From f60c3f44689ac2bc33340f37adbc837a4fb79c91 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 3 Apr 2025 12:43:35 -0700 Subject: [PATCH] perf stat: Use counter cpumask to skip zero values When a counter is 0 it may or may not be skipped. For uncore counters it is common they are only valid on 1 logical CPU and all other CPUs should be skipped. The PMU's cpumask was used for the skip calculation, but that cpumask may not reflect user overrides. Similarly a counter on a core PMU may explicitly not request a CPU be gathered. If the counter on this CPU's value is 0 then the counter should be skipped as it wasn't requested. Switch from using the PMU cpumask to that associated with the evsel to support these cases. Avoid potential crash with --per-thread mode where config->aggr_get_id is NULL. Add some examples for the tool event 0 counter skipping. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Dominique Martinet Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Weilin Wang Cc: Yicong Yang Link: https://lore.kernel.org/r/20250403194337.40202-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-display.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index aab3697aed63..e31d9f64d3ae 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -1008,8 +1008,16 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, return true; /* - * Many tool events are only gathered on the first index, skip other - * zero values. + * In per-thread mode the aggr_map and aggr_get_id functions may be + * NULL, assume all 0 values should be output in that case. + */ + if (!config->aggr_map || !config->aggr_get_id) + return false; + + /* + * Tool events may be gathered on all logical CPUs, for example + * system_time, but for many the first index is the only one used, for + * example num_cores. Don't skip for the first index. */ if (evsel__is_tool(counter)) { struct aggr_cpu_id own_id = @@ -1017,15 +1025,12 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, return !aggr_cpu_id__equal(id, &own_id); } - /* - * Skip value 0 when it's an uncore event and the given aggr id - * does not belong to the PMU cpumask. + * Skip value 0 when the counter's cpumask doesn't match the given aggr + * id. */ - if (!counter->pmu || !counter->pmu->is_uncore) - return false; - perf_cpu_map__for_each_cpu(cpu, idx, counter->pmu->cpus) { + perf_cpu_map__for_each_cpu(cpu, idx, counter->core.cpus) { struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu); if (aggr_cpu_id__equal(id, &own_id)) -- 2.50.1