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

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 224 insertions, 6 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fad649ae4de..1868625af25 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -128,7 +128,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
 	if (tab == NULL || tab[msgindex].doit == NULL)
 		tab = rtnl_msg_handlers[PF_UNSPEC];
 
-	return tab ? tab[msgindex].doit : NULL;
+	return tab[msgindex].doit;
 }
 
 static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
@@ -143,7 +143,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
 	if (tab == NULL || tab[msgindex].dumpit == NULL)
 		tab = rtnl_msg_handlers[PF_UNSPEC];
 
-	return tab ? tab[msgindex].dumpit : NULL;
+	return tab[msgindex].dumpit;
 }
 
 static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
@@ -158,7 +158,7 @@ static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
 	if (tab == NULL || tab[msgindex].calcit == NULL)
 		tab = rtnl_msg_handlers[PF_UNSPEC];
 
-	return tab ? tab[msgindex].calcit : NULL;
+	return tab[msgindex].calcit;
 }
 
 /**
@@ -1316,6 +1316,10 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			err = PTR_ERR(net);
 			goto errout;
 		}
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+			err = -EPERM;
+			goto errout;
+		}
 		err = dev_change_net_namespace(dev, net, ifname);
 		put_net(net);
 		if (err)
@@ -1638,7 +1642,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 }
 EXPORT_SYMBOL(rtnl_configure_link);
 
-struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
+struct net_device *rtnl_create_link(struct net *net,
 	char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[])
 {
 	int err;
@@ -1836,7 +1840,7 @@ replay:
 		if (IS_ERR(dest_net))
 			return PTR_ERR(dest_net);
 
-		dev = rtnl_create_link(net, dest_net, ifname, ops, tb);
+		dev = rtnl_create_link(dest_net, ifname, ops, tb);
 		if (IS_ERR(dev)) {
 			err = PTR_ERR(dev);
 			goto out;
@@ -2057,6 +2061,9 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 	u8 *addr;
 	int err;
 
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
 	if (err < 0)
 		return err;
@@ -2123,6 +2130,9 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 	int err = -EINVAL;
 	__u8 *addr;
 
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
 	if (nlmsg_len(nlh) < sizeof(*ndm))
 		return -EINVAL;
 
