Merge tag 'locking-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Lockdep:
   - Enable PROVE_RAW_LOCK_NESTING with PROVE_LOCKING (Sebastian Andrzej
     Siewior)
   - Add lockdep_cleanup_dead_cpu() (David Woodhouse)

  futexes:
   - Use atomic64_inc_return() in get_inode_sequence_number() (Uros
     Bizjak)
   - Use atomic64_try_cmpxchg_relaxed() in get_inode_sequence_number()
     (Uros Bizjak)

  RT locking:
   - Add sparse annotation PREEMPT_RT's locking (Sebastian Andrzej
     Siewior)

  spinlocks:
   - Use atomic_try_cmpxchg_release() in osq_unlock() (Uros Bizjak)

  atomics:
   - x86: Use ALT_OUTPUT_SP() for __alternative_atomic64() (Uros Bizjak)
   - x86: Use ALT_OUTPUT_SP() for __arch_{,try_}cmpxchg64_emu() (Uros
     Bizjak)

  KCSAN, seqlocks:
   - Support seqcount_latch_t (Marco Elver)

  <linux/cleanup.h>:
   - Add if_not_guard() conditional guard helper (David Lechner)
   - Adjust scoped_guard() macros to avoid potential warning (Przemek
     Kitszel)
   - Remove address space of returned pointer (Uros Bizjak)

  WW mutexes:
   - locking/ww_mutex: Adjust to lockdep nest_lock requirements (Thomas
     Hellström)

  Rust integration:
   - Fix raw_spin_lock initialization on PREEMPT_RT (Eder Zulian)

  Misc cleanups & fixes:
   - lockdep: Fix wait-type check related warnings (Ahmed Ehab)
   - lockdep: Use info level for initial info messages (Jiri Slaby)
   - spinlocks: Make __raw_* lock ops static (Geert Uytterhoeven)
   - pvqspinlock: Convert fields of 'enum vcpu_state' to uppercase
     (Qiuxu Zhuo)
   - iio: magnetometer: Fix if () scoped_guard() formatting (Stephen
     Rothwell)
   - rtmutex: Fix misleading comment (Peter Zijlstra)
   - percpu-rw-semaphores: Fix grammar in percpu-rw-semaphore.rst (Xiu
     Jianfeng)"

* tag 'locking-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  locking/Documentation: Fix grammar in percpu-rw-semaphore.rst
  iio: magnetometer: fix if () scoped_guard() formatting
  rust: helpers: Avoid raw_spin_lock initialization for PREEMPT_RT
  kcsan, seqlock: Fix incorrect assumption in read_seqbegin()
  seqlock, treewide: Switch to non-raw seqcount_latch interface
  kcsan, seqlock: Support seqcount_latch_t
  time/sched_clock: Broaden sched_clock()'s instrumentation coverage
  time/sched_clock: Swap update_clock_read_data() latch writes
  locking/atomic/x86: Use ALT_OUTPUT_SP() for __arch_{,try_}cmpxchg64_emu()
  locking/atomic/x86: Use ALT_OUTPUT_SP() for __alternative_atomic64()
  cleanup: Add conditional guard helper
  cleanup: Adjust scoped_guard() macros to avoid potential warning
  locking/osq_lock: Use atomic_try_cmpxchg_release() in osq_unlock()
  cleanup: Remove address space of returned pointer
  locking/rtmutex: Fix misleading comment
  locking/rt: Annotate unlock followed by lock for sparse.
  locking/rt: Add sparse annotation for RCU.
  locking/rt: Remove one __cond_lock() in RT's spin_trylock_irqsave()
  locking/rt: Add sparse annotation PREEMPT_RT's sleeping locks.
  locking/pvqspinlock: Convert fields of 'enum vcpu_state' to uppercase
  ...

