Merge tag 'locking-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Locking primitives:
   - Micro-optimize percpu_{,try_}cmpxchg{64,128}_op() and
     {,try_}cmpxchg{64,128} on x86 (Uros Bizjak)
   - mutexes: extend debug checks in mutex_lock() (Yunhui Cui)
   - Misc cleanups (Uros Bizjak)

  Lockdep:
   - Fix might_fault() lockdep check of current->mm->mmap_lock (Peter
     Zijlstra)
   - Don't disable interrupts on RT in disable_irq_nosync_lockdep.*()
     (Sebastian Andrzej Siewior)
   - Disable KASAN instrumentation of lockdep.c (Waiman Long)
   - Add kasan_check_byte() check in lock_acquire() (Waiman Long)
   - Misc cleanups (Sebastian Andrzej Siewior)

  Rust runtime integration:
   - Use Pin for all LockClassKey usages (Mitchell Levy)
   - sync: Add accessor for the lock behind a given guard (Alice Ryhl)
   - sync: condvar: Add wait_interruptible_freezable() (Alice Ryhl)
   - sync: lock: Add an example for Guard:: Lock_ref() (Boqun Feng)

  Split-lock detection feature (x86):
   - Fix warning mode with disabled mitigation mode (Maksim Davydov)

  Locking events:
   - Add locking events for rtmutex slow paths (Waiman Long)
   - Add locking events for lockdep (Waiman Long)"

* tag 'locking-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  lockdep: Remove disable_irq_lockdep()
  lockdep: Don't disable interrupts on RT in disable_irq_nosync_lockdep.*()
  rust: lockdep: Use Pin for all LockClassKey usages
  rust: sync: condvar: Add wait_interruptible_freezable()
  rust: sync: lock: Add an example for Guard:: Lock_ref()
  rust: sync: Add accessor for the lock behind a given guard
  locking/lockdep: Add kasan_check_byte() check in lock_acquire()
  locking/lockdep: Disable KASAN instrumentation of lockdep.c
  locking/lock_events: Add locking events for lockdep
  locking/lock_events: Add locking events for rtmutex slow paths
  x86/split_lock: Fix the delayed detection logic
  lockdep/mm: Fix might_fault() lockdep check of current->mm->mmap_lock
  x86/locking: Remove semicolon from "lock" prefix
  locking/mutex: Add MUTEX_WARN_ON() into fast path
  x86/locking: Use asm_inline for {,try_}cmpxchg{64,128} emulations
  x86/locking: Use ALT_OUTPUT_SP() for percpu_{,try_}cmpxchg{64,128}_op()

5 files changed, 72 insertions, 7 deletions

diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 0db4093d17b8..a114949eeed5 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -5,7 +5,8 @@ KCOV_INSTRUMENT		:= n
 
 obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
 
-# Avoid recursion lockdep -> sanitizer -> ... -> lockdep.
+# Avoid recursion lockdep -> sanitizer -> ... -> lockdep & improve performance.
+KASAN_SANITIZE_lockdep.o := n
 KCSAN_SANITIZE_lockdep.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
index 97fb6f3f840a..9ef9850aeebe 100644
--- a/kernel/locking/lock_events_list.h
+++ b/kernel/locking/lock_events_list.h
@@ -67,3 +67,31 @@ LOCK_EVENT(rwsem_rlock_handoff)	/* # of read lock handoffs		*/
 LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
 LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
 LOCK_EVENT(rwsem_wlock_handoff)	/* # of write lock handoffs		*/
+
+/*
+ * Locking events for rtlock_slowlock()
+ */
+LOCK_EVENT(rtlock_slowlock)	/* # of rtlock_slowlock() calls		*/
+LOCK_EVENT(rtlock_slow_acq1)	/* # of locks acquired after wait_lock	*/
+LOCK_EVENT(rtlock_slow_acq2)	/* # of locks acquired in for loop	*/
+LOCK_EVENT(rtlock_slow_sleep)	/* # of sleeps				*/
+LOCK_EVENT(rtlock_slow_wake)	/* # of wakeup's			*/
+
+/*
+ * Locking events for rt_mutex_slowlock()
+ */
+LOCK_EVENT(rtmutex_slowlock)	/* # of rt_mutex_slowlock() calls	*/
+LOCK_EVENT(rtmutex_slow_block)	/* # of rt_mutex_slowlock_block() calls	*/
+LOCK_EVENT(rtmutex_slow_acq1)	/* # of locks acquired after wait_lock	*/
+LOCK_EVENT(rtmutex_slow_acq2)	/* # of locks acquired at the end	*/
+LOCK_EVENT(rtmutex_slow_acq3)	/* # of locks acquired in *block()	*/
+LOCK_EVENT(rtmutex_slow_sleep)	/* # of sleeps				*/
+LOCK_EVENT(rtmutex_slow_wake)	/* # of wakeup's			*/
+LOCK_EVENT(rtmutex_deadlock)	/* # of rt_mutex_handle_deadlock()'s	*/
+
+/*
+ * Locking events for lockdep
+ */
+LOCK_EVENT(lockdep_acquire)
+LOCK_EVENT(lockdep_lock)
+LOCK_EVENT(lockdep_nocheck)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4470680f0226..b15757e63626 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -57,10 +57,12 @@
 #include <linux/lockdep.h>
 #include <linux/context_tracking.h>
 #include <linux/console.h>
+#include <linux/kasan.h>
 
 #include <asm/sections.h>
 
 #include "lockdep_internals.h"
+#include "lock_events.h"
 
