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

Pull networking updates from David Miller:
 "Highlights:

   1) Fix the iwlwifi regression, from Johannes Berg.

   2) Support BSS coloring and 802.11 encapsulation offloading in
      hardware, from John Crispin.

   3) Fix some potential Spectre issues in qtnfmac, from Sergey
      Matyukevich.

   4) Add TTL decrement action to openvswitch, from Matteo Croce.

   5) Allow paralleization through flow_action setup by not taking the
      RTNL mutex, from Vlad Buslov.

   6) A lot of zero-length array to flexible-array conversions, from
      Gustavo A. R. Silva.

   7) Align XDP statistics names across several drivers for consistency,
      from Lorenzo Bianconi.

   8) Add various pieces of infrastructure for offloading conntrack, and
      make use of it in mlx5 driver, from Paul Blakey.

   9) Allow using listening sockets in BPF sockmap, from Jakub Sitnicki.

  10) Lots of parallelization improvements during configuration changes
      in mlxsw driver, from Ido Schimmel.

  11) Add support to devlink for generic packet traps, which report
      packets dropped during ACL processing. And use them in mlxsw
      driver. From Jiri Pirko.

  12) Support bcmgenet on ACPI, from Jeremy Linton.

  13) Make BPF compatible with RT, from Thomas Gleixnet, Alexei
      Starovoitov, and your's truly.

  14) Support XDP meta-data in virtio_net, from Yuya Kusakabe.

  15) Fix sysfs permissions when network devices change namespaces, from
      Christian Brauner.

  16) Add a flags element to ethtool_ops so that drivers can more simply
      indicate which coalescing parameters they actually support, and
      therefore the generic layer can validate the user's ethtool
      request. Use this in all drivers, from Jakub Kicinski.

  17) Offload FIFO qdisc in mlxsw, from Petr Machata.

  18) Support UDP sockets in sockmap, from Lorenz Bauer.

  19) Fix stretch ACK bugs in several TCP congestion control modules,
      from Pengcheng Yang.

  20) Support virtual functiosn in octeontx2 driver, from Tomasz
      Duszynski.

  21) Add region operations for devlink and use it in ice driver to dump
      NVM contents, from Jacob Keller.

  22) Add support for hw offload of MACSEC, from Antoine Tenart.

  23) Add support for BPF programs that can be attached to LSM hooks,
      from KP Singh.

  24) Support for multiple paths, path managers, and counters in MPTCP.
      From Peter Krystad, Paolo Abeni, Florian Westphal, Davide Caratti,
      and others.

  25) More progress on adding the netlink interface to ethtool, from
      Michal Kubecek"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2121 commits)
  net: ipv6: rpl_iptunnel: Fix potential memory leak in rpl_do_srh_inline
  cxgb4/chcr: nic-tls stats in ethtool
  net: dsa: fix oops while probing Marvell DSA switches
  net/bpfilter: remove superfluous testing message
  net: macb: Fix handling of fixed-link node
  net: dsa: ksz: Select KSZ protocol tag
  netdevsim: dev: Fix memory leak in nsim_dev_take_snapshot_write
  net: stmmac: add EHL 2.5Gbps PCI info and PCI ID
  net: stmmac: add EHL PSE0 & PSE1 1Gbps PCI info and PCI ID
  net: stmmac: create dwmac-intel.c to contain all Intel platform
  net: dsa: bcm_sf2: Support specifying VLAN tag egress rule
  net: dsa: bcm_sf2: Add support for matching VLAN TCI
  net: dsa: bcm_sf2: Move writing of CFP_DATA(5) into slicing functions
  net: dsa: bcm_sf2: Check earlier for FLOW_EXT and FLOW_MAC_EXT
  net: dsa: bcm_sf2: Disable learning for ASP port
  net: dsa: b53: Deny enslaving port 7 for 7278 into a bridge
  net: dsa: b53: Prevent tagged VLAN on port 7 for 7278
  net: dsa: b53: Restore VLAN entries upon (re)configuration
  net: dsa: bcm_sf2: Fix overflow checks
  hv_netvsc: Remove unnecessary round_up for recv_completion_cnt
  ...

