Revert "netfilter: nat: convert nat bysrc hash to rhashtable"

This reverts commit 870190a9ec9075205c0fa795a09fa931694a3ff1 as it is
not working properly.  Please move to 4.9 to get the full fix.

Reported-by: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 445b019c2078a01b6e85dcb00386228502f221d7..79bdfa332fb29d8e2b90f96124cfe1106904d973 100644 (file)
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -17,7 +17,6 @@
 #include <linux/bitops.h>
 #include <linux/compiler.h>
 #include <linux/atomic.h>
-#include <linux/rhashtable.h>
 
 #include <linux/netfilter/nf_conntrack_tcp.h>
 #include <linux/netfilter/nf_conntrack_dccp.h>
@@ -119,7 +118,7 @@ struct nf_conn {
        struct nf_ct_ext *ext;
 
 #if IS_ENABLED(CONFIG_NF_NAT)
-       struct rhash_head       nat_bysource;
+       struct hlist_node       nat_bysource;
 #endif
        /* Storage reserved for other modules, must be the last member */
        union nf_conntrack_proto proto;

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index c327a431a6f38103598b82182d463dd728f70443..02515f7ed4cceceeaa9eb974531e2ec342346d07 100644 (file)
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -1,6 +1,5 @@
 #ifndef _NF_NAT_H
 #define _NF_NAT_H
-#include <linux/rhashtable.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/nf_nat.h>
 #include <net/netfilter/nf_conntrack_tuple.h>

diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index ecee105bbada7dca884d59bc4b1647f0f34f212d..b9f466509705a72ac3a19e9d7871d368c8d012ae 100644 (file)
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -30,19 +30,17 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <linux/netfilter/nf_nat.h>
 
+static DEFINE_SPINLOCK(nf_nat_lock);
+
 static DEFINE_MUTEX(nf_nat_proto_mutex);
 static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO]
                                                __read_mostly;
 static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO]
                                                __read_mostly;
 
-struct nf_nat_conn_key {
-       const struct net *net;
-       const struct nf_conntrack_tuple *tuple;
-       const struct nf_conntrack_zone *zone;
-};
-
-static struct rhashtable nf_nat_bysource_table;
+static struct hlist_head *nf_nat_bysource __read_mostly;
+static unsigned int nf_nat_htable_size __read_mostly;
+static unsigned int nf_nat_hash_rnd __read_mostly;
 
 inline const struct nf_nat_l3proto *
 __nf_nat_l3proto_find(u8 family)
@@ -121,17 +119,19 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family)
 EXPORT_SYMBOL(nf_xfrm_me_harder);
 #endif /* CONFIG_XFRM */
 
-static u32 nf_nat_bysource_hash(const void *data, u32 len, u32 seed)
+/* We keep an extra hash for each conntrack, for fast searching. */
+static inline unsigned int
+hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
 {
-       const struct nf_conntrack_tuple *t;
-       const struct nf_conn *ct = data;
+       unsigned int hash;
+
+       get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd));
 
-       t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
        /* Original src, to ensure we map it consistently if poss. */
+       hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
+                     tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n));
 
-       seed ^= net_hash_mix(nf_ct_net(ct));
-       return jhash2((const u32 *)&t->src, sizeof(t->src) / sizeof(u32),
-                     t->dst.protonum ^ seed);
+       return reciprocal_scale(hash, nf_nat_htable_size);
 }
 
 /* Is this tuple already taken? (not by us) */
@@ -187,26 +187,6 @@ same_src(const struct nf_conn *ct,
                t->src.u.all == tuple->src.u.all);
 }
 
-static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg,
-                              const void *obj)
-{
-       const struct nf_nat_conn_key *key = arg->key;
-       const struct nf_conn *ct = obj;
-
-       return same_src(ct, key->tuple) &&
-              net_eq(nf_ct_net(ct), key->net) &&
-              nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL);
-}
-
-static struct rhashtable_params nf_nat_bysource_params = {
-       .head_offset = offsetof(struct nf_conn, nat_bysource),
-       .obj_hashfn = nf_nat_bysource_hash,
-       .obj_cmpfn = nf_nat_bysource_cmp,
-       .nelem_hint = 256,
-       .min_size = 1024,
-       .nulls_base = (1U << RHT_BASE_SHIFT),
-};
-
 /* Only called for SRC manip */
 static int
 find_appropriate_src(struct net *net,
@@ -217,23 +197,23 @@ find_appropriate_src(struct net *net,
                     struct nf_conntrack_tuple *result,
                     const struct nf_nat_range *range)
 {
+       unsigned int h = hash_by_src(net, tuple);
        const struct nf_conn *ct;
-       struct nf_nat_conn_key key = {
-               .net = net,
-               .tuple = tuple,
-               .zone = zone
-       };
-
-       ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key,
-                                   nf_nat_bysource_params);
-       if (!ct)
-               return 0;
-
-       nf_ct_invert_tuplepr(result,
-                            &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
-       result->dst = tuple->dst;
 
