netlink, pasta: Disable DAD for link-local addresses on namespace interface

It makes no sense for a container or a guest to try and perform
duplicate address detection for their link-local address, as we'll
anyway not relay neighbour solicitations with an unspecified source
address.

While they perform duplicate address detection, the link-local address
is not usable, which prevents us from bringing up especially
containers and communicate with them right away via IPv6.

This is not enough to prevent DAD and reach the container right away:
we'll need a couple more patches.

As we send NLM_F_REPLACE requests right away, while we still have to
read out other addresses on the same socket, we can't use nl_do():
keep track of the last sequence we sent (last address we changed), and
deal with the answers to those NLM_F_REPLACE requests in a separate
loop, later.

Link: https://github.com/containers/podman/pull/23561#discussion_r1711639663
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

3 files changed, 64 insertions, 0 deletions

diff --git a/netlink.c b/netlink.c
index 873e6c7..5a5af14 100644
--- a/netlink.c
+++ b/netlink.c
@@ -674,6 +674,63 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 }
 
 /**
+ * nl_addr_set_ll_nodad() - Set IFA_F_NODAD on IPv6 link-local addresses
+ * @s:		Netlink socket
+ * @ifi:	Interface index in target namespace
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+int nl_addr_set_ll_nodad(int s, unsigned int ifi)
+{
+	struct req_t {
+		struct nlmsghdr nlh;
+		struct ifaddrmsg ifa;
+	} req = {
+		.ifa.ifa_family    = AF_INET6,
+		.ifa.ifa_index     = ifi,
+	};
+	uint32_t seq, last_seq = 0;
+	ssize_t status, ret = 0;
+	struct nlmsghdr *nh;
+	char buf[NLBUFSIZ];
+
+	seq = nl_send(s, &req, RTM_GETADDR, NLM_F_DUMP, sizeof(req));
+	nl_foreach_oftype(nh, status, s, buf, seq, RTM_NEWADDR) {
+		struct ifaddrmsg *ifa = (struct ifaddrmsg *)NLMSG_DATA(nh);
+		struct rtattr *rta;
+		size_t na;
+
+		if (ifa->ifa_index != ifi || ifa->ifa_scope != RT_SCOPE_LINK)
+			continue;
+
+		ifa->ifa_flags |= IFA_F_NODAD;
+
+		for (rta = IFA_RTA(ifa), na = IFA_PAYLOAD(nh); RTA_OK(rta, na);
+		     rta = RTA_NEXT(rta, na)) {
+			/* If 32-bit flags are used, add IFA_F_NODAD there */
+			if (rta->rta_type == IFA_FLAGS)
+				*(uint32_t *)RTA_DATA(rta) |= IFA_F_NODAD;
+		}
+
+		last_seq = nl_send(s, nh, RTM_NEWADDR, NLM_F_REPLACE,
+				   nh->nlmsg_len);
+	}
+
+	if (status < 0)
+		ret = status;
+
+	for (seq = seq + 1; seq <= last_seq; seq++) {
+		nl_foreach(nh, status, s, buf, seq)
+			warn("netlink: Unexpected response message");
+
+		if (!ret && status < 0)
+			ret = status;
+	}
+
+	return ret;
+}
+
+/**
  * nl_addr_get() - Get most specific global address, given interface and family
  * @s:		Netlink socket
  * @ifi:	Interface index in outer network namespace
diff --git a/netlink.h b/netlink.h
index 178f8ae..66a44ad 100644
--- a/netlink.h
+++ b/netlink.h
@@ -19,6 +19,7 @@ int nl_addr_get(int s, unsigned int ifi, sa_family_t af,
 		void *addr, int *prefix_len, void *addr_l);
 int nl_addr_set(int s, unsigned int ifi, sa_family_t af,
 		const void *addr, int prefix_len);
+int nl_addr_set_ll_nodad(int s, unsigned int ifi);
 int nl_addr_dup(int s_src, unsigned int ifi_src,
 		int s_dst, unsigned int ifi_dst, sa_family_t af);
 int nl_link_get_mac(int s, unsigned int ifi, void *mac);
diff --git a/pasta.c b/pasta.c
index 96545b1..17eed15 100644
--- a/pasta.c
+++ b/pasta.c
@@ -340,6 +340,12 @@ void pasta_ns_conf(struct ctx *c)
 		}
 
 		if (c->ifi6) {
+			rc = nl_addr_set_ll_nodad(nl_sock_ns, c->pasta_ifi);
+			if (rc < 0) {
+				warn("Can't set nodad for LL in namespace: %s",
+				    strerror(-rc));
+			}
+
 			if (c->ip6.no_copy_addrs) {
 				rc = nl_addr_set(nl_sock_ns, c->pasta_ifi,
 						 AF_INET6, &c->ip6.addr, 64);