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

Pull locking updates from Ingo Molnar:
 "The biggest part of this tree is the new auto-generated atomics API
  wrappers by Mark Rutland.

  The primary motivation was to allow instrumentation without uglifying
  the primary source code.

  The linecount increase comes from adding the auto-generated files to
  the Git space as well:

    include/asm-generic/atomic-instrumented.h     | 1689 ++++++++++++++++--
    include/asm-generic/atomic-long.h             | 1174 ++++++++++---
    include/linux/atomic-fallback.h               | 2295 +++++++++++++++++++++++++
    include/linux/atomic.h                        | 1241 +------------

  I preferred this approach, so that the full call stack of the (already
  complex) locking APIs is still fully visible in 'git grep'.

  But if this is excessive we could certainly hide them.

  There's a separate build-time mechanism to determine whether the
  headers are out of date (they should never be stale if we do our job
  right).

  Anyway, nothing from this should be visible to regular kernel
  developers.

  Other changes:

   - Add support for dynamic keys, which removes a source of false
     positives in the workqueue code, among other things (Bart Van
     Assche)

   - Updates to tools/memory-model (Andrea Parri, Paul E. McKenney)

   - qspinlock, wake_q and lockdep micro-optimizations (Waiman Long)

   - misc other updates and enhancements"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  locking/lockdep: Shrink struct lock_class_key
  locking/lockdep: Add module_param to enable consistency checks
  lockdep/lib/tests: Test dynamic key registration
  lockdep/lib/tests: Fix run_tests.sh
  kernel/workqueue: Use dynamic lockdep keys for workqueues
  locking/lockdep: Add support for dynamic keys
  locking/lockdep: Verify whether lock objects are small enough to be used as class keys
  locking/lockdep: Check data structure consistency
  locking/lockdep: Reuse lock chains that have been freed
  locking/lockdep: Fix a comment in add_chain_cache()
  locking/lockdep: Introduce lockdep_next_lockchain() and lock_chain_count()
  locking/lockdep: Reuse list entries that are no longer in use
  locking/lockdep: Free lock classes that are no longer in use
  locking/lockdep: Update two outdated comments
  locking/lockdep: Make it easy to detect whether or not inside a selftest
  locking/lockdep: Split lockdep_free_key_range() and lockdep_reset_lock()
  locking/lockdep: Initialize the locks_before and locks_after lists earlier
  locking/lockdep: Make zap_class() remove all matching lock order entries
  locking/lockdep: Reorder struct lock_class members
  locking/lockdep: Avoid that add_chain_cache() adds an invalid chain to the cache
  ...

