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

Pull locking/atomics update from Thomas Gleixner:
 "The locking, atomics and memory model brains delivered:

   - A larger update to the atomics code which reworks the ordering
     barriers, consolidates the atomic primitives, provides the new
     atomic64_fetch_add_unless() primitive and cleans up the include
     hell.

   - Simplify cmpxchg() instrumentation and add instrumentation for
     xchg() and cmpxchg_double().

   - Updates to the memory model and documentation"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  locking/atomics: Rework ordering barriers
  locking/atomics: Instrument cmpxchg_double*()
  locking/atomics: Instrument xchg()
  locking/atomics: Simplify cmpxchg() instrumentation
  locking/atomics/x86: Reduce arch_cmpxchg64*() instrumentation
  tools/memory-model: Rename litmus tests to comply to norm7
  tools/memory-model/Documentation: Fix typo, smb->smp
  sched/Documentation: Update wake_up() & co. memory-barrier guarantees
  locking/spinlock, sched/core: Clarify requirements for smp_mb__after_spinlock()
  sched/core: Use smp_mb() in wake_woken_function()
  tools/memory-model: Add informal LKMM documentation to MAINTAINERS
  locking/atomics/Documentation: Describe atomic_set() as a write operation
  tools/memory-model: Make scripts executable
  tools/memory-model: Remove ACCESS_ONCE() from model
  tools/memory-model: Remove ACCESS_ONCE() from recipes
  locking/memory-barriers.txt/kokr: Update Korean translation to fix broken DMA vs. MMIO ordering example
  MAINTAINERS: Add Daniel Lustig as an LKMM reviewer
  tools/memory-model: Fix ISA2+pooncelock+pooncelock+pombonce name
  tools/memory-model: Add litmus test for full multicopy atomicity
  locking/refcount: Always allow checked forms
  ...

77 files changed, 988 insertions, 1982 deletions

diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst
index 2e7165f86f55..724583453e1f 100644
--- a/Documentation/core-api/atomic_ops.rst
+++ b/Documentation/core-api/atomic_ops.rst
@@ -29,7 +29,7 @@ updated by one CPU, local_t is probably more appropriate. Please see
 local_t.
 
 The first operations to implement for atomic_t's are the initializers and
-plain reads. ::
+plain writes. ::
 
 	#define ATOMIC_INIT(i)		{ (i) }
 	#define atomic_set(v, i)	((v)->counter = (i))
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index a02d6bbfc9d0..0d8d7ef131e9 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -2179,32 +2179,41 @@ or:
 	event_indicated = 1;
 	wake_up_process(event_daemon);
 
-A write memory barrier is implied by wake_up() and co.  if and only if they
-wake something up.  The barrier occurs before the task state is cleared, and so
-sits between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+A general memory barrier is executed by wake_up() if it wakes something up.
+If it doesn't wake anything up then a memory barrier may or may not be
+executed; you must not rely on it.  The barrier occurs before the task state
+is accessed, in particular, it sits between the STORE to indicate the event
+and the STORE to set TASK_RUNNING:
 
-	CPU 1				CPU 2
+	CPU 1 (Sleeper)			CPU 2 (Waker)
 	===============================	===============================
 	set_current_state();		STORE event_indicated
 	  smp_store_mb();		wake_up();
-	    STORE current->state	  <write barrier>
-	    <general barrier>		  STORE current->state
-	LOAD event_indicated
+	    STORE current->state	  ...
+	    <general barrier>		  <general barrier>
+	LOAD event_indicated		  if ((LOAD task->state) & TASK_NORMAL)
+					    STORE task->state
 
-To repeat, this write memory barrier is present if and only if something
-is actually awakened.  To see this, consider the following sequence of
-events, where X and Y are both initially zero:
+where "task" is the thread being woken up and it equals CPU 1's "current".
+
+To repeat, a general memory barrier is guaranteed to be executed by wake_up()
+if something is actually awakened, but otherwise there is no such guarantee.
+To see this, consider the following sequence of events, where X and Y are both
+initially zero:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	X = 1;				STORE event_indicated
+	X = 1;				Y = 1;
 	smp_mb();			wake_up();
-	Y = 1;				wait_event(wq, Y == 1);
-	wake_up();			  load from Y sees 1, no memory barrier
-					load from X might see 0
+	LOAD Y				LOAD X
+
+If a wakeup does occur, one (at least) of the two loads must see 1.  If, on
+the other hand, a wakeup does not occur, both loads might see 0.
 
-In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed
-to see 1.
+wake_up_process() always executes a general memory barrier.  The barrier again
+occurs before the task state is accessed.  In particular, if the wake_up() in
+the previous snippet were replaced by a call to wake_up_process() then one of
+the two loads would be guaranteed to see 1.
 
 The available waker functions include:
 
@@ -2224,6 +2233,8 @@ The available waker functions include:
 	wake_up_poll();
 	wake_up_process();
 
+In terms of memory ordering, these functions all provide the same guarantees of
+a wake_up() (or stronger).
 
 [!] Note that the memory barriers implied by the sleeper and the waker do _not_
 order multiple stores before the wake-up with respect to loads of those stored
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 921739d00f69..7f01fb1c1084 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -1891,22 +1891,22 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효�
 		/* 소유권을 수정 */
 		desc->status = DEVICE_OWN;
 
-		/* MMIO 를 통해 디바이스에 공지를 하기 전에 메모리를 동기화 */
-		wmb();
-
 		/* 업데이트된 디스크립터의 디바이스에 공지 */
 		writel(DESC_NOTIFY, doorbell);
 	}
 
      dma_rmb() 는 디스크립터로부터 데이터를 읽어오기 전에 디바이스가 소유권을
-     내놓았음을 보장하게 하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시
-     가졌음을 보기 전에 디스크립터에 데이터가 쓰였음을 보장합니다.  wmb() 는
-     캐시 일관성이 없는 (cache incoherent) MMIO 영역에 쓰기를 시도하기 전에
-     캐시 일관성이 있는 메모리 (cache coherent memory) 쓰기가 완료되었음을
-     보장해주기 위해 필요합니다.
-
-     consistent memory 에 대한 자세한 내용을 위해선 Documentation/DMA-API.txt
-     문서를 참고하세요.
+     내려놓았을 것을 보장하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시
+     가졌음을 보기 전에 디스크립터에 데이터가 쓰였을 것을 보장합니다.  참고로,
+     writel() 을 사용하면 캐시 일관성이 있는 메모리 (cache coherent memory)
+     쓰기가 MMIO 영역에의 쓰기 전에 완료되었을 것을 보장하므로 writel() 앞에
+     wmb() 를 실행할 필요가 없음을 알아두시기 바랍니다.  writel() 보다 비용이
+     저렴한 writel_relaxed() 는 이런 보장을 제공하지 않으므로 여기선 사용되지
+     않아야 합니다.
+
+     writel_relaxed() 와 같은 완화된 I/O 접근자들에 대한 자세한 내용을 위해서는
+     "커널 I/O 배리어의 효과" 섹션을, consistent memory 에 대한 자세한 내용을
+     위해선 Documentation/DMA-API.txt 문서를 참고하세요.
 
 
 MMIO 쓰기 배리어
diff --git a/MAINTAINERS b/MAINTAINERS
index d0d729016d65..629e08703c82 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8317,10 +8317,16 @@ M:	Jade Alglave <j.alglave@ucl.ac.uk>
 M:	Luc Maranget <luc.maranget@inria.fr>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 R:	Akira Yokosawa <akiyks@gmail.com>
+R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
+L:	linux-arch@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	tools/memory-model/
+F:	Documentation/atomic_bitops.txt
+F:	Documentation/atomic_t.txt
+F:	Documentation/core-api/atomic_ops.rst
+F:	Documentation/core-api/refcount-vs-atomic.rst
 F:	Documentation/memory-barriers.txt
 
 LINUX SECURITY MODULE (LSM) FRAMEWORK
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 767bfdd42992..150a1c5d6a2c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -18,11 +18,11 @@
  * To ensure dependency ordering is preserved for the _relaxed and
  * _release atomics, an smp_read_barrier_depends() is unconditionally
  * inserted into the _relaxed variants, which are used to build the
- * barriered versions. To avoid redundant back-to-back fences, we can
- * define the _acquire and _fence versions explicitly.
+ * barriered versions. Avoid redundant back-to-back fences in the
+ * _acquire and _fence versions.
  */
-#define __atomic_op_acquire(op, args...)	op##_relaxed(args)
-#define __atomic_op_fence			__atomic_op_release
+#define __atomic_acquire_fence()
+#define __atomic_post_full_fence()
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, new, old;
 	smp_mb();
@@ -235,38 +235,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	smp_mb();
 	return old;
 }
-
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
+ * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
-	long c, tmp;
+	long c, new, old;
 	smp_mb();
 	__asm__ __volatile__(
-	"1:	ldq_l	%[tmp],%[mem]\n"
-	"	cmpeq	%[tmp],%[u],%[c]\n"
-	"	addq	%[tmp],%[a],%[tmp]\n"
+	"1:	ldq_l	%[old],%[mem]\n"
+	"	cmpeq	%[old],%[u],%[c]\n"
+	"	addq	%[old],%[a],%[new]\n"
 	"	bne	%[c],2f\n"
-	"	stq_c	%[tmp],%[mem]\n"
-	"	beq	%[tmp],3f\n"
+	"	stq_c	%[new],%[mem]\n"
+	"	beq	%[new],3f\n"
 	"2:\n"
 	".subsection 2\n"
 	"3:	br	1b\n"
 	".previous"
-	: [tmp] "=&r"(tmp), [c] "=&r"(c)
+	: [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c)
 	: [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u)
 	: "memory");
 	smp_mb();
-	return !c;
+	return old;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
@@ -295,31 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	smp_mb();
 	return old - 1;
 }
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-#define atomic64_dec_return(v) atomic64_sub_return(1,(v))
-
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-#define atomic64_inc_return(v) atomic64_add_return(1,(v))
-
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v) atomic_add(1,(v))
-#define atomic64_inc(v) atomic64_add(1,(v))
-
-#define atomic_dec(v) atomic_sub(1,(v))
-#define atomic64_dec(v) atomic64_sub(1,(v))
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* _ALPHA_ATOMIC_H */
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 11859287c52a..4e0072730241 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
-#define atomic_andnot atomic_andnot
+#define atomic_andnot		atomic_andnot
+#define atomic_fetch_andnot	atomic_fetch_andnot
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(op, c_op, asm_op)					\
@@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
-#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
 ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
 ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
@@ -308,48 +307,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v
- */
-#define __atomic_add_unless(v, a, u)					\
-({									\
-	int c, old;							\
-									\
-	/*								\
-	 * Explicit full memory barrier needed before/after as		\
-	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
-	 */								\
-	smp_mb();							\
-									\
-	c = atomic_read(v);						\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
-		c = old;						\
-									\
-	smp_mb();							\
-									\
-	c;								\
-})
-
-#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v)			atomic_add(1, v)
-#define atomic_dec(v)			atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)		(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
-
-
 #ifdef CONFIG_GENERIC_ATOMIC64
 
