Merge remote-tracking branch 'kernelorg/linux-3.0.y' into 3_0_64

Conflicts:
	arch/arm/Kconfig
	arch/arm/include/asm/hwcap.h
	arch/arm/kernel/smp.c
	arch/arm/plat-samsung/adc.c
	drivers/gpu/drm/i915/i915_reg.h
	drivers/gpu/drm/i915/intel_drv.h
	drivers/mmc/core/sd.c
	drivers/net/tun.c
	drivers/net/usb/usbnet.c
	drivers/regulator/max8997.c
	drivers/usb/core/hub.c
	drivers/usb/host/xhci.h
	drivers/usb/serial/qcserial.c
	fs/jbd2/transaction.c
	include/linux/migrate.h
	kernel/sys.c
	kernel/time/timekeeping.c
	lib/genalloc.c
	mm/memory-failure.c
	mm/memory_hotplug.c
	mm/mempolicy.c
	mm/page_alloc.c
	mm/vmalloc.c
	mm/vmscan.c
	mm/vmstat.c
	scripts/Kbuild.include

Change-Id: I91e2d85c07320c7ccfc04cf98a448e89bed6ade6

11 files changed, 266 insertions, 148 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index f134f88..465f1f6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1045,6 +1045,8 @@ rollback:
  */
 int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 {
+	char *new_ifalias;
+
 	ASSERT_RTNL();
 
 	if (len >= IFALIASZ)
@@ -1058,9 +1060,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 		return 0;
 	}
 
-	dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
-	if (!dev->ifalias)
+	new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+	if (!new_ifalias)
 		return -ENOMEM;
+	dev->ifalias = new_ifalias;
 
 	strlcpy(dev->ifalias, alias, len+1);
 	return len;
@@ -1163,6 +1166,7 @@ static int __dev_open(struct net_device *dev)
 		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	return ret;
@@ -1406,14 +1410,34 @@ EXPORT_SYMBOL(register_netdevice_notifier);
  *	register_netdevice_notifier(). The notifier is unlinked into the
  *	kernel structures and may then be reused. A negative errno code
  *	is returned on a failure.
+ *
+ * 	After unregistering unregister and down device events are synthesized
+ *	for all devices on the device list to the removed notifier to remove
+ *	the need for special case cleanup code.
  */
 
 int unregister_netdevice_notifier(struct notifier_block *nb)
 {
+	struct net_device *dev;
+	struct net *net;
 	int err;
 
 	rtnl_lock();
 	err = raw_notifier_chain_unregister(&netdev_chain, nb);
+	if (err)
+		goto unlock;
+
+	for_each_net(net) {
+		for_each_netdev(net, dev) {
+			if (dev->flags & IFF_UP) {
+				nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+				nb->notifier_call(nb, NETDEV_DOWN, dev);
+			}
+			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+			nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
+		}
+	}
+unlock:
 	rtnl_unlock();
 	return err;
 }
@@ -1513,10 +1537,14 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb_set_dev(skb, dev);
+	skb->dev = dev;
+	skb_dst_drop(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, dev);
+	skb->mark = 0;
+	secpath_reset(skb);
+	nf_reset(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1771,36 +1799,6 @@ void netif_device_attach(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_device_attach);
 
-/**
- * skb_dev_set -- assign a new device to a buffer
- * @skb: buffer for the new device
- * @dev: network device
- *
- * If an skb is owned by a device already, we have to reset
- * all data private to the namespace a device belongs to
- * before assigning it a new device.
- */
-#ifdef CONFIG_NET_NS
-void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
-{
-	skb_dst_drop(skb);
-	if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
-		secpath_reset(skb);
-		nf_reset(skb);
-		skb_init_secmark(skb);
-		skb->mark = 0;
-		skb->priority = 0;
-		skb->nf_trace = 0;
-		skb->ipvs_property = 0;
-#ifdef CONFIG_NET_SCHED
-		skb->tc_index = 0;
-#endif
-	}
-	skb->dev = dev;
-}
-EXPORT_SYMBOL(skb_set_dev);
-#endif /* CONFIG_NET_NS */
-
 /*
  * Invalidate hardware checksum when packet is to be mangled, and
  * complete checksum manually on outgoing path.
@@ -2040,7 +2038,8 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol)
 
