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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 794 insertions, 157 deletions

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 055453d48668..84f77a054025 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -15,97 +15,362 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/netdevice.h>
+#include <linux/if_bridge.h>
 #include <net/ip_fib.h>
 #include <net/switchdev.h>
 
 /**
- *	netdev_switch_parent_id_get - Get ID of a switch
+ *	switchdev_port_attr_get - Get port attribute
+ *
+ *	@dev: port device
+ *	@attr: attribute to get
+ */
+int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	const struct switchdev_ops *ops = dev->switchdev_ops;
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	struct switchdev_attr first = {
+		.id = SWITCHDEV_ATTR_UNDEFINED
+	};
+	int err = -EOPNOTSUPP;
+
+	if (ops && ops->switchdev_port_attr_get)
+		return ops->switchdev_port_attr_get(dev, attr);
+
+	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
+		return err;
+
+	/* Switch device port(s) may be stacked under
+	 * bond/team/vlan dev, so recurse down to get attr on
+	 * each port.  Return -ENODATA if attr values don't
+	 * compare across ports.
+	 */
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = switchdev_port_attr_get(lower_dev, attr);
+		if (err)
+			break;
+		if (first.id == SWITCHDEV_ATTR_UNDEFINED)
+			first = *attr;
+		else if (memcmp(&first, attr, sizeof(*attr)))
+			return -ENODATA;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
+
+static int __switchdev_port_attr_set(struct net_device *dev,
+				     struct switchdev_attr *attr)
+{
+	const struct switchdev_ops *ops = dev->switchdev_ops;
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (ops && ops->switchdev_port_attr_set)
+		return ops->switchdev_port_attr_set(dev, attr);
+
+	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
+		return err;
+
+	/* Switch device port(s) may be stacked under
+	 * bond/team/vlan dev, so recurse down to set attr on
+	 * each port.
+	 */
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = __switchdev_port_attr_set(lower_dev, attr);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+struct switchdev_attr_set_work {
+	struct work_struct work;
+	struct net_device *dev;
+	struct switchdev_attr attr;
+};
+
+static void switchdev_port_attr_set_work(struct work_struct *work)
+{
+	struct switchdev_attr_set_work *asw =
+		container_of(work, struct switchdev_attr_set_work, work);
+	int err;
+
+	rtnl_lock();
+	err = switchdev_port_attr_set(asw->dev, &asw->attr);
+	if (err && err != -EOPNOTSUPP)
+		netdev_err(asw->dev, "failed (err=%d) to set attribute (id=%d)\n",
+			   err, asw->attr.id);
+	rtnl_unlock();
+
+	dev_put(asw->dev);
+	kfree(work);
+}
+
+static int switchdev_port_attr_set_defer(struct net_device *dev,
+					 struct switchdev_attr *attr)
+{
+	struct switchdev_attr_set_work *asw;
+
+	asw = kmalloc(sizeof(*asw), GFP_ATOMIC);
+	if (!asw)
+		return -ENOMEM;
+
+	INIT_WORK(&asw->work, switchdev_port_attr_set_work);
+
+	dev_hold(dev);
+	asw->dev = dev;
+	memcpy(&asw->attr, attr, sizeof(asw->attr));
+
+	schedule_work(&asw->work);
+
+	return 0;
+}
+
+/**
+ *	switchdev_port_attr_set - Set port attribute
+ *
  *	@dev: port device
- *	@psid: switch ID
+ *	@attr: attribute to set
  *
- *	Get ID of a switch this port is part of.
+ *	Use a 2-phase prepare-commit transaction model to ensure
+ *	system is not left in a partially updated state due to
+ *	failure from driver/device.
  */
-int netdev_switch_parent_id_get(struct net_device *dev,
-				struct netdev_phys_item_id *psid)
+int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
+{
+	int err;
+
+	if (!rtnl_is_locked()) {
+		/* Running prepare-commit transaction across stacked
+		 * devices requires nothing moves, so if rtnl_lock is
+		 * not held, schedule a worker thread to hold rtnl_lock
+		 * while setting attr.
+		 */
+
+		return switchdev_port_attr_set_defer(dev, attr);
+	}
+
+	/* Phase I: prepare for attr set. Driver/device should fail
+	 * here if there are going to be issues in the commit phase,
+	 * such as lack of resources or support.  The driver/device
+	 * should reserve resources needed for the commit phase here,
+	 * but should not commit the attr.
+	 */
+
+	attr->trans = SWITCHDEV_TRANS_PREPARE;
+	err = __switchdev_port_attr_set(dev, attr);
+	if (err) {
+		/* Prepare phase failed: abort the transaction.  Any
+		 * resources reserved in the prepare phase are
+		 * released.
+		 */
+
+		attr->trans = SWITCHDEV_TRANS_ABORT;
+		__switchdev_port_attr_set(dev, attr);
+
+		return err;
+	}
+
+	/* Phase II: commit attr set.  This cannot fail as a fault
+	 * of driver/device.  If it does, it's a bug in the driver/device
+	 * because the driver said everythings was OK in phase I.
+	 */
+
+	attr->trans = SWITCHDEV_TRANS_COMMIT;
+	err = __switchdev_port_attr_set(dev, attr);
+	WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
+	     dev->name, attr->id);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_attr_set);
+
+static int __switchdev_port_obj_add(struct net_device *dev,
+				    struct switchdev_obj *obj)
 {
-	const struct swdev_ops *ops = dev->swdev_ops;
+	const struct switchdev_ops *ops = dev->switchdev_ops;
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (ops && ops->switchdev_port_obj_add)
+		return ops->switchdev_port_obj_add(dev, obj);
+
+	/* Switch device port(s) may be stacked under
+	 * bond/team/vlan dev, so recurse down to add object on
+	 * each port.
+	 */
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = __switchdev_port_obj_add(lower_dev, obj);
+		if (err)
+			break;
+	}
 
