diff options
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r-- | tools/perf/builtin-stat.c | 279 |
1 files changed, 88 insertions, 191 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fa7c40956d0f..cc9fa48d636f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -41,7 +41,6 @@ */ #include "builtin.h" -#include "perf.h" #include "util/cgroup.h" #include <subcmd/parse-options.h> #include "util/parse-events.h" @@ -71,6 +70,7 @@ #include "util/bpf_counter.h" #include "util/iostat.h" #include "util/pmu-hybrid.h" +#include "util/util.h" #include "asm/bug.h" #include <linux/time64.h> @@ -100,71 +100,6 @@ static void print_counters(struct timespec *ts, int argc, const char **argv); -/* Default events used for perf stat -T */ -static const char *transaction_attrs = { - "task-clock," - "{" - "instructions," - "cycles," - "cpu/cycles-t/," - "cpu/tx-start/," - "cpu/el-start/," - "cpu/cycles-ct/" - "}" -}; - -/* More limited version when the CPU does not have all events. */ -static const char * transaction_limited_attrs = { - "task-clock," - "{" - "instructions," - "cycles," - "cpu/cycles-t/," - "cpu/tx-start/" - "}" -}; - -static const char * topdown_attrs[] = { - "topdown-total-slots", - "topdown-slots-retired", - "topdown-recovery-bubbles", - "topdown-fetch-bubbles", - "topdown-slots-issued", - NULL, -}; - -static const char *topdown_metric_attrs[] = { - "slots", - "topdown-retiring", - "topdown-bad-spec", - "topdown-fe-bound", - "topdown-be-bound", - NULL, -}; - -static const char *topdown_metric_L2_attrs[] = { - "slots", - "topdown-retiring", - "topdown-bad-spec", - "topdown-fe-bound", - "topdown-be-bound", - "topdown-heavy-ops", - "topdown-br-mispredict", - "topdown-fetch-lat", - "topdown-mem-bound", - NULL, -}; - -#define TOPDOWN_MAX_LEVEL 2 - -static const char *smi_cost_attrs = { - "{" - "msr/aperf/," - "msr/smi/," - "cycles" - "}" -}; - static struct evlist *evsel_list; static bool all_counters_use_bpf = true; @@ -246,14 +181,13 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b) static void evlist__check_cpu_maps(struct evlist *evlist) { - struct evsel *evsel, *pos, *leader; - char buf[1024]; + struct evsel *evsel, *warned_leader = NULL; if (evlist__has_hybrid(evlist)) evlist__warn_hybrid_group(evlist); evlist__for_each_entry(evlist, evsel) { - leader = evsel__leader(evsel); + struct evsel *leader = evsel__leader(evsel); /* Check that leader matches cpus with each member. */ if (leader == evsel) @@ -262,19 +196,26 @@ static void evlist__check_cpu_maps(struct evlist *evlist) continue; /* If there's mismatch disable the group and warn user. */ - WARN_ONCE(1, "WARNING: grouped events cpus do not match, disabling group:\n"); - evsel__group_desc(leader, buf, sizeof(buf)); - pr_warning(" %s\n", buf); - + if (warned_leader != leader) { + char buf[200]; + + pr_warning("WARNING: grouped events cpus do not match.\n" + "Events with CPUs not matching the leader will " + "be removed from the group.\n"); + evsel__group_desc(leader, buf, sizeof(buf)); + pr_warning(" %s\n", buf); + warned_leader = leader; + } if (verbose > 0) { + char buf[200]; + cpu_map__snprint(leader->core.cpus, buf, sizeof(buf)); pr_warning(" %s: %s\n", leader->name, buf); cpu_map__snprint(evsel->core.cpus, buf, sizeof(buf)); pr_warning(" %s: %s\n", evsel->name, buf); } - for_each_group_evsel(pos, leader) - evsel__remove_from_group(pos, leader); + evsel__remove_from_group(evsel, leader); } } @@ -489,7 +430,6 @@ static void process_counters(void) perf_stat_merge_counters(&stat_config, evsel_list); perf_stat_process_percore(&stat_config, evsel_list); - perf_stat_process_shadow_stats(&stat_config, evsel_list); } static void process_interval(void) @@ -499,7 +439,6 @@ static void process_interval(void) clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); - perf_stat__reset_shadow_per_stat(&rt_stat); evlist__reset_aggr_stats(evsel_list); if (read_counters(&rs) == 0) @@ -610,7 +549,7 @@ static void process_evlist(struct evlist *evlist, unsigned int interval) if (evlist__ctlfd_process(evlist, &cmd) > 0) { switch (cmd) { case EVLIST_CTL_CMD_ENABLE: - __fallthrough; + fallthrough; case EVLIST_CTL_CMD_DISABLE: if (interval) process_interval(); @@ -773,7 +712,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) counter->reset_group = false; if (bpf_counter__load(counter, &target)) return -1; - if (!evsel__is_bpf(counter)) + if (!