Merge branch 'master' of /repos/git/net-next-2.6

8 files changed, 58 insertions, 81 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index dcb2e18f6f8e..8949a05ac307 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -435,7 +435,9 @@ config INET_DIAG
 	---help---
 	  Support for INET (TCP, DCCP, etc) socket monitoring interface used by
 	  native Linux tools such as ss. ss is included in iproute2, currently
-	  downloadable at <http://linux-net.osdl.org/index.php/Iproute2>.
+	  downloadable at:
+	  
+	    http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2
 
 	  If unsure, say Y.
 
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 880a5ec6dce0..86961bec70ab 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -314,14 +314,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	ah = (struct ip_auth_hdr *)skb->data;
-	iph = ip_hdr(skb);
-	ihl = ip_hdrlen(skb);
 
 	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
 		goto out;
 	nfrags = err;
 
+	ah = (struct ip_auth_hdr *)skb->data;
+	iph = ip_hdr(skb);
+	ihl = ip_hdrlen(skb);
+
 	work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len);
 	if (!work_iph)
 		goto out;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index a2fc7b961dbc..04c8b69fd426 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1143,6 +1143,23 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 	return err;
 }
 
+int arp_invalidate(struct net_device *dev, __be32 ip)
+{
+	struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
+	int err = -ENXIO;
+
+	if (neigh) {
+		if (neigh->nud_state & ~NUD_NOARP)
+			err = neigh_update(neigh, NULL, NUD_FAILED,
+					   NEIGH_UPDATE_F_OVERRIDE|
+					   NEIGH_UPDATE_F_ADMIN);
+		neigh_release(neigh);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(arp_invalidate);
+
 static int arp_req_delete_public(struct net *net, struct arpreq *r,
 		struct net_device *dev)
 {
@@ -1163,7 +1180,6 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
 {
 	int err;
 	__be32 ip;
-	struct neighbour *neigh;
 
 	if (r->arp_flags & ATF_PUBL)
 		return arp_req_delete_public(net, r, dev);
@@ -1181,16 +1197,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
 		if (!dev)
 			return -EINVAL;
 	}
-	err = -ENXIO;
-	neigh = neigh_lookup(&arp_tbl, &ip, dev);
-	if (neigh) {
-		if (neigh->nud_state & ~NUD_NOARP)
-			err = neigh_update(neigh, NULL, NUD_FAILED,
-					   NEIGH_UPDATE_F_OVERRIDE|
-					   NEIGH_UPDATE_F_ADMIN);
-		neigh_release(neigh);
-	}
-	return err;
+	return arp_invalidate(dev, ip);
 }
 
 /*
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 25e318153f14..97e5fb765265 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 ||
-			    sk2->sk_state == TCP_LISTEN) {
+			    ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) {
 				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
 				    sk2_rcv_saddr == sk_rcv_saddr(sk))
@@ -122,7 +122,8 @@ 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) {
+						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 &&
+						    !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
 							spin_unlock(&head->lock);
 							snum = smallest_rover;
 							goto have_snum;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 2ada17129fce..2746c1fa6417 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -858,7 +858,7 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	    nlmsg_len(nlh) < hdrlen)
 		return -EINVAL;
 
-	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) {
 		if (nlmsg_attrlen(nlh, hdrlen)) {
 			struct nlattr *attr;
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 47e5178b998b..e95054c690c6 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -710,42 +710,25 @@ static void get_counters(const struct xt_table_info *t,
 	struct arpt_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu = get_cpu();
-
-	/* Instead of clearing (by a previous call to memset())
-	 * the counters and using adds, we set the counters
-	 * with data used by 'current' CPU
-	 *
-	 * Bottom half has to be disabled to prevent deadlock
-	 * if new softirq were to run and call ipt_do_table
-	 */
-	local_bh_disable();
-	i = 0;
-	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
-		SET_COUNTER(counters[i], iter->counters.bcnt,
-			    iter->counters.pcnt);
-		++i;
-	}
-	local_bh_enable();
-	/* Processing counters from other cpus, we can let bottom half enabled,
-	 * (preemption is disabled)
-	 */
 
