diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
index 3fb7ea3ab22a..9899871d3d9a 100644
--- a/Documentation/locking/seqlock.rst
+++ b/Documentation/locking/seqlock.rst
@@ -220,13 +220,14 @@ Read path, three categories:
    according to a passed marker. This is used to avoid lockless readers
    starvation (too much retry loops) in case of a sharp spike in write
    activity. First, a lockless read is tried (even marker passed). If
-   that trial fails (odd sequence counter is returned, which is used as
-   the next iteration marker), the lockless read is transformed to a
-   full locking read and no retry loop is necessary::
+   that trial fails (sequence counter doesn't match), make the marker
+   odd for the next iteration, the lockless read is transformed to a
+   full locking read and no retry loop is necessary, for example::
 
 	/* marker; even initialization */
-	int seq = 0;
+	int seq = 1;
 	do {
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&foo_seqlock, &seq);
 
 		/* ... [[read-side critical section]] ... */
diff --git a/MAINTAINERS b/MAINTAINERS
index 3468f6827b13..6cdd6d749cf8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14536,6 +14536,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 F:	Documentation/locking/
 F:	arch/*/include/asm/spinlock*.h
+F:	include/linux/local_lock*.h
 F:	include/linux/lockdep*.h
 F:	include/linux/mutex*.h
 F:	include/linux/rwlock*.h
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 2ae63189091e..cbd4bc4a58e4 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -481,7 +481,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long flags;
 	int exit_code = task->exit_code;
 	struct signal_struct *sig = task->signal;
-	unsigned int seq = 1;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -538,10 +537,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	if (permitted && (!whole || num_threads < 2))
 		wchan = !task_is_running(task);
 
-	do {
-		seq++; /* 2 on the 1st/lockless path, otherwise odd */
-		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
-
+	scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) {
 		cmin_flt = sig->cmin_flt;
 		cmaj_flt = sig->cmaj_flt;
 		cutime = sig->cutime;
@@ -563,8 +559,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 			}
 			rcu_read_unlock();
 		}
-	} while (need_seqretry(&sig->stats_lock, seq));
-	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+	}
 
 	if (whole) {
 		thread_group_cputime_adjusted(task, &utime, &stime);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6299878e3d97..407b41cb6e7c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3043,21 +3043,14 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	if (whole) {
 		struct signal_struct *sig = task->signal;
 		struct task_struct *t;
-		unsigned int seq = 1;
-		unsigned long flags;
-
-		rcu_read_lock();
-		do {
-			seq++; /* 2 on the 1st/lockless path, otherwise odd */
-			flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
 
+		guard(rcu)();
+		scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) {
 			acct = sig->ioac;
 			__for_each_thread(sig, t)
 				task_io_accounting_add(&acct, &t->ioac);
 
-		} while (need_seqretry(&sig->stats_lock, seq));
-		done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
-		rcu_read_unlock();
+		}
 	} else {
 		acct = task->ioac;
 	}
diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h
index 9409a6ddf3e0..37ab6314a9f7 100644
--- a/include/linux/atomic/atomic-instrumented.h
+++ b/include/linux/atomic/atomic-instrumented.h
@@ -1276,7 +1276,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_try_cmpxchg(v, old, new);
 }
 
@@ -1298,7 +1298,7 @@ static __always_inline bool
 atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_try_cmpxchg_acquire(v, old, new);
 }
 
@@ -1321,7 +1321,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_try_cmpxchg_release(v, old, new);
 }
 
@@ -1343,7 +1343,7 @@ static __always_inline bool
 atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_try_cmpxchg_relaxed(v, old, new);
 }
 
@@ -2854,7 +2854,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic64_try_cmpxchg(v, old, new);
 }
 
@@ -2876,7 +2876,7 @@ static __always_inline bool
 atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic64_try_cmpxchg_acquire(v, old, new);
 }
 
@@ -2899,7 +2899,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic64_try_cmpxchg_release(v, old, new);
 }
 
@@ -2921,7 +2921,7 @@ static __always_inline bool
 atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic64_try_cmpxchg_relaxed(v, old, new);
 }
 
@@ -4432,7 +4432,7 @@ atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_long_try_cmpxchg(v, old, new);
 }
 
@@ -4454,7 +4454,7 @@ static __always_inline bool
 atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_long_try_cmpxchg_acquire(v, old, new);
 }
 
@@ -4477,7 +4477,7 @@ atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_long_try_cmpxchg_release(v, old, new);
 }
 