-       return in_range(l3proto, l4proto, result, range);
+       hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) {
+               if (same_src(ct, tuple) &&
+                   net_eq(net, nf_ct_net(ct)) &&
+                   nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) {
+                       /* Copy source part from reply tuple. */
+                       nf_ct_invert_tuplepr(result,
+                                      &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+                       result->dst = tuple->dst;
+
+                       if (in_range(l3proto, l4proto, result, range))
+                               return 1;
+               }
+       }
+       return 0;
 }
 
 /* For [FUTURE] fragmentation handling, we want the least-used
@@ -405,6 +385,7 @@ nf_nat_setup_info(struct nf_conn *ct,
                  const struct nf_nat_range *range,
                  enum nf_nat_manip_type maniptype)
 {
+       struct net *net = nf_ct_net(ct);
        struct nf_conntrack_tuple curr_tuple, new_tuple;
        struct nf_conn_nat *nat;
 
@@ -446,13 +427,16 @@ nf_nat_setup_info(struct nf_conn *ct,
        }
 
        if (maniptype == NF_NAT_MANIP_SRC) {
-               int err;
-
-               err = rhashtable_insert_fast(&nf_nat_bysource_table,
-                                            &ct->nat_bysource,
-                                            nf_nat_bysource_params);
-               if (err)
-                       return NF_DROP;
+               unsigned int srchash;
+
+               srchash = hash_by_src(net,
+                                     &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+               spin_lock_bh(&nf_nat_lock);
+               /* nf_conntrack_alter_reply might re-allocate extension aera */
+               nat = nfct_nat(ct);
+               hlist_add_head_rcu(&ct->nat_bysource,
+                                  &nf_nat_bysource[srchash]);
+               spin_unlock_bh(&nf_nat_lock);
        }
 
        /* It's done. */
@@ -569,10 +553,10 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
        if (!del_timer(&ct->timeout))
                return 1;
 
+       spin_lock_bh(&nf_nat_lock);
+       hlist_del_rcu(&ct->nat_bysource);
        ct->status &= ~IPS_NAT_DONE_MASK;
-
-       rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource,
-                              nf_nat_bysource_params);
+       spin_unlock_bh(&nf_nat_lock);
 
        add_timer(&ct->timeout);
 
@@ -704,8 +688,11 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
        if (!nat)
                return;
 
-       rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource,
-                              nf_nat_bysource_params);
+       NF_CT_ASSERT(ct->status & IPS_SRC_NAT_DONE);
+
+       spin_lock_bh(&nf_nat_lock);
+       hlist_del_rcu(&ct->nat_bysource);
+       spin_unlock_bh(&nf_nat_lock);
 }
 
 static struct nf_ct_ext_type nat_extend __read_mostly = {
@@ -840,13 +827,16 @@ static int __init nf_nat_init(void)
 {
        int ret;
 
-       ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params);
-       if (ret)
-               return ret;
+       /* Leave them the same for the moment. */
+       nf_nat_htable_size = nf_conntrack_htable_size;
+
+       nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0);
+       if (!nf_nat_bysource)
+               return -ENOMEM;
 
        ret = nf_ct_extend_register(&nat_extend);
        if (ret < 0) {
-               rhashtable_destroy(&nf_nat_bysource_table);
+               nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
                printk(KERN_ERR "nf_nat_core: Unable to register extension\n");
                return ret;
        }
@@ -870,7 +860,7 @@ static int __init nf_nat_init(void)
        return 0;
 
  cleanup_extend:
-       rhashtable_destroy(&nf_nat_bysource_table);
+       nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
        nf_ct_extend_unregister(&nat_extend);
        return ret;
 }
@@ -888,8 +878,8 @@ static void __exit nf_nat_cleanup(void)
 #endif
        for (i = 0; i < NFPROTO_NUMPROTO; i++)
                kfree(nf_nat_l4protos[i]);
-
-       rhashtable_destroy(&nf_nat_bysource_table);
+       synchronize_net();
+       nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
 }
 
 MODULE_LICENSE("GPL");