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

Pull networking updates from David Miller:
 "Highlights (1721 non-merge commits, this has to be a record of some
  sort):

   1) Add 'random' mode to team driver, from Jiri Pirko and Eric
      Dumazet.

   2) Make it so that any driver that supports configuration of multiple
      MAC addresses can provide the forwarding database add and del
      calls by providing a default implementation and hooking that up if
      the driver doesn't have an explicit set of handlers.  From Vlad
      Yasevich.

   3) Support GSO segmentation over tunnels and other encapsulating
      devices such as VXLAN, from Pravin B Shelar.

   4) Support L2 GRE tunnels in the flow dissector, from Michael Dalton.

   5) Implement Tail Loss Probe (TLP) detection in TCP, from Nandita
      Dukkipati.

   6) In the PHY layer, allow supporting wake-on-lan in situations where
      the PHY registers have to be written for it to be configured.

      Use it to support wake-on-lan in mv643xx_eth.

      From Michael Stapelberg.

   7) Significantly improve firewire IPV6 support, from YOSHIFUJI
      Hideaki.

   8) Allow multiple packets to be sent in a single transmission using
      network coding in batman-adv, from Martin Hundebøll.

   9) Add support for T5 cxgb4 chips, from Santosh Rastapur.

  10) Generalize the VXLAN forwarding tables so that there is more
      flexibility in configurating various aspects of the endpoints.
      From David Stevens.

  11) Support RSS and TSO in hardware over GRE tunnels in bxn2x driver,
      from Dmitry Kravkov.

  12) Zero copy support in nfnelink_queue, from Eric Dumazet and Pablo
      Neira Ayuso.

  13) Start adding networking selftests.

  14) In situations of overload on the same AF_PACKET fanout socket, or
      per-cpu packet receive queue, minimize drop by distributing the
      load to other cpus/fanouts.  From Willem de Bruijn and Eric
      Dumazet.

  15) Add support for new payload offset BPF instruction, from Daniel
      Borkmann.

  16) Convert several drivers over to mdoule_platform_driver(), from
      Sachin Kamat.

  17) Provide a minimal BPF JIT image disassembler userspace tool, from
      Daniel Borkmann.

  18) Rewrite F-RTO implementation in TCP to match the final
      specification of it in RFC4138 and RFC5682.  From Yuchung Cheng.

  19) Provide netlink socket diag of netlink sockets ("Yo dawg, I hear
      you like netlink, so I implemented netlink dumping of netlink
      sockets.") From Andrey Vagin.

  20) Remove ugly passing of rtnetlink attributes into rtnl_doit
      functions, from Thomas Graf.

  21) Allow userspace to be able to see if a configuration change occurs
      in the middle of an address or device list dump, from Nicolas
      Dichtel.

  22) Support RFC3168 ECN protection for ipv6 fragments, from Hannes
      Frederic Sowa.

  23) Increase accuracy of packet length used by packet scheduler, from
      Jason Wang.

  24) Beginning set of changes to make ipv4/ipv6 fragment handling more
      scalable and less susceptible to overload and locking contention,
      from Jesper Dangaard Brouer.

  25) Get rid of using non-type-safe NLMSG_* macros and use nlmsg_*()
      instead.  From Hong Zhiguo.

  26) Optimize route usage in IPVS by avoiding reference counting where
      possible, from Julian Anastasov.

  27) Convert IPVS schedulers to RCU, also from Julian Anastasov.

  28) Support cpu fanouts in xt_NFQUEUE netfilter target, from Holger
      Eitzenberger.

  29) Network namespace support for nf_log, ebt_log, xt_LOG, ipt_ULOG,
      nfnetlink_log, and nfnetlink_queue.  From Gao feng.

  30) Implement RFC3168 ECN protection, from Hannes Frederic Sowa.

  31) Support several new r8169 chips, from Hayes Wang.

  32) Support tokenized interface identifiers in ipv6, from Daniel
      Borkmann.

