[PATCH RFC net-next 16/18] net/ipv6: Allow routes to use nexthop objects

[dsahern@kernel.org]

From: David Ahern <dsahern@gmail.com>

Allow users to specify a nexthop id to use with a route.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/net/ip6_fib.h |  4 +++
 include/net/nexthop.h |  3 ++
 net/ipv4/nexthop.c    |  5 +++
 net/ipv6/addrconf.c   |  3 ++
 net/ipv6/ip6_fib.c    | 17 ++++++++---
 net/ipv6/ndisc.c      |  2 ++
 net/ipv6/route.c      | 85 +++++++++++++++++++++++++++++++++++++++++----------
 7 files changed, 98 insertions(+), 21 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1f04a26e4c65..170aadcd83b4 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -52,6 +52,7 @@ struct fib6_config {
 	u16		fc_type;        /* only 8 bits are used */
 	u16		fc_delete_all_nh : 1,
 			__unused : 15;
+	u32		fc_nh_id;
 
 	struct in6_addr	fc_dst;
 	struct in6_addr	fc_src;
@@ -139,6 +140,8 @@ struct fib6_info {
 	struct fib6_info __rcu		*fib6_next;
 	struct fib6_node __rcu		*fib6_node;
 
+	struct list_head		nh_list;
+
 	/* Multipath routes:
 	 * siblings is a list of fib6_info that have the the same metric/weight,
 	 * destination, but not the same gateway. nsiblings is just a cache
@@ -171,6 +174,7 @@ struct fib6_info {
 					unused:3;
 
 	struct rcu_head			rcu;
+	struct nexthop			*nh;
 	struct fib6_nh			fib6_nh[0];
 };
 
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index dae1518af3f3..759bb39e4ea7 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -175,6 +175,9 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
 
 static inline struct fib6_nh *fib6_info_nh(struct fib6_info *f6i)
 {
+	if (f6i->nh)
+		return nexthop_fib6_nh(f6i->nh);
+
 	return f6i->fib6_nh;
 }
 
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d1fc3d21af86..1e77fa94e562 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -317,6 +317,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info)
 
 static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 {
+	struct fib6_info *f6i, *tmp;
 	struct fib_info *fi;
 	bool do_flush;
 
@@ -328,6 +329,10 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 
 	if (do_flush)
 		fib_flush(net);
+
+	list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) {
+		ip6_del_rt(net, f6i);
+	}
 }
 
 /* called on insert failure too */
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index da5102bff2a9..8131cdd472cb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2366,6 +2366,9 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
+		/* prefix routes do not use nexthop objects */
+		if (rt->nh)
+			continue;
 		if (rt->fib6_nh->nh_dev->ifindex != dev->ifindex)
 			continue;
 		if ((rt->fib6_flags & flags) != flags)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5b0ca5b3710d..b6dc644a55cf 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -202,7 +202,10 @@ void fib6_info_destroy_rcu(struct rcu_head *head)
 		}
 	}
 
-	fib6_nh_release(f6i->fib6_nh);
+	if (f6i->nh)
+		nexthop_put(f6i->nh);
+	else
+		fib6_nh_release(f6i->fib6_nh);
 
 	m = f6i->fib6_metrics;
 	if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
@@ -1302,6 +1305,8 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 	if (!err) {
 		__fib6_update_sernum_upto_root(rt, sernum);
 		fib6_start_gc(info->nl_net, rt);
+		if (rt->nh)
+			list_add(&rt->nh_list, &rt->nh->f6i_list);
 	}
 
 out:
@@ -1776,6 +1781,9 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 
 	fib6_purge_rt(rt, fn, net);
 
+	if (rt->nh)
+		list_del(&rt->nh_list);
+
 	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
 	if (!info->skip_notify)
 		inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
@@ -2251,7 +2259,6 @@ void fib6_gc_cleanup(void)
 static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 {
 	struct fib6_info *rt = v;
-	struct fib6_nh *fib6_nh = rt->fib6_nh;
 	struct ipv6_route_iter *iter = seq->private;
 	const struct net_device *dev;
 
@@ -2262,12 +2269,12 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 #else
 	seq_puts(seq, "00000000000000000000000000000000 00 ");
 #endif
-	if (rt->fib6_flags & RTF_GATEWAY)
-		seq_printf(seq, "%pi6", &fib6_nh->nh_gw);
+	if (!rt->nh && rt->fib6_flags & RTF_GATEWAY)
+		seq_printf(seq, "%pi6", &rt->fib6_nh->nh_gw);
 	else
 		seq_puts(seq, "00000000000000000000000000000000");
 
