6.5-stable review patch. If anyone has any objections, please let me know.
------------------
From: Daniel Bristot de Oliveira bristot@kernel.org
[ Upstream commit 6c73daf26420b97fb8b4a620e4ffee5c1f9d44d1 ]
When estimating the IRQ timer delay, we are dealing with two different clock sources: the external clock source that timerlat uses as a reference and the clock used by the tracer. There are also two moments: the time reading the clock and the timer in which the event is placed in the buffer (the trace event timestamp).
If the processor is slow or there is some hardware noise, the difference between the timestamp and the external clock, read can be longer than the IRQ handler delay, resulting in a negative time.
If so, set IRQ to start delay as 0. In the end, it is less near-zero and relevant then the noise.
Link: https://lore.kernel.org/lkml/a066fb667c7136d86dcddb3c7ccd72587db3e7c7.169116...
Fixes: 27e348b221f6 ("rtla/timerlat: Add auto-analysis core") Signed-off-by: Daniel Bristot de Oliveira bristot@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/tracing/rtla/src/timerlat_aa.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c index dec5b4c4511e1..baf1efda0581d 100644 --- a/tools/tracing/rtla/src/timerlat_aa.c +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -338,7 +338,23 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor taa_data->timer_irq_start_time = start; taa_data->timer_irq_duration = duration;
- taa_data->timer_irq_start_delay = taa_data->timer_irq_start_time - expected_start; + /* + * We are dealing with two different clock sources: the + * external clock source that timerlat uses as a reference + * and the clock used by the tracer. There are also two + * moments: the time reading the clock and the timer in + * which the event is placed in the buffer (the trace + * event timestamp). If the processor is slow or there + * is some hardware noise, the difference between the + * timestamp and the external clock read can be longer + * than the IRQ handler delay, resulting in a negative + * time. If so, set IRQ start delay as 0. In the end, + * it is less relevant than the noise. + */ + if (expected_start < taa_data->timer_irq_start_time) + taa_data->timer_irq_start_delay = taa_data->timer_irq_start_time - expected_start; + else + taa_data->timer_irq_start_delay = 0;
/* * not exit from idle.