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 main changes in the locking subsystem in this cycle were:

   - Add the Linux Kernel Memory Consistency Model (LKMM) subsystem,
     which is an an array of tools in tools/memory-model/ that formally
     describe the Linux memory coherency model (a.k.a.
     Documentation/memory-barriers.txt), and also produce 'litmus tests'
     in form of kernel code which can be directly executed and tested.

     Here's a high level background article about an earlier version of
     this work on LWN.net:

        https://lwn.net/Articles/718628/

     The design principles:

      "There is reason to believe that Documentation/memory-barriers.txt
       could use some help, and a major purpose of this patch is to
       provide that help in the form of a design-time tool that can
       produce all valid executions of a small fragment of concurrent
       Linux-kernel code, which is called a "litmus test". This tool's
       functionality is roughly similar to a full state-space search.
       Please note that this is a design-time tool, not useful for
       regression testing. However, we hope that the underlying
       Linux-kernel memory model will be incorporated into other tools
       capable of analyzing large bodies of code for regression-testing
       purposes."

     [...]

      "A second tool is klitmus7, which converts litmus tests to
       loadable kernel modules for direct testing. As with herd7, the
       klitmus7 code is freely available from

         http://diy.inria.fr/sources/index.html

       (and via "git" at https://github.com/herd/herdtools7)"

     [...]

     Credits go to:

      "This patch was the result of a most excellent collaboration
       founded by Jade Alglave and also including Alan Stern, Andrea
       Parri, and Luc Maranget."

     ... and to the gents listed in the MAINTAINERS entry:

        LINUX KERNEL MEMORY CONSISTENCY MODEL (LKMM)
        M:      Alan Stern <stern@rowland.harvard.edu>
        M:      Andrea Parri <parri.andrea@gmail.com>
        M:      Will Deacon <will.deacon@arm.com>
        M:      Peter Zijlstra <peterz@infradead.org>
        M:      Boqun Feng <boqun.feng@gmail.com>
        M:      Nicholas Piggin <npiggin@gmail.com>
        M:      David Howells <dhowells@redhat.com>
        M:      Jade Alglave <j.alglave@ucl.ac.uk>
        M:      Luc Maranget <luc.maranget@inria.fr>
        M:      "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

     The LKMM project already found several bugs in Linux locking
     primitives and improved the understanding and the documentation of
     the Linux memory model all around.

   - Add KASAN instrumentation to atomic APIs (Dmitry Vyukov)

   - Add RWSEM API debugging and reorganize the lock debugging Kconfig
     (Waiman Long)

   - ... misc cleanups and other smaller changes"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (31 commits)
  locking/Kconfig: Restructure the lock debugging menu
  locking/Kconfig: Add LOCK_DEBUGGING_SUPPORT to make it more readable
  locking/rwsem: Add DEBUG_RWSEMS to look for lock/unlock mismatches
  lockdep: Make the lock debug output more useful
  locking/rtmutex: Handle non enqueued waiters gracefully in remove_waiter()
  locking/atomic, asm-generic, x86: Add comments for atomic instrumentation
  locking/atomic, asm-generic: Add KASAN instrumentation to atomic operations
  locking/atomic/x86: Switch atomic.h to use atomic-instrumented.h
  locking/atomic, asm-generic: Add asm-generic/atomic-instrumented.h
  locking/xchg/alpha: Remove superfluous memory barriers from the _local() variants
  tools/memory-model: Finish the removal of rb-dep, smp_read_barrier_depends(), and lockless_dereference()
  tools/memory-model: Add documentation of new litmus test
  tools/memory-model: Remove mention of docker/gentoo image
  locking/memory-barriers: De-emphasize smp_read_barrier_depends() some more
  locking/lockdep: Show unadorned pointers
  mutex: Drop linkage.h from mutex.h
  tools/memory-model: Remove rb-dep, smp_read_barrier_depends, and lockless_dereference
  tools/memory-model: Convert underscores to hyphens
  tools/memory-model: Add a S lock-based external-view litmus test
  tools/memory-model: Add required herd7 version to README file
  ...

