summaryrefslogtreecommitdiff
path: root/drivers/net/bonding
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/bonding')
-rw-r--r--drivers/net/bonding/bond_3ad.c165
-rw-r--r--drivers/net/bonding/bond_debugfs.c9
-rw-r--r--drivers/net/bonding/bond_main.c426
-rw-r--r--drivers/net/bonding/bond_netlink.c19
-rw-r--r--drivers/net/bonding/bond_options.c159
-rw-r--r--drivers/net/bonding/bond_procfs.c2
-rw-r--r--drivers/net/bonding/bond_sysfs.c25
-rw-r--r--drivers/net/bonding/bond_sysfs_slave.c2
8 files changed, 631 insertions, 176 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index c99ffe6c683a..c6807e473ab7 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -82,10 +82,6 @@ enum ad_link_speed_type {
#define MAC_ADDRESS_EQUAL(A, B) \
ether_addr_equal_64bits((const u8 *)A, (const u8 *)B)
-static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
- 0, 0, 0, 0, 0, 0
-};
-
static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL;
static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
@@ -106,6 +102,9 @@ static void ad_agg_selection_logic(struct aggregator *aggregator,
static void ad_clear_agg(struct aggregator *aggregator);
static void ad_initialize_agg(struct aggregator *aggregator);
static void ad_initialize_port(struct port *port, int lacp_fast);
+static void ad_enable_collecting(struct port *port);
+static void ad_disable_distributing(struct port *port,
+ bool *update_slave_arr);
static void ad_enable_collecting_distributing(struct port *port,
bool *update_slave_arr);
static void ad_disable_collecting_distributing(struct port *port,
@@ -172,8 +171,37 @@ static inline int __agg_has_partner(struct aggregator *agg)
}
/**
+ * __disable_distributing_port - disable the port's slave for distributing.
+ * Port will still be able to collect.
+ * @port: the port we're looking at
+ *
+ * This will disable only distributing on the port's slave.
+ */
+static void __disable_distributing_port(struct port *port)
+{
+ bond_set_slave_tx_disabled_flags(port->slave, BOND_SLAVE_NOTIFY_LATER);
+}
+
+/**
+ * __enable_collecting_port - enable the port's slave for collecting,
+ * if it's up
+ * @port: the port we're looking at
+ *
+ * This will enable only collecting on the port's slave.
+ */
+static void __enable_collecting_port(struct port *port)
+{
+ struct slave *slave = port->slave;
+
+ if (slave->link == BOND_LINK_UP && bond_slave_is_up(slave))
+ bond_set_slave_rx_enabled_flags(slave, BOND_SLAVE_NOTIFY_LATER);
+}
+
+/**
* __disable_port - disable the port's slave
* @port: the port we're looking at
+ *
+ * This will disable both collecting and distributing on the port's slave.
*/
static inline void __disable_port(struct port *port)
{
@@ -183,6 +211,8 @@ static inline void __disable_port(struct port *port)
/**
* __enable_port - enable the port's slave, if it's up
* @port: the port we're looking at
+ *
+ * This will enable both collecting and distributing on the port's slave.
*/
static inline void __enable_port(struct port *port)
{
@@ -193,10 +223,27 @@ static inline void __enable_port(struct port *port)
}
/**
- * __port_is_enabled - check if the port's slave is in active state
+ * __port_move_to_attached_state - check if port should transition back to attached
+ * state.
+ * @port: the port we're looking at
+ */
+static bool __port_move_to_attached_state(struct port *port)
+{
+ if (!(port->sm_vars & AD_PORT_SELECTED) ||
+ (port->sm_vars & AD_PORT_STANDBY) ||
+ !(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) ||
+ !(port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION))
+ port->sm_mux_state = AD_MUX_ATTACHED;
+
+ return port->sm_mux_state == AD_MUX_ATTACHED;
+}
+
+/**
+ * __port_is_collecting_distributing - check if the port's slave is in the
+ * combined collecting/distributing state
* @port: the port we're looking at
*/
-static inline int __port_is_enabled(struct port *port)
+static int __port_is_collecting_distributing(struct port *port)
{
return bond_is_active_slave(port->slave);
}
@@ -942,6 +989,7 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker)
*/
static void ad_mux_machine(struct port *port, bool *update_slave_arr)
{
+ struct bonding *bond = __get_bond_by_port(port);
mux_states_t last_state;
/* keep current State Machine state to compare later if it was
@@ -999,9 +1047,13 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr)
if ((port->sm_vars & AD_PORT_SELECTED) &&
(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) &&
!__check_agg_selection_timer(port)) {
- if (port->aggregator->is_active)
- port->sm_mux_state =
- AD_MUX_COLLECTING_DISTRIBUTING;
+ if (port->aggregator->is_active) {
+ int state = AD_MUX_COLLECTING_DISTRIBUTING;
+
+ if (!bond->params.coupled_control)
+ state = AD_MUX_COLLECTING;
+ port->sm_mux_state = state;
+ }
} else if (!(port->sm_vars & AD_PORT_SELECTED) ||
(port->sm_vars & AD_PORT_STANDBY)) {
/* if UNSELECTED or STANDBY */
@@ -1019,11 +1071,45 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr)
}
break;
case AD_MUX_COLLECTING_DISTRIBUTING:
+ if (!__port_move_to_attached_state(port)) {
+ /* if port state hasn't changed make
+ * sure that a collecting distributing
+ * port in an active aggregator is enabled
+ */
+ if (port->aggregator->is_active &&
+ !__port_is_collecting_distributing(port)) {
+ __enable_port(port);
+ *update_slave_arr = true;
+ }
+ }
+ break;
+ case AD_MUX_COLLECTING:
+ if (!__port_move_to_attached_state(port)) {
+ if ((port->sm_vars & AD_PORT_SELECTED) &&
+ (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) &&
+ (port->partner_oper.port_state & LACP_STATE_COLLECTING)) {
+ port->sm_mux_state = AD_MUX_DISTRIBUTING;
+ } else {
+ /* If port state hasn't changed, make sure that a collecting
+ * port is enabled for an active aggregator.
