Merge commit 'v2.6.29' into core/header-fixes

10 files changed, 74 insertions, 43 deletions

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 6bb2635b5de..7bc992976d2 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -3,11 +3,16 @@
  *
  * This is an implementation of the CIPSO 2.2 protocol as specified in
  * draft-ietf-cipso-ipsecurity-01.txt with additional tag types as found in
- * FIPS-188, copies of both documents can be found in the Documentation
- * directory.  While CIPSO never became a full IETF RFC standard many vendors
+ * FIPS-188.  While CIPSO never became a full IETF RFC standard many vendors
  * have chosen to adopt the protocol and over the years it has become a
  * de-facto standard for labeled networking.
  *
+ * The CIPSO draft specification can be found in the kernel's Documentation
+ * directory as well as the following URL:
+ *   http://netlabel.sourceforge.net/files/draft-ietf-cipso-ipsecurity-01.txt
+ * The FIPS-188 specification can be found at the following URL:
+ *   http://www.itl.nist.gov/fipspubs/fip188.htm
+ *
  * Author: Paul Moore <paul.moore@hp.com>
  *
  */
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 705b33b184a..fc562d29cc4 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1205,7 +1205,7 @@ static struct pernet_operations __net_initdata icmp_sk_ops = {
 
 int __init icmp_init(void)
 {
-	return register_pernet_device(&icmp_sk_ops);
+	return register_pernet_subsys(&icmp_sk_ops);
 }
 
 EXPORT_SYMBOL(icmp_err_convert);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 6659ac000ee..7985346653b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -463,6 +463,7 @@ err:
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 			 struct net_device *dev)
 {
+	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct iphdr *iph;
 	struct sk_buff *fp, *head = qp->q.fragments;
 	int len;
@@ -548,7 +549,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	iph = ip_hdr(head);
 	iph->frag_off = 0;
 	iph->tot_len = htons(len);
-	IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMOKS);
+	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
 	return 0;
 
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 42a0f3dd3fd..d722013c1ca 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1268,6 +1268,9 @@ __be32 __init root_nfs_parse_addr(char *name)
 static int __init ip_auto_config(void)
 {
 	__be32 addr;
+#ifdef IPCONFIG_DYNAMIC
+	int retries = CONF_OPEN_RETRIES;
+#endif
 
 #ifdef CONFIG_PROC_FS
 	proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops);
@@ -1304,9 +1307,6 @@ static int __init ip_auto_config(void)
 #endif
 	    ic_first_dev->next) {
 #ifdef IPCONFIG_DYNAMIC
-
-		int retries = CONF_OPEN_RETRIES;
-
 		if (ic_dynamic() < 0) {
 			ic_close_devs();
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0cd71b84e48..76b148bcb0d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -524,7 +524,8 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
 	struct tcp_splice_state *tss = rd_desc->arg.data;
 	int ret;
 
-	ret = skb_splice_bits(skb, offset, tss->pipe, rd_desc->count, tss->flags);
+	ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len),
+			      tss->flags);
 	if (ret > 0)
 		rd_desc->count -= ret;
 	return ret;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a6961d75c7e..c28976a7e59 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1374,7 +1374,8 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
 
 static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 			   struct tcp_sacktag_state *state,
-			   unsigned int pcount, int shifted, int mss)
+			   unsigned int pcount, int shifted, int mss,
+			   int dup_sack)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
@@ -1410,7 +1411,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	}
 
 	/* We discard results */
-	tcp_sacktag_one(skb, sk, state, 0, pcount);
+	tcp_sacktag_one(skb, sk, state, dup_sack, pcount);
 
 	/* Difference in this won't matter, both ACKed by the same cumul. ACK */
 	TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
@@ -1561,7 +1562,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 
 	if (!skb_shift(prev, skb, len))
 		goto fallback;
-	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss))
+	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
 		goto out;
 
 	/* Hole filled allows collapsing with the next as well, this is very
@@ -1580,7 +1581,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	len = skb->len;
 	if (skb_shift(prev, skb, len)) {
 		pcount += tcp_skb_pcount(skb);
-		tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss);
+		tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
 	}
 
 out:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 19d7b429a26..cf74c416831 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2443,7 +2443,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = {
 void __init tcp_v4_init(void)
 {
 	inet_hashinfo_init(&tcp_hashinfo);
-	if (register_pernet_device(&tcp_sk_ops))
+	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 557fe16cbfb..da2c3b8794f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -663,14 +663,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->urg_ptr		= 0;
 
 	/* The urg_mode check is necessary during a below snd_una win probe */
-	if (unlikely(tcp_urg_mode(tp))) {
-		if (between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF)) {
-			th->urg_ptr = htons(tp->snd_up - tcb->seq);
-			th->urg = 1;
-		} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
-			th->urg_ptr = 0xFFFF;
-			th->urg = 1;
-		}
+	if (unlikely(tcp_urg_mode(tp) &&
+		     between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
+		th->urg_ptr		= htons(tp->snd_up - tcb->seq);
+		th->urg			= 1;
 	}
 
 	tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
@@ -2027,7 +2023,6 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		last_lost = tp->snd_una;
 	}
 
