x86: fall back on interrupt disable in cmpxchg8b on 80386 and 80486

Actually, on 386, cmpxchg and cmpxchg_local fall back on
cmpxchg_386_u8/16/32: it disables interruptions around non atomic
updates to mimic the cmpxchg behavior.

The comment:
/* Poor man's cmpxchg for 386. Unsuitable for SMP */

already present in cmpxchg_386_u32 tells much about how this cmpxchg
implementation should not be used in a SMP context. However, the cmpxchg_local
can perfectly use this fallback, since it only needs to be atomic wrt the local
cpu.

This patch adds a cmpxchg_486_u64 and uses it as a fallback for cmpxchg64
and cmpxchg64_local on 80386 and 80486.

Q:
but why is it called cmpxchg_486 when the other functions are called

A:
Because the standard cmpxchg is missing only on 386, but cmpxchg8b is
missing both on 386 and 486.

Citing Intel's Instruction set reference:

cmpxchg:
This instruction is not supported on Intel processors earlier than the
Intel486 processors.

cmpxchg8b:
This instruction encoding is not supported on Intel processors earlier
than the Pentium processors.

Q:
What's the reason to have cmpxchg64_local on 32 bit architectures?
Without that need all this would just be a few simple defines.

A:
cmpxchg64_local on 32 bits architectures takes unsigned long long
parameters, but cmpxchg_local only takes longs. Since we have cmpxchg8b
to execute a 8 byte cmpxchg atomically on pentium and +, it makes sense
to provide a flavor of cmpxchg and cmpxchg_local using this instruction.

Also, for 32 bits architectures lacking the 64 bits atomic cmpxchg, it
makes sense _not_ to define cmpxchg64 while cmpxchg could still be
available.

Moreover, the fallback for cmpxchg8b on i386 for 386 and 486 is a

However, cmpxchg64_local will be emulated by disabling interrupts on all
architectures where it is not supported atomically.

Therefore, we *could* turn cmpxchg64_local into a cmpxchg_local, but it
would make the 386/486 fallbacks ugly, make its design different from
cmpxchg/cmpxchg64 (which really depends on atomic operations and cannot
be emulated) and require the __cmpxchg_local to be expressed as a macro
rather than an inline function so the parameters would not be fixed to
unsigned long long in every case.

So I think cmpxchg64_local makes sense there, but I am open to
suggestions.

Q:
Are there any callers?

A:
I am actually using it in LTTng in my timestamping code. I use it to
work around CPUs with asynchronous TSCs. I need to update 64 bits
values atomically on this 32 bits architecture.

Changelog:
- Ran though checkpatch.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/include/asm-x86/cmpxchg_32.h b/include/asm-x86/cmpxchg_32.h
index f86ede2..cea1dae 100644
--- a/include/asm-x86/cmpxchg_32.h
+++ b/include/asm-x86/cmpxchg_32.h
@@ -105,15 +105,24 @@
 
 #ifdef CONFIG_X86_CMPXCHG
 #define __HAVE_ARCH_CMPXCHG 1
-#define cmpxchg(ptr,o,n)\
-	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
-					(unsigned long)(n),sizeof(*(ptr))))
-#define sync_cmpxchg(ptr,o,n)\
-	((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\
-					(unsigned long)(n),sizeof(*(ptr))))
-#define cmpxchg_local(ptr,o,n)\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
-					(unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg(ptr, o, n)						     \
+	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	     \
+					(unsigned long)(n), sizeof(*(ptr))))
+#define sync_cmpxchg(ptr, o, n)						     \
+	((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),	     \
+					(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n)					     \
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	     \
+					(unsigned long)(n), sizeof(*(ptr))))
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+#define cmpxchg64(ptr, o, n)						      \
+	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o),      \
+					(unsigned long long)(n)))
+#define cmpxchg64_local(ptr, o, n)					      \
+	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o),\
+					(unsigned long long)(n)))
 #endif
 