6 files changed, 211 insertions, 190 deletions

diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 9bca54dda75c6..1f4e9ee641c92 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -42,124 +42,131 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)			READ_ONCE((v)->counter)
-#define atomic_set(v, i)		WRITE_ONCE(((v)->counter), (i))
-
-#define atomic_add_return_relaxed	atomic_add_return_relaxed
-#define atomic_add_return_acquire	atomic_add_return_acquire
-#define atomic_add_return_release	atomic_add_return_release
-#define atomic_add_return		atomic_add_return
-
-#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_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
-#define atomic_fetch_add		atomic_fetch_add
-
-#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
-#define atomic_fetch_sub_acquire	atomic_fetch_sub_acquire
-#define atomic_fetch_sub_release	atomic_fetch_sub_release
-#define atomic_fetch_sub		atomic_fetch_sub
-
-#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
-#define atomic_fetch_and_acquire	atomic_fetch_and_acquire
-#define atomic_fetch_and_release	atomic_fetch_and_release
-#define atomic_fetch_and		atomic_fetch_and
-
-#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
-#define atomic_fetch_andnot_acquire	atomic_fetch_andnot_acquire
-#define atomic_fetch_andnot_release	atomic_fetch_andnot_release
-#define atomic_fetch_andnot		atomic_fetch_andnot
-
-#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
-#define atomic_fetch_or_acquire		atomic_fetch_or_acquire
-#define atomic_fetch_or_release		atomic_fetch_or_release
-#define atomic_fetch_or			atomic_fetch_or
-
-#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
-#define atomic_fetch_xor_acquire	atomic_fetch_xor_acquire
-#define atomic_fetch_xor_release	atomic_fetch_xor_release
-#define atomic_fetch_xor		atomic_fetch_xor
-
-#define atomic_xchg_relaxed(v, new)	xchg_relaxed(&((v)->counter), (new))
-#define atomic_xchg_acquire(v, new)	xchg_acquire(&((v)->counter), (new))
-#define atomic_xchg_release(v, new)	xchg_release(&((v)->counter), (new))
-#define atomic_xchg(v, new)		xchg(&((v)->counter), (new))
-
-#define atomic_cmpxchg_relaxed(v, old, new)				\
-	cmpxchg_relaxed(&((v)->counter), (old), (new))
-#define atomic_cmpxchg_acquire(v, old, new)				\
-	cmpxchg_acquire(&((v)->counter), (old), (new))
-#define atomic_cmpxchg_release(v, old, new)				\
-	cmpxchg_release(&((v)->counter), (old), (new))
-#define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
-
-#define atomic_andnot			atomic_andnot
+#define arch_atomic_read(v)			READ_ONCE((v)->counter)
+#define arch_atomic_set(v, i)			WRITE_ONCE(((v)->counter), (i))
+
+#define arch_atomic_add_return_relaxed		arch_atomic_add_return_relaxed
+#define arch_atomic_add_return_acquire		arch_atomic_add_return_acquire
+#define arch_atomic_add_return_release		arch_atomic_add_return_release
+#define arch_atomic_add_return			arch_atomic_add_return
+
+#define arch_atomic_sub_return_relaxed		arch_atomic_sub_return_relaxed
+#define arch_atomic_sub_return_acquire		arch_atomic_sub_return_acquire
+#define arch_atomic_sub_return_release		arch_atomic_sub_return_release
+#define arch_atomic_sub_return			arch_atomic_sub_return
+
+#define arch_atomic_fetch_add_relaxed		arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_add_acquire		arch_atomic_fetch_add_acquire
+#define arch_atomic_fetch_add_release		arch_atomic_fetch_add_release
+#define arch_atomic_fetch_add			arch_atomic_fetch_add
+
+#define arch_atomic_fetch_sub_relaxed		arch_atomic_fetch_sub_relaxed
+#define arch_atomic_fetch_sub_acquire		arch_atomic_fetch_sub_acquire
+#define arch_atomic_fetch_sub_release		arch_atomic_fetch_sub_release
+#define arch_atomic_fetch_sub			arch_atomic_fetch_sub
+
+#define arch_atomic_fetch_and_relaxed		arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_and_acquire		arch_atomic_fetch_and_acquire
+#define arch_atomic_fetch_and_release		arch_atomic_fetch_and_release
+#define arch_atomic_fetch_and			arch_atomic_fetch_and
+
+#define arch_atomic_fetch_andnot_relaxed	arch_atomic_fetch_andnot_relaxed
+#define arch_atomic_fetch_andnot_acquire	arch_atomic_fetch_andnot_acquire
+#define arch_atomic_fetch_andnot_release	arch_atomic_fetch_andnot_release
+#define arch_atomic_fetch_andnot		arch_atomic_fetch_andnot
+
+#define arch_atomic_fetch_or_relaxed		arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_or_acquire		arch_atomic_fetch_or_acquire
+#define arch_atomic_fetch_or_release		arch_atomic_fetch_or_release
+#define arch_atomic_fetch_or			arch_atomic_fetch_or
+
+#define arch_atomic_fetch_xor_relaxed		arch_atomic_fetch_xor_relaxed
+#define arch_atomic_fetch_xor_acquire		arch_atomic_fetch_xor_acquire
+#define arch_atomic_fetch_xor_release		arch_atomic_fetch_xor_release
+#define arch_atomic_fetch_xor			arch_atomic_fetch_xor
+
+#define arch_atomic_xchg_relaxed(v, new) \
+	arch_xchg_relaxed(&((v)->counter), (new))
+#define arch_atomic_xchg_acquire(v, new) \
+	arch_xchg_acquire(&((v)->counter), (new))
+#define arch_atomic_xchg_release(v, new) \
+	arch_xchg_release(&((v)->counter), (new))
+#define arch_atomic_xchg(v, new) \
+	arch_xchg(&((v)->counter), (new))
+
+#define arch_atomic_cmpxchg_relaxed(v, old, new) \
+	arch_cmpxchg_relaxed(&((v)->counter), (old), (new))
+#define arch_atomic_cmpxchg_acquire(v, old, new) \
+	arch_cmpxchg_acquire(&((v)->counter), (old), (new))
+#define arch_atomic_cmpxchg_release(v, old, new) \
+	arch_cmpxchg_release(&((v)->counter), (old), (new))
+#define arch_atomic_cmpxchg(v, old, new) \
+	arch_cmpxchg(&((v)->counter), (old), (new))
+
+#define arch_atomic_andnot			arch_atomic_andnot
 