13 files changed, 116 insertions, 71 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index d293d52a3e00..c4aaf73dec9e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1338,6 +1338,7 @@ static int takedown_cpu(unsigned int cpu)
 
 	cpuhp_bp_sync_dead(cpu);
 
+	lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu));
 	tick_cleanup_dead_cpu(cpu);
 
 	/*
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 136768ae2637..692912bf1252 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -181,12 +181,12 @@ static u64 get_inode_sequence_number(struct inode *inode)
 		return old;
 
 	for (;;) {
-		u64 new = atomic64_add_return(1, &i_seq);
+		u64 new = atomic64_inc_return(&i_seq);
 		if (WARN_ON_ONCE(!new))
 			continue;
 
-		old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new);
-		if (old)
+		old = 0;
+		if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new))
 			return old;
 		return new;
 	}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 536bd471557f..2d8ec0351ef9 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4586,6 +4586,30 @@ void lockdep_softirqs_off(unsigned long ip)
 		debug_atomic_inc(redundant_softirqs_off);
 }
 
+/**
+ * lockdep_cleanup_dead_cpu - Ensure CPU lockdep state is cleanly stopped
+ *
+ * @cpu: index of offlined CPU
+ * @idle: task pointer for offlined CPU's idle thread
+ *
+ * Invoked after the CPU is dead. Ensures that the tracing infrastructure
+ * is left in a suitable state for the CPU to be subsequently brought
+ * online again.
+ */
+void lockdep_cleanup_dead_cpu(unsigned int cpu, struct task_struct *idle)
+{
+	if (unlikely(!debug_locks))
+		return;
+
+	if (unlikely(per_cpu(hardirqs_enabled, cpu))) {
+		pr_warn("CPU %u left hardirqs enabled!", cpu);
+		if (idle)
+			print_irqtrace_events(idle);
+		/* Clean it up for when the CPU comes online again. */
+		per_cpu(hardirqs_enabled, cpu) = 0;
+	}
+}
+
 static int
 mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 {
@@ -6576,17 +6600,17 @@ EXPORT_SYMBOL_GPL(lockdep_unregister_key);
 
 void __init lockdep_init(void)
 {
-	printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
+	pr_info("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
 
-	printk("... MAX_LOCKDEP_SUBCLASSES:  %lu\n", MAX_LOCKDEP_SUBCLASSES);
-	printk("... MAX_LOCK_DEPTH:          %lu\n", MAX_LOCK_DEPTH);
-	printk("... MAX_LOCKDEP_KEYS:        %lu\n", MAX_LOCKDEP_KEYS);
-	printk("... CLASSHASH_SIZE:          %lu\n", CLASSHASH_SIZE);
-	printk("... MAX_LOCKDEP_ENTRIES:     %lu\n", MAX_LOCKDEP_ENTRIES);
-	printk("... MAX_LOCKDEP_CHAINS:      %lu\n", MAX_LOCKDEP_CHAINS);
-	printk("... CHAINHASH_SIZE:          %lu\n", CHAINHASH_SIZE);
+	pr_info("... MAX_LOCKDEP_SUBCLASSES:  %lu\n", MAX_LOCKDEP_SUBCLASSES);
+	pr_info("... MAX_LOCK_DEPTH:          %lu\n", MAX_LOCK_DEPTH);
+	pr_info("... MAX_LOCKDEP_KEYS:        %lu\n", MAX_LOCKDEP_KEYS);
+	pr_info("... CLASSHASH_SIZE:          %lu\n", CLASSHASH_SIZE);
+	pr_info("... MAX_LOCKDEP_ENTRIES:     %lu\n", MAX_LOCKDEP_ENTRIES);
+	pr_info("... MAX_LOCKDEP_CHAINS:      %lu\n", MAX_LOCKDEP_CHAINS);
+	pr_info("... CHAINHASH_SIZE:          %lu\n", CHAINHASH_SIZE);
 
-	printk(" memory used by lock dependency info: %zu kB\n",
+	pr_info(" memory used by lock dependency info: %zu kB\n",
 	       (sizeof(lock_classes) +
 		sizeof(lock_classes_in_use) +
 		sizeof(classhash_table) +
@@ -6604,12 +6628,12 @@ void __init lockdep_init(void)
 		);
 
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
-	printk(" memory used for stack traces: %zu kB\n",
+	pr_info(" memory used for stack traces: %zu kB\n",
 	       (sizeof(stack_trace) + sizeof(stack_trace_hash)) / 1024
 	       );
 #endif
 
-	printk(" per task-struct memory footprint: %zu bytes\n",
+	pr_info(" per task-struct memory footprint: %zu bytes\n",
 	       sizeof(((struct task_struct *)NULL)->held_locks));
 }
 
