Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6

6 files changed, 74 insertions, 64 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index b9168c1864ca..0e98c3282d42 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -512,11 +512,17 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 			cnt++;
 		}
 
-		if (ct && unlikely(nf_ct_is_dying(ct) ||
-				   !atomic_inc_not_zero(&ct->ct_general.use)))
-			ct = NULL;
-		if (ct || cnt >= NF_CT_EVICTION_RANGE)
+		if (ct != NULL) {
+			if (likely(!nf_ct_is_dying(ct) &&
+				   atomic_inc_not_zero(&ct->ct_general.use)))
+				break;
+			else
+				ct = NULL;
+		}
+
+		if (cnt >= NF_CT_EVICTION_RANGE)
 			break;
+
 		hash = (hash + 1) % nf_conntrack_htable_size;
 	}
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index ba2b76937283..37a8c74be619 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -896,23 +896,54 @@ static int tcp_packet(struct nf_conn *ct,
 			/* b) This SYN/ACK acknowledges a SYN that we earlier
 			 * ignored as invalid. This means that the client and
 			 * the server are both in sync, while the firewall is
-			 * not. We kill this session and block the SYN/ACK so
-			 * that the client cannot but retransmit its SYN and
-			 * thus initiate a clean new session.
+			 * not. We get in sync from the previously annotated
+			 * values.
 			 */
-			spin_unlock_bh(&ct->lock);
-			if (LOG_INVALID(net, IPPROTO_TCP))
-				nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
-					  "nf_ct_tcp: killing out of sync session ");
-			nf_ct_kill(ct);
-			return NF_DROP;
+			old_state = TCP_CONNTRACK_SYN_SENT;
+			new_state = TCP_CONNTRACK_SYN_RECV;
+			ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end =
+				ct->proto.tcp.last_end;
+			ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend =
+				ct->proto.tcp.last_end;
+			ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin =
+				ct->proto.tcp.last_win == 0 ?
+					1 : ct->proto.tcp.last_win;
+			ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
+				ct->proto.tcp.last_wscale;
+			ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
+				ct->proto.tcp.last_flags;
+			memset(&ct->proto.tcp.seen[dir], 0,
+			       sizeof(struct ip_ct_tcp_state));
+			break;
 		}
 		ct->proto.tcp.last_index = index;
 		ct->proto.tcp.last_dir = dir;
 		ct->proto.tcp.last_seq = ntohl(th->seq);
 		ct->proto.tcp.last_end =
 		    segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
-
+		ct->proto.tcp.last_win = ntohs(th->window);
+
+		/* a) This is a SYN in ORIGINAL. The client and the server
+		 * may be in sync but we are not. In that case, we annotate
+		 * the TCP options and let the packet go through. If it is a
+		 * valid SYN packet, the server will reply with a SYN/ACK, and
+		 * then we'll get in sync. Otherwise, the server ignores it. */
+		if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
+			struct ip_ct_tcp_state seen = {};
+
+			ct->proto.tcp.last_flags =
+			ct->proto.tcp.last_wscale = 0;
+			tcp_options(skb, dataoff, th, &seen);
+			if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
+				ct->proto.tcp.last_flags |=
+					IP_CT_TCP_FLAG_WINDOW_SCALE;
+				ct->proto.tcp.last_wscale = seen.td_scale;
+			}
+			if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) {
+				ct->proto.tcp.last_flags |=
+					IP_CT_TCP_FLAG_SACK_PERM;
+			}
+		}
 		spin_unlock_bh(&ct->lock);
 		if (LOG_INVALID(net, IPPROTO_TCP))
 			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 49005482e39a..9de0470d557e 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -666,8 +666,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this,
 {
 	struct netlink_notify *n = ptr;
 
-	if (event == NETLINK_URELEASE &&
-	    n->protocol == NETLINK_NETFILTER && n->pid) {
+	if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) {
 		int i;
 
 		/* destroy all instances for this pid */
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 7a9dec9fb822..7e3fa410641e 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -574,8 +574,7 @@ nfqnl_rcv_nl_event(struct notifier_block *this,
 {
 	struct netlink_notify *n = ptr;
 
-	if (event == NETLINK_URELEASE &&
-	    n->protocol == NETLINK_NETFILTER && n->pid) {
+	if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) {
 		int i;
 