+ */
+ struct slave *slave = port->slave;
+
+ if (port->aggregator->is_active &&
+ bond_is_slave_rx_disabled(slave)) {
+ ad_enable_collecting(port);
+ *update_slave_arr = true;
+ }
+ }
+ }
+ break;
+ case AD_MUX_DISTRIBUTING:
if (!(port->sm_vars & AD_PORT_SELECTED) ||
(port->sm_vars & AD_PORT_STANDBY) ||
+ !(port->partner_oper.port_state & LACP_STATE_COLLECTING) ||
!(port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) ||
!(port->actor_oper_port_state & LACP_STATE_SYNCHRONIZATION)) {
- port->sm_mux_state = AD_MUX_ATTACHED;
+ port->sm_mux_state = AD_MUX_COLLECTING;
} else {
/* if port state hasn't changed make
* sure that a collecting distributing
@@ -1031,7 +1117,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr)
*/
if (port->aggregator &&
port->aggregator->is_active &&
- !__port_is_enabled(port)) {
+ !__port_is_collecting_distributing(port)) {
__enable_port(port);
*update_slave_arr = true;
}
@@ -1082,6 +1168,20 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr)
update_slave_arr);
port->ntt = true;
break;
+ case AD_MUX_COLLECTING:
+ port->actor_oper_port_state |= LACP_STATE_COLLECTING;
+ port->actor_oper_port_state &= ~LACP_STATE_DISTRIBUTING;
+ port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION;
+ ad_enable_collecting(port);
+ ad_disable_distributing(port, update_slave_arr);
+ port->ntt = true;
+ break;
+ case AD_MUX_DISTRIBUTING:
+ port->actor_oper_port_state |= LACP_STATE_DISTRIBUTING;
+ port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION;
+ ad_enable_collecting_distributing(port,
+ update_slave_arr);
+ break;
default:
break;
}
@@ -1484,7 +1584,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr)
(aggregator->partner_system_priority == port->partner_oper.system_priority) &&
(aggregator->partner_oper_aggregator_key == port->partner_oper.key)
) &&
- ((!MAC_ADDRESS_EQUAL(&(port->partner_oper.system), &(null_mac_addr)) && /* partner answers */
+ ((__agg_has_partner(aggregator) && /* partner answers */
!aggregator->is_individual) /* but is not individual OR */
)
) {
@@ -1907,6 +2007,43 @@ static void ad_initialize_port(struct port *port, int lacp_fast)
}
/**
+ * ad_enable_collecting - enable a port's receive
+ * @port: the port we're looking at
+ *
+ * Enable @port if it's in an active aggregator
+ */
+static void ad_enable_collecting(struct port *port)
+{
+ if (port->aggregator->is_active) {
+ struct slave *slave = port->slave;
+
+ slave_dbg(slave->bond->dev, slave->dev,
+ "Enabling collecting on port %d (LAG %d)\n",
+ port->actor_port_number,
+ port->aggregator->aggregator_identifier);
+ __enable_collecting_port(port);
+ }
+}
+
+/**
+ * ad_disable_distributing - disable a port's transmit
+ * @port: the port we're looking at
+ * @update_slave_arr: Does slave array need update?
+ */
+static void ad_disable_distributing(struct port *port, bool *update_slave_arr)
+{
+ if (port->aggregator && __agg_has_partner(port->aggregator)) {
+ slave_dbg(port->slave->bond->dev, port->slave->dev,
+ "Disabling distributing on port %d (LAG %d)\n",
+ port->actor_port_number,
+ port->aggregator->aggregator_identifier);
+ __disable_distributing_port(port);
+ /* Slave array needs an update */
+ *update_slave_arr = true;
+ }
+}
+
+/**
* ad_enable_collecting_distributing - enable a port's transmit/receive
* @port: the port we're looking at
* @update_slave_arr: Does slave array need update?
@@ -1935,9 +2072,7 @@ static void ad_enable_collecting_distributing(struct port *port,
static void ad_disable_collecting_distributing(struct port *port,
bool *update_slave_arr)
{
- if (port->aggregator &&
- !MAC_ADDRESS_EQUAL(&(port->aggregator->partner_system),
- &(null_mac_addr))) {
+ if (port->aggregator && __agg_has_partner(port->aggregator)) {
slave_dbg(port->slave->bond->dev, port->slave->dev,
"Disabling port %d (LAG %d)\n",
port->actor_port_number,
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index b19492a7f6ad..8adbec7c5084 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -63,13 +63,8 @@ void bond_debug_unregister(struct bonding *bond)
void bond_debug_reregister(struct bonding *bond)
{
- struct dentry *d;
-
- d = debugfs_rename(bonding_debug_root, bond->debug_dir,
- bonding_debug_root, bond->dev->name);
- if (!IS_ERR(d)) {
- bond->debug_dir = d;
- } else {
+ int err = debugfs_change_name(bond->debug_dir, "%s", bond->dev->name);
+ if (err) {
netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n");
bond_debug_unregister(bond);
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index cd0683bcca03..e45bba240cbc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -419,6 +419,41 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
#ifdef CONFIG_XFRM_OFFLOAD
/**
+ * bond_ipsec_dev - Get active device for IPsec offload
+ * @xs: pointer to transformer state struct
+ *
+ * Context: caller must hold rcu_read_lock.
+ *
+ * Return: the device for ipsec offload, or NULL if not exist.