@@ -4499,7 +4499,7 @@ static __always_inline bool
 atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
+	instrument_read_write(old, sizeof(*old));
 	return raw_atomic_long_try_cmpxchg_relaxed(v, old, new);
 }
 
@@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 8829b337928e9508259079d32581775ececd415b
+// f618ac667f868941a84ce0ab2242f1786e049ed4
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index 0d91d060e3e9..b0e6ab329b00 100644
--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -6,6 +6,7 @@
 
 /**
  * local_lock_init - Runtime initialize a lock instance
+ * @lock:	The lock variable
  */
 #define local_lock_init(lock)		__local_lock_init(lock)
 
@@ -52,7 +53,8 @@
 	__local_unlock_irqrestore(this_cpu_ptr(lock), flags)
 
 /**
- * local_lock_init - Runtime initialize a lock instance
+ * local_trylock_init - Runtime initialize a lock instance
+ * @lock:	The lock variable
  */
 #define local_trylock_init(lock)	__local_trylock_init(lock)
 
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index a4dc479157b5..8f82b4eb542f 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -99,18 +99,18 @@ do {								\
 
 #define __local_lock_acquire(lock)					\
 	do {								\
-		local_trylock_t *tl;					\
-		local_lock_t *l;					\
+		local_trylock_t *__tl;					\
+		local_lock_t *__l;					\
 									\
-		l = (local_lock_t *)(lock);				\
-		tl = (local_trylock_t *)l;				\
+		__l = (local_lock_t *)(lock);				\
+		__tl = (local_trylock_t *)__l;				\
 		_Generic((lock),					\
 			local_trylock_t *: ({				\
-				lockdep_assert(tl->acquired == 0);	\
-				WRITE_ONCE(tl->acquired, 1);		\
+				lockdep_assert(__tl->acquired == 0);	\
+				WRITE_ONCE(__tl->acquired, 1);		\
 			}),						\
 			local_lock_t *: (void)0);			\
-		local_lock_acquire(l);					\
+		local_lock_acquire(__l);				\
 	} while (0)
 
 #define __local_lock(lock)					\
@@ -133,36 +133,36 @@ do {								\
 
 #define __local_trylock(lock)					\
 	({							\
-		local_trylock_t *tl;				\
+		local_trylock_t *__tl;				\
 								\
 		preempt_disable();				\
-		tl = (lock);					\
-		if (READ_ONCE(tl->acquired)) {			\
+		__tl = (lock);					\
+		if (READ_ONCE(__tl->acquired)) {		\
 			preempt_enable();			\
-			tl = NULL;				\
+			__tl = NULL;				\
 		} else {					\
-			WRITE_ONCE(tl->acquired, 1);		\
+			WRITE_ONCE(__tl->acquired, 1);		\
 			local_trylock_acquire(			\
-				(local_lock_t *)tl);		\
+				(local_lock_t *)__tl);		\
 		}						\
-		!!tl;						\
+		!!__tl;						\
 	})
 
 #define __local_trylock_irqsave(lock, flags)			\
 	({							\
-		local_trylock_t *tl;				\
+		local_trylock_t *__tl;				\
 								\
 		local_irq_save(flags);				\
-		tl = (lock);					\
-		if (READ_ONCE(tl->acquired)) {			\
+		__tl = (lock);					\
+		if (READ_ONCE(__tl->acquired)) {		\
 			local_irq_restore(flags);		\
-			tl = NULL;				\
+			__tl = NULL;				\
 		} else {					\
-			WRITE_ONCE(tl->acquired, 1);		\
+			WRITE_ONCE(__tl->acquired, 1);		\
 			local_trylock_acquire(			\
-				(local_lock_t *)tl);		\
+				(local_lock_t *)__tl);		\
 		}						\
-		!!tl;						\
+		!!__tl;						\
 	})
 
 /* preemption or migration must be disabled before calling __local_lock_is_locked */
@@ -170,16 +170,16 @@ do {								\
 
 #define __local_lock_release(lock)					\
 	do {								\
-		local_trylock_t *tl;					\
-		local_lock_t *l;					\
+		local_trylock_t *__tl;					\
+		local_lock_t *__l;					\
 									\
-		l = (local_lock_t *)(lock);				\
-		tl = (local_trylock_t *)l;				\
-		local_lock_release(l);					\
+		__l = (local_lock_t *)(lock);				\
+		__tl = (local_trylock_t *)__l;				\
+		local_lock_release(__l);				\
 		_Generic((lock),					\
 			local_trylock_t *: ({				\
-				lockdep_assert(tl->acquired == 1);	\
-				WRITE_ONCE(tl->acquired, 0);		\
+				lockdep_assert(__tl->acquired == 1);	\
+				WRITE_ONCE(__tl->acquired, 0);		\
 			}),						\
 			local_lock_t *: (void)0);			\
 	} while (0)
@@ -223,12 +223,12 @@ typedef spinlock_t local_trylock_t;
 #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
 #define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
 
