Merge tag 'locking-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Core locking primitives updates:
    - Remove mutex_trylock_recursive() from the API - no users left
    - Simplify + constify the futex code a bit

  Lockdep updates:
    - Teach lockdep about local_lock_t
    - Add CONFIG_DEBUG_IRQFLAGS=y debug config option to check for
      potentially unsafe IRQ mask restoration patterns. (I.e.
      calling raw_local_irq_restore() with IRQs enabled.)
    - Add wait context self-tests
    - Fix graph lock corner case corrupting internal data structures
    - Fix noinstr annotations

  LKMM updates:
    - Simplify the litmus tests
    - Documentation fixes

  KCSAN updates:
    - Re-enable KCSAN instrumentation in lib/random32.c

  Misc fixes:
    - Don't branch-trace static label APIs
    - DocBook fix
    - Remove stale leftover empty file"

* tag 'locking-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  checkpatch: Don't check for mutex_trylock_recursive()
  locking/mutex: Kill mutex_trylock_recursive()
  s390: Use arch_local_irq_{save,restore}() in early boot code
  lockdep: Noinstr annotate warn_bogus_irq_restore()
  locking/lockdep: Avoid unmatched unlock
  locking/rwsem: Remove empty rwsem.h
  locking/rtmutex: Add missing kernel-doc markup
  futex: Remove unneeded gotos
  futex: Change utime parameter to be 'const ... *'
  lockdep: report broken irq restoration
  jump_label: Do not profile branch annotations
  locking: Add Reviewers
  locking/selftests: Add local_lock inversion tests
  locking/lockdep: Exclude local_lock_t from IRQ inversions
  locking/lockdep: Clean up check_redundant() a bit
  locking/lockdep: Add a skip() function to __bfs()
  locking/lockdep: Mark local_lock_t
  locking/selftests: More granular debug_locks_verbose
  lockdep/selftest: Add wait context selftests
  tools/memory-model: Fix typo in klitmus7 compatibility table
  ...

57 files changed, 617 insertions, 294 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a6c806557e25..36d6ce7cc886 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -802,13 +802,14 @@
 			insecure, please do not use on production kernels.
 
 	debug_locks_verbose=
-			[KNL] verbose self-tests
-			Format=<0|1>
+			[KNL] verbose locking self-tests
+			Format: <int>
 			Print debugging info while doing the locking API
 			self-tests.
-			We default to 0 (no extra messages), setting it to
-			1 will print _a lot_ more information - normally
-			only useful to kernel developers.
+			Bitmask for the various LOCKTYPE_ tests. Defaults to 0
+			(no extra messages), setting it to -1 (all bits set)
+			will print _a_lot_ more information - normally only
+			useful to lockdep developers.
 
 	debug_objects	[KNL] Enable object debugging
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d4fff195af5..a50a543e3c81 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10342,6 +10342,8 @@ LOCKING PRIMITIVES
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Will Deacon <will@kernel.org>
+R:	Waiman Long <longman@redhat.com>
+R:	Boqun Feng <boqun.feng@gmail.com> (LOCKDEP)
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c
index ec9f8ad5341c..b7329af076a0 100644
--- a/drivers/s390/char/sclp_early_core.c
+++ b/drivers/s390/char/sclp_early_core.c
@@ -66,13 +66,13 @@ int sclp_early_cmd(sclp_cmdw_t cmd, void *sccb)
 	unsigned long flags;
 	int rc;
 
-	raw_local_irq_save(flags);
+	flags = arch_local_irq_save();
 	rc = sclp_service_call(cmd, sccb);
 	if (rc)
 		goto out;
 	sclp_early_wait_irq();
 out:
-	raw_local_irq_restore(flags);
+	arch_local_irq_restore(flags);
 	return rc;
 }
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index b8fe0c23cfff..df5b405e6305 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -76,6 +76,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #else
 # define likely(x)	__builtin_expect(!!(x), 1)
 # define unlikely(x)	__builtin_expect(!!(x), 0)
+# define likely_notrace(x)	likely(x)
+# define unlikely_notrace(x)	unlikely(x)
 #endif
 
 /* Optimization barrier */
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 8de0e1373de7..600c10da321a 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -149,6 +149,17 @@ do {						\
 # define start_critical_timings() do { } while (0)
 #endif
 
+#ifdef CONFIG_DEBUG_IRQFLAGS
+extern void warn_bogus_irq_restore(void);
+#define raw_check_bogus_irq_restore()			\
+	do {						\
+		if (unlikely(!arch_irqs_disabled()))	\
+			warn_bogus_irq_restore();	\
+	} while (0)
+#else
+#define raw_check_bogus_irq_restore() do { } while (0)
+#endif
+
 /*
  * Wrap the arch provided IRQ routines to provide appropriate checks.
  */
@@ -162,6 +173,7 @@ do {						\
 #define raw_local_irq_restore(flags)			\
 	do {						\
 		typecheck(unsigned long, flags);	\
+		raw_check_bogus_irq_restore();		\
 		arch_local_irq_restore(flags);		\
 	} while (0)
 #define raw_local_save_flags(flags)			\
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 32809624d422..d92691262f51 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -261,14 +261,14 @@ static __always_inline void jump_label_init(void)
 
 static __always_inline bool static_key_false(struct static_key *key)
 {
-	if (unlikely(static_key_count(key) > 0))
+	if (unlikely_notrace(static_key_count(key) > 0))
 		return true;
 	return false;
 }
 
 static __always_inline bool static_key_true(struct static_key *key)
 {
-	if (likely(static_key_count(key) > 0))
+	if (likely_notrace(static_key_count(key) > 0))
 		return true;
 	return false;
 }
@@ -460,7 +460,7 @@ extern bool ____wrong_branch_error(void);
 		branch = !arch_static_branch_jump(&(x)->key, true);		\
 	else									\
 		branch = ____wrong_branch_error();				\
-	likely(branch);								\
+	likely_notrace(branch);								\
 })
 
 #define static_branch_unlikely(x)						\
@@ -472,13 +472,13 @@ extern bool ____wrong_branch_error(void);
 		branch = arch_static_branch(&(x)->key, false);			\
 	else									\
 		branch = ____wrong_branch_error();				\
-	unlikely(branch);							\
+	unlikely_notrace(branch);							\
 })
 
 #else /* !CONFIG_JUMP_LABEL */
 
-#define static_branch_likely(x)		likely(static_key_enabled(&(x)->key))
-#define static_branch_unlikely(x)	unlikely(static_key_enabled(&(x)->key))
+#define static_branch_likely(x)		likely_notrace(static_key_enabled(&(x)->key))
+#define static_branch_unlikely(x)	unlikely_notrace(static_key_enabled(&(x)->key))
 
 #endif /* CONFIG_JUMP_LABEL */
 
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 4a8795b21d77..ded90b097e6e 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -18,6 +18,7 @@ typedef struct {
 	.dep_map = {					\
 		.name = #lockname,			\
 		.wait_type_inner = LD_WAIT_CONFIG,	\
+		.lock_type = LD_LOCK_PERCPU,			\
 	}
 #else
 # define LL_DEP_MAP_INIT(lockname)
@@ -30,7 +31,9 @@ do {								\
 	static struct lock_class_key __key;			\
 								\
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
-	lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \
+			      LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_PERCPU);			\
 } while (0)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b9e9adec73e8..7b7ebf2e28ec 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -185,12 +185,19 @@ extern void lockdep_unregister_key(struct lock_class_key *key);
  * to lockdep:
  */
 
