[PATCH] locking/lockdep: Invalidate stale class_cache entries for zapped classes

[PATCH] locking/lockdep: Invalidate stale class_cache entries for zapped classes

[Eric Dumazet]

syzbot reported a lockdep splat hitting DEBUG_LOCKS_WARN_ON(1) in
hlock_class() due to an invalid class_idx:

  WARNING: kernel/locking/lockdep.c:238 at __lock_acquire+0x382/0x2cf0 kernel/locking/lockdep.c:5203
  Workqueue: wg-crypt-wg0 wg_packet_tx_worker
  RIP: 0010:hlock_class kernel/locking/lockdep.c:238 [inline]
  RIP: 0010:check_wait_context kernel/locking/lockdep.c:4870 [inline]
  RIP: 0010:__lock_acquire+0x389/0x2cf0 kernel/locking/lockdep.c:5203
  Call Trace:
   <IRQ>
   lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5886
   _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:173
   tcp_tsq_handler+0x29/0x200 net/ipv4/tcp_output.c:1291
   tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325
   ...

When a lock class is zapped (e.g. during module unload or key
unregistration), zap_class() clears the class's bit in
lock_classes_in_use and removes it from the class hash table.
However, existing lockdep_map instances embedded in data structures
may still retain a pointer to the zapped class in their class_cache[]
array.

When __lock_acquire() subsequently runs on such a lock, it finds
lock->class_cache[subclass] != NULL, skipping register_lock_class() and
assigning hlock->class_idx to the index of the zapped class. When
check_wait_context() or hlock_class() inspects the held_lock, it finds
!test_bit(class_idx, lock_classes_in_use) and warns. Furthermore, if
the zapped slot is subsequently re-allocated to an unrelated lock key,
the stale class_cache entry would erroneously match the unrelated class
(ABA issue).

Add lock_class_cache_is_valid() to validate that the cached class is
within lock_classes bounds, still allocated in lock_classes_in_use
(using uninstrumented arch_test_bit() in __always_inline context so it
is safe in noinstr contexts like match_held_lock()), and that class->key
matches the expected subkey (taking lockdep_set_subclass() overrides into
account). Also use READ_ONCE()/WRITE_ONCE() when accessing class_cache[].
If the entry is invalid or stale, fall back to register_lock_class() /
look_up_lock_class().

Fixes: a0b0fd53e1e6 ("locking/lockdep: Free lock classes that are no longer in use")
Reported-by: syzbot+2d770620059281e225a4@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6a8c66dc.4d75e56a.c9a88.0050.GAE@google.com/T/#u
Assisted-by: Gemini:gemini-3.1-pro
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 kernel/locking/lockdep.c | 50 +++++++++++++++++++++++++++++++++-------
 1 file changed, 42 insertions(+), 8 deletions(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 25d77d4a1061..763f79806bd8 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -963,6 +963,34 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 	return NULL;
 }
 
+static __always_inline bool lock_class_cache_is_valid(const struct lockdep_map *lock,
+						      const struct lock_class *class,
+						      unsigned int subclass)
+{
+	unsigned int class_subclass;
+
+	if (!class)
+		return false;
+
+	if (unlikely(class < lock_classes || class >= lock_classes + MAX_LOCKDEP_KEYS))
+		return false;
+
+	if (unlikely(!arch_test_bit(class - lock_classes, lock_classes_in_use)))
+		return false;
+
+	if (unlikely(!lock->key))
+		return false;
+
+	class_subclass = subclass ? subclass : class->subclass;
+	if (unlikely(class_subclass >= MAX_LOCKDEP_SUBCLASSES))
+		return false;
+
+	if (unlikely(READ_ONCE(class->key) != lock->key->subkeys + class_subclass))
+		return false;
+
+	return true;
+}
+
 /*
  * Static locks do not have their class-keys yet - for them the key is
  * the lock object itself. If the lock is in the per cpu area, the
@@ -1395,9 +1423,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 out_set_class_cache:
 	if (!subclass || force)
-		lock->class_cache[0] = class;
+		WRITE_ONCE(lock->class_cache[0], class);
 	else if (subclass < NR_LOCKDEP_CACHING_CLASSES)
-		lock->class_cache[subclass] = class;
+		WRITE_ONCE(lock->class_cache[subclass], class);
 
 	/*
 	 * Hash collision, did we smoke some? We found a class with a matching
@@ -4957,7 +4985,7 @@ void lockdep_init_map_type(struct lockdep_map *lock, const char *name,
 	int i;
 
