cpuidle: tracing, preempt: Squash _rcuidle tracing

Extend/fix commit:

  9aedeaed ("tracing, hardirq: No moar _rcuidle() tracing")

... to also cover trace_preempt_{on,off}() which were mysteriously
untouched.

Fixes: 9aedeaed ("tracing, hardirq: No moar _rcuidle() tracing")
Reported-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lkml.kernel.org/r/Y9D5AfnOukWNOZ5q@hirez.programming.kicks-ass.net
Link: https://lore.kernel.org/r/Y9jWXKgkxY5EZVwW@hirez.programming.kicks-ass.net

kernel/trace/trace_preemptirq.c

@@ -15,10 +15,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/preemptirq.h>
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-/* Per-cpu variable to prevent redundant calls when IRQs already off */
-static DEFINE_PER_CPU(int, tracing_irq_cpu);
-
 /*
  * Use regular trace points on architectures that implement noinstr
  * tooling: these calls will only happen with RCU enabled, which can
@@ -33,6 +29,10 @@ static DEFINE_PER_CPU(int, tracing_irq_cpu);
 #define trace(point)	if (!in_nmi()) trace_##point##_rcuidle
 #endif
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/* Per-cpu variable to prevent redundant calls when IRQs already off */
+static DEFINE_PER_CPU(int, tracing_irq_cpu);
+
 /*
  * Like trace_hardirqs_on() but without the lockdep invocation. This is
  * used in the low level entry code where the ordering vs. RCU is important
@@ -100,15 +100,13 @@ NOKPROBE_SYMBOL(trace_hardirqs_off);
 
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-	if (!in_nmi())
-		trace_preempt_enable_rcuidle(a0, a1);
+	trace(preempt_enable)(a0, a1);
 	tracer_preempt_on(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-	if (!in_nmi())
-		trace_preempt_disable_rcuidle(a0, a1);
+	trace(preempt_disable)(a0, a1);
 	tracer_preempt_off(a0, a1);
 }
 #endif