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 75a6f6133866..b4233dc2c2b0 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -215,8 +215,7 @@ void osq_unlock(struct optimistic_spin_queue *lock)
 	/*
 	 * Fast path for the uncontended case.
 	 */
-	if (likely(atomic_cmpxchg_release(&lock->tail, curr,
-					  OSQ_UNLOCKED_VAL) == curr))
+	if (atomic_try_cmpxchg_release(&lock->tail, &curr, OSQ_UNLOCKED_VAL))
 		return;
 
 	/*
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index ac2e22502741..dc1cb90e3644 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -38,13 +38,13 @@
 #define PV_PREV_CHECK_MASK	0xff
 
 /*
- * Queue node uses: vcpu_running & vcpu_halted.
- * Queue head uses: vcpu_running & vcpu_hashed.
+ * Queue node uses: VCPU_RUNNING & VCPU_HALTED.
+ * Queue head uses: VCPU_RUNNING & VCPU_HASHED.
  */
 enum vcpu_state {
-	vcpu_running = 0,
-	vcpu_halted,		/* Used only in pv_wait_node */
-	vcpu_hashed,		/* = pv_hash'ed + vcpu_halted */
+	VCPU_RUNNING = 0,
+	VCPU_HALTED,		/* Used only in pv_wait_node */
+	VCPU_HASHED,		/* = pv_hash'ed + VCPU_HALTED */
 };
 
 struct pv_node {
@@ -266,7 +266,7 @@ pv_wait_early(struct pv_node *prev, int loop)
 	if ((loop & PV_PREV_CHECK_MASK) != 0)
 		return false;
 
-	return READ_ONCE(prev->state) != vcpu_running;
+	return READ_ONCE(prev->state) != VCPU_RUNNING;
 }
 
 /*
@@ -279,7 +279,7 @@ static void pv_init_node(struct mcs_spinlock *node)
 	BUILD_BUG_ON(sizeof(struct pv_node) > sizeof(struct qnode));
 
 	pn->cpu = smp_processor_id();
-	pn->state = vcpu_running;
+	pn->state = VCPU_RUNNING;
 }
 
 /*
@@ -308,26 +308,26 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 		/*
 		 * Order pn->state vs pn->locked thusly:
 		 *
-		 * [S] pn->state = vcpu_halted	  [S] next->locked = 1
+		 * [S] pn->state = VCPU_HALTED	  [S] next->locked = 1
 		 *     MB			      MB
-		 * [L] pn->locked		[RmW] pn->state = vcpu_hashed
+		 * [L] pn->locked		[RmW] pn->state = VCPU_HASHED
 		 *
 		 * Matches the cmpxchg() from pv_kick_node().
 		 */
-		smp_store_mb(pn->state, vcpu_halted);
+		smp_store_mb(pn->state, VCPU_HALTED);
 
 		if (!READ_ONCE(node->locked)) {
 			lockevent_inc(pv_wait_node);
 			lockevent_cond_inc(pv_wait_early, wait_early);
-			pv_wait(&pn->state, vcpu_halted);
+			pv_wait(&pn->state, VCPU_HALTED);
 		}
 
 		/*
-		 * If pv_kick_node() changed us to vcpu_hashed, retain that
+		 * If pv_kick_node() changed us to VCPU_HASHED, retain that
 		 * value so that pv_wait_head_or_lock() knows to not also try
 		 * to hash this lock.
 		 */
-		cmpxchg(&pn->state, vcpu_halted, vcpu_running);
+		cmpxchg(&pn->state, VCPU_HALTED, VCPU_RUNNING);
 
 		/*
 		 * If the locked flag is still not set after wakeup, it is a
@@ -357,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	u8 old = vcpu_halted;
+	u8 old = VCPU_HALTED;
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
 	 * pv_wait_node(). If OTOH this fails, the vCPU was running and will
@@ -374,7 +374,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * subsequent writes.
 	 */
 	smp_mb__before_atomic();
-	if (!try_cmpxchg_relaxed(&pn->state, &old, vcpu_hashed))
+	if (!try_cmpxchg_relaxed(&pn->state, &old, VCPU_HASHED))
 		return;
 
 	/*
@@ -407,7 +407,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * If pv_kick_node() already advanced our state, we don't need to
 	 * insert ourselves into the hash table anymore.
 	 */
-	if (READ_ONCE(pn->state) == vcpu_hashed)
+	if (READ_ONCE(pn->state) == VCPU_HASHED)
 		lp = (struct qspinlock **)1;
 
