Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - Another attempt at enabling cross-release lockdep dependency
     tracking (automatically part of CONFIG_PROVE_LOCKING=y), this time
     with better performance and fewer false positives. (Byungchul Park)

   - Introduce lockdep_assert_irqs_enabled()/disabled() and convert
     open-coded equivalents to lockdep variants. (Frederic Weisbecker)

   - Add down_read_killable() and use it in the VFS's iterate_dir()
     method. (Kirill Tkhai)

   - Convert remaining uses of ACCESS_ONCE() to
     READ_ONCE()/WRITE_ONCE(). Most of the conversion was Coccinelle
     driven. (Mark Rutland, Paul E. McKenney)

   - Get rid of lockless_dereference(), by strengthening Alpha atomics,
     strengthening READ_ONCE() with smp_read_barrier_depends() and thus
     being able to convert users of lockless_dereference() to
     READ_ONCE(). (Will Deacon)

   - Various micro-optimizations:

        - better PV qspinlocks (Waiman Long),
        - better x86 barriers (Michael S. Tsirkin)
        - better x86 refcounts (Kees Cook)

   - ... plus other fixes and enhancements. (Borislav Petkov, Juergen
     Gross, Miguel Bernal Marin)"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  locking/x86: Use LOCK ADD for smp_mb() instead of MFENCE
  rcu: Use lockdep to assert IRQs are disabled/enabled
  netpoll: Use lockdep to assert IRQs are disabled/enabled
  timers/posix-cpu-timers: Use lockdep to assert IRQs are disabled/enabled
  sched/clock, sched/cputime: Use lockdep to assert IRQs are disabled/enabled
  irq_work: Use lockdep to assert IRQs are disabled/enabled
  irq/timings: Use lockdep to assert IRQs are disabled/enabled
  perf/core: Use lockdep to assert IRQs are disabled/enabled
  x86: Use lockdep to assert IRQs are disabled/enabled
  smp/core: Use lockdep to assert IRQs are disabled/enabled
  timers/hrtimer: Use lockdep to assert IRQs are disabled/enabled
  timers/nohz: Use lockdep to assert IRQs are disabled/enabled
  workqueue: Use lockdep to assert IRQs are disabled/enabled
  irq/softirqs: Use lockdep to assert IRQs are disabled/enabled
  locking/lockdep: Add IRQs disabled/enabled assertion APIs: lockdep_assert_irqs_enabled()/disabled()
  locking/pvqspinlock: Implement hybrid PV queued/unfair locks
  locking/rwlocks: Fix comments
  x86/paravirt: Set up the virt_spin_lock_key after static keys get initialized
  block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion()
  workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes
  ...

40 files changed, 432 insertions, 406 deletions

diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 49be4bba1e96..34a028a7bcc5 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -244,4 +244,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_inc_not_zero(l) \
 	ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l))
 
+#define atomic_long_cond_read_acquire(v, c) \
+	ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c))
+
 #endif  /*  _ASM_GENERIC_ATOMIC_LONG_H  */
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 7d026bf27713..0f7062bd55e5 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -26,51 +26,20 @@
 
 /*
  * Writer states & reader shift and bias.
- *
- *       | +0 | +1 | +2 | +3 |
- *   ----+----+----+----+----+
- *    LE | 78 | 56 | 34 | 12 | 0x12345678
- *   ----+----+----+----+----+
- *       | wr |      rd      |
- *       +----+----+----+----+
- *
- *   ----+----+----+----+----+
- *    BE | 12 | 34 | 56 | 78 | 0x12345678
- *   ----+----+----+----+----+
- *       |      rd      | wr |
- *       +----+----+----+----+
  */
-#define	_QW_WAITING	1		/* A writer is waiting	   */
-#define	_QW_LOCKED	0xff		/* A writer holds the lock */
-#define	_QW_WMASK	0xff		/* Writer mask		   */
-#define	_QR_SHIFT	8		/* Reader count shift	   */
+#define	_QW_WAITING	0x100		/* A writer is waiting	   */
+#define	_QW_LOCKED	0x0ff		/* A writer holds the lock */
+#define	_QW_WMASK	0x1ff		/* Writer mask		   */
+#define	_QR_SHIFT	9		/* Reader count shift	   */
 #define _QR_BIAS	(1U << _QR_SHIFT)
 
 /*
  * External function declarations
  */
-extern void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts);
+extern void queued_read_lock_slowpath(struct qrwlock *lock);
 extern void queued_write_lock_slowpath(struct qrwlock *lock);
 
 /**
- * queued_read_can_lock- would read_trylock() succeed?
- * @lock: Pointer to queue rwlock structure
- */
-static inline int queued_read_can_lock(struct qrwlock *lock)
-{
-	return !(atomic_read(&lock->cnts) & _QW_WMASK);
-}
-
-/**
- * queued_write_can_lock- would write_trylock() succeed?
- * @lock: Pointer to queue rwlock structure
- */
-static inline int queued_write_can_lock(struct qrwlock *lock)
-{
-	return !atomic_read(&lock->cnts);
-}
-
-/**
  * queued_read_trylock - try to acquire read lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  * Return: 1 if lock acquired, 0 if failed
@@ -118,7 +87,7 @@ static inline void queued_read_lock(struct qrwlock *lock)
 		return;
 
 	/* The slowpath will decrement the reader count, if necessary. */
-	queued_read_lock_slowpath(lock, cnts);
+	queued_read_lock_slowpath(lock);
 }
 
 /**
@@ -147,30 +116,18 @@ static inline void queued_read_unlock(struct qrwlock *lock)
 }
 