 static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features)
 {
-	if (!can_checksum_protocol(features, protocol)) {
+	if (skb->ip_summed != CHECKSUM_NONE &&
+	    !can_checksum_protocol(features, protocol)) {
 		features &= ~NETIF_F_ALL_CSUM;
 		features &= ~NETIF_F_SG;
 	} else if (illegal_highdma(skb->dev, skb)) {
@@ -2055,6 +2054,9 @@ u32 netif_skb_features(struct sk_buff *skb)
 	__be16 protocol = skb->protocol;
 	u32 features = skb->dev->features;
 
+	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+		features &= ~NETIF_F_GSO_MASK;
+
 	if (protocol == htons(ETH_P_8021Q)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
@@ -2558,16 +2560,17 @@ __u32 __skb_get_rxhash(struct sk_buff *skb)
 	poff = proto_ports_offset(ip_proto);
 	if (poff >= 0) {
 		nhoff += ihl * 4 + poff;
-		if (pskb_may_pull(skb, nhoff + 4)) {
+		if (pskb_may_pull(skb, nhoff + 4))
 			ports.v32 = * (__force u32 *) (skb->data + nhoff);
-			if (ports.v16[1] < ports.v16[0])
-				swap(ports.v16[0], ports.v16[1]);
-		}
 	}
 
 	/* get a consistent hash (same value on both flow directions) */
-	if (addr2 < addr1)
+	if (addr2 < addr1 ||
+	    (addr2 == addr1 &&
+	     ports.v16[1] < ports.v16[0])) {
 		swap(addr1, addr2);
+		swap(ports.v16[0], ports.v16[1]);
+	}
 
 	hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
 	if (!hash)
@@ -2703,8 +2706,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		if (unlikely(tcpu != next_cpu) &&
 		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
-		      rflow->last_qtail)) >= 0))
+		      rflow->last_qtail)) >= 0)) {
+			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+		}
 
 		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
 			*rflowp = rflow;
@@ -4736,6 +4741,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mac_address);
@@ -5513,6 +5519,7 @@ int register_netdevice(struct net_device *dev)
 	dev_init_scheduler(dev);
 	dev_hold(dev);
 	list_netdevice(dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 
 	/* Notify protocols, that a new device appeared. */
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
@@ -5873,6 +5880,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev_net_set(dev, &init_net);
 
 	dev->gso_max_size = GSO_MAX_SIZE;
+	dev->gso_max_segs = GSO_MAX_SEGS;
 
 	INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
 	dev->ethtool_ntuple_list.count = 0;
@@ -6256,7 +6264,8 @@ static struct hlist_head *netdev_create_hash(void)
 /* Initialize per network namespace state */
 static int __net_init netdev_init(struct net *net)
 {
-	INIT_LIST_HEAD(&net->dev_base_head);
+	if (net != &init_net)
+		INIT_LIST_HEAD(&net->dev_base_head);
 
 	net->dev_name_head = netdev_create_hash();
 	if (net->dev_name_head == NULL)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index e2e6693..c776af5 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -307,7 +307,8 @@ int dev_addr_del(struct net_device *dev, unsigned char *addr,
 	 */
 	ha = list_first_entry(&dev->dev_addrs.list,
 			      struct netdev_hw_addr, list);
-	if (ha->addr == dev->dev_addr && ha->refcount == 1)
+	if (!memcmp(ha->addr, addr, dev->addr_len) &&
+	    ha->type == addr_type && ha->refcount == 1)
 		return -ENOENT;
 
 	err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len,
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 7f36b38..b856f87 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -33,22 +33,19 @@
 #define TRACE_ON 1
 #define TRACE_OFF 0
 