 /*
- * 64-bit atomic operations.
+ * 64-bit arch_atomic operations.
  */
-#define ATOMIC64_INIT			ATOMIC_INIT
-#define atomic64_read			atomic_read
-#define atomic64_set			atomic_set
-
-#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
-#define atomic64_add_return_acquire	atomic64_add_return_acquire
-#define atomic64_add_return_release	atomic64_add_return_release
-#define atomic64_add_return		atomic64_add_return
-
-#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_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
-#define atomic64_fetch_add		atomic64_fetch_add
-
-#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
-#define atomic64_fetch_sub_acquire	atomic64_fetch_sub_acquire
-#define atomic64_fetch_sub_release	atomic64_fetch_sub_release
-#define atomic64_fetch_sub		atomic64_fetch_sub
-
-#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
-#define atomic64_fetch_and_acquire	atomic64_fetch_and_acquire
-#define atomic64_fetch_and_release	atomic64_fetch_and_release
-#define atomic64_fetch_and		atomic64_fetch_and
-
-#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot_acquire
-#define atomic64_fetch_andnot_release	atomic64_fetch_andnot_release
-#define atomic64_fetch_andnot		atomic64_fetch_andnot
-
-#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
-#define atomic64_fetch_or_acquire	atomic64_fetch_or_acquire
-#define atomic64_fetch_or_release	atomic64_fetch_or_release
-#define atomic64_fetch_or		atomic64_fetch_or
-
-#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
-#define atomic64_fetch_xor_acquire	atomic64_fetch_xor_acquire
-#define atomic64_fetch_xor_release	atomic64_fetch_xor_release
-#define atomic64_fetch_xor		atomic64_fetch_xor
-
-#define atomic64_xchg_relaxed		atomic_xchg_relaxed
-#define atomic64_xchg_acquire		atomic_xchg_acquire
-#define atomic64_xchg_release		atomic_xchg_release
-#define atomic64_xchg			atomic_xchg
-
-#define atomic64_cmpxchg_relaxed	atomic_cmpxchg_relaxed
-#define atomic64_cmpxchg_acquire	atomic_cmpxchg_acquire
-#define atomic64_cmpxchg_release	atomic_cmpxchg_release
-#define atomic64_cmpxchg		atomic_cmpxchg
-
-#define atomic64_andnot			atomic64_andnot
-
-#define atomic64_dec_if_positive	atomic64_dec_if_positive
+#define ATOMIC64_INIT				ATOMIC_INIT
+#define arch_atomic64_read			arch_atomic_read
+#define arch_atomic64_set			arch_atomic_set
+
+#define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
+#define arch_atomic64_add_return_acquire	arch_atomic64_add_return_acquire
+#define arch_atomic64_add_return_release	arch_atomic64_add_return_release
+#define arch_atomic64_add_return		arch_atomic64_add_return
+
+#define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+#define arch_atomic64_sub_return_acquire	arch_atomic64_sub_return_acquire
+#define arch_atomic64_sub_return_release	arch_atomic64_sub_return_release
+#define arch_atomic64_sub_return		arch_atomic64_sub_return
+
+#define arch_atomic64_fetch_add_relaxed		arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_add_acquire		arch_atomic64_fetch_add_acquire
+#define arch_atomic64_fetch_add_release		arch_atomic64_fetch_add_release
+#define arch_atomic64_fetch_add			arch_atomic64_fetch_add
+
+#define arch_atomic64_fetch_sub_relaxed		arch_atomic64_fetch_sub_relaxed
+#define arch_atomic64_fetch_sub_acquire		arch_atomic64_fetch_sub_acquire
+#define arch_atomic64_fetch_sub_release		arch_atomic64_fetch_sub_release
+#define arch_atomic64_fetch_sub			arch_atomic64_fetch_sub
+
+#define arch_atomic64_fetch_and_relaxed		arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_and_acquire		arch_atomic64_fetch_and_acquire
+#define arch_atomic64_fetch_and_release		arch_atomic64_fetch_and_release
+#define arch_atomic64_fetch_and			arch_atomic64_fetch_and
+
+#define arch_atomic64_fetch_andnot_relaxed	arch_atomic64_fetch_andnot_relaxed
+#define arch_atomic64_fetch_andnot_acquire	arch_atomic64_fetch_andnot_acquire
+#define arch_atomic64_fetch_andnot_release	arch_atomic64_fetch_andnot_release
+#define arch_atomic64_fetch_andnot		arch_atomic64_fetch_andnot
+
+#define arch_atomic64_fetch_or_relaxed		arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_or_acquire		arch_atomic64_fetch_or_acquire
+#define arch_atomic64_fetch_or_release		arch_atomic64_fetch_or_release
+#define arch_atomic64_fetch_or			arch_atomic64_fetch_or
+
+#define arch_atomic64_fetch_xor_relaxed		arch_atomic64_fetch_xor_relaxed
+#define arch_atomic64_fetch_xor_acquire		arch_atomic64_fetch_xor_acquire
+#define arch_atomic64_fetch_xor_release		arch_atomic64_fetch_xor_release
+#define arch_atomic64_fetch_xor			arch_atomic64_fetch_xor
+
+#define arch_atomic64_xchg_relaxed		arch_atomic_xchg_relaxed
+#define arch_atomic64_xchg_acquire		arch_atomic_xchg_acquire
+#define arch_atomic64_xchg_release		arch_atomic_xchg_release
+#define arch_atomic64_xchg			arch_atomic_xchg
+
+#define arch_atomic64_cmpxchg_relaxed		arch_atomic_cmpxchg_relaxed
+#define arch_atomic64_cmpxchg_acquire		arch_atomic_cmpxchg_acquire
+#define arch_atomic64_cmpxchg_release		arch_atomic_cmpxchg_release
+#define arch_atomic64_cmpxchg			arch_atomic_cmpxchg
+
+#define arch_atomic64_andnot			arch_atomic64_andnot
+
+#define arch_atomic64_dec_if_positive		arch_atomic64_dec_if_positive
+
+#include <asm-generic/atomic-instrumented.h>
 