1 files changed, 394 insertions, 35 deletions

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ddc0f9236928..5390ff541658 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -842,59 +842,137 @@ dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie)
 	return NULL;
 }
 
-static int dsa_slave_add_cls_matchall(struct net_device *dev,
-				      struct tc_cls_matchall_offload *cls,
-				      bool ingress)
+static int
+dsa_slave_add_cls_matchall_mirred(struct net_device *dev,
+				  struct tc_cls_matchall_offload *cls,
+				  bool ingress)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_mall_mirror_tc_entry *mirror;
 	struct dsa_mall_tc_entry *mall_tc_entry;
-	__be16 protocol = cls->common.protocol;
 	struct dsa_switch *ds = dp->ds;
 	struct flow_action_entry *act;
 	struct dsa_port *to_dp;
-	int err = -EOPNOTSUPP;
+	int err;
+
+	act = &cls->rule->action.entries[0];
 
 	if (!ds->ops->port_mirror_add)
-		return err;
+		return -EOPNOTSUPP;
 
-	if (!flow_offload_has_one_action(&cls->rule->action))
-		return err;
+	if (!act->dev)
+		return -EINVAL;
+
+	if (!flow_action_basic_hw_stats_check(&cls->rule->action,
+					      cls->common.extack))
+		return -EOPNOTSUPP;
 
 	act = &cls->rule->action.entries[0];
 
-	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
-		struct dsa_mall_mirror_tc_entry *mirror;
+	if (!dsa_slave_dev_check(act->dev))
+		return -EOPNOTSUPP;
 
-		if (!act->dev)
-			return -EINVAL;
+	mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
+	if (!mall_tc_entry)
+		return -ENOMEM;
 
-		if (!dsa_slave_dev_check(act->dev))
-			return -EOPNOTSUPP;
+	mall_tc_entry->cookie = cls->cookie;
+	mall_tc_entry->type = DSA_PORT_MALL_MIRROR;
+	mirror = &mall_tc_entry->mirror;
 
-		mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
-		if (!mall_tc_entry)
-			return -ENOMEM;
+	to_dp = dsa_slave_to_port(act->dev);
 
-		mall_tc_entry->cookie = cls->cookie;
-		mall_tc_entry->type = DSA_PORT_MALL_MIRROR;
-		mirror = &mall_tc_entry->mirror;
+	mirror->to_local_port = to_dp->index;
+	mirror->ingress = ingress;
 
-		to_dp = dsa_slave_to_port(act->dev);
+	err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress);
+	if (err) {
+		kfree(mall_tc_entry);
+		return err;
+	}
 
-		mirror->to_local_port = to_dp->index;
-		mirror->ingress = ingress;
+	list_add_tail(&mall_tc_entry->list, &p->mall_tc_list);
 
-		err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress);
-		if (err) {
-			kfree(mall_tc_entry);
-			return err;
+	return err;
+}
+
+static int
+dsa_slave_add_cls_matchall_police(struct net_device *dev,
+				  struct tc_cls_matchall_offload *cls,
+				  bool ingress)
+{
+	struct netlink_ext_ack *extack = cls->common.extack;
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_mall_policer_tc_entry *policer;
+	struct dsa_mall_tc_entry *mall_tc_entry;
+	struct dsa_switch *ds = dp->ds;
+	struct flow_action_entry *act;
+	int err;
+
+	if (!ds->ops->port_policer_add) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Policing offload not implemented\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (!ingress) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only supported on ingress qdisc\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (!flow_action_basic_hw_stats_check(&cls->rule->action,
+					      cls->common.extack))
+		return -EOPNOTSUPP;
+
+	list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) {
+		if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only one port policer allowed\n");
+			return -EEXIST;
 		}
+	}
+
+	act = &cls->rule->action.entries[0];
 
-		list_add_tail(&mall_tc_entry->list, &p->mall_tc_list);
+	mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
+	if (!mall_tc_entry)
+		return -ENOMEM;
+
+	mall_tc_entry->cookie = cls->cookie;
+	mall_tc_entry->type = DSA_PORT_MALL_POLICER;
+	policer = &mall_tc_entry->policer;
+	policer->rate_bytes_per_sec = act->police.rate_bytes_ps;
+	policer->burst = act->police.burst;
+
+	err = ds->ops->port_policer_add(ds, dp->index, policer);
+	if (err) {
+		kfree(mall_tc_entry);
+		return err;
 	}
 