8 files changed, 192 insertions, 199 deletions

diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 8a2b331e43fe..6c7c39452471 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -38,19 +38,31 @@
 #define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
 #include <asm/xchg.h>
 
+/*
+ * The leading and the trailing memory barriers guarantee that these
+ * operations are fully ordered.
+ */
 #define xchg(ptr, x)							\
 ({									\
+	__typeof__(*(ptr)) __ret;					\
 	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
-				 sizeof(*(ptr)));			\
+	smp_mb();							\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg((ptr), (unsigned long)_x_, sizeof(*(ptr)));	\
+	smp_mb();							\
+	__ret;								\
 })
 
 #define cmpxchg(ptr, o, n)						\
 ({									\
+	__typeof__(*(ptr)) __ret;					\
 	__typeof__(*(ptr)) _o_ = (o);					\
 	__typeof__(*(ptr)) _n_ = (n);					\
-	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	\
-				    (unsigned long)_n_,	sizeof(*(ptr)));\
+	smp_mb();							\
+	__ret = (__typeof__(*(ptr))) __cmpxchg((ptr),			\
+		(unsigned long)_o_, (unsigned long)_n_, sizeof(*(ptr)));\
+	smp_mb();							\
+	__ret;								\
 })
 
 #define cmpxchg64(ptr, o, n)						\
diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h
index e2b59fac5257..7adb80c6746a 100644
--- a/arch/alpha/include/asm/xchg.h
+++ b/arch/alpha/include/asm/xchg.h
@@ -12,10 +12,6 @@
  * Atomic exchange.
  * Since it can be used to implement critical sections
  * it must clobber "memory" (also for interrupts in UP).
- *
- * The leading and the trailing memory barriers guarantee that these
- * operations are fully ordered.
- *
  */
 
 static inline unsigned long
@@ -23,7 +19,6 @@ ____xchg(_u8, volatile char *m, unsigned long val)
 {
 	unsigned long ret, tmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%4,7,%3\n"
 	"	insbl	%1,%4,%1\n"
@@ -38,7 +33,6 @@ ____xchg(_u8, volatile char *m, unsigned long val)
 	".previous"
 	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
 	: "r" ((long)m), "1" (val) : "memory");
-	smp_mb();
 
 	return ret;
 }
@@ -48,7 +42,6 @@ ____xchg(_u16, volatile short *m, unsigned long val)
 {
 	unsigned long ret, tmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%4,7,%3\n"
 	"	inswl	%1,%4,%1\n"
@@ -63,7 +56,6 @@ ____xchg(_u16, volatile short *m, unsigned long val)
 	".previous"
 	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
 	: "r" ((long)m), "1" (val) : "memory");
-	smp_mb();
 
 	return ret;
 }
@@ -73,7 +65,6 @@ ____xchg(_u32, volatile int *m, unsigned long val)
 {
 	unsigned long dummy;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldl_l %0,%4\n"
 	"	bis $31,%3,%1\n"
@@ -84,7 +75,6 @@ ____xchg(_u32, volatile int *m, unsigned long val)
 	".previous"
 	: "=&r" (val), "=&r" (dummy), "=m" (*m)
 	: "rI" (val), "m" (*m) : "memory");
-	smp_mb();
 
 	return val;
 }
@@ -94,7 +84,6 @@ ____xchg(_u64, volatile long *m, unsigned long val)
 {
 	unsigned long dummy;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l %0,%4\n"
 	"	bis $31,%3,%1\n"
@@ -105,7 +94,6 @@ ____xchg(_u64, volatile long *m, unsigned long val)
 	".previous"
 	: "=&r" (val), "=&r" (dummy), "=m" (*m)
 	: "rI" (val), "m" (*m) : "memory");
-	smp_mb();
 
 	return val;
 }
@@ -135,13 +123,6 @@ ____xchg(, volatile void *ptr, unsigned long x, int size)
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
- *
- * The leading and the trailing memory barriers guarantee that these
- * operations are fully ordered.
- *
- * The trailing memory barrier is placed in SMP unconditionally, in
- * order to guarantee that dependency ordering is preserved when a
- * dependency is headed by an unsuccessful operation.
  */
 
