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

Pull networking changes from David Miller:

 1) Get rid of the error prone NLA_PUT*() macros that used an embedded
    goto.

 2) Kill off the token-ring and MCA networking drivers, from Paul
    Gortmaker.

 3) Reduce high-order allocations made by datagram AF_UNIX sockets, from
    Eric Dumazet.

 4) Add PTP hardware clock support to IGB and IXGBE, from Richard
    Cochran and Jacob Keller.

 5) Allow users to query timestamping capabilities of a card via
    ethtool, from Richard Cochran.

 6) Add loadbalance mode to the teaming driver, from Jiri Pirko.  Part
    of this is that we can now have BPF filters not attached to sockets,
    and the loadbalancing function is calculated using one.

 7) Francois Romieu went through the network drivers removing gratuitous
    uses of netdev->base_addr, perhaps some day we can remove it
    completely but it's used for ISA probing still.

 8) Add a BPF JIT for sparc.  I know, who cares, right? :-)

 9) Move networking sysctl registry away from using the compatability
    mode interfaces in the sysctl code.  From Eric W Biederman.

10) Pavel Emelyanov added a way to save and restore TCP socket state via
    TCP_REPAIR, TCP_REPAIR_QUEUE, and TCP_QUEUE_SEQ socket options as
    well as a way to forcefully bind a socket to a port via the
    sk->sk_reuse value SK_FORCE_REUSE.  There is also a
    TCP_REPAIR_OPTIONS which allows to reinstante the TCP options
    enabled on the connection.

11) Several enhancements from Eric Dumazet that, in particular, can
    enhance splice performance on TCP sockets significantly.

     a) Reset the offset of the per-socket sendmsg page when we know
        we're the only use of the page in linear_to_page().

     b) Add facilities such that skb->data can be backed a page rather
        than SLAB kmalloc'd memory.  In particular devices which were
        receiving into linear RX buffers can now end up providing paged
        data.

    The big result is that code like splice and GRO do not have to copy
    any more.

12) Allow a pure sender to more gracefully handle ACK backlogs in TCP.
    What can happen at high rates is that the sender hasn't grown his
    receive buffer limits at all (he's not receiving data so really
    doesn't need to), but the non-data ACKs consume receive buffer
    space.

    sk_add_backlog() is too aggressive in dropping frames in this case,
    so relax it's requirements by using the receive buffer plus the send
    buffer limit as the backlog limit instead of just the former.

    Also from Eric Dumazet.

13) Add ipv6 support to L2TP, from Benjamin LaHaise, James Chapman, and
    Chris Elston.

14) Implement TCP early retransmit (RFC 5827), from Yuchung Cheng.
    Basically, we can start fast retransmit before hiting the dupack
    threshold under certain conditions.

15) New CODEL active queue management packet scheduler, from Eric
    Dumazet based upon initial work by Dave Taht.

    Basically, the big feature is that packets are dropped (or ECN bits
    are set) based upon how long packets live in the queue, rather than
    the queue length (which is what RED uses).

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1341 commits)
  drivers/net/stmmac: seq_file fix memory leak
  ipv6/exthdrs: strict Pad1 and PadN check
  USB: qmi_wwan: Add ZTE (Vodafone) K3520-Z
  USB: qmi_wwan: Add ZTE (Vodafone) K3765-Z
  USB: qmi_wwan: Make forced int 4 whitelist generic
  net/ipv4: replace simple_strtoul with kstrtoul
  net/ipv4/ipconfig: neaten __setup placement
  net: qmi_wwan: Add Vodafone/Huawei K5005 support
  net: cdc_ether: Add ZTE WWAN matches before generic Ethernet
  ipv6: use skb coalescing in reassembly
  ipv4: use skb coalescing in defragmentation
  net: introduce skb_try_coalesce()
  net:ipv6:fixed space issues relating to operators.
  net:ipv6:fixed a trailing white space issue.
  ipv6: disable GSO on sockets hitting dst_allfrag
  tg3: use netdev_alloc_frag() API
  net: napi_frags_skb() is static
  ppp: avoid false drop_monitor false positives
  ipv6: bool/const conversions phase2
  ipx: Remove spurious NULL checking in ipx_ioctl().
  ...