-	return 0;
+	list_add_tail(&mall_tc_entry->list, &p->mall_tc_list);
+
+	return err;
+}
+
+static int dsa_slave_add_cls_matchall(struct net_device *dev,
+				      struct tc_cls_matchall_offload *cls,
+				      bool ingress)
+{
+	int err = -EOPNOTSUPP;
+
+	if (cls->common.protocol == htons(ETH_P_ALL) &&
+	    flow_offload_has_one_action(&cls->rule->action) &&
+	    cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED)
+		err = dsa_slave_add_cls_matchall_mirred(dev, cls, ingress);
+	else if (flow_offload_has_one_action(&cls->rule->action) &&
+		 cls->rule->action.entries[0].id == FLOW_ACTION_POLICE)
+		err = dsa_slave_add_cls_matchall_police(dev, cls, ingress);
+
+	return err;
 }
 
 static void dsa_slave_del_cls_matchall(struct net_device *dev,
@@ -904,9 +982,6 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
 	struct dsa_mall_tc_entry *mall_tc_entry;
 	struct dsa_switch *ds = dp->ds;
 
-	if (!ds->ops->port_mirror_del)
-		return;
-
 	mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie);
 	if (!mall_tc_entry)
 		return;
@@ -915,7 +990,13 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
 
 	switch (mall_tc_entry->type) {
 	case DSA_PORT_MALL_MIRROR:
-		ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror);
+		if (ds->ops->port_mirror_del)
+			ds->ops->port_mirror_del(ds, dp->index,
+						 &mall_tc_entry->mirror);
+		break;
+	case DSA_PORT_MALL_POLICER:
+		if (ds->ops->port_policer_del)
+			ds->ops->port_policer_del(ds, dp->index);
 		break;
 	default:
 		WARN_ON(1);
@@ -942,6 +1023,64 @@ static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
 	}
 }
 
+static int dsa_slave_add_cls_flower(struct net_device *dev,
+				    struct flow_cls_offload *cls,
+				    bool ingress)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+
+	if (!ds->ops->cls_flower_add)
+		return -EOPNOTSUPP;
+
+	return ds->ops->cls_flower_add(ds, port, cls, ingress);
+}
+
+static int dsa_slave_del_cls_flower(struct net_device *dev,
+				    struct flow_cls_offload *cls,
+				    bool ingress)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+
+	if (!ds->ops->cls_flower_del)
+		return -EOPNOTSUPP;
+
+	return ds->ops->cls_flower_del(ds, port, cls, ingress);
+}
+
+static int dsa_slave_stats_cls_flower(struct net_device *dev,
+				      struct flow_cls_offload *cls,
+				      bool ingress)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+
+	if (!ds->ops->cls_flower_stats)
+		return -EOPNOTSUPP;
+
+	return ds->ops->cls_flower_stats(ds, port, cls, ingress);
+}
+
+static int dsa_slave_setup_tc_cls_flower(struct net_device *dev,
+					 struct flow_cls_offload *cls,
+					 bool ingress)
+{
+	switch (cls->command) {
+	case FLOW_CLS_REPLACE:
+		return dsa_slave_add_cls_flower(dev, cls, ingress);
+	case FLOW_CLS_DESTROY:
+		return dsa_slave_del_cls_flower(dev, cls, ingress);
+	case FLOW_CLS_STATS:
+		return dsa_slave_stats_cls_flower(dev, cls, ingress);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 				       void *cb_priv, bool ingress)
 {
@@ -953,6 +1092,8 @@ static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	switch (type) {
 	case TC_SETUP_CLSMATCHALL:
 		return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress);
+	case TC_SETUP_CLSFLOWER:
+		return dsa_slave_setup_tc_cls_flower(dev, type_data, ingress);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1154,6 +1295,208 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
 	return dsa_port_vid_del(dp, vid);
 }
 
