From 512d06b5b64fb422d90f199b1be188082729edf9 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Mon, 4 Apr 2011 15:18:45 +0200
Subject: netfilter: ipset: list:set timeout variant fixes

- the timeout value was actually not set
- the garbage collector was broken

The variant is fixed, the tests to the ipset testsuite are added.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/ipset/ip_set_list_set.c | 53 ++++++++++++++++-------------------
 1 file changed, 24 insertions(+), 29 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index a47c32982f06..f4a46c0d25f3 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -43,14 +43,19 @@ struct list_set {
 static inline struct set_elem *
 list_set_elem(const struct list_set *map, u32 id)
 {
-	return (struct set_elem *)((char *)map->members + id * map->dsize);
+	return (struct set_elem *)((void *)map->members + id * map->dsize);
+}
+
+static inline struct set_telem *
+list_set_telem(const struct list_set *map, u32 id)
+{
+	return (struct set_telem *)((void *)map->members + id * map->dsize);
 }
 
 static inline bool
 list_set_timeout(const struct list_set *map, u32 id)
 {
-	const struct set_telem *elem =
-		(const struct set_telem *) list_set_elem(map, id);
+	const struct set_telem *elem = list_set_telem(map, id);
 
 	return ip_set_timeout_test(elem->timeout);
 }
@@ -58,19 +63,11 @@ list_set_timeout(const struct list_set *map, u32 id)
 static inline bool
 list_set_expired(const struct list_set *map, u32 id)
 {
-	const struct set_telem *elem =
-		(const struct set_telem *) list_set_elem(map, id);
+	const struct set_telem *elem = list_set_telem(map, id);
 
 	return ip_set_timeout_expired(elem->timeout);
 }
 
-static inline int
-list_set_exist(const struct set_telem *elem)
-{
-	return elem->id != IPSET_INVALID_ID &&
-	       !ip_set_timeout_expired(elem->timeout);
-}
-
 /* Set list without and with timeout */
 
 static int
@@ -146,11 +143,11 @@ list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id,
 	struct set_telem *e;
 
 	for (; i < map->size; i++) {
-		e = (struct set_telem *)list_set_elem(map, i);
+		e = list_set_telem(map, i);
 		swap(e->id, id);
+		swap(e->timeout, timeout);
 		if (e->id == IPSET_INVALID_ID)
 			break;
-		swap(e->timeout, timeout);
 	}
 }
 
@@ -164,7 +161,7 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id,
 		/* Last element replaced: e.g. add new,before,last */
 		ip_set_put_byindex(e->id);
 	if (with_timeout(map->timeout))
-		list_elem_tadd(map, i, id, timeout);
+		list_elem_tadd(map, i, id, ip_set_timeout_set(timeout));
 	else
 		list_elem_add(map, i, id);
 
@@ -172,11 +169,11 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id,
 }
 
 static int
-list_set_del(struct list_set *map, ip_set_id_t id, u32 i)
+list_set_del(struct list_set *map, u32 i)
 {
 	struct set_elem *a = list_set_elem(map, i), *b;
 
-	ip_set_put_byindex(id);
+	ip_set_put_byindex(a->id);
 
 	for (; i < map->size - 1; i++) {
 		b = list_set_elem(map, i + 1);
@@ -308,11 +305,11 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 				 (before == 0 ||
 				  (before > 0 &&
 				   next_id_eq(map, i, refid))))
-				ret = list_set_del(map, id, i);
+				ret = list_set_del(map, i);
 			else if (before < 0 &&
 				 elem->id == refid &&
 				 next_id_eq(map, i, id))
-				ret = list_set_del(map, id, i + 1);
+				ret = list_set_del(map, i + 1);
 		}
 		break;
 	default:
@@ -460,17 +457,15 @@ list_set_gc(unsigned long ul_set)
 	struct list_set *map = set->data;
 	struct set_telem *e;
 	u32 i;
-
-	/* We run parallel with other readers (test element)
-	 * but adding/deleting new entries is locked out */
-	read_lock_bh(&set->lock);
-	for (i = map->size - 1; i >= 0; i--) {
-		e = (struct set_telem *) list_set_elem(map, i);
-		if (e->id != IPSET_INVALID_ID &&
-		    list_set_expired(map, i))
-			list_set_del(map, e->id, i);
+	
+	/* nfnl_lock should be called */
+	write_lock_bh(&set->lock);
+	for (i = 0; i < map->size; i++) {
+		e = list_set_telem(map, i);
+		if (e->id != IPSET_INVALID_ID && list_set_expired(map, i))
+			list_set_del(map, i);
 	}
-	read_unlock_bh(&set->lock);
+	write_unlock_bh(&set->lock);
 
