Merge tag 'locking-core-2025-07-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Locking primitives:

   - Mark devm_mutex_init() as __must_check and fix drivers that didn't
     check the return code (Thomas Weißschuh)

   - Reorganize <linux/local_lock.h> to better expose the internal APIs
     to local variables (Sebastian Andrzej Siewior)

   - Remove OWNER_SPINNABLE in rwsem (Jinliang Zheng)

   - Remove redundant #ifdefs in the mutex code (Ran Xiaokai)

  Lockdep:

   - Avoid returning struct in lock_stats() (Arnd Bergmann)

   - Change `static const` into enum for LOCKF_*_IRQ_* (Arnd Bergmann)

   - Temporarily use synchronize_rcu_expedited() in
     lockdep_unregister_key() to speed things up. (Breno Leitao)

  Rust runtime:

   - Add #[must_use] to Lock::try_lock() (Jason Devers)"

* tag 'locking-core-2025-07-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  lockdep: Speed up lockdep_unregister_key() with expedited RCU synchronization
  locking/mutex: Remove redundant #ifdefs
  locking/lockdep: Change 'static const' variables to enum values
  locking/lockdep: Avoid struct return in lock_stats()
  locking/rwsem: Use OWNER_NONSPINNABLE directly instead of OWNER_SPINNABLE
  rust: sync: Add #[must_use] to Lock::try_lock()
  locking/mutex: Mark devm_mutex_init() as __must_check
  leds: lp8860: Check return value of devm_mutex_init()
  spi: spi-nxp-fspi: Check return value of devm_mutex_init()
  local_lock: Move this_cpu_ptr() notation from internal to main header

Author: torvalds

drivers/leds/leds-lp8860.c

@@ -307,7 +307,9 @@ static int lp8860_probe(struct i2c_client *client)
 	led->client = client;
 	led->led_dev.brightness_set_blocking = lp8860_brightness_set;
 
-	devm_mutex_init(&client->dev, &led->lock);
+	ret = devm_mutex_init(&client->dev, &led->lock);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to initialize lock\n");
 
 	led->regmap = devm_regmap_init_i2c(client, &lp8860_regmap_config);
 	if (IS_ERR(led->regmap)) {

drivers/spi/spi-nxp-fspi.c

@@ -1272,7 +1272,9 @@ static int nxp_fspi_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to request irq\n");
 
-	devm_mutex_init(dev, &f->lock);
+	ret = devm_mutex_init(dev, &f->lock);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to initialize lock\n");
 
 	ctlr->bus_num = -1;
 	ctlr->num_chipselect = NXP_FSPI_MAX_CHIPSELECT;

include/linux/local_lock.h

@@ -13,13 +13,13 @@
  * local_lock - Acquire a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_lock(lock)		__local_lock(lock)
+#define local_lock(lock)		__local_lock(this_cpu_ptr(lock))
 
 /**
  * local_lock_irq - Acquire a per CPU local lock and disable interrupts
  * @lock:	The lock variable
  */
-#define local_lock_irq(lock)		__local_lock_irq(lock)
+#define local_lock_irq(lock)		__local_lock_irq(this_cpu_ptr(lock))
 
 /**
  * local_lock_irqsave - Acquire a per CPU local lock, save and disable
@@ -28,19 +28,19 @@
  * @flags:	Storage for interrupt flags
  */
 #define local_lock_irqsave(lock, flags)				\
-	__local_lock_irqsave(lock, flags)
+	__local_lock_irqsave(this_cpu_ptr(lock), flags)
 
 /**
  * local_unlock - Release a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_unlock(lock)		__local_unlock(lock)
+#define local_unlock(lock)		__local_unlock(this_cpu_ptr(lock))
 
 /**
  * local_unlock_irq - Release a per CPU local lock and enable interrupts
  * @lock:	The lock variable
  */
-#define local_unlock_irq(lock)		__local_unlock_irq(lock)
+#define local_unlock_irq(lock)		__local_unlock_irq(this_cpu_ptr(lock))
 