+struct dsa_hw_port {
+	struct list_head list;
+	struct net_device *dev;
+	int old_mtu;
+};
+
+static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu)
+{
+	const struct dsa_hw_port *p;
+	int err;
+
+	list_for_each_entry(p, hw_port_list, list) {
+		if (p->dev->mtu == mtu)
+			continue;
+
+		err = dev_set_mtu(p->dev, mtu);
+		if (err)
+			goto rollback;
+	}
+
+	return 0;
+
+rollback:
+	list_for_each_entry_continue_reverse(p, hw_port_list, list) {
+		if (p->dev->mtu == p->old_mtu)
+			continue;
+
+		if (dev_set_mtu(p->dev, p->old_mtu))
+			netdev_err(p->dev, "Failed to restore MTU\n");
+	}
+
+	return err;
+}
+
+static void dsa_hw_port_list_free(struct list_head *hw_port_list)
+{
+	struct dsa_hw_port *p, *n;
+
+	list_for_each_entry_safe(p, n, hw_port_list, list)
+		kfree(p);
+}
+
+/* Make the hardware datapath to/from @dev limited to a common MTU */
+void dsa_bridge_mtu_normalization(struct dsa_port *dp)
+{
+	struct list_head hw_port_list;
+	struct dsa_switch_tree *dst;
+	int min_mtu = ETH_MAX_MTU;
+	struct dsa_port *other_dp;
+	int err;
+
+	if (!dp->ds->mtu_enforcement_ingress)
+		return;
+
+	if (!dp->bridge_dev)
+		return;
+
+	INIT_LIST_HEAD(&hw_port_list);
+
+	/* Populate the list of ports that are part of the same bridge
+	 * as the newly added/modified port
+	 */
+	list_for_each_entry(dst, &dsa_tree_list, list) {
+		list_for_each_entry(other_dp, &dst->ports, list) {
+			struct dsa_hw_port *hw_port;
+			struct net_device *slave;
+
+			if (other_dp->type != DSA_PORT_TYPE_USER)
+				continue;
+
+			if (other_dp->bridge_dev != dp->bridge_dev)
+				continue;
+
+			if (!other_dp->ds->mtu_enforcement_ingress)
+				continue;
+
+			slave = other_dp->slave;
+
+			if (min_mtu > slave->mtu)
+				min_mtu = slave->mtu;
+
+			hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL);
+			if (!hw_port)
+				goto out;
+
+			hw_port->dev = slave;
+			hw_port->old_mtu = slave->mtu;
+
+			list_add(&hw_port->list, &hw_port_list);
+		}
+	}
+
+	/* Attempt to configure the entire hardware bridge to the newly added
+	 * interface's MTU first, regardless of whether the intention of the
+	 * user was to raise or lower it.
+	 */
+	err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->slave->mtu);
+	if (!err)
+		goto out;
+
+	/* Clearly that didn't work out so well, so just set the minimum MTU on
+	 * all hardware bridge ports now. If this fails too, then all ports will
+	 * still have their old MTU rolled back anyway.
+	 */
+	dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu);
+
+out:
+	dsa_hw_port_list_free(&hw_port_list);
+}
+
+static int dsa_slave_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct net_device *master = dsa_slave_to_master(dev);
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->dp->ds;
+	struct dsa_port *cpu_dp;
+	int port = p->dp->index;
+	int largest_mtu = 0;
+	int new_master_mtu;
+	int old_master_mtu;
+	int mtu_limit;
+	int cpu_mtu;
+	int err, i;
+
+	if (!ds->ops->port_change_mtu)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < ds->num_ports; i++) {
+		int slave_mtu;
+
+		if (!dsa_is_user_port(ds, i))
+			continue;
+
+		/* During probe, this function will be called for each slave
+		 * device, while not all of them have been allocated. That's
+		 * ok, it doesn't change what the maximum is, so ignore it.
+		 */
+		if (!dsa_to_port(ds, i)->slave)
+			continue;
+
+		/* Pretend that we already applied the setting, which we
+		 * actually haven't (still haven't done all integrity checks)
+		 */
+		if (i == port)
+			slave_mtu = new_mtu;
+		else
+			slave_mtu = dsa_to_port(ds, i)->slave->mtu;
+
+		if (largest_mtu < slave_mtu)
+			largest_mtu = slave_mtu;
+	}
+
+	cpu_dp = dsa_to_port(ds, port)->cpu_dp;
+
+	mtu_limit = min_t(int, master->max_mtu, dev->max_mtu);
+	old_master_mtu = master->mtu;
+	new_master_mtu = largest_mtu + cpu_dp->tag_ops->overhead;
+	if (new_master_mtu > mtu_limit)
+		return -ERANGE;
+
+	/* If the master MTU isn't over limit, there's no need to check the CPU
+	 * MTU, since that surely isn't either.
+	 */
+	cpu_mtu = largest_mtu;
+
+	/* Start applying stuff */
+	if (new_master_mtu != old_master_mtu) {
+		err = dev_set_mtu(master, new_master_mtu);
+		if (err < 0)
+			goto out_master_failed;
+
+		/* We only need to propagate the MTU of the CPU port to
+		 * upstream switches.
+		 */
+		err = dsa_port_mtu_change(cpu_dp, cpu_mtu, true);
+		if (err)
+			goto out_cpu_failed;
+	}
+
+	err = dsa_port_mtu_change(dp, new_mtu, false);
+	if (err)
+		goto out_port_failed;
+
+	dev->mtu = new_mtu;
+
+	dsa_bridge_mtu_normalization(dp);
+
+	return 0;
+
+out_port_failed:
+	if (new_master_mtu != old_master_mtu)
+		dsa_port_mtu_change(cpu_dp, old_master_mtu -
+				    cpu_dp->tag_ops->overhead,
+				    true);
+out_cpu_failed:
+	if (new_master_mtu != old_master_mtu)
+		dev_set_mtu(master, old_master_mtu);
+out_master_failed:
+	return err;
+}
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_drvinfo		= dsa_slave_get_drvinfo,
 	.get_regs_len		= dsa_slave_get_regs_len,
@@ -1231,6 +1574,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= dsa_slave_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= dsa_slave_vlan_rx_kill_vid,
 	.ndo_get_devlink_port	= dsa_slave_get_devlink_port,
+	.ndo_change_mtu		= dsa_slave_change_mtu,
 };
 
