On Fri, Aug 16, 2024 at 09:39:15AM +0200, Stefano Brivio wrote:
> 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>
> ---
>  netlink.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  netlink.h |  1 +
>  pasta.c   |  6 ++++++
>  3 files changed, 62 insertions(+)
> 
> diff --git a/netlink.c b/netlink.c
> index 873e6c7..59f2fd9 100644
> --- a/netlink.c
> +++ b/netlink.c
> @@ -673,6 +673,61 @@ 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,
> +	};
> +	unsigned ll_addrs = 0;
> +	struct nlmsghdr *nh;
> +	char buf[NLBUFSIZ];
> +	ssize_t status;
> +	uint32_t seq;
> +
> +	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;
> +		}
> +
> +		nl_send(s, nh, RTM_NEWADDR, NLM_F_REPLACE, nh->nlmsg_len);
> +		ll_addrs++;
> +	}

Uh.. did you forget to push an update.  This looks like the last
version.

> +	if (status < 0)
> +		return status;

You still have this early return.

> +
> +	seq += ll_addrs;
> +
> +	nl_foreach(nh, status, s, buf, seq)
> +		warn("netlink: Unexpected response message");

And you need an outer loop over this nl_foreach() for each value of
seq from the one from the RTM_GETADDR to the last one from
NLM_F_REPLACE.

> +
> +	return status;
> +}
> +
>  /**
>   * 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..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);

-- 
David Gibson (he or they)	| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you, not the other way
				| around.
http://www.ozlabs.org/~dgibson