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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 60 insertions, 10 deletions

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c74893c1e620..a266aa435d4d 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -407,7 +407,7 @@ static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
 	 * while the packets use the mac-addr on the physical device.
 	 */
 	return dev_hard_header(skb, phy_dev, type, daddr,
-			       saddr ? : dev->dev_addr, len);
+			       saddr ? : phy_dev->dev_addr, len);
 }
 
 static const struct header_ops ipvlan_header_ops = {
@@ -462,11 +462,29 @@ static int ipvlan_nl_changelink(struct net_device *dev,
 	struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
 	int err = 0;
 
-	if (data && data[IFLA_IPVLAN_MODE]) {
+	if (!data)
+		return 0;
+
+	if (data[IFLA_IPVLAN_MODE]) {
 		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
 		err = ipvlan_set_port_mode(port, nmode);
 	}
+
+	if (!err && data[IFLA_IPVLAN_FLAGS]) {
+		u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+		if (flags & IPVLAN_F_PRIVATE)
+			ipvlan_mark_private(port);
+		else
+			ipvlan_clear_private(port);
+
+		if (flags & IPVLAN_F_VEPA)
+			ipvlan_mark_vepa(port);
+		else
+			ipvlan_clear_vepa(port);
+	}
+
 	return err;
 }
 
@@ -474,18 +492,34 @@ static size_t ipvlan_nl_getsize(const struct net_device *dev)
 {
 	return (0
 		+ nla_total_size(2) /* IFLA_IPVLAN_MODE */
+		+ nla_total_size(2) /* IFLA_IPVLAN_FLAGS */
 		);
 }
 
 static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[],
 			      struct netlink_ext_ack *extack)
 {
-	if (data && data[IFLA_IPVLAN_MODE]) {
+	if (!data)
+		return 0;
+
+	if (data[IFLA_IPVLAN_MODE]) {
 		u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
 
 		if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX)
 			return -EINVAL;
 	}
+	if (data[IFLA_IPVLAN_FLAGS]) {
+		u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+		/* Only two bits are used at this moment. */
+		if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA))
+			return -EINVAL;
+		/* Also both flags can't be active at the same time. */
+		if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) ==
+		    (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA))
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -502,6 +536,8 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb,
 	ret = -EMSGSIZE;
 	if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode))
 		goto err;
+	if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags))
+		goto err;
 
 	return 0;
 
@@ -549,6 +585,12 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
 
+	/* Flags are per port and latest update overrides. User has
+	 * to be consistent in setting it just like the mode attribute.
+	 */
+	if (data && data[IFLA_IPVLAN_FLAGS])
+		ipvlan->port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
 	/* If the port-id base is at the MAX value, then wrap it around and
 	 * begin from 0x1 again. This may be due to a busy system where lots
 	 * of slaves are getting created and deleted.
@@ -584,7 +626,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		goto remove_ida;
 
-	err = netdev_upper_dev_link(phy_dev, dev);
+	err = netdev_upper_dev_link(phy_dev, dev, extack);
 	if (err) {
 		goto unregister_netdev;
 	}
@@ -644,6 +686,7 @@ EXPORT_SYMBOL_GPL(ipvlan_link_setup);
 static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] =
 {
 	[IFLA_IPVLAN_MODE] = { .type = NLA_U16 },
+	[IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 },
 };
 
 static struct rtnl_link_ops ipvlan_link_ops = {
@@ -730,6 +773,11 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			ipvlan_adjust_mtu(ipvlan, dev);
 		break;
 
+	case NETDEV_CHANGEADDR:
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+			ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+		break;
+
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlying device to change its type. */
 		return NOTIFY_BAD;
@@ -803,10 +851,6 @@ static int ipvlan_addr6_event(struct notifier_block *unused,
 	struct net_device *dev = (struct net_device *)if6->idev->dev;
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	/* FIXME IPv6 autoconf calls us from bh without RTNL */
-	if (in_softirq())
-		return NOTIFY_DONE;
-
 	if (!netif_is_ipvlan(dev))
 		return NOTIFY_DONE;
 
@@ -846,8 +890,11 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
-		if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true))
+		if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) {
+			NL_SET_ERR_MSG(i6vi->extack,
+				       "Address already assigned to an ipvlan device");
 			return notifier_from_errno(-EADDRINUSE);
+		}
 		break;
 	}
 
@@ -916,8 +963,11 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
-		if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false))
+		if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) {
+			NL_SET_ERR_MSG(ivi->extack,
+				       "Address already assigned to an ipvlan device");
 			return notifier_from_errno(-EADDRINUSE);
+		}
 		break;
 	}