[NETFILTER]: reduce netfilter sk_buff enlargement

As discussed at netconf'05, we're trying to save every bit in sk_buff.
The patch below makes sk_buff 8 bytes smaller.  I did some basic
testing on my notebook and it seems to work.

The only real in-tree user of nfcache was IPVS, who only needs a
single bit.  Unfortunately I couldn't find some other free bit in
sk_buff to stuff that bit into, so I introduced a separate field for
them.  Maybe the IPVS guys can resolve that to further save space.

Initially I wanted to shrink pkt_type to three bits (PACKET_HOST and
alike are only 6 values defined), but unfortunately the bluetooth code
overloads pkt_type :(

The conntrack-event-api (out-of-tree) uses nfcache, but Rusty just
came up with a way how to do it without any skb fields, so it's safe
to remove it.

- remove all never-implemented 'nfcache' code
- don't have ipvs code abuse 'nfcache' field. currently get's their own
  compile-conditional skb->ipvs_property field.  IPVS maintainers can
  decide to move this bit elswhere, but nfcache needs to die.
- remove skb->nfcache field to save 4 bytes
- move skb->nfctinfo into three unused bits to save further 4 bytes

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netfilter.h

@@ -21,10 +21,13 @@
 #define NF_STOP 5
 #define NF_MAX_VERDICT NF_STOP
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* Generic cache responses from hook functions.
    <= 0x2000 is used for protocol-flags. */
 #define NFC_UNKNOWN 0x4000
 #define NFC_ALTERED 0x8000
+#endif
 
 #ifdef __KERNEL__
 #include <linux/config.h>

include/linux/netfilter_decnet.h

@@ -9,6 +9,8 @@
 
 #include <linux/netfilter.h>
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* IP Cache bits. */
 /* Src IP address. */
 #define NFC_DN_SRC		0x0001
@@ -18,6 +20,7 @@
 #define NFC_DN_IF_IN		0x0004
 /* Output device. */
 #define NFC_DN_IF_OUT		0x0008
+#endif /* ! __KERNEL__ */
 
 /* DECnet Hooks */
 /* After promisc drops, checksum checks. */

include/linux/netfilter_ipv4.h

@@ -8,6 +8,8 @@
 #include <linux/config.h>
 #include <linux/netfilter.h>
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* IP Cache bits. */
 /* Src IP address. */
 #define NFC_IP_SRC		0x0001
@@ -35,6 +37,7 @@
 #define NFC_IP_DST_PT		0x0400
 /* Something else about the proto */
 #define NFC_IP_PROTO_UNKNOWN	0x2000
+#endif /* ! __KERNEL__ */
 
 /* IP Hooks */
 /* After promisc drops, checksum checks. */

include/linux/netfilter_ipv6.h

@@ -10,6 +10,8 @@
 
 #include <linux/netfilter.h>
 
+/* only for userspace compatibility */
+#ifndef __KERNEL__
 /* IP Cache bits. */
 /* Src IP address. */
 #define NFC_IP6_SRC              0x0001
@@ -38,6 +40,7 @@
 #define NFC_IP6_DST_PT           0x0400
 /* Something else about the proto */
 #define NFC_IP6_PROTO_UNKNOWN    0x2000
+#endif /* ! __KERNEL__ */
 
 
 /* IP6 Hooks */

include/linux/skbuff.h

@@ -190,7 +190,6 @@ struct skb_shared_info {
  *	@end: End pointer
  *	@destructor: Destruct function
  *	@nfmark: Can be used for communication between hooks
- *	@nfcache: Cache info
  *	@nfct: Associated connection, if any
  *	@nfctinfo: Relationship of this skb to the connection
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
@@ -252,17 +251,18 @@ struct sk_buff {
 	__u8			local_df:1,
 				cloned:1,
 				ip_summed:2,
-				nohdr:1;
+				nohdr:1,
-				/* 3 bits spare */
+				nfctinfo:3;
 	__u8			pkt_type;
 	__be16			protocol;
 
 	void			(*destructor)(struct sk_buff *skb);
 #ifdef CONFIG_NETFILTER
 	__u32			nfmark;
-	__u32			nfcache;
-	__u32			nfctinfo;
 	struct nf_conntrack	*nfct;
+#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+	__u8			ipvs_property:1;
+#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif

net/bridge/netfilter/ebt_mark.c

@@ -23,10 +23,9 @@ static int ebt_target_mark(struct sk_buff **pskb, unsigned int hooknr,
 {
 	struct ebt_mark_t_info *info = (struct ebt_mark_t_info *)data;
 