-static void send_dm_alert(struct work_struct *unused);
-
-
 /*
  * Globals, our netlink socket pointer
  * and the work handle that will send up
  * netlink alerts
  */
 static int trace_state = TRACE_OFF;
-static DEFINE_SPINLOCK(trace_state_lock);
+static DEFINE_MUTEX(trace_state_mutex);
 
 struct per_cpu_dm_data {
-	struct work_struct dm_alert_work;
-	struct sk_buff *skb;
-	atomic_t dm_hit_count;
-	struct timer_list send_timer;
+	spinlock_t		lock;
+	struct sk_buff		*skb;
+	struct work_struct	dm_alert_work;
+	struct timer_list	send_timer;
 };
 
 struct dm_hw_stat_delta {
@@ -74,56 +71,59 @@ static int dm_delay = 1;
 static unsigned long dm_hw_check_delta = 2*HZ;
 static LIST_HEAD(hw_stats_list);
 
-static void reset_per_cpu_data(struct per_cpu_dm_data *data)
+static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 {
 	size_t al;
 	struct net_dm_alert_msg *msg;
 	struct nlattr *nla;
+	struct sk_buff *skb;
+	unsigned long flags;
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
 	al += sizeof(struct nlattr);
 
-	data->skb = genlmsg_new(al, GFP_KERNEL);
-	genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
-			0, NET_DM_CMD_ALERT);
-	nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg));
-	msg = nla_data(nla);
-	memset(msg, 0, al);
-	atomic_set(&data->dm_hit_count, dm_hit_limit);
+	skb = genlmsg_new(al, GFP_KERNEL);
+
+	if (skb) {
+		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				0, NET_DM_CMD_ALERT);
+		nla = nla_reserve(skb, NLA_UNSPEC,
+				  sizeof(struct net_dm_alert_msg));
+		msg = nla_data(nla);
+		memset(msg, 0, al);
+	} else {
+		mod_timer(&data->send_timer, jiffies + HZ / 10);
+	}
+
+	spin_lock_irqsave(&data->lock, flags);
+	swap(data->skb, skb);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return skb;
 }
 
-static void send_dm_alert(struct work_struct *unused)
+static void send_dm_alert(struct work_struct *work)
 {
 	struct sk_buff *skb;
-	struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+	struct per_cpu_dm_data *data;
 
-	/*
-	 * Grab the skb we're about to send
-	 */
-	skb = data->skb;
+	data = container_of(work, struct per_cpu_dm_data, dm_alert_work);
 
-	/*
-	 * Replace it with a new one
-	 */
-	reset_per_cpu_data(data);
-
-	/*
-	 * Ship it!
-	 */
-	genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+	skb = reset_per_cpu_data(data);
 
+	if (skb)
+		genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
 }
 
 /*
  * This is the timer function to delay the sending of an alert
  * in the event that more drops will arrive during the
- * hysteresis period.  Note that it operates under the timer interrupt
- * so we don't need to disable preemption here
+ * hysteresis period.
  */
-static void sched_send_work(unsigned long unused)
+static void sched_send_work(unsigned long _data)
 {
-	struct per_cpu_dm_data *data =  &__get_cpu_var(dm_cpu_data);
+	struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data;
 
 	schedule_work(&data->dm_alert_work);
 }
@@ -134,17 +134,19 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	struct nlmsghdr *nlh;
 	struct nlattr *nla;
 	int i;
-	struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+	struct sk_buff *dskb;
+	struct per_cpu_dm_data *data;
+	unsigned long flags;
 
+	local_irq_save(flags);
+	data = &__get_cpu_var(dm_cpu_data);
+	spin_lock(&data->lock);
+	dskb = data->skb;
 