 #endif
 #endif
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index af7b990054536..e321293e0c895 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -39,7 +39,7 @@
 
 #define ATOMIC_OP(op, asm_op)						\
 __LL_SC_INLINE void							\
-__LL_SC_PREFIX(atomic_##op(int i, atomic_t *v))				\
+__LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v))			\
 {									\
 	unsigned long tmp;						\
 	int result;							\
@@ -53,11 +53,11 @@ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v))				\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: "Ir" (i));							\
 }									\
-__LL_SC_EXPORT(atomic_##op);
+__LL_SC_EXPORT(arch_atomic_##op);
 
 #define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
 __LL_SC_INLINE int							\
-__LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v))		\
+__LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v))	\
 {									\
 	unsigned long tmp;						\
 	int result;							\
@@ -75,11 +75,11 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v))		\
 									\
 	return result;							\
 }									\
-__LL_SC_EXPORT(atomic_##op##_return##name);
+__LL_SC_EXPORT(arch_atomic_##op##_return##name);
 
 #define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
 __LL_SC_INLINE int							\
-__LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v))		\
+__LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v))	\
 {									\
 	unsigned long tmp;						\
 	int val, result;						\
@@ -97,7 +97,7 @@ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v))		\
 									\
 	return result;							\
 }									\
-__LL_SC_EXPORT(atomic_fetch_##op##name);
+__LL_SC_EXPORT(arch_atomic_fetch_##op##name);
 
