From ec0d7729bbaed4b9d2d3fada693278e13a3d1368 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Wed, 14 Jan 2015 14:18:23 +0200 Subject: perf: Add ITRACE_START record to indicate that tracing has started For counters that generate AUX data that is bound to the context of a running task, such as instruction tracing, the decoder needs to know exactly which task is running when the event is first scheduled in, before the first sched_switch. The decoder's need to know this stems from the fact that instruction flow trace decoding will almost always require program's object code in order to reconstruct said flow and for that we need at least its pid/tid in the perf stream. To single out such instruction tracing pmus, this patch introduces ITRACE PMU capability. The reason this is not part of RECORD_AUX record is that not all pmus capable of generating AUX data need this, and the opposite is *probably* also true. While sched_switch covers for most cases, there are two problems with it: the consumer will need to process events out of order (that is, having found RECORD_AUX, it will have to skip forward to the nearest sched_switch to figure out which task it was, then go back to the actual trace to decode it) and it completely misses the case when the tracing is enabled and disabled before sched_switch, for example, via PERF_EVENT_IOC_DISABLE. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kaixu Xia Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul Mackerras Cc: Robert Richter Cc: Stephane Eranian Cc: Thomas Gleixner Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-15-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'kernel/events/core.c') diff --git a/kernel/events/core.c b/kernel/events/core.c index 31f6b504ad62..06917d537302 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1831,6 +1831,7 @@ static void perf_set_shadow_time(struct perf_event *event, #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); +static void perf_log_itrace_start(struct perf_event *event); static int event_sched_in(struct perf_event *event, @@ -1869,6 +1870,8 @@ event_sched_in(struct perf_event *event, perf_set_shadow_time(event, ctx, tstamp); + perf_log_itrace_start(event); + if (event->pmu->add(event, PERF_EF_START)) { event->state = PERF_EVENT_STATE_INACTIVE; event->oncpu = -1; @@ -5991,6 +5994,44 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_output_end(&handle); } +static void perf_log_itrace_start(struct perf_event *event) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u32 pid; + u32 tid; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) || + event->hw.itrace_started) + return; + + event->hw.itrace_started = 1; + + rec.header.type = PERF_RECORD_ITRACE_START; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.pid = perf_event_pid(event, current); + rec.tid = perf_event_tid(event, current); + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + /* * Generic event overflow handling, sampling. */ -- cgit v1.2.3-55-g7522