-extern void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
-	struct lock_class_key *key, int subclass, short inner, short outer);
+extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name,
+	struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type);
+
+static inline void
+lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+		       struct lock_class_key *key, int subclass, u8 inner, u8 outer)
+{
+	lockdep_init_map_type(lock, name, key, subclass, inner, LD_WAIT_INV, LD_LOCK_NORMAL);
+}
 
 static inline void
 lockdep_init_map_wait(struct lockdep_map *lock, const char *name,
-		      struct lock_class_key *key, int subclass, short inner)
+		      struct lock_class_key *key, int subclass, u8 inner)
 {
 	lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV);
 }
@@ -340,6 +347,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_init()				do { } while (0)
+# define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \
+		do { (void)(name); (void)(key); } while (0)
 # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \
 		do { (void)(name); (void)(key); } while (0)
 # define lockdep_init_map_wait(lock, name, key, sub, inner) \
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 9a1fd49df17f..2ec9ff5a7fff 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -30,6 +30,12 @@ enum lockdep_wait_type {
 	LD_WAIT_MAX,		/* must be last */
 };
 
+enum lockdep_lock_type {
+	LD_LOCK_NORMAL = 0,	/* normal, catch all */
+	LD_LOCK_PERCPU,		/* percpu */
+	LD_LOCK_MAX,
+};
+
 #ifdef CONFIG_LOCKDEP
 
 /*
@@ -119,8 +125,10 @@ struct lock_class {
 	int				name_version;
 	const char			*name;
 
-	short				wait_type_inner;
-	short				wait_type_outer;
+	u8				wait_type_inner;
+	u8				wait_type_outer;
+	u8				lock_type;
+	/* u8				hole; */
 
 #ifdef CONFIG_LOCK_STAT
 	unsigned long			contention_point[LOCKSTAT_POINTS];
@@ -169,8 +177,10 @@ struct lockdep_map {
 	struct lock_class_key		*key;
 	struct lock_class		*class_cache[NR_LOCKDEP_CACHING_CLASSES];
 	const char			*name;
-	short				wait_type_outer; /* can be taken in this context */
-	short				wait_type_inner; /* presents this context */
+	u8				wait_type_outer; /* can be taken in this context */
+	u8				wait_type_inner; /* presents this context */
+	u8				lock_type;
+	/* u8				hole; */
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
 	unsigned long			ip;
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index dcd185cbfe79..0cd631a19727 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -199,29 +199,4 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
-/*
- * These values are chosen such that FAIL and SUCCESS match the
- * values of the regular mutex_trylock().
- */
-enum mutex_trylock_recursive_enum {
-	MUTEX_TRYLOCK_FAILED    = 0,
-	MUTEX_TRYLOCK_SUCCESS   = 1,
-	MUTEX_TRYLOCK_RECURSIVE,
-};
-
-/**
- * mutex_trylock_recursive - trylock variant that allows recursive locking
- * @lock: mutex to be locked
- *
- * This function should not be used, _ever_. It is purely for hysterical GEM
- * raisins, and once those are gone this will be removed.
- *
- * Returns:
- *  - MUTEX_TRYLOCK_FAILED    - trylock failed,
- *  - MUTEX_TRYLOCK_SUCCESS   - lock acquired,
- *  - MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
- */
-extern /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
-mutex_trylock_recursive(struct mutex *lock);
-
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7688bc983de5..f93f9276d848 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -607,11 +607,11 @@ asmlinkage long sys_unshare(unsigned long unshare_flags);
 
 /* kernel/futex.c */
 asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
-			struct __kernel_timespec __user *utime, u32 __user *uaddr2,
-			u32 val3);
+			  const struct __kernel_timespec __user *utime,
+			  u32 __user *uaddr2, u32 val3);
 asmlinkage long sys_futex_time32(u32 __user *uaddr, int op, u32 val,
-			struct old_timespec32 __user *utime, u32 __user *uaddr2,
-			u32 val3);
+				 const struct old_timespec32 __user *utime,
+				 u32 __user *uaddr2, u32 val3);
 asmlinkage long sys_get_robust_list(int pid,
 				    struct robust_list_head __user * __user *head_ptr,
 				    size_t __user *len_ptr);
diff --git a/kernel/futex.c b/kernel/futex.c
index 45a13eb8894e..e68db7745039 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3012,7 +3012,7 @@ retry:
 		 * Success, we're done! No tricky corner cases.
 		 */
 		if (!ret)
-			goto out_putkey;
+			return ret;
 		/*
 		 * The atomic access to the futex value generated a
 		 * pagefault, so retry the user-access and the wakeup:
@@ -3029,7 +3029,7 @@ retry:
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */
-		goto out_putkey;
+		return ret;
 	}
 
 	/*
@@ -3050,7 +3050,7 @@ retry:
 
 		default:
 			WARN_ON_ONCE(1);
-			goto out_putkey;
+			return ret;
 		}
 	}
 
@@ -3061,7 +3061,6 @@ retry:
 
 out_unlock:
 	spin_unlock(&hb->lock);
-out_putkey:
 	return ret;
 
 pi_retry:
@@ -3763,8 +3762,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
 
 SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
-		struct __kernel_timespec __user *, utime, u32 __user *, uaddr2,
-		u32, val3)
+		const struct __kernel_timespec __user *, utime,
+		u32 __user *, uaddr2, u32, val3)
 {
 	struct timespec64 ts;
 	ktime_t t, *tp = NULL;
@@ -3959,7 +3958,7 @@ err_unlock:
 
 #ifdef CONFIG_COMPAT_32BIT_TIME
 SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
-		struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
+		const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
 		u32, val3)
 {
 	struct timespec64 ts;
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 3994a217bde7..3bf98db9c702 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -12,7 +12,6 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
-#include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
@@ -101,7 +100,7 @@ static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
 static DEFINE_PER_CPU(long, kcsan_skip);
 
 /* For kcsan_prandom_u32_max(). */
-static DEFINE_PER_CPU(struct rnd_state, kcsan_rand_state);
+static DEFINE_PER_CPU(u32, kcsan_rand_state);
 
 static __always_inline atomic_long_t *find_watchpoint(unsigned long addr,
 						      size_t size,
@@ -275,20 +274,17 @@ should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *
 }
 
 /*
- * Returns a pseudo-random number in interval [0, ep_ro). See prandom_u32_max()
- * for more details.
- *
- * The open-coded version here is using only safe primitives for all contexts
- * where we can have KCSAN instrumentation. In particular, we cannot use
- * prandom_u32() directly, as its tracepoint could cause recursion.
+ * Returns a pseudo-random number in interval [0, ep_ro). Simple linear
+ * congruential generator, using constants from "Numerical Recipes".
  */
 static u32 kcsan_prandom_u32_max(u32 ep_ro)
 {
-	struct rnd_state *state = &get_cpu_var(kcsan_rand_state);
-	const u32 res = prandom_u32_state(state);
+	u32 state = this_cpu_read(kcsan_rand_state);
+
+	state = 1664525 * state + 1013904223;
+	this_cpu_write(kcsan_rand_state, state);
 
-	put_cpu_var(kcsan_rand_state);
-	return (u32)(((u64) res * ep_ro) >> 32);
+	return state % ep_ro;
 }
 
 static inline void reset_kcsan_skip(void)
@@ -639,10 +635,14 @@ static __always_inline void check_access(const volatile void *ptr, size_t size,
 
 void __init kcsan_init(void)
 {
+	int cpu;
+
 	BUG_ON(!in_task());
 
 	kcsan_debugfs_init();
-	prandom_seed_full_state(&kcsan_rand_state);
+
+	for_each_possible_cpu(cpu)
+		per_cpu(kcsan_rand_state, cpu) = (u32)get_cycles();
 
 	/*
 	 * We are in the init task, and no other tasks should be running;
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 6d11cfb9b41f..8838f1d7c4a2 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -15,6 +15,7 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
 endif
 