 	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
-		lock->class_cache[i] = NULL;
+		WRITE_ONCE(lock->class_cache[i], NULL);
 
 #ifdef CONFIG_LOCK_STAT
 	lock->cpu = raw_smp_processor_id();
@@ -5022,12 +5050,15 @@ EXPORT_SYMBOL_GPL(__lockdep_no_track__);
 void lockdep_set_lock_cmp_fn(struct lockdep_map *lock, lock_cmp_fn cmp_fn,
 			     lock_print_fn print_fn)
 {
-	struct lock_class *class = lock->class_cache[0];
+	struct lock_class *class = READ_ONCE(lock->class_cache[0]);
 	unsigned long flags;
 
 	raw_local_irq_save(flags);
 	lockdep_recursion_inc();
 
+	if (!lock_class_cache_is_valid(lock, class, 0))
+		class = NULL;
+
 	if (!class)
 		class = register_lock_class(lock, 0, 0);
 
@@ -5119,8 +5150,11 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (DEBUG_LOCKS_WARN_ON(subclass >= MAX_LOCKDEP_SUBCLASSES))
 		return 0;
 
-	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
-		class = lock->class_cache[subclass];
+	if (subclass < NR_LOCKDEP_CACHING_CLASSES) {
+		class = READ_ONCE(lock->class_cache[subclass]);
+		if (!lock_class_cache_is_valid(lock, class, subclass))
+			class = NULL;
+	}
 	/*
 	 * Not cached?
 	 */
@@ -5323,9 +5357,9 @@ static noinstr int match_held_lock(const struct held_lock *hlock,
 		return 1;
 
 	if (hlock->references) {
-		const struct lock_class *class = lock->class_cache[0];
+		const struct lock_class *class = READ_ONCE(lock->class_cache[0]);
 
-		if (!class)
+		if (!lock_class_cache_is_valid(lock, class, 0))
 			class = look_up_lock_class(lock, 0);
 
 		/*

base-commit: 0a0d1d55dad570724bf8c7ea83409639cfb4be9b
-- 
2.55.0.766.g2966f0265a-goog

Re: [PATCH] locking/lockdep: Invalidate stale class_cache entries for zapped classes

[Hillf Danton]

#syz test

syzbot reported a lockdep splat hitting DEBUG_LOCKS_WARN_ON(1) in
hlock_class() due to an invalid class_idx:

  WARNING: kernel/locking/lockdep.c:238 at __lock_acquire+0x382/0x2cf0 kernel/locking/lockdep.c:5203
  Workqueue: wg-crypt-wg0 wg_packet_tx_worker
  RIP: 0010:hlock_class kernel/locking/lockdep.c:238 [inline]
  RIP: 0010:check_wait_context kernel/locking/lockdep.c:4870 [inline]
  RIP: 0010:__lock_acquire+0x389/0x2cf0 kernel/locking/lockdep.c:5203
  Call Trace:
   <IRQ>
   lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5886
   _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:173
   tcp_tsq_handler+0x29/0x200 net/ipv4/tcp_output.c:1291
   tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325
   ...

When a lock class is zapped (e.g. during module unload or key
unregistration), zap_class() clears the class's bit in
lock_classes_in_use and removes it from the class hash table.
However, existing lockdep_map instances embedded in data structures
may still retain a pointer to the zapped class in their class_cache[]
array.

When __lock_acquire() subsequently runs on such a lock, it finds
lock->class_cache[subclass] != NULL, skipping register_lock_class() and
assigning hlock->class_idx to the index of the zapped class. When
check_wait_context() or hlock_class() inspects the held_lock, it finds
!test_bit(class_idx, lock_classes_in_use) and warns. Furthermore, if
the zapped slot is subsequently re-allocated to an unrelated lock key,
the stale class_cache entry would erroneously match the unrelated class
(ABA issue).

Add lock_class_cache_is_valid() to validate that the cached class is
within lock_classes bounds, still allocated in lock_classes_in_use
(using uninstrumented arch_test_bit() in __always_inline context so it
is safe in noinstr contexts like match_held_lock()), and that class->key
matches the expected subkey (taking lockdep_set_subclass() overrides into
account). Also use READ_ONCE()/WRITE_ONCE() when accessing class_cache[].
If the entry is invalid or stale, fall back to register_lock_class() /
look_up_lock_class().