  33) Use usbnet_link_change() helper in USB net driver, from Ming Lei.

  34) Add 802.1ad vlan offload support, from Patrick McHardy.

  35) Support mmap() based netlink communication, also from Patrick
      McHardy.

  36) Support HW timestamping in mlx4 driver, from Amir Vadai.

  37) Rationalize AF_PACKET packet timestamping when transmitting, from
      Willem de Bruijn and Daniel Borkmann.

  38) Bring parity to what's provided by /proc/net/packet socket dumping
      and the info provided by netlink socket dumping of AF_PACKET
      sockets.  From Nicolas Dichtel.

  39) Fix peeking beyond zero sized SKBs in AF_UNIX, from Benjamin
      Poirier"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  filter: fix va_list build error
  af_unix: fix a fatal race with bit fields
  bnx2x: Prevent memory leak when cnic is absent
  bnx2x: correct reading of speed capabilities
  net: sctp: attribute printl with __printf for gcc fmt checks
  netlink: kconfig: move mmap i/o into netlink kconfig
  netpoll: convert mutex into a semaphore
  netlink: Fix skb ref counting.
  net_sched: act_ipt forward compat with xtables
  mlx4_en: fix a build error on 32bit arches
  Revert "bnx2x: allow nvram test to run when device is down"
  bridge: avoid OOPS if root port not found
  drivers: net: cpsw: fix kernel warn on cpsw irq enable
  sh_eth: use random MAC address if no valid one supplied
  3c509.c: call SET_NETDEV_DEV for all device types (ISA/ISAPnP/EISA)
  tg3: fix to append hardware time stamping flags
  unix/stream: fix peeking with an offset larger than data in queue
  unix/dgram: fix peeking with an offset larger than data in queue
  unix/dgram: peek beyond 0-sized skbs
  openvswitch: Remove unneeded ovs_netdev_get_ifindex()
  ...

1 files changed, 92 insertions, 42 deletions

diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 7d168dcbd135..f8a222cb6448 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -4,6 +4,7 @@
  * (C) 2000-2004 by Harald Welte <laforge@netfilter.org>
  * (C) 1999-2001 Paul `Rusty' Russell
  * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2005-2007 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -37,7 +38,7 @@
 #include <linux/skbuff.h>
 #include <linux/kernel.h>
 #include <linux/timer.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
 #include <linux/netdevice.h>
 #include <linux/mm.h>
 #include <linux/moduleparam.h>
@@ -45,6 +46,7 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ipt_ULOG.h>
 #include <net/netfilter/nf_log.h>
+#include <net/netns/generic.h>
 #include <net/sock.h>
 #include <linux/bitops.h>
 #include <asm/unaligned.h>
@@ -78,15 +80,23 @@ typedef struct {
 	struct timer_list timer;	/* the timer function */
 } ulog_buff_t;
 
-static ulog_buff_t ulog_buffers[ULOG_MAXNLGROUPS];	/* array of buffers */
+static int ulog_net_id __read_mostly;
+struct ulog_net {
+	unsigned int nlgroup[ULOG_MAXNLGROUPS];
+	ulog_buff_t ulog_buffers[ULOG_MAXNLGROUPS];
+	struct sock *nflognl;
+	spinlock_t lock;
+};
 
-static struct sock *nflognl;		/* our socket */
-static DEFINE_SPINLOCK(ulog_lock);	/* spinlock */
+static struct ulog_net *ulog_pernet(struct net *net)
+{
+	return net_generic(net, ulog_net_id);
+}
 