 /**
- * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock
- * @lock : Pointer to queue rwlock structure
- * Return: the write byte address of a queue rwlock
- */
-static inline u8 *__qrwlock_write_byte(struct qrwlock *lock)
-{
-	return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN);
-}
-
-/**
  * queued_write_unlock - release write lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
-	smp_store_release(__qrwlock_write_byte(lock), 0);
+	smp_store_release(&lock->wlocked, 0);
 }
 
 /*
  * Remapping rwlock architecture specific functions to the corresponding
  * queue rwlock functions.
  */
-#define arch_read_can_lock(l)	queued_read_can_lock(l)
-#define arch_write_can_lock(l)	queued_write_can_lock(l)
 #define arch_read_lock(l)	queued_read_lock(l)
 #define arch_write_lock(l)	queued_write_lock(l)
 #define arch_read_trylock(l)	queued_read_trylock(l)
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
index d93573eff162..137ecdd16daa 100644
--- a/include/asm-generic/qrwlock_types.h
+++ b/include/asm-generic/qrwlock_types.h
@@ -10,12 +10,23 @@
  */
 
 typedef struct qrwlock {
-	atomic_t		cnts;
+	union {
+		atomic_t cnts;
+		struct {
+#ifdef __LITTLE_ENDIAN
+			u8 wlocked;	/* Locked for write? */
+			u8 __lstate[3];
+#else
+			u8 __lstate[3];
+			u8 wlocked;	/* Locked for write? */
+#endif
+		};
+	};
 	arch_spinlock_t		wait_lock;
 } arch_rwlock_t;
 
 #define	__ARCH_RW_LOCK_UNLOCKED {		\
-	.cnts = ATOMIC_INIT(0),			\
+	{ .cnts = ATOMIC_INIT(0), },		\
 	.wait_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
 }
 
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 66260777d644..b37b4ad7eb94 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -121,6 +121,5 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #define arch_spin_lock(l)		queued_spin_lock(l)
 #define arch_spin_trylock(l)		queued_spin_trylock(l)
 #define arch_spin_unlock(l)		queued_spin_unlock(l)
-#define arch_spin_lock_flags(l, f)	queued_spin_lock(l)
 
 #endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index bdbe43bac230..93e67a055a4d 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -38,6 +38,16 @@ static inline void __down_read(struct rw_semaphore *sem)
 		rwsem_down_read_failed(sem);
 }
 
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+	}
+
+	return 0;
+}
+
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8acfc1e099e1..e549bff87c5b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -459,6 +459,7 @@
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
 		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		*(.text..refcount)					\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
 	MEM_KEEP(exit.text)						\
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index cd18203d6ff3..8b276fd9a127 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -654,6 +654,8 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 }
 #endif
 
+#define atomic_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
+
 #ifdef CONFIG_GENERIC_ATOMIC64
 #include <asm-generic/atomic64.h>
 #endif
@@ -1073,6 +1075,8 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v
 }
 #endif
 
+#define atomic64_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
+
 #include <asm-generic/atomic-long.h>
 
 #endif /* _LINUX_ATOMIC_H */
diff --git a/include/linux/average.h b/include/linux/average.h
index 1b6f5560c264..a1a8f09631ce 100644
--- a/include/linux/average.h
+++ b/include/linux/average.h
@@ -2,6 +2,10 @@
 #ifndef _LINUX_AVERAGE_H
 #define _LINUX_AVERAGE_H
 
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/log2.h>
+
 /*
  * Exponentially weighted moving average (EWMA)
  *
@@ -49,7 +53,7 @@
 	static inline void ewma_##name##_add(struct ewma_##name *e,	\
 					     unsigned long val)		\
 	{								\
-		unsigned long internal = ACCESS_ONCE(e->internal);	\
+		unsigned long internal = READ_ONCE(e->internal);	\
 		unsigned long weight_rcp = ilog2(_weight_rcp);		\
 		unsigned long precision = _precision;			\
 									\
@@ -58,10 +62,10 @@
 		BUILD_BUG_ON((_precision) > 30);			\
 		BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp);		\
 									\
-		ACCESS_ONCE(e->internal) = internal ?			\
+		WRITE_ONCE(e->internal, internal ?			\
 			(((internal << weight_rcp) - internal) +	\
 				(val << precision)) >> weight_rcp :	\
-			(val << precision);				\
+			(val << precision));				\
 	}
 
 #endif /* _LINUX_AVERAGE_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index d03c5dd6185d..c537ac7435ad 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -237,7 +237,7 @@ static inline unsigned long __ffs64(u64 word)
 	typeof(*ptr) old, new;					\
 								\
 	do {							\
-		old = ACCESS_ONCE(*ptr);			\
+		old = READ_ONCE(*ptr);			\
 		new = (old & ~mask) | bits;			\
 	} while (cmpxchg(ptr, old, new) != old);		\
 								\
@@ -252,7 +252,7 @@ static inline unsigned long __ffs64(u64 word)
 	typeof(*ptr) old, new;					\
 								\
 	do {							\
-		old = ACCESS_ONCE(*ptr);			\
+		old = READ_ONCE(*ptr);			\
 		new = old & ~clear;				\
 	} while (!(old & test) &&				\
 		 cmpxchg(ptr, old, new) != old);		\
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 54dfef70a072..a06583e41f80 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
 #error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
 #endif
 
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index bb78e5bdff26..2272ded07496 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
 #error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
 #endif
 
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
index 523d1b74550f..bfa08160db3a 100644
--- a/include/linux/compiler-intel.h
+++ b/include/linux/compiler-intel.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_COMPILER_H
+#ifndef __LINUX_COMPILER_TYPES_H
 #error "Please don't include <linux/compiler-intel.h> directly, include <linux/compiler.h> instead."
 #endif
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 202710420d6d..3672353a0acd 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -2,111 +2,12 @@
 #ifndef __LINUX_COMPILER_H
 #define __LINUX_COMPILER_H
 
