linux-stable/net/dsa/port.c
Russell King c138806344 net: dsa: enable flooding for bridge ports
Switches work by learning the MAC address for each attached station by
monitoring traffic from each station.  When a station sends a packet,
the switch records which port the MAC address is connected to.

With IPv4 networking, before communication commences with a neighbour,
an ARP packet is broadcasted to all stations asking for the MAC address
corresponding with the IPv4.  The desired station responds with an ARP
reply, and the ARP reply causes the switch to learn which port the
station is connected to.

With IPv6 networking, the situation is rather different.  Rather than
broadcasting ARP packets, a "neighbour solicitation" is multicasted
rather than broadcasted.  This multicast needs to reach the intended
station in order for the neighbour to be discovered.

Once a neighbour has been discovered, and entered into the sending
stations neighbour cache, communication can restart at a point later
without sending a new neighbour solicitation, even if the entry in
the neighbour cache is marked as stale.  This can be after the MAC
address has expired from the forwarding cache of the DSA switch -
when that occurs, there is a long pause in communication.

Our DSA implementation for mv88e6xxx switches disables flooding of
multicast and unicast frames for bridged ports.  As per the above
description, this is fine for IPv4 networking, since the broadcasted
ARP queries will be sent to and received by all stations on the same
network.  However, this breaks IPv6 very badly - blocking neighbour
solicitations and later causing connections to stall.

The defaults that the Linux bridge code expect from bridges are for
unknown unicast and unknown multicast frames to be flooded to all ports
on the bridge, which is at odds to the defaults adopted by our DSA
implementation for mv88e6xxx switches.

This commit enables by default flooding of both unknown unicast and
unknown multicast frames whenever a port is added to a bridge, and
disables the flooding when a port leaves the bridge.  This means that
mv88e6xxx DSA switches now behave as per the bridge(8) man page, and
IPv6 works flawlessly through such a switch.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-21 14:53:07 -08:00

