

Hi Lorenzo,

I have a few comments below.  Overall the rest looks OK to me.

>  controller/lflow.h      |   1 +
>  controller/physical.c   |  30 +++++++-
>  northd/northd.c         |  35 +++++++---
>  northd/ovn-northd.8.xml |  16 +++--
>  tests/multinode.at      | 151 ++++++++++++++++++++++++++++++++++++++++
>  tests/ovn-controller.at |  63 +++++++++++++++++
>  tests/ovn-macros.at     |   1 +
>  tests/ovn-northd.at     |  22 ++++--
>  tests/ovn.at            |   5 +-
>  9 files changed, 304 insertions(+), 20 deletions(-)
> 
> diff --git a/controller/lflow.h b/controller/lflow.h
> index 9b7ffa19c..906a26280 100644
> --- a/controller/lflow.h
> +++ b/controller/lflow.h
> @@ -94,6 +94,7 @@ struct uuid;
>  #define OFTABLE_ECMP_NH                  77
>  #define OFTABLE_CHK_LB_AFFINITY          78
>  #define OFTABLE_MAC_CACHE_USE            79
> +#define OFTABLE_CT_ZONE_LOOKUP           80
>  
>  struct lflow_ctx_in {
>      struct ovsdb_idl_index *sbrec_multicast_group_by_name_datapath;
> diff --git a/controller/physical.c b/controller/physical.c
> index 7ee308694..25da789f0 100644
> --- a/controller/physical.c
> +++ b/controller/physical.c
> @@ -1498,6 +1498,26 @@ consider_port_binding(struct ovsdb_idl_index 
> *sbrec_port_binding_by_name,
>          return;
>      }
>  
> +    if (get_lport_type(binding) == LP_VIF) {
> +        /* Table 80, priority 100.
> +         * =======================
> +         *
> +         * Process ICMP{4,6} error packets too big locally generated from the
> +         * kernel in order to lookup proper ct_zone. */
> +        struct match match = MATCH_CATCHALL_INITIALIZER;
> +        match_set_metadata(&match, htonll(dp_key));
> +        match_set_reg(&match, MFF_LOG_INPORT - MFF_REG0, port_key);
> +
> +        struct zone_ids icmp_zone_ids = get_zone_ids(binding, ct_zones);
> +        ofpbuf_clear(ofpacts_p);
> +        put_zones_ofpacts(&icmp_zone_ids, ofpacts_p);
> +        put_resubmit(OFTABLE_LOG_INGRESS_PIPELINE, ofpacts_p);
> +        ofctrl_add_flow(flow_table, OFTABLE_CT_ZONE_LOOKUP, 100,
> +                        binding->header_.uuid.parts[0], &match,
> +                        ofpacts_p, &binding->header_.uuid);
> +        ofpbuf_clear(ofpacts_p);
> +    }
> +
>      struct match match;
>      if (!strcmp(binding->type, "patch")
>          || (!strcmp(binding->type, "l3gateway")
> @@ -2464,6 +2484,14 @@ physical_run(struct physical_ctx *p_ctx,
>                                flow_table, &ofpacts);
>      }
>  
> +    /* Default flow for CT_ZONE_LOOKUP Table. */
> +    struct match ct_look_def_match;
> +    match_init_catchall(&ct_look_def_match);
> +    ofpbuf_clear(&ofpacts);
> +    put_resubmit(OFTABLE_LOG_INGRESS_PIPELINE, &ofpacts);
> +    ofctrl_add_flow(flow_table, OFTABLE_CT_ZONE_LOOKUP, 0, 0,
> +                    &ct_look_def_match, &ofpacts, hc_uuid);
> +
>      /* Handle output to multicast groups, in tables 40 and 41. */
>      const struct sbrec_multicast_group *mc;
>      SBREC_MULTICAST_GROUP_TABLE_FOR_EACH (mc, p_ctx->mc_group_table) {
> @@ -2522,7 +2550,7 @@ physical_run(struct physical_ctx *p_ctx,
>          /* Add specif flows for E/W ICMPv{4,6} packets if tunnelled packets
>           * do not fit path MTU.