(evsel__is_bperf(counter))) all_counters_use_bpf = false; } @@ -789,7 +728,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (counter->reset_group || counter->errored) continue; - if (evsel__is_bpf(counter)) + if (evsel__is_bperf(counter)) continue; try_again: if (create_perf_stat_counter(counter, &stat_config, &target, @@ -970,7 +909,6 @@ try_again_reset: evlist__copy_prev_raw_counts(evsel_list); evlist__reset_prev_raw_counts(evsel_list); evlist__reset_aggr_stats(evsel_list); - perf_stat__reset_shadow_per_stat(&rt_stat); } else { update_stats(&walltime_nsecs_stats, t1 - t0); update_rusage_stats(&ru_stats, &stat_config.ru_data); @@ -1251,6 +1189,8 @@ static struct option stat_options[] = { "don't group metric events, impacts multiplexing"), OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge, "don't try to share events between metrics in a group"), + OPT_BOOLEAN(0, "metric-no-threshold", &stat_config.metric_no_threshold, + "don't try to share events between metrics in a group "), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure top-down statistics"), OPT_UINTEGER(0, "td-level", &stat_config.topdown_level, @@ -1716,7 +1656,6 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) */ static int add_default_attributes(void) { - int err; struct perf_event_attr default_attrs0[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, @@ -1837,44 +1776,29 @@ static int add_default_attributes(void) return 0; if (transaction_run) { - struct parse_events_error errinfo; /* Handle -T as -M transaction. Once platform specific metrics * support has been added to the json files, all architectures * will use this approach. To determine transaction support * on an architecture test for such a metric name. */ - if (metricgroup__has_metric("transaction")) { - return metricgroup__parse_groups(evsel_list, "transaction", - stat_config.metric_no_group, - stat_config.metric_no_merge, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events); - } - - parse_events_error__init(&errinfo); - if (pmu_have_event("cpu", "cycles-ct") && - pmu_have_event("cpu", "el-start")) - err = parse_events(evsel_list, transaction_attrs, - &errinfo); - else - err = parse_events(evsel_list, - transaction_limited_attrs, - &errinfo); - if (err) { - fprintf(stderr, "Cannot set up transaction events\n"); - parse_events_error__print(&errinfo, transaction_attrs); + if (!metricgroup__has_metric("transaction")) { + pr_err("Missing transaction metrics"); + return -1; } - parse_events_error__exit(&errinfo); - return err ? -1 : 0; + return metricgroup__parse_groups(evsel_list, "transaction", + stat_config.metric_no_group, + stat_config.metric_no_merge, + stat_config.metric_no_threshold, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events); } if (smi_cost) { - struct parse_events_error errinfo; int smi; if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) { - fprintf(stderr, "freeze_on_smi is not supported.\n"); + pr_err("freeze_on_smi is not supported."); return -1; } @@ -1886,108 +1810,62 @@ static int add_default_attributes(void) smi_reset = true; } - if (!pmu_have_event("msr", "aperf") || - !pmu_have_event("msr", "smi")) { - fprintf(stderr, "To measure SMI cost, it needs " - "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + if (!metricgroup__has_metric("smi")) { + pr_err("Missing smi metrics"); return -1; } + if (!force_metric_only) stat_config.metric_only = true; - parse_events_error__init(&errinfo); - err = parse_events(evsel_list, smi_cost_attrs, &errinfo); - if (err) { - parse_events_error__print(&errinfo, smi_cost_attrs); - fprintf(stderr, "Cannot set up SMI cost events\n"); - } - parse_events_error__exit(&errinfo); - return err ? -1 : 0; + return metricgroup__parse_groups(evsel_list, "smi", + stat_config.metric_no_group, + stat_config.metric_no_merge, + stat_config.metric_no_threshold, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events); } if (topdown_run) { - const char **metric_attrs = topdown_metric_attrs; - unsigned int max_level = 1; - char *str = NULL; - bool warn = false; - const char *pmu_name = arch_get_topdown_pmu_name(evsel_list, true); + unsigned int max_level = metricgroups__topdown_max_level(); + char str[] = "TopdownL1"; if (!force_metric_only) stat_config.metric_only = true; - if (pmu_have_event(pmu_name, topdown_metric_L2_attrs[5])) { - metric_attrs = topdown_metric_L2_attrs; - max_level = 2; + if (!max_level) { + pr_err("Topdown requested but the topdown metric groups aren't present.