Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking update from David Miller:
 "A couple weeks of bug fixing in there.  The largest chunk is all the
  broken crap Amerigo Wang found in the netpoll layer."

 1) netpoll and it's users has several serious bugs:
    a) uses GFP_KERNEL with locks held
    b) interfaces requiring interrupts disabled are called with them
       enabled
    c) and vice versa
    d) VLAN tag demuxing, as per all other RX packet input paths, is not
       applied

    All from Amerigo Wang.

 2) Hopefully cure the ipv4 mapped ipv6 address TCP early demux bugs for
    good, from Neal Cardwell.

 3) Unlike AF_UNIX, AF_PACKET sockets don't set a default credentials
    when the user doesn't specify one explicitly during sendmsg().
    Instead we attach an empty (zero) SCM credential block which is
    definitely not what we want.  Fix from Eric Dumazet.

 4) IPv6 illegally invokes netdevice notifiers with RCU lock held, fix
    from Ben Hutchings.

 5) inet_csk_route_child_sock() checks wrong inet options pointer, fix
    from Christoph Paasch.

 6) When AF_PACKET is used for transmit, packet loopback doesn't behave
    properly when a socket fanout is enabled, from Eric Leblond.

 7) On bluetooth l2cap channel create failure, we leak the socket, from
    Jaganath Kanakkassery.

 8) Fix all the netprio file handling bugs found by Al Viro, from John
    Fastabend.

 9) Several error return and NULL deref bug fixes in networking drivers
    from Julia Lawall.

10) A large smattering of struct padding et al.  kernel memory leaks to
    userspace found of Mathias Krause.

11) Conntrack expections in netfilter can access an uninitialized timer,
    fix from Pablo Neira Ayuso.

12) Several netfilter SIP tracker bug fixes from Patrick McHardy.

13) IPSEC ipv6 routes are not initialized correctly all the time,
    resulting in an OOPS in inet_putpeer().  Also from Patrick McHardy.

14) Bridging does rcu_dereference() outside of RCU protected area, from
    Stephen Hemminger.

15) Fix routing cache removal performance regression when looking up
    output routes that have a local destination.  From Zheng Yan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  af_netlink: force credentials passing [CVE-2012-3520]
  ipv4: fix ip header ident selection in __ip_make_skb()
  ipv4: Use newinet->inet_opt in inet_csk_route_child_sock()
  tcp: fix possible socket refcount problem
  net: tcp: move sk_rx_dst_set call after tcp_create_openreq_child()
  net/core/dev.c: fix kernel-doc warning
  netconsole: remove a redundant netconsole_target_put()
  net: ipv6: fix oops in inet_putpeer()
  net/stmmac: fix issue of clk_get for Loongson1B.
  caif: Do not dereference NULL in chnl_recv_cb()
  af_packet: don't emit packet on orig fanout group
  drivers/net/irda: fix error return code
  drivers/net/wan/dscc4.c: fix error return code
  drivers/net/wimax/i2400m/fw.c: fix error return code
  smsc75xx: add missing entry to MAINTAINERS
  net: qmi_wwan: new devices: UML290 and K5006-Z
  net: sh_eth: Add eth support for R8A7779 device
  netdev/phy: skip disabled mdio-mux nodes
  dt: introduce for_each_available_child_of_node, of_get_next_available_child
  net: netprio: fix cgrp create and write priomap race
  ...

4 files changed, 104 insertions, 56 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index a39354ee1432..83988362805e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1642,6 +1642,19 @@ static inline int deliver_skb(struct sk_buff *skb,
 	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
 
+static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
+{
+	if (ptype->af_packet_priv == NULL)
+		return false;
+
+	if (ptype->id_match)
+		return ptype->id_match(ptype, skb->sk);
+	else if ((struct sock *)ptype->af_packet_priv == skb->sk)
+		return true;
+
+	return false;
+}
+
 /*
  *	Support routine. Sends outgoing frames to any network
  *	taps currently in use.
@@ -1659,8 +1672,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 		 * they originated from - MvS (miquels@drinkel.ow.org)
 		 */
 		if ((ptype->dev == dev || !ptype->dev) &&
-		    (ptype->af_packet_priv == NULL ||
-		     (struct sock *)ptype->af_packet_priv != skb->sk)) {
+		    (!skb_loop_sk(ptype, skb))) {
 			if (pt_prev) {
 				deliver_skb(skb2, pt_prev, skb->dev);
 				pt_prev = ptype;
@@ -5732,6 +5744,7 @@ EXPORT_SYMBOL(netdev_refcnt_read);
 
