Merge tag 'locking-core-2026-04-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Mutexes:

   - Add killable flavor to guard definitions (Davidlohr Bueso)

   - Remove the list_head from struct mutex (Matthew Wilcox)

   - Rename mutex_init_lockep() (Davidlohr Bueso)

  rwsems:

   - Remove the list_head from struct rw_semaphore and
     replace it with a single pointer (Matthew Wilcox)

   - Fix logic error in rwsem_del_waiter() (Andrei Vagin)

  Semaphores:

   - Remove the list_head from struct semaphore (Matthew Wilcox)

  Jump labels:

   - Use ATOMIC_INIT() for initialization of .enabled (Thomas Weißschuh)

   - Remove workaround for old compilers in initializations
     (Thomas Weißschuh)

  Lock context analysis changes and improvements:

   - Add context analysis for rwsems (Peter Zijlstra)

   - Fix rwlock and spinlock lock context annotations (Bart Van Assche)

   - Fix rwlock support in <linux/spinlock_up.h> (Bart Van Assche)

   - Add lock context annotations in the spinlock implementation
     (Bart Van Assche)

   - signal: Fix the lock_task_sighand() annotation (Bart Van Assche)

   - ww-mutex: Fix the ww_acquire_ctx function annotations
     (Bart Van Assche)

   - Add lock context support in do_raw_{read,write}_trylock()
     (Bart Van Assche)

   - arm64, compiler-context-analysis: Permit alias analysis through
     __READ_ONCE() with CONFIG_LTO=y (Marco Elver)

   - Add __cond_releases() (Peter Zijlstra)

   - Add context analysis for mutexes (Peter Zijlstra)

   - Add context analysis for rtmutexes (Peter Zijlstra)

   - Convert futexes to compiler context analysis (Peter Zijlstra)

  Rust integration updates:

   - Add atomic fetch_sub() implementation (Andreas Hindborg)

   - Refactor various rust_helper_ methods for expansion (Boqun Feng)

   - Add Atomic<*{mut,const} T> support (Boqun Feng)

   - Add atomic operation helpers over raw pointers (Boqun Feng)

   - Add performance-optimal Flag type for atomic booleans, to avoid
     slow byte-sized RMWs on architectures that don't support them.
     (FUJITA Tomonori)

   - Misc cleanups and fixes (Andreas Hindborg, Boqun Feng, FUJITA
     Tomonori)

  LTO support updates:

   - arm64: Optimize __READ_ONCE() with CONFIG_LTO=y (Marco Elver)

   - compiler: Simplify generic RELOC_HIDE() (Marco Elver)

  Miscellaneous fixes and cleanups by Peter Zijlstra, Randy Dunlap,
  Thomas Weißschuh, Davidlohr Bueso and Mikhail Gavrilov"

* tag 'locking-core-2026-04-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  compiler: Simplify generic RELOC_HIDE()
  locking: Add lock context annotations in the spinlock implementation
  locking: Add lock context support in do_raw_{read,write}_trylock()
  locking: Fix rwlock support in <linux/spinlock_up.h>
  lockdep: Raise default stack trace limits when KASAN is enabled
  cleanup: Optimize guards
  jump_label: remove workaround for old compilers in initializations
  jump_label: use ATOMIC_INIT() for initialization of .enabled
  futex: Convert to compiler context analysis
  locking/rwsem: Fix logic error in rwsem_del_waiter()
  locking/rwsem: Add context analysis
  locking/rtmutex: Add context analysis
  locking/mutex: Add context analysis
  compiler-context-analysys: Add __cond_releases()
  locking/mutex: Remove the list_head from struct mutex
  locking/semaphore: Remove the list_head from struct semaphore
  locking/rwsem: Remove the list_head from struct rw_semaphore
  rust: atomic: Update a safety comment in impl of `fetch_add()`
  rust: sync: atomic: Update documentation for `fetch_add()`
  rust: sync: atomic: Add fetch_sub()
  ...

