ipv4: Add fib_nh_common to fib_result

Most of the ipv4 code only needs data from fib_nh_common. Add
fib_nh_common selection to fib_result and update users to use it.

Right now, fib_nh_common in fib_result will point to a fib_nh struct
that is embedded within a fib_info:

        fib_info  --> fib_nh
                      fib_nh
                      ...
                      fib_nh
                        ^
    fib_result->nhc ----+

Later, nhc can point to a fib_nh within a nexthop struct:

        fib_info --> nexthop --> fib_nh
                                   ^
    fib_result->nhc ---------------+

or for a nexthop group:

        fib_info --> nexthop --> nexthop --> fib_nh
                                 nexthop --> fib_nh
                                 ...
                                 nexthop --> fib_nh
                                               ^
    fib_result->nhc ---------------------------+

In all cases nhsel within fib_result will point to which leg in the
multipath route is used.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 78 insertions, 39 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index cdaafa3322db..08b53af84132 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4555,11 +4555,11 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 			       u32 flags, bool check_mtu)
 {
+	struct fib_nh_common *nhc;
 	struct in_device *in_dev;
 	struct neighbour *neigh;
 	struct net_device *dev;
 	struct fib_result res;
-	struct fib_nh *nh;
 	struct flowi4 fl4;
 	int err;
 	u32 mtu;
@@ -4632,15 +4632,15 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	nh = &res.fi->fib_nh[res.nh_sel];
+	nhc = res.nhc;
 
 	/* do not handle lwt encaps right now */
-	if (nh->fib_nh_lws)
+	if (nhc->nhc_lwtstate)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
-	dev = nh->fib_nh_dev;
-	if (nh->fib_nh_gw4)
-		params->ipv4_dst = nh->fib_nh_gw4;
+	dev = nhc->nhc_dev;
+	if (nhc->nhc_has_gw)
+		params->ipv4_dst = nhc->nhc_gw.ipv4;
 
 	params->rt_metric = res.fi->fib_priority;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ffbe24397dbe..15f779bd26b3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -307,7 +307,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 			.flowi4_mark = vmark ? skb->mark : 0,
 		};
 		if (!fib_lookup(net, &fl4, &res, 0))
-			return FIB_RES_PREFSRC(net, res);
+			return fib_result_prefsrc(net, &res);
 	} else {
 		scope = RT_SCOPE_LINK;
 	}
@@ -390,7 +390,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 
 	dev_match = fib_info_nh_uses_dev(res.fi, dev);
 	if (dev_match) {
-		ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
+		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 		return ret;
 	}
 	if (no_addr)
@@ -402,7 +402,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
-			ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
+			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 	}
 	return ret;
 
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index e6ff282bb7f4..7945f0534db7 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -45,6 +45,7 @@ static inline void fib_result_assign(struct fib_result *res,
 {
 	/* we used to play games with refcounts, but we now use RCU */
 	res->fi = fi;
+	res->nhc = fib_info_nhc(fi, 0);
 }
 
 struct fib_prop {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index df777af7e278..42666a409da0 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1075,6 +1075,21 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
 	return nh->nh_saddr;
 }
 
+__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
+{
+	struct fib_nh_common *nhc = res->nhc;
+	struct fib_nh *nh;
+
+	if (res->fi->fib_prefsrc)
+		return res->fi->fib_prefsrc;
+
+	nh = container_of(nhc, struct fib_nh, nh_common);
+	if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
+		return nh->nh_saddr;
+
+	return fib_info_update_nh_saddr(net, nh);
+}
+
 static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
 {
 	if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
@@ -1762,20 +1777,22 @@ void fib_select_multipath(struct fib_result *res, int hash)
 	struct net *net = fi->fib_net;
 	bool first = false;
 
-	for_nexthops(fi) {
+	change_nexthops(fi) {
 		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
-			if (!fib_good_nh(nh))
+			if (!fib_good_nh(nexthop_nh))
 				continue;
 			if (!first) {
 				res->nh_sel = nhsel;
+				res->nhc = &nexthop_nh->nh_common;
 				first = true;
 			}
 		}
 
-		if (hash > atomic_read(&nh->fib_nh_upper_bound))
+		if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound))
 			continue;
 
 		res->nh_sel = nhsel;
+		res->nhc = &nexthop_nh->nh_common;
 		return;
 	} endfor_nexthops(fi);
 }
@@ -1802,5 +1819,5 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 check_saddr:
 	if (!fl4->saddr)
-		fl4->saddr = FIB_RES_PREFSRC(net, *res);
+		fl4->saddr = fib_result_prefsrc(net, res);
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 13b3327206f9..334f723bdf80 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1470,17 +1470,17 @@ found:
 		if (fi->fib_flags & RTNH_F_DEAD)
 			continue;
 		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
-			const struct fib_nh *nh = &fi->fib_nh[nhsel];
+			struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel);
 
-			if (nh->fib_nh_flags & RTNH_F_DEAD)
+			if (nhc->nhc_flags & RTNH_F_DEAD)
 				continue;
-			if (ip_ignore_linkdown(nh->fib_nh_dev) &&
-			    nh->fib_nh_flags & RTNH_F_LINKDOWN &&
+			if (ip_ignore_linkdown(nhc->nhc_dev) &&
+			    nhc->nhc_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->fib_nh_oif)
+				    flp->flowi4_oif != nhc->nhc_oif)
 					continue;
 			}
 
