Merge tag 'locking-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Disable preemption in rwsem_write_trylock()'s attempt to take the
   rwsem, to avoid RT tasks hogging the CPU, which managed to preempt
   this function after the owner has been cleared but before a new owner
   is set. Also add debug checks to enforce this.

 - Add __lockfunc to more slow path functions and add __sched to
   semaphore functions.

 - Mark spinlock APIs noinline when the respective CONFIG_INLINE_SPIN_*
   toggles are disabled, to reduce LTO text size.

 - Print more debug information when lockdep gets confused in
   look_up_lock_class().

 - Improve header file abuse checks.

 - Misc cleanups

* tag 'locking-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/lockdep: Print more debug information - report name and key when look_up_lock_class() got confused
  locking: Add __sched to semaphore functions
  locking/rwsem: Disable preemption while trying for rwsem lock
  locking: Detect includes rwlock.h outside of spinlock.h
  locking: Add __lockfunc to slow path functions
  locking/spinlocks: Mark spinlocks noinline when inline spinlocks are disabled
  selftests: futex: Fix 'the the' typo in comment

7 files changed, 55 insertions, 43 deletions

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 64a13eb560781c..e3375bc40dadc7 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -934,8 +934,10 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 			 * Huh! same key, different name? Did someone trample
 			 * on some memory? We're most confused.
 			 */
-			WARN_ON_ONCE(class->name != lock->name &&
-				     lock->key != &__lockdep_no_validate__);
+			WARN_ONCE(class->name != lock->name &&
+				  lock->key != &__lockdep_no_validate__,
+				  "Looking for class \"%s\" with key %ps, but found a different class \"%s\" with the same key\n",
+				  lock->name, lock->key, class->name);
 			return class;
 		}
 	}
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 2e1600906c9f5c..d2ef312a8611eb 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -18,7 +18,7 @@
  * queued_read_lock_slowpath - acquire read lock of a queued rwlock
  * @lock: Pointer to queued rwlock structure
  */
-void queued_read_lock_slowpath(struct qrwlock *lock)
+void __lockfunc queued_read_lock_slowpath(struct qrwlock *lock)
 {
 	/*
 	 * Readers come here when they cannot get the lock without waiting
@@ -63,7 +63,7 @@ EXPORT_SYMBOL(queued_read_lock_slowpath);
  * queued_write_lock_slowpath - acquire write lock of a queued rwlock
  * @lock : Pointer to queued rwlock structure
  */
-void queued_write_lock_slowpath(struct qrwlock *lock)
+void __lockfunc queued_write_lock_slowpath(struct qrwlock *lock)
 {
 	int cnts;
 
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 65a9a10caa6f50..2b23378775feec 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -313,7 +313,7 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
  * contended             :    (*,x,y) +--> (*,0,0) ---> (*,0,1) -'  :
  *   queue               :         ^--'                             :
  */
-void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	struct mcs_spinlock *prev, *next, *node;
 	u32 old, tail;
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index e84d21aa0722b4..6afc249ce697db 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -489,7 +489,7 @@ gotlock:
  * PV versions of the unlock fastpath and slowpath functions to be used
  * instead of queued_spin_unlock().
  */
-__visible void
+__visible __lockfunc void
 __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
 	struct pv_node *node;
@@ -544,7 +544,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 #include <asm/qspinlock_paravirt.h>
 
 #ifndef __pv_queued_spin_unlock
-__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+__visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
 {
 	u8 locked;
 
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 65f0262f635e12..44873594de0316 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -133,14 +133,19 @@
  * the owner value concurrently without lock. Read from owner, however,
  * may not need READ_ONCE() as long as the pointer value is only used
  * for comparison and isn't being dereferenced.
+ *
+ * Both rwsem_{set,clear}_owner() functions should be in the same
+ * preempt disable section as the atomic op that changes sem->count.
  */
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
+	lockdep_assert_preemption_disabled();
 	atomic_long_set(&sem->owner, (long)current);
 }
 
 static inline void rwsem_clear_owner(struct rw_semaphore *sem)
 {
+	lockdep_assert_preemption_disabled();
 	atomic_long_set(&sem->owner, 0);
 }
 
@@ -251,13 +256,16 @@ static inline bool rwsem_read_trylock(struct rw_semaphore *sem, long *cntp)
 static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp = RWSEM_UNLOCKED_VALUE;
+	bool ret = false;
 
+	preempt_disable();
 	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) {
 		rwsem_set_owner(sem);
-		return true;
+		ret = true;
 	}
 
-	return false;
+	preempt_enable();
+	return ret;
 }
 
 /*
@@ -1352,8 +1360,10 @@ static inline void __up_write(struct rw_semaphore *sem)
 	DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
 			    !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);
 
