Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
  [IPV4]: Explicitly call fib_get_table() in fib_frontend.c
  [NET]: Use BUILD_BUG_ON in net/core/flowi.c
  [NET]: Remove in-code externs for some functions from net/core/dev.c
  [NET]: Don't declare extern variables in net/core/sysctl_net_core.c
  [TCP]: Remove unneeded implicit type cast when calling tcp_minshall_update()
  [NET]: Treat the sign of the result of skb_headroom() consistently
  [9P]: Fix missing unlock before return in p9_mux_poll_start
  [PKT_SCHED]: Fix sch_prio.c build with CONFIG_NETDEVICES_MULTIQUEUE
  [IPV4] ip_gre: sendto/recvfrom NBMA address
  [SCTP]: Consolidate sctp_ulpq_renege_xxx functions
  [NETLINK]: Fix ACK processing after netlink_dump_start
  [VLAN]: MAINTAINERS update
  [DCCP]: Implement SIOCINQ/FIONREAD
  [NET]: Validate device addr prior to interface-up

20 files changed, 117 insertions, 75 deletions

diff --git a/net/9p/mux.c b/net/9p/mux.c
index f14014793bed..c9f0805048e4 100644
--- a/net/9p/mux.c
+++ b/net/9p/mux.c
@@ -222,8 +222,10 @@ static int p9_mux_poll_start(struct p9_conn *m)
 	}
 
 	if (i >= ARRAY_SIZE(p9_mux_poll_tasks)) {
-		if (vptlast == NULL)
+		if (vptlast == NULL) {
+			mutex_unlock(&p9_mux_task_lock);
 			return -ENOMEM;
+		}
 
 		P9_DPRINTK(P9_DEBUG_MUX, "put in proc %d\n", i);
 		list_add(&m->mux_list, &vptlast->mux_list);
diff --git a/net/core/dev.c b/net/core/dev.c
index 872658927e47..f1647d7dd14b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -120,6 +120,8 @@
 #include <linux/ctype.h>
 #include <linux/if_arp.h>
 
+#include "net-sysfs.h"
+
 /*
  *	The list of packet types we will receive (as opposed to discard)
  *	and the routines to invoke.
@@ -249,10 +251,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
 
 DEFINE_PER_CPU(struct softnet_data, softnet_data);
 
-extern int netdev_kobject_init(void);
-extern int netdev_register_kobject(struct net_device *);
-extern void netdev_unregister_kobject(struct net_device *);
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 /*
  * register_netdevice() inits dev->_xmit_lock and sets lockdep class
@@ -1007,17 +1005,20 @@ int dev_open(struct net_device *dev)
 	 *	Call device private open method
 	 */
 	set_bit(__LINK_STATE_START, &dev->state);
-	if (dev->open) {
+
+	if (dev->validate_addr)
+		ret = dev->validate_addr(dev);
+
+	if (!ret && dev->open)
 		ret = dev->open(dev);
-		if (ret)
-			clear_bit(__LINK_STATE_START, &dev->state);
-	}
 
 	/*
 	 *	If it went open OK then:
 	 */
 
-	if (!ret) {
+	if (ret)
+		clear_bit(__LINK_STATE_START, &dev->state);
+	else {
 		/*
 		 *	Set the flags.
 		 */
@@ -1038,6 +1039,7 @@ int dev_open(struct net_device *dev)
 		 */
 		call_netdevice_notifiers(NETDEV_UP, dev);
 	}
+
 	return ret;
 }
 
diff --git a/net/core/flow.c b/net/core/flow.c
index 0ab5234b17d8..3ed2b4b1d6d4 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -142,8 +142,6 @@ typedef u64 flow_compare_t;
 typedef u32 flow_compare_t;
 #endif
 
-extern void flowi_is_missized(void);
-
 /* I hear what you're saying, use memcmp.  But memcmp cannot make
  * important assumptions that we can here, such as alignment and
  * constant size.
@@ -153,8 +151,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2)
 	flow_compare_t *k1, *k1_lim, *k2;
 	const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t);
 
-	if (sizeof(struct flowi) % sizeof(flow_compare_t))
-		flowi_is_missized();
+	BUILD_BUG_ON(sizeof(struct flowi) % sizeof(flow_compare_t));
 
 	k1 = (flow_compare_t *) key1;
 	k1_lim = k1 + n_elem;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 6628e457ddc0..61ead1d11132 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -18,6 +18,8 @@
 #include <linux/wireless.h>
 #include <net/iw_handler.h>
 
