From 0ed8c91b86b0d4bc01b4795155b25e85df1c6a9d Mon Sep 17 00:00:00 2001
From: Russell Bryant <russell@ovn.org>
Date: Fri, 25 Oct 2019 16:47:21 -0400
Subject: [PATCH 4/5] northd: Add lflows for IPv6 NAT.
Signed-off-by: Russell Bryant <russell@ovn.org>
Acked-by: Numan Siddique <numans@ovn.org>
---
ovn/northd/ovn-northd.8.xml | 233 ++++++++++++----------
ovn/northd/ovn-northd.c | 384 +++++++++++++++++++++++++++---------
2 files changed, 418 insertions(+), 199 deletions(-)
diff --git a/ovn/northd/ovn-northd.8.xml b/ovn/northd/ovn-northd.8.xml
index b9ae28e14..38e6ecec5 100644
--- a/ovn/northd/ovn-northd.8.xml
+++ b/ovn/northd/ovn-northd.8.xml
@@ -1498,11 +1498,55 @@ output;
<li>
<p>
- These flows reply to ARP requests for the virtual IP addresses
- configured in the router for DNAT or load balancing. For a
- configured DNAT IP address or a load balancer IPv4 VIP <var>A</var>,
- for each router port <var>P</var> with Ethernet
- address <var>E</var>, a priority-90 flow matches
+ Reply to IPv6 Neighbor Solicitations. These flows reply to
+ Neighbor Solicitation requests for the router's own IPv6
+ address and populate the logical router's mac binding table.
+ </p>
+
+ <p>
+ For each router port <var>P</var> that
+ owns IPv6 address <var>A</var>, solicited node address <var>S</var>,
+ and Ethernet address <var>E</var>, a priority-90 flow matches
+ <code>inport == <var>P</var> &&
+ nd_ns && ip6.dst == {<var>A</var>, <var>E</var>} &&
+ nd.target == <var>A</var></code> with the following actions:
+ </p>
+
+ <pre>
+nd_na_router {
+ eth.src = <var>E</var>;
+ ip6.src = <var>A</var>;
+ nd.target = <var>A</var>;
+ nd.tll = <var>E</var>;
+ outport = inport;
+ flags.loopback = 1;
+ output;
+};
+ </pre>
+
+ <p>
+ For the gateway port on a distributed logical router (where
+ one of the logical router ports specifies a
+ <code>redirect-chassis</code>), the above flows replying to
+ IPv6 Neighbor Solicitations are only programmed on the
+ gateway port instance on the <code>redirect-chassis</code>.
+ This behavior avoids generation of multiple replies from
+ different chassis, and allows upstream MAC learning to point
+ to the <code>redirect-chassis</code>.
+ </p>
+ </li>
+
+ <li>
+ <p>
+ These flows reply to ARP requests or IPv6 neighbor solicitation
+ for the virtual IP addresses configured in the router for DNAT
+ or load balancing.
+ </p>
+
+ <p>
+ IPv4: For a configured DNAT IP address or a load balancer
+ IPv4 VIP <var>A</var>, for each router port <var>P</var> with
+ Ethernet address <var>E</var>, a priority-90 flow matches
<code>inport == <var>P</var> && arp.op == 1 &&
arp.tpa == <var>A</var></code> (ARP request)
with the following actions:
@@ -1521,6 +1565,30 @@ flags.loopback = 1;
output;
</pre>
+ <p>
+ IPv6: For a configured DNAT IP address or a load balancer
+ IPv6 VIP <var>A</var>, solicited node address <var>S</var>,
+ for each router port <var>P</var> with
+ Ethernet address <var>E</var>, a priority-90 flow matches
+ <code>inport == <var>P</var> && nd_ns &&
+ ip6.dst == {<var>A</var>, <var>S</var>} &&
+ nd.target == <var>A</var></code>
+ with the following actions:
+ </p>
+
+ <pre>
+eth.dst = eth.src;
+nd_na {
+ eth.src = <var>E</var>;
+ nd.tll = <var>E</var>;
+ ip6.src = <var>A</var>;
+ nd.target = <var>A</var>;
+ outport = <var>P</var>;
+ flags.loopback = 1;
+ output;
+}
+ </pre>
+
<p>
For the gateway port on a distributed logical router with NAT
(where one of the logical router ports specifies a
@@ -1557,6 +1625,15 @@ eth.src = <var>external_mac</var>;
arp.sha = <var>external_mac</var>;
</pre>
+ <p>
+ or in the case of IPv6 neighbor solicition:
+ </p>
+
+ <pre>
+eth.src = <var>external_mac</var>;
+nd.tll = <var>external_mac</var>;
+ </pre>
+
<p>
This behavior avoids generation of multiple ARP responses
from different chassis, and allows upstream MAC learning to
@@ -1566,68 +1643,6 @@ arp.sha = <var>external_mac</var>;
</ul>
</li>
- <li>
- <p>
- Reply to IPv6 Neighbor Solicitations. These flows reply to
- Neighbor Solicitation requests for the router's own IPv6
- address and load balancing IPv6 VIPs and populate the logical
- router's mac binding table.
