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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 304 insertions, 23 deletions

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index f23deadf42a0..827cda560a55 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -10,10 +10,14 @@
 
 #include <linux/list.h>
 #include <linux/etherdevice.h>
+#include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
+#include <net/rtnetlink.h>
+#include <net/switchdev.h>
+#include <linux/if_bridge.h>
 #include "dsa_priv.h"
 
 /* slave mii_bus handling ***************************************************/
@@ -51,13 +55,16 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
 
 
 /* slave device handling ****************************************************/
-static int dsa_slave_init(struct net_device *dev)
+static int dsa_slave_get_iflink(const struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 
-	dev->iflink = p->parent->dst->master_netdev->ifindex;
+	return p->parent->dst->master_netdev->ifindex;
+}
 
-	return 0;
+static inline bool dsa_port_is_bridged(struct dsa_slave_priv *p)
+{
+	return !!p->bridge_dev;
 }
 
 static int dsa_slave_open(struct net_device *dev)
@@ -65,6 +72,8 @@ static int dsa_slave_open(struct net_device *dev)
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct net_device *master = p->parent->dst->master_netdev;
 	struct dsa_switch *ds = p->parent;
+	u8 stp_state = dsa_port_is_bridged(p) ?
+			BR_STATE_BLOCKING : BR_STATE_FORWARDING;
 	int err;
 
 	if (!(master->flags & IFF_UP))
@@ -93,6 +102,9 @@ static int dsa_slave_open(struct net_device *dev)
 			goto clear_promisc;
 	}
 
+	if (ds->drv->port_stp_update)
+		ds->drv->port_stp_update(ds, p->port, stp_state);
+
 	if (p->phy)
 		phy_start(p->phy);
 
@@ -133,6 +145,9 @@ static int dsa_slave_close(struct net_device *dev)
 	if (ds->drv->port_disable)
 		ds->drv->port_disable(ds, p->port, p->phy);
 
+	if (ds->drv->port_stp_update)
+		ds->drv->port_stp_update(ds, p->port, BR_STATE_DISABLED);
+
 	return 0;
 }
 
@@ -184,6 +199,105 @@ 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)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->fdb_add)
+		ret = ds->drv->fdb_add(ds, p->port, addr, vid);
+
+	return ret;
+}
+
+static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+			     struct net_device *dev,
+			     const unsigned char *addr, u16 vid)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->fdb_del)
+		ret = ds->drv->fdb_del(ds, p->port, addr, vid);
+
+	return ret;
+}
+
+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)
+{
+	struct nlmsghdr *nlh;
+	struct ndmsg *ndm;
+
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	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;
+
+	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
+		goto nla_put_failure;
+
+	if (vid && nla_put_u16(skb, NDA_VLAN, vid))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+/* 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)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	unsigned char addr[ETH_ALEN] = { 0 };
+	int ret;
+
+	if (!ds->drv->fdb_getnext)
+		return -EOPNOTSUPP;
+
+	for (; ; idx++) {
+		bool is_static;
+
+		ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static);
+		if (ret < 0)
+			break;
+
+		if (idx < cb->args[0])
+			continue;
+
+		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);
+		if (ret < 0)
+			break;
+	}
+
+	return idx;
+}
+
 static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -194,6 +308,92 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
+/* Return a bitmask of all ports being currently bridged within a given bridge
+ * device. Note that on leave, the mask will still return the bitmask of ports
+ * currently bridged, prior to port removal, and this is exactly what we want.
+ */
+static u32 dsa_slave_br_port_mask(struct dsa_switch *ds,
+				  struct net_device *bridge)
+{
+	struct dsa_slave_priv *p;
+	unsigned int port;
+	u32 mask = 0;
+
+	for (port = 0; port < DSA_MAX_PORTS; port++) {
+		if (!dsa_is_port_initialized(ds, port))
+			continue;
+
+		p = netdev_priv(ds->ports[port]);
+
+		if (ds->ports[port]->priv_flags & IFF_BRIDGE_PORT &&
+		    p->bridge_dev == bridge)
+			mask |= 1 << port;
+	}
+
+	return mask;
+}
+
+static int dsa_slave_stp_update(struct net_device *dev, u8 state)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->port_stp_update)
+		ret = ds->drv->port_stp_update(ds, p->port, state);
+
+	return ret;
+}
+
+static int dsa_slave_bridge_port_join(struct net_device *dev,
+				      struct net_device *br)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	p->bridge_dev = br;
+
+	if (ds->drv->port_join_bridge)
+		ret = ds->drv->port_join_bridge(ds, p->port,
+						dsa_slave_br_port_mask(ds, br));
+
+	return ret;
+}
+
+static int dsa_slave_bridge_port_leave(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+
+	if (ds->drv->port_leave_bridge)
+		ret = ds->drv->port_leave_bridge(ds, p->port,
+						 dsa_slave_br_port_mask(ds, p->bridge_dev));
+
+	p->bridge_dev = NULL;
+
+	/* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer,
+	 * so allow it to be in BR_STATE_FORWARDING to be kept functional
+	 */
+	dsa_slave_stp_update(dev, BR_STATE_FORWARDING);
+
+	return ret;
+}
+
+static int dsa_slave_parent_id_get(struct net_device *dev,
+				   struct netdev_phys_item_id *psid)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	psid->id_len = sizeof(ds->index);
+	memcpy(&psid->id, &ds->index, psid->id_len);
+
+	return 0;
+}
+
 static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -462,14 +662,22 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 };
 
 static const struct net_device_ops dsa_slave_netdev_ops = {
-	.ndo_init		= dsa_slave_init,
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
 	.ndo_start_xmit		= dsa_slave_xmit,
 	.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_do_ioctl		= dsa_slave_ioctl,
+	.ndo_get_iflink		= dsa_slave_get_iflink,
+};
+
+static const struct swdev_ops dsa_slave_swdev_ops = {
+	.swdev_parent_id_get = dsa_slave_parent_id_get,
+	.swdev_port_stp_update = dsa_slave_stp_update,
 };
 
 static void dsa_slave_adjust_link(struct net_device *dev)
@@ -513,6 +721,24 @@ static int dsa_slave_fixed_link_update(struct net_device *dev,
 }
 
