mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-10-26 10:57:38 +08:00
Jakub Kicinski
b6f74dff6d
netdev_lockdep_set_classes() puts dev->lock in a separate lockdep class, by type (netkit vs dummy etc), with the intent of keeping the instance locks of individual devices as independent from each other as possible. In practice it does the opposite. lockdep only calls the cmp_fn for locks of the same class, so netdev_lock_cmp_fn() never gets a say when devices from different classes are nested. Instead lockdep records a dependency between the classes, and reports a circular locking problem as soon as the nesting happens the other way round, e.g. when devices are unregistered in a batch. ====================================================== WARNING: possible circular locking dependency detected 7.3.0-rc3+ #26 Not tainted ------------------------------------------------------ kworker/u256:1/326 is trying to acquire lock: ff110000104fce28 (&dev_instance_lock_key#6){+.+.}-{4:4}, at: unregister_netdevice_many_notify+0x1141/0x1c30 but task is already holding lock: ff110000127f2e28 (&dev_instance_lock_key#7){+.+.}-{4:4}, at: unregister_netdevice_many_notify+0x1141/0x1c30 -> #1 (&dev_instance_lock_key#7){+.+.}-{4:4}: __lock_acquire+0x767/0xd60 lock_acquire.part.0+0xd0/0x260 __mutex_lock+0x17d/0x1f20 unregister_netdevice_many_notify+0x1141/0x1c30 default_device_exit_batch+0x3ee/0x520 ops_undo_list+0x2cc/0x8a0 cleanup_net+0x442/0x9c0 process_one_work+0x951/0x1ab0 worker_thread+0x5a6/0xd10 kthread+0x339/0x430 ret_from_fork+0x4a4/0x6f0 ret_from_fork_asm+0x1a/0x30 -> #0 (&dev_instance_lock_key#6){+.+.}-{4:4}: check_prev_add+0xeb/0xe60 validate_chain+0x598/0x900 __lock_acquire+0x767/0xd60 lock_acquire.part.0+0xd0/0x260 __mutex_lock+0x17d/0x1f20 unregister_netdevice_many_notify+0x1141/0x1c30 default_device_exit_batch+0x3ee/0x520 ops_undo_list+0x2cc/0x8a0 cleanup_net+0x442/0x9c0 process_one_work+0x951/0x1ab0 worker_thread+0x5a6/0xd10 kthread+0x339/0x430 ret_from_fork+0x4a4/0x6f0 ret_from_fork_asm+0x1a/0x30 Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&dev_instance_lock_key#7); lock(&dev_instance_lock_key#6); lock(&dev_instance_lock_key#7); lock(&dev_instance_lock_key#6); *** DEADLOCK *** locks held by kworker/u256:1/326: 6, last CPU#6: #0: ff11000001c2b540 ((wq_completion)netns){+.+.}-{0:0}, at: process_one_work+0x117c/0x1ab0 #1: ffa0000001a3fd18 (net_cleanup_work){+.+.}-{0:0}, at: process_one_work+0x8ce/0x1ab0 #2: ffffffff98f53288 (pernet_ops_rwsem){++++}-{4:4}, at: cleanup_net+0xc1/0x9c0 #3: ffffffff98f6ede0 (rtnl_mutex){+.+.}-{4:4}, at: default_device_exit_batch+0x92/0x520 #4: ff1100001321ae28 (&dev_instance_lock_key#7){+.+.}-{4:4}, at: unregister_netdevice_many_notify+0x1141/0x1c30 We can't put all devices in the same class, that'd be too permissive. netdev_nl_queue_create_doit() and netdev_nl_bind_tx_doit() lock a virtual device (netkit) before a physical device, without rtnl_lock. We can never allow locking in the opposite order even under rtnl_lock. cmp_fn cannot enforce this sort of rule: lockdep keys its chain cache on the sequence of lock classes, so with a single class both orders hash to the same chain and only whichever happens first is validated. netdev_lock_cmp_fn() itself has another source of false-negatives. lockdep calls it from within __lock_acquire(), with the recursion counter already raised, so lock_is_held_type() always returns LOCK_STATE_UNKNOWN, which means lockdep_rtnl_is_held() always returns true / held. Use rtnl_is_locked(), which looks at the mutex directly and does work from that context. We may still miss a bad case if some other process is holding the lock, not us, but that's better than the 100% false negative rate of lockdep_rtnl_is_held(). One last thing, lockdep compares the address of the cmp function, so it can't be a static inline - that would work similarly to having separate classes, again. Move it to a source file. Tested by nesting two instance locks from a module, one scenario per boot since the first splat turns debug_locks off: first second rtnl reported ----------------------------------------------------------- virt->virt no recursive locking virt->virt yes - virt->phys no - virt->phys yes - phys->virt no - (records the edge) phys->virt yes - (records the edge) phys->phys no recursive locking phys->phys yes - virt->phys phys->virt no, no circular dependency virt->phys phys->virt no, yes circular dependency virt->phys phys->virt yes, no circular dependency virt->phys phys->virt yes, yes circular dependency phys->virt virt->phys no, no circular dependency phys->virt virt->phys yes, yes circular dependency virt->virt virt->virt yes, no recursive locking phys->phys phys->phys yes, no recursive locking (netkit and dummy stood in for the virtual devices, virtio_net and netdevsim for the physical ones.) Signed-off-by: Jakub Kicinski <kuba@kernel.org> Reviewed-by: Eric Dumazet <edumazet@google.com> Acked-by: Stanislav Fomichev <sdf@fomichev.me> Link: https://patch.msgid.link/20260926041832.1649675-1-kuba@kernel.org Signed-off-by: Paolo Abeni <pabeni@redhat.com>