Fixes: a0b0fd53e1e6 ("locking/lockdep: Free lock classes that are no longer in use")
Reported-by: syzbot+2d770620059281e225a4@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6a8c66dc.4d75e56a.c9a88.0050.GAE@google.com/T/#u
Assisted-by: Gemini:gemini-3.1-pro
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 kernel/locking/lockdep.c | 50 +++++++++++++++++++++++++++++++++-------
 1 file changed, 42 insertions(+), 8 deletions(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 25d77d4a1061..763f79806bd8 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -963,6 +963,34 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 	return NULL;
 }
 
+static __always_inline bool lock_class_cache_is_valid(const struct lockdep_map *lock,
+						      const struct lock_class *class,
+						      unsigned int subclass)
+{
+	unsigned int class_subclass;
+
+	if (!class)
+		return false;
+
+	if (unlikely(class < lock_classes || class >= lock_classes + MAX_LOCKDEP_KEYS))
+		return false;
+
+	if (unlikely(!arch_test_bit(class - lock_classes, lock_classes_in_use)))
+		return false;
+
+	if (unlikely(!lock->key))
+		return false;
+
+	class_subclass = subclass ? subclass : class->subclass;
+	if (unlikely(class_subclass >= MAX_LOCKDEP_SUBCLASSES))
+		return false;
+
+	if (unlikely(READ_ONCE(class->key) != lock->key->subkeys + class_subclass))
+		return false;
+
+	return true;
+}
+
 /*
  * Static locks do not have their class-keys yet - for them the key is
  * the lock object itself. If the lock is in the per cpu area, the
@@ -1395,9 +1423,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 out_set_class_cache:
 	if (!subclass || force)
-		lock->class_cache[0] = class;
+		WRITE_ONCE(lock->class_cache[0], class);
 	else if (subclass < NR_LOCKDEP_CACHING_CLASSES)
-		lock->class_cache[subclass] = class;
+		WRITE_ONCE(lock->class_cache[subclass], class);
 
 	/*
 	 * Hash collision, did we smoke some? We found a class with a matching
@@ -4957,7 +4985,7 @@ void lockdep_init_map_type(struct lockdep_map *lock, const char *name,
 	int i;
 
 	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
-		lock->class_cache[i] = NULL;
+		WRITE_ONCE(lock->class_cache[i], NULL);
 
 #ifdef CONFIG_LOCK_STAT
 	lock->cpu = raw_smp_processor_id();
@@ -5022,12 +5050,15 @@ EXPORT_SYMBOL_GPL(__lockdep_no_track__);
 void lockdep_set_lock_cmp_fn(struct lockdep_map *lock, lock_cmp_fn cmp_fn,
 			     lock_print_fn print_fn)
 {
-	struct lock_class *class = lock->class_cache[0];
+	struct lock_class *class = READ_ONCE(lock->class_cache[0]);
 	unsigned long flags;
 
 	raw_local_irq_save(flags);
 	lockdep_recursion_inc();
 
+	if (!lock_class_cache_is_valid(lock, class, 0))
+		class = NULL;
+
 	if (!class)
 		class = register_lock_class(lock, 0, 0);
 
@@ -5119,8 +5150,11 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (DEBUG_LOCKS_WARN_ON(subclass >= MAX_LOCKDEP_SUBCLASSES))
 		return 0;
 
-	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
-		class = lock->class_cache[subclass];
+	if (subclass < NR_LOCKDEP_CACHING_CLASSES) {
+		class = READ_ONCE(lock->class_cache[subclass]);
+		if (!lock_class_cache_is_valid(lock, class, subclass))
+			class = NULL;
+	}
 	/*
 	 * Not cached?
 	 */
@@ -5323,9 +5357,9 @@ static noinstr int match_held_lock(const struct held_lock *hlock,
 		return 1;
 
 	if (hlock->references) {
-		const struct lock_class *class = lock->class_cache[0];
+		const struct lock_class *class = READ_ONCE(lock->class_cache[0]);
 
-		if (!class)
+		if (!lock_class_cache_is_valid(lock, class, 0))
 			class = look_up_lock_class(lock, 0);
 
 		/*

base-commit: 0a0d1d55dad570724bf8c7ea83409639cfb4be9b
-- 
2.55.0.766.g2966f0265a-goog

Re: [syzbot] [net?] WARNING: locking bug in tcp_tsq_handler

[syzbot]

Hello,

syzbot has tested the proposed patch but the reproducer is still triggering an issue:
WARNING in tcp_tsq_handler