1 files changed, 42 insertions, 33 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index faa48f70b7c9..b3025a603d56 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -104,27 +104,27 @@ static inline int netlink_is_kernel(struct sock *sk)
 }
 
 struct nl_pid_hash {
-	struct hlist_head *table;
-	unsigned long rehash_time;
+	struct hlist_head	*table;
+	unsigned long		rehash_time;
 
-	unsigned int mask;
-	unsigned int shift;
+	unsigned int		mask;
+	unsigned int		shift;
 
-	unsigned int entries;
-	unsigned int max_shift;
+	unsigned int		entries;
+	unsigned int		max_shift;
 
-	u32 rnd;
+	u32			rnd;
 };
 
 struct netlink_table {
-	struct nl_pid_hash hash;
-	struct hlist_head mc_list;
-	struct listeners __rcu *listeners;
-	unsigned int nl_nonroot;
-	unsigned int groups;
-	struct mutex *cb_mutex;
-	struct module *module;
-	int registered;
+	struct nl_pid_hash	hash;
+	struct hlist_head	mc_list;
+	struct listeners __rcu	*listeners;
+	unsigned int		nl_nonroot;
+	unsigned int		groups;
+	struct mutex		*cb_mutex;
+	struct module		*module;
+	int			registered;
 };
 
 static struct netlink_table *nl_table;
@@ -132,7 +132,6 @@ static struct netlink_table *nl_table;
 static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
 
 static int netlink_dump(struct sock *sk);
-static void netlink_destroy_callback(struct netlink_callback *cb);
 
 static DEFINE_RWLOCK(nl_table_lock);
 static atomic_t nl_table_users = ATOMIC_INIT(0);
@@ -149,6 +148,18 @@ static inline struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid
 	return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask];
 }
 
+static void netlink_destroy_callback(struct netlink_callback *cb)
+{
+	kfree_skb(cb->skb);
+	kfree(cb);
+}
+
+static void netlink_consume_callback(struct netlink_callback *cb)
+{
+	consume_skb(cb->skb);
+	kfree(cb);
+}
+
 static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -414,9 +425,9 @@ static int __netlink_create(struct net *net, struct socket *sock,
 	sock_init_data(sock, sk);
 
 	nlk = nlk_sk(sk);
-	if (cb_mutex)
+	if (cb_mutex) {
 		nlk->cb_mutex = cb_mutex;
-	else {
+	} else {
 		nlk->cb_mutex = &nlk->cb_def_mutex;
 		mutex_init(nlk->cb_mutex);
 	}
@@ -522,8 +533,9 @@ static int netlink_release(struct socket *sock)
 			nl_table[sk->sk_protocol].module = NULL;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
-	} else if (nlk->subscriptions)
+	} else if (nlk->subscriptions) {
 		netlink_update_listeners(sk);
+	}
 	netlink_table_ungrab();
 
 	kfree(nlk->groups);
@@ -866,7 +878,7 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
 		struct sk_buff *nskb = skb_clone(skb, allocation);
 		if (!nskb)
 			return skb;
-		kfree_skb(skb);
+		consume_skb(skb);
 		skb = nskb;
 	}
 
@@ -896,8 +908,10 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
 		ret = skb->len;
 		skb_set_owner_r(skb, sk);
 		nlk->netlink_rcv(skb);
+		consume_skb(skb);
+	} else {
+		kfree_skb(skb);
 	}
-	kfree_skb(skb);
 	sock_put(sk);
 	return ret;
 }
@@ -1086,8 +1100,8 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid,
 	if (info.delivery_failure) {
 		kfree_skb(info.skb2);
 		return -ENOBUFS;
-	} else
-		consume_skb(info.skb2);
+	}
+	consume_skb(info.skb2);
 
 	if (info.delivered) {
 		if (info.congested && (allocation & __GFP_WAIT))
@@ -1240,8 +1254,9 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			nlk->flags |= NETLINK_RECV_NO_ENOBUFS;
 			clear_bit(0, &nlk->state);
 			wake_up_interruptible(&nlk->wait);
-		} else
+		} else {
 			nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS;
+		}
 		err = 0;
 		break;
 	default:
@@ -1645,12 +1660,6 @@ void netlink_set_nonroot(int protocol, unsigned int flags)
 }
 EXPORT_SYMBOL(netlink_set_nonroot);
 
-static void netlink_destroy_callback(struct netlink_callback *cb)
-{
-	kfree_skb(cb->skb);
-	kfree(cb);
-}
-
 struct nlmsghdr *
 __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags)
 {
@@ -1727,7 +1736,7 @@ static int netlink_dump(struct sock *sk)
 	nlk->cb = NULL;
 	mutex_unlock(nlk->cb_mutex);
 
-	netlink_destroy_callback(cb);
+	netlink_consume_callback(cb);
 	return 0;
 
 errout_skb:
@@ -1996,11 +2005,11 @@ static void netlink_seq_stop(struct seq_file *seq, void *v)
 
 static int netlink_seq_show(struct seq_file *seq, void *v)
 {
-	if (v == SEQ_START_TOKEN)
+	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
 			 "sk       Eth Pid    Groups   "
 			 "Rmem     Wmem     Dump     Locks     Drops     Inode\n");
-	else {
+	} else {
 		struct sock *s = v;
 		struct netlink_sock *nlk = nlk_sk(s);