+obj-$(CONFIG_DEBUG_IRQFLAGS) += irqflag-debug.o
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
 obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)
diff --git a/kernel/locking/irqflag-debug.c b/kernel/locking/irqflag-debug.c
new file mode 100644
index 000000000000..810b50344d35
--- /dev/null
+++ b/kernel/locking/irqflag-debug.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/irqflags.h>
+
+noinstr void warn_bogus_irq_restore(void)
+{
+	instrumentation_begin();
+	WARN_ONCE(1, "raw_local_irq_restore() called with IRQs enabled\n");
+	instrumentation_end();
+}
+EXPORT_SYMBOL(warn_bogus_irq_restore);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index bdaf4829098c..c6d0c1dc6253 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1290,6 +1290,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	class->name_version = count_matching_names(class);
 	class->wait_type_inner = lock->wait_type_inner;
 	class->wait_type_outer = lock->wait_type_outer;
+	class->lock_type = lock->lock_type;
 	/*
 	 * We use RCU's safe list-add method to make
 	 * parallel walking of the hash-list safe:
@@ -1671,6 +1672,7 @@ static inline struct lock_list *__bfs_next(struct lock_list *lock, int offset)
 static enum bfs_result __bfs(struct lock_list *source_entry,
 			     void *data,
 			     bool (*match)(struct lock_list *entry, void *data),
+			     bool (*skip)(struct lock_list *entry, void *data),
 			     struct lock_list **target_entry,
 			     int offset)
 {
@@ -1731,7 +1733,12 @@ static enum bfs_result __bfs(struct lock_list *source_entry,
 		/*
 		 * Step 3: we haven't visited this and there is a strong
 		 *         dependency path to this, so check with @match.
+		 *         If @skip is provide and returns true, we skip this
+		 *         lock (and any path this lock is in).
 		 */
+		if (skip && skip(lock, data))
+			continue;
+
 		if (match(lock, data)) {
 			*target_entry = lock;
 			return BFS_RMATCH;
@@ -1774,9 +1781,10 @@ static inline enum bfs_result
 __bfs_forwards(struct lock_list *src_entry,
 	       void *data,
 	       bool (*match)(struct lock_list *entry, void *data),
+	       bool (*skip)(struct lock_list *entry, void *data),
 	       struct lock_list **target_entry)
 {
-	return __bfs(src_entry, data, match, target_entry,
+	return __bfs(src_entry, data, match, skip, target_entry,
 		     offsetof(struct lock_class, locks_after));
 
 }
@@ -1785,9 +1793,10 @@ static inline enum bfs_result
 __bfs_backwards(struct lock_list *src_entry,
 		void *data,
 		bool (*match)(struct lock_list *entry, void *data),
+	       bool (*skip)(struct lock_list *entry, void *data),
 		struct lock_list **target_entry)
 {
-	return __bfs(src_entry, data, match, target_entry,
+	return __bfs(src_entry, data, match, skip, target_entry,
 		     offsetof(struct lock_class, locks_before));
 
 }
@@ -2018,7 +2027,7 @@ static unsigned long __lockdep_count_forward_deps(struct lock_list *this)
 	unsigned long  count = 0;
 	struct lock_list *target_entry;
 
-	__bfs_forwards(this, (void *)&count, noop_count, &target_entry);
+	__bfs_forwards(this, (void *)&count, noop_count, NULL, &target_entry);
 
 	return count;
 }
@@ -2043,7 +2052,7 @@ static unsigned long __lockdep_count_backward_deps(struct lock_list *this)
 	unsigned long  count = 0;
 	struct lock_list *target_entry;
 
-	__bfs_backwards(this, (void *)&count, noop_count, &target_entry);
+	__bfs_backwards(this, (void *)&count, noop_count, NULL, &target_entry);
 
 	return count;
 }
@@ -2071,11 +2080,12 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
 static noinline enum bfs_result
 check_path(struct held_lock *target, struct lock_list *src_entry,
 	   bool (*match)(struct lock_list *entry, void *data),
+	   bool (*skip)(struct lock_list *entry, void *data),
 	   struct lock_list **target_entry)
 {
 	enum bfs_result ret;
 
-	ret = __bfs_forwards(src_entry, target, match, target_entry);
+	ret = __bfs_forwards(src_entry, target, match, skip, target_entry);
 
 	if (unlikely(bfs_error(ret)))
 		print_bfs_bug(ret);
@@ -2102,7 +2112,7 @@ check_noncircular(struct held_lock *src, struct held_lock *target,
 
 	debug_atomic_inc(nr_cyclic_checks);
 
-	ret = check_path(target, &src_entry, hlock_conflict, &target_entry);
+	ret = check_path(target, &src_entry, hlock_conflict, NULL, &target_entry);
 
 	if (unlikely(ret == BFS_RMATCH)) {
 		if (!*trace) {
@@ -2120,46 +2130,6 @@ check_noncircular(struct held_lock *src, struct held_lock *target,
 	return ret;
 }
 
-#ifdef CONFIG_LOCKDEP_SMALL
-/*
- * Check that the dependency graph starting at <src> can lead to
- * <target> or not. If it can, <src> -> <target> dependency is already
- * in the graph.
- *
- * Return BFS_RMATCH if it does, or BFS_RMATCH if it does not, return BFS_E* if
- * any error appears in the bfs search.
- */
-static noinline enum bfs_result
-check_redundant(struct held_lock *src, struct held_lock *target)
-{
-	enum bfs_result ret;
-	struct lock_list *target_entry;
-	struct lock_list src_entry;
-
-	bfs_init_root(&src_entry, src);
-	/*
-	 * Special setup for check_redundant().
-	 *
-	 * To report redundant, we need to find a strong dependency path that
-	 * is equal to or stronger than <src> -> <target>. So if <src> is E,
-	 * we need to let __bfs() only search for a path starting at a -(E*)->,
-	 * we achieve this by setting the initial node's ->only_xr to true in
-	 * that case. And if <prev> is S, we set initial ->only_xr to false
-	 * because both -(S*)-> (equal) and -(E*)-> (stronger) are redundant.
-	 */
-	src_entry.only_xr = src->read == 0;
-
-	debug_atomic_inc(nr_redundant_checks);
-
-	ret = check_path(target, &src_entry, hlock_equal, &target_entry);
-
-	if (ret == BFS_RMATCH)
-		debug_atomic_inc(nr_redundant);
-
-	return ret;
-}
-#endif
-
 #ifdef CONFIG_TRACE_IRQFLAGS
 
 /*
@@ -2230,6 +2200,44 @@ static inline bool usage_match(struct lock_list *entry, void *mask)
 		return !!((entry->class->usage_mask & LOCKF_IRQ) & *(unsigned long *)mask);
 }
 
+static inline bool usage_skip(struct lock_list *entry, void *mask)
+{
+	/*
+	 * Skip local_lock() for irq inversion detection.
+	 *
+	 * For !RT, local_lock() is not a real lock, so it won't carry any
+	 * dependency.
+	 *
+	 * For RT, an irq inversion happens when we have lock A and B, and on
+	 * some CPU we can have:
+	 *
+	 *	lock(A);
+	 *	<interrupted>
+	 *	  lock(B);
+	 *
+	 * where lock(B) cannot sleep, and we have a dependency B -> ... -> A.
+	 *
+	 * Now we prove local_lock() cannot exist in that dependency. First we
+	 * have the observation for any lock chain L1 -> ... -> Ln, for any
+	 * 1 <= i <= n, Li.inner_wait_type <= L1.inner_wait_type, otherwise
+	 * wait context check will complain. And since B is not a sleep lock,
+	 * therefore B.inner_wait_type >= 2, and since the inner_wait_type of
+	 * local_lock() is 3, which is greater than 2, therefore there is no
+	 * way the local_lock() exists in the dependency B -> ... -> A.
+	 *
+	 * As a result, we will skip local_lock(), when we search for irq
+	 * inversion bugs.
+	 */
+	if (entry->class->lock_type == LD_LOCK_PERCPU) {
+		if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
+			return false;
+
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Find a node in the forwards-direction dependency sub-graph starting
  * at @root->class that matches @bit.
@@ -2245,7 +2253,7 @@ find_usage_forwards(struct lock_list *root, unsigned long usage_mask,
 
 	debug_atomic_inc(nr_find_usage_forwards_checks);
 