 	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
 	add_timer(&map->gc);
-- 
cgit v1.2.3


From 2f9f28b212a2bd4948c8ceaaec33ce0123632129 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Mon, 4 Apr 2011 15:19:25 +0200
Subject: netfilter: ipset: references are protected by rwlock instead of mutex

The timeout variant of the list:set type must reference the member sets.
However, its garbage collector runs at timer interrupt so the mutex
protection of the references is a no go. Therefore the reference protection
is converted to rwlock.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/ipset/ip_set.h       |   2 +-
 include/linux/netfilter/ipset/ip_set_ahash.h |   3 +-
 net/netfilter/ipset/ip_set_bitmap_ip.c       |   3 +-
 net/netfilter/ipset/ip_set_bitmap_ipmac.c    |   3 +-
 net/netfilter/ipset/ip_set_bitmap_port.c     |   3 +-
 net/netfilter/ipset/ip_set_core.c            | 109 ++++++++++++++++-----------
 net/netfilter/ipset/ip_set_list_set.c        |   6 +-
 7 files changed, 73 insertions(+), 56 deletions(-)

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index ec333d83f3b4..5a262e3ae715 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -293,7 +293,7 @@ struct ip_set {
 	/* Lock protecting the set data */
 	rwlock_t lock;
 	/* References to the set */
-	atomic_t ref;
+	u32 ref;
 	/* The core set type */
 	struct ip_set_type *type;
 	/* The type variant doing the real job */
diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
index ec9d9bea1e37..a0196ac79051 100644
--- a/include/linux/netfilter/ipset/ip_set_ahash.h
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -515,8 +515,7 @@ type_pf_head(struct ip_set *set, struct sk_buff *skb)
 	if (h->netmask != HOST_MASK)
 		NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask);
 #endif
-	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
 	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize));
 	if (with_timeout(h->timeout))
 		NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout));
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index bca96990218d..a113ff066928 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -338,8 +338,7 @@ bitmap_ip_head(struct ip_set *set, struct sk_buff *skb)
 	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip));
 	if (map->netmask != 32)
 		NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask);
-	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
 	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
 		      htonl(sizeof(*map) + map->memsize));
 	if (with_timeout(map->timeout))
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 5e790172deff..00a33242e90c 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -434,8 +434,7 @@ bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb)
 		goto nla_put_failure;
 	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip));
 	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip));
-	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
 	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
 		      htonl(sizeof(*map)
 			    + (map->last_ip - map->first_ip + 1) * map->dsize));
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 165f09b1a9cb..6b38eb8f6ed8 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -320,8 +320,7 @@ bitmap_port_head(struct ip_set *set, struct sk_buff *skb)
 		goto nla_put_failure;
 	NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port));
 	NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port));
-	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
 	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
 		      htonl(sizeof(*map) + map->memsize));
 	if (with_timeout(map->timeout))
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index d6b48230a540..e88ac3c3ed07 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -26,6 +26,7 @@
 
 static LIST_HEAD(ip_set_type_list);		/* all registered set types */
 static DEFINE_MUTEX(ip_set_type_mutex);		/* protects ip_set_type_list */
+static DEFINE_RWLOCK(ip_set_ref_lock);		/* protects the set refs */
 
 static struct ip_set **ip_set_list;		/* all individual sets */
 static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */
@@ -301,13 +302,18 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
 static inline void
 __ip_set_get(ip_set_id_t index)
 {
-	atomic_inc(&ip_set_list[index]->ref);
+	write_lock_bh(&ip_set_ref_lock);
+	ip_set_list[index]->ref++;
+	write_unlock_bh(&ip_set_ref_lock);
 }
 
 static inline void
 __ip_set_put(ip_set_id_t index)
 {
-	atomic_dec(&ip_set_list[index]->ref);
+	write_lock_bh(&ip_set_ref_lock);
+	BUG_ON(ip_set_list[index]->ref == 0);
+	ip_set_list[index]->ref--;
+	write_unlock_bh(&ip_set_ref_lock);
 }
 