 #include <asm-generic/atomic64.h>
@@ -472,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v)	\
 	ATOMIC64_OP_RETURN(op, op1, op2)				\
 	ATOMIC64_FETCH_OP(op, op1, op2)
 
-#define atomic64_andnot atomic64_andnot
+#define atomic64_andnot		atomic64_andnot
+#define atomic64_fetch_andnot	atomic64_fetch_andnot
 
 ATOMIC64_OPS(add, add.f, adc)
 ATOMIC64_OPS(sub, sub.f, sbc)
@@ -559,53 +517,43 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return val;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * if (v != u) { v += a; ret = 1} else {ret = 0}
- * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ * Atomically adds @a to @v, if it was not @u.
+ * Returns the old value of @v
  */
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
-	int op_done;
+	long long old, temp;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	llockd  %0, [%2]	\n"
-	"	mov	%1, 1		\n"
 	"	brne	%L0, %L4, 2f	# continue to add since v != u \n"
 	"	breq.d	%H0, %H4, 3f	# return since v == u \n"
-	"	mov	%1, 0		\n"
 	"2:				\n"
-	"	add.f   %L0, %L0, %L3	\n"
-	"	adc     %H0, %H0, %H3	\n"
-	"	scondd  %0, [%2]	\n"
+	"	add.f   %L1, %L0, %L3	\n"
+	"	adc     %H1, %H0, %H3	\n"
+	"	scondd  %1, [%2]	\n"
 	"	bnz     1b		\n"
 	"3:				\n"
-	: "=&r"(val), "=&r" (op_done)
+	: "=&r"(old), "=&r" (temp)
 	: "r"(&v->counter), "r"(a), "r"(u)
 	: "cc");	/* memory clobber comes from smp_mb() */
 
 	smp_mb();
 
-	return op_done;
+	return old;
 }
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif	/* !CONFIG_GENERIC_ATOMIC64 */
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 66d0e215a773..f74756641410 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 }
 #define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int oldval, newval;
 	unsigned long tmp;
@@ -156,6 +156,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return oldval;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #else /* ARM_ARCH_6 */
 
@@ -215,15 +216,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
-		c = old;
-	return c;
-}
+#define atomic_fetch_andnot		atomic_fetch_andnot
 
 #endif /* __LINUX_ARM_ARCH__ */
 
@@ -254,17 +247,6 @@ ATOMIC_OPS(xor, ^=, eor)
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-#define atomic_inc(v)		atomic_add(1, v)
-#define atomic_dec(v)		atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
-#define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	long long counter;
@@ -494,12 +476,13 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return result;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
+	long long oldval, newval;
 	unsigned long tmp;
-	int ret = 1;
 
 	smp_mb();
 	prefetchw(&v->counter);
@@ -508,33 +491,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 "1:	ldrexd	%0, %H0, [%4]\n"
 "	teq	%0, %5\n"
 "	teqeq	%H0, %H5\n"
-"	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%Q0, %Q0, %Q6\n"
-"	adc	%R0, %R0, %R6\n"
-"	strexd	%2, %0, %H0, [%4]\n"
+"	adds	%Q1, %Q0, %Q6\n"
+"	adc	%R1, %R0, %R6\n"
+"	strexd	%2, %1, %H1, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
 
-	if (ret)
+	if (oldval != u)
 		smp_mb();
 
-	return ret;
+	return oldval;
 }
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index c0235e0ff849..9bca54dda75c 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -40,17 +40,6 @@
 
 #include <asm/cmpxchg.h>
 
-#define ___atomic_add_unless(v, a, u, sfx)				\
-({									\
-	typeof((v)->counter) c, old;					\
-									\
-	c = atomic##sfx##_read(v);					\
-	while (c != (u) &&						\
-	      (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c)	\
-		c = old;						\
-	c;								\
- })
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #define atomic_read(v)			READ_ONCE((v)->counter)
@@ -61,21 +50,11 @@
 #define atomic_add_return_release	atomic_add_return_release
 #define atomic_add_return		atomic_add_return
 
-#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
-#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
-#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
 #define atomic_sub_return_acquire	atomic_sub_return_acquire
 #define atomic_sub_return_release	atomic_sub_return_release
 #define atomic_sub_return		atomic_sub_return
 
-#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
-#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
-#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-
 #define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
 #define atomic_fetch_add_acquire	atomic_fetch_add_acquire
 #define atomic_fetch_add_release	atomic_fetch_add_release
@@ -119,13 +98,6 @@
 	cmpxchg_release(&((v)->counter), (old), (new))
 #define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
-#define __atomic_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
 #define atomic_andnot			atomic_andnot
 
 /*
@@ -140,21 +112,11 @@
 #define atomic64_add_return_release	atomic64_add_return_release
 #define atomic64_add_return		atomic64_add_return
 
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
-#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
-#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
 #define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
 #define atomic64_sub_return_acquire	atomic64_sub_return_acquire
 #define atomic64_sub_return_release	atomic64_sub_return_release
 #define atomic64_sub_return		atomic64_sub_return
 
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
-#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
-#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-
 #define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
 #define atomic64_fetch_add_acquire	atomic64_fetch_add_acquire
 #define atomic64_fetch_add_release	atomic64_fetch_add_release
@@ -195,16 +157,9 @@
 #define atomic64_cmpxchg_release	atomic_cmpxchg_release
 #define atomic64_cmpxchg		atomic_cmpxchg
 
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
-#define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
 #define atomic64_andnot			atomic64_andnot
 
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#define atomic64_dec_if_positive	atomic64_dec_if_positive
 
 #endif
 #endif
diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
index 9c19594ce7cb..10d536b1af74 100644
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -17,22 +17,11 @@
 #define __ASM_BITOPS_H
 
 #include <linux/compiler.h>
-#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif
 
-/*
- * Little endian assembly atomic bitops.
- */
-extern void set_bit(int nr, volatile unsigned long *p);
-extern void clear_bit(int nr, volatile unsigned long *p);
-extern void change_bit(int nr, volatile unsigned long *p);
-extern int test_and_set_bit(int nr, volatile unsigned long *p);
-extern int test_and_clear_bit(int nr, volatile unsigned long *p);
-extern int test_and_change_bit(int nr, volatile unsigned long *p);
-
 #include <asm-generic/bitops/builtin-__ffs.h>
 #include <asm-generic/bitops/builtin-ffs.h>
 #include <asm-generic/bitops/builtin-__fls.h>
@@ -44,15 +33,11 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p);
 
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
-
-/*
- * Ext2 is defined to use little-endian byte ordering.
- */
-#define ext2_set_bit_atomic(lock, nr, p)	test_and_set_bit_le(nr, p)
-#define ext2_clear_bit_atomic(lock, nr, p)	test_and_clear_bit_le(nr, p)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #endif /* __ASM_BITOPS_H */
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 137710f4dac3..68755fd70dcf 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
+lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
deleted file mode 100644
index 43ac736baa5b..000000000000
--- a/arch/arm64/lib/bitops.S
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Based on arch/arm/lib/bitops.h
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/lse.h>
-
-/*
- * x0: bits 5:0  bit offset
- *     bits 31:6 word offset
- * x1: address
- */
-	.macro	bitop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x3, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
-alt_lse	"	\llsc	x2, x2, x3",		"nop"
-alt_lse	"	stxr	w0, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w0, 1b",		"nop"
-
-	ret
-ENDPROC(\name	)
-	.endm
-
-	.macro	testop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x4, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"
-	lsr	x0, x2, x3
-alt_lse	"	\llsc	x2, x2, x4",		"nop"
-alt_lse	"	stlxr	w5, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w5, 1b",		"nop"
-alt_lse	"	dmb	ish",			"nop"
-
-	and	x0, x0, #1
-	ret
-ENDPROC(\name	)
-	.endm
-
-/*
- * Atomic bit operations.
- */
-	bitop	change_bit, eor, steor
-	bitop	clear_bit, bic, stclr
-	bitop	set_bit, orr, stset
-
-	testop	test_and_change_bit, eor, ldeoral
-	testop	test_and_clear_bit, bic, ldclral
-	testop	test_and_set_bit, orr, ldsetal
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 941e7554e886..c6b6a06231b2 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -2,8 +2,10 @@
 #ifndef __ARCH_H8300_ATOMIC__
 #define __ARCH_H8300_ATOMIC__
 
+#include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/irqflags.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -15,8 +17,6 @@
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
-#include <linux/kernel.h>
-
 #define ATOMIC_OP_RETURN(op, c_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)	\
 {								\
@@ -69,18 +69,6 @@ ATOMIC_OPS(sub, -=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_inc_return(v)		atomic_add_return(1, v)
-#define atomic_dec_return(v)		atomic_sub_return(1, v)
-
-#define atomic_inc(v)			(void)atomic_inc_return(v)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
-#define atomic_dec(v)			(void)atomic_dec_return(v)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -94,7 +82,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	h8300flags flags;
@@ -106,5 +94,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	arch_local_irq_restore(flags);
 	return ret;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index fb3dfb2a667e..311b9894ccc8 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -164,7 +164,7 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer to value
  * @a: amount to add
  * @u: unless value is equal to u
@@ -173,7 +173,7 @@ ATOMIC_OPS(xor)
  *
  */
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int __oldval;
 	register int tmp;
@@ -196,18 +196,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	);
 	return __oldval;
 }
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #endif
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 2524fb60fbc2..206530d0751b 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,91 +215,10 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-
-static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
-/*
- * Atomically add I to V and return TRUE if the resulting value is
- * negative.
- */
-static __inline__ int
-atomic_add_negative (int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
-static __inline__ long
-atomic64_add_negative (__s64 i, atomic64_t *v)
-{
-	return atomic64_add_return(i, v) < 0;
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-#define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_sub_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v)	(atomic64_add_return(1, (v)) == 0)
-
 #define atomic_add(i,v)			(void)atomic_add_return((i), (v))
 #define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
 
 #define atomic64_add(i,v)		(void)atomic64_add_return((i), (v))
 #define atomic64_sub(i,v)		(void)atomic64_sub_return((i), (v))
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
 
 #endif /* _ASM_IA64_ATOMIC_H */
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index e993e2860ee1..47228b0d4163 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v)
 {
 	__asm__ __volatile__("addql #1,%0" : "+m" (*v));
 }
+#define atomic_inc atomic_inc
 
 static inline void atomic_dec(atomic_t *v)
 {
 	__asm__ __volatile__("subql #1,%0" : "+m" (*v));
 }
+#define atomic_dec atomic_dec
 
 static inline int atomic_dec_and_test(atomic_t *v)
 {
@@ -138,6 +140,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	__asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_dec_and_test atomic_dec_and_test
 
 static inline int atomic_dec_and_test_lt(atomic_t *v)
 {
@@ -155,6 +158,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
 	__asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_inc_and_test atomic_inc_and_test
 
