perf stat: Support L2 Topdown events

The TMA method level 2 metrics is supported from the Intel Sapphire
Rapids server, which expose four L2 Topdown metrics events to user
space. There are eight L2 events in total. The other four L2 Topdown
metrics events are calculated from the corresponding L1 and the exposed
L2 events.

Now, the --topdown prints the complete top-down metrics that supported
by the CPU. For the Intel Sapphire Rapids server, there are 4 L1 events
and 8 L2 events displyed in one line.

Add a new option, --td-level, to display the top-down statistics that
equal to or lower than the input level.

The L2 event is marked only when both its L1 parent event and itself
crosse the threshold.

Here is an example:

  $ perf stat --topdown --td-level=2 --no-metric-only sleep 1
  Topdown accuracy may decrease when measuring long periods.
  Please print the result regularly, e.g. -I1000

  Performance counter stats for 'sleep 1':

     16,734,390   slots
      2,100,001   topdown-retiring       # 12.6% retiring
      2,034,376   topdown-bad-spec       # 12.3% bad speculation
      4,003,128   topdown-fe-bound       # 24.1% frontend bound
        328,125   topdown-heavy-ops      #  2.0% heavy operations    #  10.6% light operations
      1,968,751   topdown-br-mispredict  # 11.9% branch mispredict   #  0.4% machine clears
      2,953,127   topdown-fetch-lat      # 17.8% fetch latency       #  6.3% fetch bandwidth
      5,906,255   topdown-mem-bound      # 35.6% memory bound        #  15.4% core bound

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-9-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 92 insertions, 0 deletions

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 12eafd12a693..6ccf21a72f06 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -273,6 +273,18 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
 				    cpu, count, &rsd);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS))
+		update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS,
+				    cpu, count, &rsd);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT))
+		update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT,
+				    cpu, count, &rsd);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT))
+		update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT,
+				    cpu, count, &rsd);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND))
+		update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND,
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
 				    cpu, count, &rsd);
@@ -1174,6 +1186,86 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
+			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
+		double retiring = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_RETIRING, st,
+						  &rsd);
+		double heavy_ops = td_metric_ratio(cpu,
+						   STAT_TOPDOWN_HEAVY_OPS, st,
+						   &rsd);
+		double light_ops = retiring - heavy_ops;
+
+		if (retiring > 0.7 && heavy_ops > 0.1)
+			color = PERF_COLOR_GREEN;
+		print_metric(config, ctxp, color, "%8.1f%%", "heavy operations",
+				heavy_ops * 100.);
+		if (retiring > 0.7 && light_ops > 0.6)
+			color = PERF_COLOR_GREEN;
+		else
+			color = NULL;
+		print_metric(config, ctxp, color, "%8.1f%%", "light operations",
+				light_ops * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
+			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
+		double bad_spec = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_BAD_SPEC, st,
+						  &rsd);
+		double br_mis = td_metric_ratio(cpu,
+						STAT_TOPDOWN_BR_MISPREDICT, st,
+						&rsd);
+		double m_clears = bad_spec - br_mis;
+
+		if (bad_spec > 0.1 && br_mis > 0.05)
+			color = PERF_COLOR_RED;
+		print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict",
+				br_mis * 100.);
+		if (bad_spec > 0.1 && m_clears > 0.05)
+			color = PERF_COLOR_RED;
+		else
+			color = NULL;
+		print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
+				m_clears * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
+			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
+		double fe_bound = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_FE_BOUND, st,
+						  &rsd);
+		double fetch_lat = td_metric_ratio(cpu,
+						   STAT_TOPDOWN_FETCH_LAT, st,
+						   &rsd);
+		double fetch_bw = fe_bound - fetch_lat;
+
+		if (fe_bound > 0.2 && fetch_lat > 0.15)
+			color = PERF_COLOR_RED;
+		print_metric(config, ctxp, color, "%8.1f%%", "fetch latency",
+				fetch_lat * 100.);
+		if (fe_bound > 0.2 && fetch_bw > 0.1)
+			color = PERF_COLOR_RED;
+		else
+			color = NULL;
+		print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
+				fetch_bw * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
+			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
+		double be_bound = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_BE_BOUND, st,
+						  &rsd);
+		double mem_bound = td_metric_ratio(cpu,
+						   STAT_TOPDOWN_MEM_BOUND, st,
+						   &rsd);
+		double core_bound = be_bound - mem_bound;
+
+		if (be_bound > 0.2 && mem_bound > 0.2)
+			color = PERF_COLOR_RED;
+		print_metric(config, ctxp, color, "%8.1f%%", "memory bound",
+				mem_bound * 100.);
+		if (be_bound > 0.2 && core_bound > 0.1)
+			color = PERF_COLOR_RED;
+		else
+			color = NULL;
+		print_metric(config, ctxp, color, "%8.1f%%", "Core bound",
+				core_bound * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
 				evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);