-	if (!ops || !ops->swdev_parent_id_get)
-		return -EOPNOTSUPP;
-	return ops->swdev_parent_id_get(dev, psid);
+	return err;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get);
 
 /**
- *	netdev_switch_port_stp_update - Notify switch device port of STP
- *					state change
+ *	switchdev_port_obj_add - Add port object
+ *
  *	@dev: port device
- *	@state: port STP state
+ *	@obj: object to add
+ *
+ *	Use a 2-phase prepare-commit transaction model to ensure
+ *	system is not left in a partially updated state due to
+ *	failure from driver/device.
+ *
+ *	rtnl_lock must be held.
+ */
+int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj)
+{
+	int err;
+
+	ASSERT_RTNL();
+
+	/* Phase I: prepare for obj add. Driver/device should fail
+	 * here if there are going to be issues in the commit phase,
+	 * such as lack of resources or support.  The driver/device
+	 * should reserve resources needed for the commit phase here,
+	 * but should not commit the obj.
+	 */
+
+	obj->trans = SWITCHDEV_TRANS_PREPARE;
+	err = __switchdev_port_obj_add(dev, obj);
+	if (err) {
+		/* Prepare phase failed: abort the transaction.  Any
+		 * resources reserved in the prepare phase are
+		 * released.
+		 */
+
+		obj->trans = SWITCHDEV_TRANS_ABORT;
+		__switchdev_port_obj_add(dev, obj);
+
+		return err;
+	}
+
+	/* Phase II: commit obj add.  This cannot fail as a fault
+	 * of driver/device.  If it does, it's a bug in the driver/device
+	 * because the driver said everythings was OK in phase I.
+	 */
+
+	obj->trans = SWITCHDEV_TRANS_COMMIT;
+	err = __switchdev_port_obj_add(dev, obj);
+	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
+
+/**
+ *	switchdev_port_obj_del - Delete port object
  *
- *	Notify switch device port of bridge port STP state change.
+ *	@dev: port device
+ *	@obj: object to delete
  */
-int netdev_switch_port_stp_update(struct net_device *dev, u8 state)
+int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj)
 {
-	const struct swdev_ops *ops = dev->swdev_ops;
+	const struct switchdev_ops *ops = dev->switchdev_ops;
 	struct net_device *lower_dev;
 	struct list_head *iter;
 	int err = -EOPNOTSUPP;
 
-	if (ops && ops->swdev_port_stp_update)
-		return ops->swdev_port_stp_update(dev, state);
+	if (ops && ops->switchdev_port_obj_del)
+		return ops->switchdev_port_obj_del(dev, obj);
+
+	/* Switch device port(s) may be stacked under
+	 * bond/team/vlan dev, so recurse down to delete object on
+	 * each port.
+	 */
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = netdev_switch_port_stp_update(lower_dev, state);
-		if (err && err != -EOPNOTSUPP)
-			return err;
+		err = switchdev_port_obj_del(lower_dev, obj);
+		if (err)
+			break;
 	}
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update);
+EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
 
