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>

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 98a4dfd3b2dc92c05cd025713e107a3c4f08a85a..08a1714494f8712e405647d66f16f6b4a23ec367 100644 (file)
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -376,7 +376,7 @@ See perf list output for the possble metrics and metricgroups.
 Do not aggregate counts across all monitored CPUs.
 
 --topdown::
-Print top down level 1 metrics if supported by the CPU. This allows to
+Print complete top-down metrics supported by the CPU. This allows to
 determine bottle necks in the CPU pipeline for CPU bound workloads,
 by breaking the cycles consumed down into frontend bound, backend bound,
 bad speculation and retiring.
@@ -411,6 +411,18 @@ To interpret the results it is usually needed to know on which
 CPUs the workload runs on. If needed the CPUs can be forced using
 taskset.
 
+--td-level::
+Print the top-down statistics that equal to or lower than the input level.
+It allows users to print the interested top-down metrics level instead of
+the complete top-down metrics.
+
+The availability of the top-down metrics level depends on the hardware. For
+example, Ice Lake only supports L1 top-down metrics. The Sapphire Rapids
+supports both L1 and L2 top-down metrics.
+
+Default: 0 means the max level that the current hardware support.
+Error out if the input is higher than the supported max level.
+
 --no-merge::
 Do not merge results from same PMUs.
 

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b009dde5c60147c652311179ec3fb9129f56d978..2e2e4a8345ea2e80f3b7f109363adf019509004f 100644 (file)
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -138,6 +138,19 @@ static const char *topdown_metric_attrs[] = {
        NULL,
 };
 
+static const char *topdown_metric_L2_attrs[] = {
+       "slots",
+       "topdown-retiring",
+       "topdown-bad-spec",
+       "topdown-fe-bound",
+       "topdown-be-bound",
+       "topdown-heavy-ops",
+       "topdown-br-mispredict",
+       "topdown-fetch-lat",
+       "topdown-mem-bound",
+       NULL,
+};
+
 static const char *smi_cost_attrs = {
        "{"
        "msr/aperf/,"
@@ -1202,7 +1215,9 @@ static struct option stat_options[] = {
        OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge,
                       "don't try to share events between metrics in a group"),
        OPT_BOOLEAN(0, "topdown", &topdown_run,
-                       "measure topdown level 1 statistics"),
+                       "measure top-down statistics"),
+       OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
+                       "Set the metrics level for the top-down statistics (0: max level)"),
        OPT_BOOLEAN(0, "smi-cost", &smi_cost,
                        "measure SMI cost"),
        OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
@@ -1755,17 +1770,30 @@ static int add_default_attributes(void)
        }
 
        if (topdown_run) {
+               const char **metric_attrs = topdown_metric_attrs;
+               unsigned int max_level = 1;
                char *str = NULL;
                bool warn = false;
 
                if (!force_metric_only)
                        stat_config.metric_only = true;
 
-               if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) {
+               if (pmu_have_event("cpu", topdown_metric_L2_attrs[5])) {
+                       metric_attrs = topdown_metric_L2_attrs;
+                       max_level = 2;
+               }
+
+               if (stat_config.topdown_level > max_level) {
+                       pr_err("Invalid top-down metrics level. The max level is %u.\n", max_level);
+                       return -1;
+               } else if (!stat_config.topdown_level)
+                       stat_config.topdown_level = max_level;
+
+               if (topdown_filter_events(metric_attrs, &str, 1) < 0) {
                        pr_err("Out of memory\n");
                        return -1;
                }
-               if (topdown_metric_attrs[0] && str) {
+               if (metric_attrs[0] && str) {
                        if (!stat_config.interval && !stat_config.metric_only) {
                                fprintf(stat_config.output,
                                        "Topdown accuracy may decrease when measuring long periods.\n"

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 12eafd12a693c077178be44b5b60620dee0d03cc..6ccf21a72f061478fa3a17f050ca26ef091f7ccb 100644 (file)
--- 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);

diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 0b3957323f668a3bbfb28e8fd15beaef8dc69b30..5d8af29447f44b959d75b06acd09a2e1aa62c796 100644 (file)
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -99,6 +99,10 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
        ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
        ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
        ID(TOPDOWN_BE_BOUND, topdown-be-bound),
+       ID(TOPDOWN_HEAVY_OPS, topdown-heavy-ops),
+       ID(TOPDOWN_BR_MISPREDICT, topdown-br-mispredict),
+       ID(TOPDOWN_FETCH_LAT, topdown-fetch-lat),
+       ID(TOPDOWN_MEM_BOUND, topdown-mem-bound),
        ID(SMI_NUM, msr/smi/),
        ID(APERF, msr/aperf/),
 };

diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index b5369730b4a2a789df470527670739b043821207..d85c292148bb337f00596b85dfcf6c1563b5bff5 100644 (file)
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -33,6 +33,10 @@ enum perf_stat_evsel_id {
        PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC,
        PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND,
        PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND,
+       PERF_STAT_EVSEL_ID__TOPDOWN_HEAVY_OPS,
+       PERF_STAT_EVSEL_ID__TOPDOWN_BR_MISPREDICT,
+       PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_LAT,
+       PERF_STAT_EVSEL_ID__TOPDOWN_MEM_BOUND,
        PERF_STAT_EVSEL_ID__SMI_NUM,
        PERF_STAT_EVSEL_ID__APERF,
        PERF_STAT_EVSEL_ID__MAX,
@@ -91,6 +95,10 @@ enum stat_type {
        STAT_TOPDOWN_BAD_SPEC,
        STAT_TOPDOWN_FE_BOUND,
        STAT_TOPDOWN_BE_BOUND,
+       STAT_TOPDOWN_HEAVY_OPS,
+       STAT_TOPDOWN_BR_MISPREDICT,
+       STAT_TOPDOWN_FETCH_LAT,
+       STAT_TOPDOWN_MEM_BOUND,
        STAT_SMI_NUM,
        STAT_APERF,
        STAT_MAX
@@ -148,6 +156,7 @@ struct perf_stat_config {
        int                      ctl_fd_ack;
        bool                     ctl_fd_close;
        const char              *cgroup_list;
+       unsigned int            topdown_level;
 };
 
 void perf_stat__set_big_num(int set);