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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for your net-next
tree, they are:

1) Stash ctinfo 3-bit field into pointer to nf_conntrack object from
   sk_buff so we only access one single cacheline in the conntrack
   hotpath. Patchset from Florian Westphal.

2) Don't leak pointer to internal structures when exporting x_tables
   ruleset back to userspace, from Willem DeBruijn. This includes new
   helper functions to copy data to userspace such as xt_data_to_user()
   as well as conversions of our ip_tables, ip6_tables and arp_tables
   clients to use it. Not surprinsingly, ebtables requires an ad-hoc
   update. There is also a new field in x_tables extensions to indicate
   the amount of bytes that we copy to userspace.

3) Add nf_log_all_netns sysctl: This new knob allows you to enable
   logging via nf_log infrastructure for all existing netnamespaces.
   Given the effort to provide pernet syslog has been discontinued,
   let's provide a way to restore logging using netfilter kernel logging
   facilities in trusted environments. Patch from Michal Kubecek.

4) Validate SCTP checksum from conntrack helper, from Davide Caratti.

5) Merge UDPlite conntrack and NAT helpers into UDP, this was mostly
   a copy&paste from the original helper, from Florian Westphal.

6) Reset netfilter state when duplicating packets, also from Florian.

7) Remove unnecessary check for broadcast in IPv6 in pkttype match and
   nft_meta, from Liping Zhang.

8) Add missing code to deal with loopback packets from nft_meta when
   used by the netdev family, also from Liping.

9) Several cleanups on nf_tables, one to remove unnecessary check from
   the netlink control plane path to add table, set and stateful objects
   and code consolidation when unregister chain hooks, from Gao Feng.

10) Fix harmless reference counter underflow in IPVS that, however,
    results in problems with the introduction of the new refcount_t
    type, from David Windsor.

11) Enable LIBCRC32C from nf_ct_sctp instead of nf_nat_sctp,
    from Davide Caratti.

12) Missing documentation on nf_tables uapi header, from Liping Zhang.

13) Use rb_entry() helper in xt_connlimit, from Geliang Tang.
====================

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

1 files changed, 45 insertions, 28 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 4e8083c5e01d..071b97fcbefb 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -350,16 +350,31 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
 	spin_unlock(&pcpu->lock);
 }
 
+#define NFCT_ALIGN(len)	(((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK)
+
 /* Released via destroy_conntrack() */
 struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 				 const struct nf_conntrack_zone *zone,
 				 gfp_t flags)
 {
-	struct nf_conn *tmpl;
+	struct nf_conn *tmpl, *p;
 
-	tmpl = kzalloc(sizeof(*tmpl), flags);
-	if (tmpl == NULL)
-		return NULL;
+	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) {
+		tmpl = kzalloc(sizeof(*tmpl) + NFCT_INFOMASK, flags);
+		if (!tmpl)
+			return NULL;
+
+		p = tmpl;
+		tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
+		if (tmpl != p) {
+			tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
+			tmpl->proto.tmpl_padto = (char *)tmpl - (char *)p;
+		}
+	} else {
+		tmpl = kzalloc(sizeof(*tmpl), flags);
+		if (!tmpl)
+			return NULL;
+	}
 
 	tmpl->status = IPS_TEMPLATE;
 	write_pnet(&tmpl->ct_net, net);
@@ -374,7 +389,11 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl)
 {
 	nf_ct_ext_destroy(tmpl);
 	nf_ct_ext_free(tmpl);
-	kfree(tmpl);
+
+	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK)
+		kfree((char *)tmpl - tmpl->proto.tmpl_padto);
+	else
+		kfree(tmpl);
 }
 EXPORT_SYMBOL_GPL(nf_ct_tmpl_free);
 
@@ -686,12 +705,12 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
 	    !nfct_nat(ct) &&
 	    !nf_ct_is_dying(ct) &&
 	    atomic_inc_not_zero(&ct->ct_general.use)) {
-		nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct);
-		nf_conntrack_put(skb->nfct);
-		/* Assign conntrack already in hashes to this skbuff. Don't
-		 * modify skb->nfctinfo to ensure consistent stateful filtering.
-		 */
-		skb->nfct = &ct->ct_general;
+		enum ip_conntrack_info oldinfo;
+		struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);
+
+		nf_ct_acct_merge(ct, ctinfo, loser_ct);
+		nf_conntrack_put(&loser_ct->ct_general);
+		nf_ct_set(skb, ct, oldinfo);
 		return NF_ACCEPT;
 	}
 	NF_CT_STAT_INC(net, drop);
@@ -1218,7 +1237,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
 }
 