 /* send one ulog_buff_t to userspace */
-static void ulog_send(unsigned int nlgroupnum)
+static void ulog_send(struct ulog_net *ulog, unsigned int nlgroupnum)
 {
-	ulog_buff_t *ub = &ulog_buffers[nlgroupnum];
+	ulog_buff_t *ub = &ulog->ulog_buffers[nlgroupnum];
 
 	pr_debug("ulog_send: timer is deleting\n");
 	del_timer(&ub->timer);
@@ -103,7 +113,8 @@ static void ulog_send(unsigned int nlgroupnum)
 	NETLINK_CB(ub->skb).dst_group = nlgroupnum + 1;
 	pr_debug("throwing %d packets to netlink group %u\n",
 		 ub->qlen, nlgroupnum + 1);
-	netlink_broadcast(nflognl, ub->skb, 0, nlgroupnum + 1, GFP_ATOMIC);
+	netlink_broadcast(ulog->nflognl, ub->skb, 0, nlgroupnum + 1,
+			  GFP_ATOMIC);
 
 	ub->qlen = 0;
 	ub->skb = NULL;
@@ -114,13 +125,16 @@ static void ulog_send(unsigned int nlgroupnum)
 /* timer function to flush queue in flushtimeout time */
 static void ulog_timer(unsigned long data)
 {
+	struct ulog_net *ulog = container_of((void *)data,
+					     struct ulog_net,
+					     nlgroup[*(unsigned int *)data]);
 	pr_debug("timer function called, calling ulog_send\n");
 
 	/* lock to protect against somebody modifying our structure
 	 * from ipt_ulog_target at the same time */
-	spin_lock_bh(&ulog_lock);
-	ulog_send(data);
-	spin_unlock_bh(&ulog_lock);
+	spin_lock_bh(&ulog->lock);
+	ulog_send(ulog, data);
+	spin_unlock_bh(&ulog->lock);
 }
 
 static struct sk_buff *ulog_alloc_skb(unsigned int size)
@@ -160,6 +174,8 @@ static void ipt_ulog_packet(unsigned int hooknum,
 	size_t size, copy_len;
 	struct nlmsghdr *nlh;
 	struct timeval tv;
+	struct net *net = dev_net(in ? in : out);
+	struct ulog_net *ulog = ulog_pernet(net);
 
 	/* ffs == find first bit set, necessary because userspace
 	 * is already shifting groupnumber, but we need unshifted.
@@ -172,11 +188,11 @@ static void ipt_ulog_packet(unsigned int hooknum,
 	else
 		copy_len = loginfo->copy_range;
 
-	size = NLMSG_SPACE(sizeof(*pm) + copy_len);
+	size = nlmsg_total_size(sizeof(*pm) + copy_len);
 
-	ub = &ulog_buffers[groupnum];
+	ub = &ulog->ulog_buffers[groupnum];
 
-	spin_lock_bh(&ulog_lock);
+	spin_lock_bh(&ulog->lock);
 
 	if (!ub->skb) {
 		if (!(ub->skb = ulog_alloc_skb(size)))
@@ -186,7 +202,7 @@ static void ipt_ulog_packet(unsigned int hooknum,
 		/* either the queue len is too high or we don't have
 		 * enough room in nlskb left. send it to userspace. */
 
-		ulog_send(groupnum);
+		ulog_send(ulog, groupnum);
 
 		if (!(ub->skb = ulog_alloc_skb(size)))
 			goto alloc_failure;
@@ -260,16 +276,16 @@ static void ipt_ulog_packet(unsigned int hooknum,
 	if (ub->qlen >= loginfo->qthreshold) {
 		if (loginfo->qthreshold > 1)
 			nlh->nlmsg_type = NLMSG_DONE;
-		ulog_send(groupnum);
+		ulog_send(ulog, groupnum);
 	}
 out_unlock:
-	spin_unlock_bh(&ulog_lock);
+	spin_unlock_bh(&ulog->lock);
 
 	return;
 
 alloc_failure:
 	pr_debug("Error building netlink message\n");
-	spin_unlock_bh(&ulog_lock);
+	spin_unlock_bh(&ulog->lock);
 }
 
 static unsigned int
@@ -376,54 +392,43 @@ static struct nf_logger ipt_ulog_logger __read_mostly = {
 	.me		= THIS_MODULE,
 };
 
