powerpc: tracing: Add powerpc tracepoints for timer entry and exit

We can monitor the effectiveness of our power management of both the
kernel and hypervisor by probing the timer interrupt. For example, on
this box we see 10.37s timer interrupts on an idle core:

<idle>-0     [010]  3900.671297: timer_interrupt_entry: pt_regs=c0000000ce1e7b10
<idle>-0     [010]  3900.671302: timer_interrupt_exit: pt_regs=c0000000ce1e7b10

<idle>-0     [010]  3911.042963: timer_interrupt_entry: pt_regs=c0000000ce1e7b10
<idle>-0     [010]  3911.042968: timer_interrupt_exit: pt_regs=c0000000ce1e7b10

<idle>-0     [010]  3921.414630: timer_interrupt_entry: pt_regs=c0000000ce1e7b10
<idle>-0     [010]  3921.414635: timer_interrupt_exit: pt_regs=c0000000ce1e7b10

Since we have a 207MHz decrementer it will go negative and fire every 10.37s
even if Linux is completely idle.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

arch/powerpc/include/asm/trace.h

@@ -42,6 +42,40 @@ TRACE_EVENT(irq_exit,
 	TP_printk("pt_regs=%p", __entry->regs)
 );
 
+TRACE_EVENT(timer_interrupt_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
 #endif /* _TRACE_POWERPC_H */
 
 #undef TRACE_INCLUDE_PATH

arch/powerpc/kernel/time.c

@@ -54,6 +54,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/perf_event.h>
+#include <asm/trace.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -571,6 +572,8 @@ void timer_interrupt(struct pt_regs * regs)
 	struct clock_event_device *evt = &decrementer->event;
 	u64 now;
 
+	trace_timer_interrupt_entry(regs);
+
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continuue to take decrementer exceptions */
 	set_dec(DECREMENTER_MAX);
@@ -590,6 +593,7 @@ void timer_interrupt(struct pt_regs * regs)
 		now = decrementer->next_tb - now;
 		if (now <= DECREMENTER_MAX)
 			set_dec((int)now);
+		trace_timer_interrupt_exit(regs);
 		return;
 	}
 	old_regs = set_irq_regs(regs);
@@ -620,6 +624,8 @@ void timer_interrupt(struct pt_regs * regs)
 
 	irq_exit();
 	set_irq_regs(old_regs);
+
+	trace_timer_interrupt_exit(regs);
 }
 
 void wakeup_decrementer(void)