From 5e0c1eb7e6b61998c7ecd39b7f69a15773d894d4 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Sun, 20 Mar 2011 15:33:26 +0100
Subject: netfilter: ipset: fix address ranges at hash:*port* types

The hash:*port* types with IPv4 silently ignored when address ranges
with non TCP/UDP were added/deleted from the set and used the first
address from the range only.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/ipset/ip_set_hash_ipport.c    | 34 +++++++++--------------------
 net/netfilter/ipset/ip_set_hash_ipportip.c  | 34 +++++++++--------------------
 net/netfilter/ipset/ip_set_hash_ipportnet.c | 34 +++++++++--------------------
 net/netfilter/ipset/ip_set_hash_netport.c   | 30 +++++++------------------
 4 files changed, 38 insertions(+), 94 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index adbe787ea5dc..b9214145d357 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -150,6 +150,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_ipport4_elem data = { };
 	u32 ip, ip_to, p, port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -172,21 +173,15 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMP:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMP))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -195,7 +190,6 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	}
 
 	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
 	    !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] ||
 	      tb[IPSET_ATTR_PORT_TO])) {
 		ret = adtfn(set, &data, timeout);
@@ -219,13 +213,12 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	} else
 		ip_to = ip;
 
-	port = ntohs(data.port);
-	if (tb[IPSET_ATTR_PORT_TO]) {
+	port_to = port = ntohs(data.port);
+	if (with_ports && tb[IPSET_ATTR_PORT_TO]) {
 		port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
 		if (port > port_to)
 			swap(port, port_to);
-	} else
-		port_to = port;
+	}
 
 	for (; !before(ip_to, ip); ip++)
 		for (p = port; p <= port_to; p++) {
@@ -361,6 +354,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_ipport6_elem data = { };
 	u32 port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -385,21 +379,15 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMPV6:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMPV6))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -407,9 +395,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
 		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 	}
 
-	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
-	    !tb[IPSET_ATTR_PORT_TO]) {
+	if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
 		ret = adtfn(set, &data, timeout);
 		return ip_set_eexist(ret, flags) ? 0 : ret;
 	}
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 22e23abb86c6..4642872df6e1 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -154,6 +154,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_ipportip4_elem data = { };
 	u32 ip, ip_to, p, port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
@@ -180,21 +181,15 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMP:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMP))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -203,7 +198,6 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	}
 
 	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
 	    !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] ||
 	      tb[IPSET_ATTR_PORT_TO])) {
 		ret = adtfn(set, &data, timeout);
@@ -227,13 +221,12 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	} else
 		ip_to = ip;
 
-	port = ntohs(data.port);
-	if (tb[IPSET_ATTR_PORT_TO]) {
+	port_to = port = ntohs(data.port);
+	if (with_ports && tb[IPSET_ATTR_PORT_TO]) {
 		port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
 		if (port > port_to)
 			swap(port, port_to);
-	} else
-		port_to = port;
+	}
 
 	for (; !before(ip_to, ip); ip++)
 		for (p = port; p <= port_to; p++) {
@@ -375,6 +368,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_ipportip6_elem data = { };
 	u32 port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
@@ -403,21 +397,15 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMPV6:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMPV6))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -425,9 +413,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
 		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 	}
 
-	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
-	    !tb[IPSET_ATTR_PORT_TO]) {
+	if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
 		ret = adtfn(set, &data, timeout);
 		return ip_set_eexist(ret, flags) ? 0 : ret;
 	}
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 6033e8b54bbd..2cb84a54b7ad 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -174,6 +174,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_ipportnet4_elem data = { .cidr = HOST_MASK };
 	u32 ip, ip_to, p, port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
@@ -208,21 +209,15 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMP:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMP))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -231,7 +226,6 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	}
 
 	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
 	    !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] ||
 	      tb[IPSET_ATTR_PORT_TO])) {
 		ret = adtfn(set, &data, timeout);
@@ -255,13 +249,12 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	} else
 		ip_to = ip;
 