 		/* destroy all instances for this pid */
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 6dc4652f2fe8..ae66305f0fe5 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -113,7 +113,8 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info,
 }
 
 static bool
-conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
+conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par,
+             u16 state_mask, u16 status_mask)
 {
 	const struct xt_conntrack_mtinfo2 *info = par->matchinfo;
 	enum ip_conntrack_info ctinfo;
@@ -136,7 +137,7 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 			if (test_bit(IPS_DST_NAT_BIT, &ct->status))
 				statebit |= XT_CONNTRACK_STATE_DNAT;
 		}
-		if (!!(info->state_mask & statebit) ^
+		if (!!(state_mask & statebit) ^
 		    !(info->invert_flags & XT_CONNTRACK_STATE))
 			return false;
 	}
@@ -172,7 +173,7 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 		return false;
 
 	if ((info->match_flags & XT_CONNTRACK_STATUS) &&
-	    (!!(info->status_mask & ct->status) ^
+	    (!!(status_mask & ct->status) ^
 	    !(info->invert_flags & XT_CONNTRACK_STATUS)))
 		return false;
 
@@ -192,11 +193,17 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 static bool
 conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par)
 {
-	const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo;
-	struct xt_match_param newpar = *par;
+	const struct xt_conntrack_mtinfo1 *info = par->matchinfo;
 
-	newpar.matchinfo = *info;
-	return conntrack_mt(skb, &newpar);
+	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
+}
+
+static bool
+conntrack_mt_v2(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+	const struct xt_conntrack_mtinfo2 *info = par->matchinfo;
+
+	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
 }
 
 static bool conntrack_mt_check(const struct xt_mtchk_param *par)
@@ -209,45 +216,11 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par)
 	return true;
 }
 
-static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par)
-{
-	struct xt_conntrack_mtinfo1 *info = par->matchinfo;
-	struct xt_conntrack_mtinfo2 *up;
-	int ret = conntrack_mt_check(par);
-
-	if (ret < 0)
-		return ret;
-
-	up = kmalloc(sizeof(*up), GFP_KERNEL);
-	if (up == NULL) {
-		nf_ct_l3proto_module_put(par->family);
-		return -ENOMEM;
-	}
-
-	/*
-	 * The strategy here is to minimize the overhead of v1 matching,
-	 * by prebuilding a v2 struct and putting the pointer into the
-	 * v1 dataspace.
-	 */
-	memcpy(up, info, offsetof(typeof(*info), state_mask));
-	up->state_mask  = info->state_mask;
-	up->status_mask = info->status_mask;
-	*(void **)info  = up;
-	return true;
-}
-
 static void conntrack_mt_destroy(const struct xt_mtdtor_param *par)
 {
 	nf_ct_l3proto_module_put(par->family);
 }
 
-static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par)
-{
-	struct xt_conntrack_mtinfo2 **info = par->matchinfo;
-	kfree(*info);
-	conntrack_mt_destroy(par);
-}
-
 static struct xt_match conntrack_mt_reg[] __read_mostly = {
 	{
 		.name       = "conntrack",
@@ -255,8 +228,8 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
 		.family     = NFPROTO_UNSPEC,
 		.matchsize  = sizeof(struct xt_conntrack_mtinfo1),
 		.match      = conntrack_mt_v1,
-		.checkentry = conntrack_mt_check_v1,
-		.destroy    = conntrack_mt_destroy_v1,
+		.checkentry = conntrack_mt_check,
+		.destroy    = conntrack_mt_destroy,
 		.me         = THIS_MODULE,
 	},
 	{
@@ -264,7 +237,7 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
 		.revision   = 2,
 		.family     = NFPROTO_UNSPEC,
 		.matchsize  = sizeof(struct xt_conntrack_mtinfo2),
-		.match      = conntrack_mt,
+		.match      = conntrack_mt_v2,
 		.checkentry = conntrack_mt_check,
 		.destroy    = conntrack_mt_destroy,
 		.me         = THIS_MODULE,
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 362afbd60a96..6a902564d24f 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -192,7 +192,8 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
 		.revision	= 0,
 		.family		= NFPROTO_IPV4,
 		.match		= socket_mt_v0,
-		.hooks		= 1 << NF_INET_PRE_ROUTING,
+		.hooks		= (1 << NF_INET_PRE_ROUTING) |
+				  (1 << NF_INET_LOCAL_IN),
 		.me		= THIS_MODULE,
 	},
 	{
@@ -201,7 +202,8 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
 		.family		= NFPROTO_IPV4,
 		.match		= socket_mt_v1,
 		.matchsize	= sizeof(struct xt_socket_mtinfo1),
-		.hooks		= 1 << NF_INET_PRE_ROUTING,
+		.hooks		= (1 << NF_INET_PRE_ROUTING) |
+				  (1 << NF_INET_LOCAL_IN),
 		.me		= THIS_MODULE,
 	},
 };