x86: udelay: Use this_cpu_read to avoid address calculation

The code will use a segment prefix instead of doing the lookup and
calculation.

Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

arch/x86/lib/delay.c

@@ -121,7 +121,7 @@ inline void __const_udelay(unsigned long xloops)
 	asm("mull %%edx"
 		:"=d" (xloops), "=&a" (d0)
 		:"1" (xloops), "0"
-		(cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
+		(this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4)));
 
 	__delay(++xloops);
 }