 static inline unsigned long
@@ -149,7 +130,6 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new)
 {
 	unsigned long prev, tmp, cmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%5,7,%4\n"
 	"	insbl	%1,%5,%1\n"
@@ -167,7 +147,6 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new)
 	".previous"
 	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
 	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
-	smp_mb();
 
 	return prev;
 }
@@ -177,7 +156,6 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new)
 {
 	unsigned long prev, tmp, cmp, addr64;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%5,7,%4\n"
 	"	inswl	%1,%5,%1\n"
@@ -195,7 +173,6 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new)
 	".previous"
 	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
 	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
-	smp_mb();
 
 	return prev;
 }
@@ -205,7 +182,6 @@ ____cmpxchg(_u32, volatile int *m, int old, int new)
 {
 	unsigned long prev, cmp;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldl_l %0,%5\n"
 	"	cmpeq %0,%3,%1\n"
@@ -219,7 +195,6 @@ ____cmpxchg(_u32, volatile int *m, int old, int new)
 	".previous"
 	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
 	: "r"((long) old), "r"(new), "m"(*m) : "memory");
-	smp_mb();
 
 	return prev;
 }
@@ -229,7 +204,6 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new)
 {
 	unsigned long prev, cmp;
 
-	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l %0,%5\n"
 	"	cmpeq %0,%3,%1\n"
@@ -243,7 +217,6 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new)
 	".previous"
 	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
 	: "r"((long) old), "r"(new), "m"(*m) : "memory");
-	smp_mb();
 
 	return prev;
 }
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 72759f131cc5..0db6bec95489 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -17,36 +17,40 @@
 #define ATOMIC_INIT(i)	{ (i) }
 
 /**
- * atomic_read - read atomic variable
+ * arch_atomic_read - read atomic variable
  * @v: pointer of type atomic_t
  *
  * Atomically reads the value of @v.
  */
-static __always_inline int atomic_read(const atomic_t *v)
+static __always_inline int arch_atomic_read(const atomic_t *v)
 {
+	/*
+	 * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here,
+	 * it's non-inlined function that increases binary size and stack usage.
+	 */
 	return READ_ONCE((v)->counter);
 }
 
 /**
- * atomic_set - set atomic variable
+ * arch_atomic_set - set atomic variable
  * @v: pointer of type atomic_t
  * @i: required value
  *
  * Atomically sets the value of @v to @i.
  */
-static __always_inline void atomic_set(atomic_t *v, int i)
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
 {
 	WRITE_ONCE(v->counter, i);
 }
 
 /**
- * atomic_add - add integer to atomic variable
+ * arch_atomic_add - add integer to atomic variable
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *
  * Atomically adds @i to @v.
  */
-static __always_inline void atomic_add(int i, atomic_t *v)
+static __always_inline void arch_atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
@@ -54,13 +58,13 @@ static __always_inline void atomic_add(int i, atomic_t *v)
 }
 
 /**
- * atomic_sub - subtract integer from atomic variable
+ * arch_atomic_sub - subtract integer from atomic variable
  * @i: integer value to subtract
  * @v: pointer of type atomic_t
  *
  * Atomically subtracts @i from @v.
  */
-static __always_inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
@@ -68,7 +72,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
 }
 
 /**
- * atomic_sub_and_test - subtract value from variable and test result
+ * arch_atomic_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer of type atomic_t
  *
@@ -76,63 +80,63 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
+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);
 }
 
 /**
- * atomic_inc - increment atomic variable
+ * arch_atomic_inc - increment atomic variable
  * @v: pointer of type atomic_t
  *
  * Atomically increments @v by 1.
  */
-static __always_inline void atomic_inc(atomic_t *v)
+static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter));
 }
 