-	if ((*pskb)->nfmark != info->mark) {
+	if ((*pskb)->nfmark != info->mark)
 		(*pskb)->nfmark = info->mark;
-		(*pskb)->nfcache |= NFC_ALTERED;
+
-	}
 	return info->target;
 }
 

net/core/skbuff.c

@@ -361,7 +361,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, unsigned int __nocast gfp_mask)
 	n->destructor = NULL;
 #ifdef CONFIG_NETFILTER
 	C(nfmark);
-	C(nfcache);
 	C(nfct);
 	nf_conntrack_get(skb->nfct);
 	C(nfctinfo);
@@ -424,7 +423,6 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->destructor = NULL;
 #ifdef CONFIG_NETFILTER
 	new->nfmark	= old->nfmark;
-	new->nfcache	= old->nfcache;
 	new->nfct	= old->nfct;
 	nf_conntrack_get(old->nfct);
 	new->nfctinfo	= old->nfctinfo;

net/ipv4/ip_output.c

@@ -392,7 +392,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 #endif
 #ifdef CONFIG_NETFILTER
 	to->nfmark = from->nfmark;
-	to->nfcache = from->nfcache;
 	/* Connection association is same as pre-frag packet */
 	nf_conntrack_put(to->nfct);
 	to->nfct = from->nfct;

net/ipv4/ipvs/ip_vs_core.c

@@ -22,6 +22,7 @@
  *
  * Changes:
  *	Paul `Rusty' Russell		properly handle non-linear skbs
+ *	Harald Welte			don't use nfcache
  *
  */
 
@@ -529,7 +530,7 @@ static unsigned int ip_vs_post_routing(unsigned int hooknum,
 				       const struct net_device *out,
 				       int (*okfn)(struct sk_buff *))
 {
-	if (!((*pskb)->nfcache & NFC_IPVS_PROPERTY))
+	if (!((*pskb)->ipvs_property))
 		return NF_ACCEPT;
 
 	/* The packet was sent from IPVS, exit this chain */
@@ -701,7 +702,7 @@ static int ip_vs_out_icmp(struct sk_buff **pskb, int *related)
 	/* do the statistics and put it back */
 	ip_vs_out_stats(cp, skb);
 
-	skb->nfcache |= NFC_IPVS_PROPERTY;
+	skb->ipvs_property = 1;
 	verdict = NF_ACCEPT;
 
   out:
@@ -739,7 +740,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
 
 	EnterFunction(11);
 
-	if (skb->nfcache & NFC_IPVS_PROPERTY)
+	if (skb->ipvs_property)
 		return NF_ACCEPT;
 
 	iph = skb->nh.iph;
@@ -821,7 +822,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
 	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
 	ip_vs_conn_put(cp);
 
-	skb->nfcache |= NFC_IPVS_PROPERTY;
+	skb->ipvs_property = 1;
 
 	LeaveFunction(11);
 	return NF_ACCEPT;

net/ipv4/ipvs/ip_vs_xmit.c

@@ -127,7 +127,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
 
 #define IP_VS_XMIT(skb, rt)				\
 do {							\
-	(skb)->nfcache |= NFC_IPVS_PROPERTY;		\
+	(skb)->ipvs_property = 1;			\
 	(skb)->ip_summed = CHECKSUM_NONE;		\
 	NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, (skb), NULL,	\
 		(rt)->u.dst.dev, dst_output);		\

net/ipv4/netfilter/ip_conntrack_core.c

@@ -625,9 +625,6 @@ unsigned int ip_conntrack_in(unsigned int hooknum,
 		return NF_DROP;
 	}
 