-#ifndef __ASSEMBLY__
+#include <linux/compiler_types.h>
 
-#ifdef __CHECKER__
-# define __user		__attribute__((noderef, address_space(1)))
-# define __kernel	__attribute__((address_space(0)))
-# define __safe		__attribute__((safe))
-# define __force	__attribute__((force))
-# define __nocast	__attribute__((nocast))
-# define __iomem	__attribute__((noderef, address_space(2)))
-# define __must_hold(x)	__attribute__((context(x,1,1)))
-# define __acquires(x)	__attribute__((context(x,0,1)))
-# define __releases(x)	__attribute__((context(x,1,0)))
-# define __acquire(x)	__context__(x,1)
-# define __release(x)	__context__(x,-1)
-# define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu	__attribute__((noderef, address_space(3)))
-# define __rcu		__attribute__((noderef, address_space(4)))
-# define __private	__attribute__((noderef))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
-# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
-#else /* __CHECKER__ */
-# ifdef STRUCTLEAK_PLUGIN
-#  define __user __attribute__((user))
-# else
-#  define __user
-# endif
-# define __kernel
-# define __safe
-# define __force
-# define __nocast
-# define __iomem
-# define __chk_user_ptr(x) (void)0
-# define __chk_io_ptr(x) (void)0
-# define __builtin_warning(x, y...) (1)
-# define __must_hold(x)
-# define __acquires(x)
-# define __releases(x)
-# define __acquire(x) (void)0
-# define __release(x) (void)0
-# define __cond_lock(x,c) (c)
-# define __percpu
-# define __rcu
-# define __private
-# define ACCESS_PRIVATE(p, member) ((p)->member)
-#endif /* __CHECKER__ */
-
-/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
-#define ___PASTE(a,b) a##b
-#define __PASTE(a,b) ___PASTE(a,b)
+#ifndef __ASSEMBLY__
 
 #ifdef __KERNEL__
 
-#ifdef __GNUC__
-#include <linux/compiler-gcc.h>
-#endif
-
-#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__)
-#define notrace __attribute__((hotpatch(0,0)))
-#else
-#define notrace __attribute__((no_instrument_function))
-#endif
-
-/* Intel compiler defines __GNUC__. So we will overwrite implementations
- * coming from above header files here
- */
-#ifdef __INTEL_COMPILER
-# include <linux/compiler-intel.h>
-#endif
-
-/* Clang compiler defines __GNUC__. So we will overwrite implementations
- * coming from above header files here
- */
-#ifdef __clang__
-#include <linux/compiler-clang.h>
-#endif
-
-/*
- * Generic compiler-dependent macros required for kernel
- * build go below this comment. Actual compiler/compiler version
- * specific implementations come from the above header files
- */
-
-struct ftrace_branch_data {
-	const char *func;
-	const char *file;
-	unsigned line;
-	union {
-		struct {
-			unsigned long correct;
-			unsigned long incorrect;
-		};
-		struct {
-			unsigned long miss;
-			unsigned long hit;
-		};
-		unsigned long miss_hit[2];
-	};
-};
-
-struct ftrace_likely_data {
-	struct ftrace_branch_data	data;
-	unsigned long			constant;
-};
-
 /*
  * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
  * to disable branch tracing on a per file basis.
@@ -333,6 +234,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
  */
+#include <asm/barrier.h>
 
 #define __READ_ONCE(x, check)						\
 ({									\
@@ -341,6 +243,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 		__read_once_size(&(x), __u.__c, sizeof(x));		\
 	else								\
 		__read_once_size_nocheck(&(x), __u.__c, sizeof(x));	\
+	smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
 	__u.__val;							\
 })
 #define READ_ONCE(x) __READ_ONCE(x, 1)
@@ -363,167 +266,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 
 #endif /* __ASSEMBLY__ */
 