 /**
- * atomic_dec - decrement atomic variable
+ * arch_atomic_dec - decrement atomic variable
  * @v: pointer of type atomic_t
  *
  * Atomically decrements @v by 1.
  */
-static __always_inline void atomic_dec(atomic_t *v)
+static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter));
 }
 
 /**
- * atomic_dec_and_test - decrement and test
+ * arch_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.
  */
-static __always_inline bool atomic_dec_and_test(atomic_t *v)
+static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
 }
 
 /**
- * atomic_inc_and_test - increment and test
+ * arch_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.
  */
-static __always_inline bool atomic_inc_and_test(atomic_t *v)
+static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
 }
 
 /**
- * atomic_add_negative - add and test if negative
+ * arch_atomic_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *
@@ -140,65 +144,65 @@ static __always_inline bool atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static __always_inline bool atomic_add_negative(int i, atomic_t *v)
+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);
 }
 
 /**
- * atomic_add_return - add integer and return
+ * arch_atomic_add_return - add integer and return
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static __always_inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 
 /**
- * atomic_sub_return - subtract integer and return
+ * arch_atomic_sub_return - subtract integer and return
  * @v: pointer of type atomic_t
  * @i: integer value to subtract
  *
  * Atomically subtracts @i from @v and returns @v - @i
  */
-static __always_inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 {
-	return atomic_add_return(-i, v);
+	return arch_atomic_add_return(-i, v);
 }
 
-#define atomic_inc_return(v)  (atomic_add_return(1, v))
-#define atomic_dec_return(v)  (atomic_sub_return(1, 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 atomic_fetch_add(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
 }
 
-static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
 {
 	return xadd(&v->counter, -i);
 }
 
-static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 {
-	return cmpxchg(&v->counter, old, new);
+	return arch_cmpxchg(&v->counter, old, new);
 }
 
-#define atomic_try_cmpxchg atomic_try_cmpxchg
-static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
+static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
 
-static inline int atomic_xchg(atomic_t *v, int new)
+static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
 	return xchg(&v->counter, new);
 }
 
-static inline void atomic_and(int i, atomic_t *v)
+static inline void arch_atomic_and(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "andl %1,%0"
 			: "+m" (v->counter)
@@ -206,16 +210,16 @@ static inline void atomic_and(int i, atomic_t *v)
 			: "memory");
 }
 
-static inline int atomic_fetch_and(int i, atomic_t *v)
+static inline int arch_atomic_fetch_and(int i, atomic_t *v)
 {
-	int val = atomic_read(v);
+	int val = arch_atomic_read(v);
 
-	do { } while (!atomic_try_cmpxchg(v, &val, val & i));
+	do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i));
 
 	return val;
 }
 
-static inline void atomic_or(int i, atomic_t *v)
+static inline void arch_atomic_or(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "orl %1,%0"
 			: "+m" (v->counter)
@@ -223,16 +227,16 @@ static inline void atomic_or(int i, atomic_t *v)
 			: "memory");
 }
 
-static inline int atomic_fetch_or(int i, atomic_t *v)
+static inline int arch_atomic_fetch_or(int i, atomic_t *v)
 {
-	int val = atomic_read(v);
+	int val = arch_atomic_read(v);
 
-	do { } while (!atomic_try_cmpxchg(v, &val, val | i));
+	do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i));
 
 	return val;
 }
 
-static inline void atomic_xor(int i, atomic_t *v)
+static inline void arch_atomic_xor(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorl %1,%0"
 			: "+m" (v->counter)
@@ -240,17 +244,17 @@ static inline void atomic_xor(int i, atomic_t *v)
 			: "memory");
 }
 
-static inline int atomic_fetch_xor(int i, atomic_t *v)
+static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 {
-	int val = atomic_read(v);
+	int val = arch_atomic_read(v);
 
