diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e3903b7..3b3d3aa 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -48,7 +48,7 @@
 		".popsection\n"				\
 		"671:"
 
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
+#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock "
 
 #else /* ! CONFIG_SMP */
 #define LOCK_PREFIX_HERE ""
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 7b44b3c..db70832 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -12,11 +12,11 @@
  */
 
 #ifdef CONFIG_X86_32
-#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
+#define mb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "mfence", \
 				      X86_FEATURE_XMM2) ::: "memory", "cc")
-#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
+#define rmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "lfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
-#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
+#define wmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "sfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define __mb()	asm volatile("mfence":::"memory")
@@ -50,7 +50,7 @@
 #define __dma_rmb()	barrier()
 #define __dma_wmb()	barrier()
 
-#define __smp_mb()	asm volatile("lock; addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
+#define __smp_mb()	asm volatile("lock addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
 
 #define __smp_rmb()	dma_rmb()
 #define __smp_wmb()	barrier()
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 5612648..fd8afc1 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -134,7 +134,7 @@ extern void __add_wrong_size(void)
 	__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
 
 #define __sync_cmpxchg(ptr, old, new, size)				\
-	__raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
+	__raw_cmpxchg((ptr), (old), (new), (size), "lock ")
 
 #define __cmpxchg_local(ptr, old, new, size)				\
 	__raw_cmpxchg((ptr), (old), (new), (size), "")
@@ -222,7 +222,7 @@ extern void __add_wrong_size(void)
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
 #define __sync_try_cmpxchg(ptr, pold, new, size)			\
-	__raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ")
+	__raw_try_cmpxchg((ptr), (pold), (new), (size), "lock ")
 
 #define __try_cmpxchg_local(ptr, pold, new, size)			\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index fd1282a..8806c64 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -91,19 +91,21 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, 
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8)	\
+		: ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	o.full;								\
 })
 
 static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
 {
-	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock; ");
+	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock ");
 }
 #define arch_cmpxchg64 arch_cmpxchg64
 
@@ -119,14 +121,16 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     CC_SET(e)						\
-		     : ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
-				     "+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+		CC_SET(e)						\
+		: ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+				"+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	if (unlikely(!ret))						\
 		*(_oldp) = o.full;					\
@@ -136,7 +140,7 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 
 
 static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
 {
-	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock; ");
+	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock ");
 }
 #define arch_try_cmpxchg64 arch_try_cmpxchg64
 
diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h
index 426fc53..dfbd1eb 100644
--- a/arch/x86/include/asm/edac.h
+++ b/arch/x86/include/asm/edac.h
@@ -13,7 +13,7 @@ static inline void edac_atomic_scrub(void *va, u32 size)
 	 * are interrupt, DMA and SMP safe.
 	 */
 	for (i = 0; i < size / 4; i++, virt_addr++)
-		asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
+		asm volatile("lock addl $0, %0"::"m" (*virt_addr));
 }
 
 #endif /* _ASM_X86_EDAC_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd8..08f5f61 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -348,15 +348,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -378,17 +377,16 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
 									\
@@ -419,15 +417,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -449,19 +446,19 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
+									\
 	likely(success);						\
 })
 
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 6d8d6bc..cd21a04 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -31,7 +31,7 @@
  */
 static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(bts) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -49,7 +49,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(btr) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -66,7 +66,7 @@ static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(btc) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -82,7 +82,7 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
 /**
@@ -95,7 +95,7 @@ static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
 /**
@@ -108,7 +108,7 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
 #define sync_test_bit(nr, addr) test_bit(nr, addr)
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 6cba85c..97222ef 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -192,7 +192,13 @@ static void __split_lock_reenable(struct work_struct *work)
 {
 	sld_update_msr(true);
 }
-static DECLARE_DELAYED_WORK(sl_reenable, __split_lock_reenable);
+/*
+ * In order for each CPU to schedule its delayed work independently of the
+ * others, delayed work struct must be per-CPU. This is not required when
+ * sysctl_sld_mitigate is enabled because of the semaphore that limits
+ * the number of simultaneously scheduled delayed works to 1.
+ */
+static DEFINE_PER_CPU(struct delayed_work, sl_reenable);
 
