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

Pull networking changes from David Miller:

 1) Multiply in netfilter IPVS can overflow when calculating destination
    weight.  From Simon Kirby.

 2) Use after free fixes in IPVS from Julian Anastasov.

 3) SFC driver bug fixes from Daniel Pieczko.

 4) Memory leak in pcan_usb_core failure paths, from Alexey Khoroshilov.

 5) Locking and encapsulation fixes to serial line CAN driver, from
    Andrew Naujoks.

 6) Duplex and VF handling fixes to bnx2x driver from Yaniv Rosner,
    Eilon Greenstein, and Ariel Elior.

 7) In lapb, if no other packets are outstanding, T1 timeouts actually
    stall things and no packet gets sent.  Fix from Josselin Costanzi.

 8) ICMP redirects should not make it to the socket error queues, from
    Duan Jiong.

 9) Fix bugs in skge DMA mapping error handling, from Nikulas Patocka.

10) Fix setting of VLAN priority field on via-rhine driver, from Roget
    Luethi.

11) Fix TX stalls and VLAN promisc programming in be2net driver from
    Ajit Khaparde.

12) Packet padding doesn't get handled correctly in new usbnet SG
    support code, from Ming Lei.

13) Fix races in netdevice teardown wrt.  network namespace closing.
    From Eric W.  Biederman.

14) Fix potential missed initialization of net_secret if not TCP
    connections are openned.  From Eric Dumazet.

15) Cinterion PLXX product ID in qmi_wwan driver is wrong, from
    Aleksander Morgado.

16) skb_cow_head() can change skb->data and thus packet header pointers,
    don't use stale ip_hdr reference in ip_tunnel code.

17) Backend state transition handling fixes in xen-netback, from Paul
    Durrant.

18) Packet offset for AH protocol is handled wrong in flow dissector,
    from Eric Dumazet.

19) Taking down an fq packet scheduler instance can leave stale packets
    in the queues, fix from Eric Dumazet.

20) Fix performance regressions introduced by TCP Small Queues.  From
    Eric Dumazet.

21) IPV6 GRE tunneling code calculates max_headroom incorrectly, from
    Hannes Frederic Sowa.

22) Multicast timer handlers in ipv4 and ipv6 can be the last and final
    reference to the ipv4/ipv6 specific network device state, so use the
    reference put that will check and release the object if the
    reference hits zero.  From Salam Noureddine.

23) Fix memory corruption in ip_tunnel driver, and use skb_push()
    instead of __skb_push() so that similar bugs are less hard to find.
    From Steffen Klassert.

24) Add forgotten hookup of rtnl_ops in SIT and ip6tnl drivers, from
    Nicolas Dichtel.

25) fq scheduler doesn't accurately rate limit in certain circumstances,
    from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (103 commits)
  pkt_sched: fq: rate limiting improvements
  ip6tnl: allow to use rtnl ops on fb tunnel
  sit: allow to use rtnl ops on fb tunnel
  ip_tunnel: Remove double unregister of the fallback device
  ip_tunnel_core: Change __skb_push back to skb_push
  ip_tunnel: Add fallback tunnels to the hash lists
  ip_tunnel: Fix a memory corruption in ip_tunnel_xmit
  qlcnic: Fix SR-IOV configuration
  ll_temac: Reset dma descriptors indexes on ndo_open
  skbuff: size of hole is wrong in a comment
  ipv6 mcast: use in6_dev_put in timer handlers instead of __in6_dev_put
  ipv4 igmp: use in_dev_put in timer handlers instead of __in_dev_put
  ethernet: moxa: fix incorrect placement of __initdata tag
  ipv6: gre: correct calculation of max_headroom
  powerpc/83xx: gianfar_ptp: select 1588 clock source through dts file
  Revert "powerpc/83xx: gianfar_ptp: select 1588 clock source through dts file"
  bonding: Fix broken promiscuity reference counting issue
  tcp: TSQ can use a dynamic limit
  dm9601: fix IFF_ALLMULTI handling
  pkt_sched: fq: qdisc dismantle fixes
  ...