>           */
> -        put_resubmit(OFTABLE_LOG_INGRESS_PIPELINE, &ofpacts);
> +        put_resubmit(OFTABLE_CT_ZONE_LOOKUP, &ofpacts);
>  
>          /* IPv4 */
>          match_init_catchall(&match);
> diff --git a/northd/northd.c b/northd/northd.c
> index c568f6360..ddd960d19 100644
> --- a/northd/northd.c
> +++ b/northd/northd.c
> @@ -8678,7 +8678,7 @@ build_lswitch_lflows_admission_control(struct 
> ovn_datapath *od,
>      ovs_assert(od->nbs);
>  
>      /* Default action for recirculated ICMP error 'packet too big'. */
> -    ovn_lflow_add(lflows, od, S_SWITCH_IN_CHECK_PORT_SEC, 110,
> +    ovn_lflow_add(lflows, od, S_SWITCH_IN_CHECK_PORT_SEC, 105,
>                    "((ip4 && icmp4.type == 3 && icmp4.code == 4) ||"
>                    " (ip6 && icmp6.type == 2 && icmp6.code == 0)) &&"
>                    " flags.tunnel_rx == 1", debug_drop_action(), lflow_ref);
> @@ -11863,7 +11863,24 @@ build_lswitch_icmp_packet_toobig_admin_flows(
>  {
>      ovs_assert(op->nbsp);
>  
> +    ds_clear(match);
>      if (!lsp_is_router(op->nbsp)) {
> +        struct eth_addr mac;
> +        if (!op->nbsp->n_addresses ||
> +            !ovs_scan(op->nbsp->addresses[0], ETH_ADDR_SCAN_FMT,
> +                      ETH_ADDR_SCAN_ARGS(mac))) {

We already store the parsed addresses in op->lsp_addresses why do we
need to reparse here?

> +            return;
> +        }
> +
> +        ds_put_format(match,
> +                      "((ip4 && icmp4.type == 3 && icmp4.code == 4) ||"
> +                      " (ip6 && icmp6.type == 2 && icmp6.code == 0)) &&"
> +                      " eth.src == "ETH_ADDR_FMT" && outport == %s &&"
> +                      " !is_chassis_resident(%s) && flags.tunnel_rx == 1",
> +                      ETH_ADDR_ARGS(mac), op->json_key, op->json_key);
> +        ovn_lflow_add(lflows, op->od, S_SWITCH_IN_CHECK_PORT_SEC, 110,
> +                      ds_cstr(match), "outport <-> inport; next;",
> +                      op->lflow_ref);
>          return;
>      }
>  
> @@ -11872,26 +11889,28 @@ build_lswitch_icmp_packet_toobig_admin_flows(
>          return;
>      }
>  
> -    ds_clear(match);
>      if (peer->od->is_gw_router) {
>          ds_put_format(match,
>                        "((ip4 && icmp4.type == 3 && icmp4.code == 4) ||"
>                        " (ip6 && icmp6.type == 2 && icmp6.code == 0)) && "
>                        "eth.src == %s && outport == %s && flags.tunnel_rx == 
> 1",
>                        peer->nbrp->mac, op->json_key);
> +        ovn_lflow_add(lflows, op->od, S_SWITCH_IN_CHECK_PORT_SEC, 120,
> +                      ds_cstr(match), "outport <-> inport; next;",
> +                      op->lflow_ref);
>      } else {
>          ds_put_format(match,
>                        "((ip4 && icmp4.type == 3 && icmp4.code == 4) ||"
>                        " (ip6 && icmp6.type == 2 && icmp6.code == 0)) && "
>                        "eth.dst == %s && flags.tunnel_rx == 1",
>                        peer->nbrp->mac);
> +        ds_clear(actions);
> +        ds_put_format(actions,
> +                      "outport <-> inport; next(pipeline=ingress,table=%d);",
> +                      ovn_stage_get_table(S_SWITCH_IN_L2_LKUP));
> +        ovn_lflow_add(lflows, op->od, S_SWITCH_IN_CHECK_PORT_SEC, 120,
> +                      ds_cstr(match), ds_cstr(actions), op->lflow_ref);
>      }
> -    ds_clear(actions);
> -    ds_put_format(actions,
> -                  "outport <-> inport; next(pipeline=ingress,table=%d);",
> -                  ovn_stage_get_table(S_SWITCH_IN_L2_LKUP));
> -    ovn_lflow_add(lflows, op->od, S_SWITCH_IN_CHECK_PORT_SEC, 120,
> -                  ds_cstr(match), ds_cstr(actions), op->lflow_ref);
>  }
>  
>  static void
> diff --git a/northd/ovn-northd.8.xml b/northd/ovn-northd.8.xml
> index 90ce0de3f..82effb1b1 100644
> --- a/northd/ovn-northd.8.xml
> +++ b/northd/ovn-northd.8.xml
> @@ -324,8 +324,7 @@
>        'packet too big' and <code>eth.src == <var>D</var> &amp;&amp;
>        outport == <var>P</var> &amp;&amp; flags.tunnel_rx == 1</code> where
>        <var>D</var> is the peer logical router port <var>RP</var> mac address,
> -      swaps inport and outport and applies the action <code>
> -      next(pipeline=S_SWITCH_IN_L2_LKUP)</code>.