 /*
@@ -324,7 +330,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
 	struct ip_set *set = ip_set_list[index];
 	int ret = 0;
 
-	BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+	BUG_ON(set == NULL);
 	pr_debug("set %s, index %u\n", set->name, index);
 
 	if (dim < set->type->dimension ||
@@ -356,7 +362,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
 	struct ip_set *set = ip_set_list[index];
 	int ret;
 
-	BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+	BUG_ON(set == NULL);
 	pr_debug("set %s, index %u\n", set->name, index);
 
 	if (dim < set->type->dimension ||
@@ -378,7 +384,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
 	struct ip_set *set = ip_set_list[index];
 	int ret = 0;
 
-	BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+	BUG_ON(set == NULL);
 	pr_debug("set %s, index %u\n", set->name, index);
 
 	if (dim < set->type->dimension ||
@@ -397,7 +403,6 @@ EXPORT_SYMBOL_GPL(ip_set_del);
  * Find set by name, reference it once. The reference makes sure the
  * thing pointed to, does not go away under our feet.
  *
- * The nfnl mutex must already be activated.
  */
 ip_set_id_t
 ip_set_get_byname(const char *name, struct ip_set **set)
@@ -423,15 +428,12 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname);
  * reference count by 1. The caller shall not assume the index
  * to be valid, after calling this function.
  *
- * The nfnl mutex must already be activated.
  */
 void
 ip_set_put_byindex(ip_set_id_t index)
 {
-	if (ip_set_list[index] != NULL) {
-		BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0);
+	if (ip_set_list[index] != NULL)
 		__ip_set_put(index);
-	}
 }
 EXPORT_SYMBOL_GPL(ip_set_put_byindex);
 
@@ -441,7 +443,6 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex);
  * can't be destroyed. The set cannot be renamed due to
  * the referencing either.
  *
- * The nfnl mutex must already be activated.
  */
 const char *
 ip_set_name_byindex(ip_set_id_t index)
@@ -449,7 +450,7 @@ ip_set_name_byindex(ip_set_id_t index)
 	const struct ip_set *set = ip_set_list[index];
 
 	BUG_ON(set == NULL);
-	BUG_ON(atomic_read(&set->ref) == 0);
+	BUG_ON(set->ref == 0);
 
 	/* Referenced, so it's safe */
 	return set->name;
@@ -515,10 +516,7 @@ void
 ip_set_nfnl_put(ip_set_id_t index)
 {
 	nfnl_lock();
-	if (ip_set_list[index] != NULL) {
-		BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0);
-		__ip_set_put(index);
-	}
+	ip_set_put_byindex(index);
 	nfnl_unlock();
 }
 EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
@@ -526,7 +524,7 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
 /*
  * Communication protocol with userspace over netlink.
  *
- * We already locked by nfnl_lock.
+ * The commands are serialized by the nfnl mutex.
  */
 
 static inline bool
@@ -657,7 +655,6 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 		return -ENOMEM;
 	rwlock_init(&set->lock);
 	strlcpy(set->name, name, IPSET_MAXNAMELEN);
-	atomic_set(&set->ref, 0);
 	set->family = family;
 
