Merge commit 'v2.6.39' into for-2.6.40/core

Since for-2.6.40/core was forked off the 2.6.39 devel tree, we've
had churn in the core area that makes it difficult to handle
patches for eg cfq or blk-throttle. Instead of requiring that they
be based in older versions with bugs that have been fixed later
in the rc cycle, merge in 2.6.39 final.

Also fixes up conflicts in the below files.

Conflicts:
	drivers/block/paride/pcd.c
	drivers/cdrom/viocd.c
	drivers/ide/ide-cd.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

11 files changed, 49 insertions, 39 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5345b0bee6df..cd9ca0811cfa 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1680,7 +1680,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
 		return;
 
 	cnf->sysctl = NULL;
-	unregister_sysctl_table(t->sysctl_header);
+	unregister_net_sysctl_table(t->sysctl_header);
 	kfree(t->dev_name);
 	kfree(t);
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e9013d6c1f51..5fe9b8b41df3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1978,9 +1978,6 @@ struct fib_table *fib_trie_table(u32 id)
 	t = (struct trie *) tb->tb_data;
 	memset(t, 0, sizeof(*t));
 
-	if (id == RT_TABLE_LOCAL)
-		pr_info("IPv4 FIB: Using LC-trie version %s\n", VERSION);
-
 	return tb;
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6c0b7f4a3d7d..38f23e721b80 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -73,7 +73,7 @@ int inet_csk_bind_conflict(const struct sock *sk,
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
 			if (!reuse || !sk2->sk_reuse ||
-			    ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) {
+			    sk2->sk_state == TCP_LISTEN) {
 				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
 				    sk2_rcv_saddr == sk_rcv_saddr(sk))
@@ -122,8 +122,7 @@ again:
 					    (tb->num_owners < smallest_size || smallest_size == -1)) {
 						smallest_size = tb->num_owners;
 						smallest_rover = rover;
-						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 &&
-						    !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
 							spin_unlock(&head->lock);
 							snum = smallest_rover;
 							goto have_snum;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index dd1b20eca1a2..9df4e635fb5f 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -354,7 +354,8 @@ static void inetpeer_free_rcu(struct rcu_head *head)
 }
 
 /* May be called with local BH enabled. */
-static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base)
+static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base,
+			     struct inet_peer __rcu **stack[PEER_MAXDEPTH])
 {
 	int do_free;
 
@@ -368,7 +369,6 @@ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base)
 	 * We use refcnt=-1 to alert lockless readers this entry is deleted.
 	 */
 	if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) {
-		struct inet_peer __rcu **stack[PEER_MAXDEPTH];
 		struct inet_peer __rcu ***stackptr, ***delp;
 		if (lookup(&p->daddr, stack, base) != p)
 			BUG();
@@ -422,7 +422,7 @@ static struct inet_peer_base *peer_to_base(struct inet_peer *p)
 }
 
 /* May be called with local BH enabled. */
-static int cleanup_once(unsigned long ttl)
+static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH])
 {
 	struct inet_peer *p = NULL;
 
@@ -454,7 +454,7 @@ static int cleanup_once(unsigned long ttl)
 		 * happen because of entry limits in route cache. */
 		return -1;
 
-	unlink_from_pool(p, peer_to_base(p));
+	unlink_from_pool(p, peer_to_base(p), stack);
 	return 0;
 }
 
@@ -524,7 +524,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 
 	if (base->total >= inet_peer_threshold)
 		/* Remove one less-recently-used entry. */
-		cleanup_once(0);
+		cleanup_once(0, stack);
 
 	return p;
 }
@@ -540,6 +540,7 @@ static void peer_check_expire(unsigned long dummy)
 {
 	unsigned long now = jiffies;
 	int ttl, total;
+	struct inet_peer __rcu **stack[PEER_MAXDEPTH];
 
 	total = compute_total();
 	if (total >= inet_peer_threshold)
@@ -548,7 +549,7 @@ static void peer_check_expire(unsigned long dummy)
 		ttl = inet_peer_maxttl
 				- (inet_peer_maxttl - inet_peer_minttl) / HZ *
 					total / inet_peer_threshold * HZ;
-	while (!cleanup_once(ttl)) {
+	while (!cleanup_once(ttl, stack)) {
 		if (jiffies != now)
 			break;
 	}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a1151b8adf3c..b1d282f11be7 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -223,31 +223,30 @@ static void ip_expire(unsigned long arg)
 
 	if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
 		struct sk_buff *head = qp->q.fragments;
+		const struct iphdr *iph;
+		int err;
 
 		rcu_read_lock();
 		head->dev = dev_get_by_index_rcu(net, qp->iif);
 		if (!head->dev)
 			goto out_rcu_unlock;
 
