[PATCH 4/7] netlink, pasta: Disable DAD for link-local addresses on namespace interface

[Stefano Brivio <sbrivio@redhat.com>]

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.

A large part of the function setting the nodad attribute is copied^W
vendored from nl_routes_dup(), and we could probably refactor things
to avoid code duplication, eventually, but keep this simple for the
moment.

Link: https://github.com/containers/podman/pull/23561#discussion_r1711639663
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 netlink.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 netlink.h |  1 +
 pasta.c   |  6 ++++
 3 files changed, 104 insertions(+)

diff --git a/netlink.c b/netlink.c
index 873e6c7..4b49de1 100644
--- a/netlink.c
+++ b/netlink.c
@@ -673,6 +673,103 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 	return 0;
 }
 
+/**
+ * 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,
+	};
+	ssize_t nlmsgs_size, left, status;
+	unsigned ll_addrs = 0;
+	struct nlmsghdr *nh;
+	char buf[NLBUFSIZ];
+	uint32_t seq;
+	unsigned i;
+
+	seq = nl_send(s, &req, RTM_GETADDR, NLM_F_DUMP, sizeof(req));
+
+	/* nl_foreach() will step through multiple response datagrams,
+	 * which we don't want here because we need to have all the
+	 * addresses in the buffer at once. See also nl_route_dup().
+	 */
+	nh = nl_next(s, buf, NULL, &nlmsgs_size);
+	for (left = nlmsgs_size;
+	     NLMSG_OK(nh, left) && (status = nl_status(nh, left, seq)) > 0;
+	     nh = NLMSG_NEXT(nh, left)) {
+		struct ifaddrmsg *ifa = (struct ifaddrmsg *)NLMSG_DATA(nh);
+		bool discard = false;
+		struct rtattr *rta;
+		size_t na;
+
+		if (nh->nlmsg_type != RTM_NEWADDR)
+			continue;
+
+		if (ifa->ifa_index != ifi || ifa->ifa_scope != RT_SCOPE_LINK)
+			discard = true;
+
+		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;
+		}
+
+		if (discard)
+			nh->nlmsg_type = NLMSG_NOOP;
+		else
+			ll_addrs++;
+	}
+
+	if (!NLMSG_OK(nh, left)) {
+		/* Process any remaining datagrams in a different
+		 * buffer so we don't overwrite the first one.
+		 */
+		char tail[NLBUFSIZ];
+		unsigned extra = 0;
+
+		nl_foreach_oftype(nh, status, s, tail, seq, RTM_NEWADDR)
+			extra++;
+
+		if (extra) {
+			err("netlink: Too many link-local addresses");
+			return -E2BIG;
+		}
+	}
+
+	if (status < 0)
+		return status;
+
+	for (i = 0; i < ll_addrs; i++) {
+		for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
+		     NLMSG_OK(nh, left);
+		     nh = NLMSG_NEXT(nh, left)) {
+			int rc;
+
+			if (nh->nlmsg_type != RTM_NEWADDR)
+				continue;
+
+			rc = nl_do(s, nh, RTM_NEWADDR, NLM_F_REPLACE,
+				nh->nlmsg_len);
+			if (rc < 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * nl_addr_get() - Get most specific global address, given interface and family
  * @s:		Netlink socket
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..838bbb3 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) {
+				die("Can't disable DAD 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);
-- 
@@ -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) {
+				die("Can't disable DAD 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);
-- 
2.43.0