-#ifdef __KERNEL__
-/*
- * Allow us to mark functions as 'deprecated' and have gcc emit a nice
- * warning for each use, in hopes of speeding the functions removal.
- * Usage is:
- * 		int __deprecated foo(void)
- */
-#ifndef __deprecated
-# define __deprecated		/* unimplemented */
-#endif
-
-#ifdef MODULE
-#define __deprecated_for_modules __deprecated
-#else
-#define __deprecated_for_modules
-#endif
-
-#ifndef __must_check
-#define __must_check
-#endif
-
-#ifndef CONFIG_ENABLE_MUST_CHECK
-#undef __must_check
-#define __must_check
-#endif
-#ifndef CONFIG_ENABLE_WARN_DEPRECATED
-#undef __deprecated
-#undef __deprecated_for_modules
-#define __deprecated
-#define __deprecated_for_modules
-#endif
-
-#ifndef __malloc
-#define __malloc
-#endif
-
-/*
- * Allow us to avoid 'defined but not used' warnings on functions and data,
- * as well as force them to be emitted to the assembly file.
- *
- * As of gcc 3.4, static functions that are not marked with attribute((used))
- * may be elided from the assembly file.  As of gcc 3.4, static data not so
- * marked will not be elided, but this may change in a future gcc version.
- *
- * NOTE: Because distributions shipped with a backported unit-at-a-time
- * compiler in gcc 3.3, we must define __used to be __attribute__((used))
- * for gcc >=3.3 instead of 3.4.
- *
- * In prior versions of gcc, such functions and data would be emitted, but
- * would be warned about except with attribute((unused)).
- *
- * Mark functions that are referenced only in inline assembly as __used so
- * the code is emitted even though it appears to be unreferenced.
- */
-#ifndef __used
-# define __used			/* unimplemented */
-#endif
-
-#ifndef __maybe_unused
-# define __maybe_unused		/* unimplemented */
-#endif
-
-#ifndef __always_unused
-# define __always_unused	/* unimplemented */
-#endif
-
-#ifndef noinline
-#define noinline
-#endif
-
-/*
- * Rather then using noinline to prevent stack consumption, use
- * noinline_for_stack instead.  For documentation reasons.
- */
-#define noinline_for_stack noinline
-
-#ifndef __always_inline
-#define __always_inline inline
-#endif
-
-#endif /* __KERNEL__ */
-
-/*
- * From the GCC manual:
- *
- * Many functions do not examine any values except their arguments,
- * and have no effects except the return value.  Basically this is
- * just slightly more strict class than the `pure' attribute above,
- * since function is not allowed to read global memory.
- *
- * Note that a function that has pointer arguments and examines the
- * data pointed to must _not_ be declared `const'.  Likewise, a
- * function that calls a non-`const' function usually must not be
- * `const'.  It does not make sense for a `const' function to return
- * `void'.
- */
-#ifndef __attribute_const__
-# define __attribute_const__	/* unimplemented */
-#endif
-
-#ifndef __designated_init
-# define __designated_init
-#endif
-
-#ifndef __latent_entropy
-# define __latent_entropy
-#endif
-
-#ifndef __randomize_layout
-# define __randomize_layout __designated_init
-#endif
-
-#ifndef __no_randomize_layout
-# define __no_randomize_layout
-#endif
-
-#ifndef randomized_struct_fields_start
-# define randomized_struct_fields_start
-# define randomized_struct_fields_end
-#endif
-
-/*
- * Tell gcc if a function is cold. The compiler will assume any path
- * directly leading to the call is unlikely.
- */
-
-#ifndef __cold
-#define __cold
-#endif
-
-/* Simple shorthand for a section definition */
-#ifndef __section
-# define __section(S) __attribute__ ((__section__(#S)))
-#endif
-
-#ifndef __visible
-#define __visible
-#endif
-
-#ifndef __nostackprotector
-# define __nostackprotector
-#endif
-
-/*
- * Assume alignment of return value.
- */
-#ifndef __assume_aligned
-#define __assume_aligned(a, ...)
-#endif
-
-
-/* Are two types/vars the same type (ignoring qualifiers)? */
-#ifndef __same_type
-# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
-#endif
-
-/* Is this type a native word size -- useful for atomic operations */
-#ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
-#endif
-
 /* Compile time object size, -1 for unknown */
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1
@@ -605,24 +347,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	(volatile typeof(x) *)&(x); })
 #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
 