 #define ATOMIC_OPS(...)							\
 	ATOMIC_OP(__VA_ARGS__)						\
@@ -133,7 +133,7 @@ ATOMIC_OPS(xor, eor)
 
 #define ATOMIC64_OP(op, asm_op)						\
 __LL_SC_INLINE void							\
-__LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v))			\
+__LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v))		\
 {									\
 	long result;							\
 	unsigned long tmp;						\
@@ -147,11 +147,11 @@ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v))			\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: "Ir" (i));							\
 }									\
-__LL_SC_EXPORT(atomic64_##op);
+__LL_SC_EXPORT(arch_atomic64_##op);
 
 #define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
 __LL_SC_INLINE long							\
-__LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v))	\
+__LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\
 {									\
 	long result;							\
 	unsigned long tmp;						\
@@ -169,11 +169,11 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v))	\
 									\
 	return result;							\
 }									\
-__LL_SC_EXPORT(atomic64_##op##_return##name);
+__LL_SC_EXPORT(arch_atomic64_##op##_return##name);
 
 #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
 __LL_SC_INLINE long							\
-__LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v))	\
+__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(long i, atomic64_t *v))	\
 {									\
 	long result, val;						\
 	unsigned long tmp;						\
@@ -191,7 +191,7 @@ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v))	\
 									\
 	return result;							\
 }									\
-__LL_SC_EXPORT(atomic64_fetch_##op##name);
+__LL_SC_EXPORT(arch_atomic64_fetch_##op##name);
 
 #define ATOMIC64_OPS(...)						\
 	ATOMIC64_OP(__VA_ARGS__)					\
@@ -226,7 +226,7 @@ ATOMIC64_OPS(xor, eor)
 #undef ATOMIC64_OP
 
 __LL_SC_INLINE long
-__LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v))
+__LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v))
 {
 	long result;
 	unsigned long tmp;
@@ -246,7 +246,7 @@ __LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v))
 
 	return result;
 }
-__LL_SC_EXPORT(atomic64_dec_if_positive);
+__LL_SC_EXPORT(arch_atomic64_dec_if_positive);
 
 #define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl)		\
 __LL_SC_INLINE u##sz							\
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index a424355240c5b..9256a3921e4b2 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -25,9 +25,9 @@
 #error "please don't include this file directly"
 #endif
 
-#define __LL_SC_ATOMIC(op)	__LL_SC_CALL(atomic_##op)
+#define __LL_SC_ATOMIC(op)	__LL_SC_CALL(arch_atomic_##op)
 #define ATOMIC_OP(op, asm_op)						\
-static inline void atomic_##op(int i, atomic_t *v)			\
+static inline void arch_atomic_##op(int i, atomic_t *v)			\
 {									\
 	register int w0 asm ("w0") = i;					\
 	register atomic_t *x1 asm ("x1") = v;				\
@@ -47,7 +47,7 @@ ATOMIC_OP(add, stadd)
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...)			\
-static inline int atomic_fetch_##op##name(int i, atomic_t *v)		\
+static inline int arch_atomic_fetch_##op##name(int i, atomic_t *v)	\
 {									\
 	register int w0 asm ("w0") = i;					\
 	register atomic_t *x1 asm ("x1") = v;				\
@@ -79,7 +79,7 @@ ATOMIC_FETCH_OPS(add, ldadd)
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC_OP_ADD_RETURN(name, mb, cl...)				\
-static inline int atomic_add_return##name(int i, atomic_t *v)		\
+static inline int arch_atomic_add_return##name(int i, atomic_t *v)	\
 {									\
 	register int w0 asm ("w0") = i;					\
 	register atomic_t *x1 asm ("x1") = v;				\
@@ -105,7 +105,7 @@ ATOMIC_OP_ADD_RETURN(        , al, "memory")
 
 #undef ATOMIC_OP_ADD_RETURN
 
-static inline void atomic_and(int i, atomic_t *v)
+static inline void arch_atomic_and(int i, atomic_t *v)
 {
 	register int w0 asm ("w0") = i;
 	register atomic_t *x1 asm ("x1") = v;
@@ -123,7 +123,7 @@ static inline void atomic_and(int i, atomic_t *v)
 }
 
