[NETFILTER] nf_conntrack: clean up to reduce size of 'struct nf_conn'

This patch moves all helper related data fields of 'struct nf_conn'
into a separate structure 'struct nf_conn_help'.  This new structure
is only present in conntrack entries for which we actually have a
helper loaded.

Also, this patch cleans up the nf_conntrack 'features' mechanism to
resemble what the original idea was: Just glue the feature-specific
data structures at the end of 'struct nf_conn', and explicitly
re-calculate the pointer to it when needed rather than keeping
pointers around.

Saves 20 bytes per conntrack on my x86_64 box. A non-helped conntrack
is 276 bytes. We still need to save another 20 bytes in order to fit
into to target of 256bytes.

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

5 files changed, 80 insertions, 89 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index d622ddf..dc68d00 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -3,7 +3,7 @@
    extension. */
 
 /* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2005 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
  * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -20,6 +20,9 @@
  *	- generalize L3 protocol denendent part.
  * 23 Mar 2004: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
  *	- add support various size of conntrack structures.
+ * 26 Jan 2006: Harald Welte <laforge@netfilter.org>
+ * 	- restructure nf_conn (introduce nf_conn_help)
+ * 	- redesign 'features' how they were originally intended
  *
  * Derived from net/ipv4/netfilter/ip_conntrack_core.c
  */
@@ -55,7 +58,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <linux/netfilter_ipv4/listhelp.h>
 
-#define NF_CONNTRACK_VERSION	"0.4.1"
+#define NF_CONNTRACK_VERSION	"0.5.0"
 
 #if 0
 #define DEBUGP printk
@@ -259,21 +262,8 @@ static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple)
 				nf_conntrack_hash_rnd);
 }
 
-/* Initialize "struct nf_conn" which has spaces for helper */
-static int
-init_conntrack_for_helper(struct nf_conn *conntrack, u_int32_t features)
-{
-
-	conntrack->help = (union nf_conntrack_help *)
-		(((unsigned long)conntrack->data
-		  + (__alignof__(union nf_conntrack_help) - 1))
-		 & (~((unsigned long)(__alignof__(union nf_conntrack_help) -1))));
-	return 0;
-}
-
 int nf_conntrack_register_cache(u_int32_t features, const char *name,
-				size_t size,
-				int (*init)(struct nf_conn *, u_int32_t))
+				size_t size)
 {
 	int ret = 0;
 	char *cache_name;
@@ -296,8 +286,7 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name,
 		DEBUGP("nf_conntrack_register_cache: already resisterd.\n");
 		if ((!strncmp(nf_ct_cache[features].name, name,
 			      NF_CT_FEATURES_NAMELEN))
-		    && nf_ct_cache[features].size == size
-		    && nf_ct_cache[features].init_conntrack == init) {
+		    && nf_ct_cache[features].size == size) {
 			DEBUGP("nf_conntrack_register_cache: reusing.\n");
 			nf_ct_cache[features].use++;
 			ret = 0;
@@ -340,7 +329,6 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name,
 	write_lock_bh(&nf_ct_cache_lock);
 	nf_ct_cache[features].use = 1;
 	nf_ct_cache[features].size = size;
-	nf_ct_cache[features].init_conntrack = init;
 	nf_ct_cache[features].cachep = cachep;
 	nf_ct_cache[features].name = cache_name;
 	write_unlock_bh(&nf_ct_cache_lock);
@@ -377,7 +365,6 @@ void nf_conntrack_unregister_cache(u_int32_t features)
 	name = nf_ct_cache[features].name;
 	nf_ct_cache[features].cachep = NULL;
 	nf_ct_cache[features].name = NULL;
-	nf_ct_cache[features].init_conntrack = NULL;
 	nf_ct_cache[features].size = 0;
 	write_unlock_bh(&nf_ct_cache_lock);
 
@@ -432,11 +419,15 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 /* nf_conntrack_expect helper functions */
 void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
 {
+	struct nf_conn_help *master_help = nfct_help(exp->master);
+
+	NF_CT_ASSERT(master_help);
 	ASSERT_WRITE_LOCK(&nf_conntrack_lock);
 	NF_CT_ASSERT(!timer_pending(&exp->timeout));
+
 	list_del(&exp->list);
 	NF_CT_STAT_INC(expect_delete);
-	exp->master->expecting--;
+	master_help->expecting--;
 	nf_conntrack_expect_put(exp);
 }
 
