perf hist: Honor symbol_conf.skip_empty

So that it can skip events with no sample according to the config value.
This can omit the dummy event in the output of perf report --group.

An example output:

  $ sudo perf mem record -a sleep 1
  $ sudo perf report --group

Before)
  #
  # Samples: 232  of events 'cpu/mem-loads,ldlat=30/P, cpu/mem-stores/P, dummy:u'
  # Event count (approx.): 3089861
  #
  #                 Overhead  Command      Shared Object      Symbol
  # ........................  ...........  .................  .....................................
  #
       9.29%   0.00%   0.00%  swapper      [kernel.kallsyms]  [k] update_blocked_averages
       5.26%   0.15%   0.00%  swapper      [kernel.kallsyms]  [k] __update_load_avg_se
       4.15%   0.00%   0.00%  perf-exec    [kernel.kallsyms]  [k] slab_update_freelist.isra.0
       3.87%   0.00%   0.00%  perf-exec    [kernel.kallsyms]  [k] memcg_slab_post_alloc_hook
       3.79%   0.17%   0.00%  swapper      [kernel.kallsyms]  [k] enqueue_task_fair
       3.63%   0.00%   0.00%  sleep        [kernel.kallsyms]  [k] next_uptodate_page
       2.86%   0.00%   0.00%  swapper      [kernel.kallsyms]  [k] __update_load_avg_cfs_rq
       2.78%   0.00%   0.00%  swapper      [kernel.kallsyms]  [k] __schedule
       2.34%   0.00%   0.00%  swapper      [kernel.kallsyms]  [k] intel_idle
       2.32%   0.97%   0.00%  swapper      [kernel.kallsyms]  [k] psi_group_change

After)
  #
  # Samples: 232  of events 'cpu/mem-loads,ldlat=30/P, cpu/mem-stores/P'
  # Event count (approx.): 3089861
  #
  #         Overhead  Command      Shared Object      Symbol
  # ................  ...........  .................  .....................................
  #
       9.29%   0.00%  swapper      [kernel.kallsyms]  [k] update_blocked_averages
       5.26%   0.15%  swapper      [kernel.kallsyms]  [k] __update_load_avg_se
       4.15%   0.00%  perf-exec    [kernel.kallsyms]  [k] slab_update_freelist.isra.0
       3.87%   0.00%  perf-exec    [kernel.kallsyms]  [k] memcg_slab_post_alloc_hook
       3.79%   0.17%  swapper      [kernel.kallsyms]  [k] enqueue_task_fair
       3.63%   0.00%  sleep        [kernel.kallsyms]  [k] next_uptodate_page
       2.86%   0.00%  swapper      [kernel.kallsyms]  [k] __update_load_avg_cfs_rq
       2.78%   0.00%  swapper      [kernel.kallsyms]  [k] __schedule
       2.34%   0.00%  swapper      [kernel.kallsyms]  [k] intel_idle
       2.32%   0.97%  swapper      [kernel.kallsyms]  [k] psi_group_change

Now it doesn't have a column for the dummy event.

Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240607202918.2357459-5-namhyung@kernel.org

3 files changed, 29 insertions, 5 deletions

diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 7e863cd92781..5d1f04f66a5a 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -95,6 +95,10 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	}
 
 	for (i = 0; i < nr_members; i++) {
+		if (symbol_conf.skip_empty &&
+		    values[i].hists->stats.nr_samples == 0)
+			continue;
+
 		ret += __hpp__fmt_print(hpp, values[i].hists, values[i].val,
 					values[i].samples, fmt, len,
 					print_fn, fmtype);
@@ -296,8 +300,18 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 	int len = fmt->user_len ?: fmt->len;
 	struct evsel *evsel = hists_to_evsel(hists);
 
-	if (symbol_conf.event_group)
-		len = max(len, evsel->core.nr_members * fmt->len);
+	if (symbol_conf.event_group) {
+		int nr = 0;
+		struct evsel *pos;
+
+		for_each_group_evsel(pos, evsel) {
+			if (!symbol_conf.skip_empty ||
+			    evsel__hists(pos)->stats.nr_samples)
+				nr++;
+		}
+
+		len = max(len, nr * fmt->len);
+	}
 
 	if (len < (int)strlen(fmt->name))
 		len = strlen(fmt->name);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 28c54897a97e..25857894c047 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -55,6 +55,7 @@
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include "util/bpf-filter.h"
+#include "util/hist.h"
 #include <internal/xyarray.h>
 #include <internal/lib.h>
 #include <internal/threadmap.h>
@@ -832,16 +833,22 @@ const char *evsel__group_name(struct evsel *evsel)
 int evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
 {
 	int ret = 0;
+	bool first = true;
 	struct evsel *pos;
 	const char *group_name = evsel__group_name(evsel);
 
 	if (!evsel->forced_leader)
 		ret = scnprintf(buf, size, "%s { ", group_name);
 
-	ret += scnprintf(buf + ret, size - ret, "%s", evsel__name(evsel));
+	for_each_group_evsel(pos, evsel) {
+		if (symbol_conf.skip_empty &&
+		    evsel__hists(pos)->stats.nr_samples == 0)
+			continue;
 
-	for_each_group_member(pos, evsel)
-		ret += scnprintf(buf + ret, size - ret, ", %s", evsel__name(pos));
+		ret += scnprintf(buf + ret, size - ret, "%s%s",
+				 first ? "" : ", ", evsel__name(pos));
+		first = false;
+	}
 
 	if (!evsel->forced_leader)
 		ret += scnprintf(buf + ret, size - ret, " }");
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 0aeb97c11c03..88f98f2772fb 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -23,6 +23,7 @@
 #include "util/env.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
+#include "util/symbol_conf.h"
 #include <internal/lib.h>
 #include "util.h"
 
@@ -50,6 +51,8 @@
 #define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
 #endif
 
+struct symbol_conf symbol_conf;
+
 /*
  * Avoid bringing in event parsing.
  */