x86: mark read_crX() asm code as volatile

Some gcc versions (I checked at least 4.1.1 from RHEL5 & 4.1.2 from gentoo)
can generate incorrect code with read_crX()/write_crX() functions mix up,
due to cached results of read_crX().

The small app for x8664 below compiled with -O2 demonstrates this
(i686 does the same thing):

include/asm-x86/system_32.h

@@ -142,7 +142,7 @@ static inline unsigned long native_read_cr4_safe(void)
 {
 	unsigned long val;
 	/* This could fault if %cr4 does not exist */
-	asm("1: movl %%cr4, %0		\n"
+	asm volatile("1: movl %%cr4, %0		\n"
 		"2:				\n"
 		".section __ex_table,\"a\"	\n"
 		".long 1b,2b			\n"

include/asm-x86/system_64.h

@@ -85,7 +85,7 @@ static inline void write_cr0(unsigned long val)
 static inline unsigned long read_cr2(void)
 {
 	unsigned long cr2;
-	asm("movq %%cr2,%0" : "=r" (cr2));
+	asm volatile("movq %%cr2,%0" : "=r" (cr2));
 	return cr2;
 }
 
@@ -97,7 +97,7 @@ static inline void write_cr2(unsigned long val)
 static inline unsigned long read_cr3(void)
 { 
 	unsigned long cr3;
-	asm("movq %%cr3,%0" : "=r" (cr3));
+	asm volatile("movq %%cr3,%0" : "=r" (cr3));
 	return cr3;
 }
 
@@ -109,7 +109,7 @@ static inline void write_cr3(unsigned long val)
 static inline unsigned long read_cr4(void)
 { 
 	unsigned long cr4;
-	asm("movq %%cr4,%0" : "=r" (cr4));
+	asm volatile("movq %%cr4,%0" : "=r" (cr4));
 	return cr4;
 }
 
@@ -121,7 +121,7 @@ static inline void write_cr4(unsigned long val)
 static inline unsigned long read_cr8(void)
 {
 	unsigned long cr8;
-	asm("movq %%cr8,%0" : "=r" (cr8));
+	asm volatile("movq %%cr8,%0" : "=r" (cr8));
 	return cr8;
 }