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

1) ICMP sockets leave err uninitialized but we try to return it for the
   unsupported MSG_OOB case, reported by Dave Jones.

2) Add new Zaurus device ID entries, from Dave Jones.

3) Pointer calculation in hso driver memset is wrong, from Dan
   Carpenter.

4) ks8851_probe() checks unsigned value as negative, fix also from Dan
   Carpenter.

5) Fix crashes in atl1c driver due to TX queue handling, from Eric
   Dumazet.  I anticipate some TX side locking fixes coming in the near
   future for this driver as well.

6) The inline directive fix in Bluetooth which was breaking the build
   only with very new versions of GCC, from Johan Hedberg.

7) Fix crashes in the ATP CLIP code due to ARP cleanups this merge
   window, reported by Meelis Roos and fixed by Eric Dumazet.

8) JME driver doesn't flush RX FIFO correctly, from Guo-Fu Tseng.

9) Some ip6_route_output() callers test the return value for NULL, but
   this never happens as the convention is to return a dst entry with
   dst->error set.  Fixes from RonQing Li.

10) Logitech Harmony 900 should be handled by zaurus driver not
   cdc_ether, update white lists and black lists accordingly.  From
   Scott Talbert.

11) Receiving from certain kinds of devices there won't be a MAC header,
   so there is no MAC header to fixup in the IPSEC code, and if we try
   to do it we'll crash.  Fix from Eric Dumazet.

12) Port type array indexing off-by-one in mlx4 driver, fix from Yevgeny
   Petrilin.

13) Fix regression in link-down handling in davinci_emac which causes
   all RX descriptors to be freed up and therefore RX to wedge
   completely, from Christian Riesch.

14) It took two attempts, but ctnetlink soft lockups seem to be
   cured now, from Pablo Neira Ayuso.

15) Endianness bug fix in ENIC driver, from Santosh Nayak.

16) The long ago conversion of the PPP fragmentation code over to
   abstracted SKB list handling wasn't perfect, once we get an
   out of sequence SKB we don't flush the rest of them like we
   should.  From Ben McKeegan.

17) Fix regression of ->ip_summed initialization in sfc driver.
   From Ben Hutchings.

18) Bluetooth timeout mistakenly using msecs instead of jiffies,
   from Andrzej Kaczmarek.

19) Using _sync variant of work cancellation results in deadlocks,
   use the non _sync variants instead.  From Andre Guedes.

20) Bluetooth rfcomm code had reference counting problems leading
   to crashes, fix from Octavian Purdila.

21) The conversion of netem over to classful qdisc handling added
   two bugs to netem_dequeue(), fixes from Eric Dumazet.

22) Missing pci_iounmap() in ATM Solos driver.  Fix from Julia Lawall.

23) b44_pci_exit() should not have __exit tag since it's invoked from
   non-__exit code.  From Nikola Pajkovsky.

24) The conversion of the neighbour hash tables over to RCU added a
   race, fixed here by adding the necessary reread of tbl->nht, fix
   from Michel Machado.

25) When we added VF (virtual function) attributes for network device
   dumps, this potentially bloats up the size of the dump of one
   network device such that the dump size is too large for the buffer
   allocated by properly written netlink applications.

   In particular, if you add 255 VFs to a network device, parts of
   GLIBC stop working.

   To fix this, we add an attribute that is used to turn on these
   extended portions of the network device dump.  Sophisticaed
   applications like 'ip' that want to see this stuff  will be changed
   to set the attribute, whereas things like GLIBC that don't care
   about VFs simply will not, and therefore won't be busted by the
   mere presence of VFs on a network device.

   Thanks to the tireless work of Greg Rose on this fix.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (53 commits)
  sfc: Fix assignment of ip_summed for pre-allocated skbs
  ppp: fix 'ppp_mp_reconstruct bad seq' errors
  enic: Fix endianness bug.
  gre: fix spelling in comments
  netfilter: ctnetlink: fix soft lockup when netlink adds new entries (v2)
  Revert "netfilter: ctnetlink: fix soft lockup when netlink adds new entries"
  davinci_emac: Do not free all rx dma descriptors during init
  mlx4_core: Fixing array indexes when setting port types
  phy: IC+101G and PHY_HAS_INTERRUPT flag
  netdev/phy/icplus: Correct broken phy_init code
  ipsec: be careful of non existing mac headers
  Move Logitech Harmony 900 from cdc_ether to zaurus
  hso: memsetting wrong data in hso_get_count()
  netfilter: ip6_route_output() never returns NULL.
  ethernet/broadcom: ip6_route_output() never returns NULL.
  ipv6: ip6_route_output() never returns NULL.
  jme: Fix FIFO flush issue
  atm: clip: remove clip_tbl
  ipv4: ping: Fix recvmsg MSG_OOB error handling.
  rtnetlink: Fix problem with buffer allocation
  ...

1 files changed, 57 insertions, 21 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 65aebd45002..606a6e8f367 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -60,7 +60,6 @@ struct rtnl_link {
 };
 
 static DEFINE_MUTEX(rtnl_mutex);
-static u16 min_ifinfo_dump_size;
 
 void rtnl_lock(void)
 {
@@ -724,10 +723,11 @@ 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));
@@ -766,7 +766,8 @@ 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 */
@@ -784,8 +785,9 @@ 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 */
@@ -868,7 +870,7 @@ 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;
@@ -941,10 +943,11 @@ 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;
@@ -1048,6 +1051,8 @@ 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];
@@ -1055,6 +1060,12 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
+	nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX,
+		    ifla_policy);
+
+	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];
@@ -1064,7 +1075,8 @@ 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;
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -1100,6 +1112,7 @@ 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);
 
@@ -1509,8 +1522,6 @@ errout:
 
 	if (send_addr_notify)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
-	min_ifinfo_dump_size = max_t(u16, if_nlmsg_size(dev),
-				     min_ifinfo_dump_size);
 
 	return err;
 }
@@ -1842,6 +1853,7 @@ 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)
@@ -1850,6 +1862,9 @@ 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);
@@ -1861,12 +1876,12 @@ 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);
@@ -1877,8 +1892,31 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	return err;
 }
 
-static u16 rtnl_calcit(struct sk_buff *skb)
+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;
+
+	nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, ifla_policy);
+
+	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;
 }
 
@@ -1913,13 +1951,11 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
 	int err = -ENOBUFS;
 	size_t if_info_size;
 
-	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL);
+	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL);
 	if (skb == NULL)
 		goto errout;
 
-	min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size);
-
-	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);
@@ -1977,7 +2013,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			return -EOPNOTSUPP;
 		calcit = rtnl_get_calcit(family, type);
 		if (calcit)
-			min_dump_alloc = calcit(skb);
+			min_dump_alloc = calcit(skb, nlh);
 
 		__rtnl_unlock();
 		rtnl = net->rtnl;