+	preempt_disable();
 	rwsem_clear_owner(sem);
 	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
+	preempt_enable();
 	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
 		rwsem_wake(sem);
 }
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index f2654d2fe43aa1..34bfae72f29526 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -51,7 +51,7 @@ static noinline void __up(struct semaphore *sem);
  * Use of this function is deprecated, please use down_interruptible() or
  * down_killable() instead.
  */
-void down(struct semaphore *sem)
+void __sched down(struct semaphore *sem)
 {
 	unsigned long flags;
 
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(down);
  * If the sleep is interrupted by a signal, this function will return -EINTR.
  * If the semaphore is successfully acquired, this function returns 0.
  */
-int down_interruptible(struct semaphore *sem)
+int __sched down_interruptible(struct semaphore *sem)
 {
 	unsigned long flags;
 	int result = 0;
@@ -101,7 +101,7 @@ EXPORT_SYMBOL(down_interruptible);
  * -EINTR.  If the semaphore is successfully acquired, this function returns
  * 0.
  */
-int down_killable(struct semaphore *sem)
+int __sched down_killable(struct semaphore *sem)
 {
 	unsigned long flags;
 	int result = 0;
@@ -131,7 +131,7 @@ EXPORT_SYMBOL(down_killable);
  * Unlike mutex_trylock, this function can be used from interrupt context,
  * and the semaphore can be released by any task or interrupt.
  */
-int down_trylock(struct semaphore *sem)
+int __sched down_trylock(struct semaphore *sem)
 {
 	unsigned long flags;
 	int count;
@@ -156,7 +156,7 @@ EXPORT_SYMBOL(down_trylock);
  * If the semaphore is not released within the specified number of jiffies,
  * this function returns -ETIME.  It returns 0 if the semaphore was acquired.
  */
-int down_timeout(struct semaphore *sem, long timeout)
+int __sched down_timeout(struct semaphore *sem, long timeout)
 {
 	unsigned long flags;
 	int result = 0;
@@ -180,7 +180,7 @@ EXPORT_SYMBOL(down_timeout);
  * Release the semaphore.  Unlike mutexes, up() may be called from any
  * context and even by tasks which have never called down().
  */
-void up(struct semaphore *sem)
+void __sched up(struct semaphore *sem)
 {
 	unsigned long flags;
 
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 7f49baaa49793a..8475a0794f8c5a 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -133,7 +133,7 @@ BUILD_LOCK_OPS(write, rwlock);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_TRYLOCK
-int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock)
+noinline int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock)
 {
 	return __raw_spin_trylock(lock);
 }
@@ -141,7 +141,7 @@ EXPORT_SYMBOL(_raw_spin_trylock);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH
-int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock)
+noinline int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock)
 {
 	return __raw_spin_trylock_bh(lock);
 }
@@ -149,7 +149,7 @@ EXPORT_SYMBOL(_raw_spin_trylock_bh);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_LOCK
-void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)
 {
 	__raw_spin_lock(lock);
 }
@@ -157,7 +157,7 @@ EXPORT_SYMBOL(_raw_spin_lock);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
-unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
+noinline unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
 {
 	return __raw_spin_lock_irqsave(lock);
 }
@@ -165,7 +165,7 @@ EXPORT_SYMBOL(_raw_spin_lock_irqsave);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
-void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
 {
 	__raw_spin_lock_irq(lock);
 }
@@ -173,7 +173,7 @@ EXPORT_SYMBOL(_raw_spin_lock_irq);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_LOCK_BH
-void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
 {
 	__raw_spin_lock_bh(lock);
 }
@@ -181,7 +181,7 @@ EXPORT_SYMBOL(_raw_spin_lock_bh);
 #endif
 
 #ifdef CONFIG_UNINLINE_SPIN_UNLOCK
-void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
 {
 	__raw_spin_unlock(lock);
 }
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(_raw_spin_unlock);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
-void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
+noinline void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
 {
 	__raw_spin_unlock_irqrestore(lock, flags);
 }
@@ -197,7 +197,7 @@ EXPORT_SYMBOL(_raw_spin_unlock_irqrestore);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
-void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
 {
 	__raw_spin_unlock_irq(lock);
 }
@@ -205,7 +205,7 @@ EXPORT_SYMBOL(_raw_spin_unlock_irq);
 #endif
 
 #ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
-void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
+noinline void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
 {
 	__raw_spin_unlock_bh(lock);
 }
@@ -215,7 +215,7 @@ EXPORT_SYMBOL(_raw_spin_unlock_bh);
 #ifndef CONFIG_PREEMPT_RT
 
 #ifndef CONFIG_INLINE_READ_TRYLOCK
-int __lockfunc _raw_read_trylock(rwlock_t *lock)
+noinline int __lockfunc _raw_read_trylock(rwlock_t *lock)
 {
 	return __raw_read_trylock(lock);
 }
@@ -223,7 +223,7 @@ EXPORT_SYMBOL(_raw_read_trylock);
 #endif
 
