Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

8 files changed, 92 insertions, 72 deletions

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index f08e870100f4..72975fa8795d 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -146,7 +146,7 @@ extern void nfnl_unlock(void);
 extern int nfnetlink_subsys_register(struct nfnetlink_subsystem *n);
 extern int nfnetlink_subsys_unregister(struct nfnetlink_subsystem *n);
 
-extern int nfattr_parse(struct nfattr *tb[], int maxattr, 
+extern void nfattr_parse(struct nfattr *tb[], int maxattr, 
 			struct nfattr *nfa, int len);
 
 #define nfattr_parse_nested(tb, max, nfa) \
diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c
index 82a65043a8ef..5c1c0a3d1c4b 100644
--- a/net/ipv4/netfilter/ip_conntrack_netlink.c
+++ b/net/ipv4/netfilter/ip_conntrack_netlink.c
@@ -28,11 +28,8 @@
 #include <linux/netlink.h>
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
-#include <linux/rtnetlink.h>
 
 #include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ip_conntrack.h>
 #include <linux/netfilter_ipv4/ip_conntrack_core.h>
 #include <linux/netfilter_ipv4/ip_conntrack_helper.h>
@@ -58,14 +55,17 @@ ctnetlink_dump_tuples_proto(struct sk_buff *skb,
 			    const struct ip_conntrack_tuple *tuple)
 {
 	struct ip_conntrack_protocol *proto;
+	int ret = 0;
 
 	NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum);
 
 	proto = ip_conntrack_proto_find_get(tuple->dst.protonum);
-	if (proto && proto->tuple_to_nfattr)
-		return proto->tuple_to_nfattr(skb, tuple);
+	if (likely(proto && proto->tuple_to_nfattr)) {
+		ret = proto->tuple_to_nfattr(skb, tuple);
+		ip_conntrack_proto_put(proto);
+	}
 
-	return 0;
+	return ret;
 
 nfattr_failure:
 	return -1;
@@ -175,7 +175,7 @@ ctnetlink_dump_counters(struct sk_buff *skb, const struct ip_conntrack *ct,
 {
 	enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
 	struct nfattr *nest_count = NFA_NEST(skb, type);
-	u_int64_t tmp;
+	u_int32_t tmp;
 
 	tmp = htonl(ct->counters[dir].packets);
 	NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(u_int32_t), &tmp);
@@ -479,9 +479,7 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple)
 
 	DEBUGP("entered %s\n", __FUNCTION__);
 
-	
-	if (nfattr_parse_nested(tb, CTA_IP_MAX, attr) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_IP_MAX, attr);
 
 	if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip))
 		return -EINVAL;
@@ -497,9 +495,6 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple)
 	DEBUGP("leaving\n");
 
 	return 0;
-
-nfattr_failure:
-	return -1;
 }
 
 static const int cta_min_proto[CTA_PROTO_MAX] = {
@@ -521,8 +516,7 @@ ctnetlink_parse_tuple_proto(struct nfattr *attr,
 
 	DEBUGP("entered %s\n", __FUNCTION__);
 
-	if (nfattr_parse_nested(tb, CTA_PROTO_MAX, attr) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_PROTO_MAX, attr);
 
 	if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
 		return -EINVAL;
@@ -539,9 +533,6 @@ ctnetlink_parse_tuple_proto(struct nfattr *attr,
 	}
 	
 	return ret;
-
-nfattr_failure:
-	return -1;
 }
 
 static inline int
@@ -555,8 +546,7 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple,
 
 	memset(tuple, 0, sizeof(*tuple));
 
-	if (nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]);
 
 	if (!tb[CTA_TUPLE_IP-1])
 		return -EINVAL;
@@ -583,9 +573,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple,
 	DEBUGP("leaving\n");
 
 	return 0;
-
-nfattr_failure:
-	return -1;
 }
 
 #ifdef CONFIG_IP_NF_NAT_NEEDED
@@ -603,11 +590,10 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr,
 
 	DEBUGP("entered %s\n", __FUNCTION__);
 
-	if (nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr);
 
 	if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat))
-		goto nfattr_failure;
+		return -EINVAL;
 
 	npt = ip_nat_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
 	if (!npt)
@@ -626,9 +612,6 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr,
 
 	DEBUGP("leaving\n");
 	return 0;
-
-nfattr_failure:
-	return -1;
 }
 
 static inline int
@@ -642,8 +625,7 @@ ctnetlink_parse_nat(struct nfattr *cda[],
 
 	memset(range, 0, sizeof(*range));
 	
