Merge tag 'locking-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Changes in this cycle were:

  Bitops & cpumask:
   - Always inline various generic helpers, to improve code generation,
     but also for instrumentation, found by noinstr validation.

   - Add a x86-specific cpumask_clear_cpu() helper to improve code
     generation

  Atomics:
   - Fix atomic64_{read_acquire,set_release} fallbacks

  Lockdep:
   - Fix /proc/lockdep output loop iteration for classes

   - Fix /proc/lockdep potential access to invalid memory

   - Add Mark Rutland as reviewer for atomic primitives

   - Minor cleanups

  Jump labels:
   - Clean up the code a bit

  Misc:
   - Add __sched annotations to percpu rwsem primitives

   - Enable RT_MUTEXES on PREEMPT_RT by default

   - Stray v8086_mode() inlining fix, result of noinstr objtool
     validation"

* tag 'locking-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  jump_label: Refactor #ifdef of struct static_key
  jump_label: Avoid unneeded casts in STATIC_KEY_INIT_{TRUE,FALSE}
  locking/lockdep: Iterate lock_classes directly when reading lockdep files
  x86/ptrace: Always inline v8086_mode() for instrumentation
  cpumask: Add a x86-specific cpumask_clear_cpu() helper
  locking: Enable RT_MUTEXES by default on PREEMPT_RT.
  locking/local_lock: Make the empty local_lock_*() function a macro.
  atomics: Fix atomic64_{read_acquire,set_release} fallbacks
  locking: Add missing __sched attributes
  cpumask: Always inline helpers which use bit manipulation functions
  asm-generic/bitops: Always inline all bit manipulation helpers
  locking/lockdep: Avoid potential access of invalid memory in lock_class
  lockdep: Use memset_startat() helper in reinit_class()
  MAINTAINERS: add myself as reviewer for atomics

17 files changed, 168 insertions, 74 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 4386b12f86e8..37adcd621a02 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3205,6 +3205,7 @@ ATOMIC INFRASTRUCTURE
 M:	Will Deacon <will@kernel.org>
 M:	Peter Zijlstra <peterz@infradead.org>
 R:	Boqun Feng <boqun.feng@gmail.com>
+R:	Mark Rutland <mark.rutland@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	arch/*/include/asm/atomic*.h
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 3afa990d756b..c5aed9e9226c 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -20,11 +20,21 @@ static __always_inline bool arch_cpu_online(int cpu)
 {
 	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
 }
+
+static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	arch_clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
 #else
 static __always_inline bool arch_cpu_online(int cpu)
 {
 	return cpu == 0;
 }
+
+static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	return;
+}
 #endif
 
 #define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 703663175a5a..4357e0f2cd5f 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -137,7 +137,7 @@ static __always_inline int user_mode(struct pt_regs *regs)
 #endif
 }
 
-static inline int v8086_mode(struct pt_regs *regs)
+static __always_inline int v8086_mode(struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_32
 	return (regs->flags & X86_VM_MASK);
diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h
index c90192b1c755..4225a8ca9c1a 100644
--- a/include/asm-generic/bitops/instrumented-atomic.h
+++ b/include/asm-generic/bitops/instrumented-atomic.h
@@ -23,7 +23,7 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void set_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_set_bit(nr, addr);
@@ -36,7 +36,7 @@ static inline void set_bit(long nr, volatile unsigned long *addr)
  *
  * This is a relaxed atomic operation (no implied memory barriers).
  */
-static inline void clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void clear_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_clear_bit(nr, addr);
@@ -52,7 +52,7 @@ static inline void clear_bit(long nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_change_bit(nr, addr);
@@ -65,7 +65,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
@@ -79,7 +79,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
@@ -93,7 +93,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index 37363d570b9b..7ab1ecc37782 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -22,7 +22,7 @@
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___set_bit(nr, addr);
@@ -37,7 +37,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___clear_bit(nr, addr);
@@ -52,13 +52,13 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___change_bit(nr, addr);
 }
 