-static DEFINE_MUTEX(netdev_switch_mutex);
-static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain);
+/**
+ *	switchdev_port_obj_dump - Dump port objects
+ *
+ *	@dev: port device
+ *	@obj: object to dump
+ */
+int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj)
+{
+	const struct switchdev_ops *ops = dev->switchdev_ops;
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (ops && ops->switchdev_port_obj_dump)
+		return ops->switchdev_port_obj_dump(dev, obj);
+
+	/* Switch device port(s) may be stacked under
+	 * bond/team/vlan dev, so recurse down to dump objects on
+	 * first port at bottom of stack.
+	 */
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = switchdev_port_obj_dump(lower_dev, obj);
+		break;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_obj_dump);
+
+static DEFINE_MUTEX(switchdev_mutex);
+static RAW_NOTIFIER_HEAD(switchdev_notif_chain);
 
 /**
- *	register_netdev_switch_notifier - Register notifier
+ *	register_switchdev_notifier - Register notifier
  *	@nb: notifier_block
  *
  *	Register switch device notifier. This should be used by code
  *	which needs to monitor events happening in particular device.
  *	Return values are same as for atomic_notifier_chain_register().
  */
-int register_netdev_switch_notifier(struct notifier_block *nb)
+int register_switchdev_notifier(struct notifier_block *nb)
 {
 	int err;
 
-	mutex_lock(&netdev_switch_mutex);
-	err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb);
-	mutex_unlock(&netdev_switch_mutex);
+	mutex_lock(&switchdev_mutex);
+	err = raw_notifier_chain_register(&switchdev_notif_chain, nb);
+	mutex_unlock(&switchdev_mutex);
 	return err;
 }
-EXPORT_SYMBOL_GPL(register_netdev_switch_notifier);
+EXPORT_SYMBOL_GPL(register_switchdev_notifier);
 
 /**
- *	unregister_netdev_switch_notifier - Unregister notifier
+ *	unregister_switchdev_notifier - Unregister notifier
  *	@nb: notifier_block
  *
  *	Unregister switch device notifier.
  *	Return values are same as for atomic_notifier_chain_unregister().
  */
-int unregister_netdev_switch_notifier(struct notifier_block *nb)
+int unregister_switchdev_notifier(struct notifier_block *nb)
 {
 	int err;
 
-	mutex_lock(&netdev_switch_mutex);
-	err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb);
-	mutex_unlock(&netdev_switch_mutex);
+	mutex_lock(&switchdev_mutex);
+	err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb);
+	mutex_unlock(&switchdev_mutex);
 	return err;
 }
-EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier);
+EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);
 
 /**
- *	call_netdev_switch_notifiers - Call notifiers
+ *	call_switchdev_notifiers - Call notifiers
  *	@val: value passed unmodified to notifier function
  *	@dev: port device
  *	@info: notifier information data
@@ -114,146 +379,502 @@ EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier);
  *	when it needs to propagate hardware event.
  *	Return values are same as for atomic_notifier_call_chain().
  */
-int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
-				 struct netdev_switch_notifier_info *info)
+int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
+			     struct switchdev_notifier_info *info)
 {
 	int err;
 