 #ifdef CONFIG_RMW_INSNS
 
@@ -190,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 
 #endif /* !CONFIG_RMW_INSNS */
 
-#define atomic_dec_return(v)	atomic_sub_return(1, (v))
-#define atomic_inc_return(v)	atomic_add_return(1, (v))
-
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	char c;
@@ -201,6 +202,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
+#define atomic_sub_and_test atomic_sub_and_test
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
@@ -210,20 +212,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
-
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
+#define atomic_add_negative atomic_add_negative
 
 #endif /* __ARCH_M68K_ATOMIC __ */
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 54009ea710b3..d979f38af751 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -519,12 +519,16 @@ static inline int __fls(int x)
 
 #endif
 
+/* Simple test-and-set bit locks */
+#define test_and_set_bit_lock	test_and_set_bit
+#define clear_bit_unlock	clear_bit
+#define __clear_bit_unlock	clear_bit_unlock
+
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
 #endif /* _M68K_BITOPS_H */
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 0ab176bdb8e8..79be687de4ab 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -274,97 +274,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
-/*
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-/*
- * atomic_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
 /*
  * atomic_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
  */
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(1, v)
 
-/*
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1, (v))
-
-/*
- * atomic_dec - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1, (v))
-
-/*
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i)    { (i) }
@@ -620,99 +535,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
-/*
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-/*
- * atomic64_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic64_t
  */
 #define atomic64_dec_if_positive(v)	atomic64_sub_if_positive(1, v)
 
-/*
- * atomic64_inc - increment atomic variable
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic64_inc(v) atomic64_add(1, (v))
-
-/*
- * atomic64_dec - decrement and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic64_dec(v) atomic64_sub(1, (v))
-
-/*
- * atomic64_add_negative - add and test if negative
- * @v: pointer of type atomic64_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h
index 146e1660f00e..b589fac39b92 100644
--- a/arch/openrisc/include/asm/atomic.h
+++ b/arch/openrisc/include/asm/atomic.h
@@ -100,7 +100,7 @@ ATOMIC_OP(xor)
  *
  * This is often used through atomic_inc_not_zero()
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int old, tmp;
 
@@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return old;
 }
-#define __atomic_add_unless	__atomic_add_unless
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
 
 #include <asm-generic/atomic.h>
 
diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index d29f7db53906..f9cd43a39d72 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -16,8 +16,9 @@
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
+#include  <linux/bits.h>
+#include  <linux/compiler.h>
 #include  <linux/types.h>
-#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 88bae6676c9b..118953d41763 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC_OP(op, c_op)						\
 static __inline__ void atomic_##op(int i, atomic_t *v)			\
 {									\
@@ -160,28 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_inc(v)	(atomic_add(   1,(v)))
-#define atomic_dec(v)	(atomic_add(  -1,(v)))
-
-#define atomic_inc_return(v)	(atomic_add_return(   1,(v)))
-#define atomic_dec_return(v)	(atomic_add_return(  -1,(v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v)	(atomic_dec_return(v) == 0)
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_64BIT
@@ -264,72 +218,11 @@ atomic64_read(const atomic64_t *v)
 	return READ_ONCE((v)->counter);
 }
 
-#define atomic64_inc(v)		(atomic64_add(   1,(v)))
-#define atomic64_dec(v)		(atomic64_add(  -1,(v)))
-
-#define atomic64_inc_return(v)		(atomic64_add_return(   1,(v)))
-#define atomic64_dec_return(v)		(atomic64_add_return(  -1,(v)))
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i),(v)) == 0)
-
 /* exported interface */
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
 #endif /* !CONFIG_64BIT */
 
 
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 682b3e6a1e21..963abf8bf1c0 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -18,18 +18,11 @@
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
  * on the platform without lwsync.
  */
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
@@ -129,8 +122,6 @@ ATOMIC_OPS(xor, xor)
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
 static __inline__ void atomic_inc(atomic_t *v)
 {
 	int t;
@@ -145,6 +136,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_inc atomic_inc
 
 static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 {
@@ -163,16 +155,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 	return t;
 }
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
 static __inline__ void atomic_dec(atomic_t *v)
 {
 	int t;
@@ -187,6 +169,7 @@ static __inline__ void atomic_dec(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_dec atomic_dec
 
 static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 {
@@ -218,7 +201,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -226,13 +209,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	lwarx	%0,0,%1		# atomic_fetch_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -248,6 +231,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return t;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
@@ -280,9 +264,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v)
 }
 #define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
 
-#define atomic_sub_and_test(a, v)	(atomic_sub_return((a), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1, even if
@@ -412,8 +393,6 @@ ATOMIC64_OPS(xor, xor)
 #undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
 	long t;
@@ -427,6 +406,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_inc atomic64_inc
 
 static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 {
@@ -444,16 +424,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 	return t;
 }
 
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
 	long t;
@@ -467,6 +437,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_dec atomic64_dec
 
 static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 {
@@ -487,9 +458,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
 #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
 
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1.
@@ -513,6 +481,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 
 	return t;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_cmpxchg_relaxed(v, o, n) \
@@ -524,7 +493,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -532,13 +501,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
 	long t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	ldarx	%0,0,%1		# atomic64_fetch_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -551,8 +520,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	: "r" (&v->counter), "r" (a), "r" (u)
 	: "cc", "memory");
 
-	return t != u;
+	return t;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /**
  * atomic_inc64_not_zero - increment unless the number is zero
@@ -582,6 +552,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 
 	return t1 != 0;
 }
+#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v))
 
 #endif /* __powerpc64__ */
 
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 855115ace98c..c452359c9cb8 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -25,18 +25,11 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
 
 static __always_inline int atomic_read(const atomic_t *v)
 {
@@ -209,130 +202,8 @@ ATOMIC_OPS(xor, xor, i)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-/*
- * The extra atomic operations that are constructed from one of the core
- * AMO-based operations above (aside from sub, which is easier to fit above).
- * These are required to perform a full barrier, but they're OK this way
- * because atomic_*_return is also required to perform a full barrier.
- *
- */
-#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)		\
-static __always_inline							\
-bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_##func_op##_return(i, v) comp_op I;	\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )			\
-        ATOMIC_OP(op, func_op, comp_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(add_and_test, add, ==, 0)
-ATOMIC_OPS(sub_and_test, sub, ==, 0)
-ATOMIC_OPS(add_negative, add,  <, 0)
-
-#undef ATOMIC_OP
-#undef ATOMIC_OPS
-
-#define ATOMIC_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-void atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	atomic##prefix##_##func_op(I, v);				\
-}
-
-#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v)	\
-{									\
-	return atomic##prefix##_fetch_##func_op##_relaxed(I, v);	\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_fetch_##func_op(I, v);			\
-}
-
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)		\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v)	\
-{									\
-        return atomic##prefix##_fetch_##op##_relaxed(v) c_op I;		\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)		\
-{									\
-        return atomic##prefix##_fetch_##op(v) c_op I;			\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )			\
-        ATOMIC_OP(       op, asm_op,       I, long, 64)			\
-        ATOMIC_FETCH_OP( op, asm_op,       I, long, 64)			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(inc, add, +,  1)
-ATOMIC_OPS(dec, add, +, -1)
-
-#define atomic_inc_return_relaxed	atomic_inc_return_relaxed
-#define atomic_dec_return_relaxed	atomic_dec_return_relaxed
-#define atomic_inc_return		atomic_inc_return
-#define atomic_dec_return		atomic_dec_return
-
-#define atomic_fetch_inc_relaxed	atomic_fetch_inc_relaxed
-#define atomic_fetch_dec_relaxed	atomic_fetch_dec_relaxed
-#define atomic_fetch_inc		atomic_fetch_inc
-#define atomic_fetch_dec		atomic_fetch_dec
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-#define atomic64_inc_return_relaxed	atomic64_inc_return_relaxed
-#define atomic64_dec_return_relaxed	atomic64_dec_return_relaxed
-#define atomic64_inc_return		atomic64_inc_return
-#define atomic64_dec_return		atomic64_dec_return
-
-#define atomic64_fetch_inc_relaxed	atomic64_fetch_inc_relaxed
-#define atomic64_fetch_dec_relaxed	atomic64_fetch_dec_relaxed
-#define atomic64_fetch_inc		atomic64_fetch_inc
-#define atomic64_fetch_dec		atomic64_fetch_dec
-#endif
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
-#define ATOMIC_OP(op, func_op, comp_op, I, prefix)			\
-static __always_inline							\
-bool atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	return atomic##prefix##_##func_op##_return(v) comp_op I;	\
-}
-
-ATOMIC_OP(inc_and_test, inc, ==, 0,   )
-ATOMIC_OP(dec_and_test, dec, ==, 0,   )
-#ifndef CONFIG_GENERIC_ATOMIC64
-ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
-ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
-#endif
-
-#undef ATOMIC_OP
-
 /* This is required to provide a full barrier on success. */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
        int prev, rc;
 
@@ -349,9 +220,10 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 		: "memory");
 	return prev;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
+static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
        long prev, rc;
 
@@ -368,27 +240,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
 		: "memory");
 	return prev;
 }
-
-static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	return __atomic64_add_unless(v, a, u) != u;
-}
-#endif
-
-/*
- * The extra atomic operations that are constructed from one of the core
- * LR/SC-based operations above.
- */
-static __always_inline int atomic_inc_not_zero(atomic_t *v)
-{
-        return __atomic_add_unless(v, 1, 0);
-}
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
-{
-        return atomic64_add_unless(v, 1, 0);
-}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 #endif
 
 /*
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 4b55532f15c4..fd20ab5d4cf7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -55,17 +55,9 @@ static inline void atomic_add(int i, atomic_t *v)
 	__atomic_add(i, &v->counter);
 }
 
-#define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
-#define atomic_inc(_v)			atomic_add(1, _v)
-#define atomic_inc_return(_v)		atomic_add_return(1, _v)
-#define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
 #define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
-#define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
-#define atomic_dec(_v)			atomic_sub(1, _v)
-#define atomic_dec_return(_v)		atomic_sub_return(1, _v)
-#define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
 #define ATOMIC_OPS(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\
@@ -90,21 +82,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return __atomic_cmpxchg(&v->counter, old, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic_cmpxchg(v, c, c + a);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC64_INIT(i)  { (i) }
 
 static inline long atomic64_read(const atomic64_t *v)
@@ -168,50 +145,8 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-static inline int atomic64_add_unless(atomic64_t *v, long i, long u)
-{
-	long c, old;
-
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic64_cmpxchg(v, c, c + i);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != u;
-}
-
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
-#define atomic64_add_negative(_i, _v)	(atomic64_add_return(_i, _v) < 0)
-#define atomic64_inc(_v)		atomic64_add(1, _v)
-#define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
-#define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
 #define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
-#define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
-#define atomic64_dec(_v)		atomic64_sub(1, _v)
-#define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
-#define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 0fd0099f43cc..f37b95a80232 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -32,44 +32,9 @@
 #include <asm/atomic-irq.h>
 #endif
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-
 #define atomic_xchg(v, new)		(xchg(&((v)->counter), new))
 #define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-
-	return c;
-}
-
 #endif /* CONFIG_CPU_J2 */
 