-	port = ntohs(data.port);
-	if (tb[IPSET_ATTR_PORT_TO]) {
+	port_to = port = ntohs(data.port);
+	if (with_ports && tb[IPSET_ATTR_PORT_TO]) {
 		port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
 		if (port > port_to)
 			swap(port, port_to);
-	} else
-		port_to = port;
+	}
 
 	for (; !before(ip_to, ip); ip++)
 		for (p = port; p <= port_to; p++) {
@@ -429,6 +422,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_ipportnet6_elem data = { .cidr = HOST_MASK };
 	u32 port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
@@ -465,21 +459,15 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMPV6:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMPV6))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -487,9 +475,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 	}
 
-	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
-	    !tb[IPSET_ATTR_PORT_TO]) {
+	if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
 		ret = adtfn(set, &data, timeout);
 		return ip_set_eexist(ret, flags) ? 0 : ret;
 	}
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 34a165626ee9..8598676f2a05 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -170,6 +170,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_netport4_elem data = { .cidr = HOST_MASK };
 	u32 port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -198,21 +199,15 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMP:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMP))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -220,9 +215,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 	}
 
-	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
-	    !tb[IPSET_ATTR_PORT_TO]) {
+	if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
 		ret = adtfn(set, &data, timeout);
 		return ip_set_eexist(ret, flags) ? 0 : ret;
 	}
@@ -390,6 +383,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_netport6_elem data = { .cidr = HOST_MASK };
 	u32 port, port_to;
 	u32 timeout = h->timeout;
+	bool with_ports = false;
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -418,21 +412,15 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_PROTO]) {
 		data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+		with_ports = ip_set_proto_with_ports(data.proto);
 
 		if (data.proto == 0)
 			return -IPSET_ERR_INVALID_PROTO;
 	} else
 		return -IPSET_ERR_MISSING_PROTO;
 
-	switch (data.proto) {
-	case IPPROTO_UDP:
-	case IPPROTO_TCP:
-	case IPPROTO_ICMPV6:
-		break;
-	default:
+	if (!(with_ports || data.proto == IPPROTO_ICMPV6))
 		data.port = 0;
-		break;
-	}
 
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!with_timeout(h->timeout))
@@ -440,9 +428,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
 		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 	}
 
-	if (adt == IPSET_TEST ||
-	    !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) ||
-	    !tb[IPSET_ATTR_PORT_TO]) {
+	if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
 		ret = adtfn(set, &data, timeout);
 		return ip_set_eexist(ret, flags) ? 0 : ret;
 	}
-- 
cgit v1.2.3


From 5c1aba467828bf0574ec5754c84884d573f590af Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Sun, 20 Mar 2011 15:35:01 +0100
Subject: netfilter: ipset: fix checking the type revision at create command

The revision of the set type was not checked at the create command: if the
userspace sent a valid set type but with not supported revision number,
it'd create a loop.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/ipset/ip_set_core.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 618a615acc9d..d6b48230a540 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -94,16 +94,28 @@ static int
 find_set_type_get(const char *name, u8 family, u8 revision,
 		  struct ip_set_type **found)
 {
+	struct ip_set_type *type;
+	int err;
+
 	rcu_read_lock();
 	*found = find_set_type(name, family, revision);
 	if (*found) {
-		int err = !try_module_get((*found)->me);
-		rcu_read_unlock();
-		return err ? -EFAULT : 0;
+		err = !try_module_get((*found)->me) ? -EFAULT : 0;
+		goto unlock;
 	}
+	/* Make sure the type is loaded but we don't support the revision */
+	list_for_each_entry_rcu(type, &ip_set_type_list, list)
+		if (STREQ(type->name, name)) {
+			err = -IPSET_ERR_FIND_TYPE;
+			goto unlock;
+		}
 	rcu_read_unlock();
 
 	return try_to_load_type(name);
+
+unlock:
+	rcu_read_unlock();
+	return err;
 }
 
 /* Find a given set type by name and family.
@@ -116,7 +128,7 @@ find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max)
 	struct ip_set_type *type;
 	bool found = false;
 
-	*min = *max = 0;
+	*min = 255; *max = 0;
 	rcu_read_lock();
 	list_for_each_entry_rcu(type, &ip_set_type_list, list)
 		if (STREQ(type->name, name) &&
@@ -124,7 +136,7 @@ find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max)
 			found = true;
 			if (type->revision < *min)
 				*min = type->revision;
-			else if (type->revision > *max)
+			if (type->revision > *max)
 				*max = type->revision;
 		}
 	rcu_read_unlock();
-- 
cgit v1.2.3