> +      swaps inport and outport and applies the action <code>next</code>.
>      </p>
>  
>      <p>
> @@ -338,7 +337,16 @@
>      </p>
>  
>      <p>
> -      This table adds a priority-110 flow that matches 'recirculated' 
> icmp{4,6}
> +      For each logical switch port <var>P</var> a priority-110 flow that
> +      matches 'recirculated' icmp{4,6} error 'packet too big' and <code>
> +      eth.src == <var>D</var> &amp;&amp; outport == <var>P</var> &amp;&amp;
> +      !is_chassis_resident("<var>P</var>") &amp;&amp; flags.tunnel_rx == 1
> +      </code> where <var>D</var> is the logical switch port mac address,
> +      swaps inport and outport and applies the action <code>next</code>.
> +    </p>
> +
> +    <p>
> +      This table adds a priority-105 flow that matches 'recirculated' 
> icmp{4,6}
>        error 'packet too big' to drop the packet.
>      </p>
>  
> @@ -2466,7 +2474,7 @@ output;
>          </p>
>  
>          <p>
> -          This table adds a priority-110 flow that matches 'recirculated'
> +          This table adds a priority-105 flow that matches 'recirculated'
>            icmp{4,6} error 'packet too big' to drop the packet.
>          </p>
>  
> diff --git a/tests/multinode.at b/tests/multinode.at
> index 0187382be..ef40db9b7 100644
> --- a/tests/multinode.at
> +++ b/tests/multinode.at
> @@ -154,6 +154,11 @@ check multinode_nbctl lr-nat-add lr0 snat 172.20.0.100 
> 20.0.0.0/24
>  check multinode_nbctl acl-add sw0 from-lport 1002 'ip4 || ip6'  allow-related
>  check multinode_nbctl acl-add sw1 from-lport 1002 'ip4 || ip6'  allow-related
>  
> +# create LB
> +check multinode_nbctl lb-add lb0 10.0.0.1:8080 10.0.0.4:8080 udp
> +check multinode_nbctl ls-lb-add sw0 lb0
> +M_NS_CHECK_EXEC([ovn-chassis-2], [sw0p2], [nc -u -l 8080 >/dev/null 2>&1 &])
> +
>  m_as ovn-gw-1 ip netns add ovn-ext0
>  m_as ovn-gw-1 ovs-vsctl add-port br-ex ext0 -- set interface ext0 
> type=internal
>  m_as ovn-gw-1 ip link set ext0 netns ovn-ext0
> @@ -207,6 +212,14 @@ M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -q -c 3 
> -i 0.3 -w 2 172.20.1.2 |
>  3 packets transmitted, 3 received, 0% packet loss, time 0ms
>  ])
>  
> +m_as ovn-chassis-1 ip route change 170.168.0.0/16 mtu 1000 dev eth1
> +for i in $(seq 30); do
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [sh -c 'dd bs=512 count=2 
> if=/dev/urandom |nc -u 10.0.0.1 8080'], [ignore], [ignore], [ignore])
> +done
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route get 10.0.0.1 dev sw0p1 | 
> grep -q 'mtu 942'])
> +
> +killall nc

I don't think it's OK to use killall.  Who else what other nc instances
are running on the host where these tests are executed.

We probably need to add a NETNS_DAEMONIZE()-like version to
multinode-macros.at and use it here.

The same applies for the rest of killall invocations.