-	result = __bfs_forwards(root, &usage_mask, usage_match, target_entry);
+	result = __bfs_forwards(root, &usage_mask, usage_match, usage_skip, target_entry);
 
 	return result;
 }
@@ -2262,7 +2270,7 @@ find_usage_backwards(struct lock_list *root, unsigned long usage_mask,
 
 	debug_atomic_inc(nr_find_usage_backwards_checks);
 
-	result = __bfs_backwards(root, &usage_mask, usage_match, target_entry);
+	result = __bfs_backwards(root, &usage_mask, usage_match, usage_skip, target_entry);
 
 	return result;
 }
@@ -2627,7 +2635,7 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 	 */
 	bfs_init_rootb(&this, prev);
 
-	ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL);
+	ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, usage_skip, NULL);
 	if (bfs_error(ret)) {
 		print_bfs_bug(ret);
 		return 0;
@@ -2694,8 +2702,68 @@ static inline int check_irq_usage(struct task_struct *curr,
 {
 	return 1;
 }
+
+static inline bool usage_skip(struct lock_list *entry, void *mask)
+{
+	return false;
+}
+
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
+#ifdef CONFIG_LOCKDEP_SMALL
+/*
+ * Check that the dependency graph starting at <src> can lead to
+ * <target> or not. If it can, <src> -> <target> dependency is already
+ * in the graph.
+ *
+ * Return BFS_RMATCH if it does, or BFS_RMATCH if it does not, return BFS_E* if
+ * any error appears in the bfs search.
+ */
+static noinline enum bfs_result
+check_redundant(struct held_lock *src, struct held_lock *target)
+{
+	enum bfs_result ret;
+	struct lock_list *target_entry;
+	struct lock_list src_entry;
+
+	bfs_init_root(&src_entry, src);
+	/*
+	 * Special setup for check_redundant().
+	 *
+	 * To report redundant, we need to find a strong dependency path that
+	 * is equal to or stronger than <src> -> <target>. So if <src> is E,
+	 * we need to let __bfs() only search for a path starting at a -(E*)->,
+	 * we achieve this by setting the initial node's ->only_xr to true in
+	 * that case. And if <prev> is S, we set initial ->only_xr to false
+	 * because both -(S*)-> (equal) and -(E*)-> (stronger) are redundant.
+	 */
+	src_entry.only_xr = src->read == 0;
+
+	debug_atomic_inc(nr_redundant_checks);
+
+	/*
+	 * Note: we skip local_lock() for redundant check, because as the
+	 * comment in usage_skip(), A -> local_lock() -> B and A -> B are not
+	 * the same.
+	 */
+	ret = check_path(target, &src_entry, hlock_equal, usage_skip, &target_entry);
+
+	if (ret == BFS_RMATCH)
+		debug_atomic_inc(nr_redundant);
+
+	return ret;
+}
+
+#else
+
+static inline enum bfs_result
+check_redundant(struct held_lock *src, struct held_lock *target)
+{
+	return BFS_RNOMATCH;
+}
+
+#endif
+
 static void inc_chains(int irq_context)
 {
 	if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT)
@@ -2916,7 +2984,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		}
 	}
 
-#ifdef CONFIG_LOCKDEP_SMALL
 	/*
 	 * Is the <prev> -> <next> link redundant?
 	 */
@@ -2925,7 +2992,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		return 0;
 	else if (ret == BFS_RMATCH)
 		return 2;
-#endif
 
 	if (!*trace) {
 		*trace = save_trace();
@@ -3707,7 +3773,7 @@ static void
 print_usage_bug(struct task_struct *curr, struct held_lock *this,
 		enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit)
 {
-	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
+	if (!debug_locks_off() || debug_locks_silent)
 		return;
 
 	pr_warn("\n");
@@ -3748,6 +3814,7 @@ valid_state(struct task_struct *curr, struct held_lock *this,
 	    enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
 {
 	if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit))) {
+		graph_unlock();
 		print_usage_bug(curr, this, bad_bit, new_bit);
 		return 0;
 	}
@@ -4503,9 +4570,9 @@ print_lock_invalid_wait_context(struct task_struct *curr,
  */
 static int check_wait_context(struct task_struct *curr, struct held_lock *next)
 {
-	short next_inner = hlock_class(next)->wait_type_inner;
-	short next_outer = hlock_class(next)->wait_type_outer;
-	short curr_inner;
+	u8 next_inner = hlock_class(next)->wait_type_inner;
+	u8 next_outer = hlock_class(next)->wait_type_outer;
+	u8 curr_inner;
 	int depth;
 
 	if (!curr->lockdep_depth || !next_inner || next->trylock)
@@ -4528,7 +4595,7 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
 
 	for (; depth < curr->lockdep_depth; depth++) {
 		struct held_lock *prev = curr->held_locks + depth;
-		short prev_inner = hlock_class(prev)->wait_type_inner;
+		u8 prev_inner = hlock_class(prev)->wait_type_inner;
 
 		if (prev_inner) {
 			/*
@@ -4577,9 +4644,9 @@ static inline int check_wait_context(struct task_struct *curr,
 /*
  * Initialize a lock instance's lock-class mapping info:
  */
-void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+void lockdep_init_map_type(struct lockdep_map *lock, const char *name,
 			    struct lock_class_key *key, int subclass,
-			    short inner, short outer)
+			    u8 inner, u8 outer, u8 lock_type)
 {
 	int i;
 
@@ -4602,6 +4669,7 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
 
 	lock->wait_type_outer = outer;
 	lock->wait_type_inner = inner;
+	lock->lock_type = lock_type;
 
 	/*
 	 * No key, no joy, we need to hash something.
@@ -4636,7 +4704,7 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
 		raw_local_irq_restore(flags);
 	}
 }
-EXPORT_SYMBOL_GPL(lockdep_init_map_waits);
+EXPORT_SYMBOL_GPL(lockdep_init_map_type);
 
 struct lock_class_key __lockdep_no_validate__;
 EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 5352ce50a97e..adb935090768 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -86,16 +86,6 @@ bool mutex_is_locked(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_is_locked);
 
-__must_check enum mutex_trylock_recursive_enum
-mutex_trylock_recursive(struct mutex *lock)
-{
-	if (unlikely(__mutex_owner(lock) == current))
-		return MUTEX_TRYLOCK_RECURSIVE;
-
-	return mutex_trylock(lock);
-}
-EXPORT_SYMBOL(mutex_trylock_recursive);
-
 static inline unsigned long __owner_flags(unsigned long owner)
 {
 	return owner & MUTEX_FLAGS;
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2f8cd616d3b2..47a6e0b8073d 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1604,8 +1604,11 @@ void __sched rt_mutex_unlock(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
 /**
- * Futex variant, that since futex variants do not use the fast-path, can be
- * simple and will not need to retry.
+ * __rt_mutex_futex_unlock - Futex variant, that since futex variants
+ * do not use the fast-path, can be simple and will not need to retry.
+ *
+ * @lock:	The rt_mutex to be unlocked
+ * @wake_q:	The wake queue head from which to get the next lock waiter
  */
 bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
 				    struct wake_q_head *wake_q)
@@ -1662,13 +1665,15 @@ void rt_mutex_destroy(struct rt_mutex *lock)
 EXPORT_SYMBOL_GPL(rt_mutex_destroy);
 
 /**
- * __rt_mutex_init - initialize the rt lock
+ * __rt_mutex_init - initialize the rt_mutex
  *
- * @lock: the rt lock to be initialized
+ * @lock:	The rt_mutex to be initialized
+ * @name:	The lock name used for debugging
+ * @key:	The lock class key used for debugging
  *
- * Initialize the rt lock to unlocked state.
+ * Initialize the rt_mutex to unlocked state.
  *
- * Initializing of a locked rt lock is not allowed
+ * Initializing of a locked rt_mutex is not allowed
  */
 void __rt_mutex_init(struct rt_mutex *lock, const char *name,
 		     struct lock_class_key *key)
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/kernel/locking/rwsem.h
+++ /dev/null
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7937265ef879..5ea0c1773b0a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1335,6 +1335,7 @@ config LOCKDEP_SMALL
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
+	select DEBUG_IRQFLAGS
 	help
 	  If you say Y here, the lock dependency engine will do
 	  additional runtime checks to debug itself, at the price
@@ -1423,6 +1424,13 @@ config TRACE_IRQFLAGS_NMI
 	depends on TRACE_IRQFLAGS
 	depends on TRACE_IRQFLAGS_NMI_SUPPORT
 