 	info->dev = dev;
-	mutex_lock(&netdev_switch_mutex);
-	err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info);
-	mutex_unlock(&netdev_switch_mutex);
+	mutex_lock(&switchdev_mutex);
+	err = raw_notifier_call_chain(&switchdev_notif_chain, val, info);
+	mutex_unlock(&switchdev_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
+
+struct switchdev_vlan_dump {
+	struct switchdev_obj obj;
+	struct sk_buff *skb;
+	u32 filter_mask;
+	u16 flags;
+	u16 begin;
+	u16 end;
+};
+
+static int switchdev_port_vlan_dump_put(struct net_device *dev,
+					struct switchdev_vlan_dump *dump)
+{
+	struct bridge_vlan_info vinfo;
+
+	vinfo.flags = dump->flags;
+
+	if (dump->begin == 0 && dump->end == 0) {
+		return 0;
+	} else if (dump->begin == dump->end) {
+		vinfo.vid = dump->begin;
+		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			return -EMSGSIZE;
+	} else {
+		vinfo.vid = dump->begin;
+		vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN;
+		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			return -EMSGSIZE;
+		vinfo.vid = dump->end;
+		vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN;
+		vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_END;
+		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
+static int switchdev_port_vlan_dump_cb(struct net_device *dev,
+				       struct switchdev_obj *obj)
+{
+	struct switchdev_vlan_dump *dump =
+		container_of(obj, struct switchdev_vlan_dump, obj);
+	struct switchdev_obj_vlan *vlan = &dump->obj.u.vlan;
+	int err = 0;
+
+	if (vlan->vid_begin > vlan->vid_end)
+		return -EINVAL;
+
+	if (dump->filter_mask & RTEXT_FILTER_BRVLAN) {
+		dump->flags = vlan->flags;
+		for (dump->begin = dump->end = vlan->vid_begin;
+		     dump->begin <= vlan->vid_end;
+		     dump->begin++, dump->end++) {
+			err = switchdev_port_vlan_dump_put(dev, dump);
+			if (err)
+				return err;
+		}
+	} else if (dump->filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) {
+		if (dump->begin > vlan->vid_begin &&
+		    dump->begin >= vlan->vid_end) {
+			if ((dump->begin - 1) == vlan->vid_end &&
+			    dump->flags == vlan->flags) {
+				/* prepend */
+				dump->begin = vlan->vid_begin;
+			} else {
+				err = switchdev_port_vlan_dump_put(dev, dump);
+				dump->flags = vlan->flags;
+				dump->begin = vlan->vid_begin;
+				dump->end = vlan->vid_end;
+			}
+		} else if (dump->end <= vlan->vid_begin &&
+		           dump->end < vlan->vid_end) {
+			if ((dump->end  + 1) == vlan->vid_begin &&
+			    dump->flags == vlan->flags) {
+				/* append */
+				dump->end = vlan->vid_end;
+			} else {
+				err = switchdev_port_vlan_dump_put(dev, dump);
+				dump->flags = vlan->flags;
+				dump->begin = vlan->vid_begin;
+				dump->end = vlan->vid_end;
+			}
+		} else {
+			err = -EINVAL;
+		}
+	}
+
 	return err;
 }
-EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers);
+
+static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev,
+				    u32 filter_mask)
+{
+	struct switchdev_vlan_dump dump = {
+		.obj = {
+			.id = SWITCHDEV_OBJ_PORT_VLAN,
+			.cb = switchdev_port_vlan_dump_cb,
+		},
+		.skb = skb,
+		.filter_mask = filter_mask,
+	};
+	int err = 0;
+
+	if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
+	    (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
+		err = switchdev_port_obj_dump(dev, &dump.obj);
+		if (err)
+			goto err_out;
+		if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
+			/* last one */
+			err = switchdev_port_vlan_dump_put(dev, &dump);
+	}
+
+err_out:
+	return err == -EOPNOTSUPP ? 0 : err;
+}
 
 /**
- *	netdev_switch_port_bridge_setlink - Notify switch device port of bridge
- *	port attributes
+ *	switchdev_port_bridge_getlink - Get bridge port attributes
  *
  *	@dev: port device
- *	@nlh: netlink msg with bridge port attributes
- *	@flags: bridge setlink flags
  *
- *	Notify switch device port of bridge port attributes
+ *	Called for SELF on rtnl_bridge_getlink to get bridge port
+ *	attributes.
  */
-int netdev_switch_port_bridge_setlink(struct net_device *dev,
-				      struct nlmsghdr *nlh, u16 flags)
+int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+				  struct net_device *dev, u32 filter_mask,
+				  int nlflags)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
+	struct switchdev_attr attr = {
+		.id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS,
+	};
+	u16 mode = BRIDGE_MODE_UNDEF;
+	u32 mask = BR_LEARNING | BR_LEARNING_SYNC;
+	int err;
 
