From bf5a8c26ad7caf0772a1cd48c8a0924e48bdbaf0 Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Thu, 15 Jun 2023 03:59:47 -0300 Subject: trace,smp: Add tracepoints for scheduling remotelly called functions Add a tracepoint for when a CSD is queued to a remote CPU's call_single_queue. This allows finding exactly which CPU queued a given CSD when looking at a csd_function_{entry,exit} event, and also enables us to accurately measure IPI delivery time with e.g. a synthetic event: $ echo 'hist:keys=cpu,csd.hex:ts=common_timestamp.usecs' >\ /sys/kernel/tracing/events/smp/csd_queue_cpu/trigger $ echo 'csd_latency unsigned int dst_cpu; unsigned long csd; u64 time' >\ /sys/kernel/tracing/synthetic_events $ echo \ 'hist:keys=common_cpu,csd.hex:'\ 'time=common_timestamp.usecs-$ts:'\ 'onmatch(smp.csd_queue_cpu).trace(csd_latency,common_cpu,csd,$time)' >\ /sys/kernel/tracing/events/smp/csd_function_entry/trigger $ trace-cmd record -e 'synthetic:csd_latency' hackbench $ trace-cmd report <...>-467 [001] 21.824263: csd_queue_cpu: cpu=0 callsite=try_to_wake_up+0x2ea func=sched_ttwu_pending csd=0xffff8880076148b8 <...>-467 [001] 21.824280: ipi_send_cpu: cpu=0 callsite=try_to_wake_up+0x2ea callback=generic_smp_call_function_single_interrupt+0x0 <...>-489 [000] 21.824299: csd_function_entry: func=sched_ttwu_pending csd=0xffff8880076148b8 <...>-489 [000] 21.824320: csd_latency: dst_cpu=0, csd=18446612682193848504, time=36 Suggested-by: Valentin Schneider Signed-off-by: Leonardo Bras Tested-and-reviewed-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230615065944.188876-7-leobras@redhat.com --- include/trace/events/csd.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/csd.h b/include/trace/events/csd.h index af1df5200ae6..67e9d01f80c2 100644 --- a/include/trace/events/csd.h +++ b/include/trace/events/csd.h @@ -7,6 +7,33 @@ #include +TRACE_EVENT(csd_queue_cpu, + + TP_PROTO(const unsigned int cpu, + unsigned long callsite, + smp_call_func_t func, + struct __call_single_data *csd), + + TP_ARGS(cpu, callsite, func, csd), + + TP_STRUCT__entry( + __field(unsigned int, cpu) + __field(void *, callsite) + __field(void *, func) + __field(void *, csd) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->callsite = (void *)callsite; + __entry->func = func; + __entry->csd = csd; + ), + + TP_printk("cpu=%u callsite=%pS func=%ps csd=%p", + __entry->cpu, __entry->callsite, __entry->func, __entry->csd) + ); + /* * Tracepoints for a function which is called as an effect of smp_call_function.* */ -- cgit v1.2.3