> +
>  AT_CLEANUP
>  
>  AT_SETUP([ovn multinode pmtu - distributed router - vxlan])
> @@ -696,6 +709,11 @@ check multinode_nbctl lr-nat-add lr0 snat 172.20.0.100 
> 20.0.0.0/24
>  check multinode_nbctl acl-add sw0 from-lport 1002 'ip4 || ip6'  allow-related
>  check multinode_nbctl acl-add sw1 from-lport 1002 'ip4 || ip6'  allow-related
>  
> +# create LB
> +check multinode_nbctl lb-add lb0 10.0.0.1:8080 20.0.0.3:8080 udp
> +check multinode_nbctl lr-lb-add lr0 lb0
> +M_NS_CHECK_EXEC([ovn-chassis-2], [sw1p1], [nc -u -l 8080 >/dev/null 2>&1 &])
> +
>  m_as ovn-gw-1 ip netns add ovn-ext0
>  m_as ovn-gw-1 ovs-vsctl add-port br-ex ext0 -- set interface ext0 
> type=internal
>  m_as ovn-gw-1 ip link set ext0 netns ovn-ext0
> @@ -751,6 +769,18 @@ M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -q -c 3 
> -i 0.3 -w 2 172.20.1.2 |
>  M_NS_CHECK_EXEC([ovn-gw-1], [ovn-ext0], [ip link set dev ext1 mtu 1100])
>  M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -c 20 -i 0.5 -s 1300 -M do 
> 172.20.1.2 2>&1 |grep -q "mtu = 1100"])
>  
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route flush dev sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add 10.0.0.0/24 dev 
> sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add default via 10.0.0.1 
> dev sw0p1])
> +
> +m_as ovn-chassis-1 ip route change 170.168.0.0/16 mtu 1000 dev eth1
> +for i in $(seq 30); do
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [sh -c 'dd bs=512 count=2 
> if=/dev/urandom |nc -u 10.0.0.1 8080'], [ignore], [ignore], [ignore])
> +done
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route get 10.0.0.1 dev sw0p1 | 
> grep -q 'mtu 942'])
> +
> +killall nc
> +
>  AT_CLEANUP
>  
>  AT_SETUP([ovn multinode pmtu - gw router - vxlan])
> @@ -834,6 +864,11 @@ check multinode_nbctl lr-nat-add lr0 snat 172.20.0.100 
> 20.0.0.0/24
>  check multinode_nbctl acl-add sw0 from-lport 1002 'ip4 || ip6'  allow-related
>  check multinode_nbctl acl-add sw1 from-lport 1002 'ip4 || ip6'  allow-related
>  
> +# create LB
> +check multinode_nbctl lb-add lb0 10.0.0.1:8080 20.0.0.3:8080 udp
> +check multinode_nbctl lr-lb-add lr0 lb0
> +M_NS_CHECK_EXEC([ovn-chassis-2], [sw1p1], [nc -u -l 8080 >/dev/null 2>&1 &])
> +
>  m_as ovn-gw-1 ip netns add ovn-ext0
>  m_as ovn-gw-1 ovs-vsctl add-port br-ex ext0 -- set interface ext0 
> type=internal
>  m_as ovn-gw-1 ip link set ext0 netns ovn-ext0
> @@ -882,4 +917,120 @@ M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -q -c 3 
> -i 0.3 -w 2 172.20.1.2 |
>  
>  M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -c 20 -i 0.5 -s 1300 -M do 
> 172.20.1.2 2>&1 |grep -q "mtu = 1150"])
>  
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route flush dev sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add 10.0.0.0/24 dev 
> sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add default via 10.0.0.1 
> dev sw0p1])
> +
> +m_as ovn-chassis-1 ip route change 170.168.0.0/16 mtu 1000 dev eth1
> +for i in $(seq 30); do
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [sh -c 'dd bs=512 count=2 
> if=/dev/urandom |nc -u 10.0.0.1 8080'], [ignore], [ignore], [ignore])
> +done
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route get 10.0.0.1 dev sw0p1 | 
> grep -q 'mtu 950'])
> +
> +killall nc
> +
> +AT_CLEANUP
> +
> +AT_SETUP([ovn multinode pmtu - logical switch - geneve])
> +
> +# Check that ovn-fake-multinode setup is up and running
> +check_fake_multinode_setup
> +
> +# Delete the multinode NB and OVS resources before starting the test.
