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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 326 insertions, 68 deletions

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 35c47dd..cce9738 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -18,6 +18,7 @@
 #include <net/rtnetlink.h>
 #include <net/switchdev.h>
 #include <linux/if_bridge.h>
+#include <linux/netpoll.h>
 #include "dsa_priv.h"
 
 /* slave mii_bus handling ***************************************************/
@@ -199,103 +200,212 @@ out:
 	return 0;
 }
 
-static int dsa_slave_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
-			     struct net_device *dev,
-			     const unsigned char *addr, u16 vid, u16 nlm_flags)
+static int dsa_bridge_check_vlan_range(struct dsa_switch *ds,
+				       const struct net_device *bridge,
+				       u16 vid_begin, u16 vid_end)
 {
+	struct dsa_slave_priv *p;
+	struct net_device *dev, *vlan_br;
+	DECLARE_BITMAP(members, DSA_MAX_PORTS);
+	DECLARE_BITMAP(untagged, DSA_MAX_PORTS);
+	u16 vid;
+	int member, err;
+
+	if (!ds->drv->vlan_getnext || !vid_begin)
+		return -EOPNOTSUPP;
+
+	vid = vid_begin - 1;
+
+	do {
+		err = ds->drv->vlan_getnext(ds, &vid, members, untagged);
+		if (err)
+			break;
+
+		if (vid > vid_end)
+			break;
+
+		member = find_first_bit(members, DSA_MAX_PORTS);
+		if (member == DSA_MAX_PORTS)
+			continue;
+
+		dev = ds->ports[member];
+		p = netdev_priv(dev);
+		vlan_br = p->bridge_dev;
+		if (vlan_br == bridge)
+			continue;
+
+		netdev_dbg(vlan_br, "hardware VLAN %d already in use\n", vid);
+		return -EOPNOTSUPP;
+	} while (vid < vid_end);
+
+	return err == -ENOENT ? 0 : err;
+}
+
+static int dsa_slave_port_vlan_add(struct net_device *dev,
+				   struct switchdev_obj *obj)
+{
+	struct switchdev_obj_vlan *vlan = &obj->u.vlan;
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_switch *ds = p->parent;
-	int ret = -EOPNOTSUPP;
+	u16 vid;
+	int err;
 
-	if (ds->drv->fdb_add)
-		ret = ds->drv->fdb_add(ds, p->port, addr, vid);
+	switch (obj->trans) {
+	case SWITCHDEV_TRANS_PREPARE:
+		if (!ds->drv->port_vlan_add || !ds->drv->port_pvid_set)
+			return -EOPNOTSUPP;
 
-	return ret;
+		/* If the requested port doesn't belong to the same bridge as
+		 * the VLAN members, fallback to software VLAN (hopefully).
+		 */
+		err = dsa_bridge_check_vlan_range(ds, p->bridge_dev,
+						  vlan->vid_begin,
+						  vlan->vid_end);
+		if (err)
+			return err;
+		break;
+	case SWITCHDEV_TRANS_COMMIT:
+		for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+			err = ds->drv->port_vlan_add(ds, p->port, vid,
+						     vlan->flags &
+						     BRIDGE_VLAN_INFO_UNTAGGED);
+			if (!err && vlan->flags & BRIDGE_VLAN_INFO_PVID)
+				err = ds->drv->port_pvid_set(ds, p->port, vid);
+			if (err)
+				return err;
+		}
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
 }
 
-static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
-			     struct net_device *dev,
-			     const unsigned char *addr, u16 vid)
+static int dsa_slave_port_vlan_del(struct net_device *dev,
+				   struct switchdev_obj *obj)
 {
+	struct switchdev_obj_vlan *vlan = &obj->u.vlan;
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_switch *ds = p->parent;
-	int ret = -EOPNOTSUPP;
+	u16 vid;
+	int err;
 
-	if (ds->drv->fdb_del)
-		ret = ds->drv->fdb_del(ds, p->port, addr, vid);
+	if (!ds->drv->port_vlan_del)
+		return -EOPNOTSUPP;
 
-	return ret;
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		err = ds->drv->port_vlan_del(ds, p->port, vid);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
-static int dsa_slave_fill_info(struct net_device *dev, struct sk_buff *skb,
-			       const unsigned char *addr, u16 vid,
-			       bool is_static,
-			       u32 portid, u32 seq, int type,
-			       unsigned int flags)
+static int dsa_slave_port_vlan_dump(struct net_device *dev,
+				    struct switchdev_obj *obj)
 {
-	struct nlmsghdr *nlh;
-	struct ndmsg *ndm;
+	struct switchdev_obj_vlan *vlan = &obj->u.vlan;
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	DECLARE_BITMAP(members, DSA_MAX_PORTS);
+	DECLARE_BITMAP(untagged, DSA_MAX_PORTS);
+	u16 pvid, vid = 0;
+	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
-	if (!nlh)
-		return -EMSGSIZE;
+	if (!ds->drv->vlan_getnext || !ds->drv->port_pvid_get)
+		return -EOPNOTSUPP;
 
