netfilter: avoid race with exp->master ct

Preparation for disconnecting the nf_conntrack_lock from the
expectations code.  Once the nf_conntrack_lock is lifted, a race
condition is exposed.

The expectations master conntrack exp->master, can race with
delete operations, as the refcnt increment happens too late in
init_conntrack().  Race is against other CPUs invoking
->destroy() (destroy_conntrack()), or nf_ct_delete() (via timeout
or early_drop()).

Avoid this race in nf_ct_find_expectation() by using atomic_inc_not_zero(),
and checking if nf_ct_is_dying() (path via nf_ct_delete()).

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 289b27901d8c906f652948eccdeda5fb962242af..92d597788d6a52039adb268f1c6c54df192881de 100644 (file)
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -902,6 +902,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
                         ct, exp);
                /* Welcome, Mr. Bond.  We've been expecting you... */
                __set_bit(IPS_EXPECTED_BIT, &ct->status);
+               /* exp->master safe, refcnt bumped in nf_ct_find_expectation */
                ct->master = exp->master;
                if (exp->helper) {
                        help = nf_ct_helper_ext_add(ct, exp->helper,
@@ -916,7 +917,6 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
                ct->secmark = exp->master->secmark;
 #endif
-               nf_conntrack_get(&ct->master->ct_general);
                NF_CT_STAT_INC(net, expect_new);
        } else {
                __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);

diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index da2f84f41777bce7de8edbbbd9d7f9bd7ee75536..f02805e0c7c5c290bfb6b375d0cac21b3ddedc71 100644 (file)
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -155,6 +155,18 @@ nf_ct_find_expectation(struct net *net, u16 zone,
        if (!nf_ct_is_confirmed(exp->master))
                return NULL;
 
+       /* Avoid race with other CPUs, that for exp->master ct, is
+        * about to invoke ->destroy(), or nf_ct_delete() via timeout
+        * or early_drop().
+        *
+        * The atomic_inc_not_zero() check tells:  If that fails, we
+        * know that the ct is being destroyed.  If it succeeds, we
+        * can be sure the ct cannot disappear underneath.
+        */
+       if (unlikely(nf_ct_is_dying(exp->master) ||
+                    !atomic_inc_not_zero(&exp->master->ct_general.use)))
+               return NULL;
+
        if (exp->flags & NF_CT_EXPECT_PERMANENT) {
                atomic_inc(&exp->use);
                return exp;
@@ -162,6 +174,8 @@ nf_ct_find_expectation(struct net *net, u16 zone,
                nf_ct_unlink_expect(exp);
                return exp;
        }
+       /* Undo exp->master refcnt increase, if del_timer() failed */
+       nf_ct_put(exp->master);
 
        return NULL;
 }