> +cleanup_multinode_resources
> +
> +m_as ovn-chassis-1 ip link del sw0p1-p
> +m_as ovn-chassis-2 ip link del sw0p2-p
> +
> +# Reset geneve tunnels
> +for c in ovn-chassis-1 ovn-chassis-2 ovn-gw-1
> +do
> +    m_as $c ovs-vsctl set open . external-ids:ovn-encap-type=geneve
> +done
> +
> +OVS_WAIT_UNTIL([m_as ovn-chassis-1 ip link show | grep -q genev_sys])
> +OVS_WAIT_UNTIL([m_as ovn-chassis-2 ip link show | grep -q genev_sys])
> +OVS_WAIT_UNTIL([m_as ovn-gw-1 ip link show | grep -q genev_sys])
> +
> +# Test East-West switching
> +check multinode_nbctl ls-add sw0
> +check multinode_nbctl lsp-add sw0 sw0-port1
> +check multinode_nbctl lsp-set-addresses sw0-port1 "50:54:00:00:00:03 
> 10.0.0.3 1000::3"
> +check multinode_nbctl lsp-add sw0 sw0-port2
> +check multinode_nbctl lsp-set-addresses sw0-port2 "50:54:00:00:00:04 
> 10.0.0.4 1000::4"
> +
> +m_as ovn-chassis-1 /data/create_fake_vm.sh sw0-port1 sw0p1 50:54:00:00:00:03 
> 10.0.0.3 24 10.0.0.1 1000::3/64 1000::a
> +m_as ovn-chassis-2 /data/create_fake_vm.sh sw0-port2 sw0p2 50:54:00:00:00:04 
> 10.0.0.4 24 10.0.0.1 1000::4/64 1000::a
> +
> +# Create the second logical switch with one port
> +check multinode_nbctl ls-add sw1
> +check multinode_nbctl lsp-add sw1 sw1-port1
> +check multinode_nbctl lsp-set-addresses sw1-port1 "40:54:00:00:00:03 
> 20.0.0.3 2000::3"
> +
> +# Create a logical router and attach both logical switches
> +check multinode_nbctl lr-add lr0
> +check multinode_nbctl lrp-add lr0 lr0-sw0 00:00:00:00:ff:01 10.0.0.1/24 
> 1000::a/64
> +check multinode_nbctl lsp-add sw0 sw0-lr0
> +check multinode_nbctl lsp-set-type sw0-lr0 router
> +check multinode_nbctl lsp-set-addresses sw0-lr0 router
> +check multinode_nbctl lsp-set-options sw0-lr0 router-port=lr0-sw0
> +
> +check multinode_nbctl lrp-add lr0 lr0-sw1 00:00:00:00:ff:02 20.0.0.1/24 
> 2000::a/64
> +check multinode_nbctl lsp-add sw1 sw1-lr0
> +check multinode_nbctl lsp-set-type sw1-lr0 router
> +check multinode_nbctl lsp-set-addresses sw1-lr0 router
> +check multinode_nbctl lsp-set-options sw1-lr0 router-port=lr0-sw1
> +
> +m_as ovn-chassis-2 /data/create_fake_vm.sh sw1-port1 sw1p1 40:54:00:00:00:03 
> 20.0.0.3 24 20.0.0.1 2000::3/64 2000::a
> +
> +check multinode_nbctl lr-nat-add lr0 snat 172.20.0.100 10.0.0.0/24
> +check multinode_nbctl lr-nat-add lr0 snat 172.20.0.100 20.0.0.0/24
> +
> +check multinode_nbctl lrp-set-gateway-chassis lr0-sw0 ovn-chassis-1 10
> +check multinode_nbctl lrp-set-gateway-chassis lr0-sw1 ovn-chassis-2 10
> +
> +# create some ACLs
> +check multinode_nbctl acl-add sw0 from-lport 1002 'ip4 || ip6'  allow-related
> +check multinode_nbctl acl-add sw1 from-lport 1002 'ip4 || ip6'  allow-related
> +
> +check multinode_nbctl lb-add lb0 10.0.0.1:8080 10.0.0.4:8080 udp
> +check multinode_nbctl ls-lb-add sw0 lb0
> +M_NS_CHECK_EXEC([ovn-chassis-2], [sw0p2], [nc -u -l 8080 >/dev/null 2>&1 &])
> +
> +m_wait_for_ports_up
> +
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -q -c 3 -i 0.3 -w 2 10.0.0.4 
> | FORMAT_PING], \
> +[0], [dnl
> +3 packets transmitted, 3 received, 0% packet loss, time 0ms
> +])
> +
> +# Change ptmu for the geneve tunnel
> +m_as ovn-chassis-1 ip route change 170.168.0.0/16 mtu 1200 dev eth1
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -c 5 -s 1300 -M do 10.0.0.4 
> 2>&1 |grep -q "message too long, mtu=1142"])
> +
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route flush dev sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add 10.0.0.0/24 dev 
> sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add default via 10.0.0.1 
> dev sw0p1])
> +
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -q -c 3 -i 0.3 -w 2 20.0.0.3 
> | FORMAT_PING], \
> +[0], [dnl
> +3 packets transmitted, 3 received, 0% packet loss, time 0ms
> +])
> +
> +# Change ptmu for the geneve tunnel
> +m_as ovn-chassis-1 ip route change 170.168.0.0/16 mtu 1100 dev eth1