 /* slave device setup *******************************************************/
+static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
+				 struct net_device *slave_dev,
+				 int addr)
+{
+	struct dsa_switch *ds = p->parent;
+
+	p->phy = ds->slave_mii_bus->phy_map[addr];
+	if (!p->phy)
+		return -ENODEV;
+
+	/* Use already configured phy mode */
+	p->phy_interface = p->phy->interface;
+	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+			   p->phy_interface);
+
+	return 0;
+}
+
 static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
 				struct net_device *slave_dev)
 {
@@ -546,10 +772,25 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	if (ds->drv->get_phy_flags)
 		phy_flags = ds->drv->get_phy_flags(ds, p->port);
 
-	if (phy_dn)
-		p->phy = of_phy_connect(slave_dev, phy_dn,
-					dsa_slave_adjust_link, phy_flags,
-					p->phy_interface);
+	if (phy_dn) {
+		ret = of_mdio_parse_addr(&slave_dev->dev, phy_dn);
+		/* If this PHY address is part of phys_mii_mask, which means
+		 * that we need to divert reads and writes to/from it, then we
+		 * want to bind this device using the slave MII bus created by
+		 * DSA to make that happen.
+		 */
+		if (!phy_is_fixed && ret >= 0 &&
+		    (ds->phys_mii_mask & (1 << ret))) {
+			ret = dsa_slave_phy_connect(p, slave_dev, ret);
+			if (ret)
+				return ret;
+		} else {
+			p->phy = of_phy_connect(slave_dev, phy_dn,
+						dsa_slave_adjust_link,
+						phy_flags,
+						p->phy_interface);
+		}
+	}
 
 	if (p->phy && phy_is_fixed)
 		fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update);
@@ -558,14 +799,9 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	 * MDIO bus instead
 	 */
 	if (!p->phy) {
-		p->phy = ds->slave_mii_bus->phy_map[p->port];
-		if (!p->phy)
-			return -ENODEV;
-
-		/* Use already configured phy mode */
-		p->phy_interface = p->phy->interface;
-		phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-				   p->phy_interface);
+		ret = dsa_slave_phy_connect(p, slave_dev, p->port);
+		if (ret)
+			return ret;
 	} else {
 		netdev_info(slave_dev, "attached PHY at address %d [%s]\n",
 			    p->phy->addr, p->phy->drv->name);
@@ -605,9 +841,8 @@ int dsa_slave_resume(struct net_device *slave_dev)
 	return 0;
 }
 
-struct net_device *
-dsa_slave_create(struct dsa_switch *ds, struct device *parent,
-		 int port, char *name)
+int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
+		     int port, char *name)
 {
 	struct net_device *master = ds->dst->master_netdev;
 	struct net_device *slave_dev;
@@ -617,13 +852,14 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name,
 				 NET_NAME_UNKNOWN, ether_setup);
 	if (slave_dev == NULL)
-		return slave_dev;
+		return -ENOMEM;
 
 	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->netdev_ops = &dsa_slave_netdev_ops;
+	slave_dev->swdev_ops = &dsa_slave_swdev_ops;
 
 	SET_NETDEV_DEV(slave_dev, parent);
 	slave_dev->dev.of_node = ds->pd->port_dn[port];
@@ -667,19 +903,64 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	ret = dsa_slave_phy_setup(p, slave_dev);
 	if (ret) {
 		free_netdev(slave_dev);
-		return NULL;
+		return ret;
 	}
 
+	ds->ports[port] = slave_dev;
 	ret = register_netdev(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
 			   ret, slave_dev->name);
 		phy_disconnect(p->phy);
+		ds->ports[port] = NULL;
 		free_netdev(slave_dev);
-		return NULL;
+		return ret;
 	}
 
 	netif_carrier_off(slave_dev);
 
-	return slave_dev;
+	return 0;
+}
+
+static bool dsa_slave_dev_check(struct net_device *dev)
+{
+	return dev->netdev_ops == &dsa_slave_netdev_ops;
+}
+
+static int dsa_slave_master_changed(struct net_device *dev)
+{
+	struct net_device *master = netdev_master_upper_dev_get(dev);
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	int err = 0;
+
+	if (master && master->rtnl_link_ops &&
+	    !strcmp(master->rtnl_link_ops->kind, "bridge"))
+		err = dsa_slave_bridge_port_join(dev, master);
+	else if (dsa_port_is_bridged(p))
+		err = dsa_slave_bridge_port_leave(dev);
+
+	return err;
+}
+
+int dsa_slave_netdevice_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr)
+{
+	struct net_device *dev;
+	int err = 0;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		dev = netdev_notifier_info_to_dev(ptr);
+		if (!dsa_slave_dev_check(dev))
+			goto out;
+
+		err = dsa_slave_master_changed(dev);
+		if (err)
+			netdev_warn(dev, "failed to reflect master change\n");
+
+		break;
+	}
+
+out:
+	return NOTIFY_DONE;
 }