@@ -1490,6 +1490,7 @@ found:
 			res->prefix = htonl(n->key);
 			res->prefixlen = KEYLENGTH - fa->fa_slen;
 			res->nh_sel = nhsel;
+			res->nhc = nhc;
 			res->type = fa->fa_type;
 			res->scope = fi->fib_scope;
 			res->fi = fi;
@@ -1498,7 +1499,7 @@ found:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 			this_cpu_inc(stats->semantic_match_passed);
 #endif
-			trace_fib_table_lookup(tb->tb_id, flp, &nh->nh_common, err);
+			trace_fib_table_lookup(tb->tb_id, flp, nhc, err);
 
 			return err;
 		}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7977514d90f5..f3f2adf630d4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -778,8 +778,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			neigh_event_send(n, NULL);
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
-				struct fib_nh *nh = &FIB_RES_NH(res);
+				struct fib_nh_common *nhc = FIB_RES_NHC(res);
+				struct fib_nh *nh;
 
+				nh = container_of(nhc, struct fib_nh, nh_common);
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
@@ -1027,8 +1029,10 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 
 	rcu_read_lock();
 	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
-		struct fib_nh *nh = &FIB_RES_NH(res);
+		struct fib_nh_common *nhc = FIB_RES_NHC(res);
+		struct fib_nh *nh;
 
+		nh = container_of(nhc, struct fib_nh, nh_common);
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
@@ -1235,7 +1239,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 
 		rcu_read_lock();
 		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
-			src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
+			src = fib_result_prefsrc(dev_net(rt->dst.dev), &res);
 		else
 			src = inet_select_addr(rt->dst.dev,
 					       rt_nexthop(rt, iph->daddr),
@@ -1354,9 +1358,9 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 
 u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 {
+	struct fib_nh_common *nhc = res->nhc;
+	struct net_device *dev = nhc->nhc_dev;
 	struct fib_info *fi = res->fi;
-	struct fib_nh *nh = &fi->fib_nh[res->nh_sel];
-	struct net_device *dev = nh->fib_nh_dev;
 	u32 mtu = 0;
 
 	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
@@ -1364,6 +1368,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 		mtu = fi->fib_mtu;
 
 	if (likely(!mtu)) {
+		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct fib_nh_exception *fnhe;
 
 		fnhe = find_exception(nh, daddr);
@@ -1374,7 +1379,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 	if (likely(!mtu))
 		mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
+	return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu);
 }
 
 static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
@@ -1529,7 +1534,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 	bool cached = false;
 
 	if (fi) {
-		struct fib_nh *nh = &FIB_RES_NH(*res);
+		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 
 		if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) {
 			rt->rt_gateway = nh->fib_nh_gw4;
@@ -1699,15 +1705,18 @@ static int __mkroute_input(struct sk_buff *skb,
 			   struct in_device *in_dev,
 			   __be32 daddr, __be32 saddr, u32 tos)
 {
+	struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+	struct net_device *dev = nhc->nhc_dev;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rth;
+	struct fib_nh *nh;
 	int err;
 	struct in_device *out_dev;
 	bool do_cache;
 	u32 itag = 0;
 
 	/* get a working reference to the output device */
-	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
+	out_dev = __in_dev_get_rcu(dev);
 	if (!out_dev) {
 		net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
 		return -EINVAL;
@@ -1724,10 +1733,13 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
-	    skb->protocol == htons(ETH_P_IP) &&
-	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
-		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
+	    skb->protocol == htons(ETH_P_IP)) {
+		__be32 gw = nhc->nhc_family == AF_INET ? nhc->nhc_gw.ipv4 : 0;
+
+		if (IN_DEV_SHARED_MEDIA(out_dev) ||
+		    inet_addr_onlink(out_dev, saddr, gw))
+			IPCB(skb)->flags |= IPSKB_DOREDIRECT;
+	}
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1744,12 +1756,13 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
+	nh = container_of(nhc, struct fib_nh, nh_common);
+	fnhe = find_exception(nh, daddr);
 	if (do_cache) {
 		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
 		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			rth = rcu_dereference(nh->nh_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2043,7 +2056,11 @@ local_input:
 	do_cache = false;
 	if (res->fi) {
 		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+			struct fib_nh *nh;
+
+			nh = container_of(nhc, struct fib_nh, nh_common);
+			rth = rcu_dereference(nh->nh_rth_input);
 			if (rt_cache_valid(rth)) {
 				skb_dst_set_noref(skb, &rth->dst);
 				err = 0;
@@ -2073,15 +2090,17 @@ local_input:
 	}
 
 	if (do_cache) {
-		struct fib_nh *nh = &FIB_RES_NH(*res);
+		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+		struct fib_nh *nh;
 
-		rth->dst.lwtstate = lwtstate_get(nh->fib_nh_lws);
+		rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
 		if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
 			WARN_ON(rth->dst.input == lwtunnel_input);
 			rth->dst.lwtstate->orig_input = rth->dst.input;
 			rth->dst.input = lwtunnel_input;
 		}
 
+		nh = container_of(nhc, struct fib_nh, nh_common);
 		if (unlikely(!rt_cache_route(nh, rth)))
 			rt_add_uncached_list(rth);
 	}
@@ -2253,8 +2272,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	fnhe = NULL;
 	do_cache &= fi != NULL;
 	if (fi) {
+		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct rtable __rcu **prth;
-		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
 		if (!do_cache)
@@ -2264,8 +2284,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		} else {
 			if (unlikely(fl4->flowi4_flags &
 				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->fib_nh_gw4 &&
-				       nh->fib_nh_scope == RT_SCOPE_LINK))) {
+				     !(nhc->nhc_has_gw &&
+				       nhc->nhc_scope == RT_SCOPE_LINK))) {
 				do_cache = false;
 				goto add;
 			}