-	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
-		return 0;
+	err = switchdev_port_attr_get(dev, &attr);
+	if (err && err != -EOPNOTSUPP)
+		return err;
+
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode,
+				       attr.u.brport_flags, mask, nlflags,
+				       filter_mask, switchdev_port_vlan_fill);
+}
+EXPORT_SYMBOL_GPL(switchdev_port_bridge_getlink);
+
+static int switchdev_port_br_setflag(struct net_device *dev,
+				     struct nlattr *nlattr,
+				     unsigned long brport_flag)
+{
+	struct switchdev_attr attr = {
+		.id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS,
+	};
+	u8 flag = nla_get_u8(nlattr);
+	int err;
+
+	err = switchdev_port_attr_get(dev, &attr);
+	if (err)
+		return err;
+
+	if (flag)
+		attr.u.brport_flags |= brport_flag;
+	else
+		attr.u.brport_flags &= ~brport_flag;
+
+	return switchdev_port_attr_set(dev, &attr);
+}
+
+static const struct nla_policy
+switchdev_port_bridge_policy[IFLA_BRPORT_MAX + 1] = {
+	[IFLA_BRPORT_STATE]		= { .type = NLA_U8 },
+	[IFLA_BRPORT_COST]		= { .type = NLA_U32 },
+	[IFLA_BRPORT_PRIORITY]		= { .type = NLA_U16 },
+	[IFLA_BRPORT_MODE]		= { .type = NLA_U8 },
+	[IFLA_BRPORT_GUARD]		= { .type = NLA_U8 },
+	[IFLA_BRPORT_PROTECT]		= { .type = NLA_U8 },
+	[IFLA_BRPORT_FAST_LEAVE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_LEARNING]		= { .type = NLA_U8 },
+	[IFLA_BRPORT_LEARNING_SYNC]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_UNICAST_FLOOD]	= { .type = NLA_U8 },
+};
 
-	if (!ops->ndo_bridge_setlink)
-		return -EOPNOTSUPP;
+static int switchdev_port_br_setlink_protinfo(struct net_device *dev,
+					      struct nlattr *protinfo)
+{
+	struct nlattr *attr;
+	int rem;
+	int err;
+
+	err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX,
+				  switchdev_port_bridge_policy);
+	if (err)
+		return err;
+
+	nla_for_each_nested(attr, protinfo, rem) {
+		switch (nla_type(attr)) {
+		case IFLA_BRPORT_LEARNING:
+			err = switchdev_port_br_setflag(dev, attr,
+							BR_LEARNING);
+			break;
+		case IFLA_BRPORT_LEARNING_SYNC:
+			err = switchdev_port_br_setflag(dev, attr,
+							BR_LEARNING_SYNC);
+			break;
+		default:
+			err = -EOPNOTSUPP;
+			break;
+		}
+		if (err)
+			return err;
+	}
 
-	return ops->ndo_bridge_setlink(dev, nlh, flags);
+	return 0;
+}
+
+static int switchdev_port_br_afspec(struct net_device *dev,
+				    struct nlattr *afspec,
+				    int (*f)(struct net_device *dev,
+					     struct switchdev_obj *obj))
+{
+	struct nlattr *attr;
+	struct bridge_vlan_info *vinfo;
+	struct switchdev_obj obj = {
+		.id = SWITCHDEV_OBJ_PORT_VLAN,
+	};
+	struct switchdev_obj_vlan *vlan = &obj.u.vlan;
+	int rem;
+	int err;
+
+	nla_for_each_nested(attr, afspec, rem) {
+		if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO)
+			continue;
+		if (nla_len(attr) != sizeof(struct bridge_vlan_info))
+			return -EINVAL;
+		vinfo = nla_data(attr);
+		vlan->flags = vinfo->flags;
+		if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
+			if (vlan->vid_begin)
+				return -EINVAL;
+			vlan->vid_begin = vinfo->vid;
+		} else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) {
+			if (!vlan->vid_begin)
+				return -EINVAL;
+			vlan->vid_end = vinfo->vid;
+			if (vlan->vid_end <= vlan->vid_begin)
+				return -EINVAL;
+			err = f(dev, &obj);
+			if (err)
+				return err;
+			memset(vlan, 0, sizeof(*vlan));
+		} else {
+			if (vlan->vid_begin)
+				return -EINVAL;
+			vlan->vid_begin = vinfo->vid;
+			vlan->vid_end = vinfo->vid;
+			err = f(dev, &obj);
+			if (err)
+				return err;
+			memset(vlan, 0, sizeof(*vlan));
+		}
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_setlink);
 
 /**
- *	netdev_switch_port_bridge_dellink - Notify switch device port of bridge
- *	port attribute delete
+ *	switchdev_port_bridge_setlink - Set bridge port attributes
  *
  *	@dev: port device
- *	@nlh: netlink msg with bridge port attributes
- *	@flags: bridge setlink flags
+ *	@nlh: netlink header
+ *	@flags: netlink flags
  *
- *	Notify switch device port of bridge port attribute delete
+ *	Called for SELF on rtnl_bridge_setlink to set bridge port
+ *	attributes.
  */
-int netdev_switch_port_bridge_dellink(struct net_device *dev,
-				      struct nlmsghdr *nlh, u16 flags)
+int switchdev_port_bridge_setlink(struct net_device *dev,
+				  struct nlmsghdr *nlh, u16 flags)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
+	struct nlattr *protinfo;
+	struct nlattr *afspec;
+	int err = 0;
 
