netfilter: merge ctinfo into nfct pointer storage area

After this change conntrack operations (lookup, creation, matching from
ruleset) only access one instead of two sk_buff cache lines.

This works for normal conntracks because those are allocated from a slab
that guarantees hw cacheline or 8byte alignment (whatever is larger)
so the 3 bits needed for ctinfo won't overlap with nf_conn addresses.

Template allocation now does manual address alignment (see previous change)
on arches that don't have sufficent kmalloc min alignment.

Some spots intentionally use skb->_nfct instead of skb_nfct() helpers,
this is to avoid undoing the skb_nfct() use when we remove untracked
conntrack object in the future.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 276431e..ac0bc08 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -585,7 +585,6 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1,
  *	@cloned: Head may be cloned (check refcnt to be sure)
  *	@ip_summed: Driver fed us an IP checksum
  *	@nohdr: Payload reference only, must not modify header
- *	@nfctinfo: Relationship of this skb to the connection
  *	@pkt_type: Packet class
  *	@fclone: skbuff clone status
  *	@ipvs_property: skbuff is owned by ipvs
@@ -594,7 +593,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1,
  *	@nf_trace: netfilter packet trace flag
  *	@protocol: Packet protocol from driver
  *	@destructor: Destruct function
- *	@nfct: Associated connection, if any
+ *	@_nfct: Associated connection, if any (with nfctinfo bits)
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
@@ -668,7 +667,7 @@ struct sk_buff {
 	struct	sec_path	*sp;
 #endif
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-	struct nf_conntrack	*nfct;
+	unsigned long		 _nfct;
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	struct nf_bridge_info	*nf_bridge;
@@ -721,7 +720,6 @@ struct sk_buff {
 	__u8			pkt_type:3;
 	__u8			pfmemalloc:1;
 	__u8			ignore_df:1;
-	__u8			nfctinfo:3;
 
 	__u8			nf_trace:1;
 	__u8			ip_summed:2;
@@ -836,6 +834,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb)
 #define SKB_DST_NOREF	1UL
 #define SKB_DST_PTRMASK	~(SKB_DST_NOREF)
 
+#define SKB_NFCT_PTRMASK	~(7UL)
 /**
  * skb_dst - returns skb dst_entry
  * @skb: buffer
@@ -3556,7 +3555,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr,
 static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb)
 {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-	return skb->nfct;
+	return (void *)(skb->_nfct & SKB_NFCT_PTRMASK);
 #else
 	return NULL;
 #endif
@@ -3590,8 +3589,8 @@ static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge)
 static inline void nf_reset(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-	nf_conntrack_put(skb->nfct);
-	skb->nfct = NULL;
+	nf_conntrack_put(skb_nfct(skb));
+	skb->_nfct = 0;
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
@@ -3611,10 +3610,8 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 			     bool copy)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-	dst->nfct = src->nfct;
-	nf_conntrack_get(src->nfct);
-	if (copy)
-		dst->nfctinfo = src->nfctinfo;
+	dst->_nfct = src->_nfct;
+	nf_conntrack_get(skb_nfct(src));
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	dst->nf_bridge  = src->nf_bridge;
@@ -3629,7 +3626,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-	nf_conntrack_put(dst->nfct);
+	nf_conntrack_put(skb_nfct(dst));
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(dst->nf_bridge);