+config DEBUG_IRQFLAGS
+	bool "Debug IRQ flag manipulation"
+	help
+	  Enables checks for potentially unsafe enabling or disabling of
+	  interrupts, such as calling raw_local_irq_restore() when interrupts
+	  are enabled.
+
 config STACKTRACE
 	bool "Stack backtrace support"
 	depends on STACKTRACE_SUPPORT
diff --git a/lib/Makefile b/lib/Makefile
index a6b160c3a4fa..fb7d946bb8c3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -27,9 +27,6 @@ KASAN_SANITIZE_string.o := n
 CFLAGS_string.o += -fno-stack-protector
 endif
 
-# Used by KCSAN while enabled, avoid recursion.
-KCSAN_SANITIZE_random32.o := n
-
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o extable.o sha1.o irq_regs.o argv_split.o \
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 9959ea23529e..2d85abac1744 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -24,6 +24,7 @@
 #include <linux/debug_locks.h>
 #include <linux/irqflags.h>
 #include <linux/rtmutex.h>
+#include <linux/local_lock.h>
 
 /*
  * Change this to 1 if you want to see the failure printouts:
@@ -51,6 +52,7 @@ __setup("debug_locks_verbose=", setup_debug_locks_verbose);
 #define LOCKTYPE_RWSEM	0x8
 #define LOCKTYPE_WW	0x10
 #define LOCKTYPE_RTMUTEX 0x20
+#define LOCKTYPE_LL	0x40
 
 static struct ww_acquire_ctx t, t2;
 static struct ww_mutex o, o2, o3;
@@ -64,6 +66,9 @@ static DEFINE_SPINLOCK(lock_B);
 static DEFINE_SPINLOCK(lock_C);
 static DEFINE_SPINLOCK(lock_D);
 
+static DEFINE_RAW_SPINLOCK(raw_lock_A);
+static DEFINE_RAW_SPINLOCK(raw_lock_B);
+
 static DEFINE_RWLOCK(rwlock_A);
 static DEFINE_RWLOCK(rwlock_B);
 static DEFINE_RWLOCK(rwlock_C);
@@ -133,6 +138,8 @@ static DEFINE_RT_MUTEX(rtmutex_Z2);
 
 #endif
 
+static local_lock_t local_A = INIT_LOCAL_LOCK(local_A);
+
 /*
  * non-inlined runtime initializers, to let separate locks share
  * the same lock-class:
@@ -1306,19 +1313,23 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion3_soft_wlock)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define I_SPINLOCK(x)	lockdep_reset_lock(&lock_##x.dep_map)
+# define I_RAW_SPINLOCK(x)	lockdep_reset_lock(&raw_lock_##x.dep_map)
 # define I_RWLOCK(x)	lockdep_reset_lock(&rwlock_##x.dep_map)
 # define I_MUTEX(x)	lockdep_reset_lock(&mutex_##x.dep_map)
 # define I_RWSEM(x)	lockdep_reset_lock(&rwsem_##x.dep_map)
 # define I_WW(x)	lockdep_reset_lock(&x.dep_map)
+# define I_LOCAL_LOCK(x) lockdep_reset_lock(&local_##x.dep_map)
 #ifdef CONFIG_RT_MUTEXES
 # define I_RTMUTEX(x)	lockdep_reset_lock(&rtmutex_##x.dep_map)
 #endif
 #else
 # define I_SPINLOCK(x)
+# define I_RAW_SPINLOCK(x)
 # define I_RWLOCK(x)
 # define I_MUTEX(x)
 # define I_RWSEM(x)
 # define I_WW(x)
+# define I_LOCAL_LOCK(x)
 #endif
 
 #ifndef I_RTMUTEX
@@ -1358,9 +1369,16 @@ static void reset_locks(void)
 	I1(A); I1(B); I1(C); I1(D);
 	I1(X1); I1(X2); I1(Y1); I1(Y2); I1(Z1); I1(Z2);
 	I_WW(t); I_WW(t2); I_WW(o.base); I_WW(o2.base); I_WW(o3.base);
+	I_RAW_SPINLOCK(A); I_RAW_SPINLOCK(B);
+	I_LOCAL_LOCK(A);
+
 	lockdep_reset();
+
 	I2(A); I2(B); I2(C); I2(D);
 	init_shared_classes();
+	raw_spin_lock_init(&raw_lock_A);
+	raw_spin_lock_init(&raw_lock_B);
+	local_lock_init(&local_A);
 
 	ww_mutex_init(&o, &ww_lockdep); ww_mutex_init(&o2, &ww_lockdep); ww_mutex_init(&o3, &ww_lockdep);
 	memset(&t, 0, sizeof(t)); memset(&t2, 0, sizeof(t2));
@@ -1382,6 +1400,8 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
 
 	WARN_ON(irqs_disabled());
 
+	debug_locks_silent = !(debug_locks_verbose & lockclass_mask);
+
 	testcase_fn();
 	/*
 	 * Filter out expected failures:
@@ -1402,7 +1422,7 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
 	}
 	testcase_total++;
 
-	if (debug_locks_verbose)
+	if (debug_locks_verbose & lockclass_mask)
 		pr_cont(" lockclass mask: %x, debug_locks: %d, expected: %d\n",
 			lockclass_mask, debug_locks, expected);
 	/*
@@ -2419,6 +2439,311 @@ static void fs_reclaim_tests(void)
 	pr_cont("\n");
 }
 