15 files changed, 100 insertions, 66 deletions

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index dbc4162921e9..ea95ca4bc11c 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -286,15 +286,18 @@ static __always_inline _type class_##_name##_constructor(_init_args)	\
 	__no_context_analysis						\
 { _type t = _init; return t; }
 
-#define EXTEND_CLASS(_name, ext, _init, _init_args...)			\
-typedef lock_##_name##_t lock_##_name##ext##_t;			\
+#define EXTEND_CLASS_COND(_name, ext, _cond, _init, _init_args...)	\
+typedef lock_##_name##_t lock_##_name##ext##_t;				\
 typedef class_##_name##_t class_##_name##ext##_t;			\
-static __always_inline void class_##_name##ext##_destructor(class_##_name##_t *p) \
-{ class_##_name##_destructor(p); }					\
+static __always_inline void class_##_name##ext##_destructor(class_##_name##_t *_T) \
+{ if (_cond) return; class_##_name##_destructor(_T); }			\
 static __always_inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
 	__no_context_analysis \
 { class_##_name##_t t = _init; return t; }
 
+#define EXTEND_CLASS(_name, ext, _init, _init_args...)			\
+	EXTEND_CLASS_COND(_name, ext, 0, _init, _init_args)
+
 #define CLASS(_name, var)						\
 	class_##_name##_t var __cleanup(class_##_name##_destructor) =	\
 		class_##_name##_constructor
@@ -394,12 +397,12 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
 	__DEFINE_GUARD_LOCK_PTR(_name, _T)
 
 #define DEFINE_GUARD(_name, _type, _lock, _unlock) \
-	DEFINE_CLASS(_name, _type, if (!__GUARD_IS_ERR(_T)) { _unlock; }, ({ _lock; _T; }), _type _T); \
+	DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \
 	DEFINE_CLASS_IS_GUARD(_name)
 
 #define DEFINE_GUARD_COND_4(_name, _ext, _lock, _cond) \
 	__DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \
-	EXTEND_CLASS(_name, _ext, \
+	EXTEND_CLASS_COND(_name, _ext, __GUARD_IS_ERR(*_T), \
 		     ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \
 		     class_##_name##_t _T) \
 	static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
@@ -488,7 +491,7 @@ typedef struct {							\
 static __always_inline void class_##_name##_destructor(class_##_name##_t *_T) \
 	__no_context_analysis						\
 {									\
-	if (!__GUARD_IS_ERR(_T->lock)) { _unlock; }			\
+	if (_T->lock) { _unlock; }					\
 }									\
 									\
 __DEFINE_GUARD_LOCK_PTR(_name, &_T->lock)
@@ -565,7 +568,7 @@ __DEFINE_LOCK_GUARD_0(_name, _lock)
 
 #define DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _cond)		\
 	__DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true);		\
-	EXTEND_CLASS(_name, _ext,					\
+	EXTEND_CLASS_COND(_name, _ext, __GUARD_IS_ERR(_T->lock),	\
 		     ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\
 		        int _RET = (_lock);                             \
 		        if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\
diff --git a/include/linux/compiler-context-analysis.h b/include/linux/compiler-context-analysis.h
index 00c074a2ccb0..a9317571e6af 100644
--- a/include/linux/compiler-context-analysis.h
+++ b/include/linux/compiler-context-analysis.h
@@ -320,6 +320,38 @@ static inline void _context_unsafe_alias(void **p) { }
  */
 #define __releases(...)		__releases_ctx_lock(__VA_ARGS__)
 
+/*
+ * Clang's analysis does not care precisely about the value, only that it is
+ * either zero or non-zero. So the __cond_acquires() interface might be
+ * misleading if we say that @ret is the value returned if acquired. Instead,
+ * provide symbolic variants which we translate.
+ */
+#define __cond_acquires_impl_not_true(x, ...)     __try_acquires##__VA_ARGS__##_ctx_lock(0, x)
+#define __cond_acquires_impl_not_false(x, ...)    __try_acquires##__VA_ARGS__##_ctx_lock(1, x)
+#define __cond_acquires_impl_not_nonzero(x, ...)  __try_acquires##__VA_ARGS__##_ctx_lock(0, x)
+#define __cond_acquires_impl_not_0(x, ...)        __try_acquires##__VA_ARGS__##_ctx_lock(1, x)
+#define __cond_acquires_impl_not_nonnull(x, ...)  __try_acquires##__VA_ARGS__##_ctx_lock(0, x)
+#define __cond_acquires_impl_not_NULL(x, ...)     __try_acquires##__VA_ARGS__##_ctx_lock(1, x)
+
+/**
+ * __cond_releases() - function attribute, function conditionally
+ *                     releases a context lock exclusively
+ * @ret: abstract value returned by function if context lock releases
+ * @x: context lock instance pointer
+ *
+ * Function attribute declaring that the function conditionally releases the
+ * given context lock instance @x exclusively. The associated context(s) must
+ * be active on entry. The function return value @ret denotes when the context
+ * lock is released.
+ *
+ * @ret may be one of: true, false, nonzero, 0, nonnull, NULL.
+ *
+ * NOTE: clang does not have a native attribute for this; instead implement
+ *       it as an unconditional release and a conditional acquire for the
+ *       inverted condition -- which is semantically equivalent.
+ */
+#define __cond_releases(ret, x) __releases(x) __cond_acquires_impl_not_##ret(x)
+
 /**
  * __acquire() - function to acquire context lock exclusively
  * @x: context lock instance pointer
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index af16624b29fd..cb2f6050bdf7 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -149,10 +149,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #endif
 