472 lines
10 KiB
C

/*
* Handling of a single switch port
*
* Copyright (c) 2017 Savoir-faire Linux Inc.
* Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <linux/if_bridge.h>
#include <linux/notifier.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include "dsa_priv.h"
static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v)
{
struct raw_notifier_head *nh = &dp->ds->dst->nh;
int err;
err = raw_notifier_call_chain(nh, e, v);
return notifier_to_errno(err);
}
int dsa_port_set_state(struct dsa_port *dp, u8 state,
struct switchdev_trans *trans)
{
struct dsa_switch *ds = dp->ds;
int port = dp->index;
if (switchdev_trans_ph_prepare(trans))
return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP;
if (ds->ops->port_stp_state_set)
ds->ops->port_stp_state_set(ds, port, state);
if (ds->ops->port_fast_age) {
/* Fast age FDB entries or flush appropriate forwarding database
* for the given port, if we are moving it from Learning or
* Forwarding state, to Disabled or Blocking or Listening state.
*/
if ((dp->stp_state == BR_STATE_LEARNING ||
dp->stp_state == BR_STATE_FORWARDING) &&
(state == BR_STATE_DISABLED ||
state == BR_STATE_BLOCKING ||
state == BR_STATE_LISTENING))
ds->ops->port_fast_age(ds, port);
}
dp->stp_state = state;
return 0;
}
static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
{
int err;
err = dsa_port_set_state(dp, state, NULL);
if (err)
pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
}
int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
{
u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING;
struct dsa_switch *ds = dp->ds;
int port = dp->index;
int err;
if (ds->ops->port_enable) {
err = ds->ops->port_enable(ds, port, phy);
if (err)
return err;
}
dsa_port_set_state_now(dp, stp_state);
return 0;
}
void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy)
{
struct dsa_switch *ds = dp->ds;
int port = dp->index;
dsa_port_set_state_now(dp, BR_STATE_DISABLED);
if (ds->ops->port_disable)
ds->ops->port_disable(ds, port, phy);
}
int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br)
{
struct dsa_notifier_bridge_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.br = br,
};
int err;
/* Set the flooding mode before joining the port in the switch */
err = dsa_port_bridge_flags(dp, BR_FLOOD | BR_MCAST_FLOOD, NULL);
if (err)
return err;
/* Here the interface is already bridged. Reflect the current
* configuration so that drivers can program their chips accordingly.
*/
dp->bridge_dev = br;
err = dsa_port_notify(dp, DSA_NOTIFIER_BRIDGE_JOIN, &info);
/* The bridging is rolled back on error */
if (err) {
dsa_port_bridge_flags(dp, 0, NULL);
dp->bridge_dev = NULL;
}
return err;
}
void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br)
{
struct dsa_notifier_bridge_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.br = br,
};
int err;
/* Here the port is already unbridged. Reflect the current configuration
* so that drivers can program their chips accordingly.
*/
dp->bridge_dev = NULL;
err = dsa_port_notify(dp, DSA_NOTIFIER_BRIDGE_LEAVE, &info);
if (err)
pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n");
/* Port is leaving the bridge, disable flooding */
dsa_port_bridge_flags(dp, 0, NULL);
/* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer,
* so allow it to be in BR_STATE_FORWARDING to be kept functional
*/
dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
}
int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
struct switchdev_trans *trans)
{
struct dsa_switch *ds = dp->ds;
/* bridge skips -EOPNOTSUPP, so skip the prepare phase */
if (switchdev_trans_ph_prepare(trans))
return 0;
if (ds->ops->port_vlan_filtering)
return ds->ops->port_vlan_filtering(ds, dp->index,
vlan_filtering);
return 0;
}
int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock,
struct switchdev_trans *trans)
{
unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock);
unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies);
struct dsa_notifier_ageing_time_info info = {
.ageing_time = ageing_time,
.trans = trans,
};
if (switchdev_trans_ph_prepare(trans))
return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info);
dp->ageing_time = ageing_time;
return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info);
}
int dsa_port_bridge_flags(const struct dsa_port *dp, unsigned long flags,
struct switchdev_trans *trans)
{
struct dsa_switch *ds = dp->ds;
int port = dp->index;
int err = 0;
if (switchdev_trans_ph_prepare(trans))
return 0;
if (ds->ops->port_egress_floods)
err = ds->ops->port_egress_floods(ds, port, flags & BR_FLOOD,
flags & BR_MCAST_FLOOD);
return err;
}
int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr,
u16 vid)
{
struct dsa_notifier_fdb_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.addr = addr,
.vid = vid,
};
return dsa_port_notify(dp, DSA_NOTIFIER_FDB_ADD, &info);
}
int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
u16 vid)
{
struct dsa_notifier_fdb_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.addr = addr,
.vid = vid,
};
return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info);
}
int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data)
{
struct dsa_switch *ds = dp->ds;
int port = dp->index;
if (!ds->ops->port_fdb_dump)
return -EOPNOTSUPP;
return ds->ops->port_fdb_dump(ds, port, cb, data);
}
int dsa_port_mdb_add(const struct dsa_port *dp,
const struct switchdev_obj_port_mdb *mdb,
struct switchdev_trans *trans)
{
struct dsa_notifier_mdb_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.trans = trans,
.mdb = mdb,
};
return dsa_port_notify(dp, DSA_NOTIFIER_MDB_ADD, &info);
}
int dsa_port_mdb_del(const struct dsa_port *dp,
const struct switchdev_obj_port_mdb *mdb)
{
struct dsa_notifier_mdb_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.mdb = mdb,
};
return dsa_port_notify(dp, DSA_NOTIFIER_MDB_DEL, &info);
}
int dsa_port_vlan_add(struct dsa_port *dp,
const struct switchdev_obj_port_vlan *vlan,
struct switchdev_trans *trans)
{
struct dsa_notifier_vlan_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.trans = trans,
.vlan = vlan,
};
if (br_vlan_enabled(dp->bridge_dev))
return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info);
return 0;
}
int dsa_port_vlan_del(struct dsa_port *dp,
const struct switchdev_obj_port_vlan *vlan)
{
struct dsa_notifier_vlan_info info = {
.sw_index = dp->ds->index,
.port = dp->index,
.vlan = vlan,
};
if (netif_is_bridge_master(vlan->obj.orig_dev))
return -EOPNOTSUPP;
if (br_vlan_enabled(dp->bridge_dev))
return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
return 0;
}
static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp)
{
struct device_node *phy_dn;
struct phy_device *phydev;
phy_dn = of_parse_phandle(dp->dn, "phy-handle", 0);
if (!phy_dn)
return NULL;
phydev = of_phy_find_device(phy_dn);
if (!phydev) {
of_node_put(phy_dn);
return ERR_PTR(-EPROBE_DEFER);
}
return phydev;
}
static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable)
{
struct dsa_switch *ds = dp->ds;
struct phy_device *phydev;
int port = dp->index;
int err = 0;
phydev = dsa_port_get_phy_device(dp);
if (!phydev)
return 0;
if (IS_ERR(phydev))
return PTR_ERR(phydev);
if (enable) {
err = genphy_config_init(phydev);
if (err < 0)
goto err_put_dev;
err = genphy_resume(phydev);
if (err < 0)
goto err_put_dev;
err = genphy_read_status(phydev);
if (err < 0)
goto err_put_dev;
} else {
err = genphy_suspend(phydev);
if (err < 0)
goto err_put_dev;
}
if (ds->ops->adjust_link)
ds->ops->adjust_link(ds, port, phydev);
dev_dbg(ds->dev, "enabled port's phy: %s", phydev_name(phydev));
err_put_dev:
put_device(&phydev->mdio.dev);
return err;
}
static int dsa_port_fixed_link_register_of(struct dsa_port *dp)
{
struct device_node *dn = dp->dn;
struct dsa_switch *ds = dp->ds;
struct phy_device *phydev;
int port = dp->index;
int mode;
int err;
err = of_phy_register_fixed_link(dn);
if (err) {
dev_err(ds->dev,
"failed to register the fixed PHY of port %d\n",
port);
return err;
}
phydev = of_phy_find_device(dn);
mode = of_get_phy_mode(dn);
if (mode < 0)
mode = PHY_INTERFACE_MODE_NA;
phydev->interface = mode;
genphy_config_init(phydev);
genphy_read_status(phydev);
if (ds->ops->adjust_link)
ds->ops->adjust_link(ds, port, phydev);
put_device(&phydev->mdio.dev);
return 0;
}
int dsa_port_link_register_of(struct dsa_port *dp)
{
if (of_phy_is_fixed_link(dp->dn))
return dsa_port_fixed_link_register_of(dp);
else
return dsa_port_setup_phy_of(dp, true);
}
void dsa_port_link_unregister_of(struct dsa_port *dp)
{
if (of_phy_is_fixed_link(dp->dn))
of_phy_deregister_fixed_link(dp->dn);
else
dsa_port_setup_phy_of(dp, false);
}
int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data)
{
struct phy_device *phydev;
int ret = -EOPNOTSUPP;
if (of_phy_is_fixed_link(dp->dn))
return ret;
phydev = dsa_port_get_phy_device(dp);
if (IS_ERR_OR_NULL(phydev))
return ret;
ret = phy_ethtool_get_strings(phydev, data);
put_device(&phydev->mdio.dev);
return ret;
}
EXPORT_SYMBOL_GPL(dsa_port_get_phy_strings);
int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data)
{
struct phy_device *phydev;
int ret = -EOPNOTSUPP;
if (of_phy_is_fixed_link(dp->dn))
return ret;
phydev = dsa_port_get_phy_device(dp);
if (IS_ERR_OR_NULL(phydev))
return ret;
ret = phy_ethtool_get_stats(phydev, NULL, data);
put_device(&phydev->mdio.dev);
return ret;
}
EXPORT_SYMBOL_GPL(dsa_port_get_ethtool_phy_stats);
int dsa_port_get_phy_sset_count(struct dsa_port *dp)
{
struct phy_device *phydev;
int ret = -EOPNOTSUPP;
if (of_phy_is_fixed_link(dp->dn))
return ret;
phydev = dsa_port_get_phy_device(dp);
if (IS_ERR_OR_NULL(phydev))
return ret;
ret = phy_ethtool_get_sset_count(phydev);
put_device(&phydev->mdio.dev);
return ret;
}
EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count);