 #endif /* __ASM_SH_ATOMIC_H */
diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h
index 1e881f5db659..593a9704782b 100644
--- a/arch/sh/include/asm/cmpxchg-xchg.h
+++ b/arch/sh/include/asm/cmpxchg-xchg.h
@@ -8,7 +8,8 @@
  * This work is licensed under the terms of the GNU GPL, version 2.  See the
  * file "COPYING" in the main directory of this archive for more details.
  */
-#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler.h>
 #include <asm/byteorder.h>
 
 /*
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index d13ce517f4b9..94c930f0bc62 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -27,17 +27,17 @@ int atomic_fetch_or(int, atomic_t *);
 int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
-int __atomic_add_unless(atomic_t *, int, int);
+int atomic_fetch_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
+
 #define atomic_set_release(v, i)	atomic_set((v), (i))
 
 #define atomic_read(v)          READ_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))
-#define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
-#define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
 #define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
 #define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
@@ -46,22 +46,4 @@ void atomic_set(atomic_t *, int);
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
 #define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
 
-#define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
-#define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
 #endif /* !(__ARCH_SPARC_ATOMIC__) */
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 28db058d471b..6963482c81d8 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -50,38 +50,6 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_dec_return(v)   atomic_sub_return(1, v)
-#define atomic64_dec_return(v) atomic64_sub_return(1, v)
-
-#define atomic_inc_return(v)   atomic_add_return(1, v)
-#define atomic64_inc_return(v) atomic64_add_return(1, v)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0)
-
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic64_inc(v) atomic64_add(1, v)
-
-#define atomic_dec(v) atomic_sub(1, v)
-#define atomic64_dec(v) atomic64_sub(1, v)
-
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0)
-
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 
 static inline int atomic_xchg(atomic_t *v, int new)
@@ -89,42 +57,11 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 465a901a0ada..281fa634bb1a 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new)
 }
 EXPORT_SYMBOL(atomic_cmpxchg);
 
-int __atomic_add_unless(atomic_t *v, int a, int u)
+int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	unsigned long flags;
@@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u)
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
 	return ret;
 }
-EXPORT_SYMBOL(__atomic_add_unless);
+EXPORT_SYMBOL(atomic_fetch_add_unless);
 
 /* Atomic operations are already serializing */
 void atomic_set(atomic_t *v, int i)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 0db6bec95489..b143717b92b3 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
 static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
@@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic_inc arch_atomic_inc
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
@@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic_dec arch_atomic_dec
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
@@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
 static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
@@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
 static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
@@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic_add_negative arch_atomic_add_negative
 static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
@@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 	return arch_atomic_add_return(-i, v);
 }
 
-#define arch_atomic_inc_return(v)  (arch_atomic_add_return(1, v))
-#define arch_atomic_dec_return(v)  (arch_atomic_sub_return(1, v))
-
 static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
@@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n
 
 static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
-	return xchg(&v->counter, new);
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic_and(int i, atomic_t *v)
@@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 	return val;
 }
 
-/**
- * __arch_atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns the old value of @v.
- */
-static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c = arch_atomic_read(v);
-
-	do {
-		if (unlikely(c == u))
-			break;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
-
-	return c;
-}
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 92212bf0484f..ef959f02d070 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_inc_return arch_atomic64_inc_return
 
 static inline long long arch_atomic64_dec_return(atomic64_t *v)
 {
@@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_dec_return arch_atomic64_dec_return
 
 /**
  * arch_atomic64_add - add integer to atomic64 variable
@@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
 }
 
 /**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
-{
-	return arch_atomic64_sub_return(i, v) == 0;
-}
-
-/**
  * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
@@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
@@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v)
 }
 
 /**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int arch_atomic64_dec_and_test(atomic64_t *v)
-{
-	return arch_atomic64_dec_return(v) == 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_inc_and_test(atomic64_t *v)
-{
-	return arch_atomic64_inc_return(v) == 0;
-}
-
-/**
- * arch_atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
-{
-	return arch_atomic64_add_return(i, v) < 0;
-}
-
-/**
  * arch_atomic64_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
@@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
 	return (int)a;
 }
 
-
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
@@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 	return r;
 }
 
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6106b59d3260..4343d9b4f30e 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
@@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
@@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
@@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
@@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
@@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic64_add_negative arch_atomic64_add_negative
 static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
@@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
 	return xadd(&v->counter, -i);
 }
 
-#define arch_atomic64_inc_return(v)  (arch_atomic64_add_return(1, (v)))
-#define arch_atomic64_dec_return(v)  (arch_atomic64_sub_return(1, (v)))
-
 static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
@@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l
 
 static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 {
-	return xchg(&v->counter, new);
-}
-
-/**
- * arch_atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	s64 c = arch_atomic64_read(v);
-	do {
-		if (unlikely(c == u))
-			return false;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
-	return true;
-}
-
-#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
-
-/*
- * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
-{
-	s64 dec, c = arch_atomic64_read(v);
-	do {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
-	return dec;
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic64_and(long i, atomic64_t *v)
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index e3efd8a06066..a55d79b233d3 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -75,7 +75,7 @@ extern void __add_wrong_size(void)
  * use "asm volatile" and "memory" clobbers to prevent gcc from moving
  * information around.
  */
-#define xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
+#define arch_xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
 
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index bfca3b346c74..072e5459fe2f 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 #define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
+	arch_cmpxchg((ptr), (o), (n));					\
 })
 
 #define arch_cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
+	arch_cmpxchg_local((ptr), (o), (n));				\
 })
 
 #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4cf11d88d3b3..19b90521954c 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -5,6 +5,7 @@
  * PaX/grsecurity.
  */
 #include <linux/refcount.h>
+#include <asm/bug.h>
 
 /*
  * This is the first portion of the refcount error handling, which lives in
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index e7a23f2a519a..7de0149e1cf7 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -197,107 +197,9 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0)
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1,(v))
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1,(v))
-
-/**
- * atomic_dec_return - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0)
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0)
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0)
-
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index fa0729c1e776..d81c653b9bf6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v)
 {
 	unsigned int counter;
 
-	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0);
 	if (counter <= (unsigned int)INT_MAX)
 		return (int)counter;
 
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index a6e904973ba8..475910ffbcb6 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive)
 	 * this lock.
 	 */
 	if (!exclusive)
-		return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ?
+		return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ?
 			-EBUSY : 0;
 
 	/* lock is either WRITE or DESTROY - should be exclusive */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a1b18082991b..183cc5418722 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 	trace_afs_notify_call(rxcall, call);
 	call->need_attention = true;
 
-	u = __atomic_add_unless(&call->usage, 1, 0);
+	u = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (u != 0) {
 		trace_afs_call(call, afs_call_trace_wake, u,
 			       atomic_read(&call->net->nr_outstanding_calls),
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index ec07f23678ea..0d4b1d3dbc1e 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -84,42 +84,59 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne
 }
 #endif
 
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#ifdef arch_atomic_fetch_add_unless
+#define atomic_fetch_add_unless atomic_fetch_add_unless
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return __arch_atomic_add_unless(v, a, u);
+	return arch_atomic_fetch_add_unless(v, a, u);
 }
+#endif
 
-
-static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+#ifdef arch_atomic64_fetch_add_unless
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return arch_atomic64_add_unless(v, a, u);
+	return arch_atomic64_fetch_add_unless(v, a, u);
 }
+#endif
 
+#ifdef arch_atomic_inc
+#define atomic_inc atomic_inc
 static __always_inline void atomic_inc(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc
+#define atomic64_inc atomic64_inc
 static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
+#endif
 
+#ifdef arch_atomic_dec
+#define atomic_dec atomic_dec
 static __always_inline void atomic_dec(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
+#endif
 
+#ifdef atch_atomic64_dec
+#define atomic64_dec
 static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
+#endif
 
 static __always_inline void atomic_add(int i, atomic_t *v)
 {
@@ -181,65 +198,95 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
 	arch_atomic64_xor(i, v);
 }
 
+#ifdef arch_atomic_inc_return
+#define atomic_inc_return atomic_inc_return
 static __always_inline int atomic_inc_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_in_return
+#define atomic64_inc_return atomic64_inc_return
 static __always_inline s64 atomic64_inc_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_return
+#define atomic_dec_return atomic_dec_return
 static __always_inline int atomic_dec_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_return
+#define atomic64_dec_return atomic64_dec_return
 static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
+#endif
 
-static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+#ifdef arch_atomic64_inc_not_zero
+#define atomic64_inc_not_zero atomic64_inc_not_zero
+static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_if_positive
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_and_test
+#define atomic_dec_and_test atomic_dec_and_test
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_and_test
+#define atomic64_dec_and_test atomic64_dec_and_test
 static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic_inc_and_test
+#define atomic_inc_and_test atomic_inc_and_test
 static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc_and_test
+#define atomic64_inc_and_test atomic64_inc_and_test
 static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
+#endif
 
 static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
@@ -325,152 +372,96 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
 	return arch_atomic64_fetch_xor(i, v);
 }
 
+#ifdef arch_atomic_sub_and_test
+#define atomic_sub_and_test atomic_sub_and_test
 static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_sub_and_test
+#define atomic64_sub_and_test atomic64_sub_and_test
 static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic_add_negative
+#define atomic_add_negative atomic_add_negative
 static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_add_negative
+#define atomic64_add_negative atomic64_add_negative
 static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
+#endif
 
-static __always_inline unsigned long
-cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
+#define xchg(ptr, new)							\
+({									\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_xchg(__ai_ptr, (new));					\
+})
 
 #define cmpxchg(ptr, old, new)						\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old),	\
-		(unsigned long)(new), sizeof(*(ptr))));			\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline unsigned long
-sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new,
-		  int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define sync_cmpxchg(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))sync_cmpxchg_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_sync_cmpxchg(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline unsigned long
-cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new,
-		   int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define cmpxchg_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_local_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg_local(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline u64
-cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64(ptr, old, new);
-}
-
 #define cmpxchg64(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old),		\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline u64
-cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64_local(ptr, old, new);
-}
-
 #define cmpxchg64_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old),	\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64_local(__ai_ptr, (old), (new));			\
 })
 