- </p>
-
- <p>
- For each router port <var>P</var> that
- owns IPv6 address <var>A</var>, solicited node address <var>S</var>,
- and Ethernet address <var>E</var>, a priority-90 flow matches
- <code>inport == <var>P</var> &&
- nd_ns && ip6.dst == {<var>A</var>, <var>E</var>} &&
- nd.target == <var>A</var></code> with the following actions:
- </p>
-
- <pre>
-nd_na_router {
- eth.src = <var>E</var>;
- ip6.src = <var>A</var>;
- nd.target = <var>A</var>;
- nd.tll = <var>E</var>;
- outport = inport;
- flags.loopback = 1;
- output;
-};
- </pre>
-
- <p>
- For each router port <var>P</var> that has load balancing VIP
- <var>A</var>, solicited node address <var>S</var>, and Ethernet
- address <var>E</var>, a priority-90 flow matches
- <code>inport == <var>P</var> &&
- nd_ns && ip6.dst == {<var>A</var>, <var>E</var>} &&
- nd.target == <var>A</var></code> with the following actions:
- </p>
-
- <pre>
-nd_na {
- eth.src = <var>E</var>;
- ip6.src = <var>A</var>;
- nd.target = <var>A</var>;
- nd.tll = <var>E</var>;
- outport = inport;
- flags.loopback = 1;
- output;
-};
- </pre>
-
- <p>
- For the gateway port on a distributed logical router (where
- one of the logical router ports specifies a
- <code>redirect-chassis</code>), the above flows replying to
- IPv6 Neighbor Solicitations are only programmed on the
- gateway port instance on the <code>redirect-chassis</code>.
- This behavior avoids generation of multiple replies from
- different chassis, and allows upstream MAC learning to point
- to the <code>redirect-chassis</code>.
- </p>
- </li>
-
<li>
Priority-85 flows which drops the ARP and IPv6 Neighbor Discovery
packets.
@@ -1681,10 +1696,11 @@ nd_na {
handled by one of the flows above, which amounts to ICMP (other than
echo requests) and fragments with nonzero offsets. For each IP address
<var>A</var> owned by the router, a priority-60 flow matches
- <code>ip4.dst == <var>A</var></code> and drops the traffic. An
- exception is made and the above flow is not added if the router
- port's own IP address is used to SNAT packets passing through that
- router.
+ <code>ip4.dst == <var>A</var></code> or
+ <code>ip6.dst == <var>A</var></code>
+ and drops the traffic. An exception is made and the above flow
+ is not added if the router port's own IP address is used to SNAT
+ packets passing through that router.
</li>
</ul>
@@ -1778,23 +1794,26 @@ icmp6 {
<p>
If the Gateway router has been configured to force SNAT any
previously DNATted packets to <var>B</var>, a priority-110 flow
- matches <code>ip && ip4.dst == <var>B</var></code> with
- an action <code>ct_snat; </code>.
+ matches <code>ip && ip4.dst == <var>B</var></code> or
+ <code>ip && ip6.dst == <var>B</var></code>
+ with an action <code>ct_snat; </code>.
</p>
<p>
If the Gateway router has been configured to force SNAT any
previously load-balanced packets to <var>B</var>, a priority-100 flow
- matches <code>ip && ip4.dst == <var>B</var></code> with
- an action <code>ct_snat; </code>.
+ matches <code>ip && ip4.dst == <var>B</var></code> or
+ <code>ip && ip6.dst == <var>B</var></code>
+ with an action <code>ct_snat; </code>.
</p>
<p>
For each NAT configuration in the OVN Northbound database, that asks
to change the source IP address of a packet from <var>A</var> to
- <var>B</var>, a priority-90 flow matches <code>ip &&
- ip4.dst == <var>B</var></code> with an action
- <code>ct_snat; </code>.
+ <var>B</var>, a priority-90 flow matches
+ <code>ip && ip4.dst == <var>B</var></code> or
+ <code>ip && ip6.dst == <var>B</var></code>
+ with an action <code>ct_snat; </code>.
</p>
<p>
@@ -1812,7 +1831,9 @@ icmp6 {
For each configuration in the OVN Northbound database, that asks
to change the source IP address of a packet from <var>A</var> to
<var>B</var>, a priority-100 flow matches <code>ip &&
- ip4.dst == <var>B</var> && inport == <var>GW</var></code>,
+ ip4.dst == <var>B</var> && inport == <var>GW</var></code> or
+ <code>ip &&
+ ip6.dst == <var>B</var> && inport == <var>GW</var></code>
where <var>GW</var> is the logical router gateway port, with an
action <code>ct_snat;</code>.
</p>
@@ -1826,10 +1847,12 @@ icmp6 {
<p>
For each configuration in the OVN Northbound database, that asks
to change the source IP address of a packet from <var>A</var> to
- <var>B</var>, a priority-50 flow matches <code>ip &&
- ip4.dst == <var>B</var></code> with an action
+ <var>B</var>, a priority-50 flow matches
+ <code>ip && ip4.dst == <var>B</var></code> or
+ <code>ip && ip6.dst == <var>B</var></code>
+ with an action
<code>REGBIT_NAT_REDIRECT = 1; next;</code>. This flow is for
- east/west traffic to a NAT destination IPv4 address. By
+ east/west traffic to a NAT destination IPv4/IPv6 address. By
setting the <code>REGBIT_NAT_REDIRECT</code> flag, in the
ingress table <code>Gateway Redirect</code> this will trigger a
redirect to the instance of the gateway port on the
@@ -1875,25 +1898,27 @@ icmp6 {
For all the configured load balancing rules for a Gateway router or
Router with gateway port in <code>OVN_Northbound</code> database that
includes a L4 port <var>PORT</var> of protocol <var>P</var> and IPv4
- address <var>VIP</var>, a priority-120 flow that matches on
+ or IPv6 address <var>VIP</var>, a priority-120 flow that matches on
<code>ct.new && ip && ip4.dst == <var>VIP</var>
&& <var>P</var> && <var>P</var>.dst == <var>PORT
- </var></code> with an action of <code>ct_lb(<var>args</var>)</code>,
- where <var>args</var> contains comma separated IPv4 addresses (and
- optional port numbers) to load balance to. If the router is configured
- to force SNAT any load-balanced packets, the above action will be
- replaced by <code>flags.force_snat_for_lb = 1;
+ </var></code> (<code>ip6.dst == <var>VIP</var></code> in the IPv6 case)
+ with an action of <code>ct_lb(<var>args</var>)</code>,
+ where <var>args</var> contains comma separated IPv4 or IPv6 addresses
+ (and optional port numbers) to load balance to. If the router is
+ configured to force SNAT any load-balanced packets, the above action
+ will be replaced by <code>flags.force_snat_for_lb = 1;
ct_lb(<var>args</var>);</code>.
