Merge branch 'dsa-changes-for-multiple-cpu-ports-part-4'

Vladimir Oltean says:

====================
DSA changes for multiple CPU ports (part 4)

Those who have been following part 1:
https://patchwork.kernel.org/project/netdevbpf/cover/20220511095020.562461-1-vladimir.oltean@nxp.com/
part 2:
https://patchwork.kernel.org/project/netdevbpf/cover/20220521213743.2735445-1-vladimir.oltean@nxp.com/
and part 3:
https://patchwork.kernel.org/project/netdevbpf/cover/20220819174820.3585002-1-vladimir.oltean@nxp.com/
will know that I am trying to enable the second internal port pair from
the NXP LS1028A Felix switch for DSA-tagged traffic via "ocelot-8021q".

This series represents the final part of that effort. We have:

- the introduction of new UAPI in the form of IFLA_DSA_MASTER, the
  iproute2 patch for which is here:
  https://patchwork.kernel.org/project/netdevbpf/patch/20220904190025.813574-1-vladimir.oltean@nxp.com/

- preparation for LAG DSA masters in terms of suppressing some
  operations for masters in the DSA core that simply don't make sense
  when those masters are a bonding/team interface

- handling all the net device events that occur between DSA and a
  LAG DSA master, including migration to a different DSA master when the
  current master joins a LAG, or the LAG gets destroyed

- updating documentation

- adding an implementation for NXP LS1028A, where things are insanely
  complicated due to hardware limitations. We have 2 tagging protocols:

  * the native "ocelot" protocol (NPI port mode). This does not support
    CPU ports in a LAG, and supports a single DSA master. The DSA master
    can be changed between eno2 (2.5G) and eno3 (1G), but all ports must
    be down during the changing process, and user ports assigned to the
    old DSA master will refuse to come up if the user requests that
    during a "transient" state.

  * the "ocelot-8021q" software-defined protocol, where the Ethernet
    ports connected to the CPU are not actually "god mode" ports as far
    as the hardware is concerned. So here, static assignment between
    user and CPU ports is possible by editing the PGID_SRC masks for
    the port-based forwarding matrix, and "CPU ports in a LAG" simply
    means "a LAG like any other".

The series was regression-tested on LS1028A using the local_termination.sh
kselftest, in most of the possible operating modes and tagging protocols.
I have not done a detailed performance evaluation yet, but using LAG, is
possible to exceed the termination bandwidth of a single CPU port in an
iperf3 test with multiple senders and multiple receivers.

v1 at:
https://patchwork.kernel.org/project/netdevbpf/cover/20220830195932.683432-1-vladimir.oltean@nxp.com/

Previous (older) RFC at:
https://lore.kernel.org/netdev/20220523104256.3556016-1-olteanv@gmail.com/
====================

Link: https://lore.kernel.org/r/20220911010706.2137967-1-vladimir.oltean@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 66 insertions, 6 deletions

diff --git a/net/dsa/master.c b/net/dsa/master.c
index fb810edc82811..40367ab41cf8f 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -226,6 +226,9 @@ static int dsa_master_ethtool_setup(struct net_device *dev)
 	struct dsa_switch *ds = cpu_dp->ds;
 	struct ethtool_ops *ops;
 
+	if (netif_is_lag_master(dev))
+		return 0;
+
 	ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL);
 	if (!ops)
 		return -ENOMEM;
@@ -250,6 +253,9 @@ static void dsa_master_ethtool_teardown(struct net_device *dev)
 {
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 
+	if (netif_is_lag_master(dev))
+		return;
+
 	dev->ethtool_ops = cpu_dp->orig_ethtool_ops;
 	cpu_dp->orig_ethtool_ops = NULL;
 }
@@ -257,6 +263,9 @@ static void dsa_master_ethtool_teardown(struct net_device *dev)
 static void dsa_netdev_ops_set(struct net_device *dev,
 			       const struct dsa_netdevice_ops *ops)
 {
+	if (netif_is_lag_master(dev))
+		return;
+
 	dev->dsa_ptr->netdev_ops = ops;
 }
 
@@ -355,12 +364,14 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);
 
 	/* The DSA master must use SET_NETDEV_DEV for this to work. */
-	consumer_link = device_link_add(ds->dev, dev->dev.parent,
-					DL_FLAG_AUTOREMOVE_CONSUMER);
-	if (!consumer_link)
-		netdev_err(dev,
-			   "Failed to create a device link to DSA switch %s\n",
-			   dev_name(ds->dev));
+	if (!netif_is_lag_master(dev)) {
+		consumer_link = device_link_add(ds->dev, dev->dev.parent,
+						DL_FLAG_AUTOREMOVE_CONSUMER);
+		if (!consumer_link)
+			netdev_err(dev,
+				   "Failed to create a device link to DSA switch %s\n",
+				   dev_name(ds->dev));
+	}
 
 	/* The switch driver may not implement ->port_change_mtu(), case in
 	 * which dsa_slave_change_mtu() will not update the master MTU either,
@@ -417,3 +428,52 @@ void dsa_master_teardown(struct net_device *dev)
 	 */
 	wmb();
 }
+
+int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp,
+			 struct netdev_lag_upper_info *uinfo,
+			 struct netlink_ext_ack *extack)
+{
+	bool master_setup = false;
+	int err;
+
+	if (!netdev_uses_dsa(lag_dev)) {
+		err = dsa_master_setup(lag_dev, cpu_dp);
+		if (err)
+			return err;
+
+		master_setup = true;
+	}
+
+	err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack);
+	if (err) {
+		if (extack && !extack->_msg)
+			NL_SET_ERR_MSG_MOD(extack,
+					   "CPU port failed to join LAG");
+		goto out_master_teardown;
+	}
+
+	return 0;
+
+out_master_teardown:
+	if (master_setup)
+		dsa_master_teardown(lag_dev);
+	return err;
+}
+
+/* Tear down a master if there isn't any other user port on it,
+ * optionally also destroying LAG information.
+ */
+void dsa_master_lag_teardown(struct net_device *lag_dev,
+			     struct dsa_port *cpu_dp)
+{
+	struct net_device *upper;
+	struct list_head *iter;
+
+	dsa_port_lag_leave(cpu_dp, lag_dev);
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper, iter)
+		if (dsa_slave_dev_check(upper))
+			return;
+
+	dsa_master_teardown(lag_dev);
+}