+#include "net-sysfs.h"
+
 #ifdef CONFIG_SYSFS
 static const char fmt_hex[] = "%#x\n";
 static const char fmt_long_hex[] = "%#lx\n";
diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h
new file mode 100644
index 000000000000..f5f108db3924
--- /dev/null
+++ b/net/core/net-sysfs.h
@@ -0,0 +1,8 @@
+#ifndef __NET_SYSFS_H__
+#define __NET_SYSFS_H__
+
+int netdev_kobject_init(void);
+int netdev_register_kobject(struct net_device *);
+void netdev_unregister_kobject(struct net_device *);
+
+#endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 6d5ea9762040..113cc728dc31 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -9,25 +9,12 @@
 #include <linux/sysctl.h>
 #include <linux/module.h>
 #include <linux/socket.h>
+#include <linux/netdevice.h>
 #include <net/sock.h>
+#include <net/xfrm.h>
 
 #ifdef CONFIG_SYSCTL
 
-extern int netdev_max_backlog;
-extern int weight_p;
-
-extern __u32 sysctl_wmem_max;
-extern __u32 sysctl_rmem_max;
-
-extern int sysctl_core_destroy_delay;
-
-#ifdef CONFIG_XFRM
-extern u32 sysctl_xfrm_aevent_etime;
-extern u32 sysctl_xfrm_aevent_rseqth;
-extern int sysctl_xfrm_larval_drop;
-extern u32 sysctl_xfrm_acq_expires;
-#endif
-
 ctl_table core_table[] = {
 #ifdef CONFIG_NET
 	{
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index cc9bf1cb2646..d84973928033 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -26,6 +26,7 @@
 #include <net/sock.h>
 #include <net/xfrm.h>
 
+#include <asm/ioctls.h>
 #include <asm/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/timer.h>
@@ -378,8 +379,36 @@ EXPORT_SYMBOL_GPL(dccp_poll);
 
 int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
-	dccp_pr_debug("entry\n");
-	return -ENOIOCTLCMD;
+	int rc = -ENOTCONN;
+
+	lock_sock(sk);
+
+	if (sk->sk_state == DCCP_LISTEN)
+		goto out;
+
+	switch (cmd) {
+	case SIOCINQ: {
+		struct sk_buff *skb;
+		unsigned long amount = 0;
+
+		skb = skb_peek(&sk->sk_receive_queue);
+		if (skb != NULL) {
+			/*
+			 * We will only return the amount of this packet since
+			 * that is all that will be read.
+			 */
+			amount = skb->len;
+		}
+		rc = put_user(amount, (int __user *)arg);
+	}
+		break;
+	default:
+		rc = -ENOIOCTLCMD;
+		break;
+	}
+out:
+	release_sock(sk);
+	return rc;
 }
 
 EXPORT_SYMBOL_GPL(dccp_ioctl);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index ed8a3d49487d..6b2e454ae313 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -298,6 +298,14 @@ static int eth_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+static int eth_validate_addr(struct net_device *dev)
+{
+	if (!is_valid_ether_addr(dev->dev_addr))
+		return -EINVAL;
+
+	return 0;
+}
+
 const struct header_ops eth_header_ops ____cacheline_aligned = {
 	.create		= eth_header,
 	.parse		= eth_header_parse,
@@ -317,6 +325,7 @@ void ether_setup(struct net_device *dev)
 
 	dev->change_mtu		= eth_change_mtu;
 	dev->set_mac_address 	= eth_mac_addr;
+	dev->validate_addr	= eth_validate_addr;
 
 	dev->type		= ARPHRD_ETHER;
 	dev->hard_header_len 	= ETH_HLEN;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 78b514ba1414..60123905dbbf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -128,13 +128,14 @@ struct net_device * ip_dev_find(__be32 addr)
 	struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
 	struct fib_result res;
 	struct net_device *dev = NULL;
+	struct fib_table *local_table;
 
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	res.r = NULL;
 #endif
 
-	if (!ip_fib_local_table ||
-	    ip_fib_local_table->tb_lookup(ip_fib_local_table, &fl, &res))
+	local_table = fib_get_table(RT_TABLE_LOCAL);
+	if (!local_table || local_table->tb_lookup(local_table, &fl, &res))
 		return NULL;
 	if (res.type != RTN_LOCAL)
 		goto out;
@@ -152,6 +153,7 @@ unsigned inet_addr_type(__be32 addr)
 	struct flowi		fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
 	struct fib_result	res;
 	unsigned ret = RTN_BROADCAST;
+	struct fib_table *local_table;
 
 	if (ZERONET(addr) || BADCLASS(addr))
 		return RTN_BROADCAST;
@@ -162,10 +164,10 @@ unsigned inet_addr_type(__be32 addr)
 	res.r = NULL;
 #endif
 
