Merge branch 'fib_select_default-fixes'

Julian Anastasov says:

====================
ipv4: fib_select_default changes

This patchset contains 2 changes for the alternative routes,
one to add tb_id/fa_slen check needed after the recent
fib_trie optimizations for fib aliases and the second
change attempts to support alternative routes with TOS
requirement.

	Sorry that I don't have access to the original
report from Hagen Paul Pfeifer. I hope he will see this
change.

	The second change adds fa_default field to the
fib aliases (which can be many) and if the feature to
filter the alternative routes by TOS is not worth it,
this second patch can be scrapped.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 35 insertions, 15 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 49c142bdf01e..5fa643b4e891 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -183,7 +183,6 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
 struct fib_table {
 	struct hlist_node	tb_hlist;
 	u32			tb_id;
-	int			tb_default;
 	int			tb_num_default;
 	struct rcu_head		rcu;
 	unsigned long 		*tb_data;
@@ -290,7 +289,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb);
 int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			u8 tos, int oif, struct net_device *dev,
 			struct in_device *idev, u32 *itag);
-void fib_select_default(struct fib_result *res);
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c6211ed60b03..9c02920725db 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -13,6 +13,7 @@ struct fib_alias {
 	u8			fa_state;
 	u8			fa_slen;
 	u32			tb_id;
+	s16			fa_default;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c7358ea4ae93..3a06586b170c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1202,23 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 }
 
 /* Must be invoked inside of an RCU protected region.  */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 {
 	struct fib_info *fi = NULL, *last_resort = NULL;
 	struct hlist_head *fa_head = res->fa_head;
 	struct fib_table *tb = res->table;
+	u8 slen = 32 - res->prefixlen;
 	int order = -1, last_idx = -1;
-	struct fib_alias *fa;
+	struct fib_alias *fa, *fa1 = NULL;
+	u32 last_prio = res->fi->fib_priority;
+	u8 last_tos = 0;
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
 
+		if (fa->fa_slen != slen)
+			continue;
+		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+			continue;
+		if (fa->tb_id != tb->tb_id)
+			continue;
+		if (next_fi->fib_priority > last_prio &&
+		    fa->fa_tos == last_tos) {
+			if (last_tos)
+				continue;
+			break;
+		}
+		if (next_fi->fib_flags & RTNH_F_DEAD)
+			continue;
+		last_tos = fa->fa_tos;
+		last_prio = next_fi->fib_priority;
+
 		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
-
-		if (next_fi->fib_priority > res->fi->fib_priority)
-			break;
 		if (!next_fi->fib_nh[0].nh_gw ||
 		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
 			continue;
@@ -1228,10 +1245,11 @@ void fib_select_default(struct fib_result *res)
 		if (!fi) {
 			if (next_fi != res->fi)
 				break;
+			fa1 = fa;
 		} else if (!fib_detect_death(fi, order, &last_resort,
-					     &last_idx, tb->tb_default)) {
+					     &last_idx, fa1->fa_default)) {
 			fib_result_assign(res, fi);
-			tb->tb_default = order;
+			fa1->fa_default = order;
 			goto out;
 		}
 		fi = next_fi;
@@ -1239,20 +1257,21 @@ void fib_select_default(struct fib_result *res)
 	}
 
 	if (order <= 0 || !fi) {
-		tb->tb_default = -1;
+		if (fa1)
+			fa1->fa_default = -1;
 		goto out;
 	}
 
 	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
-				tb->tb_default)) {
+			      fa1->fa_default)) {
 		fib_result_assign(res, fi);
-		tb->tb_default = order;
+		fa1->fa_default = order;
 		goto out;
 	}
 
 	if (last_idx >= 0)
 		fib_result_assign(res, last_resort);
-	tb->tb_default = last_idx;
+	fa1->fa_default = last_idx;
 out:
 	return;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 15d32612e3c6..81797e065b21 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
 			new_fa->fa_slen = fa->fa_slen;
 			new_fa->tb_id = tb->tb_id;
+			new_fa->fa_default = -1;
 
 			err = switchdev_fib_ipv4_add(key, plen, fi,
 						     new_fa->fa_tos,
@@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 	new_fa->fa_state = 0;
 	new_fa->fa_slen = slen;
 	new_fa->tb_id = tb->tb_id;
+	new_fa->fa_default = -1;
 
 	/* (Optionally) offload fib entry to switch hardware. */
 	err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
@@ -1990,7 +1992,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)
 		return NULL;
 
 	tb->tb_id = id;
-	tb->tb_default = -1;
 	tb->tb_num_default = 0;
 	tb->tb_data = (alias ? alias->__data : tb->__data);
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d0362a2de3d3..e681b852ced1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2176,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	if (!res.prefixlen &&
 	    res.table->tb_num_default > 1 &&
 	    res.type == RTN_UNICAST && !fl4->flowi4_oif)
-		fib_select_default(&res);
+		fib_select_default(fl4, &res);
 
 	if (!fl4->saddr)
 		fl4->saddr = FIB_RES_PREFSRC(net, res);