@@ -2253,6 +2263,211 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+			    struct net_device *dev, u16 mode)
+{
+	struct nlmsghdr *nlh;
+	struct ifinfomsg *ifm;
+	struct nlattr *br_afspec;
+	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
+
+	nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ifm = nlmsg_data(nlh);
+	ifm->ifi_family = AF_BRIDGE;
+	ifm->__ifi_pad = 0;
+	ifm->ifi_type = dev->type;
+	ifm->ifi_index = dev->ifindex;
+	ifm->ifi_flags = dev_get_flags(dev);
+	ifm->ifi_change = 0;
+
+
+	if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
+	    nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
+	    nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
+	    (dev->master &&
+	     nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) ||
+	    (dev->addr_len &&
+	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
+	    (dev->ifindex != dev->iflink &&
+	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+		goto nla_put_failure;
+
+	br_afspec = nla_nest_start(skb, IFLA_AF_SPEC);
+	if (!br_afspec)
+		goto nla_put_failure;
+
+	if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) ||
+	    nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+		nla_nest_cancel(skb, br_afspec);
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, br_afspec);
+
+	return nlmsg_end(skb, nlh);
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL(ndo_dflt_bridge_getlink);
+
+static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	int idx = 0;
+	u32 portid = NETLINK_CB(cb->skb).portid;
+	u32 seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+		struct net_device *master = dev->master;
+
+		if (master && master->netdev_ops->ndo_bridge_getlink) {
+			if (idx >= cb->args[0] &&
+			    master->netdev_ops->ndo_bridge_getlink(
+				    skb, portid, seq, dev) < 0)
+				break;
+			idx++;
+		}
+
+		if (ops->ndo_bridge_getlink) {
+			if (idx >= cb->args[0] &&
+			    ops->ndo_bridge_getlink(skb, portid, seq, dev) < 0)
+				break;
+			idx++;
+		}
+	}
+	rcu_read_unlock();
+	cb->args[0] = idx;
+
+	return skb->len;
+}
+
+static inline size_t bridge_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+		+ nla_total_size(IFNAMSIZ)	/* IFLA_IFNAME */
+		+ nla_total_size(MAX_ADDR_LEN)	/* IFLA_ADDRESS */
+		+ nla_total_size(sizeof(u32))	/* IFLA_MASTER */
+		+ nla_total_size(sizeof(u32))	/* IFLA_MTU */
+		+ nla_total_size(sizeof(u32))	/* IFLA_LINK */
+		+ nla_total_size(sizeof(u32))	/* IFLA_OPERSTATE */
+		+ nla_total_size(sizeof(u8))	/* IFLA_PROTINFO */
+		+ nla_total_size(sizeof(struct nlattr))	/* IFLA_AF_SPEC */
+		+ nla_total_size(sizeof(u16))	/* IFLA_BRIDGE_FLAGS */
+		+ nla_total_size(sizeof(u16));	/* IFLA_BRIDGE_MODE */
+}
+
+static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
+{
+	struct net *net = dev_net(dev);
+	struct net_device *master = dev->master;
+	struct sk_buff *skb;
+	int err = -EOPNOTSUPP;
+
+	skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC);
+	if (!skb) {
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) &&
+	    master && master->netdev_ops->ndo_bridge_getlink) {
+		err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev);
+		if (err < 0)
+			goto errout;
+	}
+
+	if ((flags & BRIDGE_FLAGS_SELF) &&
+	    dev->netdev_ops->ndo_bridge_getlink) {
+		err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev);
+		if (err < 0)
+			goto errout;
+	}
+
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
+	return 0;
+errout:
+	WARN_ON(err == -EMSGSIZE);
+	kfree_skb(skb);
+	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	return err;
+}
+
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       void *arg)
+{
+	struct net *net = sock_net(skb->sk);
+	struct ifinfomsg *ifm;
+	struct net_device *dev;
+	struct nlattr *br_spec, *attr = NULL;
+	int rem, err = -EOPNOTSUPP;
+	u16 oflags, flags = 0;
+	bool have_flags = false;
+
+	if (nlmsg_len(nlh) < sizeof(*ifm))
+		return -EINVAL;
+
+	ifm = nlmsg_data(nlh);
+	if (ifm->ifi_family != AF_BRIDGE)
+		return -EPFNOSUPPORT;
+
+	dev = __dev_get_by_index(net, ifm->ifi_index);
+	if (!dev) {
+		pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+		return -ENODEV;
+	}
+
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (br_spec) {
+		nla_for_each_nested(attr, br_spec, rem) {
+			if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+				have_flags = true;
+				flags = nla_get_u16(attr);
+				break;
+			}
+		}
+	}
+
+	oflags = flags;
+
+	if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
+		if (!dev->master ||
+		    !dev->master->netdev_ops->ndo_bridge_setlink) {
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+
+		err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh);
+		if (err)
+			goto out;
+
+		flags &= ~BRIDGE_FLAGS_MASTER;
+	}
+
+	if ((flags & BRIDGE_FLAGS_SELF)) {
+		if (!dev->netdev_ops->ndo_bridge_setlink)
+			err = -EOPNOTSUPP;
+		else
+			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+
+		if (!err)
+			flags &= ~BRIDGE_FLAGS_SELF;
+	}
+
+	if (have_flags)
+		memcpy(nla_data(attr), &flags, sizeof(flags));
+	/* Generate event to notify upper layer of bridge change */
+	if (!err)
+		err = rtnl_bridge_notify(dev, oflags);
+out:
+	return err;
+}
+
 /* Protected by RTNL sempahore.  */
 static struct rtattr **rta_buf;
 static int rtattr_max;
@@ -2283,7 +2498,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	sz_idx = type>>2;
 	kind = type&3;
 
-	if (kind != 2 && !capable(CAP_NET_ADMIN))
+	if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
@@ -2434,5 +2649,8 @@ void __init rtnetlink_init(void)
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL);
+
+	rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL);
+	rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL);
 }