-	if (ip_fib_local_table) {
+	local_table = fib_get_table(RT_TABLE_LOCAL);
+	if (local_table) {
 		ret = RTN_UNICAST;
-		if (!ip_fib_local_table->tb_lookup(ip_fib_local_table,
-						   &fl, &res)) {
+		if (!local_table->tb_lookup(local_table, &fl, &res)) {
 			ret = res.type;
 			fib_res_put(&res);
 		}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f151900efaf9..02b02a8d681c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -674,7 +674,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct rtable *rt;     			/* Route to the other host */
 	struct net_device *tdev;			/* Device to other host */
 	struct iphdr  *iph;			/* Our new IP header */
-	int    max_headroom;			/* The extra header space needed */
+	unsigned int max_headroom;		/* The extra header space needed */
 	int    gre_hlen;
 	__be32 dst;
 	int    mtu;
@@ -1033,7 +1033,6 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-#ifdef CONFIG_NET_IPGRE_BROADCAST
 /* Nice toy. Unfortunately, useless in real life :-)
    It allows to construct virtual multiprotocol broadcast "LAN"
    over the Internet, provided multicast routing is tuned.
@@ -1092,10 +1091,19 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
 	return -t->hlen;
 }
 
+static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+	struct iphdr *iph = (struct iphdr*) skb_mac_header(skb);
+	memcpy(haddr, &iph->saddr, 4);
+	return 4;
+}
+
 static const struct header_ops ipgre_header_ops = {
 	.create	= ipgre_header,
+	.parse	= ipgre_header_parse,
 };
 
+#ifdef CONFIG_NET_IPGRE_BROADCAST
 static int ipgre_open(struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
@@ -1197,6 +1205,8 @@ static int ipgre_tunnel_init(struct net_device *dev)
 			dev->stop = ipgre_close;
 		}
 #endif
+	} else {
+		dev->header_ops = &ipgre_header_ops;
 	}
 
 	if (!tdev && tunnel->parms.link)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index f508835ba713..e5f7dc2de303 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -161,7 +161,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	struct dst_entry *dst = skb->dst;
 	struct rtable *rt = (struct rtable *)dst;
 	struct net_device *dev = dst->dev;
-	int hh_len = LL_RESERVED_SPACE(dev);
+	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 
 	if (rt->rt_type == RTN_MULTICAST)
 		IP_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 5cd5bbe1379a..8c2b2b0741da 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -515,7 +515,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device *tdev;			/* Device to other host */
 	struct iphdr  *old_iph = ip_hdr(skb);
 	struct iphdr  *iph;			/* Our new IP header */
-	int    max_headroom;			/* The extra header space needed */
+	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
 	int    mtu;
 
diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c
index d0a92dec1050..7c074e386c17 100644
--- a/net/ipv4/ipvs/ip_vs_xmit.c
+++ b/net/ipv4/ipvs/ip_vs_xmit.c
@@ -325,7 +325,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	__be16 df = old_iph->frag_off;
 	sk_buff_data_t old_transport_header = skb->transport_header;
 	struct iphdr  *iph;			/* Our new IP header */
-	int    max_headroom;			/* The extra header space needed */
+	unsigned int max_headroom;		/* The extra header space needed */
 	int    mtu;
 
 	EnterFunction(10);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9288220b73a8..3dbbb44b3e7d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3909,7 +3909,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list,
 
 	while (before(start, end)) {
 		struct sk_buff *nskb;
-		int header = skb_headroom(skb);
+		unsigned int header = skb_headroom(skb);
 		int copy = SKB_MAX_ORDER(header, 0);
 
 		/* Too big header? This can happen with IPv6. */
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 13565dfb1b45..653fc0a8235b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -171,7 +171,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	u32 mtu;
 
 	if (opt) {
-		int head_room;
+		unsigned int head_room;
 
 		/* First: exthdrs may take lots of space (~8K for now)
 		   MAX_HEADER is not enough.
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2320cc27ff9e..5383b33db8ca 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -838,7 +838,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	struct dst_entry *dst;
 	struct net_device *tdev;
 	int mtu;
-	int max_headroom = sizeof(struct ipv6hdr);
+	unsigned int max_headroom = sizeof(struct ipv6hdr);
 	u8 proto;
 	int err = -1;
 	int pkt_len;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 466657a9a8bd..71433d29d884 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -430,7 +430,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct rtable *rt;     			/* Route to the other host */
 	struct net_device *tdev;			/* Device to other host */
 	struct iphdr  *iph;			/* Our new IP header */
-	int    max_headroom;			/* The extra header space needed */
+	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
 	int    mtu;
 	struct in6_addr *addr6;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 98e313e5e594..325272925d0f 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1565,7 +1565,11 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 
 	netlink_dump(sk);
 	sock_put(sk);
-	return 0;
+
+	/* We successfully started a dump, by returning -EINTR we
+	 * signal not to send ACK even if it was requested.
+	 */
+	return -EINTR;
 }
 
 void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
@@ -1619,17 +1623,21 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
 