 	/*
@@ -420,7 +420,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 		 * Set correct vCPU state to be used by queue node wait-early
 		 * mechanism.
 		 */
-		WRITE_ONCE(pn->state, vcpu_running);
+		WRITE_ONCE(pn->state, VCPU_RUNNING);
 
 		/*
 		 * Set the pending bit in the active lock spinning loop to
@@ -460,7 +460,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 				goto gotlock;
 			}
 		}
-		WRITE_ONCE(pn->state, vcpu_hashed);
+		WRITE_ONCE(pn->state, VCPU_HASHED);
 		lockevent_inc(pv_wait_head);
 		lockevent_cond_inc(pv_wait_again, waitcnt);
 		pv_wait(&lock->locked, _Q_SLOW_VAL);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index ebebd0eec7f6..d3b72c2f983f 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1601,6 +1601,7 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 					   unsigned int state,
 					   struct hrtimer_sleeper *timeout,
 					   struct rt_mutex_waiter *waiter)
+	__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
 {
 	struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex);
 	struct task_struct *owner;
@@ -1805,6 +1806,7 @@ static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock,
  * @lock:	The underlying RT mutex
  */
 static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock)
+	__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
 {
 	struct rt_mutex_waiter waiter;
 	struct task_struct *owner;
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index a6974d044593..7e79258feb27 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -175,10 +175,10 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex_base *lock,
 	}
 
 	/*
-	 * We've already deboosted, mark_wakeup_next_waiter() will
-	 * retain preempt_disabled when we drop the wait_lock, to
-	 * avoid inversion prior to the wakeup.  preempt_disable()
-	 * therein pairs with rt_mutex_postunlock().
+	 * mark_wakeup_next_waiter() deboosts and retains preemption
+	 * disabled when dropping the wait_lock, to avoid inversion prior
+	 * to the wakeup.  preempt_disable() therein pairs with the
+	 * preempt_enable() in rt_mutex_postunlock().
 	 */
 	mark_wakeup_next_waiter(wqh, lock);
 
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 438c6086d540..7685defd7c52 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -65,7 +65,7 @@ EXPORT_PER_CPU_SYMBOL(__mmiowb_state);
  * towards that other CPU that it should break the lock ASAP.
  */
 #define BUILD_LOCK_OPS(op, locktype)					\
-void __lockfunc __raw_##op##_lock(locktype##_t *lock)			\
+static void __lockfunc __raw_##op##_lock(locktype##_t *lock)		\
 {									\
 	for (;;) {							\
 		preempt_disable();					\
@@ -77,7 +77,7 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock)			\
 	}								\
 }									\
 									\
-unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock)	\
+static unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
 {									\
 	unsigned long flags;						\
 									\
@@ -95,12 +95,12 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock)	\
 	return flags;							\
 }									\
 									\
-void __lockfunc __raw_##op##_lock_irq(locktype##_t *lock)		\
+static void __lockfunc __raw_##op##_lock_irq(locktype##_t *lock)	\
 {									\
 	_raw_##op##_lock_irqsave(lock);					\
 }									\
 									\
-void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock)		\
+static void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock)		\
 {									\
 	unsigned long flags;						\
 									\
diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c
index 38e292454fcc..d1cf8b2b6dca 100644
--- a/kernel/locking/spinlock_rt.c
+++ b/kernel/locking/spinlock_rt.c
@@ -51,7 +51,7 @@ static __always_inline void __rt_spin_lock(spinlock_t *lock)
 	migrate_disable();
 }
 
-void __sched rt_spin_lock(spinlock_t *lock)
+void __sched rt_spin_lock(spinlock_t *lock) __acquires(RCU)
 {
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 	__rt_spin_lock(lock);
@@ -75,7 +75,7 @@ void __sched rt_spin_lock_nest_lock(spinlock_t *lock,
 EXPORT_SYMBOL(rt_spin_lock_nest_lock);
 #endif
 
-void __sched rt_spin_unlock(spinlock_t *lock)
+void __sched rt_spin_unlock(spinlock_t *lock) __releases(RCU)
 {
 	spin_release(&lock->dep_map, _RET_IP_);
 	migrate_enable();
@@ -225,7 +225,7 @@ int __sched rt_write_trylock(rwlock_t *rwlock)
 }
 EXPORT_SYMBOL(rt_write_trylock);
 