 /**
  * netdev_wait_allrefs - wait until all references are gone.
+ * @dev: target net_device
  *
  * This is called when unregistering network devices.
  *
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index b4c90e42b443..346b1eb83a1f 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -26,6 +26,7 @@
 #include <linux/workqueue.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/if_vlan.h>
 #include <net/tcp.h>
 #include <net/udp.h>
 #include <asm/unaligned.h>
@@ -54,7 +55,7 @@ static atomic_t trapped;
 	 MAX_UDP_CHUNK)
 
 static void zap_completion_queue(void);
-static void arp_reply(struct sk_buff *skb);
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
 
 static unsigned int carrier_timeout = 4;
 module_param(carrier_timeout, uint, 0644);
@@ -167,15 +168,24 @@ static void poll_napi(struct net_device *dev)
 	struct napi_struct *napi;
 	int budget = 16;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		local_irq_enable();
 		if (napi->poll_owner != smp_processor_id() &&
 		    spin_trylock(&napi->poll_lock)) {
-			budget = poll_one_napi(dev->npinfo, napi, budget);
+			rcu_read_lock_bh();
+			budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
+					       napi, budget);
+			rcu_read_unlock_bh();
 			spin_unlock(&napi->poll_lock);
 
-			if (!budget)
+			if (!budget) {
+				local_irq_disable();
 				break;
+			}
 		}
+		local_irq_disable();
 	}
 }
 
@@ -185,13 +195,14 @@ static void service_arp_queue(struct netpoll_info *npi)
 		struct sk_buff *skb;
 
 		while ((skb = skb_dequeue(&npi->arp_tx)))
-			arp_reply(skb);
+			netpoll_arp_reply(skb, npi);
 	}
 }
 
 static void netpoll_poll_dev(struct net_device *dev)
 {
 	const struct net_device_ops *ops;
+	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
 
 	if (!dev || !netif_running(dev))
 		return;
@@ -206,17 +217,18 @@ static void netpoll_poll_dev(struct net_device *dev)
 	poll_napi(dev);
 
 	if (dev->flags & IFF_SLAVE) {
-		if (dev->npinfo) {
+		if (ni) {
 			struct net_device *bond_dev = dev->master;
 			struct sk_buff *skb;
-			while ((skb = skb_dequeue(&dev->npinfo->arp_tx))) {
+			struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo);
+			while ((skb = skb_dequeue(&ni->arp_tx))) {
 				skb->dev = bond_dev;
-				skb_queue_tail(&bond_dev->npinfo->arp_tx, skb);
+				skb_queue_tail(&bond_ni->arp_tx, skb);
 			}
 		}
 	}
 
-	service_arp_queue(dev->npinfo);
+	service_arp_queue(ni);
 
 	zap_completion_queue();
 }
@@ -302,6 +314,7 @@ static int netpoll_owner_active(struct net_device *dev)
 	return 0;
 }
 
+/* call with IRQ disabled */
 void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 			     struct net_device *dev)
 {
@@ -309,8 +322,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 	unsigned long tries;
 	const struct net_device_ops *ops = dev->netdev_ops;
 	/* It is up to the caller to keep npinfo alive. */
-	struct netpoll_info *npinfo = np->dev->npinfo;
+	struct netpoll_info *npinfo;
+
+	WARN_ON_ONCE(!irqs_disabled());
 
+	npinfo = rcu_dereference_bh(np->dev->npinfo);
 	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
 		__kfree_skb(skb);
 		return;
@@ -319,16 +335,22 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 	/* don't get messages out of order, and no recursion */
 	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
 		struct netdev_queue *txq;
-		unsigned long flags;
 