 		/* Only requests are handled by the kernel */
 		if (!(nlh->nlmsg_flags & NLM_F_REQUEST))
-			goto skip;
+			goto ack;
 
 		/* Skip control messages */
 		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
-			goto skip;
+			goto ack;
 
 		err = cb(skb, nlh);
-skip:
+		if (err == -EINTR)
+			goto skip;
+
+ack:
 		if (nlh->nlmsg_flags & NLM_F_ACK || err)
 			netlink_ack(skb, nlh, err);
 
+skip:
 	        msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
 			msglen = skb->len;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index abd82fc3ec60..de894096e442 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -136,7 +136,7 @@ prio_dequeue(struct Qdisc* sch)
 		 * pulling an skb.  This way we avoid excessive requeues
 		 * for slower queues.
 		 */
-		if (!netif_subqueue_stopped(sch->dev, (q->mq ? prio : 0))) {
+		if (!__netif_subqueue_stopped(sch->dev, (q->mq ? prio : 0))) {
 			qdisc = q->queues[prio];
 			skb = qdisc->dequeue(qdisc);
 			if (skb) {
@@ -165,7 +165,7 @@ static struct sk_buff *rr_dequeue(struct Qdisc* sch)
 		 * for slower queues.  If the queue is stopped, try the
 		 * next queue.
 		 */
-		if (!netif_subqueue_stopped(sch->dev,
+		if (!__netif_subqueue_stopped(sch->dev,
 					    (q->mq ? q->curband : 0))) {
 			qdisc = q->queues[q->curband];
 			skb = qdisc->dequeue(qdisc);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index b9370956b187..4be92d0a2cab 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -908,8 +908,8 @@ void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn)
 	return;
 }
 
-/* Renege 'needed' bytes from the ordering queue. */
-static __u16 sctp_ulpq_renege_order(struct sctp_ulpq *ulpq, __u16 needed)
+static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq,
+		struct sk_buff_head *list, __u16 needed)
 {
 	__u16 freed = 0;
 	__u32 tsn;
@@ -919,7 +919,7 @@ static __u16 sctp_ulpq_renege_order(struct sctp_ulpq *ulpq, __u16 needed)
 
 	tsnmap = &ulpq->asoc->peer.tsn_map;
 
-	while ((skb = __skb_dequeue_tail(&ulpq->lobby)) != NULL) {
+	while ((skb = __skb_dequeue_tail(list)) != NULL) {
 		freed += skb_headlen(skb);
 		event = sctp_skb2event(skb);
 		tsn = event->tsn;
@@ -933,30 +933,16 @@ static __u16 sctp_ulpq_renege_order(struct sctp_ulpq *ulpq, __u16 needed)
 	return freed;
 }
 
+/* Renege 'needed' bytes from the ordering queue. */
+static __u16 sctp_ulpq_renege_order(struct sctp_ulpq *ulpq, __u16 needed)
+{
+	return sctp_ulpq_renege_list(ulpq, &ulpq->lobby, needed);
+}
+
 /* Renege 'needed' bytes from the reassembly queue. */
 static __u16 sctp_ulpq_renege_frags(struct sctp_ulpq *ulpq, __u16 needed)
 {
-	__u16 freed = 0;
-	__u32 tsn;
-	struct sk_buff *skb;
-	struct sctp_ulpevent *event;
-	struct sctp_tsnmap *tsnmap;
-
-	tsnmap = &ulpq->asoc->peer.tsn_map;
-
-	/* Walk backwards through the list, reneges the newest tsns. */
-	while ((skb = __skb_dequeue_tail(&ulpq->reasm)) != NULL) {
-		freed += skb_headlen(skb);
-		event = sctp_skb2event(skb);
-		tsn = event->tsn;
-
-		sctp_ulpevent_free(event);
-		sctp_tsnmap_renege(tsnmap, tsn);
-		if (freed >= needed)
-			return freed;
-	}
-
-	return freed;
+	return sctp_ulpq_renege_list(ulpq, &ulpq->reasm, needed);
 }
 
 /* Partial deliver the first message as there is pressure on rwnd. */