-	if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
-		/*
-		 * we're already at zero, discard this hit
-		 */
+	if (!dskb)
 		goto out;
-	}
 
-	nlh = (struct nlmsghdr *)data->skb->data;
+	nlh = (struct nlmsghdr *)dskb->data;
 	nla = genlmsg_data(nlmsg_data(nlh));
 	msg = nla_data(nla);
 	for (i = 0; i < msg->entries; i++) {
@@ -153,11 +155,12 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 			goto out;
 		}
 	}
-
+	if (msg->entries == dm_hit_limit)
+		goto out;
 	/*
 	 * We need to create a new entry
 	 */
-	__nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
+	__nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
 	nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
 	memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
 	msg->points[msg->entries].count = 1;
@@ -165,11 +168,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 
 	if (!timer_pending(&data->send_timer)) {
 		data->send_timer.expires = jiffies + dm_delay * HZ;
-		add_timer_on(&data->send_timer, smp_processor_id());
+		add_timer(&data->send_timer);
 	}
 
 out:
-	return;
+	spin_unlock_irqrestore(&data->lock, flags);
 }
 
 static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
@@ -213,7 +216,7 @@ static int set_all_monitor_traces(int state)
 	struct dm_hw_stat_delta *new_stat = NULL;
 	struct dm_hw_stat_delta *temp;
 
-	spin_lock(&trace_state_lock);
+	mutex_lock(&trace_state_mutex);
 
 	if (state == trace_state) {
 		rc = -EAGAIN;
@@ -252,7 +255,7 @@ static int set_all_monitor_traces(int state)
 		rc = -EINPROGRESS;
 
 out_unlock:
-	spin_unlock(&trace_state_lock);
+	mutex_unlock(&trace_state_mutex);
 
 	return rc;
 }
@@ -295,12 +298,12 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 
 		new_stat->dev = dev;
 		new_stat->last_rx = jiffies;
-		spin_lock(&trace_state_lock);
+		mutex_lock(&trace_state_mutex);
 		list_add_rcu(&new_stat->list, &hw_stats_list);
-		spin_unlock(&trace_state_lock);
+		mutex_unlock(&trace_state_mutex);
 		break;
 	case NETDEV_UNREGISTER:
-		spin_lock(&trace_state_lock);
+		mutex_lock(&trace_state_mutex);
 		list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
 			if (new_stat->dev == dev) {
 				new_stat->dev = NULL;
@@ -311,7 +314,7 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 				}
 			}
 		}
-		spin_unlock(&trace_state_lock);
+		mutex_unlock(&trace_state_mutex);
 		break;
 	}
 out:
@@ -367,13 +370,15 @@ static int __init init_net_drop_monitor(void)
 
 	for_each_present_cpu(cpu) {
 		data = &per_cpu(dm_cpu_data, cpu);
-		reset_per_cpu_data(data);
 		INIT_WORK(&data->dm_alert_work, send_dm_alert);
 		init_timer(&data->send_timer);
-		data->send_timer.data = cpu;
+		data->send_timer.data = (unsigned long)data;
 		data->send_timer.function = sched_send_work;
+		spin_lock_init(&data->lock);
+		reset_per_cpu_data(data);
 	}
 
+
 	goto out;
 
 out_unreg:
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 4fb7704..891b19f 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1964,6 +1964,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GRXCSUM:
 	case ETHTOOL_GTXCSUM:
 	case ETHTOOL_GSG:
+	case ETHTOOL_GSSET_INFO:
 	case ETHTOOL_GSTRINGS:
 	case ETHTOOL_GTSO:
 	case ETHTOOL_GPERMADDR:
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f39ef5c..3231b46 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -740,9 +740,9 @@ static struct pernet_operations fib_rules_net_ops = {
 static int __init fib_rules_init(void)
 {
 	int err;
-	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule);
+	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL);
 
 	err = register_pernet_subsys(&fib_rules_net_ops);
 	if (err < 0)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 96bb0a3..34032f2 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1313,8 +1313,6 @@ int neigh_resolve_output(struct sk_buff *skb)
 	if (!dst)
 		goto discard;
 
