wifi: wext: Limit notifier event flushes to the device's netns

With mlx5 netdev instance locking enabled, registering an IPoIB netdev
calls the WEXT notifier while holding the instance mutex. Its call to
wireless_nlevent_flush() takes net_rwsem to walk every namespace,
completing the following lockdep dependency cycle:

  netdev instance mutex -> net_rwsem (read) -> GID table mutex
    -> event_handler_rwsem (read) -> netdev instance mutex

RoCE GID enumeration takes the GID table mutex under net_rwsem. GID
updates dispatch events under the table mutex, taking event_handler_rwsem.
The IPoIB event handler takes the netdev instance mutex in
ipoib_queue_work() to traverse child interfaces.

The all-namespace walk originated in the single global worker servicing
per-namespace WEXT queues. The ordering fixes later reused that routine
in netdevice notifiers to prevent delayed WEXT RTM_NEWLINK messages from
following RTM_DELLINK or reporting stale interface flags. A notifier only
needs to drain the affected device's namespace; there is no reason for it
to walk and flush all namespaces.

Pass dev_net(dev) from both notifier callers and make the flush helper
operate on that namespace. Keep the all-namespace walk and net_rwsem in
the existing worker. This removes the instance-mutex -> net_rwsem
dependency while retaining synchronous flushing from the notifiers.

It may seem strange that the fix for a lock cycle across multiple
subsystems lies in a completely unrelated part of the code, but this
seemed the most justified lock cycle edge to break.

Fixes: 8f7b00307b ("net/mlx5e: Convert mlx5 netdevs to instance locking")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Link: https://patch.msgid.link/20261021144111.611840-1-cratiu@nvidia.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
This commit is contained in:
Cosmin Ratiu 2026-10-21 17:41:11 +03:00 committed by Johannes Berg
parent 7ed5dce55f
commit 48c0045366
3 changed files with 23 additions and 20 deletions

View File

@ -201,6 +201,8 @@
#include <linux/wireless.h> /* IOCTL user space API */
#include <linux/if_ether.h>
struct net;
/***************************** VERSION *****************************/
/*
* This constant is used to know which version of the driver API is
@ -411,10 +413,10 @@ struct iw_spy_data {
void wireless_send_event(struct net_device *dev, unsigned int cmd,
union iwreq_data *wrqu, const char *extra);
#ifdef CONFIG_WEXT_CORE
/* flush all previous wext events - if work is done from netdev notifiers */
void wireless_nlevent_flush(void);
/* Flush previous wext events in this netns from netdev notifiers. */
void wireless_nlevent_flush(struct net *net);
#else
static inline void wireless_nlevent_flush(void) {}
static inline void wireless_nlevent_flush(struct net *net) {}
#endif
/* We may need a function to send a stream of events to user space.

View File

@ -1878,7 +1878,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
return NOTIFY_DONE;
}
wireless_nlevent_flush();
wireless_nlevent_flush(dev_net(dev));
return NOTIFY_OK;
}

View File

@ -342,32 +342,28 @@ static const int compat_event_type_size[] = {
/* IW event code */
void wireless_nlevent_flush(void)
void wireless_nlevent_flush(struct net *net)
{
struct sk_buff *skb;
struct net *net;
down_read(&net_rwsem);
for_each_net(net) {
while ((skb = skb_dequeue(&net->wext_nlevents)))
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
GFP_KERNEL);
}
up_read(&net_rwsem);
while ((skb = skb_dequeue(&net->wext_nlevents)))
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(wireless_nlevent_flush);
static int wext_netdev_notifier_call(struct notifier_block *nb,
unsigned long state, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
/*
* When a netdev changes state in any way, flush all pending messages
* to avoid them going out in a strange order, e.g. RTM_NEWLINK after
* RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close()
* or similar - all of which could otherwise happen due to delays from
* schedule_work().
* When a netdev changes state in any way, flush all pending messages in
* its network namespace to avoid them going out in a strange order,
* e.g. RTM_NEWLINK after RTM_DELLINK, or with IFF_UP after without
* IFF_UP during dev_close() or similar - all of which could otherwise
* happen due to delays from schedule_work().
*/
wireless_nlevent_flush();
wireless_nlevent_flush(dev_net(dev));
return NOTIFY_OK;
}
@ -410,7 +406,12 @@ subsys_initcall(wireless_nlevent_init);
/* Process events generated by the wireless layer or the driver. */
static void wireless_nlevent_process(struct work_struct *work)
{
wireless_nlevent_flush();
struct net *net;
down_read(&net_rwsem);
for_each_net(net)
wireless_nlevent_flush(net);
up_read(&net_rwsem);
}
static DECLARE_WORK(wireless_nlevent_work, wireless_nlevent_process);