-	do { } while (!atomic_try_cmpxchg(v, &val, val ^ i));
+	do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i));
 
 	return val;
 }
 
 /**
- * __atomic_add_unless - add unless the number is already a given value
+ * __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.
@@ -258,14 +262,14 @@ static inline int atomic_fetch_xor(int i, atomic_t *v)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns the old value of @v.
  */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
 {
-	int c = atomic_read(v);
+	int c = arch_atomic_read(v);
 
 	do {
 		if (unlikely(c == u))
 			break;
-	} while (!atomic_try_cmpxchg(v, &c, c + a));
+	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
 
 	return c;
 }
@@ -276,4 +280,6 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 # include <asm/atomic64_64.h>
 #endif
 
+#include <asm-generic/atomic-instrumented.h>
+
 #endif /* _ASM_X86_ATOMIC_H */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 97c46b8169b7..46e1ef17d92d 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -62,7 +62,7 @@ ATOMIC64_DECL(add_unless);
 #undef ATOMIC64_EXPORT
 
 /**
- * atomic64_cmpxchg - cmpxchg atomic64 variable
+ * arch_atomic64_cmpxchg - cmpxchg atomic64 variable
  * @v: pointer to type atomic64_t
  * @o: expected value
  * @n: new value
@@ -71,20 +71,21 @@ ATOMIC64_DECL(add_unless);
  * the old value.
  */
 
-static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o,
+					      long long n)
 {
-	return cmpxchg64(&v->counter, o, n);
+	return arch_cmpxchg64(&v->counter, o, n);
 }
 
 /**
- * atomic64_xchg - xchg atomic64 variable
+ * arch_atomic64_xchg - xchg atomic64 variable
  * @v: pointer to type atomic64_t
  * @n: value to assign
  *
  * Atomically xchgs the value of @v to @n and returns
  * the old value.
  */
-static inline long long atomic64_xchg(atomic64_t *v, long long n)
+static inline long long arch_atomic64_xchg(atomic64_t *v, long long n)
 {
 	long long o;
 	unsigned high = (unsigned)(n >> 32);
@@ -96,13 +97,13 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n)
 }
 
 /**
- * atomic64_set - set atomic64 variable
+ * arch_atomic64_set - set atomic64 variable
  * @v: pointer to type atomic64_t
  * @i: value to assign
  *
  * Atomically sets the value of @v to @n.
  */
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void arch_atomic64_set(atomic64_t *v, long long i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
@@ -112,12 +113,12 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 }
 
 /**
- * atomic64_read - read atomic64 variable
+ * arch_atomic64_read - read atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically reads the value of @v and returns it.
  */
-static inline long long atomic64_read(const atomic64_t *v)
+static inline long long arch_atomic64_read(const atomic64_t *v)
 {
 	long long r;
 	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
@@ -125,13 +126,13 @@ static inline long long atomic64_read(const atomic64_t *v)
  }
 
 /**
- * atomic64_add_return - add and return
+ * arch_atomic64_add_return - add and return
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v and returns @i + *@v
  */
-static inline long long atomic64_add_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -142,7 +143,7 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
 /*
  * Other variants with different arithmetic operators:
  */
-static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -150,7 +151,7 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 	return i;
 }
 
-static inline long long atomic64_inc_return(atomic64_t *v)
+static inline long long arch_atomic64_inc_return(atomic64_t *v)
 {
 	long long a;
 	alternative_atomic64(inc_return, "=&A" (a),
@@ -158,7 +159,7 @@ static inline long long atomic64_inc_return(atomic64_t *v)
 	return a;
 }
 
-static inline long long atomic64_dec_return(atomic64_t *v)
+static inline long long arch_atomic64_dec_return(atomic64_t *v)
 {
 	long long a;
 	alternative_atomic64(dec_return, "=&A" (a),
@@ -167,13 +168,13 @@ static inline long long atomic64_dec_return(atomic64_t *v)
 }
 