-#define __local_lock_init(l)					\
+#define __local_lock_init(__l)					\
 	do {							\
-		local_spin_lock_init((l));			\
+		local_spin_lock_init((__l));			\
 	} while (0)
 
-#define __local_trylock_init(l)			__local_lock_init(l)
+#define __local_trylock_init(__l)			__local_lock_init(__l)
 
 #define __local_lock(__lock)					\
 	do {							\
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 847b81ca6436..bf535f0118bb 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -86,8 +86,23 @@ do {									\
 #define DEFINE_MUTEX(mutexname) \
 	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
 
-extern void __mutex_init(struct mutex *lock, const char *name,
-			 struct lock_class_key *key);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void mutex_init_lockep(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);
+}
+#else
+extern void mutex_init_generic(struct mutex *lock);
+
+static inline void __mutex_init(struct mutex *lock, const char *name,
+				struct lock_class_key *key)
+{
+	mutex_init_generic(lock);
+}
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 /**
  * mutex_is_locked - is the mutex locked
@@ -111,17 +126,27 @@ extern bool mutex_is_locked(struct mutex *lock);
 #define DEFINE_MUTEX(mutexname)						\
 	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
 
-extern void __mutex_rt_init(struct mutex *lock, const char *name,
-			    struct lock_class_key *key);
-
 #define mutex_is_locked(l)	rt_mutex_base_is_locked(&(l)->rtmutex)
 
-#define __mutex_init(mutex, name, key)			\
-do {							\
-	rt_mutex_base_init(&(mutex)->rtmutex);		\
-	__mutex_rt_init((mutex), name, key);		\
-} while (0)
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void mutex_rt_init_lockdep(struct mutex *mutex, 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_rt_init_lockdep(lock, name, key);
+}
+
+#else
+extern void mutex_rt_init_generic(struct mutex *mutex);
+
+static inline void __mutex_init(struct mutex *lock, const char *name,
+				struct lock_class_key *key)
+{
+	mutex_rt_init_generic(lock);
+}
+#endif /* !CONFIG_LOCKDEP */
 #endif /* CONFIG_PREEMPT_RT */
 
 #ifdef CONFIG_DEBUG_MUTEXES
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 5ce48eab7a2a..a8a8661839b6 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -1209,4 +1209,118 @@ done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags)
 	if (seq & 1)
 		read_sequnlock_excl_irqrestore(lock, flags);
 }
+
+enum ss_state {
+	ss_done = 0,
+	ss_lock,
+	ss_lock_irqsave,
+	ss_lockless,
+};
+
+struct ss_tmp {
+	enum ss_state	state;
+	unsigned long	data;
+	spinlock_t	*lock;
+	spinlock_t	*lock_irqsave;
+};
+
+static inline void __scoped_seqlock_cleanup(struct ss_tmp *sst)
+{
+	if (sst->lock)
+		spin_unlock(sst->lock);
+	if (sst->lock_irqsave)
+		spin_unlock_irqrestore(sst->lock_irqsave, sst->data);
+}
+
+extern void __scoped_seqlock_invalid_target(void);
+
+#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 90000) || defined(CONFIG_KASAN)
+/*
+ * For some reason some GCC-8 architectures (nios2, alpha) have trouble
+ * determining that the ss_done state is impossible in __scoped_seqlock_next()
+ * below.
+ *
+ * Similarly KASAN is known to confuse compilers enough to break this. But we
+ * don't care about code quality for KASAN builds anyway.
+ */
+static inline void __scoped_seqlock_bug(void) { }
+#else
+/*
+ * Canary for compiler optimization -- if the compiler doesn't realize this is
+ * an impossible state, it very likely generates sub-optimal code here.
+ */
+extern void __scoped_seqlock_bug(void);
+#endif
+
+static inline void
+__scoped_seqlock_next(struct ss_tmp *sst, seqlock_t *lock, enum ss_state target)
+{
+	switch (sst->state) {
+	case ss_done:
+		__scoped_seqlock_bug();
+		return;
+
+	case ss_lock:
+	case ss_lock_irqsave:
+		sst->state = ss_done;
+		return;
+
+	case ss_lockless:
+		if (!read_seqretry(lock, sst->data)) {
+			sst->state = ss_done;
+			return;
+		}
+		break;
+	}
+
+	switch (target) {
+	case ss_done:
+		__scoped_seqlock_invalid_target();
+		return;
+
+	case ss_lock:
+		sst->lock = &lock->lock;
+		spin_lock(sst->lock);
+		sst->state = ss_lock;
+		return;
+
+	case ss_lock_irqsave:
+		sst->lock_irqsave = &lock->lock;
+		spin_lock_irqsave(sst->lock_irqsave, sst->data);
+		sst->state = ss_lock_irqsave;
+		return;
+
+	case ss_lockless:
+		sst->data = read_seqbegin(lock);
+		return;
+	}
+}
+
+#define __scoped_seqlock_read(_seqlock, _target, _s)			\
+	for (struct ss_tmp _s __cleanup(__scoped_seqlock_cleanup) =	\
+	     { .state = ss_lockless, .data = read_seqbegin(_seqlock) };	\
+	     _s.state != ss_done;					\
+	     __scoped_seqlock_next(&_s, _seqlock, _target))
+
+/**
+ * scoped_seqlock_read (lock, ss_state) - execute the read side critical
+ *                                        section without manual sequence
+ *                                        counter handling or calls to other
+ *                                        helpers
+ * @lock: pointer to seqlock_t protecting the data
+ * @ss_state: one of {ss_lock, ss_lock_irqsave, ss_lockless} indicating
+ *            the type of critical read section
+ *
+ * Example:
+ *
+ *     scoped_seqlock_read (&lock, ss_lock) {
+ *         // read-side critical section
+ *     }
+ *
+ * Starts with a lockess pass first. If it fails, restarts the critical
+ * section with the lock held.
+ */
+#define scoped_seqlock_read(_seqlock, _target)				\
+	__scoped_seqlock_read(_seqlock, _target, __UNIQUE_ID(seqlock))
+
 #endif /* __LINUX_SEQLOCK_H */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 949103fd8e9b..2c6b02d4699b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -78,16 +78,8 @@ void debug_mutex_unlock(struct mutex *lock)
 	}
 }
 