+ **/
+static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
+{
+ struct net_device *bond_dev = xs->xso.dev;
+ struct bonding *bond;
+ struct slave *slave;
+
+ if (!bond_dev)
+ return NULL;
+
+ bond = netdev_priv(bond_dev);
+ if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
+ return NULL;
+
+ slave = rcu_dereference(bond->curr_active_slave);
+ if (!slave)
+ return NULL;
+
+ if (!xs->xso.real_dev)
+ return NULL;
+
+ if (xs->xso.real_dev != slave->dev)
+ pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n",
+ bond_dev->name, slave->dev->name, xs->xso.real_dev->name);
+
+ return slave->dev;
+}
+
+/**
* bond_ipsec_add_sa - program device with a security association
* @xs: pointer to transformer state struct
* @extack: extack point to fill failure reason
@@ -427,6 +462,8 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
struct netlink_ext_ack *extack)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct net_device *real_dev;
+ netdevice_tracker tracker;
struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
@@ -438,74 +475,80 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
- if (!slave) {
- rcu_read_unlock();
- return -ENODEV;
+ real_dev = slave ? slave->dev : NULL;
+ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+ rcu_read_unlock();
+ if (!real_dev) {
+ err = -ENODEV;
+ goto out;
}
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
- netif_is_bond_master(slave->dev)) {
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(real_dev)) {
NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
- rcu_read_unlock();
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
- ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+ ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL);
if (!ipsec) {
- rcu_read_unlock();
- return -ENOMEM;
+ err = -ENOMEM;
+ goto out;
}
- xs->xso.real_dev = slave->dev;
- err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
+ xs->xso.real_dev = real_dev;
+ err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
if (!err) {
ipsec->xs = xs;
INIT_LIST_HEAD(&ipsec->list);
- spin_lock_bh(&bond->ipsec_lock);
+ mutex_lock(&bond->ipsec_lock);
list_add(&ipsec->list, &bond->ipsec_list);
- spin_unlock_bh(&bond->ipsec_lock);
+ mutex_unlock(&bond->ipsec_lock);
} else {
kfree(ipsec);
}
- rcu_read_unlock();
+out:
+ netdev_put(real_dev, &tracker);
return err;
}
static void bond_ipsec_add_sa_all(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
+ struct net_device *real_dev;
struct bond_ipsec *ipsec;
struct slave *slave;
- rcu_read_lock();
- slave = rcu_dereference(bond->curr_active_slave);
- if (!slave)
- goto out;
+ slave = rtnl_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ if (!real_dev)
+ return;
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
- netif_is_bond_master(slave->dev)) {
- spin_lock_bh(&bond->ipsec_lock);
+ mutex_lock(&bond->ipsec_lock);
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(real_dev)) {
if (!list_empty(&bond->ipsec_list))
- slave_warn(bond_dev, slave->dev,
+ slave_warn(bond_dev, real_dev,
"%s: no slave xdo_dev_state_add\n",
__func__);
- spin_unlock_bh(&bond->ipsec_lock);
goto out;
}
- spin_lock_bh(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
- ipsec->xs->xso.real_dev = slave->dev;
- if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
- slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+ /* If new state is added before ipsec_lock acquired */
+ if (ipsec->xs->xso.real_dev == real_dev)
+ continue;
+
+ ipsec->xs->xso.real_dev = real_dev;
+ if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
+ slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
ipsec->xs->xso.real_dev = NULL;
}
}
- spin_unlock_bh(&bond->ipsec_lock);
out:
- rcu_read_unlock();
+ mutex_unlock(&bond->ipsec_lock);
}
/**
@@ -515,6 +558,8 @@ out:
static void bond_ipsec_del_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct net_device *real_dev;
+ netdevice_tracker tracker;
struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
@@ -525,6 +570,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+ rcu_read_unlock();
if (!slave)
goto out;
@@ -532,18 +580,19 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
if (!xs->xso.real_dev)
goto out;
- WARN_ON(xs->xso.real_dev != slave->dev);
+ WARN_ON(xs->xso.real_dev != real_dev);
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
- netif_is_bond_master(slave->dev)) {
- slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(real_dev)) {
+ slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
goto out;
}
- slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+ real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
out:
- spin_lock_bh(&bond->ipsec_lock);
+ netdev_put(real_dev, &tracker);
+ mutex_lock(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
if (ipsec->xs == xs) {
list_del(&ipsec->list);
@@ -551,41 +600,72 @@ out:
break;
}
}
- spin_unlock_bh(&bond->ipsec_lock);
- rcu_read_unlock();
+ mutex_unlock(&bond->ipsec_lock);
}
static void bond_ipsec_del_sa_all(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
+ struct net_device *real_dev;
struct bond_ipsec *ipsec;
struct slave *slave;
- rcu_read_lock();
- slave = rcu_dereference(bond->curr_active_slave);
- if (!slave) {
- rcu_read_unlock();
+ slave = rtnl_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ if (!real_dev)
return;
- }
- spin_lock_bh(&bond->ipsec_lock);
+ mutex_lock(&bond->ipsec_lock);
list_for_each_entry(ipsec, &bond->ipsec_list, list) {
if (!ipsec->xs->xso.real_dev)
continue;
- if (!slave->dev->xfrmdev_ops ||
- !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
- netif_is_bond_master(slave->dev)) {
- slave_warn(bond_dev, slave->dev,
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(real_dev)) {
+ slave_warn(bond_dev, real_dev,
"%s: no slave xdo_dev_state_delete\n",
__func__);
} else {
- slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ if (real_dev->xfrmdev_ops->xdo_dev_state_free)
+ real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
}
- ipsec->xs->xso.real_dev = NULL;
}
- spin_unlock_bh(&bond->ipsec_lock);
+ mutex_unlock(&bond->ipsec_lock);
+}
+
+static void bond_ipsec_free_sa(struct xfrm_state *xs)
+{
+ struct net_device *bond_dev = xs->xso.dev;
+ struct net_device *real_dev;
+ netdevice_tracker tracker;
+ struct bonding *bond;
+ struct slave *slave;
+
+ if (!bond_dev)
+ return;
+
+ rcu_read_lock();
+ bond = netdev_priv(bond_dev);
+ slave = rcu_dereference(bond->curr_active_slave);