------------[ cut here ]------------
!lockdep_sock_is_held(sk) && debug_locks
WARNING: ./include/net/sock.h:1799 at sock_owned_by_me include/net/sock.h:1799 [inline], CPU#1: kworker/1:0/24
WARNING: ./include/net/sock.h:1799 at sock_owned_by_user include/net/sock.h:1812 [inline], CPU#1: kworker/1:0/24
WARNING: ./include/net/sock.h:1799 at tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292, CPU#1: kworker/1:0/24
Modules linked in:
CPU: 1 UID: 0 PID: 24 Comm: kworker/1:0 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/24/2026
Workqueue: wg-crypt-wg0 wg_packet_tx_worker
RIP: 0010:sock_owned_by_me include/net/sock.h:1799 [inline]
RIP: 0010:sock_owned_by_user include/net/sock.h:1812 [inline]
RIP: 0010:tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292
Code: 30 96 96 01 e8 7b b3 7a f7 be 02 00 00 00 eb 0a e8 6f b3 7a f7 be 01 00 00 00 4c 89 ff e8 82 3e 8f fa eb d0 e8 5b b3 7a f7 90 <0f> 0b 90 e9 fd fe ff ff 44 89 f9 80 e1 07 80 c1 03 38 c1 0f 8c 07
RSP: 0018:ffffc90000a08bb0 EFLAGS: 00010246
RAX: ffffffff8a4c8ba5 RBX: ffff88802db742d0 RCX: ffff88801e6e5dc0
RDX: 8000000000000100 RSI: 0000000000000100 RDI: 0000000000000000
RBP: 0000000000000001 R08: 0000000000000100 R09: 0000000000000004
R10: dffffc0000000000 R11: fffff52000141164 R12: dffffc0000000000
R13: ffffc90000a08c20 R14: ffff88802db74100 R15: ffff88802db74100
FS:  0000000000000000(0000) GS:ffff888124df1000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005635f5ecdbd8 CR3: 0000000072ba6000 CR4: 00000000003526f0
Call Trace:
 <IRQ>
 tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325
 process_one_work kernel/workqueue.c:3387 [inline]
 process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
 bh_worker+0x451/0x870 kernel/workqueue.c:3773
 tasklet_action+0xc/0x70 kernel/softirq.c:997
 handle_softirqs+0x226/0x860 kernel/softirq.c:645
 do_softirq+0x77/0xd0 kernel/softirq.c:546
 </IRQ>
 <TASK>
 __local_bh_enable_ip+0x100/0x140 kernel/softirq.c:473
 wg_socket_send_skb_to_peer+0x16b/0x1d0 drivers/net/wireguard/socket.c:183
 wg_packet_create_data_done drivers/net/wireguard/send.c:251 [inline]
 wg_packet_tx_worker+0x1c8/0x7e0 drivers/net/wireguard/send.c:276
 process_one_work kernel/workqueue.c:3387 [inline]
 process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
 worker_thread+0xa47/0xfb0 kernel/workqueue.c:3551
 kthread+0x38b/0x480 kernel/kthread.c:436
 ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>


Tested on:

commit:         66498c75 Merge tag 'dmaengine-7.3-rc1' of git://git.ke..
git tree:       upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=10adc979580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=e9ce1d694820ba2b
dashboard link: https://syzkaller.appspot.com/bug?extid=2d770620059281e225a4
compiler:       Debian clang version 22.1.8 (++20260613092233+e80beda6e255-1~exp1~20260613092250.77), Debian LLD 22.1.8
patch:          https://syzkaller.appspot.com/x/patch.diff?x=1497b549580000

Re: [syzbot] [net?] WARNING: locking bug in tcp_tsq_handler

[Hillf Danton]

> Date: Mon, 24 Aug 2026 17:59:01 -0700	[thread overview]
> Hello,
> 
> syzbot has tested the proposed patch but the reproducer is still triggering an issue:
> WARNING in tcp_tsq_handler
> 
Fine, another case of HBC, half baked croissant, thanks to syzbot.