 		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 
-		local_irq_save(flags);
 		/* try until next clock tick */
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
 		     tries > 0; --tries) {
 			if (__netif_tx_trylock(txq)) {
 				if (!netif_xmit_stopped(txq)) {
+					if (vlan_tx_tag_present(skb) &&
+					    !(netif_skb_features(skb) & NETIF_F_HW_VLAN_TX)) {
+						skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
+						if (unlikely(!skb))
+							break;
+						skb->vlan_tci = 0;
+					}
+
 					status = ops->ndo_start_xmit(skb, dev);
 					if (status == NETDEV_TX_OK)
 						txq_trans_update(txq);
@@ -347,10 +369,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 		}
 
 		WARN_ONCE(!irqs_disabled(),
-			"netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n",
+			"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
 			dev->name, ops->ndo_start_xmit);
 
-		local_irq_restore(flags);
 	}
 
 	if (status != NETDEV_TX_OK) {
@@ -423,9 +444,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 }
 EXPORT_SYMBOL(netpoll_send_udp);
 
-static void arp_reply(struct sk_buff *skb)
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
 {
-	struct netpoll_info *npinfo = skb->dev->npinfo;
 	struct arphdr *arp;
 	unsigned char *arp_ptr;
 	int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
@@ -543,13 +563,12 @@ static void arp_reply(struct sk_buff *skb)
 	spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 }
 
-int __netpoll_rx(struct sk_buff *skb)
+int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 {
 	int proto, len, ulen;
 	int hits = 0;
 	const struct iphdr *iph;
 	struct udphdr *uh;
-	struct netpoll_info *npinfo = skb->dev->npinfo;
 	struct netpoll *np, *tmp;
 
 	if (list_empty(&npinfo->rx_np))
@@ -565,6 +584,12 @@ int __netpoll_rx(struct sk_buff *skb)
 		return 1;
 	}
 
+	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+		skb = vlan_untag(skb);
+		if (unlikely(!skb))
+			goto out;
+	}
+
 	proto = ntohs(eth_hdr(skb)->h_proto);
 	if (proto != ETH_P_IP)
 		goto out;
@@ -715,7 +740,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 }
 EXPORT_SYMBOL(netpoll_parse_options);
 
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 {
 	struct netpoll_info *npinfo;
 	const struct net_device_ops *ops;
@@ -734,7 +759,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 	}
 
 	if (!ndev->npinfo) {
-		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
+		npinfo = kmalloc(sizeof(*npinfo), gfp);
 		if (!npinfo) {
 			err = -ENOMEM;
 			goto out;
@@ -752,7 +777,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 
 		ops = np->dev->netdev_ops;
 		if (ops->ndo_netpoll_setup) {
-			err = ops->ndo_netpoll_setup(ndev, npinfo);
+			err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
 			if (err)
 				goto free_npinfo;
 		}
@@ -857,7 +882,7 @@ int netpoll_setup(struct netpoll *np)
 	refill_skbs();
 
 	rtnl_lock();
-	err = __netpoll_setup(np, ndev);
+	err = __netpoll_setup(np, ndev, GFP_KERNEL);
 	rtnl_unlock();
 
 	if (err)
@@ -878,6 +903,24 @@ static int __init netpoll_init(void)
 }
 core_initcall(netpoll_init);
 
+static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
+{
+	struct netpoll_info *npinfo =
+			container_of(rcu_head, struct netpoll_info, rcu);
+
+	skb_queue_purge(&npinfo->arp_tx);
+	skb_queue_purge(&npinfo->txq);
+
+	/* we can't call cancel_delayed_work_sync here, as we are in softirq */
+	cancel_delayed_work(&npinfo->tx_work);
+
+	/* clean after last, unfinished work */
+	__skb_queue_purge(&npinfo->txq);
+	/* now cancel it again */
+	cancel_delayed_work(&npinfo->tx_work);
+	kfree(npinfo);
+}
+
 void __netpoll_cleanup(struct netpoll *np)
 {
 	struct netpoll_info *npinfo;
@@ -903,20 +946,24 @@ void __netpoll_cleanup(struct netpoll *np)
 			ops->ndo_netpoll_cleanup(np->dev);
 
 		RCU_INIT_POINTER(np->dev->npinfo, NULL);
+		call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
+	}
+}
+EXPORT_SYMBOL_GPL(__netpoll_cleanup);
 