 	/*
@@ -690,8 +687,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 
 	/*
 	 * Here, we have a valid, constructed set and we are protected
-	 * by nfnl_lock. Find the first free index in ip_set_list and
-	 * check clashing.
+	 * by the nfnl mutex. Find the first free index in ip_set_list
+	 * and check clashing.
 	 */
 	if ((ret = find_free_id(set->name, &index, &clash)) != 0) {
 		/* If this is the same set and requested, ignore error */
@@ -751,31 +748,51 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 	       const struct nlattr * const attr[])
 {
 	ip_set_id_t i;
+	int ret = 0;
 
 	if (unlikely(protocol_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-	/* References are protected by the nfnl mutex */
+	/* Commands are serialized and references are
+	 * protected by the ip_set_ref_lock.
+	 * External systems (i.e. xt_set) must call
+	 * ip_set_put|get_nfnl_* functions, that way we
+	 * can safely check references here.
+	 *
+	 * list:set timer can only decrement the reference
+	 * counter, so if it's already zero, we can proceed
+	 * without holding the lock.
+	 */
+	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
 		for (i = 0; i < ip_set_max; i++) {
-			if (ip_set_list[i] != NULL &&
-			    (atomic_read(&ip_set_list[i]->ref)))
-				return -IPSET_ERR_BUSY;
+			if (ip_set_list[i] != NULL && ip_set_list[i]->ref) {
+				ret = IPSET_ERR_BUSY;
+				goto out;
+			}
 		}
+		read_unlock_bh(&ip_set_ref_lock);
 		for (i = 0; i < ip_set_max; i++) {
 			if (ip_set_list[i] != NULL)
 				ip_set_destroy_set(i);
 		}
 	} else {
 		i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME]));
-		if (i == IPSET_INVALID_ID)
-			return -ENOENT;
-		else if (atomic_read(&ip_set_list[i]->ref))
-			return -IPSET_ERR_BUSY;
+		if (i == IPSET_INVALID_ID) {
+			ret = -ENOENT;
+			goto out;
+		} else if (ip_set_list[i]->ref) {
+			ret = -IPSET_ERR_BUSY;
+			goto out;
+		}
+		read_unlock_bh(&ip_set_ref_lock);
 
 		ip_set_destroy_set(i);
 	}
 	return 0;
+out:
+	read_unlock_bh(&ip_set_ref_lock);
+	return ret;
 }
 
 /* Flush sets */
@@ -834,6 +851,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
 	struct ip_set *set;
 	const char *name2;
 	ip_set_id_t i;
+	int ret = 0;
 
 	if (unlikely(protocol_failed(attr) ||
 		     attr[IPSET_ATTR_SETNAME] == NULL ||
@@ -843,25 +861,33 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
 	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
 	if (set == NULL)
 		return -ENOENT;
-	if (atomic_read(&set->ref) != 0)
-		return -IPSET_ERR_REFERENCED;
+
+	read_lock_bh(&ip_set_ref_lock);
+	if (set->ref != 0) {
+		ret = -IPSET_ERR_REFERENCED;
+		goto out;
+	}
 
 	name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
 	for (i = 0; i < ip_set_max; i++) {
 		if (ip_set_list[i] != NULL &&
-		    STREQ(ip_set_list[i]->name, name2))
-			return -IPSET_ERR_EXIST_SETNAME2;
+		    STREQ(ip_set_list[i]->name, name2)) {
+			ret = -IPSET_ERR_EXIST_SETNAME2;
+			goto out;
+		}
 	}
 	strncpy(set->name, name2, IPSET_MAXNAMELEN);
 
-	return 0;
+out:
+	read_unlock_bh(&ip_set_ref_lock);
+	return ret;
 }
 
 /* Swap two sets so that name/index points to the other.
  * References and set names are also swapped.
  *
- * We are protected by the nfnl mutex and references are
- * manipulated only by holding the mutex. The kernel interfaces
+ * The commands are serialized by the nfnl mutex and references are
+ * protected by the ip_set_ref_lock. The kernel interfaces
  * do not hold the mutex but the pointer settings are atomic
  * so the ip_set_list always contains valid pointers to the sets.
  */
@@ -874,7 +900,6 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 	struct ip_set *from, *to;
 	ip_set_id_t from_id, to_id;
 	char from_name[IPSET_MAXNAMELEN];
-	u32 from_ref;
 
 	if (unlikely(protocol_failed(attr) ||
 		     attr[IPSET_ATTR_SETNAME] == NULL ||
@@ -899,17 +924,15 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 	      from->type->family == to->type->family))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	/* No magic here: ref munging protected by the nfnl_lock */
 	strncpy(from_name, from->name, IPSET_MAXNAMELEN);
-	from_ref = atomic_read(&from->ref);
-
 	strncpy(from->name, to->name, IPSET_MAXNAMELEN);
-	atomic_set(&from->ref, atomic_read(&to->ref));
 	strncpy(to->name, from_name, IPSET_MAXNAMELEN);
-	atomic_set(&to->ref, from_ref);
 