 /**
- * atomic64_add - add integer to atomic64 variable
+ * arch_atomic64_add - add integer to atomic64 variable
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v.
  */
-static inline long long atomic64_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_add(long long i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -182,13 +183,13 @@ static inline long long atomic64_add(long long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub - subtract the atomic64 variable
+ * arch_atomic64_sub - subtract the atomic64 variable
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
  * Atomically subtracts @i from @v.
  */
-static inline long long atomic64_sub(long long i, atomic64_t *v)
+static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -197,7 +198,7 @@ static inline long long atomic64_sub(long long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub_and_test - subtract value from variable and test result
+ * arch_atomic64_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
@@ -205,46 +206,46 @@ static inline long long atomic64_sub(long long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
+static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
 {
-	return atomic64_sub_return(i, v) == 0;
+	return arch_atomic64_sub_return(i, v) == 0;
 }
 
 /**
- * atomic64_inc - increment atomic64 variable
+ * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic64_inc(atomic64_t *v)
+static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
 /**
- * atomic64_dec - decrement atomic64 variable
+ * arch_atomic64_dec - decrement atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic64_dec(atomic64_t *v)
+static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
 /**
- * atomic64_dec_and_test - decrement and test
+ * 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 atomic64_dec_and_test(atomic64_t *v)
+static inline int arch_atomic64_dec_and_test(atomic64_t *v)
 {
-	return atomic64_dec_return(v) == 0;
+	return arch_atomic64_dec_return(v) == 0;
 }
 
 /**
@@ -255,13 +256,13 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_inc_and_test(atomic64_t *v)
+static inline int arch_atomic64_inc_and_test(atomic64_t *v)
 {
-	return atomic64_inc_return(v) == 0;
+	return arch_atomic64_inc_return(v) == 0;
 }
 
 /**
- * atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
@@ -269,13 +270,13 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic64_add_negative(long long i, atomic64_t *v)
+static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
 {
-	return atomic64_add_return(i, v) < 0;
+	return arch_atomic64_add_return(i, v) < 0;
 }
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * 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.
@@ -283,7 +284,8 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns non-zero if the add was done, zero otherwise.
  */
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
+					   long long u)
 {
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
@@ -294,7 +296,7 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 }
 
 
-static inline int atomic64_inc_not_zero(atomic64_t *v)
+static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
 	alternative_atomic64(inc_not_zero, "=&a" (r),
@@ -302,7 +304,7 @@ static inline int atomic64_inc_not_zero(atomic64_t *v)
 	return r;
 }
 
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
 	alternative_atomic64(dec_if_positive, "=&A" (r),
@@ -313,70 +315,70 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
-static inline void atomic64_and(long long i, atomic64_t *v)
+static inline void arch_atomic64_and(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
 		c = old;
 }
 
-static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
 		c = old;
 
 	return old;
 }
 
-static inline void atomic64_or(long long i, atomic64_t *v)
+static inline void arch_atomic64_or(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
 		c = old;
 }
 
-static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
 		c = old;
 
 	return old;
 }
 
-static inline void atomic64_xor(long long i, atomic64_t *v)
+static inline void arch_atomic64_xor(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
 		c = old;
 }
 
-static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
 		c = old;
 
 	return old;
 }
 
-static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v)
 {
 	long long old, c = 0;
 
-	while ((old = atomic64_cmpxchg(v, c, c + i)) != c)
+	while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
 		c = old;
 
 	return old;
 }
 
-#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
+#define arch_atomic64_fetch_sub(i, v)	arch_atomic64_fetch_add(-(i), (v))
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 738495caf05f..6106b59d3260 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -11,37 +11,37 @@
 #define ATOMIC64_INIT(i)	{ (i) }
 
 /**
- * atomic64_read - read atomic64 variable
+ * arch_atomic64_read - read atomic64 variable
  * @v: pointer of type atomic64_t
  *
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-static inline long atomic64_read(const atomic64_t *v)
+static inline long arch_atomic64_read(const atomic64_t *v)
 {
 	return READ_ONCE((v)->counter);
 }
 
 /**
- * atomic64_set - set atomic64 variable
+ * arch_atomic64_set - set atomic64 variable
  * @v: pointer to type atomic64_t
  * @i: required value
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void atomic64_set(atomic64_t *v, long i)
+static inline void arch_atomic64_set(atomic64_t *v, long i)
 {
 	WRITE_ONCE(v->counter, i);
 }
 
