aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/nf_conntrack_core.c
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2014-02-09 14:20:00 -0800
committerDavid S. Miller <davem@davemloft.net>2014-02-09 14:20:00 -0800
commitf41f03196041f91acad2b6d2b3e1f800aed60100 (patch)
tree2981088eb28919bf32e8040b0ad73beead0ec815 /net/netfilter/nf_conntrack_core.c
parent4a5ab4e224288403b0b4b6b8c4d339323150c312 (diff)
parent6d8c00d58e9e484fdc41aaaf62e5d8364efe375a (diff)
downloadlinux-stericsson-f41f03196041f91acad2b6d2b3e1f800aed60100.tar.gz
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf
Pablo Neira Ayuso says: ==================== Netfilter/nftables/IPVS fixes for net The following patchset contains Netfilter/IPVS fixes, mostly nftables fixes, most relevantly they are: * Fix a crash in the h323 conntrack NAT helper due to expectation list corruption, from Alexey Dobriyan. * A couple of RCU race fixes for conntrack, one manifests by hitting BUG_ON in nf_nat_setup_info() and the destroy path, patches from Andrey Vagin and me. * Dump direction attribute in nft_ct only if it is set, from Arturo Borrero. * Fix IPVS bug in its own connection tracking system that may lead to copying only 4 bytes of the IPv6 address when initializing the ip_vs_conn object, from Michal Kubecek. * Fix -EBUSY errors in nftables when deleting the rules, chain and tables in a row due mixture of asynchronous and synchronous object releasing, from me. * Three fixes for the nf_tables set infrastructure when using intervals and mappings, from me. * Four patches to fixing the nf_tables log, reject and ct expressions from the new inet table, from Patrick McHardy. * Fix memory overrun in the map that is used to dynamically allocate names from anonymous sets, also from Patrick. * Fix a potential oops if you dump a set with NFPROTO_UNSPEC and a table name, from Patrick McHardy. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/netfilter/nf_conntrack_core.c')
-rw-r--r--net/netfilter/nf_conntrack_core.c55
1 files changed, 46 insertions, 9 deletions
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 8824ed0ccc9c..356bef519fe5 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -312,6 +312,21 @@ static void death_by_timeout(unsigned long ul_conntrack)
nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
}
+static inline bool
+nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
+ const struct nf_conntrack_tuple *tuple,
+ u16 zone)
+{
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+ /* A conntrack can be recreated with the equal tuple,
+ * so we need to check that the conntrack is confirmed
+ */
+ return nf_ct_tuple_equal(tuple, &h->tuple) &&
+ nf_ct_zone(ct) == zone &&
+ nf_ct_is_confirmed(ct);
+}
+
/*
* Warning :
* - Caller must take a reference on returned object
@@ -333,8 +348,7 @@ ____nf_conntrack_find(struct net *net, u16 zone,
local_bh_disable();
begin:
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
- if (nf_ct_tuple_equal(tuple, &h->tuple) &&
- nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
+ if (nf_ct_key_equal(h, tuple, zone)) {
NF_CT_STAT_INC(net, found);
local_bh_enable();
return h;
@@ -372,8 +386,7 @@ begin:
!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
else {
- if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
- nf_ct_zone(ct) != zone)) {
+ if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
nf_ct_put(ct);
goto begin;
}
@@ -435,7 +448,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
goto out;
add_timer(&ct->timeout);
- nf_conntrack_get(&ct->ct_general);
+ smp_wmb();
+ /* The caller holds a reference to this object */
+ atomic_set(&ct->ct_general.use, 2);
__nf_conntrack_hash_insert(ct, hash, repl_hash);
NF_CT_STAT_INC(net, insert);
spin_unlock_bh(&nf_conntrack_lock);
@@ -449,6 +464,21 @@ out:
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
+/* deletion from this larval template list happens via nf_ct_put() */
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
+{
+ __set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+ nf_conntrack_get(&tmpl->ct_general);
+
+ spin_lock_bh(&nf_conntrack_lock);
+ /* Overload tuple linked list to put us in template list. */
+ hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &net->ct.tmpl);
+ spin_unlock_bh(&nf_conntrack_lock);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
+
/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
@@ -720,11 +750,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
nf_ct_zone->id = zone;
}
#endif
- /*
- * changes to lookup keys must be done before setting refcnt to 1
+ /* Because we use RCU lookups, we set ct_general.use to zero before
+ * this is inserted in any list.
*/
- smp_wmb();
- atomic_set(&ct->ct_general.use, 1);
+ atomic_set(&ct->ct_general.use, 0);
return ct;
#ifdef CONFIG_NF_CONNTRACK_ZONES
@@ -748,6 +777,11 @@ void nf_conntrack_free(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
+ /* A freed object has refcnt == 0, that's
+ * the golden rule for SLAB_DESTROY_BY_RCU
+ */
+ NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+
nf_ct_ext_destroy(ct);
nf_ct_ext_free(ct);
kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
@@ -843,6 +877,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
NF_CT_STAT_INC(net, new);
}
+ /* Now it is inserted into the unconfirmed list, bump refcount */
+ nf_conntrack_get(&ct->ct_general);
+
/* Overload tuple linked list to put us in unconfirmed list. */
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.unconfirmed);