+	write_lock_bh(&ip_set_ref_lock);
+	swap(from->ref, to->ref);
 	ip_set_list[from_id] = to;
 	ip_set_list[to_id] = from;
+	write_unlock_bh(&ip_set_ref_lock);
 
 	return 0;
 }
@@ -926,7 +949,7 @@ ip_set_dump_done(struct netlink_callback *cb)
 {
 	if (cb->args[2]) {
 		pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name);
-		__ip_set_put((ip_set_id_t) cb->args[1]);
+		ip_set_put_byindex((ip_set_id_t) cb->args[1]);
 	}
 	return 0;
 }
@@ -1068,7 +1091,7 @@ release_refcount:
 	/* If there was an error or set is done, release set */
 	if (ret || !cb->args[2]) {
 		pr_debug("release set %s\n", ip_set_list[index]->name);
-		__ip_set_put(index);
+		ip_set_put_byindex(index);
 	}
 
 	/* If we dump all sets, continue with dumping last ones */
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index f4a46c0d25f3..e9159e99fc4b 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -366,8 +366,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
 	NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size));
 	if (with_timeout(map->timeout))
 		NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout));
-	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
-		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1));
 	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
 		      htonl(sizeof(*map) + map->size * map->dsize));
 	ipset_nest_end(skb, nested);
@@ -457,8 +456,7 @@ list_set_gc(unsigned long ul_set)
 	struct list_set *map = set->data;
 	struct set_telem *e;
 	u32 i;
-	
-	/* nfnl_lock should be called */
+
 	write_lock_bh(&set->lock);
 	for (i = 0; i < map->size; i++) {
 		e = list_set_telem(map, i);
-- 
cgit v1.2.3


From b4232a22776aa5d063f890d21ca69870dbbe431b Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.cz>
Date: Mon, 4 Apr 2011 15:21:02 +0200
Subject: netfilter: h323: bug in parsing of ASN1 SEQOF field

Static analyzer of clang found a dead store which appears to be a bug in
reading count of items in SEQOF field, only the lower byte of word is
stored. This may lead to corrupted read and communication shutdown.

The bug has been in the module since it's first inclusion into linux
kernel.

[Patrick: the bug is real, but without practical consequence since the
 largest amount of sequence-of members we parse is 30.]

Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_h323_asn1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index 867882313e49..bcd5ed6b7130 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -631,7 +631,7 @@ static int decode_seqof(bitstr_t *bs, const struct field_t *f,
 		CHECK_BOUND(bs, 2);
 		count = *bs->cur++;
 		count <<= 8;
-		count = *bs->cur++;
+		count += *bs->cur++;
 		break;
 	case SEMI:
 		BYTE_ALIGN(bs);
-- 
cgit v1.2.3


From a09d19779f3ffac6e16821accc2c1cc4df1b643a Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 4 Apr 2011 15:25:18 +0200
Subject: IPVS: fix NULL ptr dereference in ip_vs_ctl.c
 ip_vs_genl_dump_daemons()

ipvsadm -ln --daemon will trigger a Null pointer exception because
ip_vs_genl_dump_daemons() uses skb_net() instead of skb_sknet().

To prevent others from NULL ptr a check is made in ip_vs.h skb_net().