 /*
  * If a CPU goes offline with pending delayed work to re-enable split lock
@@ -213,7 +219,7 @@ static int splitlock_cpu_offline(unsigned int cpu)
 
 static void split_lock_warn(unsigned long ip)
 {
-	struct delayed_work *work;
+	struct delayed_work *work = NULL;
 	int cpu;
 
 	if (!current->reported_split_lock)
@@ -235,11 +241,17 @@ static void split_lock_warn(unsigned long ip)
 		if (down_interruptible(&buslock_sem) == -EINTR)
 			return;
 		work = &sl_reenable_unlock;
-	} else {
-		work = &sl_reenable;
 	}
 
 	cpu = get_cpu();
+
+	if (!work) {
+		work = this_cpu_ptr(&sl_reenable);
+		/* Deferred initialization of per-CPU struct */
+		if (!work->work.func)
+			INIT_DELAYED_WORK(work, __split_lock_reenable);
+	}
+
 	schedule_delayed_work_on(cpu, work, 2);
 
 	/* Disable split lock detection on this CPU to make progress */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 8cd9327..c782a74 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -448,7 +448,7 @@ irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec,
 static inline void disable_irq_nosync_lockdep(unsigned int irq)
 {
 	disable_irq_nosync(irq);
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_disable();
 #endif
 }
@@ -456,22 +456,14 @@ static inline void disable_irq_nosync_lockdep(unsigned int irq)
 static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags)
 {
 	disable_irq_nosync(irq);
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_save(*flags);
 #endif
 }
 
-static inline void disable_irq_lockdep(unsigned int irq)
-{
-	disable_irq(irq);
-#ifdef CONFIG_LOCKDEP
-	local_irq_disable();
-#endif
-}
-
 static inline void enable_irq_lockdep(unsigned int irq)
 {
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_enable();
 #endif
 	enable_irq(irq);
@@ -479,7 +471,7 @@ static inline void enable_irq_lockdep(unsigned int irq)
 
 static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags)
 {
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_restore(*flags);
 #endif
 	enable_irq(irq);
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 0db4093..a114949 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 97fb6f3..9ef9850 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 4470680..b15757e 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 b36f23d..19b636f 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 4a8df18..c80902e 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)
diff --git a/mm/memory.c b/mm/memory.c
index fb7b8dc..4f6d976 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6834,10 +6834,8 @@ void __might_fault(const char *file, int line)
 	if (pagefault_disabled())
 		return;
 	__might_sleep(file, line);
-#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
 	if (current->mm)
 		might_lock_read(&current->mm->mmap_lock);
-#endif
 }
 EXPORT_SYMBOL(__might_fault);
 #endif
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index de2341c..e1c21eb 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -31,6 +31,7 @@
 #include "signal.c"
 #include "slab.c"
 #include "spinlock.c"
+#include "sync.c"
 #include "task.c"
 #include "uaccess.c"
 #include "vmalloc.c"
diff --git a/rust/helpers/sync.c b/rust/helpers/sync.c
new file mode 100644
index 0000000..ff7e68b
--- /dev/null
+++ b/rust/helpers/sync.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/lockdep.h>
+
+void rust_helper_lockdep_register_key(struct lock_class_key *k)
+{
+	lockdep_register_key(k);
+}
+
+void rust_helper_lockdep_unregister_key(struct lock_class_key *k)
+{
+	lockdep_unregister_key(k);
+}
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 16eab91..4104bc2 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -5,6 +5,8 @@
 //! This module contains the kernel APIs related to synchronisation that have been ported or
 //! wrapped for usage by Rust code in the kernel.
 
+use crate::pin_init;
+use crate::prelude::*;
 use crate::types::Opaque;
 
 mod arc;
@@ -23,15 +25,64 @@ pub use locked_by::LockedBy;
 
 /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`.
 #[repr(transparent)]
-pub struct LockClassKey(Opaque<bindings::lock_class_key>);
+#[pin_data(PinnedDrop)]
+pub struct LockClassKey {
+    #[pin]
+    inner: Opaque<bindings::lock_class_key>,
+}
 
 // SAFETY: `bindings::lock_class_key` is designed to be used concurrently from multiple threads and
 // provides its own synchronization.
 unsafe impl Sync for LockClassKey {}
 
