Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf into netfilter

Pablo Neira Ayuso says:

====================
The following patchset contains late netfilter fixes for your net
tree, they are:

* Don't drop segmented TCP packets in the SIP helper, we've got reports
  from users that this was breaking communications when the SIP phone
  messages are larger than the MTU, from Patrick McHardy.

* Fix refcount leak in the ipset list set, from Jozsef Kadlecsik.

* On hash set resizing, the nomatch flag was lost, thus entirely inverting
  the logic of the set matching, from Jozsef Kadlecsik.

* Fix crash on NAT modules removal. Timer expiration may race with the
  module cleanup exit path while deleting conntracks, from Florian
  Westphal.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 115 insertions, 51 deletions

diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
index 01d25e6fc792..0214c4c146fa 100644
--- a/include/linux/netfilter/ipset/ip_set_ahash.h
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -291,6 +291,7 @@ ip_set_hash_destroy(struct ip_set *set)
 #define type_pf_data_tlist      TOKEN(TYPE, PF, _data_tlist)
 #define type_pf_data_next       TOKEN(TYPE, PF, _data_next)
 #define type_pf_data_flags      TOKEN(TYPE, PF, _data_flags)
+#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags)
 #ifdef IP_SET_HASH_WITH_NETS
 #define type_pf_data_match      TOKEN(TYPE, PF, _data_match)
 #else
@@ -385,9 +386,9 @@ type_pf_resize(struct ip_set *set, bool retried)
         struct ip_set_hash *h = set->data;
         struct htable *t, *orig = h->table;
         u8 htable_bits = orig->htable_bits;
-        const struct type_pf_elem *data;
+        struct type_pf_elem *data;
         struct hbucket *n, *m;
-        u32 i, j;
+        u32 i, j, flags = 0;
         int ret;
 
 retry:
@@ -412,9 +413,16 @@ retry:
                 n = hbucket(orig, i);
                 for (j = 0; j < n->pos; j++) {
                         data = ahash_data(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+                        flags = 0;
+                        type_pf_data_reset_flags(data, &flags);
+#endif
                         m = hbucket(t, HKEY(data, h->initval, htable_bits));
-                        ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0);
+                        ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags);
                         if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+                                type_pf_data_flags(data, flags);
+#endif
                                 read_unlock_bh(&set->lock);
                                 ahash_destroy(t);
                                 if (ret == -EAGAIN)
@@ -836,9 +844,9 @@ type_pf_tresize(struct ip_set *set, bool retried)
         struct ip_set_hash *h = set->data;
         struct htable *t, *orig = h->table;
         u8 htable_bits = orig->htable_bits;
-        const struct type_pf_elem *data;
+        struct type_pf_elem *data;
         struct hbucket *n, *m;
-        u32 i, j;
+        u32 i, j, flags = 0;
         int ret;
 
         /* Try to cleanup once */
@@ -873,10 +881,17 @@ retry:
                 n = hbucket(orig, i);
                 for (j = 0; j < n->pos; j++) {
                         data = ahash_tdata(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+                        flags = 0;
+                        type_pf_data_reset_flags(data, &flags);
+#endif
                         m = hbucket(t, HKEY(data, h->initval, htable_bits));
-                        ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0,
-                                                ip_set_timeout_get(type_pf_data_timeout(data)));
+                        ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags,
+                                ip_set_timeout_get(type_pf_data_timeout(data)));
                         if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+                                type_pf_data_flags(data, flags);
+#endif
                                 read_unlock_bh(&set->lock);
                                 ahash_destroy(t);
                                 if (ret == -EAGAIN)
@@ -1187,6 +1202,7 @@ type_pf_gc_init(struct ip_set *set)
 #undef type_pf_data_tlist
 #undef type_pf_data_next
 #undef type_pf_data_flags
+#undef type_pf_data_reset_flags
 #undef type_pf_data_match
 
 #undef type_pf_elem
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index f2627226a087..10a30b4fc7db 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -104,6 +104,15 @@ hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags)
         dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
+}
+
 static inline int
 hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem)
 {
@@ -414,6 +423,15 @@ hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags)
         dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
+}
+
 static inline int
 hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem)
 {
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 4b677cf6bf7d..d6a59154d710 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -87,7 +87,16 @@ hash_net4_data_copy(struct hash_net4_elem *dst,
 static inline void
 hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags)
 {
-        dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+        dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_net4_data_reset_flags(struct hash_net4_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
 }
 
 static inline int
@@ -308,7 +317,16 @@ hash_net6_data_copy(struct hash_net6_elem *dst,
 static inline void
 hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags)
 {
-        dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+        dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_net6_data_reset_flags(struct hash_net6_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
 }
 
 static inline int
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 6ba985f1c96f..f2b0a3c30130 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -198,7 +198,16 @@ hash_netiface4_data_copy(struct hash_netiface4_elem *dst,
 static inline void
 hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags)
 {
-        dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+        dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netiface4_data_reset_flags(struct hash_netiface4_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
 }
 