-	if (nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]);
 
 	if (tb[CTA_NAT_MINIP-1])
 		range->min_ip = *(u_int32_t *)NFA_DATA(tb[CTA_NAT_MINIP-1]);
@@ -665,9 +647,6 @@ ctnetlink_parse_nat(struct nfattr *cda[],
 
 	DEBUGP("leaving\n");
 	return 0;
-
-nfattr_failure:
-	return -1;
 }
 #endif
 
@@ -678,8 +657,7 @@ ctnetlink_parse_help(struct nfattr *attr, char **helper_name)
 
 	DEBUGP("entered %s\n", __FUNCTION__);
 
-	if (nfattr_parse_nested(tb, CTA_HELP_MAX, attr) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_HELP_MAX, attr);
 
 	if (!tb[CTA_HELP_NAME-1])
 		return -EINVAL;
@@ -687,9 +665,6 @@ ctnetlink_parse_help(struct nfattr *attr, char **helper_name)
 	*helper_name = NFA_DATA(tb[CTA_HELP_NAME-1]);
 
 	return 0;
-
-nfattr_failure:
-	return -1;
 }
 
 static int
@@ -804,7 +779,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	ct = tuplehash_to_ctrack(h);
 
 	err = -ENOMEM;
-	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2) {
 		ip_conntrack_put(ct);
 		return -ENOMEM;
@@ -827,7 +802,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 free:
 	kfree_skb(skb2);
 out:
-	return -1;
+	return err;
 }
 
 static inline int
@@ -957,8 +932,7 @@ ctnetlink_change_protoinfo(struct ip_conntrack *ct, struct nfattr *cda[])
 	u_int16_t npt = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
 	int err = 0;
 
-	if (nfattr_parse_nested(tb, CTA_PROTOINFO_MAX, attr) < 0)
-		goto nfattr_failure;
+	nfattr_parse_nested(tb, CTA_PROTOINFO_MAX, attr);
 
 	proto = ip_conntrack_proto_find_get(npt);
 	if (!proto)
@@ -969,9 +943,6 @@ ctnetlink_change_protoinfo(struct ip_conntrack *ct, struct nfattr *cda[])
 	ip_conntrack_proto_put(proto); 
 
 	return err;
-
-nfattr_failure:
-	return -ENOMEM;
 }
 
 static int
@@ -1005,6 +976,11 @@ ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[])
 			return err;
 	}
 
+#if defined(CONFIG_IP_NF_CONNTRACK_MARK)
+	if (cda[CTA_MARK-1])
+		ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1]));
+#endif
+
 	DEBUGP("all done\n");
 	return 0;
 }
@@ -1048,6 +1024,11 @@ ctnetlink_create_conntrack(struct nfattr *cda[],
 	if (ct->helper)
 		ip_conntrack_helper_put(ct->helper);
 
+#if defined(CONFIG_IP_NF_CONNTRACK_MARK)
+	if (cda[CTA_MARK-1])
+		ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1]));
+#endif
+
 	DEBUGP("conntrack with id %u inserted\n", ct->id);
 	return 0;
 
@@ -1312,6 +1293,14 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 	if (!exp)
 		return -ENOENT;
 
+	if (cda[CTA_EXPECT_ID-1]) {
+		u_int32_t id = *(u_int32_t *)NFA_DATA(cda[CTA_EXPECT_ID-1]);
+		if (exp->id != ntohl(id)) {
+			ip_conntrack_expect_put(exp);
+			return -ENOENT;
+		}
+	}	
+
 	err = -ENOMEM;
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)
@@ -1554,6 +1543,8 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = {
 	.cb				= ctnl_exp_cb,
 };
 
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK);
+
 static int __init ctnetlink_init(void)
 {
 	int ret;
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c
index 98f0015dd255..5198f3a1e2cd 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c
@@ -151,13 +151,13 @@ icmp_error_message(struct sk_buff *skb,
 	/* Not enough header? */
 	inside = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_in), &_in);
 	if (inside == NULL)
-		return NF_ACCEPT;
+		return -NF_ACCEPT;
 
