Merge tag 'locking-urgent-2026-09-06' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fixes from Ingo Molnar:

 - Fix a softirq processing delay bug in local_interrupt_disable(),
   which should mostly only affect the Rust runtime (Boqun Feng)

 - Remove the hardirq_disable_count() function which caused the
   previous bug and is now unused & unnecessary (Boqun Feng)

 - lockdep: Invalidate stale class_cache entries for zapped classes
   (Eric Dumazet)

 - Fix rt_mutex specific futex scheduling helpers
   (Sebastian Andrzej Siewior)

 - Fix rcuwait use-after-free race during futex requeue PI (Yao Kai)

* tag 'locking-urgent-2026-09-06' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  futex: Prevent rcuwait use-after-free during requeue PI
  futex: Provide rt_mutex_.*_schedule() equivalents for futex scheduling
  locking/lockdep: Invalidate stale class_cache entries for zapped classes
  preempt: Remove hardirq_disable_count()
  interrupt: Disable interrupt before modifying hardirq_disable counter

9 files changed, 90 insertions, 51 deletions

diff --git a/include/linux/interrupt_rc.h b/include/linux/interrupt_rc.h
index b9a7f05ecf42..a9ed937a80e7 100644
--- a/include/linux/interrupt_rc.h
+++ b/include/linux/interrupt_rc.h
@@ -20,11 +20,8 @@
 /* Per-CPU interrupt disabling state for local_interrupt_{disable,enable}(). */
 DECLARE_PER_CPU(unsigned long, local_interrupt_disable_state);
 
-static __always_inline void __local_interrupt_disable(void)
+static __always_inline void __local_interrupt_save_state(unsigned long flags)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
 	raw_cpu_write(local_interrupt_disable_state, flags);
 }
 
@@ -36,9 +33,9 @@ static __always_inline void __local_interrupt_enable(void)
 }
 
 #ifndef INSTANTIATE_EXPORTED_INTERRUPT_DISABLE
-static __always_inline void _local_interrupt_disable(void)
+static __always_inline void _local_interrupt_save_state(unsigned long flags)
 {
-	__local_interrupt_disable();
+	__local_interrupt_save_state(flags);
 }
 
 static __always_inline void _local_interrupt_enable(void)
@@ -46,27 +43,30 @@ static __always_inline void _local_interrupt_enable(void)
 	__local_interrupt_enable();
 }
 #else
-extern void _local_interrupt_disable(void);
+extern void _local_interrupt_save_state(unsigned long flags);
 extern void _local_interrupt_enable(void);
 #endif
 
 #else /* !MODULE */
-extern void _local_interrupt_disable(void);
+extern void _local_interrupt_save_state(unsigned long flags);
 extern void _local_interrupt_enable(void);
 #endif /* !MODULE */
 
+#define hardirq_disable_enter()	__preempt_count_add_return(HARDIRQ_DISABLE_OFFSET)
+#define hardirq_disable_exit()	__preempt_count_sub_return(HARDIRQ_DISABLE_OFFSET)
+
 static inline void local_interrupt_disable(void)
 {
 	int new_count;
+	unsigned long flags;
 
 	WARN_ON_ONCE(in_nmi());
 
+	local_irq_save(flags);
 	new_count = hardirq_disable_enter();
 
-	/* Interrupts can happen here, but it's OK, see __irq_exit_rcu(). */
-
 	if ((new_count & HARDIRQ_DISABLE_MASK) == HARDIRQ_DISABLE_OFFSET)
-		_local_interrupt_disable();
+		_local_interrupt_save_state(flags);
 }
 
 static inline void local_interrupt_enable(void)
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 8299657f0f86..2e689de7b29a 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -168,10 +168,6 @@ static __always_inline unsigned char interrupt_context_level(void)
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
 
-#define hardirq_disable_count()	((preempt_count() & HARDIRQ_DISABLE_MASK) >> HARDIRQ_DISABLE_SHIFT)
-#define hardirq_disable_enter()	__preempt_count_add_return(HARDIRQ_DISABLE_OFFSET)
-#define hardirq_disable_exit()	__preempt_count_sub_return(HARDIRQ_DISABLE_OFFSET)
-
 /*
  * The preempt_count offset after preempt_disable();
  */
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/futex/requeue.c b/kernel/futex/requeue.c
index 79823ad13683..b3f4a4bccb12 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -154,8 +154,16 @@ static inline void futex_requeue_pi_complete(struct futex_q *q, int locked)
 	} while (!atomic_try_cmpxchg(&q->requeue_state, &old, new));
 
 #ifdef CONFIG_PREEMPT_RT
-	/* If the waiter interleaved with the requeue let it know */
-	if (unlikely(old == Q_REQUEUE_PI_WAIT))
+	/*
+	 * The waiter in futex_requeue_pi_wakeup_sync() can interleave with the
+	 * wake below: It will assign Q_REQUEUE_PI_IN_PROGRESS and here it will
+	 * be updated to Q_REQUEUE_PI_LOCKED (locked = 1). The rcuwait_wait_event()
+	 * will already read Q_REQUEUE_PI_LOCKED and skip the schedule() invocation,
+	 * leading to an access of futex_q::requeue_wait after the waiter returned.
+	 * In this case only we skip the wake here and rely on following wake in
+	 * requeue_pi_wake_futex() to perform the wake if needed.
+	 */
+	if (unlikely(old == Q_REQUEUE_PI_WAIT) && new != Q_REQUEUE_PI_LOCKED)
 		rcuwait_wake_up(&q->requeue_wait);
 #endif
 }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c56a7f91d72e..c3dc84a7cef2 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?
 	 */
@@ -5324,9 +5358,9 @@ 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);
 
 		/*
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
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 7980a4a232f9..5d02c36c40e3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -91,11 +91,11 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
 
 DEFINE_PER_CPU(unsigned long, local_interrupt_disable_state);
 
-void _local_interrupt_disable(void)
+void _local_interrupt_save_state(unsigned long flags)
 {
-	__local_interrupt_disable();
+	__local_interrupt_save_state(flags);
 }
-EXPORT_SYMBOL(_local_interrupt_disable);
+EXPORT_SYMBOL(_local_interrupt_save_state);
 
 void _local_interrupt_enable(void)
 {
@@ -749,16 +749,7 @@ static inline void __irq_exit_rcu(void)
 #endif
 	account_hardirq_exit(current);
 	preempt_count_sub(HARDIRQ_OFFSET);
-	/*
-	 * Interrupts may happen between hardirq_disable_enter() and
-	 * local_irq_save() in local_interrupt_disable(), if irq_exit() invokes
-	 * softirq here, we may have a softirq handler calling
-	 * local_interrupt_disable() but it won't disable the IRQ because
-	 * hardirq disabling count is already 1, hence we need to prevent
-	 * invoking softirq when a local_interrupt_disable() is ongoing.
-	 */
-	if (!in_interrupt() && !hardirq_disable_count() &&
-	    local_softirq_pending()) {
+	if (!in_interrupt() && local_softirq_pending()) {
 		/*
 		 * If we left hrtimers unarmed, make sure to arm them now,
 		 * before enabling interrupts to run softirq.