Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6 into lvs-next-2.6

14 files changed, 106 insertions, 51 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8a3ac1fa71a9..1fbff5fa4241 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -469,7 +469,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 */
 	err = -EADDRNOTAVAIL;
 	if (!sysctl_ip_nonlocal_bind &&
-	    !inet->freebind &&
+	    !(inet->freebind || inet->transparent) &&
 	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
 	    chk_addr_ret != RTN_LOCAL &&
 	    chk_addr_ret != RTN_MULTICAST &&
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0c1ae68ee84b..21fcc5a9045f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -335,6 +335,7 @@ struct dst_entry* inet_csk_route_req(struct sock *sk,
 					.saddr = ireq->loc_addr,
 					.tos = RT_CONN_FLAGS(sk) } },
 			    .proto = sk->sk_protocol,
+			    .flags = inet_sk_flowi_flags(sk),
 			    .uli_u = { .ports =
 				       { .sport = inet_sk(sk)->sport,
 					 .dport = ireq->rmt_port } } };
@@ -515,6 +516,8 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
 		newicsk->icsk_bind_hash = NULL;
 
 		inet_sk(newsk)->dport = inet_rsk(req)->rmt_port;
+		inet_sk(newsk)->num = ntohs(inet_rsk(req)->loc_port);
+		inet_sk(newsk)->sport = inet_rsk(req)->loc_port;
 		newsk->sk_write_space = sk_stream_write_space;
 
 		newicsk->icsk_retransmits = 0;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 743f011b9a84..1c5fd38f8824 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -126,6 +126,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
 		tw->tw_reuse	    = sk->sk_reuse;
 		tw->tw_hash	    = sk->sk_hash;
 		tw->tw_ipv6only	    = 0;
+		tw->tw_transparent  = inet->transparent;
 		tw->tw_prot	    = sk->sk_prot_creator;
 		twsk_net_set(tw, hold_net(sock_net(sk)));
 		atomic_set(&tw->tw_refcnt, 1);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d533a89e08de..d2a8f8bb78a6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -340,6 +340,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok)
 							.saddr = inet->saddr,
 							.tos = RT_CONN_FLAGS(sk) } },
 					    .proto = sk->sk_protocol,
+					    .flags = inet_sk_flowi_flags(sk),
 					    .uli_u = { .ports =
 						       { .sport = inet->sport,
 							 .dport = inet->dport } } };
@@ -1371,7 +1372,8 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 				    .uli_u = { .ports =
 					       { .sport = tcp_hdr(skb)->dest,
 						 .dport = tcp_hdr(skb)->source } },
-				    .proto = sk->sk_protocol };
+				    .proto = sk->sk_protocol,
+				    .flags = ip_reply_arg_flowi_flags(arg) };
 		security_skb_classify_flow(skb, &fl);
 		if (ip_route_output_key(sock_net(sk), &rt, &fl))
 			return;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 105d92a039b9..465abf0a9869 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -419,7 +419,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			     (1<<IP_TTL) | (1<<IP_HDRINCL) |
 			     (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) |
 			     (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
-			     (1<<IP_PASSSEC))) ||
+			     (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) ||
 	    optname == IP_MULTICAST_TTL ||
 	    optname == IP_MULTICAST_LOOP) {
 		if (optlen >= sizeof(int)) {
@@ -878,6 +878,16 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
+	case IP_TRANSPARENT:
+		if (!capable(CAP_NET_ADMIN)) {
+			err = -EPERM;
+			break;
+		}
+		if (optlen < 1)
+			goto e_inval;
+		inet->transparent = !!val;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -1130,6 +1140,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_FREEBIND:
 		val = inet->freebind;
 		break;
+	case IP_TRANSPARENT:
+		val = inet->transparent;
+		break;
 	default:
 		release_sock(sk);
 		return -ENOPROTOOPT;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index f8edacdf991d..01671ad51ed3 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -20,6 +20,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	unsigned int type;
 
 	type = inet_addr_type(&init_net, iph->saddr);
+	if (skb->sk && inet_sk(skb->sk)->transparent)
+		type = RTN_LOCAL;
 	if (addr_type == RTN_UNSPEC)
 		addr_type = type;
 
@@ -33,6 +35,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 		fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
 		fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
 		fl.mark = skb->mark;
+		fl.flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
 		if (ip_route_output_key(&init_net, &rt, &fl) != 0)
 			return -1;
 
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index 11976ea29884..112dcfa12900 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -16,6 +16,7 @@
 #include <linux/udp.h>
 #include <net/checksum.h>
 #include <net/tcp.h>
+#include <net/route.h>
 
 #include <linux/netfilter_ipv4.h>
 #include <net/netfilter/nf_conntrack.h>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f62187bb6d08..a6d7c584f53b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2361,11 +2361,6 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 		    ipv4_is_zeronet(oldflp->fl4_src))
 			goto out;
 