-/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */
+/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */
 static inline struct nf_conn *
 resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  struct sk_buff *skb,
@@ -1277,8 +1296,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		}
 		*set_reply = 0;
 	}
-	skb->nfct = &ct->ct_general;
-	skb->nfctinfo = *ctinfo;
+	nf_ct_set(skb, ct, *ctinfo);
 	return ct;
 }
 
@@ -1286,7 +1304,7 @@ unsigned int
 nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 		struct sk_buff *skb)
 {
-	struct nf_conn *ct, *tmpl = NULL;
+	struct nf_conn *ct, *tmpl;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_l3proto *l3proto;
 	struct nf_conntrack_l4proto *l4proto;
@@ -1296,14 +1314,14 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	int set_reply = 0;
 	int ret;
 
-	if (skb->nfct) {
+	tmpl = nf_ct_get(skb, &ctinfo);
+	if (tmpl) {
 		/* Previously seen (loopback or untracked)?  Ignore. */
-		tmpl = (struct nf_conn *)skb->nfct;
 		if (!nf_ct_is_template(tmpl)) {
 			NF_CT_STAT_INC_ATOMIC(net, ignore);
 			return NF_ACCEPT;
 		}
-		skb->nfct = NULL;
+		skb->_nfct = 0;
 	}
 
 	/* rcu_read_lock()ed by nf_hook_thresh */
@@ -1324,8 +1342,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	 * inverse of the return code tells to the netfilter
 	 * core what to do with the packet. */
 	if (l4proto->error != NULL) {
-		ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo,
-				     pf, hooknum);
+		ret = l4proto->error(net, tmpl, skb, dataoff, pf, hooknum);
 		if (ret <= 0) {
 			NF_CT_STAT_INC_ATOMIC(net, error);
 			NF_CT_STAT_INC_ATOMIC(net, invalid);
@@ -1333,7 +1350,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			goto out;
 		}
 		/* ICMP[v6] protocol trackers may assign one conntrack. */
-		if (skb->nfct)
+		if (skb->_nfct)
 			goto out;
 	}
 repeat:
@@ -1353,7 +1370,7 @@ repeat:
 		goto out;
 	}
 
-	NF_CT_ASSERT(skb->nfct);
+	NF_CT_ASSERT(skb_nfct(skb));
 
 	/* Decide what timeout policy we want to apply to this flow. */
 	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
@@ -1363,8 +1380,8 @@ repeat:
 		/* Invalid: inverse of the return code tells
 		 * the netfilter core what to do */
 		pr_debug("nf_conntrack_in: Can't track with proto module\n");
-		nf_conntrack_put(skb->nfct);
-		skb->nfct = NULL;
+		nf_conntrack_put(&ct->ct_general);
+		skb->_nfct = 0;
 		NF_CT_STAT_INC_ATOMIC(net, invalid);
 		if (ret == -NF_DROP)
 			NF_CT_STAT_INC_ATOMIC(net, drop);
@@ -1522,9 +1539,8 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
 		ctinfo = IP_CT_RELATED;
 
 	/* Attach to new skbuff, and increment count */
-	nskb->nfct = &ct->ct_general;
-	nskb->nfctinfo = ctinfo;
-	nf_conntrack_get(nskb->nfct);
+	nf_ct_set(nskb, ct, ctinfo);
+	nf_conntrack_get(skb_nfct(nskb));
 }
 
 /* Bring out ya dead! */
@@ -1860,7 +1876,8 @@ int nf_conntrack_init_start(void)
 	nf_conntrack_max = max_factor * nf_conntrack_htable_size;
 
 	nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
-						sizeof(struct nf_conn), 0,
+						sizeof(struct nf_conn),
+						NFCT_INFOMASK + 1,
 						SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
 	if (!nf_conntrack_cachep)
 		goto err_cachep;