 #ifndef RELOC_HIDE
-# define RELOC_HIDE(ptr, off)					\
-  ({ unsigned long __ptr;					\
-     __ptr = (unsigned long) (ptr);				\
-    (typeof(ptr)) (__ptr + (off)); })
+# define RELOC_HIDE(ptr, off) ((typeof(ptr))((unsigned long)(ptr) + (off)))
 #endif
 
 #define absolute_pointer(val)	RELOC_HIDE((void *)(val), 0)
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index fdb79dd1ebd8..b9c7b0ebf7b9 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -87,13 +87,6 @@ struct static_key {
 	atomic_t enabled;
 #ifdef CONFIG_JUMP_LABEL
 /*
- * Note:
- *   To make anonymous unions work with old compilers, the static
- *   initialization of them requires brackets. This creates a dependency
- *   on the order of the struct with the initializers. If any fields
- *   are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need
- *   to be modified.
- *
  * bit 0 => 1 if key is initially true
  *	    0 if initially false
  * bit 1 => 1 if points to struct static_key_mod
@@ -238,19 +231,12 @@ extern void static_key_enable_cpuslocked(struct static_key *key);
 extern void static_key_disable_cpuslocked(struct static_key *key);
 extern enum jump_label_type jump_label_init_type(struct jump_entry *entry);
 
-/*
- * We should be using ATOMIC_INIT() for initializing .enabled, but
- * the inclusion of atomic.h is problematic for inclusion of jump_label.h
- * in 'low-level' headers. Thus, we are initializing .enabled with a
- * raw value, but have added a BUILD_BUG_ON() to catch any issues in
- * jump_label_init() see: kernel/jump_label.c.
- */
 #define STATIC_KEY_INIT_TRUE					\
-	{ .enabled = { 1 },					\
-	  { .type = JUMP_TYPE_TRUE } }
+	{ .enabled = ATOMIC_INIT(1),				\
+	  .type = JUMP_TYPE_TRUE }
 #define STATIC_KEY_INIT_FALSE					\
-	{ .enabled = { 0 },					\
-	  { .type = JUMP_TYPE_FALSE } }
+	{ .enabled = ATOMIC_INIT(0),				\
+	  .type = JUMP_TYPE_FALSE }
 
 #else  /* !CONFIG_JUMP_LABEL */
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index ecaa0440f6ec..734048c02f4f 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -79,7 +79,7 @@ do {									\
 #define __MUTEX_INITIALIZER(lockname) \
 		{ .owner = ATOMIC_LONG_INIT(0) \
 		, .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
-		, .wait_list = LIST_HEAD_INIT(lockname.wait_list) \
+		, .first_waiter = NULL \
 		__DEBUG_MUTEX_INITIALIZER(lockname) \
 		__DEP_MAP_MUTEX_INITIALIZER(lockname) }
 
@@ -87,12 +87,12 @@ do {									\
 	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-void mutex_init_lockep(struct mutex *lock, const char *name, struct lock_class_key *key);
+void mutex_init_lockdep(struct mutex *lock, const char *name, struct lock_class_key *key);
 
 static inline void __mutex_init(struct mutex *lock, const char *name,
 				struct lock_class_key *key)
 {
-	mutex_init_lockep(lock, name, key);
+	mutex_init_lockdep(lock, name, key);
 }
 #else
 extern void mutex_init_generic(struct mutex *lock);
@@ -146,7 +146,7 @@ static inline void __mutex_init(struct mutex *lock, const char *name,
 {
 	mutex_rt_init_generic(lock);
 }
-#endif /* !CONFIG_LOCKDEP */
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 #endif /* CONFIG_PREEMPT_RT */
 
