[PATCH RFC net-next 14/18] net/ipv4: Allow routes to use nexthop objects

[dsahern@kernel.org]

From: David Ahern <dsahern@gmail.com>

Add new RTA attribute to allow a user to specify a nexthop id to use
with a route instead of the current nexthop specification.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/net/ip_fib.h           |   1 +
 include/uapi/linux/rtnetlink.h |   1 +
 net/ipv4/fib_frontend.c        |   7 +++
 net/ipv4/fib_semantics.c       | 139 ++++++++++++++++++++++++++++++-----------
 net/ipv4/fib_trie.c            |  33 +++++++---
 5 files changed, 136 insertions(+), 45 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index c59e0f1ba59b..d2f961de732d 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -40,6 +40,7 @@ struct fib_config {
 	u32			fc_flags;
 	u32			fc_priority;
 	__be32			fc_prefsrc;
+	u32			fc_nh_id;
 	struct nlattr		*fc_mx;
 	struct rtnexthop	*fc_mp;
 	int			fc_mx_len;
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 4a0615797e5e..a036368798a9 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -349,6 +349,7 @@ enum rtattr_type_t {
 	RTA_IP_PROTO,
 	RTA_SPORT,
 	RTA_DPORT,
+	RTA_NH_ID,
 	__RTA_MAX
 };
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c483453bf037..cf133d4e02f2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -322,6 +322,9 @@ static bool fib_info_nh_uses_dev(struct fib_info *fi,
 	bool dev_match = false;
 	int ret;
 
+	if (fi->nh)
+		return nexthop_uses_dev(fi->nh, dev);
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	for (ret = 0; ret < fi->fib_nhs; ret++) {
 		struct fib_nh *nh = &fi->fib_nh[ret];
@@ -663,6 +666,7 @@ const struct nla_policy rtm_ipv4_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_fib_config(struct net *net, struct sk_buff *skb,
@@ -746,6 +750,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			if (err < 0)
 				goto errout;
 			break;
+		case RTA_NH_ID:
+			cfg->fc_nh_id = nla_get_u32(attr);
+			break;
 		}
 	}
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0cd536ad1761..c91cdafd40ec 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -226,9 +226,13 @@ static void free_fib_info_rcu(struct rcu_head *head)
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
 	struct dst_metrics *m;
 
-	change_nexthops(fi) {
-		fib_nh_release(fi->fib_net, nexthop_nh);
-	} endfor_nexthops(fi);
+	if (fi->nh) {
+		nexthop_put(fi->nh);
+	} else {
+		change_nexthops(fi) {
+			fib_nh_release(fi->fib_net, nexthop_nh);
+		} endfor_nexthops(fi);
+	}
 
 	m = fi->fib_metrics;
 	if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
@@ -260,11 +264,15 @@ void fib_release_info(struct fib_info *fi)
 		hlist_del(&fi->fib_hash);
 		if (fi->fib_prefsrc)
 			hlist_del(&fi->fib_lhash);
-		change_nexthops(fi) {
-			if (!nexthop_nh->nh_dev)
-				continue;
-			hlist_del(&nexthop_nh->nh_hash);
-		} endfor_nexthops(fi)
+		if (fi->nh) {
+			list_del(&fi->nh_list);
+		} else {
+			change_nexthops(fi) {
+				if (!nexthop_nh->nh_dev)
+					continue;
+				hlist_del(&nexthop_nh->nh_hash);
+			} endfor_nexthops(fi)
+		}
 		fi->fib_dead = 1;
 		fib_info_put(fi);
 	}
@@ -275,6 +283,12 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 {
 	const struct fib_nh *onh = ofi->fib_nh;
 
+	if (fi->nh || ofi->nh)
+		return nexthop_cmp(fi->nh, ofi->nh) ? 0 : -1;
+
+	if (ofi->fib_nhs == 0)
+		return 0;
+
 	for_nexthops(fi) {
 		if (nh->nh_oif != onh->nh_oif ||
 		    nh->nh_gw  != onh->nh_gw ||
@@ -310,10 +324,13 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
 	val ^= (fi->fib_protocol << 8) | fi->fib_scope;
 	val ^= (__force u32)fi->fib_prefsrc;
 	val ^= fi->fib_priority;
-	for_nexthops(fi) {
-		val ^= fib_devindex_hashfn(nh->nh_oif);
-	} endfor_nexthops(fi)
-
+	if (fi->nh) {
+		val ^= fib_devindex_hashfn(fi->nh->id);
+	} else {
+		for_nexthops(fi) {
+			val ^= fib_devindex_hashfn(nh->nh_oif);
+		} endfor_nexthops(fi)
+	}
 	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
 }
 
