From 7afbf90ea2e238c4d049ff59dbb6c5f1a938e669 Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 26 Jun 2024 15:54:46 +0100 Subject: perf pmu: Don't de-duplicate core PMUs Arm PMUs have a suffix, either a single decimal (armv8_pmuv3_0) or 3 hex digits which (armv8_cortex_a53) which Perf assumes are both strippable suffixes for the purposes of deduplication. S390 "cpum_cf" is a similarly suffixed core PMU but is only two characters so is not treated as strippable because the rules are a minimum of 3 hex characters or 1 decimal character. There are two paths involved in listing PMU events: * HW/cache event printing assumes core PMUs don't have suffixes so doesn't try to strip. * Sysfs PMU events share the printing function with uncore PMUs which strips. This results in slightly inconsistent Perf list behavior if a core PMU has a suffix: # perf list ... armv8_pmuv3_0/branch-load-misses/ armv8_pmuv3/l3d_cache_wb/ [Kernel PMU event] ... Fix it by partially reverting back to the old list behavior where stripping was only done for uncore PMUs. For example commit 8d9f5146f5da ("perf pmus: Sort pmus by name then suffix") mentions that only PMUs starting 'uncore_' are considered to have a potential suffix. This change doesn't go back that far, but does only strip PMUs that are !is_core. This keeps the desirable behavior where the many possibly duplicated uncore PMUs aren't repeated, but it doesn't break listing for core PMUs. Searching for a PMU continues to use the new stripped comparison functions, meaning that it's still possible to request an event by specifying the common part of a PMU name, or even open events on multiple similarly named PMUs. For example: # perf stat -e armv8_cortex/inst_retired/ 5777173628 armv8_cortex_a53/inst_retired/ (99.93%) 7469626951 armv8_cortex_a57/inst_retired/ (49.88%) Fixes: 3241d46f5f54 ("perf pmus: Sort/merge/aggregate PMUs like mrvl_ddr_pmu") Suggested-by: Ian Rogers Signed-off-by: James Clark Reviewed-by: Ian Rogers Cc: robin.murphy@arm.com Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240626145448.896746-3-james.clark@arm.com --- tools/perf/util/pmu.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 97d74fe6d816..28af48ea803f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -847,6 +847,23 @@ __weak const struct pmu_metrics_table *pmu_metrics_table__find(void) return perf_pmu__find_metrics_table(NULL); } +/** + * Return the length of the PMU name not including the suffix for uncore PMUs. + * + * We want to deduplicate many similar uncore PMUs by stripping their suffixes, + * but there are never going to be too many core PMUs and the suffixes might be + * interesting. "arm_cortex_a53" vs "arm_cortex_a57" or "cpum_cf" for example. + * + * @skip_duplicate_pmus: False in verbose mode so all uncore PMUs are visible + */ +static size_t pmu_deduped_name_len(const struct perf_pmu *pmu, const char *name, + bool skip_duplicate_pmus) +{ + return skip_duplicate_pmus && !pmu->is_core + ? pmu_name_len_no_suffix(name) + : strlen(name); +} + /** * perf_pmu__match_ignoring_suffix - Does the pmu_name match tok ignoring any * trailing suffix? The Suffix must be in form @@ -1796,9 +1813,8 @@ static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, const struct perf_pmu_alias *alias, bool skip_duplicate_pmus) { struct parse_events_term *term; - size_t pmu_name_len = skip_duplicate_pmus - ? pmu_name_len_no_suffix(pmu->name) - : strlen(pmu->name); + size_t pmu_name_len = pmu_deduped_name_len(pmu, pmu->name, + skip_duplicate_pmus); int used = snprintf(buf, len, "%.*s/%s", (int)pmu_name_len, pmu->name, alias->name); list_for_each_entry(term, &alias->terms.terms, list) { @@ -1839,9 +1855,8 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, size_t buf_used, pmu_name_len; info.pmu_name = event->pmu_name ?: pmu->name; - pmu_name_len = skip_duplicate_pmus - ? pmu_name_len_no_suffix(info.pmu_name) - : strlen(info.pmu_name); + pmu_name_len = pmu_deduped_name_len(pmu, info.pmu_name, + skip_duplicate_pmus); info.alias = NULL; if (event->desc) { info.name = event->name; -- cgit v1.2.3