-	/* FIXME: Do this right please. --RR */
-	(*pskb)->nfcache |= NFC_UNKNOWN;
-
 /* Doesn't cover locally-generated broadcast, so not worth it. */
 #if 0
 	/* Ignore broadcast: no `connection'. */
@@ -943,10 +940,8 @@ ip_ct_gather_frags(struct sk_buff *skb, u_int32_t user)
 	skb = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (skb) {
+	if (skb)
 		ip_send_check(skb->nh.iph);
-		skb->nfcache |= NFC_ALTERED;
-	}
 	return skb;
 }
 

net/ipv4/netfilter/ip_nat_core.c

@@ -321,7 +321,6 @@ manip_pkt(u_int16_t proto,
 {
 	struct iphdr *iph;
 
-	(*pskb)->nfcache |= NFC_ALTERED;
 	if (!skb_ip_make_writable(pskb, iphdroff + sizeof(*iph)))
 		return 0;
 

net/ipv4/netfilter/ip_nat_standalone.c

@@ -73,8 +73,6 @@ ip_nat_fn(unsigned int hooknum,
 	IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off
 		       & htons(IP_MF|IP_OFFSET)));
 
-	(*pskb)->nfcache |= NFC_UNKNOWN;
-
 	/* If we had a hardware checksum before, it's now invalid */
 	if ((*pskb)->ip_summed == CHECKSUM_HW)
 		if (skb_checksum_help(*pskb, (out == NULL)))

net/ipv4/netfilter/ip_queue.c

@@ -392,7 +392,6 @@ ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
 		return -ENOMEM;
 	memcpy(e->skb->data, v->payload, v->data_len);
 	e->skb->ip_summed = CHECKSUM_NONE;
-	e->skb->nfcache |= NFC_ALTERED;
 
 	/*
 	 * Extra routing may needed on local out, as the QUEUE target never

net/ipv4/netfilter/ip_tables.c

@@ -312,7 +312,6 @@ ipt_do_table(struct sk_buff **pskb,
 	do {
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
-		(*pskb)->nfcache |= e->nfcache;
 		if (ip_packet_match(ip, indev, outdev, &e->ip, offset)) {
 			struct ipt_entry_target *t;
 

net/ipv4/netfilter/ipt_CLASSIFY.c

@@ -32,10 +32,8 @@ target(struct sk_buff **pskb,
 {
 	const struct ipt_classify_target_info *clinfo = targinfo;
 
-	if((*pskb)->priority != clinfo->priority) {
+	if((*pskb)->priority != clinfo->priority) 
 		(*pskb)->priority = clinfo->priority;
-		(*pskb)->nfcache |= NFC_ALTERED;
-	}
 
 	return IPT_CONTINUE;
 }

net/ipv4/netfilter/ipt_CONNMARK.c

@@ -61,10 +61,8 @@ target(struct sk_buff **pskb,
 	    case IPT_CONNMARK_RESTORE:
 		nfmark = (*pskb)->nfmark;
 		diff = (ct->mark ^ nfmark) & markinfo->mask;
-		if (diff != 0) {
+		if (diff != 0)
 		    (*pskb)->nfmark = nfmark ^ diff;
-		    (*pskb)->nfcache |= NFC_ALTERED;
-		}
 		break;
 	    }
 	}

net/ipv4/netfilter/ipt_DSCP.c

@@ -51,7 +51,6 @@ target(struct sk_buff **pskb,
 						 sizeof(diffs),
 						 (*pskb)->nh.iph->check
 						 ^ 0xFFFF));
-		(*pskb)->nfcache |= NFC_ALTERED;
 	}
 	return IPT_CONTINUE;
 }

net/ipv4/netfilter/ipt_ECN.c

@@ -43,7 +43,6 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo)
 						 sizeof(diffs),
 						 (*pskb)->nh.iph->check
 						 ^0xFFFF));
-		(*pskb)->nfcache |= NFC_ALTERED;
 	} 
 	return 1;
 }
@@ -87,7 +86,6 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward)
 		tcph->check = csum_fold(csum_partial((char *)diffs,
 						     sizeof(diffs),
 						     tcph->check^0xFFFF));
-	(*pskb)->nfcache |= NFC_ALTERED;
 	return 1;
 }
 

net/ipv4/netfilter/ipt_MARK.c

@@ -29,10 +29,9 @@ target_v0(struct sk_buff **pskb,
 {
 	const struct ipt_mark_target_info *markinfo = targinfo;
 