@@ -508,9 +499,10 @@ find_expectation(const struct nf_conntrack_tuple *tuple)
 void nf_ct_remove_expectations(struct nf_conn *ct)
 {
 	struct nf_conntrack_expect *i, *tmp;
+	struct nf_conn_help *help = nfct_help(ct);
 
 	/* Optimization: most connection never expect any others. */
-	if (ct->expecting == 0)
+	if (!help || help->expecting == 0)
 		return;
 
 	list_for_each_entry_safe(i, tmp, &nf_conntrack_expect_list, list) {
@@ -713,6 +705,7 @@ __nf_conntrack_confirm(struct sk_buff **pskb)
 			  conntrack_tuple_cmp,
 			  struct nf_conntrack_tuple_hash *,
 			  &ct->tuplehash[IP_CT_DIR_REPLY].tuple, NULL)) {
+		struct nf_conn_help *help;
 		/* Remove from unconfirmed list */
 		list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
 
@@ -726,7 +719,8 @@ __nf_conntrack_confirm(struct sk_buff **pskb)
 		set_bit(IPS_CONFIRMED_BIT, &ct->status);
 		NF_CT_STAT_INC(insert);
 		write_unlock_bh(&nf_conntrack_lock);
-		if (ct->helper)
+		help = nfct_help(ct);
+		if (help && help->helper)
 			nf_conntrack_event_cache(IPCT_HELPER, *pskb);
 #ifdef CONFIG_NF_NAT_NEEDED
 		if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) ||
@@ -842,8 +836,9 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 {
 	struct nf_conn *conntrack = NULL;
 	u_int32_t features = 0;
+	struct nf_conntrack_helper *helper;
 
-	if (!nf_conntrack_hash_rnd_initted) {
+	if (unlikely(!nf_conntrack_hash_rnd_initted)) {
 		get_random_bytes(&nf_conntrack_hash_rnd, 4);
 		nf_conntrack_hash_rnd_initted = 1;
 	}
@@ -863,8 +858,11 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 
 	/*  find features needed by this conntrack. */
 	features = l3proto->get_features(orig);
+
+	/* FIXME: protect helper list per RCU */
 	read_lock_bh(&nf_conntrack_lock);
-	if (__nf_ct_helper_find(repl) != NULL)
+	helper = __nf_ct_helper_find(repl);
+	if (helper)
 		features |= NF_CT_F_HELP;
 	read_unlock_bh(&nf_conntrack_lock);
 
@@ -872,7 +870,7 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 
 	read_lock_bh(&nf_ct_cache_lock);
 
-	if (!nf_ct_cache[features].use) {
+	if (unlikely(!nf_ct_cache[features].use)) {
 		DEBUGP("nf_conntrack_alloc: not supported features = 0x%x\n",
 			features);
 		goto out;
@@ -886,12 +884,10 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
 
 	memset(conntrack, 0, nf_ct_cache[features].size);
 	conntrack->features = features;
-	if (nf_ct_cache[features].init_conntrack &&
-	    nf_ct_cache[features].init_conntrack(conntrack, features) < 0) {
-		DEBUGP("nf_conntrack_alloc: failed to init\n");
-		kmem_cache_free(nf_ct_cache[features].cachep, conntrack);
-		conntrack = NULL;
-		goto out;
+	if (helper) {
+		struct nf_conn_help *help = nfct_help(conntrack);
+		NF_CT_ASSERT(help);
+		help->helper = helper;
 	}
 
 	atomic_set(&conntrack->ct_general.use, 1);
@@ -972,11 +968,8 @@ init_conntrack(const struct nf_conntrack_tuple *tuple,
 #endif
 		nf_conntrack_get(&conntrack->master->ct_general);
 		NF_CT_STAT_INC(expect_new);
-	} else {
-		conntrack->helper = __nf_ct_helper_find(&repl_tuple);
-
+	} else
 		NF_CT_STAT_INC(new);
-        }
 