-static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
+static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
 {
 	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) {
 		/*
@@ -90,7 +90,7 @@ static inline void __instrument_read_write_bitop(long nr, volatile unsigned long
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_set_bit(nr, addr);
@@ -104,7 +104,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_clear_bit(nr, addr);
@@ -118,7 +118,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_change_bit(nr, addr);
@@ -129,7 +129,7 @@ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline bool test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool test_bit(long nr, const volatile unsigned long *addr)
 {
 	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_bit(nr, addr);
diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h
index a3dba31df01e..6db58d180866 100644
--- a/include/linux/atomic/atomic-arch-fallback.h
+++ b/include/linux/atomic/atomic-arch-fallback.h
@@ -151,7 +151,16 @@
 static __always_inline int
 arch_atomic_read_acquire(const atomic_t *v)
 {
-	return smp_load_acquire(&(v)->counter);
+	int ret;
+
+	if (__native_word(atomic_t)) {
+		ret = smp_load_acquire(&(v)->counter);
+	} else {
+		ret = arch_atomic_read(v);
+		__atomic_acquire_fence();
+	}
+
+	return ret;
 }
 #define arch_atomic_read_acquire arch_atomic_read_acquire
 #endif
@@ -160,7 +169,12 @@ arch_atomic_read_acquire(const atomic_t *v)
 static __always_inline void
 arch_atomic_set_release(atomic_t *v, int i)
 {
-	smp_store_release(&(v)->counter, i);
+	if (__native_word(atomic_t)) {
+		smp_store_release(&(v)->counter, i);
+	} else {
+		__atomic_release_fence();
+		arch_atomic_set(v, i);
+	}
 }
 #define arch_atomic_set_release arch_atomic_set_release
 #endif
@@ -1258,7 +1272,16 @@ arch_atomic_dec_if_positive(atomic_t *v)
 static __always_inline s64
 arch_atomic64_read_acquire(const atomic64_t *v)
 {
-	return smp_load_acquire(&(v)->counter);
+	s64 ret;
+
+	if (__native_word(atomic64_t)) {
+		ret = smp_load_acquire(&(v)->counter);
+	} else {
+		ret = arch_atomic64_read(v);
+		__atomic_acquire_fence();
+	}
+
+	return ret;
 }
 #define arch_atomic64_read_acquire arch_atomic64_read_acquire
 #endif
@@ -1267,7 +1290,12 @@ arch_atomic64_read_acquire(const atomic64_t *v)
 static __always_inline void
 arch_atomic64_set_release(atomic64_t *v, s64 i)
 {
-	smp_store_release(&(v)->counter, i);
+	if (__native_word(atomic64_t)) {
+		smp_store_release(&(v)->counter, i);
+	} else {
+		__atomic_release_fence();
+		arch_atomic64_set(v, i);
+	}
 }
 #define arch_atomic64_set_release arch_atomic64_set_release
 #endif
@@ -2358,4 +2386,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// cca554917d7ea73d5e3e7397dd70c484cad9b2c4
+// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 64dae70d31f5..fe29ac7cc469 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -102,7 +102,7 @@ extern atomic_t __num_online_cpus;
 
 extern cpumask_t cpus_booted_once_mask;
 
-static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
+static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
 {
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 	WARN_ON_ONCE(cpu >= bits);
@@ -110,7 +110,7 @@ static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
 }
 
 /* verify cpu argument to cpumask_* operators */
-static inline unsigned int cpumask_check(unsigned int cpu)
+static __always_inline unsigned int cpumask_check(unsigned int cpu)
 {
 	cpu_max_bits_warn(cpu, nr_cpumask_bits);
 	return cpu;
@@ -341,12 +341,12 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -357,12 +357,12 @@ static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 {
 	clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 {
 	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -374,7 +374,7 @@ static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  *
  * Returns 1 if @cpu is set in @cpumask, else returns 0
  */
-static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
 	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
 }
@@ -388,7 +388,7 @@ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
  *
  * test_and_set_bit wrapper for cpumasks.
  */
-static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -402,7 +402,7 @@ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
  *
  * test_and_clear_bit wrapper for cpumasks.
  */
-static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 48b9b2a82767..107751cc047b 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -82,10 +82,9 @@ extern bool static_key_initialized;
 				    "%s(): static key '%pS' used before call to jump_label_init()", \
 				    __func__, (key))
 