</li>
<li>
For all the configured load balancing rules for a router in
<code>OVN_Northbound</code> database that includes a L4 port
- <var>PORT</var> of protocol <var>P</var> and IPv4 address
+ <var>PORT</var> of protocol <var>P</var> and IPv4 or IPv6 address
<var>VIP</var>, a priority-120 flow that matches on
<code>ct.est && ip && ip4.dst == <var>VIP</var>
&& <var>P</var> && <var>P</var>.dst == <var>PORT
- </var></code> with an action of <code>ct_dnat;</code>. If the router is
+ </var></code> (<code>ip6.dst == <var>VIP</var></code> in the IPv6 case)
+ with an action of <code>ct_dnat;</code>. If the router is
configured to force SNAT any load-balanced packets, the above action
will be replaced by <code>flags.force_snat_for_lb = 1; ct_dnat;</code>.
</li>
@@ -1903,11 +1928,13 @@ icmp6 {
<code>OVN_Northbound</code> database that includes just an IP address
<var>VIP</var> to match on, a priority-110 flow that matches on
<code>ct.new && ip && ip4.dst ==
- <var>VIP</var></code> with an action of
+ <var>VIP</var></code> (<code>ip6.dst == <var>VIP</var></code> in the
+ IPv6 case) with an action of
<code>ct_lb(<var>args</var>)</code>, where <var>args</var> contains
- comma separated IPv4 addresses. If the router is configured to force
- SNAT any load-balanced packets, the above action will be replaced by
- <code>flags.force_snat_for_lb = 1; ct_lb(<var>args</var>);</code>.
+ comma separated IPv4 or IPv6 addresses. If the router is configured
+ to force SNAT any load-balanced packets, the above action will be
+ replaced by <code>flags.force_snat_for_lb = 1;
+ ct_lb(<var>args</var>);</code>.
</li>
<li>
@@ -1915,7 +1942,8 @@ icmp6 {
<code>OVN_Northbound</code> database that includes just an IP address
<var>VIP</var> to match on, a priority-110 flow that matches on
<code>ct.est && ip && ip4.dst ==
- <var>VIP</var></code> with an action of <code>ct_dnat;</code>.
+ <var>VIP</var></code> (or <code>ip6.dst == <var>VIP</var></code>)
+ with an action of <code>ct_dnat;</code>.
If the router is configured to force SNAT any load-balanced
packets, the above action will be replaced by
<code>flags.force_snat_for_lb = 1; ct_dnat;</code>.
@@ -1929,7 +1957,8 @@ icmp6 {
For each configuration in the OVN Northbound database, that asks
to change the destination IP address of a packet from <var>A</var> to
<var>B</var>, a priority-100 flow matches <code>ip &&
- ip4.dst == <var>A</var></code> with an action
+ ip4.dst == <var>A</var></code> or <code>ip &&
+ ip6.dst == <var>A</var></code> with an action
<code>flags.loopback = 1; ct_dnat(<var>B</var>);</code>. If the
Gateway router is configured to force SNAT any DNATed packet,
the above action will be replaced by
@@ -1966,7 +1995,8 @@ icmp6 {
<var>B</var>, a priority-100 flow matches <code>ip &&
ip4.dst == <var>B</var> && inport == <var>GW</var></code>,
where <var>GW</var> is the logical router gateway port, with an
- action <code>ct_dnat(<var>B</var>);</code>.
+ action <code>ct_dnat(<var>B</var>);</code>. The match will
+ include <code>ip6.dst == <var>B</var></code> in the IPv6 case.
</p>
<p>
@@ -1979,9 +2009,10 @@ icmp6 {
For each configuration in the OVN Northbound database, that asks
to change the destination IP address of a packet from <var>A</var> to
<var>B</var>, a priority-50 flow matches <code>ip &&
- ip4.dst == <var>B</var></code> with an action
+ ip4.dst == <var>B</var></code> or <code>ip &&
+ ip6.dst == <var>B</var></code> with an action
<code>REGBIT_NAT_REDIRECT = 1; next;</code>. This flow is for
- east/west traffic to a NAT destination IPv4 address. By
+ east/west traffic to a NAT destination IPv4/IPv6 address. By
setting the <code>REGBIT_NAT_REDIRECT</code> flag, in the
ingress table <code>Gateway Redirect</code> this will trigger a
redirect to the instance of the gateway port on the
@@ -2136,8 +2167,8 @@ logical_ip{0,1} = <var>LIP{0,1}</var>;
<pre>
eth.dst = <var>MAC0</var>;
eth.src = <var>MAC1</var>;
-reg0 = ip4.dst;
-reg1 = <var>EIP1</var>;
+reg0 = ip4.dst; /* xxreg0 = ip6.dst; in the IPv6 case */
+reg1 = <var>EIP1</var>; /* xxreg1 in the IPv6 case */
outport = <code>redirect-chassis-port</code>;
<code>REGBIT_DISTRIBUTED_NAT = 1; next;</code>.