 	/* Ignore ICMP's containing fragments (shouldn't happen) */
 	if (inside->ip.frag_off & htons(IP_OFFSET)) {
 		DEBUGP("icmp_error_track: fragment of proto %u\n",
 		       inside->ip.protocol);
-		return NF_ACCEPT;
+		return -NF_ACCEPT;
 	}
 
 	innerproto = ip_conntrack_proto_find_get(inside->ip.protocol);
@@ -166,7 +166,7 @@ icmp_error_message(struct sk_buff *skb,
 	if (!ip_ct_get_tuple(&inside->ip, skb, dataoff, &origtuple, innerproto)) {
 		DEBUGP("icmp_error: ! get_tuple p=%u", inside->ip.protocol);
 		ip_conntrack_proto_put(innerproto);
-		return NF_ACCEPT;
+		return -NF_ACCEPT;
 	}
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
@@ -174,7 +174,7 @@ icmp_error_message(struct sk_buff *skb,
 	if (!ip_ct_invert_tuple(&innertuple, &origtuple, innerproto)) {
 		DEBUGP("icmp_error_track: Can't invert tuple\n");
 		ip_conntrack_proto_put(innerproto);
-		return NF_ACCEPT;
+		return -NF_ACCEPT;
 	}
 	ip_conntrack_proto_put(innerproto);
 
@@ -190,7 +190,7 @@ icmp_error_message(struct sk_buff *skb,
 
 		if (!h) {
 			DEBUGP("icmp_error_track: no match\n");
-			return NF_ACCEPT;
+			return -NF_ACCEPT;
 		}
 		/* Reverse direction from that found */
 		if (DIRECTION(h) != IP_CT_DIR_REPLY)
@@ -296,7 +296,8 @@ static int icmp_nfattr_to_tuple(struct nfattr *tb[],
 				struct ip_conntrack_tuple *tuple)
 {
 	if (!tb[CTA_PROTO_ICMP_TYPE-1]
-	    || !tb[CTA_PROTO_ICMP_CODE-1])
+	    || !tb[CTA_PROTO_ICMP_CODE-1]
+	    || !tb[CTA_PROTO_ICMP_ID-1])
 		return -1;
 
 	tuple->dst.u.icmp.type = 
@@ -304,7 +305,7 @@ static int icmp_nfattr_to_tuple(struct nfattr *tb[],
 	tuple->dst.u.icmp.code =
 			*(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMP_CODE-1]);
 	tuple->src.u.icmp.id =
-			*(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMP_ID-1]);
+			*(u_int16_t *)NFA_DATA(tb[CTA_PROTO_ICMP_ID-1]);
 
 	return 0;
 }
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
index d6701cafbcc2..468c6003b4c7 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
@@ -362,8 +362,12 @@ static int nfattr_to_tcp(struct nfattr *cda[], struct ip_conntrack *ct)
 	struct nfattr *attr = cda[CTA_PROTOINFO_TCP-1];
 	struct nfattr *tb[CTA_PROTOINFO_TCP_MAX];
 
-        if (nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr) < 0)
-                goto nfattr_failure;
+	/* updates could not contain anything about the private
+	 * protocol info, in that case skip the parsing */
+	if (!attr)
+		return 0;
+
+        nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr);
 
 	if (!tb[CTA_PROTOINFO_TCP_STATE-1])
 		return -EINVAL;
@@ -374,9 +378,6 @@ static int nfattr_to_tcp(struct nfattr *cda[], struct ip_conntrack *ct)
 	write_unlock_bh(&tcp_lock);
 
 	return 0;
-
-nfattr_failure:
-	return -1;
 }
 #endif
 
diff --git a/net/ipv4/netfilter/ip_nat_helper_pptp.c b/net/ipv4/netfilter/ip_nat_helper_pptp.c
index ee6ab74ad3a9..e546203f5662 100644
--- a/net/ipv4/netfilter/ip_nat_helper_pptp.c
+++ b/net/ipv4/netfilter/ip_nat_helper_pptp.c
@@ -73,6 +73,7 @@ static void pptp_nat_expected(struct ip_conntrack *ct,
 	struct ip_conntrack_tuple t;
 	struct ip_ct_pptp_master *ct_pptp_info;
 	struct ip_nat_pptp *nat_pptp_info;
+	struct ip_nat_range range;
 
 	ct_pptp_info = &master->help.ct_pptp_info;
 	nat_pptp_info = &master->nat.help.nat_pptp_info;
@@ -110,7 +111,30 @@ static void pptp_nat_expected(struct ip_conntrack *ct,
 		DEBUGP("not found!\n");
 	}
 
