perf record: Fix duplicated sideband events with Intel PT system wide tracing (442ad225) · Commits · 戴 / test

Commit ("perf record: Add dummy event during system wide synthesis") reveals an issue with Intel PT system wide tracing. Specifically that Intel PT already adds a dummy tracking event, and it is not the first event. Adding another dummy tracking event causes duplicated sideband events. Fix by checking for an existing dummy tracking event first. Example showing duplicated switch events: Before: # perf record -a -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.895 MB perf.data ] # perf script --no-itrace --show-switch-events | head swapper 0 [007] 6390.516222: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 swapper 0 [007] 6390.516222: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [007] 6390.516223: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [007] 6390.516224: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [007] 6390.516227: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 rcu_sched 11 [007] 6390.516227: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [007] 6390.516228: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [007] 6390.516228: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [002] 6390.516415: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 5556/5559 swapper 0 [002] 6390.516416: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 5556/5559 After: # perf record -a -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.868 MB perf.data ] # perf script --no-itrace --show-switch-events | head swapper 0 [005] 6450.567013: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 7179/7181 perf 7181 [005] 6450.567014: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 perf 7181 [005] 6450.567028: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [005] 6450.567029: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 7179/7181 swapper 0 [005] 6450.571699: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [005] 6450.571700: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [005] 6450.571702: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [005] 6450.571703: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [005] 6450.579703: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [005] 6450.579704: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 Signed-off-by:

Adrian Hunter <adrian.hunter@intel.com> Tested-by:

Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lore.kernel.org/lkml/20200629091955.17090-3-adrian.hunter@intel.com Signed-off-by:

Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-record.c

+9 −9

Original line number	Diff line number	Diff line
		@@ -852,20 +852,20 @@ static int record__open(struct record *rec)
		* event synthesis.
		*/
		if (opts->initial_delay \|\| target__has_cpu(&opts->target)) {
		pos = perf_evlist__get_tracking_event(evlist);
		if (!evsel__is_dummy_event(pos)) {
		/* Set up dummy event. */
		if (perf_evlist__add_dummy(evlist))
		return -ENOMEM;

		/* Disable tracking of mmaps on lead event. */
		pos = evlist__first(evlist);
		pos->tracking = 0;
		/* Set up dummy event. */
		pos = evlist__last(evlist);
		pos->tracking = 1;
		perf_evlist__set_tracking_event(evlist, pos);
		}

		/*
		* Enable the dummy event when the process is forked for
		* initial_delay, immediately for system wide.
		*/
		if (opts->initial_delay)
		if (opts->initial_delay && !pos->immediate)
		pos->core.attr.enable_on_exec = 1;
		else
		pos->immediate = 1;

tools/perf/util/evlist.c

+12 −0

Original line number	Diff line number	Diff line
		@@ -1566,6 +1566,18 @@ void perf_evlist__to_front(struct evlist *evlist,
		list_splice(&move, &evlist->core.entries);
		}

		struct evsel perf_evlist__get_tracking_event(struct evlist evlist)
		{
		struct evsel *evsel;

		evlist__for_each_entry(evlist, evsel) {
		if (evsel->tracking)
		return evsel;
		}

		return evlist__first(evlist);
		}

		void perf_evlist__set_tracking_event(struct evlist *evlist,
		struct evsel *tracking_evsel)
		{

tools/perf/util/evlist.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -335,6 +335,7 @@ void perf_evlist__to_front(struct evlist *evlist,
		evlist__cpu_iter_start(evlist); \
		perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)

		struct evsel perf_evlist__get_tracking_event(struct evlist evlist);
		void perf_evlist__set_tracking_event(struct evlist *evlist,
		struct evsel *tracking_evsel);

tools/perf/util/evsel.c

+1 −7

Original line number	Diff line number	Diff line
		@@ -898,12 +898,6 @@ static void evsel__apply_config_terms(struct evsel *evsel,
		}
		}

		static bool is_dummy_event(struct evsel *evsel)
		{
		return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) &&
		(evsel->core.attr.config == PERF_COUNT_SW_DUMMY);
		}

		struct evsel_config_term __evsel__get_config_term(struct evsel evsel, enum evsel_term_type type)
		{
		struct evsel_config_term term, found_term = NULL;
		@@ -1161,7 +1155,7 @@ void evsel__config(struct evsel evsel, struct record_opts opts,
		* The software event will trigger -EOPNOTSUPP error out,
		* if BRANCH_STACK bit is set.
		*/
		if (is_dummy_event(evsel))
		if (evsel__is_dummy_event(evsel))
		evsel__reset_sample_bit(evsel, BRANCH_STACK);
		}

tools/perf/util/evsel.h

+6 −0

Original line number	Diff line number	Diff line
		@@ -399,6 +399,12 @@ static inline bool evsel__has_br_stack(const struct evsel *evsel)
		evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK;
		}

		static inline bool evsel__is_dummy_event(struct evsel *evsel)
		{
		return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) &&
		(evsel->core.attr.config == PERF_COUNT_SW_DUMMY);
		}

		struct perf_env evsel__env(struct evsel evsel);

		int evsel__store_ids(struct evsel evsel, struct evlist evlist);

Admin message