+ real_dev = slave ? slave->dev : NULL;
+ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
rcu_read_unlock();
+
+ if (!slave)
+ goto out;
+
+ if (!xs->xso.real_dev)
+ goto out;
+
+ WARN_ON(xs->xso.real_dev != real_dev);
+
+ if (real_dev && real_dev->xfrmdev_ops &&
+ real_dev->xfrmdev_ops->xdo_dev_state_free)
+ real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
+out:
+ netdev_put(real_dev, &tracker);
}
/**
@@ -595,44 +675,80 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
**/
static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
{
- struct net_device *bond_dev = xs->xso.dev;
struct net_device *real_dev;
- struct slave *curr_active;
- struct bonding *bond;
- int err;
+ bool ok = false;
- bond = netdev_priv(bond_dev);
rcu_read_lock();
- curr_active = rcu_dereference(bond->curr_active_slave);
- real_dev = curr_active->dev;
+ real_dev = bond_ipsec_dev(xs);
+ if (!real_dev)
+ goto out;
- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
- err = false;
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
+ netif_is_bond_master(real_dev))
+ goto out;
+
+ ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+out:
+ rcu_read_unlock();
+ return ok;
+}
+
+/**
+ * bond_advance_esn_state - ESN support for IPSec HW offload
+ * @xs: pointer to transformer state struct
+ **/
+static void bond_advance_esn_state(struct xfrm_state *xs)
+{
+ struct net_device *real_dev;
+
+ rcu_read_lock();
+ real_dev = bond_ipsec_dev(xs);
+ if (!real_dev)
goto out;
- }
- if (!xs->xso.real_dev) {
- err = false;
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) {
+ pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name);
goto out;
}
+ real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs);
+out:
+ rcu_read_unlock();
+}
+
+/**
+ * bond_xfrm_update_stats - Update xfrm state
+ * @xs: pointer to transformer state struct
+ **/
+static void bond_xfrm_update_stats(struct xfrm_state *xs)
+{
+ struct net_device *real_dev;
+
+ rcu_read_lock();
+ real_dev = bond_ipsec_dev(xs);
+ if (!real_dev)
+ goto out;
+
if (!real_dev->xfrmdev_ops ||
- !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
- netif_is_bond_master(real_dev)) {
- err = false;
+ !real_dev->xfrmdev_ops->xdo_dev_state_update_stats) {
+ pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name);
goto out;
}
- err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+ real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs);
out:
rcu_read_unlock();
- return err;
}
static const struct xfrmdev_ops bond_xfrmdev_ops = {
.xdo_dev_state_add = bond_ipsec_add_sa,
.xdo_dev_state_delete = bond_ipsec_del_sa,
+ .xdo_dev_state_free = bond_ipsec_free_sa,
.xdo_dev_offload_ok = bond_ipsec_offload_ok,
+ .xdo_dev_state_advance_esn = bond_advance_esn_state,
+ .xdo_dev_state_update_stats = bond_xfrm_update_stats,
};
#endif /* CONFIG_XFRM_OFFLOAD */
@@ -892,6 +1008,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
if (bond->dev->flags & IFF_UP)
bond_hw_addr_flush(bond->dev, old_active->dev);
+
+ bond_slave_ns_maddrs_add(bond, old_active);
}
if (new_active) {
@@ -908,6 +1026,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
dev_mc_sync(new_active->dev, bond->dev);
netif_addr_unlock_bh(bond->dev);
}
+
+ bond_slave_ns_maddrs_del(bond, new_active);
}
}
@@ -1121,13 +1241,10 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
return bestslave;
}
+/* must be called in RCU critical section or with RTNL held */
static bool bond_should_notify_peers(struct bonding *bond)
{
- struct slave *slave;
-
- rcu_read_lock();
- slave = rcu_dereference(bond->curr_active_slave);
- rcu_read_unlock();
+ struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
if (!slave || !bond->send_peer_notif ||
bond->send_peer_notif %
@@ -1363,7 +1480,7 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
slave_disable_netpoll(slave);
}
-static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
+static int bond_netpoll_setup(struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
struct list_head *iter;
@@ -1403,9 +1520,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
struct slave *slave;
mask = features;
-
- features &= ~NETIF_F_ONE_FOR_ALL;
- features |= NETIF_F_ALL_FOR_ALL;
+ features = netdev_base_features(features);
bond_for_each_slave(bond, slave, iter) {
features = netdev_increment_features(features,
@@ -1419,17 +1534,22 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
#define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
+ NETIF_F_GSO_ENCAP_ALL | \
NETIF_F_HIGHDMA | NETIF_F_LRO)
#define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
- NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE)
+ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \
+ NETIF_F_GSO_PARTIAL)
#define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_GSO_SOFTWARE)
+#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP)
+
static void bond_compute_features(struct bonding *bond)
{
+ netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES;
unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
IFF_XMIT_DST_RELEASE_PERM;
netdev_features_t vlan_features = BOND_VLAN_FEATURES;
@@ -1447,8 +1567,9 @@ static void bond_compute_features(struct bonding *bond)
if (!bond_has_slaves(bond))
goto done;
- vlan_features &= NETIF_F_ALL_FOR_ALL;
- mpls_features &= NETIF_F_ALL_FOR_ALL;
+
+ vlan_features = netdev_base_features(vlan_features);
+ mpls_features = netdev_base_features(mpls_features);
bond_for_each_slave(bond, slave, iter) {
vlan_features = netdev_increment_features(vlan_features,
@@ -1464,6 +1585,10 @@ static void bond_compute_features(struct bonding *bond)
BOND_XFRM_FEATURES);
#endif /* CONFIG_XFRM_OFFLOAD */
+ gso_partial_features = netdev_increment_features(gso_partial_features,
+ slave->dev->gso_partial_features,
+ BOND_GSO_PARTIAL_FEATURES);
+
mpls_features = netdev_increment_features(mpls_features,
slave->dev->mpls_features,
BOND_MPLS_FEATURES);
@@ -1478,6 +1603,7 @@ static void bond_compute_features(struct bonding *bond)
bond_dev->hard_header_len = max_hard_header_len;
done:
+ bond_dev->gso_partial_features = gso_partial_features;
bond_dev->vlan_features = vlan_features;
bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
NETIF_F_HW_VLAN_CTAG_TX |
@@ -2228,6 +2354,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
bond_compute_features(bond);
bond_set_carrier(bond);
+ /* Needs to be called before bond_select_active_slave(), which will
+ * remove the maddrs if the slave is selected as active slave.
