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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 59 insertions, 14 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2d8d8fcfa060..1063996f8317 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -798,8 +798,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 		size += num_vfs *
 			(nla_total_size(sizeof(struct ifla_vf_mac)) +
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
-			 nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_spoofchk)));
+			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+			 nla_total_size(sizeof(struct ifla_vf_rate)));
 		return size;
 	} else
 		return 0;
@@ -1065,6 +1065,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_info ivi;
 			struct ifla_vf_mac vf_mac;
 			struct ifla_vf_vlan vf_vlan;
+			struct ifla_vf_rate vf_rate;
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
@@ -1085,6 +1086,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				break;
 			vf_mac.vf =
 				vf_vlan.vf =
+				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
 				vf_linkstate.vf = ivi.vf;
@@ -1092,7 +1094,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
 			vf_vlan.qos = ivi.qos;
-			vf_tx_rate.rate = ivi.tx_rate;
+			vf_tx_rate.rate = ivi.max_tx_rate;
+			vf_rate.min_tx_rate = ivi.min_tx_rate;
+			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
@@ -1102,6 +1106,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			}
 			if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
 			    nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
+			    nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
+				    &vf_rate) ||
 			    nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
 				    &vf_tx_rate) ||
 			    nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
@@ -1208,6 +1214,10 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 				    .len = sizeof(struct ifla_vf_tx_rate) },
 	[IFLA_VF_SPOOFCHK]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct ifla_vf_spoofchk) },
+	[IFLA_VF_RATE]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_rate) },
+	[IFLA_VF_LINK_STATE]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_link_state) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1234,6 +1244,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	int err;
+	int hdrlen;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
@@ -1241,8 +1252,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1367,11 +1387,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 		}
 		case IFLA_VF_TX_RATE: {
 			struct ifla_vf_tx_rate *ivt;
+			struct ifla_vf_info ivf;
 			ivt = nla_data(vf);
 			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_tx_rate)
-				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
-							      ivt->rate);
+			if (ops->ndo_get_vf_config)
+				err = ops->ndo_get_vf_config(dev, ivt->vf,
+							     &ivf);
+			if (err)
+				break;
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivf.min_tx_rate,
+							   ivt->rate);
+			break;
+		}
+		case IFLA_VF_RATE: {
+			struct ifla_vf_rate *ivt;
+			ivt = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivt->min_tx_rate,
+							   ivt->max_tx_rate);
 			break;
 		}
 		case IFLA_VF_SPOOFCHK: {
@@ -1744,7 +1782,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 
@@ -2019,11 +2056,15 @@ replay:
 		if (ops->newlink) {
 			err = ops->newlink(net, dev, tb, data);
 			/* Drivers should call free_netdev() in ->destructor
-			 * and unregister it on failure so that device could be
-			 * finally freed in rtnl_unlock.
+			 * and unregister it on failure after registration
+			 * so that device could be finally freed in rtnl_unlock.
 			 */
-			if (err < 0)
+			if (err < 0) {
+				/* If device is not registered at all, free it now */
+				if (dev->reg_state == NETREG_UNINITIALIZED)
+					free_netdev(dev);
 				goto out;
+			}
 		} else {
 			err = register_netdevice(dev);
 			if (err < 0) {
@@ -2095,9 +2136,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
+
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}