From f40f94fc6c3b5a5542d5ed976e9ff69a3b463802 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 21 Mar 2011 10:15:40 +0000
Subject: ipvs: fix a typo in __ip_vs_control_init()

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Simon Horman <horms@verge.net.au>
Cc: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index b799cea31f95..33733c8872e7 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3605,7 +3605,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 
 	/* procfs stats */
 	ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (ipvs->tot_stats.cpustats) {
+	if (!ipvs->tot_stats.cpustats) {
 		pr_err("%s(): alloc_percpu.\n", __func__);
 		return -ENOMEM;
 	}
-- 
cgit v1.2.3


From 736561a01f11114146b1b7f82d486fa9c95828ef Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Mon, 21 Mar 2011 15:18:01 +0000
Subject: IPVS: Use global mutex in ip_vs_app.c

As part of the work to make IPVS network namespace aware
__ip_vs_app_mutex was replaced by a per-namespace lock,
ipvs->app_mutex. ipvs->app_key is also supplied for debugging purposes.

Unfortunately this implementation results in ipvs->app_key residing
in non-static storage which at the very least causes a lockdep warning.

This patch takes the rather heavy-handed approach of reinstating
__ip_vs_app_mutex which will cover access to the ipvs->list_head
of all network namespaces.

[   12.610000] IPVS: Creating netns size=2456 id=0
[   12.630000] IPVS: Registered protocols (TCP, UDP, SCTP, AH, ESP)
[   12.640000] BUG: key ffff880003bbf1a0 not in .data!
[   12.640000] ------------[ cut here ]------------
[   12.640000] WARNING: at kernel/lockdep.c:2701 lockdep_init_map+0x37b/0x570()
[   12.640000] Hardware name: Bochs
[   12.640000] Pid: 1, comm: swapper Tainted: G        W 2.6.38-kexec-06330-g69b7efe-dirty #122
[   12.650000] Call Trace:
[   12.650000]  [<ffffffff8102e685>] warn_slowpath_common+0x75/0xb0
[   12.650000]  [<ffffffff8102e6d5>] warn_slowpath_null+0x15/0x20
[   12.650000]  [<ffffffff8105967b>] lockdep_init_map+0x37b/0x570
[   12.650000]  [<ffffffff8105829d>] ? trace_hardirqs_on+0xd/0x10
[   12.650000]  [<ffffffff81055ad8>] debug_mutex_init+0x38/0x50
[   12.650000]  [<ffffffff8104bc4c>] __mutex_init+0x5c/0x70
[   12.650000]  [<ffffffff81685ee7>] __ip_vs_app_init+0x64/0x86
[   12.660000]  [<ffffffff81685a3b>] ? ip_vs_init+0x0/0xff
[   12.660000]  [<ffffffff811b1c33>] T.620+0x43/0x170
[   12.660000]  [<ffffffff811b1e9a>] ? register_pernet_subsys+0x1a/0x40
[   12.660000]  [<ffffffff81685a3b>] ? ip_vs_init+0x0/0xff
[   12.660000]  [<ffffffff81685a3b>] ? ip_vs_init+0x0/0xff
[   12.660000]  [<ffffffff811b1db7>] register_pernet_operations+0x57/0xb0
[   12.660000]  [<ffffffff81685a3b>] ? ip_vs_init+0x0/0xff
[   12.670000]  [<ffffffff811b1ea9>] register_pernet_subsys+0x29/0x40
[   12.670000]  [<ffffffff81685f19>] ip_vs_app_init+0x10/0x12
[   12.670000]  [<ffffffff81685a87>] ip_vs_init+0x4c/0xff
[   12.670000]  [<ffffffff8166562c>] do_one_initcall+0x7a/0x12e
[   12.670000]  [<ffffffff8166583e>] kernel_init+0x13e/0x1c2
[   12.670000]  [<ffffffff8128c134>] kernel_thread_helper+0x4/0x10
[   12.670000]  [<ffffffff8128ad40>] ? restore_args+0x0/0x30
[   12.680000]  [<ffffffff81665700>] ? kernel_init+0x0/0x1c2
[   12.680000]  [<ffffffff8128c130>] ? kernel_thread_helper+0x0/0x1global0

