ipv6: fix route selection if kernel is not compiled with CONFIG_IPV6_ROUTER_PREF

This is a follow-up patch to 3630d40067a21d4dfbadc6002bb469ce26ac5d52
("ipv6: rt6_check_neigh should successfully verify neigh if no NUD
information are available").

Since the removal of rt->n in rt6_info we can end up with a dst ==
NULL in rt6_check_neigh. In case the kernel is not compiled with
CONFIG_IPV6_ROUTER_PREF we should also select a route with unkown
NUD state but we must not avoid doing round robin selection on routes
with the same target. So introduce and pass down a boolean ``do_rr'' to
indicate when we should update rt->rr_ptr. As soon as no route is valid
we do backtracking and do a lookup on a higher level in the fib trie.

v2:
a) Improved rt6_check_neigh logic (no need to create neighbour there)
   and documented return values.

v3:
a) Introduce enum rt6_nud_state to get rid of the magic numbers
   (thanks to David Miller).
b) Update and shorten commit message a bit to actualy reflect
   the source.

Reported-by: Pierre Emeriaud <petrus.lt@gmail.com>
Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 40 insertions, 23 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5b127e09c224..a8c891aa2464 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -65,6 +65,12 @@
 #include <linux/sysctl.h>
 #endif
 
+enum rt6_nud_state {
+	RT6_NUD_FAIL_HARD = -2,
+	RT6_NUD_FAIL_SOFT = -1,
+	RT6_NUD_SUCCEED = 1
+};
+
 static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 				    const struct in6_addr *dest);
 static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
@@ -531,28 +537,29 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif)
 	return 0;
 }
 
-static inline bool rt6_check_neigh(struct rt6_info *rt)
+static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
 {
 	struct neighbour *neigh;
-	bool ret = false;
+	enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
 
 	if (rt->rt6i_flags & RTF_NONEXTHOP ||
 	    !(rt->rt6i_flags & RTF_GATEWAY))
-		return true;
+		return RT6_NUD_SUCCEED;
 
 	rcu_read_lock_bh();
 	neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
 	if (neigh) {
 		read_lock(&neigh->lock);
 		if (neigh->nud_state & NUD_VALID)
-			ret = true;
+			ret = RT6_NUD_SUCCEED;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 		else if (!(neigh->nud_state & NUD_FAILED))
-			ret = true;
+			ret = RT6_NUD_SUCCEED;
 #endif
 		read_unlock(&neigh->lock);
-	} else if (IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) {
-		ret = true;
+	} else {
+		ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
+		      RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT;
 	}
 	rcu_read_unlock_bh();
 
@@ -566,43 +573,52 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
 
 	m = rt6_check_dev(rt, oif);
 	if (!m && (strict & RT6_LOOKUP_F_IFACE))
-		return -1;
+		return RT6_NUD_FAIL_HARD;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
 #endif
-	if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE))
-		return -1;
+	if (strict & RT6_LOOKUP_F_REACHABLE) {
+		int n = rt6_check_neigh(rt);
+		if (n < 0)
+			return n;
+	}
 	return m;
 }
 
 static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
-				   int *mpri, struct rt6_info *match)
+				   int *mpri, struct rt6_info *match,
+				   bool *do_rr)
 {
 	int m;
+	bool match_do_rr = false;
 
 	if (rt6_check_expired(rt))
 		goto out;
 
 	m = rt6_score_route(rt, oif, strict);
-	if (m < 0)
+	if (m == RT6_NUD_FAIL_SOFT && !IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) {
+		match_do_rr = true;
+		m = 0; /* lowest valid score */
+	} else if (m < 0) {
 		goto out;
+	}
+
+	if (strict & RT6_LOOKUP_F_REACHABLE)
+		rt6_probe(rt);
 
 	if (m > *mpri) {
-		if (strict & RT6_LOOKUP_F_REACHABLE)
-			rt6_probe(match);
+		*do_rr = match_do_rr;
 		*mpri = m;
 		match = rt;
-	} else if (strict & RT6_LOOKUP_F_REACHABLE) {
-		rt6_probe(rt);
 	}
-
 out:
 	return match;
 }
 
 static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 				     struct rt6_info *rr_head,
-				     u32 metric, int oif, int strict)
+				     u32 metric, int oif, int strict,
+				     bool *do_rr)
 {
 	struct rt6_info *rt, *match;
 	int mpri = -1;
@@ -610,10 +626,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 	match = NULL;
 	for (rt = rr_head; rt && rt->rt6i_metric == metric;
 	     rt = rt->dst.rt6_next)
-		match = find_match(rt, oif, strict, &mpri, match);
+		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
 	     rt = rt->dst.rt6_next)
-		match = find_match(rt, oif, strict, &mpri, match);
+		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 
 	return match;
 }
@@ -622,15 +638,16 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
 {
 	struct rt6_info *match, *rt0;
 	struct net *net;
+	bool do_rr = false;
 
 	rt0 = fn->rr_ptr;
 	if (!rt0)
 		fn->rr_ptr = rt0 = fn->leaf;
 
-	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);
+	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict,
+			     &do_rr);
 
-	if (!match &&
-	    (strict & RT6_LOOKUP_F_REACHABLE)) {
+	if (do_rr) {
 		struct rt6_info *next = rt0->dst.rt6_next;
 
 		/* no entries matched; do round-robin */