-/*
- * Originally we had the following code here:
- *     __typeof__(p1) ____p1 = (p1);
- *     kasan_check_write(____p1, 2 * sizeof(*____p1));
- *     arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
- * But it leads to compilation failures (see gcc issue 72873).
- * So for now it's left non-instrumented.
- * There are few callers of cmpxchg_double(), so it's not critical.
- */
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
-	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\
+	typeof(p1) __ai_p1 = (p1);					\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));		\
+	arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)			\
-({									\
-	arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2));	\
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)				\
+({										\
+	typeof(p1) __ai_p1 = (p1);						\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));			\
+	arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index abe6dd9ca2a8..13324aa828eb 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^)
 
 #include <linux/irqflags.h>
 
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
 static inline void atomic_add(int i, atomic_t *v)
 {
 	atomic_add_return(i, v);
@@ -201,35 +196,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	atomic_sub_return(i, v);
 }
 
-static inline void atomic_inc(atomic_t *v)
-{
-	atomic_add_return(1, v);
-}
-
-static inline void atomic_dec(atomic_t *v)
-{
-	atomic_sub_return(1, v);
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#ifndef __atomic_add_unless
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
-		c = old;
-	return c;
-}
-#endif
-
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 8d28eb010d0d..97b28b7f1f29 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -11,6 +11,7 @@
  */
 #ifndef _ASM_GENERIC_ATOMIC64_H
 #define _ASM_GENERIC_ATOMIC64_H
+#include <linux/types.h>
 
 typedef struct {
 	long long counter;
@@ -50,18 +51,10 @@ ATOMIC64_OPS(xor)
 #undef ATOMIC64_OP
 
 extern long long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern int	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) 	atomic64_add_unless((v), 1LL, 0LL)
+extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 04deffaf5f7d..dd90c9792909 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,189 +2,67 @@
 #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
 #define _ASM_GENERIC_BITOPS_ATOMIC_H_
 
-#include <asm/types.h>
-#include <linux/irqflags.h>
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-#  define ATOMIC_HASH_SIZE 4
-#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);	\
-	local_irq_save(f);			\
-	arch_spin_lock(s);			\
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);		\
-	arch_spin_unlock(s);				\
-	local_irq_restore(f);				\
-} while(0)
-
-
-#else
-#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
- * NMI events can occur at any time, including when interrupts have been
- * disabled by *_irqsave().  So you can get NMI events occurring while a
- * *_bit function is holding a spin lock.  If the NMI handler also wants
- * to do bit manipulation (and they do) then you can get a deadlock
- * between the original caller of *_bit() and the NMI handler.
- *
- * by Keith Owens
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
  */
 
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile unsigned long *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p  |= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p &= ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered. It may be
- * reordered on other architectures than x86.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p ^= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old | mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old & ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (!(READ_ONCE(*p) & mask))
+		return 0;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old ^ mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
 
-	return (old & mask) != 0;
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
 #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 67ab280ad134..3ae021368f48 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_GENERIC_BITOPS_LOCK_H_
 #define _ASM_GENERIC_BITOPS_LOCK_H_
 
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
 /**
  * test_and_set_bit_lock - Set a bit and return its old value, for lock
  * @nr: Bit to set
@@ -11,7 +15,20 @@
  * the returned value is 0.
  * It can be used to implement bit locks.
  */
-#define test_and_set_bit_lock(nr, addr)	test_and_set_bit(nr, addr)
+static inline int test_and_set_bit_lock(unsigned int nr,
+					volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
+
+	old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
 
 /**
  * clear_bit_unlock - Clear a bit in memory, for unlock
@@ -20,11 +37,11 @@
  *
  * This operation is atomic and provides release barrier semantics.
  */
-#define clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+}
 
 /**
  * __clear_bit_unlock - Clear a bit in memory, for unlock
@@ -37,11 +54,38 @@ do {					\
  *
  * See for example x86's implementation.
  */
-#define __clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void __clear_bit_unlock(unsigned int nr,
+				      volatile unsigned long *p)
+{
+	unsigned long old;
 
-#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
+	p += BIT_WORD(nr);
+	old = READ_ONCE(*p);
+	old &= ~BIT_MASK(nr);
+	atomic_long_set_release((atomic_long_t *)p, old);
+}
+
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                     byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+#ifndef clear_bit_unlock_is_negative_byte
+static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
+						     volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
 
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 01ce3997cb42..1e8e88bdaf09 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -2,6 +2,8 @@
 /* Atomic operations usable in machine independent code */
 #ifndef _LINUX_ATOMIC_H
 #define _LINUX_ATOMIC_H
+#include <linux/types.h>
+
 #include <asm/atomic.h>
 #include <asm/barrier.h>
 
@@ -36,40 +38,46 @@
  * barriers on top of the relaxed variant. In the case where the relaxed
  * variant is already fully ordered, no additional barriers are needed.
  *
- * Besides, if an arch has a special barrier for acquire/release, it could
- * implement its own __atomic_op_* and use the same framework for building
- * variants
- *
- * If an architecture overrides __atomic_op_acquire() it will probably want
- * to define smp_mb__after_spinlock().
+ * If an architecture overrides __atomic_acquire_fence() it will probably
+ * want to define smp_mb__after_spinlock().
  */
-#ifndef __atomic_op_acquire
+#ifndef __atomic_acquire_fence
+#define __atomic_acquire_fence		smp_mb__after_atomic
+#endif
+
+#ifndef __atomic_release_fence
+#define __atomic_release_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_pre_full_fence
+#define __atomic_pre_full_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_post_full_fence
+#define __atomic_post_full_fence	smp_mb__after_atomic
+#endif
+
 #define __atomic_op_acquire(op, args...)				\
 ({									\
 	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	smp_mb__after_atomic();						\
+	__atomic_acquire_fence();					\
 	__ret;								\
 })
-#endif
 
-#ifndef __atomic_op_release
 #define __atomic_op_release(op, args...)				\
 ({									\
-	smp_mb__before_atomic();					\
+	__atomic_release_fence();					\
 	op##_relaxed(args);						\
 })
-#endif
 
-#ifndef __atomic_op_fence
 #define __atomic_op_fence(op, args...)					\
 ({									\
 	typeof(op##_relaxed(args)) __ret;				\
-	smp_mb__before_atomic();					\
+	__atomic_pre_full_fence();					\
 	__ret = op##_relaxed(args);					\
-	smp_mb__after_atomic();						\
+	__atomic_post_full_fence();					\
 	__ret;								\
 })
-#endif
 
 /* atomic_add_return_relaxed */
 #ifndef atomic_add_return_relaxed
@@ -95,11 +103,23 @@
 #endif
 #endif /* atomic_add_return_relaxed */
 
+#ifndef atomic_inc
+#define atomic_inc(v)			atomic_add(1, (v))
+#endif
+
 /* atomic_inc_return_relaxed */
 #ifndef atomic_inc_return_relaxed
+
+#ifndef atomic_inc_return
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
+#else /* atomic_inc_return */
 #define  atomic_inc_return_relaxed	atomic_inc_return
 #define  atomic_inc_return_acquire	atomic_inc_return
 #define  atomic_inc_return_release	atomic_inc_return
+#endif /* atomic_inc_return */
 
 #else /* atomic_inc_return_relaxed */
 
@@ -143,11 +163,23 @@
 #endif
 #endif /* atomic_sub_return_relaxed */
 
+#ifndef atomic_dec
+#define atomic_dec(v)			atomic_sub(1, (v))
+#endif
+
 /* atomic_dec_return_relaxed */
 #ifndef atomic_dec_return_relaxed
+
+#ifndef atomic_dec_return
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
+#else /* atomic_dec_return */
 #define  atomic_dec_return_relaxed	atomic_dec_return
 #define  atomic_dec_return_acquire	atomic_dec_return
 #define  atomic_dec_return_release	atomic_dec_return
+#endif /* atomic_dec_return */
 
 #else /* atomic_dec_return_relaxed */
 
@@ -328,12 +360,22 @@
 #endif
 #endif /* atomic_fetch_and_relaxed */
 
-#ifdef atomic_andnot
-/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_andnot
+#define atomic_andnot(i, v)		atomic_and(~(int)(i), (v))
+#endif
+
 #ifndef atomic_fetch_andnot_relaxed
-#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot
-#define atomic_fetch_andnot_acquire	atomic_fetch_andnot
-#define atomic_fetch_andnot_release	atomic_fetch_andnot
+
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(i, v)		atomic_fetch_and(~(int)(i), (v))
+#define atomic_fetch_andnot_relaxed(i, v)	atomic_fetch_and_relaxed(~(int)(i), (v))
+#define atomic_fetch_andnot_acquire(i, v)	atomic_fetch_and_acquire(~(int)(i), (v))
+#define atomic_fetch_andnot_release(i, v)	atomic_fetch_and_release(~(int)(i), (v))
+#else /* atomic_fetch_andnot */
+#define atomic_fetch_andnot_relaxed		atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire		atomic_fetch_andnot
+#define atomic_fetch_andnot_release		atomic_fetch_andnot
+#endif /* atomic_fetch_andnot */
 
 #else /* atomic_fetch_andnot_relaxed */
 
@@ -352,7 +394,6 @@
 	__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic_fetch_andnot_relaxed */
-#endif /* atomic_andnot */
 
 /* atomic_fetch_xor_relaxed */
 #ifndef atomic_fetch_xor_relaxed
@@ -520,112 +561,140 @@
 #endif /* xchg_relaxed */
 
 /**
+ * atomic_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic_fetch_add_unless
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic_try_cmpxchg(v, &c, c + a));
+
+	return c;
+}
+#endif
+
+/**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
  */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
+static inline bool atomic_add_unless(atomic_t *v, int a, int u)
 {
-	return __atomic_add_unless(v, a, u) != u;
+	return atomic_fetch_add_unless(v, a, u) != u;
 }
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
  * @v: pointer of type atomic_t
  *
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
  */
 #ifndef atomic_inc_not_zero
 #define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
 #endif
 
-#ifndef atomic_andnot
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	atomic_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot(int i, atomic_t *v)
-{
-	return atomic_fetch_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_inc_and_test
+static inline bool atomic_inc_and_test(atomic_t *v)
 {
-	return atomic_fetch_and_relaxed(~i, v);
+	return atomic_inc_return(v) == 0;
 }
+#endif
 
-static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic_dec_and_test
+static inline bool atomic_dec_and_test(atomic_t *v)
 {
-	return atomic_fetch_and_acquire(~i, v);
+	return atomic_dec_return(v) == 0;
 }
+#endif
 
-static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_sub_and_test
+static inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
-	return atomic_fetch_and_release(~i, v);
+	return atomic_sub_return(i, v) == 0;
 }
 #endif
 