Signed-off-by: Simon Horman <horms@verge.net.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netfilter/ipvs/ip_vs_app.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 5c48ffb60c28..2dc6de13ac18 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -43,6 +43,8 @@ EXPORT_SYMBOL(register_ip_vs_app);
 EXPORT_SYMBOL(unregister_ip_vs_app);
 EXPORT_SYMBOL(register_ip_vs_app_inc);
 
+static DEFINE_MUTEX(__ip_vs_app_mutex);
+
 /*
  *	Get an ip_vs_app object
  */
@@ -167,14 +169,13 @@ int
 register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
 		       __u16 port)
 {
-	struct netns_ipvs *ipvs = net_ipvs(net);
 	int result;
 
-	mutex_lock(&ipvs->app_mutex);
+	mutex_lock(&__ip_vs_app_mutex);
 
 	result = ip_vs_app_inc_new(net, app, proto, port);
 
-	mutex_unlock(&ipvs->app_mutex);
+	mutex_unlock(&__ip_vs_app_mutex);
 
 	return result;
 }
@@ -189,11 +190,11 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
-	mutex_lock(&ipvs->app_mutex);
+	mutex_lock(&__ip_vs_app_mutex);
 
 	list_add(&app->a_list, &ipvs->app_list);
 
-	mutex_unlock(&ipvs->app_mutex);
+	mutex_unlock(&__ip_vs_app_mutex);
 
 	return 0;
 }
@@ -205,10 +206,9 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
  */
 void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
-	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_app *inc, *nxt;
 
-	mutex_lock(&ipvs->app_mutex);
+	mutex_lock(&__ip_vs_app_mutex);
 
 	list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
 		ip_vs_app_inc_release(net, inc);
@@ -216,7 +216,7 @@ void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 
 	list_del(&app->a_list);
 
-	mutex_unlock(&ipvs->app_mutex);
+	mutex_unlock(&__ip_vs_app_mutex);
 
 	/* decrease the module use count */
 	ip_vs_use_count_dec();
@@ -501,7 +501,7 @@ static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos)
 	struct net *net = seq_file_net(seq);
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	mutex_lock(&ipvs->app_mutex);
+	mutex_lock(&__ip_vs_app_mutex);
 
 	return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN;
 }
@@ -535,9 +535,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static void ip_vs_app_seq_stop(struct seq_file *seq, void *v)
 {
-	struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq));
-
-	mutex_unlock(&ipvs->app_mutex);
+	mutex_unlock(&__ip_vs_app_mutex);
 }
 
 static int ip_vs_app_seq_show(struct seq_file *seq, void *v)
@@ -583,7 +581,6 @@ static int __net_init __ip_vs_app_init(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	INIT_LIST_HEAD(&ipvs->app_list);
-	__mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key);
 	proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
 	return 0;
 }
-- 
cgit v1.2.3


From 25985edcedea6396277003854657b5f3cb31a628 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@profusion.mobi>
Date: Wed, 30 Mar 2011 22:57:33 -0300
Subject: Fix common misspellings

Fixes generated by 'codespell' and manually reviewed.

Signed-off-by: Lucas De Marchi <lucas.demarchi@profusion.mobi>
---
 net/netfilter/ipset/ip_set_core.c       | 2 +-
 net/netfilter/ipvs/ip_vs_conn.c         | 4 ++--
 net/netfilter/ipvs/ip_vs_lblc.c         | 2 +-
 net/netfilter/ipvs/ip_vs_lblcr.c        | 2 +-
 net/netfilter/ipvs/ip_vs_proto_sctp.c   | 8 ++++----
 net/netfilter/nf_conntrack_core.c       | 4 ++--
 net/netfilter/nf_conntrack_proto_dccp.c | 2 +-
 net/netfilter/nf_conntrack_proto_sctp.c | 6 +++---
 net/netfilter/nf_conntrack_sip.c        | 2 +-
 net/netfilter/nf_queue.c                | 2 +-
 10 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index d6b48230a540..253326e8d990 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -893,7 +893,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 	to = ip_set_list[to_id];
 