-/**
- * lockless_dereference() - safely load a pointer for later dereference
- * @p: The pointer to load
- *
- * Similar to rcu_dereference(), but for situations where the pointed-to
- * object's lifetime is managed by something other than RCU.  That
- * "something other" might be reference counting or simple immortality.
- *
- * The seemingly unused variable ___typecheck_p validates that @p is
- * indeed a pointer type by using a pointer to typeof(*p) as the type.
- * Taking a pointer to typeof(*p) again is needed in case p is void *.
- */
-#define lockless_dereference(p) \
-({ \
-	typeof(p) _________p1 = READ_ONCE(p); \
-	typeof(*(p)) *___typecheck_p __maybe_unused; \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	(_________p1); \
-})
-
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
new file mode 100644
index 000000000000..6b79a9bba9a7
--- /dev/null
+++ b/include/linux/compiler_types.h
@@ -0,0 +1,274 @@
+#ifndef __LINUX_COMPILER_TYPES_H
+#define __LINUX_COMPILER_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef __CHECKER__
+# define __user		__attribute__((noderef, address_space(1)))
+# define __kernel	__attribute__((address_space(0)))
+# define __safe		__attribute__((safe))
+# define __force	__attribute__((force))
+# define __nocast	__attribute__((nocast))
+# define __iomem	__attribute__((noderef, address_space(2)))
+# define __must_hold(x)	__attribute__((context(x,1,1)))
+# define __acquires(x)	__attribute__((context(x,0,1)))
+# define __releases(x)	__attribute__((context(x,1,0)))
+# define __acquire(x)	__context__(x,1)
+# define __release(x)	__context__(x,-1)
+# define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
+# define __percpu	__attribute__((noderef, address_space(3)))
+# define __rcu		__attribute__((noderef, address_space(4)))
+# define __private	__attribute__((noderef))
+extern void __chk_user_ptr(const volatile void __user *);
+extern void __chk_io_ptr(const volatile void __iomem *);
+# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
+#else /* __CHECKER__ */
+# ifdef STRUCTLEAK_PLUGIN
+#  define __user __attribute__((user))
+# else
+#  define __user
+# endif
+# define __kernel
+# define __safe
+# define __force
+# define __nocast
+# define __iomem
+# define __chk_user_ptr(x) (void)0
+# define __chk_io_ptr(x) (void)0
+# define __builtin_warning(x, y...) (1)
+# define __must_hold(x)
+# define __acquires(x)
+# define __releases(x)
+# define __acquire(x) (void)0
+# define __release(x) (void)0
+# define __cond_lock(x,c) (c)
+# define __percpu
+# define __rcu
+# define __private
+# define ACCESS_PRIVATE(p, member) ((p)->member)
+#endif /* __CHECKER__ */
+
+/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+#define ___PASTE(a,b) a##b
+#define __PASTE(a,b) ___PASTE(a,b)
+
+#ifdef __KERNEL__
+
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
+#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__)
+#define notrace __attribute__((hotpatch(0,0)))
+#else
+#define notrace __attribute__((no_instrument_function))
+#endif
+
+/* Intel compiler defines __GNUC__. So we will overwrite implementations
+ * coming from above header files here
+ */
+#ifdef __INTEL_COMPILER
+# include <linux/compiler-intel.h>
+#endif
+
+/* Clang compiler defines __GNUC__. So we will overwrite implementations
+ * coming from above header files here
+ */
+#ifdef __clang__
+#include <linux/compiler-clang.h>
+#endif
+
+/*
+ * Generic compiler-dependent macros required for kernel
+ * build go below this comment. Actual compiler/compiler version
+ * specific implementations come from the above header files
+ */
+
+struct ftrace_branch_data {
+	const char *func;
+	const char *file;
+	unsigned line;
+	union {
+		struct {
+			unsigned long correct;
+			unsigned long incorrect;
+		};
+		struct {
+			unsigned long miss;
+			unsigned long hit;
+		};
+		unsigned long miss_hit[2];
+	};
+};
+
+struct ftrace_likely_data {
+	struct ftrace_branch_data	data;
+	unsigned long			constant;
+};
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef __KERNEL__
+/*
+ * Allow us to mark functions as 'deprecated' and have gcc emit a nice
+ * warning for each use, in hopes of speeding the functions removal.
+ * Usage is:
+ * 		int __deprecated foo(void)
+ */
+#ifndef __deprecated
+# define __deprecated		/* unimplemented */
+#endif
+
+#ifdef MODULE
+#define __deprecated_for_modules __deprecated
+#else
+#define __deprecated_for_modules
+#endif
+
+#ifndef __must_check
+#define __must_check
+#endif
+
+#ifndef CONFIG_ENABLE_MUST_CHECK
+#undef __must_check
+#define __must_check
+#endif
+#ifndef CONFIG_ENABLE_WARN_DEPRECATED
+#undef __deprecated
+#undef __deprecated_for_modules
+#define __deprecated
+#define __deprecated_for_modules
+#endif
+
+#ifndef __malloc
+#define __malloc
+#endif
+
+/*
+ * Allow us to avoid 'defined but not used' warnings on functions and data,
+ * as well as force them to be emitted to the assembly file.
+ *
+ * As of gcc 3.4, static functions that are not marked with attribute((used))
+ * may be elided from the assembly file.  As of gcc 3.4, static data not so
+ * marked will not be elided, but this may change in a future gcc version.
+ *
+ * NOTE: Because distributions shipped with a backported unit-at-a-time
+ * compiler in gcc 3.3, we must define __used to be __attribute__((used))
+ * for gcc >=3.3 instead of 3.4.
+ *
+ * In prior versions of gcc, such functions and data would be emitted, but
+ * would be warned about except with attribute((unused)).
+ *
+ * Mark functions that are referenced only in inline assembly as __used so
+ * the code is emitted even though it appears to be unreferenced.
+ */
+#ifndef __used
+# define __used			/* unimplemented */
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused		/* unimplemented */
+#endif
+
+#ifndef __always_unused
+# define __always_unused	/* unimplemented */
+#endif
+
+#ifndef noinline
+#define noinline
+#endif
+
+/*
+ * Rather then using noinline to prevent stack consumption, use
+ * noinline_for_stack instead.  For documentation reasons.
+ */
+#define noinline_for_stack noinline
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+
+#endif /* __KERNEL__ */
+
+/*
+ * From the GCC manual:
+ *
+ * Many functions do not examine any values except their arguments,
+ * and have no effects except the return value.  Basically this is
+ * just slightly more strict class than the `pure' attribute above,
+ * since function is not allowed to read global memory.
+ *
+ * Note that a function that has pointer arguments and examines the
+ * data pointed to must _not_ be declared `const'.  Likewise, a
+ * function that calls a non-`const' function usually must not be
+ * `const'.  It does not make sense for a `const' function to return
+ * `void'.
+ */
+#ifndef __attribute_const__
+# define __attribute_const__	/* unimplemented */
+#endif
+
+#ifndef __designated_init
+# define __designated_init
+#endif
+
+#ifndef __latent_entropy
+# define __latent_entropy
+#endif
+
+#ifndef __randomize_layout
+# define __randomize_layout __designated_init
+#endif
+
+#ifndef __no_randomize_layout
+# define __no_randomize_layout
+#endif
+
+#ifndef randomized_struct_fields_start
+# define randomized_struct_fields_start
+# define randomized_struct_fields_end
+#endif
+
+/*
+ * Tell gcc if a function is cold. The compiler will assume any path
+ * directly leading to the call is unlikely.
+ */
+
+#ifndef __cold
+#define __cold
+#endif
+
+/* Simple shorthand for a section definition */
+#ifndef __section
+# define __section(S) __attribute__ ((__section__(#S)))
+#endif
+
+#ifndef __visible
+#define __visible
+#endif
+
+#ifndef __nostackprotector
+# define __nostackprotector
+#endif
+
+/*
+ * Assume alignment of return value.
+ */
+#ifndef __assume_aligned
+#define __assume_aligned(a, ...)
+#endif
+
+
+/* Are two types/vars the same type (ignoring qualifiers)? */
+#ifndef __same_type
+# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
+#endif
+
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
+#endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 7828451e161a..0662a417febe 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -50,15 +50,23 @@ static inline void complete_release_commit(struct completion *x)
 	lock_commit_crosslock((struct lockdep_map *)&x->map);
 }
 
+#define init_completion_map(x, m)					\
+do {									\
+	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
+			(m)->name, (m)->key, 0);				\
+	__init_completion(x);						\
+} while (0)
+
 #define init_completion(x)						\
 do {									\
 	static struct lock_class_key __key;				\
 	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
-			"(complete)" #x,				\
+			"(completion)" #x,				\
 			&__key, 0);					\
 	__init_completion(x);						\
 } while (0)
 #else
+#define init_completion_map(x, m) __init_completion(x)
 #define init_completion(x) __init_completion(x)
 static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
@@ -68,12 +76,15 @@ static inline void complete_release_commit(struct completion *x) {}
 #ifdef CONFIG_LOCKDEP_COMPLETIONS
 #define COMPLETION_INITIALIZER(work) \
 	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
-	STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) }
+	STATIC_CROSS_LOCKDEP_MAP_INIT("(completion)" #work, &(work)) }
 #else
 #define COMPLETION_INITIALIZER(work) \
 	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
 #endif
 