</pre>
diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c
index 7cfeb60be..84b2a9ff1 100644
--- a/ovn/northd/ovn-northd.c
+++ b/ovn/northd/ovn-northd.c
@@ -66,6 +66,15 @@ struct northd_context {
struct ovsdb_idl_index *sbrec_ip_mcast_by_dp;
};
+/* An IPv4 or IPv6 address */
+struct v46_ip {
+ int family;
+ union {
+ ovs_be32 ipv4;
+ struct in6_addr ipv6;
+ };
+};
+
static const char *ovnnb_db;
static const char *ovnsb_db;
static const char *unixctl_path;
@@ -2266,6 +2275,15 @@ get_nat_addresses(const struct ovn_port *op, size_t *n)
break;
}
}
+ if (!is_router_ip) {
+ for (size_t j = 0; j < op->lrp_networks.n_ipv6_addrs; j++) {
+ if (!strcmp(nat->external_ip,
+ op->lrp_networks.ipv6_addrs[j].addr_s)) {
+ is_router_ip = true;
+ break;
+ }
+ }
+ }
if (!is_router_ip) {
ds_put_format(&c_addresses, " %s", nat->external_ip);
@@ -6013,9 +6031,28 @@ add_distributed_nat_routes(struct hmap *lflows, const struct ovn_port *op)
continue;
}
+ /* Determine if we need to create IPv4 or IPv6 flows */
+ ovs_be32 ip;
+ struct in6_addr ipv6;
+ int family = AF_INET;
+ if (!ip_parse(nat->external_ip, &ip) || !ip) {
+ family = AF_INET6;
+ if (!ipv6_parse(nat->external_ip, &ipv6)) {
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1);
+ VLOG_WARN_RL(&rl, "bad ip address %s in nat configuration "
+ "for router %s", nat->external_ip, op->key);
+ /* We'll create IPv6 flows anyway, but the address
+ * is probably bogus ... */
+ }
+ }
+
ds_put_format(&match, "inport == %s && "
- "ip4.src == %s && ip4.dst == %s",
- op->json_key, nat->logical_ip, nat->external_ip);
+ "ip%s.src == %s && ip%s.dst == %s",
+ op->json_key,
+ family == AF_INET ? "4" : "6",
+ nat->logical_ip,
+ family == AF_INET ? "4" : "6",
+ nat->external_ip);
ds_put_format(&actions, "outport = %s; eth.dst = %s; "
REGBIT_DISTRIBUTED_NAT" = 1; "
REGBIT_NAT_REDIRECT" = 0; next;",
@@ -6033,17 +6070,38 @@ add_distributed_nat_routes(struct hmap *lflows, const struct ovn_port *op)
!nat2->external_mac || !nat2->external_ip)
continue;
+ family = AF_INET;
+ if (!ip_parse(nat2->external_ip, &ip) || !ip) {
+ family = AF_INET6;
+ if (!ipv6_parse(nat2->external_ip, &ipv6)) {
+ static struct vlog_rate_limit rl =
+ VLOG_RATE_LIMIT_INIT(5, 1);
+ VLOG_WARN_RL(&rl, "bad ip address %s in nat configuration "
+ "for router %s", nat2->external_ip, op->key);
+ /* We'll create IPv6 flows anyway, but the address
+ * is probably bogus ... */
+ }
+ }
+
ds_put_format(&match, "inport == %s && "
- "ip4.src == %s && ip4.dst == %s",
- op->json_key, nat->logical_ip, nat2->external_ip);
+ "ip%s.src == %s && ip%s.dst == %s",
+ op->json_key,
+ family == AF_INET ? "4" : "6",
+ nat->logical_ip,
+ family == AF_INET ? "4" : "6",
+ nat2->external_ip);
ds_put_format(&actions, "outport = %s; "
"eth.src = %s; eth.dst = %s; "
- "reg0 = ip4.dst; reg1 = %s; "
+ "%sreg0 = ip%s.dst; %sreg1 = %s; "
REGBIT_DISTRIBUTED_NAT" = 1; "
REGBIT_NAT_REDIRECT" = 0; next;",
op->od->l3dgw_port->json_key,
op->od->l3dgw_port->lrp_networks.ea_s,
- nat2->external_mac, nat->external_ip);
+ nat2->external_mac,
+ family == AF_INET ? "" : "xx",
+ family == AF_INET ? "4" : "6",
+ family == AF_INET ? "" : "xx",
+ nat->external_ip);
ovn_lflow_add(lflows, op->od, S_ROUTER_IN_IP_ROUTING, 400,
ds_cstr(&match), ds_cstr(&actions));
ds_clear(&match);
@@ -6280,7 +6338,8 @@ op_put_v6_networks(struct ds *ds, const struct ovn_port *op)
}
static const char *
-get_force_snat_ip(struct ovn_datapath *od, const char *key_type, ovs_be32 *ip)
+get_force_snat_ip(struct ovn_datapath *od, const char *key_type,
+ struct v46_ip *ip)
{
char *key = xasprintf("%s_force_snat_ip", key_type);
const char *ip_address = smap_get(&od->nbr->options, key);
@@ -6288,19 +6347,27 @@ get_force_snat_ip(struct ovn_datapath *od, const char *key_type, ovs_be32 *ip)
if (ip_address) {
ovs_be32 mask;
- char *error = ip_parse_masked(ip_address, ip, &mask);
+ ip->family = AF_INET;
+ char *error = ip_parse_masked(ip_address, &ip->ipv4, &mask);
if (error || mask != OVS_BE32_MAX) {
- static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1);
- VLOG_WARN_RL(&rl, "bad ip %s in options of router "UUID_FMT"",
- ip_address, UUID_ARGS(&od->key));
free(error);
- *ip = 0;