 	/* Features must not change.
-	 * Not an artifical restriction anymore, as we must prevent
+	 * Not an artificial restriction anymore, as we must prevent
 	 * possible loops created by swapping in setlist type of sets. */
 	if (!(from->type->features == to->type->features &&
 	      from->type->family == to->type->family))
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index f289306cbf12..c97bd45975be 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -595,7 +595,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
 			atomic_inc(&dest->inactconns);
 	} else {
 		/* It is a persistent connection/template, so increase
-		   the peristent connection counter */
+		   the persistent connection counter */
 		atomic_inc(&dest->persistconns);
 	}
 
@@ -657,7 +657,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 		}
 	} else {
 		/* It is a persistent connection/template, so decrease
-		   the peristent connection counter */
+		   the persistent connection counter */
 		atomic_dec(&dest->persistconns);
 	}
 
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index f276df9896b3..87e40ea77a95 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -131,7 +131,7 @@ static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
 {
 	list_del(&en->list);
 	/*
-	 * We don't kfree dest because it is refered either by its service
+	 * We don't kfree dest because it is referred either by its service
 	 * or the trash dest list.
 	 */
 	atomic_dec(&en->dest->refcnt);
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index cb1c9913d38b..90f618ab6dda 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -152,7 +152,7 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set)
 	write_lock(&set->lock);
 	list_for_each_entry_safe(e, ep, &set->list, list) {
 		/*
-		 * We don't kfree dest because it is refered either
+		 * We don't kfree dest because it is referred either
 		 * by its service or by the trash dest list.
 		 */
 		atomic_dec(&e->dest->refcnt);
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index b027ccc49f43..d12ed53ec95f 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -566,7 +566,7 @@ static struct ipvs_sctp_nextstate
 	 * SHUTDOWN sent from the client, waitinf for SHUT ACK from the server
 	 */
 	/*
-	 * We recieved the data chuck, keep the state unchanged. I assume
+	 * We received the data chuck, keep the state unchanged. I assume
 	 * that still data chuncks  can be received by both the peers in
 	 * SHUDOWN state
 	 */
@@ -633,7 +633,7 @@ static struct ipvs_sctp_nextstate
 	 * SHUTDOWN sent from the server, waitinf for SHUTDOWN ACK from client
 	 */
 	/*
-	 * We recieved the data chuck, keep the state unchanged. I assume
+	 * We received the data chuck, keep the state unchanged. I assume
 	 * that still data chuncks  can be received by both the peers in
 	 * SHUDOWN state
 	 */
@@ -701,7 +701,7 @@ static struct ipvs_sctp_nextstate
 	 * SHUTDOWN ACK from the client, awaiting for SHUTDOWN COM from server
 	 */
 	/*
-	 * We recieved the data chuck, keep the state unchanged. I assume
+	 * We received the data chuck, keep the state unchanged. I assume
 	 * that still data chuncks  can be received by both the peers in
 	 * SHUDOWN state
 	 */
@@ -771,7 +771,7 @@ static struct ipvs_sctp_nextstate
 	 * SHUTDOWN ACK from the server, awaiting for SHUTDOWN COM from client
 	 */
 	/*
-	 * We recieved the data chuck, keep the state unchanged. I assume
+	 * We received the data chuck, keep the state unchanged. I assume
 	 * that still data chuncks  can be received by both the peers in
 	 * SHUDOWN state
 	 */
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 941286ca911d..2e1c11f78419 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -453,7 +453,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	   REJECT will give spurious warnings here. */
 	/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
 
-	/* No external references means noone else could have
+	/* No external references means no one else could have
 	   confirmed us. */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
@@ -901,7 +901,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	ret = l3proto->get_l4proto(skb, skb_network_offset(skb),
 				   &dataoff, &protonum);
 	if (ret <= 0) {
-		pr_debug("not prepared to track yet or error occured\n");
+		pr_debug("not prepared to track yet or error occurred\n");
 		NF_CT_STAT_INC_ATOMIC(net, error);
 		NF_CT_STAT_INC_ATOMIC(net, invalid);
 		ret = -ret;
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 9ae57c57c50e..2e664a69d7db 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -98,7 +98,7 @@ static const char * const dccp_state_names[] = {
 #define sIV	CT_DCCP_INVALID
 