 #define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
-static inline int atomic_fetch_and##name(int i, atomic_t *v)		\
+static inline int arch_atomic_fetch_and##name(int i, atomic_t *v)	\
 {									\
 	register int w0 asm ("w0") = i;					\
 	register atomic_t *x1 asm ("x1") = v;				\
@@ -149,7 +149,7 @@ ATOMIC_FETCH_OP_AND(        , al, "memory")
 
 #undef ATOMIC_FETCH_OP_AND
 
-static inline void atomic_sub(int i, atomic_t *v)
+static inline void arch_atomic_sub(int i, atomic_t *v)
 {
 	register int w0 asm ("w0") = i;
 	register atomic_t *x1 asm ("x1") = v;
@@ -167,7 +167,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 }
 
 #define ATOMIC_OP_SUB_RETURN(name, mb, cl...)				\
-static inline int atomic_sub_return##name(int i, atomic_t *v)		\
+static inline int arch_atomic_sub_return##name(int i, atomic_t *v)	\
 {									\
 	register int w0 asm ("w0") = i;					\
 	register atomic_t *x1 asm ("x1") = v;				\
@@ -195,7 +195,7 @@ ATOMIC_OP_SUB_RETURN(        , al, "memory")
 #undef ATOMIC_OP_SUB_RETURN
 
 #define ATOMIC_FETCH_OP_SUB(name, mb, cl...)				\
-static inline int atomic_fetch_sub##name(int i, atomic_t *v)		\
+static inline int arch_atomic_fetch_sub##name(int i, atomic_t *v)	\
 {									\
 	register int w0 asm ("w0") = i;					\
 	register atomic_t *x1 asm ("x1") = v;				\
@@ -222,9 +222,9 @@ ATOMIC_FETCH_OP_SUB(        , al, "memory")
 #undef ATOMIC_FETCH_OP_SUB
 #undef __LL_SC_ATOMIC
 
-#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
+#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(arch_atomic64_##op)
 #define ATOMIC64_OP(op, asm_op)						\
-static inline void atomic64_##op(long i, atomic64_t *v)			\
+static inline void arch_atomic64_##op(long i, atomic64_t *v)		\
 {									\
 	register long x0 asm ("x0") = i;				\
 	register atomic64_t *x1 asm ("x1") = v;				\
@@ -244,7 +244,7 @@ ATOMIC64_OP(add, stadd)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
-static inline long atomic64_fetch_##op##name(long i, atomic64_t *v)	\
+static inline long arch_atomic64_fetch_##op##name(long i, atomic64_t *v)\
 {									\
 	register long x0 asm ("x0") = i;				\
 	register atomic64_t *x1 asm ("x1") = v;				\
@@ -276,7 +276,7 @@ ATOMIC64_FETCH_OPS(add, ldadd)
 #undef ATOMIC64_FETCH_OPS
 
 #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
-static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
+static inline long arch_atomic64_add_return##name(long i, atomic64_t *v)\
 {									\
 	register long x0 asm ("x0") = i;				\
 	register atomic64_t *x1 asm ("x1") = v;				\
@@ -302,7 +302,7 @@ ATOMIC64_OP_ADD_RETURN(        , al, "memory")
 
 #undef ATOMIC64_OP_ADD_RETURN
 
-static inline void atomic64_and(long i, atomic64_t *v)
+static inline void arch_atomic64_and(long i, atomic64_t *v)
 {
 	register long x0 asm ("x0") = i;
 	register atomic64_t *x1 asm ("x1") = v;
@@ -320,7 +320,7 @@ static inline void atomic64_and(long i, atomic64_t *v)
 }
 
 #define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
-static inline long atomic64_fetch_and##name(long i, atomic64_t *v)	\
+static inline long arch_atomic64_fetch_and##name(long i, atomic64_t *v)	\
 {									\
 	register long x0 asm ("x0") = i;				\
 	register atomic64_t *x1 asm ("x1") = v;				\
@@ -346,7 +346,7 @@ ATOMIC64_FETCH_OP_AND(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_AND
 