-	ip_nat_follow_master(ct, exp);
+	/* This must be a fresh one. */
+	BUG_ON(ct->status & IPS_NAT_DONE_MASK);
+
+	/* Change src to where master sends to */
+	range.flags = IP_NAT_RANGE_MAP_IPS;
+	range.min_ip = range.max_ip
+		= ct->master->tuplehash[!exp->dir].tuple.dst.ip;
+	if (exp->dir == IP_CT_DIR_ORIGINAL) {
+		range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+		range.min = range.max = exp->saved_proto;
+	}
+	/* hook doesn't matter, but it has to do source manip */
+	ip_nat_setup_info(ct, &range, NF_IP_POST_ROUTING);
+
+	/* For DST manip, map port here to where it's expected. */
+	range.flags = IP_NAT_RANGE_MAP_IPS;
+	range.min_ip = range.max_ip
+		= ct->master->tuplehash[!exp->dir].tuple.src.ip;
+	if (exp->dir == IP_CT_DIR_REPLY) {
+		range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
+		range.min = range.max = exp->saved_proto;
+	}
+	/* hook doesn't matter, but it has to do destination manip */
+	ip_nat_setup_info(ct, &range, NF_IP_PRE_ROUTING);
 }
 
 /* outbound packets == from PNS to PAC */
@@ -213,7 +237,7 @@ pptp_exp_gre(struct ip_conntrack_expect *expect_orig,
 
 	/* alter expectation for PNS->PAC direction */
 	invert_tuplepr(&inv_t, &expect_orig->tuple);
-	expect_orig->saved_proto.gre.key = htons(nat_pptp_info->pac_call_id);
+	expect_orig->saved_proto.gre.key = htons(ct_pptp_info->pns_call_id);
 	expect_orig->tuple.src.u.gre.key = htons(nat_pptp_info->pns_call_id);
 	expect_orig->tuple.dst.u.gre.key = htons(ct_pptp_info->pac_call_id);
 	expect_orig->dir = IP_CT_DIR_ORIGINAL;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b7a5f51238b3..ddcf7754eec2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1022,6 +1022,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
 					continue;
 			}
 
+#ifdef CONFIG_IPV6_PRIVACY
 			/* Rule 7: Prefer public address
 			 * Note: prefer temprary address if use_tempaddr >= 2
 			 */
@@ -1042,7 +1043,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
 				if (hiscore.attrs & IPV6_SADDR_SCORE_PRIVACY)
 					continue;
 			}
-
+#endif
 			/* Rule 8: Use longest matching prefix */
 			if (hiscore.rule < 8)
 				hiscore.matchlen = ipv6_addr_diff(&ifa_result->addr, daddr);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index e6b0e3954c02..e315d0f80af1 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -525,6 +525,7 @@ ip6ip6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
 
 	if ((t = ip6ip6_tnl_lookup(&ipv6h->saddr, &ipv6h->daddr)) != NULL) {
 		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+			read_unlock(&ip6ip6_lock);
 			kfree_skb(skb);
 			return 0;
 		}
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4bc27a6334c1..83f4c53030fc 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -128,7 +128,7 @@ void __nfa_fill(struct sk_buff *skb, int attrtype, int attrlen,
 	memset(NFA_DATA(nfa) + attrlen, 0, NFA_ALIGN(size) - size);
 }
 
-int nfattr_parse(struct nfattr *tb[], int maxattr, struct nfattr *nfa, int len)
+void nfattr_parse(struct nfattr *tb[], int maxattr, struct nfattr *nfa, int len)
 {
 	memset(tb, 0, sizeof(struct nfattr *) * maxattr);
 
@@ -138,8 +138,6 @@ int nfattr_parse(struct nfattr *tb[], int maxattr, struct nfattr *nfa, int len)
 			tb[flavor-1] = nfa;
 		nfa = NFA_NEXT(nfa, len);
 	}
-
-	return 0;
 }
 
 /**
@@ -242,15 +240,18 @@ static inline int nfnetlink_rcv_msg(struct sk_buff *skb,
 	ss = nfnetlink_get_subsys(type);
 	if (!ss) {
 #ifdef CONFIG_KMOD
-		/* don't call nfnl_shunlock, since it would reenter
-		 * with further packet processing */
-		up(&nfnl_sem);
-		request_module("nfnetlink-subsys-%d", NFNL_SUBSYS_ID(type));
-		nfnl_shlock();
-		ss = nfnetlink_get_subsys(type);
+		if (cap_raised(NETLINK_CB(skb).eff_cap, CAP_NET_ADMIN)) {
+			/* don't call nfnl_shunlock, since it would reenter
+			 * with further packet processing */
+			up(&nfnl_sem);
+			request_module("nfnetlink-subsys-%d",
+					NFNL_SUBSYS_ID(type));
+			nfnl_shlock();
+			ss = nfnetlink_get_subsys(type);
+		}
 		if (!ss)
 #endif
-		goto err_inval;
+			goto err_inval;
 	}
 
 	nc = nfnetlink_find_client(type, ss);