+#define __guard(cleanup) __maybe_unused __attribute__((__cleanup__(cleanup)))
+
+static void hardirq_exit(int *_)
+{
+	HARDIRQ_EXIT();
+}
+
+#define HARDIRQ_CONTEXT(name, ...)					\
+	int hardirq_guard_##name __guard(hardirq_exit);			\
+	HARDIRQ_ENTER();
+
+#define NOTTHREADED_HARDIRQ_CONTEXT(name, ...)				\
+	int notthreaded_hardirq_guard_##name __guard(hardirq_exit);	\
+	local_irq_disable();						\
+	__irq_enter();							\
+	WARN_ON(!in_irq());
+
+static void softirq_exit(int *_)
+{
+	SOFTIRQ_EXIT();
+}
+
+#define SOFTIRQ_CONTEXT(name, ...)				\
+	int softirq_guard_##name __guard(softirq_exit);		\
+	SOFTIRQ_ENTER();
+
+static void rcu_exit(int *_)
+{
+	rcu_read_unlock();
+}
+
+#define RCU_CONTEXT(name, ...)					\
+	int rcu_guard_##name __guard(rcu_exit);			\
+	rcu_read_lock();
+
+static void rcu_bh_exit(int *_)
+{
+	rcu_read_unlock_bh();
+}
+
+#define RCU_BH_CONTEXT(name, ...)				\
+	int rcu_bh_guard_##name __guard(rcu_bh_exit);		\
+	rcu_read_lock_bh();
+
+static void rcu_sched_exit(int *_)
+{
+	rcu_read_unlock_sched();
+}
+
+#define RCU_SCHED_CONTEXT(name, ...)				\
+	int rcu_sched_guard_##name __guard(rcu_sched_exit);	\
+	rcu_read_lock_sched();
+
+static void rcu_callback_exit(int *_)
+{
+	rcu_lock_release(&rcu_callback_map);
+}
+
+#define RCU_CALLBACK_CONTEXT(name, ...)					\
+	int rcu_callback_guard_##name __guard(rcu_callback_exit);	\
+	rcu_lock_acquire(&rcu_callback_map);
+
+
+static void raw_spinlock_exit(raw_spinlock_t **lock)
+{
+	raw_spin_unlock(*lock);
+}
+
+#define RAW_SPINLOCK_CONTEXT(name, lock)						\
+	raw_spinlock_t *raw_spinlock_guard_##name __guard(raw_spinlock_exit) = &(lock);	\
+	raw_spin_lock(&(lock));
+
+static void spinlock_exit(spinlock_t **lock)
+{
+	spin_unlock(*lock);
+}
+
+#define SPINLOCK_CONTEXT(name, lock)						\
+	spinlock_t *spinlock_guard_##name __guard(spinlock_exit) = &(lock);	\
+	spin_lock(&(lock));
+
+static void mutex_exit(struct mutex **lock)
+{
+	mutex_unlock(*lock);
+}
+
+#define MUTEX_CONTEXT(name, lock)					\
+	struct mutex *mutex_guard_##name __guard(mutex_exit) = &(lock);	\
+	mutex_lock(&(lock));
+
+#define GENERATE_2_CONTEXT_TESTCASE(outer, outer_lock, inner, inner_lock)	\
+										\
+static void __maybe_unused inner##_in_##outer(void)				\
+{										\
+	outer##_CONTEXT(_, outer_lock);						\
+	{									\
+		inner##_CONTEXT(_, inner_lock);					\
+	}									\
+}
+
+/*
+ * wait contexts (considering PREEMPT_RT)
+ *
+ * o: inner is allowed in outer
+ * x: inner is disallowed in outer
+ *
+ *       \  inner |  RCU  | RAW_SPIN | SPIN | MUTEX
+ * outer  \       |       |          |      |
+ * ---------------+-------+----------+------+-------
+ * HARDIRQ        |   o   |    o     |  o   |  x
+ * ---------------+-------+----------+------+-------
+ * NOTTHREADED_IRQ|   o   |    o     |  x   |  x
+ * ---------------+-------+----------+------+-------
+ * SOFTIRQ        |   o   |    o     |  o   |  x
+ * ---------------+-------+----------+------+-------
+ * RCU            |   o   |    o     |  o   |  x
+ * ---------------+-------+----------+------+-------
+ * RCU_BH         |   o   |    o     |  o   |  x
+ * ---------------+-------+----------+------+-------
+ * RCU_CALLBACK   |   o   |    o     |  o   |  x
+ * ---------------+-------+----------+------+-------
+ * RCU_SCHED      |   o   |    o     |  x   |  x
+ * ---------------+-------+----------+------+-------
+ * RAW_SPIN       |   o   |    o     |  x   |  x
+ * ---------------+-------+----------+------+-------
+ * SPIN           |   o   |    o     |  o   |  x
+ * ---------------+-------+----------+------+-------
+ * MUTEX          |   o   |    o     |  o   |  o
+ * ---------------+-------+----------+------+-------
+ */
+
+#define GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(inner, inner_lock)		\
+GENERATE_2_CONTEXT_TESTCASE(HARDIRQ, , inner, inner_lock)			\
+GENERATE_2_CONTEXT_TESTCASE(NOTTHREADED_HARDIRQ, , inner, inner_lock)		\
+GENERATE_2_CONTEXT_TESTCASE(SOFTIRQ, , inner, inner_lock)			\
+GENERATE_2_CONTEXT_TESTCASE(RCU, , inner, inner_lock)				\
+GENERATE_2_CONTEXT_TESTCASE(RCU_BH, , inner, inner_lock)			\
+GENERATE_2_CONTEXT_TESTCASE(RCU_CALLBACK, , inner, inner_lock)			\
+GENERATE_2_CONTEXT_TESTCASE(RCU_SCHED, , inner, inner_lock)			\
+GENERATE_2_CONTEXT_TESTCASE(RAW_SPINLOCK, raw_lock_A, inner, inner_lock)	\
+GENERATE_2_CONTEXT_TESTCASE(SPINLOCK, lock_A, inner, inner_lock)		\
+GENERATE_2_CONTEXT_TESTCASE(MUTEX, mutex_A, inner, inner_lock)
+
+GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(RCU, )
+GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(RAW_SPINLOCK, raw_lock_B)
+GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(SPINLOCK, lock_B)
+GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(MUTEX, mutex_B)
+
+/* the outer context allows all kinds of preemption */
+#define DO_CONTEXT_TESTCASE_OUTER_PREEMPTIBLE(outer)			\
+	dotest(RCU_in_##outer, SUCCESS, LOCKTYPE_RWLOCK);		\
+	dotest(RAW_SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN);	\
+	dotest(SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN);		\
+	dotest(MUTEX_in_##outer, SUCCESS, LOCKTYPE_MUTEX);		\
+
+/*
+ * the outer context only allows the preemption introduced by spinlock_t (which
+ * is a sleepable lock for PREEMPT_RT)
+ */
+#define DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(outer)		\
+	dotest(RCU_in_##outer, SUCCESS, LOCKTYPE_RWLOCK);		\
+	dotest(RAW_SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN);	\
+	dotest(SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN);		\
+	dotest(MUTEX_in_##outer, FAILURE, LOCKTYPE_MUTEX);		\
+
+/* the outer doesn't allows any kind of preemption */
+#define DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(outer)			\
+	dotest(RCU_in_##outer, SUCCESS, LOCKTYPE_RWLOCK);		\
+	dotest(RAW_SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN);	\
+	dotest(SPINLOCK_in_##outer, FAILURE, LOCKTYPE_SPIN);		\
+	dotest(MUTEX_in_##outer, FAILURE, LOCKTYPE_MUTEX);		\
+
+static void wait_context_tests(void)
+{
+	printk("  --------------------------------------------------------------------------\n");
+	printk("  | wait context tests |\n");
+	printk("  --------------------------------------------------------------------------\n");
+	printk("                                 | rcu  | raw  | spin |mutex |\n");
+	printk("  --------------------------------------------------------------------------\n");
+	print_testname("in hardirq context");
+	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(HARDIRQ);
+	pr_cont("\n");
+
+	print_testname("in hardirq context (not threaded)");
+	DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(NOTTHREADED_HARDIRQ);
+	pr_cont("\n");
+
+	print_testname("in softirq context");
+	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(SOFTIRQ);
+	pr_cont("\n");
+
+	print_testname("in RCU context");
+	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU);
+	pr_cont("\n");
+
+	print_testname("in RCU-bh context");
+	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU_BH);
+	pr_cont("\n");
+
+	print_testname("in RCU callback context");
+	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU_CALLBACK);
+	pr_cont("\n");
+
+	print_testname("in RCU-sched context");
+	DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(RCU_SCHED);
+	pr_cont("\n");
+
+	print_testname("in RAW_SPINLOCK context");
+	DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(RAW_SPINLOCK);
+	pr_cont("\n");
+
+	print_testname("in SPINLOCK context");
+	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(SPINLOCK);
+	pr_cont("\n");
+
+	print_testname("in MUTEX context");
+	DO_CONTEXT_TESTCASE_OUTER_PREEMPTIBLE(MUTEX);
+	pr_cont("\n");
+}
+
+static void local_lock_2(void)
+{
+	local_lock_acquire(&local_A);	/* IRQ-ON */
+	local_lock_release(&local_A);
+
+	HARDIRQ_ENTER();
+	spin_lock(&lock_A);		/* IN-IRQ */
+	spin_unlock(&lock_A);
+	HARDIRQ_EXIT()
+
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_A);
+	local_lock_acquire(&local_A);	/* IN-IRQ <-> IRQ-ON cycle, false */
+	local_lock_release(&local_A);
+	spin_unlock(&lock_A);
+	HARDIRQ_ENABLE();
+}
+
+static void local_lock_3A(void)
+{
+	local_lock_acquire(&local_A);	/* IRQ-ON */
+	spin_lock(&lock_B);		/* IRQ-ON */
+	spin_unlock(&lock_B);
+	local_lock_release(&local_A);
+
+	HARDIRQ_ENTER();
+	spin_lock(&lock_A);		/* IN-IRQ */
+	spin_unlock(&lock_A);
+	HARDIRQ_EXIT()
+
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_A);
+	local_lock_acquire(&local_A);	/* IN-IRQ <-> IRQ-ON cycle only if we count local_lock(), false */
+	local_lock_release(&local_A);
+	spin_unlock(&lock_A);
+	HARDIRQ_ENABLE();
+}
+
+static void local_lock_3B(void)
+{
+	local_lock_acquire(&local_A);	/* IRQ-ON */
+	spin_lock(&lock_B);		/* IRQ-ON */
+	spin_unlock(&lock_B);
+	local_lock_release(&local_A);
+
+	HARDIRQ_ENTER();
+	spin_lock(&lock_A);		/* IN-IRQ */
+	spin_unlock(&lock_A);
+	HARDIRQ_EXIT()
+
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_A);
+	local_lock_acquire(&local_A);	/* IN-IRQ <-> IRQ-ON cycle only if we count local_lock(), false */
+	local_lock_release(&local_A);
+	spin_unlock(&lock_A);
+	HARDIRQ_ENABLE();
+
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_A);
+	spin_lock(&lock_B);		/* IN-IRQ <-> IRQ-ON cycle, true */
+	spin_unlock(&lock_B);
+	spin_unlock(&lock_A);
+	HARDIRQ_DISABLE();
+
+}
+
+static void local_lock_tests(void)
+{
+	printk("  --------------------------------------------------------------------------\n");
+	printk("  | local_lock tests |\n");
+	printk("  ---------------------\n");
+
+	print_testname("local_lock inversion  2");
+	dotest(local_lock_2, SUCCESS, LOCKTYPE_LL);
+	pr_cont("\n");
+
+	print_testname("local_lock inversion 3A");
+	dotest(local_lock_3A, SUCCESS, LOCKTYPE_LL);
+	pr_cont("\n");
+
+	print_testname("local_lock inversion 3B");
+	dotest(local_lock_3B, FAILURE, LOCKTYPE_LL);
+	pr_cont("\n");
+}
+
 void locking_selftest(void)
 {
 	/*
@@ -2446,7 +2771,6 @@ void locking_selftest(void)
 	printk("  --------------------------------------------------------------------------\n");
 