-	ndm = nlmsg_data(nlh);
-	ndm->ndm_family	 = AF_BRIDGE;
-	ndm->ndm_pad1    = 0;
-	ndm->ndm_pad2    = 0;
-	ndm->ndm_flags	 = NTF_EXT_LEARNED;
-	ndm->ndm_type	 = 0;
-	ndm->ndm_ifindex = dev->ifindex;
-	ndm->ndm_state   = is_static ? NUD_NOARP : NUD_REACHABLE;
+	err = ds->drv->port_pvid_get(ds, p->port, &pvid);
+	if (err)
+		return err;
 
-	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
-		goto nla_put_failure;
+	for (;;) {
+		err = ds->drv->vlan_getnext(ds, &vid, members, untagged);
+		if (err)
+			break;
 
-	if (vid && nla_put_u16(skb, NDA_VLAN, vid))
-		goto nla_put_failure;
+		if (!test_bit(p->port, members))
+			continue;
 
-	nlmsg_end(skb, nlh);
-	return 0;
+		memset(vlan, 0, sizeof(*vlan));
+		vlan->vid_begin = vlan->vid_end = vid;
+
+		if (vid == pvid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		if (test_bit(p->port, untagged))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+
+		err = obj->cb(dev, obj);
+		if (err)
+			break;
+	}
+
+	return err == -ENOENT ? 0 : err;
+}
 
-nla_put_failure:
-	nlmsg_cancel(skb, nlh);
-	return -EMSGSIZE;
+static int dsa_slave_port_fdb_add(struct net_device *dev,
+				  struct switchdev_obj *obj)
+{
+	struct switchdev_obj_fdb *fdb = &obj->u.fdb;
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (obj->trans == SWITCHDEV_TRANS_PREPARE)
+		ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP;
+	else if (obj->trans == SWITCHDEV_TRANS_COMMIT)
+		ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid);
+
+	return ret;
 }
 
-/* Dump information about entries, in response to GETNEIGH */
-static int dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
-			      struct net_device *dev,
-			      struct net_device *filter_dev, int idx)
+static int dsa_slave_port_fdb_del(struct net_device *dev,
+				  struct switchdev_obj *obj)
+{
+	struct switchdev_obj_fdb *fdb = &obj->u.fdb;
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->port_fdb_del)
+		ret = ds->drv->port_fdb_del(ds, p->port, fdb->addr, fdb->vid);
+
+	return ret;
+}
+
+static int dsa_slave_port_fdb_dump(struct net_device *dev,
+				   struct switchdev_obj *obj)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_switch *ds = p->parent;
 	unsigned char addr[ETH_ALEN] = { 0 };
+	u16 vid = 0;
 	int ret;
 
-	if (!ds->drv->fdb_getnext)
+	if (!ds->drv->port_fdb_getnext)
 		return -EOPNOTSUPP;
 
-	for (; ; idx++) {
+	for (;;) {
 		bool is_static;
 
-		ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static);
+		ret = ds->drv->port_fdb_getnext(ds, p->port, addr, &vid,
+						&is_static);
 		if (ret < 0)
 			break;
 
-		if (idx < cb->args[0])
-			continue;
+		obj->u.fdb.addr = addr;
+		obj->u.fdb.vid = vid;
+		obj->u.fdb.ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE;
 
-		ret = dsa_slave_fill_info(dev, skb, addr, 0,
-					  is_static,
-					  NETLINK_CB(cb->skb).portid,
-					  cb->nlh->nlmsg_seq,
-					  RTM_NEWNEIGH, NLM_F_MULTI);
+		ret = obj->cb(dev, obj);
 		if (ret < 0)
 			break;
 	}
 
-	return idx;
+	return ret == -ENOENT ? 0 : ret;
 }
 
 static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
@@ -363,6 +473,71 @@ static int dsa_slave_port_attr_set(struct net_device *dev,
 	return ret;
 }
 
+static int dsa_slave_port_obj_add(struct net_device *dev,
+				  struct switchdev_obj *obj)
+{
+	int err;
+
+	/* For the prepare phase, ensure the full set of changes is feasable in
+	 * one go in order to signal a failure properly. If an operation is not
+	 * supported, return -EOPNOTSUPP.
+	 */
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_PORT_FDB:
+		err = dsa_slave_port_fdb_add(dev, obj);
+		break;
+	case SWITCHDEV_OBJ_PORT_VLAN:
+		err = dsa_slave_port_vlan_add(dev, obj);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int dsa_slave_port_obj_del(struct net_device *dev,
+				  struct switchdev_obj *obj)
+{
+	int err;
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_PORT_FDB:
+		err = dsa_slave_port_fdb_del(dev, obj);
+		break;
+	case SWITCHDEV_OBJ_PORT_VLAN:
+		err = dsa_slave_port_vlan_del(dev, obj);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int dsa_slave_port_obj_dump(struct net_device *dev,
+				   struct switchdev_obj *obj)
+{
+	int err;
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_PORT_FDB:
+		err = dsa_slave_port_fdb_dump(dev, obj);
+		break;
+	case SWITCHDEV_OBJ_PORT_VLAN:
+		err = dsa_slave_port_vlan_dump(dev, obj);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
 static int dsa_slave_bridge_port_join(struct net_device *dev,
 				      struct net_device *br)
 {
@@ -418,24 +593,53 @@ static int dsa_slave_port_attr_get(struct net_device *dev,
 	return 0;
 }
 
