From 02c6be7d675b21d81f0ba3a524346850a8c0e3bf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Aug 2026 15:51:29 +0000 Subject: locking/lockdep: Invalidate stale class_cache entries for zapped classes 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: 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") Closes: https://lore.kernel.org/netdev/6a8c66dc.4d75e56a.c9a88.0050.GAE@google.com/T/#u Reported-by: syzbot+2d770620059281e225a4@syzkaller.appspotmail.com Assisted-by: Gemini:gemini-3.1-pro Signed-off-by: Eric Dumazet Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260824155129.676096-1-edumazet@google.com --- kernel/locking/lockdep.c | 50 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 42 insertions(+), 8 deletions(-) (limited to 'kernel/locking') 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 @@ out_unlock_set: 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); /* -- cgit v1.2.3 From 912edebe8501a36c6bedcef03bd238ab90a7e060 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 1 Sep 2026 15:54:51 +0200 Subject: futex: Provide rt_mutex_.*_schedule() equivalents for futex scheduling There is rt_mutex_{pre|post}_schedule() around rt_mutex_wait_proxy_lock() to ensure that sched_submit_work()/ sched_update_worker() is invoked before we schedule out and block on rt_mutex while waiting for it become available. The reason is that blocking on rt_mutex assigns a pi_waiter for the PI chain and sched_submit_work() will also assign a pi_waiter if it blocks on lock but a this point we already have a waiter assigned. We can't skip sched_submit_work() entirely because I/O relies on the fact that I/O queue is flushed while it blocks on a sleeping lock. Therefore sched_submit_work() is moved before we block on the lock. Sleeping lock in this context means mutex or rw_semaphore not spinlock_t on PREEMPT_RT. Because the mutex abstraction on PREEMPT_RT uses the same abstraction as the futex proxy lock, the futex code ended up using rt_mutex_{pre|post}_schedule(), too. Using it is/ was just to keep the task_struct::sched_rt_mutex assertion happy. Futex proxy lock is used only in the syscall context of a task. At this point it never got any I/O that needs to be flushed and it can't be a workqueue that needs to notify that it will be scheduled out. Therefore sched_submit_work() does nothing here. By mistake futex_wait_requeue_pi() -> rt_mutex_wait_proxy_lock() did not get the rt_mutex_{pre|post}_schedule() annotation. This was not noticed because in this callchain the lock is (usually) not contended and so rt_mutex_slowlock_block() does not schedule, triggering the assert. Adding rt_mutex_pre_schedule() here looks wrong (as noted by PeterZ) because at this point there is a pi_waiter recorded and invoking sched_submit_work() with a possible lock contention would be wrong. Add rt_mutex_futex_{pre|post}_schedule() which toggles the sched_rt_mutex assert and does not involve sched_submit_work(). Add asserts here to ensure that sched_submit_work() would do nothing. Use it only in futex proxy lock case which is rt_mutex_wait_proxy_lock(). Remove it from futex_lock_pi(). Fixes: d14f9e930b90 ("locking/rtmutex: Use rt_mutex specific scheduler helpers") Reported-by: Yao Kai Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260901135453.3121948-2-bigeasy@linutronix.de Closes: https://lore.kernel.org/all/20260717084922.4153317-2-yaokai34@huawei.com --- include/linux/sched/rt.h | 2 ++ kernel/futex/pi.c | 16 +++------------- kernel/locking/rtmutex_api.c | 2 ++ kernel/sched/core.c | 16 ++++++++++++++++ 4 files changed, 23 insertions(+), 13 deletions(-) (limited to 'kernel/locking') diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 4e3338103654..922935cc3383 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -52,8 +52,10 @@ static inline bool rt_or_dl_task_policy(struct task_struct *tsk) #ifdef CONFIG_RT_MUTEXES extern void rt_mutex_pre_schedule(void); +extern void rt_mutex_futex_pre_schedule(void); extern void rt_mutex_schedule(void); extern void rt_mutex_post_schedule(void); +extern void rt_mutex_futex_post_schedule(void); /* * Must hold either p->pi_lock or task_rq(p)->lock. diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index 88788e584ec8..98f1b962e59a 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -1070,17 +1070,11 @@ retry_private: * Caution; releasing @hb in-scope. The hb->lock is still locked * while the reference is dropped. The reference can not be dropped * after the unlock because if a user initiated resize is in progress - * then we might need to wake him. This can not be done after the - * rt_mutex_pre_schedule() invocation. The hb will remain valid because - * the thread, performing resize, will block on hb->lock during - * the requeue. + * then we might need to wake him. The hb will remain valid + * because the thread, performing resize, will block on + * hb->lock during the requeue. */ futex_private_hash_put(no_free_ptr(hbr.fph)); - /* - * Must be done before we enqueue the waiter, here is unfortunately - * under the hb lock, but that *should* work because it does nothing. - */ - rt_mutex_pre_schedule(); rt_mutex_init_waiter(&rt_waiter); @@ -1146,10 +1140,6 @@ cleanup: * the */ futex_q_lockptr_lock(&q); - /* - * Waiter is unqueued. - */ - rt_mutex_post_schedule(); no_block: /* * Fixup the pi_state owner and possibly acquire the lock if we diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 5d48d64725b1..eb18b094473c 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -423,6 +423,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, { int ret; + rt_mutex_futex_pre_schedule(); raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); @@ -433,6 +434,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, */ fixup_rt_mutex_waiters(lock, true); raw_spin_unlock_irq(&lock->wait_lock); + rt_mutex_futex_post_schedule(); return ret; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f78275192036..449ccd871be8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7637,6 +7637,17 @@ void rt_mutex_pre_schedule(void) sched_submit_work(current); } +/* + * Used within the futex syscall context, skips sched_submit_work() because none + * its work will be done. Asserts ensure that it is indeed the case. + */ +void rt_mutex_futex_pre_schedule(void) +{ + lockdep_assert(!(current->flags & (PF_WQ_WORKER | PF_IO_WORKER))); + lockdep_assert(!current->plug); + lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1)); +} + void rt_mutex_schedule(void) { lockdep_assert(current->sched_rt_mutex); @@ -7649,6 +7660,11 @@ void rt_mutex_post_schedule(void) lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); } +void rt_mutex_futex_post_schedule(void) +{ + lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); +} + /* * rt_mutex_setprio - set the current priority of a task * @p: task to boost -- cgit v1.2.3