-	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
-		return 0;
+	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
+				   IFLA_PROTINFO);
+	if (protinfo) {
+		err = switchdev_port_br_setlink_protinfo(dev, protinfo);
+		if (err)
+			return err;
+	}
 
-	if (!ops->ndo_bridge_dellink)
-		return -EOPNOTSUPP;
+	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
+				 IFLA_AF_SPEC);
+	if (afspec)
+		err = switchdev_port_br_afspec(dev, afspec,
+					       switchdev_port_obj_add);
 
-	return ops->ndo_bridge_dellink(dev, nlh, flags);
+	return err;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_dellink);
+EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink);
 
 /**
- *	ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink
- *						     op for master devices
+ *	switchdev_port_bridge_dellink - Set bridge port attributes
  *
  *	@dev: port device
- *	@nlh: netlink msg with bridge port attributes
- *	@flags: bridge setlink flags
+ *	@nlh: netlink header
+ *	@flags: netlink flags
  *
- *	Notify master device slaves of bridge port attributes
+ *	Called for SELF on rtnl_bridge_dellink to set bridge port
+ *	attributes.
  */
-int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
-					       struct nlmsghdr *nlh, u16 flags)
+int switchdev_port_bridge_dellink(struct net_device *dev,
+				  struct nlmsghdr *nlh, u16 flags)
 {
-	struct net_device *lower_dev;
-	struct list_head *iter;
-	int ret = 0, err = 0;
+	struct nlattr *afspec;
 
-	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
-		return ret;
+	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
+				 IFLA_AF_SPEC);
+	if (afspec)
+		return switchdev_port_br_afspec(dev, afspec,
+						switchdev_port_obj_del);
 
-	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = netdev_switch_port_bridge_setlink(lower_dev, nlh, flags);
-		if (err && err != -EOPNOTSUPP)
-			ret = err;
-	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink);
+
+/**
+ *	switchdev_port_fdb_add - Add FDB (MAC/VLAN) entry to port
+ *
+ *	@ndmsg: netlink hdr
+ *	@nlattr: netlink attributes
+ *	@dev: port device
+ *	@addr: MAC address to add
+ *	@vid: VLAN to add
+ *
+ *	Add FDB entry to switch device.
+ */
+int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+			   struct net_device *dev, const unsigned char *addr,
+			   u16 vid, u16 nlm_flags)
+{
+	struct switchdev_obj obj = {
+		.id = SWITCHDEV_OBJ_PORT_FDB,
+		.u.fdb = {
+			.addr = addr,
+			.vid = vid,
+		},
+	};
 
-	return ret;
+	return switchdev_port_obj_add(dev, &obj);
 }
-EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_setlink);
+EXPORT_SYMBOL_GPL(switchdev_port_fdb_add);
 
 /**
- *	ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink
- *						     op for master devices
+ *	switchdev_port_fdb_del - Delete FDB (MAC/VLAN) entry from port
  *
+ *	@ndmsg: netlink hdr
+ *	@nlattr: netlink attributes
  *	@dev: port device
- *	@nlh: netlink msg with bridge port attributes
- *	@flags: bridge dellink flags
+ *	@addr: MAC address to delete
+ *	@vid: VLAN to delete
  *
- *	Notify master device slaves of bridge port attribute deletes
+ *	Delete FDB entry from switch device.
  */
-int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
-					       struct nlmsghdr *nlh, u16 flags)
+int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+			   struct net_device *dev, const unsigned char *addr,
+			   u16 vid)
 {
-	struct net_device *lower_dev;
-	struct list_head *iter;
-	int ret = 0, err = 0;
+	struct switchdev_obj obj = {
+		.id = SWITCHDEV_OBJ_PORT_FDB,
+		.u.fdb = {
+			.addr = addr,
+			.vid = vid,
+		},
+	};
 
-	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
-		return ret;
+	return switchdev_port_obj_del(dev, &obj);
+}
+EXPORT_SYMBOL_GPL(switchdev_port_fdb_del);
 
