x86: Fix and improve cmpxchg_double{,_local}()

Just like the per-CPU ones they had several
problems/shortcomings:

Only the first memory operand was mentioned in the asm()
operands, and the 2x64-bit version didn't have a memory clobber
while the 2x32-bit one did. The former allowed the compiler to
not recognize the need to re-load the data in case it had it
cached in some register, while the latter was overly
destructive.

The types of the local copies of the old and new values were
incorrect (the types of the pointed-to variables should be used
here, to make sure the respective old/new variable types are
compatible).

The __dummy/__junk variables were pointless, given that local
copies of the inputs already existed (and can hence be used for
discarded outputs).

The 32-bit variant of cmpxchg_double_local() referenced
cmpxchg16b_local().

At once also:

- change the return value type to what it really is: 'bool'
- unify 32- and 64-bit variants
- abstract out the common part of the 'normal' and 'local' variants

Signed-off-by: Jan Beulich <[e-mail]>
Cc: Christoph Lameter <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

arch/x86/include/asm/cmpxchg.h

···
 #define add_smp(ptr, inc)	__add((ptr), (inc), LOCK_PREFIX)
 #define add_sync(ptr, inc)	__add((ptr), (inc), "lock; ")
 
+#define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2)			\
+({									\
+	bool __ret;							\
+	__typeof__(*(p1)) __old1 = (o1), __new1 = (n1);			\
+	__typeof__(*(p2)) __old2 = (o2), __new2 = (n2);			\
+	BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long));			\
+	BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long));			\
+	VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long)));		\
+	VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2));	\
+	asm volatile(pfx "cmpxchg%c4b %2; sete %0"			\
+		     : "=a" (__ret), "+d" (__old2),			\
+		       "+m" (*(p1)), "+m" (*(p2))			\
+		     : "i" (2 * sizeof(long)), "a" (__old1),		\
+		       "b" (__new1), "c" (__new2));			\
+	__ret;								\
+})
+
+#define 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) \
+	__cmpxchg_double(, p1, p2, o1, o2, n1, n2)
+
 #endif	/* ASM_X86_CMPXCHG_H */

arch/x86/include/asm/cmpxchg_32.h

···
 
 #endif
 
-#define cmpxchg8b(ptr, o1, o2, n1, n2)				\
-({								\
-	char __ret;						\
-	__typeof__(o2) __dummy;					\
-	__typeof__(*(ptr)) __old1 = (o1);			\
-	__typeof__(o2) __old2 = (o2);				\
-	__typeof__(*(ptr)) __new1 = (n1);			\
-	__typeof__(o2) __new2 = (n2);				\
-	asm volatile(LOCK_PREFIX "cmpxchg8b %2; setz %1"	\
-		       : "=d"(__dummy), "=a" (__ret), "+m" (*ptr)\
-		       : "a" (__old1), "d"(__old2),		\
-		         "b" (__new1), "c" (__new2)		\
-		       : "memory");				\
-	__ret; })
-
-
-#define cmpxchg8b_local(ptr, o1, o2, n1, n2)			\
-({								\
-	char __ret;						\
-	__typeof__(o2) __dummy;					\
-	__typeof__(*(ptr)) __old1 = (o1);			\
-	__typeof__(o2) __old2 = (o2);				\
-	__typeof__(*(ptr)) __new1 = (n1);			\
-	__typeof__(o2) __new2 = (n2);				\
-	asm volatile("cmpxchg8b %2; setz %1"			\
-		       : "=d"(__dummy), "=a"(__ret), "+m" (*ptr)\
-		       : "a" (__old), "d"(__old2),		\
-		         "b" (__new1), "c" (__new2),		\
-		       : "memory");				\
-	__ret; })
-
-
-#define cmpxchg_double(ptr, o1, o2, n1, n2)				\
-({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
-	VM_BUG_ON((unsigned long)(ptr) % 8);				\
-	cmpxchg8b((ptr), (o1), (o2), (n1), (n2));			\
-})
-
-#define cmpxchg_double_local(ptr, o1, o2, n1, n2)			\
-({									\
-       BUILD_BUG_ON(sizeof(*(ptr)) != 4);				\
-       VM_BUG_ON((unsigned long)(ptr) % 8);				\
-       cmpxchg16b_local((ptr), (o1), (o2), (n1), (n2));			\
-})
-
 #define system_has_cmpxchg_double() cpu_has_cx8
 
 #endif /* _ASM_X86_CMPXCHG_32_H */

arch/x86/include/asm/cmpxchg_64.h

···
 	cmpxchg_local((ptr), (o), (n));					\
 })
 
-#define cmpxchg16b(ptr, o1, o2, n1, n2)				\
-({								\
-	char __ret;						\
-	__typeof__(o2) __junk;					\
-	__typeof__(*(ptr)) __old1 = (o1);			\
-	__typeof__(o2) __old2 = (o2);				\
-	__typeof__(*(ptr)) __new1 = (n1);			\
-	__typeof__(o2) __new2 = (n2);				\
-	asm volatile(LOCK_PREFIX "cmpxchg16b %2;setz %1"	\
-		       : "=d"(__junk), "=a"(__ret), "+m" (*ptr)	\
-		       : "b"(__new1), "c"(__new2),		\
-		         "a"(__old1), "d"(__old2));		\
-	__ret; })
-
-
-#define cmpxchg16b_local(ptr, o1, o2, n1, n2)			\
-({								\
-	char __ret;						\
-	__typeof__(o2) __junk;					\
-	__typeof__(*(ptr)) __old1 = (o1);			\
-	__typeof__(o2) __old2 = (o2);				\
-	__typeof__(*(ptr)) __new1 = (n1);			\
-	__typeof__(o2) __new2 = (n2);				\
-	asm volatile("cmpxchg16b %2;setz %1"			\
-		       : "=d"(__junk), "=a"(__ret), "+m" (*ptr)	\
-		       : "b"(__new1), "c"(__new2),		\
-		         "a"(__old1), "d"(__old2));		\
-	__ret; })
-
-#define cmpxchg_double(ptr, o1, o2, n1, n2)				\
-({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	VM_BUG_ON((unsigned long)(ptr) % 16);				\
-	cmpxchg16b((ptr), (o1), (o2), (n1), (n2));			\
-})
-
-#define cmpxchg_double_local(ptr, o1, o2, n1, n2)			\
-({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	VM_BUG_ON((unsigned long)(ptr) % 16);				\
-	cmpxchg16b_local((ptr), (o1), (o2), (n1), (n2));		\
-})
-
 #define system_has_cmpxchg_double() cpu_has_cx16
 
 #endif /* _ASM_X86_CMPXCHG_64_H */

mm/slub.c

···
 	VM_BUG_ON(!irqs_disabled());
 #ifdef CONFIG_CMPXCHG_DOUBLE
 	if (s->flags & __CMPXCHG_DOUBLE) {
-		if (cmpxchg_double(&page->freelist,
+		if (cmpxchg_double(&page->freelist, &page->counters,
 			freelist_old, counters_old,
 			freelist_new, counters_new))
 		return 1;
···
 {
 #ifdef CONFIG_CMPXCHG_DOUBLE
 	if (s->flags & __CMPXCHG_DOUBLE) {
-		if (cmpxchg_double(&page->freelist,
+		if (cmpxchg_double(&page->freelist, &page->counters,
 			freelist_old, counters_old,
 			freelist_new, counters_new))
 		return 1;