 /**
- * atomic_inc_not_zero_hint - increment if not null
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
  * @v: pointer of type atomic_t
- * @hint: probable value of the atomic before the increment
- *
- * This version of atomic_inc_not_zero() gives a hint of probable
- * value of the atomic. This helps processor to not read the memory
- * before doing the atomic read/modify/write cycle, lowering
- * number of bus transactions on some arches.
  *
- * Returns: 0 if increment was not done, 1 otherwise.
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
  */
-#ifndef atomic_inc_not_zero_hint
-static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
+#ifndef atomic_add_negative
+static inline bool atomic_add_negative(int i, atomic_t *v)
 {
-	int val, c = hint;
-
-	/* sanity test, should be removed by compiler if hint is a constant */
-	if (!hint)
-		return atomic_inc_not_zero(v);
-
-	do {
-		val = atomic_cmpxchg(v, c, c + 1);
-		if (val == c)
-			return 1;
-		c = val;
-	} while (c);
-
-	return 0;
+	return atomic_add_return(i, v) < 0;
 }
 #endif
 
 #ifndef atomic_inc_unless_negative
-static inline int atomic_inc_unless_negative(atomic_t *p)
+static inline bool atomic_inc_unless_negative(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v >= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v + 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c + 1));
+
+	return true;
 }
 #endif
 
 #ifndef atomic_dec_unless_positive
-static inline int atomic_dec_unless_positive(atomic_t *p)
+static inline bool atomic_dec_unless_positive(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v <= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v - 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c - 1));
+
+	return true;
 }
 #endif
 
@@ -639,17 +708,14 @@ static inline int atomic_dec_unless_positive(atomic_t *p)
 #ifndef atomic_dec_if_positive
 static inline int atomic_dec_if_positive(atomic_t *v)
 {
-	int c, old, dec;
-	c = atomic_read(v);
-	for (;;) {
+	int dec, c = atomic_read(v);
+
+	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-		old = atomic_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
+	} while (!atomic_try_cmpxchg(v, &c, dec));
+
 	return dec;
 }
 #endif
@@ -693,11 +759,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_add_return_relaxed */
 
+#ifndef atomic64_inc
+#define atomic64_inc(v)			atomic64_add(1, (v))
+#endif
+
 /* atomic64_inc_return_relaxed */
 #ifndef atomic64_inc_return_relaxed
+
+#ifndef atomic64_inc_return
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
+#else /* atomic64_inc_return */
 #define  atomic64_inc_return_relaxed	atomic64_inc_return
 #define  atomic64_inc_return_acquire	atomic64_inc_return
 #define  atomic64_inc_return_release	atomic64_inc_return
+#endif /* atomic64_inc_return */
 
 #else /* atomic64_inc_return_relaxed */
 
@@ -742,11 +820,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_sub_return_relaxed */
 
+#ifndef atomic64_dec
+#define atomic64_dec(v)			atomic64_sub(1, (v))
+#endif
+
 /* atomic64_dec_return_relaxed */
 #ifndef atomic64_dec_return_relaxed
+
+#ifndef atomic64_dec_return
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
+#else /* atomic64_dec_return */
 #define  atomic64_dec_return_relaxed	atomic64_dec_return
 #define  atomic64_dec_return_acquire	atomic64_dec_return
 #define  atomic64_dec_return_release	atomic64_dec_return
+#endif /* atomic64_dec_return */
 
 #else /* atomic64_dec_return_relaxed */
 
@@ -927,12 +1017,22 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_fetch_and_relaxed */
 
-#ifdef atomic64_andnot
-/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_andnot
+#define atomic64_andnot(i, v)		atomic64_and(~(long long)(i), (v))
+#endif
+
 #ifndef atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_release	atomic64_fetch_andnot
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(i, v)		atomic64_fetch_and(~(long long)(i), (v))
+#define atomic64_fetch_andnot_relaxed(i, v)	atomic64_fetch_and_relaxed(~(long long)(i), (v))
+#define atomic64_fetch_andnot_acquire(i, v)	atomic64_fetch_and_acquire(~(long long)(i), (v))
+#define atomic64_fetch_andnot_release(i, v)	atomic64_fetch_and_release(~(long long)(i), (v))
+#else /* atomic64_fetch_andnot */
+#define atomic64_fetch_andnot_relaxed		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release		atomic64_fetch_andnot
+#endif /* atomic64_fetch_andnot */
 
 #else /* atomic64_fetch_andnot_relaxed */
 
@@ -951,7 +1051,6 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 	__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic64_fetch_andnot_relaxed */
-#endif /* atomic64_andnot */
 
 /* atomic64_fetch_xor_relaxed */
 #ifndef atomic64_fetch_xor_relaxed
@@ -1049,30 +1148,164 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
 #endif /* atomic64_try_cmpxchg */
 
-#ifndef atomic64_andnot
-static inline void atomic64_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic64_fetch_add_unless
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	atomic64_and(~i, v);
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+
+	return c;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
+ */
+static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	return atomic64_fetch_and(~i, v);
+	return atomic64_fetch_add_unless(v, a, u) != u;
 }
 
-static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
+/**
+ * atomic64_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
+ */
+#ifndef atomic64_inc_not_zero
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#endif
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_inc_and_test
+static inline bool atomic64_inc_and_test(atomic64_t *v)
 {
-	return atomic64_fetch_and_relaxed(~i, v);
+	return atomic64_inc_return(v) == 0;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic64_dec_and_test
+static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
-	return atomic64_fetch_and_acquire(~i, v);
+	return atomic64_dec_return(v) == 0;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_sub_and_test
+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+	return atomic64_sub_return(i, v) == 0;
+}
+#endif
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#ifndef atomic64_add_negative
+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
 {
-	return atomic64_fetch_and_release(~i, v);
+	return atomic64_add_return(i, v) < 0;
+}
+#endif
+
+#ifndef atomic64_inc_unless_negative
+static inline bool atomic64_inc_unless_negative(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c + 1));
+
+	return true;
+}
+#endif
+
+#ifndef atomic64_dec_unless_positive
+static inline bool atomic64_dec_unless_positive(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c - 1));
+
+	return true;
+}
+#endif
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic64 variable, v, was not decremented.
+ */
+#ifndef atomic64_dec_if_positive
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long dec, c = atomic64_read(v);
+
+	do {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, dec));
+
+	return dec;
 }
 #endif
 
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 4cac4e1a72ff..af419012d77d 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -2,29 +2,9 @@
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
 #include <asm/types.h>
+#include <linux/bits.h>
 
-#ifdef	__KERNEL__
-#define BIT(nr)			(1UL << (nr))
-#define BIT_ULL(nr)		(1ULL << (nr))
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
-#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#endif
-
-/*
- * Create a contiguous bitmask starting at bit position @l and ending at
- * position @h. For example
- * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(h, l) \
-	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
-
-#define GENMASK_ULL(h, l) \
-	(((~0ULL) - (1ULL << (l)) + 1) & \
-	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/bits.h b/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index a685da2c4522..e28cce21bad6 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -3,9 +3,10 @@
 #define _LINUX_REFCOUNT_H
 
 #include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/spinlock_types.h>
+
+struct mutex;
 
 /**
  * struct refcount_t - variant of atomic_t specialized for reference counts
@@ -42,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r)
 	return atomic_read(&r->refs);
 }
 
+extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r);
+extern void refcount_add_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r);
+extern void refcount_inc_checked(refcount_t *r);
+
+extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_dec_and_test_checked(refcount_t *r);
+extern void refcount_dec_checked(refcount_t *r);
+
 #ifdef CONFIG_REFCOUNT_FULL
-extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r);
-extern void refcount_add(unsigned int i, refcount_t *r);
 
-extern __must_check bool refcount_inc_not_zero(refcount_t *r);
-extern void refcount_inc(refcount_t *r);
+#define refcount_add_not_zero	refcount_add_not_zero_checked
+#define refcount_add		refcount_add_checked
+
+#define refcount_inc_not_zero	refcount_inc_not_zero_checked
+#define refcount_inc		refcount_inc_checked
+
+#define refcount_sub_and_test	refcount_sub_and_test_checked
 
-extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r);
+#define refcount_dec_and_test	refcount_dec_and_test_checked
+#define refcount_dec		refcount_dec_checked
 
-extern __must_check bool refcount_dec_and_test(refcount_t *r);
-extern void refcount_dec(refcount_t *r);
 #else
 # ifdef CONFIG_ARCH_HAS_REFCOUNT
 #  include <asm/refcount.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e0f4f56c9310..dac5086e3815 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -167,8 +167,8 @@ struct task_group;
  *   need_sleep = false;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * Where wake_up_state() (and all other wakeup primitives) imply enough
- * barriers to order the store of the variable against wakeup.
+ * where wake_up_state() executes a full memory barrier before accessing the
+ * task state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index fd57888d4942..3190997df9ca 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -114,29 +114,48 @@ do {								\
 #endif /*arch_spin_is_contended*/
 
 /*
- * This barrier must provide two things:
+ * smp_mb__after_spinlock() provides the equivalent of a full memory barrier
+ * between program-order earlier lock acquisitions and program-order later
+ * memory accesses.
  *
- *   - it must guarantee a STORE before the spin_lock() is ordered against a
- *     LOAD after it, see the comments at its two usage sites.
+ * This guarantees that the following two properties hold:
  *
- *   - it must ensure the critical section is RCsc.
+ *   1) Given the snippet:
  *
- * The latter is important for cases where we observe values written by other
- * CPUs in spin-loops, without barriers, while being subject to scheduling.
+ *	  { X = 0;  Y = 0; }
  *
- * CPU0			CPU1			CPU2
+ *	  CPU0				CPU1
  *
- *			for (;;) {
- *			  if (READ_ONCE(X))
- *			    break;
- *			}
- * X=1
- *			<sched-out>
- *						<sched-in>
- *						r = X;
+ *	  WRITE_ONCE(X, 1);		WRITE_ONCE(Y, 1);
+ *	  spin_lock(S);			smp_mb();
+ *	  smp_mb__after_spinlock();	r1 = READ_ONCE(X);
+ *	  r0 = READ_ONCE(Y);
+ *	  spin_unlock(S);
  *
- * without transitivity it could be that CPU1 observes X!=0 breaks the loop,
- * we get migrated and CPU2 sees X==0.
+ *      it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
+ *      and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
+ *      preceding the call to smp_mb__after_spinlock() in __schedule() and in
+ *      try_to_wake_up().
+ *
+ *   2) Given the snippet:
+ *
+ *  { X = 0;  Y = 0; }
+ *
+ *  CPU0		CPU1				CPU2
+ *
+ *  spin_lock(S);	spin_lock(S);			r1 = READ_ONCE(Y);
+ *  WRITE_ONCE(X, 1);	smp_mb__after_spinlock();	smp_rmb();
+ *  spin_unlock(S);	r0 = READ_ONCE(X);		r2 = READ_ONCE(X);
+ *			WRITE_ONCE(Y, 1);
+ *			spin_unlock(S);
+ *
+ *      it is forbidden that CPU0's critical section executes before CPU1's
+ *      critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
+ *      and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
+ *      preceding the calls to smp_rmb() in try_to_wake_up() for similar
+ *      snippets but "projected" onto two CPUs.
+ *
+ * Property (2) upgrades the lock to an RCsc lock.
  *
  * Since most load-store architectures implement ACQUIRE with an smp_mb() after
  * the LL/SC loop, they need no further barriers. Similarly all our TSO
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a31a1ba0f8ea..b41c6cf2eb88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
 {
 	int refold;
 