> ------------[ cut here ]------------
> !lockdep_sock_is_held(sk) && debug_locks
> WARNING: ./include/net/sock.h:1799 at sock_owned_by_me include/net/sock.h:1799 [inline], CPU#1: kworker/1:0/24
> WARNING: ./include/net/sock.h:1799 at sock_owned_by_user include/net/sock.h:1812 [inline], CPU#1: kworker/1:0/24
> WARNING: ./include/net/sock.h:1799 at tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292, CPU#1: kworker/1:0/24
> Modules linked in:
> CPU: 1 UID: 0 PID: 24 Comm: kworker/1:0 Not tainted syzkaller #0 PREEMPT(full) 
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/24/2026
> Workqueue: wg-crypt-wg0 wg_packet_tx_worker
> RIP: 0010:sock_owned_by_me include/net/sock.h:1799 [inline]
> RIP: 0010:sock_owned_by_user include/net/sock.h:1812 [inline]
> RIP: 0010:tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292
> Code: 30 96 96 01 e8 7b b3 7a f7 be 02 00 00 00 eb 0a e8 6f b3 7a f7 be 01 00 00 00 4c 89 ff e8 82 3e 8f fa eb d0 e8 5b b3 7a f7 90 <0f> 0b 90 e9 fd fe ff ff 44 89 f9 80 e1 07 80 c1 03 38 c1 0f 8c 07
> RSP: 0018:ffffc90000a08bb0 EFLAGS: 00010246
> RAX: ffffffff8a4c8ba5 RBX: ffff88802db742d0 RCX: ffff88801e6e5dc0
> RDX: 8000000000000100 RSI: 0000000000000100 RDI: 0000000000000000
> RBP: 0000000000000001 R08: 0000000000000100 R09: 0000000000000004
> R10: dffffc0000000000 R11: fffff52000141164 R12: dffffc0000000000
> R13: ffffc90000a08c20 R14: ffff88802db74100 R15: ffff88802db74100
> FS:  0000000000000000(0000) GS:ffff888124df1000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00005635f5ecdbd8 CR3: 0000000072ba6000 CR4: 00000000003526f0
> Call Trace:
>  <IRQ>
>  tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325
>  process_one_work kernel/workqueue.c:3387 [inline]
>  process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
>  bh_worker+0x451/0x870 kernel/workqueue.c:3773
>  tasklet_action+0xc/0x70 kernel/softirq.c:997
>  handle_softirqs+0x226/0x860 kernel/softirq.c:645
>  do_softirq+0x77/0xd0 kernel/softirq.c:546
>  </IRQ>
>  <TASK>
>  __local_bh_enable_ip+0x100/0x140 kernel/softirq.c:473
>  wg_socket_send_skb_to_peer+0x16b/0x1d0 drivers/net/wireguard/socket.c:183
>  wg_packet_create_data_done drivers/net/wireguard/send.c:251 [inline]
>  wg_packet_tx_worker+0x1c8/0x7e0 drivers/net/wireguard/send.c:276
>  process_one_work kernel/workqueue.c:3387 [inline]
>  process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
>  worker_thread+0xa47/0xfb0 kernel/workqueue.c:3551
>  kthread+0x38b/0x480 kernel/kthread.c:436
>  ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158
>  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
>  </TASK>
> 
> 
> Tested on:
> 
> commit:         66498c75 Merge tag 'dmaengine-7.3-rc1' of git://git.ke..
> git tree:       upstream
> console output: https://syzkaller.appspot.com/x/log.txt?x=10adc979580000
> kernel config:  https://syzkaller.appspot.com/x/.config?x=e9ce1d694820ba2b
> dashboard link: https://syzkaller.appspot.com/bug?extid=2d770620059281e225a4
> compiler:       Debian clang version 22.1.8 (++20260613092233+e80beda6e255-1~exp1~20260613092250.77), Debian LLD 22.1.8
> patch:          https://syzkaller.appspot.com/x/patch.diff?x=1497b549580000

Re: [syzbot] [net?] WARNING: locking bug in tcp_tsq_handler

[Eric Dumazet]

On Tue, Aug 25, 2026 at 2:59 AM syzbot
<syzbot+2d770620059281e225a4@syzkaller.appspotmail.com> wrote:
>
> Hello,
>
> syzbot has tested the proposed patch but the reproducer is still triggering an issue:
> WARNING in tcp_tsq_handler
>
> ------------[ cut here ]------------
> !lockdep_sock_is_held(sk) && debug_locks
> WARNING: ./include/net/sock.h:1799 at sock_owned_by_me include/net/sock.h:1799 [inline], CPU#1: kworker/1:0/24
> WARNING: ./include/net/sock.h:1799 at sock_owned_by_user include/net/sock.h:1812 [inline], CPU#1: kworker/1:0/24
> WARNING: ./include/net/sock.h:1799 at tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292, CPU#1: kworker/1:0/24

Note this is a different warning.