 #include <trace/events/lock.h>
 
@@ -170,6 +172,7 @@ static struct task_struct *lockdep_selftest_task_struct;
 static int graph_lock(void)
 {
 	lockdep_lock();
+	lockevent_inc(lockdep_lock);
 	/*
 	 * Make sure that if another CPU detected a bug while
 	 * walking the graph we dont change it (while the other
@@ -5091,8 +5094,12 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (unlikely(lock->key == &__lockdep_no_track__))
 		return 0;
 
-	if (!prove_locking || lock->key == &__lockdep_no_validate__)
+	lockevent_inc(lockdep_acquire);
+
+	if (!prove_locking || lock->key == &__lockdep_no_validate__) {
 		check = 0;
+		lockevent_inc(lockdep_nocheck);
+	}
 
 	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
 		class = lock->class_cache[subclass];
@@ -5824,6 +5831,14 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (!debug_locks)
 		return;
 
+	/*
+	 * As KASAN instrumentation is disabled and lock_acquire() is usually
+	 * the first lockdep call when a task tries to acquire a lock, add
+	 * kasan_check_byte() here to check for use-after-free and other
+	 * memory errors.
+	 */
+	kasan_check_byte(lock);
+
 	if (unlikely(!lockdep_enabled())) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index b36f23de48f1..19b636f60a24 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -143,6 +143,8 @@ static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
 	unsigned long curr = (unsigned long)current;
 	unsigned long zero = 0UL;
 
+	MUTEX_WARN_ON(lock->magic != lock);
+
 	if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
 		return true;
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4a8df1800cbb..c80902eacd79 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -27,6 +27,7 @@
 #include <trace/events/lock.h>
 
 #include "rtmutex_common.h"
+#include "lock_events.h"
 
 #ifndef WW_RT
 # define build_ww_mutex()	(false)
@@ -1612,10 +1613,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 	struct task_struct *owner;
 	int ret = 0;
 
+	lockevent_inc(rtmutex_slow_block);
 	for (;;) {
 		/* Try to acquire the lock: */
-		if (try_to_take_rt_mutex(lock, current, waiter))
+		if (try_to_take_rt_mutex(lock, current, waiter)) {
+			lockevent_inc(rtmutex_slow_acq3);
 			break;
+		}
 
 		if (timeout && !timeout->task) {
 			ret = -ETIMEDOUT;
@@ -1638,8 +1642,10 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = NULL;
 		raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q);
 
-		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
+		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner)) {
+			lockevent_inc(rtmutex_slow_sleep);
 			rt_mutex_schedule();
+		}
 
 		raw_spin_lock_irq(&lock->wait_lock);
 		set_current_state(state);
@@ -1694,6 +1700,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 	int ret;
 
 	lockdep_assert_held(&lock->wait_lock);
+	lockevent_inc(rtmutex_slowlock);
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock, current, NULL)) {
@@ -1701,6 +1708,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 			__ww_mutex_check_waiters(rtm, ww_ctx, wake_q);
 			ww_mutex_lock_acquired(ww, ww_ctx);
 		}
+		lockevent_inc(rtmutex_slow_acq1);
 		return 0;
 	}
 
@@ -1719,10 +1727,12 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 				__ww_mutex_check_waiters(rtm, ww_ctx, wake_q);
 			ww_mutex_lock_acquired(ww, ww_ctx);
 		}
+		lockevent_inc(rtmutex_slow_acq2);
 	} else {
 		__set_current_state(TASK_RUNNING);
 		remove_waiter(lock, waiter);
 		rt_mutex_handle_deadlock(ret, chwalk, lock, waiter);
+		lockevent_inc(rtmutex_deadlock);
 	}
 
 	/*
@@ -1751,6 +1761,7 @@ static inline int __rt_mutex_slowlock_locked(struct rt_mutex_base *lock,
 				  &waiter, wake_q);
 
 	debug_rt_mutex_free_waiter(&waiter);
+	lockevent_cond_inc(rtmutex_slow_wake, !wake_q_empty(wake_q));
 	return ret;
 }
 
@@ -1823,9 +1834,12 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 	struct task_struct *owner;
 
 	lockdep_assert_held(&lock->wait_lock);
+	lockevent_inc(rtlock_slowlock);
 
-	if (try_to_take_rt_mutex(lock, current, NULL))
+	if (try_to_take_rt_mutex(lock, current, NULL)) {
+		lockevent_inc(rtlock_slow_acq1);
 		return;
+	}
 
 	rt_mutex_init_rtlock_waiter(&waiter);
 
@@ -1838,8 +1852,10 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 
 	for (;;) {
 		/* Try to acquire the lock again */
-		if (try_to_take_rt_mutex(lock, current, &waiter))
+		if (try_to_take_rt_mutex(lock, current, &waiter)) {
+			lockevent_inc(rtlock_slow_acq2);
 			break;
+		}
 
 		if (&waiter == rt_mutex_top_waiter(lock))
 			owner = rt_mutex_owner(lock);
@@ -1847,8 +1863,10 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 			owner = NULL;
 		raw_spin_unlock_irq_wake(&lock->wait_lock, wake_q);
 
-		if (!owner || !rtmutex_spin_on_owner(lock, &waiter, owner))
+		if (!owner || !rtmutex_spin_on_owner(lock, &waiter, owner)) {
+			lockevent_inc(rtlock_slow_sleep);
 			schedule_rtlock();
+		}
 
 		raw_spin_lock_irq(&lock->wait_lock);
 		set_current_state(TASK_RTLOCK_WAIT);
@@ -1865,6 +1883,7 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock,
 	debug_rt_mutex_free_waiter(&waiter);
 
 	trace_contention_end(lock, 0);
+	lockevent_cond_inc(rtlock_slow_wake, !wake_q_empty(wake_q));
 }
 
 static __always_inline void __sched rtlock_slowlock(struct rt_mutex_base *lock)