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/ip_vs.h            | 2 +-
 net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 30b49ed72f0d..4d1b71ae82ba 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -52,7 +52,7 @@ static inline struct net *skb_net(const struct sk_buff *skb)
 	 */
 	if (likely(skb->dev && skb->dev->nd_net))
 		return dev_net(skb->dev);
-	if (skb_dst(skb)->dev)
+	if (skb_dst(skb) && skb_dst(skb)->dev)
 		return dev_net(skb_dst(skb)->dev);
 	WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
 		      __func__, __LINE__);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 33733c8872e7..ae47090bf45f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3120,7 +3120,7 @@ nla_put_failure:
 static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
 				   struct netlink_callback *cb)
 {
-	struct net *net = skb_net(skb);
+	struct net *net = skb_sknet(skb);
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	mutex_lock(&__ip_vs_mutex);
-- 
cgit v1.2.3


From 31ad3dd64e689bc79dd819f8f134b9b025240eb8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 4 Apr 2011 16:56:29 +0200
Subject: netfilter: af_info: add network namespace parameter to route hook

This is required to eventually replace the rt6_lookup call in
xt_addrtype.c with nf_afinfo->route().

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h              | 3 ++-
 net/ipv4/netfilter.c                   | 5 +++--
 net/ipv6/netfilter.c                   | 5 +++--
 net/netfilter/nf_conntrack_h323_main.c | 8 ++++----
 net/netfilter/xt_TCPMSS.c              | 2 +-
 5 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index eeec00abb664..20ed4528e850 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -270,7 +270,8 @@ struct nf_afinfo {
 					    unsigned int dataoff,
 					    unsigned int len,
 					    u_int8_t protocol);
-	int		(*route)(struct dst_entry **dst, struct flowi *fl);
+	int		(*route)(struct net *net, struct dst_entry **dst,
+				 struct flowi *fl);
 	void		(*saveroute)(const struct sk_buff *skb,
 				     struct nf_queue_entry *entry);
 	int		(*reroute)(struct sk_buff *skb,
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index f3c0b549b8e1..f1035f056503 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -221,9 +221,10 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
 	return csum;
 }
 
-static int nf_ip_route(struct dst_entry **dst, struct flowi *fl)
+static int nf_ip_route(struct net *net, struct dst_entry **dst,
+		       struct flowi *fl)
 {
-	struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4);
+	struct rtable *rt = ip_route_output_key(net, &fl->u.ip4);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 	*dst = &rt->dst;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 39aaca2b4fd2..e008b9b4a779 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -90,9 +90,10 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 	return 0;
 }
 
-static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl)
+static int nf_ip6_route(struct net *net, struct dst_entry **dst,
+			struct flowi *fl)
 {
-	*dst = ip6_route_output(&init_net, NULL, &fl->u.ip6);
+	*dst = ip6_route_output(net, NULL, &fl->u.ip6);
 	return (*dst)->error;
 }
 
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 533a183e6661..39a453895b4d 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -731,9 +731,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 
 		memset(&fl2, 0, sizeof(fl2));
 		fl2.daddr = dst->ip;
-		if (!afinfo->route((struct dst_entry **)&rt1,
+		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
 				   flowi4_to_flowi(&fl1))) {
-			if (!afinfo->route((struct dst_entry **)&rt2,
+			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
 					   flowi4_to_flowi(&fl2))) {
 				if (rt1->rt_gateway == rt2->rt_gateway &&
 				    rt1->dst.dev  == rt2->dst.dev)
@@ -755,9 +755,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 
 		memset(&fl2, 0, sizeof(fl2));
 		ipv6_addr_copy(&fl2.daddr, &dst->in6);
-		if (!afinfo->route((struct dst_entry **)&rt1,
+		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
 				   flowi6_to_flowi(&fl1))) {
-			if (!afinfo->route((struct dst_entry **)&rt2,
+			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
 					   flowi6_to_flowi(&fl2))) {
 				if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
 					    sizeof(rt1->rt6i_gateway)) &&
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 6e6b46cb1db9..8690125e3b18 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
 	rcu_read_lock();
 	ai = nf_get_afinfo(family);
 	if (ai != NULL)
-		ai->route((struct dst_entry **)&rt, &fl);
+		ai->route(&init_net, (struct dst_entry **)&rt, &fl);
 	rcu_read_unlock();
 
 	if (rt != NULL) {
-- 
cgit v1.2.3


From 0fae2e7740aca7e384c5f337f458897e7e337d58 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 4 Apr 2011 17:00:54 +0200
Subject: netfilter: af_info: add 'strict' parameter to limit lookup to .oif

ipv6 fib lookup can set RT6_LOOKUP_F_IFACE flag to restrict search
to an interface, but this flag cannot be set via struct flowi.