This one might have been added in nvme-tcp in commit

commit 19bdb70c77d3b24239a453291299b64040bdba86
Author: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date:   Thu Jun 4 11:32:08 2026 +0900

    nvme-tcp: lockdep: use dynamic lockdep keys per socket instance

The authors assumed that __fput_sync(queue->sock->file) in
nvme_tcp_free_queue() synchronously destroys the socket, so they
unregistered the keys immediately:

__fput_sync(queue->sock->file);
queue->sock = NULL;
...
#ifdef CONFIG_DEBUG_LOCK_ALLOC
lockdep_unregister_key(&queue->nvme_tcp_sk_key);
lockdep_unregister_key(&queue->nvme_tcp_slock_key);
#endif

However, a TCP socket's lifetime is asynchronous:
in-flight skbs (e.g. buffered in a qdisc or device ring) hold
references on sk->sk_wmem_alloc.

When those packets are freed later, tcp_wfree() puts sk on TSQ and
tcp_tsq_handler(sk)
acquires bh_lock_sock(sk) on a socket whose lockdep key has already
been unregistered and zapped.

All other kernel storage/networking clients (sunrpc, nbd, cifs,
iscsi_tcp, rxe, siw) use static lockdep keys without issue.

> Modules linked in:
> CPU: 1 UID: 0 PID: 24 Comm: kworker/1:0 Not tainted syzkaller #0 PREEMPT(full)
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/24/2026
> Workqueue: wg-crypt-wg0 wg_packet_tx_worker
> RIP: 0010:sock_owned_by_me include/net/sock.h:1799 [inline]
> RIP: 0010:sock_owned_by_user include/net/sock.h:1812 [inline]
> RIP: 0010:tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292
> Code: 30 96 96 01 e8 7b b3 7a f7 be 02 00 00 00 eb 0a e8 6f b3 7a f7 be 01 00 00 00 4c 89 ff e8 82 3e 8f fa eb d0 e8 5b b3 7a f7 90 <0f> 0b 90 e9 fd fe ff ff 44 89 f9 80 e1 07 80 c1 03 38 c1 0f 8c 07
> RSP: 0018:ffffc90000a08bb0 EFLAGS: 00010246
> RAX: ffffffff8a4c8ba5 RBX: ffff88802db742d0 RCX: ffff88801e6e5dc0
> RDX: 8000000000000100 RSI: 0000000000000100 RDI: 0000000000000000
> RBP: 0000000000000001 R08: 0000000000000100 R09: 0000000000000004
> R10: dffffc0000000000 R11: fffff52000141164 R12: dffffc0000000000
> R13: ffffc90000a08c20 R14: ffff88802db74100 R15: ffff88802db74100
> FS:  0000000000000000(0000) GS:ffff888124df1000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00005635f5ecdbd8 CR3: 0000000072ba6000 CR4: 00000000003526f0
> Call Trace:
>  <IRQ>
>  tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325
>  process_one_work kernel/workqueue.c:3387 [inline]
>  process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
>  bh_worker+0x451/0x870 kernel/workqueue.c:3773
>  tasklet_action+0xc/0x70 kernel/softirq.c:997
>  handle_softirqs+0x226/0x860 kernel/softirq.c:645
>  do_softirq+0x77/0xd0 kernel/softirq.c:546
>  </IRQ>
>  <TASK>
>  __local_bh_enable_ip+0x100/0x140 kernel/softirq.c:473
>  wg_socket_send_skb_to_peer+0x16b/0x1d0 drivers/net/wireguard/socket.c:183
>  wg_packet_create_data_done drivers/net/wireguard/send.c:251 [inline]
>  wg_packet_tx_worker+0x1c8/0x7e0 drivers/net/wireguard/send.c:276
>  process_one_work kernel/workqueue.c:3387 [inline]
>  process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
>  worker_thread+0xa47/0xfb0 kernel/workqueue.c:3551
>  kthread+0x38b/0x480 kernel/kthread.c:436
>  ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158
>  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
>  </TASK>
>
>
> Tested on:
>
> commit:         66498c75 Merge tag 'dmaengine-7.3-rc1' of git://git.ke..
> git tree:       upstream
> console output: https://syzkaller.appspot.com/x/log.txt?x=10adc979580000
> kernel config:  https://syzkaller.appspot.com/x/.config?x=e9ce1d694820ba2b
> dashboard link: https://syzkaller.appspot.com/bug?extid=2d770620059281e225a4
> compiler:       Debian clang version 22.1.8 (++20260613092233+e80beda6e255-1~exp1~20260613092250.77), Debian LLD 22.1.8
> patch:          https://syzkaller.appspot.com/x/patch.diff?x=1497b549580000
>

