page fault scalability patch V8: [4/7] universally available cmpxchg on i386

Changelog
	* Make cmpxchg and cmpxchg8b generally available on i386.
	* Provide emulation of cmpxchg suitable for UP if build and
	  run on 386.
	* Provide emulation of cmpxchg8b suitable for UP if build
	  and run on 386 or 486.

Signed-off-by: Christoph Lameter <clameter@sgi.com>

Index: linus/include/asm-i386/system.h
===================================================================
--- linus.orig/include/asm-i386/system.h	2004-09-18 14:25:23.000000000 -0700
+++ linus/include/asm-i386/system.h	2004-09-18 14:56:59.000000000 -0700
@@ -203,77 +203,6 @@
  __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
  __set_64bit(ptr, ll_low(value), ll_high(value)) )

-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- *	  but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-	switch (size) {
-		case 1:
-			__asm__ __volatile__("xchgb %b0,%1"
-				:"=q" (x)
-				:"m" (*__xg(ptr)), "0" (x)
-				:"memory");
-			break;
-		case 2:
-			__asm__ __volatile__("xchgw %w0,%1"
-				:"=r" (x)
-				:"m" (*__xg(ptr)), "0" (x)
-				:"memory");
-			break;
-		case 4:
-			__asm__ __volatile__("xchgl %0,%1"
-				:"=r" (x)
-				:"m" (*__xg(ptr)), "0" (x)
-				:"memory");
-			break;
-	}
-	return x;
-}
-
-/*
- * 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.
- */
-
-#ifdef CONFIG_X86_CMPXCHG
-#define __HAVE_ARCH_CMPXCHG 1
-#endif
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		__asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
-				     : "=a"(prev)
-				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-				     : "memory");
-		return prev;
-	case 2:
-		__asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
-				     : "=a"(prev)
-				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-				     : "memory");
-		return prev;
-	case 4:
-		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
-				     : "=a"(prev)
-				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-				     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-#define cmpxchg(ptr,o,n)\
-	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
-					(unsigned long)(n),sizeof(*(ptr))))
-
 #ifdef __KERNEL__
 struct alt_instr {
 	__u8 *instr; 		/* original instruction */
Index: linus/arch/i386/Kconfig
===================================================================
--- linus.orig/arch/i386/Kconfig	2004-09-18 14:25:23.000000000 -0700
+++ linus/arch/i386/Kconfig	2004-09-18 14:56:59.000000000 -0700
@@ -345,6 +345,11 @@
 	depends on !M386
 	default y

+config X86_CMPXCHG8B
+	bool
+	depends on !M386 && !M486
+	default y
+
 config X86_XADD
 	bool
 	depends on !M386
Index: linus/include/asm-i386/processor.h
===================================================================
--- linus.orig/include/asm-i386/processor.h	2004-09-18 14:25:23.000000000 -0700
+++ linus/include/asm-i386/processor.h	2004-09-18 14:56:59.000000000 -0700
@@ -657,4 +657,137 @@

 #define cache_line_size() (boot_cpu_data.x86_cache_alignment)

+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ *	  but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+{
+	switch (size) {
+		case 1:
+			__asm__ __volatile__("xchgb %b0,%1"
+				:"=q" (x)
+				:"m" (*__xg(ptr)), "0" (x)
+				:"memory");
+			break;
+		case 2:
+			__asm__ __volatile__("xchgw %w0,%1"
+				:"=r" (x)
+				:"m" (*__xg(ptr)), "0" (x)
+				:"memory");
+			break;
+		case 4:
+			__asm__ __volatile__("xchgl %0,%1"
+				:"=r" (x)
+				:"m" (*__xg(ptr)), "0" (x)
+				:"memory");
+			break;
+	}
+	return x;
+}
+
+/*
+ * 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.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+#endif
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long prev;
+#ifndef CONFIG_X86_CMPXCHG
+	/*
+	 * Check if the kernel was compiled for an old cpu but the
+	 * currently running cpu can do cmpxchg after all
+	 */
+	unsigned long flags;
+
+	/* All CPUs except 386 support CMPXCHG */
+	if (cpu_data->x86 > 3) goto have_cmpxchg;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	switch (size) {
+	case 1:
+		prev = * (u8 *)ptr;
+		if (prev == old) *(u8 *)ptr = new;
+		break;
+	case 2:
+		prev = * (u16 *)ptr;
+		if (prev == old) *(u16 *)ptr = new;
+	case 4:
+		prev = *(u32 *)ptr;
+		if (prev == old) *(u32 *)ptr = new;
+		break;
+	}
+	local_irq_restore(flags);
+	return prev;
+have_cmpxchg:
+#endif
+	switch (size) {
+	case 1:
+		__asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 2:
+		__asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	}
+	return prev;
+}
+
+static inline unsigned long long cmpxchg8b(volatile unsigned long long *ptr,
+	       unsigned long long old, unsigned long long newv)
+{
+	unsigned long long prev;
+#ifndef CONFIG_X86_CMPXCHG8B
+	unsigned long flags;
+
+	/*
+	 * Check if the kernel was compiled for an old cpu but
+	 * we are running really on a cpu capable of cmpxchg8b
+	 */
+
+	if (cpu_has(cpu_data, X86_FEATURE_CX8)) goto have_cmpxchg8b;
+
+	/* Poor mans cmpxchg8b for 386 and 486. Not suitable for SMP */
+	local_irq_save(flags);
+	prev = *ptr;
+	if (prev == old) *ptr = newv;
+	local_irq_restore(flags);
+	return prev;
+
+have_cmpxchg8b:
+#endif
+
+	 __asm__ __volatile__(
+	LOCK_PREFIX "cmpxchg8b %4\n"
+	: "=A" (prev)
+	: "0" (old), "c" ((unsigned long)(newv >> 32)),
+       		"b" ((unsigned long)(newv & 0xffffffffLL)), "m" (ptr)
+	: "memory");
+	return prev ;
+}
+
+#define cmpxchg(ptr,o,n)\
+	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+					(unsigned long)(n),sizeof(*(ptr))))
+
 #endif /* __ASM_I386_PROCESSOR_H */

-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html