perf stat: Support --cputype option for hybrid events

In previous patch, we have supported the syntax which enables
the event on a specified pmu, such as:

cpu_core/<event>/
cpu_atom/<event>/

While this syntax is not very easy for applying on a set of
events or applying on a group. In following example, we have to
explicitly assign the pmu prefix.

  # ./perf stat -e '{cpu_core/cycles/,cpu_core/instructions/}' -- sleep 1

   Performance counter stats for 'sleep 1':

           1,158,545      cpu_core/cycles/
           1,003,113      cpu_core/instructions/

         1.002428712 seconds time elapsed

A much easier way is:

  # ./perf stat --cputype core -e '{cycles,instructions}' -- sleep 1

   Performance counter stats for 'sleep 1':

           1,101,071      cpu_core/cycles/
             939,892      cpu_core/instructions/

         1.002363142 seconds time elapsed

For this example, the '--cputype' enables the events from specified
pmu (cpu_core).

If '--cputype' conflicts with pmu prefix, '--cputype' is ignored.

  # ./perf stat --cputype core -e cycles,cpu_atom/instructions/ -a -- sleep 1

   Performance counter stats for 'system wide':

          21,003,407      cpu_core/cycles/
             367,886      cpu_atom/instructions/

         1.002203520 seconds time elapsed

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210909062215.10278-1-yao.jin@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 604e6f2301ea725636d40b13991d62bcb0882f23..c06c341e72b956a5e558cb22047497eddf0b6561 100644 (file)
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -495,6 +495,10 @@ This option can be enabled in perf config by setting the variable
 
 $ perf config stat.no-csv-summary=true
 
+--cputype::
+Only enable events on applying cpu with this type for hybrid platform
+(e.g. core or atom)"
+
 EXAMPLES
 --------
 

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7974933dbc77f70479651199ffda9fa5920a7590..f6ca2b054c5b08f1659958b9cffafaac0f665e22 100644 (file)
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1168,6 +1168,26 @@ static int parse_stat_cgroups(const struct option *opt,
        return parse_cgroups(opt, str, unset);
 }
 
+static int parse_hybrid_type(const struct option *opt,
+                            const char *str,
+                            int unset __maybe_unused)
+{
+       struct evlist *evlist = *(struct evlist **)opt->value;
+
+       if (!list_empty(&evlist->core.entries)) {
+               fprintf(stderr, "Must define cputype before events/metrics\n");
+               return -1;
+       }
+
+       evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str);
+       if (!evlist->hybrid_pmu_name) {
+               fprintf(stderr, "--cputype %s is not supported!\n", str);
+               return -1;
+       }
+
+       return 0;
+}
+
 static struct option stat_options[] = {
        OPT_BOOLEAN('T', "transaction", &transaction_run,
                    "hardware transaction statistics"),
@@ -1282,6 +1302,10 @@ static struct option stat_options[] = {
                       "don't print 'summary' for CSV summary output"),
        OPT_BOOLEAN(0, "quiet", &stat_config.quiet,
                        "don't print output (useful with record)"),
+       OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type",
+                    "Only enable events on applying cpu with this type "
+                    "for hybrid platform (e.g. core or atom)",
+                    parse_hybrid_type),
 #ifdef HAVE_LIBPFM
        OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
                "libpfm4 event selector. use 'perf list' to list available events",

diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 993437ffe4294172d7da70bb840a72cb4f08059c..27594900a05280780ff711b4d4d8288071344f4f 100644 (file)
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -64,6 +64,7 @@ struct evlist {
        struct evsel *selected;
        struct events_stats stats;
        struct perf_env *env;
+       const char *hybrid_pmu_name;
        void (*trace_event_sample_raw)(struct evlist *evlist,
                                       union perf_event *event,
                                       struct perf_sample *sample);

diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 9fc86971027b8614362be607d7fa2dcef0c3530f..284f8eabd3b9abfa51b26d15553faf0b1ffb5936 100644 (file)
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -63,10 +63,13 @@ static int create_event_hybrid(__u32 config_type, int *idx,
 static int pmu_cmp(struct parse_events_state *parse_state,
                   struct perf_pmu *pmu)
 {
-       if (!parse_state->hybrid_pmu_name)
-               return 0;
+       if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name)
+               return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name);
+
+       if (parse_state->hybrid_pmu_name)
+               return strcmp(parse_state->hybrid_pmu_name, pmu->name);
 
-       return strcmp(parse_state->hybrid_pmu_name, pmu->name);
+       return 0;
 }
 
 static int add_hw_hybrid(struct parse_events_state *parse_state,