Re: [syzbot] [net?] WARNING: locking bug in tcp_tsq_handler

[Eric Dumazet]

On Tue, Aug 25, 2026 at 3:27 AM Eric Dumazet <edumazet@google.com> wrote:
>
> On Tue, Aug 25, 2026 at 2:59 AM syzbot
> <syzbot+2d770620059281e225a4@syzkaller.appspotmail.com> wrote:
> >
> > Hello,
> >
> > syzbot has tested the proposed patch but the reproducer is still triggering an issue:
> > WARNING in tcp_tsq_handler
> >
> > ------------[ cut here ]------------
> > !lockdep_sock_is_held(sk) && debug_locks
> > WARNING: ./include/net/sock.h:1799 at sock_owned_by_me include/net/sock.h:1799 [inline], CPU#1: kworker/1:0/24
> > WARNING: ./include/net/sock.h:1799 at sock_owned_by_user include/net/sock.h:1812 [inline], CPU#1: kworker/1:0/24
> > WARNING: ./include/net/sock.h:1799 at tcp_tsq_handler+0x1a6/0x200 net/ipv4/tcp_output.c:1292, CPU#1: kworker/1:0/24
>
> Note this is a different warning.
>
> This one might have been added in nvme-tcp in commit
>
> commit 19bdb70c77d3b24239a453291299b64040bdba86
> Author: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
> Date:   Thu Jun 4 11:32:08 2026 +0900
>
>     nvme-tcp: lockdep: use dynamic lockdep keys per socket instance
>
> The authors assumed that __fput_sync(queue->sock->file) in
> nvme_tcp_free_queue() synchronously destroys the socket, so they
> unregistered the keys immediately:
>
> __fput_sync(queue->sock->file);
> queue->sock = NULL;
> ...
> #ifdef CONFIG_DEBUG_LOCK_ALLOC
> lockdep_unregister_key(&queue->nvme_tcp_sk_key);
> lockdep_unregister_key(&queue->nvme_tcp_slock_key);
> #endif
>
> However, a TCP socket's lifetime is asynchronous:
> in-flight skbs (e.g. buffered in a qdisc or device ring) hold
> references on sk->sk_wmem_alloc.
>
> When those packets are freed later, tcp_wfree() puts sk on TSQ and
> tcp_tsq_handler(sk)
> acquires bh_lock_sock(sk) on a socket whose lockdep key has already
> been unregistered and zapped.
>
> All other kernel storage/networking clients (sunrpc, nbd, cifs,
> iscsi_tcp, rxe, siw) use static lockdep keys without issue.
>

I think 19bdb70c77d3 should be reverted.

We can change TCP to use sk_gfp_mask(sk, GFP_ATOMIC) instead of
gfp_any() in tcp_disconnect()

This ensures tcp_disconnect() respects sk->sk_allocation = GFP_ATOMIC
and never acquires fs_reclaim under sk_lock.

WDYT?

[syzbot] [net?] WARNING: locking bug in tcp_tsq_handler

[syzbot]

Hello,

syzbot found the following issue on:

HEAD commit:    388b607d107c Merge tag 'efi-next-for-v7.3' of git://git.ke..
git tree:       upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=10f98979580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=335632b21d0ce540
dashboard link: https://syzkaller.appspot.com/bug?extid=2d770620059281e225a4
compiler:       Debian clang version 22.1.8 (++20260613092233+e80beda6e255-1~exp1~20260613092250.77), Debian LLD 22.1.8
syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=133c3549580000

Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/20c420e92df0/disk-388b607d.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/82f836a86dcc/vmlinux-388b607d.xz
kernel image: https://storage.googleapis.com/syzbot-assets/c3b00ac47be8/bzImage-388b607d.xz

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+2d770620059281e225a4@syzkaller.appspotmail.com

