perf stat: Add support to measure SMI cost

Implementing a new --smi-cost mode in perf stat to measure SMI cost.

During the measurement, the /sys/device/cpu/freeze_on_smi will be set.

The measurement can be done with one counter (unhalted core cycles), and
two free running MSR counters (IA32_APERF and SMI_COUNT).

In practice, the percentages of SMI core cycles should be more useful
than absolute value. So the output will be the percentage of SMI core
cycles and SMI#. metric_only will be set by default.

SMI cycles% = (aperf - unhalted core cycles) / aperf

Here is an example output.

Performance counter stats for 'sudo echo ':

SMI cycles% SMI#
0.1% 1

0.010858678 seconds time elapsed

Users who wants to get the actual value can apply additional
--no-metric-only.

Signed-off-by: Kan Liang <[e-mail]>
Acked-by: Jiri Olsa <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Robert Elliott <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-stat.txt

···
 --no-merge::
 Do not merge results from same PMUs.
 
+--smi-cost::
+Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
+
+During the measurement, the /sys/device/cpu/freeze_on_smi will be set to
+freeze core counters on SMI.
+The aperf counter will not be effected by the setting.
+The cost of SMI can be measured by (aperf - unhalted core cycles).
+
+In practice, the percentages of SMI cycles is very useful for performance
+oriented analysis. --metric_only will be applied by default.
+The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf
+
+Users who wants to get the actual value can apply --no-metric-only.
+
 EXAMPLES
 --------
 

tools/perf/builtin-stat.c

···
 #define DEFAULT_SEPARATOR	" "
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
+#define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
 
 static void print_counters(struct timespec *ts, int argc, const char **argv);
 
···
 	NULL,
 };
 
+static const char *smi_cost_attrs = {
+	"{"
+	"msr/aperf/,"
+	"msr/smi/,"
+	"cycles"
+	"}"
+};
+
 static struct perf_evlist	*evsel_list;
 
 static struct target target = {
···
 static int			detailed_run			=  0;
 static bool			transaction_run;
 static bool			topdown_run			= false;
+static bool			smi_cost			= false;
+static bool			smi_reset			= false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*csv_sep			= NULL;
···
 			"Only print computed metrics. No raw values", enable_metric_only),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure topdown level 1 statistics"),
+	OPT_BOOLEAN(0, "smi-cost", &smi_cost,
+			"measure SMI cost"),
 	OPT_END()
 };
 
···
 			err = parse_events(evsel_list, transaction_limited_attrs, NULL);
 		if (err) {
 			fprintf(stderr, "Cannot set up transaction events\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	if (smi_cost) {
+		int smi;
+
+		if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) {
+			fprintf(stderr, "freeze_on_smi is not supported.\n");
+			return -1;
+		}
+
+		if (!smi) {
+			if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) {
+				fprintf(stderr, "Failed to set freeze_on_smi.\n");
+				return -1;
+			}
+			smi_reset = true;
+		}
+
+		if (pmu_have_event("msr", "aperf") &&
+		    pmu_have_event("msr", "smi")) {
+			if (!force_metric_only)
+				metric_only = true;
+			err = parse_events(evsel_list, smi_cost_attrs, NULL);
+		} else {
+			fprintf(stderr, "To measure SMI cost, it needs "
+				"msr/aperf/, msr/smi/ and cpu/cycles/ support\n");
+			return -1;
+		}
+		if (err) {
+			fprintf(stderr, "Cannot set up SMI cost events\n");
 			return -1;
 		}
 		return 0;
···
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
+	if (smi_cost && smi_reset)
+		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
+
 	perf_evlist__delete(evsel_list);
 	return status;
 }

tools/perf/util/stat-shadow.c

···
 static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS];
 static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
···
 	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
 	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
 	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
+	memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats));
+	memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats));
 
 	next = rb_first(&runtime_saved_values.entries);
 	while (next) {
···
 		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
 		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, SMI_NUM))
+		update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, APERF))
+		update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
 
 	if (counter->collect_stat) {
 		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
···
 	return sanitize_val(1.0 - sum);
 }
 
+static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+			   struct perf_stat_output_ctx *out)
+{
+	double smi_num, aperf, cycles, cost = 0.0;
+	int ctx = evsel_context(evsel);
+	const char *color = NULL;
+
+	smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]);
+	aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]);
+	cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if ((cycles == 0) || (aperf == 0))
+		return;
+
+	if (smi_num)
+		cost = (aperf - cycles) / aperf * 100.00;
+
+	if (cost > 10)
+		color = PERF_COLOR_RED;
+	out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out)
···
 		}
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
 		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
+		print_smi_cost(cpu, evsel, out);
 	} else {
 		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}

tools/perf/util/stat.c

···
 	ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
 	ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
 	ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
+	ID(SMI_NUM, msr/smi/),
+	ID(APERF, msr/aperf/),
 };
 #undef ID
 

tools/perf/util/stat.h

···
 	PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
 	PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
 	PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
+	PERF_STAT_EVSEL_ID__SMI_NUM,
+	PERF_STAT_EVSEL_ID__APERF,
 	PERF_STAT_EVSEL_ID__MAX,
 };