\n" + "(See perf list the metric groups have names like TopdownL1)"); + return -1; } - if (stat_config.topdown_level > max_level) { pr_err("Invalid top-down metrics level. The max level is %u.\n", max_level); return -1; } else if (!stat_config.topdown_level) - stat_config.topdown_level = max_level; - - if (topdown_filter_events(metric_attrs, &str, 1, pmu_name) < 0) { - pr_err("Out of memory\n"); - return -1; - } - - if (metric_attrs[0] && str) { - if (!stat_config.interval && !stat_config.metric_only) { - fprintf(stat_config.output, - "Topdown accuracy may decrease when measuring long periods.\n" - "Please print the result regularly, e.g. -I1000\n"); - } - goto setup_metrics; - } + stat_config.topdown_level = 1; - zfree(&str); - - if (stat_config.aggr_mode != AGGR_GLOBAL && - stat_config.aggr_mode != AGGR_CORE) { - pr_err("top down event configuration requires --per-core mode\n"); - return -1; - } - stat_config.aggr_mode = AGGR_CORE; - if (nr_cgroups || !target__has_cpu(&target)) { - pr_err("top down event configuration requires system-wide mode (-a)\n"); - return -1; - } - - if (topdown_filter_events(topdown_attrs, &str, - arch_topdown_check_group(&warn), - pmu_name) < 0) { - pr_err("Out of memory\n"); - return -1; + if (!stat_config.interval && !stat_config.metric_only) { + fprintf(stat_config.output, + "Topdown accuracy may decrease when measuring long periods.\n" + "Please print the result regularly, e.g. -I1000\n"); } - - if (topdown_attrs[0] && str) { - struct parse_events_error errinfo; - if (warn) - arch_topdown_group_warn(); -setup_metrics: - parse_events_error__init(&errinfo); - err = parse_events(evsel_list, str, &errinfo); - if (err) { - fprintf(stderr, - "Cannot set up top down events %s: %d\n", - str, err); - parse_events_error__print(&errinfo, str); - parse_events_error__exit(&errinfo); - free(str); - return -1; - } - parse_events_error__exit(&errinfo); - } else { - fprintf(stderr, "System does not support topdown\n"); + str[8] = stat_config.topdown_level + '0'; + if (metricgroup__parse_groups(evsel_list, str, + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) return -1; - } - free(str); } if (!stat_config.topdown_level) - stat_config.topdown_level = TOPDOWN_MAX_LEVEL; + stat_config.topdown_level = 1; if (!evsel_list->core.nr_entries) { + /* No events so add defaults. */ if (target__has_cpu(&target)) default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK; @@ -2003,6 +1881,25 @@ setup_metrics: } if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0) return -1; + /* + * Add TopdownL1 metrics if they exist. To minimize + * multiplexing, don't request threshold computation. + */ + /* + * TODO: TopdownL1 is disabled on hybrid CPUs to avoid a crashes + * caused by exposing latent bugs. This is fixed properly in: + * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ + */ + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && + metricgroup__parse_groups(evsel_list, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) return -1; @@ -2239,8 +2136,6 @@ static int __cmd_report(int argc, const char **argv) input_name = "perf.data"; } - perf_stat__init_shadow_stats(); - perf_stat.data.path = input_name; perf_stat.data.mode = PERF_DATA_MODE_READ; @@ -2281,7 +2176,7 @@ static void setup_system_wide(int forks) evlist__for_each_entry(evsel_list, counter) { if (!counter->core.requires_cpu && - strcmp(counter->name, "duration_time")) { + !evsel__name_is(counter, "duration_time")) { return; } } @@ -2383,8 +2278,10 @@ int cmd_stat(int argc, const char **argv) perror("failed to create output file"); return -1; } - clock_gettime(CLOCK_REALTIME, &tm); - fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); + if (!stat_config.json_output) { + clock_gettime(CLOCK_REALTIME, &tm); + fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); + } } else if (output_fd > 0) { mode = append_file ? "a" : "w"; output = fdopen(output_fd, mode); @@ -2514,12 +2411,12 @@ int cmd_stat(int argc, const char **argv) metricgroup__parse_groups(evsel_list, metrics, stat_config.metric_no_group, stat_config.metric_no_merge, + stat_config.metric_no_threshold, stat_config.user_requested_cpu_list, stat_config.system_wide, &stat_config.metric_events); zfree(&metrics); } - perf_stat__init_shadow_stats(); if (add_default_attributes()) goto out; |