-static inline void atomic64_sub(long i, atomic64_t *v)
+static inline void arch_atomic64_sub(long i, atomic64_t *v)
 {
 	register long x0 asm ("x0") = i;
 	register atomic64_t *x1 asm ("x1") = v;
@@ -364,7 +364,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 }
 
 #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...)				\
-static inline long atomic64_sub_return##name(long i, atomic64_t *v)	\
+static inline long arch_atomic64_sub_return##name(long i, atomic64_t *v)\
 {									\
 	register long x0 asm ("x0") = i;				\
 	register atomic64_t *x1 asm ("x1") = v;				\
@@ -392,7 +392,7 @@ ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 #undef ATOMIC64_OP_SUB_RETURN
 
 #define ATOMIC64_FETCH_OP_SUB(name, mb, cl...)				\
-static inline long atomic64_fetch_sub##name(long i, atomic64_t *v)	\
+static inline long arch_atomic64_fetch_sub##name(long i, atomic64_t *v)	\
 {									\
 	register long x0 asm ("x0") = i;				\
 	register atomic64_t *x1 asm ("x1") = v;				\
@@ -418,7 +418,7 @@ ATOMIC64_FETCH_OP_SUB(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_SUB
 
-static inline long atomic64_dec_if_positive(atomic64_t *v)
+static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	register long x0 asm ("x0") = (long)v;
 
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 3f9376f1c409f..e6ea0f42e097b 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -110,10 +110,10 @@ __XCHG_GEN(_mb)
 })
 
 /* xchg */
-#define xchg_relaxed(...)	__xchg_wrapper(    , __VA_ARGS__)
-#define xchg_acquire(...)	__xchg_wrapper(_acq, __VA_ARGS__)
-#define xchg_release(...)	__xchg_wrapper(_rel, __VA_ARGS__)
-#define xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
+#define arch_xchg_relaxed(...)	__xchg_wrapper(    , __VA_ARGS__)
+#define arch_xchg_acquire(...)	__xchg_wrapper(_acq, __VA_ARGS__)
+#define arch_xchg_release(...)	__xchg_wrapper(_rel, __VA_ARGS__)
+#define arch_xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
 
 #define __CMPXCHG_GEN(sfx)						\
 static inline unsigned long __cmpxchg##sfx(volatile void *ptr,		\
@@ -154,18 +154,18 @@ __CMPXCHG_GEN(_mb)
 })
 
 /* cmpxchg */
-#define cmpxchg_relaxed(...)	__cmpxchg_wrapper(    , __VA_ARGS__)
-#define cmpxchg_acquire(...)	__cmpxchg_wrapper(_acq, __VA_ARGS__)
-#define cmpxchg_release(...)	__cmpxchg_wrapper(_rel, __VA_ARGS__)
-#define cmpxchg(...)		__cmpxchg_wrapper( _mb, __VA_ARGS__)
-#define cmpxchg_local		cmpxchg_relaxed
+#define arch_cmpxchg_relaxed(...)	__cmpxchg_wrapper(    , __VA_ARGS__)
+#define arch_cmpxchg_acquire(...)	__cmpxchg_wrapper(_acq, __VA_ARGS__)
+#define arch_cmpxchg_release(...)	__cmpxchg_wrapper(_rel, __VA_ARGS__)
+#define arch_cmpxchg(...)		__cmpxchg_wrapper( _mb, __VA_ARGS__)
+#define arch_cmpxchg_local		arch_cmpxchg_relaxed
 
 /* cmpxchg64 */
-#define cmpxchg64_relaxed	cmpxchg_relaxed
-#define cmpxchg64_acquire	cmpxchg_acquire
-#define cmpxchg64_release	cmpxchg_release
-#define cmpxchg64		cmpxchg
-#define cmpxchg64_local		cmpxchg_local
+#define arch_cmpxchg64_relaxed		arch_cmpxchg_relaxed
+#define arch_cmpxchg64_acquire		arch_cmpxchg_acquire
+#define arch_cmpxchg64_release		arch_cmpxchg_release
+#define arch_cmpxchg64			arch_cmpxchg
+#define arch_cmpxchg64_local		arch_cmpxchg_local
 