 impl LockClassKey {
+    /// Initializes a dynamically allocated lock class key. In the common case of using a
+    /// statically allocated lock class key, the static_lock_class! macro should be used instead.
+    ///
+    /// # Example
+    /// ```
+    /// # use kernel::{c_str, stack_pin_init};
+    /// # use kernel::alloc::KBox;
+    /// # use kernel::types::ForeignOwnable;
+    /// # use kernel::sync::{LockClassKey, SpinLock};
+    ///
+    /// let key = KBox::pin_init(LockClassKey::new_dynamic(), GFP_KERNEL)?;
+    /// let key_ptr = key.into_foreign();
+    ///
+    /// {
+    ///     stack_pin_init!(let num: SpinLock<u32> = SpinLock::new(
+    ///         0,
+    ///         c_str!("my_spinlock"),
+    ///         // SAFETY: `key_ptr` is returned by the above `into_foreign()`, whose
+    ///         // `from_foreign()` has not yet been called.
+    ///         unsafe { <Pin<KBox<LockClassKey>> as ForeignOwnable>::borrow(key_ptr) }
+    ///     ));
+    /// }
+    ///
+    /// // SAFETY: We dropped `num`, the only use of the key, so the result of the previous
+    /// // `borrow` has also been dropped. Thus, it's safe to use from_foreign.
+    /// unsafe { drop(<Pin<KBox<LockClassKey>> as ForeignOwnable>::from_foreign(key_ptr)) };
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn new_dynamic() -> impl PinInit<Self> {
+        pin_init!(Self {
+            // SAFETY: lockdep_register_key expects an uninitialized block of memory
+            inner <- Opaque::ffi_init(|slot| unsafe { bindings::lockdep_register_key(slot) })
+        })
+    }
+
     pub(crate) fn as_ptr(&self) -> *mut bindings::lock_class_key {
-        self.0.get()
+        self.inner.get()
+    }
+}
+
+#[pinned_drop]
+impl PinnedDrop for LockClassKey {
+    fn drop(self: Pin<&mut Self>) {
+        // SAFETY: self.as_ptr was registered with lockdep and self is pinned, so the address
+        // hasn't changed. Thus, it's safe to pass to unregister.
+        unsafe { bindings::lockdep_unregister_key(self.as_ptr()) }
     }
 }
 
@@ -44,7 +95,7 @@ macro_rules! static_lock_class {
             // SAFETY: lockdep expects uninitialized memory when it's handed a statically allocated
             // lock_class_key
             unsafe { ::core::mem::MaybeUninit::uninit().assume_init() };
-        &CLASS
+        $crate::prelude::Pin::static_ref(&CLASS)
     }};
 }
 
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index 7df5650..fbf68ad 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -11,12 +11,13 @@ use crate::{
     init::PinInit,
     pin_init,
     str::CStr,
-    task::{MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE},
+    task::{
+        MAX_SCHEDULE_TIMEOUT, TASK_FREEZABLE, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE,
+    },
     time::Jiffies,
     types::Opaque,
 };
-use core::marker::PhantomPinned;
-use core::ptr;
+use core::{marker::PhantomPinned, pin::Pin, ptr};
 use macros::pin_data;
 
 /// Creates a [`CondVar`] initialiser with the given name and a newly-created lock class.
@@ -101,7 +102,7 @@ unsafe impl Sync for CondVar {}
 
 impl CondVar {
     /// Constructs a new condvar initialiser.
-    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self> {
+    pub fn new(name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
         pin_init!(Self {
             _pin: PhantomPinned,
             // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have
@@ -159,6 +160,25 @@ impl CondVar {
         crate::current!().signal_pending()
     }
 
+    /// Releases the lock and waits for a notification in interruptible and freezable mode.
+    ///
+    /// The process is allowed to be frozen during this sleep. No lock should be held when calling
+    /// this function, and there is a lockdep assertion for this. Freezing a task that holds a lock
+    /// can trivially deadlock vs another task that needs that lock to complete before it too can
+    /// hit freezable.
+    #[must_use = "wait_interruptible_freezable returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait_interruptible_freezable<T: ?Sized, B: Backend>(
+        &self,
+        guard: &mut Guard<'_, T, B>,
+    ) -> bool {
+        self.wait_internal(
+            TASK_INTERRUPTIBLE | TASK_FREEZABLE,
+            guard,
+            MAX_SCHEDULE_TIMEOUT,
+        );
+        crate::current!().signal_pending()
+    }
+
     /// Releases the lock and waits for a notification in interruptible mode.
     ///
     /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index eb80048..360a10a 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -12,7 +12,7 @@ use crate::{
     str::CStr,
     types::{NotThreadSafe, Opaque, ScopeGuard},
 };
-use core::{cell::UnsafeCell, marker::PhantomPinned};
+use core::{cell::UnsafeCell, marker::PhantomPinned, pin::Pin};
 use macros::pin_data;
 
 pub mod mutex;
@@ -129,7 +129,7 @@ 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: &'static LockClassKey) -> impl PinInit<Self> {
+    pub fn new(t: T, name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
         pin_init!(Self {
             data: UnsafeCell::new(t),
             _pin: PhantomPinned,
@@ -199,7 +199,36 @@ pub struct Guard<'a, T: ?Sized, B: Backend> {
 // SAFETY: `Guard` is sync when the data protected by the lock is also sync.
 unsafe impl<T: Sync + ?Sized, B: Backend> Sync for Guard<'_, T, B> {}
 
-impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
+impl<'a, T: ?Sized, B: Backend> Guard<'a, T, B> {
+    /// Returns the lock that this guard originates from.
+    ///
+    /// # Examples
+    ///
+    /// The following example shows how to use [`Guard::lock_ref()`] to assert the corresponding
+    /// lock is held.
+    ///
+    /// ```
+    /// # use kernel::{new_spinlock, stack_pin_init, sync::lock::{Backend, Guard, Lock}};
+    ///
+    /// fn assert_held<T, B: Backend>(guard: &Guard<'_, T, B>, lock: &Lock<T, B>) {
+    ///     // Address-equal means the same lock.
+    ///     assert!(core::ptr::eq(guard.lock_ref(), lock));
+    /// }
+    ///
+    /// // Creates a new lock on the stack.
+    /// stack_pin_init!{
+    ///     let l = new_spinlock!(42)
+    /// }
+    ///
+    /// let g = l.lock();
+    ///
+    /// // `g` originates from `l`.
+    /// assert_held(&g, &l);
+    /// ```
+    pub fn lock_ref(&self) -> &'a Lock<T, B> {
+        self.lock
+    }
+
     pub(crate) fn do_unlocked<U>(&mut self, cb: impl FnOnce() -> U) -> U {
         // SAFETY: The caller owns the lock, so it is safe to unlock it.
         unsafe { B::unlock(self.lock.state.get(), &self.state) };
diff --git a/rust/kernel/sync/lock/global.rs b/rust/kernel/sync/lock/global.rs
index 480ee72..d65f94b 100644
--- a/rust/kernel/sync/lock/global.rs
+++ b/rust/kernel/sync/lock/global.rs
@@ -13,6 +13,7 @@ use crate::{
 use core::{
     cell::UnsafeCell,
     marker::{PhantomData, PhantomPinned},
+    pin::Pin,
 };
 
 /// Trait implemented for marker types for global locks.
@@ -26,7 +27,7 @@ pub trait GlobalLockBackend {
     /// The backend used for this global lock.
     type Backend: Backend + 'static;
     /// The class for this global lock.
-    fn get_lock_class() -> &'static LockClassKey;
+    fn get_lock_class() -> Pin<&'static LockClassKey>;
 }
 
 /// Type used for global locks.
@@ -270,7 +271,7 @@ macro_rules! global_lock {
             type Item = $valuety;
             type Backend = $crate::global_lock_inner!(backend $kind);
 
-            fn get_lock_class() -> &'static $crate::sync::LockClassKey {
+            fn get_lock_class() -> Pin<&'static $crate::sync::LockClassKey> {
                 $crate::static_lock_class!()
             }
         }
diff --git a/rust/kernel/sync/poll.rs b/rust/kernel/sync/poll.rs
index d5f1715..c4934f8 100644
--- a/rust/kernel/sync/poll.rs
+++ b/rust/kernel/sync/poll.rs
@@ -89,7 +89,7 @@ pub struct PollCondVar {
 
 impl PollCondVar {
     /// Constructs a new condvar initialiser.
-    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self> {
+    pub fn new(name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self> {
         pin_init!(Self {
             inner <- CondVar::new(name, key),
         })
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 38da555..0e40a3d 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -23,6 +23,8 @@ pub const MAX_SCHEDULE_TIMEOUT: c_long = c_long::MAX;
 pub const TASK_INTERRUPTIBLE: c_int = bindings::TASK_INTERRUPTIBLE as c_int;
 /// Bitmask for tasks that are sleeping in an uninterruptible state.
 pub const TASK_UNINTERRUPTIBLE: c_int = bindings::TASK_UNINTERRUPTIBLE as c_int;
+/// Bitmask for tasks that are sleeping in a freezable state.
+pub const TASK_FREEZABLE: c_int = bindings::TASK_FREEZABLE as c_int;
 /// Convenience constant for waking up tasks regardless of whether they are in interruptible or
 /// uninterruptible sleep.
 pub const TASK_NORMAL: c_uint = bindings::TASK_NORMAL as c_uint;
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 4cf9a5a..f98bd02 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -369,7 +369,7 @@ unsafe impl<T: ?Sized, const ID: u64> Sync for Work<T, ID> {}
 impl<T: ?Sized, const ID: u64> Work<T, ID> {
     /// Creates a new instance of [`Work`].
     #[inline]
-    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self>
+    pub fn new(name: &'static CStr, key: Pin<&'static LockClassKey>) -> impl PinInit<Self>
     where
         T: WorkItem<ID>,
     {