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -183,7 +183,7 @@ static inline int __must_check __devm_mutex_init(struct device *dev, struct mute
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass) __acquires(lock);
-extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
+extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock) __acquires(lock);
 extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
 					unsigned int subclass) __cond_acquires(0, lock);
 extern int __must_check _mutex_lock_killable(struct mutex *lock,
@@ -253,6 +253,7 @@ extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) __cond_a
 DEFINE_LOCK_GUARD_1(mutex, struct mutex, mutex_lock(_T->lock), mutex_unlock(_T->lock))
 DEFINE_LOCK_GUARD_1_COND(mutex, _try, mutex_trylock(_T->lock))
 DEFINE_LOCK_GUARD_1_COND(mutex, _intr, mutex_lock_interruptible(_T->lock), _RET == 0)
+DEFINE_LOCK_GUARD_1_COND(mutex, _kill, mutex_lock_killable(_T->lock), _RET == 0)
 DEFINE_LOCK_GUARD_1(mutex_init, struct mutex, mutex_init(_T->lock), /* */)
 
 DECLARE_LOCK_GUARD_1_ATTRS(mutex,	__acquires(_T), __releases(*(struct mutex **)_T))
@@ -261,6 +262,8 @@ DECLARE_LOCK_GUARD_1_ATTRS(mutex_try,	__acquires(_T), __releases(*(struct mutex
 #define class_mutex_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_try, _T)
 DECLARE_LOCK_GUARD_1_ATTRS(mutex_intr,	__acquires(_T), __releases(*(struct mutex **)_T))
 #define class_mutex_intr_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_intr, _T)
+DECLARE_LOCK_GUARD_1_ATTRS(mutex_kill,	__acquires(_T), __releases(*(struct mutex **)_T))
+#define class_mutex_kill_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_kill, _T)
 DECLARE_LOCK_GUARD_1_ATTRS(mutex_init,	__acquires(_T), __releases(*(struct mutex **)_T))
 #define class_mutex_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_init, _T)
 
diff --git a/include/linux/mutex_types.h b/include/linux/mutex_types.h
index 80975935ec48..24ed599fdda8 100644
--- a/include/linux/mutex_types.h
+++ b/include/linux/mutex_types.h
@@ -44,7 +44,7 @@ context_lock_struct(mutex) {
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
-	struct list_head	wait_list;
+	struct mutex_waiter	*first_waiter __guarded_by(&wait_lock);
 #ifdef CONFIG_DEBUG_MUTEXES
 	void			*magic;
 #endif
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index ede4c6bf6f22..78e7e588817c 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -22,8 +22,8 @@ extern int max_lock_depth;
 
 struct rt_mutex_base {
 	raw_spinlock_t		wait_lock;
-	struct rb_root_cached   waiters;
-	struct task_struct	*owner;
+	struct rb_root_cached   waiters __guarded_by(&wait_lock);
+	struct task_struct	*owner  __guarded_by(&wait_lock);
 };
 
 #define __RT_MUTEX_BASE_INITIALIZER(rtbasename)				\
@@ -41,7 +41,7 @@ struct rt_mutex_base {
  */
 static inline bool rt_mutex_base_is_locked(struct rt_mutex_base *lock)
 {
-	return READ_ONCE(lock->owner) != NULL;
+	return data_race(READ_ONCE(lock->owner) != NULL);
 }
 
 #ifdef CONFIG_RT_MUTEXES
@@ -49,7 +49,7 @@ static inline bool rt_mutex_base_is_locked(struct rt_mutex_base *lock)
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock)
 {
-	unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
+	unsigned long owner = (unsigned long) data_race(READ_ONCE(lock->owner));
 
 	return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS);
 }
diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h
index 3390d21c95dd..4e67cd934d8f 100644
--- a/include/linux/rwlock.h
+++ b/include/linux/rwlock.h
@@ -30,17 +30,27 @@ do {								\
 