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ping -c 5 -s 1300 -M do 20.0.0.3 
> 2>&1 |grep -q "message too long, mtu=1042"])
> +
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route flush dev sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add 10.0.0.0/24 dev 
> sw0p1])
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route add default via 10.0.0.1 
> dev sw0p1])
> +
> +m_as ovn-chassis-1 ip route change 170.168.0.0/16 mtu 1000 dev eth1
> +for i in $(seq 30); do
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [sh -c 'dd bs=512 count=2 
> if=/dev/urandom |nc -u 10.0.0.1 8080'], [ignore], [ignore], [ignore])
> +done
> +M_NS_CHECK_EXEC([ovn-chassis-1], [sw0p1], [ip route get 10.0.0.1 dev sw0p1 | 
> grep -q 'mtu 942'])
> +
> +killall nc
> +
>  AT_CLEANUP
> diff --git a/tests/ovn-controller.at b/tests/ovn-controller.at
> index 3202f0bef..7e256f7b0 100644
> --- a/tests/ovn-controller.at
> +++ b/tests/ovn-controller.at
> @@ -2879,3 +2879,66 @@ AT_CHECK([test x"$port_uuid"=$(ovs-vsctl get port 
> $fakech_tunnel _uuid)])
>  OVN_CLEANUP([hv1])
>  AT_CLEANUP
>  ])
> +
> +OVN_FOR_EACH_NORTHD([
> +AT_SETUP([ovn-controller - pmtud flows])
> +AT_KEYWORDS([pmtud])
> +
> +ovn_start
> +
> +net_add n1
> +sim_add hv1
> +ovs-vsctl add-br br-phys
> +ovn_attach n1 br-phys 192.168.0.1
> +
> +check ovn-nbctl ls-add ls1 \
> +    -- lsp-add ls1 lsp1 \
> +    -- lsp-set-addresses lsp1 "00:00:00:00:00:01 192.168.1.1" \
> +    -- lsp-add ls1 lsp2 \
> +    -- lsp-set-addresses lsp2 "00:00:00:00:00:02 192.168.1.2"
> +
> +as hv1
> +check ovs-vsctl \
> +    -- add-port br-int vif1 \
> +    -- set Interface vif1 external_ids:iface-id=lsp1 \
> +    -- add-port br-int vif2 \
> +    -- set Interface vif2 external_ids:iface-id=lsp2
> +
> +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int table=OFTABLE_CT_ZONE_LOOKUP | \
> +          sed -e 's/cookie=0x.*, duration=.*, table/cookie=??, duration=??, 
> table/' | \
> +          sed -e 
> 's/actions=load:0x.*->NXM_NX_REG13/actions=load:0x?->NXM_NX_REG13/' | \
> +          grep -v NXST_FLOW |sort], [0], [dnl
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=0 
> actions=resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x1,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x2,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> +])
> +
> +check ovn-nbctl lsp-add ls1 lsp3 \
> +    -- lsp-set-addresses lsp3 "00:00:00:00:00:03 192.168.1.3"
> +check ovs-vsctl \
> +    -- add-port br-int vif3 \
> +    -- set Interface vif3 external_ids:iface-id=lsp3
> +
> +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int table=OFTABLE_CT_ZONE_LOOKUP | \
> +          sed -e 's/cookie=0x.*, duration=.*, table/cookie=??, duration=??, 
> table/' | \
> +          sed -e 
> 's/actions=load:0x.*->NXM_NX_REG13/actions=load:0x?->NXM_NX_REG13/' | \
> +          grep -v NXST_FLOW |sort], [0], [dnl
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=0 
> actions=resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x1,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x2,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x3,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> +])
> +
> +check ovn-nbctl lsp-del lsp3
> +AT_CHECK([as hv1 ovs-ofctl dump-flows br-int table=OFTABLE_CT_ZONE_LOOKUP | \
> +          sed -e 's/cookie=0x.*, duration=.*, table/cookie=??, duration=??, 
> table/' | \
> +          sed -e 
> 's/actions=load:0x.*->NXM_NX_REG13/actions=load:0x?->NXM_NX_REG13/' |
> +          grep -v NXST_FLOW |sort], [0], [dnl
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=0 
> actions=resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x1,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> + cookie=??, duration=??, table=OFTABLE_CT_ZONE_LOOKUP, n_packets=0, 
> n_bytes=0, idle_age=0, priority=100,reg14=0x2,metadata=0x1 
> actions=load:0x?->NXM_NX_REG13[[0..15]],load:0x2->NXM_NX_REG11[[]],load:0x1->NXM_NX_REG12[[]],resubmit(,OFTABLE_LOG_INGRESS_PIPELINE)
