ipv6: router reachability probing
RFC 4191 states in 3.5:
When a host avoids using any non-reachable router X and instead sends
a data packet to another router Y, and the host would have used
router X if router X were reachable, then the host SHOULD probe each
such router X's reachability by sending a single Neighbor
Solicitation to that router's address. A host MUST NOT probe a
router's reachability in the absence of useful traffic that the host
would have sent to the router if it were reachable. In any case,
these probes MUST be rate-limited to no more than one per minute per
router.
Currently, when the neighbour corresponding to a router falls into
NUD_FAILED, it's never considered again. Introduce a new rt6_nud_state
value, RT6_NUD_FAIL_PROBE, which suggests the route should not be used but
should be probed with a single NS. The probe is ratelimited by the existing
code. To better distinguish meanings of the failure values, rename
RT6_NUD_FAIL_SOFT to RT6_NUD_FAIL_DO_RR.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 41b1ce6..4c09bd2 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -252,6 +252,7 @@
void neigh_destroy(struct neighbour *neigh);
int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags);
+void __neigh_set_probe_once(struct neighbour *neigh);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8be82a7..bf6f404 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1238,6 +1238,21 @@
}
EXPORT_SYMBOL(neigh_update);
+/* Update the neigh to listen temporarily for probe responses, even if it is
+ * in a NUD_FAILED state. The caller has to hold neigh->lock for writing.
+ */
+void __neigh_set_probe_once(struct neighbour *neigh)
+{
+ neigh->updated = jiffies;
+ if (!(neigh->nud_state & NUD_FAILED))
+ return;
+ neigh->nud_state = NUD_PROBE;
+ atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+ neigh_add_timer(neigh,
+ jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
+}
+EXPORT_SYMBOL(__neigh_set_probe_once);
+
struct neighbour *neigh_event_ns(struct neigh_table *tbl,
u8 *lladdr, void *saddr,
struct net_device *dev)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ddb9d41..a1a5752 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -66,8 +66,9 @@
#endif
enum rt6_nud_state {
- RT6_NUD_FAIL_HARD = -2,
- RT6_NUD_FAIL_SOFT = -1,
+ RT6_NUD_FAIL_HARD = -3,
+ RT6_NUD_FAIL_PROBE = -2,
+ RT6_NUD_FAIL_DO_RR = -1,
RT6_NUD_SUCCEED = 1
};
@@ -521,7 +522,7 @@
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (neigh && work)
- neigh->updated = jiffies;
+ __neigh_set_probe_once(neigh);
if (neigh)
write_unlock(&neigh->lock);
@@ -577,11 +578,13 @@
#ifdef CONFIG_IPV6_ROUTER_PREF
else if (!(neigh->nud_state & NUD_FAILED))
ret = RT6_NUD_SUCCEED;
+ else
+ ret = RT6_NUD_FAIL_PROBE;
#endif
read_unlock(&neigh->lock);
} else {
ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
- RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT;
+ RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR;
}
rcu_read_unlock_bh();
@@ -618,16 +621,17 @@
goto out;
m = rt6_score_route(rt, oif, strict);
- if (m == RT6_NUD_FAIL_SOFT) {
+ if (m == RT6_NUD_FAIL_DO_RR) {
match_do_rr = true;
m = 0; /* lowest valid score */
- } else if (m < 0) {
+ } else if (m == RT6_NUD_FAIL_HARD) {
goto out;
}
if (strict & RT6_LOOKUP_F_REACHABLE)
rt6_probe(rt);
+ /* note that m can be RT6_NUD_FAIL_PROBE at this point */
if (m > *mpri) {
*do_rr = match_do_rr;
*mpri = m;