-void __sched rt_read_lock(rwlock_t *rwlock)
+void __sched rt_read_lock(rwlock_t *rwlock) __acquires(RCU)
 {
 	rtlock_might_resched();
 	rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
@@ -235,7 +235,7 @@ void __sched rt_read_lock(rwlock_t *rwlock)
 }
 EXPORT_SYMBOL(rt_read_lock);
 
-void __sched rt_write_lock(rwlock_t *rwlock)
+void __sched rt_write_lock(rwlock_t *rwlock) __acquires(RCU)
 {
 	rtlock_might_resched();
 	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
@@ -246,7 +246,7 @@ void __sched rt_write_lock(rwlock_t *rwlock)
 EXPORT_SYMBOL(rt_write_lock);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass)
+void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) __acquires(RCU)
 {
 	rtlock_might_resched();
 	rwlock_acquire(&rwlock->dep_map, subclass, 0, _RET_IP_);
@@ -257,7 +257,7 @@ void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass)
 EXPORT_SYMBOL(rt_write_lock_nested);
 #endif
 
-void __sched rt_read_unlock(rwlock_t *rwlock)
+void __sched rt_read_unlock(rwlock_t *rwlock) __releases(RCU)
 {
 	rwlock_release(&rwlock->dep_map, _RET_IP_);
 	migrate_enable();
@@ -266,7 +266,7 @@ void __sched rt_read_unlock(rwlock_t *rwlock)
 }
 EXPORT_SYMBOL(rt_read_unlock);
 
-void __sched rt_write_unlock(rwlock_t *rwlock)
+void __sched rt_write_unlock(rwlock_t *rwlock) __releases(RCU)
 {
 	rwlock_release(&rwlock->dep_map, _RET_IP_);
 	rcu_read_unlock();
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 10a5736a21c2..5d58b2c0ef98 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -62,7 +62,8 @@ static int __test_mutex(unsigned int flags)
 	int ret;
 
 	ww_mutex_init(&mtx.mutex, &ww_class);
-	ww_acquire_init(&ctx, &ww_class);
+	if (flags & TEST_MTX_CTX)
+		ww_acquire_init(&ctx, &ww_class);
 
 	INIT_WORK_ONSTACK(&mtx.work, test_mutex_work);
 	init_completion(&mtx.ready);
@@ -90,7 +91,8 @@ static int __test_mutex(unsigned int flags)
 		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
 	}
 	ww_mutex_unlock(&mtx.mutex);
-	ww_acquire_fini(&ctx);
+	if (flags & TEST_MTX_CTX)
+		ww_acquire_fini(&ctx);
 
 	if (ret) {
 		pr_err("%s(flags=%x): mutual exclusion failure\n",
@@ -679,7 +681,7 @@ static int __init test_ww_mutex_init(void)
 	if (ret)
 		return ret;
 
-	ret = stress(2047, hweight32(STRESS_ALL)*ncpus, STRESS_ALL);
+	ret = stress(2046, hweight32(STRESS_ALL)*ncpus, STRESS_ALL);
 	if (ret)
 		return ret;
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index beb808f4c367..19911c8fa7b6 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -560,10 +560,11 @@ bool printk_percpu_data_ready(void)
 /* Must be called under syslog_lock. */
 static void latched_seq_write(struct latched_seq *ls, u64 val)
 {
-	raw_write_seqcount_latch(&ls->latch);
+	write_seqcount_latch_begin(&ls->latch);
 	ls->val[0] = val;
-	raw_write_seqcount_latch(&ls->latch);
+	write_seqcount_latch(&ls->latch);
 	ls->val[1] = val;
+	write_seqcount_latch_end(&ls->latch);
 }
 
 /* Can be called from any context. */
@@ -574,10 +575,10 @@ static u64 latched_seq_read_nolock(struct latched_seq *ls)
 	u64 val;
 
 	do {
-		seq = raw_read_seqcount_latch(&ls->latch);
+		seq = read_seqcount_latch(&ls->latch);
 		idx = seq & 0x1;
 		val = ls->val[idx];
-	} while (raw_read_seqcount_latch_retry(&ls->latch, seq));
+	} while (read_seqcount_latch_retry(&ls->latch, seq));
 
 	return val;
 }
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 68d6c1190ac7..fcca4e72f1ef 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -71,16 +71,16 @@ static __always_inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 
 notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
 {
-	*seq = raw_read_seqcount_latch(&cd.seq);
+	*seq = read_seqcount_latch(&cd.seq);
 	return cd.read_data + (*seq & 1);
 }
 
 notrace int sched_clock_read_retry(unsigned int seq)
 {
-	return raw_read_seqcount_latch_retry(&cd.seq, seq);
+	return read_seqcount_latch_retry(&cd.seq, seq);
 }
 