 /*
- * DCCP state transistion table
+ * DCCP state transition table
  *
  * The assumption is the same as for TCP tracking:
  *
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 6f4ee70f460b..6772b1154654 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -107,9 +107,9 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = {
 /* abort        */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
 /* shutdown     */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA},
 /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA},
-/* error        */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant have Stale cookie*/
+/* error        */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't have Stale cookie*/
 /* cookie_echo  */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA},/* 5.2.4 - Big TODO */
-/* cookie_ack   */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant come in orig dir */
+/* cookie_ack   */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in orig dir */
 /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL}
 	},
 	{
@@ -121,7 +121,7 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = {
 /* shutdown     */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA},
 /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA},
 /* error        */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA},
-/* cookie_echo  */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant come in reply dir */
+/* cookie_echo  */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in reply dir */
 /* cookie_ack   */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA},
 /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL}
 	}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index bcf47eb518ef..237cc1981b89 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -707,7 +707,7 @@ static const char *ct_sdp_header_search(const char *dptr, const char *limit,
 }
 
 /* Locate a SDP header (optionally a substring within the header value),
- * optionally stopping at the first occurence of the term header, parse
+ * optionally stopping at the first occurrence of the term header, parse
  * it and return the offset and length of the data we're interested in.
  */
 int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr,
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5ab22e2bbd7d..5b466cd1272f 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -134,7 +134,7 @@ static int __nf_queue(struct sk_buff *skb,
 	const struct nf_afinfo *afinfo;
 	const struct nf_queue_handler *qh;
 
-	/* QUEUE == DROP if noone is waiting, to be safe. */
+	/* QUEUE == DROP if no one is waiting, to be safe. */
 	rcu_read_lock();
 
 	qh = rcu_dereference(queue_handler[pf]);
-- 
cgit v1.2.3


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(-)

(limited to 'net/netfilter')

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>
---
 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 +-
 5 files changed, 71 insertions(+), 53 deletions(-)

(limited to 'net/netfilter')

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(-)

(limited to 'net/netfilter')

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>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/netfilter')

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>
---
 net/netfilter/nf_conntrack_h323_main.c | 8 ++++----
 net/netfilter/xt_TCPMSS.c              | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'net/netfilter')

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>
---
 net/netfilter/nf_conntrack_h323_main.c | 8 ++++----
 net/netfilter/xt_TCPMSS.c              | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'net/netfilter')

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(-)

(limited to 'net/netfilter')

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(-)

(limited to 'net/netfilter')

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


From 0e8a835aa59d08d702af0fcfd296e2218b2e344b Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Wed, 13 Apr 2011 13:43:23 +0200
Subject: netfilter: ipset: bitmap:ip,mac type requires "src" for MAC

Enforce that the second "src/dst" parameter of the set match and SET target
must be "src", because we have access to the source MAC only in the packet.
The previous behaviour, that the type required the second parameter
but actually ignored the value was counter-intuitive and confusing.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/ipset/ip_set_bitmap_ipmac.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 00a33242e90c..a274300b6a56 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -343,6 +343,10 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct ipmac data;
 
+	/* MAC can be src only */
+	if (!(flags & IPSET_DIM_TWO_SRC))
+		return 0;
+
 	data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC));
 	if (data.id < map->first_ip || data.id > map->last_ip)
 		return -IPSET_ERR_BITMAP_RANGE;
-- 
cgit v1.2.3


From eafbd3fde6fc5ada0d61307367e408813b04928a Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Wed, 13 Apr 2011 13:45:57 +0200
Subject: netfilter: ipset: set match and SET target fixes

The SET target with --del-set did not work due to using wrongly
the internal dimension of --add-set instead of --del-set.
Also, the checkentries did not release the set references when
returned an error. Bugs reported by Lennert Buytenhek.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/xt_set.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 061d48cec137..b3babaed7719 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -81,6 +81,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par)
 	if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) {
 		pr_warning("Protocol error: set match dimension "
 			   "is over the limit!\n");
+		ip_set_nfnl_put(info->match_set.index);
 		return -ERANGE;
 	}
 