 	/* Overload tuple linked list to put us in unconfirmed list. */
 	list_add(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL].list, &unconfirmed);
@@ -1206,14 +1199,16 @@ void nf_conntrack_expect_put(struct nf_conntrack_expect *exp)
 
 static void nf_conntrack_expect_insert(struct nf_conntrack_expect *exp)
 {
+	struct nf_conn_help *master_help = nfct_help(exp->master);
+
 	atomic_inc(&exp->use);
-	exp->master->expecting++;
+	master_help->expecting++;
 	list_add(&exp->list, &nf_conntrack_expect_list);
 
 	init_timer(&exp->timeout);
 	exp->timeout.data = (unsigned long)exp;
 	exp->timeout.function = expectation_timed_out;
-	exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ;
+	exp->timeout.expires = jiffies + master_help->helper->timeout * HZ;
 	add_timer(&exp->timeout);
 
 	exp->id = ++nf_conntrack_expect_next_id;
@@ -1239,10 +1234,12 @@ static void evict_oldest_expect(struct nf_conn *master)
 
 static inline int refresh_timer(struct nf_conntrack_expect *i)
 {
+	struct nf_conn_help *master_help = nfct_help(i->master);
+
 	if (!del_timer(&i->timeout))
 		return 0;
 
-	i->timeout.expires = jiffies + i->master->helper->timeout*HZ;
+	i->timeout.expires = jiffies + master_help->helper->timeout*HZ;
 	add_timer(&i->timeout);
 	return 1;
 }
@@ -1251,8 +1248,11 @@ int nf_conntrack_expect_related(struct nf_conntrack_expect *expect)
 {
 	struct nf_conntrack_expect *i;
 	struct nf_conn *master = expect->master;
+	struct nf_conn_help *master_help = nfct_help(master);
 	int ret;
 
+	NF_CT_ASSERT(master_help);
+
 	DEBUGP("nf_conntrack_expect_related %p\n", related_to);
 	DEBUGP("tuple: "); NF_CT_DUMP_TUPLE(&expect->tuple);
 	DEBUGP("mask:  "); NF_CT_DUMP_TUPLE(&expect->mask);
@@ -1271,8 +1271,8 @@ int nf_conntrack_expect_related(struct nf_conntrack_expect *expect)
 		}
 	}
 	/* Will be over limit? */
-	if (master->helper->max_expected && 
-	    master->expecting >= master->helper->max_expected)
+	if (master_help->helper->max_expected &&
+	    master_help->expecting >= master_help->helper->max_expected)
 		evict_oldest_expect(master);
 
 	nf_conntrack_expect_insert(expect);
@@ -1283,24 +1283,6 @@ out:
 	return ret;
 }
 
-/* Alter reply tuple (maybe alter helper).  This is for NAT, and is
-   implicitly racy: see __nf_conntrack_confirm */
-void nf_conntrack_alter_reply(struct nf_conn *conntrack,
-			      const struct nf_conntrack_tuple *newreply)
-{
-	write_lock_bh(&nf_conntrack_lock);
-	/* Should be unconfirmed, so not in hash table yet */
-	NF_CT_ASSERT(!nf_ct_is_confirmed(conntrack));
-
-	DEBUGP("Altering reply tuple of %p to ", conntrack);
-	NF_CT_DUMP_TUPLE(newreply);
-
-	conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
-	if (!conntrack->master && conntrack->expecting == 0)
-		conntrack->helper = __nf_ct_helper_find(newreply);
-	write_unlock_bh(&nf_conntrack_lock);
-}
-
 int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 {
 	int ret;
@@ -1308,9 +1290,8 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 
 	ret = nf_conntrack_register_cache(NF_CT_F_HELP, "nf_conntrack:help",
 					  sizeof(struct nf_conn)
-					  + sizeof(union nf_conntrack_help)
-					  + __alignof__(union nf_conntrack_help),
-					  init_conntrack_for_helper);
+					  + sizeof(struct nf_conn_help)
+					  + __alignof__(struct nf_conn_help));
 	if (ret < 0) {
 		printk(KERN_ERR "nf_conntrack_helper_reigster: Unable to create slab cache for conntracks\n");
 		return ret;
@@ -1338,9 +1319,12 @@ __nf_conntrack_helper_find_byname(const char *name)
 static inline int unhelp(struct nf_conntrack_tuple_hash *i,
 			 const struct nf_conntrack_helper *me)
 {
-	if (nf_ct_tuplehash_to_ctrack(i)->helper == me) {
-		nf_conntrack_event(IPCT_HELPER, nf_ct_tuplehash_to_ctrack(i));
-		nf_ct_tuplehash_to_ctrack(i)->helper = NULL;
+	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i);
+	struct nf_conn_help *help = nfct_help(ct);
+
+	if (help && help->helper == me) {
+		nf_conntrack_event(IPCT_HELPER, ct);
+		help->helper = NULL;
 	}
 	return 0;
 }
@@ -1356,7 +1340,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 
 	/* Get rid of expectations */
 	list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list, list) {
-		if (exp->master->helper == me && del_timer(&exp->timeout)) {
+		struct nf_conn_help *help = nfct_help(exp->master);
+		if (help->helper == me && del_timer(&exp->timeout)) {
 			nf_ct_unlink_expect(exp);
 			nf_conntrack_expect_put(exp);
 		}
@@ -1697,7 +1682,7 @@ int __init nf_conntrack_init(void)
 	}
 
 	ret = nf_conntrack_register_cache(NF_CT_F_BASIC, "nf_conntrack:basic",
-					  sizeof(struct nf_conn), NULL);
+					  sizeof(struct nf_conn));
 	if (ret < 0) {
 		printk(KERN_ERR "Unable to create nf_conn slab cache\n");
 		goto err_free_hash;
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 6f210f3..cd191b0 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -440,7 +440,7 @@ static int help(struct sk_buff **pskb,
 	u32 seq;
 	int dir = CTINFO2DIR(ctinfo);
 	unsigned int matchlen, matchoff;
-	struct ip_ct_ftp_master *ct_ftp_info = &ct->help->ct_ftp_info;
+	struct ip_ct_ftp_master *ct_ftp_info = &nfct_help(ct)->help.ct_ftp_info;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_man cmd = {};
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9ff3463..aef3cb4 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2,7 +2,7 @@
  * protocol helpers and general trouble making from userspace.
  *
  * (C) 2001 by Jay Schulist <jschlst@samba.org>
- * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org>
+ * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org>
  * (C) 2003 by Patrick Mchardy <kaber@trash.net>
  * (C) 2005 by Pablo Neira Ayuso <pablo@eurodev.net>
  *
@@ -44,7 +44,7 @@
 
 MODULE_LICENSE("GPL");
 
-static char __initdata version[] = "0.92";
+static char __initdata version[] = "0.93";
 
 #if 0
 #define DEBUGP printk
@@ -165,15 +165,16 @@ static inline int
 ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct)
 {
 	struct nfattr *nest_helper;
+	const struct nf_conn_help *help = nfct_help(ct);
 
-	if (!ct->helper)
+	if (!help || !help->helper)
 		return 0;
 		
 	nest_helper = NFA_NEST(skb, CTA_HELP);
-	NFA_PUT(skb, CTA_HELP_NAME, strlen(ct->helper->name), ct->helper->name);
+	NFA_PUT(skb, CTA_HELP_NAME, strlen(help->helper->name), help->helper->name);
 
-	if (ct->helper->to_nfattr)
-		ct->helper->to_nfattr(skb, ct);
+	if (help->helper->to_nfattr)
+		help->helper->to_nfattr(skb, ct);
 
 	NFA_NEST_END(skb, nest_helper);
 
@@ -903,11 +904,17 @@ static inline int
 ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[])
 {
 	struct nf_conntrack_helper *helper;
+	struct nf_conn_help *help = nfct_help(ct);
 	char *helpname;
 	int err;
 
 	DEBUGP("entered %s\n", __FUNCTION__);
 
+	if (!help) {
+		/* FIXME: we need to reallocate and rehash */
+		return -EBUSY;
+	}
+
 	/* don't change helper of sibling connections */
 	if (ct->master)
 		return -EINVAL;
@@ -924,18 +931,18 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[])
 			return -EINVAL;
 	}
 
-	if (ct->helper) {
+	if (help->helper) {
 		if (!helper) {
 			/* we had a helper before ... */
 			nf_ct_remove_expectations(ct);
-			ct->helper = NULL;
+			help->helper = NULL;
 		} else {
 			/* need to zero data of old helper */
-			memset(&ct->help, 0, sizeof(ct->help));
+			memset(&help->help, 0, sizeof(help->help));
 		}
 	}
 	
-	ct->helper = helper;
+	help->helper = helper;
 
 	return 0;
 }
@@ -1050,14 +1057,9 @@ ctnetlink_create_conntrack(struct nfattr *cda[],
 		ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1]));
 #endif
 
-	ct->helper = nf_ct_helper_find_get(rtuple);
-
 	add_timer(&ct->timeout);
 	nf_conntrack_hash_insert(ct);
 
-	if (ct->helper)
-		nf_ct_helper_put(ct->helper);
-
 	DEBUGP("conntrack with id %u inserted\n", ct->id);
 	return 0;
 
@@ -1417,7 +1419,8 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 		}
 		list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list,
 					 list) {
-			if (exp->master->helper == h 
+			struct nf_conn_help *m_help = nfct_help(exp->master);
+			if (m_help->helper == h
 			    && del_timer(&exp->timeout)) {
 				nf_ct_unlink_expect(exp);
 				nf_conntrack_expect_put(exp);
@@ -1452,6 +1455,7 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3)
 	struct nf_conntrack_tuple_hash *h = NULL;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn *ct;
+	struct nf_conn_help *help;
 	int err = 0;
 
 	DEBUGP("entered %s\n", __FUNCTION__);
@@ -1472,8 +1476,9 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3)
 	if (!h)
 		return -ENOENT;
 	ct = nf_ct_tuplehash_to_ctrack(h);
+	help = nfct_help(ct);
 
-	if (!ct->helper) {
+	if (!help || !help->helper) {
 		/* such conntrack hasn't got any helper, abort */
 		err = -EINVAL;
 		goto out;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 617599a..290d5a0 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -839,7 +839,6 @@ EXPORT_SYMBOL(nf_conntrack_l3proto_unregister);
 EXPORT_SYMBOL(nf_conntrack_protocol_register);
 EXPORT_SYMBOL(nf_conntrack_protocol_unregister);
 EXPORT_SYMBOL(nf_ct_invert_tuplepr);
-EXPORT_SYMBOL(nf_conntrack_alter_reply);
 EXPORT_SYMBOL(nf_conntrack_destroyed);
 EXPORT_SYMBOL(need_conntrack);
 EXPORT_SYMBOL(nf_conntrack_helper_register);
diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c
index 38b6715..0ddb323 100644
--- a/net/netfilter/xt_helper.c
+++ b/net/netfilter/xt_helper.c
@@ -96,6 +96,7 @@ match(const struct sk_buff *skb,
 {
 	const struct xt_helper_info *info = matchinfo;
 	struct nf_conn *ct;
+	struct nf_conn_help *master_help;
 	enum ip_conntrack_info ctinfo;
 	int ret = info->invert;
 	
@@ -111,7 +112,8 @@ match(const struct sk_buff *skb,
 	}
 
 	read_lock_bh(&nf_conntrack_lock);
-	if (!ct->master->helper) {
+	master_help = nfct_help(ct->master);
+	if (!master_help || !master_help->helper) {
 		DEBUGP("xt_helper: master ct %p has no helper\n", 
 			exp->expectant);
 		goto out_unlock;
@@ -123,8 +125,8 @@ match(const struct sk_buff *skb,
 	if (info->name[0] == '\0')
 		ret ^= 1;
 	else
-		ret ^= !strncmp(ct->master->helper->name, info->name, 
-		                strlen(ct->master->helper->name));
+		ret ^= !strncmp(master_help->helper->name, info->name,
+		                strlen(master_help->helper->name));
 out_unlock:
 	read_unlock_bh(&nf_conntrack_lock);
 	return ret;