diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 9d9dec21f510..3ed023f4b190 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -36,51 +36,90 @@ void perf_evlist__init(struct perf_evlist *evlist) static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, struct perf_evsel *evsel) { - if (evsel->system_wide) { - /* System wide: set the cpu map of the evsel to all online CPUs. */ - perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__new_online_cpus(); - } else if (evlist->has_user_cpus && evsel->is_pmu_core) { - /* - * User requested CPUs on a core PMU, ensure the requested CPUs - * are valid by intersecting with those of the PMU. - */ - perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->pmu_cpus); - - /* - * Empty cpu lists would eventually get opened as "any" so remove - * genuinely empty ones before they're opened in the wrong place. - */ - if (perf_cpu_map__is_empty(evsel->cpus)) { - struct perf_evsel *next = perf_evlist__next(evlist, evsel); - - perf_evlist__remove(evlist, evsel); - /* Keep idx contiguous */ - if (next) - list_for_each_entry_from(next, &evlist->entries, node) - next->idx--; + if (perf_cpu_map__is_empty(evsel->cpus)) { + if (perf_cpu_map__is_empty(evsel->pmu_cpus)) { + /* + * Assume the unset PMU cpus were for a system-wide + * event, like a software or tracepoint. + */ + evsel->pmu_cpus = perf_cpu_map__new_online_cpus(); } - } else if (!evsel->pmu_cpus || evlist->has_user_cpus || - (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { - /* - * The PMU didn't specify a default cpu map, this isn't a core - * event and the user requested CPUs or the evlist user - * requested CPUs have the "any CPU" (aka dummy) CPU value. In - * which case use the user requested CPUs rather than the PMU - * ones. - */ - perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); - } else if (evsel->cpus != evsel->pmu_cpus) { - /* - * No user requested cpu map but the PMU cpu map doesn't match - * the evsel's. Reset it back to the PMU cpu map. - */ + if (evlist->has_user_cpus && !evsel->system_wide) { + /* + * Use the user CPUs unless the evsel is set to be + * system wide, such as the dummy event. + */ + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } else { + /* + * System wide and other modes, assume the cpu map + * should be set to all PMU CPUs. + */ + evsel->cpus = perf_cpu_map__get(evsel->pmu_cpus); + } + } + /* + * Avoid "any CPU"(-1) for uncore and PMUs that require a CPU, even if + * requested. + */ + if (evsel->requires_cpu && perf_cpu_map__has_any_cpu(evsel->cpus)) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evsel->pmu_cpus); } + /* + * Globally requested CPUs replace user requested unless the evsel is + * set to be system wide. + */ + if (evlist->has_user_cpus && !evsel->system_wide) { + assert(!perf_cpu_map__has_any_cpu(evlist->user_requested_cpus)); + if (!perf_cpu_map__equal(evsel->cpus, evlist->user_requested_cpus)) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } + } + + /* Ensure cpus only references valid PMU CPUs. */ + if (!perf_cpu_map__has_any_cpu(evsel->cpus) && + !perf_cpu_map__is_subset(evsel->pmu_cpus, evsel->cpus)) { + struct perf_cpu_map *tmp = perf_cpu_map__intersect(evsel->pmu_cpus, evsel->cpus); + + perf_cpu_map__put(evsel->cpus); + evsel->cpus = tmp; + } + + /* + * Was event requested on all the PMU's CPUs but the user requested is + * any CPU (-1)? If so switch to using any CPU (-1) to reduce the number + * of events. + */ + if (!evsel->system_wide && + !evsel->requires_cpu && + perf_cpu_map__equal(evsel->cpus, evsel->pmu_cpus) && + perf_cpu_map__has_any_cpu(evlist->user_requested_cpus)) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } + + /* Sanity check assert before the evsel is potentially removed. */ + assert(!evsel->requires_cpu || !perf_cpu_map__has_any_cpu(evsel->cpus)); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + + return; + } + if (evsel->system_wide) { perf_thread_map__put(evsel->threads); evsel->threads = perf_thread_map__new_dummy(); @@ -98,6 +137,10 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) evlist->needs_map_propagation = true; + /* Clear the all_cpus set which will be merged into during propagation. */ + perf_cpu_map__put(evlist->all_cpus); + evlist->all_cpus = NULL; + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index bd2d831d5123..fe2073c6b549 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -310,20 +310,18 @@ __add_event(struct list_head *list, int *idx, if (pmu) { is_pmu_core = pmu->is_core; pmu_cpus = perf_cpu_map__get(pmu->cpus); + if (perf_cpu_map__is_empty(pmu_cpus)) + pmu_cpus = cpu_map__online(); } else { is_pmu_core = (attr->type == PERF_TYPE_HARDWARE || attr->type == PERF_TYPE_HW_CACHE); pmu_cpus = is_pmu_core ? cpu_map__online() : NULL; } - if (has_user_cpus) { + if (has_user_cpus) cpus = perf_cpu_map__get(user_cpus); - /* Existing behavior that pmu_cpus matches the given user ones. */ - perf_cpu_map__put(pmu_cpus); - pmu_cpus = perf_cpu_map__get(user_cpus); - } else { + else cpus = perf_cpu_map__get(pmu_cpus); - } if (init_attr) event_attr_init(attr); diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index b0205e99a4c9..50b1a92d16df 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -769,8 +769,6 @@ int create_perf_stat_counter(struct evsel *evsel, attr->enable_on_exec = 1; } - if (target__has_cpu(target) && !target__has_per_thread(target)) - return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx); - - return evsel__open_per_thread(evsel, evsel->core.threads); + return evsel__open_per_cpu_and_thread(evsel, evsel__cpus(evsel), cpu_map_idx, + evsel->core.threads); }