Also, it cannot be set via ip6_route_output: this function uses the
passed sock struct to determine if this flag is required
(by testing for nonzero sk_bound_dev_if).

Work around this by passing in an artificial struct sk in case
'strict' argument is true.

This is required to replace the rt6_lookup call in xt_addrtype.c with
nf_afinfo->route().

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h              |  2 +-
 net/ipv4/netfilter.c                   |  2 +-
 net/ipv6/netfilter.c                   | 12 ++++++++++--
 net/netfilter/nf_conntrack_h323_main.c |  8 ++++----
 net/netfilter/xt_TCPMSS.c              |  2 +-
 5 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 20ed4528e850..7fa95df60146 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -271,7 +271,7 @@ struct nf_afinfo {
 					    unsigned int len,
 					    u_int8_t protocol);
 	int		(*route)(struct net *net, struct dst_entry **dst,
-				 struct flowi *fl);
+				 struct flowi *fl, bool strict);
 	void		(*saveroute)(const struct sk_buff *skb,
 				     struct nf_queue_entry *entry);
 	int		(*reroute)(struct sk_buff *skb,
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index f1035f056503..4614babdc45f 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -222,7 +222,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
 }
 
 static int nf_ip_route(struct net *net, struct dst_entry **dst,
-		       struct flowi *fl)
+		       struct flowi *fl, bool strict __always_unused)
 {
 	struct rtable *rt = ip_route_output_key(net, &fl->u.ip4);
 	if (IS_ERR(rt))
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index e008b9b4a779..28bc1f644b7b 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -91,9 +91,17 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 }
 
 static int nf_ip6_route(struct net *net, struct dst_entry **dst,
-			struct flowi *fl)
+			struct flowi *fl, bool strict)
 {
-	*dst = ip6_route_output(net, NULL, &fl->u.ip6);
+	static const struct ipv6_pinfo fake_pinfo;
+	static const struct inet_sock fake_sk = {
+		/* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */
+		.sk.sk_bound_dev_if = 1,
+		.pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
+	};
+	const void *sk = strict ? &fake_sk : NULL;
+
+	*dst = ip6_route_output(net, sk, &fl->u.ip6);
 	return (*dst)->error;
 }
 
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 39a453895b4d..18b2ce5c8ced 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -732,9 +732,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 		memset(&fl2, 0, sizeof(fl2));
 		fl2.daddr = dst->ip;
 		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
-				   flowi4_to_flowi(&fl1))) {
+				   flowi4_to_flowi(&fl1), false)) {
 			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
-					   flowi4_to_flowi(&fl2))) {
+					   flowi4_to_flowi(&fl2), false)) {
 				if (rt1->rt_gateway == rt2->rt_gateway &&
 				    rt1->dst.dev  == rt2->dst.dev)
 					ret = 1;
@@ -756,9 +756,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 		memset(&fl2, 0, sizeof(fl2));
 		ipv6_addr_copy(&fl2.daddr, &dst->in6);
 		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
-				   flowi6_to_flowi(&fl1))) {
+				   flowi6_to_flowi(&fl1), false)) {
 			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
-					   flowi6_to_flowi(&fl2))) {
+					   flowi6_to_flowi(&fl2), false)) {
 				if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
 					    sizeof(rt1->rt6i_gateway)) &&
 				    rt1->dst.dev == rt2->dst.dev)
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 8690125e3b18..9e63b43faeed 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
 	rcu_read_lock();
 	ai = nf_get_afinfo(family);
 	if (ai != NULL)
-		ai->route(&init_net, (struct dst_entry **)&rt, &fl);
+		ai->route(&init_net, (struct dst_entry **)&rt, &fl, false);
 	rcu_read_unlock();
 
 	if (rt != NULL) {
-- 
cgit v1.2.3


From b7225041e93f81e7e38fcdf27fc82044e7695efd Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 4 Apr 2011 17:01:43 +0200
Subject: netfilter: xt_addrtype: replace rt6_lookup with nf_afinfo->route