 static inline int
@@ -494,7 +503,7 @@ hash_netiface6_data_copy(struct hash_netiface6_elem *dst,
 static inline void
 hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags)
 {
-        dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+        dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
 static inline int
@@ -504,6 +513,15 @@ hash_netiface6_data_match(const struct hash_netiface6_elem *elem)
 }
 
 static inline void
+hash_netiface6_data_reset_flags(struct hash_netiface6_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
+}
+
+static inline void
 hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem)
 {
         elem->elem = 0;
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index af20c0c5ced2..349deb672a2d 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -104,6 +104,15 @@ hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags)
         dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_netport4_data_reset_flags(struct hash_netport4_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
+}
+
 static inline int
 hash_netport4_data_match(const struct hash_netport4_elem *elem)
 {
@@ -375,6 +384,15 @@ hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags)
         dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_netport6_data_reset_flags(struct hash_netport6_elem *dst, u32 *flags)
+{
+        if (dst->nomatch) {
+                *flags = IPSET_FLAG_NOMATCH;
+                dst->nomatch = 0;
+        }
+}
+
 static inline int
 hash_netport6_data_match(const struct hash_netport6_elem *elem)
 {
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 8371c2bac2e4..09c744aa8982 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -174,9 +174,13 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id,
 {
         const struct set_elem *e = list_set_elem(map, i);
 
-        if (i == map->size - 1 && e->id != IPSET_INVALID_ID)
-                /* Last element replaced: e.g. add new,before,last */
-                ip_set_put_byindex(e->id);
+        if (e->id != IPSET_INVALID_ID) {
+                const struct set_elem *x = list_set_elem(map, map->size - 1);
+
+                /* Last element replaced or pushed off */
+                if (x->id != IPSET_INVALID_ID)
+                        ip_set_put_byindex(x->id);
+        }
         if (with_timeout(map->timeout))
                 list_elem_tadd(map, i, id, ip_set_timeout_set(timeout));
         else
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 0e7d423324c3..e0c4373b4747 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1593,10 +1593,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
                 end += strlen("\r\n\r\n") + clen;
 
                 msglen = origlen = end - dptr;
-                if (msglen > datalen) {
-                        nf_ct_helper_log(skb, ct, "incomplete/bad SIP message");
-                        return NF_DROP;
-                }
+                if (msglen > datalen)
+                        return NF_ACCEPT;
 
                 ret = process_sip_msg(skb, ct, protoff, dataoff,
                                       &dptr, &msglen);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 8d5769c6d16e..ad24be070e53 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -467,33 +467,22 @@ EXPORT_SYMBOL_GPL(nf_nat_packet);
 struct nf_nat_proto_clean {
         u8      l3proto;
         u8      l4proto;
-        bool    hash;
 };
 
-/* Clear NAT section of all conntracks, in case we're loaded again. */
-static int nf_nat_proto_clean(struct nf_conn *i, void *data)
+/* kill conntracks with affected NAT section */
+static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 {
         const struct nf_nat_proto_clean *clean = data;
         struct nf_conn_nat *nat = nfct_nat(i);
 
         if (!nat)
                 return 0;
-        if (!(i->status & IPS_SRC_NAT_DONE))
-                return 0;
+
         if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) ||
             (clean->l4proto && nf_ct_protonum(i) != clean->l4proto))
                 return 0;
 
-        if (clean->hash) {
-                spin_lock_bh(&nf_nat_lock);
-                hlist_del_rcu(&nat->bysource);
-                spin_unlock_bh(&nf_nat_lock);
-        } else {
-                memset(nat, 0, sizeof(*nat));
-                i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK |
-                               IPS_SEQ_ADJUST);
-        }
-        return 0;
+        return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
@@ -505,16 +494,8 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
         struct net *net;
 
         rtnl_lock();
-        /* Step 1 - remove from bysource hash */
-        clean.hash = true;
         for_each_net(net)
-                nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
-        synchronize_rcu();
-
-        /* Step 2 - clean NAT section */
-        clean.hash = false;
-        for_each_net(net)
-                nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
+                nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean);
         rtnl_unlock();
 }
 
@@ -526,16 +507,9 @@ static void nf_nat_l3proto_clean(u8 l3proto)
         struct net *net;
 
         rtnl_lock();
-        /* Step 1 - remove from bysource hash */
-        clean.hash = true;
-        for_each_net(net)
-                nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
-        synchronize_rcu();
 
-        /* Step 2 - clean NAT section */
-        clean.hash = false;
         for_each_net(net)
-                nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
+                nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean);
         rtnl_unlock();
 }
 
@@ -773,7 +747,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
         struct nf_nat_proto_clean clean = {};
 
-        nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean);
+        nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean);
         synchronize_rcu();
         nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }