x86: use CLFLUSHOPT when available

Also drop an unnecessary va adjustment in the code being touched.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>

--- a/xen/arch/x86/flushtlb.c
+++ b/xen/arch/x86/flushtlb.c
@@ -139,10 +139,12 @@ unsigned int flush_area_local(const void
              c->x86_clflush_size && c->x86_cache_size && sz &&
              ((sz >> 10) < c->x86_cache_size) )
         {
-            va = (const void *)((unsigned long)va & ~(sz - 1));
+            alternative(ASM_NOP3, "sfence", X86_FEATURE_CLFLUSHOPT);
             for ( i = 0; i < sz; i += c->x86_clflush_size )
-                 asm volatile ( "clflush %0"
-                                : : "m" (((const char *)va)[i]) );
+                 alternative_input("rex clflush %0",
+                                   "data16 clflush %0",
+                                   X86_FEATURE_CLFLUSHOPT,
+                                   "m" (((const char *)va)[i]));
         }
         else
         {
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -163,6 +163,7 @@
 #define X86_FEATURE_ADX		(7*32+19) /* ADCX, ADOX instructions */
 #define X86_FEATURE_SMAP	(7*32+20) /* Supervisor Mode Access Prevention */
 #define X86_FEATURE_PCOMMIT	(7*32+22) /* PCOMMIT instruction */
+#define X86_FEATURE_CLFLUSHOPT	(7*32+23) /* CLFLUSHOPT instruction */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 8 */
 #define X86_FEATURE_PKU	(8*32+ 3) /* Protection Keys for Userspace */