- return NULL;
+ struct in6_addr mask_v6, v6_exact = IN6ADDR_EXACT_INIT;
+ ip->family = AF_INET6;
+ error = ipv6_parse_masked(ip_address, &ip->ipv6, &mask_v6);
+ if (error || memcmp(&mask_v6, &v6_exact, sizeof(mask_v6))) {
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1);
+ VLOG_WARN_RL(&rl, "bad ip %s in options of router "UUID_FMT"",
+ ip_address, UUID_ARGS(&od->key));
+ memset(ip, 0, sizeof *ip);
+ ip->family = AF_UNSPEC;
+ return NULL;
+ }
}
return ip_address;
}
- *ip = 0;
+ memset(ip, 0, sizeof *ip);
+ ip->family = AF_UNSPEC;
return NULL;
}
@@ -6866,11 +6933,11 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
/* A gateway router can have 2 SNAT IP addresses to force DNATed and
* LBed traffic respectively to be SNATed. In addition, there can be
* a number of SNAT rules in the NAT table. */
- ovs_be32 *snat_ips = xmalloc(sizeof *snat_ips *
- (op->od->nbr->n_nat + 2));
+ struct v46_ip *snat_ips = xmalloc(sizeof *snat_ips
+ * (op->od->nbr->n_nat + 2));
size_t n_snat_ips = 0;
- ovs_be32 snat_ip;
+ struct v46_ip snat_ip;
const char *dnat_force_snat_ip = get_force_snat_ip(op->od, "dnat",
&snat_ip);
if (dnat_force_snat_ip) {
@@ -6889,44 +6956,85 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
nat = op->od->nbr->nat[i];
ovs_be32 ip;
+ struct in6_addr ipv6;
+ bool is_v6 = false;
if (!ip_parse(nat->external_ip, &ip) || !ip) {
- static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1);
- VLOG_WARN_RL(&rl, "bad ip address %s in nat configuration "
- "for router %s", nat->external_ip, op->key);
- continue;
+ if (!ipv6_parse(nat->external_ip, &ipv6)) {
+ static struct vlog_rate_limit rl =
+ VLOG_RATE_LIMIT_INIT(5, 1);
+ VLOG_WARN_RL(&rl, "bad ip address %s in nat configuration "
+ "for router %s", nat->external_ip, op->key);
+ continue;
+ }
+ is_v6 = true;
}
if (!strcmp(nat->type, "snat")) {
- snat_ips[n_snat_ips++] = ip;
+ if (is_v6) {
+ snat_ips[n_snat_ips].family = AF_INET6;
+ snat_ips[n_snat_ips++].ipv6 = ipv6;
+ } else {
+ snat_ips[n_snat_ips].family = AF_INET;
+ snat_ips[n_snat_ips++].ipv4 = ip;
+ }
continue;
}
- /* ARP handling for external IP addresses.
+ /* ARP / ND handling for external IP addresses.
*
* DNAT IP addresses are external IP addresses that need ARP
* handling. */
+ char addr_s[INET6_ADDRSTRLEN + 1];
ds_clear(&match);
- ds_put_format(&match,
- "inport == %s && arp.tpa == "IP_FMT" && arp.op == 1",
- op->json_key, IP_ARGS(ip));
-
ds_clear(&actions);
- ds_put_format(&actions,
- "eth.dst = eth.src; "
- "arp.op = 2; /* ARP reply */ "
- "arp.tha = arp.sha; ");
+ if (is_v6) {
+ /* 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. */
+ char sn_addr_s[INET6_ADDRSTRLEN + 1];
+ struct in6_addr sn_addr;
+ in6_addr_solicited_node(&sn_addr, &ipv6);
+ ipv6_string_mapped(sn_addr_s, &sn_addr);
+ ipv6_string_mapped(addr_s, &ipv6);
+
+ ds_put_format(&match, "inport == %s && "
+ "nd_ns && ip6.dst == {%s, %s} && nd.target == %s",
+ op->json_key, addr_s, sn_addr_s, addr_s);
+ ds_put_format(&actions,
+ "eth.dst = eth.src; "
+ "nd_na { ");
+ } else {
+ ds_put_format(&match,
+ "inport == %s "
+ "&& arp.tpa == "IP_FMT" && arp.op == 1",
+ op->json_key, IP_ARGS(ip));
+
+ ds_put_format(&actions,
+ "eth.dst = eth.src; "
+ "arp.op = 2; /* ARP reply */ "
+ "arp.tha = arp.sha; ");
+ }
if (op->od->l3dgw_port && op == op->od->l3dgw_port) {
struct eth_addr mac;
if (nat->external_mac &&
eth_addr_from_string(nat->external_mac, &mac)
&& nat->logical_port) {
/* distributed NAT case, use nat->external_mac */
- ds_put_format(&actions,
- "eth.src = "ETH_ADDR_FMT"; "
- "arp.sha = "ETH_ADDR_FMT"; ",
- ETH_ADDR_ARGS(mac),
- ETH_ADDR_ARGS(mac));
+ if (is_v6) {
+ ds_put_format(&actions,
+ "eth.src = "ETH_ADDR_FMT"; "
+ "nd.tll = "ETH_ADDR_FMT"; ",
+ ETH_ADDR_ARGS(mac),
+ ETH_ADDR_ARGS(mac));
+
+ } else {
+ ds_put_format(&actions,
+ "eth.src = "ETH_ADDR_FMT"; "
+ "arp.sha = "ETH_ADDR_FMT"; ",
+ ETH_ADDR_ARGS(mac),
+ ETH_ADDR_ARGS(mac));
+ }
/* Traffic with eth.src = nat->external_mac should only be
* sent from the chassis where nat->logical_port is
* resident, so that upstream MAC learning points to the
@@ -6935,11 +7043,20 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