-unsigned long long noinstr sched_clock_noinstr(void)
+static __always_inline unsigned long long __sched_clock(void)
 {
 	struct clock_read_data *rd;
 	unsigned int seq;
@@ -98,11 +98,23 @@ unsigned long long noinstr sched_clock_noinstr(void)
 	return res;
 }
 
+unsigned long long noinstr sched_clock_noinstr(void)
+{
+	return __sched_clock();
+}
+
 unsigned long long notrace sched_clock(void)
 {
 	unsigned long long ns;
 	preempt_disable_notrace();
-	ns = sched_clock_noinstr();
+	/*
+	 * All of __sched_clock() is a seqcount_latch reader critical section,
+	 * but relies on the raw helpers which are uninstrumented. For KCSAN,
+	 * mark all accesses in __sched_clock() as atomic.
+	 */
+	kcsan_nestable_atomic_begin();
+	ns = __sched_clock();
+	kcsan_nestable_atomic_end();
 	preempt_enable_notrace();
 	return ns;
 }
@@ -119,17 +131,19 @@ unsigned long long notrace sched_clock(void)
  */
 static void update_clock_read_data(struct clock_read_data *rd)
 {
-	/* update the backup (odd) copy with the new data */
-	cd.read_data[1] = *rd;
-
 	/* steer readers towards the odd copy */
-	raw_write_seqcount_latch(&cd.seq);
+	write_seqcount_latch_begin(&cd.seq);
 
 	/* now its safe for us to update the normal (even) copy */
 	cd.read_data[0] = *rd;
 
 	/* switch readers back to the even copy */
-	raw_write_seqcount_latch(&cd.seq);
+	write_seqcount_latch(&cd.seq);
+
+	/* update the backup (odd) copy with the new data */
+	cd.read_data[1] = *rd;
+
+	write_seqcount_latch_end(&cd.seq);
 }
 
 /*
@@ -267,7 +281,7 @@ void __init generic_sched_clock_init(void)
  */
 static u64 notrace suspended_sched_clock_read(void)
 {
-	unsigned int seq = raw_read_seqcount_latch(&cd.seq);
+	unsigned int seq = read_seqcount_latch(&cd.seq);
 
 	return cd.read_data[seq & 1].epoch_cyc;
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 962b2a31f015..cdd61990cd14 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -428,7 +428,7 @@ static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
  * We want to use this from any context including NMI and tracing /
  * instrumenting the timekeeping code itself.
  *
- * Employ the latch technique; see @raw_write_seqcount_latch.
+ * Employ the latch technique; see @write_seqcount_latch.
  *
  * So if a NMI hits the update of base[0] then it will use base[1]
  * which is still consistent. In the worst case this can result is a
@@ -441,16 +441,18 @@ static void update_fast_timekeeper(const struct tk_read_base *tkr,
 	struct tk_read_base *base = tkf->base;
 
 	/* Force readers off to base[1] */
-	raw_write_seqcount_latch(&tkf->seq);
+	write_seqcount_latch_begin(&tkf->seq);
 
 	/* Update base[0] */
 	memcpy(base, tkr, sizeof(*base));
 
 	/* Force readers back to base[0] */
-	raw_write_seqcount_latch(&tkf->seq);
+	write_seqcount_latch(&tkf->seq);
 
 	/* Update base[1] */
 	memcpy(base + 1, base, sizeof(*base));
+
+	write_seqcount_latch_end(&tkf->seq);
 }
 
 static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
@@ -460,11 +462,11 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 	u64 now;
 
 	do {
-		seq = raw_read_seqcount_latch(&tkf->seq);
+		seq = read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
 		now = ktime_to_ns(tkr->base);
 		now += __timekeeping_get_ns(tkr);
-	} while (raw_read_seqcount_latch_retry(&tkf->seq, seq));
+	} while (read_seqcount_latch_retry(&tkf->seq, seq));
 
 	return now;
 }