@@ -339,7 +356,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
 		    memcmp(nfi->fib_metrics, fi->fib_metrics,
 			   sizeof(u32) * RTAX_MAX) == 0 &&
 		    !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) &&
-		    (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
+		    (nh_comp(fi, nfi) == 0))
 			return fi;
 	}
 
@@ -349,6 +366,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
 /* Check, that the gateway is already configured.
  * Used only by redirect accept routine.
  */
+//TO-DO: need a nexthop version
 int ip_fib_check_default(__be32 gw, struct net_device *dev)
 {
 	struct hlist_head *head;
@@ -381,16 +399,19 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
 			 + nla_total_size(4) /* RTA_PRIORITY */
 			 + nla_total_size(4) /* RTA_PREFSRC */
 			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
+	size_t nhsize = 0;
 
 	/* space for nested metrics */
 	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
 
-	if (fi->fib_nhs) {
+	if (fi->nh) {
+		nhsize = nla_total_size(4); /* RTA_NH_ID */
+	} else if (fi->fib_nhs) {
 		size_t nh_encapsize = 0;
 		/* Also handles the special case fib_nhs == 1 */
 
 		/* each nexthop is packed in an attribute */
-		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
+		nhsize = nla_total_size(sizeof(struct rtnexthop));
 
 		/* may contain flow and gateway attribute */
 		nhsize += 2 * nla_total_size(4);
@@ -539,6 +560,7 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
 	return nhs;
 }
 
+/* only called when fib_nh is integrated into fib_info */
 static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		       int remaining, struct fib_config *cfg,
 		       struct netlink_ext_ack *extack)
@@ -625,6 +647,8 @@ static void fib_rebalance(struct fib_info *fi)
 	int w;
 	struct in_device *in_dev;
 
+	WARN_ON(fi->nh);
+
 	if (fi->fib_nhs < 2)
 		return;
 
@@ -712,6 +736,9 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
 		return 1;
 
+	if (fi->nh)
+		return cfg->fc_nh_id == fi->nh->id ? 0 : 1;
+
 	if (cfg->fc_oif || cfg->fc_gw) {
 		if (cfg->fc_encap) {
 			if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
@@ -1099,9 +1126,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 {
 	int err;
 	struct fib_info *fi = NULL;
+	struct nexthop *nh = NULL;
 	struct fib_info *ofi;
 	int nhs = 1;
 	struct net *net = cfg->fc_nlinfo.nl_net;
+	unsigned char scope;
 
 	if (cfg->fc_type > RTN_MAX)
 		goto err_inval;
@@ -1118,6 +1147,21 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
+	if (cfg->fc_nh_id) {
+		if (cfg->fc_oif || cfg->fc_gw || cfg->fc_encap || cfg->fc_mp) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop specification and nexthop id are mutually exclusive");
+			goto err_inval;
+		}
+
+		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 err_inval;
+		}
+	}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (cfg->fc_mp) {
 		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack);
@@ -1180,7 +1224,10 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	if (err)
 		goto failure;
 
-	if (cfg->fc_mp) {
+	if (nh) {
+		nexthop_get(nh);
+		fi->nh = nh;
+	} else if (cfg->fc_mp) {
 		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack);
 		if (err != 0)
 			goto failure;
@@ -1214,7 +1261,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
-	if (cfg->fc_scope == RT_SCOPE_HOST) {
+	if (fi->nh) {
+		err = fib_check_nexthop(fi, cfg, extack);
+		if (err)
+			goto failure;
+	} else if (cfg->fc_scope == RT_SCOPE_HOST) {
 		struct fib_nh *nh = fi->fib_nh;
 
 		/* Local address is added. */
@@ -1254,12 +1305,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto err_inval;
 	}
 
-	change_nexthops(fi) {
-		fib_info_update_nh_saddr(net, nexthop_nh, fi->fib_scope);
-	} endfor_nexthops(fi)
-
-	fib_rebalance(fi);
+	if (!fi->nh) {
+		scope = fi->fib_scope;
+		change_nexthops(fi) {
+			fib_info_update_nh_saddr(net, nexthop_nh, scope);
+		} endfor_nexthops(fi)
 
+		fib_rebalance(fi);
+	}
 link_it:
 	ofi = fib_find_info(fi);
 	if (ofi) {
@@ -1280,16 +1333,20 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
 		hlist_add_head(&fi->fib_lhash, head);
 	}
-	change_nexthops(fi) {
-		struct hlist_head *head;
-		unsigned int hash;
+	if (fi->nh) {
+		list_add(&fi->nh_list, &nh->fi_list);
+	} else {
+		change_nexthops(fi) {
+			struct hlist_head *head;
+			unsigned int hash;
 