-	__skb_pull(skb, skb_network_offset(skb));
-
 	if (!neigh_event_send(neigh, skb)) {
 		int err;
 		struct net_device *dev = neigh->dev;
@@ -1326,6 +1324,7 @@ int neigh_resolve_output(struct sk_buff *skb)
 			neigh_hh_init(neigh, dst, dst->ops->protocol);
 
 		do {
+			__skb_pull(skb, skb_network_offset(skb));
 			seq = read_seqbegin(&neigh->ha_lock);
 			err = dev_hard_header(skb, dev, ntohs(skb->protocol),
 					      neigh->ha, NULL, skb->len);
@@ -1358,9 +1357,8 @@ int neigh_connected_output(struct sk_buff *skb)
 	struct net_device *dev = neigh->dev;
 	unsigned int seq;
 
-	__skb_pull(skb, skb_network_offset(skb));
-
 	do {
+		__skb_pull(skb, skb_network_offset(skb));
 		seq = read_seqbegin(&neigh->ha_lock);
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
 				      neigh->ha, NULL, skb->len);
@@ -2920,12 +2918,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister);
 
 static int __init neigh_init(void)
 {
-	rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info);
+	rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL);
 
-	rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info);
-	rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info,
+		      NULL);
+	rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL);
 
 	return 0;
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2772ed1..1642c30 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,9 @@ static DEFINE_MUTEX(net_mutex);
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
 
-struct net init_net;
+struct net init_net = {
+	.dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
+};
 EXPORT_SYMBOL(init_net);
 
 #define INITIAL_NET_GEN_PTRS	13 /* +1 for len +2 for rcu_head */
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 05db410..207a178 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -357,22 +357,23 @@ EXPORT_SYMBOL(netpoll_send_skb_on_dev);
 
 void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 {
-	int total_len, eth_len, ip_len, udp_len;
+	int total_len, ip_len, udp_len;
 	struct sk_buff *skb;
 	struct udphdr *udph;
 	struct iphdr *iph;
 	struct ethhdr *eth;
 
 	udp_len = len + sizeof(*udph);
-	ip_len = eth_len = udp_len + sizeof(*iph);
-	total_len = eth_len + ETH_HLEN + NET_IP_ALIGN;
+	ip_len = udp_len + sizeof(*iph);
+	total_len = ip_len + LL_RESERVED_SPACE(np->dev);
 
-	skb = find_skb(np, total_len, total_len - len);
+	skb = find_skb(np, total_len + np->dev->needed_tailroom,
+		       total_len - len);
 	if (!skb)
 		return;
 
 	skb_copy_to_linear_data(skb, msg, len);
-	skb->len += len;
+	skb_put(skb, len);
 
 	skb_push(skb, sizeof(*udph));
 	skb_reset_transport_header(skb);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index e35a6fb..4479fd1 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1803,10 +1803,13 @@ static ssize_t pktgen_thread_write(struct file *file,
 			return -EFAULT;
 		i += len;
 		mutex_lock(&pktgen_thread_lock);
-		pktgen_add_device(t, f);
+		ret = pktgen_add_device(t, f);
 		mutex_unlock(&pktgen_thread_lock);
-		ret = count;
-		sprintf(pg_result, "OK: add_device=%s", f);
+		if (!ret) {
+			ret = count;
+			sprintf(pg_result, "OK: add_device=%s", f);
+		} else
+			sprintf(pg_result, "ERROR: can not add device %s", f);
 		goto out;
 	}
 
@@ -1932,7 +1935,7 @@ static int pktgen_device_event(struct notifier_block *unused,
 {
 	struct net_device *dev = ptr;
 
-	if (!net_eq(dev_net(dev), &init_net))
+	if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting)
 		return NOTIFY_DONE;
 