-#ifdef CONFIG_JUMP_LABEL
-
 struct static_key {
 	atomic_t enabled;
+#ifdef CONFIG_JUMP_LABEL
 /*
  * Note:
  *   To make anonymous unions work with old compilers, the static
@@ -104,13 +103,9 @@ struct static_key {
 		struct jump_entry *entries;
 		struct static_key_mod *next;
 	};
+#endif	/* CONFIG_JUMP_LABEL */
 };
 
-#else
-struct static_key {
-	atomic_t enabled;
-};
-#endif	/* CONFIG_JUMP_LABEL */
 #endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_JUMP_LABEL
@@ -251,10 +246,10 @@ extern void static_key_disable_cpuslocked(struct static_key *key);
  */
 #define STATIC_KEY_INIT_TRUE					\
 	{ .enabled = { 1 },					\
-	  { .entries = (void *)JUMP_TYPE_TRUE } }
+	  { .type = JUMP_TYPE_TRUE } }
 #define STATIC_KEY_INIT_FALSE					\
 	{ .enabled = { 0 },					\
-	  { .entries = (void *)JUMP_TYPE_FALSE } }
+	  { .type = JUMP_TYPE_FALSE } }
 
 #else  /* !CONFIG_JUMP_LABEL */
 
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 975e33b793a7..6d635e8306d6 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l)
 }
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 # define LOCAL_LOCK_DEBUG_INIT(lockname)
-static inline void local_lock_acquire(local_lock_t *l) { }
-static inline void local_lock_release(local_lock_t *l) { }
-static inline void local_lock_debug_init(local_lock_t *l) { }
+# define local_lock_acquire(__ll)  do { typecheck(local_lock_t *, __ll); } while (0)
+# define local_lock_release(__ll)  do { typecheck(local_lock_t *, __ll); } while (0)
+# define local_lock_debug_init(__ll)  do { typecheck(local_lock_t *, __ll); } while (0)
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 #define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }
diff --git a/init/Kconfig b/init/Kconfig
index e9119bf54b1f..beb5b866c318 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2054,6 +2054,7 @@ source "arch/Kconfig"
 
 config RT_MUTEXES
 	bool
+	default y if PREEMPT_RT
 
 config BASE_SMALL
 	int
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index f8a0212189ca..c06cab6546ed 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -183,11 +183,9 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
 static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
 unsigned long nr_lock_classes;
 unsigned long nr_zapped_classes;
-#ifndef CONFIG_DEBUG_LOCKDEP
-static
-#endif
+unsigned long max_lock_class_idx;
 struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
-static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
+DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
 
 static inline struct lock_class *hlock_class(struct held_lock *hlock)
 {
@@ -338,7 +336,7 @@ static inline void lock_release_holdtime(struct held_lock *hlock)
  * elements. These elements are linked together by the lock_entry member in
  * struct lock_class.
  */
-LIST_HEAD(all_lock_classes);
+static LIST_HEAD(all_lock_classes);
 static LIST_HEAD(free_lock_classes);
 
 /**
@@ -1252,6 +1250,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	struct lockdep_subclass_key *key;
 	struct hlist_head *hash_head;
 	struct lock_class *class;
+	int idx;
 
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
@@ -1317,6 +1316,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * of classes.
 	 */
 	list_move_tail(&class->lock_entry, &all_lock_classes);
+	idx = class - lock_classes;
+	if (idx > max_lock_class_idx)
+		max_lock_class_idx = idx;
 
 	if (verbose(class)) {
 		graph_unlock();
@@ -6000,6 +6002,8 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 		WRITE_ONCE(class->name, NULL);
 		nr_lock_classes--;
 		__clear_bit(class - lock_classes, lock_classes_in_use);
+		if (class - lock_classes == max_lock_class_idx)
+			max_lock_class_idx--;
 	} else {
 		WARN_ONCE(true, "%s() failed for class %s\n", __func__,
 			  class->name);
@@ -6011,13 +6015,10 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 
 static void reinit_class(struct lock_class *class)
 {
-	void *const p = class;
-	const unsigned int offset = offsetof(struct lock_class, key);
-
 	WARN_ON_ONCE(!class->lock_entry.next);
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
-	memset(p + offset, 0, sizeof(*class) - offset);
+	memset_startat(class, 0, key);
 	WARN_ON_ONCE(!class->lock_entry.next);
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
@@ -6290,7 +6291,13 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 		lockdep_reset_lock_reg(lock);
 }
 