+		/* skb dst is stale, drop it, and perform route lookup again */
+		skb_dst_drop(head);
+		iph = ip_hdr(head);
+		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+					   iph->tos, head->dev);
+		if (err)
+			goto out_rcu_unlock;
+
 		/*
-		 * Only search router table for the head fragment,
-		 * when defraging timeout at PRE_ROUTING HOOK.
+		 * Only an end host needs to send an ICMP
+		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
-		if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) {
-			const struct iphdr *iph = ip_hdr(head);
-			int err = ip_route_input(head, iph->daddr, iph->saddr,
-						 iph->tos, head->dev);
-			if (unlikely(err))
-				goto out_rcu_unlock;
-
-			/*
-			 * Only an end host needs to send an ICMP
-			 * "Fragment Reassembly Timeout" message, per RFC792.
-			 */
-			if (skb_rtable(head)->rt_type != RTN_LOCAL)
-				goto out_rcu_unlock;
+		if (qp->user == IP_DEFRAG_CONNTRACK_IN &&
+		    skb_rtable(head)->rt_type != RTN_LOCAL)
+			goto out_rcu_unlock;
 
-		}
 
 		/* Send an ICMP "Fragment Reassembly Timeout" message. */
 		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 28a736f3442f..2391b24e8251 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -329,7 +329,7 @@ int ip_options_compile(struct net *net,
 					pp_ptr = optptr + 2;
 					goto error;
 				}
-				if (skb) {
+				if (rt) {
 					memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
 					opt->is_changed = 1;
 				}
@@ -371,7 +371,7 @@ int ip_options_compile(struct net *net,
 						goto error;
 					}
 					opt->ts = optptr - iph;
-					if (skb) {
+					if (rt)  {
 						memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
 						timeptr = (__be32*)&optptr[optptr[2]+3];
 					}
@@ -603,7 +603,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 	unsigned long orefdst;
 	int err;
 
-	if (!opt->srr)
+	if (!opt->srr || !rt)
 		return 0;
 
 	if (skb->pkt_type != PACKET_HOST)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c1acf69858fd..99e6e4bb1c72 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2690,6 +2690,12 @@ static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
 }
 
+static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
+					  unsigned long old)
+{
+	return NULL;
+}
+
 static struct dst_ops ipv4_dst_blackhole_ops = {
 	.family			=	AF_INET,
 	.protocol		=	cpu_to_be16(ETH_P_IP),
@@ -2698,6 +2704,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 	.default_mtu		=	ipv4_blackhole_default_mtu,
 	.default_advmss		=	ipv4_default_advmss,
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
+	.cow_metrics		=	ipv4_rt_blackhole_cow_metrics,
 };
 
 struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1a456652086b..321e6e84dbcc 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -311,7 +311,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_do_large_bitmap,
 	},
-#ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
 		.data		= &sysctl_igmp_max_memberships,
@@ -319,8 +318,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-
-#endif
 	{
 		.procname	= "igmp_max_msf",
 		.data		= &sysctl_igmp_max_msf,
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 34340c9c95fa..f376b05cca81 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,6 +93,7 @@ struct bictcp {
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
 #define ACK_RATIO_SHIFT	4
+#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
 	u16	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
 	u8	sample_cnt;	/* number of samples to decide curr_rtt */
 	u8	found;		/* the exit point is found? */
@@ -398,8 +399,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 	u32 delay;
 
 	if (icsk->icsk_ca_state == TCP_CA_Open) {
-		cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
-		ca->delayed_ack += cnt;
+		u32 ratio = ca->delayed_ack;
+
+		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
+		ratio += cnt;
+
+		ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
 	}
 
 	/* Some calls are for duplicates without timetamps */
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 571aa96a175c..2d51840e53a1 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(xfrm4_prepare_output);
 
-static int xfrm4_output_finish(struct sk_buff *skb)
+int xfrm4_output_finish(struct sk_buff *skb)
 {
 #ifdef CONFIG_NETFILTER
 	if (!skb_dst(skb)->xfrm) {
@@ -86,7 +86,11 @@ static int xfrm4_output_finish(struct sk_buff *skb)
 
 int xfrm4_output(struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
+
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
-			    NULL, skb_dst(skb)->dev, xfrm4_output_finish,
+			    NULL, dst->dev,
+			    x->outer_mode->afinfo->output_finish,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 1717c64628d1..805d63ef4340 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -78,6 +78,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
 	.init_tempsel		= __xfrm4_init_tempsel,
 	.init_temprop		= xfrm4_init_temprop,
 	.output			= xfrm4_output,
+	.output_finish		= xfrm4_output_finish,
 	.extract_input		= xfrm4_extract_input,
 	.extract_output		= xfrm4_extract_output,
 	.transport_finish	= xfrm4_transport_finish,