+#define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
+	(*({ init_completion_map(&(work), &(map)); &(work); }))
+
 #define COMPLETION_INITIALIZER_ONSTACK(work) \
 	(*({ init_completion(&work); &work; }))
 
@@ -103,8 +114,11 @@ static inline void complete_release_commit(struct completion *x) {}
 #ifdef CONFIG_LOCKDEP
 # define DECLARE_COMPLETION_ONSTACK(work) \
 	struct completion work = COMPLETION_INITIALIZER_ONSTACK(work)
+# define DECLARE_COMPLETION_ONSTACK_MAP(work, map) \
+	struct completion work = COMPLETION_INITIALIZER_ONSTACK_MAP(work, map)
 #else
 # define DECLARE_COMPLETION_ONSTACK(work) DECLARE_COMPLETION(work)
+# define DECLARE_COMPLETION_ONSTACK_MAP(work, map) DECLARE_COMPLETION(work)
 #endif
 
 /**
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index f05a659cdf34..65cd8ab60b7a 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -520,7 +520,7 @@ static inline struct inode *d_inode(const struct dentry *dentry)
 }
 
 /**
- * d_inode_rcu - Get the actual inode of this dentry with ACCESS_ONCE()
+ * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE()
  * @dentry: The dentry to query
  *
  * This is the helper normal filesystems should use to get at their own inodes
@@ -528,7 +528,7 @@ static inline struct inode *d_inode(const struct dentry *dentry)
  */
 static inline struct inode *d_inode_rcu(const struct dentry *dentry)
 {
-	return ACCESS_ONCE(dentry->d_inode);
+	return READ_ONCE(dentry->d_inode);
 }
 
 /**
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 34c0a5464c74..023eae69398c 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -89,7 +89,7 @@ static inline void dql_queued(struct dql *dql, unsigned int count)
 /* Returns how many objects can be queued, < 0 indicates over limit. */
 static inline int dql_avail(const struct dql *dql)
 {
-	return ACCESS_ONCE(dql->adj_limit) - ACCESS_ONCE(dql->num_queued);
+	return READ_ONCE(dql->adj_limit) - READ_ONCE(dql->num_queued);
 }
 
 /* Record number of completed objects and recalculate the limit. */
diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h
index b96dd4e1e663..ecc2928e8046 100644
--- a/include/linux/genetlink.h
+++ b/include/linux/genetlink.h
@@ -31,7 +31,7 @@ extern wait_queue_head_t genl_sk_destructing_waitq;
  * @p: The pointer to read, prior to dereferencing
  *
  * Return the value of the specified RCU-protected pointer, but omit
- * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * both the smp_read_barrier_depends() and the READ_ONCE(), because
  * caller holds genl mutex.
  */
 #define genl_dereference(p)					\
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 44790523057f..eaefb7a62f83 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -207,6 +207,7 @@ struct gendisk {
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
 	int node_id;
 	struct badblocks *bb;
+	struct lockdep_map lockdep_map;
 };
 
 static inline struct gendisk *part_to_disk(struct hd_struct *part)
@@ -591,8 +592,7 @@ extern void __delete_partition(struct percpu_ref *);
 extern void delete_partition(struct gendisk *, int);
 extern void printk_all_partitions(void);
 
-extern struct gendisk *alloc_disk_node(int minors, int node_id);
-extern struct gendisk *alloc_disk(int minors);
+extern struct gendisk *__alloc_disk_node(int minors, int node_id);
 extern struct kobject *get_disk(struct gendisk *disk);
 extern void put_disk(struct gendisk *disk);
 extern void blk_register_region(dev_t devt, unsigned long range,
@@ -616,6 +616,24 @@ extern ssize_t part_fail_store(struct device *dev,
 			       const char *buf, size_t count);
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
+#define alloc_disk_node(minors, node_id)				\
+({									\
+	static struct lock_class_key __key;				\
+	const char *__name;						\
+	struct gendisk *__disk;						\
+									\
+	__name = "(gendisk_completion)"#minors"("#node_id")";		\
+									\
+	__disk = __alloc_disk_node(minors, node_id);			\
+									\
+	if (__disk)							\
+		lockdep_init_map(&__disk->lockdep_map, __name, &__key, 0); \
+									\
+	__disk;								\
+})
+
+#define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE)
+
 static inline int hd_ref_init(struct hd_struct *part)
 {
 	if (percpu_ref_init(&part->ref, __delete_partition, 0,
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 87067d23a48b..a8a126259bc4 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -222,7 +222,7 @@ extern struct page *huge_zero_page;
 
 static inline bool is_huge_zero_page(struct page *page)
 {
-	return ACCESS_ONCE(huge_zero_page) == page;
+	return READ_ONCE(huge_zero_page) == page;
 }
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 30294603526f..d95cae09dea0 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -247,7 +247,7 @@ static inline struct team_port *team_get_port_by_index(struct team *team,
 
 static inline int team_num_to_port_index(struct team *team, unsigned int num)
 {
-	int en_port_count = ACCESS_ONCE(team->en_port_count);
+	int en_port_count = READ_ONCE(team->en_port_count);
 
 	if (unlikely(!en_port_count))
 		return 0;
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 3b7675bcca64..c7b368c734af 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -82,9 +82,9 @@
 
 extern bool static_key_initialized;
 
-#define STATIC_KEY_CHECK_USE() WARN(!static_key_initialized,		      \
-				    "%s used before call to jump_label_init", \
-				    __func__)
+#define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized,		      \
+				    "%s(): static key '%pS' used before call to jump_label_init()", \
+				    __func__, (key))
 