-void debug_mutex_init(struct mutex *lock, const char *name,
-		      struct lock_class_key *key)
+void debug_mutex_init(struct mutex *lock)
 {
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	/*
-	 * Make sure we are not reinitializing a held lock:
-	 */
-	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
-	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
-#endif
 	lock->magic = lock;
 }
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index de7d6702cd96..2a1d165b3167 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -43,8 +43,7 @@
 # define MUTEX_WARN_ON(cond)
 #endif
 
-void
-__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
+static void __mutex_init_generic(struct mutex *lock)
 {
 	atomic_long_set(&lock->owner, 0);
 	raw_spin_lock_init(&lock->wait_lock);
@@ -52,10 +51,8 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	osq_lock_init(&lock->osq);
 #endif
-
-	debug_mutex_init(lock, name, key);
+	debug_mutex_init(lock);
 }
-EXPORT_SYMBOL(__mutex_init);
 
 static inline struct task_struct *__owner_task(unsigned long owner)
 {
@@ -142,6 +139,11 @@ static inline bool __mutex_trylock(struct mutex *lock)
  * There is nothing that would stop spreading the lockdep annotations outwards
  * except more code.
  */
+void mutex_init_generic(struct mutex *lock)
+{
+	__mutex_init_generic(lock);
+}
+EXPORT_SYMBOL(mutex_init_generic);
 
 /*
  * Optimistic trylock that only works in the uncontended case. Make sure to
@@ -166,7 +168,21 @@ static __always_inline bool __mutex_unlock_fast(struct mutex *lock)
 
 	return atomic_long_try_cmpxchg_release(&lock->owner, &curr, 0UL);
 }
-#endif
+
+#else /* !CONFIG_DEBUG_LOCK_ALLOC */
+
+void mutex_init_lockep(struct mutex *lock, const char *name, struct lock_class_key *key)
+{
+	__mutex_init_generic(lock);
+
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
+}
+EXPORT_SYMBOL(mutex_init_lockep);
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag)
 {
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 2e8080a9bee3..9ad4da8cea00 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -59,8 +59,7 @@ extern void debug_mutex_add_waiter(struct mutex *lock,
 extern void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 				      struct task_struct *task);
 extern void debug_mutex_unlock(struct mutex *lock);
-extern void debug_mutex_init(struct mutex *lock, const char *name,
-			     struct lock_class_key *key);
+extern void debug_mutex_init(struct mutex *lock);
 #else /* CONFIG_DEBUG_MUTEXES */
 # define debug_mutex_lock_common(lock, waiter)		do { } while (0)
 # define debug_mutex_wake_waiter(lock, waiter)		do { } while (0)
@@ -68,6 +67,6 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
 # define debug_mutex_add_waiter(lock, waiter, ti)	do { } while (0)
 # define debug_mutex_remove_waiter(lock, waiter, ti)	do { } while (0)
 # define debug_mutex_unlock(lock)			do { } while (0)
-# define debug_mutex_init(lock, name, key)		do { } while (0)
+# define debug_mutex_init(lock)				do { } while (0)
 #endif /* !CONFIG_DEBUG_MUTEXES */
 #endif /* CONFIG_PREEMPT_RT */
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index bafd5af98eae..59dbd29cb219 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -515,13 +515,11 @@ void rt_mutex_debug_task_free(struct task_struct *task)
 