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_read_lock(rwlock_t *lock) __acquires_shared(lock);
- extern int do_raw_read_trylock(rwlock_t *lock);
+ extern int do_raw_read_trylock(rwlock_t *lock) __cond_acquires_shared(true, lock);
  extern void do_raw_read_unlock(rwlock_t *lock) __releases_shared(lock);
  extern void do_raw_write_lock(rwlock_t *lock) __acquires(lock);
- extern int do_raw_write_trylock(rwlock_t *lock);
+extern int do_raw_write_trylock(rwlock_t *lock) __cond_acquires(true, lock);
  extern void do_raw_write_unlock(rwlock_t *lock) __releases(lock);
 #else
 # define do_raw_read_lock(rwlock)	do {__acquire_shared(lock); arch_read_lock(&(rwlock)->raw_lock); } while (0)
-# define do_raw_read_trylock(rwlock)	arch_read_trylock(&(rwlock)->raw_lock)
+static inline int do_raw_read_trylock(rwlock_t *rwlock)
+	__cond_acquires_shared(true, rwlock)
+	__no_context_analysis
+{
+	return arch_read_trylock(&(rwlock)->raw_lock);
+}
 # define do_raw_read_unlock(rwlock)	do {arch_read_unlock(&(rwlock)->raw_lock); __release_shared(lock); } while (0)
 # define do_raw_write_lock(rwlock)	do {__acquire(lock); arch_write_lock(&(rwlock)->raw_lock); } while (0)
-# define do_raw_write_trylock(rwlock)	arch_write_trylock(&(rwlock)->raw_lock)
+static inline int do_raw_write_trylock(rwlock_t *rwlock)
+	__cond_acquires(true, rwlock)
+	__no_context_analysis
+{
+	return arch_write_trylock(&(rwlock)->raw_lock);
+}
 # define do_raw_write_unlock(rwlock)	do {arch_write_unlock(&(rwlock)->raw_lock); __release(lock); } while (0)
 #endif
 
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index 61a852609eab..9e02a5f28cd1 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -23,7 +23,7 @@ void __lockfunc _raw_write_lock_bh(rwlock_t *lock)	__acquires(lock);
 void __lockfunc _raw_read_lock_irq(rwlock_t *lock)	__acquires_shared(lock);
 void __lockfunc _raw_write_lock_irq(rwlock_t *lock)	__acquires(lock);
 unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
-							__acquires(lock);
+							__acquires_shared(lock);
 unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
 							__acquires(lock);
 int __lockfunc _raw_read_trylock(rwlock_t *lock)	__cond_acquires_shared(true, lock);
@@ -36,7 +36,7 @@ void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)	__releases_shared(lock);
 void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)	__releases(lock);
 void __lockfunc
 _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
-							__releases(lock);
+							__releases_shared(lock);
 void __lockfunc
 _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 							__releases(lock);
@@ -116,6 +116,7 @@ _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 #endif
 
 static inline int __raw_read_trylock(rwlock_t *lock)
+	__cond_acquires_shared(true, lock)
 {
 	preempt_disable();
 	if (do_raw_read_trylock(lock)) {
@@ -127,6 +128,7 @@ static inline int __raw_read_trylock(rwlock_t *lock)
 }
 
 static inline int __raw_write_trylock(rwlock_t *lock)
+	__cond_acquires(true, lock)
 {
 	preempt_disable();
 	if (do_raw_write_trylock(lock)) {
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 9bf1d93d3d7b..6a1a7bae5f81 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -57,7 +57,7 @@ context_lock_struct(rw_semaphore) {
 	struct optimistic_spin_queue osq; /* spinner MCS lock */
 #endif
 	raw_spinlock_t wait_lock;
-	struct list_head wait_list;
+	struct rwsem_waiter *first_waiter __guarded_by(&wait_lock);
 #ifdef CONFIG_DEBUG_RWSEMS
 	void *magic;
 #endif
@@ -106,7 +106,7 @@ static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *
 	  .owner = ATOMIC_LONG_INIT(0),				\
 	  __RWSEM_OPT_INIT(name)				\
 	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\
-	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
+	  .first_waiter = NULL,					\
 	  __RWSEM_DEBUG_INIT(name)				\
 	  __RWSEM_DEP_MAP_INIT(name) }
 