-	dev = fib6_nh->nh_dev;
+	dev = rt->nh ? NULL : rt->fib6_nh->nh_dev;
 	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
 		   rt->fib6_metric, atomic_read(&rt->fib6_ref), 0,
 		   rt->fib6_flags, dev ? dev->name : "");
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 4bc47b9db35b..1a6b71873dd3 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1277,6 +1277,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
 
 	if (rt) {
+		/* routes added from RAs do not use nexthop objects */
 		fib6_nh = rt->fib6_nh;
 		neigh = ip6_neigh_lookup(&fib6_nh->nh_gw, fib6_nh->nh_dev, NULL,
 					 &ipv6_hdr(skb)->saddr);
@@ -1307,6 +1308,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 			return;
 		}
 
+		/* routes added from RAs do not use nexthop objects */
 		fib6_nh = rt->fib6_nh;
 		neigh = ip6_neigh_lookup(&fib6_nh->nh_gw, fib6_nh->nh_dev, NULL,
 					 &ipv6_hdr(skb)->saddr);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2c140ce95eb4..217be2c72b69 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -439,6 +439,11 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
 	if (!fl6->mp_hash)
 		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
+	if (match->nh) {
+		// TO-DO:
+		return match;
+	}
+
 	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->nh_upper_bound))
 		return match;
 
@@ -661,13 +666,15 @@ static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 	int m;
 	bool match_do_rr = false;
 
-	if (rt->fib6_nh->nh_flags & RTNH_F_DEAD)
-		goto out;
+	if (!rt->nh) {
+		if (rt->fib6_nh->nh_flags & RTNH_F_DEAD)
+			goto out;
 
-	if (fib6_ignore_linkdown(rt) &&
-	    rt->fib6_nh->nh_flags & RTNH_F_LINKDOWN &&
-	    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
-		goto out;
+		if (fib6_ignore_linkdown(rt) &&
+		    rt->fib6_nh->nh_flags & RTNH_F_LINKDOWN &&
+		    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
+			goto out;
+	}
 
 	if (fib6_check_expired(rt))
 		goto out;
@@ -3064,6 +3071,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
 	struct fib6_info *rt = NULL;
+	struct nexthop *nh = NULL;
 	struct fib6_table *table;
 	int err = -EINVAL;
 
@@ -3099,6 +3107,15 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 #endif
+	if (cfg->fc_nh_id) {
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
+			NL_SET_ERR_MSG(extack,
+				       "Invalid nexthop id - nexthop does not exist");
+			goto out;
+		}
+	}
+
 	if (cfg->fc_metric == 0)
 		cfg->fc_metric = IP6_RT_PRIO_USER;
 
@@ -3118,7 +3135,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 
 	err = -ENOMEM;
-	rt = fib6_info_alloc(gfp_flags, true);
+	rt = fib6_info_alloc(gfp_flags, !nh);
 	if (!rt)
 		goto out;
 
@@ -3152,9 +3169,16 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
-	err = fib6_nh_init(net, rt->fib6_nh, cfg, extack);
-	if (err)
-		goto out;
+	if (nh) {
+		nexthop_get(nh);
+		rt->nh = nh;
+		if (nexthop_has_gw(nh))
+			cfg->fc_flags |= RTF_GATEWAY;
+	} else {
+		err = fib6_nh_init(net, rt->fib6_nh, cfg, extack);
+		if (err)
+			goto out;
+	}
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
 		struct net_device *dev = fib6_info_nh_dev(rt);
@@ -3327,6 +3351,9 @@ static int ip6_route_del(struct fib6_config *cfg,
 				}
 				continue;
 			}
+			if (rt->nh && rt->nh->id == cfg->fc_nh_id)
+				goto del_rt;
+
 			if (cfg->fc_ifindex &&
 			    (!rt->fib6_nh->nh_dev ||
 			     rt->fib6_nh->nh_dev->ifindex != cfg->fc_ifindex))
@@ -3340,6 +3367,7 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (!fib6_info_hold_safe(rt))
 				continue;
+del_rt:
 			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
@@ -3482,6 +3510,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
+/* RA routes do not use nexthop objects */
 static struct fib6_info *rt6_get_route_info(struct net *net,
 					   const struct in6_addr *prefix, int prefixlen,
 					   const struct in6_addr *gwaddr,
@@ -3551,6 +3580,7 @@ static struct fib6_info *rt6_add_route_info(struct net *net,
 }
 #endif
 