> +])
> +
> +OVN_CLEANUP([hv1])
> +AT_CLEANUP
> +])
> diff --git a/tests/ovn-macros.at b/tests/ovn-macros.at
> index ed93764d3..cc37f12f3 100644
> --- a/tests/ovn-macros.at
> +++ b/tests/ovn-macros.at
> @@ -1062,5 +1062,6 @@ m4_define([OFTABLE_ECMP_NH_MAC], [76])
>  m4_define([OFTABLE_ECMP_NH], [77])
>  m4_define([OFTABLE_CHK_LB_AFFINITY], [78])
>  m4_define([OFTABLE_MAC_CACHE_USE], [79])
> +m4_define([OFTABLE_CT_ZONE_LOOKUP], [80])
>  
>  m4_define([OFTABLE_SAVE_INPORT_HEX], [m4_eval(OFTABLE_SAVE_INPORT, 16)])
> diff --git a/tests/ovn-northd.at b/tests/ovn-northd.at
> index cd53755b2..e3ac8da45 100644
> --- a/tests/ovn-northd.at
> +++ b/tests/ovn-northd.at
> @@ -8571,7 +8571,7 @@ ovn_strip_lflows ], [0], [dnl
>    table=??(ls_in_apply_port_sec), priority=50   , match=(reg0[[15]] == 1), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(eth.src[[40]]), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(vlan.present), 
> action=(drop;)
> -  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=105  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
>    table=??(ls_in_check_port_sec), priority=50   , match=(1), 
> action=(reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_l2_lkup      ), priority=0    , match=(1), action=(outport 
> = get_fdb(eth.dst); next;)
>    table=??(ls_in_l2_lkup      ), priority=110  , match=(eth.dst == 
> $svc_monitor_mac && (tcp || icmp || icmp6)), 
> action=(handle_svc_check(inport);)
> @@ -8597,7 +8597,9 @@ ovn_strip_lflows ], [0], [dnl
>    table=??(ls_in_apply_port_sec), priority=50   , match=(reg0[[15]] == 1), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(eth.src[[40]]), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(vlan.present), 
> action=(drop;)
> -  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=105  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:01 && outport == "sw0p1" && 
> !is_chassis_resident("sw0p1") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:02 && outport == "sw0p2" && 
> !is_chassis_resident("sw0p2") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
>    table=??(ls_in_check_port_sec), priority=50   , match=(1), 
> action=(reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_l2_lkup      ), priority=0    , match=(1), action=(outport 
> = get_fdb(eth.dst); next;)
>    table=??(ls_in_l2_lkup      ), priority=110  , match=(eth.dst == 
> $svc_monitor_mac && (tcp || icmp || icmp6)), 
> action=(handle_svc_check(inport);)
> @@ -8624,7 +8626,9 @@ ovn_strip_lflows ], [0], [dnl
>    table=??(ls_in_apply_port_sec), priority=50   , match=(reg0[[15]] == 1), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(eth.src[[40]]), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(vlan.present), 
> action=(drop;)
> -  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=105  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:01 && outport == "sw0p1" && 
> !is_chassis_resident("sw0p1") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:02 && outport == "sw0p2" && 
> !is_chassis_resident("sw0p2") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
>    table=??(ls_in_check_port_sec), priority=50   , match=(1), 
> action=(reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_l2_lkup      ), priority=0    , match=(1), action=(outport 
> = get_fdb(eth.dst); next;)
>    table=??(ls_in_l2_lkup      ), priority=110  , match=(eth.dst == 
> $svc_monitor_mac && (tcp || icmp || icmp6)), 
> action=(handle_svc_check(inport);)
> @@ -8652,7 +8656,9 @@ ovn_strip_lflows ], [0], [dnl
>    table=??(ls_in_check_port_sec), priority=100  , match=(eth.src[[40]]), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(inport == "sw0p1"), 
> action=(reg0[[15]] = 1; next;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(vlan.present), 
> action=(drop;)
> -  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=105  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:01 && outport == "sw0p1" && 
