x86: fix IO write barrier

wmb() on x86 must always include a barrier, because stores can go out of
order in many cases when dealing with devices (eg. WC memory).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/asm-x86/system_32.h

@@ -216,6 +216,7 @@ static inline unsigned long get_limit(unsigned long segment)
 
 #define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
 #define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
 
 /**
  * read_barrier_depends - Flush all pending reads that subsequents reads
@@ -271,18 +272,14 @@ static inline unsigned long get_limit(unsigned long segment)
 
 #define read_barrier_depends()	do { } while(0)
 
-#ifdef CONFIG_X86_OOSTORE
-/* Actually there are no OOO store capable CPUs for now that do SSE, 
-   but make it already an possibility. */
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define wmb()	__asm__ __volatile__ ("": : :"memory")
-#endif
-
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
 #define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
+#ifdef CONFIG_X86_OOSTORE
+# define smp_wmb() 	wmb()
+#else
+# define smp_wmb()	barrier()
+#endif
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
 #else

include/asm-x86/system_64.h

@@ -159,12 +159,8 @@ static inline void write_cr8(unsigned long val)
  */
 #define mb() 	asm volatile("mfence":::"memory")
 #define rmb()	asm volatile("lfence":::"memory")
-
-#ifdef CONFIG_UNORDERED_IO
 #define wmb()	asm volatile("sfence" ::: "memory")
-#else
-#define wmb()	asm volatile("" ::: "memory")
-#endif
+
 #define read_barrier_depends()	do {} while(0)
 #define set_mb(var, value) do { (void) xchg(&var, value); } while (0)