-	refold = __atomic_add_unless(&map->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_map_put(map, false);
@@ -1144,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_prog_put(prog, false);
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index e426b0cb9ac6..a1ad5b7d5521 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -22,8 +22,8 @@
  *
  * See also complete_all(), wait_for_completion() and related routines.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void complete(struct completion *x)
 {
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete);
  *
  * This will wake up all threads waiting on this particular completion event.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  *
  * Since complete_all() sets the completion of @x permanently to done
  * to allow multiple waiters to finish, a call to reinit_completion()
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index deafa9fe602b..d17d99778356 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -406,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_q().
+	 * This cmpxchg() executes a full barrier, which pairs with the full
+	 * barrier executed by the wakeup in wake_up_q().
 	 */
 	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
 		return;
@@ -435,8 +435,8 @@ void wake_up_q(struct wake_q_head *head)
 		task->wake_q.next = NULL;
 
 		/*
-		 * wake_up_process() implies a wmb() to pair with the queueing
-		 * in wake_q_add() so as not to miss wakeups.
+		 * wake_up_process() executes a full barrier, which pairs with
+		 * the queueing in wake_q_add() so as not to miss wakeups.
 		 */
 		wake_up_process(task);
 		put_task_struct(task);
@@ -1859,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *     rq(c1)->lock (if not at the same time, then in that order).
  *  C) LOCK of the rq(c1)->lock scheduling in task
  *
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
  * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
@@ -1922,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *   UNLOCK rq(0)->lock
  *
  *
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
  */
 
 /**
@@ -1947,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * Atomic against schedule() which would dequeue a task, also see
  * set_current_state().
  *
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
  */
@@ -1978,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
 	 * in smp_cond_load_acquire() below.
 	 *
-	 * sched_ttwu_pending()                 try_to_wake_up()
-	 *   [S] p->on_rq = 1;                  [L] P->state
-	 *       UNLOCK rq->lock  -----.
-	 *                              \
-	 *				 +---   RMB
-	 * schedule()                   /
-	 *       LOCK rq->lock    -----'
-	 *       UNLOCK rq->lock
+	 * sched_ttwu_pending()			try_to_wake_up()
+	 *   STORE p->on_rq = 1			  LOAD p->state
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   UNLOCK rq->lock
 	 *
 	 * [task p]
-	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *   STORE p->state = UNINTERRUPTIBLE	  LOAD p->on_rq
 	 *
-	 * Pairs with the UNLOCK+LOCK on rq->lock from the
-	 * last wakeup of our task and the schedule that got our task
-	 * current.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2006,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * One must be running (->on_cpu == 1) in order to remove oneself
 	 * from the runqueue.
 	 *
-	 *  [S] ->on_cpu = 1;	[L] ->on_rq
-	 *      UNLOCK rq->lock
-	 *			RMB
-	 *      LOCK   rq->lock
-	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 * __schedule() (switch to task 'p')	try_to_wake_up()
+	 *   STORE p->on_cpu = 1		  LOAD p->on_rq
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (put 'p' to sleep)
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   STORE p->on_rq = 0			  LOAD p->on_cpu
 	 *
-	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
-	 * from the consecutive calls to schedule(); the first switching to our
-	 * task, the second putting it to sleep.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 
@@ -2120,8 +2116,7 @@ out:
  *
  * Return: 1 if the process was woken up, 0 if it was already running.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
  */
 int wake_up_process(struct task_struct *p)
 {
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 928be527477e..870f97b313e3 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
  *
  * On UP it can prevent extra preemption.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void)
  *     if (condition)
  *         break;
  *
- *     p->state = mode;				condition = true;
- *     smp_mb(); // A				smp_wmb(); // C
- *     if (!wq_entry->flags & WQ_FLAG_WOKEN)	wq_entry->flags |= WQ_FLAG_WOKEN;
- *         schedule()				try_to_wake_up();
- *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
- *     wq_entry->flags &= ~WQ_FLAG_WOKEN;		condition = true;
- *     smp_mb() // B				smp_wmb(); // C
- *						wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ *     // in wait_woken()			// in woken_wake_function()
  *
+ *     p->state = mode;				wq_entry->flags |= WQ_FLAG_WOKEN;
+ *     smp_mb(); // A				try_to_wake_up():
+ *     if (!(wq_entry->flags & WQ_FLAG_WOKEN))	   <full barrier>
+ *         schedule()				   if (p->state & mode)
+ *     p->state = TASK_RUNNING;			      p->state = TASK_RUNNING;
+ *     wq_entry->flags &= ~WQ_FLAG_WOKEN;	~~~~~~~~~~~~~~~~~~
+ *     smp_mb(); // B				condition = true;
+ * }						smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait);		wq_entry->flags |= WQ_FLAG_WOKEN;
  */
 long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 {
-	set_current_state(mode); /* A */
 	/*
-	 * The above implies an smp_mb(), which matches with the smp_wmb() from
-	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
-	 * also observe all state before the wakeup.
+	 * The below executes an smp_mb(), which matches with the full barrier
+	 * executed by the try_to_wake_up() in woken_wake_function() such that
+	 * either we see the store to wq_entry->flags in woken_wake_function()
+	 * or woken_wake_function() sees our store to current->state.
 	 */
+	set_current_state(mode); /* A */
 	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);
 
 	/*
-	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
-	 * woken_wake_function() such that we must either observe the wait
-	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
-	 * an event.
+	 * The below executes an smp_mb(), which matches with the smp_mb() (C)
+	 * in woken_wake_function() such that either we see the wait condition
+	 * being true or the store to wq_entry->flags in woken_wake_function()
+	 * follows ours in the coherence order.
 	 */
 	smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
 
@@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken);
 
 int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
-	/*
-	 * Although this function is called under waitqueue lock, LOCK
-	 * doesn't imply write barrier and the users expects write
-	 * barrier semantics on wakeup functions.  The following
-	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
-	 * and is paired with smp_store_mb() in wait_woken().
-	 */
-	smp_wmb(); /* C */
+	/* Pairs with the smp_store_mb() in wait_woken(). */
+	smp_mb(); /* C */
 	wq_entry->flags |= WQ_FLAG_WOKEN;
 
 	return default_wake_function(wq_entry, mode, sync, key);
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 53c2d5edc826..1d91e31eceec 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	int ret = 0;
+	long long val;
 
 	raw_spin_lock_irqsave(lock, flags);
-	if (v->counter != u) {
+	val = v->counter;
+	if (val != u)
 		v->counter += a;
-		ret = 1;
-	}
 	raw_spin_unlock_irqrestore(lock, flags);
-	return ret;
+
+	return val;
 }
-EXPORT_SYMBOL(atomic64_add_unless);
+EXPORT_SYMBOL(atomic64_fetch_add_unless);
diff --git a/lib/refcount.c b/lib/refcount.c
index d3b81cefce91..ebcf8cd49e05 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -35,13 +35,13 @@
  *
  */
 
+#include <linux/mutex.h>
 #include <linux/refcount.h>
+#include <linux/spinlock.h>
 #include <linux/bug.h>
 
-#ifdef CONFIG_REFCOUNT_FULL
-
 /**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * refcount_add_not_zero_checked - add a value to a refcount unless it is 0
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -58,7 +58,7 @@
  *
  * Return: false if the passed refcount is 0, true otherwise
  */
-bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -79,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_add_not_zero);
+EXPORT_SYMBOL(refcount_add_not_zero_checked);
 
 /**
- * refcount_add - add a value to a refcount
+ * refcount_add_checked - add a value to a refcount
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -97,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero);
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
  */
-void refcount_add(unsigned int i, refcount_t *r)
+void refcount_add_checked(unsigned int i, refcount_t *r)
 {
-	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_add);
+EXPORT_SYMBOL(refcount_add_checked);
 
 /**
- * refcount_inc_not_zero - increment a refcount unless it is 0
+ * refcount_inc_not_zero_checked - increment a refcount unless it is 0
  * @r: the refcount to increment
  *
  * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
@@ -115,7 +115,7 @@ EXPORT_SYMBOL(refcount_add);
  *
  * Return: true if the increment was successful, false otherwise
  */
-bool refcount_inc_not_zero(refcount_t *r)
+bool refcount_inc_not_zero_checked(refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -134,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_inc_not_zero);
+EXPORT_SYMBOL(refcount_inc_not_zero_checked);
 
 /**
- * refcount_inc - increment a refcount
+ * refcount_inc_checked - increment a refcount
  * @r: the refcount to increment
  *
  * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
@@ -148,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero);
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
-void refcount_inc(refcount_t *r)
+void refcount_inc_checked(refcount_t *r)
 {
-	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_inc);
+EXPORT_SYMBOL(refcount_inc_checked);
 
 /**
- * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0
  * @i: amount to subtract from the refcount
  * @r: the refcount
  *
@@ -174,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -192,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 
 	return !new;
 }
-EXPORT_SYMBOL(refcount_sub_and_test);
+EXPORT_SYMBOL(refcount_sub_and_test_checked);
 
 /**
- * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * refcount_dec_and_test_checked - decrement a refcount and test if it is 0
  * @r: the refcount
  *
  * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
@@ -207,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_dec_and_test(refcount_t *r)
+bool refcount_dec_and_test_checked(refcount_t *r)
 {
-	return refcount_sub_and_test(1, r);
+	return refcount_sub_and_test_checked(1, r);
 }
-EXPORT_SYMBOL(refcount_dec_and_test);
+EXPORT_SYMBOL(refcount_dec_and_test_checked);
 
 /**
- * refcount_dec - decrement a refcount
+ * refcount_dec_checked - decrement a refcount
  * @r: the refcount
  *
  * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
@@ -223,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test);
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-void refcount_dec(refcount_t *r)
+void refcount_dec_checked(refcount_t *r)
 {
-	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
-EXPORT_SYMBOL(refcount_dec);
-#endif /* CONFIG_REFCOUNT_FULL */
+EXPORT_SYMBOL(refcount_dec_checked);
 
 /**
  * refcount_dec_if_one - decrement a refcount if it is 1
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index af8c4b38b746..d84227d75717 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size)
 	 * the packet count limit, so...
 	 */
 	if (atm_may_send(pvcc->atmvcc, size) &&
-	    atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT))
+	    atomic_inc_not_zero(&pvcc->inflight))
 		return 1;
 
 	/*
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index f6734d8cb01a..9486293fef5c 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
 bool rxrpc_queue_call(struct rxrpc_call *call)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&call->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&call->processor))
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 4c77a78a252a..77440a356b14 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn)
 bool rxrpc_queue_conn(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&conn->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&conn->processor))
@@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
 	const void *here = __builtin_return_address(0);
 
 	if (conn) {
-		int n = __atomic_add_unless(&conn->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
 		else
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index b493e6b62740..777c3ed4cfc0 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 	const void *here = __builtin_return_address(0);
 
 	if (local) {
-		int n = __atomic_add_unless(&local->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
 		else
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 24ec7cdcf332..1dc7648e3eff 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
 	const void *here = __builtin_return_address(0);
 
 	if (peer) {
-		int n = __atomic_add_unless(&peer->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
 		else
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 1b09f3175a1f..0cbd1ef8f86d 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -804,7 +804,7 @@ type of fence:
 Second, some types of fence affect the way the memory subsystem
 propagates stores.  When a fence instruction is executed on CPU C:
 
-	For each other CPU C', smb_wmb() forces all po-earlier stores
+	For each other CPU C', smp_wmb() forces all po-earlier stores
 	on C to propagate to C' before any po-later stores do.
 