 #ifdef CONFIG_PREEMPT_RT
 /* Mutexes */
-void __mutex_rt_init(struct mutex *mutex, const char *name,
-		     struct lock_class_key *key)
+static void __mutex_rt_init_generic(struct mutex *mutex)
 {
+	rt_mutex_base_init(&mutex->rtmutex);
 	debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
-	lockdep_init_map_wait(&mutex->dep_map, name, key, 0, LD_WAIT_SLEEP);
 }
-EXPORT_SYMBOL(__mutex_rt_init);
 
 static __always_inline int __mutex_lock_common(struct mutex *lock,
 					       unsigned int state,
@@ -542,6 +540,13 @@ static __always_inline int __mutex_lock_common(struct mutex *lock,
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
+void mutex_rt_init_lockdep(struct mutex *mutex, const char *name, struct lock_class_key *key)
+{
+	__mutex_rt_init_generic(mutex);
+	lockdep_init_map_wait(&mutex->dep_map, name, key, 0, LD_WAIT_SLEEP);
+}
+EXPORT_SYMBOL(mutex_rt_init_lockdep);
+
 void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass)
 {
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
@@ -598,6 +603,12 @@ int __sched _mutex_trylock_nest_lock(struct mutex *lock,
 EXPORT_SYMBOL_GPL(_mutex_trylock_nest_lock);
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 
+void mutex_rt_init_generic(struct mutex *mutex)
+{
+	__mutex_rt_init_generic(mutex);
+}
+EXPORT_SYMBOL(mutex_rt_init_generic);
+
 void __sched mutex_lock(struct mutex *lock)
 {
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 87b03d2e41db..2338b3adfb55 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -184,8 +184,8 @@ void do_raw_read_unlock(rwlock_t *lock)
 static inline void debug_write_lock_before(rwlock_t *lock)
 {
 	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
-	RWLOCK_BUG_ON(lock->owner == current, lock, "recursion");
-	RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+	RWLOCK_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion");
+	RWLOCK_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(),
 							lock, "cpu recursion");
 }
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7097de2c8cda..4f97896887ec 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -313,10 +313,8 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 {
 	struct signal_struct *sig = tsk->signal;
-	u64 utime, stime;
 	struct task_struct *t;
-	unsigned int seq, nextseq;
-	unsigned long flags;
+	u64 utime, stime;
 
 	/*
 	 * Update current task runtime to account pending time since last
@@ -329,27 +327,19 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	if (same_thread_group(current, tsk))
 		(void) task_sched_runtime(current);
 
-	rcu_read_lock();
-	/* Attempt a lockless read on the first round. */
-	nextseq = 0;
-	do {
-		seq = nextseq;
-		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+	guard(rcu)();
+	scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) {
 		times->utime = sig->utime;
 		times->stime = sig->stime;
 		times->sum_exec_runtime = sig->sum_sched_runtime;
 
-		for_each_thread(tsk, t) {
+		__for_each_thread(sig, t) {
 			task_cputime(t, &utime, &stime);
 			times->utime += utime;
 			times->stime += stime;
 			times->sum_exec_runtime += read_sum_exec_runtime(t);
 		}
-		/* If lockless access failed, take the lock. */
-		nextseq = 1;
-	} while (need_seqretry(&sig->stats_lock, seq));
-	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
-	rcu_read_unlock();
+	}
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
diff --git a/rust/kernel/debugfs/traits.rs b/rust/kernel/debugfs/traits.rs
index ab009eb254b3..92054fed2136 100644
--- a/rust/kernel/debugfs/traits.rs
+++ b/rust/kernel/debugfs/traits.rs
@@ -4,14 +4,11 @@
 //! Traits for rendering or updating values exported to DebugFS.
 