3 files changed, 74 insertions, 6 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 5c713f2239cc..65f829cfd928 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5247,10 +5247,12 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
+static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {
 	list_add_tail(&dev->todo_list, &net_todo_list);
+	dev_net(dev)->dev_unreg_count++;
 }
 
 static void rollback_registered_many(struct list_head *head)
@@ -5918,6 +5920,12 @@ void netdev_run_todo(void)
 		if (dev->destructor)
 			dev->destructor(dev);
 
+		/* Report a network device has been unregistered */
+		rtnl_lock();
+		dev_net(dev)->dev_unreg_count--;
+		__rtnl_unlock();
+		wake_up(&netdev_unregistering_wq);
+
 		/* Free network device */
 		kobject_put(&dev->dev.kobj);
 	}
@@ -6603,6 +6611,34 @@ static void __net_exit default_device_exit(struct net *net)
 	rtnl_unlock();
 }
 
+static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
+{
+	/* Return with the rtnl_lock held when there are no network
+	 * devices unregistering in any network namespace in net_list.
+	 */
+	struct net *net;
+	bool unregistering;
+	DEFINE_WAIT(wait);
+
+	for (;;) {
+		prepare_to_wait(&netdev_unregistering_wq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		unregistering = false;
+		rtnl_lock();
+		list_for_each_entry(net, net_list, exit_list) {
+			if (net->dev_unreg_count > 0) {
+				unregistering = true;
+				break;
+			}
+		}
+		if (!unregistering)
+			break;
+		__rtnl_unlock();
+		schedule();
+	}
+	finish_wait(&netdev_unregistering_wq, &wait);
+}
+
 static void __net_exit default_device_exit_batch(struct list_head *net_list)
 {
 	/* At exit all network devices most be removed from a network
@@ -6614,7 +6650,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 	struct net *net;
 	LIST_HEAD(dev_kill_list);
 
-	rtnl_lock();
+	/* To prevent network device cleanup code from dereferencing
+	 * loopback devices or network devices that have been freed
+	 * wait here for all pending unregistrations to complete,
+	 * before unregistring the loopback device and allowing the
+	 * network namespace be freed.
+	 *
+	 * The netdev todo list containing all network devices
+	 * unregistrations that happen in default_device_exit_batch
+	 * will run in the rtnl_unlock() at the end of
+	 * default_device_exit_batch.
+	 */
+	rtnl_lock_unregistering(net_list);
 	list_for_each_entry(net, net_list, exit_list) {
 		for_each_netdev_reverse(net, dev) {
 			if (dev->rtnl_link_ops)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 1929af87b260..8d7d0dd72db2 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -154,8 +154,8 @@ ipv6:
 	if (poff >= 0) {
 		__be32 *ports, _ports;
 
-		nhoff += poff;
-		ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
+		ports = skb_header_pointer(skb, nhoff + poff,
+					   sizeof(_ports), &_ports);
 		if (ports)
 			flow->ports = *ports;
 	}
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 6a2f13cee86a..3f1ec1586ae1 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -10,11 +10,24 @@
 
 #include <net/secure_seq.h>
 
-static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
 
-void net_secret_init(void)
+static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+
+static void net_secret_init(void)
 {
-	get_random_bytes(net_secret, sizeof(net_secret));
+	u32 tmp;
+	int i;
+
+	if (likely(net_secret[0]))
+		return;
+
+	for (i = NET_SECRET_SIZE; i > 0;) {
+		do {
+			get_random_bytes(&tmp, sizeof(tmp));
+		} while (!tmp);
+		cmpxchg(&net_secret[--i], 0, tmp);
+	}
 }
 
 #ifdef CONFIG_INET
@@ -42,6 +55,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + (__force u32)daddr[i];
@@ -63,6 +77,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + (__force u32) daddr[i];
@@ -82,6 +97,7 @@ __u32 secure_ip_id(__be32 daddr)
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force __u32) daddr;
 	hash[1] = net_secret[13];
 	hash[2] = net_secret[14];
@@ -96,6 +112,7 @@ __u32 secure_ipv6_id(const __be32 daddr[4])
 {
 	__u32 hash[4];
 
+	net_secret_init();
 	memcpy(hash, daddr, 16);
 	md5_transform(hash, net_secret);
 
@@ -107,6 +124,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -121,6 +139,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
 	u32 hash[MD5_DIGEST_WORDS];
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = (__force u32)dport ^ net_secret[14];
@@ -140,6 +159,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 	u32 hash[MD5_DIGEST_WORDS];
 	u64 seq;
 
+	net_secret_init();
 	hash[0] = (__force u32)saddr;
 	hash[1] = (__force u32)daddr;
 	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -164,6 +184,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 	u64 seq;
 	u32 i;
 
+	net_secret_init();
 	memcpy(hash, saddr, 16);
 	for (i = 0; i < 4; i++)
 		secret[i] = net_secret[i] + daddr[i];