 	/* It is OK that we do not hold the group lock right now,
@@ -2932,7 +2935,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 		  sizeof(struct ipv6hdr) - sizeof(struct udphdr) -
 		  pkt_dev->pkt_overhead;
 
-	if (datalen < sizeof(struct pktgen_hdr)) {
+	if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) {
 		datalen = sizeof(struct pktgen_hdr);
 		if (net_ratelimit())
 			pr_info("increased datalen to %d\n", datalen);
@@ -3755,12 +3758,18 @@ static void __exit pg_cleanup(void)
 {
 	struct pktgen_thread *t;
 	struct list_head *q, *n;
+	LIST_HEAD(list);
 
 	/* Stop all interfaces & threads */
 	pktgen_exiting = true;
 
-	list_for_each_safe(q, n, &pktgen_threads) {
+	mutex_lock(&pktgen_thread_lock);
+	list_splice_init(&pktgen_threads, &list);
+	mutex_unlock(&pktgen_thread_lock);
+
+	list_for_each_safe(q, n, &list) {
 		t = list_entry(q, struct pktgen_thread, th_list);
+		list_del(&t->th_list);
 		kthread_stop(t->tsk);
 		kfree(t);
 	}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index abd936d..49f281e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -56,6 +56,7 @@
 struct rtnl_link {
 	rtnl_doit_func		doit;
 	rtnl_dumpit_func	dumpit;
+	rtnl_calcit_func 	calcit;
 };
 
 static DEFINE_MUTEX(rtnl_mutex);
@@ -144,12 +145,28 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
 	return tab ? tab[msgindex].dumpit : NULL;
 }
 
+static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
+{
+	struct rtnl_link *tab;
+
+	if (protocol <= RTNL_FAMILY_MAX)
+		tab = rtnl_msg_handlers[protocol];
+	else
+		tab = NULL;
+
+	if (tab == NULL || tab[msgindex].calcit == NULL)
+		tab = rtnl_msg_handlers[PF_UNSPEC];
+
+	return tab ? tab[msgindex].calcit : NULL;
+}
+
 /**
  * __rtnl_register - Register a rtnetlink message type
  * @protocol: Protocol family or PF_UNSPEC
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
+ * @calcit: Function pointer to calc size of dump message
  *
  * Registers the specified function pointers (at least one of them has
  * to be non-NULL) to be called whenever a request message for the
@@ -162,7 +179,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
  * Returns 0 on success or a negative error code.
  */
 int __rtnl_register(int protocol, int msgtype,
-		    rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+		    rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+		    rtnl_calcit_func calcit)
 {
 	struct rtnl_link *tab;
 	int msgindex;
@@ -185,6 +203,9 @@ int __rtnl_register(int protocol, int msgtype,
 	if (dumpit)
 		tab[msgindex].dumpit = dumpit;
 
+	if (calcit)
+		tab[msgindex].calcit = calcit;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__rtnl_register);
@@ -199,9 +220,10 @@ EXPORT_SYMBOL_GPL(__rtnl_register);
  * of memory implies no sense in continuing.
  */
 void rtnl_register(int protocol, int msgtype,
-		   rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+		   rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+		   rtnl_calcit_func calcit)
 {
-	if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0)
+	if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0)
 		panic("Unable to register rtnetlink message handler, "
 		      "protocol = %d, message type = %d\n",
 		      protocol, msgtype);
@@ -647,6 +669,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
 	}
 }
 
+static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
+{
+	return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) |
+	       (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI));
+}
+
 static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
 					   const struct ifinfomsg *ifm)
 {
@@ -655,7 +683,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
 	/* bugwards compatibility: ifi_change == 0 is treated as ~0 */
 	if (ifm->ifi_change)
 		flags = (flags & ifm->ifi_change) |
-			(dev->flags & ~ifm->ifi_change);
+			(rtnl_dev_get_flags(dev) & ~ifm->ifi_change);
 
 	return flags;
 }
@@ -698,10 +726,11 @@ static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b)
 }
 
