tracing/timers: Add tracepoint for tracking timer base is_idle flag

When debugging timer code the timer tracepoints are very important. There
is no tracepoint when the is_idle flag of the timer base changes. Instead
of always adding manually trace_printk(), add tracepoints which can be
easily enabled whenever required.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20231201092654.34614-6-anna-maria@linutronix.de

diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 99ada928d44500cde1d33852dcdb8083d0569f9e..1ef58a04fc5798011fd664e115cceb86d91a10c8 100644 (file)
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -142,6 +142,26 @@ DEFINE_EVENT(timer_class, timer_cancel,
        TP_ARGS(timer)
 );
 
+TRACE_EVENT(timer_base_idle,
+
+       TP_PROTO(bool is_idle, unsigned int cpu),
+
+       TP_ARGS(is_idle, cpu),
+
+       TP_STRUCT__entry(
+               __field( bool,          is_idle )
+               __field( unsigned int,  cpu     )
+       ),
+
+       TP_fast_assign(
+               __entry->is_idle        = is_idle;
+               __entry->cpu            = cpu;
+       ),
+
+       TP_printk("is_idle=%d cpu=%d",
+                 __entry->is_idle, __entry->cpu)
+);
+
 #define decode_clockid(type)                                           \
        __print_symbolic(type,                                          \
                { CLOCK_REALTIME,       "CLOCK_REALTIME"        },      \

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index a81d793a43d0cd9728fdfcc9cb16e697646d0857..ed8d6063d9efe2dbbd74ca3aed4d6aa3fde855d8 100644 (file)
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1950,7 +1950,10 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 
        if (time_before_eq(nextevt, basej)) {
                expires = basem;
-               base->is_idle = false;
+               if (base->is_idle) {
+                       base->is_idle = false;
+                       trace_timer_base_idle(false, base->cpu);
+               }
        } else {
                if (base->timers_pending)
                        expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
@@ -1961,8 +1964,10 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
                 * logic is only maintained for the BASE_STD base, deferrable
                 * timers may still see large granularity skew (by design).
                 */
-               if ((expires - basem) > TICK_NSEC)
+               if ((expires - basem) > TICK_NSEC && !base->is_idle) {
                        base->is_idle = true;
+                       trace_timer_base_idle(true, base->cpu);
+               }
        }
        raw_spin_unlock(&base->lock);
 
@@ -1984,7 +1989,10 @@ void timer_clear_idle(void)
         * sending the IPI a few instructions smaller for the cost of taking
         * the lock in the exit from idle path.
         */
-       base->is_idle = false;
+       if (base->is_idle) {
+               base->is_idle = false;
+               trace_timer_base_idle(false, smp_processor_id());
+       }
 }
 #endif