-		/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
-		dev_out = ip_dev_find(net, oldflp->fl4_src);
-		if (dev_out == NULL)
-			goto out;
-
 		/* I removed check for oif == dev_out->oif here.
 		   It was wrong for two reasons:
 		   1. ip_dev_find(net, saddr) can return wrong iface, if saddr
@@ -2377,6 +2372,11 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 		if (oldflp->oif == 0
 		    && (ipv4_is_multicast(oldflp->fl4_dst) ||
 			oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
+			dev_out = ip_dev_find(net, oldflp->fl4_src);
+			if (dev_out == NULL)
+				goto out;
+
 			/* Special hack: user can direct multicasts
 			   and limited broadcast via necessary interface
 			   without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
@@ -2395,9 +2395,15 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 			fl.oif = dev_out->ifindex;
 			goto make_route;
 		}
-		if (dev_out)
+
+		if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) {
+			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
+			dev_out = ip_dev_find(net, oldflp->fl4_src);
+			if (dev_out == NULL)
+				goto out;
 			dev_put(dev_out);
-		dev_out = NULL;
+			dev_out = NULL;
+		}
 	}
 
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 9d38005abbac..d346c22aa6ae 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -16,6 +16,7 @@
 #include <linux/cryptohash.h>
 #include <linux/kernel.h>
 #include <net/tcp.h>
+#include <net/route.h>
 
 /* Timestamps: lowest 9 bits store TCP options */
 #define TSBITS 9
@@ -296,6 +297,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	req->mss		= mss;
+	ireq->loc_port		= th->dest;
 	ireq->rmt_port		= th->source;
 	ireq->loc_addr		= ip_hdr(skb)->daddr;
 	ireq->rmt_addr		= ip_hdr(skb)->saddr;
@@ -337,6 +339,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 						.saddr = ireq->loc_addr,
 						.tos = RT_CONN_FLAGS(sk) } },
 				    .proto = IPPROTO_TCP,
+				    .flags = inet_sk_flowi_flags(sk),
 				    .uli_u = { .ports =
 					       { .sport = th->dest,
 						 .dport = th->source } } };
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1ab341e5d3e0..7d81a1ee5507 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -384,13 +384,17 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	/* Connected? */
 	if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+		int target = sock_rcvlowat(sk, 0, INT_MAX);
+
+		if (tp->urg_seq == tp->copied_seq &&
+		    !sock_flag(sk, SOCK_URGINLINE) &&
+		    tp->urg_data)
+			target--;
+
 		/* Potential race condition. If read of tp below will
 		 * escape above sk->sk_state, we can be illegally awaken
 		 * in SYN_* states. */
-		if ((tp->rcv_nxt != tp->copied_seq) &&
-		    (tp->urg_seq != tp->copied_seq ||
-		     tp->rcv_nxt != tp->copied_seq + 1 ||
-		     sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data))
+		if (tp->rcv_nxt - tp->copied_seq >= target)
 			mask |= POLLIN | POLLRDNORM;
 
 		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 85627f83665f..3b76bce769dd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1746,6 +1746,8 @@ int tcp_use_frto(struct sock *sk)
 		return 0;
 
 	skb = tcp_write_queue_head(sk);
+	if (tcp_skb_is_last(sk, skb))
+		return 1;
 	skb = tcp_write_queue_next(sk, skb);	/* Skips head */
 	tcp_for_write_queue_from(skb, sk) {
 		if (skb == tcp_send_head(sk))
@@ -4156,7 +4158,7 @@ drop:
 				skb1 = skb1->prev;
 			}
 		}
-		__skb_insert(skb, skb1, skb1->next, &tp->out_of_order_queue);
+		__skb_queue_after(&tp->out_of_order_queue, skb1, skb);
 
 		/* And clean segments covered by new one as whole. */
 		while ((skb1 = skb->next) !=
@@ -4254,7 +4256,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list,
 		memcpy(nskb->head, skb->head, header);
 		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
 		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
-		__skb_insert(nskb, skb->prev, skb, list);
+		__skb_queue_before(list, skb, nskb);
 		skb_set_owner_r(nskb, sk);
 
 		/* Copy data, releasing collapsed skbs. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 44aef1c1f373..8b24bd833cb4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -591,6 +591,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 				      ip_hdr(skb)->saddr, /* XXX */
 				      sizeof(struct tcphdr), IPPROTO_TCP, 0);
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
+	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
 
 	net = dev_net(skb->dst->dev);
 	ip_send_reply(net->ipv4.tcp_sock, skb,
@@ -606,7 +607,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 ts, int oif,
-			    struct tcp_md5sig_key *key)
+			    struct tcp_md5sig_key *key,
+			    int reply_flags)
 {
 	struct tcphdr *th = tcp_hdr(skb);
 	struct {
@@ -618,7 +620,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net(skb->dst->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -659,6 +661,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 				    ip_hdr(skb)->daddr, &rep.th);
 	}
 #endif
+	arg.flags = reply_flags;
 	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
 				      ip_hdr(skb)->saddr, /* XXX */
 				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
@@ -681,7 +684,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcptw->tw_ts_recent,
 			tw->tw_bound_dev_if,
-			tcp_twsk_md5_key(tcptw)
+			tcp_twsk_md5_key(tcptw),
+			tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
 			);
 
 	inet_twsk_put(tw);
@@ -694,7 +698,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
 			req->ts_recent,
 			0,
-			tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr));
+			tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
+			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
 }
 
 /*
@@ -1244,6 +1249,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq = inet_rsk(req);
 	ireq->loc_addr = daddr;
 	ireq->rmt_addr = saddr;
+	ireq->no_srccheck = inet_sk(sk)->transparent;
 	ireq->opt = tcp_v4_save_options(sk, skb);
 	if (!want_cookie)
 		TCP_ECN_create_request(req, tcp_hdr(skb));
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c3d58ee3e16f..493553c71d32 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1932,8 +1932,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	/* Collapse two adjacent packets if worthwhile and we can. */
 	if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) &&
 	    (skb->len < (cur_mss >> 1)) &&
-	    (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) &&
 	    (!tcp_skb_is_last(sk, skb)) &&
+	    (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) &&
 	    (skb_shinfo(skb)->nr_frags == 0 &&
 	     skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) &&
 	    (tcp_skb_pcount(skb) == 1 &&
@@ -2275,7 +2275,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->syn = 1;
 	th->ack = 1;
 	TCP_ECN_make_synack(req, th);
-	th->source = inet_sk(sk)->sport;
+	th->source = ireq->loc_port;
 	th->dest = ireq->rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
 	 * not even correctly set)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8e42fbbd5761..c83d0ef469c9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -302,6 +302,13 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 	return result;
 }
 
+struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+			     __be32 daddr, __be16 dport, int dif)
+{
+	return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, udp_hash);
+}
+EXPORT_SYMBOL_GPL(udp4_lib_lookup);
+
 static inline struct sock *udp_v4_mcast_next(struct sock *sk,
 					     __be16 loc_port, __be32 loc_addr,
 					     __be16 rmt_port, __be32 rmt_addr,
@@ -951,6 +958,27 @@ int udp_disconnect(struct sock *sk, int flags)
 	return 0;
 }
 
+static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	int is_udplite = IS_UDPLITE(sk);
+	int rc;
+
+	if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
+		/* Note that an ENOMEM error is charged twice */
+		if (rc == -ENOMEM)
+			UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+					 is_udplite);
+		goto drop;
+	}
+
+	return 0;
+
+drop:
+	UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+	kfree_skb(skb);
+	return -1;
+}
+
 /* returns:
  *  -1: error
  *   0: success
@@ -989,9 +1017,7 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 		    up->encap_rcv != NULL) {
 			int ret;
 
-			bh_unlock_sock(sk);
 			ret = (*up->encap_rcv)(sk, skb);
-			bh_lock_sock(sk);
 			if (ret <= 0) {
 				UDP_INC_STATS_BH(sock_net(sk),
 						 UDP_MIB_INDATAGRAMS,
@@ -1044,17 +1070,16 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 			goto drop;
 	}
 
-	if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
-		/* Note that an ENOMEM error is charged twice */
-		if (rc == -ENOMEM) {
-			UDP_INC_STATS_BH(sock_net(sk),
-					UDP_MIB_RCVBUFERRORS, is_udplite);
-			atomic_inc(&sk->sk_drops);
-		}
-		goto drop;
-	}
+	rc = 0;
 
-	return 0;
+	bh_lock_sock(sk);
+	if (!sock_owned_by_user(sk))
+		rc = __udp_queue_rcv_skb(sk, skb);
+	else
+		sk_add_backlog(sk, skb);
+	bh_unlock_sock(sk);
+
+	return rc;
 
 drop:
 	UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
@@ -1092,15 +1117,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 				skb1 = skb_clone(skb, GFP_ATOMIC);
 
 			if (skb1) {
-				int ret = 0;
-
-				bh_lock_sock(sk);
-				if (!sock_owned_by_user(sk))
-					ret = udp_queue_rcv_skb(sk, skb1);
-				else
-					sk_add_backlog(sk, skb1);
-				bh_unlock_sock(sk);
-
+				int ret = udp_queue_rcv_skb(sk, skb1);
 				if (ret > 0)
 					/* we should probably re-process instead
 					 * of dropping packets here. */
@@ -1195,13 +1212,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 			uh->dest, inet_iif(skb), udptable);
 
 	if (sk != NULL) {
-		int ret = 0;
-		bh_lock_sock(sk);
-		if (!sock_owned_by_user(sk))
-			ret = udp_queue_rcv_skb(sk, skb);
-		else
-			sk_add_backlog(sk, skb);
-		bh_unlock_sock(sk);
+		int ret = udp_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but
@@ -1494,7 +1505,7 @@ struct proto udp_prot = {
 	.sendmsg	   = udp_sendmsg,
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
-	.backlog_rcv	   = udp_queue_rcv_skb,
+	.backlog_rcv	   = __udp_queue_rcv_skb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v4_get_port,