> !is_chassis_resident("sw0p1") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:02 && outport == "sw0p2" && 
> !is_chassis_resident("sw0p2") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
>    table=??(ls_in_check_port_sec), priority=50   , match=(1), 
> action=(reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_l2_lkup      ), priority=0    , match=(1), action=(outport 
> = get_fdb(eth.dst); next;)
>    table=??(ls_in_l2_lkup      ), priority=110  , match=(eth.dst == 
> $svc_monitor_mac && (tcp || icmp || icmp6)), 
> action=(handle_svc_check(inport);)
> @@ -8679,7 +8685,9 @@ ovn_strip_lflows ], [0], [dnl
>    table=??(ls_in_check_port_sec), priority=100  , match=(eth.src[[40]]), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(inport == "sw0p1"), 
> action=(reg0[[15]] = 1; next;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(vlan.present), 
> action=(drop;)
> -  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=105  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:01 && outport == "sw0p1" && 
> !is_chassis_resident("sw0p1") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:02 && outport == "sw0p2" && 
> !is_chassis_resident("sw0p2") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
>    table=??(ls_in_check_port_sec), priority=50   , match=(1), 
> action=(reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_check_port_sec), priority=70   , match=(inport == "sw0p2"), 
> action=(set_queue(10); reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_l2_lkup      ), priority=0    , match=(1), action=(outport 
> = get_fdb(eth.dst); next;)
> @@ -8709,7 +8717,9 @@ ovn_strip_lflows ], [0], [dnl
>    table=??(ls_in_apply_port_sec), priority=50   , match=(reg0[[15]] == 1), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(eth.src[[40]]), 
> action=(drop;)
>    table=??(ls_in_check_port_sec), priority=100  , match=(vlan.present), 
> action=(drop;)
> -  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=105  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> flags.tunnel_rx == 1), action=(drop;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:01 && outport == "sw0p1" && 
> !is_chassis_resident("sw0p1") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
> +  table=??(ls_in_check_port_sec), priority=110  , match=(((ip4 && icmp4.type 
> == 3 && icmp4.code == 4) || (ip6 && icmp6.type == 2 && icmp6.code == 0)) && 
> eth.src == 00:00:00:00:00:02 && outport == "sw0p2" && 
> !is_chassis_resident("sw0p2") && flags.tunnel_rx == 1), action=(outport <-> 
> inport; next;)
>    table=??(ls_in_check_port_sec), priority=50   , match=(1), 
> action=(reg0[[15]] = check_in_port_sec(); next;)
>    table=??(ls_in_check_port_sec), priority=70   , match=(inport == 
> "localnetport"), action=(set_queue(10); reg0[[15]] = check_in_port_sec(); 
> next;)
>    table=??(ls_in_check_port_sec), priority=70   , match=(inport == "sw0p1"), 
> action=(reg0[[14]] = 1; next(pipeline=ingress, table=??);)
> diff --git a/tests/ovn.at b/tests/ovn.at
> index dd2ebce98..6151fcdda 100644
> --- a/tests/ovn.at
> +++ b/tests/ovn.at
> @@ -34917,6 +34917,9 @@ m4_define([MULTIPLE_OVS_INT],
>     check ovn-nbctl lsp-add ls lp
>     if test X$1 != X; then
>         check ovn-nbctl lsp-set-type lp $1
> +       nb_flows_ref=0
> +   else
> +       nb_flows_ref=1
>     fi
>     check ovn-nbctl lsp-set-addresses lp "00:00:00:01:01:02 192.168.1.2"
>  
> @@ -34998,7 +35001,7 @@ m4_define([MULTIPLE_OVS_INT],
>     check ovs-vsctl del-port br-int lpnew
>     OVS_WAIT_UNTIL([
>         nb_flows=`ovs-ofctl dump-flows br-int | grep $COOKIE | wc -l`
> -       test "${nb_flows}" = 0
> +       test "${nb_flows}" = $nb_flows_ref
>     ])
>  
>     echo ======================================================

Regards,
Dumitru

_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Reply via email to