 /**
- * atomic64_add - add integer to atomic64 variable
+ * arch_atomic64_add - add integer to atomic64 variable
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v.
  */
-static __always_inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
@@ -49,13 +49,13 @@ static __always_inline void atomic64_add(long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub - subtract the atomic64 variable
+ * arch_atomic64_sub - subtract the atomic64 variable
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
  * Atomically subtracts @i from @v.
  */
-static inline void atomic64_sub(long i, atomic64_t *v)
+static inline void arch_atomic64_sub(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
@@ -63,7 +63,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 }
 
 /**
- * atomic64_sub_and_test - subtract value from variable and test result
+ * arch_atomic64_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer to type atomic64_t
  *
@@ -71,18 +71,18 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
+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);
 }
 
 /**
- * atomic64_inc - increment atomic64 variable
+ * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
-static __always_inline void atomic64_inc(atomic64_t *v)
+static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
@@ -90,12 +90,12 @@ static __always_inline void atomic64_inc(atomic64_t *v)
 }
 
 /**
- * atomic64_dec - decrement atomic64 variable
+ * arch_atomic64_dec - decrement atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically decrements @v by 1.
  */
-static __always_inline void atomic64_dec(atomic64_t *v)
+static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
@@ -103,33 +103,33 @@ static __always_inline void atomic64_dec(atomic64_t *v)
 }
 
 /**
- * atomic64_dec_and_test - decrement and test
+ * 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 bool atomic64_dec_and_test(atomic64_t *v)
+static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
 }
 
 /**
- * atomic64_inc_and_test - increment and test
+ * arch_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 bool atomic64_inc_and_test(atomic64_t *v)
+static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
 }
 
 /**
- * atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
@@ -137,59 +137,59 @@ static inline bool atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline bool atomic64_add_negative(long i, atomic64_t *v)
+static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
 
 /**
- * atomic64_add_return - add and return
+ * arch_atomic64_add_return - add and return
  * @i: integer value to add
  * @v: pointer to type atomic64_t
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static __always_inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long arch_atomic64_add_return(long i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 
-static inline long atomic64_sub_return(long i, atomic64_t *v)
+static inline long arch_atomic64_sub_return(long i, atomic64_t *v)
 {
-	return atomic64_add_return(-i, v);
+	return arch_atomic64_add_return(-i, v);
 }
 
-static inline long atomic64_fetch_add(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_add(long i, atomic64_t *v)
 {
 	return xadd(&v->counter, i);
 }
 
-static inline long atomic64_fetch_sub(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
 {
 	return xadd(&v->counter, -i);
 }
 
-#define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
-#define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
+#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 atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
 {
-	return cmpxchg(&v->counter, old, new);
+	return arch_cmpxchg(&v->counter, old, new);
 }
 
-#define atomic64_try_cmpxchg atomic64_try_cmpxchg
-static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
 
-static inline long atomic64_xchg(atomic64_t *v, long new)
+static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 {
 	return xchg(&v->counter, new);
 }
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * 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.
@@ -197,37 +197,37 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
+static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
 {
-	s64 c = atomic64_read(v);
+	s64 c = arch_atomic64_read(v);
 	do {
 		if (unlikely(c == u))
 			return false;
-	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
 	return true;
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
 
 /*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * 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 atomic64_dec_if_positive(atomic64_t *v)
+static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
-	s64 dec, c = atomic64_read(v);
+	s64 dec, c = arch_atomic64_read(v);
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-	} while (!atomic64_try_cmpxchg(v, &c, dec));
+	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
 	return dec;
 }
 
-static inline void atomic64_and(long i, atomic64_t *v)
+static inline void arch_atomic64_and(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "andq %1,%0"
 			: "+m" (v->counter)
@@ -235,16 +235,16 @@ static inline void atomic64_and(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long atomic64_fetch_and(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_and(long i, atomic64_t *v)
 {
-	s64 val = atomic64_read(v);
+	s64 val = arch_atomic64_read(v);
 
 	do {
-	} while (!atomic64_try_cmpxchg(v, &val, val & i));
+	} while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 	return val;
 }
 