-		/* avoid racing with NAPI reading npinfo */
-		synchronize_rcu_bh();
+static void rcu_cleanup_netpoll(struct rcu_head *rcu_head)
+{
+	struct netpoll *np = container_of(rcu_head, struct netpoll, rcu);
 
-		skb_queue_purge(&npinfo->arp_tx);
-		skb_queue_purge(&npinfo->txq);
-		cancel_delayed_work_sync(&npinfo->tx_work);
+	__netpoll_cleanup(np);
+	kfree(np);
+}
 
-		/* clean after last, unfinished work */
-		__skb_queue_purge(&npinfo->txq);
-		kfree(npinfo);
-	}
+void __netpoll_free_rcu(struct netpoll *np)
+{
+	call_rcu_bh(&np->rcu, rcu_cleanup_netpoll);
 }
-EXPORT_SYMBOL_GPL(__netpoll_cleanup);
+EXPORT_SYMBOL_GPL(__netpoll_free_rcu);
 
 void netpoll_cleanup(struct netpoll *np)
 {
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index ed0c0431fcd8..c75e3f9d060f 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -101,12 +101,10 @@ static int write_update_netdev_table(struct net_device *dev)
 	u32 max_len;
 	struct netprio_map *map;
 
-	rtnl_lock();
 	max_len = atomic_read(&max_prioidx) + 1;
 	map = rtnl_dereference(dev->priomap);
 	if (!map || map->priomap_len < max_len)
 		ret = extend_netdev_table(dev, max_len);
-	rtnl_unlock();
 
 	return ret;
 }
@@ -256,17 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 	if (!dev)
 		goto out_free_devname;
 
+	rtnl_lock();
 	ret = write_update_netdev_table(dev);
 	if (ret < 0)
 		goto out_put_dev;
 
-	rcu_read_lock();
-	map = rcu_dereference(dev->priomap);
+	map = rtnl_dereference(dev->priomap);
 	if (map)
 		map->priomap[prioidx] = priority;
-	rcu_read_unlock();
 
 out_put_dev:
+	rtnl_unlock();
 	dev_put(dev);
 
 out_free_devname:
@@ -277,12 +275,6 @@ out_free_devname:
 void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
-	char *tmp = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
-
-	if (!tmp) {
-		pr_warn("Unable to attach cgrp due to alloc failure!\n");
-		return;
-	}
 
 	cgroup_taskset_for_each(p, cgrp, tset) {
 		unsigned int fd;
@@ -296,32 +288,24 @@ void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 			continue;
 		}
 
-		rcu_read_lock();
+		spin_lock(&files->file_lock);
 		fdt = files_fdtable(files);
 		for (fd = 0; fd < fdt->max_fds; fd++) {
-			char *path;
 			struct file *file;
 			struct socket *sock;
-			unsigned long s;
-			int rv, err = 0;
+			int err;
 
 			file = fcheck_files(files, fd);
 			if (!file)
 				continue;
 
-			path = d_path(&file->f_path, tmp, PAGE_SIZE);
-			rv = sscanf(path, "socket:[%lu]", &s);
-			if (rv <= 0)
-				continue;
-
 			sock = sock_from_file(file, &err);
-			if (!err)
+			if (sock)
 				sock_update_netprioidx(sock->sk, p);
 		}
-		rcu_read_unlock();
+		spin_unlock(&files->file_lock);
 		task_unlock(p);
 	}
-	kfree(tmp);
 }
 
 static struct cftype ss_files[] = {
diff --git a/net/core/scm.c b/net/core/scm.c
index 8f6ccfd68ef4..040cebeed45b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -265,6 +265,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 	for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax;
 	     i++, cmfptr++)
 	{
+		struct socket *sock;
 		int new_fd;
 		err = security_file_receive(fp[i]);
 		if (err)
@@ -281,6 +282,9 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 		}
 		/* Bump the usage count and install the file. */
 		get_file(fp[i]);
+		sock = sock_from_file(fp[i], &err);
+		if (sock)
+			sock_update_netprioidx(sock->sk, current);
 		fd_install(new_fd, fp[i]);
 	}