@@ -129,9 +129,9 @@ do {								\
  * rwsem to see if somebody from an incompatible type is wanting access to the
  * lock.
  */
-static inline int rwsem_is_contended(struct rw_semaphore *sem)
+static inline bool rwsem_is_contended(struct rw_semaphore *sem)
 {
-	return !list_empty(&sem->wait_list);
+	return data_race(sem->first_waiter != NULL);
 }
 
 #if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index f842c86b806f..584ae88b435e 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -740,7 +740,7 @@ static inline int thread_group_empty(struct task_struct *p)
 
 extern struct sighand_struct *lock_task_sighand(struct task_struct *task,
 						unsigned long *flags)
-	__acquires(&task->sighand->siglock);
+	__cond_acquires(nonnull, &task->sighand->siglock);
 
 static inline void unlock_task_sighand(struct task_struct *task,
 						unsigned long *flags)
diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h
index 89706157e622..a4c8651ef021 100644
--- a/include/linux/semaphore.h
+++ b/include/linux/semaphore.h
@@ -15,7 +15,7 @@
 struct semaphore {
 	raw_spinlock_t		lock;
 	unsigned int		count;
-	struct list_head	wait_list;
+	struct semaphore_waiter *first_waiter;
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	unsigned long		last_holder;
@@ -33,7 +33,7 @@ struct semaphore {
 {									\
 	.lock		= __RAW_SPIN_LOCK_UNLOCKED((name).lock),	\
 	.count		= n,						\
-	.wait_list	= LIST_HEAD_INIT((name).wait_list)		\
+	.first_waiter	= NULL						\
 	__LAST_HOLDER_SEMAPHORE_INITIALIZER				\
 }
 
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index e1e2f144af9b..241277cd34cf 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -178,7 +178,7 @@ do {									\
 
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock);
- extern int do_raw_spin_trylock(raw_spinlock_t *lock);
+ extern int do_raw_spin_trylock(raw_spinlock_t *lock) __cond_acquires(true, lock);
  extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock);
 #else
 static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
@@ -189,6 +189,7 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 }
 
 static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
+	__cond_acquires(true, lock)
 {
 	int ret = arch_spin_trylock(&(lock)->raw_lock);
 
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 1e84e71ca495..3a50976471d7 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -48,16 +48,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	lock->slock = 1;
 }
 
-/*
- * Read-write spinlocks. No debug version.
- */
-#define arch_read_lock(lock)		do { barrier(); (void)(lock); } while (0)
-#define arch_write_lock(lock)		do { barrier(); (void)(lock); } while (0)
-#define arch_read_trylock(lock)	({ barrier(); (void)(lock); 1; })
-#define arch_write_trylock(lock)	({ barrier(); (void)(lock); 1; })
-#define arch_read_unlock(lock)		do { barrier(); (void)(lock); } while (0)
-#define arch_write_unlock(lock)	do { barrier(); (void)(lock); } while (0)
-
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
 /* for sched/core.c and kernel_lock.c: */
@@ -68,4 +58,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 #define arch_spin_is_contended(lock)	(((void)(lock), 0))
 
+/*
+ * Read-write spinlocks. No debug version.
+ */
+#define arch_read_lock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_write_lock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_read_trylock(lock)	({ barrier(); (void)(lock); 1; })
+#define arch_write_trylock(lock)	({ barrier(); (void)(lock); 1; })
+#define arch_read_unlock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_write_unlock(lock)	do { barrier(); (void)(lock); } while (0)
+
 #endif /* __LINUX_SPINLOCK_UP_H */
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 85b1fff02fde..0c95ead5a297 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -181,7 +181,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
  * data structures.
  */
 static inline void ww_acquire_done(struct ww_acquire_ctx *ctx)
-	__releases(ctx) __acquires_shared(ctx) __no_context_analysis
+	__must_hold(ctx)
 {
 #ifdef DEBUG_WW_MUTEXES
 	lockdep_assert_held(ctx);
@@ -199,7 +199,7 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx)
  * mutexes have been released with ww_mutex_unlock.
  */
 static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
-	__releases_shared(ctx) __no_context_analysis
+	__releases(ctx) __no_context_analysis
 {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	mutex_release(&ctx->first_lock_dep_map, _THIS_IP_);