 	init_shared_classes();
-	debug_locks_silent = !debug_locks_verbose;
 	lockdep_set_selftest_task(current);
 
 	DO_TESTCASE_6R("A-A deadlock", AA);
@@ -2542,6 +2866,12 @@ void locking_selftest(void)
 
 	fs_reclaim_tests();
 
+	/* Wait context test cases that are specific for RAW_LOCK_NESTING */
+	if (IS_ENABLED(CONFIG_PROVE_RAW_LOCK_NESTING))
+		wait_context_tests();
+
+	local_lock_tests();
+
 	if (unexpected_testcase_failures) {
 		printk("-----------------------------------------------------------------\n");
 		debug_locks = 0;
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 1afe3af1cc09..4b2775fd31d9 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -7062,12 +7062,6 @@ sub process {
 			}
 		}
 
-# check for mutex_trylock_recursive usage
-		if ($line =~ /mutex_trylock_recursive/) {
-			ERROR("LOCKING",
-			      "recursive locking is bad, do not use this ever.\n" . $herecurr);
-		}
-
 # check for lockdep_set_novalidate_class
 		if ($line =~ /^.\s*lockdep_set_novalidate_class\s*\(/ ||
 		    $line =~ /__lockdep_no_validate__\s*\)/ ) {
diff --git a/tools/memory-model/Documentation/glossary.txt b/tools/memory-model/Documentation/glossary.txt
index 79acb75d56ea..b2da6365be63 100644
--- a/tools/memory-model/Documentation/glossary.txt
+++ b/tools/memory-model/Documentation/glossary.txt
@@ -33,10 +33,11 @@ Acquire:  With respect to a lock, acquiring that lock, for example,
 	acquire loads.
 
 	When an acquire load returns the value stored by a release store
-	to that same variable, then all operations preceding that store
-	happen before any operations following that load acquire.
+	to that same variable, (in other words, the acquire load "reads
+	from" the release store), then all operations preceding that
+	store "happen before" any operations following that load acquire.
 
-	See also "Relaxed" and "Release".
+	See also "Happens-Before", "Reads-From", "Relaxed", and "Release".
 
 Coherence (co):  When one CPU's store to a given variable overwrites
 	either the value from another CPU's store or some later value,
@@ -119,6 +120,11 @@ Fully Ordered:  An operation such as smp_mb() that orders all of
 	that orders all of its CPU's prior accesses, itself, and
 	all of its CPU's subsequent accesses.
 
+Happens-Before (hb): A relation between two accesses in which LKMM
+	guarantees the first access precedes the second.  For more
+	detail, please see the "THE HAPPENS-BEFORE RELATION: hb"
+	section of explanation.txt.
+
 Marked Access:  An access to a variable that uses an special function or
 	macro such as "r1 = READ_ONCE(x)" or "smp_store_release(&a, 1)".
 
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 39d08d1f0443..9a84c45504ab 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -51,7 +51,7 @@ klitmus7 Compatibility Table
 	============  ==========
 	target Linux  herdtools7
 	------------  ----------
-	     -- 4.18  7.48 --
+	     -- 4.14  7.48 --
 	4.15 -- 4.19  7.49 --
 	4.20 -- 5.5   7.54 --
 	5.6  --       7.56 --
diff --git a/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus b/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus
index 772544f03fb5..967f9f2a6226 100644
--- a/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus
@@ -7,9 +7,7 @@ C CoRR+poonceonce+Once
  * reads from the same variable are ordered.
  *)
 
-{
-	int x;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus b/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus
index 5faae98f7ffb..4635739f3974 100644
--- a/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus
@@ -7,9 +7,7 @@ C CoRW+poonceonce+Once
  * a given variable and a later write to that same variable are ordered.
  *)
 
-{
-	int x;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus b/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus
index 77c9cc9f8dc6..bb068c92d8da 100644
--- a/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus
@@ -7,9 +7,7 @@ C CoWR+poonceonce+Once
  * given variable and a later read from that same variable are ordered.
  *)
 
-{
-	int x;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus b/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus
index 85ef746f511a..0d9f0a958799 100644
--- a/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus
+++ b/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus
@@ -7,9 +7,7 @@ C CoWW+poonceonce
  * writes to the same variable are ordered.
  *)
 
-{
-	int x;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
index 87aa900125ab..e729d2776e89 100644
--- a/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
@@ -10,10 +10,7 @@ C IRIW+fencembonceonces+OnceOnce
  * process?  This litmus test exercises LKMM's "propagation" rule.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus
index f84022dca555..4b54dd6a6cd9 100644
--- a/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus
@@ -10,10 +10,7 @@ C IRIW+poonceonces+OnceOnce
  * different process?
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
index 398f624daa77..094d58df7789 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -7,12 +7,7 @@ C ISA2+pooncelock+pooncelock+pombonce
  * (in P0() and P1()) is visible to external process P2().
  *)
 
-{
-	spinlock_t mylock;
-	int x;
-	int y;
-	int z;
-}
+{}
 
 P0(int *x, int *y, spinlock_t *mylock)
 {
diff --git a/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus b/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus
index 212a432ba16b..b321aa6f4ea5 100644
--- a/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus
@@ -9,11 +9,7 @@ C ISA2+poonceonces
  * of the smp_load_acquire() invocations are replaced by READ_ONCE()?
  *)
 
-{
-	int x;
-	int y;
-	int z;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
index 7afd85672ccd..025b0462ec9b 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
@@ -11,11 +11,7 @@ C ISA2+pooncerelease+poacquirerelease+poacquireonce
  * (AKA non-rf) link, so release-acquire is all that is needed.
  *)
 