-	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = netdev_switch_port_bridge_dellink(lower_dev, nlh, flags);
-		if (err && err != -EOPNOTSUPP)
-			ret = err;
-	}
+struct switchdev_fdb_dump {
+	struct switchdev_obj obj;
+	struct sk_buff *skb;
+	struct netlink_callback *cb;
+	int idx;
+};
+
+static int switchdev_port_fdb_dump_cb(struct net_device *dev,
+				      struct switchdev_obj *obj)
+{
+	struct switchdev_fdb_dump *dump =
+		container_of(obj, struct switchdev_fdb_dump, obj);
+	u32 portid = NETLINK_CB(dump->cb->skb).portid;
+	u32 seq = dump->cb->nlh->nlmsg_seq;
+	struct nlmsghdr *nlh;
+	struct ndmsg *ndm;
+
+	if (dump->idx < dump->cb->args[0])
+		goto skip;
+
+	nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH,
+			sizeof(*ndm), NLM_F_MULTI);
+	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_SELF;
+	ndm->ndm_type    = 0;
+	ndm->ndm_ifindex = dev->ifindex;
+	ndm->ndm_state   = NUD_REACHABLE;
 
-	return ret;
+	if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr))
+		goto nla_put_failure;
+
+	if (obj->u.fdb.vid && nla_put_u16(dump->skb, NDA_VLAN, obj->u.fdb.vid))
+		goto nla_put_failure;
+
+	nlmsg_end(dump->skb, nlh);
+
+skip:
+	dump->idx++;
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(dump->skb, nlh);
+	return -EMSGSIZE;
 }
-EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_dellink);
 
-static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev)
+/**
+ *	switchdev_port_fdb_dump - Dump port FDB (MAC/VLAN) entries
+ *
+ *	@skb: netlink skb
+ *	@cb: netlink callback
+ *	@dev: port device
+ *	@filter_dev: filter device
+ *	@idx:
+ *
+ *	Delete FDB entry from switch device.
+ */
+int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			    struct net_device *dev,
+			    struct net_device *filter_dev, int idx)
 {
-	const struct swdev_ops *ops = dev->swdev_ops;
+	struct switchdev_fdb_dump dump = {
+		.obj = {
+			.id = SWITCHDEV_OBJ_PORT_FDB,
+			.cb = switchdev_port_fdb_dump_cb,
+		},
+		.skb = skb,
+		.cb = cb,
+		.idx = idx,
+	};
+	int err;
+
+	err = switchdev_port_obj_dump(dev, &dump.obj);
+	if (err)
+		return err;
+
+	return dump.idx;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump);
+
+static struct net_device *switchdev_get_lowest_dev(struct net_device *dev)
+{
+	const struct switchdev_ops *ops = dev->switchdev_ops;
 	struct net_device *lower_dev;
 	struct net_device *port_dev;
 	struct list_head *iter;
 
 	/* Recusively search down until we find a sw port dev.
-	 * (A sw port dev supports swdev_parent_id_get).
+	 * (A sw port dev supports switchdev_port_attr_get).
 	 */
 
-	if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD &&
-	    ops && ops->swdev_parent_id_get)
+	if (ops && ops->switchdev_port_attr_get)
 		return dev;
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		port_dev = netdev_switch_get_lowest_dev(lower_dev);
+		port_dev = switchdev_get_lowest_dev(lower_dev);
 		if (port_dev)
 			return port_dev;
 	}
@@ -261,10 +882,12 @@ static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev)
 	return NULL;
 }
 
-static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
+static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi)
 {
-	struct netdev_phys_item_id psid;
-	struct netdev_phys_item_id prev_psid;
+	struct switchdev_attr attr = {
+		.id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+	};
+	struct switchdev_attr prev_attr;
 	struct net_device *dev = NULL;
 	int nhsel;
 
@@ -276,28 +899,29 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
 		if (!nh->nh_dev)
 			return NULL;
 
-		dev = netdev_switch_get_lowest_dev(nh->nh_dev);
+		dev = switchdev_get_lowest_dev(nh->nh_dev);
 		if (!dev)
 			return NULL;
 
-		if (netdev_switch_parent_id_get(dev, &psid))
+		if (switchdev_port_attr_get(dev, &attr))
 			return NULL;
 
 		if (nhsel > 0) {
-			if (prev_psid.id_len != psid.id_len)
+			if (prev_attr.u.ppid.id_len != attr.u.ppid.id_len)
 				return NULL;
-			if (memcmp(prev_psid.id, psid.id, psid.id_len))
+			if (memcmp(prev_attr.u.ppid.id, attr.u.ppid.id,
+				   attr.u.ppid.id_len))
 				return NULL;
 		}
 