This avoids pulling in the ipv6 module when using (ipv4-only) iptables
-m addrtype.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/Kconfig       |  1 -
 net/netfilter/xt_addrtype.c | 42 ++++++++++++++++++++++++++++--------------
 2 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c3f988aa1152..32bff6d86cb2 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -652,7 +652,6 @@ comment "Xtables matches"
 config NETFILTER_XT_MATCH_ADDRTYPE
 	tristate '"addrtype" address type match support'
 	depends on NETFILTER_ADVANCED
-	depends on (IPV6 || IPV6=n)
 	---help---
 	  This option allows you to match what routing thinks of an address,
 	  eg. UNICAST, LOCAL, BROADCAST, ...
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index 2220b85e9519..b77d383cec78 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -32,11 +32,32 @@ MODULE_ALIAS("ipt_addrtype");
 MODULE_ALIAS("ip6t_addrtype");
 
 #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
-static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt)
+static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
+			    const struct in6_addr *addr)
 {
+	const struct nf_afinfo *afinfo;
+	struct flowi6 flow;
+	struct rt6_info *rt;
 	u32 ret;
+	int route_err;
 
-	if (!rt)
+	memset(&flow, 0, sizeof(flow));
+	ipv6_addr_copy(&flow.daddr, addr);
+	if (dev)
+		flow.flowi6_oif = dev->ifindex;
+
+	rcu_read_lock();
+
+	afinfo = nf_get_afinfo(NFPROTO_IPV6);
+	if (afinfo != NULL)
+		route_err = afinfo->route(net, (struct dst_entry **)&rt,
+					flowi6_to_flowi(&flow), !!dev);
+	else
+		route_err = 1;
+
+	rcu_read_unlock();
+
+	if (route_err)
 		return XT_ADDRTYPE_UNREACHABLE;
 
 	if (rt->rt6i_flags & RTF_REJECT)
@@ -48,6 +69,9 @@ static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt)
 		ret |= XT_ADDRTYPE_LOCAL;
 	if (rt->rt6i_flags & RTF_ANYCAST)
 		ret |= XT_ADDRTYPE_ANYCAST;
+
+
+	dst_release(&rt->dst);
 	return ret;
 }
 
@@ -65,18 +89,8 @@ static bool match_type6(struct net *net, const struct net_device *dev,
 		return false;
 
 	if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST |
-	     XT_ADDRTYPE_UNREACHABLE) & mask) {
-		struct rt6_info *rt;
-		u32 type;
-		int ifindex = dev ? dev->ifindex : 0;
-
-		rt = rt6_lookup(net, addr, NULL, ifindex, !!dev);
-
-		type = xt_addrtype_rt6_to_type(rt);
-
-		dst_release(&rt->dst);
-		return !!(mask & type);
-	}
+	     XT_ADDRTYPE_UNREACHABLE) & mask)
+		return !!(mask & match_lookup_rt6(net, dev, addr));
 	return true;
 }
 
-- 
cgit v1.2.3


From 96120d86fe302c006259baee9061eea9e1b9e486 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 4 Apr 2011 17:06:21 +0200
Subject: netfilter: xt_conntrack: fix inverted conntrack direction test

--ctdir ORIGINAL matches REPLY packets, and vv:

userspace sets "invert_flags &= ~XT_CONNTRACK_DIRECTION" in ORIGINAL
case.

Thus: (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) ^
      !!(info->invert_flags & XT_CONNTRACK_DIRECTION))

yields "1 ^ 0", which is true -> returns false.

Reproducer:
iptables -I OUTPUT 1 -p tcp --syn -m conntrack --ctdir ORIGINAL

Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/xt_conntrack.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 2c0086a4751e..481a86fdc409 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -195,7 +195,7 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
 		return info->match_flags & XT_CONNTRACK_STATE;
 	if ((info->match_flags & XT_CONNTRACK_DIRECTION) &&
 	    (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) ^
-	    !!(info->invert_flags & XT_CONNTRACK_DIRECTION))
+	    !(info->invert_flags & XT_CONNTRACK_DIRECTION))
 		return false;
 
 	if (info->match_flags & XT_CONNTRACK_ORIGSRC)
-- 
cgit v1.2.3