ds_put_format(&match, " && is_chassis_resident(\"%s\")",
nat->logical_port);
} else {
- ds_put_format(&actions,
- "eth.src = %s; "
- "arp.sha = %s; ",
- op->lrp_networks.ea_s,
- op->lrp_networks.ea_s);
+ if (is_v6) {
+ ds_put_format(&actions,
+ "eth.src = %s; "
+ "nd.tll = %s; ",
+ op->lrp_networks.ea_s,
+ op->lrp_networks.ea_s);
+
+ } else {
+ ds_put_format(&actions,
+ "eth.src = %s; "
+ "arp.sha = %s; ",
+ op->lrp_networks.ea_s,
+ op->lrp_networks.ea_s);
+ }
/* Traffic with eth.src = l3dgw_port->lrp_networks.ea_s
* should only be sent from the "redirect-chassis", so that
* upstream MAC learning points to the "redirect-chassis".
@@ -6950,21 +7067,40 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
op->od->l3redirect_port->json_key);
}
}
+ } else {
+ if (is_v6) {
+ ds_put_format(&actions,
+ "eth.src = %s; "
+ "nd.tll = %s; ",
+ op->lrp_networks.ea_s,
+ op->lrp_networks.ea_s);
+ } else {
+ ds_put_format(&actions,
+ "eth.src = %s; "
+ "arp.sha = %s; ",
+ op->lrp_networks.ea_s,
+ op->lrp_networks.ea_s);
+ }
+ }
+ if (is_v6) {
+ ds_put_format(&actions,
+ "ip6.src = %s; "
+ "nd.target = %s; "
+ "outport = %s; "
+ "flags.loopback = 1; "
+ "output; "
+ "};",
+ addr_s, addr_s, op->json_key);
} else {
ds_put_format(&actions,
- "eth.src = %s; "
- "arp.sha = %s; ",
- op->lrp_networks.ea_s,
- op->lrp_networks.ea_s);
+ "arp.tpa = arp.spa; "
+ "arp.spa = "IP_FMT"; "
+ "outport = %s; "
+ "flags.loopback = 1; "
+ "output;",
+ IP_ARGS(ip),
+ op->json_key);
}
- ds_put_format(&actions,
- "arp.tpa = arp.spa; "
- "arp.spa = "IP_FMT"; "
- "outport = %s; "
- "flags.loopback = 1; "
- "output;",
- IP_ARGS(ip),
- op->json_key);
ovn_lflow_add(lflows, op->od, S_ROUTER_IN_IP_INPUT, 90,
ds_cstr(&match), ds_cstr(&actions));
}
@@ -7021,7 +7157,36 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
bool snat_ip_is_router_ip = false;
for (int j = 0; j < n_snat_ips; j++) {
/* Packets to SNAT IPs should not be dropped. */
- if (op->lrp_networks.ipv4_addrs[i].addr == snat_ips[j]) {
+ if (snat_ips[j].family == AF_INET
+ && op->lrp_networks.ipv4_addrs[i].addr
+ == snat_ips[j].ipv4) {
+ snat_ip_is_router_ip = true;
+ break;
+ }
+ }
+ if (snat_ip_is_router_ip) {
+ continue;
+ }
+ ds_put_format(&match, "%s, ",
+ op->lrp_networks.ipv4_addrs[i].addr_s);
+ has_drop_ips = true;
+ }
+ if (has_drop_ips) {
+ ds_chomp(&match, ' ');
+ ds_chomp(&match, ',');
+ ds_put_cstr(&match, "} || ip6.dst == {");
+ } else {
+ ds_clear(&match);
+ ds_put_cstr(&match, "ip6.dst == {");
+ }
+
+ for (int i = 0; i < op->lrp_networks.n_ipv6_addrs; i++) {
+ bool snat_ip_is_router_ip = false;
+ for (int j = 0; j < n_snat_ips; j++) {
+ /* Packets to SNAT IPs should not be dropped. */
+ if (snat_ips[j].family == AF_INET6
+ && !memcmp(&op->lrp_networks.ipv6_addrs[i].addr,
+ &snat_ips[j].ipv6, sizeof snat_ips[j].ipv6)) {
snat_ip_is_router_ip = true;
break;
}
@@ -7030,9 +7195,10 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
continue;
}
ds_put_format(&match, "%s, ",
- op->lrp_networks.ipv4_addrs[i].addr_s);
+ op->lrp_networks.ipv6_addrs[i].addr_s);
has_drop_ips = true;
}
+
ds_chomp(&match, ' ');
ds_chomp(&match, ',');
ds_put_cstr(&match, "}");
@@ -7059,14 +7225,6 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
}
if (op->lrp_networks.n_ipv6_addrs) {
- /* L3 admission control: drop packets that originate from an
- * IPv6 address owned by the router (priority 100). */
- ds_clear(&match);
- ds_put_cstr(&match, "ip6.src == ");
- op_put_v6_networks(&match, op);
- ovn_lflow_add(lflows, op->od, S_ROUTER_IN_IP_INPUT, 100,
- ds_cstr(&match), "drop;");
-
/* ICMPv6 echo reply. These flows reply to echo requests
* received for the router's IP address. */
ds_clear(&match);
@@ -7083,13 +7241,6 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
"next; ");
ovn_lflow_add(lflows, op->od, S_ROUTER_IN_IP_INPUT, 90,
ds_cstr(&match), ds_cstr(&actions));
-
- /* Drop IPv6 traffic to this router. */
- ds_clear(&match);
- ds_put_cstr(&match, "ip6.dst == ");
- op_put_v6_networks(&match, op);
- ovn_lflow_add(lflows, op->od, S_ROUTER_IN_IP_INPUT, 60,
- ds_cstr(&match), "drop;");
}
/* ND reply. These flows reply to ND solicitations for the
@@ -7231,11 +7382,11 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
