xfrm: lwtunnel: add lwtunnel support for xfrm interfaces in collect_md mode

Allow specifying the xfrm interface if_id and link as part of a route
metadata using the lwtunnel infrastructure.

This allows for example using a single xfrm interface in collect_md
mode as the target of multiple routes each specifying a different if_id.

With the appropriate changes to iproute2, considering an xfrm device
ipsec1 in collect_md mode one can for example add a route specifying
an if_id like so:

ip route add <SUBNET> dev ipsec1 encap xfrm if_id 1

In which case traffic routed to the device via this route would use
if_id in the xfrm interface policy lookup.

Or in the context of vrf, one can also specify the "link" property:

ip route add <SUBNET> dev ipsec1 encap xfrm if_id 1 link_dev eth15

Note: LWT_XFRM_LINK uses NLA_U32 similar to IFLA_XFRM_LINK even though
internally "link" is signed. This is consistent with other _LINK
attributes in other devices as well as in bpf and should not have an
effect as device indexes can't be negative.

Reviewed-by: Nicolas Dichtel <[e-mail]>
Reviewed-by: Nikolay Aleksandrov <[e-mail]>
Signed-off-by: Eyal Birger <[e-mail]>
Signed-off-by: Steffen Klassert <[e-mail]>

include/net/dst_metadata.h

···
 	return NULL;
 }
 
+static inline struct xfrm_md_info *lwt_xfrm_info(struct lwtunnel_state *lwt)
+{
+	return (struct xfrm_md_info *)lwt->data;
+}
+
 static inline struct xfrm_md_info *skb_xfrm_md_info(const struct sk_buff *skb)
 {
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
+	struct dst_entry *dst;
 
 	if (md_dst && md_dst->type == METADATA_XFRM)
 		return &md_dst->u.xfrm_info;
+
+	dst = skb_dst(skb);
+	if (dst && dst->lwtstate &&
+	    dst->lwtstate->type == LWTUNNEL_ENCAP_XFRM)
+		return lwt_xfrm_info(dst->lwtstate);
 
 	return NULL;
 }

include/uapi/linux/lwtunnel.h

···
 	LWTUNNEL_ENCAP_SEG6_LOCAL,
 	LWTUNNEL_ENCAP_RPL,
 	LWTUNNEL_ENCAP_IOAM6,
+	LWTUNNEL_ENCAP_XFRM,
 	__LWTUNNEL_ENCAP_MAX,
 };
 
···
 #define LWT_BPF_MAX (__LWT_BPF_MAX - 1)
 
 #define LWT_BPF_MAX_HEADROOM 256
+
+enum {
+	LWT_XFRM_UNSPEC,
+	LWT_XFRM_IF_ID,
+	LWT_XFRM_LINK,
+	__LWT_XFRM_MAX,
+};
+
+#define LWT_XFRM_MAX (__LWT_XFRM_MAX - 1)
 
 #endif /* _UAPI_LWTUNNEL_H_ */

net/core/lwtunnel.c

···
 		return "IOAM6";
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
+	case LWTUNNEL_ENCAP_XFRM:
 	case LWTUNNEL_ENCAP_NONE:
 	case __LWTUNNEL_ENCAP_MAX:
 		/* should not have got here */

net/xfrm/xfrm_interface.c

···
 	struct xfrm_if __rcu *collect_md_xfrmi;
 };
 
+static const struct nla_policy xfrm_lwt_policy[LWT_XFRM_MAX + 1] = {
+	[LWT_XFRM_IF_ID]	= NLA_POLICY_MIN(NLA_U32, 1),
+	[LWT_XFRM_LINK]		= NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+static void xfrmi_destroy_state(struct lwtunnel_state *lwt)
+{
+}
+
+static int xfrmi_build_state(struct net *net, struct nlattr *nla,
+			     unsigned int family, const void *cfg,
+			     struct lwtunnel_state **ts,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[LWT_XFRM_MAX + 1];
+	struct lwtunnel_state *new_state;
+	struct xfrm_md_info *info;
+	int ret;
+
+	ret = nla_parse_nested(tb, LWT_XFRM_MAX, nla, xfrm_lwt_policy, extack);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[LWT_XFRM_IF_ID]) {
+		NL_SET_ERR_MSG(extack, "if_id must be set");
+		return -EINVAL;
+	}
+
+	new_state = lwtunnel_state_alloc(sizeof(*info));
+	if (!new_state) {
+		NL_SET_ERR_MSG(extack, "failed to create encap info");
+		return -ENOMEM;
+	}
+
+	new_state->type = LWTUNNEL_ENCAP_XFRM;
+
+	info = lwt_xfrm_info(new_state);
+
+	info->if_id = nla_get_u32(tb[LWT_XFRM_IF_ID]);
+
+	if (tb[LWT_XFRM_LINK])
+		info->link = nla_get_u32(tb[LWT_XFRM_LINK]);
+
+	*ts = new_state;
+	return 0;
+}
+
+static int xfrmi_fill_encap_info(struct sk_buff *skb,
+				 struct lwtunnel_state *lwt)
+{
+	struct xfrm_md_info *info = lwt_xfrm_info(lwt);
+
+	if (nla_put_u32(skb, LWT_XFRM_IF_ID, info->if_id) ||
+	    (info->link && nla_put_u32(skb, LWT_XFRM_LINK, info->link)))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int xfrmi_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+	return nla_total_size(sizeof(u32)) + /* LWT_XFRM_IF_ID */
+		nla_total_size(sizeof(u32)); /* LWT_XFRM_LINK */
+}
+
+static int xfrmi_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+	struct xfrm_md_info *a_info = lwt_xfrm_info(a);
+	struct xfrm_md_info *b_info = lwt_xfrm_info(b);
+
+	return memcmp(a_info, b_info, sizeof(*a_info));
+}
+
+static const struct lwtunnel_encap_ops xfrmi_encap_ops = {
+	.build_state	= xfrmi_build_state,
+	.destroy_state	= xfrmi_destroy_state,
+	.fill_encap	= xfrmi_fill_encap_info,
+	.get_encap_size = xfrmi_encap_nlsize,
+	.cmp_encap	= xfrmi_encap_cmp,
+	.owner		= THIS_MODULE,
+};
+
 #define for_each_xfrmi_rcu(start, xi) \
 	for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next))
 
···
 	if (err < 0)
 		goto rtnl_link_failed;
 
+	lwtunnel_encap_add_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM);
+
 	xfrm_if_register_cb(&xfrm_if_cb);
 
 	return err;
···
 static void __exit xfrmi_fini(void)
 {
 	xfrm_if_unregister_cb();
+	lwtunnel_encap_del_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM);
 	rtnl_link_unregister(&xfrmi_link_ops);
 	xfrmi4_fini();
 	xfrmi6_fini();