x86/asm/tsc: Use the full 64-bit TSC in delay_tsc()

As a very minor optimization, delay_tsc() was only using the low
32 bits of the TSC. It's a delay function, so just use the whole
thing.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kvm ML <kvm@vger.kernel.org>
Link: http://lkml.kernel.org/r/bd1a277c71321b67c4794970cb5ace05efe21ab6.1434501121.git.luto@kernel.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/lib/delay.c

@@ -49,16 +49,16 @@ static void delay_loop(unsigned long loops)
 /* TSC based delay: */
 static void delay_tsc(unsigned long __loops)
 {
-	u32 bclock, now, loops = __loops;
+	u64 bclock, now, loops = __loops;
 	int cpu;
 
 	preempt_disable();
 	cpu = smp_processor_id();
 	rdtsc_barrier();
-	rdtscl(bclock);
+	bclock = native_read_tsc();
 	for (;;) {
 		rdtsc_barrier();
-		rdtscl(now);
+		now = native_read_tsc();
 		if ((now - bclock) >= loops)
 			break;
 
@@ -80,7 +80,7 @@ static void delay_tsc(unsigned long __loops)
 			loops -= (now - bclock);
 			cpu = smp_processor_id();
 			rdtsc_barrier();
-			rdtscl(bclock);
+			bclock = native_read_tsc();
 		}
 	}
 	preempt_enable();