 	for_each_possible_cpu(cpu) {
-		if (cpu == curcpu)
-			continue;
+		seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock;
+
 		i = 0;
-		local_bh_disable();
-		xt_info_wrlock(cpu);
 		xt_entry_foreach(iter, t->entries[cpu], t->size) {
-			ADD_COUNTER(counters[i], iter->counters.bcnt,
-				    iter->counters.pcnt);
+			u64 bcnt, pcnt;
+			unsigned int start;
+
+			do {
+				start = read_seqbegin(lock);
+				bcnt = iter->counters.bcnt;
+				pcnt = iter->counters.pcnt;
+			} while (read_seqretry(lock, start));
+
+			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i;
 		}
-		xt_info_wrunlock(cpu);
-		local_bh_enable();
 	}
-	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -759,7 +742,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	 * about).
 	 */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc(countersize);
+	counters = vzalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1008,7 +991,7 @@ static int __do_replace(struct net *net, const char *name,
 	struct arpt_entry *iter;
 
 	ret = 0;
-	counters = vmalloc(num_counters * sizeof(struct xt_counters));
+	counters = vzalloc(num_counters * sizeof(struct xt_counters));
 	if (!counters) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index c5a75d70970f..ef7d7b9680ea 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -884,42 +884,25 @@ get_counters(const struct xt_table_info *t,
 	struct ipt_entry *iter;
 	unsigned int cpu;
 	unsigned int i;
-	unsigned int curcpu = get_cpu();
-
-	/* Instead of clearing (by a previous call to memset())
-	 * the counters and using adds, we set the counters
-	 * with data used by 'current' CPU.
-	 *
-	 * Bottom half has to be disabled to prevent deadlock
-	 * if new softirq were to run and call ipt_do_table
-	 */
-	local_bh_disable();
-	i = 0;
-	xt_entry_foreach(iter, t->entries[curcpu], t->size) {
-		SET_COUNTER(counters[i], iter->counters.bcnt,
-			    iter->counters.pcnt);
-		++i;
-	}
-	local_bh_enable();
-	/* Processing counters from other cpus, we can let bottom half enabled,
-	 * (preemption is disabled)
-	 */
 
 	for_each_possible_cpu(cpu) {
-		if (cpu == curcpu)
-			continue;
+		seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock;
+
 		i = 0;
-		local_bh_disable();
-		xt_info_wrlock(cpu);
 		xt_entry_foreach(iter, t->entries[cpu], t->size) {
-			ADD_COUNTER(counters[i], iter->counters.bcnt,
-				    iter->counters.pcnt);
+			u64 bcnt, pcnt;
+			unsigned int start;
+
+			do {
+				start = read_seqbegin(lock);
+				bcnt = iter->counters.bcnt;
+				pcnt = iter->counters.pcnt;
+			} while (read_seqretry(lock, start));
+
+			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i; /* macro does multi eval of i */
 		}
-		xt_info_wrunlock(cpu);
-		local_bh_enable();
 	}
-	put_cpu();
 }
 
 static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -932,7 +915,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	   (other than comefrom, which userspace doesn't care
 	   about). */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc(countersize);
+	counters = vzalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1204,7 +1187,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	struct ipt_entry *iter;
 
 	ret = 0;
-	counters = vmalloc(num_counters * sizeof(struct xt_counters));
+	counters = vzalloc(num_counters * sizeof(struct xt_counters));
 	if (!counters) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc7c096ddfef..406f320336e6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1350,7 +1350,7 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp,
 	return 0;
 }
 
-/* Intialize TSO state of a skb.
+/* Initialize TSO state of a skb.
  * This must be invoked the first time we consider transmitting
  * SKB onto the wire.
  */