continue;
}
- ovs_be32 snat_ip;
+ struct v46_ip snat_ip, lb_snat_ip;
const char *dnat_force_snat_ip = get_force_snat_ip(od, "dnat",
&snat_ip);
const char *lb_force_snat_ip = get_force_snat_ip(od, "lb",
- &snat_ip);
+ &lb_snat_ip);
for (int i = 0; i < od->nbr->n_nat; i++) {
const struct nbrec_nat *nat;
@@ -7243,21 +7394,38 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
nat = od->nbr->nat[i];
ovs_be32 ip, mask;
+ struct in6_addr ipv6, mask_v6, v6_exact = IN6ADDR_EXACT_INIT;
+ bool is_v6 = false;
char *error = ip_parse_masked(nat->external_ip, &ip, &mask);
if (error || mask != OVS_BE32_MAX) {
- static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 1);
- VLOG_WARN_RL(&rl, "bad external ip %s for nat",
- nat->external_ip);
free(error);
- continue;
+ error = ipv6_parse_masked(nat->external_ip, &ipv6, &mask_v6);
+ if (error || memcmp(&mask_v6, &v6_exact, sizeof(mask_v6))) {
+ /* Invalid for both IPv4 and IPv6 */
+ static struct vlog_rate_limit rl =
+ VLOG_RATE_LIMIT_INIT(5, 1);
+ VLOG_WARN_RL(&rl, "bad external ip %s for nat",
+ nat->external_ip);
+ free(error);
+ continue;
+ }
+ /* It was an invalid IPv4 address, but valid IPv6.
+ * Treat the rest of the handling of this NAT rule
+ * as IPv6. */
+ is_v6 = true;
}
/* Check the validity of nat->logical_ip. 'logical_ip' can
* be a subnet when the type is "snat". */
- error = ip_parse_masked(nat->logical_ip, &ip, &mask);
+ if (is_v6) {
+ error = ipv6_parse_masked(nat->external_ip, &ipv6, &mask_v6);
+ } else {
+ error = ip_parse_masked(nat->logical_ip, &ip, &mask);
+ }
if (!strcmp(nat->type, "snat")) {
if (error) {
+ /* Invalid for both IPv4 and IPv6 */
static struct vlog_rate_limit rl =
VLOG_RATE_LIMIT_INIT(5, 1);
VLOG_WARN_RL(&rl, "bad ip network or ip %s for snat "
@@ -7267,7 +7435,10 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
continue;
}
} else {
- if (error || mask != OVS_BE32_MAX) {
+ if (error || (!is_v6 && mask != OVS_BE32_MAX)
+ || (is_v6 && memcmp(&mask_v6, &v6_exact,
+ sizeof mask_v6))) {
+ /* Invalid for both IPv4 and IPv6 */
static struct vlog_rate_limit rl =
VLOG_RATE_LIMIT_INIT(5, 1);
VLOG_WARN_RL(&rl, "bad ip %s for dnat in router "
@@ -7308,7 +7479,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
if (!od->l3dgw_port) {
/* Gateway router. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s",
+ ds_put_format(&match, "ip && ip%s.dst == %s",
+ is_v6 ? "6" : "4",
nat->external_ip);
ovn_lflow_add(lflows, od, S_ROUTER_IN_UNSNAT, 90,
ds_cstr(&match), "ct_snat;");
@@ -7317,8 +7489,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
/* Traffic received on l3dgw_port is subject to NAT. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s"
+ ds_put_format(&match, "ip && ip%s.dst == %s"
" && inport == %s",
+ is_v6 ? "6" : "4",
nat->external_ip,
od->l3dgw_port->json_key);
if (!distributed && od->l3redirect_port) {
@@ -7334,7 +7507,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* redirected to the central instance of the l3dgw_port
* for NAT processing. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s",
+ ds_put_format(&match, "ip && ip%s.dst == %s",
+ is_v6 ? "6" : "4",
nat->external_ip);
ovn_lflow_add(lflows, od, S_ROUTER_IN_UNSNAT, 50,
ds_cstr(&match),
@@ -7353,7 +7527,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* We need to set flags.loopback because the router can
* send the packet back through the same interface. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s",
+ ds_put_format(&match, "ip && ip%s.dst == %s",
+ is_v6 ? "6" : "4",
nat->external_ip);
ds_clear(&actions);
if (dnat_force_snat_ip) {
@@ -7372,8 +7547,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
/* Traffic received on l3dgw_port is subject to NAT. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s"
+ ds_put_format(&match, "ip && ip%s.dst == %s"
" && inport == %s",
+ is_v6 ? "6" : "4",
nat->external_ip,
od->l3dgw_port->json_key);
if (!distributed && od->l3redirect_port) {
@@ -7392,7 +7568,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* redirected to the central instance of the l3dgw_port
* for NAT processing. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s",
+ ds_put_format(&match, "ip && ip%s.dst == %s",