-static int __init ulog_tg_init(void)
+static int __net_init ulog_tg_net_init(struct net *net)
 {
-	int ret, i;
+	int i;
+	struct ulog_net *ulog = ulog_pernet(net);
 	struct netlink_kernel_cfg cfg = {
 		.groups	= ULOG_MAXNLGROUPS,
 	};
 
-	pr_debug("init module\n");
-
-	if (nlbufsiz > 128*1024) {
-		pr_warning("Netlink buffer has to be <= 128kB\n");
-		return -EINVAL;
-	}
-
+	spin_lock_init(&ulog->lock);
 	/* initialize ulog_buffers */
 	for (i = 0; i < ULOG_MAXNLGROUPS; i++)
-		setup_timer(&ulog_buffers[i].timer, ulog_timer, i);
+		setup_timer(&ulog->ulog_buffers[i].timer, ulog_timer, i);
 
-	nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, &cfg);
-	if (!nflognl)
+	ulog->nflognl = netlink_kernel_create(net, NETLINK_NFLOG, &cfg);
+	if (!ulog->nflognl)
 		return -ENOMEM;
 
-	ret = xt_register_target(&ulog_tg_reg);
-	if (ret < 0) {
-		netlink_kernel_release(nflognl);
-		return ret;
-	}
 	if (nflog)
-		nf_log_register(NFPROTO_IPV4, &ipt_ulog_logger);
+		nf_log_set(net, NFPROTO_IPV4, &ipt_ulog_logger);
 
 	return 0;
 }
 
-static void __exit ulog_tg_exit(void)
+static void __net_exit ulog_tg_net_exit(struct net *net)
 {
 	ulog_buff_t *ub;
 	int i;
-
-	pr_debug("cleanup_module\n");
+	struct ulog_net *ulog = ulog_pernet(net);
 
 	if (nflog)
-		nf_log_unregister(&ipt_ulog_logger);
-	xt_unregister_target(&ulog_tg_reg);
-	netlink_kernel_release(nflognl);
+		nf_log_unset(net, &ipt_ulog_logger);
+
+	netlink_kernel_release(ulog->nflognl);
 
 	/* remove pending timers and free allocated skb's */
 	for (i = 0; i < ULOG_MAXNLGROUPS; i++) {
-		ub = &ulog_buffers[i];
+		ub = &ulog->ulog_buffers[i];
 		pr_debug("timer is deleting\n");
 		del_timer(&ub->timer);
 
@@ -434,5 +439,50 @@ static void __exit ulog_tg_exit(void)
 	}
 }
 
+static struct pernet_operations ulog_tg_net_ops = {
+	.init = ulog_tg_net_init,
+	.exit = ulog_tg_net_exit,
+	.id   = &ulog_net_id,
+	.size = sizeof(struct ulog_net),
+};
+
+static int __init ulog_tg_init(void)
+{
+	int ret;
+	pr_debug("init module\n");
+
+	if (nlbufsiz > 128*1024) {
+		pr_warn("Netlink buffer has to be <= 128kB\n");
+		return -EINVAL;
+	}
+
+	ret = register_pernet_subsys(&ulog_tg_net_ops);
+	if (ret)
+		goto out_pernet;
+
+	ret = xt_register_target(&ulog_tg_reg);
+	if (ret < 0)
+		goto out_target;
+
+	if (nflog)
+		nf_log_register(NFPROTO_IPV4, &ipt_ulog_logger);
+
+	return 0;
+
+out_target:
+	unregister_pernet_subsys(&ulog_tg_net_ops);
+out_pernet:
+	return ret;
+}
+
+static void __exit ulog_tg_exit(void)
+{
+	pr_debug("cleanup_module\n");
+	if (nflog)
+		nf_log_unregister(&ipt_ulog_logger);
+	xt_unregister_target(&ulog_tg_reg);
+	unregister_pernet_subsys(&ulog_tg_net_ops);
+}
+
 module_init(ulog_tg_init);
 module_exit(ulog_tg_exit);