+/* RA routes do not use nexthop objects */
 struct fib6_info *rt6_get_dflt_router(struct net *net,
 				     const struct in6_addr *addr,
 				     struct net_device *dev)
@@ -3892,6 +3922,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 	return NULL;
 }
 
+/* not called for rt->nh set */
 static bool rt6_is_dead(const struct fib6_info *rt)
 {
 	if (rt->fib6_nh->nh_flags & RTNH_F_DEAD ||
@@ -3970,7 +4001,7 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg)
 	const struct arg_netdev_event *arg = p_arg;
 	struct net *net = dev_net(arg->dev);
 
-	if (rt != net->ipv6.fib6_null_entry &&
+	if (rt != net->ipv6.fib6_null_entry && !rt->nh &&
 	    rt->fib6_nh->nh_dev == arg->dev) {
 		rt->fib6_nh->nh_flags &= ~arg->nh_flags;
 		fib6_update_sernum_upto_root(net, rt);
@@ -4179,6 +4210,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_IP_PROTO]		= { .type = NLA_U8 },
 	[RTA_SPORT]		= { .type = NLA_U16 },
 	[RTA_DPORT]		= { .type = NLA_U16 },
+	[RTA_NH_ID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4224,6 +4256,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	cfg->fc_nlinfo.nlh = nlh;
 	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
 
+	if (tb[RTA_NH_ID])
+		cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]);
+
 	if (tb[RTA_GATEWAY]) {
 		cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
 		cfg->fc_flags |= RTF_GATEWAY;
@@ -4421,6 +4456,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				r_cfg.fc_encap_type = nla_get_u16(nla);
+			nla = nla_find(attrs, attrlen, RTA_NH_ID);
+			if (nla) {
+				err = -EINVAL;
+				NL_SET_ERR_MSG(extack,
+					       "Multipath API can not use nexthop objects.");
+				goto cleanup;
+			}
 		}
 
 		r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK);
@@ -4596,6 +4638,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 static size_t rt6_nlmsg_size(struct fib6_info *rt)
 {
 	int nexthop_len = 0;
+	size_t nh_len;
 
 	if (rt->fib6_nsiblings) {
 		nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
@@ -4606,23 +4649,29 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 		nexthop_len *= rt->fib6_nsiblings;
 	}
 
+	if (rt->nh) {
+		nh_len = nla_total_size(4); /* RTA_NH_ID */
+	} else {
+		nh_len = lwtunnel_get_encap_size(rt->fib6_nh->nh_lwtstate)
+			 + nla_total_size(16) /* RTA_GATEWAY */
+			 + nla_total_size(4); /* RTA_OIF */
+	}
+
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
 	       + nla_total_size(16) /* RTA_SRC */
 	       + nla_total_size(16) /* RTA_DST */
-	       + nla_total_size(16) /* RTA_GATEWAY */
 	       + nla_total_size(16) /* RTA_PREFSRC */
 	       + nla_total_size(4) /* RTA_TABLE */
 	       + nla_total_size(4) /* RTA_IIF */
-	       + nla_total_size(4) /* RTA_OIF */
 	       + nla_total_size(4) /* RTA_PRIORITY */
 	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
 	       + nla_total_size(sizeof(struct rta_cacheinfo))
 	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
 	       + nla_total_size(1) /* RTA_PREF */
-	       + lwtunnel_get_encap_size(rt->fib6_nh->nh_lwtstate)
-	       + nexthop_len;
+	       + nexthop_len + nh_len;
 }
 
+/* not called for rt->nh set */
 static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt,
 			    unsigned int *flags, bool skip_oif)
 {
@@ -4777,10 +4826,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric))
 		goto nla_put_failure;
 
+	if (rt->nh) {
+		if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
+			goto nla_put_failure;
+
 	/* For multipath routes, walk the siblings list and add
 	 * each as a nexthop within RTA_MULTIPATH.
 	 */
-	if (rt->fib6_nsiblings) {
+	} else if (rt->fib6_nsiblings) {
 		struct fib6_info *sibling, *next_sibling;
 		struct nlattr *mp;
 
-- 
2.11.0