 #ifdef HAVE_JUMP_LABEL
 
@@ -212,13 +212,13 @@ static __always_inline bool static_key_true(struct static_key *key)
 
 static inline void static_key_slow_inc(struct static_key *key)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 	atomic_inc(&key->enabled);
 }
 
 static inline void static_key_slow_dec(struct static_key *key)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 	atomic_dec(&key->enabled);
 }
 
@@ -237,7 +237,7 @@ static inline int jump_label_apply_nops(struct module *mod)
 
 static inline void static_key_enable(struct static_key *key)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 
 	if (atomic_read(&key->enabled) != 0) {
 		WARN_ON_ONCE(atomic_read(&key->enabled) != 1);
@@ -248,7 +248,7 @@ static inline void static_key_enable(struct static_key *key)
 
 static inline void static_key_disable(struct static_key *key)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 
 	if (atomic_read(&key->enabled) != 1) {
 		WARN_ON_ONCE(atomic_read(&key->enabled) != 0);
diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h
index fc13ff289903..baa8eabbaa56 100644
--- a/include/linux/jump_label_ratelimit.h
+++ b/include/linux/jump_label_ratelimit.h
@@ -25,18 +25,18 @@ struct static_key_deferred {
 };
 static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 	static_key_slow_dec(&key->key);
 }
 static inline void static_key_deferred_flush(struct static_key_deferred *key)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 }
 static inline void
 jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
-	STATIC_KEY_CHECK_USE();
+	STATIC_KEY_CHECK_USE(key);
 }
 #endif	/* HAVE_JUMP_LABEL */
 #endif	/* _LINUX_JUMP_LABEL_RATELIMIT_H */
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 2e6f90bd52aa..f68db9e450eb 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_LINKAGE_H
 #define _LINUX_LINKAGE_H
 
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
 #include <linux/stringify.h>
 #include <linux/export.h>
 #include <asm/linkage.h>
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 1957635e6d5f..85abc2915e8d 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -198,7 +198,7 @@ static inline void init_llist_head(struct llist_head *list)
  */
 static inline bool llist_empty(const struct llist_head *head)
 {
-	return ACCESS_ONCE(head->first) == NULL;
+	return READ_ONCE(head->first) == NULL;
 }
 
 static inline struct llist_node *llist_next(struct llist_node *node)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index f301d31b473c..a842551fe044 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -528,6 +528,11 @@ static inline void lockdep_on(void)
  */
 struct lock_class_key { };
 
+/*
+ * The lockdep_map takes no space if lockdep is disabled:
+ */
+struct lockdep_map { };
+
 #define lockdep_depth(tsk)	(0)
 
 #define lockdep_is_held_type(l, r)		(1)
@@ -720,9 +725,24 @@ do {									\
 	lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_);	\
 	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
 } while (0)
+
+#define lockdep_assert_irqs_enabled()	do {				\
+		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
+			  !current->hardirqs_enabled,			\
+			  "IRQs not enabled as expected\n");		\
+	} while (0)
+
+#define lockdep_assert_irqs_disabled()	do {				\
+		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
+			  current->hardirqs_enabled,			\
+			  "IRQs not disabled as expected\n");		\
+	} while (0)
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
+# define lockdep_assert_irqs_enabled() do { } while (0)
+# define lockdep_assert_irqs_disabled() do { } while (0)
 #endif
 
 #ifdef CONFIG_LOCKDEP
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 414a5e769fde..495ba4dd9da5 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -67,7 +67,7 @@ static inline bool lockdep_nfnl_is_held(__u8 subsys_id)
  * @ss: The nfnetlink subsystem ID
  *
  * Return the value of the specified RCU-protected pointer, but omit
- * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * both the smp_read_barrier_depends() and the READ_ONCE(), because
  * caller holds the NFNL subsystem mutex.
  */
 #define nfnl_dereference(p, ss)					\
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 2efb08a60e63..f0fc4700b6ff 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev)
 
 static inline void pm_runtime_mark_last_busy(struct device *dev)
 {
-	ACCESS_ONCE(dev->power.last_busy) = jiffies;
+	WRITE_ONCE(dev->power.last_busy, jiffies);
 }
 
 static inline bool pm_runtime_is_irq_safe(struct device *dev)
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index c2cdd45a880a..127f534fec94 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -275,7 +275,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-	container_of(lockless_dereference(ptr), type, member)
+	container_of(READ_ONCE(ptr), type, member)
 
 /*
  * Where are list_empty_rcu() and list_first_entry_rcu()?
@@ -368,7 +368,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * example is when items are added to the list, but never deleted.
  */
 #define list_entry_lockless(ptr, type, member) \
-	container_of((typeof(ptr))lockless_dereference(ptr), type, member)
+	container_of((typeof(ptr))READ_ONCE(ptr), type, member)
 
 /**
  * list_for_each_entry_lockless - iterate over rcu list of given type
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 1a9f70d44af9..a6ddc42f87a5 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -346,7 +346,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define __rcu_dereference_check(p, c, space) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
+	typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(________p1)); \
@@ -360,7 +360,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_dereference_raw(p) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(p) ________p1 = lockless_dereference(p); \
+	typeof(p) ________p1 = READ_ONCE(p); \
 	((typeof(*p) __force __kernel *)(________p1)); \
 })
 