142 lines
3.4 KiB
C
142 lines
3.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
|
|
#ifndef _NET_NETDEV_LOCK_H
|
|
#define _NET_NETDEV_LOCK_H
|
|
|
|
#include <linux/lockdep.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/rtnetlink.h>
|
|
|
|
static inline bool netdev_trylock(struct net_device *dev)
|
|
{
|
|
return mutex_trylock(&dev->lock);
|
|
}
|
|
|
|
static inline void netdev_assert_locked(const struct net_device *dev)
|
|
{
|
|
lockdep_assert_held(&dev->lock);
|
|
}
|
|
|
|
static inline void
|
|
netdev_assert_locked_or_invisible(const struct net_device *dev)
|
|
{
|
|
if (dev->reg_state == NETREG_REGISTERED ||
|
|
dev->reg_state == NETREG_UNREGISTERING)
|
|
netdev_assert_locked(dev);
|
|
}
|
|
|
|
static inline bool netdev_need_ops_lock(const struct net_device *dev)
|
|
{
|
|
bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops;
|
|
|
|
#if IS_ENABLED(CONFIG_NET_SHAPER)
|
|
ret |= !!dev->netdev_ops->net_shaper_ops;
|
|
#endif
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline void netdev_lock_ops(struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_lock(dev);
|
|
}
|
|
|
|
static inline void netdev_unlock_ops(struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_unlock(dev);
|
|
}
|
|
|
|
static inline void netdev_lock_ops_to_full(struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_assert_locked(dev);
|
|
else
|
|
netdev_lock(dev);
|
|
}
|
|
|
|
static inline void netdev_unlock_full_to_ops(struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_assert_locked(dev);
|
|
else
|
|
netdev_unlock(dev);
|
|
}
|
|
|
|
static inline void netdev_assert_locked_ops_compat(const struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
lockdep_assert_held(&dev->lock);
|
|
else
|
|
ASSERT_RTNL();
|
|
}
|
|
|
|
static inline void
|
|
netdev_assert_locked_ops_compat_or_invisible(const struct net_device *dev)
|
|
{
|
|
if (dev->reg_state == NETREG_REGISTERED ||
|
|
dev->reg_state == NETREG_UNREGISTERING)
|
|
netdev_assert_locked_ops_compat(dev);
|
|
}
|
|
|
|
static inline void netdev_assert_locked_ops(const struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_assert_locked(dev);
|
|
}
|
|
|
|
static inline void netdev_lock_ops_compat(struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_lock(dev);
|
|
else
|
|
rtnl_lock();
|
|
}
|
|
|
|
static inline void netdev_unlock_ops_compat(struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
netdev_unlock(dev);
|
|
else
|
|
rtnl_unlock();
|
|
}
|
|
|
|
/* Matching "ops protected" category from netdevice.h */
|
|
static inline int netdev_is_locked_ops_compat(const struct net_device *dev)
|
|
{
|
|
if (netdev_need_ops_lock(dev))
|
|
return lockdep_is_held(&dev->lock);
|
|
return lockdep_rtnl_is_held();
|
|
}
|
|
|
|
void netdev_set_instance_lock_class(struct net_device *dev);
|
|
|
|
#define netdev_lockdep_set_classes(dev) \
|
|
{ \
|
|
static struct lock_class_key qdisc_tx_busylock_key; \
|
|
static struct lock_class_key qdisc_xmit_lock_key; \
|
|
static struct lock_class_key dev_addr_list_lock_key; \
|
|
unsigned int i; \
|
|
\
|
|
(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \
|
|
lockdep_set_class(&(dev)->addr_list_lock, \
|
|
&dev_addr_list_lock_key); \
|
|
if (IS_ENABLED(CONFIG_PROVE_LOCKING)) \
|
|
netdev_set_instance_lock_class(dev); \
|
|
for (i = 0; i < (dev)->num_tx_queues; i++) \
|
|
lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \
|
|
&qdisc_xmit_lock_key); \
|
|
}
|
|
|
|
#define netdev_lock_dereference(p, dev) \
|
|
rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock))
|
|
|
|
#define netdev_ops_lock_dereference(p, dev) \
|
|
rcu_dereference_protected(p, netdev_is_locked_ops_compat(dev))
|
|
|
|
int netdev_debug_event(struct notifier_block *nb, unsigned long event,
|
|
void *ptr);
|
|
|
|
#endif
|