-{
-	int x;
-	int y;
-	int z;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
index c8a93c7ee556..4727f5aaf03b 100644
--- a/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
+++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
@@ -11,10 +11,7 @@ C LB+fencembonceonce+ctrlonceonce
  * another control dependency and order would still be maintained.)
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus b/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus
index 2fa029568fa1..07b9904b0e49 100644
--- a/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus
+++ b/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus
@@ -8,10 +8,7 @@ C LB+poacquireonce+pooncerelease
  * to the other?
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/LB+poonceonces.litmus b/tools/memory-model/litmus-tests/LB+poonceonces.litmus
index 2107306e8625..74c49cb3c37b 100644
--- a/tools/memory-model/litmus-tests/LB+poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/LB+poonceonces.litmus
@@ -7,10 +7,7 @@ C LB+poonceonces
  * be prevented even with no explicit ordering?
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
index c5c168d92973..f8ca1229857a 100644
--- a/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
@@ -8,10 +8,7 @@ C MP+fencewmbonceonce+fencermbonceonce
  * is usually better to use smp_store_release() and smp_load_acquire().
  *)
 
-{
-	int buf;
-	int flag;
-}
+{}
 
 P0(int *buf, int *flag) // Producer
 {
diff --git a/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus b/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus
index 20ff62649f1e..d84160b9c1ae 100644
--- a/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus
@@ -10,9 +10,7 @@ C MP+onceassign+derefonce
  *)
 
 {
-	int *p=y;
-	int x;
-	int y=0;
+p=y;
 }
 
 P0(int *x, int **p) // Producer
diff --git a/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
index 153917ad5dc9..ba91cc63e148 100644
--- a/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
+++ b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
@@ -10,10 +10,7 @@ C MP+polockmbonce+poacquiresilsil
  * executed before the lock was acquired (loosely speaking).
  *)
 
-{
-	spinlock_t lo;
-	int x;
-}
+{}
 
 P0(spinlock_t *lo, int *x) // Producer
 {
diff --git a/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
index aad64397bb8c..a5ea3ed8f52e 100644
--- a/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
+++ b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
@@ -10,10 +10,7 @@ C MP+polockonce+poacquiresilsil
  * speaking).
  *)
 
-{
-	spinlock_t lo;
-	int x;
-}
+{}
 
 P0(spinlock_t *lo, int *x) // Producer
 {
diff --git a/tools/memory-model/litmus-tests/MP+polocks.litmus b/tools/memory-model/litmus-tests/MP+polocks.litmus
index 21cbca6f3be4..e6af05f70069 100644
--- a/tools/memory-model/litmus-tests/MP+polocks.litmus
+++ b/tools/memory-model/litmus-tests/MP+polocks.litmus
@@ -11,11 +11,7 @@ C MP+polocks
  * to see all prior accesses by those other CPUs.
  *)
 
-{
-	spinlock_t mylock;
-	int buf;
-	int flag;
-}
+{}
 
 P0(int *buf, int *flag, spinlock_t *mylock) // Producer
 {
diff --git a/tools/memory-model/litmus-tests/MP+poonceonces.litmus b/tools/memory-model/litmus-tests/MP+poonceonces.litmus
index 9f9769d647c7..ba9c99c6cf65 100644
--- a/tools/memory-model/litmus-tests/MP+poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/MP+poonceonces.litmus
@@ -7,10 +7,7 @@ C MP+poonceonces
  * no ordering at all?
  *)
 
-{
-	int buf;
-	int flag;
-}
+{}
 
 P0(int *buf, int *flag) // Producer
 {
diff --git a/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus b/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus
index cbe28e733443..f174bfe61702 100644
--- a/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus
@@ -8,10 +8,7 @@ C MP+pooncerelease+poacquireonce
  * pattern.
  *)
 
-{
-	int buf;
-	int flag;
-}
+{}
 
 P0(int *buf, int *flag) // Producer
 {
diff --git a/tools/memory-model/litmus-tests/MP+porevlocks.litmus b/tools/memory-model/litmus-tests/MP+porevlocks.litmus
index 012041bd4feb..b9599141160e 100644
--- a/tools/memory-model/litmus-tests/MP+porevlocks.litmus
+++ b/tools/memory-model/litmus-tests/MP+porevlocks.litmus
@@ -11,11 +11,7 @@ C MP+porevlocks
  * see all prior accesses by those other CPUs.
  *)
 
-{
-	spinlock_t mylock;
-	int buf;
-	int flag;
-}
+{}
 
 P0(int *buf, int *flag, spinlock_t *mylock) // Consumer
 {
diff --git a/tools/memory-model/litmus-tests/R+fencembonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
index af9463b39b4a..222a0b850b4a 100644
--- a/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
+++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
@@ -9,10 +9,7 @@ C R+fencembonceonces
  * cause the resulting test to be allowed.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/R+poonceonces.litmus b/tools/memory-model/litmus-tests/R+poonceonces.litmus
index bcd5574e304a..5386f128a131 100644
--- a/tools/memory-model/litmus-tests/R+poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/R+poonceonces.litmus
@@ -8,10 +8,7 @@ C R+poonceonces
  * store propagation delays.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
index c36341d1aed6..18479823cd6c 100644
--- a/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
@@ -7,10 +7,7 @@ C S+fencewmbonceonce+poacquireonce
  * store against a subsequent store?
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/S+poonceonces.litmus b/tools/memory-model/litmus-tests/S+poonceonces.litmus
index 7775c23143a0..8c9c2f81a580 100644
--- a/tools/memory-model/litmus-tests/S+poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/S+poonceonces.litmus
@@ -9,10 +9,7 @@ C S+poonceonces
  * READ_ONCE(), is ordering preserved?
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
index 833cdfeb7c09..ed5fff18d223 100644
--- a/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
@@ -9,10 +9,7 @@ C SB+fencembonceonces
  * suffice, but not much else.)
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/SB+poonceonces.litmus b/tools/memory-model/litmus-tests/SB+poonceonces.litmus
index c92211ecbfdf..10d550730b25 100644
--- a/tools/memory-model/litmus-tests/SB+poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+poonceonces.litmus
@@ -8,10 +8,7 @@ C SB+poonceonces
  * variable that the preceding process reads.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
index 84344b455eb7..04a16603660b 100644
--- a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
@@ -6,10 +6,7 @@ C SB+rfionceonce-poonceonces
  * This litmus test demonstrates that LKMM is not fully multicopy atomic.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x, int *y)
 {
diff --git a/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus b/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus
index 431494708611..6a2bc12a1af1 100644
--- a/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus
@@ -8,10 +8,7 @@ C WRC+poonceonces+Once
  * test has no ordering at all.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
index 554999c64db5..e9947250d7de 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
@@ -10,10 +10,7 @@ C WRC+pooncerelease+fencermbonceonce+Once
  * is A-cumulative in LKMM.
  *)
 
-{
-	int x;
-	int y;
-}
+{}
 
 P0(int *x)
 {
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus
index 265a95ffef13..415248fb6699 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus
@@ -9,12 +9,7 @@ C Z6.0+pooncelock+poonceLock+pombonce
  * by CPUs not holding that lock.
  *)
 
-{
-	spinlock_t mylock;
-	int x;
-	int y;
-	int z;
-}
+{}
 
 P0(int *x, int *y, spinlock_t *mylock)
 {
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus
index 0c9aea8e80df..10a2aa04cd07 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus
@@ -8,12 +8,7 @@ C Z6.0+pooncelock+pooncelock+pombonce
  * seen as ordered by a third process not holding that lock.
  *)
 
-{
-	spinlock_t mylock;
-	int x;
-	int y;
-	int z;
-}
+{}
 
 P0(int *x, int *y, spinlock_t *mylock)
 {
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
index 661f9aaa5791..88e70b87a683 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
@@ -14,11 +14,7 @@ C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
  * involving locking.)
  *)
 
-{
-	int x;
-	int y;
-	int z;
-}
+{}
 
 P0(int *x, int *y)
 {