 use crate::prelude::*;
+use crate::sync::atomic::{Atomic, AtomicBasicOps, AtomicType, Relaxed};
 use crate::sync::Mutex;
 use crate::uaccess::UserSliceReader;
 use core::fmt::{self, Debug, Formatter};
 use core::str::FromStr;
-use core::sync::atomic::{
-    AtomicI16, AtomicI32, AtomicI64, AtomicI8, AtomicIsize, AtomicU16, AtomicU32, AtomicU64,
-    AtomicU8, AtomicUsize, Ordering,
-};
 
 /// A trait for types that can be written into a string.
 ///
@@ -50,7 +47,7 @@ pub trait Reader {
     fn read_from_slice(&self, reader: &mut UserSliceReader) -> Result;
 }
 
-impl<T: FromStr> Reader for Mutex<T> {
+impl<T: FromStr + Unpin> Reader for Mutex<T> {
     fn read_from_slice(&self, reader: &mut UserSliceReader) -> Result {
         let mut buf = [0u8; 128];
         if reader.len() > buf.len() {
@@ -66,37 +63,21 @@ fn read_from_slice(&self, reader: &mut UserSliceReader) -> Result {
     }
 }
 
-macro_rules! impl_reader_for_atomic {
-    ($(($atomic_type:ty, $int_type:ty)),*) => {
-        $(
-            impl Reader for $atomic_type {
-                fn read_from_slice(&self, reader: &mut UserSliceReader) -> Result {
-                    let mut buf = [0u8; 21]; // Enough for a 64-bit number.
-                    if reader.len() > buf.len() {
-                        return Err(EINVAL);
-                    }
-                    let n = reader.len();
-                    reader.read_slice(&mut buf[..n])?;
+impl<T: AtomicType + FromStr> Reader for Atomic<T>
+where
+    T::Repr: AtomicBasicOps,
+{
+    fn read_from_slice(&self, reader: &mut UserSliceReader) -> Result {
+        let mut buf = [0u8; 21]; // Enough for a 64-bit number.
+        if reader.len() > buf.len() {
+            return Err(EINVAL);
+        }
+        let n = reader.len();
+        reader.read_slice(&mut buf[..n])?;
 
-                    let s = core::str::from_utf8(&buf[..n]).map_err(|_| EINVAL)?;
-                    let val = s.trim().parse::<$int_type>().map_err(|_| EINVAL)?;
-                    self.store(val, Ordering::Relaxed);
-                    Ok(())
-                }
-            }
-        )*
-    };
+        let s = core::str::from_utf8(&buf[..n]).map_err(|_| EINVAL)?;
+        let val = s.trim().parse::<T>().map_err(|_| EINVAL)?;
+        self.store(val, Relaxed);
+        Ok(())
+    }
 }
-
-impl_reader_for_atomic!(
-    (AtomicI16, i16),
-    (AtomicI32, i32),
-    (AtomicI64, i64),
-    (AtomicI8, i8),
-    (AtomicIsize, isize),
-    (AtomicU16, u16),
-    (AtomicU32, u32),
-    (AtomicU64, u64),
-    (AtomicU8, u8),
-    (AtomicUsize, usize)
-);
diff --git a/rust/kernel/sync/atomic.rs b/rust/kernel/sync/atomic.rs
index 016a6bcaf080..3afc376be42d 100644
--- a/rust/kernel/sync/atomic.rs
+++ b/rust/kernel/sync/atomic.rs
@@ -22,9 +22,10 @@
 
 pub use internal::AtomicImpl;
 pub use ordering::{Acquire, Full, Relaxed, Release};
+pub(crate) use internal::{AtomicArithmeticOps, AtomicBasicOps, AtomicExchangeOps};
 
 use crate::build_error;
-use internal::{AtomicArithmeticOps, AtomicBasicOps, AtomicExchangeOps, AtomicRepr};
+use internal::AtomicRepr;
 use ordering::OrderingType;
 
 /// A memory location which can be safely modified from multiple execution contexts.
@@ -306,6 +307,15 @@ pub fn store<Ordering: ordering::ReleaseOrRelaxed>(&self, v: T, _: Ordering) {
     }
 }
 