 /* cmpxchg_double */
 #define system_has_cmpxchg_double()     1
@@ -177,24 +177,24 @@ __CMPXCHG_GEN(_mb)
 	VM_BUG_ON((unsigned long *)(ptr2) - (unsigned long *)(ptr1) != 1);	\
 })
 
-#define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \
-({\
-	int __ret;\
-	__cmpxchg_double_check(ptr1, ptr2); \
-	__ret = !__cmpxchg_double_mb((unsigned long)(o1), (unsigned long)(o2), \
-				     (unsigned long)(n1), (unsigned long)(n2), \
-				     ptr1); \
-	__ret; \
+#define arch_cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2)				\
+({										\
+	int __ret;								\
+	__cmpxchg_double_check(ptr1, ptr2);					\
+	__ret = !__cmpxchg_double_mb((unsigned long)(o1), (unsigned long)(o2),	\
+				     (unsigned long)(n1), (unsigned long)(n2),	\
+				     ptr1);					\
+	__ret;									\
 })
 
-#define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \
-({\
-	int __ret;\
-	__cmpxchg_double_check(ptr1, ptr2); \
-	__ret = !__cmpxchg_double((unsigned long)(o1), (unsigned long)(o2), \
-				  (unsigned long)(n1), (unsigned long)(n2), \
-				  ptr1); \
-	__ret; \
+#define arch_cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2)			\
+({										\
+	int __ret;								\
+	__cmpxchg_double_check(ptr1, ptr2);					\
+	__ret = !__cmpxchg_double((unsigned long)(o1), (unsigned long)(o2),	\
+				  (unsigned long)(n1), (unsigned long)(n2),	\
+				  ptr1);					\
+	__ret;									\
 })
 
 #define __CMPWAIT_CASE(w, sfx, sz)					\
diff --git a/arch/arm64/include/asm/sync_bitops.h b/arch/arm64/include/asm/sync_bitops.h
index eee31a9f72a55..e9c1a02c21543 100644
--- a/arch/arm64/include/asm/sync_bitops.h
+++ b/arch/arm64/include/asm/sync_bitops.h
@@ -15,13 +15,13 @@
  * ops which are SMP safe even on a UP kernel.
  */
 
-#define sync_set_bit(nr, p)            set_bit(nr, p)
-#define sync_clear_bit(nr, p)          clear_bit(nr, p)
-#define sync_change_bit(nr, p)         change_bit(nr, p)
-#define sync_test_and_set_bit(nr, p)   test_and_set_bit(nr, p)
-#define sync_test_and_clear_bit(nr, p) test_and_clear_bit(nr, p)
-#define sync_test_and_change_bit(nr, p)        test_and_change_bit(nr, p)
-#define sync_test_bit(nr, addr)                test_bit(nr, addr)
-#define sync_cmpxchg                   cmpxchg
+#define sync_set_bit(nr, p)			set_bit(nr, p)
+#define sync_clear_bit(nr, p)			clear_bit(nr, p)
+#define sync_change_bit(nr, p)			change_bit(nr, p)
+#define sync_test_and_set_bit(nr, p)		test_and_set_bit(nr, p)
+#define sync_test_and_clear_bit(nr, p)		test_and_clear_bit(nr, p)
+#define sync_test_and_change_bit(nr, p)		test_and_change_bit(nr, p)
+#define sync_test_bit(nr, addr)			test_bit(nr, addr)
+#define arch_sync_cmpxchg			arch_cmpxchg
 
 #endif
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index dbaed55c1c244..232f856e0db06 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -67,16 +67,30 @@ static __always_inline void refcount_dec(refcount_t *r)
 static __always_inline __must_check
 bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 {
-	return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
+	bool ret = GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
 					 REFCOUNT_CHECK_LT_ZERO,
 					 r->refs.counter, e, "er", i, "cx");
+
+	if (ret) {
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	return false;
 }
 
 static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
-	return GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
-					REFCOUNT_CHECK_LT_ZERO,
-					r->refs.counter, e, "cx");
+	bool ret = GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
+					 REFCOUNT_CHECK_LT_ZERO,
+					 r->refs.counter, e, "cx");
+
+	if (ret) {
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	return false;
 }
 
 static __always_inline __must_check