-		if (!nexthop_nh->nh_dev)
-			continue;
-		hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
-		head = &fib_info_devhash[hash];
-		hlist_add_head(&nexthop_nh->nh_hash, head);
-	} endfor_nexthops(fi)
+			if (!nexthop_nh->nh_dev)
+				continue;
+			hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
+			head = &fib_info_devhash[hash];
+			hlist_add_head(&nexthop_nh->nh_hash, head);
+		} endfor_nexthops(fi)
+	}
 	spin_unlock_bh(&fib_info_lock);
 	return fi;
 
@@ -1298,6 +1355,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 
 failure:
 	if (fi) {
+		if (fi->nh)
+			nexthop_put(fi->nh);
+
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 	}
@@ -1344,7 +1404,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	if (fi->fib_prefsrc &&
 	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
 		goto nla_put_failure;
-	if (fi->fib_nhs == 1) {
+
+	if (fi->nh) {
+		if (nla_put_u32(skb, RTA_NH_ID, fi->nh->id))
+			goto nla_put_failure;
+	} else if (fi->fib_nhs == 1) {
 		if (fi->fib_nh->nh_gw &&
 		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
 			goto nla_put_failure;
@@ -1587,8 +1651,11 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 				continue;
 			break;
 		}
-		if (next_fi->fib_flags & RTNH_F_DEAD)
+
+		fnh = fib_info_nh(next_fi, 0);
+		if (fnh->nh_flags & RTNH_F_DEAD)
 			continue;
+
 		last_tos = fa->fa_tos;
 		last_prio = next_fi->fib_priority;
 
@@ -1596,7 +1663,6 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 		    fa->fa_type != RTN_UNICAST)
 			continue;
 
-		fnh = fib_info_nh(next_fi, 0);
 		if (!fnh->nh_gw || fnh->nh_scope != RT_SCOPE_LINK)
 			continue;
 
@@ -1749,13 +1815,14 @@ void fib_select_multipath(struct fib_result *res, int hash)
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, const struct sk_buff *skb)
 {
+	int h;
+
 	if (fl4->flowi4_oif && !(fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF))
 		goto check_saddr;
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(net, fl4, skb, NULL);
-
+		h = fib_multipath_hash(net, fl4, skb, NULL);
 		fib_select_multipath(res, h);
 	}
 	else
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index c6aab049a4ac..575bb34d895f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1445,7 +1445,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 	/* Step 3: Process the leaf, if that fails fall back to backtracing */
 	hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) {
 		struct fib_info *fi = fa->fa_info;
-		int nhsel, err;
+		int nhsel, err, nhmax;
 
 		if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
 			if (index >= (1ul << fa->fa_slen))
@@ -1460,6 +1460,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		fib_alias_accessed(fa);
 		err = fib_props[fa->fa_type].error;
 		if (unlikely(err < 0)) {
+out_reject:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 			this_cpu_inc(stats->semantic_match_passed);
 #endif
@@ -1468,17 +1469,31 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		}
 		if (fi->fib_flags & RTNH_F_DEAD)
 			continue;
-		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
-			struct fib_nh *nh = &fi->fib_nh[nhsel];
-			struct in_device *in_dev = __in_dev_get_rcu(nh->nh_dev);
+
+		if (fi->nh) {
+			if (nexthop_is_blackhole(fi->nh)) {
+				err = fib_props[RTN_BLACKHOLE].error;
+				goto out_reject;
+			}
+			nhmax = nexthop_num_path(fi->nh);
+		} else {
+			nhmax = fi->fib_nhs;
+		}
+		for (nhsel = 0; nhsel < nhmax; nhsel++) {
+			struct fib_nh *nh = fib_info_nh(fi, nhsel);
+			struct in_device *in_dev;
 
 			if (nh->nh_flags & RTNH_F_DEAD)
 				continue;
-			if (in_dev &&
-			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-			    nh->nh_flags & RTNH_F_LINKDOWN &&
-			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
-				continue;
+
+			if (!fi->nh) {
+				in_dev = __in_dev_get_rcu(nh->nh_dev);
+				if (in_dev &&
+				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+				    nh->nh_flags & RTNH_F_LINKDOWN &&
+				    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
+					continue;
+			}
 			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
 				if (flp->flowi4_oif &&
 				    flp->flowi4_oif != nh->nh_oif)
-- 
2.11.0