-		prev_psid = psid;
+		prev_attr = attr;
 	}
 
 	return dev;
 }
 
 /**
- *	netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch
+ *	switchdev_fib_ipv4_add - Add/modify switch IPv4 route entry
  *
  *	@dst: route's IPv4 destination address
  *	@dst_len: destination address length (prefix length)
@@ -307,13 +931,24 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
  *	@nlflags: netlink flags passed in (NLM_F_*)
  *	@tb_id: route table ID
  *
- *	Add IPv4 route entry to switch device.
+ *	Add/modify switch IPv4 route entry.
  */
-int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
-			       u8 tos, u8 type, u32 nlflags, u32 tb_id)
+int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
+			   u8 tos, u8 type, u32 nlflags, u32 tb_id)
 {
+	struct switchdev_obj fib_obj = {
+		.id = SWITCHDEV_OBJ_IPV4_FIB,
+		.u.ipv4_fib = {
+			.dst = dst,
+			.dst_len = dst_len,
+			.fi = fi,
+			.tos = tos,
+			.type = type,
+			.nlflags = nlflags,
+			.tb_id = tb_id,
+		},
+	};
 	struct net_device *dev;
-	const struct swdev_ops *ops;
 	int err = 0;
 
 	/* Don't offload route if using custom ip rules or if
@@ -328,25 +963,20 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 	if (fi->fib_net->ipv4.fib_offload_disabled)
 		return 0;
 
-	dev = netdev_switch_get_dev_by_nhs(fi);
+	dev = switchdev_get_dev_by_nhs(fi);
 	if (!dev)
 		return 0;
-	ops = dev->swdev_ops;
-
-	if (ops->swdev_fib_ipv4_add) {
-		err = ops->swdev_fib_ipv4_add(dev, htonl(dst), dst_len,
-					      fi, tos, type, nlflags,
-					      tb_id);
-		if (!err)
-			fi->fib_flags |= RTNH_F_OFFLOAD;
-	}
 
-	return err;
+	err = switchdev_port_obj_add(dev, &fib_obj);
+	if (!err)
+		fi->fib_flags |= RTNH_F_OFFLOAD;
+
+	return err == -EOPNOTSUPP ? 0 : err;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add);
+EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add);
 
 /**
- *	netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch
+ *	switchdev_fib_ipv4_del - Delete IPv4 route entry from switch
  *
  *	@dst: route's IPv4 destination address
  *	@dst_len: destination address length (prefix length)
@@ -357,38 +987,45 @@ EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add);
  *
  *	Delete IPv4 route entry from switch device.
  */
-int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
-			       u8 tos, u8 type, u32 tb_id)
+int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
+			   u8 tos, u8 type, u32 tb_id)
 {
+	struct switchdev_obj fib_obj = {
+		.id = SWITCHDEV_OBJ_IPV4_FIB,
+		.u.ipv4_fib = {
+			.dst = dst,
+			.dst_len = dst_len,
+			.fi = fi,
+			.tos = tos,
+			.type = type,
+			.nlflags = 0,
+			.tb_id = tb_id,
+		},
+	};
 	struct net_device *dev;
-	const struct swdev_ops *ops;
 	int err = 0;
 
 	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
 		return 0;
 
-	dev = netdev_switch_get_dev_by_nhs(fi);
+	dev = switchdev_get_dev_by_nhs(fi);
 	if (!dev)
 		return 0;
-	ops = dev->swdev_ops;
 
-	if (ops->swdev_fib_ipv4_del) {
-		err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len,
-					      fi, tos, type, tb_id);
-		if (!err)
-			fi->fib_flags &= ~RTNH_F_OFFLOAD;
-	}
+	err = switchdev_port_obj_del(dev, &fib_obj);
+	if (!err)
+		fi->fib_flags &= ~RTNH_F_OFFLOAD;
 
-	return err;
+	return err == -EOPNOTSUPP ? 0 : err;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_del);
+EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_del);
 
 /**
- *	netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation
+ *	switchdev_fib_ipv4_abort - Abort an IPv4 FIB operation
  *
  *	@fi: route FIB info structure
  */
-void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
+void switchdev_fib_ipv4_abort(struct fib_info *fi)
 {
 	/* There was a problem installing this route to the offload
 	 * device.  For now, until we come up with more refined
@@ -401,4 +1038,4 @@ void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
 	fib_flush_external(fi->fib_net);
 	fi->fib_net->ipv4.fib_offload_disabled = true;
 }
-EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_abort);
+EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort);