static void delay_tsc(unsigned long loops)
 {
-	unsigned long bclock, now;
+	unsigned prev, prev_1, now;
+	unsigned left = loops;
+	unsigned prev_cpu, cpu;
+
+	preempt_disable();
+	rdtscl(prev);

The unsigneds should be probably u64  and the rdtsc rdtscll.
Otherwise this will all overflow for longer waits on a very
fast systems (e.g. a 5Ghz system wraps 32bit in ~1.1 seconds)
Normally such delays shouldn't be that long, but why risk
overflow even in extreme cases?

-Andi