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index ff3dd2ec44b4..54bcd970bfd3 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -68,7 +68,7 @@ static inline bool lockdep_rtnl_is_held(void)
  * @p: The pointer to read, prior to dereferencing
  *
  * Return the value of the specified RCU-protected pointer, but omit
- * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * both the smp_read_barrier_depends() and the READ_ONCE(), because
  * caller holds RTNL.
  */
 #define rtnl_dereference(p)					\
diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h
index bc2994ed66e1..3dcd617e65ae 100644
--- a/include/linux/rwlock.h
+++ b/include/linux/rwlock.h
@@ -38,6 +38,15 @@ do {								\
  extern int do_raw_write_trylock(rwlock_t *lock);
  extern void do_raw_write_unlock(rwlock_t *lock) __releases(lock);
 #else
+
+#ifndef arch_read_lock_flags
+# define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
+#endif
+
+#ifndef arch_write_lock_flags
+# define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
+#endif
+
 # define do_raw_read_lock(rwlock)	do {__acquire(lock); arch_read_lock(&(rwlock)->raw_lock); } while (0)
 # define do_raw_read_lock_flags(lock, flags) \
 		do {__acquire(lock); arch_read_lock_flags(&(lock)->raw_lock, *(flags)); } while (0)
@@ -50,9 +59,6 @@ do {								\
 # define do_raw_write_unlock(rwlock)	do {arch_write_unlock(&(rwlock)->raw_lock); __release(lock); } while (0)
 #endif
 
-#define read_can_lock(rwlock)		arch_read_can_lock(&(rwlock)->raw_lock)
-#define write_can_lock(rwlock)		arch_write_can_lock(&(rwlock)->raw_lock)
-
 /*
  * Define the various rw_lock methods.  Note we define these
  * regardless of whether CONFIG_SMP or CONFIG_PREEMPT are set. The various
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index 5b9b84b20407..86ebb4bf9c6e 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -211,7 +211,7 @@ static inline void __raw_write_lock(rwlock_t *lock)
 	LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock);
 }
 
-#endif /* CONFIG_PREEMPT */
+#endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */
 
 static inline void __raw_write_unlock(rwlock_t *lock)
 {
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index dfa34d803439..56707d5ff6ad 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -112,6 +112,7 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
  * lock for reading
  */
 extern void down_read(struct rw_semaphore *sem);
+extern int __must_check down_read_killable(struct rw_semaphore *sem);
 
 /*
  * trylock for reading -- returns 1 if successful, 0 if contention
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 341e1a12bfc7..a39186194cd6 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -166,6 +166,10 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 	arch_spin_lock(&lock->raw_lock);
 }
 
+#ifndef arch_spin_lock_flags
+#define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
+#endif
+
 static inline void
 do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock)
 {
@@ -279,12 +283,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 	1 : ({ local_irq_restore(flags); 0; }); \
 })
 
-/**
- * raw_spin_can_lock - would raw_spin_trylock() succeed?
- * @lock: the spinlock in question.
- */
-#define raw_spin_can_lock(lock)	(!raw_spin_is_locked(lock))
-
 /* Include rwlock functions */
 #include <linux/rwlock.h>
 
@@ -397,11 +395,6 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 	return raw_spin_is_contended(&lock->rlock);
 }
 
-static __always_inline int spin_can_lock(spinlock_t *lock)
-{
-	return raw_spin_can_lock(&lock->rlock);
-}
-
 #define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
 
 /*
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 612fb530af41..0ac9112c1bbe 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -32,14 +32,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	barrier();
 }
 
-static inline void
-arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
-{
-	local_irq_save(flags);
-	lock->slock = 0;
-	barrier();
-}
-
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	char oldval = lock->slock;
@@ -77,7 +69,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 #define arch_spin_is_contended(lock)	(((void)(lock), 0))
 
-#define arch_read_can_lock(lock)	(((void)(lock), 1))
-#define arch_write_can_lock(lock)	(((void)(lock), 1))
-
 #endif /* __LINUX_SPINLOCK_UP_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0eae11fc7a23..1cdabfb813ab 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -219,7 +219,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
 									\
 		__init_work((_work), _onstack);				\
 		(_work)->data = (atomic_long_t) WORK_DATA_INIT();	\
-		lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0); \
+		lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \
 		INIT_LIST_HEAD(&(_work)->entry);			\
 		(_work)->func = (_func);				\
 	} while (0)
@@ -399,7 +399,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	static struct lock_class_key __key;				\
 	const char *__lock_name;					\
 									\
-	__lock_name = #fmt#args;					\
+	__lock_name = "(wq_completion)"#fmt#args;			\
 									\
 	__alloc_workqueue_key((fmt), (flags), (max_active),		\
 			      &__key, __lock_name, ##args);		\
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 5d08c1950e7d..ff68cf288f9b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -984,12 +984,12 @@ static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
 
 static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 {
-	return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]);
+	return READ_ONCE(ipvs->sysctl_sync_threshold[1]);
 }
 
 static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
 {
-	return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period);
+	return READ_ONCE(ipvs->sysctl_sync_refresh_period);
 }
 
 static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
@@ -1014,7 +1014,7 @@ static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs)
 
 static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
 {
-	return ACCESS_ONCE(ipvs->sysctl_sync_ports);
+	return READ_ONCE(ipvs->sysctl_sync_ports);
 }
 
 static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 079c69cae2f6..470c1c71e7f4 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1165,8 +1165,8 @@ static inline u8 nft_genmask_next(const struct net *net)
 
 static inline u8 nft_genmask_cur(const struct net *net)
 {
-	/* Use ACCESS_ONCE() to prevent refetching the value for atomicity */
-	return 1 << ACCESS_ONCE(net->nft.gencursor);
+	/* Use READ_ONCE() to prevent refetching the value for atomicity */
+	return 1 << READ_ONCE(net->nft.gencursor);
 }
 
 #define NFT_GENMASK_ANY		((1 << 0) | (1 << 1))
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index f65b92e0e1f9..ee8220f8dcf5 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
 
 #ifndef __always_inline
 #define __always_inline inline