 /* All VF info */
-static inline int rtnl_vfinfo_size(const struct net_device *dev)
+static inline int rtnl_vfinfo_size(const struct net_device *dev,
+				   u32 ext_filter_mask)
 {
-	if (dev->dev.parent && dev_is_pci(dev->dev.parent)) {
-
+	if (dev->dev.parent && dev_is_pci(dev->dev.parent) &&
+	    (ext_filter_mask & RTEXT_FILTER_VF)) {
 		int num_vfs = dev_num_vf(dev->dev.parent);
 		size_t size = nla_total_size(sizeof(struct nlattr));
 		size += nla_total_size(num_vfs * sizeof(struct nlattr));
@@ -739,7 +768,8 @@ static size_t rtnl_port_size(const struct net_device *dev)
 		return port_self_size;
 }
 
-static noinline size_t if_nlmsg_size(const struct net_device *dev)
+static noinline size_t if_nlmsg_size(const struct net_device *dev,
+				     u32 ext_filter_mask)
 {
 	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
 	       + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
@@ -757,8 +787,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev)
 	       + nla_total_size(4) /* IFLA_MASTER */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
-	       + nla_total_size(4) /* IFLA_NUM_VF */
-	       + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */
+	       + nla_total_size(ext_filter_mask
+			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
+	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
 	       + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */
@@ -841,7 +872,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
 
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
-			    unsigned int flags)
+			    unsigned int flags, u32 ext_filter_mask)
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
@@ -914,10 +945,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		goto nla_put_failure;
 	copy_rtnl_link_stats64(nla_data(attr), stats);
 
-	if (dev->dev.parent)
+	if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF))
 		NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent));
 
-	if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) {
+	if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent
+	    && (ext_filter_mask & RTEXT_FILTER_VF)) {
 		int i;
 
 		struct nlattr *vfinfo, *vf;
@@ -1004,11 +1036,21 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net_device *dev;
 	struct hlist_head *head;
 	struct hlist_node *node;
+	struct nlattr *tb[IFLA_MAX+1];
+	u32 ext_filter_mask = 0;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
 
 	rcu_read_lock();
+
+	if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX,
+			ifla_policy) >= 0) {
+
+		if (tb[IFLA_EXT_MASK])
+			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+	}
+
 	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
 		idx = 0;
 		head = &net->dev_index_head[h];
@@ -1018,7 +1060,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
 					     NETLINK_CB(cb->skb).pid,
 					     cb->nlh->nlmsg_seq, 0,
-					     NLM_F_MULTI) <= 0)
+					     NLM_F_MULTI,
+					     ext_filter_mask) <= 0)
 				goto out;
 cont:
 			idx++;
@@ -1052,6 +1095,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_VF_PORTS]		= { .type = NLA_NESTED },
 	[IFLA_PORT_SELF]	= { .type = NLA_NESTED },
 	[IFLA_AF_SPEC]		= { .type = NLA_NESTED },
+	[IFLA_EXT_MASK]		= { .type = NLA_U32 },
 };
 EXPORT_SYMBOL(ifla_policy);
 
@@ -1298,6 +1342,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			goto errout;
 		send_addr_notify = 1;
 		modified = 1;
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	if (tb[IFLA_MTU]) {
@@ -1783,6 +1828,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	struct net_device *dev = NULL;
 	struct sk_buff *nskb;
 	int err;
+	u32 ext_filter_mask = 0;
 
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
 	if (err < 0)
@@ -1791,6 +1837,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	if (tb[IFLA_IFNAME])
 		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 
+	if (tb[IFLA_EXT_MASK])
+		ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifi_index > 0)
 		dev = __dev_get_by_index(net, ifm->ifi_index);
@@ -1802,12 +1851,12 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	if (dev == NULL)
 		return -ENODEV;
 
