arch,x86: Convert smp_mb__*()

x86 is strongly ordered and all its atomic ops imply a full barrier.

Implement the two new primitives as the old ones were.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/n/tip-knswsr5mldkr0w1lrdxvc81w@git.kernel.org
Cc: Dave Jones <davej@redhat.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/atomic.h

@@ -7,6 +7,7 @@
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/rmwcc.h>
+#include <asm/barrier.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -243,12 +244,6 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
 		     : : "r" ((unsigned)(mask)), "m" (*(addr))	\
 		     : "memory")
 
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else

arch/x86/include/asm/barrier.h

@@ -137,6 +137,10 @@ do {									\
 
 #endif
 
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic()	barrier()
+#define smp_mb__after_atomic()	barrier()
+
 /*
  * Stop RDTSC speculation. This is needed when you need to use RDTSC
  * (or get_cycles or vread that possibly accesses the TSC) in a defined

arch/x86/include/asm/bitops.h

@@ -15,6 +15,7 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h>
 #include <asm/rmwcc.h>
+#include <asm/barrier.h>
 
 #if BITS_PER_LONG == 32
 # define _BITOPS_LONG_SHIFT 5
@@ -102,7 +103,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr)
  *
  * 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_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static __always_inline void
@@ -156,9 +157,6 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 	__clear_bit(nr, addr);
 }
 
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 /**
  * __change_bit - Toggle a bit in memory
  * @nr: the bit to change

arch/x86/include/asm/sync_bitops.h

@@ -41,7 +41,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  *
  * sync_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_clear_bit() and/or smp_mb__after_clear_bit()
+ * 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 sync_clear_bit(long nr, volatile unsigned long *addr)

arch/x86/kernel/apic/hw_nmi.c

@@ -57,7 +57,7 @@ void arch_trigger_all_cpu_backtrace(void)
 	}
 
 	clear_bit(0, &backtrace_flag);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static int __kprobes