+impl<T: AtomicType + core::fmt::Debug> core::fmt::Debug for Atomic<T>
+where
+    T::Repr: AtomicBasicOps,
+{
+    fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
+        core::fmt::Debug::fmt(&self.load(Relaxed), f)
+    }
+}
+
 impl<T: AtomicType> Atomic<T>
 where
     T::Repr: AtomicExchangeOps,
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index 27202beef90c..cb00fdb94ffd 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -11,7 +11,7 @@
     types::{NotThreadSafe, Opaque, ScopeGuard},
 };
 use core::{cell::UnsafeCell, marker::PhantomPinned, pin::Pin};
-use pin_init::{pin_data, pin_init, PinInit};
+use pin_init::{pin_data, pin_init, PinInit, Wrapper};
 
 pub mod mutex;
 pub mod spinlock;
@@ -115,6 +115,7 @@ pub struct Lock<T: ?Sized, B: Backend> {
     _pin: PhantomPinned,
 
     /// The data protected by the lock.
+    #[pin]
     pub(crate) data: UnsafeCell<T>,
 }
 
@@ -127,9 +128,13 @@ unsafe impl<T: ?Sized + Send, B: Backend> Sync for Lock<T, B> {}
 
 impl<T, B: Backend> Lock<T, B> {
     /// Constructs a new lock initialiser.
-    pub fn new(t: T, name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
+    pub fn new(
+        t: impl PinInit<T>,
+        name: &'static CStr,
+        key: Pin<&'static LockClassKey>,
+    ) -> impl PinInit<Self> {
         pin_init!(Self {
-            data: UnsafeCell::new(t),
+            data <- UnsafeCell::pin_init(t),
             _pin: PhantomPinned,
             // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have
             // static lifetimes so they live indefinitely.
@@ -240,6 +245,31 @@ pub(crate) fn do_unlocked<U>(&mut self, cb: impl FnOnce() -> U) -> U {
 
         cb()
     }
+
+    /// Returns a pinned mutable reference to the protected data.
+    ///
+    /// The guard implements [`DerefMut`] when `T: Unpin`, so for [`Unpin`]
+    /// types [`DerefMut`] should be used instead of this function.
+    ///
+    /// [`DerefMut`]: core::ops::DerefMut
+    /// [`Unpin`]: core::marker::Unpin
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// # use kernel::sync::{Mutex, MutexGuard};
+    /// # use core::{pin::Pin, marker::PhantomPinned};
+    /// struct Data(PhantomPinned);
+    ///
+    /// fn example(mutex: &Mutex<Data>) {
+    ///     let mut data: MutexGuard<'_, Data> = mutex.lock();
+    ///     let mut data: Pin<&mut Data> = data.as_mut();
+    /// }
+    /// ```
+    pub fn as_mut(&mut self) -> Pin<&mut T> {
+        // SAFETY: `self.lock.data` is structurally pinned.
+        unsafe { Pin::new_unchecked(&mut *self.lock.data.get()) }
+    }
 }
 
 impl<T: ?Sized, B: Backend> core::ops::Deref for Guard<'_, T, B> {
@@ -251,7 +281,10 @@ fn deref(&self) -> &Self::Target {
     }
 }
 
-impl<T: ?Sized, B: Backend> core::ops::DerefMut for Guard<'_, T, B> {
+impl<T: ?Sized, B: Backend> core::ops::DerefMut for Guard<'_, T, B>
+where
+    T: Unpin,
+{
     fn deref_mut(&mut self) -> &mut Self::Target {
         // SAFETY: The caller owns the lock, so it is safe to deref the protected data.
         unsafe { &mut *self.lock.data.get() }
diff --git a/rust/kernel/sync/lock/global.rs b/rust/kernel/sync/lock/global.rs
index d65f94b5caf2..38b448032799 100644
--- a/rust/kernel/sync/lock/global.rs
+++ b/rust/kernel/sync/lock/global.rs
@@ -106,7 +106,10 @@ fn deref(&self) -> &Self::Target {
     }
 }
 
-impl<B: GlobalLockBackend> core::ops::DerefMut for GlobalGuard<B> {
+impl<B: GlobalLockBackend> core::ops::DerefMut for GlobalGuard<B>
+where
+    B::Item: Unpin,
+{
     fn deref_mut(&mut self) -> &mut Self::Target {
         &mut self.inner
     }
diff --git a/samples/rust/rust_debugfs.rs b/samples/rust/rust_debugfs.rs
index 82b61a15a34b..711faa07bece 100644
--- a/samples/rust/rust_debugfs.rs
+++ b/samples/rust/rust_debugfs.rs
@@ -32,14 +32,12 @@
 //! ```
 