-/* Unregister a dynamically allocated key. */
+/*
+ * Unregister a dynamically allocated key.
+ *
+ * Unlike lockdep_register_key(), a search is always done to find a matching
+ * key irrespective of debug_locks to avoid potential invalid access to freed
+ * memory in lock_class entry.
+ */
 void lockdep_unregister_key(struct lock_class_key *key)
 {
 	struct hlist_head *hash_head = keyhashentry(key);
@@ -6305,10 +6312,8 @@ void lockdep_unregister_key(struct lock_class_key *key)
 		return;
 
 	raw_local_irq_save(flags);
-	if (!graph_lock())
-		goto out_irq;
+	lockdep_lock();
 
-	pf = get_pending_free();
 	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
 		if (k == key) {
 			hlist_del_rcu(&k->hash_entry);
@@ -6316,11 +6321,13 @@ void lockdep_unregister_key(struct lock_class_key *key)
 			break;
 		}
 	}
-	WARN_ON_ONCE(!found);
-	__lockdep_free_key_range(pf, key, 1);
-	call_rcu_zapped(pf);
-	graph_unlock();
-out_irq:
+	WARN_ON_ONCE(!found && debug_locks);
+	if (found) {
+		pf = get_pending_free();
+		__lockdep_free_key_range(pf, key, 1);
+		call_rcu_zapped(pf);
+	}
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
 	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index ecb8662e7a4e..bbe9000260d0 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -121,7 +121,6 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 
 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
 
-extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
 #define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
@@ -151,6 +150,10 @@ extern unsigned int nr_large_chain_blocks;
 
 extern unsigned int max_lockdep_depth;
 extern unsigned int max_bfs_queue_depth;
+extern unsigned long max_lock_class_idx;
+
+extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+extern unsigned long lock_classes_in_use[];
 
 #ifdef CONFIG_PROVE_LOCKING
 extern unsigned long lockdep_count_forward_deps(struct lock_class *);
@@ -205,7 +208,6 @@ struct lockdep_stats {
 };
 
 DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
-extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
 #define __debug_atomic_inc(ptr)					\
 	this_cpu_inc(lockdep_stats.ptr);
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index b8d9a050c337..15fdc7fa5c68 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -24,14 +24,33 @@
 
 #include "lockdep_internals.h"
 
+/*
+ * Since iteration of lock_classes is done without holding the lockdep lock,
+ * it is not safe to iterate all_lock_classes list directly as the iteration
+ * may branch off to free_lock_classes or the zapped list. Iteration is done
+ * directly on the lock_classes array by checking the lock_classes_in_use
+ * bitmap and max_lock_class_idx.
+ */
+#define iterate_lock_classes(idx, class)				\
+	for (idx = 0, class = lock_classes; idx <= max_lock_class_idx;	\
+	     idx++, class++)
+
 static void *l_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	return seq_list_next(v, &all_lock_classes, pos);
+	struct lock_class *class = v;
+
+	++class;
+	*pos = class - lock_classes;
+	return (*pos > max_lock_class_idx) ? NULL : class;
 }
 
 static void *l_start(struct seq_file *m, loff_t *pos)
 {
-	return seq_list_start_head(&all_lock_classes, *pos);
+	unsigned long idx = *pos;
+
+	if (idx > max_lock_class_idx)
+		return NULL;
+	return lock_classes + idx;
 }
 
 static void l_stop(struct seq_file *m, void *v)
@@ -57,14 +76,16 @@ static void print_name(struct seq_file *m, struct lock_class *class)
 
 static int l_show(struct seq_file *m, void *v)
 {
-	struct lock_class *class = list_entry(v, struct lock_class, lock_entry);
+	struct lock_class *class = v;
 	struct lock_list *entry;
 	char usage[LOCK_USAGE_CHARS];
+	int idx = class - lock_classes;
 
-	if (v == &all_lock_classes) {
+	if (v == lock_classes)
 		seq_printf(m, "all lock classes:\n");
+
+	if (!test_bit(idx, lock_classes_in_use))
 		return 0;
-	}
 
 	seq_printf(m, "%p", class->key);
 #ifdef CONFIG_DEBUG_LOCKDEP
@@ -220,8 +241,11 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class;
+	unsigned long idx;
 