-	if((*pskb)->nfmark != markinfo->mark) {
+	if((*pskb)->nfmark != markinfo->mark)
 		(*pskb)->nfmark = markinfo->mark;
-		(*pskb)->nfcache |= NFC_ALTERED;
+
-	}
 	return IPT_CONTINUE;
 }
 
@@ -61,10 +60,9 @@ target_v1(struct sk_buff **pskb,
 		break;
 	}
 
-	if((*pskb)->nfmark != mark) {
+	if((*pskb)->nfmark != mark)
 		(*pskb)->nfmark = mark;
-		(*pskb)->nfcache |= NFC_ALTERED;
+
-	}
 	return IPT_CONTINUE;
 }
 

net/ipv4/netfilter/ipt_REJECT.c

@@ -156,7 +156,6 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 
 	/* This packet will not be the same as the other: clear nf fields */
 	nf_reset(nskb);
-	nskb->nfcache = 0;
 	nskb->nfmark = 0;
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(nskb->nf_bridge);

net/ipv4/netfilter/ipt_TCPMSS.c

@@ -190,7 +190,6 @@ ipt_tcpmss_target(struct sk_buff **pskb,
 	       newmss);
 
  retmodified:
-	(*pskb)->nfcache |= NFC_UNKNOWN | NFC_ALTERED;
 	return IPT_CONTINUE;
 }
 

net/ipv4/netfilter/ipt_TOS.c

@@ -46,7 +46,6 @@ target(struct sk_buff **pskb,
 						 sizeof(diffs),
 						 (*pskb)->nh.iph->check
 						 ^0xFFFF));
-		(*pskb)->nfcache |= NFC_ALTERED;
 	}
 	return IPT_CONTINUE;
 }

net/ipv6/ip6_output.c

@@ -185,19 +185,6 @@ int ip6_route_me_harder(struct sk_buff *skb)
 }
 #endif
 
-static inline int ip6_maybe_reroute(struct sk_buff *skb)
-{
-#ifdef CONFIG_NETFILTER
-	if (skb->nfcache & NFC_ALTERED){
-		if (ip6_route_me_harder(skb) != 0){
-			kfree_skb(skb);
-			return -EINVAL;
-		}
-	}
-#endif /* CONFIG_NETFILTER */
-	return dst_output(skb);
-}
-
 /*
  *	xmit an sk_buff (used by TCP)
  */
@@ -266,7 +253,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	mtu = dst_mtu(dst);
 	if ((skb->len <= mtu) || ipfragok) {
 		IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
-		return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, ip6_maybe_reroute);
+		return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev,
+				dst_output);
 	}
 
 	if (net_ratelimit())

net/ipv6/netfilter/ip6_queue.c

@@ -388,7 +388,6 @@ ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
 		return -ENOMEM;
 	memcpy(e->skb->data, v->payload, v->data_len);
 	e->skb->ip_summed = CHECKSUM_NONE;
-	e->skb->nfcache |= NFC_ALTERED;
 
 	/*
 	 * Extra routing may needed on local out, as the QUEUE target never

net/ipv6/netfilter/ip6_tables.c

@@ -401,7 +401,6 @@ ip6t_do_table(struct sk_buff **pskb,
 	do {
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
-		(*pskb)->nfcache |= e->nfcache;
 		if (ip6_packet_match(*pskb, indev, outdev, &e->ipv6,
 			&protoff, &offset)) {
 			struct ip6t_entry_target *t;

net/ipv6/netfilter/ip6t_MARK.c

@@ -28,10 +28,9 @@ target(struct sk_buff **pskb,
 {
 	const struct ip6t_mark_target_info *markinfo = targinfo;
 
-	if((*pskb)->nfmark != markinfo->mark) {
+	if((*pskb)->nfmark != markinfo->mark)
 		(*pskb)->nfmark = markinfo->mark;
-		(*pskb)->nfcache |= NFC_ALTERED;
+
-	}
 	return IP6T_CONTINUE;
 }