 /**
  * local_unlock_irqrestore - Release a per CPU local lock and restore
@@ -49,7 +49,7 @@
  * @flags:      Interrupt flags to restore
  */
 #define local_unlock_irqrestore(lock, flags)			\
-	__local_unlock_irqrestore(lock, flags)
+	__local_unlock_irqrestore(this_cpu_ptr(lock), flags)
 
 /**
  * local_lock_init - Runtime initialize a lock instance
@@ -64,7 +64,7 @@
  * locking constrains it will _always_ fail to acquire the lock in NMI or
  * HARDIRQ context on PREEMPT_RT.
  */
-#define local_trylock(lock)		__local_trylock(lock)
+#define local_trylock(lock)		__local_trylock(this_cpu_ptr(lock))
 
 /**
  * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
@@ -77,7 +77,7 @@
  * HARDIRQ context on PREEMPT_RT.
  */
 #define local_trylock_irqsave(lock, flags)			\
-	__local_trylock_irqsave(lock, flags)
+	__local_trylock_irqsave(this_cpu_ptr(lock), flags)
 
 DEFINE_GUARD(local_lock, local_lock_t __percpu*,
 	     local_lock(_T),
@@ -91,10 +91,10 @@ DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu,
 		    unsigned long flags)
 
 #define local_lock_nested_bh(_lock)				\
-	__local_lock_nested_bh(_lock)
+	__local_lock_nested_bh(this_cpu_ptr(_lock))
 
 #define local_unlock_nested_bh(_lock)				\
-	__local_unlock_nested_bh(_lock)
+	__local_unlock_nested_bh(this_cpu_ptr(_lock))
 
 DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*,
 	     local_lock_nested_bh(_T),

include/linux/local_lock_internal.h

@@ -99,14 +99,14 @@ do {								\
 		local_trylock_t *tl;					\
 		local_lock_t *l;					\
 									\
-		l = (local_lock_t *)this_cpu_ptr(lock);			\
+		l = (local_lock_t *)(lock);				\
 		tl = (local_trylock_t *)l;				\
 		_Generic((lock),					\
-			__percpu local_trylock_t *: ({			\
+			local_trylock_t *: ({				\
 				lockdep_assert(tl->acquired == 0);	\
 				WRITE_ONCE(tl->acquired, 1);		\
 			}),						\
-			__percpu local_lock_t *: (void)0);		\
+			local_lock_t *: (void)0);			\
 		local_lock_acquire(l);					\
 	} while (0)
 
@@ -133,7 +133,7 @@ do {								\
 		local_trylock_t *tl;				\
 								\
 		preempt_disable();				\
-		tl = this_cpu_ptr(lock);			\
+		tl = (lock);					\
 		if (READ_ONCE(tl->acquired)) {			\
 			preempt_enable();			\
 			tl = NULL;				\
@@ -150,7 +150,7 @@ do {								\
 		local_trylock_t *tl;				\
 								\
 		local_irq_save(flags);				\
-		tl = this_cpu_ptr(lock);			\
+		tl = (lock);					\
 		if (READ_ONCE(tl->acquired)) {			\
 			local_irq_restore(flags);		\
 			tl = NULL;				\
@@ -167,15 +167,15 @@ do {								\
 		local_trylock_t *tl;					\
 		local_lock_t *l;					\
 									\
-		l = (local_lock_t *)this_cpu_ptr(lock);			\
+		l = (local_lock_t *)(lock);				\
 		tl = (local_trylock_t *)l;				\
 		local_lock_release(l);					\
 		_Generic((lock),					\
-			__percpu local_trylock_t *: ({			\
+			local_trylock_t *: ({				\
 				lockdep_assert(tl->acquired == 1);	\
 				WRITE_ONCE(tl->acquired, 0);		\
 			}),						\
-			__percpu local_lock_t *: (void)0);		\
+			local_lock_t *: (void)0);			\
 	} while (0)
 