 #ifndef CONFIG_INLINE_READ_LOCK
-void __lockfunc _raw_read_lock(rwlock_t *lock)
+noinline void __lockfunc _raw_read_lock(rwlock_t *lock)
 {
 	__raw_read_lock(lock);
 }
@@ -231,7 +231,7 @@ EXPORT_SYMBOL(_raw_read_lock);
 #endif
 
 #ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE
-unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
+noinline unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
 {
 	return __raw_read_lock_irqsave(lock);
 }
@@ -239,7 +239,7 @@ EXPORT_SYMBOL(_raw_read_lock_irqsave);
 #endif
 
 #ifndef CONFIG_INLINE_READ_LOCK_IRQ
-void __lockfunc _raw_read_lock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_read_lock_irq(rwlock_t *lock)
 {
 	__raw_read_lock_irq(lock);
 }
@@ -247,7 +247,7 @@ EXPORT_SYMBOL(_raw_read_lock_irq);
 #endif
 
 #ifndef CONFIG_INLINE_READ_LOCK_BH
-void __lockfunc _raw_read_lock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_read_lock_bh(rwlock_t *lock)
 {
 	__raw_read_lock_bh(lock);
 }
@@ -255,7 +255,7 @@ EXPORT_SYMBOL(_raw_read_lock_bh);
 #endif
 
 #ifndef CONFIG_INLINE_READ_UNLOCK
-void __lockfunc _raw_read_unlock(rwlock_t *lock)
+noinline void __lockfunc _raw_read_unlock(rwlock_t *lock)
 {
 	__raw_read_unlock(lock);
 }
@@ -263,7 +263,7 @@ EXPORT_SYMBOL(_raw_read_unlock);
 #endif
 
 #ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE
-void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+noinline void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
 	__raw_read_unlock_irqrestore(lock, flags);
 }
@@ -271,7 +271,7 @@ EXPORT_SYMBOL(_raw_read_unlock_irqrestore);
 #endif
 
 #ifndef CONFIG_INLINE_READ_UNLOCK_IRQ
-void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)
 {
 	__raw_read_unlock_irq(lock);
 }
@@ -279,7 +279,7 @@ EXPORT_SYMBOL(_raw_read_unlock_irq);
 #endif
 
 #ifndef CONFIG_INLINE_READ_UNLOCK_BH
-void __lockfunc _raw_read_unlock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_read_unlock_bh(rwlock_t *lock)
 {
 	__raw_read_unlock_bh(lock);
 }
@@ -287,7 +287,7 @@ EXPORT_SYMBOL(_raw_read_unlock_bh);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_TRYLOCK
-int __lockfunc _raw_write_trylock(rwlock_t *lock)
+noinline int __lockfunc _raw_write_trylock(rwlock_t *lock)
 {
 	return __raw_write_trylock(lock);
 }
@@ -295,7 +295,7 @@ EXPORT_SYMBOL(_raw_write_trylock);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_LOCK
-void __lockfunc _raw_write_lock(rwlock_t *lock)
+noinline void __lockfunc _raw_write_lock(rwlock_t *lock)
 {
 	__raw_write_lock(lock);
 }
@@ -313,7 +313,7 @@ EXPORT_SYMBOL(_raw_write_lock_nested);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE
-unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
+noinline unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
 {
 	return __raw_write_lock_irqsave(lock);
 }
@@ -321,7 +321,7 @@ EXPORT_SYMBOL(_raw_write_lock_irqsave);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_LOCK_IRQ
-void __lockfunc _raw_write_lock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_write_lock_irq(rwlock_t *lock)
 {
 	__raw_write_lock_irq(lock);
 }
@@ -329,7 +329,7 @@ EXPORT_SYMBOL(_raw_write_lock_irq);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_LOCK_BH
-void __lockfunc _raw_write_lock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_write_lock_bh(rwlock_t *lock)
 {
 	__raw_write_lock_bh(lock);
 }
@@ -337,7 +337,7 @@ EXPORT_SYMBOL(_raw_write_lock_bh);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_UNLOCK
-void __lockfunc _raw_write_unlock(rwlock_t *lock)
+noinline void __lockfunc _raw_write_unlock(rwlock_t *lock)
 {
 	__raw_write_unlock(lock);
 }
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(_raw_write_unlock);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE
-void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+noinline void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
 	__raw_write_unlock_irqrestore(lock, flags);
 }
@@ -353,7 +353,7 @@ EXPORT_SYMBOL(_raw_write_unlock_irqrestore);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ
-void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)
+noinline void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)
 {
 	__raw_write_unlock_irq(lock);
 }
@@ -361,7 +361,7 @@ EXPORT_SYMBOL(_raw_write_unlock_irq);
 #endif
 
 #ifndef CONFIG_INLINE_WRITE_UNLOCK_BH
-void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
+noinline void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
 {
 	__raw_write_unlock_bh(lock);
 }