-static inline void atomic64_or(long i, atomic64_t *v)
+static inline void arch_atomic64_or(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "orq %1,%0"
 			: "+m" (v->counter)
@@ -252,16 +252,16 @@ static inline void atomic64_or(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long atomic64_fetch_or(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_or(long i, atomic64_t *v)
 {
-	s64 val = atomic64_read(v);
+	s64 val = arch_atomic64_read(v);
 
 	do {
-	} while (!atomic64_try_cmpxchg(v, &val, val | i));
+	} while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 	return val;
 }
 
-static inline void atomic64_xor(long i, atomic64_t *v)
+static inline void arch_atomic64_xor(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorq %1,%0"
 			: "+m" (v->counter)
@@ -269,12 +269,12 @@ static inline void atomic64_xor(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long atomic64_fetch_xor(long i, atomic64_t *v)
+static inline long arch_atomic64_fetch_xor(long i, atomic64_t *v)
 {
-	s64 val = atomic64_read(v);
+	s64 val = arch_atomic64_read(v);
 
 	do {
-	} while (!atomic64_try_cmpxchg(v, &val, val ^ i));
+	} while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 	return val;
 }
 
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 56bd436ed01b..e3efd8a06066 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
 # include <asm/cmpxchg_64.h>
 #endif
 
-#define cmpxchg(ptr, old, new)						\
+#define arch_cmpxchg(ptr, old, new)					\
 	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
-#define sync_cmpxchg(ptr, old, new)					\
+#define arch_sync_cmpxchg(ptr, old, new)				\
 	__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
-#define cmpxchg_local(ptr, old, new)					\
+#define arch_cmpxchg_local(ptr, old, new)				\
 	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 
 
@@ -221,7 +221,7 @@ extern void __add_wrong_size(void)
 #define __try_cmpxchg(ptr, pold, new, size)				\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
-#define try_cmpxchg(ptr, pold, new)					\
+#define try_cmpxchg(ptr, pold, new) 					\
 	__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
 
 /*
@@ -250,10 +250,10 @@ extern void __add_wrong_size(void)
 	__ret;								\
 })
 
-#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \
+#define arch_cmpxchg_double(p1, p2, o1, o2, n1, n2) \
 	__cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2)
 
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
+#define arch_cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
 	__cmpxchg_double(, p1, p2, o1, o2, n1, n2)
 
 #endif	/* ASM_X86_CMPXCHG_H */
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 1732704f0445..1a2eafca7038 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -36,10 +36,10 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 }
 
 #ifdef CONFIG_X86_CMPXCHG64
-#define cmpxchg64(ptr, o, n)						\
+#define arch_cmpxchg64(ptr, o, n)					\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
 					 (unsigned long long)(n)))
-#define cmpxchg64_local(ptr, o, n)					\
+#define arch_cmpxchg64_local(ptr, o, n)					\
 	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
 					       (unsigned long long)(n)))
 #endif
@@ -76,7 +76,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
  * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
  */
 
-#define cmpxchg64(ptr, o, n)					\
+#define arch_cmpxchg64(ptr, o, n)				\
 ({								\
 	__typeof__(*(ptr)) __ret;				\
 	__typeof__(*(ptr)) __old = (o);				\
@@ -93,7 +93,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
 	__ret; })
 
 
-#define cmpxchg64_local(ptr, o, n)				\
+#define arch_cmpxchg64_local(ptr, o, n)				\
 ({								\
 	__typeof__(*(ptr)) __ret;				\
 	__typeof__(*(ptr)) __old = (o);				\
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 03cad196a301..bfca3b346c74 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -7,13 +7,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 	*ptr = val;
 }
 
-#define cmpxchg64(ptr, o, n)						\
+#define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg((ptr), (o), (n));					\
 })
 
-#define cmpxchg64_local(ptr, o, n)					\
+#define arch_cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg_local((ptr), (o), (n));					\