-	nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
+	nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
 	if (nskb == NULL)
 		return -ENOBUFS;
 
 	err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid,
-			       nlh->nlmsg_seq, 0, 0);
+			       nlh->nlmsg_seq, 0, 0, ext_filter_mask);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size */
 		WARN_ON(err == -EMSGSIZE);
@@ -1818,6 +1867,35 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	return err;
 }
 
+static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	struct nlattr *tb[IFLA_MAX+1];
+	u32 ext_filter_mask = 0;
+	u16 min_ifinfo_dump_size = 0;
+
+	if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX,
+			ifla_policy) >= 0) {
+		if (tb[IFLA_EXT_MASK])
+			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+	}
+
+	if (!ext_filter_mask)
+		return NLMSG_GOODSIZE;
+	/*
+	 * traverse the list of net devices and compute the minimum
+	 * buffer size based upon the filter mask.
+	 */
+	list_for_each_entry(dev, &net->dev_base_head, dev_list) {
+		min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
+					     if_nlmsg_size(dev,
+						           ext_filter_mask));
+	}
+
+	return min_ifinfo_dump_size;
+}
+
 static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	int idx;
@@ -1847,12 +1925,13 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
+	size_t if_info_size;
 
-	skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
+	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL);
 	if (skb == NULL)
 		goto errout;
 
-	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0);
+	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -1902,14 +1981,20 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
+		rtnl_calcit_func calcit;
+		u16 min_dump_alloc = 0;
 
 		dumpit = rtnl_get_dumpit(family, type);
 		if (dumpit == NULL)
 			return -EOPNOTSUPP;
+		calcit = rtnl_get_calcit(family, type);
+		if (calcit)
+			min_dump_alloc = calcit(skb, nlh);
 
 		__rtnl_unlock();
 		rtnl = net->rtnl;
-		err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
+		err = netlink_dump_start(rtnl, skb, nlh, dumpit,
+					 NULL, min_dump_alloc);
 		rtnl_lock();
 		return err;
 	}
@@ -2019,12 +2104,13 @@ void __init rtnetlink_init(void)
 	netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV);
 	register_netdevice_notifier(&rtnetlink_dev_notifier);
 
-	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo);
-	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL);
-	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
+		      rtnl_dump_ifinfo, rtnl_calcit);
+	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL);
 
-	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all);
-	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);
+	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
 }
 
diff --git a/net/core/sock.c b/net/core/sock.c
index aebb419..3da11ba 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -594,7 +594,8 @@ set_rcvbuf:
 
 	case SO_KEEPALIVE:
 #ifdef CONFIG_INET
-		if (sk->sk_protocol == IPPROTO_TCP)
+		if (sk->sk_protocol == IPPROTO_TCP &&
+		    sk->sk_type == SOCK_STREAM)
 			tcp_set_keepalive(sk, valbool);
 #endif
 		sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
@@ -1312,6 +1313,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 		} else {
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
 			sk->sk_gso_max_size = dst->dev->gso_max_size;
+			sk->sk_gso_max_segs = dst->dev->gso_max_segs;
 		}
 	}
 }
@@ -1501,6 +1503,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 	gfp_t gfp_mask;
 	long timeo;
 	int err;
+	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+
+	err = -EMSGSIZE;
+	if (npages > MAX_SKB_FRAGS)
+		goto failure;
 
 	gfp_mask = sk->sk_allocation;
 	if (gfp_mask & __GFP_WAIT)
@@ -1519,14 +1526,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
 			skb = alloc_skb(header_len, gfp_mask);
 			if (skb) {
-				int npages;
 				int i;
 
 				/* No pages, we're done... */
 				if (!data_len)
 					break;
 
-				npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 				skb->truesize += data_len;
 				skb_shinfo(skb)->nr_frags = npages;
 				for (i = 0; i < npages; i++) {