 static struct device_type dsa_type = {
@@ -1241,7 +1585,8 @@ void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up)
 {
 	const struct dsa_port *dp = dsa_to_port(ds, port);
 
-	phylink_mac_change(dp->pl, up);
+	if (dp->pl)
+		phylink_mac_change(dp->pl, up);
 }
 EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change);
 
@@ -1401,7 +1746,10 @@ int dsa_slave_create(struct dsa_port *port)
 	slave_dev->priv_flags |= IFF_NO_QUEUE;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
 	slave_dev->min_mtu = 0;
-	slave_dev->max_mtu = ETH_MAX_MTU;
+	if (ds->ops->port_max_mtu)
+		slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index);
+	else
+		slave_dev->max_mtu = ETH_MAX_MTU;
 	SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
 
 	SET_NETDEV_DEV(slave_dev, port->ds->dev);
@@ -1419,6 +1767,15 @@ int dsa_slave_create(struct dsa_port *port)
 	p->xmit = cpu_dp->tag_ops->xmit;
 	port->slave = slave_dev;
 
+	rtnl_lock();
+	ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN);
+	rtnl_unlock();
+	if (ret && ret != -EOPNOTSUPP) {
+		dev_err(ds->dev, "error %d setting MTU on port %d\n",
+			ret, port->index);
+		goto out_free;
+	}
+
 	netif_carrier_off(slave_dev);
 
 	ret = dsa_slave_phy_setup(slave_dev);
@@ -1481,6 +1838,8 @@ static int dsa_slave_changeupper(struct net_device *dev,
 	if (netif_is_bridge_master(info->upper_dev)) {
 		if (info->linking) {
 			err = dsa_port_bridge_join(dp, info->upper_dev);
+			if (!err)
+				dsa_bridge_mtu_normalization(dp);
 			err = notifier_from_errno(err);
 		} else {
 			dsa_port_bridge_leave(dp, info->upper_dev);