Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Sender: Namhyung Kim <namhyung@gmail.com>
From:   Namhyung Kim <namhyung@kernel.org>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>
Cc:     Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>,
        linux-perf-users@vger.kernel.org,
        Kan Liang <kan.liang@linux.intel.com>,
        Leo Yan <leo.yan@linaro.org>, Andi Kleen <ak@linux.intel.com>,
        Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
        James Clark <james.clark@arm.com>,
        Xing Zhengjun <zhengjun.xing@linux.intel.com>
Subject: [PATCH 20/19] perf stat: Factor out evsel__count_has_error()
Date:   Fri, 14 Oct 2022 11:16:55 -0700
Message-Id: <20221014181655.771612-1-namhyung@kernel.org>
In-Reply-To: <CAM9d7ch_CV3mpno+6D23UGaXzL9zhmzmt513RzbWq8q_0DhU4A@mail.gmail.com>
References: <CAM9d7ch_CV3mpno+6D23UGaXzL9zhmzmt513RzbWq8q_0DhU4A@mail.gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

It's possible to have 0 enabled/running time for some per-task or per-cgroup
events since it's not scheduled on any CPU.  Treating the whole event as
failed would not work in this case.  Thinking again, the code only existed
when any CPU-level aggregation is enabled (like per-socket, per-core, ...).

To make it clearer, factor out the condition check into the new
evsel__count_has_error() function and add some comments.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/stat.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 6ab9c58beca7..9dfa8cac6bc4 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -396,6 +396,25 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 	return ret;
 }
 
+static bool evsel__count_has_error(struct evsel *evsel,
+				   struct perf_counts_values *count,
+				   struct perf_stat_config *config)
+{
+	/* the evsel was failed already */
+	if (evsel->err || evsel->counts->scaled == -1)
+		return true;
+
+	/* this is meaningful for CPU aggregation modes only */
+	if (config->aggr_mode == AGGR_GLOBAL)
+		return false;
+
+	/* it's considered ok when it actually ran */
+	if (count->ena != 0 && count->run != 0)
+		return false;
+
+	return true;
+}
+
 static int
 process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 		       int cpu_map_idx, int thread,
@@ -450,11 +469,9 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 
 			/*
 			 * When any result is bad, make them all to give consistent output
-			 * in interval mode.  But per-task counters can have 0 enabled time
-			 * when some tasks are idle.
+			 * in interval mode.
 			 */
-			if (((count->ena == 0 || count->run == 0) && cpu.cpu != -1) ||
-			    evsel->counts->scaled == -1) {
+			if (evsel__count_has_error(evsel, count, config) && !ps_aggr->failed) {
 				ps_aggr->counts.val = 0;
 				ps_aggr->counts.ena = 0;
 				ps_aggr->counts.run = 0;
-- 
2.38.0.413.g74048e4d9e-goog