+ */
+ bond_slave_ns_maddrs_add(bond, new_slave);
+
if (bond_uses_primary(bond)) {
block_netpoll_tx();
bond_select_active_slave(bond);
@@ -2237,7 +2368,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
-
if (!slave_dev->netdev_ops->ndo_bpf ||
!slave_dev->netdev_ops->ndo_xdp_xmit) {
if (bond->xdp_prog) {
@@ -2261,7 +2391,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
goto err_sysfs_del;
}
- res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+ res = dev_xdp_propagate(slave_dev, &xdp);
if (res < 0) {
/* ndo_bpf() sets extack error message */
slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res);
@@ -2397,7 +2527,7 @@ static int __bond_release_one(struct net_device *bond_dev,
.prog = NULL,
.extack = NULL,
};
- if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp))
+ if (dev_xdp_propagate(slave_dev, &xdp))
slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n");
}
@@ -2435,6 +2565,12 @@ static int __bond_release_one(struct net_device *bond_dev,
if (oldcurrent == slave)
bond_change_active_slave(bond, NULL);
+ /* Must be called after bond_change_active_slave () as the slave
+ * might change from an active slave to a backup slave. Then it is
+ * necessary to clear the maddrs on the backup slave.
+ */
+ bond_slave_ns_maddrs_del(bond, slave);
+
if (bond_is_lb(bond)) {
/* Must be called only after the slave has been
* detached from the list and the curr_active_slave
@@ -2611,7 +2747,7 @@ static int bond_miimon_inspect(struct bonding *bond)
bond_propose_link_state(slave, BOND_LINK_FAIL);
commit++;
slave->delay = bond->params.downdelay;
- if (slave->delay) {
+ if (slave->delay && net_ratelimit()) {
slave_info(bond->dev, slave->dev, "link status down for %sinterface, disabling it in %d ms\n",
(BOND_MODE(bond) ==
BOND_MODE_ACTIVEBACKUP) ?
@@ -2625,9 +2761,10 @@ static int bond_miimon_inspect(struct bonding *bond)
/* recovered before downdelay expired */
bond_propose_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
- slave_info(bond->dev, slave->dev, "link status up again after %d ms\n",
- (bond->params.downdelay - slave->delay) *
- bond->params.miimon);
+ if (net_ratelimit())
+ slave_info(bond->dev, slave->dev, "link status up again after %d ms\n",
+ (bond->params.downdelay - slave->delay) *
+ bond->params.miimon);
commit++;
continue;
}
@@ -2649,7 +2786,7 @@ static int bond_miimon_inspect(struct bonding *bond)
commit++;
slave->delay = bond->params.updelay;
- if (slave->delay) {
+ if (slave->delay && net_ratelimit()) {
slave_info(bond->dev, slave->dev, "link status up, enabling it in %d ms\n",
ignore_updelay ? 0 :
bond->params.updelay *
@@ -2659,9 +2796,10 @@ static int bond_miimon_inspect(struct bonding *bond)
case BOND_LINK_BACK:
if (!link_state) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
- slave_info(bond->dev, slave->dev, "link status down again after %d ms\n",
- (bond->params.updelay - slave->delay) *
- bond->params.miimon);
+ if (net_ratelimit())
+ slave_info(bond->dev, slave->dev, "link status down again after %d ms\n",
+ (bond->params.updelay - slave->delay) *
+ bond->params.miimon);
commit++;
continue;
}
@@ -3012,8 +3150,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
tags = NULL;
/* Find out through which dev should the packet go */
- rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
- RTO_ONLINK, 0);
+ rt = ip_route_output(dev_net(bond->dev), targets[i], 0, 0, 0,
+ RT_SCOPE_LINK);
if (IS_ERR(rt)) {
/* there's no route to target - try to send arp
* probe to generate any traffic (arp_validate=0)
@@ -4708,7 +4846,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu)
}
}
- bond_dev->mtu = new_mtu;
+ WRITE_ONCE(bond_dev->mtu, new_mtu);
return 0;
@@ -5243,7 +5381,7 @@ static inline int bond_slave_override(struct bonding *bond,
/* Find out if any slaves have the same mapping as this skb. */
bond_for_each_slave_rcu(bond, slave, iter) {
- if (slave->queue_id == skb_get_queue_mapping(skb)) {
+ if (READ_ONCE(slave->queue_id) == skb_get_queue_mapping(skb)) {
if (bond_slave_is_up(slave) &&
slave->link == BOND_LINK_UP) {
bond_dev_queue_xmit(bond, skb, slave->dev);
@@ -5495,9 +5633,9 @@ bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
break;
default:
- /* Should never happen. Mode guarded by bond_xdp_check() */
- netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
- WARN_ON_ONCE(1);
+ if (net_ratelimit())
+ netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n",
+ BOND_MODE(bond));
return NULL;
}
@@ -5561,8 +5699,11 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
ASSERT_RTNL();
- if (!bond_xdp_check(bond))
+ if (!bond_xdp_check(bond)) {
+ BOND_NL_ERR(dev, extack,
+ "No native XDP support for the current bonding mode");
return -EOPNOTSUPP;
+ }
old_prog = bond->xdp_prog;
bond->xdp_prog = prog;
@@ -5585,7 +5726,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
goto err;
}
- err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+ err = dev_xdp_propagate(slave_dev, &xdp);
if (err < 0) {
/* ndo_bpf() sets extack error message */
slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err);
@@ -5617,7 +5758,7 @@ err:
if (slave == rollback_slave)
break;
- err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+ err_unwind = dev_xdp_propagate(slave_dev, &xdp);
if (err_unwind < 0)
slave_err(dev, slave_dev,
"Error %d when unwinding XDP program change\n", err_unwind);
@@ -5753,10 +5894,10 @@ static void bond_ethtool_get_drvinfo(struct net_device *bond_dev,
}
static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
- struct ethtool_ts_info *info)
+ struct kernel_ethtool_ts_info *info)
{
struct bonding *bond = netdev_priv(bond_dev);
- struct ethtool_ts_info ts_info;
+ struct kernel_ethtool_ts_info ts_info;
struct net_device *real_dev;
bool sw_tx_support = false;
struct list_head *iter;
@@ -5880,11 +6021,14 @@ void bond_setup(struct net_device *bond_dev)
/* set up xfrm device ops (only supported in active-backup right now) */
bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
INIT_LIST_HEAD(&bond->ipsec_list);
- spin_lock_init(&bond->ipsec_lock);
+ mutex_init(&bond->ipsec_lock);
#endif /* CONFIG_XFRM_OFFLOAD */
/* don't acquire bond device's netif_tx_lock when transmitting */
- bond_dev->features |= NETIF_F_LLTX;
+ bond_dev->lltx = true;
+
+ /* Don't allow bond devices to change network namespaces. */
+ bond_dev->netns_local = true;
/* By default, we declare the bond to be fully
* VLAN hardware accelerated capable. Special
@@ -5893,9 +6037,6 @@ void bond_setup(struct net_device *bond_dev)
* capable
*/
- /* Don't allow bond devices to change network namespaces. */
- bond_dev->features |= NETIF_F_NETNS_LOCAL;
-
bond_dev->hw_features = BOND_VLAN_FEATURES |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -5905,6 +6046,7 @@ void bond_setup(struct net_device *bond_dev)
bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
bond_dev->features |= bond_dev->hw_features;
bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+ bond_dev->features |= NETIF_F_GSO_PARTIAL;
#ifdef CONFIG_XFRM_OFFLOAD
bond_dev->hw_features |= BOND_XFRM_FEATURES;
/* Only enable XFRM features if this is an active-backup config */
@@ -5929,9 +6071,13 @@ static void bond_uninit(struct net_device *bond_dev)
__bond_release_one(bond_dev, slave->dev, true, true);
netdev_info(bond_dev, "Released all slaves\n");
+#ifdef CONFIG_XFRM_OFFLOAD
+ mutex_destroy(&bond->ipsec_lock);
+#endif /* CONFIG_XFRM_OFFLOAD */
+
bond_set_slave_arr(bond, NULL, NULL);
- list_del(&bond->bond_list);
+ list_del_rcu(&bond->bond_list);
bond_debug_unregister(bond);
}
@@ -6305,6 +6451,7 @@ static int __init bond_check_params(struct bond_params *params)
params->ad_actor_sys_prio = ad_actor_sys_prio;
eth_zero_addr(params->ad_actor_system);
params->ad_user_port_key = ad_user_port_key;
+ params->coupled_control = 1;
if (packets_per_slave > 0) {
params->reciprocal_packets_per_slave =
reciprocal_value(packets_per_slave);
@@ -6335,7 +6482,8 @@ static int bond_init(struct net_device *bond_dev)
netdev_dbg(bond_dev, "Begin bond_init\n");
- bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
+ bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+ bond_dev->name);
if (!bond->wq)
return -ENOMEM;
@@ -6344,7 +6492,7 @@ static int bond_init(struct net_device *bond_dev)
spin_lock_init(&bond->stats_lock);
netdev_lockdep_set_classes(bond_dev);
- list_add_tail(&bond->bond_list, &bn->dev_list);
+ list_add_tail_rcu(&bond->bond_list, &bn->dev_list);
bond_prepare_sysfs_group(bond);
@@ -6414,28 +6562,41 @@ static int __net_init bond_net_init(struct net *net)
return 0;
}
-static void __net_exit bond_net_exit_batch(struct list_head *net_list)
+/* According to commit 69b0216ac255 ("bonding: fix bonding_masters
+ * race condition in bond unloading") we need to remove sysfs files
+ * before we remove our devices (done later in bond_net_exit_batch_rtnl())
+ */
+static void __net_exit bond_net_pre_exit(struct net *net)
+{
+ struct bond_net *bn = net_generic(net, bond_net_id);
+
+ bond_destroy_sysfs(bn);
+}
+
+static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list,
+ struct list_head *dev_kill_list)
{
struct bond_net *bn;
struct net *net;
- LIST_HEAD(list);
-
- list_for_each_entry(net, net_list, exit_list) {
- bn = net_generic(net, bond_net_id);
- bond_destroy_sysfs(bn);
- }
/* Kill off any bonds created after unregistering bond rtnl ops */
- rtnl_lock();
list_for_each_entry(net, net_list, exit_list) {
struct bonding *bond, *tmp_bond;
bn = net_generic(net, bond_net_id);
list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
- unregister_netdevice_queue(bond->dev, &list);
+ unregister_netdevice_queue(bond->dev, dev_kill_list);
}
- unregister_netdevice_many(&list);
- rtnl_unlock();
+}
+
+/* According to commit 23fa5c2caae0 ("bonding: destroy proc directory
+ * only after all bonds are gone") bond_destroy_proc_dir() is called
+ * after bond_net_exit_batch_rtnl() has completed.
+ */
+static void __net_exit bond_net_exit_batch(struct list_head *net_list)
+{
+ struct bond_net *bn;
+ struct net *net;
list_for_each_entry(net, net_list, exit_list) {
bn = net_generic(net, bond_net_id);
@@ -6445,6 +6606,8 @@ static void __net_exit bond_net_exit_batch(struct list_head *net_list)
static struct pernet_operations bond_net_ops = {
.init = bond_net_init,
+ .pre_exit = bond_net_pre_exit,
+ .exit_batch_rtnl = bond_net_exit_batch_rtnl,
.exit_batch = bond_net_exit_batch,
.id = &bond_net_id,
.size = sizeof(struct bond_net),
@@ -6459,16 +6622,16 @@ static int __init bonding_init(void)
if (res)
goto out;
+ bond_create_debugfs();
+
res = register_pernet_subsys(&bond_net_ops);
if (res)
- goto out;
+ goto err_net_ops;
res = bond_netlink_init();
if (res)
goto err_link;
- bond_create_debugfs();
-
for (i = 0; i < max_bonds; i++) {
res = bond_create(&init_net, NULL);
if (res)
@@ -6483,10 +6646,11 @@ static int __init bonding_init(void)
out:
return res;
err:
- bond_destroy_debugfs();
bond_netlink_fini();
err_link:
unregister_pernet_subsys(&bond_net_ops);
+err_net_ops:
+ bond_destroy_debugfs();
goto out;
}
@@ -6495,11 +6659,11 @@ static void __exit bonding_exit(void)
{
unregister_netdevice_notifier(&bond_netdev_notifier);
- bond_destroy_debugfs();
-
bond_netlink_fini();
unregister_pernet_subsys(&bond_net_ops);
+ bond_destroy_debugfs();
+
#ifdef CONFIG_NET_POLL_CONTROLLER
/* Make sure we don't have an imbalance on our netpoll blocking */
WARN_ON(atomic_read(&netpoll_block_tx));
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index cfa74cf8bb1a..2a6a424806aa 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -51,7 +51,8 @@ static int bond_fill_slave_info(struct sk_buff *skb,
slave_dev->addr_len, slave->perm_hwaddr))
goto nla_put_failure;
- if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, slave->queue_id))