------------[ cut here ]------------
DEBUG_LOCKS_WARN_ON(1)
WARNING: kernel/locking/lockdep.c:238 at hlock_class kernel/locking/lockdep.c:238 [inline], CPU#1: kworker/1:0/24
WARNING: kernel/locking/lockdep.c:238 at check_wait_context kernel/locking/lockdep.c:4870 [inline], CPU#1: kworker/1:0/24
WARNING: kernel/locking/lockdep.c:238 at __lock_acquire+0x382/0x2cf0 kernel/locking/lockdep.c:5203, CPU#1: kworker/1:0/24
Modules linked in:
CPU: 1 UID: 0 PID: 24 Comm: kworker/1:0 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/24/2026
Workqueue: wg-crypt-wg0 wg_packet_tx_worker
RIP: 0010:hlock_class kernel/locking/lockdep.c:238 [inline]
RIP: 0010:check_wait_context kernel/locking/lockdep.c:4870 [inline]
RIP: 0010:__lock_acquire+0x389/0x2cf0 kernel/locking/lockdep.c:5203
Code: 83 3d fa 48 f9 18 00 75 27 90 e8 b2 88 35 03 85 c0 74 1c 83 3d eb 3f d7 0e 00 75 13 48 8d 3d 1e 43 da 0e 48 c7 c6 8f 4c 59 8e <67> 48 0f b9 3a 90 31 c0 0f b6 98 c4 00 00 00 41 8b 45 20 25 ff 1f
RSP: 0018:ffffc90000a089b8 EFLAGS: 00010046
RAX: 0000000000000001 RBX: 0000000000042000 RCX: ffff88801eaaddc0
RDX: 8000000000000100 RSI: ffffffff8e594c8f RDI: ffffffff907cef80
RBP: 0000000000000001 R08: 0000000000000100 R09: 1ffffffff20f3d88
R10: dffffc0000000000 R11: fffffbfff20f3d89 R12: 0000000000000949
R13: ffff88801eaaea08 R14: ffff88801eaaddc0 R15: ffff88801eaae968
FS:  0000000000000000(0000) GS:ffff888124df4000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f390df782c0 CR3: 000000007747a000 CR4: 00000000003526f0
Call Trace:
 <IRQ>
 lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5886
 __raw_spin_lock include/linux/spinlock_api_smp.h:190 [inline]
 _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:173
 spin_lock include/linux/spinlock.h:347 [inline]
 tcp_tsq_handler+0x29/0x200 net/ipv4/tcp_output.c:1291
 tcp_tsq_workfn+0x384/0x410 net/ipv4/tcp_output.c:1325
 process_one_work kernel/workqueue.c:3387 [inline]
 process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
 bh_worker+0x451/0x870 kernel/workqueue.c:3773
 tasklet_action+0xc/0x70 kernel/softirq.c:997
 handle_softirqs+0x226/0x860 kernel/softirq.c:645
 do_softirq+0x77/0xd0 kernel/softirq.c:546
 </IRQ>
 <TASK>
 __local_bh_enable_ip+0x100/0x140 kernel/softirq.c:473
 wg_socket_send_skb_to_peer+0x16b/0x1d0 drivers/net/wireguard/socket.c:183
 wg_packet_create_data_done drivers/net/wireguard/send.c:251 [inline]
 wg_packet_tx_worker+0x1c8/0x7e0 drivers/net/wireguard/send.c:276
 process_one_work kernel/workqueue.c:3387 [inline]
 process_scheduled_works+0xc3d/0x1630 kernel/workqueue.c:3470
 worker_thread+0xa47/0xfb0 kernel/workqueue.c:3551
 kthread+0x38b/0x480 kernel/kthread.c:436
 ret_from_fork+0x514/0xb70 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>
----------------
Code disassembly (best guess):
   0:	83 3d fa 48 f9 18 00 	cmpl   $0x0,0x18f948fa(%rip)        # 0x18f94901
   7:	75 27                	jne    0x30
   9:	90                   	nop
   a:	e8 b2 88 35 03       	call   0x33588c1
   f:	85 c0                	test   %eax,%eax
  11:	74 1c                	je     0x2f
  13:	83 3d eb 3f d7 0e 00 	cmpl   $0x0,0xed73feb(%rip)        # 0xed74005
  1a:	75 13                	jne    0x2f
  1c:	48 8d 3d 1e 43 da 0e 	lea    0xeda431e(%rip),%rdi        # 0xeda4341
  23:	48 c7 c6 8f 4c 59 8e 	mov    $0xffffffff8e594c8f,%rsi
* 2a:	67 48 0f b9 3a       	ud1    (%edx),%rdi <-- trapping instruction
  2f:	90                   	nop
  30:	31 c0                	xor    %eax,%eax
  32:	0f b6 98 c4 00 00 00 	movzbl 0xc4(%rax),%ebx
  39:	41 8b 45 20          	mov    0x20(%r13),%eax
  3d:	25                   	.byte 0x25
  3e:	ff 1f                	lcall  *(%rdi)


---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.

syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.

If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title

If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.

If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)

If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report

If you want to undo deduplication, reply with:
#syz undup