 #define __local_unlock(lock)					\
@@ -199,11 +199,11 @@ do {								\
 #define __local_lock_nested_bh(lock)				\
 	do {							\
 		lockdep_assert_in_softirq();			\
-		local_lock_acquire(this_cpu_ptr(lock));	\
+		local_lock_acquire((lock));			\
 	} while (0)
 
 #define __local_unlock_nested_bh(lock)				\
-	local_lock_release(this_cpu_ptr(lock))
+	local_lock_release((lock))
 
 #else /* !CONFIG_PREEMPT_RT */
 
@@ -227,7 +227,7 @@ typedef spinlock_t local_trylock_t;
 #define __local_lock(__lock)					\
 	do {							\
 		migrate_disable();				\
-		spin_lock(this_cpu_ptr((__lock)));		\
+		spin_lock((__lock));				\
 	} while (0)
 
 #define __local_lock_irq(lock)			__local_lock(lock)
@@ -241,7 +241,7 @@ typedef spinlock_t local_trylock_t;
 
 #define __local_unlock(__lock)					\
 	do {							\
-		spin_unlock(this_cpu_ptr((__lock)));		\
+		spin_unlock((__lock));				\
 		migrate_enable();				\
 	} while (0)
 
@@ -252,12 +252,12 @@ typedef spinlock_t local_trylock_t;
 #define __local_lock_nested_bh(lock)				\
 do {								\
 	lockdep_assert_in_softirq_func();			\
-	spin_lock(this_cpu_ptr(lock));				\
+	spin_lock((lock));					\
 } while (0)
 
 #define __local_unlock_nested_bh(lock)				\
 do {								\
-	spin_unlock(this_cpu_ptr((lock)));			\
+	spin_unlock((lock));					\
 } while (0)
 
 #define __local_trylock(lock)					\
@@ -268,7 +268,7 @@ do {								\
 			__locked = 0;				\
 		} else {					\
 			migrate_disable();			\
-			__locked = spin_trylock(this_cpu_ptr((lock)));	\
+			__locked = spin_trylock((lock));	\
 			if (!__locked)				\
 				migrate_enable();		\
 		}						\

include/linux/lockdep_types.h

@@ -175,7 +175,7 @@ struct lock_class_stats {
 	unsigned long			bounces[nr_bounce_types];
 };
 
-struct lock_class_stats lock_stats(struct lock_class *class);
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats);
 void clear_lock_stats(struct lock_class *class);
 #endif
 

include/linux/mutex.h

@@ -126,11 +126,11 @@ do {							\
 
 #ifdef CONFIG_DEBUG_MUTEXES
 
-int __devm_mutex_init(struct device *dev, struct mutex *lock);
+int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock);
 
 #else
 
-static inline int __devm_mutex_init(struct device *dev, struct mutex *lock)
+static inline int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock)
 {
 	/*
 	 * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so
@@ -141,14 +141,17 @@ static inline int __devm_mutex_init(struct device *dev, struct mutex *lock)
 
 #endif
 
-#define devm_mutex_init(dev, mutex)			\
+#define __mutex_init_ret(mutex)				\
 ({							\
 	typeof(mutex) mutex_ = (mutex);			\
 							\
 	mutex_init(mutex_);				\
-	__devm_mutex_init(dev, mutex_);			\
+	mutex_;						\
 })
 
+#define devm_mutex_init(dev, mutex) \
+	__devm_mutex_init(dev, __mutex_init_ret(mutex))
+
 /*
  * See kernel/locking/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/locking/mutex-design.rst.

kernel/locking/lockdep.c

@@ -297,33 +297,30 @@ static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
 	dst->nr += src->nr;
 }
 
-struct lock_class_stats lock_stats(struct lock_class *class)
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats)
 {
-	struct lock_class_stats stats;
 	int cpu, i;
 
-	memset(&stats, 0, sizeof(struct lock_class_stats));
+	memset(stats, 0, sizeof(struct lock_class_stats));
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *pcs =
 			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
-		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
-			stats.contention_point[i] += pcs->contention_point[i];
+		for (i = 0; i < ARRAY_SIZE(stats->contention_point); i++)
+			stats->contention_point[i] += pcs->contention_point[i];
 
