Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter/IPVS updates for net-next,
they are:

1) Count pre-established connections as active in "least connection"
   schedulers such that pre-established connections to avoid overloading
   backend servers on peak demands, from Michal Kubecek via Simon Horman.

2) Address a race condition when resizing the conntrack table by caching
   the bucket size when fulling iterating over the hashtable in these
   three possible scenarios: 1) dump via /proc/net/nf_conntrack,
   2) unlinking userspace helper and 3) unlinking custom conntrack timeout.
   From Liping Zhang.

3) Revisit early_drop() path to perform lockless traversal on conntrack
   eviction under stress, use del_timer() as synchronization point to
   avoid two CPUs evicting the same entry, from Florian Westphal.

4) Move NAT hlist_head to nf_conn object, this simplifies the existing
   NAT extension and it doesn't increase size since recent patches to
   align nf_conn, from Florian.

5) Use rhashtable for the by-source NAT hashtable, also from Florian.

6) Don't allow --physdev-is-out from OUTPUT chain, just like
   --physdev-out is not either, from Hangbin Liu.

7) Automagically set on nf_conntrack counters if the user tries to
   match ct bytes/packets from nftables, from Liping Zhang.

8) Remove possible_net_t fields in nf_tables set objects since we just
   simply pass the net pointer to the backend set type implementations.

9) Fix possible off-by-one in h323, from Toby DiPasquale.

10) early_drop() may be called from ctnetlink patch, so we must hold
    rcu read size lock from them too, this amends Florian's patch #3
    coming in this batch, from Liping Zhang.

11) Use binary search to validate jump offset in x_tables, this
    addresses the O(n!) validation that was introduced recently
    resolve security issues with unpriviledge namespaces, from Florian.

12) Fix reference leak to connlabel in error path of nft_ct, from Zhang.

13) Three updates for nft_log: Fix log prefix leak in error path. Bail
    out on loglevel larger than debug in nft_log and set on the new
    NF_LOG_F_COPY_LEN flag when snaplen is specified. Again from Zhang.

14) Allow to filter rule dumps in nf_tables based on table and chain
    names.

15) Simplify connlabel to always use 128 bits to store labels and
    get rid of unused function in xt_connlabel, from Florian.

16) Replace set_expect_timeout() by mod_timer() from the h323 conntrack
    helper, by Gao Feng.

17) Put back x_tables module reference in nft_compat on error, from
    Liping Zhang.

18) Add a reference count to the x_tables extensions cache in
    nft_compat, so we can remove them when unused and avoid a crash
    if the extensions are rmmod, again from Zhang.
====================

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

1 files changed, 70 insertions, 6 deletions

diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 3a1a88b9bafa..b989b81ac156 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -409,6 +409,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	struct nf_conntrack_expect *exp;
 	const struct hlist_node *next;
 	const struct hlist_nulls_node *nn;
+	unsigned int last_hsize;
+	spinlock_t *lock;
 	struct net *net;
 	unsigned int i;
 
@@ -446,18 +448,80 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	rtnl_unlock();
 
 	local_bh_disable();
-	for (i = 0; i < nf_conntrack_htable_size; i++) {
-		nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
-		if (i < nf_conntrack_htable_size) {
-			hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode)
-				unhelp(h, me);
+restart:
+	last_hsize = nf_conntrack_htable_size;
+	for (i = 0; i < last_hsize; i++) {
+		lock = &nf_conntrack_locks[i % CONNTRACK_LOCKS];
+		nf_conntrack_lock(lock);
+		if (last_hsize != nf_conntrack_htable_size) {
+			spin_unlock(lock);
+			goto restart;
 		}
-		spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+		hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode)
+			unhelp(h, me);
+		spin_unlock(lock);
 	}
 	local_bh_enable();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 
+void nf_ct_helper_init(struct nf_conntrack_helper *helper,
+		       u16 l3num, u16 protonum, const char *name,
+		       u16 default_port, u16 spec_port, u32 id,
+		       const struct nf_conntrack_expect_policy *exp_pol,
+		       u32 expect_class_max, u32 data_len,
+		       int (*help)(struct sk_buff *skb, unsigned int protoff,
+				   struct nf_conn *ct,
+				   enum ip_conntrack_info ctinfo),
+		       int (*from_nlattr)(struct nlattr *attr,
+					  struct nf_conn *ct),
+		       struct module *module)
+{
+	helper->tuple.src.l3num = l3num;
+	helper->tuple.dst.protonum = protonum;
+	helper->tuple.src.u.all = htons(spec_port);
+	helper->expect_policy = exp_pol;
+	helper->expect_class_max = expect_class_max;
+	helper->data_len = data_len;
+	helper->help = help;
+	helper->from_nlattr = from_nlattr;
+	helper->me = module;
+
+	if (spec_port == default_port)
+		snprintf(helper->name, sizeof(helper->name), "%s", name);
+	else
+		snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id);
+}
+EXPORT_SYMBOL_GPL(nf_ct_helper_init);
+
+int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper,
+				  unsigned int n)
+{
+	unsigned int i;
+	int err = 0;
+
+	for (i = 0; i < n; i++) {
+		err = nf_conntrack_helper_register(&helper[i]);
+		if (err < 0)
+			goto err;
+	}
+
+	return err;
+err:
+	if (i > 0)
+		nf_conntrack_helpers_unregister(helper, i);
+	return err;
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register);
+
+void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper,
+				unsigned int n)
+{
+	while (n-- > 0)
+		nf_conntrack_helper_unregister(&helper[n]);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister);
+
 static struct nf_ct_ext_type helper_extend __read_mostly = {
 	.len	= sizeof(struct nf_conn_help),
 	.align	= __alignof__(struct nf_conn_help),