powerpc: hard_irq_disable(): Call trace_hardirqs_off after disabling

lockdep.c has this:
        /*
         * So we're supposed to get called after you mask local IRQs,
         * but for some reason the hardware doesn't quite think you did
         * a proper job.
         */
	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
		return;

Since irqs_disabled() is based on soft_enabled(), that (not just the
hard EE bit) needs to be 0 before we call trace_hardirqs_off.
Signed-off-by: Scott Wood <scottwood@freescale.com>

arch/powerpc/include/asm/hw_irq.h

@@ -96,11 +96,12 @@ static inline bool arch_irqs_disabled(void)
 #endif
 
 #define hard_irq_disable()	do {			\
+	u8 _was_enabled = get_paca()->soft_enabled;	\
 	__hard_irq_disable();				\
-	if (local_paca->soft_enabled)			\
-		trace_hardirqs_off();			\
 	get_paca()->soft_enabled = 0;			\
 	get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;	\
+	if (_was_enabled)				\
+		trace_hardirqs_off();			\
 } while(0)
 
 static inline bool lazy_irq_pending(void)