diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c
index 4535e6d..d710f2d 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay_32.c
@@ -44,13 +44,36 @@
 static void delay_tsc(unsigned long loops)
 {
 	unsigned long bclock, now;
+	int cpu;
 
-	preempt_disable();		/* TSC's are per-cpu */
+	preempt_disable();
+	cpu = smp_processor_id();
 	rdtscl(bclock);
-	do {
-		rep_nop();
+	for (;;) {
 		rdtscl(now);
-	} while ((now-bclock) < loops);
+		if ((now - bclock) >= loops)
+			break;
+
+		/* Allow RT tasks to run */
+		preempt_enable();
+		rep_nop();
+		preempt_disable();
+
+		/*
+		 * It is possible that we moved to another CPU, and
+		 * since TSC's are per-cpu we need to calculate
+		 * that. The delay must guarantee that we wait "at
+		 * least" the amount of time. Being moved to another
+		 * CPU could make the wait longer but we just need to
+		 * make sure we waited long enough. Rebalance the
+		 * counter for this CPU.
+		 */
+		if (unlikely(cpu != smp_processor_id())) {
+			loops -= (now - bclock);
+			cpu = smp_processor_id();
+			rdtscl(bclock);
+		}
+	}
 	preempt_enable();
 }