+ is_v6 ? "6" : "4",
nat->external_ip);
ovn_lflow_add(lflows, od, S_ROUTER_IN_DNAT, 50,
ds_cstr(&match),
@@ -7411,8 +7588,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
if (od->l3dgw_port && (!strcmp(nat->type, "dnat")
|| !strcmp(nat->type, "dnat_and_snat"))) {
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.src == %s"
+ ds_put_format(&match, "ip && ip%s.src == %s"
" && outport == %s",
+ is_v6 ? "6" : "4",
nat->logical_ip,
od->l3dgw_port->json_key);
if (!distributed && od->l3redirect_port) {
@@ -7439,7 +7617,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
if (!od->l3dgw_port) {
/* Gateway router. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.src == %s",
+ ds_put_format(&match, "ip && ip%s.src == %s",
+ is_v6 ? "6" : "4",
nat->logical_ip);
ds_clear(&actions);
ds_put_format(&actions, "ct_snat(%s);", nat->external_ip);
@@ -7455,8 +7634,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
/* Distributed router. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.src == %s"
+ ds_put_format(&match, "ip && ip%s.src == %s"
" && outport == %s",
+ is_v6 ? "6" : "4",
nat->logical_ip,
od->l3dgw_port->json_key);
if (!distributed && od->l3redirect_port) {
@@ -7505,7 +7685,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* can be applied in a distributed manner. */
if (distributed) {
ds_clear(&match);
- ds_put_format(&match, "ip4.src == %s && outport == %s",
+ ds_put_format(&match, "ip%s.src == %s && outport == %s",
+ is_v6 ? "6" : "4",
nat->logical_ip,
od->l3dgw_port->json_key);
ovn_lflow_add(lflows, od, S_ROUTER_IN_GW_REDIRECT, 100,
@@ -7532,9 +7713,10 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
ds_clear(&match);
ds_put_format(&match, "is_chassis_resident(\"%s\") && "
- "ip4.src == %s && ip4.dst == %s",
- nat->logical_port, nat2->external_ip,
- nat->external_ip);
+ "ip%s.src == %s && ip%s.dst == %s",
+ nat->logical_port,
+ is_v6 ? "6" : "4", nat2->external_ip,
+ is_v6 ? "6" : "4", nat->external_ip);
ds_clear(&actions);
ds_put_format(&actions,
"inport = outport; outport = \"\"; "
@@ -7546,8 +7728,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
ds_clear(&match);
ds_put_format(&match,
- "ip4.src == %s && ip4.dst == %s",
- nat2->external_ip, nat->external_ip);
+ "ip%s.src == %s && ip%s.dst == %s",
+ is_v6 ? "6" : "4", nat2->external_ip,
+ is_v6 ? "6" : "4", nat->external_ip);
ovn_lflow_add(lflows, od, S_ROUTER_OUT_EGR_LOOP, 200,
ds_cstr(&match), "next;");
ds_clear(&match);
@@ -7555,7 +7738,8 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
}
ds_clear(&match);
- ds_put_format(&match, "ip4.dst == %s && outport == %s",
+ ds_put_format(&match, "ip%s.dst == %s && outport == %s",
+ is_v6 ? "6" : "4",
nat->external_ip,
od->l3dgw_port->json_key);
ds_clear(&actions);
@@ -7579,7 +7763,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* gateway router (as set in options:dnat_force_snat_ip) is seen,
* UNSNAT it. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s", dnat_force_snat_ip);
+ ds_put_format(&match, "ip && ip%s.dst == %s",
+ snat_ip.family == AF_INET ? "4" : "6",
+ dnat_force_snat_ip);
ovn_lflow_add(lflows, od, S_ROUTER_IN_UNSNAT, 110,
ds_cstr(&match), "ct_snat;");
@@ -7598,7 +7784,9 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
* gateway router (as set in options:lb_force_snat_ip) is seen,
* UNSNAT it. */
ds_clear(&match);
- ds_put_format(&match, "ip && ip4.dst == %s", lb_force_snat_ip);
+ ds_put_format(&match, "ip && ip%s.dst == %s",
+ lb_snat_ip.family == AF_INET ? "4" : "6",
+ lb_force_snat_ip);
ovn_lflow_add(lflows, od, S_ROUTER_IN_UNSNAT, 100,
ds_cstr(&match), "ct_snat;");
@@ -7700,7 +7888,7 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
if (addr_family == AF_INET) {
ds_put_format(&match, "ip && ip4.dst == %s",
ip_address);
- } else {
+ } else if (addr_family == AF_INET6) {
ds_put_format(&match, "ip && ip6.dst == %s",
ip_address);
}
@@ -7720,7 +7908,7 @@ build_lrouter_flows(struct hmap *datapaths, struct hmap *ports,
if (addr_family == AF_INET) {
ds_put_format(&match, "ip && ip4.dst == %s",
ip_address);
- } else {
+ } else if (addr_family == AF_INET6) {
ds_put_format(&match, "ip && ip6.dst == %s",
ip_address);
}
--
2.23.0