xen/x86: Fix cflush()'s parameter tracking

Forcing a register operand hides (from the compiler) the fact that clflush
behaves as a read from the memory operand (wrt memory order, faults, etc.).
It also reduces the compilers flexibility with register scheduling.

Re-implement clfush() (and wbinvd() for consistency) as a static inline rather
than a macro, and have it take a const void pointer.

In practice, the only generated code which gets modified by this is in
mwait_idle_with_hints(), where a disp8 encoding now gets used.

While here, I noticed that &mwait_wakeup(cpu) was being calculated twice.
This is caused by the memory clobber in mb(), so take the opportunity to help
the optimiser by calculating it once, ahead of time.  bloat-o-meter reports a
delta of -26 as a result of this change.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/acpi/cpu_idle.c

@@ -401,15 +401,16 @@ void mwait_idle_with_hints(unsigned int eax, unsigned int ecx)
 {
     unsigned int cpu = smp_processor_id();
     s_time_t expires = per_cpu(timer_deadline, cpu);
+    const void *monitor_addr = &mwait_wakeup(cpu);
 
     if ( boot_cpu_has(X86_FEATURE_CLFLUSH_MONITOR) )
     {
         mb();
-        clflush((void *)&mwait_wakeup(cpu));
+        clflush(monitor_addr);
         mb();
     }
 
-    __monitor((void *)&mwait_wakeup(cpu), 0, 0);
+    __monitor(monitor_addr, 0, 0);
     smp_mb();
 
     /*

xen/include/asm-x86/system.h

@@ -11,11 +11,15 @@
     __sel;                                                      \
 })
 
-#define wbinvd() \
-    asm volatile ( "wbinvd" : : : "memory" )
+static inline void wbinvd(void)
+{
+    asm volatile ( "wbinvd" ::: "memory" );
+}
 
-#define clflush(a) \
-    asm volatile ( "clflush (%0)" : : "r"(a) )
+static inline void clflush(const void *p)
+{
+    asm volatile ( "clflush %0" :: "m" (*(const char *)p) );
+}
 
 #define xchg(ptr,v) \
     ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))