[PATCH 06/14] perf tools: show NMI overhead

[kan.liang@intel.com]

From: Kan Liang <kan.liang@intel.com>

Caculate the total NMI overhead on each CPU, and display them in perf
report

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/builtin-report.c | 11 +++++++++++
 tools/perf/util/event.h     |  4 ++++
 tools/perf/util/machine.c   |  9 +++++++++
 tools/perf/util/session.c   | 18 ++++++++++++++++++
 4 files changed, 42 insertions(+)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1416c39..b1437586 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -365,11 +365,22 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 					 struct report *rep,
 					 const char *help)
 {
+	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
+	int cpu;
 
 	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
 	if (symbol_conf.show_overhead) {
 		fprintf(stdout, "# Overhead:\n");
+		for (cpu = 0; cpu < session->header.env.nr_cpus_online; cpu++) {
+			if (!evlist->stats.total_nmi_overhead[cpu][0])
+				continue;
+			if (rep->cpu_list && !test_bit(cpu, rep->cpu_bitmap))
+				continue;
+			fprintf(stdout, "#\tCPU %d: NMI#: %" PRIu64 " time: %" PRIu64 " ns\n",
+				cpu, evlist->stats.total_nmi_overhead[cpu][0],
+				evlist->stats.total_nmi_overhead[cpu][1]);
+		}
 		fprintf(stdout, "#\n");
 	}
 	evlist__for_each_entry(evlist, pos) {
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d1b179b..7d40d54 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -262,6 +262,9 @@ enum auxtrace_error_type {
  * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
  * the total number of low level events, it is necessary to to sum all struct
  * sample_event.period and stash the result in total_period.
+ *
+ * The total_nmi_overhead tells exactly the NMI handler overhead on each CPU.
+ * The total NMI# is stored in [0], while the accumulated time is in [1].
  */
 struct events_stats {
 	u64 total_period;
@@ -270,6 +273,7 @@ struct events_stats {
 	u64 total_lost_samples;
 	u64 total_aux_lost;
 	u64 total_invalid_chains;
+	u64 total_nmi_overhead[MAX_NR_CPUS][2];
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
 	u32 nr_lost_warned;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 1101757..58076f2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -558,6 +558,15 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 int machine__process_overhead_event(struct machine *machine __maybe_unused,
 				    union perf_event *event __maybe_unused)
 {
+	if (event->overhead.type == PERF_NMI_OVERHEAD) {
+		dump_printf(" NMI nr: %llu  time: %llu cpu %u\n",
+			    event->overhead.entry.nr,
+			    event->overhead.entry.time,
+			    event->overhead.entry.cpu);
+	} else {
+		dump_printf("\tUNSUPPORT OVERHEAD TYPE 0x%x!\n", event->overhead.type);
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index bc0bc21..a79ab99 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1207,6 +1207,23 @@ static int
 					    &sample->read.one, machine);
 }
 
+static void
+overhead_stats_update(struct perf_tool *tool,
+		      struct perf_evlist *evlist,
+		      union perf_event *event)
+{
+	if (tool->overhead == perf_event__process_overhead) {
+		switch (event->overhead.type) {
+		case PERF_NMI_OVERHEAD:
+			evlist->stats.total_nmi_overhead[event->overhead.entry.cpu][0] += event->overhead.entry.nr;
+			evlist->stats.total_nmi_overhead[event->overhead.entry.cpu][1] += event->overhead.entry.time;
+			break;
+		default:
+			break;
+		}
+	}
+}
+
 static int machines__deliver_event(struct machines *machines,
 				   struct perf_evlist *evlist,
 				   union perf_event *event,
@@ -1271,6 +1288,7 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_SWITCH_CPU_WIDE:
 		return tool->context_switch(tool, event, sample, machine);
 	case PERF_RECORD_OVERHEAD:
+		overhead_stats_update(tool, evlist, event);
 		return tool->overhead(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
-- 
2.5.5