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
+	iterate_lock_classes(idx, class) {
+		if (!test_bit(idx, lock_classes_in_use))
+			continue;
 
 		if (class->usage_mask == 0)
 			nr_unused++;
@@ -254,6 +278,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 
 		sum_forward_deps += lockdep_count_forward_deps(class);
 	}
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 	DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused);
 #endif
@@ -345,6 +370,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, " max bfs queue depth:           %11u\n",
 			max_bfs_queue_depth);
 #endif
+	seq_printf(m, " max lock class index:          %11lu\n",
+			max_lock_class_idx);
 	lockdep_stats_debug_show(m);
 	seq_printf(m, " debug_locks:                   %11u\n",
 			debug_locks);
@@ -622,12 +649,16 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 	if (!res) {
 		struct lock_stat_data *iter = data->stats;
 		struct seq_file *m = file->private_data;
+		unsigned long idx;
 
-		list_for_each_entry(class, &all_lock_classes, lock_entry) {
+		iterate_lock_classes(idx, class) {
+			if (!test_bit(idx, lock_classes_in_use))
+				continue;
 			iter->class = class;
 			iter->stats = lock_stats(class);
 			iter++;
 		}
+
 		data->iter_end = iter;
 
 		sort(data->stats, data->iter_end - data->stats,
@@ -645,6 +676,7 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf,
 			       size_t count, loff_t *ppos)
 {
 	struct lock_class *class;
+	unsigned long idx;
 	char c;
 
 	if (count) {
@@ -654,8 +686,11 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf,
 		if (c != '0')
 			return count;
 
-		list_for_each_entry(class, &all_lock_classes, lock_entry)
+		iterate_lock_classes(idx, class) {
+			if (!test_bit(idx, lock_classes_in_use))
+				continue;
 			clear_lock_stats(class);
+		}
 	}
 	return count;
 }
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 70a32a576f3f..c9fdae94e098 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -7,6 +7,7 @@
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/debug.h>
 #include <linux/errno.h>
 
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
@@ -162,7 +163,7 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	__set_current_state(TASK_RUNNING);
 }
 
-bool __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
+bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 {
 	if (__percpu_down_read_trylock(sem))
 		return true;
@@ -211,7 +212,7 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem)
 	return true;
 }
 
-void percpu_down_write(struct percpu_rw_semaphore *sem)
+void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 69aba4abe104..acde5d6f1254 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1048,7 +1048,7 @@ out_nolock:
 /*
  * Wait until we successfully acquire the write lock
  */
-static struct rw_semaphore *
+static struct rw_semaphore __sched *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
 	long count;
diff --git a/scripts/atomic/fallbacks/read_acquire b/scripts/atomic/fallbacks/read_acquire
index 803ba7561076..a0ea1d26e6b2 100755
--- a/scripts/atomic/fallbacks/read_acquire
+++ b/scripts/atomic/fallbacks/read_acquire
@@ -2,6 +2,15 @@ cat <<EOF
 static __always_inline ${ret}
 arch_${atomic}_read_acquire(const ${atomic}_t *v)
 {
-	return smp_load_acquire(&(v)->counter);
+	${int} ret;
+
+	if (__native_word(${atomic}_t)) {
+		ret = smp_load_acquire(&(v)->counter);
+	} else {
+		ret = arch_${atomic}_read(v);
+		__atomic_acquire_fence();
+	}
+
+	return ret;
 }
 EOF
diff --git a/scripts/atomic/fallbacks/set_release b/scripts/atomic/fallbacks/set_release
index 86ede759f24e..05cdb7f42477 100755
--- a/scripts/atomic/fallbacks/set_release
+++ b/scripts/atomic/fallbacks/set_release
@@ -2,6 +2,11 @@ cat <<EOF
 static __always_inline void
 arch_${atomic}_set_release(${atomic}_t *v, ${int} i)
 {
-	smp_store_release(&(v)->counter, i);
+	if (__native_word(${atomic}_t)) {
+		smp_store_release(&(v)->counter, i);
+	} else {
+		__atomic_release_fence();
+		arch_${atomic}_set(v, i);
+	}
 }
 EOF