-		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
-			stats.contending_point[i] += pcs->contending_point[i];
+		for (i = 0; i < ARRAY_SIZE(stats->contending_point); i++)
+			stats->contending_point[i] += pcs->contending_point[i];
 
-		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
-		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
+		lock_time_add(&pcs->read_waittime, &stats->read_waittime);
+		lock_time_add(&pcs->write_waittime, &stats->write_waittime);
 
-		lock_time_add(&pcs->read_holdtime, &stats.read_holdtime);
-		lock_time_add(&pcs->write_holdtime, &stats.write_holdtime);
+		lock_time_add(&pcs->read_holdtime, &stats->read_holdtime);
+		lock_time_add(&pcs->write_holdtime, &stats->write_holdtime);
 
-		for (i = 0; i < ARRAY_SIZE(stats.bounces); i++)
-			stats.bounces[i] += pcs->bounces[i];
+		for (i = 0; i < ARRAY_SIZE(stats->bounces); i++)
+			stats->bounces[i] += pcs->bounces[i];
 	}
-
-	return stats;
 }
 
 void clear_lock_stats(struct lock_class *class)
@@ -6619,8 +6616,16 @@ void lockdep_unregister_key(struct lock_class_key *key)
 	if (need_callback)
 		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
 
-	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
-	synchronize_rcu();
+	/*
+	 * Wait until is_dynamic_key() has finished accessing k->hash_entry.
+	 *
+	 * Some operations like __qdisc_destroy() will call this in a debug
+	 * kernel, and the network traffic is disabled while waiting, hence
+	 * the delay of the wait matters in debugging cases. Currently use a
+	 * synchronize_rcu_expedited() to speed up the wait at the cost of
+	 * system IPIs. TODO: Replace RCU with hazptr for this.
+	 */
+	synchronize_rcu_expedited();
 }
 EXPORT_SYMBOL_GPL(lockdep_unregister_key);
 

kernel/locking/lockdep_internals.h

@@ -47,29 +47,31 @@ enum {
 	__LOCKF(USED_READ)
 };
 
+enum {
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
-static const unsigned long LOCKF_ENABLED_IRQ =
+	LOCKF_ENABLED_IRQ =
 #include "lockdep_states.h"
-	0;
+	0,
 #undef LOCKDEP_STATE
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE |
-static const unsigned long LOCKF_USED_IN_IRQ =
+	LOCKF_USED_IN_IRQ =
 #include "lockdep_states.h"
-	0;
+	0,
 #undef LOCKDEP_STATE
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE##_READ |
-static const unsigned long LOCKF_ENABLED_IRQ_READ =
+	LOCKF_ENABLED_IRQ_READ =
 #include "lockdep_states.h"
-	0;
+	0,
 #undef LOCKDEP_STATE
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE##_READ |
-static const unsigned long LOCKF_USED_IN_IRQ_READ =
+	LOCKF_USED_IN_IRQ_READ =
 #include "lockdep_states.h"
-	0;
+	0,
 #undef LOCKDEP_STATE
+};
 
 #define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ)
 #define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ)

kernel/locking/lockdep_proc.c

@@ -657,7 +657,7 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 			if (!test_bit(idx, lock_classes_in_use))
 				continue;
 			iter->class = class;
-			iter->stats = lock_stats(class);
+			lock_stats(class, &iter->stats);
 			iter++;
 		}
 

kernel/locking/mutex.c

@@ -191,9 +191,7 @@ static void
 __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 		   struct list_head *list)
 {
-#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	hung_task_set_blocker(lock, BLOCKER_TYPE_MUTEX);
-#endif
 	debug_mutex_add_waiter(lock, waiter, current);
 
 	list_add_tail(&waiter->list, list);
@@ -209,9 +207,7 @@ __mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
 		__mutex_clear_flag(lock, MUTEX_FLAGS);
 
 	debug_mutex_remove_waiter(lock, waiter, current);
-#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	hung_task_clear_blocker();
-#endif
 }
 
 /*