+ if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID,
+ READ_ONCE(slave->queue_id)))
goto nla_put_failure;
if (nla_put_s32(skb, IFLA_BOND_SLAVE_PRIO, slave->prio))
@@ -122,6 +123,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
[IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range),
[IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 },
[IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED },
+ [IFLA_BOND_COUPLED_CONTROL] = { .type = NLA_U8 },
};
static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = {
@@ -549,6 +551,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
return err;
}
+ if (data[IFLA_BOND_COUPLED_CONTROL]) {
+ int coupled_control = nla_get_u8(data[IFLA_BOND_COUPLED_CONTROL]);
+
+ bond_opt_initval(&newval, coupled_control);
+ err = __bond_opt_set(bond, BOND_OPT_COUPLED_CONTROL, &newval,
+ data[IFLA_BOND_COUPLED_CONTROL], extack);
+ if (err)
+ return err;
+ }
+
return 0;
}
@@ -615,6 +627,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
/* IFLA_BOND_NS_IP6_TARGET */
nla_total_size(sizeof(struct nlattr)) +
nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS +
+ nla_total_size(sizeof(u8)) + /* IFLA_BOND_COUPLED_CONTROL */
0;
}
@@ -774,6 +787,10 @@ static int bond_fill_info(struct sk_buff *skb,
bond->params.missed_max))
goto nla_put_failure;
+ if (nla_put_u8(skb, IFLA_BOND_COUPLED_CONTROL,
+ bond->params.coupled_control))
+ goto nla_put_failure;
+
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
struct ad_info info;
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index f3f27f0bd2a6..d1b095af253b 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -15,6 +15,7 @@
#include <linux/sched/signal.h>
#include <net/bonding.h>
+#include <net/ndisc.h>
static int bond_option_active_slave_set(struct bonding *bond,
const struct bond_opt_value *newval);
@@ -84,7 +85,8 @@ static int bond_option_ad_user_port_key_set(struct bonding *bond,
const struct bond_opt_value *newval);
static int bond_option_missed_max_set(struct bonding *bond,
const struct bond_opt_value *newval);
-
+static int bond_option_coupled_control_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
static const struct bond_opt_value bond_mode_tbl[] = {
{ "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT},
@@ -232,6 +234,12 @@ static const struct bond_opt_value bond_missed_max_tbl[] = {
{ NULL, -1, 0},
};
+static const struct bond_opt_value bond_coupled_control_tbl[] = {
+ { "on", 1, BOND_VALFLAG_DEFAULT},
+ { "off", 0, 0},
+ { NULL, -1, 0},
+};
+
static const struct bond_option bond_opts[BOND_OPT_LAST] = {
[BOND_OPT_MODE] = {
.id = BOND_OPT_MODE,
@@ -496,6 +504,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
.desc = "Delay between each peer notification on failover event, in milliseconds",
.values = bond_peer_notif_delay_tbl,
.set = bond_option_peer_notif_delay_set
+ },
+ [BOND_OPT_COUPLED_CONTROL] = {
+ .id = BOND_OPT_COUPLED_CONTROL,
+ .name = "coupled_control",
+ .desc = "Opt into using coupled control MUX for LACP states",
+ .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+ .flags = BOND_OPTFLAG_IFDOWN,
+ .values = bond_coupled_control_tbl,
+ .set = bond_option_coupled_control_set,
}
};
@@ -920,7 +937,7 @@ static int bond_option_active_slave_set(struct bonding *bond,
/* check to see if we are clearing active */
if (!slave_dev) {
netdev_dbg(bond->dev, "Clearing current active slave\n");
- RCU_INIT_POINTER(bond->curr_active_slave, NULL);
+ bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
} else {
struct slave *old_active = rtnl_dereference(bond->curr_active_slave);
@@ -1198,9 +1215,9 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond,
__be32 target;
if (newval->string) {
- if (!in4_pton(newval->string+1, -1, (u8 *)&target, -1, NULL)) {
- netdev_err(bond->dev, "invalid ARP target %pI4 specified\n",
- &target);
+ if (strlen(newval->string) < 1 ||
+ !in4_pton(newval->string + 1, -1, (u8 *)&target, -1, NULL)) {
+ netdev_err(bond->dev, "invalid ARP target specified\n");
return ret;
}
if (newval->string[0] == '+')
@@ -1218,6 +1235,107 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond,
}
#if IS_ENABLED(CONFIG_IPV6)
+static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *slave)
+{
+ return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
+ !bond_is_active_slave(slave) &&
+ slave->dev->flags & IFF_MULTICAST;
+}
+
+/**
+ * slave_set_ns_maddrs - add/del all NS mac addresses for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @add: add or remove all the NS mac addresses
+ *
+ * This function tries to add or delete all the NS mac addresses on the slave
+ *
+ * Note, the IPv6 NS target address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ * * arp_validate changes
+ * * enslaving, releasing new slaves
+ */
+static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add)
+{
+ struct in6_addr *targets = bond->params.ns_targets;
+ char slot_maddr[MAX_ADDR_LEN];
+ struct in6_addr mcaddr;
+ int i;
+
+ if (!slave_can_set_ns_maddr(bond, slave))
+ return;
+
+ for (i = 0; i < BOND_MAX_NS_TARGETS; i++) {
+ if (ipv6_addr_any(&targets[i]))
+ break;
+
+ addrconf_addr_solict_mult(&targets[i], &mcaddr);
+ if (!ndisc_mc_map(&mcaddr, slot_maddr, slave->dev, 0)) {
+ if (add)
+ dev_mc_add(slave->dev, slot_maddr);
+ else
+ dev_mc_del(slave->dev, slot_maddr);
+ }
+ }
+}
+
+void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave)
+{
+ if (!bond->params.arp_validate)
+ return;
+ slave_set_ns_maddrs(bond, slave, true);
+}
+
+void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave)
+{
+ if (!bond->params.arp_validate)
+ return;
+ slave_set_ns_maddrs(bond, slave, false);
+}
+
+/**
+ * slave_set_ns_maddr - set new NS mac address for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @target: the new IPv6 target
+ * @slot: the old IPv6 target in the slot
+ *
+ * This function tries to replace the old mac address to new one on the slave.