 	For each other CPU C', any store which propagates to C before
diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index ee4309a87fc4..af72700cc20a 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by
 locking will be seen as ordered by CPUs not holding that lock.
 Consider this example:
 
-	/* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+	/* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */
 	void CPU0(void)
 	{
 		spin_lock(&mylock);
@@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb().  However, the older
 smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
 to understand their use cases.  The general approach is shown below:
 
-	/* See MP+wmbonceonce+rmbonceonce.litmus. */
+	/* See MP+fencewmbonceonce+fencermbonceonce.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
@@ -322,9 +322,9 @@ the following write-side code fragment:
 And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
 the corresponding read-side code fragment:
 
-	cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+	cur_cycle = READ_ONCE(log->l_curr_cycle);
 	smp_rmb();
-	cur_block = ACCESS_ONCE(log->l_curr_block);
+	cur_block = READ_ONCE(log->l_curr_block);
 
 Alternatively, consider the following comment in function
 perf_output_put_handle() in kernel/events/ring_buffer.c:
@@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test.
 One way of avoiding the counter-intuitive outcome is through the use of a
 control dependency paired with a full memory barrier:
 
-	/* See LB+ctrlonceonce+mbonceonce.litmus. */
+	/* See LB+fencembonceonce+ctrlonceonce.litmus. */
 	void CPU0(void)
 	{
 		r0 = READ_ONCE(x);
@@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second,
 while another CPU stores to the second variable and then loads from the
 first.  Preserving order requires nothing less than full barriers:
 
-	/* See SB+mbonceonces.litmus. */
+	/* See SB+fencembonceonces.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 734f7feaa5dc..ee987ce20aae 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -35,13 +35,13 @@ BASIC USAGE: HERD7
 The memory model is used, in conjunction with "herd7", to exhaustively
 explore the state space of small litmus tests.
 
-For example, to run SB+mbonceonces.litmus against the memory model:
+For example, to run SB+fencembonceonces.litmus against the memory model:
 
-  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus
 
 Here is the corresponding output:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   States 3
   0:r0=0; 1:r0=1;
   0:r0=1; 1:r0=0;
@@ -50,8 +50,8 @@ Here is the corresponding output:
   Witnesses
   Positive: 0 Negative: 3
   Condition exists (0:r0=0 /\ 1:r0=0)
-  Observation SB+mbonceonces Never 0 3
-  Time SB+mbonceonces 0.01
+  Observation SB+fencembonceonces Never 0 3
+  Time SB+fencembonceonces 0.01
   Hash=d66d99523e2cac6b06e66f4c995ebb48
 
 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
@@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7
 The "klitmus7" tool converts a litmus test into a Linux kernel module,
 which may then be loaded and run.
 
-For example, to run SB+mbonceonces.litmus against hardware:
+For example, to run SB+fencembonceonces.litmus against hardware:
 
   $ mkdir mymodules
-  $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+  $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus
   $ cd mymodules ; make
   $ sudo sh run.sh
 
 The corresponding output includes:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   Histogram (3 states)
   644580  :>0:r0=1; 1:r0=0;
   644328  :>0:r0=0; 1:r0=1;
@@ -86,8 +86,8 @@ The corresponding output includes:
   Positive: 0, Negative: 2000000
   Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
   Hash=d66d99523e2cac6b06e66f4c995ebb48
-  Observation SB+mbonceonces Never 0 2000000
-  Time SB+mbonceonces 0.16
+  Observation SB+fencembonceonces Never 0 2000000
+  Time SB+fencembonceonces 0.16
 
 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
 that during two million trials, the state specified in this litmus
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 64f5740e0e75..b84fb2f67109 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -13,7 +13,7 @@
 
 "Linux-kernel memory consistency model"
 
-enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) ||
 		'release (*smp_store_release*) ||
 		'acquire (*smp_load_acquire*) ||
 		'noreturn (* R of non-return RMW *)
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
index 98a3716efa37..e729d2776e89 100644
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
@@ -1,4 +1,4 @@
-C IRIW+mbonceonces+OnceOnce
+C IRIW+fencembonceonces+OnceOnce
 
 (*
  * Result: Never
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 7a39a0aaa976..0f749e419b34 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -1,4 +1,4 @@
-C ISA2+pooncelock+pooncelock+pombonce.litmus
+C ISA2+pooncelock+pooncelock+pombonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
index de6708229dd1..4727f5aaf03b 100644
--- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
@@ -1,4 +1,4 @@
-C LB+ctrlonceonce+mbonceonce
+C LB+fencembonceonce+ctrlonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
index c078f38ff27a..a273da9faa6d 100644
--- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
@@ -1,4 +1,4 @@
-C MP+wmbonceonce+rmbonceonce
+C MP+fencewmbonceonce+fencermbonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
index a0e884ad2132..222a0b850b4a 100644
--- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C R+mbonceonces
+C R+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 17eb9a8c222d..4581ec2d3c57 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -18,7 +18,7 @@ CoWW+poonceonce.litmus
 	Test of write-write coherence, that is, whether or not two
 	successive writes to the same variable are ordered.
 
-IRIW+mbonceonces+OnceOnce.litmus
+IRIW+fencembonceonces+OnceOnce.litmus
 	Test of independent reads from independent writes with smp_mb()
 	between each pairs of reads.  In other words, is smp_mb()
 	sufficient to cause two different reading processes to agree on
@@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
 	Can a release-acquire chain order a prior store against
 	a later load?
 
-LB+ctrlonceonce+mbonceonce.litmus
+LB+fencembonceonce+ctrlonceonce.litmus
 	Does a control dependency and an smp_mb() suffice for the
 	load-buffering litmus test, where each process reads from one
 	of two variables then writes to the other?
@@ -88,14 +88,14 @@ MP+porevlocks.litmus
 	As below, but with the first access of the writer process
 	and the second access of reader process protected by a lock.
 
-MP+wmbonceonce+rmbonceonce.litmus
+MP+fencewmbonceonce+fencermbonceonce.litmus
 	Does a smp_wmb() (between the stores) and an smp_rmb() (between
 	the loads) suffice for the message-passing litmus test, where one
 	process writes data and then a flag, and the other process reads
 	the flag and then the data.  (This is similar to the ISA2 tests,
 	but with two processes instead of three.)
 
-R+mbonceonces.litmus
+R+fencembonceonces.litmus
 	This is the fully ordered (via smp_mb()) version of one of
 	the classic counterintuitive litmus tests that illustrates the
 	effects of store propagation delays.
@@ -103,7 +103,7 @@ R+mbonceonces.litmus
 R+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
-SB+mbonceonces.litmus
+SB+fencembonceonces.litmus
 	This is the fully ordered (again, via smp_mb() version of store
 	buffering, which forms the core of Dekker's mutual-exclusion
 	algorithm.
@@ -111,15 +111,24 @@ SB+mbonceonces.litmus
 SB+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
+SB+rfionceonce-poonceonces.litmus
+	This litmus test demonstrates that LKMM is not fully multicopy
+	atomic.  (Neither is it other multicopy atomic.)  This litmus test
+	also demonstrates the "locations" debugging aid, which designates
+	additional registers and locations to be printed out in the dump
+	of final states in the herd7 output.  Without the "locations"
+	statement, only those registers and locations mentioned in the
+	"exists" clause will be printed.
+
 S+poonceonces.litmus
 	As below, but without the smp_wmb() and acquire load.
 
-S+wmbonceonce+poacquireonce.litmus
+S+fencewmbonceonce+poacquireonce.litmus
 	Can a smp_wmb(), instead of a release, and an acquire order
 	a prior store against a subsequent store?
 
 WRC+poonceonces+Once.litmus
-WRC+pooncerelease+rmbonceonce+Once.litmus
+WRC+pooncerelease+fencermbonceonce+Once.litmus
 	These two are members of an extension of the MP litmus-test
 	class in which the first write is moved to a separate process.
 	The second is forbidden because smp_store_release() is
@@ -134,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus
 	As above, but with smp_mb__after_spinlock() immediately
 	following the spin_lock().
 
-Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
 	Is the ordering provided by a release-acquire chain sufficient
 	to make ordering apparent to accesses by a process that does
 	not participate in that release-acquire chain?
diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
index c53350205d28..18479823cd6c 100644
--- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
@@ -1,4 +1,4 @@
-C S+wmbonceonce+poacquireonce
+C S+fencewmbonceonce+poacquireonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
index 74b874ffa8da..ed5fff18d223 100644
--- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C SB+mbonceonces
+C SB+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
new file mode 100644
index 000000000000..04a16603660b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+rfionceonce-poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that LKMM is not fully multicopy atomic.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	int r1;
+	int r2;
+
+	WRITE_ONCE(*x, 1);
+	r1 = READ_ONCE(*x);
+	r2 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+	int r3;
+	int r4;
+
+	WRITE_ONCE(*y, 1);
+	r3 = READ_ONCE(*y);
+	r4 = READ_ONCE(*x);
+}
+
+locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *)
+exists (0:r2=0 /\ 1:r4=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
index ad3448b941e6..e9947250d7de 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
@@ -1,4 +1,4 @@
-C WRC+pooncerelease+rmbonceonce+Once
+C WRC+pooncerelease+fencermbonceonce+Once
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
index a20fc3fafb53..88e70b87a683 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
@@ -1,4 +1,4 @@
-C Z6.0+pooncerelease+poacquirerelease+mbonceonce
+C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
index af0aa15ab84e..ca528f9a24d4 100644..100755
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -9,7 +9,7 @@
 # appended.
 #
 # Usage:
-#	sh checkalllitmus.sh [ directory ]
+#	checkalllitmus.sh [ directory ]
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, whose default is defined by the checklitmus.sh script.
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
index e2e477472844..bf12a75c0719 100644..100755
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -8,7 +8,7 @@
 # with ".out" appended.
 #
 # Usage:
-#	sh checklitmus.sh file.litmus
+#	checklitmus.sh file.litmus
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,