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
@@ -203,57 +212,8 @@
 	return old;
 }
 
-#ifndef CONFIG_X86_CMPXCHG
-/*
- * Building a kernel capable running on 80386. It may be necessary to
- * simulate the cmpxchg on the 80386 CPU. For that purpose we define
- * a function for each of the sizes we support.
- */
-
-extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
-extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
-extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
-
-static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 1:
-		return cmpxchg_386_u8(ptr, old, new);
-	case 2:
-		return cmpxchg_386_u16(ptr, old, new);
-	case 4:
-		return cmpxchg_386_u32(ptr, old, new);
-	}
-	return old;
-}
-
-#define cmpxchg(ptr,o,n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 3))				\
-		__ret = __cmpxchg((ptr), (unsigned long)(o),		\
-					(unsigned long)(n), sizeof(*(ptr))); \
-	else								\
-		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
-					(unsigned long)(n), sizeof(*(ptr))); \
-	__ret;								\
-})
-#define cmpxchg_local(ptr,o,n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 3))				\
-		__ret = __cmpxchg_local((ptr), (unsigned long)(o),	\
-					(unsigned long)(n), sizeof(*(ptr))); \
-	else								\
-		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
-					(unsigned long)(n), sizeof(*(ptr))); \
-	__ret;								\
-})
-#endif
-
-static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old,
-				      unsigned long long new)
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+			unsigned long long old, unsigned long long new)
 {
 	unsigned long long prev;
 	__asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
@@ -280,10 +240,86 @@
 	return prev;
 }
 
-#define cmpxchg64(ptr,o,n)\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
-					(unsigned long long)(n)))
-#define cmpxchg64_local(ptr,o,n)\
-	((__typeof__(*(ptr)))__cmpxchg64_local((ptr),(unsigned long long)(o),\
-					(unsigned long long)(n)))
+#ifndef CONFIG_X86_CMPXCHG
+/*
+ * Building a kernel capable running on 80386. It may be necessary to
+ * simulate the cmpxchg on the 80386 CPU. For that purpose we define
+ * a function for each of the sizes we support.
+ */
+
+extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
+extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
+extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
+
+static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	switch (size) {
+	case 1:
+		return cmpxchg_386_u8(ptr, old, new);
+	case 2:
+		return cmpxchg_386_u16(ptr, old, new);
+	case 4:
+		return cmpxchg_386_u32(ptr, old, new);
+	}
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 3))				\
+		__ret = __cmpxchg((ptr), (unsigned long)(o),		\
+					(unsigned long)(n), sizeof(*(ptr))); \
+	else								\
+		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
+					(unsigned long)(n), sizeof(*(ptr))); \
+	__ret;								\
+})
+#define cmpxchg_local(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 3))				\
+		__ret = __cmpxchg_local((ptr), (unsigned long)(o),	\
+					(unsigned long)(n), sizeof(*(ptr))); \
+	else								\
+		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
+					(unsigned long)(n), sizeof(*(ptr))); \
+	__ret;								\
+})
+#endif
+
+#ifndef CONFIG_X86_CMPXCHG64
+/*
+ * Building a kernel capable running on 80386 and 80486. It may be necessary
+ * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
+ */
+
+extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
+
+#define cmpxchg64(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 4))				\
+		__ret = __cmpxchg64((ptr), (unsigned long long)(o),	\
+				(unsigned long long)(n));		\
+	else								\
+		__ret = cmpxchg_486_u64((ptr), (unsigned long long)(o),	\
+				(unsigned long long)(n));		\
+	__ret;								\
+})
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 4))				\
+		__ret = __cmpxchg64_local((ptr), (unsigned long long)(o), \
+				(unsigned long long)(n));		\
+	else								\
+		__ret = cmpxchg_486_u64((ptr), (unsigned long long)(o),	\
+				(unsigned long long)(n));		\
+	__ret;								\
+})
+
+#endif
+
 #endif