net: dsa: configure the MTU for switch ports

It is useful be able to configure port policers on a switch to accept
frames of various sizes:

- Increase the MTU for better throughput from the default of 1500 if it
  is known that there is no 10/100 Mbps device in the network.
- Decrease the MTU to limit the latency of high-priority frames under
  congestion, or work around various network segments that add extra
  headers to packets which can't be fragmented.

For DSA slave ports, this is mostly a pass-through callback, called
through the regular ndo ops and at probe time (to ensure consistency
across all supported switches).

The CPU port is called with an MTU equal to the largest configured MTU
of the slave ports. The assumption is that the user might want to
sustain a bidirectional conversation with a partner over any switch
port.

The DSA master is configured the same as the CPU port, plus the tagger
overhead. Since the MTU is by definition L2 payload (sans Ethernet
header), it is up to each individual driver to figure out if it needs to
do anything special for its frame tags on the CPU port (it shouldn't
except in special cases). So the MTU does not contain the tagger
overhead on the CPU port.
However the MTU of the DSA master, minus the tagger overhead, is used as
a proxy for the MTU of the CPU port, which does not have a net device.
This is to avoid uselessly calling the .change_mtu function on the CPU
port when nothing should change.

So it is safe to assume that the DSA master and the CPU port MTUs are
apart by exactly the tagger's overhead in bytes.

Some changes were made around dsa_master_set_mtu(), function which was
now removed, for 2 reasons:
  - dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to
    do the same thing in DSA
  - __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method
That is to say, there's no need for this function in DSA, we can safely
call dev_set_mtu() directly, take the rtnl lock when necessary, and just
propagate whatever errors get reported (since the user probably wants to
be informed).

Some inspiration (mainly in the MTU DSA notifier) was taken from a
vaguely similar patch from Murali and Florian, who are credited as
co-developers down below.

Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Co-developed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 104 insertions, 1 deletions

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 5f782fa3029f..1a99bbab0722 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1218,6 +1218,96 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
 	return dsa_port_vid_del(dp, vid);
 }
 
+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;
+
+	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,
@@ -1295,6 +1385,7 @@ 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 = {
@@ -1465,7 +1556,10 @@ 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);
@@ -1483,6 +1577,15 @@ 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);