-	/* First pass: retransmit lost packets. */
 	tcp_for_write_queue_from(skb, sk) {
 		__u8 sacked = TCP_SKB_CB(skb)->sacked;
 
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 2747ec7bfb6..4660b088a8c 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -1,6 +1,6 @@
 /* Tom Kelly's Scalable TCP
  *
- * See htt://www-lce.eng.cam.ac.uk/~ctk21/scalable/
+ * See http://www.deneholme.net/tom/scalable/
  *
  * John Heffner <jheffner@sc.edu>
  */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cf5ab0581eb..c47c989cb1f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -120,8 +120,11 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min);
 atomic_t udp_memory_allocated;
 EXPORT_SYMBOL(udp_memory_allocated);
 
+#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE)
+
 static int udp_lib_lport_inuse(struct net *net, __u16 num,
 			       const struct udp_hslot *hslot,
+			       unsigned long *bitmap,
 			       struct sock *sk,
 			       int (*saddr_comp)(const struct sock *sk1,
 						 const struct sock *sk2))
@@ -132,12 +135,17 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 	sk_nulls_for_each(sk2, node, &hslot->head)
 		if (net_eq(sock_net(sk2), net)			&&
 		    sk2 != sk					&&
-		    sk2->sk_hash == num				&&
+		    (bitmap || sk2->sk_hash == num)		&&
 		    (!sk2->sk_reuse || !sk->sk_reuse)		&&
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
 			|| sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
-		    (*saddr_comp)(sk, sk2))
-			return 1;
+		    (*saddr_comp)(sk, sk2)) {
+			if (bitmap)
+				__set_bit(sk2->sk_hash / UDP_HTABLE_SIZE,
+					  bitmap);
+			else
+				return 1;
+		}
 	return 0;
 }
 
@@ -160,32 +168,47 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 	if (!snum) {
 		int low, high, remaining;
 		unsigned rand;
-		unsigned short first;
+		unsigned short first, last;
+		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
 
 		inet_get_local_port_range(&low, &high);
 		remaining = (high - low) + 1;
 
 		rand = net_random();
-		snum = first = rand % remaining + low;
-		rand |= 1;
-		for (;;) {
-			hslot = &udptable->hash[udp_hashfn(net, snum)];
+		first = (((u64)rand * remaining) >> 32) + low;
+		/*
+		 * force rand to be an odd multiple of UDP_HTABLE_SIZE
+		 */
+		rand = (rand | 1) * UDP_HTABLE_SIZE;
+		for (last = first + UDP_HTABLE_SIZE; first != last; first++) {
+			hslot = &udptable->hash[udp_hashfn(net, first)];
+			bitmap_zero(bitmap, PORTS_PER_CHAIN);
 			spin_lock_bh(&hslot->lock);
-			if (!udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp))
-				break;
-			spin_unlock_bh(&hslot->lock);
+			udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
+					    saddr_comp);
+
+			snum = first;
+			/*
+			 * Iterate on all possible values of snum for this hash.
+			 * Using steps of an odd multiple of UDP_HTABLE_SIZE
+			 * give us randomization and full range coverage.
+			 */
 			do {
-				snum = snum + rand;
-			} while (snum < low || snum > high);
-			if (snum == first)
-				goto fail;
+				if (low <= snum && snum <= high &&
+				    !test_bit(snum / UDP_HTABLE_SIZE, bitmap))
+					goto found;
+				snum += rand;
+			} while (snum != first);
+			spin_unlock_bh(&hslot->lock);
 		}
+		goto fail;
 	} else {
 		hslot = &udptable->hash[udp_hashfn(net, snum)];
 		spin_lock_bh(&hslot->lock);
-		if (udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp))
+		if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp))
 			goto fail_unlock;
 	}
+found:
 	inet_sk(sk)->num = snum;
 	sk->sk_hash = snum;
 	if (sk_unhashed(sk)) {
@@ -992,9 +1015,11 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
 		/* Note that an ENOMEM error is charged twice */
-		if (rc == -ENOMEM)
+		if (rc == -ENOMEM) {
 			UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
 					 is_udplite);
+			atomic_inc(&sk->sk_drops);
+		}
 		goto drop;
 	}
 
@@ -1206,11 +1231,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
 	struct sock *sk;
-	struct udphdr *uh = udp_hdr(skb);
+	struct udphdr *uh;
 	unsigned short ulen;
 	struct rtable *rt = (struct rtable*)skb->dst;
-	__be32 saddr = ip_hdr(skb)->saddr;
-	__be32 daddr = ip_hdr(skb)->daddr;
+	__be32 saddr, daddr;
 	struct net *net = dev_net(skb->dev);
 
 	/*
@@ -1219,6 +1243,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 		goto drop;		/* No space for header. */
 
+	uh   = udp_hdr(skb);
 	ulen = ntohs(uh->len);
 	if (ulen > skb->len)
 		goto short_packet;
@@ -1233,6 +1258,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
+	saddr = ip_hdr(skb)->saddr;
+	daddr = ip_hdr(skb)->daddr;
+
 	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
 		return __udp4_lib_mcast_deliver(net, skb, uh,
 				saddr, daddr, udptable);