linux/net/dsa/switch.h
Vladimir Oltean d06f925f13 net: dsa: avoid suspicious RCU usage for synced VLAN-aware MAC addresses
When using the felix driver (the only one which supports UC filtering
and MC filtering) as a DSA master for a random other DSA switch, one can
see the following stack trace when the downstream switch ports join a
VLAN-aware bridge:

=============================
WARNING: suspicious RCU usage
-----------------------------
net/8021q/vlan_core.c:238 suspicious rcu_dereference_protected() usage!

stack backtrace:
Workqueue: dsa_ordered dsa_slave_switchdev_event_work
Call trace:
 lockdep_rcu_suspicious+0x170/0x210
 vlan_for_each+0x8c/0x188
 dsa_slave_sync_uc+0x128/0x178
 __hw_addr_sync_dev+0x138/0x158
 dsa_slave_set_rx_mode+0x58/0x70
 __dev_set_rx_mode+0x88/0xa8
 dev_uc_add+0x74/0xa0
 dsa_port_bridge_host_fdb_add+0xec/0x180
 dsa_slave_switchdev_event_work+0x7c/0x1c8
 process_one_work+0x290/0x568

What it's saying is that vlan_for_each() expects rtnl_lock() context and
it's not getting it, when it's called from the DSA master's ndo_set_rx_mode().

The caller of that - dsa_slave_set_rx_mode() - is the slave DSA
interface's dsa_port_bridge_host_fdb_add() which comes from the deferred
dsa_slave_switchdev_event_work().

We went to great lengths to avoid the rtnl_lock() context in that call
path in commit 0faf890fc5 ("net: dsa: drop rtnl_lock from
dsa_slave_switchdev_event_work"), and calling rtnl_lock() is simply not
an option due to the possibility of deadlocking when calling
dsa_flush_workqueue() from the call paths that do hold rtnl_lock() -
basically all of them.

So, when the DSA master calls vlan_for_each() from its ndo_set_rx_mode(),
the state of the 8021q driver on this device is really not protected
from concurrent access by anything.

Looking at net/8021q/, I don't think that vlan_info->vid_list was
particularly designed with RCU traversal in mind, so introducing an RCU
read-side form of vlan_for_each() - vlan_for_each_rcu() - won't be so
easy, and it also wouldn't be exactly what we need anyway.

In general I believe that the solution isn't in net/8021q/ anyway;
vlan_for_each() is not cut out for this task. DSA doesn't need rtnl_lock()
to be held per se - since it's not a netdev state change that we're
blocking, but rather, just concurrent additions/removals to a VLAN list.
We don't even need sleepable context - the callback of vlan_for_each()
just schedules deferred work.

The proposed escape is to remove the dependency on vlan_for_each() and
to open-code a non-sleepable, rtnl-free alternative to that, based on
copies of the VLAN list modified from .ndo_vlan_rx_add_vid() and
.ndo_vlan_rx_kill_vid().

Fixes: 64fdc5f341 ("net: dsa: sync unicast and multicast addresses for VLAN filters too")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20230626154402.3154454-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-06-27 09:37:41 -07:00

124 lines
2.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef __DSA_SWITCH_H
#define __DSA_SWITCH_H
#include <net/dsa.h>
struct netlink_ext_ack;
enum {
DSA_NOTIFIER_AGEING_TIME,
DSA_NOTIFIER_BRIDGE_JOIN,
DSA_NOTIFIER_BRIDGE_LEAVE,
DSA_NOTIFIER_FDB_ADD,
DSA_NOTIFIER_FDB_DEL,
DSA_NOTIFIER_HOST_FDB_ADD,
DSA_NOTIFIER_HOST_FDB_DEL,
DSA_NOTIFIER_LAG_FDB_ADD,
DSA_NOTIFIER_LAG_FDB_DEL,
DSA_NOTIFIER_LAG_CHANGE,
DSA_NOTIFIER_LAG_JOIN,
DSA_NOTIFIER_LAG_LEAVE,
DSA_NOTIFIER_MDB_ADD,
DSA_NOTIFIER_MDB_DEL,
DSA_NOTIFIER_HOST_MDB_ADD,
DSA_NOTIFIER_HOST_MDB_DEL,
DSA_NOTIFIER_VLAN_ADD,
DSA_NOTIFIER_VLAN_DEL,
DSA_NOTIFIER_HOST_VLAN_ADD,
DSA_NOTIFIER_HOST_VLAN_DEL,
DSA_NOTIFIER_MTU,
DSA_NOTIFIER_TAG_PROTO,
DSA_NOTIFIER_TAG_PROTO_CONNECT,
DSA_NOTIFIER_TAG_PROTO_DISCONNECT,
DSA_NOTIFIER_TAG_8021Q_VLAN_ADD,
DSA_NOTIFIER_TAG_8021Q_VLAN_DEL,
DSA_NOTIFIER_MASTER_STATE_CHANGE,
};
/* DSA_NOTIFIER_AGEING_TIME */
struct dsa_notifier_ageing_time_info {
unsigned int ageing_time;
};
/* DSA_NOTIFIER_BRIDGE_* */
struct dsa_notifier_bridge_info {
const struct dsa_port *dp;
struct dsa_bridge bridge;
bool tx_fwd_offload;
struct netlink_ext_ack *extack;
};
/* DSA_NOTIFIER_FDB_* */
struct dsa_notifier_fdb_info {
const struct dsa_port *dp;
const unsigned char *addr;
u16 vid;
struct dsa_db db;
};
/* DSA_NOTIFIER_LAG_FDB_* */
struct dsa_notifier_lag_fdb_info {
struct dsa_lag *lag;
const unsigned char *addr;
u16 vid;
struct dsa_db db;
};
/* DSA_NOTIFIER_MDB_* */
struct dsa_notifier_mdb_info {
const struct dsa_port *dp;
const struct switchdev_obj_port_mdb *mdb;
struct dsa_db db;
};
/* DSA_NOTIFIER_LAG_* */
struct dsa_notifier_lag_info {
const struct dsa_port *dp;
struct dsa_lag lag;
struct netdev_lag_upper_info *info;
struct netlink_ext_ack *extack;
};
/* DSA_NOTIFIER_VLAN_* */
struct dsa_notifier_vlan_info {
const struct dsa_port *dp;
const struct switchdev_obj_port_vlan *vlan;
struct netlink_ext_ack *extack;
};
/* DSA_NOTIFIER_MTU */
struct dsa_notifier_mtu_info {
const struct dsa_port *dp;
int mtu;
};
/* DSA_NOTIFIER_TAG_PROTO_* */
struct dsa_notifier_tag_proto_info {
const struct dsa_device_ops *tag_ops;
};
/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */
struct dsa_notifier_tag_8021q_vlan_info {
const struct dsa_port *dp;
u16 vid;
};
/* DSA_NOTIFIER_MASTER_STATE_CHANGE */
struct dsa_notifier_master_state_info {
const struct net_device *master;
bool operational;
};
struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
const struct switchdev_obj_port_vlan *vlan);
int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v);
int dsa_broadcast(unsigned long e, void *v);
int dsa_switch_register_notifier(struct dsa_switch *ds);
void dsa_switch_unregister_notifier(struct dsa_switch *ds);
#endif