+ *
+ * Note, the target/slot IPv6 address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ * * An IPv6 NS target is added or removed.
+ */
+static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave,
+ struct in6_addr *target, struct in6_addr *slot)
+{
+ char mac_addr[MAX_ADDR_LEN];
+ struct in6_addr mcast_addr;
+
+ if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave))
+ return;
+
+ /* remove the previous mac addr from slave */
+ addrconf_addr_solict_mult(slot, &mcast_addr);
+ if (!ipv6_addr_any(slot) &&
+ !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+ dev_mc_del(slave->dev, mac_addr);
+
+ /* add new mac addr on slave if target is set */
+ addrconf_addr_solict_mult(target, &mcast_addr);
+ if (!ipv6_addr_any(target) &&
+ !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+ dev_mc_add(slave->dev, mac_addr);
+}
+
static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
struct in6_addr *target,
unsigned long last_rx)
@@ -1227,8 +1345,10 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
struct slave *slave;
if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) {
- bond_for_each_slave(bond, slave, iter)
+ bond_for_each_slave(bond, slave, iter) {
slave->target_last_arp_rx[slot] = last_rx;
+ slave_set_ns_maddr(bond, slave, target, &targets[slot]);
+ }
targets[slot] = *target;
}
}
@@ -1280,15 +1400,30 @@ static int bond_option_ns_ip6_targets_set(struct bonding *bond,
{
return -EPERM;
}
+
+static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) {}
+
+void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) {}
+
+void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) {}
#endif
static int bond_option_arp_validate_set(struct bonding *bond,
const struct bond_opt_value *newval)
{
+ bool changed = !!bond->params.arp_validate != !!newval->value;
+ struct list_head *iter;
+ struct slave *slave;
+
netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n",
newval->string, newval->value);
bond->params.arp_validate = newval->value;
+ if (changed) {
+ bond_for_each_slave(bond, slave, iter)
+ slave_set_ns_maddrs(bond, slave, !!bond->params.arp_validate);
+ }
+
return 0;
}
@@ -1573,7 +1708,7 @@ static int bond_option_queue_id_set(struct bonding *bond,
goto err_no_cmd;
/* Actually set the qids for the slave */
- update_slave->queue_id = qid;
+ WRITE_ONCE(update_slave->queue_id, qid);
out:
return ret;
@@ -1692,3 +1827,13 @@ static int bond_option_ad_user_port_key_set(struct bonding *bond,
bond->params.ad_user_port_key = newval->value;
return 0;
}
+
+static int bond_option_coupled_control_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
+{
+ netdev_info(bond->dev, "Setting coupled_control to %s (%llu)\n",
+ newval->string, newval->value);
+
+ bond->params.coupled_control = newval->value;
+ return 0;
+}
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 43be458422b3..7edf72ec816a 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -209,7 +209,7 @@ static void bond_info_show_slave(struct seq_file *seq,
seq_printf(seq, "Permanent HW addr: %*phC\n",
slave->dev->addr_len, slave->perm_hwaddr);
- seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id);
+ seq_printf(seq, "Slave queue ID: %d\n", READ_ONCE(slave->queue_id));
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
const struct port *port = &SLAVE_AD_INFO(slave)->port;
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 2805135a7205..1e13bb170515 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -37,12 +37,12 @@ static ssize_t bonding_show_bonds(const struct class *cls,
{
const struct bond_net *bn =
container_of_const(attr, struct bond_net, class_attr_bonding_masters);
- int res = 0;
struct bonding *bond;
+ int res = 0;
- rtnl_lock();
+ rcu_read_lock();
- list_for_each_entry(bond, &bn->dev_list, bond_list) {
+ list_for_each_entry_rcu(bond, &bn->dev_list, bond_list) {
if (res > (PAGE_SIZE - IFNAMSIZ)) {
/* not enough space for another interface name */
if ((PAGE_SIZE - res) > 10)
@@ -55,7 +55,7 @@ static ssize_t bonding_show_bonds(const struct class *cls,
if (res)
buf[res-1] = '\n'; /* eat the leftover space */
- rtnl_unlock();
+ rcu_read_unlock();
return res;
}
@@ -170,10 +170,9 @@ static ssize_t bonding_show_slaves(struct device *d,
struct slave *slave;
int res = 0;
- if (!rtnl_trylock())
- return restart_syscall();
+ rcu_read_lock();
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
if (res > (PAGE_SIZE - IFNAMSIZ)) {
/* not enough space for another interface name */
if ((PAGE_SIZE - res) > 10)
@@ -184,7 +183,7 @@ static ssize_t bonding_show_slaves(struct device *d,
res += sysfs_emit_at(buf, res, "%s ", slave->dev->name);
}
- rtnl_unlock();
+ rcu_read_unlock();
if (res)
buf[res-1] = '\n'; /* eat the leftover space */
@@ -626,10 +625,9 @@ static ssize_t bonding_show_queue_id(struct device *d,
struct slave *slave;
int res = 0;
- if (!rtnl_trylock())
- return restart_syscall();
+ rcu_read_lock();
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
if (res > (PAGE_SIZE - IFNAMSIZ - 6)) {
/* not enough space for another interface_name:queue_id pair */
if ((PAGE_SIZE - res) > 10)
@@ -638,12 +636,13 @@ static ssize_t bonding_show_queue_id(struct device *d,
break;
}
res += sysfs_emit_at(buf, res, "%s:%d ",
- slave->dev->name, slave->queue_id);
+ slave->dev->name,
+ READ_ONCE(slave->queue_id));
}
if (res)
buf[res-1] = '\n'; /* eat the leftover space */
- rtnl_unlock();
+ rcu_read_unlock();
return res;
}
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 313866f2c0e4..36d0e8440b5b 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -53,7 +53,7 @@ static SLAVE_ATTR_RO(perm_hwaddr);
static ssize_t queue_id_show(struct slave *slave, char *buf)
{
- return sysfs_emit(buf, "%d\n", slave->queue_id);
+ return sysfs_emit(buf, "%d\n", READ_ONCE(slave->queue_id));
}
static SLAVE_ATTR_RO(queue_id);