@@ -135,6 +136,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find del_set index %u as target\n",
 				   info->del_set.index);
+			if (info->add_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(info->add_set.index);
 			return -ENOENT;
 		}
 	}
@@ -142,6 +145,10 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
 	    info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) {
 		pr_warning("Protocol error: SET target dimension "
 			   "is over the limit!\n");
+		if (info->add_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->add_set.index);
+		if (info->del_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->del_set.index);
 		return -ERANGE;
 	}
 
@@ -192,6 +199,7 @@ set_match_checkentry(const struct xt_mtchk_param *par)
 	if (info->match_set.dim > IPSET_DIM_MAX) {
 		pr_warning("Protocol error: set match dimension "
 			   "is over the limit!\n");
+		ip_set_nfnl_put(info->match_set.index);
 		return -ERANGE;
 	}
 
@@ -219,7 +227,7 @@ set_target(struct sk_buff *skb, const struct xt_action_param *par)
 	if (info->del_set.index != IPSET_INVALID_ID)
 		ip_set_del(info->del_set.index,
 			   skb, par->family,
-			   info->add_set.dim,
+			   info->del_set.dim,
 			   info->del_set.flags);
 
 	return XT_CONTINUE;
@@ -245,13 +253,19 @@ set_target_checkentry(const struct xt_tgchk_param *par)
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find del_set index %u as target\n",
 				   info->del_set.index);
+			if (info->add_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(info->add_set.index);
 			return -ENOENT;
 		}
 	}
 	if (info->add_set.dim > IPSET_DIM_MAX ||
-	    info->del_set.flags > IPSET_DIM_MAX) {
+	    info->del_set.dim > IPSET_DIM_MAX) {
 		pr_warning("Protocol error: SET target dimension "
 			   "is over the limit!\n");
+		if (info->add_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->add_set.index);
+		if (info->del_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(info->del_set.index);
 		return -ERANGE;
 	}
 
-- 
cgit v1.2.3


From a8a8a0937e22a5fd55aeb22586724ba6bb70aadd Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 19 Apr 2011 15:59:15 +0200
Subject: netfilter: ipset: Fix the order of listing of sets

A restoreable saving of sets requires that list:set type of sets
come last and the code part which should have taken into account
the ordering was broken. The patch fixes the listing order.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/ipset/ip_set_core.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e88ac3c3ed07..d87e03bc8ef8 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1022,8 +1022,9 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	if (cb->args[1] >= ip_set_max)
 		goto out;
 
-	pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]);
 	max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max;
+dump_last:
+	pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]);
 	for (; cb->args[1] < max; cb->args[1]++) {
 		index = (ip_set_id_t) cb->args[1];
 		set = ip_set_list[index];
@@ -1038,8 +1039,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 		 * so that lists (unions of sets) are dumped last.
 		 */
 		if (cb->args[0] != DUMP_ONE &&
-		    !((cb->args[0] == DUMP_ALL) ^
-		      (set->type->features & IPSET_DUMP_LAST)))
+		    ((cb->args[0] == DUMP_ALL) ==
+		     !!(set->type->features & IPSET_DUMP_LAST)))
 			continue;
 		pr_debug("List set: %s\n", set->name);
 		if (!cb->args[2]) {
@@ -1083,6 +1084,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 			goto release_refcount;
 		}
 	}
+	/* If we dump all sets, continue with dumping last ones */
+	if (cb->args[0] == DUMP_ALL) {
+		cb->args[0] = DUMP_LAST;
+		cb->args[1] = 0;
+		goto dump_last;
+	}
 	goto out;
 
 nla_put_failure:
@@ -1093,11 +1100,6 @@ release_refcount:
 		pr_debug("release set %s\n", ip_set_list[index]->name);
 		ip_set_put_byindex(index);
 	}
-
-	/* If we dump all sets, continue with dumping last ones */
-	if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2])
-		cb->args[0] = DUMP_LAST;
-
 out:
 	if (nlh) {
 		nlmsg_end(skb, nlh);
-- 
cgit v1.2.3