 use core::str::FromStr;
-use core::sync::atomic::AtomicUsize;
-use core::sync::atomic::Ordering;
 use kernel::c_str;
 use kernel::debugfs::{Dir, File};
 use kernel::new_mutex;
 use kernel::prelude::*;
+use kernel::sync::atomic::{Atomic, Relaxed};
 use kernel::sync::Mutex;
-
 use kernel::{acpi, device::Core, of, platform, str::CString, types::ARef};
 
 kernel::module_platform_driver! {
@@ -59,7 +57,7 @@ struct RustDebugFs {
     #[pin]
     _compatible: File<CString>,
     #[pin]
-    counter: File<AtomicUsize>,
+    counter: File<Atomic<usize>>,
     #[pin]
     inner: File<Mutex<Inner>>,
 }
@@ -109,7 +107,7 @@ fn probe(
     ) -> Result<Pin<KBox<Self>>> {
         let result = KBox::try_pin_init(RustDebugFs::new(pdev), GFP_KERNEL)?;
         // We can still mutate fields through the files which are atomic or mutexed:
-        result.counter.store(91, Ordering::Relaxed);
+        result.counter.store(91, Relaxed);
         {
             let mut guard = result.inner.lock();
             guard.x = guard.y;
@@ -120,8 +118,8 @@ fn probe(
 }
 
 impl RustDebugFs {
-    fn build_counter(dir: &Dir) -> impl PinInit<File<AtomicUsize>> + '_ {
-        dir.read_write_file(c_str!("counter"), AtomicUsize::new(0))
+    fn build_counter(dir: &Dir) -> impl PinInit<File<Atomic<usize>>> + '_ {
+        dir.read_write_file(c_str!("counter"), Atomic::<usize>::new(0))
     }
 
     fn build_inner(dir: &Dir) -> impl PinInit<File<Mutex<Inner>>> + '_ {
diff --git a/samples/rust/rust_debugfs_scoped.rs b/samples/rust/rust_debugfs_scoped.rs
index b0c4e76b123e..9f0ec5f24cda 100644
--- a/samples/rust/rust_debugfs_scoped.rs
+++ b/samples/rust/rust_debugfs_scoped.rs
@@ -6,9 +6,9 @@
 //! `Scope::dir` to create a variety of files without the need to separately
 //! track them all.
 
-use core::sync::atomic::AtomicUsize;
 use kernel::debugfs::{Dir, Scope};
 use kernel::prelude::*;
+use kernel::sync::atomic::Atomic;
 use kernel::sync::Mutex;
 use kernel::{c_str, new_mutex, str::CString};
 
@@ -62,7 +62,7 @@ fn create_file_write(
     let file_name = CString::try_from_fmt(fmt!("{name_str}"))?;
     for sub in items {
         nums.push(
-            AtomicUsize::new(sub.parse().map_err(|_| EINVAL)?),
+            Atomic::<usize>::new(sub.parse().map_err(|_| EINVAL)?),
             GFP_KERNEL,
         )?;
     }
@@ -109,7 +109,7 @@ fn init(device_dir: Dir) -> impl PinInit<Self> {
 
 struct DeviceData {
     name: CString,
-    nums: KVec<AtomicUsize>,
+    nums: KVec<Atomic<usize>>,
 }
 
 fn init_control(base_dir: &Dir, dyn_dirs: Dir) -> impl PinInit<Scope<ModuleData>> + '_ {
diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh
index 592f3ec89b5f..9c1d53f81eb2 100755
--- a/scripts/atomic/gen-atomic-instrumented.sh
+++ b/scripts/atomic/gen-atomic-instrumented.sh
@@ -12,7 +12,7 @@ gen_param_check()
 	local arg="$1"; shift
 	local type="${arg%%:*}"
 	local name="$(gen_param_name "${arg}")"
-	local rw="write"
+	local rw="atomic_write"
 
 	case "${type#c}" in
 	i) return;;
@@ -20,14 +20,17 @@ gen_param_check()
 
 	if [ ${type#c} != ${type} ]; then
 		# We don't write to constant parameters.
-		rw="read"
+		rw="atomic_read"
+	elif [ "${type}" = "p" ] ; then
+		# The "old" argument in try_cmpxchg() gets accessed non-atomically
+		rw="read_write"
 	elif [ "${meta}" != "s" ]; then
 		# An atomic RMW: if this parameter is not a constant, and this atomic is
 		# not just a 's'tore, this parameter is both read from and written to.
-		rw="read_write"
+		rw="atomic_read_write"
 	fi
 
-	printf "\tinstrument_atomic_${rw}(${name}, sizeof(*${name}));\n"
+	printf "\tinstrument_${rw}(${name}, sizeof(*${name}));\n"
 }
 
 #gen_params_checks(meta, arg...)