6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Rogers irogers@google.com
[ Upstream commit 8ce0d2da14d3fb62844dd0e95982c194326b1a5f ]
Legacy events typically don't have a PMU when added leading to mismatched legacy/non-legacy cases in find_stat. Use evsel__find_pmu to make sure the evsel PMU is looked up. Update the evsel__find_pmu code to look for the PMU using the extended config type or, for legacy hardware/hw_cache events on non-hybrid systems, just use the core PMU.
Before: ``` $ perf stat -e cycles,cpu/instructions/ -a sleep 1 Performance counter stats for 'system wide':
215,309,764 cycles 44,326,491 cpu/instructions/
1.002555314 seconds time elapsed ``` After: ``` $ perf stat -e cycles,cpu/instructions/ -a sleep 1
Performance counter stats for 'system wide':
990,676,332 cycles 1,235,762,487 cpu/instructions/ # 1.25 insn per cycle
1.002667198 seconds time elapsed ```
Fixes: 3612ca8e2935 ("perf stat: Fix the hard-coded metrics calculation on the hybrid") Signed-off-by: Ian Rogers irogers@google.com Tested-by: James Clark james.clark@linaro.org Tested-by: Leo Yan leo.yan@arm.com Tested-by: Atish Patra atishp@rivosinc.com Link: https://lore.kernel.org/r/20250109222109.567031-3-irogers@google.com Signed-off-by: Namhyung Kim namhyung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/pmus.c | 20 +++++++++++++++++--- tools/perf/util/stat-shadow.c | 3 ++- 2 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index f0577aa7eca88..dda5ba9c73fd9 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -587,11 +587,25 @@ char *perf_pmus__default_pmu_name(void) struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = evsel->pmu; + bool legacy_core_type;
- if (!pmu) { - pmu = perf_pmus__find_by_type(evsel->core.attr.type); - ((struct evsel *)evsel)->pmu = pmu; + if (pmu) + return pmu; + + pmu = perf_pmus__find_by_type(evsel->core.attr.type); + legacy_core_type = + evsel->core.attr.type == PERF_TYPE_HARDWARE || + evsel->core.attr.type == PERF_TYPE_HW_CACHE; + if (!pmu && legacy_core_type) { + if (perf_pmus__supports_extended_type()) { + u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT; + + pmu = perf_pmus__find_by_type(type); + } else { + pmu = perf_pmus__find_core_pmu(); + } } + ((struct evsel *)evsel)->pmu = pmu; return pmu; }
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 2affa4d45aa21..56b186d307453 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -154,6 +154,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type { const struct evsel *cur; int evsel_ctx = evsel_context(evsel); + struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel);
evlist__for_each_entry(evsel->evlist, cur) { struct perf_stat_aggr *aggr; @@ -180,7 +181,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type * Except the SW CLOCK events, * ignore if not the PMU we're looking for. */ - if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu)) + if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur))) continue;
aggr = &cur->stats->aggr[aggr_idx];