netfilter: nf_conntrack: fix a race in __nf_conntrack_confirm against nf_ct_get_next_...

This race was triggered by a 'conntrack -F' command running in parallel
to the insertion of a hash for a new connection. Losing this race led to
a dead conntrack entry effectively blocking traffic for a particular
connection until timeout or flushing the conntrack hashes again.
Now the check for an already dying connection is done inside the lock.

Signed-off-by: Joerg Marx <joerg.marx@secunet.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index dffde8e6920eb43c37184692fa6d49d054938366..3d7524fba1946d2993033f44b8330f210eaa4bb4 100644 (file)
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -61,7 +61,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
        int ret = NF_ACCEPT;
 
        if (ct && ct != &nf_conntrack_untracked) {
-               if (!nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct))
+               if (!nf_ct_is_confirmed(ct))
                        ret = __nf_conntrack_confirm(skb);
                if (likely(ret == NF_ACCEPT))
                        nf_ct_deliver_cached_events(ct);

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index b83c530c5e0a391c7f09e5ee8950884991377053..eeeb8bc73982275655e37342c214f1fa2669efb2 100644 (file)
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -424,6 +424,16 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 
        spin_lock_bh(&nf_conntrack_lock);
 
+       /* We have to check the DYING flag inside the lock to prevent
+          a race against nf_ct_get_next_corpse() possibly called from
+          user context, else we insert an already 'dead' hash, blocking
+          further use of that particular connection -JM */
+
+       if (unlikely(nf_ct_is_dying(ct))) {
+               spin_unlock_bh(&nf_conntrack_lock);
+               return NF_ACCEPT;
+       }
+
        /* See if there's one in the list already, including reverse:
           NAT could have grabbed it without realizing, since we're
           not in the hash.  If there is, we lost race. */