-static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
+static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p,
+					       struct sk_buff *skb)
 {
-	struct dsa_slave_priv *p = netdev_priv(dev);
-
-	return p->xmit(skb, dev);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	if (p->netpoll)
+		netpoll_send_skb(p->netpoll, skb);
+#else
+	BUG();
+#endif
+	return NETDEV_TX_OK;
 }
 
-static netdev_tx_t dsa_slave_notag_xmit(struct sk_buff *skb,
-					struct net_device *dev)
+static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct sk_buff *nskb;
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	/* Transmit function may have to reallocate the original SKB */
+	nskb = p->xmit(skb, dev);
+	if (!nskb)
+		return NETDEV_TX_OK;
 
-	skb->dev = p->parent->dst->master_netdev;
-	dev_queue_xmit(skb);
+	/* SKB for netpoll still need to be mangled with the protocol-specific
+	 * tag to be successfully transmitted
+	 */
+	if (unlikely(netpoll_tx_running(dev)))
+		return dsa_netpoll_send_skb(p, nskb);
+
+	/* Queue the SKB for transmission on the parent interface, but
+	 * do not modify its EtherType
+	 */
+	nskb->dev = p->parent->dst->master_netdev;
+	dev_queue_xmit(nskb);
 
 	return NETDEV_TX_OK;
 }
 
+static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
+					    struct net_device *dev)
+{
+	/* Just return the original SKB */
+	return skb;
+}
+
 
 /* ethtool operations *******************************************************/
 static int
@@ -665,6 +869,49 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	return ret;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static int dsa_slave_netpoll_setup(struct net_device *dev,
+				   struct netpoll_info *ni)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	struct net_device *master = ds->dst->master_netdev;
+	struct netpoll *netpoll;
+	int err = 0;
+
+	netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+	if (!netpoll)
+		return -ENOMEM;
+
+	err = __netpoll_setup(netpoll, master);
+	if (err) {
+		kfree(netpoll);
+		goto out;
+	}
+
+	p->netpoll = netpoll;
+out:
+	return err;
+}
+
+static void dsa_slave_netpoll_cleanup(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct netpoll *netpoll = p->netpoll;
+
+	if (!netpoll)
+		return;
+
+	p->netpoll = NULL;
+
+	__netpoll_free_async(netpoll);
+}
+
+static void dsa_slave_poll_controller(struct net_device *dev)
+{
+}
+#endif
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
@@ -692,16 +939,27 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_change_rx_flags	= dsa_slave_change_rx_flags,
 	.ndo_set_rx_mode	= dsa_slave_set_rx_mode,
 	.ndo_set_mac_address	= dsa_slave_set_mac_address,
-	.ndo_fdb_add		= dsa_slave_fdb_add,
-	.ndo_fdb_del		= dsa_slave_fdb_del,
-	.ndo_fdb_dump		= dsa_slave_fdb_dump,
+	.ndo_fdb_add		= switchdev_port_fdb_add,
+	.ndo_fdb_del		= switchdev_port_fdb_del,
+	.ndo_fdb_dump		= switchdev_port_fdb_dump,
 	.ndo_do_ioctl		= dsa_slave_ioctl,
 	.ndo_get_iflink		= dsa_slave_get_iflink,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_netpoll_setup	= dsa_slave_netpoll_setup,
+	.ndo_netpoll_cleanup	= dsa_slave_netpoll_cleanup,
+	.ndo_poll_controller	= dsa_slave_poll_controller,
+#endif
+	.ndo_bridge_getlink	= switchdev_port_bridge_getlink,
+	.ndo_bridge_setlink	= switchdev_port_bridge_setlink,
+	.ndo_bridge_dellink	= switchdev_port_bridge_dellink,
 };
 
 static const struct switchdev_ops dsa_slave_switchdev_ops = {
 	.switchdev_port_attr_get	= dsa_slave_port_attr_get,
 	.switchdev_port_attr_set	= dsa_slave_port_attr_set,
+	.switchdev_port_obj_add		= dsa_slave_port_obj_add,
+	.switchdev_port_obj_del		= dsa_slave_port_obj_del,
+	.switchdev_port_obj_dump	= dsa_slave_port_obj_dump,
 };
 
 static void dsa_slave_adjust_link(struct net_device *dev)
@@ -889,7 +1147,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	slave_dev->features = master->vlan_features;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	eth_hw_addr_inherit(slave_dev, master);
-	slave_dev->tx_queue_len = 0;
+	slave_dev->priv_flags |= IFF_NO_QUEUE;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
 	slave_dev->switchdev_ops = &dsa_slave_switchdev_ops;